MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 11 callersFunctionE
(s,o,i)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 11 callersFunctionK
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 11 callersFunctionNs
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:333
↓ 11 callersFunctionP
(e,t,n=new WeakMap)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 11 callersFunctionR
(s,o,u,_,w)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 11 callersFunctionResourceLiteLLMTeam
()
terraform/provider/litellm/resource_team.go:24
↓ 11 callersFunction_
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:7
↓ 11 callersMethod__init__
(self)
tests/unit/integrations/test_custom_guardrail.py:3682
↓ 11 callersFunction_accepted
(response: httpx.Response)
tests/integration/management/test_batch_file_usage_caps.py:143
↓ 11 callersFunction_adaptive
Registries hold tag-scoped strategy lists; these tests use a single tagless entry.
tests/unit/router_strategy/adaptive_router/test_router_dispatch.py:24
↓ 11 callersFunction_admin_user
()
tests/unit/proxy/pass_through_endpoints/test_managed_id_rewriter.py:352
↓ 11 callersFunction_ai_studio_deployment
(scenario: Scenario, api_base: str, **parameters: JsonValue)
tests/integration/providers/test_vertex_gemini_count_tokens_wire.py:228
↓ 11 callersFunction_answered
(response: httpx.Response, marker: str)
tests/integration/providers/test_responses_bridge_verbosity_wire.py:131
↓ 11 callersFunction_anthropic_body
(model: str = _ANTHROPIC_MODEL, msg_id: str = "msg_1")
tests/unit/llms/anthropic/messages/native/test_anthropic_messages_router.py:45
↓ 11 callersFunction_anthropic_call
(call_id: str, name: str, arguments: dict, *, is_error: bool)
tests/unit/router_strategy/test_stall_detector.py:9
↓ 11 callersFunction_anthropic_tool_result_turn
(blocks_by_tool_use_id)
tests/unit/llms/anthropic/messages/adapters/test_anthropic_messages_adapters_transformation.py:4642
↓ 11 callersFunction_as_object_list
(value: object | None)
litellm/integrations/anthropic_cache_control_hook.py:577
↓ 11 callersMethod_as_proxy_admin
(self, monkeypatch)
tests/unit/proxy/ui_crud_endpoints/test_proxy_setting_endpoints.py:4228
↓ 11 callersFunction_assert_classified
(headers: Mapping[str, str], *, router: str)
tests/integration/routing/test_complexity_router_databricks_classifier.py:227
↓ 11 callersFunction_assert_guardrail_request
( request: Request, text: str, model: str, key: str, *, key_alias: str | None = None,
tests/integration/management/test_policy_attachment_runtime.py:176
↓ 11 callersFunction_assert_labeled
(rig: _Rig, deployment: _Deployment)
tests/integration/observability/test_prometheus_deployment_failure_api_provider.py:227
↓ 11 callersFunction_assert_operator_span
(rig: Rig, response_id: str, marker: str)
tests/integration/observability/test_signoz_delivery.py:430
↓ 11 callersFunction_assert_success_row
( row: Mapping[str, JsonValue], model_group: str, backend: str, call_type: str, cost: float )
tests/integration/providers/test_bedrock_mantle_claude_chat_wire.py:222
↓ 11 callersFunction_async_iter
(items)
tests/unit/proxy/proxy_server/test_streaming_helpers.py:107
↓ 11 callersFunction_attach_mock_success_dispatch
Match production entrypoint: ``_run_deferred_stream_guardrails`` uses dispatch.
tests/unit/proxy/guardrails/test_deferred_guardrail_logging.py:47
↓ 11 callersFunction_attr
(span, key)
tests/unit/integrations/test_otel_guardrail_violation_spans.py:177
↓ 11 callersMethod_auth_401
(self)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:8227
↓ 11 callersFunction_authorize
( client_id, session_user_id, redirect_uri=REDIRECT_URI, challenge=CODE_CHALLENGE, method=
tests/unit/proxy/mcp_server/test_gateway_dcr_flow.py:272
↓ 11 callersFunction_avertex_search_file_ids
( peer: TlsPeer, search_url: str | None = None, ssl_verify: ssl.SSLContext | None = None, extr
tests/integration/sdk/test_http2_wire.py:303
↓ 11 callersFunction_await_db_span
(sink_url: str, trace_id: str | None, needle: str, seconds: float = 40, since: int = 0)
tests/integration/observability/test_otel_excluded_services.py:215
↓ 11 callersFunction_batch_cost_result
Build the BatchCostUsageResult calculate_batch_cost_and_usage now returns, for mocking it in tests that only care about cost/usage/models.
tests/unit/proxy/common_utils/test_check_batch_cost.py:73
↓ 11 callersFunction_batches_body_is_safe
(body: dict[str, object], general_settings: dict[str, object])
tests/unit/proxy/auth/test_auth_utils.py:5614
↓ 11 callersFunction_bearer
(token: str)
tests/integration/mcp/test_mcp_toolsets.py:231
↓ 11 callersFunction_benchmark_rows
( db, start: datetime, end: datetime, key: str | None = None, user_id: str | None = None )
tests/integration/spend/test_autorouter_session_rollup.py:130
↓ 11 callersFunction_bill_through_a_priced_deployment
( read: ResponsesAPIResponse, litellm_params: Mapping[str, object] = _PRICED_LITELLM_PARAMS, model
tests/unit/proxy/common_utils/test_check_responses_cost.py:1828
↓ 11 callersFunction_body
( scenario: str, marker: str, guardrails: Sequence[str], *directives: str, **extra: JsonValue )
tests/integration/streaming/test_chat_stream_guardrail_error_events.py:224
↓ 11 callersFunction_body
(text: str = "Stable cached context")
tests/unit/proxy/common_utils/test_cache_aware_routing.py:46
↓ 11 callersMethod_build_langfuse_kwargs
(self, standard_logging_payload)
tests/unit/integrations/test_langfuse.py:486
↓ 11 callersFunction_build_oauth_authorization_server_response
Build OAuth authorization server metadata response (gateway-as-AS shape).
litellm/proxy/mcp_server/discoverable_endpoints.py:3309
↓ 11 callersFunction_build_prisma_mock
(db_batch_object=None)
tests/unit/enterprise/proxy/test_batch_update_db_managed_output_file_id.py:49
↓ 11 callersFunction_build_ui_spend_logs_response
Build the paginated response for the UI spend-logs endpoint. When ``enrich_session_counts`` is ``True`` (the default for the v1/UI endpo
litellm/proxy/spend_tracking/spend_management_endpoints.py:4546
↓ 11 callersMethod_build_user_agent
Build the User-Agent string for Databricks API calls. If a custom user agent is provided, the partner name (part before /) i
litellm/llms/databricks/common_utils.py:229
↓ 11 callersFunction_call
( target: Router | None, logging_obj: Logging, *, trusted: bool = True, messages: str = _M
tests/unit/proxy/hooks/test_autorouter_baseline_cache.py:168
↓ 11 callersFunction_call
(core: RouterCore, endpoint: str, request: Mapping[str, object])
tests/unit/test_router/core/test_endpoints_characterization_generic.py:42
↓ 11 callersFunction_call_id
()
tests/integration/providers/test_malformed_tools_wire.py:564
↓ 11 callersFunction_calls_with
(wire: Wire, marker: str)
tests/integration/streaming/test_chat_stream_guardrail_error_events.py:242
↓ 11 callersFunction_caps
(*, url=True, form=True)
tests/unit/proxy/mcp_server/test_mcp_elicitation_handler.py:51
↓ 11 callersFunction_chat
( gateway: Gateway, model: str, marker: str, extra: Mapping[str, JsonValue] = MappingProxyType
tests/integration/security/test_api_key_secret_reference.py:463
↓ 11 callersFunction_chat
(rig: Rig, key: str, model: str, text: str, client: Client = "httpx", *, cached: bool = False)
tests/integration/providers/test_anthropic_refusal_stop_details_wire.py:281
↓ 11 callersFunction_chat_response
(completion_tokens: int)
tests/unit/router_strategy/test_lowest_latency.py:102
↓ 11 callersFunction_chat_signature
(prefix: str, api_key: str)
tests/integration/authorization/test_rag_team_provider_credentials.py:818
↓ 11 callersFunction_chat_tool_response
(*tool_calls: dict[str, object])
tests/unit/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py:5254
↓ 11 callersFunction_check
(counter: str)
tests/unit/redis/stores/spend_counters_double.py:38
↓ 11 callersMethod_check_and_reload_model_cost_map
Check if model cost map needs to be reloaded based on database configuration. Runs on the periodic reload job, independently of `stor
litellm/proxy/proxy_server.py:9431
↓ 11 callersFunction_check_key_model_budget_with_fallback
Enforce the key's per-model budget for `model_name`. If exceeded and the key has a `budget_fallbacks` chain configured for `model_name`, rero
litellm/proxy/auth/user_api_key_auth.py:1069
↓ 11 callersFunction_check_vector_store_access
Check if the user has access to the vector store. Delegates to :func:`can_user_access_vector_store`, which honors: - PROXY_ADMIN bypass
litellm/proxy/vector_store_endpoints/management_endpoints.py:166
↓ 11 callersFunction_choice
(chunk: Mapping[str, JsonValue])
tests/integration/providers/test_anthropic_refusal_stop_details_wire.py:476
↓ 11 callersFunction_chunked_job
(chunks_by_table)
tests/unit/proxy/common_utils/test_reset_budget_job.py:2319
↓ 11 callersFunction_cimd_request
()
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:14569
↓ 11 callersFunction_classify_cursor_request
Classify a Cursor API request into a readable operation name.
litellm/proxy/pass_through_endpoints/llm_provider_handlers/cursor_passthrough_logging_handler.py:35
↓ 11 callersFunction_clear_azure_ai_auth_environment
(monkeypatch: pytest.MonkeyPatch)
tests/unit/decisions/test_main.py:2835
↓ 11 callersFunction_client
(gateway: Gateway, key: str, prefix: str)
tests/integration/authorization/test_responses_id_ownership.py:103
↓ 11 callersFunction_client
(http_client: FakeHTTPClient, clock: FakeClock | None = None)
tests/unit/integrations/zerobus/test_zerobus_client.py:98
↓ 11 callersFunction_client_video
(video_id: str, model: str, *, created: bool)
tests/integration/compatibility/test_missing_body_param_status.py:1868
↓ 11 callersFunction_commit
(repo: Path, cost_map: dict[str, object], message: str, pins: str | None = None)
tests/unit/test_cost_map_guard.py:358
↓ 11 callersFunction_completion
(identity: str, content: str)
tests/integration/providers/test_hosted_vllm_reasoning_content_wire.py:26
↓ 11 callersFunction_config
( *, token_endpoint: str = "https://identity.example.com/oauth2/token", client_id: str = "client-9
tests/unit/litellm_core_utils/test_oauth_token_exchange.py:29
↓ 11 callersMethod_config
(self)
tests/unit/llms/oci/test_oci_coverage_boost.py:855
↓ 11 callersFunction_config_cache_key
(param_name: str)
litellm/proxy/utils.py:5483
↓ 11 callersFunction_config_param_table
(client: PrismaClient | None, *, use_writer: bool = False)
litellm/proxy/proxy_server.py:2520
↓ 11 callersFunction_configured
( rate: int = 24_000, turn_detection: str | None = "server_vad", language: str | None = "en" )
tests/unit/llms/vertex_ai/audio_transcription/test_vertex_ai_realtime_transformation.py:75
↓ 11 callersFunction_contents
(marker: str)
tests/integration/providers/test_google_genai_vertex_routes_wire.py:179
↓ 11 callersFunction_contract_requests
(wire: Wire)
tests/integration/authorization/test_responses_id_ownership.py:66
↓ 11 callersFunction_converse_data
(endpoint: str = "model/anthropic.claude-3-sonnet/converse")
tests/unit/llms/bedrock/passthrough/guardrail_translation/test_handler.py:81
↓ 11 callersMethod_convert_cached_result_to_model_response
Internal method to process the cached result Checks the call type and converts the cached result to the appropriate model response o
litellm/caching/caching_handler.py:1026
↓ 11 callersMethod_convert_consecutive_user_messages_to_guarded_text
Convert consecutive user messages at the end to guarded_text type if guardrailConfig is present and no guarded_text is already presen
litellm/llms/bedrock/chat/converse_transformation.py:260
↓ 11 callersFunction_convert_mcp_messages_to_openai
Convert MCP SamplingMessage list to OpenAI messages format. MCP messages use: - role: "user" | "assistant" - content: TextContent | I
litellm/proxy/mcp_server/sampling_handler.py:394
↓ 11 callersMethod_convert_response_output_to_choices
Convert Responses API output items to chat completion choices. Args: output_items: List of items from ResponsesAPIRespon
litellm/completion_extras/litellm_responses_transformation/transformation.py:1370
↓ 11 callersFunction_counts
(rig: Rig, setting: str, holder: str)
tests/integration/management/test_batch_file_usage_caps.py:152
↓ 11 callersMethod_create_bedrock_block
Create appropriate Bedrock content block based on mime type.
litellm/litellm_core_utils/prompt_templates/factory.py:4198
↓ 11 callersFunction_create_fallback
( gateway: Gateway, scenario: Scenario, model: str, fallback_models: list[str], fallback_type: str = "gene
tests/integration/management/test_fallback_management_public_names.py:82
↓ 11 callersFunction_create_guardrail
( gateway: Gateway, cleanups: ExitStack, guardrail_name: str, api_base: str, api_key: str,
tests/integration/management/test_policy_attachment_runtime.py:91
↓ 11 callersFunction_create_policy
(gateway: Gateway, cleanups: ExitStack, policy_name: str, guardrail_name: str)
tests/integration/management/test_policy_attachment_runtime.py:120
↓ 11 callersFunction_daily_upserts
(db: _DailySpendFakeDB, table: str)
tests/unit/proxy/db/test_db_spend_update_writer.py:3458
↓ 11 callersFunction_days
(db, key: str | None = None, user_id: str | None = None, router: str | None = None)
tests/integration/spend/test_autorouter_session_rollup.py:144
↓ 11 callersMethod_db_health_watchdog_loop
(self)
litellm/proxy/utils.py:7992
↓ 11 callersFunction_decode_user_credential
Read back a value persisted in ``LiteLLM_MCPUserCredentials.credential_b64``. Tries nacl decryption first (current write format). Falls back to
litellm/proxy/mcp_server/db.py:1593
↓ 11 callersFunction_delegate_scope
(headers: list)
tests/unit/proxy/mcp_server/test_mcp_server_tool_calls_and_headers.py:7276
↓ 11 callersMethod_delete_old_logs
( self, prisma_client: PrismaClient, cutoff_date: datetime, deadline: float )
litellm/proxy/db/db_transaction_queue/spend_log_cleanup.py:969
↓ 11 callersFunction_deployment
(scenario: Scenario, group: str, model: str, api_base: str)
tests/integration/providers/test_chat_template_tool_count_wire.py:85
↓ 11 callersFunction_deployment
(gateway: Gateway, scenario: Scenario, wire: Wire, route: Route, **extra: JsonValue)
tests/integration/providers/test_google_genai_vertex_routes_wire.py:166
↓ 11 callersFunction_deployment
(scenario: Scenario, handle: ScenarioHandle, provider: _Provider)
tests/integration/providers/test_decisions_wire.py:239
↓ 11 callersFunction_deployment
(scenario: Scenario, route: Route, wire_url: str)
tests/integration/providers/test_responses_bridge_tool_search_undeferred_wire.py:283
↓ 11 callersFunction_deployment
(scenario: Scenario, wire: Wire)
tests/integration/authorization/test_responses_id_ownership.py:89
↓ 11 callersFunction_deployment
(model_name: str, model: str = "openai/gpt-4o", **model_info)
tests/unit/proxy/common_utils/test_discoverable_model_filter.py:17
↓ 11 callersFunction_deployment
(model_name: str, deployment_id: str, **params: object)
tests/unit/test_router/core/test_registry_changesets.py:40
↓ 11 callersMethod_descovery_metadata
Discover OAuth metadata by following RFC 9728 (protected resource metadata discovery). ``allow_origin_fallback`` controls the last-resort gue
litellm/proxy/mcp_server/mcp_server_manager.py:5177
↓ 11 callersFunction_discovery_server
()
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:16606
↓ 11 callersFunction_drain
(chunks: list[ModelResponseStream], use_async: bool)
tests/unit/llms/anthropic/messages/adapters/test_streaming_iterator_tool_args.py:400
↓ 11 callersFunction_drain_spend_events
()
tests/unit/proxy/response_api_endpoints/test_endpoints.py:767
← previousnext →5,801–5,900 of 202,479, ranked by callers