fix(overton): correct 3 critical data errors and 3 high-severity caveats

CRIT-1: Stylistic extremity direction reversed — both dimensions declined
  (stijl 1.875→1.744, not increased +0.097). Holistic moderation, not divergence.
CRIT-2: Masking rate corrected from 36.1% to 9.7% (S≤2, M≥4 on full dataset).
  Original 36.8% was from 117-motion manual audit, not extrapolatable.
CRIT-3: Material impact values harmonized to motion-level means (2.79→2.45).
  Old values (2.78→2.43) used undisclosed mean-of-yearly-means aggregation.
HIGH-1: Migration domain provenance caveat — category column is NULL,
  analysis relies on title keyword matching (approximate boundaries).
HIGH-2: 2026-Q2 bounce caveat — n=44, bimodal distribution, sensitive to
  composition (many consensus defense motions among CS=1.0 items).
HIGH-3: Non-right-wing control group corrected — CS rose 58%→62% (+3.5pp),
  not 'flat at 49%'. Surge was disproportionate for right-wing content.

Also: fixed 6-party centrist definition (line 30) to 4-party,
removed 'did not shift rightward' phrasing, added Phase 4 synthesis
reminder to build_all_reports.py.

analysis/right_wing/build_all_reports.py

@@ -190,6 +190,18 @@ def main() -> int:
     else:
         logger.info("Skipping LLM-dependent phase (--skip-llm).")
 
+    # Phase 4: Synthesis reminder (manual)
+    print("\n" + "=" * 50)
+    print("PHASE 4 — MANUAL STEP REQUIRED")
+    print("=" * 50)
+    print("  After all scripts complete, manually update:")
+    print("    - reports/overton_window/overton_window_synthesis.md")
+    print("    - reports/overton_window/overton_window.qmd (then: quarto render)")
+    print("    - reports/overton_window/overton_report.html")
+    print("  These narrative files require human judgment to integrate")
+    print("  new data into the existing analysis framework.")
+    print("=" * 50)
+
     total_elapsed = time.perf_counter() - t_start
 
     # Summary