MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 9 callersFunctionI
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 9 callersFunctionI
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 9 callersFunctionM
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 9 callersFunctionU
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 9 callersFunctionZf
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 9 callersFunction_access_group_table_mocks
Back the access group table with an in-memory dict so the sync's writes are observable. The sync writes through guarded set-based SQL statem
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:20323
↓ 9 callersFunction_access_record
A record shaped exactly like the one uvicorn.access emits per request.
tests/unit/test_logging.py:1485
↓ 9 callersFunction_access_response
(body: object)
tests/unit/secret_managers/test_google_secret_manager.py:114
↓ 9 callersMethod_acquire
The processor for ``destination``, marked busy until ``_release``. The build happens under the same lock that reads the cache, so a cold cach
litellm/integrations/otel/plumbing/providers.py:1013
↓ 9 callersFunction_active_hours_on_day
Hours the model's PTU window overlaps ``day`` (UTC), clamped to [0, 24].
litellm/proxy/spend_tracking/ptu_flat_cost_rollup.py:227
↓ 9 callersFunction_activity
(auth: UserAPIKeyAuth, team_lookup=_no_teams, **overrides)
tests/unit/proxy/analytics_endpoints/test_analytics_endpoints.py:40
↓ 9 callersMethod_add_cache_control_if_applicable
Extract cache_control from source and add to target if it should be preserved. This method accepts an unconstrained type to support
litellm/llms/anthropic/messages/adapters/transformation.py:521
↓ 9 callersMethod_add_mcp_list_tools_to_first_chunk
Add mcp_list_tools from _hidden_params to the first chunk's delta.provider_specific_fields. This method checks if MCP metadata with
litellm/litellm_core_utils/streaming_handler.py:1996
↓ 9 callersMethod_admin_key_dict
(self)
tests/unit/proxy/management_endpoints/test_team_default_params.py:704
↓ 9 callersFunction_agent_model_ceiling_resolver
Resolver that records the agent ids it was asked about and answers with a fixed model ceiling, or None when the agent has no access groups attache
tests/unit/proxy/auth/test_auth_checks_object_access_and_lookup.py:11140
↓ 9 callersFunction_aliases
(response: httpx.Response, digest: str)
tests/integration/spend/test_daily_activity_key_metadata_query_timeout.py:347
↓ 9 callersFunction_annotation_only_chunk
()
tests/unit/responses/litellm_completion_transformation/test_streaming_iterator_transformation.py:1365
↓ 9 callersFunction_answer
(marker: str)
tests/integration/observability/test_content_filter_logging_only.py:46
↓ 9 callersMethod_answer
(error: Exception)
tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py:1926
↓ 9 callersFunction_anthropic_message
(*content: Mapping[str, object])
tests/unit/responses/litellm_completion_transformation/test_anthropic_responses_bridge.py:582
↓ 9 callersFunction_anthropic_model
(scenario: Scenario, provider: Wire)
tests/integration/messages_endpoint/test_guardrail_long_tool_names_wire.py:243
↓ 9 callersFunction_anthropic_sse
(*events: Mapping[str, object])
tests/unit/responses/litellm_completion_transformation/test_anthropic_responses_bridge.py:514
↓ 9 callersFunction_anthropic_text_deltas
(chunks: list[bytes])
tests/unit/proxy/guardrails/guardrail_hooks/test_presidio.py:2400
↓ 9 callersMethod_append
(self, label_values: tuple[str, ...])
litellm/integrations/prometheus_helpers/shared_prometheus_series_admissions.py:46
↓ 9 callersFunction_apply_finding_guardrail_over_http
( mocker: MockerFixture, findings: tuple[object, ...], body: dict[str, object], hook_result: o
tests/unit/proxy/guardrails/test_guardrail_endpoints.py:2238
↓ 9 callersFunction_apply_with_transport
( guardrail: CrowdStrikeAIDRHandler, transport: httpx.MockTransport, inputs: GenericGuardrailAPIIn
tests/unit/proxy/guardrails/guardrail_hooks/test_crowdstrike_aidr.py:1428
↓ 9 callersFunction_arize_kwargs
(callback_vars: dict[str, object] | None = None)
tests/unit/integrations/arize/test_arize.py:191
↓ 9 callersFunction_arn
(runtime: str, region: str = _US_EAST)
tests/integration/providers/test_strands_decider_agentcore_wire.py:178
↓ 9 callersFunction_as_proxy_exception
Convert an authentication failure into the ProxyException the client receives.
litellm/proxy/auth/auth_exception_handler.py:51
↓ 9 callersFunction_assert_answered
(response: httpx.Response, marker: str)
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_safeguards_beta_wire.py:199
↓ 9 callersFunction_assert_legacy_wire
(sent: tuple[dict[str, JsonValue], ...], marker: str, method: str = "message/send")
tests/integration/compatibility/test_a2a_protocol_version_override.py:50
↓ 9 callersFunction_assert_logged_once
(rows: Sequence[Mapping[str, JsonValue]], *, route: str, request_id: str)
tests/integration/routing/test_complexity_router_databricks_classifier.py:284
↓ 9 callersFunction_assert_one_attempt
(wire: Wire, marker: str)
tests/integration/streaming/test_responses_top_level_error_events.py:71
↓ 9 callersFunction_assert_provider_request
(request: Request, text: str)
tests/integration/management/test_policy_attachment_runtime.py:252
↓ 9 callersFunction_assert_redacted_twin
( rig: Rig, sent: Sent, cursors: Cursors, sink: str, since: int, credential: Credential | None = None )
tests/integration/observability/test_otel_team_capture_message_content.py:341
↓ 9 callersFunction_assert_rejected
(rig: _Rig, response: httpx.Response, marker: str, expected: dict[str, JsonValue])
tests/integration/routing/test_non_chat_model_endpoint_gate.py:272
↓ 9 callersFunction_assert_sends_the_control_request
( vendor: _Vendor, send: Send, flagged: str, control: str, expected: Callable[[str], str] = _echo )
tests/integration/routing/test_model_capability_flags.py:323
↓ 9 callersFunction_assert_served
(response: httpx.Response, marker: str, stream: bool)
tests/integration/providers/test_responses_bridge_tool_search_undeferred_wire.py:329
↓ 9 callersFunction_assert_stored_without_canary
At-rest control: the stored value exists, is non-trivial, and does not hold the canary.
tests/integration/security/test_stored_config_slots.py:170
↓ 9 callersFunction_assert_upstream_requests
( upstream: Wire, expected: tuple[tuple[str, str, dict[str, JsonValue] | None], ...], )
tests/integration/authorization/test_jwt_key_mapping_lifecycle.py:315
↓ 9 callersFunction_assistant
(*blocks: JsonValue)
tests/integration/observability/test_bedrock_converse_guardrail_rewrites.py:376
↓ 9 callersFunction_assistant_choice
(content: str, finish_reason: str | None = None)
tests/unit/integrations/otel/test_otel_v2_sources_of_truth.py:976
↓ 9 callersFunction_async
An endpoint both cores serve outside the ``RouterCore`` protocol.
tests/unit/test_router/core/test_parity_provider_scoped_fallbacks.py:44
↓ 9 callersFunction_async_client
An async Azure client (passes ``isinstance(.., AsyncAzureOpenAI)``). The ``batches.*`` SDK methods are awaited by the handler, so they must be
tests/unit/llms/azure/batches/test_handler.py:80
↓ 9 callersMethod_async_set_router_remaining_metrics
Populate ``litellm_remaining_tokens_metric`` / ``litellm_remaining_requests_metric`` from the router's internal usage counter
litellm/integrations/prometheus.py:3431
↓ 9 callersFunction_attach_litellm_config
Attach a litellm_config table mock (not in conftest's _PRISMA_TABLES).
tests/unit/proxy/proxy_server/test_routes_model_cost_map.py:35
↓ 9 callersFunction_attempt_json_repair
Attempt to repair truncated JSON produced by LLM tool calls. Handles the most common truncation patterns where the model generates valid
litellm/litellm_core_utils/prompt_templates/tool_call_json_repair.py:12
↓ 9 callersMethod_attr
(self, span, exporter)
tests/unit/integrations/test_opentelemetry.py:6164
↓ 9 callersFunction_auto_router_capability_slot
Hand out the model table to write through while the row's claim on a licensed capability is settled. A write that leaves the row claiming a licen
litellm/proxy/management_endpoints/model_management_endpoints.py:667
↓ 9 callersFunction_azure_prompts
(azure: Wire)
tests/integration/sdk/test_azure_prompt_shield_tuple_messages.py:101
↓ 9 callersFunction_b64
(num_bytes: int)
tests/unit/llms/xai/test_xai_realtime_usage_meter.py:6
↓ 9 callersFunction_backend_events
(config: VertexChirpRealtimeConfig, frame: object)
tests/unit/llms/vertex_ai/audio_transcription/test_vertex_ai_realtime_transformation.py:84
↓ 9 callersFunction_background_response
(status: str, text: str = "")
tests/unit/proxy/utils/proxy_logging/test_guardrail_pipeline.py:2282
↓ 9 callersFunction_bare_manager
An ``MCPServerManager`` without running ``__init__``. The authorization/validation helpers on the path are stubbed out so the test reaches th
tests/unit/proxy/mcp_server/test_mcp_guardrail_usage_monitor.py:44
↓ 9 callersMethod_batch_database_updates
Runs every spend-update helper for one request. Each helper goes through _run_spend_update_step so one failure never skips the siblin
litellm/proxy/db/db_spend_update_writer.py:1294
↓ 9 callersFunction_batch_rates_model_info
(**rates: object)
tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py:4143
↓ 9 callersFunction_batch_rows
(messages: Sequence[str])
tests/unit/proxy/hooks/test_batch_rate_limiter.py:333
↓ 9 callersFunction_bedrock_router
(model: str, *, timeout: float, stream_timeout: float)
tests/unit/llms/bedrock/chat/test_bedrock_converse_handler.py:354
↓ 9 callersFunction_blocking
(needle, status_code=400, guardrail_name="block-guard")
tests/unit/proxy/openai_files_endpoint/test_batch_guardrails.py:628
↓ 9 callersFunction_boot_with_general_settings
(monkeypatch, tmp_path, general_settings)
tests/unit/proxy/test_proxy_server_endpoints_and_startup.py:1749
↓ 9 callersFunction_bridged_chat_completion_response
(**overrides)
tests/unit/responses/litellm_completion_transformation/test_litellm_completion_responses.py:5439
↓ 9 callersFunction_bridged_echo_answer_round
( stop: str = "end_turn", cache_usage: Mapping[str, object] = MappingProxyType({}) )
tests/unit/responses/mcp/test_aresponses_api_with_mcp.py:3070
↓ 9 callersFunction_bridged_echo_call_round
(cache_usage: Mapping[str, object] = MappingProxyType({}))
tests/unit/responses/mcp/test_aresponses_api_with_mcp.py:3056
↓ 9 callersFunction_budget_cache
A real DualCache holding spend at the given LITERAL counter keys. The keys are spelled out in full on purpose. Seeding via model_budget_spend
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:17592
↓ 9 callersMethod_build_error_detail
Build enhanced error detail with scan information.
litellm/proxy/guardrails/guardrail_hooks/panw_prisma_airs/panw_prisma_airs.py:786
↓ 9 callersFunction_build_managed_files_mock
(unified_id: str = "file-bWFuYWdlZF9vdXRwdXRfaWQ=")
tests/unit/enterprise/proxy/test_batch_update_db_managed_output_file_id.py:42
↓ 9 callersFunction_build_model_max_budget_usage
( api_key_hash: str, model_max_budget: Mapping[str, Mapping[str, object]], user_api_key_cache: Dua
litellm/proxy/management_endpoints/key_management_endpoints.py:4862
↓ 9 callersFunction_build_request_mock_with_headers
(headers: dict)
tests/unit/proxy/test_litellm_pre_call_utils.py:6663
↓ 9 callersMethod_build_routing_decision
Assemble the per-request provenance record for this router's decision. Optional facts are omitted rather than set to None, so a spend log row
litellm/router_strategy/complexity_router/complexity_router.py:1971
↓ 9 callersFunction_build_test_client
()
tests/unit/proxy/google_endpoints/test_google_api_endpoints.py:16
↓ 9 callersFunction_cached_usage_object
A cache-heavy Anthropic request, shaped as the spend log records it. `prompt_tokens` is the inclusive total: 3 uncached text tokens plus 500 read
tests/unit/proxy/spend_tracking/test_savings.py:94
↓ 9 callersFunction_call
(router: Router, name: str, *args: object, **kwargs: object)
tests/unit/test_router/core/test_deprecated_members.py:363
↓ 9 callersFunction_call_handler_and_capture_optional_params
Call anthropic_messages_handler with an Anthropic model and capture the anthropic_messages_optional_request_params dict passed to base_ll
tests/unit/llms/anthropic/messages/native/test_reasoning_auto_summary_messages.py:22
↓ 9 callersFunction_capture_host_progress_callback
Return a progress-forwarding callback bound to the host MCP session. Returns ``None`` when the host did not supply a progress token.
litellm/proxy/mcp_server/server.py:973
↓ 9 callersFunction_cassette
(played: int, dirty: bool, total: int)
tests/unit/test_vcr_classification.py:151
↓ 9 callersMethod_ceiling_resolver
A resolver that records the agent ids it was asked about and answers with a fixed ceiling, or None when the agent has no access groups attache
tests/unit/proxy/agent_endpoints/auth/test_agent_permission_handler.py:306
↓ 9 callersFunction_chaos_codes
(tmp_path, source, name=_CHAOS_TEST)
tests/unit/test_check_test_quality.py:690
↓ 9 callersFunction_charged_windows
(enqueued: Sequence[Mapping[str, object]])
tests/unit/proxy/test_proxy_server_endpoints_and_startup.py:14061
↓ 9 callersFunction_chat
( gateway: Gateway, model: str, key: str, text: str, *, policies: list[str] | None = N
tests/integration/management/test_policy_attachment_runtime.py:277
↓ 9 callersFunction_chat_body
(rig: _DisconnectRig, index: int, stream: bool = True)
tests/integration/observability/test_guardrail_effects.py:2489
↓ 9 callersFunction_chat_messages
(marker: str)
tests/integration/providers/test_responses_bridge_verbosity_wire.py:156
↓ 9 callersFunction_chat_request
(model: str, text: str, *, stream: bool, cached: bool)
tests/integration/providers/test_anthropic_refusal_stop_details_wire.py:271
↓ 9 callersFunction_chat_round_cost
(body: Mapping[str, object])
tests/unit/responses/mcp/test_chat_completions_handler.py:1615
↓ 9 callersFunction_check_agent_access_group_model_access
Attached groups naming no model deny every model; the empty allowlist in ``_can_object_call_model`` allows.
litellm/proxy/auth/auth_checks.py:5185
↓ 9 callersFunction_check_agent_management_permission
Raises HTTP 403 if the caller does not have permission to create, update, or delete agents. Only PROXY_ADMIN users are allowed to perform th
litellm/proxy/agent_endpoints/endpoints.py:250
↓ 9 callersFunction_check_model_access
Enforce model-permission checks for MCP sampling requests. Runs the same authorization checks as ``/chat/completions``: key-level, team-level
litellm/proxy/mcp_server/sampling_handler.py:732
↓ 9 callersFunction_check_team_project_limits
Check that project limits respect its parent Team's limits. Mirrors _check_org_team_limits() from team_endpoints.py. Validates: - P
enterprise/litellm_enterprise/proxy/management_endpoints/project_endpoints.py:208
↓ 9 callersFunction_child
(node: object, key: str | int)
litellm/llms/bedrock/passthrough/guardrail_translation/handler.py:340
↓ 9 callersFunction_chunking_guardrail
(chunk_size_bytes=100, **kwargs)
tests/unit/proxy/guardrails/guardrail_hooks/test_presidio.py:4053
↓ 9 callersMethod_clean_env
(self)
tests/unit/integrations/test_langfuse_otel.py:568
↓ 9 callersFunction_client_usage_chunks
(chunks: list[ModelResponseStream])
tests/unit/test_main.py:4530
↓ 9 callersFunction_collect
(wrapper: CustomStreamWrapper, sync_mode: bool)
tests/unit/litellm_core_utils/test_streaming_handler.py:2395
↓ 9 callersMethod_commit_spend_updates_to_db_without_redis_buffer
Commits all the spend `UPDATE` transactions to the Database This is the regular flow of committing to db without using a redis buffe
litellm/proxy/db/db_spend_update_writer.py:2029
↓ 9 callersFunction_complete
(client: str, router: Router, **request: object)
tests/integration/sdk/test_router_unsupported_params_fallback_wire.py:125
↓ 9 callersFunction_complete
( messages: Sequence[Mapping[str, object]], backend: Callable[[httpx.Request], httpx.Response], is
tests/unit/llms/vertex_ai/gemini/test_rejected_thought_signature_retry.py:117
↓ 9 callersFunction_config
( directory: Path, handles: Sequence[ScenarioHandle], *, model_info: Mapping[str, JsonValue] |
tests/integration/spend/test_background_response_billing_proxies.py:109
↓ 9 callersMethod_configured
()
tests/unit/proxy/management_endpoints/test_ptu_model_settings.py:308
↓ 9 callersMethod_connected
()
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:11
↓ 9 callersFunction_consumed
(gateway: Gateway, path: str, body: Mapping[str, JsonValue])
tests/integration/providers/test_bedrock_mantle_context_overflow_fallbacks_wire.py:339
↓ 9 callersFunction_content_frames
(response: httpx.Response)
tests/integration/providers/test_vertex_anthropic_structured_output_wire.py:700
← previousnext →7,401–7,500 of 202,479, ranked by callers