release: v0.7.2 (#1581)

Author: NanmiCoder

desktop/package.json

@@ -1,7 +1,7 @@
 {
   "name": "claude-code-desktop",
   "private": true,
-  "version": "0.7.1",
+  "version": "0.7.2",
   "description": "Desktop coding agent workbench for Claude Code Haha.",
   "homepage": "https://github.com/NanmiCoder/cc-haha",
   "author": {

release-notes/v0.7.2.md

@@ -0,0 +1,114 @@
+# Claude Code Haha v0.7.2
+
+本次新增 **DeepSeek 账号登录**、**会话标签数量上限** 和 **智能体团队提示**，并集中修复长会话、上下文压缩、OpenAI Chat 代理和 Windows 平台上的一批问题。
+
+## 核心功能
+
+- **DeepSeek 账号登录**（#1548，#1578）：在「设置 → 提供商」中直接用 DeepSeek 账号登录，无需填写 API Key。模型列表按账号实际可用的目录拉取，可直接选择 DeepSeek V4.1 Flash 等模型；已保存的模型映射会自动迁移。
+- **会话标签数量上限**（#1550）：「设置 → 通用 → 标签页」可限制同时打开的会话标签数（5 / 8 / 12 / 20 或不限），可关闭启动时恢复标签，标签菜单新增「重新打开已关闭的标签」。正在运行、等待输入、有未发送草稿、团队队长和其他标签正在查看的会话不会被自动关闭；全部默认保持现有行为。
+- **智能体团队**（9fd74c66c）：界面统一为「智能体团队」，在设置或输入框开启前会说明 token 消耗和性能影响，输入框中的提示可选择不再提醒。
+- **登录风险确认**（#1526）：Claude、ChatGPT、Grok 官方登录前先确认第三方应用登录可能带来的账号风险，按提供商分别说明。
+- **复制图片**（#1551）：右键菜单可直接复制聊天中的图片。
+- **模型更新**（#1580，#1546）：新增 Modelflare 预设并刷新 AruHub 模型；第一方 Haiku 默认升级为 Haiku 5.5（1M 上下文），Claude 5 系列继续使用自适应思考。
+
+## 稳定性与性能
+
+- **长会话的回合改动预览**（0894dc813）：不再因为记录过大而丢失每回合的改动卡片，也不再逐文件重复扫描，长会话打开改动预览明显更快。
+- **自动压缩空转熔断**（#1544）：压缩后上下文仍接近阈值时，连续三次后停止并提示，不再反复压缩直到用户新建会话；压缩确实释放了空间的任务不受影响。
+- **缓存共享压缩超出窗口**（#1527）：为摘要预留的输出额度不再挤爆上下文窗口，压缩继续走缓存路径，而不是回退重发整段上下文。
+- **长工具输入不再被中断**（#1536）：写入大文件时，工具输入的等待时间跟随请求超时，不再被固定的 120 秒预算打断。
+- **恢复会话的上下文窗口**（#1547）：原提供商已被删除或记录有误时，回退到当前或唯一匹配的提供商，不再把 1M 模型显示成「200,000 / 200,000，剩余 0%」。
+
+## 修复
+
+- **侧边会话恢复父链**（#1529）：父会话停在还没有结果的工具调用上时，侧边会话也能正常创建。
+- **OpenCode Go 模型报 400**（eb3d75aa6）：上游拒绝 `thinking` 字段时自动去掉该字段重发一次，只在重发成功后记住，不影响同一网关的其他模型。
+- **图片生成**（#1545）：中转地址和原生协议的图片请求都能正常发出。
+- **Cmd+N 新建会话**（#1543）：快捷键恢复为直接新建会话；Windows / Linux 上 Ctrl+N 仍用于输入框换行。
+- **路径含空格的输出文件**（#1556）：以编码形式出现的链接能定位到磁盘上的真实文件，无法打开时给出提示。
+- **分支选择器**（#dee09f5ce）：打开时刷新分支列表；后台刷新失败不再清空已有列表、丢掉已选分支或冲掉刚创建的分支。
+- **Windows 控制台窗口**（#1489）：补齐剩余子进程的隐藏窗口设置，打开诊断日志目录时仍能正常显示资源管理器。
+- **Windows 构建解压 ripgrep**（#1491，9988877d1）：没有 `unzip` 时也能完成解压，不再因为缺少命令直接失败。
+- **侧栏项目分组折叠**（#1522）：折叠状态在重启后保留。
+- **Token 数量格式**（#1572，#1465）：设置页与聊天头部使用同一个格式，十亿级数量显示为 `1.5B` 而不是 `1500M`。
+- **已发送消息的标签**（#1577）：重新显示团队、技能和命令胶囊。
+- **等宽字体下的有序列表**（9e1731309）：`10.` 之类的序号不再被裁掉。
+- **选区操作菜单位置**（#1541）：新增设置项，可让选中文本后的菜单浮在选择处上方。
+- **运行时回归**（#1570）：固定 Bun 1.4.3，修复历史加载、输出卡片路径和搜索索引 worker 的一批回归。
+
+## 其他
+
+- **许可证变更**（#1575，#1576）：新增内容改用 cc-haha Community Source License 1.0，个人使用和公司内部使用不受影响；竞争性商业产品、付费二次开发和商业再分发需事先获得许可，再分发需保留来源署名。历史 MIT 授权与第三方声明保持不变。
+- **赞助商**（#1542，#1532）：新增 Modelflare 白金赞助，退役 ApiSmart 预设（已保存的提供商不受影响）。
+- **PR 门禁与流量回放**（#1567）：CI 质量门禁更可靠，并新增回放录制的 DeepSeek Flash 流量来检查 agent 循环。
+
+## 安装
+
+请在下方 Assets 中下载对应平台和架构的安装包：
+
+- macOS：`Claude-Code-Haha-0.7.2-mac-arm64.dmg` / `Claude-Code-Haha-0.7.2-mac-x64.dmg`
+- Windows：`Claude-Code-Haha-0.7.2-win-x64.exe` / `Claude-Code-Haha-0.7.2-win-arm64.exe`
+- Linux x64：`Claude-Code-Haha-0.7.2-linux-x86_64.AppImage`、`Claude-Code-Haha-0.7.2-linux-amd64.deb` 或 `Claude-Code-Haha-0.7.2-linux-x86_64.rpm`
+- Linux ARM64：`Claude-Code-Haha-0.7.2-linux-arm64.AppImage`、`Claude-Code-Haha-0.7.2-linux-arm64.deb` 或 `Claude-Code-Haha-0.7.2-linux-aarch64.rpm`
+
+**完整变更：**[v0.7.1...v0.7.2](https://github.com/NanmiCoder/cc-haha/compare/v0.7.1...v0.7.2)
+
+<details>
+<summary><b>English Version</b></summary>
+
+# Claude Code Haha v0.7.2
+
+This release adds **DeepSeek account sign-in**, **session tab limits** and **an Agent Teams notice**, and fixes a batch of issues around long sessions, context compaction, the OpenAI Chat proxy and Windows.
+
+## Highlights
+
+- **DeepSeek account sign-in** (#1548, #1578): sign in with a DeepSeek account from `Settings → Providers` without an API key. Models are listed from the account's own catalog, including DeepSeek V4.1 Flash, and saved model mappings are migrated automatically.
+- **Session tab limits** (#1550): `Settings → General → Tabs` limits how many session tabs stay open (5 / 8 / 12 / 20 or no limit), can stop restoring tabs on launch, and adds Reopen Closed Tab to the tab menu. Running chats, chats waiting for input, unsent drafts, team leads and chats viewed by another tab are never auto-closed. Every default keeps today's behavior.
+- **Agent Teams** (9fd74c66c): the feature is now named 智能体团队 across the interface, and enabling it from Settings or the composer explains the token cost and slowdown first. The composer notice can be dismissed permanently.
+- **Login risk confirmation** (#1526): Claude, ChatGPT and Grok sign-in now confirm the account-ban risk of signing in through a third-party app, graded per provider.
+- **Copy Image** (#1551): copy images from a chat directly from the context menu.
+- **Model updates** (#1580, #1546): adds the Modelflare preset and refreshes AruHub models. First-party Haiku now defaults to Haiku 5.5 (1M context), and Claude 5 models keep adaptive thinking.
+
+## Stability and performance
+
+- **Turn change previews on long sessions** (0894dc813): per-turn change cards no longer disappear when a transcript is large, and turns no longer rescan every tracked file, so opening a change preview on a long session is much faster.
+- **Auto-compaction thrashing** (#1544): when a compaction leaves the context near the threshold, three consecutive compactions end the turn with a notice instead of compacting until a new conversation is started. Tasks where compaction does free space are unaffected.
+- **Cache-sharing compaction fork** (#1527): the summary output allowance no longer overflows the context window, so compaction stays on the cached path instead of resending the whole context.
+- **Long tool inputs** (#1536): the tool-input budget now follows the request timeout, so large file writes are no longer aborted by a fixed 120-second budget.
+- **Context window of resumed sessions** (#1547): when the recorded provider is gone or wrong, the session falls back to the active or unique matching provider instead of showing "200,000 / 200,000, 0% left" for a 1M model.
+
+## Fixes
+
+- **Side-chat parent chain** (#1529): a side chat can be created when the parent stopped on a tool call that has no result yet.
+- **OpenCode Go 400s** (eb3d75aa6): when an upstream rejects the `thinking` field, the request is resent once without it and only remembered after that resend succeeds. Other models on the same gateway keep the toggle.
+- **Image generation** (#1545): relay URLs and native provider protocols both work.
+- **Cmd+N** (#1543): the shortcut creates a new session again; Ctrl+N stays the composer's next-line key on Windows / Linux.
+- **Output files with spaces in their paths** (#1556): percent-encoded links resolve to the real file on disk, and a card that still cannot route its target says so.
+- **Branch picker** (dee09f5ce): the branch list refreshes when opened, and a failed background refresh no longer blanks the list or drops a just-created branch.
+- **Windows console windows** (#1489): the remaining child-process spawn sites hide their console, while opening the diagnostics log directory still shows Explorer.
+- **Extracting ripgrep on Windows** (#1491, 9988877d1): builds without `unzip` on PATH now extract successfully.
+- **Sidebar project groups** (#1522): collapsed groups stay collapsed after a restart.
+- **Token count formatting** (#1572, #1465): settings and the chat header share one formatter, and billions render as `1.5B` instead of `1500M`.
+- **Pills on sent messages** (#1577): team, skill and command pills show again on messages that were sent.
+- **Ordered lists in monospace** (9e1731309): numbers such as `10.` are no longer clipped.
+- **Selection menu placement** (#1541): a new setting floats the text-selection menu above the selection.
+- **Runtime regressions** (#1570): pins Bun 1.4.3 and fixes history loading, output card paths and the search index worker.
+
+## Other
+
+- **License change** (#1575, #1576): new content is covered by the cc-haha Community Source License 1.0. Personal and internal business use are unaffected; competing commercial products, paid customization and commercial redistribution require prior permission, and redistributions must keep source attribution. Historical MIT grants and third-party notices are unchanged.
+- **Sponsors** (#1542, #1532): Modelflare joins as a platinum sponsor, and the ApiSmart preset is retired (saved providers keep working).
+- **PR gate and traffic replay** (#1567): the CI quality gate is more reliable and now replays recorded DeepSeek Flash traffic to check the agent loop.
+
+## Installation
+
+Download the installer for your platform and architecture from the Assets section below:
+
+- macOS: `Claude-Code-Haha-0.7.2-mac-arm64.dmg` / `Claude-Code-Haha-0.7.2-mac-x64.dmg`
+- Windows: `Claude-Code-Haha-0.7.2-win-x64.exe` / `Claude-Code-Haha-0.7.2-win-arm64.exe`
+- Linux x64: `Claude-Code-Haha-0.7.2-linux-x86_64.AppImage`, `Claude-Code-Haha-0.7.2-linux-amd64.deb` or `Claude-Code-Haha-0.7.2-linux-x86_64.rpm`
+- Linux ARM64: `Claude-Code-Haha-0.7.2-linux-arm64.AppImage`, `Claude-Code-Haha-0.7.2-linux-arm64.deb` or `Claude-Code-Haha-0.7.2-linux-aarch64.rpm`
+
+**Full changelog:** [v0.7.1...v0.7.2](https://github.com/NanmiCoder/cc-haha/compare/v0.7.1...v0.7.2)
+
+</details>