Deep Research Mode, Enhanced Workflow Controls, and Cloud Onboarding Improvements

Introducing deep research capabilities for complex analytical workflows:

Multi-Step Research Plans - Agents can now autonomously plan and execute comprehensive research workflows with multiple transition types
Structured Research Flow - Define research workflows with start, transitions, and end configurations for query, visualization, and insight generation
Block-Based Message Architecture - Refactored message storage to support rich, structured content blocks for better research output organization
Integrated Thread Display - Seamlessly view research progress and results within conversation threads Deep research mode enables agents to conduct thorough analysis by combining data queries, visualizations, and insights into cohesive research outputs.

Example transition types:

query - Execute analytical queries against databases
visualize - Generate data visualizations
insight - Synthesize findings and generate insights An example of deep research can be[ found in our repo

Improved interaction with workflow execution logs:

Expand/Collapse All - Toggle visibility of all log items simultaneously with centralized state management
Copy Functionality - Copy individual log items or all logs at once with dedicated copy buttons
Better Log Management - Enhanced user control over large workflow execution outputs

GitHub App Webhook Fix - Resolved onboarding issue in cloud mode where users were blocked if GitHub app was installed before deployment
Workflow Output UX - Added header controls for batch operations on workflow logs
Rust and Dependencies Update - Updated to latest Rust version and upgraded all dependencies for improved performance and security