mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-07 07:58:09 +00:00
bee787b4b5
Guardrails silently skipped three surfaces on the Anthropic Messages path, so an agent loop driven by /v1/messages ran unguarded: - The Anthropic input translation never walked tool_result blocks, so content returned by a local tool (a curl, a file read, an MCP call) reached the model unscanned in both the string and list content shapes, images inside a tool_result included. - tool_permission only understood ModelResponse, so an Anthropic non-streaming response or a raw SSE stream carrying tool_use blocks passed through with no rule ever evaluated. - ContentFilterGuardrail scanned inputs["texts"] but never inputs["tool_calls"], so the arguments a model proposes for a tool call went unchecked. Tool call arguments are parsed as JSON before filtering so a MASK action rewrites the value and leaves the payload valid JSON; non-JSON arguments fall back to scanning the raw string. Denied tool_use blocks are dropped from the Anthropic content array and replaced with a text block, and stop_reason resets to end_turn when nothing tool-shaped survives. |
||
|---|---|---|
| .. | ||
| azure_client_usage_test.py | ||
| ban_constant_numbers.py | ||
| ban_copy_deepcopy_kwargs.py | ||
| bedrock_pricing.py | ||
| callback_manager_test.py | ||
| check_data_replace_usage.py | ||
| check_e2e_no_raw_requests.py | ||
| check_endpoint_coverage.py | ||
| check_fastuuid_usage.py | ||
| check_get_model_cost_key_performance.py | ||
| check_guardrail_apply_decorator.py | ||
| check_licenses.py | ||
| check_provider_folders_documented.py | ||
| check_spanattributes_value_usage.py | ||
| check_unsafe_enterprise_import.py | ||
| code_qa_check_tests.py | ||
| enforce_llms_folder_style.py | ||
| ensure_async_clients_test.py | ||
| info_log_check.py | ||
| liccheck.ini | ||
| license_cache.json | ||
| litellm_logging_code_coverage.py | ||
| log.txt | ||
| memory_test.py | ||
| pass_through_code_coverage.py | ||
| prevent_key_leaks_in_exceptions.py | ||
| recursive_detector.py | ||
| router_code_coverage.py | ||
| router_enforce_line_length.py | ||
| test_aio_http_image_conversion.py | ||
| test_ban_set_verbose.py | ||
| test_chat_completion_imports.py | ||
| test_proxy_types_import.py | ||
| test_router_strategy_async.py | ||
| user_api_key_auth_code_coverage.py | ||