fix(vision): proactive downgrade for providers rejecting list-type tool content (#41072)

Xiaomi MiMo (and potentially other providers) support multimodal user
messages but reject list-type tool message content with 400 'text is not
set'. Previously this was handled reactively — the API call would fail,
images would be stripped, and the request retried, losing visual info.

Fix: add supports_vision_tool_messages field to ProviderProfile (default
True). Xiaomi sets it to False. _tool_result_content_for_active_model
now checks this field proactively and returns a text summary instead of
list content, avoiding the round-trip failure entirely.

plugins/model-providers/xiaomi/__init__.py

@@ -10,6 +10,7 @@ xiaomi = ProviderProfile(
     base_url="https://api.xiaomimimo.com/v1",
     supports_health_check=False,  # /v1/models returns 401 even with valid key
     supports_vision=True,  # mimo-v2-omni is vision-capable
+    supports_vision_tool_messages=False,  # rejects list-type tool content (400 "text is not set")
 )
 
 register_provider(xiaomi)