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
In older versions of Appwrite, the internal ID was the $internalId attribute. However, it has now changed to $sequence so that it can align with the publicly exposed attribute for an auto-incrementing ID.
The problem with this change is that data in the cache still references the old $internalId attribute, which can lead to inconsistencies and errors when accessing cached documents. To resolve this issue, we need to clear the cache for all collections and documents at the beginning of the migration so that the new $sequence attribute is used.
Chirag Aggarwal
Steven Nguyen
Steven Nguyen
Matej Bačo
Veeresh
copilot-swe-agent[bot]
Harsh Mahajan
Jake Barnby
Luke B. Silver