## Why

The current `lookup_knowledge` result is still shaped as one L0 primary result plus one L1 supplement. That makes retrieval evidence hard to inspect, hard to deduplicate, and hard to reuse later by verifier/evaluator code. The RAG refactor needs a structured evidence layer before Spring AI retriever migration.

## What Changes

- Add structured evidence blocks to `LookupResult`.
- Build evidence blocks from L0 hint matches and L1 candidates.
- Deduplicate evidence by source identity where possible.
- Add hit reasons such as L0 matched keywords, L1 semantic rank, category filter, and fallback.
- Persist evidence block summaries and postprocess counts in `tool_invocation.retrieval_details`.
- Keep existing `primary` and `supplement` fields for compatibility.

## Capabilities

### New Capabilities

- None.

### Modified Capabilities

- `rag-knowledge-retrieval`: Add evidence block post-processing requirements for explicit RAG knowledge retrieval.

## Impact

- Affects `LookupResult`, `LookupKnowledgeTool`, and `ToolInvocationRecorder`.
- Updates tool tests and trace recorder tests.
- Does not change Milvus schema, document upload, chunking, or Spring AI integration.