Unify figure store globally, enable cross-agent figure references

Add save_image tool to image agent

Fix tool message handling, parallel image refs, error display, and UX polish

Trim system prompts ~35% and strengthen figure embedding rule

Split frontend script.js (5460 lines) into 8 focused modules

Refactor backend: extract async stream helper, direct tool registry, nudge_for_result via call_llm

Debug panel: full LLM call parity, show_html tool, drag-drop file upload

Image agent fixes: sizing, error handling, result nudge, registry filtering

Fix image agent: multimodal tool responses, read_image rename, default model

Add abort/stop feature and agentui CLI command

UI design refinements: resizable sidebar, compact tabs, widget improvements

Improve web agent prompts, add chunked read_url, and UI refinements

Fix binary file download, add tool element tab persistence, and UI refinements

Add command center continuation, result nudge, input blocking, and prompt improvements

Improve agent routing prompts, add timeline inline labels, drop chat agent

Rename notebooks→agents, Productive→AgentUI across full codebase

Add IMAGE agent, web tools for AGENT, and fix conversation history

Centralize agent type registry into single source of truth