e33dc25ad3
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
|
||
|---|---|---|
| .. | ||
| 2026-06-05-001-feat-agentkit-tdd-validation-plan.md | ||
| 2026-06-05-002-design-agentkit-v2-architecture.md | ||
| 2026-06-05-003-feat-agentkit-v2-phase1-plan.md | ||
| 2026-06-05-004-geo-migration-mode-a.md | ||
| 2026-06-05-005-refactor-agentkit-framework-hardening.md | ||
| 2026-06-05-006-refactor-agentkit-v2-phase2-plan.md | ||
| 2026-06-05-007-feat-agentkit-cli-deployment-plan.md | ||
| 2026-06-06-008-feat-agentkit-phase3-upgrade-plan.md | ||
| 2026-06-06-009-feat-agentkit-rag-optimization-plan.md | ||