✓ PASS

litellm 1.105.5

truncation.structured-output · openai-chat

Requirements

Id	Level	Status	Evidence
no-partial-success	MUST	SATISFIED	structured.attempted=true; structured.returned_as_success=false
cause-is-truncation	MUST	SATISFIED	finish.value="length" (primary: choices[0].finish_reason); truth.finish="length"; error.category=null; structured.returned_as_success=false
text-reported	SHOULD	SATISFIED	text.value="{\"islands\":[{\"name\":\"Κρήτη\",\"sea\":\"Κρητικό Πέ" (primary); truth.text="{\"islands\":[{\"name\":\"Κρήτη\",\"sea\":\"Κρητικό Πέ"
usage-reported	SHOULD	SATISFIED	usage.input=72 (primary); truth.usage.input=72; usage.output=24 (primary); truth.usage.output=24

What the provider sent

Finish: length
Raw finish: length
Text: {"islands":[{"name":"Κρήτη","sea":"Κρητικό Πέ
Tool calls: []
Usage: { "alternatives": {}, "cached_input": 0, "input": 72, "output": 24, "raw": { "completion_tokens": 24, "completion_tokens_details": { "accepted_prediction_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 0, "rejected_prediction_tokens": 0 }, "prompt_tokens": 72, "prompt_tokens_details": { "audio_tokens": 0, "cache_write_tokens": 0, "cached_tokens": 0 }, "total_tokens": 96 }, "reasoning": 0, "total": 96 }
Stream completed: null
Error: null

Wire excerpt

status: 200
content-type: application/json
body (json):
{
  "id": "chatcmpl-EimSbrSUy62MoDs7OPLFoo7hYvPlx",
  "object": "chat.completion",
  "created": 1794341421,
  "model": "gpt-6-luna",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "{\"islands\":[{\"name\":\"Κρήτη\",\"sea\":\"Κρητικό Πέ",
        "refusal": null,
        "annotations": []
      },
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 72,
    "completion_tokens": 24,
    "total_tokens": 96,
    "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": "choices[0].finish_reason",
  "surface": "primary",
  "value": "length"
}

Text

Value: {"islands":[{"name":"Κρήτη","sea":"Κρητικό Πέ
Surface: primary

Tool calls

[]

Usage

{
  "cached_input": 0,
  "input": 72,
  "output": 24,
  "reasoning": 0,
  "surface": {
    "cached_input": "primary",
    "input": "primary",
    "output": "primary",
    "reasoning": "primary",
    "total": "primary"
  },
  "total": 96
}

Stream

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

Error

null

Unsupported reason

null

Full observation JSON

{
  "elapsed_ms": 542.4254555255175,
  "error": null,
  "finish": {
    "raw": "length",
    "source": "choices[0].finish_reason",
    "surface": "primary",
    "value": "length"
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "litellm.completion",
    "language": "python",
    "name": "litellm",
    "version": "1.105.5"
  },
  "notes": [],
  "outcome": "returned",
  "stream": {
    "chunks_seen": null,
    "completed": null,
    "used": false
  },
  "structured": {
    "attempted": true,
    "returned_as_success": false,
    "value": null
  },
  "text": {
    "surface": "primary",
    "value": "{\"islands\":[{\"name\":\"Κρήτη\",\"sea\":\"Κρητικό Πέ"
  },
  "tool_calls": [],
  "unsupported_reason": null,
  "usage": {
    "cached_input": 0,
    "input": 72,
    "output": 24,
    "reasoning": 0,
    "surface": {
      "cached_input": "primary",
      "input": "primary",
      "output": "primary",
      "reasoning": "primary",
      "total": "primary"
    },
    "total": 96
  }
}

Fixture

recorded openai-chat/truncation.structured-output

Provenance	Value
Recorded at	2026-11-10T20:10:19Z
Requested model	gpt-6-luna
Returned model	gpt-6-luna
CI run	https://github.com/kartsan03/wiretruth/actions/runs/42892575092

Reproduce

wiretruth serve openai-chat/truncation.structured-output

Plain-library snippet from the shim manifest.

litellm.completion(model='openai/' + model, api_base=WIRETRUTH_BASE_URL_OPENAI_CHAT, api_key=WIRETRUTH_API_KEY)

Upstream

No matching upstream report.

History

Version	Grade
1.105.5	✓ PASS
1.105.1	✓ PASS