spring-projects / spring-projects/spring-ai
com.fasterxml.jackson.databind.JsonMappingException: Unexpected end-of-input: was expecting closing quote for a string value at [Source: REDACTED (`StreamReadFeature.INCLUDE_SOURCE_IN_LOCATION` disabled); line: 43, column: 43]
Nobody has claimed this yet.
- Dominant language
- Java
- Stars
- 9.5k
- Forks
- 2.9k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 6
Description
调用gpt4.1报错，大模型输出的结果被截断导致反序列化失败，怀疑是completionTokens超过了1024，但我并没有显式设置token任何长度限制的参数。
是spring ai本身对模型输出长度做了限制吗？请问怎么解决？
Here is the English translation:
Calling GPT-4.1 results in an error. The output from the large model is being truncated, causing deserialization to fail. I suspect that the completionTokens exceeded 1024, but I did not explicitly set any token length limit parameters.
Does Spring AI itself impose a limit on the output length of the model? How can I resolve this issue?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No repository files, tests, or entry points are identified. Start by reproducing the GPT-4.1 call and tracing the response through Spring AI to Jackson deserialization, while checking the configured output-token limits. Done means identifying whether Spring AI truncates the response and documenting or fixing the responsible limit.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- java, spring
- Domain
- ai, backend
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100