docs: bicorder_model.json is research-only (app integration removed in v1.3.0)

Verified: bicorder-app has no classifier implementation and reads
bicorder_model.json nowhere (src, build config); ascii_bicorder.py doesn't
use it either. Corrected the stale 'read by bicorder-app at build time'
claims in README, WORKFLOW, and the export script docstring.

analysis/WORKFLOW.md

@@ -25,7 +25,7 @@ The scripts automatically draw the gradients from the current state of the [bico
 9. **scripts/univariate_analysis.py** - Per-protocol and per-gradient averages, distributions, and summary stats (replaces the ad-hoc averages workflow)
 10. **scripts/compare_analyses.py** - Compare readings CSVs to a reference (Euclidean distance, RMSE, correlation); canonicalizes renamed gradients so versions can be compared
 11. **scripts/visualize_clusters.py** - Additional cluster visualizations
-12. **scripts/export_model_for_js.py** - Export trained model to `bicorder_model.json` (read by `bicorder-app` at build time)
+12. **scripts/export_model_for_js.py** - Export trained model to `bicorder_model.json` (research-only since v1.3.0 — the app integration was removed)
 
 Version-agnostic helpers shared by these scripts live in **scripts/bicorder_common.py**: the historical gradient rename map, version detection (from the `bicorder_version`/`version` column, falling back to the `data/<type>_<version>/` directory convention), and training-CSV selection. When gradients are renamed in `../bicorder.json`, update `COLUMN_RENAMES` in that one module.