– UNSUPPORTED

tanstack-ai 1.4.0

tools.parallel-calls · anthropic

Requirements

Id	Level	Status	Evidence

Notes

TanStack AI's chat() always requests a streamed response (stream: false collects the stream), so it never sends the non-streamed request this fixture replays. (https://tanstack.com/ai/latest/docs/api/ai#chat-options)

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

unsupported

Finish

{
  "raw": null,
  "source": null,
  "surface": "absent",
  "value": null
}

Text

Value: null
Surface: absent

Tool calls

[]

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

Error

null

Unsupported reason

TanStack AI's chat() always requests a streamed response (stream: false collects the stream), so it never sends the non-streamed request this fixture replays. https://tanstack.com/ai/latest/docs/api/ai#chat-options

Full observation JSON

{
  "elapsed_ms": 1.0481080000000134,
  "error": null,
  "finish": {
    "raw": null,
    "source": null,
    "surface": "absent",
    "value": null
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "chat",
    "language": "javascript",
    "name": "tanstack-ai",
    "version": "1.4.0"
  },
  "notes": [],
  "outcome": "unsupported",
  "stream": {
    "chunks_seen": null,
    "completed": null,
    "used": false
  },
  "structured": {
    "attempted": false,
    "returned_as_success": false,
    "value": null
  },
  "text": {
    "surface": "absent",
    "value": null
  },
  "tool_calls": [],
  "unsupported_reason": "TanStack AI's chat() always requests a streamed response (stream: false collects the stream), so it never sends the non-streamed request this fixture replays. https://tanstack.com/ai/latest/docs/api/ai#chat-options",
  "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

documented anthropic/tools.parallel-calls

Provenance	Value
Source	https://platform.claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use
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. 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.

Provenance

Value

Source

https://platform.claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use

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. 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.

createAnthropicChat(model, apiKey, { baseURL: WIRETRUTH_BASE_URL_ANTHROPIC }); its fetch client appends /v1/messages?beta=true.

Upstream

No matching upstream report.

History

Version	Grade
1.4.0	– UNSUPPORTED
1.0.0	– UNSUPPORTED
0.71.0	– UNSUPPORTED