Kimi Code @moonshot-ai/kimi-code@0.24.1

### 补丁更新 - [#1678](https://github.com/MoonshotAI/kimi-code/pull/1678) [`ec1c974`](https://github.com/MoonshotAI/kimi-code/commit/ec1c9748c816d152bf06af2456e82ac35786bba9) Thanks [@chengluyu](https://github.com/chengluyu)! - 在步骤中断事件中，保留目标完成摘要，并显示不带内部错误码前缀的未类型化 LLM 错误。 - [#1688](https://github.com/MoonshotAI/kimi-code/pull/1688) [`94c0ef8`](https://github.com/MoonshotAI/kimi-code/commit/94c0ef89d29ea8532be02828201328fa1281273c) Thanks [@sailist](https://github.com/sailist)! - 修复会话启动后模型提供商变为就绪状态时，内置工具不可用的问题。 - [#1684](https://github.com/MoonshotAI/kimi-code/pull/1684) [`e417ee7`](https://github.com/MoonshotAI/kimi-code/commit/e417ee7c2c282f00113dc0e4f4514ca5018b76c9) Thanks [@RealKai42](https://github.com/RealKai42)! - 修复当保留的思考历史包含空推理步骤时，Kimi 会话卡死的问题。 - [#1673](https://github.com/MoonshotAI/kimi-code/pull/1673) [`0f64b4d`](https://github.com/MoonshotAI/kimi-code/commit/0f64b4dcc4f2d295d0039b176d96d8003cb49991) Thanks [@wbxl2000](https://github.com/wbxl2000)! - Web 端：使思考级别处理与 CLI 保持一致：按原样提交所选级别而非静默降级，未选择时固定模型的目录默认值，切换模型时预选择目标模型的默认值，并将显式选择持久化为守护进程级默认值，以便新会话继承这些设置。 - [#1689](https://github.com/MoonshotAI/kimi-code/pull/1689) [`ab22a2a`](https://github.com/MoonshotAI/kimi-code/commit/ab22a2adf0ca17cbb94f1abdab334ebc58814e8d) Thanks [@wbxl2000](https://github.com/wbxl2000)! - Web 端：在模型标签中仅显示级别名称（例如 Max），而非“thinking: max”。 - [#1625](https://github.com/MoonshotAI/kimi-code/pull/1625) [`d158e0a`](https://github.com/MoonshotAI/kimi-code/commit/d158e0a7ac4e432046d56787263dd2dbac40285e) Thanks [@RealKai42](https://github.com/RealKai42)! - 修复思考力度路由逻辑：非 Kimi 提供商保留配置值以供上游验证，Kimi 模型则验证运行时选择，在模型解析期间安全回退，并将生效的力度同步回客户端。

### Patch Changes - [#1678](https://github.com/MoonshotAI/kimi-code/pull/1678) [`ec1c974`](https://github.com/MoonshotAI/kimi-code/commit/ec1c9748c816d152bf06af2456e82ac35786bba9) Thanks [@chengluyu](https://github.com/chengluyu)! - Preserve goal completion summaries and show untyped LLM errors without an internal error-code prefix in step interruption events. - [#1688](https://github.com/MoonshotAI/kimi-code/pull/1688) [`94c0ef8`](https://github.com/MoonshotAI/kimi-code/commit/94c0ef89d29ea8532be02828201328fa1281273c) Thanks [@sailist](https://github.com/sailist)! - Fix built-in tools being unavailable when the model provider becomes ready after the session starts. - [#1684](https://github.com/MoonshotAI/kimi-code/pull/1684) [`e417ee7`](https://github.com/MoonshotAI/kimi-code/commit/e417ee7c2c282f00113dc0e4f4514ca5018b76c9) Thanks [@RealKai42](https://github.com/RealKai42)! - Fix Kimi sessions getting stuck when preserved-thinking history contains an empty reasoning step. - [#1673](https://github.com/MoonshotAI/kimi-code/pull/1673) [`0f64b4d`](https://github.com/MoonshotAI/kimi-code/commit/0f64b4dcc4f2d295d0039b176d96d8003cb49991) Thanks [@wbxl2000](https://github.com/wbxl2000)! - web: Align thinking-level handling with the CLI: submit the selected level verbatim instead of silently downgrading it, pin the model's catalog default when nothing was chosen, pre-select the target model's default on model switches, and persist explicit picks as the daemon-wide default so new sessions inherit them. - [#1689](https://github.com/MoonshotAI/kimi-code/pull/1689) [`ab22a2a`](https://github.com/MoonshotAI/kimi-code/commit/ab22a2adf0ca17cbb94f1abdab334ebc58814e8d) Thanks [@wbxl2000](https://github.com/wbxl2000)! - web: Show just the level name (e.g. Max) in the model pill instead of "thinking: max". - [#1625](https://github.com/MoonshotAI/kimi-code/pull/1625) [`d158e0a`](https://github.com/MoonshotAI/kimi-code/commit/d158e0a7ac4e432046d56787263dd2dbac40285e) Thanks [@RealKai42](https://github.com/RealKai42)! - Fix Thinking effort routing so non-Kimi providers preserve configured values for upstream validation, while Kimi models validate runtime selections, fall back safely during model resolution, and synchronize the effective effort back to clients.

Kimi Code @moonshot-ai/[email protected]