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
2026-01-29 06:10:24 +00:00
parent 54ca0997ee
commit 248acf715e
12 changed files with 2626 additions and 134 deletions

View File

@@ -33,10 +33,16 @@ TOOLSETS = {
# Basic toolsets - individual tool categories
"web": {
"description": "Web research and content extraction tools",
"tools": ["web_search", "web_extract", "web_crawl"],
"tools": ["web_search", "web_extract"],
"includes": [] # No other toolsets included
},
"search": {
"description": "Web search only (no content extraction/scraping)",
"tools": ["web_search"],
"includes": []
},
"vision": {
"description": "Image analysis and vision tools",
"tools": ["vision_analyze"],
@@ -61,6 +67,17 @@ TOOLSETS = {
"includes": []
},
"browser": {
"description": "Browser automation for web interaction (navigate, click, type, scroll, iframes, hold-click) with web search for finding URLs",
"tools": [
"browser_navigate", "browser_snapshot", "browser_click",
"browser_type", "browser_scroll", "browser_back",
"browser_press", "browser_close", "browser_get_images",
"browser_vision", "web_search"
],
"includes": []
},
# Scenario-specific toolsets
"debugging": {