– UNSUPPORTED

pydantic-ai 2.61.0

truncation.text-stream · 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: Octopuses are master of camouflage, relying on a distinct ability where their color
Tool calls: []
Usage: { "alternatives": {}, "cached_input": 0, "input": 32, "output": 16, "raw": { "eval_count": 16, "prompt_eval_cached_count": 0, "prompt_eval_count": 32 }, "reasoning": null, "total": 48 }
Stream completed: true
Error: null

Wire excerpt

status: 200
content-type: application/x-ndjson
body (ndjson):
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:19.421674958Z","message":{"role":"assistant","content":"Oct"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:19.533325633Z","message":{"role":"assistant","content":"op"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:19.533383631Z","message":{"role":"assistant","content":"uses"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:19.533501035Z","message":{"role":"assistant","content":" are"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:19.65099542Z","message":{"role":"assistant","content":" master"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:19.759551535Z","message":{"role":"assistant","content":" of"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:19.872036409Z","message":{"role":"assistant","content":" camouflage"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:19.982184117Z","message":{"role":"assistant","content":","},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:19.982211749Z","message":{"role":"assistant","content":" relying"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:20.092858018Z","message":{"role":"assistant","content":" on"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:20.092890519Z","message":{"role":"assistant","content":" a"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:20.202009085Z","message":{"role":"assistant","content":" distinct"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:20.315262694Z","message":{"role":"assistant","content":" ability"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:20.4294355Z","message":{"role":"assistant","content":" where"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:20.510076663Z","message":{"role":"assistant","content":" their"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:20.543159517Z","message":{"role":"assistant","content":" color"},"done":false}
{"model":"qwen3.5:0.8b","created_at":"2026-10-12T19:01:20.543468977Z","message":{"role":"assistant","content":""},"done":true,"done_reason":"length","total_duration":1478058493,"load_duration":3370746,"prompt_eval_count":32,"prompt_eval_cached_count":0,"prompt_eval_duration":346200000,"eval_count":16,"eval_duration":1121510000}

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": 0,
  "completed": null,
  "used": true
}

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": 0.9447140619158745,
  "error": null,
  "finish": {
    "raw": null,
    "source": null,
    "surface": "absent",
    "value": null
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "Agent.run_stream_events",
    "language": "python",
    "name": "pydantic-ai",
    "version": "2.61.0"
  },
  "notes": [],
  "outcome": "unsupported",
  "stream": {
    "chunks_seen": 0,
    "completed": null,
    "used": true
  },
  "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.text-stream

Provenance	Value
Recorded at	2026-10-12T19:01:19Z
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.text-stream

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