BerriAI/litellm · error · ValueError

No active custom logger found for callback name: {callback_n

Error message

No active custom logger found for callback name: {callback_name}

What it means

get_active_custom_logger_for_callback_name looks up the CustomLoggerRegistry class type for a callback name, then searches the currently active litellm.callbacks list for instances of that type. If zero instances are registered, it raises ValueError. This happens when config references a named callback (e.g. 'langfuse', 'openmeter') that was never activated — the class exists in the registry but no live logger object was added to litellm.callbacks.

Source

Thrown at litellm/litellm_core_utils/logging_callback_manager.py:478

    def get_active_custom_logger_for_callback_name(
        self,
        callback_name: _custom_logger_compatible_callbacks_literal,
    ) -> CustomLogger | None:
        """
        Get the active custom logger for a given callback name
        """
        from litellm.litellm_core_utils.custom_logger_registry import (
            CustomLoggerRegistry,
        )

        # get the custom logger class type
        custom_logger_class_type: Final = CustomLoggerRegistry.get_class_type_for_custom_logger_name(callback_name)

        # get the active custom logger
        custom_logger: Final = self.get_custom_loggers_for_type(custom_logger_class_type)

        if len(custom_logger) == 0:
            raise ValueError(f"No active custom logger found for callback name: {callback_name}")

        return custom_logger[0]

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Install the integration package for the callback (e.g. pip install 'litellm[langfuse]') and set its required env variables, then restart so the logger activates.
2. Verify activation at runtime: assert any(isinstance(c, ExpectedLoggerClass) for c in litellm.callbacks) before the lookup.
3. Check the proxy/general settings logs for callback initialization errors that were swallowed earlier.
4. If calling the API yourself, fall back gracefully when zero loggers are found.

Example fix

// before
from litellm.litellm_core_utils.logging_callback_manager import LoggingCallbackManager
logger = mgr.get_active_custom_logger_for_callback_name('langfuse')

# after
import litellm
loggers = [c for c in litellm.callbacks if type(c).__name__.lower().startswith('langfuse')]
logger = loggers[0] if loggers else None

import litellm

def callback_is_active(name: str) -> bool:
    return any(type(c).__name__.lower().startswith(name.lower()) for c in litellm.callbacks)

try:
    logger = mgr.get_active_custom_logger_for_callback_name('langfuse')
except ValueError:
    logger = None  # observability optional; degrade gracefully

When it happens

Trigger: Setting a config field like success_callback=['langfuse'] without the integration package installed or without litellm initializing the callback; referencing a callback name in proxy config.yaml while the corresponding env vars/credentials are missing so activation was skipped; calling get_active_custom_logger_for_callback_name manually before litellm.settings.callbacks is populated.

Common situations: Missing 'langfuse' pip package; proxy config lists a callback whose required env keys (e.g. LANGFUSE_PUBLIC_KEY) are absent so the logger never activates; ordering issues where the lookup runs before callback initialization; typos in callback names that silently map to a registry entry but never get instantiated.

Related errors

• Missing keys={missing_keys} in environment.
• LEVOAI_API_KEY environment variable is required for Levo int
• No valid endpoint found for Arize, please set 'ARIZE_ENDPOIN
• LOGFIRE_TOKEN not found in environment variables
• LANGTRACE_API_KEY not found in environment variables

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/ade14ae7927dc1be. Report an issue: GitHub.