fix: wrap acompletion in asyncio.wait_for to prevent indefinite hangs (#453)

* fix: wrap acompletion in asyncio.wait_for to prevent indefinite hangs

litellm's timeout parameter doesn't always propagate to the underlying
httpx transport for Bedrock converse streaming. When Bedrock accepts the
TCP connection but never starts streaming chunks, the acompletion call
hangs indefinitely with all connections in CLOSED state.

This wraps the acompletion call in asyncio.wait_for() using the
configured LLM_TIMEOUT (default 300s). TimeoutError is already retryable
via _should_retry (status_code=None), so the retry loop handles it.

Diagnosed via faulthandler thread dump showing the main asyncio event
loop blocked in selectors.select() with no pending callbacks.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: add per-chunk timeout to streaming loop

Addresses review feedback: the initial asyncio.wait_for only guards the
acompletion call. If Bedrock returns headers but stalls mid-stream, the
async for loop could still hang indefinitely.

Replaces async for with explicit __anext__ calls wrapped in
asyncio.wait_for, using the same configured timeout. Mid-stream stalls
now raise TimeoutError and trigger the existing retry logic.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Sean Turner <sean.turner@zerohash.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

strix/llm/llm.py

@@ -176,9 +176,18 @@ class LLM:
         done_streaming = 0
 
         self._total_stats.requests += 1
-        response = await acompletion(**self._build_completion_args(messages), stream=True)
+        timeout = self.config.timeout
+        response = await asyncio.wait_for(
+            acompletion(**self._build_completion_args(messages), stream=True),
+            timeout=timeout,
+        )
 
-        async for chunk in response:
+        async_iter = response.__aiter__()
+        while True:
+            try:
+                chunk = await asyncio.wait_for(async_iter.__anext__(), timeout=timeout)
+            except StopAsyncIteration:
+                break
             chunks.append(chunk)
             if done_streaming:
                 done_streaming += 1