– UNSUPPORTED

tanstack-ai 1.4.0

finish.stop-sequence · ollama-openai

Back to results · Scenario

Requirements

IdLevelStatusEvidence

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
```text 1 2 3 4 5 6 7 8 9
Tool calls
[]
Usage
{
  "alternatives": {},
  "cached_input": 0,
  "input": 32,
  "output": 22,
  "raw": {
    "completion_tokens": 22,
    "prompt_tokens": 32,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "total_tokens": 54
  },
  "reasoning": null,
  "total": 54
}
Stream completed
null
Error
null
Wire excerpt
status: 200
content-type: application/json
body (json):
{
  "id": "chatcmpl-551",
  "object": "chat.completion",
  "created": 1791831669,
  "model": "qwen3.5:0.8b",
  "system_fingerprint": "fp_ollama",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "```text\n1\n2\n3\n4\n5\n6\n7\n8\n9"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 32,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens": 22,
    "total_tokens": 54
  }
}

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": 1.2684390000000008,
  "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 ollama-openai/finish.stop-sequence

ProvenanceValue
Recorded at2026-10-12T19:01:06Z
Requested modelqwen3.5:0.8b
Returned modelqwen3.5:0.8b
CI runhttps://github.com/kartsan03/wiretruth/actions/runs/38294739276

Reproduce

wiretruth serve ollama-openai/finish.stop-sequence

Plain-library snippet from the shim manifest.

openaiCompatible({ name: 'ollama', baseURL: WIRETRUTH_BASE_URL_OLLAMA_OPENAI, apiKey, models: [model] })(model); Chat Completions is the documented default for Ollama /v1. https://tanstack.com/ai/latest/docs/adapters/openai-compatible

Upstream

No matching upstream report.

History

VersionGrade
1.4.0– UNSUPPORTED
1.0.0– UNSUPPORTED
0.71.0– UNSUPPORTED