spring-projects / spring-projects/spring-ai

Cannot access llm provider error message from ChatResponse (Stream Mode)

Open
#5,244 1 comment 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

status: waiting-for-triage
Dominant language
Java
Stars
9.5k
Forks
2.9k
Avg merge
1d 7h
Merged PRs (30d)
6

Description

Bug description
When the LLM provider returns an error response, the error message is not accessible from ChatResponse. (Stream Mode)
For example:

data: {"error": "This model's maximum context length is 163840 tokens. However, your request has 215558 input tokens. Please reduce the length of the input messages. None"}

Environment
Spring AI 1.1.2

Steps to reproduce
Simply make the context length exceed the limitations of the large language model.

Expected behavior
The error message from the provider should be exposed through ChatResponse (or a related error field) so that clients can handle it programmatically. Or throw a exception.

Minimal Complete Reproducible example
Simply make the context length exceed the limitations of the large language model.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing how ChatResponse represents provider errors in stream mode, then follow the streaming response handling for the error payload shown in the issue. Reproduce the oversized-context request and verify that the provider message is exposed through ChatResponse or surfaced as an exception.

Written by the indexing model from the issue text.

Assessment

Tech stack
java, spring
Domain
api, backend
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.