oscerd opened a new pull request, #25050:
URL: https://github.com/apache/camel/pull/25050

   ## Summary
   
   Adds a new MCP tool `camel_runtime_ai_trace` that traces AI-specific 
exchange flow in running Camel applications.
   
   - **AI component detection**: identifies Bedrock, LangChain4j, Docling, 
Textract, OpenAI, KServe, TorchServe, DJL, HuggingFace components in running 
routes
   - **AI header extraction**: captures token usage, model IDs, guardrail 
outcomes, completion reasons, streaming chunk counts from exchange headers
   - **Processor statistics**: filters top processor stats to AI components 
only, showing latency (mean/max/min/last) and exchange counts
   - **Structured summary**: aggregates key AI metrics (token usage, model, 
completion reason, guardrail action) into a summary
   
   Combines data from three existing runtime queries (`get_history`, 
`get_top_processors`, `get_route_structure`) and filters for AI-relevant data.
   
   ## Test plan
   
   - [x] 10 unit tests covering component extraction, header categorization, 
processor stats, scheme parsing, and edge cases
   - [x] All 309 existing MCP server tests pass (no regressions)
   
   _Claude Code on behalf of oscerd_
   
   🤖 Generated with [Claude Code](https://claude.com/claude-code)


-- 
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