mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
dbe4e84aca
I think the implementation needs more simplification. Spent way too much time trying to get the tests pass with models not co-operating :( Finally had to switch claude-sonnet to get things to pass reliably. ### Test Plan ``` export TAVILY_SEARCH_API_KEY=... export OPENAI_API_KEY=... uv run pytest -p no:warnings \ -s -v tests/verifications/openai_api/test_responses.py \ --provider=stack:starter \ --model openai/gpt-4o ```
136 lines
4.8 KiB
YAML
136 lines
4.8 KiB
YAML
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_mcp_tool:
|
|
test_name: test_response_mcp_tool
|
|
test_params:
|
|
case:
|
|
- case_id: "boiling_point_tool"
|
|
input: "What is the boiling point of myawesomeliquid in Celsius?"
|
|
tools:
|
|
- type: mcp
|
|
server_label: "localmcp"
|
|
server_url: "<FILLED_BY_TEST_RUNNER>"
|
|
output: "Hello, world!"
|
|
|
|
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"
|
|
|
|
# the models are really poor at tool calling after seeing images :/
|
|
test_response_multi_turn_image:
|
|
test_name: test_response_multi_turn_image
|
|
test_params:
|
|
case:
|
|
- case_id: "llama_image_understanding"
|
|
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: "What country do you find this animal primarily in? What continent?"
|
|
output: "peru"
|
|
|
|
test_response_multi_turn_tool_execution:
|
|
test_name: test_response_multi_turn_tool_execution
|
|
test_params:
|
|
case:
|
|
- case_id: "user_file_access_check"
|
|
input: "I need to check if user 'alice' can access the file 'document.txt'. First, get alice's user ID, then check if that user ID can access the file 'document.txt'. Do this as a series of steps, where each step is a separate message. Return only one tool call per step. Summarize the final result with a single 'yes' or 'no' response."
|
|
tools:
|
|
- type: mcp
|
|
server_label: "localmcp"
|
|
server_url: "<FILLED_BY_TEST_RUNNER>"
|
|
output: "yes"
|
|
- case_id: "experiment_results_lookup"
|
|
input: "I need to get the results for the 'boiling_point' experiment. First, get the experiment ID for 'boiling_point', then use that ID to get the experiment results. Tell me what you found."
|
|
tools:
|
|
- type: mcp
|
|
server_label: "localmcp"
|
|
server_url: "<FILLED_BY_TEST_RUNNER>"
|
|
output: "100°C"
|
|
|
|
test_response_multi_turn_tool_execution_streaming:
|
|
test_name: test_response_multi_turn_tool_execution_streaming
|
|
test_params:
|
|
case:
|
|
- case_id: "user_permissions_workflow"
|
|
input: "Help me with this security check: First, get the user ID for 'charlie', then get the permissions for that user ID, and finally check if that user can access 'secret_file.txt'. Stream your progress as you work through each step."
|
|
tools:
|
|
- type: mcp
|
|
server_label: "localmcp"
|
|
server_url: "<FILLED_BY_TEST_RUNNER>"
|
|
stream: true
|
|
output: "no"
|
|
- case_id: "experiment_analysis_streaming"
|
|
input: "I need a complete analysis: First, get the experiment ID for 'chemical_reaction', then get the results for that experiment, and tell me if the yield was above 80%. Please stream your analysis process."
|
|
tools:
|
|
- type: mcp
|
|
server_label: "localmcp"
|
|
server_url: "<FILLED_BY_TEST_RUNNER>"
|
|
stream: true
|
|
output: "85%"
|