BREAKING CHANGES:
- Remove review mode entirely - now handled via slash commands in agent mode
- Remove all deprecated backward compatibility fields (mode, anthropic_model, override_prompt, direct_prompt)
- Simplify mode detection: prompt overrides everything, then @claude mentions trigger tag mode, default is agent mode
- Remove slash command resolution from GitHub Action - Claude Code handles natively
- Remove variable substitution - prompts passed through as-is
Architecture changes:
- Only two modes now: tag (for @claude mentions) and agent (everything else)
- Agent mode is the default for all events including PRs
- Users configure behavior via prompts/slash commands (e.g. /review)
- GitHub Action is now a thin wrapper that passes prompts to Claude Code
- Mode names changed: 'experimental-review' → removed entirely
This aligns with the philosophy that the GitHub Action should do minimal work and delegate to Claude Code for all intelligent behavior.
- introduced a new input parameter `label_trigger` in `action.yml` to allow triggering actions based on specific labels applied to issues.
- Enhanced the context preparation and event handling in the code to support the new labled event.
* fix: use direct assignee field
* fix: correct assignee trigger test to handle different assignee properly
The test was failing because the mockIssueAssignedContext was missing the
top-level assignee field that the trigger validation logic checks. Added
the missing assignee field to the mock context and updated the test to
properly override both the top-level assignee and issue.assignee fields
when testing assignment to a different user.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Adjust IssuesAssignedEvent import position (#2)
---------
Co-authored-by: Claude <noreply@anthropic.com>
