litellm/tests/code_coverage_tests/recursive_detector.py

import ast
import os

IGNORE_FUNCTIONS = [
    "_json_cost",  # bounded at depth 32 and consumed under byte/node limits.
    "detached",  # router_config: copies only the plain containers of the router's own constructor arguments, once per build or changeset
    "_format_type",
    "remove_additional_properties",
    "remove_strict_from_schema",
    "filter_schema_fields",
    "text_completion",
    "_check_for_os_environ_vars",
    "clean_message",
    "unpack_defs",
    "convert_anyof_null_to_nullable",  # has a set max depth
    "add_object_type",
    "strip_field",
    "transform_prompt",
    "mask_dict",
    "_serialize",  # we now set a max depth for this
    "_sanitize_request_body_for_spend_logs_payload",  # testing added for circular reference
    "_sanitize_value",  # testing added for circular reference
    "set_schema_property_ordering",  # testing added for infinite recursion
    "process_items",  # testing added for infinite recursion + max depth set.
    "_can_object_call_model",  # max depth set.
    "encode_unserializable_types",  # max depth set.
    "filter_value_from_dict",  # max depth set.
    "normalize_json_schema_types",  # max depth set.
    "_extract_fields_recursive",  # max depth set.
    "remove_json_schema_refs",  # max depth set.,
    "_convert_schema_types",  # max depth set.,
    "_fix_enum_empty_strings",  # max depth set.,
    "get_access_token",  # max depth set.,
    "_redact_base64",  # max depth set.
    "_contains_vision_content",  # max depth set.
    "_read_all_bytes",  # max depth set.
    "_fix_enum_types",  # max depth set.
    "_collect_argument_paths",  # max depth set.
    "_split_text",  # max depth set.
    "_mask_sequence",  # max depth set.
    "_encrypted_param",  # max depth set.
    "_decrypted_param",  # max depth set.
    "contains_encrypted_marker",  # max depth set.
    "_rotate_guardrail_row",  # bounded by attempts_left.
    "_delete_nested_value_custom",  # max depth set (bounded by number of path segments).
    "_filter_exceptions_from_params",  # max depth set (default 20) to prevent infinite recursion.
    "__getattr__",  # lazy loading pattern in litellm/__init__.py with proper caching to prevent infinite recursion.
    "_validate_inheritance_chain",  # max depth set (default 100) to prevent infinite recursion in policy inheritance validation.
    "_basic_json_schema_validate",  # max depth set.
    "extract_text_from_a2a_message",  # max depth set (default 10) to prevent infinite recursion in A2A message parsing.
    "_convert_to_json_serializable_dict",  # max depth set (default 20) and circular reference protection to prevent infinite recursion.
    "dict",  # max depth set. _LiteLLMParamsDictView.dict() calls builtin dict(), not itself.
    "_read_image_bytes",  # max depth set.
    "get_masked_values",  # max depth set (default 20) to prevent infinite recursion while masking nested sensitive config dicts.
    "_redact_sensitive_litellm_params",  # max depth set (default 10).
    "_redact_secret_values_in_obj",  # max depth set (default 10, _REDACT_SECRET_MAX_DEPTH); fails closed by returning "REDACTED" at the cap.
    "_resolve",  # OCI: $ref resolver bounded by `resolving_stack` cycle guard.
    "resolve_oci_schema_anyof",  # OCI: bounded by JSON-schema tree depth (no cycles possible in well-formed input).
    "sanitize_oci_schema",  # OCI: bounded by JSON-schema tree depth.
    "_freeze_for_dedupe",  # OTEL: max depth set (default 16, _FREEZE_MAX_DEPTH); fails closed by returning repr(value) at the cap.
    "apply_json_merge_patch",  # max depth set (_MAX_MERGE_DEPTH=64); fails closed by raising ValueError at the cap.
    "_inlined",  # max depth set (_MAX_INLINE_DEPTH=32); passes the schema node through untouched at the cap. Walks a Pydantic JSON schema once at import time.
    "_filter_argument_value",  # max depth set (DEFAULT_MAX_RECURSE_DEPTH); fails closed by blocking the tool call at the cap.
    "_redact_scanned_content",  # max depth set (DEFAULT_MAX_RECURSE_DEPTH); fails closed by returning "[REDACTED]" at the cap.
    "replace_ciphertexts",  # max depth set (DEFAULT_MAX_RECURSE_DEPTH); walks stored JSON, which has no cycles, and leaves values below the cap untouched.
    "_iter_fallback_targets",  # max depth set (2 * ROUTER_MAX_FALLBACKS); fails closed by raising ValueError at the cap.
    "_mergeable_branch",  # max depth set (_MAX_SCHEMA_FLATTEN_DEPTH=32) plus a seen_refs cycle guard; passes the schema through untouched at the cap.
    "json_string_leaves",  # max depth set (MAX_STRUCTURED_CONTENT_SCAN_DEPTH); fails closed by raising at the cap so nothing goes unscanned.
    "strict_json_schema",  # harness: max depth set (DEFAULT_MAX_RECURSE_DEPTH); fails closed by raising ValueError at the cap.
    "toml_value",  # harness/codex: max depth set (DEFAULT_MAX_RECURSE_DEPTH); fails closed by raising OptionsMismatch at the cap.
    "with_json_string_leaves",  # transitively bounded: only runs on a tree json_string_leaves already walked under the cap.
    "_clean_extraction",  # ScaleDown: traverses the entity map built under MAX_SCHEMA_DEPTH=32 and MAX_ENTITIES=1000.
    "json_unrewritable_labels",  # max depth set (MAX_STRUCTURED_CONTENT_SCAN_DEPTH); returns the None sentinel at the cap so the caller blocks.
    "_flatten_form_field",  # bounded by the nesting depth of the already-parsed request body (a finite JSON tree, no cycles possible).
    "_flatten_form_data_field",  # bounded by the nesting depth of the already-parsed request body (a finite JSON tree, no cycles possible).
    "_json_safe",  # max depth set (_MAX_DEPTH) plus a seen-ids cycle guard for self-referential input.
    "_redact_agent_params_tree",  # max depth set (default 10), same shape as _redact_sensitive_litellm_params.
    "_restore_redacted_nested_value",  # max depth set (default 10), mirrors _redact_agent_params_tree on the write side.
    "_unqualified",  # bounded by the qualifier depth of a static TypedDict annotation (Annotated, Required/NotRequired, ReadOnly around one type, no cycles possible).
    "_render_json",  # bounded by the nesting depth of a pydantic-validated JsonValue from the operator's config (a finite JSON tree, no cycles possible).
    "with_id_fields_replaced",  # harness/opencode: bounded by the nesting depth of the JsonValue that validate_json parsed from `opencode export`, which refuses nesting past ~200 levels.
    "completion_cost",  # max depth 1: recursion only fires for mixed-tier Responses WS logging objects, and each split part carries a single service_tier so _split_responses_ws_logging_object_by_service_tier returns None.
    "_string_leaves",  # bounded by the nesting depth of a safe_json_structure output (a finite JSON tree, no cycles possible).
    "_replace_string_leaves",  # bounded by the nesting depth of a safe_json_structure output (a finite JSON tree, no cycles possible).
    "_redacted_client_field",  # bounded by the nesting depth of a JSON-decoded error body (a finite JSON tree, no cycles possible).
    "_sort_processed_sets",  # bounded by the nesting depth of the log-record extra it walks (a finite JSON tree, no cycles possible).
    "scrub_json_strings",  # max depth set (MAX_SCRUB_DEPTH); fails closed by returning "[Filtered]" for anything nested past the cap.
    "_without_requester_ip_address",  # walks only the fresh tree _sanitize_request_body_for_spend_logs_payload returns (mapping cycles already cut), so it never goes deeper than that sanitizer did.
    "_merge_session_fields",  # max depth set (_SESSION_MERGE_MAX_DEPTH); deeper mappings are replaced wholesale by the later session.update.
    "_json",  # router_rust index views: max depth set (DEFAULT_MAX_RECURSE_DEPTH); fails closed by raising ValueError at the cap.
    "to_wire",  # router_rust model info: bounded by the nesting depth of a stored deployment or cost-map entry (finite JSON trees: pydantic refuses a cycle when it dumps a deployment).
    "from_wire",  # router_rust model info: walks only what router-core merged from to_wire's output, so it never goes deeper than to_wire did.
]


class RecursiveFunctionFinder(ast.NodeVisitor):
    def __init__(self):
        self.recursive_functions = []
        self.ignored_recursive_functions = []

    def visit_FunctionDef(self, node):
        # Check if the function calls itself
        if any(self._is_recursive_call(node, call) for call in ast.walk(node)):
            if node.name in IGNORE_FUNCTIONS:
                self.ignored_recursive_functions.append(node.name)
            else:
                self.recursive_functions.append(node.name)
        self.generic_visit(node)

    def _is_recursive_call(self, func_node, call_node):
        # Check if the call node is a function call
        if not isinstance(call_node, ast.Call):
            return False

        # Case 1: Direct function call (e.g., my_func())
        if isinstance(call_node.func, ast.Name) and call_node.func.id == func_node.name:
            return True

        # Case 2: Method call with self (e.g., self.my_func())
        if isinstance(call_node.func, ast.Attribute) and isinstance(
            call_node.func.value, ast.Name
        ):
            return (
                call_node.func.value.id == "self"
                and call_node.func.attr == func_node.name
            )

        return False


def find_recursive_functions_in_file(file_path):
    with open(file_path, "r") as file:
        tree = ast.parse(file.read(), filename=file_path)
    finder = RecursiveFunctionFinder()
    finder.visit(tree)
    return finder.recursive_functions, finder.ignored_recursive_functions


def find_recursive_functions_in_directory(directory):
    recursive_functions = {}
    ignored_recursive_functions = {}
    for root, _, files in os.walk(directory):
        for file in files:
            print("file: ", file)
            if file.endswith(".py"):
                file_path = os.path.join(root, file)
                functions, ignored = find_recursive_functions_in_file(file_path)
                if functions:
                    recursive_functions[file_path] = functions
                if ignored:
                    ignored_recursive_functions[file_path] = ignored
    return recursive_functions, ignored_recursive_functions


if __name__ == "__main__":
    # Example usage
    # raise exception if any recursive functions are found, except for the ignored ones
    # this is used in the CI/CD pipeline to prevent recursive functions from being merged

    directory_path = "./litellm"
    recursive_functions, ignored_recursive_functions = (
        find_recursive_functions_in_directory(directory_path)
    )
    print("UNIGNORED RECURSIVE FUNCTIONS: ", recursive_functions)
    print("IGNORED RECURSIVE FUNCTIONS: ", ignored_recursive_functions)

    if len(recursive_functions) > 0:
        # raise exception if any recursive functions are found
        for file, functions in recursive_functions.items():
            print(
                f"🚨 Unignored recursive functions found in {file}: {functions}. THIS IS REALLY BAD, it has caused CPU Usage spikes in the past. Only keep this if it's ABSOLUTELY necessary."
            )
        file, functions = list(recursive_functions.items())[0]
        raise Exception(
            f"🚨 Unignored recursive functions found include {file}: {functions}. THIS IS REALLY BAD, it has caused CPU Usage spikes in the past. Only keep this if it's ABSOLUTELY necessary."
        )