AI API receipt · BerriAI/litellm
BerriAI/litellm#45033 · upstream bug reproduced by running the issue's own reproduction
Badgr cannot tell this response is wrong
The Azure-style Responses path matched only the OpenAI pass-through, so a model configured as an Azure deployment was served by public OpenAI.
the reply is a normal, valid answer; which provider produced it is decided inside the gateway and is not visible in the response. The receipt therefore records success. This is a limit of what the contract can prove, shown here so it is not mistaken for protection.
The output the bug produces, taken from the issue’s reproduction and fed to Badgr’s validators. Not a live provider call.
text: "Hello! How can I help you today?" tool_calls: none
Written by Badgr’s receipt ledger and read back from GET /v1/receipts/replay-litellm-45033-azure-responses-wrong-provider.
{
"request_id": "replay-litellm-45033-azure-responses-wrong-provider",
"status": "success",
"endpoint": "/v1/chat/completions",
"stream": false,
"failure_stage": null,
"error_code": null,
"error_message": null,
"retryable": null,
"provider_mode": "replay",
"routing_decision": "replayed_upstream_output",
"created_at": "1791529032.0804312"
}Recorded 2026-10-09 in Badgr’s local development environment. Replay cases and verdicts are pinned by backend/test_ai_api_replay_cases.py.
← All AI API receipts