MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 28 callersFunction_responses_body
( model: str, marker: str, tools: Sequence[Mapping[str, JsonValue]], stream: bool )
tests/integration/providers/test_responses_bridge_tool_search_wire.py:347
↓ 28 callersFunction_serve_responses
( respx_mock: respx.MockRouter, monkeypatch: pytest.MonkeyPatch, responses: Sequence[httpx.Respons
tests/unit/responses/mcp/test_aresponses_api_with_mcp.py:1642
↓ 28 callersMethod_set_oauth_discovery_deferred
(self, server_id: str, discovery_deferred: bool)
litellm/proxy/mcp_server/mcp_server_manager.py:2112
↓ 28 callersFunction_store
( rows: _FakeRows, transport: _FakeTransport, *, client_config: Callable[[], SSOClientConfig |
tests/unit/proxy/mcp_server/outbound_credentials/test_sso_assertion_refresher.py:145
↓ 28 callersFunction_stored
A row as the SSO callback wrote it: ``expires_in`` seconds from now, mirroring the id_token.
tests/unit/proxy/mcp_server/outbound_credentials/test_sso_assertion_refresher.py:76
↓ 28 callersMethod_sync
(self, listing, codex_home, base_url="http://localhost:4000/", run=None, groups=(), model_info=None)
tests/unit/proxy/client/cli/test_agents.py:748
↓ 28 callersFunction_team_row
()
tests/unit/proxy/proxy_server/test_team_model_name_translation.py:36
↓ 28 callersFunction_text_deltas
(events: List[dict])
tests/unit/llms/anthropic/messages/adapters/test_streaming_iterator_first_delta.py:106
↓ 28 callersFunctionapply_clear_tool_uses_20250919
Apply clear_tool_uses to an edit ``check_clear_tool_uses_spec`` returned; return (messages, AppliedEdit or None). Like the API, it reads only the
litellm/llms/anthropic/messages/context_management/editors/clear_tool_uses.py:355
↓ 28 callersFunctionassert_charged_exactly
(read_spend: Callable[[], float], expected: float)
tests/integration/spend/_background_responses.py:263
↓ 28 callersMethodasync_service_failure_hook
Arize is used mainly for LLM I/O tracing, sending router+caching metrics adds bloat to arize logs
litellm/integrations/arize/arize.py:239
↓ 28 callersFunctionbuild
(make_core: MakeCore, **arguments: object)
tests/unit/test_router/core/test_streaming_characterization_chat.py:46
↓ 28 callersFunctionbuild_model_max_budget_usage
Current-window spend per configured budget model, as `/key/info` and `/user/info` report it. `cache` must be the DualCache the limiter writes the
litellm/proxy/hooks/model_max_budget_limiter.py:629
↓ 28 callersFunctioncall
(url: str, body: bytes = BODY, headers: dict[str, str] = HEADERS)
tests/code_coverage_tests/test_provider_cache.py:238
↓ 28 callersFunctioncall_id
(city: str)
tests/integration/providers/_cache_control_marks_support.py:65
↓ 28 callersFunctioncapture
(py: Python<'_>)
litellm-rust/crates/python-bridge/src/logger/mod.rs:157
↓ 28 callersMethodcheck_and_create_cache
Receives - messages: List of dict - messages in the openai format Returns - messages - List[dict] - filtered list of
litellm/llms/vertex_ai/context_caching/vertex_ai_context_caching.py:412
↓ 28 callersFunctionchunks_of
(text: str)
tests/integration/_support/anthropic_thinking.py:165
↓ 28 callersMethodcleanup_old_spend_logs
The scheduled retention run: every age rule, plus the size rule when one cron drives both. If pod_lock_manager is available, ensures
litellm/proxy/db/db_transaction_queue/spend_log_cleanup.py:1423
↓ 28 callersFunctionconverse_frames
A Converse stream with one text content block per entry of ``blocks``, one delta frame per string.
tests/integration/observability/test_bedrock_converse_stream_post_call_guardrail.py:80
↓ 28 callersFunctioncreate
(gateway: Gateway, body: Mapping[str, JsonValue], key: str | None = None)
tests/integration/providers/_dashscope_video_support.py:197
↓ 28 callersMethoddecode_responses_api_response_id
Decode the responses_api_response_id Returns: DecodedResponseId: Structured tuple with custom_llm_provider, model_id, an
litellm/responses/utils.py:739
↓ 28 callersMethodexecute
(self, _operation: ListToolsRequest, _context: OperationContext)
tests/unit/proxy/mcp_server/test_subscriptions.py:53
↓ 28 callersMethodfind_many
( self, take: int | None = None, skip: int | None = None, where: Mapping[str,
litellm/repositories/prisma_protocols.py:42
↓ 28 callersMethodforce_flush
(self, timeout_millis: int = 30_000)
tests/unit/integrations/langfuse/test_langfuse_sdk.py:658
↓ 28 callersFunctiongetGatewayBaseUrl
()
ui/litellm-dashboard/src/components/networking.tsx:248
↓ 28 callersMethodget_cache_key
Get the cache key for the given arguments. Args: **kwargs: kwargs to litellm.completion() or embedding() Return
litellm/caching/caching.py:410
↓ 28 callersMethodget_custom_loggers_for_type
Get all custom loggers that are instances of the given class type
litellm/litellm_core_utils/logging_callback_manager.py:466
↓ 28 callersMethodget_deployment_credentials_with_provider
( self, model_id: str, team_id: str | None = None )
litellm/router_deprecated.py:630
↓ 28 callersFunctionget_management_object_ttl
In-memory TTL for management-object cache writes (keys, teams, users, budgets, ...). Honors ``general_settings.user_api_key_cache_ttl``, whi
litellm/proxy/common_utils/user_api_key_cache.py:593
↓ 28 callersFunctionget_model_cost_map
Public entry point — returns the model cost map dict. 1. If ``LITELLM_LOCAL_MODEL_COST_MAP`` is set or this is a ``lite`` / ``litellm
litellm/litellm_core_utils/get_model_cost_map.py:740
↓ 28 callersFunctionget_supported_openai_params
Returns the supported openai params for a given model + provider Example: ``` get_supported_openai_params(model="anthropic.claude-3"
litellm/litellm_core_utils/get_supported_openai_params.py:10
↓ 28 callersFunctionget_token_type_cost_breakdown
Provider-agnostic cost of reasoning and cache tokens, derived from the usage object and model pricing alone. This works for every provid
litellm/litellm_core_utils/llm_cost_calc/utils.py:1965
↓ 28 callersFunctionguard
(**kwargs: object)
tests/unit/test_router/core/test_gaps_l5600.py:355
↓ 28 callersFunctionhash_password
Hash a password using scrypt with a random salt, or PBKDF2 in FIPS mode.
litellm/proxy/utils.py:8492
↓ 28 callersFunctionheaders
(response: object)
tests/unit/test_router/core/fallbacks_helpers.py:39
↓ 28 callersFunctioninitialize_standard_callback_dynamic_params
Initialize the standard callback dynamic params from the kwargs checks supported request callback params in kwargs and sets the correspondin
litellm/litellm_core_utils/initialize_dynamic_callback_params.py:197
↓ 28 callersFunctionis_budget_block
True if the call was rejected for being over budget (vs a provider error).
tests/e2e/quota_management/budgets/budget_client.py:212
↓ 28 callersFunctionis_str_keyed_mapping
( value: object, )
litellm/llms/azure/ptu_capacity.py:92
↓ 28 callersMethodload_auth
( self, credentials: VERTEX_CREDENTIALS_TYPES | None, project_id: str | None, )
litellm/llms/vertex_ai/vertex_llm_base.py:164
↓ 28 callersMethodmap_extra_body_params
( self, optional_params: Mapping[str, object], model: str )
litellm/llms/fireworks_ai/chat/transformation.py:374
↓ 28 callersMethodnow
(self)
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:92
↓ 28 callersMethodreadline
(self, size: int | None = -1, /)
tests/integration/_support/wire.py:112
↓ 28 callersMethodresolve
(self, target: CallTarget)
scripts/check_test_quality.py:316
↓ 28 callersFunctionscripted_upstream
( scenario: Scenario, response: RoutedResponse | SseResponse, *, model_info: Mapping[str, Json
tests/integration/spend/_background_responses.py:132
↓ 28 callersMethodset
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 28 callersMethodset
(self, tenant: str, session_id: str, model: str, ttl_seconds: float)
tests/unit/proxy/hooks/test_sensitive_data_routing.py:63
↓ 28 callersMethodsign
(&self, request: &Request)
litellm-rust/crates/http/src/outbound.rs:73
↓ 28 callersMethodsignature
(cause: impl std::error::Error + Send + Sync + 'static)
litellm-rust/crates/http/src/error.rs:220
↓ 28 callersFunctionspend_marker
(marker: str)
tests/integration/authorization/_hidden_alias_budget.py:98
↓ 28 callersMethodsubscribe
(e)
litellm/proxy/_experimental/out/_next/static/chunks/3lb5gjzjxjxem.js:1
↓ 28 callersMethodtransform_audio_transcription_request
(self, model, audio_file, optional_params, litellm_params)
tests/unit/llms/custom_httpx/test_llm_http_handler.py:3003
↓ 28 callersMethodtransform_realtime_request
( self, message: str, model: str, session_configuration_request: str | None =
litellm/llms/gemini/realtime/transformation.py:810
↓ 28 callersMethodupload
(self, key: str, filename: str)
tests/integration/management/test_vector_store_file_list_managed_ids.py:392
↓ 28 callersFunctionuseComponent
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 28 callersMethodvalue
(&self)
litellm-rust/crates/auth-types/src/lib.rs:32
↓ 28 callersFunctionwalk_user_text
Rewrite every text fragment in place via ``visit``. Mutates ``data["messages"]`` and ``data["input"]`` (including tool payloads), ``data["system"
litellm/proxy/guardrails/_content_utils.py:339
↓ 27 callersMethodPOST
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 27 callersFunctionW
({open:e,onCancel:t,selectedUsers:r,possibleUIRoles:i,accessToken:n,onSuccess:d,teams:o,userRole:c,userModels:
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 27 callersMethod_PROXY_track_cost_callback
( self, kwargs, # kwargs to completion completion_response: litellm.ModelResponse | o
litellm/proxy/hooks/proxy_track_cost_callback.py:765
↓ 27 callersFunction_anthropic_deployment
(scenario: Scenario, wire: Wire, **fields: JsonValue)
tests/integration/providers/test_cache_control_tool_call_marks_wire.py:107
↓ 27 callersFunction_anthropic_deployment
(scenario: Scenario, wire: Wire, *, inject: bool = False)
tests/integration/providers/test_responses_bridge_message_cache_control_wire.py:157
↓ 27 callersFunction_assert_answered
(outcome: _Outcome)
tests/integration/providers/test_bedrock_kimi_k3_cache_point_wire.py:559
↓ 27 callersFunction_assert_instructed_once
(prompt: str, *tool_names: str)
tests/integration/providers/test_ollama_prompt_tools_wire.py:149
↓ 27 callersFunction_build_event_stream_frame
(event_type: str, payload: dict)
tests/unit/llms/bedrock/passthrough/guardrail_translation/test_handler.py:836
↓ 27 callersFunction_build_key_filter_conditions
Build filter conditions for key listing. Visibility rules: - Users always see their own keys (user_id match) - Team admins see ALL keys f
litellm/proxy/management_endpoints/key_management_endpoints.py:7641
↓ 27 callersFunction_calls
(guardrail)
tests/unit/proxy/guardrails/guardrail_hooks/akto/test_akto.py:514
↓ 27 callersFunction_catalog_database
(monkeypatch, read_rows, read_revision=None)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:17936
↓ 27 callersFunction_count
(gateway: Gateway, body: Mapping[str, JsonValue])
tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py:299
↓ 27 callersFunction_day
A UTC date relative to DAY, which is the last day the backfill may price.
tests/unit/proxy/spend_tracking/test_ptu_flat_cost_rollup.py:1123
↓ 27 callersFunction_drain_surface_hook
(guardrail, chunks, request_data=None)
tests/unit/proxy/guardrails/guardrail_hooks/test_model_armor.py:3935
↓ 27 callersFunction_fail
One wrong guess; returns the status code it was answered with.
tests/unit/proxy/auth/test_login_utils.py:707
↓ 27 callersFunction_get
(query: str = "", **kwargs)
tests/unit/proxy/public_endpoints/public_v1/test_model_hub.py:60
↓ 27 callersFunction_mock_allowed_response
()
tests/unit/proxy/guardrails/guardrail_hooks/akto/test_akto.py:89
↓ 27 callersFunction_model_list
()
tests/unit/test_router/core/test_registry_changesets.py:27
↓ 27 callersFunction_patches
(prisma: MagicMock, handler: InMemoryGuardrailHandler)
tests/unit/proxy/guardrails/test_usage_endpoints.py:124
↓ 27 callersFunction_paths
(wire: Wire)
tests/integration/providers/test_anthropic_refusal_stop_details_wire.py:513
↓ 27 callersFunction_prisma
( *, find_many=None, find_unique=None, metrics=None, index_find_many=None, units=None,
tests/unit/proxy/guardrails/test_usage_endpoints.py:104
↓ 27 callersFunction_relay_through_post_call_guardrail
( chunks: tuple[bytes, ...], guardrail: CustomGuardrail, monkeypatch: pytest.MonkeyPatch, hold
tests/unit/llms/bedrock/passthrough/guardrail_translation/test_handler.py:2557
↓ 27 callersFunction_renewal
(id_token: str, refresh_token: str | None = None)
tests/unit/proxy/mcp_server/outbound_credentials/test_sso_assertion_refresher.py:140
↓ 27 callersFunction_request_body
(route: respx.Route)
tests/unit/llms/base_llm/chat/test_provider_chat_translation.py:613
↓ 27 callersFunction_resolve_jwt_to_virtual_key
Returns: - ``UserAPIKeyAuth``: a resolved virtual key (cache hit or DB hit). The caller may use this directly; JWT policy has been
litellm/proxy/auth/user_api_key_auth.py:1879
↓ 27 callersFunction_restamp_streaming_chunk_model
( *, chunk: object, requested_model_from_client: str, request_data: dict, model_mismatch_l
litellm/proxy/proxy_server.py:10272
↓ 27 callersMethod_run_check
(self, server: MCPServer, name: str, arguments: dict[str, Any] | None = None)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:13617
↓ 27 callersMethod_send_to_backend
Send a message to the backend WebSocket. If a provider_config is set the message is first passed through transform_realtime_request s
litellm/litellm_core_utils/realtime_streaming.py:982
↓ 27 callersFunction_served
(wire: Wire)
tests/integration/compatibility/test_openai_sdk_client_paths.py:126
↓ 27 callersFunction_should_cooldown_deployment
Helper that decides if a deployment should be put in cooldown Returns True if the deployment should be put in cooldown Returns False if
litellm/router_utils/cooldown_handlers.py:479
↓ 27 callersFunction_static_guardrail
()
tests/unit/proxy/guardrails/guardrail_hooks/test_ovalix.py:684
↓ 27 callersFunction_surface_guardrail
(**kwargs)
tests/unit/proxy/guardrails/guardrail_hooks/test_model_armor.py:3868
↓ 27 callersFunction_terminal_response
(status: str = "completed")
tests/unit/proxy/common_utils/test_check_responses_cost.py:159
↓ 27 callersMethod_transform_request_helper
( self, model: str, system_content_blocks: list[SystemContentBlock], optional_
litellm/llms/bedrock/chat/converse_transformation.py:2152
↓ 27 callersFunction_two
(**params: object)
tests/unit/test_router/core/test_selection_characterization_strategies.py:35
↓ 27 callersFunction_user_with_metadata
(metadata)
tests/unit/proxy/management_endpoints/scim/test_scim_patch_user.py:341
↓ 27 callersFunction_vendor
(violation: float = 0.0)
tests/integration/observability/test_grayswan_wire.py:109
↓ 27 callersMethodadd
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 27 callersFunctionadd_server_prefix_to_name
Add server name prefix to any MCP resource name.
litellm/proxy/mcp_server/utils.py:322
↓ 27 callersMethodarerank
(self, *args: object, **kwargs: object)
litellm/router_rust/core.py:2604
↓ 27 callersFunctionassert_answered
(outcome: Outcome, marker: str)
tests/integration/providers/_mantle_gpt_prompt_cache_support.py:661
↓ 27 callersFunctionassert_served
(answer: Answer, marker: str)
tests/integration/routing/test_priority_scheduler_queue_cleanup.py:340
↓ 27 callersMethodasync_pre_call_hook
(self, user_api_key_dict, cache, data, call_type)
tests/unit/proxy/guardrails/test_guardrail_load_balancing.py:29
← previousnext →1,801–1,900 of 202,479, ranked by callers