Return a deep copy of metadata with callback_vars values encrypted at rest. Idempotent: a value that already decrypts cleanly is left unchanged s

Rewrite an ``mcp_tool_permissions`` dict keyed by id/name/alias so every key is a concrete server_id where possible. Tool lists from

Creates appropriate wrapper functions for different API call types. Returns: - A synchronous function for synchronous ca

Log failed db read/writes Currently only logs exceptions to sentry

If a model has a team_id Only use if request is from that team

Retrieves the Arize Phoenix configuration based on environment variables. Returns:

Returns the config model for the guardrail This is used to render the config model in the UI.

Returns `extra_body` to be added to the request body for the Guardrail API call Use this to pass dynamic params to the guardrail API

Determine MIME type from file path extension. Falls back to mimetypes.guess_type, then to 'application/octet-stream'.

v2 vector store config, use this for new vector store integrations

Clean and filter the metadata dictionary to include only the specified keys in StandardLoggingMetadata. Args: metadata (

Fast, cached check for whether a callback is an async function. Falls back gracefully if the object cannot be weak-referenced or cached.

Create a tool call dict matching the ChatCompletionMessageToolCall schema.

Normalize a reasoning effort value based on model capabilities. Degradation chains: - "max" → max / xhigh / high - "xhigh" → x

Update data dictionary with model credentials (in-place). Args: data: Data dictionary to update credentials: Credentials fro

Process Gemini embedContent response (single embedding for multimodal input). Args: input: Original input model_response: Em

Return the json str of the request This is currently in BETA, and tested for `/chat/completions` -> `litellm.completion` calls.

Safely get Vertex AI credentials without mutating the litellm_params dict. Unlike get_vertex_ai_credentials(), this does NOT pop val

Recursively remove OCI-incompatible fields from a JSON schema. Strips ``title`` keys, removes ``None``-valued ``default`` entries, normalises

Strip LiteLLM routing prefixes from model name.

Check if the given model + provider supports 'response_schema' as a param. Parameters: model (str): The model name to be checked. cu

Map a v1 server onto a ServerSpec for a migrated mode, or None to defer to v1. BYOK is the per-user source of the ``api_key`` mode; its scheme ri

Transform user_api_key_dict to a metadata dict with prefixed keys. Converts keys like 'user_id' to 'user_api_key_user_id' to clearly

Short-circuit web-search-only requests by executing the search directly. Claude Code sends web search as a separate, standalone /v1/

Update the router settings.

Return minimal kwargs for set_attributes with Responses API defaults.

Fingerprint API keys, scrub them, and normalize multipart boundaries. Order matters in two ways: 1. vcrpy's ``filter_headers`` config option

Check if the user has access to the vector store. Delegates to :func:`can_user_access_vector_store`, which honors: - PROXY_ADMIN bypass

Helper: return dict[attr_name] = value of all set_attribute calls.

Construct Azure realtime WebSocket URL. Args: api_base: Azure API base URL (will be converted from https:// to wss://)

Instantiate ContentFilterGuardrail with a given category.

Internal method to process the cached result Checks the call type and converts the cached result to the appropriate model response o

Reject the batch if the caller is not authorized for the upload target. For managed files, ``target_model_names`` (from the unified file id)

Legacy path: execute search + build patch + run follow-up call.

Get Azure config based on model type. When *base_model* is provided (e.g. ``"azure/gpt-5.2"``), it is used for model-type detection i

Checks the request 'source' if a cli state token was passed in This is used to authenticate through the CLI login flow. The

Resolve the key's unified `access_group_ids` (LiteLLM_AccessGroupTable) to MCP server IDs as additive grants: a group attached to the

Internal function. Returns the token and url for the call. Handles logic if it's google ai studio vs. vertex ai. Returns

Helper method to get tools from a single MCP server with prefixed names. Args: server (MCPServer): The server to query t

Helper to get a valid ClientSession for the current event loop. This handles the case where the session was created in a different

Tolerantly read ``web_search_requests`` from a ``server_tool_use`` value that may be ``None``, a ``dict``, a ``ServerToolUse`` pydantic insta

Handles Connection Errors when reading a Virtual Key from LiteLLM DB Use this if you don't want failed DB queries to block LLM API re

Optional continuous profiling via Grafana Pyroscope. Off by default. Enable with LITELLM_ENABLE_PYROSCOPE=true. Requires: pi

Run invoke_agent_a2a with standard patches applied.

Check if the current environment is already running as the target IAM role. This handles multiple AWS environments: - IRSA (

Check if the input contains multimodal data (data URIs, file references, GCS URLs, or nested lists for combined embeddings). Args:

Check if the error message indicates a database permission error. Permission errors should NOT be marked as applied, as the migratio

Find a deployment whose declared keywords appear in `user_message`. Returns (model_name, matched_keyword) or None when no keyword ma

Check if a token exists in the deprecated keys table and is still within its grace period. Returns the active_token_id if found and valid, o