test_response_basic: test_name: test_response_basic test_params: case: - case_id: "earth" input: "Which planet do humans live on?" output: "earth" - case_id: "saturn" input: "Which planet has rings around it with a name starting with letter S?" output: "saturn" test_response_multi_turn: test_name: test_response_multi_turn test_params: case: - case_id: "earth" turns: - input: "Which planet do humans live on?" output: "earth" - input: "What is the name of the planet from your previous response?" output: "earth" test_response_web_search: test_name: test_response_web_search test_params: case: - case_id: "llama_experts" input: "How many experts does the Llama 4 Maverick model have?" tools: - type: web_search search_context_size: "low" output: "128" test_response_custom_tool: test_name: test_response_custom_tool test_params: case: - case_id: "sf_weather" input: "What's the weather like in San Francisco?" tools: - type: function name: get_weather description: Get current temperature for a given location. parameters: additionalProperties: false properties: location: description: "City and country e.g. Bogot\xE1, Colombia" type: string required: - location type: object test_response_image: test_name: test_response_image test_params: case: - case_id: "llama_image" input: - role: user content: - type: input_text text: "Identify the type of animal in this image." - type: input_image image_url: "https://upload.wikimedia.org/wikipedia/commons/f/f7/Llamas%2C_Vernagt-Stausee%2C_Italy.jpg" output: "llama" test_response_multi_turn_image: test_name: test_response_multi_turn_image test_params: case: - case_id: "llama_image_search" turns: - input: - role: user content: - type: input_text text: "What type of animal is in this image? Please respond with a single word that starts with the letter 'L'." - type: input_image image_url: "https://upload.wikimedia.org/wikipedia/commons/f/f7/Llamas%2C_Vernagt-Stausee%2C_Italy.jpg" output: "llama" - input: "Search the web using the search tool for the animal from the previous response. Your search query should be a single phrase that includes the animal's name and the words 'maverick', 'scout' and 'llm'" tools: - type: web_search output: "model"