MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 11 callersFunction_oversized_response_id
()
tests/unit/integrations/test_s3_v2.py:1631
↓ 11 callersFunction_owners
Stand-in owners for the real `lite up` / `lite autoroute start` registry.
tests/unit/proxy/client/cli/test_claude_settings.py:45
↓ 11 callersMethod_parse_lines
(lines: list[str])
litellm/llms/e2b/sandbox/transformation.py:176
↓ 11 callersMethod_parse_s3_uri
Parse S3 URI to extract bucket name and object key. Args: s3_uri: S3 URI (e.g., "s3://bucket-name/path/to/file")
litellm/llms/bedrock/files/handler.py:47
↓ 11 callersFunction_parse_sse
(raw: bytes)
tests/unit/llms/anthropic/messages/adapters/test_streaming_iterator_mid_stream_error.py:75
↓ 11 callersFunction_parsed_response_json
(raw_response: httpx.Response)
litellm/llms/openai/evals/transformation.py:38
↓ 11 callersFunction_payload
(transcript: Path, session_id: str = SESSION_ID)
tests/unit/proxy/client/cli/test_statusline_script.py:77
↓ 11 callersFunction_peer
(route: Callable[[Request], Reply | None])
tests/integration/compatibility/test_openai_sdk_client_paths.py:110
↓ 11 callersFunction_ping
(model: str = CHEAP_OPENAI_MODEL)
tests/e2e/other/test_jwt_auth_e2e.py:108
↓ 11 callersFunction_png_data_url
(width: int, height: int)
tests/unit/litellm_core_utils/test_token_counter.py:3176
↓ 11 callersFunction_policy_table
(prisma_client: "PrismaClient")
litellm/proxy/policy_engine/policy_registry.py:129
↓ 11 callersFunction_poll
(rig: _Rig, video_id: str, key: str | None = None)
tests/integration/routing/test_video_poll_routing_wire.py:206
↓ 11 callersFunction_post
(rig: _Rig, path: str, body: Mapping[str, JsonValue])
tests/integration/providers/test_chatgpt_responses_caller_stream_wire.py:100
↓ 11 callersFunction_post_call_guardrail
(on_flagged_action: str = "monitor")
tests/unit/proxy/guardrails/guardrail_hooks/test_grayswan.py:622
↓ 11 callersFunction_post_call_statuses
(rig: _DisconnectRig, model: str, rows: int = 1)
tests/integration/observability/test_guardrail_effects.py:2621
↓ 11 callersFunction_post_returning
(mapping_fn)
tests/unit/proxy/guardrails/guardrail_hooks/test_ovalix.py:698
↓ 11 callersMethod_pre_call_with_fallbacks
( self, request: Request, general_settings: dict, proxy_logging_obj: ProxyLogg
litellm/proxy/common_request_processing.py:2864
↓ 11 callersMethod_prepare_completion_kwargs
Prepare kwargs for litellm.completion/acompletion
litellm/google_genai/adapters/handler.py:39
↓ 11 callersFunction_prisma
(rows: dict[str, object] | None = ALL_ROWS)
tests/unit/proxy/auth/test_auth_object_prefetch.py:78
↓ 11 callersMethod_prisma_with_workers
(live_workers=None, error=None)
tests/unit/proxy/health_endpoints/test_health_endpoints.py:5772
↓ 11 callersFunction_probe
(caller: McpCaller, name: str, server_id: str)
tests/integration/mcp/test_mcp_listed_tool_metadata.py:118
↓ 11 callersFunction_process_all
(events: list)
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_streaming_iterator.py:33
↓ 11 callersMethod_process_includes
Process includes by appending their contents to the main config Handles nested config.yamls with `include` section Example
litellm/proxy/proxy_server.py:6065
↓ 11 callersMethod_process_response_create
Parse one ``response.create`` event, call ``litellm.aresponses(stream=True)``, and forward every streaming event to the client.
litellm/responses/streaming_iterator.py:3598
↓ 11 callersFunction_profile
(user_id: str, email: str)
tests/integration/authorization/test_sso_blank_identity.py:119
↓ 11 callersFunction_prompt
()
tests/integration/observability/test_prometheus_deployment_failure_api_provider.py:251
↓ 11 callersFunction_prompt
(shape: ShapeName, tag: str)
tests/integration/messages_endpoint/chat_bridge/test_chat_bridge_multi_tool_call_blocks_wire.py:361
↓ 11 callersFunction_provider_config
(collector: _RecordingCollector)
tests/unit/passthrough/test_streaming_interrupt_spend_tracking.py:53
↓ 11 callersFunction_ptu_success_kwargs
()
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:9234
↓ 11 callersFunction_ptu_terms
(shares: Mapping[str, JsonValue] | None, count: int)
tests/integration/management/test_ptu_share_guards.py:67
↓ 11 callersFunction_query_response
(task: dict)
tests/unit/llms/minimax/videos/test_minimax_video_transformation.py:48
↓ 11 callersMethod_queue_tool_call_delta_events
Convert chat-completions streaming `tool_calls` deltas into Responses API streaming events. We emit: - response.output_item.
litellm/responses/litellm_completion_transformation/streaming_iterator.py:466
↓ 11 callersFunction_quota_error
( models: list[str], rpm: dict[str, int] | None = None, tpm: dict[str, int] | None = None, set
tests/unit/enterprise/proxy/management_endpoints/test_project_endpoints_prisma.py:1626
↓ 11 callersFunction_read_ws_model_from_first_frame
Read the first WS frame and return (model, raw_message), or None on error. Sends an appropriate error frame and closes the socket before returnin
litellm/proxy/response_api_endpoints/endpoints.py:2000
↓ 11 callersFunction_reasoning_effort_sent_for_thinking
( model: str, provider: str | None, thinking: dict[str, object], *, tools: list[dict[str,
tests/unit/llms/anthropic/messages/adapters/test_handler_reasoning_effort_normalization.py:85
↓ 11 callersFunction_redact_mcp_credentials
Return a copy with secret credentials removed, keeping only non-secret admin config so the admin form can show and clear it. Non-admin and vir
litellm/proxy/management_endpoints/mcp_management_endpoints.py:680
↓ 11 callersFunction_redacting_logger
( **kwargs: Any, )
tests/unit/integrations/datadog/test_datadog_llm_obs.py:581
↓ 11 callersFunction_refresh
(client: TestClient, refresh_token: str)
tests/unit/proxy/anthropic_endpoints/test_gateway_endpoints.py:226
↓ 11 callersFunction_refusal
( reason: UnsafeMasterKeyReason = UnsafeMasterKeyReason.PUBLICLY_KNOWN, source: ConfigFileSource | Env
tests/unit/proxy/auth/test_master_key_boot_check.py:215
↓ 11 callersFunction_register
(gateway: Gateway, scenario: Scenario, provider: Provider, wire: Wire)
tests/integration/providers/test_gemini_thinking_replay_wire.py:160
↓ 11 callersFunction_register
( scenario: Scenario, route: str, *, streaming: bool = False, deployment_params: dict[str,
tests/integration/compatibility/test_missing_body_param_status.py:817
↓ 11 callersFunction_register
(proxy: ProxyClient, resources: ResourceManager)
tests/e2e/llm_translation/test_bedrock_native_e2e.py:89
↓ 11 callersFunction_registered_endpoint
(gateway: Gateway, scenario: Scenario, wire: Wire, *, auth: bool = True)
tests/integration/authorization/test_passthrough_route_denylist.py:20
↓ 11 callersFunction_relay_logging_result
( config: AzureAIPassthroughConfig, model: str, native_path: str, body, api_base: str = FO
tests/unit/llms/azure_ai/passthrough/test_azure_ai_passthrough_transformation.py:367
↓ 11 callersMethod_release
(self, keys: list[str], args: list[object])
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:8399
↓ 11 callersMethod_release_stashed_parallel_slot
( self, stash: RequestRateLimiterStash | None, parent_otel_span: Span | None,
litellm/proxy/hooks/parallel_request_limiter_v3.py:1662
↓ 11 callersFunction_replay
(*observations: BaselineObservation)
tests/unit/proxy/spend_tracking/test_baseline_accounting.py:72
↓ 11 callersFunction_replay
(turns: list)
tests/unit/router_strategy/adaptive_router/test_signals.py:22
↓ 11 callersFunction_replayed_fields
(message: Mapping[str, object])
tests/unit/completion_extras/litellm_responses_transformation/test_completion_extras_litellm_responses_transformation_history.py:240
↓ 11 callersFunction_reporting_guardrail
(call: str)
tests/unit/proxy/guardrails/test_custom_code_security.py:459
↓ 11 callersFunction_require_store
(uploads: PluginUploadStore | None)
litellm/proxy/discovery_endpoints/skill_hub_endpoints.py:259
↓ 11 callersFunction_resolve_active_litellm_key
Resolve the presented litellm key to an active key record, or say precisely why not. Single resolution path the OAuth token endpoint reuses, reso
litellm/proxy/mcp_server/bridge_token_flow.py:217
↓ 11 callersFunction_resolve_model_from_preferences
Resolve an LLM model name from MCP ModelPreferences. Strategy: 1. Check hints for substring matches against known model names. 2. Fal
litellm/proxy/mcp_server/sampling_handler.py:67
↓ 11 callersFunction_response
(ticks: object = None)
tests/unit/llms/xai/image_generation/test_cost_calculator.py:15
↓ 11 callersFunction_responses
(gateway: Gateway, model: str, marker: str, **fields: JsonValue)
tests/integration/providers/test_responses_bridge_verbosity_wire.py:98
↓ 11 callersFunction_responses_body
( model: str, marker: str, *directives: str, stream: bool | None = None, extra_body: Mappi
tests/integration/providers/test_chatgpt_responses_caller_stream_wire.py:83
↓ 11 callersFunction_responses_body
( model: str, marker: str, tools: Sequence[Mapping[str, JsonValue]], stream: bool )
tests/integration/providers/test_responses_bridge_tool_search_undeferred_wire.py:309
↓ 11 callersFunction_responses_router
(model: str)
tests/unit/router_utils/pre_call_checks/test_prompt_caching_deployment_check.py:1621
↓ 11 callersFunction_restore_model_cost_entries
(original_entries)
tests/unit/test_register_model_custom_pricing.py:37
↓ 11 callersFunction_rewriting_stream_guardrail
(transform: Callable[[Dict[str, Any]], Dict[str, Any]])
tests/unit/proxy/utils/proxy_logging/test_guardrail_pipeline.py:3271
↓ 11 callersMethod_rich_search_input
Extract the optional objective/search_queries pair from a tool input. Returns None when the input carries neither, so callers can pa
litellm/integrations/websearch_interception/handler.py:1513
↓ 11 callersFunction_rollup_prisma
(group_rows: list, daily_rows: list | None = None)
tests/unit/proxy/management_endpoints/test_tool_management_endpoints.py:118
↓ 11 callersFunction_round_cost
(body: Mapping[str, object])
tests/unit/responses/mcp/test_aresponses_api_with_mcp.py:1590
↓ 11 callersMethod_routed
Drive the real routing entry point and return the request kwargs it leaves behind.
tests/unit/router_strategy/test_complexity_router.py:17072
↓ 11 callersFunction_router
( strong_output_rate: float = 0.000015, *, free: bool = False, cheap_limit: int = 30000, strong_limit: int
tests/unit/proxy/common_utils/test_cache_aware_routing.py:61
↓ 11 callersFunction_router
(*deployments, **router_kwargs)
tests/unit/proxy/common_utils/test_discoverable_model_filter.py:25
↓ 11 callersMethod_router
( cls, cheap_response: str = "cheap response", fallbacks: list[dict[str, list[str]]] |
tests/unit/test_router/test_router.py:9116
↓ 11 callersFunction_row
(user_id="user-a", credential_name="copilot-cred", credential_b64="cipher", provider="github_copilot")
tests/unit/proxy/credential_endpoints/test_user_provider_credentials.py:41
↓ 11 callersFunction_row
( daily_spend: float = 0.0, monthly_spend: float = 0.0, baseline_spend: float = 0.0, )
tests/unit/integrations/SlackAlerting/test_user_spend_alerts.py:22
↓ 11 callersFunction_rpc
(result: dict, request_id: str = "1")
tests/unit/proxy/a2a/test_version_convert.py:21
↓ 11 callersFunction_run
(coro)
tests/unit/test_openai_record_replay_proxy.py:39
↓ 11 callersFunction_run
(args: list[str], transport: httpx.MockTransport)
tests/unit/db_scripts/test_strip_vector_store_internal_metadata.py:56
↓ 11 callersMethod_run
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:11
↓ 11 callersFunction_run_guard
( repo: Path, base: str, head: str, head_ref: str, *, target: str | None = None, t
tests/unit/test_cost_map_guard.py:388
↓ 11 callersFunction_sample_cassette_dict
()
tests/unit/test_vcr_redis_persister.py:30
↓ 11 callersFunction_sanitize_guardrail_information_for_spend_logs
When ``store_prompts_in_spend_logs`` is False, redact prompt-carrying fields (``guardrail_request``, ``guardrail_response``, ``match_details`
litellm/proxy/spend_tracking/spend_tracking_utils.py:1664
↓ 11 callersFunction_schema
(document: dict[str, object])
tests/unit/llms/anthropic/chat/test_anthropic_chat_transformation.py:8321
↓ 11 callersFunction_sealed_wire_json
(sealed, prefix, debug_key)
tests/unit/proxy/mcp_server/test_gateway_dcr_flow.py:1109
↓ 11 callersFunction_search_signature
(prefix: str, api_key: str, store_id: str)
tests/integration/authorization/test_rag_team_provider_credentials.py:814
↓ 11 callersFunction_send
( gateway: Gateway, upstream: Wire, endpoint: Endpoint, model: str, tags: Sequence[str],
tests/integration/routing/test_tag_routing_prefix.py:147
↓ 11 callersMethod_send
(self, **request_params)
tests/unit/llms/bedrock_mantle/test_bedrock_mantle_messages_transformation.py:377
↓ 11 callersFunction_send_messages
( path: str, accept_encoding: str | None, app: ASGIApp = APP, method: str = "GET", root_path: str = "" )
tests/unit/proxy/middleware/test_gzip_middleware.py:96
↓ 11 callersFunction_sent_body
(mock_post)
tests/unit/responses/test_responses_api_request_body.py:833
↓ 11 callersFunction_serve
( websocket: _FakeWebSocket, endpoint: str, user_api_key_dict: UserAPIKeyAuth, general_setting
tests/unit/proxy/test_openai_ws_passthrough_routes.py:139
↓ 11 callersFunction_service_parent
Helper: a live PROXY_REQUEST span to parent service spans under.
tests/unit/integrations/otel/test_otel_v2_logger.py:1900
↓ 11 callersFunction_session_cache_key
(user_id: str, credential_name: str, github_host: str)
litellm/llms/github_copilot/per_user_auth.py:215
↓ 11 callersFunction_session_header
(params: dict, litellm_params: dict)
tests/unit/a2a_protocol/providers/bedrock_agentcore/test_bedrock_agentcore_a2a.py:273
↓ 11 callersFunction_settings_client
( role: LitellmUserRoles, settings: TelemetrySettings, db: SettingsDatabase | None )
tests/unit/proxy/telemetry/test_endpoints.py:188
↓ 11 callersFunction_settle
Wait out the flush a full batch schedules, the way the proxy's loop would. The upload runs off the request path now, and either the batch ta
tests/unit/integrations/pointfive/test_logger.py:490
↓ 11 callersFunction_shadow_reply_router
A router whose shadow arm answers with a caller-supplied message, so a reply that yields no judgeable text can be posed as the two different thing
tests/unit/integrations/test_shadow_eval_logger.py:150
↓ 11 callersFunction_should_cooldown_based_on_deployment_policy
Resolve deployment-level allowed-fails and delegate to the shared counting logic. When the deployment's policy doesn't cover *original_exception*
litellm/router_utils/cooldown_handlers.py:195
↓ 11 callersMethod_should_skip_metrics_for_invalid_key
Determine if Prometheus metrics should be skipped for invalid API key requests. This is a centralized validation method that extract
litellm/integrations/prometheus.py:2901
↓ 11 callersFunction_size_cleaner
(settings: dict, **kwargs)
tests/unit/proxy/test_spend_log_cleanup.py:1777
↓ 11 callersFunction_snapshot_model_cost_entries
(keys)
tests/unit/test_register_model_custom_pricing.py:33
↓ 11 callersFunction_source
( github: _GitHub, clock: _Clock | None = None, *, failure_ttl: float = _TTL, max_versions
tests/unit/proxy/common_utils/test_codex_catalog_source.py:54
↓ 11 callersFunction_span_json
(logger_under_test: DataDogLLMObsLogger, payload: dict[str, Any])
tests/unit/integrations/datadog/test_datadog_llm_obs.py:589
↓ 11 callersFunction_spend_row
(*request_ids: str)
tests/integration/providers/test_gemini_thinking_replay_wire.py:459
↓ 11 callersFunction_split_pass_through_body
( body: str, user_api_key_dict: UserAPIKeyAuth = UserAPIKeyAuth(api_key="hashed-key") )
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:11104
↓ 11 callersFunction_stage_file
(repo: Path, relative: str, body: str)
tests/unit/test_pre_commit_lint.py:172
↓ 11 callersFunction_stagger
(scheduler: AsyncIOScheduler, identity: str = "pod-a:1", **overrides)
tests/unit/proxy/common_utils/test_scheduled_job_stagger.py:63
← previousnext →6,001–6,100 of 202,479, ranked by callers