Skip to content

Instantly share code, notes, and snippets.

@lmyslinski

lmyslinski/gist:21a151a76ee01313bbd81efe20621df4

Created January 14, 2026 10:57
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save lmyslinski/21a151a76ee01313bbd81efe20621df4 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save lmyslinski/21a151a76ee01313bbd81efe20621df4 to your computer and use it in GitHub Desktop.
Download ZIP
Custom skills tasks
Raw
gistfile1.txt
1. Setup mock workflow server - it needs to receive a call from the reasoning api, do some sleep work/processing and return a randomized(?) response with expected schema
2. Prepare DB for custom skills storage - we need to store workflow references, config and any additional fields that might be required
Q: Should we use json here? It makes sense since the workflow config is likely to be highly customizable
Q: Should we explore using langgraph here?
3. Implement workflow API calling and pausing the skill execution
4. Implement resuming the workflow from the workflow server -> reasoning service API call
5. Implement long-polling/some sync mechanism for status updates from the workflow engine
Q: Could we use Redis as a store for the workflow execution state? The workflow api could just dump the state there on updates and we can query it whenever we need by workflow id - Alternative: Pub/sub?
6. Reconcile in the reasoning agent based on the response from workflow and existing memory contents
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment