test: run history-independent identity checks before the history lookup

tests/unit/test_jet_circle_cv.py

@@ -171,10 +171,10 @@ class Host(unittest.TestCase):
         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)
+        with TemporaryDirectory() as directory:
+            verify(historical_tree(PIN, directory))
 
 
 if __name__ == "__main__":

tests/unit/test_les_flow_runner.py

@@ -48,8 +48,11 @@ class GuardTests(unittest.TestCase):
     def test_current_corrected_pins(self):
         with TemporaryDirectory() as directory:
             root = historical_tree(A135, directory)
-            with patch("run_uniform_les_flow.subprocess.check_output", return_value=A135 + "\n"):
-                self.assertEqual(source_guard(root, "corrected", "a135252")["base_commit"], A135)
+            with patch("run_uniform_les_flow.subprocess.check_output", return_value="historical-tree\n"):
+                identity = source_guard(root, "corrected", "a135252")
+            # base_commit comes from the pins file; the mock only feeds checkout_commit.
+            self.assertEqual(identity["base_commit"], A135)
+            self.assertEqual(identity["checkout_commit"], "historical-tree")
 
     def test_corrected_and_tamper_guard(self):
         pins = json.loads((HERE / "data/les_flow/source_pins_a135252.json").read_text())

tests/unit/test_refined_dfg.py

@@ -20,6 +20,12 @@ 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")
+    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"):
+        r.verify_source(r.DEFAULT_SOURCE, "SRT")
     with TemporaryDirectory() as directory:
         for collision, mode, prefix in (
             ("SRT", "last_base_step", "cd3a657"),
@@ -32,12 +38,6 @@ def test_source_pin():
             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"):
-        r.verify_source(r.DEFAULT_SOURCE, "SRT")
 
 
 def test_matched_units_and_planes():

tests/unit/test_validation_source_provenance.py

@@ -19,8 +19,8 @@ ORIGIN = "47b05bc8abfc957fe876b0c63bdb386e3c6cbaa5"
 
 
 def test_manifests_cover_current_source_and_preserve_origin(tmp_path):
-    names = tracked(ORIGIN)
-    origin = historical_tree(ORIGIN, tmp_path)
+    assert re100_helpers.PIN == run_jet_circle_cv.PIN == ORIGIN
+    manifests = {}
     for group, hashes_key, revision_key in (
         ("dfg_re100", "production_sha256", "commit"),
         ("jet_circle_cv", "files", "revision"),
@@ -31,18 +31,22 @@ def test_manifests_cover_current_source_and_preserve_origin(tmp_path):
             ).read_text()
         )
         assert manifest[revision_key] == ORIGIN
-        assert set(manifest[hashes_key]) == set(names)
         assert manifest["source_origin_commits"][-1] == ORIGIN
         assert (
             manifest["historical_checkpoints"]["production"]
             == "d79e3f6f0a424f5bcc3a1a6d610313e49daf97a2"
         )
         assert "not inherited from d79" in manifest["experiment"]
-        for name, expected in manifest[hashes_key].items():
+        manifests[group] = manifest[hashes_key]
+    # History-dependent checks last, so a missing commit masks nothing above.
+    names = tracked(ORIGIN)
+    origin = historical_tree(ORIGIN, tmp_path)
+    for group, hashes in manifests.items():
+        assert set(hashes) == set(names), group
+        for name, expected in hashes.items():
             assert (
                 hashlib.sha256((origin / name).read_bytes()).hexdigest() == expected
             ), name
-    assert re100_helpers.PIN == run_jet_circle_cv.PIN == ORIGIN
 
 
 def test_runtime_checkout_identity_is_separate_from_source_origin(tmp_path):