– UNSUPPORTED

tanstack-ai 1.4.0

truncation.reasoning-only · ollama-openai

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: length
Raw finish: length
Text
Tool calls: []
Usage: { "alternatives": {}, "cached_input": 0, "input": 54, "output": 64, "raw": { "completion_tokens": 64, "prompt_tokens": 54, "prompt_tokens_details": { "cached_tokens": 0 }, "total_tokens": 118 }, "reasoning": null, "total": 118 }
Stream completed: null
Error: null

Wire excerpt

status: 200
content-type: application/json
body (json):
{
  "id": "chatcmpl-741",
  "object": "chat.completion",
  "created": 1791831679,
  "model": "qwen3.5:0.8b",
  "system_fingerprint": "fp_ollama",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "",
        "reasoning": "Here's my thought process for finding the smallest positive whole number with these constraints:\n\n1.  **Understand the Goal:** I need to find a specific integer $x$ satisfying three conditions simultaneously:\n    *   Condition A (Modulo): $x \\equiv 1 \\pmod{2}$ ("
      },
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 54,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens": 64,
    "total_tokens": 118
  }
}

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": 1.1798370000000205,
  "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/truncation.reasoning-only

Provenance	Value
Recorded at	2026-10-12T19:01:16Z
Requested model	qwen3.5:0.8b
Returned model	qwen3.5:0.8b
CI run	https://github.com/kartsan03/wiretruth/actions/runs/38294739276

Reproduce

wiretruth serve ollama-openai/truncation.reasoning-only

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

Version	Grade
1.4.0	– UNSUPPORTED
1.0.0	– UNSUPPORTED
0.71.0	– UNSUPPORTED