Pi v0.79.5 - 更新日志

### 新功能 - **提供商范围 API 密钥环境** - `auth.json` 中的 API 密钥条目现在可包含 `env` 覆盖项，用于提供商特定的 Cloudflare、Azure OpenAI、Google Vertex、Amazon Bedrock、缓存保留和代理设置，且无需更改项目 shell。请参阅 [Auth File](https://github.com/earendil-works/pi/blob/v0.79.5/packages/coding-agent/docs/providers.md#auth-file)。 - **全局 HTTP 代理设置** - 在全局设置中配置一次 `httpProxy`，即可将 `HTTP_PROXY` 和 `HTTPS_PROXY` 应用于 Pi 管理的 HTTP 客户端。请参阅 [Network](https://github.com/earendil-works/pi/blob/v0.79.5/packages/coding-agent/docs/settings.md#network)。 - **Vercel AI Gateway 归属标识** - Vercel AI Gateway 请求现在默认包含 Pi 归属标识头。请参阅 [API Keys](https://github.com/earendil-works/pi/blob/v0.79.5/packages/coding-agent/docs/providers.md#api-keys)。 ### 新增 - 为 Vercel AI Gateway 模型添加了请求归属标识头（`http-referer` 和 `x-title`）([#5798](https://github.com/earendil-works/pi/pull/5798) by [@rwachtler](https://github.com/rwachtler))。 - 启用实验性功能时，添加了 `xp` 页脚标记。 - 添加了全局 `httpProxy` 设置，作为 `HTTP_PROXY` 和 `HTTPS_PROXY` 应用于 Pi 管理的 HTTP 客户端 ([#5790](https://github.com/earendil-works/pi/issues/5790))。 - 添加了 `auth.json` API 密钥的 `env` 值，使提供商特定的环境覆盖能够限定于 Pi 范围内，并传播到继承的提供商配置中 ([#5728](https://github.com/earendil-works/pi/issues/5728))。 ### 更改 - 将 HTML 会话导出所使用的内置 Markdown 解析器更新为 `marked` 18.0.5。 ### 修复 - 修复了继承的 OpenAI Responses 流式传输，使其能够容忍 OpenAI 兼容服务器在工具调用前返回的 null 消息内容 ([#5819](https://github.com/earendil-works/pi/issues/5819))。 - 修复了继承的 OpenCode DeepSeek V4 思考请求，避免同时发送 `thinking` 和 `reasoning_effort` ([#5818](https://github.com/earendil-works/pi/issues/5818))。 - 修复了设备码登录，停止自动打开浏览器。 - 修复了继承编辑器中 Cursor Up 的处理逻辑，使非空草稿在浏览输入历史前跳转至行首 ([#5789](https://github.com/earendil-works/pi/pull/5789) by [@4h9fbZ](https://github.com/4h9fbZ))。 - 修复了继承的 Z.AI GLM-5.2 思考请求，使其随提供商的 `high`/`max` 努力程度映射发送 `reasoning_effort` ([#5770](https://github.com/earendil-works/pi/issues/5770))。 - 修复了 Windows 上成功执行 `pi update` 后的退出逻辑，改为自然退出而非调用 `process.exit(0)`，从而避免在版本检查网络请求后触发 Node.js/libuv 断言 ([#5805](https://github.com/earendil-works/pi/issues/5805))。 - 修复了继承的 Google 和 `google-vertex` Gemini 模型元数据，将 `latest` 别名映射到当前模型，为 Vertex 添加 Gemini 3.5 Flash，修正 Gemini 2.5 Flash Vertex 缓存定价，并移除已停用的 Vertex 预览模型 ([#5761](https://github.com/earendil-works/pi/issues/5761))。 - 修复了会话选择器，当当前文件夹和所有范围的会话列表均为空时，保持打开状态并显示全会话空状态 ([#5747](https://github.com/earendil-works/pi/issues/5747))。 - 修复了继承的 Moonshot AI 中国模型元数据，包含 Kimi K2.7 Code，并省略了 Kimi K2.7 Code 模型不支持的 thinking-off 负载 ([#5760](https://github.com/earendil-works/pi/issues/5760))。

### New Features - **Provider-scoped API key environments** - `auth.json` API key entries can now include `env` overrides for provider-specific Cloudflare, Azure OpenAI, Google Vertex, Amazon Bedrock, cache retention, and proxy settings without changing the project shell. See [Auth File](https://github.com/earendil-works/pi/blob/v0.79.5/packages/coding-agent/docs/providers.md#auth-file). - **Global HTTP proxy setting** - Configure `httpProxy` once in global settings to apply `HTTP_PROXY` and `HTTPS_PROXY` to Pi-managed HTTP clients. See [Network](https://github.com/earendil-works/pi/blob/v0.79.5/packages/coding-agent/docs/settings.md#network). - **Vercel AI Gateway attribution** - Vercel AI Gateway requests now include Pi attribution headers by default. See [API Keys](https://github.com/earendil-works/pi/blob/v0.79.5/packages/coding-agent/docs/providers.md#api-keys). ### Added - Added Vercel AI Gateway request attribution headers (`http-referer` and `x-title`) for Vercel AI Gateway models ([#5798](https://github.com/earendil-works/pi/pull/5798) by [@rwachtler](https://github.com/rwachtler)). - Added an `xp` footer marker when experimental features are enabled. - Added a global `httpProxy` setting that applies as `HTTP_PROXY` and `HTTPS_PROXY` for Pi-managed HTTP clients ([#5790](https://github.com/earendil-works/pi/issues/5790)). - Added `auth.json` API key `env` values so provider-specific environment overrides can be scoped to Pi and propagated to inherited provider configuration ([#5728](https://github.com/earendil-works/pi/issues/5728)). ### Changed - Updated the vendored Markdown parser used by HTML session exports to `marked` 18.0.5. ### Fixed - Fixed inherited OpenAI Responses streaming to tolerate null message content from OpenAI-compatible servers before tool calls ([#5819](https://github.com/earendil-works/pi/issues/5819)). - Fixed inherited OpenCode DeepSeek V4 thinking requests to avoid sending both `thinking` and `reasoning_effort` ([#5818](https://github.com/earendil-works/pi/issues/5818)). - Fixed device-code login to stop opening the browser automatically. - Fixed inherited editor Cursor Up handling so non-empty drafts jump to the start of the line before browsing input history ([#5789](https://github.com/earendil-works/pi/pull/5789) by [@4h9fbZ](https://github.com/4h9fbZ)). - Fixed inherited Z.AI GLM-5.2 thinking requests to send `reasoning_effort` with the provider's `high`/`max` effort mapping ([#5770](https://github.com/earendil-works/pi/issues/5770)). - Fixed successful `pi update` on Windows to exit naturally instead of calling `process.exit(0)`, avoiding a Node.js/libuv assertion after version-check network requests ([#5805](https://github.com/earendil-works/pi/issues/5805)). - Fixed inherited Google and `google-vertex` Gemini model metadata to map `latest` aliases to the current models, add Gemini 3.5 Flash for Vertex, correct Gemini 2.5 Flash Vertex cache pricing, and remove shut-down Vertex preview models ([#5761](https://github.com/earendil-works/pi/issues/5761)). - Fixed the session selector to stay open and show the all-sessions empty state when both current-folder and all-scope session lists are empty ([#5747](https://github.com/earendil-works/pi/issues/5747)). - Fixed inherited Moonshot AI China model metadata to include Kimi K2.7 Code, and omitted unsupported thinking-off payloads for Kimi K2.7 Code models ([#5760](https://github.com/earendil-works/pi/issues/5760)).