MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 8 callersMethod_responses_api_response_obj
Return a dict mimicking ResponsesAPIResponse with a message output.
tests/unit/integrations/test_opentelemetry.py:4366
↓ 8 callersFunction_responses_body
(deployment: _Deployment, extra: Mapping[str, JsonValue] = _NO_CACHE)
tests/integration/streaming/test_interception_converted_stream_options.py:247
↓ 8 callersMethod_responses_request
(self, *input_items: Mapping[str, object], **extra: object)
tests/unit/proxy/guardrails/guardrail_hooks/test_panw_prisma_airs.py:4793
↓ 8 callersMethod_restore_correlation_context
Restore trace_id/session_id contextvars to their pre-call value. Without this, a nested LiteLLM call sharing the same asyncio Task as an
litellm/litellm_core_utils/litellm_logging.py:3608
↓ 8 callersFunction_result
(**overrides)
tests/unit/llms/nimble/search/test_nimble_search_transformation.py:22
↓ 8 callersFunction_retrieve_batch
(writer: DBSpendUpdateWriter, cost: float)
tests/integration/database/test_spendlogs_ledger_parity.py:1019
↓ 8 callersFunction_retrieve_tool_call
(hash_value: str, tool_id: str)
tests/unit/proxy/guardrails/guardrail_hooks/test_compresr.py:208
↓ 8 callersFunction_return_huggingface_tokenizer
( model: str, outcomes: _HuggingFaceTokenizerLoadOutcomes = _HUGGINGFACE_TOKENIZER_LOAD_OUTCOMES )
litellm/utils.py:3009
↓ 8 callersFunction_round
(response_id: str, response_cost: object, served_from_cache: bool = False)
tests/unit/responses/mcp/test_round_billing.py:13
↓ 8 callersMethod_round_trip
(self, *command: object)
tests/unit/redis/stores/auth_cache_double.py:48
↓ 8 callersMethod_route_openai_thinking_to_responses_api_if_needed
When users call `litellm.anthropic.messages.*` with a non-Anthropic model and `thinking={"type": "enabled", ...}`, LiteLLM converts t
litellm/llms/anthropic/messages/adapters/handler.py:552
↓ 8 callersFunction_route_tools
(gateway: Gateway, headers: dict[str, str], name: str)
tests/integration/mcp/test_mcp_toolsets.py:264
↓ 8 callersFunction_routed_model_cost
()
tests/unit/llms/azure_ai/test_azure_ai_cost_calculator.py:126
↓ 8 callersFunction_router
(wire: Wire, deployments: tuple[str, ...], **settings: object)
tests/integration/sdk/test_router_tool_call_stream_fallback_budget_wire.py:134
↓ 8 callersFunction_router
(wire: Wire, *, cache_responses: bool = False)
tests/integration/sdk/test_router_include_fallback_errors_wire.py:94
↓ 8 callersFunction_router
(redis: MagicMock, routing_strategy: str)
tests/unit/router_utils/test_routing_read_batch.py:46
↓ 8 callersMethod_router
( cls, registrations: dict[str, "TestTeamPublicNameReachesPreRoutingStrategies._RewriteStrateg
tests/unit/test_router/test_router.py:10293
↓ 8 callersFunction_router_acompletion
(router: Router, **request_kwargs: object)
tests/unit/router_utils/test_kubernetes_pod_discovery.py:375
↓ 8 callersFunction_router_config
(config_path)
tests/unit/proxy/client/cli/autoroute/test_wizard.py:88
↓ 8 callersFunction_router_health_fixture
A real Router whose SIMPLE tier, default and classifier can each be pointed at a dead group. That group has two replicas, so a verdict reached on
tests/unit/proxy/test_health_check_max_tokens.py:1034
↓ 8 callersFunction_router_pricing
(model: str = AN_UNDERLYING_MODEL, **pricing: float)
tests/unit/proxy/management_endpoints/test_cost_tracking_settings.py:870
↓ 8 callersFunction_row_for_call
(call_id: str)
tests/integration/spend/test_requester_ip_address_logging.py:401
↓ 8 callersFunction_rows
(rig: _Rig, caller: _Caller)
tests/integration/authorization/test_agent_denial_logging.py:365
↓ 8 callersMethod_rows
The stored entries router-core's lookup ``rows`` name, read as Python's list reads them: a row it could not read is indexed here, and raises a
litellm/router_rust/surface/registry.py:1605
↓ 8 callersFunction_run
( database: _FakeDatabase | _DatabaseThatMustNotBeTouched | None, *, previous_master_key: str = PR
tests/unit/proxy/db/test_master_key_migration.py:310
↓ 8 callersFunction_run
(root: Path, *argv: str)
tests/code_coverage_tests/test_merge_smoke.py:15
↓ 8 callersMethod_run
(self, server, oauth2_headers, has_stored_token: bool)
tests/unit/proxy/mcp_server/test_mcp_server_tool_calls_and_headers.py:10710
↓ 8 callersMethod_run_login
( self, tmp_path, monkeypatch, args, base_url="https://test.example.com", *, config_dir_env=None, stor
tests/unit/proxy/client/cli/test_auth_commands.py:1488
↓ 8 callersFunction_run_named_request
( logger: OpenTelemetryV2, exporter: InMemorySpanExporter, litellm_params: Mapping[str, object],
tests/unit/integrations/otel/test_langfuse_logger.py:346
↓ 8 callersFunction_run_post_call_guardrail_on_stream
( stream_bytes: bytes, guardrail: CustomGuardrail, monkeypatch: pytest.MonkeyPatch, endpoint:
tests/unit/llms/bedrock/passthrough/guardrail_translation/test_handler.py:889
↓ 8 callersFunction_run_success_event
( additional_headers: Mapping[str, object] | None, logger: PrometheusLogger | None = None )
tests/unit/integrations/test_prometheus_rate_limit_labels.py:560
↓ 8 callersMethod_run_update
(self, data, existing_key_row)
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:12732
↓ 8 callersFunction_run_update_organization_v2
( monkeypatch, *, body: dict, existing_budget_id, existing_metadata, existing_object_p
tests/unit/proxy/management_endpoints/test_organization_endpoints.py:808
↓ 8 callersFunction_s3_logger_on_production_handler
S3Logger wired to the real AsyncHTTPHandler over an httpx MockTransport that answers with the given statuses (or raises the given transport e
tests/unit/integrations/test_s3_v2.py:606
↓ 8 callersFunction_saml
()
tests/unit/proxy/mcp_server/outbound_credentials/test_login_assertion_exchange.py:61
↓ 8 callersFunction_sanitize_file_path
Reject path traversal and URL-encode each path segment.
litellm/integrations/bitbucket/bitbucket_client.py:63
↓ 8 callersFunction_save_health_check_results_if_changed
Save health check results to database, but only if status changed or >1 hour since last save. OPTIMIZATION: Only saves to database if the st
litellm/proxy/health_endpoints/_health_endpoints.py:934
↓ 8 callersFunction_saved_profile_path
(target: Literal["claude", "codex"], settings_path: Path)
tests/unit/proxy/client/cli/test_configure_commands.py:720
↓ 8 callersFunction_scan
(tmp_path: Path, source: str)
tests/unit/test_check_py310_typing_imports.py:10
↓ 8 callersFunction_scan
(tmp_path: Path, sql: str, name: str = "20261010000000_fixture")
tests/unit/test_check_migrations_lock_timeout.py:13
↓ 8 callersFunction_schema_at
(container: Mapping[str, object], key: str)
litellm/litellm_core_utils/prompt_templates/json_schema_utils.py:402
↓ 8 callersFunction_schema_nodes
(schema: Mapping[str, object])
litellm/litellm_core_utils/prompt_templates/json_schema_utils.py:303
↓ 8 callersMethod_scope
(self, value: object)
litellm/router_rust/invoke/walk.py:229
↓ 8 callersFunction_screen_messages
(image_url: str)
tests/unit/decisions/test_main.py:1968
↓ 8 callersFunction_script
A script's reply; one declared without Redis raises where it is awaited, like a failed script.
litellm/redis/stores/rate_limits/__init__.py:62
↓ 8 callersFunction_scripted_error
(status: int, marker: str)
tests/integration/providers/test_assistants_route_errors_wire.py:135
↓ 8 callersFunction_sdk
(gateway: Gateway, path: str, api_key: str)
tests/integration/compatibility/test_audio_transcriptions_wire.py:161
↓ 8 callersFunction_searches_for_marker
( gateway: Gateway, marker: str, store_id: str = CONFIG_STORE_ID )
tests/integration/authorization/test_rag_query_vector_store_allowlist.py:79
↓ 8 callersFunction_seed
(day: str, rows: Sequence[tuple[object, ...]])
tests/integration/spend/test_daily_activity_aggregated_breakdowns.py:24
↓ 8 callersFunction_select_model_by_priority
Score available models by MCP priority weights and return the best. Scoring strategy (per the MCP spec, priorities are 0-1 floats): * **cost
litellm/proxy/mcp_server/sampling_handler.py:181
↓ 8 callersFunction_semantic_cache
(**cache_kwargs)
tests/unit/caching/test_caching.py:134
↓ 8 callersFunction_sent_betas
(route: respx.Route)
tests/unit/llms/bedrock_mantle/test_bedrock_mantle_messages_transformation.py:371
↓ 8 callersFunction_serve_aliases
Point the mock router's ``registry().resolve(name, kind="alias")`` at this model_group_alias map.
tests/unit/integrations/test_shadow_eval_logger.py:101
↓ 8 callersFunction_serve_file
(router: respx.MockRouter, file_id: str, rows: Sequence[_BatchLine])
tests/unit/proxy/hooks/test_batch_rate_limiter.py:345
↓ 8 callersFunction_served_id
(deployment: str, marker: str, attempt: int)
tests/integration/routing/test_ptu_shares.py:150
↓ 8 callersFunction_server_tool_call
(call_id: str, name: str, arguments: Mapping[str, object])
tests/unit/llms/openai/chat/guardrail_translation/test_openai_guardrail_handler.py:151
↓ 8 callersFunction_session
(response: httpx.Response)
tests/integration/spend/test_spend_log_caller_session.py:247
↓ 8 callersMethod_session_usage
( handler: VertexAILivePassthroughLoggingHandler, mock_logging_obj: MagicMock, message
tests/unit/proxy/pass_through_endpoints/test_vertex_ai_live_passthrough.py:290
↓ 8 callersFunction_set_base_ref
(repo: Path, branch: str = "release_branch")
tests/unit/test_pre_commit_lint.py:164
↓ 8 callersFunction_set_cli_sso_flow
(login_id: str, cache: DualCache, flow: dict)
litellm/proxy/management_endpoints/ui_sso.py:436
↓ 8 callersMethod_set_customer_budget_metrics
( self, end_user_id: str, spend: float, max_budget: float | None, budg
litellm/integrations/prometheus.py:4677
↓ 8 callersFunction_set_full_env
(monkeypatch: pytest.MonkeyPatch)
tests/unit/proxy/enterprise_billing/test_billing_metrics.py:51
↓ 8 callersFunction_set_redis_usage_cache
Publish the resolved coordination Redis to the consumers that read it directly.
litellm/proxy/proxy_server.py:5320
↓ 8 callersFunction_settle
(recorded: Sequence[Mapping[str, object]], count: int = 1)
tests/unit/proxy/pass_through_endpoints/test_streaming_handler_interrupt.py:946
↓ 8 callersFunction_settle
(logger: ZerobusLogger)
tests/unit/integrations/zerobus/test_zerobus_logger.py:57
↓ 8 callersFunction_setup_patch_scope_guardrail
( mocker, monkeypatch, mock_guardrail_registry, callback_type: type[CustomGuardrail], guar
tests/unit/proxy/guardrails/test_guardrail_endpoints.py:273
↓ 8 callersFunction_sha1_upper
(password: str)
tests/unit/proxy/auth/test_password_policy.py:33
↓ 8 callersFunction_shield_guardrail
(api_base: str = "azure_prompt_shield_api_base")
tests/unit/proxy/guardrails/guardrail_hooks/azure/test_azure_prompt_shield.py:283
↓ 8 callersMethod_should_block
Return True if any policyAction requires blocking.
litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/base.py:379
↓ 8 callersMethod_should_delete_spend_logs
Determines if logs should be deleted based on the max retention period in settings.
litellm/proxy/db/db_transaction_queue/spend_log_cleanup.py:536
↓ 8 callersMethod_should_preserve_cache_control_for_endpoint
( self, custom_llm_provider: str | None, api_base: str | None, )
litellm/llms/openai_like/dynamic_config.py:80
↓ 8 callersFunction_sign_connect_code
(master_key: str, moyai_url: str, user_id: str | None)
litellm/proxy/moyai_endpoints.py:103
↓ 8 callersFunction_signed_in
(client: TestClient, cache: DualCache)
tests/unit/proxy/anthropic_endpoints/test_gateway_endpoints.py:234
↓ 8 callersFunction_simple_data
Return a fresh copy of _SIMPLE_DATA, optionally merged with extras.
tests/unit/proxy/guardrails/guardrail_hooks/test_panw_prisma_airs.py:113
↓ 8 callersMethod_sink
(self, hooks)
tests/unit/llms/base_llm/auth/test_token_exchange.py:1722
↓ 8 callersFunction_sink_key
The account an exporter writes to, or ``None`` when it has no fixed one. Normalized on the three counts that make one account look like two: the
litellm/integrations/otel/plumbing/providers.py:1738
↓ 8 callersFunction_spec
(config: TokenExchangeConfig)
tests/unit/proxy/mcp_server/outbound_credentials/test_token_exchanger.py:68
↓ 8 callersFunction_spend_for_key
(gateway: Gateway, key: str)
tests/integration/spend/test_passthrough_stream_pricing_paths_spend.py:303
↓ 8 callersFunction_spend_row
(call_id: str)
tests/integration/providers/test_decisions_wire.py:303
↓ 8 callersFunction_spend_row
(digest: str, call_type: str)
tests/integration/spend/test_passthrough_request_tags.py:54
↓ 8 callersFunction_spend_row_for_call_id
(call_id: str)
tests/integration/observability/_logging_only_scope_support.py:1091
↓ 8 callersFunction_spend_tags
(proxy: Gateway, key: str)
tests/integration/spend/test_baggage_tag_mappings.py:311
↓ 8 callersFunction_spender
(proxy: Gateway, database_url: str, label: str)
tests/integration/spend/test_daily_activity_key_metadata_query_timeout.py:312
↓ 8 callersFunction_split_tags
(tags: Sequence[str])
litellm/router_strategy/tag_based_routing.py:227
↓ 8 callersFunction_sse
(*events: Mapping[str, object])
tests/unit/llms/base_llm/responses/test_transformation.py:754
↓ 8 callersFunction_sse_payloads
(response: httpx.Response)
tests/integration/streaming/test_openai_like_stream_usage_wire.py:120
↓ 8 callersFunction_sse_text
(frame: str | bytes)
tests/unit/proxy/proxy_server/test_streaming_helpers.py:103
↓ 8 callersFunction_standard_logging_object
( team_id="team-a", response_cost=0.25, team_max_budget: float | None = None, team_spend: float | None = N
tests/unit/integrations/newrelic/test_newrelic_metrics.py:65
↓ 8 callersFunction_standard_logging_payload
( response: object = None, usage_object: object = None, model_parameters: object = None, )
tests/unit/integrations/test_prometheus_service_tier_label.py:51
↓ 8 callersFunction_start_cli_login
(proxy: Gateway)
tests/integration/authorization/test_sso_blank_identity.py:474
↓ 8 callersFunction_start_root
(logger: OpenTelemetryV2, parent_context: Context | None = None)
tests/unit/integrations/otel/test_langfuse_logger.py:69
↓ 8 callersFunction_started
(settings: TelemetrySettings, db: SettingsDatabase | None)
tests/unit/proxy/telemetry/test_runtime.py:26
↓ 8 callersFunction_statuses
(responses: tuple[httpx.Response, ...])
tests/integration/management/test_batch_file_usage_caps_chaos.py:104
↓ 8 callersFunction_store
( table, claimed_by: str, claim_lease_seconds: float = BACKGROUND_INTERACTION_SETTLEMENT_CLAIM_LEA
tests/unit/proxy/spend_tracking/test_background_interaction_settlement.py:111
↓ 8 callersMethod_store_batch_managed_object
Store batch managed object for cost tracking. This will be picked up by the check_batch_cost polling mechanism. A poll refre
litellm/proxy/pass_through_endpoints/llm_provider_handlers/vertex_passthrough_logging_handler.py:1027
↓ 8 callersFunction_stored_models
(name: str)
tests/integration/management/test_ptu_share_guards.py:94
↓ 8 callersFunction_stored_row
( interaction_id: str, claimed_at: Optional[datetime] = None, settled: bool = False, create_co
tests/unit/proxy/spend_tracking/test_background_interaction_settlement.py:154
↓ 8 callersFunction_str_keyed_fields
(value: object)
litellm/proxy/hooks/proxy_track_cost_callback.py:176
↓ 8 callersFunction_stream
(client: str, router: Router, **extra: object)
tests/integration/sdk/test_router_tool_call_stream_fallback_budget_wire.py:194
↓ 8 callersFunction_stream_auto_execute
(logging_obj: Logging)
tests/unit/responses/mcp/test_aresponses_api_with_mcp.py:2528
← previousnext →8,901–9,000 of 202,479, ranked by callers