DLP

The SDK ships with a regex-based DLP detector and an optional Presidio-backed one (via the [presidio] extra). DLP runs before policy evaluation so detections become first-class policy fields. See DLP concepts for the philosophy and policy patterns. This page is the API.

Enable

Three knobs — pick one:

from rubric import Governance

# 1. Constructor kwarg
with Governance.bootstrap(agent_name="…", dlp="auto") as gov:
    ...

# 2. Constructor with a concrete detector
from rubric.dlp import RegexDetector
with Governance.bootstrap(agent_name="…", dlp=RegexDetector()) as gov:
    ...

# 3. Env var
# AG_DLP=auto python my_agent.py

Modes

from rubric.constants import (
    DLP_MODE_OFF,
    DLP_MODE_REGEX,
    DLP_MODE_PRESIDIO,
    DLP_MODE_AUTO,
)

Constant	Value	Behavior
`DLP_MODE_OFF`	`"off"`	Detector disabled.
`DLP_MODE_REGEX`	`"regex"`	Built-in regex patterns only.
`DLP_MODE_PRESIDIO`	`"presidio"`	Presidio NER + regex (requires `[presidio]` extra).
`DLP_MODE_AUTO`	`"auto"`	Presidio if available, otherwise regex.

DlpDetection

class DlpDetection(BaseModel):
    detected: bool
    severity: Literal["low", "medium", "high"]
    types: list[str]
    matches: list[DlpMatch]

Field	Notes
`detected`	`True` if any pattern fired. `False` only if the detector ran and found nothing.
`severity`	The highest severity tier of any match.
`types`	Sorted list of matched type names (`EMAIL`, `SSN`, `AWS_KEY`, …).
`matches`	Detailed match records — value (sometimes redacted), location, type, severity.

DlpMatch

class DlpMatch(BaseModel):
    type: str
    value: str          # redacted to first/last 2 chars when severity is high
    severity: Literal["low", "medium", "high"]
    location: str       # JSON path in the scanned payload

Custom detector

Any object with this shape:

class MyDetector:
    def detect(self, payload: dict[str, Any]) -> DlpDetection | None:
        ...  # return None for no detection, DlpDetection for a hit

Pass via dlp=MyDetector() on bootstrap. The SDK calls .detect() once per evaluate(), passing the combined metadata dict (input + args + kwargs).

Built-in regex patterns

The default regex detector covers:

Type	Severity
`EMAIL`	low
`PHONE`	low
`IP_ADDRESS`	low
`JWT`	medium
`GITHUB_TOKEN`	medium
`SLACK_TOKEN`	medium
`GENERIC_API_KEY`	medium
`SSN`	high
`CREDIT_CARD`	high
`AWS_ACCESS_KEY`	high
`MEDICAL_RECORD_NUMBER`	high

Override per-detector by subclassing and changing the _PATTERNS map.

Failures

If a detector raises during detect(), the SDK logs and treats it as no-detection. Your evaluate() proceeds with dlp_detected: false. Fix the detector and you’re back. Detector exceptions never propagate up to the caller.

Python

Node

Enable

Modes

DlpDetection

DlpMatch

Custom detector

Built-in regex patterns

Failures

​Enable

​Modes

​DlpDetection

​DlpMatch

​Custom detector

​Built-in regex patterns

​Failures

Enable

Modes

DlpDetection

DlpMatch

Custom detector

Built-in regex patterns

Failures