feat: BooCode 2.0 UI — Ember theme, brand banner, coder tabs, model-attribution chips

- Ember theme (Obsidian charcoal + #ff7a18 orange), now DEFAULT_THEME_ID; server theme_id whitelist gains 'ember'
- Brand banner: transparent Westie mascot + >_BooCode wordmark, big/edge-to-edge (flood-filled to transparency + cropped)
- Coder panes are multi-tab: + opens a BooCode tab, split opens a pane (shared ChatTabBar via tabKind + createCoderTab; closeOtherTabs/tab-numbering extended to coder)
- Model-attribution: new messages.model column stamped at finalizeCompletion (BooChat/native coder) + dispatcher assistant-row creation (external coder); surfaced via view + wire types + live frame; rendered as a subtle shortened-name chip (shortenModelName)
- Composer Web toggle moved into a boxed focus-ringed input; glowing accent dot on tool rows
- Claude SDK follow-ups (1M context, follow-up-message fix, collapsed thinking/tool chips) + CLAUDE_SDK_BACKEND=1

apps/web/src/api/types.ts

@@ -201,6 +201,9 @@ export interface Message {
   tokens_used: number | null;
   ctx_used: number | null;
   ctx_max: number | null;
+  // model-attribution: which model produced this assistant message (null for
+  // user/system rows + pre-attribution messages). Rendered as a chip.
+  model: string | null;
   started_at: string | null;
   finished_at: string | null;
   created_at: string;
@@ -351,7 +354,13 @@ export interface CoderMessageWire {
   role: 'user' | 'assistant' | 'system';
   content: string;
   status?: 'streaming' | 'complete' | 'failed';
+  // model-attribution: which model produced this coder assistant message.
+  model?: string | null;
   reasoning_text?: string;
+  // Context-window fill for the ContextBar (claude SDK turns set these from the
+  // SDK's reported window; other agents omit them). Read via the Message cast.
+  ctx_used?: number | null;
+  ctx_max?: number | null;
   tool_calls?: Array<{
     id: string;
     function: { name: string; arguments: string };
@@ -571,6 +580,8 @@ export type WsFrame =
       ctx_max?: number | null;
       started_at?: string | null;
       finished_at?: string | null;
+      // model-attribution: the model that produced this assistant message.
+      model?: string | null;
       // v1.8.2: piggybacks the persisted metadata onto the terminal frame so
       // cap-hit sentinels (and any future stamped-on-complete metadata) flow
       // to the client without a refetch.