Aias00 opened a new issue, #1008:
URL: https://github.com/apache/rocketmq-dashboard/issues/1008

   ## Problem
   
   `OpenAiCompatibleLlmClient` reads provider responses without any size limit:
   
   - `complete` and `listModels` use `HttpResponse.BodyHandlers.ofString()`.
   - A failed streaming request calls `InputStream.readAllBytes()`.
   - SSE parsing accumulates every `data:` line for an event and has no 
per-event or cumulative response budget.
   
   A malformed or unexpectedly large upstream response can therefore allocate 
excessive memory and delay the Studio server.
   
   ## Expected behavior
   
   - Apply documented limits to regular completion/model responses, streaming 
error bodies, individual SSE events, and the cumulative streamed response.
   - Stop reading as soon as a limit is exceeded and return a structured 
`llm.provider.response_too_large` error.
   - Keep normal OpenAI-compatible completion and SSE behavior unchanged within 
the limits.
   
   ## Scope
   
   Track 3 / AI Native. This complements, but does not duplicate, the timeout, 
concurrency, and CLI process hardening in #940.


-- 
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