✗ WRONG

litellm 1.105.5

tools.parallel-calls-stream · gemini

Back to results · Scenario

Requirements

IdLevelStatusEvidence
calls-reportedMUSTCONTRADICTEDtool_calls[0] id="call_89893__thought__EmAKXgFpFH0TxZ2NGVDnAk7zdroOwEtjCQZ5QStCxNyB3D0EMEvzcedHokaxnZ1ccgbmfFfhWDeIyd0qiEnNn4U+roU6nrrrPT3fZoLqOOMqJVT9oPtsSaWF14m+Eb5xptM=", name="get_weather", args={"city": "São Paulo"}, parsed=true; truth id="call_89893", name="get_weather", args={"city": "São Paulo"}, parsed=true; tool_calls[1] id="call_89896", name="get_weather", args={"city": "Zürich"}, parsed=true; truth id="call_89896", name="get_weather", args={"city": "Zürich"}, parsed=true

What the provider sent

Finish
tool_calls
Raw finish
STOP
Text
Tool calls
[
  {
    "arguments": {
      "city": "São Paulo"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\":\"São Paulo\"}",
    "id": "call_89893",
    "name": "get_weather"
  },
  {
    "arguments": {
      "city": "Zürich"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\":\"Zürich\"}",
    "id": "call_89896",
    "name": "get_weather"
  }
]
Usage
{
  "alternatives": {},
  "cached_input": null,
  "input": 69,
  "output": 34,
  "raw": {
    "candidatesTokenCount": 34,
    "promptTokenCount": 69,
    "promptTokensDetails": [
      {
        "modality": "TEXT",
        "tokenCount": 69
      }
    ],
    "serviceTier": "standard",
    "totalTokenCount": 103
  },
  "reasoning": null,
  "total": 103
}
Stream completed
true
Error
null
Wire excerpt
status: 200
content-type: text/event-stream
body (sse):
data: {"candidates": [{"content": {"parts": [{"functionCall": {"name": "get_weather","args": {"city": "São Paulo"},"id": "call_89893"},"thoughtSignature": "EmAKXgFpFH0TxZ2NGVDnAk7zdroOwEtjCQZ5QStCxNyB3D0EMEvzcedHokaxnZ1ccgbmfFfhWDeIyd0qiEnNn4U+roU6nrrrPT3fZoLqOOMqJVT9oPtsSaWF14m+Eb5xptM="}],"role": "model"},"index": 0}],"usageMetadata": {"promptTokenCount": 69,"candidatesTokenCount": 17,"totalTokenCount": 86,"promptTokensDetails": [{"modality": "TEXT","tokenCount": 69}],"serviceTier": "standard"},"modelVersion": "gemini-3.5-flash-lite","responseId": "hwTOat8Lv_D7xg-8iNfgCw"}


data: {"candidates": [{"content": {"parts": [{"functionCall": {"name": "get_weather","args": {"city": "Zürich"},"id": "call_89896"}}],"role": "model"},"index": 0}],"usageMetadata": {"promptTokenCount": 69,"candidatesTokenCount": 34,"totalTokenCount": 103,"promptTokensDetails": [{"modality": "TEXT","tokenCount": 69}],"serviceTier": "standard"},"modelVersion": "gemini-3.5-flash-lite","responseId": "hwTOat8Lv_D7xg-8iNfgCw"}


data: {"candidates": [{"content": {"parts": [{"text": ""}],"role": "model"},"finishReason": "STOP","index": 0}],"usageMetadata": {"promptTokenCount": 69,"candidatesTokenCount": 34,"totalTokenCount": 103,"promptTokensDetails": [{"modality": "TEXT","tokenCount": 69}],"serviceTier": "standard"},"modelVersion": "gemini-3.5-flash-lite","responseId": "hwTOat8Lv_D7xg-8iNfgCw"}

What the library reported

Outcome
returned
Finish
{
  "raw": "tool_calls",
  "source": "choices[0].finish_reason",
  "surface": "primary",
  "value": "tool_calls"
}
Text
Value
null
Surface
absent
Tool calls
[
  {
    "arguments": {
      "city": "São Paulo"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\": \"São Paulo\"}",
    "id": "call_89893__thought__EmAKXgFpFH0TxZ2NGVDnAk7zdroOwEtjCQZ5QStCxNyB3D0EMEvzcedHokaxnZ1ccgbmfFfhWDeIyd0qiEnNn4U+roU6nrrrPT3fZoLqOOMqJVT9oPtsSaWF14m+Eb5xptM=",
    "name": "get_weather"
  },
  {
    "arguments": {
      "city": "Zürich"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\": \"Zürich\"}",
    "id": "call_89896",
    "name": "get_weather"
  }
]
Usage
{
  "cached_input": null,
  "input": null,
  "output": null,
  "reasoning": null,
  "surface": {
    "cached_input": "absent",
    "input": "absent",
    "output": "absent",
    "reasoning": "absent",
    "total": "absent"
  },
  "total": null
}
Stream
{
  "chunks_seen": 3,
  "completed": null,
  "used": true
}
Error
null
Unsupported reason
null
Full observation JSON
{
  "elapsed_ms": 338.2083736360073,
  "error": null,
  "finish": {
    "raw": "tool_calls",
    "source": "choices[0].finish_reason",
    "surface": "primary",
    "value": "tool_calls"
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "litellm.completion",
    "language": "python",
    "name": "litellm",
    "version": "1.105.5"
  },
  "notes": [],
  "outcome": "returned",
  "stream": {
    "chunks_seen": 3,
    "completed": null,
    "used": true
  },
  "structured": {
    "attempted": false,
    "returned_as_success": false,
    "value": null
  },
  "text": {
    "surface": "absent",
    "value": null
  },
  "tool_calls": [
    {
      "arguments": {
        "city": "São Paulo"
      },
      "arguments_parsed_ok": true,
      "arguments_raw": "{\"city\": \"São Paulo\"}",
      "id": "call_89893__thought__EmAKXgFpFH0TxZ2NGVDnAk7zdroOwEtjCQZ5QStCxNyB3D0EMEvzcedHokaxnZ1ccgbmfFfhWDeIyd0qiEnNn4U+roU6nrrrPT3fZoLqOOMqJVT9oPtsSaWF14m+Eb5xptM=",
      "name": "get_weather"
    },
    {
      "arguments": {
        "city": "Zürich"
      },
      "arguments_parsed_ok": true,
      "arguments_raw": "{\"city\": \"Zürich\"}",
      "id": "call_89896",
      "name": "get_weather"
    }
  ],
  "unsupported_reason": null,
  "usage": {
    "cached_input": null,
    "input": null,
    "output": null,
    "reasoning": null,
    "surface": {
      "cached_input": "absent",
      "input": "absent",
      "output": "absent",
      "reasoning": "absent",
      "total": "absent"
    },
    "total": null
  }
}

Fixture

recorded gemini/tools.parallel-calls-stream

ProvenanceValue
Recorded at2026-10-13T10:14:30Z
Requested modelgemini-3.5-flash-lite
Returned modelgemini-3.5-flash-lite
CI runhttps://github.com/kartsan03/wiretruth/actions/runs/38381941285

Reproduce

wiretruth serve gemini/tools.parallel-calls-stream

Plain-library snippet from the shim manifest.

litellm.completion(model='gemini/' + model, api_base=WIRETRUTH_BASE_URL_GEMINI + '/v1beta', api_key=WIRETRUTH_API_KEY); the runner supplies the host root and LiteLLM appends /models/...

Upstream

reported Issue

Fixed in: not specified

Existing upstream issue, not opened by wiretruth. LiteLLM deliberately appends __thought__ and the thought signature to the provider's tool-call id for OpenAI client compatibility (https://github.com/BerriAI/litellm/blob/v1.105.1/litellm/litellm_core_utils/prompt_templates/factory.py#L1163-L1179). Both suite cells preserve names, arguments and the second id, but the first id differs from the wire. The issue tracks interoperability failures caused by this encoding; the shim reports the exposed id unchanged.

History

VersionGrade
1.105.5✗ WRONG
1.105.1✗ WRONG