MoonshotAI / MoonshotAI/kimi-code
支持为自部署模型配置请求超时时间（request timeout）
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 7.5k
- Forks
- 1.2k
- Avg merge
- 11h 53m
- Merged PRs (30d)
- 350
Description
你希望看到什么功能？
config.toml 中支持配置
[providers.oMLX]
request_timeout_ms = xxx
或
[models."oMLX/qwen3.8-27b"]
request_timeout_ms = xxx
用于控制模型返回超时，避免任务进行一段时间后，上下文变长导致中途开始不可用
补充信息
Kimi Code CLI 是一个很好的开箱即用的工具，但是套餐额度很尴尬，所以会有使用 Kimi Code CLI 连接本地部署的模型做一些简单任务的需求。目前已经适配了 lmstudio 等其他本地部署引擎并且可以正常使用，但是自部署模型在长上下文或复杂推理场景下耗时较长，单次请求经常需要数分钟才能返回。目前 CLI 似乎没有暴露“模型请求超时”的配置项，导致请求容易被内部超时中断，影响正常使用。
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 with config.toml and trace how provider-level and model-level settings are loaded and passed into model requests. Check the existing request timeout handling for self-hosted providers, then verify that either configuration form controls the timeout and that long-running requests are not interrupted prematurely.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- cli
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 68/100