Pi v0.79.1 - 更新日志

### 新功能 - **Claude Fable 5** - Claude Fable 5 现已在 Anthropic 和 Amazon Bedrock 提供商处可用，支持自适应思考与 `xhigh` 处理强度。 - **提示词模板默认值** - 提示词模板现在可以使用默认位置参数（如 `${1:-7}`）来处理可选值。详见 [提示词模板参数](https://github.com/earendil-works/pi/blob/v0.79.1/packages/coding-agent/docs/prompt-templates.md#arguments)。 - **可配置的项目信任默认值** - `defaultProjectTrust` 允许用户默认选择对未解析的项目信任请求是询问、始终信任还是从不信任，扩展程序也可检查实际信任决策。详见 [项目信任](https://github.com/earendil-works/pi/blob/v0.79.1/packages/coding-agent/docs/security.md#project-trust) 和 [`ctx.isProjectTrusted()`](https://github.com/earendil-works/pi/blob/v0.79.1/packages/coding-agent/docs/extensions.md#ctxisprojecttrusted)。 - **自然的扩展自动补全触发器** - 扩展自动补全提供商可以声明触发字符（如 `#` 或 `$`），从而无需斜杠命令前缀即可打开建议。详见 [自动补全提供商](https://github.com/earendil-works/pi/blob/v0.79.1/packages/coding-agent/docs/extensions.md#autocomplete-providers)。 ### 新增 - 为提示词模板位置参数添加了默认值展开功能，例如 `${1:-7}` ([#5553](https://github.com/earendil-works/pi/pull/5553) by [@dannote](https://github.com/dannote))。 - 添加了 `areExperimentalFeaturesEnabled` 功能开关，允许用户选择加入早期功能 ([#5547](https://github.com/earendil-works/pi/pull/5547) by [@vegarsti](https://github.com/vegarsti))。 - 为扩展程序添加了 `ctx.isProjectTrusted()`，用于观察实际的项目信任决策，包括临时信任决策 ([#5523](https://github.com/earendil-works/pi/issues/5523))。 - 添加了全局 `defaultProjectTrust` 设置，用于默认选择对未解析的项目信任请求是询问、始终信任还是从不信任。 - 为 `ctx.ui.addAutocompleteProvider()` 包装器添加了扩展自动补全触发字符支持 ([#4703](https://github.com/earendil-works/pi/issues/4703))。 - 为 Anthropic 和 Amazon Bedrock 提供商添加了源自 `@earendil-works/pi-ai` 的 Claude Fable 5 模型支持，包含自适应思考与 `xhigh` 处理强度支持。 ### 修复 - 修复了继承的 Amazon Bedrock 推理配置文件 ARN 区域解析问题，使其优先使用 ARN 内置区域而非 `AWS_REGION` ([#5527](https://github.com/earendil-works/pi/pull/5527) by [@AJM10565](https://github.com/AJM10565))。 - 修复了斜杠命令自动补全可见时继承的 IME 硬件光标定位问题 ([#5283](https://github.com/earendil-works/pi/pull/5283) by [@smoosex](https://github.com/smoosex))。 - 修复了继承的 z.ai 关闭思考请求，使其正确发送提供商的 `thinking: { type: "disabled" }` 兼容参数 ([#5330](https://github.com/earendil-works/pi/issues/5330))。 - 修复了继承的 OpenCode 补全模型元数据，使其将显式 `maxTokens` 发送为 `max_tokens` ([#5331](https://github.com/earendil-works/pi/issues/5331))。 - 修复了继承的 Moonshot Kimi 关闭思考请求，使其正确发送提供商的 `thinking: { type: "disabled" }` 兼容参数 ([#5531](https://github.com/earendil-works/pi/issues/5531))。 - 修复了继承的 Azure OpenAI Responses 请求，以禁用服务器端响应存储 ([#5530](https://github.com/earendil-works/pi/issues/5530))。 - 修复了继承的 Azure GPT-5.4 和 GPT-5.5 上下文窗口元数据，将其调整为 1,050,000 tokens，以匹配 Azure Foundry 部署，而非 OpenAI 的 272k 限制 ([#5559](https://github.com/earendil-works/pi/issues/5559))。 - 修复了继承的 OpenAI 和 Azure GPT-5 Pro `maxTokens` 元数据，将其调整为 128,000，纠正了上游将输入子限制重复作为输出限制的错误值 ([#5559](https://github.com/earendil-works/pi/issues/5559))。 - 修复了继承的提示词历史记录导航，在从历史记录浏览返回时恢复当前草稿 ([#5494](https://github.com/earendil-works/pi/issues/5494))。 - 修复了继承的拉丁文与中日韩（CJK）混合文本换行问题，使无空格 CJK 序列能在字素边界处正确换行，避免留下过长的尾部空白 ([#5495](https://github.com/earendil-works/pi/issues/5495))。 - 修复了扩展 OAuth 登录提示，使已提交的提示词行保持稳定，而非镜像当前输入值 ([#5433](https://github.com/earendil-works/pi/issues/5433))。 - 修复了 `/reload` 命令，使其能将更新后的 `steeringMode` 和 `followUpMode` 设置应用到当前会话 ([#5377](https://github.com/earendil-works/pi/issues/5377))。 - 修复了无效的 `models.json` 语法处理逻辑，使其跳过启动配置迁移，并报告正常的文件路径感知模型错误，而非原始 JSON 解析堆栈跟踪 ([#5418](https://github.com/earendil-works/pi/issues/5418))。 - 修复了 GitHub 发布说明和交互式更新日志链接，使其能正确解析包相对文档 URL ([#5516](https://github.com/earendil-works/pi/issues/5516))。 - 修复了 CLI 帮助和版本输出，包括普通重定向的 `--help`/`--version` 输出，并简化了 `list`/`config` 帮助文本。 - 修复了从临时会话执行 `/new` 的问题，确保新建会话保持为临时会话，而非默认持久化 ([#5045](https://github.com/earendil-works/pi/issues/5045))。 - 澄清了自定义模型文档，说明 `name` 和 `modelOverrides.name` 不会替换页脚或主模型列表中的模型 ID ([#4841](https://github.com/earendil-works/pi/issues/4841))。

### New Features - **Claude Fable 5** - Claude Fable 5 is now available on the Anthropic and Amazon Bedrock providers, with adaptive thinking and `xhigh` effort support. - **Prompt template defaults** - Prompt templates can use default positional arguments such as `${1:-7}` for optional values. See [Prompt Template Arguments](https://github.com/earendil-works/pi/blob/v0.79.1/packages/coding-agent/docs/prompt-templates.md#arguments). - **Configurable project trust defaults** - `defaultProjectTrust` lets users choose whether unresolved project trust asks, always trusts, or never trusts by default, and extensions can inspect effective trust decisions. See [Project Trust](https://github.com/earendil-works/pi/blob/v0.79.1/packages/coding-agent/docs/security.md#project-trust) and [`ctx.isProjectTrusted()`](https://github.com/earendil-works/pi/blob/v0.79.1/packages/coding-agent/docs/extensions.md#ctxisprojecttrusted). - **Natural extension autocomplete triggers** - Extension autocomplete providers can declare trigger characters such as `#` or `$` so suggestions open without slash-command prefixes. See [Autocomplete Providers](https://github.com/earendil-works/pi/blob/v0.79.1/packages/coding-agent/docs/extensions.md#autocomplete-providers). ### Added - Added default-value expansion for prompt template positional arguments, e.g. `${1:-7}` ([#5553](https://github.com/earendil-works/pi/pull/5553) by [@dannote](https://github.com/dannote)). - Added `areExperimentalFeaturesEnabled` feature guard to allow users to opt in to early features ([#5547](https://github.com/earendil-works/pi/pull/5547) by [@vegarsti](https://github.com/vegarsti)). - Added `ctx.isProjectTrusted()` for extensions to observe the effective project trust decision, including temporary trust decisions ([#5523](https://github.com/earendil-works/pi/issues/5523)). - Added a global `defaultProjectTrust` setting to choose whether unresolved project trust asks, always trusts, or never trusts by default. - Added extension autocomplete trigger character support for `ctx.ui.addAutocompleteProvider()` wrappers ([#4703](https://github.com/earendil-works/pi/issues/4703)). - Added Claude Fable 5 model support inherited from `@earendil-works/pi-ai` for the Anthropic and Amazon Bedrock providers, with adaptive thinking and `xhigh` effort support. ### Fixed - Fixed inherited Amazon Bedrock inference profile ARN region resolution to prefer the ARN's embedded region over `AWS_REGION` ([#5527](https://github.com/earendil-works/pi/pull/5527) by [@AJM10565](https://github.com/AJM10565)). - Fixed inherited IME hardware cursor positioning while slash-command autocomplete is visible ([#5283](https://github.com/earendil-works/pi/pull/5283) by [@smoosex](https://github.com/smoosex)). - Fixed inherited z.ai thinking-off requests to send the provider's `thinking: { type: "disabled" }` compatibility parameter ([#5330](https://github.com/earendil-works/pi/issues/5330)). - Fixed inherited OpenCode completions model metadata to send explicit `maxTokens` as `max_tokens` ([#5331](https://github.com/earendil-works/pi/issues/5331)). - Fixed inherited Moonshot Kimi thinking-off requests to send the provider's `thinking: { type: "disabled" }` compatibility parameter ([#5531](https://github.com/earendil-works/pi/issues/5531)). - Fixed inherited Azure OpenAI Responses requests to disable server-side response storage ([#5530](https://github.com/earendil-works/pi/issues/5530)). - Fixed inherited Azure GPT-5.4 and GPT-5.5 context window metadata to 1,050,000 tokens, matching Azure Foundry deployments instead of OpenAI's 272k limit ([#5559](https://github.com/earendil-works/pi/issues/5559)). - Fixed inherited OpenAI and Azure GPT-5 Pro `maxTokens` metadata to 128,000, correcting an upstream value that duplicated the input sub-limit as the output limit ([#5559](https://github.com/earendil-works/pi/issues/5559)). - Fixed inherited prompt history navigation to restore the current draft when returning from history browsing ([#5494](https://github.com/earendil-works/pi/issues/5494)). - Fixed inherited wrapping for mixed Latin and CJK text so unspaced CJK runs can break at grapheme boundaries without leaving large trailing gaps ([#5495](https://github.com/earendil-works/pi/issues/5495)). - Fixed extension OAuth login prompts to keep previous submitted prompt rows stable instead of mirroring the active input value ([#5433](https://github.com/earendil-works/pi/issues/5433)). - Fixed `/reload` to apply updated `steeringMode` and `followUpMode` settings to the current session ([#5377](https://github.com/earendil-works/pi/issues/5377)). - Fixed invalid `models.json` syntax to skip startup config migrations and report the normal file-path-aware models error instead of a raw JSON parse stack trace ([#5418](https://github.com/earendil-works/pi/issues/5418)). - Fixed GitHub release notes and interactive changelog links to resolve package-relative documentation URLs correctly ([#5516](https://github.com/earendil-works/pi/issues/5516)). - Fixed CLI help and version output, including plain redirected `--help`/`--version` output and simplified `list`/`config` help text. - Fixed `/new` from ephemeral sessions to keep the new session ephemeral instead of persisting it by default ([#5045](https://github.com/earendil-works/pi/issues/5045)). - Clarified custom model docs that `name` and `modelOverrides.name` do not replace model IDs in the footer or primary model lists ([#4841](https://github.com/earendil-works/pi/issues/4841)).