– UNSUPPORTED
tanstack-ai 1.4.0
finish.unknown-value · ollama
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
- other
- Raw finish
- wiretruth_unknown_reason
- Text
- Octopuses are unique marine invertebrates that possess three separate hearts, enabling
- Tool calls
[]
- Usage
{ "alternatives": {}, "cached_input": 28, "input": 32, "output": 16, "raw": { "eval_count": 16, "prompt_eval_cached_count": 28, "prompt_eval_count": 32 }, "reasoning": null, "total": 48 }- Stream completed
null
- Error
null
Wire excerpt
status: 200
content-type: application/json; charset=utf-8
body (json):
{
"model": "qwen3.5:0.8b",
"created_at": "2026-10-12T19:01:21.735707058Z",
"message": {
"role": "assistant",
"content": "Octopuses are unique marine invertebrates that possess three separate hearts, enabling"
},
"done": true,
"done_reason": "wiretruth_unknown_reason",
"total_duration": 1180977461,
"load_duration": 2015632,
"prompt_eval_count": 32,
"prompt_eval_cached_count": 28,
"prompt_eval_duration": 70673000,
"eval_count": 16,
"eval_duration": 1106321000
}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": 4.20780000000002,
"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
derived ollama/finish.unknown-value
| Provenance | Value |
|---|---|
| Transform | replace_finish_value |
| Source fixture | ollama/truncation.text |
| Rationale | The provider sends a finish value that a library may not recognize. |
| Evidence | https://github.com/BerriAI/litellm/issues/21347 |
Reproduce
wiretruth serve ollama/finish.unknown-valuePlain-library snippet from the shim manifest.
createOllamaChat(model, { host: WIRETRUTH_BASE_URL_OLLAMA }); POST /api/chat.Upstream
No matching upstream report.
History
| Version | Grade |
|---|---|
| 1.4.0 | – UNSUPPORTED |
| 1.0.0 | – UNSUPPORTED |
| 0.71.0 | – UNSUPPORTED |