feat: refocus on drawings — code/ADA gated off, drawing-integrity wave, Brain-directed clarification

- ENABLE_CODE_REVIEW flag (default off): skips code/ADA/jurisdiction review
  path in both pipelines; nothing deleted, one env flag to restore.
- Per-sheet Drawing Integrity QA wave (agent + classic, default on):
  dangling refs, on-sheet contradictions, dimension sanity, missing sheet
  essentials, tag hygiene. New DrawingIntegrityAgent + classic stage.
- Broadened conflict critic: intra-sheet + same-discipline contradictions,
  not just cross-discipline.
- Wave 6.5 Brain-directed clarification (bounded hub-and-spoke): Brain names
  uncertain findings, verify_evidence requests route through the wave-5b
  verifier; refuted findings suppressed. One planning call + capped verifies,
  single iteration. Shared _build_verify_scopes across 5b and 6.5.
- Config knobs, .env.example, frontend copy, tests (182 passing).

backend/agents/verifier.py

@@ -36,6 +36,15 @@ def _valid_verdict(item):
 
 
 def _status(verdicts):
+    """Roll per-evidence verdicts up to a finding-level status.
+
+    NOTE on "corrected": it is deliberately NON-confirming. The canonical case
+    (job 959e16407573) is evidence quoting "(2) 2x6 STUD PACK" against a sheet
+    that reads "(5)" — the text exists but the VALUE the finding rests on was a
+    wave-1 misread, so the finding's basis is gone. Hence refuted = zero
+    CONFIRMED verdicts, not zero not_found ones. Do not "fix" this to treat
+    corrected as supporting; see tests/agents/test_verifier.py.
+    """
     if not verdicts:
         return "unverified"
     confirmed = sum(1 for v in verdicts if v["verdict"] == "confirmed")