mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-15 22:18:00 +00:00
chore(tests): refactor and move responses tests away from verifications (#3068)
This PR kills the verifications infrastructure which is no longer used. It was relocated to the `llama-stack-evals` (https://github.com/meta-llama/llama-stack-evals) repository previously. Responses tests used this infrastructure but that wasn't quite necessary, just a little useful back when @bbrownin introduced the tests. On Discord, we agreed that tests can be moved to our regular integrations test infra. ## Test Plan Some tests currently do fail (although they run!) I will send a follow-up PR which makes them all pass.
This commit is contained in:
Ashwin Bharambe
GitHub
parent
342550c1e2
commit
5f1ddd35e4
36 changed files with 93 additions and 13032 deletions
|
|
@ -0,0 +1,397 @@
|
|||
test_chat_basic:
|
||||
test_name: test_chat_basic
|
||||
test_params:
|
||||
case:
|
||||
- case_id: "earth"
|
||||
input:
|
||||
messages:
|
||||
- content: Which planet do humans live on?
|
||||
role: user
|
||||
output: Earth
|
||||
- case_id: "saturn"
|
||||
input:
|
||||
messages:
|
||||
- content: Which planet has rings around it with a name starting with letter
|
||||
S?
|
||||
role: user
|
||||
output: Saturn
|
||||
test_chat_input_validation:
|
||||
test_name: test_chat_input_validation
|
||||
test_params:
|
||||
case:
|
||||
- case_id: "messages_missing"
|
||||
input:
|
||||
messages: []
|
||||
output:
|
||||
error:
|
||||
status_code: 400
|
||||
- case_id: "messages_role_invalid"
|
||||
input:
|
||||
messages:
|
||||
- content: Which planet do humans live on?
|
||||
role: fake_role
|
||||
output:
|
||||
error:
|
||||
status_code: 400
|
||||
- case_id: "tool_choice_invalid"
|
||||
input:
|
||||
messages:
|
||||
- content: Which planet do humans live on?
|
||||
role: user
|
||||
tool_choice: invalid
|
||||
output:
|
||||
error:
|
||||
status_code: 400
|
||||
- case_id: "tool_choice_no_tools"
|
||||
input:
|
||||
messages:
|
||||
- content: Which planet do humans live on?
|
||||
role: user
|
||||
tool_choice: required
|
||||
output:
|
||||
error:
|
||||
status_code: 400
|
||||
- case_id: "tools_type_invalid"
|
||||
input:
|
||||
messages:
|
||||
- content: Which planet do humans live on?
|
||||
role: user
|
||||
tools:
|
||||
- type: invalid
|
||||
output:
|
||||
error:
|
||||
status_code: 400
|
||||
test_chat_image:
|
||||
test_name: test_chat_image
|
||||
test_params:
|
||||
case:
|
||||
- input:
|
||||
messages:
|
||||
- content:
|
||||
- text: What is in this image?
|
||||
type: text
|
||||
- image_url:
|
||||
url: https://upload.wikimedia.org/wikipedia/commons/f/f7/Llamas%2C_Vernagt-Stausee%2C_Italy.jpg
|
||||
type: image_url
|
||||
role: user
|
||||
output: llama
|
||||
test_chat_structured_output:
|
||||
test_name: test_chat_structured_output
|
||||
test_params:
|
||||
case:
|
||||
- case_id: "calendar"
|
||||
input:
|
||||
messages:
|
||||
- content: Extract the event information.
|
||||
role: system
|
||||
- content: Alice and Bob are going to a science fair on Friday.
|
||||
role: user
|
||||
response_format:
|
||||
json_schema:
|
||||
name: calendar_event
|
||||
schema:
|
||||
properties:
|
||||
date:
|
||||
title: Date
|
||||
type: string
|
||||
name:
|
||||
title: Name
|
||||
type: string
|
||||
participants:
|
||||
items:
|
||||
type: string
|
||||
title: Participants
|
||||
type: array
|
||||
required:
|
||||
- name
|
||||
- date
|
||||
- participants
|
||||
title: CalendarEvent
|
||||
type: object
|
||||
type: json_schema
|
||||
output: valid_calendar_event
|
||||
- case_id: "math"
|
||||
input:
|
||||
messages:
|
||||
- content: You are a helpful math tutor. Guide the user through the solution
|
||||
step by step.
|
||||
role: system
|
||||
- content: how can I solve 8x + 7 = -23
|
||||
role: user
|
||||
response_format:
|
||||
json_schema:
|
||||
name: math_reasoning
|
||||
schema:
|
||||
$defs:
|
||||
Step:
|
||||
properties:
|
||||
explanation:
|
||||
title: Explanation
|
||||
type: string
|
||||
output:
|
||||
title: Output
|
||||
type: string
|
||||
required:
|
||||
- explanation
|
||||
- output
|
||||
title: Step
|
||||
type: object
|
||||
properties:
|
||||
final_answer:
|
||||
title: Final Answer
|
||||
type: string
|
||||
steps:
|
||||
items:
|
||||
$ref: '#/$defs/Step'
|
||||
title: Steps
|
||||
type: array
|
||||
required:
|
||||
- steps
|
||||
- final_answer
|
||||
title: MathReasoning
|
||||
type: object
|
||||
type: json_schema
|
||||
output: valid_math_reasoning
|
||||
test_tool_calling:
|
||||
test_name: test_tool_calling
|
||||
test_params:
|
||||
case:
|
||||
- input:
|
||||
messages:
|
||||
- content: You are a helpful assistant that can use tools to get information.
|
||||
role: system
|
||||
- content: What's the weather like in San Francisco?
|
||||
role: user
|
||||
tools:
|
||||
- function:
|
||||
description: Get current temperature for a given location.
|
||||
name: get_weather
|
||||
parameters:
|
||||
additionalProperties: false
|
||||
properties:
|
||||
location:
|
||||
description: "City and country e.g. Bogot\xE1, Colombia"
|
||||
type: string
|
||||
required:
|
||||
- location
|
||||
type: object
|
||||
type: function
|
||||
output: get_weather_tool_call
|
||||
|
||||
test_chat_multi_turn_tool_calling:
|
||||
test_name: test_chat_multi_turn_tool_calling
|
||||
test_params:
|
||||
case:
|
||||
- case_id: "text_then_weather_tool"
|
||||
input:
|
||||
messages:
|
||||
- - role: user
|
||||
content: "What's the name of the Sun in latin?"
|
||||
- - role: user
|
||||
content: "What's the weather like in San Francisco?"
|
||||
tools:
|
||||
- function:
|
||||
description: Get the current weather
|
||||
name: get_weather
|
||||
parameters:
|
||||
type: object
|
||||
properties:
|
||||
location:
|
||||
description: "The city and state (both required), e.g. San Francisco, CA."
|
||||
type: string
|
||||
required: ["location"]
|
||||
type: function
|
||||
tool_responses:
|
||||
- response: "{'response': '70 degrees and foggy'}"
|
||||
expected:
|
||||
- num_tool_calls: 0
|
||||
answer: ["sol"]
|
||||
- num_tool_calls: 1
|
||||
tool_name: get_weather
|
||||
tool_arguments:
|
||||
location: "San Francisco, CA"
|
||||
- num_tool_calls: 0
|
||||
answer: ["foggy", "70 degrees"]
|
||||
- case_id: "weather_tool_then_text"
|
||||
input:
|
||||
messages:
|
||||
- - role: user
|
||||
content: "What's the weather like in San Francisco?"
|
||||
tools:
|
||||
- function:
|
||||
description: Get the current weather
|
||||
name: get_weather
|
||||
parameters:
|
||||
type: object
|
||||
properties:
|
||||
location:
|
||||
description: "The city and state (both required), e.g. San Francisco, CA."
|
||||
type: string
|
||||
required: ["location"]
|
||||
type: function
|
||||
tool_responses:
|
||||
- response: "{'response': '70 degrees and foggy'}"
|
||||
expected:
|
||||
- num_tool_calls: 1
|
||||
tool_name: get_weather
|
||||
tool_arguments:
|
||||
location: "San Francisco, CA"
|
||||
- num_tool_calls: 0
|
||||
answer: ["foggy", "70 degrees"]
|
||||
- case_id: "add_product_tool"
|
||||
input:
|
||||
messages:
|
||||
- - role: user
|
||||
content: "Please add a new product with name 'Widget', price 19.99, in stock, and tags ['new', 'sale'] and give me the product id."
|
||||
tools:
|
||||
- function:
|
||||
description: Add a new product
|
||||
name: addProduct
|
||||
parameters:
|
||||
type: object
|
||||
properties:
|
||||
name:
|
||||
description: "Name of the product"
|
||||
type: string
|
||||
price:
|
||||
description: "Price of the product"
|
||||
type: number
|
||||
inStock:
|
||||
description: "Availability status of the product."
|
||||
type: boolean
|
||||
tags:
|
||||
description: "List of product tags"
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
required: ["name", "price", "inStock"]
|
||||
type: function
|
||||
tool_responses:
|
||||
- response: "{'response': 'Successfully added product with id: 123'}"
|
||||
expected:
|
||||
- num_tool_calls: 1
|
||||
tool_name: addProduct
|
||||
tool_arguments:
|
||||
name: "Widget"
|
||||
price: 19.99
|
||||
inStock: true
|
||||
tags:
|
||||
- "new"
|
||||
- "sale"
|
||||
- num_tool_calls: 0
|
||||
answer: ["123", "product id: 123"]
|
||||
- case_id: "get_then_create_event_tool"
|
||||
input:
|
||||
messages:
|
||||
- - role: system
|
||||
content: "Todays date is 2025-03-01."
|
||||
- role: user
|
||||
content: "Do i have any meetings on March 3rd at 10 am? Yes or no?"
|
||||
- - role: user
|
||||
content: "Alright then, Create an event named 'Team Building', scheduled for that time same time, in the 'Main Conference Room' and add Alice, Bob, Charlie to it. Give me the created event id."
|
||||
tools:
|
||||
- function:
|
||||
description: Create a new event
|
||||
name: create_event
|
||||
parameters:
|
||||
type: object
|
||||
properties:
|
||||
name:
|
||||
description: "Name of the event"
|
||||
type: string
|
||||
date:
|
||||
description: "Date of the event in ISO format"
|
||||
type: string
|
||||
time:
|
||||
description: "Event Time (HH:MM)"
|
||||
type: string
|
||||
location:
|
||||
description: "Location of the event"
|
||||
type: string
|
||||
participants:
|
||||
description: "List of participant names"
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
required: ["name", "date", "time", "location", "participants"]
|
||||
type: function
|
||||
- function:
|
||||
description: Get an event by date and time
|
||||
name: get_event
|
||||
parameters:
|
||||
type: object
|
||||
properties:
|
||||
date:
|
||||
description: "Date of the event in ISO format"
|
||||
type: string
|
||||
time:
|
||||
description: "Event Time (HH:MM)"
|
||||
type: string
|
||||
required: ["date", "time"]
|
||||
type: function
|
||||
tool_responses:
|
||||
- response: "{'response': 'No events found for 2025-03-03 at 10:00'}"
|
||||
- response: "{'response': 'Successfully created new event with id: e_123'}"
|
||||
expected:
|
||||
- num_tool_calls: 1
|
||||
tool_name: get_event
|
||||
tool_arguments:
|
||||
date: "2025-03-03"
|
||||
time: "10:00"
|
||||
- num_tool_calls: 0
|
||||
answer: ["no", "no events found", "no meetings"]
|
||||
- num_tool_calls: 1
|
||||
tool_name: create_event
|
||||
tool_arguments:
|
||||
name: "Team Building"
|
||||
date: "2025-03-03"
|
||||
time: "10:00"
|
||||
location: "Main Conference Room"
|
||||
participants:
|
||||
- "Alice"
|
||||
- "Bob"
|
||||
- "Charlie"
|
||||
- num_tool_calls: 0
|
||||
answer: ["e_123", "event id: e_123"]
|
||||
- case_id: "compare_monthly_expense_tool"
|
||||
input:
|
||||
messages:
|
||||
- - role: system
|
||||
content: "Todays date is 2025-03-01."
|
||||
- role: user
|
||||
content: "what was my monthly expense in Jan of this year?"
|
||||
- - role: user
|
||||
content: "Was it less than Feb of last year? Only answer with yes or no."
|
||||
tools:
|
||||
- function:
|
||||
description: Get monthly expense summary
|
||||
name: getMonthlyExpenseSummary
|
||||
parameters:
|
||||
type: object
|
||||
properties:
|
||||
month:
|
||||
description: "Month of the year (1-12)"
|
||||
type: integer
|
||||
year:
|
||||
description: "Year"
|
||||
type: integer
|
||||
required: ["month", "year"]
|
||||
type: function
|
||||
tool_responses:
|
||||
- response: "{'response': 'Total expenses for January 2025: $1000'}"
|
||||
- response: "{'response': 'Total expenses for February 2024: $2000'}"
|
||||
expected:
|
||||
- num_tool_calls: 1
|
||||
tool_name: getMonthlyExpenseSummary
|
||||
tool_arguments:
|
||||
month: 1
|
||||
year: 2025
|
||||
- num_tool_calls: 0
|
||||
answer: ["1000", "$1,000", "1,000"]
|
||||
- num_tool_calls: 1
|
||||
tool_name: getMonthlyExpenseSummary
|
||||
tool_arguments:
|
||||
month: 2
|
||||
year: 2024
|
||||
- num_tool_calls: 0
|
||||
answer: ["yes"]
|
||||
|
|
@ -0,0 +1,166 @@
|
|||
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"
|
||||
- case_id: "image_input"
|
||||
input:
|
||||
- role: user
|
||||
content:
|
||||
- type: input_text
|
||||
text: "what teams are playing in this image?"
|
||||
- role: user
|
||||
content:
|
||||
- type: input_image
|
||||
image_url: "https://upload.wikimedia.org/wikipedia/commons/3/3b/LeBron_James_Layup_%28Cleveland_vs_Brooklyn_2018%29.jpg"
|
||||
output: "brooklyn nets"
|
||||
|
||||
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_file_search:
|
||||
test_name: test_response_file_search
|
||||
test_params:
|
||||
case:
|
||||
- case_id: "llama_experts"
|
||||
input: "How many experts does the Llama 4 Maverick model have?"
|
||||
tools:
|
||||
- type: file_search
|
||||
# vector_store_ids param for file_search tool gets added by the test runner
|
||||
file_content: "Llama 4 Maverick has 128 experts"
|
||||
output: "128"
|
||||
- case_id: "llama_experts_pdf"
|
||||
input: "How many experts does the Llama 4 Maverick model have?"
|
||||
tools:
|
||||
- type: file_search
|
||||
# vector_store_ids param for file_search toolgets added by the test runner
|
||||
file_path: "pdfs/llama_stack_and_models.pdf"
|
||||
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%"
|
||||
Loading…
Add table
Add a link
Reference in a new issue