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
c62d435c43
Merge branch 'feat/portal-platform-evolution' — portal platform evolution (U1-U17 + RAG + channels + LiteLLM + ce-code-review fixes + ce-compound doc)
Deploy to Production / deploy (push) Waiting to run
Details
2026-06-26 01:48:19 +08:00
75e9b58e46
docs(ce-compound): 记录 portal-platform 安全/可靠性修复批次
...
记录 ce-code-review 修复批次（commit 53faa60）的 10 个 P1/P2/P3 修复：
- P1: WeCom 重放、缓存跨用户泄漏、webhook 异常风暴、shutdown 泄漏
- P2: Feishu TTL、无界任务集、配额 N+1、冗余 SHA-256、未用参数
- P3: DIRECT_CHAT 去重
新增 docs/solutions/security-issues/portal-platform-security-reliability-fixes.md
CONCEPTS.md 补充 3 个领域术语：Per-User Cache Namespace、Webhook Signature Freshness、Webhook Backpressure
2026-06-26 01:47:57 +08:00
53faa60472
fix(review): ce-code-review P1+P2 修复 — 安全/可靠性/性能
...
P1 安全与可靠性（4 项）：
- wecom: verify_signature 增加时间戳新鲜度校验（5 分钟窗口防重放）
- cache: should_cache 在 per_user_namespace 开启时拒绝 user_id=None
匿名请求，避免跨用户缓存泄漏（安全要求 a/e）
- channels: webhook receive_message 异常兜底，防止 500 触发平台重试风暴
- app: shutdown 调用 close_all_adapters + await _pending_webhook_tasks，
防止 httpx 连接泄漏和丢失 IM 回复
P2 效率与可维护性（5 项）：
- feishu: _TOKEN_CACHE_TTL 300 → 6900（2h 减 5min 余量，避免 24x 过频刷新）
- channels: _pending_webhook_tasks 有界化（2x 并发上限时 429 拒绝）
- gateway: quota 检查每 period 单次 get_usage，复用 summary 检查 token+cost
- cache_key: generate_cache_key 合并为单次 SHA-256（消除 8-10 次冗余哈希）
- config: ProviderConfig.get_api_key 移除未用的 secrets_store 参数
P3 去重（1 项）：
- channels: _process_inbound_message DIRECT_CHAT 路径提取 _direct_chat 辅助函数
测试：
- test_wecom: 时间戳改用 int(time.time())，新增 test_expired_timestamp_rejected
- test_cache: should_cache 测试覆盖匿名拒绝 + namespace_off 兼容
- test_config_migration: get_api_key 测试适配新签名
- channels/config_migration/quota_enforcement 测试全部通过
2026-06-26 01:40:31 +08:00
1ccaf56b9a
refactor: ce-simplify-code 审查修复 — 去重 + 效率 + 死代码清理
...
3 个审查代理（复用/质量/效率）发现 15 个问题，全部修复：
效率与安全（6 项）：
- MCPClient 缓存 MultiServerMCPClient 单例 + aclose()，修复连接/子进程泄漏
- _rate_limits 清理空 IP 条目，修复 X-Forwarded-For 欺骗下内存泄漏
- _seen_nonces 改用 OrderedDict，O(1) 摊销过期清理
- webhook 后台任务加 Semaphore(20) + 任务引用追踪，限制无界并发
- _build_adapter 用 asyncio.gather 并行解密 secrets
- 适配器实例缓存（_adapter_cache），token TTL 缓存跨请求命中
去重（4 项）：
- header_get 提取到 channels/base.py，4 个适配器统一 import
- _get_client/close() 移入 MessageAdapter 基类，子类继承
- URLVerificationChallenge 统一到 base.py，feishu/slack/wecom 共用
- Transport ABC 添加 endpoint_url 属性，from_transport 不再访问私有字段
死代码与类型安全（5 项）：
- detect_cache_hit 死方法替换为 record_cache_result 公开 API
- execution_mode.value == "direct_chat" 改用枚举比较
- 删除 yielded_any 死变量、重复 from fastapi import Request、
多余 getattr 防御
453 tests passed, ruff clean（预存 F841 非本次引入）
2026-06-25 23:54:14 +08:00
793476cafa
feat(llm): U17 — LiteLLM 语义缓存替换 + per-user/ACL scope 安全隔离
...
- 新增 LitellmCacheManager：配置 litellm.cache 全局，三级后端 fallback
(RedisSemanticCache -> RedisCache -> InMemoryCache)，redisvl lazy import
- cache_key 扩展 user_id + kb_acl_hash 参数（安全要求 a/b/e）
- gateway 集成：读取 KB caching_disabled flag（安全要求 c），构建带 scope
的 cache_key，命中时 cost=0
- LLMResponse 新增 cache_hit 字段；LLMRequest 新增 cache 参数
- litellm_provider 透传 cache 参数 + 检测 _hidden_params 缓存命中
- 33 个新测试覆盖 13 场景（含 User A != User B 缓存隔离）
- 旧 InMemoryLLMCache/RedisLLMCache 保留向后兼容
2026-06-25 22:49:59 +08:00
86541d7172
feat(mcp): U16 — langchain-mcp-adapters client replacement + transport deprecation
...
- 重写 MCPClient：URL scheme 自动检测（stdio/http/sse）→ langchain config
- 旧 Transport 注入路径保留（DeprecationWarning），向后兼容
- transport.py 模块级弃用警告
- 28 个新测试覆盖 URL 检测、list_tools、call_tool、legacy 路径、ImportError
- 修复 manager.py / transport.py 预存 F401/F841
2026-06-25 22:04:37 +08:00
069dbc22b1
feat(llm): U15 — LiteLLM unified provider + api_key encrypted secrets migration
2026-06-25 21:41:15 +08:00
13c516a54f
feat(mcp): U14 — Skill/Team MCP publish with admin auth + dangerous-tool opt-in
2026-06-25 21:10:06 +08:00
16c33be295
feat(mcp): U13 — refactor MCPServer to route factory + mount at /api/v1/mcp with auth
2026-06-25 20:58:41 +08:00
8998f94c42
feat(channels): U12 — DingTalk/WeCom/Slack adapters + multi-channel webhook dispatch
2026-06-25 20:45:43 +08:00
4b58e8f661
feat(channels): U11 — Feishu IM adapter end-to-end (webhook + signature + AES-CBC decrypt + chat integration)
2026-06-25 20:24:21 +08:00
5572387c01
feat(channels): U10 — message adapter ABC + AES-256-GCM secrets store + channel CRUD routes
2026-06-25 20:13:37 +08:00
af96cb49bd
docs(plan): deepen portal platform evolution plan — KTD5/7/8/9 expanded, KTD11 added
2026-06-25 20:13:27 +08:00
864bb95a30
feat(server): wire rag_platform components to app.state lifespan
...
Initialize in lifespan() (after bitable, before yield):
- KBStore + ensure_tables() → app.state.kb_store (if database_url available)
- RetrievalEngine + vector_store → app.state.retrieval_engine (if database_url available)
- HitProcessor → app.state.hit_processor (with llm_gateway)
- TaskManager → app.state.task_manager (degraded mode, InMemoryTaskStore)
- KBSettingsStore → app.state.kb_settings_store (singleton)
Each component wrapped in try/except — failures logged but don't block startup.
Follows same pattern as episodic memory initialization.
2026-06-25 20:02:01 +08:00
1f691ca178
feat(frontend): U9 — KB management extension with segment preview, status display, settings
...
New: SegmentPreview.vue, KBSettings.vue
Extended: DocumentUpload.vue (status badges, retry, preview), SearchTest.vue (3 modes), SourceConfig.vue (ACL), KnowledgeBaseView.vue (settings + task history tabs)
API+Store: kb.ts new types/methods, knowledge.ts new state/actions
typecheck: passed
2026-06-25 13:14:58 +08:00
e3ae2f3a56
feat(rag_platform): U8 — TaskIQ async task integration
...
Add tasks.py: TaskManager with vectorize/batch_index tasks, per-user concurrency limits, degraded mode (sync execution without broker), WorkerSweeper for timeout detection, error message sanitization
Add taskiq>=0.11 and taskiq-redis>=0.5 to pyproject.toml
Task parameter schema validation (VectorizeTaskParams, BatchIndexTaskParams)
Tests: 41 new tests, 289 total passing
2026-06-25 12:58:51 +08:00
d026a91f43
feat(rag_platform): U6 — hit processing mode + KB settings
...
Add hit_processing.py: HitProcessor with model_opt (LLM-generated) and direct (concatenated chunks) modes, with in-process cache
Add settings.py: KBSettings/KBSettingsUpdate models, KBSettingsStore with async CRUD
Add KB settings endpoints to kb_management.py: GET/PUT /kb-management/kbs/{kb_id}/settings with owner-only modification
Tests: 43 new tests (25 hit_processing + 18 settings), 293 total passing
2026-06-25 12:44:47 +08:00
5c562dbff3
feat(rag_platform): U5 — rerank + question generation + termbase
...
Add rerank.py: Reranker with Cohere/BGE provider support, data export risk annotation, graceful degradation
Add question_gen.py: LLM-based question generation following ContextualChunker pattern, with caching
Add termbase.py: jieba custom dictionary management, add/remove/load terms
Tests: 58 new tests (14 rerank + 19 question_gen + 25 termbase), 205 total passing
2026-06-25 12:31:43 +08:00
fb9f16d6e5
feat(rag_platform): U4 — dual-index retrieval (pgvector semantic + PG fulltext jieba)
...
Add fulltext.py: jieba tokenization + tsvector write/query
Add retrieval.py: RetrievalEngine with embedding/keywords/blend modes
Update models.py: add RetrievalRequest model
Tests: 35 new tests, 147 total passing
2026-06-25 12:20:48 +08:00
3f9588e673
feat(rag_platform): U3+U7 — rewrite upload endpoint with sanitization + pipeline
...
Rewrite upload_document() to use rag_platform sanitize + DocumentProcessor:
- File type whitelist validation (8 allowed types, reject .exe/.sh)
- File size limit (50MB) + zip bomb detection for ZIP-based formats
- DocumentProcessor.parse() (with content sanitization) + segment()
- Return chunks preview, status="segmenting" (pending vectorization)
Add POST /kb-management/documents/preview endpoint:
- Pre-upload preview with adjustable chunk_size/chunk_overlap
- Same security validation as upload, no document record created
Add POST /kb-management/documents/{id}/vectorize placeholder:
- Returns 503 — full async vectorization deferred to U8 (TaskIQ)
Test: update test_upload_document assertion (status "indexed" → "segmenting")
2026-06-25 12:06:16 +08:00
b55c896794
feat(rag_platform): U3+U7 — document processing pipeline + upload security
...
U3: Document processing pipeline (document_processor.py)
- DocumentProcessor class wrapping parse → segment → vectorize
- parse() uses memory/document_loader.py for multi-format extraction
- segment() uses LlamaIndex SentenceSplitter
- preview() returns chunks for read-only preview (no vectorization)
- vectorize() embeds chunks and stores in pgvector (all-or-nothing)
- process() orchestrates full pipeline with status transitions:
pending → parsing → segmenting → vectorizing → indexed | failed
U7: Upload security & content sanitization (sanitize.py)
- ALLOWED_FILE_TYPES whitelist (pdf/docx/xlsx/pptx/txt/md/csv/html)
- MAX_FILE_SIZE 50MB limit
- validate_file_type() / validate_file_size() guards
- check_zip_bomb() for ZIP-based formats (ratio > 100:1 or > 500MB)
- check_image_bomb() for pixel count > 100MP (PNG/JPEG/GIF header parsing)
- is_safe_ip() SSRF protection (loopback/RFC1918/link-local/ULA denied)
- sanitize_markdown() removes dangerous HTML tags (script/iframe/object/embed)
- sanitize_content() main entry point for text format sanitization
- parse_xml_safe() XXE protection (forbid_dtd/forbid_entities/forbid_external)
Preview API (preview.py)
- PreviewChunk / PreviewResult Pydantic models
- generate_preview() returns read-only segmentation preview
Tests: 112 tests passing (45 new + 67 existing)
- test_sanitize.py: file type/size, markdown sanitization, SSRF, zip/image bomb
- test_document_processor.py: parse/segment, preview, vectorize, failure status
2026-06-25 11:21:42 +08:00
c1a21f57a1
feat(rag_platform): U2 — KB persistence + per-KB ACL
...
Add PostgreSQL-backed KB store replacing in-memory KnowledgeSourceStore:
- models.py: ORM models (KBModel, DocumentModel, KBAclModel) using
SQLAlchemy 2 DeclarativeBase + Mapped style
- store.py: KBStore with async CRUD for KBs and documents,
create_kb creates owner ACL in same transaction
- acl.py: filter_kb_by_user_acl(), grant_access(), revoke_access(),
list_acl() — follows filter_kb_sources_by_department pattern
Schema: rag_platform_kbs, rag_platform_documents, rag_platform_kb_acl
with FK CASCADE on kb_id. UniqueConstraint on (kb_id, user_id).
Tests: 23 unit tests covering KB CRUD, document operations, ACL
filtering, grant/revoke. All 37 rag_platform tests pass.
2026-06-25 11:01:04 +08:00
27d0184392
feat(rag_platform): U1 — RAG platform skeleton + LlamaIndex integration
...
Create src/agentkit/rag_platform/ module with:
- models.py: Pydantic domain models (KB, Document, Chunk, QueryResult)
- indexing.py: PGVectorStore wrapper with explicit table name
(rag_platform_kb_chunks) for schema isolation from episodic_memory
- pipeline.py: RAGPipeline wrapping LlamaIndex IngestionPipeline
(SentenceSplitter + embedding + vector store)
Add dependencies: llama-index-core, llama-index-vector-stores-postgres,
llama-index-embeddings-openai, pgvector, jieba.
Tests: 14 unit tests covering models, indexing (URL conversion, table
name isolation, embed_dim), and pipeline (ingest, query, chunk params).
2026-06-25 10:49:35 +08:00
22c89763e2
docs: add long-horizon reliability fixes learning + scrub CONCEPTS.md
...
- New solution doc: logic-errors/long-horizon-reliability-code-review-fixes.md
Documents 13 code-review fixes (2 P0, 5 P1, 6 P2) across U1-U7
long-horizon reliability features (disclosure_level default, resume
plan_id mismatch, middleware dataclass compat, state offload readback,
checkpoint dedup, dynamic phase persistence, debate count restore,
loop detection reset, concurrent resume lock, FAILED phase handling,
checkpoint cleanup, offload type guard).
- CONCEPTS.md: add Expert Orchestration cluster (Disclosure Level,
State Offloading, Pipeline Checkpoint, Debate Phase, Resume).
Scrub Bitable entries to remove implementation specifics per
vocabulary rules (API paths, library calls, SQL syntax, class names,
enum values).
2026-06-25 02:40:22 +08:00
71eaf8dc7c
docs: add bitable security/reliability patterns solution doc + CONCEPTS.md
...
Deploy to Production / deploy (push) Has been cancelled
Details
- docs/solutions/architecture-patterns/bitable-companion-service-security-reliability-patterns.md
Knowledge-track doc capturing 10 security/reliability patterns from the
bitable companion service (SSRF prevention, SQL injection, IDOR, atomic
task claiming, cache invalidation, composite cursor, batch ops, async
I/O safety, OOM prevention, internal token auth)
- CONCEPTS.md
Seeded with 3 core domain nouns: Bitable, Field Ownership, Recalc
- AGENTS.md
Added discoverability tips for docs/solutions/ and CONCEPTS.md
2026-06-25 01:25:06 +08:00
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
567cbc9c9b
refactor: simplify code across U1-U7 (bug fix + efficiency + reuse + quality)
2026-06-24 22:35:52 +08:00
0847c0e086
fix(checkpoint): add TTL expiration for memory fallback mode
...
内存降级模式之前没有 TTL 过期机制，长期运行进程会导致内存泄漏。
现在 list_checkpoints 和 load_plan 在内存模式下会过滤/清除过期数据。
- list_checkpoints: 内存降级分支过滤过期 checkpoint
- load_plan: 内存降级分支检查 TTL 过期，过期则清除并返回 None
- 新增 _is_expired 方法检查 saved_at 是否超过 TTL
- _memory_plans 类型改为 tuple(plan_dict, timestamp) 以支持 TTL
- 新增 5 个 TTL 过期测试覆盖内存模式和 Redis 降级场景
2026-06-24 22:04:55 +08:00
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
dfd188b1a4
feat(orchestrator): add pipeline checkpoint and crash recovery (U7)
...
Add PipelineCheckpoint for stage-level crash recovery with Redis-first
+ memory fallback. TeamOrchestrator saves checkpoints after each phase
finalizes and supports resume(plan_id) to continue from the last
completed phase. New POST /api/v1/tasks/{id}/resume endpoint recreates
the team from saved plan and calls resume.
2026-06-24 21:04:18 +08:00
3dfda904d7
feat(core): add middleware pipeline architecture with onion model
...
U6: Unified middleware protocol (before/after) with MiddlewareChain
implementing onion model execution. Parallel integration (KTD1) —
middleware path controlled by presence of middleware_chain parameter,
existing ReActEngine path unchanged when None.
- New core/middleware.py: RequestContext, Middleware protocol,
MiddlewareChain (onion model: before outer→inner, after inner→outer)
- 3 example middlewares: SummarizationMiddleware (U3 headroom compression),
TokenUsageMiddleware, LoopDetectionMiddleware (request-level audit)
- ReActEngine.__init__ accepts middleware_chain parameter
- execute() branches: middleware path when chain present, existing path otherwise
- 22 tests covering ordering, error handling, state passing, backward compat
2026-06-24 20:52:15 +08:00
ef84e3fd53
feat(experts): add SharedWorkspace state offloading for long-horizon runs
...
U4: ExpertTeam accepts redis_client, passes to SharedWorkspace. After phase
completion, full result is written to workspace and in-memory phase.result
is replaced with a 500-char summary + _ref_key. Dependency output reading
resolves offloaded content from workspace on demand, with graceful fallback
to summary on read failure.
Tests: 8 scenarios (offload creation, short content, dependency resolution,
workspace failure fallback, non-offloaded passthrough, redis_client wiring,
memory dict fallback, pipeline integration) — all pass.
2026-06-24 20:32:10 +08:00
122173ec2c
feat(core): add headroom-based compression trigger
...
U3: ContextCompressor now accepts model_context_limit, headroom_threshold,
and min_tokens. should_compress() triggers when token ratio exceeds 0.8 of
model limit OR exceeds min_tokens (8000 fallback). ReActEngine._should_compress
delegates to compressor when available, checks is_available() first.
Tests: 6 scenarios (headroom trigger, min_tokens guard, small model,
unavailable compressor, delegation, fallback) — all pass.
2026-06-24 20:28:14 +08:00
717aad1303
feat(experts): add concurrency limit to TeamOrchestrator parallel phases
...
U2: Add asyncio.Semaphore to bound concurrent phase execution and debate
argument generation. Default limit=3, configurable via max_concurrent_phases.
Prevents LLM rate-limit spikes when many phases run in the same layer.
Tests: 5 scenarios (happy path, 5-phase edge case, serial mode, failure
release, debate integration) — all pass.
2026-06-24 20:23:30 +08:00
018b342d96
feat(react): add loop detection to prevent repeated identical tool calls
...
U1: Sliding window hash detection in ReAct loop. When the same tool is
called with identical arguments >= threshold times (default 2), injects
a correction message first, then raises LoopDetectedError if the LLM
doesn't change strategy. Covers both _execute_loop and execute_stream.
2026-06-24 20:12:35 +08:00
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
20a4c55d5b
feat(skills): SkillHarness 前置条件 + 风险守卫学习增强
...
- cli/skill.py: skill learn 子命令增强
- evolution/risk_guard_learner.py: 风险守卫学习改进
- memory/models.py: 记忆模型扩展
- skills/base.py + loader.py: SkillHarness 前置条件支持
- 对应测试更新
2026-06-24 18:56:51 +08:00
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
6016c087fe
feat(cli): U6 CLI 协同事件 Rich 渲染
...
- chat.py 新增 _render_collaboration_contracts 和 _render_pm_collaboration_event
- 4 种 PM 协同事件渲染：
collaboration_contract_defined (cyan Panel)
collaboration_notice (蓝→品红 文本)
review_result (passed=green / failed=red Panel)
risk_flagged (yellow Panel)
- plan_update 中提取 collaboration_contracts 并渲染
- _print_help 更新项目经理模式说明
- 优雅降级：字段缺失回退到 ?，空契约不输出，整体 try/except 不中断编排
- 新增 11 个测试（TestPMCollaborationRendering 9 + TestPrintHelpPMMode 2）
- ruff 通过，pytest 23 passed
2026-06-24 14:57:49 +08:00
34a4164430
feat(frontend): U5 前端协作关系图 + 验收/风险卡片
...
- types.ts 新增 ICollaborationContract/ICollaborationNotice/IReviewResult/IRiskFlag 等接口
- chat.ts 新增 collaborationState ref，处理 4 种协同事件
(collaboration_contract_defined/collaboration_notice/review_result/risk_flagged)
并在 plan_update 中提取 contracts，team_formed/dissolved 清理状态
- CollaborationGraphCard.vue SVG 协作关系图：
圆形布局节点（专家首字），实线=契约，虚线动画=数据流向
节点颜色编码验收状态（绿=通过，红=返工/失败），橙色!标记风险
- ReviewResultCard.vue 验收结果卡片（passed/failed + feedback）
- RiskFlagCard.vue 风险标记卡片（专家 + 风险描述）
- useMessageRenderer.ts 新增 3 个视图类型和渲染规格
- index.ts 导出 3 个新组件
- 遵循 U5 辩论可视化 BoardState 模式
- typecheck 通过
2026-06-24 14:42:00 +08:00
5487cca199
feat(experts): U4 专家风险标记 + risk_flagged 事件
...
- orchestrator 新增 _parse_risk_flags 静态方法，正则解析 [RISK: ...] 标记
- _execute_execution_phase 在协作通知后、验收前解析风险标记
- 风险标记通过 risk_flagged 事件广播，供前端/CLI 渲染
- 无风险标记时行为不变，向后兼容
- 新增 TestRiskFlagging 7 个测试（单/多/无/格式错误/事件发出/内容/兼容）
2026-06-24 14:17:58 +08:00
62fcbc0feb
feat(experts): U3 Lead 验收环节 + 返工机制
...
- PlanPhase 添加 rework_count 和 review_feedback 字段
- 添加 _review_phase_output 方法，Lead 用 LLM 验收阶段输出
- _execute_execution_phase 重构为返工循环（MAX_REWORKS=2）
- 验收通过/返工/失败三种路径，发出 review_result 事件
- LLM 不可用时优雅降级直接通过
- 6 个新测试，全套 449 passed 无回归
2026-06-24 14:09:18 +08:00
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
c46cf06f6d
feat(experts): U2 协作契约执行 — 专家可见 + 主动通知
...
- _execute_execution_phase 按协作契约读取相关专家输出（可见性）
- 添加 _notify_collaborators 方法，完成后通知相关专家（可协助）
- 发出 collaboration_notice 事件，契约状态更新为 delivered
- 7 个新测试，全套 443 passed 无回归
2026-06-24 13:54:38 +08:00
f219c5f016
feat(experts): U1 协作契约数据模型 + Lead 生成契约
...
- PlanPhase 添加 collaboration_contracts 字段（CollaborationContract dataclass）
- 修改 _decompose_task prompt，要求 Lead 分解任务时定义协作契约
- 修改 _parse_phases 解析 LLM 返回的协作契约信息
- plan_update 事件自动包含协作契约（通过 to_dict 序列化）
- 71 + 9 = 80 个新测试，全套 436 passed 无回归
2026-06-24 13:44:50 +08:00
0957afb0a2
Merge branch 'test/calendar-e2e' into main
...
Deploy to Production / deploy (push) Waiting to run
Details
Calendar E2E testing: 5-layer test plan + 8 Playwright e2e tests + config fixes.
- Layer 2: Wire calendar router into app.py (was missing)
- Layer 3: 7 integration tests (lifecycle, recurrence, tags, types, invitations, permissions, ICS)
- Layer 4: 8 Playwright e2e tests (E1-E8, all passing)
- Config: JWT secret + rate_limit fix for e2e test environment
2026-06-24 13:22:11 +08:00
59e47c5871
test(calendar): 8 Playwright e2e tests + config fixes (JWT secret, rate limit)
...
E2E tests (calendar.spec.ts):
- E1: panel loads, shows empty state
- E2: create event via UI, verify in panel
- E3: switch between calendar/card/list views
- E4: edit event title via UI
- E5: delete event via API, verify removal from UI
- E6: create event with tag via UI (keyboard.type for Ant Select)
- E7: recurring event displays multiple occurrences
- E8: invitation manager button accessible
Config fixes (playwright.config.ts):
- Set AGENTKIT_JWT_SECRET so AuthMiddleware can verify login tokens
(without it, get_jwt_secret() returns None → 401 on all API calls)
- Call create_app(rate_limit=10000) explicitly instead of uvicorn
factory=True — factory mode lets server_config.rate_limit (60, from
agentkit.yaml) override the env var, causing 429 rate limiting
- Use .venv/bin/python instead of system python3 (missing deps)
All 8 tests pass (47s).
2026-06-24 13:17:53 +08:00
b86100a0a1
feat(cli): U6 CLI 多 Agent 入口 + 辩论 Rich 渲染
...
- 新增 _execute_team_cli() 处理 @team 前缀，运行 ExpertTeam 流水线
- Rich 事件渲染：team_formed/plan_update/phase_*/debate_*/team_synthesis
- 干预循环使用 select.select() 非阻塞轮询 stdin（Unix-only，ponytail 标注）
- 支持 /debate 手动触发辩论、/stop 终止团队、纯文本作为上下文注入
- 扩展 _print_help() 增加 Multi-Agent 与 Interventions 说明
- 新增 12 个单元测试覆盖路由、帮助文档、函数返回值、干预基础设施
2026-06-24 13:03:57 +08:00
49b483b933
feat(frontend): U5 前端辩论可视化
...
前端展示辩论过程，专家交锋有独立气泡样式，裁决结果清晰可见。
类型 (api/types.ts):
- WsServerMessage 新增 5 个辩论事件：debate_started / expert_argument /
debate_round_summary / debate_resolved / team_intervention_ack
- IChatMessage.message_type 新增 4 个辩论消息类型
- IChatMessage 新增 7 个可选辩论字段（topic/round/decision 等）
- 新增 4 个数据接口
Chat Store (stores/chat.ts):
- 新增 debateState ref（topic/participants/round/status）
- WS switch 新增 5 个 case，复用 appendMessage/appendStep 模式
- 辩论结束 1s 后清空 debateState（与 board_concluded 一致）
渲染器 (useMessageRenderer.ts):
- MessageViewType + resolveMessageType 新增 4 个辩论视图类型
- useMessageRenderer 新增 4 个 render spec
新组件 (messages/):
- DebateBannerCard.vue — 辩论开始横幅（主题 + 参与专家 + 开场白）
- DebateArgumentCard.vue — 专家论点卡片（专家色边框 + 轮次标签）
- DebateSummaryCard.vue — 主持人轮次小结
- DebateConclusionCard.vue — 裁决卡片（按 decision 着色）
输入框 (ChatInput.vue):
- 团队模式下显示「辩论」按钮，点击弹出 prompt 输入主题
- 发送 /debate <topic> 命令（U4 WS 干预通道处理）
npm run typecheck 通过。
2026-06-24 12:37:37 +08:00
chiguyong