cleanup: remove stale .mindmodel, old venvs, orphaned code, and transient artifacts

Removes:
- .mindmodel/ directory and related CI workflows (mindmodel-schedule.yml, mindmodel-validation.yml)
- scripts/mindmodel/ and scripts/validate_mindmodel.py
- src/types/ and src/validators/ (orphaned type modules, only used by mindmodel)
- tests/ci/, tests/scripts/mindmodel/, tests/types/, tests/validators/ (mindmodel-only tests)
- thoughts/ledgers/ and thoughts/shared/ (stale transient directories)
- .venv_axis and .venv_plotly (orphaned virtual environments, ~1.1 GB)
- outputs/blog-charts/ (stale generated HTML files)
- data/*.json sidecars (empty cache artifacts)
- __pycache__ and *.pyc files across repo

Updates:
- .gitignore: remove thoughts/shared/analyses/ entry

Space reclaimed: ~1.1 GB+

analysis/explorer_data.py

@@ -346,7 +346,12 @@ def load_party_mp_vectors(db_path: str) -> Dict[str, List[np.ndarray]]:
 
 
 def load_scree_data(db_path: str) -> List[float]:
-    """Load scree plot data (explained variance) for current_parliament."""
+    """Load scree plot data (explained variance) for current_parliament.
+
+    First tries to read the cached metadata row from svd_vectors.
+    Falls back to on-the-fly computation via compute_svd_spectrum for
+    backward compatibility with databases that haven't stored it yet.
+    """
     try:
         con = duckdb.connect(database=db_path, read_only=True)
         row = con.execute(
@@ -364,7 +369,11 @@ def load_scree_data(db_path: str) -> List[float]:
             import json
 
             return json.loads(row[0])
-        return []
+
+        # Fallback: compute dynamically for backward compatibility
+        from analysis.political_axis import compute_svd_spectrum
+
+        return compute_svd_spectrum(db_path)
     except Exception:
         logger.exception("Failed to load scree data")
         return []