– UNSUPPORTED

pydantic-ai 2.61.0

truncation.structured-output · ollama

Requirements

Id	Level	Status	Evidence

Notes

pydantic-ai 2.61.0 implements OllamaModel via OpenAI-compatible Chat Completions only; there is no native /api/chat client. (https://ai.pydantic.dev/models/ollama/)

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

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

pydantic-ai 2.61.0 implements OllamaModel via OpenAI-compatible Chat Completions only; there is no native /api/chat client. https://ai.pydantic.dev/models/ollama/

Full observation JSON

{
  "elapsed_ms": 1.3075396418571472,
  "error": null,
  "finish": {
    "raw": null,
    "source": null,
    "surface": "absent",
    "value": null
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "Agent.run",
    "language": "python",
    "name": "pydantic-ai",
    "version": "2.61.0"
  },
  "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": "pydantic-ai 2.61.0 implements OllamaModel via OpenAI-compatible Chat Completions only; there is no native /api/chat client. https://ai.pydantic.dev/models/ollama/",
  "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.

Unsupported: OllamaModel uses only the OpenAI-compatible /v1 API, not native /api/chat.

Upstream

No matching upstream report.

History

Version	Grade
2.61.0	– UNSUPPORTED
2.56.0	– UNSUPPORTED