Retry Ollama 500 errors in optimistic stream with backoff

With optimistic streaming, intent (qwen2.5:1.5b) and the main stream
(qwen3:latest) start concurrently. When both models are cold-loading,
Ollama returns 500 for both simultaneously. The intent 500 was already
handled silently in classify_intent; the stream 500 now retries up to
2 times (3s then 6s delay) before propagating as an error. 500s only
occur on the first cold-load pair — subsequent requests hit warm models.

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

src/fabledassistant/services/generation_task.py

@@ -11,6 +11,8 @@ import re
 import time
 from collections.abc import AsyncGenerator
 
+import httpx
+
 from sqlalchemy import update
 
 from fabledassistant.config import Config
@@ -291,13 +293,30 @@ async def run_generation(
                 stream_queue: asyncio.Queue[ChatChunk | BaseException | None] = asyncio.Queue(maxsize=256)
 
                 async def _fill_queue() -> None:
-                    try:
+                    # Retry on Ollama 500 (model cold-loading race) up to 2 times.
-                        async for c in stream_chat_with_tools(messages, model, tools=tools, think=think):
+                    last_exc: BaseException | None = None
-                            await stream_queue.put(c)
+                    for attempt in range(3):
-                    except BaseException as exc:
+                        if attempt > 0:
-                        await stream_queue.put(exc)
+                            wait = 3.0 * attempt
-                    finally:
+                            logger.warning(
-                        await stream_queue.put(None)
+                                "Ollama stream 500 (attempt %d/3), retrying in %.0fs", attempt, wait
+                            )
+                            await asyncio.sleep(wait)
+                        try:
+                            async for c in stream_chat_with_tools(messages, model, tools=tools, think=think):
+                                await stream_queue.put(c)
+                            last_exc = None
+                            break
+                        except httpx.HTTPStatusError as exc:
+                            last_exc = exc
+                            if exc.response.status_code != 500:
+                                break  # non-500 errors are not retryable
+                        except BaseException as exc:
+                            last_exc = exc
+                            break
+                    if last_exc is not None:
+                        await stream_queue.put(last_exc)
+                    await stream_queue.put(None)
 
                 stream_fill_task = asyncio.create_task(_fill_queue())
                 buf.append_event("status", {"status": "Generating response..."})