– UNSUPPORTED

tanstack-ai 1.4.0

truncation.reasoning-only · ollama

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
length
Raw finish
length
Text
Tool calls
[]
Usage
{
  "alternatives": {},
  "cached_input": 0,
  "input": 54,
  "output": 64,
  "raw": {
    "eval_count": 64,
    "prompt_eval_cached_count": 0,
    "prompt_eval_count": 54
  },
  "reasoning": null,
  "total": 118
}
Stream completed
null
Error
null
Wire excerpt
status: 200
content-type: application/json; charset=utf-8
body (json):
{
  "model": "qwen3.5:0.8b",
  "created_at": "2026-10-12T19:01:17.433604074Z",
  "message": {
    "role": "assistant",
    "content": "",
    "thinking": "Let $n$ be the smallest positive whole number satisfying the given conditions.\nThe conditions are:\n1. Remainder when dividing by 2 is 1. So $n \\equiv 1 \\pmod 2$. This implies $n$ is odd.\n2. Remainder when dividing by"
  },
  "done": true,
  "done_reason": "length",
  "total_duration": 3728486452,
  "load_duration": 2447425,
  "prompt_eval_count": 54,
  "prompt_eval_cached_count": 0,
  "prompt_eval_duration": 554808000,
  "eval_count": 64,
  "eval_duration": 3162410000
}

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": 1.1738560000000007,
  "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/truncation.reasoning-only

ProvenanceValue
Recorded at2026-10-12T19:01:13Z
Requested modelqwen3.5:0.8b
Returned modelqwen3.5:0.8b
CI runhttps://github.com/kartsan03/wiretruth/actions/runs/38294709109

Reproduce

wiretruth serve ollama/truncation.reasoning-only

Plain-library snippet from the shim manifest.

createOllamaChat(model, { host: WIRETRUTH_BASE_URL_OLLAMA }); POST /api/chat.

Upstream

No matching upstream report.

History

VersionGrade
1.4.0– UNSUPPORTED
1.0.0– UNSUPPORTED
0.71.0– UNSUPPORTED