development #115

Merged
lmiranda merged 7 commits from development into main 2026-01-23 17:25:18 +00:00

7 Commits

Author SHA1 Message Date
8a75203251 Merge pull request 'fix: hooks command type conversion + org-level labels' (#114) from fix/hooks-and-labels-v3.2.0 into development
Reviewed-on: #114
2026-01-23 17:24:08 +00:00
da6e81260e fix(hooks): convert ALL hooks to command type with proper prefixes
ALL hooks now use command type (bash scripts) instead of prompt type.
Prompt hooks are unreliable - model ignores instructions.

Changes:
- projman: SessionStart → startup-check.sh with [projman] prefix
- pr-review: SessionStart → startup-check.sh with [pr-review] prefix
- project-hygiene: cleanup.sh now has [project-hygiene] prefix
- doc-guardian: already fixed (notify.sh with [doc-guardian] prefix)
- code-sentinel: already fixed (security-check.sh with [code-sentinel] prefix)

All hook output now guaranteed to have plugin name prefix.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 12:18:40 -05:00
e1f1335655 fix(code-sentinel): replace prompt hook with command hook
Same fix as doc-guardian - prompt hooks unreliable.
Command hook guarantees exact behavior.

- Add security-check.sh that skips config/doc files silently
- Only checks code files for hardcoded secrets
- Outputs with [code-sentinel] prefix

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 12:16:06 -05:00
b017db83a1 feat(gitea): add organization-level label creation
- Add create_org_label() method to gitea_client.py for org-level labels
- Add create_label_smart() to labels.py that auto-detects correct level
- Register both tools in server.py
- Update labels-sync.md to use create_label_smart

Label level detection:
- Organization: Type/*, Priority/*, Complexity/*, Effort/*, Risk/*, Source/*, Agent/*
- Repository: Component/*, Tech/*

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 12:15:14 -05:00
bc136fab7e docs: update CHANGELOG with actual fix for #110
Prompt hook approach didn't work - Claude ignores instructions.
Real fix was switching to command hook type.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 11:51:31 -05:00
6c24bcbb91 fix(doc-guardian): replace prompt hook with command hook
Prompt hooks are unreliable - Claude ignores instructions and generates
verbose analysis despite explicit FORBIDDEN rules. Command hooks guarantee
the exact output we want.

- Add notify.sh script that only outputs for config file changes
- Change hooks.json from prompt type to command type
- Script exits silently for non-config files (no blocking)

Fixes #110

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 11:48:54 -05:00
11a05799d3 docs: sync documentation with codebase
- CLAUDE.md: Update version 3.0.1 → 3.1.2, projman 3.0.0 → 3.1.0, command count 12 → 13
- README.md: Add debug-report/debug-review to projman commands, add DEBUGGING-CHECKLIST.md to docs table
- CANONICAL-PATHS.md: Update version, remove non-existent docs/workflows/, add COMMANDS-CHEATSHEET.md
- projman/README.md: Fix "Three-Agent" → "Four-Agent", update architecture to show symlink
- pr-review/README.md: Add missing setup commands (initial-setup, project-init, project-sync)
- cmdb-assistant/README.md: Add initial-setup.md to architecture
- project-hygiene/README.md: Fix invalid hook event name (task-completed → PostToolUse)
- doc-guardian/plugin.json: Add missing commands field
- code-sentinel/plugin.json: Add missing commands field

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 11:25:14 -05:00