mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-31 06:56:59 +00:00
323d3956d6
* feat(rust): one typed decline from core up to each host Rust core says it cannot serve a request with one Decline that travels unchanged through llms and inference up to the host. The Python bridge raises RustBridgeDeclined for it in route_failure before the public exception mapping, so dispatch falls back to legacy Python instead of failing the call, and the gateway answers 501. Every route collapses errors after the send with Error::after_send, which keeps a provider answer and a response fault as they are and nests anything else as the source of an invalid response, so a billed call can never read as a decline. Response-side cases that used to decline are now ErrorDetail::Unhandled response faults. The rust-error skill documents declined() as the first question both boundaries ask, and the Python suites pin that a native decline reaches the dispatcher before any provider IO. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * fix(rust): keep post-provider hook failures terminal --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
75 lines
2.3 KiB
Python
75 lines
2.3 KiB
Python
from typing import Final
|
|
|
|
import litellm
|
|
from tests.test_litellm_rust.support.gaps import gap
|
|
from tests.test_litellm_rust.support.recording_server import RecordingServer
|
|
from tests.test_litellm_rust.support.routing import call_public
|
|
|
|
RESPONSES_MODEL: Final = "openai/gpt-6.1-sol"
|
|
RESPONSES_TEXT: Final = "Hello from native Responses"
|
|
RESPONSES_RESPONSE: Final = {
|
|
"id": "resp_native",
|
|
"object": "response",
|
|
"created_at": 1,
|
|
"status": "completed",
|
|
"model": RESPONSES_MODEL.removeprefix("openai/"),
|
|
"output": [
|
|
{
|
|
"id": "msg_native",
|
|
"type": "message",
|
|
"role": "assistant",
|
|
"status": "completed",
|
|
"content": [{"type": "output_text", "text": RESPONSES_TEXT, "annotations": []}],
|
|
}
|
|
],
|
|
"usage": {"input_tokens": 5, "output_tokens": 4, "total_tokens": 9},
|
|
}
|
|
RESPONSES_EVENTS: Final = (
|
|
(
|
|
"response.created",
|
|
{
|
|
"type": "response.created",
|
|
"sequence_number": 0,
|
|
"response": {**RESPONSES_RESPONSE, "status": "in_progress", "output": []},
|
|
},
|
|
),
|
|
(
|
|
"response.output_text.delta",
|
|
{
|
|
"type": "response.output_text.delta",
|
|
"sequence_number": 1,
|
|
"item_id": "msg_native",
|
|
"output_index": 0,
|
|
"content_index": 0,
|
|
"delta": RESPONSES_TEXT,
|
|
},
|
|
),
|
|
("response.completed", {"type": "response.completed", "sequence_number": 2, "response": RESPONSES_RESPONSE}),
|
|
)
|
|
|
|
|
|
def _error(kind: str) -> dict[str, object]:
|
|
return {"error": {"type": kind, "message": kind, "param": None, "code": None}}
|
|
|
|
|
|
REQUEST: Final = {"model": RESPONSES_MODEL, "input": "Hello"}
|
|
BAD_REQUEST: Final = _error("invalid_request_error")
|
|
RATE_LIMITED: Final = _error("rate_limit_exceeded")
|
|
|
|
|
|
async def call(server: RecordingServer, *, asynchronous: bool = True, **kwargs: object) -> object:
|
|
return await call_public(
|
|
litellm.responses,
|
|
litellm.aresponses,
|
|
REQUEST,
|
|
server,
|
|
asynchronous=asynchronous,
|
|
**kwargs,
|
|
)
|
|
|
|
|
|
SYNC_DEPLOYMENT_HOOK: Final = gap("native sync calls skip the async pre-call deployment hook")
|
|
STREAMING: Final = gap(
|
|
"native Responses streaming is unsupported, the catalog keeps it on Python", raises=RuntimeError
|
|
)
|
|
BODY_HOOKS: Final = gap("native Responses does not run the handler body hooks")
|