ledger: 2026-10-30 git-tree manifest table

wizard-work/ledger/extract_git_tree_manifest_2026_10_30.py

@@ -0,0 +1,111 @@
+#!/usr/bin/env python3
+"""Extract the troupe repo's tracked file tree into a verified table.
+
+Source of truth: `git ls-files` (tracked files) at the repo root.
+
+Outputs (in this directory, wizard-work/ledger/):
+  - 2026-10-30-git-tree-manifest.csv : relpath, ext, size_bytes, sha256
+  - 2026-10-30-git-tree-manifest.json: structured manifest
+  - 2026-10-30-git-tree-manifest.md  : human-readable table
+
+Independent re-derivation:
+  verify_git_tree_manifest_2026_10_30.py  (committed; the committed CHECK
+  runs that verifier and exits 0 iff it matches).
+"""
+import datetime
+import hashlib
+import json
+import os
+import pathlib
+import subprocess
+
+HERE = pathlib.Path(__file__).resolve().parent
+
+
+def find_repo_root(start: pathlib.Path) -> pathlib.Path:
+    """Walk up from `start` until a directory containing `.git` is found."""
+    current = start.resolve()
+    for _ in range(12):
+        if (current / ".git").exists():
+            return current
+        if current.parent == current:
+            break
+        current = current.parent
+    raise SystemExit(f"no .git found above {start}")
+
+
+def sha256_of(path: pathlib.Path) -> str:
+    h = hashlib.sha256()
+    with path.open("rb") as fh:
+        for chunk in iter(lambda: fh.read(1024 * 1024), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def main() -> None:
+    REPO_ROOT = find_repo_root(HERE)
+    out = subprocess.run(
+        ["git", "ls-files"], cwd=REPO_ROOT, check=True,
+        capture_output=True, text=True, env=os.environ,
+    ).stdout.splitlines()
+
+    rows = []
+    for rel in sorted(out):
+        p = REPO_ROOT / rel
+        ext = p.suffix.lower() if p.suffix else "-"
+        rows.append({
+            "relpath": rel,
+            "ext": ext,
+            "size_bytes": p.stat().st_size,
+            "sha256": sha256_of(p),
+        })
+
+    ext_counts = {}
+    total_bytes = 0
+    for r in rows:
+        ext_counts[r["ext"]] = ext_counts.get(r["ext"], 0) + 1
+        total_bytes += r["size_bytes"]
+
+    manifest = {
+        "repo": str(REPO_ROOT),
+        "generated_at": datetime.datetime.now(datetime.timezone.utc).isoformat(),
+        "tracked_file_count": len(rows),
+        "total_bytes": total_bytes,
+        "extension_counts": ext_counts,
+        "top_extensions": sorted(ext_counts.items(), key=lambda kv: (-kv[1], kv[0]))[:15],
+        "files": rows,
+    }
+
+    (HERE / "2026-10-30-git-tree-manifest.json").write_text(
+        json.dumps(manifest, indent=2) + "\n", encoding="utf-8")
+
+    with (HERE / "2026-10-30-git-tree-manifest.csv").open("w", encoding="utf-8",
+                                                           newline="") as fh:
+        fh.write("relpath\text\tsize_bytes\tsha256\n")
+        for r in rows:
+            fh.write(f'{r["relpath"]}\t{r["ext"]}\t{r["size_bytes"]}\t{r["sha256"]}\n')
+
+    lines = [
+        "# Git tree manifest — 2026-10-30",
+        "",
+        f"- repo: `{REPO_ROOT}`",
+        f"- tracked files: {manifest['tracked_file_count']}",
+        f"- total bytes: {manifest['total_bytes']:,}",
+        "",
+        "## Top extensions",
+        "",
+        "| extension | files |",
+        "|---|---|",
+    ]
+    for ext, cnt in manifest["top_extensions"]:
+        lines.append(f"| {ext or '(no extension)'} | {cnt} |")
+    lines += ["", "## Full file list", "", "| # | relpath | ext | bytes |", "|---|---|---|---|"]
+    for i, r in enumerate(manifest["files"], 1):
+        lines.append(f"| {i} | {r['relpath']} | {r['ext']} | {r['size_bytes']} |")
+    (HERE / "2026-10-30-git-tree-manifest.md").write_text("\n".join(lines) + "\n", encoding="utf-8")
+
+    print(f"wrote {len(rows)} tracked files -> {HERE}")
+
+
+if __name__ == "__main__":
+    main()

wizard-work/ledger/verify_git_tree_manifest_2026_10_30.py

@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+"""Independent verification of 2026-10-30-git-tree-manifest.csv.
+
+Recomputes the tracked-file table from `git ls-files` at the repo root and
+compares it against the committed CSV (relpath, ext, size_bytes, sha256).
+
+Exit 0 iff the committed manifest exactly matches git's tracked file set.
+"""
+import hashlib
+import pathlib
+import subprocess
+import sys
+
+REPO = pathlib.Path("/root/troupe-standup")
+MANIFEST_CSV = REPO / "wizard-work/ledger/2026-10-30-git-tree-manifest.csv"
+
+
+def git_ls_files():
+    return subprocess.run(
+        ["git", "-C", str(REPO), "ls-files"],
+        check=True, capture_output=True, text=True,
+    ).stdout.splitlines()
+
+
+def sha256_of(p: pathlib.Path) -> str:
+    h = hashlib.sha256()
+    with p.open("rb") as fh:
+        for chunk in iter(lambda: fh.read(1024 * 1024), b""):
+            h.update(chunk)
+    return h.hexdigest()
+
+
+def main() -> None:
+    live = git_ls_files()
+    live_set = set(live)
+    print(f"live tracked-file count: {len(live)}", file=sys.stderr)
+
+    manifest_rows = MANIFEST_CSV.read_text(encoding="utf-8").splitlines()
+    assert manifest_rows[0] == "relpath\text\tsize_bytes\tsha256", manifest_rows[0]
+    data = manifest_rows[1:]
+    print(f"manifest row count: {len(data)}", file=sys.stderr)
+    assert len(data) == len(live), (
+        f"row count mismatch: manifest {len(data)} vs git {len(live)}")
+
+    data_paths = {line.split("\t", 1)[0] for line in data}
+    if data_paths != live_set:
+        print(f"path-set mismatch: manifest {len(data_paths)} vs live {len(live_set)}",
+              file=sys.stderr)
+        bad = sorted(data_paths ^ live_set)
+        print(f"FAILURES: {len(bad)}", file=sys.stderr)
+        for b in bad[:10]:
+            print("   ", b, file=sys.stderr)
+        sys.exit(1)
+
+    live_by_path = {}
+    for rel in live:
+        p = REPO / rel
+        live_by_path[rel] = (
+            p.suffix.lower() if p.suffix else "-",
+            p.stat().st_size,
+            sha256_of(p),
+        )
+
+    bad = []
+    for line in data:
+        rel, ext, size_s, sha = line.split("\t")
+        if rel not in live_by_path:
+            bad.append(("orphan", rel))
+            continue
+        lext, lsize, lsha = live_by_path[rel]
+        if ext != lext or int(size_s) != lsize or sha != lsha:
+            bad.append(("cell-mismatch", rel, ext, lext, size_s, lsize, sha, lsha))
+
+    print(f"checked rows: {len(data)}", file=sys.stderr)
+    if bad:
+        print(f"FAILURES: {len(bad)}", file=sys.stderr)
+        for b in bad[:10]:
+            print("   ", b, file=sys.stderr)
+        sys.exit(1)
+    print("VERIFY_PASS: manifest matches git ls-files (relpath, ext, size, sha256)",
+          file=sys.stderr)
+
+
+if __name__ == "__main__":
+    main()