~ LOSSY

any-llm 1.40.2

stream.missing-finish · gemini

Requirements

Id	Level	Status	Evidence
no-normal-stop	MUST	SATISFIED	outcome=returned; finish.value=null (absent); truth.finish="none"; forbidden finish="stop"
stream-incomplete	MUST	NOT_OBSERVABLE	stream.completed=null; outcome=returned; truth.stream_completed=false

Notes

shim: Gemini reasoning_effort none is unsupported by any-llm; omitted to use the model default.

What the provider sent

Finish: none
Raw finish: null
Text: Octopuses are the ultimate masters of disguise, utilizing a
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: false
Error: null

Wire excerpt

status: 200
content-type: text/event-stream
body (sse):
data: {"candidates": [{"content": {"parts": [{"text": "Octop"}],"role": "model"},"index": 0}],"usageMetadata": {"promptTokenCount": 22,"candidatesTokenCount": 2,"totalTokenCount": 24,"promptTokensDetails": [{"modality": "TEXT","tokenCount": 22}],"serviceTier": "standard"},"modelVersion": "gemini-3.5-flash-lite","responseId": "pgTOaonbKMuV_uMPvK7d4AE"}


data: {"candidates": [{"content": {"parts": [{"text": "uses are the ultimate masters of disguise, utilizing a"}],"role": "model"},"index": 0}],"usageMetadata": {"promptTokenCount": 22,"candidatesTokenCount": 12,"totalTokenCount": 34,"promptTokensDetails": [{"modality": "TEXT","tokenCount": 22}],"serviceTier": "standard"},"modelVersion": "gemini-3.5-flash-lite","responseId": "pgTOaonbKMuV_uMPvK7d4AE"}

What the library reported

Outcome

returned

Finish

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

Text

Value: Octopuses are the ultimate masters of disguise, utilizing a
Surface: primary

Tool calls

[]

Usage

{
  "cached_input": null,
  "input": 22,
  "output": 12,
  "reasoning": null,
  "surface": {
    "cached_input": "absent",
    "input": "primary",
    "output": "primary",
    "reasoning": "absent",
    "total": "primary"
  },
  "total": 34
}

Stream

{
  "chunks_seen": 2,
  "completed": null,
  "used": true
}

Error

null

Unsupported reason

null

Full observation JSON

{
  "elapsed_ms": 761.2541867420077,
  "error": null,
  "finish": {
    "raw": null,
    "source": null,
    "surface": "absent",
    "value": null
  },
  "format": "wiretruth.observation/v1",
  "library": {
    "api": "any_llm.completion",
    "language": "python",
    "name": "any-llm",
    "version": "1.40.2"
  },
  "notes": [
    "Gemini reasoning_effort none is unsupported by any-llm; omitted to use the model default."
  ],
  "outcome": "returned",
  "stream": {
    "chunks_seen": 2,
    "completed": null,
    "used": true
  },
  "structured": {
    "attempted": false,
    "returned_as_success": false,
    "value": null
  },
  "text": {
    "surface": "primary",
    "value": "Octopuses are the ultimate masters of disguise, utilizing a"
  },
  "tool_calls": [],
  "unsupported_reason": null,
  "usage": {
    "cached_input": null,
    "input": 22,
    "output": 12,
    "reasoning": null,
    "surface": {
      "cached_input": "absent",
      "input": "primary",
      "output": "primary",
      "reasoning": "absent",
      "total": "primary"
    },
    "total": 34
  }
}

Fixture

derived gemini/stream.missing-finish

Provenance	Value
Transform	strip_finish
Source fixture	gemini/truncation.text-stream
Rationale	The stream ends cleanly without its finish signal.
Evidence	https://github.com/pydantic/pydantic-ai/issues/6610

Reproduce

wiretruth serve gemini/stream.missing-finish

Plain-library snippet from the shim manifest.

any_llm.completion(model=model, provider='gemini', api_base=WIRETRUTH_BASE_URL_GEMINI, api_key=WIRETRUTH_API_KEY); host-root base URL

Upstream

reported Issue

Fixed in: not specified

A stream that ends before the provider's terminal signal returns the partial chunks normally, with no error and no incomplete flag (reproduced on 1.40.2 and 1.50.0). The OpenAI Responses path reports the output item as incomplete and passes.

History

Version	Grade
1.40.2	~ LOSSY
1.38.0	~ LOSSY
1.33.0	~ LOSSY