fix: handle image_url rejection by retrying without images

Replace the static provider-level supports_vision check with a
reactive fallback: when a model returns an image-unsupported error,
strip image_url blocks from messages and retry once. This avoids
maintaining an inaccurate vision capability table and correctly
handles gateway/unknown model scenarios.

Also extract _safe_chat() to deduplicate try/except boilerplate
in chat_with_retry().

nanobot/providers/registry.py

@@ -61,9 +61,6 @@ class ProviderSpec:
     # Provider supports cache_control on content blocks (e.g. Anthropic prompt caching)
     supports_prompt_caching: bool = False
 
-    # Provider supports vision/image inputs (most modern models do)
-    supports_vision: bool = True
-
     @property
     def label(self) -> str:
         return self.display_name or self.name.title()