- 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
- 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
Implements a pipeline that orchestrates 7 g3 agents in sequence:
1. euler - dependency graph and hotspots analysis
2. breaker - whitebox exploration and edge-case discovery
3. hopper - deep testing and regression integrity
4. fowler - refactoring to deduplicate and reduce complexity
5. carmack - in-place rewriting for readability and concision
6. lamport - human-readable documentation and validation
7. huffman - semantic compression of memory
Features:
- Commit cursor tracking (--from flag to set starting point)
- Crash recovery (resumes from last incomplete stage)
- Git worktree isolation for all pipeline work
- Visual pipeline display with status icons
- Summary generation saved to .g3/sessions/sdlc/
- Pipeline state persisted to analysis/sdlc/pipeline.json
CLI:
- studio sdlc run [-c N] [--from COMMIT]
- studio sdlc status
- studio sdlc reset
Also adds huffman agent to embedded agents list.
- 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
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
Added plan_approve to the compact tool list in format_tool_result_summary()
so it displays in the same format as other tools like read_file and write_file.
The format_plan_approve_summary() function already existed but was never
called because plan_approve was missing from the matches! block.
- Start g3 in plan mode with ' >>' prompt and welcome message
- Add is_approval_input() to detect 'approve', 'a', 'yes', etc. and misspellings
- Allow trailing punctuation (!, ., ,) on approval words
- Call plan_approve tool directly without LLM when approval detected
- Add synthetic assistant message after approval for LLM context
- Exit plan mode after successful approval, return to 'g3>' prompt
- CTRL-D in plan mode exits plan mode first, then exits g3
- /plan command enters plan mode and shows welcome message
- Agent mode (--agent) does not start in plan mode
- Add CommandResult enum to signal plan mode entry from commands
- Fix vertical bar continuation: │ continues all the way down, only the
very last sub-line (boundary of last item) gets └
- Add visual gap before plan file path and change 📄 to ->
- Dedent file path to align with tree root
- Fix plan_approve to use proper compact tool format (was missing from
is_compact_tool matches! in print_tool_compact, causing it to fall
through to regular output with | prefix)
- Update command matching from /feature to /plan in commands.rs
- Update help text, usage message, and example
- Update workspace memory references
- /feature is no longer recognized (completely removed)
Fixes two bugs in the input formatter:
1. Single/double quote regex now requires word boundaries:
- Contractions like it's, don't, won't no longer trigger highlighting
- Only properly quoted text like 'special' or "hello" gets cyan
- Mixed input like "it's a 'test' case" only highlights 'test'
2. Visual line calculation fix for exact terminal width:
- When text exactly fills terminal width, cursor wraps to next line
- Added +1 adjustment to account for this edge case
- Extracted calculate_visual_lines() for testability
Added 9 new tests covering all edge cases.
Plan tools (plan_read, plan_write) now display with elegant tree-style
formatting similar to the old todo_write UI:
- State indicators: □ (todo), ◐ (doing), ■ (done), ⊘ (blocked)
- Tree prefixes (├/└) for items with child details
- Strikethrough for completed items
- Shows touches and all three checks (happy/negative/boundary)
- Displays plan file path link at the end
plan_approve uses compact single-line format like read_file:
- Shows approval status and revision number
- Handles already-approved and error cases
Changes:
- Add print_plan_compact() to UiWriter trait with default impl
- Implement print_plan_compact() in ConsoleUiWriter
- Call print_plan_compact() from execute_plan_read/write
- Add plan_read/plan_write to is_self_handled_tool()
- Add plan_approve to is_compact_tool() with format_plan_approve_summary()
- Add serde_yaml dependency to g3-cli
Adds a verification system that checks evidence in completed plan items:
- Evidence parsing: supports code locations (file:line, file:line-line, file only)
and test references (file::test_name)
- Code location verification: checks file exists, validates line numbers in range
- Test reference verification: checks test file exists, searches for fn pattern
- Verification results: Verified, Warning, Error, Skipped statuses
- Loud output formatting with emoji indicators for warnings/errors
- Integration with execute_plan_write(): runs when plan is complete and approved
- 12 new unit tests covering parsing and verification
Warnings are advisory (don't block), errors are loud but also don't block.
Blocked items are skipped during verification.
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
Add characterization tests for the streaming parser stuttering bug fix (fa3c920).
These tests verify that when an LLM "stutters" and emits incomplete tool call
fragments followed by complete tool calls, the parser:
1. Does not get stuck waiting for the incomplete fragment to complete
2. Successfully parses complete tool calls that appear after the fragment
Tests cover:
- The exact pattern from butler session butler_c6ab59af2e4f991c
- Edge cases that should NOT trigger invalidation (nested JSON, patterns in strings)
- Recovery behavior after reset
- Multiple complete tool calls
- Boundary conditions (chunk boundaries, minimal patterns)
Agent: hopper
Fixes issues in the last 11 commits:
1. pending_research.rs: Fix flaky test_generate_id_uniqueness
- Replaced random u16 suffix with atomic counter for guaranteed uniqueness
- The timestamp+random approach could collide when generating IDs rapidly
- Now uses static AtomicU32 counter that increments monotonically
2. embedded/adapters/glm.rs: Remove unused in_code_fence field
- Field was written but never read (dead code)
- Removed from struct definition, constructor, and reset()
3. embedded/adapters/glm.rs: Fix orphaned tests
- Two tests (test_strip_code_fences, test_code_fenced_tool_call) were
outside the #[cfg(test)] mod tests block
- Moved closing brace to include them in the test module
All 446 library tests pass.
Agent: fowler
Allow users to view research reports directly from the CLI:
- /research - List all research tasks (unchanged)
- /research <id> - View the full report for a specific research task
- /research latest - View the most recent completed research report
Report display includes query, status, elapsed time, and full content.
When the LLM 'stutters' and emits incomplete tool call fragments like:
{"tool": "shell", "args": {...}}
{"tool":
{"tool": "shell", "args": {...}}
The parser would get stuck waiting for the incomplete fragment to complete,
causing the entire response to be lost (no tool executed, no text displayed).
This was observed in butler session butler_c6ab59af2e4f991c where the user's
'send!' command produced no response.
Fix: Enhanced is_json_invalidated() to detect when a new tool call pattern
({"tool"}) appears after a newline while parsing an incomplete JSON fragment.
This indicates the previous fragment was abandoned and should be invalidated.
Safety:
- Tool patterns inside JSON strings (e.g., writing example code) are not
affected because the check only runs outside strings
- Added tests for the stuttering pattern and the file-writing edge case
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]"
Fixes three bugs in the input formatter introduced in 4e16942:
1. Bug 2 & 3 (missing newline, line duplication):
- Changed print! to println! to add trailing newline
- Calculate visual lines based on terminal width instead of
logical line count, fixing duplication for wrapped lines
2. Bug 1 (^M on non-interactive prompts):
- Added TTY check to skip formatting when stdout is not a terminal
- Prevents terminal state corruption for stdin prompts
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
When users type prompts in interactive mode, the input is now
reformatted in place with enhanced highlighting:
- ALL CAPS words (2+ chars) become bold green (e.g., FIX, BUG, HTTP2)
- Quoted text ("..." or ...) becomes cyan
- Standard markdown formatting is also supported
New module: input_formatter.rs with 10 unit tests
Integrated into interactive.rs for both single-line and multiline input
- Add CommonFlags struct to group flags that apply across all modes
- Refactor run_agent_mode() to accept CommonFlags instead of individual params
- Add project loading logic for agent chat mode
- Add integration tests for --project with agent mode
This refactor prevents future bugs where new flags work in one mode
but are forgotten in another.
GLM-4 models wrap tool calls in markdown code fences and inline backticks,
which prevents the streaming parser from detecting them. This adapter:
- Strips ```json and ``` code fence markers during streaming
- Strips inline backticks from tool call JSON
- Handles chunked streaming correctly (buffers potential fence lines)
- Transforms GLM native format (<|assistant|>tool_name) to g3 JSON format
Also refactors embedded provider into module structure:
- embedded/mod.rs - module exports
- embedded/provider.rs - main EmbeddedProvider (moved from embedded.rs)
- embedded/adapters/mod.rs - ToolFormatAdapter trait
- embedded/adapters/glm.rs - GLM-specific adapter
Includes 22 unit tests covering edge cases like nested JSON in strings,
chunk boundary handling, and false pattern detection.
Updates README to show GLM-4 9B now works (⭐⭐) for agentic tasks.
embedded.rs (937→789 lines, -16%):
- Extract duplicated inference setup into prepare_context() helper
- Extract stop sequence handling into find_stop_sequence() and truncate_at_stop_sequence()
- Add InferenceParams struct to consolidate request parameter extraction
- Add clear section markers for code organization
- Tests now use module-level format functions directly (no duplication)
gemini.rs:
- Extract common request building into build_request() method
- Reduces duplication between complete() and stream() methods
All 399 unit tests pass. Behavior unchanged.
Agent: carmack
Agent: hopper
Added two new integration test files:
1. cache_stats_integration_test.rs (g3-core)
- Tests CacheStats accumulation through streaming completion flow
- Verifies cache hit detection (cache_read_tokens > 0)
- Tests multi-request accumulation of cache statistics
- Verifies cache efficiency and hit rate calculations
- Uses MockProvider to simulate provider usage data
2. gemini_serialization_test.rs (g3-providers)
- Tests Gemini API message format conversion
- Verifies system messages become system_instruction
- Verifies assistant role maps to "model" (Gemini terminology)
- Tests tool conversion to function_declarations format
- Characterizes multi-system-message behavior (last wins)
Both test files follow blackbox/integration testing principles:
- Test observable behavior through stable surfaces
- Do not assert internal implementation details
- Include documentation of what is/is not asserted
Named after David Huffman, inventor of Huffman coding -
compression that preserves information with fewer bits.
Fits the agent's purpose: compact memory, preserve semantics.
