feat(agentkit): Phase 3 upgrade - persistence, memory, evolution, observability #1

fischer · 2026-06-06T18:00:03+08:00

fischer commented

2026-06-06 18:00:03 +08:00

AgentKit Phase 3 upgrade. 10 Implementation Units across 3 phases. Tier 2 code review: all P0+P1 fixed. 924 tests passed.

fischer added 13 commits 2026-06-06 18:00:03 +08:00

47a848fbcb feat(deploy): add Dockerfile and .dockerignore for AgentKit Server

- Multi-stage build (builder + runner) based on python:3.11-slim
- Installs .[server] extra (fastapi + uvicorn)
- Runs as non-root appuser
- Health check on /api/v1/health
- Default command: uvicorn configs.geo_server:create_geo_app --port 8001

669ca604e5 feat(configs): add GEO AgentKit Server configuration

- llm_config.yaml: DeepSeek + OpenAI-compatible providers with env var substitution
- skills/ (8 YAML): citation_detector, content_generator, deai_agent, geo_optimizer,
  monitor, schema_advisor, competitor_analyzer, trend_agent
  - Added intent fields for content_generator, competitor_analyzer, trend_agent
  - Added quality_gate fields for content_generator, deai_agent, geo_optimizer
  - Updated custom_handler paths to configs.geo_handlers
- geo_tools.py: 14 FunctionTools calling GEO Backend via HTTP
- geo_handlers.py: 3 custom handlers (citation/monitor/schema) calling /internal/ API
- geo_server.py: FastAPI factory with LLM Gateway, Tool Registry, Skill Registry

f87b790c0f feat(agentkit): v2 Phase 1 - ReAct/LLM Gateway/Skill/Server + review fixes

535 unit + 52 integration tests passing. README added.

5f1c51cf9a feat(server): Phase B - auth, rate limiting, SSRF protection, handler whitelist

U1: API Key authentication middleware (dev mode skip, health whitelist)
U2: Rate limiting middleware (fixed-window, 60 req/min default)
U3: Callback URL SSRF protection (private IP blocking)
U4: custom_handler module prefix whitelist

65 tests passing. CORS conflict fixed.

ec0e221beb feat(server): Phase D - async task system (TaskStore + BackgroundRunner + API)

U5: TaskStore - in-memory task state with TTL cleanup and max records
U6: BackgroundRunner - async task execution with semaphore concurrency control
U7: Task status/result API + cancel endpoint + async submit mode

45 tests passing (28 new + 17 existing, no regression).

2844eeb548 feat(streaming): Phase C - LLM streaming + ReAct events + SSE endpoint

U8: StreamChunk protocol + OpenAI chat_stream + Gateway streaming with usage tracking
U9: ReActEvent dataclass + execute_stream() yielding thinking/tool_call/tool_result/final_answer
U10: POST /tasks/stream SSE endpoint + Client SDK stream_task()

15 new tests passing, no regression.

acec8ff743 feat(evolution): Phase A - lifecycle hooks + EvolutionConfig

U11: EvolutionMixin integrated into ConfigDrivenAgent lifecycle
  - on_task_complete triggers evolve_after_task
  - on_task_failed records failure patterns
  - Evolution errors never break main task flow

U12: EvolutionConfig added to SkillConfig
  - enabled, reflect_on_failure, auto_apply, min_quality_threshold
  - Backward compatible: defaults to enabled=False

21 new tests passing, no regression.

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.

3cd6a73d86 feat(cli): Docker deployment + README CLI section

U5: docker-compose.yaml (agentkit + redis + postgres) + Dockerfile ENTRYPOINT
U6: README updated with CLI quick start + Docker deployment guide

31 CLI tests passing, no regression.

74e2223153 feat(cli): pair command + doctor rename + client config priority

- health → doctor (better naming)
- agentkit pair --name <client> generates ak_live_ API key
- agentkit pair --list / --revoke for client management
- ClientConfig class: client config > init defaults > hardcoded
- README updated with pair usage + business system pairing guide
- 38 CLI tests passing

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

f976fade99 docs: mark Phase 3 upgrade plan as completed

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

fischer added 1 commit 2026-06-06 18:21:04 +08:00

0456429beb fix(review): address all 14 P2 advisory findings

fischer added 1 commit 2026-06-06 18:36:23 +08:00

cd5b39087e feat(memory): add HttpRAGService for config-driven knowledge base integration

fischer added 1 commit 2026-06-06 19:27:20 +08:00

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

fischer closed this pull request

2026-06-10 15:19:55 +08:00

fischer referenced this issue from a commit

2026-07-01 13:26:29 +08:00

fix(experts): resolve residual review findings from PR #13

fischer referenced this pull request

2026-07-01 13:27:48 +08:00

fix(experts): resolve residual review findings from PR #13 #14

fischer referenced this issue from a commit

2026-07-01 13:37:52 +08:00

Merge PR #14: fix(experts): resolve residual review findings from PR #13

fischer referenced this issue from a commit