fix: add startup permission fix for data volume (chown critical dirs on boot)

Reviewed-on: #16

ai/Dockerfile

@@ -0,0 +1,116 @@
+# 1. On récupère la version la plus récente d'UV
+FROM ghcr.io/astral-sh/uv:latest AS uv_source
+
+# 2. Image de base stable
+FROM debian:stable-slim
+
+# Disable Python stdout buffering to ensure logs are printed immediately
+ENV PYTHONUNBUFFERED=1
+
+# Install system dependencies in one layer, clear APT cache
+# tini reaps orphaned zombie processes (MCP stdio subprocesses, git, bun, etc.)
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+        build-essential python3 ripgrep ffmpeg gcc python3-dev libffi-dev procps git openssh-client docker-cli tini \
+        curl poppler-utils imagemagick \
+        texlive-latex-base texlive-latex-extra texlive-fonts-recommended texlive-xetex texlive-science \
+        qemu-user-static binfmt-support qemu-user-binfmt \
+        emacs-nox \
+        libportaudio2 \
+        ca-certificates && \
+    rm -rf /var/lib/apt/lists/*
+
+# Création de l'utilisateur 'hermes' directement avec les bons accès
+RUN useradd -u 10000 -m -d /opt/data hermes
+
+# Copie d'uv (dernière version)
+COPY --chmod=0755 --from=uv_source /uv /usr/local/bin/
+
+WORKDIR /opt/hermes
+
+# On donne la propriété du dossier de travail à l'utilisateur hermes
+RUN chown hermes:hermes /opt/hermes
+
+# ---------- Hermes venv ----------
+# Passer immédiatement sous l'utilisateur hermes pour tout le reste du build
+USER hermes
+
+# ---------- Source code ----------
+# On copie tout le projet d'un coup sans assumer la présence de fichiers de lock spécifiques
+COPY --chown=hermes:hermes . .
+
+# ---------- Python virtualenv avec Piper TTS ----------
+RUN uv venv && \
+    uv pip install --no-cache-dir piper-tts sounddevice numpy faster-whisper
+
+# ---------- Télécharger la voix Piper Ryan (high quality) ----------
+RUN mkdir -p /opt/hermes/.venv/share/piper/voices && \
+    /opt/hermes/.venv/bin/python3 /dev/stdin << 'PYEOF'
+import urllib.request
+base = '/opt/hermes/.venv/share/piper/voices'
+url = 'https://huggingface.co/rhasspy/piper-voices/resolve/main/en/en_US/ryan/high/en_US-ryan-high.onnx'
+urllib.request.urlretrieve(url, base + '/en_US-ryan-high.onnx')
+urllib.request.urlretrieve(url + '.json', base + '/en_US-ryan-high.onnx.json')
+PYEOF
+ 
+# ---------- Patch atomic writes to preserve file permissions ----------
+# Fixes https://github.com/NousResearch/hermes-agent/issues/14181
+# tempfile.mkstemp() creates files as 0600; os.replace() preserves that mode,
+# so group-readable files silently collapse to owner-private 0600.
+# This affects: skills, sessions, memories, and any file written atomically.
+RUN /opt/hermes/.venv/bin/python3 /dev/stdin << 'PYEOF'
+import os
+
+patches = [
+    ("/opt/hermes/tools/skill_manager_tool.py", [
+        ("# Restore existing file mode if present", True),  # already patched
+    ]),
+    ("/opt/hermes/tools/skills_sync.py", [
+        ("# Restore existing file mode if present", True),  # already patched
+    ]),
+]
+
+for fpath, checks in patches:
+    if not os.path.exists(fpath):
+        print(f"SKIP {fpath} (not found)")
+        continue
+    with open(fpath) as f:
+        code = f.read()
+    all_ok = all(marker in code for marker, _ in checks)
+    if all_ok:
+        print(f"OK {fpath} (already patched)")
+        continue
+    print(f"PATCH {fpath}")
+    # _atomic_write_text in skill_manager_tool.py
+    code = code.replace(
+        "        os.replace(temp_path, file_path)",
+        "        if file_path.exists():\n"
+        "            existing_mode = file_path.stat().st_mode\n"
+        "            os.chmod(temp_path, existing_mode)\n"
+        "        os.replace(temp_path, file_path)",
+    )
+    # _write_manifest in skills_sync.py
+    code = code.replace(
+        "            os.replace(tmp_path, MANIFEST_FILE)",
+        "            if MANIFEST_FILE.exists():\n"
+        "                existing_mode = MANIFEST_FILE.stat().st_mode\n"
+        "                os.chmod(tmp_path, existing_mode)\n"
+        "            os.replace(tmp_path, MANIFEST_FILE)",
+    )
+    with open(fpath, 'w') as f:
+        f.write(code)
+    print(f"DONE {fpath}")
+PYEOF
+
+# ---------- Runtime ----------
+ENV HERMES_HOME=/opt/data
+ENV PATH="/opt/data/.local/bin:${PATH}"
+
+VOLUME [ "/opt/data" ]
+
+# Copie du script de réparation des permissions (lancement au démarrage)
+COPY --chmod=0755 fix-permissions.sh /opt/hermes/fix-permissions.sh
+
+# Le conteneur tourne de manière ultra-sécurisée sous l'utilisateur hermes dès le départ
+# fix-permissions.sh chown les répertoires critiques avant de chaîner vers entrypoint.sh
+ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/fix-permissions.sh" ]

ai/compose.yml

@@ -1,32 +1,32 @@
 version: "3.8"
 services:
 
-  webui:
+  # webui:
-    image: ghcr.io/open-webui/open-webui:main
+  #   image: ghcr.io/open-webui/open-webui:main
-    volumes:
+  #   volumes:
-      - /mnt/HoardingCow_docker_data/Ollama/open-webui:/app/backend/data
+  #     - /mnt/HoardingCow_docker_data/Ollama/open-webui:/app/backend/data
-    restart: always
+  #   restart: always
-    environment:
+  #   environment:
-      - OLLAMA_API_BASE_URL=http://ollama:11434/api
+  #     - OLLAMA_API_BASE_URL=http://ollama:11434/api
-    networks:
+  #   networks:
-      - ai_net
+  #     - ai_net
-      - ai_backend
+  #     - ai_backend
-    labels:
+  #   labels:
-      - "traefik.enable=true"
+  #     - "traefik.enable=true"
 
-      # Router for HTTP + redirection to HTTPS
+  #     # Router for HTTP + redirection to HTTPS
-      - "traefik.http.routers.webui-http.rule=Host(`ai.lazyworkhorse.net`)"
+  #     - "traefik.http.routers.webui-http.rule=Host(`ai.lazyworkhorse.net`)"
-      - "traefik.http.routers.webui-http.entrypoints=web"
+  #     - "traefik.http.routers.webui-http.entrypoints=web"
-      - "traefik.http.routers.webui-http.middlewares=redirect-to-https"
+  #     - "traefik.http.routers.webui-http.middlewares=redirect-to-https"
 
-      # Router for HTTPS with TLS
+  #     # Router for HTTPS with TLS
-      - "traefik.http.routers.webui-https.rule=Host(`ai.lazyworkhorse.net`)"
+  #     - "traefik.http.routers.webui-https.rule=Host(`ai.lazyworkhorse.net`)"
-      - "traefik.http.routers.webui-https.entrypoints=websecure"
+  #     - "traefik.http.routers.webui-https.entrypoints=websecure"
-      - "traefik.http.routers.webui-https.tls=true"
+  #     - "traefik.http.routers.webui-https.tls=true"
-      - "traefik.http.routers.webui-https.tls.certresolver=njalla"
+  #     - "traefik.http.routers.webui-https.tls.certresolver=njalla"
 
   hermes:
-    image: nousresearch/hermes-agent:latest
+    build: ./
     container_name: hermes
     restart: always
     # Gateway run enables the internal API server on port 8642
@@ -39,6 +39,12 @@ services:
       - API_SERVER_KEY=hermes_local_key
       - GATEWAY_ALLOW_ALL_USERS=true
       - OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
+      # ROCm for GPU-accelerated faster-whisper STT
+      - HSA_OVERRIDE_GFX_VERSION=9.0.6
+      - HCC_AMDGPU_TARGET=gfx906
+      - HIP_VISIBLE_DEVICES=0,1
+      - ROCR_VISIBLE_DEVICES=0,1
+      - HSA_ENABLE_SDMA=0
     volumes:
       - /mnt/HoardingCow_docker_data/Hermes/data:/opt/data
     devices:

ai/fix-permissions.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+# Startup permission fix for the Hermes data volume.
+# Runs as root before the entrypoint drops to the hermes user.
+# Fixes files that were created by root (host agent, cron jobs, etc.)
+# becoming inaccessible to the hermes runtime user.
+set -e
+
+HERMES_HOME="${HERMES_HOME:-/opt/data}"
+
+# Fix ownership on critical writable directories so hermes user can access them
+chown -R hermes:hermes \
+  "$HERMES_HOME/sessions" \
+  "$HERMES_HOME/checkpoints" \
+  "$HERMES_HOME/skills" \
+  "$HERMES_HOME/memories" \
+  "$HERMES_HOME/workspace" \
+  "$HERMES_HOME/pastes" \
+  "$HERMES_HOME/logs" \
+  "$HERMES_HOME/cron" \
+  "$HERMES_HOME/plans" \
+  "$HERMES_HOME/hooks" \
+  "$HERMES_HOME/cache" \
+  2>/dev/null || true
+
+# Also fix the data volume root if it's wrong
+if [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$(id -u hermes)" ]; then
+  chown hermes:hermes "$HERMES_HOME" 2>/dev/null || true
+fi
+
+# Now chain to the real entrypoint
+exec /opt/hermes/docker/entrypoint.sh "$@"

ai/patch_tts_tool.py

@@ -0,0 +1,96 @@
+#!/usr/bin/env python3
+"""Patch Hermes TTS tool: remove Edge TTS, replace with Piper as default/fallback."""
+import sys
+
+tts_path = '/opt/hermes/tools/tts_tool.py'
+
+with open(tts_path) as f:
+    code = f.read()
+
+# Replace the Edge fallback with Piper fallback
+old_edge = '''        else:
+            # Default: Edge TTS (free), with NeuTTS as local fallback
+            edge_available = True
+            try:
+                _import_edge_tts()
+            except ImportError:
+                edge_available = False
+
+            if edge_available:
+                logger.info("Generating speech with Edge TTS...")
+                try:
+                    import concurrent.futures
+                    with concurrent.futures.ThreadPoolExecutor(max_workers=1) as pool:
+                        pool.submit(
+                            lambda: asyncio.run(_generate_edge_tts(text, file_str, tts_config))
+                        ).result(timeout=60)
+                except RuntimeError:
+                    asyncio.run(_generate_edge_tts(text, file_str, tts_config))
+            elif _check_neutts_available():
+                logger.info("Edge TTS not available, falling back to NeuTTS (local)...")
+                provider = "neutts"
+                _generate_neutts(text, file_str, tts_config)
+            else:
+                return json.dumps({
+                    "success": False,
+                    "error": "No TTS provider available. Install edge-tts (pip install edge-tts) "
+                             "or set up NeuTTS for local synthesis."
+                }, ensure_ascii=False)'''
+
+new_piper = '''        else:
+            # Default: Piper TTS (local, CPU, no cloud, no Microsoft)
+            piper_available = False
+            try:
+                piper_binary = "/opt/hermes/.venv/bin/piper"
+                piper_config = tts_config.get("piper", {})
+                voice = piper_config.get("voice", "en_US-lessac-medium")
+                model_dir = piper_config.get("model_dir", "/opt/hermes/.venv/share/piper/voices")
+                model_path = os.path.join(model_dir, f"{voice}.onnx")
+                if os.path.exists(model_path):
+                    piper_available = True
+            except Exception:
+                pass
+
+            if piper_available:
+                logger.info("Generating speech with Piper TTS (local, CPU)...")
+                import subprocess
+                piper_binary = "/opt/hermes/.venv/bin/piper"
+                piper_config = tts_config.get("piper", {})
+                voice = piper_config.get("voice", "en_US-lessac-medium")
+                model_dir = piper_config.get("model_dir", "/opt/hermes/.venv/share/piper/voices")
+                model_path = os.path.join(model_dir, f"{voice}.onnx")
+                cmd = [piper_binary, "--model", model_path, "--output-raw"]
+                proc = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+                raw_audio, stderr = proc.communicate(input=text.encode(), timeout=60)
+                if proc.returncode != 0:
+                    raise RuntimeError(f"Piper TTS failed: {stderr.decode()[:200]}")
+                ffmpeg_cmd = ["ffmpeg", "-f", "s16le", "-ar", "22050", "-ac", "1", "-i", "-", "-y", file_str]
+                subprocess.run(ffmpeg_cmd, input=raw_audio, capture_output=True, timeout=30)
+                logger.info("Piper TTS audio saved: %s", file_str)
+            else:
+                return json.dumps({
+                    "success": False,
+                    "error": "No TTS provider available. Install Piper TTS (pip install piper-tts) "
+                             "and download a voice model."
+                }, ensure_ascii=False)'''
+
+if old_edge in code:
+    code = code.replace(old_edge, new_piper)
+    print("Edge fallback replaced with Piper")
+else:
+    if 'Default: Piper TTS' in code:
+        print("Piper fallback already present")
+    else:
+        print("ERROR: Could not find Edge fallback in tts_tool.py")
+        # Debug output
+        import re
+        for m in re.finditer(r'        else:\n            # Default:', code):
+            start = max(0, m.start() - 100)
+            end = min(len(code), m.end() + 200)
+            print(f"Found else/default at position {m.start()}:")
+            print(code[start:end])
+        sys.exit(1)
+
+with open(tts_path, 'w') as f:
+    f.write(code)
+print("tts_tool.py patched successfully")

coms/compose.yml

@@ -1,15 +1,15 @@
 version: "3.9"
 services:
-  nomadnet:
+  # nomadnet:
-    image: ghcr.io/markqvist/nomadnet:master
+  #   image: ghcr.io/markqvist/nomadnet:master
-    container_name: nomadnet
+  #   container_name: nomadnet
-    restart: always
+  #   restart: always
-    volumes:
+  #   volumes:
-      - /mnt/HoardingCow_docker_data/Nomadnet:/root/.nomadnetwork
+  #     - /mnt/HoardingCow_docker_data/Nomadnet:/root/.nomadnetwork
-      - /mnt/HoardingCow_docker_data/Reticulum:/root/.reticulum
+  #     - /mnt/HoardingCow_docker_data/Reticulum:/root/.reticulum
-    # Reticulum transport must be reachable directly (NOT through Traefik)
+  #   # Reticulum transport must be reachable directly (NOT through Traefik)
-    ports:
+  #   ports:
-      - "4242:4242"
+  #     - "4242:4242"
 
   synapse:
     image: ghcr.io/element-hq/synapse:latest

network/compose.yml

@@ -13,17 +13,20 @@ services:
       - "--certificatesresolvers.njalla.acme.storage=/letsencrypt/acme.json"
       - "--certificatesresolvers.njalla.acme.httpchallenge.entrypoint=web"
 
-      - "--log.level=DEBUG"
+      - "--log.level=INFO"
+      - "--log.filepath=/var/log/traefik/traefik.log"
+      - "--accesslog.filepath=/var/log/traefik/access.log"
       - "--providers.docker=true"
       - "--providers.docker.exposedByDefault=false"
     ports:
       - "80:80"
       - "443:443"
     environment:
-      - NJALLA_TOKEN=${NJALLA_TOKEN}
+      - NJALLA_TOKEN=***
     volumes:
       - /var/run/docker.sock:/var/run/docker.sock:ro
       - /mnt/HoardingCow_docker_data/Traefik:/letsencrypt
+      - /var/log/traefik:/var/log/traefik
     restart: unless-stopped
     networks:
       - traefik_backend

vpn/compose.yml

@@ -0,0 +1,35 @@
+version: "3.8"
+
+services:
+  wireguard:
+    image: weejewel/wg-easy:latest
+    container_name: wireguard
+    cap_add:
+      - NET_ADMIN
+      - SYS_MODULE
+    environment:
+      - WG_HOST=vpn.lazyworkhorse.net
+      - PASSWORD=${WG_PASSWORD}
+      - WG_PORT=51820
+      - WG_DEFAULT_ADDRESS=10.8.0.x
+      - WG_DEFAULT_DNS=1.1.1.1,8.8.8.8
+      - WG_ALLOWED_IPS=0.0.0.0/0, ::/0
+      - WG_PERSISTENT_KEEPALIVE=25
+      - UI_TRAFFIC_STATS=true
+      - UI_CHART_TYPE=0
+    ports:
+      - "51820:51820/udp"
+      - "51821:51821/tcp"
+    volumes:
+      - /mnt/HoardingCow_docker_data/WireGuard:/etc/wireguard:rw
+    sysctls:
+      - net.ipv4.conf.all.src_valid_mark=1
+      - net.ipv4.ip_forward=1
+    restart: unless-stopped
+    networks:
+      - vpn_net
+
+networks:
+  vpn_net:
+    external: true
+    name: vpn_net