mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-16 14:57:20 +00:00
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 ```
300 lines
8.6 KiB
JSON
300 lines
8.6 KiB
JSON
{
|
|
"test_id": "tests/integration/responses/test_file_search.py::test_response_text_format[openai_client-txt=openai/gpt-4o-text_format0]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "https://api.openai.com/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "gpt-4o",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "What is the capital of France?"
|
|
}
|
|
],
|
|
"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-313ecfe661c7",
|
|
"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": "1WZ2knPyb1RAXt"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-313ecfe661c7",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "The",
|
|
"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": "oV3TMmLTiynnz"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-313ecfe661c7",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " capital",
|
|
"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": "kz0CqPWG"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-313ecfe661c7",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " of",
|
|
"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": "R4jykhQRTZy9p"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-313ecfe661c7",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " France",
|
|
"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": "n1cGWJwLH"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-313ecfe661c7",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " is",
|
|
"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": "kchWsk58hsAP8"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-313ecfe661c7",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " Paris",
|
|
"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": "b2g8KtcGLT"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-313ecfe661c7",
|
|
"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": "q6KxOIgDlg5alMB"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-313ecfe661c7",
|
|
"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": "TMwJD6aSDE"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-313ecfe661c7",
|
|
"choices": [],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_eb3c3cb84d",
|
|
"usage": {
|
|
"completion_tokens": 7,
|
|
"prompt_tokens": 14,
|
|
"total_tokens": 21,
|
|
"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": {}
|
|
}
|