mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +00:00
* fix(otel): hashable scope for _emit_once when guardrail_mode is list `_emit_once` keys `spans_logged` by `(class, id, *scope)`. When a guardrail entry's `guardrail_mode` arrives as a `List[GuardrailEventHooks]` (the shape Presidio expands to with `output_parse_pii: true`, and the shape `event_hook` carries for any `mode: [...]` in config), the tuple contains a list and `spans_logged.get(dedupe_key)` raises `TypeError: unhashable type: 'list'`. On the post-call path this fires inside the logging callback and is swallowed; the request returns 200 but the OTEL `guardrail` span is silently dropped. On the blocking path the same error surfaces as HTTP 500. Adds `_freeze_for_dedupe`, a small recursive normalizer that turns lists and tuples into tuples, sets into frozensets, dicts into frozensets of `(key, value)` pairs, and falls back to `repr` for arbitrary unhashables. Applied inside `_emit_once` before the dict lookup, so all three callsites are protected without touching the guardrail-specific callsite. Helper assumes acyclic input; `guardrail_mode` values are built fresh from config (str enums, lists of str enums, TypedDict of str/list-of-str), so no cycle can arise in practice. Regression tests in `TestOpenTelemetrySpanDedupe` cover the list crash, distinct-list-scope collision, dict and set scope parts, and an end-to-end `_create_guardrail_span` exercise that confirms exactly one `guardrail` span is emitted across repeated lifecycle entrypoints. Each new test fails on a reverted helper (4/4 mutation kill) * fix(otel): cap _freeze_for_dedupe recursion depth and ignore in recursive detector CI's recursive_detector blocks new recursive functions in litellm/ unless they are in the allowlist with a documented bound. Cap the helper at 16 levels and return repr(value) past the cap; this is well past the realistic depth of guardrail_mode (1-3 levels) and means a future caller passing a cyclic container can no longer push the proxy logging path into a RecursionError. Add a regression test that exercises the cycle path. * refactor(otel): annotate _freeze_for_dedupe return as a HashableScope union Per review feedback from @mateo-berri: replace the loose `-> object` annotation with a recursive `HashableScope` union (str | int | float | bool | bytes | None | Tuple[HashableScope, ...] | FrozenSet[HashableScope]) so the helper's contract is visible at the signature. Replace the `try/except hash(value); return value` passthrough with an explicit isinstance check over the hashable-scalar types so the type checker can narrow without requiring `cast(Hashable, value)` on the return. Symmetric: dict keys also flow through the freezer (a TypedDict key is already a string in practice, so behaviorally identical). All 16 regression tests still pass; mutation kill behavior preserved * fix: avoid explicit casting --------- Co-authored-by: Mateo Wang <277851410+mateo-berri@users.noreply.github.com>
138 lines
6.4 KiB
Python
138 lines
6.4 KiB
Python
import ast
|
|
import os
|
|
|
|
IGNORE_FUNCTIONS = [
|
|
"_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.
|
|
"_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.
|
|
]
|
|
|
|
|
|
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."
|
|
)
|