feat: complete knowledge core storage — named graphs, provenance, source material (#973)

Implements all three changes from the knowledge-core-completeness tech spec:

1. Named graph field preserved through Cassandra storage (7-element tuple),
   enabling provenance triples to retain their graph URIs on round-trip.

2. Provenance triples already arrive on triples-input — no routing change
   needed; Change 1 was sufficient.

3. Source material (library documents) streamed alongside triples and
   embeddings during core download/upload. The knowledge manager fetches
   the document hierarchy from the librarian on download and recreates it
   on upload, preserving the full provenance chain across instances.

trustgraph-cli/trustgraph/cli/get_kg_core.py

@@ -47,6 +47,31 @@ def write_ge(f, data):
     )
     f.write(msgpack.packb(msg, use_bin_type=True))
 
+def write_library_metadata(f, data):
+    msg = (
+        "lm",
+        {
+            "i": data["id"],
+            "k": data.get("kind", ""),
+            "t": data.get("title", ""),
+            "p": data.get("parent-id", ""),
+            "d": data.get("document-type", ""),
+            "c": data.get("comments", ""),
+            "g": data.get("tags", []),
+        }
+    )
+    f.write(msgpack.packb(msg, use_bin_type=True))
+
+def write_library_blob(f, data):
+    msg = (
+        "lb",
+        {
+            "i": data["id"],
+            "d": data.get("data", b""),
+        }
+    )
+    f.write(msgpack.packb(msg, use_bin_type=True))
+
 def fetch(url, workspace, id, output, token=None):
 
     api = Api(url=url, token=token, workspace=workspace)
@@ -55,6 +80,8 @@ def fetch(url, workspace, id, output, token=None):
     try:
         ge = 0
         t = 0
+        lm = 0
+        lb = 0
 
         with open(output, "wb") as f:
 
@@ -68,7 +95,15 @@ def fetch(url, workspace, id, output, token=None):
                     ge += 1
                     write_ge(f, response["graph-embeddings"])
 
-        print(f"Got: {t} triple, {ge} GE messages.")
+                if "library-metadata" in response:
+                    lm += 1
+                    write_library_metadata(f, response["library-metadata"])
+
+                if "library-blob" in response:
+                    lb += 1
+                    write_library_blob(f, response["library-blob"])
+
+        print(f"Got: {t} triple, {ge} GE, {lm} library metadata, {lb} library blob messages.")
 
     finally:
         socket.close()

trustgraph-cli/trustgraph/cli/put_kg_core.py

@@ -40,6 +40,23 @@ def read_message(unpacked, id):
             },
             "triples": msg["t"],
         }
+    elif unpacked[0] == "lm":
+        msg = unpacked[1]
+        return "lm", {
+            "id": msg["i"],
+            "kind": msg.get("k", ""),
+            "title": msg.get("t", ""),
+            "parent-id": msg.get("p", ""),
+            "document-type": msg.get("d", ""),
+            "comments": msg.get("c", ""),
+            "tags": msg.get("g", []),
+        }
+    elif unpacked[0] == "lb":
+        msg = unpacked[1]
+        return "lb", {
+            "id": msg["i"],
+            "data": msg.get("d", b""),
+        }
     else:
         raise RuntimeError("Unpacked unexpected messsage type", unpacked[0])
 
@@ -51,6 +68,8 @@ def put(url, workspace, id, input, token=None):
     try:
         ge = 0
         t = 0
+        lm = 0
+        lb = 0
 
         with open(input, "rb") as f:
 
@@ -73,10 +92,18 @@ def put(url, workspace, id, input, token=None):
                     t += 1
                     socket.put_kg_core(id, triples=msg)
 
+                elif kind == "lm":
+                    lm += 1
+                    socket.put_kg_core(id, library_metadata=msg)
+
+                elif kind == "lb":
+                    lb += 1
+                    socket.put_kg_core(id, library_blob=msg)
+
                 else:
                     raise RuntimeError("Unexpected message kind", kind)
 
-        print(f"Put: {t} triple, {ge} GE messages.")
+        print(f"Put: {t} triple, {ge} GE, {lm} library metadata, {lb} library blob messages.")
 
     finally:
         socket.close()