12 Commits

Author	SHA1	Message	Date
drew	8ed4b96b1a	feat(auto-agents): perf + observability + persistent comment cache ... Folds B1-B4 + C2-C5 from the post-live-test plan into one commit: B1 — npx tsx pre-warm in dispatchers-launcher.sh closes the cold-cache 30s AbortSignal timeout that killed both dispatchers' first cycle. B2 — per-tier worker timeout (IMPLEMENTER_DISPATCHER_WORKER_TIMEOUT_TIER_{N}_SECONDS) lets Tier 1 (qwen-large) and Tier 2 (kimi) get more wallclock than gpt-5-mini; floor 60s. B3 — _rebuild_prompt_from_cached_result skips the full prefetch on tier transitions (worktree-reset puts everything back at the prefetched head_sha, so the prefetch result + det_sections don't change). Saves ~7 min per tier transition on comment-heavy PRs. B4 — git-commit-util.md documents the FORBIDDEN naive recovery pattern (git fetch && git reset --hard) that lost PR #30 attempt 3's real fix in the live test. Two correct paths now spelled out: --force-with-lease=<branch>:<old-remote-sha> or stash+rebase+pop. C2 — _pr_clone._refresh_mirror_with_retry adds one retry on git fetch failure and force-reclones the bare mirror if both attempts fail. Previously a single exit 128 logged WARN and continued with stale data forever. C3 — in-flight turn markers (asterisk suffix on input/output token counts) in the per-turn log when completed=False. The archived turn dict's completed field was already there; the log now surfaces it. Sub-agent timeout archiving was already correct via _archive_subagent_tree. C4 — new module _recent_push_cache.py records per-PR push events (head_sha + timestamp + cycle metadata). Prefetch surfaces in the sentinel under recent_implementer_push (with --field accessor) when the cached push matches the PR's current head_sha within 1h. Prevents the "dispatcher re-cycles right after pushing, worker re-does the same compliance work" failure mode from PR #28 cycle 2 in the live test. C5 (replaces C1) — new module _pr_comments_cache.py wraps _review_fetch.fetch_pr_comments with disk-backed delta-fetch semantics. PR #30's 1340+ comment fetch (which previously took ~30s and hit the 20-page pagination cap) now becomes a 5-10 item delta. Cache is per-PR, shared between reviewer + implementer dispatchers, has 24h staleness bound, kill-switch via IMPLEMENTER_DISPATCHER_COMMENT_CACHE_DISABLE=1. Tests: 1484 passed, 3 skipped (+20 from 49a28b5c). New test files test_pr_comments_cache.py (16 tests) and test_recent_push_cache.py (7 tests); new TestPerTierWorkerTimeout class (4 tests). ISSUES CLOSED: #30 #28 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-05-13 10:25:10 -04:00
drew	132a5a2269	feat(auto-agents): centralise model registry under .opencode/models with session-create model stamp ... Every agent's model assignment now lives in a single-line text file at .opencode/models/<name>.txt; default.txt is the 27-agent catch-all. opencode.json's agent.<name>.model uses {file:./.opencode/models/<name>.txt} interpolation, and tools/_opencode_worker.py reads the same files at session-create to stamp the resolved model on the session record (observability + drift sentinel; OpenCode does NOT propagate session-level model to prompt_async — schema for that is undocumented and deferred to Stage 2). 39 .md frontmatter `model:` lines stripped; the two intentional inheritors (task-implementor, agent-evolution-pool-supervisor) keep their model-less frontmatter. Operator workflow for swapping a model is now: edit .opencode/models/<role>.txt, restart OpenCode so opencode.json's {file:...} re-resolves, run the dispatcher. Live-swap without restart was attempted (override on prompt_async); OpenCode 0.x silently dropped those requests (200 OK, no assistant message) and the prompt_async override was reverted. The session-create override remains for observability + drift detection. End-to-end validation (2026-05-10): dispatch_review.py on PR #25 with default.txt=openai/gpt-5-mini produced a clean REQUEST_CHANGES review in 26 s for ~$0.016; dispatch_implementer.py on PR #30 with tier-qwen-* files remapped to openai/{gpt-5-nano, gpt-5-mini, gpt-5-codex} ran the full implementation-worker → tier-dispatcher → estimator-implementation → tier-qwen-med → task-implementor → git-isolator-util chain in 16 min with model=gpt-5-mini end-to-end. Also documents the printenv VAR form as the only allowed env-read in implementation-worker.md and task-implementor.md (live testing showed the worker burning 2–4 turns on permission-denied trial-and-error trying printf and echo variants). Tests: 21 in tests/auto_agents/test_opencode_worker_models.py (resolver semantics with caplog assertions on every malformed-input path; session-create body shape; prompt_async body never carries model; three repo-level invariants — every {file:...} reference resolves, every .md is wired or in the inheritor allowlist, no .md has a model: frontmatter). 1027 auto_agents tests pass / 3 skipped. Note: .opencode/models/default.txt and the three tier-qwen-*.txt files are committed with their OpenAI swaps in place (gpt-5-mini, gpt-5-nano, gpt-5-mini, gpt-5-codex respectively) because the CleverThis HuggingFace endpoints are paused. Revert with `git diff HEAD~1 -- .opencode/models/*.txt | git apply -R` if/when they come back. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-05-10 17:23:06 -04:00
drew	e247c10219	chore(opencode): reconcile providers and agents with agents/final-working ... Imports the source-of-truth tier selector shape (tier-qwen-small/med/ large, tier-kimi) and the explicit-only variable-propagation contract from agents/final-working, while preserving this branch's deterministic merge_drive.py / conflict_drive.py ownership model and the implementer/reviewer claim-release behavior so LLM workers do not race the host drivers. Rebuilds root opencode.json so host-launched OpenCode sees the same live HF endpoints as the devcontainer, and corrects pipeline-agent model pins to the live default CleverThis-15/Qwen3-6-35B-A3B-GGUF-UD-Q3-K-XL after CleverThis-8 was decommissioned. Drops the stale single tier-qwen selector. Telemetry pricing keys are updated to match the new model pin. Scope is intentionally limited to provider/model routing and agent- definition reconciliation; the Tier 2 deterministic dispatchers and their telemetry land in a separate commit. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-05-06 22:41:41 -04:00
freemo	ce396d2b43	build: reordered agent perms	2026-05-02 14:33:45 -04:00
freemo	9632ea55dd	build: trying new qwen instruct model instead	2026-05-01 20:03:27 -04:00
freemo	bdcc44cb09	build: read and write permissions set seperate edit since read seems to be getting denied as does write	2026-05-01 17:58:29 -04:00
freemo	3a6d42ee79	build: fixed some bad permissions and no longer require prompt to be written to a file for supervisors	2026-05-01 17:45:27 -04:00
freemo	9b34d47371	build: new models	2026-05-01 16:32:39 -04:00
freemo	816c16901b	build: fixed uncensored model	2026-04-30 20:02:13 -04:00
freemo	516c600c0e	build: updated and rename hosted models	2026-04-30 19:47:54 -04:00
freemo	1691def164	build: Moved to using new default qwen instance	2026-04-30 16:12:38 -04:00
freemo	1885990081	build: auto opencode agents rewritten	2026-04-27 12:49:08 -04:00