test: check historical source manifests against their recorded commits

Manifests and receipts unchanged. Each of the 8 group-A identity tests now
extracts its manifest's recorded commit and verifies hashes there instead of
against the current checkout. Tamper assertions and runner source refusals are
kept; missing recorded history is an explicit failure, not a skip or repin.

tests/unit/historical_tree.py

@@ -0,0 +1,46 @@
+"""Check historical source manifests against their own recorded commit, not today's checkout."""
+
+import io
+from pathlib import Path
+import subprocess
+import tarfile
+
+ROOT = Path(__file__).resolve().parents[2]
+
+
+def _require(commit):
+    """Missing recorded history is an explicit failure, never a skip or a repin."""
+    found = subprocess.run(
+        ["git", "-C", str(ROOT), "cat-file", "-e", commit + "^{commit}"],
+        capture_output=True,
+    )
+    if found.returncode:
+        raise AssertionError(
+            f"Required history missing: commit {commit} is not in this clone; "
+            "fetch it instead of repinning or substituting"
+        )
+
+
+def tracked(commit, prefix="src"):
+    """Tracked paths under prefix at the recorded commit."""
+    _require(commit)
+    return set(
+        subprocess.check_output(
+            ["git", "-C", str(ROOT), "ls-tree", "-r", "--name-only", commit, prefix],
+            text=True,
+        ).splitlines()
+    )
+
+
+def historical_tree(commit, dest):
+    """Extract the tracked tree of the recorded commit into dest."""
+    _require(commit)
+    archive = subprocess.check_output(
+        ["git", "-C", str(ROOT), "archive", "--format=tar", commit]
+    )
+    dest = Path(dest)
+    dest.mkdir(parents=True, exist_ok=True)
+    extra = {"filter": "data"} if hasattr(tarfile, "data_filter") else {}
+    with tarfile.open(fileobj=io.BytesIO(archive)) as tar:
+        tar.extractall(dest, **extra)
+    return dest

tests/unit/test_jet_circle_cv.py

@@ -8,6 +8,7 @@ import numpy as np
 ROOT = Path(__file__).resolve().parents[2]
 REPO = ROOT
 sys.path.insert(0, str(ROOT / "tests/validation"))
+sys.path.insert(0, str(ROOT / "tests/unit"))
 sys.path.insert(0, str(REPO / "src"))
 from run_jet_circle_cv import (
     CX,
@@ -19,6 +20,7 @@ from run_jet_circle_cv import (
     cv_from_macros,
     aperture_probe,
     measured_aperture_flux,
+    PIN,
     verify,
 )
 
@@ -166,7 +168,13 @@ class Host(unittest.TestCase):
         self.assertEqual(a["steps"] * 4, b["steps"])
 
     def test_source_pin(self):
-        verify(REPO)
+        from tempfile import TemporaryDirectory
+        from historical_tree import historical_tree
+
+        with TemporaryDirectory() as directory:
+            verify(historical_tree(PIN, directory))
+        with self.assertRaisesRegex(RuntimeError, "Source hash mismatch"):
+            verify(REPO)
 
 
 if __name__ == "__main__":

tests/unit/test_les_flow_runner.py

@@ -15,6 +15,10 @@ sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "validation"))
 from run_uniform_les_flow import source_guard, decode_macros, HERE, HEADER
 
 ROOT = HERE.parents[1]
+sys.path.insert(0, str(ROOT / "tests/unit"))
+from historical_tree import historical_tree, tracked
+
+A135 = "a135252ae78b47b57d7e77d19001700b3bedac8b"
 
 
 class GuardTests(unittest.TestCase):
@@ -42,19 +46,20 @@ class GuardTests(unittest.TestCase):
             decode_macros(invalid, w, cx, cy)
 
     def test_current_corrected_pins(self):
-        self.assertEqual(
+        with TemporaryDirectory() as directory:
-            source_guard(ROOT, "corrected", "a135252")["base_commit"],
+            root = historical_tree(A135, directory)
-            "a135252ae78b47b57d7e77d19001700b3bedac8b",
+            with patch("run_uniform_les_flow.subprocess.check_output", return_value=A135 + "\n"):
-        )
+                self.assertEqual(source_guard(root, "corrected", "a135252")["base_commit"], A135)
 
     def test_corrected_and_tamper_guard(self):
         pins = json.loads((HERE / "data/les_flow/source_pins_a135252.json").read_text())
         with TemporaryDirectory() as directory:
-            root = Path(directory)
+            origin = historical_tree(A135, Path(directory) / "origin")
+            root = Path(directory) / "fixture"
             for name in pins["sources"]:
                 dest = root / name
                 dest.parent.mkdir(parents=True, exist_ok=True)
-                shutil.copyfile(ROOT / name, dest)
+                shutil.copyfile(origin / name, dest)
             with patch(
                 "run_uniform_les_flow.subprocess.check_output",
                 return_value="isolated-fixture\n",
@@ -87,23 +92,26 @@ class GuardTests(unittest.TestCase):
 
     def test_current_manifest_pins_actual_corrected_tree(self):
         pins = json.loads((HERE / "data/les_flow/source_pins_a135252.json").read_text())
-        tracked = subprocess.check_output(["git", "-C", str(ROOT), "ls-files", "src"], text=True)
+        self.assertEqual(pins["base_commit"], A135)
-        self.assertEqual(set(pins["sources"]), set(tracked.splitlines()))
+        self.assertEqual(set(pins["sources"]), tracked(A135))
-        for name, expected in pins["sources"].items():
+        with TemporaryDirectory() as directory:
-            self.assertEqual(hashlib.sha256((ROOT / name).read_bytes()).hexdigest(), expected)
+            root = historical_tree(A135, directory)
-        self.assertEqual(pins["sources"][HEADER], pins["candidate_header_sha256"])
+            for name, expected in pins["sources"].items():
-        self.assertNotEqual(pins["sources"][HEADER], pins["baseline_header_sha256"])
+                self.assertEqual(hashlib.sha256((root / name).read_bytes()).hexdigest(), expected)
-        with self.assertRaisesRegex(RuntimeError, "Source pin mismatch"):
+            self.assertEqual(pins["sources"][HEADER], pins["candidate_header_sha256"])
-            source_guard(ROOT, "baseline", "a135252")
+            self.assertNotEqual(pins["sources"][HEADER], pins["baseline_header_sha256"])
+            with self.assertRaisesRegex(RuntimeError, "Source pin mismatch"):
+                source_guard(root, "baseline", "a135252")
 
     def test_named_baseline_accepts_only_reversed_header(self):
         pins = json.loads((HERE / "data/les_flow/source_pins_a135252.json").read_text())
         with TemporaryDirectory() as directory:
-            root = Path(directory)
+            origin = historical_tree(A135, Path(directory) / "origin")
+            root = Path(directory) / "fixture"
             for name in pins["sources"]:
                 dest = root / name
                 dest.parent.mkdir(parents=True, exist_ok=True)
-                shutil.copyfile(ROOT / name, dest)
+                shutil.copyfile(origin / name, dest)
             subprocess.run(["git", "apply", "--reverse", str(HERE / "les/data/smagorinsky_normalization.patch")], cwd=root, check=True)
             with patch("run_uniform_les_flow.subprocess.check_output", return_value="baseline-fixture\n"):
                 source_guard(root, "baseline", "a135252")

tests/unit/test_re100.py

@@ -5,6 +5,7 @@ import pytest
 
 ROOT = Path(__file__).resolve().parents[2]
 sys.path.insert(0, str(ROOT / "tests/validation"))
+sys.path.insert(0, str(ROOT / "tests/unit"))
 import re100_helpers as h
 import periodic as p
 
@@ -62,13 +63,16 @@ def test_periodic_synthetic():
     assert not p.assess(rows()[:100])["periodic"]
 
 
-def test_production_unmodified():
+def test_production_unmodified(tmp_path):
+    from historical_tree import historical_tree
+
     m = json.loads(
         (ROOT / "tests/validation/data/dfg_re100/source_manifest.json").read_text()
     )
     assert m["commit"] == h.PIN
+    origin = historical_tree(m["commit"], tmp_path)
     for name, digest in m["production_sha256"].items():
-        assert hashlib.sha256((ROOT / name).read_bytes()).hexdigest() == digest, name
+        assert hashlib.sha256((origin / name).read_bytes()).hexdigest() == digest, name
 
 
 def test_reference():

tests/unit/test_refined_dfg.py

@@ -7,7 +7,10 @@ import numpy as np
 import unittest
 
 sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "validation"))
+sys.path.insert(0, str(Path(__file__).resolve().parent))
 import run_refined_dfg as r
+from historical_tree import historical_tree
+from tempfile import TemporaryDirectory
 
 h, periodic = r.helpers(r.DEFAULT_SOURCE)
 
@@ -17,7 +20,20 @@ def test_source_pin():
     assert historical["commit"].startswith("cd3a657")
     mrt_history = json.loads((r.HERE / "data/refined_dfg/source_manifest_mrt.json").read_text())
     assert mrt_history["commit"].startswith("3ea131e")
-    assert r.verify_source(r.DEFAULT_SOURCE, "MRT", "window")["commit"].startswith("a233c90")
+    with TemporaryDirectory() as directory:
+        for collision, mode, prefix in (
+            ("SRT", "last_base_step", "cd3a657"),
+            ("MRT", "last_base_step", "3ea131e"),
+            ("MRT", "window", "a233c90"),
+        ):
+            name = {"SRT": "source_manifest.json", "MRT": "source_manifest_mrt.json"}[collision]
+            name = "source_manifest_window.json" if mode == "window" else name
+            commit = json.loads((r.HERE / "data/refined_dfg" / name).read_text())["commit"]
+            assert commit.startswith(prefix)
+            root = historical_tree(commit, Path(directory) / commit)
+            assert r.verify_source(root, collision, mode)["commit"] == commit
+    with unittest.TestCase().assertRaisesRegex(RuntimeError, "Source mismatch"):
+        r.verify_source(r.DEFAULT_SOURCE, "MRT", "window")
     with unittest.TestCase().assertRaisesRegex(RuntimeError, "Source mismatch"):
         r.verify_source(r.DEFAULT_SOURCE, "MRT")
     with unittest.TestCase().assertRaisesRegex(RuntimeError, "Source mismatch"):

tests/unit/test_validation_source_provenance.py

@@ -12,13 +12,15 @@ from source_provenance import checkout_provenance
 import re100_helpers
 import run_jet_circle_cv
 
+sys.path.insert(0, str(ROOT / "tests/unit"))
+from historical_tree import historical_tree, tracked
+
 ORIGIN = "47b05bc8abfc957fe876b0c63bdb386e3c6cbaa5"
 
 
-def test_manifests_cover_current_source_and_preserve_origin():
+def test_manifests_cover_current_source_and_preserve_origin(tmp_path):
-    names = subprocess.check_output(
+    names = tracked(ORIGIN)
-        ["git", "-C", str(ROOT), "ls-files", "src"], text=True
+    origin = historical_tree(ORIGIN, tmp_path)
-    ).splitlines()
     for group, hashes_key, revision_key in (
         ("dfg_re100", "production_sha256", "commit"),
         ("jet_circle_cv", "files", "revision"),
@@ -38,7 +40,7 @@ def test_manifests_cover_current_source_and_preserve_origin():
         assert "not inherited from d79" in manifest["experiment"]
         for name, expected in manifest[hashes_key].items():
             assert (
-                hashlib.sha256((ROOT / name).read_bytes()).hexdigest() == expected
+                hashlib.sha256((origin / name).read_bytes()).hexdigest() == expected
             ), name
     assert re100_helpers.PIN == run_jet_circle_cv.PIN == ORIGIN