✓ PASS

tanstack-ai 1.4.0

truncation.structured-output · ollama

Requirements

Id	Level	Status	Evidence
no-partial-success	MUST	SATISFIED	structured.attempted=true; structured.returned_as_success=false
cause-is-truncation	MUST	SATISFIED	finish.value=null (absent); truth.finish="length"; error.category="truncation"; structured.returned_as_success=false
text-reported	SHOULD	NOT_OBSERVABLE	text.value=null (absent); truth.text="{\n \"islands\": [\n {\n \"name\": \"Κορύδαιο\","
usage-reported	SHOULD	NOT_OBSERVABLE	usage.input=null (absent); truth.usage.input=30; usage.output=null (absent); truth.usage.output=24

What the provider sent

Finish: length
Raw finish: length
Text: { "islands": [ { "name": "Κορύδαιο",
Tool calls: []
Usage: { "alternatives": {}, "cached_input": 0, "input": 30, "output": 24, "raw": { "eval_count": 24, "prompt_eval_cached_count": 0, "prompt_eval_count": 30 }, "reasoning": null, "total": 54 }
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": "2026-10-12T19:01:19.05881681Z",
  "message": {
    "role": "assistant",
    "content": "{\n  \"islands\": [\n    {\n      \"name\": \"Κορύδαιο\","
  },
  "done": true,
  "done_reason": "length",
  "total_duration": 1619139724,
  "load_duration": 2649959,
  "prompt_eval_count": 30,
  "prompt_eval_cached_count": 0,
  "prompt_eval_duration": 351993000,
  "eval_count": 24,
  "eval_duration": 1256211000
}

What the library reported

Outcome

raised

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

Type: Error
Message: Structured output generation failed: ollama.structuredOutput: the response was cut off because the maximum token limit was reached (done_reason=length); raise modelOptions.options.num_predict
Category: truncation
Retry after: null
Stack top: @tanstack/ai/dist/esm/activities/chat/index.js:3694

Unsupported reason

null

Full observation JSON

{
  "elapsed_ms": 142.27672500000006,
  "error": {
    "category": "truncation",
    "message": "Structured output generation failed: ollama.structuredOutput: the response was cut off because the maximum token limit was reached (done_reason=length); raise modelOptions.options.num_predict",
    "retry_after": null,
    "stack_top": "@tanstack/ai/dist/esm/activities/chat/index.js:3694",
    "type": "Error"
  },
  "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": "raised",
  "stream": {
    "chunks_seen": null,
    "completed": null,
    "used": false
  },
  "structured": {
    "attempted": true,
    "returned_as_success": false,
    "value": null
  },
  "text": {
    "surface": "absent",
    "value": null
  },
  "tool_calls": [],
  "unsupported_reason": null,
  "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.structured-output

Provenance	Value
Recorded at	2026-10-12T19:01:17Z
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/truncation.structured-output

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	✓ PASS
1.0.0	✓ PASS
0.71.0	✓ PASS