– UNSUPPORTED
tanstack-ai 1.4.0
finish.unknown-value · gemini
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 masters of disguise, utilizing an extraordinary biological
- Tool calls
[]
- Usage
{ "alternatives": {}, "cached_input": null, "input": 22, "output": 12, "raw": { "candidatesTokenCount": 12, "promptTokenCount": 22, "promptTokensDetails": [ { "modality": "TEXT", "tokenCount": 22 } ], "serviceTier": "standard", "totalTokenCount": 34 }, "reasoning": null, "total": 34 }- Stream completed
null
- Error
null
Wire excerpt
status: 200
content-type: application/json; charset=UTF-8
body (json):
{
"candidates": [
{
"content": {
"parts": [
{
"text": "Octopuses are masters of disguise, utilizing an extraordinary biological",
"thoughtSignature": "EmAKXgFpFH0Tm8qzVWNDFvDnBwobD+/9o7uFQz9+c2VcCrTB9RWT+X+x31DAAin+FtIl2C83hppDgmzNy1HB9PPsQ8rPuUnop8Dz511I6ZzJISG/duJhXlK9Qx4iq7WblXs="
}
],
"role": "model"
},
"finishReason": "WIRETRUTH_UNKNOWN_REASON",
"index": 0
}
],
"usageMetadata": {
"promptTokenCount": 22,
"candidatesTokenCount": 12,
"totalTokenCount": 34,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 22
}
],
"serviceTier": "standard"
},
"modelVersion": "gemini-3.5-flash-lite",
"responseId": "qATOaqvbNv6NjMcPlvHCoA4"
}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": 1.0017100000000028,
"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 gemini/finish.unknown-value
| Provenance | Value |
|---|---|
| Transform | replace_finish_value |
| Source fixture | gemini/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 gemini/finish.unknown-valuePlain-library snippet from the shim manifest.
createGeminiChat(model, apiKey, { baseURL: WIRETRUTH_BASE_URL_GEMINI }); SDK appends /v1beta/models/<model>:streamGenerateContent or :generateContent.Upstream
No matching upstream report.
History
| Version | Grade |
|---|---|
| 1.4.0 | – UNSUPPORTED |
| 1.0.0 | – UNSUPPORTED |
| 0.71.0 | – UNSUPPORTED |