release: v0.4.0 — retrieval precision overhaul, 75% Combined QA

Performance: 29% → 75.2% Combined QA (+46.2%p over 6 iterations)
- BM25 min-max score normalization
- Document coherence boost
- Reranker score blending (0.7 reranker + 0.3 fusion)
- Full ingest mode with HyPE enabled
- Adaptive post-correction time budget
- Query deadline gate (70s)
- Auto-skip correction for simple confident queries

Playground: pipeline trace visualization, latency breakdown, source
excerpts, code block rendering fix, demo command

Infrastructure: serve auto-detects quantumrag.yaml and .env,
provider/model status on startup

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: unamedkr

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "quantumrag"
-version = "0.3.3"
+version = "0.4.0"
 description = "Index-Heavy, Query-Light RAG Engine — Put in docs, ask questions, it just works."
 readme = "README.md"
 license = "Apache-2.0"

quantumrag/_version.py

@@ -1 +1 @@
-__version__ = "0.3.3"
+__version__ = "0.4.0"