summaryrefslogtreecommitdiffstats
path: root/packages
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
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')
-rw-r--r--packages/meshbay-common/src/meshbay_common/__init__.py35
-rw-r--r--packages/meshbay-common/src/meshbay_common/groupbox.py17
-rw-r--r--packages/meshbay-common/src/meshbay_common/protocol.py109
-rw-r--r--packages/meshbay-common/tests/test_js_python_parity.py13
-rw-r--r--packages/meshbay-hub/src/meshbay_hub/static/crypto.js10
-rw-r--r--packages/meshbay-hub/src/meshbay_hub/static/transport.js111
-rw-r--r--packages/meshbay-hub/tests/harness/upload_seal_probe.mjs102
-rw-r--r--packages/meshbay-hub/tests/test_transport_contracts.py50
-rw-r--r--packages/meshbay-hub/tests/test_upload_seal_client.py169
-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
14 files changed, 1039 insertions, 167 deletions
diff --git a/packages/meshbay-common/src/meshbay_common/__init__.py b/packages/meshbay-common/src/meshbay_common/__init__.py
index b3e24e3..ac69e18 100644
--- a/packages/meshbay-common/src/meshbay_common/__init__.py
+++ b/packages/meshbay-common/src/meshbay_common/__init__.py
@@ -93,5 +93,38 @@ __version__ = "0.11.0"
# The index at rest, `index_progress` (counters only, never a path — see
# `groupbox.py` and daemon.py `_push_index_progress`), chat, and file content
# on the operator's disk are all deliberately unchanged.
-MNP_VERSION = "1.1"
+# 1.1: `index_delta` carries `roots` (additive — a 1.0 client ignores it), and
+# the per-root/per-app operations: `root_update`/`root_eject`/`root_plug`,
+# `app_directories`, `chat_directory`, `chat_link_preview`.
+# 2.0: the **write** path is sealed, and the last unencrypted content message
+# is gone.
+#
+# - `file_upload` and `file_upload_ack` travel sealed under a GEK-derived
+# subkey (`groupbox.PURPOSE_UPLOAD`). The filename, the destination folder
+# and the bytes all ride inside the seal; `upload_id` — a fresh
+# client-chosen correlation id — and `chunk_index` stay in clear because
+# the node routes and orders on them. `filename` used to be the
+# correlation key and cannot be any more, which is what forced `upload_id`.
+# - `stream_seg` is **removed**. It answered with an MPEG-TS segment as
+# base64 with no encryption at all, on both transports, to any
+# authenticated member — the one content-plane message that never went
+# through a GEK-derived key. `stream_data` has done the job properly since
+# Phase 12, and `fetchStreamSegment`, its only browser caller, was defined
+# and never once invoked.
+#
+# **Breaking, on the wire every deployed client speaks**, and MAJOR by the same
+# rule 1.0 was: a 1.x client's upload reaches a 2.0 node with no `filename` and
+# no `data` outside the seal. That is why the break is confined rather than
+# total — `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
+# `upload_not_sealed` and a message saying which side is old. A client refuses
+# symmetrically before sending (`supportsSealedUpload` in transport.js), so
+# neither side discovers this as a timeout.
+#
+# Still deliberately in clear, and none of it is content: the handshake itself,
+# `index_progress` (counters only — see daemon.py `_push_index_progress`), the
+# admin and configuration acks, and the media-metadata replies. Chat is next,
+# under sender keys. The index at rest and file content on the operator's disk
+# are unchanged.
+MNP_VERSION = "2.0"
MHP_VERSION = "0.1"
diff --git a/packages/meshbay-common/src/meshbay_common/groupbox.py b/packages/meshbay-common/src/meshbay_common/groupbox.py
index f1091c3..eb2f630 100644
--- a/packages/meshbay-common/src/meshbay_common/groupbox.py
+++ b/packages/meshbay-common/src/meshbay_common/groupbox.py
@@ -24,6 +24,14 @@ and group configuration. It buys nothing against a network observer (DTLS/TLS
already covers that), nothing against the hub (it never sees channel traffic), and
nothing against a member — who holds the GEK. That is the whole claim.
+**Both, for the upload (MNP 2.0).** `file_upload` carried the filename and the raw
+bytes in clear, and `file_upload_ack` carried the name it was stored under. The
+download path had been sealed end to end since the beginning — so the same file was
+ciphertext coming out of a node and plaintext going in, which is not a threat model,
+it is an oversight. The node holds the GEK for its own group, so unlike the index
+this direction seals *towards* the node: it opens the payload before it writes
+anything to disk, and refuses a chunk that does not open rather than guessing.
+
Purpose separation is deliberate. `GroupIndex.serialize()` reuses
`chunk_key_aes(gek, file_hash, chunk_index)` with a pseudo-file ("the index as chunk
0 of a virtual index file"), which borrows a file's key space for something that is
@@ -41,6 +49,7 @@ from cryptography.hazmat.primitives.kdf.hkdf import HKDF
PURPOSE_INDEX = "index"
PURPOSE_ACK = "ack"
+PURPOSE_UPLOAD = "upload"
# `salt=None` here and `salt: new Uint8Array(0)` in crypto.js agree — RFC 5869
# extracts with a zero key either way. Already proven in production by
@@ -48,8 +57,16 @@ PURPOSE_ACK = "ack"
_INFO = {
PURPOSE_INDEX: b"meshbay:index:v1",
PURPOSE_ACK: b"meshbay:ack:v1",
+ PURPOSE_UPLOAD: b"meshbay:upload:v1",
}
+# One subkey per purpose, and `seal` draws a fresh 96-bit nonce per message, so
+# the bound that matters is birthday collision under `PURPOSE_UPLOAD` — the only
+# purpose with real volume, one message per 48 KiB chunk. 2**32 chunks is 200 TB
+# uploaded under a single GEK before the collision probability reaches 2**-32,
+# and `gek_rotate` exists. Deriving the nonce from the payload instead would be
+# worse, not better: two chunks of identical bytes are ordinary in a file.
+
NONCE_LEN = 12 # 96-bit, the WebCrypto AES-GCM standard
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)
diff --git a/packages/meshbay-common/tests/test_js_python_parity.py b/packages/meshbay-common/tests/test_js_python_parity.py
index 6f7437f..1abae75 100644
--- a/packages/meshbay-common/tests/test_js_python_parity.py
+++ b/packages/meshbay-common/tests/test_js_python_parity.py
@@ -258,6 +258,11 @@ GROUPBOX_VECTORS = [
("index", "index_sync", "groupe-café-日本"),
# A '|' inside the group id, which is the AAD's own separator.
("index", "index_sync", "a|b"),
+ # MNP 2.0 — the upload, and the only purpose the *browser* seals in
+ # production. A disagreement here means no file can be uploaded from any
+ # browser to any node, and the node reports only "it did not open".
+ ("upload", "file_upload", "g" * 32),
+ ("upload", "file_upload_ack", "g" * 32),
]
GROUPBOX_GEK = bytes.fromhex("5a" * 32)
@@ -349,9 +354,11 @@ def test_browser_opens_what_python_sealed(idx, vector, groupbox_js):
@pytest.mark.parametrize("idx,vector", list(enumerate(GROUPBOX_VECTORS)))
def test_python_opens_what_the_browser_sealed(idx, vector, groupbox_js):
"""
- The other direction. Nothing in the SPA seals today — `sealGroup` exists for
- the chat plan, which needs the same primitive — but a codec that only ever
- runs one way is a codec whose encoder is untested.
+ The other direction, and since MNP 2.0 it is a shipping path rather than a
+ precaution: `uploadFile` seals every chunk under `upload`, and the node
+ opens it with `unseal`. The index vectors above still only ever run one way
+ in production, and are kept because a codec whose encoder is untested is a
+ codec with half a test.
"""
from meshbay_common.groupbox import unseal
diff --git a/packages/meshbay-hub/src/meshbay_hub/static/crypto.js b/packages/meshbay-hub/src/meshbay_hub/static/crypto.js
index d2e19b7..4d26c6d 100644
--- a/packages/meshbay-hub/src/meshbay_hub/static/crypto.js
+++ b/packages/meshbay-hub/src/meshbay_hub/static/crypto.js
@@ -111,8 +111,9 @@ async function decryptChunkBin(gek, fileHashHex, chunkIndex, nonce, ct) {
// ── Sealing a payload under the group key ────────────────────────────────────
//
-// Mirrors meshbay_common/groupbox.py. `index_sync`, `index_delta` and the
-// `handshake_ack` config payload travel sealed under a GEK-derived subkey; the
+// Mirrors meshbay_common/groupbox.py. `index_sync`, `index_delta`, the
+// `handshake_ack` config payload and both halves of an upload travel sealed
+// under a GEK-derived subkey; the
// routing fields (type, v, group_id) and the ack's own authentication (node_pk,
// proof, sig) stay in clear, because a receiver must route, version-check and
// *authenticate* before it would trust a decryption.
@@ -126,6 +127,11 @@ async function decryptChunkBin(gek, fileHashHex, chunkIndex, nonce, ct) {
const GROUPBOX_INFO = {
index: new TextEncoder().encode('meshbay:index:v1'),
ack: new TextEncoder().encode('meshbay:ack:v1'),
+ // MNP 2.0: `file_upload` and `file_upload_ack`. This is the one purpose that
+ // seals *towards* the node — it holds the GEK for its own group — and the one
+ // with real message volume, one per 48 KB chunk. groupbox.py carries the
+ // nonce-collision arithmetic that makes a random 96-bit nonce fine at that rate.
+ upload: new TextEncoder().encode('meshbay:upload:v1'),
};
/**
diff --git a/packages/meshbay-hub/src/meshbay_hub/static/transport.js b/packages/meshbay-hub/src/meshbay_hub/static/transport.js
index 2668e02..681a9ba 100644
--- a/packages/meshbay-hub/src/meshbay_hub/static/transport.js
+++ b/packages/meshbay-hub/src/meshbay_hub/static/transport.js
@@ -248,7 +248,7 @@ window.addEventListener('hashchange', () => {
// The `v: '0.1'` on every other message in this file is the historical value
// and is read by nothing; it is left alone deliberately. The range is
// negotiated once, at the start, not restated per message.
-const MNP_V = '1.1';
+const MNP_V = '2.0';
const MNP_V_MIN = '1.0';
// Codes a NODE sends us, in its own vocabulary (meshbay_common/handshake.py's
@@ -301,10 +301,17 @@ class MeshBayTransport {
this._onStreamEnd = null;
this._onStreamError = null;
this._onIndexSync = null;
- // filename → the uploader waiting on it. Keyed rather than FIFO because
- // several uploads may be in flight at once and their acks interleave; the
- // node names the file in every one.
+ // upload_id → the uploader waiting on it. Keyed rather than FIFO because
+ // several uploads may be in flight at once and their acks interleave.
+ //
+ // It was keyed by filename until MNP 2.0, which is no longer possible: the
+ // name is sealed under the group key, and echoing it in clear so the two
+ // sides could match on it would give back precisely what the seal is for.
+ // `upload_id` is drawn per upload here and is opaque to the node.
this._uploaders = new Map();
+ // Names, not ids: the "already being uploaded" guard is about the file the
+ // caller passed, and two `uploadFile` calls for one file draw two ids.
+ this._inFlightUploads = new Set();
// Set once close() runs — stops the automatic reconnect from firing on a
// connection the caller tore down on purpose (leaving the group, page
// unload), which would otherwise race back in right as everything else
@@ -381,6 +388,19 @@ class MeshBayTransport {
if (!m) return false;
return (Number(m[1]) > 1) || (Number(m[1]) === 1 && Number(m[2]) >= 1);
}
+ /**
+ * Whether the node opens a sealed upload (MNP 2.0).
+ *
+ * A 1.x node reads `filename` and `data` off the message itself, finds
+ * neither — they are inside the seal — and answers "Missing filename or
+ * data", an error about the wrong thing that names no upload_id and so fails
+ * every upload in flight. Asked before sending rather than discovered after,
+ * for the same reason `supportsAppOps` is.
+ */
+ get supportsSealedUpload() {
+ const m = /^(\d+)\.(\d+)$/.exec(this._nodeVersion || '');
+ return !!m && Number(m[1]) >= 2;
+ }
set onAppsEnabled(fn) { this._onAppsEnabled = fn; }
set onAppDirectories(fn) { this._onAppDirectories = fn; }
set onChatDirectory(fn) { this._onChatDirectory = fn; }
@@ -1812,10 +1832,21 @@ class MeshBayTransport {
*/
async uploadFile(file, { chunkSize, onProgress, signal, root, dir } = {}) {
// The same file twice at once would confuse the node, which keys its own
- // upload state by name — and would race for the same destination.
- if (this._uploaders.has(file.name)) {
+ // upload state by name — and would race for the same destination. The guard
+ // is by name for that reason, even though the map below is keyed by id.
+ if (this._inFlightUploads.has(file.name)) {
throw new Error(`${file.name} is already being uploaded`);
}
+ if (!this._gekRaw) throw new Error('This group has no key on this device');
+ if (!this.supportsSealedUpload) {
+ throw new Error(
+ 'This node is running an older MeshBay and cannot accept an upload '
+ + 'from this page. Its operator has to update it.');
+ }
+ const C = window.MeshBayCrypto;
+ const groupId = (this._connectArgs && this._connectArgs.groupId) || '';
+ this._inFlightUploads.add(file.name);
+ const uploadId = _hex(crypto.getRandomValues(new Uint8Array(16)));
const size = chunkSize || UPLOAD_CHUNK_SIZE;
const total = Math.max(1, Math.ceil(file.size / size));
let acked = 0;
@@ -1823,16 +1854,32 @@ class MeshBayTransport {
let failure = null;
const acks = [];
- this._uploaders.set(file.name, (msg) => {
- if (msg.type === 'error') {
- failure = new Error(msg.detail || 'Upload refused');
- } else if (msg.stored_as) {
- stored = msg;
- }
+ const wake = () => {
acked += 1;
if (onProgress) onProgress(Math.min(file.size, acked * size), file.size);
const waiter = acks.shift();
if (waiter) waiter();
+ };
+ this._uploaders.set(uploadId, (msg) => {
+ if (msg.type === 'error') {
+ failure = new Error(msg.detail || 'Upload refused');
+ wake();
+ return;
+ }
+ // The ack is sealed too — `stored_as` and the folder it landed in name
+ // the operator's content. Opening it is what makes the result usable, so
+ // a failure here fails the upload rather than being swallowed: a chat
+ // attachment that cannot learn its stored name would point at nothing.
+ C.openGroup(this._gekRaw, 'upload', 'file_upload_ack', groupId, msg)
+ .then((plain) => {
+ const payload = msgpack_decode(plain);
+ if (payload.stored_as) stored = payload;
+ })
+ .catch((e) => {
+ failure = new Error(
+ `The node's upload reply did not open under the group key (${e.message})`);
+ })
+ .finally(wake);
});
const nextAck = () => new Promise(r => acks.push(r));
@@ -1854,15 +1901,20 @@ class MeshBayTransport {
const buf = new Uint8Array(
await file.slice(i * size, (i + 1) * size).arrayBuffer());
+ // The name, the destination and the bytes go inside the seal together.
+ // Mirrors `file_upload_wire` in meshbay_common/protocol.py; only the
+ // fields the node routes on stay outside it.
+ const sealed = await C.sealGroup(
+ this._gekRaw, 'upload', 'file_upload', groupId,
+ msgpack_encode({ filename: file.name, data: buf,
+ dir: dir || '', root: root || '' }));
this._send({
type: 'file_upload',
v: '0.1',
- filename: file.name,
+ upload_id: uploadId,
chunk_index: i,
total_chunks: total,
- data: buf,
- ...(root ? { root } : {}),
- ...(dir ? { dir } : {}),
+ ...sealed,
});
}
while (acked < total) {
@@ -1870,7 +1922,8 @@ class MeshBayTransport {
if (failure) throw failure;
}
} finally {
- this._uploaders.delete(file.name);
+ this._uploaders.delete(uploadId);
+ this._inFlightUploads.delete(file.name);
}
return stored || {};
}
@@ -2427,21 +2480,21 @@ class MeshBayTransport {
// While an upload is in flight the acks are its own, and there are many of
// them: they must not be handed to whatever request happens to be oldest in
// the pending map.
- if (msg.type === 'file_upload_ack' && this._uploaders.has(msg.filename)) {
- this._uploaders.get(msg.filename)(msg);
+ if (msg.type === 'file_upload_ack' && this._uploaders.has(msg.upload_id)) {
+ this._uploaders.get(msg.upload_id)(msg);
return;
}
- // An upload refusal names the file it is about, so only that upload fails.
- // It did not use to, and there was no way to tell whose error it was, so
- // every upload in flight was failed together — send a second file whose
- // name the node dislikes and both died. The broadcast is kept for a node
- // that does not name it, where guessing wrong is worse than stopping.
+ // An upload refusal names the upload it is about, so only that upload
+ // fails. It did not use to, and there was no way to tell whose error it
+ // was, so every upload in flight was failed together — send a second file
+ // whose name the node dislikes and both died. The broadcast is kept for a
+ // refusal that names none, where guessing wrong is worse than stopping.
if (msg.type === 'error' && this._uploaders.size) {
- if (msg.filename && this._uploaders.has(msg.filename)) {
- this._uploaders.get(msg.filename)(msg);
+ if (msg.upload_id && this._uploaders.has(msg.upload_id)) {
+ this._uploaders.get(msg.upload_id)(msg);
return;
}
- if (!msg.filename) {
+ if (!msg.upload_id) {
for (const handler of [...this._uploaders.values()]) handler(msg);
return;
}
@@ -3017,6 +3070,10 @@ function _decodeMap(buf, view, offset, count) {
return [obj, offset];
}
+function _hex(bytes) {
+ return [...bytes].map(b => b.toString(16).padStart(2, '0')).join('');
+}
+
function _extractDtlsFingerprint(sdp) {
const match = sdp.match(/a=fingerprint:sha-256 ([0-9A-Fa-f:]+)/);
if (!match) return new Uint8Array(0);
diff --git a/packages/meshbay-hub/tests/harness/upload_seal_probe.mjs b/packages/meshbay-hub/tests/harness/upload_seal_probe.mjs
new file mode 100644
index 0000000..0b77e42
--- /dev/null
+++ b/packages/meshbay-hub/tests/harness/upload_seal_probe.mjs
@@ -0,0 +1,102 @@
+/**
+ * Does the browser's real `uploadFile` produce frames a real node can open —
+ * and does it read back what that node actually answered?
+ *
+ * Drives **the real `MeshBayTransport` over the real `crypto.js`**. Only the DOM
+ * and the DataChannel are stand-ins; the msgpack encode, the HKDF, the AES-GCM
+ * and the whole upload loop are the shipped code.
+ *
+ * It exists because a source-reading test cannot show either half of MNP 2.0's
+ * upload. `test_transport_contracts` can see that `sealGroup` is called; only
+ * this can show that what comes out opens under `meshbay_common.groupbox` — and
+ * that the caller of `uploadFile` is told the name the *node* chose, which now
+ * arrives sealed and would otherwise be `undefined` with nothing to notice it.
+ *
+ * node upload_seal_probe.mjs <static-dir> <input.json>
+ *
+ * Two modes, because the node half runs in Python between them:
+ * "send" — run the upload, print every frame it emits, answer nothing
+ * "receive" — run it again, answering with acks Python built. Their
+ * `upload_id` is retargeted to this run's; it is outside the
+ * seal, so the ciphertext stays exactly the one Python produced.
+ */
+import fs from 'fs';
+
+const STATIC = process.argv[2];
+const input = JSON.parse(fs.readFileSync(process.argv[3], 'utf8'));
+
+for (const level of ['log', 'warn', 'error', 'info', 'debug']) {
+ console[level] = (...args) => process.stderr.write(args.join(' ') + '\n');
+}
+
+globalThis.window = globalThis;
+globalThis.addEventListener = () => {};
+globalThis.removeEventListener = () => {};
+globalThis.location = { hash: '' };
+globalThis.document = {
+ addEventListener() {}, removeEventListener() {}, visibilityState: 'visible',
+};
+
+new Function(fs.readFileSync(`${STATIC}/crypto.js`, 'utf8'))();
+const transportSrc = fs.readFileSync(`${STATIC}/transport.js`, 'utf8');
+new Function(transportSrc)();
+// The msgpack codec is private to transport.js — pulled out the same way the
+// groupbox parity harness pulls out sealGroup, so this probe encodes and
+// decodes with the codec that is actually shipped rather than a second one.
+const { msgpack_encode, msgpack_decode } =
+ new Function(transportSrc + '\nreturn { msgpack_encode, msgpack_decode };')();
+
+const hex = (s) => Uint8Array.from(s.match(/../g).map((b) => parseInt(b, 16)));
+const toHex = (u8) =>
+ Array.from(u8).map((b) => b.toString(16).padStart(2, '0')).join('');
+
+// Just enough of a File: a name, a size, and slices that yield ArrayBuffers.
+const bytes = hex(input.file.data);
+const file = {
+ name: input.file.name,
+ size: bytes.length,
+ slice(a, b) {
+ const part = bytes.slice(a, b);
+ return { arrayBuffer: async () => part.buffer.slice(
+ part.byteOffset, part.byteOffset + part.byteLength) };
+ },
+};
+
+const tp = new window.MeshBayTransport('', 'token');
+tp._connected = true;
+tp._channel = { readyState: 'open', bufferedAmount: 0, send() {}, close() {} };
+tp._pc = { close() {} };
+tp._gekRaw = hex(input.gek);
+tp._connectArgs = { groupId: input.group_id };
+tp._nodeVersion = input.node_version;
+
+const frames = [];
+let uploadId = null;
+tp._send = (msg) => {
+ frames.push(toHex(msgpack_encode(msg)));
+ if (msg.upload_id) uploadId = msg.upload_id;
+ if (input.mode !== 'receive') return;
+ // Answer as the node did, on the next turn of the loop so the send path
+ // finishes first — which is also how a real ack arrives.
+ const ack = msgpack_decode(hex(input.acks[msg.chunk_index]));
+ ack.upload_id = uploadId;
+ // Through the real `_dispatch`, so the routing under test — matching an
+ // ack to its uploader by `upload_id` — is the shipped one.
+ setImmediate(() => tp._dispatch(ack));
+};
+
+const out = { frames, mode: input.mode };
+const done = tp.uploadFile(file, { chunkSize: input.chunk_size,
+ dir: input.dir, root: input.root });
+
+if (input.mode === 'receive') {
+ done.then((stored) => { out.state = 'resolved'; out.stored = stored; })
+ .catch((e) => { out.state = 'rejected'; out.message = e.message; })
+ .finally(() => { out.upload_id = uploadId;
+ process.stdout.write(JSON.stringify(out)); });
+} else {
+ // Nothing will answer, so let the send loop run itself out and report.
+ done.catch((e) => { out.state = 'rejected'; out.message = e.message; });
+ setTimeout(() => { out.upload_id = uploadId;
+ process.stdout.write(JSON.stringify(out)); }, 250);
+}
diff --git a/packages/meshbay-hub/tests/test_transport_contracts.py b/packages/meshbay-hub/tests/test_transport_contracts.py
index b462242..879062b 100644
--- a/packages/meshbay-hub/tests/test_transport_contracts.py
+++ b/packages/meshbay-hub/tests/test_transport_contracts.py
@@ -307,26 +307,60 @@ def test_no_setter_survives_the_state_it_belonged_to():
# ── Parallel uploads ──────────────────────────────────────────────────────────
-def test_an_upload_refusal_names_the_file_it_is_about(transport):
+def test_an_upload_refusal_names_the_upload_it_is_about(transport):
"""Reported 2026-08-16: a second upload started in parallel killed both.
- An error used to carry no filename, so the client could not tell whose it
- was and failed every upload in flight — one name the node disliked took the
- other file with it. The node names the file now, and only that upload stops.
+ An error used to carry nothing identifying, so the client could not tell
+ whose it was and failed every upload in flight — one name the node disliked
+ took the other file with it.
+
+ The node named the *file* until MNP 2.0 and names the `upload_id` now: the
+ filename moved inside the seal, and echoing it in clear so the two sides
+ could match on it would give back precisely what sealing the upload is for.
+ The property is unchanged — one refusal, one failed upload.
"""
body = transport[transport.index("if (msg.type === 'error' && this._uploaders.size)"):]
body = body[:body.index("\n if (msg.type === 'chat_msg'")]
- assert "this._uploaders.has(msg.filename)" in body, (
+ assert "this._uploaders.has(msg.upload_id)" in body, (
"a named refusal must reach one uploader, not all of them")
- assert "if (!msg.filename)" in body, (
+ assert "if (!msg.upload_id)" in body, (
"an unnamed error from an older node must still stop everything — "
"guessing which upload it belongs to would be worse")
-def test_uploads_are_tracked_per_file(transport):
+def test_uploads_are_tracked_per_upload(transport):
"""Acks interleave when two files are in flight."""
assert "this._uploaders = new Map()" in transport
- assert "this._uploaders.set(file.name" in transport
+ assert "this._uploaders.set(uploadId" in transport
+ # And the "already being uploaded" guard still speaks in filenames, because
+ # that is what the caller passed and what it would recognise in the error.
+ assert "this._inFlightUploads.has(file.name)" in transport
+
+
+def test_the_upload_itself_is_sealed(transport):
+ """
+ MNP 2.0. The filename, the destination and the bytes go inside the seal
+ together — sealing the content and announcing the name beside it would be
+ theatre — and only what the node routes on stays outside.
+ """
+ start = transport.index(" async uploadFile(file,")
+ body = transport[start:transport.index("\n /** Create a directory", start)]
+ assert "sealGroup(" in body and "'file_upload'" in body, (
+ "the upload must be sealed under the group key")
+ assert "openGroup(" in body and "'file_upload_ack'" in body, (
+ "the ack carries the stored name and must be opened, not read")
+ # The message the node actually receives: everything between `this._send({`
+ # and its close. Read on its own, because the same field names appear a few
+ # lines above inside `msgpack_encode({...})`, which is the sealed half.
+ sent = body[body.index("this._send({"):]
+ sent = sent[:sent.index("});")]
+ assert "filename" not in sent, "the filename is on the message in clear"
+ assert "data" not in sent, "the bytes are on the message in clear"
+ assert "dir" not in sent and "root" not in sent, (
+ "the destination is on the message in clear")
+ assert "...sealed," in sent, "the message must carry the sealed pair"
+ assert "supportsSealedUpload" in body, (
+ "an older node must be refused before a chunk is sent, not after")
# ── MNP 1.0: the sealed handshake ack ────────────────────────────────────────
diff --git a/packages/meshbay-hub/tests/test_upload_seal_client.py b/packages/meshbay-hub/tests/test_upload_seal_client.py
new file mode 100644
index 0000000..d6f9156
--- /dev/null
+++ b/packages/meshbay-hub/tests/test_upload_seal_client.py
@@ -0,0 +1,169 @@
+"""
+The browser half of MNP 2.0's sealed upload, measured rather than read.
+
+`test_upload_sealed.py` (node side) proves the node opens what the shared
+encoder produces and refuses everything else. This proves the *shipped browser
+code* produces it — and, the part that matters more, that a caller of
+`uploadFile` is still told the name the node stored the file under, which now
+arrives sealed and would otherwise be `undefined` with nothing on screen to say
+so: a chat attachment would point at a file that is not there.
+
+Driven through `harness/upload_seal_probe.mjs`, which runs the shipped
+`transport.js` over the shipped `crypto.js`. The node half in between is the
+real `_do_file_upload`, writing to a real directory.
+
+A source-reading test can see that `sealGroup` is called. Only this can see
+whether what comes out of it opens.
+"""
+
+import json
+import shutil
+import subprocess
+import tempfile
+from pathlib import Path
+
+import msgpack
+import pytest
+from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey
+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
+from meshbay_node.transport.webrtc_server import WebRTCPeerSession
+
+STATIC = Path(__file__).resolve().parents[1] / "src" / "meshbay_hub" / "static"
+PROBE = Path(__file__).resolve().parent / "harness" / "upload_seal_probe.mjs"
+
+pytestmark = pytest.mark.skipif(
+ shutil.which("node") is None or not PROBE.exists(),
+ reason="node unavailable — the client half cannot be measured",
+)
+
+GROUP = "g-upload-probe"
+CHUNK = 32
+BODY = bytes(range(256)) * 3 # 768 bytes → 24 chunks of 32
+
+
+def _run_probe(payload: dict) -> dict:
+ with tempfile.TemporaryDirectory() as d:
+ f = Path(d) / "input.json"
+ f.write_text(json.dumps(payload))
+ proc = subprocess.run(
+ ["node", str(PROBE), str(STATIC), str(f)],
+ capture_output=True, text=True, timeout=60,
+ )
+ if proc.returncode != 0 or not proc.stdout:
+ pytest.fail(f"upload probe failed:\n{proc.stderr}")
+ return json.loads(proc.stdout)
+
+
+def _node_session(tmp_path: Path, gek: bytes) -> WebRTCPeerSession:
+ root = tmp_path / "library"
+ root.mkdir()
+ index = GroupIndex(group_id=GROUP, sk_node=Ed25519PrivateKey.generate())
+ session = WebRTCPeerSession.__new__(WebRTCPeerSession)
+ session._ctx = {
+ "roots": RootSet.build([{"path": str(root), "name": "library",
+ "writable": True}]),
+ "index": index, "sk_node": index.sk_node, "gek": gek,
+ }
+ session._group_id = GROUP
+ session._user_id = "prober"
+ session._pk_user = ""
+ session._uploads = {}
+ session.sent = []
+ session._send = session.sent.append
+ session._audit = lambda *a, **k: None
+ return session
+
+
+def _probe_input(gek: bytes, mode: str, **extra) -> dict:
+ return {
+ "mode": mode, "gek": gek.hex(), "group_id": GROUP,
+ "node_version": "2.0", "chunk_size": CHUNK, "dir": "library",
+ "root": "library",
+ "file": {"name": "holiday.jpg", "data": BODY.hex()},
+ **extra,
+ }
+
+
+@pytest.fixture(scope="module")
+def _gek():
+ return generate_gek()
+
+
+@pytest.fixture(scope="module")
+def _sent(_gek):
+ """Every frame the shipped `uploadFile` puts on the wire, unanswered."""
+ return _run_probe(_probe_input(_gek, "send"))
+
+
+def test_the_browser_puts_no_filename_and_no_content_on_the_wire(_sent):
+ """The whole point, measured on the bytes rather than read off the source."""
+ assert _sent["frames"], "the client sent nothing"
+ for hexframe in _sent["frames"]:
+ raw = bytes.fromhex(hexframe)
+ assert b"holiday.jpg" not in raw, "the filename is on the wire in clear"
+ msg = msgpack.unpackb(raw, raw=False)
+ assert set(msg) == {"type", "v", "upload_id", "chunk_index",
+ "total_chunks", "nonce", "ct"}
+ assert msg["type"] == MNP.FILE_UPLOAD
+
+
+def test_a_real_node_opens_what_the_real_browser_sealed(tmp_path, _gek, _sent):
+ """
+ End to end: the shipped browser encoder into the shipped node handler, with
+ the file that lands on disk as the assertion. A mismatch in the HKDF salt,
+ the AAD encoding or the payload shape shows up here as "did not open" — and
+ nowhere else until somebody tries to upload something.
+ """
+ session = _node_session(tmp_path, _gek)
+ for hexframe in _sent["frames"]:
+ session._do_file_upload(msgpack.unpackb(bytes.fromhex(hexframe), raw=False))
+
+ errors = [m for m in session.sent if m.get("type") == "error"]
+ assert not errors, f"the node refused a frame the browser built: {errors[:1]}"
+
+ root = session._ctx["roots"].roots[0].path
+ assert (root / "holiday.jpg").read_bytes() == BODY
+ assert not list(root.glob("*.part")), "a temp file was left behind"
+
+
+def test_the_caller_is_told_the_name_the_node_chose(tmp_path, _gek, _sent):
+ """
+ `stored_as` is sealed now, so reading it takes a decrypt that can fail
+ silently. It must not: the node finds a free name rather than replacing
+ anything, and a chat attachment that never learns which name points at
+ nothing.
+
+ The acks below are the ones the node really produced — only their
+ `upload_id`, which is outside the seal, is retargeted to the second probe
+ run's own upload.
+ """
+ session = _node_session(tmp_path, _gek)
+ # A file of that name is already there, so the node has to choose another.
+ (session._ctx["roots"].roots[0].path / "holiday.jpg").write_bytes(b"someone else's")
+
+ for hexframe in _sent["frames"]:
+ session._do_file_upload(msgpack.unpackb(bytes.fromhex(hexframe), raw=False))
+ acks = [msgpack.packb(m, use_bin_type=True).hex()
+ for m in session.sent if m.get("type") == MNP.FILE_UPLOAD_ACK]
+ assert len(acks) == len(_sent["frames"])
+
+ result = _run_probe(_probe_input(_gek, "receive", acks=acks))
+ assert result["state"] == "resolved", result.get("message")
+ assert result["stored"]["stored_as"] == "holiday (2).jpg"
+ assert result["stored"]["dir"] == "library"
+
+
+def test_the_client_refuses_an_older_node_before_sending_a_chunk(_gek):
+ """
+ A 1.x node would answer "Missing filename or data" — an error about the
+ wrong thing, naming no upload, which fails every upload in flight. Asked
+ first instead, and nothing goes on the wire.
+ """
+ result = _run_probe(_probe_input(_gek, "receive", acks=[],
+ node_version="1.1"))
+ assert result["state"] == "rejected"
+ assert "older MeshBay" in result["message"]
+ assert result["frames"] == [], "a chunk was sent to a node that cannot open it"
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)