Add browser automation tools and enhance environment configuration
- Introduced new browser automation tools in `browser_tool.py` for navigating, interacting with, and extracting content from web pages using the agent-browser CLI and Browserbase cloud execution. - Updated `.env.example` to include new configuration options for Browserbase API keys and session settings. - Enhanced `model_tools.py` and `toolsets.py` to integrate browser tools into the existing tool framework, ensuring consistent access across toolsets. - Updated `README.md` with setup instructions for browser tools and their usage examples. - Added new test script `test_modal_terminal.py` to validate Modal terminal backend functionality. - Improved `run_agent.py` to support browser tool integration and logging enhancements for better tracking of API responses.
This commit is contained in:
teknium
100
.env.example
100
.env.example
@@ -2,14 +2,15 @@
|
||||
# Copy this file to .env and fill in your API keys
|
||||
|
||||
# =============================================================================
|
||||
# LLM PROVIDER (OpenRouter - Primary)
|
||||
# LLM PROVIDER (OpenRouter)
|
||||
# =============================================================================
|
||||
# OpenRouter provides access to many models through one API
|
||||
# Get at: https://openrouter.ai/keys
|
||||
# All LLM calls go through OpenRouter - no direct provider keys needed
|
||||
# Get your key at: https://openrouter.ai/keys
|
||||
OPENROUTER_API_KEY=
|
||||
|
||||
# Default model to use (OpenRouter format: provider/model)
|
||||
# Examples: anthropic/claude-sonnet-4, openai/gpt-4o, google/gemini-2.0-flash
|
||||
# Examples: anthropic/claude-sonnet-4, openai/gpt-4o, google/gemini-2.0-flash, zhipuai/glm-4-plus
|
||||
LLM_MODEL=anthropic/claude-sonnet-4
|
||||
|
||||
# =============================================================================
|
||||
@@ -31,14 +32,17 @@ FAL_KEY=
|
||||
# =============================================================================
|
||||
# TERMINAL TOOL CONFIGURATION (mini-swe-agent backend)
|
||||
# =============================================================================
|
||||
# Backend type: "local", "docker", or "modal"
|
||||
# Backend type: "local", "singularity", "docker", or "modal"
|
||||
# - local: Runs directly on your machine (fastest, no isolation)
|
||||
# - docker: Runs in Docker containers (isolated, requires Docker installed)
|
||||
# - singularity: Runs in Apptainer/Singularity containers (HPC clusters, no root needed)
|
||||
# - docker: Runs in Docker containers (isolated, requires Docker + docker group)
|
||||
# - modal: Runs in Modal cloud sandboxes (scalable, requires Modal account)
|
||||
TERMINAL_ENV=docker
|
||||
TERMINAL_ENV=singularity
|
||||
|
||||
# Docker image to use (for docker and modal backends)
|
||||
TERMINAL_DOCKER_IMAGE=python:3.11-slim
|
||||
# Container images (for singularity/docker/modal backends)
|
||||
TERMINAL_DOCKER_IMAGE=python:3.11
|
||||
TERMINAL_SINGULARITY_IMAGE=docker://python:3.11
|
||||
TERMINAL_MODAL_IMAGE=python:3.11
|
||||
|
||||
# Working directory inside the container
|
||||
TERMINAL_CWD=/tmp
|
||||
@@ -57,6 +61,73 @@ TERMINAL_LIFETIME_SECONDS=300
|
||||
# This will authenticate via browser and store credentials locally.
|
||||
# No API key needed in .env - Modal handles auth automatically.
|
||||
|
||||
# =============================================================================
|
||||
# BROWSER TOOL CONFIGURATION (agent-browser + Browserbase)
|
||||
# =============================================================================
|
||||
# Browser automation requires Browserbase cloud service for remote browser execution.
|
||||
# This allows the agent to navigate websites, fill forms, and extract information.
|
||||
#
|
||||
# STEALTH MODES:
|
||||
# - Basic Stealth: ALWAYS active (random fingerprints, auto CAPTCHA solving)
|
||||
# - Advanced Stealth: Requires BROWSERBASE_ADVANCED_STEALTH=true (Scale Plan only)
|
||||
|
||||
# Browserbase API Key - Cloud browser execution
|
||||
# Get at: https://browserbase.com/
|
||||
BROWSERBASE_API_KEY=
|
||||
|
||||
# Browserbase Project ID - From your Browserbase dashboard
|
||||
BROWSERBASE_PROJECT_ID=
|
||||
|
||||
# Enable residential proxies for better CAPTCHA solving (default: true)
|
||||
# Routes traffic through residential IPs, significantly improves success rate
|
||||
BROWSERBASE_PROXIES=true
|
||||
|
||||
# Enable advanced stealth mode (default: false, requires Scale Plan)
|
||||
# Uses custom Chromium build to avoid bot detection altogether
|
||||
BROWSERBASE_ADVANCED_STEALTH=false
|
||||
|
||||
# Browser session timeout in seconds (optional, default: 300)
|
||||
# Sessions are cleaned up after this duration of inactivity
|
||||
BROWSER_SESSION_TIMEOUT=300
|
||||
|
||||
# =============================================================================
|
||||
# Browser automation requires Browserbase cloud service for remote browser execution.
|
||||
# This allows the agent to navigate websites, fill forms, and extract information.
|
||||
|
||||
# Browserbase API Key - Cloud browser execution
|
||||
# Get at: https://browserbase.com/
|
||||
BROWSERBASE_API_KEY=
|
||||
|
||||
# Browserbase Project ID - From your Browserbase dashboard
|
||||
BROWSERBASE_PROJECT_ID=
|
||||
|
||||
# Enable proxies for better CAPTCHA solving and anti-bot avoidance (default: true)
|
||||
# Proxies route traffic through residential IPs for more reliable access
|
||||
BROWSERBASE_PROXIES=true
|
||||
|
||||
# Enable advanced stealth mode (default: false, requires Scale Plan)
|
||||
# Uses custom Chromium build to avoid bot detection altogether
|
||||
BROWSERBASE_ADVANCED_STEALTH=false
|
||||
|
||||
# Browser session timeout in seconds (optional, default: 300)
|
||||
# Sessions are cleaned up after this duration of inactivity
|
||||
BROWSER_SESSION_TIMEOUT=300
|
||||
|
||||
# =============================================================================
|
||||
# Browser automation requires Browserbase cloud service for remote browser execution.
|
||||
# This allows the agent to navigate websites, fill forms, and extract information.
|
||||
|
||||
# Browserbase API Key - Cloud browser execution
|
||||
# Get at: https://browserbase.com/
|
||||
BROWSERBASE_API_KEY=
|
||||
|
||||
# Browserbase Project ID - From your Browserbase dashboard
|
||||
BROWSERBASE_PROJECT_ID=
|
||||
|
||||
# Browser session timeout in seconds (optional, default: 300)
|
||||
# Sessions are cleaned up after this duration of inactivity
|
||||
BROWSER_SESSION_TIMEOUT=300
|
||||
|
||||
# =============================================================================
|
||||
# LEGACY/OPTIONAL API KEYS
|
||||
# =============================================================================
|
||||
@@ -69,10 +140,6 @@ MORPH_API_KEY=
|
||||
HECATE_VM_LIFETIME_SECONDS=300
|
||||
HECATE_DEFAULT_SNAPSHOT_ID=snapshot_p5294qxt
|
||||
|
||||
# Direct provider keys (optional - OpenRouter is preferred)
|
||||
ANTHROPIC_API_KEY=
|
||||
OPENAI_API_KEY=
|
||||
|
||||
# =============================================================================
|
||||
# DEBUG OPTIONS
|
||||
# =============================================================================
|
||||
@@ -80,3 +147,12 @@ WEB_TOOLS_DEBUG=false
|
||||
VISION_TOOLS_DEBUG=false
|
||||
MOA_TOOLS_DEBUG=false
|
||||
IMAGE_TOOLS_DEBUG=false
|
||||
|
||||
# Scratch directory for Singularity sandboxes (optional)
|
||||
# If not set, uses /scratch (if available) or /tmp
|
||||
# Set this to a directory with lots of space for large pip installs
|
||||
# TERMINAL_SCRATCH_DIR=/scratch/myuser
|
||||
|
||||
# Disk usage warning threshold in GB (default: 500)
|
||||
# Warning is printed when total sandbox disk usage exceeds this
|
||||
TERMINAL_DISK_WARNING_GB=500
|
||||
|
||||
Reference in New Issue
Block a user