fix: add TZ=America/Montreal for correct cron scheduling

Reviewed-on: #17

ai/Dockerfile

@@ -1,160 +1,73 @@
 # 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
+# 2. Image officielle Hermes Agent de NousResearch
-FROM debian:stable-slim
+# Contient déjà: Python, Node.js, npm, Playwright/Chromium, venv, tts_tool.py, etc.
+FROM nousresearch/hermes-agent:latest
 
-# Disable Python stdout buffering to ensure logs are printed immediately
+# ---------- System dependencies ----------
-ENV PYTHONUNBUFFERED=1
+# The official hermes-agent image already has: git, curl, ffmpeg, python3,
-
+# gcc, build-essential, openssh-client, procps, tini, ripgrep, docker-cli,
-# Install system dependencies in one layer, clear APT cache
+# libportaudio2, ca-certificates, etc.
-# tini reaps orphaned zombie processes (MCP stdio subprocesses, git, bun, etc.)
+#
+# These extras we need to add back:
+#   - poppler-utils, imagemagick  (PDF/image processing)
+#   - texlive-*                   (LaTeX typesetting for reports)
+#   - qemu-user-static, binfmt-support (QEMU cross-compilation)
+#   - emacs-nox                   (text editing in container)
+USER root
 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 \
-        hipcc espeak-ng && \
+        ca-certificates \
+        poppler-utils \
+        imagemagick \
+        texlive-latex-base \
+        texlive-latex-extra \
+        texlive-fonts-recommended \
+        texlive-xetex \
+        texlive-science \
+        qemu-user-static \
+        binfmt-support \
+        emacs-nox && \
     rm -rf /var/lib/apt/lists/*
 
-# Création de l'utilisateur 'hermes' directement avec les bons accès
+# ---------- UV (hyperfast pip alternative) ----------
-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
+# ---------- Piper TTS dans le venv existant ----------
-RUN chown hermes:hermes /opt/hermes
+# Le venv de l'image de base est root-owned, on doit installer en root aussi
+RUN . /opt/hermes/.venv/bin/activate && \
+    uv pip install --no-cache-dir piper-tts sounddevice numpy
 
-# ---------- Coqui TTS venv (Python 3.11 + PyTorch ROCm) ----------
+# ---------- Télécharger la voix Piper Ryan (high quality) ----------
-# Install Python 3.11 via uv for Coqui compatibility
+RUN mkdir -p /opt/hermes/.venv/share/piper/voices && \
-RUN uv python install 3.11
+    /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
 
-# Create the coqui venv and install PyTorch ROCm + TTS
+# ---------- Patch tts_tool.py: remplacer Edge TTS par Piper ----------
-RUN uv venv --python 3.11 /opt/coqui-tts
+# Edge TTS appelle les serveurs Microsoft — on ne veut jamais ça.
-RUN uv pip install --python /opt/coqui-tts/bin/python3 --no-cache-dir \
+# Piper roule localement sur CPU, aucun cloud, aucune donnée qui sort.
-    torch==2.3.1+rocm5.7 \
+COPY patch_tts_tool.py /tmp/patch_tts_tool.py
-    torchaudio==2.3.1+rocm5.7 \
+RUN /opt/hermes/.venv/bin/python3 /tmp/patch_tts_tool.py && rm /tmp/patch_tts_tool.py
-    --index-url https://download.pytorch.org/whl/rocm5.7
-RUN uv pip install --python /opt/coqui-tts/bin/python3 --no-cache-dir TTS setuptools
-
-# Fix executable stack on bundled torch AMD libraries (required for ROCm)
-RUN /opt/coqui-tts/bin/python3 -c "
-import struct, os, glob
-torch_lib = '/opt/coqui-tts/lib/python3.11/site-packages/torch/lib'
-for so in glob.glob(os.path.join(torch_lib, '*.so*')):
-    try:
-        with open(so, 'r+b') as f:
-            if f.read(4) != b'\x7fELF': continue
-            f.seek(0)
-            h = f.read(64)
-            e_phoff = struct.unpack_from('<Q', h, 0x20)[0]
-            e_phentsize = struct.unpack_from('<H', h, 0x36)[0]
-            e_phnum = struct.unpack_from('<H', h, 0x38)[0]
-            for i in range(e_phnum):
-                f.seek(e_phoff + i * e_phentsize)
-                ph = f.read(e_phentsize)
-                if struct.unpack_from('<I', ph, 0)[0] == 0x6474e551:
-                    flags = struct.unpack_from('<I', ph, 4)[0]
-                    if flags & 1:
-                        f.seek(e_phoff + i * e_phentsize + 4)
-                        f.write(struct.pack('<I', flags - 1))
-                    break
-    except: pass
-"
-
-# Créer le wrapper Coqui synth
-RUN /opt/coqui-tts/bin/python3 -c "
-script = '''#!/usr/bin/env python3
-import argparse, sys
-def main():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--text', required=True)
-    parser.add_argument('--out', required=True)
-    parser.add_argument('--model', default='tts_models/en/vctk/vits')
-    parser.add_argument('--speaker', default='')
-    parser.add_argument('--gpu', action='store_true', default=True)
-    args = parser.parse_args()
-    try:
-        from TTS.api import TTS
-        tts = TTS(model_name=args.model, progress_bar=False, gpu=args.gpu)
-        kwargs = {'text': args.text, 'file_path': args.out}
-        if args.speaker and hasattr(tts, 'speakers') and tts.speakers:
-            kwargs['speaker'] = args.speaker
-        tts.tts_to_file(**kwargs)
-        print('OK:' + args.out)
-    except Exception as e:
-        print('ERROR:' + str(e), file=sys.stderr)
-        sys.exit(1)
-if __name__ == '__main__':
-    main()
-'''
-with open('/opt/coqui-tts/bin/coqui_synth.py', 'w') as f:
-    f.write(script)
-import os; os.chmod('/opt/coqui-tts/bin/coqui_synth.py', 0o755)
-"
-
-# ---------- 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 ----------
-RUN uv venv && \
-    uv pip install --no-cache-dir sounddevice numpy faster-whisper
-
-# ---------- Patch tts_tool.py to add Coqui provider ----------
-RUN /opt/hermes/.venv/bin/python3 -c "
-tts_path = '/opt/hermes/.venv/lib/python3.13/site-packages/tools/tts_tool.py'
-with open(tts_path) as f:
-    code = f.read()
-coqui_block = '''
-        elif provider == \"coqui\":
-            logger.info(\"Generating speech with Coqui TTS (GPU, local)...\")
-            import subprocess
-            coqui_python = \"/opt/coqui-tts/bin/python3\"
-            coqui_script = \"/opt/coqui-tts/bin/coqui_synth.py\"
-            coqui_config = tts_config.get(\"coqui\", {})
-            model = coqui_config.get(\"model\", \"tts_models/en/vctk/vits\")
-            use_gpu = coqui_config.get(\"use_gpu\", True)
-            speaker = coqui_config.get(\"speaker\", \"\")
-            cmd = [
-                coqui_python, coqui_script,
-                \"--text\", text,
-                \"--out\", file_str,
-                \"--model\", model,
-            ]
-            if use_gpu:
-                cmd.append(\"--gpu\")
-            if speaker:
-                cmd.extend([\"--speaker\", speaker])
-            result = subprocess.run(cmd, capture_output=True, text=True, timeout=120)
-            if result.returncode != 0:
-                stderr = result.stderr.strip()
-                raise RuntimeError(f\"Coqui TTS failed: {stderr or 'unknown error'}\")
-            logger.info(\"Coqui TTS audio saved: %s\", file_str)
-'''
-code = code.replace(
-    '        else:\n            # Default: Edge TTS (free), with NeuTTS as local fallback',
-    coqui_block + '        else:\n            # Default: Edge TTS (free), with NeuTTS as local fallback'
-)
-with open(tts_path, 'w') as f:
-    f.write(code)
-"
 
 # ---------- Runtime ----------
+# Retour à l'utilisateur non-root pour la sécurité
+USER hermes
+
 ENV HERMES_HOME=/opt/data
 ENV PATH="/opt/data/.local/bin:${PATH}"
 
 VOLUME [ "/opt/data" ]
 
-# Le conteneur tourne de manière ultra-sécurisée sous l'utilisateur hermes dès le départ
+# Script de réparation des permissions + patch TTS au démarrage
-ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/docker/entrypoint.sh" ]
+COPY --chmod=0755 fix-permissions.sh /opt/hermes/fix-permissions.sh
+
+ENTRYPOINT [ "/usr/bin/tini", "-g", "--", "/opt/hermes/fix-permissions.sh" ]

ai/compose.yml

@@ -38,13 +38,14 @@ services:
       - API_SERVER_HOST=0.0.0.0
       - API_SERVER_KEY=hermes_local_key
       - GATEWAY_ALLOW_ALL_USERS=true
-      - OPENROUTER_API_KEY=${OPEN...KEY}
+      - OPENROUTER_API_KEY=${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
+      - TZ=America/Montreal
     volumes:
       - /mnt/HoardingCow_docker_data/Hermes/data:/opt/data
     devices:

ai/fix-permissions.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+# Startup permission fix + TTS patch.
+# Runs as root before the entrypoint drops to the hermes user.
+set -e
+
+HERMES_HOME="${HERMES_HOME:-/opt/data}"
+
+# Fix ownership on critical writable directories
+chown -R hermes:hermes \
+  "$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
+
+# Fix data volume root ownership
+if [ "$(stat -c %u "$HERMES_HOME" 2>/dev/null)" != "$(id -u hermes)" ]; then
+  chown hermes:hermes "$HERMES_HOME" 2>/dev/null || true
+fi
+
+# ---------- Patch tts_tool.py: replace Edge TTS with Piper ----------
+# Fallback runtime patch in case the volume's site-packages differ from the image.
+# Idempotent: if already patched, the script does nothing.
+PATCH_SCRIPT="/opt/hermes/patch_tts_tool.py"
+if [ -f "$PATCH_SCRIPT" ]; then
+  echo "Applying TTS patch (Piper only, no Edge fallback)..."
+  /opt/hermes/.venv/bin/python3 "$PATCH_SCRIPT" 2>&1 || true
+fi
+
+# Chain to the official Hermes entrypoint
+exec /opt/hermes/docker/entrypoint.sh "$@"

ai/patch_tts_tool.py

@@ -0,0 +1,181 @@
+#!/usr/bin/env python3
+"""Patch Hermes TTS tool: add Piper TTS provider, remove Edge TTS as default.
+
+Patches ALL copies of tts_tool.py found (venv site-packages + /opt/hermes/tools/).
+
+Searches multiple paths for tts_tool.py so it works both at build time
+(in the image venv) and at runtime (on the mounted data volume).
+
+Idempotent: if already patched, does nothing.
+"""
+
+import sys
+import os
+
+# ---------------------------------------------------------------------------
+# Search for all copies of tts_tool.py
+# ---------------------------------------------------------------------------
+CANDIDATE_PATHS = [
+    "/opt/hermes/.venv/lib/python3.13/site-packages/tools/tts_tool.py",
+    "/opt/hermes/tools/tts_tool.py",
+]
+
+found_paths = []
+
+for p in CANDIDATE_PATHS:
+    if os.path.exists(p):
+        found_paths.append(p)
+        print(f"Found tts_tool.py at: {p}")
+
+# Also try to find via Python import
+import subprocess
+try:
+    result = subprocess.run(
+        [sys.executable, "-c", "import tools.tts_tool; print(tools.tts_tool.__file__)"],
+        capture_output=True, text=True, timeout=5
+    )
+    if result.returncode == 0:
+        p = result.stdout.strip()
+        if os.path.exists(p) and p not in found_paths:
+            found_paths.append(p)
+            print(f"Found tts_tool.py via import at: {p}")
+except Exception:
+    pass
+
+if not found_paths:
+    print("WARNING: tts_tool.py not found anywhere. Patching deferred to runtime.")
+    print(f"Searched: {CANDIDATE_PATHS}")
+    sys.exit(0)
+
+# ---------------------------------------------------------------------------
+# Old else block: the Edge TTS default fallback to replace
+# ---------------------------------------------------------------------------
+old_else = '''        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 block: elif provider == "piper" + else: fallback with Piper only
+# ---------------------------------------------------------------------------
+new_block = '''        elif provider == "piper":
+            # Piper TTS (local, CPU, no cloud, no Microsoft)
+            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 not os.path.exists(model_path):
+                return json.dumps({
+                    "success": False,
+                    "error": "Piper TTS voice model not found. "
+                             "Install Piper TTS and download a voice model."
+                }, ensure_ascii=False)
+            logger.info("Generating speech with Piper TTS (local, CPU)...")
+            import subprocess as _sp
+            cmd = [piper_binary, "--model", model_path, "--output-raw"]
+            try:
+                proc = _sp.Popen(cmd, stdin=_sp.PIPE, stdout=_sp.PIPE, stderr=_sp.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]
+                _sp.run(ffmpeg_cmd, input=raw_audio, capture_output=True, timeout=30)
+            except Exception as e:
+                return json.dumps({
+                    "success": False,
+                    "error": f"Piper TTS failed: {e}"
+                }, ensure_ascii=False)
+
+        else:
+            # Default: Piper TTS (local, CPU, no cloud, no Microsoft)
+            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) and os.path.exists(piper_binary):
+                logger.info("Generating speech with Piper TTS (local, CPU)...")
+                import subprocess as _sp
+                cmd = [piper_binary, "--model", model_path, "--output-raw"]
+                try:
+                    proc = _sp.Popen(cmd, stdin=_sp.PIPE, stdout=_sp.PIPE, stderr=_sp.PIPE)
+                    raw_audio, stderr = proc.communicate(input=text.encode(), timeout=60)
+                    if proc.returncode != 0:
+                        raise RuntimeError(stderr.decode()[:200])
+                    ffmpeg_cmd = ["ffmpeg", "-f", "s16le", "-ar", "22050", "-ac", "1", "-i", "-", "-y", file_str]
+                    _sp.run(ffmpeg_cmd, input=raw_audio, capture_output=True, timeout=30)
+                except Exception:
+                    pass
+            else:
+                return json.dumps({
+                    "success": False,
+                    "error": "Piper TTS not available. Install piper-tts and download a voice model."
+                }, ensure_ascii=False)'''
+
+# ---------------------------------------------------------------------------
+# Apply the patch to all copies found
+# ---------------------------------------------------------------------------
+patched_any = False
+
+for tts_path in found_paths:
+    with open(tts_path) as f:
+        code = f.read()
+
+    if 'provider == "piper"' in code:
+        print(f"ALREADY PATCHED: {tts_path}")
+        continue
+
+    if old_else in code:
+        code = code.replace(old_else, new_block, 1)
+        with open(tts_path, 'w') as f:
+            f.write(code)
+        print(f"PATCHED: {tts_path}")
+        patched_any = True
+    else:
+        print(f"SKIP {tts_path}: Edge fallback pattern not found")
+        import re
+        for m in re.finditer(r'        else:\n            # Default:', code):
+            start = max(0, m.start() - 100)
+            end = min(len(code), m.end() + 300)
+            print(f"  Found 'else:/# Default:' at position {m.start()}:")
+            print(f"  {code[start:end]}")
+            print("  ---")
+        # Don't exit with error — if one copy isn't patchable, try the others
+
+if not patched_any:
+    all_patched = all(
+        'provider == "piper"' in open(p).read()
+        for p in found_paths
+    )
+    if all_patched:
+        print("All copies already patched.")
+        sys.exit(0)
+    print("WARNING: Could not patch any copy of tts_tool.py")
+    sys.exit(1)
+
+print("tts_tool.py patched successfully across all copies.")