1 files changed, 109 insertions, 0 deletions
diff --git a/packages/meshbay-common/src/meshbay_common/protocol.py b/packages/meshbay-common/src/meshbay_common/protocol.py
index bb52a51..876f465 100644
--- a/packages/meshbay-common/src/meshbay_common/protocol.py
+++ b/packages/meshbay-common/src/meshbay_common/protocol.py
@@ -30,6 +30,7 @@ number — it is a label chosen by the peer, and the only thing it decides is
 which local promise a reply belongs to.
 """
 
+import os
 from dataclasses import dataclass, field
 from typing import Any
 
@@ -37,6 +38,7 @@ from typing import Any
 # second copy here said "0.1" while every message on the wire carried "0.2".
 # Nothing imported it, which is the only reason it was harmless.
 from meshbay_common import MNP_VERSION, MHP_VERSION   # noqa: F401  (re-export)
+from meshbay_common.groupbox import PURPOSE_UPLOAD, seal, unseal
 from meshbay_common.webcrypto import (
     chunk_key_aes,
     decrypt_chunk_aes,
@@ -370,3 +372,110 @@ def file_chunk_plaintext(
         file_hash = bytes.fromhex(msg["file_id"])
     ckey = chunk_key_aes(gek, file_hash, msg["chunk_index"])
     return decrypt_chunk_aes(ckey, msg["nonce"], msg["ct"])
+
+
+# ── Uploads (MNP 2.0) ─────────────────────────────────────────────────────────
+#
+# The write path, sealed under the group key the way the read path always was.
+# One encoder for both directions, here rather than in the client, for the reason
+# `file_chunk` has one: two copies of a wire shape with a single consumer each is
+# how `index_sync` and `file_chunk` forked (finding C6), and nothing noticed
+# until someone went looking.
+#
+# What stays in clear, and why each has to:
+#   `type`, `v`     — routed and version-checked before anything can be decrypted
+#   `upload_id`     — the correlation key. It replaces `filename`, which used to
+#                     play that role and cannot any more: naming the file in clear
+#                     to match an ack against a request would give back exactly
+#                     what the seal is for. Client-chosen, opaque to the node,
+#                     unique within one connection; never an authorization input.
+#   `chunk_index`   — ordering, which the node enforces before it opens anything
+#   `total_chunks`  — how many to expect
+#
+# `group_id` is *not* on the message: the session already decided which group it
+# is on, and the node uses that as the AAD. A client naming its own group here
+# would be choosing which key its bytes are checked against.
+
+UPLOAD_ID_LEN = 16   # 128 bits of client-chosen correlation, hex on the wire
+
+
+def new_upload_id() -> str:
+    """A fresh correlation id for one upload."""
+    return os.urandom(UPLOAD_ID_LEN).hex()
+
+
+def file_upload_wire(
+    gek: bytes,
+    group_id: str,
+    *,
+    upload_id: str,
+    chunk_index: int,
+    total_chunks: int,
+    filename: str,
+    data: bytes,
+    dir: str = "",
+    root: str = "",
+) -> dict:
+    """
+    One sealed `file_upload` chunk.
+
+    `filename`, `dir` and `root` ride inside the seal with the bytes: sealing the
+    content and announcing the name beside it would be theatre. They are repeated
+    on every chunk rather than sent once — a hundred bytes against a 48 KiB chunk
+    — because a header that arrives once is state the node has to carry, and
+    upload state that can disagree with the chunk in hand is what `_free_name` and
+    the chunk-ordering rule exist to prevent.
+    """
+    payload = {"filename": filename, "data": data, "dir": dir, "root": root}
+    return {
+        "type": MNP.FILE_UPLOAD,
+        "v": MNP_VERSION,
+        "upload_id": upload_id,
+        "chunk_index": chunk_index,
+        "total_chunks": total_chunks,
+        **seal(gek, PURPOSE_UPLOAD, MNP.FILE_UPLOAD, group_id, payload),
+    }
+
+
+def file_upload_payload(gek: bytes, group_id: str, msg: dict) -> dict:
+    """
+    Open a `file_upload`. Raises on anything that does not open.
+
+    Never a partial result and never a default: a chunk that does not open is not
+    an empty file with an empty name, it is a peer we cannot talk to. `unseal`
+    says why at length.
+    """
+    return unseal(gek, PURPOSE_UPLOAD, MNP.FILE_UPLOAD, group_id, msg)
+
+
+def file_upload_ack_wire(
+    gek: bytes,
+    group_id: str,
+    *,
+    upload_id: str,
+    chunk_index: int,
+    filename: str,
+    stored_as: str,
+    dir: str = "",
+) -> dict:
+    """
+    The node's answer to one chunk, sealed the same way.
+
+    `stored_as` is the name the node settled on — it finds a free one rather than
+    replacing anything — and `dir` is where it landed. Both name the operator's
+    content, so both belong inside the seal; only `upload_id` and `chunk_index`
+    stay out, because the client matches on them.
+    """
+    payload = {"filename": filename, "stored_as": stored_as, "dir": dir}
+    return {
+        "type": MNP.FILE_UPLOAD_ACK,
+        "v": MNP_VERSION,
+        "upload_id": upload_id,
+        "chunk_index": chunk_index,
+        **seal(gek, PURPOSE_UPLOAD, MNP.FILE_UPLOAD_ACK, group_id, payload),
+    }
+
+
+def file_upload_ack_payload(gek: bytes, group_id: str, msg: dict) -> dict:
+    """Open a `file_upload_ack`. Raises on anything that does not open."""
+    return unseal(gek, PURPOSE_UPLOAD, MNP.FILE_UPLOAD_ACK, group_id, msg)