pii.py — langchain Source File

Source Code

"""PII detection and handling middleware for agents."""

from __future__ import annotations

from typing import TYPE_CHECKING, Any, Literal

from langchain_core.messages import AIMessage, AnyMessage, HumanMessage, ToolMessage
from typing_extensions import override

from langchain.agents.middleware._redaction import (
    PIIDetectionError,
    PIIMatch,
    RedactionRule,
    ResolvedRedactionRule,
    apply_strategy,
    detect_credit_card,
    detect_email,
    detect_ip,
    detect_mac_address,
    detect_url,
)
from langchain.agents.middleware.types import (
    AgentMiddleware,
    AgentState,
    ContextT,
    ResponseT,
    hook_config,
)

if TYPE_CHECKING:
    from collections.abc import Callable

    from langgraph.runtime import Runtime


class PIIMiddleware(AgentMiddleware[AgentState[ResponseT], ContextT, ResponseT]):
    """Detect and handle Personally Identifiable Information (PII) in conversations.

    This middleware detects common PII types and applies configurable strategies
    to handle them. It can detect emails, credit cards, IP addresses, MAC addresses, and
    URLs in both user input and agent output.

    Built-in PII types:

    - `email`: Email addresses
    - `credit_card`: Credit card numbers (validated with Luhn algorithm)
    - `ip`: IP addresses (validated with stdlib)
    - `mac_address`: MAC addresses
    - `url`: URLs (both `http`/`https` and bare URLs)

    Strategies:

    - `block`: Raise an exception when PII is detected
    - `redact`: Replace PII with `[REDACTED_TYPE]` placeholders
    - `mask`: Partially mask PII (e.g., `****-****-****-1234` for credit card)
    - `hash`: Replace PII with deterministic hash (e.g., `<email_hash:a1b2c3d4>`)

    Strategy Selection Guide:

    | Strategy | Preserves Identity? | Best For                                |
// ... (317 more lines)