llama-stack-mirror/tests/integration/agents/recordings/585a2cf2c22b0db155a6a94052836b34c42f68bf04b1b2cb74ddf00943c0442d.json
Ashwin Bharambe 1394403360
feat(responses): implement usage tracking in streaming responses (#3771)
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
2025-10-10 12:27:03 -07:00

122 lines
3.5 KiB
JSON

{
"test_id": "tests/integration/agents/test_openai_responses.py::test_function_call_output_response_with_none_arguments[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": "what's the current time? You MUST call the `get_current_time` function to find out."
}
],
"stream": true,
"stream_options": {
"include_usage": true
},
"tools": [
{
"type": "function",
"function": {
"type": "function",
"name": "get_current_time",
"description": "Get the current time",
"parameters": {},
"strict": null
}
}
]
},
"endpoint": "/v1/chat/completions",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": [
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "rec-585a2cf2c22b",
"choices": [
{
"delta": {
"content": "",
"function_call": null,
"refusal": null,
"role": "assistant",
"tool_calls": [
{
"index": 0,
"id": "call_lqrdy0rt",
"function": {
"arguments": "{}",
"name": "get_current_time"
},
"type": "function"
}
]
},
"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-585a2cf2c22b",
"choices": [
{
"delta": {
"content": "",
"function_call": null,
"refusal": null,
"role": "assistant",
"tool_calls": null
},
"finish_reason": "tool_calls",
"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-585a2cf2c22b",
"choices": [],
"created": 0,
"model": "llama3.2:3b-instruct-fp16",
"object": "chat.completion.chunk",
"service_tier": null,
"system_fingerprint": "fp_ollama",
"usage": {
"completion_tokens": 14,
"prompt_tokens": 161,
"total_tokens": 175,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
}
],
"is_streaming": true
},
"id_normalization_mapping": {}
}