Muawiya-contact opened a new issue, #360:
URL: https://github.com/apache/hugegraph-ai/issues/360

   ### Bug Type (问题类型)
   
   None
   
   ### Before submit
   
   - [x] I had searched in the 
[issues](https://github.com/apache/hugegraph-ai/issues) and found no similar 
issues.
   
   ### Environment (环境信息)
   
   - repo: apache/hugegraph-ai
   - module: hugegraph-llm
   - Python: 3.10
   - OS: Windows
   
   ### Expected & Actual behavior (期望与实际表现)
   
   ## Expected Behavior
   When `pipeline` is `None`, `schedule_stream_flow` should build the flow 
once, run it once, and stream the result once.
   
   ## Actual Behavior
   The code falls through into the second `try` block after the first branch 
finishes, so the flow can be prepared and run again.
   
   
   ## Why This Matters
   This can cause duplicate execution, extra LLM calls, and wrong streaming 
behavior.
   
   ### Vertex/Edge example (问题点 / 边数据举例)
   
   ```javascript
   1. Call `schedule_stream_flow`.
   2. Make `manager.fetch()` return `None`.
   3. Observe the flow is executed once in the `if pipeline is None` branch and 
then again in the later `try` block.
   ```
   
   ### Schema [VertexLabel, EdgeLabel, IndexLabel] (元数据结构)
   
   ```javascript
   
   ```


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to