ChatCompletionsResponse

Response payload for the Chat Completions HTTP API.

This response is 100% compatible with OpenAI's Chat Completions API format. All fields follow the official OpenAI specification exactly.

Standard Response:

`{
"id": "chatcmpl-xxx",
"object": "chat.completion",
"created": 1234567890,
"model": "gpt-4",
"choices": [
{
"index": 0,
"message": {"role": "assistant", "content": "Hello!"},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 10,
"completion_tokens": 5,
"total_tokens": 15
}
}
`

Response with Tool Calls:

When the assistant calls tools:

`{
"id": "chatcmpl-xxx",
"object": "chat.completion",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": null,
"tool_calls": [{
"id": "call_abc",
"type": "function",
"function": {"name": "get_weather", "arguments": "{\"city\":\"Hangzhou\"}"}
}]
},
"finish_reason": "tool_calls"
}],
"usage": {...}
}
`

Stateless Client Responsibility:

The client must:

• Append the assistant message from response to their conversation history

• If tool_calls present, execute tools and append tool result messages

• Send the complete history in the next request