feat(api): dispatch /predict/mri via MRI_MODEL_KIND env var

feat(models): selector dispatch for volumetric vs 2D MRI models

feat(models): add 2D resnet18 4-class Alzheimer's MRI inference module

deps: add torch/torchvision/pillow for MRI DL 2D

docs(plan): swap OASIS branch for EEG stub plan; soften MRI prerequisite

docs(plan): external assets integration (MRI DL 2D + TF-IDF RAG + OASIS tabular)

fix(fusion): correct logit-scale comment; top_disease=None on empty input

test(fusion): end-to-end smoke + README section

feat(agents): register run_fusion tool for multi-modal disease confidence

feat(api): add POST /fusion/predict route for multi-modal fusion

feat(fusion): add core multi-modal fuse() with per-disease attribution

feat(fusion): map modality predictions to per-disease signals

feat(fusion): add clinical-test signal normalisers (MMSE/MoCA/UPDRS/gait/age)

feat(fusion): add disease/modality weight registry

fix(fusion): drop unused protected_namespaces; pin tighter bound tests

feat(fusion): add pydantic data contract for multi-modal fusion

docs(plan): clinical platform roadmap + fusion engine plan

superpowerfixes.md

test(agents/orchestrator): pin caplog handler to INFO (hardens against pytest variance)

fix(agents/orchestrator): log dropped out-of-stage tool calls (was silent)

docs(agents/tools): TODO race on shared parquet output for concurrent /agent/run

test(agents/routing): assert sites_csv key on NIfTI route (depth parity with EEG test)

test(agents/routing): regression tests for MRI/EEG/BBB routing heuristic

feat(frontend/mri): expose target_shape as 3 number inputs (was hardcoded 64³)

test(mri/model): drop redundant caplog.at_level (direct handler attach is the actual mechanism)

fix(mri/model): warn when label_names length != model output dim (was silent override)

Add project files

fix(agents/live): skip on NotFoundError (model availability churns on OpenRouter free-tier)

Merge feat/orchestrator-rag: orchestrator agent + RAG feedback layer

docs(plan): orchestrator agent + RAG feedback implementation plan

feat(agents): live OpenRouter integration test (slow) + GET /diag/agent

fix(agents/live): also gate live test on BBB model artifact (avoids dotenv-loaded key path)

docs: §15 orchestrator agent + §16 RAG surface (AGENTS.md + README pointers)

feat(deploy): build RAG index at Docker build time + KB seed dir

feat(frontend): Agent tab with decision-trace expander

feat(api): POST /agent/run endpoint (orchestrator + RAG, stub-injectable)

fix(agents/tools): parameterize processed_dir + translate HTTPException → ValueError

feat(agents): orchestrator loop (function-calling + tool trace + max-steps gate)

fix(rag/ingest): drop print() in main() — INFO log already covers it (AGENTS.md §3)

feat(agents): Tool dataclass + registry + 4 tool wrappers (3 pipelines + RAG)

feat(rag): RAGRetriever (load + search → chunks with scores)

feat(rag): ingest CLI (markdown/PDF → chunks → FAISS) + sample KB fixtures

fix(rag/store): copy vectors before in-place normalize_L2 (no caller mutation)

feat(rag): FAISS inner-product store with chunk metadata + roundtrip

feat(rag): fastembed wrapper (Embedder, bge-small-en-v1.5, 384-dim)

feat(rag): paragraph-aware chunker (chunk_text)

fix(gitignore): blanket-ignore data/knowledge_base/ except README+.gitkeep

feat(rag): add fastembed/faiss-cpu/pypdf for retrieval layer

md updates

feat(llm): user-question-driven prompt (language match + intent split)