Commit Graph

8 Commits

Author SHA1 Message Date
98b47fe021 feat(preflight): catch logged-out auth and treat empty result as failure
Some checks failed
CI / test (push) Failing after 14s
CI / test (pull_request) Failing after 13s
ORCH-044 closes two blind spots that let a single de-authenticated agent
stall the shared queue for all projects:

P1 — preflight auth gate. `claude --version` answers even when logged out,
so version-only preflight was blind to auth. Adds a token-free, network-free
check of <AGENT_HOME>/.claude/.credentials.json: missing/unreadable/no-oauth
or an expired `claudeAiOauth.expiresAt` (epoch ms, vs now + skew) => preflight
FAIL; absent expiry => OK (no false positives). Result is cached on the same
preflight_cache_ttl. Post-factum safety net: launcher detects auth markers
("not logged in" / "/login" / "unauthorized" / 401) in the run log and resets
the preflight cache so the next tick re-evaluates auth. Auth failure is a gate,
not a transient — it does not spin the circuit breaker. Emergency toggle
ORCH_PREFLIGHT_CHECK_AUTH=false restores version-only behaviour.

P3 — empty log / no result-JSON => job failed. exit_code==0 with an empty or
JSON-less run log no longer counts as success: a separate result_ok flag gates
stage advance + usage comments, fires a Telegram alert, and routes the job
through the normal transient/permanent failure path (exit_code integrity in
agent_runs preserved).

Scope: P2 (--effort) is intentionally excluded and tracked in ORCH-50.

New settings: ORCH_PREFLIGHT_CHECK_AUTH, ORCH_CLAUDE_CREDENTIALS_PATH,
ORCH_AUTH_EXPIRY_SKEW_SECONDS. Docs updated (INFRA.md, internals.md, CHANGELOG).

Refs: ORCH-044

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-06 08:11:27 +00:00
8fb59cd87f architect(ET): auto-commit from architect run_id=158
All checks were successful
CI / test (push) Successful in 13s
2026-06-06 07:57:07 +00:00
03c3d77cac feat(stage-engine): embed verbatim reviewer/tester findings in rollback task_desc
All checks were successful
CI / test (push) Successful in 12s
CI / test (pull_request) Successful in 11s
При заворотах на development task_desc теперь несёт дословный must-fix текст
(P0/P1 ревьюера, причина FAIL тестера) вместо одной ссылки на файл — developer-
агент видит суть претензий сразу и не повторяет ту же ошибку, экономя retry-
бюджет и токены общего инстанса.

- Новый defensive-модуль src/review_parse.py (never-raise): extract_review_findings
  (P0/P1 из 12-review.md ## Findings), extract_test_failures (фрагмент тела
  13-test-report.md: pytest output / FAIL-строки / Итог), усечение по лимиту.
- Две rollback-ветки stage_engine: встраивают текст + сохраняют ссылку на полный
  файл; graceful-фоллбэк на ссылку-строку при битом/пустом артефакте.
- Последовательность отката, retry-счётчик, поля AdvanceResult, реестр QG_CHECKS
  не менялись.
- Доки: README (Stage Engine / Откаты), CHANGELOG.
- Тесты: tests/test_review_parse.py, test_stage_engine.py::TestRollbackTaskDescEmbedding.

Refs: ORCH-046

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-06-06 04:42:11 +00:00
75fb4069a4 architect(ET): auto-commit from architect run_id=126
All checks were successful
CI / test (push) Successful in 11s
2026-06-05 21:00:57 +00:00
stream
0eff781d13 feat(qg): ORCH-045 — poll check_ci_green with retry to fix CI race (pending->success)
All checks were successful
CI / test (push) Successful in 12s
CI / test (pull_request) Successful in 12s
2026-06-05 19:59:06 +00:00
401bf66fe0 feat(agents): configurable LLM model + effort per-agent and per-project (ORCH-41) (#36)
Some checks failed
CI / test (push) Has been cancelled
2026-06-05 19:45:19 +03:00
8da571de86 feat(plane): unified status-comment format with duration line (ORCH-016) (#34) 2026-06-05 17:50:47 +03:00
Dev Agent
7c68d1d812 docs(orchestrator): adopt enduro doc canon + CLAUDE.md + ADR (ORCH-9)
All checks were successful
CI / test (pull_request) Successful in 9s
2026-06-05 12:33:55 +03:00