fix: contextual retrieval latency — max_chunks gate + prompt trim + model update

fix: revert out-of-scope model default change in contextualize_chunks

feat: add source_type metadata to all ingested chunks

feat: semantic chunking via SemanticChunker, toggled by config.yaml semantic_enabled

fix: reduce max_concurrent 20→3 to stay under Groq 6k TPM; smart 429 retry wait

fix: return 422 on password-protected PDF upload instead of 500

feat: contextual retrieval in production via async BackgroundTask

feat: add contextualize_chunks() for LLM-prefixed chunk embeddings

fix: URL size guard for OOM prevention, eliminate double retrieval in chat, fix print

feat: multi-workspace backend — workspace_id routes ChromaDB collections + BM25 dict

feat: rebrand FinRAG → Prism (collection names, system prompt, UI branding)

Swap to API-based embeddings for Render

Add Dockerfile and Render config