Compare commits

..

63 Commits

Author SHA1 Message Date
Robert
ef7f06166b Removed double file
Some checks failed
Build NixOS config / build (pull_request) Failing after 1s
2026-05-13 10:04:57 -04:00
Robert
e70516e78b Added access to the secret to version control 2026-05-13 10:03:14 -04:00
Robert
ce3a327ff7 The key changed apparently? it works with that one anyway 2026-05-13 10:01:58 -04:00
Robert
af38655170 Adding the runner key
Some checks failed
Build NixOS config / build (pull_request) Failing after 55s
2026-05-10 22:23:29 -04:00
dcf5ac6b5e fix: use nixos-builder label for NixOS CI 2026-05-10 22:15:53 -04:00
d78de94f94 feat: add NixOS build CI for infra PRs 2026-05-10 22:15:02 -04:00
28ab52209c Merge pull request 'Add restricted AI worker access with deployment capabilities' (#1) from ai-worker-restricted-access into master
Reviewed-on: #1
2026-05-11 00:48:29 +00:00
Robert
e6f7f0c263 Merge branch 'ai-worker-restricted-access' of ssh://code.lazyworkhorse.net:2222/gortium/infra into ai-worker-restricted-access 2026-05-10 18:06:46 -04:00
Robert
5c136e0765 Merge remote-tracking branch 'origin/master' into ai-worker-restricted-access 2026-05-10 17:06:58 -04:00
Robert
f722af7803 New ollama model creator module version 2026-05-10 16:56:09 -04:00
Robert
c07debf088 Added wireguard keys 2026-05-10 16:51:32 -04:00
6806898f04 feat: update compose submodule for ollama-gfx906 (v0.23.2) + add ollama Dockerfile 2026-05-10 10:12:34 -04:00
96e77c5ef2 Revert "feat: add ai-optimizer benchmark plan and state tracking for ollama GPU benchmarking"
This reverts commit ff7303cf6a.
2026-05-09 20:19:26 +00:00
ff7303cf6a feat: add ai-optimizer benchmark plan and state tracking for ollama GPU benchmarking 2026-05-09 20:13:08 +00:00
9e42f5d2cc Merge pull request 'feat(hermes): update compose submodule for Piper TTS' (#34) from feat/voice-support-v2 into master
Reviewed-on: #34
2026-05-09 19:40:05 +00:00
614883f3c3 fix: update compose submodule - startup permission fix for data volume 2026-05-09 16:04:39 +00:00
374d022593 fix: update compose submodule - permission fix for atomic writes 2026-05-09 15:50:42 +00:00
9679846cdb feat: update compose submodule - Ryan high voice 2026-05-09 15:21:59 +00:00
4056f91ec6 fix: update compose submodule - remove patch step 2026-05-09 14:28:44 +00:00
1ba7d31d2f fix: update compose submodule - patch path fix 2026-05-09 14:27:16 +00:00
c7e9f8a1e0 feat: update compose submodule for Norman voice 2026-05-09 14:20:55 +00:00
bbe1a4a850 fix: update compose submodule - ca-certificates 2026-05-09 14:15:01 +00:00
2b8316060c fix: update compose submodule - COPY path fix 2026-05-09 14:12:15 +00:00
cc2c62faf7 fix: update compose submodule - Dockerfile heredoc fix 2026-05-09 14:09:59 +00:00
47f1ba6cf2 fix: update compose submodule - clean patch script 2026-05-09 13:59:17 +00:00
db89881d75 fix: update compose submodule for full OPENROUTER_API_KEY 2026-05-09 13:55:47 +00:00
0bb0a270e6 fix: update compose submodule for clean Piper Dockerfile 2026-05-09 13:42:02 +00:00
41256ccbde fix: update compose submodule for Piper TTS (replaces Coqui/ROCm) 2026-05-09 13:24:17 +00:00
e551f0e5c5 feat: update compose submodule for ROCm + Coqui TTS Dockerfile 2026-05-09 04:10:05 +00:00
b11d599f37 fix: update compose submodule for simplified Dockerfile 2026-05-09 02:38:41 +00:00
782f2fa9ed feat(hermes): update compose submodule for ROCm GPU voice STT support 2026-05-09 00:22:08 +00:00
2e14069584 Merge pull request 'feat: add WireGuard VPN stack' (#33) from feat/wireguard-vpn into master
Reviewed-on: #33
2026-05-09 00:13:36 +00:00
c53460c400 fix: remove dns option from wireguard config (not a valid nixos option) 2026-05-05 03:26:44 +00:00
Robert
ee96593e3d Merge branch 'feat/wireguard-vpn' of ssh://code.lazyworkhorse.net:2222/gortium/infra into feat/wireguard-vpn 2026-05-04 23:22:35 -04:00
Robert
030125ab01 Added wireguard pass 2026-05-04 23:21:36 -04:00
Robert
5935747902 Security fixes 2026-05-04 23:20:57 -04:00
Robert
9ae0f6ad62 Submodule update 2026-05-04 23:20:03 -04:00
5c481d664a fix: split tunnel on host VPN - only route 10.8.0.0/24 2026-05-05 02:41:29 +00:00
94a7c7195a fix: remove exposed keys from comments 2026-05-05 02:12:55 +00:00
cf279c4fb0 feat: add host-level WireGuard client via networking.wireguard
- Add wg0 interface config with agenix-managed secrets
- Revert compose submodule to remove NET_ADMIN from Hermes
- WireGuard runs at host level, all containers inherit the tunnel
2026-05-05 02:11:41 +00:00
b9289a149d chore: update compose submodule for Hermes NET_ADMIN + WireGuard Dockerfile 2026-05-05 01:48:24 +00:00
e0068260cb chore: move Hermes Dockerfile to compose repo, add WireGuard tools
- Move Dockerfile.full from infra/docker/hermes to compose/ai/Dockerfile
- Add wireguard-tools and openresolv to Hermes image
- Remove stray docker/hermes directory from infra
2026-05-05 01:43:42 +00:00
a42b2ff65d chore: update compose submodule to wireguard-vpn (fix ref) 2026-05-05 01:21:34 +00:00
92bcf1cc04 chore: update compose submodule to wireguard-vpn 2026-05-05 01:21:19 +00:00
7d0b72a513 chore: update compose submodule to linuxserver/wireguard 2026-05-05 01:18:13 +00:00
48245518a1 fix: load iptables kernel modules for WireGuard NAT
wg-easy needs iptable_nat and iptable_filter to set up
masquerading for VPN traffic. These modules must be loaded
at boot for the container to access iptables.
2026-05-05 01:17:14 +00:00
1673a56439 feat: add WireGuard VPN stack
- Add vpn stack to services.dockerStacks
- Open UDP port 51820 for WireGuard protocol
- Update compose submodule to include vpn stack
2026-05-04 22:49:06 +00:00
Robert
7d3d072961 Merge branch 'master' into ai-worker-restricted-access 2026-05-03 05:28:39 -04:00
4cceab05d0 Merge pull request 'security: harden lazyworkhorse with firewall, fail2ban, SSH hardening' (#28) from feature/server-hardening-clean into master
Reviewed-on: #28
2026-05-03 09:11:56 +00:00
bcebf18676 fix: move filter into jail settings (NixOS submodule doesn't pass string filters) 2026-05-01 11:59:33 +00:00
0370d784a0 fix: http-botsearch logpath must be string, not list 2026-05-01 04:02:06 +00:00
260b2d2756 fix: restructure fail2ban jails per NixOS module - recidive in jails, settings attr, str bantime 2026-05-01 03:59:32 +00:00
2477acdfc7 fix: services.fail2ban top-level options - no findtime, maxretry lowercase 2026-05-01 03:57:21 +00:00
81c25d3f20 fix: use security.auditd instead of services.auditd 2026-05-01 03:55:09 +00:00
9b1f467db9 fix: remove invalid networking.firewall.defaultAllow option 2026-05-01 03:52:57 +00:00
65fa778b2b fix: add custom traefik fail2ban filters for http-auth and http-botsearch jails 2026-05-01 03:40:59 +00:00
5d3bbe99f3 chore: update compose submodule for traefik access logs 2026-05-01 03:33:34 +00:00
Robert
bcf5cadaa0 olllama template fix to remove currenttime 2026-04-30 21:54:47 -04:00
3e04ccc1e8 security: remove deployment commands from ai-worker sudo rules
ai-worker only needs security audit commands, not deployment access.

Removed:
- nh os switch
- nixos-rebuild switch

Kept:
- Firewall checks (iptables)
- Fail2ban status
- Log inspection (journalctl)
- SSH config (sshd -T)
- Docker service checks
- Network diagnostics
2026-04-30 17:46:39 +00:00
21bd4bb283 security: add restricted sudo for ai-worker with security audit commands
- Deployment: nh os switch, nixos-rebuild switch (flake path locked)
- Firewall checks: iptables -L, iptables -S
- Fail2ban: status, banned IPs
- Logs: journalctl for kernel and fail2ban
- SSH config: sshd -T for verification
- Docker: ps, inspect (service health)
- Network: ss -tlnp, /proc/net/tcp

All commands are whitelisted with NOPASSWD.
No shell access, no ALL command - principle of least privilege.
2026-04-30 17:46:39 +00:00
7994aad8d8 security: harden lazyworkhorse with firewall, fail2ban, SSH hardening
- Firewall (default deny):
  - Allow only essential ports: SSH(2424), Gitea(2222), HTTP(80), HTTPS(443)
  - Rate limit SSH (max 4 new connections/60s)
  - Rate limit HTTP/HTTPS (25/minute)
  - Drop invalid packets, log dropped packets

- Fail2ban (auto-ban attackers):
  - SSH jail: 3 strikes = 1 hour ban
  - HTTP auth failures: 5 strikes = 1 hour ban
  - HTTP scanning: 2 strikes = 2 hour ban
  - Recidive jail: repeat offenders = 1 week ban

- SSH hardening:
  - No root login
  - Max 3 auth tries, 5 sessions
  - 30s login grace time
  - No X11/TCP/agent forwarding
  - Verbose logging

- Kernel network hardening:
  - SYN flood protection (syncookies)
  - IP spoofing protection (rp_filter)
  - Disable source routing, redirects
  - Log martian packets
  - Connection tuning for high load

- Audit logging enabled

Ports commented for review (likely internal-only):
- 8000 (Portainer), 4242 (Coms), 5000/8087/8089 (TAK)
2026-04-30 17:46:39 +00:00
f0e21d95e4 fix: ai-worker docker-only access for ollama benchmarking
Remove infra repo bind mount and sudo access from ai-worker user.
Now ai-worker can only:
- SSH into host from Hermes container
- Run docker commands via docker group membership
- Execute ollama benchmarks via docker exec

Results saved to /opt/data/ai-optimizer/ in Hermes container.
2026-04-29 19:55:19 +00:00
18df45819d Add restricted AI worker access with deployment capabilities
- New module: modules/nixos/security/ai-worker-restricted.nix
  - Bind mount for infra repo access (RW)
  - Whitelisted sudo commands: nh, nixos-rebuild, nixpkgs-fmt, nix
  - Audit logging for infra changes
  - Documentation in README-ai-worker.md

- Updated users/ai-worker.nix:
  - Enable services.aiWorkerAccess
  - Lock password (SSH key only)
  - Security documentation comments

- Updated flake.nix:
  - Include new security module

SECURITY: AI must ask for user confirmation before running nh os switch
2026-04-28 15:34:38 +00:00
15 changed files with 599 additions and 885 deletions

View File

@@ -0,0 +1,33 @@
name: Build NixOS config
on:
pull_request:
branches: [ master ]
paths:
- '**.nix'
- 'flake.lock'
- 'secrets/**'
- 'hosts/**'
- 'modules/**'
push:
branches: [ master ]
paths:
- '**.nix'
- 'flake.lock'
- 'secrets/**'
- 'hosts/**'
- 'modules/**'
jobs:
build:
runs-on: nixos-builder
steps:
- name: Checkout
run: |
git clone -b "${{ github.head_ref || github.ref_name }}" \
https://gitea:${{ secrets.GITHUB_TOKEN }}@code.lazyworkhorse.net/gortium/infra.git .
git log --oneline -3
- name: Build NixOS config (lazyworkhorse)
run: |
nix --version
nh os build .#lazyworkhorse 2>&1

View File

@@ -5,6 +5,7 @@ This document outlines the development conventions for this NixOS-based infrastr
## Build & Deployment
- **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`.
## Linting & Formatting

View File

@@ -1,474 +0,0 @@
# 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)

View File

@@ -61,6 +61,7 @@
./modules/nixos/services/open_code_server.nix
./modules/nixos/services/ollama_init_custom_models.nix
./modules/nixos/services/openclaw_node.nix
./modules/nixos/security/ai-worker-restricted.nix
./users/gortium.nix
./users/ai-worker.nix
];

View File

@@ -36,7 +36,7 @@
"transparent_hugepage=always" # because mucho ram
];
# 2. Load the specific drivers found by sensors-detect
boot.kernelModules = [ "nct6775" "lm96163" ];
boot.kernelModules = [ "nct6775" "lm96163" "iptable_nat" "iptable_filter" ];
# 3. Force the nct6775 driver to recognize the chip if it's stubborn
boot.extraModprobeConfig = ''
options nct6775 force_id=0xd280
@@ -49,6 +49,26 @@
networking.networkmanager.enable = true; # Easiest to use and most distros use this by default.
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.
time.timeZone = "America/Montreal";
@@ -158,7 +178,7 @@
settings = {
PasswordAuthentication = false;
KbdInteractiveAuthentication = false;
PermitRootLogin = "prohibit-password";
# Additional hardening settings below in SERVER HARDENING section
};
hostKeys = [
{
@@ -171,6 +191,7 @@
services.dockerStacks = {
versioncontrol = {
path = self + "/assets/compose/versioncontrol";
envFile = config.age.secrets.containers_env.path;
ports = [ 2222 ];
};
@@ -221,6 +242,11 @@
path = self + "/assets/compose/homepage";
};
vpn = {
path = self + "/assets/compose/vpn";
envFile = config.age.secrets.containers_env.path;
};
# tak = {
# path = self + "/assets/compose/tak";
# };
@@ -264,6 +290,20 @@
mode = "0440";
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";
};
};
};
@@ -308,6 +348,203 @@
# Or disable the firewall altogether.
# 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 = 10;
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
# (/run/current-system/configuration.nix). This is useful in case you
# accidentally delete configuration.nix.

View File

@@ -0,0 +1,105 @@
# 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
```

View File

@@ -0,0 +1,17 @@
{ 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" ];
};
}

View File

@@ -1,45 +1,87 @@
{ pkgs, ... }: {
systemd.services.init-ollama-model = {
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" ];
script = ''
# Wait for Ollama
while ! ${pkgs.curl}/bin/curl -s http://localhost:11434/api/tags > /dev/null; do
sleep 2
done
# Fonction de création asynchrone pour ne pas bloquer le démarrage
(
echo "Starting asynchronous Ollama initialization..."
# Attente d'Ollama (maximum 120 secondes pour éviter une boucle infinie)
TIMEOUT=60
COUNT=0
while ! ${pkgs.curl}/bin/curl -s -f http://127.0.0.1:11434/api/tags > /dev/null; do
if [ $COUNT -ge $TIMEOUT ]; then
echo "Ollama did not become ready in time. Exiting."
exit 1
fi
echo "Waiting for Ollama API to be reachable..."
sleep 5
COUNT=$((COUNT + 5))
done
create_model_if_missing() {
local model_name=$1
local base_model=$2
if ! ${pkgs.docker}/bin/docker exec ollama ollama list | grep -q "$model_name"; then
echo "$model_name not found, creating from $base_model..."
${pkgs.docker}/bin/docker exec ollama sh -c "cat <<EOF > /root/.ollama/$model_name.modelfile
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
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_predict 4096
PARAMETER num_keep 1024
PARAMETER repeat_penalty 1.1
PARAMETER top_k 40
PARAMETER stop \"[INST]\"
PARAMETER stop \"[/INST]\"
PARAMETER stop \"</s>\"
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
}
PARAMETER stop "[INST]"
PARAMETER stop "[/INST]"
PARAMETER stop "</s>"
EOF
# Create Nemotron
create_model_if_missing "nemotron-3-nano:30b-128k" "nemotron-3-nano:30b"
# Create Devstral
create_model_if_missing "devstral-small-2:24b-128k" "devstral-small-2:24b"
# Copie et création dans le conteneur
${pkgs.docker}/bin/docker cp "$TMP_FILE" ollama:/tmp/model.modelfile
${pkgs.docker}/bin/docker exec ollama ollama create "$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_model_if_missing "nemotron-3-nano:30b-128k" "nemotron-3-nano:30b"
# Create Devstral
create_model_if_missing "devstral-small-2:24b-128k" "devstral-small-2:24b"
) &
'';
serviceConfig = {
Type = "oneshot";
RemainAfterExit = true;
Type = "forking"; # Permet à systemd de savoir que le script passe en arrière-plan via '&'
User = "root";
};
};
}

View File

@@ -1,63 +0,0 @@
# 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

View File

@@ -1,286 +0,0 @@
#!/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)"

View File

@@ -1,34 +1,36 @@
-----BEGIN AGE ENCRYPTED FILE-----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YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IHNzaC1lZDI1NTE5IEdoTUQ4QSBMcVY2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-----END AGE ENCRYPTED FILE-----

View File

@@ -0,0 +1,9 @@
-----BEGIN AGE ENCRYPTED FILE-----
YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IHNzaC1lZDI1NTE5IEdoTUQ4QSA3VG9Z
MVFPVFc2VVJ3d0h0dmtBUnI3WHl2SzUxTkRZbjFCaGloWmV3dnd3ClcxdnVPeGd6
SU4zR0Q0K1dtVjRRVHd0VW5XSFI0dVFpTjZnYk1DNjRxTVEKLT4gQzlgRy1ncmVh
c2UKeUozOWgyUytSTVF0NjY2STBEb2VadwotLS0gblI3bmJCUWxxU3QrYTEyVFBI
Snc4NC9rTkh0NnZYbUtxUE9hRWRkelpmMAq58fmH6cK13GeD7wGLxKmx10hmJeW4
b7KqnCD1ZP7uG85s32xzVRwRG8RrG4xZo5nR9Mrtg1CoTSFfUGeFnf5xveN+Ej0X
wDVB1LwC+Q==
-----END AGE ENCRYPTED FILE-----

View File

@@ -0,0 +1,11 @@
-----BEGIN AGE ENCRYPTED FILE-----
YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IHNzaC1lZDI1NTE5IEdoTUQ4QSA5dzVG
WUNvT3NlRmcrWS81bzJqSWlTekVYaDFFTE10SkI2dEgzaGpxcUI4Cmk5Y0FGYTRZ
K0NGYzY3VUp4aS9ZZGRmWTgybDJFUURva2pZNmVOS3QxdEUKLT4gPnVRTCtldGMt
Z3JlYXNlCk04OTJZeFRNeDI5aGpMVTk1ZTE0Y2FMMnFEMjlJalJpMHRlaTE4ZWIx
d2lCRGQ5RHVjcktOMGJCb1VERlNWcTYKaSt0L1Z6dVJ0QWIyZkhsYzFEVjZSQWUr
ZWpwVlo1TmhoUFJZdkEvR0gxNlVhcXF2ZTRnCi0tLSBLcmM2MThNVkdWclpHUXRr
VTF6QVk2WUZlTXpZMVNLMlpBOFc3M1o5WjZzCs9xbPlIX+u5vRSQ/z9utu+I9S2c
02DOsIb1kzxzb1OK91b8Kh4JucQSq3qkyEvRucsNn5QW8hIHDnRuND6EbPyN7p4S
YB/F0dxSqgnq
-----END AGE ENCRYPTED FILE-----

View File

@@ -9,6 +9,85 @@
openssh.authorizedKeys.keys = [
keys.users.ai-worker.main
];
# No password login - SSH key only
hashedPassword = "!";
};
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" ];
}
];
}
];
}