MoonshotAI / MoonshotAI/kimi-cli
在使用provider type:"openai_legacy"的模型时，支持在配置文件里指定采样参数和模型特有的extra_body。 || When using a model with provider type: "openai_legacy", it is supported to specify sampling parameters and model-specific extra_body in the configuration file.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.4k
- Forks
- 1.3k
- Avg merge
- 9h 47m
- Merged PRs (30d)
- 2
Description
What feature would you like to see?
config.toml支持指定采样参数和模型特有的extra_body。
[providers.providername.extra_generation_kwargs]
[标准的采样参数]
[providers.providername.extra_generation_kwargs.extra_body]
模型特有的extra_body
Additional information
No response
What feature would you like to see?
config.toml supports specifying sampling parameters and model-specific extra_body.
[providers.providername.extra_generation_kwargs]
[Standard sampling parameters]
[providers.providername.extra_generation_kwargs.extra_body]
[Model-specific extra_body] (such as preserve_thinking of qwen3.6 series)
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 with the config.toml provider configuration, especially providers.providername.extra_generation_kwargs and its extra_body section, and trace how openai_legacy settings are loaded. Confirm that standard sampling parameters and model-specific extra_body values such as preserve_thinking reach the provider configuration, then verify the relevant configuration and provider tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- cli
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 58/100