feat: harden local runtime and verification

installer/scripts/launch-local.sh

@@ -0,0 +1,17 @@
+#!/usr/bin/env bash
+set -euo pipefail
+set +x
+
+cd "$(dirname "${BASH_SOURCE[0]}")/../.."
+
+if [[ -z "${OBLITERATUS_SECRET_COMMAND:-}" ]] && \
+   [[ -x /home/roctinam/.local/bin/obliteratus-secret-broker ]]; then
+  export OBLITERATUS_SECRET_COMMAND=/home/roctinam/.local/bin/obliteratus-secret-broker
+fi
+
+# Avoid dynamic mixing between PyTorch's bundled cuDNN and a host cuDNN
+# installation. Causal convolutions and attention use other CUDA kernels.
+export OBLITERATUS_DISABLE_CUDNN="${OBLITERATUS_DISABLE_CUDNN:-1}"
+
+exec .venv/bin/python app.py --host "${OBLITERATUS_HOST:-127.0.0.1}" \
+  --port "${OBLITERATUS_PORT:-7860}"

installer/scripts/setup.sh

@@ -0,0 +1,38 @@
+#!/usr/bin/env bash
+set -euo pipefail
+set +x
+
+cd "$(dirname "${BASH_SOURCE[0]}")/../.."
+
+uv sync --locked --extra spaces --extra dev --no-editable
+
+enable_cuda="${ENABLE_CUDA:-auto}"
+if [[ "$enable_cuda" != "false" ]] && command -v nvidia-smi >/dev/null 2>&1; then
+  torch_version="$(.venv/bin/python -c 'import torch; print(torch.__version__.split("+", 1)[0])')"
+  UV_TORCH_BACKEND=cu130 uv pip install \
+    --python .venv/bin/python \
+    --reinstall-package torch \
+    "torch==$torch_version"
+fi
+
+uv pip check --python .venv/bin/python
+.venv/bin/python - <<'PY'
+import shutil
+import torch
+
+if torch.cuda.is_available():
+    probe = torch.arange(16, device="cuda", dtype=torch.float32).square().sum()
+    assert probe.device.type == "cuda"
+    torch.backends.cudnn.enabled = False
+    torch.backends.cuda.enable_cudnn_sdp(False)
+    conv_input = torch.randn(1, 8, 32, device="cuda", dtype=torch.float16)
+    conv_weight = torch.randn(8, 8, 3, device="cuda", dtype=torch.float16)
+    convolution = torch.nn.functional.conv1d(conv_input, conv_weight)
+    q = torch.randn(1, 2, 32, 16, device="cuda", dtype=torch.float16)
+    attention = torch.nn.functional.scaled_dot_product_attention(q, q, q, is_causal=True)
+    torch.cuda.synchronize()
+    assert convolution.device.type == "cuda" and torch.isfinite(convolution).all()
+    assert attention.device.type == "cuda" and torch.isfinite(attention).all()
+elif shutil.which("nvidia-smi"):
+    raise SystemExit("NVIDIA hardware detected but the installed PyTorch runtime cannot use CUDA")
+PY

installer/scripts/verify.sh

@@ -0,0 +1,37 @@
+#!/usr/bin/env bash
+set -euo pipefail
+set +x
+
+cd "$(dirname "${BASH_SOURCE[0]}")/../.."
+
+.venv/bin/python - <<'PY'
+import os
+import shutil
+import torch
+
+from obliteratus.credential_sources import secret_available
+
+assert torch.ones(1).add(1).item() == 2
+if shutil.which("nvidia-smi"):
+    assert torch.cuda.is_available(), "NVIDIA GPU detected but CUDA is unavailable"
+    assert torch.ones(1, device="cuda").device.type == "cuda"
+    torch.backends.cudnn.enabled = False
+    torch.backends.cuda.enable_cudnn_sdp(False)
+    conv_input = torch.randn(1, 8, 32, device="cuda", dtype=torch.float16)
+    conv_weight = torch.randn(8, 8, 3, device="cuda", dtype=torch.float16)
+    convolution = torch.nn.functional.conv1d(conv_input, conv_weight)
+    q = torch.randn(1, 2, 32, 16, device="cuda", dtype=torch.float16)
+    attention = torch.nn.functional.scaled_dot_product_attention(q, q, q, is_causal=True)
+    torch.cuda.synchronize()
+    assert convolution.device.type == "cuda" and torch.isfinite(convolution).all()
+    assert attention.device.type == "cuda" and torch.isfinite(attention).all()
+
+broker = os.environ.get("OBLITERATUS_SECRET_COMMAND")
+if broker:
+    assert os.path.isabs(broker)
+    assert secret_available("HF_TOKEN")
+    assert secret_available("OPENROUTER_API_KEY")
+PY
+
+.venv/bin/pytest -q --no-cov tests/test_device_boundaries.py tests/test_secrets.py \
+  tests/test_abliterate.py::TestCoherenceScoring

installer/setup.dev.manifest.yaml

@@ -0,0 +1,81 @@
+apiVersion: setup.aiwg.io/v1
+kind: SetupManifest
+metadata:
+  name: obliteratus-dev
+  version: 1.0.0
+  description: Provider-orchestrated Linux setup with optional NVIDIA CUDA and scoped OpenBao runtime credentials.
+  install_type: developer
+  execution_mode: provider-orchestrated
+spec:
+  platforms:
+    - os: linux
+      arch: [x86_64, arm64]
+      shell: bash
+  params:
+    - name: ENABLE_CUDA
+      type: choice
+      choices: [auto, "true", "false"]
+      default: auto
+      description: Install the matching CUDA PyTorch wheel when NVIDIA hardware is available.
+    - name: ENABLE_OPENBAO
+      type: choice
+      choices: [auto, "true", "false"]
+      default: auto
+      description: Configure the scoped OBLITERATUS AppRole through the sibling itops repository.
+    - name: OPENBAO_ITOPS_ROOT
+      type: path
+      default: "${HOME}/dev/itops"
+      description: Trusted itops checkout containing OpenBao policy and token helpers.
+  prerequisites:
+    - name: python
+      detect: "python3 --version | awk '{print $2}'"
+      version_min: "3.10"
+      install_hint: Install Python 3.10 or newer.
+    - name: uv
+      detect: "uv --version | awk '{print $2}'"
+      install_hint: Install uv from https://docs.astral.sh/uv/.
+    - name: git
+      detect: "git --version | awk '{print $3}'"
+      version_min: "2.30"
+      install_hint: Install Git from https://git-scm.com/.
+    - name: disk-space
+      detect: "df --output=avail -BG . | tail -1 | tr -d ' G'"
+      version_min: "12"
+      install_hint: At least 12 GB free space is required for dependencies and a test model.
+    - name: ram
+      detect: "awk '/MemTotal/ {printf \"%.0f\", $2/1024/1024}' /proc/meminfo"
+      version_min: "8"
+      install_hint: At least 8 GB RAM is required; 16 GB or more is recommended.
+  steps:
+    - id: install-runtime
+      type: script
+      script: scripts/setup.sh
+      verify: ".venv/bin/python -c 'import gradio, torch, transformers'"
+    - id: configure-openbao
+      type: agentic
+      depends_on: [install-runtime]
+      instruction: |
+        When ENABLE_OPENBAO is true, or auto and OPENBAO_ITOPS_ROOT is usable,
+        follow that repository's AGENTS.md and security SOP. Reuse or provision a
+        least-privilege obliteratus-local AppRole restricted to reads of
+        kv_internal/data/{huggingface/read-token,openrouter/automation-agent-key}
+        and their exact metadata leaves. Seal the AppRole bootstrap to the host
+        TPM when available. Install a mode-0700 OBLITERATUS_SECRET_COMMAND broker
+        that maps only HF_TOKEN and OPENROUTER_API_KEY. Verify intended reads and
+        an adjacent 403 denial. Never print secret values. Do not map the read-only
+        HF token to HF_PUSH_TOKEN or OBLITERATUS_HUB_TOKEN.
+    - id: verify-runtime
+      type: script
+      script: scripts/verify.sh
+      depends_on: [install-runtime, configure-openbao]
+  briefing:
+    success: OBLITERATUS developer runtime is ready.
+    next_steps:
+      - Run installer/scripts/launch-local.sh and open http://127.0.0.1:7860.
+      - Use a separate write-scoped HF_PUSH_TOKEN or OBLITERATUS_HUB_TOKEN only when testing Hub publishing.
+  recovery:
+    - id: reinstall-runtime
+      steps:
+        - id: reinstall
+          type: script
+          script: scripts/setup.sh