✓ PASS

any-llm 1.40.2

tools.parallel-calls · ollama-openai

Back to results · Scenario

Requirements

IdLevelStatusEvidence
calls-reportedMUSTSATISFIEDtool_calls[0] id="call_s1866drw", name="get_weather", args={"city": "São Paulo"}, parsed=true; truth id="call_s1866drw", name="get_weather", args={"city": "São Paulo"}, parsed=true; tool_calls[1] id="call_awj9t52c", name="get_weather", args={"city": "Zürich"}, parsed=true; truth id="call_awj9t52c", name="get_weather", args={"city": "Zürich"}, parsed=true

What the provider sent

Finish
tool_calls
Raw finish
tool_calls
Text
Tool calls
[
  {
    "arguments": {
      "city": "São Paulo"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\":\"São Paulo\"}",
    "id": "call_s1866drw",
    "name": "get_weather"
  },
  {
    "arguments": {
      "city": "Zürich"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\":\"Zürich\"}",
    "id": "call_awj9t52c",
    "name": "get_weather"
  }
]
Usage
{
  "alternatives": {},
  "cached_input": 288,
  "input": 292,
  "output": 55,
  "raw": {
    "completion_tokens": 55,
    "prompt_tokens": 292,
    "prompt_tokens_details": {
      "cached_tokens": 288
    },
    "total_tokens": 347
  },
  "reasoning": null,
  "total": 347
}
Stream completed
null
Error
null
Wire excerpt
status: 200
content-type: application/json
body (json):
{
  "id": "chatcmpl-598",
  "object": "chat.completion",
  "created": 1791831676,
  "model": "qwen3.5:0.8b",
  "system_fingerprint": "fp_ollama",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "",
        "tool_calls": [
          {
            "id": "call_s1866drw",
            "index": 0,
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"city\":\"São Paulo\"}"
            }
          },
          {
            "id": "call_awj9t52c",
            "index": 1,
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"city\":\"Zürich\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls"
    }
  ],
  "usage": {
    "prompt_tokens": 292,
    "prompt_tokens_details": {
      "cached_tokens": 288
    },
    "completion_tokens": 55,
    "total_tokens": 347
  }
}

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\":\"São Paulo\"}",
    "id": "call_s1866drw",
    "name": "get_weather"
  },
  {
    "arguments": {
      "city": "Zürich"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\":\"Zürich\"}",
    "id": "call_awj9t52c",
    "name": "get_weather"
  }
]
Usage
{
  "cached_input": 288,
  "input": 292,
  "output": 55,
  "reasoning": null,
  "surface": {
    "cached_input": "primary",
    "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": 150.9873103350401,
  "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\":\"São Paulo\"}",
      "id": "call_s1866drw",
      "name": "get_weather"
    },
    {
      "arguments": {
        "city": "Zürich"
      },
      "arguments_parsed_ok": true,
      "arguments_raw": "{\"city\":\"Zürich\"}",
      "id": "call_awj9t52c",
      "name": "get_weather"
    }
  ],
  "unsupported_reason": null,
  "usage": {
    "cached_input": 288,
    "input": 292,
    "output": 55,
    "reasoning": null,
    "surface": {
      "cached_input": "primary",
      "input": "primary",
      "output": "primary",
      "reasoning": "absent",
      "total": "primary"
    },
    "total": 347
  }
}

Fixture

recorded ollama-openai/tools.parallel-calls

ProvenanceValue
Recorded at2026-10-12T19:01:14Z
Requested modelqwen3.5:0.8b
Returned modelqwen3.5:0.8b
CI runhttps://github.com/kartsan03/wiretruth/actions/runs/38294739276

Reproduce

wiretruth serve ollama-openai/tools.parallel-calls

Plain-library snippet from the shim manifest.

any_llm.completion(model=model, provider='openai', api_base=WIRETRUTH_BASE_URL_OLLAMA_OPENAI, api_key=WIRETRUTH_API_KEY)

Upstream

No matching upstream report.

History

VersionGrade
1.40.2✓ PASS
1.38.0✓ PASS
1.33.0✓ PASS