3 Commits

Include renames

Author	SHA1	Message	Date
usernameandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>	bfe05ef18a	feat(ci): add mypy, radon, and deptry to CI pipeline ... Add mypy strict type checking, radon cyclomatic complexity analysis, and deptry unused dependency detection. Fix type annotations in eval-coverage.py and release.py to pass strict mypy checks. Resolves 4 agent-readiness signals: type_check, strict_typing, cyclomatic_complexity, unused_dependencies_detection. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>	2026-07-29 17:52:28 -04:00
usernameandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>	476d7e11b0	feat(ci): add linting, formatting, coverage, and security configs ... Add ruff linter/formatter with pre-commit hooks, pytest-cov with 60% coverage threshold, CODEOWNERS, Dependabot for pip/GHA updates, and .env.example. Auto-fix existing ruff violations across eval_runner/ and scripts/. 10 agent-readiness criteria resolved: lint_config, formatter, pre_commit_hooks, naming_consistency, dead_code_detection, test_coverage_thresholds, test_performance_tracking, codeowners, dependency_update_automation, env_template. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>	2026-07-29 17:43:41 -04:00
3 people	0a80bda800	feat: add release-grade repeated and rubric-based skill evaluation (#136) ... Add release evaluation layer on top of deterministic paired execution: - schemas/release-eval-v1.schema.json: release report schema with freeze snapshot, per-case trial aggregation, rubric graders, blinded pairwise comparison, calibration tracking, and PASS/CONDITIONAL/HOLD/BLOCK outcomes - eval_runner/release.py: core module for multi-trial aggregation, versioned rubric graders with abstain/insufficient-evidence, pairwise planning with position randomization and order-reversal testing, calibration records, and release decision computation - eval_runner/tests/test_release.py: 34 tests covering all acceptance criteria - schemas/evals-v1.schema.json: optional case_set field (dev/regression/release) - eval_runner/models.py: case_set on EvalCase - eval_runner/runner.py: load case_set from manifest - .github/workflows/skill-eval.yml: run release tests in CI Gate semantics: hard invariants (privacy, auth, destructive) tolerate zero violations and cannot be averaged away. Missing evidence produces HOLD, not PASS. Uncalibrated judge results are advisory only. Closes #106 Co-authored-by: magnus919 <magnus919>	2026-07-24 23:26:07 -04:00