fix(image-list): bound acknowledgements and configure run deadline

This commit is contained in:
Robert Wojciechowski
2026-10-11 21:07:19 +00:00
parent bac16afaad
commit eac29590bb
4 changed files with 389 additions and 21 deletions
+37 -20
View File
@@ -77,27 +77,44 @@ async def _dispatch_via_websocket(worker_url, payload, client_id, timeout=60.0):
ws_url = worker_url.replace("http://", "ws://").replace("https://", "wss://")
ws_url = f"{ws_url}/distributed/worker_ws"
session = await get_client_session()
loop = asyncio.get_running_loop()
deadline = loop.time() + timeout
ws = None
async with session.ws_connect(ws_url, heartbeat=20, timeout=timeout) as ws:
await ws.send_json(ws_payload)
async for msg in ws:
if msg.type == aiohttp.WSMsgType.TEXT:
data = json.loads(msg.data or "{}")
if data.get("type") == "dispatch_ack" and data.get("request_id") == request_id:
if data.get("ok"):
return data.get("prompt_id")
error_text = data.get("error") or "Worker rejected websocket dispatch."
validation_error = data.get("validation_error")
node_errors = data.get("node_errors")
if validation_error:
error_text = f"{error_text} | validation_error={validation_error}"
if node_errors:
error_text = f"{error_text} | node_errors={node_errors}"
raise RuntimeError(error_text)
elif msg.type in (aiohttp.WSMsgType.ERROR, aiohttp.WSMsgType.CLOSED):
raise RuntimeError(f"Worker websocket closed unexpectedly: {msg.type}")
raise RuntimeError("Worker websocket closed before dispatch_ack was received.")
try:
async with asyncio.timeout_at(deadline):
ws = await session.ws_connect(ws_url, heartbeat=20)
await ws.send_json(ws_payload)
while True:
msg = await ws.receive()
if msg.type == aiohttp.WSMsgType.TEXT:
data = json.loads(msg.data or "{}")
if data.get("type") == "dispatch_ack" and data.get("request_id") == request_id:
if data.get("ok"):
return data.get("prompt_id")
error_text = data.get("error") or "Worker rejected websocket dispatch."
validation_error = data.get("validation_error")
node_errors = data.get("node_errors")
if validation_error:
error_text = f"{error_text} | validation_error={validation_error}"
if node_errors:
error_text = f"{error_text} | node_errors={node_errors}"
raise RuntimeError(error_text)
elif msg.type in (aiohttp.WSMsgType.ERROR, aiohttp.WSMsgType.CLOSE, aiohttp.WSMsgType.CLOSED):
raise RuntimeError(f"Worker websocket closed before acknowledgement: {msg.type}; submission status is ambiguous")
except asyncio.TimeoutError as exc:
raise RuntimeError(
"Worker websocket dispatch timed out before dispatch_ack; submission status is ambiguous."
) from exc
finally:
if ws is not None:
# Closing must not discard an already acknowledged prompt ID or
# replace a definite rejection with an ambiguous timeout.
try:
async with asyncio.timeout_at(min(deadline, loop.time() + 1.0)):
await ws.close()
except (asyncio.TimeoutError, aiohttp.ClientError):
pass
async def dispatch_worker_prompt(