fix(contributor-scan): retain declared Gruntfile and report census gaps honestly

tests/test_frontend_retention.py

@@ -29,3 +29,9 @@ def test_builder_rejects_unrecognized_dependency_before_download(tmp_path):
         builder.build(tmp_path)
     assert jar.read_bytes() == b"different dependency"
     assert not (tmp_path / "ousast-frontend-retention-v1").exists()
+
+
+def test_build_config_retention_is_explicit_and_overrides_ambient_policy(monkeypatch):
+    monkeypatch.setenv("OUSAST_INCLUDE_BUILD_CONFIGS", "0")
+    assert JoernBackend()._jvm_env()["OUSAST_INCLUDE_BUILD_CONFIGS"] == "1"
+    assert JoernBackend(include_build_configs=False)._jvm_env()["OUSAST_INCLUDE_BUILD_CONFIGS"] == "0"

tests/test_model_partitions.py

@@ -1,5 +1,7 @@
 from pathlib import Path
 
+import pytest
+
 from openultrasast.cpg.backend import CpgResult
 from openultrasast.model.regions import ScanRegion
 from openultrasast.model.scan import ScanBudget, scan_repository
@@ -153,7 +155,8 @@ def test_unsupported_only_population_is_named(tmp_path):
     assert "frontend_unsupported" in result.scope.unresolved_boundaries
 
 
-def test_partial_partition_census_never_completes_questions(tmp_path):
+@pytest.mark.parametrize("census", [[{"methods": 2, "files": 1}], [], ["invalid"], None])
+def test_partial_partition_census_never_completes_questions(tmp_path, census):
     for name in ("a.py", "b.py"):
         (tmp_path / name).write_text("print('readable')")
 
@@ -162,13 +165,14 @@ def test_partial_partition_census_never_completes_questions(tmp_path):
             return CpgResult(
                 Path("graph"),
                 lambda q, p: [],
-                run_batch=lambda q, reqs: {**{rid: [] for rid in reqs}, "__census__": [{"methods": 2, "files": 1}]},
+                run_batch=lambda q, reqs: {**{rid: [] for rid in reqs}, **({"__census__": census} if census is not None else {})},
             )
 
     region = ScanRegion(path="a.py", function="f", language="python", families=("injection",), rank=1.0, source="entry_point")
     result = scan_repository(tmp_path, [region], backend=Backend(), budget=ScanBudget(tiering=False))
     assert result.question_outcomes[0].status == "unresolved"
-    assert "cpg_empty" in result.scope.unresolved_boundaries
+    assert "partition_file_census_unavailable" in result.scope.unresolved_boundaries
+    assert "cpg_empty" not in result.scope.unresolved_boundaries
 
 
 def test_projection_refuses_substituted_ancestor(tmp_path):
@@ -286,7 +290,9 @@ def test_synthetic_census_node_cannot_mask_missing_source(tmp_path):
     graph = build_partitions(tmp_path, build, None)
     try:
         result = graph.run_batch("taint", {"q": {"file": "a.php"}})
-        assert result["__census__"][0]["files"] == 0
+        assert result["__census__"][0]["files"] == 2
+        assert result["__census__"][0]["methods"] == 3
+        assert result["__census__"][0]["missing_file_names"] == ["b.php"]
         assert "partition_file_census_incomplete" in graph.execution_diagnostics()
     finally:
         graph.cleanup()
@@ -331,7 +337,10 @@ def test_unnamed_sharded_census_remains_explicitly_incomplete(tmp_path):
     )
     try:
         result = graph.run_batch("taint", {"q": {"file": "app.php"}})
-        assert result["__census__"] == [{"methods": 0, "files": 0, "shards": 2}]
+        assert result["__census__"][0]["methods"] == 20
+        assert result["__census__"][0]["files"] == 20
+        assert result["__census__"][0]["shards"] == 2
+        assert result["__census__"][0]["census_failure"] == "partition_file_census_unavailable"
         assert "partition_file_census_unavailable" in graph.execution_diagnostics()
     finally:
         graph.cleanup()

tests/test_model_scan.py

@@ -463,7 +463,15 @@ def test_tier_zero_pairs_are_not_asked_and_nothing_else_is_skipped(tmp_path: Pat
                 issued.append({"kind": kind, "count": len(requests)})
                 return {rid: [] for rid in requests}
 
-            return CpgResult(cpg_path=Path("cpg.bin"), run=lambda q, p: [], run_batch=batch)
+            names = [str(p) for p in root.rglob("*.py")]
+            return CpgResult(
+                cpg_path=Path("cpg.bin"),
+                run=lambda q, p: [],
+                run_batch=lambda kind, requests: {
+                    "__census__": [{"methods": len(names), "files": len(names), "file_names": names}],
+                    **batch(kind, requests),
+                },
+            )
 
     region = ScanRegion(
         path="a.py", function="run", language="python", families=("injection", "path", "deserialization"), rank=0.9, source="entry_point"
@@ -521,7 +529,15 @@ def test_the_budget_is_spent_by_evidence_when_asked(tmp_path: Path) -> None:
                     self.taint_files.append(sorted({str(p.get("file", "")) for p in requests.values()}))
                 return {rid: [] for rid in requests}
 
-            return CpgResult(cpg_path=Path("cpg.bin"), run=lambda q, p: [], run_batch=batch)
+            names = [str(p) for p in root.rglob("*.py")]
+            return CpgResult(
+                cpg_path=Path("cpg.bin"),
+                run=lambda q, p: [],
+                run_batch=lambda kind, requests: {
+                    "__census__": [{"methods": len(names), "files": len(names), "file_names": names}],
+                    **batch(kind, requests),
+                },
+            )
 
     top = ScanRegion(path="top.py", function="handle", language="python", families=("injection",), rank=1.0, source="entry_point")
     low = ScanRegion(path="low.py", function="run", language="python", families=("injection",), rank=0.3, source="entry_point")

tests/test_model_scope.py

@@ -26,7 +26,12 @@ class Backend:
         assert any(p.read_bytes() for p in root.rglob("*") if p.is_file())
         if self.fail:
             return None
-        return SimpleNamespace(cpg_path=Path("test.cpg"), run_batch=self.batch, cleanup=lambda: None)
+        names = [str(p) for p in root.rglob("*") if p.is_file()]
+
+        def batch(kind, requests):
+            return {"__census__": [{"methods": len(names), "files": len(names), "file_names": names}], **self.batch(kind, requests)}
+
+        return SimpleNamespace(cpg_path=Path("test.cpg"), run_batch=batch, cleanup=lambda: None)
 
     def batch(self, kind, requests):
         if any(p.get("evidenceOnly") == "true" for p in requests.values()):

tests/test_push_policy.py

@@ -117,7 +117,14 @@ def test_targeted_base_uses_real_driver_same_deadline(tmp_path):
             assert (root / "a.js").read_bytes()
             seen.append(execution_budget)
             rows = json.loads(scan(line=5, sanitized=True).question_outcomes[0].raw_rows_json)
-            return CpgResult(Path("graph"), lambda kind, params: rows)
+            return CpgResult(
+                Path("graph"),
+                lambda kind, params: rows,
+                run_batch=lambda kind, requests: {
+                    **{rid: rows for rid in requests},
+                    "__census__": [{"methods": 1, "files": 1, "file_names": [str(root / "a.js")]}],
+                },
+            )
 
     region = ScanRegion("a.js", "handler", "javascript", ("injection",), 1.0, "entry_point")
     budget = ExecutionBudget(time.monotonic() + 30, 1.0)