conductor(chronology): Phase 8 bulk verification + cross-check helpers (FR6)

scripts/audit/check_chronology_rows.py

@@ -0,0 +1,69 @@
+"""Bulk cross-check of chronology.md rows.
+
+Run from repo root: uv run python scripts/audit/check_chronology_rows.py
+"""
+from __future__ import annotations
+import subprocess
+import sys
+from pathlib import Path
+
+# Add repo root to path so we can import the helper
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent.parent))
+from scripts.audit.generate_chronology import walk_track_folders  # noqa: E402
+
+rows = walk_track_folders(Path("conductor"))
+errors: list[str] = []
+checked = 0
+
+for i, row in enumerate(rows):
+    checked += 1
+    folder_relpath = row["folder_link"]
+    track_id = row["track_id"]
+
+    folder = Path(folder_relpath)
+    if not folder.is_dir():
+        errors.append(f"Row {i+2} [{track_id}]: folder does not exist: {folder_relpath}")
+        continue
+
+    try:
+        result = subprocess.run(
+            ["git", "log", "--reverse", "--format=%h", "--", folder_relpath],
+            capture_output=True, text=True, timeout=30, check=False,
+        )
+        actual_init = result.stdout.strip().splitlines()[0] if result.stdout.strip() else ""
+        if row["init_sha"] != actual_init:
+            errors.append(
+                f"Row {i+2} [{track_id}]: init_sha mismatch: row={row['init_sha']!r} actual={actual_init!r}"
+            )
+    except Exception as exc:
+        errors.append(f"Row {i+2} [{track_id}]: init_sha check failed: {exc}")
+
+    try:
+        result = subprocess.run(
+            ["git", "log", "-1", "--format=%h", "--", folder_relpath],
+            capture_output=True, text=True, timeout=30, check=False,
+        )
+        actual_end = result.stdout.strip()
+        if row["end_sha"] != actual_end:
+            errors.append(
+                f"Row {i+2} [{track_id}]: end_sha mismatch: row={row['end_sha']!r} actual={actual_end!r}"
+            )
+    except Exception as exc:
+        errors.append(f"Row {i+2} [{track_id}]: end_sha check failed: {exc}")
+
+    date = row["date"]
+    if date and not (len(date) == 10 and date[4] == "-" and date[7] == "-"):
+        errors.append(f"Row {i+2} [{track_id}]: bad date format: {date!r}")
+
+    if not row["status"]:
+        errors.append(f"Row {i+2} [{track_id}]: empty status")
+
+    if not row["summary"]:
+        errors.append(f"Row {i+2} [{track_id}]: empty summary")
+
+print(f"Checked: {checked} rows")
+print(f"Errors: {len(errors)}")
+if errors:
+    print("All errors:")
+    for e in errors:
+        print(f"  {e}")

scripts/audit/check_commit_counts.py

@@ -0,0 +1,53 @@
+"""Verify commit_count field in chronology rows."""
+from __future__ import annotations
+import subprocess
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent.parent))
+from scripts.audit.generate_chronology import walk_track_folders  # noqa: E402
+
+rows = walk_track_folders(Path("conductor"))
+issues: list[str] = []
+
+for i, row in enumerate(rows):
+    folder = row["folder_link"]
+    track_id = row["track_id"]
+    init_sha = row["init_sha"]
+    end_sha = row["end_sha"]
+    expected_count = row["commit_count"]
+
+    try:
+        result = subprocess.run(
+            ["git", "log", "--oneline", "--", folder],
+            capture_output=True, text=True, timeout=30, check=False,
+        )
+        actual_count = len(result.stdout.strip().splitlines())
+    except Exception:
+        continue
+
+    if init_sha and end_sha:
+        if init_sha == end_sha:
+            if expected_count not in (0, 1):
+                issues.append(
+                    f"Row {i+2} [{track_id}]: init==end but count={expected_count} (expected 0 or 1)"
+                )
+        else:
+            if expected_count < 1:
+                issues.append(
+                    f"Row {i+2} [{track_id}]: init!=end but count={expected_count} (expected >=1)"
+                )
+            if abs(expected_count - actual_count) > 1:
+                issues.append(
+                    f"Row {i+2} [{track_id}]: count={expected_count} actual_total={actual_count} (off by >1)"
+                )
+    else:
+        if expected_count != 0:
+            issues.append(
+                f"Row {i+2} [{track_id}]: no SHAs but count={expected_count}"
+            )
+
+print(f"Total rows: {len(rows)}")
+print(f"Issues: {len(issues)}")
+for issue in issues[:30]:
+    print(f"  {issue}")

scripts/audit/sample_summaries.py

@@ -0,0 +1,23 @@
+"""Spot-check summary quality across random rows."""
+from __future__ import annotations
+import json
+import random
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent.parent))
+from scripts.audit.generate_chronology import walk_track_folders  # noqa: E402
+
+rows = walk_track_folders(Path("conductor"))
+random.seed(42)
+sample = random.sample(rows, 15)
+
+for row in sample:
+    track_id = row["track_id"]
+    date = row["date"]
+    status = row["status"]
+    summary = row["summary"][:300]
+    print(f"=== {track_id} ({date}) ===")
+    print(f"Status: {status}")
+    print(f"Summary: {summary}")
+    print()