Skip to main content

Builtin evaluators for agent-control

Project description

Agent Control Evaluators

Built-in evaluators for agent-control.

Installation

pip install agent-control-evaluators

Available Evaluators

Name Description
regex Regular expression pattern matching
list List-based value matching (allow/deny)
json JSON validation (schema, required fields, types)
sql SQL query validation

Usage

Evaluators are automatically discovered via Python entry points:

from agent_control_evaluators import discover_evaluators, list_evaluators

# Load all available evaluators
discover_evaluators()

# See what's available
print(list_evaluators())
# {'regex': <class 'RegexEvaluator'>, 'list': ..., 'json': ..., 'sql': ...}

External Evaluators

Additional evaluators are available via separate packages:

  • agent-control-evaluator-galileo - Galileo Luna2 evaluator
# Direct install
pip install agent-control-evaluator-galileo

# Or via convenience extra
pip install agent-control-evaluators[galileo]

Creating Custom Evaluators

See AGENTS.md for guidance on creating new evaluators.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agent_control_evaluators-5.2.0.tar.gz (44.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agent_control_evaluators-5.2.0-py3-none-any.whl (35.1 kB view details)

Uploaded Python 3

File details

Details for the file agent_control_evaluators-5.2.0.tar.gz.

File metadata

  • Download URL: agent_control_evaluators-5.2.0.tar.gz
  • Upload date:
  • Size: 44.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for agent_control_evaluators-5.2.0.tar.gz
Algorithm Hash digest
SHA256 90f12411dd3d321c161f7d9ba17f353b6c007ca3615a0af17aa0c7a65359ca4d
MD5 222f834348d42f05256d131f523a7b49
BLAKE2b-256 1225bcd44bb394c031faf110362be2c5d4ec120a139d3e76a51c223fbfd9e8b9

See more details on using hashes here.

File details

Details for the file agent_control_evaluators-5.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for agent_control_evaluators-5.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3a3a281ccf1f160487ba9e18ff0ab15689c98bf78f1d48c14e5ee26a0fa81265
MD5 2b63837822a9cadd99d1f24503277857
BLAKE2b-256 a012a3b283f2f92083c9d4e96216423d71811c6f6355a1fbe225d4824b7ea1bc

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page