hermoso 0.1.2 → 0.1.3

package/mcp/tools.mjs

@@ -169,6 +169,52 @@ export function registerTools(server) {
     return okVideo(`Ad video ready: ${r.url}${r.model ? `  (${r.model})` : ''}  [job ${r.jobId}]\n${notes || ''}`, r);
   }));
 
+
+  server.registerTool('make_template_ad', {
+    description: "Render a NATIVE-STYLE TEMPLATE ad from pure HTML — no AI video/image model in the loop, renders in ~30 seconds for a couple of credits. Perfect for native-feel social ads at volume. YOU author the content (short, casual, believable — never marketing-speak). Templates (pass as config.template): 'imessage-chat' (VIDEO ~15s: a real-looking iMessage thread where a friend reveals the product as a rich-link card; config: { thread: { contactName, messages: [{from:'them'|'me', text?, product?:{image,title,domain}}] }, theme?:'dark'|'light', endCard:{headline,cta,domain,logo?,color} } — 4-6 short lowercase bubbles, product card mid-thread from 'me', 1-2 excited replies after); 'chatgpt-chat' (VIDEO: a ChatGPT answer streams the punchline; config: { question, answer (may **bold** the brand), productImage?, endCard }); 'apple-notes' (VIDEO: an iPhone note types itself out; config: { title, lines: string[], theme?, endCard }); 'value-prop' (VIDEO ~17s kinetic typography: config: { hook, claims: string[] (3-5, ≤4 words each), productImages: string[], palette: string[], endCard }); 'static-mockup' (IMAGE: config: { style:'imessage'|'notes'|'card', size?:{w,h}, ...style fields }); 'airdrop-carousel' (VIDEO ~10s: an iOS AirDrop share card springs up and cycles 3-16 REAL product photos to a full-lineup payoff; config: { brandName, products: [{image, title?}], contactLine?, endCard }); 'app-ui-tour' (VIDEO ~12-16s for APP brands: floating-iPhone mockup walks through REAL app screenshots with kinetic captions; config: { hook?, appName, iconImage?, beats: [{screenImage, caption}] (2-6), palette?, fontStack?, endCard }); 'imessage-cascade' (VIDEO ~12s: iOS notification banners spring in and stack over a blurred backdrop; config: { notifications: [{sender, text}] (4-8), backgroundImage?, endCard }). Image URLs may be any public URL — the server localizes them. Spends a couple of credits.",
+    inputSchema: {
+      config: z.object({}).passthrough().describe("the template config — MUST include config.template (one of the template ids above) plus that template's fields"),
+    },
+    annotations: { readOnlyHint: false, destructiveHint: false, openWorldHint: true },
+  }, wrap(async (a) => {
+    const r = await renderJob('templatead', { config: a.config }, 'MCP template ad');
+    if (r?.raw?.image || /\.png($|\?)/.test(r?.url || '')) { const img = r?.url ? await imageBlock(r.url) : null; return { content: [{ type: 'text', text: `Template ad ready: ${r.url}  [job ${r.jobId}]` }, ...(img ? [img] : [])], structuredContent: r ?? undefined }; }
+    return okVideo(`Template ad ready: ${r.url}${r.model ? `  (${r.model})` : ''}  [job ${r.jobId}]`, r);
+  }));
+
+  server.registerTool('finish_video', {
+    description: "Post-process an EXISTING rendered video (its served mp4 URL) with the proven direct-response 'reviewer' finish and/or a film-grain pass — no AI model, ~30s, a couple of credits. pills=true composites a header pill (e.g. '10/10 would buy again'), a brand-accent sub-pill, and 3-4 green-check proof pills cascading in on the beat (YOU author the copy: header ≤40 chars, sub ≤34, each point ≤44 — concrete real benefits, never fabricated stats). grain=true applies a subtle camera-grain finish that makes photoreal AI renders look phone-shot ('less AI') — works alone or with pills. Returns a NEW video; the original is untouched.",
+    inputSchema: {
+      videoUrl: z.string().describe('the served URL of the video to finish (from a previous render/job)'),
+      header: z.string().optional().describe('header pill copy, ≤40 chars (required when pills is on)'),
+      sub: z.string().optional().describe('accent sub-pill copy, ≤34 chars (usually the product/brand)'),
+      points: z.array(z.string()).optional().describe('3-4 proof points, ≤44 chars each'),
+      accent: z.string().optional().describe('brand accent hex for the sub-pill'),
+      pills: z.boolean().optional().describe('default true — set false for a grain-only pass'),
+      grain: z.boolean().optional().describe('default false — anti-AI film-grain finish'),
+    },
+    annotations: { readOnlyHint: false, destructiveHint: false, openWorldHint: true },
+  }, wrap(async (a) => {
+    const r = await renderJob('videofinish', { videoUrl: a.videoUrl, header: a.header, sub: a.sub, points: a.points, accent: a.accent, pills: a.pills !== false, grain: !!a.grain }, 'MCP video finish');
+    return okVideo(`Finished video ready: ${r.url}  [job ${r.jobId}]`, r);
+  }));
+
+  server.registerTool('fix_beat', {
+    description: "Surgically re-render ONE time window (1.5-8s) of an existing rendered video and splice it back on the VIDEO TRACK ONLY — the rest of the video and ALL audio stay byte-identical. Use when one beat/shot is broken ('the shot at 8 seconds glitches') and a full re-render would waste the parts that worked; bills only the replacement clip's seconds (~1/3 of a full render). Do NOT pick a window covering spoken dialogue (a video-only splice under speech breaks lip-sync) — pass speechWindows to enforce this.",
+    inputSchema: {
+      videoUrl: z.string().describe('the served URL of the master video to fix'),
+      startSeconds: z.number().describe('window start in seconds'),
+      endSeconds: z.number().describe('window end in seconds (window 1.5-8s)'),
+      prompt: z.string().describe('what the replacement footage should show — describe the shot, matching the master\'s style'),
+      refImage: z.string().optional().describe('optional product/style anchor image URL'),
+      speechWindows: z.array(z.array(z.number())).optional().describe('[[start,end],...] windows with spoken lines — the fix window must not overlap these'),
+    },
+    annotations: { readOnlyHint: false, destructiveHint: false, openWorldHint: true },
+  }, wrap(async (a) => {
+    const r = await renderJob('fixbeat', { videoUrl: a.videoUrl, startSeconds: a.startSeconds, endSeconds: a.endSeconds, prompt: a.prompt, refImage: a.refImage, speechWindows: a.speechWindows }, 'MCP fix beat');
+    return okVideo(`Fixed beat spliced in: ${r.url}  [job ${r.jobId}]`, r);
+  }));
+
   server.registerTool('generate_video', {
     description: 'Render a RAW video clip from your own prompt and return its served mp4 URL. For finished brand ADS prefer render_ad (it runs the Studio quality pipeline — composited text, clean speech, end card, music); use this for raw/experimental clips or precise manual control. ONE generation = one continuous clip up to the model’s longest listed duration (seedance-2 goes to 15s single-pass with a full multi-beat arc — never assume a generic 8–10s cap); durationSeconds must be one of the model’s durations from hermoso_capabilities. Renders take 1–3 min. refImage anchors the opening frame; ttsScript adds a voiceover. Spends credits (Starter plan is video-blocked server-side).',
     inputSchema: {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "hermoso",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "Drive Hermoso — the AI ad studio — from any AI agent: MCP server, CLI, and Claude skills for researching winning ads and generating finished image & video ads.",
   "type": "module",
   "bin": {