feat(rag): switch to rich context judge with reasoning (D3 strategy)

tune(rag): calibrate relevance filter for raw logit scores

feat(rag): add adaptive relevance filter (score gap + LLM fallback)

fix(test): increase retrieval latency budget to 1000ms for reranker

test: add unit tests for eval/runner.py

test: add unit tests for rag/prompts.py build_context

feat: add LRU-cached embed_query to avoid re-embedding repeated searches

refactor: remove streaming generator and rewriter

feat(api): replace SSE chat with sync POST /api/search

feat: correct story links, loading UX, slug-based card filtering

feat: conditional query rewriting for conversational follow-ups

feat: metadata routing for structural queries (most awarded, newest, oldest)

feat: integrate cross-encoder reranker into hybrid retriever

feat: cross-encoder reranker with ONNX inference

feat: /api/chat SSE endpoint with hybrid RAG

feat: /api/stories endpoint for landing mosaic

feat: FastAPI skeleton with health endpoint

fix(test): replace quantum_computing edge case with minecraft_redstone

refactor: remove Reranker references from all entrypoint files

refactor: remove cross-encoder reranker, RRF handles ranking alone

feat: replace sentence-transformers with ONNX Runtime embedder (bge-small 384d)

test: expand generation tests to 30 queries across full spectrum

test: add generation quality tests for Flash responses

feat: streaming responses with Flash, remove story cards

feat: retrieval evaluation script with router improvements

fix: pipeline cleanup + retrieval improvements

feat: update prompts for stories-only context with enriched metadata

feat: rewrite retriever as HybridRetriever with dense+BM25+RRF+reranking

feat: add QueryRouter with regex-first intent classification

feat: add Reranker with cross-encoder ms-marco-MiniLM-L-12-v2

feat: expand chunk_story metadata (20+ fields), remove chunk_segments

feat: add BM25Store with tokenization, stemming, save/load

refactor: remove segments collection from VectorStore, add get_all_metadata

feat: expand StoryEnrichment with themes, countries, regions, event_period, media_type, is_subject

feat: propagate content_type from nav tree position in fetcher

feat: add parse_recognition, parse_press_mentions, extract_director, extract_commissioned_by parsers

feat: display poster images alongside RAG results

feat: propagate poster_images as ChromaDB metadata

feat: extract poster_images during story ingest

feat: add extract_poster_images parser function