mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-19 00:01:29 +00:00
Carry the listed tool's description and inputSchema from MCPServerManager through the pre-call and during-call hook request objects into the Agent 365 evaluate payload, omitting them when the tool was never listed. An allowed verdict whose defender.status is not Evaluated (Skipped, FailedOpen, missing) now follows the unreachable_fallback policy instead of counting as a scanned allow. The conversationId prefers the proxy-owned litellm_call_id over caller-controlled mcp-session-id headers. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| _harness_smoke_test.py | ||
| conftest.py | ||
| test_alerting.py | ||
| test_callback_capabilities_class.py | ||
| test_callback_capabilities_dataclass.py | ||
| test_during_call_hook.py | ||
| test_guardrail_pipeline.py | ||
| test_internal_usage_cache.py | ||
| test_lifecycle.py | ||
| test_mcp_bridging.py | ||
| test_module_helpers.py | ||
| test_post_call_failure_hook.py | ||
| test_post_call_success_hook.py | ||
| test_pre_call_hook.py | ||
| test_streaming_hooks.py | ||