MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 10 callersFunction_policy_tags
(row: Mapping[str, JsonValue])
tests/integration/spend/test_passthrough_request_tags.py:78
↓ 10 callersFunction_poll_for_ready_data
( url: str, *, headers: dict[str, str] | None = None, total_timeout: int = 300, poll_inter
litellm/proxy/client/cli/commands/auth.py:559
↓ 10 callersFunction_posted
(wire: Wire)
tests/integration/routing/test_vllm_passthrough_stream_relay.py:148
↓ 10 callersFunction_pre_call
(check: ModelRateLimitingCheck, deployment: dict[str, object])
tests/unit/test_router/test_enforce_model_rate_limits.py:486
↓ 10 callersFunction_prep_env
(monkeypatch)
tests/unit/llms/sap/test_sap_fetch_creds.py:46
↓ 10 callersFunction_primary_with_fallback
(fallback_model: str)
tests/unit/llms/base_llm/responses/test_transformation.py:792
↓ 10 callersFunction_prisma
(rows)
tests/unit/proxy/db/test_health_check_latest.py:19
↓ 10 callersFunction_prisma
(**tables)
tests/unit/proxy/management_helpers/test_resource_display_names.py:21
↓ 10 callersMethod_prisma
(row: _FakeManagedObjectRow, journal: list)
tests/unit/proxy/common_utils/test_check_batch_cost.py:3223
↓ 10 callersFunction_prisma_with_user
(row)
tests/unit/proxy/auth/test_login_utils.py:2121
↓ 10 callersMethod_process
( self, monkeypatch: pytest.MonkeyPatch, llm_call: Callable[[Mapping[str, object]], ob
tests/unit/proxy/test_common_request_processing.py:13351
↓ 10 callersFunction_prompt
(marker: str)
tests/integration/providers/test_bedrock_mantle_claude_chat_wire.py:57
↓ 10 callersFunction_proxy_request
(model: str, route: str = "acompletion", **fields: object)
tests/unit/litellm_core_utils/test_tool_fields.py:36
↓ 10 callersFunction_proxy_url
(gateway: Gateway)
tests/integration/providers/test_bedrock_mantle_output_limit_wire.py:333
↓ 10 callersFunction_ptu_increment
(handler: _PROXY_MaxParallelRequestsHandler, ops: list)
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:9257
↓ 10 callersFunction_raise_on_missing_project_model_quota
Require the positive `rpm`/`tpm` quotas the policy asks of each model on project CREATE. `model_rpm_limit`/`model_tpm_limit` are relocated into `
enterprise/litellm_enterprise/proxy/management_endpoints/project_endpoints.py:333
↓ 10 callersFunction_raises
Mock the way AsyncHTTPHandler.post really behaves: raise_for_status() turns every non-2xx into an HTTPStatusError rather than returning the respon
tests/unit/integrations/newrelic/test_newrelic_metrics.py:103
↓ 10 callersFunction_raw
( gateway: Gateway, path: str, body: Mapping[str, JsonValue], *, key: str | None | EllipsisType = ... )
tests/integration/providers/test_responses_minted_reasoning_replay_wire.py:188
↓ 10 callersFunction_raw
(gateway: Gateway, body: Mapping[str, JsonValue])
tests/integration/providers/test_responses_bridge_tool_search_undeferred_wire.py:321
↓ 10 callersFunction_reads
Admin detail reads that take their id as a query parameter, which S2 does not fill.
tests/integration/security/test_stored_config_slots.py:161
↓ 10 callersFunction_real_user_api_key_dict
(parent_span)
tests/unit/integrations/open_telemetry/test_otel_admin_endpoints.py:28
↓ 10 callersFunction_realtime_http_logging
(route: str)
tests/unit/realtime_api/test_main.py:1981
↓ 10 callersMethod_record_partial_usage_for_failure
A stream that breaks mid-flight still billed the provider for the chunks already delivered. Recover that partial usage from the chunk
litellm/litellm_core_utils/streaming_handler.py:2776
↓ 10 callersFunction_record_swallowed_redis_failure
Record a Redis failure that the calling method is about to swallow. The marker is a ContextVar rather than a counter on the breaker because break
litellm/caching/redis_cache.py:348
↓ 10 callersFunction_recorded_guardrail_info
(container)
tests/unit/proxy/guardrails/guardrail_hooks/azure/test_azure_prompt_shield.py:369
↓ 10 callersFunction_refresh_native
(refresh_token, client_id, minter, cache, **overrides)
tests/unit/proxy/mcp_server/test_gateway_dcr_flow.py:1858
↓ 10 callersFunction_refs
()
tests/unit/proxy/auth/test_auth_object_prefetch.py:105
↓ 10 callersFunction_register
( proxy: ProxyClient, resources: ResourceManager, params: LiteLLMParamsBody | None = None, pre
tests/e2e/llm_translation/test_messages_e2e.py:93
↓ 10 callersFunction_relay_client_request
(method: str = "GET", headers: Mapping[str, str] | None = None)
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:6273
↓ 10 callersFunction_relayed_in
(events: Sequence[JsonValue])
tests/integration/providers/test_anthropic_refusal_stop_details_wire.py:472
↓ 10 callersFunction_remove_default_user
(gateway: Gateway, team_id: str)
tests/integration/management/test_team_member_lifecycle.py:170
↓ 10 callersFunction_repin_key
(caller: str = "caller-1")
tests/unit/router_utils/pre_call_checks/test_session_id_affinity.py:64
↓ 10 callersFunction_require_row
( rows: list[SpendLogRow], predicate: Callable[[SpendLogRow], bool], what: str )
tests/e2e/quota_management/spend_tracking/test_spend_tracking_e2e.py:70
↓ 10 callersFunction_resolve_one
Resolve a single value that may be a passthrough managed ID. Returns the raw provider ID on success. Returns *managed_id* unchanged when
litellm/proxy/pass_through_endpoints/managed_id_rewriter.py:310
↓ 10 callersFunction_resource_server
(**overrides)
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:11469
↓ 10 callersFunction_resp
(payload, status_code: int = 200)
tests/unit/llms/nimble/search/test_nimble_search_transformation.py:14
↓ 10 callersFunction_resp_with_content
Build a ModelResponse-like object with a single assistant message.
tests/unit/router_strategy/adaptive_router/test_hooks.py:28
↓ 10 callersFunction_responses_payload
(output: list[object], status: str = "completed", **response_fields: object)
tests/unit/integrations/otel/test_otel_v2_sources_of_truth.py:770
↓ 10 callersFunction_retrieval_data
(model_id: str)
tests/unit/proxy/policy_engine/test_response_retrieval.py:90
↓ 10 callersFunction_revision_row
(revision)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:19126
↓ 10 callersFunction_route_invoice_reader_to_clairic
( monkeypatch: pytest.MonkeyPatch, drop_params: bool = False, additional_drop_params: tuple[str, ...] = ()
tests/unit/proxy/decisions_endpoints/test_endpoints.py:1371
↓ 10 callersMethod_routed_config
Clone the config, rewriting headers on the callback's own exporter. Both header sets apply only to the exporter ``self._callback_name``
litellm/integrations/otel/plumbing/routing.py:355
↓ 10 callersFunction_routed_features
(candidate: Gateway)
tests/integration/configuration/test_lazy_routes_flag.py:60
↓ 10 callersFunction_routed_prisma_client
(deployment_count: int, writer_unavailable: bool = False)
tests/unit/proxy/management_helpers/test_access_group_model_sync.py:16
↓ 10 callersFunction_router
(model_group_alias: dict[str, object] | None = None)
tests/unit/proxy/policy_engine/test_response_retrieval.py:39
↓ 10 callersFunction_router_pick
(router: Router, group: str = ROUTER_GROUP)
tests/unit/router_strategy/test_least_busy.py:668
↓ 10 callersFunction_row
(budget_id: str, **overrides: Any)
tests/unit/proxy/management_endpoints/management_v1/test_budgets.py:58
↓ 10 callersFunction_row_payload_bytes
Bytes this row contributes to the encoded write statement. The whole row is serialized rather than its values summed, so the count includes t
litellm/proxy/db/spend_log_batching.py:35
↓ 10 callersFunction_row_to_policy_db_response
Build PolicyDBResponse from a Prisma LiteLLM_PolicyTable row.
litellm/proxy/policy_engine/policy_registry.py:141
↓ 10 callersFunction_run
(source: str, argv: tuple[str, ...], home: Path)
tests/unit/test_litellm_cli.py:238
↓ 10 callersMethod_run
(self, provider, destinations=(LANGFUSE_DEST,))
tests/unit/integrations/otel/test_otel_v2_destinations.py:204
↓ 10 callersMethod_run
( provider: TracerProvider, destinations: tuple[OtelDestination, ...], attributes: Mapping[str, object
tests/unit/integrations/otel/test_otel_v2_destinations.py:5138
↓ 10 callersFunction_run_post_custom_auth_checks
( valid_token: UserAPIKeyAuth, request: Request, request_data: dict[str, object], route: str,
litellm/proxy/auth/user_api_key_auth.py:4943
↓ 10 callersMethod_run_view_setup
( self, poll_interval_seconds: float = _VIEW_SETUP_POLL_INTERVAL_SECONDS, deadline_sec
litellm/proxy/utils.py:7940
↓ 10 callersFunction_run_websearch_init
(monkeypatch, stored_params, starting_callbacks)
tests/unit/proxy/proxy_server/test_proxy_config.py:6315
↓ 10 callersFunction_safe_body_matcher
Compare request bodies as bytes; never invokes ``json.loads``. vcrpy's stock ``body`` matcher unconditionally json-decodes ``application/json
tests/_vcr_conftest_common.py:671
↓ 10 callersFunction_sample_agent_config
()
tests/unit/proxy/agent_endpoints/test_endpoints.py:73
↓ 10 callersFunction_sampling_msg
(role: str, content: Any)
tests/unit/proxy/mcp_server/test_mcp_sampling_tool_conversion.py:41
↓ 10 callersFunction_scans
(policy: Wire)
tests/integration/observability/test_bedrock_guardrail_attachments.py:315
↓ 10 callersMethod_score_and_classify
Classify a prompt by complexity, reporting whether the score chose the tier. Args: prompt: The user's prompt/message.
litellm/router_strategy/complexity_router/complexity_router.py:1838
↓ 10 callersFunction_scripted
(response: RoutedResponse | SseResponse, count: int = 1)
tests/integration/spend/test_background_response_billing_proxies.py:69
↓ 10 callersMethod_seed_and_run
(self, model, custom_llm_provider, api_base=None, prompt_cache_options=None)
tests/unit/integrations/test_anthropic_cache_control_hook.py:3990
↓ 10 callersFunction_seeded_tables
()
tests/unit/proxy/db/test_master_key_migration.py:91
↓ 10 callersFunction_send
( gateway: Gateway, route: Route, marker: str, headers: Mapping[str, str] = MappingProxyType({}) )
tests/integration/providers/test_assistants_route_errors_wire.py:120
↓ 10 callersFunction_send
(candidate: Gateway, model: str, key: str, identity: str)
tests/integration/observability/test_s3_v2_upload_fanout.py:373
↓ 10 callersFunction_send_everything
(consent: TelemetryConsent)
tests/unit/telemetry/test_consent.py:102
↓ 10 callersFunction_send_ok
(gateway: Gateway, identity: str, marker: str, path: str = "/a2a/{id}")
tests/integration/compatibility/test_a2a_protocol_version_override.py:73
↓ 10 callersFunction_sent_messages
(respx_mock: respx.MockRouter)
tests/unit/test_main.py:11109
↓ 10 callersFunction_serve
(websocket: _FakeWebSocket, user_api_key_dict: UserAPIKeyAuth | None = None)
tests/unit/proxy/pass_through_endpoints/test_deepgram_ws_passthrough_routes.py:104
↓ 10 callersFunction_served_id
(backend: str, marker: str, attempt: int)
tests/integration/routing/test_messages_stream_retry_budget_sources_owned_proxy.py:66
↓ 10 callersFunction_server
(text: str, client_frames_before: int)
tests/unit/test_ws_vcr.py:35
↓ 10 callersFunction_serves_pdf
(mode: str, url: str, **kwargs)
tests/unit/litellm_core_utils/test_image_handling.py:787
↓ 10 callersFunction_session_request
( agent_id: str | None = None, caller: str = "caller-hash" )
tests/unit/test_router/core/test_selection_characterization_prerouting.py:344
↓ 10 callersFunction_setup_mcp_call_environment
Patch MCP globals so _execute_tool_calls can run in tests.
tests/unit/responses/mcp/test_litellm_proxy_mcp_handler.py:52
↓ 10 callersFunction_signatures_of
(body: Mapping[str, object], key: str = "thoughtSignature")
tests/unit/llms/vertex_ai/gemini/test_rejected_thought_signature_retry.py:98
↓ 10 callersFunction_simulate_price_data_reload
Drive what a price data reload does to this process's litellm state. Mirrors `litellm.proxy.proxy_server._swap_in_model_cost_map`, which is the
tests/unit/test_router_model_cost_isolation.py:53
↓ 10 callersFunction_single_spend_row
(key: str)
tests/integration/spend/test_service_tier_stream_billing.py:146
↓ 10 callersFunction_single_team
(model: str = "azure/gpt-4.1")
tests/unit/router_utils/test_ptu_shares.py:43
↓ 10 callersFunction_spans
(requests: tuple[Request, ...])
tests/integration/observability/_openinference_support.py:536
↓ 10 callersFunction_spend_logs_prisma
(inserted: int, existing: object, taken_over: int = 1)
tests/unit/proxy/db/test_db_spend_update_writer.py:4434
↓ 10 callersFunction_spend_row
(request_id: str)
tests/integration/providers/test_bedrock_converse_missing_content_wire.py:251
↓ 10 callersFunction_spend_row
(call_id: str)
tests/integration/providers/test_databricks_decisions_wire.py:161
↓ 10 callersFunction_spend_rows
(call_id: str, call_type: str, status: str)
tests/integration/mcp/test_mcp_llm_endpoints.py:945
↓ 10 callersFunction_start_request
(frames: tuple[str | bytes, ...])
tests/unit/llms/soniox/realtime/test_soniox_realtime_transformation.py:49
↓ 10 callersFunction_stored
(caller: Caller, response_id: str, *, masked: bool = True, cache: bool = False)
tests/integration/security/test_hide_secrets_tool_compatibility.py:202
↓ 10 callersFunction_stream
(gateway: Gateway, body: Mapping[str, JsonValue])
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_messages_pre_content_retry_wire.py:130
↓ 10 callersFunction_stream
(client: str, router: Router, **request: object)
tests/integration/sdk/test_router_sync_stream_fallback_wire.py:125
↓ 10 callersFunction_success
(custom_id: str, prompt_tokens: int, completion_tokens: int)
tests/unit/batches/test_batch_line_items.py:41
↓ 10 callersFunction_success_kwargs
( *, provider_in_litellm_params: str | None, provider_in_payload: str | None, call_type: str =
tests/unit/router_strategy/test_budget_limiter.py:36
↓ 10 callersMethod_supports_model_capability
Check a boolean capability ``key`` in the model map under the caller's provider. The provider-aware lookup is authoritative when it resolves
litellm/llms/anthropic/common_utils.py:1105
↓ 10 callersMethod_sync
(self, coro: Coroutine[object, object, T])
litellm/llms/deepagents/harness/sandbox_backend.py:174
↓ 10 callersFunction_sync_call
( endpoints: ContextCachingEndpoints, client: HTTPHandler, api_key: str = "k", custom_llm_prov
tests/unit/llms/vertex_ai/context_caching/test_known_cached_contents.py:64
↓ 10 callersFunction_table
(rows=())
tests/unit/proxy/management_helpers/test_resource_display_names.py:17
↓ 10 callersFunction_targets
(wire: Wire)
tests/integration/providers/test_inferenceapis_wire.py:206
↓ 10 callersFunction_task
(**fields: object)
tests/unit/llms/volcengine/test_volcengine_video_transformation.py:79
↓ 10 callersFunction_team_router
(primary_mock_response: str | None = None, fallback_mock_response: str | None = None)
tests/unit/proxy/test_fallback_management_endpoints.py:160
↓ 10 callersFunction_team_rows
(team_id: str)
tests/integration/management/test_team_delete_inputs.py:52
↓ 10 callersFunction_team_with_admin
A team with a tpm_limit, and the key of a user who is an admin of that team.
tests/e2e/management/test_team_management_e2e.py:446
↓ 10 callersFunction_teams_by_id
A team lookup that knows exactly `team_ids` and, like the real one, reports any other id as provably absent.
tests/unit/proxy/auth/test_handle_jwt.py:5923
↓ 10 callersFunction_tiered_model
( scenario: Scenario, wire: Wire, *, litellm_model: str, api_base: str | None = None,
tests/integration/spend/test_service_tier_stream_billing.py:109
← previousnext →6,801–6,900 of 202,479, ranked by callers