iven
f4ed1b33e0
feat(kernel): add multi-skill orchestration bridge + true parallel execution
...
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
- 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
...
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
- 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
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
813b49a986
feat: P0 KernelClient功能修复 + P1/P2/P3质量改进
...
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
P0 KernelClient 功能断裂修复:
- Skill CUD: registry.rs create/update/delete + serialize_skill_md + kernel proxy
- Workflow CUD: pipeline_commands.rs create/update/delete + serde_yaml依赖
- Agent更新: registry update方法 + AgentConfigUpdated事件 + agent_update命令
- Hand流式事件: HandStart/HandEnd变体替换ToolStart/ToolEnd
- 后端验证: hand_get/hand_run_status/hand_run_list确认实现完整
- Approval闭环: respond_to_approval后台spawn+5分钟超时轮询
P2/P3 质量改进:
- Browser WebDriver: TCP探测ChromeDriver/GeckoDriver/Edge端口替换硬编码true
- api-fallbacks: 移除假技能和16个捏造安全层，替换为真实能力映射
- dead_code清理: 移除5个模块级#![allow(dead_code)]，删除3个真正死方法，
删除未注册的compactor_compact_llm命令，warnings从8降到3
- 所有变更通过cargo check + tsc --noEmit验证
2026-03-30 10:55:08 +08:00
iven
5595083b96
feat(skills): SemanticSkillRouter — TF-IDF + Embedding 混合路由
...
实现 SemanticSkillRouter 核心模块 (zclaw-skills):
- Embedder trait + NoOpEmbedder (TF-IDF fallback)
- SkillTfidfIndex 全文索引
- retrieve_candidates() Top-K 检索
- route() 置信度阈值路由 (0.85)
- cosine_similarity 公共函数
- 单元测试覆盖
Kernel 适配层 (zclaw-kernel):
- EmbeddingAdapter: zclaw-growth EmbeddingClient → Embedder
文档同步:
- 01-intelligent-routing.md Phase 1+2 标记完成
2026-03-30 00:54:11 +08:00
iven
eed26a1ce4
feat(pipeline): Pipeline 图持久化 — GraphStore 实现
...
新增 GraphStore trait 和 MemoryGraphStore 实现:
- save/load/delete/list_ids 异步接口
- 可选文件持久化到 JSON 目录
- 启动时从磁盘加载已保存的图
SkillOrchestrationDriver 集成:
- 新增 with_graph_store() 构造函数
- graph_id 路径从硬编码错误改为从 GraphStore 查找
- 无 store 时返回明确的错误信息
修复了 "Graph loading by ID not yet implemented" 的 TODO
2026-03-30 00:25:38 +08:00
iven
04c366fe8b
feat(runtime): DeerFlow 模式中间件链 Phase 1-4 全部完成
...
借鉴 DeerFlow 架构，实现完整中间件链系统：
Phase 1 - Agent 中间件链基础设施
- MiddlewareChain Clone 支持
- LoopRunner 双路径集成 (middleware/legacy)
- Kernel create_middleware_chain() 工厂方法
Phase 2 - 技能按需注入
- SkillIndexMiddleware (priority 200)
- SkillLoadTool 工具
- SkillDetail/SkillIndexEntry 结构体
- KernelSkillExecutor trait 扩展
Phase 3 - Guardrail 安全护栏
- GuardrailMiddleware (priority 400, fail_open)
- ShellExecRule / FileWriteRule / WebFetchRule
Phase 4 - 记忆闭环统一
- MemoryMiddleware (priority 150, 30s 防抖)
- after_completion 双路径调用
中间件注册顺序：
100 Compaction | 150 Memory | 200 SkillIndex
400 Guardrail | 500 LoopGuard | 700 TokenCalibration
向后兼容：Option<MiddlewareChain> 默认 None 走旧路径
2026-03-29 23:19:41 +08:00
iven
5fdf96c3f5
chore: 提交所有工作进度 — SaaS 后端增强、Admin UI、桌面端集成
...
包含大量 SaaS 平台改进、Admin 管理后台更新、桌面端集成完善、
文档同步、测试文件重构等内容。为 QA 测试准备干净工作树。
2026-03-29 10:46:41 +08:00
iven
a71c4138cc
fix(audit): 修复深度审计发现的 P0/P1 问题 (8项)
...
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
基于 DEEP_AUDIT_REPORT.md 修复 2 CRITICAL + 4 HIGH + 1 MEDIUM 问题:
- C1: PromptOnly 技能集成 LLM 调用 — 定义 LlmCompleter trait，
通过 LlmDriverAdapter 桥接 zclaw_runtime::LlmDriver，
PromptOnlySkill.execute() 现在调用 LLM 生成内容
- C2: 反思引擎空记忆 bug — 新增 query_memories_for_reflection()
从 VikingStorage 查询真实记忆传入 reflect()
- H7: Agent Store 接口适配 — KernelClient 添加 listClones/createClone/
deleteClone/updateClone 方法，映射到 agent_* 命令
- H8: Hand 审批检查 — hand_execute 执行前检查 needs_approval，
需审批返回 pending_approval 状态
- M1: 幽灵命令注册 — 注册 hand_get/hand_run_status/hand_run_list
三个 Tauri 桩命令
- H1/H2: SpeechHand/TwitterHand 添加 demo 标签
- H5: 归档过时 VERIFICATION_REPORT
文档更新: DEEP_AUDIT_REPORT.md 标记修复状态，README.md 更新
关键指标和变更历史。整体完成度从 ~50% 提升至 ~58%。
2026-03-27 09:36:50 +08:00
iven
8bcabbfb43
refactor: 代码质量清理 - 移除死代码和遗留别名
...
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
基于全面审计报告的 P0-P2 修复工作：
P0 (已完成):
- intelligence 模块: 精确注释 dead_code 标注原因（Tauri runtime 注册）
- compactor.rs: 实现 LLM 摘要生成（compact_with_llm）
- pipeline_commands.rs: 替换 println! 为 tracing 宏
P1 (已完成):
- 移除 8 个 gateway_* 向后兼容别名（OpenClaw 遗留）
- 前端 tauri-gateway.ts 改为调用 zclaw_* 命令
- 清理 generation.rs 6 个重复的实例方法（-217 行）
- A2A dead_code 注释更新
P2 (已完成):
- Predictor/Lead HAND.toml 设置 enabled=false
- Wasm/Native SkillMode 添加未实现说明
- browser/mod.rs 移除未使用的 re-export（消除 4 个警告）
文档更新:
- feature-checklist.md 从 v0.4.0 更新到 v0.6.0
- CLAUDE.md Hands 状态更新
验证: cargo check 零警告, 42 测试通过, 净减 371 行代码
2026-03-27 00:54:57 +08:00
iven
978dc5cdd8
fix(安全): 修复HTML导出中的XSS漏洞并清理调试日志
...
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
refactor(日志): 替换console.log为tracing日志系统
style(代码): 移除未使用的代码和依赖项
feat(测试): 添加端到端测试文档和CI工作流
docs(变更日志): 更新CHANGELOG.md记录0.1.0版本变更
perf(构建): 更新依赖版本并优化CI流程
2026-03-26 19:49:03 +08:00
iven
bf6d81f9c6
refactor: 清理未使用代码并添加未来功能标记
...
CI / Rust Check (push) Has been cancelled
CI / Lint & TypeCheck (push) Has been cancelled
CI / Unit Tests (push) Has been cancelled
CI / Build Frontend (push) Has been cancelled
CI / Security Scan (push) Has been cancelled
CI / E2E Tests (push) Has been cancelled
style: 统一代码格式和注释风格
docs: 更新多个功能文档的完整度和状态
feat(runtime): 添加路径验证工具支持
fix(pipeline): 改进条件判断和变量解析逻辑
test(types): 为ID类型添加全面测试用例
chore: 更新依赖项和Cargo.lock文件
perf(mcp): 优化MCP协议传输和错误处理
2026-03-25 21:55:12 +08:00
iven
aa6a9cbd84
feat: 新增技能编排引擎和工作流构建器组件
...
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
refactor: 统一Hands系统常量到单个源文件
refactor: 更新Hands中文名称和描述
fix: 修复技能市场在连接状态变化时重新加载
fix: 修复身份变更提案的错误处理逻辑
docs: 更新多个功能文档的验证状态和实现位置
docs: 更新Hands系统文档
test: 添加测试文件验证工作区路径
2026-03-25 08:27:25 +08:00
iven
9981a4674e
fix(skills): inject skill list into system prompt for LLM awareness
...
Problem: Agent could not invoke appropriate skills when user asked about
financial reports because LLM didn't know which skills were available.
Root causes:
1. System prompt lacked available skill list
2. SkillManifest struct missing 'triggers' field
3. SKILL.md loader not parsing triggers list
4. "财报" keyword not matching "财务报告" trigger
Changes:
- Add triggers field to SkillManifest struct
- Parse triggers list from SKILL.md frontmatter
- Inject skill list into system prompt in kernel.rs
- Add "财报", "财务数据", "盈利", "营收" triggers to finance-tracker
- Add "财报分析" trigger to analytics-reporter
- Document fix in troubleshooting.md
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-24 15:39:18 +08:00
iven
0ab2f7afda
feat(phase4): complete zclaw-skills, zclaw-hands, zclaw-channels, zclaw-protocols 模块实现
2026-03-22 08:57:37 +08:00
