DeepChat: baixar versions anteriors

v1.1.3 (2026-10-09)
- 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

v1.1.2 (2026-09-20)
- 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

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

v1.1.0 (2026-08-11)
- 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 deepchat CLI 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 deepchat CLI，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

v1.0.9 (2026-07-10)
- 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

v1.0.8 (2026-07-10)
- 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

v1.0.7 (2026-06-25)
- 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

v1.0.6 (2026-06-22)
- 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

v1.0.5 (2026-06-05)
- Added scheduled tasks, agent progress todos, session transfer, session tape memory, and remote /agent commands 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

v1.0.4 (2026-05-15)
- 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

v1.0.3 (2026-04-24)
- 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

v1.0.2 (2026-04-08)
- 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

v1.0.1 (2026-04-02)
- 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

v1.0.0 (2026-03-31)
- 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

v0.5.8 (2026-02-09)
- 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

v0.5.7 (2026-02-05)
- 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

🚀 DeepChat 0.5.3 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🌟
🔥 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
- 增加了希伯来语翻译
- 优化 ACP 体验，创建 ACP 对话速度更快
- 增加了自定义软件字体能力
- 增加了 ACP 调试界面，方便开发 ACP Agent
💬 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！
🎮 加入 Discord 社区：https://discord.gg/6RBatENX

🚀 DeepChat 0.5.3 Official Release | Redefine Your AI Conversation Experience!
—— Not just a simple ChatBot, but your natural language Agent tool 🌟
🔥 Why Choose DeepChat?
✅ Business-Friendly: Open source under Apache License 2.0, with no additional constraints beyond the license, truly open source.
✅ Ready to Use: Minimal configuration, start your intelligent conversation journey immediately.
✅ Ultra Flexible: Freely switch models, customize model sources, meet your diverse conversation and exploration needs.
✅ Excellent Experience: LaTeX formula rendering, code highlighting, Markdown support, model conversations have never been smoother.
✅ Continuous Evolution: We listen to user feedback, continuously iterate and update, bringing you an even better AI conversation experience.
📥 Experience the Future Now
- add Hebrew (he-IL) Translation
- add acp process warmup
- add font settings
- add acp debug view
💬 Feedback Welcome: We welcome your valuable suggestions, join the user community, and shape the future of DeepChat together!
🎮 Join Discord Community: https://discord.gg/6RBatENX
What's Changed
- fix: Multiple Issues Affecting Conversation Flow and Model Settings by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1166
- feat: Hebrew (he-IL) Translation by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1157
- feat: add custom font setting by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1167
- fix: font setting not work on settings page by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/1169
- style: unify scroll bar style by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/1173
- feat: acp init and process manage by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1171
- chore: update markstream-vue to version 0.0.3-beta.3 by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/1176
- fix: increase button size for web content limit adjustment by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/1177
- fix: close app kill all acp processes by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1175
- feat: add shell to powerpack by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1178
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.5.2...v0.5.3

🚀 DeepChat 0.5.1 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🌟
- 新增 DeepSeek V3.2 Thinking 模型支持：为复杂推理场景提供更好的思考链路和响应质量
- 集成 DeepChat 到 nowledge-mem：实现一键导入对话内容到知识库，方便长期记忆与检索
- i18n 新增丹麦语支持：持续完善多语言体验
- 优化 DeepLink 一键唤起逻辑：修复偶现的一键跳转失败问题，提升使用成功率
- Added DeepSeek V3.2 Thinking model support: Provides improved reasoning chains and response quality for complex use cases
- Integrated DeepChat into nowledge-mem: Enables one-click import of conversations into the knowledge base for long-term memory and retrieval
- Extended i18n with Danish language support: Continues to improve the multilingual experience
- Refined DeepLink one-click invocation logic: Fixed occasional failures, improving the success rate of DeepLink usage
🔥 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！
🎮 加入 Discord 社区：https://discord.gg/6RBatENX

🚀 DeepChat 0.5.1 Official Release | Redefine Your AI Conversation Experience!
—— Not just a simple ChatBot, but your natural language Agent tool 🌟
🔥 Why Choose DeepChat?
✅ Business-Friendly: Open source under Apache License 2.0, with no additional constraints beyond the license, truly open source.
✅ Ready to Use: Minimal configuration, start your intelligent conversation journey immediately.
✅ Ultra Flexible: Freely switch models, customize model sources, meet your diverse conversation and exploration needs.
✅ Excellent Experience: LaTeX formula rendering, code highlighting, Markdown support, model conversations have never been smoother.
✅ Continuous Evolution: We listen to user feedback, continuously iterate and update, bringing you an even better AI conversation experience.
📥 Experience the Future Now
💬 Feedback Welcome: We welcome your valuable suggestions, join the user community, and shape the future of DeepChat together!
🎮 Join Discord Community: https://discord.gg/6RBatENX
What's Changed
- chore: upgrade markstream-vue and stream-monaco by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/1133
- fix: update kimi init script and acp command by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1134
- feat: import deepchat to nowledge-mem by @fatelei in https://github.com/ThinkInAIXYZ/deepchat/pull/1132
- fix: fix first chat error loading timing by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/1137
- fix: deeplink one click by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1138
- feat: i18n add da dk by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1139
- chore: update providers in readme by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1140
- feat: implement paralleled vectorizing and thread-safe processing in … by @Blackjack200 in https://github.com/ThinkInAIXYZ/deepchat/pull/1111
- chore: migrate node-pty to beta version by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1144
- feat: add vertex support by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1145
- fix: fix tooltip content not hiding by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/1146
- fix: fix monaco vertical scroll by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/1147
- chore: upgrade markstream-vue by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/1148
- feat: add deepseek v3.2 thinking by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1151
New Contributors
- @fatelei made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/1132
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.5.0...v0.5.1

🚀 DeepChat 0.4.3 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🌟
🔧 New Features
- Ollama: Support for custom providers
Added capability to define and use custom provider endpoints for Ollama models, with updated icon representation for better UI consistency.
🧰 Improvements
- Settings Panel Enhancements
- Restored auto-approve toggles and provider verification dialog for Model Configuration Panel (MCP).
- Optimistically updates provider and model toggles for smoother UX.
- Merged stored provider models for better consistency across sessions.
- AppBar Adaptation
- Fixed background display issues on Windows versions earlier than 11.

🔧 新增功能
- Ollama：支持自定义模型提供商
新增可自定义 Ollama 模型提供商的功能，并更新了自定义提供商的图标样式，使界面更加统一。
🧰 功能优化
- 设置面板改进
- 恢复了 自动批准开关 与 模型提供商验证对话框（MCP 模块）。
- 优化了模型与提供商切换逻辑，切换时即时更新界面状态。
- 合并本地存储的提供商模型信息，保证多会话一致性。
- 顶部栏适配
- 修复了在 Windows 11 以下版本中应用栏背景显示异常的问题。
🔥 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！
What's Changed
- fix: restore MCP auto approve toggles and provider verification dialog by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1045
- feat(ollama): support custom providers by @Dw9 in https://github.com/ThinkInAIXYZ/deepchat/pull/1046
- Fix/win10 appbar by @deepinfect in https://github.com/ThinkInAIXYZ/deepchat/pull/1048
- fix: improve optimistic toggles in settings store by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1049
- fix: merge stored provider models when refreshing settings by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1051
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.4.2...v0.4.3

🚀 DeepChat 0.4.2 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🌟
- Markdown 渲染器升级： 增强了 markdown 渲染功能，支持新的表格样式和 markdown 布局样式。
- LLM 提供商增强： 集成了新的 LLM 提供商 jiekou.ai ,zenmux，并更新了提供商配置以提升性能和灵活性。
- UI 改进： 对 ChatConfig 和 ChatInput 组件进行了调整和优化，提升了交互体验和一致性。
- 性能优化： 优化了代码库，提高了大数据集的性能并减少了渲染时间，包括实现了防抖处理和改进了滚动行为。
- Bug 修复： 解决了多个问题，包括修复自动滚动问题、处理设置中的外部链接以及改进了各组件的错误处理。
- Markdown Renderer Upgrade: Enhanced the markdown rendering capabilities, including updates to support new table styles and markdown layout styles.
- LLM Provider Enhancements: Integrated new LLM provider jiekou.ai ,zenmux and updated provider configurations to improve performance and flexibility.
- UI Improvements: Adjusted and refined UI components, especially within the ChatConfig and ChatInput components, for better interaction and consistency.
- Performance Enhancements: Optimized codebase for better performance with large datasets and reduced rendering times, including implementing debounce and improving scroll behavior.
- Bug Fixes: Addressed several issues, including fixing the auto-scroll problem, handling external links in settings, and improving error handling in various components.
🔥 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！
What's Changed
- style: format About page link handler by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1016
- feat: enable custom model config for Ollama provider by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1018
- bugfix: think content scroll issue by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1023
- fix import button bug and prevent backup overwriting during import by @Dw9 in https://github.com/ThinkInAIXYZ/deepchat/pull/1024
- Feat/codeoptimize by @deepinfect in https://github.com/ThinkInAIXYZ/deepchat/pull/1026
- Add poe by @cp90-pixel in https://github.com/ThinkInAIXYZ/deepchat/pull/1028
- fix: make auto scroll works by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1030
- fix: allow settings window links to open externally by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1029
- feat: enhance GitHub Copilot Device Flow with OAuth token management and API token retrieval by @douyixuan in https://github.com/ThinkInAIXYZ/deepchat/pull/1021
- feat(theme): fix message paragraph gap and toolcall block by @deepinfect in https://github.com/ThinkInAIXYZ/deepchat/pull/1031
- fix: scroll to bottom by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1034
- fix: ensure renderer workers build as ES modules by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1037
- feat: remove function deleteOllamaModel by @Dw9 in https://github.com/ThinkInAIXYZ/deepchat/pull/1036
- perf: update dependencies to use stream-monaco and bump vue-renderer-markdown version by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/1038
- feat(theme): add markdown layout style and table style by @deepinfect in https://github.com/ThinkInAIXYZ/deepchat/pull/1039
- feat: support effort and verbosity by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/1040
- feat: add jiekou.ai as LLM provider by @cnJasonZ in https://github.com/ThinkInAIXYZ/deepchat/pull/1041
- feat: add zenmux provider by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/1043
New Contributors
- @cp90-pixel made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/1028
- @cnJasonZ made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/1041
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.4.1...v0.4.2

🚀 DeepChat 0.3.6 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🌟
- Fix: Migrate model config data from new default settings
- Chore: Update Monaco editor dependencies
- Fix: Add support for zero temperature option
- Fix: Add 'copied' keys and remove copy toast
- Fix: Make model selector choose correct model when thread is pinned
- Feature: Add regenerate action on user messages
- Fix: Code block rendering bug in markdown renderer
- Fix: Layer support in vue-renderer-markdown
- Other optimizations, dependency bumps, and code cleanliness improvements
- 修复：模型配置数据迁移以适配新默认设置
- 其他：更新 Monaco 编辑器依赖
- 修复：新增零温度选项支持
- 修复：添加 copied 键并移除复制提示
- 修复：固定主题时模型选择器可选中正确模型
- 新增功能：用户消息支持重新生成
- 修复：Markdown 渲染器代码块渲染问题
- 修复：vue-renderer-markdown 支持图层
- 其他优化、依赖升级及代码清理完善
🔥 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！
What's Changed
- fix: add missing qwen3-max search configuration in frontend by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/877
- fix: upgrade reboot failed by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/876
- fix: auto-scroll to view after pasting large content by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/878
- fix: preserve line breaks and formatting when pasting text in ChatInput by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/879
- fix: align DashScope thinking models support between frontend and backend by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/883
- refactor: replace mime-types with es-mime-types by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/884
- feat: add full-screen in mermaid & perf renderer code_block by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/885
- feat: add live search support for Grok provider by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/886
- feat: add GoogleSearch support for Gemini provider by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/889
- feat: mcpclient support json $ref schema by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/890
- feat: add chatConfig entry for gemini search option by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/891
- fix: revert json ref support by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/892
- chore(deps-dev): bump vite from 7.1.4 to 7.1.5 by @dependabot[bot] in https://github.com/ThinkInAIXYZ/deepchat/pull/893
- fix: add missing delete button for anthropic custom providers by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/895
- chore: update vue-renderer-markdown & vue-use-monaco deps to perf use Monaco use raf render by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/896
- fix: paste image into editor not working by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/900
- fix: fork msg can not retry by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/902
- fix: add image capture for variants by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/904
- feat: upgrade vue-renderer-markdown support code_block collpase and mermaid progressive render by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/903
- chore: upgrade vue-renderer-markdown perf mermaid render by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/908
- fix: css style override by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/911
- fix: Enter inserts newline in edit mode by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/912
- feat: add regenerate on user messages by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/913
- fix: make model select choose right model when pinned thread by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/914
- fix: add 'copied' keys and dr

🚀 DeepChat 0.3.5 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🌟
⚠️ 重要通知：从本版本开始，团队将暂停接受 feature（功能类）PR，需等新的架构与 UI 发布后才会恢复。如有需求类 PR，请提前联系开发团队沟通。
Release Highlights / 主要变更
- 停接 feature 类 PR，专注架构与 UI 大重构
后续仅处理修复与重构相关内容，feature 需求请与开发团队提前对接。
- 基础改进与修复
- 聊天模型切换后自动同步最新配置
- 适配与兼容多家模型供应商（如 OpenAI、Gemini Nano、Banana、Siliconcloud、DashScope、Qwen3、Grok 等），包括输入、推理支持与更多模型配置能力
- 文件类型标记修正，避免 audio/HTML 误判
- 拖拽窗口大小异常修复
- MCP 工具和 prompt 管理优化，日志改进
- 系统 prompt 增强（如插入当前日期时间）
- UI/Markdown 滚动、按钮 glow、Clipboard 粘贴体验优化
- 代码和国际化提升
- presenter/agent/type 强类型解耦与重构
- 全面翻译中文注释与日志
- 多语言包/i18n 内容补全及修正

⚠️ Notice: Starting from this release, feature PRs are temporarily suspended until the new architecture and UI are published. If you have any feature requests, please contact the dev team in advance.
Release Highlights
- Feature PRs on hold, focus on major refactor and UI overhaul
Only bugfixes and refactor-related changes are accepted. Please reach out to the dev team early for any feature discussions.
- General improvements and fixes
- Chat config now synchronizes when switching models
- Enhanced adaptation and compatibility for multiple model providers (OpenAI, Gemini Nano, Banana, Siliconcloud, DashScope, Qwen3, Grok, etc.), including improved input, reasoning features, and more configurable options
- File-type tag fix to avoid HTML/audio confusion
- Fixed abnormal window resizing with drag
- Optimized MCP prompt management and tool logging
- Enhanced system prompt logic (e.g., current datetime insertion)
- UI/Markdown scrolling, button glow, clipboard data sanitization improvements
- Code structure & i18n
- Presenter/agent/type strong typing and modular refactor
- All Chinese comments/logs translated to English
- i18n package fixes and content enrichment
🔥 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！
What's Changed
- fix: chat confg need sync to new value when change model in chat by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/823
- fix: remove file-type ,this will mark html as audio by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/824
- fix: Solve the problem of the window becoming larger when dragging floating button under Windows by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/826
- chore: update vue-renderer-markdown to v0.0.35 by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/827
- refactor: remove custom-prompts-server by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/829
- feat: ux update by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/831
- feat: setting provider ux update by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/832
- fix(markdown): auto-wrap hide scroll by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/833
- feat: add enable_thinking parameter support for siliconcloud by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/835
- chore: bump deps by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/834
- refactor: adjust scroll-to-bottom button glow effect by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/837
- feat: add mutual exclusive confirmation dialogs for DeepSeek-V3.1 by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/838
- feat: add sanitizeText utility for clipboard data handling by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/843
- feat: support canary upgrade by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/840
- feat: implement thinking parameter support for doubao models by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/842
- feat: implement dedicated DashScope provider with enable_thinking support by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/844
- fix: prioritize provid

🚀 DeepChat 0.3.4 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🌟
新功能
- 支持 TokenFlux.ai、更新豆包模型
- 全新启动画面 + 主题
- 悬浮按钮 JS 重写，支持多屏边界检测
优化
- Gemini 推理解析、模型配置、关闭内存占用
- 减少 IPC 调用、并行退出、原子化 provider 操作
- Markdown 转义、导入器修复
- 优化了默认的系统提示词，并且允许用户在设置中进行修改
New
- TokenFlux.ai provider + updated Doubao models
- New splash screen with themes
- Floating button re-written in JS, multi-monitor aware
Improved
- Gemini reasoning & model fixes, memory leak on close
- Fewer IPC calls, faster shutdown, atomic provider ops
- Markdown escape fixes, importer tweaks
- Optimized the default system prompts and allowed users to modify the built-in system prompts
What's Changed
- fix: Correctly parse Gemini reasoning for both new thought field an… by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/801
- fix: correct Gemini 2.5 Flash Image Preview model capabilities and token limits by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/802
- feat: add TokenFlux.ai provider support by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/804
- fix: optimize polling logic to prevent unnecessary IPC calls by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/806
- fix: escape brackets in Markdown content to prevent parsing issues & refactor MessageBlockContent if branch by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/808
- fix memory when close window by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/809
- Reorganize gemini model configs; Refine Gemini reasoning content parsing; Markdown rendering of fixed by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/807
- feat: refactor floating button with JavaScript-based drag and fix interaction issues by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/810
- Refactor/app lifecycle management by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/803
- perf: parallelize lifecycle hooks execution for faster app shutdown by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/811
- fix: resolve race condition in floating button drag-and-drop detection by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/813
- fix: resolve floating button multi-display boundary detection issue by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/814
- Optimize/lifecycle actuator optimization by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/812
- perf: implement atomic provider operations to optimize performance by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/815
- feat: update Doubao provider with new models by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/816
- fix: resolve application hang when quitting during startup by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/817
- chore: fix DataImporter bug and some ux optimises by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/818
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.3.3...v0.3.4
🔥 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！

🚀 DeepChat 0.3.2 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🌟
✨ 新功能 / New Features
1. AWS Bedrock 模型接入
原生支持调用 Amazon Bedrock 的全部模型家族，包含新的设置面板与区域/凭据管理。
Native support for the entire Amazon Bedrock model family, with a dedicated settings panel for regions & credentials.
2. HTML 预览 – 多尺寸视图
渲染 HTML 内容时，可一键切换桌面 / 平板 / 手机三种尺寸，实时预览响应式效果。
Responsive HTML preview now supports desktop, tablet and mobile viewports.
3. 消息侧边栏导航与全文搜索
左侧新增可折叠的消息导航面板；支持关键字高亮、即时过滤，以及快速跳转到指定消息。
New collapsible message navigation sidebar with full-text search, highlighting & quick-jump.
4. 自动滚动与“回到最新”按钮
生成消息时自动保持最新内容可见；一键滚动到底部，并带有加载动画。
Auto-scroll to latest message during generation + animated “scroll-to-bottom” button.
5. 品牌焕新 (Rebrand) 支持
全量替换应用标识、名称、主题色等，并配套完整的中英文迁移文档。
Complete rebrand kit: swap app identity, name, theme colors + bilingual migration guide.

🔧 改进 / Enhancements
- 内置知识切片算法重构
更快的分块速度、更低的内存占用、对中文/代码混合文本更友好。
Refactored built-in knowledge text splitter for faster & memory-efficient chunking, better CJK/code mixed text support.
- 依赖升级
better-sqlite3-multiple-ciphers → v12.2.0，已适配 Electron 37。
Dependency bump for Electron 37 compatibility.
- 所有搜索引擎均可在设置内一键测试连通性
解决因验证码/网络差异导致的配置困扰。
Every search engine can now be connectivity-tested inside settings to preempt CAPTCHA issues.

🐞 问题修复 / Bug Fixes
- UI/样式
- 修复 CSS 样式注入顺序导致的优先级错乱
- 修复 MCP 市场按钮对齐及布局异常 (#769)
- 修复主题切换后部分组件未即时更新 (#770)
- 消息导航滚动定位现在始终可见 (#776)
- 字体大小变更实时同步到所有标签页 (#786)
- 新增图标支持，避免缺失导致的异常空白
- 模型与 Provider
- 禁用 deepseek-reasoner 的原生工具调用，恢复思考链展示
- 修复 Gemini 2.5 Thinking Budget 初始化与跨标签同步问题
- 修复模型列表、Provider 顺序在多个标签页间的同步异常 (#763, #765)
- 交互体验
- 生成结束后不再强制滚动到底部 (#783)
- 正则表达式移除多余转义字符，避免匹配错误 (#764)
- 修复 Windows 下 VS Redistributable 检测提示重复出现 (#755)

What's Changed
- fix vsredist check nsh by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/755
- Optimize/builtin knowledge text splitter by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/757
- feat: add aws bedrock provider by @bigyao25 in https://github.com/ThinkInAIXYZ/deepchat/pull/756
- fix: improve AWS Bedrock provider settings UI by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/759
- feat: html 预览新增尺寸切换 by @Yealove in https://github.com/ThinkInAIXYZ/deepchat/pull/618
- chore: bump better-sqlite3-multiple-ciphers to 12.2.0 for Electron 37 by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/761
- fix: resolve model list synchronization issue across tabs by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/763
- fix: remove unnecessary escape character in regex pattern by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/764
- fix: sync provider order changes across all tabs by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/765
- fix: resolve Gemini 2.5 thinking budget initialization and sync issues by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/767
- fix: resolve MCP market button alignment and layout issues by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/769
- fix: theme change issue by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/770
- fix: enable search engine testing for all engines to resolve CAPTCHA timeout issue by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/771
- feat: add message navigation sidebar with search functionality by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/776
- fix: improve message navigation scroll position to show content from top by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/777
- feat: support rebrand by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/778
- feat: implement auto-scroll to latest message and scroll-to-bottom button by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/780
- doc: optimize and remove outdated docs by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/781
- fix: prevent automatic scroll to bottom after message generation by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepch

🚀 DeepChat 0.3.1 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🌟
- 修复了内存泄漏问题
- 修复了 DeepLink 和 Artifacts 带来的安全漏洞
- 为提供商设置添加搜索功能
- 为 API 密钥输入添加密码可见性切换
- 添加了 Vercel AI 和 AWS Bedrock 新供应商
- 为 OpenRouter 添加全面的 OpenAI 推理模型支持
- 增加了 GPT5 系列模型的更完善支持
- 为 GPT-OSS 模型添加 reasoning_effort 参数支持
- 添加架构兼容性检查和 Visual C++ Redistribu 支持
- 解决使用 Ctrl+Shift+N 创建新窗口时的焦点闪烁问题
- 为 PopoverContent 添加可滚动支持以防止溢出
- Fixed memory leak issues
- Fixed security vulnerabilities caused by DeepLink and Artifacts
- Added search functionality for provider settings
- Added password visibility toggle for API key inputs
- Added new providers: Vercel AI and AWS Bedrock
- Added comprehensive OpenAI reasoning models support for OpenRouter
- Enhanced support for GPT-5 series models
- Added reasoning_effort parameter support for GPT-OSS models
- Added architecture compatibility checks and Visual C++ Redistributable support
- Resolved focus flicker issue when creating new windows with Ctrl+Shift+N
- Added scrollable support to PopoverContent to prevent overflow
What's Changed
- fix: resolve OpenRouter model sync timeout and welcome view UI issues by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/738
- feat: add GLM-4.5V model support by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/739
- feat: add search functionality for provider settings by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/740
- fix: optimize ModelScope MCP sync UI layout for consistent window height by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/741
- fix: resolve reasoningEffort parameter transmission issues by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/742
- feat: add Vercel AI Gateway provider support by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/743
- fix: pass user reasoningEffort/verbosity settings to GPT-5 API requests by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/746
- feat: add password visibility toggle for API key inputs by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/747
- Feature/add aws bedrock provider by @bigyao25 in https://github.com/ThinkInAIXYZ/deepchat/pull/744
- fix: extend reasoningEffort support to all reasoning models by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/749
- feat: add comprehensive OpenAI reasoning models support for OpenRouter by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/751
- chore(deps): bump electron to 37.3.0 fix #737 by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/753
- feat: add architecture compatibility checks and Visual C++ Redistributable installation support by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/752
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.3.0...v0.3.1
🔥 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！

🚀 DeepChat 0.3.0 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🌟
- ✅ 新增模型：GPT-5 系列、Claude Opus 4.1
- ✅ 悬浮对话：浮动窗口、ESC 关闭、位置记忆
- ✅ MCP 生态：市场同步、魔搭社区接入
- ⚡ 性能提升：单文件打包、窗口创建更流畅
- 🔧 体验优化：焦点闪烁、数学渲染、文件移动问题修复
- 📚 文档更新：开发者链接、翻译优化
- ✅ New models: GPT-5 series, Claude Opus 4.1
- ✅ Hovering Dialogue: Floating window, ESC off, position memory
- ✅ MCP Ecosystem: Market synchronization and community access
- ⚡ Performance improvements: Single file packaging and smoother window creation
- 🔧 Experience Optimization: Fix focus flickering, mathematical rendering, file movement issues
- 📚 Documentation updates: developer links, translation optimizations
What's Changed
- fix: add AlertDialogDescription to resolve accessibility warning by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/706
- fix: resolve focus flicker when creating new windows with Ctrl+Shift+N by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/707
- fix: memory leak issue when closing window by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/709
- docs: update zhipu developer doc website link by @tomsun28 in https://github.com/ThinkInAIXYZ/deepchat/pull/715
- refactor: better translate by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/716
- feat: add GPT-5 series model support by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/717
- ci(vite): Bundle the main file into a single file to speed up loading. by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/718
- fix(math): parser by upgrade vue-renderer-markdown by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/722
- chore: bump deps by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/721
- fix: add scrollable support to PopoverContent to prevent overflow by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/720
- feat: implement floating chat window system with performance optimization by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/724
- feat: add mcp sync and modelscope provider #615 by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/723
- fix: move_files newPath 参数计算规则 by @wangle201210 in https://github.com/ThinkInAIXYZ/deepchat/pull/725
- feat: add Claude Opus 4.1 to anthropic default model list by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/726
- feat: Add mcprouter's MCP marketplace api support by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/727
- feat: add ESC key to close floating chat window by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/728
- feat: add floating button position persistence with boundary validation by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/729
- feat: add reasoning_effort parameter support for gpt-oss models by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/731
- fix: artifacts code not streaming by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/732
- feat: disable automatic model enabling for better UX by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/734
- feat: sync provider sorting from settings to model selection by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/736
New Contributors
- @tomsun28 made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/715
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.2.9...v0.3.0
🔥 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！

🚀 DeepChat 0.2.9 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🌟
主要更新
- 基于服务商的请求速率限制： 告别 too many request，自定义各个供应商的请求限制
- 适配了 Claude Opus 4.1 和 OpenAI gpt-oss
- 性能优化，启动速度变快了一点点
- 常规 Bug 修复
What's Changed
- fix: prevent tooltip from overlapping HTML preview in ArtifactDialog by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/683
- fix: unwatch is not a function error in knowledge settings components by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/684
- fix: resolve message editing and markdown rendering issues by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/685
- docs: update Electron-Vite link format to full URL by @cycleccc in https://github.com/ThinkInAIXYZ/deepchat/pull/687
- fix: built-in knowledge settings not loaded when first entering by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/688
- fix: resolve database lock issue in data reset functionality by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/689
- feat: implement provider-based request rate limit by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/686
- Optimize/builtin knowledge interaction by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/690
- fix: fixed dirty data problems by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/691
- feat: add mentions support in deeplink by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/692
- bugfix: prompt attach files by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/695
- feat: add npm registry caching and optimization system by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/697
- fix: resolve input focus loss issue after sending messages by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/694
- fix: resolve deeplink message not displaying when triggered from settings page by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/699
- fix: a potential problem with mcp tools by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/698
- feat: add support for new models by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/700
- fix: refine #698 by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/701
- feat: add Claude Opus 4.1 support and fix anthropic model list dialog by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/702
New Contributors
- @cycleccc made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/687
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.2.8...v0.2.9
🔥 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！

🚀 DeepChat 0.2.8 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🌟
最新更新
- Anthropic 支持 OAuth 使用 Claude Pro/Max 订阅
- 优化多 Tab 和多会话的交互的体验
- 性能优化，界面流畅度优化
- 优化输出时的打字机效果
🔥 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！

🚀 DeepChat 0.2.7 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🌟
最新更新
1. 支持内置知识库 (全新功能⭐️)
2. 支持会话整体导出为 markdown/txt/html (全新功能⭐️)
3. Gemini 支持 thinking 相关的设置
4. 新增了 Groq 供应商
5. 修复 e2b 的 bug
What's Changed
- feat: builtin knowledge by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/597
- fix: update text fixed by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/608
- Add Groq as Provider by @Dw9 in https://github.com/ThinkInAIXYZ/deepchat/pull/609
- feat: remove python code run on js by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/617
- feature: renderer dialog for main process by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/629
- fix issue 622 by @Dw9 in https://github.com/ThinkInAIXYZ/deepchat/pull/631
- Feature/export to html by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/632
- Feature/builtin knowledge by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/630
- feat: add click outside to close sidebar functionality by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/636
- Feature/mcp tool improve by @sqsyli in https://github.com/ThinkInAIXYZ/deepchat/pull/635
- style(threads): optimize the operation logic of new sessions by @RSS1102 in https://github.com/ThinkInAIXYZ/deepchat/pull/633
- chore(ci): add code lint check by @RSS1102 in https://github.com/ThinkInAIXYZ/deepchat/pull/634
- fix: resolve sidebar toggle button conflict by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/637
- Bugfix/gemini thinking by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/639
- perf(ChatConfig): 设置 TooltipProvider 组件添加延迟持续时间 200&更新 tsconfig.web.json 文件中 include 配置 by @flingyp in https://github.com/ThinkInAIXYZ/deepchat/pull/640
- feat: Add thinking budget support for Gemini 2.5 series models by @yyhhyyyyyy in https://github.com/ThinkInAIXYZ/deepchat/pull/643
New Contributors
- @yyhhyyyyyy made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/636
- @sqsyli made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/635
- @RSS1102 made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/633
- @flingyp made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/640
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.2.6...v0.2.7
🔥 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！

🚀 DeepChat 0.2.6 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🌟
主要更新
- MCP 权限系统全面重构：引入全新的 MCP 工具权限请求与管理系统，提升安全性与用户体验。
- Apple MCP 支持：新增 Apple Server MCP , macOS 用户可以用模型操作电脑了
- 模型加载逻辑优化，减少突然模型列表消失和刷新不及时问题
- 新增 Kimi K2 Preview 模型默认配置
- 快捷键清除功能
- 修复 GitHub 设备授权流程在 Windows 下的 URL 处理问题
- 工具调用参数类型修复
- 系统提示重复拼接问题修复
- UI 修复
- 构建工具升级：从 Vite 切换至 Rolldown-Vite，提升构建性能
- 302 AI 支持增强，可以读取余额，可以自动适配模型参数
What's Changed
- Update i18n translations for knowledge settings to include names with… by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/571
- fix French typo by @aooyoo in https://github.com/ThinkInAIXYZ/deepchat/pull/572
- Refactor/better translate by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/573
- feat: add 302 balance api by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/575
- chore: remove chatInput editor codeBlock process by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/578
- Feature/302 provider model api by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/582
- fix(formatMessage): system prompt is spliced ​​twice by @bigyao25 in https://github.com/ThinkInAIXYZ/deepchat/pull/581
- Refactor/check provider by model by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/585
- fix(auth): improve GitHub device flow URL handling on windows by @Dw9 in https://github.com/ThinkInAIXYZ/deepchat/pull/583
- gemini bug fix by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/586
- feat: clear shortcutsKey by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/587
- Add MseeP.ai badge by @lwsinclair in https://github.com/ThinkInAIXYZ/deepchat/pull/588
- feat: 添加 Kimi K2 Preview 模型默认设置 by @deepinfect in https://github.com/ThinkInAIXYZ/deepchat/pull/592
- Revert "Add MseeP.ai badge" by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/593
- Fixed: the edit mode not work good by @cmdparkour in https://github.com/ThinkInAIXYZ/deepchat/pull/596
- Feature/add permission check by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/594
- add apple macos inmem mcp by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/595
- fixed: the mcpServer you need maybe undefined when you want to use by @cmdparkour in https://github.com/ThinkInAIXYZ/deepchat/pull/601
- Refactor/rolldown vite by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/603
- fix: fix autoCheck dialog by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/604
New Contributors
- @aooyoo made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/572
- @bigyao25 made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/581
- @Dw9 made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/583
- @lwsinclair made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/588
- @cmdparkour made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/596
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.2.5...workflow-16321989156
🔥 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！

🚀 DeepChat 0.2.5 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🌟
✨ 本次主要更新内容 ✨
- 初步支持桌面小浮窗
- 增强了自带文件 MCP，目前可以让 AI 编辑文件了
- 和 aihubmix 进行了合作，所有 DeepChat 的用户可以享受 10% 的 token 优惠
- 输入框支持上下键切换历史，tab 补全
- 修复了大量 Bug
What's Changed
- feat(agent): implement mcp server of multi-tab participant meeting for topic-based discussions by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/550
- refactor: 将 Model Control Protocol (MCP) 重命名为 Model Context Protocol by @wushanchao in https://github.com/ThinkInAIXYZ/deepchat/pull/554
- feat: Floating window by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/553
- feat(searchHistory): 优化上下键使用场景 by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/559
- fix(ChatInput): when hasMentionSuggestion select not use searchHistory by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/560
- Feature/support aihubmix app code by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/566
- Enhance in-memory file read-write service| 增强 inmemory 文件读写服务 by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/567
- update siliconflow name & logo by @astaxie in https://github.com/ThinkInAIXYZ/deepchat/pull/570
- 0.2.5 Release by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/569
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.2.4...v0.2.5
🔥 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！

🚀 DeepChat 0.2.4 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🌟
✨ 本次主要更新内容 ✨
- 新增模型配置设置界面，可以自己配置模型的各类参数了
- 适配了 macOS 26 Tahoe
- 优化了更新流程，新增托盘菜单版本检查功能和提示对话框
- 支持设置显示/隐藏窗口的快捷键
- 新增对 Minimax 和 Gemini 模型列表 API 的优化
- 支持 OpenRouter 和 PPIO 模型配置 API，不再需要更新软件才获取最新配置了
- 新增对 E2B 沙箱的支持，增强工具箱里面可以选择用 E2B 来执行代码。
- 新增 Vitest 测试框架支持
- 支持 Bun 和 UV 运行时环境，MCP 体验更丝滑
- 全面使用 Oxlint 保障
- 包管理正式切换为 pnpm
- 修复模型选择框的一系列展示问题
- 修复窗口最大化的时候的一些不正常的情况
- 取消了 MCP Server 启停后的排序修改逻辑
- 优化了 IPC 通道的信息，减少了开销
What's Changed
- refactor: migration to pnpm by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/444
- fix: fix sharp on mac arm build by x64 by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/449
- style: optimize shortcutKey style by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/501
- feat: tray menu check version by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/505
- add oxlint for default lint by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/506
- feat: show laste-version-dialog tips for user by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/504
- Add TogetherAI Provider by @noQuli in https://github.com/ThinkInAIXYZ/deepchat/pull/497
- feat: setting show/hide key by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/507
- test: add vitest by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/509
- migration to pnpm | 迁移到 pnpm 为了后续拆包做准备 by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/511
- docs(README): add details about pnpm under win32 by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/512
- fix(agent): fix inconsistent fc call record format in chained non-native function calling by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/515
- 支持自定义模型参数 by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/516
- inject bun and uv runtime | 增加 bun 和 uv 的 runtime by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/519
- fix: improve default model selection logic to ensure that only 'chat' model can be selected by default by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/520
- refactor: remove redundant server status sorting logic #518 by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/523
- fix(agent): improve accuracy of semantic descriptions for non-native fc calling by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/526
- docs: 将 "Model Controller Platform (MCP)" 修正为 "Model Context Protocol… by @wushanchao in https://github.com/ThinkInAIXYZ/deepchat/pull/528
- fix custom modle not show in the chat list by @astaxie in https://github.com/ThinkInAIXYZ/deepchat/pull/529
- Feature/enhance provider api | openrouter 和 ppio 支持动态获取模型参数 by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/527
- 增加 e2b 沙盒支持 Feature/add e2b support by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/531
- feat: enhance model selection logic in common setting by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/533
- feat: add support for mcp http 400 by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/540
- fix(markdown): initial style undefined by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/541
- 0.2.4 release by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/549
New Contributors
- @noQuli made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/497
- @wushanchao made their first contribution in https://github.com/ThinkInAIXYZ/deepchat/pull/528
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.2.3...v0.2.4
🔥 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！

🚀 DeepChat 0.2.3 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🌟
✨ 本次主要更新内容 ✨
- 自定义 Prompt 支持附加文件了
- DeepSeek，OpenRouter，PPIO 以及硅基流动四家供应商目前支持查询用户余额了
- 支持了 RTL 的 i18n
- 优化了大量快捷键和输入框的体验
- 重构了事件总线和滚动性能，整体性能提升
- 更新模型配置，增加了新的供应商
- 修复大量 Bug
What's Changed
- feat(sfx): add AI typing and function calling sound effects with UI toggle options @_@ by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/441
- feat(ui): add 'Copy with COT details' option in setting by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/446
- fix(shortcut): make CLEAN_CHAT_HISTORY (Ctrl+L) shortcut work properly again by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/447
- style: fix prompt dialog scroll by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/450
- chore: adjust model-configs of deepseek & ppio by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/452
- Refactor deepresearch by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/453
- fix(sfx): fix sound-effects performance issue by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/455
- Refactor split store by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/456
- feat(dsearch): support self-driven retrieval with confidence scoring and incremental reflection evaluation by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/458
- fix(sfx): fix sound-effects issue caused by store refactor by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/461
- refactor: replace codemirror with monaco by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/459
- Files prompt by @astaxie in https://github.com/ThinkInAIXYZ/deepchat/pull/462
- feat(shortcut): add delete conversation shortcut (Ctrl+D) by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/464
- fix: update vue-renderer-markdown dependency to version 0.0.25 to fix katex lost style## Pull Request Description by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/465
- Refactor/send to renderer migrate to eventbus by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/466
- feat(agent): enable robust MCP agentic control for multi-tab environments by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/476
- 重构 ipc 通讯和 tab 绑定逻辑 by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/474
- fix device code copy utton of github copilot login by @douyixuan in https://github.com/ThinkInAIXYZ/deepchat/pull/478
- Refactor/virtual scroll in threads by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/480
- fix(agent): resolve bug where chained tool invocation did not display… by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/481
- fix(ui): enforce strict tab-session binding so that a session can only appear in one tab at any time and in any interaction flow by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/483
- embedding support by @hllshiro in https://github.com/ThinkInAIXYZ/deepchat/pull/479
- feat(ChatInput): implement search history functionality with navigation support by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/486
- feat: update vue-renderer-markdown deps support dir auto by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/487
- 🇮🇷 Persian Translation by @alr86 in https://github.com/ThinkInAIXYZ/deepchat/pull/490
- add fa-IR i18n by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/491
- feat: add 301.ai as provider by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/492
- add key status by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/495
- feat(ArtifactDialog): use monaco replace pre markdown render by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/496
- fix: theme switch monaco not update by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/499
- feat(mcp): 添加路径展开功能，支持用户主目录和环境变量的解析 by @Acring in https://github.com/ThinkInAIXYZ/deepchat/pull/498
- Rele

🚀 DeepChat 0.2.2 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🌟
⚠BREAKING CHANGES⚠
- 本版本 macOS 上无法自动更新，需要手动下载覆盖安装
✨ 本次主要更新内容 ✨
1. 修复了输入框无法复制富文本的问题
2. 内置文件 mcp 设置改为文件选择
3. 修复了 markdown 渲染的一系列问题
4. 支持自定义快捷键设置，重构了快捷键注册逻辑
5. 修复了 Windows 最小化到 Tray 错误
6. tool_call 的适应性优化
7. 更新了 r1 和 gemini 一系列的模型配置
8. i18n 补全
详细变更
- docs: Add comprehensive user and developer documentation by @astaxie in https://github.com/ThinkInAIXYZ/deepchat/pull/398
- fix the fullscreen close issue by @astaxie in https://github.com/ThinkInAIXYZ/deepchat/pull/400
- fix all i18n check errors, add i18n check github action by @douyixuan in https://github.com/ThinkInAIXYZ/deepchat/pull/403
- feat(mcp): add folder select for buildinFileserver by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/402
- add memory mcp conversation-search-server by @astaxie in https://github.com/ThinkInAIXYZ/deepchat/pull/404
- refactor(markdown): use vue-renderer-markdown by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/401
- feat: Implement conversation pinning with full i18n by @astaxie in https://github.com/ThinkInAIXYZ/deepchat/pull/405
- fix: fix the initialization SQL statement by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/408
- chore: replace markdown.css with vue-renderer-markdown/index.css by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/409
- feat(setting): add default system prompt setting by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/412
- fix(markdown): style by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/414
- Fix: Correct MCP full name and add semantic workflow information by @astaxie in https://github.com/ThinkInAIXYZ/deepchat/pull/416
- chore: remove unuse code by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/417
- fix(markdown): with custom style by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/419
- fix: welcome component style problem by @Soya-xy in https://github.com/ThinkInAIXYZ/deepchat/pull/421
- feat: add i18n-ally Custom Namespaces Match by @Soya-xy in https://github.com/ThinkInAIXYZ/deepchat/pull/422
- feat: Display the model provider ID in the title bar by @Soya-xy in https://github.com/ThinkInAIXYZ/deepchat/pull/423
- feat(ui): add context window ratio estimation and messagetoolbar display by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/424
- feat(ui): supplement context window occupancy color indication by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/425
- Bugfix/mcp install failed by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/427
- chore(markdown): upgrade vue-renderer-markdown version by @Simon-He95 in https://github.com/ThinkInAIXYZ/deepchat/pull/428
- chore(modelcfg): Update deepseek-r1-0528 model config by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/432
- feat(setting): support custom shortcut Key by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/418
- Support paste files by @astaxie in https://github.com/ThinkInAIXYZ/deepchat/pull/434
- Feature/GitHub copilot plugin app by @douyixuan in https://github.com/ThinkInAIXYZ/deepchat/pull/420
- refactor(openai): clean-up character stream handling, normalize non-native function-calling tag streaming, add corner case defenses by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/437
- fix(ui): Adjust tray lifecycle management; fix Win11 tab display after zoom restore by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/438
- fix(tool): fix MAX_TOOL_CALLS in LLMProviderPresenter by @neoragex2002 in https://github.com/ThinkInAIXYZ/deepchat/pull/439
- style: fix foucs scrollview outline & shortcutKey scroll-bar by @zhangmo8 in https://github.com/ThinkInAIXYZ/deepchat/pull/440
- Refactor/merge corestream fix to ollama by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/442
- Release V0.2.2 by @zerob13 in https://github.com/ThinkInAIXYZ/deepchat/pull/443
- fix: fix shortcutKey

🚀 DeepChat 0.2.1 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🌟
✨ 本次主要更新内容 ✨
- fix(openai): remove citation markers from forced search results in context / 修复(openai): 从上下文中的强制搜索结果中移除引文标记，避免遗留幽灵引用 by @neoragex2002 in #371
- fix(openai): fix crash caused by message stream merge in fc call; remove forced citation remnants from search results in both native and non-native fc contexts; improve search intent recognition / 修复(openai): 修正消息流合并导致 fc 调用崩溃的 bug；去除原生及非原生 fc 上下文中强制搜索结果中遗留的引文；完善搜索意图识别 by @neoragex2002 in #372
- fix prompt add / 修复提示词添加 by @astaxie in #373
- Some bug fixes for multiple windows / 多窗口的一些 bug 修复 by @zerob13 in #375
- Refactor/migration new sdks / 重构/迁移新 SDK by @zerob13 in #377
- fix(artifacts): improve code detection accuracy / 修复(artifacts): 提升代码检测准确性 by @neoragex2002 in #378
- refactor(prompts): extract customprompt from powerpack / 重构(prompts): 从 powerpack 中提取自定义提示词 by @zerob13 in #380
- Optimize/components / 优化/组件 by @deepinfect in #381
- Fix/prompt reload / 修复/提示词重载 by @astaxie in #383
- new tab set default provider / 新标签页设置默认提供者 by @astaxie in #384
- [Feature]inmemory deep research mcp / [功能]内存深度研究 MCP by @zerob13 in #382
- add copy-as-image button for artifact preview / 为 artifact 预览添加“复制为图片”按钮 by @douyixuan in #385
- feat(prompt): add template-based auto-prompting tools / 功能(提示词): 添加基于模板的自动提示工具 by @neoragex2002 in #389
- Modify CI strategy to easily create Release drafts / 修改 CI 的策略，能够简单的创建 Release 的草稿 by @zerob13 in #391
- Optimize/mcpserverui / 优化/MCP 服务器 UI by @deepinfect in #392
- support card style / 支持卡片样式 by @astaxie in #394
- Dialog description / 对话框描述 by @astaxie in #395
Full Changelog: https://github.com/ThinkInAIXYZ/deepchat/compare/v0.2.0...v0.2.1
🔥 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！