feat: deterministic sheet-list reconciliation (cover index vs identified sheets)

backend/agents/runner.py

@@ -31,6 +31,7 @@ from backend.pipeline.report import build_report, to_markdown
 from backend.pipeline.sheet_index import derive_project_meta_from_cover
 from backend.review.gate import build_review_queue
 from backend.review.store import ReviewStore
+from backend.sheet_reconcile import declared_sheet_list, reconcile_sheets
 from backend.text_layer import (
     attach_text_layers, coverage_gaps, find_evidence_bbox, render_crop,
 )
@@ -84,6 +85,20 @@ def run_agent_pipeline(
     sheets.sort(key=lambda sheet: sheet.get("page_number") or 0)
     memory.replace("sheets", sheets)
     memory.dump("01-extract.json")
+
+    # Deterministic reconciliation: the cover sheet's own sheet index
+    # declares what the set should contain; compare against what wave 1
+    # identified (catches missed sheets AND phantom/misread sheet numbers).
+    sheet_recon = reconcile_sheets(sheets, declared_sheet_list(page_to_text))
+    if sheet_recon["declared_total"]:
+        print(f"[SheetIndex] cover declares {sheet_recon['declared_total']} "
+              f"sheets; {sheet_recon['found_total']} identified in set")
+        if sheet_recon["declared_not_in_set"]:
+            print(f"[SheetIndex] declared but not in set: "
+                  f"{', '.join(sheet_recon['declared_not_in_set'][:20])}")
+        if sheet_recon["in_set_not_declared"]:
+            print(f"[SheetIndex] in set but not declared: "
+                  f"{', '.join(sheet_recon['in_set_not_declared'][:20])}")
     # Coverage signal: text layer present but extraction failed/empty reuses
     # the failed-scopes gap-finding path (finding built below wave 6).
     for gap_page in coverage_gaps(pages, sheets):
@@ -289,6 +304,7 @@ def run_agent_pipeline(
             "project_input": merged_input,
             "jurisdiction": jurisdiction,
             "sheet_index": sheet_index,
+            "sheet_reconciliation": sheet_recon,
             "project_intelligence": object_graph,
             "validated_issues": prioritized,
             "rfis": [],
@@ -365,6 +381,7 @@ def run_agent_pipeline(
         "project_input": merged_input,
         "jurisdiction": jurisdiction,
         "sheet_index": sheet_index,
+        "sheet_reconciliation": sheet_recon,
         "project_intelligence": object_graph,
         "validated_issues": prioritized,
         "rfis": rfis,