✓ PASS

any-llm 1.40.2

tools.parallel-calls · anthropic

Back to results · Scenario

Requirements

IdLevelStatusEvidence
calls-reportedMUSTSATISFIEDtool_calls[0] id="toolu_01A09q90qw90lq917835lq9", name="get_weather", args={"city": "São Paulo"}, parsed=true; truth id="toolu_01A09q90qw90lq917835lq9", name="get_weather", args={"city": "São Paulo"}, parsed=true; tool_calls[1] id="toolu_01B09q90qw90lq917835lq9", name="get_weather", args={"city": "Zürich"}, parsed=true; truth id="toolu_01B09q90qw90lq917835lq9", name="get_weather", args={"city": "Zürich"}, parsed=true

What the provider sent

Finish
tool_calls
Raw finish
tool_use
Text
null
Tool calls
[
  {
    "arguments": {
      "city": "São Paulo"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\":\"São Paulo\"}",
    "id": "toolu_01A09q90qw90lq917835lq9",
    "name": "get_weather"
  },
  {
    "arguments": {
      "city": "Zürich"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\":\"Zürich\"}",
    "id": "toolu_01B09q90qw90lq917835lq9",
    "name": "get_weather"
  }
]
Usage
{
  "alternatives": {},
  "cached_input": null,
  "input": 180,
  "output": 48,
  "raw": {
    "input_tokens": 180,
    "output_tokens": 48
  },
  "reasoning": null,
  "total": 228
}
Stream completed
null
Error
null
Wire excerpt
status: 200
content-type: application/json
body (json):
{
  "id": "msg_01Aq9w938a90dw8q",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "tool_use",
      "id": "toolu_01A09q90qw90lq917835lq9",
      "name": "get_weather",
      "input": {
        "city": "São Paulo"
      }
    },
    {
      "type": "tool_use",
      "id": "toolu_01B09q90qw90lq917835lq9",
      "name": "get_weather",
      "input": {
        "city": "Zürich"
      }
    }
  ],
  "model": "claude-sonnet-5-5",
  "stop_reason": "tool_use",
  "stop_sequence": null,
  "stop_details": null,
  "usage": {
    "input_tokens": 180,
    "output_tokens": 48
  }
}

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": "toolu_01A09q90qw90lq917835lq9",
    "name": "get_weather"
  },
  {
    "arguments": {
      "city": "Zürich"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"city\": \"Z\\u00fcrich\"}",
    "id": "toolu_01B09q90qw90lq917835lq9",
    "name": "get_weather"
  }
]
Usage
{
  "cached_input": null,
  "input": 180,
  "output": 48,
  "reasoning": null,
  "surface": {
    "cached_input": "absent",
    "input": "primary",
    "output": "primary",
    "reasoning": "absent",
    "total": "primary"
  },
  "total": 228
}
Stream
{
  "chunks_seen": null,
  "completed": null,
  "used": false
}
Error
null
Unsupported reason
null
Full observation JSON
{
  "elapsed_ms": 142.85535737872124,
  "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": "toolu_01A09q90qw90lq917835lq9",
      "name": "get_weather"
    },
    {
      "arguments": {
        "city": "Zürich"
      },
      "arguments_parsed_ok": true,
      "arguments_raw": "{\"city\": \"Z\\u00fcrich\"}",
      "id": "toolu_01B09q90qw90lq917835lq9",
      "name": "get_weather"
    }
  ],
  "unsupported_reason": null,
  "usage": {
    "cached_input": null,
    "input": 180,
    "output": 48,
    "reasoning": null,
    "surface": {
      "cached_input": "absent",
      "input": "primary",
      "output": "primary",
      "reasoning": "absent",
      "total": "primary"
    },
    "total": 228
  }
}

Fixture

documented anthropic/tools.parallel-calls

ProvenanceValue
Sourcehttps://platform.claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use
NotesDocumented shapes, not a recording. Message envelope and stop fields follow handling-stop-reasons; content blocks follow thinking/streaming and handle-tool-calls. Model changed to claude-sonnet-5-5; IDs and scenario text are filled in. Token counts are illustrative, filled in to include thinking within the requested output limit, not measured. The docs show multiple tool_use blocks in one response. City values and the second distinct ID are filled in for this scenario. No thinking block: thinking-steering-and-cost explicitly permits adaptive turns that skip thinking; this occurrence is assumed.

Reproduce

wiretruth serve anthropic/tools.parallel-calls

Plain-library snippet from the shim manifest.

any_llm.completion(model=model, provider='anthropic', api_base=WIRETRUTH_BASE_URL_ANTHROPIC, api_key=WIRETRUTH_API_KEY); host root, SDK appends /v1/messages and uses x-api-key

Upstream

No matching upstream report.

History

VersionGrade
1.40.2✓ PASS
1.38.0✓ PASS
1.33.0✓ PASS