yunfengzhou-hub commented on issue #736:
URL: https://github.com/apache/flink-agents/issues/736#issuecomment-4642440756

   Verification completed. All documented features work as described.
   
   **What I verified:**
   - Ollama provider: basic chat, tool calling (auto loop), 
`extract_reasoning=True`
   - Tongyi/DashScope provider: basic chat, tool calling, `extract_reasoning` 
(qwen3-235b-a22b)
   - OpenAI Completions provider: via DashScope compatible API, custom 
`base_url`
   - Custom provider: `BaseChatModelConnection` + `BaseChatModelSetup` 
subclassing, `ResourceDescriptor(clazz="module.ClassName")`
   - PyFlink MiniCluster submission: `from_datastream`, `key_selector`, 
`add_python_file()`, `python.pythonpath` configuration
   - Cross-language wrapper: Python agent using Java Ollama ChatModel via 
`JAVA_WRAPPER_CONNECTION` / `JAVA_WRAPPER_SETUP`
   - Java E2E: `@ChatModelConnection` + `@ChatModelSetup` annotations, embedded 
Flink MiniCluster
   - Source code review: Anthropic, Amazon Bedrock, Azure AI, Azure OpenAI (I 
don't have these API keys/resources)
   
   **Issues found:** None.


-- 
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