Files
new-api/relaykit/relayconvert/testdata/golden/response/openai_to_openai_responses.golden.json
T
Calcium-Ion 0ed497f066 feat(relay): hosted-tool conversion fidelity, reasoning normalization, and billing usage integrity (#7137)
* feat(relaykit): preserve hosted tools across conversions

- add protocol-neutral hosted-tool DTOs, conversion metadata, and loss policies
- bridge citations, grounding metadata, and hosted-tool stream lifecycles
- document the public conversion behavior and channel policy controls

* refactor(relaykit): normalize reasoning and thinking intent

- centralize provider-neutral reasoning intent, effort, and budget mappings
- parse model suffixes at the host entry boundary while preserving provider-owned tails
- keep adaptive Claude thinking and explicit zero-token compatibility consistent

* fix(billing): preserve authoritative usage across relay hops

- carry native BillingUsage sidecars through direct and streamed protocol bridges
- merge partial and terminal usage monotonically with safe fallback settlement
- retain cache metadata, penultimate usage, and per-call Gemini tool surcharges

* feat(relay): bridge Responses with Claude and Gemini protocols

- add direct request, response, and stream converters across supported relay formats
- expose Claude count_tokens and Chat-to-Responses compatibility endpoints
- carry conversion diagnostics through the host while retaining the curated public goldens

* fix(relay): wire relaykit conversions into host channels

- connect handlers, adaptors, and channel settings to the standalone conversion layer
- keep model mapping, pricing identity, retries, and provider-specific suffix behavior aligned
- ignore local audit artifacts and retain focused public regression coverage
2026-09-01 21:53:35 +08:00

118 lines
2.6 KiB
JSON

{
"id": "chatcmpl-fixed",
"object": "response",
"created_at": 0,
"status": "completed",
"instructions": null,
"max_output_tokens": 0,
"model": "gpt-test",
"output": [
{
"type": "reasoning",
"id": "chatcmpl-fixed_reasoning_0",
"status": "completed",
"role": "",
"content": null,
"summary": [
{
"type": "summary_text",
"text": "Deep thought."
}
],
"quality": "",
"size": ""
},
{
"type": "message",
"id": "chatcmpl-fixed_msg_0",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The answer is 42.",
"annotations": []
}
],
"quality": "",
"size": ""
},
{
"type": "function_call",
"id": "call_abc",
"status": "completed",
"role": "",
"content": null,
"quality": "",
"size": "",
"call_id": "call_abc",
"name": "get_weather",
"arguments": "{\"city\":\"Paris\"}"
}
],
"parallel_tool_calls": false,
"previous_response_id": null,
"reasoning": null,
"store": false,
"temperature": 0,
"tool_choice": null,
"tools": null,
"top_p": 0,
"truncation": null,
"usage": {
"prompt_tokens": 10,
"completion_tokens": 5,
"total_tokens": 15,
"billing_usage": {
"source": "oai_chat",
"semantic": "openai",
"openai_usage": {
"prompt_tokens": 10,
"completion_tokens": 5,
"total_tokens": 15,
"prompt_tokens_details": {
"cached_tokens": 3,
"text_tokens": 0,
"audio_tokens": 0,
"image_tokens": 0
},
"completion_tokens_details": {
"text_tokens": 0,
"audio_tokens": 0,
"image_tokens": 0,
"reasoning_tokens": 2
},
"input_tokens": 0,
"output_tokens": 0,
"input_tokens_details": null,
"claude_cache_creation_5_m_tokens": 0,
"claude_cache_creation_1_h_tokens": 0
}
},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 0,
"audio_tokens": 0,
"image_tokens": 0
},
"completion_tokens_details": {
"text_tokens": 0,
"audio_tokens": 0,
"image_tokens": 0,
"reasoning_tokens": 2
},
"input_tokens": 10,
"output_tokens": 5,
"input_tokens_details": {
"cached_tokens": 3,
"text_tokens": 0,
"audio_tokens": 0,
"image_tokens": 0
},
"claude_cache_creation_5_m_tokens": 0,
"claude_cache_creation_1_h_tokens": 0
},
"user": null,
"metadata": null
}