MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 7 callersMethod_response
()
tests/unit/litellm_core_utils/test_litellm_logging.py:10987
↓ 7 callersFunction_responses_output_with_web_search
(call_id: str = "fc_1", query: str = "latest ai news")
tests/unit/integrations/websearch_interception/test_websearch_responses.py:28
↓ 7 callersFunction_responses_response
(identity: str, calls: Sequence[dict[str, JsonValue]] | None = None)
tests/integration/observability/_openinference_support.py:988
↓ 7 callersFunction_responses_turn
(model: str)
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:8427
↓ 7 callersFunction_responses_turn_started
(model: str)
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:8431
↓ 7 callersFunction_restore_redacted_litellm_params
Restore the real credential behind any litellm_params value the caller echoed back as ``REDACTED_BY_LITELM_STRING``, and behind any sensitive key
litellm/proxy/agent_endpoints/agent_registry.py:393
↓ 7 callersFunction_retrieved_batch
( status: str, output_file_id: str | None = None, counts: BatchRequestCounts | None = None )
tests/unit/litellm_core_utils/test_batch_utils.py:583
↓ 7 callersFunction_riva_model
(scenario: Scenario, server: RivaServer, **parameters: JsonValue)
tests/integration/providers/test_nvidia_riva_wire.py:20
↓ 7 callersMethod_routable_deployments
(self, model_name: str, team_id: str | None)
litellm/router_rust/surface/registry.py:1991
↓ 7 callersFunction_routable_over_gateway
(gateway: Gateway, model: str)
tests/integration/compatibility/test_missing_body_param_status.py:1857
↓ 7 callersFunction_route_paths
(app: FastAPI)
tests/unit/proxy/common_utils/test_openapi_route.py:18
↓ 7 callersFunction_routed_backends
(upstream: Wire, marker: str)
tests/integration/routing/test_tag_routing_prefix.py:163
↓ 7 callersFunction_routed_decision
()
tests/unit/proxy/spend_tracking/test_savings.py:1127
↓ 7 callersFunction_router
(wire: Wire, team: bool = False)
tests/integration/sdk/test_router_concurrent_deployment_delete_sdk.py:90
↓ 7 callersFunction_router
()
tests/unit/proxy/auth/test_fallback_model_access.py:15
↓ 7 callersMethod_router
()
tests/unit/proxy/test_common_request_processing.py:10129
↓ 7 callersMethod_router
(cls, marker_tags, include_plain_sibling: bool, enable_tag_filtering: bool)
tests/unit/test_router/test_router.py:9500
↓ 7 callersFunction_router_config
(classifier: Mapping[str, JsonValue], simple: str, complex_: str)
tests/integration/management/test_auto_router_databricks_classifier_writes.py:112
↓ 7 callersFunction_router_proxy_module
(router, model_name)
tests/unit/caching/test_qdrant_semantic_cache.py:775
↓ 7 callersFunction_router_with_a_stream_timeout_shorter_than_the_upstreams_first_byte
(model: str)
tests/unit/llms/bedrock/chat/test_bedrock_converse_handler.py:373
↓ 7 callersFunction_router_with_deployment
Build a stub router whose `get_deployment(model_id=...)` returns a deployment with the given guardrails. ``by_alias=True`` also stubs `get_mod
tests/unit/proxy/utils/helpers/test_guardrail_merge.py:18
↓ 7 callersFunction_row_status
(unified_id: str, database_url: str | None = None)
tests/integration/spend/test_background_response_poll_retirement.py:151
↓ 7 callersMethod_run
(self, cmd: Sequence[str], timeout: float | None = DEEPAGENTS_FS_TIMEOUT_SECONDS)
litellm/llms/deepagents/harness/sandbox_backend.py:184
↓ 7 callersMethod_run
(self, *args: str)
tests/unit/test_check_unbounded_in_lists.py:351
↓ 7 callersFunction_run_common_checks
( model: Optional[str], llm_router: Optional["Router"], route: str = "/chat/completions" )
tests/unit/proxy/auth/test_auth_checks_object_access_and_lookup.py:10155
↓ 7 callersFunction_run_hook
( route: str, stream: AsyncGenerator[Union[ModelResponseStream, JsonPayload], None], sampling_rate
tests/unit/proxy/guardrails/guardrail_hooks/unified_guardrails/test_openai_streaming_block.py:139
↓ 7 callersFunction_run_post_mcp_call_guardrails
Run ``post_mcp_call`` guardrails over an executed tool result. Lives on ``execute_mcp_tool``'s return path rather than inside ``_fire_mcp_too
litellm/proxy/mcp_server/operations.py:2591
↓ 7 callersFunction_run_refused_rerun
( response: ModelResponse, rail_kwargs: Dict[str, object], stream: bool = False, gate_tool_cal
tests/unit/litellm_core_utils/test_chat_completion_agentic_loop.py:463
↓ 7 callersFunction_run_request
(logger, data: dict, call_type: str, response: object)
tests/unit/integrations/otel/test_langfuse_logger.py:80
↓ 7 callersMethod_run_rules
(self, migrations)
tests/unit/litellm_proxy_extras/test_litellm_proxy_extras_utils.py:532
↓ 7 callersMethod_run_scheduler_helper
Returns: - True -> report sent - False -> report not sent
litellm/integrations/SlackAlerting/slack_alerting.py:1755
↓ 7 callersFunction_run_update_with_existing
(data: UpdateMCPServerRequest, existing_auth_type: str)
tests/unit/proxy/mcp_server/test_mcp_partial_update.py:199
↓ 7 callersFunction_runtime_counts
(wire: Wire)
tests/integration/providers/test_count_tokens_model_wire.py:189
↓ 7 callersMethod_safe_add_callback_to_list
Safe add a callback to a list, if the callback is already in the list, do not add it again. Ensures no duplicates are added for `str
litellm/litellm_core_utils/logging_callback_manager.py:267
↓ 7 callersMethod_safe_get_remaining_budget
(self, max_budget: float | None, spend: float | None)
litellm/integrations/prometheus.py:4047
↓ 7 callersFunction_sample_payload
(**overrides)
tests/unit/proxy/logging_endpoints/test_callback_logs_endpoints.py:22
↓ 7 callersFunction_sandbox_api
(created: object, polled: Sequence[object] = ())
tests/unit/llms/opensandbox/sandbox/test_transformation.py:18
↓ 7 callersFunction_savings
(baseline: str, selected: str, usage: Usage, baseline_usage: Usage | None = None)
tests/unit/proxy/spend_tracking/test_savings.py:489
↓ 7 callersFunction_scope_resolver
(resolved_without_agent: dict[str, str], access_groups: tuple[str, ...] = ())
tests/unit/proxy/mcp_server/test_mcp_server_tool_calls_and_headers.py:1555
↓ 7 callersFunction_scoped_session
(url: str, key: str = MASTER_KEY, **headers: str)
tests/integration/mcp/test_proxy_mcp_e2e.py:831
↓ 7 callersFunction_scratch_proxy
( gateway: Gateway, directory: Path, monkeypatch: pytest.MonkeyPatch, config: Path, overri
tests/integration/spend/test_background_response_billing_proxies.py:131
↓ 7 callersFunction_scripted
(scenario: Scenario)
tests/integration/providers/test_vertex_realtime_multi_region_host.py:132
↓ 7 callersFunction_scripted
(error: Exception)
tests/integration/sdk/test_stream_open_error_provider_headers_sdk.py:219
↓ 7 callersFunction_search
(session: ClientSession, query: str)
tests/integration/mcp/test_proxy_mcp_e2e.py:839
↓ 7 callersFunction_search_tool_responses
(*names: str)
tests/unit/proxy/management_endpoints/search_endpoints/test_search_tool_management.py:754
↓ 7 callersFunction_search_tools_table
(prisma_client: PrismaClient)
litellm/proxy/search_endpoints/search_tool_registry.py:60
↓ 7 callersFunction_searched_responses_body
(model: str)
tests/unit/completion_extras/litellm_responses_transformation/test_completion_extras_litellm_responses_transformation_transformation.py:277
↓ 7 callersFunction_seed_budget
(prisma, access_group, spend=0.0, budget_id="budget-seed", **budget_fields)
tests/unit/proxy/management_endpoints/test_access_group_management.py:869
↓ 7 callersFunction_seed_membership
(user_id: str, team_id: str, *, spend: float, total_spend: float)
tests/integration/spend/test_team_member_total_spend_reconciliation.py:61
↓ 7 callersFunction_send
(runtime: object, action: str, model: str, prompt: str, caller_guardrail: bool)
tests/integration/providers/test_bedrock_passthrough_guardrail_config_wire.py:182
↓ 7 callersFunction_send
(gateway: Gateway, endpoint: Endpoint, model: str, key: str, *, stream: bool = False)
tests/integration/providers/test_openai_like_response_headers_wire.py:170
↓ 7 callersFunction_send_message
Send a non-streaming message via a2a-sdk 1.x and return JSON-RPC response.
litellm/a2a_protocol/main.py:306
↓ 7 callersFunction_send_request
(request_id)
tests/unit/a2a_protocol/test_main.py:399
↓ 7 callersFunction_sent
(observed: tuple[dict[str, JsonValue], ...])
tests/integration/providers/test_realtime_unguarded_voice_turns.py:412
↓ 7 callersFunction_sent_messages
(request: Request)
tests/integration/providers/test_databricks_chat_wire.py:1282
↓ 7 callersFunction_sent_reasoning_items
(request: httpx.Request)
tests/unit/llms/anthropic/messages/adapters/test_anthropic_messages_adapters_transformation.py:5854
↓ 7 callersFunction_serve
(proxy: ProxyClient, backend: LiteLLMParamsBody, model_info: ModelInfoBody | None = None)
tests/e2e/llm_translation/test_count_tokens_source_e2e.py:102
↓ 7 callersFunction_serve_db_models
(monkeypatch: pytest.MonkeyPatch, db: object, router: "Router | None")
tests/unit/proxy/common_utils/test_registry_read_through.py:578
↓ 7 callersFunction_serve_rounds
( respx_mock: respx.MockRouter, monkeypatch: pytest.MonkeyPatch, bodies: Sequence[Mapping[str, object]] )
tests/unit/responses/mcp/test_aresponses_api_with_mcp.py:1654
↓ 7 callersFunction_served
( router: litellm.Router, *names: str, team_id: str | None = None, **listing: int )
tests/unit/proxy/common_utils/test_codex_model_catalog.py:1216
↓ 7 callersFunction_served_content
(registry: InMemoryPromptRegistry, environment: str | None = None)
tests/unit/proxy/prompts/test_prompt_registry.py:31
↓ 7 callersFunction_served_model
(router: Router, name: str)
tests/unit/proxy/auth/test_unmapped_model_budget_enforcement.py:62
↓ 7 callersFunction_server
(server_id: str, auth_type: MCPAuth)
tests/unit/proxy/mcp_server/test_operations.py:1082
↓ 7 callersFunction_server_forwarding
(*header_names: str)
tests/unit/proxy/mcp_server/test_utils.py:17
↓ 7 callersFunction_servers
(gateway: Gateway, key: str | None = None)
tests/integration/mcp/test_mcp_management.py:40
↓ 7 callersFunction_session_page
(read: _Reader, request: _Request)
litellm/proxy/spend_tracking/session_page.py:119
↓ 7 callersFunction_session_pin_key
(session_id, user_key)
tests/unit/router_utils/pre_call_checks/test_session_id_affinity.py:572
↓ 7 callersFunction_set_fake_aws_env
(monkeypatch: pytest.MonkeyPatch)
tests/unit/llms/anthropic/messages/native/test_anthropic_messages_router.py:184
↓ 7 callersMethod_set_semconv_request_attributes
Add ``gen_ai.request.*`` span attributes from ``optional_params``. Covers the sampling params plus the conditionally-required ``stop_
litellm/integrations/opentelemetry_utils/gen_ai_semconv.py:166
↓ 7 callersMethod_set_wif_env
(self, monkeypatch)
tests/unit/llms/anthropic/test_anthropic_common_utils.py:2655
↓ 7 callersFunction_settings
(response: Response)
tests/unit/proxy/telemetry/test_endpoints.py:201
↓ 7 callersFunction_settle_router_accounting
()
tests/unit/proxy/test_route_llm_request.py:2557
↓ 7 callersFunction_setup_passthrough_upload_endpoint
Like _setup_batch_upload_endpoint, but reads the forwarded file bytes while the spool is open.
tests/unit/proxy/openai_files_endpoint/test_files_endpoint.py:6076
↓ 7 callersFunction_shared_model
(guarded: _Guarded, model_info: Mapping[str, JsonValue])
tests/integration/management/test_ptu_share_guards.py:172
↓ 7 callersMethod_should_anonymize
Determine if content should be anonymized based on Noma API response. Logic: - If aggregatedScanResult=False: Content is saf
litellm/proxy/guardrails/guardrail_hooks/noma/noma.py:432
↓ 7 callersMethod_should_load_db_object
(self, object_type: str | SupportedDBObjectType)
litellm/proxy/proxy_server.py:8881
↓ 7 callersFunction_single_deployment_router
(litellm_params: dict[str, object], model_info: dict[str, object])
tests/unit/proxy/test_proxy_token_counter.py:3048
↓ 7 callersFunction_slice
(**overrides)
tests/unit/test_assert_ci_coverage.py:347
↓ 7 callersMethod_soft_floor_pick
hard_floor excludes every candidate whose tiers all sit below it, turning this pick's soft floors (a distance penalty a high-scoring cheap mod
litellm/router_strategy/complexity_router/complexity_router.py:3323
↓ 7 callersFunction_spend_row
(proxy: Gateway, key: str)
tests/integration/providers/test_bedrock_native_guardrail_trace_spend.py:277
↓ 7 callersFunction_spend_rows
(key: str, count: int)
tests/integration/providers/test_google_genai_vertex_routes_wire.py:219
↓ 7 callersFunction_spend_rows
(model: str, count: int)
tests/integration/spend/test_disable_end_user_cost_tracking.py:353
↓ 7 callersFunction_sse
(chunks: Sequence[bytes])
tests/integration/routing/test_vllm_passthrough_stream_relay.py:90
↓ 7 callersFunction_sse_payloads
(lines: Iterable[str])
tests/integration/providers/test_bedrock_converse_stream_event_frames_wire.py:233
↓ 7 callersFunction_stalled_tool_history
`repeats` identical bash tool calls in a row, the automatic counterpart to a user typing an escalation keyword: the assistant, not the human, is t
tests/unit/router_strategy/test_complexity_router.py:9032
↓ 7 callersMethod_start_engine_watcher
Start watching the Prisma query engine process for death. Detection priority: 1. os.waitpid() in a dedicated thread, works w
litellm/proxy/utils.py:7435
↓ 7 callersMethod_stored_complexity_params
(self)
tests/unit/proxy/management_endpoints/test_model_management_endpoints.py:6391
↓ 7 callersFunction_stored_fallbacks
(fallback_key: str = "fallbacks")
tests/integration/management/test_fallback_management_public_names.py:110
↓ 7 callersFunction_stored_response
(status: str)
tests/unit/responses/test_responses_api_lifecycle.py:131
↓ 7 callersFunction_stored_row
(search_tool_id: str, name: str, litellm_params: dict)
tests/unit/proxy/management_endpoints/search_endpoints/test_search_tool_management.py:1321
↓ 7 callersFunction_stream_hops
()
tests/unit/llms/vertex_ai/gemini/test_long_decode.py:718
↓ 7 callersFunction_stream_path
()
tests/integration/observability/test_bedrock_converse_stream_post_call_guardrail.py:434
↓ 7 callersFunction_strip_compaction_blocks
Drop any ``compaction`` content blocks from messages. Used to build the downstream-bound message list — the adapter has no concept of a compa
litellm/llms/anthropic/messages/context_management/editors/compact.py:170
↓ 7 callersFunction_stub_iam_token
Patch the AWS-touching token mint so tests don't need boto3 / network.
tests/unit/proxy/db/test_db_url_settings.py:96
↓ 7 callersFunction_submit_background_response
(scenario: Scenario, key: str, model: str, database_url: str | None = None)
tests/integration/spend/test_background_response_poll_retirement.py:141
↓ 7 callersFunction_succeed_after
(failures: int, stderr: str)
litellm-proxy-extras/tests/test_setup_database_fail_fast.py:230
↓ 7 callersFunction_success_kwargs
( now: datetime.datetime, prompt_tokens: int, requester_metadata: Mapping[str, object] | None = None )
tests/unit/integrations/test_prometheus_input_sequence_length_label.py:151
↓ 7 callersFunction_supervised
(tmp_path: Path, healthcheck: WorkerHealthcheck)
tests/unit/integration_support/test_process.py:502
↓ 7 callersFunction_synthesized_audio
(run_async: bool, endpoint: respx.Route, payload: object)
tests/unit/llms/vertex_ai/text_to_speech/test_text_to_speech_handler.py:36
↓ 7 callersFunction_table
( prisma_client: "PrismaClient", )
litellm/proxy/credential_endpoints/user_provider_credentials.py:61
← previousnext →10,401–10,500 of 202,479, ranked by callers