fischer
/
fischer-agentkit
1
0
Fork 0
Code Issues Pull Requests Actions 93 Packages Projects Releases Wiki Activity
309 Commits 1 Branch 0 Tags 22 MiB
Commit Graph

29 Commits

Author SHA1 Message Date
chiguyong c9ce15fa4b fix(code-review): 修复走查发现的 13 High + Medium 安全/可靠性问题 
代码修复（8 High + 9 Medium）：
- portal.py — C1 IDOR 文档 / C2 类型修复 / C3 WS 连接上限 16 / C4 ws_user_id 早初始化 / M silent swallow 日志化
- auth/middleware.py — C5 WS sid 补齐
- calendar_tool.py — C6 偏移量 ±43200 双向校验 + reminder_channels 类型/白名单校验
- sqlite_conversation_store.py — C7 DELETE 事务回滚
- chat.ts (Pinia) — C8 deleteConversation 清理 pending 缓存
- app.py — M except: pass → logger.debug(exc_info=True)
- Scene6Error.vue — M onUnmounted 清理 setTimeout
- DocumentsTab.vue — M Invalid Date 守卫
- ChatSidebar/RightPanel/TopNav.vue — M aria-label 无障碍标签
- SystemMonitorPanel.vue — M v-else 兜底 + active 边框色 + tablist 键盘导航
- CalendarDrawer.vue — M overflow-y: auto
- CalendarGrid.vue — M ResizeObserver 反馈循环防护
- SkillsTab.vue — M onMounted 始终 fetchSkills

文档修复（5 High + 6 Medium）：
- portal-platform-security-reliability-fixes.md — D2 测试路径 / D3 Root Cause+Impact 章节 / D4 severity: mixed / 标题中文化 / 12 处绝对路径转相对 / P2 #12 数字口径
- AGENTS.md — D5 路由表 22→28 / 专家模板 5→15 / LiteLLM U15 迁移 / 配置查找 fallback
- README.md — 8 处端口 8000→8001

新增测试：
- tests/unit/calendar/test_calendar_tool.py — ponytail 自检断言

验证：
- ruff check (5 文件) — All checks passed
- vue-tsc --noEmit — exit 0
- git stash baseline 验证 — portal 17 个 401 失败为预存在问题

已知限制（预存在）：
- 17 个 portal 测试 401 失败 — 需另起 ce-debug 调查
- README.md 7 处 CostAwareRouter 引用过时 — 文档同步另起任务
 2026-06-28 15:06:41 +08:00
chiguyong 43e9025c6d fix(calendar): 日历能力缺失修复 + UI 布局优化 + 会话404处理 
P0: calendar_tool reminder_rules 未传入 create_event，提醒功能完全失效。P1: chat.ts deleteConversation 未清理 pending + 404 递归保护。P2: app.py 系统提示重复段落 + gui_mode F821 + SystemMonitorPanel flex 布局。P3: portal send_json 快照 + WS connected 清除 is_local + 移除死代码。验证: ruff+pytest 98passed+typecheck 通过。
 2026-06-28 14:24:58 +08:00
chiguyong 567cbc9c9b refactor: simplify code across U1-U7 (bug fix + efficiency + reuse + quality) 2026-06-24 22:35:52 +08:00
chiguyong fa152e24ac feat(skills): add progressive skill loading with disclosure_level=0 (U5) 
When disclosure_level=0, system prompt only injects skill name + description
(summary mode). SkillDetailTool is injected into the tool set, allowing the
LLM to load full instructions on-demand via skill_detail(query). This reduces
context window consumption when many skills are registered.
 2026-06-24 21:49:00 +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
TraeAI d245f2e3d8 fix: UI/UX 修复 + 暗色主题 + async generator 防御 
- App.vue: 重构 bootstrapBackend 流程，新增 retryBootstrap 重试入口
- SplashScreen.vue: 错误状态显示「重试」按钮
- system.py: /system/resources 移除 SYSTEM_CONFIG 权限依赖，避免 dev 模式 401
- react.py + gateway.py: 新增 _ensure_async_iterable helper 防御
  'async for requires aiter, got coroutine'
- theme.ts: Ant Design colorTextLightSolid 映射到 --text-inverse
  修复暗色主题下所有 primary 按钮白底白字
- ChatSidebar.vue: 新建对话按钮兜底深色文字
- SystemMonitorPanel.vue: 服务状态区域间距优化
- chat.ts + portal.py + sqlite_conversation_store.py: 会话标题派生修复
  解决点击对话标题变成"对话"的问题
- app.py: Serve 模式自动创建 default agent
- Tauri src-tauri/: 完整 Tauri 客户端配置 (icons, capabilities, Cargo)
 2026-06-20 23:35:57 +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 b4ba65b9ca fix(gui): 修复启动报错和对话列表不正确的两个关键Bug 
Bug1: 'async for' requires __aiter__ method, got coroutine
- EventQueue.subscribe() 在 _closed=True 时直接 return，
  Python 将其视为协程而非异步生成器
- 修复: 添加不可达的 yield 语句，确保函数始终为异步生成器

Bug2: 启动时对话列表全显示"对话"，无法识别之前的对话
- list_conversations() 不加载消息，_derive_conversation_title
  遍历空 messages 列表导致标题全为"对话"
- 修复: list_conversations 从 SQLite 加载首条用户消息用于标题推导

Bug2b: WebSocket 不响应前端对话切换
- conv 变量只在首条消息时设置，之后忽略 conversation_id
- 修复: 每条消息都检查 conversation_id，切换时更新 conv
 2026-06-18 16:26:02 +08:00
chiguyong 200174c5c7 feat: SQLite persistence, verification loop, spec-driven execution 
Phase 2 of architecture optimization (U5/U6/U9):

- U5: SqliteConversationStore with WAL mode + LRU cache (1000 convs)
  Replaces in-memory ConversationStore in portal.py
  Data survives server restarts (ref: Codex Thread persistence)
- U6: VerificationLoop with verify/verify_and_retry
  Default commands: pytest + ruff check
  ReActEngine integration via verification_enabled flag
  New run_tests tool for LLM to invoke verification
- U9: SpecManager for plan-as-contract (ref: Qoder Quest Mode)
  Plans persisted to .agentkit/specs/{spec_id}.yaml
  API: GET/PUT /api/v1/specs, POST /api/v1/specs/{id}/confirm
  PlanExecEngine emits spec_created event after plan generation

Also fixes: portal skill_name routing, app.py SessionManager guard,
test_telemetry CostAwareRouter removal, test_compression_config fixture
 2026-06-17 10:45:20 +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 f99b3517d9 fix(review): apply code review fixes from ce-code-review 
- P1: Use _resolve_execution_mode() instead of hardcoding SKILL_REACT
  in semantic_low_complexity, semantic_high, and merged_llm paths
- P1: QualityGate escalation uses name-based check (c.name) instead
  of identity check (c is) for robustness
- P2: Remove tautological complexity >= 0.3 in short_text_llm_hint
- P2: Add empty query guard in SemanticRouter.route()
- P2: Upgrade debug → warning log level for low-complexity fallback errors
- P2: Validate skill_hint against _SKILL_NAME_RE in _classify_merged
- P2: Rename has_high_signal → has_non_low_signal for clarity
 2026-06-16 00:24:14 +08:00
chiguyong 11e2009cb8 feat(router): improve colloquial/mixed-lang routing, fix low-complexity IntentRouter bypass 
Key improvements:
- Low-complexity queries (<0.3) now try IntentRouter keyword match
  before falling back to DIRECT_CHAT, fixing 0% F1 on keyword_match
- SemanticRouter similarity_low lowered from 0.6 to 0.4
- Short text (<20 chars) uses effective_low = max(0.25, low - 0.15)
- Short text with no semantic match forces LLM classify fallback
- Added colloquial keywords to 7 skill YAMLs
- Fixed code_reviewer.yaml output_schema placement
- Fixed SemanticRouter build in e2e tests
- Fixed base_url detection for bailian-coding API keys

Results: keyword_match F1 0->60.87%, colloquial F1 0->100%, mixed_lang F1 0->100%
 2026-06-15 23:54:57 +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 0ccef7be5c feat: P0 production hardening — LLM cache, semantic routing, state persistence 
U1: LLM Cache Core (exact + semantic match, InMemory + Redis backends)
U2: Cache integration into LLMGateway with CacheConfig
U3: Semantic Router as Layer 1.5 in CostAwareRouter
U4: UsageStore persistence (Redis Hash + InMemory fallback)
U5: CascadeStateStore persistence (Redis INCR + InMemory TTL)
U6: EvolutionStore interface unification (Protocol + PostgreSQL backend)
U7: Configuration integration + E2E tests

Code review fixes:
- P0: date iteration bug (day>=28), semantic router index never built,
      Redis connection leak (per-call → persistent pool)
- P1: cache degradation recovery, semantic_search degradation,
      double miss counting, asyncio.Lock for PG init, LIMIT on queries,
      __import__ anti-pattern → _utcnow()
- P2: InMemory TTL cleanup, embedding preservation on put(),
      data TTL = max(exact_ttl, semantic_ttl)
 2026-06-14 15:16:00 +08:00
chiguyong 5ef08a3b30 fix(review): comprehensive P0-P2 code review fixes 2026-06-12 22:18:25 +08:00
chiguyong 2e55aae775 fix(review): address code review findings for speed optimization 
- P0: Rename WAL buffer to pending buffer, add crash-loss warning
- P1: Fix keyword substring false matches with word-boundary regex
- P1: Pass connection pool params in _build_llm_config
- P1: Change parallel_tools default to False (safer default)
- P1: Add classifier value validation in CostAwareRouter
- P2: Replace __import__ with proper datetime import
- P2: Add max_buffer_size enforcement in AsyncWriteQueue
 2026-06-12 13:21:44 +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 2110c84fb6 fix: switch default model to qwen3-coder-plus for better function calling 
DeepSeek-chat has limited/partial function calling support. Qwen3-coder-plus
(DashScope) has robust OpenAI-compatible function calling.

Also added tool usage instructions to system prompt and enhanced logging
to trace tool propagation through the pipeline.
 2026-06-12 09:27:52 +08:00
chiguyong 44f19fcf14 feat: loading animation + tool descriptions in system prompt 
1. Loading indicator: three-dot bouncing animation appears after
   sending a message and disappears when server starts responding.

2. Tool descriptions: resolve_skill_routing now appends available
   tools (name + description + parameters) to the system prompt so
   the LLM knows what tools it can call.
 2026-06-11 22:25:21 +08:00
chiguyong cc4c6fe346 fix: direct-mode agent falls through to default when task needs tools 
When IntentRouter matches a direct-mode agent (no tools), but the task
content suggests tool needs (shell, search, file ops, etc.), the routing
now falls through to the default agent which has full tool access.

This fixes the issue where "帮我执行个命令" would be routed to
direct_agent and fail because direct mode doesn't support tool calling.

Also restored "你好" in direct_agent keywords since it's correctly
handled now — greetings don't need tools, direct mode is fine.
 2026-06-11 15:26:19 +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 cc2cd414c9 fix: resolve all code review issues from cross-validation 
1. Critical: Add missing TaskResult import in plan_exec_engine.py
2. Critical: Fix ReWOOEngine param name (max_steps → max_plan_steps)
3. Major: Remove duplicate token counting in reflexion.py
4. Major: LLM audit failure now passes (trusts rule check) instead of failing
5. Major: Fix dict iteration with del using list() copy in lifecycle.py
6. Major: Fix Chinese content tokenization using regex split instead of space split
7. Minor: _is_positive_mention now checks all occurrences, not just the first
 2026-06-11 06:22:35 +08:00
chiguyong bba394be38 fix(marketplace): address code review findings 
- Fix str.format() crash when user input contains curly braces
- Fix Layer 2 passing str to find_best_agent (expects list[str])
- Fix AlignmentGuard fail-open on LLM audit failure (now fail-closed)
- Fix _config_reload_lock not initialized in create_app()
- Fix evolve_soul redundant reflector.reflect() call (reuse existing reflection)
- Fix test mocks using AsyncMock for sync find_best_agent method
- Remove unused _COMPLEXITY_CLASSIFY_PROMPT constant
 2026-06-10 19:21:40 +08:00
chiguyong 8713636d50 feat(marketplace): add Phase B/C - CostAwareRouter, OrganizationContext, AlignmentGuard, Soul Evolution, Auction, Server Integration 
Phase B:
- U1: CostAwareRouter with 3-layer routing (rule/LLM/capability matching)
- U6: OrganizationContext with agent profiles and capability-based discovery
- U7: AlignmentGuard with constraint injection and cascade detection

Phase C:
- U8: Soul dynamic evolution with version tracking and reflection-triggered updates
- U9: Auction mechanism as optional advanced routing mode
- U10: Server integration + end-to-end integration tests

250 new tests passing across all units.
 2026-06-10 19:09:02 +08:00
chiguyong 31bd3b126c feat(phase8): chat adaptive enhancements, pipeline reflection, search tools upgrade 
- Enhanced chat CLI with adaptive mode and session management
- Added pipeline reflection and schema extensions
- Upgraded BaiduSearch and WebSearch tools with advanced capabilities
- Expanded server routes for skills and chat
- Added session store enhancements
- New chat module and pipeline reflection support
 2026-06-09 23:18:06 +08:00