✗ WRONG

any-llm 1.40.2

tools.parallel-calls · ollama

Requirements

Id	Level	Status	Evidence
calls-reported	MUST	CONTRADICTED	tool_calls[0] id="81193cdc-7f88-4adc-8e6c-ac29f9b61b66", name="get_weather", args={"city": "São Paulo"}, parsed=true; truth id="call_9epwsqu6", name="get_weather", args={"city": "São Paulo"}, parsed=true; tool_calls[1] id="4e915b8d-84fe-4964-a833-09d08f617d15", name="get_weather", args={"city": "Zürich"}, parsed=true; truth id="call_bvzy1ra9", 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_9epwsqu6", "name": "get_weather" }, { "arguments": { "city": "Zürich" }, "arguments_parsed_ok": true, "arguments_raw": "{\"city\":\"Zürich\"}", "id": "call_bvzy1ra9", "name": "get_weather" } ]
Usage: { "alternatives": {}, "cached_input": 288, "input": 292, "output": 55, "raw": { "eval_count": 55, "prompt_eval_cached_count": 288, "prompt_eval_count": 292 }, "reasoning": null, "total": 347 }
Stream completed: null
Error: null

Wire excerpt

status: 200
content-type: application/json; charset=utf-8
body (json):
{
  "model": "qwen3.5:0.8b",
  "created_at": "2026-10-12T19:01:13.696397757Z",
  "message": {
    "role": "assistant",
    "content": "",
    "tool_calls": [
      {
        "id": "call_9epwsqu6",
        "function": {
          "index": 0,
          "name": "get_weather",
          "arguments": {
            "city": "São Paulo"
          }
        }
      },
      {
        "id": "call_bvzy1ra9",
        "function": {
          "index": 1,
          "name": "get_weather",
          "arguments": {
            "city": "Zürich"
          }
        }
      }
    ]
  },
  "done": true,
  "done_reason": "stop",
  "total_duration": 2299982620,
  "load_duration": 3338545,
  "prompt_eval_count": 292,
  "prompt_eval_cached_count": 288,
  "prompt_eval_duration": 71919000,
  "eval_count": 55,
  "eval_duration": 2221115000
}

What the library reported

Outcome

returned

Finish

{
  "raw": "tool_calls",
  "source": "choices[0].finish_reason",
  "surface": "primary",
  "value": "tool_calls"
}

Text

Value
Surface: primary

Tool calls

[
  {
    "arguments": {
      "city": "São Paulo"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\": \"S\\u00e3o Paulo\"}",
    "id": "81193cdc-7f88-4adc-8e6c-ac29f9b61b66",
    "name": "get_weather"
  },
  {
    "arguments": {
      "city": "Zürich"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\": \"Z\\u00fcrich\"}",
    "id": "4e915b8d-84fe-4964-a833-09d08f617d15",
    "name": "get_weather"
  }
]

Usage

{
  "cached_input": null,
  "input": 292,
  "output": 55,
  "reasoning": null,
  "surface": {
    "cached_input": "absent",
    "input": "primary",
    "output": "primary",
    "reasoning": "absent",
    "total": "primary"
  },
  "total": 347
}

Stream

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

Error

null

Unsupported reason

null

Full observation JSON

{
  "elapsed_ms": 188.51633928716183,
  "error": null,
  "finish": {
    "raw": "tool_calls",
    "source": "choices[0].finish_reason",
    "surface": "primary",
    "value": "tool_calls"
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "any_llm.completion",
    "language": "python",
    "name": "any-llm",
    "version": "1.40.2"
  },
  "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": {
        "city": "São Paulo"
      },
      "arguments_parsed_ok": true,
      "arguments_raw": "{\"city\": \"S\\u00e3o Paulo\"}",
      "id": "81193cdc-7f88-4adc-8e6c-ac29f9b61b66",
      "name": "get_weather"
    },
    {
      "arguments": {
        "city": "Zürich"
      },
      "arguments_parsed_ok": true,
      "arguments_raw": "{\"city\": \"Z\\u00fcrich\"}",
      "id": "4e915b8d-84fe-4964-a833-09d08f617d15",
      "name": "get_weather"
    }
  ],
  "unsupported_reason": null,
  "usage": {
    "cached_input": null,
    "input": 292,
    "output": 55,
    "reasoning": null,
    "surface": {
      "cached_input": "absent",
      "input": "primary",
      "output": "primary",
      "reasoning": "absent",
      "total": "primary"
    },
    "total": 347
  }
}

Fixture

recorded ollama/tools.parallel-calls

Provenance	Value
Recorded at	2026-10-12T19:01:11Z
Requested model	qwen3.5:0.8b
Returned model	qwen3.5:0.8b
CI run	https://github.com/kartsan03/wiretruth/actions/runs/38294709109

Reproduce

wiretruth serve ollama/tools.parallel-calls

Plain-library snippet from the shim manifest.

any_llm.completion(model=model, provider='ollama', api_base=WIRETRUTH_BASE_URL_OLLAMA, api_key=WIRETRUTH_API_KEY)

Upstream

reported Issue

Fixed in: not specified

Existing upstream issue, not opened by wiretruth. Ollama sends an id on each tool call, but the ollama Python client (0.6.3, latest) has no field for it, so any-llm's native provider generates UUIDs instead (providers/ollama/utils.py).

History

Version	Grade
1.40.2	✗ WRONG
1.38.0	✗ WRONG
1.33.0	✗ WRONG