Merge pull request #5 from co-browser/docker-publish

chore: dockerfile + github package registry action

Author: maceip

.env.example

@@ -1 +1,2 @@
-OPENAI_API_KEY=sk
+OPENAI_API_KEY=sk
+CHROME_PATH=/usr/bin/chromium

.github/workflows/ci.yml

@@ -12,6 +12,8 @@ concurrency:
 
 env:
   PYTHON_VERSION: "3.13"
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
 
 jobs:
   determine_changes:
@@ -69,3 +71,47 @@ jobs:
 
       - name: "Validate project metadata"
         run: uvx --from 'validate-pyproject[all,store]' validate-pyproject pyproject.toml
+
+  build-and-publish:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+      packages: write
+      # attestations: write
+      id-token: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build and push Docker image
+        id: push
+        uses: docker/build-push-action@v6
+        with:
+          context: ./
+          file: ./Dockerfile
+          platforms: linux/amd64
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          build-args: |
+            VNC_PASSWORD=${{ secrets.VNC_PASSWORD }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

Dockerfile

@@ -0,0 +1,70 @@
+FROM ghcr.io/astral-sh/uv:bookworm-slim AS builder
+
+ARG VNC_PASSWORD=browser-use
+
+ENV UV_COMPILE_BYTECODE=1 \
+    UV_LINK_MODE=copy \
+    UV_PYTHON_INSTALL_DIR=/python \
+    UV_PYTHON_PREFERENCE=only-managed
+
+# Install build dependencies and clean up in the same layer
+RUN apt-get update -y && \
+    apt-get install --no-install-recommends -y clang && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install Python before the project for caching
+RUN uv python install 3.13
+
+WORKDIR /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --no-dev
+ADD . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen --no-dev
+
+FROM debian:bookworm-slim AS runtime
+
+# Install required packages including Chromium and clean up in the same layer
+RUN apt-get update && \
+    apt-get install --no-install-recommends -y \
+    xfce4 \
+    dbus-x11 \
+    tigervnc-standalone-server \
+    tigervnc-tools \
+    nodejs \
+    npm \
+    chromium \
+    chromium-driver \
+    fonts-freefont-ttf \
+    fonts-ipafont-gothic \
+    fonts-wqy-zenhei \
+    fonts-thai-tlwg \
+    fonts-kacst \
+    fonts-symbola \
+    fonts-noto-color-emoji && \
+    npm i -g proxy-login-automator && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/* && \
+    rm -rf /var/cache/apt/*
+
+# Copy only necessary files from builder
+COPY --from=builder --chown=python:python /python /python
+COPY --from=builder --chown=app:app /app /app
+
+ENV PATH="/app/.venv/bin:$PATH" \
+    DISPLAY=:0 \
+    CHROME_BIN=/usr/bin/chromium \
+    CHROMIUM_FLAGS="--no-sandbox --headless --disable-gpu --disable-software-rasterizer --disable-dev-shm-usage"
+
+# Combine VNC setup commands to reduce layers
+RUN mkdir -p ~/.vnc && \
+    echo ${VNC_PASSWORD} | vncpasswd -f > /root/.vnc/passwd && \
+    chmod 600 /root/.vnc/passwd && \
+    printf '#!/bin/sh\nunset SESSION_MANAGER\nunset DBUS_SESSION_BUS_ADDRESS\nstartxfce4' > /root/.vnc/xstartup && \
+    chmod +x /root/.vnc/xstartup && \
+    printf '#!/bin/bash\nvncserver -depth 24 -geometry 1920x1080 -localhost no -PasswordFile /root/.vnc/passwd :0\nproxy-login-automator\npython /app/server --transport sse --port 8000' > /app/boot.sh && \
+    chmod +x /app/boot.sh
+
+ENTRYPOINT ["/bin/bash", "/app/boot.sh"]

server/server.py

@@ -1,11 +1,12 @@
+import os
 import anyio
 import click
 import asyncio
 import uuid
 from datetime import datetime
 from langchain_openai import ChatOpenAI
 from browser_use import Agent
-from browser_use.browser.browser import Browser
+from browser_use.browser.browser import Browser, BrowserConfig
 import mcp.types as types
 from mcp.server.lowlevel import Server
 from dotenv import load_dotenv
@@ -31,7 +32,18 @@
 )
 
 # Initialize browser and context
-browser = Browser()
+browser = Browser(
+    config=BrowserConfig(
+        chrome_instance_path=os.environ.get("CHROME_PATH"),
+        extra_chromium_args=[
+            "--no-sandbox",
+            "--disable-gpu",
+            "--disable-software-rasterizer",
+            "--disable-dev-shm-usage",
+            "--remote-debugging-port=9222",
+        ],
+    )
+)
 context = BrowserContext(browser=browser, config=config)
 
 # Initialize LLM