feat(redstone): wiki_recipe_image — composite real recipe PNG and upload

Previous wiki_recipe only returned the page thumbnail, so "send me the
recipe image" delivered a picture of the item, not the recipe itself.
minecraft.wiki renders recipes as live HTML grids, not standalone PNGs,
so we now generate the image ourselves.

mcp/lib/minecraft-wiki-tools.ts:
- parseCraftingGrid(html): pulls the 3×3 input grid + result item URL
  from <span class="mcui mcui-Crafting_Table">. Each <span class="invslot">
  is either empty (chunk starts with </span>) or has an <img src="/images/
  Invicon_X.png?h">. Reading-order chunks → grid; first non-null after
  the 9th input slot → result.
- composeRecipePng(grid, result): fetches each unique sprite, resizes
  to 64×64 via sharp (nearest-neighbour to keep pixel art crisp),
  composites onto a #8b8b8b inventory-style background with #6f6f6f
  slot squares + dark borders, places an SVG-rendered "→" arrow,
  then the result cell next to it. PNG buffer returned.
- New tool wiki_recipe_image(title, chat, caption?) that runs the
  pipeline end-to-end and uploads via tg.sendPhotoBytes — one tool
  call, image already in the chat when it returns.

mcp/lib/types.ts:
- TgClient gains sendPhotoBytes({ chat_id, bytes, filename?, caption?,
  parse_mode?, reply_to_message_id? }). Multipart/form-data POST to
  sendPhoto, since Telegram's URL-mode can only fetch public URLs and
  the composited PNG only lives in memory. 30s timeout (vs the 20s on
  the JSON call) because uploads are bigger.

mcp/package.json + bot/package.json: add sharp ^0.33.5. mcp/ pulls it
in too so /mc/mcp/lib resolves it at the bot's runtime (the bot's
node_modules is at /app while the lib files live at /mc/mcp/lib).

Persona prompt: wiki_recipe_image is now the FIRST call for any
"recipe" / "send me the recipe image" request. Single tool turn ends
with the photo already in the chat. wiki_recipe stays as a fallback
when the page has no 3×3 crafting widget (smelting / brewing / smithing
use different mcui classes).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

mcp/lib/types.ts

@@ -7,6 +7,19 @@ import type { Database } from "bun:sqlite";
 
 export type TgClient = {
   call: <T = unknown>(method: string, params?: Record<string, unknown>) => Promise<T>;
+  /**
+   * Upload a binary photo to Telegram via multipart/form-data sendPhoto.
+   * Use for synthesized images (e.g. composited recipe grids) that don't
+   * live at a public URL Telegram can fetch itself.
+   */
+  sendPhotoBytes: (params: {
+    chat_id: number | string;
+    bytes: Uint8Array;
+    filename?: string;
+    caption?: string;
+    parse_mode?: "HTML" | "MarkdownV2";
+    reply_to_message_id?: number;
+  }) => Promise<{ message_id: number }>;
 };
 
 export function createTgClient(token: string): TgClient {
@@ -24,6 +37,24 @@ export function createTgClient(token: string): TgClient {
       if (!data.ok) throw new Error(`${method}: ${data.description} (code ${data.error_code})`);
       return data.result as T;
     },
+    async sendPhotoBytes({ chat_id, bytes, filename = "photo.png", caption, parse_mode, reply_to_message_id }) {
+      const fd = new FormData();
+      fd.set("chat_id", String(chat_id));
+      if (caption !== undefined) fd.set("caption", caption);
+      if (parse_mode !== undefined) fd.set("parse_mode", parse_mode);
+      if (reply_to_message_id !== undefined) {
+        fd.set("reply_parameters", JSON.stringify({ message_id: reply_to_message_id }));
+      }
+      fd.set("photo", new Blob([bytes], { type: "image/png" }), filename);
+      const res = await fetch(`${base}/sendPhoto`, {
+        method: "POST",
+        body: fd,
+        signal: AbortSignal.timeout(30_000),
+      });
+      const data = (await res.json()) as { ok: boolean; result?: { message_id: number }; description?: string; error_code?: number };
+      if (!data.ok) throw new Error(`sendPhoto(bytes): ${data.description} (code ${data.error_code})`);
+      return data.result!;
+    },
   };
 }