MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 9 callersMethodtransform_chat_completion_tools_to_responses_tools
Transform a Chat Completion tools into a Responses API tools. For custom tools (e.g. apply_patch), returns CustomToolCallOutputItem
litellm/responses/litellm_completion_transformation/transformation.py:3120
↓ 9 callersMethodtransform_realtime_request
Transform OpenAI realtime request to Bedrock Nova Sonic format. Args: message: OpenAI format message (JSON string)
litellm/llms/bedrock/realtime/transformation.py:835
↓ 9 callersMethodtransform_request
Transform request using parent AnthropicConfig, then remove unsupported params. Azure Anthropic doesn't support extra_body, max_retri
litellm/llms/azure_ai/anthropic/transformation.py:122
↓ 9 callersMethodtransform_request
Transform the overall request to be sent to the API. Returns: dict: The transformed request. Sent as the body of the API
litellm/llms/moonshot/chat/transformation.py:208
↓ 9 callersMethodtransform_response
( self, model: str, raw_response: httpx.Response, model_response: "ModelRespon
litellm/llms/github_copilot/chat/transformation.py:301
↓ 9 callersMethodtransform_search_response
Transform an MCP tools/call response to LiteLLM unified SearchResponse. The gateway returns JSON-RPC (as plain JSON or a single-mess
litellm/llms/bedrock/search/transformation.py:366
↓ 9 callersMethodtransform_search_vector_store_request
( self, vector_store_id: str, query: str | list[str], vector_store_search_opti
litellm/llms/pg_vector/vector_stores/transformation.py:71
↓ 9 callersMethodtransform_session_created_event
( self, model: str, logging_session_id: str, session_configuration_request: st
litellm/llms/meta/realtime/transformation.py:470
↓ 9 callersMethodtranslate_streaming_completion_to_generate_content
Transform streaming litellm completion chunk to Google GenAI generate_content format Args: response: Streaming ModelResp
litellm/google_genai/adapters/transformation.py:697
↓ 9 callersMethodtranslate_system_message
Translate system message to anthropic format. Removes system message from the original list and returns a new list of anthropic syst
litellm/llms/anthropic/chat/transformation.py:2230
↓ 9 callersMethodtx
(self, *, timeout: timedelta)
tests/integration/spend/test_session_grouped_logs_pages.py:323
↓ 9 callersFunctionu
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:1
↓ 9 callersFunctionu
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 9 callersFunctionui_view_spend_logs
View spend logs with pagination support. Available at both `/spend/logs/v2` (public API) and `/spend/logs/ui` (internal UI). Returns pag
litellm/proxy/spend_tracking/spend_management_endpoints.py:2512
↓ 9 callersFunctionunconvertible_line_message
(line: int)
tests/integration/providers/_vertex_batch_rows.py:124
↓ 9 callersFunctionunix_now
()
litellm-rust/crates/cache-disk/src/cache.rs:278
↓ 9 callersMethodupdate
(self, where: Mapping[str, object], data: Mapping[str, object])
litellm/proxy/management_endpoints/scim/scim_v2.py:136
↓ 9 callersMethodupdate
Read-modify-write of one entry, atomic against every other update of this tier.
litellm-rust/crates/redis-store/src/memory.rs:71
↓ 9 callersFunctionupdateConfigFieldSetting
(accessToken: string, fieldName: string, fieldValue: any)
ui/litellm-dashboard/src/components/networking.tsx:3183
↓ 9 callersMethodupdate_auth_value
Set the authentication header for the MCP client.
litellm/mcp_client/client.py:924
↓ 9 callersFunctionupdate_breakdown_metrics
Updates breakdown metrics for a single record using the existing update_metrics function. PTU sentinel rows (api_key == PTU_SENTINEL_API_KEY) add
litellm/proxy/management_endpoints/common_daily_activity.py:309
↓ 9 callersFunctionupdate_metrics
Update metrics with new record data. Rollup rows can carry None for numeric fields when SUM() spans zero rows (e.g. a key with no spend), so
litellm/proxy/management_endpoints/common_daily_activity.py:231
↓ 9 callersMethodupdate_redis_cache
(self, cache: "RedisCache")
litellm/router_rust/core.py:2308
↓ 9 callersFunctionupdate_responses_tools_with_model_file_ids
Updates responses API tools with provider-specific file IDs. Pass 1 (always): decode unified vector_store_ids in file_search tools. Pass
litellm/litellm_core_utils/prompt_templates/file_id_utils.py:257
↓ 9 callersMethodupsert
(self, *, where: Mapping[str, object], data: Mapping[str, object])
litellm/proxy/db/model_usage_rollup.py:32
↓ 9 callersFunctionupstream_for
(groups: Sequence[str], *, hold: Sequence[str] = ())
tests/integration/routing/test_priority_scheduler_queue_cleanup.py:154
↓ 9 callersMethoduseSyncedValueWithCleanup
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 9 callersFunctionv
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2n5r7czpxrc08.js:1
↓ 9 callersMethodvalidate_anthropic_messages_environment
Validate environment for GitHub Copilot and add Copilot-specific headers. The caller-supplied ``api_base`` is intentionally ignored.
litellm/llms/github_copilot/messages/transformation.py:54
↓ 9 callersFunctionvector
(parts: list[JsonValue])
tests/integration/providers/test_gemini_embedding_file_block_wire.py:64
↓ 9 callersFunctionvendor_id
()
tests/integration/authorization/_responses_compact.py:88
↓ 9 callersFunctionvertex_proxy_route
Call LiteLLM proxy via Vertex AI SDK. [Docs](https://docs.litellm.ai/docs/pass_through/vertex_ai)
litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:3331
↓ 9 callersFunctionvirtual_key_max_budget_alert_check
Triggers a budget alert if the token has reached EMAIL_BUDGET_ALERT_MAX_SPEND_ALERT_PERCENTAGE (default 80%) of its max budget. This is a
litellm/proxy/auth/auth_checks.py:6933
↓ 9 callersFunctionw
(e,t,n,r,a,l,u,o)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 9 callersMethodwait
(&self)
litellm-rust/crates/gateway-forward/src/connections.rs:54
↓ 9 callersFunctionwatsonx_proxy_route
Watsonx pass-through endpoint. Allows using Watsonx APIs with automatic IAM token management and version parameter injection. Example:
litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:4630
↓ 9 callersMethodwith
(mut self, hooks: impl PythonCallHooks + 'static)
litellm-rust/crates/host-python/src/hooks/chain/dispatch.rs:33
↓ 9 callersFunctionwith_python
(f: impl for<'py> FnOnce(Python<'py>))
litellm-rust/crates/python-bridge/src/coercion.rs:269
↓ 9 callersFunctionwith_safeguard_results
( response: AnthropicMessagesResponse, evaluator: SafeguardsEvaluator | None )
litellm/llms/anthropic/messages/safeguards.py:499
↓ 9 callersFunctionwith_usage
Same request and stored body as ``base``, with the provider usage block and the expected row swapped.
tests/integration/cost_calculation/cost_tracking_case.py:677
↓ 9 callersFunctionwithout_attachment_content
(messages: object)
litellm/proxy/guardrails/guardrail_hooks/akto/akto_attachments.py:363
↓ 9 callersMethodwriter
(url: &str)
litellm-rust/crates/storage-clickhouse/src/lib.rs:56
↓ 9 callersFunctionwritten
(directory: Path, name: str, contents: str | bytes)
tests/integration/providers/test_vertex_credentials_source_wire.py:177
↓ 9 callersFunctionx
({className:e,...r})
litellm/proxy/_experimental/out/_next/static/chunks/0csaxmztgrx3b.js:434
↓ 9 callersFunctiony
litellm/proxy/_experimental/out/_next/static/chunks/0rgp8d4pvt399.js:1
↓ 9 callersFunctiony
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2bsaba02innfw.js:1
↓ 8 callersFunction$
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 8 callersFunctionBody
({ rowHeight, children, after, className }: BodyProps<T>)
ui/litellm-dashboard/src/components/shared/InspectorTable.tsx:100
↓ 8 callersFunctionC
(t)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 8 callersFunctionI
()
litellm/proxy/_experimental/out/_next/static/chunks/39v0w3tgm6n4z.js:1
↓ 8 callersFunctionJ
(t)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 8 callersFunctionL
(e,t,n,r,a,l)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 8 callersFunctionN
(e,t,n,r,a)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 8 callersFunctionUrl
(s,o,i)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersFunctionVe
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersFunctionXi
(s,o,i,a)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersFunction_
(e={})
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 8 callersMethod__init__
(self, response: AsyncGenerator[Any, None])
tests/unit/proxy/hooks/test_async_post_call_streaming_iterator_hook.py:267
↓ 8 callersFunction_a2a_params
()
tests/unit/a2a_protocol/providers/watsonx_orchestrate/test_config.py:33
↓ 8 callersMethod_access_token
(self, **kw)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:8588
↓ 8 callersFunction_acknowledge_notifications_after_dispatch
(app: ASGIApp)
tests/integration/_support/mcp.py:171
↓ 8 callersMethod_addCheck
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 8 callersFunction_add_team_members_to_team
Add team members to the team, under the team's advisory lock. The lock (``TEAM_ADVISORY_LOCK_SQL``, keyed on the team id) is taken first, and the
litellm/proxy/management_endpoints/team_endpoints.py:3383
↓ 8 callersMethod_add_tools_to_optional_params
Helper util to add tools to optional_params.
litellm/llms/base_llm/chat/transformation.py:180
↓ 8 callersMethod_admin
()
tests/unit/proxy/management_endpoints/test_model_management_endpoints.py:8700
↓ 8 callersFunction_admit
(handler, auth, data=None)
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:7947
↓ 8 callersFunction_agent_body
(model: str, marker: str, options: Mapping[str, JsonValue])
tests/integration/providers/test_vertex_gemini_count_tokens_wire.py:352
↓ 8 callersFunction_agent_prisma
(object_permission_id=None, side_effect=None)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:11006
↓ 8 callersFunction_aggregate_grouping_sets_records_sync
Build the response from rollup rows produced by the GROUPING SETS query. Each row carries a `group_level` bitmask (from Postgres GROUPING()) that
litellm/proxy/management_endpoints/common_daily_activity.py:776
↓ 8 callersMethod_alerted
(self, exc: Exception)
tests/unit/proxy/test_proxy_utils_model_creation_and_error_logging.py:1983
↓ 8 callersMethod_alias_less_server
(**overrides: Any)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:13640
↓ 8 callersFunction_answer
(marker: str)
tests/integration/providers/test_bedrock_mantle_output_limit_wire.py:102
↓ 8 callersFunction_answer_after_content_policy_refusal
(router: litellm.Router, model: str = "primary")
tests/unit/proxy/test_proxy_server_endpoints_and_startup.py:5723
↓ 8 callersFunction_anthropic_costs
(model: str)
tests/unit/proxy/spend_tracking/test_savings.py:87
↓ 8 callersFunction_app
( handler: Callable[[Request], Awaitable[Response]], release: Callable[[Mapping[str, object]], Awaitab
tests/unit/proxy/middleware/test_budget_reservation_release_middleware.py:103
↓ 8 callersFunction_app_with_relay
(relay: _FakeRelay)
tests/unit/proxy/pass_through_endpoints/test_deepgram_ws_passthrough_routes.py:319
↓ 8 callersFunction_assert_blocked_422
(client: BudgetClient, key: str)
tests/e2e/quota_management/budgets/test_budget_enforcement_e2e.py:51
↓ 8 callersFunction_assert_chat
(gateway: Gateway, model: str, token: str, prompt: str, key_hash: str)
tests/integration/authorization/test_jwt_key_mapping_lifecycle.py:335
↓ 8 callersFunction_assert_chat_request
( request: Request, *, messages: JsonValue, tools: JsonValue = CHAT_TOOLS, tool_choice: Js
tests/integration/observability/_openinference_support.py:87
↓ 8 callersFunction_assert_core_intact
(span)
tests/unit/integrations/otel/test_otel_v2_emitter.py:535
↓ 8 callersFunction_assert_datadog_configured
Recorded state: the proxy reports the DataDog callback among its active callbacks, so a missing destination config fails here, before any deli
tests/e2e/logging/test_datadog_log_e2e.py:55
↓ 8 callersFunction_assert_failure_logged_once
(logging_obj: Mock, exception: Exception)
tests/unit/responses/test_streaming_iterator.py:292
↓ 8 callersFunction_assert_id_resolves_to_deployment
(response: object, *, deployment_id: str | None = None)
tests/unit/proxy/video_endpoints/test_endpoints.py:89
↓ 8 callersFunction_assert_json_answer
(response: httpx.Response, marker: str)
tests/integration/providers/test_chatgpt_responses_caller_stream_wire.py:139
↓ 8 callersFunction_assert_landed_once
(model: str, identities: frozenset[str], *, rows: int)
tests/integration/streaming/test_interception_converted_stream_options.py:318
↓ 8 callersFunction_assert_legacy_database_parity
( parity_database: str, monkeypatch: pytest.MonkeyPatch, status: str, origin: str | None,
tests/integration/database/test_spendlogs_ledger_parity.py:331
↓ 8 callersFunction_assert_logged_failure
(model: str, *, rows: int, error_class: str, code: str = "529")
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_messages_overloaded_wire.py:171
↓ 8 callersFunction_assert_names_its_server_span
(rig: Rig, headers: httpx.Headers)
tests/integration/observability/test_otel_trace_response_header.py:388
↓ 8 callersFunction_assert_no_structured_tool_blocks
A valid Bedrock body for a neutralized request has no tool config AND no structured tool blocks in messages. Checking only toolConfig is insuffici
tests/unit/llms/bedrock/chat/test_converse_transformation.py:8147
↓ 8 callersFunction_assert_one_row_bills_round_one
(logged: Sequence[StandardLoggingPayload])
tests/unit/responses/mcp/test_chat_completions_handler.py:1856
↓ 8 callersFunction_assert_operation
(span: Span, operation: str)
tests/integration/observability/test_passthrough_operation_name.py:124
↓ 8 callersMethod_assert_parity
(self, raw_frames)
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_anthropic_passthrough_logging_handler.py:1301
↓ 8 callersFunction_assert_passed_with_discard_warning
(result, caplog, reason)
tests/unit/proxy/policy_engine/test_pipeline_executor.py:1266
↓ 8 callersFunction_assert_peer_untouched
(rig: FederationRig, *fragments: str)
tests/integration/management/test_credential_federation_values.py:1039
↓ 8 callersFunction_assert_refused
(response: httpx.Response, setting: str, entity: str)
tests/integration/management/test_batch_limit_metadata_admin_only.py:26
↓ 8 callersFunction_assert_responses_restreamed
(stream: _Stream, text: str)
tests/integration/streaming/test_interception_converted_stream_options.py:298
↓ 8 callersFunction_assert_runtime_call
(request: Request, runtime: str, region: str = _US_EAST, route: _Route = _SYSTEMONE)
tests/integration/providers/test_strands_decider_agentcore_wire.py:381
↓ 8 callersFunction_assert_scripted_response
(route: str, caller: dict[str, JsonValue])
tests/integration/compatibility/test_missing_body_param_status.py:714
↓ 8 callersFunction_assert_tool_turn
(sent: _Sent, calls: tuple[_Call, ...], *, text: str = "")
tests/integration/messages_endpoint/chat_bridge/test_chat_bridge_multi_tool_call_blocks_wire.py:479
↓ 8 callersFunction_assert_upstream_clean
(rig: Rig, marker: str, session: str)
tests/integration/observability/test_otel_conversation_id.py:309
← previousnext →8,401–8,500 of 202,479, ranked by callers