fix(providers): allow retry and fallback on stream stalled timeout

When a stream stalls mid-response, both the retry layer and
FallbackProvider blocked recovery because content had already been
emitted via on_content_delta. This left users with truncated replies
and no automatic recovery.

For error_kind="timeout" specifically:
- _run_with_retry now suppresses delta callbacks and retries the same
  model instead of returning immediately
- FallbackProvider now allows failover to a different model with
  delta callbacks suppressed

Non-timeout errors retain the original "skip retry/failover after
streamed content" behavior to avoid duplicate output.

nanobot/providers/base.py

@@ -827,10 +827,22 @@ class LLMProvider(ABC):
                 return response
             last_response = response
             if should_retry_guard is not None and not should_retry_guard():
-                logger.warning(
-                    "LLM stream failed after content was emitted; skipping retry"
-                )
-                return response
+                is_timeout = (response.error_kind or "").lower() == "timeout"
+                if is_timeout:
+                    logger.warning(
+                        "LLM stream stalled after content was emitted; "
+                        "suppressing delta callbacks and retrying"
+                    )
+                    kw.setdefault("on_content_delta", None)
+                    kw["on_content_delta"] = None
+                    kw["on_thinking_delta"] = None
+                    kw["on_tool_call_delta"] = None
+                    should_retry_guard = None
+                else:
+                    logger.warning(
+                        "LLM stream failed after content was emitted; skipping retry"
+                    )
+                    return response
             error_key = ((response.content or "").strip().lower() or None)
             if error_key and error_key == last_error_key:
                 identical_error_count += 1

nanobot/providers/fallback_provider.py

@@ -149,10 +149,20 @@ class FallbackProvider(LLMProvider):
                 return response
 
             if has_streamed is not None and has_streamed[0]:
-                logger.warning(
-                    "Primary model error but content already streamed; skipping failover"
-                )
-                return response
+                is_timeout = (response.error_kind or "").lower() == "timeout"
+                if is_timeout:
+                    logger.warning(
+                        "Primary model '{}' stream stalled after content was emitted; "
+                        "attempting failover anyway",
+                        primary_model,
+                    )
+                    has_streamed[0] = False
+                    kwargs["on_content_delta"] = None
+                else:
+                    logger.warning(
+                        "Primary model error but content already streamed; skipping failover"
+                    )
+                    return response
 
             if not self._should_fallback(response):
                 logger.warning(