Stanley Code

# Stanley

**A Jev-first, self-improving coding agent.**

Stanley is a command-line tool for checking and understanding code changes. Instead of naming a command,
you describe what you need. [TypeSafe Jev](https://typesafe.ai) routes the request to one workflow: a built-in,
a trusted repository workflow, or one Stanley wrote for itself. Each workflow is deterministic code that
gathers bounded evidence and asks Jev small fixed-choice questions about it; code, not a model, makes the
decisions. That is the hot path, and it never starts a general agent.

When no workflow supports a request, Stanley falls back to the [Pi](https://www.npmjs.com/package/@earendil-works/pi-coding-agent)
coding agent if it is installed, reports the agent's own account of what it did without claiming to have verified
it, and then, in the background, asks an agent to write a Stanley workflow for that kind of request. The
candidate is validated and staged; you promote it, and the next such request runs without any agent.

Stanley was previously published as the `jev-code` placeholder package; see [docs/decision-log.md](docs/decision-log.md).

## Get started

> **Release status:** `stanley-code` is not on npm yet. This README describes `0.1.0`, which is not released;
> until it is, build from source. (The old `jev-code` placeholder package on npm is `0.0.1` and does nothing.)

**Requirements:** Node.js 22.18 or newer, `git`, a Git repository to check, and a TypeSafe API key. Optional:
the [Pi coding agent](https://www.npmjs.com/package/@earendil-works/pi-coding-agent) (`npm install -g
@earendil-works/pi-coding-agent`, configured with its own model credentials) for the agent fallback. CI tests
on Linux; Windows is untested.

**Install** (from source, until 0.1.0 is on npm):

```sh
git clone https://g