Metadata-Version: 2.4
Name: rpek-lite
Version: 1.0.0
Summary: RPEK Prompt Execution Kernel - Certified Baseline
Author: RPEK Governance Board
Project-URL: Documentation, https://github.com/peteroluoch/prompt-governance-rpek-lite
Project-URL: Source Code, https://github.com/peteroluoch/prompt-governance-rpek-lite
Project-URL: Issue Tracker, https://github.com/peteroluoch/prompt-governance-rpek-lite/issues
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Software Development :: Build Tools
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: pytest==7.4.3
Dynamic: author
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: license-file
Dynamic: project-url
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# Prompt Governance RPEK-Lite

> [!WARNING]
> RPEK-LITE-V2 enforces live evidence for all TASK_COMPLETION reports. Simulated timestamps, log-inferred results, and heartbeat confirmations are auto-rejected.

A standalone, reusable, lightweight prompt execution kernel. This package scaffolds a generic framework for governing, building, and executing AI prompt tasks in a predictable, auditable manner.

**Core Principle:** No raw prompts. All prompts must pass through RPEK-LITE governance: adapter context, task payload, and strict validation.

## Installation

RPEK-Lite is distributed as a standard Python package. It has no external dependencies, making offline installation seamless.

```bash
# Install directly from the source tree
pip install .
```

This installs the package and registers the `rpek-build`, `rpek-task`, and `rpek-admit` CLI commands.

## Quick Start

1. **Initialize Project:** Create your consumer directory (e.g., `projects/my_project`) and an `adapter.json`.
2. **Scaffold a Task:**
   ```bash
   rpek-task my_project TASK_001 \
     --objective "Fix the login bug" \
     --allowed "auth/login.py" \
     --build
   ```
3. **Execute:** Submit `build/final_prompt_TASK_001.md` to your language model.
4. **Audit:** Review the execution in the `audit/` directory.

## CLI Commands

The package provides three primary console scripts:

- `rpek-task`: Scaffolds a new governed task definition (`task.json`) and optionally builds the prompt.
- `rpek-build`: Compiles the task and adapter into a final Markdown prompt payload.
- `rpek-admit`: Runs the canonical ingress controller admission directly.

## Where to Go Next

- **[Usage Guide](docs/USAGE.md)**: Detailed instructions on CLI usage, execution modes (NORMAL/STRICT), and manual prompt building.
- **[Execution Artefact Lifecycle](docs/EXECUTION_ARTEFACT_LIFECYCLE.md)**: Official retention, storage, and disposal policies regarding generated artifacts like audit logs and compiled prompts.
