Pi v0.79.9 - 更新日志

### 新功能 - **Chat-template 思考兼容性** - OpenAI 兼容的自定义提供商可以将 Pi 的思考级别映射到 `chat_template_kwargs` 中，使 vLLM/Hugging Face 聊天模板模型（如 DeepSeek）能够使用提供商原生的思考控制功能。请参阅 [自定义提供商 API 类型](https://github.com/earendil-works/pi/blob/v0.79.9/packages/coding-agent/docs/custom-provider.md#api-types) 和 [OpenAI 兼容性](https://github.com/earendil-works/pi/blob/v0.79.9/packages/coding-agent/docs/models.md#openai-compatibility)。 - **GLM-5.2 提供商改进** - GLM-5.2 现已修复 Fireworks OpenAI 兼容路由，并支持 OpenRouter `xhigh` 思考模式，改善了 GLM-5.2 用户的 `/model` 行为及高努力推理体验。请参阅 [模型选项](https://github.com/earendil-works/pi/blob/v0.79.9/packages/coding-agent/docs/usage.md#model-options)。 ### 新增 - 为使用 `chat_template_kwargs` 的 OpenAI 兼容提供商（如 vLLM 后端的 DeepSeek 模型）添加了继承式可配置的 `chat-template` 思考支持 ([#5673](https://github.com/earendil-works/pi/issues/5673))。 ### 修复 - 修复了继承的 Fireworks GLM-5.2 元数据，使其使用支持 `reasoning_effort` 的 OpenAI 兼容 Chat Completions 端点 ([#5923](https://github.com/earendil-works/pi/issues/5923))。 - 修复了同目录会话切换问题，使其在重用已导入的扩展模块的同时，保留全新的扩展实例和生命周期事件 ([#5905](https://github.com/earendil-works/pi/issues/5905))。 - 修复了深层会话分支在构建上下文或分支路径时耗时呈二次方增长的问题 ([#5909](https://github.com/earendil-works/pi/issues/5909))。 - 修复了继承的 OpenRouter GLM-5.2 元数据，使其暴露 `xhigh` 推理并发送 OpenRouter 原生的 `xhigh` 努力级别 ([#5770](https://github.com/earendil-works/pi/issues/5770))。 - 修复了继承的 Markdown 流式代码块围栏渲染问题，使内容流式传输时部分闭合围栏不再导致代码块收缩或闪烁 ([#5846](https://github.com/earendil-works/pi/pull/5846) by [@xl0](https://github.com/xl0))。 - 修复了模糊 `edit` 匹配问题，使其保留未修改的行块，而不是通过标准化内容重写整个文件 ([#5899](https://github.com/earendil-works/pi/issues/5899))。 - 修复了通过旧版 WSL `bash.exe` 执行 bash 命令的问题，改为通过 stdin 传递脚本，以便在目标 bash 中正确展开 shell 变量 ([#5893](https://github.com/earendil-works/pi/issues/5893))。 - 修复了 `/model` 命令，使其隐藏当前认证账户不可用的 GitHub Copilot 模型 ([#5897](https://github.com/earendil-works/pi/issues/5897))。 - 修复了 `/model` 选择器搜索的排序逻辑，使精确的提供商前缀匹配优先于代理提供商模型 ID 匹配 ([#5892](https://github.com/earendil-works/pi/issues/5892))。

### New Features - **Chat-template thinking compatibility** - OpenAI-compatible custom providers can map Pi thinking levels into `chat_template_kwargs`, enabling vLLM/Hugging Face chat-template models such as DeepSeek to use provider-native thinking controls. See [Custom Provider API Types](https://github.com/earendil-works/pi/blob/v0.79.9/packages/coding-agent/docs/custom-provider.md#api-types) and [OpenAI Compatibility](https://github.com/earendil-works/pi/blob/v0.79.9/packages/coding-agent/docs/models.md#openai-compatibility). - **GLM-5.2 provider improvements** - GLM-5.2 now has corrected Fireworks OpenAI-compatible routing and OpenRouter `xhigh` thinking support, improving `/model` behavior and high-effort reasoning for GLM-5.2 users. See [Model Options](https://github.com/earendil-works/pi/blob/v0.79.9/packages/coding-agent/docs/usage.md#model-options). ### Added - Added inherited configurable `chat-template` thinking support for OpenAI-compatible providers that use `chat_template_kwargs`, such as DeepSeek models behind vLLM ([#5673](https://github.com/earendil-works/pi/issues/5673)). ### Fixed - Fixed inherited Fireworks GLM-5.2 metadata to use the OpenAI-compatible Chat Completions endpoint with `reasoning_effort` support ([#5923](https://github.com/earendil-works/pi/issues/5923)). - Fixed same-directory session switches to reuse imported extension modules while preserving fresh extension instances and lifecycle events ([#5905](https://github.com/earendil-works/pi/issues/5905)). - Fixed deep session branches taking quadratic time to build context or branch paths ([#5909](https://github.com/earendil-works/pi/issues/5909)). - Fixed inherited OpenRouter GLM-5.2 metadata to expose `xhigh` reasoning and send OpenRouter's native `xhigh` effort ([#5770](https://github.com/earendil-works/pi/issues/5770)). - Fixed inherited Markdown streaming code fence rendering so partial closing fences no longer make code blocks shrink or flicker while content streams ([#5846](https://github.com/earendil-works/pi/pull/5846) by [@xl0](https://github.com/xl0)). - Fixed fuzzy `edit` matches to preserve untouched line blocks instead of rewriting the whole file through normalized content ([#5899](https://github.com/earendil-works/pi/issues/5899)). - Fixed bash commands through legacy WSL `bash.exe` to pass scripts over stdin so shell variables expand in the target bash ([#5893](https://github.com/earendil-works/pi/issues/5893)). - Fixed `/model` to hide GitHub Copilot models that are unavailable to the authenticated account ([#5897](https://github.com/earendil-works/pi/issues/5897)). - Fixed `/model` selector search to rank exact provider-prefixed matches before proxy-provider model ID matches ([#5892](https://github.com/earendil-works/pi/issues/5892)).