fix: filter image_url for non-vision models at provider layer

- Add  field to ProviderSpec (default True)
- Add  and  methods in LiteLLMProvider
- Filter image_url content blocks in  before sending to non-vision models
- Reverts session-layer filtering from original PR (wrong layer)

This fixes the issue where switching from Claude (vision-capable) to
non-vision models (e.g., Baidu Qianfan) causes API errors due to
unsupported image_url content blocks.

The provider layer is the correct place for this filtering because:
1. It has access to model/provider capabilities
2. It only affects non-vision models
3. It preserves session layer purity (storage should not know about model capabilities)

nanobot/providers/registry.py

@@ -61,6 +61,9 @@ 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()