120 Commits

Author	SHA1	Message	Date
iven	58ff0bdde7	fix(kernel,desktop): Core Chain Hardening 穷尽审计 7 项修复 ... 审计发现 1 CRITICAL + 4 HIGH + 4 MEDIUM + 4 LOW, 修复如下: CRITICAL: - TS seam 测试改为 JSON round-trip 验证 (12 测试覆盖 10 事件类型) HIGH: - post_conversation_hook 拦截路径 driver=None 加 debug 日志 - schedule intercept channel send 失败回退 LLM (return Ok(None)) MEDIUM: - DeltaBuffer.flush() 先 mutation 再 clear, 防止异常丢数据 - ModelsAPI.tsx 去重: 改用 model-config.ts 导出 (消除 2 函数+1 接口+2 常量) - boot_with_driver docstring 记录跳过 agent 恢复 TypeScript 0 错误, Rust 76 kernel 测试通过, TS 12 seam 测试通过	2026-04-21 23:30:08 +08:00
iven	27006157da	refactor(desktop): connectionStore 拆分 — 模型配置提取为 lib/model-config.ts ... - 提取 213 行模型配置逻辑到独立模块: CustomModel 接口/API Key 管理/默认模型解析 - connectionStore 通过 re-export 保持向后兼容, 外部导入无需变更 - 消除 ModelsAPI.tsx 中 loadCustomModelsBase/saveCustomModelsBase 的重复逻辑 (待后续对接) - connectionStore 891→693 行 (-22%), model-config.ts 225 行 - TypeScript 类型检查通过	2026-04-21 23:07:15 +08:00
iven	191cc3097c	refactor(desktop): streamStore sendMessage 拆分 Phase 3 — 提取 DeltaBuffer+4 Handler ... - DeltaBuffer 类: ~60fps 文本/思考增量缓冲，替换内联 textBuffer/thinkBuffer - createToolHandler: 工具步骤管理 (toolStart/toolEnd + artifact 自动创建) - createHandHandler: Hand 能力消息生成 - createSubtaskHandler: 子任务状态映射 - createCompleteHandler: 完成回调 (token 统计+记忆提取+反思+建议) - sendMessage 内联回调从 ~350 行缩减到 ~130 行 (-63%) - TypeScript 类型检查通过, 8 个 seam 测试通过	2026-04-21 23:03:04 +08:00
iven	317b8254e4	fix(growth,saas): B9 Agent创建502调查+日志增强 ... 深入追踪 B9 (Agent 创建 502): - SaaS create_agent_from_template 端点代码不可能产生 502 (SaasError::Relay 是唯一 502 来源,仅 relay 模块使用) - 前端 createFromTemplate 双层 try-catch + fallback 已足够健壮 - 结论: B9 不可复现,可能因当时 SaaS 未运行或 token 过期导致 改进: - handlers.rs: 添加 create_agent_from_template 请求/响应日志 - agentStore.ts: outer catch 记录 status + message 便于未来诊断	2026-04-21 21:19:44 +08:00
iven	b2908791f6	fix(desktop): Tauri 端找碴验证 7 项修复 — 消息泄漏/UUID暴露/错误友好化 ... B15/B11: streamStore onAgentStream 添加 activeRunId 过滤，移除降级匹配， hand/workflow 消息追加前验证 runId 归属；chatStore 切换/新建对话时 先 cancelStream 终止旧流；ChatArea hand-execution-complete 事件 添加 isStreaming 守卫 B4/B5: ChatArea 模型列表过滤 embedding 模型，provider 设为 undefined 隐藏 UUID B2/B3: streamStore onError 添加 formatUserError 函数，将原始 JSON 错误转换为中文友好提示 B1: SuggestionChips onSelect 延迟调用 handleSend 自动发送建议 fix(runtime): test_util.rs with_error 添加 mut self，with_stream_chunks 移除多余 mut fix(saas): lib.rs 添加 Result/SaasError re-export	2026-04-21 20:29:47 +08:00
iven	f2917366a8	fix(growth,kernel,runtime,desktop): 50 轮功能链路审计 7 项断链修复 ... P0 修复: - B-MEM-2: 跨会话记忆丢失 — 添加 IdentityRecall 查询意图检测， 身份类查询绕过 FTS5/LIKE 文本搜索，直接按 scope 检索全部偏好+知识记忆； 缓存 GrowthIntegration 到 Kernel 避免每次请求重建空 scorer - B-HAND-1: Hands 未触发 — 创建 HandTool wrapper 实现 Tool trait， 在 create_tool_registry() 中注册所有已启用 Hands 为 LLM 可调用工具 P1 修复: - B-SCHED-4: 一次性定时未拦截 — 添加 RE_ONE_SHOT_TODAY 正则匹配 "下午3点半提醒我..."类无日期前缀的同日触发模式 - B-CHAT-2: 工具调用循环 — ToolErrorMiddleware 添加连续失败计数器， 3 次连续失败后自动 AbortLoop 防止无限重试 - B-CHAT-5: Stream 竞态 — cancelStream 后添加 500ms cancelCooldown， 防止后端 active-stream 检查竞态	2026-04-20 09:43:38 +08:00
iven	24b866fc28	fix(growth,runtime,desktop): E2E 验证 4 项 Bug 修复 ... P1 BUG-1: SemanticScorer CJK 分词缺失导致 TF-IDF 相似度为 0 - 新增 CJK bigram 分词: "北京工作" → ["北京","京工","工作","北京工作"] - 非CJK文本保持原有分割逻辑 - 3 个新测试: bigram 生成 + 混合文本 + CJK 相似度>0 P1 BUG-2: streamStore lifecycle:end 未记录 token 使用量 - AgentStreamDelta 增加 input_tokens/output_tokens 字段 - lifecycle:end 处理中检查并调用 addTokenUsage P2 BUG-3: NlScheduleParser "X点半" 解析为整点 - 所有时间正则增加可选的 (半) 捕获组 - extract_minute 辅助函数: 半 → 30 P2 BUG-4: NlScheduleParser "工作日每天" 未转为 1-5 - RE_WORKDAY_EXACT 支持 (每天|每日)? 中缀 - try_workday 优先级提升至 try_every_day 之前 E2E 报告: docs/E2E_TEST_REPORT_2026_04_19.md 测试: 806 passed / 0 failed (含 9 个新增测试)	2026-04-20 00:07:07 +08:00
iven	e12766794b	fix(relay,store): 审计修复 — 自动恢复可达化 + 类型化错误 + 全路径重连 ... C1: mark_key_429 设 is_active=FALSE，使 select_best_key 自动恢复 路径真正可达。之前 429 只设 cooldown_until，恢复代码为死代码。 H1+H2: 重试查询补全 debug 日志（RPM/TPM 跳过、解密失败）+ 修复 fallthrough 错误信息（RateLimited 而非 NotFound）。 H3+H4+M3+M4+M5: agentStore.ts 提取 classifyAgentError() 类型化错误 分类，覆盖 502/503/401/403/429/500，统一 createClone/ createFromTemplate/updateClone/deleteClone 错误处理，不再泄露原始 错误详情。所有 catch 块添加 log.error。 H5+H6: auth.ts 提取 triggerReconnect() 共享函数，login/loginWithTotp/ restoreSession 三处统一调用。状态检查改为仅 'disconnected' 时触发， 避免 connecting/reconnecting 状态下并发 connect。 M1: toggle_key_active(true) 同步清除 cooldown_until，防止管理员 激活后 key 仍被 cooldown 过滤不可见。	2026-04-19 13:45:49 +08:00
iven	0bd50aad8c	fix(heartbeat,skills): 健康快照降级处理 + 技能加载重试 ... P1-3: health_snapshot 在 heartbeat engine 未初始化时不再报错， 返回 pending 状态快照，避免 HealthPanel 竞态报错。 P1-1: loadSkillsCatalog 新增 Path C 延迟重试（最多2次，间隔 1.5s/3s），解决 kernel 初始化未完成时 skills 返回空数组的问题。	2026-04-19 13:27:25 +08:00
iven	4ee587d070	fix(relay,store): Provider Key 自动恢复 + Agent 创建友好错误 + 登录后重连 ... P0-1: key_pool.rs 新增 cooldown 过期 Key 自动恢复逻辑。 当所有 Key 的 is_active=false 且 cooldown_until 已过期时， 自动重新激活并重试选择，避免 relay/models 返回空数组导致聊天失败。 P0-2: agentStore.ts createClone/createFromTemplate 错误信息 从原始 HTTP 错误改为可操作的中文提示（502/503/401 分类处理）。 P1-2: auth.ts login 成功后触发 connectionStore.connect()， 确保 kernel 使用新 JWT 而非旧 token。	2026-04-19 13:16:12 +08:00
iven	0fd78ac321	fix: 全面审计修复 — P0 功能缺陷 + P1 代码质量 ... P0 功能修复: - stats: Admin V2 仪表盘 API 路径修正 (/stats/dashboard → /admin/dashboard) - mcp: 桌面端 MCP 插件增加 isTauriRuntime() 守卫，避免浏览器模式崩溃 - admin: 侧边栏高亮逻辑修复 (startsWith → 精确匹配+子路径) P1 代码质量: - 删除 workflowBuilderStore.ts 死代码 (456行，零引用) - sqlite.rs 3 处 SQL 静默失败改为 tracing::warn! 日志 - mcp_tool_adapter 2 处 unwrap 改为安全回退 - orchestration_execute 添加 @reserved 标注 - TRUTH.md 测试数字校准 (734→803)，Store 数 26→25	2026-04-18 23:57:03 +08:00
iven	e3b6003be2	refactor(store): saasStore 拆分为子模块 (Phase 2B) ... 1025行单文件 → 5个文件 + barrel re-export: - saas/types.ts (103行) — 类型定义 - saas/shared.ts (93行) — Device ID、常量、recovery probe - saas/auth.ts (362行) — 登录/注册/登出/恢复/TOTP - saas/billing.ts (84行) — 计划/订阅/支付 - saas/index.ts (309行) — Store 组装 + 连接/模板/配置 - saasStore.ts (15行) — re-export barrel（外部零改动） 所有 25+ 消费者 import 路径不变，`tsc --noEmit` ✓	2026-04-17 20:05:43 +08:00
iven	cb9e48f11d	refactor(hands): 移除空壳 Hand — Whiteboard/Slideshow/Speech (Phase 5) ... 删除 3 个仅含 UI 占位的 Hand，清理 Rust 实现与前端引用： - Rust: whiteboard.rs(422行) + slideshow.rs(797行) + speech.rs(442行) - 前端: WhiteboardCanvas + SlideshowRenderer + speech-synth + 相关类型/常量 - 配置: 3 个 HAND.toml - 净减 ~5400 行，Hands 9→6(启用) + Quiz/Browser/Researcher/Collector/Clip/Twitter/Reminder	2026-04-17 19:55:59 +08:00
iven	1309101a94	fix(ui): Agent 面板信息不随对话更新 — 事件时序 + clones 刷新 ... - streamStore: zclaw:agent-profile-updated 事件从记忆提取前改为 .then() 后触发 - RightPanel: profile 更新事件中新增 loadClones() 刷新 selectedClone 数据	2026-04-16 22:57:32 +08:00
iven	a0d1392371	fix(ui): 5 项 E2E 测试 Bug 修复 — Agent 502 / 错误持久化 / 模型标记 / 侧面板 / 记忆页 ... - BUG-01: createFromTemplate 在 saas-relay 模式下 try-catch 跳过本地 Kernel - BUG-02: upsertActiveConversation 持久化前剥离 error/streaming/optimistic 字段 - BUG-04: ModelSelector 添加 available 标记，ChatArea 追踪失败模型 ID - BUG-05: VikingPanel 移除 status?.available 门控，不可用时 disabled + 重连按钮 - BUG-06: 侧面板 tooltip 改为"查看产物文件"，空状态增加图标和说明	2026-04-16 19:12:21 +08:00
iven	3c01754c40	fix(agent): 12 项 agent 对话链路全栈修复 ... 深端到端验证发现 12 个问题，6 Phase 全栈修复： Phase 5 — 快速 UX 修复: - #9: SimpleSidebar 添加新对话按钮 (SquarePen + useChatStore) - #5: 模型列表 JOIN provider_keys 过滤无 API Key 的模型 - #11: AgentOnboardingWizard 焦点领域增加 4 行业选项 (医疗健康/教育培训/金融财务/法律合规) Phase 1 — ButlerPanel 记忆修复: - #2a: MemorySection URI 从 viking://agent/.../memories/ 修正为 agent://.../ - #2b: "立即分析对话"按钮现在触发 extractAndStoreMemories Phase 2 — FTS5 中文分词: - #4: FTS5 tokenizer 从 unicode61 切换到 trigram，原生支持 CJK - 自动迁移：检测旧 unicode61 表并重建索引 - sanitize_fts_query 支持中文引号短语查询 Phase 3 — 跨会话身份持久化: - #6-8: 重新启用 USER.md 注入系统提示词 (截断前 10 行) Phase 4 — Agent 面板同步: - #1,#10: listClones 从 4 字段扩展到完整映射 (soul/userProfile 解析 nickname/emoji/userName/userRole) - updateClone 通过 identity 系统同步 nickname→SOUL.md 和 userName/userRole→USER.md Phase 6 — Agent 创建容错: - #12: createFromTemplate 增加 SaaS 不可用 fallback 验证: tsc --noEmit ✅ cargo check ✅	2026-04-16 09:21:46 +08:00
iven	215c079d29	fix(intelligence): Heartbeat 统一健康系统 — 6处断链修复 + 健康面板 + SaaS自动恢复 ... Rust 后端 (heartbeat.rs): - 告警实时推送: OnceLock<AppHandle> + Tauri emit heartbeat:alert - 动态间隔: tokio::select! + Notify 替代不可变 interval - Config 持久化: update_config 写入 VikingStorage - heartbeat_init 从 VikingStorage 恢复 config - 移除 dead code (subscribe, HeartbeatCheckFn) - Memory stats fallback 分层处理 新增 health_snapshot.rs: - HealthSnapshot Tauri 命令 — 按需查询引擎/记忆状态 - 注册到 lib.rs invoke_handler 前端修复: - HeartbeatConfig handleSave 同步到 Rust 后端 - App.tsx 读 localStorage 持久化配置 + heartbeat:alert 监听 + toast - saasStore 降级后指数退避探测恢复 + saas-recovered 事件 - 新增 HealthPanel.tsx 只读健康面板 (4卡片 + 告警列表) - SettingsLayout 添加 health 导航入口 清理: - 删除 intelligence-client/ 目录版 (9文件 -1640行, 单文件版是活跃代码)	2026-04-15 23:19:24 +08:00
iven	76d36f62a6	fix(desktop): 模型自动路由 — 首次登录自动选择可用模型 ... - saasStore: fetchAvailableModels 处理 currentModel 为空的情况，自动选择第一个可用模型 - connectionStore: SaaS relay 连接成功后同步 currentModel 到 conversationStore - 同时覆盖 Tauri 和浏览器两条 SaaS relay 路径 - 修复首次登录用户需手动选模型的问题	2026-04-15 01:45:36 +08:00
iven	02a4ba5e75	fix(desktop): 替换 require() 为 ES import — 修复生产构建崩溃 ... - connectionStore: 2 处 require() → loadConversationStore() 异步预加载 + 闭包引用 - saasStore: 1 处 require() → await import()（logout 是 async） - llm-service: 1 处 require() → 顶层 import（无循环依赖） - streamStore: 移除重复动态导入，统一使用顶层 useConnectionStore - tsc --noEmit 0 errors	2026-04-15 00:47:29 +08:00
iven	e0eb7173c5	fix: 三端联调 P1 修复 — API密钥页崩溃 + 桌面端401恢复 + 用量统计全零 ... P1-03: vite.config.ts proxy '/api' → '/api/' 加尾部斜杠， 防止前缀匹配 /api-keys 导致 SPA 路由崩溃 P1-01: kernel_init 增加 api_key 变更检测（token 刷新后自动重连）， streamStore 增加 401 自动恢复（refresh token → kernel reconnect）， KernelClient 新增 getConfig() 方法 P1-02: /api/v1/usage 总计改从 billing_usage_quotas 读取 （authoritative source，SSE 和 JSON 均写入）， by_model/by_day 仍从 usage_records 读取	2026-04-14 22:02:02 +08:00
iven	dd854479eb	fix: 三端联调测试 2 P1 + 2 P2 + 4 P3 修复 ... P1-07: billing get_or_create_usage 同步 max_* 列到当前计划限额 P1-08: relay handler 增加直接配额检查 (relay_requests/input/output_tokens) P2-09: relay failover 成功后记录 tokens 并标记 completed P2-10: Tauri agentStore saas-relay 模式下从 SaaS API 获取真实用量 P2-14: super_admin 合成 subscription + check_quota 放行 P3-19: 新建 ApiKeys.tsx 页面替代 ModelServices 路由 P3-15: antd destroyOnClose → destroyOnHidden (3处) P3-16: ProTable onSearch → onSubmit (2处)	2026-04-14 17:48:22 +08:00
iven	45fd9fee7b	fix(desktop): P0-1 验证 SaaS 模型选择 — 防止残留模型 ID 导致请求失败 ... Tauri 桌面端通过 SaaS Token Pool 中转访问 LLM，模型列表由 SaaS 后端 动态提供。之前的实现直接使用 conversationStore 持久化的 currentModel， 可能在切换连接模式后使用过期的模型 ID，导致 relay 请求失败。 修复： - Tauri 路径：用 SaaS relayModels 的 id+alias 构建 validModelIds 集合， preferredModel 仅在集合内时才使用，否则回退到第一个可用模型 - 浏览器路径：同样验证 currentModel 在 SaaS 模型列表中才使用 后端 cache.resolve_model() 别名解析作为二道防线保留。	2026-04-14 07:08:56 +08:00
iven	4c3136890b	fix: 三端联调测试 2 P0 + 6 P1 + 2 P2 修复 ... P0-1: SaaS relay 模型别名解析 — "glm-4-flash" → "glm-4-flash-250414" (resolve_model) P0-2: config.rs interpolate_env_vars UTF-8 修复 (chars 迭代器替代 bytes as char) + DB 启动编码检查 + docker-compose UTF-8 编码参数 P1-3: UI 模型选择器覆盖 Agent 默认模型 (model_override 全链路: TS→Tauri→Rust kernel) P1-6: 知识搜索管道修复 — seed_knowledge 创建 chunks + 默认分类 (seed/uploaded/distillation) P1-7: 用量限额从当前 Plan 读取 (非 stale usage 表) P1-8: relay 双维度配额检查 (relay_requests + input_tokens) P2-9: SSE 路径 token 计数修复 — 流结束检测替代固定 500ms sleep + billing increment	2026-04-14 00:17:08 +08:00
iven	f8c5a76ce6	fix(industry): 审计收尾 — MEDIUM + LOW 全部清零 ... M-1: Industries 创建弹窗添加 cold_start_template + pain_seed_categories M-3: industryStore console.warn → createLogger 结构化日志 B2: classify_with_industries 平局打破 + 归一化因子 3.0 文档化 S3: set_account_industries 验证移入事务内消除 TOCTOU T1: 4 个 SaaS 请求类型添加 deny_unknown_fields I3: store_trigger_experience Debug 格式 → signal_name 描述名 L-1: 删除 Accounts.tsx 死代码 editingIndustries L-3: Industries.tsx filters 类型补全 source 字段	2026-04-12 20:37:48 +08:00
iven	b853978771	feat(industry): Phase 3 Tauri 行业配置加载 — SaaS API mixin + industryStore + Tauri 命令 ... - 新增 saas-industry.ts mixin: listIndustries/getIndustryFullConfig/getMyIndustries - 新增 saas-types 行业类型: IndustryInfo/IndustryFullConfig/AccountIndustryItem - 新增 industryStore.ts: Zustand store + localStorage persist + Rust 注入 - 新增 viking_load_industry_keywords Tauri 命令: 接收 JSON configs → 全局存储 - 前端 bootstrap 后自动拉取行业配置并推送到 ButlerRouter	2026-04-12 17:18:53 +08:00
iven	b3f7328778	feat(ui): '我眼中的你' 双源渲染 — 静态Clone + 动态UserProfile ... - RightPanel 增加 userProfile state + fetch 逻辑 - 对话结束后通过 CustomEvent 触发画像刷新 - UserProfile 字段: 行业/角色/沟通偏好/近期话题 桥接 identity 系统 → 前端面板。	2026-04-11 12:51:28 +08:00
iven	f7edc59abb	fix(auth): 修复重启后无法对话 — restoreSession 优先验证 SaaS token ... 根因: 心跳降级将 'tauri' 持久化到 localStorage，重启后盲信该值。 修复: token refresh 成功时强制恢复 'saas' 模式；connectionMode 携带时间戳。	2026-04-11 12:32:20 +08:00
iven	d871685e25	fix(auth): 5 BUG 修复 — refresh token 持久化 + 密码验证 + 浏览器兼容 ... BUG-1 (P1): LoginPage 注册密码验证从 6 位改为 8 位，与后端一致 BUG-2 (P0): refresh token 持久化到 OS keyring + restoreSession 三级恢复 (access token → refresh token → cookie auth) + saveSaaSSession 改为 await BUG-3 (P0): Tauri 聊天路由降级问题，根因同 BUG-2（会话恢复失败） BUG-4 (P1): App.tsx 跳过 Onboarding 改用 agentStore（兼容所有 client）， Workspace.tsx Tauri invoke 改为动态 import 避免浏览器崩溃 BUG-5: tauri.conf.json createUpdaterArtifacts 改为 boolean true	2026-04-11 09:43:17 +08:00
iven	722d8a3a9e	fix(ui): UX 文案优化 — 区分新/老用户 + 去政务化 + 友好提示 ... - FirstConversationPrompt: 新用户显示"欢迎开始!"，老用户"欢迎回来!" - use-cold-start: 冷启动问候语改为通用语言，去掉政务场景特定文案 - LoginPage: 添加"忘记密码？请联系管理员重置"提示 - connectionStore: 错误提示改为用户友好的"暂时没有可用的 AI 模型"	2026-04-11 02:56:19 +08:00
iven	4e641bd38d	refactor(desktop): SaaS URL 集中配置化，消除 5 处硬编码 ... - 新增 .env.development / .env.production (VITE_SAAS_URL) - saasStore.ts / LoginPage.tsx / saas-client.ts / SaaSLogin.tsx 统一读取 import.meta.env.VITE_SAAS_URL - 移除 LoginPage 中未使用的 isTauriRuntime import	2026-04-11 02:09:23 +08:00
iven	550e525554	fix(ui): 审计修复 — 路径规范化/SkillInfo类型/分页offset/初始加载/显示统一 ... - workspace.rs: canonicalize() 解析 '..' 和符号链接 - Workspace.tsx: 组件挂载时调用 loadDirStats + 统一 KB 显示 - configStore: SkillInfo 接口补充 category 字段 + 空数组回退注释 - securityStore: localStorage 审计日志添加 offset 分页支持	2026-04-10 23:24:32 +08:00
iven	1d0e60d028	fix(ui): 9项端到端真实审计 — 修复记忆/技能/审计/工作区/MCP数据流断裂 ... 基于 Tauri MCP 实机排查发现并修复： 1. VikingPanel: viking_ls('/') 返回0 → 改为 viking_ls('') 返回100条记忆 2. 技能列表: loadSkillsCatalog 静默失败 → 添加直接 invoke('skill_list') 回退 3. 审计日志: 面板读Gateway API无数据 → 回退读localStorage双源数据 4. 工作区: 浏览按钮无事件 → 接入prompt选择 + workspace_dir_stats 命令 5. MCP: 空列表无引导 → 添加配置文件路径提示 6. 新增 workspace_dir_stats Tauri 命令 (Rust) 排查确认正常的功能: 安全存储(OS Keyring✅), 心跳引擎(运行中✅), 定时任务(管道连通), Kernel(已初始化✅), SaaS relay模式	2026-04-10 23:00:19 +08:00
iven	9442471c98	fix(relay): send conversation history to SaaS relay (BUG-008) ... SaaS Relay was sending only the current message without conversation history, giving LLM no context from previous turns. Root cause: streamStore passed only `content` string to chatStream(), and saas-relay-client hard-coded a single-element messages array. Fix: - GatewayClient.chatStream() opts: add `history` field - streamStore: extract last 20 messages as history before calling chatStream - saas-relay-client: build messages array from history + current message	2026-04-09 22:41:56 +08:00
iven	bf728c34f3	fix: saasStore require() bug + health check pool formula + DEV error details ... - saasStore.ts: replace require('./chat/conversationStore') with await import() to fix ReferenceError in Vite ESM environment (P1) - main.rs: fix health check pool usage formula from max_connections - num_idle to pool.size() - num_idle, preventing false "degraded" status (P1) - error.rs: show detailed error messages in ZCLAW_SAAS_DEV=true mode - Update bug tracker with BUG-003 through BUG-007	2026-04-09 22:23:05 +08:00
iven	e6eb97dcaa	perf(relay): full-chain optimization — key pool, model sync, SSE stream ... Phase 1 (Key Pool correctness): - RPM: fixed-minute window → sliding 60s aggregation (prevents 2x burst) - Remove fallback-to-provider-key bypass when all keys rate-limited - SSE semaphore: 16→64 permits, cleanup delay 60s→5s - Default 429 cooldown: 5min→60s (better for Coding Plan quotas) - Expire old key_usage_window rows on record Phase 2 (Frontend model sync): - currentModel empty-string fallback to glm-4-flash-250414 in relay client - Merge duplicate listModels() calls in connectionStore SaaS path - Show ModelSelector in Tauri mode when models available - Clear currentModel on SaaS logout Phase 3 (Relay performance): - Key Pool: DashMap in-memory cache (TTL 5s) for select_best_key - Cache invalidation on 429 marking Phase 4 (SSE stream): - AbortController integration for user-cancelled streams - SSE parsing: split by event boundaries (\n\n) instead of per-line - streamStore cancelStream adapts to 0-arg and 1-arg cancel fns	2026-04-09 19:34:02 +08:00
iven	5c6964f52a	fix(desktop): error response improvements — content, retry, model selector ... P1: onError callback now sets content to error message instead of empty string. Previously API errors (404/429) produced empty assistant messages with only a visual error badge — now the error text is persisted in message content. P3: Retry button now re-sends the preceding user message via sendToGateway instead of copying to input. Works for both virtualized and non-virtualized message lists. Removed unused setInput prop from MessageBubble. Also hides model selector in Tauri runtime (SaaS token pool routes models).	2026-04-09 18:52:27 +08:00
iven	125da57436	fix: sync currentModel from SaaS available models on login ... Root cause: conversationStore hardcoded 'glm-4-flash' as default model, which may not exist in SaaS admin config, causing 404 on all chat requests. - conversationStore: default currentModel to empty string (runtime-resolved) - saasStore: after fetching available models, auto-switch currentModel to first available if the stored model is not in the list - SaaS relay getModel() already had fallback to first available model	2026-04-09 18:50:38 +08:00
iven	1965fa5269	fix: migrate glm-4-flash to glm-4-flash-250414 (model deprecated by Zhipu) ... Zhipu AI has deprecated glm-4-flash, causing 404 errors on all chat requests. Updated all references: - config: glm-4-flash → glm-4-flash-250414, added glm-z1-flash - frontend: defaultModel, conversationStore, ChatArea fallback, ModelsAPI	2026-04-09 18:42:47 +08:00
iven	e6937e1e5f	feat: deliverables 3-6 — cold start, simple mode UI, bridge tests, docs ... Deliverable 3 — Cold Start Flow: - New: use-cold-start.ts — cold start detection + greeting management - Default Chinese greeting for hospital admin users - Phase tracking: idle → greeting_sent → waiting_response → completed Deliverable 4 — Simple Mode UI: - New: uiModeStore.ts — 'simple'|'professional' mode with localStorage - New: SimpleTopBar.tsx — minimal top bar with mode toggle - Modified: App.tsx — dual layout rendering based on UI mode - Modified: ChatArea.tsx — compact prop hides advanced controls - Default: 'simple' mode for zero-barrier first experience Deliverable 5 — Tauri Bridge Integration Tests: - New: tauri-bridge.integration.test.ts — 14 test cases - Covers: cold start, chat flow, persistence, memory, butler, UI mode, e2e - 14/14 passing Deliverable 6 — Release Documentation: - New: installation-guide.md — user-facing install guide (Chinese, no jargon) - New: hospital-deployment.md — IT admin deployment guide (Docker, GPO, SCCM)	2026-04-09 09:51:56 +08:00
iven	adcce0d70c	fix: 4 pre-release bug fixes — identity override, model config, agent sync, auto-identity ... P1: identity.rs get_identity() returns empty soul/instructions for agents without explicit identity files. This prevents the default ZCLAW personality from overriding agent_config.system_prompt. New get_identity_or_default() method added for the DEFAULT agent. P2: messaging.rs now uses agent_config.model.model when available, falling back to global Kernel config. This allows per-agent model selection. P2: agentStore.ts loadClones retries up to 3 times (300ms interval) when getClient() returns null, handling the coordinator initialization race. P2: agent_create Tauri command auto-populates identity files (soul + instructions) from creation parameters, ensuring build_system_prompt() has content for new agents. Also fixes conversationStore upsertActiveConversation to persist generated conversation IDs, preventing duplicate entries on new conversations.	2026-04-08 21:47:46 +08:00
iven	0b0ab00b9c	fix(chat): prevent React Maximum update depth exceeded during streaming ... Root cause: Each LLM delta (text/thinking) triggered a synchronous setState via updateMessages → chatStore.setState. With Kimi thinking model emitting many deltas per frame, this caused a React render storm that hit the maximum update depth limit. Fix (two-layer approach): 1. streamStore: Buffer text/thinking deltas locally and flush to store via setTimeout(0), batching multiple deltas per frame 2. chatStore: Microtask batching in injectChatStore.updateMessages to coalesce rapid successive updates Verified: 2-round conversation (4 messages) with Kimi thinking model completes without crash. Previously crashed 100% on 2nd message.	2026-04-08 14:47:43 +08:00
iven	02c69bb3cf	fix: subagent unique ID matching + AgentState serialization + pre-existing TS errors ... - S-3: Thread task_id (UUID) through all 6 layers (LoopEvent → StreamChatEvent → kernel-types → gateway-client → streamStore) so subtasks are matched by ID, not description string - AgentState: Add #[serde(rename_all = "lowercase")] to fix PascalCase serialization ("Running" → "running"), update frontend matcher - S-1: Remove unused onClose prop from ArtifactPanel + ChatArea call site - Fix hooks/index.ts: remove orphaned useAutomationEvents re-exports (module deleted) - Fix types/index.ts: remove orphaned automation type/value re-exports (module deleted) - Fix ChatArea.tsx: framer-motion 12 + React 19 type compat — use createElement + explicit any return type to avoid unknown-in-JSX-child error Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-06 22:30:16 +08:00
iven	9871c254be	feat: sub-agent streaming progress — TaskTool emits real-time status events ... - Rust: LoopEvent::SubtaskStatus variant added to loop_runner.rs - Rust: ToolContext.event_sender field for streaming tool progress - Rust: TaskTool emits started/running/completed/failed via event_sender - Rust: StreamChatEvent::SubtaskStatus mapped in Tauri chat command - TS: StreamEventSubtaskStatus type + onSubtaskStatus callback added - TS: kernel-chat.ts handles subtaskStatus event from Tauri - TS: streamStore.ts wires callback, maps backend→frontend status, updates assistant message subtasks array in real-time	2026-04-06 13:05:37 +08:00
iven	15a1849255	feat: auto-create artifacts from file_write tool output ... When the agent writes files via the file_write tool, artifacts are now automatically created in the artifact panel. The file extension determines the artifact type (code/markdown/text) and syntax highlighting language. This connects the existing ArtifactPanel UI to actual tool output data.	2026-04-06 12:50:48 +08:00
iven	cb140b5151	feat: DeerFlow 2.0 core capabilities — Phase 1.0 + 1.1 ... Phase 1.0 — Butler Mode UI: - Hide "自动化" and "技能市场" entries from sidebar navigation - Remove AutomationPanel and SkillMarket view rendering from App.tsx - Simplify MainViewType to only 'chat' - Main interface is now: chat + conversation list + detail panel only Phase 1.1 — Mode Differentiation: - Add subagent_enabled field to ChatModeConfig (Rust), StreamChatRequest (Tauri), gateway-client, kernel-client, saas-relay-client, and streamStore - TaskTool is now only registered when subagent_enabled=true (Ultra mode) - System prompt includes sub-agent delegation instructions only in Ultra mode - Frontend transmits subagent_enabled from ChatMode config through the full stack This connects the 4-tier mode selector (Flash/Thinking/Pro/Ultra) to actual backend behavioral differences — Ultra mode now truly enables sub-agent delegation.	2026-04-06 12:46:43 +08:00
iven	828be3cc9e	fix: resolve 6 remaining defects (P2-18, P2-21, P3-04, P3-05, P3-06, P3-02) ... - P2-18: TOTP QR code local generation via qrcode lib (no external service) - P2-21: Suspend foreign LLM providers (OpenAI/Anthropic/Gemini) for early stage - P3-04: get_progress() now calculates actual percentage from completed/total steps - P3-05: saveSaaSSession calls now have .catch() error logging - P3-06: SaaS relay chatStream passes session_key/agent_id to backend - P3-02: Whiteboard unification plan document created Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-06 09:52:28 +08:00
iven	26a833d1c8	fix: resolve 17 P2 defects and 5 P3 defects from pre-launch audit ... Batch fix covering multiple modules: - P2-01: HandRegistry Semaphore-based max_concurrent enforcement - P2-03: Populate toolCount/metricCount from Hand trait methods - P2-06: heartbeat_update_config minimum interval validation - P2-07: ReflectionResult used_fallback marker for rule-based fallback - P2-08/09: identity_propose_change parameter naming consistency - P2-10: ClassroomMetadata is_placeholder flag for LLM failure - P2-11: classroomStore userDidCloseDuringGeneration intent tracking - P2-12: workflowStore pipeline_create sends actionType - P2-13/14: PipelineInfo step_count + PipelineStepInfo for proper step mapping - P2-15: Pipe transform support in context.resolve (8 transforms) - P2-16: Mustache {{...}} → \${...} auto-normalization - P2-17: SaaSLogin password placeholder 6→8 - P2-19: serialize_skill_md + update_skill preserve tools field - P2-22: ToolOutputGuard sensitive patterns from warn→block - P2-23: Mutex::unwrap() → unwrap_or_else in relay/service.rs - P3-01/03/07/08/09: Various P3 fixes - DEFECT_LIST.md: comprehensive status sync (43/51 fixed, 8 remaining) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-06 00:49:16 +08:00
iven	9ee89ff67c	fix(desktop): 功能验证 6 项缺陷修复 ... - ISS-002: SkillInfoResponse 增加 source/path 字段，修复技能系统显示 0 个 - ISS-003: Sidebar 添加自动化/技能市场导航入口 + App 返回按钮 - ISS-004: SaaS fetchAvailableModels 添加 .catch() 防限流崩溃 - ISS-006: SaaSSettings/PricingPage 包裹 ErrorBoundary 防白屏 - ISS-008: listModels 加载 localStorage 自定义模型，修复仅显示 1 个模型 - configStore listSkills 映射添加 source/path 转发	2026-04-05 16:12:06 +08:00
iven	af0acff2aa	fix(desktop): QA 驱动的 6 项缺陷修复 ... P0-C1: SecureStorage 解密失败上限 — 添加 per-key 失败计数器， 超过 2 次自动清除过期加密数据，阻断无限重试循环 P0-C2: Bootstrap 空指针防护 — connectionStore 中 relayModels[0]?.id 添加 null guard，抛出用户友好错误 P1-H1: 侧边栏对话列表去重 — ConversationList 添加按 ID 去重逻辑， 保留最新版本后按 updatedAt 排序 P1-H2: 搜索框过滤生效 — Sidebar 传递 searchQuery 给 ConversationList， 支持按标题和消息内容过滤 P1-H3: 模型选择器 fallback — 当 SaaS 和 config 均无模型时， 提供 6 个默认模型（GLM/GPT/DeepSeek/Qwen/Claude） P1-H4: 详情面板错误友好化 — RightPanel 中 JS 错误替换为 '连接状态获取失败，请重新连接' Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-05 07:57:53 +08:00
iven	3b0ab1a7b7	fix(types): Desktop type safety hardening (TYPE-01) ... - Unify ConnectionState: kernel-types.ts now canonical source with 'handshaking', gateway-types.ts re-exports - PromptTemplateInfo source/status → union literals - PromptVariable.type → union literal - CreateRoleRequest id/permissions → optional - PropertyPanel: replace 13 as any with typed accessor pattern - chatStore: window cast via as unknown as Record	2026-04-05 01:30:29 +08:00