发布日期: 2026-09-04
版本号: v0.85.0

本次更新引入了Claude思考过程持久化支持、全屏对话记录控制以及可恢复的内存会话等新功能，同时新增了包括会话管理、模型参数渲染和交互优化在内的多项特性。改进方面主要涉及流式处理指示器和搜索性能的优化，修复了涵盖系统兼容性、模型支持、会话管理、工具交互及终端处理在内的多个问题，提升了整体稳定性和用户体验。

更新内容 （中文）

新功能

  • 持久化Claude思维力度 — 支持的Anthropic传输协议可保存每轮交互的思维力度设置，并能在符号化思维不匹配时安全恢复。参见模型配置。
  • 全屏转录控制 — 在滚动的转录界面中可直接跳转至最新消息，并使用内嵌的工作状态指示器。参见终端UI全屏视口。
  • 可恢复的内存会话 — 通过SDK恢复外部存储的会话条目。参见会话管理。

新增

  • 新增SessionManager.inMemory()支持，用于恢复外部管理的会话条目（#8980 by @y-nk）。
  • 新增继承的OpenAI兼容vllmPriority和supportsMaxOutputTokens模型设置，用于vLLM调度器优先级和OpenAI响应输出token限制（#9004 by @AppleDannyClegg，#8941 by @scturtle）。
  • 新增关系代数连接符号的继承LaTeX渲染支持（#9050 by @haoqixu）。
  • 在全屏转录界面滚动时新增可点击的"跳转至最新消息"标签，配合altScreen.bottom快捷键使用（#9080 by @rwachtler）。

变更

  • 将流式工作状态指示器移至默认编辑器边框，并使其默认旋转动画和标签与思维级别边框颜色匹配。自定义编辑器保留独立指示器，除非主动选择嵌入（#8799 by @cristinaponcela）。
  • 通过缓存未变更的搜索结果、索引ASCII连续字符段并将高亮处理限制于可见匹配项，降低了继承的全屏转录界面在大型转录文本中的搜索延迟（#8800 by @cristinaponcela）。

修复

  • 修复了Linux musl系统上受管理的fd和ripgrep下载问题（#9070 by @Charlie0113-T）。
  • 从/model列表中移除了不可用的继承Grok Build 0.1模型（#9093 by @Jaaneek）。
  • 修复了继承的提供商流发出不兼容事件序列和自定义工具调用增量的问题。
  • 恢复了@earendil-works/pi-coding-agent/client兼容性入口点。
  • 修复了继承的Qwen Token Plan Individual目录，现在包含Qwen3.8 Flash（#9021）。
  • 修复了继承的OpenAI Codex SSE解析问题，现在可处理后面不跟空行的终端事件（#9047）。
  • 修复了继承的GitHub Copilot Claude Fable 5请求问题，现在可发送所选推理级别（#8961）。
  • 修复了继承的Baseten GLM-5.2模型错误宣称支持图像输入的问题（#8293 by @Panoplos）。
  • 修复了当Bash是唯一启用工具时技能不可用的问题（#8552 by @xl0）。
  • 修复了并发会话共享时相互覆盖的问题（#8613 by @wutongyuonce）。
  • 修复了图像方向检测在非EXIF APP1段后跳过EXIF数据的问题（#8616 by @wutongyuonce）。
  • 修复了导入会话覆盖同名现有会话的问题（#8985 by @wutongyuonce）。
  • 修复了会话分支丢失压缩边界的问题（#8990 by @acmerfight）。
  • 修复了活动轮次结算前的内存会话分支问题（#8937 by @acmerfight）。
  • 修复了继承的Fireworks GLM模型使用错误API适配器的问题。
  • 修复了继承的NO_PROXY对根域和子域的匹配问题（#8737 by @MeiSiristhebest）。
  • 修复了bash、edit、find、grep、ls、read和write工具忽略ctx.cwd的问题（#8627 by @vmizg）。
  • 修复了在拒绝SIGWINCH自信号的受限seccomp策略下继承的终端启动问题（#8898 by @bartlomiejkida）。
  • 修复了继承的Zed终端图像能力检测问题（#8828 by @Perlence）。
  • 修复了拖拽选择在全屏编辑器中持续延伸的问题。
  • 修复了受管理的fd和ripgrep下载依赖GitHub Releases API的问题（#8708 by @Terminator666666）。
  • 修复了当推理消耗前2048个token输出上限时分支摘要失败的问题（#8845）。
  • 修复了写入工具将UTF-16代码单元计数误报为字节计数的问题，已移除误导性计数（#8979）。
  • 通过使用CONNECT隧道传输，修复了代理的纯HTTP提供商请求在工具调用后挂起的问题（#8134）。
  • 修复了RPC abort在未取消进行中的手动压缩时即报告成功的问题（#8920）。

更新内容 （原始）

New Features

  • Persistent Claude thinking effort — Supported Anthropic transports preserve per-turn effort and recover safely from signed-thinking mismatches. See Model Configuration.
  • Fullscreen transcript controls — Jump to the latest message from a scrolled transcript and use the embedded working indicator. See TUI Fullscreen Viewport.
  • Restorable in-memory sessions — Resume externally stored session entries through the SDK. See Session Management.

Added

  • Added SessionManager.inMemory() support for restoring externally managed session entries (#8980 by @y-nk).
  • Added inherited OpenAI-compatible vllmPriority and supportsMaxOutputTokens model settings for vLLM scheduler priority and OpenAI Responses output-token limits (#9004 by @AppleDannyClegg, #8941 by @scturtle).
  • Added inherited LaTeX rendering for relational algebra join symbols (#9050 by @haoqixu).
  • Added a clickable “Jump to latest message” label with the tui.altScreen.bottom shortcut to the fullscreen transcript while it is scrolled up (#9080 by @rwachtler).

Changed

  • Moved the streaming working indicator into the default editor border and matched its default spinner and label to the thinking-level border color. Custom editors retain the standalone indicator unless they opt in to embedding it (#8799 by @cristinaponcela).
  • Reduced inherited fullscreen transcript search latency on large transcripts by caching unchanged search results, indexing ASCII runs, and limiting highlight work to visible matches (#8800 by @cristinaponcela).

Fixed

  • Fixed managed fd and ripgrep downloads on Linux musl systems (#9070 by @Charlie0113-T).
  • Removed the unavailable inherited Grok Build 0.1 model from /model (#9093 by @Jaaneek).
  • Fixed inherited provider streams emitting incompatible event sequences and custom tool-call deltas.
  • Restored the @earendil-works/pi-coding-agent/client compatibility entry point.
  • Fixed the inherited Qwen Token Plan Individual catalog to include Qwen3.8 Flash (#9021).
  • Fixed inherited OpenAI Codex SSE parsing to process terminal events that are not followed by a blank line (#9047).
  • Fixed inherited GitHub Copilot Claude Fable 5 requests so selected reasoning levels are sent (#8961).
  • Fixed inherited Baseten GLM-5.2 models incorrectly advertising image input support (#8293 by @Panoplos).
  • Fixed skills being unavailable when Bash is the only enabled tool (#8552 by @xl0).
  • Fixed concurrent session shares overwriting one another (#8613 by @wutongyuonce).
  • Fixed image orientation detection skipping EXIF data after non-EXIF APP1 segments (#8616 by @wutongyuonce).
  • Fixed imported sessions overwriting an existing session with the same filename (#8985 by @wutongyuonce).
  • Fixed session forks losing their compaction boundary (#8990 by @acmerfight).
  • Fixed in-memory session forks before an active turn settled (#8937 by @acmerfight).
  • Fixed inherited Fireworks GLM models using the wrong API adapter.
  • Fixed inherited NO_PROXY matching for root domains and subdomains (#8737 by @MeiSiristhebest).
  • Fixed bash, edit, find, grep, ls, read, and write tools ignoring ctx.cwd (#8627 by @vmizg).
  • Fixed inherited terminal startup under restricted seccomp policies that reject the SIGWINCH self-signal (#8898 by @bartlomiejkida).
  • Fixed inherited Zed terminal image capability detection (#8828 by @Perlence).
  • Fixed drag selection continuing over the fullscreen editor.
  • Fixed managed fd and ripgrep downloads requiring the GitHub Releases API (#8708 by @Terminator666666).
  • Fixed branch summaries failing when reasoning consumes the previous 2048-token output cap (#8845).
  • Fixed the write tool reporting UTF-16 code-unit counts as byte counts by removing the misleading count (#8979).
  • Fixed proxied plain-HTTP provider requests hanging after a tool call by tunneling them with CONNECT (#8134).
  • Fixed RPC abort reporting success without cancelling an in-progress manual compaction (#8920).

下载链接