ed/manual_slop
Private
Public Access
0
0
Fork 0
Code Activity
3,335 Commits 16 Branches 1 Tag
959ea38b87ae653a25caa22dd7ded7d1a88754fa
Commit Graph

3335 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
ed 959ea38b87 conductor(track): fable_review_20260617 metadata — point to plan.md 
Plan committed at 8ec6d8f4 (1010 lines, 7 phases, 50+ tasks).
 2026-06-17 01:41:58 -04:00
ed 8ec6d8f4a6 conductor(plan): Add fable_review_20260617 plan 
7 phases, 50+ bite-sized tasks. Phase 1: init + 4 skeleton files. Phase 2: 10 parallel Tier 3 cluster sub-agent dispatches. Phase 3: 17 synthesis sections (Tier 1 max-token-output strategy). Phase 4: 3 side artifacts. Phase 5: self-review. Phase 6: user review. Phase 7: final commit + register. Every task has a verification command. Fable artifact at docs/artifacts/Fable System Prompt.txt is NEVER staged (verified per-task). No day estimates (per conductor/workflow.md §Tier 1 Track Initialization Rules).
 2026-06-17 01:41:42 -04:00
ed 8eaf694f4a conductor(tracks): Register fable_review_20260617 in tracks.md 
New research track for critical analysis of Anthropic's Claude Fable 5 system prompt. Added as row 25 in the Active Tracks table (Priority B research) and as a section in the new 'Active Research Tracks (2026-06+)' grouping. The companion spec + metadata + state.toml are committed in 058e2c93 and a6114ef9.
 2026-06-17 01:19:45 -04:00
ed a6114ef9ac conductor(track): Add fable_review_20260617 state.toml 
7 phases (init -> 10 parallel cluster dispatches -> 17 synthesis sections -> 3 side artifacts -> self-review -> user review -> register). Each phase has explicit task IDs (t1_1 .. t7_4) for Tier 2 to walk through. current_phase = 0 (spec approved, not started). Hard rule encoded in [meta]: docs/artifacts/Fable System Prompt.txt is NEVER committed.
 2026-06-17 01:16:20 -04:00
ed 058e2c9385 conductor(track): Add fable_review_20260617 spec + metadata 
Critical-analysis track for Anthropic's Claude Fable 5 system prompt (1585 lines, the public 'Mythos' version). 10 cluster sub-reports written by Tier 3 workers in parallel, synthesized by Tier 1 into a 17-section report (>3500 LOC) with 3 side artifacts. T-shirt size: XL. Fable artifact at docs/artifacts/Fable System Prompt.txt is local-only and MUST NOT be committed (per user hard rule). No day estimates (per conductor/workflow.md §Tier 1 Track Initialization Rules).
 2026-06-17 01:15:58 -04:00
ed c1d9a966d7 conductor(plan): Rename send_result to send (sandbox test track) 
The first end-to-end test of the tier2_autonomous_sandbox_20260616
sandbox. Pure mechanical rename: ai_client.send_result to ai_client.send
across 38 active files (6 src/, 29 tests/, 3 current docs). 10 atomic
commits across 5 phases. No behavior change; no new tests; the existing
test suite is the safety net.

Phase structure:
- Phase 1: rename src/ai_client.py (TDD red moment)
- Phase 2: rename 5 other src/ files (batch)
- Phase 3: rename top 5 test files (one commit per file)
- Phase 4: rename 24 remaining test files (batch)
- Phase 5: rename 3 current docs + final verification
- Phase 6: update state + metadata + register in tracks.md

Historical archives (conductor/tracks/*/spec.md, conductor/tracks/*/plan.md,
docs/reports/*) are NOT modified per spec section 7.
 2026-06-16 23:52:59 -04:00
ed 9ba61d43d3 docs(tier2): add track completion report (final verification + spec coverage matrix) 2026-06-16 23:29:00 -04:00
ed 00c6922c0b conductor(plan): mark tier2_autonomous_sandbox_20260616 as complete (all 9 phases done) 2026-06-16 23:23:28 -04:00
ed eedbfa1180 conductor(plan): update metadata.json to status=shipped + actual test counts 2026-06-16 23:22:24 -04:00
ed 2f79f19989 conductor(plan): register tier2_autonomous_sandbox_20260616 in tracks.md 2026-06-16 23:21:21 -04:00
ed 8bf7cd175b docs(tier2): add user guide for Tier 2 autonomous sandbox 2026-06-16 22:48:13 -04:00
ed 3e17aa6c8b test(tier2): add smoke e2e test (opt-in, double-gate TIER2_SANDBOX_TESTS+TIER2_SMOKE) 2026-06-16 22:26:04 -04:00
ed 5b6e7db174 test(tier2): add sandbox enforcement test (pre-push hook refuses push) 2026-06-16 20:25:44 -04:00
ed 5d150dc6e0 test(tier2): add bootstrap -WhatIf test (opt-in via TIER2_SANDBOX_TESTS) 2026-06-16 20:01:32 -04:00
ed 37eafc008e test(tier2): add trivial smoke track for e2e test (force-added, fixture) 2026-06-16 19:57:36 -04:00
ed cb7c82008e test(tier2): add tier2_sandbox and tier2_smoke pytest markers 2026-06-16 19:56:20 -04:00
ed e487d34b40 feat(tier2): add post-checkout detection hook (logs to tier2_checkout_log.txt) 2026-06-16 19:51:16 -04:00
ed 01be39236b feat(tier2): add pre-push hook that refuses all pushes 2026-06-16 19:50:58 -04:00
ed cba5457b9d feat(tier2): add run_tier2_sandboxed.ps1 launcher with restricted token (skeleton) 2026-06-16 19:49:47 -04:00
ed a9be60ae50 feat(tier2): add setup_tier2_clone.ps1 bootstrap script with -WhatIf support 2026-06-16 19:47:06 -04:00
ed 796da0de60 feat(tier2): add run_track.py CLI with init/status/report modes + git fetch/switch 2026-06-16 19:27:08 -04:00
ed 9964ad3b3e test(tier2): add 12 slash command + agent + config spec contract tests 2026-06-16 19:23:10 -04:00
ed 154a370728 feat(tier2): add opencode.json.fragment with deny rules + path allowlist 2026-06-16 19:19:37 -04:00
ed 016381c4ff feat(tier2): create tier2-autonomous agent profile template 2026-06-16 19:18:36 -04:00
ed 7380e23bc0 feat(tier2): create tier-2-auto-execute slash command template 2026-06-16 19:17:41 -04:00
ed 73ab2778ca feat(report): implement write_failure_report + 8 tests, 100% coverage 2026-06-16 19:13:30 -04:00
ed 5ca8444f35 test(report): add report writer tests (red, opt-in via TIER2_SANDBOX_TESTS=1) 2026-06-16 19:10:22 -04:00
ed 2dbfaeb60e test(failcount): add 13 unit tests + 6 coverage tests; 100% coverage achieved 2026-06-16 19:06:09 -04:00
ed 190766fe03 feat(failcount): add default failcount.toml thresholds 2026-06-16 19:01:31 -04:00
ed fc92e1aa74 feat(failcount): add FailcountState + FailcountConfig dataclasses + all stub functions 2026-06-16 18:59:38 -04:00
ed e646067a8a test(failcount): add test_initial_state_zero (red) 2026-06-16 18:58:00 -04:00
ed 9f2ff29c2e feat(tier2): create scripts/tier2/ package 2026-06-16 18:57:09 -04:00
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 2551ff18c7 no t-shirt nonsense (agents.md) 2026-06-16 18:47:50 -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 88e44d1c0e docs(report): add session report (audit + migration plan + tech-rot prevention) 2026-06-16 10:48:15 -04:00
ed b90d4bdd4e feat(scripts): add --ci alias for --strict + CI-gate doc updates 2026-06-16 10:40:21 -04:00
ed ce85c379ad docs(agents): add Convention Enforcement section at the top (4 mechanisms) 2026-06-16 10:37:35 -04:00
ed 734840375f docs(guidelines): add AI Agent Obligations section with 4 enforcement audit scripts 2026-06-16 10:35:55 -04:00
ed ef1b0a1c6d docs(styleguide): add AI Agent Checklist section against tech rot 2026-06-16 10:29:26 -04:00
ed 4a55a14fc0 conductor: register result_migration_20260616 in tracks.md (umbrella + 5 sub-tracks) 2026-06-16 10:26:10 -04:00
ed 4cf885da90 docs(workflow+agents): add HARD BAN on day estimates + Tier 1 Track Initialization Rules section 2026-06-16 10:16:49 -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 4521a7df96 feat(scripts): add --summary and --by-size modes to exception_handling audit 2026-06-16 09:41:20 -04:00
ed 01fbd62a3f conductor(track): mark exception_handling_audit_20260616 as completed 2026-06-16 09:10:14 -04:00
ed 4b8363bd71 conductor: register exception_handling_audit_20260616 in tracks.md 2026-06-16 09:09:34 -04:00
ed 3c59e24162 docs(report): add exception handling audit report (211 violations across 42 files) 2026-06-16 09:07:42 -04:00