✓ PASS

pydantic-ai 2.61.0

truncation.reasoning-only · openai-chat

Requirements

Id	Level	Status	Evidence
cause-is-truncation	MUST	SATISFIED	finish.value="length" (raw: ModelResponse.finish_reason); truth.finish="length"; error.category="truncation"; structured.returned_as_success=false
text-reported	MUST	SATISFIED	text.value=null (absent); truth.text=""
usage-reported	SHOULD	NOT_OBSERVABLE	usage.output=64 (raw); truth.usage.output=64

What the provider sent

Finish: length
Raw finish: length
Text
Tool calls: []
Usage: { "alternatives": {}, "cached_input": 0, "input": 49, "output": 64, "raw": { "completion_tokens": 64, "completion_tokens_details": { "accepted_prediction_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 64, "rejected_prediction_tokens": 0 }, "prompt_tokens": 49, "prompt_tokens_details": { "audio_tokens": 0, "cache_write_tokens": 0, "cached_tokens": 0 }, "total_tokens": 113 }, "reasoning": 64, "total": 113 }
Stream completed: null
Error: null

Wire excerpt

status: 200
content-type: application/json
body (json):
{
  "id": "chatcmpl-EXmWY18aHzANfC6JTSbCvBtmeGdRS",
  "object": "chat.completion",
  "created": 1791720058,
  "model": "gpt-6-luna",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "",
        "refusal": null,
        "annotations": []
      },
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 49,
    "completion_tokens": 64,
    "total_tokens": 113,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 64,
      "audio_tokens": 0,
      "accepted_prediction_tokens": 0,
      "rejected_prediction_tokens": 0
    }
  },
  "service_tier": "default",
  "system_fingerprint": null
}

What the library reported

Outcome

raised

Finish

{
  "raw": "length",
  "source": "ModelResponse.finish_reason",
  "surface": "raw",
  "value": "length"
}

Text

Value: null
Surface: absent

Tool calls

[]

Usage

{
  "cached_input": 0,
  "input": 49,
  "output": 64,
  "reasoning": 64,
  "surface": {
    "cached_input": "raw",
    "input": "raw",
    "output": "raw",
    "reasoning": "raw",
    "total": "raw"
  },
  "total": 113
}

Stream

{
  "chunks_seen": null,
  "completed": null,
  "used": false
}

Error

Type: pydantic_ai.exceptions.UnexpectedModelBehavior
Message: Model token limit (64) exceeded before any response was generated. Increase the `max_tokens` model setting, or simplify the prompt to result in a shorter response that will fit within the limit.
Category: truncation
Retry after: null
Stack top: pydantic_ai/_agent_graph.py:2495

Unsupported reason

null

Full observation JSON

{
  "elapsed_ms": 234.43376179784536,
  "error": {
    "category": "truncation",
    "message": "Model token limit (64) exceeded before any response was generated. Increase the `max_tokens` model setting, or simplify the prompt to result in a shorter response that will fit within the limit.",
    "retry_after": null,
    "stack_top": "pydantic_ai/_agent_graph.py:2495",
    "type": "pydantic_ai.exceptions.UnexpectedModelBehavior"
  },
  "finish": {
    "raw": "length",
    "source": "ModelResponse.finish_reason",
    "surface": "raw",
    "value": "length"
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "Agent.run",
    "language": "python",
    "name": "pydantic-ai",
    "version": "2.61.0"
  },
  "notes": [],
  "outcome": "raised",
  "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": null,
  "usage": {
    "cached_input": 0,
    "input": 49,
    "output": 64,
    "reasoning": 64,
    "surface": {
      "cached_input": "raw",
      "input": "raw",
      "output": "raw",
      "reasoning": "raw",
      "total": "raw"
    },
    "total": 113
  }
}

Fixture

recorded openai-chat/truncation.reasoning-only

Provenance	Value
Recorded at	2026-10-11T12:00:57Z
Requested model	gpt-6-luna
Returned model	gpt-6-luna
CI run	https://github.com/kartsan03/wiretruth/actions/runs/38137650119

Reproduce

wiretruth serve openai-chat/truncation.reasoning-only

Plain-library snippet from the shim manifest.

OpenAIChatModel(model, provider=OpenAIProvider(base_url=WIRETRUTH_BASE_URL_OPENAI_CHAT, api_key=WIRETRUTH_API_KEY))

Upstream

No matching upstream report.

History

Version	Grade
2.61.0	✓ PASS
2.56.0	✓ PASS