MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 19 callersFunction_bearer_peer
(expected: Mapping[str, JsonValue], reply: Reply)
tests/integration/providers/test_bedrock_mantle_claude_chat_wire.py:170
↓ 19 callersFunction_body
(model: str, messages: list[JsonValue], **extra: JsonValue)
tests/integration/messages_endpoint/test_tool_result_text_wire.py:58
↓ 19 callersFunction_body
(ttl: str = "5m", *, extended: bool = False)
tests/unit/proxy/management_endpoints/test_prompt_cache_prediction.py:39
↓ 19 callersFunction_bridged_request
( *items: Mapping[str, object], model: str = f"bedrock/{_CLAUDE_ON_BEDROCK}", custom_llm_provider:
tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py:6466
↓ 19 callersFunction_build_oauth_protected_resource_response
Build OAuth protected resource response with the appropriate URL pattern. For pass-through MCP servers, the gateway proxies the upstream's o
litellm/proxy/mcp_server/discoverable_endpoints.py:2980
↓ 19 callersFunction_chat
(gateway: Gateway, model: str, marker: str, **params: JsonValue)
tests/integration/providers/test_bedrock_runtime_chat_completions_wire.py:112
↓ 19 callersFunction_chat_body
(model: str, text: str, guardrail: str | None, stream: bool = False)
tests/integration/observability/test_cache_hit_guardrail_metrics.py:330
↓ 19 callersFunction_chat_provider
(message: dict[str, JsonValue])
tests/integration/observability/test_grayswan_wire.py:128
↓ 19 callersFunction_chat_response
(identity: str, calls: Sequence[dict[str, JsonValue]] | None = None)
tests/integration/observability/_openinference_support.py:878
↓ 19 callersFunction_claude_chat_entry
(custom_id: str | None, content: str, **body: object)
tests/unit/llms/vertex_ai/files/test_vertex_ai_files_transformation.py:1987
↓ 19 callersFunction_cleared_ids
(messages: list[dict[str, object]])
tests/unit/llms/anthropic/messages/context_management/test_clear_tool_uses.py:330
↓ 19 callersFunction_compile
(code: str)
tests/unit/proxy/guardrails/test_custom_code_security.py:41
↓ 19 callersFunction_complete
(case: _Case, params: Mapping[str, JsonValue])
tests/unit/llms/base_llm/chat/test_provider_chat_translation.py:590
↓ 19 callersMethod_config
(**overrides: object)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:14650
↓ 19 callersFunction_config_with
( directory: Path, otel_audit_config: AuditConfigWriter, *, otel: Mapping[str, JsonValue] = Ma
tests/integration/observability/test_otel_excluded_services.py:76
↓ 19 callersFunction_create_mock_client
Utility to create a mocked async httpx client for the given method. ``status_code`` and ``headers`` are part of the real response the tool functi
tests/unit/proxy/mcp_server/test_openapi_to_mcp_generator.py:214
↓ 19 callersFunction_created
(name: str, expire_time: str | None)
tests/unit/llms/vertex_ai/context_caching/test_known_cached_contents.py:59
↓ 19 callersFunction_decide
( gateway: Gateway, route: Route, model: str, marker: str, images: Sequence[JsonValue], **extra: JsonValue
tests/integration/providers/test_cloudflare_clef_images_wire.py:169
↓ 19 callersFunction_decide
(gateway: Gateway, model: str, route: _Route = _SYSTEMONE, **extra: JsonValue)
tests/integration/providers/test_strands_decider_agentcore_wire.py:346
↓ 19 callersFunction_deploy
(scenario: Scenario, row: Row, api_base: str)
tests/integration/providers/test_api_base_url_join_wire.py:73
↓ 19 callersFunction_deployment
(scenario: Scenario, wire: Wire, **overrides: JsonValue)
tests/integration/providers/test_bedrock_runtime_chat_completions_wire.py:100
↓ 19 callersFunction_deployment
(scenario: Scenario, provider: Provider, wire_url: str, upstream_url: str)
tests/integration/providers/test_anthropic_thinking_signature_stream_wire.py:110
↓ 19 callersFunction_deployment
( scenario: Scenario, wire: Wire, backend: str, mode: str | None, *, provider_pin: boo
tests/integration/routing/test_deployment_mode_routing_wire.py:150
↓ 19 callersFunction_deployment
(name: str, reply: object)
tests/unit/test_router/test_router_fuzz_regressions_rust_only.py:30
↓ 19 callersFunction_embeddings_entry
(**overrides)
tests/unit/llms/vertex_ai/files/test_vertex_ai_files_transformation.py:1211
↓ 19 callersFunction_enable
(monkeypatch: pytest.MonkeyPatch)
tests/unit/proxy/auth/test_personal_key_team_model_access.py:51
↓ 19 callersFunction_extract_converse_texts
Walk a Bedrock Converse request body and collect text content. Returns (texts, holders) where each holder is the (container, key) pair t
litellm/llms/bedrock/passthrough/guardrail_translation/handler.py:236
↓ 19 callersFunction_first_turn
()
tests/integration/providers/test_ollama_prompt_tools_wire.py:216
↓ 19 callersFunction_forwarded
(rig: _Rig, response: httpx.Response)
tests/integration/observability/test_bedrock_converse_guardrail_rewrites.py:355
↓ 19 callersFunction_generation
( tracing, *, name="gen", trace_id=TRACE_A, parent=None, existing=False, observati
tests/unit/integrations/langfuse/test_langfuse_sdk.py:91
↓ 19 callersMethod_get_agentic_loop_settings
(kwargs: dict)
litellm/llms/custom_httpx/llm_http_handler.py:5969
↓ 19 callersFunction_get_jwt_handler_with_scripted_endpoint
( cache: "DualCache", endpoint: _ScriptedJWKSEndpoint, public_key_ttl: float = 600, public_key
tests/unit/proxy/auth/test_handle_jwt.py:4262
↓ 19 callersFunction_handle
( messages: Sequence[Mapping[str, object]], kwargs: Mapping[str, object] = MappingProxyType({}), l
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_openai_websocket_passthrough_logging_handler.py:83
↓ 19 callersMethod_handle_logging_proxy_only_error
Handle logging for proxy only errors by calling `litellm_logging_obj.async_failure_handler` Is triggered when self._is_proxy_only_er
litellm/proxy/utils.py:4249
↓ 19 callersFunction_headers
(headers: BaseModel)
tests/e2e/e2e_http.py:283
↓ 19 callersFunction_identities
(observed: Seen, response_id: str)
tests/integration/providers/test_gemini_long_decode_wire.py:309
↓ 19 callersFunction_identity
(prefix: str)
tests/integration/compatibility/test_openai_sdk_client_paths.py:84
↓ 19 callersMethod_litellm_params
(self)
tests/unit/llms/bedrock/files/test_bedrock_files_transformation.py:2289
↓ 19 callersFunction_make_batch_response
Create a LiteLLMBatch response with hidden params set as the router would.
tests/unit/enterprise/proxy/test_managed_files_hook.py:43
↓ 19 callersFunction_make_challenge
(verifier: str)
tests/unit/proxy/mcp_server/test_byok_oauth_endpoints.py:39
↓ 19 callersFunction_make_key_obj
(token: str = "tok")
tests/unit/proxy/common_utils/test_user_api_key_cache.py:51
↓ 19 callersFunction_mock_mcp_resolution_prisma_client
( server: LiteLLM_MCPServerTable, key_permission: LiteLLM_ObjectPermissionTable, team: LiteLLM_Tea
tests/unit/proxy/management_endpoints/test_mcp_management_endpoints.py:9188
↓ 19 callersFunction_models
(*rows, **kwargs)
tests/unit/proxy/common_utils/test_codex_model_catalog.py:83
↓ 19 callersFunction_msgs
(block)
tests/unit/proxy/guardrails/guardrail_hooks/test_ovalix_extraction.py:145
↓ 19 callersFunction_native_handle
(client: object)
tests/unit/rust_bridge/host/test_secret_manager.py:70
↓ 19 callersFunction_open_chat_echo_stream
( logging_obj: Logging, metadata: dict[str, object] | None = None )
tests/unit/responses/mcp/test_chat_completions_handler.py:1799
↓ 19 callersFunction_params
(region: str, compartment_id: object = None)
tests/unit/llms/oci/test_oci_common_utils.py:237
↓ 19 callersMethod_patch_key_reload
Patch the live-policy dependencies of the admission arm: the ``get_key_object`` reload, the ``prisma_client`` / ``user_api_key_cache`` globals
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:6643
↓ 19 callersFunction_payload
(response: httpx.Response)
tests/integration/providers/test_vertex_partner_count_tokens_wire.py:232
↓ 19 callersMethod_pre_call
( self, data: dict[str, object], user_api_key_dict: ProxyUserAPIKeyAuth, rig:
tests/unit/proxy/test_common_request_processing.py:8513
↓ 19 callersMethod_prepare_payload
(self, model: str, api_params: WatsonXAPIParams)
litellm/llms/watsonx/common_utils.py:342
↓ 19 callersFunction_proxy_config
(file_general_settings: dict | None = None)
tests/unit/proxy/management_endpoints/test_coordination_redis_endpoints.py:60
↓ 19 callersFunction_raw
(gateway: Gateway, path: str, body: Mapping[str, JsonValue])
tests/integration/providers/test_responses_bridge_tool_search_wire.py:329
↓ 19 callersMethod_recording_logger
(journal: list, error: Exception | None = None)
tests/unit/proxy/common_utils/test_check_batch_cost.py:3879
↓ 19 callersFunction_register
(scenario: Scenario, body: dict[str, JsonValue], *, status: int = 200)
tests/integration/providers/test_decisions_openai_format_wire.py:306
↓ 19 callersFunction_relay_client_frames
( frames: Sequence[str | bytes], gate: WebsocketFrameModelGate | None, user_api_key_dict: UserAPIK
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:7959
↓ 19 callersFunction_reload_schedule_row
LiteLLM_Config row shape: admin-owned interval in param_value, run state in dedicated columns
tests/unit/proxy/test_proxy_server_endpoints_and_startup.py:4612
↓ 19 callersMethod_resolve_static_headers_with_env_vars
Return server.static_headers with ``${NAME}`` interpolated. Globals come from ``server.env_vars`` entries with ``scope=="global"``. P
litellm/proxy/mcp_server/mcp_server_manager.py:4179
↓ 19 callersFunction_response
(status_code: int, text: str = "")
tests/unit/integrations/newrelic/test_newrelic_metrics.py:99
↓ 19 callersFunction_roster
(prisma: _FakePrisma, team_id: str)
tests/unit/proxy/management_helpers/test_bulk_user_deletion.py:244
↓ 19 callersFunction_route_payload
(call_type: str, model: str, response: Mapping[str, object])
tests/unit/integrations/otel/test_otel_v2_sources_of_truth.py:983
↓ 19 callersMethod_run
(provider, destinations)
tests/unit/integrations/otel/test_otel_v2_destinations.py:2529
↓ 19 callersMethod_run_reconnect_cycle
Run a reconnect cycle with a single overall timeout budget. Uses the _engine_confirmed_dead flag (set by waitpid thread / pidfd / po
litellm/proxy/utils.py:7497
↓ 19 callersFunction_scope
( *, table: DailyActivityTable = DailyActivityTable.USER, entity_ids: tuple[str, ...] | None = ("u
tests/unit/repositories/test_daily_activity_sql.py:25
↓ 19 callersMethod_serialize_chunk
Serialize a streaming chunk to a JSON string for WebSocket transmission.
litellm/responses/streaming_iterator.py:3217
↓ 19 callersFunction_server
(**overrides)
tests/unit/proxy/mcp_server/test_oauth2_token_cache.py:23
↓ 19 callersFunction_session
(callback: httpx.Response)
tests/integration/authorization/test_sso_blank_identity.py:433
↓ 19 callersFunction_shield_prompts
(requests: tuple[Request, ...])
tests/integration/observability/test_azure_content_safety_audit.py:316
↓ 19 callersFunction_spend_log_transaction
(mock_prisma: MagicMock, query_raw: AsyncMock)
tests/unit/proxy/spend_tracking/test_key_metadata_recovery.py:66
↓ 19 callersFunction_statuses
(responses: tuple[httpx.Response, ...])
tests/integration/management/test_batch_file_usage_caps.py:148
↓ 19 callersFunction_strategy_router_write_violation
Reject writes that would corrupt a strategy router's pseudo-model. An auto-router deployment's ``litellm_params.model`` (``auto_router/...``) is
litellm/proxy/management_endpoints/model_management_endpoints.py:386
↓ 19 callersMethod_tier_pools
(self)
litellm/router_strategy/complexity_router/complexity_router.py:3129
↓ 19 callersFunction_transient_failure_response
(status: int = 503)
tests/unit/integrations/test_s3_v2.py:3363
↓ 19 callersFunction_turn_taking_client
A client that sends each frame, and then leaves, once the answers due by then reached it (by default the answer to every earlier frame), and that
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:8365
↓ 19 callersFunction_upstream
( prompt: str, failure: _Failure, attempts: Attempts, *, failing_attempts: int = 1, stream: bool = True )
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_messages_pre_content_retry_wire.py:97
↓ 19 callersFunction_window_spend_enqueue_env
Point increment_spend_counters at throwaway caches and a real WindowSpendUpdateQueue, and hand back the queue to inspect.
tests/unit/proxy/test_proxy_server_endpoints_and_startup.py:13822
↓ 19 callersFunction_wire_update_team
Mock just enough of update_team to reach (or pass) the estimate gate.
tests/unit/proxy/management_endpoints/test_team_endpoints.py:15853
↓ 19 callersFunction_write_home_json
(home: Path, filename: str, payload: dict[str, object])
tests/unit/proxy/client/cli/test_auth_commands.py:51
↓ 19 callersMethodaclose
(self)
tests/unit/test_redis.py:789
↓ 19 callersMethodaembedding
( # pyright: ignore[reportIncompatibleMethodOverride] # see acompletion self, model: str, input:
litellm/router.py:275
↓ 19 callersFunctionagent
(**overrides: object)
tests/unit/proxy/agent_endpoints/auth/test_managed_authorization.py:29
↓ 19 callersMethodaggregated
(req: DailyActivityRequest)
ui/litellm-dashboard/src/app/(dashboard)/usage/_components/components/EntityUsage/entityFetchFns.ts:21
↓ 19 callersMethodaiter_text
(self)
litellm/a2a_protocol/providers/watsonx_orchestrate/handler.py:78
↓ 19 callersMethodanalyze_text
Send text to the Presidio analyzer endpoint and get analysis results Texts larger than ``presidio_analyze_chunk_size_bytes`` (UTF-8)
litellm/proxy/guardrails/guardrail_hooks/presidio.py:474
↓ 19 callersMethodapply_guardrail
Apply the DeepKeep AI Firewall guardrail to the given inputs. This is the main method called by the LiteLLM framework for guardrail
litellm/proxy/guardrails/guardrail_hooks/deepkeep/deepkeep.py:325
↓ 19 callersFunctionasend_message
Async: Send a message to an A2A agent. Uses the @client decorator for LiteLLM logging and tracking. If litellm_params contains custom_ll
litellm/a2a_protocol/main.py:442
↓ 19 callersMethodasync_check_and_create_cache
Receives - messages: List of dict - messages in the openai format Returns - messages - List[dict] - filtered list of
litellm/llms/vertex_ai/context_caching/vertex_ai_context_caching.py:561
↓ 19 callersMethodasync_log_success_event
( self, kwargs: Mapping[str, object], response_obj: object, start_time: datetime, end_time: datetime
tests/unit/router_strategy/complexity_router/test_jev_classifier.py:43
↓ 19 callersMethodasync_success_handler
Restores trace_id/session_id contextvars once this attempt's own success logging (including any nested calls its callbacks trigger) is fully d
litellm/litellm_core_utils/litellm_logging.py:4162
↓ 19 callersMethodattach
(&self, f: F)
litellm-rust/crates/host-python/src/lib.rs:62
↓ 19 callersMethodbatch_metadata
(self, job: ManagedObjectRow, object_id: str)
enterprise/litellm_enterprise/proxy/common_utils/managed_object_attribution.py:160
↓ 19 callersFunctionbuild_inspection_messages
Synthesize a chat-style messages list for posting to a guardrail API. Each returned message has a plain-string ``content`` — multimodal text
litellm/proxy/guardrails/_content_utils.py:551
↓ 19 callersFunctionbundled_codex_models
Codex's bundled catalog by slug, read once from the vendored file.
litellm/proxy/common_utils/codex_model_catalog.py:155
↓ 19 callersFunctionc
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 19 callersFunctioncache
(clock: &Clock, capacity: usize)
litellm-rust/crates/cache-memory/tests/cache.rs:32
↓ 19 callersMethodcall
(self, cell: _Cell)
tests/integration/providers/test_device_code_login_guard_wire.py:120
↓ 19 callersMethodcall_tool
Call a tool with the given name and arguments Args: server_name: Server name name: Tool name arg
litellm/proxy/mcp_server/mcp_server_manager.py:7057
↓ 19 callersFunctioncan_key_call_resolved_model
( model: str, llm_model_list: Sequence[object] | None, valid_token: UserAPIKeyAuth, llm_router
litellm/proxy/auth/auth_checks.py:5597
↓ 19 callersFunctionchain
(make_core: MakeCore, **arguments: object)
tests/unit/test_router/core/test_usage_and_failure_counting_parity.py:104
↓ 19 callersMethodchat
( self, key: str, model: str, content: str, *, max_tokens: int
tests/e2e/quota_management/spend_tracking/spend_e2e_client.py:269
← previousnext →2,901–3,000 of 202,479, ranked by callers