Parameter "todos" must be an array.
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 28k
- Forks
- 3.1k
- Avg merge
- 1d 2h
- Merged PRs (30d)
- 714
Description
What happened?
qwen-code以openai的形式，连接本地部署的Qwen3-coder-flash，运行的时候会报错这个，是模型的问题嘛？
模型是用vllm启动的
docker run --gpus all
--restart=unless-stopped
-p 8000:8000
-v /home/model/:/models
-e TZ=Asia/Shanghai
vllm/vllm-openai:latest
--model /models/Qwen3-Coder-30B-A3B-Instruct
--max_model_len 194512
--served-model-name nsd-qwen3-coder
--api-key sk-ninestar
--gpu_memory_utilization 0.95
--dtype auto
--enable-auto-tool-choice
--tool-call-parser qwen3_coder
--trust-remote-code
What did you expect to happen?
fix bugs
Client information
$ qwen /about
# paste output here
Login information
No response
Anything else we need to know?
No response
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 by reproducing the todos parameter error with the supplied qwen /about context and vLLM Docker command. No source file or test is identified, so trace the CLI's request handling to determine whether the invalid parameter comes from qwen-code or the model server; done means a confirmed cause and a reproducible regression check.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- ai, cli
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100