Support multimodal images in local chat agent

2026-08-29 21:17:20 +08:00
parent a315c62f3a
commit 71fd182f50
3 changed files with 56 additions and 4 deletions
@@ -429,11 +429,11 @@ def create_console_app(
        if not isinstance(raw_messages, list) or not raw_messages:
            raise HTTPException(status_code=400, detail="messages must be a non-empty list")
        messages = [
-            {"role": str(item["role"]), "content": str(item["content"])}
+            {key: value for key, value in item.items() if key in {"role", "content", "image_base64", "mime_type", "text"}}
            for item in raw_messages
            if isinstance(item, dict)
            and item.get("role") in {"user", "assistant"}
-            and isinstance(item.get("content"), str)
+            and (isinstance(item.get("content"), (str, list)) or isinstance(item.get("image_base64"), str))
        ]
        if not messages:
            raise HTTPException(status_code=400, detail="messages are invalid")