SuperBizAgent-java/openspec/changes/archive/2026-07-04-rag-spring-ai-vectorstore-sidecar/tasks.md

1. Dependency And Configuration

• 1.1 Inspect available Spring AI VectorStore/Milvus classes for the current dependency set.
• 1.2 Add the narrow dependency or optional configuration needed for the sidecar path.
• 1.3 Add disabled-by-default sidecar properties under RAG configuration.

2. Sidecar Retrieval Adapter

• 2.1 Define a comparable retrieval result DTO for current and sidecar paths.
• 2.2 Implement a Spring AI sidecar retrieval service that reports readiness and failures without breaking the main path.
• 2.3 Normalize sidecar metadata into source/doc id, title, breadcrumb, category, rank, content preview, and score label/value.

3. Comparison Evaluation

• 3.1 Add a comparison service or script that runs golden cases against current retrieval and the sidecar path when enabled.
• 3.2 Write sidecar comparison JSON/Markdown reports separate from the offline baseline reports.
• 3.3 Preserve the existing offline evaluator behavior without requiring live Spring AI/Milvus services.

4. Tests And Validation

• 4.1 Add tests for disabled sidecar fallback/readiness behavior.
• 4.2 Add tests for comparable result normalization and report generation.
• 4.3 Run targeted tests, the offline RAG retrieval baseline evaluator, and OpenSpec validation.
• 4.4 Review git diff to confirm the default lookup_knowledge runtime path is unchanged.