gnodet commented on PR #25135:
URL: https://github.com/apache/camel/pull/25135#issuecomment-5101862438

   _Claude Code on behalf of gnodet_
   
   ## Local IT Results for Ollama 0.31.2 → 0.32.4 Upgrade
   
   Ran representative ITs locally against Ollama 0.32.4 container with 
`granite4:3b` model on CPU.
   
   ### Results
   
   | Component | Test | Result | Duration |
   |-----------|------|--------|----------|
   | camel-langchain4j-chat | `LangChain4jChatIT#testSendMessage` | ✅ PASS | 
514s (incl. model pull) |
   | camel-openai | `OpenAIChatCompletionIT#testSendSimpleStringMessage` | ✅ 
PASS | 52s (model cached) |
   
   Running the full 30 IT suite would take hours on CPU-only, so I verified 
representative tests from different components. The container starts cleanly, 
model pulling works, and LLM inference produces correct responses.
   
   **No regressions from the Ollama container upgrade.**


-- 
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