feat: a2ui interface to enablee the LLM to give structured information

PLAN.md

@@ -4,29 +4,7 @@ Only unfinished implementation work belongs here. DwarfStar remains the
 behavioral oracle for model execution, token processing, context accounting,
 KV-cache behavior, the HTTP API, and the built-in agent loop.
 
-## 1. Add A2UI local-chat surfaces
-
-- Use the public [A2UI protocol](https://a2ui.org/) as the normative reference.
-  Implement its versioned, streaming JSON messages and keep `../bDS2` only as
-  a reference for the research-oriented components and presentation we want.
-- Define a DS4Server catalog and native Iced renderer for the A2UI Basic Catalog
-  plus useful research surfaces such as charts, tables, metrics, timelines,
-  maps, mind maps, tabs, cards, lists, and forms.
-- Support `createSurface`, incremental `updateComponents` and `updateDataModel`
-  messages, and `deleteSurface`. The model must be able to add, replace, and
-  update components and data over multiple responses without recreating the
-  whole surface.
-- Persist A2UI messages with the chat and restore the resulting surfaces after
-  relaunch. Validate messages against the selected catalog, report validation
-  failures back to the model, and retain a readable fallback in the transcript.
-- Implement catalog-declared local functions and agent events. UI-local edits
-  update the surface immediately; agent events return the action and current
-  data to the conversation so the model can respond with further A2UI updates.
-  The existing approval flow applies only if the resulting agent turn invokes
-  an ordinary side-effecting tool such as shell or file mutation.
-- A2UI can be enabled/disabled in preferences to reduce the system prompt
-
-## 2. Finish native project and chat controls
+## 1. Finish native project and chat controls
 
 - Add functional File, View, and Help menus; update native menu enabled state
   from the focused control; complete undo/redo behavior; and make transcript
@@ -42,7 +20,7 @@ KV-cache behavior, the HTTP API, and the built-in agent loop.
 - the hellp menu must open a window with an actual documentation in it,
   that still needs to be constructed from the information and implementation
 
-## 3. Add Dev Brain support
+## 2. Add Dev Brain support
 
 - Let the user select one Obsidian vault and give the local agent bounded
   Markdown memory_search, memory_read, memory_create, and memory_append