– UNSUPPORTED

tanstack-ai 1.4.0

tools.parallel-calls · ollama

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: tool_calls
Raw finish: stop
Text
Tool calls: [ { "arguments": { "city": "São Paulo" }, "arguments_parsed_ok": true, "arguments_raw": "{\"city\":\"São Paulo\"}", "id": "call_9epwsqu6", "name": "get_weather" }, { "arguments": { "city": "Zürich" }, "arguments_parsed_ok": true, "arguments_raw": "{\"city\":\"Zürich\"}", "id": "call_bvzy1ra9", "name": "get_weather" } ]
Usage: { "alternatives": {}, "cached_input": 288, "input": 292, "output": 55, "raw": { "eval_count": 55, "prompt_eval_cached_count": 288, "prompt_eval_count": 292 }, "reasoning": null, "total": 347 }
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": "2026-10-12T19:01:13.696397757Z",
  "message": {
    "role": "assistant",
    "content": "",
    "tool_calls": [
      {
        "id": "call_9epwsqu6",
        "function": {
          "index": 0,
          "name": "get_weather",
          "arguments": {
            "city": "São Paulo"
          }
        }
      },
      {
        "id": "call_bvzy1ra9",
        "function": {
          "index": 1,
          "name": "get_weather",
          "arguments": {
            "city": "Zürich"
          }
        }
      }
    ]
  },
  "done": true,
  "done_reason": "stop",
  "total_duration": 2299982620,
  "load_duration": 3338545,
  "prompt_eval_count": 292,
  "prompt_eval_cached_count": 288,
  "prompt_eval_duration": 71919000,
  "eval_count": 55,
  "eval_duration": 2221115000
}

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": 0.9375350000000253,
  "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/tools.parallel-calls

Provenance	Value
Recorded at	2026-10-12T19:01:11Z
Requested model	qwen3.5:0.8b
Returned model	qwen3.5:0.8b
CI run	https://github.com/kartsan03/wiretruth/actions/runs/38294709109

Reproduce

wiretruth serve ollama/tools.parallel-calls

Plain-library snippet from the shim manifest.

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

Upstream

No matching upstream report.

History

Version	Grade
1.4.0	– UNSUPPORTED
1.0.0	– UNSUPPORTED
0.71.0	– UNSUPPORTED