unseen: make clone disk-size guard tolerate git's mid-walk churn

disk_bytes() summed the clone tree with rglob + stat() as a size cap
before every git command. On a blob:none clone, `git show` triggers an
on-demand blob fetch that writes and deletes transient
.git/objects/pack/*.rev files, so a path rglob had just listed could be
gone by the stat() call -> FileNotFoundError aborted the whole draft as
an instrument_failure. The race can hit any candidate, so it was a
non-deterministic draft-killer (observed extracting a real npm repo).

Skip a file that raises OSError mid-walk; the size cap is unaffected.

Co-Authored-By: Claude Opus 4.8 <[email protected]>

benchmarks/unseen/extract.py

@@ -57,7 +57,16 @@ class Git:
         return done.stdout.decode("utf-8", errors="replace")
 
     def disk_bytes(self) -> int:
-        return sum(p.stat().st_size for p in self.path.rglob("*") if p.is_file() and not p.is_symlink())
+        # git churns .git/objects/pack (incl. transient *.rev) during on-demand blob
+        # fetches, so a path rglob just listed can vanish before stat(): skip it.
+        total = 0
+        for p in self.path.rglob("*"):
+            try:
+                if p.is_file() and not p.is_symlink():
+                    total += p.stat().st_size
+            except OSError:
+                continue
+        return total
 
     def parents(self, sha: str) -> list[str]:
         return self.run("rev-list", "--parents", "-n", "1", sha).split()[1:]

tests/test_unseen_extract.py

@@ -312,3 +312,25 @@ def test_unbalanced_cells_remain_proportional_and_seed_changes_draw():
     draw, _ = e.draw_ordinary(rows, set(), set(), seed=1)
     assert len([r for r in draw if r["size_bucket"] == 0]) == 9
     assert draw != e.draw_ordinary(rows, set(), set(), seed=2)[0]
+
+
+def test_disk_bytes_skips_files_that_vanish_mid_walk(tmp_path):
+    # git churns .git/objects/pack (transient *.rev) during on-demand blob fetches,
+    # so a path rglob just listed can be gone by the time disk_bytes stat()s it.
+    git = e.Git(tmp_path, runner=subprocess.run)
+    (tmp_path / "a").write_bytes(b"x" * 10)
+    (tmp_path / "b").write_bytes(b"y" * 20)
+    real = [p for p in tmp_path.rglob("*")]
+
+    class Vanished:
+        def is_file(self):
+            return True
+
+        def is_symlink(self):
+            return False
+
+        def stat(self):
+            raise FileNotFoundError(2, "No such file or directory")
+
+    git.path = type("P", (), {"rglob": lambda self, pattern: iter([*real, Vanished()])})()
+    assert git.disk_bytes() == 30