Get a proxy hook from the proxy_hook_mapping

Parse a single GENERIC SSE chunk into a LiteLLM ModelResponseStream.

Mint a fresh managed ID for a given raw provider ID.

Returns a dictionary of label + values for prometheus. Ensures end_user param is not sent to prometheus if it is not supported. When ``

Call from the post-yield section of an autouse fixture per test.

Resolve a single-secret search API key, falling back to a server-managed secret only when the request targets a trusted host.

Authenticate with AWS Role

Checks if token can call a given model Args: - model: str - llm_router: Optional[Router] - models: List[str]

Create the litellm_request span then close the proxy span.

Return server.static_headers with ``${NAME}`` interpolated. Globals come from ``server.env_vars`` entries with ``scope=="global"``. P

Run ``common_checks`` once at the ``user_api_key_auth`` wrapper boundary, regardless of which ``_user_api_key_auth_builder`` path returned. Th

Recursively sanitize request body to prevent logging large base64 strings or other large values. Truncates strings longer than MAX_STRING_LEN

Serialize a streaming chunk to a JSON string for WebSocket transmission.

Bedrock doesn't support tool calling without `tools=` param specified.

Extract model name from an encoded file/batch ID. Handles IDs that start with "file-" or "batch_" prefix.

Parameters: - duration: - "<number>s" - seconds - "<number>m" - minutes - "<number>h" - hours - "<number>d" -

Get the labels for a metric, filtered if configured. The result is cached on the instance so the label set used to construct

if 'model_name' is none, returns all. Returns list of model id's. Optimized with O(1) or O(k) index lookup when model_name

Build a minimal ModelResponse-like dict.

`preserve_litellm_internal_headers` must only be True when the input is a LiteLLM-owned dict (e.g. `_hidden_params["additional_headers"]` tha

Disconnect and reconnect the Prisma client with a new database URL. Kills the old engine subprocess directly (SIGTERM → SIGKILL) rather than

Safely parse a JSON string. If parsing fails, return the default value (None by default).

Check if management route is disabled and raise exception

Transform LiteLLM data to CBF format, dropping records with zero successful_requests or invalid CZRNs.

Transform the video creation request for Veo API. Veo expects: { "instances": [ {

Translate an OpenAI ResponsesAPIResponse to AnthropicMessagesResponse.

Expects LAGO_API_BASE, LAGO_API_KEY, LAGO_API_EVENT_CODE, Optional: LAGO_API_CHARGE_BY in t

Run the production call path: load from env, write to env.

Get the function names from the previous 1-2 functions in the call stack. Args: num_frames: Number of previous frames to include (de

Force the OpenAI-compatible `model` field in the response to match what the client requested. LiteLLM internally prefixes some provider/depl

Build the minimal proxy_server module attributes that _run_centralized_common_checks reads. ``master_key`` defaults to a non-None value becau

Redact match-like fields from a Bedrock ApplyGuardrail JSON payload. Delegates to :func:`redact_nested_match_and_regex_keys` (same rules as

Strip ``s3://`` / ``gcs://`` entries from the DB-overlay value for fields whose contents reach ``get_instance_fn``. The same scheme is allowed

- Check if the cache key is in-memory - Else: - add missing cache key from REDIS - update in-memory cache

Attempt to reconnect the Prisma client in a singleflight manner. Returns: bool: True if reconnection succeeded, else Fal

Removes litellm api key from headers Args: headers: Request headers litellm_key_header_name: Custom header name for LiteLLM

Seed a scratch-tagged key via /key/generate; returns its cleartext. Shared by the write-scenario matrices (key update/regenerate/delete). key

For closing connection on server shutdown

Render the per-classification summary at session end. Output sections (only included when non-empty): * **Verdict counts** — full breakdown

Get list of policy names attached to the given context. Args: context: The request context to match against Ret

Get the model tpm limit for a given api key. Priority order (returns first found): 1. Key metadata (model_tpm_limit) 2. Key model_ma

Get the MCP Server from the server name. Uses priority-based matching to avoid collisions: 1. First pass: exact alias match

Mock iter_lines method for synchronous streaming.

Load attachments from a configuration list. Args: attachments_config: List of attachment dictionaries from YAML.

Build the LiteLLM-fronted agent card. Args: upstream_card: Card returned by the upstream agent's well-known endpoint. Ma

Helper to create a mock file object

Route a requested model to the corresponding llm deployments based on the regex pattern loop through all the patterns and find the m

Check if the given model supports reasoning and return a boolean value.