-
Notifications
You must be signed in to change notification settings - Fork 62
Add comprehensive documentation for Slack/Linear interrupt system #1175
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add comprehensive documentation for Slack/Linear interrupt system #1175
Conversation
- Document how real-time interrupts work during agent execution - Explain technical implementation with BaseRunner and TaskTimeline - Include examples for both Slack and Linear workflows - Add best practices and troubleshooting guidance - Update docs.json navigation to include new interrupts page
Codecov ReportAll modified and coverable lines are covered by tests ✅ ✅ All tests successful. No failed tests found. |
docs/capabilities/interrupts.mdx
Outdated
| Interrupt messages are structured as: | ||
|
|
||
| ```json | ||
| { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Let's remove the technical implementation since htese are user-facing docs!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Got it! I'll remove the technical implementation section since these are user-facing docs and update the Linear section with the mention requirements. Making those changes now! 📝
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
✅ Updated the documentation with your feedback!
Changes made:
- Added clear warning that
@codegenmentions are required in Slack channels (but not in DMs) - Added note that Linear responds automatically unless other users are tagged
- Removed technical implementation section to keep it user-focused
- Updated best practices and troubleshooting to emphasize mention requirements
The docs now clearly explain when mentions are needed vs. when Codegen responds automatically. Much more user-friendly! 🎯
- Add clear warning that @codegen mentions are required in Slack channels (not DMs) - Add note that Linear responds automatically unless other users are tagged - Remove technical implementation section for user-facing docs - Update best practices and troubleshooting with mention requirements
This PR adds comprehensive documentation for Codegen's real-time interrupt system that allows users to send follow-up messages while the agent is actively working.
What's Added
New Documentation Page:
/docs/capabilities/interrupts.mdxKey sections covered:
BaseRunner,TaskTimeline, andLangGraphUpdated Navigation
capabilities/interruptsto the docs.json navigation structureTechnical Background
Based on analysis of the
cloudrepo implementation:app/agent_runners/base_runner.py): Handles interrupt detection and routingapp/agents/agent_run/task_timeline.py): Stores interrupt messages in theinterrupt_messagesqueueapp/agents/langgraph_utils/graph.py): Processes interrupts as[INTERRUPT]prefixed messagesapp/agents/langgraph_utils/memory_store.py): Manages interrupt message processing and indexingUser Impact
This documentation will help users understand:
The documentation is positioned in the "Capabilities" section alongside existing wake-up and general capabilities docs.
💻 View my work • 👤 Initiated by
Jay Hack• 💬 Initiated in #ext-notion-codegen • About Codegen