291 lines
11 KiB
Python
291 lines
11 KiB
Python
"""Outbound relay bridge for NAT-safe node HTTP requests."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import base64
|
|
import json
|
|
import logging
|
|
import os
|
|
import re
|
|
import threading
|
|
import time
|
|
import urllib.parse
|
|
import urllib.error
|
|
import urllib.request
|
|
from concurrent.futures import ThreadPoolExecutor
|
|
from dataclasses import dataclass
|
|
|
|
log = logging.getLogger(__name__)
|
|
|
|
DEFAULT_MAX_CONCURRENCY = 8
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class RelayBridgeInfo:
|
|
peer_id: str
|
|
relay_addr: str
|
|
|
|
|
|
def _make_envelope(topic: str, payload: dict, peer_id: str) -> dict:
|
|
return {
|
|
"topic": topic,
|
|
"version": 1,
|
|
"from_peer": peer_id,
|
|
"timestamp": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()),
|
|
"msg_id": f"{peer_id}-{time.time_ns():x}",
|
|
"ttl": 1,
|
|
"payload": payload,
|
|
}
|
|
|
|
|
|
def _max_concurrency_from_env() -> int:
|
|
try:
|
|
value = int(os.environ.get("MESHNET_RELAY_CONCURRENCY", DEFAULT_MAX_CONCURRENCY))
|
|
except (TypeError, ValueError):
|
|
return DEFAULT_MAX_CONCURRENCY
|
|
return max(1, value)
|
|
|
|
|
|
class RelayHttpBridge:
|
|
"""Connect outbound to a relay and proxy relay HTTP requests to localhost.
|
|
|
|
Requests are dispatched on a bounded worker pool (US-037) so a node that is
|
|
the head of one route can still serve per-token ``/forward`` hops of another.
|
|
Streaming responses (``text/event-stream``) are forwarded as multiple chunk
|
|
frames sharing one ``request_id`` (US-036); everything else stays a single
|
|
frame for backward compatibility.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
relay_url: str,
|
|
peer_id: str,
|
|
local_base_url: str,
|
|
advertised_addr: str,
|
|
reconnect_interval: float = 3.0,
|
|
max_concurrency: int | None = None,
|
|
) -> None:
|
|
self.relay_url = relay_url.rstrip("/")
|
|
self.peer_id = peer_id
|
|
self.local_base_url = local_base_url.rstrip("/")
|
|
self.advertised_addr = advertised_addr
|
|
self.reconnect_interval = reconnect_interval
|
|
self.max_concurrency = max(1, max_concurrency) if max_concurrency else _max_concurrency_from_env()
|
|
self._running = False
|
|
self._thread: threading.Thread | None = None
|
|
self._connected = threading.Event()
|
|
self._executor: ThreadPoolExecutor | None = None
|
|
self._send_lock = threading.Lock()
|
|
self._ws = None
|
|
|
|
@property
|
|
def relay_addr(self) -> str:
|
|
base = self.relay_url
|
|
if base.endswith("/ws"):
|
|
base = base[:-3]
|
|
return f"{base}/rpc/{self.peer_id}"
|
|
|
|
def start(self) -> RelayBridgeInfo:
|
|
self._running = True
|
|
self._executor = ThreadPoolExecutor(
|
|
max_workers=self.max_concurrency, thread_name_prefix="relay-http-worker"
|
|
)
|
|
self._thread = threading.Thread(target=self._run, daemon=True, name="relay-http-bridge")
|
|
self._thread.start()
|
|
return RelayBridgeInfo(peer_id=self.peer_id, relay_addr=self.relay_addr)
|
|
|
|
def wait_connected(self, timeout: float = 5.0) -> bool:
|
|
return self._connected.wait(timeout)
|
|
|
|
def stop(self) -> None:
|
|
self._running = False
|
|
if self._thread:
|
|
self._thread.join(timeout=3.0)
|
|
if self._executor is not None:
|
|
self._executor.shutdown(wait=False)
|
|
|
|
def _run(self) -> None:
|
|
import websockets.sync.client as wsc # type: ignore[import]
|
|
|
|
while self._running:
|
|
try:
|
|
with wsc.connect(self.relay_url, open_timeout=5) as ws:
|
|
self._ws = ws
|
|
self._connected.set()
|
|
ws.send(json.dumps(_make_envelope(
|
|
"peer-register",
|
|
{"peer_id": self.peer_id, "addr": self.advertised_addr},
|
|
self.peer_id,
|
|
)))
|
|
while self._running:
|
|
try:
|
|
raw = ws.recv(timeout=1)
|
|
except TimeoutError:
|
|
continue
|
|
try:
|
|
envelope = json.loads(raw)
|
|
except (TypeError, json.JSONDecodeError):
|
|
continue
|
|
if envelope.get("topic") != "relay-http-request":
|
|
continue
|
|
payload = envelope.get("payload", {})
|
|
if payload.get("target_peer") not in {None, self.peer_id}:
|
|
continue
|
|
if self._executor is None:
|
|
break
|
|
self._executor.submit(self._process_request, payload)
|
|
except Exception as exc:
|
|
self._connected.clear()
|
|
self._ws = None
|
|
if self._running:
|
|
log.debug("relay bridge disconnected: %s", exc)
|
|
time.sleep(self.reconnect_interval)
|
|
self._ws = None
|
|
|
|
def _send_response_frame(self, payload: dict) -> bool:
|
|
"""Send one relay-http-response frame; False if the socket is gone.
|
|
|
|
The lock is held per frame so concurrent workers interleave whole
|
|
frames on the shared WebSocket, never torn ones.
|
|
"""
|
|
ws = self._ws
|
|
if ws is None:
|
|
return False
|
|
message = json.dumps(_make_envelope("relay-http-response", payload, self.peer_id))
|
|
try:
|
|
with self._send_lock:
|
|
ws.send(message)
|
|
return True
|
|
except Exception as exc:
|
|
log.debug("relay bridge send failed (request orphaned): %s", exc)
|
|
return False
|
|
|
|
def _process_request(self, payload: dict) -> None:
|
|
request_id = str(payload.get("request_id") or "")
|
|
method = str(payload.get("method") or "POST").upper()
|
|
path = str(payload.get("path") or "/")
|
|
headers = payload.get("headers") if isinstance(payload.get("headers"), dict) else {}
|
|
|
|
req_suffix = f" request_id={request_id}" if request_id else ""
|
|
print(f" [node] relay {method} {path}{req_suffix}", flush=True)
|
|
|
|
# body_base64 carries binary data (e.g. bfloat16 activation tensors) safely.
|
|
# Fallback to text "body" for backward-compat with non-binary requests.
|
|
body_b64 = payload.get("body_base64")
|
|
if body_b64:
|
|
data = base64.b64decode(body_b64)
|
|
else:
|
|
body_text = payload.get("body") or ""
|
|
data = body_text.encode() if isinstance(body_text, str) else bytes(body_text)
|
|
|
|
url = f"{self.local_base_url}{path}"
|
|
req = urllib.request.Request(url, data=data, headers=headers, method=method)
|
|
try:
|
|
with urllib.request.urlopen(req, timeout=300.0) as resp:
|
|
resp_headers = dict(resp.headers)
|
|
content_type = resp.headers.get("Content-Type", "")
|
|
if "text/event-stream" in content_type:
|
|
self._stream_response(request_id, resp, resp_headers)
|
|
return
|
|
resp_bytes = resp.read()
|
|
# Forward all X-Meshnet-* headers so the caller can reconstruct the activation.
|
|
is_binary = "octet-stream" in content_type
|
|
result: dict = {
|
|
"request_id": request_id,
|
|
"status": resp.status,
|
|
"headers": resp_headers,
|
|
}
|
|
if is_binary:
|
|
result["body_base64"] = base64.b64encode(resp_bytes).decode()
|
|
else:
|
|
result["body"] = resp_bytes.decode(errors="replace")
|
|
self._send_response_frame(result)
|
|
except urllib.error.HTTPError as exc:
|
|
self._send_response_frame({
|
|
"request_id": request_id,
|
|
"status": exc.code,
|
|
"headers": {"Content-Type": exc.headers.get("Content-Type", "application/json")},
|
|
"body": exc.read().decode(errors="replace"),
|
|
})
|
|
except Exception as exc:
|
|
self._send_response_frame({
|
|
"request_id": request_id,
|
|
"status": 503,
|
|
"headers": {"Content-Type": "application/json"},
|
|
"body": json.dumps({"error": f"relay bridge local request failed: {exc}"}),
|
|
})
|
|
|
|
def _stream_response(self, request_id: str, resp, resp_headers: dict) -> None:
|
|
"""Forward an SSE response as chunk frames, one per complete SSE event.
|
|
|
|
Frame order: header frame (status + headers), chunk frames, done frame.
|
|
A receiver that sees no ``stream`` key treats the frame as a complete
|
|
legacy response, so non-streaming peers are unaffected.
|
|
"""
|
|
sent = self._send_response_frame({
|
|
"request_id": request_id,
|
|
"status": resp.status,
|
|
"headers": resp_headers,
|
|
"stream": True,
|
|
"done": False,
|
|
})
|
|
if not sent:
|
|
return
|
|
event_lines: list[str] = []
|
|
for raw_line in resp:
|
|
line = raw_line.decode(errors="replace")
|
|
event_lines.append(line)
|
|
if line.strip():
|
|
continue
|
|
# Blank line terminates one SSE event — flush it as a frame.
|
|
if not self._send_response_frame({
|
|
"request_id": request_id,
|
|
"stream": True,
|
|
"chunk": "".join(event_lines),
|
|
"done": False,
|
|
}):
|
|
return
|
|
event_lines = []
|
|
if event_lines:
|
|
if not self._send_response_frame({
|
|
"request_id": request_id,
|
|
"stream": True,
|
|
"chunk": "".join(event_lines),
|
|
"done": False,
|
|
}):
|
|
return
|
|
self._send_response_frame({
|
|
"request_id": request_id,
|
|
"stream": True,
|
|
"done": True,
|
|
})
|
|
|
|
|
|
def _peer_id_suffix(value: str) -> str:
|
|
"""Return a relay-safe suffix for a human node name or numeric instance id."""
|
|
suffix = re.sub(r"[^A-Za-z0-9_.-]+", "-", value.strip()).strip("-._")
|
|
return suffix[:32]
|
|
|
|
|
|
def peer_id_from_wallet(
|
|
wallet_address: str,
|
|
*,
|
|
node_name: str | None = None,
|
|
advertised_addr: str | None = None,
|
|
) -> str:
|
|
"""Build a per-node relay peer id from the wallet plus node identity.
|
|
|
|
Multiple nodes can legitimately share one wallet for payouts, but the relay
|
|
registry is keyed by peer_id. Using only the wallet prefix makes those
|
|
nodes overwrite each other at the relay. Prefer the operator-provided node
|
|
name; if absent, use the advertised endpoint port as the stable integer
|
|
instance suffix (7001, 7002, ... for local multi-node runs).
|
|
"""
|
|
wallet_prefix = wallet_address[:16] if len(wallet_address) >= 16 else wallet_address
|
|
suffix = _peer_id_suffix(node_name or "") if node_name else ""
|
|
if not suffix and advertised_addr:
|
|
parsed = urllib.parse.urlparse(advertised_addr)
|
|
if parsed.port is not None:
|
|
suffix = str(parsed.port)
|
|
return f"{wallet_prefix}-{suffix}" if suffix else wallet_prefix
|