✓ PASS
pydantic-ai 2.61.0
stream.missing-finish-abort · gemini
Requirements
| Id | Level | Status | Evidence |
|---|---|---|---|
| no-normal-stop | MUST | SATISFIED | outcome=raised; finish.value=null (absent); truth.finish="none"; forbidden finish="stop" |
| stream-incomplete | MUST | SATISFIED | stream.completed=false; outcome=raised; truth.stream_completed=false |
What the provider sent
- Finish
- none
- Raw finish
null
- Text
- Octop
- Tool calls
[]
- Usage
{ "alternatives": {}, "cached_input": null, "input": 22, "output": 2, "raw": { "candidatesTokenCount": 2, "promptTokenCount": 22, "promptTokensDetails": [ { "modality": "TEXT", "tokenCount": 22 } ], "serviceTier": "standard", "totalTokenCount": 24 }, "reasoning": null, "total": 24 }- 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"}
end: abortWhat the library reported
- Outcome
- raised
- Finish
{ "raw": null, "source": null, "surface": "absent", "value": null }- Text
- Value
- Octop
- Surface
- primary
- Tool calls
[]
- Usage
{ "cached_input": 0, "input": 22, "output": 2, "reasoning": 0, "surface": { "cached_input": "raw", "input": "raw", "output": "raw", "reasoning": "raw", "total": "raw" }, "total": 24 }- Stream
{ "chunks_seen": 2, "completed": false, "used": true }- Error
- Type
- pydantic_ai.exceptions.ModelConnectionError
- Message
- peer closed connection without sending complete message body (incomplete chunked read)
- Category
- api
- Retry after
null
- Stack top
- pydantic_ai/models/google.py:1898
- Unsupported reason
null
Full observation JSON
{
"elapsed_ms": 290.25459848344326,
"error": {
"category": "api",
"message": "peer closed connection without sending complete message body (incomplete chunked read)",
"retry_after": null,
"stack_top": "pydantic_ai/models/google.py:1898",
"type": "pydantic_ai.exceptions.ModelConnectionError"
},
"finish": {
"raw": null,
"source": null,
"surface": "absent",
"value": null
},
"format": "wiretruth.observation/v1",
"library": {
"api": "Agent.run_stream_events",
"language": "python",
"name": "pydantic-ai",
"version": "2.61.0"
},
"notes": [],
"outcome": "raised",
"stream": {
"chunks_seen": 2,
"completed": false,
"used": true
},
"structured": {
"attempted": false,
"returned_as_success": false,
"value": null
},
"text": {
"surface": "primary",
"value": "Octop"
},
"tool_calls": [],
"unsupported_reason": null,
"usage": {
"cached_input": 0,
"input": 22,
"output": 2,
"reasoning": 0,
"surface": {
"cached_input": "raw",
"input": "raw",
"output": "raw",
"reasoning": "raw",
"total": "raw"
},
"total": 24
}
}Fixture
derived gemini/stream.missing-finish-abort
| Provenance | Value |
|---|---|
| Transform | cut_stream_after |
| Source fixture | gemini/truncation.text-stream |
| Rationale | The connection closes before the stream has delivered every event. |
| Evidence | https://github.com/openai/openai-python/issues/2065 |
Reproduce
wiretruth serve gemini/stream.missing-finish-abortPlain-library snippet from the shim manifest.
GoogleModel(model, provider=GoogleProvider(base_url=WIRETRUTH_BASE_URL_GEMINI, api_key=WIRETRUTH_API_KEY)); host rootUpstream
No matching upstream report.
History
| Version | Grade |
|---|---|
| 2.61.0 | ✓ PASS |
| 2.56.0 | ✓ PASS |