chiguyong
|
57f4ee9ac0
|
refactor: remove Any from tools/ + skills/ (220 sites)
Wave 3 Any 治理:
- tools/ 146 sites: bitable_tool(20), computer_use(16), schema_tools(14), shell(7), builtin(7), file_read(8), calendar_tool(8), web_crawl(6), computer_use_recorder(6), ask_human(5), baidu_search(5), web_search(5), base(5), memory_tool(3), skill_search(3), function_tool(3), skill_install(3), document_tool(4), mcp_tool(4), output_parser(2), advance_phase(2), search(2), composition(2), agent_tool(2), headroom_retrieve(2), terminal_session(1), registry(1)
- skills/ 74 sites: geo_pipeline(23), base(18), pipeline(13), schema(8), skill_detail(6), skill_md(6) + 3 F401 fixes
Strategy: dict[str,object] > object > TYPE_CHECKING Protocol
Tests: 577 passed, 0 regressions
ruff: 13 errors (all pre-existing, 0 new)
|
2026-07-01 04:52:57 +08:00 |
|
chiguyong
|
8620751864
|
fix(review): address P0+P1 findings from Tier 2 code review
P0: MemoryRetriever.retrieve score mutation fix
P1: Redis atomic Lua script, deprecated API fix, SQLite WAL mode,
Redis URL masking, UniqueConstraint, TraceRecorder completed flag,
EpisodicMemory recall improvement, LLMReflector sanitization,
A/B test safety, generator cleanup, ContextCompressor guards,
OpenAIEmbedder reuse, Pipeline failure handling, Metrics O(1),
Health check Redis PING, CLI skill loading, CORS config,
API key direct pass-through
Tests: 924 passed, 18 skipped, 0 failed
|
2026-06-06 17:57:47 +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 |