MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 8 callersFunction_oauth_state_cookie_name
(relay_state: str)
litellm/proxy/mcp_server/discoverable_endpoints.py:509
↓ 8 callersFunction_observed
( buffer: _Observations, identity: str, expected_count: int = 1, )
tests/integration/compatibility/test_missing_body_param_status.py:911
↓ 8 callersFunction_ocr_row
(pages_processed, annotation_pages=None, model="mistral-ocr-latest")
tests/unit/batches/test_batch_utils.py:2034
↓ 8 callersMethod_on_engine_death_from_thread
Called on the event loop thread when the waitpid thread detects engine death.
litellm/proxy/utils.py:7290
↓ 8 callersFunction_only_request
(wire: Wire)
tests/integration/sdk/test_sagemaker_embedding_sdk.py:51
↓ 8 callersFunction_open_weights
(model_name: str, mode: str | None = None, upstream: str | None = None)
tests/unit/proxy/pass_through_endpoints/test_codex_passthrough_endpoints.py:239
↓ 8 callersFunction_openai_stream_cut_after
(partial: str)
tests/unit/llms/base_llm/responses/test_transformation.py:762
↓ 8 callersFunction_openai_tool
(function: Mapping[str, object])
tests/unit/litellm_core_utils/test_token_counter.py:588
↓ 8 callersFunction_openai_transcription_client
(transport: httpx.MockTransport)
tests/unit/llms/openai/transcriptions/test_gpt_transcribe.py:275
↓ 8 callersFunction_output_item_added_chunk
()
tests/unit/responses/mcp/test_mcp_streaming_iterator.py:46
↓ 8 callersFunction_over_httpx
(gateway: Gateway, endpoint: Endpoint, model: str, stream: bool)
tests/integration/providers/test_gemini_long_decode_wire.py:284
↓ 8 callersFunction_overlay_writer
(tmp_path)
tests/unit/proxy/client/cli/test_agents.py:220
↓ 8 callersFunction_override_live_session_authorizer
( monkeypatch: pytest.MonkeyPatch, authorizer: Callable[[WebSocket, str], Awaitable[UserAPIKeyAuth]],
tests/unit/proxy/test_proxy_server.py:3497
↓ 8 callersFunction_pair
(scenario: Scenario, params: Mapping[str, JsonValue], flag: Mapping[str, JsonValue])
tests/integration/routing/test_model_capability_flags.py:304
↓ 8 callersFunction_params
(config, query, optional_params)
tests/unit/llms/apiserpent/test_apiserpent_search.py:17
↓ 8 callersFunction_params_of
(entry: Mapping[str, object])
litellm/router_rust/surface/registry.py:554
↓ 8 callersMethod_parse_bool_env
Parse a boolean environment variable. Accepts true/false, 1/0, yes/no, on/off (case-insensitive, whitespace-tolerant) — matching the
litellm/integrations/newrelic/newrelic.py:163
↓ 8 callersFunction_parse_deprecation_date
(raw_value: object)
litellm/proxy/common_utils/model_deprecation.py:41
↓ 8 callersFunction_parsed_sse_events
(sse_stream: str)
litellm/llms/anthropic/messages/stream_assembly.py:515
↓ 8 callersFunction_pass_through_key_limits
()
tests/unit/llms/litellm_proxy/skills/test_skill_search.py:55
↓ 8 callersMethod_patch_model
( monkeypatch, db_model: Deployment, user_api_key_dict: UserAPIKeyAuth, creden
tests/unit/proxy/management_endpoints/test_model_management_endpoints.py:5477
↓ 8 callersFunction_patched_globals
(prisma)
tests/unit/proxy/management_endpoints/test_session_endpoints.py:42
↓ 8 callersFunction_paths
(candidate: Gateway)
tests/integration/configuration/test_lazy_routes_flag.py:54
↓ 8 callersFunction_patient_client
(gateway: Gateway)
tests/integration/spend/test_normalized_error_long_message.py:69
↓ 8 callersFunction_peer
(shape: Shape, answer: str = _ANSWER)
tests/integration/providers/test_hosted_vllm_stream_stall_wire.py:94
↓ 8 callersFunction_peer
(respond: Callable[[Request], Reply] = _embeddings)
tests/integration/sdk/test_ollama_embedding_wire.py:57
↓ 8 callersFunction_per_issuer_virtual_key_jwt_handler
( global_claim_field: str | None, global_behavior: str = "fallback_team_mapping" )
tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py:12139
↓ 8 callersFunction_plain
``value`` as plain JSON values, the shape the Rust core reads.
litellm/router_rust/core.py:571
↓ 8 callersFunction_png_item
(encoded: str = PNG_B64)
tests/unit/llms/bedrock/test_guardrail_attachments.py:14
↓ 8 callersFunction_poll_status_keys
( router: Router, model: str, deployment_id: str, respx_mock: respx.MockRouter, caller: Us
tests/unit/test_router/test_router_provider_endpoints.py:648
↓ 8 callersFunction_post
(app: ASGIApp)
tests/unit/proxy/middleware/test_budget_reservation_release_middleware.py:112
↓ 8 callersFunction_post_and_read
(rig: _Rig, path: str, body: Mapping[str, JsonValue], headers: Mapping[str, str])
tests/integration/spend/test_passthrough_stream_pricing_paths_spend.py:313
↓ 8 callersFunction_post_exchange_endpoint
( url: str, form: dict[str, str], client_auth_headers: dict[str, str] )
litellm/proxy/mcp_server/outbound_credentials/token_exchange_provider.py:64
↓ 8 callersFunction_posted_headers
(g: StraikerGuardrail)
tests/unit/proxy/guardrails/guardrail_hooks/test_straiker.py:1197
↓ 8 callersMethod_prepare_request
Prepare the AWS Secrets Manager request
litellm/secret_managers/aws_secret_manager_v2.py:636
↓ 8 callersMethod_prisma_schema_param
The `schema` query param Prisma uses to pick its target schema, or None when the URL does not set one.
litellm-proxy-extras/litellm_proxy_extras/utils.py:718
↓ 8 callersFunction_prisma_with_batcher
()
tests/unit/proxy/db/test_spend_log_tool_index.py:55
↓ 8 callersMethod_process_response_for_pii
Helper to recursively process a ModelResponse for PII. Handles all choices and tool calls.
litellm/proxy/guardrails/guardrail_hooks/presidio.py:1396
↓ 8 callersMethod_processor
(self)
tests/unit/proxy/guardrails/test_deferred_guardrail_logging.py:1449
↓ 8 callersFunction_prompt
(marker: str, *directives: str)
tests/integration/providers/test_chatgpt_responses_caller_stream_wire.py:75
↓ 8 callersFunction_prompt
(payload: Mapping[str, JsonValue])
tests/integration/observability/test_s3_v2_partition_granularity.py:74
↓ 8 callersFunction_prompt
(ending: Ending)
tests/integration/streaming/test_stream_clean_eof_without_finish_reason.py:184
↓ 8 callersFunction_provider
(flags: Mapping[str, JsonValue] | None = None)
tests/code_coverage_tests/test_generate_provider_endpoints_support.py:33
↓ 8 callersFunction_proxy_environment
(no_proxy: str)
tests/unit/router_utils/test_kubernetes_pod_discovery.py:272
↓ 8 callersFunction_proxy_exc
(message, code)
tests/unit/integrations/otel/test_otel_v2_logger.py:1389
↓ 8 callersFunction_proxy_url
(gateway: Gateway)
tests/integration/providers/test_bedrock_stream_timeout_wire.py:183
↓ 8 callersFunction_ptu_priced_deployment
``model_params`` with PTU pricing applied, or itself when it configures no PTU.
litellm/proxy/management_endpoints/model_management_endpoints.py:1304
↓ 8 callersFunction_public_named_router
(*team_rows: dict)
tests/unit/proxy/proxy_server/test_team_model_name_translation.py:1415
↓ 8 callersFunction_query
(url: str)
tests/unit/proxy/db/test_db_url_settings.py:830
↓ 8 callersMethod_query
(self, query: SqlQuery)
litellm/repositories/daily_activity_repository.py:162
↓ 8 callersFunction_query_spend_logs
(prisma_client: PrismaClient, sql_query: str, *args: object)
litellm/proxy/spend_tracking/spend_management_endpoints.py:268
↓ 8 callersFunction_question
(marker: str)
tests/integration/providers/test_bedrock_mantle_output_limit_wire.py:98
↓ 8 callersFunction_quota_media_payload
(kind: str, compressed: bool)
tests/unit/proxy/hooks/test_tpm_concurrent.py:3591
↓ 8 callersFunction_rag_query
( gateway: Gateway, model: str, marker: str, key: str, *, store_id: str = CONFIG_STORE
tests/integration/authorization/test_rag_query_vector_store_allowlist.py:66
↓ 8 callersMethod_raise_at
Read the list at the row router-core could not read it at, which raises.
litellm/router_rust/surface/registry.py:1631
↓ 8 callersFunction_raise_if_rate_limits_required_but_missing
Off by default, so deployments keep adding models without limits. Once the operator opts in under general_settings, the policy decides per model n
litellm/proxy/management_endpoints/model_management_endpoints.py:867
↓ 8 callersFunction_raise_masked_async_error
Raise a MaskedHTTPStatusError for async HTTP handlers.
litellm/llms/custom_httpx/http_handler.py:613
↓ 8 callersFunction_raise_masked_sync_error
Raise a MaskedHTTPStatusError for sync HTTP handlers.
litellm/llms/custom_httpx/http_handler.py:571
↓ 8 callersFunction_read_during_held_delete
(router: Router, deployment_id: str, read: Callable[[], T])
tests/integration/sdk/test_router_concurrent_deployment_delete_sdk.py:159
↓ 8 callersMethod_reap_all_zombies
Reap ALL zombie child processes via waitpid(-1, WNOHANG). Returns a set of reaped PIDs. As PID 1 in Docker (or any process that spaw
litellm/proxy/utils.py:7167
↓ 8 callersFunction_reasoning_effort_sent
(model: str, provider: str, reasoning_effort: object)
tests/unit/llms/anthropic/messages/adapters/test_handler_reasoning_effort_normalization.py:30
↓ 8 callersMethod_rebuild
A new Rust core for changed static settings, over the same deployments and the providers the old one's builds resolved for them.
litellm/router_rust/core.py:1860
↓ 8 callersMethod_rebuild_anthropic_response_from_sse
Parse collected SSE bytes into an Anthropic Messages response dict. Processes SSE events in order: - message_start -> enve
litellm/llms/anthropic/messages/native/agentic_streaming_iterator.py:415
↓ 8 callersFunction_recompute_scim_member_roles
Recompute and persist each user's global proxy role from their resulting team membership. No-op unless scim_admin_group is configured, so a S
litellm/proxy/management_endpoints/scim/scim_v2.py:495
↓ 8 callersMethod_record_exception_on_span
Record exception information on the span using OTEL standard methods. This extracts error information from StandardLoggingPayload an
litellm/integrations/opentelemetry.py:2274
↓ 8 callersFunction_redeem
(gateway: Gateway, token: str, path: str = "/v1/realtime/calls")
tests/integration/providers/test_realtime_webrtc_http.py:140
↓ 8 callersFunction_refresh_for_bridge_server
Drive a refresh_token grant for a bridge server: the client presents ``refresh_envelope_value``, the sealed subject re-validates to ``revalidate_r
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:6946
↓ 8 callersFunction_refusal
(agent: str, response: httpx.Response | None = None)
tests/integration/authorization/test_agent_denial_logging.py:102
↓ 8 callersMethod_region_marker_entry
()
tests/unit/router_strategy/test_complexity_router.py:5343
↓ 8 callersFunction_register_poll
(logging_obj: LitellmLogging, poll_fetch=None, store=None)
tests/unit/interactions/test_background_cost_polling.py:562
↓ 8 callersFunction_registry_cost
Derives the expected charge from the live cost map rather than pinning a vendor price.
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_deepgram_listen_passthrough_logging_handler.py:69
↓ 8 callersFunction_registry_with
(collector: Collector)
tests/unit/integrations/test_prometheus_metrics_endpoint.py:50
↓ 8 callersFunction_reject_mcp_proxy_operation
()
litellm/proxy/mcp_server/server.py:998
↓ 8 callersFunction_rejection
(message: str)
tests/unit/llms/custom_httpx/test_llm_http_handler.py:4296
↓ 8 callersFunction_relayed
(pieces: Iterable[bytes])
tests/unit/proxy/pass_through_endpoints/test_injected_stream_usage.py:45
↓ 8 callersMethod_release
(self, processor: SpanProcessor)
litellm/integrations/otel/plumbing/providers.py:1065
↓ 8 callersFunction_release_files
(slug: str, prompt: str)
tests/unit/proxy/common_utils/test_codex_catalog_source.py:20
↓ 8 callersMethod_remove_key
Remove a key from both cache_dict and ttl_dict
litellm/caching/in_memory_cache.py:106
↓ 8 callersFunction_replayed_conversation
(reasoning: JsonValue, marker: str)
tests/integration/providers/test_hosted_vllm_reasoning_content_wire.py:62
↓ 8 callersFunction_request
( *, provider: str = "openai", latency_ms: float = 80.0, tokens: TokenCounts = TokenCounts(), attempts: in
tests/unit/telemetry/test_aggregate.py:47
↓ 8 callersMethod_request
(self, method: str, path: str)
tests/unit/proxy/vector_store_endpoints/test_vector_store_endpoints.py:2866
↓ 8 callersMethod_request
(self, content_type: str)
tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py:7174
↓ 8 callersMethod_request
(router: Router, surface: str, stream: bool, metadata: dict[str, object])
tests/unit/router_strategy/test_complexity_router.py:15699
↓ 8 callersFunction_request_bodies
(respx_mock: respx.MockRouter)
tests/unit/test_tool_loop.py:64
↓ 8 callersFunction_request_body
( endpoint: Endpoint, model: str, description: str, parameters: JsonValue, stream: bool )
tests/integration/providers/test_gemini_anyof_null_branches_wire.py:164
↓ 8 callersFunction_request_count_key
(model_group: str, deployment_id: str)
litellm/router_strategy/least_busy.py:90
↓ 8 callersMethod_request_kwargs
(session_id: str)
tests/unit/router_strategy/test_complexity_router.py:7803
↓ 8 callersFunction_request_spans
(exporter: InMemorySpanExporter)
tests/unit/integrations/arize/test_arize.py:187
↓ 8 callersFunction_reset
()
tests/unit/sandbox/test_sandbox_tools.py:6
↓ 8 callersMethod_resolve_io_token_reconcile_usage
Resolve ``(billable_input_tokens, completion_tokens, usage_resolved)`` for ITPM/OTPM reconciliation. Cache-read tokens are excluded f
litellm/proxy/hooks/parallel_request_limiter_v3.py:4406
↓ 8 callersMethod_resolve_oauth2_headers_for_tool_call
Look up per-user OAuth headers when the client did not supply a token.
litellm/proxy/mcp_server/mcp_server_manager.py:6941
↓ 8 callersMethod_resolve_read_gcs_config
Resolve the GCS bucket and service-account credentials for the read/content path. Sources them from the deployment's ``litellm_param
litellm/llms/vertex_ai/files/handler.py:46
↓ 8 callersFunction_resolve_session_key
Pick a stable per-conversation key for owner-cache attribution. Order: 1. Honor a client-supplied session id (`litellm_session_id` on eithe
litellm/router_strategy/adaptive_router/hooks.py:52
↓ 8 callersFunction_respond_for
( request_id: str, prompt: str, *, expected_target: str = "/v1/chat/completions", pause: f
tests/integration/spend/test_service_tier_stream_billing.py:61
↓ 8 callersFunction_response
(model: str = "gpt-4o")
tests/test_litellm_rust/responses/test_dispatch.py:33
↓ 8 callersFunction_response
(queries: int | None)
tests/unit/proxy/hooks/test_search_free_tier.py:44
↓ 8 callersFunction_response
A real httpx.Response whose .json() yields ``payload``.
tests/unit/llms/anthropic/batches/test_transformation.py:33
↓ 8 callersFunction_response_asking_for_another_search
(block_id: str = "toolu_internal_1")
tests/unit/integrations/websearch_interception/test_websearch_agentic_loop_cap.py:83
↓ 8 callersFunction_response_body
(response_id: str, store: bool = False, created_at: float = _CREATED_AT)
tests/unit/llms/openai/responses/test_openai_responses_http.py:90
↓ 8 callersFunction_response_dones
(events: tuple[Event, ...])
tests/integration/providers/test_bedrock_nova_sonic_realtime_tool_calls.py:263
← previousnext →8,801–8,900 of 202,479, ranked by callers