litellm/tests/test_litellm/proxy/guardrails
devin-ai-integration[bot] fa6b209165
feat(guardrails): add only_scan_new_messages for per-session incremental scanning (#33278)
* feat(guardrails): add only_scan_new_messages for per-session incremental scanning

Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>

* fix(guardrails): use fixed TTL constant and revert unrelated test formatting

Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>

* fix(guardrails): run only_scan_new_messages in the unified apply_guardrail path

The initial wiring lived in BedrockGuardrail.async_pre_call_hook, but the proxy
routes Bedrock through the unified apply_guardrail interface, so the flag had no
effect live. Move incremental selection into apply_guardrail: filter the flat
texts list against per-session scanned hashes, skip the Bedrock call when nothing
is new, and mark hashes only after a successful (non-blocked) scan. Full-context
fallback is preserved when there is no session id, the cache is unavailable, or a
masking guardrail is configured.

Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>

* test(guardrails): cover session-id fallbacks and mark_texts_scanned guards

Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>

* fix(guardrails): fall back to full scan when incremental guardrail masks content, use shared cache

Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>

* test(guardrails): cover generic agent multi-turn incremental scan

Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>

* test(guardrails): cover incremental scan cache resolver fallbacks

Co-Authored-By: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>

* test(guardrails): cover flag interactions and /v1/messages incremental scan semantics

* feat(guardrails): make GUARDRAIL_SCANNED_MESSAGES_CACHE_TTL_SECONDS env configurable

* test(guardrails): prove skip_system/skip_tool are enforced upstream of incremental scan

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Ishaan Jaffer <155045088+ishaan-berri@users.noreply.github.com>
Co-authored-by: Yucheng Zhu <yucheng@berri.ai>
2026-07-22 09:56:59 -07:00
..
guardrail_hooks feat(guardrails): add only_scan_new_messages for per-session incremental scanning (#33278) 2026-07-22 09:56:59 -07:00
test_content_filter_path_traversal.py Litellm OSS Staging 010626 (#29422) 2026-06-01 21:42:51 -07:00
test_content_utils.py fix(guardrails): walk custom_tool_call_output items in _content_utils (#32969) 2026-07-13 09:27:57 -07:00
test_custom_code_security.py fix(guardrails): return HTTP 400 for litellm content filter blocks (#28418) 2026-05-30 14:28:46 -07:00
test_deferred_guardrail_logging.py feat(proxy): enforce key/team guardrails on bedrock passthrough routes (#30194) 2026-06-12 07:23:29 -07:00
test_guardrail_coverage.py fix(tests): use canonical litellm_enterprise import path (#27699) 2026-05-12 12:32:57 -07:00
test_guardrail_endpoints.py feat(guardrails): forward optional metadata on POST /guardrails/apply_guardrail (#33067) 2026-07-16 01:36:17 +03:00
test_guardrail_registry.py fix(guardrails): show YAML-defined guardrails in the Guardrail Monitor 2026-07-10 16:49:30 -07:00
test_init_guardrails.py fix(guardrails): show YAML-defined guardrails in the Guardrail Monitor 2026-07-10 16:49:30 -07:00
test_llm_as_a_judge.py feat(guardrails): LLM-as-a-Judge guardrail (#26360) 2026-04-24 17:15:32 -07:00
test_mcp_jwt_signer.py fix(mcp): JWT on tools/list and REST tools/call server resolution (#28227) 2026-05-20 13:31:44 -07:00
test_pillar_guardrails.py chore(proxy): harden request control fields 2026-04-29 22:35:17 -07:00
test_prompt_security_guardrails.py fixing prompt-security's guardrail implementation (#19374) 2026-01-21 20:09:40 -08:00
test_qostodian_nexus_guardrail.py feat: add Qohash Nexus guardrail hook (#24927) 2026-05-01 17:26:32 +05:30
test_usage_endpoints.py fix(guardrails): show YAML-defined guardrails in the Guardrail Monitor 2026-07-10 16:49:30 -07:00