# managed_rejections

> **Function** in `deepagents_code`

📖 [View in docs](https://reference.langchain.com/python/deepagents-code/configuration/service/managed_rejections)

Return manifest keys managed policy declares whose value was dropped.

Not a launch failure: only `ENFORCED_MANAGED_KEYS` stops a launch, and every
other rejected managed value deliberately falls through to the user tier.
But the fall-through was announced only through `logger.warning`, which the
package's in-memory log handler makes unreachable from stderr — the handler
installed at import time means `logging.lastResort` never fires. An
administrator who typed `max_tokens = "8000"` saw a clean green table and
had no way to learn the value was ignored.

## Signature

```python
managed_rejections(
    managed_data: dict[str, Any],
) -> tuple[str, ...]
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `managed_data` | `dict[str, Any]` | Yes | Managed table to inspect. Must come from a snapshot whose status is `usable`. |

## Returns

`tuple[str, ...]`

The rejected keys, sorted, empty when every declared value is readable.

---

[View source on GitHub](https://github.com/langchain-ai/deepagents/blob/caaa7e7c12d214afa5cf0a1afed8eb6232aa6f7b/libs/code/deepagents_code/configuration/service.py#L423)