feat(agent): make ingestion preparation reproducible

scripts/install.py

@@ -42,13 +42,18 @@ def _safe_regular(path: Path) -> bool:
 
 
 def _validated_state(state: object) -> dict[str, Any]:
-    if not isinstance(state, dict) or set(state) != {
+    base_keys = {
         "format",
         "mode",
         "pack_path",
         "files",
         "routes",
-    }:
+    }
+    if (
+        not isinstance(state, dict)
+        or not base_keys.issubset(state)
+        or set(state) - base_keys - {"run_pins"}
+    ):
         raise ValueError("unrecognized GEWU installation state")
     if (
         state.get("format") != "gewu-install-state@1"
@@ -82,6 +87,38 @@ def _validated_state(state: object) -> dict[str, Any]:
             or not re.fullmatch(r"[a-f0-9]{64}", route["block_sha256"])
         ):
             raise ValueError("GEWU installation routes are invalid")
+    if "run_pins" in state:
+        pins = state["run_pins"]
+        if not isinstance(pins, dict) or set(pins) != {
+            "pack_id",
+            "pack_version",
+            "pack_snapshot_digest",
+            "module_pins",
+        }:
+            raise ValueError("GEWU run pins are invalid")
+        if (
+            not isinstance(pins.get("pack_id"), str)
+            or not pins["pack_id"]
+            or not isinstance(pins.get("pack_version"), str)
+            or not pins["pack_version"]
+            or not isinstance(pins.get("pack_snapshot_digest"), str)
+            or not re.fullmatch(r"[a-f0-9]{64}", pins["pack_snapshot_digest"])
+            or not isinstance(pins.get("module_pins"), list)
+            or not pins["module_pins"]
+        ):
+            raise ValueError("GEWU run pins are invalid")
+        for module in pins["module_pins"]:
+            if (
+                not isinstance(module, dict)
+                or set(module) != {"module_id", "implementation_version", "sha256"}
+                or not isinstance(module.get("module_id"), str)
+                or not module["module_id"]
+                or not isinstance(module.get("implementation_version"), str)
+                or not module["implementation_version"]
+                or not isinstance(module.get("sha256"), str)
+                or not re.fullmatch(r"[a-f0-9]{64}", module["sha256"])
+            ):
+                raise ValueError("GEWU run pins are invalid")
     return state
 
 
@@ -159,6 +196,7 @@ def install(workspace: Path, source: Path = PACK_ROOT, mode: str = "integrated")
 
     # Prepare all bytes and validate the destinations before mutating the workspace.
     copied = {name: path.read_bytes() for name, path in source_files.items()}
+    manifest = json.loads(copied["manifest.json"])
     route_originals = {
         name: target.read_bytes() if target.exists() else None for name, target in targets.items()
     }
@@ -171,6 +209,19 @@ def install(workspace: Path, source: Path = PACK_ROOT, mode: str = "integrated")
         "mode": mode,
         "pack_path": PACK_DIR.as_posix(),
         "files": {name: digest(content) for name, content in copied.items()},
+        "run_pins": {
+            "pack_id": manifest["pack_id"],
+            "pack_version": manifest["pack_version"],
+            "pack_snapshot_digest": manifest["snapshot"]["digest"],
+            "module_pins": [
+                {
+                    "module_id": module["module_id"],
+                    "implementation_version": module["implementation_version"],
+                    "sha256": module["sha256"],
+                }
+                for module in manifest["modules"]
+            ],
+        },
         "routes": {
             name: {
                 "block_sha256": digest(route_blocks[name]),