fischer
/
fischer-agentkit
1
0
Fork 0
Code Issues Pull Requests Actions 87 Packages Projects Releases Wiki Activity
323 Commits 1 Branch 0 Tags 20 MiB
Commit Graph

51 Commits

Author SHA1 Message Date
chiguyong a872a459a6 docs: add PLAN_EXEC concepts + commit Wave 4 plan
Test / backend-test (pull_request) Has been cancelled Details
Test / frontend-unit (pull_request) Has been cancelled Details
Test / api-e2e (pull_request) Has been cancelled Details
Test / frontend-e2e (pull_request) Has been cancelled Details 
CONCEPTS.md: new PLAN_EXEC section (Phase State Machine, PhasePolicy, Phase Violation, AdvancePhaseTool, _build_phase_engine).

docs/plans/: commit the Wave 4 plan document (was untracked).
 2026-06-30 12:46:24 +08:00
Fischer 2b8a7d8909 feat(agent): Wave 3 strategic coupling (G5/G6) (#6)
Deploy to Production / deploy (push) Waiting to run Details
Test / backend-test (push) Waiting to run Details
Test / frontend-unit (push) Waiting to run Details
Test / api-e2e (push) Waiting to run Details
Test / frontend-e2e (push) Waiting to run Details
2026-06-30 09:17:19 +08:00
Fischer a2dcde01b8 feat(agent): Wave 2 medium coupling (G4/G7/G9) (#5)
Deploy to Production / deploy (push) Waiting to run Details
Test / backend-test (push) Waiting to run Details
Test / frontend-unit (push) Waiting to run Details
Test / api-e2e (push) Waiting to run Details
Test / frontend-e2e (push) Waiting to run Details
2026-06-30 09:09:33 +08:00
chiguyong 2747bb4e64 chore(prior): malformed tool call handling, auth whitelist, dev scripts, wave1 plan 2026-06-29 20:25:03 +08:00
chiguyong a6e1bf5884 feat(bitable): 多维表格文件层 + 默认字段 + 表内字段操作 + ce-code-review 修复 (Stage 1)
Test / backend-test (pull_request) Has been cancelled Details
Test / frontend-unit (pull_request) Has been cancelled Details
Test / api-e2e (pull_request) Has been cancelled Details
Test / frontend-e2e (pull_request) Has been cancelled Details 
实现多维表格 UI 完整性 Stage 1（U1-U6），补齐飞书/twenty 对齐缺失的文件层、
默认字段与表内字段操作能力，并修复 ce-code-review 走查发现的 P0/P1 级问题。

后端（U1-U2）:
- 新增 BitableFile 实体（models/db/repository/service/routes），三级层级：文件→数据表→字段/记录
- Schema V2 迁移：bitable_files 表 + tables.file_id 列，幂等（IF NOT EXISTS），保留 V1 孤儿表
- 新建数据表自动创建 5 个默认字段（标题/状态/日期/创建人/创建时间）
- agent-owned 字段在 create_record 时自动填充（按 type+owner 匹配，传 actor_user_id）
- 7 个文件 REST 端点 + IDOR ownership 检查（404-before-403，internal token 旁路）

前端（U3-U5）:
- 文件列表页（FileCard 网格 + 新建/重命名/删除）+ 文件详情页（侧栏表格列表 + vxe-table 网格）
- Vue Router 嵌套路由 /bitable → /bitable/:fileId → /bitable/:fileId/:tableId
- 列头菜单（编辑/隐藏/删除字段）+ 末尾 + 列新增字段
- select/multiselect 字段自定义单元格编辑器 + Tag 展示
- Pinia store 扩展 file 状态与动作，深链直访回退 getFile，fileId 切换 watch

测试（U6）:
- 文件 CRUD（12 例）+ 默认字段（10 例）单元测试
- 3 个 E2E spec（视图加载、文件流、字段操作），后端不可用时优雅跳过

ce-code-review 修复（P0/P1）:
- P0 路由冲突：GET /files/{file_id} 遮蔽下载端点 → 下载改 /uploads/{filename}
- P0 IDOR：update/delete field/record/view 五端点补 ownership 检查
- P1 is_initialized property 缺失致二次初始化崩溃
- P1 直接 URL 导航失效（files 数组为空）→ selectFile 回退 getFile
- P1 fileId 切换不重载 → 增加 watch
- P1 轮询丢弃最终公式值（wasCalculating 守卫）+ 复用视图 filters
- P1 测试断言 200→201；test_db 无 URL 用例解除 postgres 标记得以执行
- P2 _check_table_ownership 403→404；输入长度校验；upload field-table 一致性校验
- P2 multiselect 浅比较 → 深比较；E2E bitable-view 补 waitForServer 守卫

验证：ruff check 通过；pytest 91 passed/116 skipped；vue-tsc --noEmit 通过。
 2026-06-29 04:07:45 +08:00
chiguyong 5c15238a5a fix(calendar): 修复 agent 创建日历事件后 UI 不刷新 + 文档化三根因三部曲
Test / backend-test (pull_request) Has been cancelled Details
Test / frontend-unit (pull_request) Has been cancelled Details
Test / api-e2e (pull_request) Has been cancelled Details
Test / frontend-e2e (pull_request) Has been cancelled Details 
代码修复 (ce-debug):
- CalendarService.create_event 注入 notify_callback，成功后广播 calendar_event_created WS 消息
- app.py 调整 _calendar_ws_sender 闭包定义顺序，注入 CalendarService（与 ReminderScheduler 共享）
- tauri-auth.ts keychain fallback 修复（localStorage 始终作为备份）
- 新增 2 个广播回归测试

文档 (ce-compound + ce-compound-refresh):
- 新增 docs/solutions/ui-bugs/calendar-agent-create-no-refresh.md（第三根因：WS 广播缺失）
- 更新 calendar-capability-and-ui-fixes.md：刷新 test count + 加 Related Issues 前向引用
- 更新 jwt-secret-dev-mode-user-id-mismatch.md：扩展 e2e bullet + 加第三个根因引用
- CONCEPTS.md 新增 Service Broadcast Callback 条目 (Real-Time Fan-Out 节)

测试:
- 新增 E2E 测试套件 (admin/auth-persistence/bitable/calendar/conversation/documents/evolution/settings/skills)
- 新增 tests/e2e/test_api_coverage.py
- CI: .gitea/.github workflows/test.yml
 2026-06-29 02:20:33 +08:00
chiguyong 31c65e01b8 fix(security): P0 安全加固 + 多实例部署一致性 (U1-U4 + U5c)
Deploy to Production / deploy (push) Has been cancelled Details 
U1: LLM gateway KB 缓存 fail-closed — 异常时默认禁用缓存防止 KB 数据泄漏
U2: MCP 危险工具黑名单过滤 — 6+1 端点覆盖，防止绕过 chat confirmation
U3: SecretsStore Redis 迁移 — 多 worker 共享凭证，内存降级保留开发模式
U4: channels webhook Redis 状态 — ZSET 滑动窗口限流 + nonce dedup + backpressure
U5c: ce-code-review 修复批次:
  - P0: 统一 MCP 黑名单与 publisher.py 一致 (terminal_execute -> terminal, +file_read)
  - P1: ZSET 限流 member 加 uuid 后缀避免同时间戳碰撞
  - P1: SecretsStore redis 参数 Any -> aioredis.Redis | None (AGENTS.md 合规)
  - P1: Redis client 添加 socket_timeout 防止单点故障请求挂死

测试: 171 scoped tests pass, ruff clean
 2026-06-26 04:05:33 +08:00
chiguyong af96cb49bd docs(plan): deepen portal platform evolution plan — KTD5/7/8/9 expanded, KTD11 added 2026-06-25 20:13:27 +08:00
chiguyong bbbf9cd40a feat(bitable): add bitable companion service with full P0-P2 fixes 
Bitable is a multi-dimensional table companion service that runs alongside
the main AgentKit server. It provides structured data storage with formula
fields, views, and ingestion pipelines.

Major components:
- Domain models (Pydantic v2): Table, Field, Record, View, RecalcTask
- SQLAlchemy 2 async ORM with independent bitable PostgreSQL schema
- Formula engine: AST parser, DAG, Kahn topological sort, safe eval
- RecalcWorker: atomic task claiming (FOR UPDATE SKIP LOCKED), topo-order
  processing, stale-threshold reaper for crash recovery
- REST API (/api/v1/bitable): tables, fields, records, views, files
- BitableTool: agent-facing tool with batch chunking (500/batch)
- CLI: agentkit bitable subcommands (create, list, import-excel, etc.)
- Frontend: Vue 3 + vxe-table grid with field management, views, filters
- Ingestion: Excel (openpyxl), database reflection, API collector

Security fixes (ce-code-review P0 + ce-debug P1):
- SQL injection prevention (field_id validation, parameterized queries)
- IDOR protection (_check_table_ownership on all table-level endpoints)
- SSRF prevention (URL scheme + private IP validation in parse_excel_url)
- OOM prevention (streaming file upload, batch delete, batch insert)
- Atomic recalc task claiming (FOR UPDATE SKIP LOCKED)
- Formula engine cache invalidation on field changes
- Composite cursor pagination for non-id sort orders
- Batch upsert (eliminates N+1 queries)
- Sync I/O offloaded to thread pool in async contexts
- Internal token auth (X-Internal-Token, hmac.compare_digest)
- PK unique index enforcement

Test coverage: 88 unit tests (95 skipped without Docker)
 2026-06-25 01:09:59 +08:00
chiguyong a312e584ae Merge branch 'feat/expert-team-pm-collaboration' — PM 协同模式 + 代码审查全量修复
Deploy to Production / deploy (push) Waiting to run Details 
# Conflicts:
#	src/agentkit/server/frontend/components.d.ts
 2026-06-24 18:57:37 +08:00
chiguyong 574db8458f fix(experts): PM 协同代码审查全量修复 
P0: 跨阶段契约状态同步 — _notify_collaborators 更新接收方契约状态为 received
P0: 4 个 PM 事件加入 _VALID_TEAM_EVENT_TYPES 白名单

P1: 验收 fail-open 改标注降级原因
P1: 返工失败抛 RuntimeError 而非返回 dict
P1: 验收 prompt injection 防护 — 专家输出用 XML 标签包裹
P1: 契约字段校验 _EXPERT_NAME_RE
P1: bool("false") 修复 — 显式比较避免字符串真值陷阱
P1: _parse_risk_flags(None) 防御

P2: _notify_collaborators 移到验收通过后
P2: SharedWorkspace 写入移到验收通过后
P2: 验收贪婪正则修复
P2: 风险标记数量上限 MAX_RISK_FLAGS=10
P2: 返工 feedback 截断
P2: 前端会话隔离 — 切换会话时清除/恢复 collaborationState
P2: 前端契约状态更新 — collaboration_notice 时标记 delivered
P2: CLI 死代码标注 + 异常改 debug 日志
P2: 模块级 _RISK_FLAG_RE 预编译
 2026-06-24 18:56:27 +08:00
chiguyong fef7ecea39 feat(skills): SkillHarness 激活前置条件 + 风险守卫学习 
基于 SkillHarness 论文（arXiv:2606.20636）与 Agent Skills 综述
（arXiv:2602.12430）引入激活前置条件（preconditions）与来源标记
（provenance），并新增从失败轨迹学习风险守卫建议的能力。

变更内容：
- U1: SkillConfig 新增 v7 preconditions/provenance 字段（base.py）
- U2: build_skill_system_prompt 注入 preconditions 软检查段落
- U3: SkillLoader 三路径记录 provenance + entry_points 危险能力告警
- U4: 10 个业务 Skill YAML 补充 preconditions（2-4 条中文短句）
- U5: RiskGuardLearner 从失败轨迹学习风险守卫建议（人工审查，不自动应用）
- U6: CLI 命令 agentkit skill learn-risk-guards

关键决策：
- KTD1: preconditions 通过 system_prompt 注入（软检查），不做硬 LLM 调用
- KTD2: RiskGuardLearner 不自动应用，需人工审查（论文显示 75% 自动学习不安全）
- KTD3: provenance 为轻量字符串，不加 hash/签名（无合规需求）

测试：39 个新增单元测试全部通过，ruff 检查通过。
 2026-06-24 13:56:37 +08:00
chiguyong d4bc79e409 test(calendar): wire calendar router into app.py + test plan 
- Register calendar router in create_app() so /api/v1/calendar/* is reachable
- Initialize CalendarService + ReminderScheduler in lifespan
- Register CalendarTool into tool registry for ReAct integration
- Lazy-import ICSProvider in routes to break circular import
- Add test plan document (5 layers: unit/integration/e2e)
 2026-06-24 11:51:31 +08:00
chiguyong 460cf6e926 docs(calendar): add implementation history with code review summary 2026-06-24 11:36:10 +08:00
chiguyong fbe08cb1e2 feat(experts): add debate phase executor to TeamOrchestrator (U2) 
Implement _execute_debate_phase() with Lead-facilitated structured debate:
- Lead opens with divergence point + dependency context
- Experts argue in parallel per round (asyncio.gather)
- Lead summarizes each round, then adjudicates final verdict
- Verdict produces decision (adopt/compromise/shelve/inconclusive) + conclusion
- Conclusion written to SharedWorkspace for downstream phases

Escape hatches:
- debate_config.skip=true short-circuits with template text
- MAX_DEBATE_ROUNDS=4 hard cap on rounds
- User /stop intervention ends debate early (U4-compatible via getattr fallback)
- LLM unavailable falls back to template verdict, no crash

New events: debate_started, expert_argument, debate_round_summary,
debate_resolved (plus existing phase_completed for consistency).

Phase dispatcher (_execute_phase) routes by phase_type:
EXECUTION to _execute_execution_phase, DEBATE to _execute_debate_phase.

36 new tests in test_orchestrator_debate.py covering happy path (2 rounds,
2 experts), max_rounds=1 boundary, empty participants, user stop, skip
escape hatch, LLM unavailable, SharedWorkspace integration, event
broadcasting, intervention channel compatibility, and helper methods.
All 377 expert tests pass.

Also includes planning artifacts (brainstorm requirements + implementation
plan with 6 units U1-U6).
 2026-06-24 10:54:51 +08:00
chiguyong d1250cf32b docs(calendar): mark plan as completed — all 12 units implemented 2026-06-24 05:04:39 +08:00
chiguyong 47f3bfecfc feat(documents): add document processing capability (U1-U9) 
Implements end-to-end document generation, template filling, and reading:

- DocumentService: unified business layer for create/query/download
- Renderers: Word (Markdown->docx), Excel (Markdown/JSON->xlsx),
  PDF (Markdown->pdf with CJK font), Template (Jinja2 sandbox .docx fill)
- DocumentLoader: read PDF/Word/Excel/Markdown/HTML/text -> Document
- DocumentTool: Agent tool with action=create|read
- REST API: /api/v1/documents (create, upload-template, list, download)
- Frontend: DocumentPanel, DocumentCard, documents Pinia store,
  chat store tool_result detection
- Security: path traversal guard (Path.resolve + relative_to),
  SSTI guard (SandboxedEnvironment), API key auth, 50MB upload limit
- Bug fixes: template path traversal (400 not 500), TemplateRenderer
  lazy-load (no external registration dependency)
- Tests: 168 tests (unit + security + E2E F1/F2/F3 + bug hunt)
- Docs: README section 17, requirements + plan + test-plan docs

Requirements R1-R28 verified, F1-F3 user flows pass.
 2026-06-23 15:05:01 +08:00
chiguyong 3efdaafb5f docs: mark admin console plan as completed 2026-06-21 20:02:27 +08:00
chiguyong ad65f7a8d7 feat(admin): U1+U2+U4 — schema v3, department service, context filtering 
U1: Bump _SCHEMA_VERSION to 3, add 5 department tables (departments,
user_departments, department_skill_bindings, department_kb_bindings,
department_quotas) + 5 ORM models + helpers.

U2: DepartmentService (12 async methods: CRUD + bind/unbind skill/KB +
count_users). Mount admin_router in app.py. 36 unit + 28 integration tests.

U4: DepartmentContext FastAPI dependency (per-route, admin bypasses
filtering). filter_skills_by_department / filter_kb_sources_by_department
helpers. Applied to GET /skills and GET /kb-management/* routes.
15 integration tests for department isolation.

Also includes brainstorm + plan docs. 108 new tests, all pass.
 2026-06-21 15:03:27 +08:00
chiguyong 67c0d67262 fix(auth,chat): P0 security fixes + stop-generation button + doc sync 
U1: whoami cold-start security — add is_active check (disabled users
now get 401, not 200) and replace create_token_pair with create_access_token
to avoid minting a discarded refresh token (token-amplification risk).

U2: list_active_by_provider now filters expired sessions (expires_at > now)
matching its docstring promise; previously only checked revoked = 0.

U3: Fix asyncio.run() crash in test_revoke_other_user_session_returns_404
(converted to async). Add U1/U2 verification tests (disabled-user whoami,
no-refresh-leak, expired-session filtering, provider filtering) and
strengthen admin route tests (404 boundary, non-admin 403 on /admin/sessions).

U4: Update CLAUDE.md/AGENTS.md Request Flow — CostAwareRouter 3-layer
diagram replaced with actual RequestPreprocessor architecture (@board/@team
prefix intercepts then @skill: prefix then trivial-input regex then default
REACT). ExecutionMode list expanded to all 7 values.

U5: Frontend stop-generation button — ChatInput.vue shows a stop button
when isGenerating is true; chat store gains stopGeneration() that sends
{type:"cancel"} over WebSocket (backend portal.py already handles cancel).

Tests: 120 auth tests pass (unit + integration). ruff clean. vue-tsc clean.
 2026-06-21 11:36:58 +08:00
chiguyong 54955aab50 plan: 计划审查修订 + AuthProvider 抽象层设计 
- 修复 U1 (Schema): 澄清不使用 Alembic，采用 _SCHEMA_SQL + init_auth_db()，
  新增 user_sessions → auth_sessions 一次性数据回填
- 修复 U4 (Routes): whoami 端点添加到中间件白名单并实现自主认证，
  明确 get_current_session / load_user / user_to_response 等函数定义
- 新增 AuthProvider 抽象层：Protocol 接口、LocalAuthProvider、StubOIDCProvider
  及依赖注入工厂，支持未来对接集团 IdP
- 新增 AE-10 (Provider 切换) + AE-11 (审计字段) 验收用例
- 更新 Component Map，添加 AuthProvider 相关组件
 2026-06-21 00:21:52 +08:00
TraeAI 3d1cad4710 plan: 集中鉴权与 Token 持久化实施计划 
10 个实施单元，分 5 个阶段：
- Phase 1 (U1-U3): 后端 Schema / JWT sid / SessionService + reuse 检测
- Phase 2 (U4, U10): 新端点 + 向后兼容 shim
- Phase 3 (U5, U6): Tauri keyring + 前端 adapter
- Phase 4 (U7-U9): auth store 重构 + 登录/Settings/Admin UI
- Phase 5: 30 天后清理 legacy path

验收 9 条端到端 AE 覆盖 F1-F12 / N5 / N6。
 2026-06-20 23:48:58 +08:00
chiguyong cac9c73dd5 fix(routing): U1-U6 路由优化 + 修复方案 + 代码审查修复 
实现 6 个修复单元（U1-U6）并应用 ce-code-review 发现的 5 项安全修复。

## U1: benchmark 超时阈值
- 按 difficulty 分级超时：easy=45s, medium=60s, hard=90s
- 替换原单一 60s 硬编码

## U2: OpenAICompatibleProvider httpx 超时
- 新增 timeout 参数（默认 120s），替换硬编码 60s
- ProviderConfig.timeout 透传到 Provider
- 新增 2 项单元测试

## U3: 激活 QualityGate skill_match 校验
- BaseAgent._build_skill_context() 构造 skill_context
- 在 base.py / tasks.py / runner.py 三处传入 QualityGate.validate()

## U4: 添加 disambiguation_keywords 字段
- IntentConfig 新增 disambiguation_keywords 字段
- 8 个 skill YAML 补充该字段

## U5: 优化 RequestPreprocessor 路由正则
- 拆分 _FACTUAL_RE 为 CN/EN 双正则（中文无空格）
- 新增 _MATH_RE / _TRANSLATION_RE 纯模式
- _TOOL_CONTEXT_RE 排除需要工具的实时查询
- 多行输入守卫 + 结尾标点支持
- 新增 21 项单元测试（共 40 项全通过）

## U6: 重新基准测试
- 真实 LLM benchmark：准确率 60% -> 93.3%
- 4/5 通过，p50=40.8s，一致性=100%
- 旧基线备份至 baseline_2026-06-17_old_arch.json

## ce-code-review 修复（5 项）
- 修复 \s 字符类匹配换行符的安全隐患
- 添加事实/数学正则的结尾标点支持
- 修复 geo_optimizer.yaml 关键词重复
- 修复 _login_with_retry 不可达 return
- 修复 real_llm_server fixture stderr_fh 资源泄漏

测试：tests/unit/chat/ 63 项全通过，ruff 检查通过。
 2026-06-20 19:31:49 +08:00
chiguyong 91f56ca663 feat: 企业级客户端-服务端架构 + 代码审查修复 
## 主要变更

### 新增功能
- 企业级客户端-服务端架构（JWT 认证 + RBAC 权限 + 终端安全）
- Tauri 桌面客户端与服务端配置同步
- 远程 LLM 网关（RemoteLLMProvider，支持 401 token 刷新重试）
- 服务端终端 WebSocket（带管理员审批流程）
- 终端白名单六层防御（黑名单 → shell 操作符检测 → 内置安全 → 全局/用户/会话白名单 → 危险检测）

### 代码审查修复（P0/P1/P2）
- P0: 危险二进制（rm/docker 等）不再加入白名单，compute_whitelist_entry 返回 None
- P1: 终端审批所有权追踪（_approval_owners dict）+ 会话清理防泄漏
- P1: 本地终端 WebSocket URL 补齐 JWT token
- P1: 审计日志支持 terminal_mode 过滤
- P1: /system/resources 端点强制 SYSTEM_CONFIG 权限
- P1: RemoteLLMProvider 增加 401 token 刷新重试机制
- P1: auth/models.py 使用 Mapping[str, object] 替代 Any 类型
- P2: 终端授权依赖检查 is_active 账户状态
- 修复 app.py 未使用的 APIKeyAuthMiddleware 导入

### 文档更新
- README.md: 新增第 16 章「企业级客户端-服务端架构」
- AGENTS.md / CLAUDE.md: 同步模块映射、路由表、前端页面
- 计划文档标记为 completed

Closes: docs/plans/2026-06-19-003-feat-enterprise-client-server-evolution-plan.md
 2026-06-20 06:48:18 +08:00
chiguyong cdd5212751 docs: U3+U10 更新 AGENTS.md 流水线模式文档 + 计划状态改为 completed 
- AGENTS.md: 更新 Expert Team Mode 为 Pipeline 模式，补充 PlanPhase/TeamPlan/topological_sort 说明

- AGENTS.md: 新增 Pipeline Flow、Event Sequence、Team Templates 说明

- AGENTS.md: WebSocket 事件新增 phase_started/phase_completed/phase_failed

- AGENTS.md: Conventions 新增专家模板和团队模板配置说明

- 计划文档状态从 active 改为 completed
 2026-06-18 03:04:47 +08:00
chiguyong dddcbd24e3 feat: 私董会讨论模式 + 回测集成 + WS持久化修复 
私董会讨论模式 (Board Meeting Mode):
- BoardRouter: @board 前缀路由, 专家名验证, 模板回退
- BoardTeam: 讨论容器, 状态机 (FORMING->DISCUSSING->CONCLUDING->COMPLETED)
- BoardOrchestrator: 多轮自主循环讨论引擎, 主持人小结, 停止命令检测
- 9个预设名人专家 YAML (马斯克/贝佐斯/张小龙/芒格等)
- 前端 BoardStatusView 群聊式 UI + WebSocket 事件处理
- 后端 chat.py 集成 @board 路由到主聊天流程

回测集成:
- benchmark.py: 新增 board_meeting 维度 (18 tasks, 6 categories)
- benchmark_dataset.py: 新增 BOARD_BENCHMARKS (11 E2E cases)
- test_board_backtest.py: 66 个回测测试 (9 test classes)

Bug 修复:
- resolve_expert_configs: deep-copy 防止 is_lead 修改污染共享模板
- 所有专家名无效时回退到默认模板
- board_router: 非匹配路径 topic 未 strip
- benchmark_dataset: board-name-invalid-001 输入修正

WebSocket 持久化修复:
- chat.py: 三层防御机制确保任务结果不丢失
- chat store: 断线恢复逻辑

部署配置:
- Gitea Actions CI/CD workflow
- docker-compose.deploy.yaml 部署编排
- scripts/deploy.sh 自动化部署脚本

测试结果: 120 单元测试通过, 71 benchmark 测试 100% 通过, ruff 全部通过
 2026-06-17 23:52:53 +08:00
chiguyong 840d1afd6a fix: resolve benchmark failures from root cause (LLM timeout, WebSocket, latency stats) 
U1: LLM reasoning - difficulty-based timeout (easy=20s/medium=40s/hard=60s)
    + streaming keyword detection for hard tasks with non-stream fallback
U2: GUI WebSocket - remove unreliable HTTP pre-check (FastAPI returns 404
    for HTTP GET to WS endpoints), directly test WS connection, treat
    {"type":"connected"} as pass (ping/pong is bonus info)
U3: Verification latency - exclude timeout-tagged cases from P95/p99
    percentile calculation (accuracy stats unaffected)
U4: LLM Gateway - add timeout field to LLMRequest, gateway.chat()/
    chat_stream() passthrough for provider-level timeout support

Test results: 62/63 pass (98.4%), gui-004 fixed, no regressions
pytest: 64 passed, ruff: clean
 2026-06-17 13:32:54 +08:00
chiguyong 5374bc8501 refactor: eliminate routing layer, align with industry best practices 
Phase 1 of architecture optimization (U1/U2/U4/U8):

- U1: Rename SimpleRouter to RequestPreprocessor, route() to preprocess()
  Eliminates misleading routing concept; LLM decides autonomously
  in REACT agent loop (matches Codex/Claude Code/Trae pattern)
- U2: Delete CostAwareRouter, HeuristicClassifier, SemanticRouter
  (~700 lines removed). skill_routing.py: 1688 to 220 lines
- U4: PlanExecEngine defaults to ReActStepExecutor, delete _LLMStepExecutor
  (pure LLM calls without tools = no execution capability)
- U8: ReActEngine defaults to ContextCompressor(keep_recent=10)

Supersedes plans 2026-06-15-002/003/004.
New plan: 2026-06-16-006-refactor-architecture-optimization-evolution-plan.md
 2026-06-17 10:44:40 +08:00
chiguyong c4257591d4 refactor(router): replace CostAwareRouter with SimpleRouter and prompt-based tool calling 2026-06-16 03:31:05 +08:00
chiguyong fa2a6dece2 feat(router): enable SemanticRouter + upgrade benchmark to L3/L5 
- Enable SemanticRouter in agentkit.yaml (router.semantic.enabled: true)
- Integrate SemanticRouter into e2e backtest (_build_real_components)
- Add 8 new semantic test cases: 5 colloquial + 3 mixed-lang expressions
- Add L3 output quality evaluation framework (LLM-as-Judge, 1-5 score)
- Add L5 adaptive capability metrics (consistency rate from overfitting data)
- Add OutputQualityObservation model and evaluate_output_quality() method
- Report now includes L3 and L5 sections

Results: 52 tests pass, description_match F1=66.67%, L5 adaptive rate=100%
 2026-06-15 23:02:47 +08:00
chiguyong e984b4c462 feat(router): optimize routing intelligence — ExecutionMode expansion, multi-candidate scoring, quality gate skill match 
- Expand ExecutionMode enum with REWOO/REFLEXION/PLAN_EXEC
- Add _resolve_execution_mode() to respect skill.config.execution_mode
- Rewrite IntentRouter._match_keywords() for multi-candidate scoring
- Add QualityGate 5th dimension: skill_match validation with warning escalation
- Calibrate HeuristicClassifier: low-complexity signals only when no high signals
- Fix negation regex for Chinese text (avoid matching past punctuation)
- Fix backtest mode_map normalization and .env loading
- Add 61 unit tests (21 HeuristicClassifier + 14 IntentRouter + 13 QualityGate + 13 existing)

Results: execution_mode_accuracy 9.09%→36.36%, skill_routing_F1 66.67%→77.78%
 2026-06-15 22:43:13 +08:00
chiguyong 64d62a2b60 feat: autonomous task execution - connect PlanExecEngine + TeamOrchestrator 
U1: TeamOrchestrator._execute_phase real execution (Expert.agent.execute)
U2: LLM-based merge strategies (BEST/VOTE/FUSION) with fallback
U3: ReActStepExecutor replacing _LLMStepAgent for tool-enabled steps
U4: SharedWorkspace integration for cross-phase/cross-execution state
U5: GoalPlanner prompt tuning with few-shot and verb pattern matching
U6: Replan-before-fallback in TeamOrchestrator
U7: End-to-end validation tests for multi-step research tasks
U8: WebSocket progress events (step_event_callback + new event types)

Code review fixes: P0 response.strip fix, P1 competitor status check,
milestone real impl, VOTE self-bias fix, confirmation_handler wiring,
ExpertTeam public API, DRY _build_result_summaries, replan tests

Also: geo_server.py refactor (ServerConfig.from_yaml), delete llm_config.yaml
 2026-06-15 12:41:32 +08:00
chiguyong 7384ecb03e feat: Expert Team Mode — plan-execute collaboration with conversation UI 
Implements B+C hybrid Expert Team Mode with ExpertConfig, CollaborationPlan,
TeamOrchestrator, ExpertTeamRouter, HandoffTransport, SharedWorkspace, and
Expert wrapper. Frontend includes ExpertTeamView, ExpertMessage,
PlanVisualization, team store, and WS event handlers.

Code review fixes: sentinel-based close, per-phase retry, name validation,
Vue component integration, teamState dedup, Redis reset, plan reassign,
event_type validation, hmac timing-safe compare, message dedup,
reactive updatePhases, O(1) phase lookup, iterative DFS, bounded Queue.

232 unit tests passing.
 2026-06-14 22:20:14 +08:00
chiguyong 94c4c8b887 feat: accumulated frontend enhancements, docs, and static assets 
- Frontend view updates (ChatView, EvolutionView, SkillsView, etc.)
- Updated portal routes and chat store
- New frontend components (FilePreview, ToolCallCard, IconNav)
- Updated static build assets
- New test files (merged router, parallel tools, ReWOO fallback)
- Documentation and brainstorm files
- Codegraph and understand-anything artifacts
 2026-06-14 16:35:01 +08:00
chiguyong bc43b962c7 feat(client): add Tauri 2.x desktop client with sidecar process management 
- Tauri 2.x project scaffold with dual-window (splash + main)
- Rust sidecar management: spawn/kill Python backend, port discovery via stdout
- CancellationToken for graceful task cancellation on exit
- System tray with show/quit, close-to-tray behavior
- Frontend: dynamic baseURL, SplashScreen, TitleBar, Tauri IPC adapter
- PyInstaller build scripts for cross-platform sidecar packaging
- GitHub Actions CI for Win/Mac/Linux release builds
- CSP security policy, proper capabilities configuration
 2026-06-14 10:06:12 +08:00
chiguyong 14f548b56a docs: mark GUI redesign plan as completed 
All 7 implementation units (U1-U7) plus color migration audit are done.
 2026-06-13 03:01:31 +08:00
chiguyong 09698d7a06 feat: frontend productization with code review fixes 
- Workflow: visual canvas, undo/redo, drag-and-drop, real-time execution WebSocket
- Evolution: dashboard, ECharts metrics, experience timeline, pitfall warnings, usage panel
- KB: source CRUD, document upload, search test
- Terminal: interactive PTY WebSocket, whitelist security
- Security: hmac.compare_digest, API key auth on all endpoints, whitelist bypass fix
- Fixes: ECharts async init, WebSocket intentional disconnect, TOCTOU race, Pydantic models
 2026-06-13 01:29:58 +08:00
chiguyong a36bc3d1c1 feat: optimize chat response speed for sub-1s first token latency 
- Add HeuristicClassifier to replace LLM quick_classify with zero-cost
  local heuristic (keyword/length/code-pattern scoring), gated by
  router.classifier config (default: heuristic)
- Add parallel tool execution in ReActEngine via asyncio.gather for
  multiple independent tool_calls, gated by parallel_tools param
- Add AsyncWriteQueue for non-blocking session persistence with WAL
  buffer, gated by async_writes param on SessionManager
- Add httpx.Limits connection pool config to all LLM providers
- Add router config section to ServerConfig and agentkit.yaml
- All optimizations have config switches for safe rollback
 2026-06-12 13:15:06 +08:00
chiguyong d47f279887 fix: resolve code review issues from deferred improvements 
1. InMemoryMessageBus.request(): fix param name (timeout→timeout_seconds) to match ABC
2. InMemoryMessageBus: track consumer tasks, cancel on unsubscribe
3. InMemoryMessageBus: _try_resolve_pending() in queue consumer path
4. evolve_soul(): use "default" category when patterns is empty
5. quick_classify(): use delimiter-based prompt to mitigate injection risk
6. Use asyncio.get_running_loop() instead of deprecated get_event_loop()
 2026-06-11 13:49:02 +08:00
chiguyong 6852dfe892 fix(security,reliability): resolve all P2 findings from code review 2026-06-10 15:05:40 +08:00
chiguyong b34b06724d fix(agentkit): resolve all P0/P1/P2/P3 issues from code review 2026-06-07 22:05:18 +08:00
chiguyong 3645c7a080 docs: mark Phase 7 Headroom integration plan as completed 2026-06-07 18:21:27 +08:00
chiguyong 80a505b1c1 docs: mark Phase 6 plan as completed 2026-06-07 17:27:01 +08:00
chiguyong 9b6c0230c0 docs: add Phase 6 toolkit plan 2026-06-07 16:21:50 +08:00
chiguyong 11a12fed29 docs: mark Phase 5 plan as completed 2026-06-06 22:53:14 +08:00
chiguyong 6e362a8ae7 feat(agentkit): Phase 4 enterprise production upgrade — 12 Implementation Units 
Phase A (P0): EpisodicMemory pgvector search+EmbeddingCache, ReAct timeout+CancellationToken, evolution system fix (A/B test+LLMPromptOptimizer+StrategyTuner), AnthropicProvider native Messages API
Phase B (P1): RetryPolicy+CircuitBreaker, chat_stream fallback chain, WebSocket endpoint, SSE stream fix, Evolution+Memory API routes (7 endpoints), embedding cache+Enhanced Search per-KB degradation fix
Phase C (P2): GeminiProvider native generateContent API, Agent state lock+config hot-reload

Tests: 1301 passed, 18 skipped, 0 failed
 2026-06-06 21:51:04 +08:00
chiguyong e33dc25ad3 feat(memory): RAG pipeline optimization — 5 Implementation Units 
U1: QueryTransformer — LLM/rule-based query rewriting + sub-query decomposition
U2: HttpRAGService enhanced_search() — rerank + compression via /bases/{kb_id}/retrieve
U3: Structured context injection — source attribution headers in RAG results
U4: RetrieveKnowledgeTool — built-in tool for mid-reasoning knowledge retrieval
U5: Configurable retrieval params + per-KB weights + CJK token estimation

Config example:
  memory:
    retrieval:
      top_k: 5
      token_budget: 2000
      context_template: structured
    query_transform:
      enabled: true
      strategy: llm
    semantic:
      search_mode: enhanced
      use_rerank: true
      kb_weights:
        industry-kb-id: 1.2
        enterprise-kb-id: 0.8

Tests: 1037 passed, 18 skipped, 0 failed
 2026-06-06 19:27:09 +08:00
chiguyong f976fade99 docs: mark Phase 3 upgrade plan as completed 2026-06-06 17:18:07 +08:00
chiguyong f858d279f3 feat(agentkit): Phase 3 upgrade - persistence, memory, evolution, observability 
10 Implementation Units across 3 phases:

Phase A - Infrastructure:
- U1: RedisTaskStore with Redis/memory backend + factory function
- U2: TraceRecorder for execution trace recording
- U3: PersistentEvolutionStore with SQLite backend

Phase B - Core Capabilities:
- U4: MemoryRetriever integration into ReAct engine
- U5: Embedder abstraction + EpisodicMemory vector search
- U6: LLMReflector for LLM-in-the-loop reflection
- U7: SkillPipeline for multi-skill orchestration

Phase C - Enhancement:
- U8: SKILL.md format + progressive disclosure levels
- U9: ContextCompressor + prompt cache rendering
- U10: Structured logging + metrics endpoint + enhanced health check

Tests: 924 passed, 18 skipped, 0 failed
 2026-06-06 17:17:45 +08:00
chiguyong b2709da08b feat(cli): AgentKit CLI with serve/version/health/task/skill/init/usage 
U1: CLI framework (Typer) + serve/version/health commands + __main__.py + pyproject scripts
U2: task command group (submit/status/list/cancel) with remote mode
U3: skill command group (list/load/info) with local and remote modes
U4: init command (generates agentkit.yaml/.env.example/docker-compose/skills) + usage command

31 tests passing, TDD workflow.
 2026-06-06 12:45:51 +08:00