diff options
| author | Christophe Besson <cbesson@gmail.com> | 2026-09-03 15:20:40 +0200 |
|---|---|---|
| committer | Christophe Besson <cbesson@gmail.com> | 2026-09-03 15:20:40 +0200 |
| commit | c1be7571973c3d0b671ed4db2da41266ae3099d8 (patch) | |
| tree | d2b98bf33727c5905669c9c3f40edba30db11ac3 /packages/meshbay-node/src/meshbay_node/transport/webrtc_server.py | |
| parent | 691c6ba4ef51085c89aeddbcabd5c733861eb56b (diff) | |
| download | meshbay-c1be7571973c3d0b671ed4db2da41266ae3099d8.tar.gz | |
refactor!: one file_chunk and index_sync encoder for every transport
`file_chunk` and `index_sync` were each built twice, once per transport, and
the two copies did not agree. WebRTC sent binary, unsigned chunks carrying a
`file_id`; QUIC sent base64 fields, two BLAKE3 hashes, a per-chunk Ed25519
signature and no `file_id`. `index_sync` was plain entries on one transport
and a `GroupIndex.serialize()` envelope on the other. One message type, two
shapes, one consumer each, and nothing that failed when they drifted — finding
C6 one size down, in the two places the handshake unification did not reach.
Phase 9.15 moved WebRTC to the binary format and dropped the per-chunk
signature; the QUIC encoder was never brought along. It is dropped here rather
than reintroduced: the AES-GCM tag authenticates the ciphertext under a
GEK-derived key, and since C3 the node authenticates itself once in the
handshake instead of once per megabyte.
`meshbay_common.protocol` now owns the chunk codec (`chunk_ciphertext`,
`file_chunk_wire`, `file_chunk_plaintext`) and `meshbay_node/transport/wire.py`
the index builder, which also absorbs the delta the daemon used to hand-build.
`test_transport_wire_parity.py` fails if either server grows its own copy back.
`ChunkRequest`/`ChunkResponse` are deleted. `ChunkResponse` described the QUIC
half while reading like the contract for both, which is what made the fork hard
to see at all.
BREAKING CHANGE: MNP 0.15 changes the encoding of `file_chunk` and `index_sync`
on the QUIC transport. The WebRTC shapes are byte for byte unchanged and no
QUIC client ships, which is why this is a MINOR bump; a deployed QUIC peer
would have made it MAJOR.
Also fixes a test fixture that put a `Path` where the daemon puts a `RootSet`.
Nothing caught it: the old QUIC index handler never touched `roots`, and
`entry_abs_path` fell through `Path.resolve(strict=...)`, reading the virtual
path as a truthy flag and returning the right file by accident.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AsoWC3GmhNdwVFomW3QjH3
Diffstat (limited to 'packages/meshbay-node/src/meshbay_node/transport/webrtc_server.py')
| -rw-r--r-- | packages/meshbay-node/src/meshbay_node/transport/webrtc_server.py | 97 |
1 files changed, 11 insertions, 86 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 1f069e7..370a8b4 100644 --- a/packages/meshbay-node/src/meshbay_node/transport/webrtc_server.py +++ b/packages/meshbay-node/src/meshbay_node/transport/webrtc_server.py @@ -93,8 +93,8 @@ from meshbay_common.join import ( ROLE_OPERATOR, join_transcript, ) -from meshbay_common.webcrypto import chunk_key_aes, encrypt_chunk_aes -from meshbay_common.protocol import MNP, index_entry_wire +from meshbay_common.protocol import MNP, chunk_ciphertext, file_chunk_wire +from meshbay_node.transport.wire import index_sync_message from meshbay_node.indexer import GroupIndex from meshbay_node.indexer.indexer import DirectoryIndexer from meshbay_node import linkpreview, ops @@ -2608,50 +2608,7 @@ class WebRTCPeerSession: def _do_index_sync(self) -> None: ctx = self._group_ctx() - idx = ctx["index"] - entries = [index_entry_wire(e) for e in idx.entries] - self._send({ - "type": MNP.INDEX_SYNC, - "v": MNP_VERSION, - "group_id": idx.group_id, - "version": idx.version, - "entries": entries, - # Directories are not index entries, so the client used to infer them - # from file paths — which means a folder someone just created, or one - # they emptied, simply did not exist as far as the UI was concerned. - "dirs": self._list_dirs(ctx.get("roots")), - # Which top-level folders are roots, and whether each is readable. - # A frozen root's files stay listed, so without this a member cannot - # tell "the drive is unplugged" from "it is all still there". - "roots": ctx["roots"].describe() if ctx.get("roots") else [], - }) - - @staticmethod - def _list_dirs(roots: RootSet | None) -> list[str]: - """ - Every directory in the group, as members address them, sorted. - - Each root appears as a directory in its own right, so a root holding no - files yet is still somewhere a member can navigate to and upload into. - An unavailable root is listed too — its content is frozen, not gone, and - hiding it would look exactly like deletion. - """ - if not roots: - return [] - out: list[str] = [] - for root in roots: - out.append(root.name) - if not root.available: - continue - try: - for path in sorted(root.path.rglob("*")): - if path.is_dir() and not path.name.startswith("."): - rel = path.relative_to(root.path) - if not any(part.startswith(".") for part in rel.parts): - out.append(f"{root.name}/{rel.as_posix()}") - except OSError: - continue - return sorted(out)[:2000] + self._send(index_sync_message(ctx["index"], ctx.get("roots"))) async def _try_serve_thumbnail( self, thumb_hash: str, chunk_index: int, gek: bytes | None, @@ -2677,10 +2634,8 @@ class WebRTCPeerSession: if start > len(blob) or (start == len(blob) and chunk_index != 0): return None piece = blob[start:start + CHUNK_SIZE] - return _encrypt_chunk_bytes( - self._ctx["sk_node"], gek, piece, chunk_index, - bytes.fromhex(thumb_hash), thumb_hash, - ) + return file_chunk_wire( + gek, piece, chunk_index, bytes.fromhex(thumb_hash), thumb_hash) async def _do_file_request(self, msg: dict) -> None: ctx = self._group_ctx() @@ -2707,13 +2662,7 @@ class WebRTCPeerSession: getattr(self._channel, "bufferedAmount", "?")) file_hash = bytes.fromhex(entry.id) chunk_data = _read_and_encrypt( - self._ctx["sk_node"], - ctx["gek"], - file_path, - chunk_index, - file_hash, - entry.id, - ) + ctx["gek"], file_path, chunk_index, file_hash, entry.id) # Backpressure. Without it the node hands the whole window to the # channel at once and the reader sees the first chunk, then nothing for # as long as the link takes to drain the rest. @@ -4435,8 +4384,9 @@ class WebRTCPeerSession: data = await proc.stdout.read(STREAM_SEGMENT_SIZE) if not data: break - ckey = chunk_key_aes(gek, file_hash, index) - nonce, ct = encrypt_chunk_aes(ckey, data) + # Same derivation as a file chunk, indexed by segment: one + # implementation, in `meshbay_common.protocol`. + nonce, ct = chunk_ciphertext(gek, data, index, file_hash) self._send({ "type": MNP.STREAM_DATA, "v": MNP_VERSION, @@ -4546,43 +4496,18 @@ class WebRTCPeerSession: await self._pc.close() -def _encrypt_chunk_bytes( - sk_node: Ed25519PrivateKey, - gek: bytes, - plaintext: bytes, - chunk_index: int, - file_hash: bytes, - file_id: str = "", -) -> dict: - ckey = chunk_key_aes(gek, file_hash, chunk_index) - nonce, ct = encrypt_chunk_aes(ckey, plaintext) - - return { - "type": MNP.FILE_CHUNK, - "v": MNP_VERSION, - # Named so a client running several downloads at once can tell whose - # reply this is. It used to carry only the index, which made matching a - # reply to its request a question of arrival order. - "file_id": file_id, - "chunk_index": chunk_index, - "plaintext_size": len(plaintext), - "nonce": nonce, - "ct": ct, - } - - def _read_and_encrypt( - sk_node: Ed25519PrivateKey, gek: bytes, file_path: Path, chunk_index: int, file_hash: bytes, file_id: str = "", ) -> dict: + """Read one chunk off disk and encrypt it. Blocking; the caller keeps it short.""" with open(file_path, "rb") as f: f.seek(chunk_index * CHUNK_SIZE) plaintext = f.read(CHUNK_SIZE) - return _encrypt_chunk_bytes(sk_node, gek, plaintext, chunk_index, file_hash, file_id) + return file_chunk_wire(gek, plaintext, chunk_index, file_hash, file_id) async def _transcode_audio_to_aac(file_path: Path) -> bytes: |