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

# Google ADK

> Register BenchGuard as a beforeModelCallback on your Gemini agent.

The Google Agent Development Kit (ADK) exposes a `before_model_callback` / `beforeModelCallback` hook that fires before every LLM call. Benchspan ships a factory that scans each content part before the Gemini call goes out.

## Python

<Steps>
  <Step title="Install">
    ```bash theme={null}
    pip install benchspan google-adk
    ```
  </Step>

  <Step title="Register the callback">
    ```python agent.py theme={null}
    from benchspan import BenchGuard
    from google.adk import LlmAgent

    guard = BenchGuard(api_key="ag_live_...", agent="gemini-app")

    agent = LlmAgent(
        name="assistant",
        model="gemini-2.5-pro",
        before_model_callback=guard.as_adk_callback(),
    )
    ```
  </Step>
</Steps>

## TypeScript

<Steps>
  <Step title="Install">
    ```bash theme={null}
    npm install @benchspan/sdk @google/adk
    ```
  </Step>

  <Step title="Register the callback">
    ```typescript agent.ts theme={null}
    import { BenchGuard } from "@benchspan/sdk";
    import { LlmAgent } from "@google/adk";

    const guard = new BenchGuard({ apiKey: "ag_live_...", agent: "gemini-app" });

    const agent = new LlmAgent({
      name: "assistant",
      model: "gemini-2.5-pro",
      beforeModelCallback: guard.asAdkCallback(),
    });
    ```
  </Step>
</Steps>

## What gets scanned

Every text part in `llmRequest.contents`. The `role` of each content determines how it's classified:

| ADK role                            | Scanned as |
| ----------------------------------- | ---------- |
| `user`                              | `user`     |
| `model` (tool response round-trips) | `tool`     |

System instructions and pure model completions are skipped; they're inside your trust boundary.

## Handling blocks

In block mode, the callback raises `InjectionDetectedError` which propagates out of the ADK invocation. Wrap your agent call in a `try / except` (Python) or `try / catch` (TypeScript):

```python theme={null}
from benchspan import InjectionDetectedError

try:
    response = await agent.run_async(user_input)
except InjectionDetectedError as e:
    # Log, alert, return safe error to user
    print(f"Blocked: score={e.result.score:.4f}")
```