~ LOSSY
pydantic-ai 2.61.0
finish.unknown-value · anthropic
Requirements
| Id | Level | Status | Evidence |
|---|---|---|---|
| response-returned | MUST | SATISFIED | outcome=returned; error.category=null; truth.error=null |
| finish-is-other | MUST | NOT_OBSERVABLE | finish.value=null (raw: provider_details.finish_reason); truth.finish="other"; required finish="other" |
| text-reported | MUST | SATISFIED | text.value="Octopuses change colour by" (primary); truth.text="Octopuses change colour by" |
| raw-finish-reported | SHOULD | SATISFIED | finish.raw="WIRETRUTH_UNKNOWN_REASON"; truth.raw_finish="WIRETRUTH_UNKNOWN_REASON" |
What the provider sent
- Finish
- other
- Raw finish
- WIRETRUTH_UNKNOWN_REASON
- Text
- Octopuses change colour by
- Tool calls
[]
- Usage
{ "alternatives": {}, "cached_input": null, "input": 25, "output": 16, "raw": { "input_tokens": 25, "output_tokens": 16, "output_tokens_details": { "thinking_tokens": 8 } }, "reasoning": 8, "total": 41 }- Stream completed
null
- Error
null
Wire excerpt
status: 200
content-type: application/json
body (json):
{
"id": "msg_01Aq9w938a90dw8q",
"type": "message",
"role": "assistant",
"content": [
{
"type": "thinking",
"thinking": "",
"signature": "EqQBCgIYAhIM1gbcDa9GJwZA2b3hGgxBdjrkzLoky3dl1pkiMOYds..."
},
{
"type": "text",
"text": "Octopuses change colour by"
}
],
"model": "claude-sonnet-5-5",
"stop_reason": "WIRETRUTH_UNKNOWN_REASON",
"stop_sequence": null,
"stop_details": null,
"usage": {
"input_tokens": 25,
"output_tokens": 16,
"output_tokens_details": {
"thinking_tokens": 8
}
}
}What the library reported
- Outcome
- returned
- Finish
{ "raw": "WIRETRUTH_UNKNOWN_REASON", "source": "provider_details.finish_reason", "surface": "raw", "value": null }- Text
- Value
- Octopuses change colour by
- Surface
- primary
- Tool calls
[]
- Usage
{ "cached_input": 0, "input": 25, "output": 16, "reasoning": 8, "surface": { "cached_input": "primary", "input": "primary", "output": "primary", "reasoning": "primary", "total": "primary" }, "total": 41 }- Stream
{ "chunks_seen": null, "completed": null, "used": false }- Error
null
- Unsupported reason
null
Full observation JSON
{
"elapsed_ms": 268.39912310242653,
"error": null,
"finish": {
"raw": "WIRETRUTH_UNKNOWN_REASON",
"source": "provider_details.finish_reason",
"surface": "raw",
"value": null
},
"format": "wiretruth.observation/v1",
"library": {
"api": "Agent.run",
"language": "python",
"name": "pydantic-ai",
"version": "2.61.0"
},
"notes": [],
"outcome": "returned",
"stream": {
"chunks_seen": null,
"completed": null,
"used": false
},
"structured": {
"attempted": false,
"returned_as_success": false,
"value": null
},
"text": {
"surface": "primary",
"value": "Octopuses change colour by"
},
"tool_calls": [],
"unsupported_reason": null,
"usage": {
"cached_input": 0,
"input": 25,
"output": 16,
"reasoning": 8,
"surface": {
"cached_input": "primary",
"input": "primary",
"output": "primary",
"reasoning": "primary",
"total": "primary"
},
"total": 41
}
}Fixture
derived anthropic/finish.unknown-value
| Provenance | Value |
|---|---|
| Transform | replace_finish_value |
| Source fixture | anthropic/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 anthropic/finish.unknown-valuePlain-library snippet from the shim manifest.
AnthropicModel(model, provider=AnthropicProvider(base_url=WIRETRUTH_BASE_URL_ANTHROPIC, api_key=WIRETRUTH_API_KEY)); host rootUpstream
No matching upstream report.
History
| Version | Grade |
|---|---|
| 2.61.0 | ~ LOSSY |
| 2.56.0 | ~ LOSSY |