Merge remote-tracking branch 'refs/remotes/upstream/main'

# Conflicts:
#	README.md
#	docker-compose.yml

Author: al-one

.dockerignore

@@ -1,2 +1,5 @@
 data
-tmp
+tmp
+results
+
+.env

.env.example

@@ -27,20 +27,27 @@ MOONSHOT_API_KEY=
 UNBOUND_ENDPOINT=https://api.getunbound.ai
 UNBOUND_API_KEY=
 
+SiliconFLOW_ENDPOINT=https://api.siliconflow.cn/v1/
+SiliconFLOW_API_KEY=
+
+IBM_ENDPOINT=https://us-south.ml.cloud.ibm.com
+IBM_API_KEY=
+IBM_PROJECT_ID=
+
 # Set to false to disable anonymized telemetry
 ANONYMIZED_TELEMETRY=false
 
 # LogLevel: Set to debug to enable verbose logging, set to result to get results only. Available: result | debug | info
 BROWSER_USE_LOGGING_LEVEL=info
 
-# Chrome settings
-CHROME_PATH=
-CHROME_USER_DATA=
-CHROME_DEBUGGING_PORT=9222
-CHROME_DEBUGGING_HOST=localhost
+# Browser settings
+BROWSER_PATH=
+BROWSER_USER_DATA=
+BROWSER_DEBUGGING_PORT=9222
+BROWSER_DEBUGGING_HOST=localhost
 # Set to true to keep browser open between AI tasks
-CHROME_PERSISTENT_SESSION=false
-CHROME_CDP=
+KEEP_BROWSER_OPEN=true
+BROWSER_CDP=
 # Display settings
 # Format: WIDTHxHEIGHTxDEPTH
 RESOLUTION=1920x1080x24

.gitignore

@@ -187,3 +187,6 @@ data/
 
 # For Config Files (Current Settings)
 .config.pkl
+*.pdf
+
+workflow

Dockerfile

@@ -1,5 +1,9 @@
 FROM python:3.11-slim
 
+# Set platform for multi-arch builds (Docker Buildx will set this)
+ARG TARGETPLATFORM
+ARG NODE_MAJOR=20
+
 # Install system dependencies
 RUN apt-get update && apt-get install -y \
     wget \
@@ -28,7 +32,6 @@ RUN apt-get update && apt-get install -y \
     fonts-liberation \
     dbus \
     xauth \
-    xvfb \
     x11vnc \
     tigervnc-tools \
     supervisor \
@@ -40,47 +43,58 @@ RUN apt-get update && apt-get install -y \
     fonts-dejavu \
     fonts-dejavu-core \
     fonts-dejavu-extra \
+    vim \
     && rm -rf /var/lib/apt/lists/*
 
 # Install noVNC
 RUN git clone https://github.com/novnc/noVNC.git /opt/novnc \
     && git clone https://github.com/novnc/websockify /opt/novnc/utils/websockify \
     && ln -s /opt/novnc/vnc.html /opt/novnc/index.html
 
-# Set platform for ARM64 compatibility
-ARG TARGETPLATFORM=linux/amd64
+# Install Node.js using NodeSource PPA
+RUN mkdir -p /etc/apt/keyrings \
+    && curl -fsSL https://deb.nodesource.com/gpgkey/nodesource-repo.gpg.key | gpg --dearmor -o /etc/apt/keyrings/nodesource.gpg \
+    && echo "deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesource.com/node_$NODE_MAJOR.x nodistro main" | tee /etc/apt/sources.list.d/nodesource.list \
+    && apt-get update \
+    && apt-get install nodejs -y \
+    && rm -rf /var/lib/apt/lists/*
+
+# Verify Node.js and npm installation (optional, but good for debugging)
+RUN node -v && npm -v && npx -v
 
 # Set up working directory
 WORKDIR /app
 
 # Copy requirements and install Python dependencies
 COPY requirements.txt .
+# Ensure 'patchright' is in your requirements.txt or install it directly
+# RUN pip install --no-cache-dir -r requirements.txt patchright # If not in requirements
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Install Playwright and browsers with system dependencies
-ENV PLAYWRIGHT_BROWSERS_PATH=/ms-playwright
-RUN playwright install --with-deps chromium
-RUN playwright install-deps
+# Install Patchright browsers and dependencies
+# Patchright documentation suggests PLAYWRIGHT_BROWSERS_PATH is still relevant
+# or that Patchright installs to a similar default location that Playwright would.
+# Let's assume Patchright respects PLAYWRIGHT_BROWSERS_PATH or its default install location is findable.
+ENV PLAYWRIGHT_BROWSERS_PATH=/ms-browsers
+RUN mkdir -p $PLAYWRIGHT_BROWSERS_PATH
+
+# Install recommended: Google Chrome (instead of just Chromium for better undetectability)
+# The 'patchright install chrome' command might download and place it.
+# The '--with-deps' equivalent for patchright install is to run 'patchright install-deps chrome' after.
+# RUN patchright install chrome --with-deps
+
+# Alternative: Install Chromium if Google Chrome is problematic in certain environments
+RUN patchright install chromium --with-deps
+
 
 # Copy the application code
 COPY . .
 
-# Set environment variables
-ENV PYTHONUNBUFFERED=1
-ENV BROWSER_USE_LOGGING_LEVEL=info
-ENV CHROME_PATH=/ms-playwright/chromium-*/chrome-linux/chrome
-ENV ANONYMIZED_TELEMETRY=false
-ENV DISPLAY=:99
-ENV RESOLUTION=1920x1080x24
-ENV VNC_PASSWORD=vncpassword
-ENV CHROME_PERSISTENT_SESSION=true
-ENV RESOLUTION_WIDTH=1920
-ENV RESOLUTION_HEIGHT=1080
-
 # Set up supervisor configuration
 RUN mkdir -p /var/log/supervisor
 COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
 
-EXPOSE 7788 6080 5901
+EXPOSE 7788 6080 5901 9222
 
 CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]
+#CMD ["/bin/bash"]