MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 7 callersFunction_table
(repository: DailyTagSpendRepository)
litellm/proxy/management_endpoints/tag_management_endpoints.py:126
↓ 7 callersFunction_tag_max_budget_check
Check if any tags in the request are over their max budget. Raises: BudgetExceededError if any tag is over its max budget. T
litellm/proxy/auth/auth_checks.py:7662
↓ 7 callersFunction_tagged_key
(scenario: Scenario, marker: str, **fields: JsonValue)
tests/integration/spend/test_passthrough_request_tags.py:90
↓ 7 callersFunction_targets_after
(forward: ForwardProxy, call: Callable[[], object])
tests/integration/providers/test_api_base_url_join_host_owned_proxy.py:103
↓ 7 callersFunction_team
(**updates: object)
tests/unit/proxy/management_helpers/test_auto_router_permissions.py:46
↓ 7 callersMethod_team_scoped
(per_team: Mapping[str, list[str]])
tests/unit/proxy/management_endpoints/test_mcp_management_endpoints.py:1809
↓ 7 callersFunction_teams_of
(prisma: _FakePrisma, user_id: str)
tests/unit/proxy/management_helpers/test_team_roster_sync.py:289
↓ 7 callersFunction_terminal_response_id
( gateway: Gateway, key: str, body: dict[str, JsonValue], headers: Mapping[str, str] | None = None )
tests/integration/spend/test_responses_stream_spend_row_id.py:114
↓ 7 callersFunction_text
(value: str)
tests/unit/llms/openai/chat/test_openai_gpt_transformation.py:953
↓ 7 callersFunction_text_only_stream
(text: str, response_id: str = "resp-1")
tests/unit/responses/mcp/test_mcp_streaming_iterator.py:84
↓ 7 callersFunction_text_stream_request
(marker: str, **fields: JsonValue)
tests/integration/providers/test_google_genai_adapter_wire.py:814
↓ 7 callersFunction_think_chunk
(text: str)
tests/unit/llms/mistral/test_mistral_chat_transformation.py:955
↓ 7 callersFunction_three_reads
()
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_handler.py:1054
↓ 7 callersMethod_tinyfish_logging_obj
(self)
tests/unit/proxy/pass_through_endpoints/test_streaming_handler_interrupt.py:1336
↓ 7 callersFunction_token_counter_total
(rows: Sequence[_BatchLine])
tests/unit/proxy/hooks/test_batch_rate_limiter.py:352
↓ 7 callersFunction_token_requests
(requests: list[httpx.Request])
tests/unit/llms/microsoft_365_copilot/chat/test_handler.py:132
↓ 7 callersFunction_tokens_counted
(handler: _PROXY_MaxParallelRequestsHandler, key: str, value: str)
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:4100
↓ 7 callersFunction_too_large_validation_httpx_response
()
tests/unit/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py:3616
↓ 7 callersFunction_tool_config_data
()
tests/unit/llms/bedrock/passthrough/guardrail_translation/test_handler.py:2007
↓ 7 callersFunction_tool_result
( *, tool_use_id: str, content: Any = None, is_error: bool = False )
tests/unit/proxy/mcp_server/test_mcp_sampling_tool_conversion.py:33
↓ 7 callersFunction_tool_schema_properties
(model, tool, litellm_params=None)
tests/unit/llms/bedrock/chat/test_converse_transformation.py:1169
↓ 7 callersFunction_toolset_permission
(*toolset_ids: str)
tests/unit/proxy/mcp_server/test_ui_session_utils.py:264
↓ 7 callersFunction_trace_fields
(attributes: Mapping[str, object])
tests/unit/integrations/test_langfuse_otel.py:1126
↓ 7 callersFunction_transform
(payload: object, query: str = "q=python&format=json")
tests/unit/llms/duckduckgo/search/test_duckduckgo_search_transformation.py:305
↓ 7 callersFunction_transform
(body: object, *, requested_tier: str | None = None)
tests/unit/llms/aiohttp_openai/chat/test_transformation.py:12
↓ 7 callersFunction_transform
(payload: object)
tests/unit/llms/tavily/search/test_tavily_search_transformation.py:97
↓ 7 callersFunction_transform
(payload: object)
tests/unit/llms/perplexity/embedding/test_perplexity_embedding_transformation.py:308
↓ 7 callersFunction_transform
(payload: object)
tests/unit/llms/dataforseo/search/test_dataforseo_search_transformation.py:64
↓ 7 callersMethod_transform
(self, config, chunk)
tests/unit/llms/github_copilot/responses/test_github_copilot_responses_transformation.py:554
↓ 7 callersMethod_transform_dbrx_choices
(self, choices: list[DatabricksChoice], json_mode: bool | None = None)
litellm/llms/databricks/chat/transformation.py:856
↓ 7 callersFunction_transform_gemini_response
(payload: object)
tests/unit/llms/vertex_ai/image_generation/test_vertex_ai_image_generation_transformation.py:740
↓ 7 callersMethod_transform_interactions_input_to_responses_input
Transform Interactions API input to Responses API input format. Interactions API input can be: - string: "Hello" - S
litellm/interactions/litellm_responses_transformation/transformation.py:97
↓ 7 callersFunction_transform_message_body
(body: dict)
tests/unit/llms/anthropic/chat/test_anthropic_chat_transformation.py:10465
↓ 7 callersFunction_transform_response
(model: str, payload: object)
tests/unit/llms/gemini/test_gemini_image_generation_transformation.py:428
↓ 7 callersMethod_transform_response_input_param_to_chat_completion_message
Transform a ResponseInputParam into a Chat Completion message See ``transform_responses_api_input_to_messages`` for what ``r
litellm/responses/litellm_completion_transformation/transformation.py:1603
↓ 7 callersMethod_translate
(self, user_content)
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_transformation.py:2077
↓ 7 callersMethod_translate_event_to_beta
Translate a single GA event dict to its beta equivalent. Returns None when the event must be dropped (the GA-only conversation.item.d
litellm/litellm_core_utils/realtime_streaming.py:2167
↓ 7 callersFunction_typed_table
(repo: EndUserRepository)
litellm/proxy/management_endpoints/customer_endpoints.py:114
↓ 7 callersMethod_unmask_sse_bytes_chunk
(chunk: bytes, pii_tokens: dict[str, str])
litellm/proxy/guardrails/guardrail_hooks/presidio.py:1613
↓ 7 callersMethod_unregister_models
()
tests/unit/litellm_core_utils/test_litellm_logging.py:10955
↓ 7 callersFunction_update_database_for_video_poll
( db_writer: DBSpendUpdateWriter, prisma: MagicMock, litellm_call_id: str, response_cost: floa
tests/unit/proxy/db/test_db_spend_update_writer.py:4929
↓ 7 callersFunction_update_model_if_team_alias_exists
Update the model if the team alias exists If a alias map has been set on a team, then we want to make the request with the model the team al
litellm/proxy/litellm_pre_call_utils.py:3589
↓ 7 callersFunction_update_request_data_with_managed_file_id
Update request data with model routing information from managed file ID. This function handles two types of file IDs: 1. Simple encoded
litellm/proxy/vector_store_files_endpoints/endpoints.py:131
↓ 7 callersFunction_update_team_model_in_db
Handle team model updates with proper alias management. If patch_data contains a team_id: - Creates unique internal model_name and team
litellm/proxy/management_endpoints/model_management_endpoints.py:2232
↓ 7 callersFunction_updated
(payload)
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:15556
↓ 7 callersFunction_upgrades
(observed: tuple[dict[str, JsonValue], ...])
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:747
↓ 7 callersFunction_upload
(content: bytes, form: dict)
tests/unit/proxy/openai_files_endpoint/test_files_endpoint.py:6100
↓ 7 callersFunction_upstream
(marker: str)
tests/integration/messages_endpoint/chat_bridge/test_chat_bridge_mid_stream_failure_bookkeeping_wire.py:106
↓ 7 callersFunction_upstream
(pages_by_after)
tests/unit/containers/test_container_proxy_ownership.py:275
↓ 7 callersFunction_upstream_http_status_error
(status_code: int, headers: dict[str, str] | None = None)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:21631
↓ 7 callersFunction_usage
(payload: Mapping[str, JsonValue])
tests/integration/providers/test_sagemaker_embedding_wire.py:161
↓ 7 callersFunction_usage_only
(identity: str)
tests/integration/routing/test_vllm_passthrough_stream_relay.py:82
↓ 7 callersFunction_user
(marker: str, *words: str)
tests/integration/providers/test_responses_bridge_tool_search_replay.py:118
↓ 7 callersFunction_user
(teams=(TEAM_ID,), user_id=USER_ID)
tests/unit/proxy/auth/test_resolvers_grants.py:68
↓ 7 callersMethod_user_content
(items)
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_transformation.py:2081
↓ 7 callersFunction_user_credential_actions
( prisma_client: PrismaClient, )
litellm/proxy/mcp_server/db.py:767
↓ 7 callersFunction_v1_model_info_names
(user_api_key_dict: UserAPIKeyAuth)
tests/unit/proxy/test_model_list_callback_filter.py:149
↓ 7 callersFunction_valid_claims
(**overrides)
tests/unit/proxy/mcp_server/outbound_credentials/test_session_token.py:80
↓ 7 callersFunction_validate_caller_can_assign_key_org
Reject ``/key/update`` requests that point a key at an organization the caller does not belong to. Mirrors the org-membership rule already en
litellm/proxy/management_endpoints/key_management_endpoints.py:2272
↓ 7 callersFunction_validate_team_member_reset_spend_value
( reset_to: object, membership: LiteLLM_TeamMembership, )
litellm/proxy/management_endpoints/team_endpoints.py:4370
↓ 7 callersFunction_vectors
(response: litellm.EmbeddingResponse)
tests/integration/sdk/test_sagemaker_embedding_sdk.py:71
↓ 7 callersFunction_vertex_deployment
(model_name: str, model: str, **litellm_params)
tests/unit/proxy/pass_through_endpoints/test_passthrough_endpoint_router.py:250
↓ 7 callersFunction_wire
(caller: Caller, marker: str)
tests/integration/security/test_hide_secrets_tool_compatibility.py:193
↓ 7 callersFunction_wire_update_key_fn
( monkeypatch: pytest.MonkeyPatch, existing_key: LiteLLM_VerificationToken | MagicMock )
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:19504
↓ 7 callersMethod_with_db_retry
Reconnect and retry once on a transport error, so a dropped connection costs one retry instead of the whole tick.
litellm/proxy/common_utils/reset_budget_job.py:593
↓ 7 callersFunction_with_line
(schema: str, after: int, line: str)
tests/unit/test_spend_logs_guard.py:56
↓ 7 callersFunction_worker
(gateway: Gateway)
tests/integration/mcp/test_mcp_accounting_guardrails.py:359
↓ 7 callersFunction_wrapped
(payload: Sequence[str])
tests/unit/test_gate_slot_lock.py:56
↓ 7 callersMethod_write
(self, tmp_path: Path, source: str)
tests/unit/test_check_unbounded_in_lists.py:354
↓ 7 callersFunction_write_auth_file
(tmp_path, payload)
tests/unit/llms/xai/test_xai_oauth.py:30
↓ 7 callersFunction_write_back_texts
(text_parts: Sequence[object], guardrailed_texts: Sequence[str] | None)
litellm/llms/gemini/google_genai/guardrail_translation/handler.py:107
↓ 7 callersFunction_write_vault_backed_config
Write a config whose secrets live only in a custom secret manager, never in the env.
tests/unit/proxy/proxy_server/test_proxy_config.py:1824
↓ 7 callersFunction_written
(tmp_path, source, name="conftest.py")
tests/unit/test_check_test_quality.py:506
↓ 7 callersFunction_xai_batch
(**overrides: object)
tests/unit/llms/xai/batches/test_xai_batches_transformation.py:24
↓ 7 callersFunction_yield_to_loop
Let already-scheduled tasks make progress. Bound to the real ``asyncio.sleep`` at import time: the tests below patch ``asyncio.sleep`` to ski
tests/unit/proxy/db/test_prisma_planned_engine_restart.py:84
↓ 7 callersMethodaccept
(self, name: str, body: bytes)
tests/integration/observability/test_batch_line_items_cold_storage.py:70
↓ 7 callersMethodaclose
(self)
litellm/passthrough/main.py:218
↓ 7 callersMethodaclose
Stop the runtime and the endpoint. Safe to call twice.
litellm/harness/runtime.py:684
↓ 7 callersMethodaclose
(self)
tests/unit/proxy/common_utils/test_config_sync_pubsub.py:127
↓ 7 callersMethodaclose
(self)
tests/unit/proxy/hooks/test_async_post_call_streaming_iterator_hook.py:313
↓ 7 callersMethodaclose
(self)
tests/unit/llms/opencode/chat/test_transformation.py:132
↓ 7 callersMethodacquire_permit
Return a generation-scoped permit, or deny the call while the circuit is open. Calls admitted together while closed share a generation. The f
litellm/router_strategy/complexity_router/complexity_router.py:1282
↓ 7 callersMethodactive
The deployments still cooling down, read on the batch `send` picks. An entry whose cooldown already ended is dropped from memory, and one memory would
litellm-rust/crates/redis-store/src/router_cooldowns/mod.rs:131
↓ 7 callersFunctionactive_connection
(stored: StoredROISettings)
litellm/proxy/roi_calculator/settings.py:66
↓ 7 callersFunctionactive_spend_counter_batch
()
litellm/proxy/spend_tracking/spend_counter_batch.py:147
↓ 7 callersMethodactive_tier_severity_order
This router's built-in ladder, ascending; not meaningful for a custom tier set.
litellm/router_strategy/complexity_router/config.py:2056
↓ 7 callersFunctionadapt_messages_to_generic_oci_standard_tool_call
Convert an assistant tool-call message to OCI format.
litellm/llms/oci/chat/generic.py:115
↓ 7 callersMethodadd
(e,t,s)
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:28
↓ 7 callersMethodadd
``add_optional_pre_call_checks``.
litellm/router_rust/steps/callbacks.py:289
↓ 7 callersFunctionadd_custom_logger_callback_to_specific_event
Add a custom logger callback to the specific event
litellm/utils.py:647
↓ 7 callersFunctionadd_missing_query_params
Return ``url`` with the ``params`` it does not already carry appended. Params the operator pinned on the URL win, so a hand-tuned replica URL kee
litellm/proxy/db/db_url_settings.py:122
↓ 7 callersFunctionadd_new_user_to_default_team
( user_id: str, user_email: str | None, user_api_key_dict: UserAPIKeyAuth, teams: Sequence[str
litellm/proxy/management_endpoints/internal_user_endpoints.py:451
↓ 7 callersFunctionadd_shared_session_to_data
Add shared aiohttp session for connection reuse (prevents cold starts). If the session was closed (e.g. due to network interruption or idle t
litellm/proxy/route_llm_request.py:541
↓ 7 callersMethodadd_state_delta
Aggregate a bandit-cell delta. Multiple deltas to the same cell sum.
litellm/router_strategy/adaptive_router/update_queue.py:50
↓ 7 callersFunctionadvance_baseline_history
Apply one request-start timestamp; ties cannot manufacture initial equality. The storage owner groups and orders observations before calling this
litellm/proxy/spend_tracking/baseline_accounting.py:310
↓ 7 callersFunctionagent_commands
Build one top-level command per known agent, e.g. `lite claude`.
litellm/proxy/client/cli/commands/agents.py:1265
↓ 7 callersFunctionagent_profile
Return the (display name, env profiles) for a wrapped command. Known agents map to the API family they speak. Anything else gets both familie
litellm/proxy/client/cli/commands/agents.py:103
↓ 7 callersFunctionagent_search_text
(agent: AgentResponse)
litellm/proxy/agent_endpoints/agent_search.py:88
↓ 7 callersFunctionaget_anthropic_wif_token
( litellm_params: Mapping[str, object] | None, api_base: str | None, model: str, engine: JwtBe
litellm/llms/anthropic/wif.py:371
↓ 7 callersMethodaget_auth_header
Async counterpart of get_auth_header: the WIF tier can block on a token exchange POST, so async callers await it off the event loop.
litellm/llms/anthropic/common_utils.py:1730
← previousnext →10,501–10,600 of 202,479, ranked by callers