MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 7 callersFunction_history_with_two_tool_pairs
()
tests/unit/llms/anthropic/messages/context_management/test_dispatcher.py:13
↓ 7 callersFunction_hooks
(events: tuple[_Event, ...])
tests/integration/authorization/test_agent_denial_logging.py:369
↓ 7 callersFunction_hunk
(old_start: int, old_count: int, new_start: int, new_count: int, *lines: str)
tests/unit/test_spend_logs_guard.py:39
↓ 7 callersFunction_hybrid_router
(mock_router_instance, **config_overrides)
tests/unit/router_strategy/test_complexity_router.py:14215
↓ 7 callersFunction_id_jag_claims
(**overrides)
tests/unit/proxy/auth/test_handle_jwt.py:8494
↓ 7 callersFunction_identities
(tmp_path: Path, source: str)
tests/unit/test_check_unbounded_in_lists.py:278
↓ 7 callersFunction_identity_server
(**overrides)
tests/unit/proxy/mcp_server/test_db_credentials.py:81
↓ 7 callersFunction_idp_server
Exercise provisioning failures through the same HTTP transport as live tests.
tests/e2e_harness/test_idp.py:71
↓ 7 callersMethod_image_message
(role="user")
tests/unit/llms/deepseek/chat/test_deepseek_chat_transformation.py:267
↓ 7 callersFunction_imagen_edit_response_images
(payload: object)
tests/unit/llms/vertex_ai/image_edit/test_vertex_ai_image_edit_transformation.py:549
↓ 7 callersFunction_in_memory_store
()
tests/unit/proxy/hooks/test_batch_enqueued_tokens.py:34
↓ 7 callersFunction_in_stream_error_status
(gateway: Gateway, stream: tuple[bytes, ...])
tests/integration/streaming/test_responses_bridge_stream_errors.py:263
↓ 7 callersFunction_indexed_messages
(attributes, prefix)
tests/unit/integrations/otel/test_otel_v2_emitter.py:531
↓ 7 callersMethod_initialize_tool_name_to_mcp_server_name_mapping
Call list_tools for each server and update the tool name to MCP server name mapping Note: This now handles prefixed tool names
litellm/proxy/mcp_server/mcp_server_manager.py:7262
↓ 7 callersMethod_input_images
(items)
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_transformation.py:1803
↓ 7 callersFunction_input_json_deltas
(events: List[dict])
tests/unit/llms/anthropic/messages/adapters/test_streaming_iterator_first_delta.py:295
↓ 7 callersFunction_input_tokens
(router: Router, request_body: Mapping[str, JsonValue])
tests/unit/proxy/test_proxy_token_counter.py:4128
↓ 7 callersMethod_install
( self, monkeypatch: pytest.MonkeyPatch, body: dict, upstream: _AzureRelayUpst
tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py:7948
↓ 7 callersFunction_install_router
(monkeypatch, *deployments, **router_kwargs)
tests/unit/proxy/test_model_list_callback_filter.py:73
↓ 7 callersMethod_instance
(self, track_unmanaged, router)
tests/unit/proxy/common_utils/test_check_batch_cost.py:1994
↓ 7 callersMethod_instance
(key_row=None, team_row=None, error: Exception | None = None)
tests/unit/proxy/common_utils/test_check_batch_cost.py:4479
↓ 7 callersFunction_internal_tool_use_block
(block_id: str = "toolu_internal_1")
tests/unit/integrations/websearch_interception/test_websearch_agentic_loop_cap.py:58
↓ 7 callersMethod_is_always_on_thinking_model
Whether ``model`` always thinks and rejects ``thinking.type=disabled`` (Fable 5 / Mythos 5 generation). The model cost map is authoritative: a
litellm/llms/anthropic/common_utils.py:1159
↓ 7 callersFunction_is_converse_endpoint
(endpoint: str)
litellm/llms/bedrock/passthrough/guardrail_translation/handler.py:70
↓ 7 callersMethod_is_gemini_tts_model
(model: str)
litellm/llms/vertex_ai/text_to_speech/transformation.py:350
↓ 7 callersFunction_is_message_item
(event: BaseLiteLLMOpenAIResponseObject)
tests/unit/responses/litellm_completion_transformation/test_streaming_iterator_transformation.py:1409
↓ 7 callersFunction_is_object_list
(value: object)
litellm/proxy/guardrails/guardrail_hooks/repelloai/repelloai.py:62
↓ 7 callersFunction_is_str_keyed_mapping
( value: object, )
litellm/router_utils/embedding_batch_size_check.py:19
↓ 7 callersFunction_is_valid_deployment_tag_regex
Test compiled regex patterns against "Header-Name: value" strings. Returns the first matching pattern string, or None if nothing matches.
litellm/router_strategy/tag_based_routing.py:96
↓ 7 callersFunction_is_within_off_peak_window
Return True if current_time (UTC, defaulting to now) falls inside any off-peak window. off_peak_hours_utc is a "HH:MM-HH:MM" string in UTC, or a
litellm/litellm_core_utils/llm_cost_calc/utils.py:459
↓ 7 callersFunction_item
(role: str, text: str, mark: JsonValue = EPHEMERAL)
tests/integration/providers/test_responses_bridge_message_cache_control_wire.py:80
↓ 7 callersFunction_items
(value: JsonValue)
tests/integration/providers/test_gemini_tool_result_part_reference_wire.py:103
↓ 7 callersFunction_iter_numbered_openai_jsonl_lines
Yield non-empty JSONL lines one at a time without materializing the whole payload, so peak memory stays bounded regardless of payload size. M
litellm/llms/vertex_ai/files/transformation.py:923
↓ 7 callersFunction_iter_with_keepalive
Wrap `aiter` with idle-gap heartbeats, re-resolving the interval after each real chunk via `resolve_keepalive_seconds`. A mid-stream router fallba
litellm/proxy/proxy_server.py:10599
↓ 7 callersMethod_job
(self, file_object=None)
tests/unit/proxy/common_utils/test_check_batch_cost.py:2006
↓ 7 callersMethod_job
(self, job_id, unified_object_id)
tests/unit/proxy/common_utils/test_check_batch_cost.py:2758
↓ 7 callersFunction_json_body
(request: Request)
tests/integration/providers/test_realtime_webrtc_http.py:111
↓ 7 callersFunction_json_body
(request: Request)
tests/integration/authorization/test_rag_team_provider_credentials.py:175
↓ 7 callersFunction_json_mode_group
(make_core: MakeCore, **arguments: object)
tests/unit/test_router/core/test_construction_precall_characterization_precall.py:98
↓ 7 callersFunction_json_object
(value: object)
litellm/litellm_core_utils/realtime_guardrails.py:58
↓ 7 callersFunction_kb_route
(respx_mock: respx.MockRouter)
tests/unit/integrations/vector_store_integrations/test_vector_store_pre_call_hook_bedrock_kb.py:78
↓ 7 callersFunction_key
(key_skills: list[str] | None, team_skills: list[str] | None)
tests/unit/proxy/anthropic_endpoints/test_claude_code_skill_access.py:22
↓ 7 callersFunction_key_for_scope
(scenario: Scenario, model: str, scope: Literal["key", "team"], store_id: str)
tests/integration/authorization/test_rag_query_vector_store_allowlist.py:48
↓ 7 callersFunction_key_row
(gateway: Gateway, key: str)
tests/integration/authorization/test_key_budget_owner_updates.py:74
↓ 7 callersMethod_kwargs
(configured=None)
tests/unit/integrations/test_anthropic_cache_control_hook.py:2834
↓ 7 callersFunction_kwargs_snapshot
(call)
tests/unit/proxy/utils/proxy_logging/test_internal_usage_cache.py:18
↓ 7 callersFunction_langfuse_attrs
( metadata: Mapping[str, object], metadata_keys: tuple[str, ...] = DEFAULT_BAGGAGE_METADATA_KEYS )
tests/unit/integrations/otel/test_otel_v2_vendor_mappers.py:847
↓ 7 callersFunction_leaky_list_server
A server whose url/static_headers/env carry embedded secrets, for the list-endpoint sanitization tests. ``model_construct`` skips validation so
tests/unit/proxy/management_endpoints/test_mcp_management_endpoints.py:6676
↓ 7 callersFunction_list_files
( gateway: Gateway, key: str, *, purpose: str | None = None, )
tests/integration/management/test_batch_output_file_listing.py:240
↓ 7 callersFunction_list_owned
(fetch_page, after=None, limit=None)
tests/unit/containers/test_container_proxy_ownership.py:293
↓ 7 callersFunction_listed
(proxy: Gateway, expected: tuple[tuple[str, str], ...])
tests/integration/configuration/test_callback_delete.py:83
↓ 7 callersMethod_listing
(*models)
tests/unit/proxy/client/cli/test_agents.py:564
↓ 7 callersFunction_load_callbacks
(value, config_file_path)
tests/unit/proxy/common_utils/test_callback_utils.py:674
↓ 7 callersMethod_load_categories
Load content categories from configuration. Args: categories: List of category configurations with format:
litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/content_filter.py:598
↓ 7 callersMethod_load_user_env_vars
Look up the calling user's env var values for ``server``. Returns an empty dict when no user is available. Results are cached in a sh
litellm/proxy/mcp_server/mcp_server_manager.py:4272
↓ 7 callersFunction_log_success
(limiter, **kwargs)
tests/unit/proxy/hooks/test_unit_test_max_model_budget_limiter.py:1815
↓ 7 callersFunction_log_success
(limiter: RouterBudgetLimiting, kwargs: dict[str, object])
tests/unit/router_strategy/test_budget_limiter.py:62
↓ 7 callersFunction_logger
(insert: AsyncMock)
tests/unit/integrations/clickhouse/test_clickhouse_batch_logger.py:20
↓ 7 callersFunction_logging_obj
()
tests/unit/proxy/pass_through_endpoints/test_upstream_usage_headers.py:80
↓ 7 callersFunction_logging_obj
()
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_openai_websocket_passthrough_logging_handler.py:29
↓ 7 callersFunction_logging_obj
(metadata: Optional[dict] = None)
tests/unit/proxy/spend_tracking/test_background_interaction_settlement.py:125
↓ 7 callersFunction_logging_obj
( start_time: datetime = datetime(2026, 10, 9, 12, 0, 0), recorder: _SuccessRecorder | None = None )
tests/unit/google_genai/test_google_genai_streaming_iterator.py:30
↓ 7 callersMethod_logging_obj
( self, model_info: dict, *, flag: str, litellm_rate: float, monkeypatch, deployment: str | None = Non
tests/unit/litellm_core_utils/test_litellm_logging.py:10959
↓ 7 callersMethod_logging_obj
(*, call_type, recovered_cost=0.0)
tests/unit/proxy/test_common_request_processing.py:7808
↓ 7 callersFunction_logging_to
(langfuse_url: str, **callback_vars: JsonValue)
tests/integration/spend/test_background_response_billed_once.py:926
↓ 7 callersFunction_long_messages
Return a message list at the SIGNAL_GATE_MIN_MESSAGES threshold.
tests/unit/router_strategy/adaptive_router/test_hooks.py:40
↓ 7 callersFunction_lookup_tool
(description: str | Callable[[Mapping[str, str]], str] = "Look up one record")
tests/integration/mcp/test_mcp_listed_tool_metadata.py:198
↓ 7 callersMethod_make_app_with_auth
(self, auth_fn)
tests/unit/proxy/management_endpoints/test_workflow_management_endpoints.py:543
↓ 7 callersFunction_make_chunk
Helper to build a ModelResponseStream chunk with tool_calls on the delta.
tests/unit/llms/chatgpt/chat/test_streaming_utils.py:26
↓ 7 callersFunction_make_deployment
( model_name: str, default_tpm: Optional[int] = None, default_rpm: Optional[int] = None, )
tests/unit/proxy/test_model_info_default_limits.py:17
↓ 7 callersFunction_make_event
( event_id: str = "evt-1", run_id: str = "run-1", event_type: str = "step.started", step_name:
tests/unit/proxy/management_endpoints/test_workflow_management_endpoints.py:50
↓ 7 callersFunction_make_guardrail_dict
(name="g", **litellm_params_overrides)
tests/unit/proxy/guardrails/test_llm_as_a_judge.py:105
↓ 7 callersFunction_make_httpx_response
( body: dict, status_code: int = 200 )
tests/unit/llms/gigachat/chat/test_gigachat_chat_transformation.py:27
↓ 7 callersFunction_make_incomplete_responses_api_response
( incomplete_reason: Optional[str], output: "List[ResponseOutputItem]", status: Literal["completed
tests/unit/completion_extras/litellm_responses_transformation/test_completion_extras_litellm_responses_transformation_transformation.py:5025
↓ 7 callersMethod_make_iterator
(self)
tests/unit/interactions/test_gemini_interactions_transformation.py:210
↓ 7 callersFunction_make_leader_election_job
A ResetBudgetJob wired to one lock manager, with every read observable. `prisma_client.get_data_calls` plus `prisma_client.db.query_raw` together
tests/unit/proxy/common_utils/test_reset_budget_job.py:2594
↓ 7 callersFunction_make_litellm_params
(**overrides)
tests/unit/proxy/guardrails/test_llm_as_a_judge.py:96
↓ 7 callersMethod_make_litellm_params
(self, api_key=FAKE_API_KEY)
tests/unit/test_anthropic_skills_transformation.py:104
↓ 7 callersFunction_make_manager
(servers)
tests/unit/proxy/auth/test_mcp_ip_filtering.py:38
↓ 7 callersFunction_make_mcp_server_for_scope_filter
(server_id: str, alias: str)
tests/unit/proxy/mcp_server/test_mcp_server_tool_calls_and_headers.py:9052
↓ 7 callersFunction_make_mock_mcp_manager
Return a mock global_mcp_server_manager with a registry containing every explicit server plus simple server objects for every ID in *existing
tests/unit/proxy/management_helpers/test_object_permission_utils.py:260
↓ 7 callersMethod_make_mock_response
Create a mock httpx.Response with the given JSON body.
tests/unit/llms/github_copilot/test_github_copilot_transformation.py:460
↓ 7 callersFunction_make_model_response_with_content
(content: str)
tests/unit/proxy/guardrails/guardrail_hooks/_cisco_ai_defense_test_utils.py:29
↓ 7 callersFunction_make_openai_response_with_tool_call
(tool_name: str, arguments: dict, tool_id: str = "call_abc123")
tests/unit/proxy/guardrails/guardrail_hooks/test_compresr.py:124
↓ 7 callersFunction_make_otel
Spin up a real OTEL pipeline backed by an in-memory exporter.
tests/unit/integrations/test_otel_guardrail_violation_spans.py:154
↓ 7 callersFunction_make_owner_lookup_prisma
(rows)
tests/unit/proxy/spend_tracking/test_spend_management_endpoints.py:487
↓ 7 callersMethod_make_passthrough_server
()
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:2025
↓ 7 callersFunction_make_payload
( *, mcp_tool_name: str = "get_weather", mcp_server_name: str = "weather-server", response_cos
tests/unit/integrations/test_prometheus_mcp_tool_metrics.py:58
↓ 7 callersFunction_make_personal_key_row_for_alice
()
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:18433
↓ 7 callersFunction_make_prisma_client
A ``PrismaClient`` whose ``db`` is a real wrapper and whose alerting hook is observable.
tests/unit/proxy/db/test_prisma_planned_engine_restart.py:67
↓ 7 callersFunction_make_prisma_with_config
Build a MagicMock prisma_client with a ``db.litellm_config`` namespace. The conftest's ``mock_prisma`` fixture stubs ``litellm_configtable`` but
tests/unit/proxy/proxy_server/test_routes_anthropic_beta.py:31
↓ 7 callersFunction_make_real_managed_files_instance
Create a PROXY_LiteLLMManagedFiles with a real store_unified_file_id but an AsyncMock prisma client, so the DB write path itself can be asserted.
tests/unit/enterprise/proxy/test_managed_files_hook.py:1406
↓ 7 callersFunction_make_request
(base_url: str = "https://gateway.example.com/")
tests/unit/proxy/mcp_server/test_mcp_oauth_passthrough.py:49
↓ 7 callersFunction_make_request
Build a minimal mock Request whose query_params match *query_string*.
tests/unit/proxy/google_endpoints/test_gemini_agents_endpoints.py:35
↓ 7 callersMethod_make_response
(self, output)
tests/unit/types/llms/test_types_llms_openai.py:365
↓ 7 callersFunction_make_server
(server_id, available_on_public_internet=False)
tests/unit/proxy/auth/test_mcp_ip_filtering.py:28
↓ 7 callersMethod_make_server
(self, **kwargs)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:10442
↓ 7 callersMethod_make_server
(self, server_id: str, server_name: str, alias=None)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:10703
↓ 7 callersMethod_make_server
( self, static_headers: Optional[Dict[str, str]] = None, extra_headers_config: Optiona
tests/unit/proxy/mcp_server/test_mcp_hook_extra_headers.py:480
↓ 7 callersMethod_make_session
(self, mock_session_cls, initialize)
tests/unit/mcp_client/test_mcp_client.py:777
← previousnext →10,101–10,200 of 202,479, ranked by callers