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

# PII Rehydration

> Configure transparent PII deanonymization so sandbox code receives original PII values in API responses.

## What You'll Learn

* Creating a sandbox with `rehydrate_response=True` (transparent mode)
* Creating a sandbox with `rehydrate_response=False` (strict mode)
* The five-step flow: send, redact, process, restore, receive
* When to use each mode

## How Rehydration Works

When `rehydrate_response=True`, the edge proxy maintains a per-request token mapping:

1. **Send** — Code in the sandbox sends an HTTP request containing PII (e.g., `john@example.com`)
2. **Redact** — Proxy replaces PII with a token: `[REDACTED_EMAIL_1]` and stores the mapping
3. **Process** — The external API receives the sanitized request and responds (possibly echoing the token)
4. **Restore** — Proxy scans the response, finds `[REDACTED_EMAIL_1]`, and restores `john@example.com`
5. **Receive** — Sandbox code receives the response with the original PII value — completely transparent

With `rehydrate_response=False`, step 4 is skipped and redaction tokens remain in the response.

<Note>
  PII scanning via the guardrails service is rolling out. This example demonstrates the SDK API for configuring PII rehydration — the policy is accepted and stored today.
</Note>

## Prerequisites

<Snippet file="snippets/env-setup.mdx" />

<Note>This example is available in Python. TypeScript version coming soon.</Note>

## Code Walkthrough

**Rehydration enabled** — sandbox code sees the original PII in responses:

```python theme={null}
from declaw import Sandbox, SecurityPolicy, PIIConfig

policy = SecurityPolicy(
    pii=PIIConfig(
        enabled=True,
        types=["email", "phone"],
        action="redact",
        rehydrate_response=True,
    )
)

sbx = Sandbox.create(template="base", timeout=300, security=policy)
try:
    print(f"Sandbox created: {sbx.sandbox_id}")
    # When guardrails service is active:
    # POST { "msg": "Contact john@example.com" }
    # -> proxy sends: { "msg": "Contact [REDACTED_EMAIL_1]" }
    # <- API replies: { "reply": "I will email [REDACTED_EMAIL_1]" }
    # -> proxy restores: { "reply": "I will email john@example.com" }
    # Sandbox code receives the restored version.
finally:
    sbx.kill()
```

**Rehydration disabled** — redaction tokens remain in responses (strict mode):

```python theme={null}
policy = SecurityPolicy(
    pii=PIIConfig(
        enabled=True,
        types=["email", "phone"],
        action="redact",
        rehydrate_response=False,
    )
)

sbx = Sandbox.create(template="base", timeout=300, security=policy)
try:
    print(f"Sandbox created: {sbx.sandbox_id}")
    # POST { "msg": "Contact john@example.com" }
    # -> proxy sends: { "msg": "Contact [REDACTED_EMAIL_1]" }
    # <- API replies: { "reply": "I will email [REDACTED_EMAIL_1]" }
    # -> proxy passes through unchanged
    # Sandbox code receives: { "reply": "I will email [REDACTED_EMAIL_1]" }
finally:
    sbx.kill()
```

## Choosing a Mode

| Mode        | `rehydrate_response` | Use When                                                                         |
| ----------- | -------------------- | -------------------------------------------------------------------------------- |
| Transparent | `True`               | Application must work as if PII was never redacted; best for most LLM workflows  |
| Strict      | `False`              | Sandbox code must never see original PII in responses; maximum privacy isolation |