MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 10 callersFunction_guardrail
(gateway: Gateway, scenario: Scenario, api_base: str, mode: str, **extra: JsonValue)
tests/integration/messages_endpoint/test_guardrail_long_tool_names_wire.py:228
↓ 10 callersFunction_guardrail_entries
(request_data: dict)
tests/unit/integrations/test_custom_guardrail.py:2392
↓ 10 callersMethod_guardrail_errors
(cls, client_ws: DisconnectingClientWS | RealtimeClientWS)
tests/unit/llms/bedrock/realtime/test_bedrock_realtime_handler.py:1848
↓ 10 callersFunction_hand_off
Replace this process with the agent; on Windows, run it as a child instead. os.exec* has no process-replacement semantics on Windows: the C runti
litellm/proxy/client/cli/commands/agents.py:1044
↓ 10 callersFunction_ids
(size: int)
tests/unit/repositories/test_chunked_in.py:76
↓ 10 callersFunction_image_generation_client
( monkeypatch: pytest.MonkeyPatch, user_api_key_dict: UserAPIKeyAuth, team_settings: Mapping[str,
tests/unit/proxy/image_endpoints/test_endpoints.py:449
↓ 10 callersFunction_import_validate
Lazy import to avoid pulling orjson at collection time.
tests/unit/proxy/mcp_server/test_per_user_oauth_cache.py:31
↓ 10 callersFunction_ini
(plan: PgBouncerPlan)
tests/unit/proxy/db/test_pgbouncer.py:59
↓ 10 callersFunction_initialized
(instructions: str | None = None)
tests/unit/mcp_client/test_mcp_client.py:278
↓ 10 callersFunction_install_prisma
(monkeypatch, prisma)
tests/unit/proxy/proxy_server/test_routes_anthropic_beta.py:53
↓ 10 callersMethod_instance
(self, track_unmanaged, router)
tests/unit/proxy/common_utils/test_check_batch_cost.py:1683
↓ 10 callersMethod_instance
(prisma, llm_router)
tests/unit/proxy/common_utils/test_check_batch_cost.py:3210
↓ 10 callersMethod_is_gemini_3_or_newer
Check if the model is Gemini 3 or newer.
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:837
↓ 10 callersMethod_is_guardrail_intervention
Retained spelling for existing callers; prefer ``is_guardrail_intervention``.
litellm/integrations/custom_guardrail.py:1759
↓ 10 callersMethod_is_nova_2_model
Check if the model is a Nova 2 model that supports reasoningConfig. Nova 2 models use a different reasoning configuration structure
litellm/llms/bedrock/chat/converse_transformation.py:435
↓ 10 callersFunction_issued_context
(*hashes: str, affinity: str | None = None)
tests/unit/proxy/guardrails/guardrail_hooks/test_headroom.py:155
↓ 10 callersFunction_job
( status: str, media_uri: str | None = MEDIA_URI, created_at: float | None = CREATED_AT, **members: object
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_transcribe_passthrough_logging_handler.py:80
↓ 10 callersMethod_job
(self, file_object=None)
tests/unit/proxy/common_utils/test_check_batch_cost.py:1695
↓ 10 callersFunction_json_tool_schema
(delivery: _Delivery)
tests/integration/providers/test_vertex_anthropic_structured_output_wire.py:624
↓ 10 callersFunction_key
(model_max_budget: Mapping[str, object])
tests/unit/proxy/hooks/test_model_max_budget_limiter.py:487
↓ 10 callersFunction_langtrace_rig
( gateway: Gateway, tmp_path: Path, *, mode: str = "callbacks", host: Callable[[str], str]
tests/integration/observability/test_langtrace_delivery.py:244
↓ 10 callersFunction_leave_invalid_index
(schema: str, table: str, index: str, columns: str)
tests/integration/database/migrations/test_invalid_index_repair.py:60
↓ 10 callersFunction_listed
(response: httpx.Response)
tests/integration/management/test_vector_store_file_list_managed_ids.py:303
↓ 10 callersMethod_live_handle
(self)
litellm/router_rust/surface/registry.py:1350
↓ 10 callersMethod_load_environment_variables
(self, config: dict)
litellm/proxy/proxy_server.py:6734
↓ 10 callersMethod_load_registry_config
( self, manager: MCPServerManager, config: dict[str, MCPServerConfig], )
tests/unit/proxy/management_endpoints/test_mcp_management_endpoints.py:9966
↓ 10 callersFunction_log
(logger, queue_attr, record)
tests/unit/integrations/test_azure_sentinel.py:739
↓ 10 callersMethod_logger
(self, cap=3, exporter="console")
tests/unit/integrations/test_opentelemetry.py:6879
↓ 10 callersFunction_logging_only_guardrail
( responses: Sequence[dict[str, object] | Exception] = (_clean_armor_response(), _clean_armor_response()),
tests/unit/proxy/guardrails/guardrail_hooks/test_model_armor.py:4981
↓ 10 callersFunction_make_alice_internal_user
()
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:18445
↓ 10 callersFunction_make_async_client
()
tests/unit/interactions/test_agents_http_handler.py:57
↓ 10 callersFunction_make_client
()
tests/unit/proxy/public_endpoints/test_public_endpoints.py:1216
↓ 10 callersFunction_make_endpoint_request
(query_string: str = "")
tests/unit/proxy/google_endpoints/test_gemini_agents_endpoints.py:151
↓ 10 callersFunction_make_handler
(answers: dict[str, float], status: int = 200)
tests/unit/proxy/guardrails/guardrail_hooks/test_typesafe.py:85
↓ 10 callersFunction_make_https_request
()
tests/unit/proxy/management_endpoints/test_ui_sso.py:10822
↓ 10 callersFunction_make_logging_obj
()
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_azure_speech_passthrough_logging_handler.py:80
↓ 10 callersFunction_make_logging_obj
( model: str = "bedrock/us.anthropic.claude-opus-4-6-v1", )
tests/unit/integrations/websearch_interception/test_websearch_thinking_constraint.py:38
↓ 10 callersFunction_make_managed_files_instance_with_batches
Create a PROXY_LiteLLMManagedFiles instance with mocked DB and batches. Args: file_id: The unified file ID batches: List
tests/unit/enterprise/proxy/test_file_deletion_blocking.py:61
↓ 10 callersFunction_make_mcp_handler
()
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:4639
↓ 10 callersFunction_make_oauth2_server
An auth_type=oauth2 MCP server in one of its sub-modes. oauth2_flow 'client_credentials' is M2M; delegate_auth_to_upstream toggles the upstrea
tests/unit/proxy/mcp_server/test_mcp_server_tool_calls_and_headers.py:10662
↓ 10 callersFunction_make_output_message
Build a mock ResponseOutputMessage with output_text parts.
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_transformation.py:1366
↓ 10 callersFunction_make_prisma_client
()
tests/unit/proxy/management_endpoints/test_workflow_management_endpoints.py:104
↓ 10 callersFunction_make_reasoning_item
Build a mock ResponseReasoningItem.
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_transformation.py:1406
↓ 10 callersMethod_make_request
(self, body: dict[str, Any])
tests/unit/proxy/mcp_server/test_mcp_tool_search.py:667
↓ 10 callersFunction_make_response
(url: str, uploaded: bytes = b"")
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_azure_speech_passthrough_logging_handler.py:75
↓ 10 callersMethod_make_router
(self, model_info: dict | None = None)
tests/unit/router_utils/test_cooldown_handlers.py:206
↓ 10 callersFunction_make_team_key
(token: str, team_id: str = "team-abc")
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:15534
↓ 10 callersFunction_make_tool_calls
()
tests/unit/integrations/websearch_interception/test_websearch_thinking_constraint.py:27
↓ 10 callersFunction_make_unified_file_id
Create a base64-encoded unified file ID.
tests/unit/enterprise/proxy/test_file_deletion_blocking.py:25
↓ 10 callersFunction_management_guardrail_rows
(identity: str)
tests/integration/observability/_logging_only_scope_support.py:883
↓ 10 callersFunction_map_reasoning_effort
(model: str, effort: str)
tests/unit/llms/together_ai/chat/test_together_ai_chat_transformation.py:49
↓ 10 callersMethod_map_size_to_aspect_ratio
Map OpenAI size format to OpenRouter aspect_ratio format. Uses the same mapping as image generation since OpenRouter handles
litellm/llms/openrouter/image_edit/transformation.py:317
↓ 10 callersFunction_mapping
(value: JsonValue)
tests/unit/llms/base_llm/chat/test_provider_chat_translation.py:618
↓ 10 callersMethod_mask_response_completed
Apply Presidio output masking (apply_to_output=True) to the ``response.completed`` event before it is forwarded to the client.
litellm/responses/streaming_iterator.py:2976
↓ 10 callersFunction_masking_akto
A post mock that masks secret in place in the sent payload field.
tests/unit/proxy/guardrails/guardrail_hooks/akto/test_akto.py:518
↓ 10 callersMethod_masking_guardrail
()
tests/unit/llms/openai/responses/test_openai_responses_guardrail_handler.py:2460
↓ 10 callersFunction_mcp_response
(content=None, response_cost=0.0)
tests/unit/proxy/guardrails/guardrail_hooks/_cisco_ai_defense_test_utils.py:123
↓ 10 callersMethod_merge
(self, servers)
tests/unit/proxy/mcp_server/test_mcp_server_tool_calls_and_headers.py:6467
↓ 10 callersFunction_message_response
(text: str, annotations: list)
tests/unit/llms/azure/search/test_bing_grounding_search_transformation.py:39
↓ 10 callersFunction_messages
(model: str, prompt: str, stream: bool = False)
tests/integration/providers/test_bedrock_mantle_context_overflow_wire.py:187
↓ 10 callersFunction_messages
(marker: str)
tests/integration/sdk/test_responses_bridge_stream_errors_sdk.py:28
↓ 10 callersFunction_messages_text
(response: httpx.Response)
tests/integration/providers/test_vertex_anthropic_structured_output_wire.py:778
↓ 10 callersFunction_minor_release
(**overrides: httpx.Response | Exception)
tests/unit/proxy/ui_crud_endpoints/test_latest_release_endpoints.py:106
↓ 10 callersFunction_mint_test_refresh_envelope
Mint a refresh envelope the way the producer does, for driving the refresh_token grant in tests. Defaults to a key_hash subject; pass ``identity``
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:6910
↓ 10 callersMethod_mock_prisma
(monkeypatch, stored=None)
tests/unit/proxy/ui_crud_endpoints/test_proxy_setting_endpoints.py:3948
↓ 10 callersFunction_mock_prisma_for_retention
(side_effect: list)
tests/unit/proxy/test_spend_log_cleanup.py:791
↓ 10 callersFunction_mock_pyroscope_module
Return a mock module so 'import pyroscope' succeeds in _init_pyroscope.
tests/unit/proxy/test_pyroscope.py:14
↓ 10 callersFunction_mock_request
()
tests/unit/proxy/vector_store_endpoints/test_vector_store_tenant_guard.py:19
↓ 10 callersFunction_model_from_frame
(frame: bytes | str)
tests/unit/proxy/anthropic_endpoints/test_streaming_model_restamp.py:34
↓ 10 callersFunction_model_info
(billing_unit: str, count: int, period: str = "month", provider: str = "vertex_ai")
tests/unit/proxy/hooks/test_search_free_tier.py:34
↓ 10 callersFunction_model_name
(prefix: str)
tests/integration/compatibility/test_codex_model_catalog.py:212
↓ 10 callersFunction_models
()
tests/integration/configuration/test_json_logs_startup.py:74
↓ 10 callersFunction_native_classifier_router
( output: str = '{"tier":"REASONING"}', classifier_type: str = "llm", deployment_model: str = "ope
tests/unit/router_strategy/test_complexity_router.py:3501
↓ 10 callersFunction_next_turn_input
( assistant: Mapping[str, object], model: str = f"openai/responses/{MODEL}", tools: Sequence[Mappi
tests/unit/completion_extras/litellm_responses_transformation/test_completion_extras_litellm_responses_transformation_history.py:218
↓ 10 callersFunction_no_authenticator
()
tests/unit/llms/github_copilot/test_per_user_auth.py:771
↓ 10 callersFunction_non_admin
()
tests/unit/proxy/common_utils/test_discoverable_model_filter.py:29
↓ 10 callersFunction_number
(value: JsonValue)
tests/integration/providers/test_databricks_decisions_wire.py:93
↓ 10 callersFunction_observe
(endpoint: Endpoint, wire: Wire, sent: _Sent, *, stream: bool)
tests/integration/routing/test_include_fallback_errors_wire.py:253
↓ 10 callersFunction_observe_at
( gateway: Gateway, wire: Wire, endpoint: Endpoint, body: Mapping[str, JsonValue] )
tests/integration/providers/test_bedrock_kimi_k3_cache_point_wire.py:1157
↓ 10 callersFunction_observed
(cache: DualCache, *, caller: str = _CALLER, expires_at: float = 1290.0)
tests/unit/proxy/common_utils/test_cache_aware_routing.py:122
↓ 10 callersFunction_observed_models
(upstream: httpx.Client)
tests/integration/spend/test_team_member_spend.py:161
↓ 10 callersFunction_only_post
(wire: Wire, target: str)
tests/integration/providers/test_responses_bridge_verbosity_wire.py:150
↓ 10 callersFunction_only_request
(wire: Wire)
tests/integration/providers/test_hosted_vllm_reasoning_content_wire.py:93
↓ 10 callersFunction_only_request
(wire: Wire)
tests/integration/providers/test_responses_bridge_tool_search_undeferred_wire.py:341
↓ 10 callersFunction_open_bridged_stream_auto_execute
(logging_obj: Logging)
tests/unit/responses/mcp/test_aresponses_api_with_mcp.py:3118
↓ 10 callersFunction_openai_deployment
(scenario: Scenario, scenario_id: str)
tests/integration/providers/test_realtime_unguarded_voice_turns.py:241
↓ 10 callersFunction_output_request
Arrange a guardrail and act: build the Bedrock OUTPUT payload.
tests/unit/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py:2499
↓ 10 callersFunction_output_types
(output: Sequence[object])
tests/unit/responses/mcp/test_aresponses_api_with_mcp.py:1757
↓ 10 callersFunction_pairs
(upgrade: dict[str, JsonValue])
tests/integration/providers/test_openai_realtime_transcription_url.py:210
↓ 10 callersFunction_parallel_tool_calls
(*signatures)
tests/unit/llms/vertex_ai/gemini/test_vertex_ai_gemini_transformation.py:988
↓ 10 callersFunction_params
(mode: str = "pre_call", **extras: object)
tests/unit/proxy/guardrails/guardrail_hooks/test_conduct.py:120
↓ 10 callersFunction_parse_task_response
(raw_response: httpx.Response)
litellm/llms/minimax/videos/transformation.py:204
↓ 10 callersFunction_patch_delegate_resolver
Patch the admission-parity resolver the delegate probe gates on. Returns ``server`` only for names admission's ``get_mcp_server_by_name`` would ma
tests/unit/proxy/mcp_server/test_mcp_server_tool_calls_and_headers.py:7287
↓ 10 callersFunction_payload
(status: str = "failure", error_code: str | None = "429", **overrides: object)
tests/unit/proxy/db/test_request_error_tracking.py:27
↓ 10 callersFunction_pdf_messages
()
tests/unit/test_main.py:11099
↓ 10 callersFunction_peer_card
(url: str, name: str, version: str = "0.3")
tests/integration/compatibility/test_a2a_wire_versions.py:36
↓ 10 callersFunction_persist_return_to_cookie
Best-effort: persist a SAFE ``return_to`` on ``response`` as the one-shot ``litellm_cp_return_to`` cookie so ANY sign-in path — SSO / Okta / gener
litellm/proxy/management_endpoints/ui_sso.py:3192
↓ 10 callersFunction_persister_with_fake_redis
()
tests/unit/test_vcr_redis_persister.py:45
↓ 10 callersFunction_pin
(tool: MCPTool)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:20013
↓ 10 callersFunction_pinned_deployment_ids
( first_request: dict[str, object], logged_messages: object, next_request: dict[str, object] )
tests/unit/router_utils/pre_call_checks/test_prompt_caching_deployment_check.py:1871
← previousnext →6,701–6,800 of 202,479, ranked by callers