- Move system prompt for native tool calling models to prompts/system/native.md
- Use include_str! to embed at compile time
- Remove concatenated SHARED_* string constants
- Prompt is now readable/editable as a complete markdown document
- Non-native prompt still uses Rust constants (acceptable for now)
Change Plan Mode to allow multiple negative and boundary checks per item,
while keeping happy path as a single check.
Schema change:
- checks.negative: Check -> Vec<Check> (>=1 required)
- checks.boundary: Check -> Vec<Check> (>=1 required)
- checks.happy: Check (unchanged, single)
This better reflects real-world tasks where there are often multiple
error conditions and edge cases worth tracking.
Changes:
- Update Checks struct to use Vec<Check> for negative/boundary
- Update validation to require at least 1 of each
- Update prompts and tool definitions with new array syntax
- Add 4 new tests for multi-check scenarios
Adds rulespec.yaml and envelope.yaml support for machine-readable
invariant checking during plan completion.
- Add invariants module with Rulespec, ActionEnvelope, and evaluation logic
- Add Invariants section to system prompt with workflow instructions
- Show rulespec/envelope file status in plan verification output
- Rulespec written during planning (captures constraints from task)
- Envelope written after implementation (documents what was built)
- Add auto-approval logic in execute_plan_write() when ctx.is_autonomous is true
- Update system prompt to document auto-approval behavior
- Plans still require explicit approval in interactive mode
Plan Mode is a cognitive forcing system that requires reasoning about:
- Happy path
- Negative case
- Boundary condition
New tools:
- plan_read: Read current plan for session
- plan_write: Create/update plan with YAML content (validates structure)
- plan_approve: Mark current revision as approved
New command:
- /feature <description>: Start Plan Mode for a new feature
Plan schema requires:
- plan_id, revision, approved_revision
- items with id, description, state, touches, checks (happy/negative/boundary)
- evidence and notes required when marking items done
Verification:
- plan_verify() called automatically when all items are done/blocked
Removed:
- todo_read, todo_write tools
- todo.rs module and related tests
The research tool now spawns the scout agent in a background tokio task
and returns immediately with a research_id placeholder. This allows the
agent to continue working while research runs (30-120 seconds).
Key changes:
- New PendingResearchManager for tracking async research tasks
- research tool returns immediately with placeholder containing research_id
- research_status tool to check progress of pending research
- Auto-injection of completed research at natural break points:
- Start of each tool iteration (before LLM call)
- Before prompting user in interactive mode
- /research CLI command to list all research tasks
- Updated system prompt to explain async behavior
The agent can:
- Continue with other work while research runs
- Check status with research_status tool
- Yield turn to user if results are critical before continuing
Rename all references from "Project Memory" to "Workspace Memory" to avoid
future conflation if a "project" concept is introduced later.
Changes:
- Rename read_project_memory() -> read_workspace_memory()
- Update all prompts, tool descriptions, and comments
- Update header parsing in memory.rs to use "# Workspace Memory"
- Update display detection for "=== Workspace Memory ==="
- Update documentation and analysis/memory.md
11 files changed, ~36 occurrences updated.
- Updated memory reminder prompt with per-symbol char ranges
- Added two few-shot examples: Session Continuation (feature) + UTF-8 Safe Slicing (pattern)
- Updated system prompt Memory Format section to match
- Format: file -> nested symbols with [start..end] ranges and descriptions
- Enables direct read_file navigation to specific functions
When the streaming parser encountered fragments of JSON that looked like
partial tool calls (e.g., {"tool":) embedded in inline text (like code
examples or prose), it would incorrectly enter JSON parsing mode and
poison the parser state, causing control to be returned to the user
mid-task.
This fix:
- Adds sanitize_inline_tool_patterns() to detect tool-call patterns that
are NOT on their own line and replace the opening brace with a Unicode
homoglyph (fullwidth left curly bracket U+FF5B)
- Integrates sanitization into process_chunk() before text is buffered
- Updates system prompts to instruct LLMs to use homoglyphs when showing
example tool call JSON in prose
- Adds comprehensive tests for the sanitization logic
Real tool calls from LLMs always appear on their own line, so those are
left untouched. Only inline patterns (with non-whitespace before them)
are sanitized.
Project memory is now stored at analysis/memory.md instead of .g3/memory.md.
This change enables:
- Shared memory across git worktrees (studio agent sessions)
- Version-controlled memory that persists across clones
- Memory changes tracked in git history and reviewable in PRs
Changes:
- crates/g3-core/src/tools/memory.rs: Update get_memory_path() to use analysis/
- crates/g3-cli/src/project_files.rs: Update read_project_memory() path
- crates/g3-core/src/prompts.rs: Update documentation references (2 occurrences)
- analysis/memory.md: Add memory file (copied from .g3/memory.md)
- Remove IMPORTANT FOR CODING section (~1,500 chars of coding guidelines)
- Remove <use_parallel_tool_calls> block (~500 chars)
- Remove unused const_format dependency from g3-core
- Simplify get_system_prompt_for_native() to just return base prompt
- Response Guidelines now cleanly ends the static prompt
Prompt reduced from ~8,500 to ~6,500 characters.
Simplified the main system prompt's web research section to just direct
users to the research tool. Moved the detailed WebDriver usage instructions
to scout.md where they belong, since the scout agent is the one that
actually uses WebDriver for research.
Main prompt now simply says: use the research tool for web research.
Scout agent now has the full WebDriver best practices documentation.
New tool that spawns a scout agent to perform web research and return
a structured research brief. The scout agent uses webdriver to browse
the web and returns a decision-ready report.
Changes:
- Added 'research' tool definition (12 core tools total)
- Added research tool dispatch in tool_dispatch.rs
- Created tools/research.rs implementation:
- Spawns 'g3 --agent scout <query>' as subprocess
- Captures stdout and extracts last line (report file path)
- Reads and returns the report file contents
- Added exclude_research flag to ToolConfig
- Scout agent (agent_name == 'scout') does NOT have access to research
tool to prevent infinite recursion
- Updated system prompts to describe when to use research tool
- Added scout.md agent prompt with research brief output contract
The research tool is preferred for complex research tasks (APIs, SDKs,
libraries, approaches, bugs). WebDriver can still be used directly for
simple lookups or fine-grained control.
- Remove final_output from tool definitions, dispatch, and misc tools
- Update system prompts to request summaries as regular markdown text
- Remove print_final_output from UiWriter trait and all implementations
- Remove final_output handling from agent core logic
- Rename final_output_summary → summary in session continuation
- Delete final_output test files
- Update tool count tests (12→11, 27→26)
This allows LLM summaries to stream through the markdown formatter
for a more natural, responsive user experience instead of buffering
everything into a tool call.
This fixes a bug where the agent would stop responding abruptly without
calling final_output. The root cause was the allow_multiple_tool_calls
config option (default: false) which caused the agent to break out of
the streaming loop mid-stream after executing the first tool, losing
any subsequent content.
Changes:
- Remove allow_multiple_tool_calls config option entirely
- Always process all tool calls without breaking mid-stream
- Simplify system prompt generation (no longer needs boolean param)
- Let the stream complete fully before continuing to next iteration
- Change find_last_tool_call_start to find_first_tool_call_start
- Remove parser.reset() call on duplicate detection
Benefits:
- Simpler logic with less conditional branching
- No lost content after tool calls
- Consistent behavior for all users
- Reduced config complexity
macOS uses U+202F (Narrow No-Break Space) in screenshot filenames
between the time and am/pm. When users type or paste these paths,
they use regular spaces, causing file-not-found errors.
Changes:
- Add resolve_path_with_unicode_fallback() to try U+202F variants
- Add resolve_paths_in_shell_command() for shell command paths
- Apply fix to read_file, read_image, and shell tools
- Fix read_image prompt docs: file_path -> file_paths (array)
- Add 6 unit tests for Unicode space normalization
- Add TODO completion check to final_output tool in autonomous mode only
- When incomplete TODO items exist, reject final_output and prompt LLM to continue
- Non-autonomous modes (interactive, chat) are unaffected
- Add 6 tests verifying behavior in both autonomous and non-autonomous modes
Fixes issue where LLM would call final_output after completing first phase,
causing agent to stop prematurely instead of continuing with remaining phases.
TODO lists are now stored in .g3/sessions/<session_id>/todo.g3.md instead
of the workspace root. This prevents different g3 sessions from accidentally
picking up or overwriting each other's TODOs.
Changes:
- Add get_session_todo_path() function in paths.rs
- Update todo_read/todo_write handlers to use session-specific paths
- Remove TODO loading at Agent initialization (sessions start fresh)
- Update prompts to reflect session-scoped behavior
Fallback behavior preserved for planner mode (G3_TODO_PATH env var).
Adds a new tool that allows launching processes (like game servers) in the
background while g3 continues to operate. The process runs independently
with stdout/stderr captured to a log file.
Features:
- Named process tracking for easy reference
- Automatic log capture to logs/background_processes/
- Returns PID and log file path for use with shell tool
- Automatic cleanup on agent shutdown via Drop trait
Usage: Use shell tool to interact with the process:
- Read logs: tail -100 <logfile>
- Check status: ps -p <pid>
- Stop process: kill <pid>
Files:
- New: crates/g3-core/src/background_process.rs
- New: crates/g3-core/tests/background_process_demo_test.rs
- Modified: crates/g3-core/src/lib.rs (tool definition + handler)
- Modified: crates/g3-core/src/prompts.rs (documentation)
- Add --safari flag to CLI for explicitly choosing Safari
- Update --chrome-headless flag description to indicate it's the default
- Update README to reflect Chrome headless as default
- Remove broken link to non-existent docs/webdriver-setup.md
- Add Safari flag handling in all webdriver config locations
The config already had ChromeHeadless as the default, this commit
updates the CLI and documentation to match.
Writes the current context window to logs/current_context_window (uses a symlink to a session ID).
This PR was unfortunately generated by a different LLM and did a ton of superficial reformating, it's actually a fairly small and benign change, but I don't want to roll back everything. Hope that's ok.
