feat(redstone): wiki_recipe tool — extract recipe + thumbnail in one call

Adds a new MCP tool that parses minecraft.wiki's <table data-description=
"Crafting recipes"> directly, pulling the ingredients column out of each
row (e.g. "Block of Iron + Iron Ingot" for Anvil), then chases up the
page's main item thumbnail via prop=pageimages so the bot can deliver
text + a real image in one tool round.

Why a dedicated tool: minecraft.wiki does not host standalone "recipe.png"
files — recipes are rendered live as HTML grids composed from individual
BlockSprite icons. Filtering wiki_page_images for 'recipe' / 'craft' /
'grid' returned empty for every craftable item, leaving the model with
nothing to call tg_send_photo with. Confirmed by inspecting the Anvil
page's image inventory (Anvil1-6.png + GUI + sound files, no recipe).

Tool returns {
  title, page_url,
  recipes: [{ ingredients: "…" }, …],   // strips <br>/<a>/&nbsp; cleanly
  thumbnail_url,                          // for tg_send_photo
  note?,                                  // present when no recipe rows
}

Persona prompt tightened:
- wiki_recipe is now the FIRST call for "how do I craft X" / "recipe for X"
- wiki_page_images is downgraded to "specific non-thumbnail images only"
- IMAGE DELIVERY MANDATORY clause: must end the turn with tg_send_photo
  using a real URL or say plainly that no thumbnail was found — no more
  describing-the-image-in-prose-and-stopping failures.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-05-13 23:47:25 +02:00
parent 8ae89610f3
commit f1d4fb596a
2 changed files with 75 additions and 3 deletions

View File

@@ -102,6 +102,76 @@ export const minecraftWikiTools: Tool<z.ZodRawShape>[] = [
},
}),
tool({
name: "wiki_recipe",
title: "Get a crafting recipe from the Minecraft wiki",
description:
"Extracts the crafting recipe ingredient list from a wiki page (parses the live recipe table — minecraft.wiki renders recipes as HTML grids, not standalone images, so wiki_page_images is the wrong tool for recipe queries). Returns the ingredients string for each recipe variant, plus the page's main item thumbnail URL to send with tg_send_photo. Use this whenever a user asks 'how do I craft X' or 'recipe for X'.",
parameters: {
title: z.string().min(1).describe("Exact wiki page title — e.g. 'Anvil', 'Beacon', 'Crafting Table'. Use wiki_search first if unsure."),
},
handler: async ({ title }) => {
// 1. Parsed HTML — the recipe lives in a wikitable with data-description="Crafting recipes"
type ParseRes = { parse?: { title?: string; text?: string } };
const data = await wikiGet<ParseRes>({
action: "parse",
page: title,
prop: "text",
redirects: "1",
disableeditsection: "1",
});
const html = data.parse?.text ?? "";
if (!html) return { error: `no wiki page titled '${title}'` };
const resolvedTitle = data.parse?.title ?? title;
// 2. Find each crafting-recipes table and pull the first <td> (ingredients) of each data row.
const stripHtml = (s: string) =>
s.replace(/<br\s*\/?>/gi, " + ")
.replace(/<[^>]+>/g, "")
.replace(/&#160;|&nbsp;/g, " ")
.replace(/&amp;/g, "&")
.replace(/\s*\+\s*/g, " + ")
.replace(/\s+/g, " ")
.trim();
const tableRe = /<table\b[^>]*data-description="Crafting recipes"[^>]*>([\s\S]*?)<\/table>/g;
const recipes: { ingredients: string }[] = [];
let m: RegExpExecArray | null;
while ((m = tableRe.exec(html)) !== null) {
const rowRe = /<tr\b[^>]*>([\s\S]*?)<\/tr>/g;
let r: RegExpExecArray | null;
while ((r = rowRe.exec(m[1])) !== null) {
if (/<th\b/.test(r[1])) continue;
const td = /<td\b[^>]*>([\s\S]*?)<\/td>/.exec(r[1]);
if (!td) continue;
const text = stripHtml(td[1]);
if (text) recipes.push({ ingredients: text });
}
}
// 3. Pull the page thumbnail in a second query — gives the bot a URL to send.
type ThumbRes = { query?: { pages?: { title: string; thumbnail?: { source: string } }[] } };
const meta = await wikiGet<ThumbRes>({
action: "query",
prop: "pageimages",
titles: resolvedTitle,
piprop: "thumbnail",
pithumbsize: 600,
redirects: "1",
});
const thumbnail = meta.query?.pages?.[0]?.thumbnail?.source ?? null;
return {
title: resolvedTitle,
recipes, // [{ ingredients: "Block of Iron + Iron Ingot" }, ...]
thumbnail_url: thumbnail, // page's main item image — pass to tg_send_photo
page_url: pageUrl(resolvedTitle),
note: recipes.length === 0
? "No recipe table on this page — the item may be uncraftable, found only via loot/structure, or listed under a different page."
: undefined,
};
},
}),
tool({
name: "wiki_page_images",
title: "List images on a Minecraft wiki page (with full URLs)",