ed/manual_slop
Private
Public Access
0
0
Fork 0
Code Activity
3,320 Commits 36 Branches 1 Tag
cb7c82008e18d237b4f33dcd8ff56f2385b45c71
Commit Graph
1197 Commits
Author SHA1 Message Date
ed e060399579 conductor(plan): add state.toml for tier2_autonomous_sandbox track 
44 tasks across 9 phases, all pending. Tracks:
- failcount unit test progression (13 target)
- slash command spec tests (11 target)
- report writer tests (4 opt-in)
- bootstrap test (1 opt-in)
- sandbox enforcement test (1 opt-in)
- smoke e2e test (1 opt-in, double gate)

Enforcement stack contract: 9 flags tracking the 4 git bans + filesystem
boundary + 3 hook installs + OpenCode deny rules + Windows restricted token.
Final verification requires all 9 enforcement flags = true.

status: active, current_phase: 0, blocked_by: none, blocks: none
 2026-06-16 18:51:42 -04:00
ed 6a26713d74 conductor(plan): Tier 2 autonomous sandbox - implementation plan + metadata 
9 phases, 30+ tasks, scope-only (no T-shirt size per user feedback):
- Phase 1: failcount module (15 TDD tasks, 13 unit tests, 100% coverage target)
- Phase 2: failure report writer (4 sections, opt-in tests)
- Phase 3: slash command + agent + opencode.json.fragment templates (11 spec tests)
- Phase 4: run_track.py CLI entry point (duplicates slash command protocol)
- Phase 5: setup_tier2_clone.ps1 bootstrap (idempotent, -WhatIf support)
- Phase 6: run_tier2_sandboxed.ps1 launcher (restricted token skeleton v1)
- Phase 7: git hooks (pre-push refuses all pushes, post-checkout logs)
- Phase 8: opt-in tests (TIER2_SANDBOX_TESTS=1, TIER2_SMOKE=1)
- Phase 9: user guide + tracks.md registration + metadata

Key contracts:
- FailcountState dataclass with 3 signals (red/green/no_progress)
- Result-style with to_dict/from_dict for state persistence
- Atomic write via tmp + os.replace
- 3-layer enforcement: OpenCode permission system + Windows restricted token + git hooks
 2026-06-16 18:46:36 -04:00
ed 568804c7d9 conductor(spec): drop T-shirt size per user feedback 2026-06-16 18:38:09 -04:00
ed 024938bd46 conductor(spec): Tier 2 autonomous sandbox track spec 2026-06-16 18:31:48 -04:00
ed ed6602274d docs(tracks): strip day estimates from exception_handling_audit + rag_test_failures (Tier 1 rule) 2026-06-16 10:16:17 -04:00
ed 4c0b19b4db conductor(track): spec/plan/metadata for result_migration_20260616 (5 sub-tracks, NO day estimates) 2026-06-16 10:15:46 -04:00
ed 01fbd62a3f conductor(track): mark exception_handling_audit_20260616 as completed 2026-06-16 09:10:14 -04:00
ed 3c267f6b9c conductor(track): metadata.json for exception_handling_audit_20260616 2026-06-16 09:05:59 -04:00
ed a33bfb0abd conductor(track): plan for exception_handling_audit_20260616 (5 phases, ~12 tasks) 2026-06-16 09:05:40 -04:00
ed e81413a2cd conductor(track): spec for exception_handling_audit_20260616 (audit + doc clarification) 2026-06-16 09:05:19 -04:00
ed ba04363003 conductor(track): mark rag_test_failures_20260615 as completed 
Updated metadata.json: status=completed, completed_at=2026-06-15,
verification_criteria filled with actual results.

Updated tracks.md: status=shipped, 4-commit summary, test file added.

Final result: 1288 pass + 4 skip + 0 fail. All 11 batched test tiers pass
in 873.6s. First fully green baseline since 2026-06-12.
 2026-06-16 00:31:26 -04:00
ed 3fc492e302 conductor(track): metadata.json for rag_test_failures_20260615 2026-06-15 21:54:36 -04:00
ed 3aa4cfa133 conductor(track): plan for rag_test_failures_20260615 (5 phases, ~10 tasks) 2026-06-15 21:53:13 -04:00
ed 006df67637 conductor(track): spec for rag_test_failures_20260615 (3 RAG test fixes, single root cause) 2026-06-15 21:51:11 -04:00
ed bbd4c7b5c0 conductor(track): mark public_api_migration_and_ui_polish_20260615 as completed 
- metadata.json: status -> completed
- state.toml: all 7 phases marked completed; all tasks marked completed
  with their commit SHAs
- Includes the 4 Phase 2 follow-up mock fixes for:
  test_conductor_engine_v2.py (10 tests)
  test_context_pruner.py (1 test)
  test_rag_integration.py (1 test)
  test_tiered_aggregation.py (1 test)

Test count: 1286 + 12 newly-passing = 1298 pass; 4 RAG failures deferred.
(Note: 12 newly-passing includes the 6 pre-existing failures from the
spec PLUS 6 more from test_conductor_engine_v2.py and the user's
manual corrections to test_ai_loop_regressions_20260614.py and
test_conductor_engine_v2.py.)

Total commits in this track: ~25 atomic commits + 6 phase checkpoints.
 2026-06-15 20:41:12 -04:00
ed 4514487283 messing around (intent scripting lang) 2026-06-15 19:34:20 -04:00
ed 0e55ebaf08 conductor(checkpoint): Phase 6 complete - deprecation removed 
- 8c81b727: Removed @deprecated send() function and typing_extensions.deprecated
  import from src/ai_client.py (lines 2939-3000)
- e40b122b: Deleted obsolete tests/test_deprecation_warnings.py (both
  tests were obsolete after send() removal)
- 90122df3: Removed filterwarnings entry in pyproject.toml that silenced
  the send() deprecation

Verified:
- uv run rg 'ai_client.send\\(' src/ tests/ returns 0 real call sites
  (3 remaining hits are docstring references only)
- import src.ai_client; hasattr(ai, 'send') is False
- 73/73 migrated tests pass

Phases 1-6 complete. Phase 7 (docs + final sweep) in progress.
 2026-06-15 18:54:34 -04:00
ed da6e084893 conductor(checkpoint): Phase 2 complete - 18 test files migrated to send_result() 
Migrated 11 call-site files + 7 production-affected mock files to use
send_result() instead of send():

Call-site migrations (11 files):
- test_ai_client_cli.py
- test_ai_cache_tracking.py
- test_ai_client_result.py (deleted test_send_deprecated_emits_warning;
  renamed test_send_extracts_data_from_result to
  test_send_result_does_not_emit_deprecation)
- test_api_events.py
- test_deepseek_provider.py (6 sites in 1 file)
- test_gemini_cli_edge_cases.py
- test_gemini_cli_integration.py
- test_gemini_cli_parity_regression.py
- test_gui2_mcp.py
- test_tier4_interceptor.py
- test_token_usage.py

Mock migrations (7 files; pre-empted Phase 1 regressions):
- test_conductor_tech_lead.py (3 mocks)
- test_orchestration_logic.py (4 mocks including the missed
  test_run_worker_lifecycle_blocked)
- test_orchestrator_pm.py (3 mocks)
- test_orchestrator_pm_history.py (1 mock)
- test_phase6_engine.py (1 mock)
- test_run_worker_lifecycle_abort.py (1 mock)
- test_spawn_interception_v2.py (1 mock)

test_rag_integration.py mock migration deferred to RAG track (OOS1).

Verified: 64/64 tests pass in the 18 migrated files.
 2026-06-15 17:46:26 -04:00
ed b7fd4e4f6a conductor(checkpoint): Phase 1 complete - 3 production call sites migrated to send_result() 
- src/conductor_tech_lead.py:68 (G1, commit bbb3d597): 2-arg call, no callbacks
- src/orchestrator_pm.py:86 (G2, commit 7ea802ab): 3-arg call with enable_tools
- src/multi_agent_conductor.py:591 (G3, commit bdd46299): 8-arg call with 5 callbacks
  (the hardest; per-ticket error handling routes the error to comms +
  pushes a 'response' event with status='error' + marks ticket.status='error')

Verified: uv run rg 'ai_client\.send\(' src/ returns 0 hits in production code
(line 8 of conductor_tech_lead.py is a docstring mention only).

Pending: 7 test files broken by these production migrations need
send_result() mocks instead of send() mocks. These are scheduled in
Phase 2.12-2.18 (added in the plan update bb3b3056).
 2026-06-15 16:01:23 -04:00
ed bb3b3056b4 conductor(plan): add 7 production-affected test mock files to Phase 2 
The original Phase 2 covered 12 test files that *call* ai_client.send(...).
Phase 1.1 implementation revealed 7 additional test files that *mock*
ai_client.send (via patch()) for tests of the production code paths.
When production migrates to send_result(), these mocks receive 0 calls
and the tests fail with 'send was called 0 times'.

Adding Phase 2.12-2.18 to cover:
- test_conductor_tech_lead.py (3 mocks; breaks after Phase 1.1)
- test_orchestration_logic.py (1 mock; breaks after Phase 1.1)
- test_orchestrator_pm.py (3 mocks; pre-empt Phase 1.2)
- test_orchestrator_pm_history.py (1 mock; pre-empt Phase 1.2)
- test_phase6_engine.py (1 mock; pre-empt Phase 1.3)
- test_run_worker_lifecycle_abort.py (1 mock; pre-empt Phase 1.3)
- test_spawn_interception_v2.py (1 mock; pre-empt Phase 1.3)

test_rag_integration.py mock migration deferred to RAG track (OOS1).

Also adds state.toml for the track (7 phases, 28 tasks, audit fields).
 2026-06-15 15:50:56 -04:00
ed 55ff733df5 conductor(track): metadata.json for public_api_migration_and_ui_polish_20260615 2026-06-15 15:24:46 -04:00
ed 8ab71035d5 conductor(track): plan for public_api_migration_and_ui_polish_20260615 (7 phases, 28 tasks) 2026-06-15 15:23:19 -04:00
ed 3febdab42c conductor(track): spec for public_api_migration_and_ui_polish_20260615 (3 prod + 12 test migrations + 2 UI Polish test fixes) 2026-06-15 15:20:44 -04:00
ed a8c8125118 conductor(track): mark doeh_test_thinking_cleanup_20260615 as completed 2026-06-15 14:49:59 -04:00
ed 6edeb2b5a9 conductor(state): fix duplicate keys in ai_loop_regressions_20260614 state.toml 2026-06-15 14:29:07 -04:00
ed 27d7a04fd3 conductor(plan): Mark Phase 1 (G1 critical regression fix) complete 2026-06-15 12:58:34 -04:00
ed 88bf04eb3d conductor(track): metadata.json for doeh_test_thinking_cleanup_20260615 2026-06-15 12:21:16 -04:00
ed 304f469663 conductor(track): plan for doeh_test_thinking_cleanup_20260615 (TDD-style, 5 phases, 16 tasks) 2026-06-15 12:20:06 -04:00
ed 925e366cdd conductor(track): spec for doeh_test_thinking_cleanup_20260615 (1 critical regression + 11 test mocks + 2 deferred bugs) 2026-06-15 12:17:51 -04:00
ed e6afefdc66 conductor(plan): mark track complete (all 5 phases, 17 tasks done) 2026-06-15 11:25:32 -04:00
ed 010752229b conductor(track): mark ai_loop_regressions_20260614 as completed 
Updates status: active -> completed, adds completed_at date,
updates verification_criteria with the actual verification results.

7 regression tests pass; 14 pre-existing failures (parent track's
state.toml [regressions_20260612]) are not caused by these changes.
 2026-06-15 11:24:43 -04:00
ed 5f4c347824 conductor(plan): mark Phase 4 (FR3 fix) complete 2026-06-15 10:58:45 -04:00
ed 722b09b99b conductor(plan): mark Phase 3 (FR2 fix) complete 2026-06-15 10:28:26 -04:00
ed 95288e4cb2 conductor(plan): mark Phase 2 (FR1 fix) complete 2026-06-15 09:42:44 -04:00
ed 9b280a43fb conductor(plan): mark Phase 1 (TDD red) complete 2026-06-15 09:20:41 -04:00
ed 44dc90bca8 test(ai_loop): add FR1/FR2/FR3 tests for ai_loop_regressions_20260614 (TDD red) 
3 bug groups, all reproducing documented regressions:
- test_fr1_*: error response becomes a discussion entry (Bug #2)
- test_fr2_*: no ProviderError references in src/app_controller.py (Bug #1)
- test_fr3_*: MiniMax thinking mono rendering in returned text (Bug #3)

4 critical tests fail for the documented reasons; 3 sanity checks pass.
 2026-06-15 09:18:07 -04:00
ed acc294ae4e conductor(track): metadata.json for ai_loop_regressions_20260614 2026-06-15 00:44:52 -04:00
ed 884e40b9d1 conductor(track): plan for ai_loop_regressions_20260614 (TDD-style, 5 phases, 17 tasks) 2026-06-15 00:41:57 -04:00
ed 7a4dcc9690 conductor(track): spec for ai_loop_regressions_20260614 (MiniMax/Gemini/Gemini CLI/DeepSeek) 2026-06-15 00:33:04 -04:00
ed 4b4721ded4 Track: Complete track ai_client_docs_20260613 2026-06-13 18:27:50 -04:00
ed 9ffd3576f9 Track: Complete Phase 1 of ai_client documentation 
Updates plan.md and state.toml to mark Phase 1 tasks (core loops and public entry points documentation) as completed.
 2026-06-13 18:05:45 -04:00
ed 23a8554051 Initialize track: SQLite-Granularity Inline Docs for ai_client.py 
Creates spec, plan, and state configurations to document the dispatch loops, providers, and helper functions in src/ai_client.py.
 2026-06-13 17:55:48 -04:00
ed e02a865dea Docstrings: Complete registration of continued SQLite inline docs track 2026-06-13 16:45:23 -04:00
ed 4691848683 Docstrings: SSDL + ASCII Layout Map for Personas, Providers, and Command Palette 2026-06-13 16:45:12 -04:00
ed cb129aaed9 Docstrings: SSDL + ASCII Layout Map for Preset Managers and Windows 2026-06-13 16:30:34 -04:00
ed 56e1950b4b Document settings hubs and diagnostics in gui_2.py and complete track 
Add SQLite-style inline docstrings to render_ai_settings_hub, render_agent_tools_panel, and render_diagnostics_panel under simplified granularity per user request. Mark track sqlite_docs_gui_2_20260612 as complete.
 2026-06-12 21:30:47 -04:00
ed db850478e9 docs(plan): Record Phase 3 completions and transition to Phase 4 2026-06-12 21:27:58 -04:00
ed 92cff70543 docs(gui_2): Document context composition, context files table, and ast inspector 2026-06-12 21:27:44 -04:00
ed d1a69395b8 docs(plan): Record Phase 2 completions and move to Phase 3 2026-06-12 21:25:06 -04:00
ed 7952817c98 docs(plan): Record Task 2.1 & 2.2 completions 2026-06-12 21:24:29 -04:00