~ LOSSY

pydantic-ai 2.61.0

truncation.tool-call-args · openai-chat

Requirements

Id	Level	Status	Evidence
no-complete-partial-call	MUST	SATISFIED	outcome=raised; error signalled
cause-is-truncation	MUST	NOT_OBSERVABLE	finish.value="length" (raw: ModelResponse.finish_reason); truth.finish="length"; error.category="validation"; structured.returned_as_success=false

What the provider sent

Finish: length
Raw finish: length
Text: null
Tool calls: [ { "arguments": null, "arguments_parsed_ok": false, "arguments_raw": "{\"title\":\"Weekend Pottery Workshop\",\"", "id": "call_W6i0YDA3qww31EI14Xkd4cmB", "name": "create_event" } ]
Usage: { "alternatives": {}, "cached_input": 0, "input": 182, "output": 20, "raw": { "completion_tokens": 20, "completion_tokens_details": { "accepted_prediction_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 0, "rejected_prediction_tokens": 0 }, "prompt_tokens": 182, "prompt_tokens_details": { "audio_tokens": 0, "cache_write_tokens": 0, "cached_tokens": 0 }, "total_tokens": 202 }, "reasoning": 0, "total": 202 }
Stream completed: null
Error: null

Wire excerpt

status: 200
content-type: application/json
body (json):
{
  "id": "chatcmpl-EXmWepZSbcMU86TnlRq4kH4xvQ2nK",
  "object": "chat.completion",
  "created": 1791720064,
  "model": "gpt-6-luna",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": [
          {
            "id": "call_W6i0YDA3qww31EI14Xkd4cmB",
            "type": "function",
            "function": {
              "name": "create_event",
              "arguments": "{\"title\":\"Weekend Pottery Workshop\",\""
            }
          }
        ],
        "refusal": null,
        "annotations": []
      },
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 182,
    "completion_tokens": 20,
    "total_tokens": 202,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0,
      "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

[
  {
    "arguments": {
      "INVALID_JSON": "{\"title\":\"Weekend Pottery Workshop\",\""
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"INVALID_JSON\":\"{\\\"title\\\":\\\"Weekend Pottery Workshop\\\",\\\"\"}",
    "id": "call_W6i0YDA3qww31EI14Xkd4cmB",
    "name": "create_event"
  }
]

Usage

{
  "cached_input": 0,
  "input": 182,
  "output": 20,
  "reasoning": 0,
  "surface": {
    "cached_input": "raw",
    "input": "raw",
    "output": "raw",
    "reasoning": "raw",
    "total": "raw"
  },
  "total": 202
}

Stream

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

Error

Type: pydantic_ai.exceptions.UnexpectedModelBehavior
Message: Tool 'create_event' exceeded max retries count of 0. Consider raising the retry limit, or see the docs on tool retries: https://pydantic.dev/docs/ai/tools-toolsets/tools-advanced/#tool-retries
Category: validation
Retry after: null
Stack top: pydantic_ai/tool_manager.py:523

Unsupported reason

null

Full observation JSON

{
  "elapsed_ms": 238.96948993206024,
  "error": {
    "category": "validation",
    "message": "Tool 'create_event' exceeded max retries count of 0. Consider raising the retry limit, or see the docs on tool retries: https://pydantic.dev/docs/ai/tools-toolsets/tools-advanced/#tool-retries",
    "retry_after": null,
    "stack_top": "pydantic_ai/tool_manager.py:523",
    "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": [
    {
      "arguments": {
        "INVALID_JSON": "{\"title\":\"Weekend Pottery Workshop\",\""
      },
      "arguments_parsed_ok": true,
      "arguments_raw": "{\"INVALID_JSON\":\"{\\\"title\\\":\\\"Weekend Pottery Workshop\\\",\\\"\"}",
      "id": "call_W6i0YDA3qww31EI14Xkd4cmB",
      "name": "create_event"
    }
  ],
  "unsupported_reason": null,
  "usage": {
    "cached_input": 0,
    "input": 182,
    "output": 20,
    "reasoning": 0,
    "surface": {
      "cached_input": "raw",
      "input": "raw",
      "output": "raw",
      "reasoning": "raw",
      "total": "raw"
    },
    "total": 202
  }
}

Fixture

recorded openai-chat/truncation.tool-call-args

Provenance	Value
Recorded at	2026-10-11T12:01:04Z
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.tool-call-args

Plain-library snippet from the shim manifest.

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

Upstream

reported Issue

Fixed in: not specified

Reported in a comment on the token-limit issue: https://github.com/pydantic/pydantic-ai/issues/12399#issuecomment-6780480981. Tool-call arguments cut off at the limit fail validation and end in the per-tool retry limit (UnexpectedModelBehavior: Tool 'create_event' exceeded max retries count of 0), not in IncompleteToolCall; reproduced on 2.61.0 and 2.66.0 with an ExternalToolset.

History

Version	Grade
2.61.0	~ LOSSY
2.56.0	~ LOSSY