Merge branch 'main' into micn/fix-anthropic-1p

* main:
  control commands for machine mode
  Fix duplicate dump at end
  minor
  --machine mode flag for verbose CLI output
  fixed x,y detection in vision click
  screenshotting bug fix
  test
  Native api for screen capture
  replace tesseract with apple vision
  more macax tooling
  coach rigor +++
  thinning message highlighted
  warnings fix
  macax tools
  control commands
  Add --interactive-requirements flag for AI-enhanced requirements mode

.cargo/config.toml

@@ -1,5 +0,0 @@
-[target.aarch64-apple-darwin]
-rustflags = ["-C", "link-args=-Wl,-rpath,@executable_path"]
-
-[target.x86_64-apple-darwin]
-rustflags = ["-C", "link-args=-Wl,-rpath,@executable_path"]

.gitignore

@@ -23,13 +23,6 @@ target
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
 
-# G3 session data directory
-.g3/
-
-# g3 artifacts
-requirements.md
-todo.g3.md
-tmp/
-
-# Studio worktrees
-.worktrees/
+# Session logs directory
+logs/
+*.json

AGENTS.md

@@ -1,87 +0,0 @@
-# AGENTS.md - Machine Instructions for g3
-
-**Purpose**: Machine-specific instructions for AI agents working with this codebase.  
-**For code locations**: See Workspace Memory (loaded automatically)  
-**For project overview**: See [README.md](README.md)
-
-## Critical Invariants
-
-### MUST Hold
-
-1. **Tool calls must be valid JSON** - The streaming parser expects well-formed tool calls
-2. **Context window limits must be respected** - Exceeding limits causes API errors
-3. **Provider trait implementations must be Send + Sync** - Required for async runtime
-4. **Session IDs must be unique** - Used for log file paths and TODO scoping
-5. **File paths in tools support tilde expansion** - `~` expands to home directory
-6. **Streaming is preferred** - Non-streaming requests block UI
-7. **Tool results are size-limited** - Large outputs are truncated or thinned automatically
-8. **String slicing must be UTF-8 safe** - Use `chars().take(n)` or `char_indices()`, never byte slicing like `&s[..n]` on user-facing strings
-
-### MUST NOT Do
-
-1. **Never block the async runtime** - Use `tokio::spawn` for CPU-intensive work
-2. **Never store secrets in logs** - API keys are redacted in error logs
-3. **Never modify files outside working directory without explicit permission**
-4. **Never assume tool results fit in context** - Large results are thinned automatically
-5. **Never use byte-index string slicing on text with potential multi-byte characters** - Causes panics on emoji, CJK, box-drawing chars
-
-## Adding Features
-
-- **New tool**: Add definition in `tool_definitions.rs`, implement in `tools/`, add dispatch case
-- **New provider**: Implement `LLMProvider` trait in `g3-providers`
-- **New CLI mode**: Add to CLI args, implement handler in `g3-cli`
-- **New skill**: Create `skills/<name>/SKILL.md`, optionally add to `embedded.rs` for binary inclusion
-- **New config option**: Add to `g3-config` structs
-
-## Dangerous Code Paths
-
-These areas have subtle bugs if modified incorrectly:
-
-| Area | Risk |
-|------|------|
-| **Context window management** | Incorrect token estimates cause context overflow |
-| **Streaming parser** | Partial JSON across chunks causes parsing failures |
-| **Tool dispatch** | Missing dispatch cases cause silent failures |
-| **Retry logic** | Aggressive retries hit rate limits harder |
-| **Parser sanitization** | Inline JSON can trigger false tool call detection |
-| **Skill extraction** | Version hash mismatch causes stale scripts; path issues on Windows |
-
-## Do's and Don'ts
-
-### Do
-- ✅ Run `cargo check` after modifications
-- ✅ Run `cargo test` before committing
-- ✅ Update tool definitions when adding tools
-- ✅ Add tests for new functionality
-- ✅ Keep functions under 80 lines
-
-### Don't
-- ❌ Add blocking code in async contexts
-- ❌ Store sensitive data in plain text
-- ❌ Ignore error handling
-- ❌ Create deeply nested conditionals (>6 levels)
-- ❌ Add external dependencies for simple tasks
-
-## Common Incorrect Assumptions
-
-1. **"All providers support tool calling"** - Embedded models use JSON fallback
-2. **"Context window is unlimited"** - Each provider has limits (4k-200k tokens)
-3. **"Tool results are always small"** - File reads can return megabytes
-4. **"Sessions persist across runs"** - Sessions are ephemeral by default
-5. **"All platforms are equal"** - macOS has more features (Vision, Accessibility)
-
-## Dependency Analysis Artifacts
-
-The `analysis/deps/` directory contains static analysis artifacts generated by the euler agent:
-
-| File | Purpose |
-|------|--------|
-| `graph.json` | Canonical dependency graph with nodes (crates, files) and edges (imports) |
-| `graph.summary.md` | One-page overview with metrics, entrypoints, and top fan-in/fan-out nodes |
-| `sccs.md` | Strongly connected components (dependency cycles) analysis |
-| `layers.observed.md` | Observed layering structure derived from dependency direction |
-| `hotspots.md` | Files with disproportionate coupling (high fan-in or fan-out) |
-| `limitations.md` | What could not be observed and what may invalidate conclusions |
-
-These artifacts are useful for understanding coupling, planning refactors, and identifying architectural boundaries.
-

Cargo.toml

@@ -2,12 +2,10 @@
 members = [
     "crates/g3-cli",
     "crates/g3-core", 
-    "crates/g3-planner",
     "crates/g3-providers",
     "crates/g3-config",
     "crates/g3-execution",
-    "crates/g3-computer-control",
-    "crates/studio"
+    "crates/g3-computer-control"
 ]
 resolver = "2"
 
@@ -23,11 +21,12 @@ serde_json = "1.0"
 clap = { version = "4.0", features = ["derive"] }
 # Error handling
 anyhow = "1.0"
+thiserror = "1.0"
 # Logging
 tracing = "0.1"
 tracing-subscriber = "0.3"
 # Configuration
-config = "0.15"
+config = "0.14"
 # Utilities
 uuid = { version = "1.0", features = ["v4"] }
 
@@ -35,7 +34,7 @@ uuid = { version = "1.0", features = ["v4"] }
 name = "g3"
 version = "0.1.0"
 edition = "2021"
-authors = ["g3 Team"]
+authors = ["G3 Team"]
 description = "A general purpose AI agent that helps you complete tasks by writing code"
 license = "MIT"
 
@@ -43,9 +42,3 @@ license = "MIT"
 g3-cli = { path = "crates/g3-cli" }
 tokio = { workspace = true }
 anyhow = { workspace = true }
-g3-providers = { path = "crates/g3-providers" }
-serde_json = { workspace = true }
-
-[[example]]
-name = "verify_message_id"
-path = "examples/verify_message_id.rs"

DESIGN.md

@@ -1,10 +1,10 @@
-# g3 - AI Coding Agent - Design Document
+# G3 - AI Coding Agent - Design Document
 
 ## Overview
 
-g3 is a **modular, composable AI coding agent** built in Rust that helps you complete tasks by writing and executing code. It provides a flexible architecture for interacting with various Large Language Model (LLM) providers while offering powerful code generation, file manipulation, and task automation capabilities.
+G3 is a **modular, composable AI coding agent** built in Rust that helps you complete tasks by writing and executing code. It provides a flexible architecture for interacting with various Large Language Model (LLM) providers while offering powerful code generation, file manipulation, and task automation capabilities.
 
-The agent follows a **tool-first philosophy**: instead of just providing advice, g3 actively uses tools to read files, write code, execute commands, and complete tasks autonomously.
+The agent follows a **tool-first philosophy**: instead of just providing advice, G3 actively uses tools to read files, write code, execute commands, and complete tasks autonomously.
 
 ## Core Principles
 
@@ -14,12 +14,12 @@ The agent follows a **tool-first philosophy**: instead of just providing advice,
 4. **Modularity**: Clear separation of concerns
 5. **Composability**: Components can be combined in different ways
 6. **Performance**: Built in Rust for speed and reliability
-7. **Context Intelligence**: Smart context window management with auto-compaction
+7. **Context Intelligence**: Smart context window management with auto-summarization
 8. **Error Resilience**: Robust error handling with automatic retry logic
 
 ## Project Structure
 
-g3 is organized as a Rust workspace with the following crates:
+G3 is organized as a Rust workspace with the following crates:
 
 ```
 g3/
@@ -87,7 +87,7 @@ g3/
 - Error handling with automatic retry logic
 
 **Key Features:**
-- **Context Window Intelligence**: Automatic monitoring with percentage-based tracking (80% capacity triggers auto-compaction)
+- **Context Window Intelligence**: Automatic monitoring with percentage-based tracking (80% capacity triggers auto-summarization)
 - **Tool System**: Built-in tools for file operations (read, write, edit), shell commands, and structured output
 - **Streaming Parser**: Real-time parsing of LLM responses with tool call detection and execution
 - **Session Management**: Automatic session logging with detailed conversation history and token usage
@@ -106,6 +106,7 @@ g3/
 - `type_text`: Type text at the current cursor position
 - `find_element`: Find UI elements by text, role, or attributes
 - `take_screenshot`: Capture screenshots of screen, region, or window
+- `extract_text`: Extract text from images or screen regions using OCR
 - `find_text_on_screen`: Find text visually on screen and return coordinates
 - `list_windows`: List all open windows with IDs and titles
 
@@ -217,7 +218,7 @@ g3/
 
 ### Context Window Management
 
-g3 implements sophisticated context window management:
+G3 implements sophisticated context window management:
 
 - **Automatic Monitoring**: Tracks token usage with percentage-based thresholds
 - **Smart Summarization**: Auto-triggers at 80% capacity to prevent context overflow
@@ -389,7 +390,7 @@ g3 --retro --theme dracula
 - **Caching**: Strategic caching of expensive operations
 - **Profiling**: Regular performance profiling and optimization
 
-This design document reflects the current state of g3 as a mature, production-ready AI coding agent with sophisticated architecture and comprehensive feature set.
+This design document reflects the current state of G3 as a mature, production-ready AI coding agent with sophisticated architecture and comprehensive feature set.
 
 ## Current Implementation Status
 
@@ -402,7 +403,7 @@ This design document reflects the current state of g3 as a mature, production-re
 - ✅ **Configuration**: TOML-based config with environment overrides
 - ✅ **Error Handling**: Comprehensive retry logic and error classification
 - ✅ **Session Logging**: Automatic session tracking and JSON logs
-- ✅ **Context Management**: Context thinning (50-80%) and auto-compaction at 80% capacity
+- ✅ **Context Management**: Context thinning (50-80%) and auto-summarization at 80% capacity
 - ✅ **Computer Control**: Cross-platform automation with OCR support
 - ✅ **TODO Management**: In-memory TODO list with read/write tools
 

README.md

@@ -1,17 +1,17 @@
-# g3 - AI Coding Agent
+# G3 - AI Coding Agent
 
-g3 is a coding AI agent designed to help you complete tasks by writing code and executing commands. Built in Rust, it provides a flexible architecture for interacting with various Large Language Model (LLM) providers while offering powerful code generation and task automation capabilities.
+G3 is a coding AI agent designed to help you complete tasks by writing code and executing commands. Built in Rust, it provides a flexible architecture for interacting with various Large Language Model (LLM) providers while offering powerful code generation and task automation capabilities.
 
 ## Architecture Overview
 
-g3 follows a modular architecture organized as a Rust workspace with multiple crates, each responsible for specific functionality:
+G3 follows a modular architecture organized as a Rust workspace with multiple crates, each responsible for specific functionality:
 
 ### Core Components
 
 #### **g3-core**
 The heart of the agent system, containing:
 - **Agent Engine**: Main orchestration logic for handling conversations, tool execution, and task management
-- **Context Window Management**: Intelligent tracking of token usage with context thinning (50-80%) and auto-compaction at 80% capacity
+- **Context Window Management**: Intelligent tracking of token usage with context thinning (50-80%) and auto-summarization at 80% capacity
 - **Tool System**: Built-in tools for file operations, shell commands, computer control, TODO management, and structured output
 - **Streaming Response Parser**: Real-time parsing of LLM responses with tool call detection and execution
 - **Task Execution**: Support for single and iterative task execution with automatic retry logic
@@ -56,40 +56,26 @@ Command-line interface:
 
 ### Error Handling & Resilience
 
-g3 includes robust error handling with automatic retry logic:
+G3 includes robust error handling with automatic retry logic:
 - **Recoverable Error Detection**: Automatically identifies recoverable errors (rate limits, network issues, server errors, timeouts)
 - **Exponential Backoff with Jitter**: Implements intelligent retry delays to avoid overwhelming services
 - **Detailed Error Logging**: Captures comprehensive error context including stack traces, request/response data, and session information
-- **Error Persistence**: Saves detailed error logs to `.g3/errors/` for post-mortem analysis
+- **Error Persistence**: Saves detailed error logs to `logs/errors/` for post-mortem analysis
 - **Graceful Degradation**: Non-recoverable errors are logged with full context before terminating
 
-### Tool Call Duplicate Detection
-
-g3 includes intelligent duplicate detection to prevent the LLM from accidentally calling the same tool twice in a row:
-- **Sequential Duplicate Prevention**: Only immediately sequential identical tool calls are blocked
-- **Text Separation Allowed**: If there's any text between tool calls, they're not considered duplicates
-- **Session-Wide Reuse**: Tools can be called multiple times throughout a session - only back-to-back duplicates are prevented
-
-This catches cases where the LLM "stutters" and outputs the same tool call twice, while still allowing legitimate re-use of tools.
-
-### Timing Footer
-
-After each response, g3 displays a timing footer showing elapsed time, time to first token, token usage (from the LLM, not estimated), and current context window usage percentage. The token and context info is displayed dimmed for a clean interface.
-
 ## Key Features
 
 ### Intelligent Context Management
 - Automatic context window monitoring with percentage-based tracking
-- Smart auto-compaction when approaching token limits
+- Smart auto-summarization when approaching token limits
 - **Context thinning** at 50%, 60%, 70%, 80% thresholds - automatically replaces large tool results with file references
 - Conversation history preservation through summaries
 - Dynamic token allocation for different providers (4k to 200k+ tokens)
 
 ### Interactive Control Commands
-g3's interactive CLI includes control commands for manual context management:
-- **`/compact`**: Manually trigger compaction to compact conversation history
+G3's interactive CLI includes control commands for manual context management:
+- **`/compact`**: Manually trigger summarization to compact conversation history
 - **`/thinnify`**: Manually trigger context thinning to replace large tool results with file references
-- **`/skinnify`**: Manually trigger full context thinning (like `/thinnify` but processes the entire context window, not just the first third)
 - **`/readme`**: Reload README.md and AGENTS.md from disk without restarting
 - **`/stats`**: Show detailed context and performance statistics
 - **`/help`**: Display all available control commands
@@ -103,102 +89,19 @@ These commands give you fine-grained control over context management, allowing y
 - **TODO Management**: Read and write TODO lists with markdown checkbox format
 - **Computer Control** (Experimental): Automate desktop applications
   - Mouse and keyboard control
+  - macOS Accessibility API for native app automation (via `--macax` flag)
   - UI element inspection
   - Screenshot capture and window management
+  - OCR text extraction from images and screen regions
   - Window listing and identification
-- **Code Search**: Embedded tree-sitter for syntax-aware code search (Rust, Python, JavaScript, TypeScript, Go, Java, C, C++) - see [Code Search Guide](docs/CODE_SEARCH.md)
 - **Final Output**: Formatted result presentation
 
-### Agent Skills
-
-g3 supports the [Agent Skills](https://agentskills.io) specification - an open format for portable skill packages that give the agent new capabilities.
-
-**Skill Locations** (in priority order, later overrides earlier):
-1. Embedded skills (compiled into binary)
-2. Global: `~/.g3/skills/`
-3. Extra paths from config
-4. Workspace: `.g3/skills/`
-5. Repo: `skills/` (highest priority, checked into git)
-
-**SKILL.md Format**:
-```yaml
----
-name: pdf-processing          # Required: 1-64 chars, lowercase + hyphens
-description: Extract text...  # Required: 1-1024 chars, when to use
-license: Apache-2.0           # Optional
-compatibility: Requires git   # Optional: environment requirements
----
-
-# PDF Processing
-
-Detailed instructions for the agent...
-```
-
-**Configuration** (in `g3.toml`):
-```toml
-[skills]
-enabled = true                    # Default: true
-extra_paths = ["/path/to/skills"] # Additional skill directories
-```
-
-At startup, g3 scans skill directories and injects a summary into the system prompt. When the agent needs a skill, it reads the full `SKILL.md` using the `read_file` tool.
-
-Each skill adds ~50-100 tokens to context (name + description + path). Skills can include:
-- `scripts/` - Executable code (Python, Bash, etc.)
-- `references/` - Additional documentation
-- `assets/` - Templates, data files
-
-**Embedded Skills**: Core skills like `research` are compiled into the binary, ensuring they work anywhere without external files. Embedded scripts are automatically extracted to `.g3/bin/` on first use.
-
-**Built-in Research Skill**: Perform asynchronous web research via `background_process("research", ".g3/bin/g3-research 'your query'")`. Results are saved to `.g3/research/<id>/report.md`.
-
-See [Skills Guide](docs/skills.md) for detailed documentation.
-
 ### Provider Flexibility
 - Support for multiple LLM providers through a unified interface
 - Hot-swappable providers without code changes
 - Provider-specific optimizations and feature support
 - Local model support for offline operation
 
-### Embedded Models (Local LLMs)
-
-g3 supports local models via llama.cpp with Metal acceleration on macOS. Here's a performance comparison for **agentic tasks** (multi-step tool-calling workflows):
-
-**Test case**: Comic book repacking - extract CBR/CBZ archives, reorder files preserving page and issue order, repack into single archive. Requires correct sequencing, file handling, and no race conditions.
-
-#### Cloud Models (Baseline)
-| Model | Agentic Score | Notes |
-|-------|---------------|-------|
-| **Claude Opus 4.5** | ⭐⭐⭐⭐⭐ | Flawless execution |
-| **Gemini 3 Pro** | ⭐⭐⭐⭐⭐ | Flawless, fast execution |
-| Claude Sonnet 4.5 | ⭐⭐⭐⭐ | Good, occasional issues |
-| Claude 4 family | ⭐⭐⭐ | Gets there eventually, needs manual checking |
-
-#### Local Models
-| Model | Size | Speed | Agentic Score | Notes |
-|-------|------|-------|---------------|-------|
-| ~~Qwen3-32B~~ (Dense) | 18 GB | Slow | ❌ | Good reasoning, but flails on execution and crashes |
-| Qwen3-14B | 8.4 GB | Medium | ⭐⭐ | Understands tasks but makes implementation errors |
-| GLM-4 9B | 5.7 GB | Fast | ⭐⭐ | Works with adapter (strips code fences) |
-| Qwen3-4B | 2.3 GB | Very Fast | ❌ | Generates malformed tool calls - not for agentic use |
-| ~~Qwen3-30B-A3B~~ (MoE) | 17 GB | Very Fast | ❌ | **Avoid** - loops infinitely on tool calls |
-
-**Key findings**:
-- **Dense models** (Qwen3-32B, Qwen3-14B) handle agentic loops correctly
-- **MoE models** (Qwen3-30B-A3B) are fast but don't know when to stop tool-calling
-- **Metal GPU** works well with dense models on Apple Silicon
-- Even the best local models (32B) lag significantly behind Claude Opus 4.5 on complex tasks
-- Local models are best for simpler agentic tasks or when offline/privacy is required
-
-Configuration example:
-```toml
-[providers.embedded.qwen3-big]
-model_path = "~/.g3/models/Qwen_Qwen3-32B-Q4_K_M.gguf"
-model_type = "qwen"
-context_length = 40960
-gpu_layers = 99  # Full GPU offload on Apple Silicon
-```
-
 ### Task Automation
 - Single-shot task execution for quick operations
 - Iterative task mode for complex, multi-step workflows
@@ -212,12 +115,12 @@ gpu_layers = 99  # Full GPU offload on Apple Silicon
 - **HTTP Client**: Reqwest for API communications
 - **Serialization**: Serde for JSON handling
 - **CLI Framework**: Clap for command-line parsing
-- **Logging**: Tracing for structured logging (INFO logs converted to DEBUG for cleaner CLI output)
+- **Logging**: Tracing for structured logging
 - **Local Models**: llama.cpp with Metal acceleration support
 
 ## Use Cases
 
-g3 is designed for:
+G3 is designed for:
 - Automated code generation and refactoring
 - File manipulation and project scaffolding
 - System administration tasks
@@ -225,125 +128,28 @@ g3 is designed for:
 - API integration and testing
 - Documentation generation
 - Complex multi-step workflows
-- Parallel development of modular architectures
 - Desktop application automation and testing
 
 ## Getting Started
 
-### Default Mode: Accumulative Autonomous
-
-The default interactive mode now uses **accumulative autonomous mode**, which combines the best of interactive and autonomous workflows:
-
-```bash
-# Simply run g3 in any directory
-g3
-
-# You'll be prompted to describe what you want to build
-# Each input you provide:
-# 1. Gets added to accumulated requirements
-# 2. Automatically triggers autonomous mode (coach-player loop)
-# 3. Implements your requirements iteratively
-
-# Example session:
-requirement> create a simple web server in Python with Flask
-# ... autonomous mode runs and implements it ...
-requirement> add a /health endpoint that returns JSON
-# ... autonomous mode runs again with both requirements ...
-```
-
-### Other Modes
-
-```bash
-# Single-shot mode (one task, then exit)
-g3 "implement a function to calculate fibonacci numbers"
-
-# Traditional autonomous mode (reads requirements.md)
-g3 --autonomous
-
-# Traditional chat mode (simple interactive chat without autonomous runs)
-g3 --chat
-```
-
-### Planning Mode
-
-Planning mode provides a structured workflow for requirements-driven development with git integration:
-
-```bash
-# Start planning mode for a codebase
-g3 --planning --codepath ~/my-project --workspace ~/g3_workspace
-
-# Without git operations (for repos not yet initialized)
-g3 --planning --codepath ~/my-project --no-git --workspace ~/g3_workspace
-```
-
-Planning mode workflow:
-1. **Refine Requirements**: Write requirements in `<codepath>/g3-plan/new_requirements.md`, then let the LLM suggest improvements
-2. **Implement**: Once requirements are approved, they're renamed to `current_requirements.md` and the coach/player loop implements them
-3. **Complete**: After implementation, files are archived with timestamps (e.g., `completed_requirements_2025-01-15_10-30-00.md`)
-4. **Git Commit**: Staged files are committed with an LLM-generated commit message
-5. **Repeat**: Return to step 1 for the next iteration
-
-All planning artifacts are stored in `<codepath>/g3-plan/`:
-- `planner_history.txt` - Audit log of all planning activities
-- `new_requirements.md` / `current_requirements.md` - Active requirements
-- `todo.g3.md` - Implementation TODO list
-- `completed_*.md` - Archived requirements and todos
-
-See the configuration section for setting up different providers for the planner role.
-
 ```bash
 # Build the project
 cargo build --release
 
-# Run from the build directory
-./target/release/g3
-
-# Or copy both files to somewhere in your PATH (macOS only needs both files)
-cp target/release/g3 ~/.local/bin/
-cp target/release/libVisionBridge.dylib ~/.local/bin/  # macOS only
+# Run G3
+cargo run
 
 # Execute a task
 g3 "implement a function to calculate fibonacci numbers"
 ```
 
-## Configuration
-
-G3 uses a TOML configuration file for settings. The config file is automatically created at `~/.config/g3/config.toml` on first run with sensible defaults.
-
-### Retry Configuration
-
-g3 includes configurable retry logic for handling recoverable errors (timeouts, rate limits, network issues, server errors):
-
-```toml
-[agent]
-max_context_length = 8192
-enable_streaming = true
-timeout_seconds = 60
-
-# Retry configuration for recoverable errors
-max_retry_attempts = 3              # Default mode retry attempts
-autonomous_max_retry_attempts = 6   # Autonomous mode retry attempts
-```
-
-**Retry Behavior:**
-- **Default Mode** (`max_retry_attempts`): Used for interactive chat and single-shot tasks. Default: 3 attempts.
-- **Autonomous Mode** (`autonomous_max_retry_attempts`): Used for long-running autonomous tasks. Default: 6 attempts.
-- Retries use exponential backoff with jitter to avoid overwhelming services
-- Autonomous mode spreads retries over ~10 minutes to handle extended outages
-- Only recoverable errors are retried (timeouts, rate limits, 5xx errors, network issues)
-- Non-recoverable errors (auth failures, invalid requests) fail immediately
-
-**Example:** To increase timeout resilience in autonomous mode, set `autonomous_max_retry_attempts = 10` in your config.
-
-See `config.example.toml` for a complete configuration example.
-
 ## WebDriver Browser Automation
 
-g3 includes WebDriver support for browser automation tasks. Chrome headless is the default, with Safari available as an alternative.
+G3 includes WebDriver support for browser automation tasks using Safari.
 
 **One-Time Setup** (macOS only):
 
-If you want to use Safari instead of Chrome headless, Safari Remote Automation must be enabled. Run this once:
+Safari Remote Automation must be enabled before using WebDriver tools. Run this once:
 
 ```bash
 # Option 1: Use the provided script
@@ -357,40 +163,28 @@ safaridriver --enable  # Requires password
 # Then: Develop → Allow Remote Automation
 ```
 
-**Usage**:
+**For detailed setup instructions and troubleshooting**, see [WebDriver Setup Guide](docs/webdriver-setup.md).
 
-```bash
-# Use Safari (opens a visible browser window)
-g3 --safari
+**Usage**: Run G3 with the `--webdriver` flag to enable browser automation tools.
 
-# Use Chrome in headless mode (default, no visible window, runs in background)
-g3
-```
+## macOS Accessibility API Tools
 
-**Chrome Setup Options**:
+G3 includes support for controlling macOS applications via the Accessibility API, allowing you to automate native macOS apps.
 
-*Option 1: Use Chrome for Testing (Recommended)* - Guarantees version compatibility:
-```bash
-./scripts/setup-chrome-for-testing.sh
-```
-Then add to your `~/.config/g3/config.toml`:
-```toml
-[webdriver]
-chrome_binary = "/Users/yourname/.chrome-for-testing/chrome-mac-arm64/Google Chrome for Testing.app/Contents/MacOS/Google Chrome for Testing"
-```
+**Available Tools**: `macax_list_apps`, `macax_get_frontmost_app`, `macax_activate_app`, `macax_get_ui_tree`, `macax_find_elements`, `macax_click`, `macax_set_value`, `macax_get_value`, `macax_press_key`
 
-*Option 2: Use system Chrome* - Requires matching ChromeDriver version:
-- macOS: `brew install chromedriver`
-- Linux: `apt install chromium-chromedriver`
-- Or download from: https://chromedriver.chromium.org/downloads
+**Setup**: Enable with the `--macax` flag or in config with `macax.enabled = true`. Grant accessibility permissions:
+- **macOS**: System Preferences → Security & Privacy → Privacy → Accessibility → Add your terminal app
 
-**Note**: If you see "ChromeDriver version doesn't match Chrome version" errors, use Option 1 (Chrome for Testing) which bundles matching versions.
+**For detailed documentation**, see [macOS Accessibility Tools Guide](docs/macax-tools.md).
+
+**Note**: This is particularly useful for testing and automating apps you're building with G3, as you can add accessibility identifiers to your UI elements.
 
 ## Computer Control (Experimental)
 
-g3 can interact with your computer's GUI for automation tasks:
+G3 can interact with your computer's GUI for automation tasks:
 
-**Available Tools**: `mouse_click`, `type_text`, `find_element`, `take_screenshot`, `list_windows`
+**Available Tools**: `mouse_click`, `type_text`, `find_element`, `take_screenshot`, `extract_text`, `find_text_on_screen`, `list_windows`
 
 **Setup**: Enable in config with `computer_control.enabled = true` and grant OS accessibility permissions:
 - **macOS**: System Preferences → Security & Privacy → Accessibility  
@@ -399,108 +193,17 @@ g3 can interact with your computer's GUI for automation tasks:
 
 ## Session Logs
 
-G3 automatically saves session logs for each interaction in the `.g3/sessions/` directory. These logs contain:
+G3 automatically saves session logs for each interaction in the `logs/` directory. These logs contain:
 - Complete conversation history
 - Token usage statistics
 - Timestamps and session status
 
-The `.g3/` directory is created automatically on first use and is excluded from version control.
-
-## Agent Mode
-
-Agent mode runs specialized AI agents with custom prompts tailored for specific tasks. Each agent has a distinct personality and focus area.
-
-### Built-in Agents
-
-g3 comes with several embedded agents that work out of the box:
-
-| Agent | Focus |
-|-------|-------|
-| **carmack** | Code readability and craft - simplifies, refactors, improves naming |
-| **hopper** | Testing and quality - writes tests, finds edge cases |
-| **euler** | Architecture and dependencies - analyzes structure, finds coupling |
-| **huffman** | Memory maintenance - compacts, deduplicates, increases signal |
-| **lamport** | Concurrency and correctness - reviews async code, finds race conditions |
-| **fowler** | Refactoring patterns - applies design patterns, reduces duplication |
-| **breaker** | Adversarial testing - finds bugs, creates minimal repros |
-| **scout** | Research - investigates APIs, libraries, approaches |
-
-### Usage
-
-```bash
-# List all available agents
-g3 --list-agents
-
-# Run an agent on the current project
-g3 --agent carmack
-
-# Run an agent with a specific task
-g3 --agent hopper "add tests for the parser module"
-```
-
-### Custom Agents
-
-Create custom agents by adding markdown files to `agents/<name>.md` in your workspace. Workspace agents override embedded agents with the same name, allowing per-project customization.
-
-## Studio - Multi-Agent Workspace Manager
-
-Studio is a companion tool for managing multiple g3 agent sessions using git worktrees. Each session runs in an isolated worktree with its own branch, allowing multiple agents to work on the same codebase without conflicts.
-
-### Usage
-
-```bash
-# Build studio alongside g3
-cargo build --release
-
-# Run an agent session (creates worktree, runs g3, tails output)
-studio run --agent carmack "fix the memory leak in cache.rs"
-
-# Run a one-shot session without a specific agent
-studio run "add unit tests for the parser module"
-
-# List all sessions
-studio list
-
-# Check session status (shows summary when complete)
-studio status <session-id>
-
-# Accept a session: merge changes to main and cleanup
-studio accept <session-id>
-
-# Discard a session: delete without merging
-studio discard <session-id>
-```
-
-### How It Works
-
-1. **Isolation**: Each session creates a git worktree at `.worktrees/sessions/<agent>/<session-id>/`
-2. **Branching**: Sessions run on branches named `sessions/<agent>/<session-id>`
-3. **Tracking**: Session metadata is stored in `.worktrees/.sessions/`
-4. **Workflow**: Run → Review → Accept (merge) or Discard (delete)
-
-Studio is the recommended way to run multiple agents in parallel on the same codebase, replacing the deprecated flock mode.
-
-## Documentation Map
-
-Detailed documentation is available in the `docs/` directory:
-
-| Document | Description |
-|----------|-------------|
-| [Architecture](docs/architecture.md) | System design, crate responsibilities, data flow |
-| [Configuration](docs/configuration.md) | Config file format, provider setup, all options |
-| [Tools Reference](docs/tools.md) | Complete reference for all available tools |
-| [Providers Guide](docs/providers.md) | LLM provider setup and selection guide |
-| [Control Commands](docs/CONTROL_COMMANDS.md) | Interactive `/` commands for context management |
-| [Skills Guide](docs/skills.md) | Agent Skills system, SKILL.md format, creating skills |
-| [Code Search](docs/CODE_SEARCH.md) | Tree-sitter code search query patterns |
-
-For AI agents working with this codebase, see [AGENTS.md](AGENTS.md).
-
-Additional resources:
-- `DESIGN.md` - Original design document and rationale
-- `config.example.toml` - Complete configuration example
-- `config.coach-player.example.toml` - Multi-role configuration example
+The `logs/` directory is created automatically on first use and is excluded from version control.
 
 ## License
 
-MIT License
+MIT License - see LICENSE file for details
+
+## Contributing
+
+G3 is an open-source project. Contributions are welcome! Please see CONTRIBUTING.md for guidelines.

TODO

@@ -0,0 +1,19 @@
+next tasks
+
+x get something working with autonomous mode
+- g3d
+- bug where it prints everything in a conversation turn all over again before final_output
+x ui abstraction from core
+- context token counting bug
+- embedded model
+  - prompt rewriting
+  - generates status messages "ruffling feathers..."
+  - project description?
+- treesitter + friends
+x error where it just gives up turn
+- "project" behaviors (read readme first)
+- advance project mgmt
+  - git for reverting
+  - swarm
+  - ui tests / computer controller
+

agents/breaker.md

@@ -1,79 +0,0 @@
-You are **Breaker**.
-
-Your role is to **find real failures**: bugs, brittleness, edge cases, and unsafe assumptions.
-You are adversarial and methodical. You try to make the system fail fast, then explain why.
-
-You are **whitebox-aware** (you may read internals to choose targets), your findings must be grounded in **observable behavior** and **minimal repros**.
-
----
-
-## Prime Directive
-**DO NOT CHANGE PRODUCTION CODE.**
-
-- You must not modify application/runtime code, architecture, assets, or documentation.
-- You may add **minimal isolated repro fixtures** (e.g., tiny inputs) only if necessary to make a failure deterministic.
-
----
-
-## What You Produce
-Your output is a **bounded breakage/QA report** with high-signal items only.
-
-For each issue you report, include:
-
-### 1) Title
-Short, specific failure statement.
-
-### 2) Repro
-- exact command / steps
-- minimal input(s) or state needed
-- expected vs actual
-
-### 3) Diagnosis
-- suspected root cause with file:line pointers
-- triggering conditions
-- deterministic vs flaky
-
-### 4) Impact
-- severity (crash / data loss / incorrect behavior / annoying)
-- likelihood (rare / common)
-
-### 5) Next probe (optional)
-If not fully proven, state the single most informative next experiment.
-
-IMPORTANT: Write your report to: `analysis/breaker/YYYY-MM-DD.md` (today's date)
-
----
-
-## Exploration Rules
-- Start broad, then shrink: find a failure, then minimize it.
-- Prefer **minimal repros** over exhaustive enumeration.
-- Prefer **integration-style failures** (end-to-end behavior) over unit-internal assertions.
-- In addition to repo exploration, use git diffs to guide exploration.
-- If you cannot reproduce, say so plainly and list what’s missing.
-
----
-
-## Explicit Bans (Noise Control)
-You must not:
-- generate large test suites
-- chase coverage
-- list speculative “what if” edge cases without evidence
-- propose refactors or redesigns
-
-No hype. No “next steps” backlog.
-
----
-
-## Output Size Discipline
-- Report **0–5 issues max**.
-- If you find more, keep only the most severe or most likely.
-- If nothing meaningful is found, write: `No actionable failures found.`
-
----
-
-## Success Criteria
-You succeed when:
-- failures are real and reproducible
-- repros are minimal and deterministic when possible
-- diagnoses are crisp and grounded
-- output is concise and high-signal

agents/carmack.md

@@ -1,232 +0,0 @@
-SYSTEM PROMPT — “Carmack” (In-Code Readability & Craft Agent)
-
-You are Carmack: a code-aware readability agent, inspired by John Carmack.
-You work **inside source code files only — ever.**
-
-Your job is to simplify, make code easy to understand, and a joy to read.
-
-------------------------------------------------------------
-PRIME DIRECTIVE
-
-- Produce readability through:
-  - elegant local design
-  - simpler functions  
-  - straightforward control flow  
-  - clear, semantically consistent naming
-  - concise explanation **in place**
-
-- Non-negotiable nudge:  
-  **Readable code > commented code.**
-
-Stay inside the source. Do NOT touch docs, READMEs, etc.
-
-------------------------------------------------------------
-ALLOWED ACTIVITIES
-
-LOCAL REFACTORS (behavior-preserving, BUT aggressively readability improving):
-
-- Rename private functions/variables for legibility  
-- Pull out constants, interfaces, structs for readability
-- Simplify nested control flow and conditionals
-- Return well-defined structs over tuples/vectors
-- Extract overly long functions and files into smaller helpers/components
-  - If files are larger than 1000 lines, refactor them into smaller pieces
-  - If functions are longer than 250 lines refactor them
-
-ADD EXPLANATIONS (when needed):
-
-- Describe non-obvious algorithms in a short header comment sketch
-- Explain macros, protocols, serializers, hotspot systems, briefly
-- State invariants and assumptions the code already implies
-- Comment to elucidate any complex regions **within** functions
-- If comments distract from reading the code, you've gone too far
-
-------------------------------------------------------------
-EXPLICIT BANS
-
-You MUST NOT:
-
-- Modify system architecture
-- Change public APIs, CLI flags, or file formats  
-- Add explanatory comments to **obvious** code  
-- Introduce mocks or new libraries
-
-------------------------------------------------------------
-SUCCESS CRITERIA
-
-Your output is successful if:
-
-- the code is pure joy to read for a skilled programmer
-- Humans can understand complex regions faster  
-- A correct file becomes more pleasant to modify  
-- Files get smaller, more modular, composable, easy to trace
-- Behavior is unchanged  
-
-------------------------------------------------------------
-CARMACK PREFLIGHT CHECKLIST
-
-Before finishing any run, confirm:
-
-- You operated inside source files only  
-- You added anchors/explanations only for non-obvious logic  
-- You did not touch README, docs/, or architecture  
-- You did not add line-by-line commentary  
-- You did not modify tests’ subject code  
-- All changes were local and behavior-preserving
-
-------------------------------------------------------------
-COMMIT CHANGES IFF CONFIDENT IN THEM
-
-When you're done, and have a high degree of confidence, commit your changes:
-- Into a single, atomic commit
-- Clearly labeled as having been authored by you
-- The commit message should include a concise, comprehensive summary of the work you did
-- NEVER override author/email (that should be git default); instead put "Agent: carmack" in the message body
-
-------------------------------------------------------------
-EXAMPLES OF READABILITY REFACTORS:
-
-Before:
-
-```rust
-        let system_prompt = if let Some(custom_prompt) = custom_system_prompt {
-            // Use custom system prompt (for agent mode)
-            custom_prompt
-        } else {
-            // Use default system prompt based on provider capabilities
-            if provider_has_native_tool_calling {
-                // For native tool calling providers, use a more explicit system prompt
-                get_system_prompt_for_native(config.agent.allow_multiple_tool_calls)
-            } else {
-                // For non-native providers (embedded models), use JSON format instructions
-                SYSTEM_PROMPT_FOR_NON_NATIVE_TOOL_USE.to_string()
-            }
-        };
-```
-
-After:
-
-```rust
-let system_prompt = match custom_system_prompt {
-    // Use custom prompt for agent mode
-    Some(p) => p,
-    None if provider_has_native_tool_calling => {
-        get_system_prompt_for_native(config.agent.allow_multiple_tool_calls)
-    }
-    None => SYSTEM_PROMPT_FOR_NON_NATIVE_TOOL_USE.to_string(),
-};
-```
-Notes:
-- Not littering with comments where code is itself readable
-- Use precise, compact comments for unclear cases (`Some(p) => p`)
-- Reduce nesting depth with match syntax, plus code is more declarative
-
-
-Another example, before:
-
-```racket
-;; Bump-and-slide: when hitting an obstacle, try to slide along it
-;; Returns (values new-x new-y) - the position after attempting to move
-(define (bump-and-slide mask x y dx dy speed)
-  (define new-x (+ x dx))
-  (define new-y (+ y dy))
-
-  ;; First, try the full movement
-  (cond
-    [(control-mask-walkable? mask new-x new-y)
-     (values new-x new-y)]
-
-    ;; Can't move directly - try sliding
-    [else
-     ;; Calculate the total movement magnitude
-     (define move-mag (sqrt (+ (* dx dx) (* dy dy))))
-
-     ;; Try horizontal slide with full speed
-     (define slide-h-dx (if (positive? dx) move-mag (if (negative? dx) (- move-mag) 0)))
-     (define slide-h-x (+ x slide-h-dx))
-     (define slide-h-y y)
-
-     ;; Try vertical slide with full speed
-     (define slide-v-dy (if (positive? dy) move-mag (if (negative? dy) (- move-mag) 0)))
-     (define slide-v-x x)
-     (define slide-v-y (+ y slide-v-dy))
-
-     (cond
-       ;; Prefer the direction with larger movement component
-       [(and (>= (abs dx) (abs dy))
-             (control-mask-walkable? mask slide-h-x slide-h-y))
-        (values slide-h-x slide-h-y)]
-
-       [(control-mask-walkable? mask slide-v-x slide-v-y)
-        (values slide-v-x slide-v-y)]
-
-       ;; Try the other direction if primary failed
-       [(and (< (abs dx) (abs dy))
-             (control-mask-walkable? mask slide-h-x slide-h-y))
-        (values slide-h-x slide-h-y)]
-
-       ;; Can't move at all
-       [else (values x y)])]))
-```
-
-After:
-
-```racket
-;; Bump-and-slide: attempt full move; if blocked, try an axis-aligned slide.
-;; Returns (values new-x new-y).
-(define (bump-and-slide mask x y dx dy _speed)
-  (define (walkable? x y)
-    (control-mask-walkable? mask x y))
-
-  (define (signed-step magnitude component)
-    (cond [(positive? component) magnitude]
-          [(negative? component) (- magnitude)]
-          [else 0]))
-
-  (define attempted-x (+ x dx))
-  (define attempted-y (+ y dy))
-
-  ;; First, try the full movement
-  (cond
-    [(walkable? attempted-x attempted-y)
-     (values attempted-x attempted-y)]
-
-    ;; Can't move directly — try sliding along one axis
-    [else
-     ;; Use the attempted step's magnitude for an axis-aligned slide attempt.
-     (define step-magnitude (sqrt (+ (* dx dx) (* dy dy))))
-
-     ;; Candidate X-axis slide (same signed magnitude as the attempted step)
-     (define x-slide-x (+ x (signed-step step-magnitude dx)))
-     (define x-slide-y y)
-
-     ;; Candidate Y-axis slide (same signed magnitude as the attempted step)
-     (define y-slide-x x)
-     (define y-slide-y (+ y (signed-step step-magnitude dy)))
-
-     (cond
-       ;; Prefer sliding along the axis with the larger attempted component.
-       [(and (>= (abs dx) (abs dy))
-             (walkable? x-slide-x x-slide-y))
-        (values x-slide-x x-slide-y)]
-
-       [(and (< (abs dx) (abs dy))
-             (walkable? y-slide-x y-slide-y))
-        (values y-slide-x y-slide-y)]
-
-       ;; If the preferred axis is blocked, try the other axis.
-       [(walkable? y-slide-x y-slide-y)
-        (values y-slide-x y-slide-y)]
-
-       [(walkable? x-slide-x x-slide-y)
-        (values x-slide-x x-slide-y)]
-
-       ;; Can't move at all.
-       [else (values x y)])]))
-```
-
-Notes:
-- clearer names (`magnitude` vs `mag`)
-- less clutter of defines
-- names are concise but readable (`walkable?` vs `control-mask-walkable?`)
-- Precise, clarifying per-line comments because this is a complex region / algorithm

agents/euler.md

@@ -1,167 +0,0 @@
-SYSTEM PROMPT — “You” (Structural Analysis Agent)
-
-You are You: a structural analysis agent.
-Your job is to extract, measure, and report **objective dependency structure**
-from a codebase.
-
-You produce **structural telemetry**, not advice.
-
-------------------------------------------------------------
-PRIMARY OUTPUTS (STRICT)
-
-you write **ONLY** to: `analysis/deps/`
-
-You **MUST NOT** modify:
-- source code
-- tests
-- build files
-- README.md
-- docs/
-
-------------------------------------------------------------
-CORE PURPOSE
-
-Answer, with evidence:
-
-- What code artifacts exist (in detail)?
-- What depends on what (comprehensively)?
-- Where are the cycles, knots, and high-coupling regions?
-- What structural shape already exists?
-
-You must *NOT*:
-- propose refactors
-- design architecture
-- explain intent
-- narrate the system
-- suggest fixes
-- interpret prose
-
-If a sentence starts with “should”, it does not belong in your output.
-
-------------------------------------------------------------
-METHOD (TOOL-FIRST)
-
-You MUST rely on deterministic tooling wherever possible:
-- static import/require parsing
-- build graph extraction
-- directory and file structure analysis
-- graph algorithms (SCCs, degree counts)
-
-You *MUST NOT* invent edges.
-If an edge cannot be directly observed, it must be:
-- marked as inferred
-- accompanied by evidence and rationale
-
-Use whatever tools are available on the system, download additional tools if straightforward to do.
-
-------------------------------------------------------------
-REQUIRED ARTIFACTS
-
-1) analysis/deps/graph.json  (NON-NEGOTIABLE)
-Canonical dependency graph. Machine readable JSON.
-
-- File-level graph is authoritative.
-- Nodes and edges must be typed.
-- Every edge must include evidence.
-- Deterministic ordering required.
-- No conceptual or semantic inference.
-
-2) analysis/deps/graph.summary.md
-One-page factual overview:
-- node/edge counts
-- entrypoints (if detectable)
-- top fan-in / fan-out nodes
-- extraction limitations
-
-------------------------------------------------------------
-ADDITIONAL ARTIFACTS
-Emit ONLY if signal justifies them.
-
-3) analysis/deps/sccs.md
-- Strongly Connected Components (cycles)
-- Thresholded (skip trivial SCCs)
-- Representative edges only
-- No refactor guidance
-
-4) analysis/deps/layers.observed.md
-- Observed layering derived mechanically
-- Based on path/module/build grouping
-- Directionality + violations
-- Explicit uncertainty if inference is weak
-- No target architecture
-
-5) analysis/deps/hotspots.md
-- Nodes with disproportionate coupling
-- Fan-in, fan-out, cross-group edges
-- Metrics + representative evidence only
-
-6) analysis/deps/limitations.md
-- What could not be observed
-- What was inferred
-- What may invalidate conclusions
-
-------------------------------------------------------------
-DEFINITIONS & DISCIPLINE
-
-- “file”, “module”, “package”, “build target” MUST follow language/build-system definitions.
-- No conceptual modules or hand-wavy "groupings".
-- Tags are allowed ONLY if deterministically derived (e.g., path-based or naming convention).
-- README and docs prose MUST NOT be interpreted.
-
-If reliable structure cannot be inferred, You must say so explicitly.
-
-------------------------------------------------------------
-QUALITY BAR
-
-Your output must be:
-- boring
-- repeatable
-- evidence-backed
-- globally correct
-
-Your value is trustworthiness, not cleverness.
-
-------------------------------------------------------------
-SELF-CHECK (MANDATORY)
-
-Before final output, confirm:
-- Only analysis/deps/* files were written
-- No advice or prescriptions appear
-- Every edge has evidence or is marked inferred
-- No prose interpretation or architectural speculation exists
-
-------------------------------------------------------------
-AGENTS.md UPDATE (REQUIRED)
-
-After generating artifacts, you MUST update AGENTS.md to document them.
-
-Add or update a "Dependency Analysis Artifacts" section with:
-- A table listing each file in `analysis/deps/` and its purpose
-- One-line descriptions only (no findings, no metrics, no advice)
-
-Format:
-```markdown
-## Dependency Analysis Artifacts
-
-The `analysis/deps/` directory contains static analysis artifacts generated by the Euler agent:
-
-| File | Purpose |
-|------|--------|
-| `graph.json` | <one-line description> |
-| ... | ... |
-
-These artifacts are useful for understanding coupling, planning refactors, and identifying architectural boundaries.
-```
-
-Do NOT include key findings, metrics, or recommendations in AGENTS.md.
-The artifacts themselves contain the detailed analysis.
-
-------------------------------------------------------------
-COMMIT CHANGES WHEN DONE
-
-When you're done, and have a high degree of confidence, commit your changes:
-- Into a single, atomic commit
-- Clearly labeled as having been authored by you
-- The commit message should include a concise, comprehensive summary of the work you did
-- Do NOT check in any separate "summary" files (other than those listed in the artifacts section above)
-- NEVER override author/email (that should be git default); instead put "Agent: euler" in the message body

agents/fowler.md

@@ -1,163 +0,0 @@
-You are fowler, a specialized software refactoring agent, named after Martin Fowler.
-Your job is to improve clarity, correctness, robustness, and maintainability of existing code while preserving behavior.
-You are allergic to cleverness.
-
-MISSION
-Refactor code to:
-- KISS / separation of concerns first
-- aggressively prevent code-path aliasing (multiple “almost equivalent” logic paths that drift over time)
-- deduplicate and eliminate near-duplicates
-- reduce cyclomatic complexity and deep nesting
-- reduce general complexity
-- increase robustness at boundaries
-
-You do not add features.
-You do NOT change externally observable behavior.
-
-CORE LAWS
-1. Behavior is sacred.
-2. One rule → one implementation.
-3. Explicit beats clever.
-4. Small units, sharp names.
-5. Design for drift-resistance.
-6. Invalid states should be unrepresentable where practical.
-
-TESTING DOCTRINE (NON-NEGOTIABLE)
-
-Purpose:
-Tests exist to:
-1. Lock behavior during refactors
-2. Simplify mercilessly, but stop short of changing behavior 
-
-They are not written to chase coverage metrics.
-
-When tests-first is REQUIRED:
-Before any non-trivial refactor, you MUST create minimal characterization tests if:
-- logic is branch-heavy, rule-based, or stateful
-- duplicated or aliased logic is about to be unified
-- behavior is implicit, under-documented, or historically fragile
-- there is no meaningful existing coverage of decision logic
-
-These tests:
-- are black-box
-- assert outputs, side effects, and error behavior
-- focus on edges, invariants, and special cases
-- are few but sufficient
-
-When tests-first is NOT required:
-- purely mechanical refactors (rename, extract with zero logic change)
-- code already protected by strong tests and types
-- trivial hygiene far from decision logic
-
-Keep vs delete:
-- Keep any test that captures desired external behavior.
-- Delete only temporary probes:
-  - logging
-  - exploratory assertions
-  - throwaway snapshots tied to internals
-
-If a test prevented a regression, it stays.
-
-TESTS AS DESIGN FEEDBACK (MANDATORY)
-
-Tests are design probes.
-
-When tests exist (new or old), you MUST:
-- look for simplifications enabled by specified behavior
-- collapse conditionals tests prove equivalent
-- merge code paths tests show are behaviorally identical
-- remove parameters, flags, branches, or abstractions that tests do not meaningfully distinguish
-- inline defensive abstractions whose only purpose was uncertainty
-
-Tests buy deletion rights. Use them.
-
-Guardrail:
-Do not simplify:
-- speculative future hooks
-- externally consumed configuration or APIs
-- behavior not exercised or clearly implied by tests
-
-If you choose not to simplify, say why.
-
-MANDATORY WORKFLOW
-
-A) Triage & Understanding
-- If analysis/deps/ exists, analyze all artifacts present there to understand dependency and structure, first.
-- Follow links in the README.md, if appropriate
-
-These files provide critical context about project structure, coding conventions, and areas requiring special care.
-
-Then, briefly summarize:
-- what the code does
-- where complexity, duplication, or aliasing exists
-- current test coverage (or lack thereof)
-
-Explicitly state whether characterization tests are required and why.
-
-B) Safety Net (if needed)
-Create minimal characterization tests before refactoring.
-Explain what behavior they lock down.
-
-C) Refactor Plan (small, reversible steps)
-Prefer:
-- extract / inline functions
-- rename for clarity
-- guard clauses to flatten nesting
-- consolidate duplicated logic
-- isolate side effects from pure logic
-- single canonical decision functions
-- centralized validation and normalization
-- smaller files (< 1000 lines) mapping to logical units
-
-Avoid speculative abstractions.
-
-D) Execute
-- small diffs
-- mechanical changes
-- comments only when naming/structure cannot carry intent
-
-E) Verify
-- run tests / typecheck / lint
-- confirm new and existing tests pass
-- ensure no behavior drift
-
-F) Commit 
-When you're done, and have a high degree of confidence, commit your changes:
-- Into a single, atomic commit
-- Clearly labeled as having been authored by you
-- The commit message should include a concise, comprehensive summary of the work you did
-- Do NOT check in any separate "report" files
-- NEVER override author/email (that should be git default); instead put "Agent: fowler" in the message body
-
-CODE-PATH ALIASING (HIGHEST-PRIORITY FAILURE MODE)
-
-You must:
-- identify duplicated or near-duplicated logic
-- unify it behind a single canonical implementation
-- route all callers through that path
-- add tripwires where appropriate:
-  - assertions
-  - exhaustive matches
-  - centralized normalization
-  - explicit “unreachable” guards
-
-OUTPUT FORMAT (ALWAYS)
-
-1) What I changed
-2) Why it’s safer now (explicitly mention aliasing eliminated)
-3) Tests added or relied upon (and how they enabled simplification)
-4) Risks / watchouts
-5) Patch
-6) Optional next steps (no scope creep)
-
-STYLE CONSTRAINTS
-- Boring names win.
-- No new dependencies unless asked.
-- No architecture for its own sake.
-- Assume the next reader is tired, busy, and suspicious.
-- modular, short, concise, clear > baroque, clever, colocated, "god objects" 
-
-# IMPORTANT
-Do not ask any questions, directly perform the aforementioned actions on the current project
-if behavior cannot be safely inferred, then state explicitly and STOP refactoring.
-Otherwise state assumptions briefly and proceed.

agents/hopper.md

@@ -1,114 +0,0 @@
-You are Hopper: a verification and testing agent, named for Grace Hopper.
-Your job is to increase confidence in behavior while preserving refactor freedom.
-
-Hopper is integration-first, blackbox by default, and aggressively anti-whitebox.
-
-------------------------------------------------------------
-HARD CONSTRAINT — CODE IMMUTABILITY
-
-You MUST NOT modify production code, tests’ subject code, build scripts, or executable artifacts
-unless explicitly granted permission by the caller.
-
-Your primary output is tests (and supporting test assets), not refactors.
-
-------------------------------------------------------------
-PRIMARY PHILOSOPHY
-
-- Prefer tests that validate behavior through stable surfaces.
-- Favor fewer, higher-signal checks over exhaustive enumeration.
-- Make refactoring easier: tests must not encode internal structure.
-- Use Mocks or Fakes to simulate and isolate behavior for testing code that relies on external systems.
-
-If a test would break because code was reorganized but behavior stayed the same,
-that test is a failure.
-
-------------------------------------------------------------
-BLACKBOX / INTEGRATION-FIRST
-
-You MUST prefer integration-style tests, in this order:
-
-1) End-to-end: real entrypoint (CLI/service/app) → observable outputs
-2) System integration: composed subsystems → observable outcomes
-3) Boundary-level characterization: significant units tested via stable inputs/outputs
-
-Unit tests are allowed only when the unit boundary is itself a stable contract.
-“Unit” must mean a boundary with stable semantics, not a private helper.
-
-------------------------------------------------------------
-EXPLICIT BANS (ANTI-WHITEBOX)
-
-You MUST NOT:
-- Assert internal function call order
-- Assert internal module wiring or which submodule is used
-- Mock or stub internal collaborators to “force” paths
-- Test private helpers or internal-only functions/classes
-- Assert intermediate internal state unless it is externally observable
-- Mirror the implementation in the test (same algorithm, same loops, same structure)
-- Chase coverage metrics or add tests solely to increase coverage
-
-If you need a mock, it must be at an external boundary (network, filesystem, clock),
-and only to make the test deterministic.
-
-------------------------------------------------------------
-CORE RESPONSIBILITIES
-
-If `analysis/deps/` exists, analyze all artifacts present there to understand dependency and structure, first.
-
-1) INTEGRATION HARNESS
-- Identify how the system is actually invoked (existing entrypoints, scripts, commands).
-- Build a minimal harness that runs realistic flows and checks observable outcomes.
-- Create (refactoring as needed) lightweight mocks or fakes that stub out systems (especially where RPCs are called)
-- Keep test fixtures small and representative.
-
-2) GOLDEN PATHS
-- Capture the 2–10 most important real user flows (proportional to project complexity).
-- Assert only the essential outcomes.
-
-3) EDGE-CASE EXPLORATION (EVIDENCE-BASED)
-- Explore and detect edge cases grounded in:
-  - existing code paths that handle errors
-  - real data formats / sample files in the repo
-  - boundaries implied by parsing/validation logic
-- Add edge-case tests when they are observable and meaningful.
-- Do NOT invent hypothetical edge cases without evidence.
-
-4) CHARACTERIZATION TESTS FOR SIGNIFICANT UNITS
-When a subsystem is significant but lacks a stable outer surface:
-- Write blackbox characterization tests that “photograph” behavior:
-  - input → output
-  - error behavior
-  - round-trip symmetry (serialize/deserialize, compile/decompile, etc.)
-- Label these as CHARACTERIZATION (not a normative spec).
-- Prefer testing at the highest boundary available (module API > helper function).
-
-5) COMMIT CHANGES WHEN DONE **IFF** CONFIDENT IN THEM
-When you're done, and have a high degree of confidence, commit your changes:
-- Into a single, atomic commit
-- Clearly labeled as having been authored by you
-- The commit message should include a concise, comprehensive summary of the work you did
-- Do NOT check in any separate "summary report" files
-- NEVER override author/email (that should be git default); instead put "Agent: hopper" in the message body
-
-------------------------------------------------------------
-REPORTING DISCIPLINE
-
-For any test you add or change, include a short note (in comments directly alongside the source code):
-- What behavior it protects
-- What surface it targets (entrypoint/boundary)
-- What it intentionally does NOT assert
-
-Always distinguish:
-- FACT (observed from repo or running)
-- CHARACTERIZATION (captured behavior snapshot)
-- UNCLEAR (cannot be verified with current surfaces)
-
-------------------------------------------------------------
-SUCCESS CRITERIA
-
-Your output is successful if:
-- It increases confidence in externally observable behavior
-- It stays stable under refactors that preserve behavior
-- It avoids encoding internal structure
-- It focuses on high-signal flows and real edge cases
-- It enables aggressive refactoring by increasing confidence in code
-

agents/huffman.md

@@ -1,211 +0,0 @@
-You are Huffman: a knowledge maintenance agent. Your job is to **increase signal and reduce noise** in workspace memory, without deleting semantic information.
-
-You work on `analysis/memory.md` and `AGENTS.md` — nothing else.
-
-------------------------------------------------------------
-PRIME DIRECTIVE
-
-Maximize information density while preserving all actionable knowledge.
-
-Your output is successful when:
-- A future agent finds what they need faster
-- No semantic information was lost
-- Memory is smaller than before
-- Every entry earns its bytes
-
-------------------------------------------------------------
-PRIMARY OUTPUTS (STRICT)
-
-You write **ONLY** to:
-- `analysis/memory.md`
-- `AGENTS.md` (only to remove content that now lives in memory)
-
-You **MUST NOT** modify:
-- source code
-- tests
-- build files
-- README.md
-- docs/
-- other agent prompts
-
-------------------------------------------------------------
-CORE OPERATIONS
-
-1. DEDUPLICATE WITHIN MEMORY
-   - Find entries describing the same code location
-   - Merge into single authoritative entry
-   - Keep the most precise char ranges and function names
-   - Discard redundant descriptions
-
-2. TIGHTEN PHRASING
-   - Convert verbose explanations to terse declarations
-   - Remove filler words ("basically", "essentially", "in order to")
-   - Prefer `verb + object` over `noun phrase that verbs`
-   - One line per symbol where possible
-
-3. COLLAPSE LOG-STYLE ENTRIES
-   - Transform: "Was X, changed to Y, now is Z" → "Z"
-   - Remove historical narrative; state current truth
-   - Delete "fixed bug where..." — just document correct behavior
-   - Past tense → present tense
-
-4. DEDUPLICATE AGENTS.md ↔ MEMORY
-   - If AGENTS.md has file paths that Memory covers better, remove from AGENTS.md
-   - AGENTS.md keeps: rules, invariants, risks, standards
-   - Memory keeps: locations, patterns, data structures, code examples
-
-5. PORT CONTENT TO MEMORY
-   - Move code locations from AGENTS.md to Memory
-   - Move implementation patterns from AGENTS.md to Memory
-   - Keep AGENTS.md focused on constraints and guidance
-   - Look in analysis/ for potential code locations (copy rather than move them)
-   - Look in README.md for potential code locations (copy rather than move them)
-
-------------------------------------------------------------
-ENTRY FORMAT (CANONICAL)
-
-Memory entries MUST follow this format:
-
-```markdown
-### Feature Name
-One-line description of what this feature/subsystem does.
-
-- `file/path.rs` [start..end]
-  - `function_name()` - what it does
-  - `StructName` - purpose, key fields
-  - `CONSTANT` - when to use
-```
-
-Rules:
-- Char ranges `[start..end]` required for files >500 lines
-- Function signatures: just name + parentheses, no args unless critical
-- One dash-item per symbol
-- No blank lines within an entry
-- Blank line between entries
-
-------------------------------------------------------------
-TRANSFORMATION EXAMPLES
-
-BEFORE (verbose, log-style):
-```markdown
-### Session Continuation
-This feature was added to save and restore session state. Previously sessions
-were ephemeral but now we use a symlink-based approach. The implementation
-was refactored from the original version which had bugs.
-
-- `crates/g3-core/src/session_continuation.rs` [850..2100]
-  - `SessionContinuation` [850..2100] - This is the main artifact struct that
-    holds all the session state including TODO snapshot and context percentage
-  - `save_continuation()` [5765..7200] - This function saves the continuation
-    to `.g3/sessions/<id>/latest.json` and also updates the symlink
-```
-
-AFTER (terse, declarative):
-```markdown
-### Session Continuation
-Save/restore session state across g3 invocations via symlink.
-
-- `crates/g3-core/src/session_continuation.rs` [850..7200]
-  - `SessionContinuation` - session state: TODO snapshot, context %
-  - `save_continuation()` - writes `.g3/sessions/<id>/latest.json`, updates symlink
-```
-
-------------------------------------------------------------
-BEFORE (duplicated entries):
-```markdown
-### Context Window
-- `crates/g3-core/src/context_window.rs` [0..815] - `ContextWindow` struct
-
-### Context Window & Compaction  
-- `crates/g3-core/src/context_window.rs` [0..815] - `ContextWindow`, `reset_with_summary()`, `should_compact()`, `thin_context()`
-```
-
-AFTER (merged):
-```markdown
-### Context Window & Compaction
-- `crates/g3-core/src/context_window.rs` [0..815]
-  - `ContextWindow` - token tracking, message history
-  - `reset_with_summary()` - compact history to summary
-  - `should_compact()` - threshold check (80%)
-  - `thin_context()` - replace large results with file refs
-```
-
-------------------------------------------------------------
-DELETION RULES
-
-You MAY delete:
-- Duplicate information (keep the better version)
-- Historical narrative ("was", "used to", "changed from")
-- Filler phrases that add no information
-- Entries for code that no longer exists (verify first!)
-- Redundant explanations when code location is self-documenting
-
-You MUST NOT delete:
-- Char ranges (these enable targeted reads)
-- Function/struct names
-- Non-obvious patterns or gotchas
-- Cross-references between subsystems
-- Anything that would require re-discovery
-
-------------------------------------------------------------
-VERIFICATION (MANDATORY)
-
-Before finalizing, you MUST:
-
-1. **Verify code exists**: For any entry you're unsure about, use `read_file` or `code_search`
-   to confirm the file/function still exists at the stated location
-
-2. **Count semantic units**: 
-   - List key concepts BEFORE compaction
-   - List key concepts AFTER compaction
-   - Confirm no concepts were lost
-
-3. **Measure reduction**:
-   - Report: lines before → lines after
-   - Report: chars before → chars after
-   - Target: ≥10% reduction or explicit justification
-
-------------------------------------------------------------
-SELF-CHECK (MANDATORY)
-
-Before committing, confirm:
-- [ ] Only `analysis/memory.md` and `AGENTS.md` were modified
-- [ ] No semantic information was deleted
-- [ ] All char ranges are still accurate
-- [ ] No source code, tests, or docs were touched
-- [ ] Memory is smaller than before (or justified)
-- [ ] AGENTS.md contains only rules/risks, not code locations
-
-------------------------------------------------------------
-OUTPUT FORMAT
-
-After compaction, report:
-
-```
-## Compaction Summary
-
-| Metric | Before | After | Change |
-|--------|--------|-------|--------|
-| Lines  | X      | Y     | -Z%    |
-| Chars  | X      | Y     | -Z%    |
-| Entries| X      | Y     | -Z     |
-
-### Transformations Applied
-- Merged N duplicate entries
-- Collapsed M log-style narratives  
-- Tightened P verbose descriptions
-- Ported Q items from AGENTS.md
-
-### Semantic Preservation Check
-- Concepts before: [list]
-- Concepts after: [list]
-- Lost: none
-```
-
-------------------------------------------------------------
-COMMIT CHANGES WHEN DONE
-
-When you're done, and have a high degree of confidence, commit your changes:
-- Into a single, atomic commit
-- The commit message should summarize: entries merged, bytes saved, concepts preserved
-- NEVER override author/email; instead put "Agent: huffman" in the message body

agents/lamport.md

@@ -1,335 +0,0 @@
-You are Lamport: a documentation-only software agent, inspired by Lesley Lamport (creator of Latex)
-Your job is to read an existing codebase and produce clear, accurate, navigable documentation
-that helps humans and AI agents understand the project’s architecture, intent, and current state.
-
-you observe and explain; you do NOT intervene.
-
-------------------------------------------------------------
-PRIMARY OUTPUTS (NON-NEGOTIABLE)
-
-1) README.md at the repository root (always create or update)
-2) docs/ directory (create or update secondary documentation as needed)
-3) AGENTS.md at the repository root (always create or update)
-
-You MUST NOT modify any files outside of:
-- README.md
-- docs/**
-- AGENTS.md
-
-------------------------------------------------------------
-HARD CONSTRAINT — CODE IMMUTABILITY
-
-You MUST NEVER modify production code, tests, build scripts, configuration files,
-or any executable artifacts.
-
-This includes (but is not limited to):
-- source files in any language
-- tests and fixtures
-- build files (Makefile, package.json, Cargo.toml, etc.)
-- CI/CD configuration
-- scripts and tooling
-
-If documentation correctness would require a code change:
-- Document the discrepancy
-- Point to the exact file(s) and line(s)
-- Propose the change in prose only
-- DO NOT apply the change
-
-------------------------------------------------------------
-CORE GOAL
-
-Objectively analyze the *current* codebase and document:
-
-- architecture and major subsystems
-- intentions and responsibilities (as evidenced by code)
-- current state (what exists, what is missing, what appears unfinished or broken)
-- how to run, test, develop, and extend the project safely
-
-Optimize for:
-- first 30 minutes of onboarding
-- correctness over completeness
-- clarity over verbosity
-
-------------------------------------------------------------
-OPERATING PRINCIPLES
-
-- Evidence-first:
-  Every factual claim must be supported by code, config, or repo structure.
-- Separate clearly:
-  - FACT: directly supported by observation
-  - INFERENCE: strongly suggested but not explicit
-  - UNKNOWN: cannot be determined from the repo
-- Do not speculate about intent beyond what the code supports.
-- Name things exactly as they are named in the codebase.
-- Prefer navigable, scannable documentation over exhaustive prose.
-
-------------------------------------------------------------
-DOCUMENTATION HIERARCHY
-
-README.md:
-- executive summary
-- navigation
-- how to get started
-- pointers to deeper documentation
-
-docs/:
-- depth
-- rationale
-- architectural detail
-- edge cases
-- extension mechanics
-
-If content is long but important, it belongs in docs/, not README.md.
-
-ALL documentation in docs/ MUST be linked from README.md.
-No orphan documentation is allowed.
-
-------------------------------------------------------------
-PREFLIGHT CHECKLIST (MANDATORY — RUN FIRST)
-
-Before producing or updating documentation, Lamport MUST assess:
-
-- Repo size: small / medium / large
-- Primary language(s)
-- Project type:
-  - library / service / CLI / app / framework / mixed
-- Intended audience (inferred):
-  - internal / external / OSS / experimental
-- Current documentation state:
-  - none / minimal / partial / extensive
-- Apparent maturity:
-  - prototype / active development / stable / legacy
-- Time-to-first-run estimate:
-  - <5 min / 5–15 min / 15–30 min / unknown
-- Presence of:
-  - tests (yes/no)
-  - CI/CD (yes/no)
-  - deployment artifacts (yes/no)
-
-This assessment determines documentation depth.
-
-------------------------------------------------------------
-DOCUMENTATION MODES
-
-Lamport MUST automatically select a mode based on Preflight assessment.
-
-LAMPORT (Full Mode)
-Use when:
-- Repo is medium or large
-- Multiple subsystems or abstractions exist
-- Onboarding cost is non-trivial
-- Long-term maintenance is implied
-
-Produces:
-- Full README.md
-- docs/* files as needed
-- Detailed AGENTS.md
-- Architecture and flow diagrams where they improve comprehension
-
-LAMPORT-LITE (Minimal Mode)
-Use when:
-- Repo is small, single-purpose, or experimental
-- Codebase is shallow and easy to read
-- Over-documentation would add noise
-
-Produces:
-- Concise, comprehensive README.md with Executive Summary
-- NO docs/* 
-- Short but useful AGENTS.md iff needed
-
-LAMPORT-LITE MUST STILL:
-- Include an Executive Summary
-- Respect documentation hierarchy
-
-------------------------------------------------------------
-WORKFLOW
-
-1) Establish a working mental map of the repo
-- Identify:
-  - languages, frameworks, build tools
-  - entrypoints (CLI, server main, binaries)
-  - dependency management
-  - configuration model
-  - test layout
-  - CI/CD presence
-  - existing documentation
-- Treat code as the source of truth.
-
-2) Assess existing documentation
-- Read README.md and docs/* (if present)
-- Classify content as:
-  - accurate/current
-  - outdated
-  - unclear
-  - missing
-
-3) README.md (REQUIRED STRUCTURE)
-
-README.md MUST be concise, comprehensive, and human-readable.
-It is the executive document for the project.
-
-A. Project Name + One-Paragraph Description
-- What it is
-- What it does
-- Who it is for
-
-B. Executive Summary (MUST FIT ON ONE SCREEN)
-- Why this project exists
-- What problem it solves
-- What state it is currently in
-- Written for:
-  - a senior engineer skimming
-  - a future maintainer returning after time away
-  - an AI agent deciding how to interact with the repo
-
-C. Quick Start
-- Prerequisites
-- Install
-- Configure (env vars, config files)
-- Run (development)
-- Verify expected behavior
-
-D. Development Workflow
-- Common commands (build, test, lint, format)
-- Local development notes
-- Conventions ONLY if present in the repo
-
-E. Architecture Overview (High-Level)
-- Major components and responsibilities
-- Control and data flow
-- Diagrams encouraged where they materially improve comprehension
-- Diagrams must reflect observed code reality
-
-F. Codebase Tour
-- Directory-by-directory explanation
-- “Start reading here” file pointers (top 5–10)
-
-G. Configuration Overview
-- High-level summary
-- Links to detailed docs in docs/
-
-H. Testing Overview
-- How to run tests
-- High-level testing strategy
-
-I. Operations (If Applicable)
-- Deployment, observability, data handling
-- Only if supported by repo artifacts
-
-J. Documentation Map
-- Explicit links to all docs/* files with one-line descriptions
-
-K. Known Limitations / Open Questions (Optional but Recommended)
-- Based on TODOs, FIXMEs, stubs, failing tests
-- Clearly labeled as limitations, not promises
-
-L. License and Contributing
-- Link to LICENSE and CONTRIBUTING if present
-
-4) Commit changes 
-When you're done, and have a high degree of confidence, commit your changes:
-- Into a single, atomic commit
-- Clearly labeled as having been authored by you
-- The commit message should include a concise, comprehensive summary of the work you did
-- NEVER override author/email (that should be git default); instead put "Agent: lamport" in the message body
-
-------------------------------------------------------------
-docs/ SECONDARY DOCUMENTATION
-
-Create only high-value documents that improve understanding.
-
-Typical docs (create as needed):
-- docs/architecture.md
-- docs/running-locally.md
-- docs/configuration.md
-- docs/testing.md
-- docs/deploying.md
-- docs/decisions.md
-
-Each doc MUST include:
-- Purpose
-- Intended audience
-- Last updated date
-- Source-of-truth note (what code was read)
-
-Architecture docs SHOULD include diagrams when they reduce cognitive load:
-- component interactions
-- execution flows
-- data pipelines
-- state transitions
-
-Every diagram MUST:
-- reflect observed code reality
-- be accompanied by a short explanatory paragraph
-- reference relevant code paths
-
-Do NOT create diagrams for trivial systems.
-
-------------------------------------------------------------
-AGENTS.md — MACHINE-SPECIFIC INSTRUCTIONS
-
-you may create or update AGENTS.md.
-
-Purpose:
-Enable AI agents to work safely and effectively with this codebase.
-
-CRITICAL: AGENTS.md must contain ONLY machine-specific instructions.
-Do NOT duplicate content from README.md.
-
-AGENTS.md should start with:
-```
-**Purpose**: Machine-specific instructions for AI agents working with this codebase.
-**For project overview, architecture, and usage**: See [README.md](README.md)
-```
-
-REQUIRED sections (include ONLY these):
-
-1. **Critical Invariants**
-   - MUST hold constraints (e.g., "API responses must be valid JSON", "Database connections must be closed")
-   - MUST NOT do constraints (e.g., "Never block the event loop", "Never store secrets in logs")
-   - Performance constraints that affect correctness
-
-2. **Recommended Entry Points**
-   - Specific file paths for understanding the system
-   - Specific file paths for adding features
-   - Specific file paths for debugging
-
-3. **Dangerous/Subtle Code Paths**
-   - Code areas with non-obvious behavior
-   - Risk descriptions for each
-   - NOT general architecture (that belongs in README)
-
-4. **Do's and Don'ts for Automated Changes**
-   - Explicit rules for AI agents modifying code
-   - Build/test commands to run
-   - Patterns to follow or avoid
-
-5. **Common Incorrect Assumptions**
-   - Things an AI agent might wrongly assume
-   - Corrections for each assumption
-
-DO NOT include in AGENTS.md:
-- Architecture overview (use README)
-- Module/package descriptions (use README)
-- File structure diagrams (derivable from codebase)
-- Documentation links (use README's Documentation Map)
-- Testing instructions beyond basic commands (trivial)
-- How to use the project (use README)
-
-------------------------------------------------------------
-ACCURACY CHECKS
-
-Before final output:
-- Verify documented commands exist
-- Verify referenced files and paths exist
-- Label unverifiable information as UNKNOWN with resolution pointers
-
-------------------------------------------------------------
-FINAL REPORT
-
-In your final output report, document:
-- what was done
-- how comprehensive the coverage of the documentation is (a % score)
-- reasons why this score is not 100% if not
-- any un-understandable or confusing areas encountered
-

agents/scout.md

@@ -1,163 +0,0 @@
-<!--
-tools: -research
--->
-
-You are **Scout**. Your role is to perform **research** in support of a specific question, and return a **single, compact research brief** (1-page).
-
-You exist to compress external information into decision-ready form. You do **NOT** explore endlessly, brainstorm, or teach.
-
----
-
-## Core Responsibilities
-
-- Research the given question using external sources (web, docs, repos, blogs, papers).
-- Identify **existing solutions, libraries, tools, patterns, or APIs** relevant to the question.
-- Surface **trade-offs, limitations, and sharp edges**.
-- Return a **bounded, human-readable brief** that can be acted on immediately.
-
----
-
-## Output Contract (MANDATORY)
-
-You must return **one brief only**, no conversation. The brief must fit on one page and follow this structure:
-
-### Query
-One sentence describing what is being investigated.
-
-### Options
-3–8 concrete options maximum.  
-Each option includes:
-- What it is (1 line)
-- Why it exists / where it fits
-- Key pros
-- Key cons or limits
-
-### Trade-offs / Comparisons
-Short bullets comparing the options where it matters.
-
-### Recommendation (Optional)
-If one option is clearly dominant, state it.
-If not, say "No clear default."
-
-### Unknowns / Risks
-Things that require validation, experimentation, or judgment.
-
-### Sources
-Links only (titles + URLs).  
-Brief quotes or snippets if relevant to decision making. No page dumps.
-
-**CRITICAL**: When your research is complete, output the brief between these exact delimiters:
-
-```
----SCOUT_REPORT_START---
-(your full research brief here)
----SCOUT_REPORT_END---
-```
-
----
-
-## Example Output
-
-Here is an example of the expected output format:
-
----SCOUT_REPORT_START---
-# Research Brief: Best Rust JSON Parsing Libraries
-
-## Query
-What are the best JSON parsing libraries for Rust with streaming support?
-
-## Options
-
-### 1. **serde_json**
-- The standard JSON library for Rust
-- Pros: Mature, fast, excellent ecosystem integration
-- Cons: No built-in streaming for large files
-
-### 2. **simd-json**
-- SIMD-accelerated JSON parser
-- Pros: 2-4x faster than serde_json for large payloads
-- Cons: Requires mutable input buffer, x86-64 only
-
-## Trade-offs / Comparisons
-| Aspect | serde_json | simd-json |
-|--------|------------|----------|
-| Speed | Fast | Fastest |
-| Portability | All platforms | x86-64 |
-| Ease of use | Excellent | Good |
-
-## Recommendation
-Use **serde_json** for most cases. Consider **simd-json** only for performance-critical large JSON processing on x86-64.
-
-## Unknowns / Risks
-- simd-json API stability for newer versions
-- Memory usage differences at scale
-
-## Sources
-- https://docs.rs/serde_json
-- https://github.com/simd-lite/simd-json
----SCOUT_REPORT_END---
-
----
-
-## Strict Constraints
-
-- **No raw webpage text** beyond short quoted fragments only as necessary.
-- **No code dumps** beyond tiny illustrative snippets.
-- **No repo writes.**
-- **No follow-up questions.**
-
-If the research report would exceed one page, **rank and discard** lower-value material.
-
-If nothing useful exists, say so explicitly and back this up with evidence.
-
----
-
-## Research Style
-
-- Be pragmatic, not academic.
-- Prefer real-world usage, maturity, and sharp edges over novelty.
-- Treat hype skeptically.
-- Optimize for *your user* making a decision, not for completeness.
-
-You are allowed to say:
-> "This exists but is immature / fragile / not worth it."
-
----
-
-## Ephemerality
-
-Your output is **decision support**, not institutional knowledge.
-
-Do not assume it will be saved.
-Do not suggest documentation updates.
-Do not try to future-proof.
-
----
-
-## Success Criteria
-
-You succeed if:
-- The reader can decide what to try or ignore in under 5 minutes.
-- The brief is calm, bounded, and opinionated where justified.
-- No context bloat is introduced.
-- **The report is wrapped in the exact delimiters shown above.**
-
-If nothing meets the bar, saying so is OK.
-
----
-
-## WebDriver Usage
-
-You have access to WebDriver browser automation tools for web research.
-
-**How to use WebDriver:**
-1. Call `webdriver_start` to begin a browser session
-2. Use `webdriver_navigate` to go to URLs (search engines, documentation sites, etc.)
-3. Use all the standard webdriver DOM tools to scan and navigate within websites
-4. Use `webdriver_get_page_source` to save the HTML to a file and inspect with `read_file` for actual content, articles, code examples etc., **INSTEAD** of reading screenshots
-5. Call `webdriver_quit` when done
-
-**Best practices:**
-- Do NOT use Google, prefer Startpage, Brave Search, DuckDuckGo in that order.
-- For github or OSS repos, shallow-clone the repo (or download individual raw source files) and `read_file` or `shell` tools to analyze them instead of using screenshots
-- Save pages to the `tmp/` subdirectory (e.g., `tmp/search_results.html`), then parse the HTML to read content. Paginate so you are not reading huge chunks of HTML at once.

agents/solon.md

@@ -1,487 +0,0 @@
-SYSTEM PROMPT — "Solon" (Rulespec Authoring Agent)
-
-You are Solon: an interactive rulespec authoring agent.
-Your job is to help users create, refine, and validate invariant rules
-in `analysis/rulespec.yaml` — the machine-readable contract that governs
-what `write_envelope` verifies at plan completion.
-
-You are named for the Athenian lawgiver. You write precise, enforceable rules.
-
-------------------------------------------------------------
-PRIME DIRECTIVE
-
-You author **rulespec rules** — claims and predicates that define invariants
-over action envelopes. Every rule you write must be:
-
-1. Syntactically valid YAML conforming to the rulespec schema
-2. Semantically meaningful (tests something the user cares about)
-3. **Validated** — you MUST call `write_envelope` with a sample envelope
-   that exercises your rules before finishing
-
-You operate ONLY on `analysis/rulespec.yaml`. You do not modify source code,
-tests, build files, or any other configuration.
-
-The canonical schema reference is at `prompts/schemas/rulespec.schema.md`.
-
-------------------------------------------------------------
-WORKFLOW
-
-1. **Understand** — Ask the user what invariants they want to enforce.
-   What facts should agents produce? What properties must hold?
-
-2. **Read** — Load the current `analysis/rulespec.yaml` (if it exists)
-   to understand existing rules. Never duplicate or contradict them
-   without explicit user consent.
-
-3. **Author** — Write claims and predicates using the schema below.
-   Explain each rule to the user in plain language.
-
-4. **Validate** — Call `write_envelope` with a sample envelope that
-   should PASS all your new rules. Inspect the verification output.
-   If any rule fails, fix it and re-validate.
-
-5. **Confirm** — Show the user the final rulespec and verification results.
-
-Step 4 is NON-NEGOTIABLE. Never finish without validating.
-
-------------------------------------------------------------
-RULESPEC SCHEMA
-
-The file `analysis/rulespec.yaml` has two top-level arrays:
-
-```yaml
-claims:
-  - name: <claim_name>        # Unique identifier (referenced by predicates)
-    selector: <selector_path>  # Path into the action envelope
-
-predicates:
-  - claim: <claim_name>       # Must reference a defined claim
-    rule: <rule_type>          # One of the 12 predicate rules below
-    value: <expected_value>    # Required for most rules (optional for exists/not_exists)
-    source: task_prompt        # Either "task_prompt" or "memory"
-    notes: <explanation>       # Optional human-readable explanation
-    when:                      # Optional conditional trigger
-      claim: <claim_name>     # Must reference a defined claim
-      rule: <rule_type>       # Condition rule type
-      value: <value>          # Condition value (if needed)
-```
-
-------------------------------------------------------------
-SELECTOR SYNTAX
-
-Selectors navigate the envelope's fact structure using path notation:
-
-| Syntax | Meaning | Example |
-|--------|---------|--------|
-| `foo.bar` | Nested field access | `csv_importer.file` |
-| `foo[0]` | Array index (0-based) | `tests[0]` |
-| `foo[*].id` | Wildcard (all elements) | `items[*].name` |
-| `foo.bar.baz` | Deep nesting | `api.endpoints.count` |
-
-**IMPORTANT**: Selectors operate on the envelope's `facts` map directly.
-Do NOT prefix selectors with `facts.` — the system already unwraps the
-`facts` key. Write `my_feature.capabilities`, not `facts.my_feature.capabilities`.
-
-While selectors with a `facts.` prefix will work (there is a fallback),
-it is unnecessary and should be avoided for clarity.
-
-------------------------------------------------------------
-THE 12 PREDICATE RULES
-
-| Rule | Value Required | Value Type | What It Checks |
-|------|---------------|------------|----------------|
-| `exists` | No | — | Value is present and not null |
-| `not_exists` | No | — | Value is null or missing |
-| `equals` | Yes | any | Selected value exactly equals expected |
-| `contains` | Yes | any | Array contains element, or string contains substring |
-| `not_contains` | Yes | any | Negation of contains — value must NOT be present |
-| `any_of` | Yes | array | Value is one of the specified set |
-| `none_of` | Yes | array | Value is none of the specified set |
-| `greater_than` | Yes | number | Numeric value > expected |
-| `less_than` | Yes | number | Numeric value < expected |
-| `min_length` | Yes | number | Array has at least N elements |
-| `max_length` | Yes | number | Array has at most N elements |
-| `matches` | Yes | string | String value matches a regex pattern |
-
-### Rule Details & Examples
-
-**exists** — Assert a value is present (not null):
-```yaml
-claims:
-  - name: has_file
-    selector: my_feature.file
-predicates:
-  - claim: has_file
-    rule: exists
-    source: task_prompt
-    notes: Feature must specify its implementation file
-```
-
-**not_exists** — Assert a value is absent or null:
-```yaml
-claims:
-  - name: no_breaking
-    selector: breaking_changes
-predicates:
-  - claim: no_breaking
-    rule: not_exists
-    source: task_prompt
-    notes: No breaking changes allowed
-```
-
-**equals** — Exact value match:
-```yaml
-claims:
-  - name: api_breaking
-    selector: api_changes.breaking
-predicates:
-  - claim: api_breaking
-    rule: equals
-    value: false
-    source: task_prompt
-```
-
-**contains** — Element in array or substring in string:
-```yaml
-claims:
-  - name: capabilities
-    selector: csv_importer.capabilities
-predicates:
-  - claim: capabilities
-    rule: contains
-    value: handle_tsv
-    source: task_prompt
-    notes: Must support TSV format
-```
-
-**not_contains** — Element must NOT be in array or substring NOT in string:
-```yaml
-claims:
-  - name: capabilities
-    selector: csv_importer.capabilities
-predicates:
-  - claim: capabilities
-    rule: not_contains
-    value: deprecated_parser
-    source: task_prompt
-    notes: Must not use the deprecated parser
-```
-
-**any_of** — Value must be one of a set (value must be an array):
-```yaml
-claims:
-  - name: output_format
-    selector: feature.output_format
-predicates:
-  - claim: output_format
-    rule: any_of
-    value: [json, yaml, toml]
-    source: task_prompt
-    notes: Output must be a supported format
-```
-
-**none_of** — Value must NOT be any of a set (value must be an array):
-```yaml
-claims:
-  - name: output_format
-    selector: feature.output_format
-predicates:
-  - claim: output_format
-    rule: none_of
-    value: [xml, csv]
-    source: task_prompt
-    notes: XML and CSV are not supported
-```
-
-**greater_than / less_than** — Numeric comparisons:
-```yaml
-claims:
-  - name: test_count
-    selector: metrics.test_count
-predicates:
-  - claim: test_count
-    rule: greater_than
-    value: 0
-    source: task_prompt
-    notes: Must have at least one test
-```
-
-**min_length / max_length** — Array size bounds:
-```yaml
-claims:
-  - name: endpoints
-    selector: api.endpoints
-predicates:
-  - claim: endpoints
-    rule: min_length
-    value: 2
-    source: task_prompt
-    notes: API must expose at least 2 endpoints
-```
-
-**matches** — Regex pattern matching:
-```yaml
-claims:
-  - name: impl_file
-    selector: feature.file
-predicates:
-  - claim: impl_file
-    rule: matches
-    value: "^src/.*\\.rs$"
-    source: task_prompt
-    notes: Implementation must be a Rust source file
-```
-
-------------------------------------------------------------
-CONDITIONAL PREDICATES (`when`)
-
-Predicates can have an optional `when` condition. If the condition is
-**not met**, the predicate is **skipped** (vacuous pass) — it does NOT fail.
-
-This is useful for rules that only apply in certain contexts.
-
-### When Condition Structure
-
-```yaml
-when:
-  claim: <claim_name>     # Must reference a defined claim
-  rule: <rule_type>        # Any predicate rule type
-  value: <value>           # Optional, depends on rule
-```
-
-### When Examples
-
-```yaml
-# Only enforce endpoint count when there are breaking changes
-predicates:
-  - claim: api_endpoints
-    rule: min_length
-    value: 3
-    source: task_prompt
-    when:
-      claim: is_breaking
-      rule: equals
-      value: true
-    notes: Breaking changes must document all endpoints
-
-# Only check test coverage when tests exist
-predicates:
-  - claim: coverage_percent
-    rule: greater_than
-    value: 80
-    source: memory
-    when:
-      claim: has_tests
-      rule: exists
-
-# Only enforce format when feature is present
-predicates:
-  - claim: output_format
-    rule: any_of
-    value: [json, yaml]
-    source: task_prompt
-    when:
-      claim: has_output
-      rule: exists
-```
-
-```yaml
-# Only require reply threading when subject indicates a reply
-predicates:
-  - claim: reply_to_id
-    rule: exists
-    source: task_prompt
-    when:
-      claim: subject_line
-      rule: matches
-      value: "^Re: "
-    notes: Reply emails must include reply_to_message_id
-```
-
-------------------------------------------------------------
-NULL HANDLING
-
-Null values in the action envelope have specific semantics:
-
-- **`null` is treated as absent** — `exists` returns false, `not_exists` returns true
-- A fact with value `null` produces NO datalog facts (skipped entirely)
-- This is the correct way to assert explicit absence in envelopes
-
-```yaml
-# In the envelope:
-facts:
-  breaking_changes: null    # explicitly absent
-
-# In the rulespec — this passes:
-predicates:
-  - claim: no_breaking
-    rule: not_exists
-    source: task_prompt
-```
-
-| Envelope Value | `exists` | `not_exists` | `contains "x"` |
-|---------------|----------|-------------|----------------|
-| `null` | ❌ fail | ✅ pass | ❌ fail |
-| missing key | ❌ fail | ✅ pass | ❌ fail |
-| `""` (empty) | ✅ pass | ❌ fail | ❌ fail |
-| `[]` (empty) | ✅ pass | ❌ fail | ❌ fail |
-
-------------------------------------------------------------
-ACTION ENVELOPE FORMAT
-
-The action envelope is what agents produce via `write_envelope`.
-It contains facts about completed work. The YAML MUST have a
-top-level `facts:` key:
-
-```yaml
-facts:
-  feature_name:
-    capabilities: [cap_a, cap_b]
-    file: "src/feature.rs"
-    tests: ["test_a", "test_b"]
-  api_changes:
-    breaking: false
-    new_endpoints: ["/api/foo"]
-  breaking_changes: null    # null asserts explicit absence
-```
-
-**Critical**: The `facts:` wrapper is required. Without it, the envelope
-will be empty and all predicates will fail. This is the #1 mistake.
-
-------------------------------------------------------------
-VERIFICATION PIPELINE
-
-When `write_envelope` is called, the system:
-
-1. Parses the YAML into an `ActionEnvelope`
-2. Writes it to `.g3/sessions/<id>/envelope.yaml`
-3. Reads `analysis/rulespec.yaml` from the workspace
-4. Compiles claims into selectors, predicates into datalog rules
-5. Extracts facts from the envelope using selectors
-6. Evaluates each predicate against the extracted facts
-7. Reports pass/fail for each predicate
-
-The output shows ✅ for passing and ❌ for failing predicates,
-with the total count. Artifacts are written to the session directory:
-- `rulespec.compiled.dl` — the generated datalog program
-- `datalog_evaluation.txt` — full evaluation report
-
-------------------------------------------------------------
-VALIDATION STEP (MANDATORY)
-
-After writing or modifying `analysis/rulespec.yaml`, you MUST validate
-your rules by calling `write_envelope` with a sample envelope designed
-to exercise your rules.
-
-**How to validate:**
-
-1. Construct a sample envelope whose facts should make ALL your
-   predicates pass. Call `write_envelope` with it.
-
-2. Check the verification output. Every predicate should show ✅.
-
-3. If any predicate shows ❌, diagnose and fix either the rulespec
-   or the sample envelope, then re-validate.
-
-Example validation call:
-```
-write_envelope(facts: "
-facts:
-  csv_importer:
-    capabilities: [handle_headers, handle_tsv]
-    file: src/import/csv.rs
-    tests: [test_valid_csv, test_missing_column]
-  api_changes:
-    breaking: false
-  breaking_changes: null
-")
-```
-
-------------------------------------------------------------
-COMMON MISTAKES TO AVOID
-
-1. **Missing `facts:` key in envelope** — The envelope YAML must have
-   `facts:` as the top-level key. Raw YAML without it produces an
-   empty envelope and all predicates fail silently.
-
-2. **Using `facts.` prefix in selectors** — Selectors already operate
-   inside the facts map. Write `my_feature.file`, not `facts.my_feature.file`.
-
-3. **Predicate references unknown claim** — Every predicate's `claim`
-   field must match a defined claim's `name`. Typos cause compilation errors.
-
-4. **Missing `value` for rules that need it** — All rules except `exists`
-   and `not_exists` require a `value` field.
-
-5. **Duplicate claim names** — Each claim name must be unique.
-
-6. **Regex escaping** — In YAML, backslashes in regex patterns need
-   quoting. Use `"^src/.*\\.rs$"` (double-quoted with escaped backslash).
-
-7. **`any_of`/`none_of` value must be an array** — These rules require
-   the `value` field to be a YAML array, not a scalar.
-   Write `value: [json, yaml]`, not `value: json`.
-
-8. **Null is absent, not a string** — `null` in the envelope means the
-   value does not exist. `exists` will fail, `not_exists` will pass.
-   If you want to check for the literal string "null", the value must
-   be quoted: `"null"`.
-
-9. **`when` condition claim must be defined** — The `when.claim` field
-   must reference a claim defined in the `claims` array, just like
-   the predicate's own `claim` field.
-
-------------------------------------------------------------
-CREATING A RULESPEC FROM SCRATCH
-
-If `analysis/rulespec.yaml` does not exist yet:
-
-1. Create the `analysis/` directory if needed
-2. Start with a minimal rulespec:
-
-```yaml
-claims:
-  - name: feature_exists
-    selector: my_feature.file
-
-predicates:
-  - claim: feature_exists
-    rule: exists
-    source: task_prompt
-    notes: The feature must declare its implementation file
-```
-
-3. Validate immediately with `write_envelope`
-4. Iterate with the user to add more rules
-
-------------------------------------------------------------
-EXPLICIT BANS
-
-You MUST NOT:
-- Modify source code, tests, or build files
-- Write rules that are untestable or tautological
-- Skip the validation step
-- Delete existing rules without user confirmation
-- Write predicates that reference undefined claims
-
-------------------------------------------------------------
-SUCCESS CRITERIA
-
-Your output is successful when:
-- `analysis/rulespec.yaml` is valid YAML conforming to the schema
-- All claims have valid selectors
-- All predicates reference defined claims
-- All `when` conditions reference defined claims
-- A sample `write_envelope` call passes all predicates (✅)
-- The user understands what each rule enforces
-- Existing rules are preserved unless explicitly changed
-
-------------------------------------------------------------
-INTERACTIVE STYLE
-
-- Be conversational. Ask clarifying questions.
-- Explain rules in plain language before writing YAML.
-- Show the user what a passing envelope looks like.
-- When modifying existing rules, show a diff of changes.
-- If the user's request is ambiguous, propose alternatives.
-- Always end with a validated rulespec.

analysis/breaker/2025-02-05.md

@@ -1,142 +0,0 @@
-# Breaker Report: 2025-02-05
-
-> **Note**: Issue 1 below is now obsolete. The research skill was removed and replaced
-> with a first-class `research` tool in `crates/g3-core/src/tools/research.rs`.
-> The g3-research script no longer exists.
-
-Focused on changes in commits b6d2582..9443f933 (past 10 commits).
-
-## Issue 1: JSON Escaping Bug in g3-research Script (OBSOLETE)
-
-### Title
-`g3-research` produces invalid JSON when query contains actual newlines
-
-### Repro
-```bash
-# In skills/research/g3-research, the write_status function uses:
-escaped_query=$(echo -n "$query" | sed 's/\\/\\\\/g; s/"/\\"/g; s/\n/\\n/g')
-
-# Test with actual newlines:
-QUERY=$'What is\nthe best\nRust library?'
-escaped=$(echo -n "$QUERY" | sed 's/\\/\\\\/g; s/"/\\"/g; s/\n/\\n/g')
-echo "{\"query\": \"$escaped\"}" | python3 -m json.tool
-# Output: Invalid control character at: line 1 column 19 (char 18)
-```
-
-**Expected**: Valid JSON with `\n` escape sequences  
-**Actual**: Invalid JSON with literal newline characters
-
-### Diagnosis
-- **File**: `skills/research/g3-research:66`
-- **Root cause**: The sed pattern `s/\n/\\n/g` matches the literal two-character string `\n`, not actual newline characters. Sed processes line-by-line by default and doesn't see newlines in the pattern space.
-- **Triggering condition**: User query contains actual newline characters (e.g., from multi-line input or programmatic construction)
-- **Deterministic**: Yes
-
-### Impact
-- **Severity**: Incorrect behavior - `status.json` becomes unparseable
-- **Likelihood**: Uncommon but possible - queries are typically single-line, but multi-line queries from programmatic sources or copy-paste could trigger this
-
-### Fix
-Replace sed with perl which handles newlines correctly:
-```bash
-escaped_query=$(echo -n "$query" | perl -pe 's/\\/\\\\/g; s/"/\\"/g; s/\n/\\n/g')
-```
-
----
-
-## Issue 2: Embedded Skill Path Not Readable
-
-### Title
-Embedded skills have non-existent file paths that agents are instructed to `read_file`
-
-### Repro
-```
-# When no repo skills/ directory exists, embedded skills are loaded
-# The generated prompt contains:
-<skill>
-  <name>example-skill</name>
-  <description>...</description>
-  <location><embedded:example-skill>/SKILL.md</location>
-</skill>
-
-# The prompt instructs:
-"read the full skill file using `read_file` to get detailed instructions"
-
-# Agent attempts:
-read_file("<embedded:example-skill>/SKILL.md")
-# Result: File not found error
-```
-
-**Expected**: Agent can read skill documentation  
-**Actual**: File path doesn't exist on disk
-
-### Diagnosis
-- **File**: `crates/g3-core/src/skills/discovery.rs:97` - sets path to `<embedded:name>/SKILL.md`
-- **File**: `crates/g3-core/src/skills/prompt.rs:14-15` - instructs agent to use `read_file`
-- **Root cause**: Embedded skills use a synthetic path marker, but the prompt doesn't account for this
-- **Triggering condition**: User has no `skills/` directory in their repo (embedded skill not overridden)
-- **Deterministic**: Yes
-
-### Impact
-- **Severity**: Annoying - agent will fail to read skill docs and may hallucinate or ask for help
-- **Likelihood**: Common for users outside the g3 repo itself
-
-### Possible Fixes
-1. Include the full skill body in the prompt for embedded skills (increases prompt size)
-2. Add special handling in `read_file` for `<embedded:*>` paths
-3. Change prompt to say "skill instructions are below" for embedded skills and inline the body
-
----
-
-## Issue 3: Hardcoded 'main' Branch in SDLC Pipeline
-
-### Title
-`studio sdlc` assumes default branch is named 'main'
-
-### Repro
-```bash
-# In a repo where default branch is 'master':
-studio sdlc run
-
-# has_commits_on_branch runs:
-git rev-list --count main..sdlc/session-branch
-# Fails silently (returns Ok(false)) because 'main' doesn't exist
-
-# merge_to_main runs:
-git checkout main
-# Fails with "Failed to checkout main"
-```
-
-**Expected**: Works with any default branch name  
-**Actual**: Fails or behaves incorrectly on repos using 'master' or other branch names
-
-### Diagnosis
-- **File**: `crates/studio/src/main.rs:720` - `has_commits_on_branch()` hardcodes `main..{branch}`
-- **File**: `crates/studio/src/git.rs` - `merge_to_main()` hardcodes `checkout main`
-- **Root cause**: No detection of actual default branch name
-- **Triggering condition**: Repository uses 'master' or custom default branch
-- **Deterministic**: Yes
-
-### Impact
-- **Severity**: Incorrect behavior - merge fails or skipped incorrectly
-- **Likelihood**: Common - many repos still use 'master'
-
-### Fix
-Detect default branch:
-```bash
-git symbolic-ref refs/remotes/origin/HEAD | sed 's@^refs/remotes/origin/@@'
-# or
-git config --get init.defaultBranch
-```
-
----
-
-## Summary
-
-| # | Issue | Severity | Likelihood |
-|---|-------|----------|------------|
-| 1 | JSON escaping with newlines | Incorrect behavior | Uncommon |
-| 2 | Embedded skill path unreadable | Annoying | Common |
-| 3 | Hardcoded 'main' branch | Incorrect behavior | Common |
-
-All issues are deterministic and reproducible.

analysis/deps/graph.json

@@ -1,440 +0,0 @@
-{
-  "metadata": {
-    "generated_at": "2025-02-05T14:00:00Z",
-    "scope": "Changes in commits b6d2582..9443f933 (10 commits)",
-    "extraction_method": "Static analysis of Rust use/mod statements and Cargo.toml",
-    "tool_version": "euler-manual-1.0"
-  },
-  "nodes": {
-    "crates": [
-      {
-        "id": "g3-core",
-        "type": "crate",
-        "path": "crates/g3-core",
-        "changed_in_scope": true
-      },
-      {
-        "id": "g3-cli",
-        "type": "crate",
-        "path": "crates/g3-cli",
-        "changed_in_scope": true
-      },
-      {
-        "id": "g3-config",
-        "type": "crate",
-        "path": "crates/g3-config",
-        "changed_in_scope": true
-      },
-      {
-        "id": "studio",
-        "type": "crate",
-        "path": "crates/studio",
-        "changed_in_scope": true
-      },
-      {
-        "id": "g3-providers",
-        "type": "crate",
-        "path": "crates/g3-providers",
-        "changed_in_scope": false
-      },
-      {
-        "id": "g3-execution",
-        "type": "crate",
-        "path": "crates/g3-execution",
-        "changed_in_scope": false
-      },
-      {
-        "id": "g3-computer-control",
-        "type": "crate",
-        "path": "crates/g3-computer-control",
-        "changed_in_scope": false
-      },
-      {
-        "id": "g3-planner",
-        "type": "crate",
-        "path": "crates/g3-planner",
-        "changed_in_scope": false
-      }
-    ],
-    "files": [
-      {
-        "id": "g3-core/src/skills/mod.rs",
-        "type": "module",
-        "crate": "g3-core",
-        "status": "added"
-      },
-      {
-        "id": "g3-core/src/skills/parser.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "added"
-      },
-      {
-        "id": "g3-core/src/skills/discovery.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "added"
-      },
-      {
-        "id": "g3-core/src/skills/prompt.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "added"
-      },
-      {
-        "id": "g3-core/src/skills/embedded.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "added"
-      },
-      {
-        "id": "g3-core/src/skills/extraction.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "added"
-      },
-      {
-        "id": "g3-core/src/prompts.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "modified"
-      },
-      {
-        "id": "g3-core/src/lib.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "modified"
-      },
-      {
-        "id": "g3-core/src/tool_definitions.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "modified"
-      },
-      {
-        "id": "g3-core/src/tool_dispatch.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "modified"
-      },
-      {
-        "id": "g3-core/src/tools/mod.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "modified"
-      },
-      {
-        "id": "g3-core/src/tools/executor.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "modified"
-      },
-      {
-        "id": "g3-core/src/tools/acd.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "modified"
-      },
-      {
-        "id": "g3-core/src/pending_research.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "deleted"
-      },
-      {
-        "id": "g3-core/src/tools/research.rs",
-        "type": "file",
-        "crate": "g3-core",
-        "status": "deleted"
-      },
-      {
-        "id": "g3-cli/src/lib.rs",
-        "type": "file",
-        "crate": "g3-cli",
-        "status": "modified"
-      },
-      {
-        "id": "g3-cli/src/project_files.rs",
-        "type": "file",
-        "crate": "g3-cli",
-        "status": "modified"
-      },
-      {
-        "id": "g3-cli/src/agent_mode.rs",
-        "type": "file",
-        "crate": "g3-cli",
-        "status": "modified"
-      },
-      {
-        "id": "g3-cli/src/interactive.rs",
-        "type": "file",
-        "crate": "g3-cli",
-        "status": "modified"
-      },
-      {
-        "id": "g3-cli/src/commands.rs",
-        "type": "file",
-        "crate": "g3-cli",
-        "status": "modified"
-      },
-      {
-        "id": "g3-cli/src/g3_status.rs",
-        "type": "file",
-        "crate": "g3-cli",
-        "status": "modified"
-      },
-      {
-        "id": "g3-cli/src/ui_writer_impl.rs",
-        "type": "file",
-        "crate": "g3-cli",
-        "status": "modified"
-      },
-      {
-        "id": "g3-cli/src/accumulative.rs",
-        "type": "file",
-        "crate": "g3-cli",
-        "status": "modified"
-      },
-      {
-        "id": "g3-config/src/lib.rs",
-        "type": "file",
-        "crate": "g3-config",
-        "status": "modified"
-      },
-      {
-        "id": "studio/src/main.rs",
-        "type": "file",
-        "crate": "studio",
-        "status": "modified"
-      },
-      {
-        "id": "studio/src/sdlc.rs",
-        "type": "file",
-        "crate": "studio",
-        "status": "modified"
-      },
-      {
-        "id": "skills/research/SKILL.md",
-        "type": "skill",
-        "crate": null,
-        "status": "added"
-      },
-      {
-        "id": "skills/research/g3-research",
-        "type": "script",
-        "crate": null,
-        "status": "added"
-      },
-      {
-        "id": "prompts/system/native.md",
-        "type": "prompt",
-        "crate": null,
-        "status": "modified"
-      }
-    ]
-  },
-  "edges": {
-    "crate_dependencies": [
-      {
-        "from": "g3-cli",
-        "to": "g3-core",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-cli/Cargo.toml: g3-core = { path = \"../g3-core\" }"
-      },
-      {
-        "from": "g3-cli",
-        "to": "g3-config",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-cli/Cargo.toml: g3-config = { path = \"../g3-config\" }"
-      },
-      {
-        "from": "g3-cli",
-        "to": "g3-providers",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-cli/Cargo.toml: g3-providers = { path = \"../g3-providers\" }"
-      },
-      {
-        "from": "g3-cli",
-        "to": "g3-planner",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-cli/Cargo.toml: g3-planner = { path = \"../g3-planner\" }"
-      },
-      {
-        "from": "g3-cli",
-        "to": "g3-computer-control",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-cli/Cargo.toml: g3-computer-control = { path = \"../g3-computer-control\" }"
-      },
-      {
-        "from": "g3-core",
-        "to": "g3-config",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-core/Cargo.toml: g3-config = { path = \"../g3-config\" }"
-      },
-      {
-        "from": "g3-core",
-        "to": "g3-providers",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-core/Cargo.toml: g3-providers = { path = \"../g3-providers\" }"
-      },
-      {
-        "from": "g3-core",
-        "to": "g3-execution",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-core/Cargo.toml: g3-execution = { path = \"../g3-execution\" }"
-      },
-      {
-        "from": "g3-core",
-        "to": "g3-computer-control",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-core/Cargo.toml: g3-computer-control = { path = \"../g3-computer-control\" }"
-      },
-      {
-        "from": "g3-planner",
-        "to": "g3-core",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-planner/Cargo.toml: g3-core = { path = \"../g3-core\" }"
-      },
-      {
-        "from": "g3-planner",
-        "to": "g3-config",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-planner/Cargo.toml: g3-config = { path = \"../g3-config\" }"
-      },
-      {
-        "from": "g3-planner",
-        "to": "g3-providers",
-        "type": "cargo_dependency",
-        "evidence": "crates/g3-planner/Cargo.toml: g3-providers = { path = \"../g3-providers\" }"
-      }
-    ],
-    "file_imports": [
-      {
-        "from": "g3-core/src/skills/discovery.rs",
-        "to": "g3-core/src/skills/parser.rs",
-        "type": "use_super",
-        "evidence": "use super::parser::Skill"
-      },
-      {
-        "from": "g3-core/src/skills/discovery.rs",
-        "to": "g3-core/src/skills/embedded.rs",
-        "type": "use_super",
-        "evidence": "use super::embedded::get_embedded_skills"
-      },
-      {
-        "from": "g3-core/src/skills/prompt.rs",
-        "to": "g3-core/src/skills/parser.rs",
-        "type": "use_super",
-        "evidence": "use super::parser::Skill"
-      },
-      {
-        "from": "g3-core/src/skills/extraction.rs",
-        "to": "g3-core/src/skills/embedded.rs",
-        "type": "use_super",
-        "evidence": "use super::embedded::get_embedded_skill"
-      },
-      {
-        "from": "g3-core/src/skills/mod.rs",
-        "to": "g3-core/src/skills/parser.rs",
-        "type": "mod_declaration",
-        "evidence": "mod parser"
-      },
-      {
-        "from": "g3-core/src/skills/mod.rs",
-        "to": "g3-core/src/skills/discovery.rs",
-        "type": "mod_declaration",
-        "evidence": "mod discovery"
-      },
-      {
-        "from": "g3-core/src/skills/mod.rs",
-        "to": "g3-core/src/skills/prompt.rs",
-        "type": "mod_declaration",
-        "evidence": "mod prompt"
-      },
-      {
-        "from": "g3-core/src/skills/mod.rs",
-        "to": "g3-core/src/skills/embedded.rs",
-        "type": "mod_declaration",
-        "evidence": "mod embedded"
-      },
-      {
-        "from": "g3-core/src/skills/mod.rs",
-        "to": "g3-core/src/skills/extraction.rs",
-        "type": "mod_declaration",
-        "evidence": "pub mod extraction"
-      },
-      {
-        "from": "g3-core/src/prompts.rs",
-        "to": "g3-core/src/skills/mod.rs",
-        "type": "use_crate",
-        "evidence": "use crate::skills::{Skill, generate_skills_prompt}"
-      },
-      {
-        "from": "g3-core/src/lib.rs",
-        "to": "g3-core/src/skills/mod.rs",
-        "type": "pub_mod",
-        "evidence": "pub mod skills"
-      },
-      {
-        "from": "g3-core/src/lib.rs",
-        "to": "g3-core/src/prompts.rs",
-        "type": "mod_declaration",
-        "evidence": "mod prompts"
-      },
-      {
-        "from": "g3-cli/src/project_files.rs",
-        "to": "g3-core/src/skills/mod.rs",
-        "type": "use_external",
-        "evidence": "use g3_core::{discover_skills, generate_skills_prompt, Skill}"
-      },
-      {
-        "from": "g3-cli/src/project_files.rs",
-        "to": "g3-config/src/lib.rs",
-        "type": "use_external",
-        "evidence": "use g3_config::SkillsConfig"
-      },
-      {
-        "from": "g3-cli/src/agent_mode.rs",
-        "to": "g3-cli/src/project_files.rs",
-        "type": "use_crate",
-        "evidence": "use crate::project_files::{..., discover_and_format_skills, ...}"
-      },
-      {
-        "from": "g3-cli/src/lib.rs",
-        "to": "g3-cli/src/project_files.rs",
-        "type": "use_crate",
-        "evidence": "use project_files::{..., discover_and_format_skills, ...}"
-      },
-      {
-        "from": "g3-core/src/skills/embedded.rs",
-        "to": "skills/research/SKILL.md",
-        "type": "include_str",
-        "evidence": "include_str!(\"../../../../skills/research/SKILL.md\")"
-      },
-      {
-        "from": "g3-core/src/skills/embedded.rs",
-        "to": "skills/research/g3-research",
-        "type": "include_str",
-        "evidence": "include_str!(\"../../../../skills/research/g3-research\")"
-      },
-      {
-        "from": "studio/src/main.rs",
-        "to": "studio/src/sdlc.rs",
-        "type": "mod_declaration",
-        "evidence": "mod sdlc"
-      },
-      {
-        "from": "studio/src/main.rs",
-        "to": "studio/src/git.rs",
-        "type": "mod_declaration",
-        "evidence": "mod git"
-      },
-      {
-        "from": "studio/src/main.rs",
-        "to": "studio/src/session.rs",
-        "type": "mod_declaration",
-        "evidence": "mod session"
-      }
-    ]
-  }
-}

analysis/deps/graph.summary.md

@@ -1,105 +0,0 @@
-# Dependency Graph Summary
-
-**Scope**: Changes in commits `b6d2582..9443f933` (10 commits)  
-**Generated**: 2025-02-05
-
-## Metrics
-
-| Metric | Count |
-|--------|-------|
-| Crates (total) | 8 |
-| Crates (changed) | 4 |
-| Files (changed) | 29 |
-| Files (added) | 8 |
-| Files (deleted) | 2 |
-| Files (modified) | 19 |
-| Crate-level edges | 12 |
-| File-level edges | 21 |
-
-## Changed Crates
-
-| Crate | Path | Role |
-|-------|------|------|
-| g3-core | crates/g3-core | Core engine, skills module added |
-| g3-cli | crates/g3-cli | CLI interface, skills integration |
-| g3-config | crates/g3-config | Configuration, SkillsConfig added |
-| studio | crates/studio | Multi-agent workspace, SDLC changes |
-
-## Entrypoints
-
-| Entrypoint | Type | Evidence |
-|------------|------|----------|
-| g3-cli/src/lib.rs | Library root | `pub fn run()` |
-| studio/src/main.rs | Binary | `fn main()` |
-| g3-core/src/lib.rs | Library root | Re-exports skills module |
-
-## Top Fan-In Nodes (most depended upon)
-
-| Node | Fan-In | Dependents |
-|------|--------|------------|
-| g3-core/src/skills/parser.rs | 3 | discovery.rs, prompt.rs, mod.rs |
-| g3-core/src/skills/embedded.rs | 3 | discovery.rs, extraction.rs, mod.rs |
-| g3-core/src/skills/mod.rs | 3 | lib.rs, prompts.rs, project_files.rs |
-| g3-config/src/lib.rs | 2 | g3-core (crate), g3-cli (crate) |
-| g3-cli/src/project_files.rs | 2 | lib.rs, agent_mode.rs |
-
-## Top Fan-Out Nodes (most dependencies)
-
-| Node | Fan-Out | Dependencies |
-|------|---------|-------------|
-| g3-cli (crate) | 5 | g3-core, g3-config, g3-providers, g3-planner, g3-computer-control |
-| g3-core/src/skills/mod.rs | 5 | parser.rs, discovery.rs, prompt.rs, embedded.rs, extraction.rs |
-| g3-core/src/skills/discovery.rs | 2 | parser.rs, embedded.rs |
-| g3-cli/src/project_files.rs | 2 | g3-core::skills, g3-config::SkillsConfig |
-| studio/src/main.rs | 3 | sdlc.rs, git.rs, session.rs |
-
-## Major Structural Changes
-
-### Added: Skills Module (`g3-core/src/skills/`)
-
-New module implementing Agent Skills specification:
-
-```
-g3-core/src/skills/
-├── mod.rs        # Module root, re-exports
-├── parser.rs     # SKILL.md YAML frontmatter parser
-├── discovery.rs  # Skill directory scanning
-├── prompt.rs     # XML prompt generation
-├── embedded.rs   # Compile-time embedded skills
-└── extraction.rs # Script extraction to .g3/bin/
-```
-
-**Internal dependency flow**:
-```
-mod.rs
-  ├── parser.rs (Skill struct)
-  ├── discovery.rs → parser.rs, embedded.rs
-  ├── prompt.rs → parser.rs
-  ├── embedded.rs (standalone)
-  └── extraction.rs → embedded.rs
-```
-
-### Removed: Research Tool (hardcoded)
-
-- `g3-core/src/pending_research.rs` (540 lines deleted)
-- `g3-core/src/tools/research.rs` (710 lines deleted)
-
-### Added: Research Skill (external)
-
-- `skills/research/SKILL.md` (144 lines)
-- `skills/research/g3-research` (338 lines, bash script)
-
-Research functionality moved from hardcoded tool to external skill.
-
-### Modified: SDLC Pipeline
-
-- State storage moved from `analysis/sdlc/` to `.g3/sdlc/`
-- Added merge-to-main on successful completion
-- Worktree preserved on failure for debugging
-
-## Extraction Limitations
-
-- Dynamic imports not detected (none expected in Rust)
-- Test-only dependencies not distinguished from production
-- Conditional compilation (`#[cfg(...)]`) not analyzed
-- External crate dependencies (from crates.io) not enumerated

analysis/deps/hotspots.md

@@ -1,101 +0,0 @@
-# Coupling Hotspots
-
-**Scope**: Changes in commits `b6d2582..9443f933` (10 commits)
-
-## High Fan-In Files (Most Depended Upon)
-
-Files that many other files depend on. Changes here have wide impact.
-
-| File | Fan-In | Dependents | Risk |
-|------|--------|------------|------|
-| `g3-core/src/skills/parser.rs` | 3 | discovery.rs, prompt.rs, mod.rs | Medium |
-| `g3-core/src/skills/embedded.rs` | 3 | discovery.rs, extraction.rs, mod.rs | Medium |
-| `g3-core/src/skills/mod.rs` | 3 | lib.rs, prompts.rs, project_files.rs (cross-crate) | High |
-| `g3-config/src/lib.rs` | 2 | g3-core, g3-cli (cross-crate) | High |
-| `g3-cli/src/project_files.rs` | 2 | lib.rs, agent_mode.rs | Medium |
-
-### Analysis
-
-**`g3-core/src/skills/mod.rs`** (Fan-In: 3, Cross-Crate: Yes)
-- Re-exports `Skill`, `discover_skills`, `generate_skills_prompt`, `EmbeddedSkill`
-- Used by `g3-core/src/lib.rs` (re-export), `g3-core/src/prompts.rs`, `g3-cli/src/project_files.rs`
-- **Evidence**: `pub use parser::Skill`, `pub use discovery::discover_skills`
-- **Impact**: API changes affect both g3-core internals and g3-cli
-
-**`g3-core/src/skills/parser.rs`** (Fan-In: 3, Cross-Crate: No)
-- Defines `Skill` struct used throughout skills module
-- **Evidence**: `use super::parser::Skill` in discovery.rs, prompt.rs
-- **Impact**: Struct field changes ripple through entire skills subsystem
-
-**`g3-config/src/lib.rs`** (Fan-In: 2, Cross-Crate: Yes)
-- Added `SkillsConfig` struct
-- **Evidence**: `use g3_config::SkillsConfig` in project_files.rs
-- **Impact**: Config schema changes affect CLI startup
-
-## High Fan-Out Files (Most Dependencies)
-
-Files that depend on many others. Complex, potentially fragile.
-
-| File | Fan-Out | Dependencies | Risk |
-|------|---------|--------------|------|
-| `g3-core/src/skills/mod.rs` | 5 | parser, discovery, prompt, embedded, extraction | Medium |
-| `g3-core/src/skills/discovery.rs` | 2 | parser.rs, embedded.rs | Low |
-| `g3-cli/src/project_files.rs` | 2 | g3-core::skills, g3-config | Medium |
-| `studio/src/main.rs` | 3 | sdlc.rs, git.rs, session.rs | Low |
-
-### Analysis
-
-**`g3-core/src/skills/mod.rs`** (Fan-Out: 5)
-- Module root that coordinates all skills submodules
-- **Evidence**: `mod parser; mod discovery; mod prompt; mod embedded; pub mod extraction`
-- **Impact**: Central coordination point, but each submodule is relatively independent
-
-**`g3-cli/src/project_files.rs`** (Fan-Out: 2, Cross-Crate: Yes)
-- Bridges g3-core skills and g3-config
-- **Evidence**: `use g3_core::{discover_skills, ...}`, `use g3_config::SkillsConfig`
-- **Impact**: Integration point for skills feature in CLI
-
-## Cross-Crate Coupling
-
-Edges that cross crate boundaries. Higher coordination cost for changes.
-
-| From | To | Type | Evidence |
-|------|----|------|----------|
-| g3-cli/src/project_files.rs | g3-core::skills | use_external | `use g3_core::{discover_skills, generate_skills_prompt, Skill}` |
-| g3-cli/src/project_files.rs | g3-config | use_external | `use g3_config::SkillsConfig` |
-| g3-core/src/lib.rs | g3-core::skills | pub_use | `pub use skills::{Skill, discover_skills, generate_skills_prompt}` |
-
-## Compile-Time Coupling (include_str!)
-
-Files embedded at compile time. Build breaks if missing.
-
-| Source | Embedded File | Evidence |
-|--------|---------------|----------|
-| g3-core/src/skills/embedded.rs | skills/research/SKILL.md | `include_str!("../../../../skills/research/SKILL.md")` |
-| g3-core/src/skills/embedded.rs | skills/research/g3-research | `include_str!("../../../../skills/research/g3-research")` |
-
-**Impact**: 
-- Moving or renaming `skills/research/` breaks g3-core compilation
-- Content changes require g3-core recompilation
-- Relative path `../../../../` is fragile to directory restructuring
-
-## Deleted Code Impact
-
-Removed files and their former dependents.
-
-| Deleted File | Lines | Former Dependents |
-|--------------|-------|-------------------|
-| g3-core/src/pending_research.rs | 540 | g3-core/src/lib.rs, tools/research.rs |
-| g3-core/src/tools/research.rs | 710 | tool_dispatch.rs, tools/mod.rs |
-
-**Impact**: 
-- Research functionality moved to external skill
-- `tool_dispatch.rs` and `tools/mod.rs` modified to remove research tool dispatch
-- CLI commands related to research removed from `commands.rs`
-
-## Recommendations for Monitoring
-
-1. **`g3-core/src/skills/mod.rs`**: Watch for API surface changes
-2. **`g3-config/src/lib.rs`**: Watch for `SkillsConfig` schema changes
-3. **`skills/research/`**: Watch for path changes (compile-time dependency)
-4. **`g3-cli/src/project_files.rs`**: Integration point, test after skills changes

analysis/deps/layers.observed.md

@@ -1,120 +0,0 @@
-# Observed Layering
-
-**Scope**: Changes in commits `b6d2582..9443f933` (10 commits)
-
-## Layer Structure
-
-Observed from dependency direction (higher layers depend on lower):
-
-```
-┌─────────────────────────────────────────────────────────────┐
-│  Layer 4: Binaries / Entry Points                           │
-│  ┌─────────────┐  ┌─────────────┐                          │
-│  │  g3-cli     │  │   studio    │                          │
-│  └─────────────┘  └─────────────┘                          │
-└─────────────────────────────────────────────────────────────┘
-                          │
-                          ▼
-┌─────────────────────────────────────────────────────────────┐
-│  Layer 3: Orchestration                                     │
-│  ┌─────────────┐                                           │
-│  │ g3-planner  │                                           │
-│  └─────────────┘                                           │
-└─────────────────────────────────────────────────────────────┘
-                          │
-                          ▼
-┌─────────────────────────────────────────────────────────────┐
-│  Layer 2: Core Engine                                       │
-│  ┌─────────────────────────────────────────────────────┐   │
-│  │                     g3-core                          │   │
-│  │  ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐   │   │
-│  │  │ skills  │ │ tools   │ │ prompts │ │ context │   │   │
-│  │  └─────────┘ └─────────┘ └─────────┘ └─────────┘   │   │
-│  └─────────────────────────────────────────────────────┘   │
-└─────────────────────────────────────────────────────────────┘
-                          │
-                          ▼
-┌─────────────────────────────────────────────────────────────┐
-│  Layer 1: Infrastructure                                    │
-│  ┌─────────────┐ ┌─────────────┐ ┌───────────────────────┐ │
-│  │ g3-config   │ │g3-providers │ │ g3-computer-control   │ │
-│  └─────────────┘ └─────────────┘ └───────────────────────┘ │
-│  ┌─────────────┐                                           │
-│  │g3-execution │                                           │
-│  └─────────────┘                                           │
-└─────────────────────────────────────────────────────────────┘
-                          │
-                          ▼
-┌─────────────────────────────────────────────────────────────┐
-│  Layer 0: External Assets                                   │
-│  ┌─────────────────────────────────────────────────────┐   │
-│  │  skills/research/  (SKILL.md, g3-research script)   │   │
-│  └─────────────────────────────────────────────────────┘   │
-│  ┌─────────────────────────────────────────────────────┐   │
-│  │  prompts/system/   (native.md, etc.)                │   │
-│  └─────────────────────────────────────────────────────┘   │
-└─────────────────────────────────────────────────────────────┘
-```
-
-## Layer Assignments (Changed Files)
-
-| Layer | File | Evidence |
-|-------|------|----------|
-| 4 | g3-cli/src/lib.rs | Entry point, depends on g3-core |
-| 4 | g3-cli/src/agent_mode.rs | Uses g3-core::Agent |
-| 4 | g3-cli/src/interactive.rs | Uses g3-core::Agent |
-| 4 | g3-cli/src/project_files.rs | Uses g3-core::skills, g3-config |
-| 4 | studio/src/main.rs | Binary entry point |
-| 4 | studio/src/sdlc.rs | Orchestrates g3 agents |
-| 2 | g3-core/src/lib.rs | Core library root |
-| 2 | g3-core/src/skills/mod.rs | Skills subsystem |
-| 2 | g3-core/src/skills/parser.rs | SKILL.md parsing |
-| 2 | g3-core/src/skills/discovery.rs | Skill directory scanning |
-| 2 | g3-core/src/skills/prompt.rs | XML prompt generation |
-| 2 | g3-core/src/skills/embedded.rs | Compile-time embedding |
-| 2 | g3-core/src/skills/extraction.rs | Script extraction |
-| 2 | g3-core/src/prompts.rs | System prompt generation |
-| 2 | g3-core/src/tool_definitions.rs | Tool schema definitions |
-| 2 | g3-core/src/tool_dispatch.rs | Tool routing |
-| 1 | g3-config/src/lib.rs | Configuration structs |
-| 0 | skills/research/SKILL.md | External skill definition |
-| 0 | skills/research/g3-research | External skill script |
-| 0 | prompts/system/native.md | System prompt template |
-
-## Layer Violations
-
-**None detected** in the changed files.
-
-All dependencies flow downward (higher layer → lower layer).
-
-## Skills Module Internal Layering
-
-Within `g3-core/src/skills/`:
-
-```
-┌───────────────────────────────────────┐
-│  mod.rs (coordinator, re-exports)     │  Layer 2.3
-└───────────────────────────────────────┘
-              │
-              ▼
-┌───────────────────────────────────────┐
-│  discovery.rs, prompt.rs, extraction  │  Layer 2.2
-│  (use parser.rs and/or embedded.rs)   │
-└───────────────────────────────────────┘
-              │
-              ▼
-┌───────────────────────────────────────┐
-│  parser.rs, embedded.rs (leaf nodes)  │  Layer 2.1
-│  (no internal dependencies)           │
-└───────────────────────────────────────┘
-```
-
-## Derivation Method
-
-Layers derived mechanically from:
-1. Cargo.toml `[dependencies]` sections
-2. `use` statement analysis
-3. `mod` declaration hierarchy
-4. `include_str!` compile-time references
-
-No semantic interpretation applied.

analysis/deps/limitations.md

@@ -1,66 +0,0 @@
-# Analysis Limitations
-
-**Scope**: Changes in commits `b6d2582..9443f933` (10 commits)
-
-## What Could Not Be Observed
-
-| Limitation | Impact | Mitigation |
-|------------|--------|------------|
-| Runtime dispatch | Tool dispatch uses string matching, not static imports | Analyzed `tool_dispatch.rs` manually |
-| Conditional compilation | `#[cfg(...)]` blocks not analyzed | May miss platform-specific deps |
-| Macro-generated code | `include_str!` detected, other macros not | Limited to explicit macros |
-| External crate deps | crates.io dependencies not enumerated | Focus on workspace crates only |
-| Test-only imports | Not distinguished from production | May overcount dependencies |
-| Dynamic skill loading | Skills loaded at runtime from filesystem | Only compile-time embedded skills tracked |
-
-## What Was Inferred
-
-| Inference | Confidence | Rationale |
-|-----------|------------|----------|
-| Layer assignments | High | Based on Cargo.toml dependency direction |
-| Fan-in/fan-out counts | High | Direct count of `use`/`mod` statements |
-| Cross-crate edges | High | Explicit `use external_crate::` statements |
-| Deleted file impact | Medium | Based on git diff, former imports not verified |
-
-## Potential Invalidators
-
-Conditions that would invalidate this analysis:
-
-1. **Feature flags**: If `Cargo.toml` uses `[features]` to conditionally include dependencies, the graph may be incomplete for non-default configurations.
-
-2. **Workspace-level dependencies**: The `[workspace.dependencies]` section in root `Cargo.toml` was not analyzed for version constraints.
-
-3. **Build scripts**: `build.rs` files may generate code or modify dependencies at build time.
-
-4. **Proc macros**: Procedural macros in dependencies may generate additional imports not visible in source.
-
-5. **Path aliases**: If `Cargo.toml` uses `[patch]` or path aliases, actual dependency resolution may differ.
-
-## Scope Boundaries
-
-- **Included**: All files changed in commits `b6d2582..9443f933`
-- **Excluded**: Unchanged files, even if they depend on changed files
-- **Excluded**: Files outside `crates/` and `skills/` directories (except prompts/)
-
-## Tool Versions
-
-| Tool | Version | Purpose |
-|------|---------|--------|
-| git | system | Commit range, diff |
-| rg (ripgrep) | system | Import pattern matching |
-| Manual analysis | - | Cargo.toml parsing |
-
-## Reproducibility
-
-To reproduce this analysis:
-
-```bash
-# Get changed files
-git diff --name-only 9443f933~10..9443f933
-
-# Extract imports from Rust files
-rg "^use |^mod |use g3_|use crate::" crates/*/src/*.rs
-
-# Check Cargo.toml dependencies
-cat crates/*/Cargo.toml | grep -A20 "\[dependencies\]"
-```

analysis/deps/sccs.md

@@ -1,61 +0,0 @@
-# Strongly Connected Components (Cycles)
-
-**Scope**: Changes in commits `b6d2582..9443f933` (10 commits)
-
-## Summary
-
-| Metric | Count |
-|--------|-------|
-| SCCs with >1 node | 0 |
-| Trivial SCCs (single node) | 29 |
-
-## Analysis
-
-**No dependency cycles detected** in the changed files.
-
-The skills module has a clean DAG structure:
-
-```
-mod.rs (root)
-    │
-    ├── parser.rs (leaf - no internal deps)
-    │       ▲
-    │       │
-    ├── discovery.rs ──┬──► parser.rs
-    │                  └──► embedded.rs
-    │
-    ├── prompt.rs ─────────► parser.rs
-    │
-    ├── embedded.rs (leaf - no internal deps)
-    │       ▲
-    │       │
-    └── extraction.rs ─────► embedded.rs
-```
-
-## Crate-Level Cycles
-
-No cycles at crate level. Dependency direction:
-
-```
-g3-cli ──► g3-core ──► g3-config
-   │           │
-   │           └──► g3-providers
-   │           └──► g3-execution
-   │           └──► g3-computer-control
-   │
-   └──► g3-config
-   └──► g3-providers
-   └──► g3-planner ──► g3-core (creates potential for cycle)
-```
-
-**Note**: `g3-planner` depends on `g3-core`, and `g3-cli` depends on both. This is not a cycle but creates a diamond dependency pattern.
-
-## Verification Method
-
-Cycles detected by analyzing `use` statements and `mod` declarations:
-- `use super::*` → parent module
-- `use crate::*` → crate root
-- `mod name` → child module
-- `use external_crate::*` → cross-crate
-
-No bidirectional edges found within the changed file set.

analysis/memory.md

@@ -1,414 +0,0 @@
-# Workspace Memory
-> Updated: 2026-03-18T03:59:01Z | Size: 25.2k chars
-
-### Remember Tool Wiring
-- `crates/g3-core/src/tools/memory.rs` [0..5686]
-  - `get_memory_path()` [486] - resolves `analysis/memory.md`
-  - `execute_remember()` [1066] - tool handler
-  - `merge_memory()` [2324] - merges new notes into existing
-- `crates/g3-core/src/tool_definitions.rs` [956..] - remember tool in `create_core_tools()`
-- `crates/g3-core/src/tool_dispatch.rs` [670] - dispatch case
-- `crates/g3-core/src/prompts.rs` [4200..6500] - Workspace Memory prompt section
-- `crates/g3-cli/src/project_files.rs` - `read_workspace_memory()` loads `analysis/memory.md`
-
-### Context Window & Compaction
-- `crates/g3-core/src/context_window.rs` [0..43282]
-  - `ThinResult` [765] - scope, before/after %, chars_saved
-  - `ContextWindow` [2220] - token tracking, message history
-  - `add_message_with_tokens()` [3171] - preserves messages with `tool_calls` even if content empty
-  - `estimate_message_tokens()` [7695] - sums content + tool_calls[].input tokens (chars/3 * 1.1 + 20 overhead)
-  - `should_compact()` [8954] - threshold check (80%)
-  - `reset_with_summary()` [10685] - compact history to summary
-  - `reset_with_summary_and_stub()` [11120] - ACD integration
-  - `extract_preserved_messages()` [13199] - strips `tool_calls` from last assistant to prevent orphaned `tool_use`
-  - `thin_context()` [15038] - replace large results with file refs
-- `crates/g3-core/src/compaction.rs` [0..11404]
-  - `CompactionResult`, `CompactionConfig` - result/config structs
-  - `perform_compaction()` - unified for force_compact() and auto-compaction
-  - `calculate_capped_summary_tokens()`, `should_disable_thinking()`
-  - `build_summary_messages()`, `apply_summary_fallback_sequence()`
-  - ACD integration [195..240] - creates fragment+stub during compaction
-- `crates/g3-core/src/lib.rs`
-  - `force_compact()` [47902]
-  - `stream_completion_with_tools()` [85389] - main agent loop
-
-### Session Storage & Continuation
-- `crates/g3-core/src/session_continuation.rs` [0..22907]
-  - `SessionContinuation` [1024]
-  - `save_continuation()` [5581]
-  - `load_continuation()` [6428]
-- `crates/g3-core/src/paths.rs` [0..5498]
-  - `get_session_logs_dir()` [2434]
-  - `get_thinned_dir()` [3060]
-  - `get_fragments_dir()` [3295] - `.g3/sessions/<id>/fragments/`
-  - `get_session_file()` [3517]
-- `crates/g3-core/src/session.rs` - session logging utilities
-
-### Tool System
-- `crates/g3-core/src/tool_definitions.rs` [0..15391]
-  - `ToolConfig` [381]
-  - `create_tool_definitions()` [742]
-  - `create_core_tools()` [956]
-- `crates/g3-core/src/tool_dispatch.rs` [0..3983] - `dispatch_tool()` [670] routing
-
-### CLI Module Structure
-- `crates/g3-cli/src/lib.rs` [0..9309] - `run()` [1242], mode dispatch, config loading
-- `crates/g3-cli/src/cli_args.rs` [0..6043] - `Cli` [1374] struct (clap)
-- `crates/g3-cli/src/autonomous.rs` [0..25630] - `run_autonomous()` [638], coach-player loop
-- `crates/g3-cli/src/agent_mode.rs` [0..13558] - `run_agent_mode()` [1000]
-- `crates/g3-cli/src/accumulative.rs` [0..12006] - `run_accumulative_mode()` [796]
-- `crates/g3-cli/src/interactive.rs` [0..19222] - `run_interactive()` [3809], REPL
-- `crates/g3-cli/src/task_execution.rs` [0..5520] - `execute_task_with_retry()` [1069]
-- `crates/g3-cli/src/commands.rs` [0..20115] - `/help`, `/compact`, `/thinnify`, `/fragments`, `/rehydrate`
-- `crates/g3-cli/src/utils.rs` [0..6154] - `display_context_progress()`, `setup_workspace_directory()`, `load_config_with_cli_overrides()`
-- `crates/g3-cli/src/display.rs` [0..12573] - `format_workspace_path()` [286], `LoadedContent`, `print_loaded_status()`
-
-### Auto-Memory System
-- `crates/g3-core/src/lib.rs`
-  - `tool_calls_this_turn` [5272] - tracks tools per turn
-  - `set_auto_memory()` [64643] - enable/disable
-  - `send_auto_memory_reminder()` [72800] - MEMORY CHECKPOINT prompt
-  - `execute_tool_in_dir()` [132582] - records tool calls
-- `crates/g3-core/src/prompts.rs` [3800..4500] - Memory Format in system prompt
-- `crates/g3-cli/src/lib.rs` - `--auto-memory` CLI flag
-
-### Streaming Markdown Formatter
-- `crates/g3-cli/src/streaming_markdown.rs` [0..37669]
-  - `process_in_code_block()` [17159] - detects closing fence
-  - `format_header()` [21339] - headers with inline formatting
-  - `emit_code_block()` [27134] - joins buffer, highlights code
-  - `flush_incomplete()` [28434] - handles unclosed blocks at stream end
-- `crates/g3-cli/tests/streaming_markdown_test.rs` - header formatting tests
-- **Gotcha**: closing ``` without trailing newline must be detected in `flush_incomplete()`
-
-### Retry Infrastructure
-- `crates/g3-core/src/retry.rs` [0..11865] - `execute_with_retry()`, `retry_operation()`, `RetryConfig`, `RetryResult`
-- `crates/g3-cli/src/task_execution.rs` - `execute_task_with_retry()`
-
-### UI Abstraction Layer
-- `crates/g3-core/src/ui_writer.rs` [0..8007] - `UiWriter` trait [211], `NullUiWriter` [6538], `print_thin_result()` [1136]
-- `crates/g3-cli/src/ui_writer_impl.rs` [0..14000] - `ConsoleUiWriter`, `print_tool_compact()`
-- `crates/g3-cli/src/simple_output.rs` [0..1200] - `SimpleOutput` helper
-
-### Feedback Extraction
-- `crates/g3-core/src/feedback_extraction.rs` [0..22455] - `extract_coach_feedback()`, `try_extract_from_session_log()`, `try_extract_from_native_tool_call()`
-- `crates/g3-cli/src/coach_feedback.rs` [0..4025] - `extract_from_logs()` for coach-player loop
-
-### Streaming Utilities & State
-- `crates/g3-core/src/streaming.rs` [0..27241]
-  - `MAX_ITERATIONS` [419] - constant (400)
-  - `StreamingState` [499] - cross-iteration: full_response, first_token_time, iteration_count
-  - `ToolOutputFormat` [1606] - enum: SelfHandled, Compact(String), Regular
-  - `format_tool_result_summary()` [1743], `is_compact_tool()` [2635], `format_compact_tool_summary()` [3179]
-  - `IterationState` [5061] - per-iteration: parser, current_response, tool_executed
-  - `log_stream_error()` [8017], `truncate_for_display()` [10887], `truncate_line()` [11247]
-  - `is_connection_error()` [21620]
-
-### Background Process Management
-- `crates/g3-core/src/background_process.rs` [0..9048]
-  - `BackgroundProcessManager` [1466], `start()` [2601], `list()` [5527], `get()` [5731], `is_running()` [5934], `remove()` [6462]
-- No `stop()` method — use shell `kill <pid>`
-
-### Unified Diff Application
-- `crates/g3-core/src/utils.rs` [5000..15000] - `apply_unified_diff_to_string()`, `parse_unified_diff_hunks()`
-- Handles multi-hunk diffs, CRLF normalization, range constraints
-
-### Error Classification
-- `crates/g3-core/src/error_handling.rs` [0..19454]
-  - `ErrorType` [5206], `RecoverableError` [5465] (enum), `classify_error()` [5972]
-- Priority: rate limit > network > server > busy > timeout > token limit > context length
-- **Gotcha**: "Connection timeout" → NetworkError (not Timeout) due to "connection" keyword priority
-
-### CLI Metrics
-- `crates/g3-cli/src/metrics.rs` [0..5416] - `TurnMetrics`, `format_elapsed_time()`, `generate_turn_histogram()`
-
-### ACD (Aggressive Context Dehydration)
-Saves conversation fragments to disk, replaces with stubs.
-
-- `crates/g3-core/src/acd.rs` [0..22830]
-  - `Fragment` - `new()`, `save()`, `load()`, `generate_stub()`, `list_fragments()`, `get_latest_fragment_id()`
-- `crates/g3-core/src/tools/acd.rs` [0..8500] - `execute_rehydrate()` tool
-- `crates/g3-cli/src/lib.rs` - `--acd` flag; `/fragments`, `/rehydrate` commands
-- **Fragment JSON**: `fragment_id`, `created_at`, `messages`, `message_count`, `user_message_count`, `assistant_message_count`, `tool_call_summary`, `estimated_tokens`, `topics`, `preceding_fragment_id`
-
-### UTF-8 Safe String Slicing
-Rust `&s[..n]` panics on multi-byte chars (emoji, CJK) if sliced mid-character.
-**Pattern**: `s.char_indices().nth(n).map(|(i,_)| i).unwrap_or(s.len())`
-**Danger zones**: Display truncation, ACD stubs, user input, non-ASCII text.
-
-### Studio - Multi-Agent Workspace Manager
-- `crates/studio/src/main.rs` [0..12500] - `cmd_run()`, `cmd_status()`, `cmd_accept()`, `cmd_discard()`, `extract_session_summary()`
-- `crates/studio/src/session.rs` - `Session`, `SessionStatus`
-- `crates/studio/src/git.rs` - `GitWorktree` for isolated agent sessions
-- **Session log**: `<worktree>/.g3/sessions/<session_id>/session.json`
-- **Fields**: `context_window.{conversation_history, percentage_used, total_tokens, used_tokens}`, `session_id`, `status`, `timestamp`
-
-### Racket Code Search Support
-- `crates/g3-core/src/code_search/searcher.rs`
-  - Racket parser [~45] - `tree_sitter_racket::LANGUAGE`
-  - Extensions [~90] - `.rkt`, `.rktl`, `.rktd` → "racket"
-
-### Language-Specific Prompt Injection
-Auto-detects languages and injects toolchain guidance.
-
-- `crates/g3-cli/src/language_prompts.rs`
-  - `LANGUAGE_PROMPTS` - (lang_name, extensions, prompt_content)
-  - `AGENT_LANGUAGE_PROMPTS` - (agent_name, lang_name, prompt_content)
-  - `detect_languages()` - scans workspace
-  - `scan_directory_for_extensions()` - recursive, depth 2, skips hidden/vendor
-  - `get_language_prompts_for_workspace()`, `get_agent_language_prompts_for_workspace()`
-- `crates/g3-cli/src/agent_mode.rs` - appends agent-specific prompts
-- `prompts/langs/` - language prompt files
-- **To add language**: Create `prompts/langs/<lang>.md`, add to `LANGUAGE_PROMPTS`
-- **To add agent+lang**: Create `prompts/langs/<agent>.<lang>.md`, add to `AGENT_LANGUAGE_PROMPTS`
-
-### MockProvider for Testing
-- `crates/g3-providers/src/mock.rs`
-  - `MockProvider` [220..320] - response queue, request tracking
-  - `MockResponse` [35..200] - configurable chunks and usage
-  - `scenarios` module [410..480] - `text_only_response()`, `multi_turn()`, `tool_then_response()`
-- `crates/g3-core/tests/mock_provider_integration_test.rs` - integration tests
-- **Usage**: `MockProvider::new().with_response(MockResponse::text("Hello!"))`
-
-### G3 Status Message Formatting
-- `crates/g3-cli/src/g3_status.rs`
-  - `Status` [12] - enum: Done, Failed, Error, Custom, Resolved, Insufficient, NoChanges
-  - `G3Status` [44] - static methods for "g3:" prefixed messages
-  - `progress()` [48], `done()` [72], `failed()` [81], `thin_result()` [236]
-
-### Prompt Cache Statistics
-- `crates/g3-providers/src/lib.rs` - `Usage.cache_creation_tokens` [6780], `cache_read_tokens` [6929]
-- `crates/g3-providers/src/anthropic.rs` - parses `cache_creation_input_tokens`, `cache_read_input_tokens`
-- `crates/g3-providers/src/openai.rs` - parses `prompt_tokens_details.cached_tokens`
-- `crates/g3-core/src/lib.rs` - `CacheStats` [3066]; `Agent.cache_stats`
-- `crates/g3-core/src/stats.rs` [189..230] - `format_cache_stats()` with hit rate metrics
-
-### Embedded Provider (Local LLM)
-Local inference via llama-cpp-rs with Metal acceleration.
-
-- `crates/g3-providers/src/embedded.rs`
-  - `EmbeddedProvider` [22..85] - session, model_name, max_tokens, temperature, context_length
-  - `new()` [26..85] - tilde expansion, auto-downloads Qwen if missing
-  - `format_messages()` [87..175] - converts to prompt string (Qwen/Mistral/Llama templates)
-  - `get_stop_sequences()` [280..340] - model-specific stop tokens
-  - `stream()` [560..780] - via spawn_blocking + mpsc
-
-### Chat Template Formats
-| Model | Start Token | End Token |
-|-------|-------------|----------|
-| Qwen | `<\|im_start\|>role\n` | `<\|im_end\|>` |
-| GLM-4 | `[gMASK]<sop><\|role\|>\n` | `<\|endoftext\|>` |
-| Mistral | `<s>[INST]` | `[/INST]` |
-| Llama | `<<SYS>>` | `<</SYS>>` |
-
-### Recommended GGUF Models
-| Model | Size | Use Case |
-|-------|------|----------|
-| GLM-4-9B-Q8_0 | ~10GB | Fast, capable |
-| GLM-4-32B-Q6_K_L | ~27GB | Top tier coding/reasoning |
-| Qwen3-4B-Q4_K_M | ~2.3GB | Small, rivals 72B |
-
-**Download**: `huggingface-cli download <repo> --include "<file>" --local-dir ~/.g3/models/`
-
-**Config**:
-```toml
-[providers.embedded.glm4]
-model_path = "~/.g3/models/THUDM_GLM-4-32B-0414-Q6_K_L.gguf"
-model_type = "glm4"
-context_length = 32768
-max_tokens = 4096
-gpu_layers = 99
-```
-
-### Agent Skills System
-Portable skill packages with SKILL.md + optional scripts per Agent Skills spec (agentskills.io).
-
-- `crates/g3-core/src/skills/mod.rs` [0..1501] - exports: `Skill`, `discover_skills`, `generate_skills_prompt`
-- `crates/g3-core/src/skills/parser.rs` [0..10750]
-  - `Skill` [389] - name, description, metadata, body, path
-  - `Skill::parse()` [1632] - parses SKILL.md with YAML frontmatter
-  - `validate_name()` [4970] - 1-64 chars, lowercase+hyphens
-- `crates/g3-core/src/skills/discovery.rs` [0..12921]
-  - `discover_skills()` [1266] - scans 5 locations: embedded → global → extra → workspace → repo
-  - `load_embedded_skills()` [3263] - synthetic path `<embedded:name>/SKILL.md`
-- `crates/g3-core/src/skills/embedded.rs` [0..1674]
-  - `EmbeddedSkill` [574] - name, skill_md
-  - `EMBEDDED_SKILLS` [944] - static array (currently empty)
-- `crates/g3-core/src/skills/prompt.rs` [0..5628]
-  - `generate_skills_prompt()` [397] - generates `<available_skills>` XML
-- `crates/g3-config/src/lib.rs` [180..200] - `SkillsConfig` (enabled, extra_paths)
-- `crates/g3-cli/src/project_files.rs` - `discover_and_format_skills()`
-
-**Skill Locations** (priority: later overrides earlier):
-1. Embedded (compiled in)
-2. `~/.g3/skills/` (global)
-3. Config extra_paths
-4. `.g3/skills/` (workspace)
-5. `skills/` (repo root)
-
-**SKILL.md Format**:
-```yaml
----
-name: skill-name          # Required: 1-64 chars, lowercase + hyphens
-description: What it does # Required: 1-1024 chars
-license: Apache-2.0       # Optional
-compatibility: Requires X # Optional
----
-# Instructions...
-```
-
-### Research Tool (First-Class)
-Async web research via background scout agent.
-
-- `crates/g3-core/src/pending_research.rs` [0..18348]
-  - `ResearchStatus` [682] - Pending/Complete/Failed
-  - `ResearchTask` [1273] - task state
-  - `PendingResearchManager` [2906] - thread-safe tracking with Arc<RwLock>
-  - `with_notifications()` [3749] - broadcast channel for interactive mode
-  - `register()` [5069], `complete()` [5480], `fail()` [6419], `get()` [7344], `list_pending()` [7806], `take_completed()` [8952]
-- `crates/g3-core/src/tools/research.rs` [0..17060]
-  - `CONTEXT_ERROR_PATTERNS` [929] - detects context window exhaustion
-  - `execute_research()` [1644] - spawns scout agent in background tokio task
-  - `execute_research_status()` [7540] - check pending/completed
-  - `extract_report()` [10694], `strip_ansi_codes()` [13148]
-- `crates/g3-core/src/lib.rs`
-  - `inject_completed_research()` [31375] - injects results as user messages
-  - `enable_research_notifications()` [33459] - for interactive mode
-- **Tools**: `research` (async, returns research_id), `research_status` (check pending)
-
-### Plan Mode
-Structured task planning with cognitive forcing — requires happy/negative/boundary checks.
-
-- `crates/g3-core/src/tools/plan.rs` [0..49798]
-  - `PlanState` [1044] - enum: Todo, Doing, Done, Blocked
-  - `Checks` [2823] - happy, negative[], boundary[]
-  - `PlanItem` [4021] - id, description, state, touches, checks, evidence, notes
-  - `Plan` [6498] - plan_id, revision, approved_revision, items[]
-  - `EvidenceType` [9578] - CodeLocation, TestReference, Unknown
-  - `VerificationStatus` [10133] - Verified, Warning, Error, Skipped
-  - `parse_evidence()` [12712] - parses `file:line-line` or `file::test_name`
-  - `verify_code_location()` [14888] - checks file exists, lines in range
-  - `verify_test_reference()` [16733] - checks test file, searches for fn
-  - `get_plan_path()` [18655] - `.g3/sessions/<id>/plan.g3.md`
-  - `read_plan()` [18818], `write_plan()` [19277] - YAML in markdown
-  - `plan_verify()` [21978] - verifies evidence when complete; checks envelope existence
-  - `format_verification_results()` [23395] - takes `working_dir: Option<&Path>` as third param
-  - `execute_plan_read()` [25881], `execute_plan_write()` [27233], `execute_plan_approve()` [30651]
-- `crates/g3-core/src/tool_definitions.rs` [263..330] - plan_read, plan_write, plan_approve
-- `crates/g3-core/src/prompts.rs` [21..130] - SHARED_PLAN_SECTION
-- **Tool names**: `plan_read`, `plan_write`, `plan_approve` (underscores, not dots)
-- **Evidence formats**: `src/foo.rs:42-118`, `src/foo.rs:42`, `tests/foo.rs::test_bar`
-
-### Invariants System (Rulespec & Envelope)
-Machine-readable invariants for Plan Mode verification. Rulespec read from `analysis/rulespec.yaml` (checked-in).
-
-- `crates/g3-core/src/tools/invariants.rs` [0..73975]
-  - `Claim` [2024] - name + selector
-  - `PredicateRule` [3009] - Contains, Equals, Exists, NotExists, GreaterThan, LessThan, MinLength, MaxLength, Matches
-  - `Predicate` [5617] - claim, rule, value, source, notes
-  - `Rulespec` [8734] - claims[] + predicates[]
-  - `ActionEnvelope` [11203] - facts HashMap
-  - `Selector` [12900] - XPath-like: `foo.bar`, `foo[0]`, `foo[*]`
-  - `read_rulespec()` [29472] - takes `&Path` (working_dir)
-  - `evaluate_rulespec()` [32056] - evaluates against envelope
-
-### Write Envelope Tool
-- `crates/g3-core/src/tools/envelope.rs` [0..23347]
-  - `execute_write_envelope()` [8764] - parses YAML facts, writes envelope.yaml, calls verify_envelope()
-  - `verify_envelope()` [11705] - compiles rulespec on-the-fly, extracts facts, runs datalog, writes `.dl` + `datalog_evaluation.txt` (shadow mode)
-- `crates/g3-core/src/tool_definitions.rs` [266..282] - write_envelope tool definition
-- `crates/g3-core/src/tool_dispatch.rs` - write_envelope dispatch case
-- **Workflow**: `write_envelope` → `verify_envelope()` → datalog shadow, then `plan_write(done)` → `plan_verify()` → checks envelope exists
-
-### Datalog Invariant Verification
-- `crates/g3-core/src/tools/datalog.rs` [0..80172]
-  - `CompiledPredicate` [1681] - id, claim_name, selector, rule, expected_value, source, notes
-  - `CompiledRulespec` [2728] - plan_id, compiled_at_revision, predicates, claims
-  - `compile_rulespec()` [3588] - validates selectors, builds claim lookup
-  - `Fact` [6741] - claim_name, value
-  - `extract_facts()` [7057] - uses Selector to navigate envelope YAML; fallback wraps in `facts:` if selector has `facts.` prefix
-  - `extract_values_recursive()` [8478] - handles arrays/objects/scalars, adds __length facts
-  - `DatalogPredicateResult` [10308], `DatalogExecutionResult` [10862]
-  - `execute_rules()` [11627] - builds fact lookup, uses datafrog Iteration; when conditions delegate to `evaluate_predicate_datalog()`
-  - `evaluate_predicate_datalog()` [14872] - handles all 9 PredicateRule types
-  - `escape_datalog_string()` [23990], `format_datalog_program()` [24582] - Soufflé-style .dl output
-  - `format_datalog_results()` [31136] - formats for shadow mode display
-- **Relations**: `claim_value(claim, value)`, `claim_length(claim, length)`, `predicate_pass(id)`, `predicate_fail(id)`
-
-### Solon Agent (Rulespec Authoring)
-- `agents/solon.md` - interactive rulespec authoring agent prompt
-- `crates/g3-cli/src/embedded_agents.rs` [551] - 9 embedded agents: breaker, carmack, euler, fowler, hopper, huffman, lamport, scout, solon
-- **Usage**: `g3 --agent solon`
-
-### Structured Tool Call Messages
-Native tool calls stored as structured `MessageToolCall` objects, not inline JSON text.
-
-- `crates/g3-providers/src/lib.rs` [0..17486]
-  - `MessageToolCall` [2894] - id, name, input
-  - `Message` [3014] - `tool_calls: Vec<MessageToolCall>`, `tool_result_id: Option<String>`
-- `crates/g3-providers/src/anthropic.rs` [0..74631]
-  - `convert_messages()` [8642] - emits `tool_use`/`tool_result` blocks for structured tool calls
-  - `strip_orphaned_tool_use()` [14737] - defense-in-depth: strips orphaned `tool_use` blocks with no matching `tool_result`
-  - `ToolResultContent` [46268] - enum (Text | Blocks) for structured content
-  - `ToolResultBlock` [46650] - enum (Image, Text) inside tool_result; images from read_image nested here, not as top-level blocks
-- `crates/g3-core/src/lib.rs` - `ToolCall.id` [2516] field from native providers
-- `crates/g3-core/src/streaming_parser.rs` [0..29244] - `process_chunk()` [10449] preserves tool call `id`
-- **Gotcha**: Images in tool result messages must be nested inside `tool_result.content` array, not as top-level `Image` blocks (Anthropic API rejects mixed top-level Image+ToolResult)
-
-### Tool Call Token Tracking
-- `crates/g3-core/src/context_window.rs` - `estimate_message_tokens()` [7695] accounts for `tool_calls[].input`
-- Token formula: content_tokens + per-tool (input_chars/3 * 1.1 + 20 overhead)
-- **Gotcha**: Without this, tool input JSON is invisible to tracker → compaction never triggers → API 400
-
-### Studio SDLC Pipeline
-Orchestrates 7 agents in sequence for codebase maintenance.
-
-- `crates/studio/src/sdlc.rs`
-  - `PIPELINE_STAGES` [28..62] - euler → breaker → hopper → fowler → carmack → lamport → huffman
-  - `Stage` [18..26], `StageStatus` [65..80] - Pending, Running, Complete, Failed, Skipped
-  - `PipelineState` [108..140] - run_id, stages[], commit_cursor, session_id
-  - `display_pipeline()` [354..390] - box display with status icons
-- `crates/studio/src/main.rs`
-  - `cmd_sdlc_run()` [540..655] - orchestrates pipeline, merges on completion
-  - `has_commits_on_branch()` [715..728] - counts commits ahead of main
-- `crates/studio/src/git.rs` - `merge_to_main()` (hardcodes 'main')
-- **State**: `.g3/sdlc/pipeline.json`
-- **CLI**: `studio sdlc run [-c N]`, `studio sdlc status`, `studio sdlc reset`
-
-### Terminal Width Responsive Output
-Tool output responsive to terminal width — no line wrapping, 4-char right margin.
-
-- `crates/g3-cli/src/terminal_width.rs`
-  - `get_terminal_width()` [21..28] - usable width (terminal - 4), min 40, default 80
-  - `clip_line()` [33..44] - clips with "…", UTF-8 safe
-  - `compress_path()` [53..96] - preserves filename, truncates dirs from left
-  - `compress_command()` [101..103] - clips from right
-  - `available_width_after_prefix()` [115..117]
-- `crates/g3-cli/src/ui_writer_impl.rs`
-  - `print_tool_output_header()` [293..410] - uses compress_path/compress_command
-  - `update_tool_output_line()` [407..445], `print_tool_output_line()` [447..454] - clip_line()
-  - `print_tool_compact()` [475..635] - width-aware compact display
-
-### Plan Approval Gate (Non-Destructive + Baseline-Aware)
-- `crates/g3-core/src/tools/plan.rs` [973..983] - `ApprovalGateResult` enum: `Allowed`, `Blocked { message }`, `NotGitRepo` — no `reverted_files` field
-- `crates/g3-core/src/tools/plan.rs` [985..1003] - `get_dirty_files()` - returns `HashSet<String>` of dirty file paths from `git status --porcelain`
-- `crates/g3-core/src/tools/plan.rs` [1005..1098] - `check_plan_approval_gate(session_id, working_dir, baseline_dirty)` - warn-only, never reverts/deletes files, excludes baseline dirty files
-- `crates/g3-core/src/lib.rs` [170..171] - `baseline_dirty_files: HashSet<String>` field on Agent
-- `crates/g3-core/src/lib.rs` [1675..1686] - `set_plan_mode(enabled, working_dir)` - captures baseline on enable, clears on disable
-- **Key invariant**: The approval gate NEVER deletes or reverts files. It only warns.
-- **Key invariant**: Pre-existing dirty files (captured at plan mode start) are excluded from gate checks.
-
-### Context Window Calibration (Token Drift Fix)
-- `crates/g3-core/src/context_window.rs` [159..189] - `update_usage_from_response()` now calibrates `used_tokens` from API `prompt_tokens` (ground truth). When `prompt_tokens > 0`, snaps `used_tokens` to it. When 0, leaves unchanged (heuristic fallback).
-- `crates/g3-core/src/context_window.rs` [93..100] - No more 1% safety buffer. `total_tokens = raw` (was `raw * 0.99`).
-- `crates/g3-core/src/context_window.rs` [222..250] - `estimate_message_tokens()` now adds: +4 per-message overhead, +30 per tool_use block (was 20), +15 per tool_result message.
-- `crates/g3-core/src/lib.rs` [2232..2241] - `ensure_context_capacity()` called inside streaming loop for iteration > 1 (catches post-tool-execution growth).
-- **Root cause**: Heuristic token estimation drifted ~48% over 809 messages / 388 tool calls (136k estimated vs 201k actual). API `prompt_tokens` is ground truth.
-
-### Context Window Calibration (Token Drift Fix) - CORRECTED
-- `crates/g3-core/src/context_window.rs` [168..189] - `update_usage_from_response()` calibrates `used_tokens` from API `prompt_tokens` (ground truth). When `prompt_tokens > 0`, snaps `used_tokens` to it. When 0, leaves unchanged (heuristic fallback).
-- `crates/g3-core/src/lib.rs` [2316..2319] - Calibration call placed **inline** during streaming (when usage chunk arrives in `chunk.usage`), NOT after the streaming loop. Critical because text-only responses take an early return path that bypasses post-loop code.
-- `crates/g3-core/src/lib.rs` [2892..2898] - Post-loop code only handles fallback (no-usage) case now.
-- `crates/g3-core/src/context_window.rs` [87..93] - 1% safety buffer IS still in place (`total_tokens * 0.99`). Left as safety net between calibration points.
-- **Root cause of display bug**: (1) `update_usage_from_response` never calibrated `used_tokens`, only `cumulative_tokens`. (2) `execute_single_task` had mock usage with hardcoded `prompt_tokens: 100`. (3) Post-loop usage update was bypassed by early returns in text-only response paths.
-- **Key streaming flow**: For text-only responses (most common in interactive mode), `chunk.finished` triggers an early `return Ok(self.finalize_streaming_turn(...))` that bypasses all post-loop code. Calibration MUST happen inline when `chunk.usage` arrives.

config.coach-player.example.toml

@@ -1,73 +1,24 @@
-# g3 Configuration Example - Coach/Player Mode
-#
-# This configuration demonstrates using different providers for coach and player
-# roles in autonomous mode. The coach reviews code while the player implements.
-
 [providers]
-# Default provider used when no specific provider is specified
-default_provider = "anthropic.default"
+default_provider = "databricks"
+# Specify different providers for coach and player in autonomous mode
+coach = "databricks"    # Provider for coach (code reviewer) - can be more powerful/expensive
+player = "anthropic"    # Provider for player (code implementer) - can be faster/cheaper
 
-# Coach uses a model optimized for code review and analysis
-coach = "anthropic.coach"
+[providers.databricks]
+host = "https://your-workspace.cloud.databricks.com"
+# token = "your-databricks-token"  # Optional - will use OAuth if not provided
+model = "databricks-claude-sonnet-4"
+max_tokens = 4096
+temperature = 0.1
+use_oauth = true
 
-# Player uses a model optimized for code generation
-player = "anthropic.player"
-
-# Optional: Use a specialized model for planning mode
-# planner = "anthropic.planner"
-
-# Default Anthropic configuration
-[providers.anthropic.default]
+[providers.anthropic]
 api_key = "your-anthropic-api-key"
-model = "claude-sonnet-4-5"
-max_tokens = 64000
-temperature = 0.2
-
-# Coach configuration - focused on careful analysis
-[providers.anthropic.coach]
-api_key = "your-anthropic-api-key"
-model = "claude-sonnet-4-5"
-max_tokens = 32000
-temperature = 0.1  # Lower temperature for more consistent reviews
-
-# Player configuration - focused on code generation
-[providers.anthropic.player]
-api_key = "your-anthropic-api-key"
-model = "claude-sonnet-4-5"
-max_tokens = 64000
-temperature = 0.3  # Slightly higher for more creative implementations
-
-# Optional: Planner configuration with extended thinking
-# [providers.anthropic.planner]
-# api_key = "your-anthropic-api-key"
-# model = "claude-opus-4-5"
-# max_tokens = 64000
-# thinking_budget_tokens = 16000  # Enable extended thinking for planning
-
-# Example: Using Databricks for one of the roles
-# [providers.databricks.default]
-# host = "https://your-workspace.cloud.databricks.com"
-# model = "databricks-claude-sonnet-4"
-# max_tokens = 4096
-# temperature = 0.1
-# use_oauth = true
+model = "claude-3-haiku-20240307"  # Using a faster model for player
+max_tokens = 4096
+temperature = 0.3  # Slightly higher temperature for more creative implementations
 
 [agent]
-fallback_default_max_tokens = 8192
+max_context_length = 8192
 enable_streaming = true
 timeout_seconds = 60
-max_retry_attempts = 3
-autonomous_max_retry_attempts = 6
-allow_multiple_tool_calls = true
-
-[computer_control]
-enabled = false
-require_confirmation = true
-max_actions_per_second = 5
-
-[webdriver]
-enabled = false
-safari_port = 4444
-
-[macax]
-enabled = false

config.example.toml

@@ -1,111 +1,25 @@
-# g3 Configuration Example
-#
-# Most settings have sensible defaults. A minimal config only needs:
-#
-#   [providers]
-#   default_provider = "anthropic.default"
-#
-#   [providers.anthropic.default]
-#   api_key = "your-api-key"
-#   model = "claude-sonnet-4-5"
-#
-# Everything else below is optional.
-
 [providers]
-default_provider = "anthropic.default"
+default_provider = "databricks"
+# Optional: Specify different providers for coach and player in autonomous mode
+# If not specified, will use default_provider for both
+# coach = "databricks"    # Provider for coach (code reviewer)
+# player = "anthropic"    # Provider for player (code implementer)
+# Note: Make sure the specified providers are configured below
 
-# Optional: Specify different providers for each mode
-# If not specified, these fall back to default_provider
-# planner = "anthropic.planner"   # Provider for planning mode
-# coach = "anthropic.default"     # Provider for coach in autonomous mode
-# player = "anthropic.default"    # Provider for player in autonomous mode
+[providers.databricks]
+host = "https://your-workspace.cloud.databricks.com"
+# token = "your-databricks-token"  # Optional - will use OAuth if not provided
+model = "databricks-claude-sonnet-4"
+max_tokens = 4096
+temperature = 0.1
+use_oauth = true
 
-[providers.anthropic.default]
-api_key = "your-anthropic-api-key"
-model = "claude-sonnet-4-5"
-# max_tokens = 64000              # Optional (default: provider's max)
-# temperature = 0.3               # Optional
-# cache_config = "ephemeral"      # Optional: Enable prompt caching
-# enable_1m_context = true        # Optional: Enable 1M context (costs extra)
-# thinking_budget_tokens = 10000  # Optional: Enable extended thinking mode
+[agent]
+max_context_length = 8192
+enable_streaming = true
+timeout_seconds = 60
 
-# Example: A separate config for planning mode with a more capable model
-# [providers.anthropic.planner]
-# api_key = "your-anthropic-api-key"
-# model = "claude-opus-4-5"
-# thinking_budget_tokens = 16000
-
-# Databricks provider example
-# [providers.databricks.default]
-# host = "https://your-workspace.cloud.databricks.com"
-# model = "databricks-claude-sonnet-4"
-# use_oauth = true
-
-# OpenAI provider example
-# [providers.openai.default]
-# api_key = "your-openai-api-key"
-# model = "gpt-4-turbo"
-
-# OpenAI-compatible providers (OpenRouter, Groq, etc.)
-# [providers.openai_compatible.openrouter]
-# api_key = "your-openrouter-api-key"
-# model = "anthropic/claude-3.5-sonnet"
-# base_url = "https://openrouter.ai/api/v1"
-
-# =============================================================================
-# Embedded providers (local models via llama.cpp with Metal acceleration)
-# =============================================================================
-# Download models from Hugging Face:
-#   huggingface-cli download bartowski/THUDM_GLM-4-32B-0414-GGUF \
-#     --include "THUDM_GLM-4-32B-0414-Q6_K_L.gguf" --local-dir ~/.g3/models/
-#
-# GLM-4 32B - Top-tier local model for coding/reasoning (context_length auto-detected from GGUF)
-# [providers.embedded.glm4]
-# model_path = "~/.g3/models/THUDM_GLM-4-32B-0414-Q6_K_L.gguf"
-# model_type = "glm4"            # Required: glm4, qwen, mistral, llama, codellama
-# context_length = 32768         # Optional: auto-detected from GGUF (GLM-4 = 32K)
-# max_tokens = 4096              # Optional: defaults to min(4096, context/4)
-# temperature = 0.1
-# gpu_layers = 99                # Use all GPU layers on Apple Silicon
-# threads = 8
-
-# GLM-4 9B - Smaller but very capable (minimal config - most settings auto-detected)
-# [providers.embedded.glm4-9b]
-# model_path = "~/.g3/models/THUDM_GLM-4-9B-0414-Q8_0.gguf"
-# model_type = "glm4"
-# gpu_layers = 99                # Optional but recommended for Apple Silicon
-
-# Qwen3 4B - Small but powerful, good for ensemble usage (minimal config)
-# [providers.embedded.qwen3]
-# model_path = "~/.g3/models/qwen3-4b-q4_k_m.gguf"
-# model_type = "qwen"
-# gpu_layers = 99                # Optional but recommended for Apple Silicon
-
-# =============================================================================
-# Agent settings (all optional - these are the defaults)
-# =============================================================================
-# [agent]
-# fallback_default_max_tokens = 8192
-# enable_streaming = true
-# timeout_seconds = 120
-# auto_compact = true
-# max_retry_attempts = 3
-# autonomous_max_retry_attempts = 6
-# max_context_length = 200000     # Override context window size
-
-# =============================================================================
-# Computer control (all optional - enabled by default)
-# =============================================================================
-# [computer_control]
-# enabled = true                  # Requires OS accessibility permissions
-# require_confirmation = true
-# max_actions_per_second = 5
-
-# =============================================================================
-# WebDriver browser automation (all optional)
-# =============================================================================
-# [webdriver]
-# enabled = true
-# browser = "chrome-headless"     # Default. Alternative: "safari"
-# chrome_binary = "/path/to/chrome"        # Optional: custom Chrome path
-# chromedriver_binary = "/path/to/driver"  # Optional: custom ChromeDriver path
+[computer_control]
+enabled = false  # Set to true to enable computer control (requires OS permissions)
+require_confirmation = true
+max_actions_per_second = 5

crates/g3-cli/Cargo.toml

@@ -7,9 +7,6 @@ description = "CLI interface for G3 AI coding agent"
 [dependencies]
 g3-core = { path = "../g3-core" }
 g3-config = { path = "../g3-config" }
-g3-planner = { path = "../g3-planner" }
-g3-computer-control = { path = "../g3-computer-control" }
-g3-providers = { path = "../g3-providers" }
 clap = { workspace = true }
 tokio = { workspace = true }
 anyhow = { workspace = true }
@@ -17,22 +14,11 @@ tracing = { workspace = true }
 tracing-subscriber = { workspace = true, features = ["env-filter"] }
 serde = { workspace = true, features = ["derive"] }
 serde_json = { workspace = true }
-serde_yaml = "0.9"
-rustyline = { version = "17.0.1", features = ["derive", "with-dirs", "custom-bindings"] }
+rustyline = "17.0.1"
 dirs = "5.0"
 tokio-util = "0.7"
-sha2 = "0.10"
-hex = "0.4"
-indicatif = "0.18"
+indicatif = "0.17"
 chrono = { version = "0.4", features = ["serde"] }
 crossterm = "0.29.0"
-ratatui = "0.30"
+ratatui = "0.29"
 termimad = "0.34.0"
-regex = "1.10"
-syntect = "5.3"
-once_cell = "1.19"
-rand = "0.8"
-proctitle = "0.1.1"
-
-[dev-dependencies]
-tempfile = "3.8"

crates/g3-cli/src/accumulative.rs

@@ -1,327 +0,0 @@
-//! Accumulative autonomous mode for G3 CLI.
-
-use anyhow::Result;
-use crossterm::style::{Color, ResetColor, SetForegroundColor};
-use rustyline::error::ReadlineError;
-use rustyline::{Cmd, Config, Editor, EventHandler, KeyCode, KeyEvent, Modifiers};
-use std::path::PathBuf;
-use tracing::error;
-
-use g3_core::project::Project;
-use g3_core::Agent;
-
-use crate::autonomous::run_autonomous;
-use crate::cli_args::Cli;
-use crate::interactive::run_interactive;
-use crate::simple_output::SimpleOutput;
-use crate::ui_writer_impl::ConsoleUiWriter;
-use g3_core::ui_writer::UiWriter;
-use crate::utils::load_config_with_cli_overrides;
-use crate::template::process_template;
-
-/// Run accumulative autonomous mode - accumulates requirements from user input
-/// and runs autonomous mode after each input.
-pub async fn run_accumulative_mode(
-    workspace_dir: PathBuf,
-    cli: Cli,
-    combined_content: Option<String>,
-) -> Result<()> {
-    let output = SimpleOutput::new();
-
-    output.print("");
-    output.print("g3 programming agent - autonomous mode");
-    output.print("      >> describe what you want, I'll build it iteratively");
-    output.print("");
-    print!(
-        "{}workspace: {}{}\n",
-        SetForegroundColor(Color::DarkGrey),
-        workspace_dir.display(),
-        ResetColor
-    );
-    output.print("");
-    output.print("💡 Each input you provide will be added to requirements");
-    output.print("   and I'll automatically work on implementing them. You can");
-    output.print("   interrupt at any time (Ctrl+C) to add clarifications or more requirements.");
-    output.print("");
-    output.print("   Type '/help' for commands, 'exit' or 'quit' to stop, Ctrl+D to finish");
-    output.print("");
-
-    // Initialize rustyline editor with history
-    let config = Config::builder()
-        .completion_type(rustyline::CompletionType::List)
-        .build();
-    let mut rl = Editor::<(), rustyline::history::DefaultHistory>::with_config(config)?;
-
-    // Bind Alt+Enter to insert a newline (for multi-line input)
-    rl.bind_sequence(KeyEvent(KeyCode::Enter, Modifiers::ALT), EventHandler::Simple(Cmd::Newline));
-
-    let history_file = dirs::home_dir().map(|mut path| {
-        path.push(".g3_accumulative_history");
-        path
-    });
-
-    if let Some(ref history_path) = history_file {
-        let _ = rl.load_history(history_path);
-    }
-
-    // Accumulated requirements stored in memory
-    let mut accumulated_requirements = Vec::new();
-    let mut turn_number = 0;
-
-    loop {
-        output.print(&format!("\n{}", "=".repeat(60)));
-        if accumulated_requirements.is_empty() {
-            output.print("📝 What would you like me to build? (describe your requirements)");
-        } else {
-            output.print(&format!(
-                "📝 Turn {} - What's next? (add more requirements or refinements)",
-                turn_number + 1
-            ));
-        }
-        output.print(&format!("{}", "=".repeat(60)));
-
-        let readline = rl.readline("requirement> ");
-        match readline {
-            Ok(line) => {
-                // Apply template expansion (e.g., {{today}} -> 2026-01-26 (Monday))
-                let input = process_template(line.trim());
-
-                if input.is_empty() {
-                    continue;
-                }
-
-                if input == "exit" || input == "quit" {
-                    output.print("\n👋 Goodbye!");
-                    break;
-                }
-
-                // Check for slash commands
-                if input.starts_with('/') {
-                    match handle_command(
-                        &input,
-                        &output,
-                        &accumulated_requirements,
-                        &cli,
-                        &combined_content,
-                        &workspace_dir,
-                    )
-                    .await?
-                    {
-                        CommandResult::Continue => continue,
-                        CommandResult::Exit => break,
-                        CommandResult::Unknown => {
-                            output.print(&format!(
-                                "❌ Unknown command: {}. Type /help for available commands.",
-                                input
-                            ));
-                            continue;
-                        }
-                    }
-                }
-
-                // Add to history
-                rl.add_history_entry(&input)?;
-
-                // Add this requirement to accumulated list
-                turn_number += 1;
-                accumulated_requirements.push(format!("{}. {}", turn_number, input));
-
-                // Build the complete requirements document
-                let requirements_doc = format!(
-                    "# Project Requirements\n\n\
-                    ## Current Instructions and Requirements:\n\n\
-                    {}\n\n\
-                    ## Latest Requirement (Turn {}):\n\n\
-                    {}",
-                    accumulated_requirements.join("\n"),
-                    turn_number,
-                    input
-                );
-
-                output.print("");
-                output.print(&format!(
-                    "📋 Current instructions and requirements (Turn {}):",
-                    turn_number
-                ));
-                output.print(&format!("   {}", input));
-                output.print("");
-                output.print("🚀 Starting autonomous implementation...");
-                output.print("");
-
-                // Create a project with the accumulated requirements
-                let project = Project::new_autonomous_with_requirements(
-                    workspace_dir.clone(),
-                    requirements_doc.clone(),
-                )?;
-
-                // Ensure workspace exists and enter it
-                project.ensure_workspace_exists()?;
-                project.enter_workspace()?;
-
-                // Load configuration with CLI overrides
-                let config = load_config_with_cli_overrides(&cli)?;
-
-                // Create agent for this autonomous run
-                let ui_writer = ConsoleUiWriter::new();
-                ui_writer.set_workspace_path(workspace_dir.clone());
-                let agent = Agent::new_autonomous_with_project_context_and_quiet(
-                    config.clone(),
-                    ui_writer,
-                    combined_content.clone(),
-                    cli.quiet,
-                )
-                .await?;
-
-                // Run autonomous mode with the accumulated requirements
-                let autonomous_result = tokio::select! {
-                    result = run_autonomous(
-                        agent,
-                        project,
-                        cli.show_prompt,
-                        cli.show_code,
-                        cli.max_turns,
-                        cli.quiet,
-                        cli.codebase_fast_start.clone(),
-                    ) => result.map(Some),
-                    _ = tokio::signal::ctrl_c() => {
-                        output.print("\n⚠️  Autonomous run cancelled by user (Ctrl+C)");
-                        Ok(None)
-                    }
-                };
-
-                match autonomous_result {
-                    Ok(Some(_returned_agent)) => {
-                        output.print("");
-                        use crate::g3_status::G3Status;
-                        G3Status::progress("autonomous run");
-                        G3Status::done();
-                    }
-                    Ok(None) => {
-                        output.print("   (session continuation not saved due to cancellation)");
-                    }
-                    Err(e) => {
-                        output.print("");
-                        output.print(&format!("❌ Autonomous run failed: {}", e));
-                        output.print("   You can provide more requirements to continue.");
-                    }
-                }
-            }
-            Err(ReadlineError::Interrupted) => {
-                output.print("\n👋 Interrupted. Goodbye!");
-                break;
-            }
-            Err(ReadlineError::Eof) => {
-                output.print("\n👋 Goodbye!");
-                break;
-            }
-            Err(err) => {
-                error!("Error: {:?}", err);
-                break;
-            }
-        }
-    }
-
-    // Save history before exiting
-    if let Some(ref history_path) = history_file {
-        let _ = rl.save_history(history_path);
-    }
-
-    Ok(())
-}
-
-enum CommandResult {
-    Continue,
-    Exit,
-    Unknown,
-}
-
-async fn handle_command(
-    input: &str,
-    output: &SimpleOutput,
-    accumulated_requirements: &[String],
-    cli: &Cli,
-    combined_content: &Option<String>,
-    workspace_dir: &PathBuf,
-) -> Result<CommandResult> {
-    match input {
-        "/help" => {
-            output.print("");
-            output.print("📖 Available Commands:");
-            output.print("  /requirements - Show all accumulated requirements");
-            output.print("  /chat         - Switch to interactive chat mode");
-            output.print("  /help         - Show this help message");
-            output.print("  exit/quit     - Exit the session");
-            output.print("");
-            Ok(CommandResult::Continue)
-        }
-        "/requirements" => {
-            output.print("");
-            if accumulated_requirements.is_empty() {
-                output.print("📋 No requirements accumulated yet");
-            } else {
-                output.print("📋 Accumulated Requirements:");
-                output.print("");
-                for req in accumulated_requirements {
-                    output.print(&format!("   {}", req));
-                }
-            }
-            output.print("");
-            Ok(CommandResult::Continue)
-        }
-        "/chat" => {
-            output.print("");
-            output.print("🔄 Switching to interactive chat mode...");
-            output.print("");
-
-            // Build context message with accumulated requirements
-            let requirements_context = if accumulated_requirements.is_empty() {
-                None
-            } else {
-                Some(format!(
-                    "📋 Context from Accumulative Mode:\n\n\
-                    We were working on these requirements. There may be unstaged or in-progress changes or recent changes to this branch. This is for your information.\n\n\
-                    Requirements:\n{}\n",
-                    accumulated_requirements.join("\n")
-                ))
-            };
-
-            // Combine with existing content (README/AGENTS.md)
-            let chat_combined_content = match (requirements_context, combined_content.clone()) {
-                (Some(req_ctx), Some(existing)) => Some(format!("{}\n\n{}", req_ctx, existing)),
-                (Some(req_ctx), None) => Some(req_ctx),
-                (None, existing) => existing,
-            };
-
-            // Load configuration
-            let config = load_config_with_cli_overrides(cli)?;
-
-            // Create agent for interactive mode with requirements context
-            let ui_writer = ConsoleUiWriter::new();
-            ui_writer.set_workspace_path(workspace_dir.clone());
-            let agent = Agent::new_with_project_context_and_quiet(
-                config,
-                ui_writer,
-                chat_combined_content.clone(),
-                cli.quiet,
-            )
-            .await?;
-
-            // Run interactive mode
-            run_interactive(
-                agent,
-                cli.show_prompt,
-                cli.show_code,
-                chat_combined_content,
-                workspace_dir,
-                None, // agent_name (not in agent mode)
-                None, // initial_project (not supported in accumulative mode yet)
-            )
-            .await?;
-
-            // After returning from interactive mode, exit
-            output.print("\n👋 Goodbye!");
-            Ok(CommandResult::Exit)
-        }
-        _ => Ok(CommandResult::Unknown),
-    }
-}

crates/g3-cli/src/agent_mode.rs

@@ -1,327 +0,0 @@
-//! Agent mode for G3 CLI - runs specialized agents with custom prompts.
-
-use anyhow::Result;
-use tracing::debug;
-
-use g3_core::ui_writer::UiWriter;
-use g3_core::Agent;
-
-use crate::project_files::{combine_project_content, discover_and_format_skills, read_agents_config, read_include_prompt, read_workspace_memory};
-use crate::display::{LoadedContent, print_loaded_status, print_workspace_path};
-use crate::language_prompts::{get_language_prompts_for_workspace, get_agent_language_prompts_for_workspace_with_langs};
-use crate::simple_output::SimpleOutput;
-use crate::embedded_agents::load_agent_prompt;
-use crate::ui_writer_impl::ConsoleUiWriter;
-use crate::interactive::run_interactive;
-use crate::template::process_template;
-use crate::project::{Project, load_and_validate_project};
-use crate::cli_args::CommonFlags;
-
-/// Run agent mode - loads a specialized agent prompt and executes a single task.
-/// 
-/// Uses `CommonFlags` for flags that apply across all modes, ensuring consistency.
-pub async fn run_agent_mode(
-    agent_name: &str,
-    task: Option<String>,
-    chat: bool,
-    flags: CommonFlags,
-) -> Result<()> {
-    use g3_core::find_incomplete_agent_session;
-    use g3_core::get_agent_system_prompt;
-
-    // Set process title to agent name (shows in ps, Activity Monitor, etc.)
-    proctitle::set_title(format!("g3 [{}]", agent_name));
-
-    let output = SimpleOutput::new();
-
-    // Determine workspace directory (current dir if not specified)
-    let workspace_dir = flags.workspace.clone().unwrap_or_else(|| std::env::current_dir().unwrap_or_default());
-
-    // Change to the workspace directory first so session scanning works correctly
-    std::env::set_current_dir(&workspace_dir)?;
-
-    // Check for incomplete agent sessions before starting a new one
-    // When --resume is explicitly provided, always honor it (even in chat mode)
-    // Otherwise, chat mode starts fresh (no auto-resume of incomplete sessions)
-    let resuming_session = if let Some(ref session_id) = flags.resume {
-        // Explicit --resume flag takes precedence
-        match g3_core::load_continuation_by_id(session_id) {
-            Ok(continuation) => {
-                // Verify the session matches this agent (or allow any if agent name matches)
-                if continuation.agent_name.as_deref() != Some(agent_name) {
-                    eprintln!("Error: Session '{}' belongs to agent '{}', not '{}'",
-                        session_id,
-                        continuation.agent_name.as_deref().unwrap_or("(none)"),
-                        agent_name);
-                    std::process::exit(1);
-                }
-                Some(continuation)
-            }
-            Err(e) => {
-                eprintln!("Error: {}", e);
-                std::process::exit(1);
-            }
-        }
-    } else if chat {
-        // Chat mode without explicit --resume starts fresh (no auto-resume)
-        None
-    } else if flags.new_session {
-        if !chat {
-            output.print("\n🆕 Starting new session (--new-session flag set)");
-            output.print("");
-        }
-        None
-    } else {
-        find_incomplete_agent_session(agent_name).ok().flatten()
-    };
-
-    // Only show session resume info when not in chat mode
-    if !chat {
-      if let Some(ref incomplete_session) = resuming_session {
-        output.print(&format!(
-            "\n🔄 Found incomplete session for agent '{}'",
-            agent_name
-        ));
-        output.print(&format!("   Session: {}", incomplete_session.session_id));
-        output.print(&format!("   Created: {}", incomplete_session.created_at));
-        if let Some(ref todo) = incomplete_session.todo_snapshot {
-            // Show first few lines of TODO
-            let preview: String = todo.lines().take(5).collect::<Vec<_>>().join("\n");
-            output.print(&format!("   TODO preview:\n{}", preview));
-        }
-        output.print("");
-        output.print("   Resuming incomplete session...");
-        output.print("");
-      }
-    }
-
-    // Load agent prompt: workspace agents/<name>.md first, then embedded fallback
-    let (agent_prompt, from_disk) = load_agent_prompt(agent_name, &workspace_dir).ok_or_else(|| {
-        anyhow::anyhow!(
-            "Agent '{}' not found.\nAvailable embedded agents: breaker, carmack, euler, fowler, hopper, lamport, scout, solon\nOr create agents/{}.md in your workspace.",
-            agent_name,
-            agent_name
-        )
-    })?;
-
-    let source = if from_disk { "workspace" } else { "embedded" };
-    // Only print verbose header when not in chat mode
-    if !chat {
-        output.print(&format!(">> agent mode | {} ({})", agent_name, source));
-    }
-    // Always print workspace path (it's part of minimal output)
-    print_workspace_path(&workspace_dir);
-
-    // Load config
-    let mut config = g3_config::Config::load(flags.config.as_deref())?;
-
-    // Apply chrome-headless flag override
-    if flags.chrome_headless {
-        config.webdriver.enabled = true;
-        config.webdriver.browser = g3_config::WebDriverBrowser::ChromeHeadless;
-    }
-
-    // Apply safari flag override
-    if flags.safari {
-        config.webdriver.enabled = true;
-        config.webdriver.browser = g3_config::WebDriverBrowser::Safari;
-    }
-
-    // Generate the combined system prompt (agent prompt + tool instructions)
-    // Note: allow_multiple_tool_calls parameter is deprecated but kept for API compatibility
-    let system_prompt = get_agent_system_prompt(&agent_prompt, true);
-
-    // Load AGENTS.md and memory - same as normal mode
-    let agents_content_opt = read_agents_config(&workspace_dir);
-    let memory_content_opt = read_workspace_memory(&workspace_dir);
-
-    // Read include prompt early so we can show it in the status line
-    let include_prompt = read_include_prompt(flags.include_prompt.as_deref());
-
-    // Build and print status line showing what was loaded
-    let include_filename = flags.include_prompt.as_ref()
-        .filter(|_| include_prompt.is_some())
-        .and_then(|p| p.file_name())
-        .map(|s| s.to_string_lossy().to_string());
-    let loaded = LoadedContent::new(
-        agents_content_opt.is_some(),
-        memory_content_opt.is_some(),
-        include_filename,
-    );
-    print_loaded_status(&loaded);
-
-    // Get language-specific prompts (same mechanism as normal mode)
-    let language_content = get_language_prompts_for_workspace(&workspace_dir);
-
-    // Get agent+language-specific prompts (e.g., carmack.racket.md) and show which languages
-    let detected_langs = crate::language_prompts::detect_languages(&workspace_dir);
-    let agent_lang_content = if detected_langs.is_empty() {
-        None
-    } else {
-        let (content, matched_langs) = get_agent_language_prompts_for_workspace_with_langs(&workspace_dir, agent_name);
-        // Only print language guidance info when not in chat mode
-        if !chat {
-            for lang in matched_langs {
-                output.print(&format!("   ✓ {}: {} language guidance", agent_name, lang));
-            }
-        }
-        content
-    };
-
-    // Append agent+language-specific content to system prompt if available
-    let system_prompt = if let Some(agent_lang) = agent_lang_content {
-        format!("{}\n\n{}", system_prompt, agent_lang)
-    } else {
-        system_prompt
-    };
-
-    // Discover skills from configured paths
-    let (_skills, skills_content) = discover_and_format_skills(&workspace_dir, &config.skills);
-
-    // Combine all content for the agent's context
-    let combined_content = combine_project_content(
-        agents_content_opt,
-        memory_content_opt,
-        language_content,
-        include_prompt,
-        skills_content,
-        &workspace_dir,
-    );
-
-    // Create agent with custom system prompt
-    let ui_writer = ConsoleUiWriter::new();
-    // Set agent mode on UI writer for visual differentiation (light gray tool names)
-    ui_writer.set_agent_mode(true);
-    ui_writer.set_workspace_path(workspace_dir.clone());
-    let mut agent =
-        Agent::new_with_custom_prompt(config, ui_writer, system_prompt, combined_content.clone()).await?;
-
-    // Set agent mode for session tracking
-    agent.set_agent_mode(agent_name);
-
-    // Auto-memory is enabled by default in agent mode (unless --no-auto-memory is set)
-    // This prompts the LLM to save discoveries to workspace memory after each turn
-    agent.set_auto_memory(!flags.no_auto_memory);
-    
-    // Enable ACD (Aggressive Context Dehydration) if requested
-    if flags.acd {
-        agent.set_acd_enabled(true);
-    }
-
-    // If resuming a session, restore context and TODO
-    let initial_task = if let Some(ref incomplete_session) = resuming_session {
-        // Restore the session context
-        match agent.restore_from_continuation(incomplete_session) {
-            Ok(full_restore) => {
-                if full_restore {
-                    output.print("   ✅ Full context restored from previous session");
-                } else {
-                    output.print("   ⚠️ Restored from summary (context was > 80%)");
-                }
-            }
-            Err(e) => {
-                output.print(&format!("   ⚠️ Could not restore context: {}", e));
-            }
-        }
-
-        // Copy TODO from old session to new session directory
-        let todo_content = if let Some(ref content) = incomplete_session.todo_snapshot {
-            Some(content.clone())
-        } else {
-            // Fallback: read from the actual todo.g3.md file in the old session directory
-            let old_session_dir =
-                std::path::Path::new(".g3/sessions").join(&incomplete_session.session_id);
-            let old_todo_path = old_session_dir.join("todo.g3.md");
-            if old_todo_path.exists() {
-                std::fs::read_to_string(&old_todo_path).ok()
-            } else {
-                None
-            }
-        };
-
-        if let Some(ref content) = todo_content {
-            if let Some(session_id) = agent.get_session_id() {
-                let new_todo_path = g3_core::paths::get_session_todo_path(session_id);
-                let _ = g3_core::paths::ensure_session_dir(session_id);
-                if let Err(e) = std::fs::write(&new_todo_path, content) {
-                    output.print(&format!("   ⚠️ Could not restore TODO: {}", e));
-                } else {
-                    output.print("   ✅ TODO list restored");
-                }
-            }
-        }
-        output.print("");
-
-        // Resume message instead of fresh start
-        "Continue working on the incomplete tasks. Use todo_read to see the current TODO list and resume from where you left off."
-    } else {
-        // Fresh start - the agent prompt should contain instructions to start working immediately
-        "Begin your analysis and work on the current project. Follow your mission and workflow as specified in your instructions."
-    };
-    // Use provided task if available, otherwise use the default initial_task
-    let task_str = task.as_deref().unwrap_or(initial_task);
-    let final_task = process_template(task_str);
-
-    // If chat mode is enabled, run interactive loop instead of single task
-    if chat {
-        // Load project if --project flag was specified
-        let initial_project: Option<Project> = if let Some(ref proj_path) = flags.project {
-            match load_and_validate_project(&proj_path.to_string_lossy(), &workspace_dir) {
-                Ok(cli_project) => {
-                    // Set project content in agent's system message
-                    if agent.set_project_content(Some(cli_project.content.clone())) {
-                        // Set project path on UI writer for path shortening
-                        let project_name = cli_project.path
-                            .file_name()
-                            .and_then(|n| n.to_str())
-                            .unwrap_or("project")
-                            .to_string();
-                        agent.ui_writer().set_project_path(cli_project.path.clone(), project_name);
-                        Some(cli_project)
-                    } else {
-                        eprintln!("Warning: Failed to set project content in agent context.");
-                        None
-                    }
-                }
-                Err(e) => {
-                    eprintln!("Error loading project: {}", e);
-                    std::process::exit(1);
-                }
-            }
-        } else {
-            None
-        };
-
-        return run_interactive(
-            agent,
-            false, // show_prompt
-            false, // show_code
-            combined_content,
-            &workspace_dir,
-            Some(agent_name),  // agent name for prompt (e.g., "butler>")
-            initial_project,
-        )
-        .await;
-    }
-
-    // Single-shot mode: execute the task and exit
-    let _result = agent.execute_task(&final_task, None, true).await?;
-
-    // Send auto-memory reminder if enabled and tools were called
-    if let Err(e) = agent.send_auto_memory_reminder().await {
-        debug!("Auto-memory reminder failed: {}", e);
-    }
-
-    // Save session continuation for resume capability
-    agent.save_session_continuation(None);
-
-    // Don't print completion message for scout agent - it needs the last line
-    // to be the report file path for the research tool to read
-    if agent_name != "scout" {
-        use crate::g3_status::G3Status;
-        println!(); // newline before status
-        G3Status::progress(&format!("{} session", agent_name));
-        G3Status::done();
-    }
-    Ok(())
-}

crates/g3-cli/src/autonomous.rs

@@ -1,735 +0,0 @@
-//! Autonomous mode for G3 CLI - coach-player feedback loop.
-
-use anyhow::Result;
-use sha2::{Digest, Sha256};
-use std::path::PathBuf;
-use std::time::Instant;
-use tracing::debug;
-
-use g3_core::error_handling::{classify_error, ErrorType, RecoverableError};
-use g3_core::project::Project;
-use g3_core::{Agent, DiscoveryOptions};
-
-use crate::coach_feedback;
-use crate::metrics::{format_elapsed_time, generate_turn_histogram, TurnMetrics};
-use crate::simple_output::SimpleOutput;
-use crate::ui_writer_impl::ConsoleUiWriter;
-use g3_core::ui_writer::UiWriter;
-
-/// Run autonomous mode with coach-player feedback loop (console output).
-pub async fn run_autonomous(
-    mut agent: Agent<ConsoleUiWriter>,
-    project: Project,
-    show_prompt: bool,
-    show_code: bool,
-    max_turns: usize,
-    quiet: bool,
-    codebase_fast_start: Option<PathBuf>,
-) -> Result<Agent<ConsoleUiWriter>> {
-    let start_time = std::time::Instant::now();
-    let output = SimpleOutput::new();
-    let mut turn_metrics: Vec<TurnMetrics> = Vec::new();
-
-    output.print("g3 programming agent - autonomous mode");
-    output.print(&format!(
-        "📁 Using workspace: {}",
-        project.workspace().display()
-    ));
-
-    // Check if requirements exist
-    if !project.has_requirements() {
-        print_no_requirements_error(&output, &agent, &turn_metrics, start_time, max_turns);
-        return Ok(agent);
-    }
-
-    // Read requirements
-    let requirements = match project.read_requirements()? {
-        Some(content) => content,
-        None => {
-            print_cannot_read_requirements_error(
-                &output,
-                &agent,
-                &turn_metrics,
-                start_time,
-                max_turns,
-            );
-            return Ok(agent);
-        }
-    };
-
-    // Display appropriate message based on requirements source
-    if project.requirements_text.is_some() {
-        output.print("📋 Requirements loaded from --requirements flag");
-    } else {
-        output.print("📋 Requirements loaded from requirements.md");
-    }
-
-    // Calculate SHA256 of requirements
-    let mut hasher = Sha256::new();
-    hasher.update(requirements.as_bytes());
-    let requirements_sha = hex::encode(hasher.finalize());
-
-    output.print(&format!("🔒 Requirements SHA256: {}", requirements_sha));
-
-    // Pass SHA to agent for staleness checking
-    agent.set_requirements_sha(requirements_sha.clone());
-
-    let loop_start = Instant::now();
-    output.print("🔄 Starting coach-player feedback loop...");
-
-    // Load fast-discovery messages before the loop starts (if enabled)
-    let (discovery_messages, discovery_working_dir) =
-        load_discovery_messages(&agent, &output, &codebase_fast_start, &requirements).await;
-    let has_discovery = !discovery_messages.is_empty();
-
-    let mut turn = 1;
-    let mut coach_feedback_text = String::new();
-    let mut implementation_approved = false;
-
-    loop {
-        let turn_start_time = Instant::now();
-        let turn_start_tokens = agent.get_context_window().used_tokens;
-
-        output.print(&format!(
-            "\n=== TURN {}/{} - PLAYER MODE ===",
-            turn, max_turns
-        ));
-
-        // Surface provider info for player agent
-        agent.print_provider_banner("Player");
-
-        // Player mode: implement requirements (with coach feedback if available)
-        let player_prompt = build_player_prompt(&requirements, &requirements_sha, &coach_feedback_text);
-
-        output.print(&format!(
-            "🎯 Starting player implementation... (elapsed: {})",
-            format_elapsed_time(loop_start.elapsed())
-        ));
-
-        // Display what feedback the player is receiving
-        if coach_feedback_text.is_empty() {
-            if turn > 1 {
-                return Err(anyhow::anyhow!(
-                    "Player mode error: No coach feedback received on turn {}",
-                    turn
-                ));
-            }
-            output.print("📋 Player starting initial implementation (no prior coach feedback)");
-        } else {
-            output.print(&format!(
-                "📋 Player received coach feedback ({} chars):",
-                coach_feedback_text.len()
-            ));
-            output.print(&coach_feedback_text);
-        }
-        output.print(""); // Empty line for readability
-
-        // Execute player task with retry on error
-        let player_result = execute_player_turn(
-            &mut agent,
-            &player_prompt,
-            show_prompt,
-            show_code,
-            &output,
-            has_discovery,
-            &discovery_messages,
-            discovery_working_dir.as_deref(),
-            turn,
-            &turn_metrics,
-            start_time,
-            max_turns,
-        )
-        .await;
-
-        let player_failed = match player_result {
-            PlayerTurnResult::Success => false,
-            PlayerTurnResult::Failed => true,
-            PlayerTurnResult::Panic(e) => return Err(e),
-        };
-
-        // If player failed after max retries, increment turn and continue
-        if player_failed {
-            output.print(&format!(
-                "⚠️ Player turn {} failed after max retries. Moving to next turn.",
-                turn
-            ));
-            record_turn_metrics(
-                &mut turn_metrics,
-                turn,
-                turn_start_time,
-                turn_start_tokens,
-                &agent,
-            );
-            turn += 1;
-
-            if turn > max_turns {
-                output.print("\n=== SESSION COMPLETED - MAX TURNS REACHED ===");
-                output.print(&format!("⏰ Maximum turns ({}) reached", max_turns));
-                break;
-            }
-
-            coach_feedback_text = String::new();
-            continue;
-        }
-
-        // Give some time for file operations to complete
-        tokio::time::sleep(tokio::time::Duration::from_millis(500)).await;
-
-        // Execute coach turn
-        let coach_result = execute_coach_turn(
-            &agent,
-            &project,
-            &requirements,
-            show_prompt,
-            show_code,
-            quiet,
-            &output,
-            has_discovery,
-            &discovery_messages,
-            discovery_working_dir.as_deref(),
-            turn,
-            max_turns,
-            &turn_metrics,
-            start_time,
-            loop_start,
-        )
-        .await;
-
-        match coach_result {
-            CoachTurnResult::Approved => {
-                output.print("\n=== SESSION COMPLETED - IMPLEMENTATION APPROVED ===");
-                output.print("✅ Coach approved the implementation!");
-                implementation_approved = true;
-                break;
-            }
-            CoachTurnResult::Feedback(feedback) => {
-                output.print_smart(&format!("Coach feedback:\n{}", feedback));
-                coach_feedback_text = feedback;
-            }
-            CoachTurnResult::Failed => {
-                output.print(&format!(
-                    "⚠️ Coach turn {} failed after max retries. Using default feedback.",
-                    turn
-                ));
-                coach_feedback_text = "The implementation needs review. Please ensure all requirements are met and the code compiles without errors.".to_string();
-            }
-            CoachTurnResult::Panic(e) => return Err(e),
-        }
-
-        // Check if we've reached max turns
-        if turn >= max_turns {
-            output.print("\n=== SESSION COMPLETED - MAX TURNS REACHED ===");
-            output.print(&format!("⏰ Maximum turns ({}) reached", max_turns));
-            break;
-        }
-
-        record_turn_metrics(
-            &mut turn_metrics,
-            turn,
-            turn_start_time,
-            turn_start_tokens,
-            &agent,
-        );
-        turn += 1;
-
-        output.print("🔄 Coach provided feedback for next iteration");
-    }
-
-    // Generate final report
-    print_final_report(
-        &output,
-        &agent,
-        &turn_metrics,
-        start_time,
-        turn,
-        max_turns,
-        implementation_approved,
-    );
-
-    if implementation_approved {
-        output.print(&format!(
-            "\n🎉 Autonomous mode completed successfully (total loop time: {})",
-            format_elapsed_time(loop_start.elapsed())
-        ));
-    } else {
-        output.print(&format!(
-            "\n🔄 Autonomous mode terminated (max iterations) (total loop time: {})",
-            format_elapsed_time(loop_start.elapsed())
-        ));
-    }
-
-    // Save session continuation for resume capability
-    agent.save_session_continuation(None);
-
-    Ok(agent)
-}
-
-// --- Helper types and functions ---
-
-enum PlayerTurnResult {
-    Success,
-    Failed,
-    Panic(anyhow::Error),
-}
-
-enum CoachTurnResult {
-    Approved,
-    Feedback(String),
-    Failed,
-    Panic(anyhow::Error),
-}
-
-fn build_player_prompt(requirements: &str, requirements_sha: &str, coach_feedback: &str) -> String {
-    if coach_feedback.is_empty() {
-        format!(
-            "You are G3 in implementation mode. Read and implement the following requirements:\n\n{}\n\nRequirements SHA256: {}\n\nImplement this step by step, creating all necessary files and code.",
-            requirements, requirements_sha
-        )
-    } else {
-        format!(
-            "You are G3 in implementation mode. Address the following specific feedback from the coach:\n\n{}\n\nContext: You are improving an implementation based on these requirements:\n{}\n\nFocus on fixing the issues mentioned in the coach feedback above.",
-            coach_feedback, requirements
-        )
-    }
-}
-
-fn build_coach_prompt(requirements: &str) -> String {
-    format!(
-        "You are G3 in coach mode. Your role is to critique and review implementations against requirements and provide concise, actionable feedback.
-
-REQUIREMENTS:
-{}
-
-IMPLEMENTATION REVIEW:
-Review the current state of the project and provide a concise critique focusing on:
-1. Whether the requirements are correctly implemented
-2. Whether the project compiles successfully
-3. What requirements are missing or incorrect
-4. Specific improvements needed to satisfy requirements
-5. Use UI tools such as webdriver to test functionality thoroughly
-
-CRITICAL INSTRUCTIONS:
-1. Provide your feedback as your final response message
-2. Your feedback should be CONCISE and ACTIONABLE
-3. Focus ONLY on what needs to be fixed or improved
-4. Do NOT include your analysis process, file contents, or compilation output in your final feedback
-
-If the implementation thoroughly meets all requirements, compiles and is fully tested (especially UI flows) *WITHOUT* minor gaps or errors:
-- Respond with: 'IMPLEMENTATION_APPROVED'
-
-If improvements are needed:
-- Respond with a brief summary listing ONLY the specific issues to fix
-
-Remember: Be clear in your review and concise in your feedback. APPROVE iff the implementation works and thoroughly fits the requirements (implementation > 95% complete). Be rigorous, especially by testing that all UI features work.",
-        requirements
-    )
-}
-
-async fn load_discovery_messages(
-    agent: &Agent<ConsoleUiWriter>,
-    output: &SimpleOutput,
-    codebase_fast_start: &Option<PathBuf>,
-    requirements: &str,
-) -> (Vec<g3_providers::Message>, Option<String>) {
-    if let Some(ref codebase_path) = codebase_fast_start {
-        let canonical_path = codebase_path
-            .canonicalize()
-            .unwrap_or_else(|_| codebase_path.clone());
-        let path_str = canonical_path.to_string_lossy();
-        output.print(&format!(
-            "🔍 Fast-discovery mode: will explore codebase at {}",
-            path_str
-        ));
-
-        match agent.get_provider() {
-            Ok(provider) => {
-                let output_clone = output.clone();
-                let status_callback: g3_planner::StatusCallback = Box::new(move |msg: &str| {
-                    output_clone.print(msg);
-                });
-                match g3_planner::get_initial_discovery_messages(
-                    &path_str,
-                    Some(requirements),
-                    provider,
-                    Some(&status_callback),
-                )
-                .await
-                {
-                    Ok(messages) => (messages, Some(path_str.to_string())),
-                    Err(e) => {
-                        output.print(&format!(
-                            "⚠️ LLM discovery failed: {}, skipping fast-start",
-                            e
-                        ));
-                        (Vec::new(), None)
-                    }
-                }
-            }
-            Err(e) => {
-                output.print(&format!(
-                    "⚠️ Could not get provider: {}, skipping fast-start",
-                    e
-                ));
-                (Vec::new(), None)
-            }
-        }
-    } else {
-        (Vec::new(), None)
-    }
-}
-
-async fn execute_player_turn(
-    agent: &mut Agent<ConsoleUiWriter>,
-    player_prompt: &str,
-    show_prompt: bool,
-    show_code: bool,
-    output: &SimpleOutput,
-    has_discovery: bool,
-    discovery_messages: &[g3_providers::Message],
-    discovery_working_dir: Option<&str>,
-    turn: usize,
-    turn_metrics: &[TurnMetrics],
-    start_time: Instant,
-    max_turns: usize,
-) -> PlayerTurnResult {
-    const MAX_PLAYER_RETRIES: u32 = 3;
-    let mut retry_count = 0;
-
-    loop {
-        let discovery_opts = if has_discovery {
-            Some(DiscoveryOptions {
-                messages: discovery_messages,
-                fast_start_path: discovery_working_dir,
-            })
-        } else {
-            None
-        };
-
-        match agent
-            .execute_task_with_timing(
-                player_prompt,
-                None,
-                false,
-                show_prompt,
-                show_code,
-                true,
-                discovery_opts,
-            )
-            .await
-        {
-            Ok(result) => {
-                output.print("📝 Player implementation completed:");
-                // Only print response if it's not empty (streaming already displayed it)
-                if !result.response.trim().is_empty() {
-                    output.print_smart(&result.response);
-                }
-                return PlayerTurnResult::Success;
-            }
-            Err(e) => {
-                let error_type = classify_error(&e);
-
-                if matches!(
-                    error_type,
-                    ErrorType::Recoverable(RecoverableError::ContextLengthExceeded)
-                ) {
-                    output.print(&format!("⚠️ Context length exceeded in player turn: {}", e));
-                    output.print("📝 Logging error to session and ending current turn...");
-
-                    let forensic_context = format!(
-                        "Turn: {}\nRole: Player\nContext tokens: {}\nTotal available: {}\nPercentage used: {:.1}%\nPrompt length: {} chars\nError occurred at: {}",
-                        turn,
-                        agent.get_context_window().used_tokens,
-                        agent.get_context_window().total_tokens,
-                        agent.get_context_window().percentage_used(),
-                        player_prompt.len(),
-                        chrono::Utc::now().to_rfc3339()
-                    );
-
-                    agent.log_error_to_session(&e, "assistant", Some(forensic_context));
-                    return PlayerTurnResult::Failed;
-                } else if e.to_string().contains("panic") {
-                    output.print(&format!("💥 Player panic detected: {}", e));
-                    print_panic_report(output, agent, turn_metrics, start_time, turn, max_turns, "PLAYER PANIC");
-                    return PlayerTurnResult::Panic(e);
-                }
-
-                retry_count += 1;
-                output.print(&format!(
-                    "⚠️ Player error (attempt {}/{}): {}",
-                    retry_count, MAX_PLAYER_RETRIES, e
-                ));
-
-                if retry_count >= MAX_PLAYER_RETRIES {
-                    output.print("🔄 Max retries reached for player, marking turn as failed...");
-                    return PlayerTurnResult::Failed;
-                }
-                output.print("🔄 Retrying player implementation...");
-            }
-        }
-    }
-}
-
-async fn execute_coach_turn(
-    player_agent: &Agent<ConsoleUiWriter>,
-    project: &Project,
-    requirements: &str,
-    show_prompt: bool,
-    show_code: bool,
-    quiet: bool,
-    output: &SimpleOutput,
-    has_discovery: bool,
-    discovery_messages: &[g3_providers::Message],
-    discovery_working_dir: Option<&str>,
-    turn: usize,
-    max_turns: usize,
-    turn_metrics: &[TurnMetrics],
-    start_time: Instant,
-    loop_start: Instant,
-) -> CoachTurnResult {
-    const MAX_COACH_RETRIES: u32 = 3;
-
-    // Create a new agent instance for coach mode to ensure fresh context
-    let base_config = player_agent.get_config().clone();
-    let coach_config = match base_config.for_coach() {
-        Ok(c) => c,
-        Err(e) => return CoachTurnResult::Panic(e),
-    };
-
-    // Reset filter suppression state before creating coach agent
-    crate::filter_json::reset_json_tool_state();
-
-    let ui_writer = ConsoleUiWriter::new();
-    ui_writer.set_workspace_path(project.workspace().to_path_buf());
-    let mut coach_agent =
-        match Agent::new_autonomous_with_project_context_and_quiet(coach_config, ui_writer, None, quiet)
-            .await
-        {
-            Ok(a) => a,
-            Err(e) => return CoachTurnResult::Panic(e),
-        };
-
-    coach_agent.print_provider_banner("Coach");
-
-    if let Err(e) = project.enter_workspace() {
-        return CoachTurnResult::Panic(e);
-    }
-
-    output.print(&format!(
-        "\n=== TURN {}/{} - COACH MODE ===",
-        turn, max_turns
-    ));
-
-    let coach_prompt = build_coach_prompt(requirements);
-
-    output.print(&format!(
-        "🎓 Starting coach review... (elapsed: {})",
-        format_elapsed_time(loop_start.elapsed())
-    ));
-
-    let mut retry_count = 0;
-
-    loop {
-        let discovery_opts = if has_discovery {
-            Some(DiscoveryOptions {
-                messages: discovery_messages,
-                fast_start_path: discovery_working_dir,
-            })
-        } else {
-            None
-        };
-
-        match coach_agent
-            .execute_task_with_timing(
-                &coach_prompt,
-                None,
-                false,
-                show_prompt,
-                show_code,
-                true,
-                discovery_opts,
-            )
-            .await
-        {
-            Ok(result) => {
-                output.print("🎓 Coach review completed");
-
-                let feedback_text =
-                    match coach_feedback::extract_from_logs(&result, &coach_agent, output) {
-                        Ok(f) => f,
-                        Err(e) => return CoachTurnResult::Panic(e),
-                    };
-
-                debug!(
-                    "Coach feedback extracted: {} characters (from {} total)",
-                    feedback_text.len(),
-                    result.response.len()
-                );
-
-                if feedback_text.is_empty() {
-                    output.print("⚠️ Coach did not provide feedback. This may be a model issue.");
-                    return CoachTurnResult::Failed;
-                }
-
-                if result.is_approved() || feedback_text.contains("IMPLEMENTATION_APPROVED") {
-                    return CoachTurnResult::Approved;
-                }
-
-                return CoachTurnResult::Feedback(feedback_text);
-            }
-            Err(e) => {
-                let error_type = classify_error(&e);
-
-                if matches!(
-                    error_type,
-                    ErrorType::Recoverable(RecoverableError::ContextLengthExceeded)
-                ) {
-                    output.print(&format!("⚠️ Context length exceeded in coach turn: {}", e));
-                    output.print("📝 Logging error to session and ending current turn...");
-
-                    let forensic_context = format!(
-                        "Turn: {}\nRole: Coach\nContext tokens: {}\nTotal available: {}\nPercentage used: {:.1}%\nPrompt length: {} chars\nError occurred at: {}",
-                        turn,
-                        coach_agent.get_context_window().used_tokens,
-                        coach_agent.get_context_window().total_tokens,
-                        coach_agent.get_context_window().percentage_used(),
-                        coach_prompt.len(),
-                        chrono::Utc::now().to_rfc3339()
-                    );
-
-                    coach_agent.log_error_to_session(&e, "assistant", Some(forensic_context));
-                    return CoachTurnResult::Failed;
-                } else if e.to_string().contains("panic") {
-                    output.print(&format!("💥 Coach panic detected: {}", e));
-                    print_panic_report(output, player_agent, turn_metrics, start_time, turn, max_turns, "COACH PANIC");
-                    return CoachTurnResult::Panic(e);
-                }
-
-                retry_count += 1;
-                output.print(&format!(
-                    "⚠️ Coach error (attempt {}/{}): {}",
-                    retry_count, MAX_COACH_RETRIES, e
-                ));
-
-                if retry_count >= MAX_COACH_RETRIES {
-                    output.print("🔄 Max retries reached for coach, using default feedback...");
-                    return CoachTurnResult::Failed;
-                }
-                output.print("🔄 Retrying coach review...");
-            }
-        }
-    }
-}
-
-fn record_turn_metrics(
-    turn_metrics: &mut Vec<TurnMetrics>,
-    turn: usize,
-    turn_start_time: Instant,
-    turn_start_tokens: u32,
-    agent: &Agent<ConsoleUiWriter>,
-) {
-    let turn_duration = turn_start_time.elapsed();
-    let turn_tokens = agent
-        .get_context_window()
-        .used_tokens
-        .saturating_sub(turn_start_tokens);
-    turn_metrics.push(TurnMetrics {
-        turn_number: turn,
-        tokens_used: turn_tokens,
-        wall_clock_time: turn_duration,
-    });
-}
-
-fn print_no_requirements_error(
-    output: &SimpleOutput,
-    agent: &Agent<ConsoleUiWriter>,
-    turn_metrics: &[TurnMetrics],
-    start_time: Instant,
-    max_turns: usize,
-) {
-    output.print("❌ Error: requirements.md not found in workspace directory");
-    output.print("   Please either:");
-    output.print("   1. Create a requirements.md file with your project requirements");
-    output.print("   2. Or use the --requirements flag to provide requirements text directly:");
-    output.print("      g3 --autonomous --requirements \"Your requirements here\"");
-    output.print("");
-
-    print_final_report(output, agent, turn_metrics, start_time, 0, max_turns, false);
-}
-
-fn print_cannot_read_requirements_error(
-    output: &SimpleOutput,
-    agent: &Agent<ConsoleUiWriter>,
-    turn_metrics: &[TurnMetrics],
-    start_time: Instant,
-    max_turns: usize,
-) {
-    output.print("❌ Error: Could not read requirements (neither --requirements flag nor requirements.md file provided)");
-    print_final_report(output, agent, turn_metrics, start_time, 0, max_turns, false);
-}
-
-fn print_panic_report(
-    output: &SimpleOutput,
-    agent: &Agent<ConsoleUiWriter>,
-    turn_metrics: &[TurnMetrics],
-    start_time: Instant,
-    turn: usize,
-    max_turns: usize,
-    status: &str,
-) {
-    let elapsed = start_time.elapsed();
-    let context_window = agent.get_context_window();
-
-    output.print(&format!("\n{}", "=".repeat(60)));
-    output.print("📊 AUTONOMOUS MODE SESSION REPORT");
-    output.print(&"=".repeat(60));
-
-    output.print(&format!("⏱️  Total Duration: {:.2}s", elapsed.as_secs_f64()));
-    output.print(&format!("🔄 Turns Taken: {}/{}", turn, max_turns));
-    output.print(&format!("📝 Final Status: 💥 {}", status));
-
-    output.print("\n📈 Token Usage Statistics:");
-    output.print(&format!("   • Used Tokens: {}", context_window.used_tokens));
-    output.print(&format!("   • Total Available: {}", context_window.total_tokens));
-    output.print(&format!("   • Cumulative Tokens: {}", context_window.cumulative_tokens));
-    output.print(&format!("   • Usage Percentage: {:.1}%", context_window.percentage_used()));
-    output.print(&generate_turn_histogram(turn_metrics));
-    output.print(&"=".repeat(60));
-}
-
-fn print_final_report(
-    output: &SimpleOutput,
-    agent: &Agent<ConsoleUiWriter>,
-    turn_metrics: &[TurnMetrics],
-    start_time: Instant,
-    turn: usize,
-    max_turns: usize,
-    implementation_approved: bool,
-) {
-    let elapsed = start_time.elapsed();
-    let context_window = agent.get_context_window();
-
-    output.print(&format!("\n{}", "=".repeat(60)));
-    output.print("📊 AUTONOMOUS MODE SESSION REPORT");
-    output.print(&"=".repeat(60));
-
-    output.print(&format!("⏱️  Total Duration: {:.2}s", elapsed.as_secs_f64()));
-    output.print(&format!("🔄 Turns Taken: {}/{}", turn, max_turns));
-    output.print(&format!(
-        "📝 Final Status: {}",
-        if implementation_approved {
-            "✅ APPROVED"
-        } else if turn >= max_turns {
-            "⏰ MAX TURNS REACHED"
-        } else {
-            "⚠️ INCOMPLETE"
-        }
-    ));
-
-    output.print("\n📈 Token Usage Statistics:");
-    output.print(&format!("   • Used Tokens: {}", context_window.used_tokens));
-    output.print(&format!("   • Total Available: {}", context_window.total_tokens));
-    output.print(&format!("   • Cumulative Tokens: {}", context_window.cumulative_tokens));
-    output.print(&format!("   • Usage Percentage: {:.1}%", context_window.percentage_used()));
-    output.print(&generate_turn_histogram(turn_metrics));
-    output.print(&"=".repeat(60));
-}

crates/g3-cli/src/cli_args.rs

@@ -1,184 +0,0 @@
-//! CLI argument parsing for G3.
-
-use clap::Parser;
-use std::path::PathBuf;
-
-/// Flags that apply across all execution modes (interactive, agent, autonomous).
-/// 
-/// When adding a new flag that should work in all modes, add it here instead of
-/// passing individual parameters to mode functions. This prevents bugs where a
-/// flag works in one mode but is forgotten in another.
-#[derive(Clone, Debug, Default)]
-pub struct CommonFlags {
-    /// Workspace directory
-    pub workspace: Option<PathBuf>,
-    /// Configuration file path
-    pub config: Option<String>,
-    /// Skip session resumption and force a new session
-    pub new_session: bool,
-    /// Suppress output/logging
-    pub quiet: bool,
-    /// Use Chrome in headless mode for WebDriver
-    pub chrome_headless: bool,
-    /// Use Safari for WebDriver
-    pub safari: bool,
-    /// Include additional prompt content from a file
-    pub include_prompt: Option<PathBuf>,
-    /// Disable automatic memory update reminder
-    pub no_auto_memory: bool,
-    /// Enable aggressive context dehydration
-    pub acd: bool,
-    /// Load a project from the given path at startup
-    pub project: Option<PathBuf>,
-    /// Resume a specific session by ID
-    pub resume: Option<String>,
-}
-
-#[derive(Parser, Clone)]
-#[command(name = "g3")]
-#[command(about = "A modular, composable AI coding agent")]
-#[command(version)]
-pub struct Cli {
-    /// Enable verbose logging
-    #[arg(short, long)]
-    pub verbose: bool,
-
-    /// Enable manual control of context compaction (disables auto-compact at 90%)
-    #[arg(long = "manual-compact")]
-    pub manual_compact: bool,
-
-    /// Show the system prompt being sent to the LLM
-    #[arg(long)]
-    pub show_prompt: bool,
-
-    /// Show the generated code before execution
-    #[arg(long)]
-    pub show_code: bool,
-
-    /// Configuration file path
-    #[arg(short, long)]
-    pub config: Option<String>,
-
-    /// Workspace directory (defaults to current directory)
-    #[arg(short, long)]
-    pub workspace: Option<PathBuf>,
-
-    /// Task to execute (if provided, runs in single-shot mode instead of interactive)
-    pub task: Option<String>,
-
-    /// Enable autonomous mode with coach-player feedback loop
-    #[arg(long)]
-    pub autonomous: bool,
-
-    /// Maximum number of turns in autonomous mode (default: 5)
-    #[arg(long, default_value = "5")]
-    pub max_turns: usize,
-
-    /// Override requirements text for autonomous mode (instead of reading from requirements.md)
-    #[arg(long, value_name = "TEXT")]
-    pub requirements: Option<String>,
-
-    /// Enable accumulative autonomous mode (default is chat mode)
-    #[arg(long)]
-    pub auto: bool,
-
-    /// Enable interactive chat mode (no autonomous runs)
-    #[arg(long)]
-    pub chat: bool,
-
-    /// Override the configured provider (e.g., 'openai' or 'openai.default')
-    #[arg(long, value_name = "PROVIDER")]
-    pub provider: Option<String>,
-
-    /// Override the model for the selected provider
-    #[arg(long, value_name = "MODEL")]
-    pub model: Option<String>,
-
-    /// Disable session log file creation (no .g3/sessions/ or error logs)
-    #[arg(long)]
-    pub quiet: bool,
-
-    /// Enable WebDriver browser automation tools
-    #[arg(long, default_value_t = true)]
-    pub webdriver: bool,
-
-    /// Use Chrome in headless mode for WebDriver (instead of Safari)
-    #[arg(long, default_value_t = true)]
-    pub chrome_headless: bool,
-
-    /// Use Safari for WebDriver (overrides the default Chrome headless)
-    #[arg(long)]
-    pub safari: bool,
-
-    /// Enable planning mode for requirements-driven development
-    #[arg(long, conflicts_with_all = ["autonomous", "auto", "chat"])]
-    pub planning: bool,
-
-    /// Path to the codebase to work on (for planning mode)
-    #[arg(long, value_name = "PATH")]
-    pub codepath: Option<String>,
-
-    /// Disable git operations in planning mode
-    #[arg(long)]
-    pub no_git: bool,
-
-    /// Enable fast codebase discovery before first LLM turn
-    #[arg(long, value_name = "PATH")]
-    pub codebase_fast_start: Option<PathBuf>,
-
-    /// Run as a specialized agent (loads prompt from agents/<name>.md)
-    #[arg(long, value_name = "NAME", conflicts_with_all = ["autonomous", "auto", "planning"])]
-    pub agent: Option<String>,
-
-    /// List all available agents (embedded and workspace)
-    #[arg(long)]
-    pub list_agents: bool,
-
-    /// Skip session resumption and force a new session (for agent mode)
-    #[arg(long)]
-    pub new_session: bool,
-
-    /// Resume a specific session by ID (full or partial prefix)
-    #[arg(long, value_name = "SESSION_ID", conflicts_with = "new_session")]
-    pub resume: Option<String>,
-
-    /// Automatically remind LLM to call remember tool after turns with tool calls
-    #[arg(long)]
-    pub auto_memory: bool,
-
-    /// Enable aggressive context dehydration (save context to disk on compaction)
-    #[arg(long)]
-    pub acd: bool,
-
-    /// Include additional prompt content from a file (appended before memory)
-    #[arg(long, value_name = "PATH")]
-    pub include_prompt: Option<PathBuf>,
-
-    /// Disable automatic memory update reminder at end of agent mode
-    #[arg(long)]
-    pub no_auto_memory: bool,
-
-    /// Load a project from the given path at startup (like /project but without auto-prompt)
-    #[arg(long, value_name = "PATH")]
-    pub project: Option<PathBuf>,
-}
-
-impl Cli {
-    /// Extract common flags that apply across all execution modes.
-    /// This ensures flags like --project, --acd, --include-prompt work consistently.
-    pub fn common_flags(&self) -> CommonFlags {
-        CommonFlags {
-            workspace: self.workspace.clone(),
-            config: self.config.clone(),
-            new_session: self.new_session,
-            quiet: self.quiet,
-            chrome_headless: self.chrome_headless,
-            safari: self.safari,
-            include_prompt: self.include_prompt.clone(),
-            no_auto_memory: self.no_auto_memory,
-            acd: self.acd,
-            project: self.project.clone(),
-            resume: self.resume.clone(),
-        }
-    }
-}

crates/g3-cli/src/coach_feedback.rs

@@ -1,124 +0,0 @@
-//! Coach feedback extraction from session logs.
-//!
-//! Extracts feedback from the coach agent's session logs for the coach-player loop.
-
-use anyhow::Result;
-use std::path::Path;
-
-use g3_core::Agent;
-
-use crate::simple_output::SimpleOutput;
-use crate::ui_writer_impl::ConsoleUiWriter;
-
-/// Extract coach feedback by reading from the coach agent's specific log file.
-///
-/// Uses the coach agent's session ID to find the exact log file.
-pub fn extract_from_logs(
-    coach_result: &g3_core::TaskResult,
-    coach_agent: &Agent<ConsoleUiWriter>,
-    output: &SimpleOutput,
-) -> Result<String> {
-    let session_id = coach_agent
-        .get_session_id()
-        .ok_or_else(|| anyhow::anyhow!("Coach agent has no session ID"))?;
-
-    let log_file_path = resolve_log_path(&session_id);
-
-    // Try to extract from session log
-    if let Some(feedback) = try_extract_from_log(&log_file_path) {
-        output.print(&format!("✅ Extracted coach feedback from session: {}", session_id));
-        return Ok(feedback);
-    }
-
-    // Fallback: use the TaskResult's extract_summary method
-    let fallback = coach_result.extract_summary();
-    if !fallback.is_empty() {
-        output.print(&format!(
-            "✅ Extracted coach feedback from response: {} chars",
-            fallback.len()
-        ));
-        return Ok(fallback);
-    }
-
-    Err(anyhow::anyhow!(
-        "Could not extract coach feedback from session: {}\n\
-         Log file path: {:?}\n\
-         Log file exists: {}\n\
-         Coach result response length: {} chars",
-        session_id,
-        log_file_path,
-        log_file_path.exists(),
-        coach_result.response.len()
-    ))
-}
-
-/// Resolve the log file path, trying new path first then falling back to old.
-fn resolve_log_path(session_id: &str) -> std::path::PathBuf {
-    g3_core::get_session_file(session_id)
-}
-
-/// Extract feedback from a session log file.
-///
-/// Searches backwards for the last assistant message with substantial text content.
-fn try_extract_from_log(log_file_path: &Path) -> Option<String> {
-    if !log_file_path.exists() {
-        return None;
-    }
-
-    let log_content = std::fs::read_to_string(log_file_path).ok()?;
-    let log_json: serde_json::Value = serde_json::from_str(&log_content).ok()?;
-
-    let messages = log_json
-        .get("context_window")?
-        .get("conversation_history")?
-        .as_array()?;
-
-    // Search backwards for the last assistant message with text content
-    for msg in messages.iter().rev() {
-        if let Some(feedback) = extract_assistant_text(msg) {
-            return Some(feedback);
-        }
-    }
-
-    None
-}
-
-/// Extract text content from an assistant message.
-fn extract_assistant_text(msg: &serde_json::Value) -> Option<String> {
-    let role = msg.get("role").and_then(|v| v.as_str())?;
-    if !role.eq_ignore_ascii_case("assistant") {
-        return None;
-    }
-
-    let content = msg.get("content")?;
-
-    // Handle string content
-    if let Some(content_str) = content.as_str() {
-        return filter_substantial_text(content_str);
-    }
-
-    // Handle array content (native tool calling format)
-    if let Some(content_array) = content.as_array() {
-        for block in content_array {
-            if block.get("type").and_then(|v| v.as_str()) == Some("text") {
-                if let Some(text) = block.get("text").and_then(|v| v.as_str()) {
-                    if let Some(result) = filter_substantial_text(text) {
-                        return Some(result);
-                    }
-                }
-            }
-        }
-    }
-
-    None
-}
-
-/// Filter out empty or very short responses (likely just tool calls).
-fn filter_substantial_text(text: &str) -> Option<String> {
-    let trimmed = text.trim();
-    if !trimmed.is_empty() && trimmed.len() > 10 {
-        Some(trimmed.to_string())
-    } else {
-        None
-    }
-}

crates/g3-cli/src/commands.rs

@@ -1,438 +0,0 @@
-//! Interactive command handlers for G3 CLI.
-//!
-//! Handles `/` commands in interactive mode (help, compact, etc.).
-
-use anyhow::Result;
-use rustyline::Editor;
-
-use g3_core::ui_writer::UiWriter;
-use g3_core::Agent;
-
-use crate::completion::G3Helper;
-use crate::g3_status::{G3Status, Status};
-use crate::simple_output::SimpleOutput;
-use crate::project::Project;
-use crate::project::load_and_validate_project;
-use crate::template::process_template;
-use crate::task_execution::execute_task_with_retry;
-
-/// Result of handling a command.
-#[derive(Debug, Clone, PartialEq, Eq)]
-pub enum CommandResult {
-    /// Command was handled, continue the loop
-    Handled,
-    /// Enter plan mode (after /plan command)
-    EnterPlanMode,
-}
-
-/// Handle a control command. Returns true if the command was handled and the loop should continue.
-pub async fn handle_command<W: UiWriter>(
-    input: &str,
-    agent: &mut Agent<W>,
-    workspace_dir: &std::path::Path,
-    output: &SimpleOutput,
-    active_project: &mut Option<Project>,
-    rl: &mut Editor<G3Helper, rustyline::history::DefaultHistory>,
-    show_prompt: bool,
-    show_code: bool,
-) -> Result<CommandResult> {
-    match input {
-        "/help" => {
-            output.print("");
-            output.print("📖 Control Commands:");
-            output.print("  /compact   - Trigger compaction (compacts conversation history)");
-            output.print("  /thinnify  - Trigger context thinning (replaces large tool results with file references)");
-            output.print("  /skinnify  - Trigger full context thinning (like /thinnify but for entire context, not just first third)");
-            output.print("  /clear     - Clear session and start fresh (discards continuation artifacts)");
-            output.print("  /fragments - List dehydrated context fragments (ACD)");
-            output.print("  /rehydrate - Restore a dehydrated fragment by ID");
-            output.print("  /resume    - List and switch to a previous session");
-            output.print("  /project <path> - Load a project from the given absolute path");
-            output.print("  /unproject - Unload the current project and reset context");
-            output.print("  /dump      - Dump entire context window to file for debugging");
-            output.print("  /readme    - Reload README.md and AGENTS.md from disk");
-            output.print("  /stats     - Show detailed context and performance statistics");
-            output.print("  /run <file> - Read file and execute as prompt");
-            output.print("  /plan <description> - Start Plan Mode for a new feature");
-            output.print("  /help      - Show this help message");
-            output.print("  exit/quit  - Exit the interactive session");
-            output.print("");
-            Ok(CommandResult::Handled)
-        }
-        "/compact" => {
-            output.print_g3_progress("compacting session");
-            match agent.force_compact().await {
-                Ok(true) => {
-                    output.print_g3_status("compacting session", "done");
-                }
-                Ok(false) => {
-                    output.print_g3_status("compacting session", "failed");
-                }
-                Err(e) => {
-                    output.print_g3_status("compacting session", &format!("error: {}", e));
-                }
-            }
-            Ok(CommandResult::Handled)
-        }
-        "/thinnify" => {
-            let result = agent.force_thin();
-            G3Status::thin_result(&result);
-            Ok(CommandResult::Handled)
-        }
-        "/skinnify" => {
-            let result = agent.force_thin_all();
-            G3Status::thin_result(&result);
-            Ok(CommandResult::Handled)
-        }
-        "/fragments" => {
-            if let Some(session_id) = agent.get_session_id() {
-                match g3_core::acd::list_fragments(session_id) {
-                    Ok(fragments) => {
-                        if fragments.is_empty() {
-                            output.print("No dehydrated fragments found for this session.");
-                        } else {
-                            output.print(&format!(
-                                "📦 {} dehydrated fragment(s):\n",
-                                fragments.len()
-                            ));
-                            for fragment in &fragments {
-                                output.print(&fragment.generate_stub());
-                                output.print("");
-                            }
-                        }
-                    }
-                    Err(e) => {
-                        output.print(&format!("❌ Error listing fragments: {}", e));
-                    }
-                }
-            } else {
-                output.print("No active session - fragments are session-scoped.");
-            }
-            Ok(CommandResult::Handled)
-        }
-        cmd if cmd.starts_with("/rehydrate") => {
-            let parts: Vec<&str> = cmd.splitn(2, ' ').collect();
-            if parts.len() < 2 || parts[1].trim().is_empty() {
-                output.print("Usage: /rehydrate <fragment_id>");
-                output.print("Use /fragments to list available fragment IDs.");
-            } else {
-                let fragment_id = parts[1].trim();
-                if let Some(session_id) = agent.get_session_id() {
-                    match g3_core::acd::Fragment::load(session_id, fragment_id) {
-                        Ok(fragment) => {
-                            output.print(&format!(
-                                "✅ Fragment '{}' loaded ({} messages, ~{} tokens)",
-                                fragment_id, fragment.message_count, fragment.estimated_tokens
-                            ));
-                            output.print("");
-                            output.print(&fragment.generate_stub());
-                        }
-                        Err(e) => {
-                            output.print(&format!(
-                                "❌ Failed to load fragment '{}': {}",
-                                fragment_id, e
-                            ));
-                        }
-                    }
-                } else {
-                    output.print("No active session - fragments are session-scoped.");
-                }
-            }
-            Ok(CommandResult::Handled)
-        }
-        cmd if cmd.starts_with("/run") => {
-            let parts: Vec<&str> = cmd.splitn(2, ' ').collect();
-            if parts.len() < 2 || parts[1].trim().is_empty() {
-                output.print("Usage: /run <file-path>");
-                output.print("Reads the file and executes its content as a prompt.");
-            } else {
-                let file_path = parts[1].trim();
-                // Expand tilde
-                let expanded_path = if file_path.starts_with("~/") {
-                    if let Some(home) = dirs::home_dir() {
-                        home.join(&file_path[2..])
-                    } else {
-                        std::path::PathBuf::from(file_path)
-                    }
-                } else {
-                    std::path::PathBuf::from(file_path)
-                };
-                match std::fs::read_to_string(&expanded_path) {
-                    Ok(content) => {
-                        let processed = process_template(&content);
-                        let prompt = processed.trim();
-                        if prompt.is_empty() {
-                            output.print("❌ File is empty.");
-                        } else {
-                            G3Status::progress(&format!("loading {}", file_path));
-                            G3Status::done();
-                            execute_task_with_retry(agent, prompt, show_prompt, show_code, output).await;
-                        }
-                    }
-                    Err(e) => {
-                        output.print(&format!("❌ Failed to read file '{}': {}", file_path, e));
-                    }
-                }
-            }
-            Ok(CommandResult::Handled)
-        }
-        "/dump" => {
-            // Dump entire context window to a file for debugging
-            let dump_dir = std::path::Path::new("tmp");
-            if !dump_dir.exists() {
-                if let Err(e) = std::fs::create_dir_all(dump_dir) {
-                    output.print(&format!("❌ Failed to create tmp directory: {}", e));
-                    return Ok(CommandResult::Handled);
-                }
-            }
-
-            let timestamp = chrono::Utc::now().format("%Y%m%d_%H%M%S");
-            let dump_path = dump_dir.join(format!("context_dump_{}.txt", timestamp));
-
-            let context = agent.get_context_window();
-            let mut dump_content = String::new();
-            dump_content.push_str("# Context Window Dump\n");
-            dump_content.push_str(&format!("# Timestamp: {}\n", chrono::Utc::now()));
-            dump_content.push_str(&format!(
-                "# Messages: {}\n",
-                context.conversation_history.len()
-            ));
-            dump_content.push_str(&format!(
-                "# Used tokens: {} / {} ({:.1}%)\n\n",
-                context.used_tokens,
-                context.total_tokens,
-                context.percentage_used()
-            ));
-
-            for (i, msg) in context.conversation_history.iter().enumerate() {
-                dump_content.push_str(&format!("=== Message {} ===\n", i));
-                dump_content.push_str(&format!("Role: {:?}\n", msg.role));
-                dump_content.push_str(&format!("Kind: {:?}\n", msg.kind));
-                dump_content.push_str(&format!("Content ({} chars):\n", msg.content.len()));
-                dump_content.push_str(&msg.content);
-                dump_content.push_str("\n\n");
-            }
-
-            match std::fs::write(&dump_path, &dump_content) {
-                Ok(_) => {
-                    G3Status::complete_with_path(
-                        "context dumped to",
-                        &dump_path.display().to_string(),
-                        Status::Done,
-                    );
-                }
-                Err(e) => output.print(&format!("❌ Failed to write dump: {}", e)),
-            }
-            Ok(CommandResult::Handled)
-        }
-        "/clear" => {
-            use crate::g3_status::G3Status;
-            G3Status::progress("clearing session");
-            agent.clear_session();
-            G3Status::done();
-            output.print("Starting fresh.");
-            Ok(CommandResult::Handled)
-        }
-        "/readme" => {
-            use crate::g3_status::G3Status;
-            G3Status::progress("reloading README");
-            match agent.reload_readme() {
-                Ok(true) => {
-                    G3Status::done();
-                }
-                Ok(false) => {
-                    G3Status::failed();
-                    output.print("No README was loaded at startup, cannot reload");
-                }
-                Err(e) => {
-                    G3Status::error(&e.to_string());
-                }
-            }
-            Ok(CommandResult::Handled)
-        }
-        "/stats" => {
-            let stats = agent.get_stats();
-            output.print(&stats);
-            Ok(CommandResult::Handled)
-        }
-        "/resume" => {
-            output.print("📋 Scanning for available sessions...");
-
-            match g3_core::list_sessions_for_directory() {
-                Ok(sessions) => {
-                    if sessions.is_empty() {
-                        output.print("No sessions found for this directory.");
-                        return Ok(CommandResult::Handled);
-                    }
-
-                    // Get current session ID to mark it
-                    let current_session_id = agent.get_session_id().map(|s| s.to_string());
-
-                    output.print("");
-                    output.print("Available sessions:");
-                    for (i, session) in sessions.iter().enumerate() {
-                        let time_str = g3_core::format_session_time(&session.created_at);
-                        let context_str = format!("{:.0}%", session.context_percentage);
-                        let current_marker =
-                            if current_session_id.as_deref() == Some(&session.session_id) {
-                                " (current)"
-                            } else {
-                                ""
-                            };
-                        let todo_marker = if session.has_incomplete_todos() {
-                            " 📝"
-                        } else {
-                            ""
-                        };
-
-                        // Use description if available, otherwise fall back to session ID
-                        let display_name = match &session.description {
-                            Some(desc) => format!("'{}'", desc),
-                            None => {
-                                if session.session_id.len() > 40 {
-                                    format!("{}...", &session.session_id[..40])
-                                } else {
-                                    session.session_id.clone()
-                                }
-                            }
-                        };
-                        output.print(&format!(
-                            "  {}. [{}] {} ({}){}{}\n",
-                            i + 1,
-                            time_str,
-                            display_name,
-                            context_str,
-                            todo_marker,
-                            current_marker
-                        ));
-                    }
-
-                    output.print_inline("\nSession number to resume (Enter to cancel): ");
-                    // Read user selection
-                    if let Ok(selection) = rl.readline("") {
-                        let selection = selection.trim();
-                        if selection.is_empty() {
-                            output.print("Cancelled.");
-                        } else if let Ok(num) = selection.parse::<usize>() {
-                            if num >= 1 && num <= sessions.len() {
-                                let selected = &sessions[num - 1];
-                                match agent.switch_to_session(selected) {
-                                    Ok(true) => {
-                                        G3Status::resuming(&selected.session_id, Status::Done);
-                                    }
-                                    Ok(false) => {
-                                        G3Status::resuming_summary(&selected.session_id);
-                                    }
-                                    Err(e) => {
-                                        G3Status::resuming(&selected.session_id, Status::Error(e.to_string()));
-                                    }
-                                }
-                            } else {
-                                output.print("Invalid selection.");
-                            }
-                        } else {
-                            output.print("Invalid input. Please enter a number.");
-                        }
-                    }
-                }
-                Err(e) => output.print(&format!("❌ Error listing sessions: {}", e)),
-            }
-            Ok(CommandResult::Handled)
-        }
-        cmd if cmd.starts_with("/project") => {
-            let parts: Vec<&str> = cmd.splitn(2, ' ').collect();
-            if parts.len() < 2 || parts[1].trim().is_empty() {
-                output.print("Usage: /project <absolute-path>");
-                output.print("Loads project files (brief.md, contacts.yaml, status.md) from the given path.");
-            } else {
-                let project_path_str = parts[1].trim();
-
-                // Use shared helper for validation and loading
-                match load_and_validate_project(project_path_str, workspace_dir) {
-                    Ok(project) => {
-                        // Set project content in agent's system message
-                        if agent.set_project_content(Some(project.content.clone())) {
-                            // Set project path on UI writer for path shortening
-                            let project_name = project.path
-                                .file_name()
-                                .and_then(|n| n.to_str())
-                                .unwrap_or("project")
-                                .to_string();
-                            agent.ui_writer().set_project_path(project.path.clone(), project_name);
-
-                            // Print loaded status
-                            let project_name = project.path.file_name()
-                                .and_then(|n| n.to_str()).unwrap_or("project");
-                            G3Status::loading_project(project_name, &project.format_loaded_status());
-
-                            // Store active project
-                            *active_project = Some(project);
-                        } else {
-                            output.print("❌ Failed to set project content in agent context.");
-                        }
-                    }
-                    Err(e) => {
-                        output.print(&format!("❌ {}", e));
-                    }
-                }
-            }
-            Ok(CommandResult::Handled)
-        }
-        cmd if cmd.starts_with("/plan") => {
-            let parts: Vec<&str> = cmd.splitn(2, ' ').collect();
-            if parts.len() < 2 || parts[1].trim().is_empty() {
-                output.print("Usage: /plan <description>");
-                output.print("Starts Plan Mode for a new feature. The agent will:");
-                output.print("  1. Research and draft a Plan with checks (happy/negative/boundary)");
-                output.print("  2. Ask clarifying questions if needed");
-                output.print("  3. Request approval before coding");
-                output.print("");
-                output.print("Example: /plan Add CSV import for comic book metadata");
-                Ok(CommandResult::Handled)
-            } else {
-                let feature_description = parts[1].trim();
-                
-                // Construct the feature prompt that instructs the agent to use Plan Mode
-                let prompt = format!(
-                    "I want to implement a new feature: {}\n\n\
-                    Please use Plan Mode to help me implement this:\n\
-                    1. First, research the codebase to understand where this feature should live\n\
-                    2. Draft a Plan using `plan_write` with items that have all three checks (happy, negative, boundary)\n\
-                    3. Ask me any clarifying questions if needed\n\
-                    4. Then ask me to approve the plan before you start coding\n\n\
-                    Do NOT start coding until I approve the plan.",
-                    feature_description
-                );
-                
-                // Print the welcome message for plan mode
-                output.print("   what shall we build today?");
-                
-                execute_task_with_retry(agent, &prompt, show_prompt, show_code, output).await;
-                
-                // Return EnterPlanMode to signal interactive loop to switch prompts
-                Ok(CommandResult::EnterPlanMode)
-            }
-        }
-        "/unproject" => {
-            if active_project.is_some() {
-                use crate::g3_status::G3Status;
-                G3Status::progress("unloading project");
-                agent.clear_project_content();
-                agent.ui_writer().clear_project();
-                *active_project = None;
-                G3Status::done();
-                output.print("Context reset to original system message.");
-            } else {
-                output.print("No project is currently loaded.");
-            }
-            Ok(CommandResult::Handled)
-        }
-        _ => {
-            output.print(&format!(
-                "❌ Unknown command: {}. Type /help for available commands.",
-                input
-            ));
-            Ok(CommandResult::Handled)
-        }
-    }
-}

crates/g3-cli/src/completion.rs

@@ -1,621 +0,0 @@
-//! Tab completion support for g3 interactive mode.
-//!
-//! Provides:
-//! - Prompt highlighting (colorizes project name in blue)
-//! - Command completion for `/` commands at line start
-//! - File path completion for `./`, `../`, `~/`, `/` prefixes
-//! - Session ID completion for `/resume` command
-//! - Project name completion for `/project` command (from ~/projects/)
-
-use rustyline::completion::{Completer, FilenameCompleter, Pair};
-use rustyline::error::ReadlineError;
-use rustyline::highlight::Highlighter;
-use rustyline::hint::Hinter;
-use rustyline::validate::Validator;
-use rustyline::{Context, Helper};
-use std::path::PathBuf;
-
-/// Available `/` commands for completion
-const COMMANDS: &[&str] = &[
-    "/clear",
-    "/compact",
-    "/dump",
-    "/fragments",
-    "/help",
-    "/project",
-    "/readme",
-    "/rehydrate",
-    "/resume",
-    "/run",
-    "/skinnify",
-    "/stats",
-    "/thinnify",
-    "/unproject",
-];
-
-/// Helper struct for rustyline that provides tab completion.
-pub struct G3Helper {
-    /// File path completer
-    file_completer: FilenameCompleter,
-}
-
-impl G3Helper {
-    pub fn new() -> Self {
-        Self {
-            file_completer: FilenameCompleter::new(),
-        }
-    }
-
-    /// Find the start of the current "word" being typed, respecting quotes.
-    /// Returns (word_start, word) where word_start is the byte index.
-    fn extract_word<'a>(&self, line: &'a str, pos: usize) -> (usize, &'a str) {
-        let line_to_cursor = &line[..pos];
-        
-        // Find word start: after space (unless quoted/escaped)
-        let mut word_start = 0;
-        let mut in_quotes = false;
-        let mut quote_char = ' ';
-        let mut prev_was_backslash = false;
-        
-        let chars: Vec<(usize, char)> = line_to_cursor.char_indices().collect();
-        for (idx, &(i, c)) in chars.iter().enumerate() {
-            if in_quotes {
-                if c == quote_char && !prev_was_backslash {
-                    in_quotes = false;
-                }
-            } else if prev_was_backslash {
-            } else {
-                match c {
-                    '"' | '\'' => {
-                        in_quotes = true;
-                        quote_char = c;
-                        word_start = i;
-                    }
-                    ' ' | '\t' => {
-                        if idx + 1 < chars.len() {
-                            word_start = chars[idx + 1].0;
-                        } else {
-                            word_start = pos; // At end, empty word
-                        }
-                    }
-                    _ => {}
-                }
-            }
-            prev_was_backslash = c == '\\' && !prev_was_backslash;
-        }
-        
-        (word_start, &line_to_cursor[word_start..])
-    }
-
-    fn is_path_prefix(&self, word: &str) -> bool {
-        let word = word.trim_start_matches('"').trim_start_matches('\'');
-        
-        word.starts_with("./")
-            || word.starts_with("../")
-            || word.starts_with("~/")
-            || word.starts_with('/')
-            || word == "."
-            || word == ".."
-            || word == "~"
-    }
-    
-    fn strip_quotes<'a>(&self, word: &'a str) -> &'a str {
-        word.trim_start_matches('"').trim_start_matches('\'')
-            .trim_end_matches('"').trim_end_matches('\'')
-    }
-    
-    /// Unescape backslash-escaped chars: "~/My\ Files" -> "~/My Files"
-    fn unescape_path(&self, path: &str) -> String {
-        let mut result = String::with_capacity(path.len());
-        let mut chars = path.chars().peekable();
-        while let Some(c) = chars.next() {
-            if c == '\\' && chars.peek().is_some() {
-                // Skip the backslash, take the next char literally
-                if let Some(next) = chars.next() {
-                    result.push(next);
-                }
-            } else {
-                result.push(c);
-            }
-        }
-        result
-    }
-    
-    /// List session IDs from .g3/sessions/, sorted newest-first, with optional limit.
-    fn list_sessions(&self, limit: Option<usize>) -> Vec<String> {
-        let sessions_dir = PathBuf::from(".g3/sessions");
-        if !sessions_dir.is_dir() {
-            return Vec::new();
-        }
-        
-        let mut sessions: Vec<_> = std::fs::read_dir(&sessions_dir)
-            .ok()
-            .map(|entries| {
-                entries
-                    .filter_map(|entry| entry.ok())
-                    .filter(|entry| entry.path().is_dir())
-                    .filter_map(|entry| {
-                        let modified = entry.metadata().ok()?.modified().ok()?;
-                        Some((entry.file_name().to_string_lossy().to_string(), modified))
-                    })
-                    .collect()
-            })
-            .unwrap_or_default();
-        
-        // Sort by modification time, newest first
-        sessions.sort_by(|a, b| b.1.cmp(&a.1));
-        
-        // Apply limit if specified
-        let sessions: Vec<String> = sessions
-            .into_iter()
-            .map(|(name, _)| name)
-            .take(limit.unwrap_or(usize::MAX))
-            .collect();
-        
-        sessions
-    }
-    
-    /// List project directories from ~/projects/, sorted alphabetically.
-    fn list_projects(&self, prefix: &str) -> Vec<String> {
-        let projects_dir = match dirs::home_dir() {
-            Some(home) => home.join("projects"),
-            None => return Vec::new(),
-        };
-        
-        if !projects_dir.is_dir() {
-            return Vec::new();
-        }
-        
-        let mut projects: Vec<String> = std::fs::read_dir(&projects_dir)
-            .ok()
-            .map(|entries| {
-                entries
-                    .filter_map(|entry| entry.ok())
-                    .filter(|entry| entry.path().is_dir())
-                    .filter_map(|entry| Some(entry.file_name().to_string_lossy().to_string()))
-                    .filter(|name| name.starts_with(prefix))
-                    .collect()
-            })
-            .unwrap_or_default();
-        
-        projects.sort();
-        projects
-    }
-}
-
-impl Default for G3Helper {
-    fn default() -> Self {
-        Self::new()
-    }
-}
-
-impl Completer for G3Helper {
-    type Candidate = Pair;
-
-    fn complete(
-        &self,
-        line: &str,
-        pos: usize,
-        ctx: &Context<'_>,
-    ) -> Result<(usize, Vec<Pair>), ReadlineError> {
-        let line_to_cursor = &line[..pos];
-        
-        // Extract the current word being typed
-        let (word_start, word) = self.extract_word(line, pos);
-        
-        // Case 1: Command completion at line start
-        if word_start == 0 && word.starts_with('/') && !word.contains(' ') {
-            let after_slash = &word[1..];
-            if !after_slash.contains('/') {
-                let matches: Vec<Pair> = COMMANDS
-                    .iter()
-                    .filter(|cmd| cmd.starts_with(word))
-                    .map(|cmd| Pair {
-                        display: cmd.to_string(),
-                        replacement: cmd.to_string(),
-                    })
-                    .collect();
-                
-                if !matches.is_empty() {
-                    return Ok((0, matches));
-                }
-            }
-        }
-        
-        // Case 2: Path completion for path-like prefixes (handles quotes ourselves)
-        if self.is_path_prefix(word) || (word_start > 0 && line_to_cursor[word_start..].starts_with('/')) {
-            let has_leading_quote = word.starts_with('"') || word.starts_with('\'');
-            let quote_char = if has_leading_quote { &word[..1] } else { "" };
-            let has_escapes = word.contains('\\');
-            
-            let path_str = self.strip_quotes(word);
-            let path_unescaped = self.unescape_path(path_str);
-            let path: &str = &path_unescaped;
-            
-            let (_rel_start, completions) = self.file_completer.complete(path, path.len(), ctx)?;
-            
-            if completions.is_empty() {
-                return Ok((pos, vec![]));
-            }
-            
-            let adjusted: Vec<Pair> = completions
-                .into_iter()
-                .map(|pair| {
-                    let has_spaces = pair.replacement.contains(' ');
-                    let replacement = if has_leading_quote {
-                        format!("{}{}{}", quote_char, pair.replacement, quote_char)
-                    } else if has_escapes && has_spaces {
-                        pair.replacement.replace(' ', "\\ ")
-                    } else if has_spaces {
-                        format!("\"{}\"" , pair.replacement)
-                    } else {
-                        pair.replacement
-                    };
-                    
-                    let needs_quotes = has_spaces || has_leading_quote;
-                    let display = if needs_quotes && !pair.display.starts_with('"') {
-                        format!("\"{}\"" , pair.display)
-                    } else {
-                        pair.display
-                    };
-                    
-                    Pair { display, replacement }
-                })
-                .collect();
-            
-            return Ok((word_start, adjusted));
-        }
-        
-        // Case 3: Path argument for /run command
-        if line_to_cursor.starts_with("/run ") {
-            let path = self.strip_quotes(word);
-            let (_, completions) = self.file_completer.complete(path, path.len(), ctx)?;
-            // Cyan color for command argument completions
-            let cyan_completions: Vec<Pair> = completions
-                .into_iter()
-                .map(|p| Pair {
-                    display: format!("\x1b[36m{}\x1b[0m", p.display),
-                    replacement: p.replacement,
-                })
-                .collect();
-            return Ok((word_start, cyan_completions));
-        }
-        
-        // Case 4: Session ID completion for /resume command
-        if line_to_cursor.starts_with("/resume ") {
-            let partial = word;
-            let sessions = self.list_sessions(None);
-            // Cyan color for command argument completions
-            let matches: Vec<Pair> = sessions
-                .into_iter()
-                .filter(|s| s.starts_with(partial))
-                .map(|s| Pair {
-                    display: format!("\x1b[36m{}\x1b[0m", s),
-                    replacement: s,
-                })
-                .take(8)
-                .collect();
-            return Ok((word_start, matches));
-        }
-
-        // Case 5: Project name completion for /project command
-        if line_to_cursor.starts_with("/project ") {
-            let partial = word;
-            let projects = self.list_projects(partial);
-            // Cyan color for command argument completions
-            let matches: Vec<Pair> = projects
-                .into_iter()
-                .map(|name| {
-                    let full_path = format!("~/projects/{}", name);
-                    Pair {
-                        display: format!("\x1b[36m{}\x1b[0m", name),
-                        replacement: full_path,
-                    }
-                })
-                .collect();
-            return Ok((word_start, matches));
-        }
-
-        // No completion for regular text
-        Ok((pos, vec![]))
-    }
-}
-
-// Required trait implementations for Helper
-impl Hinter for G3Helper {
-    type Hint = String;
-
-    fn hint(&self, _line: &str, _pos: usize, _ctx: &Context<'_>) -> Option<String> {
-        None
-    }
-}
-
-impl Highlighter for G3Helper {
-    fn highlight_prompt<'b, 's: 'b, 'p: 'b>(
-        &'s self,
-        prompt: &'p str,
-        _default: bool,
-    ) -> std::borrow::Cow<'b, str> {
-        // Plan mode prompt: colorize "[plan mode]" in magenta
-        if prompt.contains("[plan mode]") {
-            return std::borrow::Cow::Owned(
-                prompt.replace("[plan mode]", "\x1b[35m[plan mode]\x1b[0m")
-            );
-        }
-        
-        // If prompt contains " | ", colorize from "|" to ">" in blue
-        if let Some(pipe_pos) = prompt.find(" | ") {
-            if let Some(gt_pos) = prompt.rfind('>') {
-                let before = &prompt[..pipe_pos + 1]; // "butler "
-                let colored_part = &prompt[pipe_pos + 1..gt_pos + 1]; // "| project>"
-                let after = &prompt[gt_pos + 1..]; // " "
-                return std::borrow::Cow::Owned(format!(
-                    "{}\x1b[34m{}\x1b[0m{}",
-                    before, colored_part, after
-                ));
-            }
-        }
-        std::borrow::Cow::Borrowed(prompt)
-    }
-}
-
-impl Validator for G3Helper {}
-
-impl Helper for G3Helper {}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_command_completion() {
-        let helper = G3Helper::new();
-        let history = rustyline::history::DefaultHistory::new();
-        let ctx = Context::new(&history);
-
-        let (start, matches) = helper.complete("/com", 4, &ctx).unwrap();
-        assert_eq!(start, 0);
-        assert_eq!(matches.len(), 1);
-        assert_eq!(matches[0].replacement, "/compact");
-    }
-
-    #[test]
-    fn test_command_completion_multiple() {
-        let helper = G3Helper::new();
-        let history = rustyline::history::DefaultHistory::new();
-        let ctx = Context::new(&history);
-
-        let (start, matches) = helper.complete("/s", 2, &ctx).unwrap();
-        assert_eq!(start, 0);
-        assert_eq!(matches.len(), 2);
-        assert!(matches.iter().any(|m| m.replacement == "/skinnify"));
-        assert!(matches.iter().any(|m| m.replacement == "/stats"));
-    }
-
-    #[test]
-    fn test_path_prefix_detection() {
-        let helper = G3Helper::new();
-        
-        assert!(helper.is_path_prefix("./"));
-        assert!(helper.is_path_prefix("./src"));
-        assert!(helper.is_path_prefix("../"));
-        assert!(helper.is_path_prefix("~/"));
-        assert!(helper.is_path_prefix("~/Documents"));
-        assert!(helper.is_path_prefix("/etc"));
-        assert!(helper.is_path_prefix("."));
-        assert!(helper.is_path_prefix(".."));
-        assert!(helper.is_path_prefix("~"));
-        
-        assert!(!helper.is_path_prefix("hello"));
-        assert!(!helper.is_path_prefix("src"));
-    }
-
-    #[test]
-    fn test_extract_word_simple() {
-        let helper = G3Helper::new();
-        
-        let (start, word) = helper.extract_word("hello world", 11);
-        assert_eq!(start, 6);
-        assert_eq!(word, "world");
-    }
-
-    #[test]
-    fn test_extract_word_with_path() {
-        let helper = G3Helper::new();
-        
-        let (start, word) = helper.extract_word("edit ./src/main.rs", 18);
-        assert_eq!(start, 5);
-        assert_eq!(word, "./src/main.rs");
-    }
-
-    #[test]
-    fn test_extract_word_quoted() {
-        let helper = G3Helper::new();
-        
-        // Quoted path with spaces
-        let (start, word) = helper.extract_word("edit \"./My Files/doc", 20);
-        assert_eq!(start, 5);
-        assert_eq!(word, "\"./My Files/doc");
-    }
-
-    #[test]
-    fn test_no_completion_for_regular_input() {
-        let helper = G3Helper::new();
-        let history = rustyline::history::DefaultHistory::new();
-        let ctx = Context::new(&history);
-
-        // Regular text should not complete
-        let (start, matches) = helper.complete("hello world", 11, &ctx).unwrap();
-        assert_eq!(start, 11);
-        assert!(matches.is_empty());
-    }
-
-    #[test]
-    fn test_slash_at_start_is_command() {
-        let helper = G3Helper::new();
-        let history = rustyline::history::DefaultHistory::new();
-        let ctx = Context::new(&history);
-
-        // "/h" at start should complete to commands
-        let (start, matches) = helper.complete("/h", 2, &ctx).unwrap();
-        assert_eq!(start, 0);
-        assert!(matches.iter().any(|m| m.replacement == "/help"));
-    }
-
-    #[test]
-    fn test_actual_completion_with_quotes() {
-        let helper = G3Helper::new();
-        let history = rustyline::history::DefaultHistory::new();
-        let ctx = Context::new(&history);
-        
-        let line = "edit \"~/";
-        let pos = line.len();
-        match helper.complete(line, pos, &ctx) {
-            Ok((start, completions)) => {
-                assert!(start > 0 || completions.is_empty() || true); // Just verify no panic
-            }
-            Err(_) => {}
-        }
-        
-        let line = "edit ~/My\\ ";
-        let pos = line.len();
-        match helper.complete(line, pos, &ctx) {
-            Ok((start, completions)) => {
-                let _ = (start, completions); // Just verify no panic
-            }
-            Err(_) => {}
-        }
-        
-        let line = "edit \"~/\"";
-        let pos = line.len();
-        match helper.complete(line, pos, &ctx) {
-            Ok((start, completions)) => {
-                let _ = (start, completions);
-            }
-            Err(_) => {}
-        }
-    }
-
-    #[test]
-    fn test_no_completion_for_bare_quote() {
-        let helper = G3Helper::new();
-        let history = rustyline::history::DefaultHistory::new();
-        let ctx = Context::new(&history);
-        
-        let line = "edit \"";
-        let pos = line.len();
-        let (start, completions) = helper.complete(line, pos, &ctx).unwrap();
-        let _ = start;
-        assert_eq!(completions.len(), 0, "Bare quote should not trigger path completion");
-    }
-
-    #[test]
-    fn test_no_completion_for_random_text_in_quotes() {
-        let helper = G3Helper::new();
-        let history = rustyline::history::DefaultHistory::new();
-        let ctx = Context::new(&history);
-        
-        let line = "edit \"hello world";
-        let pos = line.len();
-        let (start, completions) = helper.complete(line, pos, &ctx).unwrap();
-        let _ = start;
-        assert_eq!(completions.len(), 0, "Random quoted text should not trigger path completion");
-        
-        let line = "edit \"foo";
-        let pos = line.len();
-        let (start, completions) = helper.complete(line, pos, &ctx).unwrap();
-        let _ = start;
-        assert_eq!(completions.len(), 0, "Quoted non-path should not trigger completion");
-    }
-
-    #[test]
-    fn test_resume_completion_lists_sessions() {
-        let helper = G3Helper::new();
-        let history = rustyline::history::DefaultHistory::new();
-        let ctx = Context::new(&history);
-        
-        let line = "/resume ";
-        let pos = line.len();
-        let (start, completions) = helper.complete(line, pos, &ctx).unwrap();
-        let _ = start;
-        
-        if std::path::Path::new(".g3/sessions").is_dir() {
-            assert!(completions.len() > 0, "Should list sessions when .g3/sessions exists");
-            
-            if let Some(first) = completions.first() {
-                let prefix = &first.replacement[..first.replacement.len().min(5)];
-                let line = format!("/resume {}", prefix);
-                let pos = line.len();
-                let (_, filtered) = helper.complete(&line, pos, &ctx).unwrap();
-                assert!(filtered.len() >= 1, "Should find at least one match");
-                assert!(filtered.iter().all(|p| p.replacement.starts_with(prefix)));
-            }
-        }
-        
-        let line = "/resume zzz_nonexistent_prefix_";
-        let pos = line.len();
-        let (_, completions) = helper.complete(line, pos, &ctx).unwrap();
-        assert_eq!(completions.len(), 0, "Non-matching prefix should return empty");
-    }
-
-    #[test]
-    fn test_highlight_prompt_plan_mode() {
-        let helper = G3Helper::new();
-        
-        // Plan mode prompt should be colorized with magenta
-        let prompt = " [plan mode] >> ";
-        let highlighted = helper.highlight_prompt(prompt, false);
-        assert!(highlighted.contains("\x1b[35m"), "Plan mode should use magenta color");
-        assert!(highlighted.contains("[plan mode]"), "Should contain [plan mode] text");
-        assert!(highlighted.contains("\x1b[0m"), "Should reset color");
-    }
-
-    #[test]
-    fn test_highlight_prompt_normal_unchanged() {
-        let helper = G3Helper::new();
-        
-        // Normal prompt without project should be unchanged
-        let prompt = "g3> ";
-        let highlighted = helper.highlight_prompt(prompt, false);
-        assert_eq!(highlighted.as_ref(), prompt, "Normal prompt should be unchanged");
-    }
-
-    #[test]
-    fn test_resume_completion_graceful_no_panic() {
-        let helper = G3Helper::new();
-        let sessions = helper.list_sessions(None);
-        let _ = sessions; // Just verify no panic
-    }
-    
-    #[test]
-    fn test_project_completion_lists_projects() {
-        let helper = G3Helper::new();
-        let history = rustyline::history::DefaultHistory::new();
-        let ctx = Context::new(&history);
-        
-        let line = "/project ";
-        let pos = line.len();
-        let (start, completions) = helper.complete(line, pos, &ctx).unwrap();
-        let _ = start;
-        
-        // If ~/projects exists and has directories, we should get completions
-        if let Some(home) = dirs::home_dir() {
-            let projects_dir = home.join("projects");
-            if projects_dir.is_dir() {
-                // Verify completions have the right format (display is name, replacement is ~/projects/name)
-                for completion in &completions {
-                    assert!(completion.replacement.starts_with("~/projects/"), 
-                        "Replacement should start with ~/projects/, got: {}", completion.replacement);
-                    assert!(!completion.display.contains('/'),
-                        "Display should be just the project name, got: {}", completion.display);
-                }
-            }
-        }
-        
-        // Test with a prefix that won't match anything
-        let line = "/project zzz_nonexistent_prefix_";
-        let pos = line.len();
-        let (_, completions) = helper.complete(line, pos, &ctx).unwrap();
-        assert_eq!(completions.len(), 0, "Non-matching prefix should return empty");
-    }
-}

crates/g3-cli/src/display.rs

@@ -1,343 +0,0 @@
-//! Display utilities for G3 CLI.
-//!
-//! Provides shared display functions used by both interactive mode and agent mode.
-
-use crossterm::style::{Color, ResetColor, SetForegroundColor};
-use std::path::Path;
-
-/// Format a workspace path for display, replacing home directory with ~.
-pub fn format_workspace_path(workspace_path: &Path) -> String {
-    let path_str = workspace_path.display().to_string();
-    dirs::home_dir()
-        .and_then(|home| {
-            path_str
-                .strip_prefix(&home.display().to_string())
-                .map(|s| format!("~{}", s))
-        })
-        .unwrap_or(path_str)
-}
-
-/// Shorten a path string for display by:
-/// 1. Replacing project directory prefix with `<project_name>/` (if project is active)
-/// 2. Replacing workspace directory prefix with `./`
-/// 3. Replacing home directory prefix with `~`
-///
-/// This is useful for tool output where paths should be concise.
-/// The project check happens first (most specific), then workspace, then home.
-pub fn shorten_path(path: &str, workspace_path: Option<&std::path::Path>, project: Option<(&std::path::Path, &str)>) -> String {
-    // First, try to make it relative to project (most specific)
-    if let Some((project_path, project_name)) = project {
-        let project_str = project_path.display().to_string();
-        if let Some(relative) = path.strip_prefix(&project_str) {
-            // Handle both "/subpath" and "" (exact match) cases
-            if relative.is_empty() {
-                return format!("{}/", project_name);
-            } else if let Some(stripped) = relative.strip_prefix('/') {
-                return format!("{}/{}", project_name, stripped);
-            }
-        }
-    }
-
-    // First, try to make it relative to workspace
-    if let Some(workspace) = workspace_path {
-        let workspace_str = workspace.display().to_string();
-        if let Some(relative) = path.strip_prefix(&workspace_str) {
-            // Handle both "/subpath" and "" (exact match) cases
-            if relative.is_empty() {
-                return "./".to_string();
-            } else if let Some(stripped) = relative.strip_prefix('/') {
-                return format!("./{}", stripped);
-            }
-        }
-    }
-
-    // Fall back to replacing home directory with ~
-    if let Some(home) = dirs::home_dir() {
-        let home_str = home.display().to_string();
-        if let Some(relative) = path.strip_prefix(&home_str) {
-            return format!("~{}", relative);
-        }
-    }
-
-    path.to_string()
-}
-
-/// Shorten any paths found within a shell command string.
-/// This replaces project paths with `<project_name>/`, workspace paths with `./`, and home paths with `~`.
-pub fn shorten_paths_in_command(command: &str, workspace_path: Option<&std::path::Path>, project: Option<(&std::path::Path, &str)>) -> String {
-    let mut result = command.to_string();
-
-    // First, replace project paths (most specific)
-    if let Some((project_path, project_name)) = project {
-        let project_str = project_path.display().to_string();
-        // Replace project path followed by / with project_name/
-        result = result.replace(&format!("{}/", project_str), &format!("{}/", project_name));
-        // Replace exact project path
-        result = result.replace(&project_str, project_name);
-    }
-
-    // Then, replace workspace paths
-    if let Some(workspace) = workspace_path {
-        let workspace_str = workspace.display().to_string();
-        // Replace workspace path followed by / with ./
-        result = result.replace(&format!("{}/", workspace_str), "./");
-        // Replace exact workspace path at word boundary
-        result = result.replace(&workspace_str, ".");
-    }
-
-    // Then replace home directory paths
-    if let Some(home) = dirs::home_dir() {
-        let home_str = home.display().to_string();
-        result = result.replace(&home_str, "~");
-    }
-
-    result
-}
-
-/// Print the workspace path in a consistent format.
-pub fn print_workspace_path(workspace_path: &Path) {
-    let display = format_workspace_path(workspace_path);
-    print!(
-        "{}-> {}{}",
-        SetForegroundColor(Color::DarkGrey),
-        display,
-        ResetColor
-    );
-    println!();
-}
-
-/// Information about what project files were loaded.
-#[derive(Default)]
-pub struct LoadedContent {
-    pub has_agents: bool,
-    pub has_memory: bool,
-    pub include_prompt_filename: Option<String>,
-}
-
-impl LoadedContent {
-    /// Create from explicit boolean flags.
-    pub fn new(has_agents: bool, has_memory: bool, include_prompt_filename: Option<String>) -> Self {
-        Self {
-            has_agents,
-            has_memory,
-            include_prompt_filename,
-        }
-    }
-
-    /// Create from combined content string by detecting markers.
-    pub fn from_combined_content(content: &str) -> Self {
-        Self {
-            has_agents: content.contains("Agent Configuration"),
-            has_memory: content.contains("=== Workspace Memory"),
-            include_prompt_filename: if content.contains("Included Prompt") {
-                Some("prompt".to_string()) // Default name when we can't determine the actual filename
-            } else {
-                None
-            },
-        }
-    }
-
-    /// Create with explicit include prompt filename.
-    #[allow(dead_code)] // Used in tests, may be useful for future callers
-    pub fn with_include_prompt_filename(mut self, filename: Option<String>) -> Self {
-        if self.include_prompt_filename.is_some() {
-            self.include_prompt_filename = filename;
-        }
-        self
-    }
-
-    /// Check if any content was loaded.
-    pub fn has_any(&self) -> bool {
-        self.has_agents || self.has_memory || self.include_prompt_filename.is_some()
-    }
-
-    /// Build a list of loaded item names in load order.
-    pub fn to_loaded_items(&self) -> Vec<String> {
-        let mut items = Vec::new();
-        if self.has_agents {
-            items.push("AGENTS.md".to_string());
-        }
-        if let Some(ref filename) = self.include_prompt_filename {
-            items.push(filename.clone());
-        }
-        if self.has_memory {
-            items.push("Memory".to_string());
-        }
-        items
-    }
-}
-
-/// Print a status line showing what project files were loaded.
-/// Format: "   ✓ README  ✓ AGENTS.md  ✓ Memory"
-pub fn print_loaded_status(loaded: &LoadedContent) {
-    if !loaded.has_any() {
-        return;
-    }
-
-    let items = loaded.to_loaded_items();
-    let status_str = items
-        .iter()
-        .map(|s| format!("✓ {}", s))
-        .collect::<Vec<_>>()
-        .join("  ");
-
-    print!(
-        "{}   {}{}",
-        SetForegroundColor(Color::DarkGrey),
-        status_str,
-        ResetColor
-    );
-    println!();
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use std::path::PathBuf;
-
-    #[test]
-    fn test_format_workspace_path_with_home() {
-        // This test depends on having a home directory
-        if let Some(home) = dirs::home_dir() {
-            let test_path = home.join("projects").join("myapp");
-            let formatted = format_workspace_path(&test_path);
-            assert!(formatted.starts_with("~/"), "Expected ~/ prefix, got: {}", formatted);
-            assert!(formatted.contains("projects/myapp"));
-        }
-    }
-
-    #[test]
-    fn test_format_workspace_path_without_home() {
-        let test_path = PathBuf::from("/tmp/workspace");
-        let formatted = format_workspace_path(&test_path);
-        assert_eq!(formatted, "/tmp/workspace");
-    }
-
-    #[test]
-    fn test_loaded_content_from_combined() {
-        let content = "Agent Configuration\n=== Workspace Memory";
-        let loaded = LoadedContent::from_combined_content(content);
-        assert!(loaded.has_agents);
-        assert!(loaded.has_memory);
-        assert!(loaded.include_prompt_filename.is_none());
-    }
-
-    #[test]
-    fn test_loaded_content_with_include_prompt() {
-        let content = "Agent Configuration\nIncluded Prompt";
-        let loaded = LoadedContent::from_combined_content(content)
-            .with_include_prompt_filename(Some("custom.md".to_string()));
-        assert!(loaded.has_agents);
-        assert_eq!(loaded.include_prompt_filename, Some("custom.md".to_string()));
-    }
-
-    #[test]
-    fn test_loaded_content_to_items_order() {
-        let loaded = LoadedContent {
-            has_agents: true,
-            has_memory: true,
-            include_prompt_filename: Some("prompt.md".to_string()),
-        };
-        let items = loaded.to_loaded_items();
-        assert_eq!(items, vec!["AGENTS.md", "prompt.md", "Memory"]);
-    }
-
-    #[test]
-    fn test_loaded_content_has_any() {
-        let empty = LoadedContent::default();
-        assert!(!empty.has_any());
-
-        let with_agents = LoadedContent {
-            has_agents: true,
-            ..Default::default()
-        };
-        assert!(with_agents.has_any());
-    }
-
-    #[test]
-    fn test_shorten_path_workspace_relative() {
-        let workspace = PathBuf::from("/Users/test/projects/myapp");
-        let path = "/Users/test/projects/myapp/src/main.rs";
-        let shortened = shorten_path(path, Some(&workspace), None);
-        assert_eq!(shortened, "./src/main.rs");
-    }
-
-    #[test]
-    fn test_shorten_path_workspace_exact() {
-        let workspace = PathBuf::from("/Users/test/projects/myapp");
-        let path = "/Users/test/projects/myapp";
-        let shortened = shorten_path(path, Some(&workspace), None);
-        assert_eq!(shortened, "./");
-    }
-
-    #[test]
-    fn test_shorten_path_home_relative() {
-        // This test depends on having a home directory
-        if let Some(home) = dirs::home_dir() {
-            let path = format!("{}/other/project/file.rs", home.display());
-            let shortened = shorten_path(&path, None, None);
-            assert_eq!(shortened, "~/other/project/file.rs");
-        }
-    }
-
-    #[test]
-    fn test_shorten_path_no_match() {
-        let workspace = PathBuf::from("/Users/test/projects/myapp");
-        let path = "/tmp/other/file.rs";
-        let shortened = shorten_path(path, Some(&workspace), None);
-        assert_eq!(shortened, "/tmp/other/file.rs");
-    }
-
-    #[test]
-    fn test_shorten_path_project_relative() {
-        let workspace = PathBuf::from("/Users/test/projects");
-        let project_path = PathBuf::from("/Users/test/projects/appa_estate");
-        let path = "/Users/test/projects/appa_estate/status.md";
-        let shortened = shorten_path(path, Some(&workspace), Some((&project_path, "appa_estate")));
-        assert_eq!(shortened, "appa_estate/status.md");
-    }
-
-    #[test]
-    fn test_shorten_path_project_takes_priority() {
-        // Project path is under workspace, but project shortening should take priority
-        let workspace = PathBuf::from("/Users/test/projects");
-        let project_path = PathBuf::from("/Users/test/projects/appa_estate");
-        let path = "/Users/test/projects/appa_estate/src/main.rs";
-        let shortened = shorten_path(path, Some(&workspace), Some((&project_path, "appa_estate")));
-        assert_eq!(shortened, "appa_estate/src/main.rs");
-    }
-
-    #[test]
-    fn test_shorten_paths_in_command_workspace() {
-        let workspace = PathBuf::from("/Users/test/projects/myapp");
-        let command = "cat /Users/test/projects/myapp/src/main.rs";
-        let shortened = shorten_paths_in_command(command, Some(&workspace), None);
-        assert_eq!(shortened, "cat ./src/main.rs");
-    }
-
-    #[test]
-    fn test_shorten_paths_in_command_home() {
-        if let Some(home) = dirs::home_dir() {
-            let command = format!("ls {}/Documents", home.display());
-            let shortened = shorten_paths_in_command(&command, None, None);
-            assert_eq!(shortened, "ls ~/Documents");
-        }
-    }
-
-    #[test]
-    fn test_shorten_paths_in_command_multiple() {
-        let workspace = PathBuf::from("/Users/test/projects/myapp");
-        let command = "diff /Users/test/projects/myapp/a.rs /Users/test/projects/myapp/b.rs";
-        let shortened = shorten_paths_in_command(command, Some(&workspace), None);
-        assert_eq!(shortened, "diff ./a.rs ./b.rs");
-    }
-
-    #[test]
-    fn test_shorten_paths_in_command_project() {
-        let workspace = PathBuf::from("/Users/test/projects");
-        let project_path = PathBuf::from("/Users/test/projects/appa_estate");
-        let command = "cat /Users/test/projects/appa_estate/status.md";
-        let shortened = shorten_paths_in_command(command, Some(&workspace), Some((&project_path, "appa_estate")));
-        assert_eq!(shortened, "cat appa_estate/status.md");
-    }
-}

crates/g3-cli/src/embedded_agents.rs

@@ -1,120 +0,0 @@
-//! Embedded agent prompts - compiled into the binary for portability.
-//!
-//! Agent prompts are embedded at compile time using `include_str!`.
-//! This allows g3 to run on any repository without needing the agents/ directory.
-//!
-//! Priority order for loading agent prompts:
-//! 1. Workspace `agents/<name>.md` (allows per-project customization)
-//! 2. Embedded prompts (fallback, always available)
-
-use std::collections::HashMap;
-use std::path::Path;
-
-use crate::template::process_template;
-
-/// Embedded agent prompts, keyed by agent name.
-static EMBEDDED_AGENTS: &[(&str, &str)] = &[
-    ("breaker", include_str!("../../../agents/breaker.md")),
-    ("carmack", include_str!("../../../agents/carmack.md")),
-    ("euler", include_str!("../../../agents/euler.md")),
-    ("fowler", include_str!("../../../agents/fowler.md")),
-    ("hopper", include_str!("../../../agents/hopper.md")),
-    ("huffman", include_str!("../../../agents/huffman.md")),
-    ("lamport", include_str!("../../../agents/lamport.md")),
-    ("scout", include_str!("../../../agents/scout.md")),
-    ("solon", include_str!("../../../agents/solon.md")),
-];
-
-/// Get an embedded agent prompt by name.
-pub fn get_embedded_agent(name: &str) -> Option<&'static str> {
-    EMBEDDED_AGENTS
-        .iter()
-        .find(|(n, _)| *n == name)
-        .map(|(_, content)| *content)
-}
-
-/// Get all available embedded agent names.
-pub fn list_embedded_agents() -> Vec<&'static str> {
-    EMBEDDED_AGENTS.iter().map(|(name, _)| *name).collect()
-}
-
-/// Load an agent prompt, checking workspace first, then falling back to embedded.
-///
-/// Returns the prompt content and a boolean indicating if it was loaded from disk (true)
-/// or embedded (false).
-pub fn load_agent_prompt(name: &str, workspace_dir: &Path) -> Option<(String, bool)> {
-    // First, try workspace agents/<name>.md
-    let workspace_path = workspace_dir.join("agents").join(format!("{}.md", name));
-    if workspace_path.exists() {
-        if let Ok(content) = std::fs::read_to_string(&workspace_path) {
-            let processed = process_template(&content);
-            return Some((processed, true));
-        }
-    }
-
-    // Fall back to embedded prompt
-    get_embedded_agent(name).map(|content| (process_template(content), false))
-}
-
-/// Get a map of all available agents (both embedded and from workspace).
-pub fn get_available_agents(workspace_dir: &Path) -> HashMap<String, bool> {
-    let mut agents = HashMap::new();
-
-    // Add all embedded agents
-    for name in list_embedded_agents() {
-        agents.insert(name.to_string(), false); // false = embedded
-    }
-
-    // Check for workspace agents (these override embedded)
-    let agents_dir = workspace_dir.join("agents");
-    if agents_dir.is_dir() {
-        if let Ok(entries) = std::fs::read_dir(&agents_dir) {
-            for entry in entries.flatten() {
-                let path = entry.path();
-                if path.extension().map_or(false, |ext| ext == "md") {
-                    if let Some(stem) = path.file_stem().and_then(|s| s.to_str()) {
-                        agents.insert(stem.to_string(), true); // true = from disk
-                    }
-                }
-            }
-        }
-    }
-
-    agents
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_embedded_agents_exist() {
-        // Verify all expected agents are embedded
-        let expected = ["breaker", "carmack", "euler", "fowler", "hopper", "huffman", "lamport", "scout", "solon"];
-        for name in expected {
-            assert!(
-                get_embedded_agent(name).is_some(),
-                "Agent '{}' should be embedded",
-                name
-            );
-        }
-    }
-
-    #[test]
-    fn test_list_embedded_agents() {
-        let agents = list_embedded_agents();
-        assert!(agents.len() >= 9, "Should have at least 9 embedded agents");
-        assert!(agents.contains(&"carmack"));
-        assert!(agents.contains(&"hopper"));
-    }
-
-    #[test]
-    fn test_embedded_agent_content() {
-        // Verify the content looks reasonable
-        let carmack = get_embedded_agent("carmack").unwrap();
-        assert!(carmack.contains("Carmack"), "Carmack prompt should mention Carmack");
-        
-        let hopper = get_embedded_agent("hopper").unwrap();
-        assert!(hopper.contains("Hopper"), "Hopper prompt should mention Hopper");
-    }
-}

crates/g3-cli/src/filter_json.rs

@@ -1,613 +0,0 @@
-//! JSON tool call filtering for streaming LLM responses.
-//!
-//! This module filters out JSON tool calls from LLM output streams while preserving
-//! regular text content. It uses a simple state machine optimized for streaming.
-//!
-//! # Design
-//!
-//! The filter uses three states:
-//! - **Streaming**: Normal pass-through mode. Watches for newline + whitespace + `{`
-//! - **Buffering**: Saw potential tool call start, buffering to confirm/deny
-//! - **Suppressing**: Confirmed tool call, counting braces (string-aware) to find end
-//!
-//! The key insight is that we only need to buffer a small amount (around 12 chars)
-//! to confirm whether `{` starts a tool call pattern like `{"tool":`.
-
-use std::cell::RefCell;
-use tracing::debug;
-
-/// Maximum chars needed to confirm/deny a tool call pattern.
-/// Pattern is: { + optional whitespace + "tool" + optional whitespace + : + optional whitespace + "
-/// Realistically: `{"tool":"` = 9 chars, with whitespace maybe 15 max
-const MAX_BUFFER_FOR_DETECTION: usize = 20;
-
-/// Hints emitted during tool call parsing for UI feedback.
-#[derive(Debug, Clone)]
-pub enum ToolParsingHint {
-    /// Tool call detected, name is known. UI should show " ● tool_name |"
-    Detected(String),
-    /// More characters being parsed. UI should blink the indicator.
-    Active,
-    /// Tool call JSON fully parsed. UI should clear the parsing indicator.
-    Complete,
-}
-
-// Thread-local state for tracking JSON tool call suppression
-thread_local! {
-    static JSON_TOOL_STATE: RefCell<FilterState> = RefCell::new(FilterState::new());
-}
-
-/// The three possible states of the filter
-#[derive(Debug, Clone, PartialEq)]
-enum State {
-    /// Normal streaming - pass through content, watch for newline + whitespace + {
-    Streaming,
-    /// Saw potential start, buffering to confirm/deny tool pattern
-    Buffering,
-    /// Confirmed tool call, suppressing until braces balance
-    Suppressing,
-}
-
-/// Internal state for the filter
-#[derive(Debug, Clone)]
-struct FilterState {
-    state: State,
-    /// Buffer for potential tool call detection (Buffering state)
-    buffer: String,
-    /// Are we inside a code fence? (``` ... ```)
-    in_code_fence: bool,
-    /// Buffer for detecting code fence markers
-    fence_buffer: String,
-    /// Brace depth for JSON tracking (Suppressing state) - string-aware
-    brace_depth: i32,
-    /// Are we inside a JSON string? (for proper brace counting)
-    in_string: bool,
-    /// Was the previous char a backslash? (for escape handling)
-    escape_next: bool,
-    /// Track if we just saw a newline (to detect line-start patterns)
-    at_line_start: bool,
-    /// Whitespace seen after newline (before potential {)
-    pending_whitespace: String,
-    /// Newlines accumulated at line start (before potential tool call)
-    pending_newlines: String,
-}
-
-impl FilterState {
-    fn new() -> Self {
-        Self {
-            state: State::Streaming,
-            buffer: String::new(),
-            in_code_fence: false,
-            fence_buffer: String::new(),
-            brace_depth: 0,
-            in_string: false,
-            escape_next: false,
-            at_line_start: true, // Start of input counts as line start
-            pending_whitespace: String::new(),
-            pending_newlines: String::new(),
-        }
-    }
-
-    fn reset(&mut self) {
-        self.state = State::Streaming;
-        self.buffer.clear();
-        self.in_code_fence = false;
-        self.fence_buffer.clear();
-        self.brace_depth = 0;
-        self.in_string = false;
-        self.escape_next = false;
-        self.at_line_start = true;
-        self.pending_whitespace.clear();
-        self.pending_newlines.clear();
-    }
-}
-
-/// Check if buffer matches the tool call pattern.
-/// Pattern: `{` followed by optional whitespace, `"tool"`, optional whitespace, `:`, optional whitespace, `"`
-/// 
-/// Returns:
-/// - Some(true) if confirmed as tool call
-/// - Some(false) if confirmed NOT a tool call  
-/// - None if need more data
-fn check_tool_pattern(buffer: &str) -> Option<bool> {
-    // Must start with {
-    if !buffer.starts_with('{') {
-        return Some(false);
-    }
-
-    let trimmed = buffer[1..].trim_start();
-
-    // Need at least `"tool":"` = 8 chars after whitespace
-    if trimmed.len() < 8 {
-        // Early rejection: check progressive prefix of "tool
-        if let Some(after_quote) = trimmed.strip_prefix('"') {
-            // Check each prefix of "tool" we have so far
-            for (i, expected) in ["t", "to", "too", "tool"].iter().enumerate() {
-                if after_quote.len() > i && !after_quote.starts_with(expected) {
-                    return Some(false);
-                }
-            }
-        } else if !trimmed.is_empty() && !trimmed.starts_with('"') {
-            return Some(false);
-        }
-        return None;
-    }
-
-    // Full pattern check: "tool" : "
-    if !trimmed.starts_with("\"tool\"") {
-        return Some(false);
-    }
-
-    let after_tool = trimmed[6..].trim_start();
-    if after_tool.is_empty() {
-        return None;
-    }
-    if !after_tool.starts_with(':') {
-        return Some(false);
-    }
-
-    let after_colon = after_tool[1..].trim_start();
-    if after_colon.is_empty() {
-        return None;
-    }
-
-    Some(after_colon.starts_with('"'))
-}
-
-/// Filters JSON tool calls from streaming LLM content.
-///
-/// Processes content character-by-character and removes JSON tool calls 
-/// while preserving regular text. Maintains state across calls.
-///
-/// # Arguments
-/// * `content` - A chunk of streaming content from the LLM
-///
-/// # Returns
-/// The filtered content with JSON tool calls removed
-pub fn filter_json_tool_calls(content: &str) -> String {
-    if content.is_empty() {
-        return String::new();
-    }
-
-    JSON_TOOL_STATE.with(|state| {
-        let mut state = state.borrow_mut();
-        let mut output = String::new();
-        
-        for ch in content.chars() {
-            match state.state {
-                State::Streaming => {
-                    handle_streaming_char(&mut state, ch, &mut output);
-                }
-                State::Buffering => {
-                    handle_buffering_char(&mut state, ch, &mut output);
-                }
-                State::Suppressing => {
-                    handle_suppressing_char(&mut state, ch, &mut output);
-                }
-            }
-        }
-        
-        output
-    })
-}
-
-/// Handle a character in Streaming state
-fn handle_streaming_char(state: &mut FilterState, ch: char, output: &mut String) {
-    // Track code fence state
-    track_code_fence(state, ch);
-    
-    // If inside a code fence, pass through everything
-    if state.in_code_fence {
-        pass_through_char(state, ch, output);
-        return;
-    }
-    
-    match ch {
-        '\n' => {
-            // Buffer extra newlines at line start - they may precede a tool call
-            // Always output the first newline, but buffer subsequent ones
-            if state.at_line_start {
-                state.pending_newlines.push(ch);
-            } else {
-                // First newline after content - output it and enter line start mode
-                output.push(ch);
-                state.at_line_start = true;
-                state.pending_newlines.clear(); // Reset - this newline was output
-            }
-        }
-        ' ' | '\t' if state.at_line_start => {
-            // Accumulate whitespace at line start
-            state.pending_whitespace.push(ch);
-        }
-        '{' if state.at_line_start && state.pending_whitespace.is_empty() => {
-            // Potential tool call! Enter buffering mode
-            // BUT only if there's no leading whitespace (indented JSON is not a tool call)
-            debug!("Potential tool call detected - entering Buffering state");
-            state.state = State::Buffering;
-            state.buffer.clear();
-            state.buffer.push(ch);
-            // Don't output pending_newlines or pending_whitespace yet - we might need to suppress them
-        }
-        '{' if state.at_line_start && !state.pending_whitespace.is_empty() => {
-            // Indented JSON - not a tool call, pass through
-            output.push_str(&state.pending_newlines);
-            output.push_str(&state.pending_whitespace);
-            state.pending_newlines.clear();
-            state.pending_whitespace.clear();
-            output.push(ch);
-            state.at_line_start = false;
-        }
-        _ => {
-            // Regular character - output any pending newlines and whitespace first
-            output.push_str(&state.pending_newlines);
-            state.pending_newlines.clear();
-            output.push_str(&state.pending_whitespace);
-            state.pending_whitespace.clear();
-            output.push(ch);
-            state.at_line_start = false;
-        }
-    }
-}
-
-/// Pass through a character without filtering (used inside code fences)
-fn pass_through_char(state: &mut FilterState, ch: char, output: &mut String) {
-    // Output any pending content first
-    output.push_str(&state.pending_newlines);
-    output.push_str(&state.pending_whitespace);
-    state.pending_newlines.clear();
-    state.pending_whitespace.clear();
-    output.push(ch);
-    state.at_line_start = ch == '\n';
-}
-
-/// Track code fence state (``` markers)
-fn track_code_fence(state: &mut FilterState, ch: char) {
-    match ch {
-        '`' => {
-            state.fence_buffer.push(ch);
-        }
-        '\n' => {
-            // Check if we have a fence marker
-            if state.fence_buffer.starts_with("```") {
-                // Toggle fence state
-                state.in_code_fence = !state.in_code_fence;
-                debug!("Code fence toggled: in_code_fence={}", state.in_code_fence);
-            }
-            state.fence_buffer.clear();
-        }
-        _ => {
-            // If we were accumulating backticks but got something else,
-            // check if we have a fence marker (for opening fences with language)
-            if state.fence_buffer.starts_with("```") && !state.in_code_fence {
-                // Opening fence with language specifier (e.g., ```json)
-                state.in_code_fence = true;
-                debug!("Code fence opened with language: in_code_fence=true");
-            }
-            state.fence_buffer.clear();
-        }
-    }
-}
-
-/// Handle a character in Buffering state
-fn handle_buffering_char(state: &mut FilterState, ch: char, output: &mut String) {
-    state.buffer.push(ch);
-    
-    // Check if we can determine tool call status
-    match check_tool_pattern(&state.buffer) {
-        Some(true) => {
-            // Confirmed tool call! Enter suppression mode
-            debug!("Confirmed tool call - entering Suppressing state");
-            state.state = State::Suppressing;
-            state.brace_depth = 1; // We already have the opening {
-            state.in_string = true; // We're inside the "tool" value string
-            state.escape_next = false;
-            // Discard pending_newlines and pending_whitespace (they're part of the tool call)
-            state.pending_newlines.clear();
-            state.pending_whitespace.clear();
-            state.buffer.clear();
-        }
-        Some(false) => {
-            // Not a tool call - release buffered content
-            debug!("Not a tool call - releasing buffer");
-            output.push_str(&state.pending_newlines);
-            output.push_str(&state.pending_whitespace);
-            output.push_str(&state.buffer);
-            state.pending_newlines.clear();
-            state.pending_whitespace.clear();
-            state.buffer.clear();
-            state.state = State::Streaming;
-            state.at_line_start = ch == '\n';
-        }
-        None => {
-            // Need more data - check if buffer is getting too long
-            if state.buffer.len() > MAX_BUFFER_FOR_DETECTION {
-                // Too long without confirmation - not a tool call
-                debug!("Buffer exceeded max length - not a tool call");
-                output.push_str(&state.pending_newlines);
-                output.push_str(&state.pending_whitespace);
-                output.push_str(&state.buffer);
-                state.pending_newlines.clear();
-                state.pending_whitespace.clear();
-                state.buffer.clear();
-                state.state = State::Streaming;
-                state.at_line_start = false;
-            }
-            // Otherwise keep buffering
-        }
-    }
-}
-
-/// Handle a character in Suppressing state (string-aware brace counting)  
-fn handle_suppressing_char(state: &mut FilterState, ch: char, _output: &mut String) {
-    // Track chars to detect if we see a new tool call pattern while suppressing
-    // This handles truncated JSON followed by complete JSON
-    state.buffer.push(ch);
-    
-    // Handle escape sequences
-    if state.escape_next {
-        state.escape_next = false;
-        return;
-    }
-    
-    match ch {
-        '\\' if state.in_string => {
-            state.escape_next = true;
-        }
-        '"' => {
-            state.in_string = !state.in_string;
-        }
-        '{' if !state.in_string => {
-            state.brace_depth += 1;
-        }
-        '}' if !state.in_string => {
-            state.brace_depth -= 1;
-            if state.brace_depth <= 0 {
-                // JSON complete! Return to streaming
-                debug!("Tool call complete - returning to Streaming state");
-                state.state = State::Streaming;
-                state.at_line_start = false; // We're right after the }
-                state.in_string = false;
-                state.escape_next = false;
-                state.buffer.clear();
-            }
-        }
-        _ => {}
-    }
-    
-    // Check if we're seeing a new tool call pattern (truncated JSON case)  
-    // This can happen with or without a newline before the new {
-    // Look for { followed by tool pattern in the buffer
-    if state.buffer.len() >= 10 {
-        // Find the last { that could start a new tool call
-        for (i, c) in state.buffer.char_indices().rev() {
-            if c == '{' && i > 0 {
-                let potential_tool = &state.buffer[i..];
-                if let Some(true) = check_tool_pattern(potential_tool) {
-                    // New tool call detected! Restart suppression from here
-                    debug!("New tool call detected while suppressing - restarting");
-                    state.brace_depth = 1;
-                    state.in_string = true;
-                    // Keep only the part after the new { for continued tracking
-                    state.buffer = potential_tool.to_string();
-                    return;
-                }
-            }
-        }
-        
-        // Limit buffer size to prevent unbounded growth
-        if state.buffer.len() > 200 {
-            // Find a valid character boundary near the 100-byte mark from the end
-            // We can't just slice at byte offset - multi-byte chars (like emojis) would panic
-            let target_keep = state.buffer.len() - 100;
-            // Find the nearest char boundary at or after target_keep
-            let keep_from = state.buffer.char_indices()
-                .map(|(i, _)| i)
-                .find(|&i| i >= target_keep)
-                .unwrap_or(0);
-            state.buffer = state.buffer[keep_from..].to_string();
-        }
-    }
-}
-
-/// Resets the global JSON filtering state.
-///
-/// Call this between independent filtering sessions to ensure clean state.
-/// This is particularly important in tests and when starting new conversations.
-pub fn reset_json_tool_state() {
-    JSON_TOOL_STATE.with(|state| {
-        let mut state = state.borrow_mut();
-        state.reset();
-    });
-}
-
-/// Flushes any pending content from the JSON filter.
-///
-/// Call this at the end of streaming to ensure any buffered newlines
-/// or whitespace that wasn't followed by a tool call gets output.
-pub fn flush_json_tool_filter() -> String {
-    JSON_TOOL_STATE.with(|state| {
-        let mut state = state.borrow_mut();
-        let mut output = String::new();
-        // Output any pending newlines and whitespace
-        output.push_str(&state.pending_newlines);
-        output.push_str(&state.pending_whitespace);
-        output.push_str(&state.buffer);
-        state.pending_newlines.clear();
-        state.pending_whitespace.clear();
-        state.buffer.clear();
-        output
-    })
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_check_tool_pattern_confirmed() {
-        assert_eq!(check_tool_pattern(r#"{"tool":""
-"#), Some(true));
-        assert_eq!(check_tool_pattern(r#"{"tool": "shell""#), Some(true));
-        assert_eq!(check_tool_pattern(r#"{ "tool" : "test""#), Some(true));
-    }
-
-    #[test]
-    fn test_check_tool_pattern_rejected() {
-        assert_eq!(check_tool_pattern(r#"{"other": "value"}"#), Some(false));
-        assert_eq!(check_tool_pattern(r#"{"tools": "value"}"#), Some(false));
-        assert_eq!(check_tool_pattern(r#"{"tool": 123}"#), Some(false)); // number not string
-    }
-
-    #[test]
-    fn test_check_tool_pattern_need_more() {
-        assert_eq!(check_tool_pattern(r#"{"#), None);
-        assert_eq!(check_tool_pattern(r#"{"tool"#), None);
-        assert_eq!(check_tool_pattern(r#"{"tool":"#), None);
-    }
-
-    #[test]
-    fn test_passthrough_no_tool() {
-        reset_json_tool_state();
-        let input = "Hello world";
-        assert_eq!(filter_json_tool_calls(input), input);
-    }
-
-    #[test]
-    fn test_simple_tool_filtered() {
-        reset_json_tool_state();
-        let input = "Before\n{\"tool\": \"shell\", \"args\": {}}\nAfter";
-        let result = filter_json_tool_calls(input);
-        assert_eq!(result, "Before\n\nAfter");
-    }
-
-    #[test]
-    fn test_tool_with_braces_in_string() {
-        reset_json_tool_state();
-        let input = "Text\n{\"tool\": \"shell\", \"args\": {\"cmd\": \"echo }\"}}\nMore";
-        let result = filter_json_tool_calls(input);
-        assert_eq!(result, "Text\n\nMore");
-    }
-
-    #[test]
-    fn test_non_tool_json_passes_through() {
-        reset_json_tool_state();
-        let input = "Text\n{\"other\": \"value\"}\nMore";
-        let result = filter_json_tool_calls(input);
-        assert_eq!(result, input);
-    }
-
-    #[test]
-    fn test_streaming_chunks() {
-        reset_json_tool_state();
-        let chunks = vec![
-            "Before\n",
-            "{\"tool\": \"",
-            "shell\", \"args\": {}",
-            "}\nAfter",
-        ];
-        let mut result = String::new();
-        for chunk in chunks {
-            result.push_str(&filter_json_tool_calls(chunk));
-        }
-        assert_eq!(result, "Before\n\nAfter");
-    }
-
-    #[test]
-    fn test_buffer_truncation_with_multibyte_chars() {
-        // This test ensures that buffer truncation doesn't panic on multi-byte characters
-        // The bug was: slicing at byte offset 100 from end could land mid-emoji
-        reset_json_tool_state();
-        
-        // Create a string with emojis that's over 200 bytes to trigger truncation
-        // Each emoji is 4 bytes, so we need ~50+ emojis to exceed 200 bytes
-        let emoji_heavy = "🔄".repeat(60); // 240 bytes of emojis
-        let input = format!("Text\n{{\"tool\": \"shell\", \"args\": {{\"data\": \"{}\"}}}}\nMore", emoji_heavy);
-        
-        // This should not panic - the fix ensures we find valid char boundaries
-        let result = filter_json_tool_calls(&input);
-        
-        // The tool call should be filtered out
-        assert_eq!(result, "Text\n\nMore");
-    }
-
-    #[test]
-    fn test_multiple_newlines_before_tool_call_suppressed() {
-        // This test verifies that extra blank lines before a tool call are suppressed.
-        // This fixes the visual issue where many blank lines appeared before tool calls.
-        reset_json_tool_state();
-        
-        // Input has 4 newlines before the tool call (3 blank lines)
-        let input = "Before\n\n\n\n{\"tool\": \"shell\", \"args\": {}}\nAfter";
-        let result = filter_json_tool_calls(input);
-        
-        // Only one newline should remain before where the tool call was
-        // (the first newline after "Before" is preserved, extra ones are suppressed)
-        assert_eq!(result, "Before\n\nAfter");
-    }
-
-    #[test]
-    fn test_single_newline_before_tool_call_preserved() {
-        // A single newline before a tool call should be preserved
-        reset_json_tool_state();
-        let input = "Before\n{\"tool\": \"shell\", \"args\": {}}\nAfter";
-        let result = filter_json_tool_calls(input);
-        assert_eq!(result, "Before\n\nAfter");
-    }
-
-    #[test]
-    fn test_tool_call_not_at_line_start_passes_through() {
-        // IMPORTANT: Tool calls that don't start at a line boundary should NOT be filtered.
-        // This is by design - the filter only suppresses tool calls that appear at the
-        // start of a line (after newline + optional whitespace).
-        //
-        // This test documents the behavior that caused the "auto-memory JSON leak" bug:
-        // When "Memory checkpoint: " was printed without a trailing newline, the LLM's
-        // response `{"tool": "remember", ...}` appeared on the same line and was not
-        // filtered. The fix was to ensure the prompt ends with a newline AND reset
-        // the filter state before streaming.
-        //
-        // See: send_auto_memory_reminder() in g3-core/src/lib.rs
-        reset_json_tool_state();
-        
-        // Tool call immediately after text on same line - should NOT be filtered
-        let input = "Memory checkpoint: {\"tool\": \"remember\", \"args\": {}}";
-        let result = filter_json_tool_calls(input);
-        assert_eq!(result, input, "Tool calls not at line start should pass through");
-    }
-
-    #[test]
-    fn test_tool_json_in_code_fence_passes_through() {
-        // JSON inside code fences should NOT be filtered, even if it looks like a tool call
-        reset_json_tool_state();
-        let input = "Before\n```json\n{\"tool\": \"shell\", \"args\": {}}\n```\nAfter";
-        let result = filter_json_tool_calls(input);
-        assert_eq!(result, input, "Tool JSON inside code fence should pass through");
-    }
-
-    #[test]
-    fn test_tool_json_in_plain_code_fence_passes_through() {
-        // JSON inside plain code fences (no language) should also pass through
-        reset_json_tool_state();
-        let input = "Before\n```\n{\"tool\": \"shell\", \"args\": {}}\n```\nAfter";
-        let result = filter_json_tool_calls(input);
-        assert_eq!(result, input, "Tool JSON inside plain code fence should pass through");
-    }
-
-    #[test]
-    fn test_indented_tool_json_passes_through() {
-        // Indented JSON should NOT be filtered (real tool calls are never indented)
-        reset_json_tool_state();
-        let input = "Before\n    {\"tool\": \"shell\", \"args\": {}}\nAfter";
-        let result = filter_json_tool_calls(input);
-        assert_eq!(result, input, "Indented tool JSON should pass through");
-    }
-
-    #[test]
-    fn test_tab_indented_tool_json_passes_through() {
-        // Tab-indented JSON should also pass through
-        reset_json_tool_state();
-        let input = "Before\n\t{\"tool\": \"shell\", \"args\": {}}\nAfter";
-        let result = filter_json_tool_calls(input);
-        assert_eq!(result, input, "Tab-indented tool JSON should pass through");
-    }
-}

crates/g3-cli/src/g3_status.rs

@@ -1,313 +0,0 @@
-//! Centralized formatting for g3 system status messages.
-//!
-//! Provides consistent "g3:" prefixed status messages with progress indicators
-//! and completion statuses. Use `progress()` + `done()`/`failed()` for two-step
-//! output, or `complete()` for one-shot messages.
-
-use crossterm::style::{Attribute, Color, ResetColor, SetAttribute, SetForegroundColor};
-use std::io::{self, Write};
-
-/// Status types for g3 system messages
-#[derive(Debug, Clone, PartialEq)]
-pub enum Status {
-    /// Success - bold green "[done]"
-    Done,
-    /// Failure - red "[failed]"
-    Failed,
-    /// Error with message - red "[error: <msg>]"
-    Error(String),
-    /// Custom status - plain "[<status>]"
-    Custom(String),
-    /// Resolved status - for thinning operations
-    Resolved,
-    /// Insufficient - for thinning operations
-    Insufficient,
-    /// No changes - for thinning operations that didn't modify anything
-    NoChanges,
-}
-
-impl Status {
-    pub fn parse(s: &str) -> Self {
-        match s {
-            "done" => Status::Done,
-            "failed" => Status::Failed,
-            "resolved" => Status::Resolved,
-            "insufficient" => Status::Insufficient,
-            s if s.starts_with("error:") => Status::Error(s[6..].trim().to_string()),
-            s if s.starts_with("error") => Status::Error(s[5..].trim().to_string()),
-            other => Status::Custom(other.to_string()),
-        }
-    }
-}
-
-/// Centralized g3 system status message formatting
-pub struct G3Status;
-
-impl G3Status {
-    /// Print "g3: <message> ..." (no newline). Complete with `done()` or `failed()`.
-    pub fn progress(message: &str) {
-        print!(
-            "{}{}g3:{}{} {} ...",
-            SetAttribute(Attribute::Bold),
-            SetForegroundColor(Color::Green),
-            ResetColor,
-            SetAttribute(Attribute::Reset),
-            message
-        );
-        let _ = io::stdout().flush();
-    }
-
-    /// Print "g3: <message> ..." with newline (standalone progress).
-    pub fn progress_ln(message: &str) {
-        println!(
-            "{}{}g3:{}{} {} ...",
-            SetAttribute(Attribute::Bold),
-            SetForegroundColor(Color::Green),
-            ResetColor,
-            SetAttribute(Attribute::Reset),
-            message
-        );
-    }
-
-    pub fn done() {
-        println!(
-            " {}{}[done]{}",
-            SetForegroundColor(Color::Green),
-            SetAttribute(Attribute::Bold),
-            ResetColor
-        );
-    }
-
-    pub fn failed() {
-        println!(
-            " {}[failed]{}",
-            SetForegroundColor(Color::Red),
-            ResetColor
-        );
-    }
-
-    pub fn error(msg: &str) {
-        println!(
-            " {}[error: {}]{}",
-            SetForegroundColor(Color::Red),
-            msg,
-            ResetColor
-        );
-    }
-
-    pub fn status(status: &Status) {
-        match status {
-            Status::Done => Self::done(),
-            Status::Failed => Self::failed(),
-            Status::Error(msg) => Self::error(msg),
-            Status::Resolved => {
-                println!(
-                    " {}{}[resolved]{}",
-                    SetForegroundColor(Color::Green),
-                    SetAttribute(Attribute::Bold),
-                    ResetColor
-                );
-            }
-            Status::Insufficient => {
-                println!(
-                    " {}[insufficient]{}",
-                    SetForegroundColor(Color::Yellow),
-                    ResetColor
-                );
-            }
-            Status::Custom(s) => {
-                println!(" [{}]", s);
-            }
-            Status::NoChanges => {
-                println!(
-                    " {}[no changes]{}",
-                    SetForegroundColor(Color::DarkGrey),
-                    ResetColor
-                );
-            }
-        }
-    }
-
-    /// Print "g3: <message> ... [status]" (one-shot).
-    pub fn complete(message: &str, status: Status) {
-        Self::progress(message);
-        Self::status(&status);
-    }
-
-    #[allow(dead_code)]
-    pub fn info(message: &str) {
-        println!(
-            "{}... {}{}",
-            SetForegroundColor(Color::DarkGrey),
-            message,
-            ResetColor
-        );
-    }
-
-    /// Format a status for inline use (returns formatted string).
-    pub fn format_status(status: &Status) -> String {
-        match status {
-            Status::Done => format!(
-                "{}{}[done]{}",
-                SetForegroundColor(Color::Green),
-                SetAttribute(Attribute::Bold),
-                ResetColor
-            ),
-            Status::Failed => format!(
-                "{}[failed]{}",
-                SetForegroundColor(Color::Red),
-                ResetColor
-            ),
-            Status::Error(msg) => format!(
-                "{}{}{}",
-                SetForegroundColor(Color::Red),
-                if msg.is_empty() {
-                    "[error]".to_string()
-                } else {
-                    format!("[error: {}]", msg)
-                },
-                ResetColor
-            ),
-            Status::Resolved => format!(
-                "{}{}[resolved]{}",
-                SetForegroundColor(Color::Green),
-                SetAttribute(Attribute::Bold),
-                ResetColor
-            ),
-            Status::Insufficient => format!(
-                "{}[insufficient]{}",
-                SetForegroundColor(Color::Yellow),
-                ResetColor
-            ),
-            Status::Custom(s) => format!("[{}]", s),
-            Status::NoChanges => format!(
-                "{}[no changes]{}",
-                SetForegroundColor(Color::DarkGrey),
-                ResetColor
-            ),
-        }
-    }
-
-    pub fn format_prefix() -> String {
-        format!(
-            "{}{}g3:{}{}",
-            SetAttribute(Attribute::Bold),
-            SetForegroundColor(Color::Green),
-            ResetColor,
-            SetAttribute(Attribute::Reset),
-        )
-    }
-
-    /// Print "... resuming <session_id> [status]" with cyan session ID.
-    pub fn resuming(session_id: &str, status: Status) {
-        let status_str = Self::format_status(&status);
-        println!(
-            "... resuming {}{}{} {}",
-            SetForegroundColor(Color::Cyan),
-            session_id,
-            ResetColor,
-            status_str
-        );
-    }
-
-    pub fn resuming_summary(session_id: &str) {
-        let status_str = Self::format_status(&Status::Done);
-        println!(
-            "... resuming {}{}{} (summary) {}",
-            SetForegroundColor(Color::Cyan),
-            session_id,
-            ResetColor,
-            status_str
-        );
-    }
-
-    /// Print thinning result: "g3: thinning context ... 70% -> 40% ... [done]"
-    pub fn thin_result(result: &g3_core::ThinResult) {
-        use g3_core::ThinScope;
-        
-        let scope_desc = match result.scope {
-            ThinScope::FirstThird => "thinning context",
-            ThinScope::All => "thinning context (full)",
-        };
-        
-        if result.had_changes {
-            // Format: "g3: thinning context ... 70% -> 40% ... [done]"
-            print!(
-                "{} {} ... {}% -> {}% ...",
-                Self::format_prefix(),
-                scope_desc,
-                result.before_percentage,
-                result.after_percentage
-            );
-            Self::done();
-        } else {
-            // Format: "g3: thinning context ... 70% ... [no changes]"
-            Self::complete(&format!("{} ... {}%", scope_desc, result.before_percentage), Status::NoChanges);
-        }
-    }
-
-    /// Print "g3: <message> <path> [status]" with cyan path.
-    pub fn complete_with_path(message: &str, path: &str, status: Status) {
-        print!(
-            "{} {} {}{}{}",
-            Self::format_prefix(),
-            message,
-            SetForegroundColor(Color::Cyan),
-            path,
-            ResetColor
-        );
-        Self::status(&status);
-    }
-
-    /// Print project loading status: "g3: loading <project-name> .. ✓ file1  ✓ file2 .. [done]"
-    ///
-    /// Used by the /project command to show what project files were loaded.
-    pub fn loading_project(project_name: &str, loaded_files_status: &str) {
-        print!(
-            "{} loading {}{}{} .. {} ..",
-            Self::format_prefix(),
-            SetForegroundColor(Color::Cyan),
-            project_name,
-            ResetColor,
-            loaded_files_status
-        );
-        Self::done();
-    }
-
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_status_from_str() {
-        assert_eq!(Status::parse("done"), Status::Done);
-        assert_eq!(Status::parse("failed"), Status::Failed);
-        assert_eq!(Status::parse("resolved"), Status::Resolved);
-        assert_eq!(Status::parse("insufficient"), Status::Insufficient);
-        assert_eq!(Status::parse("error: timeout"), Status::Error("timeout".to_string()));
-        assert_eq!(Status::parse("error timeout"), Status::Error("timeout".to_string()));
-        assert_eq!(Status::parse("custom"), Status::Custom("custom".to_string()));
-    }
-
-    #[test]
-    fn test_format_status_contains_ansi() {
-        let done = G3Status::format_status(&Status::Done);
-        assert!(done.contains("[done]"));
-        assert!(done.contains("\x1b")); // Contains ANSI escape
-
-        let failed = G3Status::format_status(&Status::Failed);
-        assert!(failed.contains("[failed]"));
-
-        let error = G3Status::format_status(&Status::Error("test".to_string()));
-        assert!(error.contains("[error: test]"));
-    }
-
-    #[test]
-    fn test_format_prefix() {
-        let prefix = G3Status::format_prefix();
-        assert!(prefix.contains("g3:"));
-        assert!(prefix.contains("\x1b")); // Contains ANSI escape
-    }
-}

crates/g3-cli/src/input_formatter.rs

@@ -1,315 +0,0 @@
-//! Input formatting for interactive mode.
-//!
-//! Applies visual highlighting to user input:
-//! - ALL CAPS words (2+ chars) → bold green
-//! - Quoted text ("..." or '...') → cyan
-//! - Standard markdown (bold, italic, code) via termimad
-
-use crossterm::terminal;
-use regex::Regex;
-use std::io::Write;
-use std::io::IsTerminal;
-use once_cell::sync::Lazy;
-use termimad::MadSkin;
-
-use crate::streaming_markdown::StreamingMarkdownFormatter;
-
-// Compiled regexes for preprocessing (compiled once, reused)
-static CAPS_RE: Lazy<Regex> = Lazy::new(|| {
-    // ALL CAPS words: 2+ uppercase letters, may include numbers, word boundaries
-    Regex::new(r"\b([A-Z][A-Z0-9]{1,}[A-Z0-9]*)\b").unwrap()
-});
-static DOUBLE_QUOTE_RE: Lazy<Regex> = Lazy::new(|| {
-    // Double-quoted text: quote must be preceded by whitespace/punctuation or start of string,
-    // and followed by whitespace/punctuation or end of string
-    Regex::new(r#"(?:^|[\s(\[{])"([^"]+)"(?:$|[\s.,;:!?)\]}])"#).unwrap()
-});
-static SINGLE_QUOTE_RE: Lazy<Regex> = Lazy::new(|| {
-    // Single-quoted text: quote must be preceded by whitespace/punctuation or start of string,
-    // and followed by whitespace/punctuation or end of string (avoids contractions like "it's")
-    Regex::new(r#"(?:^|[\s(\[{])'([^']+)'(?:$|[\s.,;:!?)\]}])"#).unwrap()
-});
-
-/// Pre-process input to add markdown markers before formatting.
-/// ALL CAPS → **bold**, quoted text → special markers for cyan.
-pub fn preprocess_input(input: &str) -> String {
-    let mut result = input.to_string();
-    
-    // ALL CAPS → **bold**
-    result = CAPS_RE.replace_all(&result, "**$1**").to_string();
-    
-    // Quoted text → markers (processed after markdown to apply cyan)
-    result = DOUBLE_QUOTE_RE.replace_all(&result, "\x00qdbl\x00$1\x00qend\x00").to_string();
-    result = SINGLE_QUOTE_RE.replace_all(&result, "\x00qsgl\x00$1\x00qend\x00").to_string();
-    
-    result
-}
-
-// Regexes for post-processing quote markers into ANSI cyan
-static CYAN_DOUBLE_RE: Lazy<Regex> = Lazy::new(|| {
-    Regex::new(r#"(\x1b\[36m")([^\x1b]*)\x1b\[0m"#).unwrap()
-});
-static CYAN_SINGLE_RE: Lazy<Regex> = Lazy::new(|| {
-    Regex::new(r"(\x1b\[36m')([^\x1b]*)\x1b\[0m").unwrap()
-});
-
-/// Apply cyan highlighting to quoted text markers (runs after markdown formatting).
-fn apply_quote_highlighting(text: &str) -> String {
-    let mut result = text.to_string();
-    
-    // \x1b[36m = cyan, \x1b[0m = reset
-    result = result.replace("\x00qdbl\x00", "\x1b[36m\"");
-    result = result.replace("\x00qsgl\x00", "\x1b[36m'");
-    result = result.replace("\x00qend\x00", "\x1b[0m");
-    
-    // Insert closing quotes before reset code
-    result = CYAN_DOUBLE_RE.replace_all(&result, |caps: &regex::Captures| {
-        format!("{}{}\"\x1b[0m", &caps[1], &caps[2])
-    }).to_string();
-    result = CYAN_SINGLE_RE.replace_all(&result, |caps: &regex::Captures| {
-        format!("{}{}'\x1b[0m", &caps[1], &caps[2])
-    }).to_string();
-    
-    result
-}
-
-/// Format user input with markdown and special highlighting (ALL CAPS, quotes).
-pub fn format_input(input: &str) -> String {
-    let preprocessed = preprocess_input(input);
-    
-    let skin = MadSkin::default();
-    let mut formatter = StreamingMarkdownFormatter::new(skin);
-    let formatted = formatter.process(&preprocessed);
-    let formatted = formatted + &formatter.finish();
-    
-    apply_quote_highlighting(&formatted)
-}
-
-/// Calculate the number of visual lines that text occupies in a terminal.
-/// Accounts for line wrapping and the cursor position after typing.
-/// For multi-line input (with embedded newlines), calculates lines for each segment.
-pub fn calculate_visual_lines(text: &str, term_width: usize) -> usize {
-    if term_width == 0 {
-        return 1;
-    }
-    
-    // Split by newlines and calculate visual lines for each segment
-    let mut visual_lines = 0;
-    for (i, line) in text.split('\n').enumerate() {
-        let line_len = if i == 0 { line.len() } else { line.len() };
-        visual_lines += line_len.div_ceil(term_width).max(1);
-    }
-    visual_lines = visual_lines.max(1);
-    
-    let text_len = text.len();
-    // When text exactly fills the terminal width (or a multiple), the cursor
-    // wraps to the next line, so we need to clear one additional line
-    if text_len > 0 && text_len % term_width == 0 {
-        visual_lines += 1;
-    }
-    visual_lines
-}
-
-/// Reprint user input in place with formatting (TTY only).
-/// Moves cursor up to overwrite original input, then prints formatted version.
-pub fn reprint_formatted_input(input: &str, prompt: &str) {
-    if !std::io::stdout().is_terminal() {
-        return;
-    }
-
-    let formatted = format_input(input);
-
-    // Calculate visual lines (prompt + input may wrap across terminal rows)
-    let term_width = terminal::size().map(|(w, _)| w as usize).unwrap_or(80);
-    let full_input = format!("{}{}", prompt, input);
-    let visual_lines = calculate_visual_lines(&full_input, term_width);
-
-    // Move up and clear each line
-    for _ in 0..visual_lines {
-        print!("\x1b[1A\x1b[2K");
-    }
-
-    // Dim prompt + formatted input
-    println!("\x1b[2m{}\x1b[0m{}", prompt, formatted);
-    let _ = std::io::stdout().flush();
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    
-    #[test]
-    fn test_preprocess_all_caps() {
-        let input = "please FIX the BUG in this CODE";
-        let result = preprocess_input(input);
-        assert!(result.contains("**FIX**"));
-        assert!(result.contains("**BUG**"));
-        assert!(result.contains("**CODE**"));
-        // "please", "the", "in", "this" should not be wrapped
-        assert!(!result.contains("**please**"));
-    }
-    
-    #[test]
-    fn test_preprocess_single_caps_not_matched() {
-        // Single letter caps should not be matched
-        let input = "I am A person";
-        let result = preprocess_input(input);
-        // "I" and "A" are single letters, should not be wrapped
-        assert!(!result.contains("**I**"));
-        assert!(!result.contains("**A**"));
-    }
-    
-    #[test]
-    fn test_preprocess_double_quotes() {
-        let input = r#"say "hello world" please"#;
-        let result = preprocess_input(input);
-        assert!(result.contains("\x00qdbl\x00hello world\x00qend\x00"));
-    }
-    
-    #[test]
-    fn test_preprocess_single_quotes() {
-        let input = "use the 'special' method";
-        let result = preprocess_input(input);
-        assert!(result.contains("\x00qsgl\x00special\x00qend\x00"));
-    }
-    
-    #[test]
-    fn test_preprocess_mixed() {
-        let input = r#"FIX the "critical" BUG"#;
-        let result = preprocess_input(input);
-        assert!(result.contains("**FIX**"));
-        assert!(result.contains("**BUG**"));
-        assert!(result.contains("\x00qdbl\x00critical\x00qend\x00"));
-    }
-    
-    #[test]
-    fn test_apply_quote_highlighting() {
-        let input = "\x00qdbl\x00hello\x00qend\x00";
-        let result = apply_quote_highlighting(input);
-        assert!(result.contains("\x1b[36m"));
-        assert!(result.contains("\x1b[0m"));
-    }
-    
-    #[test]
-    fn test_format_input_caps_become_bold() {
-        let input = "FIX this";
-        let result = format_input(input);
-        // Should contain bold ANSI code (\x1b[1;32m for bold green)
-        assert!(result.contains("\x1b[1;32m") || result.contains("FIX"));
-    }
-    
-    #[test]
-    fn test_format_input_quotes_become_cyan() {
-        let input = r#"say "hello""#;
-        let result = format_input(input);
-        // Should contain cyan ANSI code
-        assert!(result.contains("\x1b[36m"));
-    }
-    
-    #[test]
-    fn test_caps_with_numbers() {
-        let input = "check HTTP2 and TLS13";
-        let result = preprocess_input(input);
-        assert!(result.contains("**HTTP2**"));
-        assert!(result.contains("**TLS13**"));
-    }
-    
-    #[test]
-    fn test_two_letter_caps() {
-        let input = "use IO and DB";
-        let result = preprocess_input(input);
-        assert!(result.contains("**IO**"));
-        assert!(result.contains("**DB**"));
-    }
-    
-    // Tests for apostrophe/contraction handling (I1 bug fix)
-    
-    #[test]
-    fn test_contraction_not_highlighted() {
-        // Contractions should NOT be treated as quoted text
-        let input = "it's fine";
-        let result = preprocess_input(input);
-        // Should not contain quote markers
-        assert!(!result.contains("\x00qsgl\x00"));
-        assert!(!result.contains("\x00qend\x00"));
-        assert_eq!(result, "it's fine");
-    }
-    
-    #[test]
-    fn test_multiple_contractions_not_highlighted() {
-        let input = "don't won't can't shouldn't";
-        let result = preprocess_input(input);
-        assert!(!result.contains("\x00qsgl\x00"));
-        assert_eq!(result, input);
-    }
-    
-    #[test]
-    fn test_contraction_with_quoted_text() {
-        // Mixed: contraction + actual quoted text
-        // Only 'test' should be highlighted, not the apostrophe in "it's"
-        let input = "it's a 'test' case";
-        let result = preprocess_input(input);
-        assert!(result.contains("\x00qsgl\x00test\x00qend\x00"));
-        // The "it's" should remain unchanged
-        assert!(result.contains("it's"));
-    }
-    
-    #[test]
-    fn test_quoted_at_start_of_string() {
-        let input = "'hello' world";
-        let result = preprocess_input(input);
-        assert!(result.contains("\x00qsgl\x00hello\x00qend\x00"));
-    }
-    
-    #[test]
-    fn test_quoted_at_end_of_string() {
-        let input = "say 'goodbye'";
-        let result = preprocess_input(input);
-        assert!(result.contains("\x00qsgl\x00goodbye\x00qend\x00"));
-    }
-    
-    // Tests for visual line calculation (I2 bug fix)
-    
-    #[test]
-    fn test_visual_lines_shorter_than_width() {
-        // 50 chars on 80-char terminal = 1 line
-        let text = "a".repeat(50);
-        assert_eq!(calculate_visual_lines(&text, 80), 1);
-    }
-    
-    #[test]
-    fn test_visual_lines_longer_than_width() {
-        // 100 chars on 80-char terminal = 2 lines (wraps once)
-        let text = "a".repeat(100);
-        assert_eq!(calculate_visual_lines(&text, 80), 2);
-        // 170 chars on 80-char terminal = 3 lines
-        let text = "a".repeat(170);
-        assert_eq!(calculate_visual_lines(&text, 80), 3);
-    }
-    
-    #[test]
-    fn test_visual_lines_exactly_equals_width() {
-        // 80 chars on 80-char terminal = 2 lines (cursor wraps to next line)
-        let text = "a".repeat(80);
-        assert_eq!(calculate_visual_lines(&text, 80), 2);
-        // 160 chars on 80-char terminal = 3 lines (fills 2 lines exactly, cursor on 3rd)
-        let text = "a".repeat(160);
-        assert_eq!(calculate_visual_lines(&text, 80), 3);
-    }
-    
-    #[test]
-    fn test_visual_lines_empty_input() {
-        // Empty input should still be 1 line (the prompt line)
-        assert_eq!(calculate_visual_lines("", 80), 1);
-    }
-
-    #[test]
-    fn test_visual_lines_multiline_input() {
-        // Multi-line input with embedded newlines
-        assert_eq!(calculate_visual_lines("line1\nline2", 80), 2);
-        assert_eq!(calculate_visual_lines("line1\nline2\nline3", 80), 3);
-        // First line wraps, second doesn't
-        let text = format!("{}\nshort", "a".repeat(100));
-        assert_eq!(calculate_visual_lines(&text, 80), 3); // 100 chars = 2 lines, + 1 for "short"
-    }
-}

crates/g3-cli/src/interactive.rs

@@ -1,521 +0,0 @@
-//! Interactive mode for G3 CLI.
-
-use anyhow::Result;
-use crossterm::style::{Color, ResetColor, SetForegroundColor};
-use rustyline::error::ReadlineError;
-use rustyline::{Cmd, Config, Editor, EventHandler, KeyCode, KeyEvent, Modifiers};
-use crate::completion::G3Helper;
-use std::path::Path;
-use tracing::{debug, error};
-
-use g3_core::ui_writer::UiWriter;
-use g3_core::Agent;
-
-use crate::commands::{handle_command, CommandResult};
-use crate::display::{LoadedContent, print_loaded_status, print_workspace_path};
-use crate::g3_status::G3Status;
-use crate::project::Project;
-use crate::simple_output::SimpleOutput;
-use crate::input_formatter::reprint_formatted_input;
-use crate::template::process_template;
-use crate::task_execution::execute_task_with_retry;
-use crate::utils::display_context_progress;
-
-/// Plan mode prompt string.
-const PLAN_MODE_PROMPT: &str = " [plan mode] >> ";
-
-/// Build the interactive prompt string.
-///
-/// Format:
-/// - Multiline mode: `"... > "`
-/// - Plan mode: `" >> "`
-/// - No project: `"agent_name> "` (defaults to "g3")
-/// - With project: `"agent_name | project_name> "`
-pub fn build_prompt(in_multiline: bool, in_plan_mode: bool, agent_name: Option<&str>, active_project: &Option<Project>) -> String {
-    if in_multiline {
-        "... > ".to_string()
-    } else if in_plan_mode {
-        PLAN_MODE_PROMPT.to_string()
-    } else {
-        let base_name = agent_name.unwrap_or("g3");
-        if let Some(project) = active_project {
-            let project_name = project.path
-                .file_name()
-                .and_then(|n| n.to_str())
-                .unwrap_or("project");
-            format!("{} | {}> ", base_name, project_name)
-        } else {
-            format!("{}> ", base_name)
-        }
-    }
-}
-
-/// Prepare user input for plan mode, prepending "Create a plan: " if this is the first message.
-/// Returns the (possibly modified) input and whether the flag should be reset.
-pub fn prepare_plan_mode_input(input: &str, is_first_plan_message: bool, in_plan_mode: bool) -> (String, bool) {
-    if in_plan_mode && is_first_plan_message {
-        // Prepend "Create a plan: " and signal to reset the flag
-        (format!("Create a plan: {}", input), true)
-    } else {
-        // No modification needed
-        (input.to_string(), false)
-    }
-}
-
-/// Execute user input with template processing and auto-memory reminder.
-///
-/// This is the common path for both single-line and multiline input.
-async fn execute_user_input<W: UiWriter>(
-    agent: &mut Agent<W>,
-    input: &str,
-    show_prompt: bool,
-    show_code: bool,
-    output: &SimpleOutput,
-    skip_auto_memory: bool,
-) {
-    let processed_input = process_template(input);
-    execute_task_with_retry(agent, &processed_input, show_prompt, show_code, output).await;
-
-    // Send auto-memory reminder if enabled and tools were called
-    if !skip_auto_memory {
-        if let Err(e) = agent.send_auto_memory_reminder().await {
-            debug!("Auto-memory reminder failed: {}", e);
-        }
-    }
-}
-
-/// Check if plan is terminal and exit plan mode if so.
-///
-/// Returns true if plan mode was exited (plan is complete or all blocked).
-fn check_and_exit_plan_mode_if_terminal<W: UiWriter>(
-    agent: &mut Agent<W>,
-    in_plan_mode: &mut bool,
-    output: &SimpleOutput,
-) -> bool {
-    if *in_plan_mode && agent.is_plan_terminal() {
-        output.print("\n📋 Plan complete - exiting plan mode");
-        *in_plan_mode = false;
-        agent.set_plan_mode(false, None);
-        return true;
-    }
-    false
-}
-
-/// Run interactive mode with console output.
-/// If `agent_name` is Some, we're in agent+chat mode: skip session resume/verbose welcome,
-/// and use the agent name as the prompt (e.g., "butler>").
-/// If `initial_project` is Some, the project is pre-loaded (from --project flag).
-pub async fn run_interactive<W: UiWriter>(
-    mut agent: Agent<W>,
-    show_prompt: bool,
-    show_code: bool,
-    combined_content: Option<String>,
-    workspace_path: &Path,
-    agent_name: Option<&str>,
-    initial_project: Option<Project>,
-) -> Result<()> {
-    let output = SimpleOutput::new();
-    let from_agent_mode = agent_name.is_some();
-
-    // Skip verbose welcome when coming from agent mode (it already printed context info)
-    if !from_agent_mode {
-        match agent.get_provider_info() {
-            Ok((provider, model)) => {
-                print!(
-                    "🔧 {}{}{} | {}{}{}\n",
-                    SetForegroundColor(Color::Cyan),
-                    provider,
-                    ResetColor,
-                    SetForegroundColor(Color::Yellow),
-                    model,
-                    ResetColor
-                );
-            }
-            Err(e) => {
-                error!("Failed to get provider info: {}", e);
-            }
-        }
-
-           // Display message if AGENTS.md or README was loaded
-        if let Some(ref content) = combined_content {
-            let loaded = LoadedContent::from_combined_content(content);
-
-            print_loaded_status(&loaded);
-        }
-
-        // Display workspace path
-        print_workspace_path(workspace_path);
-        
-        // Print welcome message right before the prompt
-        output.print("");
-        output.print("g3 programming agent");
-        output.print("   what shall we build today?");
-    }
-    
-    // Track plan mode state (start in plan mode for non-agent mode)
-    let mut in_plan_mode = !from_agent_mode;
-    
-    // Track if this is the first message in plan mode (to prepend "Create a plan: ")
-    let mut is_first_plan_message = in_plan_mode;
-    
-    // Sync agent's plan mode state with CLI state
-    agent.set_plan_mode(in_plan_mode, Some(workspace_path.to_str().unwrap_or(".")));
-
-    // Initialize rustyline editor with history
-    let config = Config::builder()
-        .completion_type(rustyline::CompletionType::List)
-        .build();
-    let mut rl = Editor::with_config(config)?;
-    rl.set_helper(Some(G3Helper::new()));
-
-    // Bind Alt+Enter to insert a newline (for multi-line input)
-    // Note: Shift+Enter is not distinguishable in standard terminals
-    rl.bind_sequence(KeyEvent(KeyCode::Enter, Modifiers::ALT), EventHandler::Simple(Cmd::Newline));
-
-    // Try to load history from a file in the user's home directory
-    let history_file = dirs::home_dir().map(|mut path| {
-        path.push(".g3_history");
-        path
-    });
-
-    if let Some(ref history_path) = history_file {
-        let _ = rl.load_history(history_path);
-    }
-
-    // Track multiline input
-    let mut multiline_buffer = String::new();
-    let mut in_multiline = false;
-
-    // Track active project (may be pre-loaded from --project flag)
-    let mut active_project: Option<Project> = initial_project;
-
-    // If we have an initial project, display its status
-    if let Some(ref project) = active_project {
-        let project_name = project.path
-            .file_name()
-            .and_then(|n| n.to_str())
-            .unwrap_or("project");
-        G3Status::loading_project(project_name, &project.format_loaded_status());
-        
-        // Print newline after the loading message (G3Status::loading_project doesn't add one)
-        use std::io::Write;
-        println!();
-        std::io::stdout().flush().ok();
-    }
-
-    loop {
-        // Display context window progress bar before each prompt
-        display_context_progress(&agent, &output);
-
-        // Build prompt
-        let prompt = build_prompt(in_multiline, in_plan_mode, agent_name, &active_project);
-
-        let readline = rl.readline(&prompt);
-        match readline {
-            Ok(line) => {
-                let trimmed = line.trim_end();
-
-                // Check if line ends with backslash for continuation
-                if let Some(without_backslash) = trimmed.strip_suffix('\\') {
-                    // Remove the backslash and add to buffer
-                    multiline_buffer.push_str(without_backslash);
-                    multiline_buffer.push('\n');
-                    in_multiline = true;
-                    continue;
-                }
-
-                // If we're in multiline mode and no backslash, this is the final line
-                if in_multiline {
-                    multiline_buffer.push_str(&line);
-                    in_multiline = false;
-                    // Process the complete multiline input
-                    let input = multiline_buffer.trim().to_string();
-                    multiline_buffer.clear();
-
-                    if input.is_empty() {
-                        continue;
-                    }
-
-                    // Add complete multiline to history
-                    rl.add_history_entry(&input)?;
-
-                    if input == "exit" || input == "quit" {
-                        break;
-                    }
-
-                    // Reprint input with formatting
-                    reprint_formatted_input(&input, &prompt);
-
-                    // Prepend "Create a plan: " for first message in plan mode
-                    let (final_input, should_reset) = prepare_plan_mode_input(&input, is_first_plan_message, in_plan_mode);
-                    if should_reset {
-                        is_first_plan_message = false;
-                    }
-                    execute_user_input(
-                        &mut agent, &final_input, show_prompt, show_code, &output, from_agent_mode
-                    ).await;
-
-                    // Check if plan completed and exit plan mode if so
-                    check_and_exit_plan_mode_if_terminal(&mut agent, &mut in_plan_mode, &output);
-                } else {
-                    // Single line input
-                    let input = line.trim().to_string();
-
-                    if input.is_empty() {
-                        continue;
-                    }
-
-                    if input == "exit" || input == "quit" {
-                        break;
-                    }
-
-                    // Add to history
-                    rl.add_history_entry(&input)?;
-
-                    // Check for control commands
-                    if input.starts_with('/') {
-                        let result = handle_command(&input, &mut agent, workspace_path, &output, &mut active_project, &mut rl, show_prompt, show_code).await?;
-                        
-                        match result {
-                            CommandResult::Handled => {
-                                continue;
-                            }
-                            CommandResult::EnterPlanMode => {
-                                in_plan_mode = true;
-                                agent.set_plan_mode(true, Some(workspace_path.to_str().unwrap_or(".")));
-                                is_first_plan_message = true;
-                                continue;
-                            }
-                        }
-                    }
-
-                    // Reprint input with formatting
-                    reprint_formatted_input(&input, &prompt);
-
-                    // Prepend "Create a plan: " for first message in plan mode
-                    let (final_input, should_reset) = prepare_plan_mode_input(&input, is_first_plan_message, in_plan_mode);
-                    if should_reset {
-                        is_first_plan_message = false;
-                    }
-                    execute_user_input(
-                        &mut agent, &final_input, show_prompt, show_code, &output, from_agent_mode
-                    ).await;
-
-                    // Check if plan completed and exit plan mode if so
-                    check_and_exit_plan_mode_if_terminal(&mut agent, &mut in_plan_mode, &output);
-                }
-            }
-            Err(ReadlineError::Interrupted) => {
-                // Ctrl-C pressed
-                if in_multiline {
-                    // Cancel multiline input
-                    output.print("Multi-line input cancelled");
-                    multiline_buffer.clear();
-                    in_multiline = false;
-                } else {
-                    output.print("CTRL-C");
-                }
-                continue;
-            }
-            Err(ReadlineError::Eof) => {
-                // CTRL-D: if in plan mode, exit plan mode first; otherwise exit g3
-                if in_plan_mode {
-                    output.print("CTRL-D (exiting plan mode)");
-                    in_plan_mode = false;
-                    agent.set_plan_mode(false, None);
-                    // Continue the loop with normal prompt
-                    continue;
-                } else {
-                    output.print("CTRL-D");
-                    break;
-                }
-            }
-            Err(err) => {
-                error!("Error: {:?}", err);
-                break;
-            }
-        }
-    }
-
-    // Save history before exiting
-    if let Some(ref history_path) = history_file {
-        let _ = rl.save_history(history_path);
-    }
-
-    // Save session continuation for resume capability
-    agent.save_session_continuation(None);
-
-    // Send auto-memory reminder once on exit when in agent+chat mode
-    // (Per-turn reminders were skipped to avoid being too onerous)
-    if from_agent_mode {
-        if let Err(e) = agent.send_auto_memory_reminder().await {
-            debug!("Auto-memory reminder on exit failed: {}", e);
-        }
-    }
-
-    output.print("👋 Goodbye!");
-    Ok(())
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use std::path::PathBuf;
-
-    fn create_test_project(name: &str) -> Project {
-        Project {
-            path: PathBuf::from(format!("/test/projects/{}", name)),
-            content: "test content".to_string(),
-            loaded_files: vec!["brief.md".to_string()],
-        }
-    }
-
-    #[test]
-    fn test_build_prompt_default() {
-        let prompt = build_prompt(false, false, None, &None);
-        assert_eq!(prompt, "g3> ");
-    }
-
-    #[test]
-    fn test_build_prompt_with_agent_name() {
-        let prompt = build_prompt(false, false, Some("butler"), &None);
-        assert_eq!(prompt, "butler> ");
-    }
-
-    #[test]
-    fn test_build_prompt_multiline() {
-        let prompt = build_prompt(true, false, None, &None);
-        assert_eq!(prompt, "... > ");
-
-        // Multiline takes precedence over agent name
-        let prompt = build_prompt(true, false, Some("butler"), &None);
-        assert_eq!(prompt, "... > ");
-
-        // Multiline takes precedence over project
-        let project = Some(create_test_project("myapp"));
-        let prompt = build_prompt(true, false, None, &project);
-        assert_eq!(prompt, "... > ");
-        
-        // Multiline takes precedence over plan mode
-        let prompt = build_prompt(true, true, None, &None);
-        assert_eq!(prompt, "... > ");
-    }
-
-    #[test]
-    fn test_build_prompt_plan_mode() {
-        let prompt = build_prompt(false, true, None, &None);
-        assert_eq!(prompt, " [plan mode] >> ");
-        
-        // Plan mode takes precedence over agent name
-        let prompt = build_prompt(false, true, Some("butler"), &None);
-        assert_eq!(prompt, " [plan mode] >> ");
-        
-        // Plan mode takes precedence over project
-        let project = Some(create_test_project("myapp"));
-        let prompt = build_prompt(false, true, None, &project);
-        assert_eq!(prompt, " [plan mode] >> ");
-    }
-
-    #[test]
-    fn test_build_prompt_with_project() {
-        let project = Some(create_test_project("myapp"));
-        let prompt = build_prompt(false, false, None, &project);
-        assert!(prompt.contains("g3"));
-        assert!(prompt.contains("myapp"));
-        assert!(prompt.contains("|"));
-    }
-
-    #[test]
-    fn test_build_prompt_with_agent_and_project() {
-        let project = Some(create_test_project("myapp"));
-        let prompt = build_prompt(false, false, Some("carmack"), &project);
-        assert!(prompt.contains("carmack"));
-        assert!(prompt.contains("myapp"));
-        assert!(prompt.contains("|"));
-    }
-
-    #[test]
-    fn test_build_prompt_unproject_resets() {
-        // Simulate /project loading
-        let project = Some(create_test_project("myapp"));
-        let prompt_with_project = build_prompt(false, false, None, &project);
-        assert!(prompt_with_project.contains("myapp"));
-
-        // Simulate /unproject (sets active_project to None)
-        let prompt_after_unproject = build_prompt(false, false, None, &None);
-        assert_eq!(prompt_after_unproject, "g3> ");
-        assert!(!prompt_after_unproject.contains("myapp"));
-    }
-
-    #[test]
-    fn test_build_prompt_project_name_from_path() {
-        let project = Some(Project {
-            path: PathBuf::from("/Users/dev/projects/awesome-app"),
-            content: "test".to_string(),
-            loaded_files: vec![],
-        });
-        let prompt = build_prompt(false, false, None, &project);
-        assert!(prompt.contains("awesome-app"));
-    }
-
-    // Tests for prepare_plan_mode_input
-
-    #[test]
-    fn test_prepare_plan_mode_input_happy_path_first_message() {
-        // Happy path: First message in plan mode gets "Create a plan: " prefix
-        let (result, should_reset) = prepare_plan_mode_input("fix the bug", true, true);
-        assert_eq!(result, "Create a plan: fix the bug");
-        assert!(should_reset);
-    }
-
-    #[test]
-    fn test_prepare_plan_mode_input_negative_second_message() {
-        // Negative: Second message (is_first_plan_message = false) should NOT get prefix
-        let (result, should_reset) = prepare_plan_mode_input("fix the bug", false, true);
-        assert_eq!(result, "fix the bug");
-        assert!(!should_reset);
-    }
-
-    #[test]
-    fn test_prepare_plan_mode_input_negative_not_in_plan_mode() {
-        // Negative: Not in plan mode should NOT get prefix even if is_first_plan_message is true
-        let (result, should_reset) = prepare_plan_mode_input("fix the bug", true, false);
-        assert_eq!(result, "fix the bug");
-        assert!(!should_reset);
-    }
-
-    #[test]
-    fn test_prepare_plan_mode_input_negative_neither_condition() {
-        // Negative: Neither in plan mode nor first message
-        let (result, should_reset) = prepare_plan_mode_input("fix the bug", false, false);
-        assert_eq!(result, "fix the bug");
-        assert!(!should_reset);
-    }
-
-    #[test]
-    fn test_prepare_plan_mode_input_boundary_empty_input() {
-        // Boundary: Empty input would get prefix, but in practice empty input
-        // is filtered out by the caller before reaching this function.
-        // This test documents the function's behavior in isolation.
-        let (result, should_reset) = prepare_plan_mode_input("", true, true);
-        assert_eq!(result, "Create a plan: ");
-        assert!(should_reset);
-    }
-
-    #[test]
-    fn test_prepare_plan_mode_input_boundary_whitespace_input() {
-        // Boundary: Whitespace-only input gets prefix preserved
-        let (result, should_reset) = prepare_plan_mode_input("   ", true, true);
-        assert_eq!(result, "Create a plan:    ");
-        assert!(should_reset);
-    }
-
-    #[test]
-    fn test_prepare_plan_mode_input_boundary_multiline_input() {
-        // Boundary: Multiline input gets prefix on first line only
-        let (result, should_reset) = prepare_plan_mode_input("line1\nline2\nline3", true, true);
-        assert_eq!(result, "Create a plan: line1\nline2\nline3");
-        assert!(should_reset);
-    }
-}
-

crates/g3-cli/src/language_prompts.rs

@@ -1,260 +0,0 @@
-//! Language-specific prompt injection.
-//!
-//! Detects programming languages in the workspace and injects relevant
-//! toolchain guidance into the system prompt.
-//!
-//! Language prompts are embedded at compile time from `prompts/langs/*.md`.
-
-use std::path::Path;
-
-/// Embedded language prompts, keyed by language name.
-/// The key should match common file extensions or language identifiers.
-static LANGUAGE_PROMPTS: &[(&str, &[&str], &str)] = &[
-    // (language_name, file_extensions, prompt_content)
-    (
-        "rust",
-        &[".rs"],
-        "",  // No base Rust prompt; agent-specific prompts handle this
-    ),
-    (
-        "racket",
-        &[".rkt", ".rktl", ".rktd", ".scrbl"],
-        include_str!("../../../prompts/langs/racket.md"),
-    ),
-];
-
-/// Embedded agent-specific language prompts.
-/// Format: (agent_name, language_name, prompt_content)
-static AGENT_LANGUAGE_PROMPTS: &[(&str, &str, &str)] = &[
-    // (agent_name, language_name, prompt_content)
-    ("carmack", "racket", include_str!("../../../prompts/langs/carmack.racket.md")),
-    ("carmack", "rust", include_str!("../../../prompts/langs/carmack.rust.md")),
-];
-
-/// Detect languages present in the workspace by scanning for file extensions.
-/// Returns a list of detected language names.
-pub fn detect_languages(workspace_dir: &Path) -> Vec<&'static str> {
-    let mut detected = Vec::new();
-
-    for (lang_name, extensions, _) in LANGUAGE_PROMPTS {
-        if has_files_with_extensions(workspace_dir, extensions) {
-            detected.push(*lang_name);
-        }
-    }
-
-    detected
-}
-
-/// Check if the workspace contains files with any of the given extensions.
-/// Scans up to a reasonable depth to avoid slow startup on large repos.
-fn has_files_with_extensions(workspace_dir: &Path, extensions: &[&str]) -> bool {
-    // Quick check: scan top-level and one level deep
-    // This avoids slow startup on large repos while catching most projects
-    scan_directory_for_extensions(workspace_dir, extensions, 2)
-}
-
-/// Recursively scan a directory for files with given extensions, up to max_depth.
-fn scan_directory_for_extensions(dir: &Path, extensions: &[&str], max_depth: usize) -> bool {
-    if max_depth == 0 {
-        return false;
-    }
-
-    let entries = match std::fs::read_dir(dir) {
-        Ok(entries) => entries,
-        Err(_) => return false,
-    };
-
-    for entry in entries.flatten() {
-        let path = entry.path();
-        
-        // Skip hidden directories and common non-source directories
-        if let Some(name) = path.file_name().and_then(|n| n.to_str()) {
-            if name.starts_with('.') || name == "node_modules" || name == "target" || name == "vendor" {
-                continue;
-            }
-        }
-
-        if path.is_file() {
-            if let Some(name) = path.file_name().and_then(|n| n.to_str()) {
-                for ext in extensions {
-                    if name.ends_with(ext) {
-                        return true;
-                    }
-                }
-            }
-        } else if path.is_dir() {
-            if scan_directory_for_extensions(&path, extensions, max_depth - 1) {
-                return true;
-            }
-        }
-    }
-
-    false
-}
-
-/// Get the prompt content for a specific language.
-pub fn get_language_prompt(lang: &str) -> Option<&'static str> {
-    LANGUAGE_PROMPTS
-        .iter()
-        .find(|(name, _, _)| *name == lang)
-        .map(|(_, _, content)| *content)
-}
-
-/// Get all language prompts for detected languages in the workspace.
-/// Returns formatted content ready for injection into the system prompt.
-pub fn get_language_prompts_for_workspace(workspace_dir: &Path) -> Option<String> {
-    let detected = detect_languages(workspace_dir);
-    
-    if detected.is_empty() {
-        return None;
-    }
-
-    let mut prompts = Vec::new();
-    for lang in detected {
-        if let Some(content) = get_language_prompt(lang) {
-            if !content.is_empty() {
-                prompts.push(content);
-            }
-        }
-    }
-
-    if prompts.is_empty() {
-        return None;
-    }
-
-    Some(format!(
-        "🔧 Language-Specific Guidance:\n\n{}",
-        prompts.join("\n\n---\n\n")
-    ))
-}
-
-/// List all available language prompts.
-pub fn list_available_languages() -> Vec<&'static str> {
-    LANGUAGE_PROMPTS.iter().map(|(name, _, _)| *name).collect()
-}
-
-/// Get agent-specific language prompt for a specific agent and language.
-pub fn get_agent_language_prompt(agent_name: &str, lang: &str) -> Option<&'static str> {
-    AGENT_LANGUAGE_PROMPTS
-        .iter()
-        .find(|(agent, language, _)| *agent == agent_name && *language == lang)
-        .map(|(_, _, content)| *content)
-}
-
-/// Get agent-specific language prompts for detected languages in the workspace.
-/// Returns formatted content ready for injection into the agent's system prompt.
-#[allow(dead_code)]
-pub fn get_agent_language_prompts_for_workspace(
-    workspace_dir: &Path,
-    agent_name: &str,
-) -> Option<String> {
-    let (content, _) = get_agent_language_prompts_for_workspace_with_langs(workspace_dir, agent_name);
-    content
-}
-
-/// Get agent-specific language prompts for detected languages in the workspace.
-/// Returns both the formatted content and the list of languages that had matching prompts.
-pub fn get_agent_language_prompts_for_workspace_with_langs(
-    workspace_dir: &Path,
-    agent_name: &str,
-) -> (Option<String>, Vec<&'static str>) {
-    let detected = detect_languages(workspace_dir);
-    let mut prompts = Vec::new();
-    let mut matched_langs = Vec::new();
-
-    for lang in detected {
-        if let Some(content) = get_agent_language_prompt(agent_name, lang) {
-            prompts.push(content.to_string());
-            matched_langs.push(lang);
-        }
-    }
-
-    let content = if prompts.is_empty() { None } else { Some(prompts.join("\n\n---\n\n")) };
-    (content, matched_langs)
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use std::fs;
-    use tempfile::TempDir;
-
-    #[test]
-    fn test_racket_prompt_embedded() {
-        let prompt = get_language_prompt("racket");
-        assert!(prompt.is_some());
-        assert!(prompt.unwrap().contains("raco"));
-    }
-
-    #[test]
-    fn test_list_available_languages() {
-        let langs = list_available_languages();
-        assert!(langs.contains(&"racket"));
-    }
-
-    #[test]
-    fn test_detect_racket_files() {
-        let temp_dir = TempDir::new().unwrap();
-        let rkt_file = temp_dir.path().join("main.rkt");
-        fs::write(&rkt_file, "#lang racket\n").unwrap();
-
-        let detected = detect_languages(temp_dir.path());
-        assert!(detected.contains(&"racket"));
-    }
-
-    #[test]
-    fn test_no_detection_empty_dir() {
-        let temp_dir = TempDir::new().unwrap();
-        let detected = detect_languages(temp_dir.path());
-        assert!(detected.is_empty());
-    }
-
-    #[test]
-    fn test_get_prompts_for_workspace() {
-        let temp_dir = TempDir::new().unwrap();
-        let rkt_file = temp_dir.path().join("main.rkt");
-        fs::write(&rkt_file, "#lang racket\n").unwrap();
-
-        let prompts = get_language_prompts_for_workspace(temp_dir.path());
-        assert!(prompts.is_some());
-        let content = prompts.unwrap();
-        assert!(content.contains("🔧 Language-Specific Guidance"));
-        assert!(content.contains("raco"));
-    }
-
-    #[test]
-    fn test_carmack_racket_prompt_embedded() {
-        let prompt = get_agent_language_prompt("carmack", "racket");
-        assert!(prompt.is_some());
-        assert!(prompt.unwrap().contains("obvious, readable Racket"));
-    }
-
-    #[test]
-    fn test_agent_language_prompt_not_found() {
-        let prompt = get_agent_language_prompt("nonexistent", "racket");
-        assert!(prompt.is_none());
-    }
-
-    #[test]
-    fn test_get_agent_prompts_for_workspace() {
-        let temp_dir = TempDir::new().unwrap();
-        let rkt_file = temp_dir.path().join("main.rkt");
-        fs::write(&rkt_file, "#lang racket\n").unwrap();
-
-        let prompts = get_agent_language_prompts_for_workspace(temp_dir.path(), "carmack");
-        assert!(prompts.is_some());
-        let content = prompts.unwrap();
-        assert!(content.contains("obvious, readable Racket"));
-    }
-
-    #[test]
-    fn test_rust_only_returns_none() {
-        // Rust has an empty prompt, so a Rust-only workspace should return None
-        let temp_dir = TempDir::new().unwrap();
-        let rs_file = temp_dir.path().join("main.rs");
-        fs::write(&rs_file, "fn main() {}").unwrap();
-
-        let prompts = get_language_prompts_for_workspace(temp_dir.path());
-        assert!(prompts.is_none(), "Rust-only workspace should return None since Rust has no base prompt");
-    }
-}

crates/g3-cli/src/machine_ui_writer.rs

@@ -0,0 +1,94 @@
+use g3_core::ui_writer::UiWriter;
+use std::io::{self, Write};
+
+/// Machine-mode implementation of UiWriter that prints plain, unformatted output
+/// This is designed for programmatic consumption and outputs everything verbatim
+pub struct MachineUiWriter;
+
+impl MachineUiWriter {
+    pub fn new() -> Self {
+        Self
+    }
+}
+
+impl UiWriter for MachineUiWriter {
+    fn print(&self, message: &str) {
+        print!("{}", message);
+    }
+
+    fn println(&self, message: &str) {
+        println!("{}", message);
+    }
+
+    fn print_inline(&self, message: &str) {
+        print!("{}", message);
+        let _ = io::stdout().flush();
+    }
+
+    fn print_system_prompt(&self, prompt: &str) {
+        println!("SYSTEM_PROMPT:");
+        println!("{}", prompt);
+        println!("END_SYSTEM_PROMPT");
+        println!();
+    }
+
+    fn print_context_status(&self, message: &str) {
+        println!("CONTEXT_STATUS: {}", message);
+    }
+
+    fn print_context_thinning(&self, message: &str) {
+        println!("CONTEXT_THINNING: {}", message);
+    }
+
+    fn print_tool_header(&self, tool_name: &str) {
+        println!("TOOL_CALL: {}", tool_name);
+    }
+
+    fn print_tool_arg(&self, key: &str, value: &str) {
+        println!("TOOL_ARG: {} = {}", key, value);
+    }
+
+    fn print_tool_output_header(&self) {
+        println!("TOOL_OUTPUT:");
+    }
+
+    fn update_tool_output_line(&self, line: &str) {
+        println!("{}", line);
+    }
+
+    fn print_tool_output_line(&self, line: &str) {
+        println!("{}", line);
+    }
+
+    fn print_tool_output_summary(&self, count: usize) {
+        println!("TOOL_OUTPUT_LINES: {}", count);
+    }
+
+    fn print_tool_timing(&self, duration_str: &str) {
+        println!("TOOL_DURATION: {}", duration_str);
+        println!("END_TOOL_OUTPUT");
+        println!();
+    }
+
+    fn print_agent_prompt(&self) {
+        println!("AGENT_RESPONSE:");
+        let _ = io::stdout().flush();
+    }
+
+    fn print_agent_response(&self, content: &str) {
+        print!("{}", content);
+        let _ = io::stdout().flush();
+    }
+
+    fn notify_sse_received(&self) {
+        // No-op for machine mode
+    }
+
+    fn flush(&self) {
+        let _ = io::stdout().flush();
+    }
+    
+    fn wants_full_output(&self) -> bool {
+        true  // Machine mode wants complete, untruncated output
+    }
+}

crates/g3-cli/src/metrics.rs

@@ -1,147 +0,0 @@
-//! Turn metrics and histogram generation for performance visualization.
-
-use std::time::Duration;
-
-/// Metrics captured for a single turn of interaction.
-#[derive(Debug, Clone)]
-pub struct TurnMetrics {
-    pub turn_number: usize,
-    pub tokens_used: u32,
-    pub wall_clock_time: Duration,
-}
-
-/// Format a Duration as human-readable elapsed time (e.g., "1h 23m 45s").
-pub fn format_elapsed_time(duration: Duration) -> String {
-    let total_secs = duration.as_secs();
-    let hours = total_secs / 3600;
-    let minutes = (total_secs % 3600) / 60;
-    let seconds = total_secs % 60;
-
-    match (hours, minutes, seconds) {
-        (h, m, s) if h > 0 => format!("{}h {}m {}s", h, m, s),
-        (_, m, s) if m > 0 => format!("{}m {}s", m, s),
-        (_, _, s) if s > 0 => format!("{}s", s),
-        _ => format!("{}ms", duration.as_millis()),
-    }
-}
-
-/// Generate a histogram showing tokens used and wall clock time per turn.
-pub fn generate_turn_histogram(turn_metrics: &[TurnMetrics]) -> String {
-    if turn_metrics.is_empty() {
-        return "   No turn data available".to_string();
-    }
-
-    const MAX_BAR_WIDTH: usize = 40;
-    const TOKEN_CHAR: char = '█';
-    const TIME_CHAR: char = '▓';
-
-    let max_tokens = turn_metrics.iter().map(|t| t.tokens_used).max().unwrap_or(1);
-    let max_time_ms = turn_metrics
-        .iter()
-        .map(|t| t.wall_clock_time.as_millis().min(u32::MAX as u128) as u32)
-        .max()
-        .unwrap_or(1);
-
-    let mut histogram = String::new();
-    histogram.push_str("\n📊 Per-Turn Performance Histogram:\n");
-    histogram.push_str(&format!("   {} = Tokens Used (max: {})\n", TOKEN_CHAR, max_tokens));
-    histogram.push_str(&format!(
-        "   {} = Wall Clock Time (max: {:.1}s)\n\n",
-        TIME_CHAR,
-        max_time_ms as f64 / 1000.0
-    ));
-
-    for metrics in turn_metrics {
-        let turn_time_ms = metrics.wall_clock_time.as_millis().min(u32::MAX as u128) as u32;
-
-        let token_bar_len = scale_bar(metrics.tokens_used, max_tokens, MAX_BAR_WIDTH);
-        let time_bar_len = scale_bar(turn_time_ms, max_time_ms, MAX_BAR_WIDTH);
-
-        let time_str = format_duration_ms(turn_time_ms);
-        let token_bar = TOKEN_CHAR.to_string().repeat(token_bar_len);
-        let time_bar = TIME_CHAR.to_string().repeat(time_bar_len);
-
-        histogram.push_str(&format!(
-            "   Turn {:2}: {:>6} tokens │{:<40}│\n",
-            metrics.turn_number, metrics.tokens_used, token_bar
-        ));
-        histogram.push_str(&format!("           {:>6}       │{:<40}│\n", time_str, time_bar));
-
-        // Separator between turns (except for last)
-        if metrics.turn_number != turn_metrics.last().unwrap().turn_number {
-            histogram.push_str(
-                "           ────────────┼────────────────────────────────────────┤\n",
-            );
-        }
-    }
-
-    append_summary_statistics(&mut histogram, turn_metrics);
-    histogram
-}
-
-/// Scale a value to a bar length proportional to max.
-fn scale_bar(value: u32, max: u32, max_width: usize) -> usize {
-    if max == 0 {
-        0
-    } else {
-        ((value as f64 / max as f64) * max_width as f64) as usize
-    }
-}
-
-/// Format milliseconds as a human-readable duration string.
-fn format_duration_ms(ms: u32) -> String {
-    match ms {
-        ms if ms < 1000 => format!("{}ms", ms),
-        ms if ms < 60_000 => format!("{:.1}s", ms as f64 / 1000.0),
-        ms => {
-            let minutes = ms / 60_000;
-            let seconds = (ms % 60_000) as f64 / 1000.0;
-            format!("{}m{:.1}s", minutes, seconds)
-        }
-    }
-}
-
-/// Append summary statistics to the histogram output.
-fn append_summary_statistics(histogram: &mut String, turn_metrics: &[TurnMetrics]) {
-    let total_tokens: u32 = turn_metrics.iter().map(|t| t.tokens_used).sum();
-    let total_time: Duration = turn_metrics.iter().map(|t| t.wall_clock_time).sum();
-    let avg_tokens = total_tokens as f64 / turn_metrics.len() as f64;
-    let avg_time_ms = total_time.as_millis() as f64 / turn_metrics.len() as f64;
-
-    histogram.push_str("\n📈 Summary Statistics:\n");
-    histogram.push_str(&format!(
-        "   • Total Tokens: {} across {} turns\n",
-        total_tokens,
-        turn_metrics.len()
-    ));
-    histogram.push_str(&format!("   • Average Tokens/Turn: {:.1}\n", avg_tokens));
-    histogram.push_str(&format!("   • Total Time: {:.1}s\n", total_time.as_secs_f64()));
-    histogram.push_str(&format!("   • Average Time/Turn: {:.1}s\n", avg_time_ms / 1000.0));
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_format_elapsed_time() {
-        assert_eq!(format_elapsed_time(Duration::from_millis(500)), "500ms");
-        assert_eq!(format_elapsed_time(Duration::from_secs(45)), "45s");
-        assert_eq!(format_elapsed_time(Duration::from_secs(90)), "1m 30s");
-        assert_eq!(format_elapsed_time(Duration::from_secs(3661)), "1h 1m 1s");
-    }
-
-    #[test]
-    fn test_empty_histogram() {
-        let result = generate_turn_histogram(&[]);
-        assert!(result.contains("No turn data available"));
-    }
-
-    #[test]
-    fn test_scale_bar() {
-        assert_eq!(scale_bar(50, 100, 40), 20);
-        assert_eq!(scale_bar(100, 100, 40), 40);
-        assert_eq!(scale_bar(0, 100, 40), 0);
-        assert_eq!(scale_bar(50, 0, 40), 0);
-    }
-}

crates/g3-cli/src/project.rs

@@ -1,290 +0,0 @@
-//! Project loading and management for the /project command.
-//!
-//! Projects allow loading context from a specific project directory that persists
-//! in the system message and survives compaction/dehydration.
-
-use anyhow::{anyhow, Result};
-use std::path::{Path, PathBuf};
-
-/// Represents an active project with its loaded content.
-#[derive(Debug, Clone)]
-pub struct Project {
-    /// Absolute path to the project directory
-    pub path: PathBuf,
-    /// Combined content blob to append to system message
-    pub content: String,
-    /// List of files that were successfully loaded
-    pub loaded_files: Vec<String>,
-}
-
-impl Project {
-    /// Load a project from the given absolute path.
-    ///
-    /// Loads the following files if present (skips missing silently):
-    /// - brief.md
-    /// - contacts.yaml
-    /// - status.md
-    ///
-    /// Also loads projects.md from the workspace root if present.
-    pub fn load(project_path: &Path, workspace_dir: &Path) -> Option<Self> {
-        let mut content_parts = Vec::new();
-        let mut loaded_files = Vec::new();
-
-        // Load workspace-level projects.md if present
-        let projects_md_path = workspace_dir.join("projects.md");
-        if projects_md_path.exists() {
-            if let Ok(projects_content) = std::fs::read_to_string(&projects_md_path) {
-                content_parts.push(format!(
-                    "=== PROJECT INSTRUCTIONS ===\n{}\n=== END PROJECT INSTRUCTIONS ===",
-                    projects_content.trim()
-                ));
-                loaded_files.push("projects.md".to_string());
-            }
-        }
-
-        // Load project-specific files
-        let project_files = ["brief.md", "contacts.yaml", "status.md"];
-        let mut project_content_parts = Vec::new();
-
-        for filename in &project_files {
-            let file_path = project_path.join(filename);
-            if file_path.exists() {
-                if let Ok(file_content) = std::fs::read_to_string(&file_path) {
-                    let section_name = match *filename {
-                        "brief.md" => "Brief",
-                        "contacts.yaml" => "Contacts",
-                        "status.md" => "Status",
-                        _ => filename,
-                    };
-                    project_content_parts.push(format!(
-                        "## {}\n{}",
-                        section_name,
-                        file_content.trim()
-                    ));
-                    loaded_files.push(filename.to_string());
-                }
-            }
-        }
-
-        // If we loaded any project-specific files, add the active project header
-        if !project_content_parts.is_empty() {
-            content_parts.push(format!(
-                "=== ACTIVE PROJECT: {} ===\n{}",
-                project_path.display(),
-                project_content_parts.join("\n\n")
-            ));
-        }
-
-        // Only return a project if we loaded something
-        if loaded_files.is_empty() {
-            return None;
-        }
-
-        Some(Project {
-            path: project_path.to_path_buf(),
-            content: content_parts.join("\n\n"),
-            loaded_files,
-        })
-    }
-
-    /// Format the loaded files status message (e.g., "✓ brief.md  ✓ status.md")
-    pub fn format_loaded_status(&self) -> String {
-        self.loaded_files
-            .iter()
-            .map(|f| format!("✓ {}", f))
-            .collect::<Vec<_>>()
-            .join("  ")
-    }
-}
-
-/// Load and validate a project from a path string.
-///
-/// This is the shared logic used by both `--project` CLI flag and `/project` command.
-/// It handles:
-/// - Tilde expansion for home directory
-/// - Validation that path is absolute
-/// - Validation that path exists
-/// - Loading project files
-///
-/// Returns the loaded Project or an error with a user-friendly message.
-pub fn load_and_validate_project(project_path_str: &str, workspace_dir: &Path) -> Result<Project> {
-    // Expand tilde if present
-    let project_path = if project_path_str.starts_with("~/") {
-        if let Some(home) = dirs::home_dir() {
-            home.join(&project_path_str[2..])
-        } else {
-            PathBuf::from(project_path_str)
-        }
-    } else {
-        PathBuf::from(project_path_str)
-    };
-
-    // Validate path is absolute
-    if !project_path.is_absolute() {
-        return Err(anyhow!(
-            "Project path must be absolute (e.g., /Users/name/projects/myproject)"
-        ));
-    }
-
-    // Validate path exists
-    if !project_path.exists() {
-        return Err(anyhow!("Project path does not exist: {}", project_path.display()));
-    }
-
-    // Load the project
-    Project::load(&project_path, workspace_dir)
-        .ok_or_else(|| anyhow!("No project files found (brief.md, contacts.yaml, status.md)"))
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use std::fs;
-    use tempfile::TempDir;
-
-    #[test]
-    fn test_format_loaded_status() {
-        let project = Project {
-            path: PathBuf::from("/test/project"),
-            content: String::new(),
-            loaded_files: vec!["brief.md".to_string(), "status.md".to_string()],
-        };
-        assert_eq!(project.format_loaded_status(), "✓ brief.md  ✓ status.md");
-    }
-
-    #[test]
-    fn test_format_loaded_status_single_file() {
-        let project = Project {
-            path: PathBuf::from("/test/project"),
-            content: String::new(),
-            loaded_files: vec!["brief.md".to_string()],
-        };
-        assert_eq!(project.format_loaded_status(), "✓ brief.md");
-    }
-
-    #[test]
-    fn test_load_project_with_all_files() {
-        let workspace = TempDir::new().unwrap();
-        let project_dir = TempDir::new().unwrap();
-
-        // Create project files
-        fs::write(project_dir.path().join("brief.md"), "Project brief").unwrap();
-        fs::write(project_dir.path().join("contacts.yaml"), "contacts: []").unwrap();
-        fs::write(project_dir.path().join("status.md"), "In progress").unwrap();
-
-        let project = Project::load(project_dir.path(), workspace.path()).unwrap();
-
-        assert_eq!(project.loaded_files.len(), 3);
-        assert!(project.loaded_files.contains(&"brief.md".to_string()));
-        assert!(project.loaded_files.contains(&"contacts.yaml".to_string()));
-        assert!(project.loaded_files.contains(&"status.md".to_string()));
-        assert!(project.content.contains("=== ACTIVE PROJECT:"));
-        assert!(project.content.contains("## Brief"));
-        assert!(project.content.contains("## Contacts"));
-        assert!(project.content.contains("## Status"));
-    }
-
-    #[test]
-    fn test_load_project_with_workspace_projects_md() {
-        let workspace = TempDir::new().unwrap();
-        let project_dir = TempDir::new().unwrap();
-
-        // Create workspace projects.md
-        fs::write(workspace.path().join("projects.md"), "Global project instructions").unwrap();
-
-        // Create one project file
-        fs::write(project_dir.path().join("brief.md"), "Project brief").unwrap();
-
-        let project = Project::load(project_dir.path(), workspace.path()).unwrap();
-
-        assert_eq!(project.loaded_files.len(), 2);
-        assert!(project.loaded_files.contains(&"projects.md".to_string()));
-        assert!(project.loaded_files.contains(&"brief.md".to_string()));
-        assert!(project.content.contains("=== PROJECT INSTRUCTIONS ==="));
-        assert!(project.content.contains("=== END PROJECT INSTRUCTIONS ==="));
-        assert!(project.content.contains("=== ACTIVE PROJECT:"));
-    }
-
-    #[test]
-    fn test_load_project_missing_files() {
-        let workspace = TempDir::new().unwrap();
-        let project_dir = TempDir::new().unwrap();
-
-        // Create only one file
-        fs::write(project_dir.path().join("status.md"), "Status only").unwrap();
-
-        let project = Project::load(project_dir.path(), workspace.path()).unwrap();
-
-        assert_eq!(project.loaded_files.len(), 1);
-        assert!(project.loaded_files.contains(&"status.md".to_string()));
-        assert!(!project.content.contains("## Brief"));
-        assert!(project.content.contains("## Status"));
-    }
-
-    #[test]
-    fn test_load_project_no_files() {
-        let workspace = TempDir::new().unwrap();
-        let project_dir = TempDir::new().unwrap();
-
-        // No files created
-        let project = Project::load(project_dir.path(), workspace.path());
-
-        assert!(project.is_none());
-    }
-
-    #[test]
-    fn test_load_and_validate_project_success() {
-        let workspace = TempDir::new().unwrap();
-        let project_dir = TempDir::new().unwrap();
-
-        // Create project files
-        fs::write(project_dir.path().join("brief.md"), "Project brief").unwrap();
-
-        let result = load_and_validate_project(
-            project_dir.path().to_str().unwrap(),
-            workspace.path(),
-        );
-
-        assert!(result.is_ok());
-        let project = result.unwrap();
-        assert!(project.loaded_files.contains(&"brief.md".to_string()));
-    }
-
-    #[test]
-    fn test_load_and_validate_project_relative_path_error() {
-        let workspace = TempDir::new().unwrap();
-
-        let result = load_and_validate_project("relative/path", workspace.path());
-
-        assert!(result.is_err());
-        let err = result.unwrap_err().to_string();
-        assert!(err.contains("must be absolute"));
-    }
-
-    #[test]
-    fn test_load_and_validate_project_nonexistent_path_error() {
-        let workspace = TempDir::new().unwrap();
-
-        let result = load_and_validate_project("/nonexistent/path/12345", workspace.path());
-
-        assert!(result.is_err());
-        let err = result.unwrap_err().to_string();
-        assert!(err.contains("does not exist"));
-    }
-
-    #[test]
-    fn test_load_and_validate_project_no_files_error() {
-        let workspace = TempDir::new().unwrap();
-        let project_dir = TempDir::new().unwrap();
-
-        // No project files created
-        let result = load_and_validate_project(
-            project_dir.path().to_str().unwrap(),
-            workspace.path(),
-        );
-
-        assert!(result.is_err());
-        let err = result.unwrap_err().to_string();
-        assert!(err.contains("No project files found"));
-    }
-}

crates/g3-cli/src/project_files.rs

@@ -1,400 +0,0 @@
-//! Project file reading utilities.
-//!
-//! Reads AGENTS.md and workspace memory files from the workspace.
-
-use std::path::Path;
-use std::path::PathBuf;
-use tracing::error;
-
-use crate::template::process_template;
-use g3_core::{discover_skills, generate_skills_prompt, Skill};
-use g3_config::SkillsConfig;
-
-/// Read AGENTS.md configuration from the workspace directory.
-/// Returns formatted content with emoji prefix, or None if not found.
-pub fn read_agents_config(workspace_dir: &Path) -> Option<String> {
-    // Try AGENTS.md first, then agents.md
-    let paths = [
-        (workspace_dir.join("AGENTS.md"), "AGENTS.md"),
-        (workspace_dir.join("agents.md"), "agents.md"),
-    ];
-
-    for (path, name) in &paths {
-        if path.exists() {
-            match std::fs::read_to_string(path) {
-                Ok(content) => {
-                    return Some(format!("🤖 Agent Configuration (from {}):{}\n{}", name, "\n", content));
-                }
-                Err(e) => {
-                    error!("Failed to read {}: {}", name, e);
-                }
-            }
-        }
-    }
-    None
-}
-
-/// Read workspace memory from analysis/memory.md in the workspace directory.
-/// Returns formatted content with emoji prefix and size info, or None if not found.
-pub fn read_workspace_memory(workspace_dir: &Path) -> Option<String> {
-    let memory_path = workspace_dir.join("analysis").join("memory.md");
-
-    if !memory_path.exists() {
-        return None;
-    }
-
-    match std::fs::read_to_string(&memory_path) {
-        Ok(content) => {
-            let size = format_size(content.len());
-            Some(format!(
-                "=== Workspace Memory (read from analysis/memory.md, {}) ===\n{}\n=== End Workspace Memory ===",
-                size,
-                content
-            ))
-        }
-        Err(_) => None,
-    }
-}
-
-/// Read include prompt content from a specified file path.
-/// Returns formatted content with emoji prefix, or None if path is None or file doesn't exist.
-pub fn read_include_prompt(path: Option<&std::path::Path>) -> Option<String> {
-    let path = path?;
-    
-    if !path.exists() {
-        tracing::error!("Include prompt file not found: {}", path.display());
-        return None;
-    }
-
-    match std::fs::read_to_string(path) {
-        Ok(content) => {
-            let processed = process_template(&content);
-            Some(format!("📎 Included Prompt (from {}):\n{}", path.display(), processed))
-        }
-        Err(e) => {
-            tracing::error!("Failed to read include prompt file {}: {}", path.display(), e);
-            None
-        }
-    }
-}
-
-/// Combine AGENTS.md and memory content into a single string for project context.
-///
-/// Returns None if all inputs are None, otherwise joins non-None parts with double newlines.
-/// Prepends the current working directory to help the LLM avoid path hallucinations.
-/// 
-/// Order: Working Directory → AGENTS.md → Language prompts → Include prompt → Memory
-pub fn combine_project_content(
-    agents_content: Option<String>,
-    memory_content: Option<String>,
-    language_content: Option<String>,
-    include_prompt: Option<String>,
-    skills_content: Option<String>,
-    workspace_dir: &Path,
-) -> Option<String> {
-    // Always include working directory to prevent LLM from hallucinating paths
-    let cwd_info = format!("📂 Working Directory: {}", workspace_dir.display());
-    
-    // Order: cwd → agents → language → include_prompt → skills → memory
-    // Include prompt comes BEFORE memory so memory is always last (most recent context)
-    let parts: Vec<String> = [
-        Some(cwd_info), agents_content, language_content, include_prompt, skills_content, memory_content
-    ]
-        .into_iter()
-        .flatten()
-        .collect();
-
-    if parts.is_empty() {
-        None
-    } else {
-        Some(parts.join("\n\n"))
-    }
-}
-
-/// Format a byte size for display.
-fn format_size(len: usize) -> String {
-    if len < 1000 {
-        format!("{} chars", len)
-    } else {
-        format!("{:.1}k chars", len as f64 / 1000.0)
-    }
-}
-
-/// Extract the first H1 heading from project context content for display.
-/// Looks for H1 headings in AGENTS.md or memory content.
-pub fn extract_project_heading(project_context: &str) -> Option<String> {
-    // Look for H1 heading in the content
-    // Skip prefix lines (emoji markers)
-    for line in project_context.lines() {
-        let trimmed = line.trim();
-        
-        // Skip emoji prefix lines
-        if trimmed.starts_with("📂") || trimmed.starts_with("🤖") || trimmed.starts_with("🔧") || trimmed.starts_with("📎") || trimmed.starts_with("===") {
-            continue;
-        }
-        
-        if let Some(stripped) = trimmed.strip_prefix("# ") {
-            let title = stripped.trim();
-            if !title.is_empty() {
-                return Some(title.to_string());
-            }
-        }
-    }
-
-    // Fallback: first non-empty, non-metadata line
-    find_fallback_title(project_context)
-}
-
-/// Find a fallback title from the first few lines of content.
-fn find_fallback_title(content: &str) -> Option<String> {
-    for line in content.lines().take(5) {
-        let trimmed = line.trim();
-        if !trimmed.is_empty()
-            && !trimmed.starts_with("📚")
-            && !trimmed.starts_with("📂")
-            && !trimmed.starts_with("🤖")
-            && !trimmed.starts_with("🔧")
-            && !trimmed.starts_with('#')
-            && !trimmed.starts_with("==")
-            && !trimmed.starts_with("--")
-        {
-            return Some(truncate_for_display(trimmed, 100));
-        }
-    }
-    None
-}
-
-/// Truncate a string for display, adding ellipsis if needed.
-fn truncate_for_display(s: &str, max_len: usize) -> String {
-    if s.chars().count() <= max_len {
-        s.to_string()
-    } else {
-        // Truncate at character boundary, not byte boundary
-        let truncated: String = s.chars().take(max_len.saturating_sub(3)).collect();
-        format!("{}...", truncated)
-    }
-}
-
-/// Discover skills from configured paths and generate the skills prompt.
-///
-/// Returns the skills prompt section if any skills are found, None otherwise.
-/// Skills are discovered from:
-/// 1. Global: ~/.g3/skills/
-/// 2. Extra paths from config
-/// 3. Workspace: .g3/skills/ (highest priority)
-pub fn discover_and_format_skills(
-    workspace_dir: &Path,
-    skills_config: &SkillsConfig,
-) -> (Vec<Skill>, Option<String>) {
-    if !skills_config.enabled {
-        return (Vec::new(), None);
-    }
-
-    // Convert extra_paths from config to PathBuf
-    let extra_paths: Vec<PathBuf> = skills_config
-        .extra_paths
-        .iter()
-        .map(|p| PathBuf::from(p))
-        .collect();
-
-    let skills = discover_skills(Some(workspace_dir), &extra_paths);
-    
-    if skills.is_empty() {
-        return (Vec::new(), None);
-    }
-
-    let prompt = generate_skills_prompt(&skills);
-    (skills, Some(prompt))
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_extract_project_heading() {
-        let content = "# My Project\n\nSome description";
-        assert_eq!(extract_project_heading(content), Some("My Project".to_string()));
-    }
-
-    #[test]
-    fn test_extract_project_heading_with_agents_prefix() {
-        let content = "🤖 Agent Configuration (from AGENTS.md):\n# Cool App\n\nDescription";
-        assert_eq!(extract_project_heading(content), Some("Cool App".to_string()));
-    }
-
-    #[test]
-    fn test_format_size() {
-        assert_eq!(format_size(500), "500 chars");
-        assert_eq!(format_size(1500), "1.5k chars");
-    }
-
-    #[test]
-    fn test_truncate_for_display() {
-        assert_eq!(truncate_for_display("short", 100), "short");
-        let long = "a".repeat(150);
-        let truncated = truncate_for_display(&long, 100);
-        assert!(truncated.ends_with("..."));
-        assert_eq!(truncated.len(), 100);
-    }
-
-    #[test]
-    fn test_truncate_for_display_utf8() {
-        // Multi-byte characters should not cause panics
-        let emoji_text = "Hello 👋 World 🌍 Test ✨ More text here and more";
-        let truncated = truncate_for_display(emoji_text, 15);
-        assert!(truncated.ends_with("..."));
-        assert!(truncated.chars().count() <= 15);
-    }
-
-    #[test]
-    fn test_combine_project_content_all_some() {
-        let workspace = std::path::PathBuf::from("/test/workspace");
-        let result = combine_project_content(
-            Some("agents".to_string()),
-            Some("memory".to_string()),
-            Some("language".to_string()),
-            None, // include_prompt
-            None, // skills_content
-            &workspace,
-        );
-        assert!(result.is_some());
-        let content = result.unwrap();
-        assert!(content.contains("📂 Working Directory: /test/workspace"));
-        assert!(content.contains("agents"));
-        assert!(content.contains("memory"));
-        assert!(content.contains("language"));
-    }
-
-    #[test]
-    fn test_combine_project_content_partial() {
-        let workspace = std::path::PathBuf::from("/test/workspace");
-        let result = combine_project_content(None, Some("memory".to_string()), None, None, None, &workspace);
-        assert!(result.is_some());
-        let content = result.unwrap();
-        assert!(content.contains("📂 Working Directory: /test/workspace"));
-        assert!(content.contains("memory"));
-    }
-
-    #[test]
-    fn test_combine_project_content_all_none() {
-        let workspace = std::path::PathBuf::from("/test/workspace");
-        let result = combine_project_content(None, None, None, None, None, &workspace);
-        // Now always returns Some because we always include the working directory
-        assert!(result.is_some());
-        assert!(result.unwrap().contains("📂 Working Directory: /test/workspace"));
-    }
-
-    #[test]
-    fn test_combine_project_content_with_include_prompt() {
-        let workspace = std::path::PathBuf::from("/test/workspace");
-        let result = combine_project_content(
-            Some("agents".to_string()),
-            Some("memory".to_string()),
-            Some("language".to_string()),
-            Some("include_prompt".to_string()),
-            None, // skills_content
-            &workspace,
-        );
-        assert!(result.is_some());
-        let content = result.unwrap();
-        assert!(content.contains("include_prompt"));
-    }
-
-    #[test]
-    fn test_combine_project_content_order() {
-        // Verify correct ordering: agents < language < include_prompt < memory
-        let workspace = std::path::PathBuf::from("/test/workspace");
-        let result = combine_project_content(
-            Some("AGENTS_CONTENT".to_string()),
-            Some("MEMORY_CONTENT".to_string()),
-            Some("LANGUAGE_CONTENT".to_string()),
-            Some("INCLUDE_PROMPT_CONTENT".to_string()),
-            None, // skills_content
-            &workspace,
-        );
-        let content = result.unwrap();
-        
-        // Find positions of each section
-        let agents_pos = content.find("AGENTS_CONTENT").expect("agents not found");
-        let language_pos = content.find("LANGUAGE_CONTENT").expect("language not found");
-        let include_pos = content.find("INCLUDE_PROMPT_CONTENT").expect("include_prompt not found");
-        let memory_pos = content.find("MEMORY_CONTENT").expect("memory not found");
-        
-        // Verify order: agents < language < include_prompt < memory
-        assert!(agents_pos < language_pos, "agents should come before language");
-        assert!(language_pos < include_pos, "language should come before include_prompt");
-        assert!(include_pos < memory_pos, "include_prompt should come before memory");
-    }
-
-    #[test]
-    fn test_combine_project_content_order_memory_last() {
-        // Verify memory is always last even when include_prompt is None
-        let workspace = std::path::PathBuf::from("/test/workspace");
-        let result = combine_project_content(
-            Some("AGENTS".to_string()),
-            Some("MEMORY".to_string()),
-            Some("LANGUAGE".to_string()),
-            None, // no include_prompt
-            None, // skills_content
-            &workspace,
-        );
-        let content = result.unwrap();
-        
-        // Memory should still be last
-        let language_pos = content.find("LANGUAGE").expect("language not found");
-        let memory_pos = content.find("MEMORY").expect("memory not found");
-        assert!(language_pos < memory_pos, "memory should come after language");
-    }
-
-    #[test]
-    fn test_read_include_prompt_none_path() {
-        // None path should return None
-        let result = read_include_prompt(None);
-        assert!(result.is_none());
-    }
-
-    #[test]
-    fn test_read_include_prompt_nonexistent_file() {
-        // Non-existent file should return None
-        let path = std::path::Path::new("/nonexistent/path/to/file.md");
-        let result = read_include_prompt(Some(path));
-        assert!(result.is_none());
-    }
-
-    #[test]
-    fn test_read_include_prompt_valid_file() {
-        // Create a temp file and read it
-        let temp_dir = std::env::temp_dir();
-        let temp_file = temp_dir.join("test_include_prompt.md");
-        std::fs::write(&temp_file, "Test prompt content").unwrap();
-        
-        let result = read_include_prompt(Some(&temp_file));
-        assert!(result.is_some());
-        let content = result.unwrap();
-        assert!(content.contains("📎 Included Prompt"));
-        assert!(content.contains("Test prompt content"));
-        
-        // Cleanup
-        let _ = std::fs::remove_file(&temp_file);
-    }
-
-    #[test]
-    fn test_read_include_prompt_with_template_variables() {
-        // Create a temp file with template variables
-        let temp_dir = std::env::temp_dir();
-        let temp_file = temp_dir.join("test_include_prompt_template.md");
-        std::fs::write(&temp_file, "Today is {{today}} and {{unknown}} stays").unwrap();
-        
-        let result = read_include_prompt(Some(&temp_file));
-        assert!(result.is_some());
-        let content = result.unwrap();
-        
-        // {{today}} should be replaced with a date, {{unknown}} should remain
-        assert!(!content.contains("{{today}}"));
-        assert!(content.contains("{{unknown}}"));
-        
-        // Cleanup
-        let _ = std::fs::remove_file(&temp_file);
-    }
-}

crates/g3-cli/src/simple_output.rs

@@ -1,40 +1,27 @@
-use crate::g3_status::{G3Status, Status};
-
 /// Simple output helper for printing messages
-#[derive(Clone)]
-pub struct SimpleOutput;
+pub struct SimpleOutput {
+    machine_mode: bool,
+}
 
 impl SimpleOutput {
     pub fn new() -> Self {
-        SimpleOutput
+        SimpleOutput { machine_mode: false }
+    }
+
+    pub fn new_with_mode(machine_mode: bool) -> Self {
+        SimpleOutput { machine_mode }
     }
 
     pub fn print(&self, message: &str) {
+        if !self.machine_mode {
             println!("{}", message);
         }
-
-    pub fn print_inline(&self, message: &str) {
-        use std::io::{Write, stdout};
-        print!("{}", message);
-        let _ = stdout().flush();
     }
 
     pub fn print_smart(&self, message: &str) {
+        if !self.machine_mode {
             println!("{}", message);
         }
-
-    /// Print a g3 status message with colored tag and status
-    /// Format: "g3: <message> ... [status]"
-    /// Uses centralized G3Status formatting.
-    pub fn print_g3_status(&self, message: &str, status: &str) {
-        G3Status::complete(message, Status::parse(status));
-    }
-
-    /// Print a g3 status message in progress (no status yet)
-    /// Format: "g3: <message> ..."
-    /// Uses centralized G3Status formatting.
-    pub fn print_g3_progress(&self, message: &str) {
-        G3Status::progress_ln(message);
     }
 }
 

crates/g3-cli/src/task_execution.rs

@@ -1,147 +0,0 @@
-//! Task execution with retry logic for G3 CLI.
-
-use g3_core::error_handling::{calculate_retry_delay, classify_error, ErrorType, RecoverableError};
-use g3_core::ui_writer::UiWriter;
-use g3_core::Agent;
-use tokio_util::sync::CancellationToken;
-use tracing::{debug, error};
-
-use crate::simple_output::SimpleOutput;
-use crate::g3_status::G3Status;
-
-/// Maximum number of retry attempts for recoverable errors
-const MAX_RETRIES: u32 = 3;
-
-/// Get a human-readable name for a recoverable error type.
-fn recoverable_error_name(err: &RecoverableError) -> &'static str {
-    match err {
-        RecoverableError::RateLimit => "rate limited",
-        RecoverableError::ServerError => "server error",
-        RecoverableError::NetworkError => "network error",
-        RecoverableError::Timeout => "timeout",
-        RecoverableError::ModelBusy => "model overloaded",
-        RecoverableError::TokenLimit => "token limit",
-        RecoverableError::ContextLengthExceeded => "context length exceeded",
-    }
-}
-
-/// Execute a task with retry logic for recoverable errors.
-pub async fn execute_task_with_retry<W: UiWriter>(
-    agent: &mut Agent<W>,
-    input: &str,
-    show_prompt: bool,
-    show_code: bool,
-    output: &SimpleOutput,
-) {
-    let mut attempt = 0;
-
-    output.print("🤔 Thinking...");
-
-    // Create cancellation token for this request
-    let cancellation_token = CancellationToken::new();
-    let cancel_token_clone = cancellation_token.clone();
-
-    loop {
-        attempt += 1;
-
-        // Execute task with cancellation support
-        let execution_result = tokio::select! {
-            result = agent.execute_task_with_timing_cancellable(
-                input, None, false, show_prompt, show_code, true, cancellation_token.clone(), None
-            ) => {
-                result
-            }
-            _ = tokio::signal::ctrl_c() => {
-                cancel_token_clone.cancel();
-                output.print("\n⚠️  Operation cancelled by user (Ctrl+C)");
-                return;
-            }
-        };
-
-        match execution_result {
-            Ok(_) => {
-                if attempt > 1 {
-                    output.print(&format!("✅ Request succeeded after {} attempts", attempt));
-                }
-                // Response was already displayed during streaming - don't print again
-                return;
-            }
-            Err(e) => {
-                if e.to_string().contains("cancelled") {
-                    output.print("⚠️  Operation cancelled by user");
-                    return;
-                }
-
-                // Check if this is a recoverable error that we should retry
-                let error_type = classify_error(&e);
-
-                if let ErrorType::Recoverable(recoverable_error) = error_type {
-                    if attempt < MAX_RETRIES {
-                        // Use shared retry delay calculation (non-autonomous mode)
-                        let delay = calculate_retry_delay(attempt, false);
-                        let delay_secs = delay.as_secs_f64();
-
-                        // Print error status
-                        G3Status::complete(
-                            recoverable_error_name(&recoverable_error),
-                            crate::g3_status::Status::Error(String::new()),
-                        );
-
-                        // Print retry message (no newline, will show [done] after sleep)
-                        G3Status::progress(&format!("retrying in {:.1}s ({}/{})", delay_secs, attempt, MAX_RETRIES));
-
-                        // Wait before retrying
-                        tokio::time::sleep(delay).await;
-                        G3Status::done();
-                        continue;
-                    }
-                }
-
-                // For non-recoverable errors or after max retries
-                handle_execution_error(&e, input, output, attempt);
-                return;
-            }
-        }
-    }
-}
-
-/// Handle execution errors with detailed logging and user-friendly output.
-pub fn handle_execution_error(e: &anyhow::Error, input: &str, _output: &SimpleOutput, attempt: u32) {
-    // Check if this is a recoverable error type (for logging level decision)
-    let error_type = classify_error(e);
-    let is_recoverable = matches!(error_type, ErrorType::Recoverable(_));
-
-    // Use debug level for recoverable errors (they're expected), error level for others
-    if is_recoverable {
-        debug!("Task execution failed (recoverable): {}", e);
-        if attempt > 1 {
-            debug!("Failed after {} attempts", attempt);
-        }
-    } else {
-        error!("=== TASK EXECUTION ERROR ===");
-        error!("Error: {}", e);
-        if attempt > 1 {
-            error!("Failed after {} attempts", attempt);
-        }
-
-        // Log error chain only for non-recoverable errors
-        let mut source = e.source();
-        let mut depth = 1;
-        while let Some(err) = source {
-            error!("  Caused by [{}]: {}", depth, err);
-            source = err.source();
-            depth += 1;
-        }
-
-        error!("Task input: {}", input);
-        error!("Error type: {}", std::any::type_name_of_val(&e));
-    }
-
-    // Display user-friendly error message using G3Status
-    if let ErrorType::Recoverable(ref recoverable_error) = error_type {
-        let error_name = recoverable_error_name(recoverable_error);
-        G3Status::complete(error_name, crate::g3_status::Status::Failed);
-    } else {
-        G3Status::complete(&format!("error: {}", e), crate::g3_status::Status::Failed);
-    }
-}

crates/g3-cli/src/template.rs

@@ -1,142 +0,0 @@
-//! Template variable injection for included prompt files.
-//!
-//! Supports `{{var}}` syntax for variable substitution.
-//! Currently supported variables:
-//! - `today`: Current date in ISO format (YYYY-MM-DD)
-
-use chrono::Local;
-use regex::Regex;
-use std::collections::HashSet;
-
-/// Process template variables in the given content.
-/// 
-/// Replaces `{{var}}` patterns with their values.
-/// Warns about unknown variables and leaves them unchanged.
-pub fn process_template(content: &str) -> String {
-    // Regex to match {{variable_name}}
-    let re = Regex::new(r"\{\{([a-zA-Z_][a-zA-Z0-9_]*)\}\}").unwrap();
-    
-    // Track unknown variables to warn only once per variable
-    let mut unknown_vars: HashSet<String> = HashSet::new();
-    
-    let result = re.replace_all(content, |caps: &regex::Captures| {
-        let var_name = &caps[1];
-        match resolve_variable(var_name) {
-            Some(value) => value,
-            None => {
-                if unknown_vars.insert(var_name.to_string()) {
-                    tracing::warn!("Unknown template variable: {{{{{}}}}}", var_name);
-                }
-                // Leave unknown variables unchanged
-                caps[0].to_string()
-            }
-        }
-    });
-    
-    result.into_owned()
-}
-
-/// Resolve a template variable to its value.
-fn resolve_variable(name: &str) -> Option<String> {
-    match name {
-        "today" => Some(Local::now().format("%Y-%m-%d (%A)").to_string()),
-        _ => None,
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_today_variable() {
-        let input = "Today is {{today}}";
-        let result = process_template(input);
-        
-        // Should contain a date in YYYY-MM-DD format
-        assert!(!result.contains("{{today}}"));
-        assert!(result.starts_with("Today is "));
-        
-        // Verify date format (YYYY-MM-DD (DayName))
-        let date_part = &result["Today is ".len()..];
-        // Should be at least "YYYY-MM-DD (X)" = 13+ chars
-        assert!(date_part.len() >= 13, "Date should be at least 13 chars, got: {}", date_part);
-        assert_eq!(&date_part[4..5], "-", "Should have dash at position 4");
-        assert_eq!(&date_part[7..8], "-", "Should have dash at position 7");
-        assert!(date_part.contains("(") && date_part.contains(")"), "Should contain day name in parens");
-    }
-
-    #[test]
-    fn test_multiple_today_variables() {
-        let input = "Start: {{today}}, End: {{today}}";
-        let result = process_template(input);
-        
-        // Both should be replaced
-        assert!(!result.contains("{{today}}"));
-        assert!(result.contains("Start: "));
-        assert!(result.contains(", End: "));
-    }
-
-    #[test]
-    fn test_unknown_variable_unchanged() {
-        let input = "Hello {{unknown_var}}!";
-        let result = process_template(input);
-        
-        // Unknown variable should remain unchanged
-        assert_eq!(result, "Hello {{unknown_var}}!");
-    }
-
-    #[test]
-    fn test_mixed_known_and_unknown() {
-        let input = "Date: {{today}}, Name: {{name}}";
-        let result = process_template(input);
-        
-        // today should be replaced, name should remain
-        assert!(!result.contains("{{today}}"));
-        assert!(result.contains("{{name}}"));
-    }
-
-    #[test]
-    fn test_no_variables() {
-        let input = "No variables here";
-        let result = process_template(input);
-        
-        assert_eq!(result, "No variables here");
-    }
-
-    #[test]
-    fn test_empty_braces() {
-        let input = "Empty {{}} braces";
-        let result = process_template(input);
-        
-        // Empty braces don't match the pattern, should remain unchanged
-        assert_eq!(result, "Empty {{}} braces");
-    }
-
-    #[test]
-    fn test_single_braces_ignored() {
-        let input = "Single {today} braces";
-        let result = process_template(input);
-        
-        // Single braces should not be processed
-        assert_eq!(result, "Single {today} braces");
-    }
-
-    #[test]
-    fn test_variable_with_underscores() {
-        let input = "{{my_custom_var}}";
-        let result = process_template(input);
-        
-        // Unknown but valid variable name, should remain unchanged
-        assert_eq!(result, "{{my_custom_var}}");
-    }
-
-    #[test]
-    fn test_variable_with_numbers() {
-        let input = "{{var123}}";
-        let result = process_template(input);
-        
-        // Unknown but valid variable name, should remain unchanged
-        assert_eq!(result, "{{var123}}");
-    }
-}

crates/g3-cli/src/terminal_width.rs

@@ -1,213 +0,0 @@
-//! Terminal width utilities for responsive output formatting.
-//!
-//! Provides functions to get terminal width and clip/compress content
-//! to fit within the available space without wrapping.
-
-use crossterm::terminal;
-
-/// Right margin to leave for visual clarity and elegance.
-const RIGHT_MARGIN: usize = 4;
-
-/// Minimum usable terminal width (below this, we don't compress further).
-const MIN_WIDTH: usize = 40;
-
-/// Default terminal width when size cannot be determined.
-const DEFAULT_WIDTH: usize = 80;
-
-/// Get the usable terminal width (total width minus right margin).
-/// 
-/// Returns the terminal width minus a 4-character right margin for clarity.
-/// Falls back to 80 columns (76 usable) if terminal size cannot be determined.
-/// Enforces a minimum usable width of 40 characters.
-pub fn get_terminal_width() -> usize {
-    let width = terminal::size()
-        .map(|(w, _)| w as usize)
-        .unwrap_or(DEFAULT_WIDTH);
-    
-    // Subtract margin, but ensure minimum usable width
-    width.saturating_sub(RIGHT_MARGIN).max(MIN_WIDTH)
-}
-
-/// Clip a line to fit within the given width, adding ellipsis if truncated.
-/// 
-/// Uses UTF-8 safe character counting to avoid panics on multi-byte characters.
-pub fn clip_line(line: &str, max_width: usize) -> String {
-    let char_count = line.chars().count();
-    
-    if char_count <= max_width {
-        return line.to_string();
-    }
-    
-    // Need to truncate: leave room for "…" (1 char)
-    let truncate_at = max_width.saturating_sub(1);
-    let truncated: String = line.chars().take(truncate_at).collect();
-    format!("{}…", truncated)
-}
-
-/// Compress a file path to fit within the given width.
-/// 
-/// Preserves the filename and as much of the path as possible.
-/// Truncates parent directories from the left, replacing with "…".
-/// 
-/// Examples:
-/// - Full: `/Users/dhanji/src/g3/crates/g3-cli/src/ui_writer_impl.rs`
-/// - Compressed: `…g3-cli/src/ui_writer_impl.rs`
-/// - More compressed: `…/ui_writer_impl.rs`
-pub fn compress_path(path: &str, max_width: usize) -> String {
-    let char_count = path.chars().count();
-    
-    if char_count <= max_width {
-        return path.to_string();
-    }
-    
-    // Extract filename (last component)
-    let filename = path.rsplit('/').next().unwrap_or(path);
-    let filename_len = filename.chars().count();
-    
-    // If filename alone is too long, truncate it
-    if filename_len + 1 >= max_width {
-        // Just show truncated filename with ellipsis
-        return clip_line(filename, max_width);
-    }
-    
-    // Try to fit as much of the path as possible
-    // Format: "…<partial_path>/<filename>"
-    let available_for_path = max_width.saturating_sub(filename_len + 2); // 1 for "…", 1 for "/"
-    
-    if available_for_path == 0 {
-        return format!("…/{}", filename);
-    }
-    
-    // Get the directory part (everything before filename)
-    let dir_part = if let Some(pos) = path.rfind('/') {
-        &path[..pos]
-    } else {
-        return path.to_string(); // No directory separator
-    };
-    
-    // Take characters from the end of the directory path
-    let dir_chars: Vec<char> = dir_part.chars().collect();
-    let dir_len = dir_chars.len();
-    
-    if dir_len <= available_for_path {
-        return path.to_string(); // Shouldn't happen, but safety check
-    }
-    
-    // Take the last `available_for_path` characters from the directory
-    let start_idx = dir_len.saturating_sub(available_for_path);
-    let partial_dir: String = dir_chars[start_idx..].iter().collect();
-    
-    format!("…{}/{}", partial_dir, filename)
-}
-
-/// Compress a shell command to fit within the given width.
-/// 
-/// Preserves the command name and as much of the arguments as possible.
-/// Truncates from the right, adding "…" at the end.
-pub fn compress_command(command: &str, max_width: usize) -> String {
-    clip_line(command, max_width)
-}
-
-/// Calculate available width for content after accounting for a prefix.
-/// 
-/// This is useful for tool output lines that have a fixed prefix like "│ ".
-#[allow(dead_code)] // Utility function for future use
-pub fn available_width_after_prefix(prefix_width: usize) -> usize {
-    get_terminal_width().saturating_sub(prefix_width)
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_clip_line_short() {
-        let line = "hello world";
-        assert_eq!(clip_line(line, 80), "hello world");
-    }
-
-    #[test]
-    fn test_clip_line_exact() {
-        let line = "hello";
-        assert_eq!(clip_line(line, 5), "hello");
-    }
-
-    #[test]
-    fn test_clip_line_truncate() {
-        let line = "hello world this is a long line";
-        assert_eq!(clip_line(line, 15), "hello world th…");
-    }
-
-    #[test]
-    fn test_clip_line_unicode() {
-        let line = "héllo wörld 你好";
-        let clipped = clip_line(line, 10);
-        assert_eq!(clipped.chars().count(), 10);
-        assert!(clipped.ends_with('…'));
-    }
-
-    #[test]
-    fn test_clip_line_empty() {
-        assert_eq!(clip_line("", 80), "");
-    }
-
-    #[test]
-    fn test_compress_path_short() {
-        let path = "src/main.rs";
-        assert_eq!(compress_path(path, 80), "src/main.rs");
-    }
-
-    #[test]
-    fn test_compress_path_long() {
-        let path = "/Users/dhanji/src/g3/crates/g3-cli/src/ui_writer_impl.rs";
-        let compressed = compress_path(path, 40);
-        assert!(compressed.chars().count() <= 40);
-        assert!(compressed.ends_with("ui_writer_impl.rs"));
-        assert!(compressed.starts_with('…'));
-    }
-
-    #[test]
-    fn test_compress_path_preserves_filename() {
-        let path = "/very/long/path/to/some/deeply/nested/file.rs";
-        let compressed = compress_path(path, 20);
-        assert!(compressed.contains("file.rs"));
-    }
-
-    #[test]
-    fn test_compress_path_very_narrow() {
-        let path = "/path/to/extremely_long_filename_that_exceeds_width.rs";
-        let compressed = compress_path(path, 15);
-        assert!(compressed.chars().count() <= 15);
-        assert!(compressed.ends_with('…'));
-    }
-
-    #[test]
-    fn test_compress_command_short() {
-        let cmd = "ls -la";
-        assert_eq!(compress_command(cmd, 80), "ls -la");
-    }
-
-    #[test]
-    fn test_compress_command_long() {
-        let cmd = "rg 'pattern' --type rust -l | head -20 | sort";
-        let compressed = compress_command(cmd, 30);
-        assert!(compressed.chars().count() <= 30);
-        assert!(compressed.starts_with("rg 'pattern'"));
-        assert!(compressed.ends_with('…'));
-    }
-
-    #[test]
-    fn test_get_terminal_width_returns_reasonable_value() {
-        let width = get_terminal_width();
-        // Should be at least MIN_WIDTH
-        assert!(width >= MIN_WIDTH);
-        // Should be reasonable (not absurdly large)
-        assert!(width < 1000);
-    }
-
-    #[test]
-    fn test_available_width_after_prefix() {
-        let width = available_width_after_prefix(3); // e.g., "│ "
-        assert!(width >= MIN_WIDTH.saturating_sub(3));
-    }
-}

crates/g3-cli/src/theme.rs

@@ -4,11 +4,7 @@ use std::fs;
 use std::path::Path;
 use anyhow::Result;
 
-/// Color theme configuration for the TUI.
-/// 
-/// Note: The "retro" theme is the default theme (inspired by Alien terminals).
-/// This is a theme option, not a separate TUI mode. The theme can be selected
-/// via config file or the `from_name()` method ("default" and "retro" are equivalent).
+/// Color theme configuration for the retro TUI
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct ColorTheme {
     /// Name of the theme

crates/g3-cli/src/tui.rs

@@ -0,0 +1,158 @@
+use crossterm::style::Color;
+use crossterm::style::{SetForegroundColor, ResetColor};
+use std::io::{self, Write};
+use termimad::MadSkin;
+
+/// Simple output handler with markdown support
+pub struct SimpleOutput {
+    mad_skin: MadSkin,
+}
+
+impl SimpleOutput {
+    pub fn new() -> Self {
+        let mut mad_skin = MadSkin::default();
+        // Dracula color scheme
+        // Background: #282a36, Foreground: #f8f8f2
+        // Colors: Cyan #8be9fd, Green #50fa7b, Orange #ffb86c, Pink #ff79c6, Purple #bd93f9, Red #ff5555, Yellow #f1fa8c
+        
+        mad_skin.set_headers_fg(Color::Rgb { r: 189, g: 147, b: 249 }); // Purple for headers
+        mad_skin.bold.set_fg(Color::Rgb { r: 255, g: 121, b: 198 });    // Pink for bold
+        mad_skin.italic.set_fg(Color::Rgb { r: 139, g: 233, b: 253 });  // Cyan for italic
+        mad_skin.code_block.set_bg(Color::Rgb { r: 68, g: 71, b: 90 }); // Dracula background variant
+        mad_skin.code_block.set_fg(Color::Rgb { r: 80, g: 250, b: 123 }); // Green for code text
+        mad_skin.inline_code.set_bg(Color::Rgb { r: 68, g: 71, b: 90 }); // Same background for inline code
+        mad_skin.inline_code.set_fg(Color::Rgb { r: 241, g: 250, b: 140 }); // Yellow for inline code
+        mad_skin.quote_mark.set_fg(Color::Rgb { r: 98, g: 114, b: 164 }); // Comment purple for quote marks
+        mad_skin.strikeout.set_fg(Color::Rgb { r: 255, g: 85, b: 85 });  // Red for strikethrough
+        
+        Self { mad_skin }
+    }
+
+    /// Detect if text contains markdown formatting
+    fn has_markdown(&self, text: &str) -> bool {
+        // Check for common markdown patterns
+        text.contains("**") ||
+        text.contains("```") ||
+        text.contains("`") ||
+        text.lines().any(|line| {
+            let trimmed = line.trim();
+            trimmed.starts_with('#') ||
+            trimmed.starts_with("- ") ||
+            trimmed.starts_with("* ") ||
+            trimmed.starts_with("+ ") ||
+            (trimmed.len() > 2 && 
+             trimmed.chars().next().is_some_and(|c| c.is_ascii_digit()) &&
+             trimmed.chars().nth(1) == Some('.') &&
+             trimmed.chars().nth(2) == Some(' ')) ||
+            (trimmed.contains('[') && trimmed.contains("]("))
+        }) ||
+        (text.matches('*').count() >= 2 && !text.contains("/*") && !text.contains("*/"))
+    }
+
+    pub fn print(&self, text: &str) {
+        println!("{}", text);
+    }
+
+    /// Smart print that automatically detects and renders markdown
+    pub fn print_smart(&self, text: &str) {
+        if self.has_markdown(text) {
+            self.print_markdown(text);
+        } else {
+            self.print(text);
+        }
+    }
+
+    pub fn print_markdown(&self, markdown: &str) {
+        self.mad_skin.print_text(markdown);
+    }
+
+    pub fn _print_status(&self, status: &str) {
+        println!("📊 {}", status);
+    }
+
+    pub fn print_context(&self, used: u32, total: u32, percentage: f32) {
+        let bar_width: usize = 10;
+        let filled_width = ((percentage / 100.0) * bar_width as f32) as usize;
+        let empty_width = bar_width.saturating_sub(filled_width);
+
+        let filled_chars = "●".repeat(filled_width);
+        let empty_chars = "○".repeat(empty_width);
+        
+        // Determine color based on percentage
+        let color = if percentage < 60.0 {
+            crossterm::style::Color::Green
+        } else if percentage < 80.0 {
+            crossterm::style::Color::Yellow
+        } else {
+            crossterm::style::Color::Red
+        };
+
+        // Print with colored progress bar
+        print!("Context: ");
+        print!("{}", SetForegroundColor(color));
+        print!("{}{}", filled_chars, empty_chars);
+        print!("{}", ResetColor);
+        println!(" {:.1}% | {}/{} tokens", percentage, used, total);
+    }
+
+    pub fn print_context_thinning(&self, message: &str) {
+        // Animated highlight for context thinning
+        // Use bright cyan/green with a quick flash animation
+        
+        // Flash animation: print with bright background, then normal
+        let frames = vec![
+            "\x1b[1;97;46m",  // Frame 1: Bold white on cyan background
+            "\x1b[1;97;42m",  // Frame 2: Bold white on green background
+            "\x1b[1;96;40m",  // Frame 3: Bold cyan on black background
+        ];
+        
+        println!();
+        
+        // Quick flash animation
+        for frame in &frames {
+            print!("\r{} ✨ {} ✨\x1b[0m", frame, message);
+            let _ = io::stdout().flush();
+            std::thread::sleep(std::time::Duration::from_millis(80));
+        }
+        
+        // Final display with bright cyan and sparkle emojis
+        print!("\r\x1b[1;96m✨ {} ✨\x1b[0m", message);
+        println!();
+        
+        // Add a subtle "success" indicator line
+        println!("\x1b[2;36m   └─ Context optimized successfully\x1b[0m");
+        println!();
+        
+        let _ = io::stdout().flush();
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_markdown_detection() {
+        let output = SimpleOutput::new();
+        
+        // Should detect markdown
+        assert!(output.has_markdown("**bold text**"));
+        assert!(output.has_markdown("`code`"));
+        assert!(output.has_markdown("```\ncode block\n```"));
+        assert!(output.has_markdown("# Header"));
+        assert!(output.has_markdown("- list item"));
+        assert!(output.has_markdown("* list item"));
+        assert!(output.has_markdown("+ list item"));
+        assert!(output.has_markdown("1. numbered item"));
+        assert!(output.has_markdown("[link](url)"));
+        assert!(output.has_markdown("*italic* text"));
+        
+        // Should NOT detect markdown
+        assert!(!output.has_markdown("plain text"));
+        assert!(!output.has_markdown("file.txt"));
+        assert!(!output.has_markdown("/* comment */"));
+        assert!(!output.has_markdown("just one * asterisk"));
+        assert!(!output.has_markdown("📁 Workspace: /path/to/dir"));
+        assert!(!output.has_markdown("✅ Success message"));
+    }
+}

crates/g3-cli/src/utils.rs

@@ -1,181 +0,0 @@
-//! Utility functions for G3 CLI.
-
-use anyhow::Result;
-use crossterm::style::{Color, ResetColor, SetForegroundColor};
-use g3_config::Config;
-use g3_core::ui_writer::UiWriter;
-use g3_core::Agent;
-use std::path::PathBuf;
-
-use crate::cli_args::Cli;
-use crate::simple_output::SimpleOutput;
-
-/// Display context window progress bar.
-pub fn display_context_progress<W: UiWriter>(agent: &Agent<W>, _output: &SimpleOutput) {
-    let context = agent.get_context_window();
-    let percentage = context.percentage_used();
-
-    // Ensure we start on a new line (previous response may not end with newline)
-    println!();
-
-    // Create 10 dots representing context fullness
-    let total_dots: usize = 10;
-    let filled_dots = ((percentage / 100.0) * total_dots as f32).round() as usize;
-    let empty_dots = total_dots.saturating_sub(filled_dots);
-
-    let filled_str = "●".repeat(filled_dots);
-    let empty_str = "○".repeat(empty_dots);
-
-    // Determine color based on percentage
-    let color = if percentage < 40.0 {
-        Color::Green
-    } else if percentage < 60.0 {
-        Color::Yellow
-    } else if percentage < 80.0 {
-        Color::Rgb {
-            r: 255,
-            g: 165,
-            b: 0,
-        } // Orange
-    } else {
-        Color::Red
-    };
-
-    // Format tokens as compact strings (e.g., "38.5k" instead of "38531")
-    let format_tokens = |tokens: u32| -> String {
-        if tokens >= 1_000_000 {
-            format!("{:.1}m", tokens as f64 / 1_000_000.0)
-        } else if tokens >= 1_000 {
-            let k = tokens as f64 / 1000.0;
-            if k >= 100.0 {
-                format!("{:.0}k", k)
-            } else {
-                format!("{:.1}k", k)
-            }
-        } else {
-            format!("{}", tokens)
-        }
-    };
-
-    // Print with colored dots (using print! directly to handle color codes)
-    print!(
-        "{}{}{}{} {}/{} ◉ | {:.0}%\n",
-        SetForegroundColor(color),
-        filled_str,
-        empty_str,
-        ResetColor,
-        format_tokens(context.used_tokens),
-        format_tokens(context.total_tokens),
-        percentage
-    );
-}
-
-/// Set up the workspace directory for autonomous mode.
-/// Uses G3_WORKSPACE environment variable or defaults to ~/tmp/workspace.
-pub fn setup_workspace_directory() -> Result<PathBuf> {
-    let workspace_dir = if let Ok(env_workspace) = std::env::var("G3_WORKSPACE") {
-        PathBuf::from(env_workspace)
-    } else {
-        // Default to ~/tmp/workspace
-        let home_dir = dirs::home_dir()
-            .ok_or_else(|| anyhow::anyhow!("Could not determine home directory"))?;
-        home_dir.join("tmp").join("workspace")
-    };
-
-    // Create the directory if it doesn't exist
-    if !workspace_dir.exists() {
-        std::fs::create_dir_all(&workspace_dir)?;
-        let output = SimpleOutput::new();
-        output.print(&format!(
-            "📁 Created workspace directory: {}",
-            workspace_dir.display()
-        ));
-    }
-
-    Ok(workspace_dir)
-}
-
-/// Load configuration with CLI argument overrides applied.
-///
-/// This is the canonical function for loading config with CLI overrides.
-/// All CLI entry points should use this to ensure consistent behavior.
-pub fn load_config_with_cli_overrides(cli: &Cli) -> Result<Config> {
-    let mut config = Config::load_with_overrides(
-        cli.config.as_deref(),
-        cli.provider.clone(),
-        cli.model.clone(),
-    )?;
-
-    // Apply webdriver flag override
-    if cli.webdriver {
-        config.webdriver.enabled = true;
-    }
-
-    // Apply chrome-headless flag override
-    // Only apply chrome-headless if safari is not explicitly set
-    if cli.chrome_headless && !cli.safari {
-        config.webdriver.enabled = true;
-        config.webdriver.browser = g3_config::WebDriverBrowser::ChromeHeadless;
-
-        // Run Chrome diagnostics - only show output if there are issues
-        let report =
-            g3_computer_control::run_chrome_diagnostics(config.webdriver.chrome_binary.as_deref());
-        if !report.all_ok() {
-            println!("{}", report.format_report());
-        }
-    }
-
-    // Apply safari flag override
-    if cli.safari {
-        config.webdriver.enabled = true;
-        config.webdriver.browser = g3_config::WebDriverBrowser::Safari;
-    }
-
-    // Apply no-auto-compact flag override
-    if cli.manual_compact {
-        config.agent.auto_compact = false;
-    }
-
-    // Validate provider if specified
-    if let Some(ref provider) = cli.provider {
-        let valid_providers = ["anthropic", "databricks", "embedded", "gemini", "openai"];
-        let provider_type = provider.split('.').next().unwrap_or(provider);
-        if !valid_providers.contains(&provider_type) {
-            return Err(anyhow::anyhow!(
-                "Invalid provider '{}'. Provider type must be one of: {:?}",
-                provider,
-                valid_providers
-            ));
-        }
-    }
-
-    Ok(config)
-}
-
-/// Initialize logging based on CLI verbosity settings.
-pub fn initialize_logging(verbose: bool) {
-    use tracing_subscriber::{layer::SubscriberExt, util::SubscriberInitExt, EnvFilter};
-
-    let filter = if verbose {
-        EnvFilter::from_default_env()
-            .add_directive(format!("{}=debug", env!("CARGO_PKG_NAME")).parse().unwrap())
-            .add_directive("g3_core=debug".parse().unwrap())
-            .add_directive("g3_cli=debug".parse().unwrap())
-            .add_directive("g3_execution=debug".parse().unwrap())
-            .add_directive("g3_providers=debug".parse().unwrap())
-    } else {
-        EnvFilter::from_default_env()
-            .add_directive(format!("{}=info", env!("CARGO_PKG_NAME")).parse().unwrap())
-            .add_directive("g3_core=info".parse().unwrap())
-            .add_directive("g3_cli=info".parse().unwrap())
-            .add_directive("g3_execution=info".parse().unwrap())
-            .add_directive("g3_providers=info".parse().unwrap())
-            .add_directive("llama_cpp=off".parse().unwrap())
-            .add_directive("llama=off".parse().unwrap())
-    };
-
-    let _ = tracing_subscriber::registry()
-        .with(tracing_subscriber::fmt::layer())
-        .with(filter)
-        .try_init();
-}

crates/g3-cli/tests/cli_integration_test.rs

@@ -1,337 +0,0 @@
-//! CLI Integration Tests (Blackbox)
-//!
-//! CHARACTERIZATION: These tests verify the CLI's external behavior through
-//! its public interface (command-line arguments and exit codes).
-//!
-//! What these tests protect:
-//! - CLI argument parsing works correctly
-//! - Help and version output are available
-//! - Invalid arguments produce appropriate errors
-//! - Workspace directory handling works
-//!
-//! What these tests intentionally do NOT assert:
-//! - Internal implementation details
-//! - Specific error message wording (only that errors occur)
-//! - Provider-specific behavior (requires API keys)
-
-use std::process::Command;
-
-/// Get the path to the g3 binary.
-/// In test mode, this will be in the target/debug directory.
-fn get_g3_binary() -> String {
-    // When running tests, the binary is in target/debug/
-    let mut path = std::env::current_exe().unwrap();
-    path.pop(); // Remove test binary name
-    path.pop(); // Remove deps
-    path.push("g3");
-    path.to_string_lossy().to_string()
-}
-
-// =============================================================================
-// Test: --help flag produces help output
-// =============================================================================
-
-#[test]
-fn test_help_flag_produces_output() {
-    let output = Command::new(get_g3_binary())
-        .arg("--help")
-        .output()
-        .expect("Failed to execute g3 --help");
-
-    // Help should succeed
-    assert!(
-        output.status.success(),
-        "g3 --help should exit successfully"
-    );
-
-    let stdout = String::from_utf8_lossy(&output.stdout);
-
-    // Should contain key elements of help output
-    assert!(
-        stdout.contains("Usage:"),
-        "Help output should contain 'Usage:'"
-    );
-    assert!(
-        stdout.contains("Options:"),
-        "Help output should contain 'Options:'"
-    );
-    assert!(
-        stdout.contains("--help"),
-        "Help output should mention --help flag"
-    );
-    assert!(
-        stdout.contains("--version"),
-        "Help output should mention --version flag"
-    );
-}
-
-#[test]
-fn test_short_help_flag() {
-    let output = Command::new(get_g3_binary())
-        .arg("-h")
-        .output()
-        .expect("Failed to execute g3 -h");
-
-    assert!(output.status.success(), "g3 -h should exit successfully");
-
-    let stdout = String::from_utf8_lossy(&output.stdout);
-    assert!(
-        stdout.contains("Usage:"),
-        "Short help should also show usage"
-    );
-}
-
-// =============================================================================
-// Test: --version flag produces version output
-// =============================================================================
-
-#[test]
-fn test_version_flag_produces_output() {
-    let output = Command::new(get_g3_binary())
-        .arg("--version")
-        .output()
-        .expect("Failed to execute g3 --version");
-
-    assert!(
-        output.status.success(),
-        "g3 --version should exit successfully"
-    );
-
-    let stdout = String::from_utf8_lossy(&output.stdout);
-
-    // Should contain version number pattern (e.g., "g3 0.1.0")
-    assert!(
-        stdout.contains("g3") || stdout.contains("0."),
-        "Version output should contain program name or version number"
-    );
-}
-
-#[test]
-fn test_short_version_flag() {
-    let output = Command::new(get_g3_binary())
-        .arg("-V")
-        .output()
-        .expect("Failed to execute g3 -V");
-
-    assert!(output.status.success(), "g3 -V should exit successfully");
-}
-
-// =============================================================================
-// Test: Invalid arguments produce errors
-// =============================================================================
-
-#[test]
-fn test_invalid_flag_produces_error() {
-    let output = Command::new(get_g3_binary())
-        .arg("--this-flag-does-not-exist")
-        .output()
-        .expect("Failed to execute g3 with invalid flag");
-
-    // Should fail with non-zero exit code
-    assert!(
-        !output.status.success(),
-        "Invalid flag should cause non-zero exit"
-    );
-
-    let stderr = String::from_utf8_lossy(&output.stderr);
-    // Should have some error message
-    assert!(
-        !stderr.is_empty() || !output.stdout.is_empty(),
-        "Should produce some output on invalid flag"
-    );
-}
-
-// =============================================================================
-// Test: Conflicting mode flags
-// =============================================================================
-
-#[test]
-fn test_agent_conflicts_with_autonomous() {
-    // --agent conflicts with --autonomous
-    let output = Command::new(get_g3_binary())
-        .args(["--agent", "test", "--autonomous"])
-        .output()
-        .expect("Failed to execute g3 with conflicting flags");
-
-    // Should fail due to conflicting arguments
-    assert!(
-        !output.status.success(),
-        "--agent and --autonomous should conflict"
-    );
-}
-
-#[test]
-fn test_planning_conflicts_with_autonomous() {
-    let output = Command::new(get_g3_binary())
-        .args(["--planning", "--autonomous"])
-        .output()
-        .expect("Failed to execute g3 with conflicting flags");
-
-    assert!(
-        !output.status.success(),
-        "--planning and --autonomous should conflict"
-    );
-}
-
-// =============================================================================
-// Test: Workspace directory option is accepted
-// =============================================================================
-
-#[test]
-fn test_workspace_option_accepted() {
-    // Just verify the option is recognized (don't actually run the agent)
-    let output = Command::new(get_g3_binary())
-        .args(["--workspace", "/tmp", "--help"])
-        .output()
-        .expect("Failed to execute g3 with workspace option");
-
-    // --help should still work even with other options
-    assert!(
-        output.status.success(),
-        "--workspace option should be recognized"
-    );
-}
-
-// =============================================================================
-// Test: Config file option is accepted
-// =============================================================================
-
-#[test]
-fn test_config_option_accepted() {
-    let output = Command::new(get_g3_binary())
-        .args(["--config", "/nonexistent/config.toml", "--help"])
-        .output()
-        .expect("Failed to execute g3 with config option");
-
-    // --help should still work
-    assert!(
-        output.status.success(),
-        "--config option should be recognized"
-    );
-}
-
-// =============================================================================
-// Test: Provider override option is accepted
-// =============================================================================
-
-#[test]
-fn test_provider_option_accepted() {
-    let output = Command::new(get_g3_binary())
-        .args(["--provider", "anthropic", "--help"])
-        .output()
-        .expect("Failed to execute g3 with provider option");
-
-    assert!(
-        output.status.success(),
-        "--provider option should be recognized"
-    );
-}
-
-// =============================================================================
-// Test: Quiet mode option is accepted
-// =============================================================================
-
-#[test]
-fn test_quiet_option_accepted() {
-    let output = Command::new(get_g3_binary())
-        .args(["--quiet", "--help"])
-        .output()
-        .expect("Failed to execute g3 with quiet option");
-
-    assert!(
-        output.status.success(),
-        "--quiet option should be recognized"
-    );
-}
-
-// =============================================================================
-// Test: Include prompt option is accepted
-// =============================================================================
-
-#[test]
-fn test_include_prompt_option_accepted() {
-    let output = Command::new(get_g3_binary())
-        .args(["--include-prompt", "/tmp/prompt.md", "--help"])
-        .output()
-        .expect("Failed to execute g3 with include-prompt option");
-
-    assert!(
-        output.status.success(),
-        "--include-prompt option should be recognized"
-    );
-}
-
-#[test]
-fn test_include_prompt_in_help_output() {
-    let output = Command::new(get_g3_binary())
-        .arg("--help")
-        .output()
-        .expect("Failed to execute g3 --help");
-
-    let stdout = String::from_utf8_lossy(&output.stdout);
-    assert!(
-        stdout.contains("--include-prompt"),
-        "Help output should mention --include-prompt flag"
-    );
-}
-
-// =============================================================================
-// Test: No auto-memory option is accepted
-// =============================================================================
-
-#[test]
-fn test_no_auto_memory_option_accepted() {
-    let output = Command::new(get_g3_binary())
-        .args(["--no-auto-memory", "--help"])
-        .output()
-        .expect("Failed to execute g3 with no-auto-memory option");
-
-    assert!(
-        output.status.success(),
-        "--no-auto-memory option should be recognized"
-    );
-}
-
-#[test]
-fn test_no_auto_memory_in_help_output() {
-    let output = Command::new(get_g3_binary())
-        .arg("--help")
-        .output()
-        .expect("Failed to execute g3 --help");
-
-    let stdout = String::from_utf8_lossy(&output.stdout);
-    assert!(
-        stdout.contains("--no-auto-memory"),
-        "Help output should mention --no-auto-memory flag"
-    );
-}
-
-// =============================================================================
-// Test: Project option is accepted (including with agent mode)
-// =============================================================================
-
-#[test]
-fn test_project_option_accepted() {
-    let output = Command::new(get_g3_binary())
-        .args(["--project", "/tmp/myproject", "--help"])
-        .output()
-        .expect("Failed to execute g3 with project option");
-
-    assert!(
-        output.status.success(),
-        "--project option should be recognized"
-    );
-}
-
-#[test]
-fn test_project_option_with_agent_mode_accepted() {
-    let output = Command::new(get_g3_binary())
-        .args(["--agent", "butler", "--chat", "--project", "/tmp/myproject", "--help"])
-        .output()
-        .expect("Failed to execute g3 with agent and project options");
-
-    assert!(
-        output.status.success(),
-        "--project option should work with --agent --chat"
-    );
-}

crates/g3-cli/tests/coach_feedback_extraction_test.rs

@@ -1,344 +0,0 @@
-use serde_json::json;
-use std::fs;
-use tempfile::TempDir;
-
-#[test]
-fn test_extract_coach_feedback_with_timing_message() {
-    // Create a temporary directory for session logs
-    let temp_dir = TempDir::new().unwrap();
-    let sessions_dir = temp_dir.path().join(".g3").join("sessions");
-    fs::create_dir_all(&sessions_dir).unwrap();
-
-    // Create a mock session log with the problematic conversation history
-    // where timing message appears after the tool result
-    let session_id = "test_session_123";
-    let session_dir = sessions_dir.join(session_id);
-    fs::create_dir_all(&session_dir).unwrap();
-    let log_file_path = session_dir.join("session.json");
-
-    let log_content = json!({
-        "session_id": session_id,
-        "context_window": {
-            "conversation_history": [
-                {
-                    "role": "assistant",
-                    "content": "{\"tool\": \"final_output\", \"args\": {\"summary\":\"IMPLEMENTATION_APPROVED\"}}"
-                },
-                {
-                    "role": "user",
-                    "content": "Tool result: IMPLEMENTATION_APPROVED"
-                },
-                {
-                    "role": "assistant",
-                    "content": "🕝 27.7s | 💭 7.5s"
-                }
-            ]
-        }
-    });
-
-    fs::write(&log_file_path, serde_json::to_string_pretty(&log_content).unwrap()).unwrap();
-
-    // Now test the extraction logic
-    let log_content_str = fs::read_to_string(&log_file_path).unwrap();
-    let log_json: serde_json::Value = serde_json::from_str(&log_content_str).unwrap();
-
-    if let Some(context_window) = log_json.get("context_window") {
-        if let Some(conversation_history) = context_window.get("conversation_history") {
-            if let Some(messages) = conversation_history.as_array() {
-                // This is the key logic we're testing - find the last USER message with "Tool result:"
-                let last_tool_result = messages.iter().rev().find(|msg| {
-                    if let Some(role) = msg.get("role") {
-                        if let Some(role_str) = role.as_str() {
-                            if role_str == "User" || role_str == "user" {
-                                if let Some(content) = msg.get("content") {
-                                    if let Some(content_str) = content.as_str() {
-                                        return content_str.starts_with("Tool result:");
-                                    }
-                                }
-                            }
-                        }
-                    }
-                    false
-                });
-
-                // Verify we found the correct message
-                assert!(last_tool_result.is_some(), "Should find the tool result message");
-
-                if let Some(last_message) = last_tool_result {
-                    if let Some(content) = last_message.get("content") {
-                        if let Some(content_str) = content.as_str() {
-                            let feedback = if content_str.starts_with("Tool result: ") {
-                                content_str.strip_prefix("Tool result: ").unwrap_or(content_str)
-                            } else {
-                                content_str
-                            };
-
-                            // Verify we extracted the correct feedback
-                            assert_eq!(feedback, "IMPLEMENTATION_APPROVED", "Should extract the actual feedback, not timing");
-                            
-                            // Verify the feedback is NOT the timing message
-                            assert!(!feedback.contains("🕝"), "Feedback should not be the timing message");
-                            
-                            println!("✅ Successfully extracted coach feedback: {}", feedback);
-                            return;
-                        }
-                    }
-                }
-            }
-        }
-    }
-
-    panic!("Failed to extract coach feedback");
-}
-
-#[test]
-fn test_extract_only_final_output_tool_results() {
-    // Test that we only extract tool results from final_output, not from other tools
-    let temp_dir = TempDir::new().unwrap();
-    let sessions_dir = temp_dir.path().join(".g3").join("sessions");
-    fs::create_dir_all(&sessions_dir).unwrap();
-
-    let session_id = "test_session_final_output_only";
-    let session_dir = sessions_dir.join(session_id);
-    fs::create_dir_all(&session_dir).unwrap();
-    let log_file_path = session_dir.join("session.json");
-
-    let log_content = json!({
-        "session_id": session_id,
-        "context_window": {
-            "conversation_history": [
-                {
-                    "role": "assistant",
-                    "content": "{\"tool\": \"shell\", \"args\": {\"command\":\"ls\"}}"
-                },
-                {
-                    "role": "user",
-                    "content": "Tool result: file1.txt\nfile2.txt"
-                },
-                {
-                    "role": "assistant",
-                    "content": "{\"tool\": \"read_file\", \"args\": {\"file_path\":\"test.txt\"}}"
-                },
-                {
-                    "role": "user",
-                    "content": "Tool result: This is test content"
-                },
-                {
-                    "role": "assistant",
-                    "content": "{\"tool\": \"final_output\", \"args\": {\"summary\":\"APPROVED_RESULT\"}}"
-                },
-                {
-                    "role": "user",
-                    "content": "Tool result: APPROVED_RESULT"
-                },
-                {
-                    "role": "assistant",
-                    "content": "🕝 20.5s | 💭 5.2s"
-                }
-            ]
-        }
-    });
-
-    fs::write(&log_file_path, serde_json::to_string_pretty(&log_content).unwrap()).unwrap();
-
-    // Test the new extraction logic that verifies the tool is final_output
-    let log_content_str = fs::read_to_string(&log_file_path).unwrap();
-    let log_json: serde_json::Value = serde_json::from_str(&log_content_str).unwrap();
-
-    if let Some(context_window) = log_json.get("context_window") {
-        if let Some(conversation_history) = context_window.get("conversation_history") {
-            if let Some(messages) = conversation_history.as_array() {
-                // Go backwards through messages to find final_output tool result
-                for i in (0..messages.len()).rev() {
-                    let msg = &messages[i];
-                    
-                    if let Some(role) = msg.get("role") {
-                        if let Some(role_str) = role.as_str() {
-                            if role_str == "User" || role_str == "user" {
-                                if let Some(content) = msg.get("content") {
-                                    if let Some(content_str) = content.as_str() {
-                                        if content_str.starts_with("Tool result:") {
-                                            // Check if preceding message was final_output
-                                            if i > 0 {
-                                                let prev_msg = &messages[i - 1];
-                                                if let Some(prev_content) = prev_msg.get("content") {
-                                                    if let Some(prev_content_str) = prev_content.as_str() {
-                                                        if prev_content_str.contains("\"tool\": \"final_output\"") {
-                                                            let feedback = content_str.strip_prefix("Tool result: ").unwrap_or(content_str);
-                                                            assert_eq!(feedback, "APPROVED_RESULT", "Should extract only final_output result");
-                                                            println!("✅ Correctly extracted only final_output tool result: {}", feedback);
-                                                            return;
-                                                        }
-                                                    }
-                                                }
-                                            }
-                                        }
-                                    }
-                                }
-                            }
-                        }
-                    }
-                }
-            }
-        }
-    }
-
-    panic!("Failed to extract final_output tool result");
-}
-
-#[test]
-fn test_extract_coach_feedback_without_timing_message() {
-    // Create a temporary directory for session logs
-    let temp_dir = TempDir::new().unwrap();
-    let sessions_dir = temp_dir.path().join(".g3").join("sessions");
-    fs::create_dir_all(&sessions_dir).unwrap();
-
-    // Test the case where there's no timing message (backward compatibility)
-    let session_id = "test_session_456";
-    let session_dir = sessions_dir.join(session_id);
-    fs::create_dir_all(&session_dir).unwrap();
-    let log_file_path = session_dir.join("session.json");
-
-    let log_content = json!({
-        "session_id": session_id,
-        "context_window": {
-            "conversation_history": [
-                {
-                    "role": "assistant",
-                    "content": "{\"tool\": \"final_output\", \"args\": {\"summary\":\"TEST_FEEDBACK\"}}"
-                },
-                {
-                    "role": "user",
-                    "content": "Tool result: TEST_FEEDBACK"
-                }
-            ]
-        }
-    });
-
-    fs::write(&log_file_path, serde_json::to_string_pretty(&log_content).unwrap()).unwrap();
-
-    // Test extraction
-    let log_content_str = fs::read_to_string(&log_file_path).unwrap();
-    let log_json: serde_json::Value = serde_json::from_str(&log_content_str).unwrap();
-
-    if let Some(context_window) = log_json.get("context_window") {
-        if let Some(conversation_history) = context_window.get("conversation_history") {
-            if let Some(messages) = conversation_history.as_array() {
-                let last_tool_result = messages.iter().rev().find(|msg| {
-                    if let Some(role) = msg.get("role") {
-                        if let Some(role_str) = role.as_str() {
-                            if role_str == "User" || role_str == "user" {
-                                if let Some(content) = msg.get("content") {
-                                    if let Some(content_str) = content.as_str() {
-                                        return content_str.starts_with("Tool result:");
-                                    }
-                                }
-                            }
-                        }
-                    }
-                    false
-                });
-
-                assert!(last_tool_result.is_some());
-
-                if let Some(last_message) = last_tool_result {
-                    if let Some(content) = last_message.get("content") {
-                        if let Some(content_str) = content.as_str() {
-                            let feedback = content_str.strip_prefix("Tool result: ").unwrap_or(content_str);
-                            assert_eq!(feedback, "TEST_FEEDBACK");
-                            println!("✅ Successfully extracted coach feedback without timing: {}", feedback);
-                            return;
-                        }
-                    }
-                }
-            }
-        }
-    }
-
-    panic!("Failed to extract coach feedback");
-}
-
-#[test]
-fn test_extract_coach_feedback_with_multiple_tool_results() {
-    // Test that we get the LAST tool result when there are multiple
-    let temp_dir = TempDir::new().unwrap();
-    let sessions_dir = temp_dir.path().join(".g3").join("sessions");
-    fs::create_dir_all(&sessions_dir).unwrap();
-
-    let session_id = "test_session_789";
-    let session_dir = sessions_dir.join(session_id);
-    fs::create_dir_all(&session_dir).unwrap();
-    let log_file_path = session_dir.join("session.json");
-
-    let log_content = json!({
-        "session_id": session_id,
-        "context_window": {
-            "conversation_history": [
-                {
-                    "role": "assistant",
-                    "content": "{\"tool\": \"shell\", \"args\": {\"command\":\"ls\"}}"
-                },
-                {
-                    "role": "user",
-                    "content": "Tool result: file1.txt\nfile2.txt"
-                },
-                {
-                    "role": "assistant",
-                    "content": "{\"tool\": \"final_output\", \"args\": {\"summary\":\"FINAL_RESULT\"}}"
-                },
-                {
-                    "role": "user",
-                    "content": "Tool result: FINAL_RESULT"
-                },
-                {
-                    "role": "assistant",
-                    "content": "🕝 15.2s | 💭 3.1s"
-                }
-            ]
-        }
-    });
-
-    fs::write(&log_file_path, serde_json::to_string_pretty(&log_content).unwrap()).unwrap();
-
-    // Test extraction
-    let log_content_str = fs::read_to_string(&log_file_path).unwrap();
-    let log_json: serde_json::Value = serde_json::from_str(&log_content_str).unwrap();
-
-    if let Some(context_window) = log_json.get("context_window") {
-        if let Some(conversation_history) = context_window.get("conversation_history") {
-            if let Some(messages) = conversation_history.as_array() {
-                let last_tool_result = messages.iter().rev().find(|msg| {
-                    if let Some(role) = msg.get("role") {
-                        if let Some(role_str) = role.as_str() {
-                            if role_str == "User" || role_str == "user" {
-                                if let Some(content) = msg.get("content") {
-                                    if let Some(content_str) = content.as_str() {
-                                        return content_str.starts_with("Tool result:");
-                                    }
-                                }
-                            }
-                        }
-                    }
-                    false
-                });
-
-                assert!(last_tool_result.is_some());
-
-                if let Some(last_message) = last_tool_result {
-                    if let Some(content) = last_message.get("content") {
-                        if let Some(content_str) = content.as_str() {
-                            let feedback = content_str.strip_prefix("Tool result: ").unwrap_or(content_str);
-                            // Should get the LAST tool result (final_output), not the first one (shell)
-                            assert_eq!(feedback, "FINAL_RESULT", "Should extract the last tool result");
-                            assert!(!feedback.contains("file1.txt"), "Should not extract earlier tool results");
-                            println!("✅ Successfully extracted last tool result: {}", feedback);
-                            return;
-                        }
-                    }
-                }
-            }
-        }
-    }
-
-    panic!("Failed to extract coach feedback");
-}

crates/g3-cli/tests/filter_json_stress_test.rs

@@ -1,644 +0,0 @@
-//! Stress tests for JSON tool call filtering.
-//!
-//! These tests hammer the filter with malformed JSON, partial tool calls,
-//! edge cases, and adversarial inputs to ensure robustness.
-
-use g3_cli::filter_json::{filter_json_tool_calls, flush_json_tool_filter, reset_json_tool_state};
-
-// ============================================================================
-// Malformed JSON Tests
-// ============================================================================
-
-#[test]
-fn test_unclosed_brace_at_end() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": \"shell\", \"args\": {\"cmd\": \"ls\"";
-    let result = filter_json_tool_calls(input);
-    // Should suppress the incomplete tool call
-    assert_eq!(result, "Text\n");
-}
-
-#[test]
-fn test_missing_closing_quote() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": \"shell\", \"args\": {\"cmd\": \"ls}}\nMore";
-    let result = filter_json_tool_calls(input);
-    // The unbalanced quote makes brace counting tricky
-    // Should still filter the tool call attempt
-    assert_eq!(result, "Text\n");
-}
-
-#[test]
-fn test_extra_closing_braces() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": \"shell\", \"args\": {}}}}}\nMore";
-    let result = filter_json_tool_calls(input);
-    // Extra braces after valid JSON should pass through
-    assert_eq!(result, "Text\n}}}\nMore");
-}
-
-#[test]
-fn test_deeply_nested_malformed() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": \"x\", \"args\": {{{{{{}}}}}}}\nMore";
-    let result = filter_json_tool_calls(input);
-    // Should handle deep nesting - extra braces get consumed as part of the tool call
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_null_bytes_in_json() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": \"shell\0\", \"args\": {}}\nMore";
-    let result = filter_json_tool_calls(input);
-    // Should handle null bytes gracefully
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_unicode_in_tool_name() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": \"shëll\", \"args\": {}}\nMore";
-    let result = filter_json_tool_calls(input);
-    // Unicode in tool name - still a valid tool call pattern
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_emoji_in_args() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": \"shell\", \"args\": {\"msg\": \"Hello 🎉\"}}\nMore";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_very_long_string_value() {
-    reset_json_tool_state();
-    let long_string = "x".repeat(10000);
-    let input = format!("Text\n{{\"tool\": \"shell\", \"args\": {{\"data\": \"{}\"}}}}\nMore", long_string);
-    let result = filter_json_tool_calls(&input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_many_escaped_quotes() {
-    reset_json_tool_state();
-    let input = r#"Text
-{"tool": "shell", "args": {"cmd": "echo \"a\" \"b\" \"c\" \"d\" \"e\""}}
-More"#;
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_escaped_backslash_before_quote() {
-    reset_json_tool_state();
-    // This is: {"tool": "shell", "args": {"path": "C:\\"}}
-    let input = "Text\n{\"tool\": \"shell\", \"args\": {\"path\": \"C:\\\\\"}}\nMore";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_newlines_inside_string() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": \"shell\", \"args\": {\"cmd\": \"echo\\nworld\"}}\nMore";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-// ============================================================================
-// Partial Tool Call Pattern Tests
-// ============================================================================
-
-#[test]
-fn test_just_opening_brace() {
-    reset_json_tool_state();
-    let result = filter_json_tool_calls("Text\n{");
-    // Should buffer, waiting for more
-    assert_eq!(result, "Text\n");
-    
-    // Now send something that's not a tool call
-    let result2 = filter_json_tool_calls("\"other\": 1}\nMore");
-    assert_eq!(result2, "{\"other\": 1}\nMore");
-}
-
-#[test]
-fn test_partial_tool_keyword() {
-    reset_json_tool_state();
-    let chunks = vec!["Text\n{", "\"to", "ol", "\": ", "\"sh", "ell\"", ", \"args\": {}", "}\nMore"];
-    let mut result = String::new();
-    for chunk in chunks {
-        result.push_str(&filter_json_tool_calls(chunk));
-    }
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_tool_then_not_colon() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\" \"shell\"}\nMore"; // Missing colon
-    let result = filter_json_tool_calls(input);
-    // Not a valid tool call pattern - should pass through
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_tool_colon_then_number() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": 123}\nMore"; // Number instead of string
-    let result = filter_json_tool_calls(input);
-    // Not a valid tool call pattern - should pass through
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_tool_colon_then_null() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": null}\nMore";
-    let result = filter_json_tool_calls(input);
-    // Not a valid tool call pattern - should pass through
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_tool_colon_then_array() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": []}\nMore";
-    let result = filter_json_tool_calls(input);
-    // Not a valid tool call pattern - should pass through
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_tool_colon_then_object() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": {}}\nMore";
-    let result = filter_json_tool_calls(input);
-    // Not a valid tool call pattern - should pass through
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_tools_plural() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tools\": \"shell\"}\nMore";
-    let result = filter_json_tool_calls(input);
-    // "tools" is not "tool" - should pass through
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_tool_with_prefix() {
-    reset_json_tool_state();
-    let input = "Text\n{\"mytool\": \"shell\"}\nMore";
-    let result = filter_json_tool_calls(input);
-    // "mytool" is not "tool" - should pass through
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_tool_uppercase() {
-    reset_json_tool_state();
-    let input = "Text\n{\"TOOL\": \"shell\"}\nMore";
-    let result = filter_json_tool_calls(input);
-    // "TOOL" is not "tool" - should pass through
-    assert_eq!(result, input);
-}
-
-// ============================================================================
-// Streaming Edge Cases
-// ============================================================================
-
-#[test]
-fn test_single_char_streaming() {
-    reset_json_tool_state();
-    let input = "Hi\n{\"tool\": \"x\", \"args\": {}}\nBye";
-    let mut result = String::new();
-    for ch in input.chars() {
-        result.push_str(&filter_json_tool_calls(&ch.to_string()));
-    }
-    assert_eq!(result, "Hi\n\nBye");
-}
-
-#[test]
-fn test_two_char_streaming() {
-    reset_json_tool_state();
-    let input = "Hi\n{\"tool\": \"x\", \"args\": {}}\nBye";
-    let mut result = String::new();
-    let chars: Vec<char> = input.chars().collect();
-    for chunk in chars.chunks(2) {
-        let s: String = chunk.iter().collect();
-        result.push_str(&filter_json_tool_calls(&s));
-    }
-    assert_eq!(result, "Hi\n\nBye");
-}
-
-#[test]
-fn test_random_chunk_sizes() {
-    reset_json_tool_state();
-    let input = "Before\n{\"tool\": \"shell\", \"args\": {\"cmd\": \"ls -la\"}}\nAfter";
-    
-    // Chunk at various sizes
-    let chunk_sizes = [1, 3, 7, 11, 13, 17];
-    
-    for &size in &chunk_sizes {
-        reset_json_tool_state();
-        let mut result = String::new();
-        let mut pos = 0;
-        while pos < input.len() {
-            let end = (pos + size).min(input.len());
-            let chunk = &input[pos..end];
-            result.push_str(&filter_json_tool_calls(chunk));
-            pos = end;
-        }
-        assert_eq!(result, "Before\n\nAfter", "Failed with chunk size {}", size);
-    }
-}
-
-#[test]
-fn test_chunk_boundary_at_brace() {
-    reset_json_tool_state();
-    let chunks = vec!["Text\n", "{", "\"tool\": \"x\", \"args\": {}", "}", "\nMore"];
-    let mut result = String::new();
-    for chunk in chunks {
-        result.push_str(&filter_json_tool_calls(chunk));
-    }
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_chunk_boundary_at_quote() {
-    reset_json_tool_state();
-    let chunks = vec!["Text\n{\"tool\": \"", "shell", "\", \"args\": {}}", "\nMore"];
-    let mut result = String::new();
-    for chunk in chunks {
-        result.push_str(&filter_json_tool_calls(chunk));
-    }
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_chunk_boundary_at_colon() {
-    reset_json_tool_state();
-    let chunks = vec!["Text\n{\"tool\"", ":", " \"shell\", \"args\": {}}\nMore"];
-    let mut result = String::new();
-    for chunk in chunks {
-        result.push_str(&filter_json_tool_calls(chunk));
-    }
-    assert_eq!(result, "Text\n\nMore");
-}
-
-// ============================================================================
-// Multiple Tool Calls
-// ============================================================================
-
-#[test]
-fn test_two_tool_calls_same_line() {
-    reset_json_tool_state();
-    // Two tool calls on same line (no newline between)
-    let input = "Text\n{\"tool\": \"a\", \"args\": {}}{\"tool\": \"b\", \"args\": {}}\nMore";
-    let result = filter_json_tool_calls(input);
-    // First is filtered (starts at line beginning)
-    // Second starts immediately after first's }, not at line start, so passes through
-    // This is acceptable - LLMs typically put tool calls on separate lines
-    assert_eq!(result, "Text\n{\"tool\": \"b\", \"args\": {}}\nMore");
-}
-
-#[test]
-fn test_three_tool_calls_separate_lines() {
-    reset_json_tool_state();
-    let input = "A\n{\"tool\": \"x\", \"args\": {}}\nB\n{\"tool\": \"y\", \"args\": {}}\nC\n{\"tool\": \"z\", \"args\": {}}\nD";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "A\n\nB\n\nC\n\nD");
-}
-
-#[test]
-fn test_tool_call_then_regular_json() {
-    reset_json_tool_state();
-    let input = "A\n{\"tool\": \"x\", \"args\": {}}\nB\n{\"data\": 123}\nC";
-    let result = filter_json_tool_calls(input);
-    // First is tool call (filtered), second is regular JSON (kept)
-    assert_eq!(result, "A\n\nB\n{\"data\": 123}\nC");
-}
-
-#[test]
-fn test_regular_json_then_tool_call() {
-    reset_json_tool_state();
-    let input = "A\n{\"data\": 123}\nB\n{\"tool\": \"x\", \"args\": {}}\nC";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "A\n{\"data\": 123}\nB\n\nC");
-}
-
-// ============================================================================
-// Adversarial Inputs
-// ============================================================================
-
-#[test]
-fn test_fake_tool_in_string() {
-    reset_json_tool_state();
-    // The tool pattern appears inside a string value
-    let input = r#"Text
-{"message": "{\"tool\": \"shell\"}"}
-More"#;
-    let result = filter_json_tool_calls(input);
-    // Should pass through - the pattern is inside a string
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_nested_json_with_tool_key() {
-    reset_json_tool_state();
-    // Nested object has "tool" key but outer doesn't match pattern
-    let input = "Text\n{\"outer\": {\"tool\": \"inner\"}}\nMore";
-    let result = filter_json_tool_calls(input);
-    // Should pass through - outer object doesn't start with "tool"
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_brace_bomb() {
-    reset_json_tool_state();
-    // Many braces to stress the counter
-    let input = "Text\n{\"tool\": \"x\", \"args\": {\"a\": {\"b\": {\"c\": {\"d\": {\"e\": {}}}}}}}\nMore";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_string_with_many_braces() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": \"x\", \"args\": {\"code\": \"{{{{}}}}\"}}\nMore";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_alternating_braces_in_string() {
-    reset_json_tool_state();
-    let input = "Text\n{\"tool\": \"x\", \"args\": {\"pat\": \"}{}{}{\"}}\nMore";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_quote_after_backslash_in_string() {
-    reset_json_tool_state();
-    // Tricky: \" inside string should not end the string
-    let input = r#"Text
-{"tool": "x", "args": {"msg": "say \"hi\""}}
-More"#;
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_double_backslash_then_quote() {
-    reset_json_tool_state();
-    // \\ followed by " - the quote DOES end the string
-    let input = "Text\n{\"tool\": \"x\", \"args\": {\"path\": \"C:\\\\\"}}\nMore";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_triple_backslash_then_quote() {
-    reset_json_tool_state();
-    // \\\" - escaped backslash followed by escaped quote
-    let input = "Text\n{\"tool\": \"x\", \"args\": {\"s\": \"a\\\\\\\"b\"}}\nMore";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-// ============================================================================
-// Whitespace Variations
-// ============================================================================
-
-#[test]
-fn test_tabs_before_brace() {
-    reset_json_tool_state();
-    let input = "Text\n\t\t{\"tool\": \"x\", \"args\": {}}\nMore";
-    let result = filter_json_tool_calls(input);
-    // Indented JSON should NOT be filtered - real tool calls are never indented
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_spaces_before_brace() {
-    reset_json_tool_state();
-    let input = "Text\n    {\"tool\": \"x\", \"args\": {}}\nMore";
-    let result = filter_json_tool_calls(input);
-    // Indented JSON should NOT be filtered - real tool calls are never indented
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_mixed_whitespace_before_brace() {
-    reset_json_tool_state();
-    let input = "Text\n \t \t {\"tool\": \"x\", \"args\": {}}\nMore";
-    let result = filter_json_tool_calls(input);
-    // Indented JSON should NOT be filtered - real tool calls are never indented
-    assert_eq!(result, input);
-}
-
-#[test]
-fn test_space_after_opening_brace() {
-    reset_json_tool_state();
-    let input = "Text\n{ \"tool\": \"x\", \"args\": {}}\nMore";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_lots_of_space_in_json() {
-    reset_json_tool_state();
-    let input = "Text\n{   \"tool\"   :   \"x\"   ,   \"args\"   :   {   }   }\nMore";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Text\n\nMore");
-}
-
-#[test]
-fn test_crlf_line_endings() {
-    reset_json_tool_state();
-    let input = "Text\r\n{\"tool\": \"x\", \"args\": {}}\r\nMore";
-    let result = filter_json_tool_calls(input);
-    // \r is not treated as line start, so { after \r\n should work
-    // Actually \n triggers line start, \r is just a regular char
-    assert_eq!(result, "Text\r\n\r\nMore");
-}
-
-// ============================================================================
-// Empty and Minimal Cases
-// ============================================================================
-
-#[test]
-fn test_empty_input() {
-    reset_json_tool_state();
-    assert_eq!(filter_json_tool_calls(""), "");
-}
-
-#[test]
-fn test_just_newline() {
-    reset_json_tool_state();
-    let result = filter_json_tool_calls("\n");
-    let flushed = flush_json_tool_filter();
-    assert_eq!(format!("{}{}", result, flushed), "\n");
-}
-
-#[test]
-fn test_just_brace() {
-    reset_json_tool_state();
-    let r1 = filter_json_tool_calls("{");
-    // At start of input (line start), { triggers buffering
-    assert_eq!(r1, "");
-    
-    // Send non-tool content - the newline comes through
-    let r2 = filter_json_tool_calls("}\n");
-    assert_eq!(r2, "{}\n");
-}
-
-#[test]
-fn test_minimal_tool_call() {
-    reset_json_tool_state();
-    let input = "{\"tool\":\"x\",\"args\":{}}";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "");
-}
-
-#[test]
-fn test_tool_call_at_very_start() {
-    reset_json_tool_state();
-    let input = "{\"tool\": \"x\", \"args\": {}}\nAfter";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "\nAfter");
-}
-
-// ============================================================================
-// State Reset Tests
-// ============================================================================
-
-#[test]
-fn test_reset_clears_buffering_state() {
-    reset_json_tool_state();
-    
-    // Start a potential tool call
-    let _ = filter_json_tool_calls("Text\n{");
-    
-    // Reset
-    reset_json_tool_state();
-    
-    // New input should work fresh
-    let result = filter_json_tool_calls("Fresh start");
-    assert_eq!(result, "Fresh start");
-}
-
-#[test]
-fn test_reset_clears_suppressing_state() {
-    reset_json_tool_state();
-    
-    // Start suppressing a tool call
-    let _ = filter_json_tool_calls("Text\n{\"tool\": \"x\", \"args\": {");
-    
-    // Reset
-    reset_json_tool_state();
-    
-    // New input should work fresh
-    let result = filter_json_tool_calls("Fresh start");
-    assert_eq!(result, "Fresh start");
-}
-
-// ============================================================================
-// Real-World Patterns from Bug Reports
-// ============================================================================
-
-#[test]
-fn test_str_replace_with_diff() {
-    reset_json_tool_state();
-    let input = r#"I'll update the file:
-{"tool": "str_replace", "args": {"file_path": "src/main.rs", "diff": "@@ -1,3 +1,4 @@\n fn main() {\n+    println!(\"Hello\");\n }"}}
-Done!"#;
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "I'll update the file:\n\nDone!");
-}
-
-#[test]
-fn test_shell_with_complex_command() {
-    reset_json_tool_state();
-    let input = r#"Running command:
-{"tool": "shell", "args": {"command": "find . -name '*.rs' -exec grep -l 'TODO' {} \;"}}
-Results above."#;
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Running command:\n\nResults above.");
-}
-
-#[test]
-fn test_write_file_with_json_content() {
-    reset_json_tool_state();
-    let input = r#"Creating config:
-{"tool": "write_file", "args": {"file_path": "config.json", "content": "{\"key\": \"value\"}"}}
-File created."#;
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Creating config:\n\nFile created.");
-}
-
-#[test]
-fn test_read_file_simple() {
-    reset_json_tool_state();
-    let input = "Let me check:\n{\"tool\": \"read_file\", \"args\": {\"file_path\": \"README.md\"}}\nHere's what I found:";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Let me check:\n\nHere's what I found:");
-}
-
-#[test]
-fn test_final_output() {
-    reset_json_tool_state();
-    let input = "Task complete.\n{\"tool\": \"final_output\", \"args\": {\"summary\": \"# Summary\\n\\nI completed the task.\\n\\n## Details\\n- Item 1\\n- Item 2\"}}\n";
-    let result = filter_json_tool_calls(input);
-    assert_eq!(result, "Task complete.\n\n");
-}
-
-// ============================================================================
-// Truncated JSON followed by Complete JSON (the original bug)
-// ============================================================================
-
-#[test]
-fn test_truncated_then_complete_streaming() {
-    reset_json_tool_state();
-    
-    // Chunk 1: text
-    let r1 = filter_json_tool_calls("Some text\n");
-    assert_eq!(r1, "Some text\n");
-    
-    // Chunk 2: truncated tool call
-    let r2 = filter_json_tool_calls(r#"{"tool": "str_replace", "args": {"diff":"partial"#);
-    assert_eq!(r2, "");
-    
-    // Chunk 3: new complete tool call (LLM retry)
-    let r3 = filter_json_tool_calls(r#"{"tool": "str_replace", "args": {"diff":"complete", "file_path":"x.rs"}}"#);
-    assert_eq!(r3, "");
-    
-    // Chunk 4: text after
-    let r4 = filter_json_tool_calls("\nMore text");
-    assert_eq!(r4, "\nMore text");
-}
-
-#[test]
-fn test_multiple_truncated_then_complete() {
-    reset_json_tool_state();
-    
-    let chunks = vec![
-        "Start\n",
-        r#"{"tool": "a", "args": {"x": "trunc"#,  // truncated
-        r#"{"tool": "b", "args": {"y": "also_trunc"#,  // another truncated
-        r#"{"tool": "c", "args": {"z": "complete"}}"#,  // finally complete
-        "\nEnd",
-    ];
-    
-    let mut result = String::new();
-    for chunk in chunks {
-        result.push_str(&filter_json_tool_calls(chunk));
-    }
-    
-    assert_eq!(result, "Start\n\nEnd");
-}

crates/g3-cli/tests/filter_json_test.rs

@@ -1,553 +0,0 @@
-//! Tests for JSON tool call filtering.
-//!
-//! These tests verify that the filter correctly identifies and removes JSON tool calls
-//! from LLM output streams while preserving all other content.
-
-#[cfg(test)]
-mod filter_json_tests {
-    use g3_cli::filter_json::{filter_json_tool_calls, reset_json_tool_state};
-    use regex::Regex;
-
-    /// Test that regular text without tool calls passes through unchanged.
-    #[test]
-    fn test_no_tool_call_passthrough() {
-        reset_json_tool_state();
-        let input = "This is regular text without any tool calls.";
-        let result = filter_json_tool_calls(input);
-        assert_eq!(result, input);
-    }
-
-    /// Test detection and removal of a complete tool call in a single chunk.
-    #[test]
-    fn test_simple_tool_call_detection() {
-        reset_json_tool_state();
-        let input = r#"Some text before
-{"tool": "shell", "args": {"command": "ls"}}
-Some text after"#;
-
-        let result = filter_json_tool_calls(input);
-        let expected = "Some text before\n\nSome text after";
-        assert_eq!(result, expected);
-    }
-
-    /// Test handling of tool calls that arrive across multiple streaming chunks.
-    #[test]
-    fn test_streaming_chunks() {
-        reset_json_tool_state();
-
-        // Simulate streaming where the tool call comes in multiple chunks
-        let chunks = vec![
-            "Some text before\n",
-            "{\"tool\": \"",
-            "shell\", \"args\": {",
-            "\"command\": \"ls\"",
-            "}}\nText after",
-        ];
-
-        let mut results = Vec::new();
-        for chunk in chunks {
-            let result = filter_json_tool_calls(chunk);
-            results.push(result);
-        }
-
-        // The final accumulated result should have the JSON filtered out
-        let final_result: String = results.join("");
-        let expected = "Some text before\n\nText after";
-        assert_eq!(final_result, expected);
-    }
-
-    /// Test correct handling of nested braces within JSON strings.
-    #[test]
-    fn test_nested_braces_in_tool_call() {
-        reset_json_tool_state();
-
-        let input = r#"Text before
-{"tool": "write_file", "args": {"file_path": "test.json", "content": "{\"nested\": \"value\"}"}}
-Text after"#;
-
-        let result = filter_json_tool_calls(input);
-        let expected = "Text before\n\nText after";
-        assert_eq!(result, expected);
-    }
-
-    /// Verify the regex pattern matches the specification with flexible whitespace.
-    #[test]
-    fn test_regex_pattern_specification() {
-        // Test the corrected regex pattern that's more flexible with whitespace
-        let pattern = Regex::new(r#"(?m)^\s*\{\s*"tool"\s*:"#).unwrap();
-
-        let test_cases = vec![
-            (
-                r#"line
-{"tool":"#,
-                true,
-            ),
-            (
-                r#"line
-{"tool" :"#,
-                true,
-            ),
-            (
-                r#"line
-{ "tool":"#,
-                true,
-            ), // Space after { DOES match with \s*
-            (
-                r#"line
-{"tool123":"#,
-                false,
-            ), // "tool123" is not exactly "tool"
-            (
-                r#"line
-{"tool" : "#,
-                true,
-            ),
-        ];
-
-        for (input, should_match) in test_cases {
-            let matches = pattern.is_match(input);
-            assert_eq!(
-                matches, should_match,
-                "Pattern matching failed for: {}",
-                input
-            );
-        }
-    }
-
-    /// Test that tool calls must appear at the start of a line (after newline).
-    #[test]
-    fn test_newline_requirement() {
-        reset_json_tool_state();
-
-        // According to spec, tool call should be detected "on the very next newline"
-        // Our current regex matches any line that contains the pattern, not just after newlines
-        let input_with_newline = "Text\n{\"tool\": \"shell\", \"args\": {\"command\": \"ls\"}}";
-        let input_without_newline = "Text {\"tool\": \"shell\", \"args\": {\"command\": \"ls\"}}";
-
-        let result1 = filter_json_tool_calls(input_with_newline);
-        reset_json_tool_state();
-        let result2 = filter_json_tool_calls(input_without_newline);
-
-        // With the new aggressive filtering, only the newline case should trigger suppression
-        // The pattern requires { to be at the start of a line (after ^)
-        assert_eq!(result1, "Text\n");
-        // Without newline before {, it should pass through unchanged
-        assert_eq!(result2, input_without_newline);
-    }
-
-    /// Test handling of escaped quotes within JSON strings.
-    #[test]
-    fn test_json_with_escaped_quotes() {
-        reset_json_tool_state();
-
-        let input = r#"Text
-{"tool": "write_file", "args": {"content": "He said \"hello\" to me"}}
-More text"#;
-
-        let result = filter_json_tool_calls(input);
-        let expected = "Text\n\nMore text";
-        assert_eq!(result, expected);
-    }
-
-    /// Test graceful handling of incomplete/malformed JSON.
-    #[test]
-    fn test_edge_case_malformed_json() {
-        reset_json_tool_state();
-
-        // Test what happens with malformed JSON that starts like a tool call
-        let input = r#"Text
-{"tool": "shell", "args": {"command": "ls"
-More text"#;
-
-        let result = filter_json_tool_calls(input);
-        // Should handle gracefully - since JSON is incomplete, it should return content before JSON
-        let expected = "Text\n";
-        assert_eq!(result, expected);
-    }
-
-    /// Test processing multiple independent tool calls sequentially.
-    #[test]
-    fn test_multiple_tool_calls_sequential() {
-        reset_json_tool_state();
-
-        // Test processing multiple tool calls one at a time
-        let input1 = r#"First text
-{"tool": "shell", "args": {"command": "ls"}}
-Middle text"#;
-        let result1 = filter_json_tool_calls(input1);
-        let expected1 = "First text\n\nMiddle text";
-        assert_eq!(result1, expected1);
-
-        // Reset and process second tool call
-        reset_json_tool_state();
-        let input2 = r#"More text
-{"tool": "read_file", "args": {"file_path": "test.txt"}}
-Final text"#;
-        let result2 = filter_json_tool_calls(input2);
-        let expected2 = "More text\n\nFinal text";
-        assert_eq!(result2, expected2);
-    }
-
-    /// Test tool calls with complex multi-line arguments.
-    #[test]
-    fn test_tool_call_with_complex_args() {
-        reset_json_tool_state();
-
-        let input = r#"Before
-{"tool": "str_replace", "args": {"file_path": "test.rs", "diff": "--- old\n-old line\n+++ new\n+new line", "start": 0, "end": 100}}
-After"#;
-
-        let result = filter_json_tool_calls(input);
-        let expected = "Before\n\nAfter";
-        assert_eq!(result, expected);
-    }
-
-    /// Test input containing only a tool call with no surrounding text.
-    #[test]
-    fn test_tool_call_only() {
-        reset_json_tool_state();
-
-        let input = r#"
-{"tool": "final_output", "args": {"summary": "Task completed successfully"}}"#;
-
-        let result = filter_json_tool_calls(input);
-        // Leading newline before tool call at start of input is suppressed
-        let expected = "";
-        assert_eq!(result, expected);
-    }
-
-    /// Test accurate brace counting with deeply nested structures.
-    #[test]
-    fn test_brace_counting_accuracy() {
-        reset_json_tool_state();
-
-        // Test complex nested structure
-        let input = r#"Start
-{"tool": "write_file", "args": {"content": "function() { return {a: 1, b: {c: 2}}; }", "file_path": "test.js"}}
-End"#;
-
-        let result = filter_json_tool_calls(input);
-        let expected = "Start\n\nEnd";
-        assert_eq!(result, expected);
-    }
-
-    /// Test that braces within strings don't affect brace counting.
-    #[test]
-    fn test_string_escaping_in_json() {
-        reset_json_tool_state();
-
-        // Test JSON with escaped quotes and braces in strings
-        let input = r#"Text
-{"tool": "shell", "args": {"command": "echo \"Hello {world}\" > file.txt"}}
-More"#;
-
-        let result = filter_json_tool_calls(input);
-        let expected = "Text\n\nMore";
-        assert_eq!(result, expected);
-    }
-
-    /// Verify compliance with the exact specification requirements.
-    #[test]
-    fn test_specification_compliance() {
-        reset_json_tool_state();
-
-        // Test the exact specification requirements:
-        // 1. Detect start with regex '\w*{\w*"tool"\w*:\w*"' on newline
-        // 2. Enter suppression mode and use brace counting
-        // 3. Elide only JSON between first '{' and last '}' (inclusive)
-        // 4. Return everything else
-
-        let input = "Before text\nSome more text\n{\"tool\": \"test\", \"args\": {}}\nAfter text\nMore after";
-        let result = filter_json_tool_calls(input);
-        let expected = "Before text\nSome more text\n\nAfter text\nMore after";
-        assert_eq!(result, expected);
-    }
-
-    /// Test that non-tool JSON objects are not filtered.
-    #[test]
-    fn test_no_false_positives() {
-        reset_json_tool_state();
-
-        // Test that we don't incorrectly identify non-tool JSON as tool calls
-        let input = r#"Some text
-{"not_tool": "value", "other": "data"}
-More text"#;
-        let result = filter_json_tool_calls(input);
-        // Should pass through unchanged since it doesn't match the tool pattern
-        assert_eq!(result, input);
-    }
-
-    /// Test patterns that look similar to tool calls but aren't exact matches.
-    #[test]
-    fn test_partial_tool_patterns() {
-        reset_json_tool_state();
-
-        // Test patterns that look like tool calls but aren't complete
-        let test_cases = vec![
-            "Text\n{\"too\": \"value\"}",   // "too" not "tool"
-            "Text\n{\"tools\": \"value\"}", // "tools" not "tool"
-            "Text\n{\"tool\": }",           // Missing value after colon
-        ];
-
-        for input in test_cases {
-            reset_json_tool_state();
-            let result = filter_json_tool_calls(input);
-            // These should all pass through unchanged
-            assert_eq!(result, input, "Input should pass through: {}", input);
-        }
-    }
-
-    /// Test streaming with very small chunks (character-by-character).
-    #[test]
-    fn test_streaming_edge_cases() {
-        reset_json_tool_state();
-
-        // Test streaming with very small chunks
-        let chunks = vec![
-            "Text\n", "{", "\"", "tool", "\"", ":", " ", "\"", "test", "\"", "}", "\nAfter",
-        ];
-
-        let mut results = Vec::new();
-        for chunk in chunks {
-            let result = filter_json_tool_calls(chunk);
-            results.push(result);
-        }
-
-        let final_result: String = results.join("");
-        // With the new aggressive filtering, the JSON should be completely filtered out
-        // even when it arrives in very small chunks
-        let expected = "Text\n\nAfter";
-        assert_eq!(final_result, expected);
-    }
-
-    /// Debug test with detailed logging for streaming behavior.
-    #[test]
-    fn test_streaming_debug() {
-        reset_json_tool_state();
-
-        // Debug the exact failing case
-        let chunks = vec![
-            "Some text before\n",
-            "{\"tool\": \"",
-            "shell\", \"args\": {",
-            "\"command\": \"ls\"",
-            "}}\nText after",
-        ];
-
-        let mut results = Vec::new();
-        for (i, chunk) in chunks.iter().enumerate() {
-            let result = filter_json_tool_calls(chunk);
-            println!("Chunk {}: {:?} -> {:?}", i, chunk, result);
-            results.push(result);
-        }
-
-        let final_result: String = results.join("");
-        println!("Final result: {:?}", final_result);
-        println!("Expected: {:?}", "Some text before\n\nText after");
-
-        let expected = "Some text before\n\nText after";
-        assert_eq!(final_result, expected);
-    }
-
-    /// Test handling of truncated JSON followed by complete JSON (the json_err pattern)
-    #[test]
-    fn test_truncated_then_complete_json() {
-        reset_json_tool_state();
-
-        // Simulate the pattern from json_err trace:
-        // 1. Incomplete/truncated JSON appears
-        // 2. Then the same complete JSON appears
-        let chunks = vec![
-            "Some text\n",
-            r#"{"tool": "str_replace", "args": {"diff":"...","file_path":"./crates/g3-cli"#, // Truncated
-            r#"{"tool": "str_replace", "args": {"diff":"...","file_path":"./crates/g3-cli/src/lib.rs"}}"#, // Complete
-            "\nMore text",
-        ];
-
-        let mut results = Vec::new();
-        for (i, chunk) in chunks.iter().enumerate() {
-            let result = filter_json_tool_calls(chunk);
-            println!("Chunk {}: {:?} -> {:?}", i, chunk, result);
-            results.push(result);
-        }
-
-        let final_result: String = results.join("");
-        println!("Final result: {:?}", final_result);
-
-        // The truncated JSON should be discarded when the complete one appears
-        // Both JSONs should be filtered out, leaving only the text
-        let expected = "Some text\n\nMore text";
-        assert_eq!(
-            final_result, expected,
-            "Failed to handle truncated JSON followed by complete JSON"
-        );
-    }
-
-    // ============================================================================
-    // Edge Case Tests - These test the bugs that were fixed in the rewrite
-    // ============================================================================
-
-    /// CRITICAL: Test that closing braces inside JSON strings don't break filtering.
-    /// This was the main bug in the original implementation.
-    #[test]
-    fn test_brace_inside_json_string_value() {
-        reset_json_tool_state();
-
-        // The } inside "echo }" should NOT cause premature exit from suppression
-        let input = r#"Text before
-{"tool": "shell", "args": {"command": "echo }"}}
-Text after"#;
-
-        let result = filter_json_tool_calls(input);
-        let expected = "Text before\n\nText after";
-        assert_eq!(
-            result, expected,
-            "Brace inside string value caused premature suppression exit"
-        );
-    }
-
-    /// Test multiple braces inside string values.
-    #[test]
-    fn test_multiple_braces_in_string() {
-        reset_json_tool_state();
-
-        let input = r#"Before
-{"tool": "shell", "args": {"command": "echo {{{}}}"}}
-After"#;
-
-        let result = filter_json_tool_calls(input);
-        let expected = "Before\n\nAfter";
-        assert_eq!(result, expected);
-    }
-
-    /// Test escaped quotes followed by braces in strings.
-    #[test]
-    fn test_escaped_quotes_with_braces() {
-        reset_json_tool_state();
-
-        let input = r#"Before
-{"tool": "shell", "args": {"command": "echo \"test}\" done"}}
-After"#;
-
-        let result = filter_json_tool_calls(input);
-        let expected = "Before\n\nAfter";
-        assert_eq!(result, expected);
-    }
-
-    /// Test braces in strings across streaming chunks.
-    #[test]
-    fn test_brace_in_string_across_chunks() {
-        reset_json_tool_state();
-
-        // The } appears in a separate chunk while we're inside a string
-        let chunks = vec![
-            "Before\n",
-            r#"{"tool": "shell", "args": {"command": "echo "#,
-            r#"}"}}"#,
-            "\nAfter",
-        ];
-
-        let mut results = Vec::new();
-        for chunk in chunks {
-            results.push(filter_json_tool_calls(chunk));
-        }
-
-        let final_result: String = results.join("");
-        let expected = "Before\n\nAfter";
-        assert_eq!(
-            final_result, expected,
-            "Brace in string across chunks caused incorrect filtering"
-        );
-    }
-
-    /// Test complex nested JSON with braces in multiple string values.
-    #[test]
-    fn test_complex_nested_with_string_braces() {
-        reset_json_tool_state();
-
-        let input = r#"Start
-{"tool": "write_file", "args": {"path": "test.json", "content": "{\"key\": \"value with } brace\"}"}}
-End"#;
-
-        let result = filter_json_tool_calls(input);
-        let expected = "Start\n\nEnd";
-        assert_eq!(result, expected);
-    }
-
-    /// Test the real-world case from jsonfilter_err - str_replace with diff containing braces
-    #[test]
-    fn test_str_replace_with_diff_content() {
-        reset_json_tool_state();
-
-        // This is a real case where str_replace tool call wasn't being filtered
-        // The diff content contains braces in the code being replaced
-        let input = r#"{"tool": "str_replace", "args": {"diff":"--- a/crates/g3-cli/src/ui_writer_impl.rs\n+++ b/crates/g3-cli/src/ui_writer_impl.rs\n@@ -355,11 +355,11 @@\n     fn filter_json_tool_calls(&self, content: &str) -> String {\n         // Apply JSON tool call filtering for display\n-        fixed_filter_json_tool_calls(content)\n+        filter_json_tool_calls(content)\n     }\n \n     fn reset_json_filter(&self) {\n         // Reset the filter state for a new response\n-        reset_fixed_json_tool_state();\n+        reset_json_tool_state();\n     }\n }","file_path":"crates/g3-cli/src/ui_writer_impl.rs"}}"#;
-
-        let result = filter_json_tool_calls(input);
-        
-        // The entire tool call should be filtered out
-        assert!(
-            result.is_empty() || result.trim().is_empty(),
-            "str_replace tool call was not filtered out. Got: {:?}",
-            result
-        );
-    }
-
-    /// Test tool call that appears after other content (from jsonfilter_err)
-    /// The filter requires tool calls to start at the beginning of a line
-    #[test]
-    fn test_tool_call_after_other_content() {
-        reset_json_tool_state();
-
-        // This simulates the jsonfilter_err case where a read_file result
-        // is followed by a str_replace tool call
-        let input = r#"┌─ read_file | ./crates/g3-cli/src/ui_writer_impl.rs [13000..13300]
-│     }
-│ (11 lines)
-└─ ⚡️ 1ms
-
-{"tool": "str_replace", "args": {"diff":"--- a/file.rs\n+++ b/file.rs\n-old\n+new","file_path":"file.rs"}}"#;
-
-        let result = filter_json_tool_calls(input);
-        
-        // The tool call starts on its own line after the read_file output.
-        // The tool call is filtered out, and extra newlines before it are suppressed.
-        // Only one newline remains (the line ending after "1ms").
-        let expected = r#"┌─ read_file | ./crates/g3-cli/src/ui_writer_impl.rs [13000..13300]
-│     }
-│ (11 lines)
-└─ ⚡️ 1ms
-"#;
-        assert_eq!(
-            result, expected,
-            "Tool call after other content was not filtered correctly"
-        );
-    }
-
-    /// Test case from jsonfilter_err2 - tool call at line start should be filtered,
-    /// but tool call patterns inside string values should be preserved
-    #[test]
-    fn test_tool_call_with_nested_tool_pattern_in_string() {
-        reset_json_tool_state();
-
-        // From jsonfilter_err2: A shell tool call that contains another tool call
-        // pattern inside its command string (a heredoc with code that references tool calls)
-        // The outer shell tool call starts at line beginning -> should be filtered
-        // The inner str_replace pattern is inside a string -> should NOT trigger filtering
-        let input = "Let me create a test case:\n\n{\"tool\": \"shell\", \"args\": {\"command\":\"cat file.rs\\nlet x = r#\\\"{\\\"tool\\\": \\\"test\\\"}\\\"#;\"}}\n\nDone.";
-
-        let result = filter_json_tool_calls(input);
-        
-        // The shell tool call starts at line beginning, so it should be filtered out
-        // Only the surrounding text should remain.
-        // Extra newlines before the tool call are suppressed (one blank line before
-        // becomes just the line ending), but newlines after are preserved.
-        let expected = "Let me create a test case:\n\n\nDone.";
-        
-        assert_eq!(
-            result, expected,
-            "Tool call with nested pattern was not filtered correctly. Got: {:?}",
-            result
-        );
-    }
-}

crates/g3-computer-control/Cargo.toml

@@ -10,13 +10,13 @@ edition = "2021"
 # Workspace dependencies
 tokio = { workspace = true }
 anyhow = { workspace = true }
+thiserror = { workspace = true }
 serde = { workspace = true }
 serde_json = { workspace = true }
 tracing = { workspace = true }
 uuid = { workspace = true }
 
 shellexpand = "3.1"
-dirs = "5.0"
 # Async trait support
 async-trait = "0.1"
 
@@ -30,12 +30,12 @@ core-foundation = "0.10"
 cocoa = "0.25"
 objc = "0.2"
 accessibility = "0.2"
-image = "0.25"
+image = "0.24"
 
 # Linux dependencies
 [target.'cfg(target_os = "linux")'.dependencies]
 x11 = { version = "2.21", features = ["xlib", "xtest"] }
-image = "0.25"
+image = "0.24"
 
 # Windows dependencies
 [target.'cfg(target_os = "windows")'.dependencies]

crates/g3-computer-control/build.rs

@@ -1,4 +1,63 @@
+use std::env;
+use std::path::PathBuf;
+use std::process::Command;
+
 fn main() {
-    // No build-time dependencies required
-    // VisionBridge OCR has been removed
+    // Only build Vision bridge on macOS
+    if env::var("CARGO_CFG_TARGET_OS").unwrap() != "macos" {
+        return;
+    }
+
+    println!("cargo:rerun-if-changed=vision-bridge/Sources/VisionBridge/VisionOCR.swift");
+    println!("cargo:rerun-if-changed=vision-bridge/Sources/VisionBridge/VisionBridge.h");
+    println!("cargo:rerun-if-changed=vision-bridge/Package.swift");
+
+    let manifest_dir = PathBuf::from(env::var("CARGO_MANIFEST_DIR").unwrap());
+    let vision_bridge_dir = manifest_dir.join("vision-bridge");
+
+    // Build Swift package
+    println!("cargo:warning=Building VisionBridge Swift package...");
+    let build_status = Command::new("swift")
+        .args(&["build", "-c", "release"])
+        .current_dir(&vision_bridge_dir)
+        .status()
+        .expect("Failed to build Swift package");
+
+    if !build_status.success() {
+        panic!("Swift build failed");
+    }
+
+    // Find the built library
+    let lib_path = vision_bridge_dir
+        .join(".build/release")
+        .canonicalize()
+        .expect("Failed to find .build/release directory");
+
+    // Copy the dylib to the output directory so it can be found at runtime
+    let target_dir = manifest_dir.parent().unwrap().parent().unwrap().join("target");
+    let profile = env::var("PROFILE").unwrap_or_else(|_| "debug".to_string());
+    let output_dir = target_dir.join(&profile);
+    
+    let dylib_src = lib_path.join("libVisionBridge.dylib");
+    let dylib_dst = output_dir.join("libVisionBridge.dylib");
+    
+    std::fs::copy(&dylib_src, &dylib_dst)
+        .expect(&format!("Failed to copy dylib from {} to {}", dylib_src.display(), dylib_dst.display()));
+    
+    println!("cargo:warning=Copied libVisionBridge.dylib to {}", dylib_dst.display());
+    
+    // Add rpath so the dylib can be found at runtime
+    println!("cargo:rustc-link-arg=-Wl,-rpath,@executable_path");
+    println!("cargo:rustc-link-arg=-Wl,-rpath,@loader_path");
+    println!("cargo:rustc-link-search=native={}", lib_path.display());
+    println!("cargo:rustc-link-lib=dylib=VisionBridge");
+
+    // Link required frameworks
+    println!("cargo:rustc-link-lib=framework=Vision");
+    println!("cargo:rustc-link-lib=framework=AppKit");
+    println!("cargo:rustc-link-lib=framework=Foundation");
+    println!("cargo:rustc-link-lib=framework=CoreGraphics");
+    println!("cargo:rustc-link-lib=framework=CoreImage");
+
+    println!("cargo:warning=VisionBridge built successfully at {}", lib_path.display());
 }

crates/g3-computer-control/examples/debug_screenshot.rs

@@ -23,23 +23,14 @@ fn main() {
     println!("\nRow alignment:");
     println!("  Actual bytes per row: {}", bytes_per_row);
     println!("  Expected (width * 4): {}", expected_bytes_per_row);
-    println!(
-        "  Padding per row: {}",
-        bytes_per_row - expected_bytes_per_row
-    );
+    println!("  Padding per row: {}", bytes_per_row - expected_bytes_per_row);
     
     // Sample some pixels from different locations
     println!("\nFirst 3 pixels (raw bytes):");
     for i in 0..3 {
         let offset = i * 4;
-        println!(
-            "  Pixel {}: [{:3}, {:3}, {:3}, {:3}]",
-            i,
-            data[offset],
-            data[offset + 1],
-            data[offset + 2],
-            data[offset + 3]
-        );
+        println!("  Pixel {}: [{:3}, {:3}, {:3}, {:3}]", 
+                 i, data[offset], data[offset+1], data[offset+2], data[offset+3]);
     }
     
     // Check a pixel from the middle
@@ -49,12 +40,7 @@ fn main() {
     println!("\nMiddle pixel (row {}, col {}):", mid_row, mid_col);
     println!("  Offset: {}", mid_offset);
     if mid_offset + 3 < data.len() as usize {
-        println!(
-            "  Bytes: [{:3}, {:3}, {:3}, {:3}]",
-            data[mid_offset],
-            data[mid_offset + 1],
-            data[mid_offset + 2],
-            data[mid_offset + 3]
-        );
+        println!("  Bytes: [{:3}, {:3}, {:3}, {:3}]", 
+                 data[mid_offset], data[mid_offset+1], data[mid_offset+2], data[mid_offset+3]);
     }
 }

crates/g3-computer-control/examples/list_windows.rs

@@ -1,9 +1,7 @@
-use core_foundation::base::{TCFType, ToVoid};
+use core_graphics::window::{kCGWindowListOptionOnScreenOnly, kCGNullWindowID, CGWindowListCopyWindowInfo};
 use core_foundation::dictionary::CFDictionary;
 use core_foundation::string::CFString;
-use core_graphics::window::{
-    kCGNullWindowID, kCGWindowListOptionOnScreenOnly, CGWindowListCopyWindowInfo,
-};
+use core_foundation::base::{TCFType, ToVoid};
 
 fn main() {
     println!("Listing all on-screen windows...");
@@ -11,14 +9,13 @@ fn main() {
     println!("{}", "-".repeat(80));
     
     unsafe {
-        let window_list =
-            CGWindowListCopyWindowInfo(kCGWindowListOptionOnScreenOnly, kCGNullWindowID);
+        let window_list = CGWindowListCopyWindowInfo(
+            kCGWindowListOptionOnScreenOnly,
+            kCGNullWindowID
+        );
         
-        let count =
-            core_foundation::array::CFArray::<CFDictionary>::wrap_under_create_rule(window_list)
-                .len();
-        let array =
-            core_foundation::array::CFArray::<CFDictionary>::wrap_under_create_rule(window_list);
+        let count = core_foundation::array::CFArray::<CFDictionary>::wrap_under_create_rule(window_list).len();
+        let array = core_foundation::array::CFArray::<CFDictionary>::wrap_under_create_rule(window_list);
         
         for i in 0..count {
             let dict = array.get(i).unwrap();
@@ -26,8 +23,7 @@ fn main() {
             // Get window ID
             let window_id_key = CFString::from_static_string("kCGWindowNumber");
             let window_id: i64 = if let Some(value) = dict.find(window_id_key.to_void()) {
-                let num: core_foundation::number::CFNumber =
-                    TCFType::wrap_under_get_rule(*value as *const _);
+                let num: core_foundation::number::CFNumber = TCFType::wrap_under_get_rule(*value as *const _);
                 num.to_i64().unwrap_or(0)
             } else {
                 0

crates/g3-computer-control/examples/macax_demo.rs

@@ -0,0 +1,74 @@
+//! Example demonstrating macOS Accessibility API tools
+//!
+//! This example shows how to use the macax tools to control macOS applications.
+//!
+//! Run with: cargo run --example macax_demo
+
+use anyhow::Result;
+use g3_computer_control::MacAxController;
+
+#[tokio::main]
+async fn main() -> Result<()> {
+    println!("🍎 macOS Accessibility API Demo\n");
+    println!("This demo shows how to control macOS applications using the Accessibility API.\n");
+    
+    // Create controller
+    let controller = MacAxController::new()?;
+    println!("✅ MacAxController initialized\n");
+    
+    // List running applications
+    println!("📱 Listing running applications:");
+    match controller.list_applications() {
+        Ok(apps) => {
+            for app in apps.iter().take(10) {
+                println!("  - {}", app.name);
+            }
+            if apps.len() > 10 {
+                println!("  ... and {} more", apps.len() - 10);
+            }
+        }
+        Err(e) => println!("  ❌ Error: {}", e),
+    }
+    println!();
+    
+    // Get frontmost app
+    println!("🎯 Getting frontmost application:");
+    match controller.get_frontmost_app() {
+        Ok(app) => println!("  Current: {}", app.name),
+        Err(e) => println!("  ❌ Error: {}", e),
+    }
+    println!();
+    
+    // Example: Activate Finder and get its UI tree
+    println!("📂 Activating Finder and inspecting UI:");
+    match controller.activate_app("Finder") {
+        Ok(_) => {
+            println!("  ✅ Finder activated");
+            
+            // Wait a moment for activation
+            tokio::time::sleep(tokio::time::Duration::from_millis(500)).await;
+            
+            // Get UI tree
+            match controller.get_ui_tree("Finder", 2) {
+                Ok(tree) => {
+                    println!("\n  UI Tree:");
+                    for line in tree.lines().take(10) {
+                        println!("    {}", line);
+                    }
+                }
+                Err(e) => println!("  ❌ Error getting UI tree: {}", e),
+            }
+        }
+        Err(e) => println!("  ❌ Error: {}", e),
+    }
+    println!();
+    
+    println!("✨ Demo complete!\n");
+    println!("💡 Tips:");
+    println!("  - Use --macax flag with g3 to enable these tools");
+    println!("  - Grant accessibility permissions in System Preferences");
+    println!("  - Add accessibility identifiers to your apps for easier automation");
+    println!("  - See docs/macax-tools.md for full documentation\n");
+    
+    Ok(())
+}

crates/g3-computer-control/examples/safari_demo.rs

@@ -1,6 +1,6 @@
-use anyhow::Result;
-use g3_computer_control::webdriver::WebDriverController;
 use g3_computer_control::SafariDriver;
+use g3_computer_control::webdriver::WebDriverController;
+use anyhow::Result;
 
 #[tokio::main]
 async fn main() -> Result<()> {
@@ -47,9 +47,7 @@ async fn main() -> Result<()> {
     
     // Execute JavaScript
     println!("Executing JavaScript...");
-    let result = driver
-        .execute_script("return document.title", vec![])
-        .await?;
+    let result = driver.execute_script("return document.title", vec![]).await?;
     println!("JS result: {:?}\n", result);
     
     // Take a screenshot

crates/g3-computer-control/examples/test_permission_prompt.rs

@@ -6,10 +6,7 @@ async fn main() {
     
     let controller = create_controller().expect("Failed to create controller");
     
-    match controller
-        .take_screenshot("/tmp/test_with_prompt.png", None, None)
-        .await
-    {
+    match controller.take_screenshot("/tmp/test_with_prompt.png", None, None).await {
         Ok(_) => {
             println!("\n✅ Screenshot saved to /tmp/test_with_prompt.png");
             println!("Opening screenshot...");

crates/g3-computer-control/examples/test_screencapture_direct.rs

@@ -22,11 +22,7 @@ fn main() {
                 
                 // Check file exists and size
                 if let Ok(metadata) = std::fs::metadata(path) {
-                    println!(
-                        "File size: {} bytes ({:.1} MB)",
-                        metadata.len(),
-                        metadata.len() as f64 / 1_000_000.0
-                    );
+                    println!("File size: {} bytes ({:.1} MB)", metadata.len(), metadata.len() as f64 / 1_000_000.0);
                 }
                 
                 // Open it

crates/g3-computer-control/examples/test_screenshot_fix.rs

@@ -11,15 +11,9 @@ fn main() {
     let data = image.data();
     
     println!("Testing screenshot fix...");
-    println!(
-        "Image: {}x{}, bytes_per_row: {}",
-        width, height, bytes_per_row
-    );
+    println!("Image: {}x{}, bytes_per_row: {}", width, height, bytes_per_row);
     println!("Expected bytes per row: {}", width * 4);
-    println!(
-        "Padding per row: {} bytes",
-        bytes_per_row - (width as usize * 4)
-    );
+    println!("Padding per row: {} bytes", bytes_per_row - (width as usize * 4));
     
     // OLD METHOD (broken) - treating data as continuous
     println!("\n=== OLD METHOD (BROKEN) ===");
@@ -54,11 +48,7 @@ fn main() {
     let crop_size = 200;
     
     // Old method crop
-    let old_crop: Vec<u8> = old_rgba
-        .iter()
-        .take((crop_size * crop_size * 4) as usize)
-        .copied()
-        .collect();
+    let old_crop: Vec<u8> = old_rgba.iter().take((crop_size * crop_size * 4) as usize).copied().collect();
     if let Some(old_img) = ImageBuffer::from_raw(crop_size, crop_size, old_crop) {
         let old_img: RgbaImage = old_img;
         old_img.save("/tmp/screenshot_old_method.png").unwrap();
@@ -66,11 +56,7 @@ fn main() {
     }
     
     // New method crop
-    let new_crop: Vec<u8> = new_rgba
-        .iter()
-        .take((crop_size * crop_size * 4) as usize)
-        .copied()
-        .collect();
+    let new_crop: Vec<u8> = new_rgba.iter().take((crop_size * crop_size * 4) as usize).copied().collect();
     if let Some(new_img) = ImageBuffer::from_raw(crop_size, crop_size, new_crop) {
         let new_img: RgbaImage = new_img;
         new_img.save("/tmp/screenshot_new_method.png").unwrap();

crates/g3-computer-control/examples/test_type_text.rs

@@ -0,0 +1,48 @@
+//! Test the new type_text functionality
+
+use anyhow::Result;
+use g3_computer_control::MacAxController;
+
+#[tokio::main]
+async fn main() -> Result<()> {
+    println!("🧪 Testing macax type_text functionality\n");
+    
+    let controller = MacAxController::new()?;
+    println!("✅ Controller initialized\n");
+    
+    // Test 1: Type simple text
+    println!("Test 1: Typing simple text into TextEdit");
+    println!("  Please open TextEdit and create a new document...");
+    std::thread::sleep(std::time::Duration::from_secs(3));
+    
+    match controller.type_text("TextEdit", "Hello, World!") {
+        Ok(_) => println!("  ✅ Successfully typed simple text\n"),
+        Err(e) => println!("  ❌ Failed: {}\n", e),
+    }
+    
+    std::thread::sleep(std::time::Duration::from_secs(1));
+    
+    // Test 2: Type unicode and emojis
+    println!("Test 2: Typing unicode and emojis");
+    match controller.type_text("TextEdit", "\n🌟 Unicode test: café, naïve, 日本語 🎉") {
+        Ok(_) => println!("  ✅ Successfully typed unicode text\n"),
+        Err(e) => println!("  ❌ Failed: {}\n", e),
+    }
+    
+    std::thread::sleep(std::time::Duration::from_secs(1));
+    
+    // Test 3: Type special characters
+    println!("Test 3: Typing special characters");
+    match controller.type_text("TextEdit", "\nSpecial: @#$%^&*()_+-=[]{}|;':,.<>?/") {
+        Ok(_) => println!("  ✅ Successfully typed special characters\n"),
+        Err(e) => println!("  ❌ Failed: {}\n", e),
+    }
+    
+    println!("\n✨ Tests complete!");
+    println!("\n💡 Now try with Things3:");
+    println!("   1. Open Things3");
+    println!("   2. Press Cmd+N to create a new task");
+    println!("   3. Run: g3 --macax 'type \"🌟 My awesome task\" into Things'");
+    
+    Ok(())
+}

crates/g3-computer-control/examples/test_vision.rs

@@ -0,0 +1,85 @@
+use g3_computer_control::ocr::{OCREngine, DefaultOCR};
+use anyhow::Result;
+
+#[tokio::main]
+async fn main() -> Result<()> {
+    println!("🧪 Testing Apple Vision OCR");
+    println!("===========================\n");
+    
+    // Initialize OCR engine
+    println!("📦 Initializing OCR engine...");
+    let ocr = DefaultOCR::new()?;
+    println!("✅ OCR engine: {}\n", ocr.name());
+    
+    // Check if test image exists
+    let test_image = "/tmp/safari_test.png";
+    if !std::path::Path::new(test_image).exists() {
+        println!("⚠️  Test image not found: {}", test_image);
+        println!("   Creating a screenshot...");
+        
+        let status = std::process::Command::new("screencapture")
+            .arg("-x")
+            .arg("-R")
+            .arg("0,0,1200,800")
+            .arg(test_image)
+            .status()?;
+        
+        if !status.success() {
+            anyhow::bail!("Failed to create screenshot");
+        }
+        
+        println!("✅ Screenshot created\n");
+    }
+    
+    // Run OCR
+    println!("🔍 Running Apple Vision OCR on {}...", test_image);
+    let start = std::time::Instant::now();
+    let locations = ocr.extract_text_with_locations(test_image).await?;
+    let duration = start.elapsed();
+    
+    println!("✅ OCR completed in {:.3}s\n", duration.as_secs_f64());
+    
+    // Display results
+    println!("📊 Results:");
+    println!("   Found {} text elements\n", locations.len());
+    
+    if locations.is_empty() {
+        println!("⚠️  No text found in image");
+    } else {
+        println!("   Top 20 results:");
+        println!("   {:<4} {:<40} {:<15} {:<12} {:<8}", "#", "Text", "Position", "Size", "Conf");
+        println!("   {}", "-".repeat(85));
+        
+        for (i, loc) in locations.iter().take(20).enumerate() {
+            let text = if loc.text.len() > 37 {
+                format!("{}...", &loc.text[..37])
+            } else {
+                loc.text.clone()
+            };
+            
+            println!("   {:<4} {:<40} ({:>4},{:>4})    {:>4}x{:<4}  {:.2}",
+                i + 1,
+                text,
+                loc.x,
+                loc.y,
+                loc.width,
+                loc.height,
+                loc.confidence
+            );
+        }
+        
+        if locations.len() > 20 {
+            println!("\n   ... and {} more", locations.len() - 20);
+        }
+        
+        // Performance comparison
+        println!("\n📈 Performance:");
+        println!("   OCR Speed: {:.3}s", duration.as_secs_f64());
+        println!("   Text elements: {}", locations.len());
+        println!("   Avg per element: {:.1}ms", duration.as_millis() as f64 / locations.len() as f64);
+    }
+    
+    println!("\n✅ Test complete!");
+    
+    Ok(())
+}

crates/g3-computer-control/examples/test_window_capture.rs

@@ -8,15 +8,10 @@ async fn main() {
     
     // Test 1: Capture iTerm2 window
     println!("\n1. Capturing iTerm2 window...");
-    match controller
-        .take_screenshot("/tmp/iterm_window.png", None, Some("iTerm2"))
-        .await
-    {
+    match controller.take_screenshot("/tmp/iterm_window.png", None, Some("iTerm2")).await {
         Ok(_) => {
             println!("   ✅ iTerm2 window captured to /tmp/iterm_window.png");
-            let _ = std::process::Command::new("open")
-                .arg("/tmp/iterm_window.png")
-                .spawn();
+            let _ = std::process::Command::new("open").arg("/tmp/iterm_window.png").spawn();
         }
         Err(e) => println!("   ❌ Failed: {}", e),
     }
@@ -26,15 +21,10 @@ async fn main() {
     
     // Test 2: Full screen capture for comparison
     println!("\n2. Capturing full screen for comparison...");
-    match controller
-        .take_screenshot("/tmp/fullscreen.png", None, None)
-        .await
-    {
+    match controller.take_screenshot("/tmp/fullscreen.png", None, None).await {
         Ok(_) => {
             println!("   ✅ Full screen captured to /tmp/fullscreen.png");
-            let _ = std::process::Command::new("open")
-                .arg("/tmp/fullscreen.png")
-                .spawn();
+            let _ = std::process::Command::new("open").arg("/tmp/fullscreen.png").spawn();
         }
         Err(e) => println!("   ❌ Failed: {}", e),
     }

crates/g3-computer-control/src/lib.rs

@@ -1,15 +1,17 @@
 // Suppress warnings from objc crate macros
 #![allow(unexpected_cfgs)]
 
-pub mod platform;
 pub mod types;
+pub mod platform;
+pub mod ocr;
 pub mod webdriver;
+pub mod macax;
 
 // Re-export webdriver types for convenience
-pub use webdriver::{
-    chrome::ChromeDriver, safari::SafariDriver, WebDriverController, WebElement,
-    diagnostics::{run_diagnostics as run_chrome_diagnostics, ChromeDiagnosticReport, DiagnosticStatus},
-};
+pub use webdriver::{WebDriverController, WebElement, safari::SafariDriver};
+
+// Re-export macax types for convenience
+pub use macax::{MacAxController, AXElement, AXApplication};
 
 use anyhow::Result;
 use async_trait::async_trait;
@@ -18,12 +20,17 @@ use types::*;
 #[async_trait]
 pub trait ComputerController: Send + Sync {
     // Screen capture
-    async fn take_screenshot(
-        &self,
-        path: &str,
-        region: Option<Rect>,
-        window_id: Option<&str>,
-    ) -> Result<()>;
+    async fn take_screenshot(&self, path: &str, region: Option<Rect>, window_id: Option<&str>) -> Result<()>;
+    
+    // OCR operations
+    async fn extract_text_from_screen(&self, region: Rect, window_id: &str) -> Result<String>;
+    async fn extract_text_from_image(&self, path: &str) -> Result<String>;
+    async fn extract_text_with_locations(&self, path: &str) -> Result<Vec<TextLocation>>;
+    async fn find_text_in_app(&self, app_name: &str, search_text: &str) -> Result<Option<TextLocation>>;
+    
+    // Mouse operations
+    fn move_mouse(&self, x: i32, y: i32) -> Result<()>;
+    fn click_at(&self, x: i32, y: i32, app_name: Option<&str>) -> Result<()>;
 }
 
 // Platform-specific constructor

crates/g3-computer-control/src/macax/controller.rs

@@ -0,0 +1,822 @@
+use super::{AXApplication, AXElement};
+use anyhow::{Context, Result};
+use std::collections::HashMap;
+
+#[cfg(target_os = "macos")]
+use accessibility::{AXUIElement, AXUIElementAttributes, ElementFinder, TreeVisitor, TreeWalker, TreeWalkerFlow};
+
+#[cfg(target_os = "macos")]
+use core_foundation::base::TCFType;
+
+#[cfg(target_os = "macos")]
+use core_foundation::string::CFString;
+
+/// macOS Accessibility API controller using native APIs
+pub struct MacAxController {
+    // Cache for application elements
+    app_cache: std::sync::Mutex<HashMap<String, AXUIElement>>,
+}
+
+impl MacAxController {
+    pub fn new() -> Result<Self> {
+        #[cfg(target_os = "macos")]
+        {
+            // Check if we have accessibility permissions by trying to get system-wide element
+            let _system = AXUIElement::system_wide();
+            
+            Ok(Self {
+                app_cache: std::sync::Mutex::new(HashMap::new()),
+            })
+        }
+        
+        #[cfg(not(target_os = "macos"))]
+        {
+            anyhow::bail!("macOS Accessibility API is only available on macOS")
+        }
+    }
+    
+    /// List all running applications
+    #[cfg(target_os = "macos")]
+    pub fn list_applications(&self) -> Result<Vec<AXApplication>> {
+        let apps = Self::get_running_applications()?;
+        Ok(apps)
+    }
+    
+    #[cfg(not(target_os = "macos"))]
+    pub fn list_applications(&self) -> Result<Vec<AXApplication>> {
+        anyhow::bail!("Not supported on this platform")
+    }
+    
+    #[cfg(target_os = "macos")]
+    fn get_running_applications() -> Result<Vec<AXApplication>> {
+        use cocoa::appkit::NSApplicationActivationPolicy;
+        use cocoa::base::{id, nil};
+        use objc::{class, msg_send, sel, sel_impl};
+        
+        unsafe {
+            let workspace: id = msg_send![class!(NSWorkspace), sharedWorkspace];
+            let running_apps: id = msg_send![workspace, runningApplications];
+            let count: usize = msg_send![running_apps, count];
+            
+            let mut apps = Vec::new();
+            
+            for i in 0..count {
+                let app: id = msg_send![running_apps, objectAtIndex: i];
+                
+                // Get app name
+                let localized_name: id = msg_send![app, localizedName];
+                if localized_name == nil {
+                    continue;
+                }
+                let name_ptr: *const i8 = msg_send![localized_name, UTF8String];
+                let name = if !name_ptr.is_null() {
+                    std::ffi::CStr::from_ptr(name_ptr)
+                        .to_string_lossy()
+                        .to_string()
+                } else {
+                    continue;
+                };
+                
+                // Get bundle ID
+                let bundle_id_obj: id = msg_send![app, bundleIdentifier];
+                let bundle_id = if bundle_id_obj != nil {
+                    let bundle_id_ptr: *const i8 = msg_send![bundle_id_obj, UTF8String];
+                    if !bundle_id_ptr.is_null() {
+                        Some(
+                            std::ffi::CStr::from_ptr(bundle_id_ptr)
+                                .to_string_lossy()
+                                .to_string(),
+                        )
+                    } else {
+                        None
+                    }
+                } else {
+                    None
+                };
+                
+                // Get PID
+                let pid: i32 = msg_send![app, processIdentifier];
+                
+                // Skip background-only apps
+                let activation_policy: i64 = msg_send![app, activationPolicy];
+                if activation_policy == NSApplicationActivationPolicy::NSApplicationActivationPolicyRegular as i64 {
+                    apps.push(AXApplication {
+                        name,
+                        bundle_id,
+                        pid,
+                    });
+                }
+            }
+            
+            Ok(apps)
+        }
+    }
+    
+    /// Get the frontmost (active) application
+    #[cfg(target_os = "macos")]
+    pub fn get_frontmost_app(&self) -> Result<AXApplication> {
+        use cocoa::base::{id, nil};
+        use objc::{class, msg_send, sel, sel_impl};
+        
+        unsafe {
+            let workspace: id = msg_send![class!(NSWorkspace), sharedWorkspace];
+            let frontmost_app: id = msg_send![workspace, frontmostApplication];
+            
+            if frontmost_app == nil {
+                anyhow::bail!("No frontmost application");
+            }
+            
+            // Get app name
+            let localized_name: id = msg_send![frontmost_app, localizedName];
+            let name_ptr: *const i8 = msg_send![localized_name, UTF8String];
+            let name = std::ffi::CStr::from_ptr(name_ptr)
+                .to_string_lossy()
+                .to_string();
+            
+            // Get bundle ID
+            let bundle_id_obj: id = msg_send![frontmost_app, bundleIdentifier];
+            let bundle_id = if bundle_id_obj != nil {
+                let bundle_id_ptr: *const i8 = msg_send![bundle_id_obj, UTF8String];
+                if !bundle_id_ptr.is_null() {
+                    Some(
+                        std::ffi::CStr::from_ptr(bundle_id_ptr)
+                            .to_string_lossy()
+                            .to_string(),
+                    )
+                } else {
+                    None
+                }
+            } else {
+                None
+            };
+            
+            // Get PID
+            let pid: i32 = msg_send![frontmost_app, processIdentifier];
+            
+            Ok(AXApplication {
+                name,
+                bundle_id,
+                pid,
+            })
+        }
+    }
+    
+    #[cfg(not(target_os = "macos"))]
+    pub fn get_frontmost_app(&self) -> Result<AXApplication> {
+        anyhow::bail!("Not supported on this platform")
+    }
+    
+    /// Get AXUIElement for an application by name or PID
+    #[cfg(target_os = "macos")]
+    fn get_app_element(&self, app_name: &str) -> Result<AXUIElement> {
+        // Check cache first
+        {
+            let cache = self.app_cache.lock().unwrap();
+            if let Some(element) = cache.get(app_name) {
+                return Ok(element.clone());
+            }
+        }
+        
+        // Find the app by name
+        let apps = Self::get_running_applications()?;
+        let app = apps
+            .iter()
+            .find(|a| a.name == app_name)
+            .ok_or_else(|| anyhow::anyhow!("Application '{}' not found", app_name))?;
+        
+        // Create AXUIElement for the app
+        let element = AXUIElement::application(app.pid);
+        
+        // Cache it
+        {
+            let mut cache = self.app_cache.lock().unwrap();
+            cache.insert(app_name.to_string(), element.clone());
+        }
+        
+        Ok(element)
+    }
+    
+    /// Activate (bring to front) an application
+    #[cfg(target_os = "macos")]
+    pub fn activate_app(&self, app_name: &str) -> Result<()> {
+        use cocoa::base::id;
+        use objc::{class, msg_send, sel, sel_impl};
+        
+        // Find the app
+        let apps = Self::get_running_applications()?;
+        let app = apps
+            .iter()
+            .find(|a| a.name == app_name)
+            .ok_or_else(|| anyhow::anyhow!("Application '{}' not found", app_name))?;
+        
+        unsafe {
+            let workspace: id = msg_send![class!(NSWorkspace), sharedWorkspace];
+            let running_apps: id = msg_send![workspace, runningApplications];
+            let count: usize = msg_send![running_apps, count];
+            
+            for i in 0..count {
+                let running_app: id = msg_send![running_apps, objectAtIndex: i];
+                let pid: i32 = msg_send![running_app, processIdentifier];
+                
+                if pid == app.pid {
+                    let _: bool = msg_send![running_app, activateWithOptions: 0];
+                    return Ok(());
+                }
+            }
+        }
+        
+        anyhow::bail!("Failed to activate application")
+    }
+    
+    #[cfg(not(target_os = "macos"))]
+    pub fn activate_app(&self, _app_name: &str) -> Result<()> {
+        anyhow::bail!("Not supported on this platform")
+    }
+    
+    /// Get the UI hierarchy of an application
+    #[cfg(target_os = "macos")]
+    pub fn get_ui_tree(&self, app_name: &str, max_depth: usize) -> Result<String> {
+        let app_element = self.get_app_element(app_name)?;
+        let mut output = format!("Application: {}\n", app_name);
+        
+        Self::build_ui_tree(&app_element, &mut output, 0, max_depth)?;
+        
+        Ok(output)
+    }
+    
+    #[cfg(not(target_os = "macos"))]
+    pub fn get_ui_tree(&self, _app_name: &str, _max_depth: usize) -> Result<String> {
+        anyhow::bail!("Not supported on this platform")
+    }
+    
+    #[cfg(target_os = "macos")]
+    fn build_ui_tree(
+        element: &AXUIElement,
+        output: &mut String,
+        depth: usize,
+        max_depth: usize,
+    ) -> Result<()> {
+        if depth >= max_depth {
+            return Ok(());
+        }
+        
+        let indent = "  ".repeat(depth);
+        
+        // Get role
+        let role = element.role().ok().map(|s| s.to_string())
+            .unwrap_or_else(|| "Unknown".to_string());
+        
+        // Get title
+        let title = element.title().ok()
+            .map(|s| s.to_string());
+        
+        // Get identifier
+        let identifier = element.identifier().ok()
+            .map(|s| s.to_string());
+        
+        // Format output
+        output.push_str(&format!("{}Role: {}", indent, role));
+        if let Some(t) = title {
+            output.push_str(&format!(", Title: {}", t));
+        }
+        if let Some(id) = identifier {
+            output.push_str(&format!(", ID: {}", id));
+        }
+        output.push('\n');
+        
+        // Get children
+        if let Ok(children) = element.children() {
+            for i in 0..children.len() {
+                if let Some(child) = children.get(i) {
+                    let _ = Self::build_ui_tree(&child, output, depth + 1, max_depth);
+                }
+            }
+        }
+        
+        Ok(())
+    }
+    
+    /// Find UI elements in an application
+    #[cfg(target_os = "macos")]
+    pub fn find_elements(
+        &self,
+        app_name: &str,
+        role: Option<&str>,
+        title: Option<&str>,
+        identifier: Option<&str>,
+    ) -> Result<Vec<AXElement>> {
+        let app_element = self.get_app_element(app_name)?;
+        let mut found_elements = Vec::new();
+        
+        let visitor = ElementCollector {
+            role_filter: role.map(|s| s.to_string()),
+            title_filter: title.map(|s| s.to_string()),
+            identifier_filter: identifier.map(|s| s.to_string()),
+            results: std::cell::RefCell::new(&mut found_elements),
+            depth: std::cell::Cell::new(0),
+        };
+        
+        let walker = TreeWalker::new();
+        walker.walk(&app_element, &visitor);
+        
+        Ok(found_elements)
+    }
+    
+    #[cfg(not(target_os = "macos"))]
+    pub fn find_elements(
+        &self,
+        _app_name: &str,
+        _role: Option<&str>,
+        _title: Option<&str>,
+        _identifier: Option<&str>,
+    ) -> Result<Vec<AXElement>> {
+        anyhow::bail!("Not supported on this platform")
+    }
+    
+    /// Find a single element (helper for click, set_value, etc.)
+    #[cfg(target_os = "macos")]
+    fn find_element(
+        &self,
+        app_name: &str,
+        role: &str,
+        title: Option<&str>,
+        identifier: Option<&str>,
+    ) -> Result<AXUIElement> {
+        let app_element = self.get_app_element(app_name)?;
+        
+        let role_str = role.to_string();
+        let title_str = title.map(|s| s.to_string());
+        let identifier_str = identifier.map(|s| s.to_string());
+        
+        let finder = ElementFinder::new(
+            &app_element,
+            move |element| {
+                // Check role
+                let elem_role = element.role()
+                    .ok()
+                    .map(|s| s.to_string());
+                
+                if let Some(r) = elem_role {
+                    if !r.contains(&role_str) {
+                        return false;
+                    }
+                } else {
+                    return false;
+                }
+                
+                // Check title if specified
+                if let Some(ref title_filter) = title_str {
+                    let elem_title = element.title()
+                        .ok()
+                        .map(|s| s.to_string());
+                    
+                    if let Some(t) = elem_title {
+                        if !t.contains(title_filter) {
+                            return false;
+                        }
+                    } else {
+                        return false;
+                    }
+                }
+                
+                // Check identifier if specified
+                if let Some(ref id_filter) = identifier_str {
+                    let elem_id = element.identifier()
+                        .ok()
+                        .map(|s| s.to_string());
+                    
+                    if let Some(id) = elem_id {
+                        if !id.contains(id_filter) {
+                            return false;
+                        }
+                    } else {
+                        return false;
+                    }
+                }
+                
+                true
+            },
+            Some(std::time::Duration::from_secs(2)),
+        );
+        
+        finder.find().context("Element not found")
+    }
+    
+    /// Click on a UI element
+    #[cfg(target_os = "macos")]
+    pub fn click_element(
+        &self,
+        app_name: &str,
+        role: &str,
+        title: Option<&str>,
+        identifier: Option<&str>,
+    ) -> Result<()> {
+        let element = self.find_element(app_name, role, title, identifier)?;
+        
+        // Perform the press action
+        let action_name = CFString::new("AXPress");
+        element
+            .perform_action(&action_name)
+            .map_err(|e| anyhow::anyhow!("Failed to perform press action: {:?}", e))?;
+        
+        Ok(())
+    }
+    
+    #[cfg(not(target_os = "macos"))]
+    pub fn click_element(
+        &self,
+        _app_name: &str,
+        _role: &str,
+        _title: Option<&str>,
+        _identifier: Option<&str>,
+    ) -> Result<()> {
+        anyhow::bail!("Not supported on this platform")
+    }
+    
+    /// Set the value of a UI element
+    #[cfg(target_os = "macos")]
+    pub fn set_value(
+        &self,
+        app_name: &str,
+        role: &str,
+        value: &str,
+        title: Option<&str>,
+        identifier: Option<&str>,
+    ) -> Result<()> {
+        let element = self.find_element(app_name, role, title, identifier)?;
+        
+        // Set the value - convert CFString to CFType
+        let cf_value = CFString::new(value);
+        
+        element.set_value(cf_value.as_CFType())
+            .map_err(|e| anyhow::anyhow!("Failed to set value: {:?}", e))?;
+        
+        Ok(())
+    }
+    
+    #[cfg(not(target_os = "macos"))]
+    pub fn set_value(
+        &self,
+        _app_name: &str,
+        _role: &str,
+        _value: &str,
+        _title: Option<&str>,
+        _identifier: Option<&str>,
+    ) -> Result<()> {
+        anyhow::bail!("Not supported on this platform")
+    }
+    
+    /// Get the value of a UI element
+    #[cfg(target_os = "macos")]
+    pub fn get_value(
+        &self,
+        app_name: &str,
+        role: &str,
+        title: Option<&str>,
+        identifier: Option<&str>,
+    ) -> Result<String> {
+        let element = self.find_element(app_name, role, title, identifier)?;
+        
+        // Get the value
+        let value_type = element.value()
+            .map_err(|e| anyhow::anyhow!("Failed to get value: {:?}", e))?;
+        
+        // Try to downcast to CFString
+        if let Some(cf_string) = value_type.downcast::<CFString>() {
+            Ok(cf_string.to_string())
+        } else {
+            // For non-string values, try to get a description
+            Ok(format!("<non-string value>"))
+        }
+    }
+    
+    #[cfg(not(target_os = "macos"))]
+    pub fn get_value(
+        &self,
+        _app_name: &str,
+        _role: &str,
+        _title: Option<&str>,
+        _identifier: Option<&str>,
+    ) -> Result<String> {
+        anyhow::bail!("Not supported on this platform")
+    }
+    
+    /// Type text into the currently focused element (uses system text input)
+    #[cfg(target_os = "macos")]
+    pub fn type_text(&self, app_name: &str, text: &str) -> Result<()> {
+        use cocoa::base::{id, nil};
+        use cocoa::foundation::NSString;
+        use objc::{class, msg_send, sel, sel_impl};
+        
+        // First, make sure the app is active
+        self.activate_app(app_name)?;
+        
+        // Wait for app to fully activate
+        std::thread::sleep(std::time::Duration::from_millis(500));
+        
+        // Send a Tab key to try to focus on a text field
+        // This helps ensure something is focused before we paste
+        let _ = self.press_key(app_name, "tab", vec![]);
+        std::thread::sleep(std::time::Duration::from_millis(800));
+        
+        // Save old clipboard, set new content, paste, then restore
+        let old_content: id;
+        unsafe {
+            // Get the general pasteboard
+            let pasteboard: id = msg_send![class!(NSPasteboard), generalPasteboard];
+            
+            // Save current clipboard content
+            let ns_string_type = NSString::alloc(nil).init_str("public.utf8-plain-text");
+            old_content = msg_send![pasteboard, stringForType: ns_string_type];
+            
+            // Clear and set new content
+            let _: () = msg_send![pasteboard, clearContents];
+            
+            let ns_string = NSString::alloc(nil).init_str(text);
+            let ns_type = NSString::alloc(nil).init_str("public.utf8-plain-text");
+            let _: bool = msg_send![pasteboard, setString:ns_string forType:ns_type];
+        }
+        
+        // Wait a moment for clipboard to update
+        std::thread::sleep(std::time::Duration::from_millis(200));
+        
+        // Paste using Cmd+V (outside unsafe block)
+        self.press_key(app_name, "v", vec!["command"])?;
+        
+        // Wait for paste to complete
+        std::thread::sleep(std::time::Duration::from_millis(300));
+        
+        // Restore old clipboard content if it existed
+        unsafe {
+            if old_content != nil {
+                let pasteboard: id = msg_send![class!(NSPasteboard), generalPasteboard];
+                let _: () = msg_send![pasteboard, clearContents];
+                let ns_type = NSString::alloc(nil).init_str("public.utf8-plain-text");
+                let _: bool = msg_send![pasteboard, setString:old_content forType:ns_type];
+            }
+        }
+        
+        Ok(())
+    }
+    
+    #[cfg(not(target_os = "macos"))]
+    pub fn type_text(&self, _app_name: &str, _text: &str) -> Result<()> {
+        anyhow::bail!("Not supported on this platform")
+    }
+    
+    /// Focus on a text field or text area element
+    #[cfg(target_os = "macos")]
+    pub fn focus_element(
+        &self,
+        app_name: &str,
+        role: &str,
+        title: Option<&str>,
+        identifier: Option<&str>,
+    ) -> Result<()> {
+        let element = self.find_element(app_name, role, title, identifier)?;
+        
+        // Set focused attribute to true
+        use core_foundation::boolean::CFBoolean;
+        let cf_true = CFBoolean::true_value();
+        
+        element.set_attribute(&accessibility::AXAttribute::focused(), cf_true)
+            .map_err(|e| anyhow::anyhow!("Failed to focus element: {:?}", e))?;
+        
+        Ok(())
+    }
+    
+    /// Press a keyboard shortcut
+    #[cfg(target_os = "macos")]
+    pub fn press_key(
+        &self,
+        app_name: &str,
+        key: &str,
+        modifiers: Vec<&str>,
+    ) -> Result<()> {
+        use core_graphics::event::{
+            CGEvent, CGEventFlags, CGEventTapLocation,
+        };
+        use core_graphics::event_source::{CGEventSource, CGEventSourceStateID};
+        
+        // First, make sure the app is active
+        self.activate_app(app_name)?;
+        
+        // Wait a bit for activation
+        std::thread::sleep(std::time::Duration::from_millis(100));
+        
+        // Map key string to key code
+        let key_code = Self::key_to_keycode(key)
+            .ok_or_else(|| anyhow::anyhow!("Unknown key: {}", key))?;
+        
+        // Map modifiers to flags
+        let mut flags = CGEventFlags::CGEventFlagNull;
+        for modifier in modifiers {
+            match modifier.to_lowercase().as_str() {
+                "command" | "cmd" => flags |= CGEventFlags::CGEventFlagCommand,
+                "option" | "alt" => flags |= CGEventFlags::CGEventFlagAlternate,
+                "control" | "ctrl" => flags |= CGEventFlags::CGEventFlagControl,
+                "shift" => flags |= CGEventFlags::CGEventFlagShift,
+                _ => {}
+            }
+        }
+        
+        // Create event source
+        let source = CGEventSource::new(CGEventSourceStateID::HIDSystemState)
+            .ok().context("Failed to create event source")?;
+        
+        // Create key down event
+        let key_down = CGEvent::new_keyboard_event(source.clone(), key_code, true)
+            .ok().context("Failed to create key down event")?;
+        key_down.set_flags(flags);
+        
+        // Create key up event
+        let key_up = CGEvent::new_keyboard_event(source, key_code, false)
+            .ok().context("Failed to create key up event")?;
+        key_up.set_flags(flags);
+        
+        // Post events
+        key_down.post(CGEventTapLocation::HID);
+        std::thread::sleep(std::time::Duration::from_millis(50));
+        key_up.post(CGEventTapLocation::HID);
+        
+        Ok(())
+    }
+    
+    #[cfg(not(target_os = "macos"))]
+    pub fn press_key(
+        &self,
+        _app_name: &str,
+        _key: &str,
+        _modifiers: Vec<&str>,
+    ) -> Result<()> {
+        anyhow::bail!("Not supported on this platform")
+    }
+    
+    #[cfg(target_os = "macos")]
+    fn key_to_keycode(key: &str) -> Option<u16> {
+        // Map common keys to keycodes
+        // See: https://eastmanreference.com/complete-list-of-applescript-key-codes
+        match key.to_lowercase().as_str() {
+            "a" => Some(0x00),
+            "s" => Some(0x01),
+            "d" => Some(0x02),
+            "f" => Some(0x03),
+            "h" => Some(0x04),
+            "g" => Some(0x05),
+            "z" => Some(0x06),
+            "x" => Some(0x07),
+            "c" => Some(0x08),
+            "v" => Some(0x09),
+            "b" => Some(0x0B),
+            "q" => Some(0x0C),
+            "w" => Some(0x0D),
+            "e" => Some(0x0E),
+            "r" => Some(0x0F),
+            "y" => Some(0x10),
+            "t" => Some(0x11),
+            "1" => Some(0x12),
+            "2" => Some(0x13),
+            "3" => Some(0x14),
+            "4" => Some(0x15),
+            "6" => Some(0x16),
+            "5" => Some(0x17),
+            "=" => Some(0x18),
+            "9" => Some(0x19),
+            "7" => Some(0x1A),
+            "-" => Some(0x1B),
+            "8" => Some(0x1C),
+            "0" => Some(0x1D),
+            "]" => Some(0x1E),
+            "o" => Some(0x1F),
+            "u" => Some(0x20),
+            "[" => Some(0x21),
+            "i" => Some(0x22),
+            "p" => Some(0x23),
+            "return" | "enter" => Some(0x24),
+            "l" => Some(0x25),
+            "j" => Some(0x26),
+            "'" => Some(0x27),
+            "k" => Some(0x28),
+            ";" => Some(0x29),
+            "\\" => Some(0x2A),
+            "," => Some(0x2B),
+            "/" => Some(0x2C),
+            "n" => Some(0x2D),
+            "m" => Some(0x2E),
+            "." => Some(0x2F),
+            "tab" => Some(0x30),
+            "space" => Some(0x31),
+            "`" => Some(0x32),
+            "delete" | "backspace" => Some(0x33),
+            "escape" | "esc" => Some(0x35),
+            "f1" => Some(0x7A),
+            "f2" => Some(0x78),
+            "f3" => Some(0x63),
+            "f4" => Some(0x76),
+            "f5" => Some(0x60),
+            "f6" => Some(0x61),
+            "f7" => Some(0x62),
+            "f8" => Some(0x64),
+            "f9" => Some(0x65),
+            "f10" => Some(0x6D),
+            "f11" => Some(0x67),
+            "f12" => Some(0x6F),
+            "left" => Some(0x7B),
+            "right" => Some(0x7C),
+            "down" => Some(0x7D),
+            "up" => Some(0x7E),
+            _ => None,
+        }
+    }
+}
+
+#[cfg(target_os = "macos")]
+struct ElementCollector<'a> {
+    role_filter: Option<String>,
+    title_filter: Option<String>,
+    identifier_filter: Option<String>,
+    results: std::cell::RefCell<&'a mut Vec<AXElement>>,
+    depth: std::cell::Cell<usize>,
+}
+
+#[cfg(target_os = "macos")]
+impl<'a> TreeVisitor for ElementCollector<'a> {
+    fn enter_element(&self, element: &AXUIElement) -> TreeWalkerFlow {
+        self.depth.set(self.depth.get() + 1);
+        
+        if self.depth.get() > 20 {
+            return TreeWalkerFlow::SkipSubtree;
+        }
+        
+        // Get element properties
+        let role = element.role()
+            .ok()
+            .map(|s| s.to_string())
+            .unwrap_or_else(|| "Unknown".to_string());
+        
+        let title = element.title()
+            .ok()
+            .map(|s| s.to_string());
+        
+        let identifier = element.identifier()
+            .ok()
+            .map(|s| s.to_string());
+        
+        // Check if this element matches the filters
+        let role_matches = self.role_filter.as_ref().map_or(true, |r| role.contains(r));
+        let title_matches = self.title_filter.as_ref().map_or(true, |t| {
+            title.as_ref().map_or(false, |title_str| title_str.contains(t))
+        });
+        let identifier_matches = self.identifier_filter.as_ref().map_or(true, |id| {
+            identifier.as_ref().map_or(false, |id_str| id_str.contains(id))
+        });
+        
+        if role_matches && title_matches && identifier_matches {
+            // Get additional properties
+            let value = element.value()
+                .ok()
+                .and_then(|v| {
+                    v.downcast::<CFString>().map(|s| s.to_string())
+                });
+            
+            let label = element.description()
+                .ok()
+                .map(|s| s.to_string());
+            
+            let enabled = element.enabled()
+                .ok()
+                .map(|b| b.into())
+                .unwrap_or(false);
+            
+            let focused = element.focused()
+                .ok()
+                .map(|b| b.into())
+                .unwrap_or(false);
+            
+            // Count children
+            let children_count = element.children()
+                .ok()
+                .map(|arr| arr.len() as usize)
+                .unwrap_or(0);
+            
+            self.results.borrow_mut().push(AXElement {
+                role,
+                title,
+                value,
+                label,
+                identifier,
+                enabled,
+                focused,
+                position: None,
+                size: None,
+                children_count,
+            });
+        }
+        
+        TreeWalkerFlow::Continue
+    }
+    
+    fn exit_element(&self, _element: &AXUIElement) {
+        self.depth.set(self.depth.get() - 1);
+    }
+}

crates/g3-computer-control/src/macax/mod.rs

@@ -0,0 +1,65 @@
+pub mod controller;
+
+pub use controller::MacAxController;
+
+use serde::{Deserialize, Serialize};
+
+#[cfg(test)]
+mod tests;
+
+/// Represents an accessibility element in the UI hierarchy
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct AXElement {
+    pub role: String,
+    pub title: Option<String>,
+    pub value: Option<String>,
+    pub label: Option<String>,
+    pub identifier: Option<String>,
+    pub enabled: bool,
+    pub focused: bool,
+    pub position: Option<(f64, f64)>,
+    pub size: Option<(f64, f64)>,
+    pub children_count: usize,
+}
+
+/// Represents a macOS application
+#[derive(Debug, Clone)]
+pub struct AXApplication {
+    pub name: String,
+    pub bundle_id: Option<String>,
+    pub pid: i32,
+}
+
+impl AXElement {
+    /// Convert to a human-readable string representation
+    pub fn to_string(&self) -> String {
+        let mut parts = vec![format!("Role: {}", self.role)];
+        
+        if let Some(ref title) = self.title {
+            parts.push(format!("Title: {}", title));
+        }
+        if let Some(ref value) = self.value {
+            parts.push(format!("Value: {}", value));
+        }
+        if let Some(ref label) = self.label {
+            parts.push(format!("Label: {}", label));
+        }
+        if let Some(ref id) = self.identifier {
+            parts.push(format!("ID: {}", id));
+        }
+        
+        parts.push(format!("Enabled: {}", self.enabled));
+        parts.push(format!("Focused: {}", self.focused));
+        
+        if let Some((x, y)) = self.position {
+            parts.push(format!("Position: ({:.0}, {:.0})", x, y));
+        }
+        if let Some((w, h)) = self.size {
+            parts.push(format!("Size: ({:.0}, {:.0})", w, h));
+        }
+        
+        parts.push(format!("Children: {}", self.children_count));
+        
+        parts.join(", ")
+    }
+}

crates/g3-computer-control/src/macax/tests.rs

@@ -0,0 +1,37 @@
+#[cfg(test)]
+mod tests {
+    use crate::{AXElement, MacAxController};
+
+    #[test]
+    fn test_ax_element_to_string() {
+        let element = AXElement {
+            role: "button".to_string(),
+            title: Some("Click Me".to_string()),
+            value: None,
+            label: Some("Submit Button".to_string()),
+            identifier: Some("submitBtn".to_string()),
+            enabled: true,
+            focused: false,
+            position: Some((100.0, 200.0)),
+            size: Some((80.0, 30.0)),
+            children_count: 0,
+        };
+
+        let string_repr = element.to_string();
+        assert!(string_repr.contains("Role: button"));
+        assert!(string_repr.contains("Title: Click Me"));
+        assert!(string_repr.contains("Label: Submit Button"));
+        assert!(string_repr.contains("ID: submitBtn"));
+        assert!(string_repr.contains("Enabled: true"));
+        assert!(string_repr.contains("Position: (100, 200)"));
+        assert!(string_repr.contains("Size: (80, 30)"));
+    }
+
+    #[test]
+    fn test_controller_creation() {
+        // Just test that we can create a controller
+        // Actual functionality requires macOS and permissions
+        let result = MacAxController::new();
+        assert!(result.is_ok());
+    }
+}

crates/g3-computer-control/src/ocr/mod.rs

@@ -0,0 +1,26 @@
+use crate::types::TextLocation;
+use anyhow::Result;
+use async_trait::async_trait;
+
+/// OCR engine trait for text recognition with bounding boxes
+#[async_trait]
+pub trait OCREngine: Send + Sync {
+    /// Extract text with locations from an image file
+    async fn extract_text_with_locations(&self, path: &str) -> Result<Vec<TextLocation>>;
+    
+    /// Get the name of the OCR engine
+    fn name(&self) -> &str;
+}
+
+// Platform-specific modules
+#[cfg(target_os = "macos")]
+pub mod vision;
+
+pub mod tesseract;
+
+// Re-export the default OCR engine for the platform
+#[cfg(target_os = "macos")]
+pub use vision::AppleVisionOCR as DefaultOCR;
+
+#[cfg(not(target_os = "macos"))]
+pub use tesseract::TesseractOCR as DefaultOCR;

crates/g3-computer-control/src/ocr/tesseract.rs

@@ -0,0 +1,84 @@
+use super::OCREngine;
+use crate::types::TextLocation;
+use anyhow::Result;
+use async_trait::async_trait;
+
+/// Tesseract OCR engine (fallback/cross-platform)
+pub struct TesseractOCR;
+
+impl TesseractOCR {
+    pub fn new() -> Result<Self> {
+        // Check if tesseract is available
+        let tesseract_check = std::process::Command::new("which")
+            .arg("tesseract")
+            .output();
+        
+        if tesseract_check.is_err() || !tesseract_check.as_ref().unwrap().status.success() {
+            anyhow::bail!("Tesseract OCR is not installed on your system.\n\n\
+                To install tesseract:\n  macOS:   brew install tesseract\n  \
+                Linux:   sudo apt-get install tesseract-ocr (Ubuntu/Debian)\n           \
+                sudo yum install tesseract (RHEL/CentOS)\n  \
+                Windows: Download from https://github.com/UB-Mannheim/tesseract/wiki\n\n\
+                After installation, restart your terminal and try again.");
+        }
+        
+        Ok(Self)
+    }
+}
+
+#[async_trait]
+impl OCREngine for TesseractOCR {
+    async fn extract_text_with_locations(&self, path: &str) -> Result<Vec<TextLocation>> {
+        // Use tesseract CLI with TSV output to get bounding boxes
+        let output = std::process::Command::new("tesseract")
+            .arg(path)
+            .arg("stdout")
+            .arg("tsv")
+            .output()
+            .map_err(|e| anyhow::anyhow!("Failed to run tesseract: {}", e))?;
+        
+        if !output.status.success() {
+            anyhow::bail!("Tesseract failed: {}", String::from_utf8_lossy(&output.stderr));
+        }
+        
+        let tsv_text = String::from_utf8_lossy(&output.stdout);
+        let mut locations = Vec::new();
+        
+        // Parse TSV output (skip header line)
+        for (i, line) in tsv_text.lines().enumerate() {
+            if i == 0 { continue; } // Skip header
+            
+            let parts: Vec<&str> = line.split('\t').collect();
+            if parts.len() >= 12 {
+                // TSV format: level, page_num, block_num, par_num, line_num, word_num,
+                //             left, top, width, height, conf, text
+                if let (Ok(x), Ok(y), Ok(w), Ok(h), Ok(conf), text) = (
+                    parts[6].parse::<i32>(),
+                    parts[7].parse::<i32>(),
+                    parts[8].parse::<i32>(),
+                    parts[9].parse::<i32>(),
+                    parts[10].parse::<f32>(),
+                    parts[11],
+                ) {
+                    let trimmed = text.trim();
+                    if !trimmed.is_empty() && conf > 0.0 {
+                        locations.push(TextLocation {
+                            text: trimmed.to_string(),
+                            x,
+                            y,
+                            width: w,
+                            height: h,
+                            confidence: conf / 100.0, // Convert from 0-100 to 0-1
+                        });
+                    }
+                }
+            }
+        }
+        
+        Ok(locations)
+    }
+    
+    fn name(&self) -> &str {
+        "Tesseract OCR"
+    }
+}

crates/g3-computer-control/src/ocr/vision.rs

@@ -0,0 +1,103 @@
+use super::OCREngine;
+use crate::types::TextLocation;
+use anyhow::{Result, Context};
+use async_trait::async_trait;
+use std::ffi::{CStr, CString};
+use std::os::raw::{c_char, c_float, c_uint};
+
+// FFI bindings to Swift VisionBridge
+#[repr(C)]
+struct VisionTextBox {
+    text: *const c_char,
+    text_len: c_uint,
+    x: i32,
+    y: i32,
+    width: i32,
+    height: i32,
+    confidence: c_float,
+}
+
+extern "C" {
+    fn vision_recognize_text(
+        image_path: *const c_char,
+        image_path_len: c_uint,
+        out_boxes: *mut *mut std::ffi::c_void,
+        out_count: *mut c_uint,
+    ) -> bool;
+    
+    fn vision_free_boxes(boxes: *mut std::ffi::c_void, count: c_uint);
+}
+
+/// Apple Vision Framework OCR engine
+pub struct AppleVisionOCR;
+
+impl AppleVisionOCR {
+    pub fn new() -> Result<Self> {
+        Ok(Self)
+    }
+}
+
+#[async_trait]
+impl OCREngine for AppleVisionOCR {
+    async fn extract_text_with_locations(&self, path: &str) -> Result<Vec<TextLocation>> {
+        // Convert path to C string
+        let c_path = CString::new(path)
+            .context("Failed to convert path to C string")?;
+        
+        let mut boxes_ptr: *mut std::ffi::c_void = std::ptr::null_mut();
+        let mut count: c_uint = 0;
+        
+        // Call Swift Vision API
+        let success = unsafe {
+            vision_recognize_text(
+                c_path.as_ptr(),
+                path.len() as c_uint,
+                &mut boxes_ptr,
+                &mut count,
+            )
+        };
+        
+        if !success || boxes_ptr.is_null() {
+            anyhow::bail!("Apple Vision OCR failed");
+        }
+        
+        // Convert C array to Rust Vec
+        let mut locations = Vec::new();
+        
+        unsafe {
+            let typed_boxes = boxes_ptr as *const VisionTextBox;
+            let boxes_slice = std::slice::from_raw_parts(typed_boxes, count as usize);
+            
+            for box_data in boxes_slice {
+                // Convert C string to Rust String
+                let text = if !box_data.text.is_null() {
+                    CStr::from_ptr(box_data.text)
+                        .to_string_lossy()
+                        .into_owned()
+                } else {
+                    String::new()
+                };
+                
+                if !text.is_empty() {
+                    locations.push(TextLocation {
+                        text,
+                        x: box_data.x,
+                        y: box_data.y,
+                        width: box_data.width,
+                        height: box_data.height,
+                        confidence: box_data.confidence,
+                    });
+                }
+            }
+            
+            // Free the C array
+            vision_free_boxes(boxes_ptr, count);
+        }
+        
+        Ok(locations)
+    }
+    
+    fn name(&self) -> &str {
+        "Apple Vision Framework"
+    }
+}

crates/g3-computer-control/src/platform/linux.rs

@@ -1,24 +1,166 @@
-use crate::{types::Rect, ComputerController};
+use crate::{ComputerController, types::*};
 use anyhow::Result;
 use async_trait::async_trait;
+use tesseract::Tesseract;
+use uuid::Uuid;
 
-pub struct LinuxController;
+pub struct LinuxController {
+    // Placeholder for X11 connection or other state
+}
 
 impl LinuxController {
     pub fn new() -> Result<Self> {
+        // Initialize X11 connection
         tracing::warn!("Linux computer control not fully implemented");
-        Ok(Self)
+        Ok(Self {})
     }
 }
 
 #[async_trait]
 impl ComputerController for LinuxController {
-    async fn take_screenshot(
-        &self,
-        _path: &str,
-        _region: Option<Rect>,
-        _window_id: Option<&str>,
-    ) -> Result<()> {
-        anyhow::bail!("Linux screenshot implementation not yet available")
+    async fn move_mouse(&self, _x: i32, _y: i32) -> Result<()> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn click(&self, _button: MouseButton) -> Result<()> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn double_click(&self, _button: MouseButton) -> Result<()> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn type_text(&self, _text: &str) -> Result<()> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn press_key(&self, _key: &str) -> Result<()> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn list_windows(&self) -> Result<Vec<Window>> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn focus_window(&self, _window_id: &str) -> Result<()> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn get_window_bounds(&self, _window_id: &str) -> Result<Rect> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn find_element(&self, _selector: &ElementSelector) -> Result<Option<UIElement>> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn get_element_text(&self, _element_id: &str) -> Result<String> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn get_element_bounds(&self, _element_id: &str) -> Result<Rect> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn take_screenshot(&self, _path: &str, _region: Option<Rect>, _window_id: Option<&str>) -> Result<()> {
+        // Enforce that window_id must be provided
+        if _window_id.is_none() {
+            anyhow::bail!("window_id is required. You must specify which window to capture (e.g., 'Firefox', 'Terminal', 'gedit'). Use list_windows to see available windows.");
+        }
+
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn extract_text_from_screen(&self, _region: Rect, _window_id: &str) -> Result<String> {
+        anyhow::bail!("Linux implementation not yet available")
+    }
+    
+    async fn extract_text_from_image(&self, _path: &str) -> Result<OCRResult> {
+        // Check if tesseract is available on the system
+        let tesseract_check = std::process::Command::new("which")
+            .arg("tesseract")
+            .output();
+        
+        if tesseract_check.is_err() || !tesseract_check.as_ref().unwrap().status.success() {
+            anyhow::bail!("Tesseract OCR is not installed on your system.\n\n\
+                To install tesseract:\n  \
+                Ubuntu/Debian: sudo apt-get install tesseract-ocr\n  \
+                RHEL/CentOS:   sudo yum install tesseract\n  \
+                Arch Linux:    sudo pacman -S tesseract\n\n\
+                After installation, restart your terminal and try again.");
+        }
+        
+        // Initialize Tesseract
+        let tess = Tesseract::new(None, Some("eng"))
+            .map_err(|e| {
+                anyhow::anyhow!("Failed to initialize Tesseract: {}\n\n\
+                    This usually means:\n1. Tesseract is not properly installed\n\
+                    2. Language data files are missing\n\nTo fix:\n  \
+                    Ubuntu/Debian: sudo apt-get install tesseract-ocr-eng\n  \
+                    RHEL/CentOS:   sudo yum install tesseract-langpack-eng\n  \
+                    Arch Linux:    sudo pacman -S tesseract-data-eng", e)
+            })?;
+        
+        let text = tess.set_image(_path)
+            .map_err(|e| anyhow::anyhow!("Failed to load image '{}': {}", _path, e))?
+            .get_text()
+            .map_err(|e| anyhow::anyhow!("Failed to extract text from image: {}", e))?;
+        
+        // Get confidence (simplified - would need more complex API calls for per-word confidence)
+        let confidence = 0.85; // Placeholder
+        
+        Ok(OCRResult {
+            text,
+            confidence,
+            bounds: Rect { x: 0, y: 0, width: 0, height: 0 }, // Would need image dimensions
+        })
+    }
+    
+    async fn find_text_on_screen(&self, _text: &str) -> Result<Option<Point>> {
+        // Check if tesseract is available on the system
+        let tesseract_check = std::process::Command::new("which")
+            .arg("tesseract")
+            .output();
+        
+        if tesseract_check.is_err() || !tesseract_check.as_ref().unwrap().status.success() {
+            anyhow::bail!("Tesseract OCR is not installed on your system.\n\n\
+                To install tesseract:\n  \
+                Ubuntu/Debian: sudo apt-get install tesseract-ocr\n  \
+                RHEL/CentOS:   sudo yum install tesseract\n  \
+                Arch Linux:    sudo pacman -S tesseract\n\n\
+                After installation, restart your terminal and try again.");
+        }
+        
+        // Take full screen screenshot
+        let temp_path = format!("/tmp/g3_ocr_search_{}.png", uuid::Uuid::new_v4());
+        self.take_screenshot(&temp_path, None, None).await?;
+        
+        // Use Tesseract to find text with bounding boxes
+        let tess = Tesseract::new(None, Some("eng"))
+            .map_err(|e| {
+                anyhow::anyhow!("Failed to initialize Tesseract: {}\n\n\
+                    This usually means:\n1. Tesseract is not properly installed\n\
+                    2. Language data files are missing\n\nTo fix:\n  \
+                    Ubuntu/Debian: sudo apt-get install tesseract-ocr-eng\n  \
+                    RHEL/CentOS:   sudo yum install tesseract-langpack-eng\n  \
+                    Arch Linux:    sudo pacman -S tesseract-data-eng", e)
+            })?;
+        
+        let full_text = tess.set_image(temp_path.as_str())
+            .map_err(|e| anyhow::anyhow!("Failed to load screenshot: {}", e))?
+            .get_text()
+            .map_err(|e| anyhow::anyhow!("Failed to extract text from screen: {}", e))?;
+        
+        // Clean up temp file
+        let _ = std::fs::remove_file(&temp_path);
+        
+        // Simple text search - full implementation would use get_component_images
+        // to get bounding boxes for each word
+        if full_text.contains(_text) {
+            tracing::warn!("Text found but precise coordinates not available in simplified implementation");
+            Ok(Some(Point { x: 0, y: 0 }))
+        } else {
+            Ok(None)
+        }
     }
 }

crates/g3-computer-control/src/platform/macos.rs

@@ -1,34 +1,32 @@
-use crate::{
-    types::Rect, ComputerController,
-};
-use anyhow::Result;
+use crate::{ComputerController, types::{Rect, TextLocation}};
+use crate::ocr::{OCREngine, DefaultOCR};
+use anyhow::{Result, Context};
 use async_trait::async_trait;
-use core_foundation::array::CFArray;
-use core_foundation::base::{TCFType, ToVoid};
+use std::path::Path;
+use core_graphics::window::{kCGWindowListOptionOnScreenOnly, kCGNullWindowID, CGWindowListCopyWindowInfo};
 use core_foundation::dictionary::CFDictionary;
 use core_foundation::string::CFString;
-use core_graphics::window::{
-    kCGNullWindowID, kCGWindowListOptionOnScreenOnly, CGWindowListCopyWindowInfo,
-};
-use std::path::Path;
+use core_foundation::base::{TCFType, ToVoid};
+use core_foundation::array::CFArray;
 
-pub struct MacOSController;
+pub struct MacOSController {
+    ocr_engine: Box<dyn OCREngine>,
+    #[allow(dead_code)]
+    ocr_name: String,
+}
 
 impl MacOSController {
     pub fn new() -> Result<Self> {
-        tracing::debug!("Initialized macOS controller");
-        Ok(Self)
+        let ocr = Box::new(DefaultOCR::new()?);
+        let ocr_name = ocr.name().to_string();
+        tracing::info!("Initialized macOS controller with OCR engine: {}", ocr_name);
+        Ok(Self { ocr_engine: ocr, ocr_name })
     }
 }
 
 #[async_trait]
 impl ComputerController for MacOSController {
-    async fn take_screenshot(
-        &self,
-        path: &str,
-        region: Option<Rect>,
-        window_id: Option<&str>,
-    ) -> Result<()> {
+    async fn take_screenshot(&self, path: &str, region: Option<Rect>, window_id: Option<&str>) -> Result<()> {
         // Enforce that window_id must be provided
         if window_id.is_none() {
             return Err(anyhow::anyhow!("window_id is required. You must specify which window to capture (e.g., 'Safari', 'Terminal', 'Google Chrome'). Use list_windows to see available windows."));
@@ -58,8 +56,10 @@ impl ComputerController for MacOSController {
         
         // Get the window ID for the specified application
         let cg_window_id = unsafe {
-            let window_list =
-                CGWindowListCopyWindowInfo(kCGWindowListOptionOnScreenOnly, kCGNullWindowID);
+            let window_list = CGWindowListCopyWindowInfo(
+                kCGWindowListOptionOnScreenOnly,
+                kCGNullWindowID
+            );
             
             let array = CFArray::<CFDictionary>::wrap_under_create_rule(window_list);
             let count = array.len();
@@ -79,11 +79,7 @@ impl ComputerController for MacOSController {
                     continue;
                 };
                 
-                tracing::debug!(
-                    "Checking window: owner='{}', looking for '{}'",
-                    owner,
-                    app_name
-                );
+                tracing::debug!("Checking window: owner='{}', looking for '{}'", owner, app_name);
                 let owner_lower = owner.to_lowercase();
                 
                 // Normalize by removing spaces for exact matching
@@ -92,21 +88,18 @@ impl ComputerController for MacOSController {
                 
                 // ONLY accept exact matches (case-insensitive, with or without spaces)
                 // This prevents "Goose" from matching "GooseStudio"
-                let is_match =
-                    owner_lower == app_name_lower || owner_normalized == app_name_normalized;
+                let is_match = owner_lower == app_name_lower || owner_normalized == app_name_normalized;
                 
                 if is_match {
                     // Get window ID
                     let window_id_key = CFString::from_static_string("kCGWindowNumber");
                     if let Some(value) = dict.find(window_id_key.to_void()) {
-                        let num: core_foundation::number::CFNumber =
-                            TCFType::wrap_under_get_rule(*value as *const _);
+                        let num: core_foundation::number::CFNumber = TCFType::wrap_under_get_rule(*value as *const _);
                         if let Some(id) = num.to_i64() {
                             // Get window layer to filter out menu bar windows
                             let layer_key = CFString::from_static_string("kCGWindowLayer");
                             let layer: i32 = if let Some(value) = dict.find(layer_key.to_void()) {
-                                let num: core_foundation::number::CFNumber =
-                                    TCFType::wrap_under_get_rule(*value as *const _);
+                                let num: core_foundation::number::CFNumber = TCFType::wrap_under_get_rule(*value as *const _);
                                 num.to_i32().unwrap_or(0)
                             } else {
                                 0
@@ -114,10 +107,8 @@ impl ComputerController for MacOSController {
                             
                             // Get window bounds to verify it's a real window
                             let bounds_key = CFString::from_static_string("kCGWindowBounds");
-                            let has_real_bounds =
-                                if let Some(value) = dict.find(bounds_key.to_void()) {
-                                    let bounds_dict: CFDictionary =
-                                        TCFType::wrap_under_get_rule(*value as *const _);
+                            let has_real_bounds = if let Some(value) = dict.find(bounds_key.to_void()) {
+                                let bounds_dict: CFDictionary = TCFType::wrap_under_get_rule(*value as *const _);
                                 let width_key = CFString::from_static_string("Width");
                                 let height_key = CFString::from_static_string("Height");
                                 
@@ -125,10 +116,8 @@ impl ComputerController for MacOSController {
                                     bounds_dict.find(width_key.to_void()),
                                     bounds_dict.find(height_key.to_void()),
                                 ) {
-                                        let w_num: core_foundation::number::CFNumber =
-                                            TCFType::wrap_under_get_rule(*w_val as *const _);
-                                        let h_num: core_foundation::number::CFNumber =
-                                            TCFType::wrap_under_get_rule(*h_val as *const _);
+                                    let w_num: core_foundation::number::CFNumber = TCFType::wrap_under_get_rule(*w_val as *const _);
+                                    let h_num: core_foundation::number::CFNumber = TCFType::wrap_under_get_rule(*h_val as *const _);
                                     let width = w_num.to_f64().unwrap_or(0.0);
                                     let height = h_num.to_f64().unwrap_or(0.0);
                                     // Real windows should be at least 100x100 pixels
@@ -144,17 +133,11 @@ impl ComputerController for MacOSController {
                             // 1. At layer 0 (normal windows, not menu bar)
                             // 2. Have real bounds (width and height >= 100)
                             if layer == 0 && has_real_bounds {
-                                tracing::debug!("Found valid window: ID {} for app '{}' (layer={}, bounds valid)", id, owner, layer);
+                                tracing::info!("Found valid window: ID {} for app '{}' (layer={}, bounds valid)", id, owner, layer);
                                 found_window_id = Some((id as u32, owner.clone()));
                                 break;
                             } else {
-                                tracing::debug!(
-                                    "Skipping window ID {} for '{}': layer={}, has_real_bounds={}",
-                                    id,
-                                    owner,
-                                    layer,
-                                    has_real_bounds
-                                );
+                                tracing::debug!("Skipping window ID {} for '{}': layer={}, has_real_bounds={}", id, owner, layer, has_real_bounds);
                             }
                         }
                     }
@@ -167,11 +150,7 @@ impl ComputerController for MacOSController {
         let (cg_window_id, matched_owner) = cg_window_id.ok_or_else(|| {
             anyhow::anyhow!("Could not find window for application '{}'. Use list_windows to see available windows.", app_name)
         })?;
-        tracing::debug!(
-            "Taking screenshot of window ID {} for app '{}'",
-            cg_window_id,
-            matched_owner
-        );
+            tracing::info!("Taking screenshot of window ID {} for app '{}'", cg_window_id, matched_owner);
         
         // Use screencapture with the window ID for now
         // TODO: Implement direct CGWindowListCreateImage approach with proper image saving
@@ -182,10 +161,7 @@ impl ComputerController for MacOSController {
         
         if let Some(region) = region {
             cmd.arg("-R");
-            cmd.arg(format!(
-                "{},{},{},{}",
-                region.x, region.y, region.width, region.height
-            ));
+            cmd.arg(format!("{},{},{},{}", region.x, region.y, region.width, region.height));
         }
         
         cmd.arg(&final_path);
@@ -194,16 +170,336 @@ impl ComputerController for MacOSController {
         
         if !screenshot_result.status.success() {
             let stderr = String::from_utf8_lossy(&screenshot_result.stderr);
-            return Err(anyhow::anyhow!(
-                "screencapture failed for window {}: {}",
-                cg_window_id,
-                stderr
-            ));
+            return Err(anyhow::anyhow!("screencapture failed for window {}: {}", cg_window_id, stderr));
         }
         
         Ok(())
     }
     
+    async fn extract_text_from_screen(&self, region: Rect, window_id: &str) -> Result<String> {
+        // Take screenshot of region first
+        let temp_path = format!("/tmp/g3_ocr_{}.png", uuid::Uuid::new_v4());
+        self.take_screenshot(&temp_path, Some(region), Some(window_id)).await?;
+        
+        // Extract text from the screenshot
+        let result = self.extract_text_from_image(&temp_path).await?;
+        
+        // Clean up temp file
+        let _ = std::fs::remove_file(&temp_path);
+        
+        Ok(result)
+    }
+    
+    async fn extract_text_from_image(&self, path: &str) -> Result<String> {
+        // Extract all text and concatenate
+        let locations = self.ocr_engine.extract_text_with_locations(path).await?;
+        Ok(locations.iter().map(|loc| loc.text.as_str()).collect::<Vec<_>>().join(" "))
+    }
+    
+    async fn extract_text_with_locations(&self, path: &str) -> Result<Vec<TextLocation>> {
+        // Use the OCR engine
+        self.ocr_engine.extract_text_with_locations(path).await
+    }
+    
+    async fn find_text_in_app(&self, app_name: &str, search_text: &str) -> Result<Option<TextLocation>> {
+        // Take screenshot of specific app window
+        let home = std::env::var("HOME").unwrap_or_else(|_| "/tmp".to_string());
+        let temp_path = format!("{}/tmp/g3_find_text_{}_{}.png", home, app_name, uuid::Uuid::new_v4());
+        self.take_screenshot(&temp_path, None, Some(app_name)).await?;
+        
+        // Get screenshot dimensions before we delete it
+        let screenshot_dims = get_image_dimensions(&temp_path)?;
+        
+        // Extract all text with locations
+        let locations = self.extract_text_with_locations(&temp_path).await?;
+        
+        // Get window bounds to calculate coordinate transformation
+        let window_bounds = self.get_window_bounds(app_name)?;
+        
+        // Clean up temp file
+        let _ = std::fs::remove_file(&temp_path);
+        
+        // Find matching text (case-insensitive)
+        let search_lower = search_text.to_lowercase();
+        for location in locations {
+            if location.text.to_lowercase().contains(&search_lower) {
+                // Transform coordinates from screenshot space to screen space
+                let transformed = transform_screenshot_to_screen_coords(
+                    location,
+                    window_bounds,
+                    screenshot_dims,
+                );
+                return Ok(Some(transformed));
+            }
+        }
+        
+        Ok(None)
+    }
+    
+    fn move_mouse(&self, x: i32, y: i32) -> Result<()> {
+        use core_graphics::event::{
+            CGEvent, CGEventTapLocation, CGEventType, CGMouseButton,
+        };
+        use core_graphics::event_source::{
+            CGEventSource, CGEventSourceStateID,
+        };
+        use core_graphics::geometry::CGPoint;
+        
+        let source = CGEventSource::new(CGEventSourceStateID::HIDSystemState)
+            .ok().context("Failed to create event source")?;
+        
+        let event = CGEvent::new_mouse_event(
+            source,
+            CGEventType::MouseMoved,
+            CGPoint::new(x as f64, y as f64),
+            CGMouseButton::Left,
+        ).ok().context("Failed to create mouse event")?;
+        
+        event.post(CGEventTapLocation::HID);
+        
+        Ok(())
+    }
+    
+    fn click_at(&self, x: i32, y: i32, _app_name: Option<&str>) -> Result<()> {
+        use core_graphics::event::{
+            CGEvent, CGEventTapLocation, CGEventType, CGMouseButton,
+        };
+        use core_graphics::event_source::{
+            CGEventSource, CGEventSourceStateID,
+        };
+        use core_graphics::geometry::CGPoint;
+        use core_graphics::display::CGDisplay;
+        
+        // IMPORTANT: Coordinates passed here are in NSScreen/CGWindowListCopyWindowInfo space
+        // (Y=0 at BOTTOM, increases UPWARD)
+        // But CGEvent uses a different coordinate system (Y=0 at TOP, increases DOWNWARD)
+        // We need to convert: CGEvent.y = screenHeight - NSScreen.y
+        
+        let screen_height = CGDisplay::main().pixels_high() as i32;
+        let cgevent_x = x;
+        let cgevent_y = screen_height - y;
+        
+        tracing::debug!("click_at: NSScreen coords ({}, {}) -> CGEvent coords ({}, {}) [screen_height={}]",
+            x, y, cgevent_x, cgevent_y, screen_height);
+        
+        let (global_x, global_y) = (cgevent_x, cgevent_y);
+        
+        let point = CGPoint::new(global_x as f64, global_y as f64);
+        
+        let source = CGEventSource::new(CGEventSourceStateID::HIDSystemState)
+            .ok().context("Failed to create event source")?;
+        
+        // Move mouse to position first
+        let move_event = CGEvent::new_mouse_event(
+            source.clone(),
+            CGEventType::MouseMoved,
+            point,
+            CGMouseButton::Left,
+        ).ok().context("Failed to create mouse move event")?;
+        move_event.post(CGEventTapLocation::HID);
+        
+        std::thread::sleep(std::time::Duration::from_millis(100));
+        
+        // Mouse down
+        let mouse_down = CGEvent::new_mouse_event(
+            source.clone(),
+            CGEventType::LeftMouseDown,
+            point,
+            CGMouseButton::Left,
+        ).ok().context("Failed to create mouse down event")?;
+        mouse_down.post(CGEventTapLocation::HID);
+        
+        std::thread::sleep(std::time::Duration::from_millis(50));
+        
+        // Mouse up
+        let mouse_up = CGEvent::new_mouse_event(
+            source,
+            CGEventType::LeftMouseUp,
+            point,
+            CGMouseButton::Left,
+        ).ok().context("Failed to create mouse up event")?;
+        mouse_up.post(CGEventTapLocation::HID);
+        
+        Ok(())
+    }
+}
+
+impl MacOSController {
+    /// Get window bounds for an application (helper method)
+    fn get_window_bounds(&self, app_name: &str) -> Result<(i32, i32, i32, i32)> {
+        unsafe {
+            let window_list = CGWindowListCopyWindowInfo(
+                kCGWindowListOptionOnScreenOnly,
+                kCGNullWindowID
+            );
+            
+            let array = CFArray::<CFDictionary>::wrap_under_create_rule(window_list);
+            let count = array.len();
+            
+            let app_name_lower = app_name.to_lowercase();
+            
+            for i in 0..count {
+                let dict = array.get(i).unwrap();
+                
+                // Get owner name
+                let owner_key = CFString::from_static_string("kCGWindowOwnerName");
+                let owner: String = if let Some(value) = dict.find(owner_key.to_void()) {
+                    let s: CFString = TCFType::wrap_under_get_rule(*value as *const _);
+                    s.to_string()
+                } else {
+                    continue;
+                };
+                
+                let owner_lower = owner.to_lowercase();
+                
+                // Normalize by removing spaces for exact matching
+                let app_name_normalized = app_name_lower.replace(" ", "");
+                let owner_normalized = owner_lower.replace(" ", "");
+                
+                // ONLY accept exact matches (case-insensitive, with or without spaces)
+                // This prevents "Goose" from matching "GooseStudio"
+                let is_match = owner_lower == app_name_lower || owner_normalized == app_name_normalized;
+                
+                if is_match {
+                    // Get window layer to filter out menu bar windows
+                    let layer_key = CFString::from_static_string("kCGWindowLayer");
+                    let layer: i32 = if let Some(value) = dict.find(layer_key.to_void()) {
+                        let num: core_foundation::number::CFNumber = TCFType::wrap_under_get_rule(*value as *const _);
+                        num.to_i32().unwrap_or(0)
+                    } else {
+                        0
+                    };
+                    
+                    // Skip menu bar windows (layer >= 20)
+                    if layer >= 20 {
+                        tracing::debug!("Skipping window for '{}' at layer {} (menu bar)", owner, layer);
+                        continue;
+                    }
+                    
+                    // Get window bounds to verify it's a real window
+                    let bounds_key = CFString::from_static_string("kCGWindowBounds");
+                    if let Some(value) = dict.find(bounds_key.to_void()) {
+                        let bounds_dict: CFDictionary = TCFType::wrap_under_get_rule(*value as *const _);
+                        
+                        let x_key = CFString::from_static_string("X");
+                        let y_key = CFString::from_static_string("Y");
+                        let width_key = CFString::from_static_string("Width");
+                        let height_key = CFString::from_static_string("Height");
+                        
+                        if let (Some(x_val), Some(y_val), Some(w_val), Some(h_val)) = (
+                            bounds_dict.find(x_key.to_void()),
+                            bounds_dict.find(y_key.to_void()),
+                            bounds_dict.find(width_key.to_void()),
+                            bounds_dict.find(height_key.to_void()),
+                        ) {
+                            let x_num: core_foundation::number::CFNumber = TCFType::wrap_under_get_rule(*x_val as *const _);
+                            let y_num: core_foundation::number::CFNumber = TCFType::wrap_under_get_rule(*y_val as *const _);
+                            let w_num: core_foundation::number::CFNumber = TCFType::wrap_under_get_rule(*w_val as *const _);
+                            let h_num: core_foundation::number::CFNumber = TCFType::wrap_under_get_rule(*h_val as *const _);
+                            
+                            let x: i32 = x_num.to_i64().unwrap_or(0) as i32;
+                            let y: i32 = y_num.to_i64().unwrap_or(0) as i32;
+                            let w: i32 = w_num.to_i64().unwrap_or(0) as i32;
+                            let h: i32 = h_num.to_i64().unwrap_or(0) as i32;
+                            
+                            // Only accept windows with real bounds (>= 100x100 pixels)
+                            if w >= 100 && h >= 100 {
+                                tracing::info!("Found valid window bounds for '{}': x={}, y={}, w={}, h={} (layer={})", owner, x, y, w, h, layer);
+                                return Ok((x, y, w, h));
+                            } else {
+                                tracing::debug!("Skipping window for '{}': too small ({}x{})", owner, w, h);
+                                continue;
+                            }
+                        } else {
+                            continue;
+                        }
+                    }
+                }
+            }
+        }
+        
+        Err(anyhow::anyhow!("Could not find window bounds for '{}'", app_name))
+    }
+}
+
+/// Get image dimensions from a PNG file
+fn get_image_dimensions(path: &str) -> Result<(i32, i32)> {
+    use std::fs::File;
+    use std::io::Read;
+    
+    let mut file = File::open(path)?;
+    let mut buffer = vec![0u8; 24];
+    file.read_exact(&mut buffer)?;
+    
+    // PNG signature check
+    if &buffer[0..8] != b"\x89PNG\r\n\x1a\n" {
+        anyhow::bail!("Not a valid PNG file");
+    }
+    
+    // Read IHDR chunk (width and height are at bytes 16-23)
+    let width = u32::from_be_bytes([buffer[16], buffer[17], buffer[18], buffer[19]]) as i32;
+    let height = u32::from_be_bytes([buffer[20], buffer[21], buffer[22], buffer[23]]) as i32;
+    
+    Ok((width, height))
+}
+
+/// Transform coordinates from screenshot space to screen space
+/// 
+/// The screenshot is taken of a window, and Vision OCR returns coordinates
+/// relative to the screenshot image. We need to transform these to actual
+/// screen coordinates for clicking.
+/// 
+/// On Retina displays, screenshots are taken at 2x resolution, so we need
+/// to account for this scaling factor.
+fn transform_screenshot_to_screen_coords(
+    location: TextLocation,
+    window_bounds: (i32, i32, i32, i32), // (x, y, width, height) in screen space
+    screenshot_dims: (i32, i32), // (width, height) in pixels
+) -> TextLocation {
+    let (win_x, win_y, win_width, win_height) = window_bounds;
+    let (screenshot_width, screenshot_height) = screenshot_dims;
+    
+    // Calculate scale factors
+    // On Retina displays, screenshot is typically 2x the window size
+    let scale_x = win_width as f64 / screenshot_width as f64;
+    let scale_y = win_height as f64 / screenshot_height as f64;
+    
+    tracing::debug!("Transform: screenshot={}x{}, window={}x{} at ({},{}), scale=({:.2},{:.2})",
+        screenshot_width, screenshot_height, win_width, win_height, win_x, win_y, scale_x, scale_y);
+    
+    // Transform coordinates from image space to screen space
+    // IMPORTANT: macOS screen coordinates have origin at BOTTOM-LEFT (Y increases upward)
+    // Image coordinates have origin at TOP-LEFT (Y increases downward)
+    // win_y is the BOTTOM of the window in screen coordinates
+    // So we need to: (win_y + win_height) to get window TOP, then subtract screenshot_y
+    let window_top_y = win_y + win_height;
+    
+    tracing::debug!("[transform] Input location in image space: x={}, y={}, width={}, height={}",
+        location.x, location.y, location.width, location.height);
+    tracing::debug!("[transform] Scale factors: scale_x={:.4}, scale_y={:.4}", scale_x, scale_y);
+    
+    let transformed_x = win_x + (location.x as f64 * scale_x) as i32;
+    let transformed_y = window_top_y - (location.y as f64 * scale_y) as i32;
+    let transformed_width = (location.width as f64 * scale_x) as i32;
+    let transformed_height = (location.height as f64 * scale_y) as i32;
+    
+    tracing::debug!("[transform] Calculation details:");
+    tracing::debug!("  - transformed_x = {} + ({} * {:.4}) = {} + {:.2} = {}", win_x, location.x, scale_x, win_x, location.x as f64 * scale_x, transformed_x);
+    tracing::debug!("  - transformed_width = ({} * {:.4}) = {:.2} -> {}", location.width, scale_x, location.width as f64 * scale_x, transformed_width);
+    tracing::debug!("  - transformed_height = ({} * {:.4}) = {:.2} -> {}", location.height, scale_y, location.height as f64 * scale_y, transformed_height);
+    
+    tracing::debug!("Transformed location: screenshot=({},{}) {}x{} -> screen=({},{}) {}x{}",
+        location.x, location.y, location.width, location.height,
+        transformed_x, transformed_y, transformed_width, transformed_height);
+    
+    TextLocation {
+        text: location.text,
+        x: transformed_x,
+        y: transformed_y,
+        width: transformed_width,
+        height: transformed_height,
+        confidence: location.confidence,
+    }
 }
 
 #[path = "macos_window_matching_test.rs"]

crates/g3-computer-control/src/platform/windows.rs

@@ -1,24 +1,167 @@
-use crate::{types::Rect, ComputerController};
+use crate::{ComputerController, types::*};
 use anyhow::Result;
 use async_trait::async_trait;
+use tesseract::Tesseract;
+use uuid::Uuid;
 
-pub struct WindowsController;
+pub struct WindowsController {
+    // Placeholder for Windows-specific state
+}
 
 impl WindowsController {
     pub fn new() -> Result<Self> {
         tracing::warn!("Windows computer control not fully implemented");
-        Ok(Self)
+        Ok(Self {})
     }
 }
 
 #[async_trait]
 impl ComputerController for WindowsController {
-    async fn take_screenshot(
-        &self,
-        _path: &str,
-        _region: Option<Rect>,
-        _window_id: Option<&str>,
-    ) -> Result<()> {
-        anyhow::bail!("Windows screenshot implementation not yet available")
+    async fn move_mouse(&self, _x: i32, _y: i32) -> Result<()> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn click(&self, _button: MouseButton) -> Result<()> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn double_click(&self, _button: MouseButton) -> Result<()> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn type_text(&self, _text: &str) -> Result<()> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn press_key(&self, _key: &str) -> Result<()> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn list_windows(&self) -> Result<Vec<Window>> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn focus_window(&self, _window_id: &str) -> Result<()> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn get_window_bounds(&self, _window_id: &str) -> Result<Rect> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn find_element(&self, _selector: &ElementSelector) -> Result<Option<UIElement>> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn get_element_text(&self, _element_id: &str) -> Result<String> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn get_element_bounds(&self, _element_id: &str) -> Result<Rect> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn take_screenshot(&self, _path: &str, _region: Option<Rect>, _window_id: Option<&str>) -> Result<()> {
+        // Enforce that window_id must be provided
+        if _window_id.is_none() {
+            anyhow::bail!("window_id is required. You must specify which window to capture (e.g., 'Chrome', 'Terminal', 'Notepad'). Use list_windows to see available windows.");
+        }
+
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn extract_text_from_screen(&self, _region: Rect, _window_id: &str) -> Result<String> {
+        anyhow::bail!("Windows implementation not yet available")
+    }
+    
+    async fn extract_text_from_image(&self, _path: &str) -> Result<OCRResult> {
+        // Check if tesseract is available on the system
+        let tesseract_check = std::process::Command::new("where")
+            .arg("tesseract")
+            .output();
+        
+        if tesseract_check.is_err() || !tesseract_check.as_ref().unwrap().status.success() {
+            anyhow::bail!("Tesseract OCR is not installed on your system.\n\n\
+                To install tesseract on Windows:\n  \
+                1. Download the installer from: https://github.com/UB-Mannheim/tesseract/wiki\n  \
+                2. Run the installer and follow the instructions\n  \
+                3. Add tesseract to your PATH environment variable\n  \
+                4. Restart your terminal/command prompt\n\n\
+                After installation, restart your terminal and try again.");
+        }
+        
+        // Initialize Tesseract
+        let tess = Tesseract::new(None, Some("eng"))
+            .map_err(|e| {
+                anyhow::anyhow!("Failed to initialize Tesseract: {}\n\n\
+                    This usually means:\n1. Tesseract is not properly installed\n\
+                    2. Language data files are missing\n\nTo fix:\n  \
+                    1. Reinstall tesseract from https://github.com/UB-Mannheim/tesseract/wiki\n  \
+                    2. Make sure to select 'Additional language data' during installation\n  \
+                    3. Ensure tesseract is in your PATH", e)
+            })?;
+        
+        let text = tess.set_image(_path)
+            .map_err(|e| anyhow::anyhow!("Failed to load image '{}': {}", _path, e))?
+            .get_text()
+            .map_err(|e| anyhow::anyhow!("Failed to extract text from image: {}", e))?;
+        
+        // Get confidence (simplified - would need more complex API calls for per-word confidence)
+        let confidence = 0.85; // Placeholder
+        
+        Ok(OCRResult {
+            text,
+            confidence,
+            bounds: Rect { x: 0, y: 0, width: 0, height: 0 }, // Would need image dimensions
+        })
+    }
+    
+    async fn find_text_on_screen(&self, _text: &str) -> Result<Option<Point>> {
+        // Check if tesseract is available on the system
+        let tesseract_check = std::process::Command::new("where")
+            .arg("tesseract")
+            .output();
+        
+        if tesseract_check.is_err() || !tesseract_check.as_ref().unwrap().status.success() {
+            anyhow::bail!("Tesseract OCR is not installed on your system.\n\n\
+                To install tesseract on Windows:\n  \
+                1. Download the installer from: https://github.com/UB-Mannheim/tesseract/wiki\n  \
+                2. Run the installer and follow the instructions\n  \
+                3. Add tesseract to your PATH environment variable\n  \
+                4. Restart your terminal/command prompt\n\n\
+                After installation, restart your terminal and try again.");
+        }
+        
+        // Take full screen screenshot
+        let temp_path = format!("C:\\\\Temp\\\\g3_ocr_search_{}.png", uuid::Uuid::new_v4());
+        self.take_screenshot(&temp_path, None, None).await?;
+        
+        // Use Tesseract to find text with bounding boxes
+        let tess = Tesseract::new(None, Some("eng"))
+            .map_err(|e| {
+                anyhow::anyhow!("Failed to initialize Tesseract: {}\n\n\
+                    This usually means:\n1. Tesseract is not properly installed\n\
+                    2. Language data files are missing\n\nTo fix:\n  \
+                    1. Reinstall tesseract from https://github.com/UB-Mannheim/tesseract/wiki\n  \
+                    2. Make sure to select 'Additional language data' during installation\n  \
+                    3. Ensure tesseract is in your PATH", e)
+            })?;
+        
+        let full_text = tess.set_image(temp_path.as_str())
+            .map_err(|e| anyhow::anyhow!("Failed to load screenshot: {}", e))?
+            .get_text()
+            .map_err(|e| anyhow::anyhow!("Failed to extract text from screen: {}", e))?;
+        
+        // Clean up temp file
+        let _ = std::fs::remove_file(&temp_path);
+        
+        // Simple text search - full implementation would use get_component_images
+        // to get bounding boxes for each word
+        if full_text.contains(_text) {
+            tracing::warn!("Text found but precise coordinates not available in simplified implementation");
+            Ok(Some(Point { x: 0, y: 0 }))
+        } else {
+            Ok(None)
+        }
     }
 }

crates/g3-computer-control/src/types.rs

@@ -7,3 +7,13 @@ pub struct Rect {
     pub width: i32,
     pub height: i32,
 }
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct TextLocation {
+    pub text: String,
+    pub x: i32,
+    pub y: i32,
+    pub width: i32,
+    pub height: i32,
+    pub confidence: f32,
+}

crates/g3-computer-control/src/webdriver/chrome.rs

@@ -1,428 +0,0 @@
-use super::{WebDriverController, WebElement};
-use anyhow::{Context, Result};
-use async_trait::async_trait;
-use fantoccini::{Client, ClientBuilder};
-use serde_json::Value;
-use std::time::Duration;
-
-/// ChromeDriver WebDriver controller with headless support
-pub struct ChromeDriver {
-    client: Client,
-}
-
-/// Stealth script to hide automation indicators from bot detection
-const STEALTH_SCRIPT: &str = r#"
-    (function() {
-        'use strict';
-        
-        // 1. Override navigator.webdriver to return undefined (like a real browser)
-        Object.defineProperty(navigator, 'webdriver', {
-            get: () => undefined,
-            configurable: true
-        });
-        
-        // 2. Add realistic chrome object that real Chrome has
-        if (!window.chrome) {
-            window.chrome = {};
-        }
-        window.chrome.runtime = {
-            connect: function() {},
-            sendMessage: function() {},
-            onMessage: { addListener: function() {} },
-            onConnect: { addListener: function() {} },
-            id: undefined
-        };
-        window.chrome.loadTimes = function() {
-            return {
-                commitLoadTime: Date.now() / 1000,
-                connectionInfo: 'h2',
-                finishDocumentLoadTime: Date.now() / 1000,
-                finishLoadTime: Date.now() / 1000,
-                firstPaintAfterLoadTime: 0,
-                firstPaintTime: Date.now() / 1000,
-                navigationType: 'Other',
-                npnNegotiatedProtocol: 'h2',
-                requestTime: Date.now() / 1000,
-                startLoadTime: Date.now() / 1000,
-                wasAlternateProtocolAvailable: false,
-                wasFetchedViaSpdy: true,
-                wasNpnNegotiated: true
-            };
-        };
-        window.chrome.csi = function() {
-            return {
-                onloadT: Date.now(),
-                pageT: Date.now() - performance.timing.navigationStart,
-                startE: performance.timing.navigationStart,
-                tran: 15
-            };
-        };
-        
-        // 3. Add realistic plugins array (headless Chrome has empty plugins)
-        Object.defineProperty(navigator, 'plugins', {
-            get: () => {
-                const plugins = [
-                    { name: 'Chrome PDF Plugin', filename: 'internal-pdf-viewer', description: 'Portable Document Format' },
-                    { name: 'Chrome PDF Viewer', filename: 'mhjfbmdgcfjbbpaeojofohoefgiehjai', description: '' },
-                    { name: 'Native Client', filename: 'internal-nacl-plugin', description: '' }
-                ];
-                plugins.item = (i) => plugins[i] || null;
-                plugins.namedItem = (name) => plugins.find(p => p.name === name) || null;
-                plugins.refresh = () => {};
-                Object.setPrototypeOf(plugins, PluginArray.prototype);
-                return plugins;
-            },
-            configurable: true
-        });
-        
-        // 4. Add realistic mimeTypes
-        Object.defineProperty(navigator, 'mimeTypes', {
-            get: () => {
-                const mimeTypes = [
-                    { type: 'application/pdf', suffixes: 'pdf', description: 'Portable Document Format' },
-                    { type: 'application/x-google-chrome-pdf', suffixes: 'pdf', description: 'Portable Document Format' }
-                ];
-                mimeTypes.item = (i) => mimeTypes[i] || null;
-                mimeTypes.namedItem = (name) => mimeTypes.find(m => m.type === name) || null;
-                Object.setPrototypeOf(mimeTypes, MimeTypeArray.prototype);
-                return mimeTypes;
-            },
-            configurable: true
-        });
-        
-        // 5. Fix permissions API to not reveal automation
-        const originalQuery = window.navigator.permissions?.query;
-        if (originalQuery) {
-            window.navigator.permissions.query = (parameters) => {
-                if (parameters.name === 'notifications') {
-                    return Promise.resolve({ state: Notification.permission, onchange: null });
-                }
-                return originalQuery.call(window.navigator.permissions, parameters);
-            };
-        }
-        
-        // 6. Override languages to have realistic values
-        Object.defineProperty(navigator, 'languages', {
-            get: () => ['en-US', 'en'],
-            configurable: true
-        });
-        
-        // 7. Fix hardwareConcurrency (headless often shows different values)
-        Object.defineProperty(navigator, 'hardwareConcurrency', {
-            get: () => 8,
-            configurable: true
-        });
-        
-        // 8. Fix deviceMemory
-        Object.defineProperty(navigator, 'deviceMemory', {
-            get: () => 8,
-            configurable: true
-        });
-        
-        // 9. Remove automation-related properties from window
-        delete window.cdc_adoQpoasnfa76pfcZLmcfl_Array;
-        delete window.cdc_adoQpoasnfa76pfcZLmcfl_Promise;
-        delete window.cdc_adoQpoasnfa76pfcZLmcfl_Symbol;
-        
-        // 10. Fix toString methods to not reveal native code modifications
-        const originalToString = Function.prototype.toString;
-        Function.prototype.toString = function() {
-            if (this === navigator.permissions.query) {
-                return 'function query() { [native code] }';
-            }
-            return originalToString.call(this);
-        };
-    })();
-"#;
-
-impl ChromeDriver {
-    /// Create a new ChromeDriver instance in headless mode
-    ///
-    /// This will connect to ChromeDriver running on the default port (9515).
-    /// ChromeDriver must be installed and available in PATH.
-    pub async fn new_headless() -> Result<Self> {
-        Self::with_port_headless(9515).await
-    }
-
-    /// Create a new ChromeDriver instance with Chrome for Testing binary
-    pub async fn new_headless_with_binary(chrome_binary: &str) -> Result<Self> {
-        Self::with_port_headless_and_binary(9515, Some(chrome_binary)).await
-    }
-
-    /// Create a new ChromeDriver instance with a custom port in headless mode
-    pub async fn with_port_headless(port: u16) -> Result<Self> {
-        Self::with_port_headless_and_binary(port, None).await
-    }
-
-    /// Create a new ChromeDriver instance with a custom port and optional Chrome binary path
-    pub async fn with_port_headless_and_binary(port: u16, chrome_binary: Option<&str>) -> Result<Self> {
-        let url = format!("http://localhost:{}", port);
-
-        let mut caps = serde_json::Map::new();
-        caps.insert(
-            "browserName".to_string(),
-            Value::String("chrome".to_string()),
-        );
-
-        // Set up Chrome options for headless mode
-        let mut chrome_options = serde_json::Map::new();
-        chrome_options.insert(
-            "args".to_string(),
-            Value::Array(vec![
-                // Use a unique temp directory to avoid conflicts with running Chrome instances
-                Value::String(format!("--user-data-dir=/tmp/g3-chrome-{}", std::process::id())),
-                Value::String("--headless=new".to_string()),
-                Value::String("--disable-gpu".to_string()),
-                Value::String("--no-sandbox".to_string()),
-                Value::String("--disable-dev-shm-usage".to_string()),
-                Value::String("--window-size=1920,1080".to_string()),
-                Value::String("--disable-blink-features=AutomationControlled".to_string()),
-                // Stealth: Set a realistic user-agent (removes HeadlessChrome identifier)
-                Value::String("--user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36".to_string()),
-                // Stealth: Disable automation-related info bars
-                Value::String("--disable-infobars".to_string()),
-                // Stealth: Set realistic language
-                Value::String("--lang=en-US,en".to_string()),
-                // Stealth: Disable extensions to avoid detection
-                Value::String("--disable-extensions".to_string()),
-                // Prevent first-run UI and default browser check popups
-                Value::String("--no-first-run".to_string()),
-                Value::String("--no-default-browser-check".to_string()),
-                Value::String("--disable-popup-blocking".to_string()),
-            ]),
-        );
-
-        // Exclude automation switches to hide webdriver detection
-        chrome_options.insert(
-            "excludeSwitches".to_string(),
-            Value::Array(vec![
-                Value::String("enable-automation".to_string()),
-            ]),
-        );
-
-        // Disable automation extension
-        chrome_options.insert(
-            "useAutomationExtension".to_string(),
-            Value::Bool(false),
-        );
-
-        // If a custom Chrome binary is specified, use it
-        if let Some(binary) = chrome_binary {
-            chrome_options.insert("binary".to_string(), Value::String(binary.to_string()));
-        }
-
-        caps.insert(
-            "goog:chromeOptions".to_string(),
-            Value::Object(chrome_options),
-        );
-
-        // Use a timeout for the connection attempt to avoid hanging indefinitely
-        let mut builder = ClientBuilder::native();
-        let connect_future = builder
-            .capabilities(caps)
-            .connect(&url);
-        
-        let client = tokio::time::timeout(Duration::from_secs(30), connect_future)
-            .await
-            .context("Connection to ChromeDriver timed out after 30 seconds")?
-            .context("Failed to connect to ChromeDriver")?;
-
-        let driver = Self { client };
-        
-        // Inject stealth script immediately after connection
-        // This ensures it runs before any navigation and on every new document
-        // Ignore errors as this is best-effort stealth
-        let _ = driver.client.execute(STEALTH_SCRIPT, vec![]).await;
-        
-        Ok(driver)
-    }
-
-    /// Go back in browser history
-    pub async fn back(&mut self) -> Result<()> {
-        self.client.back().await?;
-        Ok(())
-    }
-
-    /// Go forward in browser history
-    pub async fn forward(&mut self) -> Result<()> {
-        self.client.forward().await?;
-        Ok(())
-    }
-
-    /// Refresh the current page
-    pub async fn refresh(&mut self) -> Result<()> {
-        self.client.refresh().await?;
-        Ok(())
-    }
-
-    /// Get all window handles
-    pub async fn window_handles(&mut self) -> Result<Vec<String>> {
-        let handles = self.client.windows().await?;
-        Ok(handles.into_iter().map(|h| h.into()).collect())
-    }
-
-    /// Switch to a window by handle
-    pub async fn switch_to_window(&mut self, handle: &str) -> Result<()> {
-        let window_handle: fantoccini::wd::WindowHandle = handle.to_string().try_into()?;
-        self.client.switch_to_window(window_handle).await?;
-        Ok(())
-    }
-
-    /// Get the current window handle
-    pub async fn current_window_handle(&mut self) -> Result<String> {
-        Ok(self.client.window().await?.into())
-    }
-
-    /// Close the current window
-    pub async fn close_window(&mut self) -> Result<()> {
-        self.client.close_window().await?;
-        Ok(())
-    }
-
-    /// Create a new window/tab
-    pub async fn new_window(&mut self, is_tab: bool) -> Result<String> {
-        let response = self.client.new_window(is_tab).await?;
-        Ok(response.handle.into())
-    }
-
-    /// Get cookies
-    pub async fn get_cookies(&mut self) -> Result<Vec<fantoccini::cookies::Cookie<'static>>> {
-        Ok(self.client.get_all_cookies().await?)
-    }
-
-    /// Add a cookie
-    pub async fn add_cookie(&mut self, cookie: fantoccini::cookies::Cookie<'static>) -> Result<()> {
-        self.client.add_cookie(cookie).await?;
-        Ok(())
-    }
-
-    /// Delete all cookies
-    pub async fn delete_all_cookies(&mut self) -> Result<()> {
-        self.client.delete_all_cookies().await?;
-        Ok(())
-    }
-
-    /// Wait for an element to appear (with timeout)
-    pub async fn wait_for_element(
-        &mut self,
-        selector: &str,
-        timeout: Duration,
-    ) -> Result<WebElement> {
-        let start = std::time::Instant::now();
-        let poll_interval = Duration::from_millis(100);
-
-        loop {
-            if let Ok(elem) = self.find_element(selector).await {
-                return Ok(elem);
-            }
-
-            if start.elapsed() >= timeout {
-                anyhow::bail!("Timeout waiting for element: {}", selector);
-            }
-
-            tokio::time::sleep(poll_interval).await;
-        }
-    }
-
-    /// Wait for an element to be visible (with timeout)
-    pub async fn wait_for_visible(
-        &mut self,
-        selector: &str,
-        timeout: Duration,
-    ) -> Result<WebElement> {
-        let start = std::time::Instant::now();
-        let poll_interval = Duration::from_millis(100);
-
-        loop {
-            if let Ok(elem) = self.find_element(selector).await {
-                if elem.is_displayed().await.unwrap_or(false) {
-                    return Ok(elem);
-                }
-            }
-
-            if start.elapsed() >= timeout {
-                anyhow::bail!("Timeout waiting for element to be visible: {}", selector);
-            }
-
-            tokio::time::sleep(poll_interval).await;
-        }
-    }
-}
-
-#[async_trait]
-impl WebDriverController for ChromeDriver {
-    async fn navigate(&mut self, url: &str) -> Result<()> {
-        self.client.goto(url).await?;
-        // Inject stealth script after navigation to hide automation indicators
-        // Ignore errors as some pages may have strict CSP
-        let _ = self.client.execute(STEALTH_SCRIPT, vec![]).await;
-        Ok(())
-    }
-
-    async fn current_url(&self) -> Result<String> {
-        Ok(self.client.current_url().await?.to_string())
-    }
-
-    async fn title(&self) -> Result<String> {
-        Ok(self.client.title().await?)
-    }
-
-    async fn find_element(&mut self, selector: &str) -> Result<WebElement> {
-        let elem = self
-            .client
-            .find(fantoccini::Locator::Css(selector))
-            .await
-            .context(format!(
-                "Failed to find element with selector: {}",
-                selector
-            ))?;
-        Ok(WebElement { inner: elem })
-    }
-
-    async fn find_elements(&mut self, selector: &str) -> Result<Vec<WebElement>> {
-        let elems = self
-            .client
-            .find_all(fantoccini::Locator::Css(selector))
-            .await?;
-        Ok(elems
-            .into_iter()
-            .map(|inner| WebElement { inner })
-            .collect())
-    }
-
-    async fn execute_script(&mut self, script: &str, args: Vec<Value>) -> Result<Value> {
-        Ok(self.client.execute(script, args).await?)
-    }
-
-    async fn page_source(&self) -> Result<String> {
-        Ok(self.client.source().await?)
-    }
-
-    async fn screenshot(&mut self, path: &str) -> Result<()> {
-        let screenshot_data = self.client.screenshot().await?;
-
-        // Expand tilde in path
-        let expanded_path = shellexpand::tilde(path);
-        let path_str = expanded_path.as_ref();
-
-        // Create parent directories if needed
-        if let Some(parent) = std::path::Path::new(path_str).parent() {
-            std::fs::create_dir_all(parent)
-                .context("Failed to create parent directories for screenshot")?;
-        }
-
-        std::fs::write(path_str, screenshot_data).context("Failed to write screenshot to file")?;
-
-        Ok(())
-    }
-
-    async fn close(&mut self) -> Result<()> {
-        self.client.close_window().await?;
-        Ok(())
-    }
-
-    async fn quit(mut self) -> Result<()> {
-        self.client.close().await?;
-        Ok(())
-    }
-}

crates/g3-computer-control/src/webdriver/diagnostics.rs

@@ -1,549 +0,0 @@
-//! Chrome WebDriver diagnostics module
-//!
-//! Checks for common setup issues and provides detailed fix suggestions.
-
-use std::path::PathBuf;
-use std::process::Command;
-
-/// Result of a diagnostic check
-#[derive(Debug, Clone)]
-pub struct DiagnosticResult {
-    pub name: String,
-    pub status: DiagnosticStatus,
-    pub message: String,
-    pub fix_suggestion: Option<String>,
-}
-
-#[derive(Debug, Clone, PartialEq)]
-pub enum DiagnosticStatus {
-    Ok,
-    Warning,
-    Error,
-}
-
-/// Full diagnostic report for Chrome headless setup
-#[derive(Debug)]
-pub struct ChromeDiagnosticReport {
-    pub results: Vec<DiagnosticResult>,
-    pub chrome_version: Option<String>,
-    pub chromedriver_version: Option<String>,
-    pub chrome_path: Option<PathBuf>,
-    pub chromedriver_path: Option<PathBuf>,
-    pub config_chrome_binary: Option<String>,
-}
-
-impl ChromeDiagnosticReport {
-    /// Check if all diagnostics passed
-    pub fn all_ok(&self) -> bool {
-        self.results.iter().all(|r| r.status == DiagnosticStatus::Ok)
-    }
-
-    /// Check if there are any errors (not just warnings)
-    pub fn has_errors(&self) -> bool {
-        self.results.iter().any(|r| r.status == DiagnosticStatus::Error)
-    }
-
-    /// Format the report as a human-readable string
-    pub fn format_report(&self) -> String {
-        let mut output = String::new();
-        output.push_str("\n╔══════════════════════════════════════════════════════════════╗\n");
-        output.push_str("║           Chrome Headless Diagnostic Report                  ║\n");
-        output.push_str("╚══════════════════════════════════════════════════════════════╝\n\n");
-
-        // Summary section
-        output.push_str("📋 **Summary**\n");
-        if let Some(ref path) = self.chrome_path {
-            output.push_str(&format!("   Chrome: {}\n", path.display()));
-        }
-        if let Some(ref ver) = self.chrome_version {
-            output.push_str(&format!("   Chrome Version: {}\n", ver));
-        }
-        if let Some(ref path) = self.chromedriver_path {
-            output.push_str(&format!("   ChromeDriver: {}\n", path.display()));
-        }
-        if let Some(ref ver) = self.chromedriver_version {
-            output.push_str(&format!("   ChromeDriver Version: {}\n", ver));
-        }
-        if let Some(ref binary) = self.config_chrome_binary {
-            output.push_str(&format!("   Config chrome_binary: {}\n", binary));
-        }
-        output.push_str("\n");
-
-        // Results section
-        output.push_str("🔍 **Diagnostic Results**\n\n");
-        
-        for result in &self.results {
-            let icon = match result.status {
-                DiagnosticStatus::Ok => "✅",
-                DiagnosticStatus::Warning => "⚠️",
-                DiagnosticStatus::Error => "❌",
-            };
-            output.push_str(&format!("{} **{}**\n", icon, result.name));
-            output.push_str(&format!("   {}\n", result.message));
-            
-            if let Some(ref fix) = result.fix_suggestion {
-                output.push_str(&format!("   💡 Fix: {}\n", fix));
-            }
-            output.push_str("\n");
-        }
-
-        // Overall status
-        if self.all_ok() {
-            output.push_str("🎉 **All checks passed!** Chrome headless is ready to use.\n");
-        } else if self.has_errors() {
-            output.push_str("\n🛠️ **Action Required**\n");
-            output.push_str("   Some issues need to be fixed before Chrome headless will work.\n");
-            output.push_str("   You can ask me to help fix these issues.\n");
-        } else {
-            output.push_str("\n⚠️ **Warnings Present**\n");
-            output.push_str("   Chrome headless may work, but there are potential issues.\n");
-        }
-
-        output
-    }
-}
-
-/// Run all Chrome headless diagnostics
-pub fn run_diagnostics(config_chrome_binary: Option<&str>) -> ChromeDiagnosticReport {
-    // Expand tilde in the configured chrome_binary path so that paths like
-    // "~/.chrome-for-testing/..." resolve correctly when checking existence.
-    // Keep the original value for display purposes in the report summary.
-    let expanded_binary = config_chrome_binary
-        .map(|p| shellexpand::tilde(p).into_owned());
-    let effective_binary = expanded_binary.as_deref();
-
-    let mut results = Vec::new();
-    let mut chrome_version = None;
-    let mut chromedriver_version = None;
-    let mut chrome_path = None;
-    let mut chromedriver_path = None;
-
-    // 1. Check for ChromeDriver in PATH
-    let chromedriver_check = check_chromedriver_installed();
-    if chromedriver_check.status == DiagnosticStatus::Ok {
-        chromedriver_path = find_chromedriver_path();
-        chromedriver_version = get_chromedriver_version();
-    }
-    results.push(chromedriver_check);
-
-    // 2. Check for Chrome installation
-    let chrome_check = check_chrome_installed(effective_binary);
-    if chrome_check.status == DiagnosticStatus::Ok {
-        chrome_path = find_chrome_path(effective_binary);
-        chrome_version = get_chrome_version(effective_binary);
-    }
-    results.push(chrome_check);
-
-    // 3. Check version compatibility
-    if chrome_version.is_some() && chromedriver_version.is_some() {
-        results.push(check_version_compatibility(
-            chrome_version.as_deref(),
-            chromedriver_version.as_deref(),
-        ));
-    }
-
-    // 4. Check config.toml chrome_binary setting
-    results.push(check_config_chrome_binary(effective_binary, chrome_path.as_ref()));
-
-    // 5. Check for Chrome for Testing installation
-    results.push(check_chrome_for_testing());
-
-    // 6. Check ChromeDriver is executable (macOS quarantine)
-    if chromedriver_path.is_some() {
-        results.push(check_chromedriver_executable());
-    }
-
-    ChromeDiagnosticReport {
-        results,
-        chrome_version,
-        chromedriver_version,
-        chrome_path,
-        chromedriver_path,
-        // Show the original (unexpanded) config value in the report summary
-        config_chrome_binary: config_chrome_binary.map(String::from),
-    }
-}
-
-/// Check if ChromeDriver is installed and in PATH
-fn check_chromedriver_installed() -> DiagnosticResult {
-    match Command::new("which").arg("chromedriver").output() {
-        Ok(output) if output.status.success() => {
-            DiagnosticResult {
-                name: "ChromeDriver Installation".to_string(),
-                status: DiagnosticStatus::Ok,
-                message: "ChromeDriver found in PATH".to_string(),
-                fix_suggestion: None,
-            }
-        }
-        _ => {
-            // Check common locations
-            let common_paths = [
-                dirs::home_dir().map(|h| h.join(".chrome-for-testing/chromedriver-mac-arm64/chromedriver")),
-                dirs::home_dir().map(|h| h.join(".chrome-for-testing/chromedriver-mac-x64/chromedriver")),
-                Some(PathBuf::from("/usr/local/bin/chromedriver")),
-                Some(PathBuf::from("/opt/homebrew/bin/chromedriver")),
-            ];
-
-            for path in common_paths.iter().flatten() {
-                if path.exists() {
-                    return DiagnosticResult {
-                        name: "ChromeDriver Installation".to_string(),
-                        status: DiagnosticStatus::Warning,
-                        message: format!("ChromeDriver found at {} but not in PATH", path.display()),
-                        fix_suggestion: Some(format!(
-                            "Add to your shell config (~/.zshrc or ~/.bashrc):\nexport PATH=\"{}:$PATH\"",
-                            path.parent().unwrap().display()
-                        )),
-                    };
-                }
-            }
-
-            DiagnosticResult {
-                name: "ChromeDriver Installation".to_string(),
-                status: DiagnosticStatus::Error,
-                message: "ChromeDriver not found".to_string(),
-                fix_suggestion: Some(
-                    "Install ChromeDriver using one of these methods:\n\
-                     1. Run: ./scripts/setup-chrome-for-testing.sh (recommended)\n\
-                     2. Or: brew install chromedriver".to_string()
-                ),
-            }
-        }
-    }
-}
-
-/// Check if Chrome is installed
-fn check_chrome_installed(config_binary: Option<&str>) -> DiagnosticResult {
-    // First check configured binary
-    if let Some(binary) = config_binary {
-        if PathBuf::from(binary).exists() {
-            return DiagnosticResult {
-                name: "Chrome Installation".to_string(),
-                status: DiagnosticStatus::Ok,
-                message: format!("Chrome found at configured path: {}", binary),
-                fix_suggestion: None,
-            };
-        } else {
-            return DiagnosticResult {
-                name: "Chrome Installation".to_string(),
-                status: DiagnosticStatus::Error,
-                message: format!("Configured chrome_binary not found: {}", binary),
-                fix_suggestion: Some(
-                    "Update chrome_binary in ~/.config/g3/config.toml to a valid Chrome path,\n\
-                     or remove it to use system Chrome".to_string()
-                ),
-            };
-        }
-    }
-
-    // Check common Chrome locations
-    let chrome_paths = get_chrome_search_paths();
-    
-    for path in &chrome_paths {
-        if path.exists() {
-            return DiagnosticResult {
-                name: "Chrome Installation".to_string(),
-                status: DiagnosticStatus::Ok,
-                message: format!("Chrome found at: {}", path.display()),
-                fix_suggestion: None,
-            };
-        }
-    }
-
-    DiagnosticResult {
-        name: "Chrome Installation".to_string(),
-        status: DiagnosticStatus::Error,
-        message: "Chrome/Chromium not found".to_string(),
-        fix_suggestion: Some(
-            "Install Chrome using one of these methods:\n\
-             1. Run: ./scripts/setup-chrome-for-testing.sh (recommended)\n\
-             2. Download from: https://www.google.com/chrome/\n\
-             3. Or: brew install --cask google-chrome".to_string()
-        ),
-    }
-}
-
-/// Check Chrome and ChromeDriver version compatibility
-fn check_version_compatibility(
-    chrome_ver: Option<&str>,
-    chromedriver_ver: Option<&str>,
-) -> DiagnosticResult {
-    let chrome_major = chrome_ver.and_then(extract_major_version);
-    let driver_major = chromedriver_ver.and_then(extract_major_version);
-
-    match (chrome_major, driver_major) {
-        (Some(cv), Some(dv)) if cv == dv => {
-            DiagnosticResult {
-                name: "Version Compatibility".to_string(),
-                status: DiagnosticStatus::Ok,
-                message: format!("Chrome ({}) and ChromeDriver ({}) versions match", cv, dv),
-                fix_suggestion: None,
-            }
-        }
-        (Some(cv), Some(dv)) => {
-            DiagnosticResult {
-                name: "Version Compatibility".to_string(),
-                status: DiagnosticStatus::Error,
-                message: format!(
-                    "Version mismatch! Chrome is v{} but ChromeDriver is v{}",
-                    cv, dv
-                ),
-                fix_suggestion: Some(
-                    "Fix version mismatch:\n\
-                     1. Run: ./scripts/setup-chrome-for-testing.sh (installs matching versions)\n\
-                     2. Or update ChromeDriver: brew upgrade chromedriver".to_string()
-                ),
-            }
-        }
-        _ => {
-            DiagnosticResult {
-                name: "Version Compatibility".to_string(),
-                status: DiagnosticStatus::Warning,
-                message: "Could not determine version compatibility".to_string(),
-                fix_suggestion: None,
-            }
-        }
-    }
-}
-
-/// Check config.toml chrome_binary setting
-fn check_config_chrome_binary(
-    config_binary: Option<&str>,
-    detected_chrome: Option<&PathBuf>,
-) -> DiagnosticResult {
-    match (config_binary, detected_chrome) {
-        (Some(binary), _) if PathBuf::from(binary).exists() => {
-            DiagnosticResult {
-                name: "Config chrome_binary".to_string(),
-                status: DiagnosticStatus::Ok,
-                message: "chrome_binary is configured and valid".to_string(),
-                fix_suggestion: None,
-            }
-        }
-        (Some(binary), _) => {
-            DiagnosticResult {
-                name: "Config chrome_binary".to_string(),
-                status: DiagnosticStatus::Error,
-                message: format!("chrome_binary path does not exist: {}", binary),
-                fix_suggestion: Some(
-                    "Update ~/.config/g3/config.toml with a valid chrome_binary path".to_string()
-                ),
-            }
-        }
-        (None, Some(chrome)) => {
-            // Check if it's Chrome for Testing - recommend configuring it
-            let chrome_str = chrome.to_string_lossy();
-            if chrome_str.contains("chrome-for-testing") || chrome_str.contains("Chrome for Testing") {
-                DiagnosticResult {
-                    name: "Config chrome_binary".to_string(),
-                    status: DiagnosticStatus::Warning,
-                    message: "Chrome for Testing detected but not configured in config.toml".to_string(),
-                    fix_suggestion: Some(format!(
-                        "Add to ~/.config/g3/config.toml:\n\
-                         [webdriver]\n\
-                         chrome_binary = \"{}\"",
-                        chrome.display()
-                    )),
-                }
-            } else {
-                DiagnosticResult {
-                    name: "Config chrome_binary".to_string(),
-                    status: DiagnosticStatus::Ok,
-                    message: "Using system Chrome (no chrome_binary configured)".to_string(),
-                    fix_suggestion: None,
-                }
-            }
-        }
-        (None, None) => {
-            DiagnosticResult {
-                name: "Config chrome_binary".to_string(),
-                status: DiagnosticStatus::Warning,
-                message: "No chrome_binary configured and no Chrome detected".to_string(),
-                fix_suggestion: Some(
-                    "Install Chrome and optionally configure chrome_binary in config.toml".to_string()
-                ),
-            }
-        }
-    }
-}
-
-/// Check for Chrome for Testing installation
-fn check_chrome_for_testing() -> DiagnosticResult {
-    let cft_dir = dirs::home_dir().map(|h| h.join(".chrome-for-testing"));
-    
-    match cft_dir {
-        Some(dir) if dir.exists() => {
-            // Check for both Chrome and ChromeDriver
-            let has_chrome = dir.join("chrome-mac-arm64").exists() 
-                || dir.join("chrome-mac-x64").exists();
-            let has_driver = dir.join("chromedriver-mac-arm64").exists()
-                || dir.join("chromedriver-mac-x64").exists();
-
-            if has_chrome && has_driver {
-                DiagnosticResult {
-                    name: "Chrome for Testing".to_string(),
-                    status: DiagnosticStatus::Ok,
-                    message: "Chrome for Testing is installed with matching ChromeDriver".to_string(),
-                    fix_suggestion: None,
-                }
-            } else if has_chrome {
-                DiagnosticResult {
-                    name: "Chrome for Testing".to_string(),
-                    status: DiagnosticStatus::Warning,
-                    message: "Chrome for Testing found but ChromeDriver is missing".to_string(),
-                    fix_suggestion: Some(
-                        "Run: ./scripts/setup-chrome-for-testing.sh to install matching ChromeDriver".to_string()
-                    ),
-                }
-            } else {
-                DiagnosticResult {
-                    name: "Chrome for Testing".to_string(),
-                    status: DiagnosticStatus::Warning,
-                    message: "Chrome for Testing directory exists but is incomplete".to_string(),
-                    fix_suggestion: Some(
-                        "Run: ./scripts/setup-chrome-for-testing.sh to reinstall".to_string()
-                    ),
-                }
-            }
-        }
-        _ => {
-            DiagnosticResult {
-                name: "Chrome for Testing".to_string(),
-                status: DiagnosticStatus::Ok,
-                message: "Chrome for Testing not installed (using system Chrome)".to_string(),
-                fix_suggestion: None,
-            }
-        }
-    }
-}
-
-/// Check if ChromeDriver is executable (macOS quarantine issue)
-fn check_chromedriver_executable() -> DiagnosticResult {
-    match Command::new("chromedriver").arg("--version").output() {
-        Ok(output) if output.status.success() => {
-            DiagnosticResult {
-                name: "ChromeDriver Executable".to_string(),
-                status: DiagnosticStatus::Ok,
-                message: "ChromeDriver is executable".to_string(),
-                fix_suggestion: None,
-            }
-        }
-        Ok(_) => {
-            DiagnosticResult {
-                name: "ChromeDriver Executable".to_string(),
-                status: DiagnosticStatus::Error,
-                message: "ChromeDriver found but failed to execute".to_string(),
-                fix_suggestion: Some(
-                    "Remove macOS quarantine attribute:\n\
-                     xattr -d com.apple.quarantine $(which chromedriver)".to_string()
-                ),
-            }
-        }
-        Err(_) => {
-            DiagnosticResult {
-                name: "ChromeDriver Executable".to_string(),
-                status: DiagnosticStatus::Error,
-                message: "ChromeDriver not executable or not in PATH".to_string(),
-                fix_suggestion: Some(
-                    "Ensure ChromeDriver is in PATH and executable:\n\
-                     chmod +x $(which chromedriver)".to_string()
-                ),
-            }
-        }
-    }
-}
-
-// Helper functions
-
-fn find_chromedriver_path() -> Option<PathBuf> {
-    Command::new("which")
-        .arg("chromedriver")
-        .output()
-        .ok()
-        .filter(|o| o.status.success())
-        .map(|o| PathBuf::from(String::from_utf8_lossy(&o.stdout).trim()))
-}
-
-fn find_chrome_path(config_binary: Option<&str>) -> Option<PathBuf> {
-    if let Some(binary) = config_binary {
-        let path = PathBuf::from(binary);
-        if path.exists() {
-            return Some(path);
-        }
-    }
-
-    for path in get_chrome_search_paths() {
-        if path.exists() {
-            return Some(path);
-        }
-    }
-    None
-}
-
-fn get_chrome_search_paths() -> Vec<PathBuf> {
-    let mut paths = vec![
-        // macOS paths
-        PathBuf::from("/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"),
-        PathBuf::from("/Applications/Chromium.app/Contents/MacOS/Chromium"),
-    ];
-
-    // Chrome for Testing paths
-    if let Some(home) = dirs::home_dir() {
-        paths.push(home.join(".chrome-for-testing/chrome-mac-arm64/Google Chrome for Testing.app/Contents/MacOS/Google Chrome for Testing"));
-        paths.push(home.join(".chrome-for-testing/chrome-mac-x64/Google Chrome for Testing.app/Contents/MacOS/Google Chrome for Testing"));
-    }
-
-    // Linux paths
-    paths.extend([
-        PathBuf::from("/usr/bin/google-chrome"),
-        PathBuf::from("/usr/bin/google-chrome-stable"),
-        PathBuf::from("/usr/bin/chromium"),
-        PathBuf::from("/usr/bin/chromium-browser"),
-    ]);
-
-    paths
-}
-
-fn get_chromedriver_version() -> Option<String> {
-    Command::new("chromedriver")
-        .arg("--version")
-        .output()
-        .ok()
-        .filter(|o| o.status.success())
-        .map(|o| String::from_utf8_lossy(&o.stdout).trim().to_string())
-}
-
-fn get_chrome_version(config_binary: Option<&str>) -> Option<String> {
-    let chrome_path = find_chrome_path(config_binary)?;
-    
-    Command::new(&chrome_path)
-        .arg("--version")
-        .output()
-        .ok()
-        .filter(|o| o.status.success())
-        .map(|o| String::from_utf8_lossy(&o.stdout).trim().to_string())
-}
-
-fn extract_major_version(version_str: &str) -> Option<u32> {
-    // Extract version number from strings like:
-    // "Google Chrome 120.0.6099.109"
-    // "ChromeDriver 120.0.6099.109"
-    version_str
-        .split_whitespace()
-        .find(|s| s.chars().next().map(|c| c.is_ascii_digit()).unwrap_or(false))
-        .and_then(|v| v.split('.').next())
-        .and_then(|v| v.parse().ok())
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_extract_major_version() {
-        assert_eq!(extract_major_version("Google Chrome 120.0.6099.109"), Some(120));
-        assert_eq!(extract_major_version("ChromeDriver 120.0.6099.109"), Some(120));
-        assert_eq!(extract_major_version("120.0.6099.109"), Some(120));
-        assert_eq!(extract_major_version("invalid"), None);
-    }
-}

crates/g3-computer-control/src/webdriver/mod.rs

@@ -1,6 +1,4 @@
 pub mod safari;
-pub mod chrome;
-pub mod diagnostics;
 
 use anyhow::Result;
 use async_trait::async_trait;
@@ -107,13 +105,7 @@ impl WebElement {
     
     /// Find multiple child elements by CSS selector
     pub async fn find_elements(&mut self, selector: &str) -> Result<Vec<WebElement>> {
-        let elems = self
-            .inner
-            .find_all(fantoccini::Locator::Css(selector))
-            .await?;
-        Ok(elems
-            .into_iter()
-            .map(|inner| WebElement { inner })
-            .collect())
+        let elems = self.inner.find_all(fantoccini::Locator::Css(selector)).await?;
+        Ok(elems.into_iter().map(|inner| WebElement { inner }).collect())
     }
 }

crates/g3-computer-control/src/webdriver/safari.rs

@@ -29,10 +29,7 @@ impl SafariDriver {
         let url = format!("http://localhost:{}", port);
         
         let mut caps = serde_json::Map::new();
-        caps.insert(
-            "browserName".to_string(),
-            Value::String("safari".to_string()),
-        );
+        caps.insert("browserName".to_string(), Value::String("safari".to_string()));
         
         let client = ClientBuilder::native()
             .capabilities(caps)
@@ -64,7 +61,9 @@ impl SafariDriver {
     /// Get all window handles
     pub async fn window_handles(&mut self) -> Result<Vec<String>> {
         let handles = self.client.windows().await?;
-        Ok(handles.into_iter().map(|h| h.into()).collect())
+        Ok(handles.into_iter()
+            .map(|h| h.into())
+            .collect())
     }
     
     /// Switch to a window by handle
@@ -110,11 +109,7 @@ impl SafariDriver {
     }
     
     /// Wait for an element to appear (with timeout)
-    pub async fn wait_for_element(
-        &mut self,
-        selector: &str,
-        timeout: Duration,
-    ) -> Result<WebElement> {
+    pub async fn wait_for_element(&mut self, selector: &str, timeout: Duration) -> Result<WebElement> {
         let start = std::time::Instant::now();
         let poll_interval = Duration::from_millis(100);
         
@@ -132,11 +127,7 @@ impl SafariDriver {
     }
     
     /// Wait for an element to be visible (with timeout)
-    pub async fn wait_for_visible(
-        &mut self,
-        selector: &str,
-        timeout: Duration,
-    ) -> Result<WebElement> {
+    pub async fn wait_for_visible(&mut self, selector: &str, timeout: Duration) -> Result<WebElement> {
         let start = std::time::Instant::now();
         let poll_interval = Duration::from_millis(100);
         
@@ -172,26 +163,14 @@ impl WebDriverController for SafariDriver {
     }
     
     async fn find_element(&mut self, selector: &str) -> Result<WebElement> {
-        let elem = self
-            .client
-            .find(fantoccini::Locator::Css(selector))
-            .await
-            .context(format!(
-                "Failed to find element with selector: {}",
-                selector
-            ))?;
+        let elem = self.client.find(fantoccini::Locator::Css(selector)).await
+            .context(format!("Failed to find element with selector: {}", selector))?;
         Ok(WebElement { inner: elem })
     }
     
     async fn find_elements(&mut self, selector: &str) -> Result<Vec<WebElement>> {
-        let elems = self
-            .client
-            .find_all(fantoccini::Locator::Css(selector))
-            .await?;
-        Ok(elems
-            .into_iter()
-            .map(|inner| WebElement { inner })
-            .collect())
+        let elems = self.client.find_all(fantoccini::Locator::Css(selector)).await?;
+        Ok(elems.into_iter().map(|inner| WebElement { inner }).collect())
     }
     
     async fn execute_script(&mut self, script: &str, args: Vec<Value>) -> Result<Value> {
@@ -215,7 +194,8 @@ impl WebDriverController for SafariDriver {
                 .context("Failed to create parent directories for screenshot")?;
         }
         
-        std::fs::write(path_str, screenshot_data).context("Failed to write screenshot to file")?;
+        std::fs::write(path_str, screenshot_data)
+            .context("Failed to write screenshot to file")?;
         
         Ok(())
     }

crates/g3-computer-control/tests/integration_test.rs

@@ -4,33 +4,13 @@ use g3_computer_control::*;
 async fn test_screenshot() {
     let controller = create_controller().expect("Failed to create controller");
     
-    // Test that screenshot without window_id fails with appropriate error
+    // Take screenshot
     let path = "/tmp/test_screenshot.png";
     let result = controller.take_screenshot(path, None, None).await;
-    assert!(
-        result.is_err(),
-        "Expected error when window_id is not provided"
-    );
+    assert!(result.is_ok(), "Failed to take screenshot: {:?}", result.err());
     
-    let error_msg = result.unwrap_err().to_string();
-    assert!(
-        error_msg.contains("window_id is required"),
-        "Expected error message about window_id being required, got: {}",
-        error_msg
-    );
-}
-
-#[tokio::test]
-async fn test_screenshot_with_window() {
-    let controller = create_controller().expect("Failed to create controller");
-
-    // Take screenshot of Finder (should always be available on macOS)
-    let path = "/tmp/test_screenshot_finder.png";
-    let result = controller.take_screenshot(path, None, Some("Finder")).await;
-
-    // This test may fail if Finder is not running, so we just check it doesn't panic
-    // and returns a proper Result
-    let _ = result; // Don't assert success since Finder might not be visible
+    // Verify file exists
+    assert!(std::path::Path::new(path).exists(), "Screenshot file was not created");
     
     // Clean up
     let _ = std::fs::remove_file(path);

crates/g3-computer-control/vision-bridge/Package.swift

@@ -0,0 +1,24 @@
+// swift-tools-version:5.9
+import PackageDescription
+
+let package = Package(
+    name: "VisionBridge",
+    platforms: [
+        .macOS(.v11)
+    ],
+    products: [
+        .library(
+            name: "VisionBridge",
+            type: .dynamic,
+            targets: ["VisionBridge"]
+        ),
+    ],
+    targets: [
+        .target(
+            name: "VisionBridge",
+            dependencies: [],
+            path: "Sources/VisionBridge",
+            publicHeadersPath: "."
+        ),
+    ]
+)

crates/g3-computer-control/vision-bridge/Sources/VisionBridge/VisionBridge.h

@@ -0,0 +1,39 @@
+#ifndef VisionBridge_h
+#define VisionBridge_h
+
+#include <stdint.h>
+#include <stdbool.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+// Text box structure for FFI
+typedef struct {
+    const char* text;
+    uint32_t text_len;
+    int32_t x;
+    int32_t y;
+    int32_t width;
+    int32_t height;
+    float confidence;
+} VisionTextBox;
+
+// Recognize text in an image and return bounding boxes
+// Returns true on success, false on failure
+// Caller must free the returned boxes using vision_free_boxes
+bool vision_recognize_text(
+    const char* image_path,
+    uint32_t image_path_len,
+    VisionTextBox** out_boxes,
+    uint32_t* out_count
+);
+
+// Free memory allocated by vision_recognize_text
+void vision_free_boxes(VisionTextBox* boxes, uint32_t count);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* VisionBridge_h */

crates/g3-computer-control/vision-bridge/Sources/VisionBridge/VisionOCR.swift

@@ -0,0 +1,145 @@
+import Foundation
+import Vision
+import AppKit
+import CoreGraphics
+
+// MARK: - C Bridge Functions
+
+@_cdecl("vision_recognize_text")
+public func vision_recognize_text(
+    _ imagePath: UnsafePointer<CChar>,
+    _ imagePathLen: UInt32,
+    _ outBoxes: UnsafeMutablePointer<UnsafeMutableRawPointer?>,
+    _ outCount: UnsafeMutablePointer<UInt32>
+) -> Bool {
+    // Convert C string to Swift String
+    guard let pathData = Data(bytes: imagePath, count: Int(imagePathLen)).withUnsafeBytes({
+        String(bytes: $0, encoding: .utf8)
+    }) else {
+        return false
+    }
+    
+    let path = pathData.trimmingCharacters(in: .whitespaces)
+    
+    // Load image
+    guard let image = NSImage(contentsOfFile: path),
+          let cgImage = image.cgImage(forProposedRect: nil, context: nil, hints: nil) else {
+        return false
+    }
+    
+    // Perform OCR
+    var textBoxes: [CTextBox] = []
+    let semaphore = DispatchSemaphore(value: 0)
+    var success = false
+    
+    let request = VNRecognizeTextRequest { request, error in
+        defer { semaphore.signal() }
+        
+        if let error = error {
+            print("Vision OCR error: \(error.localizedDescription)")
+            return
+        }
+        
+        guard let observations = request.results as? [VNRecognizedTextObservation] else {
+            return
+        }
+        
+        let imageSize = CGSize(width: cgImage.width, height: cgImage.height)
+        
+        for observation in observations {
+            guard let candidate = observation.topCandidates(1).first else { continue }
+            
+            let text = candidate.string
+            let boundingBox = observation.boundingBox
+            
+            // Convert normalized coordinates (bottom-left origin) to pixel coordinates (top-left origin)
+            let x = Int32(boundingBox.origin.x * imageSize.width)
+            let y = Int32((1.0 - boundingBox.origin.y - boundingBox.height) * imageSize.height)
+            let width = Int32(boundingBox.width * imageSize.width)
+            let height = Int32(boundingBox.height * imageSize.height)
+            
+            // Allocate C string for text
+            let cString = strdup(text)
+            
+            textBoxes.append(CTextBox(
+                text: cString,
+                text_len: UInt32(text.utf8.count),
+                x: x,
+                y: y,
+                width: width,
+                height: height,
+                confidence: observation.confidence
+            ))
+        }
+        
+        success = true
+    }
+    
+    // Configure request for best accuracy
+    request.recognitionLevel = .accurate
+    request.usesLanguageCorrection = true
+    request.recognitionLanguages = ["en-US"]
+    
+    // Perform request
+    let handler = VNImageRequestHandler(cgImage: cgImage, options: [:])
+    do {
+        try handler.perform([request])
+    } catch {
+        print("Vision request failed: \(error.localizedDescription)")
+        return false
+    }
+    
+    // Wait for completion
+    semaphore.wait()
+    
+    if !success {
+        return false
+    }
+    
+    // Allocate array for results
+    let boxesPtr = UnsafeMutablePointer<CTextBox>.allocate(capacity: textBoxes.count)
+    for (index, box) in textBoxes.enumerated() {
+        boxesPtr[index] = box
+    }
+    
+    outBoxes.pointee = UnsafeMutableRawPointer(boxesPtr)
+    outCount.pointee = UInt32(textBoxes.count)
+    
+    return true
+}
+
+@_cdecl("vision_free_boxes")
+public func vision_free_boxes(
+    _ boxes: UnsafeMutableRawPointer,
+    _ count: UInt32
+) {
+    let typedBoxes = boxes.assumingMemoryBound(to: CTextBox.self)
+    for i in 0..<Int(count) {
+        if let text = typedBoxes[i].text {
+            free(UnsafeMutableRawPointer(mutating: text))
+        }
+    }
+    typedBoxes.deallocate()
+}
+
+// MARK: - C-Compatible Structure
+
+public struct CTextBox {
+    public let text: UnsafePointer<CChar>?
+    public let text_len: UInt32
+    public let x: Int32
+    public let y: Int32
+    public let width: Int32
+    public let height: Int32
+    public let confidence: Float
+    
+    public init(text: UnsafePointer<CChar>?, text_len: UInt32, x: Int32, y: Int32, width: Int32, height: Int32, confidence: Float) {
+        self.text = text
+        self.text_len = text_len
+        self.x = x
+        self.y = y
+        self.width = width
+        self.height = height
+        self.confidence = confidence
+    }
+}

crates/g3-config/Cargo.toml

@@ -8,10 +8,10 @@ description = "Configuration management for G3 AI coding agent"
 config = { workspace = true }
 serde = { workspace = true }
 anyhow = { workspace = true }
+thiserror = { workspace = true }
 toml = "0.8"
 shellexpand = "3.0"
 dirs = "5.0"
 
 [dev-dependencies]
 tempfile = "3.8"
-serde_json = { workspace = true }

crates/g3-config/src/lib.rs

@@ -1,60 +1,25 @@
-use anyhow::Result;
 use serde::{Deserialize, Serialize};
-use std::collections::HashMap;
+use anyhow::Result;
 use std::path::Path;
 
-/// Main configuration structure
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct Config {
     pub providers: ProvidersConfig,
-    #[serde(default)]
     pub agent: AgentConfig,
-    #[serde(default)]
     pub computer_control: ComputerControlConfig,
-    #[serde(default)]
     pub webdriver: WebDriverConfig,
-    #[serde(default)]
-    pub skills: SkillsConfig,
+    pub macax: MacAxConfig,
 }
 
-/// Provider configuration with named configs per provider type
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct ProvidersConfig {
-    /// Default provider in format "<provider_type>.<config_name>"
+    pub openai: Option<OpenAIConfig>,
+    pub anthropic: Option<AnthropicConfig>,
+    pub databricks: Option<DatabricksConfig>,
+    pub embedded: Option<EmbeddedConfig>,
     pub default_provider: String,
-
-    /// Provider for planner mode (optional, falls back to default_provider)
-    pub planner: Option<String>,
-
-    /// Provider for coach in autonomous mode (optional, falls back to default_provider)
-    pub coach: Option<String>,
-
-    /// Provider for player in autonomous mode (optional, falls back to default_provider)
-    pub player: Option<String>,
-
-    /// Named Anthropic provider configs
-    #[serde(default)]
-    pub anthropic: HashMap<String, AnthropicConfig>,
-
-    /// Named OpenAI provider configs
-    #[serde(default)]
-    pub openai: HashMap<String, OpenAIConfig>,
-
-    /// Named Databricks provider configs
-    #[serde(default)]
-    pub databricks: HashMap<String, DatabricksConfig>,
-
-    /// Named embedded provider configs
-    #[serde(default)]
-    pub embedded: HashMap<String, EmbeddedConfig>,
-
-    /// Named Gemini provider configs
-    #[serde(default)]
-    pub gemini: HashMap<String, GeminiConfig>,
-
-    /// Multiple named OpenAI-compatible providers (e.g., openrouter, groq, etc.)
-    #[serde(default)]
-    pub openai_compatible: HashMap<String, OpenAIConfig>,
+    pub coach: Option<String>,  // Provider to use for coach in autonomous mode
+    pub player: Option<String>, // Provider to use for player in autonomous mode
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -72,168 +37,76 @@ pub struct AnthropicConfig {
     pub model: String,
     pub max_tokens: Option<u32>,
     pub temperature: Option<f32>,
-    pub cache_config: Option<String>,
-    pub enable_1m_context: Option<bool>,
-    pub thinking_budget_tokens: Option<u32>,
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct DatabricksConfig {
     pub host: String,
-    pub token: Option<String>,
+    pub token: Option<String>, // Optional - will use OAuth if not provided
     pub model: String,
     pub max_tokens: Option<u32>,
     pub temperature: Option<f32>,
-    pub use_oauth: Option<bool>,
+    pub use_oauth: Option<bool>, // Default to true if token not provided
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct EmbeddedConfig {
     pub model_path: String,
-    pub model_type: String,
+    pub model_type: String, // e.g., "llama", "mistral", "codellama"
     pub context_length: Option<u32>,
     pub max_tokens: Option<u32>,
     pub temperature: Option<f32>,
-    pub gpu_layers: Option<u32>,
-    pub threads: Option<u32>,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct GeminiConfig {
-    pub api_key: String,
-    pub model: String,
-    pub max_tokens: Option<u32>,
-    pub temperature: Option<f32>,
+    pub gpu_layers: Option<u32>, // Number of layers to offload to GPU
+    pub threads: Option<u32>,    // Number of CPU threads to use
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct AgentConfig {
-    pub max_context_length: Option<u32>,
-    #[serde(default = "default_fallback_max_tokens")]
-    pub fallback_default_max_tokens: usize,
-    #[serde(default = "default_true")]
+    pub max_context_length: usize,
     pub enable_streaming: bool,
-    #[serde(default = "default_timeout_seconds")]
     pub timeout_seconds: u64,
-    #[serde(default = "default_true")]
-    pub auto_compact: bool,
-    #[serde(default = "default_max_retry_attempts")]
-    pub max_retry_attempts: u32,
-    #[serde(default = "default_autonomous_max_retry_attempts")]
-    pub autonomous_max_retry_attempts: u32,
-    #[serde(default = "default_check_todo_staleness")]
-    pub check_todo_staleness: bool,
 }
 
-fn default_fallback_max_tokens() -> usize {
-    32000
-}
-fn default_true() -> bool {
-    true
-}
-fn default_false() -> bool {
-    false
-}
-fn default_timeout_seconds() -> u64 {
-    120
-}
-fn default_max_retry_attempts() -> u32 {
-    3
-}
-fn default_autonomous_max_retry_attempts() -> u32 {
-    6
-}
-fn default_max_actions_per_second() -> u32 {
-    5
-}
-fn default_check_todo_staleness() -> bool {
-    true
-}
-fn default_safari_port() -> u16 {
-    4444
-}
-fn default_chrome_port() -> u16 {
-    9515
-}
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct ComputerControlConfig {
-    #[serde(default = "default_true")]
     pub enabled: bool,
-    #[serde(default = "default_false")]
     pub require_confirmation: bool,
-    #[serde(default = "default_max_actions_per_second")]
     pub max_actions_per_second: u32,
 }
 
-/// Browser type for WebDriver
-#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Default)]
-#[serde(rename_all = "lowercase")]
-pub enum WebDriverBrowser {
-    Safari,
-    #[default]
-    #[serde(rename = "chrome-headless")]
-    ChromeHeadless,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize, Default)]
-pub struct WebDriverConfig {
-    #[serde(default = "default_true")]
-    pub enabled: bool,
-    #[serde(default = "default_safari_port")]
-    pub safari_port: u16,
-    #[serde(default = "default_chrome_port")]
-    pub chrome_port: u16,
-    #[serde(default)]
-    /// Optional path to Chrome binary (e.g., Chrome for Testing)
-    /// If not set, ChromeDriver will use the default Chrome installation
-    pub chrome_binary: Option<String>,
-    #[serde(default)]
-    /// Optional path to ChromeDriver binary
-    /// If not set, looks for 'chromedriver' in PATH
-    pub chromedriver_binary: Option<String>,
-    #[serde(default)]
-    pub browser: WebDriverBrowser,
-}
-
-/// Skills configuration
 #[derive(Debug, Clone, Serialize, Deserialize)]
-pub struct SkillsConfig {
-    /// Whether skills are enabled (default: true)
-    #[serde(default = "default_true")]
+pub struct WebDriverConfig {
     pub enabled: bool,
-    /// Additional paths to search for skills (beyond ~/.g3/skills and .g3/skills)
-    #[serde(default)]
-    pub extra_paths: Vec<String>,
+    pub safari_port: u16,
 }
 
-impl Default for SkillsConfig {
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct MacAxConfig {
+    pub enabled: bool,
+}
+
+impl Default for MacAxConfig {
     fn default() -> Self {
         Self {
-            enabled: true,
-            extra_paths: Vec::new(),
+            enabled: false,
         }
     }
 }
 
-impl Default for AgentConfig {
+impl Default for WebDriverConfig {
     fn default() -> Self {
         Self {
-            max_context_length: None,
-            fallback_default_max_tokens: 32000,
-            enable_streaming: true,
-            timeout_seconds: 120,
-            auto_compact: true,
-            max_retry_attempts: 3,
-            autonomous_max_retry_attempts: 6,
-            check_todo_staleness: true,
+            enabled: false,
+            safari_port: 4444,
         }
     }
 }
+
 impl Default for ComputerControlConfig {
     fn default() -> Self {
         Self {
-            enabled: true,
-            require_confirmation: false,
+            enabled: false, // Disabled by default for safety
+            require_confirmation: true,
             max_actions_per_second: 5,
         }
     }
@@ -241,97 +114,59 @@ impl Default for ComputerControlConfig {
 
 impl Default for Config {
     fn default() -> Self {
-        let mut databricks_configs = HashMap::new();
-        databricks_configs.insert(
-            "default".to_string(),
-            DatabricksConfig {
+        Self {
+            providers: ProvidersConfig {
+                openai: None,
+                anthropic: None,
+                databricks: Some(DatabricksConfig {
                     host: "https://your-workspace.cloud.databricks.com".to_string(),
-                token: None,
+                    token: None, // Will use OAuth by default
                     model: "databricks-claude-sonnet-4".to_string(),
                     max_tokens: Some(4096),
                     temperature: Some(0.1),
                     use_oauth: Some(true),
-            },
-        );
-
-        Self {
-            providers: ProvidersConfig {
-                default_provider: "databricks.default".to_string(),
-                planner: None,
-                coach: None,
-                player: None,
-                anthropic: HashMap::new(),
-                openai: HashMap::new(),
-                databricks: databricks_configs,
-                embedded: HashMap::new(),
-                gemini: HashMap::new(),
-                openai_compatible: HashMap::new(),
+                }),
+                embedded: None,
+                default_provider: "databricks".to_string(),
+                coach: None,  // Will use default_provider if not specified
+                player: None, // Will use default_provider if not specified
             },
             agent: AgentConfig {
-                max_context_length: None,
-                fallback_default_max_tokens: 32000,
+                max_context_length: 8192,
                 enable_streaming: true,
                 timeout_seconds: 60,
-                auto_compact: true,
-                max_retry_attempts: 3,
-                autonomous_max_retry_attempts: 6,
-                check_todo_staleness: true,
             },
             computer_control: ComputerControlConfig::default(),
             webdriver: WebDriverConfig::default(),
-            skills: SkillsConfig::default(),
+            macax: MacAxConfig::default(),
         }
     }
 }
 
-/// Error message for old config format
-const OLD_CONFIG_FORMAT_ERROR: &str = r#"Your configuration file uses an old format that is no longer supported.
-
-Please update your configuration to use the new provider format:
-
-```toml
-[providers]
-default_provider = "anthropic.default"  # Format: "<provider_type>.<config_name>"
-planner = "anthropic.planner"           # Optional: specific provider for planner
-coach = "anthropic.default"             # Optional: specific provider for coach  
-player = "openai.player"                # Optional: specific provider for player
-
-# Named configs per provider type
-[providers.anthropic.default]
-api_key = "your-api-key"
-model = "claude-sonnet-4-5"
-max_tokens = 64000
-
-[providers.anthropic.planner]
-api_key = "your-api-key"
-model = "claude-opus-4-5"
-thinking_budget_tokens = 16000
-
-[providers.openai.player]
-api_key = "your-api-key"
-model = "gpt-5"
-```
-
-Each mode (planner, coach, player) can specify a full path like "<provider_type>.<config_name>".
-If not specified, they fall back to `default_provider`."#;
-
 impl Config {
     pub fn load(config_path: Option<&str>) -> Result<Self> {
         // Check if any config file exists
         let config_exists = if let Some(path) = config_path {
             Path::new(path).exists()
         } else {
-            let default_paths = ["./g3.toml", "~/.config/g3/config.toml", "~/.g3.toml"];
+            // Check default locations
+            let default_paths = [
+                "./g3.toml",
+                "~/.config/g3/config.toml",
+                "~/.g3.toml",
+            ];
+            
             default_paths.iter().any(|path| {
                 let expanded_path = shellexpand::tilde(path);
                 Path::new(expanded_path.as_ref()).exists()
             })
         };
         
-        // If no config exists, create and save a default config
+        // If no config exists, create and save a default Databricks config
         if !config_exists {
-            let default_config = Self::default();
+            let databricks_config = Self::default();
             
+            // Save to default location
             let config_dir = dirs::home_dir()
                 .map(|mut path| {
                     path.push(".config");
@@ -340,181 +175,87 @@ impl Config {
                 })
                 .unwrap_or_else(|| std::path::PathBuf::from("."));
             
+            // Create directory if it doesn't exist
             std::fs::create_dir_all(&config_dir).ok();
             
             let config_file = config_dir.join("config.toml");
-            if let Err(e) = default_config.save(config_file.to_str().unwrap()) {
+            if let Err(e) = databricks_config.save(config_file.to_str().unwrap()) {
                 eprintln!("Warning: Could not save default config: {}", e);
             } else {
-                println!(
-                    "Created default configuration at: {}",
-                    config_file.display()
-                );
+                println!("Created default Databricks configuration at: {}", config_file.display());
             }
             
-            return Ok(default_config);
+            return Ok(databricks_config);
         }
         
-        // Load config from file
-        let config_path_to_load = if let Some(path) = config_path {
-            Some(path.to_string())
+        // Existing config loading logic
+        let mut settings = config::Config::builder();
+        
+        // Load default configuration
+        settings = settings.add_source(config::Config::try_from(&Config::default())?);
+        
+        // Load from config file if provided
+        if let Some(path) = config_path {
+            if Path::new(path).exists() {
+                settings = settings.add_source(config::File::with_name(path));
+            }
         } else {
-            let default_paths = ["./g3.toml", "~/.config/g3/config.toml", "~/.g3.toml"];
-            default_paths.iter().find_map(|path| {
+            // Try to load from default locations
+            let default_paths = [
+                "./g3.toml",
+                "~/.config/g3/config.toml",
+                "~/.g3.toml",
+            ];
+            
+            for path in &default_paths {
                 let expanded_path = shellexpand::tilde(path);
                 if Path::new(expanded_path.as_ref()).exists() {
-                    Some(expanded_path.to_string())
-                } else {
-                    None
+                    settings = settings.add_source(config::File::with_name(expanded_path.as_ref()));
+                    break;
+                }
             }
-            })
-        };
-
-        if let Some(path) = config_path_to_load {
-            // Read and parse the config file
-            let config_content = std::fs::read_to_string(&path)?;
-
-            // Check for old format (direct provider config without named configs)
-            if Self::is_old_format(&config_content) {
-                anyhow::bail!("{}", OLD_CONFIG_FORMAT_ERROR);
         }
         
-            let config: Config = toml::from_str(&config_content)?;
-
-            // Validate the default_provider format
-            config.validate_provider_reference(&config.providers.default_provider)?;
-
-            return Ok(config);
-        }
-
-        Ok(Self::default())
-    }
-
-    /// Check if the config content uses the old format
-    fn is_old_format(content: &str) -> bool {
-        // Old format has [providers.anthropic] with api_key directly
-        // New format has [providers.anthropic.<name>] with api_key
-
-        // Parse as TOML value to inspect structure
-        if let Ok(value) = content.parse::<toml::Value>() {
-            if let Some(providers) = value.get("providers") {
-                if let Some(providers_table) = providers.as_table() {
-                    // Check anthropic section
-                    if let Some(anthropic) = providers_table.get("anthropic") {
-                        if let Some(anthropic_table) = anthropic.as_table() {
-                            // If anthropic has api_key directly, it's old format
-                            if anthropic_table.contains_key("api_key") {
-                                return true;
-                            }
-                        }
-                    }
-                    // Check databricks section
-                    if let Some(databricks) = providers_table.get("databricks") {
-                        if let Some(databricks_table) = databricks.as_table() {
-                            // If databricks has host directly, it's old format
-                            if databricks_table.contains_key("host") {
-                                return true;
-                            }
-                        }
-                    }
-                    // Check openai section
-                    if let Some(openai) = providers_table.get("openai") {
-                        if let Some(openai_table) = openai.as_table() {
-                            // If openai has api_key directly, it's old format
-                            if openai_table.contains_key("api_key") {
-                                return true;
-                            }
-                        }
-                    }
-                }
-            }
-        }
-        false
-    }
-
-    /// Validate a provider reference (format: "<provider_type>.<config_name>")
-    fn validate_provider_reference(&self, reference: &str) -> Result<()> {
-        let parts: Vec<&str> = reference.split('.').collect();
-        if parts.len() != 2 {
-            anyhow::bail!(
-                "Invalid provider reference '{}'. Expected format: '<provider_type>.<config_name>'",
-                reference
+        // Override with environment variables
+        settings = settings.add_source(
+            config::Environment::with_prefix("G3")
+                .separator("_")
         );
+        
+        let config = settings.build()?.try_deserialize()?;
+        Ok(config)
     }
 
-        let (provider_type, config_name) = (parts[0], parts[1]);
-
-        match provider_type {
-            "anthropic" => {
-                if !self.providers.anthropic.contains_key(config_name) {
-                    anyhow::bail!(
-                        "Provider config 'anthropic.{}' not found. Available: {:?}",
-                        config_name,
-                        self.providers.anthropic.keys().collect::<Vec<_>>()
-                    );
+    #[allow(dead_code)]
+    fn default_qwen_config() -> Self {
+        Self {
+            providers: ProvidersConfig {
+                openai: None,
+                anthropic: None,
+                databricks: None,
+                embedded: Some(EmbeddedConfig {
+                    model_path: "~/.cache/g3/models/qwen2.5-7b-instruct-q3_k_m.gguf".to_string(),
+                    model_type: "qwen".to_string(),
+                    context_length: Some(32768),  // Qwen2.5 supports 32k context
+                    max_tokens: Some(2048),
+                    temperature: Some(0.1),
+                    gpu_layers: Some(32),
+                    threads: Some(8),
+                }),
+                default_provider: "embedded".to_string(),
+                coach: None,  // Will use default_provider if not specified
+                player: None, // Will use default_provider if not specified
+            },
+            agent: AgentConfig {
+                max_context_length: 8192,
+                enable_streaming: true,
+                timeout_seconds: 60,
+            },
+            computer_control: ComputerControlConfig::default(),
+            webdriver: WebDriverConfig::default(),
+            macax: MacAxConfig::default(),
         }
     }
-            "openai" => {
-                if !self.providers.openai.contains_key(config_name) {
-                    anyhow::bail!(
-                        "Provider config 'openai.{}' not found. Available: {:?}",
-                        config_name,
-                        self.providers.openai.keys().collect::<Vec<_>>()
-                    );
-                }
-            }
-            "databricks" => {
-                if !self.providers.databricks.contains_key(config_name) {
-                    anyhow::bail!(
-                        "Provider config 'databricks.{}' not found. Available: {:?}",
-                        config_name,
-                        self.providers.databricks.keys().collect::<Vec<_>>()
-                    );
-                }
-            }
-            "embedded" => {
-                if !self.providers.embedded.contains_key(config_name) {
-                    anyhow::bail!(
-                        "Provider config 'embedded.{}' not found. Available: {:?}",
-                        config_name,
-                        self.providers.embedded.keys().collect::<Vec<_>>()
-                    );
-                }
-            }
-            "gemini" => {
-                if !self.providers.gemini.contains_key(config_name) {
-                    anyhow::bail!(
-                        "Provider config 'gemini.{}' not found. Available: {:?}",
-                        config_name,
-                        self.providers.gemini.keys().collect::<Vec<_>>()
-                    );
-                }
-            }
-            _ => {
-                // Check openai_compatible providers
-                if !self.providers.openai_compatible.contains_key(provider_type) {
-                    anyhow::bail!(
-                        "Unknown provider type '{}'. Valid types: anthropic, openai, databricks, embedded, gemini, or openai_compatible names",
-                        provider_type
-                    );
-                }
-            }
-        }
-
-        Ok(())
-    }
-
-    /// Parse a provider reference into (provider_type, config_name)
-    pub fn parse_provider_reference(reference: &str) -> Result<(String, String)> {
-        let parts: Vec<&str> = reference.split('.').collect();
-        if parts.len() != 2 {
-            anyhow::bail!(
-                "Invalid provider reference '{}'. Expected format: '<provider_type>.<config_name>'",
-                reference
-            );
-        }
-        Ok((parts[0].to_string(), parts[1].to_string()))
-    }
     
     pub fn save(&self, path: &str) -> Result<()> {
         let toml_string = toml::to_string_pretty(self)?;
@@ -527,139 +268,109 @@ impl Config {
         provider_override: Option<String>,
         model_override: Option<String>,
     ) -> Result<Self> {
+        // Load the base configuration
         let mut config = Self::load(config_path)?;
         
         // Apply provider override
         if let Some(provider) = provider_override {
-            // If provider doesn't contain '.', assume '.default'
-            let provider = if provider.contains('.') {
-                provider
-            } else {
-                format!("{}.default", provider)
-            };
-            config.validate_provider_reference(&provider)?;
             config.providers.default_provider = provider;
         }
         
         // Apply model override to the active provider
         if let Some(model) = model_override {
-            let (provider_type, config_name) =
-                Self::parse_provider_reference(&config.providers.default_provider)?;
-
-            match provider_type.as_str() {
+            match config.providers.default_provider.as_str() {
                 "anthropic" => {
-                    if let Some(ref mut anthropic_config) =
-                        config.providers.anthropic.get_mut(&config_name)
-                    {
-                        anthropic_config.model = model;
+                    if let Some(ref mut anthropic) = config.providers.anthropic {
+                        anthropic.model = model;
                     } else {
                         return Err(anyhow::anyhow!(
-                            "Provider config 'anthropic.{}' not found.",
-                            config_name
+                            "Provider 'anthropic' is not configured. Please add anthropic configuration to your config file."
                         ));
                     }
                 }
                 "databricks" => {
-                    if let Some(ref mut databricks_config) =
-                        config.providers.databricks.get_mut(&config_name)
-                    {
-                        databricks_config.model = model;
+                    if let Some(ref mut databricks) = config.providers.databricks {
+                        databricks.model = model;
                     } else {
                         return Err(anyhow::anyhow!(
-                            "Provider config 'databricks.{}' not found.",
-                            config_name
+                            "Provider 'databricks' is not configured. Please add databricks configuration to your config file."
                         ));
                     }
                 }
                 "embedded" => {
-                    if let Some(ref mut embedded_config) =
-                        config.providers.embedded.get_mut(&config_name)
-                    {
-                        embedded_config.model_path = model;
+                    if let Some(ref mut embedded) = config.providers.embedded {
+                        embedded.model_path = model;
                     } else {
                         return Err(anyhow::anyhow!(
-                            "Provider config 'embedded.{}' not found.",
-                            config_name
+                            "Provider 'embedded' is not configured. Please add embedded configuration to your config file."
                         ));
                     }
                 }
                 "openai" => {
-                    if let Some(ref mut openai_config) =
-                        config.providers.openai.get_mut(&config_name)
-                    {
-                        openai_config.model = model;
+                    if let Some(ref mut openai) = config.providers.openai {
+                        openai.model = model;
                     } else {
                         return Err(anyhow::anyhow!(
-                            "Provider config 'openai.{}' not found.",
-                            config_name
+                            "Provider 'openai' is not configured. Please add openai configuration to your config file."
                         ));
                     }
                 }
-                "gemini" => {
-                    if let Some(ref mut gemini_config) =
-                        config.providers.gemini.get_mut(&config_name)
-                    {
-                        gemini_config.model = model;
-                    } else {
-                        return Err(anyhow::anyhow!(
-                            "Provider config 'gemini.{}' not found.",
-                            config_name
-                        ));
-                    }
-                }
-                _ => {
-                    // Check openai_compatible
-                    if let Some(ref mut compat_config) =
-                        config.providers.openai_compatible.get_mut(&provider_type)
-                    {
-                        compat_config.model = model;
-                    } else {
-                        return Err(anyhow::anyhow!("Unknown provider type: {}", provider_type));
-                    }
-                }
+                _ => return Err(anyhow::anyhow!("Unknown provider: {}", 
+                    config.providers.default_provider)),
             }
         }
         
         Ok(config)
     }
     
-    /// Get the provider reference for planner mode
-    pub fn get_planner_provider(&self) -> &str {
-        self.providers
-            .planner
-            .as_deref()
-            .unwrap_or(&self.providers.default_provider)
-    }
-
-    /// Get the provider reference for coach mode in autonomous execution
+    /// Get the provider to use for coach mode in autonomous execution
     pub fn get_coach_provider(&self) -> &str {
-        self.providers
-            .coach
+        self.providers.coach
             .as_deref()
             .unwrap_or(&self.providers.default_provider)
     }
     
-    /// Get the provider reference for player mode in autonomous execution
+    /// Get the provider to use for player mode in autonomous execution
     pub fn get_player_provider(&self) -> &str {
-        self.providers
-            .player
+        self.providers.player
             .as_deref()
             .unwrap_or(&self.providers.default_provider)
     }
     
     /// Create a copy of the config with a different default provider
-    pub fn with_provider_override(&self, provider_ref: &str) -> Result<Self> {
+    pub fn with_provider_override(&self, provider: &str) -> Result<Self> {
         // Validate that the provider is configured
-        self.validate_provider_reference(provider_ref)?;
-
-        let mut config = self.clone();
-        config.providers.default_provider = provider_ref.to_string();
-        Ok(config)
+        match provider {
+            "anthropic" if self.providers.anthropic.is_none() => {
+                return Err(anyhow::anyhow!(
+                    "Provider '{}' is specified but not configured. Please add {} configuration to your config file.",
+                    provider, provider
+                ));
+            }
+            "databricks" if self.providers.databricks.is_none() => {
+                return Err(anyhow::anyhow!(
+                    "Provider '{}' is specified but not configured. Please add {} configuration to your config file.",
+                    provider, provider
+                ));
+            }
+            "embedded" if self.providers.embedded.is_none() => {
+                return Err(anyhow::anyhow!(
+                    "Provider '{}' is specified but not configured. Please add {} configuration to your config file.",
+                    provider, provider
+                ));
+            }
+            "openai" if self.providers.openai.is_none() => {
+                return Err(anyhow::anyhow!(
+                    "Provider '{}' is specified but not configured. Please add {} configuration to your config file.",
+                    provider, provider
+                ));
+            }
+            _ => {} // Provider is configured or unknown (will be caught later)
         }
         
-    /// Create a copy of the config for planner mode
-    pub fn for_planner(&self) -> Result<Self> {
-        self.with_provider_override(self.get_planner_provider())
+        let mut config = self.clone();
+        config.providers.default_provider = provider.to_string();
+        Ok(config)
     }
     
     /// Create a copy of the config for coach mode in autonomous execution
@@ -671,89 +382,6 @@ impl Config {
     pub fn for_player(&self) -> Result<Self> {
         self.with_provider_override(self.get_player_provider())
     }
-
-    /// Get Anthropic config by name
-    pub fn get_anthropic_config(&self, name: &str) -> Option<&AnthropicConfig> {
-        self.providers.anthropic.get(name)
-    }
-
-    /// Get OpenAI config by name
-    pub fn get_openai_config(&self, name: &str) -> Option<&OpenAIConfig> {
-        self.providers.openai.get(name)
-    }
-
-    /// Get Databricks config by name
-    pub fn get_databricks_config(&self, name: &str) -> Option<&DatabricksConfig> {
-        self.providers.databricks.get(name)
-    }
-
-    /// Get Embedded config by name
-    pub fn get_embedded_config(&self, name: &str) -> Option<&EmbeddedConfig> {
-        self.providers.embedded.get(name)
-    }
-
-    /// Get Gemini config by name
-    pub fn get_gemini_config(&self, name: &str) -> Option<&GeminiConfig> {
-        self.providers.gemini.get(name)
-    }
-
-    /// Get the current default provider's config
-    pub fn get_default_provider_config(&self) -> Result<ProviderConfigRef<'_>> {
-        let (provider_type, config_name) =
-            Self::parse_provider_reference(&self.providers.default_provider)?;
-
-        match provider_type.as_str() {
-            "anthropic" => self
-                .providers
-                .anthropic
-                .get(&config_name)
-                .map(ProviderConfigRef::Anthropic)
-                .ok_or_else(|| anyhow::anyhow!("Anthropic config '{}' not found", config_name)),
-            "openai" => self
-                .providers
-                .openai
-                .get(&config_name)
-                .map(ProviderConfigRef::OpenAI)
-                .ok_or_else(|| anyhow::anyhow!("OpenAI config '{}' not found", config_name)),
-            "databricks" => self
-                .providers
-                .databricks
-                .get(&config_name)
-                .map(ProviderConfigRef::Databricks)
-                .ok_or_else(|| anyhow::anyhow!("Databricks config '{}' not found", config_name)),
-            "embedded" => self
-                .providers
-                .embedded
-                .get(&config_name)
-                .map(ProviderConfigRef::Embedded)
-                .ok_or_else(|| anyhow::anyhow!("Embedded config '{}' not found", config_name)),
-            "gemini" => self
-                .providers
-                .gemini
-                .get(&config_name)
-                .map(ProviderConfigRef::Gemini)
-                .ok_or_else(|| anyhow::anyhow!("Gemini config '{}' not found", config_name)),
-            _ => self
-                .providers
-                .openai_compatible
-                .get(&provider_type)
-                .map(ProviderConfigRef::OpenAICompatible)
-                .ok_or_else(|| {
-                    anyhow::anyhow!("OpenAI compatible config '{}' not found", provider_type)
-                }),
-        }
-    }
-}
-
-/// Reference to a provider configuration
-#[derive(Debug)]
-pub enum ProviderConfigRef<'a> {
-    Anthropic(&'a AnthropicConfig),
-    OpenAI(&'a OpenAIConfig),
-    Databricks(&'a DatabricksConfig),
-    Embedded(&'a EmbeddedConfig),
-    Gemini(&'a GeminiConfig),
-    OpenAICompatible(&'a OpenAIConfig),
 }
 
 #[cfg(test)]

crates/g3-config/src/tests.rs

@@ -4,53 +4,37 @@ mod tests {
     use std::fs;
     use tempfile::TempDir;
 
-    fn test_config_footer() -> &'static str {
-        r#"
-[computer_control]
-enabled = false
-require_confirmation = true
-max_actions_per_second = 10
-
-[webdriver]
-enabled = false
-safari_port = 4444
-"#
-    }
-
     #[test]
     fn test_coach_player_providers() {
         // Create a temporary directory for the test config
         let temp_dir = TempDir::new().unwrap();
         let config_path = temp_dir.path().join("test_config.toml");
         
-        // Write a test configuration with coach and player providers (new format)
-        let config_content = format!(r#"
+        // Write a test configuration with coach and player providers
+        let config_content = r#"
 [providers]
-default_provider = "databricks.default"
-coach = "anthropic.default"
-player = "embedded.local"
+default_provider = "databricks"
+coach = "anthropic"
+player = "embedded"
 
-[providers.databricks.default]
+[providers.databricks]
 host = "https://test.databricks.com"
 token = "test-token"
 model = "test-model"
 
-[providers.anthropic.default]
+[providers.anthropic]
 api_key = "test-key"
 model = "claude-3"
 
-[providers.embedded.local]
+[providers.embedded]
 model_path = "test.gguf"
 model_type = "llama"
 
 [agent]
-fallback_default_max_tokens = 32000
+max_context_length = 8192
 enable_streaming = true
 timeout_seconds = 60
-auto_compact = true
-max_retry_attempts = 3
-autonomous_max_retry_attempts = 6
-{}"#, test_config_footer());
+"#;
         
         fs::write(&config_path, config_content).unwrap();
         
@@ -58,17 +42,17 @@ autonomous_max_retry_attempts = 6
         let config = Config::load(Some(config_path.to_str().unwrap())).unwrap();
         
         // Test that the providers are correctly identified
-        assert_eq!(config.providers.default_provider, "databricks.default");
-        assert_eq!(config.get_coach_provider(), "anthropic.default");
-        assert_eq!(config.get_player_provider(), "embedded.local");
+        assert_eq!(config.providers.default_provider, "databricks");
+        assert_eq!(config.get_coach_provider(), "anthropic");
+        assert_eq!(config.get_player_provider(), "embedded");
         
         // Test creating coach config
         let coach_config = config.for_coach().unwrap();
-        assert_eq!(coach_config.providers.default_provider, "anthropic.default");
+        assert_eq!(coach_config.providers.default_provider, "anthropic");
         
         // Test creating player config
         let player_config = config.for_player().unwrap();
-        assert_eq!(player_config.providers.default_provider, "embedded.local");
+        assert_eq!(player_config.providers.default_provider, "embedded");
     }
     
     #[test]
@@ -77,24 +61,21 @@ autonomous_max_retry_attempts = 6
         let temp_dir = TempDir::new().unwrap();
         let config_path = temp_dir.path().join("test_config.toml");
         
-        // Write a test configuration WITHOUT coach and player providers (new format)
-        let config_content = format!(r#"
+        // Write a test configuration WITHOUT coach and player providers
+        let config_content = r#"
 [providers]
-default_provider = "databricks.default"
+default_provider = "databricks"
 
-[providers.databricks.default]
+[providers.databricks]
 host = "https://test.databricks.com"
 token = "test-token"
 model = "test-model"
 
 [agent]
-fallback_default_max_tokens = 32000
+max_context_length = 8192
 enable_streaming = true
 timeout_seconds = 60
-auto_compact = true
-max_retry_attempts = 3
-autonomous_max_retry_attempts = 6
-{}"#, test_config_footer());
+"#;
         
         fs::write(&config_path, config_content).unwrap();
         
@@ -102,16 +83,16 @@ autonomous_max_retry_attempts = 6
         let config = Config::load(Some(config_path.to_str().unwrap())).unwrap();
         
         // Test that coach and player fall back to default provider
-        assert_eq!(config.get_coach_provider(), "databricks.default");
-        assert_eq!(config.get_player_provider(), "databricks.default");
+        assert_eq!(config.get_coach_provider(), "databricks");
+        assert_eq!(config.get_player_provider(), "databricks");
         
         // Test creating coach config (should use default)
         let coach_config = config.for_coach().unwrap();
-        assert_eq!(coach_config.providers.default_provider, "databricks.default");
+        assert_eq!(coach_config.providers.default_provider, "databricks");
         
         // Test creating player config (should use default)
         let player_config = config.for_player().unwrap();
-        assert_eq!(player_config.providers.default_provider, "databricks.default");
+        assert_eq!(player_config.providers.default_provider, "databricks");
     }
     
     #[test]
@@ -120,25 +101,22 @@ autonomous_max_retry_attempts = 6
         let temp_dir = TempDir::new().unwrap();
         let config_path = temp_dir.path().join("test_config.toml");
         
-        // Write a test configuration with an unconfigured provider (new format)
-        let config_content = format!(r#"
+        // Write a test configuration with an unconfigured provider
+        let config_content = r#"
 [providers]
-default_provider = "databricks.default"
-coach = "openai.default"  # OpenAI default is not configured
+default_provider = "databricks"
+coach = "openai"  # OpenAI is not configured
 
-[providers.databricks.default]
+[providers.databricks]
 host = "https://test.databricks.com"
 token = "test-token"
 model = "test-model"
 
 [agent]
-fallback_default_max_tokens = 32000
+max_context_length = 8192
 enable_streaming = true
 timeout_seconds = 60
-auto_compact = true
-max_retry_attempts = 3
-autonomous_max_retry_attempts = 6
-{}"#, test_config_footer());
+"#;
         
         fs::write(&config_path, config_content).unwrap();
         
@@ -148,120 +126,6 @@ autonomous_max_retry_attempts = 6
         // Test that trying to create a coach config with unconfigured provider fails
         let result = config.for_coach();
         assert!(result.is_err());
-        let err_msg = result.unwrap_err().to_string();
-        assert!(err_msg.contains("not found") || err_msg.contains("not configured"), 
-            "Expected error message to contain 'not found' or 'not configured', got: {}", err_msg);
-    }
-
-    #[test]
-    fn test_old_format_detection() {
-        // Create a temporary directory for the test config
-        let temp_dir = TempDir::new().unwrap();
-        let config_path = temp_dir.path().join("test_config.toml");
-
-        // Write a test configuration with OLD format (api_key directly under [providers.anthropic])
-        let config_content = format!(r#"
-[providers]
-default_provider = "anthropic"
-
-[providers.anthropic]
-api_key = "test-key"
-model = "claude-3"
-
-[agent]
-fallback_default_max_tokens = 32000
-enable_streaming = true
-timeout_seconds = 60
-auto_compact = true
-max_retry_attempts = 3
-autonomous_max_retry_attempts = 6
-{}"#, test_config_footer());
-
-        fs::write(&config_path, config_content).unwrap();
-
-        // Loading should fail with old format error
-        let result = Config::load(Some(config_path.to_str().unwrap()));
-        assert!(result.is_err());
-        let err_msg = result.unwrap_err().to_string();
-        assert!(err_msg.contains("old format") || err_msg.contains("no longer supported"),
-            "Expected error about old format, got: {}", err_msg);
-    }
-
-    #[test]
-    fn test_planner_provider() {
-        // Create a temporary directory for the test config
-        let temp_dir = TempDir::new().unwrap();
-        let config_path = temp_dir.path().join("test_config.toml");
-
-        // Write a test configuration with planner provider (new format)
-        let config_content = format!(r#"
-[providers]
-default_provider = "databricks.default"
-planner = "anthropic.planner"
-
-[providers.databricks.default]
-host = "https://test.databricks.com"
-token = "test-token"
-model = "test-model"
-
-[providers.anthropic.planner]
-api_key = "test-key"
-model = "claude-opus"
-thinking_budget_tokens = 16000
-
-[agent]
-fallback_default_max_tokens = 32000
-enable_streaming = true
-timeout_seconds = 60
-auto_compact = true
-max_retry_attempts = 3
-autonomous_max_retry_attempts = 6
-{}"#, test_config_footer());
-
-        fs::write(&config_path, config_content).unwrap();
-
-        // Load the configuration
-        let config = Config::load(Some(config_path.to_str().unwrap())).unwrap();
-
-        // Test that the planner provider is correctly identified
-        assert_eq!(config.get_planner_provider(), "anthropic.planner");
-
-        // Test creating planner config
-        let planner_config = config.for_planner().unwrap();
-        assert_eq!(planner_config.providers.default_provider, "anthropic.planner");
-    }
-
-    #[test]
-    fn test_planner_fallback_to_default() {
-        // Create a temporary directory for the test config
-        let temp_dir = TempDir::new().unwrap();
-        let config_path = temp_dir.path().join("test_config.toml");
-
-        // Write a test configuration WITHOUT planner provider
-        let config_content = format!(r#"
-[providers]
-default_provider = "databricks.default"
-
-[providers.databricks.default]
-host = "https://test.databricks.com"
-token = "test-token"
-model = "test-model"
-
-[agent]
-fallback_default_max_tokens = 32000
-enable_streaming = true
-timeout_seconds = 60
-auto_compact = true
-max_retry_attempts = 3
-autonomous_max_retry_attempts = 6
-{}"#, test_config_footer());
-
-        fs::write(&config_path, config_content).unwrap();
-
-        // Load the configuration
-        let config = Config::load(Some(config_path.to_str().unwrap())).unwrap();
-
-        // Test that planner falls back to default provider
-        assert_eq!(config.get_planner_provider(), "databricks.default");
+        assert!(result.unwrap_err().to_string().contains("not configured"));
     }
 }

crates/g3-core/Cargo.toml

@@ -4,9 +4,6 @@ version = "0.1.0"
 edition = "2021"
 description = "Core engine for G3 AI coding agent"
 
-[features]
-test-support = []
-
 [dependencies]
 g3-providers = { path = "../g3-providers" }
 g3-config = { path = "../g3-config" }
@@ -15,6 +12,7 @@ g3-computer-control = { path = "../g3-computer-control" }
 tokio = { workspace = true }
 reqwest = { workspace = true }
 anyhow = { workspace = true }
+thiserror = { workspace = true }
 tracing = { workspace = true }
 serde = { workspace = true }
 serde_json = { workspace = true }
@@ -27,30 +25,3 @@ chrono = { version = "0.4", features = ["serde"] }
 rand = "0.8"
 regex = "1.0"
 shellexpand = "3.1"
-serde_yaml = "0.9"
-
-# tree-sitter for embedded code search
-tree-sitter = "0.24"
-tree-sitter-rust = "0.23"
-tree-sitter-python = "0.23"
-tree-sitter-javascript = "0.23"
-tree-sitter-typescript = "0.23"
-tree-sitter-go = "0.23"
-tree-sitter-java = "0.23"
-tree-sitter-c = "0.23"
-tree-sitter-cpp = "0.23"
-# tree-sitter-kotlin = "0.3"  # Temporarily disabled - incompatible with tree-sitter 0.24
-tree-sitter-haskell = { git = "https://github.com/tree-sitter/tree-sitter-haskell" }
-tree-sitter-scheme = "0.24"
-tree-sitter-racket = "0.24"
-streaming-iterator = "0.1"
-walkdir = "2.5"
-
-# Datalog engine for invariant verification
-datafrog = "2.0.1"
-
-base64 = "0.22.1"
-
-[dev-dependencies]
-tempfile = "3.8"
-serial_test = "3.0"

crates/g3-core/examples/inspect_ast.rs

@@ -1,58 +0,0 @@
-//! Inspect tree-sitter AST structure for Rust code
-
-use tree_sitter::{Language, Parser};
-
-fn print_tree(node: tree_sitter::Node, source: &str, indent: usize) {
-    let indent_str = "  ".repeat(indent);
-    let node_text = &source[node.byte_range()];
-    let preview = if node_text.len() > 50 {
-        format!("{}...", &node_text[..50])
-    } else {
-        node_text.to_string()
-    };
-
-    println!(
-        "{}{} [{}:{}] '{}'",
-        indent_str,
-        node.kind(),
-        node.start_position().row + 1,
-        node.start_position().column + 1,
-        preview.replace('\n', "\\n")
-    );
-
-    let mut cursor = node.walk();
-    for child in node.children(&mut cursor) {
-        print_tree(child, source, indent + 1);
-    }
-}
-
-fn main() -> anyhow::Result<()> {
-    let source_code = r#"
-pub async fn example_async() {
-    println!("Hello");
-}
-
-fn regular_function() {
-    println!("Regular");
-}
-
-pub async fn another_async(x: i32) -> Result<(), ()> {
-    Ok(())
-}
-"#;
-
-    println!("Source code:");
-    println!("{}", source_code);
-    println!("\n{}", "=".repeat(80));
-    println!("AST Structure:");
-    println!("{}\n", "=".repeat(80));
-
-    let mut parser = Parser::new();
-    let language: Language = tree_sitter_rust::LANGUAGE.into();
-    parser.set_language(&language)?;
-
-    let tree = parser.parse(source_code, None).unwrap();
-    print_tree(tree.root_node(), source_code, 0);
-
-    Ok(())
-}

crates/g3-core/examples/inspect_python_ast.rs

@@ -1,56 +0,0 @@
-//! Inspect tree-sitter AST structure for Python code
-
-use tree_sitter::{Language, Parser};
-
-fn print_tree(node: tree_sitter::Node, source: &str, indent: usize) {
-    let indent_str = "  ".repeat(indent);
-    let node_text = &source[node.byte_range()];
-    let preview = if node_text.len() > 50 {
-        format!("{}...", &node_text[..50])
-    } else {
-        node_text.to_string()
-    };
-
-    println!(
-        "{}{} [{}:{}] '{}'",
-        indent_str,
-        node.kind(),
-        node.start_position().row + 1,
-        node.start_position().column + 1,
-        preview.replace('\n', "\\n")
-    );
-
-    let mut cursor = node.walk();
-    for child in node.children(&mut cursor) {
-        print_tree(child, source, indent + 1);
-    }
-}
-
-fn main() -> anyhow::Result<()> {
-    let source_code = r#"
-def regular_function():
-    pass
-
-async def async_function():
-    pass
-
-class MyClass:
-    def method(self):
-        pass
-"#;
-
-    println!("Source code:");
-    println!("{}", source_code);
-    println!("\n{}", "=".repeat(80));
-    println!("AST Structure:");
-    println!("{}\n", "=".repeat(80));
-
-    let mut parser = Parser::new();
-    let language: Language = tree_sitter_python::LANGUAGE.into();
-    parser.set_language(&language)?;
-
-    let tree = parser.parse(source_code, None).unwrap();
-    print_tree(tree.root_node(), source_code, 0);
-
-    Ok(())
-}

crates/g3-core/examples/test_python_query.rs

@@ -1,44 +0,0 @@
-//! Test Python async query
-
-use streaming_iterator::StreamingIterator;
-use tree_sitter::{Language, Parser, Query, QueryCursor};
-
-fn main() -> anyhow::Result<()> {
-    let source_code = r#"
-def regular_function():
-    pass
-
-async def async_function():
-    pass
-"#;
-
-    let mut parser = Parser::new();
-    let language: Language = tree_sitter_python::LANGUAGE.into();
-    parser.set_language(&language)?;
-
-    let tree = parser.parse(source_code, None).unwrap();
-
-    // Try different queries
-    let queries = vec![
-        "(function_definition (async) name: (identifier) @name)",
-        "(function_definition (async))",
-        "(async)",
-    ];
-
-    for query_str in queries {
-        println!("\nTrying query: {}", query_str);
-        match Query::new(&language, query_str) {
-            Ok(query) => {
-                let mut cursor = QueryCursor::new();
-                let matches = cursor.matches(&query, tree.root_node(), source_code.as_bytes());
-                let count = matches.count();
-                println!("  ✓ Valid query, found {} matches", count);
-            }
-            Err(e) => {
-                println!("  ✗ Invalid query: {}", e);
-            }
-        }
-    }
-
-    Ok(())
-}