– UNSUPPORTED
pydantic-ai 2.61.0
finish.stop-sequence · 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
- stop
- Raw finish
- stop
- Text
- Here are two ways to do this. You can copy the code block and run it in a text editor or use the provided Python script. ### Method 1: Using Python Code This script counts from 1 to 10, then executes "
- Tool calls
[]
- Usage
{ "alternatives": {}, "cached_input": 0, "input": 32, "output": 53, "raw": { "eval_count": 53, "prompt_eval_cached_count": 0, "prompt_eval_count": 32 }, "reasoning": null, "total": 85 }- 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": "2026-10-12T19:00:54.40490571Z",
"message": {
"role": "assistant",
"content": "Here are two ways to do this. You can copy the code block and run it in a text editor or use the provided Python script.\n\n### Method 1: Using Python Code\nThis script counts from 1 to 10, then executes \""
},
"done": true,
"done_reason": "stop",
"total_duration": 6648731547,
"load_duration": 2649670219,
"prompt_eval_count": 32,
"prompt_eval_cached_count": 0,
"prompt_eval_duration": 355958000,
"eval_count": 53,
"eval_duration": 3640907000
}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": 1.0384824126958847,
"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/finish.stop-sequence
| Provenance | Value |
|---|---|
| Recorded at | 2026-10-12T19:00:47Z |
| 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/finish.stop-sequencePlain-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 |