Two bugs in the v0.5.7 "Continue from here" hand-off path landed in the wild and the user caught them while exercising 0.5.8 prep: 1. **Stray empty session.** When the user previously opened a "New session in X" tab from the sidebar, then closed the tab to declutter, the freshly-created empty session was already on disk and visible in the sidebar. Coming back to the welcome screen (activeTabId = null → EmptySession route) and clicking "Continue from here" called `createSession` unconditionally, minting yet another empty session next to the now-stale one. The user ended up with `Untitled Session 27 minutes ago` lingering in the sidebar while the hand-off ran in a completely separate fresh session. Extract the picker into `desktop/src/lib/sessionReuse.ts` — `pickReusableEmptySession(sessions, workDir, excludeSessionId?)` filters by exact-workDir match, `messageCount === 0`, excludes the previous session being handed off FROM, and sorts by `modifiedAt` desc. Caller in `EmptySession.onAutoHandoff` runs this before `createSession`; on hit, openTab on the existing sessionId and let ContentRouter switch to ActiveSession naturally; on miss, create fresh as before. 7 unit tests cover the boundaries: workDir mismatch, non-zero messageCount, excludeSessionId honored, null workDir treated as "no candidates" (so we never silently merge home-dir sessions into a project hand-off), empty workDir argument, empty session list, freshness sort order. 2. **Summary too abstract; AI doesn't know specific recent state.** The previous implementation only injected the LLM-summarized `main` + `recent` paragraphs into the next session's system prompt. That summarization tends to wash out exact wording, file paths, error messages, and the user's literal last question — the user reported "AI doesn't know what we just hit a wall on." Add `recentRaw?: string` to `SessionSummary`. New helper `buildRecentRawSlice` keeps the LAST ~12 turns (env-tunable via `CLAUDE_CODE_HANDOFF_RAW_TURNS`, range 0–50, default 12), each truncated to 400 chars preserving the `USER:` / `ASSISTANT:` role prefix, total capped at ~8000 chars (env-tunable via `CLAUDE_CODE_HANDOFF_RAW_CHARS`, range 500–30000, default 8000). Older turns drop first when the total cap is busted by dense recent turns. `formatHandoffSystemPrompt` renders the raw slice inside a fenced code block AFTER the abstracted recent summary, so the next session sees both the digest and the literal text. Section is omitted entirely when `recentRaw` is absent — v0.5.7 caches still load and produce the exact same prompt bytes (back-compat). 8 unit tests cover the formatter's back-compat path, the raw block placement, fence rendering, tail-N selection, all-fits case, per-turn truncation with role prefix preservation, total cap busting (older drops first), and the `RAW_TURNS=0` opt-out. Both fixes fold into the unreleased v0.5.8 — release-notes/v0.5.8.md gets two new fix bullets and the 范围 / 验证 sections call out the new files and 15 added tests. desktop/package.json bump to 0.5.8 stays as-is (preset earlier in the same worktree before this commit). Tested: - bun run lint (desktop) clean - bunx vitest run sessionReuse.test.ts → 7/7 pass - bun test sessionSummaryService.test.ts → 8/8 pass - bunx vitest run EmptySession.test.tsx → 22/22 pass (regression check after the helper extraction — the existing tests don't go through the hand-off branch but exercise the rest of the file) Confidence: high Scope-risk: narrow (no shape changes to any persistence — recentRaw is an additive field, old caches deserialize cleanly because `tryParseSummaryResponse` already only required main+recent) Co-authored-by: 你的姓名 <you@example.com>
9.4 KiB
v0.5.8
新功能
-
逆向工程插件 v0.4.0(
plugins/reverse-engineering)。仓库自带的 marketplace 现在收录一个多平台 逆向工具箱,一键安装即可获得 7 个 MCP 服务器、1 个编排 agent、11 个 skill、2 个 slash 命令:- 静态分析:Ghidra(pyghidra-mcp)/ radare2 / JADX / apktool。覆盖 PE / ELF / Mach-O,以及 无 header 的固件 blob(路由器固件、Cortex-M flash dump、ECU dump 等)。多架构:x86/x64、ARM (含 Cortex-M Thumb-only)、AArch64、MIPS、PowerPC(含 VLE)、Motorola 68k / ColdFire、SuperH、 RISC-V,以及 AVR / MSP430 / 6502 / Z80 等小架构
- 动态分析:Frida(Java/ObjC hook + Stalker trace)/ GDB(单步、硬件断点、watchpoint、跨架构
via
gdb-multiarch + qemu)/ LLDB(Apple 平台单步 + ObjC method hook)。dynamic-debug-overviewskill 让 agent 自动选车道 - 编排:
reverse-engineeragent 走 triage → static → 可选 dynamic → report 流程,产物落在${ARTIFACT_DIR}/<sample-id>/(默认artifacts/re-runs) - slash 命令:
/reverse-engineering:triage <path>、/reverse-engineering:report <sample-id> - 配置:
GHIDRA_INSTALL_DIR(可选,Ghidra 安装目录)、ARTIFACT_DIR(产物输出位置) - 规则:对样本只读,不向外推任何样本(无 VT / no malware-bazaar),不破解商业授权,Frida 只跑 用户授权过的目标,纯静态结论可信度上限封在 medium
桌面端「设置 → 插件」添加本仓库
plugins/目录作为 marketplace 即可启用。详见plugins/reverse-engineering/README.md。 -
零成本会话接力。新建会话欢迎页"最近活动"卡片新增"从这里继续"按钮。点击后服务端用 LLM 生成上一个会话的两层摘要(主线 + 最新进展)落盘缓存,通过
--append-system-prompt注入到新 会话的 system prompt,再自动发一条短的 trigger message 让 AI 接续。前端展示生成进度阶段 ("读缓存 → 生成摘要 → 启动会话"),完成后会话头部出现↗ 已接续 (N tokens)小芯片。摘要生成 失败时静默降级到原有的 zero-token textarea 预填路径。摘要 token 上限受CLAUDE_CODE_HANDOFF_MAX_TOKENS(默认 1500)和CLAUDE_CODE_HANDOFF_INPUT_CHARS(默认 80000)约束,WS handler 缓存命中后不重生成。 -
欢迎任务卡片项目感知。原本写死的 4 个起始 prompt 现在按项目状态动态填充:
- "PR 预合并审查"会替换成实际的
git.defaultBranch,develop 分支上不会再让 AI 对着 main 做审查 - "排查失败的测试"和"补单元测试"会从最新的 dirty files 列表里挑一个真实文件路径(测试文件正则 + 源码文件正则,跳过锁文件 / 构建产物 / 二进制),自动填进 prompt
- 每张卡片的
title=属性都是完整解析后的 prompt,鼠标悬停就能预览要发送什么 - 第 4 张卡
explainCode重命名为understandProject,prompt 改成读 CLAUDE.md / AGENTS.md / README + 列技术栈和顶层目录的项目全景介绍 - 服务端
recent-activity接口新增dirtyFiles[]字段(git status --porcelain=v1 -z解析,按 mtime 倒序,最多 20 个),走原有 TTL 缓存
- "PR 预合并审查"会替换成实际的
-
伪 tool_use 检测与 provider 兼容追踪。某些第三方 Anthropic 兼容网关(mimo / lgfzer / 部分代理) 不转发原生 tool_use block,模型只能在
content_delta里输出 XML 风格的<tool_use ...>{...}</tool_use>当文本流过来,渲染后变成<tool_useid="..."那样的乱码,而且模型自己以为调用成功还会写"Done."。 这次三层防御:- 桌面端
desktop/src/lib/fakeToolUseDetection.ts用正则提取这种伪块(闭合 / 流式半开 / 多块连续 / 属性顺序互换 / 引号变体 / 自闭合 / 围栏代码块内的合法示例不误伤),AssistantMessage在交给MarkdownRenderer前清掉,copyText也走净化版本 - 新组件
FakeToolUseNotice在气泡上方渲染灰色提示卡:"模型尝试用 XML 文本块调用Bash,但当前 provider 似乎不转发原生 tool_use,实际并未执行",让用户不会误信后续"Done." - 新 store
providerCompatStore按 provider id 计数(localStorage 持久化),累计 3 次伪 tool_use 弹一次 warning toast 建议切换 provider;Settings → Provider 列表上对应 provider 显示"工具调用异常"红色徽标, 编辑该 provider 配置后会自动清零(给新配置一次机会),阈值之后只增不弹,不打扰
- 桌面端
修复
- 会话接力不再留下空白会话。当用户从 sidebar 顶部点过"新建会话"创建了一个空白 sessionA(然后
关掉 tab 留在 sidebar),回到欢迎屏点"从这里继续"时,之前的实现会再 createSession 一个新会话
sessionB,sessionA 变成孤儿空白会话。现在 EmptySession.onAutoHandoff 在 createSession 前先用
pickReusableEmptySession找同 workDir 下消息数=0 且不是 previousSessionId 的最新空白会话,有 就 openTab 复用它,没有才创建新的。新增desktop/src/lib/sessionReuse.ts+ 7 个单测覆盖 workDir 过滤、消息数过滤、excludeSessionId、null workDir 防御等边界。 - 会话接力摘要现在带最后 12 轮原文(可调)。原本的两层摘要 main + recent 是 LLM 抽象出来的,
容易丢失"用户上一句具体问什么"、"AI 上一次回复到哪了"的真实措辞。现在
sessionSummaryService生成摘要时额外保留原会话最后 12 轮(默认)的 USER:/ASSISTANT: 原文,每条截到 400 字、整体 cap 8000 字,新字段recentRaw落进缓存,formatHandoffSystemPrompt在 main+recent 之后追加这段 到接续 system prompt 里。可通过环境变量CLAUDE_CODE_HANDOFF_RAW_TURNS(0–50,默认 12)和CLAUDE_CODE_HANDOFF_RAW_CHARS(500–30000,默认 8000)调节。0.5.7 旧缓存没有recentRaw字段, formatter 自动跳过原文段,完全向后兼容。 - 服务端模型上下文不再示范错误格式。
specialistRouter.ts早就警告过key="value"属性式片段 会让网关模型把 tool_use 退化成 XML 文本,但还有 3 处反复给模型喂subagent_type="verification":verification_gate_reminder(messages.ts)、TodoWriteTool 的 verification 提醒、TaskUpdateTool 的 verification 提醒。改成散文形式("set the subagent_type parameter to verification"),从源头降低 伪 tool_use 概率。新增noKeyValueNudges.test.ts锁住这 3 处,以后改回属性形式立即挂 CI。
范围
- 会话接力修复:
desktop/src/lib/sessionReuse.ts(空白会话复用 picker)、desktop/src/lib/sessionReuse.test.ts(7 单测)、desktop/src/pages/EmptySession.tsx(onAutoHandoff 接入 picker)、src/server/services/sessionSummaryService.ts(recentRaw字段 + buildRecentRawSlice + formatHandoffSystemPrompt 注入)、src/server/services/sessionSummaryService.test.ts(8 单测)。 - 逆向插件:
plugins/.claude-plugin/marketplace.json、plugins/reverse-engineering/(plugin.json / mcp/servers.json / agents/reverse-engineer.md / 11 个 SKILL.md / 2 个 slash 命令 / scripts/{dev-link,smoke,validate}.ts / README.md)。 - 会话接力:
src/server/services/sessionSummaryService.ts(LLM 双层摘要 + 磁盘缓存)、src/server/api/sessions.ts、src/server/ws/handler.ts(set_handoff_summary路径)、desktop/src/components/welcome/RecentActivityCard.tsx、desktop/src/api/projects.ts、desktop/src/stores/sessionRuntimeStore.ts(handoffInfo)。 - 欢迎卡片:
desktop/src/components/welcome/WelcomeTaskCards.tsx(resolver 模式 + 内部 fetch)、desktop/src/api/projects.ts、desktop/src/pages/{EmptySession,ActiveSession}.tsx、src/server/services/projectActivityService.ts(dirtyFiles 派生)、5 个语言的 i18n 模板参数化。 - 伪 tool_use 检测:
desktop/src/lib/fakeToolUseDetection.ts、desktop/src/stores/providerCompatStore.ts、desktop/src/components/chat/{FakeToolUseNotice.tsx,AssistantMessage.tsx}、desktop/src/pages/Settings.tsx(badge + clear-on-edit)、src/utils/messages.ts、src/tools/{TodoWriteTool,TaskUpdateTool}/、src/utils/noKeyValueNudges.test.ts。 - i18n:5 个语言新增会话接力、欢迎卡片参数化 prompt、providerCompat 共 10+ 条 key。
验证
- 单元测试:
fakeToolUseDetection.test.ts14 /providerCompatStore.test.ts8 /AssistantMessage.faketooluse.test.tsx6 /EmptySession.test.tsx22 /sessionRuntimeStore.test.ts(含 handoffInfo)/noKeyValueNudges.test.ts3 /sessionReuse.test.ts7 /sessionSummaryService.test.ts8 全部通过 ✅ cd desktop && bun run lint:tsc --noEmit 通过 ✅- 服务端
bun test src/utils/{verificationGate,noKeyValueNudges} src/tools/AgentTool/specialistRouter: 31 个测试通过 ✅ - 浏览器 MCP 端到端:在
feat/welcome-cards-polishworktree 下,4 张卡片正确替换为feat/welcome-cards-polish分支名,脏文件desktop/src/pages/EmptySession.test.tsx/desktop/src/pages/ActiveSession.tsx自动填进 testPath / filePath 槽位,点击后撰写框正确预填 ✅ - 会话接力 MCP 端到端:
feat/session-handoff-summary分支生成两层摘要,新会话头部出现↗ 已接续 (N tokens)芯片,AI 首条响应直接基于摘要继续,不再要求用户重新解释上下文 ✅ - 逆向插件:本次发布未运行端到端 smoke。校验入口在
plugins/reverse-engineering/scripts/smoke.ts(注册 marketplace → enable →/api/plugins/update+/reload→ 断言版本号、组件计数与磁盘源 一致),需服务端 + vite 起来后手动跑 ⚠️ pending