fix(rna_sc): harden load/visualize UMAP against missing embedding/leiden (#1)

feat(loveless): integrate biodata-registry 0.1.8 sc datasets (Path P by modality)

feat(loveless): sc loaders resolve hosted/private h5ad URLs (ADR-0006)

feat(loveless): ADR-0006 #6 — h5ad source type + Path P loading plan

feat(loveless): ADR-0006 + agent-side sc serving scaffold

perf(mcp): HTTP transport core — add_mcp_http on agent/tool_manager + adata cache + instrumentation

fix(loader): authenticate h5ad loads in dataset metadata tools

feat(integration): ComBat per-sample scoring tool decoupler_pool_cohorts (ADR-0001 item 10)

refactor(loader): centralize authenticated URL->local resolution

fix(loader): authenticate huggingface.co downloads via HF_TOKEN

ADR-0001 Phase 2 Mode A: early integration (T7 + T8 + T9)

feat(concordance): same-cohort normalization concordance routine (decoupler_normalization_concordance)

fix(loaders): accept http(s)/ftp URLs in bulk dataset loaders

feat(sanity): ADR-0002 Phase 2 — auto-fire tissue-identity contamination + PROGENy/Hallmark parity

feat(sanity): ADR-0002 Layer-2 result-aware sanity layer (Phase 1 + S1)

feat: hide microarray from advertised inventory + plain-language Approach in solutions

ADR-0001 Phase 1, steps 5-6 (T5): decoupler_meta_analyze + A->B->refuse wiring

ADR-0001 Phase 1, step 3 (T4): dataset_get_integration_plan wrapper + 0.1.2 re-pin

ADR-0001 Phase 1, step 1: declare Mode-B combine conformance on rna tools

Split bulk_rnaseq.py (1073) into a package preserving the public API

Split dataset_tools.py (1709) into a package preserving the public API

Suppress star-import lint noise in rna package (file-level noqa)

Split rna.py (1847 lines) into an rna/ package preserving the public API

Lint cleanup: remove unused imports, empty f-strings, split import lines

Refactor decoupler_join_clinical_metadata: extract helpers (CC 36->15)

Refactor dataset_count_metadata_values: extract helpers (CC 38->14)

Code-quality fixes: dead assignments, redundant imports, MD5 intent, type hints

Add probe-collapse precompute Phase 2 (collapsed_url support)

Fix 4 GPL-annotation fallback edge cases + 2 integration test bugs

Document residual GPL annotation limitations (Known Gaps #15)

Add GEOparse fallback for GPL platforms with no .annot.gz (Tier 2)

Switch GPL platform annotation to NCBI .annot.gz instead of _family.soft.gz

Add dataset_filter_to_curated_samples tool and loading plan integration

Fix 7 pre-existing test failures

Switch tcga_paad to HF-hosted pre-assembled h5ad; fix clinical join dedup

Add decoupler_load_gdc_star_counts; pivot tcga_paad to Path A / DESeq2

Add dataset_disclaimer field; assert it in TCGA-PAAD contract test

Phase 4: TCGA-PAAD manifest, integration tests, schema fix

Phase 3: Update loading plan builder for url-type expression sources

Phase 2: Add decoupler_join_clinical_metadata for clinical data join

Phase 1: Add decoupler_load_url_counts for flat matrix loading

Remove local manifest copies; expand list_available_datasets with full fields

Add subset_query to DE tool, fix limma check, tighten efficiency rules

Add in-memory dataset cache to eliminate GEO re-downloads

Add dataset_validate_manifest_against_data tool and tests

Add DESeq2 Path A integration tests; fix pydeseq2 design deprecation

Improve agent accuracy: guardrails, routing rules, and workflow examples

Set limma as preferred DE method for Moffitt with ttest fallback

Improve dataset_count_metadata_values single-column UX

Refactor manifest/metadata to separate semantics from runtime counts