Kimi Code @moonshot-ai/kimi-code@0.29.0

### 次要更改 - [#1992](https://github.com/MoonshotAI/kimi-code/pull/1992) [`a8f1ca3`](https://github.com/MoonshotAI/kimi-code/commit/a8f1ca3f1016a3e84986f297367e833bc731ac39) Thanks [@RealKai42](https://github.com/RealKai42)! - 支持从 ACP 客户端选择思考强度等级：思考选择器现在会列出当前模型声明的等级（例如 off / low / medium / high），而不仅仅是开/关切换。在你的 ACP 客户端（如 Zed）中使用思考选择器来挑选等级；原有的开/关值仍兼容。 - [#1735](https://github.com/MoonshotAI/kimi-code/pull/1735) [`ce0e3ce`](https://github.com/MoonshotAI/kimi-code/commit/ce0e3ceb04223bdaad8e8931bad46eff561055b6) Thanks [@7Sageer](https://github.com/7Sageer)! - 允许自定义代理文件限制其可委托的子代理类型（仅限 v2 引擎）。 - [#1735](https://github.com/MoonshotAI/kimi-code/pull/1735) [`ce0e3ce`](https://github.com/MoonshotAI/kimi-code/commit/ce0e3ceb04223bdaad8e8931bad46eff561055b6) Thanks [@7Sageer](https://github.com/7Sageer)! - 支持使用带 frontmatter 的 Markdown 文件定义自定义代理，可用作主代理或子代理（仅限 v2 引擎）。 - [#1735](https://github.com/MoonshotAI/kimi-code/pull/1735) [`ce0e3ce`](https://github.com/MoonshotAI/kimi-code/commit/ce0e3ceb04223bdaad8e8931bad46eff561055b6) Thanks [@7Sageer](https://github.com/7Sageer)! - 新增全局工具门控以限制代理可用的工具，并支持按会话覆盖（仅限 v2 引擎）。 - [#2012](https://github.com/MoonshotAI/kimi-code/pull/2012) [`d67a200`](https://github.com/MoonshotAI/kimi-code/commit/d67a2003abf2d8d802dcf24f806e0a811724b83e) Thanks [@sailist](https://github.com/sailist)! - 新增 `GET /api/v1/fs:content` 服务端点，可通过绝对路径以原始内容形式提供主机上的任意文件，并支持 Content-Type、ETag 和 Range 请求。 - [#1999](https://github.com/MoonshotAI/kimi-code/pull/1999) [`4c763f6`](https://github.com/MoonshotAI/kimi-code/commit/4c763f6763acb67a73d133f7450d092e71d63692) Thanks [@RealKai42](https://github.com/RealKai42)! - 附加到提示词的视频（在 TUI 中粘贴或在 Web UI 中上传）现在会随提示词一同发送给模型，无需额外的工具往返调用，且在刷新后仍可在聊天中播放。 - [#1735](https://github.com/MoonshotAI/kimi-code/pull/1735) [`ce0e3ce`](https://github.com/MoonshotAI/kimi-code/commit/ce0e3ceb04223bdaad8e8931bad46eff561055b6) Thanks [@7Sageer](https://github.com/7Sageer)! - 支持为每次会话使用用户级文件覆盖默认的主代理系统提示词（仅限 v2 引擎）。 ### 补丁修复 - [#1997](https://github.com/MoonshotAI/kimi-code/pull/1997) [`74da87a`](https://github.com/MoonshotAI/kimi-code/commit/74da87a457c2964694a844dd22a4925f5113b167) Thanks [@sailist](https://github.com/sailist)! - 在服务端会话事件流中添加 `agent.created` 和 `agent.disposed` 事件，并在 transcript API 中暴露每个代理的销毁时间。 - [#2030](https://github.com/MoonshotAI/kimi-code/pull/2030) [`ec88d35`](https://github.com/MoonshotAI/kimi-code/commit/ec88d352e8f4dc5e8ffd1212f016138458f69893) Thanks [@RealKai42](https://github.com/RealKai42)! - 修复目录导入的 Claude 模型被错误锁定为始终开启思考的问题，并停止为无法真正禁用推理的模型（如 Gemini 3）提供具有误导性的“思考关闭”选项。同时规范化了配置的思考强度值并统一了上下文使用情况报告。 - [#2015](https://github.com/MoonshotAI/kimi-code/pull/2015) [`b5efba7`](https://github.com/MoonshotAI/kimi-code/commit/b5efba7abcaf4041f81ec520097a61e6546e8c50) Thanks [@RealKai42](https://github.com/RealKai42)! - 从 models.dev 目录导入更多提供商：xai 和 openrouter 等厂商 SDK 现在可以正常导入，而非被拒绝（附带“推测”提示）；已弃用和 Alpha 阶段的模型已被过滤；尊重按模型配置的网关协议和端点覆盖，并修正了上下文限制（压缩使用输入限制，补全使用总窗口限制）。缺少可用端点的导入项现在会通过 `--base-url` 或提示符请求提供。 - [#1993](https://github.com/MoonshotAI/kimi-code/pull/1993) [`37eda4e`](https://github.com/MoonshotAI/kimi-code/commit/37eda4e59aebc8ecafa91be3f43f971ed63963a3) Thanks [@RealKai42](https://github.com/RealKai42)! - 新增用于代理循环和后台任务限制的环境变量覆盖。设置 `KIMI_LOOP_MAX_STEPS_PER_TURN`、`KIMI_LOOP_MAX_RETRIES_PER_STEP` 或 `KIMI_CODE_BACKGROUND_MAX_RUNNING_TASKS` 将优先于 `[loop_control]` 和 `[background]` 配置。 - [#1993](https://github.com/MoonshotAI/kimi-code/pull/1993) [`37eda4e`](https://github.com/MoonshotAI/kimi-code/commit/37eda4e59aebc8ecafa91be3f43f971ed63963a3) Thanks [@RealKai42](https://github.com/RealKai42)! - 修复配置环境变量覆盖（如 `KIMI_IMAGE_MAX_EDGE_PX` 或 `KIMI_SUBAGENT_TIMEOUT_MS`）在环境变量设置时通过配置 API 写入被持久化到 `config.toml` 的问题，以及环境变量更改为无效值或被移除后仍保留旧值的问题。 - [#2050](https://github.com/MoonshotAI/kimi-code/pull/2050) [`8250e59`](https://github.com/MoonshotAI/kimi-code/commit/8250e590f3ed5990c233ef5a2c7666468f0bcb05) Thanks [@sailist](https://github.com/sailist)! - 从定时任务工具描述中移除对不存在的 `kimi resume` 命令的引用。 - [#1970](https://github.com/MoonshotAI/kimi-code/pull/1970) [`6dd4fd3`](https://github.com/MoonshotAI/kimi-code/commit/6dd4fd33688b37904d5302436fc2daaf09d66c7d) Thanks [@sailist](https://github.com/sailist)! - 修复被取消的模型请求被包装为可重试的提供商错误的问题，从而在中断请求时不再触发静默重试。 - [#1970](https://github.com/MoonshotAI/kimi-code/pull/1970) [`6dd4fd3`](https://github.com/MoonshotAI/kimi-code/commit/6dd4fd33688b37904d5302436fc2daaf09d66c7d) 感谢 [@sailist](https://github.com/sailist)！- 将会话提示词缓存键发送给 OpenAI 和 OpenAI Responses 提供商，恢复此前仅支持 Kimi 和 Anthropic 的提供商端提示词缓存亲和性。 - [#1999](https://github.com/MoonshotAI/kimi-code/pull/1999) [`4c763f6`](https://github.com/MoonshotAI/kimi-code/commit/4c763f6763acb67a73d133f7450d092e71d63692) 感谢 [@RealKai42](https://github.com/RealKai42)！- 修复当提供商没有文件上传通道时 `ReadMediaFile` 在视频上失败的问题——此类视频现在将回退到内联传输。 - [#1968](https://github.com/MoonshotAI/kimi-code/pull/1968) [`71bcfba`](https://github.com/MoonshotAI/kimi-code/commit/71bcfba54a6836f4b6d4e26babde67576b293a64) 感谢 [@RealKai42](https://github.com/RealKai42)！- 修复在内容过滤响应后，会话在每一轮都因提供商返回“消息不能为空”错误而卡住的问题。 - [#2022](https://github.com/MoonshotAI/kimi-code/pull/2022) [`154e082`](https://github.com/MoonshotAI/kimi-code/commit/154e0824880c8573433e4ec7ada083744dbfe9f9) 感谢 [@wbxl2000](https://github.com/wbxl2000)！- web：在棋盘格画布上显示透明图像，以便在浅色和深色主题下都能清晰显示白色和黑色内容。 - [#1990](https://github.com/MoonshotAI/kimi-code/pull/1990) [`115b096`](https://github.com/MoonshotAI/kimi-code/commit/115b0968cefede7fac1494c6f0154ea5545a89da) 感谢 [@liruifengv](https://github.com/liruifengv)！- 修复恢复会话时目标模式（goal mode）的续写提示词泄漏到对话记录中的问题。 - [#1970](https://github.com/MoonshotAI/kimi-code/pull/1970) [`6dd4fd3`](https://github.com/MoonshotAI/kimi-code/commit/6dd4fd33688b37904d5302436fc2daaf09d66c7d) 感谢 [@sailist](https://github.com/sailist)！- 将实验性 v2 引擎中的模型连接层重构为一组协议基类加上声明式提供商特征定义，使得添加提供商不再需要复制适配器代码，且每轮请求意图（缓存键、思考强度、采样）作为请求参数传递，而非克隆模型对象。移除了从未生效的 `[platforms]` 配置节和 `provider.platformId` 字段；凭证解析现在改为两层模型 → 提供商查找。 - [#1976](https://github.com/MoonshotAI/kimi-code/pull/1976) [`e458323`](https://github.com/MoonshotAI/kimi-code/commit/e45832398d0d9cad98dbad1cbf1e5b103a20aace) 感谢 [@liruifengv](https://github.com/liruifengv)！- 提升长时间运行会话的 TUI 性能与恢复速度。 - [#1991](https://github.com/MoonshotAI/kimi-code/pull/1991) [`92576e4`](https://github.com/MoonshotAI/kimi-code/commit/92576e4d850ada51a24e72fe76a83cc512df922a) 感谢 [@7Sageer](https://github.com/7Sageer)！- 当调用 MCP 服务器的某个工具时，自动重连已断开的连接，并重试调用一次。 - [#1970](https://github.com/MoonshotAI/kimi-code/pull/1970) [`6dd4fd3`](https://github.com/MoonshotAI/kimi-code/commit/6dd4fd33688b37904d5302436fc2daaf09d66c7d) 感谢 [@sailist](https://github.com/sailist)！- 在服务器的 RPC 接口中只读模型解析检查功能和实时连通性探测，报告每个字段的值来源（配置、覆盖、内置、环境变量、合成），供内部调试工具使用。 - [#2015](https://github.com/MoonshotAI/kimi-code/pull/2015) [`b5efba7`](https://github.com/MoonshotAI/kimi-code/commit/b5efba7abcaf4041f81ec520097a61e6546e8c50) 感谢 [@RealKai42](https://github.com/RealKai42)！- 修复为不支持思考功能的模型提供思考级别选项的问题（例如 Kimi K3 上的虚假选项）：级别现在取自各模型声明的能力。无法关闭推理的模型（例如 gpt-5）不再提供“关闭”选项，而在支持该功能的模型（例如 xai grok）上关闭思考现在会真正禁用推理。 - [#1735](https://github.com/MoonshotAI/kimi-code/pull/1735) [`ce0e3ce`](https://github.com/MoonshotAI/kimi-code/commit/ce0e3ceb04223bdaad8e8931bad46eff561055b6) 感谢 [@7Sageer](https://github.com/7Sageer)！- 当工具允许/拒绝列表中的条目永远无法匹配任何工具时发出警告，例如拼写错误的名称（仅限 v2 引擎）。 - [#2005](https://github.com/MoonshotAI/kimi-code/pull/2005) [`a3699dd`](https://github.com/MoonshotAI/kimi-code/commit/a3699dd6aa7b41efd3129a117007d195282379fd) 感谢 [@7Sageer](https://github.com/7Sageer)！- 在服务器的工具列表 API 中为每个工具添加 `active` 标志。 - [#1995](https://github.com/MoonshotAI/kimi-code/pull/1995) [`73eb5f8`](https://github.com/MoonshotAI/kimi-code/commit/73eb5f89e06fb15d42c7585a147eb1c5caef0725) 感谢 [@liruifengv](https://github.com/liruifengv)！- 移除代码预览和 Markdown 代码块语法高亮中的红色。 - [#2014](https://github.com/MoonshotAI/kimi-code/pull/2014) [`576d650`](https://github.com/MoonshotAI/kimi-code/commit/576d65038035570bea90b58d5824bcd60ca11258) 感谢 [@liruifengv](https://github.com/liruifengv)！- 在更新提示中增加提醒，建议第三方安装源使用官方安装程序。

### Minor Changes - [#1992](https://github.com/MoonshotAI/kimi-code/pull/1992) [`a8f1ca3`](https://github.com/MoonshotAI/kimi-code/commit/a8f1ca3f1016a3e84986f297367e833bc731ac39) Thanks [@RealKai42](https://github.com/RealKai42)! - Support selecting a thinking effort level from ACP clients: the thinking picker now lists the current model's declared levels (for example off / low / medium / high) instead of only an on/off toggle. Use the thinking selector in your ACP client (e.g. Zed) to pick a level; the legacy on/off values keep working. - [#1735](https://github.com/MoonshotAI/kimi-code/pull/1735) [`ce0e3ce`](https://github.com/MoonshotAI/kimi-code/commit/ce0e3ceb04223bdaad8e8931bad46eff561055b6) Thanks [@7Sageer](https://github.com/7Sageer)! - Let custom agent files restrict which sub-agent types they may delegate to (v2 engine only). - [#1735](https://github.com/MoonshotAI/kimi-code/pull/1735) [`ce0e3ce`](https://github.com/MoonshotAI/kimi-code/commit/ce0e3ceb04223bdaad8e8931bad46eff561055b6) Thanks [@7Sageer](https://github.com/7Sageer)! - Support custom agents defined as Markdown files with frontmatter, usable as the main agent or a sub-agent (v2 engine only). - [#1735](https://github.com/MoonshotAI/kimi-code/pull/1735) [`ce0e3ce`](https://github.com/MoonshotAI/kimi-code/commit/ce0e3ceb04223bdaad8e8931bad46eff561055b6) Thanks [@7Sageer](https://github.com/7Sageer)! - Add global tool gating to constrain which tools agents may use, with a per-session override (v2 engine only). - [#2012](https://github.com/MoonshotAI/kimi-code/pull/2012) [`d67a200`](https://github.com/MoonshotAI/kimi-code/commit/d67a2003abf2d8d802dcf24f806e0a811724b83e) Thanks [@sailist](https://github.com/sailist)! - Add a GET /api/v1/fs:content server endpoint that serves any file on the host by absolute path as raw content with Content-Type, ETag, and Range support. - [#1999](https://github.com/MoonshotAI/kimi-code/pull/1999) [`4c763f6`](https://github.com/MoonshotAI/kimi-code/commit/4c763f6763acb67a73d133f7450d092e71d63692) Thanks [@RealKai42](https://github.com/RealKai42)! - Videos attached to a prompt — pasted in the TUI or uploaded in the web UI — now reach the model together with the prompt, with no extra tool round trip, and stay playable in the chat after a reload. - [#1735](https://github.com/MoonshotAI/kimi-code/pull/1735) [`ce0e3ce`](https://github.com/MoonshotAI/kimi-code/commit/ce0e3ceb04223bdaad8e8931bad46eff561055b6) Thanks [@7Sageer](https://github.com/7Sageer)! - Support overriding the default main-agent system prompt with a user-level file for every session (v2 engine only). ### Patch Changes - [#1997](https://github.com/MoonshotAI/kimi-code/pull/1997) [`74da87a`](https://github.com/MoonshotAI/kimi-code/commit/74da87a457c2964694a844dd22a4925f5113b167) Thanks [@sailist](https://github.com/sailist)! - Add agent.created and agent.disposed events to the server session event stream, and expose each agent's disposal time in the transcript API. - [#2030](https://github.com/MoonshotAI/kimi-code/pull/2030) [`ec88d35`](https://github.com/MoonshotAI/kimi-code/commit/ec88d352e8f4dc5e8ffd1212f016138458f69893) Thanks [@RealKai42](https://github.com/RealKai42)! - Fix catalog-imported Claude models being wrongly locked into always-on thinking, and stop offering a misleading thinking Off option for models that cannot truly disable reasoning (such as Gemini 3). Also normalizes configured thinking effort values and unifies context-usage reporting. - [#2015](https://github.com/MoonshotAI/kimi-code/pull/2015) [`b5efba7`](https://github.com/MoonshotAI/kimi-code/commit/b5efba7abcaf4041f81ec520097a61e6546e8c50) Thanks [@RealKai42](https://github.com/RealKai42)! - Import many more providers from the models.dev catalog: vendor SDKs like xai and openrouter now import instead of being refused (with a "guessed" note), deprecated and alpha models are filtered out, per-model gateway protocol and endpoint overrides are honored, and context limits are correct (input limit for compaction, total window for completion). Imports lacking a usable endpoint now ask for one via `--base-url` or a prompt. - [#1993](https://github.com/MoonshotAI/kimi-code/pull/1993) [`37eda4e`](https://github.com/MoonshotAI/kimi-code/commit/37eda4e59aebc8ecafa91be3f43f971ed63963a3) Thanks [@RealKai42](https://github.com/RealKai42)! - Add environment variable overrides for agent loop and background task limits. Set KIMI_LOOP_MAX_STEPS_PER_TURN, KIMI_LOOP_MAX_RETRIES_PER_STEP, or KIMI_CODE_BACKGROUND_MAX_RUNNING_TASKS to take priority over the [loop_control] and [background] config. - [#1993](https://github.com/MoonshotAI/kimi-code/pull/1993) [`37eda4e`](https://github.com/MoonshotAI/kimi-code/commit/37eda4e59aebc8ecafa91be3f43f971ed63963a3) Thanks [@RealKai42](https://github.com/RealKai42)! - Fix config environment overrides (such as KIMI_IMAGE_MAX_EDGE_PX or KIMI_SUBAGENT_TIMEOUT_MS) being persisted into config.toml by config API writes while the env var is set, and keeping the old value after the env var is changed to an invalid value or removed. - [#2050](https://github.com/MoonshotAI/kimi-code/pull/2050) [`8250e59`](https://github.com/MoonshotAI/kimi-code/commit/8250e590f3ed5990c233ef5a2c7666468f0bcb05) Thanks [@sailist](https://github.com/sailist)! - Remove references to the non-existent `kimi resume` command from the scheduled-task tool descriptions. - [#1970](https://github.com/MoonshotAI/kimi-code/pull/1970) [`6dd4fd3`](https://github.com/MoonshotAI/kimi-code/commit/6dd4fd33688b37904d5302436fc2daaf09d66c7d) Thanks [@sailist](https://github.com/sailist)! - Fix cancelled model requests being wrapped as retryable provider errors, so interrupting a request no longer triggers silent retries. - [#1970](https://github.com/MoonshotAI/kimi-code/pull/1970) [`6dd4fd3`](https://github.com/MoonshotAI/kimi-code/commit/6dd4fd33688b37904d5302436fc2daaf09d66c7d) Thanks [@sailist](https://github.com/sailist)! - Send the session prompt cache key to OpenAI and OpenAI Responses providers, restoring provider-side prompt cache affinity that previously only reached Kimi and Anthropic. - [#1999](https://github.com/MoonshotAI/kimi-code/pull/1999) [`4c763f6`](https://github.com/MoonshotAI/kimi-code/commit/4c763f6763acb67a73d133f7450d092e71d63692) Thanks [@RealKai42](https://github.com/RealKai42)! - Fix ReadMediaFile failing on videos when the provider has no file upload channel — such videos now fall back to inline delivery. - [#1968](https://github.com/MoonshotAI/kimi-code/pull/1968) [`71bcfba`](https://github.com/MoonshotAI/kimi-code/commit/71bcfba54a6836f4b6d4e26babde67576b293a64) Thanks [@RealKai42](https://github.com/RealKai42)! - Fix sessions getting stuck on every turn with a provider "message must not be empty" error after a content-filtered response. - [#2022](https://github.com/MoonshotAI/kimi-code/pull/2022) [`154e082`](https://github.com/MoonshotAI/kimi-code/commit/154e0824880c8573433e4ec7ada083744dbfe9f9) Thanks [@wbxl2000](https://github.com/wbxl2000)! - web: Show transparent images over a checkerboard canvas so white and black content stays visible in both light and dark themes. - [#1990](https://github.com/MoonshotAI/kimi-code/pull/1990) [`115b096`](https://github.com/MoonshotAI/kimi-code/commit/115b0968cefede7fac1494c6f0154ea5545a89da) Thanks [@liruifengv](https://github.com/liruifengv)! - Fix goal mode continuation prompts leaking into the transcript when resuming a session. - [#1970](https://github.com/MoonshotAI/kimi-code/pull/1970) [`6dd4fd3`](https://github.com/MoonshotAI/kimi-code/commit/6dd4fd33688b37904d5302436fc2daaf09d66c7d) Thanks [@sailist](https://github.com/sailist)! - Rework the model wire layer in the experimental v2 engine into a small set of protocol bases plus declarative provider trait definitions, so adding a provider no longer means copying adapter code, and per-turn request intent (cache key, thinking effort, sampling) flows as request parameters instead of cloned model objects. The never-functional `[platforms]` config section and the `provider.platformId` field are removed; credential resolution is now a two-layer model → provider lookup. - [#1976](https://github.com/MoonshotAI/kimi-code/pull/1976) [`e458323`](https://github.com/MoonshotAI/kimi-code/commit/e45832398d0d9cad98dbad1cbf1e5b103a20aace) Thanks [@liruifengv](https://github.com/liruifengv)! - Improve TUI performance and resume speed for long-running sessions. - [#1991](https://github.com/MoonshotAI/kimi-code/pull/1991) [`92576e4`](https://github.com/MoonshotAI/kimi-code/commit/92576e4d850ada51a24e72fe76a83cc512df922a) Thanks [@7Sageer](https://github.com/7Sageer)! - Reconnect a dropped MCP server connection automatically when one of its tools is called, and retry the call once. - [#1970](https://github.com/MoonshotAI/kimi-code/pull/1970) [`6dd4fd3`](https://github.com/MoonshotAI/kimi-code/commit/6dd4fd33688b37904d5302436fc2daaf09d66c7d) Thanks [@sailist](https://github.com/sailist)! - Add read-only model resolution inspection and a live connectivity probe to the server's RPC surface, reporting per-field value provenance (config, override, builtin, env, synthesized) for internal debugging tools. - [#2015](https://github.com/MoonshotAI/kimi-code/pull/2015) [`b5efba7`](https://github.com/MoonshotAI/kimi-code/commit/b5efba7abcaf4041f81ec520097a61e6546e8c50) Thanks [@RealKai42](https://github.com/RealKai42)! - Fix thinking levels being offered for models that do not support them (e.g. phantom levels on Kimi K3): levels now come from each model's declared capabilities. Models that cannot disable reasoning (e.g. gpt-5) no longer offer an Off option, and turning thinking Off on models that support it (e.g. xai grok) now truly disables reasoning. - [#1735](https://github.com/MoonshotAI/kimi-code/pull/1735) [`ce0e3ce`](https://github.com/MoonshotAI/kimi-code/commit/ce0e3ceb04223bdaad8e8931bad46eff561055b6) Thanks [@7Sageer](https://github.com/7Sageer)! - Warn when a tool allow/deny list entry can never match any tool, for example a misspelled name (v2 engine only). - [#2005](https://github.com/MoonshotAI/kimi-code/pull/2005) [`a3699dd`](https://github.com/MoonshotAI/kimi-code/commit/a3699dd6aa7b41efd3129a117007d195282379fd) Thanks [@7Sageer](https://github.com/7Sageer)! - Add an `active` flag to each tool in the server's tool listing API. - [#1995](https://github.com/MoonshotAI/kimi-code/pull/1995) [`73eb5f8`](https://github.com/MoonshotAI/kimi-code/commit/73eb5f89e06fb15d42c7585a147eb1c5caef0725) Thanks [@liruifengv](https://github.com/liruifengv)! - Remove red coloring from syntax highlighting in code previews and markdown code blocks. - [#2014](https://github.com/MoonshotAI/kimi-code/pull/2014) [`576d650`](https://github.com/MoonshotAI/kimi-code/commit/576d65038035570bea90b58d5824bcd60ca11258) Thanks [@liruifengv](https://github.com/liruifengv)! - Add a reminder for third-party install sources to use the official installer in the update prompt.

Kimi Code @moonshot-ai/[email protected]