AI API receipt · BerriAI/litellm

A pre_call guardrail adds litellm_metadata, so tag-based routing ignores the request tags

BerriAI/litellm#45543 · upstream bug reproduced by running the issue's own reproduction

Badgr cannot tell this response is wrong

A request tagged for the glm-5 deployment was served by the qwen3-coder deployment; no error was raised.

the reply is a normal answer; which deployment 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.

What the upstream returned (replayed)

The output the bug produces, taken from the issue’s reproduction and fed to Badgr’s validators. Not a live provider call.

text: "Hi! How can I help?"
tool_calls: none

Badgr receipt

Written by Badgr’s receipt ledger and read back from GET /v1/receipts/replay-litellm-45543-guardrail-breaks-tag-routing.

{
  "request_id": "replay-litellm-45543-guardrail-breaks-tag-routing",
  "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": "1791542228.514068"
}

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