# Deployment

## Local OpenEnv Validation

```bash
bash scripts/bootstrap_openenv.sh
bash scripts/bootstrap_openenv.sh --runtime-check
```

The first command validates local OpenEnv packaging. The runtime check starts the FastAPI environment service and validates `GET /openapi.json`, `GET /health`, `GET /metadata`, `GET /schema`, `POST /mcp`, and the `/reset`/`/step`/`/state` HTTP contract.

## Hugging Face CLI

Use the repository virtual environment CLI:

```bash
./.venv/bin/hf version
./.venv/bin/hf auth login
./.venv/bin/hf auth whoami
```

The global `hf` command on this workstation currently fails because its installed `huggingface_hub` and Typer versions are incompatible. Do not use it for final deployment.

## Hugging Face Space Deployment

```bash
export HF_SPACE_REPO_ID="Vishwa-docs/polyguard-openenv"
bash scripts/deploy_space.sh --repo-id "$HF_SPACE_REPO_ID"
./.venv/bin/hf spaces info "$HF_SPACE_REPO_ID"
openenv validate --url "https://Vishwa-docs-polyguard-openenv.hf.space"
```

Useful deploy flags:

- `--dry-run`: print commands only.
- `--skip-build`: skip `openenv build`.
- `--skip-validate`: skip local validation.
- `--private`: deploy as a private Space.
- `--create-pr`: push deployment changes as a pull request when supported by the OpenEnv CLI.

Default deploy configuration is in [`configs/deployment.yaml`](/Users/daver/Desktop/Meta_Pytorch_OpenEnv_Scaler/polyguard-rl/configs/deployment.yaml).

## Required Submission Evidence

After deployment, replace `docs/results/hf_space_verification.json` with a successful payload that includes:

- `passed: true`
- HF Space repo id
- HF Space URL
- `hf spaces info` output or summary
- `openenv validate --url ...` result

Strict acceptance mode will continue to fail until this file reports `passed: true`.

## Hugging Face Training Space

Use this path when local Ollama/GPU training is unavailable. It creates a private Docker Space under the authenticated account, starts the Gradio training runner, and uploads outputs/checkpoints to a private artifact repo.

```bash
export HF_TOKEN="<write-token>"
.venv/bin/python scripts/deploy_training_space.py \
  --repo-id TheJackBright/polyguard-openenv-training \
  --artifact-repo-id TheJackBright/polyguard-openenv-training-artifacts \
  --hardware t4-small \
  --model-id Qwen/Qwen2.5-0.5B-Instruct
```

The Space executes the notebook-equivalent training loop from `notebooks/09_training_loop.ipynb`, including SFT, GRPO, adapter merge, post-save inference, ablations, and comparison reports. After the Space uploads artifacts, pull them locally and stop paid GPU usage:

```bash
.venv/bin/python scripts/pull_training_artifacts.py \
  --artifact-repo-id TheJackBright/polyguard-openenv-training-artifacts
.venv/bin/python scripts/pause_training_space.py \
  --repo-id TheJackBright/polyguard-openenv-training \
  --mode cpu-basic
```

## Local Services

```bash
bash scripts/run_all_local.sh --quick --skip-train
```

This builds local data/model assets, skips TRL training, starts the environment/API/UI services, and runs smoke checks. Local inference defaults to the HF Transformers path; set `POLYGUARD_ENABLE_OLLAMA=true` only when a local Ollama runtime is intentionally available.