fischer
/
fischer-agentkit
1
0
Fork 0
Code Issues Pull Requests Actions 85 Packages Projects Releases Wiki Activity
407 Commits 1 Branch 0 Tags 22 MiB
Commit Graph

15 Commits

Author SHA1 Message Date
Chiguyong d3bd0d3b5f feat(auth): U4 — SSO 集成 (OIDC + SAML + SCIM + RBAC 审计) 
实现 U4 SSO 集成，按 R1a 多 IDP 信任边界（按 (idp_name, idp_subject)
主键关联，禁止邮箱合并）、R1b 过渡期手动 deprovisioning、R1c 单租户假设。

- OIDC 适配器 (authlib)：redirect flow + JIT 用户创建（KTD-2）
  GET  /auth/oauth/{provider}/redirect → IDP authorize
  GET  /auth/oauth/{provider}/callback  → token + userinfo + 关联本地用户
- SAML 适配器 (python3-saml)：ACS endpoint
  POST /auth/saml/{provider}/acs → 解析 NameID + JIT 用户创建
- IDPRegistry (idp_registry.py)：多 IDP 注册 + 热证书切换 + 健康隔离
- SCIM 2.0 minimal：bearer token 认证 + push 失败告警
  POST  /scim/v2/Users      (create)
  PATCH /scim/v2/Users/{id} (disable)
  GET   /scim/v2/Users       (filter/list)
- 手动 deprovisioning (R1b)：operator/admin RBAC + OTel 审计
  POST /admin/users/{user_id}/deprovision
  POST /admin/users/{user_id}/role        (RBAC 角色变更审计 KTD-8)
- AuthDB schema V5：user_idp_links + auth_audit_log（additive）
- middleware 白名单：auth/oauth/、auth/saml/、scim/v2/ 走前缀匹配

测试：31 个单元测试全部通过（OIDC 8 + SAML 7 + SCIM 9 + Audit 6 + 1 schema）
ponytail 简化：
- _StateCache 进程内 dict + TTL 5min（多实例需 Redis 共享 state）
- OneLogin_Saml2_Auth 同步解析走 asyncio.to_thread 避免阻塞
- SCIM alert 走 OTel span event（无独立告警通道）
- 邮箱冲突时使用 fallback 邮箱（@sso.{provider}.local）保留 UNIQUE 约束
 2026-07-06 04:15:02 +08:00
Chiguyong 60a58a0fdb feat(llm): U2 — Prompt Cache 全链路监控 + PII 脱敏 hook 
U2/R3 — Anthropic prompt cache 命中率监控 + 等保合规 PII 脱敏。

变更：
- protocol.py: TokenUsage 添加 cache_read/creation_input_tokens + cache_hit property
- providers/anthropic.py: 非流式 + 流式两处解析 cache 字段（cache_read_input_tokens / cache_creation_input_tokens）
- gateway.py: chat() / chat_stream() emit prompt_cache.hit / prompt_cache.miss OTel counter + span attributes
- telemetry/metrics.py: 新增 4 个 metric instruments（prompt_cache.hit/miss + pii_filter.coverage/redacted）
- llm/pii_filter.py（新文件）: 正则版 PII 脱敏（手机/邮箱/身份证/银行卡）+ ner_hook + fail-closed + sha256 hash 审计
- agentkit.yaml: 添加 fallbacks + pii_filter 配置模板（默认 disabled，等保场景按需启用）
- tests: test_prompt_cache_layers.py +4 cache metric 测试；test_pii_filter.py 新增 PII 脱敏测试（29 测试通过）

设计决策：
- PII 脱敏用 stdlib（re + hashlib），不引入 NER 依赖；ner_hook 接入客户内网 NER 模型
- 正则顺序 id_card 在 phone 之前（避免身份证号内 11 位数字子串被手机号误匹配）
- ner_hook 异常不吞掉：传播到 filter_pii 由 fail_closed 决定（True→PIIFilterError；False→降级正则版重试）
- fail-closed：脱敏失败拒绝发送（不降级到原文），等保合规要求
 2026-07-06 00:32:35 +08:00
Chiguyong d998c0344c feat(telemetry): U1 — OTel 默认启用，从 optional 升级为 required 依赖 
- pyproject.toml: 添加 opentelemetry-api/sdk/exporter-otlp-proto-grpc/
  instrumentation-fastapi 到 [project] dependencies（KTD-3）
- telemetry/{tracer,metrics,tracing,setup}.py: 移除 try/except ImportError
  静默回退 — 缺包现在是硬安装错误，不再是监控盲区。保留 except Exception
  处理运行时错误（OTLP 连接失败），保留 enabled=false 配置开关
- setup.py: 修复已存在 bug — MeterProvider 的 readers kwarg 在 OTel SDK 1.16+
  改名为 metric_readers（被 ImportError fallback 掩盖）
- agentkit.yaml: 取消 telemetry 段注释，设 enabled=true + otlp_endpoint +
  service_name + export_traces/metrics
- test_telemetry.py: 更新 test_missing_opentelemetry → test_enabled_initializes_otel_tracer；
  新增 TestSetupTelemetry smoke test（disabled/none 是 no-op，enabled instrument FastAPI）；
  清理 unused imports/vars

Verification:
- pytest tests/unit/test_telemetry.py: 21 passed
- pytest tests/unit/test_react_compression.py: 22 passed（_OTEL_AVAILABLE patch 兼容）
- runtime check: enabled=True → OTelTracer, enabled=False → NoOpTracer
 2026-07-06 00:18:09 +08:00
chiguyong 36b0296730 fix: 私董会数据持久化修复 + emoji 移除计划 
- 修复 board_started/expert_speech/round_summary/board_concluded 事件持久化
- 添加 is_board 标记到会话列表和详情接口
- 实现 restoreBoardStateFromMessages 从持久化消息恢复 boardState
- 添加 ChatSidebar 私董会徽章
- 添加 emoji 移除计划文档 (docs/plans/2026-07-02-001)
 2026-07-02 01:07:12 +08:00
chiguyong a3cecd4b50 fix(review): apply P0/P2 findings from dual-agent review 
- Dockerfile: split ENTRYPOINT/CMD to align with docker-compose serve
- test_termbase: guard jieba import with pytest.importorskip
- orchestrator: mark silent review-degradation with [DEGRADED] prefix
- chat.py: accurate ExecutionMode log message
- agentkit.yaml: document OTel exporter config
- skill_routing: replace 12 Any with object/typed (AGENTS.md compliance)
- AssistantText.vue: add aria-live/role for a11y
 2026-06-30 14:27:46 +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 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 a27eed3714 fix(config): unify config loading chain and protect ${VAR} references 
- Settings API: reverse-resolve env vars to preserve ${VAR} refs in yaml,
  write new API keys to .env instead of agentkit.yaml, extract env_key
  from existing ${VAR} reference when updating providers
- Onboarding: merge-update instead of overwrite when config exists,
  use config_arg to determine output path, .env merge instead of overwrite
- Unified templates: bailian-coding provider name, full model_aliases,
  docker-compose with postgres, expanded .env.example
- Optional ruamel.yaml for comment/format preservation in Settings API
- clients.yaml: add _deep_resolve for ${VAR} env var references
- All CLI commands use load_config_with_dotenv() consistently
- Tests: mock find_config_path and CWD auto-discovery to avoid env leaks
 2026-06-16 00:26:54 +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 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 99fe4c99f7 fix: comprehensive code review fixes + WS test stability 2026-06-15 08:17:34 +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 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