c0a6adf9ed
leo: model diversity + calibrated review prompts
...
- Domain review → GPT-4o (OpenRouter), Leo STANDARD → Sonnet (OpenRouter),
Leo DEEP → Opus (Claude Max). Two model families = no correlated blind spots.
- Opus reserved for DEEP eval only — protects rate limit for overnight research.
- Review prompts calibrated: require per-criterion evidence, blocking-vs-observation
verdict rules. Moved from 100% rubber-stamp approval to 12% pass rate.
- OpenRouter failures classified as openrouter_failed (not rate_limited) to avoid
spurious 15-min Opus backoff.
- merge.py: pre-check PR state before merge API call (prevents 405 on re-merge).
Pentagon-Agent: Leo <294C3CA1-0205-4668-82FA-B984D54F48AD>
2026-03-13 17:10:30 +00:00
ff5162d5ba
ganymede: extract lib/domains.py — single domain→agent mapping
...
CI / lint-and-test (pull_request) Has been cancelled
- What: Unified DOMAIN_AGENT_MAP, VALID_DOMAINS, agent_for_domain(),
detect_domain_from_diff(), detect_domain_from_branch() into lib/domains.py.
Removed duplicated mappings from evaluate.py and merge.py. VALID_DOMAINS in
validate.py now derives from DOMAIN_AGENT_MAP.keys() (single source of truth).
- Why: Phase 3 structural refactor. Domain mapping was duplicated across evaluate.py
(DOMAIN_AGENT_MAP) and merge.py (agent_domain dict). Adding a domain required
editing 3 files; now it requires editing 1.
- Connections: evaluate.py uses agent_for_domain() + detect_domain_from_diff(),
merge.py uses detect_domain_from_branch(), validate.py uses VALID_DOMAINS.
Pentagon-Agent: Ganymede <F99EBFA6-547B-4096-BEEA-1D59C3E4028A>
2026-03-13 15:33:18 +00:00
9d69629893
ganymede: extract lib/forgejo.py — single Forgejo API client
...
CI / lint-and-test (pull_request) Has been cancelled
- What: Unified forgejo_api(), get_pr_diff(), get_agent_token(), repo_path()
into lib/forgejo.py. Removed 3 duplicate _forgejo_api functions (evaluate.py,
merge.py, validate.py), 2 duplicate _get_pr_diff functions (evaluate.py,
validate.py), and 1 _agent_token function (evaluate.py).
- Why: Phase 3 structural refactor. Single source of truth for all Forgejo HTTP
calls. Eliminates ~90 lines of duplicated code across 3 modules.
- Connections: All hardcoded repo paths now use repo_path() helper. Consumer
modules no longer reference config.FORGEJO_URL/OWNER/REPO/TOKEN_FILE directly.
Pentagon-Agent: Ganymede <F99EBFA6-547B-4096-BEEA-1D59C3E4028A>
2026-03-13 15:29:34 +00:00
a7251d7529
ganymede: add dev infrastructure — pyproject.toml, CI, deploy script
...
CI / lint-and-test (pull_request) Has been cancelled
Phase 2 of pipeline refactoring:
- pyproject.toml: Python >=3.11, aiohttp dep, dev extras (pytest,
pytest-asyncio, ruff). Ruff configured with sane defaults + ignore
rules for existing code patterns (implicit Optional, timezone.utc).
- .forgejo/workflows/ci.yml: Forgejo Actions CI — syntax check, ruff
lint, ruff format, pytest on every PR and push to main.
- deploy.sh: Pull + venv update + syntax check + optional restart.
Replaces ad-hoc scp workflow.
- tests/conftest.py: Shared fixture for in-memory SQLite with full
schema. Ready for Phase 4 test suite.
- .gitignore: Added venv, pytest cache, coverage, build artifacts.
- Ruff auto-fixes: import sorting, unused imports removed across all
modules. All files pass ruff check + ruff format.
Pentagon-Agent: Ganymede <F99EBFA6-547B-4096-BEEA-1D59C3E4028A>
2026-03-13 14:24:27 +00:00
799249d470
Initial commit: Pipeline v2 daemon + infrastructure docs
...
- teleo-pipeline.py: async daemon with 4 stage loops (ingest/validate/evaluate/merge)
- lib/: config, db, evaluate, validate, merge, breaker, costs, health, log modules
- INFRASTRUCTURE.md: comprehensive deep-dive for onboarding
- teleo-pipeline.service: systemd unit file
Pentagon-Agent: Leo <294C3CA1-0205-4668-82FA-B984D54F48AD>
2026-03-12 14:11:18 +00:00
