Commit Graph

75 Commits

Author SHA1 Message Date
iven
a389082dd4 fix(llm-service): 在内核模式下使用 Tauri invoke 而非 HTTP 端点
Some checks failed
CI / Lint & TypeCheck (push) Has been cancelled
CI / Unit Tests (push) Has been cancelled
CI / Build Frontend (push) Has been cancelled
CI / Rust Check (push) Has been cancelled
CI / Security Scan (push) Has been cancelled
CI / E2E Tests (push) Has been cancelled
问题:记忆系统尝试调用 /api/agents/default/message 导致 ECONNREFUSED
根因:GatewayLLMAdapter 在内核模式下仍使用外部 OpenFang HTTP 端点

修复:检测 Tauri 运行时,使用 agent_chat Tauri 命令代替 HTTP 请求

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-23 23:59:50 +08:00
iven
cbd3da46a3 chore: remove debug logging
Some checks failed
CI / Lint & TypeCheck (push) Has been cancelled
CI / Unit Tests (push) Has been cancelled
CI / Build Frontend (push) Has been cancelled
CI / Rust Check (push) Has been cancelled
CI / Security Scan (push) Has been cancelled
CI / E2E Tests (push) Has been cancelled
Remove temporary console.log and eprintln! statements added during
troubleshooting the model configuration issue.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-23 23:06:20 +08:00
iven
ae4bf815e3 fix(kernel): 使用 Kernel 配置的 model 而非 Agent 持久化的旧值
Some checks failed
CI / Lint & TypeCheck (push) Has been cancelled
CI / Unit Tests (push) Has been cancelled
CI / Build Frontend (push) Has been cancelled
CI / Rust Check (push) Has been cancelled
CI / Security Scan (push) Has been cancelled
CI / E2E Tests (push) Has been cancelled
问题:在"模型与 API"页面切换模型后,对话仍使用旧模型
根因:Agent 配置从数据库恢复,其 model 字段优先于 Kernel 配置

修复:
- kernel.rs: send_message/send_message_stream 始终使用 Kernel 的当前 model
- openai.rs: 添加 User-Agent header 解决 Coding Plan API 405 错误
- kernel_commands.rs: 添加详细调试日志便于追踪配置传递
- troubleshooting.md: 记录此问题的排查过程和解决方案

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-23 22:56:06 +08:00
iven
e8b9e813a6 chore: cleanup phase 5, remove external runtime dependencies 2026-03-22 09:43:01 +08:00
iven
2fb914c965 fix: UTF-8 boundary issue in compactor and remove openfang-runtime from bundle 2026-03-22 09:23:19 +08:00
iven
f9fefc1557 chore: remove openfang-runtime and update start script 2026-03-22 09:04:39 +08:00
iven
7abfca9d5c feat(kernel): add internal ZCLAW kernel integration with Tauri
Phase 1-3 of independence architecture:
- zclaw-types: Add ToolDefinition, ToolResult, KernelConfig, ModelConfig
- zclaw-kernel: Fix AgentInfo provider field, export config module
- desktop: Add kernel_commands for internal kernel access
- Add AgentId FromStr implementation for parsing

New Tauri commands:
- kernel_init, kernel_status, kernel_shutdown
- agent_create, agent_list, agent_get, agent_delete
- agent_chat

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-22 08:37:20 +08:00
iven
185763868a feat: production readiness improvements
## Error Handling
- Add GlobalErrorBoundary with error classification and recovery
- Add custom error types (SecurityError, ConnectionError, TimeoutError)
- Fix ErrorAlert component syntax errors

## Offline Mode
- Add offlineStore for offline state management
- Implement message queue with localStorage persistence
- Add exponential backoff reconnection (1s→60s)
- Add OfflineIndicator component with status display
- Queue messages when offline, auto-retry on reconnect

## Security Hardening
- Add AES-256-GCM encryption for chat history storage
- Add secure API key storage with OS keychain integration
- Add security audit logging system
- Add XSS prevention and input validation utilities
- Add rate limiting and token generation helpers

## CI/CD (Gitea Actions)
- Add .gitea/workflows/ci.yml for continuous integration
- Add .gitea/workflows/release.yml for release automation
- Support Windows Tauri build and release

## UI Components
- Add LoadingSpinner, LoadingOverlay, LoadingDots components
- Add MessageSkeleton, ConversationListSkeleton skeletons
- Add EmptyMessages, EmptyConversations empty states
- Integrate loading states in ChatArea and ConversationList

## E2E Tests
- Fix WebSocket mock for streaming response tests
- Fix approval endpoint route matching
- Add store state exposure for testing
- All 19 core-features tests now passing

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-22 00:03:22 +08:00
iven
ce562e8bfc feat: complete Phase 1-3 architecture optimization
Phase 1 - Security:
- Add AES-GCM encryption for localStorage fallback
- Enforce WSS protocol for non-localhost WebSocket connections
- Add URL sanitization to prevent XSS in markdown links

Phase 2 - Domain Reorganization:
- Create Intelligence Domain with Valtio store and caching
- Add unified intelligence-client for Rust backend integration
- Migrate from legacy agent-memory, heartbeat, reflection modules

Phase 3 - Core Optimization:
- Add virtual scrolling for ChatArea with react-window
- Implement LRU cache with TTL for intelligence operations
- Add message virtualization utilities

Additional:
- Add OpenFang compatibility test suite
- Update E2E test fixtures
- Add audit logging infrastructure
- Update project documentation and plans

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 22:11:50 +08:00
iven
a65b3d3958 feat(chat): add virtual scrolling for large message lists
- Integrate react-window v2 List component for messages > 100
- Add VirtualizedMessageList and VirtualizedMessageRow components
- Use useVirtualizedMessages hook for dynamic height measurement
- Preserve smooth animations for small message counts (< 100)
- Auto-scroll to bottom for both virtualized and non-virtualized modes

Performance improvements:
- Only render visible messages in viewport
- Dynamic height measurement for accurate positioning
- LRU cache for message content

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 20:43:07 +08:00
iven
32b9b41144 feat(domains): add Intelligence Domain with Valtio store and caching
- Create types.ts with frontend-friendly types
- Create cache.ts with LRU cache + TTL support
- Create store.ts wrapping intelligence-client with reactive state
- Create hooks.ts for React component integration
- Re-export backend types for compatibility

Intelligence Domain provides:
- Memory: store, search, delete with caching
- Heartbeat: init, start, stop, tick operations
- Compaction: threshold check and compact
- Reflection: conversation tracking and reflection
- Identity: load, build prompt, propose changes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 20:01:47 +08:00
iven
5513d5d8e4 fix(domains): resolve TypeScript type errors in domain hooks
- Add type assertions for Valtio snapshot readonly arrays
- Remove unused fromPromise import from hands machine
- Ensures type compatibility with Valtio's useSnapshot

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 19:52:14 +08:00
iven
7ffd5e1531 feat(domains): create domain-driven architecture for Phase 2
Chat Domain:
- Add types.ts with Message, Conversation, Agent types
- Add store.ts with Valtio-based state management
- Add hooks.ts with useChatState, useMessages, etc.
- Add index.ts for public API export

Hands Domain:
- Add types.ts with Hand, Trigger, Approval types
- Add machine.ts with XState state machine
- Add store.ts with Valtio-based state management
- Add hooks.ts with useHands, useApprovalQueue, etc.

Shared Module:
- Add types.ts with Result, AsyncResult, PaginatedResponse
- Add error-handling.ts with AppError, NetworkError, etc.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 19:47:48 +08:00
iven
20eed290f8 feat(deps): add Valtio and XState for Phase 2
- Add valtio for Proxy-based state management
- Add xstate and @xstate/react for state machines
- Create domains directory structure (chat, hands, intelligence, skills)
- Create shared directory for common utilities

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 19:43:12 +08:00
iven
32c9f93a7b feat(security): enforce WSS for non-localhost connections
- Add SecurityError class for clear error handling
- Add validateWebSocketSecurity function
- Block ws:// connections to non-localhost hosts
- Add unit tests for security validation logic

Security: Prevents man-in-the-middle attacks on remote connections
by requiring WSS protocol for all non-localhost WebSocket connections.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 17:27:56 +08:00
iven
d266a1435f feat(security): add AES-GCM encryption for localStorage fallback
- Encrypt credentials before storing in localStorage when OS keyring unavailable
- Decrypt on retrieval with automatic fallback
- Backward compatible with existing unencrypted data (migration on next set)
- Add comprehensive unit tests (11 test cases)

Security: Credentials are now encrypted using AES-GCM when
OS keyring is unavailable, preventing plaintext exposure.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 17:13:50 +08:00
iven
a199434e08 test(crypto): add generateMasterKey test coverage
- Add test for base64 string output
- Add test for 32-byte key length
- Add test for uniqueness

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 17:07:08 +08:00
iven
f070d9151e feat(crypto): add AES-GCM encryption utilities
- Add arrayToBase64/base64ToArray conversion functions
- Add deriveKey for PBKDF2 key derivation
- Add encrypt/decrypt using AES-GCM
- Add generateMasterKey for random key generation
- Update setup.ts to use real Web Crypto API instead of mock
- Add comprehensive unit tests for all crypto functions

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 17:05:15 +08:00
iven
47a84f52a2 fix(test): add @vitest/coverage-v8 dependency for coverage reports
- Add @vitest/coverage-v8@2.1.8 matching vitest version
- Required for test:coverage script to work

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 17:00:09 +08:00
iven
2c80a2c3c2 test: add Vitest configuration and setup
- Add vitest.config.ts with jsdom environment and path aliases
- Add tests/setup.ts with mocks for Tauri API, crypto, and localStorage
- Add test:coverage script to package.json

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 16:55:44 +08:00
iven
9fc17e9d36 test(desktop): add Vitest and testing dependencies
Install testing framework dependencies for unit testing:
- vitest@2.1.8 - Test runner
- @testing-library/react@16.1.0 - React component testing
- @testing-library/jest-dom@6.6.3 - Jest DOM matchers
- jsdom@25.0.1 - DOM simulation environment

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 16:50:38 +08:00
iven
f3ec3c8d4c feat(intelligence): complete migration to Rust backend
- Unify all intelligence modules to use intelligenceClient
- Delete legacy TS implementations (agent-memory, reflection-engine, heartbeat-engine, context-compactor, agent-identity, memory-index)
- Update all consumers to use snake_case backend types
- Remove deprecated llm-integration.test.ts

This eliminates code duplication between frontend and backend, resolves
localStorage limitations, and enables persistent intelligence features.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 15:17:39 +08:00
iven
17fb1e69aa feat(intelligence): add TypeScript frontend adapter for Rust commands
Provides unified API for calling Tauri intelligence commands:

- memory: store, search, get, delete, stats, export/import
- heartbeat: init, start, stop, tick, config management
- compactor: token estimation, threshold check, compact
- reflection: should_reflect, reflect, history, state
- identity: get/update files, proposals, snapshots

Usage:
```typescript
import { intelligence } from './intelligence-backend';
await intelligence.memory.store({ ... });
await intelligence.heartbeat.start('agent-1');
```

Part of Phase 4: Integration and documentation.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 00:54:31 +08:00
iven
ef8f5cdb43 feat(intelligence): complete Phase 2-3 migration to Rust
Phase 2 - Core Engines:
- Heartbeat Engine: Periodic proactive checks with quiet hours support
- Context Compactor: Token estimation and message summarization
  - CJK character handling (1.5 tokens per char)
  - Rule-based summary generation

Phase 3 - Advanced Features:
- Reflection Engine: Pattern analysis and improvement suggestions
- Agent Identity: SOUL.md/AGENTS.md/USER.md management
  - Proposal-based changes (requires user approval)
  - Snapshot history for rollback

All modules include:
- Tauri commands for frontend integration
- Unit tests
- Re-exported types via mod.rs

Reference: docs/plans/INTELLIGENCE-LAYER-MIGRATION.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 00:52:44 +08:00
iven
0db8a2822f feat(backend): implement Phase 1 of Intelligence Layer Migration
- Add SQLite-based persistent memory storage (persistent.rs)
- Create memory persistence Tauri commands (memory_commands.rs)
- Add sqlx dependency to Cargo.toml for SQLite support
- Update memory module to export new persistent types
- Register memory commands in Tauri invoke handler
- Add comprehensive migration plan document

Phase 1 delivers:
- PersistentMemory struct with SQLite storage
- MemoryStoreState for Tauri state management
- 10 memory commands: init, store, get, search, delete,
  delete_all, stats, export, import, db_path
- Full-text search capability
- Cross-session memory retention

Reference: docs/plans/INTELLIGENCE-LAYER-MIGRATION.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 00:36:06 +08:00
iven
48a430fc97 refactor(skills): add skill-adapter and refactor SkillMarket
- Add skill-adapter.ts to bridge configStore and UI skill formats
- Refactor SkillMarket to use new skill-adapter instead of skill-discovery
- Add health check state to connectionStore
- Update multiple components with improved typing
- Clean up test artifacts and add new test results
- Update README and add skill-market-mvp plan

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 00:28:03 +08:00
iven
d3a4de2480 docs: add setup guides and error notification component
- Add OpenFang Kernel configuration guide (docs/setup/OPENFANG-SETUP.md)
- Add Chinese models configuration guide (docs/setup/chinese-models.md)
- Add quick start guide (docs/quick-start.md)
- Add quick start scripts for Windows and Linux/macOS
- Add ErrorNotification component for centralized error display

These additions help users:
- Quickly set up development environment
- Configure OpenFang backend correctly
- Configure Chinese LLM providers (GLM, Qwen, Kimi, MiniMax)
- See error notifications in a consistent UI

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 00:17:44 +08:00
iven
c5d91cf9f0 feat: add integration test framework and health check improvements
- Add test helper library with assertion functions (scripts/lib/test-helpers.sh)
- Add gateway integration test script (scripts/tests/gateway-test.sh)
- Add configuration validation tool (scripts/validate-config.ts)
- Add health-check.ts library with Tauri command wrappers
- Add HealthStatusIndicator component to ConnectionStatus.tsx
- Add E2E test specs for memory, settings, and team collaboration
- Update ZCLAW-DEEP-ANALYSIS.md to reflect actual project state

Key improvements:
- Store architecture now properly documented as migrated
- Tauri backend shown as 85-90% complete
- Component integration status clarified

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-21 00:09:47 +08:00
iven
ce522de7e9 feat: integrate DevQALoop into TeamOrchestrator and add integration test checklist
- Add Review tab to TeamOrchestrator with DevQALoopPanel integration
- Create comprehensive integration test checklist (22 test cases)
- Document component integration status analysis
- Update progress documentation

Key findings:
- Most "low integration" components were actually integrated via indirect paths
- DevQALoop was the only truly unintegrated component, now fixed

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-20 23:27:16 +08:00
iven
1cf3f585d3 refactor(store): split gatewayStore into specialized domain stores
Major restructuring:
- Split monolithic gatewayStore into 5 focused stores:
  - connectionStore: WebSocket connection and gateway lifecycle
  - configStore: quickConfig, workspaceInfo, MCP services
  - agentStore: clones, usage stats, agent management
  - handStore: hands, approvals, triggers, hand runs
  - workflowStore: workflows, workflow runs, execution

- Update all components to use new stores with selector pattern
- Remove
2026-03-20 22:14:13 +08:00
iven
6f72442531 docs(guide): rewrite CLAUDE.md with ZCLAW-first perspective
Major changes:
- Shift from "OpenFang desktop client" to "independent AI Agent desktop app"
- Add decision principle: "Is this useful for ZCLAW? Does it affect ZCLAW?"
- Simplify project structure and tech stack sections
- Replace OpenClaw vs OpenFang comparison with unified backend approach
- Consolidate troubleshooting from scattered sections into organized FAQ
- Update Hands system documentation with 8 capabilities and status
- Stream
2026-03-20 19:30:09 +08:00
iven
3518fc8ece feat(automation): complete unified automation system redesign
Phase 4 completion:
- Add ApprovalQueue component for managing pending approvals
- Add ExecutionResult component for displaying hand/workflow results
- Update Sidebar navigation to use unified AutomationPanel
- Replace separate 'hands' and 'workflow' tabs with single 'automation' tab
- Fix TypeScript type safety issues with unknown types in JSX expressions

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-18 17:12:05 +08:00
iven
3a7631e035 feat(automation): implement unified automation system with Hands and Workflows
Phase 1 - Core Fixes:
- Fix parameter passing in HandsPanel (params now passed to triggerHand)
- Migrate HandsPanel from useGatewayStore to useHandStore
- Add type adapters and category mapping for 7 Hands
- Create useAutomationEvents hook for WebSocket event handling

Phase 2 - UI Components:
- Create AutomationPanel as unified entry point
- Create AutomationCard with grid/list view support
- Create AutomationFilters with category tabs and search
- Create BatchActionBar for batch operations

Phase 3 - Advanced Features:
- Create ScheduleEditor with visual scheduling (no cron syntax)
- Support frequency: once, daily, weekly, monthly, custom
- Add timezone selection and end date options

Technical Details:
- AutomationItem type unifies Hand and Workflow
- CategoryType: research, data, automation, communication, content, productivity
- ScheduleInfo interface for scheduling configuration
- WebSocket events: hand, workflow, approval

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-18 16:32:18 +08:00
iven
e262200f1e 首页布局优化前 2026-03-17 23:26:16 +08:00
iven
74dbf42644 refactor(startup): simplify stack to Tauri-managed OpenFang + optional ChromeDriver
- Remove OpenFang CLI dependency from startup scripts
- OpenFang now bundled with Tauri and managed via gateway_start/gateway_status commands
- Add bootstrap screen in App.tsx to auto-start local gateway before UI loads
- Update Makefile: replace start-no-gateway with start-desktop-only
- Fix gateway config endpoints: use /api/config instead of /api/config/quick
- Add Playwright dependencies for future E2E testing
2026-03-17 14:08:03 +08:00
iven
d890fa1858 feat(scripts): add unified startup scripts for full stack development
Add comprehensive startup scripts for managing all ZCLAW services:

Windows (PowerShell):
- start.ps1 / start-all.ps1 - Unified service launcher
- Supports -NoBrowser, -NoGateway, -Dev, -Stop flags

Unix (Bash):
- start.sh - Cross-platform launcher for macOS/Linux

Makefile:
- make start / make start-unix
- make desktop / make desktop-build
- make setup / make test / make clean

pnpm commands:
- pnpm start - Start all services
- pnpm start:dev - Development mode with hot reload
- pnpm start:no-browser - Skip ChromeDriver
- pnpm start:no-gateway - Skip OpenFang gateway
- pnpm desktop - Start Tauri only
- pnpm chromedriver - Start ChromeDriver only

Services managed:
1. ChromeDriver (port 4444) - Browser automation
2. OpenFang Gateway (port 4200) - AI Agent runtime
3. Tauri Desktop - React + Rust frontend

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-17 09:23:44 +08:00
iven
6bd9b841aa feat(browser-hand): implement Browser Hand UI components
Add complete Browser Hand UI system for browser automation:

Components:
- BrowserHandCard: Main card with status display and screenshot preview
- TaskTemplateModal: Template selection and parameter configuration
- ScreenshotPreview: Screenshot display with fullscreen capability

Templates:
- Basic operations: navigate, screenshot, form fill, click, execute JS
- Scraping: text, list, images, links, tables
- Automation: login+action, multi-page, monitoring, pagination

Features:
- 15 built-in task templates across 3 categories
- Real-time execution status with progress bar
- Screenshot preview with zoom and fullscreen
- Integration with HandsPanel for seamless UX
- Zustand store for state management
- Comprehensive test coverage (16 tests)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-17 08:56:02 +08:00
iven
f4efc823e2 refactor(types): comprehensive TypeScript type system improvements
Major type system refactoring and error fixes across the codebase:

**Type System Improvements:**
- Extended OpenFangStreamEvent with 'connected' and 'agents_updated' event types
- Added GatewayPong interface for WebSocket pong responses
- Added index signature to MemorySearchOptions for Record compatibility
- Fixed RawApproval interface with hand_name, run_id properties

**Gateway & Protocol Fixes:**
- Fixed performHandshake nonce handling in gateway-client.ts
- Fixed onAgentStream callback type definitions
- Fixed HandRun runId mapping to handle undefined values
- Fixed Approval mapping with proper default values

**Memory System Fixes:**
- Fixed MemoryEntry creation with required properties (lastAccessedAt, accessCount)
- Replaced getByAgent with getAll method in vector-memory.ts
- Fixed MemorySearchOptions type compatibility

**Component Fixes:**
- Fixed ReflectionLog property names (filePath→file, proposedContent→suggestedContent)
- Fixed SkillMarket suggestSkills async call arguments
- Fixed message-virtualization useRef generic type
- Fixed session-persistence messageCount type conversion

**Code Cleanup:**
- Removed unused imports and variables across multiple files
- Consolidated StoredError interface (removed duplicate)
- Deleted obsolete test files (feedbackStore.test.ts, memory-index.test.ts)

**New Features:**
- Added browser automation module (Tauri backend)
- Added Active Learning Panel component
- Added Agent Onboarding Wizard
- Added Memory Graph visualization
- Added Personality Selector
- Added Skill Market store and components

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-17 08:05:07 +08:00
iven
adfd7024df docs(claude): restructure documentation management and add feedback system
- Restructure §8 from "文档沉淀规则" to "文档管理规则" with 4 subsections
  - Add docs/ structure with features/ and knowledge-base/ directories
  - Add feature documentation template with 7 sections (概述/设计初衷/技术设计/预期作用/实际效果/演化路线/头脑风暴)
  - Add feature update trigger matrix (新增/修改/完成/问题/反馈)
  - Add documentation quality checklist
- Add §16
2026-03-16 13:54:03 +08:00
iven
8e630882c7 feat(l4): add AutonomyManager for tiered authorization system (Phase 3)
Implements L4 self-evolution authorization with:

Autonomy Levels:
- Supervised: All actions require user confirmation
- Assisted: Low-risk actions auto-execute, high-risk need approval
- Autonomous: Agent decides, only high-impact actions notify

Features:
- Risk-based action classification (low/medium/high)
- Importance threshold for auto-approval
- Approval workflow with pending queue
- Full audit logging with rollback support
- Configurable action permissions per level

Security:
- High-risk actions ALWAYS require confirmation
- Self-modification disabled by default even in autonomous mode
- All autonomous actions logged for audit
- One-click rollback to any historical state

Tests: 30 passing

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 10:49:49 +08:00
iven
0b89329e19 feat(l4): upgrade engines with LLM-powered capabilities (Phase 2)
Phase 2 LLM Engine Upgrades:
- ReflectionEngine: Add LLM semantic analysis for pattern detection
- ContextCompactor: Add LLM summarization for high-quality compaction
- MemoryExtractor: Add LLM importance scoring for memory extraction
- Add unified LLM service adapter (OpenAI, Volcengine, Gateway, Mock)
- Add MemorySource 'llm-reflection' for LLM-generated memories
- Add 13 integration tests for LLM-powered features

Config options added:
- useLLM: Enable LLM mode for each engine
- llmProvider: Preferred LLM provider
- llmFallbackToRules: Fallback to rules if LLM fails

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 10:41:03 +08:00
iven
ef3315db69 feat(l4): add LLM service adapter for Phase 2 engine upgrades
- Unified interface for OpenAI, Volcengine, Gateway, and Mock providers
- Structured LLMMessage and LLMResponse types
- Configurable via localStorage with API key security
- Built-in prompt templates for reflection, compaction, extraction
- Helper functions: llmReflect(), llmCompact(), llmExtract()

This adapter enables the 3 engines to be upgraded from rule-based
to LLM-powered in Phase 2.1-2.3.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 10:28:10 +08:00
iven
85e39ecafd feat(l4): add Phase 1 UI components for self-evolution capability
SwarmDashboard (多 Agent 协作面板):
- Task list with real-time status updates
- Subtask visualization with results
- Communication style indicators (Sequential/Parallel/Debate)
- Task creation form with manual triggers

SkillMarket (技能市场):
- Browse 12 built-in skills by category
- Keyword/capability search
- Skill details with triggers and capabilities
- Install/uninstall with L4 autonomy hooks

HeartbeatConfig (心跳配置):
- Enable/disable periodic proactive checks
- Interval slider (5-120 minutes)
- Proactivity level selector (Silent/Light/Standard/Autonomous)
- Quiet hours configuration
- Built-in check item toggles

ReflectionLog (反思日志):
- Reflection history with pattern analysis
- Improvement suggestions by priority
- Identity change proposal approval workflow
- Manual reflection trigger
- Config panel for trigger settings

Part of ZCLAW L4 Self-Evolution capability.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 10:24:00 +08:00
iven
134798c430 feat(viking): add local server management for privacy-first deployment
Backend (Rust):
- viking_commands.rs: Tauri commands for server status/start/stop/restart
- memory/mod.rs: Memory module exports
- memory/context_builder.rs: Context building with memory injection
- memory/extractor.rs: Memory extraction from conversations
- llm/mod.rs: LLM integration for memory summarization

Frontend (TypeScript):
- context-builder.ts: Context building with OpenViking integration
- viking-client.ts: OpenViking API client
- viking-local.ts: Local storage fallback when Viking unavailable
- viking-memory-adapter.ts: Memory extraction and persistence

Features:
- Multi-mode adapter (local/sidecar/remote) with auto-detection
- Privacy-first: all data stored in ~/.openviking/, server only on 127.0.0.1
- Graceful degradation when local server unavailable
- Context compaction with memory flush before compression

Tests: 21 passing (viking-adapter.test.ts)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 09:59:14 +08:00
iven
26e64a3fff fix(hands): use hand.id instead of hand.name for API calls
- Fix HandTaskPanel to use hand.id when loading runs and triggering
- Fix HandsPanel to use hand.id for getHandDetails and triggerHand
- Fix WorkflowEditor to use hand.id as option value

The API expects hand identifiers, not names. This ensures correct
hand execution and run history loading.

Also clean up old plan files and add Gateway stability plan.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 09:57:01 +08:00
iven
a312524abb fix(gateway): add API fallbacks and connection stability improvements
- Add api-fallbacks.ts with structured fallback data for 6 missing API endpoints
  - QuickConfig, WorkspaceInfo, UsageStats, PluginStatus, ScheduledTasks, SecurityStatus
  - Graceful degradation when backend returns 404
- Add heartbeat mechanism (30s interval, 3 max missed)
  - Automatic connection keep-alive with ping/pong
  - Triggers reconnect when heartbeats fail
- Improve reconnection strategy
  - Emit 'reconnecting' events for UI feedback
  - Support infinite reconnect mode
- Add ConnectionStatus component
  - Visual indicators for 5 connection states
  - Manual reconnect button when disconnected
  - Compact and full display modes

Diagnosed via Chrome DevTools: WebSocket was working fine, real issue was
404 errors from missing API endpoints being mistaken for connection problems.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 09:56:25 +08:00
iven
131b9c93ae docs: update OpenViking installation requirements
- Add Python version compatibility notes (3.10-3.12 required)
- Add Windows-specific installation instructions
- Add conda/WSL alternatives for Python 3.13+ users
- Update binaries README with system requirements table
- Clarify that CLI requires server to run

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 08:28:27 +08:00
iven
c8202d04e0 feat(viking): add local server management for privacy-first deployment
- Add viking_server.rs (Rust) for managing local OpenViking server process
- Add viking-server-manager.ts (TypeScript) for server control from UI
- Update VikingAdapter to support 'local' mode with auto-start capability
- Update documentation for local deployment mode

Key features:
- Auto-start local server when needed
- All data stays in ~/.openviking/ (privacy-first)
- Server listens only on 127.0.0.1
- Graceful fallback to remote/localStorage modes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 08:14:44 +08:00
iven
137f1a32fa feat: implement Phase 4 - Multi-Agent Swarm + Skill Discovery
Phase 4a: Agent Swarm Collaboration Framework (agent-swarm.ts)
- AgentSwarm class with configurable coordinator + specialist agents
- Three collaboration modes: Sequential (chain), Parallel (concurrent), Debate (multi-round)
- Auto task decomposition based on specialist capabilities
- Debate consensus detection with keyword similarity heuristic
- Rule-based result aggregation with structured markdown output
- Specialist management (add/update/remove) and config updates
- History persistence to localStorage (last 25 tasks)
- Memory integration: saves task completion as lesson memories

Phase 4b: Skill Discovery Engine (skill-discovery.ts)
- SkillDiscoveryEngine with 12 built-in skill definitions from skills/ directory
- Multi-signal search: name, description, triggers, capabilities, category matching
- Conversation-based skill recommendation via topic extraction (CN + EN patterns)
- Memory-augmented confidence scoring for suggestions
- Skill registration, install status toggle, category filtering
- localStorage persistence for skill index and suggestion cache

Phase 4c: chatStore Integration
- dispatchSwarmTask(description, style): creates and executes swarm task, adds result as message
- searchSkills(query): exposes skill search to UI layer

Tests: 317 passing across 13 test files (43 new for swarm + skills)
- AgentSwarm: createTask, sequential/parallel/debate execution, history, specialist mgmt
- SkillDiscovery: search, suggest, register, persist, categories

Refs: ZCLAW_AGENT_INTELLIGENCE_EVOLUTION.md updated - all 4 phases complete
2026-03-15 22:44:18 +08:00
iven
04ddf94123 feat: implement ZCLAW Agent Intelligence Evolution Phase 1-3
Phase 1: Persistent Memory + Identity Dynamic Evolution
- agent-memory.ts: MemoryManager with localStorage persistence, keyword search, deduplication, importance scoring, pruning, markdown export
- agent-identity.ts: AgentIdentityManager with per-agent SOUL/AGENTS/USER.md, change proposals with approval workflow, snapshot rollback
- memory-extractor.ts: Rule-based conversation memory extraction (Phase 1), LLM extraction prompt ready for Phase 2
- MemoryPanel.tsx: Memory browsing UI with search, type filter, delete, export (integrated as 4th tab in RightPanel)

Phase 2: Context Governance
- context-compactor.ts: Token estimation, threshold monitoring (soft/hard), memory flush before compaction, rule-based summarization
- chatStore integration: auto-compact when approaching token limits

Phase 3: Proactive Intelligence + Self-Reflection
- heartbeat-engine.ts: Periodic checks (pending tasks, memory health, idle greeting), quiet hours, proactivity levels (silent/light/standard/autonomous)
- reflection-engine.ts: Pattern analysis from memory corpus, improvement suggestions, identity change proposals, meta-memory creation

Chat Flow Integration (chatStore.ts):
- Pre-send: context compaction check -> memory search -> identity system prompt injection
- Post-complete: async memory extraction -> reflection conversation tracking -> auto-trigger reflection

Tests: 274 passing across 12 test files
- agent-memory.test.ts: 42 tests
- context-compactor.test.ts: 23 tests
- heartbeat-reflection.test.ts: 28 tests
- chatStore.test.ts: 11 tests (no regressions)

Refs: ZCLAW_AGENT_INTELLIGENCE_EVOLUTION.md updated with implementation progress
2026-03-15 22:24:57 +08:00