continuedev / continuedev/continue
GPT 5.5 - reoccurring 'message' was provided without its required 'reasoning' item
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 36k
- Forks
- 5.4k
- PR merge metrics
- No merged PRs in 30d
Description
Before submitting your bug report
- I've tried using the "Ask AI" feature on the Continue docs site to see if the docs have an answer
- I'm not able to find a related conversation on GitHub discussions that reports the same bug
- I'm not able to find an open issue that reports the same bug
- I've seen the troubleshooting guide on the Continue Docs
Relevant environment info
- OS: WSL 2
- Continue version: 1.2.22
- IDE version: 1.124.2 (Visual Studio Code)
- Model: GPT 5.5 (Open AI apki key)
- config:
- name: GPT-5.5
provider: openai
model: gpt-5.5
apiKey: sk-proj-
defaultCompletionOptions:
promptCaching: true
Description
It's not always, just sometimes but Resubmit last message doesnt' help. After several click GPT 5.5 I guess chooses different approach and the error disappers. I have no problem with Opus 4.6, so it might be model related.
here is error output:
Error handling model response
{"message":"Item 'msg_07ddda73bf133ab6006a2cfd8e30f481a3b33726a611ef9119' of type 'message' was provided without its required 'reasoning' item: 'rs_07ddda73bf133ab6006a2cfd8bb24881a3b60b5630fce8f932'.","type":"invalid_request_error","param":"input","code":null}
To reproduce
No response
Log output
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
Start from the reported model-response error and trace the GPT-5.5 request and response-handling path in the Continue codebase; the issue does not name a file, test, or reproduction. Compare the failing OpenAI interaction with the working Opus 4.6 case, and consider the issue addressed when the missing reasoning-item error is prevented or reliably handled.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- ai
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100