docker/hermes/Dockerfile

@@ -1,71 +1,24 @@
-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
+# Custom Hermes Agent image with voice support and ROCm for AMD GPU
+# Builds on upstream image and adds local STT capabilities
+FROM nousresearch/hermes-agent:latest AS base
 
-# 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.
+# Install system dependencies for audio capture
+USER root
 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/*
+        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
+# Install Python packages for voice support
+# Using uv for consistency with Hermes build process
+RUN uv pip install --no-cache-dir \
+    sounddevice \
+    numpy \
+    faster-whisper
 
-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/
+# Switch back to hermes user
+USER hermes
 
-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" ]
+# Health check for voice readiness
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
+    CMD python3 -c "import sounddevice, faster_whisper; print('voice deps OK')" || exit 1