✓ PASS

tanstack-ai 1.4.0

truncation.tool-call-args-stream · openai-chat

Requirements

Id	Level	Status	Evidence
no-complete-partial-call	MUST	SATISFIED	outcome=returned; error signalled
cause-is-truncation	MUST	SATISFIED	finish.value="length" (primary: RUN_FINISHED.metadata.tanstack.finishReason); truth.finish="length"; error.category="other"; structured.returned_as_success=false

What the provider sent

Finish: length
Raw finish: length
Text: null
Tool calls: [ { "arguments": null, "arguments_parsed_ok": false, "arguments_raw": "{\"title\":\"Weekend Pottery Workshop\",\"", "id": "call_DkXNh5JdHW4s54IKfPr4dP1U", "name": "create_event" } ]
Usage: { "alternatives": {}, "cached_input": null, "input": null, "output": null, "raw": null, "reasoning": null, "total": null }
Stream completed: true
Error: null

Wire excerpt

status: 200
content-type: text/event-stream; charset=utf-8
body (sse):
data: {"id":"chatcmpl-EXmWbuEH1m1F3czcaV6FIXqLd54H7","object":"chat.completion.chunk","created":1791720061,"model":"gpt-6-luna","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_DkXNh5JdHW4s54IKfPr4dP1U","type":"function","function":{"name":"create_event","arguments":""}}],"refusal":null},"finish_reason":null}],"obfuscation":"AoLyAol"}


data: {"id":"chatcmpl-EXmWbuEH1m1F3czcaV6FIXqLd54H7","object":"chat.completion.chunk","created":1791720061,"model":"gpt-6-luna","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"obfuscation":"q3"}


data: {"id":"chatcmpl-EXmWbuEH1m1F3czcaV6FIXqLd54H7","object":"chat.completion.chunk","created":1791720061,"model":"gpt-6-luna","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"title"}}]},"finish_reason":null}],"obfuscation":""}


data: {"id":"chatcmpl-EXmWbuEH1m1F3czcaV6FIXqLd54H7","object":"chat.completion.chunk","created":1791720061,"model":"gpt-6-luna","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"obfuscation":""}


data: {"id":"chatcmpl-EXmWbuEH1m1F3czcaV6FIXqLd54H7","object":"chat.completion.chunk","created":1791720061,"model":"gpt-6-luna","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Weekend"}}]},"finish_reason":null}],"obfuscation":"MHeTX929pznvFG"}


data: {"id":"chatcmpl-EXmWbuEH1m1F3czcaV6FIXqLd54H7","object":"chat.completion.chunk","created":1791720061,"model":"gpt-6-luna","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Pot"}}]},"finish_reason":null}],"obfuscation":"X"}


data: {"id":"chatcmpl-EXmWbuEH1m1F3czcaV6FIXqLd54H7","object":"chat.completion.chunk","created":1791720061,"model":"gpt-6-luna","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tery"}}]},"finish_reason":null}],"obfuscation":"v"}


data: {"id":"chatcmpl-EXmWbuEH1m1F3czcaV6FIXqLd54H7","object":"chat.completion.chunk","created":1791720061,"model":"gpt-6-luna","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Workshop"}}]},"finish_reason":null}],"obfuscation":"eBxdZFJ0AQaC"}


data: {"id":"chatcmpl-EXmWbuEH1m1F3czcaV6FIXqLd54H7","object":"chat.completion.chunk","created":1791720061,"model":"gpt-6-luna","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"obfuscation":""}


data: {"id":"chatcmpl-EXmWbuEH1m1F3czcaV6FIXqLd54H7","object":"chat.completion.chunk","created":1791720061,"model":"gpt-6-luna","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"length"}],"obfuscation":"ppOIfIY"}


data: [DONE]

What the library reported

Outcome

returned

Finish

{
  "raw": null,
  "source": "RUN_FINISHED.metadata.tanstack.finishReason",
  "surface": "primary",
  "value": "length"
}

Text

Value: null
Surface: absent

Tool calls

[
  {
    "arguments": null,
    "arguments_parsed_ok": false,
    "arguments_raw": "{\"title\":\"Weekend Pottery Workshop\",\"",
    "id": "call_DkXNh5JdHW4s54IKfPr4dP1U",
    "name": "create_event"
  }
]

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": 13,
  "completed": true,
  "used": true
}

Error

Type: TOOL_CALL_RESULT
Message: The answer stopped at the output limit, so no tool call in it ran. Send the tool calls again. Do not repeat text you already wrote. If one call has a large input, split the work into smaller calls.
Category: other
Retry after: null
Stack top: null

Unsupported reason

null

Full observation JSON

{
  "elapsed_ms": 176.29159000000004,
  "error": {
    "category": "other",
    "message": "The answer stopped at the output limit, so no tool call in it ran. Send the tool calls again. Do not repeat text you already wrote. If one call has a large input, split the work into smaller calls.",
    "retry_after": null,
    "stack_top": null,
    "type": "TOOL_CALL_RESULT"
  },
  "finish": {
    "raw": null,
    "source": "RUN_FINISHED.metadata.tanstack.finishReason",
    "surface": "primary",
    "value": "length"
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "chat",
    "language": "javascript",
    "name": "tanstack-ai",
    "version": "1.4.0"
  },
  "notes": [],
  "outcome": "returned",
  "stream": {
    "chunks_seen": 13,
    "completed": true,
    "used": true
  },
  "structured": {
    "attempted": false,
    "returned_as_success": false,
    "value": null
  },
  "text": {
    "surface": "absent",
    "value": null
  },
  "tool_calls": [
    {
      "arguments": null,
      "arguments_parsed_ok": false,
      "arguments_raw": "{\"title\":\"Weekend Pottery Workshop\",\"",
      "id": "call_DkXNh5JdHW4s54IKfPr4dP1U",
      "name": "create_event"
    }
  ],
  "unsupported_reason": null,
  "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

recorded openai-chat/truncation.tool-call-args-stream

Provenance	Value
Recorded at	2026-10-11T12:01:01Z
Requested model	gpt-6-luna
Returned model	gpt-6-luna
CI run	https://github.com/kartsan03/wiretruth/actions/runs/38137650119

Reproduce

wiretruth serve openai-chat/truncation.tool-call-args-stream

Plain-library snippet from the shim manifest.

createOpenaiChatCompletions(model, apiKey, { baseURL: WIRETRUTH_BASE_URL_OPENAI_CHAT }); POST /v1/chat/completions. https://tanstack.com/ai/latest/docs/adapters/openai#chat-completions-api

Upstream

released Issue · PR

Fixed in: @tanstack/openai-base 1.0.0 (@tanstack/ai-openai 1.0.0)

@tanstack/openai-base Chat Completions picks tool_calls over a pending finish_reason "length" once TOOL_CALL_END was emitted for the unfinished arguments. The core then treats the arguments as a parse failure and the agent loop sends the conversation back to the model: 5 requests in the fixture replay. Fixed by #1874: a pending 'length' now wins over the tool-call flag, so 1.0.0 reports length and sends one request.

History

Version	Grade
1.4.0	✓ PASS
1.0.0	✓ PASS
0.71.0	✗ WRONG