0b03b612b9
chore: Wire architecture docs into mma_exec.py and workflow delegation prompts
...
mma_exec.py changes:
- get_role_documents: Tier 1 now gets docs/guide_architecture.md + guide_mma.md
(was: only product.md). Tier 2 gets same (was: only tech-stack + workflow).
Tier 3 gets guide_architecture.md (was: only workflow.md — workers modifying
gui_2.py had zero knowledge of threading model). Tier 4 gets guide_architecture.md
(was: nothing).
- Tier 3 system directive: Added ARCHITECTURE REFERENCE callout, CRITICAL
THREADING RULE (never write GUI state from background thread), TASK FORMAT
instruction (follow WHERE/WHAT/HOW/SAFETY from surgical tasks), and
py_get_definition to tool list.
- Tier 4 system directive: Added ARCHITECTURE REFERENCE callout and instruction
to trace errors through thread domains documented in guide_architecture.md.
conductor/workflow.md changes:
- Red Phase delegation prompt: Replaced 'with a prompt to create tests' with
surgical prompt format example showing WHERE/WHAT/HOW/SAFETY.
- Green Phase delegation prompt: Replaced 'with a highly specific prompt' with
surgical prompt format example with exact line refs and API calls.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-03-01 10:16:38 -05:00
bcbccf3cc4
dont use flash-lite for tier 3
2026-03-01 09:07:17 -05:00
6326546005
feat(taxonomy): Redirect logs and artifacts to dedicated sub-folders
2026-03-01 09:03:02 -05:00
397b4e6001
chore(mma): Clean up mma_exec.py and robustify visual simulation mocking
2026-02-28 22:27:17 -05:00
37df4c8003
chore(mma): Deterministic track IDs, worker spawn hooks, and improved simulation reliability
2026-02-28 22:09:18 -05:00
cb0e14e1c0
Fixes to mma and conductor.
2026-02-28 21:59:28 -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
3d861ecf08
chore(mma): Update Tier 2 model to gemini-3-flash
2026-02-28 20:54:04 -05:00
da7a2e35c0
fix(conductor): Apply review suggestions for track 'python_style_refactor_20260227'
2026-02-28 20:53:03 -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
53c2bbfa81
refactor(scripts): Add strict type hints to utility scripts
2026-02-28 18:58:53 -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
db118f0a5c
updates to tools and mma skills
2026-02-28 07:51:02 -05:00
c062361ef9
back to usual agents
2026-02-28 00:07:57 -05:00
605dfc3149
fix(conductor): Apply review suggestions for track 'robust_live_simulation_verification'
2026-02-27 23:09:37 -05:00
fcd60c908b
idk
2026-02-27 21:25:39 -05:00
5608d8d6cd
checkpoint
2026-02-27 21:15:56 -05:00
7adacd06b7
checkpoint
2026-02-27 20:48:38 -05:00
a6e264bb4e
feat(mma): Optimize sub-agent research with get_code_outline and get_git_diff
2026-02-27 20:43:44 -05:00
138e31374b
checkpoint
2026-02-27 20:41:30 -05:00
3c0d412219
checkpoint
2026-02-27 19:54:12 -05:00
e1a3712d9a
feat(mma): Implement track-scoped state persistence and configure sub-agents
2026-02-27 19:45:21 -05:00
a5684bf773
checkpoint!
2026-02-27 19:33:18 -05:00
3b2d82ed0d
feat(mma): Finalize Orchestrator Integration and fix all regressions
2026-02-27 18:31:14 -05:00
d087a20f7b
checkpoint: mma_orchestrator track
2026-02-26 22:59:26 -05:00
716d8b4e13
chore(conductor): Archive completed track 'MMA Core Engine Implementation'
2026-02-26 22:02:33 -05:00
8bb72e351d
chore(conductor): Mark track 'MMA Core Engine Implementation' as complete and verify with Phase 6 tests
2026-02-26 21:34:28 -05:00
ff98a63450
flash-lite is too dumb
2026-02-26 09:03:58 -05:00
a664dfbbec
fix(mma): Final refinement of delegation command and log tracking
2026-02-26 08:38:10 -05:00
d343066435
fix(conductor): Apply review suggestions for track 'mma_utilization_refinement_20260226'
2026-02-26 08:35:50 -05:00
91693a5168
feat(mma): Refine tier roles, tool access, and observability
2026-02-26 08:31:19 -05:00
3a2856b27d
pain
2026-02-25 23:11:42 -05:00
75bf912f60
conductor(plan): Mark Phase 1 of DeepSeek track as verified
2026-02-25 22:36:57 -05:00
f0c1af986d
mma docs support
2026-02-25 22:29:20 -05:00
74dcd89ec5
mma execution fix
2026-02-25 22:26:59 -05:00
221374eed6
feat(mma): Complete Phase 3 context features (injection, dependency mapping, logging)
2026-02-25 20:21:12 -05:00
678fa89747
feat(mma): Implement logging/auditing for role hand-offs
2026-02-25 20:16:56 -05:00
32ec14f5c3
feat(mma): Add dependency mapping to mma-exec
2026-02-25 20:12:14 -05:00
4e564aad79
feat(mma): Implement AST Skeleton View generator using tree-sitter
2026-02-25 20:08:43 -05:00
794cc2a7f2
fix(mma): Fix tier 2 model name to valid preview model and adjust tests
2026-02-25 19:57:42 -05:00
9da08e9c42
fix(mma): Adjust skill trigger format to avoid policy blocks
2026-02-25 19:54:45 -05:00
be2a77cc79
fix(mma): Assign dedicated models per tier in execute_agent
2026-02-25 19:51:00 -05:00
f6e6d418f6
fix(mma): Use headless execution flag for context amnesia and parse json output
2026-02-25 19:45:59 -05:00
9a27a80d65
feat(mma): Implement Context Amnesia bridge via subprocess
2026-02-25 19:16:41 -05:00
55c0fd1c52
feat(mma): Implement Role-Scoped Document selection logic
2026-02-25 19:12:02 -05:00
0b2cd324e5
feat(mma): Scaffold mma_exec.py with basic CLI structure
2026-02-25 19:09:14 -05:00
