Compare commits
2 Commits
feat/rollb
...
feat/nix-d
| Author | SHA1 | Date | |
|---|---|---|---|
| 2c5dc3d58d | |||
| 8b004c47b9 |
@@ -5,7 +5,6 @@ This document outlines the development conventions for this NixOS-based infrastr
|
|||||||
## Build & Deployment
|
## Build & Deployment
|
||||||
|
|
||||||
- **Build/Deploy:** Use `nixos-rebuild switch --flake .#<hostname>` to build and deploy the configuration for a specific host.
|
- **Build/Deploy:** Use `nixos-rebuild switch --flake .#<hostname>` to build and deploy the configuration for a specific host.
|
||||||
- **CRITICAL — Validate before pushing:** Always `nix build --no-link '.#nixosConfigurations.<hostname>.config.system.build.toplevel'` (or `nh os build`) and confirm it succeeds before pushing any changes. Never push untested NixOS configs.
|
|
||||||
- **Development Shell:** Activate the development environment with `nix develop`.
|
- **Development Shell:** Activate the development environment with `nix develop`.
|
||||||
|
|
||||||
## Linting & Formatting
|
## Linting & Formatting
|
||||||
|
|||||||
Submodule assets/compose updated: d3f2e3b7b9...fb0f2cbe84
@@ -1,106 +0,0 @@
|
|||||||
# ollama-gfx906/Dockerfile
|
|
||||||
#
|
|
||||||
# Custom ollama image with ROCm 6.1 + gfx906 (MI50) support.
|
|
||||||
# The official ollama/rocm image ships ROCm 7.2 which dropped gfx906.
|
|
||||||
# This uses v0.23.2's native CMake build system with AMDGPU_TARGETS including gfx906.
|
|
||||||
#
|
|
||||||
# Build: docker build -t ollama/ollama:rocm-gfx906 ai/ollama
|
|
||||||
|
|
||||||
FROM rocm/dev-ubuntu-22.04:6.1.2-complete AS builder
|
|
||||||
|
|
||||||
# Build dependencies (CMake, Ninja, Go)
|
|
||||||
ARG CMAKEVERSION=3.31.2
|
|
||||||
ARG NINJAVERSION=1.12.1
|
|
||||||
ARG GOLANG_VERSION=1.22.0
|
|
||||||
|
|
||||||
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
|
|
||||||
curl git ccache build-essential pkg-config unzip \
|
|
||||||
&& rm -rf /var/lib/apt/lists/*
|
|
||||||
|
|
||||||
# Install CMake from official binaries
|
|
||||||
RUN curl -fsSL https://github.com/Kitware/CMake/releases/download/v${CMAKEVERSION}/cmake-${CMAKEVERSION}-linux-x86_64.tar.gz \
|
|
||||||
| tar xz -C /usr/local --strip-components 1
|
|
||||||
|
|
||||||
# Install Ninja
|
|
||||||
RUN curl -fsSL -o /tmp/ninja.zip \
|
|
||||||
https://github.com/ninja-build/ninja/releases/download/v${NINJAVERSION}/ninja-linux.zip \
|
|
||||||
&& unzip /tmp/ninja.zip -d /usr/local/bin && rm /tmp/ninja.zip
|
|
||||||
|
|
||||||
# Install Go
|
|
||||||
RUN curl -fsSL https://go.dev/dl/go${GOLANG_VERSION}.linux-amd64.tar.gz \
|
|
||||||
| tar xz -C /usr/local
|
|
||||||
ENV PATH=/usr/local/go/bin:$PATH
|
|
||||||
|
|
||||||
ARG OLLAMA_VERSION=v0.23.2
|
|
||||||
RUN git clone --depth 1 --branch ${OLLAMA_VERSION} https://github.com/ollama/ollama.git /build
|
|
||||||
WORKDIR /build
|
|
||||||
|
|
||||||
# ROCm paths
|
|
||||||
ENV HIP_PATH=/opt/rocm
|
|
||||||
ENV ROCM_PATH=/opt/rocm
|
|
||||||
ENV CMAKE_GENERATOR=Ninja
|
|
||||||
ENV LDFLAGS=-s
|
|
||||||
|
|
||||||
# Step 1: Build CPU backends with GCC (no ROCm preset)
|
|
||||||
# Pre-set CMAKE_HIP_COMPILER="" to prevent check_language(HIP) from
|
|
||||||
# finding a HIP compiler (it searches /opt/rocm even without PATH).
|
|
||||||
# Remove /opt/rocm from PATH to prevent find_program from finding hipcc.
|
|
||||||
RUN mkdir -p build-cpu && \
|
|
||||||
PATH=/usr/local/go/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
|
|
||||||
cmake -B build-cpu -DCMAKE_BUILD_TYPE=Release \
|
|
||||||
-DCMAKE_HIP_COMPILER="" \
|
|
||||||
-DCMAKE_INSTALL_PREFIX=/build/dist && \
|
|
||||||
cmake --build build-cpu --target ggml-cpu -- -l $(nproc) && \
|
|
||||||
cmake --install build-cpu --component CPU --strip && \
|
|
||||||
echo "=== CPU install ===" && \
|
|
||||||
(find /build/dist/lib/ollama -type f -o -type l 2>&1 | head -20 || echo "empty")
|
|
||||||
|
|
||||||
# Step 2: Build HIP backend with ROCm preset + gfx906 target only
|
|
||||||
# The ROCm 6 preset enables HIP language detection (enable_language(HIP))
|
|
||||||
# which ensures GPU kernels are properly compiled for gfx906.
|
|
||||||
# OLLAMA_RUNNER_DIR=rocm from the preset, so HIP goes to lib/ollama/rocm/
|
|
||||||
# Need CMAKE_PREFIX_PATH so find_package(hip) finds hip-config.cmake
|
|
||||||
# at /opt/rocm/lib/cmake/hip/hip-config.cmake.
|
|
||||||
RUN mkdir -p build-hip && \
|
|
||||||
cmake -B build-hip \
|
|
||||||
--preset 'ROCm 6' \
|
|
||||||
-DAMDGPU_TARGETS="gfx906:xnack-" \
|
|
||||||
-DCMAKE_BUILD_TYPE=Release \
|
|
||||||
-DCMAKE_PREFIX_PATH="/opt/rocm" && \
|
|
||||||
cmake --build build-hip --target ggml-hip -- -l $(nproc) && \
|
|
||||||
cmake --install build-hip --component HIP --strip && \
|
|
||||||
echo "=== HIP install ===" && \
|
|
||||||
find /build/dist/lib/ollama -type f -o -type l | head -20
|
|
||||||
|
|
||||||
# Step 3: Build Go binary (GCC for CGo linking)
|
|
||||||
ENV CGO_ENABLED=1
|
|
||||||
RUN go build -trimpath -ldflags="-X=github.com/ollama/ollama/version.Version=${OLLAMA_VERSION}" -o /build/dist/ollama .
|
|
||||||
|
|
||||||
# ---------- Runtime image ----------
|
|
||||||
FROM ubuntu:24.04
|
|
||||||
|
|
||||||
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
|
|
||||||
ca-certificates curl libstdc++6 libgomp1 libvulkan1 libopenblas0 \
|
|
||||||
&& rm -rf /var/lib/apt/lists/*
|
|
||||||
|
|
||||||
# Copy ROCm 6.1 runtime libraries
|
|
||||||
# These are needed at runtime by ggml-hip via LD_LIBRARY_PATH
|
|
||||||
COPY --from=builder /opt/rocm/lib/ /opt/rocm/lib/
|
|
||||||
COPY --from=builder /opt/rocm/share/ /opt/rocm/share/
|
|
||||||
|
|
||||||
# Copy ollama binary + all backends (CPU + HIP)
|
|
||||||
# CPU install: /build/dist/lib/ollama/libggml-*.so
|
|
||||||
# HIP install: /build/dist/lib/ollama/rocm/libggml-hip.so
|
|
||||||
COPY --from=builder /build/dist/ollama /usr/bin/ollama
|
|
||||||
COPY --from=builder /build/dist/lib/ollama/ /usr/lib/ollama/
|
|
||||||
|
|
||||||
RUN ldconfig
|
|
||||||
|
|
||||||
ENV LD_LIBRARY_PATH=/opt/rocm/lib:/usr/lib/ollama/rocm:/usr/lib/ollama
|
|
||||||
ENV HSA_OVERRIDE_GFX_VERSION=9.0.6
|
|
||||||
ENV HCC_AMDGPU_TARGET=gfx906
|
|
||||||
ENV HSA_ENABLE_SDMA=0
|
|
||||||
|
|
||||||
EXPOSE 11434
|
|
||||||
ENTRYPOINT ["/bin/ollama"]
|
|
||||||
CMD ["serve"]
|
|
||||||
474
docs/nix-container-install.md
Normal file
474
docs/nix-container-install.md
Normal file
@@ -0,0 +1,474 @@
|
|||||||
|
# Nix Installation for Hermes Agent Container
|
||||||
|
|
||||||
|
This guide covers several approaches for installing Nix in the Hermes Agent Docker
|
||||||
|
container to enable remote NixOS deployment via `nixos-rebuild`. It covers both
|
||||||
|
x86_64 (lazyworkhorse) and aarch64 (cyt-pi, uConsole) architectures.
|
||||||
|
|
||||||
|
## Table of Contents
|
||||||
|
|
||||||
|
1. [Why Nix in a Container?](#why-nix-in-a-container)
|
||||||
|
2. [Prerequisites](#prerequisites)
|
||||||
|
3. [Installation Methods](#installation-methods)
|
||||||
|
- [Method A: Determinate Systems Installer](#method-a-determinate-systems-installer-recommended)
|
||||||
|
- [Method B: Vanilla Nix Installer](#method-b-vanilla-nix-installer)
|
||||||
|
- [Method C: NixOS-Based Container Image](#method-c-nixos-based-container-image)
|
||||||
|
4. [Architecture-Specific Notes](#architecture-specific-notes)
|
||||||
|
- [x86_64 (lazyworkhorse)](#x86_64-lazyworkhorse)
|
||||||
|
- [aarch64 (cyt-pi, uConsole)](#aarch64-cyt-pi-uconsole)
|
||||||
|
- [Cross-Compilation](#cross-compilation)
|
||||||
|
5. [Post-Install Configuration](#post-install-configuration)
|
||||||
|
6. [Verification](#verification)
|
||||||
|
7. [Container-Specific Considerations](#container-specific-considerations)
|
||||||
|
- [Persistence](#persistence)
|
||||||
|
- [Disk Space](#disk-space)
|
||||||
|
- [Security](#security)
|
||||||
|
- [Resource Constraints](#resource-constraints)
|
||||||
|
8. [Integration with deploy.sh](#integration-with-deploysh)
|
||||||
|
9. [Troubleshooting](#troubleshooting)
|
||||||
|
10. [References](#references)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Why Nix in a Container?
|
||||||
|
|
||||||
|
The Hermes Agent container runs on an Ubuntu/Debian base. To deploy NixOS
|
||||||
|
configurations to remote hosts, we need:
|
||||||
|
|
||||||
|
- `nix` — the Nix package manager (for building configurations)
|
||||||
|
- `nixos-rebuild` — the NixOS deployment tool
|
||||||
|
- Access to the infra repo with flake configuration
|
||||||
|
|
||||||
|
Installing Nix inside the container avoids:
|
||||||
|
- Host-level Nix installation on the Docker host
|
||||||
|
- Cross-container volume mounts of /nix/store
|
||||||
|
- Dependencies on the host's Nix daemon (which may be a different version)
|
||||||
|
|
||||||
|
## Prerequisites
|
||||||
|
|
||||||
|
- Docker host running Linux (x86_64 and/or aarch64)
|
||||||
|
- Container base: Debian/Ubuntu (apt-based)
|
||||||
|
- 1-2 GB additional disk space for Nix store
|
||||||
|
- Network access to cache.nixos.org (or a local binary cache)
|
||||||
|
- Git access to the infra repository
|
||||||
|
|
||||||
|
## Installation Methods
|
||||||
|
|
||||||
|
### Method A: Determinate Systems Installer (Recommended)
|
||||||
|
|
||||||
|
The Determinate Systems installer is the recommended approach. It is non-interactive,
|
||||||
|
sets up flakes by default, and handles multi-user installation cleanly.
|
||||||
|
|
||||||
|
**Dockerfile additions:**
|
||||||
|
|
||||||
|
```dockerfile
|
||||||
|
# Install Nix (Determinate Systems installer)
|
||||||
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||||
|
curl \
|
||||||
|
xz-utils \
|
||||||
|
&& rm -rf /var/lib/apt/lists/*
|
||||||
|
|
||||||
|
# Download and run Nix installer (non-interactive)
|
||||||
|
RUN curl --proto '=https' --tlsv1.2 -sSf -L https://install.determinate.systems/nix \
|
||||||
|
-o /tmp/nix-install.sh \
|
||||||
|
&& chmod +x /tmp/nix-install.sh \
|
||||||
|
&& sh /tmp/nix-install.sh install --no-confirm \
|
||||||
|
&& rm /tmp/nix-install.sh
|
||||||
|
|
||||||
|
# Configure Nix for flakes
|
||||||
|
RUN mkdir -p /root/.config/nix \
|
||||||
|
&& echo 'experimental-features = nix-command flakes' > /root/.config/nix/nix.conf
|
||||||
|
|
||||||
|
# Add Nix to PATH for all users
|
||||||
|
ENV PATH="/nix/var/nix/profiles/default/bin:$PATH"
|
||||||
|
```
|
||||||
|
|
||||||
|
**Pros:**
|
||||||
|
- Fully non-interactive (--no-confirm)
|
||||||
|
- Enables flakes automatically
|
||||||
|
- Sets up multi-user daemon
|
||||||
|
- Auto-selects correct architecture
|
||||||
|
- Handles upgrades gracefully
|
||||||
|
|
||||||
|
**Cons:**
|
||||||
|
- Downloads ~100 MB installer
|
||||||
|
- Requires systemd in container (works with --privileged or cgroupv2)
|
||||||
|
- Daemon mode may conflict with container exit semantics
|
||||||
|
|
||||||
|
**Container runtime additions:**
|
||||||
|
|
||||||
|
For the Nix daemon to work properly inside a container, you may need:
|
||||||
|
```dockerfile
|
||||||
|
# Ensure /nix is a volume for persistence
|
||||||
|
VOLUME /nix
|
||||||
|
|
||||||
|
# Or mount tmpfs for ephemeral builds:
|
||||||
|
# docker run --tmpfs /nix:exec,size=4G ...
|
||||||
|
```
|
||||||
|
|
||||||
|
### Method B: Vanilla Nix Installer
|
||||||
|
|
||||||
|
The official single-user Nix installer is lighter but requires manual flake setup.
|
||||||
|
|
||||||
|
**Dockerfile additions:**
|
||||||
|
|
||||||
|
```dockerfile
|
||||||
|
# Install Nix (single-user, official installer)
|
||||||
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||||
|
curl \
|
||||||
|
sudo \
|
||||||
|
xz-utils \
|
||||||
|
&& rm -rf /var/lib/apt/lists/*
|
||||||
|
|
||||||
|
# Install Nix as root (single-user)
|
||||||
|
RUN curl -L https://nixos.org/nix/install -o /tmp/nix-install.sh \
|
||||||
|
&& chmod +x /tmp/nix-install.sh \
|
||||||
|
&& sh /tmp/nix-install.sh --no-daemon \
|
||||||
|
&& rm /tmp/nix-install.sh
|
||||||
|
|
||||||
|
# Enable flakes
|
||||||
|
RUN mkdir -p /root/.config/nix \
|
||||||
|
&& echo 'experimental-features = nix-command flakes' > /root/.config/nix/nix.conf
|
||||||
|
|
||||||
|
# Source Nix in shell
|
||||||
|
RUN echo '. /root/.nix-profile/etc/profile.d/nix.sh' >> /root/.bashrc
|
||||||
|
ENV PATH="/root/.nix-profile/bin:$PATH"
|
||||||
|
```
|
||||||
|
|
||||||
|
**Pros:**
|
||||||
|
- Smaller installer
|
||||||
|
- No daemon needed (single-user mode)
|
||||||
|
- Works in containers without systemd
|
||||||
|
- Simpler container lifecycle
|
||||||
|
|
||||||
|
**Cons:**
|
||||||
|
- Manual flake configuration required
|
||||||
|
- Single-user only (no multi-user isolation)
|
||||||
|
- PATH must be set manually
|
||||||
|
- No automatic garbage collection
|
||||||
|
|
||||||
|
### Method C: NixOS-Based Container Image
|
||||||
|
|
||||||
|
For maximum isolation, use an official NixOS base image for the build stage.
|
||||||
|
|
||||||
|
**Multi-stage Dockerfile:**
|
||||||
|
|
||||||
|
```dockerfile
|
||||||
|
# Build stage: NixOS builder
|
||||||
|
FROM nixos/nix:latest AS builder
|
||||||
|
|
||||||
|
COPY infra /infra
|
||||||
|
WORKDIR /infra
|
||||||
|
|
||||||
|
# Build the configuration once
|
||||||
|
RUN nix build '.#nixosConfigurations.lazyworkhorse.config.system.build.toplevel'
|
||||||
|
|
||||||
|
# Final stage: Hermes container
|
||||||
|
FROM ubuntu:22.04
|
||||||
|
|
||||||
|
# Copy the Nix closure and binary cache
|
||||||
|
COPY --from=builder /nix /nix
|
||||||
|
|
||||||
|
# ... rest of Hermes setup
|
||||||
|
```
|
||||||
|
|
||||||
|
**Pros:**
|
||||||
|
- Purely declarative build environment
|
||||||
|
- No installation at runtime
|
||||||
|
- Easy to pin Nix version
|
||||||
|
- Good for CI/CD pipelines
|
||||||
|
|
||||||
|
**Cons:**
|
||||||
|
- Requires multi-stage Docker build
|
||||||
|
- Larger initial image build
|
||||||
|
- Harder to update Nix version at runtime
|
||||||
|
- Overkill if Nix is only needed for `nixos-rebuild`
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Architecture-Specific Notes
|
||||||
|
|
||||||
|
### x86_64 (lazyworkhorse)
|
||||||
|
|
||||||
|
The Hermes container likely runs on x86_64 hardware for the primary server.
|
||||||
|
Nix will download x86_64 binaries from cache.nixos.org by default.
|
||||||
|
|
||||||
|
**No special configuration needed** — the standard installer works out of the box.
|
||||||
|
|
||||||
|
If the container is running on an AMD Ryzen/EPYC or Intel Xeon, consider:
|
||||||
|
```bash
|
||||||
|
# Enable CPU-specific optimizations (optional)
|
||||||
|
echo 'extra-platforms = x86_64-v1 x86_64-v2 x86_64-v3' >> /root/.config/nix/nix.conf
|
||||||
|
```
|
||||||
|
|
||||||
|
### aarch64 (cyt-pi, uConsole)
|
||||||
|
|
||||||
|
When building for aarch64 targets from an x86_64 container, you need either:
|
||||||
|
1. Remote builder (aarch64 machine does the build), or
|
||||||
|
2. QEMU-based emulation (slower but self-contained), or
|
||||||
|
3. Build directly on the aarch64 target using `--build-host`
|
||||||
|
|
||||||
|
**For QEMU emulation in the container:**
|
||||||
|
|
||||||
|
```dockerfile
|
||||||
|
# Enable binfmt for aarch64 emulation
|
||||||
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||||
|
qemu-user-static \
|
||||||
|
binfmt-support \
|
||||||
|
&& rm -rf /var/lib/apt/lists/*
|
||||||
|
|
||||||
|
# Register aarch64 binfmt
|
||||||
|
RUN update-binfmts --enable qemu-aarch64
|
||||||
|
```
|
||||||
|
|
||||||
|
**Container runtime (for QEMU):**
|
||||||
|
```bash
|
||||||
|
docker run --privileged --rm ... hermes-agent
|
||||||
|
# Or with specific capability:
|
||||||
|
docker run --cap-add=SYS_ADMIN --security-opt seccomp=unconfined ... hermes-agent
|
||||||
|
```
|
||||||
|
|
||||||
|
### Cross-Compilation
|
||||||
|
|
||||||
|
For native cross-compilation (without emulation), add to your Nix configuration:
|
||||||
|
|
||||||
|
```nix
|
||||||
|
# In your flake.nix or nix.conf
|
||||||
|
{
|
||||||
|
nix.settings.extra-platforms = [ "aarch64-linux" "x86_64-linux" ];
|
||||||
|
nix.settings.extra-sandbox-paths = [ ];
|
||||||
|
boot.binfmt.emulatedSystems = [ "aarch64-linux" ];
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
Or in `nix.conf`:
|
||||||
|
```
|
||||||
|
extra-platforms = x86_64-linux aarch64-linux
|
||||||
|
extra-sandbox-paths =
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Post-Install Configuration
|
||||||
|
|
||||||
|
### nix.conf for Container Usage
|
||||||
|
|
||||||
|
Recommended `/root/.config/nix/nix.conf`:
|
||||||
|
|
||||||
|
```ini
|
||||||
|
experimental-features = nix-command flakes
|
||||||
|
substituters = https://cache.nixos.org/
|
||||||
|
trusted-users = root
|
||||||
|
max-jobs = auto
|
||||||
|
cores = 0
|
||||||
|
sandbox = false
|
||||||
|
```
|
||||||
|
|
||||||
|
Note: `sandbox = false` is needed inside containers that lack full sandbox
|
||||||
|
support. This is safe in a single-tenant container environment.
|
||||||
|
|
||||||
|
### PATH Setup
|
||||||
|
|
||||||
|
Add to your Dockerfile:
|
||||||
|
```dockerfile
|
||||||
|
ENV PATH="/nix/var/nix/profiles/default/bin:/root/.nix-profile/bin:${PATH}"
|
||||||
|
```
|
||||||
|
|
||||||
|
### Shell Integration
|
||||||
|
|
||||||
|
```dockerfile
|
||||||
|
RUN echo 'source /root/.nix-profile/etc/profile.d/nix.sh' >> /root/.bashrc
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Verification
|
||||||
|
|
||||||
|
After installation, verify with:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Check Nix is available
|
||||||
|
nix --version
|
||||||
|
|
||||||
|
# Check nixos-rebuild
|
||||||
|
nixos-rebuild --help | head -3
|
||||||
|
|
||||||
|
# Verify flakes are enabled
|
||||||
|
nix flake --help
|
||||||
|
|
||||||
|
# Test a build (must be in infra repo)
|
||||||
|
cd /opt/data/infra
|
||||||
|
nix build --no-link '.#nixosConfigurations.lazyworkhorse.config.system.build.toplevel'
|
||||||
|
|
||||||
|
# Check available systems
|
||||||
|
nix eval --impure --expr 'builtins.currentSystem'
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Container-Specific Considerations
|
||||||
|
|
||||||
|
### Persistence
|
||||||
|
|
||||||
|
The `/nix` directory should be a Docker volume to avoid re-downloading
|
||||||
|
packages on every container restart:
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
# docker-compose.yml
|
||||||
|
volumes:
|
||||||
|
- nix-store:/nix
|
||||||
|
|
||||||
|
volumes:
|
||||||
|
nix-store:
|
||||||
|
```
|
||||||
|
|
||||||
|
Without persistence, every container restart requires re-downloading the
|
||||||
|
entire Nix store (~500 MB - 2 GB depending on packages used).
|
||||||
|
|
||||||
|
### Disk Space
|
||||||
|
|
||||||
|
The Nix store grows over time as old generations accumulate. Set up garbage
|
||||||
|
collection:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Manual GC
|
||||||
|
nix store gc
|
||||||
|
|
||||||
|
# Remove old generations
|
||||||
|
nix-collect-garbage --delete-older-than 30d
|
||||||
|
|
||||||
|
# Automatic GC (in nix.conf)
|
||||||
|
# Currently not supported in nix.conf, but you can run a cron job:
|
||||||
|
# nix store gc --max 10G
|
||||||
|
```
|
||||||
|
|
||||||
|
In Docker, limit store growth with:
|
||||||
|
```dockerfile
|
||||||
|
# Configure max store size
|
||||||
|
RUN mkdir -p /etc/nix && \
|
||||||
|
echo 'min-free = 5368709120' > /etc/nix/nix.conf # Keep 5GB free
|
||||||
|
```
|
||||||
|
|
||||||
|
### Security
|
||||||
|
|
||||||
|
Running Nix in a container introduces some security considerations:
|
||||||
|
|
||||||
|
1. **Sandboxing:** `sandbox = false` disables build isolation. In a multi-tenant
|
||||||
|
container, this means Nix builds can affect the container filesystem.
|
||||||
|
**Mitigation:** Only build configs you trust (your own infra repo).
|
||||||
|
|
||||||
|
2. **Network access:** The container needs outbound access to cache.nixos.org.
|
||||||
|
If using a restricted network, set up a local binary cache:
|
||||||
|
```nix
|
||||||
|
substituters = https://cache.nixos.org/ https://nix-cache.internal/
|
||||||
|
```
|
||||||
|
|
||||||
|
3. **Privileged mode:** QEMU emulation for aarch64 builds may need `--privileged`
|
||||||
|
or `--security-opt seccomp=unconfined`. This reduces container isolation.
|
||||||
|
**Mitigation:** Use remote builders or build natively on the target.
|
||||||
|
|
||||||
|
4. **Supply chain:** Nix derivations pin exact inputs via hashes. Verify
|
||||||
|
flake.lock is committed and reviewed.
|
||||||
|
|
||||||
|
### Resource Constraints
|
||||||
|
|
||||||
|
Nix builds can be memory and CPU intensive:
|
||||||
|
|
||||||
|
```nix
|
||||||
|
# Limit build parallelism in nix.conf
|
||||||
|
max-jobs = 2
|
||||||
|
cores = 4
|
||||||
|
|
||||||
|
# Or set per-build:
|
||||||
|
# nix build --max-jobs 2 --cores 4
|
||||||
|
```
|
||||||
|
|
||||||
|
For containers with limited memory (< 2 GB), consider:
|
||||||
|
- Building on the target host instead (`--build-host`)
|
||||||
|
- Using the deploy script's `build` action separately
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Integration with deploy.sh
|
||||||
|
|
||||||
|
The deployment script at `scripts/deploy.sh` expects:
|
||||||
|
|
||||||
|
1. **Nix installed** with flakes enabled
|
||||||
|
2. **SSH key** at `/opt/data/home/.ssh/id_hermes_gitea` (or via SSH_KEY env)
|
||||||
|
3. **Infra repo** cloned at the script's parent directory
|
||||||
|
4. **Network access** to:
|
||||||
|
- `code.lazyworkhorse.net:2222` (Gitea for git operations)
|
||||||
|
- Target hosts via SSH (see deploy-ssh-config)
|
||||||
|
- `cache.nixos.org` or a local substitute
|
||||||
|
|
||||||
|
Typical usage from Hermes:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Full deployment
|
||||||
|
./scripts/deploy.sh lazyworkhorse master switch
|
||||||
|
|
||||||
|
# Build-only check (no remote deployment)
|
||||||
|
./scripts/deploy.sh cyt-pi master build
|
||||||
|
|
||||||
|
# Dry run
|
||||||
|
./scripts/deploy.sh uConsole feat/test dry-activate
|
||||||
|
|
||||||
|
# Override SSH key
|
||||||
|
SSH_KEY=/opt/data/home/.ssh/my-custom-key ./deploy.sh lazyworkhorse
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Troubleshooting
|
||||||
|
|
||||||
|
### "nix: command not found"
|
||||||
|
|
||||||
|
- Ensure Nix is installed and PATH is set:
|
||||||
|
```bash
|
||||||
|
export PATH="/nix/var/nix/profiles/default/bin:/root/.nix-profile/bin:$PATH"
|
||||||
|
```
|
||||||
|
- Check installation: `ls -la /nix/` should exist
|
||||||
|
- Re-source profile: `. /root/.nix-profile/etc/profile.d/nix.sh`
|
||||||
|
|
||||||
|
### "error: unable to download ... cache.nixos.org"
|
||||||
|
|
||||||
|
- Check network connectivity: `ping cache.nixos.org`
|
||||||
|
- Check DNS resolution from inside the container
|
||||||
|
- If behind a proxy, set `http_proxy` / `https_proxy` environment variables
|
||||||
|
|
||||||
|
### "sandbox: cannot run build in sandbox"
|
||||||
|
|
||||||
|
- Add `sandbox = false` to nix.conf
|
||||||
|
- Or run container with `--privileged` or `--security-opt seccomp=unconfined`
|
||||||
|
|
||||||
|
### "aarch64-linux builds fail on x86_64"
|
||||||
|
|
||||||
|
- QEMU binfmt not registered. Check: `ls /proc/sys/fs/binfmt_misc/`
|
||||||
|
- Rebuild QEMU registration: `docker run --privileged --rm tonistiigi/binfmt --install all`
|
||||||
|
- Or use `--build-host` to build on the target directly
|
||||||
|
|
||||||
|
### "nixos-rebuild fails with SSH errors"
|
||||||
|
|
||||||
|
- Verify SSH key exists and has correct permissions:
|
||||||
|
```bash
|
||||||
|
ls -la /opt/data/home/.ssh/id_hermes_gitea
|
||||||
|
chmod 600 /opt/data/home/.ssh/id_hermes_gitea
|
||||||
|
```
|
||||||
|
- Test SSH manually: `ssh -p 2424 -i /opt/data/home/.ssh/id_hermes_gitea ai-worker@lazyworkhorse.net`
|
||||||
|
- Check target host is reachable: `nc -zv lazyworkhorse.net 2424`
|
||||||
|
|
||||||
|
### "git fetch fails from Gitea"
|
||||||
|
|
||||||
|
- Verify GIT_SSH_COMMAND is set: `echo $GIT_SSH_COMMAND`
|
||||||
|
- Test git SSH: `ssh -T git@code.lazyworkhorse.net -p 2222`
|
||||||
|
- Check the infra repo remote: `git remote -v`
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## References
|
||||||
|
|
||||||
|
- [Determinate Systems Nix Installer](https://github.com/DeterminateSystems/nix-installer)
|
||||||
|
- [NixOS Manual: Installation](https://nixos.org/manual/nix/stable/installation/)
|
||||||
|
- [NixOS Wiki: Flakes](https://nixos.wiki/wiki/Flakes)
|
||||||
|
- [NixOS Wiki: nixos-rebuild](https://nixos.wiki/wiki/Nixos-rebuild)
|
||||||
|
- [NixOS Wiki: Cross Compilation](https://nixos.wiki/wiki/Cross_Compilation)
|
||||||
|
- [Multi-arch Docker with QEMU](https://github.com/multiarch/qemu-user-static)
|
||||||
@@ -61,8 +61,6 @@
|
|||||||
./modules/nixos/services/open_code_server.nix
|
./modules/nixos/services/open_code_server.nix
|
||||||
./modules/nixos/services/ollama_init_custom_models.nix
|
./modules/nixos/services/ollama_init_custom_models.nix
|
||||||
./modules/nixos/services/openclaw_node.nix
|
./modules/nixos/services/openclaw_node.nix
|
||||||
./modules/nixos/services/rollback-sentinel.nix
|
|
||||||
./modules/nixos/security/ai-worker-restricted.nix
|
|
||||||
./users/gortium.nix
|
./users/gortium.nix
|
||||||
./users/ai-worker.nix
|
./users/ai-worker.nix
|
||||||
];
|
];
|
||||||
|
|||||||
@@ -36,7 +36,7 @@
|
|||||||
"transparent_hugepage=always" # because mucho ram
|
"transparent_hugepage=always" # because mucho ram
|
||||||
];
|
];
|
||||||
# 2. Load the specific drivers found by sensors-detect
|
# 2. Load the specific drivers found by sensors-detect
|
||||||
boot.kernelModules = [ "nct6775" "lm96163" "iptable_nat" "iptable_filter" ];
|
boot.kernelModules = [ "nct6775" "lm96163" ];
|
||||||
# 3. Force the nct6775 driver to recognize the chip if it's stubborn
|
# 3. Force the nct6775 driver to recognize the chip if it's stubborn
|
||||||
boot.extraModprobeConfig = ''
|
boot.extraModprobeConfig = ''
|
||||||
options nct6775 force_id=0xd280
|
options nct6775 force_id=0xd280
|
||||||
@@ -49,26 +49,6 @@
|
|||||||
networking.networkmanager.enable = true; # Easiest to use and most distros use this by default.
|
networking.networkmanager.enable = true; # Easiest to use and most distros use this by default.
|
||||||
networking.hostId = "deadbeef";
|
networking.hostId = "deadbeef";
|
||||||
|
|
||||||
# WireGuard VPN client -- always up, connects to wg-easy server
|
|
||||||
# Create age-encrypted secrets before deploying (run on the host):
|
|
||||||
# echo -n "<private_key>" | agenix -e secrets/wireguard_private_key.age
|
|
||||||
# echo -n "<preshared_key>" | agenix -e secrets/wireguard_preshared_key.age
|
|
||||||
networking.wireguard.interfaces = {
|
|
||||||
wg0 = {
|
|
||||||
ips = [ "10.8.0.3/24" ];
|
|
||||||
privateKeyFile = config.age.secrets.wireguard_private_key.path;
|
|
||||||
peers = [
|
|
||||||
{
|
|
||||||
publicKey = "rY9zII3AOm8rog2rv02PyA3Bq7zdvTOGkZapfCV1DkE=";
|
|
||||||
presharedKeyFile = config.age.secrets.wireguard_preshared_key.path;
|
|
||||||
allowedIPs = [ "10.8.0.0/24" ];
|
|
||||||
endpoint = "vpn.lazyworkhorse.net:51820";
|
|
||||||
persistentKeepalive = 25;
|
|
||||||
}
|
|
||||||
];
|
|
||||||
};
|
|
||||||
};
|
|
||||||
|
|
||||||
# Set your time zone.
|
# Set your time zone.
|
||||||
time.timeZone = "America/Montreal";
|
time.timeZone = "America/Montreal";
|
||||||
|
|
||||||
@@ -178,7 +158,7 @@
|
|||||||
settings = {
|
settings = {
|
||||||
PasswordAuthentication = false;
|
PasswordAuthentication = false;
|
||||||
KbdInteractiveAuthentication = false;
|
KbdInteractiveAuthentication = false;
|
||||||
# Additional hardening settings below in SERVER HARDENING section
|
PermitRootLogin = "prohibit-password";
|
||||||
};
|
};
|
||||||
hostKeys = [
|
hostKeys = [
|
||||||
{
|
{
|
||||||
@@ -207,7 +187,6 @@
|
|||||||
ai = {
|
ai = {
|
||||||
path = self + "/assets/compose/ai";
|
path = self + "/assets/compose/ai";
|
||||||
envFile = config.age.secrets.containers_env.path;
|
envFile = config.age.secrets.containers_env.path;
|
||||||
ports = [ 22000 ]; # Syncthing TCP sync
|
|
||||||
};
|
};
|
||||||
|
|
||||||
cloudstorage = {
|
cloudstorage = {
|
||||||
@@ -242,11 +221,6 @@
|
|||||||
path = self + "/assets/compose/homepage";
|
path = self + "/assets/compose/homepage";
|
||||||
};
|
};
|
||||||
|
|
||||||
vpn = {
|
|
||||||
path = self + "/assets/compose/vpn";
|
|
||||||
envFile = config.age.secrets.containers_env.path;
|
|
||||||
};
|
|
||||||
|
|
||||||
# tak = {
|
# tak = {
|
||||||
# path = self + "/assets/compose/tak";
|
# path = self + "/assets/compose/tak";
|
||||||
# };
|
# };
|
||||||
@@ -290,20 +264,6 @@
|
|||||||
mode = "0440";
|
mode = "0440";
|
||||||
path = "/run/secrets/openclaw_gateway_token";
|
path = "/run/secrets/openclaw_gateway_token";
|
||||||
};
|
};
|
||||||
wireguard_private_key = {
|
|
||||||
file = ../../secrets/wireguard_private_key.age;
|
|
||||||
owner = "root";
|
|
||||||
group = "root";
|
|
||||||
mode = "0400";
|
|
||||||
path = "/run/secrets/wireguard_private_key";
|
|
||||||
};
|
|
||||||
wireguard_preshared_key = {
|
|
||||||
file = ../../secrets/wireguard_preshared_key.age;
|
|
||||||
owner = "root";
|
|
||||||
group = "root";
|
|
||||||
mode = "0400";
|
|
||||||
path = "/run/secrets/wireguard_preshared_key";
|
|
||||||
};
|
|
||||||
};
|
};
|
||||||
};
|
};
|
||||||
|
|
||||||
@@ -321,41 +281,11 @@
|
|||||||
environment.etc."ssh/ssh_host_ed25519_key.pub".text =
|
environment.etc."ssh/ssh_host_ed25519_key.pub".text =
|
||||||
"${keys.hosts.lazyworkhorse.main}";
|
"${keys.hosts.lazyworkhorse.main}";
|
||||||
|
|
||||||
# ── Boot sentinel: auto-rollback on critical service failure ───────────────
|
|
||||||
services.rollbackSentinel.enable = true;
|
|
||||||
# Tier-1: failure triggers rollback
|
|
||||||
services.rollbackSentinel.tier1Services = [
|
|
||||||
"sshd" "docker" "traefik" "authelia"
|
|
||||||
];
|
|
||||||
# Tier-2: warn only
|
|
||||||
services.rollbackSentinel.tier2Services = [
|
|
||||||
"gitea" "hermes" "ollama" "synapse" "nextcloud"
|
|
||||||
"vaultwarden" "wireguard" "homeassistant" "fail2ban"
|
|
||||||
];
|
|
||||||
# Wait 2 minutes after boot before checking (lets services initialize)
|
|
||||||
services.rollbackSentinel.bootDelay = "120";
|
|
||||||
# Change boot default only (not --rollback-now) for safety
|
|
||||||
services.rollbackSentinel.rollbackMode = "set-default";
|
|
||||||
|
|
||||||
services.fstrim.enable = true;
|
services.fstrim.enable = true;
|
||||||
|
|
||||||
services.zfs.autoSnapshot.enable = true;
|
services.zfs.autoSnapshot.enable = true;
|
||||||
services.zfs.autoScrub.enable = true;
|
services.zfs.autoScrub.enable = true;
|
||||||
|
|
||||||
# Ensure com.sun:auto-snapshot is set on ZFS datasets so auto-snapshots actually run
|
|
||||||
systemd.services."zfs-set-auto-snapshot" = {
|
|
||||||
description = "Set com.sun:auto-snapshot=true on ZFS datasets";
|
|
||||||
after = [ "zfs-import.target" ];
|
|
||||||
wants = [ "zfs-import.target" ];
|
|
||||||
wantedBy = [ "multi-user.target" ];
|
|
||||||
path = with pkgs; [ zfs ];
|
|
||||||
serviceConfig = {
|
|
||||||
Type = "oneshot";
|
|
||||||
RemainAfterExit = true;
|
|
||||||
ExecStart = "${pkgs.zfs}/bin/zfs set -r com.sun:auto-snapshot=true rpool";
|
|
||||||
};
|
|
||||||
};
|
|
||||||
|
|
||||||
# Mi50 config
|
# Mi50 config
|
||||||
hardware.graphics = {
|
hardware.graphics = {
|
||||||
enable = true;
|
enable = true;
|
||||||
@@ -378,203 +308,6 @@
|
|||||||
# Or disable the firewall altogether.
|
# Or disable the firewall altogether.
|
||||||
# networking.firewall.enable = false;
|
# networking.firewall.enable = false;
|
||||||
|
|
||||||
# =============================================================================
|
|
||||||
# SERVER HARDENING - Firewall, Fail2ban, SSH, Kernel
|
|
||||||
# =============================================================================
|
|
||||||
|
|
||||||
# Firewall - default deny, explicit allow
|
|
||||||
networking.firewall = {
|
|
||||||
# Enable firewall with default deny policy (NixOS firewall denies all by default)
|
|
||||||
enable = true;
|
|
||||||
allowPing = true;
|
|
||||||
|
|
||||||
# Only essential ports exposed to internet
|
|
||||||
allowedTCPPorts = [
|
|
||||||
2424 # SSH (non-standard port)
|
|
||||||
2222 # Gitea (version control)
|
|
||||||
80 # HTTP (Traefik redirect)
|
|
||||||
443 # HTTPS (Traefik)
|
|
||||||
# 8000 # Portainer - REVIEW: internal only?
|
|
||||||
# 4242 # Coms - REVIEW: internal only?
|
|
||||||
# 5000 # TAK API - REVIEW: internal only?
|
|
||||||
# 8087 # TAK Connect - REVIEW: internal only?
|
|
||||||
# 8089 # TAK Management - REVIEW: internal only?
|
|
||||||
];
|
|
||||||
|
|
||||||
allowedUDPPorts = [
|
|
||||||
51820 # WireGuard VPN
|
|
||||||
];
|
|
||||||
|
|
||||||
# Rate limiting and attack prevention
|
|
||||||
extraCommands = ''
|
|
||||||
# 1. Wipe the INPUT chain clean at the start of every activation
|
|
||||||
iptables -F INPUT
|
|
||||||
|
|
||||||
# Rate limit SSH connections (max 20 new connections per 60 seconds)
|
|
||||||
iptables -A INPUT -p tcp --dport 2424 -m state --state NEW -m recent --set
|
|
||||||
iptables -A INPUT -p tcp --dport 2424 -m state --state NEW -m recent --update --seconds 60 --hitcount 20 -j DROP
|
|
||||||
|
|
||||||
# Rate limit HTTP/HTTPS (protects Traefik)
|
|
||||||
iptables -A INPUT -p tcp --dport 80 -m state --state NEW -m limit --limit 25/minute --limit-burst 100 -j ACCEPT
|
|
||||||
iptables -A INPUT -p tcp --dport 443 -m state --state NEW -m limit --limit 25/minute --limit-burst 100 -j ACCEPT
|
|
||||||
|
|
||||||
# Drop invalid packets
|
|
||||||
iptables -A INPUT -m state --state INVALID -j DROP
|
|
||||||
|
|
||||||
# Log dropped packets (rate limited)
|
|
||||||
iptables -A INPUT -m limit --limit 5/min -j LOG --log-prefix "IPTables-Dropped: " --log-level 4
|
|
||||||
|
|
||||||
# 3. CRITICAL: Re-link the NixOS default firewall chain
|
|
||||||
# Without this line, the 'allowedTCPPorts' in your Nix config will be ignored!
|
|
||||||
iptables -A INPUT -j nixos-fw
|
|
||||||
'';
|
|
||||||
};
|
|
||||||
|
|
||||||
# Fail2ban - automatic IP banning
|
|
||||||
services.fail2ban = {
|
|
||||||
enable = true;
|
|
||||||
maxretry = 3;
|
|
||||||
bantime = "1h";
|
|
||||||
banaction = "iptables-multiport";
|
|
||||||
|
|
||||||
jails = {
|
|
||||||
# SSH brute force protection (uses systemd journal backend)
|
|
||||||
sshd = {
|
|
||||||
enabled = true;
|
|
||||||
settings = {
|
|
||||||
filter = "sshd";
|
|
||||||
port = "2424";
|
|
||||||
maxretry = 3;
|
|
||||||
bantime = "1h";
|
|
||||||
};
|
|
||||||
};
|
|
||||||
|
|
||||||
# Recidive - ban repeat offenders for 1 week
|
|
||||||
recidive = {
|
|
||||||
enabled = true;
|
|
||||||
settings = {
|
|
||||||
filter = "recidive";
|
|
||||||
logpath = "/var/log/fail2ban.log";
|
|
||||||
bantime = "1w";
|
|
||||||
findtime = "1d";
|
|
||||||
maxretry = 3;
|
|
||||||
};
|
|
||||||
};
|
|
||||||
|
|
||||||
# HTTP authentication failures (Traefik)
|
|
||||||
http-auth = {
|
|
||||||
enabled = true;
|
|
||||||
settings = {
|
|
||||||
filter = "traefik-auth";
|
|
||||||
port = "80,443";
|
|
||||||
logpath = "/var/log/traefik/access.log";
|
|
||||||
maxretry = 5;
|
|
||||||
bantime = "1h";
|
|
||||||
};
|
|
||||||
};
|
|
||||||
|
|
||||||
# HTTP scanning/attacks (Traefik)
|
|
||||||
http-botsearch = {
|
|
||||||
enabled = true;
|
|
||||||
settings = {
|
|
||||||
filter = "traefik-botsearch";
|
|
||||||
port = "80,443";
|
|
||||||
logpath = "/var/log/traefik/access.log";
|
|
||||||
maxretry = 2;
|
|
||||||
bantime = "2h";
|
|
||||||
};
|
|
||||||
};
|
|
||||||
};
|
|
||||||
};
|
|
||||||
|
|
||||||
# Custom fail2ban filters for Traefik
|
|
||||||
environment.etc."fail2ban/filter.d/traefik-auth.conf".text = ''
|
|
||||||
[Definition]
|
|
||||||
failregex = ^<HOST> -.*"(GET|POST|HEAD|PUT|DELETE).*" (401|403) \d+.*$
|
|
||||||
ignoreregex =
|
|
||||||
'';
|
|
||||||
|
|
||||||
environment.etc."fail2ban/filter.d/traefik-botsearch.conf".text = ''
|
|
||||||
[Definition]
|
|
||||||
failregex = ^<HOST> -.*"(GET|POST|HEAD|PUT|DELETE).*" 404 \d+.*$
|
|
||||||
^<HOST> -.*"(GET|POST|HEAD|PUT|DELETE).*/(\.|wp-|php|admin|login|xmlrpc|\.env|\.git|\.aws|\.azure).*" \d+.*$
|
|
||||||
ignoreregex =
|
|
||||||
'';
|
|
||||||
|
|
||||||
# SSH hardening
|
|
||||||
services.openssh.settings = {
|
|
||||||
PermitRootLogin = "no";
|
|
||||||
MaxAuthTries = 3;
|
|
||||||
MaxSessions = 20;
|
|
||||||
LoginGraceTime = 30;
|
|
||||||
ClientAliveInterval = 300;
|
|
||||||
ClientAliveCountMax = 2;
|
|
||||||
PermitEmptyPasswords = "no";
|
|
||||||
ChallengeResponseAuthentication = "no";
|
|
||||||
UsePAM = true;
|
|
||||||
LogLevel = "VERBOSE";
|
|
||||||
X11Forwarding = false;
|
|
||||||
AllowTcpForwarding = "no";
|
|
||||||
AllowAgentForwarding = "no";
|
|
||||||
PermitTunnel = "no";
|
|
||||||
};
|
|
||||||
|
|
||||||
# Kernel network hardening
|
|
||||||
boot.kernel.sysctl = {
|
|
||||||
# IP Spoofing protection
|
|
||||||
"net.ipv4.conf.all.rp_filter" = 1;
|
|
||||||
"net.ipv4.conf.default.rp_filter" = 1;
|
|
||||||
|
|
||||||
# Ignore ICMP broadcasts
|
|
||||||
"net.ipv4.icmp_echo_ignore_broadcasts" = 1;
|
|
||||||
|
|
||||||
# Disable source routing
|
|
||||||
"net.ipv4.conf.all.accept_source_route" = 0;
|
|
||||||
"net.ipv4.conf.default.accept_source_route" = 0;
|
|
||||||
"net.ipv6.conf.all.accept_source_route" = 0;
|
|
||||||
"net.ipv6.conf.default.accept_source_route" = 0;
|
|
||||||
|
|
||||||
# Disable redirects
|
|
||||||
"net.ipv4.conf.all.send_redirects" = 0;
|
|
||||||
"net.ipv4.conf.default.send_redirects" = 0;
|
|
||||||
|
|
||||||
# SYN flood protection
|
|
||||||
"net.ipv4.tcp_syncookies" = 1;
|
|
||||||
"net.ipv4.tcp_max_syn_backlog" = 2048;
|
|
||||||
"net.ipv4.tcp_synack_retries" = 2;
|
|
||||||
"net.ipv4.tcp_syn_retries" = 5;
|
|
||||||
|
|
||||||
# Log martian packets
|
|
||||||
"net.ipv4.conf.all.log_martians" = 1;
|
|
||||||
"net.ipv4.conf.default.log_martians" = 1;
|
|
||||||
|
|
||||||
# Ignore redirects
|
|
||||||
"net.ipv4.conf.all.accept_redirects" = 0;
|
|
||||||
"net.ipv4.conf.default.accept_redirects" = 0;
|
|
||||||
"net.ipv4.conf.all.secure_redirects" = 0;
|
|
||||||
"net.ipv4.conf.default.secure_redirects" = 0;
|
|
||||||
"net.ipv6.conf.all.accept_redirects" = 0;
|
|
||||||
"net.ipv6.conf.default.accept_redirects" = 0;
|
|
||||||
|
|
||||||
# Connection tuning
|
|
||||||
"net.core.somaxconn" = 4096;
|
|
||||||
"net.core.netdev_max_backlog" = 65536;
|
|
||||||
"net.ipv4.tcp_max_orphans" = 65536;
|
|
||||||
"net.ipv4.tcp_fin_timeout" = 15;
|
|
||||||
"net.ipv4.tcp_keepalive_time" = 300;
|
|
||||||
"net.ipv4.tcp_keepalive_probes" = 5;
|
|
||||||
"net.ipv4.tcp_keepalive_intvl" = 15;
|
|
||||||
};
|
|
||||||
|
|
||||||
# Audit logging
|
|
||||||
security.auditd.enable = true;
|
|
||||||
|
|
||||||
# Fail2ban log directory
|
|
||||||
systemd.tmpfiles.rules = [
|
|
||||||
"d /var/log/fail2ban 0755 root root -"
|
|
||||||
"d /var/log/traefik 0755 root root -"
|
|
||||||
];
|
|
||||||
|
|
||||||
# Copy the NixOS configuration file and link it from the resulting system
|
# Copy the NixOS configuration file and link it from the resulting system
|
||||||
# (/run/current-system/configuration.nix). This is useful in case you
|
# (/run/current-system/configuration.nix). This is useful in case you
|
||||||
# accidentally delete configuration.nix.
|
# accidentally delete configuration.nix.
|
||||||
|
|||||||
@@ -1,105 +0,0 @@
|
|||||||
# AI Worker Restricted Access
|
|
||||||
|
|
||||||
This module provides SSH access for the AI worker (hermes-agent) to run ollama benchmarks on the host.
|
|
||||||
|
|
||||||
## Security Model
|
|
||||||
|
|
||||||
The `ai-worker` user has:
|
|
||||||
|
|
||||||
### Filesystem Access
|
|
||||||
- **Home directory**: `/home/ai-worker` (standard user home)
|
|
||||||
- **No bind mounts**: Cannot access `/home/gortium/infra` or other host files
|
|
||||||
- **Cannot access**: Any files outside standard system paths
|
|
||||||
|
|
||||||
### Sudo Access
|
|
||||||
- **NONE**: ai-worker has no sudo privileges
|
|
||||||
- Cannot run `nh`, `nixos-rebuild`, `nixpkgs-fmt`, or `nix` with elevated permissions
|
|
||||||
|
|
||||||
### Docker Access
|
|
||||||
- Member of `docker` group - can run `docker` and `docker exec` commands
|
|
||||||
- Primary use: `docker exec ollama ollama ...` for benchmarking
|
|
||||||
- Can run `docker exec --privileged ollama rocm-smi ...` for VRAM monitoring
|
|
||||||
|
|
||||||
## Workflow: SSH + Docker Benchmarking
|
|
||||||
|
|
||||||
The AI worker connects from the Hermes container to the host via SSH, runs ollama benchmarks, then returns to save results.
|
|
||||||
|
|
||||||
### Example Workflow
|
|
||||||
|
|
||||||
```bash
|
|
||||||
# From Hermes container, SSH to host
|
|
||||||
ssh -i /path/to/ssh/key ai-worker@host.docker.internal
|
|
||||||
|
|
||||||
# On host, run ollama benchmarks via docker
|
|
||||||
docker exec ollama ollama pull devstral-small-2:24b
|
|
||||||
|
|
||||||
# Create test modelfile
|
|
||||||
docker exec ollama bash -c 'cat <<EOF > /root/.ollama/test.modelfile
|
|
||||||
FROM devstral-small-2:24b
|
|
||||||
PARAMETER num_ctx 65536
|
|
||||||
PARAMETER num_gpu 99
|
|
||||||
PARAMETER flash_attn true
|
|
||||||
EOF'
|
|
||||||
|
|
||||||
# Create and test model
|
|
||||||
docker exec ollama ollama create test-model -f /root/.ollama/test.modelfile
|
|
||||||
docker exec ollama ollama run test-model "Write a Python async function"
|
|
||||||
|
|
||||||
# Check VRAM usage
|
|
||||||
docker exec --privileged ollama rocm-smi --showmeminfo vram
|
|
||||||
|
|
||||||
# Cleanup
|
|
||||||
docker exec ollama ollama rm test-model
|
|
||||||
|
|
||||||
# Exit SSH, return to Hermes container
|
|
||||||
exit
|
|
||||||
|
|
||||||
# Save results in Hermes container
|
|
||||||
# /opt/data/ai-optimizer/state.json
|
|
||||||
# /opt/data/ai-optimizer/results.csv
|
|
||||||
```
|
|
||||||
|
|
||||||
## SSH Access
|
|
||||||
|
|
||||||
Connect as:
|
|
||||||
```bash
|
|
||||||
ssh ai-worker@lazyworkhorse
|
|
||||||
```
|
|
||||||
|
|
||||||
The working directory will be `/home/ai-worker`. No infra repo access.
|
|
||||||
|
|
||||||
## Verification
|
|
||||||
|
|
||||||
Check ai-worker permissions:
|
|
||||||
```bash
|
|
||||||
# On the host, as root or gortium:
|
|
||||||
sudo -u ai-worker sudo -l
|
|
||||||
# Should show: no sudo access
|
|
||||||
|
|
||||||
# Check docker group membership
|
|
||||||
groups ai-worker
|
|
||||||
# Should show: ai-worker docker
|
|
||||||
```
|
|
||||||
|
|
||||||
## Troubleshooting
|
|
||||||
|
|
||||||
If ai-worker cannot run docker commands:
|
|
||||||
```bash
|
|
||||||
# Check docker group membership
|
|
||||||
groups ai-worker
|
|
||||||
|
|
||||||
# Verify ollama container is running
|
|
||||||
docker ps | grep ollama
|
|
||||||
|
|
||||||
# Test docker access
|
|
||||||
sudo -u ai-worker docker exec ollama ollama list
|
|
||||||
```
|
|
||||||
|
|
||||||
If SSH connection fails:
|
|
||||||
```bash
|
|
||||||
# Check SSH key is authorized
|
|
||||||
cat /home/ai-worker/.ssh/authorized_keys
|
|
||||||
|
|
||||||
# Check SSH service
|
|
||||||
systemctl status sshd
|
|
||||||
```
|
|
||||||
@@ -1,17 +0,0 @@
|
|||||||
{ config, pkgs, lib, ... }:
|
|
||||||
|
|
||||||
with lib;
|
|
||||||
|
|
||||||
{
|
|
||||||
options.services.aiWorkerAccess = mkOption {
|
|
||||||
type = types.bool;
|
|
||||||
default = false;
|
|
||||||
description = "Enable AI worker SSH access with docker group membership for ollama benchmarking";
|
|
||||||
};
|
|
||||||
|
|
||||||
config = mkIf config.services.aiWorkerAccess {
|
|
||||||
# ai-worker is member of docker group - can run docker commands via SSH
|
|
||||||
# No bind mounts, no sudo access - docker-only for ollama benchmarking
|
|
||||||
users.groups.docker.members = [ "ai-worker" ];
|
|
||||||
};
|
|
||||||
}
|
|
||||||
@@ -1,400 +0,0 @@
|
|||||||
#!/usr/bin/env bash
|
|
||||||
# =============================================================================
|
|
||||||
# nixos-rollback.sh — NixOS systemd-boot Rollback Script
|
|
||||||
#
|
|
||||||
# Detects a failed NixOS generation (critical services not starting) and sets
|
|
||||||
# the previous generation as the default boot option for systemd-boot.
|
|
||||||
# Logs all actions to syslog/journald and a local logfile. Fails safely when
|
|
||||||
# no previous generation exists or required files are missing.
|
|
||||||
#
|
|
||||||
# Integration with the boot sentinel:
|
|
||||||
# sentinel-check.sh → detects Tier-1 service failures (sshd, docker,
|
|
||||||
# traefik, authelia) after a boot
|
|
||||||
# nixos-rollback.sh ← called when sentinel exits nonzero; sets previous
|
|
||||||
# generation as default for next boot
|
|
||||||
#
|
|
||||||
# Usage:
|
|
||||||
# nixos-rollback.sh # auto-detect & set previous gen
|
|
||||||
# nixos-rollback.sh --dry-run # show what would be done
|
|
||||||
# nixos-rollback.sh --rollback-now # also run nixos-rebuild switch
|
|
||||||
# # --rollback for immediate fix
|
|
||||||
# nixos-rollback.sh --help # full help text
|
|
||||||
#
|
|
||||||
# Exit codes:
|
|
||||||
# 0 — rollback applied (or dry-run would apply)
|
|
||||||
# 1 — preflight failure (missing files, permissions)
|
|
||||||
# 2 — no previous generation available
|
|
||||||
# 3 — nixos-rebuild --rollback failed (only with --rollback-now)
|
|
||||||
#
|
|
||||||
# Installation on NixOS:
|
|
||||||
# Place in /usr/local/bin/nixos-rollback.sh and make executable.
|
|
||||||
# Add a systemd oneshot service to run it after sentinel-check detects
|
|
||||||
# failures, or invoke directly from a sentinel timer.
|
|
||||||
# =============================================================================
|
|
||||||
|
|
||||||
set -euo pipefail
|
|
||||||
|
|
||||||
# ── Configuration ────────────────────────────────────────────────────────────
|
|
||||||
# These can be overridden via environment variables for testing.
|
|
||||||
LOADER_CONF="${NIXOS_ROLLBACK_LOADER_CONF:-/boot/loader/loader.conf}"
|
|
||||||
ENTRIES_DIR="${NIXOS_ROLLBACK_ENTRIES_DIR:-/boot/loader/entries}"
|
|
||||||
LOGFILE="${NIXOS_ROLLBACK_LOGFILE:-/var/log/nixos-rollback.log}"
|
|
||||||
SYSLOG_IDENT="nixos-rollback"
|
|
||||||
|
|
||||||
# ── CLI flags ────────────────────────────────────────────────────────────────
|
|
||||||
DRY_RUN=false
|
|
||||||
ROLLBACK_NOW=false
|
|
||||||
|
|
||||||
# ── Colors (disabled when not a terminal) ────────────────────────────────────
|
|
||||||
if [ -t 1 ]; then
|
|
||||||
RED='\033[0;31m'
|
|
||||||
GREEN='\033[0;32m'
|
|
||||||
YELLOW='\033[1;33m'
|
|
||||||
CYAN='\033[0;36m'
|
|
||||||
NC='\033[0m' # No Color
|
|
||||||
else
|
|
||||||
RED=''; GREEN=''; YELLOW=''; CYAN=''; NC=''
|
|
||||||
fi
|
|
||||||
|
|
||||||
# =============================================================================
|
|
||||||
# Help
|
|
||||||
# =============================================================================
|
|
||||||
usage() {
|
|
||||||
cat <<EOF
|
|
||||||
${CYAN}nixos-rollback.sh${NC} — Set the previous NixOS generation as systemd-boot default
|
|
||||||
|
|
||||||
${CYAN}USAGE${NC}
|
|
||||||
nixos-rollback.sh [OPTIONS]
|
|
||||||
|
|
||||||
${CYAN}OPTIONS${NC}
|
|
||||||
--dry-run Show what would be done without making changes
|
|
||||||
--rollback-now Also run 'nixos-rebuild switch --rollback' for
|
|
||||||
immediate fix of the running system (requires
|
|
||||||
nixos-rebuild on PATH)
|
|
||||||
-h, --help Show this help text
|
|
||||||
|
|
||||||
${CYAN}DESCRIPTION${NC}
|
|
||||||
Reads the current default boot entry from ${LOADER_CONF},
|
|
||||||
determines the previous generation number, and writes it as the
|
|
||||||
new default. The script only modifies systemd-boot config —
|
|
||||||
it does NOT touch the Nix store or system profile unless
|
|
||||||
--rollback-now is passed.
|
|
||||||
|
|
||||||
Designed as the rollback half of a boot sentinel:
|
|
||||||
1. System boots into generation N
|
|
||||||
2. sentinel-check.sh detects Tier-1 service failures
|
|
||||||
3. nixos-rollback.sh sets default to generation N-1
|
|
||||||
4. Next reboot uses the working generation
|
|
||||||
|
|
||||||
${CYAN}EXIT CODES${NC}
|
|
||||||
0 Rollback applied (or dry-run would apply)
|
|
||||||
1 Preflight failure (missing files, permissions)
|
|
||||||
2 No previous generation available (only one generation)
|
|
||||||
3 nixos-rebuild --rollback failed (with --rollback-now)
|
|
||||||
|
|
||||||
${CYAN}FILES${NC}
|
|
||||||
${LOADER_CONF} systemd-boot loader configuration
|
|
||||||
${ENTRIES_DIR}/ generation entry .conf files
|
|
||||||
${LOGFILE} action log (append-only)
|
|
||||||
EOF
|
|
||||||
}
|
|
||||||
|
|
||||||
# =============================================================================
|
|
||||||
# Logging
|
|
||||||
# =============================================================================
|
|
||||||
log() {
|
|
||||||
local level="$1"; shift
|
|
||||||
local msg="$*"
|
|
||||||
local timestamp
|
|
||||||
timestamp="$(date '+%Y-%m-%d %H:%M:%S')"
|
|
||||||
echo "${timestamp} [${level}] ${msg}" >> "${LOGFILE}"
|
|
||||||
logger -t "${SYSLOG_IDENT}" -p "user.${level}" "${msg}"
|
|
||||||
|
|
||||||
# Also print to stderr for ERROR/WARN, stdout for INFO
|
|
||||||
case "${level}" in
|
|
||||||
ERROR) echo >&2 "${RED}[ERROR]${NC} ${msg}" ;;
|
|
||||||
WARN) echo >&2 "${YELLOW}[WARN]${NC} ${msg}" ;;
|
|
||||||
INFO) echo " ${GREEN}[INFO]${NC} ${msg}" ;;
|
|
||||||
esac
|
|
||||||
}
|
|
||||||
|
|
||||||
info() { log "INFO" "$@"; }
|
|
||||||
warn() { log "WARN" "$@"; }
|
|
||||||
error() { log "ERROR" "$@"; }
|
|
||||||
|
|
||||||
# =============================================================================
|
|
||||||
# Preflight checks
|
|
||||||
# =============================================================================
|
|
||||||
preflight() {
|
|
||||||
# Must run as root (need to write to /boot), unless overridden for testing
|
|
||||||
if [ -z "${NIXOS_ROLLBACK_SKIP_ROOT_CHECK:-}" ] && [ "$(id -u)" -ne 0 ]; then
|
|
||||||
error "This script must be run as root (needs write access to /boot/loader)"
|
|
||||||
error "Set NIXOS_ROLLBACK_SKIP_ROOT_CHECK=1 for testing against mock paths."
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Directories and files
|
|
||||||
if [ ! -d "${ENTRIES_DIR}" ]; then
|
|
||||||
error "Boot entries directory not found: ${ENTRIES_DIR}"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
if [ ! -f "${LOADER_CONF}" ]; then
|
|
||||||
error "Loader config not found: ${LOADER_CONF}"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
if [ ! -r "${LOADER_CONF}" ]; then
|
|
||||||
error "Cannot read loader config: ${LOADER_CONF}"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Check write access to /boot/loader (parent of loader.conf)
|
|
||||||
local loader_dir
|
|
||||||
loader_dir="$(dirname "${LOADER_CONF}")"
|
|
||||||
if [ ! -w "${loader_dir}" ]; then
|
|
||||||
error "Cannot write to ${loader_dir} (insufficient permissions)"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Logfile directory must exist
|
|
||||||
local log_dir
|
|
||||||
log_dir="$(dirname "${LOGFILE}")"
|
|
||||||
if [ ! -d "${log_dir}" ]; then
|
|
||||||
warn "Log directory ${log_dir} does not exist, creating it"
|
|
||||||
mkdir -p "${log_dir}" 2>/dev/null || {
|
|
||||||
error "Cannot create log directory ${log_dir}"
|
|
||||||
exit 1
|
|
||||||
}
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Check --rollback-now dependencies
|
|
||||||
if [ "${ROLLBACK_NOW}" = true ]; then
|
|
||||||
if ! command -v nixos-rebuild &>/dev/null; then
|
|
||||||
error "nixos-rebuild not found on PATH (required for --rollback-now)"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
# =============================================================================
|
|
||||||
# Generation helpers
|
|
||||||
# =============================================================================
|
|
||||||
|
|
||||||
# get_current_default: reads the current default entry from loader.conf
|
|
||||||
# Returns: "nixos-generation-N.conf" or empty string
|
|
||||||
get_current_default() {
|
|
||||||
grep -E '^default\s+' "${LOADER_CONF}" 2>/dev/null \
|
|
||||||
| awk '{print $2}' \
|
|
||||||
|| true
|
|
||||||
}
|
|
||||||
|
|
||||||
# extract_gen_number: extracts the numeric generation from a conf filename
|
|
||||||
# Input: "nixos-generation-367.conf"
|
|
||||||
# Output: 367
|
|
||||||
extract_gen_number() {
|
|
||||||
echo "$1" | sed 's/nixos-generation-//;s/\.conf//'
|
|
||||||
}
|
|
||||||
|
|
||||||
# get_all_gen_numbers: returns sorted list of generation numbers from entries dir
|
|
||||||
get_all_gen_numbers() {
|
|
||||||
local -a gens=()
|
|
||||||
local f n
|
|
||||||
for f in "${ENTRIES_DIR}"/nixos-generation-*.conf; do
|
|
||||||
[ -f "${f}" ] || continue
|
|
||||||
n="$(basename "${f}" | sed 's/nixos-generation-//;s/\.conf//')"
|
|
||||||
gens+=("${n}")
|
|
||||||
done
|
|
||||||
|
|
||||||
if [ "${#gens[@]}" -eq 0 ]; then
|
|
||||||
return 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Sort numerically and output
|
|
||||||
printf '%s\n' "${gens[@]}" | sort -n
|
|
||||||
}
|
|
||||||
|
|
||||||
# get_previous_gen: given current generation number, find the previous one
|
|
||||||
# from the list of all available generations
|
|
||||||
get_previous_gen() {
|
|
||||||
local current="$1"
|
|
||||||
shift
|
|
||||||
local -a gens=("$@")
|
|
||||||
|
|
||||||
local prev=""
|
|
||||||
local g
|
|
||||||
for g in "${gens[@]}"; do
|
|
||||||
if [ "${g}" -lt "${current}" ]; then
|
|
||||||
prev="${g}"
|
|
||||||
fi
|
|
||||||
done
|
|
||||||
|
|
||||||
if [ -z "${prev}" ]; then
|
|
||||||
return 1
|
|
||||||
fi
|
|
||||||
echo "${prev}"
|
|
||||||
}
|
|
||||||
|
|
||||||
# =============================================================================
|
|
||||||
# Main rollback logic
|
|
||||||
# =============================================================================
|
|
||||||
do_rollback() {
|
|
||||||
# Step 1: Read current default
|
|
||||||
local current_entry
|
|
||||||
current_entry="$(get_current_default)"
|
|
||||||
|
|
||||||
if [ -z "${current_entry}" ]; then
|
|
||||||
error "No 'default' entry found in ${LOADER_CONF}"
|
|
||||||
error "Cannot determine current generation — aborting"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
info "Current default boot entry: ${current_entry}"
|
|
||||||
|
|
||||||
# Step 2: Build sorted list of all available generations
|
|
||||||
local -a all_gens=()
|
|
||||||
local line
|
|
||||||
while IFS= read -r line; do
|
|
||||||
all_gens+=("${line}")
|
|
||||||
done < <(get_all_gen_numbers || true)
|
|
||||||
|
|
||||||
if [ "${#all_gens[@]}" -eq 0 ]; then
|
|
||||||
error "No NixOS generation .conf files found in ${ENTRIES_DIR}"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
info "Available generations: ${all_gens[*]}"
|
|
||||||
|
|
||||||
# Step 3: Find current generation number
|
|
||||||
local current_gen
|
|
||||||
current_gen="$(extract_gen_number "${current_entry}")"
|
|
||||||
|
|
||||||
# Verify current_gen is a valid number
|
|
||||||
if ! [[ "${current_gen}" =~ ^[0-9]+$ ]]; then
|
|
||||||
error "Could not parse generation number from '${current_entry}'"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Step 4: Find the previous generation
|
|
||||||
local prev_gen
|
|
||||||
prev_gen="$(get_previous_gen "${current_gen}" "${all_gens[@]}")" || {
|
|
||||||
error "No previous generation found before generation ${current_gen}"
|
|
||||||
error "This is the oldest available generation — cannot roll back further"
|
|
||||||
exit 2
|
|
||||||
}
|
|
||||||
|
|
||||||
local prev_entry="nixos-generation-${prev_gen}.conf"
|
|
||||||
local prev_conf_path="${ENTRIES_DIR}/${prev_entry}"
|
|
||||||
|
|
||||||
if [ ! -f "${prev_conf_path}" ]; then
|
|
||||||
error "Previous generation entry not found: ${prev_conf_path}"
|
|
||||||
error "The .conf file for generation ${prev_gen} is missing — cannot roll back"
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
info "Target rollback generation: ${prev_gen} → ${prev_entry}"
|
|
||||||
|
|
||||||
# Step 5: Apply the rollback
|
|
||||||
if [ "${DRY_RUN}" = true ]; then
|
|
||||||
echo ""
|
|
||||||
echo " ${CYAN}[DRY RUN]${NC} Would change ${LOADER_CONF}:"
|
|
||||||
echo " ${YELLOW}-${NC} default ${current_entry}"
|
|
||||||
echo " ${GREEN}+${NC} default ${prev_entry}"
|
|
||||||
echo ""
|
|
||||||
info "DRY RUN — no changes made"
|
|
||||||
exit 0
|
|
||||||
fi
|
|
||||||
|
|
||||||
# Write new default
|
|
||||||
# Use sed with a backup (.bak)
|
|
||||||
sed -i.bak "s/^default\s\+${current_entry}/default ${prev_entry}/" "${LOADER_CONF}"
|
|
||||||
|
|
||||||
# Verify the change was applied
|
|
||||||
local new_default
|
|
||||||
new_default="$(get_current_default)"
|
|
||||||
if [ "${new_default}" != "${prev_entry}" ]; then
|
|
||||||
error "Failed to set default boot entry to ${prev_entry}"
|
|
||||||
error "Current default is still: ${new_default}"
|
|
||||||
# Attempt to restore backup
|
|
||||||
if [ -f "${LOADER_CONF}.bak" ]; then
|
|
||||||
cp "${LOADER_CONF}.bak" "${LOADER_CONF}"
|
|
||||||
info "Restored backup from ${LOADER_CONF}.bak"
|
|
||||||
fi
|
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
|
|
||||||
info "Successfully set default boot entry to ${prev_entry} (generation ${prev_gen})"
|
|
||||||
info "Backup of previous config saved to ${LOADER_CONF}.bak"
|
|
||||||
|
|
||||||
# Step 6: Optionally run nixos-rebuild switch --rollback
|
|
||||||
if [ "${ROLLBACK_NOW}" = true ]; then
|
|
||||||
echo ""
|
|
||||||
info "Running nixos-rebuild switch --rollback for immediate effect..."
|
|
||||||
if nixos-rebuild switch --rollback 2>&1 | while IFS= read -r line; do
|
|
||||||
logger -t "${SYSLOG_IDENT}" "nixos-rebuild: ${line}"
|
|
||||||
echo " ${line}"
|
|
||||||
done; then
|
|
||||||
info "nixos-rebuild switch --rollback completed successfully"
|
|
||||||
else
|
|
||||||
local rc=$?
|
|
||||||
error "nixos-rebuild switch --rollback failed with exit code ${rc}"
|
|
||||||
error "The boot default has been changed but the current system was NOT rolled back"
|
|
||||||
error "Reboot to apply the rollback"
|
|
||||||
exit 3
|
|
||||||
fi
|
|
||||||
fi
|
|
||||||
|
|
||||||
info "Rollback complete. Next boot will use generation ${prev_gen}."
|
|
||||||
if [ "${ROLLBACK_NOW}" = false ]; then
|
|
||||||
echo ""
|
|
||||||
echo " ${YELLOW}NOTE:${NC} The current running system is unchanged."
|
|
||||||
echo " Reboot to boot into generation ${prev_gen}."
|
|
||||||
echo " Or re-run with --rollback-now for immediate effect."
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
# =============================================================================
|
|
||||||
# Main
|
|
||||||
# =============================================================================
|
|
||||||
main() {
|
|
||||||
# Parse arguments
|
|
||||||
while [ $# -gt 0 ]; do
|
|
||||||
case "$1" in
|
|
||||||
--dry-run)
|
|
||||||
DRY_RUN=true
|
|
||||||
shift
|
|
||||||
;;
|
|
||||||
--rollback-now)
|
|
||||||
ROLLBACK_NOW=true
|
|
||||||
shift
|
|
||||||
;;
|
|
||||||
-h|--help)
|
|
||||||
usage
|
|
||||||
exit 0
|
|
||||||
;;
|
|
||||||
*)
|
|
||||||
echo >&2 "Unknown option: $1"
|
|
||||||
echo >&2 "Use --help for usage information."
|
|
||||||
exit 1
|
|
||||||
;;
|
|
||||||
esac
|
|
||||||
done
|
|
||||||
|
|
||||||
echo ""
|
|
||||||
echo " ${CYAN}═══ NixOS systemd-boot Rollback ═══${NC}"
|
|
||||||
echo ""
|
|
||||||
|
|
||||||
preflight
|
|
||||||
|
|
||||||
if [ "${DRY_RUN}" = true ]; then
|
|
||||||
info "DRY RUN mode — no changes will be made"
|
|
||||||
fi
|
|
||||||
if [ "${ROLLBACK_NOW}" = true ]; then
|
|
||||||
info "ROLLBACK NOW mode — will also run nixos-rebuild switch --rollback"
|
|
||||||
fi
|
|
||||||
|
|
||||||
echo ""
|
|
||||||
do_rollback
|
|
||||||
}
|
|
||||||
|
|
||||||
main "$@"
|
|
||||||
@@ -1,87 +1,45 @@
|
|||||||
{ pkgs, ... }: {
|
{ pkgs, ... }: {
|
||||||
systemd.services.init-ollama-model = {
|
systemd.services.init-ollama-model = {
|
||||||
description = "Initialize LLM models with extra context in Ollama Docker";
|
description = "Initialize LLM models with extra context in Ollama Docker";
|
||||||
|
after = [ "docker-ollama.service" ];
|
||||||
# On s'assure que Docker tourne avant de lancer ce script
|
|
||||||
after = [ "docker.service" ];
|
|
||||||
wantedBy = [ "multi-user.target" ];
|
wantedBy = [ "multi-user.target" ];
|
||||||
|
|
||||||
script = ''
|
script = ''
|
||||||
# Fonction de création asynchrone pour ne pas bloquer le démarrage
|
# Wait for Ollama
|
||||||
(
|
while ! ${pkgs.curl}/bin/curl -s http://localhost:11434/api/tags > /dev/null; do
|
||||||
echo "Starting asynchronous Ollama initialization..."
|
sleep 2
|
||||||
|
done
|
||||||
|
|
||||||
# Attente d'Ollama (maximum 120 secondes pour éviter une boucle infinie)
|
create_model_if_missing() {
|
||||||
TIMEOUT=60
|
local model_name=$1
|
||||||
COUNT=0
|
local base_model=$2
|
||||||
while ! ${pkgs.curl}/bin/curl -s -f http://127.0.0.1:11434/api/tags > /dev/null; do
|
if ! ${pkgs.docker}/bin/docker exec ollama ollama list | grep -q "$model_name"; then
|
||||||
if [ $COUNT -ge $TIMEOUT ]; then
|
echo "$model_name not found, creating from $base_model..."
|
||||||
echo "Ollama did not become ready in time. Exiting."
|
${pkgs.docker}/bin/docker exec ollama sh -c "cat <<EOF > /root/.ollama/$model_name.modelfile
|
||||||
exit 1
|
|
||||||
fi
|
|
||||||
echo "Waiting for Ollama API to be reachable..."
|
|
||||||
sleep 5
|
|
||||||
COUNT=$((COUNT + 5))
|
|
||||||
done
|
|
||||||
|
|
||||||
create_model_if_missing() {
|
|
||||||
local model_name=$1
|
|
||||||
local base_model=$2
|
|
||||||
|
|
||||||
# Vérification robuste via l'API HTTP d'Ollama plutôt que docker exec (évite les conflits de tty)
|
|
||||||
if ! ${pkgs.curl}/bin/curl -s http://127.0.0.1:11434/api/tags | ${pkgs.jq}/bin/jq -e ".models[] | select(.name == \"$model_name\")" > /dev/null; then
|
|
||||||
echo "$model_name not found, creating from $base_model..."
|
|
||||||
|
|
||||||
# Utilisation d'un fichier temporaire sur l'hôte pour l'injecter proprement dans Docker
|
|
||||||
TMP_FILE=$(mktemp)
|
|
||||||
cat <<EOF > "$TMP_FILE"
|
|
||||||
FROM $base_model
|
FROM $base_model
|
||||||
TEMPLATE """{{- if .System }}
|
|
||||||
[SYSTEM_PROMPT]
|
|
||||||
{{ .System }}
|
|
||||||
[/SYSTEM_PROMPT]
|
|
||||||
{{- end }}
|
|
||||||
{{- range .Messages }}
|
|
||||||
{{- if eq .Role "user" }}
|
|
||||||
[INST]
|
|
||||||
{{ .Content }}
|
|
||||||
[/INST]
|
|
||||||
{{- else if eq .Role "assistant" }}
|
|
||||||
{{ .Content }}
|
|
||||||
{{- end }}
|
|
||||||
{{- end }}"""
|
|
||||||
PARAMETER num_ctx 131072
|
PARAMETER num_ctx 131072
|
||||||
PARAMETER num_predict 4096
|
PARAMETER num_predict 4096
|
||||||
PARAMETER num_keep 1024
|
PARAMETER num_keep 1024
|
||||||
PARAMETER repeat_penalty 1.1
|
PARAMETER repeat_penalty 1.1
|
||||||
PARAMETER top_k 40
|
PARAMETER top_k 40
|
||||||
PARAMETER stop "[INST]"
|
PARAMETER stop \"[INST]\"
|
||||||
PARAMETER stop "[/INST]"
|
PARAMETER stop \"[/INST]\"
|
||||||
PARAMETER stop "</s>"
|
PARAMETER stop \"</s>\"
|
||||||
EOF
|
EOF"
|
||||||
|
${pkgs.docker}/bin/docker exec ollama ollama create "$model_name" -f "/root/.ollama/$model_name.modelfile"
|
||||||
|
else
|
||||||
|
echo "$model_name already exists, skipping."
|
||||||
|
fi
|
||||||
|
}
|
||||||
|
|
||||||
# Copie et création dans le conteneur
|
# Create Nemotron
|
||||||
${pkgs.docker}/bin/docker cp "$TMP_FILE" ollama:/tmp/model.modelfile
|
create_model_if_missing "nemotron-3-nano:30b-128k" "nemotron-3-nano:30b"
|
||||||
${pkgs.docker}/bin/docker exec ollama ollama create "$model_name" -f /tmp/model.modelfile
|
|
||||||
${pkgs.docker}/bin/docker exec ollama rm /tmp/model.modelfile
|
|
||||||
rm -f "$TMP_FILE"
|
|
||||||
else
|
|
||||||
echo "$model_name already exists, skipping."
|
|
||||||
fi
|
|
||||||
}
|
|
||||||
|
|
||||||
# Create Nemotron
|
# Create Devstral
|
||||||
create_model_if_missing "nemotron-3-nano:30b-128k" "nemotron-3-nano:30b"
|
create_model_if_missing "devstral-small-2:24b-128k" "devstral-small-2:24b"
|
||||||
|
|
||||||
# Create Devstral
|
|
||||||
create_model_if_missing "devstral-small-2:24b-128k" "devstral-small-2:24b"
|
|
||||||
|
|
||||||
) &
|
|
||||||
'';
|
'';
|
||||||
|
|
||||||
serviceConfig = {
|
serviceConfig = {
|
||||||
Type = "forking"; # Permet à systemd de savoir que le script passe en arrière-plan via '&'
|
Type = "oneshot";
|
||||||
User = "root";
|
RemainAfterExit = true;
|
||||||
};
|
};
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,184 +0,0 @@
|
|||||||
{ config, pkgs, lib, ... }:
|
|
||||||
|
|
||||||
with lib;
|
|
||||||
|
|
||||||
let
|
|
||||||
cfg = config.services.rollbackSentinel;
|
|
||||||
|
|
||||||
# ── Scripts ────────────────────────────────────────────────────────────────
|
|
||||||
|
|
||||||
# Sentinel check — verifies Tier-1 services are active after boot.
|
|
||||||
# Exits nonzero when any Tier-1 service is down, which triggers the rollback.
|
|
||||||
sentinelCheck = pkgs.writeShellScriptBin "sentinel-check.sh" ''
|
|
||||||
#!/usr/bin/env bash
|
|
||||||
set -euo pipefail
|
|
||||||
|
|
||||||
SYSLOG_IDENT="nixos-sentinel"
|
|
||||||
LOGFILE="/var/log/nixos-sentinel.log"
|
|
||||||
|
|
||||||
echo "=== NixOS Sentinel Check ==="
|
|
||||||
echo "Tier-1 services: ${builtins.toString cfg.tier1Services}"
|
|
||||||
echo "Tier-2 services: ${builtins.toString cfg.tier2Services}"
|
|
||||||
|
|
||||||
FAILED=0
|
|
||||||
|
|
||||||
# Check Tier-1 services — any failure means rollback
|
|
||||||
for svc in ${builtins.toString cfg.tier1Services}; do
|
|
||||||
if systemctl is-active --quiet "$svc" 2>/dev/null; then
|
|
||||||
echo " [OK] Tier-1: $svc"
|
|
||||||
else
|
|
||||||
echo " [FAIL] Tier-1: $svc is NOT active"
|
|
||||||
logger -t "$SYSLOG_IDENT" -p user.err "Tier-1 FAILURE: $svc is not active"
|
|
||||||
FAILED=1
|
|
||||||
fi
|
|
||||||
done
|
|
||||||
|
|
||||||
# Check Tier-2 services — warn only
|
|
||||||
for svc in ${builtins.toString cfg.tier2Services}; do
|
|
||||||
if systemctl is-active --quiet "$svc" 2>/dev/null; then
|
|
||||||
echo " [OK] Tier-2: $svc"
|
|
||||||
else
|
|
||||||
echo " [WARN] Tier-2: $svc is NOT active"
|
|
||||||
logger -t "$SYSLOG_IDENT" -p user.warn "Tier-2 WARNING: $svc is not active"
|
|
||||||
fi
|
|
||||||
done
|
|
||||||
|
|
||||||
echo "=== Sentinel result: $([ "$FAILED" -eq 0 ] && echo 'PASS' || echo 'FAIL') ==="
|
|
||||||
echo "$(date '+%Y-%m-%d %H:%M:%S') [INFO] sentinel $([ "$FAILED" -eq 0 ] && echo 'PASS' || echo 'FAIL')" >> "$LOGFILE"
|
|
||||||
exit $FAILED
|
|
||||||
'';
|
|
||||||
|
|
||||||
# Rollback script — package the companion shell script from this directory.
|
|
||||||
# Uses builtins.readFile to embed the content at evaluation time.
|
|
||||||
rollbackScript = pkgs.writeShellScriptBin "nixos-rollback.sh" (builtins.readFile ./nixos-rollback.sh);
|
|
||||||
|
|
||||||
# Resolve rollback flags from config
|
|
||||||
rollbackFlags =
|
|
||||||
if cfg.rollbackMode == "dry-run" then "--dry-run"
|
|
||||||
else if cfg.rollbackMode == "rollback-now" then "--rollback-now"
|
|
||||||
else "";
|
|
||||||
|
|
||||||
in {
|
|
||||||
options.services.rollbackSentinel = {
|
|
||||||
enable = mkEnableOption "NixOS Rollback Sentinel — auto-rollback on critical service failure";
|
|
||||||
|
|
||||||
tier1Services = mkOption {
|
|
||||||
type = types.listOf types.str;
|
|
||||||
default = [ "sshd" "docker" "traefik" "authelia" ];
|
|
||||||
description = ''
|
|
||||||
Tier-1 services whose failure triggers an automatic systemd-boot rollback.
|
|
||||||
On boot, the sentinel waits ${cfg.bootDelay} seconds, then checks each
|
|
||||||
service. If ANY service in this list is inactive, it runs the rollback
|
|
||||||
script which sets the previous NixOS generation as the default boot entry.
|
|
||||||
'';
|
|
||||||
};
|
|
||||||
|
|
||||||
tier2Services = mkOption {
|
|
||||||
type = types.listOf types.str;
|
|
||||||
default = [
|
|
||||||
"gitea" "hermes" "ollama" "synapse" "nextcloud"
|
|
||||||
"vaultwarden" "wireguard" "homeassistant" "fail2ban"
|
|
||||||
];
|
|
||||||
description = ''
|
|
||||||
Tier-2 services whose failure is logged as a warning but does NOT trigger
|
|
||||||
an automatic rollback. Useful for detecting non-critical service issues.
|
|
||||||
'';
|
|
||||||
};
|
|
||||||
|
|
||||||
tier3InfoServices = mkOption {
|
|
||||||
type = types.listOf types.str;
|
|
||||||
default = [
|
|
||||||
"act_runner" "syncthing" "restic" "fava"
|
|
||||||
"homer" "cups" "fstrim"
|
|
||||||
];
|
|
||||||
description = ''
|
|
||||||
Tier-3 informational checks (log-only, no warning). These are services
|
|
||||||
that the sentinel will note the status of for diagnostics.
|
|
||||||
'';
|
|
||||||
};
|
|
||||||
|
|
||||||
bootDelay = mkOption {
|
|
||||||
type = types.str;
|
|
||||||
default = "120";
|
|
||||||
description = ''
|
|
||||||
Seconds to wait after multi-user.target before running the boot-time
|
|
||||||
sentinel check. This gives Tier-1 services time to start before
|
|
||||||
the sentinel decides they've failed.
|
|
||||||
'';
|
|
||||||
};
|
|
||||||
|
|
||||||
rollbackMode = mkOption {
|
|
||||||
type = types.enum [ "set-default" "rollback-now" "dry-run" ];
|
|
||||||
default = "set-default";
|
|
||||||
description = ''
|
|
||||||
Rollback strategy when Tier-1 failures are detected:
|
|
||||||
- set-default: Write the previous generation to loader.conf (next reboot).
|
|
||||||
- rollback-now: Also run nixos-rebuild switch --rollback for immediate fix.
|
|
||||||
- dry-run: Log what would happen but take no action (testing).
|
|
||||||
'';
|
|
||||||
};
|
|
||||||
|
|
||||||
enablePostRebuild = mkOption {
|
|
||||||
type = types.bool;
|
|
||||||
default = true;
|
|
||||||
description = ''
|
|
||||||
When enabled, the sentinel check runs after every nixos-rebuild switch
|
|
||||||
activation. If a newly deployed generation has Tier-1 failures, it
|
|
||||||
triggers rollback immediately.
|
|
||||||
'';
|
|
||||||
};
|
|
||||||
};
|
|
||||||
|
|
||||||
config = mkIf cfg.enable {
|
|
||||||
# ── Deploy scripts to PATH ───────────────────────────────────────────────
|
|
||||||
environment.systemPackages = [ sentinelCheck rollbackScript ];
|
|
||||||
|
|
||||||
# Ensure log directory exists
|
|
||||||
systemd.tmpfiles.rules = [
|
|
||||||
"d /var/log/nixos-sentinel 0755 root root -"
|
|
||||||
];
|
|
||||||
|
|
||||||
# ── Boot-time sentinel service ───────────────────────────────────────────
|
|
||||||
# Runs after multi-user.target with a configurable delay, checks Tier-1
|
|
||||||
# services, and triggers rollback if any are down.
|
|
||||||
systemd.services.nixos-sentinel = {
|
|
||||||
description = "NixOS Boot Sentinel — check critical services, roll back on failure";
|
|
||||||
after = [ "network.target" "multi-user.target" ];
|
|
||||||
wants = [ "network.target" ];
|
|
||||||
wantedBy = [ "multi-user.target" ];
|
|
||||||
|
|
||||||
path = with pkgs; [ coreutils gawk gnused systemd ];
|
|
||||||
|
|
||||||
serviceConfig = {
|
|
||||||
Type = "oneshot";
|
|
||||||
RemainAfterExit = true;
|
|
||||||
ExecStartPre = "${pkgs.coreutils}/bin/sleep ${cfg.bootDelay}";
|
|
||||||
ExecStart = "${sentinelCheck}/bin/sentinel-check.sh";
|
|
||||||
ExecStartPost = "${rollbackScript}/bin/nixos-rollback.sh ${rollbackFlags}";
|
|
||||||
};
|
|
||||||
};
|
|
||||||
|
|
||||||
# ── Post-rebuild sentinel service (triggered by activation script) ──────
|
|
||||||
systemd.services.nixos-sentinel-rebuild = mkIf cfg.enablePostRebuild {
|
|
||||||
description = "NixOS Post-Rebuild Sentinel — check services after nixos-rebuild";
|
|
||||||
after = [ "network.target" ];
|
|
||||||
|
|
||||||
path = with pkgs; [ coreutils gawk gnused systemd ];
|
|
||||||
|
|
||||||
serviceConfig = {
|
|
||||||
Type = "oneshot";
|
|
||||||
ExecStart = "${sentinelCheck}/bin/sentinel-check.sh";
|
|
||||||
ExecStartPost = "${rollbackScript}/bin/nixos-rollback.sh ${rollbackFlags}";
|
|
||||||
};
|
|
||||||
};
|
|
||||||
|
|
||||||
# Activation script — fires after every nixos-rebuild switch
|
|
||||||
system.activationScripts.rollback-sentinel = mkIf cfg.enablePostRebuild ''
|
|
||||||
# Start the post-rebuild sentinel in the background.
|
|
||||||
# This runs on every activation (boot + nixos-rebuild). On boot the
|
|
||||||
# boot-time service handles it, so this is primarily for nixos-rebuild,
|
|
||||||
# but running twice is safe (idempotent rollback).
|
|
||||||
systemctl start nixos-sentinel-rebuild.service --no-block 2>/dev/null || true
|
|
||||||
'';
|
|
||||||
};
|
|
||||||
}
|
|
||||||
63
scripts/deploy-ssh-config
Normal file
63
scripts/deploy-ssh-config
Normal file
@@ -0,0 +1,63 @@
|
|||||||
|
# Hermes Container SSH Configuration
|
||||||
|
# For NixOS deployment to remote hosts
|
||||||
|
#
|
||||||
|
# Usage:
|
||||||
|
# cp scripts/deploy-ssh-config ~/.ssh/config.d/hermes-include
|
||||||
|
# Or: cat scripts/deploy-ssh-config >> ~/.ssh/config
|
||||||
|
#
|
||||||
|
# This config covers all NixOS hosts managed from the Hermes container.
|
||||||
|
# Lazyworkhorse has two users: ai-worker (primary automation) and gortium (admin).
|
||||||
|
# Cyt-pi connects via reverse SSH tunnel on port 19999.
|
||||||
|
# uConsole is a placeholder until LAN-hostname resolution is confirmed.
|
||||||
|
|
||||||
|
# ── Global defaults ──────────────────────────────────────────────────
|
||||||
|
Host *
|
||||||
|
ServerAliveInterval 60
|
||||||
|
ServerAliveCountMax 3
|
||||||
|
TCPKeepAlive yes
|
||||||
|
Compression yes
|
||||||
|
CompressionLevel 6
|
||||||
|
ControlMaster auto
|
||||||
|
ControlPath ~/.ssh/controlmasters/%r@%h:%p
|
||||||
|
ControlPersist 10m
|
||||||
|
StrictHostKeyChecking no
|
||||||
|
UserKnownHostsFile /dev/null
|
||||||
|
|
||||||
|
# ── Hosts ──────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
# Lazyworkhorse — x86_64 main server (ai-worker@lazyworkhorse.net:2424)
|
||||||
|
Host lazyworkhorse
|
||||||
|
HostName lazyworkhorse.net
|
||||||
|
User ai-worker
|
||||||
|
Port 2424
|
||||||
|
IdentityFile /opt/data/home/.ssh/id_hermes_gitea
|
||||||
|
|
||||||
|
# Lazyworkhorse — admin access (gortium@lazyworkhorse.net:2425)
|
||||||
|
Host lazyworkhorse-admin
|
||||||
|
HostName lazyworkhorse.net
|
||||||
|
User gortium
|
||||||
|
Port 2425
|
||||||
|
IdentityFile /opt/data/home/.ssh/id_hermes_gitea
|
||||||
|
|
||||||
|
# Cyt-pi — aarch64 Pi Zero 2 W
|
||||||
|
# Connected via reverse SSH tunnel (gortium directs tunnel to :19999)
|
||||||
|
Host cyt-pi
|
||||||
|
HostName localhost
|
||||||
|
User gortium
|
||||||
|
Port 19999
|
||||||
|
IdentityFile /opt/data/home/.ssh/id_hermes_gitea
|
||||||
|
|
||||||
|
# uConsole — aarch64 ClockworkPi (placeholder hostname)
|
||||||
|
# Replace uconsole.lan with actual IP/hostname when deployed
|
||||||
|
Host uConsole uconsole
|
||||||
|
HostName uconsole.lan
|
||||||
|
User gortium
|
||||||
|
Port 22
|
||||||
|
IdentityFile /opt/data/home/.ssh/id_hermes_gitea
|
||||||
|
|
||||||
|
# ── Gitea host — for git operations ──────────────────────────────────
|
||||||
|
Host code
|
||||||
|
HostName code.lazyworkhorse.net
|
||||||
|
Port 2222
|
||||||
|
User gortium
|
||||||
|
IdentityFile /opt/data/home/.ssh/id_hermes_gitea
|
||||||
286
scripts/deploy.sh
Executable file
286
scripts/deploy.sh
Executable file
@@ -0,0 +1,286 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# NixOS Deployment Helper Script
|
||||||
|
# Remote NixOS deployment from Hermes container to target hosts.
|
||||||
|
#
|
||||||
|
# Usage: ./deploy.sh <hostname> [branch] [action]
|
||||||
|
#
|
||||||
|
# Actions:
|
||||||
|
# switch Activate configuration now (default)
|
||||||
|
# boot Activate on next reboot
|
||||||
|
# test Activate without switching generations
|
||||||
|
# build Build locally only, no remote activation
|
||||||
|
# dry-activate Show what would change without applying
|
||||||
|
#
|
||||||
|
# Examples:
|
||||||
|
# ./deploy.sh lazyworkhorse # deploy master/switch to lazyworkhorse
|
||||||
|
# ./deploy.sh cyt-pi feat/test boot # deploy feat/test branch, activate on boot
|
||||||
|
# ./deploy.sh uConsole master build # just build, don't deploy
|
||||||
|
# NO_BUILD_CHECK=1 ./deploy.sh uConsole # skip the pre-flight nix build
|
||||||
|
#
|
||||||
|
# Environment variables:
|
||||||
|
# SSH_USER SSH user (default: auto-detected per host)
|
||||||
|
# SSH_PORT SSH port (default: auto-detected per host)
|
||||||
|
# SSH_KEY SSH identity file
|
||||||
|
# BUILD_HOST Build flake for this host (default: same as target host)
|
||||||
|
# NO_BUILD_CHECK Set to 1 to skip local nix build before deployment
|
||||||
|
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
# ── Colors ──────────────────────────────────────────────────────────────
|
||||||
|
RED='\033[0;31m'
|
||||||
|
GREEN='\033[0;32m'
|
||||||
|
YELLOW='\033[1;33m'
|
||||||
|
BLUE='\033[0;34m'
|
||||||
|
CYAN='\033[0;36m'
|
||||||
|
NC='\033[0m' # No Color
|
||||||
|
|
||||||
|
info() { echo -e "${BLUE}[INFO]${NC} $*"; }
|
||||||
|
ok() { echo -e "${GREEN}[OK]${NC} $*"; }
|
||||||
|
warn() { echo -e "${YELLOW}[WARN]${NC} $*"; }
|
||||||
|
error() { echo -e "${RED}[ERROR]${NC} $*" >&2; }
|
||||||
|
step() { echo -e "\n${CYAN}━━━ $* ━━━${NC}"; }
|
||||||
|
|
||||||
|
# ── Cleanup trap ───────────────────────────────────────────────────────
|
||||||
|
cleanup() {
|
||||||
|
local ec=$?
|
||||||
|
if [ $ec -ne 0 ]; then
|
||||||
|
error "Deployment failed with exit code $ec"
|
||||||
|
fi
|
||||||
|
exit $ec
|
||||||
|
}
|
||||||
|
trap cleanup EXIT
|
||||||
|
|
||||||
|
# ── Usage / Help ───────────────────────────────────────────────────────
|
||||||
|
show_usage() {
|
||||||
|
cat <<EOF
|
||||||
|
Usage: $0 <hostname> [branch] [action]
|
||||||
|
|
||||||
|
Remote NixOS deployment from Hermes container to target hosts.
|
||||||
|
|
||||||
|
HOSTNAME (required):
|
||||||
|
lazyworkhorse x86_64 main server
|
||||||
|
cyt-pi aarch64 Pi Zero 2 W (via reverse tunnel)
|
||||||
|
uConsole aarch64 ClockworkPi
|
||||||
|
|
||||||
|
BRANCH (optional, default: master):
|
||||||
|
Git branch or tag to deploy. Fetched from origin.
|
||||||
|
|
||||||
|
ACTION (optional, default: switch):
|
||||||
|
switch Activate configuration now (default)
|
||||||
|
boot Activate on next reboot
|
||||||
|
test Activate without switching generations
|
||||||
|
build Build locally only, skip remote deployment
|
||||||
|
dry-activate Show what would change without applying
|
||||||
|
|
||||||
|
Environment variables:
|
||||||
|
SSH_USER SSH username override
|
||||||
|
SSH_PORT SSH port override
|
||||||
|
SSH_KEY SSH identity file path
|
||||||
|
BUILD_HOST Build flake hostname (default: same as HOSTNAME)
|
||||||
|
NO_BUILD_CHECK Skip local nix build validation (set to 1)
|
||||||
|
|
||||||
|
Examples:
|
||||||
|
$0 lazyworkhorse # deploy master/switch
|
||||||
|
$0 cyt-pi feat/test boot # deploy feature branch, boot
|
||||||
|
$0 uConsole master build # just build, no remote
|
||||||
|
NO_BUILD_CHECK=1 $0 uConsole # skip build check
|
||||||
|
|
||||||
|
EOF
|
||||||
|
exit 0
|
||||||
|
}
|
||||||
|
|
||||||
|
# ── Argument parsing ───────────────────────────────────────────────────
|
||||||
|
HOSTNAME="${1:-}"
|
||||||
|
BRANCH="${2:-master}"
|
||||||
|
ACTION="${3:-switch}"
|
||||||
|
NO_BUILD_CHECK="${NO_BUILD_CHECK:-0}"
|
||||||
|
|
||||||
|
if [ "$HOSTNAME" = "--help" ] || [ "$HOSTNAME" = "-h" ] || [ -z "$HOSTNAME" ]; then
|
||||||
|
show_usage
|
||||||
|
fi
|
||||||
|
|
||||||
|
# ── Host configuration ─────────────────────────────────────────────────
|
||||||
|
case "$HOSTNAME" in
|
||||||
|
lazyworkhorse)
|
||||||
|
DEFAULT_SSH_USER="ai-worker"
|
||||||
|
DEFAULT_SSH_PORT="2424"
|
||||||
|
ARCH="x86_64-linux"
|
||||||
|
;;
|
||||||
|
cyt-pi)
|
||||||
|
DEFAULT_SSH_USER="gortium"
|
||||||
|
DEFAULT_SSH_PORT="19999"
|
||||||
|
ARCH="aarch64-linux"
|
||||||
|
;;
|
||||||
|
uConsole)
|
||||||
|
DEFAULT_SSH_USER="gortium"
|
||||||
|
DEFAULT_SSH_PORT="22"
|
||||||
|
ARCH="aarch64-linux"
|
||||||
|
;;
|
||||||
|
*)
|
||||||
|
error "Unknown host: $HOSTNAME"
|
||||||
|
echo "Supported hosts: lazyworkhorse, cyt-pi, uConsole"
|
||||||
|
exit 1
|
||||||
|
;;
|
||||||
|
esac
|
||||||
|
|
||||||
|
SSH_USER="${SSH_USER:-$DEFAULT_SSH_USER}"
|
||||||
|
SSH_PORT="${SSH_PORT:-$DEFAULT_SSH_PORT}"
|
||||||
|
SSH_KEY="${SSH_KEY:-/opt/data/home/.ssh/id_hermes_gitea}"
|
||||||
|
BUILD_HOST="${BUILD_HOST:-$HOSTNAME}"
|
||||||
|
|
||||||
|
SSH_OPTS="-p $SSH_PORT -i $SSH_KEY -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null"
|
||||||
|
SSH_TARGET="${SSH_USER}@${HOSTNAME}"
|
||||||
|
export GIT_SSH_COMMAND="ssh -i $SSH_KEY -p 2222 -o StrictHostKeyChecking=no"
|
||||||
|
export PATH="/nix/var/nix/profiles/default/bin:$PATH"
|
||||||
|
|
||||||
|
# ── Banner ─────────────────────────────────────────────────────────────
|
||||||
|
echo "╔══════════════════════════════════════════════╗"
|
||||||
|
echo "║ NixOS Remote Deployment ║"
|
||||||
|
echo "╚══════════════════════════════════════════════╝"
|
||||||
|
info "Host: $HOSTNAME ($ARCH)"
|
||||||
|
info "Branch: $BRANCH"
|
||||||
|
info "Action: $ACTION"
|
||||||
|
info "SSH: ${SSH_USER}@${HOSTNAME}:${SSH_PORT}"
|
||||||
|
echo ""
|
||||||
|
|
||||||
|
# ── Pre-flight checks ─────────────────────────────────────────────────
|
||||||
|
step "Pre-flight checks"
|
||||||
|
|
||||||
|
# 1. Check required tools
|
||||||
|
for cmd in nix git ssh; do
|
||||||
|
if ! command -v "$cmd" &>/dev/null; then
|
||||||
|
error "Required tool not found: $cmd"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
done
|
||||||
|
ok "Required tools available (nix, git, ssh)"
|
||||||
|
|
||||||
|
# 2. Check infra repo
|
||||||
|
INFRA_DIR="$(cd "$(dirname "$0")/.." && pwd)"
|
||||||
|
if [ ! -d "$INFRA_DIR/.git" ]; then
|
||||||
|
error "Not a git repository: $INFRA_DIR"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
ok "Infra repo found at $INFRA_DIR"
|
||||||
|
|
||||||
|
# 3. Check SSH connectivity (skip for build-only actions)
|
||||||
|
if [ "$ACTION" != "build" ]; then
|
||||||
|
if ssh $SSH_OPTS -o ConnectTimeout=5 "$SSH_TARGET" "echo connected" &>/dev/null; then
|
||||||
|
ok "SSH connectivity to $HOSTNAME verified"
|
||||||
|
else
|
||||||
|
warn "Cannot reach $HOSTNAME via SSH — deployment step will fail later"
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
|
||||||
|
# ── Git sync ───────────────────────────────────────────────────────────
|
||||||
|
step "Git sync"
|
||||||
|
|
||||||
|
cd "$INFRA_DIR"
|
||||||
|
|
||||||
|
# Stash local changes if any
|
||||||
|
if ! git diff --quiet HEAD; then
|
||||||
|
warn "Local changes detected, stashing..."
|
||||||
|
git stash push -m "auto-stash before deploy $(date -Iseconds)"
|
||||||
|
STASHED=1
|
||||||
|
else
|
||||||
|
STASHED=0
|
||||||
|
fi
|
||||||
|
|
||||||
|
# Fetch and checkout
|
||||||
|
git fetch origin "$BRANCH" 2>/dev/null || git fetch origin master
|
||||||
|
if git rev-parse --verify "origin/$BRANCH" &>/dev/null 2>&1; then
|
||||||
|
# Remote branch exists — fast-forward merge
|
||||||
|
git checkout -B "$BRANCH" "origin/$BRANCH"
|
||||||
|
elif git rev-parse --verify "$BRANCH" &>/dev/null 2>&1; then
|
||||||
|
# Local branch or tag
|
||||||
|
git checkout "$BRANCH"
|
||||||
|
else
|
||||||
|
error "Branch/tag not found: $BRANCH"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
ok "Checked out $BRANCH ($(git rev-parse --short HEAD))"
|
||||||
|
|
||||||
|
# Update submodules
|
||||||
|
if [ -f .gitmodules ]; then
|
||||||
|
git submodule update --init --recursive
|
||||||
|
ok "Submodules updated"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# ── Build validation ──────────────────────────────────────────────────
|
||||||
|
if [ "$NO_BUILD_CHECK" != "1" ]; then
|
||||||
|
step "Build validation"
|
||||||
|
info "Building nixosConfigurations.$BUILD_HOST (no link)..."
|
||||||
|
|
||||||
|
if nix build --no-link --print-build-logs \
|
||||||
|
".#nixosConfigurations.${BUILD_HOST}.config.system.build.toplevel" 2>&1; then
|
||||||
|
ok "Build succeeded for $BUILD_HOST"
|
||||||
|
else
|
||||||
|
error "Build failed for $BUILD_HOST"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
else
|
||||||
|
warn "Build check skipped (NO_BUILD_CHECK=1)"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# ── Deployment ─────────────────────────────────────────────────────────
|
||||||
|
if [ "$ACTION" = "build" ]; then
|
||||||
|
step "Build complete (no deployment)"
|
||||||
|
info "Use one of: switch, boot, test, dry-activate to deploy"
|
||||||
|
exit 0
|
||||||
|
fi
|
||||||
|
|
||||||
|
step "Deployment ($ACTION)"
|
||||||
|
|
||||||
|
# Build the nixos-rebuild command
|
||||||
|
case "$ACTION" in
|
||||||
|
switch|boot|test)
|
||||||
|
nixos-rebuild "$ACTION" \
|
||||||
|
--flake ".#$HOSTNAME" \
|
||||||
|
--target-host "$SSH_TARGET" \
|
||||||
|
--build-host "localhost" \
|
||||||
|
--use-remote-sudo \
|
||||||
|
--max-jobs 4
|
||||||
|
;;
|
||||||
|
dry-activate)
|
||||||
|
nixos-rebuild dry-activate \
|
||||||
|
--flake ".#$HOSTNAME" \
|
||||||
|
--target-host "$SSH_TARGET" \
|
||||||
|
--build-host "localhost" \
|
||||||
|
--use-remote-sudo
|
||||||
|
;;
|
||||||
|
*)
|
||||||
|
error "Unknown action: $ACTION"
|
||||||
|
echo "Valid actions: switch, boot, test, build, dry-activate"
|
||||||
|
exit 1
|
||||||
|
;;
|
||||||
|
esac
|
||||||
|
|
||||||
|
# ── Check result ───────────────────────────────────────────────────────
|
||||||
|
DEPLOY_EXIT=$?
|
||||||
|
if [ $DEPLOY_EXIT -eq 0 ]; then
|
||||||
|
echo ""
|
||||||
|
ok "Deployment to $HOSTNAME ($ACTION) completed successfully"
|
||||||
|
case "$ACTION" in
|
||||||
|
switch|test)
|
||||||
|
info "Configuration is now active"
|
||||||
|
;;
|
||||||
|
boot)
|
||||||
|
info "Configuration will activate on next reboot"
|
||||||
|
;;
|
||||||
|
dry-activate)
|
||||||
|
info "Dry-run complete — no changes applied"
|
||||||
|
;;
|
||||||
|
esac
|
||||||
|
else
|
||||||
|
error "Deployment failed with exit code $DEPLOY_EXIT"
|
||||||
|
exit $DEPLOY_EXIT
|
||||||
|
fi
|
||||||
|
|
||||||
|
echo ""
|
||||||
|
echo "╔══════════════════════════════════════════════╗"
|
||||||
|
echo "║ Deployment Complete ║"
|
||||||
|
echo "╚══════════════════════════════════════════════╝"
|
||||||
|
info "Host: $HOSTNAME"
|
||||||
|
info "Branch: $BRANCH ($(git rev-parse --short HEAD))"
|
||||||
|
info "Action: $ACTION"
|
||||||
|
info "Time: $(date -Iseconds)"
|
||||||
@@ -1,36 +1,34 @@
|
|||||||
-----BEGIN AGE ENCRYPTED FILE-----
|
-----BEGIN AGE ENCRYPTED FILE-----
|
||||||
YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IHNzaC1lZDI1NTE5IEdoTUQ4QSBWNEpt
|
YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IHNzaC1lZDI1NTE5IEdoTUQ4QSBOL29w
|
||||||
cGFNeVBBaDRqb3pLSEZGQW0wb3VmVnBoZCswUFkzbnBLUnJ0QTNrClRqVkk4RUVO
|
eGk1N2xxTHJtaUEvWWZmbkh1bk11Tjk3anNnMDB1cCtPYUMzdTNJCkdhQ08vblNG
|
||||||
d29KYjd5YUcwankvaTFmVHUxQVpDT2ZYWHRaY3JXTUtQMU0KLT4gKXBtQ3UsXi1n
|
UlV1K2xVTGZVTzFWYXAzcjZaMWs0RTFWdStKSmlSTURvK1EKLT4gLC1zKU8zVkgt
|
||||||
cmVhc2UgNnwxYCBXVyA/KCQmIHt9NAo3OTZVUHR2UXkvaEFwY0ZBdEJsaFpsbHJ0
|
Z3JlYXNlIFUiXFcpS302IHByVn5jOy0gRDMKQjV3SHpDWUIybGFyQUg3ZlR0R2hV
|
||||||
cklKcDVHcEdWMEdPSkpnN0FiRU43RW5hUWFMdjR3WFRRSFBLSGlmClM3cTNJWlNM
|
eWM3SFlCVW5mdlpBVUF3a0xpNlZCeGNUd1oxTTlkc1RkTXdZS0lFTmN3Ci0tLSA3
|
||||||
TExkdHdXUHJISkNIaE1TTUxUc1NUWkV1a09HeFU3bVZwQXMKLS0tIGhOcXFTUElS
|
VlBqM1VLWllZc0JnOTMvUFRjMU13OTdzMmhsdGJubkk5eGpERVVLYUk4Cnzh5UbU
|
||||||
azJJNnEreUhMWTJBaVZGSTJPRUFqQkVYS01KRENUVVpZSDgK8+8onFejroBo7MeO
|
FlgqpM8jkJ6XlsaIDCw/G3D6uJ/GRJW4gIekuhAUxpZJrc8eOA8ZuHfGrBbH3acV
|
||||||
dW+so4lOsq4zJKn3f0cxmCFg1f0X8zt6h4Uc3A5Cvr1uU+6yw1FWmJ7xa3jJz3lO
|
tVafX5F0Kr2oOblqZ6gduZOUS52KmWH8stiBJM+e5ZZ7zRQVE4PJUKUPCzi+WdcH
|
||||||
EEaKQJXYC+xIIKGcA7qILa0SFp4a/4OuYjcg27HrlPhg7u5wDhQrd0LdVEe1Xngp
|
zr295T//FOdicrYHdsjfziKEHzBtUCFiATW05+O2zMjYjO6cPzePcCzPWinwiID6
|
||||||
ZivX7P7HwIna3X8C+TL+K2v/AG2N/z86cdKfRvxyMKNbHhYw+CfHEnWgh8tJ++4h
|
V+f6ngfkkQaj3wBGkzaieQJzRcdSwky21aVhGCCX/bvqx61iW2d5QAKxGbtQ2RcG
|
||||||
G9evNniuNqte6cQaRe7jODfPNW4FuY/Sb7barlJ/M9iAQdYAdyLAzU1LABeHeUfD
|
X1okr+xunAM94nzDMv46vyN97KxY7cZd4pAaOxoICc2Tfhtw6F+iS6QkQh1odJzO
|
||||||
wtHjxy9DUZ55Vg8bB8M2JJU9MkoRT4ewiVd9LeC1GWeVmKsm93wsmrov714i7U2j
|
7ZH+sSQCvndG+8z9shXGiHalASF5tdguM+JlEvAGljcaiAUtsQWxr9CoWiEkC6c6
|
||||||
wHtDkjqEF2MmzuQc18sjNaAHiwz8j6o5xU2L/Q4+Q707yISWG7RGZYh389Cr1rnw
|
NCaECSYO8Il+SXBQnSZSGJSNDhuPYCYrsjXGSAONFixuyeslAkq9x2WUaUS4H063
|
||||||
siUq/Vunqw2wk13+J/4vu9nqt5mMktBaCtp+QiWIurjwB5LUAyChrSm+dg5lb0Mt
|
1QvRF7XO2tBPtgCLsSjdiGp0h+ImUaGdu6fDR7zrDsGsaAFCSFeH/rGNNXRQ2vP2
|
||||||
UhSc0lq1+E3vxAXM2Hmk+vP86VD+6WJvAU82VFApF1s6zG2FU1/AcOVVf54nan/q
|
CSfPfDDCqpUSCn0WuA30BtaPLxGmZT6OjFevKzYMNDmdeq9ia/q8K0hmjLUBdN3k
|
||||||
f+rgSFfASHQCYSblUJHyEtwLNsWEmTGmOEn1buUKD/H0zatPQnc0rYpjlx2V0Sjd
|
tdYWbwoaf4gYbUWxSleD768b0Jgxss9Vod+sFQ+NYRksdGIeyND+aQIc312XehfA
|
||||||
6yB5+wPrZ0AkN1pjcsPKOv8Kaog2DzqIjib+SaSTaRxWHQEb9uzvaReAcYI5HOpE
|
qHFBS8nlj7eUF5bdvCYQ64z741mH4cNlGxyjPBH1x8FHnEOocJXYt1l2AZSRJmJA
|
||||||
gkC040HN33BItATbo4+hz70Im8Ni/VXD+g6yzM6Hj1hJL+PinTKeg5keQRFIZjMx
|
c3z0QGXyuCbsrLBXWK1EKa/Juo4PGGsEVoLRhwJAQy9+i1JN0yrfRvSPyzvD4px6
|
||||||
grzievB2wVBBgLgN3qMdTFmpplaL7iL702JjXZUTTK9Izp+9wiCsV1fTa53FWDht
|
wRPzlZ80MQdb2lv84WS/zcOEZmZzlLntszTRRdIfAsuaavP2Rquh4rEXABYeTZwp
|
||||||
ylFL5SWElqXjK+QBXxAe+Jk6VQov5HI21YDXL67S554ABeRok23wxrQ31TCI4xq9
|
5dem79s8bdW2nFsGMNz1OQKQwocyjYu1jJMHu6Gp7Ngdl1xyW7xfg0dezE1c0cIh
|
||||||
PQV7VtNRjyVud7S29m3OwpWOsgTZhn+JclHj2v4bNJzJkJnZRTmcvGPktzRI5+R4
|
xt1aLER9YJp4n5to5cOH16l3mjDHnAvABx38xE9loNL3399J/evw7LxpTYQ4v2Xv
|
||||||
e5vxVhGnJDzI71txaHl8+xS1lu9VzCQUrxX6TXyTRV4KjIOz0g06JOBgmBRBvJca
|
x8xnDHcqJ+deFSwyuUnMS5DkUeYuHmUl0Q2WYcfY+ibCmcgCb2ObTtuN1/ZxNYrL
|
||||||
7MZbC65xpisl/gyLRbgkVga3t94dPV+dpZsn8eq6427IyRbKslJefatggR9//c6I
|
OKrnmfuSvBgyuIOj5e6uWW0+Zs8dHKXu2TgV8WignxOhl5zQgCpCBlqVfO0t+NCu
|
||||||
5N5fl0fR3gJQMB+HRbipBH2YsdbdWJyb4Nn6STZxIfrqoG/xC6C1raF0xK7hUx6i
|
Gi26hU/fhGWQ/1oQa3VkpGsypZbJpgQvfWxfcGHP/MMhnl01zzlP8/aexSY3pAxf
|
||||||
4DUDSPohM8fOIswQPfE+FH3eygfzu/Ln5+ghsgHTEhgFvmgMvyxaAt6kHIzIUhMX
|
fz9v0IVh6xxtu3zbiiVzUsXbfG7t+xY98jMphf4AS2mWva3GWVmhhu0lS3J3P+go
|
||||||
M3dASr4VPDpIXuXsRWwYLEifhzxsuvwVxfwtsnCaR6XKijsYECWGDdYOWHdleeqx
|
YEEP4rOFHeU0Y1/6kLydTXvz4jMH0H92XQIzshd7vzQnEJPUPAzqRmw3LKYGgCI+
|
||||||
wDPhxEesfFVhKxhrKY9Ir8k9/FFBKQU/3GjW4+SMAg5Al1YEzxshP9vKuVcsei7W
|
wZEnxJ6ckqTkGBFnxTpy9LLllwmnz2Ky87nY3XAmqxlhb2Ap1XFAlfgszmGjc+Il
|
||||||
JDwAwotNXaCm6NBckiyZJE53ou6+gckPY7V9cOfnuH74Z9ywkFzB3HW3ZlonaGyM
|
KkIgoWQHTUm6QM9ta++oUTIDneOvxGd0zZsqoEhiC/7E01BNNZ6E58TeJU3fDlA3
|
||||||
oGmLGcccavFtyhg5s/As4i6X8ARIpDiwe59Pn3GNXMctySqIrrr2ogUoXgrfFCie
|
mX6n05XjwPRpgXZfayPoAgBlZc2H4KeiynxwNZ/dWu7qz7L6Ppk6Nvtly8giTbFx
|
||||||
6GOTdeMW7GeOSdJUxCofghlspS/nq01Og77VI/beWYrIwLubSka6Zaltww9zgObk
|
CA+tto7vq+D+CAEJ4bgyq4BCH4GL4APrhPcWp98Mko1WCiRTIKgkZxQCYvlg/LZq
|
||||||
/FGEMgFkEpq7iyCvYSPA8F46pJKvnMP3S84AWCPmcTcHeg4lwGPvs6btexXBGdoz
|
LNhMacP9T1qTvNC+yR1NEMiegE3APzk6CkDpVaO9+5f/sqifNPINCMothenI9ePw
|
||||||
nkCyq7wdH5Nngm7jUbl88LtaLZPAQkuqXphBVTnrF9Ofbnb4iRZ2Op4xpx9rGyvx
|
zjQLI3Mo1m73bkomytUZ7i1VstP5sEZ5LF72Sq7BpR3oQ3Gp0CAN9w==
|
||||||
mO6UEhL6V1i2YZFNkNMg/W8aoMiUgBdqbkxaxblT9L0aNdlFU9+LbWYolURVEadd
|
|
||||||
Qjv0Z1gMA+tsuBbVszwsMfneZ5+B9Q==
|
|
||||||
-----END AGE ENCRYPTED FILE-----
|
-----END AGE ENCRYPTED FILE-----
|
||||||
|
|||||||
@@ -1,9 +0,0 @@
|
|||||||
-----BEGIN AGE ENCRYPTED FILE-----
|
|
||||||
YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IHNzaC1lZDI1NTE5IEdoTUQ4QSA3VG9Z
|
|
||||||
MVFPVFc2VVJ3d0h0dmtBUnI3WHl2SzUxTkRZbjFCaGloWmV3dnd3ClcxdnVPeGd6
|
|
||||||
SU4zR0Q0K1dtVjRRVHd0VW5XSFI0dVFpTjZnYk1DNjRxTVEKLT4gQzlgRy1ncmVh
|
|
||||||
c2UKeUozOWgyUytSTVF0NjY2STBEb2VadwotLS0gblI3bmJCUWxxU3QrYTEyVFBI
|
|
||||||
Snc4NC9rTkh0NnZYbUtxUE9hRWRkelpmMAq58fmH6cK13GeD7wGLxKmx10hmJeW4
|
|
||||||
b7KqnCD1ZP7uG85s32xzVRwRG8RrG4xZo5nR9Mrtg1CoTSFfUGeFnf5xveN+Ej0X
|
|
||||||
wDVB1LwC+Q==
|
|
||||||
-----END AGE ENCRYPTED FILE-----
|
|
||||||
@@ -1,11 +0,0 @@
|
|||||||
-----BEGIN AGE ENCRYPTED FILE-----
|
|
||||||
YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IHNzaC1lZDI1NTE5IEdoTUQ4QSA5dzVG
|
|
||||||
WUNvT3NlRmcrWS81bzJqSWlTekVYaDFFTE10SkI2dEgzaGpxcUI4Cmk5Y0FGYTRZ
|
|
||||||
K0NGYzY3VUp4aS9ZZGRmWTgybDJFUURva2pZNmVOS3QxdEUKLT4gPnVRTCtldGMt
|
|
||||||
Z3JlYXNlCk04OTJZeFRNeDI5aGpMVTk1ZTE0Y2FMMnFEMjlJalJpMHRlaTE4ZWIx
|
|
||||||
d2lCRGQ5RHVjcktOMGJCb1VERlNWcTYKaSt0L1Z6dVJ0QWIyZkhsYzFEVjZSQWUr
|
|
||||||
ZWpwVlo1TmhoUFJZdkEvR0gxNlVhcXF2ZTRnCi0tLSBLcmM2MThNVkdWclpHUXRr
|
|
||||||
VTF6QVk2WUZlTXpZMVNLMlpBOFc3M1o5WjZzCs9xbPlIX+u5vRSQ/z9utu+I9S2c
|
|
||||||
02DOsIb1kzxzb1OK91b8Kh4JucQSq3qkyEvRucsNn5QW8hIHDnRuND6EbPyN7p4S
|
|
||||||
YB/F0dxSqgnq
|
|
||||||
-----END AGE ENCRYPTED FILE-----
|
|
||||||
@@ -9,85 +9,6 @@
|
|||||||
openssh.authorizedKeys.keys = [
|
openssh.authorizedKeys.keys = [
|
||||||
keys.users.ai-worker.main
|
keys.users.ai-worker.main
|
||||||
];
|
];
|
||||||
# No password login - SSH key only
|
|
||||||
hashedPassword = "!";
|
|
||||||
};
|
};
|
||||||
users.groups.ai-worker = {};
|
users.groups.ai-worker = {};
|
||||||
|
|
||||||
# Enable restricted AI worker SSH access for ollama benchmarking
|
|
||||||
# SECURITY: ai-worker can only:
|
|
||||||
# - SSH into host from Hermes container
|
|
||||||
# - Run docker commands (docker exec ollama ...) via docker group
|
|
||||||
# - Run specific security audit commands
|
|
||||||
# - NO access to infra repo (no bind mount)
|
|
||||||
# - NO sudo access (no nh, nixos-rebuild, nixpkgs-fmt, nix)
|
|
||||||
# WORKFLOW: SSH from Hermes container, run docker benchmarks, return and save results to /opt/data/ai-optimizer/
|
|
||||||
services.aiWorkerAccess = true;
|
|
||||||
|
|
||||||
# Restricted sudo for ai-worker - security checks only
|
|
||||||
security.sudo.extraRules = [
|
|
||||||
{
|
|
||||||
users = [ "ai-worker" ];
|
|
||||||
commands = [
|
|
||||||
# Firewall checks
|
|
||||||
{
|
|
||||||
command = "/run/wrappers/bin/sudo iptables -L -n -v";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
{
|
|
||||||
command = "/run/wrappers/bin/sudo iptables -S";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
# Fail2ban status
|
|
||||||
{
|
|
||||||
command = "/run/current-system/sw/bin/fail2ban-client status";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
{
|
|
||||||
command = "/run/current-system/sw/bin/fail2ban-client status *";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
{
|
|
||||||
command = "/run/current-system/sw/bin/fail2ban-client get * banned";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
# Log inspection
|
|
||||||
{
|
|
||||||
command = "/run/current-system/sw/bin/journalctl -t kernel -n 100";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
{
|
|
||||||
command = "/run/current-system/sw/bin/journalctl -u fail2ban -n 50";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
{
|
|
||||||
command = "/run/current-system/sw/bin/journalctl -u firewall -n 50";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
# SSH config verification
|
|
||||||
{
|
|
||||||
command = "/run/current-system/sw/bin/sshd -T";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
# Docker service checks
|
|
||||||
{
|
|
||||||
command = "/run/current-system/sw/bin/docker ps";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
{
|
|
||||||
command = "/run/current-system/sw/bin/docker inspect *";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
# Network diagnostics
|
|
||||||
{
|
|
||||||
command = "/run/current-system/sw/bin/ss -tlnp";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
{
|
|
||||||
command = "/run/current-system/sw/bin/cat /proc/net/tcp";
|
|
||||||
options = [ "NOPASSWD" ];
|
|
||||||
}
|
|
||||||
];
|
|
||||||
}
|
|
||||||
];
|
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user