MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 5 callersFunctionspend_database
A proxy on its own database with its spend views created, reading through a real read-only role when `with_reader`, and with no read replica at al
tests/integration/database/test_global_spend_refresh_writer.py:51
↓ 5 callersFunctionspend_event_callback_args
The ``(kwargs, response_obj, start_time, end_time)`` the in-process cost callback receives.
litellm/proxy/spend_tracking/spend_event.py:394
↓ 5 callersFunctionspend_log_insert_statement
(rows: Sequence[Mapping[str, object]])
litellm/repositories/spend_log_insert.py:68
↓ 5 callersFunctionspend_log_row_bytes
Bytes this row costs, measured the same way the write budget measures it.
litellm/proxy/db/spend_log_batching.py:65
↓ 5 callersFunctionspend_logs_seed_totals
LiteLLM_SpendLogs spend for one entity since window_start, both in full and up to the start of the batch being flushed, in one scan. The spen
litellm/proxy/db/budget_window_spend_writer.py:207
↓ 5 callersFunctionspend_marker
(text: str)
tests/integration/authorization/_responses_compact.py:247
↓ 5 callersFunctionspend_rows
( name: str, markers: frozenset[str], *, expected: int, seconds: float = 90 )
tests/integration/providers/_mantle_gpt_prompt_cache_support.py:609
↓ 5 callersFunctionspend_statuses
(call_id: str)
tests/integration/streaming/faked_responses_case.py:322
↓ 5 callersFunctionsse
(data)
tests/unit/sandbox/test_opensandbox_sandbox.py:26
↓ 5 callersFunctionsse
(event: str, data: Mapping[str, object])
tests/unit/test_router/core/streaming_helpers.py:240
↓ 5 callersMethodsse
The event as a ``/v1/messages`` stream carries it, the shape its guardrail translation scans.
litellm/llms/bedrock/passthrough/guardrail_translation/handler.py:833
↓ 5 callersFunctionsse_response
()
litellm-rust/crates/inference-messages/tests/messages/stream.rs:136
↓ 5 callersFunctionstale_pools
( gateway: Gateway, directory: Path, rows: tuple[Row, ...], overrides: Mapping[str, str],
tests/integration/providers/_idle_upstream_support.py:754
↓ 5 callersFunctionstamp_litellm_bill_on_usage
Writes litellm's bill into ``usage.cost`` and the hidden ``response_cost`` cache, keeping the upstream's own ``usage.cost`` under ``upstream_usage
litellm/litellm_core_utils/core_helpers.py:1108
↓ 5 callersFunctionstamp_matched_model_access_groups
Record the groups that authorized this request on its auth object, for the post-call spend writer and the reservation counters, and hand them back
litellm/proxy/auth/auth_checks.py:5478
↓ 5 callersMethodstart
(self, pool: ThreadPoolExecutor, calls: Sequence[Call])
tests/integration/caching/test_response_cache_chaos.py:224
↓ 5 callersFunctionstart_child_span
Create an observation under the generation, keeping its own time window. The server folds the trace's ``public`` flag across every observation, w
litellm/integrations/langfuse/langfuse_sdk.py:406
↓ 5 callersMethodstart_config_sync_subscriber
( self, prisma_client: PrismaClient, proxy_logging_obj: ProxyLogging, redis_ca
litellm/proxy/proxy_server.py:9016
↓ 5 callersFunctionstart_on_free_ports
( start: impl Fn([u16; N]) -> F, )
litellm-rust/crates/redis-testing/src/ports.rs:64
↓ 5 callersFunctionstart_query_engine_reaper
Start the reaper daemon thread in the supervisor process. Must only be called from a process that never hosts the proxy app itself (uvicorn w
litellm/proxy/db/query_engine_reaper.py:183
↓ 5 callersFunctionstate
(server: &MockServer, settings: KeyManagementSettings)
litellm-rust/crates/python-bridge/src/secrets/resolved.rs:66
↓ 5 callersMethodstate
(self)
tests/e2e/migrations/containers.py:49
↓ 5 callersMethodstatus
(&self)
litellm-rust/crates/gateway-mcp/src/error.rs:60
↓ 5 callersMethodsteps
One reading per step of a ramped run: the gateway's added latency over the step's requests, the rate at which requests completed inside the st
tests/e2e/perf/setup/observe.py:250
↓ 5 callersMethodstop_config_sync_subscriber
(self)
litellm/proxy/proxy_server.py:9036
↓ 5 callersMethodstop_db_health_watchdog_task
Stop DB health watchdog task and engine watcher gracefully.
litellm/proxy/utils.py:7914
↓ 5 callersFunctionstop_processes
(processes: Iterable[psutil.Process], grace_seconds: float = 5)
tests/integration/_support/process.py:390
↓ 5 callersFunctionstop_shadow_eval_job
Stop an active shadow eval job, every target it scopes at once. Attempts are kept; sampling halts within ~10s. Targets that already stopped on the
litellm/proxy/management_endpoints/auto_router_endpoints.py:2030
↓ 5 callersMethodstore
Python `set_cache` under the held lock: evict first (even when `key` already exists), then skip oversized values, then write, keeping a live key's exp
litellm-rust/crates/cache-memory/src/cache.rs:302
↓ 5 callersMethodstore_input
Store input message
litellm/litellm_core_utils/realtime_streaming.py:820
↓ 5 callersFunctionstore_read_errors
()
litellm/proxy/telemetry/store.py:148
↓ 5 callersFunctionstored_custom_ids
(request: Request)
tests/integration/providers/_vertex_batch_rows.py:128
↓ 5 callersFunctionstr_keyed
``value`` as a read-only str-keyed mapping, empty when it is not a dict.
litellm/litellm_core_utils/deployment_pricing.py:40
↓ 5 callersMethodstream
(self, prompt: str)
litellm/harness/sync.py:175
↓ 5 callersMethodstream
(self, **_kwargs)
tests/unit/llms/openai/test_openai.py:2059
↓ 5 callersFunctionstream_reply
(request: Request, events: Sequence[Event], *, abort_after: int | None = None)
tests/integration/_support/anthropic_thinking.py:152
↓ 5 callersFunctionstrip_advisor_blocks_from_messages
Remove (or replace) server_tool_use (name='advisor') and advisor_tool_result blocks from assistant message content. Prevents Anthropic 4
litellm/llms/anthropic/common_utils.py:1835
↓ 5 callersFunctionstrip_encrypted_reasoning_from_messages
Drop the bridge-tagged reasoning blocks a routed deployment cannot decrypt from Anthropic-shaped history. The whole block goes, the way #4028
litellm/litellm_core_utils/prompt_templates/reasoning_utils.py:253
↓ 5 callersFunctionsubmitMountedSSOValues
( form: UseFormReturn<SSOSettingsFormValues>, variant: SSOFormVariant, onFormSubmit: (formValues:
ui/litellm-dashboard/src/components/Settings/AdminSettings/SSOSettings/Modals/BaseSSOSettingsForm.tsx:242
↓ 5 callersFunctionsubscription_default
Whether `lite <agent>` keeps the agent's own subscription login unless told otherwise.
litellm/proxy/client/cli/commands/config.py:123
↓ 5 callersMethodsuccess_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:3644
↓ 5 callersFunctionsupported_grant_types
The grants ``/token`` can serve on this deployment. The RFC 8693 exchange is listed only where the JWT auth that proves a subject token is on, bac
litellm/proxy/mcp_server/gateway_dcr_flow.py:209
↓ 5 callersMethodsupports_native_file_search
(self)
litellm/llms/openai/responses/transformation.py:354
↓ 5 callersMethodsupports_sampling_params
Whether Google still honors ``temperature`` / ``top_p`` / ``top_k`` for ``model``. Driven by ``supports_sampling_params`` in the model map: G
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:890
↓ 5 callersFunctionsupports_tool_choice
Check if the given model supports `tool_choice` and return a boolean value.
litellm/utils.py:3410
↓ 5 callersMethodsuspend
Yields a suspension with its reply handle and waits for the answer.
litellm-rust/crates/host-python/src/caller.rs:52
↓ 5 callersFunctionsync_key_access_group_membership
Mirror a key-side change to `access_group_ids` onto each access group's `assigned_key_ids`.
litellm/proxy/management_helpers/access_group_key_sync.py:111
↓ 5 callersFunctionsync_model_allowlists_for_renamed_model
( prisma_client: object, *, model_id: str, old_name: str, new_name: str, llm_router: R
litellm/proxy/management_helpers/model_allowlist_rename_sync.py:142
↓ 5 callersMethodsync_read_secret
Sync function to read a secret from AWS Secrets Manager Done for backwards compatibility with existing codebase, since get_secret is
litellm/secret_managers/aws_secret_manager_v2.py:182
↓ 5 callersFunctionsync_team_access_group_membership
Reconcile the mirror for an already committed team write, in its own transaction.
litellm/proxy/management_helpers/access_group_team_sync.py:168
↓ 5 callersFunctionsync_ui_settings_to_general_settings
Re-read the persisted UI settings and apply the runtime flags to ``general_settings``. Runs on startup and on every periodic config reload: the P
litellm/proxy/ui_crud_endpoints/proxy_setting_endpoints.py:1882
↓ 5 callersFunctionsystem_messages_first
( messages: list[AllMessageValues], # mutable-ok: message pipelines type messages as mutable lists )
litellm/litellm_core_utils/prompt_templates/common_utils.py:1512
↓ 5 callersFunctiont
litellm/proxy/_experimental/out/_next/static/chunks/2bjw0usamfm54.js:4
↓ 5 callersFunctiont
()
litellm/proxy/_experimental/out/_next/static/chunks/03q-w6h_lqdi1.js:1
↓ 5 callersFunctiont1
(e,t,n,s)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 5 callersFunctiontN
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:5
↓ 5 callersFunctiontO
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:5
↓ 5 callersFunctiontT
(e)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 5 callersFunctionta
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 5 callersFunctiontarget
(provider: Provider, stream: bool)
tests/integration/providers/_tool_search_support.py:206
↓ 5 callersFunctiontb
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 5 callersFunctiontd
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 5 callersFunctionteamListCall
( accessToken: string, organizationID: string | null, userID: string | null = null, teamID: string | n
ui/litellm-dashboard/src/components/networking.tsx:1201
↓ 5 callersFunctionteamListCall
( accessToken: string, page: number, pageSize: number, options: TeamListCallOptions = {}, )
ui/litellm-dashboard/src/app/(dashboard)/hooks/teams/useTeams.ts:47
↓ 5 callersFunctionteamMemberBudgetGate
( teamInfo: TeamMemberBudgetSource | null | undefined, userId: string | null | undefined, memberLabel?:
ui/litellm-dashboard/src/components/shared/InheritedBudgetHint.tsx:103
↓ 5 callersFunctionteam_admin_member_key_creation_or_raise
(verdict: TeamAdminMemberKeyCreationVerdict)
litellm/proxy/management_endpoints/team_admin_field_permissions.py:254
↓ 5 callersFunctionteam_admin_member_key_creation_verdict
``owner_role`` is the stored proxy role of the member the key is for, None when they have no user row.
litellm/proxy/management_endpoints/team_admin_field_permissions.py:239
↓ 5 callersFunctionteam_admin_request_or_raise
(verdict: TeamAdminEditVerdict)
litellm/proxy/management_endpoints/team_admin_field_permissions.py:486
↓ 5 callersFunctionteam_caller
(scenario: Scenario)
tests/integration/security/_sinks.py:288
↓ 5 callersMethodteam_info_status
(self, team_id: str)
tests/e2e/management/management_client.py:397
↓ 5 callersFunctionteam_max_budget_check
Check if the team is over it's max budget. Raises: BudgetExceededError if the team is over it's max budget. Triggers a budge
litellm/proxy/auth/auth_checks.py:7229
↓ 5 callersFunctionteam_model_aliases_for_auth_check
(valid_token: UserAPIKeyAuth)
litellm/proxy/auth/auth_checks.py:5295
↓ 5 callersMethodtenant
(self)
tests/e2e/management/jwt_actors.py:94
↓ 5 callersFunctionternary_peers
(directory: Path)
tests/integration/observability/_ternary_support.py:127
↓ 5 callersFunctiontest_cache_connection
Test cache connection with provided credentials. Creates a temporary cache instance and uses its test_connection method to verify the cr
litellm/proxy/management_endpoints/cache_settings_endpoints.py:520
↓ 5 callersFunctiontext
(value: &Value)
litellm-rust/crates/gateway/src/redis/configured.rs:137
↓ 5 callersFunctiontf
(e,t,n,s)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 5 callersFunctiontg
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 5 callersFunctionth
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 5 callersMethodthinking_betas
(self, thinking: AnthropicThinkingParam | None)
litellm/llms/anthropic/common_utils.py:757
↓ 5 callersFunctiontierRowByName
(rows: readonly T[], name: string)
ui/litellm-dashboard/src/components/add_model/tier_rows.ts:88
↓ 5 callersMethodtier_label
Operator-facing display name for a tier, falling back to its canonical name.
litellm/router_strategy/complexity_router/config.py:2362
↓ 5 callersMethodtimeout
(&self)
litellm-rust/crates/secrets-types/src/context.rs:34
↓ 5 callersMethodtiming
(&self)
litellm-rust/crates/host-python/src/driver.rs:67
↓ 5 callersFunctiontl
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 5 callersFunctiontn
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 5 callersFunctiontn
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:11
↓ 5 callersMethodtoObject
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersMethodtoReference
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersMethodto_response_dict
(self)
litellm/llms/sagemaker/common_utils.py:234
↓ 5 callersMethodto_sdk_workload_identity
(self)
litellm/llms/openai/workload_identity.py:50
↓ 5 callersMethodto_value
(self)
litellm-rust/crates/redis-store/src/number.rs:37
↓ 5 callersFunctiontoken_count_error_to_pyerr
(error: Error)
litellm-rust/crates/python-bridge/src/routes/token_counter.rs:73
↓ 5 callersFunctiontoken_exchange_available
()
litellm/proxy/mcp_server/idp_token_exchange.py:100
↓ 5 callersMethodtoken_url
(self, realm: str)
tests/e2e/idp.py:153
↓ 5 callersFunctiontoml_value
Encode a Python value as a TOML value for `codex -c key=value`.
litellm/llms/codex/harness/transformation.py:155
↓ 5 callersMethodtool
(self)
tests/integration/mcp/test_mcp_llm_endpoints.py:518
↓ 5 callersFunctiontool_args
`--tools` allowlist for a permission mode and MCP servers, plus `--exclude-tools` for disable_tools.
litellm/llms/pi/harness/transformation.py:299
↓ 5 callersFunctiontool_list_item
(*tools: dict[str, JsonValue])
tests/integration/providers/test_responses_codex_repeated_additional_tools_wire.py:31
↓ 5 callersFunctiontool_rig
( directory: Path, respond: Callable[[Request], Reply] = _provider, *, configure: Callable[[di
tests/integration/security/test_hide_secrets_tool_traffic.py:95
← previousnext →16,701–16,800 of 202,479, ranked by callers