Skip to content

Changelog

All notable changes to this project are documented here. The format follows Keep a Changelog, and the project uses Semantic Versioning.

[Unreleased]

Changed

  • The docs now live at https://keeljourney.dev.
  • Reframed the project as a learning journey with the tagline "Learning by building, one port at a time". The one-file agent is Destination 1.
  • Docs are organized by destination: a journey home page, then a section per destination.
  • bench/baseline.sh needs MODELS, and bench/setup.sh pulls only the Ollama models it lists.

Added

  • MIT license.
  • GitHub Actions workflow that type-checks and tests every push and pull request.
  • npm run typecheck, powered by TypeScript.
  • .nvmrc pinning Node 22.18.0.
  • Package metadata: description, repository, keywords and license.
  • Documentation site built with MkDocs Material and published to GitHub Pages.
  • bench/swebench_lite.py: runs Keel on SWE-bench Lite and grades the patches, with resumable runs and automatic Node download.
  • Benchmark instructions for Terminal-Bench 4.0 and Aider Polyglot through Harbor.
  • Logo and banner, and a README header with badges.
  • PROXY_HOST for the Bedrock proxy, so benchmark containers on Linux can reach it.

Fixed

  • Keel no longer fails with other side closed when a command outlasts the model server's keep-alive timeout, as with the Bedrock proxy or vLLM.
  • bench/setup.sh and bench/baseline.sh work on Linux, and bench/swebench_lite.py uses KEEL_BASE_URL like the Harbor runs.

[0.1.0] - 2026-11-20

Added

  • agent.ts: a single-file coding agent that works through a bash tool over any OpenAI-compatible chat API.
  • Text adapter that reads one fenced bash block per reply, so it works the same on every model and server.
  • Canonical Part and Message types with an Adapter interface for supporting new APIs.
  • Completion signalled by a command that prints COMPLETE_TASK_AND_SUBMIT_FINAL_OUTPUT.
  • Test suite that runs the real loop against a scripted fake model server.
  • Harbor adapter (bench/keel_agent.py) for Terminal-Bench and SWE-bench.
  • Optional AWS Bedrock proxy (bedrock/).