MoonshotAI / MoonshotAI/kimi-code
CLI 模式下设置 Secondary Model 时 config.toml 的 key 错误
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 7.5k
- Forks
- 1.2k
- Avg merge
- 11h 53m
- Merged PRs (30d)
- 350
Description
What version of Kimi Code is running?
0.36.1
Which open platform/subscription were you using?
coding plan
Which model were you using?
not relevant
What platform is your computer?
Linux
What issue are you seeing?
在 Kimi Code CLI 模式下,当用户尝试设置 secondary model 时,工具向 config.toml 写入的 key 是 default_model。然而这个 key 似乎不会被正确识别。
对比之下,在 Kimi Code Web 界面设置 secondary model 时,写入 config.toml 的 key 是 model,这是正确的且可以正常工作的。
[secondary_model]
default_effort = "xxx"
default_model = "xxx" <- created by kimi code cli /setting, which is not working.
model = "xxx"
What steps can reproduce the bug?
- 打开终端,使用 Kimi Code CLI
- 执行设置 secondary model 的操作(例如通过交互式配置或命令)
- 检查生成的
config.toml文件 - 发现写入的 key 为
default_model - 重启或重新加载后,secondary model 配置未生效
预期行为
CLI 模式下设置 secondary model 时,应写入 config.toml 的 key 为 model,与 Web 端行为保持一致。
What is the expected behavior?
CLI 模式下设置 secondary model 时,应写入 config.toml 的 key 为 model,与 Web 端行为保持一致。
Additional information
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 locating the CLI interactive configuration or command that writes the [secondary_model] section of config.toml. Compare its key selection with the Web configuration behavior, then verify that setting a secondary model writes model rather than default_model. Reproduce the reported steps and reload the configuration to confirm the secondary model takes effect.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- cli
- Issue type
- Bug
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 72/100