mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-14 22:33:48 +00:00
1394403360
Implementats usage accumulation to StreamingResponseOrchestrator.
The most important part was to pass `stream_options = { "include_usage":
true }` to the chat_completion call. This means I will have to record
all responses tests again because request hash will change :)
Test changes:
- Add usage assertions to streaming and non-streaming tests
- Update test recordings with actual usage data from OpenAI
272 lines
7.7 KiB
JSON
272 lines
7.7 KiB
JSON
{
|
|
"test_id": "tests/integration/agents/test_openai_responses.py::test_list_response_input_items_with_limit_and_order[txt=ollama/llama3.2:3b-instruct-fp16]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Message A: What is the capital of France?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "The capital of France is Paris."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Message B: What about Spain?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "The capital of Spain is Madrid."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Message C: And Italy?"
|
|
}
|
|
],
|
|
"stream": true,
|
|
"stream_options": {
|
|
"include_usage": true
|
|
}
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-4da32cdf48ae",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "The",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-4da32cdf48ae",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " capital",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-4da32cdf48ae",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " of",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-4da32cdf48ae",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " Italy",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-4da32cdf48ae",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " is",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-4da32cdf48ae",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " Rome",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-4da32cdf48ae",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": ".",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-4da32cdf48ae",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-4da32cdf48ae",
|
|
"choices": [],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 8,
|
|
"prompt_tokens": 82,
|
|
"total_tokens": 90,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|