mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-13 08:52:02 +00:00
2b4485dee5
#40154 made the deployment post_call hook really run apply_guardrail guardrails, so the proxy checked the same response a second time (LIT-10481). The deployment hook now records guardrail + response hash on the request and on the response, and the proxy skips a guardrail only on a matching record. The hash covers every field except ids, usage, model and other metadata set between layers, so a response rewritten between the layers (OCR included) is still checked. Guardrails with their own post_call hook keep their pre-#40154 behavior Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| helpers | ||
| prisma_and_spend | ||
| proxy_logging | ||
| __init__.py | ||