The dedup logic compared only tool name+args, ignoring the unique tool call
IDs that native providers (Anthropic) assign to each invocation. When the
model called research_status {} in iteration 1, auto-continued, and called
it again in iteration 2 with identical args but a new ID, the second call
was marked DUP IN MSG and skipped. With no tool executed and no text, the
stream errored with 'No response received from the model.'
Three-part fix:
- ID-aware DUP IN MSG: check_duplicate_in_previous_message() uses tool call
IDs when both are non-empty (different IDs = different invocations)
- History cutoff: only checks messages from before the current iteration to
prevent within-iteration false positives
- DUP IN ITER: last_executed_tool on IterationState catches stuttered
duplicates across chunks within the same response
Regression test reproduces the exact bug (fails without fix, passes with).
The agent would stop mid-task because native tool calls were stored as
inline JSON text in Message.content. When sent back to the Anthropic API
via convert_messages(), they went as plain text instead of structured
tool_use/tool_result blocks. The model would occasionally get confused
and emit text describing what it wanted to do instead of invoking the
tool mechanism.
Changes:
- Add MessageToolCall struct and tool_calls/tool_result_id fields to Message
- Add id field to core ToolCall struct to preserve provider tool call IDs
- Update Anthropic convert_messages() to emit tool_use and tool_result blocks
- Add ToolResult variant to AnthropicContent enum
- Store tool calls structurally in tool message construction (not inline JSON)
- Fix add_message() to preserve empty-content messages with tool_calls
- Fix check_duplicate_in_previous_message() to check structured tool_calls
- Generate valid IDs for JSON fallback tool calls (Anthropic pattern requirement)
- Update planner create_tool_message() to use structured tool calls
When the LLM emits identical JSON tool calls as text content (JSON
fallback mode), the raw duplicate JSON was being stored in the assistant
message in conversation history. This confused the model on subsequent
turns, causing it to stall or repeat itself.
Root cause: raw_content_for_log used get_text_content() which returns
the full parser buffer including all duplicate tool call JSONs.
Fix: Added get_text_before_tool_calls() to StreamingToolParser that
returns only the text before the first JSON tool call. Changed
raw_content_for_log to use this method so the assistant message only
contains the preamble text + the single executed tool call.
Added 5 integration tests covering stuttered duplicates, triple
stutter, cross-turn dedup, and different-args boundary case.
Added MockResponse helpers for simulating LLM stutter patterns.
Restores the research tool that was previously externalized as a skill:
- Add pending_research.rs: PendingResearchManager with thread-safe task tracking
- Add tools/research.rs: execute_research (async), execute_research_status
- Add research/research_status tool definitions with exclude_research config
- Integrate PendingResearchManager into Agent and ToolContext
- Inject completed research results in streaming loop
Remove research skill:
- Clear EMBEDDED_SKILLS array in embedded.rs
- Delete skills/research/ directory
- Update all tests expecting embedded research skill
- Update docs and memory to reflect the change
The research tool now:
- Spawns scout agent in background tokio task
- Returns immediately with research_id
- Automatically injects results into conversation when ready
- Supports status checks via research_status tool
Removed redundant and vague content from prompts/system/native.md:
- Simplified intro from 17 lines to 3 lines
- Reduced Code Search section to one line
- Removed duplicate Plan Mode example (kept one)
- Removed Action Envelope section (rarely used correctly)
- Removed verbose Memory Format details (tool description covers it)
- Removed Response Guidelines (obvious to modern LLMs)
Size: 8,620 chars -> 4,498 chars
Also updated:
- G3_IDENTITY_LINE constant for agent mode compatibility
- Test assertions to check for new prompt markers
- System prompt validation to use new marker string
When a plan reaches a terminal state (all items done or blocked) in
interactive mode, automatically exit plan mode and return to normal
prompt.
Changes:
- Add Agent::is_plan_terminal() method to check if plan is complete
- Add check_and_exit_plan_mode_if_terminal() helper in interactive.rs
- Call the helper after each execute_user_input() to detect completion
Fixes issue where plan mode prompt ' >> ' persisted after plan completion.
Replaces the built-in research/research_status tools with a portable
skill-based approach:
- Add embedded skills infrastructure (skills compiled into binary)
- Add repo-local skills/ directory support (highest priority)
- Create research skill with SKILL.md and g3-research shell script
- Script extraction to .g3/bin/ with version tracking
- Filesystem-based handoff via .g3/research/<id>/status.json
- Remove PendingResearchManager and all research tool code
- Update system prompt to reference skill instead of tool
Benefits:
- No special tool infrastructure needed (just shell + read_file)
- Context-efficient (reports stay on disk until needed)
- Crash-resilient (state persisted to filesystem)
- Portable (skill can be overridden per-workspace)
Breaking change: research tool calls now return a deprecation message
pointing to the research skill.
- Add in_plan_mode flag to Agent struct
- Add set_plan_mode() and is_plan_mode() methods
- Gate check now only runs when in_plan_mode is true
- CLI calls set_plan_mode(true) on /plan command and EnterPlanMode
- CLI calls set_plan_mode(false) on approval and CTRL-D exit
- Update integration test to enable plan mode
- Fix test YAML to use Vec<Check> for negative/boundary checks
- Add check_plan_approval_gate() in tools/plan.rs that runs after each tool call
- Detects file changes via git status --porcelain when plan exists but not approved
- Reverts changes: git checkout for modified files, rm for new untracked files
- Returns blocking message instructing LLM to create/approve plan first
- Add ApprovalGateResult enum with Allowed/Blocked/NotGitRepo variants
- Add set_session_id() and set_working_dir() methods on Agent for testing
- Add integration test using MockProvider to simulate blocked write_file
- Add --resume CLI flag that conflicts with --new-session
- Add load_continuation_by_id() to load sessions by full or partial ID
- Support loading from latest.json or falling back to session.json
- Handle --resume in both normal and agent modes
- Agent mode validates session belongs to correct agent
Implements the Agent Skills specification (https://agentskills.io) for
portable skill packages that give the agent new capabilities.
Changes:
- Add skills module with SKILL.md parser (YAML frontmatter + markdown body)
- Implement skill discovery from ~/.g3/skills/, config extra_paths, and .g3/skills/
- Generate <available_skills> XML for system prompt injection
- Add SkillsConfig to g3-config with enabled flag and extra_paths
- Wire skills discovery into CLI startup
- Add 29 unit tests for parser, discovery, and prompt generation
- Update README with Agent Skills documentation
Skill locations (priority order):
1. ~/.g3/skills/ (global)
2. Config extra_paths
3. .g3/skills/ (workspace, highest priority)
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.
When background research completes, g3 now immediately prints a status
message instead of waiting for the next user interaction:
- Added ResearchCompletionNotification and broadcast channel to
PendingResearchManager for push-based notifications
- Added spawn_research_notification_handler() in interactive mode that
listens for completions in a background task
- When idle (at prompt): clears line, prints status, reprints prompt
- When busy (processing): prints status inline (interleaving is fine)
- Added G3Status::research_complete() for consistent formatting
- Added enable_research_notifications() method to Agent
Output format: "g3: 1 research report ... [done]"
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
README.md is no longer auto-loaded into the LLM context at startup.
This saves ~4,600 tokens per session while AGENTS.md and memory.md
still provide all critical information for code tasks.
Changes:
- Delete read_project_readme() function
- Remove readme_content parameter from combine_project_content()
- Rename extract_readme_heading() -> extract_project_heading()
- Rename Agent constructors: *_with_readme_* -> *_with_project_context_*
- Update context preservation to only check for Agent Configuration
- Remove has_readme field from LoadedContent
- Update all tests to use new markers and function names
The LLM can still read README.md on-demand via read_file when needed.
- Add GeminiProvider with streaming and native tool calling
- Support gemini-2.5-pro, gemini-2.0-flash, gemini-1.5-pro/flash models
- Model-specific context window detection (1M-2M tokens)
- Message conversion: assistant -> model role mapping
- System messages extracted to system_instruction field
- Tool schema conversion with functionCall/functionResponse parts
- SSE streaming with JSON array buffer parsing
- 8 unit tests for conversion and parsing logic
- Register provider in g3-core and validate in g3-cli
- Add context_window_size() method to LLMProvider trait
- Implement for EmbeddedProvider to return the auto-detected context length
- Update Agent to query provider directly instead of using hardcoded defaults
- Removes need for model-specific context length mappings
Eliminate code-path aliasing in Agent construction methods by introducing
a single `build_agent()` helper that all constructors delegate to.
Before: 3 nearly-identical `Ok(Self { ... })` blocks (~30 lines each)
with subtle differences in auto_compact, is_autonomous, quiet, and
computer_controller fields - prone to drift over time.
After: Single canonical `build_agent()` method that constructs Agent
with all fields. All public constructors delegate to this single path:
- new_for_test() -> new_for_test_with_readme() -> build_agent()
- new_with_mode_and_readme() -> build_agent()
Changes:
- Add `build_agent()` private helper method (single source of truth)
- Simplify `new_for_test()` to delegate to `new_for_test_with_readme()`
- Update `new_for_test_with_readme()` to use `build_agent()`
- Update `new_with_mode_and_readme()` to use `build_agent()`
Net reduction: ~43 lines (-109/+66)
All 190 tests pass.
Agent: fowler
- Extend Usage struct with cache_creation_tokens and cache_read_tokens fields
- Parse Anthropic cache_creation_input_tokens and cache_read_input_tokens
- Parse OpenAI prompt_tokens_details.cached_tokens for automatic prefix caching
- Add CacheStats struct to Agent for cumulative tracking across API calls
- Add "Prompt Cache Statistics" section to /stats output showing:
- API call count and cache hit count
- Hit rate percentage
- Total input tokens and cache read/creation tokens
- Cache efficiency (% of input served from cache)
- Update all provider implementations and test files
The prefix was causing duplication when users typed 'Task: ...' themselves,
resulting in '📋 Task: Task: ...' in context dumps.
User messages are now stored as-is without any prefix.
Centralize tool output formatting logic that was duplicated/scattered in
stream_completion_with_tools(). This eliminates code-path aliasing where
tool type checks were done in multiple places.
Changes:
- Add ToolOutputFormat enum (SelfHandled, Compact, Regular)
- Add format_tool_result_summary() for centralized formatting decisions
- Add is_compact_tool() and is_self_handled_tool() helper functions
- Move parse_diff_stats() from lib.rs to streaming.rs
- Simplify tool execution display logic in lib.rs using new helpers
Net effect: -86 lines in lib.rs, +112 lines in streaming.rs
The streaming.rs additions are reusable, well-named functions.
All 585+ workspace tests pass.
Agent: fowler
Consolidate scattered state variables in the 834-line stream_completion_with_tools()
function to use the existing StreamingState and IterationState structs from
streaming.rs. This eliminates code-path aliasing where state was tracked in
multiple places and makes the streaming loop easier to reason about.
Changes:
- Add assistant_message_added field to StreamingState
- Add stream_stop_reason field to IterationState
- Replace 8 inline state variables with StreamingState::new()
- Replace 7 iteration-local variables with IterationState::new()
- All 585 workspace tests pass
This is a pure refactor with no behavior changes. The state structs were already
defined in streaming.rs but not used in the main streaming loop.
Agent: fowler
Extract a new g3_status module in g3-cli that provides consistent formatting
for all 'g3:' prefixed system status messages.
Key changes:
- Add G3Status struct with methods for progress, done, failed, error, etc.
- Add Status enum with Done, Failed, Error, Resolved, Insufficient, NoChanges
- Add ThinResult struct in g3-core for semantic thinning data
- Update UiWriter trait with print_thin_result() method
- Refactor context thinning to return ThinResult instead of formatted strings
- Update all callers to use the new centralized formatting
- Session resume/decline messages now use G3Status
- Compaction status messages now use G3Status
This maintains clean separation of concerns: g3-core emits semantic data,
g3-cli handles all terminal formatting and colors.
Adds 8 unit tests verifying:
- Research tool has 20-minute timeout
- All other tools (shell, read_file, write_file, str_replace, code_search,
webdriver_*, etc.) have standard 8-minute timeout
- Comprehensive test_only_research_has_extended_timeout covers 19 tools
This ensures future changes don't accidentally affect other tool timeouts.
The research tool often runs past 8 minutes due to web browsing and
analysis. Increased its timeout to 20 minutes while keeping other
tools at 8 minutes.
Changes:
- Tool timeout is now tool-specific (20 min for research, 8 min for others)
- Timeout error message now shows the correct duration for each tool
The bug was caused by mark_tool_calls_consumed() being called after
displaying each chunk, which advanced last_consumed_position to the
end of the current buffer. When the next chunk arrived with JSON,
the unchecked_buffer started at position 0 of the slice, causing
is_on_own_line() to return true (position 0 is always "on its own line").
Removed the problematic mark_tool_calls_consumed() call from the
"no tool executed" branch. The remaining call after actual tool
execution is correct and necessary.
Added integration test that verifies inline JSON in prose is not
detected as a tool call.
Bug: When the LLM responded with text-only (no tool calls), the assistant
message was sometimes not saved to the context window. This caused consecutive
user messages where the LLM would lose track of previous responses.
Root causes found and fixed:
1. Early return path (line ~2535): When stream finishes with no tools executed
in previous iterations (any_tool_executed=false), the code returned early
without saving the assistant message. Fixed by adding save before return.
2. Post-loop path (line ~2657): When raw_clean was empty but current_response
had content, no message was saved. Fixed by falling back to current_response.
Both paths now properly save the assistant message before returning.
The assistant_message_added flag prevents any duplication.
Added tests:
- missing_assistant_message_test.rs: verifies the fallback logic
- assistant_message_dedup_test.rs: verifies no duplicate messages
- consecutive_assistant_message_test.rs: verifies alternation invariant
Adds tests to verify that:
- All streaming chunks are processed before control returns to caller
- Both tool calls in a multi-tool-call stream are executed
- The finished signal properly terminates stream processing
Also adds Agent::new_for_test() to allow injecting mock providers.
The JSON filter only suppresses tool calls at line boundaries. When
"Memory checkpoint: " was printed without a trailing newline, the LLM
response `{"tool": "remember", ...}` appeared on the same line and
leaked through to the UI.
Fix:
- Add trailing newline to "Memory checkpoint:" message
- Reset JSON filter state before streaming the response
Added test: test_tool_call_not_at_line_start_passes_through
Documents the filter behavior and references the fix location.
- Add ToolParsingHint enum (Detected/Active/Complete) for UI feedback
- New UiWriter methods: print_tool_streaming_hint(), print_tool_streaming_active()
- Refactor ConsoleUiWriter state to use atomics in ParsingHintState
- Add tool_call_streaming field to CompletionChunk for provider hints
- Anthropic provider sends streaming hints when tool name detected
- New streaming helpers: make_tool_streaming_hint(), make_tool_streaming_active()
Parser improvements:
- Add is_json_invalidated() to detect false positive tool patterns
- Fix tool result poisoning when file contents contain partial JSON
- Unescaped newlines in strings or prose after JSON invalidates detection
User sees ' ● tool_name |' immediately when tool call starts streaming,
with blinking indicator while args are received.
The streaming parser was incorrectly detecting tool call patterns that
appeared inline in prose (e.g., when explaining the format), causing
g3 to return control mid-task.
Fix: Modified find_first_tool_call_start() and find_last_tool_call_start()
to only recognize patterns that appear on their own line (at start of
buffer or after newline with only whitespace before the pattern).
Changes:
- Added is_on_own_line() helper to check line-boundary conditions
- Updated detection methods to skip inline patterns
- Removed sanitize_inline_tool_patterns() and LBRACE_HOMOGLYPH (no longer needed)
- Rewrote tests for new behavior
- Added streaming_repro tests that use process_chunk() to verify the exact bug scenario
28 tests covering: streaming repro, line boundaries, Unicode, code contexts, edge cases
- Rename take_screenshot -> screenshot, code_coverage -> coverage (shorter names)
- Align | character across all compact tools (pad to 11 chars for str_replace)
- Make code_search a compact tool with summary display
- Show language and search name in code_search output (e.g., rust:"find structs")
- Add format_code_search_summary() to extract match/file counts from JSON response
Remove dead code - constructor variants that had no callers:
- new_with_readme()
- new_autonomous_with_readme()
- new_with_quiet()
These were thin wrappers around new_with_mode_and_readme() that were
never used externally. All 5 remaining constructors have verified callers.
Results:
- lib.rs reduced from 2817 to 2797 lines (-20 lines)
- Eliminated code-path aliasing: 8 constructors → 5 constructors
- All g3-core tests pass
- Full workspace compiles cleanly
Agent: fowler
- 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
Extract the get_stats() function (158 lines) from lib.rs to a new stats.rs module.
Changes:
- Create stats.rs with AgentStatsSnapshot struct for capturing agent state
- Replace inline formatting logic with delegation to snapshot.format()
- Add unit tests for stats formatting (empty and populated states)
- Reduce lib.rs from 2961 to 2818 lines (-143 lines)
The new module improves:
- Testability: Stats formatting can now be unit tested in isolation
- Separation of concerns: Formatting logic is decoupled from Agent struct
- Readability: lib.rs is more focused on core agent behavior
All 271 workspace tests pass.
Agent: fowler
Improve readability of stream_completion_with_tools (~1000 line function):
- Add deduplicate_tool_calls() helper with closure for previous-message check
- Add should_auto_continue() with AutoContinueReason enum for clearer control flow
- Replace inline deduplication loop with helper call (-19 lines)
- Replace complex auto-continue conditional with match on reason enum (-13 lines)
- Add section comments for major phases (State Init, Pre-loop, Main Loop, Auto-Continue, Post-Loop)
- Add comprehensive tests for new helpers
Net reduction: 82 deletions, behavior unchanged (172+ tests pass)
Agent: carmack
