✓ PASS

vercel-ai 7.0.153

truncation.tool-call-args · openai-chat

Requirements

Id	Level	Status	Evidence
no-complete-partial-call	MUST	SATISFIED	outcome=returned; error signalled
cause-is-truncation	MUST	SATISFIED	finish.value="length" (primary: result.finishReason); 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

returned

Finish

{
  "raw": "length",
  "source": "result.finishReason",
  "surface": "primary",
  "value": "length"
}

Text

Value
Surface: primary

Tool calls

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

Usage

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

Stream

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

Error

Type: AI_InvalidToolInputError
Message: Invalid input for tool create_event: AI_JSONParseError: JSON parsing failed: Text: {"title":"Weekend Pottery Workshop",". Error message: SyntaxError: Unterminated string in JSON at position 37 (line 1 column 38)
Category: validation
Retry after: null
Stack top: ai/dist/index.js:4223

Unsupported reason

null

Full observation JSON

{
  "elapsed_ms": 124.75300999999999,
  "error": {
    "category": "validation",
    "message": "Invalid input for tool create_event: AI_JSONParseError: JSON parsing failed: Text: {\"title\":\"Weekend Pottery Workshop\",\".\nError message: SyntaxError: Unterminated string in JSON at position 37 (line 1 column 38)",
    "retry_after": null,
    "stack_top": "ai/dist/index.js:4223",
    "type": "AI_InvalidToolInputError"
  },
  "finish": {
    "raw": "length",
    "source": "result.finishReason",
    "surface": "primary",
    "value": "length"
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "generateText",
    "language": "javascript",
    "name": "vercel-ai",
    "version": "7.0.153"
  },
  "notes": [],
  "outcome": "returned",
  "stream": {
    "chunks_seen": null,
    "completed": null,
    "used": false
  },
  "structured": {
    "attempted": false,
    "returned_as_success": false,
    "value": null
  },
  "text": {
    "surface": "primary",
    "value": ""
  },
  "tool_calls": [
    {
      "arguments": null,
      "arguments_parsed_ok": false,
      "arguments_raw": "{\"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": "primary",
      "input": "primary",
      "output": "primary",
      "reasoning": "primary",
      "total": "primary"
    },
    "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.

createOpenAI({ baseURL: WIRETRUTH_BASE_URL_OPENAI_CHAT, apiKey }).chat(model)

Upstream

No matching upstream report.

History

Version	Grade
7.0.153	✓ PASS
7.0.146	✓ PASS
7.0.142	✓ PASS