✓ PASS

vercel-ai 7.0.153

truncation.tool-call-args · anthropic

Requirements

Id	Level	Status	Evidence
no-complete-partial-call	MUST	SATISFIED	1 tool calls; no partial args made complete
cause-is-truncation	MUST	SATISFIED	finish.value="length" (primary: result.finishReason); truth.finish="length"; error.category=null; structured.returned_as_success=false

What the provider sent

Finish: length
Raw finish: max_tokens
Text: null
Tool calls: [ { "arguments": { "title": "Pottery" }, "arguments_parsed_ok": true, "arguments_raw": "{\"title\":\"Pottery\"}", "id": "toolu_01A09q90qw90lq917835lq9", "name": "create_event" } ]
Usage: { "alternatives": {}, "cached_input": null, "input": 25, "output": 20, "raw": { "input_tokens": 25, "output_tokens": 20, "output_tokens_details": { "thinking_tokens": 8 } }, "reasoning": 8, "total": 45 }
Stream completed: null
Error: null

Wire excerpt

status: 200
content-type: application/json
body (json):
{
  "id": "msg_01Aq9w938a90dw8q",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "thinking",
      "thinking": "",
      "signature": "EqQBCgIYAhIM1gbcDa9GJwZA2b3hGgxBdjrkzLoky3dl1pkiMOYds..."
    },
    {
      "type": "tool_use",
      "id": "toolu_01A09q90qw90lq917835lq9",
      "name": "create_event",
      "input": {
        "title": "Pottery"
      }
    }
  ],
  "model": "claude-sonnet-5-5",
  "stop_reason": "max_tokens",
  "stop_sequence": null,
  "stop_details": null,
  "usage": {
    "input_tokens": 25,
    "output_tokens": 20,
    "output_tokens_details": {
      "thinking_tokens": 8
    }
  }
}

What the library reported

Outcome

returned

Finish

{
  "raw": "max_tokens",
  "source": "result.finishReason",
  "surface": "primary",
  "value": "length"
}

Text

Value
Surface: primary

Tool calls

[
  {
    "arguments": {
      "title": "Pottery"
    },
    "arguments_parsed_ok": true,
    "arguments_raw": "{\"title\":\"Pottery\"}",
    "id": "toolu_01A09q90qw90lq917835lq9",
    "name": "create_event"
  }
]

Usage

{
  "cached_input": 0,
  "input": 25,
  "output": 20,
  "reasoning": 8,
  "surface": {
    "cached_input": "primary",
    "input": "primary",
    "output": "primary",
    "reasoning": "primary",
    "total": "primary"
  },
  "total": 45
}

Stream

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

Error

null

Unsupported reason

null

Full observation JSON

{
  "elapsed_ms": 102.07816099999997,
  "error": null,
  "finish": {
    "raw": "max_tokens",
    "source": "result.finishReason",
    "surface": "primary",
    "value": "length"
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "generateText",
    "language": "javascript",
    "name": "vercel-ai",
    "version": "7.0.153"
  },
  "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": {
        "title": "Pottery"
      },
      "arguments_parsed_ok": true,
      "arguments_raw": "{\"title\":\"Pottery\"}",
      "id": "toolu_01A09q90qw90lq917835lq9",
      "name": "create_event"
    }
  ],
  "unsupported_reason": null,
  "usage": {
    "cached_input": 0,
    "input": 25,
    "output": 20,
    "reasoning": 8,
    "surface": {
      "cached_input": "primary",
      "input": "primary",
      "output": "primary",
      "reasoning": "primary",
      "total": "primary"
    },
    "total": 45
  }
}

Fixture

documented anthropic/truncation.tool-call-args

Provenance	Value
Source	https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls#handling-results-from-client-tools
Notes	Documented 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. ASSUMED non-stream truncation: the documented input object contains only title and lacks date, city and attendees. No official example shows this particular max_tokens object. This preserves the documented object type; the partial-JSON check is not exercised by a parsed object. The finish check still applies. The output_tokens_details.thinking_tokens breakdown follows thinking-steering.md (https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost#pricing); the thinking count of 8 is filled in, not measured.

Provenance

Value

Source

https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls#handling-results-from-client-tools

Notes

Documented 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. ASSUMED non-stream truncation: the documented input object contains only title and lacks date, city and attendees. No official example shows this particular max_tokens object. This preserves the documented object type; the partial-JSON check is not exercised by a parsed object. The finish check still applies. The output_tokens_details.thinking_tokens breakdown follows thinking-steering.md (https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost#pricing); the thinking count of 8 is filled in, not measured.

Reproduce

wiretruth serve anthropic/truncation.tool-call-args

Plain-library snippet from the shim manifest.

createAnthropic({ baseURL: WIRETRUTH_BASE_URL_ANTHROPIC + '/v1', apiKey })(model)

Upstream

No matching upstream report.

History

Version	Grade
7.0.153	✓ PASS
7.0.146	✓ PASS
7.0.142	✓ PASS