feat(browser): auto-snapshot on navigate, screenshot prompt guidance

Browser tool enhancements:
- Navigate action now auto-includes snapshot result, saving one LLM round-trip
- Wait for networkidle + 800ms after navigation for SPA/JS-rendered pages
- Prompt guides agent to screenshot key results and ask user for login/CAPTCHA help
- Fixed playwright version pinned to 1.52.0; mirror fallback to official CDN on failure

Web console file/image support:
- SSE real-time push for images and files via on_event (file_to_send)
- Added /api/file endpoint to serve local files for web preview
- Frontend renders images in media-content container (survives delta/done overwrites)
- File attachment cards with download links; RFC 5987 encoding for non-ASCII filenames

Tool workspace fix:
- Inject workspace_dir as cwd into send and browser tools (previously only file tools)
- Screenshots now save to ~/cow/tmp/ instead of project directory
This commit is contained in:
zhayujie
2026-03-29 19:09:11 +08:00
parent 511ee0bbaf
commit d09ae49287
8 changed files with 105 additions and 10 deletions

View File

@@ -271,10 +271,13 @@ class AgentBridge:
tool_manager.load_tools()
tools = []
workspace_dir = kwargs.get("workspace_dir")
for tool_name in tool_manager.tool_classes.keys():
try:
tool = tool_manager.create_tool(tool_name)
if tool:
if workspace_dir and hasattr(tool, 'cwd'):
tool.cwd = workspace_dir
tools.append(tool)
except Exception as e:
logger.warning(f"[AgentBridge] Failed to load tool {tool_name}: {e}")