~ LOSSY

pydantic-ai 2.61.0

finish.unknown-value · openai-responses

Back to results · Scenario

Requirements

IdLevelStatusEvidence
response-returnedMUSTSATISFIEDoutcome=returned; error.category=null; truth.error=null
finish-is-otherMUSTNOT_OBSERVABLEfinish.value=null (raw: provider_details.finish_reason); truth.finish="other"; required finish="other"
text-reportedMUSTSATISFIEDtext.value="Octopuses are masters of disguise, able to change colour in" (primary); truth.text="Octopuses are masters of disguise, able to change colour in"
raw-finish-reportedSHOULDSATISFIEDfinish.raw="wiretruth_unknown_reason"; truth.raw_finish="wiretruth_unknown_reason"

What the provider sent

Finish
other
Raw finish
wiretruth_unknown_reason
Text
Octopuses are masters of disguise, able to change colour in
Tool calls
[]
Usage
{
  "alternatives": {},
  "cached_input": 0,
  "input": 24,
  "output": 16,
  "raw": {
    "input_tokens": 24,
    "input_tokens_details": {
      "cache_write_tokens": 0,
      "cached_tokens": 0
    },
    "output_tokens": 16,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 40
  },
  "reasoning": 0,
  "total": 40
}
Stream completed
null
Error
null
Wire excerpt
status: 200
content-type: application/json
body (json):
{
  "id": "resp_094389768e05d226006acbfc03e52887d1b6e75d17520a0a64",
  "object": "response",
  "created_at": 1791753219,
  "status": "incomplete",
  "access_programs": null,
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": null,
  "error": null,
  "frequency_penalty": 0.0,
  "incomplete_details": {
    "reason": "wiretruth_unknown_reason"
  },
  "instructions": null,
  "max_output_tokens": 16,
  "max_tool_calls": null,
  "model": "gpt-6-luna",
  "moderation": null,
  "output": [
    {
      "id": "msg_094389768e05d226006acbfc04c2b487d187d11a4b4425c595",
      "type": "message",
      "status": "incomplete",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "logprobs": [],
          "text": "Octopuses are masters of disguise, able to change colour in"
        }
      ],
      "phase": "final_answer",
      "role": "assistant"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0.0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": "24h",
  "reasoning": {
    "context": "all_turns",
    "effort": "none",
    "mode": "standard",
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "store": true,
  "temperature": 1.0,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tool_usage": {
    "image_gen": {
      "input_tokens": 0,
      "input_tokens_details": {
        "image_tokens": 0,
        "text_tokens": 0
      },
      "output_tokens": 0,
      "output_tokens_details": {
        "image_tokens": 0,
        "text_tokens": 0
      },
      "total_tokens": 0
    },
    "web_search": {
      "num_requests": 0
    }
  },
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.98,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 24,
    "input_tokens_details": {
      "cache_write_tokens": 0,
      "cached_tokens": 0
    },
    "output_tokens": 16,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 40
  },
  "user": null,
  "metadata": {}
}

What the library reported

Outcome
returned
Finish
{
  "raw": "wiretruth_unknown_reason",
  "source": "provider_details.finish_reason",
  "surface": "raw",
  "value": null
}
Text
Value
Octopuses are masters of disguise, able to change colour in
Surface
primary
Tool calls
[]
Usage
{
  "cached_input": 0,
  "input": 24,
  "output": 16,
  "reasoning": 0,
  "surface": {
    "cached_input": "primary",
    "input": "primary",
    "output": "primary",
    "reasoning": "primary",
    "total": "primary"
  },
  "total": 40
}
Stream
{
  "chunks_seen": null,
  "completed": null,
  "used": false
}
Error
null
Unsupported reason
null
Full observation JSON
{
  "elapsed_ms": 347.55531419068575,
  "error": null,
  "finish": {
    "raw": "wiretruth_unknown_reason",
    "source": "provider_details.finish_reason",
    "surface": "raw",
    "value": null
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "Agent.run",
    "language": "python",
    "name": "pydantic-ai",
    "version": "2.61.0"
  },
  "notes": [],
  "outcome": "returned",
  "stream": {
    "chunks_seen": null,
    "completed": null,
    "used": false
  },
  "structured": {
    "attempted": false,
    "returned_as_success": false,
    "value": null
  },
  "text": {
    "surface": "primary",
    "value": "Octopuses are masters of disguise, able to change colour in"
  },
  "tool_calls": [],
  "unsupported_reason": null,
  "usage": {
    "cached_input": 0,
    "input": 24,
    "output": 16,
    "reasoning": 0,
    "surface": {
      "cached_input": "primary",
      "input": "primary",
      "output": "primary",
      "reasoning": "primary",
      "total": "primary"
    },
    "total": 40
  }
}

Fixture

derived openai-responses/finish.unknown-value

ProvenanceValue
Transformreplace_finish_value
Source fixtureopenai-responses/truncation.text
RationaleThe provider sends a finish value that a library may not recognize.
Evidencehttps://github.com/BerriAI/litellm/issues/21347

Reproduce

wiretruth serve openai-responses/finish.unknown-value

Plain-library snippet from the shim manifest.

OpenAIResponsesModel(model, provider=OpenAIProvider(base_url=WIRETRUTH_BASE_URL_OPENAI_RESPONSES, api_key=WIRETRUTH_API_KEY))

Upstream

No matching upstream report.

History

VersionGrade
2.61.0~ LOSSY
2.56.0~ LOSSY