- Select the Agent directly in the new-conversation composer while preserving Agent-specific drafts, model choices, and workspace defaults
- Restored ACP composer preparation, automatically created or recovered the Chats workspace, and kept composer controls and option menus usable in narrow windows
- Fixed Code Mode access to subagent tools
- Added the CloudGPU, Runcrate, AtmoRouter, apimodels.app, and AI Stupid Level providers with compatible chat model filtering
- Added Webz news search, EvoLink media generation, and deed.page hosting MCP presets, plus an optional Baizhi cloud browser plugin example
- Fixed MCP OAuth issuer matching and callback handling while preserving existing client registrations
- Refreshed the bundled model and ACP catalogs
- 在新对话输入框中直接选择 Agent，并保留各 Agent 的草稿、模型选择和工作区默认值
- 恢复 ACP 输入框预准备，自动创建或恢复 Chats 工作区，并改善窄窗口中的输入框控件和选项菜单
- 修复 Code Mode 无法调用子代理工具的问题
- 新增 CloudGPU、Runcrate、AtmoRouter、apimodels.app 和 AI Stupid Level 服务商，并筛选兼容的聊天模型
- 新增 Webz 新闻搜索、EvoLink 媒体生成和 deed.page 托管 MCP 预设，以及可选的百智云浏览器插件示例
- 修复 MCP OAuth 授权服务地址匹配与回调处理，并保留已有客户端注册信息
- 刷新内置模型与 ACP 目录
- Simplified sidebar navigation and consolidated conversation search in global search, with matching conversation titles shown before message results
- Fixed global search selecting results while confirming text with an input method, and loaded bundled icons before rendering the interface
- Removed built-in RTK command rewriting, its runtime, and the RTK usage dashboard
- Updated Electron to 43.8.3, bundled Node.js to 24.22.1, uv to 0.13.5, and cloudflared to 2026.10.3
- Refreshed the bundled model and ACP catalogs
- 简化侧栏导航，将会话搜索统一到全局搜索，优先展示标题匹配的会话，再展示消息结果
- 修复全局搜索中使用输入法确认文字时误选结果的问题，并在界面渲染前加载内置图标
- 移除内置 RTK 命令改写、运行时与 RTK 用量面板
- 将 Electron 升级至 43.8.3，内置 Node.js 升级至 24.22.1、uv 升级至 0.13.5、cloudflared 升级至 2026.10.3
- 刷新内置模型与 ACP 目录
- Refreshed the desktop interface in light and dark themes, with a unified sidebar, integrated composer controls, searchable settings navigation, and compact ACP Agent details
- Open the workspace and browser before sending the first message, keeping their state after submission
- Copy session references from the conversation menu and paste them into another conversation with source validation
- Configure an Agent's default tool mode for new conversations and scheduled tasks that follow its configuration
- Added a hover wave to the message minimap with readable, scrollable previews
- Preserved unrelated ACP drafts when confirming a removed Agent during registry reloads, canceled obsolete confirmations, and improved floating-window behavior, Markdown tables, and context-usage visibility
- Refreshed the bundled model and ACP catalogs
- 刷新桌面端明暗主题界面，统一侧栏与输入框控制，支持搜索设置导航，并以紧凑列表和详情页管理 ACP Agent
- 发送首条消息前即可打开工作区与浏览器，发送后保留已有状态
- 从会话菜单复制会话引用并粘贴到其他对话，插入前校验来源有效性
- 为 Agent 设置默认工具模式，新对话及跟随 Agent 配置的定时任务会继承该设置
- 消息地图新增悬停波浪效果，提供易读、可滚动的消息预览
- ACP 目录刷新时，确认移除 Agent 仅丢弃该 Agent 的草稿，并撤销过时确认；同时改善悬浮窗行为、Markdown 表格和上下文用量显示
- 刷新内置模型与 ACP 目录
- Added the LiteLLM proxy provider with model capability discovery and virtual-key usage and budget reporting
- Added an optional Keenable web search MCP preset
- Completed French interface and native menu translations
- 新增 LiteLLM 代理服务商，支持识别模型能力以及查看虚拟密钥用量和预算
- 新增可选的 Keenable 网页搜索 MCP 预设
- 补全法语界面与原生菜单翻译
- Added the Atlas Cloud model provider
- Fixed GitHub Copilot session authentication, validated access before saving login credentials, and prevented requests from using another account after an account switch
- Updated the Codex model list with GPT-6 and GPT Image 2.5 models, keeping supported image models available when catalog metadata is missing
- Codex media generation now preserves provider failure details and requests sign-in again when credentials expire instead of retrying authentication failures
- Added optional Parallel Search and Sem MCP user-plugin examples
- Restored retries when attaching macOS notarization tickets after temporary connection failures
- Added bounded retries for macOS ticket-service errors during DMG and update ZIP verification, with full failure diagnostics
- Refreshed the built-in model and ACP catalogs
- 新增 Atlas Cloud 模型服务商
- 修复 GitHub Copilot 会话认证，保存登录凭据前验证访问权限，并防止切换账号后请求使用另一账号
- 更新 Codex 模型列表，新增 GPT-6 与 GPT Image 2.5 模型，目录元数据缺失时仍保留支持的图像模型
- Codex 媒体生成保留服务商错误信息，凭据失效时提示重新登录，不再重试认证失败
- 新增可选的 Parallel Search 与 Sem MCP 用户插件示例
- 恢复 macOS 公证票据附加时的重试，临时连接失败后可重新尝试
- DMG 与更新 ZIP 的 macOS 票据服务错误支持有限重试，并保留完整失败日志
- 刷新内置模型与 ACP 目录
- Added the Atlas Cloud model provider
- Fixed GitHub Copilot session authentication, validated access before saving login credentials, and prevented requests from using another account after an account switch
- Updated the Codex model list with GPT-6 and GPT Image 2.5 models, keeping supported image models available when catalog metadata is missing
- Codex media generation now preserves provider failure details and requests sign-in again when credentials expire instead of retrying authentication failures
- Added optional Parallel Search and Sem MCP user-plugin examples
- Restored retries when attaching macOS notarization tickets after temporary connection failures
- Refreshed the built-in model and ACP catalogs
- 新增 Atlas Cloud 模型服务商
- 修复 GitHub Copilot 会话认证，保存登录凭据前验证访问权限，并防止切换账号后请求使用另一账号
- 更新 Codex 模型列表，新增 GPT-6 与 GPT Image 2.5 模型，目录元数据缺失时仍保留支持的图像模型
- Codex 媒体生成保留服务商错误信息，凭据失效时提示重新登录，不再重试认证失败
- 新增可选的 Parallel Search 与 Sem MCP 用户插件示例
- 恢复 macOS 公证票据附加时的重试，临时连接失败后可重新尝试
- 刷新内置模型与 ACP 目录
- Added the Atlas Cloud model provider
- Fixed GitHub Copilot session authentication, validated access before saving login credentials, and prevented requests from using another account after an account switch
- Updated the Codex model list with GPT-6 and GPT Image 2.5 models, keeping supported image models available when catalog metadata is missing
- Codex media generation now preserves provider failure details and requests sign-in again when credentials expire instead of retrying authentication failures
- Added optional Parallel Search and Sem MCP user-plugin examples
- Refreshed the built-in model and ACP catalogs
- 新增 Atlas Cloud 模型服务商
- 修复 GitHub Copilot 会话认证，保存登录凭据前验证访问权限，并防止切换账号后请求使用另一账号
- 更新 Codex 模型列表，新增 GPT-6 与 GPT Image 2.5 模型，目录元数据缺失时仍保留支持的图像模型
- Codex 媒体生成保留服务商错误信息，凭据失效时提示重新登录，不再重试认证失败
- 新增可选的 Parallel Search 与 Sem MCP 用户插件示例
- 刷新内置模型与 ACP 目录
- Added automatic two-way device sync, Codex-compatible Nowledge Mem integration, and a bundled optional Memcode memory plugin
- Reference past conversations in native chats with @ or by dragging from the sidebar, so the agent can look up their content when needed
- File references now show their paths, uploads sit in a collapsible attachment area, and the composer focuses on paste without opening the slash menu on URLs or paths
- Compactly displayed token usage in the message toolbar, and redesigned scheduled tasks into a list-and-detail layout with templates, run history, and a leave guard
- Added a ChatGPT sign-in option for OpenAI, plus search and an enabled-only filter in the connection-test model picker
- Chat and workspace sidebar groups now show five recent conversations at a time, with Show more to load older conversations
- Added inspectable memory evidence with lineage views, a dependent-memory review before editing or deleting, an opt-in judgment model that can prune stale tool results, and retries for failed reflections
- Added support for Lody ACP client extensions, covering elicitation forms, plan and usage reporting, subagent events, and session steering
- Added explicit Save and Cancel actions for API keys and service URLs, allowed custom providers to be saved without testing, and isolated workspace HTML and SVG previews from the app
- Removed the built-in agent plan tool and plan progress panel while keeping existing plan tool records readable
- Added the Cloudflare Workers AI, TypeSafe, Requesty, DemonRoute, FutureInfra, Y-API, Magpie, Opper, and AstrLink providers, plus SkyAccess and Cohesivity MCP server presets
- Hardened skill discovery and worker loading, repaired auto-approve, flattened compatible tool schema intersections, and kept failed edits and references intact through retries, queues, copy, search, and export
- Fixed non-ASCII conversation search, sidebar rows overlapping the header, reasoning effort conflicting with thinking budget, and device sync getting stuck while enabling
- Updated Electron to 43.7.0, bundled Node.js to 24.21.0, improved in-app update-note readability, and refreshed the built-in model and ACP catalogs with dependency security fixes
- 新增设备双向自动同步，以及与兼容 Codex 的 Nowledge Mem 插件集成，并内置可选的 Memcode 记忆插件
- 原生对话支持用 @ 或从侧栏拖入历史会话，让 Agent 按需查阅之前聊过的内容
- 文件引用显示路径，上传文件集中显示在可折叠附件栏中，粘贴时聚焦输入框，斜杠命令菜单不再在 URL 或文件路径上弹出
- 在消息工具栏中紧凑展示 Token 用量，并将定时任务改为列表+详情布局，提供模板、运行历史与离开保护
- 为 OpenAI 增加 ChatGPT 登录选项，服务商连接测试的模型选择器支持搜索和仅显示已启用模型
- 侧栏的 Chat 与工作区分组每次显示五个最近会话，可通过“显示更多”加载更早的会话
- 新增记忆证据检视与依赖记忆复核，支持启用判断模型清理过期工具结果，记忆反思失败后可继续重试
- 支持 Lody ACP 客户端扩展：涵盖 elicitation 表单、计划与用量上报、子代理事件与会话引导
- 修改 API 密钥和服务地址后可明确保存或取消，新建自定义服务商可跳过测试直接保存，并隔离工作区 HTML 和 SVG 预览
- 移除内置 Agent 计划工具与计划进度面板，旧对话中的计划工具记录仍可查看
- 新增 Cloudflare Workers AI、TypeSafe、Requesty、DemonRoute、FutureInfra、Y-API、Magpie、Opper 与 AstrLink 模型服务商，以及 SkyAccess 和 Cohesivity MCP 服务预设
- 加固 Skill 发现与 Worker 加载，修复自动批准与合法工具 schema 被拒绝的问题，编辑失败时保留草稿，消息排队、重试、复制、搜索和导出时也会保留引用
- 修复会话字面搜索中非 ASCII 文本匹配、展开侧栏 Chat 分组时会话行与标题重叠、推理强度与思考预算冲突，以及开启设备同步时一直加载的问题
- 将 Electron 升级至 43.7.0、内置 Node.js 升级至 24.21.0，改善应用内更新日志阅读体验，并刷新内置模型与 ACP 目录及安全相关依赖
- Added the Magpie gateway provider
- Added search and an enabled-only filter to the model picker in provider connection tests
- Chat and workspace sidebar groups now show five recent conversations at a time, with Show more to load older conversations
- Fixed conversation rows moving and overlapping the header when expanding the Chat sidebar group
- 新增 Magpie 网关模型服务商
- 服务商连接测试的模型选择器支持搜索和仅显示已启用模型
- 侧栏的 Chat 与工作区分组每次显示五个最近会话，可通过“显示更多”加载更早的会话
- 修复展开侧栏 Chat 分组时，会话行发生位移并与标题重叠的问题
- Added the Y-API provider and SkyAccess and Cohesivity MCP server presets
- Fixed case-insensitive matching of non-ASCII text in literal conversation searches and kept excerpts aligned with the original text
- Refreshed the built-in provider and model catalog
- 新增 Y-API 模型服务商，以及 SkyAccess 和 Cohesivity MCP 服务预设
- 修复会话字面搜索中非 ASCII 文本的大小写匹配，并确保搜索摘要准确定位原文
- 刷新内置服务商与模型目录
- Reference past conversations in native DeepChat chats with @ or by dragging from the sidebar, so the agent can look up their content when needed
- File references now show their paths to distinguish same-named files, with smoother keyboard selection and IME input in the @ menu
- Uploaded files now appear in a separate, collapsible attachment area, and removing one returns focus to the message input
- Failed edits now keep your draft, and references stay intact through queued messages, retries, copying, searching, and exporting
- Fixed conflicts between reasoning effort and thinking budget, preserved reasoning settings across conversations, and added checks for invalid budget values
- Model settings now update with the catalog, without losing available controls when a background refresh fails
- Fixed device sync getting stuck while enabling it
- Updated the built-in model and ACP catalogs and corrected the TokenLab documentation link
- 原生 DeepChat 对话支持用 @ 或从侧栏拖入历史会话，让 Agent 按需查阅之前聊过的内容
- 文件引用显示路径，方便区分同名文件，并改善 @ 菜单的键盘操作和输入法体验
- 上传文件集中显示在可折叠的附件栏中，删除附件后可直接继续输入
- 编辑保存失败时保留草稿，消息排队、重试、复制、搜索和导出时也会保留引用信息
- 修复推理强度与思考预算冲突、切换对话后设置未保留的问题，并检查预算数值是否有效
- 模型目录更新后，设置选项随之刷新，后台刷新失败也不会让已有选项消失
- 修复开启设备同步时一直加载的问题
- 更新内置模型与 ACP 目录，修正 TokenLab 文档链接
- Removed the built-in agent plan tool and plan progress panel, including ACP plan updates, while keeping existing plan tool records readable
- Added the FutureInfra provider
- Added explicit Save and Cancel actions for API keys and service URLs, with saving separate from connection testing and drafts retained when saving fails
- Allowed custom providers to be saved without testing, and made connection checks use a chosen text model so one successful test does not imply every model is available
- Fixed custom-model edits losing the original model when saving fails and similarly named models sharing enablement status
- Preserved offline model lists, limited filtered batch actions to matching models, and made model controls fit smaller windows
- Fixed failed memory reflections being treated as complete, so invalid model responses can be retried
- Improved update-note readability with formatted headings and lists, a larger reading area, and links that open in the browser
- Isolated workspace HTML and SVG previews from the app so preview scripts cannot access the app's native APIs
- Updated Electron to 43.7.0, bundled Node.js to 24.21.0, and dependencies with security fixes
- Refreshed the bundled model and ACP catalogs
- 移除内置 Agent 计划工具、计划进度面板及 ACP 计划更新，旧对话中的计划工具记录仍可查看
- 新增 FutureInfra 模型服务商
- 修改 API 密钥和服务地址后可明确保存或取消，保存不再依赖连接测试，保存失败时保留已填写的内容
- 新建自定义服务商时可跳过测试直接保存，连接测试可选择具体的文本模型，单个模型测试通过不再被视为所有模型都可用
- 修复编辑自定义模型时保存失败可能丢失原模型的问题，避免名称相近的模型互相影响启用状态
- 保留离线模型列表，筛选后的批量操作只影响匹配的模型，并改善小窗口下模型操作区的显示
- 修复记忆反思失败后被误认为已完成的问题，模型返回无效内容时可继续重试
- 改善应用内更新日志的阅读体验，正确显示标题和列表，扩大阅读区域，并在浏览器中打开链接
- 隔离工作区 HTML 和 SVG 预览，防止预览脚本调用应用的原生接口
- 将 Electron 升级至 43.7.0、内置 Node.js 升级至 24.21.0，并升级相关依赖以修复安全问题
- 刷新内置模型与 ACP 目录
- Added a dependent-memory review before editing or deleting a memory, so affected reflections can be inspected and archived explicitly
- Made memory evidence inspectable with paged lineage views that show derivation sources and derived claims
- Added the DemonRoute provider
- Added support for Lody ACP client extensions, covering elicitation forms, plan and usage reporting, subagent events, and session steering
- Bundled the optional Memcode memory plugin across all release targets
- Refreshed the bundled model and ACP catalogs
- 新增依赖记忆复核：编辑或删除记忆前可查看受影响的反思记忆，并显式归档所选项目
- 新增记忆证据检视：以分页血缘视图展示来源记忆与派生记忆
- 新增 DemonRoute Provider
- 支持 Lody ACP 客户端扩展：涵盖 elicitation 表单、计划与用量上报、子代理事件与会话引导
- 在所有发布目标中内置可选的 Memcode 记忆插件
- 刷新内置模型与 ACP 目录
- Added the Requesty provider and a ChatGPT sign-in option for OpenAI
- Focused the composer on paste and kept the slash menu from opening on URLs or file paths
- Redesigned scheduled tasks into a list-and-detail layout with templates, run history, and a leave guard
- Repaired auto-approve so reviews follow each tool's execution contract, and closing the last approval no longer leaves a session stuck generating
- Flattened compatible scalar schema intersections so valid tool schemas convert instead of being rejected
- 新增 Requesty Provider，并为 OpenAI 增加 ChatGPT 登录选项
- 粘贴时聚焦输入框，斜杠命令菜单不再在 URL 或文件路径上弹出
- 重设计时任务为列表+详情布局，提供模板、运行历史与离开保护
- 修复自动批准：按工具执行契约审查，关闭最后一项批准不再卡住生成中的会话
- 展平兼容的标量 schema 交集，避免合法工具 schema 被拒绝
- Added automatic two-way device sync and integration with the Codex-compatible Nowledge Mem plugin
- Added Cloudflare Workers AI and TypeSafe providers, plus an opt-in judgment model that can prune stale tool results to reduce context usage
- Compactly displayed token usage in the message toolbar
- Hardened skill discovery and worker loading against malformed caches and unsafe manifest targets
- 新增设备双向自动同步，以及与兼容 Codex 的 Nowledge Mem 插件集成
- 新增 Cloudflare Workers AI 和 TypeSafe Provider，并支持启用判断模型来清理过期工具结果、减少上下文占用
- 在消息工具栏中紧凑展示 Token 用量
- 加固 Skill 发现与 Worker 加载流程，防范异常缓存和不安全的清单目标
- Added an Open With picker for workspace files, with detected editors and terminals, remembered preferences, and system-default fallback
- Added installation and management of Codex-compatible user plugin packages from Git repositories, ZIP archives, and local folders, including Skills, supported context hooks, and MCP configurations
- Added a scroll-to-latest pill and message map that counts the messages below the viewport and jumps straight to a chosen one
- Added type-to-focus so typing anywhere in the chat reaches the composer without dropping the keystroke
- Added Tibetan, Uyghur, and Mongolian locales and full keyboard navigation across chat, files, panels, settings, and setup flows
- Added a Cloudflare Tunnel host sync endpoint for device pairing, snapshots, and transfers, and scoped plugin settings windows to the owning plugin
- Added the API Route, Cheaper Inference, and AnonRouter providers, plus You.com, Serply, and Baizhi MCP server examples
- Discovered workspace skills from the current project directory and preserved skill bodies when resuming a session
- Restored DeepSeek Responses tool streaming, native web search, and follow-up replay, and made delegated sessions inherit the parent tool mode
- Hardened OAuth credential storage and provider credential validation, refreshed provider settings without UI lag, and reaped orphaned child processes through a shared registry
- Repaired memory recall, extraction, atomicity, and recovery, hardened recalled text against forged prompt markers, and clarified that forgetting a memory archives it
- Reduced stalls and background load with asynchronous backup reads under a WAL read lock, coalesced model discovery, batched preference lookups, canceled embeddings, and faster Tape reads and message rendering
- Restored partially migrated legacy databases, preserved session recency, cached generated image previews, and brought back macOS browser preview capture
- Upgraded dependencies with security patches, capped Electron at 43.6.0, upgraded markstream-vue to 2.0.11, and refreshed the built-in model and ACP catalogs
- 新增工作区文件“打开方式”选择器，支持检测编辑器与终端、记住所选应用，并在不可用时回退到系统默认应用
- 新增兼容 Codex 的用户插件包安装与管理，支持 Git 仓库、ZIP 压缩包和本地文件夹，并可选择导入 Skills、受支持的上下文钩子及 MCP 配置
- 新增“回到最新消息”浮标与消息地图，可显示视口下方的消息数量，并直接跳转到指定消息
- 新增输入即聚焦：在聊天界面任意位置输入都会进入输入框，且不会丢失该次按键
- 新增藏文、维吾尔文与蒙古文语言，并为聊天、文件、面板、设置与初始化流程启用完整键盘导航
- 新增 Cloudflare Tunnel 主机端同步端点，支持设备配对、快照与传输；并将插件设置窗口限定在所属插件内
- 新增 API Route、Cheaper Inference 与 AnonRouter Provider，以及 You.com、Serply 与 Baizhi MCP 服务示例
- 支持从当前项目目录发现工作区 Skills，并在恢复会话时保留 Skill 正文
- 恢复 DeepSeek Responses 的工具流式传输、原生网页搜索与后续对话回放，并使委派会话继承父会话的工具模式
- 强化 OAuth 凭据存储与 Provider 凭据校验，刷新 Provider 设置不再出现 UI 卡顿，并通过共享注册表回收孤儿子进程
- 修复记忆召回、提取、原子性与恢复问题，强化召回文本对伪造提示词标记的防护，并明确遗忘记忆会将其归档且可恢复
- 通过 WAL 读锁下的异步备份读取、模型发现请求合并、项目偏好批量读取、嵌入请求取消，以及更快的 Tape 读取与消息渲染，减少卡顿与后台负载
- 恢复部分迁移的旧版数据库，保留会话最近活动时间，缓存生成的图片预览，并恢复 macOS 浏览器预览画面
- 升级依赖并修复安全公告，将 Electron 上限固定在 43.6.0，升级 markstream-vue 至 2.0.11，并刷新内置模型与 ACP 目录
- Reaped orphaned child processes via a shared registry that attests identity with pid start time and command-line fingerprint, guarding against pid reuse
- Refreshed provider settings without UI lag and limited provider debug logs to development builds
- Simplified memory service boundaries by separating bounded merging from maintenance scheduling
- Upgraded dependencies and capped Electron at 43.6.0 to preserve compatibility
- Upgraded markstream-vue to 2.0.11
- 通过共享子进程注册表回收孤儿子进程，使用启动时间与命令行指纹进行身份校验，规避 pid 复用带来的误杀
- 刷新 Provider 设置不再出现 UI 卡顿，并将 Provider 调试日志限制在开发版输出
- 拆分记忆服务边界，将有界合并与维护调度分离
- 升级依赖并将 Electron 上限固定在 43.6.0 以保持兼容性
- 升级 markstream-vue 至 2.0.11
- Restored the live assistant response when resuming an Agent conversation
- Preserved skill bodies when resuming a session
- Discovered workspace skills from the current project directory
- Enabled full keyboard navigation across chat, files, panels, settings, and setup flows
- 恢复 Agent 对话恢复时的实时助手响应
- 恢复会话时保留 Skill 正文内容
- 从当前项目目录发现工作区 Skills
- 为聊天、文件、面板、设置与初始化流程启用完整键盘导航
- Simplified tool, reasoning, and compaction activity with persistent expand/collapse state, readable historical plans, and restored parent-session navigation
- Preserved workspace conversation history and pagination, kept Agent filters stable, and reused the workspace's latest Agent for new conversations
- Restored browser preview frames and screenshots on macOS
- Repaired vector recall recovery, prevented repeated memory extraction when forking conversations, recovered invalid memory records, and coordinated background maintenance with database operations
- Improved memory recall on slow networks with adaptive timeouts and bounded embedding input, reduced repeated searches, and repaired missing vectors without rebuilding healthy data
- Hardened recalled text against forged prompt markers, stopped extracting memories from Subagent task instructions, and clarified that forgetting a memory archives it for recovery
- Restored partially migrated legacy databases and preserved conversation recency during migration
- Reduced duplicate model discovery requests, project preference lookups, and plugin history scans; canceled abandoned embedding requests and released download probe responses
- Refreshed the built-in model catalog
- 简化工具、思考与上下文压缩活动展示，保留展开与折叠状态、提供可读的历史计划，并恢复返回父会话的导航
- 保留工作区对话历史与分页状态，保持 Agent 筛选稳定，并为新对话沿用工作区最近使用的 Agent
- 恢复 macOS 浏览器预览画面与截图
- 修复向量召回恢复、分叉对话重复提取记忆及异常记忆记录问题，并协调后台维护与数据库操作
- 通过自适应超时和嵌入输入长度限制改善慢速网络下的记忆召回，减少重复搜索，并在保留健康数据的同时修复缺失向量
- 强化召回文本对伪造提示词标记的防护，停止从 Subagent 任务指令中提取记忆，并明确遗忘记忆会将其归档且可恢复
- 恢复部分迁移的旧版数据库，并在迁移时保留对话最近活动时间
- 减少重复模型发现请求、项目偏好读取和插件历史扫描；取消已放弃的嵌入请求，并释放下载探测响应
- 刷新内置模型目录
- Added installation and management of Codex-compatible user plugin packages from Git repositories, ZIP archives, and local folders, with selectable Skills, supported context hooks, and MCP configurations
- Preserved new conversation drafts across Agent switches and removed drafts when their Agent is deleted
- Increased the pending message queue limit to 10 and restored queue capacity after messages leave the queue
- Restored prompt editor scrolling and desktop notifications, and added error feedback when saving the tool mode fails
- Improved conversation history recovery and prevented duplicated usage totals when forking sessions
- Refreshed the built-in model and ACP catalogs
- 新增兼容 Codex 的用户插件包安装与管理，支持 Git 仓库、ZIP 压缩包和本地文件夹，并可选择导入 Skills、受支持的上下文钩子及 MCP 配置
- 在切换 Agent 时保留新对话草稿，并在删除 Agent 时清理对应草稿
- 将待处理消息队列上限提升至 10 条，并在消息离开队列后恢复可用容量
- 恢复提示词编辑器滚动与桌面通知，并在工具模式保存失败时显示错误反馈
- 改进对话历史恢复，并修复分叉会话重复累计用量的问题
- 刷新内置模型与 ACP 目录
- Added an Open With picker for workspace files, with detected editors and terminals, remembered preferences, and system-default fallback
- Restored DeepSeek Responses tool streaming, native web search, and follow-up replay
- Added visible waiting feedback during provider retry delays
- Made delegated sessions inherit the parent tool mode
- Improved agent turn performance and session consistency with faster Tape reads and atomic message and fact writes
- Refreshed the built-in model and ACP catalogs
- 新增工作区文件“打开方式”选择器，支持检测编辑器与终端、记住所选应用，并在不可用时回退到系统默认应用
- 恢复 DeepSeek Responses 的工具流式传输、原生网页搜索与后续对话回放
- 在 Provider 重试等待期间显示明确反馈
- 使委派会话继承父会话的工具模式
- 通过更快的 Tape 读取以及消息与事实的原子写入，提升 Agent 回合性能与会话一致性
- 刷新内置模型与 ACP 目录
- Added Code and Minimal tool modes, on-demand tool discovery, and permission-scoped CLI tool access
- Added a Tape Trace Inspector for Agent runs, provider requests, tool calls, and Skill usage
- Improved long-context compaction and overflow recovery while preserving full conversation history
- Unified Skills into a shared library with per-Agent enablement and progressive loading, and restored manual installation from folders, ZIP archives, URLs, and Git repositories
- Added managed Node.js and uv toolchains with detection, installation, repair, and recovery, plus terminal authentication for ACP agents
- Redesigned provider Settings with staged credential verification, API key copying, and direct chat entry; added validated custom request headers with cross-origin protections
- Added APIMart, Synthorai, and RunInfra providers, native APIMart image and video generation, and Codex image generation support
- Upgraded Markstream to 2.0.6 and reduced Markdown streaming stalls with split rendering and a managed worker pool
- Improved workspace navigation, conversation retry, and permission prompt recovery, and reduced startup delays
- Made Agent stop requests interrupt stalled provider and browser waits, and added configurable Code Mode cell timeouts
- Repaired usage statistics and MCP startup, retained corrupt databases for recovery, and fixed Ollama context budgets and provider timeout handling
- Refreshed the built-in model and ACP catalogs
- 新增 Code 与 Minimal 工具模式、按需工具发现，以及受权限约束的 CLI 工具访问
- 新增 Tape Trace Inspector，用于查看 Agent 运行、Provider 请求、工具调用与 Skill 使用记录
- 改进长上下文压缩与溢出恢复，同时保留完整对话历史
- 将 Skills 统一为共享库，支持逐 Agent 启用与渐进式加载，并恢复从文件夹、ZIP 压缩包、URL 与 Git 仓库手动安装
- 新增托管式 Node.js 与 uv 工具链，支持检测、安装、修复与恢复，并为 ACP Agent 新增终端身份验证
- 重做 Provider 设置，支持暂存并验证凭据、复制 API Key 和直接开始聊天；新增经过验证且具备跨域保护的自定义请求头
- 新增 APIMart、Synthorai 与 RunInfra Provider，支持 APIMart 原生图片与视频生成，以及 Codex 图片生成
- 将 Markstream 升级至 2.0.6，并通过分段渲染与受控 Worker 池减少 Markdown 流式渲染卡顿
- 改进工作区导航、对话重试与权限提示恢复，并减少启动延迟
- 使 Agent 停止请求能够中断卡住的 Provider 与浏览器等待，并支持配置 Code Mode 代码单元超时
- 修复用量统计与 MCP 启动，保留损坏数据库以便恢复，并修复 Ollama 上下文预算与 Provider 超时处理
- 刷新内置模型与 ACP 目录
- Added built-in APIMart and Synthorai providers, including native APIMart image and video generation
- Added validated per-provider custom request headers with cross-origin protections
- Restored manual Skill installation from folders, ZIP archives, URLs, and Git repositories
- Refreshed the built-in model and ACP catalogs
- Fixed stale permission and question prompts blocking conversations
- Reduced startup delays when background tasks occupy the available work lanes
- 新增内置 APIMart 与 Synthorai Provider，并支持 APIMart 原生图片与视频生成
- 新增经过验证的 Provider 自定义请求头，并提供跨域保护
- 恢复从文件夹、ZIP 压缩包、URL 与 Git 仓库手动安装 Skill
- 刷新内置模型与 ACP 目录
- 修复过期的权限与问题提示阻塞对话
- 减少后台任务占满工作通道时的启动延迟
- Added Codex image generation support for providers
- Reduced markdown streaming stalls with split rendering and gentle prefix batching
- Kept the user message mounted on retry, fixed retry budget double counting and duplicate pinned prompts
- Fixed decimal value formatting in the memory diagnostics panel
- 新增 Provider 的 Codex 图片生成支持
- 通过分段渲染与温和的前缀批处理减少 Markdown 流式渲染卡顿
- 重试时保留用户消息挂载，修复重试预算重复计算与重复固定提示词
- 修复内存诊断面板中十进制数值的格式化
- Added managed Node.js and uv toolchains with automatic detection, installation, repair, and recovery
- Added terminal authentication for ACP agents
- Added verified staged provider credential edits, API key copying, and a Start chatting action after provider setup
- Upgraded Markstream rendering with a managed stream-diffs worker pool
- Improved CLI, MCP, and OCR reliability around runtime discovery and toolchain changes
- 新增托管式 Node.js 与 uv 工具链，支持自动检测、安装、修复与恢复
- 新增 ACP Agent 终端身份验证
- 新增经验证的 Provider 凭据暂存编辑、API Key 复制，以及 Provider 配置完成后的“开始聊天”操作
- 升级 Markstream 渲染，引入受控的 stream-diffs Worker 池
- 改进 CLI、MCP 与 OCR 在运行时发现和工具链变更场景下的可靠性
- Redesigned the Settings provider sidebar and configured-provider page
- Honored provider model-configured timeouts instead of the default 300s undici header timeout
- Inherited global fetch timeouts on remaining proxy fetches
- Repaired usage statistics and MCP startup
- Allowed ACP apps to be uninstalled while disabled
- Stopped Agent from silently reading empty files
- Made body portals non-draggable and improved enabled tool chip visibility in dark mode
- 重新设计设置页的 Provider 侧边栏与已配置 Provider 页面
- 修复 Provider 模型超时，改为遵循模型配置的超时而非默认 300s 请求头超时
- 在剩余代理请求上继承全局 fetch 超时
- 修复用量统计与 MCP 启动
- 允许在禁用状态下卸载 ACP 应用
- 修复 Agent 静默读取空文件的问题
- 使 body 门户不可拖拽，并改善暗色模式下已启用工具 chip 的可见性
- Added virtualized tool surfaces: agents load tools on demand with search, canary performance gates, and permission-gated activation for large catalogs
- Added a Tape Trace Inspector to audit agent runs, tool calls, and skill usage
- Added context compaction with occupancy tracking, silent-pressure recovery, pinned context, and summary provenance
- Added new Agent run modes (code and minimal) and workspace management in the sidebar
- Added programmatic tool access through the CLI with bounded batches, grants, and trusted discovery
- Upgraded Markstream code rendering to the v2 language API with normalized language and code block handling
- Added bounded exec stdin and explicit shell dialect declaration for Agent tools
- Fixed corrupt database retention, guard-stop terminal surfacing, Ollama runtime context budget handling, and MiniMax-M3 temperature omission
- Improved skill lifecycle reliability, session restoration, workspace ordering, and tool execution recovery
- 新增虚拟化工具表面：Agent 按需加载工具，支持搜索、Canary 性能门控，以及针对大型工具目录的按权限激活
- 新增 Tape Trace Inspector，用于审计 Agent 运行、工具调用与技能使用
- 新增上下文压缩，支持占用跟踪、静默压力恢复、固定上下文与摘要来源标记
- 新增 Agent 运行模式（code 与 minimal）及侧边栏工作区管理
- 新增 CLI 程序化工具访问，支持有界批次、授权授予与可信发现
- 将 Markstream 代码渲染升级至 v2 语言 API，并规范化语言与代码块处理
- 为 Agent 工具新增有界 exec 标准输入与显式 Shell 方言声明
- 修复损坏数据库保留、guard-stop 终止反馈、Ollama 运行时上下文预算处理及 MiniMax-M3 温度参数遗漏
- 改进技能生命周期可靠性、会话恢复、工作区排序与工具执行恢复
- Added proactive multi-Agent collaboration with live child Sessions, progress controls, result handoff, durable execution journaling, and contract-bound delegation recovery
- Added a bundled local
deepchatCLI for inference, media, OCR, artifacts, Agent runs, provider and model administration, Settings, Skills, and MCP operations - Expanded Agent Memory with time-aware Directives, persistent corrections and deletions, incremental maintenance, and more reliable vector storage and recovery
- Added fully offline OCR for image and PDF attachments, with per-attachment modes, cancellation, caching, page-aware truncation, and reuse across history, retry, export, and search
- Gave every Agent an isolated Skills catalog with explicit imports, and added MCP v2 ecosystem support, a built-in McDonald's server, larger tool catalogs, and resilient schema handling
- Added native DeepSeek web search and built-in support for AMD GPU Cloud, DaoXE, GreenPT, Modelsell, OrcaRouter, Routerra, Straico, StepFun Token Plan, and Grok OAuth
- Upgraded Computer Use to 0.19.2 with snapshot-bound targeting, post-action verification, new window, menu, and clipboard tools, native picture-in-picture previews, and stronger runtime integrity checks
- Added browser session import, sidebar workspace management, persistent composer drafts, configurable Agent output limits, and Windows command shell profiles
- Improved chat and Agent recovery for pending or released inputs, permission outcomes, interrupted sessions, truncated tool calls, transient provider failures, and long-context prompt caching
- Refined notifications, Steer conversations, Settings, startup visuals, UI controls, motion, scrolling, search, and message actions while reducing renderer and dashboard overhead
- Added Linux ARM64 packages and a branded macOS installer, hardened updater metadata and native distribution verification, and rebuilt release assembly around reproducible, fail-closed checks
- Upgraded Electron to 41.10.4, the bundled Node.js runtime to 24.18.0, Light OCR to 0.5.7, and patched DOMPurify, Nano ID, YAML, and Mermaid security issues
- 新增主动式多 Agent 协作，支持实时子会话、进度控制、结果回传、持久化执行日志，以及受契约约束的委派恢复
- 新增内置本地
deepchatCLI，覆盖推理、媒体生成、OCR、产物管理、Agent 运行、Provider 与模型管理、设置、Skills 和 MCP 操作 - 扩展 Agent Memory，新增具备时间感知能力的 Directives、可持久生效的纠正与删除、增量维护，以及更可靠的向量存储与恢复机制
- 新增完全离线的图片与 PDF 附件 OCR，支持逐附件模式、取消、缓存、按页截断，以及在历史、重试、导出和搜索中复用结果
- 为每个 Agent 提供隔离的 Skills 目录与显式导入，并新增 MCP v2 生态、内置 McDonald's 服务器、大型工具目录支持和稳健的 Schema 兼容处理
- 新增 DeepSeek 原生联网搜索，并内置支持 AMD GPU Cloud、DaoXE、GreenPT、Modelsell、OrcaRouter、Routerra、Straico、StepFun Token Plan 和 Grok OAuth
- 将 Computer Use 升级至 0.19.2，新增基于快照的目标定位、操作后验证、窗口、菜单与剪贴板工具、原生画中画预览，并强化运行时完整性校验
- 新增浏览器会话导入、侧边栏工作区管理、输入框草稿持久化、Agent 输出上限配置，以及 Windows 命令行 Shell 配置
- 改进待处理或已释放输入、权限结果、中断会话、截断工具调用、瞬时 Provider 故障和长上下文提示词缓存的恢复与可靠性
- 优化通知反馈、Steer 对话、设置页、启动视觉、UI 控件、动效、滚动、搜索和消息操作，并降低渲染器与 Dashboard 开销
- 新增 Linux ARM64 安装包和品牌化 macOS 安装器，强化更新元数据与原生分发校验，并以可复现、失败即关闭的检查重构发布组装流程
- 将 Electron 升级至 41.10.4、内置 Node.js 运行时升级至 24.18.0、Light OCR 升级至 0.5.7，并修复 DOMPurify、Nano ID、YAML 与 Mermaid 安全问题
- Added proactive multi-Agent collaboration with live child Sessions, progress tracking, controls, and result handoff
- Added a bundled local
deepchatCLI for inference, media, OCR, artifacts, Agent runs, provider and model administration, Settings, Skills, and MCP operations - Added native web search for supported DeepSeek V4 Flash models, with a per-turn toggle, visible search activity, and source links
- Added OrcaRouter as a built-in provider with live model discovery
- Upgraded the bundled Computer Use driver to 0.17.0 with snapshot-bound targeting, post-action verification, and new window, menu, and clipboard tools
- Persisted images generated through MCP tools so they remain available after restart and in follow-up actions
- Improved compatibility with large MCP tool catalogs and equivalent JSON schemas
- Standardized UI controls and refined interface motion, hover behavior, and reduced-motion feedback
- Upgraded Light OCR to 0.5.7, Electron to 41.10.4, and the bundled Node.js runtime to 24.18.0
- Restored provider database refreshes for larger catalogs and refreshed model and Agent registries
- Fixed long unbroken text expanding the chat composer, untranslated confirmation labels, and scheduler restart and manual-run feedback
- 新增主动式多 Agent 协作，支持实时子会话、进度跟踪、控制与结果回传
- 新增内置本地
deepchatCLI，覆盖推理、媒体生成、OCR、产物管理、Agent 运行、Provider 与模型管理、设置、Skills 和 MCP 操作 - 为支持的 DeepSeek V4 Flash 模型新增原生联网搜索，提供逐轮开关、可见搜索过程与来源链接
- 新增 OrcaRouter 内置 Provider，并支持动态获取模型列表
- 将内置 Computer Use 驱动升级至 0.17.0，新增基于快照的目标定位、操作后验证，以及窗口、菜单和剪贴板工具
- 持久化 MCP 工具生成的图片，确保重启后及后续操作中仍可使用
- 改进大型 MCP 工具目录及等价 JSON Schema 的兼容性
- 统一界面控件，并优化动效、悬停行为与减少动态效果反馈
- 将 Light OCR 升级至 0.5.7、Electron 升级至 41.10.4，并将内置 Node.js 运行时升级至 24.18.0
- 恢复大型 Provider 数据库的刷新能力，并更新模型与 Agent 注册表
- 修复无空格长文本撑宽聊天输入框、确认按钮未翻译，以及调度器重启与手动运行反馈异常
- Tolerated invalid MCP tool output schemas without rejecting otherwise usable tools
- 容忍无效的 MCP 工具输出 Schema，避免拒绝其他可用工具
- Improved alert confirmations and notification feedback so user actions report reliable results
- Added MCP v2 ecosystem support and a built-in McDonald's server
- Upgraded Light OCR to 0.5.6 and moved OCR management into Plugins Hub
- Redesigned Steer messages as IM-style conversations
- Deferred automatic updates until active tasks finish
- Fixed provider image inputs by sending file parts where required
- Removed dashboard usage cost figures and hardened locale resolution
- Restored scheduled package regression checks
- Upgraded the bundled Computer Use driver to v0.14.1
- 改进提醒确认与通知反馈，确保用户操作能够可靠地显示结果
- 支持 MCP v2 生态，并新增 McDonald's 内置服务器
- 将 Light OCR 升级至 0.5.6，并将 OCR 管理移至 Plugins Hub
- 将 Steer 消息重做为类似即时通讯的对话形式
- 延迟自动更新安装，避免打断正在执行的任务
- 修复部分 Provider 的图片输入，按要求改用文件分片发送
- 移除 Dashboard 费用估算，并强化语言环境解析
- 恢复定时软件包回归检查
- 内置 Computer Use 驱动升级至 v0.14.1
- Added Directives to Agent Memory: instructions you write take effect immediately, instructions the model suggests stay as drafts until you approve them, and suppression directives keep a topic out of recalled memory. Clearing memories now keeps your directives
- Made Agent Memory time-aware: it records when a fact was true, so expired plans and outdated states are no longer recalled as current; corrections and deletions now stick instead of reappearing in the next conversation; and memory maintenance runs incrementally instead of rescanning everything
- Added fully offline PDF OCR (Light-OCR 0.5.5): multi-page recognition with a per-attachment Auto / Text / OCR switch, page-aware truncation that reports which pages were included, and results cached and reused across history, retry, export and search
- Added GreenPT and Modelsell as built-in providers, with model lists fetched live from the provider
- Fixed enabling Computer Use blacking out the desktop on Linux/X11: the driver now starts only when a tool actually needs it, its files are verified before every launch, and a runtime that exits uncleanly is quarantined with Test runtime and Retry runtime controls in Settings
- Upgraded the bundled Computer Use driver to v0.13.1, and added a read-only picture-in-picture showing the latest snapshot of the app being controlled
- Made native preview support load only on first use so missing dependencies no longer affect startup: Browser opens in the side panel when native preview is unavailable, Computer Use keeps working without picture-in-picture, and Windows x64 now uses a statically linked runtime to reduce missing-DLL launch failures
- Fixed model context and output limits being overwritten on refresh, reset, restart and backup restore — GPT-5.6-sol on New API was capped at 16000/4096 instead of 1050000/32000 — and fixed Kimi K3 on New API sending temperature and top_p, which it does not support
- Replaced the startup window with an animated DeepChat splash
- Redesigned the Settings overview and usage dashboard: hovering a day in the activity calendar now shows that day's input, output and cache-hit tokens. The usage trend chart and estimated cost figures have been removed
- Fixed confirming a message deletion doing nothing, and delete failures now show an error instead of failing silently
- Fixed three Agent Skills issues: importing from another Agent failing with "An object could not be cloned", a failed skill snapshot migration blocking startup, and the skill list flickering when toggling a skill on or off
- Agent Memory 新增 Directives（长期指令）：自己写的指令立即生效，模型建议的指令先存为草稿、经你确认后才生效，抑制类指令可以让某个话题不再被记忆召回。清空记忆时会保留这些指令
- Agent Memory 现在理解时间：会记录一条信息在什么时间范围内成立，过期的计划和已失效的状态不再被当作当前事实召回；纠正和删除会真正生效，不会在下一次对话里重新冒出来；记忆整理改为增量进行，不再每次全量扫描
- 新增完全离线的 PDF OCR（Light-OCR 0.5.5）：支持多页识别，每个附件可单独选择 Auto / 文本 / OCR；超出限制时会明确告知识别到了哪些页面。识别结果会缓存，并在历史、重试、导出和搜索中复用
- 新增 GreenPT 与 Modelsell 两个内置 Provider，模型列表从服务商动态获取
- 修复 Linux/X11 下启用 Computer Use 导致桌面黑屏的问题：驱动改为在工具真正需要时才启动，每次启动前校验文件完整性；异常退出的运行时会被隔离，并在设置中提供「测试运行时」和「重试运行时」操作
- 内置 Computer Use 驱动升级至 v0.13.1，并新增只读画中画，显示被操作应用的最新截图
- 原生预览能力改为首次使用时才加载，避免依赖缺失影响应用启动：原生预览不可用时 Browser 自动打开侧边栏、Computer Use 不显示画中画但功能照常；Windows x64 改用静态链接运行时，减少缺少 DLL 导致的启动失败
- 修复模型上下文与输出上限在刷新、重置、重启和备份恢复后被覆盖的问题（New API 下 GPT-5.6-sol 会被限制为 16000/4096 而非 1050000/32000），以及 New API 下 Kimi K3 发送了它并不支持的 temperature 和 top_p
- 启动窗口更换为带动画的 DeepChat 启动页
- 重做设置概览页与用量面板：在活跃日历上悬停某一天可查看当天的输入、输出与缓存命中 token。已移除用量趋势图和费用估算
- 修复点击确认删除消息后没有任何反应的问题，删除失败时也会给出错误提示而不再静默失败
- 修复 Agent Skills 的三个问题：从其他 Agent 导入时报「An object could not be cloned」、技能快照迁移失败会阻塞启动、开关技能时列表闪烁
- Added fully offline OCR for image attachments (Light-OCR): images are routed to vision or OCR based on the selected model, OCR text is reused across history, retry, edit and compaction, and per-attachment mode, cancellation and cache controls are available in Settings
- Gave every Agent its own Skills root and catalog, replacing the shared catalog and its sync workflow with explicit import from another Agent or from an external DeepChat data directory
- Rebuilt the Agent browser picture-in-picture as a native overlay: open-in-side-panel and close controls, dragging outside the DeepChat window, with the Canvas overlay kept as a fallback
- Added Routerra, Straico, and StepFun Token Plan as built-in provider presets
- Added Linux ARM64 installers, and gave the macOS DMG installer a proper drag-to-install window with a background image and the app and Applications icons aligned to it
- Made long conversations reuse the provider prompt cache: the system prompt no longer changes whenever a summary, handoff state or memory updates, cache markers now reach the request for OpenAI, Anthropic, Bedrock, OpenRouter and Zenmux, and compaction sizes the retained history to the model's context budget
- Retried transient provider failures with bounded, abortable backoff, and never replayed a request once text, reasoning or tool output was committed
- Stopped executing tool calls truncated by
max_tokens: the batch is rejected atomically, matching error results are written, and the request is retried once - Restructured the Agent runtime into a one-directional owner graph behind a harness facade, added a typed tool execution contract that keeps write-capable tools sequential, and rebuilt Hooks on a typed event pipeline with bounded command execution
- Fixed chat search highlights on streamed rows, sidebar search pagination, the invisible pending-assistant row, session-restore scrolling that overrode a search or spotlight jump, and session revision recovery on existing databases
- Cut Settings startup cost by lazy-loading locales (synchronous JS 4.25 MB to 0.9 MB) and reduced Dashboard CPU with cached formatters and polling that pauses in the background
- Fixed auto-update failing with
Invalid input: expected string, received Date: updater metadata is now published with a quoted releaseDate and validated against electron-updater's own parser across all four channel files - Fixed the macOS clean-install Gatekeeper failure caused by the bundled Computer Use helper, and added distribution verification for both the app and the macOS updater payload
- Rebuilt the release pipeline to verify every published package before release, and locked dependencies with a tracked pnpm lockfile for reproducible builds
- 新增完全离线的图片附件 OCR（Light-OCR）：根据所选模型自动在视觉与 OCR 之间路由，OCR 文本在历史、重试、编辑与压缩中复用，并提供逐附件模式、取消与缓存管理
- 每个 Agent 拥有独立的 Skills 根目录与目录管理，取消共享目录与同步流程，改为从其他 Agent 或外部 DeepChat 数据目录显式导入
- 将 Agent 浏览器画中画重构为原生浮窗：提供打开侧边栏与关闭按钮，可拖动到 DeepChat 窗口之外，并保留 Canvas 浮层作为回退方案
- 新增 Routerra、Straico 与 StepFun Token Plan 内置 Provider
- 新增 Linux ARM64 安装包；macOS DMG 安装窗口改为带背景图的拖拽安装界面，应用图标与 Applications 快捷方式按背景对齐
- 让长对话真正复用 Provider 的提示词缓存：系统提示词不再随摘要、handoff 状态与记忆的更新而变化，缓存标记能正确传给 OpenAI、Anthropic、Bedrock、OpenRouter 与 Zenmux，压缩时按模型上下文预算保留近期历史
- 对瞬时 Provider 失败进行有界、可中断的退避重试，并在已产出文本、思考或工具调用后不再重放请求
- 不再执行被
max_tokens截断的工具调用：整批原子拒绝并写入对应错误结果，随后仅自动重试一次 - 将 Agent runtime 重构为 harness facade 之上的单向 owner 图，引入类型化工具执行契约（可写工具强制串行），并将 Hook 重建为类型化事件管道与有界命令执行
- 修复流式消息的搜索高亮、侧边栏搜索分页、待生成消息行不可见、会话恢复滚动覆盖搜索/聚光跳转，以及已有数据库的 session revision 恢复问题
- 懒加载语言包降低设置页启动开销（同步 JS 4.25 MB 降至 0.9 MB），并通过缓存 formatter 与后台暂停轮询降低 Dashboard CPU 占用
- 修复自动更新报错
Invalid input: expected string, received Date：发布端强制为 releaseDate 加引号，并用 electron-updater 自身的解析器校验全部四个更新渠道文件 - 修复由内置 Computer Use 助手导致的 macOS 全新安装 Gatekeeper 失败，并对应用与 macOS 更新包补充分发校验
- 重构发布流水线，发布前校验每个产物；纳入 pnpm lockfile 锁定依赖，保证构建可复现
- Added browser session import and an agent picture-in-picture view
- Improved Feishu delivery error feedback and test user-data directory handling
- Reworked the Tape runtime into layered architecture with improved session recall reliability
- Restructured the chat main renderer and added rendering performance diagnostics
- 新增浏览器会话导入与 Agent 画中画视图
- 改进飞书投递错误反馈及测试用户数据目录处理
- 将 Tape runtime 重构为分层架构，提升会话召回可靠性
- 重构聊天主渲染器并新增渲染性能诊断
- Reworked the overall architecture and improved reliability
- 重构整体架构，提升可靠性
- Centralized Subagent capability policy ownership across the agent runtime and sessions
- Added explicit subagent tape lineage with linked tape views and cross-tape recall
- Separated Tape runtime tool capabilities for clearer isolation
- Split agent runtime lifecycle owners and tightened message, permission, and stop boundaries
- Improved renderer interaction quality for panels, MCP market, and message actions
- Stabilized chat scroll ownership and hardened session view ownership
- Fixed Agent Memory provider cancellation and config ABA fence bypass
- Upgraded markstream-vue and stream-monaco for streaming render alignment
- 集中管理 Subagent capability policy 与 ownership，统一 runtime 与 session 边界
- 新增显式 subagent tape lineage，支持 linked tape 视图与跨 tape 召回
- 拆分 Tape runtime 工具能力边界，提升隔离性
- 拆分 agent runtime lifecycle owners，收紧 message、permission 与 stop 边界
- 改进面板、MCP market 与消息操作等交互体验
- 稳定聊天滚动归属并强化 session view ownership
- 修复 Agent Memory provider cancellation 与 config ABA fence 绕过问题
- 升级 markstream-vue 与 stream-monaco，对齐流式渲染依赖
- Added Grok OAuth device login and DaoXE provider support
- Reworked the agent runtime and session boundaries to improve isolation and lifecycle handling
- Improved Agent Memory vector storage, embedding reindex recovery, and bounded workload reliability
- Improved streaming rendering and preserved the active sidebar workspace while navigating chat history
- Fixed ACP direct-runtime refresh and manual health checks
- 新增 Grok OAuth 设备登录和 DaoXE Provider 支持
- 重构 Agent runtime 与 session 边界，提升隔离性和生命周期处理能力
- 改进 Agent Memory 向量存储、embedding reindex 恢复与有界工作负载的可靠性
- 优化流式渲染，并在浏览聊天历史时保留侧边栏当前工作区
- 修复 ACP direct runtime 刷新和手动健康检查问题
- Fixed Agent Memory correctness edge cases and strengthened record-level privacy controls
- Fixed chat scroll position jumping to the bottom during streaming output
- Fixed chat history restoration race conditions that could cause message loss
- 修复 Agent Memory 正确性边界问题，并强化记录级隐私控制
- 修复流式输出时聊天滚动位置跳到底部的问题
- 修复聊天历史恢复竞态条件可能导致消息丢失的问题
- Added the main-window Plugins Hub, Feishu/Lark install authentication, and streaming card delivery for remote control
- Added MCP OAuth authentication, agent-scoped plugin controls for skills, MCP servers, and tools, plus improved skill sync workflows
- Expanded Agent Memory with task-aware recall, redesigned settings, health and lifecycle diagnostics, in-chat visibility, and reliability improvements
- Reworked scheduled tasks into Cron Jobs with a dedicated scheduler runtime, delivery routing, settings UI, and agent tool support
- Added TokenLab, OpenCode Go, and GPT-5.6/Codex 5.6 support with configurable effort levels
- Upgraded the provider and runtime stack to AI SDK v7, Zod v4, Electron 40.10.5, and DuckDB 1.5.4, while improving startup, chat rendering, scrolling, and responsive interaction performance
- Fixed New API response handling, endpoint debug selection, memory first-turn stalls, context-overflow auto-handoff, ACP permission requests, assistant loading state, attachment replay, draft cleanup, and macOS window restoration and hide behavior
- 新增主窗口插件中心、飞书/Lark 安装认证，以及远程控制流式卡片推送
- 新增 MCP OAuth 认证、Agent 级 skills、MCP servers 与 tools 控制，并改进 skill sync 工作流
- 扩展 Agent Memory，支持任务感知召回、重做设置页、健康与生命周期诊断、聊天内可见性，并提升可靠性
- 将 scheduled tasks 重构为 Cron Jobs，支持独立 scheduler runtime、delivery routing、设置 UI 和 Agent tool
- 新增 TokenLab、OpenCode Go 和 GPT-5.6/Codex 5.6 支持，并提供可配置的 effort levels
- 将 provider 与 runtime 栈升级至 AI SDK v7、Zod v4、Electron 40.10.5 和 DuckDB 1.5.4，同时提升启动、聊天渲染、滚动与响应式交互性能
- 修复 New API 响应处理、endpoint debug 选择、memory 首轮卡顿、context overflow 自动 handoff、ACP 权限请求、Assistant loading state、附件内容回放、草稿清理，以及 macOS 窗口恢复与隐藏行为
- Added TokenLab and OpenCode Go provider support
- Redesigned Agent Memory settings with inline configuration, inbox, diagnostics, persona, and list views
- Improved Agent Memory reliability for retrieval, pruning, write coordination, vector storage, and audit handling
- Optimized chat markdown rendering to reduce send-time jitter and improve message layout stability
- Updated Computer Use driver/runtime metadata and renamed the bundled CUA skill to
computer-use - 新增 TokenLab 和 OpenCode Go provider 支持
- 重做 Agent Memory 设置页，加入 inline configuration、inbox、diagnostics、persona 和 list views
- 改进 Agent Memory retrieval、pruning、write coordination、vector storage 与 audit handling 的可靠性
- 优化聊天 Markdown 渲染，减少发送时抖动并提升消息布局稳定性
- 更新 Computer Use driver/runtime 元数据，并将内置 CUA skill 重命名为
computer-use
- Added MCP OAuth authentication, assistant approval review mode, delete confirmations, and in-chat Agent Memory visibility
- Reworked scheduled tasks into Cron Jobs with scheduler runtime, delivery routing, settings UI, and agent tool support
- Improved Agent Memory lifecycle management, skill sync UX, startup performance, and packaged Linux OpenDAL native libraries
- Fixed ACP permission requests, assistant loading state, attachment replay behavior, MCP session tools, skill adoption, and multiple chat/settings regressions
- 新增 MCP OAuth 认证、Assistant approval review mode、删除确认，以及聊天内 Agent Memory 可见性
- 将 scheduled tasks 重构为 Cron Jobs，支持 scheduler runtime、delivery routing、设置页 UI 和 Agent tool
- 改进 Agent Memory 生命周期管理、skill sync 体验、启动性能，并补齐 Linux OpenDAL native libraries 打包
- 修复 ACP permission requests、Assistant loading state、附件内容重复回放、MCP session tools、skill adopt 和多项聊天/设置回归问题
- Added agent-scoped plugin extension controls for skills, MCP servers, and tools
- Added Agent Memory health snapshots and audit details in settings
- Fixed settings window sizing, sidebar chat actions, manual memory category handling, skill conflict popup layout, and provider 302 domain
- Migrated commit hooks to commitlint and refreshed electron-builder plus provider and ACP registry data
- 新增 Agent 级插件扩展控制，可按 Agent 限制 skills、MCP servers 和 tools
- 新增 Agent Memory health snapshot 与设置页审计详情
- 修复设置窗口尺寸、侧边栏会话操作、手动添加 memory category、技能冲突弹窗布局和 provider 302 domain
- 迁移 commit hooks 到 commitlint，并刷新 electron-builder、Provider 与 ACP registry 数据
- Added the main-window Plugins Hub plus Feishu/Lark install authentication and streaming card delivery for remote control
- Upgraded the provider/runtime stack with AI SDK v7, Zod v4 schemas, Electron 40.10.5, DuckDB 1.5.4, and refreshed toolchains
- Fixed New API responses handling and endpoint debug selection, memory first-turn stalls, context-overflow auto-handoff, message-scoped skill activation, and request preview editor layout
- 新增主窗口插件中心，并支持飞书/Lark 安装认证与远程控制流式卡片推送
- 升级 provider/runtime 栈到 AI SDK v7、Zod v4 schema、Electron 40.10.5、DuckDB 1.5.4，并刷新工具链
- 修复 New API responses 处理与 endpoint debug 选择、memory 首轮卡顿、context overflow 自动 handoff、按消息激活 skill，以及请求预览编辑器布局
- Added the default chat workspace, task-aware Agent Memory, and persistent agent plan blocks in chat history
- Improved Computer Use helper runtime isolation, packaging, shutdown cleanup, and refreshed bundled dependencies and resources
- Fixed fresh SQLite schema bootstrap, stale Tape FTS search hits, New API responses endpoint configuration, sidebar history pagination, and locked skill reinstall handling
- 新增默认聊天工作区、任务感知 Agent Memory，并支持在聊天历史中持久化 Agent plan blocks
- 优化 Computer Use helper runtime 的隔离、打包和退出清理，并刷新内置依赖与资源
- 修复首次 SQLite schema 初始化、陈旧 Tape FTS 搜索命中、New API responses endpoint 配置、侧边栏历史分页和技能重装锁定目录处理
- Fixed fresh SQLite schema bootstrap so new installations initialize reliably
- Fixed New API responses endpoint configuration so it stays separate from other endpoint options
- 修复首次 SQLite schema 初始化，提升新安装启动可靠性
- 修复 New API responses endpoint 配置，避免与其他 endpoint 选项混用
- Added the default chat workspace so new chats start with prepared workspace context
- Added task-aware Agent Memory with improved maintenance scheduling and management controls
- Improved Computer Use helper runtime isolation, packaging, and shutdown cleanup
- Fixed sidebar history pagination, locked skill reinstall handling, and refreshed Markstream Vue
- 新增默认聊天工作区，让新聊天具备预设工作区上下文
- 新增任务感知 Agent Memory，并改进维护调度与管理控制
- 优化 Computer Use helper runtime 的隔离、打包和退出清理
- 修复侧边栏历史分页、技能重装锁定目录处理，并刷新 Markstream Vue
- Added S3-compatible cloud backup sync, OpenDAL-based backup storage, and workspace environment management
- Added Agent Memory, Tape view manifests, replay lineage details, and focused workspace file inspection
- Added OpenAI Codex runtime support, built-in API key providers, AWS Bedrock profile authentication, MiniMax M3 handling, and drag-and-drop skill installation
- Added cross-platform Computer Use runtime packaging and improved agent runtime discovery, watcher reliability, and provider/ACP registry freshness
- Fixed packaged cloud sync startup, Codex login behavior, memory followups, MCP server cleanup, steer abort queue handling, sidebar pagination, markdown scrollbar jitter, and settings save payloads
- 新增 S3 兼容云备份同步、基于 OpenDAL 的备份存储，以及工作区环境管理
- 新增 Agent Memory、Tape view manifests、replay lineage 详情，以及聚焦式工作区文件检查
- 新增 OpenAI Codex runtime、内置 API key providers、AWS Bedrock profile 认证、MiniMax M3 处理和技能拖放安装
- 新增跨平台 Computer Use runtime 打包，并改进 Agent runtime 发现、工作区监听可靠性和 Provider/ACP registry 更新
- 修复打包版云同步启动、Codex 登录行为、memory followups、MCP server 清理、steer abort queue 处理、侧边栏分页、Markdown 滚动条抖动和设置保存 payload 问题
- Added OpenAI Codex runtime support with OAuth authentication and provider-specific request handling
- Added built-in API key providers and provider registry metadata for easier model setup
- Added environment management for workspace sessions and improved directory state persistence
- Fixed steer abort queue handling so pending chat input pauses and resumes more reliably
- Updated Markstream Vue and refreshed bundled provider/model and ACP registry data
- 新增 OpenAI Codex runtime 支持，包含 OAuth 认证与 Provider 专属请求处理
- 新增内置 API key providers 和 Provider registry metadata，简化模型配置
- 新增工作区会话的环境管理，并改进目录状态持久化
- 修复 steer abort queue 处理，让待处理聊天输入的暂停和恢复更可靠
- 更新 Markstream Vue，并刷新内置 Provider/模型与 ACP registry 数据
- Added Tape manifest integrity and lineage details so replay traces can be audited more reliably
- Added a workspace single item viewer for focused file inspection from the workspace panel
- Added cross-platform CUA runtime packaging and plugin runtime build improvements
- Fixed deterministic Tape view hashing and trace sequence handling
- 新增 Tape manifest 完整性与 lineage 详情，让 replay trace 审计更可靠
- 新增工作区单项查看器，方便从工作区面板聚焦检查文件
- 支持了 Windows 和 Linux 平台的 Computer Use 能力
- 修复 Tape view hash 与 trace sequence 的确定性处理
- Added Agent Memory so agents can extract, manage, and reuse persistent memory in agent workflows
- Added DeepChat Tape view manifests and richer trace inspection for replay and context provenance
- Added drag-and-drop skill installation, MiniMax M3 handling, and refreshed provider/model and ACP registry data
- Improved workspace watching with a Parcel watcher utility host for large workspace reliability
- Fixed markdown code block scrollbar jitter, sidebar history pagination stalls, and cloned settings save payloads
- 新增 Agent Memory，让 Agent 工作流可以提取、管理并复用持久记忆
- 新增 DeepChat Tape view manifest 与更完整的 trace 检查，支持 replay 和上下文来源追踪
- 新增技能拖放安装、MiniMax M3 处理，并刷新 Provider/模型与 ACP registry 数据
- 使用 Parcel watcher utility host 改进工作区监听，提升大型工作区可靠性
- 修复 Markdown 代码块滚动条抖动、侧边栏历史分页卡住，以及设置保存 payload clone 问题
- Fixed packaged app startup by bundling the OpenDAL native binding needed by cloud sync
- 修复打包应用启动问题，补齐云同步所需的 OpenDAL native binding
- Migrated cloud sync to OpenDAL and improved R2 setup for more reliable S3-compatible backups
- Fixed agent runtime FFF loading from unpacked app builds and cleaned up logging, skill IO, and status bar behavior
- 将云同步迁移到 OpenDAL，并优化 R2 设置，让 S3 兼容备份更可靠
- 修复 Agent 运行时在 unpacked app 构建中的 FFF 加载，并清理日志、skill IO 与状态栏行为
- Added AWS Bedrock profile authentication support for easier account and credential switching
- Improved agent runtime node discovery with FFF search and refreshed AI SDK packages plus bundled resources
- Fixed Anthropic reasoning controls so supported thinking settings stay available after provider data refreshes
- Fixed AWS provider styling consistency in the provider configuration UI
- 新增 AWS Bedrock profile 认证支持，方便切换账号与凭据
- 改进 Agent 运行时节点发现，使用 FFF 搜索，并刷新 AI SDK 依赖与内置资源
- 修复 Anthropic 推理控制，让支持的 thinking 设置在 Provider 数据刷新后仍保持可用
- 修复 AWS Provider 配置界面的样式一致性
- Fixed release CI tooltip module resolution so macOS release builds can complete reliably
- 修复发布 CI 中 tooltip 模块解析问题，让 macOS 发布构建可稳定完成
- Added S3-compatible cloud backup sync for more flexible cross-device data backup
- Improved Dify knowledge import compatibility with the latest
retrieval_modelschema - Refreshed bundled provider and ACP registry data for current model and agent availability
- 新增 S3 兼容云备份同步，让跨设备数据备份更灵活
- 优化 Dify 知识库导入兼容性，适配最新
retrieval_modelschema - 刷新内置 Provider 与 ACP registry 数据，更新模型和 Agent 可用性
- Added scheduled tasks, agent progress todos, session transfer, session tape memory, and remote
/agentcommands for more persistent agent workflows - Added OpenAI-compatible video generation, tool result image previews, remote image delivery, and richer TTS model routing controls
- Added provider configuration import for CC Switch and external tools, plus refreshed bundled provider data to 142 providers and 6,964 models
- Added encrypted SQLite database storage and a safer settings Danger Zone reset flow
- Added the workspace file tree sidebar, richer Git diff rendering, sidebar theme and chat shortcut controls, and a cleaner new-thread input transition
- Improved chat readability and performance with automatic activity collapsing, merged activity groups, content-visibility message windowing, and smoother streaming
- Improved ACP v1 and remote-control reliability with stronger session handling, diagnostics, alias resolution, media delivery, and working-directory errors
- Fixed macOS foreground identity, provider capability handling, browser recovery errors, startup warning noise, floating button persistence, and session list behavior
- 新增定时任务、Agent 进度 todo、会话转移、Session Tape Memory 和远程
/agent命令，让 Agent 工作流更持久可控 - 新增 OpenAI 兼容视频生成、工具结果图片预览、远程图片投递和更完整的 TTS 模型路由控制
- 新增 CC Switch 与外部工具的 Provider 配置导入，并刷新内置 Provider 数据至 142 个 Provider、6,964 个模型
- 新增 SQLite 数据库加密存储，并让设置里的 Danger Zone 重置流程更安全
- 新增工作区文件树侧栏、更丰富的 Git diff 渲染、侧栏主题与聊天快捷键控制，以及更清爽的新会话输入框过渡
- 通过活动自动折叠、活动组合并、content-visibility 消息窗口和更平滑的流式渲染，提升聊天可读性与性能
- 提升 ACP v1 与远程控制可靠性，强化会话处理、诊断、别名解析、媒体投递和工作目录错误处理
- 修复 macOS 前台身份、Provider 能力处理、浏览器恢复错误、启动告警噪声、浮动按钮位置持久化和会话列表行为
- Added a collapsible workspace file tree sidebar and an animated theme toggle in the app sidebar
- Added automatic chat activity collapsing so completed reasoning and tool-call work stays easier to scan
- Improved ACP v1 reliability with stronger capability handling, session persistence, terminal behavior, diagnostics, and protocol coverage
- Fixed model capability handling for temperature controls and provider database budget sentinels
- 新增可折叠的工作区文件树侧栏和应用侧栏动态主题切换按钮
- 新增聊天活动自动折叠，让完成后的思考和工具调用内容更易扫读
- 提升 ACP v1 可靠性，完善能力处理、会话持久化、终端行为、诊断和协议覆盖
- 修复温度控制和 Provider 数据库预算特殊值的模型能力处理
- Added agent session transfer so chats can be preserved or moved when changing agent ownership
- Added a richer workspace Git diff panel rendering experience
- Improved NewAPI routing, AI SDK system prompt handling, image-capable model switching, and plan model styling
- Fixed workspace file reference insertion, floating button position persistence, and collapsed sidebar agent expansion
- 新增 Agent 会话转移能力，让切换 Agent 归属时可以保留或移动聊天
- 新增更完整的工作区 Git diff 面板渲染体验
- 优化 NewAPI 路由、AI SDK system prompt 处理、图片能力模型切回聊天和计划模型样式
- 修复工作区文件引用插入、浮动按钮位置持久化和折叠侧边栏 Agent 展开问题
- Added
/agentcommands across remote-control channels so remote conversations can switch agents more easily - Added tool result image previews and remote image delivery for richer agent output
- Added skill draft confirmation cards with view, install, and discard actions, plus Top P generation controls
- Improved ACP agent alias resolution and remote workdir error handling
- Fixed agent exec utility host startup failures, prerelease upgrade channel handling, startup warning noise, and inline stream auto-follow jitter
- 新增远程控制渠道的
/agent命令，让远程会话更方便地切换 Agent - 新增工具结果图片预览与远程图片投递，完善 Agent 输出展示
- 新增带查看、安装、丢弃操作的 Skill 草稿确认卡，并加入 Top P 生成设置
- 优化 ACP Agent 别名解析和远程工作目录错误处理
- 修复 Agent exec utility host 启动失败、预发布渠道升级、防降级、启动告警噪声和流式输出底部抖动问题
- Added scheduled tasks for recurring agent work
- Added high-priority language support and completed missing locale keys for broader localization coverage
- Simplified the data settings Danger Zone entry so reset choices stay inside the confirmation dialog
- Fixed MiMo Pro TTS routing so it uses chat-compatible provider behavior
- Preserved paired Feishu users across remote-control state updates
- 新增定时任务能力，支持周期性的 Agent 工作
- 新增高优先级语言支持，并补齐缺失的本地化 keys，扩大多语言覆盖
- 简化数据设置中的 Danger Zone 入口，将具体重置选项收进确认弹窗
- 修复 MiMo Pro 的 TTS 路由，使其使用兼容聊天的 Provider 行为
- 修复飞书远程控制状态更新时配对用户被丢失的问题
- Added session tape memory to persist and compress agent conversation history more reliably
- Synced CUA driver to v0.2.0 with diagnostic tools and improved app launching
- Telegram replies now render Markdown as HTML for proper formatting
- Improved agent steer execution responsiveness
- Updated AI SDK packages and refreshed bundled provider registry data
- 新增 Session Tape Memory，更可靠地持久化和压缩 Agent 会话历史
- 同步 CUA driver 至 v0.2.0，新增诊断工具并改进应用启动能力
- Telegram 回复现在将 Markdown 渲染为 HTML，格式展示更准确
- 提升 Agent steer 执行的响应性
- 更新 AI SDK 依赖并刷新内置 Provider registry 数据
- Added encrypted SQLite database storage to strengthen local data protection
- Improved onboarding guide handoff by refreshing state after setup transitions
- Refined onboarding spotlight rendering with SVG paths and fixed panel stacking and hover performance issues
- 新增 SQLite 数据库加密存储，增强本地数据保护
- 优化引导流程交接，在设置切换后刷新状态
- 优化引导高亮的 SVG path 渲染，并修复面板层级与 hover 性能问题
- Added provider configuration import with preview, validation, conflict handling, and localized settings UI
- Added CC Switch configuration import and broader provider import path discovery for smoother migration from external tools
- Added a hero transition for the chat input on new threads and refined chat overlay/sidebar styling for a cleaner first-run flow
- Improved session list behavior with stable alphabetical ordering and more predictable pinning
- Added Feishu thing reactions and tightened Feishu remote-control runtime handling
- 新增 Provider 配置导入，支持预览、校验、冲突处理和本地化设置界面
- 新增 CC Switch 配置导入，并扩展 Provider 导入路径发现，方便从外部工具迁移
- 新增新会话聊天输入框的 hero 过渡，并优化聊天浮层与侧边栏样式，让首次使用流程更清爽
- 优化会话列表行为，保持稳定的字母排序和更可预期的置顶表现
- 新增飞书 thing 表情互动，并加强飞书远程控制运行时处理
- Added an agent progress todo tool with floating progress UI and plan message rendering so long-running agent work is easier to track
- Added OpenAI-compatible video generation with model settings, generated video message rendering, and provider runtime support
- Improved TTS routing and Gemini TTS behavior with unified model settings, provider metadata, and stronger runtime coverage
- Improved Feishu plugin packaging with platform bundles, release workflow support, and updated packaging documentation
- Updated TypeScript native preview, vue-tsgo, provider registry, and ACP registry data for current tooling and runtime compatibility
- Fixed image-route chat budget handling so generated image requests avoid unnecessary context budget failures
- 新增 Agent 进度 todo 工具、浮动进度界面和计划消息渲染，让长时间 Agent 工作更容易跟踪
- 新增 OpenAI 兼容的视频生成能力，包含模型设置、生成视频消息渲染和 Provider 运行时支持
- 优化 TTS 路由和 Gemini TTS 表现，补齐统一模型设置、Provider 元数据和更强的运行时覆盖
- 优化飞书插件打包，支持平台 bundle、发布 workflow，并更新插件打包文档
- 更新 TypeScript native preview、vue-tsgo、Provider registry 和 ACP registry 数据，提升当前工具链与运行时兼容性
- 修复图片路线的聊天预算处理，让生成图片请求避免不必要的上下文预算失败
- Added guided onboarding, voice input transcription, and a redesigned settings control center to make first setup and daily configuration easier
- Added agent image generation, OpenAI image settings, Mac computer use, manual compaction, and side panel fullscreen controls for more capable agent workflows
- Added Mistral, Xiaomi Token Plan regions, refreshed provider data, and improved model capability controls for broader model access
- Improved remote control across Feishu, Weixin, Discord, QQ Bot, Telegram, and WeChat iLink with richer media delivery and steadier streamed replies
- Improved ACP and agent runtime reliability with safer working-directory handling, context budgeting, session routing, tool output limits, and persisted turn metadata
- Improved chat and workspace responsiveness with smoother Markdown streaming, older-message pagination, YoBrowser activity feedback, and more native desktop interactions
- Hardened plugin MCP isolation, SVG and external-link handling, provider verification, config import compatibility, and SQLite upgrade recovery
- Updated bundled runtimes, AI SDK patch versions, Markstream rendering, provider registry data, and release packaging support for stable builds
- 新增引导式上手、语音输入转写和重新设计的设置控制中心，让首次配置与日常设置更顺手
- 新增 Agent 图片生成、OpenAI 图片设置、Mac 电脑使用、手动压缩和侧边栏全屏控制，提升 Agent 工作流能力
- 新增 Mistral、小米 Token Plan 多区域支持，刷新 Provider 数据，并优化模型能力控制，扩展模型接入范围
- 优化飞书、微信、Discord、QQ Bot、Telegram 与 WeChat iLink 远程控制，支持更丰富的媒体投递和更稳定的流式回复
- 优化 ACP 与 Agent 运行时可靠性，包括工作目录保护、上下文预算、会话路由、工具输出限制和 turn 元数据持久化
- 优化聊天与工作区响应表现，改进 Markdown 流式渲染、历史消息分页、YoBrowser 活动反馈和更原生的桌面交互
- 加强 Plugin MCP 隔离、SVG 与外部链接处理、Provider 验证、配置导入兼容性和 SQLite 升级恢复
- 更新内置运行时、AI SDK patch 版本、Markstream 渲染、Provider registry 数据与发布打包支持，面向稳定构建
- Added a redesigned settings control center with overview cards, grouped navigation, settings activity, and refined MCP, provider, and data panels
- Added a fullscreen toggle for the side panel and improved layout responsiveness across side panel and workspace views
- Added an isolated Feishu plugin settings surface with credential management, MCP presets, and plugin-owned MCP servers hidden from global MCP settings
- ACP client runtime now has clearer connection and session routing, debug logging, path guarding, and persisted turn metadata for steadier ACP sessions
- Weixin remote control now delivers generated images and avoids leaving silent pending interactions behind
- Feishu remote replies now send post payloads with the expected message shape
- Agent failed-message context is preserved more consistently after compaction and context-pressure errors
- Updated AI SDK patch versions and refreshed bundled provider and ACP registry data for fresher runtime compatibility
- 设置页升级为控制中心，新增概览卡片、分组导航、设置活动记录，并优化 MCP、Provider 与数据设置面板
- 新增侧边栏全屏切换，并优化侧边栏与工作区视图的布局响应表现
- 新增隔离的飞书插件设置页，支持凭证管理、MCP 预设，并从全局 MCP 设置中隐藏插件自有 MCP server
- ACP client runtime 现在具备更清晰的连接与会话路由、调试日志、路径保护和 turn 元数据持久化，让 ACP 会话更稳定
- 微信远程控制现在可以发送生成图片，并避免留下静默的 pending 交互
- 飞书远程回复现在会按预期消息结构发送 post payload
- Agent 在上下文压缩和上下文压力错误后，会更稳定地保留失败消息上下文
- 更新 AI SDK patch 版本，并刷新内置 Provider 与 ACP registry 数据，提升运行时兼容性新鲜度
- Added Mistral as a built-in provider, including model icons, provider catalog support, and deeplink handling
- Agent runs now budget tool schemas and tool output more defensively, reducing oversized context failures and follow-up stalls
- Context-window overflow errors now include budget diagnostics and try pressure recovery before failing oversized requests
- Feishu remote control replies now use optimized Markdown posts for headings, tables, lists, code blocks, and streamed updates
- Markdown streaming now stays smooth while messages are loading without leaving completed content in a streaming state
- Upgraded markstream-vue to 0.0.14-beta.8 for improved Markdown rendering behavior
- Agent terminal execution is steadier when shells, working directories, or context compaction need fallback handling
- Disabled providers no longer trigger verification requests from settings screens
- Plugin MCP servers now keep their lifecycle more isolated, improving start/stop behavior and built-in plugin visibility
- 新增 Mistral 内置 Provider，补齐模型图标、Provider 目录与 deeplink 支持
- Agent 运行会更谨慎地预算工具 schema 与工具输出，减少上下文过大和后续执行卡住的问题
- 上下文窗口溢出错误现在会带上预算诊断，并在失败前尝试恢复上下文压力
- 飞书远程控制回复改用优化后的 Markdown post，改善标题、表格、列表、代码块和流式更新
- Markdown 流式渲染只在消息加载中保持平滑，完成后的内容不会继续停留在流式状态
- markstream-vue 升级到 0.0.14-beta.8，改善 Markdown 渲染表现
- 当 shell、工作目录或上下文压缩需要 fallback 时，Agent 终端执行更稳定
- 设置页不会再对已禁用的 Provider 发起验证请求
- Plugin MCP server 的生命周期隔离更清晰，启动、停止和内置插件展示更可靠
- Agents can now generate images right inside chat, with OpenAI image settings available when you want more control
- Image previews and image actions feel smoother, especially around generated results and tool output
- Long conversations should feel lighter when you scroll back through older messages
- Sync and import are more forgiving when settings come from a different app version
- Mac computer use got a couple of driver updates, so window handling, clicking, and app control should be steadier
- Fixed a handful of everyday annoyances around Ollama, provider search, Windows command output, search docs, and empty computer-use settings messages
- Agent 现在可以直接在聊天里生成图片；需要细调时，也能设置 OpenAI 图片生成选项
- 图片预览和图片操作更顺了一些，生成结果和工具输出里的图片都更好处理
- 长对话回看历史时会轻快一点，旧消息加载不再那么吃劲
- 设置同步和导入更宽容了，从不同版本带来的备份也更稳
- Mac 电脑使用能力升级了几轮驱动，窗口处理、点击和控制应用会更稳
- 修了一批日常小毛病，包括 Ollama、模型服务商搜索、Windows 命令输出、搜索文档和电脑使用设置里的空提示
- Added Mac computer use capability for enhanced desktop automation
- Added launch at login and access controls for better app startup management
- Enhanced agent capabilities with improved model source derivation
- Upgraded markstream-vue for better stream rendering performance
- Fixed disabled provider models still appearing in model selection
- Fixed DeepSeek empty reasoning content handling
- Fixed file join failures in chat flows
- 新增 Mac 电脑使用功能，增强桌面自动化能力
- 新增开机启动与访问控制，优化应用启动管理
- 增强 Agent 功能，优化模型源选择逻辑
- 升级 markstream-vue，提升流式渲染性能
- 修复已禁用供应商模型仍在模型选择中显示的问题
- 修复 DeepSeek 空推理内容处理
- 修复聊天流程中的文件连接失败问题
- Added model fetching fallbacks for Anthropic and Gemini so provider model lists recover more reliably
- Added Xiaomi Token Plan providers for CN, SGP, and AMS regions
- Enhanced DeepSeek V4 compatibility across provider and model workflows
- Improved active chat input routing and tool-call image previews for clearer chat workflows
- Fixed agent and ACP workspace propagation, interleaved tool streams, and context budgeting for tool schemas
- 新增 Anthropic 与 Gemini 模型拉取 fallback，提升 Provider 模型列表恢复稳定性
- 新增小米 Token Plan 的 CN、SGP 与 AMS 区域 Provider
- 增强 DeepSeek V4 在 Provider 与模型流程中的兼容性
- 优化当前聊天输入路由与工具调用图片预览，让聊天流程更清晰
- 修复 Agent 与 ACP 工作区传递、交错工具流以及工具 schema 上下文预算处理
- Fixed attachment date metadata transfer across IPC payloads so attachment records stay valid in chat flows
- 修复附件日期元数据在 IPC 载荷中的传递，确保聊天流程中的附件记录保持有效
- Preserved interleaved reasoning output so mixed reasoning and answer streams stay in the correct order
- Updated the Markstream renderer to the stable 0.0.13 release for more reliable Markdown streaming
- Improved chat message transitions, sidebar updates, and side panel rendering performance
- Fixed RTK and built-in knowledge configuration status handling across MCP tool setup flows
- 保留交错 reasoning 输出顺序，确保 reasoning 与正文混合流式内容按预期展示
- 将 Markstream 渲染器更新到稳定版 0.0.13，提升 Markdown 流式渲染可靠性
- 优化聊天消息动效、侧边栏更新与侧边面板渲染性能
- 修复 RTK 与内置知识库配置状态处理，完善 MCP 工具配置流程
- Improved remote control media delivery across Discord, Feishu, QQ Bot, Telegram, and WeChat iLink, including block streaming and file handling
- Fixed ACP working directory propagation for remote executions so agent commands run in the intended workspace
- Added batch model status updates to reduce provider model list churn and keep model management more responsive
- Hardened renderer model capability detection, external URL opening, and SVG sanitization against stale state and unsafe links
- Fixed RTK runtime startup when the expected hook is missing, improving agent runtime resilience on affected installs
- 优化 Discord、飞书、QQ Bot、Telegram 与微信 iLink 的远程控制媒体投递，完善块流式输出与文件处理
- 修复远程执行中的 ACP 工作目录传递，确保 agent 命令在预期工作区运行
- 新增模型状态批量更新，减少 Provider 模型列表抖动并提升模型管理响应速度
- 加强渲染端模型能力检测、外部链接打开与 SVG 清理，避免过期状态和不安全链接
- 修复缺少预期 hook 时 RTK runtime 启动失败的问题，提升受影响安装环境下的 agent runtime 韧性
- Added DeepSeek V4 series model support and refreshed provider model data for more complete default model availability
- Migrated model requests to the AI SDK runtime for more consistent provider behavior, streaming, prompt cache, and tool calling
- Expanded remote control into a unified multi-channel setup with Discord, QQ Bot, and WeChat iLink support
- Added project workspace directories, privacy mode, inline chat session renaming, long user message collapse, and improved new chat entry behavior
- Added NewAPI and Astraflow (ModelVerse) provider support, richer model capability controls, request timeout settings, and more reliable model list management
- Improved desktop security, startup responsiveness, embedded browser resizing, image paste submission, Gemini compatibility, and SQLite upgrade recovery
- Added Sharp native package hoisting to keep image processing dependencies available in release builds
- 新增 DeepSeek V4 系列模型支持，并刷新 Provider 模型数据，提升默认模型可用性覆盖
- 将模型请求迁移到 AI SDK 运行时，提升 Provider 行为、流式输出、Prompt Cache 与工具调用一致性
- 远程控制升级为统一多渠道配置，新增 Discord、QQ Bot 与微信 iLink 支持
- 新增项目工作区目录、隐私模式、会话内联重命名、长用户消息折叠，并优化新建会话入口体验
- 新增 NewAPI 与 Astraflow（ModelVerse）Provider，补充模型能力控制、请求超时配置与更稳定的模型列表管理
- 提升桌面端安全性、启动响应、内嵌浏览器尺寸调整、图片粘贴提交、Gemini 兼容性与 SQLite 升级恢复稳定性
- 增加 Sharp 原生包 hoist 配置，确保图片处理依赖在 release 构建中可用
- Added model initialization in settings so ModelSelect respects the current chat mode and restores default model controls more reliably
- Added ACP registry icon request handling in the floating widget to improve agent icon rendering and related session visuals
- Simplified YoBrowser host readiness handling to keep the embedded browser lifecycle more predictable
- 新增设置页模型初始化流程，使 ModelSelect 更准确地遵循当前聊天模式，并提升默认模型配置恢复稳定性
- 新增悬浮组件中的 ACP registry 图标请求处理，优化 Agent 图标渲染与相关会话视觉表现
- 精简 YoBrowser host readiness 处理逻辑，提升内嵌浏览器生命周期的可预测性
- Added privacy mode and inline chat session renaming to improve workspace discretion and session organization
- Added request timeout controls with a higher default range, and refined Kimi fixed-temperature plus Gemini v1beta compatibility handling
- Improved startup and runtime responsiveness through asynchronous icon loading, store initialization cleanup, and more stable navigation payload normalization
- Hardened desktop security by enabling Electron context isolation and disabling node integration for embedded web contents
- Fixed several workflow regressions across trackpad scrolling, new thread entry visibility, project clearing, timeout propagation, and upgraded SQLite/provider recovery
- 新增隐私模式与会话内联重命名，提升工作区信息保护和会话整理效率
- 新增请求超时配置并扩展默认范围，同时优化 Kimi 固定温度策略与 Gemini v1beta 兼容处理
- 通过异步图标加载、store 初始化清理与导航载荷规范化，改善启动速度和运行时响应性
- 强化桌面端安全基线，为内嵌 Web 内容启用 Electron context isolation 并关闭 node integration
- 修复触控板滚动、新建会话入口显隐、项目清空选择、超时参数传递，以及升级后 SQLite/provider 恢复等多项流程问题
- Recovered missing SQLite
deepchat_sessionscolumns on upgraded installs to restore stable session persistence - 修复升级安装后 SQLite
deepchat_sessions缺失列的问题，恢复会话持久化稳定性
- Added Anthropic temperature support in model capability controls
- Added
noneandxhighreasoning effort options for supported models - Improved sidebar session pin feedback and stabilized session group identity handling
- Refined app update installation by cleaning up floating windows before relaunch
- Added Astraflow (ModelVerse) provider support and removed the deprecated Laoshi provider
- Added project-based workspace directories with drag-and-drop setup support
- Enhanced the floating agent widget to support all agents with more stable session handling
- Improved Anthropic reasoning routing and capped derived max token defaults for safer model setup
- 为模型能力配置补充 Anthropic temperature 支持
- 为受支持模型新增
none与xhighreasoning effort 选项 - 优化侧栏会话 pin 反馈，并稳定会话分组标识处理
- 在应用更新安装前清理悬浮窗口，提升升级流程稳定性
- 新增 Astraflow（ModelVerse）Provider 支持，并移除已废弃的 Laoshi Provider
- 新增基于项目目录的工作区管理能力，并支持拖拽接入工作区
- 增强悬浮 Agent 按钮，支持全部 Agent 并提升会话管理稳定性
- 优化 Anthropic reasoning 路由，并限制推导出的默认 max tokens，降低模型配置风险
- Expanded remote control into a unified multi-channel setup with Discord, QQ Bot, and WeChat iLink support
- Added default collapsing for long user messages so dense chats stay readable while attachments remain fully visible
- Polished the new conversation entry flow with a persistent collapsed-sidebar
+action and a shorter default input box - Improved streaming responsiveness by reducing renderer reflow and translate popup overhead during live updates
- Fixed ACP terminal permission approval bridging so streamed permission requests stay intact during execution
- 远程控制升级为统一多渠道配置流程，新增 Discord、QQ Bot 与微信 iLink 支持
- 为超长用户消息加入默认折叠，保留附件完整展示，提升长会话可读性
- 打磨新建会话入口体验，在折叠侧栏下保留常驻
+按钮，并缩短默认输入框高度 - 降低流式更新期间的渲染回流与翻译弹窗开销，提升消息流动顺滑度
- 修复 ACP 终端权限审批桥接流程，保证执行期间的流式权限请求信息完整传递
- Migrated model requests to the AI SDK runtime, improving prompt cache behavior, provider consistency, and streaming stability
- Added NewAPI provider support and refined compatible endpoint configuration
- Improved model management with more stable provider toggles and synchronized Ollama selectable model status
- Added
skill_viewdraft flow and automatic tool activation after skill previews to smooth skill setup - Enhanced Markdown and workspace link navigation, added sidebar panel toggle hotkeys, and fixed artifact viewer sizing in the side panel
- 将模型请求迁移到 AI SDK 运行时，进一步改善 Prompt Cache 表现、Provider 一致性与流式稳定性
- 新增 NewAPI Provider 支持，并完善兼容端点配置体验
- 改进模型管理，修复 Provider 模型开关稳定性并同步 Ollama 可选模型状态
- 新增
skill_view草稿流，并在技能预览后自动激活工具，减少技能接入摩擦 - 优化 Markdown 与工作区链接跳转体验，新增侧栏面板切换快捷键，并修复侧边栏制品预览高度问题
- Added provider model list filtering and sorting, and now remembers the sidebar session grouping mode
- Added ACP Agent uninstall support and refined provider prompt cache configuration
- Improved remote delivery ordering for Telegram and Feishu, and fixed db-backed model list sync stability
- Refined dashboard and settings responsiveness, and fixed auto compact settings persistence
- 新增 Provider 模型列表筛选排序能力，并记住侧边栏会话分组方式
- 新增 ACP Agent 卸载支持，并完善 Provider Prompt Cache 配置体验
- 优化 Telegram 与 Feishu 远程消息投递顺序，修复数据库驱动模型列表同步稳定性
- 改进仪表盘与设置页响应式布局，并修复自动压缩设置保存问题
- Added in-chat search and Spotlight global search for faster access to messages and app entry points
- Improved the provider database refresh flow and added manual model config refresh
- Updated the Markdown renderer preprocessing flow to improve rendering stability
- Fixed rate limit handling to reduce failures and degraded request experience
- 新增会话内搜索与 Spotlight 全局搜索，方便快速定位历史消息与应用入口
- 优化 Provider 数据库刷新流程，支持手动刷新模型配置
- 更新 Markdown 渲染器预处理逻辑，提升消息渲染稳定性
- 修复速率限制处理问题，减少请求受限时的异常体验
- DeepChat 1.0 正式发布：完成全新 Agent 架构切换，统一 DeepChat Agent 与 ACP Agent 主流程，并内置 DimCode Agent
- 新增远程控制能力矩阵：支持 Telegram、Feishu 与 ACP Agent Remote，补齐权限消息、流式块渲染与工作目录选择
- 强化工作流与工具链：支持 RTK 工具调用、Environments、Provider Deeplink 导入、Workspace 拖拽引用与 DeepChat Sub Agent 协作
- 持续打磨桌面端体验：新增浮动窗口、用户仪表盘、自动压缩控制，并优化侧边栏、悬浮按钮、状态栏与工具调用交互
- 完成正式版稳定性收敛：修复 HTML 预览、主题同步、消息标题选择、会话工作目录、MCP 生命周期与历史序列化等问题
- 新增 Novita AI LLM 提供商接入
- 新增 Provider 配置导入能力（Deeplink 导入）
- 新增 Feishu Bot 远端接入能力
- 改进悬浮窗与侧边栏交互体验：SessionItem 由右键菜单切换为 hover/浮层交互，浮动按钮 hover 与透明度细节优化
- 修复消息标题选择与 MCP 生命周期相关稳定性问题，并清理已过期 MCP Server
- 新增 Telegram Remote Control，可通过 Telegram 远程查看与驱动会话，远程控制配置也已接入设置页
- 统一 DeepChat Agent 与 ACP Agent 的 Agent 能力和入口，补齐欢迎页、本地化文案与默认配置，整体使用路径更一致
- 优化会话默认工作目录传递，修复 Agent / ACP / Skills 在 session workdir 继承上的问题
- 强化启动与工具输出稳定性，修复 Splash 窗口显示时机，并为大体量工具输出增加保护与批处理适配
- 移除过时 MCP UI 支持，修复 OpenAI Responses 历史序列化问题，同时继续打磨状态同步与路由细节
- 优化启动 Splash 窗口与 ACP 配置加载提示，启动过程更直观
- 支持 ACP Registry 搜索安装与 ACP 模型选择，ACP Agent 配置体验继续完善
- 新增会话 steer / queue 能力，支持待发送消息排队、转向与恢复处理
- 打磨工具调用卡片、状态栏控制与更新入口，整体交互更顺手
- 修复 OpenAI Compatible MCP 工具、interleaved thinking，以及队列与 stop 状态同步等问题
- 新增浮动窗口，全新效果一目了然
- 增加用户仪表盘，token使用一目了然
- 重构内建工具链，支持 RTK 工具调用，控制和性能都有提升
- 新增 Environments 设置，方便为不同场景管理独立运行配置
- 修复全新安装时 SQLite 迁移冲突问题，提升首次启动稳定性
- 新增浮动窗口，全新效果一目了然
- 增加用户仪表盘，token使用一目了然
- 重构内建工具链，支持 RTK 工具调用，控制和性能都有提升
- 统一 Workspace 生命周期刷新，清理旧代码，提升整体稳定性
- 新增自动压缩控制，可在设置中配置会话摘要压缩行为
- 优化 Yo Browser 生命周期与迁移流程，提升稳定性
- 强化 Skills 运行时执行安全，并补齐欢迎页自定义能力
- 修复多项界面问题，包括 Agent 文案对齐、语音输入按钮显示与悬浮按钮细节
- 全新 Agent 架构：重构 Agent UI 与 Agent Loop，模块化流处理，统一代码路径
- 移除 Chat 模式：简化模式选择，仅保留 Agent 和 ACP Agent 两种模式
- 默认模型配置系统：新增默认模型与默认视觉模型全局设置
- 内置 DimCode Agent：预置 ACP Agent，开箱即用的代码助手
- OpenAI 默认改为 Responses API
- 支持了 Telegram/Discord/Confirmo 通知
- 支持任务生命周期 hooks
- 修复少量 Bug
- 完善 Skills 支持
- Agent 现在可以生成可交互的提问信息
- 增加 Voice.ai 为新供应商
- 修复大量 Bug
- 全新 Skills 管理系统，支持技能安装、同步与多平台适配
- 新增 o3.fan 提供商、优化工具调用（大型调用卸载、差异块展示、权限管理）、性能提升（消息列表虚拟滚动、流式事件批处理调度）
- 修复多项问题：Ollama 错误处理、滚动定位、聊天输入高度、macOS 全屏等
- All-new Skills management system with installation, sync, and multi-platform adapters
- Added o3.fan provider, enhanced tool calls (offloading, diff blocks, permissions), performance boost (message list virtual scrolling, batched stream scheduling)
- Fixed multiple issues: Ollama error handling, scroll positioning, chat input height, macOS fullscreen, etc.
- 全面重构 Agent 与会话架构：拆分 agent/session/loop/tool/persistence，替换 Thread Presenter 为 Session Presenter，强化消息压缩、工具调用、持久化与导出
- 增强搜索体验：新增 Search Presenter 与搜索提示模板，完善搜索助手与搜索引擎配置流程
- 加固权限与数据：新增命令权限缓存/服务，更新模型与提供商数据库，并补充多语言 i18n 文案
- Agent and session architecture refactor (agent/session/loop/tool/persistence) with Session Presenter replacing Thread Presenter to improve compression, tool calls, persistence, and exports
- Better search experience via new Search Presenter and prompt templates, refining the search assistant and engine setup
- Hardened permissions and data updates with command permission cache/service, refreshed provider/model DB, and broader i18n coverage
- 全新 Agent Mode，支持 RipGrep 等数十项新特性
- 全新子会话概念，随时针对会话中任意消息单独讨论
- 修复一些已知问题
- ACP Agent 可以直接使用软件里面配置的 MCP
- All-new Agent Mode with dozens of new features, including RipGrep
- New sub-session concept: discuss any message in a conversation at any time
- Fixed some known issues
- ACP Agent can directly use the MCP configured in the app
- Markdown 优化，修复列表元素异常
- 修复 Ollama 视觉模型图片格式
- Improved Markdown rendering, fixed list element issues
- Fixed Ollama vision model image format
- 全新 Yo Browser 功能，让你的模型畅游网络
- All-new Yo Browser lets your model roam the web
- 优化 ACP 体验,增加 ACP 调试能力
- 增加了自定义软件字体能力
- add acp process warmup and debug panel
- add font settings
- add Hebrew (he-IL) Translation