Reject stale native runtime build provenance before release staging

tools/embeddinggemma2/build_runtime.py

@@ -9,10 +9,11 @@ from pathlib import Path
 import shutil
 import subprocess
 import sys
+from runtime_provenance import fingerprint, UPSTREAM_COMMIT
 
 ROOT = Path(__file__).resolve().parents[2]
 TAG = "b11461"
-COMMIT = "4d756bc72bf00a4aacf410ae15a2d315f3db400d"
+COMMIT = UPSTREAM_COMMIT
 WINDOWS_CRT_FILES = (
     "concrt140.dll", "msvcp140.dll", "msvcp140_1.dll", "msvcp140_2.dll",
     "msvcp140_atomic_wait.dll", "msvcp140_codecvt_ids.dll", "vccorlib140.dll",
@@ -40,7 +41,7 @@ def elf_dynamic(path):
     return values
 
 
-def bundle_linux_libraries(build):
+def bundle_linux_libraries(build, provenance=None):
     """Flatten approved SONAME files beside the worker and record dependency closure.
 
     System libc/C++ ABI remains a declared distro compatibility gate. Vulkan's
@@ -94,6 +95,7 @@ def bundle_linux_libraries(build):
         with path.open("rb") as stream:
             return hashlib.file_digest(stream, "sha256").hexdigest()
     inventory = {"platform": "linux", "worker_sha256": checksum(worker),
+        "build_provenance": provenance if provenance is not None else fingerprint(ROOT),
         "libraries": [{"path": path.name, "bytes": path.stat().st_size, "sha256": checksum(path)}
                       for _, path, _ in sorted(records)]}
     temporary = build / "runtime-libraries.json.partial"
@@ -188,10 +190,13 @@ def main():
         except ImportError as error:
             raise RuntimeError("Install CMake first (python -m pip install cmake)") from error
     worker_source = ROOT / "crates/searchi-semantic/native"
+    provenance = fingerprint(ROOT)
     run([cmake_exe, "-S", worker_source, "-B", build,
          "-DCMAKE_BUILD_TYPE=Release", f"-DLLAMA_CPP_DIR={source}",
          f"-DSEARCHI_ACCELERATION={args.backend}"])
     run([cmake_exe, "--build", build, "--config", "Release", "--parallel", args.jobs])
+    if fingerprint(ROOT) != provenance:
+        raise RuntimeError("Native build inputs changed during compilation; rerun the build")
     if vulkan_loader:
         for name in ["vulkan-1.dll", "VULKAN-LICENSE.txt"]:
             shutil.copy2(vulkan_loader / name, build / "Release" / name)
@@ -202,13 +207,14 @@ def main():
             with path.open("rb") as stream:
                 return hashlib.file_digest(stream, "sha256").hexdigest()
         inventory = {"worker_sha256": checksum(directory / "searchi-gemma-worker.exe"),
+            "build_provenance": provenance,
             "libraries": [{"path": path.name, "bytes": path.stat().st_size, "sha256": checksum(path)}
                 for path in sorted(directory.glob("*.dll"))]}
         temporary = directory / "runtime-libraries.json.partial"
         temporary.write_text(json.dumps(inventory, indent=2), encoding="utf-8")
         os.replace(temporary, directory / "runtime-libraries.json")
     if linux_dispatch(args.backend):
-        bundle_linux_libraries(build)
+        bundle_linux_libraries(build, provenance)
     print(f"Runtime build complete: {build}")
 
 

tools/embeddinggemma2/runtime_provenance.py

@@ -0,0 +1,34 @@
+"""Build-input identity for detecting stale, otherwise checksum-valid runtimes."""
+import hashlib
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[2]
+UPSTREAM_COMMIT = "4d756bc72bf00a4aacf410ae15a2d315f3db400d"
+INPUTS = (
+    "crates/searchi-semantic/native/worker.cpp",
+    "crates/searchi-semantic/native/CMakeLists.txt",
+    "tools/embeddinggemma2/build_runtime.py",
+    "tools/embeddinggemma2/no-logits.patch",
+    "tools/embeddinggemma2/cpu-dispatch.patch",
+    "tools/embeddinggemma2/cpu-only-loader.patch",
+)
+
+
+def fingerprint(root=ROOT):
+    hashes = {}
+    for name in INPUTS:
+        path = Path(root) / name
+        with path.open("rb") as source:
+            data = source.read(1024 * 1024 + 1)
+        if not data or len(data) > 1024 * 1024:
+            raise ValueError("Native build input is empty or oversized")
+        # Only build-source line endings are canonicalized; indexed user bytes
+        # and extraction provenance are never processed by this helper.
+        hashes[name] = hashlib.sha256(data.replace(b"\r\n", b"\n")).hexdigest()
+    return {"schema": 1, "upstream_commit": UPSTREAM_COMMIT,
+            "normalization": "CRLF-to-LF build inputs only", "inputs": hashes}
+
+
+def verify(manifest, root=ROOT):
+    if not isinstance(manifest.get("build_provenance"), dict) or manifest["build_provenance"] != fingerprint(root):
+        raise ValueError("Runtime build provenance missing or stale; rebuild the normal native runtime")

tools/embeddinggemma2/stage_runtime.py

@@ -10,6 +10,7 @@ import shutil
 import stat
 import time
 import uuid
+from runtime_provenance import verify as verify_provenance
 
 ROOT = Path(__file__).resolve().parents[2]
 CRT_LIBRARIES = {"concrt140.dll", "msvcp140.dll", "msvcp140_1.dll", "msvcp140_2.dll", "msvcp140_atomic_wait.dll", "msvcp140_codecvt_ids.dll", "vccorlib140.dll", "vcruntime140.dll", "vcruntime140_1.dll", "vcruntime140_threads.dll"}
@@ -339,6 +340,11 @@ def verify_runtime(source, required=False):
     manifest = json.loads(inventory.read_text(encoding="utf-8"))
     if not isinstance(manifest, dict):
         raise RuntimeError("Invalid runtime dependency inventory")
+    if required or "build_provenance" in manifest:
+        try:
+            verify_provenance(manifest, ROOT)
+        except ValueError as error:
+            raise RuntimeError(str(error)) from error
     with source.open("rb") as stream:
         if hashlib.file_digest(stream, "sha256").hexdigest() != manifest.get("worker_sha256"):
             raise RuntimeError("Runtime worker checksum mismatch")

tools/embeddinggemma2/test_runtime_provenance.py

@@ -0,0 +1,39 @@
+from pathlib import Path
+import tempfile
+import unittest
+
+import runtime_provenance as provenance
+
+
+class ProvenanceTests(unittest.TestCase):
+    def test_line_endings_equivalent_but_changed_source_rejected(self):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            for name in provenance.INPUTS:
+                path = root / name
+                path.parent.mkdir(parents=True, exist_ok=True)
+                path.write_bytes(b"first\nsecond\n")
+            manifest = {"build_provenance": provenance.fingerprint(root)}
+            for name in provenance.INPUTS:
+                (root / name).write_bytes(b"first\r\nsecond\r\n")
+            provenance.verify(manifest, root)
+            (root / provenance.INPUTS[0]).write_bytes(b"different source\n")
+            with self.assertRaisesRegex(ValueError, "stale"):
+                provenance.verify(manifest, root)
+
+    def test_missing_old_inventory_rejected_and_inputs_bounded(self):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            for name in provenance.INPUTS:
+                path = root / name
+                path.parent.mkdir(parents=True, exist_ok=True)
+                path.write_bytes(b"source\n")
+            with self.assertRaisesRegex(ValueError, "missing or stale"):
+                provenance.verify({"worker_sha256": "old-valid-hash"}, root)
+            (root / provenance.INPUTS[0]).write_bytes(b"x" * (1024 * 1024 + 1))
+            with self.assertRaisesRegex(ValueError, "oversized"):
+                provenance.fingerprint(root)
+
+
+if __name__ == "__main__":
+    unittest.main()

tools/embeddinggemma2/test_stage_runtime.py

@@ -9,6 +9,7 @@ import unittest
 from unittest.mock import patch
 
 import stage_runtime
+import runtime_provenance
 
 
 class StagingTests(unittest.TestCase):
@@ -28,7 +29,7 @@ class StagingTests(unittest.TestCase):
                 records.append({"path": name, "bytes": path.stat().st_size,
                                 "sha256": hashlib.sha256(path.read_bytes()).hexdigest()})
             inventory = runtime / "runtime-libraries.json"
-            inventory.write_text(json.dumps({"platform": "linux", "worker_sha256": hashlib.sha256(worker.read_bytes()).hexdigest(), "libraries": records}))
+            inventory.write_text(json.dumps({"platform": "linux", "worker_sha256": hashlib.sha256(worker.read_bytes()).hexdigest(), "build_provenance": runtime_provenance.fingerprint(), "libraries": records}))
             dependencies = stage_runtime.verify_runtime(worker, True)
             destination = root / "resources"
             destination.mkdir()
@@ -419,6 +420,10 @@ class StagingTests(unittest.TestCase):
     def test_missing_crt_notice_preserves_existing_staged_worker(self):
         with tempfile.TemporaryDirectory() as directory:
             root = Path(directory)
+            for name in runtime_provenance.INPUTS:
+                path = root / name
+                path.parent.mkdir(parents=True, exist_ok=True)
+                path.write_bytes((runtime_provenance.ROOT / name).read_bytes())
             runtime = root / ".searchi/runtime/auto/Release"
             runtime.mkdir(parents=True)
             worker = runtime / "searchi-gemma-worker.exe"
@@ -429,7 +434,7 @@ class StagingTests(unittest.TestCase):
                 data = name.encode()
                 (runtime / name).write_bytes(data)
                 records.append({"path": name, "bytes": len(data), "sha256": hashlib.sha256(data).hexdigest()})
-            (runtime / "runtime-libraries.json").write_text(json.dumps({"worker_sha256": hashlib.sha256(worker.read_bytes()).hexdigest(), "libraries": records}))
+            (runtime / "runtime-libraries.json").write_text(json.dumps({"worker_sha256": hashlib.sha256(worker.read_bytes()).hexdigest(), "build_provenance": runtime_provenance.fingerprint(root), "libraries": records}))
             license_path = root / ".searchi/references/llama.cpp/LICENSE"
             license_path.parent.mkdir(parents=True)
             license_path.write_text("license")