mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 06:23:45 +00:00
79bed44b04
Propagate test IDs from client to server via HTTP headers to maintain proper test isolation when running with server-based stack configs. Without this, recorded/replayed inference requests in server mode would leak across tests. Changes: - Patch client _prepare_request to inject test ID into provider data header - Sync test context from provider data on server side before storage operations - Set LLAMA_STACK_TEST_STACK_CONFIG_TYPE env var based on stack config - Configure console width for cleaner log output in CI - Add SQLITE_STORE_DIR temp directory for test data isolation
93 lines
2.6 KiB
JSON
93 lines
2.6 KiB
JSON
{
|
|
"test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_with_tools[txt=ollama/llama3.2:3b-instruct-fp16-inference:chat_completion:tool_calling]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": "Pretend you are a weather assistant."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "What's the weather like in San Francisco, CA?"
|
|
}
|
|
],
|
|
"stream": false,
|
|
"tool_choice": "auto",
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "get_weather",
|
|
"description": "Get the current weather",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"location": {
|
|
"type": "string",
|
|
"description": "The city and state (both required), e.g. San Francisco, CA."
|
|
}
|
|
},
|
|
"required": [
|
|
"location"
|
|
]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "rec-0de34091fb19",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "tool_calls",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": "",
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": [
|
|
{
|
|
"id": "call_pj4polk7",
|
|
"function": {
|
|
"arguments": "{\"location\":\"San Francisco, CA\"}",
|
|
"name": "get_weather"
|
|
},
|
|
"type": "function",
|
|
"index": 0
|
|
}
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 20,
|
|
"prompt_tokens": 185,
|
|
"total_tokens": 205,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|