MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 15 callersMethodsign_request
Authenticate the MCP request. CUSTOM_JWT gateways: attach the caller's OAuth2 bearer token (api_key or AGENTCORE_GATEWAY_TOK
litellm/llms/bedrock/search/transformation.py:256
↓ 15 callersFunctionsnapshot_tuning_baselines
One immutable first-observation baseline for every heuristic-v1 complexity router.
litellm/router_strategy/auto_router/auto_router_tuning_baseline.py:113
↓ 15 callersFunctionspend_logs_of_key
( api_key: str, rows: Sequence[SpendLogRow], *, database_url: str | None = None )
tests/integration/_support/daily_activity.py:187
↓ 15 callersFunctionsr
litellm/proxy/_experimental/out/_next/static/chunks/2k-fkubkt19cc.js:8
↓ 15 callersMethodstart
Start the logging worker. Idempotent - safe to call multiple times.
litellm/litellm_core_utils/logging_worker.py:187
↓ 15 callersMethodstart
(self)
litellm/proxy/common_utils/config_sync_pubsub.py:277
↓ 15 callersMethodstart
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 15 callersMethodstart_shutdown
Mark the worker as draining. Idempotent — repeated calls (e.g. SIGTERM followed by a preStop hit on /health/drain) do not reset the c
litellm/proxy/shutdown/graceful_shutdown_manager.py:80
↓ 15 callersMethodstep
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 15 callersMethodstock
(self, client_version: str)
litellm/proxy/common_utils/codex_catalog_source.py:120
↓ 15 callersMethodstored
(self)
tests/integration/observability/_azure_storage_support.py:169
↓ 15 callersMethodstream
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 15 callersFunctiont
(t,n,r,l,a)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 15 callersFunctiontextControl
(control: MountedFieldControlProps)
ui/litellm-dashboard/src/app/(dashboard)/mcp-servers/_components/mcpFieldRules.ts:19
↓ 15 callersMethodthen
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 15 callersFunctiontool
()
tests/unit/proxy/mcp_server/test_operations.py:166
↓ 15 callersMethodtouch
(self, unified_batch_id: str, updated_by: str | None)
litellm/repositories/managed_batch_repository.py:39
↓ 15 callersFunctiontrack_audit_task
(task: asyncio.Task[_T])
litellm/proxy/management_helpers/audit_logs.py:176
↓ 15 callersMethodtransform_compact_response_api_request
Transform the compact response API request into a URL and data OpenAI API expects the following request - POST /v1/responses
litellm/llms/openai/responses/transformation.py:1400
↓ 15 callersMethodtransform_delete_file_response
( self, raw_response: httpx.Response, logging_obj: LiteLLMLoggingObj, litellm_
litellm/llms/xai/files/transformation.py:194
↓ 15 callersMethodtransform_image_edit_request
( self, model: str, prompt: str | None, image: FileTypes | None, image
litellm/llms/bedrock/image_edit/amazon_nova_canvas_image_edit_transformation.py:319
↓ 15 callersMethodtransform_session_update_event
Transform session.update event to Bedrock session configuration. Args: json_message: OpenAI session.update message
litellm/llms/bedrock/realtime/transformation.py:364
↓ 15 callersMethodttl
(self, name: str)
tests/unit/caching/test_redis_cache.py:1462
↓ 15 callersFunctionu
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 15 callersFunctionundiscoverable_model_names
( model_names: Iterable[str], llm_router: Router | None, user_api_key_dict: UserAPIKeyAuth, te
litellm/proxy/common_utils/discoverable_model_filter.py:88
↓ 15 callersMethoduniform
(self, a: float, b: float)
tests/unit/proxy/common_utils/test_config_sync_pubsub.py:353
↓ 15 callersMethodunwrap_encrypted_content_with_model_id
Unwrap encrypted_content to extract model_id and original content. Returns: Tuple of (model_id, original_encrypted_content).
litellm/responses/utils.py:540
↓ 15 callersMethodupdate_from_kwargs
( self, kwargs: dict[str, object], litellm_params: dict[str, object] | None = None,
litellm/rust_bridge/host/callbacks_legacy_python.py:120
↓ 15 callersMethodupdate_responses_api_response_id_with_model_id
( responses_api_response: ResponsesAPIResponse, custom_llm_provider: str | None, litel
litellm/responses/utils.py:412
↓ 15 callersMethodupdate_state
Update the polling state in Redis Uses OpenAI Response object format with native status types: https://platform.openai.com/d
litellm/proxy/response_polling/polling_handler.py:99
↓ 15 callersFunctionupstream
(responses: impl IntoIterator<Item = ResponseTemplate>)
litellm-rust/crates/inference-responses/tests/support/mod.rs:30
↓ 15 callersFunctionuseCan
(capability: Capability)
ui/litellm-dashboard/src/app/(dashboard)/hooks/useCan.ts:8
↓ 15 callersMethodvalidate_anthropic_messages_environment
OPTIONAL Validate the environment for the request
litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/messages/transformation.py:85
↓ 15 callersMethodvalidate_environment
( self, *args, **kwargs )
litellm/llms/base.py:79
↓ 15 callersFunctionvirtual_key_max_budget_check
Raises: BudgetExceededError if the token is over it's max budget. Triggers a budget alert if the token is over it's max budget.
litellm/proxy/auth/auth_checks.py:6723
↓ 15 callersFunctionw
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 15 callersFunctionwait_for_worker_readiness
( gateway: Gateway, group: str, deployments: int, workers: int, )
tests/integration/_support/worker_readiness.py:23
↓ 15 callersFunctionweighted_pair
``d1`` takes every pick while it is not cooling down, and one failure cools it.
tests/unit/test_router/core/test_request_scoped_outcomes.py:117
↓ 14 callersFunctionA
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 14 callersFunctionE
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 14 callersFunctionH
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 14 callersMethod__init__
(self)
tests/unit/litellm_core_utils/test_litellm_logging.py:11201
↓ 14 callersMethod__init__
(self)
tests/unit/proxy/guardrails/guardrail_hooks/unified_guardrails/test_unified_guardrail.py:72
↓ 14 callersMethod_additive
(monkeypatch)
tests/unit/integrations/otel/test_otel_v2_destinations.py:2525
↓ 14 callersFunction_admin_auth
()
tests/unit/proxy/management_endpoints/test_cache_settings_endpoints.py:489
↓ 14 callersFunction_app
( monkeypatch: pytest.MonkeyPatch, cache: DualCache, *, caller: UserAPIKeyAuth | None = None,
tests/unit/proxy/management_endpoints/test_prompt_cache_prediction.py:201
↓ 14 callersMethod_apply_guardrail
(**kwargs)
tests/unit/proxy/test_common_request_processing.py:6707
↓ 14 callersFunction_assert_answered
(response: httpx.Response, model: str, route: _Route = _SYSTEMONE)
tests/integration/providers/test_strands_decider_agentcore_wire.py:369
↓ 14 callersFunction_attachment_guardrail
(**kwargs)
tests/unit/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py:6247
↓ 14 callersFunction_await_spend_row
(call_id: str)
tests/integration/observability/test_langfuse_delivery.py:842
↓ 14 callersFunction_bare
(model: str)
tests/integration/providers/test_vertex_partner_count_tokens_wire.py:206
↓ 14 callersFunction_bare
()
tests/integration/routing/test_declared_provider_bare_model_routes.py:53
↓ 14 callersFunction_base
(gateway: Gateway)
tests/integration/mcp/test_mcp_oauth_flows.py:53
↓ 14 callersMethod_bearer_scope
(token: str)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:2658
↓ 14 callersFunction_build_hold_back_iterator
( stream: MockAsyncStream, mock_handler: MagicMock, ping_interval_seconds: float = 15.0, serve
tests/unit/llms/anthropic/messages/native/test_agentic_streaming_iterator.py:264
↓ 14 callersFunction_build_model_response
()
tests/unit/llms/test_predibase_transformation.py:16
↓ 14 callersMethod_build_standard_logging_payload
(self, trace_id: str | None = None)
tests/unit/integrations/test_langfuse.py:449
↓ 14 callersFunction_call_prepare
Drive ``_prepare_completion_kwargs`` with the minimum scaffolding needed. ``output_format`` is a top-level parameter on the function, so cal
tests/unit/llms/anthropic/messages/adapters/test_handler_output_config_passthrough.py:52
↓ 14 callersFunction_caller
(rig: _Rig, scenario: Scenario, grant: str = "team")
tests/integration/authorization/test_agent_denial_logging.py:280
↓ 14 callersFunction_canonical_path
Normalise a passthrough route to a bare /v1/... path for map lookup. Examples: /openai_passthrough/v1/files -> /v1/files /open
litellm/proxy/pass_through_endpoints/managed_id_rewriter.py:276
↓ 14 callersFunction_capture_cost_calls
(monkeypatch, prompt_cost=0.5, completion_cost=0.25)
tests/unit/batches/test_batch_utils.py:2199
↓ 14 callersMethod_capture_translation_output_audio
(self, event_obj: Mapping[str, object])
litellm/litellm_core_utils/realtime_streaming.py:846
↓ 14 callersFunction_chat
(gateway: Gateway, model: str, **extra: JsonValue)
tests/integration/providers/test_custom_prompt_template_wire.py:175
↓ 14 callersFunction_chat
(candidate: Gateway, model: str, token: str)
tests/integration/authorization/test_jwt_auto_register_map_existing_key.py:88
↓ 14 callersFunction_chat
( rig: Rig, key: str, baggage: str | None, *, model: str | None = None, fields: Mappin
tests/integration/spend/test_baggage_tag_mappings.py:370
↓ 14 callersFunction_chat_body
( model: str, marker: str, *, cache_control: Mapping[str, JsonValue] = NO_CACHE, messages:
tests/integration/providers/test_anthropic_thinking_signature_stream_wire.py:146
↓ 14 callersFunction_chat_response
(content: str)
tests/unit/integrations/test_langfuse_otel.py:1108
↓ 14 callersFunction_check_team_member_budget
Check if team member is over their max budget within the team.
litellm/proxy/auth/auth_checks.py:7079
↓ 14 callersFunction_cleanup
()
tests/unit/proxy/management_endpoints/test_config_override_endpoints.py:78
↓ 14 callersFunction_client_turns
(update: dict[str, JsonValue], labels: tuple[str, ...])
tests/integration/providers/test_realtime_unguarded_voice_turns.py:308
↓ 14 callersFunction_client_websocket
(receive)
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:7582
↓ 14 callersFunction_collect_stream
(is_async: bool, hops: Sequence[httpx.Response], sent: list[dict[str, object]])
tests/unit/llms/vertex_ai/gemini/test_long_decode.py:752
↓ 14 callersFunction_common_checks
( model: str | list[str], user: LiteLLM_UserTable | None, token: UserAPIKeyAuth, fallbacks: tu
tests/unit/proxy/auth/test_personal_key_team_model_access.py:55
↓ 14 callersFunction_completion
()
tests/unit/proxy/roi_calculator/test_sync.py:224
↓ 14 callersFunction_config
( directory: Path, claim_field: str, *, behavior: Literal["auto_register", "link_only", "rejec
tests/integration/authorization/test_jwt_auto_register_map_existing_key.py:36
↓ 14 callersFunction_config
(**overrides: object)
tests/unit/proxy/agent_endpoints/test_kill_switch.py:66
↓ 14 callersFunction_config
(**overrides: object)
tests/unit/proxy/common_utils/test_cache_aware_routing.py:98
↓ 14 callersFunction_confusion_matrix
Run all cases, print confusion matrix, save results JSON.
litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/guardrail_benchmarks/test_eval.py:152
↓ 14 callersMethod_core_get_model_from_alias
(self, model: str)
litellm/router_rust/surface/registry.py:1853
↓ 14 callersFunction_count_content_list
Recursively count tokens from a list of content blocks.
litellm/litellm_core_utils/token_counter.py:1877
↓ 14 callersFunction_create_metadata
(**extra)
tests/unit/interactions/test_background_cost_polling.py:854
↓ 14 callersMethod_create_mock_logging_obj
Create a mock logging object
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_openai_passthrough_logging_handler.py:63
↓ 14 callersFunction_create_test_router
()
tests/unit/router_strategy/test_lar1_routing.py:52
↓ 14 callersFunction_deferred_tools_with_server_tool_search
()
tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py:1641
↓ 14 callersMethod_delete_deployment
(Helper function of add deployment) -> combined to reduce prisma db calls - Create all up list of model id's (db + config) -
litellm/proxy/proxy_server.py:7883
↓ 14 callersFunction_deployment
( gateway: Gateway, scenario: Scenario, scenario_id: str, *, model: str = f"openai/{TRANSC
tests/integration/providers/test_openai_realtime_transcription_url.py:135
↓ 14 callersFunction_deployment
(gateway: Gateway, scenario: Scenario, api_base: str, **parameters: JsonValue)
tests/integration/providers/test_vertex_gemini_count_tokens_wire.py:72
↓ 14 callersFunction_deployment
( scenario: Scenario, params: Mapping[str, JsonValue], model_info: Mapping[str, JsonValue] | None
tests/integration/routing/test_model_capability_flags.py:283
↓ 14 callersFunction_deployments_visible
(gateway: Gateway, names: Sequence[str])
tests/integration/management/test_credential_federation_values.py:260
↓ 14 callersFunction_description
()
tests/integration/providers/test_gemini_anyof_null_branches_wire.py:213
↓ 14 callersFunction_directions_for_audit_leg
(base_default: tuple[Direction, ...], scope: str | None)
tests/integration/observability/_logging_only_scope_support.py:255
↓ 14 callersFunction_drained
(rig: Rig)
tests/integration/compatibility/test_fine_tuning_jobs.py:211
↓ 14 callersFunction_drive
( candidate: Gateway, callback_vars: Mapping[str, JsonValue], callback_name: str = "langfuse_otel"
tests/integration/observability/test_otel_excluded_services.py:130
↓ 14 callersFunction_drive_success
Construct a metrics-on logger, optionally populate callback_settings AFTER construction (mirroring the proxy ordering), run the real success hook.
tests/unit/integrations/otel/test_otel_v2_metrics.py:160
↓ 14 callersMethod_emit_once
Return True the first time this handler is asked to emit a span for the given (handler, scope) on this kwargs; False on repeats. Used
litellm/integrations/opentelemetry.py:1331
↓ 14 callersMethod_enhance_usage_with_perplexity_fields
Extract citation tokens and search queries from Perplexity API response and add them to the usage object using standard LiteLLM field
litellm/llms/perplexity/chat/transformation.py:123
↓ 14 callersFunction_error_message
(text: str)
tests/integration/providers/test_device_code_login_guard_wire.py:339
↓ 14 callersFunction_events_sent_to_client
(streaming: RealTimeStreaming)
tests/unit/litellm_core_utils/test_realtime_streaming.py:3010
↓ 14 callersFunction_expand_model_aliases
Expand alias rows into top-level entries that share their owner's ``AliasedCostEntry``. A row whose ``alias_of`` names another row is served
litellm/litellm_core_utils/get_model_cost_map.py:581
↓ 14 callersMethod_extract_assistant_text_from_response
(response: object)
litellm/proxy/guardrails/guardrail_hooks/xecguard/xecguard.py:474
← previousnext →4,201–4,300 of 202,479, ranked by callers