308 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
iven	985644dd9a	fix(memory): FTS5 full-text search + browser hand autonomy gate ... M4-05: Replace LIKE-only search with FTS5-first strategy: - Add memories_fts virtual table (unicode61 tokenizer) - FTS5 MATCH primary path with CJK LIKE fallback - Sync FTS index on store() M3-03: Add autonomy approval check to browserHandStore: - executeTemplate: check canAutoExecute before running - executeScript: check approval gate for JS execution	2026-04-04 18:52:02 +08:00
iven	59f660b93b	fix(hands): add max_concurrent + timeout_secs fields + hand timeout enforcement ... M3-04/M3-05 audit fixes: - HandConfig: add max_concurrent (u32) and timeout_secs (u64) with serde defaults - Kernel execute_hand: enforce timeout via tokio::time::timeout, cancel on expiry - All 9 hand implementations: add max_concurrent: 0, timeout_secs: 0 - Agent createClone: pass soul field through to kernel - Fix duplicate soul block in agent_create command	2026-04-04 18:41:15 +08:00
iven	a644988ca3	fix(desktop): ConfigMigrationWizard PUT 使用 config item ID 替代布尔值 ... M7-02: exists 是 boolean，不能用作 URL 路径参数。 改为使用 saasConfigs.find() 获取完整对象， 用 existing.id 作为 PUT 路径参数。	2026-04-04 18:27:31 +08:00
iven	6d1f2d108a	fix(audit): P1 心跳自启动 + refreshToken body + 类型修复 ... 审计修复 Batch 2 (M4-03/M7-04/M11-01): M4-03: 心跳引擎自动启动 - chat.rs auto-init 块: engine 创建后立即 start() - 通过 engines.get() 获取引用避免 move 后使用 M7-04: refreshToken 发送 body 修复 - SaaSClient 新增 refreshTokenValue 存储 refresh_token - refreshToken() 发送 { refresh_token } body - SaaSRefreshResponse 新增 refresh_token 字段 - login/register 自动存储 refresh_token - 添加 getRefreshToken/setRefreshToken 访问器 M11-01: blocking_lock 死锁修复 (已存在) - 确认 try_lock + Result 匹配模式已正确	2026-04-04 18:26:10 +08:00
iven	05762261be	fix(audit): P0 反思引擎 LLM 接入 + P1 hand run_id/skill triggers/pipeline v2 ... 审计修复 Batch 1 (M4-02/M3-01/M5-01/M6-02): P0 M4-02: reflection_reflect 从 KernelState 获取 LLM driver - 新增 kernel_state 参数，从 kernel.driver() 获取驱动 - 自动路径(post_conversation_hook)已正常，手动 Tauri 命令路径已修复 P1 M3-01: hand_execute 返回 run_id 给前端 - HandResult 新增 run_id 字段 - execute_hand 结果包含 run_id.to_string() P1 M5-01: skill-discovery 使用后端 triggers 字段 - BackendSkillInfo 新增 triggers 字段 - convertFromBackend 优先使用 triggers，fallback tags P1 M6-02: pipeline_list 支持 v2 YAML 格式 - scan_pipelines_with_paths 增加 v2 fallback 解析 - 新增 pipeline_v2_to_info 转换函数 - discovery.rs 导入 parse_pipeline_v2_yaml 注: M4-01 双数据库问题已在之前批次修复 M6-01 route_intent 已确认注册，审计结论过时	2026-04-04 18:11:21 +08:00
iven	442ec0eeef	docs(audit): V12 模块化端到端审计报告 — 11 模块 + 总报告 ... 混合矩阵式审计：10 个功能模块 × 五维检查清单 - 项目整体健康度: 76/100 - 2 个 P0 (M4 双数据库 + 反思引擎 LLM 未接入) - 15 个 P1 (跨 M2/M3/M4/M5/M6/M7/M11) - 三类断链模式: 写了没接/接了不对/双实现未统一 - 三阶段修复路线图: P0(2-3天) → P1(5-7天) → P2(5-7天)	2026-04-04 17:55:03 +08:00
iven	e90eb5df60	feat: Sprint 3 — benchmark + conversion funnel + invoice PDF ... - 3.1: Add criterion benchmark for zclaw-growth TF-IDF retrieval (indexing throughput, query scoring latency, top-K retrieval) - 3.2: Extend admin-v2 Usage page with recharts funnel chart (registration → trial → paid conversion) and daily trend bar chart - 3.3: Add invoice PDF export via genpdf (Arial font, Windows) with GET /api/v1/billing/invoices/{id}/pdf handler Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-04 14:42:29 +08:00
iven	a6902c28f5	: ChatArea TS2322 workaround + SubscriptionPanel component ... The ChatArea.tsx toolSteps/subtasks rendering uses helper functions to avoid TypeScript strict mode && chain producing unknown type in JSX children. Add SubscriptionPanel component for subscription status display in SaaS billing section.	2026-04-04 13:39:11 +08:00
iven	9f8b0ba375	fix(desktop): fix ChatArea TSx type narrowing for toolSteps and subtasks ... unknown→ unknown ReactNode error	2026-04-04 12:39:45 +08:00
iven	5c48d62f7e	fix(saas): harden model group failover + relay reliability ... - cache: insert-then-retain pattern avoids empty-window race during refresh - relay: manage_task_status flag for proper failover state transitions - relay: retry_task re-resolves model groups instead of blind provider reuse - relay: filter empty-member groups from available models list - relay: quota cache stale entry cleanup (TTL 5x expiry) - error: from_sqlx_unique helper for 409 vs 500 distinction - model_config: unique constraint handling, duplicate member check - model_config: failover_strategy whitelist, model_id vs group name conflict check - model_config: group-scoped member removal with group_id validation Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-04 12:26:55 +08:00
iven	894c0d7b15	feat(desktop): pipeline result preview + industry templates + onboarding auto-trigger ... Sprint 2: 产品体验打磨 + 行业模板 - Create PipelineResultPreview component with tab-based output switching - Connect workflow/hand messages to PresentationContainer in ChatArea - Add auto-trigger first Hand after onboarding (industry-specific queries) - Seed 3 industry agent templates (education, healthcare, design-shantou) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-04 10:48:47 +08:00
iven	eac1d9449e	feat(desktop): add billing frontend — plans, subscription, payment flow ... Sprint 1: Desktop 计费闭环 - Add 7 billing types to saas-types.ts (BillingPlan, Subscription, UsageQuota, etc.) - Add 6 billing API methods to saas-billing.ts (listPlans, getSubscription, createPayment, etc.) - Extend saas-client.ts with interface merging for billing methods - Extend saasStore with billing state/actions (plans, subscription, payment polling) - Create PricingPage component with plan cards, usage bars, and checkout modal - Add billing page entry in SettingsLayout (CreditCard icon + route) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-04 10:48:33 +08:00
iven	be0a78a523	feat(saas): add model groups for cross-provider failover ... Model Groups provide logical model names that map to multiple physical models across providers, with automatic failover when one provider's key pool is exhausted. Backend: - New model_groups + model_group_members tables with FK constraints - Full CRUD API (7 endpoints) with admin-only write permissions - Cache layer: DashMap-backed CachedModelGroup with load_from_db - Relay integration: ModelResolution enum for Direct/Group routing - Cross-provider failover: sort_candidates_by_quota + OnceLock cache - Relay failure path: record failure usage + relay_dequeue (fixes queue counter leak that caused connection pool exhaustion) - add_group_member: validate model_id exists before insert Frontend: - saas-relay-client: accept getModel() callback for dynamic model selection - connectionStore: prefer conversationStore.currentModel over first available Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-04 09:56:21 +08:00
iven	9af7b0dd46	fix(kernel): enable multi-agent compilation + A2A routing tests ... - director.rs: add missing CompletionRequest fields (thinking_enabled, reasoning_effort, plan_mode) for multi-agent feature gate - agents.rs: remove unused AgentState import behind multi-agent feature - lib.rs: replace ambiguous glob re-export with explicit director types, resolving AgentRole conflict between director and generation modules - a2a.rs: add 5 integration tests covering direct message delivery, broadcast routing, group messaging, agent unregistration, and expired message rejection (10 total A2A tests, all passing) - Verified: 537 workspace tests pass with multi-agent feature enabled Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-04 09:41:24 +08:00
iven	f4ed1b33e0	feat(kernel): add multi-skill orchestration bridge + true parallel execution ... - Kernel orchestration bridge: execute_orchestration, auto_compose_skills, validate_orchestration methods on Kernel struct - True parallel execution: replace sequential for-loop with tokio::JoinSet for concurrent node execution within parallel groups - Tauri commands: orchestration_execute (auto-compose or pre-defined graph), orchestration_validate (dry-run validation) - Full type conversions: OrchestrationRequest/Response with camelCase serde Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-04 09:18:26 +08:00
iven	1399054547	feat(skills): add LLM fallback routing + CJK TF-IDF bigram fix ... - SemanticSkillRouter: add RuntimeLlmIntent trait and with_llm_fallback() builder - route(): call LLM fallback when TF-IDF/embedding confidence < threshold - CJK tokenization: generate bigrams for Chinese/Japanese/Korean text - Fix: previous tokenizer treated entire CJK string as one huge token - SemanticSkillRouter: add RuntimeLlmIntent trait and with_llm_fallback() builder - route(): call LLM fallback when TF-IDF/embedding confidence < threshold - CJK tokenization: generate bigrams for Chinese/Japanese/Korean text - Fix: previous tokenizer treated entire CJK string as one huge token - LlmSkillFallback: concrete RuntimeLlmIntent using LlmDriver - Asks LLM to pick best skill from ambiguous candidates list - Parses structured JSON response from LLM output - Includes tests for LLM fallback and CJK tokenization Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-04 07:44:42 +08:00
iven	769bfdf5d6	fix(desktop): 修复 10 个 agent 对话测试发现的缺陷 ... - BUG-001+002 P0: 模型选择器合并 SaaS 可用模型列表 - BUG-003 P1: 修复 relay 错误消息重复显示 - BUG-005 P1: 设置页面显示实际连接模式和地址 - BUG-006 P2: 统一 UI 语言为中文 - BUG-009 P3: 错误时隐藏建议按钮 - BUG-010 P3: 密码切换按钮添加 aria-label Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-04 01:31:28 +08:00
iven	912f117ea3	feat(desktop): wire MCP client to settings UI ... - MCPServices.tsx now calls real Tauri commands (start/stop/list) instead of only toggling config flags - Show running service count, discovered tools per service - Expand/collapse tool list for each running MCP service - Extended QuickConfig mcpServices type with command/args/env/cwd - Config change persists enabled state, MCP start/stop happens live	2026-04-04 01:30:13 +08:00
iven	0be31bbf7e	feat(memory): add message pagination support ... - get_messages_paginated(session_id, limit, offset) for batch loading - count_messages(session_id) for total count queries - Enables frontend to load messages progressively instead of all-at-once	2026-04-04 01:22:03 +08:00
iven	b25dfc967a	feat(kernel): persist agent runtime state across restarts ... - Schema: migrations now execute ALTER TABLE ADD COLUMN for state/message_count - MemoryStore: add update_agent_runtime() and list_agents_with_runtime() - Registry: add register_with_runtime() to accept persisted state/message_count - Kernel boot: restore agents with their persisted state (not always Running) - Kernel shutdown: persist all agent states/message_counts before terminating Agents that were suspended stay suspended after restart. Message counts survive restarts instead of resetting to 0.	2026-04-04 01:19:53 +08:00
iven	b4e5af7a58	feat(growth): add memory decay + time-weighted scoring + remove dead frontend ... - Add effective_importance() with exponential time decay (30-day half-life) and access count boost for fair scoring of stale vs fresh memories - Add SqliteStorage::decay_memories() for periodic maintenance: reduces stored importance per interval, archives (deletes) below threshold - Update find() scoring to use time-decayed importance in sort - Add DecayResult type and effective_importance re-export in lib.rs - Remove dead frontend active-learning.ts (370 lines, zero imports)	2026-04-04 00:45:16 +08:00
iven	276ec3ca94	chore(desktop): remove dead active-learning frontend code ... Zero imports across codebase — never wired to any UI or Tauri command. Rust Growth crate handles memory/summary generation instead.	2026-04-04 00:38:13 +08:00
iven	8faefd6a61	fix(tests): resolve workspace compilation + CJK search failures ... - saas test harness: align WorkerDispatcher::new and AppState::new signatures with SpawnLimiter addition and init_db(&DatabaseConfig) - growth sqlite: add CJK fallback (LIKE-based) when FTS5 unicode61 tokenizer fails on Chinese queries (unicode61 doesn't index CJK)	2026-04-04 00:34:34 +08:00
iven	5db2907420	test(desktop): add agent-chat comprehensive E2E test spec ... Full E2E test suite for agent chat functionality including: - Message send/receive flow - Streaming response verification - Model switching behavior - Error handling scenarios - Multi-turn conversation context Includes test report documenting coverage and known gaps.	2026-04-03 23:02:00 +08:00
iven	5eeabd1f30	feat(saas): add webhook event notification system (@unplugged) ... Webhook infrastructure for external event notifications: - SQL migration: webhook_subscriptions + webhook_deliveries tables - Types: CreateWebhookRequest, UpdateWebhookRequest, WebhookDelivery - Service: CRUD operations + trigger_webhooks + HMAC-SHA256 signing - Handlers: REST API endpoints (CRUD + delivery logs) - Worker: WebhookDeliveryWorker with exponential retry (max 3) NOT YET INTEGRATED: needs mod registration in lib.rs + workers/mod.rs, hmac crate dependency, and route mounting. Code is ready for future integration after stabilization phase completes.	2026-04-03 23:01:49 +08:00
iven	1c99e5f3a3	fix(browser): stability enhancements + MCP frontend client ... S7 Browser Hand: - Remove dead code: browser/actions.rs (314 lines of unused BrowserAction/ActionResult types) - Fix browser_scrape_page: log failed selector matches instead of silently swallowing errors - Fix element_to_info: document known limitation for always-None location/size fields - Fix browserHandStore: reuse activeSessionId in executeScript/takeScreenshot/executeTemplate instead of creating orphan Browser sessions - Add Browser.connect(sessionId) method for session reuse MCP Frontend: - Add desktop/src/lib/mcp-client.ts (77 lines) — typed client for MCP Tauri commands (startMcpService, stopMcpService, listMcpServices, callMcpTool) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-03 22:16:12 +08:00
iven	943afe3b6b	feat(protocols): MCP tool adapter + Tauri commands + initialize bug fix ... S6 MCP Protocol: - Fix McpTransport::initialize() — store actual server capabilities instead of discarding them and storing empty ServerCapabilities::default() - Add send_notification() method to McpTransport for JSON-RPC notifications - Send notifications/initialized after MCP handshake (spec requirement) - Add McpToolAdapter: bridges MCP server tools into the tool execution path - Add McpServiceManager: lifecycle management for MCP server connections - Add 4 Tauri commands: mcp_start_service, mcp_stop_service, mcp_list_services, mcp_call_tool - Register zclaw-protocols dependency in desktop Cargo.toml New files: - crates/zclaw-protocols/src/mcp_tool_adapter.rs (153 lines) - desktop/src-tauri/src/kernel_commands/mcp.rs (145 lines) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-03 22:07:35 +08:00
iven	cc26797faf	fix(saas): eliminate 6 compiler warnings + stabilize directive complete ... - Remove unused imports: Utc (billing/service), StatusCode (billing/handlers), Sha256 (billing/handlers) - Fix unused variables: _db (scheduler), _e (payment WeChat error) - Fix visibility: RegisterDeviceRequest pub(super) → pub (used in pub handler) - Update STABILIZATION_DIRECTIVE.md: all 7 criteria met, downgrade to advisory - Fix TRUTH.md §2.2: mark P0/P1 defects as resolved, update Admin pages count to 14 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-03 21:57:04 +08:00
iven	264dc75b2c	fix(production-readiness): audit fixes — duplicate useState + route mismatch + stale @reserved ... - ChatArea.tsx: remove duplicate useState(searchOpen) declaration on line 70 - scheduled_task/mod.rs: fix route from /api/scheduler/tasks to /api/v1/scheduler/tasks (matches admin-v2 service baseURL pattern and all other modules) - scheduled_task/handlers.rs: remove @reserved annotations (now has Admin V2 frontend) - scheduled_task/handlers.rs: update doc comments with correct /api/v1/ paths	2026-04-03 21:41:30 +08:00
iven	4281ce35b4	fix(saas): remove hardcoded model fallback — dynamic from available models ... - service.rs: template model passed as-is (Option<String>), no hardcoded fallback - saas-types.ts: AgentConfigFromTemplate.model → string | null - agentStore.ts: when model is null, resolve from saasStore.availableModels[0] - AgentOnboardingWizard.tsx: restore full file (was corrupted), apply assignTemplate try/catch fix	2026-04-03 21:38:15 +08:00
iven	2ceeeaba3d	fix(production-readiness): 3-batch production readiness cleanup — 12 tasks ... Batch 1 — User-facing fixes: - B1-1: Pipeline verified end-to-end (14 Rust commands, 8 frontend invoke, fully connected) - B1-2: MessageSearch restored to ChatArea with search button in DeerFlow header - B1-3: Viking cleanup — removed 5 orphan invokes (no Rust impl), added addWithMetadata + storeWithSummaries methods + summary generation UI - B1-4: api-fallbacks transparency — added _isFallback markers + console.warn to all 6 fallback functions Batch 2 — System health: - B2-1: Document drift calibration — TRUTH.md/README.md numbers verified and updated - B2-2: @reserved annotations on 15 SaaS handler functions with no frontend callers - B2-3: Scheduled Task Admin V2 — new service + page + route + sidebar navigation - B2-4: TRUTH.md Pipeline/Viking/ScheduledTask records corrected Batch 3 — Long-term quality: - B3-1: hand_run_status/hand_run_list verified as fully implemented (not stubs) - B3-2: Identity snapshot rollback UI added to RightPanel - B3-3: P2 code quality — 4 fixes (TODO comments, fire-and-forget notes, design notes, table name validation), 2 verified N/A, 1 upstream - B3-4: Config PATCH→PUT alignment (admin-v2 config.ts matched to SaaS backend)	2026-04-03 21:34:56 +08:00
iven	305984c982	fix(saas): P2 code quality fixes + config PATCH/PUT alignment ... P2 code quality (SEC2-P2-01~10): - P2-04: Replace vague TODO with detailed Phase 2 design note in generate_embedding.rs - P2-05: Add NOTE(fire-and-forget) annotations to 4 long-running tokio::spawn in main.rs - P2-07: Add DESIGN NOTE to scheduler explaining sequential execution rationale - P2-08: Add compile-time table name whitelist + runtime char validation in db.rs - P2-02: Verified N/A (only zclaw-pipeline uses serde_yaml_bw, no inconsistency) - P2-06: Verified N/A (bind loop correctly matches 6-column placeholders) - P2-03: Remains OPEN (requires upstream sqlx release) Config HTTP method alignment (B3-4): - Fix admin-v2 config.ts: request.patch -> request.put to match backend .put() route - Fix backend handler doc comment: PATCH -> PUT - Add @reserved annotations to 6 config handlers without frontend callers	2026-04-03 21:32:17 +08:00
iven	22b967d2a6	docs(features): v0.10.1/v0.10.2 数字校准 + 行业模板文档更新 ... - README.md: SKILL 76→75, Tauri 命令 175→171, SaaS API 58→131, Workers 5→7, 数据表 25→34, Admin 11→13 页面 - 00-saas-overview.md: Agent Template 新增 5 个端点文档、种子数据表、端到端数据流图 - roadmap.md: 同步最新数字 - fix(saasStore): toTopRequired → totpRequired 拼写修复	2026-04-03 21:29:44 +08:00
iven	edecd4c81f	fix(saas): deep audit round industry template system - critical fixes ... C1: Use backend createAgentFromTemplate API + tools forwarding C3: seed source='builtin' instead of 'custom' C4: immutable clone data handling (return fresh from store) + spread) H3: assignTemplate error propagation (try/catch) H4: input validation for name/fields H5: assign_template account existence check H6: remove dead route get_full_template H7: model fallback gpt-4o-mini (hardcoded constant) H8: logout clears template state H9: console.warn -> structured logger C2: restoreSession fetches assignedTemplate	2026-04-03 19:45:25 +08:00
iven	0857a1f608	feat(desktop): wire template welcome_message + quick_commands to chat UI ... - Add welcomeMessage/quickCommands fields to Clone interface - Persist template welcome/quick data via updateClone after creation - FirstConversationPrompt: prefer template-provided welcome message over dynamically generated one - FirstConversationPrompt: render template quick_commands as chips instead of hardcoded QUICK_ACTIONS when available - Tighten assign/unassign template endpoint permissions from model:read to relay:use (self-service operation for all authenticated users)	2026-04-03 15:20:15 +08:00
iven	1048901665	fix(saas): industry template audit fixes + pgvector optional + relay timeout ... - Fix seed template tools to match actual runtime tool names (file_read/file_write/shell_exec/web_fetch) - Persist system_prompt/temperature/max_tokens via identity system in agentStore.createFromTemplate() - Fire-and-forget assignTemplate() in AgentOnboardingWizard - Fix saas-relay-client unused variable warning - Make pgvector extension optional in knowledge_base migration - Increase StreamBridge timeout from 30s to 90s for thinking models	2026-04-03 15:10:13 +08:00
iven	ea00c32c08	feat(saas): industry agent template assignment system ... Phase 1-8 of industry-agent-delivery plan: - DB migration: accounts.assigned_template_id (ON DELETE SET NULL) - SaaS API: 4 new endpoints (assign/get/unassign/create-agent) - Service layer: assign_template_to_account, get_assigned_template, unassign_template, create_agent_from_template) - Types: AssignTemplateRequest, AgentConfigFromTemplate (capabilities merged into tools) - Frontend SaaS Client: assignTemplate, getAssignedTemplate, unassignTemplate, createAgentFromTemplate - saasStore: assignedTemplate state + login auto-fetch + actions - saas-relay-client: fix unused import and saasUrl reference error - connectionStore: fix relayModel undefined error - capabilities default to glm-4-flash - Route registration: new template assignment routes Cospec and handlers consolidated Build: cargo check --workspace PASS, tsc --noEmit Pass	2026-04-03 13:31:58 +08:00
iven	5b1b747810	fix(desktop): prevent transformCallback crash in browser mode ... Root cause: ChatArea.tsx called listen() from @tauri-apps/api/event directly on component mount without checking isTauriRuntime(). When accessed from a regular browser (not Tauri WebView), window.__TAURI_INTERNALS__ is undefined, causing "Cannot read properties of undefined (reading 'transformCallback')". Solution: - Created lib/safe-tauri.ts with safe wrappers (safeInvoke, safeListen, safeListenEvent, requireInvoke) that gracefully degrade when Tauri IPC is unavailable - Replaced direct listen() call in ChatArea.tsx with safeListenEvent()	2026-04-03 13:00:36 +08:00
iven	564c7ca28f	fix(desktop): guard invoke calls with isTauriRuntime check ... Step 5 (embedding config) and Step 5b (summary driver) in App.tsx bootstrap called invoke() without checking if Tauri IPC is available. When accessing http://localhost:1420/ in a regular browser, this caused "Cannot read properties of undefined (reading 'transformCallback')". Also added __TAURI_INTERNALS__ guard in saasStore kernel config sync.	2026-04-03 12:46:14 +08:00
iven	65b73c547f	fix(desktop): resolve Tauri state panic on startup ... SessionStreamGuard and StreamCancelFlags were type aliases to the same Arc<DashMap<String, Arc<AtomicBool>>> type. Tauri distinguishes managed state by Rust type, so registering both caused a runtime panic: "state for type ... is already being managed". Changed to newtype structs with Deref impl to the inner Arc<DashMap>, keeping all call sites compatible without changes.	2026-04-03 12:29:10 +08:00
iven	54764a8bbd	docs: enforce commit-push-after-comeliminate-work as mandatory step ... CLAUDE.md §3.3 闭环工作法: 代码通过→提交→推送→文档同步 三步必须按顺序执行，不允许跳过 CLAUDE.md |8.3 收尾流程: 按步骤 A/B/C/D 强制执行	2026-04-03 00:54:14 +08:00
iven	1c697d0b46	chore: 清理临时管理目录并更新文档索引 ... 删除 admin-temp-dir 目录及其内容 更新文档索引以包含 dashmap 相关文件	2026-04-03 00:42:48 +08:00
iven	5a5a4b322d	docs: update CLAUDE.md with stabilization rules, security audit, and production checklist	2026-04-03 00:29:21 +08:00
iven	d8e2954d73	docs: stabilization directive + TRUTH document + AI session prompts + dockerignore ... - STABILIZATION_DIRECTIVE.md: feature freeze rules, banned actions, priorities - TRUTH.md: single source of truth for system state (crate counts, store counts) - AI_SESSION_PROMPTS.md: three-layer prompt system for AI sessions - Industry agent delivery design spec - Stabilization test suite for regression prevention - Delete stale ISSUE-TRACKER.md - Add .dockerignore for container builds - Add brainstorm session artifacts	2026-04-03 00:29:16 +08:00
iven	5c74e74f2a	fix(desktop): component cleanup + dead code removal + DeerFlow ai-elements ... - ChatArea: DeerFlow ai-elements annotations for accessibility - Conversation: remove unused Context, simplify message rendering - Delete dead modules: audit-logger.ts, gateway-reconnect.ts - Replace console.log with structured logger across components - Add idb dependency for IndexedDB persistence - Fix kernel-skills type safety improvements	2026-04-03 00:28:58 +08:00
iven	15d578c5bc	fix(tauri): replace silent let _ = with structured logging across 20 modules ... Replace error-swallowing let _ = patterns with tracing::warn! in browser, classroom, gateway, intelligence, memory, pipeline, secure_storage, and viking command handlers. Ensures errors are observable in production logs.	2026-04-03 00:28:39 +08:00
iven	52bdafa633	refactor(crates): kernel/generation module split + DeerFlow optimizations + middleware + dead code cleanup ... - Split zclaw-kernel/kernel.rs (1486 lines) into 9 domain modules - Split zclaw-kernel/generation.rs (1080 lines) into 3 modules - Add DeerFlow-inspired middleware: DanglingTool, SubagentLimit, ToolError, ToolOutputGuard - Add PromptBuilder for structured system prompt assembly - Add FactStore (zclaw-memory) for persistent fact extraction - Add task builtin tool for agent task management - Driver improvements: Anthropic/OpenAI extended thinking, Gemini safety settings - Replace let _ = with proper log::warn! across SaaS handlers - Remove unused dependency (url) from zclaw-hands	2026-04-03 00:28:03 +08:00
iven	0a04b260a4	refactor(desktop): ChatStore structured split + IDB persistence + stream cancel ... Split monolithic chatStore.ts (908 lines) into 4 focused stores: - chatStore.ts: facade layer, owns messages[], backward-compatible selectors - conversationStore.ts: conversation CRUD, agent switching, IndexedDB persistence - streamStore.ts: streaming orchestration, chat mode, suggestions - messageStore.ts: token tracking Key fixes from 3-round deep audit: - C1: Fix Rust serde camelCase vs TS snake_case mismatch (toolStart/toolEnd/iterationStart) - C2: Fix IDB async rehydration race with persist.hasHydrated() subscribe - C3: Add sessionKey to partialize to survive page refresh - H3: Fix IDB migration retry on failure (don't set migrated=true in catch) - M3: Fix ToolCallStep deduplication (toolStart creates, toolEnd updates) - M-NEW-2: Clear sessionKey on cancelStream Also adds: - Rust backend stream cancellation via AtomicBool + cancel_stream command - IndexedDB storage adapter with one-time localStorage migration - HMR cleanup for cross-store subscriptions	2026-04-03 00:24:16 +08:00
iven	da438ad868	fix(billing): resolve all audit findings — CSRF, float precision, TOCTOU, error sanitization ... - Add CSRF token protection for mock payment (SHA256 + constant-time verify) - Replace f64 currency conversion with pure integer string parsing (parse_yuan_to_cents) - Move subscription check inside transaction to prevent TOCTOU race - Rewrite increment_usage to use atomic SQL (account_id+period_start WHERE) - Add trade_no format validation in payment callback - Sanitize error messages to prevent sensitive data leakage - Use i32::try_from for WeChat amount conversion (prevent truncation) - Replace window.__ZCLAW_STATS_SYNC_INTERVAL__ with useRef pattern - Replace eprintln/println with tracing macros in lifecycle - Remove unused variable in scheduler - Remove duplicate sha2 and unused hmac from Cargo.toml	2026-04-02 20:04:43 +08:00
iven	8898bb399e	docs: audit reports + feature docs + skills + admin-v2 + config sync ... Update audit tracker, roadmap, architecture docs, add admin-v2 Roles page + Billing tests, sync CLAUDE.md, Cargo.toml, docker-compose.yml, add deep-research / frontend-design / chart-visualization skills Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-04-02 19:25:00 +08:00