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

src/openultrasast/cpg/backend.py

@@ -267,7 +267,11 @@ class NullBackend:
 
 
 def engine_runtime_identity(
-    *, include_tests: bool = True, language: str | None = None, execution_budget: ExecutionBudget | None = None
+    *,
+    include_tests: bool = True,
+    include_build_configs: bool = True,
+    language: str | None = None,
+    execution_budget: ExecutionBudget | None = None,
 ) -> str:
     """Installed frontend/adaptation bytes, also used by comparison eligibility provenance."""
     from .artifact import digest_value, graph_bytes
@@ -296,6 +300,7 @@ def engine_runtime_identity(
             "version": version,
             "files": installation,
             "include_tests": include_tests,
+            "include_build_configs": include_build_configs,
             "java_options": os.environ.get("JAVA_TOOL_OPTIONS", ""),
         }
     )
@@ -307,6 +312,7 @@ class JoernBackend:
 
     runner: Runner | None = None
     include_tests: bool = True  # Explicit input policy for the versioned frontend adaptation.
+    include_build_configs: bool = True  # Explicit retention of supported build configuration source.
     build_timeout: int = BUILD_TIMEOUT_SECONDS
     query_timeout: int = field(default_factory=lambda: _configured_timeout())
     heap_mb: int = 0  # 0 means read the environment, then fall back to CPG_HEAP_MB
@@ -380,10 +386,14 @@ class JoernBackend:
             (("implementation", code),),
             (
                 ("include_tests", str(self.include_tests)),
+                ("include_build_configs", str(self.include_build_configs)),
                 (
                     "installation",
                     engine_runtime_identity(
-                        include_tests=self.include_tests, language=language, execution_budget=execution_budget or self.execution_budget
+                        include_tests=self.include_tests,
+                        include_build_configs=self.include_build_configs,
+                        language=language,
+                        execution_budget=execution_budget or self.execution_budget,
                     ),
                 ),
                 ("java_options", os.environ.get("JAVA_TOOL_OPTIONS", "default") or "default"),
@@ -1189,6 +1199,7 @@ class JoernBackend:
         """
         env = dict(os.environ)
         env["OUSAST_INCLUDE_TESTS"] = "1" if self.include_tests else "0"
+        env["OUSAST_INCLUDE_BUILD_CONFIGS"] = "1" if self.include_build_configs else "0"
         env["JAVA_TOOL_OPTIONS"] = f"{env.get('JAVA_TOOL_OPTIONS', '').strip()} -Xmx{self._heap_mb()}m".strip()
         return env
 

src/openultrasast/model/partitions.py

@@ -106,6 +106,9 @@ class PartitionGraph:
             raw = batch(kind, selected) if callable(batch) else {rid: graph.run(kind, params) for rid, params in selected.items()}
             if not isinstance(raw, Mapping):
                 continue
+            raw = dict(raw)
+            if not isinstance(raw.get("__census__"), list):
+                raw["__census__"] = []
             for rid, rows in raw.items():
                 if rid in selected and isinstance(rows, list):
                     answers[rid] = self._normalize(rows)
@@ -117,17 +120,18 @@ class PartitionGraph:
                     observed = {p.removeprefix("./") for n in names if isinstance(n, list) for p in n if isinstance(p, str)}
                     if not named or not expected <= observed:
                         self.diagnostics.append("partition_file_census_incomplete" if named else "partition_file_census_unavailable")
+                        reason = "partition_file_census_incomplete" if named else "partition_file_census_unavailable"
                         rows = [
-                            {
-                                "methods": 0,
-                                "files": 0,
-                                "shards": max((int(str(r.get("shards", 1))) for r in rows if isinstance(r, Mapping)), default=1),
-                            }
-                        ]
+                            dict(r, census_failure=reason, missing_file_names=sorted(expected - observed) if named else [])
+                            for r in normalized
+                            if isinstance(r, Mapping)
+                        ] or [{"census_failure": reason, "missing_file_names": []}]
                     # Preserve any individual empty or sharded graph's degradation.
                     previous = answers.get(rid, [])
                     if not previous or any(
-                        isinstance(r, Mapping) and (int(str(r.get("methods", 0))) == 0 or int(str(r.get("shards", 1))) > 1) for r in rows
+                        isinstance(r, Mapping)
+                        and (r.get("census_failure") or int(str(r.get("methods", 0))) == 0 or int(str(r.get("shards", 1))) > 1)
+                        for r in rows
                     ):
                         answers[rid] = rows
         return answers

src/openultrasast/model/scan.py

@@ -355,6 +355,8 @@ def _scan_repository_impl(
             in {
                 "files_unparsed",
                 "cpg_empty",
+                "partition_file_census_incomplete",
+                "partition_file_census_unavailable",
                 "cpg_sharded",
                 "cross_partition_semantics_unresolved",
                 "vendor_semantics_unresolved",
@@ -410,8 +412,14 @@ def _scan_repository_impl(
                 if census and not census_reported:
                     entry = census[0] if isinstance(census[0], Mapping) else {}
                     methods = int(str(entry.get("methods", "0")) or 0)
-                    if methods == 0:
-                        degradations.append({"stage": "model", "reason": "cpg_empty", "files": int(str(entry.get("files", "0")) or 0)})
+                    if methods == 0 or entry.get("census_failure"):
+                        degradations.append(
+                            {
+                                "stage": "model",
+                                "reason": "cpg_empty" if "methods" in entry and methods == 0 else entry.get("census_failure", "cpg_empty"),
+                                **{k: entry[k] for k in ("methods", "files", "missing_file_names") if k in entry},
+                            }
+                        )
                     # More than one graph means some files could only be built apart from the rest, and a
                     # flow whose source is in one shard and whose sink is in another does not exist for any
                     # question we can ask. Reporting the split is the difference between a partial answer and
@@ -508,6 +516,8 @@ def _scan_repository_impl(
         in {
             "files_unparsed",
             "cpg_empty",
+            "partition_file_census_incomplete",
+            "partition_file_census_unavailable",
             "cpg_sharded",
             "cross_partition_semantics_unresolved",
             "vendor_semantics_unresolved",
@@ -741,8 +751,14 @@ def _evidence_pass(
             shards = int(str(entry.get("shards", "1")))
         except ValueError:
             methods, shards = 0, 1
-        if methods <= 0:
-            degradations.append({"stage": "model", "reason": "cpg_empty"})
+        if methods <= 0 or entry.get("census_failure"):
+            degradations.append(
+                {
+                    "stage": "model",
+                    "reason": "cpg_empty" if "methods" in entry and methods <= 0 else entry.get("census_failure", "cpg_empty"),
+                    **{k: entry[k] for k in ("methods", "files", "missing_file_names") if k in entry},
+                }
+            )
         if shards > 1:
             degradations.append({"stage": "model", "reason": "cpg_sharded", "shards": shards})
     by_rid = {rid: (region, spec) for rid, region, spec in work}