llama-stack-mirror/tests/integration/responses/recordings/a99db6a17bb74960fab54946774974f0e958acfe389ee5d43d58fd39c20e194c.json
Ashwin Bharambe e9b4278a51
feat(responses)!: improve responses + conversations implementations (#3810)
This PR updates the Conversation item related types and improves a
couple critical parts of the implemenation:

- it creates a streaming output item for the final assistant message
output by
  the model. until now we only added content parts and included that
  message in the final response.

- rewrites the conversation update code completely to account for items
  other than messages (tool calls, outputs, etc.)

## Test Plan

Used the test script from
https://github.com/llamastack/llama-stack-client-python/pull/281 for
this

```
TEST_API_BASE_URL=http://localhost:8321/v1 \
  pytest tests/integration/test_agent_turn_step_events.py::test_client_side_function_tool -xvs
```
2025-10-15 09:36:11 -07:00

273 lines
7.8 KiB
JSON

{
"test_id": "tests/integration/responses/test_basic_responses.py::test_response_non_streaming_basic[openai_client-txt=openai/gpt-4o-earth]",
"request": {
"method": "POST",
"url": "https://api.openai.com/v1/v1/chat/completions",
"headers": {},
"body": {
"model": "gpt-4o",
"messages": [
{
"role": "user",
"content": "Which planet do humans live on?"
}
],
"stream": true,
"stream_options": {
"include_usage": true
}
},
"endpoint": "/v1/chat/completions",
"model": "gpt-4o"
},
"response": {
"body": [
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "rec-a99db6a17bb7",
"choices": [
{
"delta": {
"content": "",
"function_call": null,
"refusal": null,
"role": "assistant",
"tool_calls": null
},
"finish_reason": null,
"index": 0,
"logprobs": null
}
],
"created": 0,
"model": "gpt-4o-2024-08-06",
"object": "chat.completion.chunk",
"service_tier": "default",
"system_fingerprint": "fp_eb3c3cb84d",
"usage": null,
"obfuscation": "ElQiOEZaLdsQRl"
}
},
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "rec-a99db6a17bb7",
"choices": [
{
"delta": {
"content": "Hum",
"function_call": null,
"refusal": null,
"role": null,
"tool_calls": null
},
"finish_reason": null,
"index": 0,
"logprobs": null
}
],
"created": 0,
"model": "gpt-4o-2024-08-06",
"object": "chat.completion.chunk",
"service_tier": "default",
"system_fingerprint": "fp_eb3c3cb84d",
"usage": null,
"obfuscation": "JiYTbm0V0ao3u"
}
},
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "rec-a99db6a17bb7",
"choices": [
{
"delta": {
"content": "ans",
"function_call": null,
"refusal": null,
"role": null,
"tool_calls": null
},
"finish_reason": null,
"index": 0,
"logprobs": null
}
],
"created": 0,
"model": "gpt-4o-2024-08-06",
"object": "chat.completion.chunk",
"service_tier": "default",
"system_fingerprint": "fp_eb3c3cb84d",
"usage": null,
"obfuscation": "pbgYLzXrs2jA7"
}
},
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "rec-a99db6a17bb7",
"choices": [
{
"delta": {
"content": " live",
"function_call": null,
"refusal": null,
"role": null,
"tool_calls": null
},
"finish_reason": null,
"index": 0,
"logprobs": null
}
],
"created": 0,
"model": "gpt-4o-2024-08-06",
"object": "chat.completion.chunk",
"service_tier": "default",
"system_fingerprint": "fp_eb3c3cb84d",
"usage": null,
"obfuscation": "IUviZYD0Jsc"
}
},
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "rec-a99db6a17bb7",
"choices": [
{
"delta": {
"content": " on",
"function_call": null,
"refusal": null,
"role": null,
"tool_calls": null
},
"finish_reason": null,
"index": 0,
"logprobs": null
}
],
"created": 0,
"model": "gpt-4o-2024-08-06",
"object": "chat.completion.chunk",
"service_tier": "default",
"system_fingerprint": "fp_eb3c3cb84d",
"usage": null,
"obfuscation": "jd8BXYakJJIgW"
}
},
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "rec-a99db6a17bb7",
"choices": [
{
"delta": {
"content": " Earth",
"function_call": null,
"refusal": null,
"role": null,
"tool_calls": null
},
"finish_reason": null,
"index": 0,
"logprobs": null
}
],
"created": 0,
"model": "gpt-4o-2024-08-06",
"object": "chat.completion.chunk",
"service_tier": "default",
"system_fingerprint": "fp_eb3c3cb84d",
"usage": null,
"obfuscation": "kj88HaazyL"
}
},
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "rec-a99db6a17bb7",
"choices": [
{
"delta": {
"content": ".",
"function_call": null,
"refusal": null,
"role": null,
"tool_calls": null
},
"finish_reason": null,
"index": 0,
"logprobs": null
}
],
"created": 0,
"model": "gpt-4o-2024-08-06",
"object": "chat.completion.chunk",
"service_tier": "default",
"system_fingerprint": "fp_eb3c3cb84d",
"usage": null,
"obfuscation": "G5pOip6OdViiW4q"
}
},
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "rec-a99db6a17bb7",
"choices": [
{
"delta": {
"content": null,
"function_call": null,
"refusal": null,
"role": null,
"tool_calls": null
},
"finish_reason": "stop",
"index": 0,
"logprobs": null
}
],
"created": 0,
"model": "gpt-4o-2024-08-06",
"object": "chat.completion.chunk",
"service_tier": "default",
"system_fingerprint": "fp_eb3c3cb84d",
"usage": null,
"obfuscation": "Oc0jk2Qe7E"
}
},
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "rec-a99db6a17bb7",
"choices": [],
"created": 0,
"model": "gpt-4o-2024-08-06",
"object": "chat.completion.chunk",
"service_tier": "default",
"system_fingerprint": "fp_eb3c3cb84d",
"usage": {
"completion_tokens": 6,
"prompt_tokens": 14,
"total_tokens": 20,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0
}
},
"obfuscation": ""
}
}
],
"is_streaming": true
},
"id_normalization_mapping": {}
}