CRITICAL FIX: Bot was triggering itself causing 10+ duplicate runs
Problem:
- When bot posts comments containing @codebot (e.g., help responses, PR reviews)
- Workflows trigger on those bot comments
- Bot responds again with @codebot mention
- Infinite loop → 10+ duplicate workflow runs → excessive API costs
Solution:
- Added github.event.comment.user.login != 'Bartender' to all workflow conditions
- Prevents bot from reacting to its own comments
- Bot username 'Bartender' is now hardcoded in workflows
Changes:
- .gitea/workflows/ai-comment-reply.yml: Added bot username check
- .gitea/workflows/ai-chat.yml: Added bot username check
- .gitea/workflows/ai-issue-triage.yml: Added bot username check
- CLAUDE.md: Documented bot self-trigger prevention and username update instructions
- README.md: Added Step 3 to bot customization with critical warning
Impact:
- Eliminates infinite loop scenarios
- Prevents excessive API costs from duplicate runs
- Workflows only trigger on human user comments
Note: If bot username changes from 'Bartender', all three workflow files must be updated.
Implements PR changelog generator that analyzes diffs and generates
Keep a Changelog format entries ready for CHANGELOG.md.
Features:
- Generates structured changelog entries (Added/Changed/Fixed/etc.)
- Automatically detects breaking changes
- Includes technical details (files, LOC, components)
- User-focused language filtering out noise
- Ready to copy-paste into CHANGELOG.md
Implementation:
- Added changelog.md prompt template with Keep a Changelog format
- Implemented _handle_changelog_command() in PRAgent
- Added _format_changelog() for markdown formatting
- Updated PRAgent.can_handle() to route changelog commands
- Added 'changelog' to config.yml commands list
Workflow Safety (prevents duplicate runs):
- Added '@codebot changelog' to ai-comment-reply.yml conditions
- Excluded from ai-chat.yml to prevent duplication
- Only triggers on PR comments (not issues)
- Manual command only (no automatic triggering)
Testing:
- 9 comprehensive tests in TestChangelogGeneration class
- Tests command detection, formatting, config validation
- Verifies prompt formatting and Keep a Changelog structure
Documentation:
- Updated README.md with changelog command and examples
- Added detailed implementation guide in CLAUDE.md
- Included example output and use cases
Related: Milestone 2 feature - PR changelog generation for release notes
Critical fix for workflow routing that was causing 3x duplication on every
@codebot mention. All three workflows (ai-chat, ai-comment-reply, ai-issue-triage)
were triggering simultaneously.
Changes:
- ai-issue-triage.yml: Only runs on '@codebot triage' (unchanged, already specific)
- ai-comment-reply.yml: Only runs on specific commands (help, explain, suggest, etc)
- ai-chat.yml: Only runs on free-form questions (excludes all specific commands)
Workflow routing logic:
1. '@codebot triage' → ai-issue-triage.yml ONLY
2. '@codebot <command>' → ai-comment-reply.yml ONLY
3. '@codebot <question>' → ai-chat.yml ONLY (fallback)
This prevents the massive duplication issue where every @codebot mention
triggered all three workflows simultaneously, causing 10+ redundant runs.
Updated documentation in CLAUDE.md with workflow routing architecture.
- Replace inline toJSON() with environment variables
- Use Python to parse JSON and dispatch events properly
- Avoid bash syntax errors with parentheses in JSON
- Maintain same functionality for PR vs issue comment handling
Fixes: /var/run/act/workflow/4: line 25: syntax error near unexpected token
- Add review-again command to trigger PR review without new commits
- Implement review comparison logic to show resolved/new/changed issues
- Update workflow to handle PR comments via dispatcher
- Add comprehensive help documentation in README and CLAUDE.md
- Show diff from previous review with resolved/new issues count
- Update PR labels based on new severity assessment
- Support re-evaluation after config changes or false positive clarification
Key features:
- ✅ Shows diff from previous review (resolved/new/changed issues)
- 🏷️ Updates labels based on new severity
- ⚡ No need for empty commits to trigger review
- 🔧 Respects latest .ai-review.yml configuration
Closes feature request for manual PR re-review capability
Implements help command that shows all available bot commands with examples and categories.
Users can now type '@codebot help' to see complete command list without reading docs.
PRAgent was trying to use dict as hashable key, causing TypeError.
Added _get_label_config() helper to support both old string and new
dict format, matching the fix in IssueAgent.
