精选75pi coding agent(GitHub Releases)AI 编程与模型
Pi v0.84.4:新增终端能力覆盖、扩展 UI 提示事件与 RPC 队列清理,修复多项问题
v0.84.4
New Features
新特性
- Terminal capability overrides — Override detected terminal hyperlink, image, and truecolor support. See Capability Overrides.
- Extension UI prompt events — Integrations can distinguish active agent work from time spent waiting for ctx.ui prompts. See Extension UI prompt events.
- RPC queue clearing — Retrieve and clear queued steering and follow-up messages with clear_queue. See RPC clear_queue.
- Fullscreen selection copy controls — Disable automatic selection copying in fullscreen mode and use Ctrl+X to copy the active selection. See UI & Display.
- DeepSeek V4 Flash Vision (experimental) — Use the vision-capable model through the built-in DeepSeek provider. See API Keys.
- 终端能力覆盖 — 覆盖检测到的终端超链接、图像和真彩色支持。参见能力覆盖。
- 扩展UI提示事件 — 集成可以区分活跃的代理工作与等待ctx.ui提示的时间。参见扩展UI提示事件。
- RPC队列清除 — 使用clear_queue检索并清除排队的转向和后续消息。参见RPC clear_queue。
- 全屏选择复制控制 — 在全屏模式下禁用自动选择复制,并使用Ctrl+X复制活动选择。参见UI与显示。
- DeepSeek V4 Flash Vision(实验性)— 通过内置的DeepSeek提供商使用支持视觉的模型。参见API密钥。
Added
新增
- Added ui_prompt_start and ui_prompt_end extension events so host integrations can distinguish active agent work from waiting on user-facing ctx.ui prompts (#8355 by @cristinaponcela).
- Added detectSupportedImageMimeTypeFromFile() to the public library exports (#8600 by @xl0).
- Added inherited experimental vision-capable deepseek-v4-flash-vision-exp model support.
- Added transcript usage notices for compaction and branch summaries when cache miss notices are enabled.
- Added RPC clear_queue to retrieve and remove queued steering and follow-up messages (#8432).
- Added environment variables and advanced settings for overriding auto-detected terminal hyperlink, image, and truecolor capabilities (#8665).
- Added fullscreenCopyOnSelect to disable automatic fullscreen selection copy; when disabled, Ctrl+X copies the active text selection before falling back to the last assistant message, while /tree still copies the selected message (#7720).
- 添加了ui_prompt_start和ui_prompt_end扩展事件,以便宿主集成可以区分活跃的代理工作与等待用户界面的ctx.ui提示(#8355,由@cristinaponcela贡献)。
- 在公共库导出中添加了detectSupportedImageMimeTypeFromFile()(#8600,由@xl0贡献)。
- 添加了继承的实验性支持视觉的deepseek-v4-flash-vision-exp模型。
- 当启用缓存未命中通知时,为压缩和分支摘要添加了转录使用通知。
- 添加了RPC clear_queue以检索并移除排队的转向和后续消息(#8432)。
- 添加了环境变量和高级设置,用于覆盖自动检测的终端超链接、图像和真彩色能力(#8665)。
- 添加了fullscreenCopyOnSelect以禁用自动全屏选择复制;禁用后,Ctrl+X复制活动文本选择,然后回退到最后一条助手消息,而/tree仍复制所选消息(#7720)。
Fixed
修复
- Fixed toggling thinking visibility clearing partial output from running Bash tools (#8611).
- Fixed Windows shell aborts crashing Pi when taskkill.exe is unavailable on PATH (#6596).
- Fixed resumed sessions corrupting the next appended entry when their JSONL file lacks a trailing newline (#8345).
- Fixed extension messages sent with triggerTurn: false while the agent is running being inserted between a tool call and its result, which made providers that validate message order reject the replayed history. They are now appended once the turn's tool results are in (#8537).
- Fixed compaction and branch summaries forcing toolChoice: "none" (#8649, #8638).
- Fixed large tool results crossing the auto-compaction threshold being sent to the provider before compaction. Pi now compacts between tool execution and the next assistant response in the same run, and restores interactive progress when that run resumes (#6879).
- Fixed Google Vertex requests failing with HttpsProxyAgent is not a constructor when the bundled Node.js runtime uses an HTTP(S) proxy (#8610).
- Fixed saving a default model from a non-empty model scope so it remains available in that scope.
- Fixed inherited @ file autocomplete ranking to prefer direct and shallower matches over similarly ranked nested paths (#8669).
- Fixed inherited OpenAI-compatible streams serializing thinking signatures repeatedly during streaming (#8671).
- Fixed inherited main-screen rendering crashing when image-heavy output exceeded V8's string length limit (#8028).
- Fixed inherited fullscreen double-click word selection splitting paths and kebab-case tokens on / and - (#8676).
- Fixed inherited Cloudflare AI Gateway catalogs omitting supported workers-ai/* passthrough models.
- Fixed inherited OpenAI-compatible reasoning replay to merge consecutive streamed text and summary reasoning_details deltas.
- Fixed inherited OpenRouter reasoning controls so reasoning-mandatory models do not receive effort: "none" (#8614 by @davidbrai).
- Fixed inherited OpenAI-compatible Chat Completions ignoring an explicitly requested toolChoice when no tools are defined.
- Fixed inherited fragmented Mistral tool calls splitting when continuation chunks omit the tool-call ID (#8387).
- 修复了切换思考可见性时清除运行中Bash工具的部分输出问题(#8611)。
- 修复了当taskkill.exe在PATH中不可用时,Windows shell中止导致Pi崩溃的问题(#6596)。
- 修复了恢复的会话在其JSONL文件缺少尾部换行时损坏下一个附加条目的问题(#8345)。
- 修复了代理运行时发送的triggerTurn: false的扩展消息被插入到工具调用及其结果之间,导致验证消息顺序的提供商拒绝重放历史的问题。现在它们会在该轮工具结果就绪后追加(#8537)。
- 修复了压缩和分支摘要强制toolChoice: "none"的问题(#8649, #8638)。
- 修复了大型工具结果在自动压缩阈值之前被发送给提供者的问题。Pi 现在在同一运行中的工具执行和下一次助手响应之间进行压缩,并在该运行恢复时恢复交互进度 (#6879)。
- 修复了当捆绑的 Node.js 运行时使用 HTTP(S) 代理时,Google Vertex 请求因 HttpsProxyAgent 不是构造函数而失败的问题 (#8610)。
- 修复了从非空模型作用域保存默认模型,使其在该作用域中保持可用的问题。
- 修复了继承的 @ 文件自动补全排序,优先选择直接和较浅的匹配,而不是相似排名的嵌套路径 (#8669)。
- 修复了继承的 OpenAI 兼容流在流式传输期间重复序列化思考签名的问题 (#8671)。
- 修复了继承的主屏幕渲染在图像密集型输出超过 V8 字符串长度限制时崩溃的问题 (#8028)。
- 修复了继承的全屏双击单词选择在 / 和 - 上拆分路径和 kebab-case 标记的问题 (#8676)。
- 修复了继承的 Cloudflare AI 网关目录遗漏支持的 workers-ai/* 直通模型的问题。
- 修复了继承的 OpenAI 兼容推理重放,以合并连续的流式文本和摘要 reasoning_details 增量。
- 修复了继承的 OpenRouter 推理控制,使强制推理模型不会收到 effort: "none" (#8614,感谢 @davidbrai)。
- 修复了继承的 OpenAI 兼容聊天完成在未定义工具时忽略显式请求的 toolChoice 的问题。
- 修复了继承的 Mistral 工具调用在连续块省略工具调用 ID 时分裂的问题 (#8387)。
更进一步:量化金融体系
看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力