Update app.py

app.py

@@ -43,25 +43,25 @@ logger = logging.getLogger(__name__)
 
 # Model configuration mapping for different API requirements and limits
 MODEL_CONFIGS = {
-    "DeepSeek-V3-0324": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "DeepSeek"},
-    "DeepSeek-R1": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "DeepSeek"},
-    "Meta-Llama-3.1-405B-Instruct": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Meta"},
-    "Llama-3.2-90B-Vision-Instruct": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Meta"},
-    "Llama-3.3-70B-Instruct": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Meta"},
-    "Llama-4-Scout-17B-16E-Instruct": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Meta"},
-    "Llama-4-Maverick-17B-128E-Instruct-FP8": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Meta"},
-    "gpt-4o-mini": {"max_tokens": 16000, "param_name": "max_tokens", "api_version": None, "category": "OpenAI"},
-    "gpt-4.1": {"max_tokens": 16000, "param_name": "max_tokens", "api_version": None, "category": "OpenAI"},
-    "gpt-4o": {"max_tokens": 16000, "param_name": "max_tokens", "api_version": None, "category": "OpenAI"},
-    "o3-mini": {"max_tokens": 16000, "param_name": "max_tokens", "api_version": "2024-12-01-preview", "category": "Anthropic"},
-    "o1": {"max_tokens": 16000, "param_name": "max_completion_tokens", "api_version": "2024-12-01-preview", "category": "Anthropic"},
-    "o1-mini": {"max_tokens": 16000, "param_name": "max_completion_tokens", "api_version": "2024-12-01-preview", "category": "Anthropic"},
-    "o1-preview": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Anthropic"},
-    "Phi-4-multimodal-instruct": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Microsoft"},
-    "Mistral-large-2407": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Mistral"},
-    "Codestral-2501": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Mistral"},
+    "DeepSeek-V3-0324": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "DeepSeek", "warning": None},
+    "DeepSeek-R1": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "DeepSeek", "warning": None},
+    "Meta-Llama-3.1-405B-Instruct": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Meta", "warning": None},
+    "Llama-3.2-90B-Vision-Instruct": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Meta", "warning": None},
+    "Llama-3.3-70B-Instruct": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Meta", "warning": None},
+    "Llama-4-Scout-17B-16E-Instruct": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Meta", "warning": None},
+    "Llama-4-Maverick-17B-128E-Instruct-FP8": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Meta", "warning": None},
+    "gpt-4o-mini": {"max_tokens": 15000, "param_name": "max_tokens", "api_version": None, "category": "OpenAI", "warning": None},
+    "gpt-4.1": {"max_tokens": 15000, "param_name": "max_tokens", "api_version": None, "category": "OpenAI", "warning": None},
+    "gpt-4o": {"max_tokens": 15000, "param_name": "max_tokens", "api_version": None, "category": "OpenAI", "warning": None},
+    "o3-mini": {"max_tokens": 15000, "param_name": "max_tokens", "api_version": "2024-12-01-preview", "category": "Anthropic", "warning": None},
+    "o1": {"max_tokens": 15000, "param_name": "max_completion_tokens", "api_version": "2024-12-01-preview", "category": "Anthropic", "warning": "Uses special parameters. Will use gpt-4o instead."},
+    "o1-mini": {"max_tokens": 15000, "param_name": "max_completion_tokens", "api_version": "2024-12-01-preview", "category": "Anthropic", "warning": "Uses special parameters. Will use gpt-4o instead."},
+    "o1-preview": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Anthropic", "warning": None},
+    "Phi-4-multimodal-instruct": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Microsoft", "warning": None},
+    "Mistral-large-2407": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Mistral", "warning": None},
+    "Codestral-2501": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Mistral", "warning": None},
     # Default configuration for other models
-    "default": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Other"}
+    "default": {"max_tokens": 4000, "param_name": "max_tokens", "api_version": None, "category": "Other", "warning": None}
 }
 
 # Try to import Streamlit Ace
@@ -335,14 +335,15 @@ Here's the complete Manim code:
             # Get configuration for this model (or use default)
             config = MODEL_CONFIGS.get(model_name, MODEL_CONFIGS["default"])
             
-            # Prepare API call parameters based on model requirements
-            api_params = {
-                "messages": [UserMessage(prompt)],
-                "model": model_name
-            }
+            # Check if this is a model that requires max_completion_tokens
+            if config["param_name"] == "max_completion_tokens":
+                # For models requiring max_completion_tokens (Anthropic models)
+                st.warning(f"Model {model_name} requires special handling. Switching to gpt-4o.")
+                model_name = "gpt-4o"
+                config = MODEL_CONFIGS["gpt-4o"]
             
-            # Add the appropriate token parameter
-            api_params[config["param_name"]] = config["max_tokens"]
+            # Prepare common API parameters
+            messages = [UserMessage(prompt)]
             
             # Check if we need to specify API version
             if config["api_version"]:
@@ -366,11 +367,19 @@ Here's the complete Manim code:
                     api_version=config["api_version"]
                 )
                 
-                # Make the API call with the version-specific client
-                response = version_specific_client.complete(**api_params)
+                # Make the API call with the version-specific client and normal max_tokens
+                response = version_specific_client.complete(
+                    messages=messages,
+                    model=model_name,
+                    max_tokens=config["max_tokens"]
+                )
             else:
-                # Use the existing client
-                response = models["client"].complete(**api_params)
+                # Use the existing client with normal max_tokens
+                response = models["client"].complete(
+                    messages=messages,
+                    model=model_name,
+                    max_tokens=config["max_tokens"]
+                )
             
             # Process the response
             completed_code = response.choices[0].message.content