ed/manual_slop
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
985 Commits 7 Branches 0 Tags
e8cd3e5e87db912748791cb828d5f9008bff6340
Commit Graph

470 Commits

Author SHA1 Message Date
ed a7903d3a4b conductor(plan): Mark tasks 1.2 and 1.3 complete — 8e57ae1 2026-03-01 15:49:32 -05:00
ed 05cd321aa9 conductor(plan): Mark task 'Task 1.1' as complete 3a68243 2026-03-01 15:28:51 -05:00
ed a7c8183364 conductor(plan): Mark simulation_hardening_20260301 all tasks complete 
All 9 tasks done across 3 phases. Key fixes beyond spec:
- btn_approve_script wired (was implemented but not registered)
- pending_script_approval exposed in hook API
- mma_tier_usage exposed in hook API
- pytest-timeout installed
- Tier 3 subscription auth fixed (ANTHROPIC_API_KEY stripping)
- --dangerously-skip-permissions for headless workers

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-01 14:32:25 -05:00
ed 5cacbb1151 conductor(plan): Mark task 3.2 complete — sim test PASSED 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-01 14:04:57 -05:00
ed c023ae14dc conductor(plan): Update task 3.1 complete, 3.2 awaiting verification 2026-03-01 13:42:52 -05:00
ed 24ed309ac1 conductor(plan): Mark task 3.1 complete — Stage 8 assertions already correct 2026-03-01 13:26:15 -05:00
ed 0fe74660e1 conductor(plan): Mark Phase 2 complete, begin Phase 3 2026-03-01 13:25:24 -05:00
ed 2f9f71d2dc conductor(plan): Mark task 2.1 complete, begin 2.2 2026-03-01 13:22:34 -05:00
ed d5eb3f472e conductor(plan): Mark task 1.4 as complete, begin Phase 2 2026-03-01 13:20:10 -05:00
ed 130a36d7b2 conductor(plan): Mark tasks 1.1, 1.2, 1.3 as complete 2026-03-01 13:18:09 -05:00
ed cf7938a843 wrong archive location 2026-03-01 13:17:34 -05:00
ed 52f3820199 conductor(gui_ux): Add Phase 6 — live streaming, per-tier model config, parallel DAG, auto-retry 
Addresses three gaps where Claude Code and Gemini CLI outperform Manual Slop's
MMA during actual execution:

1. Live worker streaming: Wire comms_log_callback to per-ticket streams so
   users see real-time output instead of waiting for worker completion.
2. Per-tier model config: Replace hardcoded get_model_for_role with GUI
   dropdowns persisted to project TOML.
3. Parallel DAG execution: asyncio.gather for independent tickets (exploratory
   — _send_lock may block, needs investigation).
4. Auto-retry with escalation: flash-lite -> flash -> pro on BLOCKED, up to
   2 retries (wires existing --failure-count mechanism into ConductorEngine).

7 new tasks across Phase 6, bringing total to 30 tasks across 6 phases.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-01 10:24:29 -05:00
ed 458529fb13 chore(conductor): Add index.md to new tracks, archive completed/superseded tracks 
- Add index.md to mma_pipeline_fix, simulation_hardening, context_token_viz
- Archive documentation_refresh_20260224 (superseded by 08e003a rewrite)
- Archive robust_live_simulation_verification (context distilled into
  simulation_hardening_20260301 spec)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-01 10:00:49 -05:00
ed 0d2b6049d1 conductor: Create 3 MVP tracks with surgical specs from full codebase analysis 
Three new tracks identified by analyzing product.md requirements against
actual codebase state using 1M-context Opus with all architecture docs loaded:

1. mma_pipeline_fix_20260301 (P0, blocker):
   - Diagnoses why Tier 3 worker output never reaches mma_streams in GUI
   - Identifies 4 root cause candidates: positional arg ordering, asyncio.Queue
     thread-safety violation, ai_client.reset_session() side effects, token
     stats stub returning empty dict
   - 2 phases, 6 tasks with exact line references

2. simulation_hardening_20260301 (P1, depends on pipeline fix):
   - Addresses 3 documented issues from robust_live_simulation session compression
   - Mock triggers wrong approval popup, popup state desync, approval ambiguity
   - 3 phases, 9 tasks including standalone mock test suite

3. context_token_viz_20260301 (P2):
   - Builds UI for product.md primary use case #2 'Context & Memory Management'
   - Backend already complete (get_history_bleed_stats, 140 lines)
   - Token budget bar, proportion breakdown, trimming preview, cache status
   - 3 phases, 10 tasks

Execution order: pipeline_fix -> simulation_hardening -> gui_ux (parallel w/ token_viz)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-01 09:58:34 -05:00
ed d93f650c3a conductor: Refine GUI UX track with full codebase knowledge, add doc references 
Rewrites comprehensive_gui_ux_20260228 spec and plan using deep analysis of
the actual gui_2.py implementation (3078 lines). The previous spec asked to
implement features that already exist (Track Browser, DAG tree, epic planning,
approval dialogs, token table, performance monitor). The new spec:

- Documents 15 already-implemented features with exact line references
- Identifies 8 actual gaps (tier stream panels, DAG editing, cost tracking,
  conductor lifecycle forms, track-scoped discussions, approval indicators,
  track proposal editing, stream scrollability)
- Rewrites all 5 phases with surgical task descriptions referencing exact
  gui_2.py line ranges, function names, and data structures
- Each task specifies the precise imgui API calls to use
- References docs/guide_architecture.md for threading constraints
- References docs/guide_mma.md for Ticket/Track data structures

Also adds architecture documentation fallback references to:
- conductor/workflow.md (new principle #9)
- conductor/product.md (new Architecture Reference section)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-01 09:51:37 -05:00
ed bf4468f125 docs(conductor): Expert-level architectural documentation refresh 2026-03-01 09:19:48 -05:00
ed 7384df1e29 remove track fro tracks 2026-03-01 09:09:04 -05:00
ed 68b9f9baee conductor(plan): Mark Phase 4 and Track as complete 2026-03-01 09:06:55 -05:00
ed 7f95ebd85e conductor(plan): Mark Phase 3 as complete [checkpoint: 61d513a] 2026-03-01 09:06:19 -05:00
ed 61d513ad08 feat(migration): Add script to consolidate legacy logs and artifacts 2026-03-01 09:06:07 -05:00
ed 32f7a13fa8 conductor(plan): Mark Phase 2 as complete [checkpoint: 6326546] 2026-03-01 09:03:15 -05:00
ed 6326546005 feat(taxonomy): Redirect logs and artifacts to dedicated sub-folders 2026-03-01 09:03:02 -05:00
ed 09bedbf4f0 conductor(plan): Mark Phase 1 as complete [checkpoint: 590293e] 2026-03-01 08:59:15 -05:00
ed 590293e3d8 conductor(plan): Mark Phase 1 as complete 2026-03-01 08:59:07 -05:00
ed 27e67df4e3 prep doc track. 2026-03-01 08:57:01 -05:00
ed efaf4e98c4 chore(conductor): Add new track 'Consolidate Temp/Test Cruft & Log Taxonomy' 2026-03-01 08:49:19 -05:00
ed 472966cb61 chore(conductor): Add new track 'Comprehensive Conductor & MMA GUI UX' 2026-03-01 08:43:15 -05:00
ed 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
ed 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
ed 2a69244f36 remove slop tracks 2026-02-28 22:40:40 -05:00
ed 397b4e6001 chore(mma): Clean up mma_exec.py and robustify visual simulation mocking 2026-02-28 22:27:17 -05:00
ed 42c42985ee chore(mma): Verify track loading in visual simulation and fix deterministic ID logic 2026-02-28 22:12:57 -05:00
ed 37df4c8003 chore(mma): Deterministic track IDs, worker spawn hooks, and improved simulation reliability 2026-02-28 22:09:18 -05:00
ed ed56e56a2c chore(mma): Checkpoint progress on visual simulation and UI refresh before sub-agent delegation 2026-02-28 21:41:46 -05:00
ed d65fa79e26 chore(mma): Implement visual simulation for Epic planning and fix UI refresh 2026-02-28 21:07:46 -05:00
ed 5792fb3bb1 checkpoint 2026-02-28 20:53:46 -05:00
ed aea782bda2 conductor(plan): Mark task 'Apply review suggestions' as complete 2026-02-28 20:53:11 -05:00
ed 7b31ac7f81 conductor(plan): Mark Phase 6 and Track as complete 2026-02-28 20:43:06 -05:00
ed 21496ee58f test(stabilization): Implement high-signal live_gui telemetry and update plan 2026-02-28 20:36:31 -05:00
ed 5e320b2bbf test(stabilization): Align tier4_interceptor tests with Popen and integrate vlogger 2026-02-28 20:20:17 -05:00
ed dfb4fa1b26 test(stabilization): Fix ai_style_formatter test expectations and integrate vlogger 2026-02-28 20:18:54 -05:00
ed c746276090 conductor(plan): Mark Phase 6 Task 1 as complete 2026-02-28 20:18:16 -05:00
ed 2a2675e386 conductor(plan): Add high-signal reporting requirements to Phase 6 2026-02-28 19:42:56 -05:00
ed 0454b94bfb conductor(plan): Add Phase 6 for Test Suite Stabilization 2026-02-28 19:40:07 -05:00
ed 8b19deeeff conductor(plan): Mark Phase 5 and Track as complete 2026-02-28 19:36:47 -05:00
ed 8bfc41ddba conductor(plan): Mark formatter script task as complete 2026-02-28 19:36:21 -05:00
ed 39bbc3f31b conductor(plan): Mark Phase 4 as complete and add Phase 5 2026-02-28 19:36:01 -05:00
ed e8833b6656 conductor(plan): Mark script and simulation tasks as complete 2026-02-28 19:00:55 -05:00
ed b801e1668d conductor(plan): Mark variable-only files task as complete 2026-02-28 18:36:03 -05:00
ed 42af2e1fa4 conductor(plan): Mark task 'Phase 4 core module type hint sweep' as complete 2026-02-28 15:14:13 -05:00