> ## Documentation Index
> Fetch the complete documentation index at: https://icrl.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Harbor Coding Agent

> Python coding-agent example aligned with Harbor-style sandbox workflows

## Overview

The Harbor coding agent demonstrates ICRL's performance improvement on realistic software engineering tasks. It uses a simulated coding workspace (`/workspace/src`, `/workspace/tests`) with shell-like commands for editing, navigation, and testing. The demo shows baseline vs post-training behavior on verifiable coding tasks.

## Source Files

| File                              | Purpose                                   |
| --------------------------------- | ----------------------------------------- |
| `examples/harbor_coding_agent.py` | Main demo script with `CodingEnvironment` |
| `tests/test_harbor_coding.py`     | Pytest tests for the demo                 |

## Run Demo

```bash theme={null}
OPENAI_API_KEY=... uv run python examples/harbor_coding_agent.py
```

Or with Anthropic:

```bash theme={null}
ANTHROPIC_API_KEY=... uv run python examples/harbor_coding_agent.py
```

Optional model override:

```bash theme={null}
MODEL=gpt-4o-mini uv run python examples/harbor_coding_agent.py
```

## Run Tests

```bash theme={null}
uv run pytest tests/test_harbor_coding.py -v
```

## What It Demonstrates

* **Coding workspace simulation** — Sandboxed `/workspace` with `src/` and `tests/`
* **Shell-like commands** — `ls`, `cd`, `cat`, `grep`, `find`, `sed`, `echo`, `pytest`, etc.
* **Baseline vs post-training** — Phase 1 runs evaluation tasks with no examples; Phase 2 trains on coding tasks; Phase 3 re-evaluates with learned examples
* **Verifiable tasks** — Each task has a `verify(workspace_state) -> bool` function

## Task Structure

Tasks are `CodingTask` objects with:

* `goal` — Natural language description
* `verify(workspace_state) -> bool` — Success predicate
* `setup` — Optional hook to modify initial state
* `difficulty` — `"easy"`, `"medium"`, `"hard"`
* `category` — `"code-analysis"`, `"debugging"`, `"navigation"`, `"testing"`, `"refactoring"`

This structure is suitable for repeatable benchmarking workflows and aligns with Harbor/Terminal-Bench 2.0 style evaluations.