Merge branch 'master' into ai-worker-restricted-access

Reviewed-on: #28

AGENTS.md

@@ -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

docker/hermes/Dockerfile.full

@@ -0,0 +1,71 @@
+FROM ghcr.io/astral-sh/uv:0.11.6-python3.13-trixie@sha256:b3c543b6c4f23a5f2df22866bd7857e5d304b67a564f4feab6ac22044dde719b AS uv_source
+FROM tianon/gosu:1.19-trixie@sha256:3b176695959c71e123eb390d427efc665eeb561b1540e82679c15e992006b8b9 AS gosu_source
+FROM debian:13.4
+
+# Disable Python stdout buffering to ensure logs are printed immediately
+ENV PYTHONUNBUFFERED=1
+
+# Store Playwright browsers outside the volume mount so the build-time
+# install survives the /opt/data volume overlay at runtime.
+ENV PLAYWRIGHT_BROWSERS_PATH=/opt/hermes/.playwright
+
+# Install system dependencies in one layer, clear APT cache
+# tini reaps orphaned zombie processes (MCP stdio subprocesses, git, bun, etc.)
+# that would otherwise accumulate when hermes runs as PID 1. See #15012.
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+        build-essential nodejs npm python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli tini \
+        curl poppler-utils imagemagick \
+        chromium xvfb fonts-noto-color-emoji fonts-unifont fonts-liberation fonts-ipafont-gothic fonts-wqy-zenhei fonts-tlwg-loma-otf fonts-freefont-ttf \
+        libasound2t64 libatk-bridge2.0-0t64 libatk1.0-0t64 libatspi2.0-0t64 libcairo2 libcups2t64 libdbus-1-3 libdrm2 libgbm1 libglib2.0-0t64 libnspr4 libnss3 libpango-1.0-0 libx11-6 libxcb1 libxcomposite1 libxdamage1 libxext6 libxfixes3 libxkbcommon0 libxrandr2 \
+        texlive-latex-base texlive-latex-extra texlive-fonts-recommended texlive-xetex texlive-science \
+        qemu-user-static binfmt-support qemu-user-binfmt \
+        emacs-nox \
+        libportaudio2 && \
+    rm -rf /var/lib/apt/lists/*
+
+# Non-root user for runtime; UID can be overridden via HERMES_UID at runtime
+RUN useradd -u 10000 -m -d /opt/data hermes
+
+COPY --chmod=0755 --from=gosu_source /gosu /usr/local/bin/
+COPY --chmod=0755 --from=uv_source /usr/local/bin/uv /usr/local/bin/uvx /usr/local/bin/
+
+WORKDIR /opt/hermes
+
+# ---------- Layer-cached dependency install ----------
+# Copy only package manifests first so npm install + Playwright are cached
+# unless the lockfiles themselves change.
+COPY package.json package-lock.json ./
+COPY web/package.json web/package-lock.json web/
+
+RUN npm install --prefer-offline --no-audit && \
+    npx playwright install --with-deps chromium --only-shell && \
+    (cd web && npm install --prefer-offline --no-audit) && \
+    npm cache clean --force
+
+# ---------- Source code ----------
+# .dockerignore excludes node_modules, so the installs above survive.
+COPY --chown=hermes:hermes . .
+
+# Build web dashboard (Vite outputs to hermes_cli/web_dist/)
+RUN cd web && npm run build
+
+# ---------- Permissions ----------
+# Make install dir world-readable so any HERMES_UID can read it at runtime.
+# The venv needs to be traversable too.
+USER root
+RUN chmod -R a+rX /opt/hermes
+# Start as root so the entrypoint can usermod/groupmod + gosu.
+# If HERMES_UID is unset, the entrypoint drops to the default hermes user (10000).
+
+# ---------- Python virtualenv ----------
+RUN uv venv && \
+    uv pip install --no-cache-dir -e ".[all]" && \
+    uv pip install --no-cache-dir sounddevice numpy faster-whisper
+
+# ---------- Runtime ----------
+ENV HERMES_WEB_DIST=/opt/hermes/hermes_cli/web_dist
+ENV HERMES_HOME=/opt/data
+ENV PATH="/opt/data/.local/bin:${PATH}"
+VOLUME [ "/opt/data" ]
+ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/docker/entrypoint.sh" ]

hosts/lazyworkhorse/configuration.nix

@@ -158,7 +158,7 @@
     settings = {
       PasswordAuthentication = false;
       KbdInteractiveAuthentication = false;
-      PermitRootLogin = "prohibit-password"; 
+      # Additional hardening settings below in SERVER HARDENING section
     };
     hostKeys = [
       {
@@ -308,6 +308,196 @@
   # 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 = [
+      # Add UDP ports if required
+    ];
+    
+    # Rate limiting and attack prevention
+    extraCommands = ''
+      # Rate limit SSH connections (max 4 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 4 -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
+    '';
+  };
+
+  # 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 = 5;
+    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.

modules/nixos/services/ollama_init_custom_models.nix

@@ -14,8 +14,25 @@
         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..."
+          
+          # We use a custom TEMPLATE block to strip the 'currentDate' function 
+          # which is unsupported in Ollama 0.5.7 but present in Devstral's default manifest.
           ${pkgs.docker}/bin/docker exec ollama sh -c "cat <<EOF > /root/.ollama/$model_name.modelfile
 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
@@ -26,6 +43,7 @@ PARAMETER stop \"[/INST]\"
 PARAMETER stop \"</s>\"
 EOF"
           ${pkgs.docker}/bin/docker exec ollama ollama create "$model_name" -f "/root/.ollama/$model_name.modelfile"
+          ${pkgs.docker}/bin/docker exec ollama rm "/root/.ollama/$model_name.modelfile"
         else
           echo "$model_name already exists, skipping."
         fi
@@ -36,6 +54,10 @@ EOF"
       
       # Create Devstral
       create_model_if_missing "devstral-small-2:24b-128k" "devstral-small-2:24b" 
+      
+      # create_model_if_missing "qwen2.5-coder:32b-128k" "qwen2.5-coder:32b"
+      
+      # create_model_if_missing "mistral-large-planner:123b" "mistral-large:123b-instruct-v2407-q4_K_S"
     '';
     serviceConfig = {
       Type = "oneshot";

users/ai-worker.nix

@@ -18,8 +18,76 @@
   # 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" ];
+        }
+      ];
+    }
+  ];
 }