Pi v0.78.1 - 更新日志

### 新功能 - **更全面的内置提供商覆盖** - 新增了 Ant Ling 和 NVIDIA NIM 提供商的配置说明，并为直接 MiniMax 提供商添加了 MiniMax-M3 支持。详见 [Providers](https://github.com/earendil-works/pi/blob/v0.78.1/packages/coding-agent/docs/providers.md)。 - **更丰富的扩展上下文** - 扩展程序现在可以使用 `ctx.mode` 和 `ctx.getSystemPromptOptions()` 来适配 TUI、RPC、JSON 和 print 模式下的行为，并检查基础系统提示词输入。详见 [Extensions](https://github.com/earendil-works/pi/blob/v0.78.1/packages/coding-agent/docs/extensions.md)。 ### 新增 - 新增容器化文档以及 Gondolin 扩展示例，用于将内置工具路由到本地微虚拟机。 - 新增 Ant Ling 提供商的选择与配置文档。 - 为 `minimax` 和 `minimax-cn` 直接提供商新增 MiniMax-M3 模型支持（继承自 `@earendil-works/pi-ai`）([#5313](https://github.com/earendil-works/pi/issues/5313))。 - 新增 NVIDIA NIM 提供商的选择、配置文档，以及直接 NIM 请求的归属标头。 - 在扩展上下文中新增 `ctx.mode`，使扩展能够区分 TUI、RPC、JSON 和 print 模式。 - 为扩展命令新增 `ctx.getSystemPromptOptions()`，用于检查当前基础系统提示词输入 ([#5306](https://github.com/earendil-works/pi/pull/5306)，由 [@xl0](https://github.com/xl0) 贡献)。 ### 修复 - 修复临时扩展包安装问题，现使用权限为 `0700` 的私有目录 `~/.pi/agent/tmp/extensions`，替代原来的 `os.tmpdir()/pi-extensions`。 - 修复 git 包源处理逻辑，拒绝不安全的 host/path 组件，并确保受管理的克隆路径保留在安装根目录内。 - 修复 HTML 会话导出中的存储型 XSS 漏洞，在去除控制字符后，使用协议白名单对 Markdown 链接和图片 URL 进行清理。 - 修复在捆绑 Node 应用中，当 `package.json` 未与捆绑入口点并列时，SDK 嵌入会因 `ENOENT` 错误而失败的问题。包元数据读取器现在能优雅地处理缺失 `package.json` 的情况（使用默认值），使 `createAgentSession()` 在运行时不再依赖包相邻文件 ([#5226](https://github.com/earendil-works/pi/issues/5226))。 - 修复非 Codex 提供商（例如通过 OpenAI 兼容 API 的 llama.cpp）未遵循 HTTP 超时设置的问题。`httpIdleTimeoutMs` 设置（通过 `/settings` HTTP 超时配置）现在作为所有支持该设置的提供商的默认 SDK 请求超时时间，而不仅限于 OpenAI Codex Responses。禁用超时（HTTP 超时 = false）现在通过发送最大 int32 值（相当于无限）而非 0 来正确禁用所有支持提供商的 SDK 超时（因为 SDK 将 timeout=0 视为立即超时）([#5294](https://github.com/earendil-works/pi/issues/5294))。 - 修复继承的 Amazon Bedrock 请求，将空白的必填用户/工具结果文本替换为占位符，并跳过空白的重放文本块 ([#4975](https://github.com/earendil-works/pi/issues/4975))。 - 修复继承的 Anthropic Claude Opus 4.7+ 请求，以屏蔽已弃用的 temperature 参数 ([#5251](https://github.com/earendil-works/pi/pull/5251)，由 [@yzhg1983](https://github.com/yzhg1983) 贡献)。 - 修复继承的 OpenAI GPT-5.5 生成的元数据，移除不支持的 minimal thinking 字段 ([#5243](https://github.com/earendil-works/pi/issues/5243))。 - 修复继承的 OpenRouter Kimi K2.6 思考过程重放及开发者角色指令处理 ([#5309](https://github.com/earendil-works/pi/issues/5309))。 - 修复继承的 OpenRouter 推理指令请求，在需要时保留 system 角色 ([#5221](https://github.com/earendil-works/pi/pull/5221)，由 [@PriNova](https://github.com/PriNova) 贡献)。 - 修复继承的覆盖层焦点恢复问题，使非捕获型覆盖层在 UI 重新渲染和显式释放焦点后仍能保持交互 ([#5235](https://github.com/earendil-works/pi/pull/5235)，由 [@nicobailon](https://github.com/nicobailon) 贡献)。 - 修复继承的列切片和覆盖层合成中的制表符宽度计算，确保包含制表符的输出不会超出终端宽度 ([#5218](https://github.com/earendil-works/pi/issues/5218))。 - 修复打开和列出超大 JSONL 会话文件的问题，改为逐行读取会话条目，而非将整个文件加载为单个字符串 ([#5231](https://github.com/earendil-works/pi/issues/5231))。 - 修复 WSL `/mnt/...` 仓库中页脚分支显示的问题，使其在分支变更后刷新 ([#5264](https://github.com/earendil-works/pi/pull/5264)，由 [@psoukie](https://github.com/psoukie) 贡献)。 - 修复 `renderShell: "self"` 工具渲染器在无组件行输出时留下空白聊天行的问题 ([#5299](https://github.com/earendil-works/pi/issues/5299))。 - 恢复继承的 NVIDIA Qwen 3.5 122B NIM 模型支持。

### New Features - **More built-in provider coverage** - Added Ant Ling and NVIDIA NIM provider setup, plus MiniMax-M3 support for the direct MiniMax providers. See [Providers](https://github.com/earendil-works/pi/blob/v0.78.1/packages/coding-agent/docs/providers.md). - **Richer extension context** - Extensions can use `ctx.mode` and `ctx.getSystemPromptOptions()` to adapt behavior across TUI, RPC, JSON, and print modes and inspect base system prompt inputs. See [Extensions](https://github.com/earendil-works/pi/blob/v0.78.1/packages/coding-agent/docs/extensions.md). ### Added - Added containerization documentation and a Gondolin extension example for routing built-in tools into a local micro-VM. - Added Ant Ling provider selection and setup documentation. - Added MiniMax-M3 model support inherited from `@earendil-works/pi-ai` for the `minimax` and `minimax-cn` direct providers ([#5313](https://github.com/earendil-works/pi/issues/5313)). - Added NVIDIA NIM provider selection, setup documentation, and direct NIM request attribution headers. - Added `ctx.mode` to extension contexts so extensions can distinguish TUI, RPC, JSON, and print mode. - Added `ctx.getSystemPromptOptions()` for extension commands to inspect the current base system prompt inputs ([#5306](https://github.com/earendil-works/pi/pull/5306) by [@xl0](https://github.com/xl0)). ### Fixed - Fixed temporary extension package installs to use a private `~/.pi/agent/tmp/extensions` directory with `0700` permissions instead of `os.tmpdir()/pi-extensions`. - Fixed git package source handling to reject unsafe host/path components and keep managed clone paths inside install roots. - Fixed stored XSS in HTML session exports by sanitizing Markdown link and image URLs with a scheme allow-list after stripping control characters. - Fixed SDK embedding in bundled Node apps failing with `ENOENT` when `package.json` is not present next to the bundle entrypoint. The package metadata reader now gracefully handles missing `package.json` by using defaults, enabling `createAgentSession()` without requiring package-adjacent files at runtime ([#5226](https://github.com/earendil-works/pi/issues/5226)). - Fixed HTTP timeout setting not being respected for non-Codex providers (e.g., llama.cpp via OpenAI-compatible API). The `httpIdleTimeoutMs` setting (set via `/settings` HTTP timeout) now applies as the default SDK request timeout for all providers that support it, not just OpenAI Codex Responses. Disabling the timeout (HTTP timeout = false) now correctly disables SDK timeouts for all supported providers by sending a maximum int32 value (effectively infinite) instead of 0, since SDKs treat timeout=0 as an immediate timeout ([#5294](https://github.com/earendil-works/pi/issues/5294)). - Fixed inherited Amazon Bedrock requests to replace blank required user/tool-result text with a placeholder and skip blank replay text blocks ([#4975](https://github.com/earendil-works/pi/issues/4975)). - Fixed inherited Anthropic Claude Opus 4.7+ requests to suppress deprecated temperature parameters ([#5251](https://github.com/earendil-works/pi/pull/5251) by [@yzhg1983](https://github.com/yzhg1983)). - Fixed inherited OpenAI GPT-5.5 generated metadata to omit unsupported minimal thinking ([#5243](https://github.com/earendil-works/pi/issues/5243)). - Fixed inherited OpenRouter Kimi K2.6 thinking replay and developer-role instruction handling ([#5309](https://github.com/earendil-works/pi/issues/5309)). - Fixed inherited OpenRouter reasoning instruction requests to preserve the system role when required ([#5221](https://github.com/earendil-works/pi/pull/5221) by [@PriNova](https://github.com/PriNova)). - Fixed inherited overlay focus restoration so non-capturing overlays remain interactive after UI rerenders and explicit focus release ([#5235](https://github.com/earendil-works/pi/pull/5235) by [@nicobailon](https://github.com/nicobailon)). - Fixed inherited tab width accounting in column slicing and overlay compositing so tab-containing output cannot exceed the terminal width ([#5218](https://github.com/earendil-works/pi/issues/5218)). - Fixed opening and listing very large JSONL session files by reading session entries line-by-line instead of materializing the full file as one string ([#5231](https://github.com/earendil-works/pi/issues/5231)). - Fixed the footer branch display in WSL `/mnt/...` repositories to refresh after branch changes ([#5264](https://github.com/earendil-works/pi/pull/5264) by [@psoukie](https://github.com/psoukie)). - Fixed `renderShell: "self"` tool renderers that emit no component lines leaving a blank chat row ([#5299](https://github.com/earendil-works/pi/issues/5299)). - Restored inherited NVIDIA Qwen 3.5 122B NIM model support.