fix: improve MiniMax code plan integration (#1169)

This PR improves MiniMax Code Plan integration in DeerFlow by fixing three issues in the current flow: stream errors were not clearly surfaced in the UI, the frontend could not display the actual provider model ID, and MiniMax reasoning output could leak into final assistant content as inline <think>...</think>. The change adds a MiniMax-specific adapter, exposes real model IDs end-to-end, and adds a frontend fallback for historical messages.
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

backend/app/gateway/routers/models.py

@@ -10,6 +10,7 @@ class ModelResponse(BaseModel):
     """Response model for model information."""
 
     name: str = Field(..., description="Unique identifier for the model")
+    model: str = Field(..., description="Actual provider model identifier")
     display_name: str | None = Field(None, description="Human-readable name")
     description: str | None = Field(None, description="Model description")
     supports_thinking: bool = Field(default=False, description="Whether model supports thinking mode")
@@ -61,6 +62,7 @@ async def list_models() -> ModelsListResponse:
     models = [
         ModelResponse(
             name=model.name,
+            model=model.model,
             display_name=model.display_name,
             description=model.description,
             supports_thinking=model.supports_thinking,
@@ -106,6 +108,7 @@ async def get_model(model_name: str) -> ModelResponse:
 
     return ModelResponse(
         name=model.name,
+        model=model.model,
         display_name=model.display_name,
         description=model.description,
         supports_thinking=model.supports_thinking,