[loop-cycle-38] fix: add retry logic for Ollama 500 errors (#131) (#133)

Co-authored-by: hermes <hermes@timmy.local>
Co-committed-by: hermes <hermes@timmy.local>

src/timmy/agents/base.py

@@ -10,6 +10,7 @@ SubAgent is the single seed class for ALL agents.  Differentiation
 comes entirely from config (agents.yaml), not from Python subclasses.
 """
 
+import asyncio
 import logging
 from abc import ABC, abstractmethod
 from typing import Any
@@ -124,15 +125,34 @@ class BaseAgent(ABC):
         Returns:
             Agent response
         """
-        try:
-            result = self.agent.run(message, stream=False)
-            response = result.content if hasattr(result, "content") else str(result)
-        except (httpx.ConnectError, httpx.ReadError, ConnectionError) as exc:
-            logger.error("Ollama disconnected: %s", exc)
-            raise
-        except Exception as exc:
-            logger.error("Agent run failed: %s", exc)
-            raise
+        max_retries = 3
+        last_exception = None
+
+        for attempt in range(1, max_retries + 1):
+            try:
+                result = self.agent.run(message, stream=False)
+                response = result.content if hasattr(result, "content") else str(result)
+                break  # Success, exit the retry loop
+            except (httpx.ConnectError, httpx.ReadError, ConnectionError) as exc:
+                logger.error("Ollama disconnected: %s", exc)
+                raise
+            except Exception as exc:
+                last_exception = exc
+                if attempt < max_retries:
+                    logger.warning(
+                        "Agent run failed on attempt %d/%d: %s. Retrying...",
+                        attempt,
+                        max_retries,
+                        exc,
+                    )
+                    await asyncio.sleep(1)
+                else:
+                    logger.error(
+                        "Agent run failed after %d attempts: %s",
+                        max_retries,
+                        exc,
+                    )
+                    raise last_exception from exc
 
         # Emit completion event
         if self.event_bus: