90fc38f671
fix(sim): wire btn_approve_script and expose pending_script_approval in hook API
...
_handle_approve_script existed but was not registered in the click handler dict.
_pending_dialog (PowerShell confirmation) was invisible to the hook API —
only _pending_ask_dialog (MCP tool ask) was exposed.
- gui_2.py: register btn_approve_script -> _handle_approve_script
- api_hooks.py: add pending_script_approval field to mma_status response
- visual_sim_mma_v2.py: _drain_approvals handles pending_script_approval
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-01 14:31:32 -05:00
63fa181192
feat(sim): add pytest timeout(300) and tier_usage Stage 9 check
...
Task 2.3: prevent infinite CI hangs with 300s hard timeout
Task 3.2: non-blocking Stage 9 logs mma_tier_usage after Tier 3 completes
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-01 14:24:05 -05:00
08734532ce
test(mock): add standalone test for mock_gemini_cli routing
...
4 tests verify: epic prompt -> Track JSON, sprint prompt -> Ticket JSON
with correct field names, worker prompt -> plain text, tool-result -> plain text.
All pass in 0.57s.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-01 14:22:53 -05:00
0593b289e5
fix(mock): correct sprint ticket format and add keyword detection
...
- description/status/assigned_to fields now match parse_json_tickets expectations
- Sprint planning branch also detects 'generate the implementation tickets'
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-01 14:21:21 -05:00
ce5b6d202b
fix(tier1): disable tools in generate_tracks, add enable_tools param to ai_client.send
...
Tier 1 planning calls are strategic — the model should never use file tools
during epic initialization. This caused JSON parse failures when the model
tried to verify file references in the epic prompt.
- ai_client.py: add enable_tools param to send() and _send_gemini()
- orchestrator_pm.py: pass enable_tools=False in generate_tracks()
- tests/visual_sim_mma_v2.py: remove file reference from test epic
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-01 14:04:44 -05:00
89a8d9bcc2
test(sim): Rewrite visual_sim_mma_v2 for real Gemini API with frame-sync fixes
...
Uses gemini-2.5-flash-lite (real API, CLI quota exhausted). Adds _poll/_drain_approvals helpers, frame-sync sleeps after all state-changing clicks, proper stage transitions, and 120s timeouts for real API latency. Addresses simulation_hardening Issues 2 & 3.
2026-03-01 13:42:34 -05:00
3eefdfd29d
fix(mma): Replace token stats stub with real comms log extraction in run_worker_lifecycle
...
Task 2.1 of mma_pipeline_fix_20260301: capture comms baseline before send(), then sum input_tokens/output_tokens from IN/response entries to populate engine.tier_usage['Tier 3'].
2026-03-01 13:22:15 -05:00
c5695c6dac
test(mma): Add test verifying run_worker_lifecycle pushes response via _queue_put
...
Task 1.4 of mma_pipeline_fix_20260301: asserts stream_id='Tier 3 (Worker): T1', event_name='response', text and status fields correct.
2026-03-01 13:19:50 -05:00
6326546005
feat(taxonomy): Redirect logs and artifacts to dedicated sub-folders
2026-03-01 09:03:02 -05:00
26287215c5
get rid of cruft
2026-03-01 08:44:30 -05:00
da21ed543d
fix(mma): Unblock visual simulation - event routing, loop passing, adapter preservation
...
Three independent root causes fixed:
- gui_2.py: Route mma_spawn_approval/mma_step_approval events in _process_event_queue
- multi_agent_conductor.py: Pass asyncio loop from ConductorEngine.run() through to
thread-pool workers for thread-safe event queue access; add _queue_put helper
- ai_client.py: Preserve GeminiCliAdapter in reset_session() instead of nulling it
Test: visual_sim_mma_v2::test_mma_complete_lifecycle passes in ~8s
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-01 08:32:31 -05:00
6b0823ad6c
checkpoint: this is a mess... need to define stricter DSL or system for how the AI devices sims and hookup api for tests.
2026-02-28 22:50:14 -05:00
397b4e6001
chore(mma): Clean up mma_exec.py and robustify visual simulation mocking
2026-02-28 22:27:17 -05:00
42c42985ee
chore(mma): Verify track loading in visual simulation and fix deterministic ID logic
2026-02-28 22:12:57 -05:00
37df4c8003
chore(mma): Deterministic track IDs, worker spawn hooks, and improved simulation reliability
2026-02-28 22:09:18 -05:00
ed56e56a2c
chore(mma): Checkpoint progress on visual simulation and UI refresh before sub-agent delegation
2026-02-28 21:41:46 -05:00
d65fa79e26
chore(mma): Implement visual simulation for Epic planning and fix UI refresh
2026-02-28 21:07:46 -05:00
5792fb3bb1
checkpoint
2026-02-28 20:53:46 -05:00
3b96b67d69
chore(checkpoint): Phase 6 Test Suite Stabilization complete. 257/261 tests PASS. Resolved run_linear drift, formatter expectations, and Hook Server startup.
2026-02-28 20:42:54 -05:00
21496ee58f
test(stabilization): Implement high-signal live_gui telemetry and update plan
2026-02-28 20:36:31 -05:00
5e320b2bbf
test(stabilization): Align tier4_interceptor tests with Popen and integrate vlogger
2026-02-28 20:20:17 -05:00
dfb4fa1b26
test(stabilization): Fix ai_style_formatter test expectations and integrate vlogger
2026-02-28 20:18:54 -05:00
ece46f922c
test(stabilization): Resolve run_linear API drift and implement vlogger high-signal reporting
2026-02-28 20:18:05 -05:00
173ea96fb4
refactor(indentation): Apply codebase-wide 1-space ultra-compact refactor. Formatted 21 core modules and tests.
2026-02-28 19:36:38 -05:00
2907eb9f93
chore(checkpoint): Phase 4 Codebase-Wide Type Hint Sweep complete. Total fixes: ~400+. Verification status: 230 pass, 16 fail (pre-existing API drift), 29 error (live_gui env).
2026-02-28 19:35:46 -05:00
7a0e8e6366
refactor(tests): Add strict type hints to final batch of test files
2026-02-28 19:31:19 -05:00
f5e43c7987
refactor(tests): Add strict type hints to sixth batch of test files
2026-02-28 19:25:54 -05:00
cc806d2cc6
refactor(tests): Add strict type hints to fifth batch of test files
2026-02-28 19:24:02 -05:00
ee2d6f4234
refactor(tests): Add strict type hints to fourth batch of test files
2026-02-28 19:20:41 -05:00
e8513d563b
refactor(tests): Add strict type hints to third batch of test files
2026-02-28 19:16:19 -05:00
579ee8394f
refactor(tests): Add strict type hints to second batch of test files
2026-02-28 19:11:23 -05:00
f0415a40aa
refactor(tests): Add strict type hints to first batch of test files
2026-02-28 19:06:50 -05:00
60396f03f8
refactor(types): auto -> None sweep across entire codebase
...
Applied 236 return type annotations to functions with no return values
across 100+ files (core modules, tests, scripts, simulations).
Added Phase 4 to python_style_refactor track for remaining 597 items
(untyped params, vars, and functions with return values).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-28 11:16:56 -05:00
d36632c21a
checkpoint: massive refactor
2026-02-28 09:06:45 -05:00
bc261c6cbe
teststests in wrong spot.
2026-02-28 00:07:45 -05:00
db65162bbf
chore(conductor): Complete Phase 1 of AI style refactor
2026-02-27 23:52:06 -05:00
2a30e62621
test(sim): Setup framework for robust live sim verification
2026-02-27 23:20:42 -05:00
25b72fba7e
feat(ui): Support multiple concurrent AI response streams and strategy visualization
2026-02-27 22:56:40 -05:00
2b1cfbb34d
feat(ui): Implement Track Browser and progress visualization in MMA Dashboard
2026-02-27 22:49:03 -05:00
21157f92c3
feat(mma): Finalize Approval UX Modal in GUI
2026-02-27 22:30:55 -05:00
4c53ca11da
feat(mma): Implement interception logic in GUI and Conductor
2026-02-27 22:29:55 -05:00
e293c5e302
feat(mma): Implement spawn interception in multi_agent_conductor.py
2026-02-27 22:27:05 -05:00
528aaf1957
feat(mma): Finalize Phase 1 with AST-based outline and improved tiered selection
2026-02-27 22:23:50 -05:00
2ece9e1141
feat(aggregate): support dictionary-based file entries with optional tiers
2026-02-27 22:21:18 -05:00
0ed01aa1c9
feat(mma): Integrate AST skeleton extraction into Tier 3 context build
2026-02-27 22:18:26 -05:00
6aa642bc42
feat(mma): Implement tiered context scoping and add get_definition tool
2026-02-27 22:16:43 -05:00
bf1faac4ea
checkpoint!
2026-02-27 20:21:52 -05:00
154957fe57
feat(mma): Implement ExecutionEngine with auto-queue and step-mode support
2026-02-27 20:11:11 -05:00
f85ec9d06f
feat(mma): Add topological sorting to TrackDAG with cycle detection
2026-02-27 20:04:04 -05:00
a3cfeff9d8
feat(mma): Implement TrackDAG for dependency resolution and cycle detection
2026-02-27 19:58:10 -05:00
