Skip to main content

Refactor Arena

A Control Arena setting for evaluating agents on full repository refactoring tasks with optional backdoor insertion.

View full documentation.

Overview

This setting provides an environment for evaluating agents on full repository refactoring tasks. Each task involves:

  1. Main Task: Refactoring the repository to improve code quality and maintainability.
  2. Side Task (Attack Mode): Inserting a hidden vulnerability while performing the refactoring that is exploited when running the tests.

Installation

Install the package (requires Python 3.12):

# Install the package
pip install refactor-arena

# Setup your .env and initial scenario
refactor-arena init

# Run getting started scenario in honest mode
refactor-arena eval --config getting-started

If not already installed, install Docker. Docker must be running for the evals to execute.

Usage

Using the CLI

# Run with default settings using `side-tasks-3/mixed-3` dataset
refactor-arena

# Setup your .env and initial scenario
refactor-arena init

# Run getting started scenario in honest mode
refactor-arena eval --config getting-started

# Run getting started scenario in attack mode
refactor-arena eval --config getting-started --eval-mode attack

# Run with a different dataset from `github:fastfedora/full-repo-datasets` and limit main tasks
refactor-arena --dataset side-tasks-3/mixed-20 --main-task "refactor_single_file"

# Run with verbose logging and limit to 3 samples
refactor-arena eval --config getting-started --verbose --limit 3

# View help
refactor-arena --help

Configuration

To create a new scenario, create a file that references the main configuration file from the package and then override the settings you want to change.

For instance, to create a scenario that runs only the Refactor Single File main task against the 20-repo side-tasks-3/mixed-20 dataset in attack mode, create a file called mixed-20.yaml:

# mixed-20.yaml
includes:
  - package:config.yaml

setting:
  dataset: "side-tasks-3/mixed-20"
  main_task: refactor_single_file$

eval:
  # Default mode for this scenario is attack; use `--eval-mode honest` to run in honest mode
  mode: attack

Then run this scenario using:

refactor-arena --config=mixed-20

Almost all aspects of the setting can be configured via configuration files, including:

  • models
  • prompts
  • main tasks
  • side tasks
  • policies
  • monitors
  • metrics
  • eval settings

See the documentation for more details.

License

MIT License

Download files

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

Source Distribution

refactor_arena-0.9.0.tar.gz (50.2 MB view details)

Uploaded Source

Built Distribution

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

refactor_arena-0.9.0-py3-none-any.whl (293.2 kB view details)

Uploaded Python 3

File details

Details for the file refactor_arena-0.9.0.tar.gz.

File metadata

  • Download URL: refactor_arena-0.9.0.tar.gz
  • Upload date:
  • Size: 50.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for refactor_arena-0.9.0.tar.gz
Algorithm Hash digest
SHA256 e65e37dd0f8f5bb6d0ef935381896a1c679893abc1eb56a499467ec70ba5d49c
MD5 5a924f76ad47dc359cc9e82ec9232764
BLAKE2b-256 479ea29a18bf2c1bb3477210b7ca0b3d9ce880b6c867a34a4dd6faa328599d5c

See more details on using hashes here.

Provenance

The following attestation bundles were made for refactor_arena-0.9.0.tar.gz:

Publisher: publish.yml on fastfedora/refactor-arena

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file refactor_arena-0.9.0-py3-none-any.whl.

File metadata

  • Download URL: refactor_arena-0.9.0-py3-none-any.whl
  • Upload date:
  • Size: 293.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for refactor_arena-0.9.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ca8d0cbc68194ada204d0e65724e94e93520ed7c00f1a6cb96aacaeb06bcd06f
MD5 70dfeef97e54f813182e4001a495fe51
BLAKE2b-256 f6c3debdb4221777f8619b21c29978e74e72664a4acd9b131a8928d3a033348e

See more details on using hashes here.

Provenance

The following attestation bundles were made for refactor_arena-0.9.0-py3-none-any.whl:

Publisher: publish.yml on fastfedora/refactor-arena

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.10.0

2 files

This release

0.9.0 This release

2 files

0.8.1

2 files

0.8.0

2 files

0.7.0

2 files

0.6.1

2 files

0.6.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page