summaryrefslogtreecommitdiffstats
path: root/packages/meshbay-node
diff options
context:
space:
mode:
authorChristophe Besson <cbesson@gmail.com>2026-09-07 17:46:33 +0200
committerChristophe Besson <cbesson@gmail.com>2026-09-07 17:46:33 +0200
commit8980a8e42d94ab7c0bc9739283d39f938f8402b0 (patch)
treebbb830b48162ebfdcf443f300c82495f452ad1e0 /packages/meshbay-node
parent77dd077491aea50e71e21e0d17555a2f91cf818b (diff)
downloadmeshbay-8980a8e42d94ab7c0bc9739283d39f938f8402b0.tar.gz
feat(mnp)!: seal the upload under the group key
Downloads have been encrypted under a GEK-derived key since the beginning: `file_chunk` and `stream_data` both go through `chunk_ciphertext`. Uploads never were. `file_upload` carried the filename and the raw bytes in plain msgpack, and `file_upload_ack` carried the name the node stored them under — so the same file was ciphertext leaving a node and plaintext arriving at one. There was no threat model behind that asymmetry. Both halves now travel sealed under a third groupbox purpose, HKDF(GEK, info="meshbay:upload:v1"). The filename, the destination folder and the bytes are all inside the seal; only `upload_id` and `chunk_index` stay in clear, because the node routes and orders on them before it can decrypt. This direction seals *towards* the node — it holds the GEK for its own group — and it opens the payload before it picks a destination or touches the disk. What that forced, and why none of it is optional: - `filename` was the correlation key on both sides. It cannot be: matching an ack to its request by name would hand back exactly what the seal hides. `upload_id` replaces it — client-drawn, opaque to the node, unique within a connection, never an authorization input. The property it guarded (one refusal fails one upload, not every upload in flight) is unchanged. - Refusals can no longer quote what they refused. `No directory named 'X'` becomes `No such directory in this group` plus the `code` that was already there; the client knows what it sent. - No plaintext fallback. A path that still accepts plaintext is not a sealed path, so an unsealed `file_upload` is refused with `upload_not_sealed`. Hardened while here, because what comes out of a seal is authenticated but not validated — a member can seal anything: `filename` and `data` have their types checked before any upload state is created, and `chunk_index`/`total_chunks`, which are outside the seal by necessity, can no longer raise where a refusal was meant. Tests. `test_upload_sealed.py` pins the node half: nothing identifying on the wire, tamper/wrong-key/wrong-group all refused with nothing written, and multi-chunk reassembly unchanged. `test_upload_seal_client.py` drives the shipped `uploadFile` over the shipped `crypto.js` under node and feeds its real frames to the real `_do_file_upload` — the file lands intact, and the ack the node actually produced comes back with the name it chose for a collision, which is the half a source-reading test cannot see. Both upload purposes join the JS/Python groupbox parity vectors. BREAKING CHANGE: MNP 2.0. `file_upload`/`file_upload_ack` change shape on the wire every deployed client speaks, which is MAJOR by the same rule 1.0 was — but the break is confined to uploads. `MNP_MIN_SUPPORTED` stays at "1.0", so a 1.x peer still connects, browses, downloads, streams and chats; only its uploads are refused, with a message saying which side is old. The client checks the node's version before sending a chunk, so neither side meets this as a timeout. This is the version negotiation shipped in 1.0 earning its keep: 1.0 cost a flag day, 2.0 costs a refusal code. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AsoWC3GmhNdwVFomW3QjH3
Diffstat (limited to 'packages/meshbay-node')
-rw-r--r--packages/meshbay-node/src/meshbay_node/transport/webrtc_server.py173
-rw-r--r--packages/meshbay-node/tests/conftest.py31
-rw-r--r--packages/meshbay-node/tests/test_root_writable_policy.py12
-rw-r--r--packages/meshbay-node/tests/test_security_regressions.py89
-rw-r--r--packages/meshbay-node/tests/test_upload_sealed.py285
5 files changed, 464 insertions, 126 deletions
diff --git a/packages/meshbay-node/src/meshbay_node/transport/webrtc_server.py b/packages/meshbay-node/src/meshbay_node/transport/webrtc_server.py
index f8b6c03..5318c25 100644
--- a/packages/meshbay-node/src/meshbay_node/transport/webrtc_server.py
+++ b/packages/meshbay-node/src/meshbay_node/transport/webrtc_server.py
@@ -103,7 +103,13 @@ from meshbay_common.join import (
ROLE_OPERATOR,
join_transcript,
)
-from meshbay_common.protocol import MNP, chunk_ciphertext, file_chunk_wire
+from meshbay_common.protocol import (
+ MNP,
+ chunk_ciphertext,
+ file_chunk_wire,
+ file_upload_ack_wire,
+ file_upload_payload,
+)
from meshbay_node.transport.wire import index_sync_message
from meshbay_node.indexer import GroupIndex
from meshbay_node.indexer.indexer import DirectoryIndexer
@@ -3998,27 +4004,88 @@ class WebRTCPeerSession:
self._send(resp)
def _do_file_upload(self, msg: dict) -> None:
+ """
+ One chunk of an upload, sealed under the group key (MNP 2.0).
+
+ Sealing this direction is not symmetry for its own sake. Downloads have
+ been under a GEK-derived key since the beginning; uploads carried the
+ filename and the raw bytes in plain msgpack, so the same file was
+ ciphertext leaving a node and plaintext arriving at one. The node holds
+ the GEK for its own group, so it opens the payload here — before it
+ decides a destination, before it touches the disk — and refuses a chunk
+ that does not open.
+
+ `upload_id` is the correlation key and stays in clear; `filename`, `dir`
+ and `root` moved inside the seal, which is why every refusal below names
+ the upload rather than the file. A `code` says which refusal it is, and
+ the client already knows what it sent.
+ """
ctx = self._group_ctx()
- filename = msg.get("filename", "")
- chunk_index = msg.get("chunk_index", 0)
- total_chunks = msg.get("total_chunks", 1)
- data = msg.get("data")
+ upload_id = str(msg.get("upload_id") or "")[:64]
+
+ gek = ctx.get("gek")
+ if not gek:
+ self._send({"type": "error", "detail": "Group encryption not initialized",
+ "code": "no_group_key", "upload_id": upload_id})
+ return
+
+ try:
+ payload = file_upload_payload(gek, self._group_id or "", msg)
+ except Exception:
+ # Deliberately one answer for "not sealed at all" and "sealed wrong":
+ # distinguishing them tells a peer which of the two it got right.
+ # An MNP 1.x client lands here, which is the whole of the upgrade
+ # story — everything else it does still works.
+ self._audit("upload_refused", "unsealed")
+ self._send({
+ "type": "error",
+ "detail": "This upload did not open under the group key — the "
+ "client may be running an older version",
+ "code": "upload_not_sealed",
+ "upload_id": upload_id,
+ })
+ return
+
+ filename = payload.get("filename") or ""
+ data = payload.get("data")
+ # From the clear part of the message, so peer-controlled and unchecked
+ # by the AEAD. Everything below compares and adds to them.
+ try:
+ chunk_index = int(msg.get("chunk_index", 0))
+ total_chunks = int(msg.get("total_chunks", 1))
+ except (TypeError, ValueError):
+ self._send({"type": "error", "detail": "Invalid chunk index",
+ "code": "bad_chunk_index", "upload_id": upload_id})
+ return
+
+ def _refuse(detail: str, code: str = "") -> None:
+ """A refusal names the upload, never the file: the name is sealed."""
+ out = {"type": "error", "detail": detail, "upload_id": upload_id}
+ if code:
+ out["code"] = code
+ self._send(out)
- if not filename or data is None:
- self._send({"type": "error", "detail": "Missing filename or data",
- "filename": filename})
+ # Types first, and before any state is created. What comes out of a
+ # sealed payload is authenticated, not validated: it is msgpack a
+ # member wrote, and `SAFE_UPLOAD_NAME.match(123)` raises where a
+ # refusal was meant.
+ if not isinstance(filename, str) or not filename:
+ _refuse("Missing filename or data", "upload_incomplete")
return
+ # Bytes, always: base64 was the shape of the old plaintext `data` field
+ # and there is no sealed message that can carry a string here.
+ if not isinstance(data, (bytes, bytearray)):
+ _refuse("Invalid chunk encoding", "bad_chunk_encoding")
+ return
+ chunk_bytes = bytes(data)
if not SAFE_UPLOAD_NAME.match(filename):
- self._send({"type": "error", "detail": "Invalid filename",
- "filename": filename})
+ _refuse("Invalid filename", "invalid_filename")
return
roots: RootSet | None = ctx.get("roots")
if not roots:
- self._send({"type": "error",
- "detail": "No directories configured for this group",
- "filename": filename})
+ _refuse("No directories configured for this group", "no_roots")
return
# The client names the root it is uploading into — it is browsing one,
@@ -4029,47 +4096,32 @@ class WebRTCPeerSession:
# An unknown name is refused rather than falling back to a writable
# root, because "the file went somewhere else" is discovered weeks
# later — the same reason the old single upload root was never guessed.
- # A client that names nothing is an MNP 1.0 one, and there was exactly
- # one destination in its world: the first writable root.
# `dir` is the folder being browsed, as a virtual path
# (`Media/Films/1999`); `root` is the older, coarser form and is what
- # its first segment means on its own.
- target_rel = str(msg.get("dir") or "").strip().strip("/")
+ # its first segment means on its own. Both are sealed now, so a refusal
+ # below can no longer quote them back.
+ target_rel = str(payload.get("dir") or "").strip().strip("/")
target_root_name = (target_rel.split("/")[0] if target_rel
- else str(msg.get("root") or "").strip())
+ else str(payload.get("root") or "").strip())
upload_root = None
if target_root_name:
upload_root = roots.by_name(target_root_name)
if upload_root is None:
- self._send({"type": "error",
- "detail": f"No directory named "
- f"{target_root_name!r} in this group",
- "code": "no_such_root",
- "filename": filename})
+ _refuse("No such directory in this group", "no_such_root")
return
else:
writable = roots.writable_roots
upload_root = writable[0] if writable else None
if upload_root is None:
- self._send({"type": "error",
- "detail": "No writable directory in this group",
- "code": "no_writable_root",
- "filename": filename})
+ _refuse("No writable directory in this group", "no_writable_root")
return
if not upload_root.writable:
- self._send({"type": "error",
- "detail": f"Directory '{upload_root.name}' is read-only",
- "code": "root_read_only",
- "filename": filename})
+ _refuse("That directory is read-only", "root_read_only")
self._audit("upload_refused", filename[:64])
return
if not upload_root.available:
- self._send({"type": "error",
- "detail": f"Directory '{upload_root.name}' is "
- f"currently unavailable",
- "code": "root_unavailable",
- "filename": filename})
+ _refuse("That directory is currently unavailable", "root_unavailable")
return
# The folder the sender is looking at, and no subdirectory of the node's
@@ -4093,23 +4145,17 @@ class WebRTCPeerSession:
if target_rel:
target_dir = roots.resolve(target_rel)
if target_dir is None or not target_dir.is_dir():
- self._send({"type": "error",
- "detail": "Not a directory in this group",
- "code": "no_such_directory",
- "filename": filename})
+ _refuse("Not a directory in this group", "no_such_directory")
return
rel_dir = target_rel
else:
- # An MNP 1.0 client names nothing; the root itself is where its one
- # destination now is.
+ # A client that names nothing: the first writable root is where its
+ # one destination is.
target_dir = upload_root.path
rel_dir = upload_root.name
if not target_dir.is_dir():
- self._send({"type": "error",
- "detail": f"Directory '{upload_root.name}' is "
- f"currently unavailable",
- "code": "root_unavailable",
- "filename": filename})
+ _refuse("That directory is currently unavailable",
+ "root_unavailable")
return
upload_key = f"{rel_dir}/{filename}"
@@ -4125,33 +4171,24 @@ class WebRTCPeerSession:
# Backstop: _free_name already guarantees this, and it stays because
# it asserts the invariant where the write happens.
if final_path.exists():
- self._send({"type": "error", "detail": "File already exists",
- "filename": filename})
+ _refuse("File already exists", "already_exists")
return
state = {"next_index": 0, "bytes": 0, "stored_name": stored_name}
self._uploads[upload_key] = state
elif state is None:
- self._send({"type": "error", "detail": "Upload not started",
- "filename": filename})
+ _refuse("Upload not started", "not_started")
return
# Reject out-of-order or replayed chunks — otherwise chunk_index>0 appends
# blindly to whatever .part file is already on disk.
if chunk_index != state["next_index"]:
- self._send({"type": "error", "detail": "Unexpected chunk index",
- "filename": filename})
+ _refuse("Unexpected chunk index", "bad_chunk_index")
return
- if isinstance(data, str):
- chunk_bytes = base64.b64decode(data)
- else:
- chunk_bytes = bytes(data)
-
if state["bytes"] + len(chunk_bytes) > MAX_UPLOAD_BYTES:
self._uploads.pop(upload_key, None)
tmp_path.unlink(missing_ok=True)
- self._send({"type": "error", "detail": "Upload exceeds size limit",
- "filename": filename})
+ _refuse("Upload exceeds size limit", "too_large")
return
with open(tmp_path, "wb" if chunk_index == 0 else "ab") as f:
@@ -4159,16 +4196,16 @@ class WebRTCPeerSession:
state["next_index"] = chunk_index + 1
state["bytes"] += len(chunk_bytes)
- self._send({
- "type": MNP.FILE_UPLOAD_ACK,
- "v": MNP_VERSION,
- "chunk_index": chunk_index,
- "filename": filename,
+ self._send(file_upload_ack_wire(
+ gek, self._group_id or "",
+ upload_id=upload_id,
+ chunk_index=chunk_index,
+ filename=filename,
# What it is actually called on disk, which a chat attachment has to
# reference and the uploader deserves to be told.
- "stored_as": stored_name,
- "dir": rel_dir,
- })
+ stored_as=stored_name,
+ dir=rel_dir,
+ ))
if chunk_index + 1 >= total_chunks:
self._uploads.pop(upload_key, None)
diff --git a/packages/meshbay-node/tests/conftest.py b/packages/meshbay-node/tests/conftest.py
index 3dc9cd9..ba86c13 100644
--- a/packages/meshbay-node/tests/conftest.py
+++ b/packages/meshbay-node/tests/conftest.py
@@ -39,3 +39,34 @@ def one_root(path: Path, *, name: str = "", kind: str = "generic",
"""
return RootSet.build([{"path": str(path), "name": name, "kind": kind,
"writable": writable}])
+
+
+def sealed_upload(session, *, filename: str, data: bytes,
+ chunk_index: int = 0, total_chunks: int = 1,
+ dir: str = "", root: str = "",
+ upload_id: str = "up-test") -> dict:
+ """
+ A `file_upload` message as the shipping client builds one (MNP 2.0).
+
+ Built through `file_upload_wire`, not by hand: a test that assembles the
+ wire shape itself is a second encoder, and a second encoder is how
+ `file_chunk` and `index_sync` forked between the transports (finding C6)
+ with nobody noticing. The key and the AAD are taken off the session, so
+ these agree with the handler by construction rather than by copying.
+ """
+ from meshbay_common.protocol import file_upload_wire
+
+ ctx = session._group_ctx()
+ return file_upload_wire(
+ ctx["gek"], session._group_id or "",
+ upload_id=upload_id, chunk_index=chunk_index, total_chunks=total_chunks,
+ filename=filename, data=data, dir=dir, root=root,
+ )
+
+
+def opened_ack(session, msg: dict) -> dict:
+ """The payload of a `file_upload_ack` the node sent, opened as a client would."""
+ from meshbay_common.protocol import file_upload_ack_payload
+
+ ctx = session._group_ctx()
+ return file_upload_ack_payload(ctx["gek"], session._group_id or "", msg)
diff --git a/packages/meshbay-node/tests/test_root_writable_policy.py b/packages/meshbay-node/tests/test_root_writable_policy.py
index 7eb75fd..8345880 100644
--- a/packages/meshbay-node/tests/test_root_writable_policy.py
+++ b/packages/meshbay-node/tests/test_root_writable_policy.py
@@ -21,13 +21,14 @@ anything. A deprecated instruction that still works is not deprecated, and this
one would reopen uploads group-wide.
"""
-import base64
from pathlib import Path
import pytest
from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey
+from conftest import sealed_upload
from meshbay_common.adminop import OP_ROOT_UPDATE, OP_ROOT_EJECT, OP_ROOT_PLUG
+from meshbay_common.crypto import generate_gek
from meshbay_common.protocol import MNP
from meshbay_node.indexer.group_index import GroupIndex
from meshbay_node.roots import RootSet
@@ -47,6 +48,8 @@ def _session(tmp_path: Path, user_id: str, *,
"index": index,
"sk_node": index.sk_node,
"node_user_id": operator,
+ # Uploads are sealed under the group key since MNP 2.0.
+ "gek": generate_gek(),
}
session = WebRTCPeerSession.__new__(WebRTCPeerSession)
session._ctx = ctx
@@ -61,11 +64,8 @@ def _session(tmp_path: Path, user_id: str, *,
def _upload(session, filename="clip.mp4", body=b"bytes"):
- session._do_file_upload({
- "filename": filename, "dir": "shared",
- "chunk_index": 0, "total_chunks": 1,
- "data": base64.b64encode(body).decode(),
- })
+ session._do_file_upload(sealed_upload(
+ session, filename=filename, data=body, dir="shared"))
def _uploads_dir(session) -> Path:
diff --git a/packages/meshbay-node/tests/test_security_regressions.py b/packages/meshbay-node/tests/test_security_regressions.py
index fa821d9..988aa46 100644
--- a/packages/meshbay-node/tests/test_security_regressions.py
+++ b/packages/meshbay-node/tests/test_security_regressions.py
@@ -16,10 +16,11 @@ from pathlib import Path
import pytest
from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey
+from meshbay_common.crypto import generate_gek
from meshbay_common.protocol import IndexEntry
from meshbay_node.indexer.group_index import GroupIndex
from meshbay_node.roots import RootSet
-from conftest import one_root
+from conftest import one_root, opened_ack, sealed_upload
from meshbay_node.transport.webrtc_server import WebRTCPeerSession
@@ -156,7 +157,10 @@ def _session(tmp_path: Path, user_id: str) -> WebRTCPeerSession:
shared_root = tmp_path / "shared"
shared_root.mkdir(exist_ok=True)
index = GroupIndex(group_id="g" * 32, sk_node=Ed25519PrivateKey.generate())
- ctx = {"roots": one_root(shared_root), "index": index, "sk_node": index.sk_node}
+ # A group key, because uploads are sealed under it since MNP 2.0 — the
+ # handler opens the payload before it has a filename to refuse.
+ ctx = {"roots": one_root(shared_root), "index": index,
+ "sk_node": index.sk_node, "gek": generate_gek()}
session = WebRTCPeerSession.__new__(WebRTCPeerSession)
session._ctx = ctx
@@ -188,12 +192,8 @@ def test_upload_cannot_overwrite_another_members_file(tmp_path):
original.write_bytes(b"operator's original content")
attacker = _session(tmp_path, "attacker-user")
- attacker._do_file_upload({
- "filename": "important.mp4",
- "chunk_index": 0,
- "total_chunks": 1,
- "data": base64.b64encode(b"attacker content").decode(),
- })
+ attacker._do_file_upload(sealed_upload(
+ attacker, filename="important.mp4", data=b"attacker content"))
assert original.read_bytes() == b"operator's original content", (
"an upload replaced an existing file (C5a)")
@@ -203,12 +203,15 @@ def test_upload_cannot_overwrite_another_members_file(tmp_path):
def test_upload_second_attempt_cannot_replace_own_completed_file(tmp_path):
"""C5a: even the original uploader does not get to overwrite."""
session = _session(tmp_path, "user-1")
- payload = {"filename": "movie.mp4", "chunk_index": 0, "total_chunks": 1,
- "data": base64.b64encode(b"first").decode()}
- session._do_file_upload(dict(payload))
- session.sent.clear()
+ def _send_it():
+ # Sealed afresh each time: a nonce is drawn per message, so re-sending
+ # the same dict would be a replay rather than a second upload.
+ session._do_file_upload(sealed_upload(
+ session, filename="movie.mp4", data=b"first"))
- session._do_file_upload(dict(payload))
+ _send_it()
+ session.sent.clear()
+ _send_it()
uploads = _uploads_dir(session)
assert (uploads / "movie.mp4").read_bytes() == b"first", (
"the first upload was replaced")
@@ -252,11 +255,8 @@ def test_the_client_names_a_folder_and_never_a_filesystem_path(tmp_path):
for bad in ("../../etc", "/etc", "shared/../..", "shared/../../etc",
"nope", "shared/missing"):
session.sent.clear()
- session._do_file_upload({
- "filename": "note.txt", "dir": bad,
- "chunk_index": 0, "total_chunks": 1,
- "data": base64.b64encode(b"x").decode(),
- })
+ session._do_file_upload(sealed_upload(
+ session, filename="note.txt", data=b"x", dir=bad))
refusal = [m for m in session.sent if m.get("type") == "error"]
assert refusal, f"{bad!r} was accepted"
assert refusal[0].get("code") in ("no_such_root", "no_such_directory"), bad
@@ -274,11 +274,8 @@ def test_an_upload_lands_in_the_folder_it_names(tmp_path):
root = session._ctx["roots"].roots[0]
(root.path / "Albums").mkdir()
- session._do_file_upload({
- "filename": "note.txt", "dir": f"{root.name}/Albums",
- "chunk_index": 0, "total_chunks": 1,
- "data": base64.b64encode(b"x").decode(),
- })
+ session._do_file_upload(sealed_upload(
+ session, filename="note.txt", data=b"x", dir=f"{root.name}/Albums"))
assert (root.path / "Albums" / "note.txt").read_bytes() == b"x"
assert not (root.path / "Albums" / "uploads").exists(), (
@@ -304,11 +301,8 @@ def test_an_upload_goes_to_the_root_it_names(tmp_path):
{"path": str(incoming), "writable": True},
])
- session._do_file_upload({
- "filename": "note.txt", "dir": "Incoming",
- "chunk_index": 0, "total_chunks": 1,
- "data": base64.b64encode(b"x").decode(),
- })
+ session._do_file_upload(sealed_upload(
+ session, filename="note.txt", data=b"x", dir="Incoming"))
assert (incoming / "note.txt").read_bytes() == b"x"
assert not (media / "note.txt").exists(), "it went to the first root instead"
@@ -327,11 +321,8 @@ def test_a_read_only_root_refuses_an_upload(tmp_path):
session._ctx["roots"] = RootSet.build([{"path": str(published)}])
session._is_node_admin = lambda: True
- session._do_file_upload({
- "filename": "note.txt", "dir": "Published",
- "chunk_index": 0, "total_chunks": 1,
- "data": base64.b64encode(b"x").decode(),
- })
+ session._do_file_upload(sealed_upload(
+ session, filename="note.txt", data=b"x", dir="Published"))
refusal = [m for m in session.sent if m.get("type") == "error"]
assert refusal and refusal[0].get("code") == "root_read_only"
@@ -349,11 +340,8 @@ def test_a_fully_read_only_group_refuses_an_unaddressed_upload(tmp_path):
session = _session(tmp_path, "user-1")
session._ctx["roots"] = RootSet.build([{"path": str(published)}])
- session._do_file_upload({
- "filename": "note.txt",
- "chunk_index": 0, "total_chunks": 1,
- "data": base64.b64encode(b"x").decode(),
- })
+ session._do_file_upload(sealed_upload(
+ session, filename="note.txt", data=b"x"))
refusal = [m for m in session.sent if m.get("type") == "error"]
assert refusal and refusal[0].get("code") == "no_writable_root"
@@ -375,11 +363,8 @@ def test_an_ejected_root_refuses_an_upload(tmp_path):
roots.roots[0].available = False
session._ctx["roots"] = roots
- session._do_file_upload({
- "filename": "note.txt", "dir": "USB",
- "chunk_index": 0, "total_chunks": 1,
- "data": base64.b64encode(b"x").decode(),
- })
+ session._do_file_upload(sealed_upload(
+ session, filename="note.txt", data=b"x", dir="USB"))
refusal = [m for m in session.sent if m.get("type") == "error"]
assert refusal and refusal[0].get("code") == "root_unavailable"
@@ -392,22 +377,22 @@ def test_two_members_can_send_the_same_filename(tmp_path):
IMG_1234.jpg. The second gets a free name; neither replaces the other.
"""
first = _session(tmp_path, "user-1")
- first._do_file_upload({
- "filename": "IMG_1234.jpg", "chunk_index": 0, "total_chunks": 1,
- "data": base64.b64encode(b"first").decode(),
- })
+ first._do_file_upload(sealed_upload(
+ first, filename="IMG_1234.jpg", data=b"first"))
second = _session(tmp_path, "user-2")
- second._do_file_upload({
- "filename": "IMG_1234.jpg", "chunk_index": 0, "total_chunks": 1,
- "data": base64.b64encode(b"second").decode(),
- })
+ # Same group, so the same key: `_session` builds one per call, and two
+ # members of one group do not have two.
+ second._ctx["gek"] = first._ctx["gek"]
+ second._do_file_upload(sealed_upload(
+ second, filename="IMG_1234.jpg", data=b"second"))
uploads = _uploads_dir(first)
assert (uploads / "IMG_1234.jpg").read_bytes() == b"first"
assert (uploads / "IMG_1234 (2).jpg").read_bytes() == b"second"
ack = [m for m in second.sent if m.get("type") == "file_upload_ack"][-1]
- assert ack["stored_as"] == "IMG_1234 (2).jpg", (
+ assert "stored_as" not in ack, "the name the node chose must be sealed"
+ assert opened_ack(second, ack)["stored_as"] == "IMG_1234 (2).jpg", (
"the sender must be told the name that was used, or a chat attachment "
"points at someone else's file")
diff --git a/packages/meshbay-node/tests/test_upload_sealed.py b/packages/meshbay-node/tests/test_upload_sealed.py
new file mode 100644
index 0000000..7c1be96
--- /dev/null
+++ b/packages/meshbay-node/tests/test_upload_sealed.py
@@ -0,0 +1,285 @@
+"""
+The write path, sealed under the group key (MNP 2.0).
+
+Downloads have been encrypted under a GEK-derived key since the beginning:
+`file_chunk` and `stream_data` both go through `chunk_ciphertext`. Uploads did
+not. `file_upload` carried the filename and the raw bytes in plain msgpack and
+`file_upload_ack` carried the name the node stored them under, so the same file
+was ciphertext leaving a node and plaintext arriving at one — an asymmetry with
+no threat model behind it.
+
+What sealing buys is what `groupbox.py` says and no more: nothing against a
+network observer (DTLS covers that), nothing against the hub (never on this
+channel), nothing against a member (they hold the GEK). It buys defence in
+depth against our own next handshake bug, of a class already shipped twice —
+C1, the unauthenticated node HTTP API, and C6, the transport that took a bare
+JWT. Both were "a peer that had not finished the handshake was served data".
+Sealed, the equivalent bug on this path leaks ciphertext instead of the
+operator's filenames.
+"""
+
+from pathlib import Path
+
+import pytest
+from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey
+from meshbay_common.crypto import generate_gek
+from meshbay_common.protocol import MNP, file_upload_wire
+from meshbay_node.indexer.group_index import GroupIndex
+from meshbay_node.transport.webrtc_server import WebRTCPeerSession
+
+from conftest import one_root, opened_ack, sealed_upload
+
+GROUP = "g" * 32
+
+
+def _session(tmp_path: Path, *, gek: bytes | None = None) -> WebRTCPeerSession:
+ shared_root = tmp_path / "shared"
+ shared_root.mkdir(exist_ok=True)
+ index = GroupIndex(group_id=GROUP, sk_node=Ed25519PrivateKey.generate())
+ session = WebRTCPeerSession.__new__(WebRTCPeerSession)
+ session._ctx = {"roots": one_root(shared_root), "index": index,
+ "sk_node": index.sk_node, "gek": gek or generate_gek()}
+ session._group_id = GROUP
+ session._user_id = "user-1"
+ session._pk_user = ""
+ session._uploads = {}
+ session.sent = []
+ session._send = session.sent.append
+ session._audit = lambda *a, **k: None
+ return session
+
+
+def _root(session):
+ return session._ctx["roots"].roots[0]
+
+
+def _errors(session):
+ return [m for m in session.sent if m.get("type") == "error"]
+
+
+def _wrote_anything(tmp_path) -> bool:
+ return any(p.is_file() for p in tmp_path.rglob("*"))
+
+
+# ── The message itself ───────────────────────────────────────────────────────
+
+def test_the_wire_message_carries_no_filename_and_no_plaintext(tmp_path):
+ """
+ The point of the exercise. `upload_id` and `chunk_index` are outside the
+ seal because the node routes and orders on them before it can decrypt;
+ everything that names or is the operator's content is inside it.
+ """
+ session = _session(tmp_path)
+ msg = sealed_upload(session, filename="holiday.jpg", data=b"JPEGDATA",
+ dir=f"{_root(session).name}")
+
+ assert set(msg) == {"type", "v", "upload_id", "chunk_index",
+ "total_chunks", "nonce", "ct"}
+ blob = repr(msg).encode() + msg["ct"]
+ assert b"holiday.jpg" not in blob, "the filename is on the wire in clear"
+ assert b"JPEGDATA" not in blob, "the file content is on the wire in clear"
+
+
+def test_the_ack_carries_no_stored_name(tmp_path):
+ """
+ `stored_as` is the name the node settled on — it finds a free one rather
+ than replacing anything — and naming it in clear would hand back exactly
+ what the request took the trouble to hide.
+ """
+ session = _session(tmp_path)
+ session._do_file_upload(sealed_upload(
+ session, filename="holiday.jpg", data=b"x", dir=_root(session).name))
+
+ ack = [m for m in session.sent if m.get("type") == MNP.FILE_UPLOAD_ACK][-1]
+ assert set(ack) == {"type", "v", "upload_id", "chunk_index", "nonce", "ct"}
+ assert b"holiday.jpg" not in repr(ack).encode() + ack["ct"]
+ assert opened_ack(session, ack) == {
+ "filename": "holiday.jpg", "stored_as": "holiday.jpg",
+ "dir": _root(session).name}
+
+
+def test_the_ack_names_the_upload_so_one_refusal_fails_one_upload(tmp_path):
+ """
+ `filename` used to be the correlation key on both sides. It cannot be one
+ any more, and `upload_id` replaces it — a client-chosen label, opaque to
+ the node, never an authorization input. Without it a client running several
+ uploads could only match replies by arrival order, which is how a refusal
+ for one file used to fail every upload in flight.
+ """
+ session = _session(tmp_path)
+ session._do_file_upload(sealed_upload(
+ session, filename="a.txt", data=b"x", dir=_root(session).name,
+ upload_id="upload-A"))
+ session._do_file_upload(sealed_upload(
+ session, filename="../evil", data=b"x", dir=_root(session).name,
+ upload_id="upload-B"))
+
+ ack = [m for m in session.sent if m.get("type") == MNP.FILE_UPLOAD_ACK][-1]
+ assert ack["upload_id"] == "upload-A"
+ assert _errors(session)[0]["upload_id"] == "upload-B"
+
+
+# ── What is refused ──────────────────────────────────────────────────────────
+
+def test_a_plaintext_upload_is_refused(tmp_path):
+ """
+ The MNP 1.x shape, which is what an un-updated client sends. Refused with a
+ code and a message saying which side is old — never accepted "just this
+ once", because a path that still takes plaintext is not a sealed path.
+ """
+ session = _session(tmp_path)
+ session._do_file_upload({
+ "filename": "note.txt", "dir": _root(session).name,
+ "chunk_index": 0, "total_chunks": 1, "data": b"x",
+ })
+
+ assert _errors(session)[0]["code"] == "upload_not_sealed"
+ assert not _wrote_anything(tmp_path)
+
+
+def test_a_tampered_chunk_is_refused(tmp_path):
+ """
+ AES-GCM's tag, asserted where it matters: a flipped bit in the ciphertext
+ must stop the upload, not produce a corrupt file with a plausible name.
+ """
+ session = _session(tmp_path)
+ msg = sealed_upload(session, filename="note.txt", data=b"x" * 64,
+ dir=_root(session).name)
+ msg["ct"] = bytes([msg["ct"][0] ^ 0x01]) + msg["ct"][1:]
+ session._do_file_upload(msg)
+
+ assert _errors(session)[0]["code"] == "upload_not_sealed"
+ assert not _wrote_anything(tmp_path)
+
+
+def test_an_upload_sealed_for_another_group_is_refused(tmp_path):
+ """
+ The group is the AAD, so a node hosting two groups cannot have a chunk
+ moved between them — and a member of one cannot write into the other by
+ reaching a session that is on it (finding H1's shape, on the write path).
+ """
+ session = _session(tmp_path)
+ msg = file_upload_wire(
+ session._ctx["gek"], "some-other-group",
+ upload_id="u1", chunk_index=0, total_chunks=1,
+ filename="note.txt", data=b"x", dir=_root(session).name)
+ session._do_file_upload(msg)
+
+ assert _errors(session)[0]["code"] == "upload_not_sealed"
+ assert not _wrote_anything(tmp_path)
+
+
+def test_an_upload_under_another_key_is_refused(tmp_path):
+ """A peer past the handshake with the wrong GEK still writes nothing."""
+ session = _session(tmp_path)
+ msg = file_upload_wire(
+ generate_gek(), GROUP,
+ upload_id="u1", chunk_index=0, total_chunks=1,
+ filename="note.txt", data=b"x", dir=_root(session).name)
+ session._do_file_upload(msg)
+
+ assert _errors(session)[0]["code"] == "upload_not_sealed"
+ assert not _wrote_anything(tmp_path)
+
+
+def test_an_ack_replayed_as_a_request_does_not_open(tmp_path):
+ """
+ The message type is in the AAD, so the two halves of an upload cannot be
+ confused for each other. Cheap, and it closes a class that is tedious to
+ reason about after the fact.
+ """
+ from cryptography.exceptions import InvalidTag
+ from meshbay_common.protocol import file_upload_ack_wire, file_upload_payload
+
+ session = _session(tmp_path)
+ ack = file_upload_ack_wire(
+ session._ctx["gek"], GROUP, upload_id="u1", chunk_index=0,
+ filename="note.txt", stored_as="note.txt", dir="shared")
+ with pytest.raises(InvalidTag):
+ file_upload_payload(session._ctx["gek"], GROUP, ack)
+
+
+def test_a_group_with_no_key_refuses_rather_than_falling_back(tmp_path):
+ """
+ A node whose group has no GEK yet cannot open anything. It must say so, not
+ read the message as though it were the old plaintext shape.
+ """
+ session = _session(tmp_path)
+ msg = sealed_upload(session, filename="note.txt", data=b"x",
+ dir=_root(session).name)
+ session._ctx["gek"] = b""
+ session._do_file_upload(msg)
+
+ assert _errors(session)[0]["code"] == "no_group_key"
+ assert not _wrote_anything(tmp_path)
+
+
+# ── What must still work ─────────────────────────────────────────────────────
+
+def test_a_multi_chunk_upload_reassembles(tmp_path):
+ """
+ Every chunk is sealed under its own nonce, and the node appends in order.
+ Nothing about the seal may change what lands on disk.
+ """
+ session = _session(tmp_path)
+ body = bytes(range(256)) * 40
+ parts = [body[i:i + 1024] for i in range(0, len(body), 1024)]
+ for i, part in enumerate(parts):
+ session._do_file_upload(sealed_upload(
+ session, filename="blob.bin", data=part,
+ chunk_index=i, total_chunks=len(parts), dir=_root(session).name))
+
+ assert (_root(session).path / "blob.bin").read_bytes() == body
+ assert not list(_root(session).path.glob("*.part")), "a temp file was left"
+ acks = [m for m in session.sent if m.get("type") == MNP.FILE_UPLOAD_ACK]
+ assert [m["chunk_index"] for m in acks] == list(range(len(parts)))
+
+
+def test_two_identical_chunks_do_not_reuse_a_nonce(tmp_path):
+ """
+ A file of repeated bytes is ordinary, so the nonce must come from the RNG
+ and never from the payload. Cheap to assert and expensive to discover.
+ """
+ session = _session(tmp_path)
+ a = sealed_upload(session, filename="f", data=b"same", chunk_index=0)
+ b = sealed_upload(session, filename="f", data=b"same", chunk_index=0)
+ assert a["nonce"] != b["nonce"]
+ assert a["ct"] != b["ct"]
+
+
+def test_a_sealed_payload_is_authenticated_not_validated(tmp_path):
+ """
+ Opening a payload proves a member wrote it, not that they wrote something
+ sensible. A member can seal anything, so the fields still need their types
+ checked — `SAFE_UPLOAD_NAME.match(123)` raises where a refusal was meant,
+ and the dispatcher's catch-all would turn that into "Request failed".
+ """
+ from meshbay_common.groupbox import PURPOSE_UPLOAD, seal
+
+ session = _session(tmp_path)
+ for payload in ({"filename": 123, "data": b"x"},
+ {"filename": "note.txt", "data": "not bytes"},
+ {"filename": "note.txt"}):
+ session.sent.clear()
+ session._do_file_upload({
+ "type": MNP.FILE_UPLOAD, "v": "2.0", "upload_id": "u1",
+ "chunk_index": 0, "total_chunks": 1,
+ **seal(session._ctx["gek"], PURPOSE_UPLOAD, MNP.FILE_UPLOAD,
+ GROUP, payload),
+ })
+ errs = _errors(session)
+ assert errs, f"{payload!r} was accepted"
+ assert errs[0]["code"] in ("upload_incomplete", "bad_chunk_encoding")
+ assert not _wrote_anything(tmp_path)
+
+
+def test_a_peer_controlled_chunk_index_cannot_crash_the_handler(tmp_path):
+ """`chunk_index` is outside the seal by necessity, so it is unchecked input."""
+ session = _session(tmp_path)
+ msg = sealed_upload(session, filename="note.txt", data=b"x",
+ dir=_root(session).name)
+ msg["chunk_index"] = "zero"
+ session._do_file_upload(msg)
+
+ assert _errors(session)[0]["code"] == "bad_chunk_index"
+ assert not _wrote_anything(tmp_path)