- Add COMPOSE_FILE=docker-compose.yml to tests, benchmark, and sdk-preview to prevent loading overrides in CI
- Add target: development to tests/benchmark builds, target: production to pr-scan/nightly builds
- Bump actions/checkout v4→v6, docker/build-push-action v4/v5→v6, actions/upload-artifact v4→v6, actions/github-script v7→v8
- Pin composer images to 2.8 in linter and static-analysis workflows
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The list_issues tool's 'since' parameter already filters by updated_at,
which captures both newly created issues AND recently commented issues in
a single query. Removed redundant second query.
- Include issues updated in last 24 hours (with new comments), not just newly created
- Add non-English content check: detect and request English translation respectfully
- Add multi-topic detection: ask users to split issues with multiple unrelated topics
- Improve spam detection with clear guidance
- Enhanced with empathetic approach for language and topic guidance
- Add parameter hints for list_label tool usage
- Clarify good first issue label application criteria
- Update summary message to reflect new triage scope
- Add github tool configuration with 'default' and 'labels' toolsets
- The labels toolset was not enabled by default, causing the agent
to fall back to bash commands like 'gh label list'
- Now list_label MCP tool will be available to the agent
The correct tool name in GitHub MCP server is 'list_label' (singular), not 'list_labels' (plural). This was causing the agent to fall back to bash commands like 'gh label list' instead of using the proper MCP tool.
- Add target: "*" to safe-outputs configuration for add-labels and add-comment
- This allows the workflow to apply comments and labels to multiple issues
when running in scheduled/manual trigger mode (batch processing)
- Previously, safe-outputs jobs were skipped because they required
github.event.issue.number which only exists in event-triggered runs
- With target: "*", the workflow now reads issue numbers from the agent
output and applies changes to each issue individually
