mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-19 00:01:29 +00:00
8e25720c08
Response-side guardrail scans on OpenAI Chat Completions, Anthropic Messages, and OpenAI Responses now carry structured_messages (the request turns scoped exactly like the pre-call scan, closed by the model's reply as an assistant turn) and tools (the request's function definitions), in addition to texts, images, and tool_calls. Guardrails that used structured_messages or tools as a response-side signal (akto, crowdstrike_aidr, hiddenlayer, openai moderations, promptguard, qualifire, straiker) keep their previous response payloads. Logging-only scans whose output translation differs from the input translation get a chat-shaped request so the context survives. Resolves LIT-6628 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| conftest.py | ||
| test_akto_guardrails.py | ||
| test_bedrock_guardrails.py | ||
| test_custom_guardrail.py | ||
| test_deepkeep_guardrails.py | ||
| test_dynamoai_guardrails.py | ||
| test_eu_ai_act_article5.py | ||
| test_eu_ai_act_french_3_scenarios.py | ||
| test_guardrail_load_balancing.py | ||
| test_guardrails_config.py | ||
| test_javelin_guardrails.py | ||
| test_lakera_v2.py | ||
| test_lasso_guardrails.py | ||
| test_presidio_pii.py | ||
| test_semantic_guard.py | ||
| test_sg_mas_ai_guardrails.py | ||
| test_sg_pdpa_guardrails.py | ||
| test_tracing_guardrails.py | ||
| test_zscaler_ai_guard.py | ||