Skip to content

DeepChat Release Notes

ThinkInAIXYZ · DeepChat is an AI assistant for macOS, distributed as a graphical app with a `deepchat` command-line binary.

CaskAI ToolsAuto-updates 6.4K
Install command
brew install --cask deepchat
30-day installs
10
#2039 in App
1-year installs
326
Last 365 days
Latest version
1.1.4
Download size
421MB
dmg
Release cadence
Weekly
4 releases in 30 days
  1. 19022687016

    Latest

    GitHub Release

    DeepChat V0.4.4

    🚀 DeepChat 0.4.4 正式发布 | 重新定义你的 AI 对话体验!

    —— 不再是简单的 ChatBot,而是你的自然语言 Agent 工具🌟

    • 重新设计了数据备份及导入流程,调整为新的架构,存在不兼容变更
    • 内置增加 Nowledge(MCP)
    • 支持国际化检查,新增 @lingual/i18n-check 依赖
    • 增加空系统提示选项和自定义提示同步能力
    • 话题线程系统重构,优化对话生命周期
    • 修复快捷方式失效、同步自定义提示后设置等多个问题
    • 更新 models 数据库,清理无用依赖和日志
    • MentionList 支持类别索引优化,组件性能提升
    • Markdown 渲染器升级,数学公式与矩阵渲染更完善
    • 多项代码样式工具升级,包括 prettier 插件和 electron 至 37.8.0
    • 增加 SVGSanitizer 最大尺寸控制
    • 补全和优化部分注释翻译及 i18n 配置

    English Release Notes

    • Redesign of data backup and import process with breaking changes to architecture
    • Added Nowledge MCP
    • Added support for internationalization check with @lingual/i18n-check dependency
    • Added empty system prompt option and enhanced prompt synchronization
    • Refactored thread/conversation lifecycle for better topic management
    • Fixed issues for shortcut failure and custom prompt sync after setting
    • Updated models database, removed unused dependencies and logs
    • MentionList component now optimizes category index management and performance
    • Upgraded markdown renderer – better mathematical formula and matrix handling
    • Upgraded code style tools, including prettier plugin and electron 37.8.0
    • Added maxSize option to SVGSanitizer
    • Improved and completed i18n for comments and prompt settings 🔥 为什么选择 DeepChat?

    ✅ 商业友好:基于原版 Apache License 2.0 开源,无任何协议外的额外约束,面向开源。 ✅ 开箱即用:极简配置,即刻开启你的智能对话之旅。 ✅ 极致灵活:自由切换模型,自定义模型源,满足你多样化的对话和探索需求。 ✅ 体验绝佳:LaTeX 公式渲染、代码高亮、Markdown 支持,模型对话从未如此顺畅。 ✅ 持续进化:我们倾听用户反馈,不断迭代更新,为你带来更卓越的 AI 对话体验。

    📥 立即体验未来

    💬 反馈有礼:欢迎提交你的宝贵建议,加入 VIP 用户社群,与我们一同塑造 DeepChat 的未来!

  2. 1.1.4

    Patch

    GitHub Release Added to Homebrew

    CompatibilitymacOS 12 or later

    v1.1.4 (2026-11-12)

    • Refreshed the desktop interface with a unified sidebar, searchable settings, compact ACP Agent details, and a message minimap with scrollable previews
    • Moved conversation search into global search, prioritized matching titles, and fixed accidental selection when confirming input method text
    • Select an Agent in the new-chat composer while preserving Agent-specific drafts, models, and workspace defaults. Open the workspace and browser before sending the first message, and copy session references between chats
    • Added opt-in interactive HTML visualizations in chat and moved Markdown infographics into an isolated renderer
    • Added per-Agent tool mode and proactive collaboration settings, with proactive collaboration enabled for new Agents. Default output budgets now use the model's output limit within the context budget. Fixed subagent model selection, resumed execution settings, stop reason reporting, and access from Code Mode
    • Separated the built-in Agent runtime from desktop dependencies and verified persistence, permissions, cancellation, and recovery in standalone Node.js. Unified MCP settings across windows and consolidated chat session state
    • Improved provider model discovery and refresh, connection-test model selection, and GitHub Copilot sign-in. Added providers including Atlas Cloud, LiteLLM, Wally, Standard Compute, UberLLM, OpenLLM, and Wiro AI
    • Fixed MCP OAuth issuer and callback handling, and added optional MCP presets for search, media generation, and hosting, including Parallel Search, Webz, EvoLink, deed.page, Bowmark, and Sofya
    • Improved file watcher recovery and reduced unnecessary Git watching. Fixed question dialogs lingering after an answer and preserved literal braces in HTML chat exports
    • Completed French interface and native menu translations, updated Electron and bundled runtimes, removed built-in RTK command rewriting, and refreshed the model and ACP catalogs
    • 刷新桌面界面,统一侧栏,支持搜索设置,精简 ACP Agent 详情,并为消息地图增加可滚动预览
    • 将会话搜索整合到全局搜索,优先展示标题匹配的会话,并修复使用输入法确认文字时误选结果的问题
    • 可在新对话输入框直接选择 Agent,保留各 Agent 的草稿、模型和工作区默认值。发送首条消息前即可打开工作区和浏览器,也可在对话间复制会话引用
    • 对话支持按需启用交互式 HTML 可视化,Markdown 信息图在隔离环境中渲染
    • 支持为各 Agent 设置工具模式和主动协作,新建 Agent 默认开启主动协作。默认输出预算在上下文预算内采用模型的输出上限。修复子代理模型选择、恢复执行时的配置、停止原因上报,以及 Code Mode 调用子代理的问题
    • 将内置 Agent 运行时与桌面依赖解耦,在独立 Node.js 环境验证持久化、权限、取消与恢复。统一各窗口的 MCP 设置,并整合会话状态
    • 改善服务商模型发现与刷新、连接测试中的模型选择,以及 GitHub Copilot 登录。新增 Atlas Cloud、LiteLLM、Wally、Standard Compute、UberLLM、OpenLLM 和 Wiro AI 等服务商
    • 修复 MCP OAuth 授权服务地址匹配与回调处理,新增 Parallel Search、Webz、EvoLink、deed.page、Bowmark、Sofya 等可选 MCP 预设,覆盖搜索、媒体生成和托管
    • 改善文件监听的故障恢复,缩小 Git 监听范围。修复回答后提问对话框滞留的问题,并在导出 HTML 对话时保留原始花括号
    • 补全法语界面和原生菜单翻译,升级 Electron 与内置运行时,移除内置 RTK 命令改写,并刷新模型和 ACP 目录
  3. 1.1.4-beta.9

    Pre-release

    GitHub Release

    v1.1.4-beta.9 (2026-11-04)

    • Decoupled the built-in Agent runtime from desktop dependencies and added standalone Node.js verification for persistence, permissions, cancellation, and recovery
    • Unified MCP settings across windows and consolidated chat session state management
    • Refreshed the bundled model and ACP catalogs
    • 将内置 Agent 运行时与桌面依赖解耦,并新增独立 Node.js 验证,覆盖持久化、权限、取消与恢复
    • 统一主窗口与设置窗口的 MCP 设置,并整合聊天会话状态管理
    • 刷新内置模型与 ACP 目录
  4. 1.1.4-beta.8

    Expand

    GitHub Release

    v1.1.4-beta.8 (2026-11-03)

    • Provider model refreshes now contact the current catalog source, show sync status, and preserve existing models on failure
    • Improved gateway model capability detection, connection-test model lists, and model selection after the first connection
    • Enabled proactive collaboration by default for new Agents and added an Agent-level setting
    • Fixed subagents ignoring their configured default models and preserved their execution settings when resuming
    • Added the cheapaimodel, xxapi, llm.buzz, Obscurify.ai, and Wally providers, plus the Bowmark web data MCP preset
    • Updated dependencies with security fixes and refreshed the bundled model and ACP catalogs
    • 修复服务商模型刷新未请求当前目录来源的问题,展示同步状态,并在刷新失败时保留已有模型
    • 改善网关模型能力识别、连接测试模型列表,以及首次连接后的模型选择同步
    • 新建 Agent 默认启用主动协作,并支持为各 Agent 单独设置
    • 修复子代理忽略自身默认模型配置的问题,并在恢复执行时保留其运行设置
    • 新增 cheapaimodel、xxapi、llm.buzz、Obscurify.ai 和 Wally 服务商,以及 Bowmark 网页数据 MCP 预设
    • 更新依赖以修复安全问题,并刷新内置模型与 ACP 目录
  5. 1.1.4-beta.7

    Expand

    GitHub Release

    v1.1.4-beta.7 (2026-10-28)

    • 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
  6. 1.1.4-beta.6

    Expand

    GitHub Release

    v1.1.4-beta.6 (2026-10-22)

    • 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
  7. 1.1.4-beta.5

    Expand

    GitHub Release

    v1.1.4-beta.5 (2026-10-20)

    • 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
  8. 1.1.4-beta.4

    Expand

    GitHub Release

    v1.1.4-beta.4 (2026-10-19)

    • 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
  9. 1.1.4-beta.3

    Expand

    GitHub Release

    v1.1.4-beta.3 (2026-10-12)

    • 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
  10. 1.1.3

    Expand

    OpenNavo editorial Added to Homebrew

    CompatibilitymacOS 12 or later

    Adds device sync, memory integrations and inspection tools, conversation references, provider options, and ACP extensions. Updates scheduling and attachment workflows, removes the built-in plan tool while preserving old records, and includes security-related dependency fixes.

    Memory
    Added automatic two-way device sync and optional memory integrations.Added inspectable memory evidence, dependency review, and reflection retries.
    Chat
    Reference past conversations with @ or by dragging them from the sidebar.Added file paths, a collapsible upload area, and compact token usage.Scheduled tasks now have templates, run history, and a leave guard.
    Platform
    Added ChatGPT sign-in, provider options, and Lody ACP extensions.Removed the built-in plan tool; existing plan records remain readable.Updated Electron and Node.js; refreshed catalogs and security dependencies.

    DeepChat 1.1.3 adds automatic two-way device synchronization, a Codex-compatible Nowledge Mem integration, and an optional bundled Memcode memory plugin. Memory features include inspectable evidence with lineage, review of dependent memories before edits or deletion, optional pruning of stale tool results, and retries for failed reflections.

    Native chats can reference prior conversations with @ or by dragging them from the sidebar. The update also revises file attachments, token-usage display, and scheduled-task management. OpenAI gains a ChatGPT sign-in option; the connection-test model picker gains search and an enabled-only filter. Lody ACP client extensions cover elicitation forms, plan and usage reporting, subagent events, and session steering.

    The built-in agent plan tool and progress panel are removed, but existing plan tool records remain readable. The release also lists new provider and MCP presets, hardening and workflow fixes, and updates Electron to 43.7.0 and bundled Node.js to 24.21.0, alongside refreshed catalogs and security-related dependency fixes.

    Official release notes

  11. 1.1.3-beta.7

    Expand

    GitHub Release

    v1.1.3-beta.7 (2026-10-08)

    • 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
  12. 1.1.3-beta.6

    Expand

    GitHub Release

    v1.1.3-beta.6 (2026-10-07)

    • 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
  13. 1.1.3-beta.5

    Expand

    GitHub Release

    v1.1.3-beta.5 (2026-10-03)

    • 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
  14. 1.1.3-beta.4

    Expand

    GitHub Release

    v1.1.3-beta.4 (2026-10-02)

    • 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
  15. 1.1.3-beta.3

    Expand

    GitHub Release

    v1.1.3-beta.3 (2026-09-30)

    • 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
  16. 1.1.3-beta.2

    Expand

    GitHub Release

    v1.1.3-beta.2 (2026-09-26)

    • 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
  17. 1.1.3-beta.1

    Expand

    GitHub Release

    v1.1.3-beta.1 (2026-09-23)

    • 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
  18. 1.1.2

    Expand

    OpenNavo editorial

    Adds workspace and plugin capabilities, chat navigation, keyboard access, and locales; restores DeepSeek Responses features and addresses memory, database, credential, and background-load issues.

    Workspace
    Adds an Open With picker and Codex-compatible plugin package management.Adds Tibetan, Uyghur, and Mongolian locales and full keyboard navigation.
    Chat & tools
    Adds message navigation, type-to-focus, providers, and MCP examples.Restores DeepSeek Responses tool streaming, web search, and follow-up replay.
    Reliability
    Repairs memory and legacy database recovery; hardens credential handling.Adds dependency security patches and refreshes built-in catalogs.

    DeepChat 1.1.2 adds an Open With picker for workspace files. It detects editors and terminals, remembers preferences, and falls back to the system default when needed. Users can install and manage Codex-compatible plugin packages from Git repositories, ZIP archives, and local folders, with Skills, supported context hooks, and MCP configurations. Workspace Skills are discovered from the current project directory and their contents are preserved when resuming a session.

    Chat adds a scroll-to-latest control, a message map that counts messages below the viewport and jumps to a selected message, and type-to-focus. Tibetan, Uyghur, and Mongolian locales and full keyboard navigation are added. New providers are API Route, Cheaper Inference, and AnonRouter; MCP examples include You.com, Serply, and Baizhi. DeepSeek Responses tool streaming, native web search, and follow-up replay are restored.

    The release hardens OAuth credential storage and provider credential validation, protects recalled memory text against forged prompt markers, and repairs memory recall, extraction, atomicity, and recovery. It restores support for partially migrated legacy databases and macOS browser preview capture. Changes to reduce stalls and background load include asynchronous backup reads, coalesced model discovery, batched preference lookups, canceled embeddings, and faster Tape reads and message rendering. Dependencies receive security patches; Electron is capped at 43.6.0, markstream-vue is upgraded to 2.0.11, and built-in model and ACP catalogs are refreshed. Official release

  19. 1.1.2-beta.5

    Expand

    GitHub Release

    v1.1.2-beta.5 (2026-09-10)

    • 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
  20. 1.1.2-beta.4

    Expand

    GitHub Release

    v1.1.2-beta.4 (2026-09-09)

    • 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
  21. 1.1.2-beta.3

    Expand

    GitHub Release

    v1.1.2-beta.3 (2026-09-08)

    • 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
  22. 1.1.2-beta.2

    Expand

    GitHub Release

    v1.1.2-beta.2 (2026-09-07)

    • 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
  23. 1.1.2-beta.1

    Expand

    GitHub Release

    v1.1.2-beta.1 (2026-09-04)

    • 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
  24. 1.1.1

    Expand

    GitHub Release

    v1.1.1 (2026-08-31)

    • 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