Commit Graph
4 Commits
Author SHA1 Message Date
windyboy dfa18ed405 refactor: consolidate skill docs, add anti-drift tests, and apply audit fixes
DLO-13: Restructure vlm-library-workflow skill as safety contract layer.
- Rewrite SKILL.md (69 lines): safety contract, execution threshold semantics,
  six-step high-risk loop, decision rules, phase skeleton
- Delete redundant references (cli-reference, workflow, command-recipes, dev-guide)
- Add triage.md (failure mapping + preflight) and dev-map.md (module→test mapping)
- Add tests/test_docs_consistency.py: 78 parametrized tests verifying documented
  vlm commands exist in CLI registry
- Add CSV path mismatch test to test_plan_review.py (4th safety gate path)
- Delete vlm-expert.skill (Gemini package, 7 months stale) and README Gemini section

DLO-2 audit fixes: rate limiter injection, symmetric quarantine categories,
review-plan safety gates, parser improvements, planner validation.

CLI modularization: commands/ directory with one module per command group.
2026-09-25 13:50:09 +08:00
6f0df5a774 release: v0.2.0 repository hygiene, CI, and docs sync
Stop tracking personal workflow artifacts at repo root, add CI and MIT
license, align README and agent skills with artifacts/ defaults, and
enable Ruff in dev/CI so releases are verifiable without local-only runs.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-01 15:32:03 +08:00
79797644e1 chore: trim dead code, modularize CLI, and archive stale docs
Extract review-plan, report, quarantine, state, and config handlers into
commands/ with shared cli_helpers; remove unused exceptions and duplicate
plan summary wrappers. Archive superseded review markdown, sync docs to
517-test baseline, and fix empty series titles when only a quality tag remains.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-21 10:36:03 +08:00
windyboyandCursor 5f0b531269 Improve plan review UX with enriched rows, TUI filters, and execute gate.
Make review-plan easier to act on: Chinese risk labels, relative paths,
verdict/next-step footer, optional identity/analysis enrichment, grouping,
spot-check sampling, and structure preview. Extend the TUI with filters,
duplicate-group reject, and quality context. Persist review_context on
plan operations and add --require-review for confirmed execute.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-21 09:27:12 +08:00