Workflow Debugging and Monitoring
Use the validation checklist, node traces, and run metrics to locate issues
Workflow issues fall into configuration issues, data flow issues, and runtime issues. First check the checklist, then debug run, and finally inspect node traces and service logs.
Configuration Validation
The Checklist reports: unselected models, tools, or knowledge bases, inputs/outputs without a source, nonexistent variable references, incomplete conditional branches, empty code or templates, iterations/loops missing start or processing nodes, and missing output nodes.
Debug Runs
Select Debug Run and fill in the inputs. Debug runs use the draft and do not change the published version. The run drawer's Details shows inputs, outputs, and errors; Trace shows each node's status, inputs, outputs, Tokens, duration, and retry count.
Run Status
| Status | Meaning |
|---|---|
pending | Created, waiting for execution |
running | Executing |
success | All flows completed successfully |
failed | A node or the runtime failed |
cancelled | Cancelled by the user |
timeout | Reached the runtime limit |
skipped | Skipped by a condition or loop |
Monitoring Metrics
The workflow Monitoring page shows total runs, success rate, average duration, failure count, status distribution, and run trends over 7d or 30d. Run logs support filtering by status, time, and full run ID.
Troubleshooting Order
- Check whether the input variables exist and have the correct types.
- Look at the first failed node, not just the final error.
- For LLMs, check model authorization, prompt, and Tokens; for HTTP, check the URL, headers, timeout, and response path; for code, check package versions, resource limits, and artifact paths.
- For knowledge bases, check whether documents finished processing, whether embedding dimensions match, and whether the retrieval service is available.
- If it is a published app, confirm the published version rather than the draft editor.
How is this guide?