Quick test mode for simulation tests

Fixed o4-mini name, OpenAI removed o4-mini-high
Add max_output_tokens property to ModelCapabilities

conf/custom_models.json

@@ -22,6 +22,7 @@
       "model_name": "The model identifier - OpenRouter format (e.g., 'anthropic/claude-opus-4') or custom model name (e.g., 'llama3.2')",
       "aliases": "Array of short names users can type instead of the full model name",
       "context_window": "Total number of tokens the model can process (input + output combined)",
+      "max_output_tokens": "Maximum number of tokens the model can generate in a single response",
       "supports_extended_thinking": "Whether the model supports extended reasoning tokens (currently none do via OpenRouter or custom APIs)",
       "supports_json_mode": "Whether the model can guarantee valid JSON output",
       "supports_function_calling": "Whether the model supports function/tool calling",
@@ -36,6 +37,7 @@
       "model_name": "my-local-model",
       "aliases": ["shortname", "nickname", "abbrev"],
       "context_window": 128000,
+      "max_output_tokens": 32768,
       "supports_extended_thinking": false,
       "supports_json_mode": true,
       "supports_function_calling": true,
@@ -52,6 +54,7 @@
       "model_name": "anthropic/claude-opus-4",
       "aliases": ["opus", "claude-opus", "claude4-opus", "claude-4-opus"],
       "context_window": 200000,
+      "max_output_tokens": 64000,
       "supports_extended_thinking": false,
       "supports_json_mode": false,
       "supports_function_calling": false,
@@ -63,6 +66,7 @@
       "model_name": "anthropic/claude-sonnet-4",
       "aliases": ["sonnet", "claude-sonnet", "claude4-sonnet", "claude-4-sonnet", "claude"],
       "context_window": 200000,
+      "max_output_tokens": 64000,
       "supports_extended_thinking": false,
       "supports_json_mode": false,
       "supports_function_calling": false,
@@ -74,6 +78,7 @@
       "model_name": "anthropic/claude-3.5-haiku",
       "aliases": ["haiku", "claude-haiku", "claude3-haiku", "claude-3-haiku"],
       "context_window": 200000,
+      "max_output_tokens": 64000,
       "supports_extended_thinking": false,
       "supports_json_mode": false,
       "supports_function_calling": false,
@@ -85,6 +90,7 @@
       "model_name": "google/gemini-2.5-pro",
       "aliases": ["pro","gemini-pro", "gemini", "pro-openrouter"],
       "context_window": 1048576,
+      "max_output_tokens": 65536,
       "supports_extended_thinking": false,
       "supports_json_mode": true,
       "supports_function_calling": false,
@@ -96,6 +102,7 @@
       "model_name": "google/gemini-2.5-flash",
       "aliases": ["flash","gemini-flash", "flash-openrouter", "flash-2.5"],
       "context_window": 1048576,
+      "max_output_tokens": 65536,
       "supports_extended_thinking": false,
       "supports_json_mode": true,
       "supports_function_calling": false,
@@ -107,6 +114,7 @@
       "model_name": "mistralai/mistral-large-2411",
       "aliases": ["mistral-large", "mistral"],
       "context_window": 128000,
+      "max_output_tokens": 32000,
       "supports_extended_thinking": false,
       "supports_json_mode": true,
       "supports_function_calling": true,
@@ -118,6 +126,7 @@
       "model_name": "meta-llama/llama-3-70b",
       "aliases": ["llama", "llama3", "llama3-70b", "llama-70b", "llama3-openrouter"],
       "context_window": 8192,
+      "max_output_tokens": 8192,
       "supports_extended_thinking": false,
       "supports_json_mode": false,
       "supports_function_calling": false,
@@ -129,6 +138,7 @@
       "model_name": "deepseek/deepseek-r1-0528",
       "aliases": ["deepseek-r1", "deepseek", "r1", "deepseek-thinking"],
       "context_window": 65536,
+      "max_output_tokens": 32768,
       "supports_extended_thinking": true,
       "supports_json_mode": true,
       "supports_function_calling": false,
@@ -140,6 +150,7 @@
       "model_name": "perplexity/llama-3-sonar-large-32k-online",
       "aliases": ["perplexity", "sonar", "perplexity-online"],
       "context_window": 32768,
+      "max_output_tokens": 32768,
       "supports_extended_thinking": false,
       "supports_json_mode": false,
       "supports_function_calling": false,
@@ -151,6 +162,7 @@
       "model_name": "openai/o3",
       "aliases": ["o3"],
       "context_window": 200000,
+      "max_output_tokens": 100000,
       "supports_extended_thinking": false,
       "supports_json_mode": true,
       "supports_function_calling": true,
@@ -164,6 +176,7 @@
       "model_name": "openai/o3-mini",
       "aliases": ["o3-mini", "o3mini"],
       "context_window": 200000,
+      "max_output_tokens": 100000,
       "supports_extended_thinking": false,
       "supports_json_mode": true,
       "supports_function_calling": true,
@@ -177,6 +190,7 @@
       "model_name": "openai/o3-mini-high",
       "aliases": ["o3-mini-high", "o3mini-high"],
       "context_window": 200000,
+      "max_output_tokens": 100000,
       "supports_extended_thinking": false,
       "supports_json_mode": true,
       "supports_function_calling": true,
@@ -190,6 +204,7 @@
       "model_name": "openai/o3-pro",
       "aliases": ["o3-pro", "o3pro"],
       "context_window": 200000,
+      "max_output_tokens": 100000,
       "supports_extended_thinking": false,
       "supports_json_mode": true,
       "supports_function_calling": true,
@@ -203,6 +218,7 @@
       "model_name": "openai/o4-mini",
       "aliases": ["o4-mini", "o4mini"],
       "context_window": 200000,
+      "max_output_tokens": 100000,
       "supports_extended_thinking": false,
       "supports_json_mode": true,
       "supports_function_calling": true,
@@ -212,23 +228,11 @@
       "temperature_constraint": "fixed",
       "description": "OpenAI's o4-mini model - optimized for shorter contexts with rapid reasoning and vision"
     },
-    {
-      "model_name": "openai/o4-mini-high",
-      "aliases": ["o4-mini-high", "o4mini-high", "o4minihigh", "o4minihi"],
-      "context_window": 200000,
-      "supports_extended_thinking": false,
-      "supports_json_mode": true,
-      "supports_function_calling": true,
-      "supports_images": true,
-      "max_image_size_mb": 20.0,
-      "supports_temperature": false,
-      "temperature_constraint": "fixed",
-      "description": "OpenAI's o4-mini with high reasoning effort - enhanced for complex tasks with vision"
-    },
     {
       "model_name": "llama3.2",
       "aliases": ["local-llama", "local", "llama3.2", "ollama-llama"],
       "context_window": 128000,
+      "max_output_tokens": 64000,
       "supports_extended_thinking": false,
       "supports_json_mode": false,
       "supports_function_calling": false,