> ## Documentation Index
> Fetch the complete documentation index at: https://studio.chat-atp.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Error Handling

> Handling errors from the ChatATP Studio SDK

## Exception hierarchy

All SDK errors extend `ChatATPError`, which carries:

* `status_code` — the HTTP status code (if applicable)
* `args[0]` — a human-readable message
* `payload` — the raw API response body
* `request_id` — the server request ID (when available)

```
ChatATPError
├── AuthenticationError   (401)
├── PermissionError       (403)
├── ValidationError       (400)
├── RateLimitError        (429)
├── NotFoundError         (404)
├── ServerError           (5xx)
└── NetworkError
    └── TimeoutError
```

## Handling errors

```python theme={null}
from chatatp_studio import (
    ChatATPClient,
    AuthenticationError,
    NotFoundError,
    RateLimitError,
    ValidationError,
    ServerError,
    NetworkError,
)

client = ChatATPClient(api_key="chatatp_sk_...")

try:
    agent = await client.agents.retrieve(999)
except AuthenticationError:
    print("Check your API key.")
except NotFoundError:
    print("Agent not found.")
except RateLimitError:
    print("Slow down — you've hit the rate limit.")
except ValidationError as e:
    print("Bad request:", e.payload)
except ServerError:
    print("ChatATP server error, try again shortly.")
except NetworkError as e:
    print("Network failure:", e)
```

## Retries

The SDK retries automatically on transient failures with exponential backoff. The default is **2 retries**. Adjust via:

```python theme={null}
client = ChatATPClient(api_key="chatatp_sk_...", max_retries=3)
```

Set `max_retries=0` to disable retries entirely.