– UNSUPPORTED

tanstack-ai 1.4.0

usage.cached-tokens · openai-chat

Requirements

Id	Level	Status	Evidence

Notes

TanStack AI's chat() always requests a streamed response (stream: false collects the stream), so it never sends the non-streamed request this fixture replays. (https://tanstack.com/ai/latest/docs/api/ai#chat-options)

What the provider sent

Finish: stop
Raw finish: stop
Text: A hot pan helps mushrooms brown instead of releasing water and turning soggy. Heat the pan first, then add the mushrooms in a single layer; if they crowd the pan, cook them in batches.
Tool calls: []
Usage: { "alternatives": {}, "cached_input": 1080, "input": 1083, "output": 43, "raw": { "completion_tokens": 43, "completion_tokens_details": { "accepted_prediction_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 0, "rejected_prediction_tokens": 0 }, "prompt_tokens": 1083, "prompt_tokens_details": { "audio_tokens": 0, "cache_write_tokens": 0, "cached_tokens": 1080 }, "total_tokens": 1126 }, "reasoning": 0, "total": 1126 }
Stream completed: null
Error: null

Wire excerpt

status: 200
content-type: application/json
body (json):
{
  "id": "chatcmpl-Ei7jsQ8otN5546zOgRwUVUiVE7g9K",
  "object": "chat.completion",
  "created": 1794184888,
  "model": "gpt-6-luna",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "A hot pan helps mushrooms brown instead of releasing water and turning soggy. Heat the pan first, then add the mushrooms in a single layer; if they crowd the pan, cook them in batches.",
        "refusal": null,
        "annotations": []
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 1083,
    "completion_tokens": 43,
    "total_tokens": 1126,
    "prompt_tokens_details": {
      "cached_tokens": 1080,
      "cache_write_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0,
      "audio_tokens": 0,
      "accepted_prediction_tokens": 0,
      "rejected_prediction_tokens": 0
    }
  },
  "service_tier": "default",
  "system_fingerprint": null
}

What the library reported

Outcome

unsupported

Finish

{
  "raw": null,
  "source": null,
  "surface": "absent",
  "value": null
}

Text

Value: null
Surface: absent

Tool calls

[]

Usage

{
  "cached_input": null,
  "input": null,
  "output": null,
  "reasoning": null,
  "surface": {
    "cached_input": "absent",
    "input": "absent",
    "output": "absent",
    "reasoning": "absent",
    "total": "absent"
  },
  "total": null
}

Stream

{
  "chunks_seen": null,
  "completed": null,
  "used": false
}

Error

null

Unsupported reason

TanStack AI's chat() always requests a streamed response (stream: false collects the stream), so it never sends the non-streamed request this fixture replays. https://tanstack.com/ai/latest/docs/api/ai#chat-options

Full observation JSON

{
  "elapsed_ms": 3.055505000000039,
  "error": null,
  "finish": {
    "raw": null,
    "source": null,
    "surface": "absent",
    "value": null
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "chat",
    "language": "javascript",
    "name": "tanstack-ai",
    "version": "1.4.0"
  },
  "notes": [],
  "outcome": "unsupported",
  "stream": {
    "chunks_seen": null,
    "completed": null,
    "used": false
  },
  "structured": {
    "attempted": false,
    "returned_as_success": false,
    "value": null
  },
  "text": {
    "surface": "absent",
    "value": null
  },
  "tool_calls": [],
  "unsupported_reason": "TanStack AI's chat() always requests a streamed response (stream: false collects the stream), so it never sends the non-streamed request this fixture replays. https://tanstack.com/ai/latest/docs/api/ai#chat-options",
  "usage": {
    "cached_input": null,
    "input": null,
    "output": null,
    "reasoning": null,
    "surface": {
      "cached_input": "absent",
      "input": "absent",
      "output": "absent",
      "reasoning": "absent",
      "total": "absent"
    },
    "total": null
  }
}

Fixture

recorded openai-chat/usage.cached-tokens

Provenance	Value
Recorded at	2026-11-09T00:41:27Z
Requested model	gpt-6-luna
Returned model	gpt-6-luna
CI run	https://github.com/kartsan03/wiretruth/actions/runs/42541525617

Reproduce

wiretruth serve openai-chat/usage.cached-tokens

Plain-library snippet from the shim manifest.

createOpenaiChatCompletions(model, apiKey, { baseURL: WIRETRUTH_BASE_URL_OPENAI_CHAT }); POST /v1/chat/completions. https://tanstack.com/ai/latest/docs/adapters/openai#chat-completions-api

Upstream

No matching upstream report.

History

Version	Grade
1.4.0	– UNSUPPORTED
1.0.0	– UNSUPPORTED
0.71.0	not covered