AI API receipt · BerriAI/litellm
BerriAI/litellm#45645 · upstream bug reproduced by running the issue's own reproduction
✓ Badgr rejects this response
After two streaming 429s on the primary, a direct request to the healthy "backup" group answered HTTP 429 "No deployments available for selected model" although backup never returned a 429 (reproduced on a live LiteLLM 1.104.2 proxy).
Outcome contract verdict: response is empty. The attempt is recorded as failed (invalid_outcome) instead of a verified success, so it is not billed as a good answer and can fall back to another route.
The output the bug produces, taken from the issue’s reproduction and fed to Badgr’s validators. Not a live provider call.
text: none tool_calls: none
Written by Badgr’s receipt ledger and read back from GET /v1/receipts/replay-litellm-45645-fallback-cooled-by-primary-429.
{
"request_id": "replay-litellm-45645-fallback-cooled-by-primary-429",
"status": "failed",
"endpoint": "/v1/responses",
"stream": false,
"failure_stage": "outcome_contract",
"error_code": "invalid_outcome",
"error_message": "Response did not satisfy the outcome contract: response is empty",
"retryable": true,
"provider_mode": "replay",
"routing_decision": "replayed_upstream_output",
"created_at": "1791652209.3107882"
}Recorded 2026-10-11 in Badgr’s local development environment. Replay cases and verdicts are pinned by backend/test_ai_api_replay_cases.py.
← All AI API receipts