feat: Slice 1 polish - MiMo V2.5 model, visible reasoning, image attachments, mobile keyboard fix

- Switch conversation agent to xiaomi/mimo-v2.5 (multimodal: text + image)
- Render native reasoning parts as live 'Thinking trace' (streaming open,
  collapsed after completion); inline <think> extraction for streaming models
- Image attachments: picker (up to 4, 10MB each), base64 to Flue
  AgentPromptImage, authenticated blob-URL replay for historical images
- Mobile keyboard viewport fix: visual-viewport hook, fixed shell,
  interactive-widget=resizes-content, header pinned, composer follows keyboard
- Conversation to Signal to proposed Work: Convex persistence, Effect
  validation in @code/work-os, Work cards with exact source provenance
- Streamdown markdown + Mermaid chart rendering in chat messages
- Flue tool turns hidden, reasoning-containing turns remain visible
- Frontend regression tests: keyboard viewport, responsive shell,
  attachment overflow, authenticated images, reasoning traces, transforms
- .env.example updated to xiaomi/mimo-v2.5 config

packages/backend/convex/_generated/api.d.ts

@@ -30,6 +30,7 @@ import type * as signalRouting from "../signalRouting.js";
 import type * as signals from "../signals.js";
 import type * as todos from "../todos.js";
 import type * as workflows from "../workflows.js";
+import type * as works from "../works.js";
 
 import type {
   ApiFromModules,
@@ -60,6 +61,7 @@ declare const fullApi: ApiFromModules<{
   signals: typeof signals;
   todos: typeof todos;
   workflows: typeof workflows;
+  works: typeof works;
 }>;
 
 /**