@koda-sl/baker-cli 0.132.1 → 0.133.0

package/README.md

@@ -3094,7 +3094,8 @@ The adaptation prompt is baked into the backend and is direction-aware (a wider
 | Name | Type | Required | Notes |
 |---|---|---|---|
 | `model` | enum | yes | one of `google/gemini-3-pro-image-preview`, `google/gemini-3.1-flash-image-preview` |
-| `formats` | enum[] | yes | 1–6 unique target ratios from `1:1 \| 2:3 \| 3:2 \| 3:4 \| 4:3 \| 4:5 \| 5:4 \| 9:16 \| 16:9 \| 21:9` — output order follows this list |
+| `formats` | enum[] | one of `formats`/`platform` | 1–6 unique target ratios from `1:1 \| 2:3 \| 3:2 \| 3:4 \| 4:3 \| 4:5 \| 5:4 \| 9:16 \| 16:9 \| 21:9` — output order follows this list |
+| `platform` | enum | one of `formats`/`platform` | a placement preset that expands to that platform's canonical on-grid set: `meta_feed` (4:5), `meta_feed_stories` (4:5, 9:16), `meta_all` (4:5, 9:16, 1:1), `linkedin` (1:1), `google_demandgen` (1:1, 4:5, 16:9), `tiktok` (9:16), `youtube` (16:9). Mutually exclusive with `formats`. Off-grid platform targets (e.g. Google 1.91:1) are not rendered here — crop them from the nearest rendered ratio with `baker images crop`. |
 | `guidance` | string | no | hints appended to the baked prompt, e.g. `"keep the CTA button fully visible"` |
 | `image_size` | enum | no | `1K \| 2K \| 4K` on `3-pro`, `0.5K \| 1K \| 2K \| 4K` on `3.1-flash` |
 
@@ -3104,9 +3105,10 @@ The adaptation prompt is baked into the backend and is direction-aware (a wider
 |---|---|---|
 | `images` | image[] | one per requested format, in `formats` order; each carries `metadata.aspect_ratio` and `metadata.adapted` (`false` = source passed through) |
 
-**Cost** — per-format estimate: 20 credits on `3-pro`, 5 on `3.1-flash`, × `formats.length` (backend charges actual OpenRouter usage; pass-through formats are free).
+**Cost** — per-format estimate: 20 credits on `3-pro`, 5 on `3.1-flash`, × the resolved format count (a `platform` preset expands first; backend charges actual OpenRouter usage; pass-through formats are free).
 
 Guidance:
+- Reach for `platform` when you want a placement's whole set without naming ratios (e.g. `"platform": "meta_feed_stories"`); use `formats` when you need an exact, custom ratio list. Set one, never both.
 - List the source's own ratio in `formats` too when you want the full set in one output — it passes through for free.
 - Use `google/gemini-3.1-flash-image-preview` while iterating; switch to `google/gemini-3-pro-image-preview` for final-quality adaptation.
 - Indexes are positional: `$ref:adapt.images#1` is always the second entry of `formats`.
@@ -3992,7 +3994,9 @@ Turn a source/inspiration image into a **runnable, self-validated static-ad canv
 2. **element selection** (`~google/gemini-flash-latest`) — picks the **main, identity-critical** elements (the brand logo, a showcased product, a trust badge) **plus any foreground/hero person or animal** — the emotional focal point — even a generic one, because a free-generated face/muzzle reads as AI and grows artifacts; the emotional hero always gets a real-reference slot. When the advertiser's logo appears in **more than one lockup** (a square/icon **mark** and a horizontal **wordmark**), each is emitted as its **own** element (e.g. `LOGO_MARK`, `LOGO_WORDMARK`) so you drop the right file in each slot instead of stretching one logo to cover both. The describe pass also records the ad's **typography** under a `fonts` block (each typeface's classification, a best-guess family, and its weight/case) so you know exactly what to drop at the brand-font slot. Background extras are dropped. Each element is stamped back onto its blueprint entry as a `reference_image` label so the JSON self-documents which slot grounds which subject.
 3. **global layout** (`~google/gemini-flash-latest`) — produces a structured `layout` block in `prompt.json`: the column/row grid, each region's `x_pct`/`y_pct` bounds, panel splits, background/shape, and every text block's relative size/weight/case/alignment. This is what gives the generator a precise composition to rebuild.
 
-It then scaffolds a canvas that ingests `prompt.json`, wires **one `[TODO]` ingest slot per detected element** (plus an optional brand-font → type-specimen) into `image_generate`, and wires the original image in for composition only. Each **person/animal hero** is additionally fused into a generated **multi-view reference sheet** (`image_reference_sheet`, a turnaround built from the one dropped photo) that the render grounds on instead of the lone flat snapshot — the same identity lock the video scaffold uses, so the face/muzzle stays consistent and artifact-free from a single reference. Pass `--skip-actor-sheets` to ground straight on the dropped photo. The canvas is validated before it's written. stdout returns `{ ok, canvas_path, prompt_path, models, layout_regions, stats, checklist }` — the **checklist** lists every real asset to drop in (and which heroes get a sheet).
+It then scaffolds a canvas that ingests `prompt.json`, wires **one `[TODO]` ingest slot per detected element** (plus an optional brand-font → type-specimen) into `image_generate`, and wires the original image in for composition only. Each **person/animal hero** is additionally fused into a generated **multi-view reference sheet** (`image_reference_sheet`, a turnaround built from the one dropped photo) that the render grounds on instead of the lone flat snapshot — the same identity lock the video scaffold uses, so the face/muzzle stays consistent and artifact-free from a single reference. Pass `--skip-actor-sheets` to ground straight on the dropped photo. The canvas is validated before it's written. stdout returns `{ ok, canvas_path, prompt_path, models, aspect_ratio, placements, output_formats, layout_regions, stats, checklist }` — the **checklist** lists every real asset to drop in (and which heroes get a sheet).
+
+**Automatic placement fan-out.** By default the canvas doesn't stop at one ratio: the hero renders once at the platform's primary ratio, then an `image_aspect_adapt` node recomposes it into that platform's full placement set, and the canvas `output` points at the adapted images. The placement set is derived from `--platform` (`meta` → 4:5 + 9:16, `google` → 1:1 + 4:5 + 16:9, `linkedin` → 1:1, `tiktok` → 9:16, `youtube` → 16:9); override it with `--placements <preset>` or disable it with `--placements none` for a single base ad. The hero ratio passes through the adapt node **free**; each other ratio is a billed recomposition — and because adaptation re-generates, every ratio should be eyeballed for text and brand-color fidelity before publish (`ad-formats.md` in the scaffold skill covers this).
 
 The generation prompt is **model-aware and typography-hardened** (a static ad is the only path that bakes text *into* the image — video frames are clean plates). It resolves the image model's profile, so for **gpt-image** the exclusions (no invented badges/watermark) are hoisted to the very *end* of the prompt where the model reads them as pure exclusions rather than composition, and it quotes every blueprint string with an instruction to render each **once, verbatim**, lock brand names letter-by-letter, and keep type crisp and legible — the fix for the #1 static-ad defect (garbled/duplicated/dropped copy). Run `baker canvas critique` on the scaffolded canvas for an advisory read on text-legibility risk, identity grounding, and brand-type fidelity before you spend.
 
@@ -4013,7 +4017,9 @@ baker canvas run ./static-ad.canvas.json
 | `--select-model <id>` | registry default (`~google/gemini-flash-latest`) | Override the element-selection `text_generate` model. |
 | `--layout-model <id>` | registry default (`~google/gemini-flash-latest`) | Override the global-layout `text_generate` model. |
 | `--gen-model <id>` | registry default (`openai/gpt-5.4-image-2`) | Override the `image_generate` model. |
-| `--aspect <ratio>` | inferred from the image, else `9:16` | Force the output aspect ratio. |
+| `--platform <channel>` | `meta` | `_definition.md` channel **and** the default placement set the hero fans out to (`meta`\|`google`\|`linkedin`\|`tiktok`\|`youtube`\|`x`\|`other`; `x`/`other` fan out to nothing). |
+| `--placements <preset\|none>` | derived from `--platform` | Override the fan-out set: `meta_feed`\|`meta_feed_stories`\|`meta_all`\|`linkedin`\|`google_demandgen`\|`tiktok`\|`youtube`, or `none` for a single base ad. |
+| `--aspect <ratio>` | inferred from the image, else `9:16` | Force the hero's aspect ratio (clamped into the placement set so it stays a free pass-through). |
 | `--skip-font` | off | Skip the brand-font → type-specimen slot. |
 | `--skip-actor-sheets` | off | Ground each person/animal on its lone dropped photo instead of a generated multi-view reference sheet. |
 

package/dist/{chunk-MWR25ZMU.js → chunk-UBFU3E7L.js}

@@ -1002,6 +1002,38 @@ function describeCause(c) {
   }
 }
 
+// ../canvas-contract/src/adPlatformFormats.ts
+var AD_FORMAT_PLATFORMS = [
+  "meta_feed",
+  "meta_feed_stories",
+  "meta_all",
+  "linkedin",
+  "google_demandgen",
+  "tiktok",
+  "youtube"
+];
+var AD_PLATFORM_FORMAT_PRESETS = {
+  meta_feed: { formats: ["4:5"], note: "Meta/Instagram feed static." },
+  meta_feed_stories: { formats: ["4:5", "9:16"], note: "Meta feed + Stories/Reels." },
+  meta_all: { formats: ["4:5", "9:16", "1:1"], note: "Meta feed + Stories/Reels + square." },
+  linkedin: { formats: ["1:1"], note: "LinkedIn single-image feed (square)." },
+  google_demandgen: {
+    // Renders 16:9 too so the off-grid 1.91:1 landscape has a native source to crop from.
+    formats: ["1:1", "4:5", "16:9"],
+    offGrid: ["1.91:1"],
+    note: "Google Demand Gen; also wants 1.91:1 landscape \u2014 crop that from the rendered 16:9."
+  },
+  tiktok: { formats: ["9:16"], note: "TikTok full-screen vertical." },
+  youtube: { formats: ["16:9"], note: "YouTube in-stream / companion display." }
+};
+function platformFormats(platform) {
+  return AD_PLATFORM_FORMAT_PRESETS[platform].formats;
+}
+function resolveAdaptFormats(params) {
+  if (params.platform) return platformFormats(params.platform);
+  return params.formats ?? [];
+}
+
 // ../../node_modules/.pnpm/safe-stable-stringify@2.5.0/node_modules/safe-stable-stringify/esm/wrapper.js
 var import__ = __toESM(require_safe_stable_stringify(), 1);
 var configure = import__.default.configure;
@@ -1265,16 +1297,20 @@ var MODEL_REGISTRY = {
   },
   image_aspect_adapt: {
     // Multi-format adaptation of one creative. The recomposition prompt is
-    // baked into the backend handler; `formats` is the target-ratio list
-    // (ad-format set only — the registry can't gate array elements, the node's
-    // Zod schema is the strict per-element gate). The source creative is a
-    // required input slot.
+    // baked into the backend handler. The target ratios come from EITHER an
+    // explicit `formats` list OR a `platform` preset that expands to the
+    // canonical set; exactly one of the two is required — that "one of" gate,
+    // and per-element ratio validation, live in the node's Zod schema (the
+    // registry can't express "one of" or gate array elements), so `formats`
+    // is not listed as registry-required. The source creative is a required
+    // input slot.
     "google/gemini-3-pro-image-preview": {
       label: "Google Gemini 3 Pro Image (Nano Banana Pro)",
       inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES }],
-      required: ["formats"],
+      required: [],
       params: {
         formats: { kind: "json" },
+        platform: { kind: "string", enum: AD_FORMAT_PLATFORMS },
         guidance: { kind: "string" },
         image_size: { kind: "string", enum: OPENROUTER_IMAGE_SIZE }
       }
@@ -1282,9 +1318,10 @@ var MODEL_REGISTRY = {
     "google/gemini-3.1-flash-image-preview": {
       label: "Google Gemini 3.1 Flash Image (Preview)",
       inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES }],
-      required: ["formats"],
+      required: [],
       params: {
         formats: { kind: "json" },
+        platform: { kind: "string", enum: AD_FORMAT_PLATFORMS },
         guidance: { kind: "string" },
         image_size: { kind: "string", enum: OPENROUTER_IMAGE_SIZE_EXTENDED }
       }
@@ -6860,23 +6897,27 @@ var ASPECT_ADAPT_MODELS = ["google/gemini-3-pro-image-preview", "google/gemini-3
 var ASPECT_ADAPT_FORMATS = ["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"];
 var ImageAspectAdaptParams = z18.object({
   model: z18.enum(ASPECT_ADAPT_MODELS),
-  formats: z18.array(z18.enum(ASPECT_ADAPT_FORMATS)).min(1).max(6).refine((formats) => new Set(formats).size === formats.length, { message: "formats must be unique" }),
+  formats: z18.array(z18.enum(ASPECT_ADAPT_FORMATS)).min(1).max(6).refine((formats) => new Set(formats).size === formats.length, { message: "formats must be unique" }).optional(),
+  platform: z18.enum(AD_FORMAT_PLATFORMS).optional(),
   guidance: z18.string().min(1).optional(),
   image_size: z18.enum(["0.5K", "1K", "2K", "4K"]).optional()
-}).strict();
+}).strict().refine((p) => p.formats === void 0 !== (p.platform === void 0), {
+  message: "provide exactly one of `formats` (explicit ratios) or `platform` (a placement preset)",
+  path: ["formats"]
+});
 var imageAspectAdaptNode = delegated({
   id: "image_aspect_adapt",
   version: "1.0.0",
   category: "image",
-  summary: "Adapt ONE creative into multiple aspect ratios (Meta: 9:16 stories, 1:1 feed, 4:5, 16:9\u2026) in a single step. AI recomposes the layout per format \u2014 identical subject, text, logos, colors, and style; the scene is extended/restructured, never stretched or cropped. Formats that already match the source ratio pass through unchanged at zero cost. Outputs are ordered exactly as `formats`.",
-  when_to_use: "Use after a hero creative exists (image_generate, ingest, image_search) to fan it out to every placement format \u2014 wire the creative into `source` and list the target ratios in `formats`. Cost is estimated per format; formats matching the source ratio are free pass-throughs. Pick `google/gemini-3.1-flash-image-preview` (Nano Banana flash) while iterating, `google/gemini-3-pro-image-preview` (Nano Banana Pro) for final-quality adaptation.",
+  summary: "Adapt ONE creative into multiple aspect ratios (Meta: 9:16 stories, 1:1 feed, 4:5, 16:9\u2026) in a single step. Give it either an explicit `formats` list OR a `platform` preset (meta_feed, meta_feed_stories, meta_all, linkedin, google_demandgen, tiktok, youtube) that expands to that platform's canonical set. AI recomposes the layout per format \u2014 identical subject, text, logos, colors, and style; the scene is extended/restructured, never stretched or cropped. Formats that already match the source ratio pass through unchanged at zero cost. Outputs are ordered exactly as the resolved format list.",
+  when_to_use: "Use after a hero creative exists (image_generate, ingest, image_search) to fan it out to every placement format \u2014 wire the creative into `source` and set EITHER `formats` (exact ratios) OR `platform` (e.g. `meta_feed_stories`). Cost is estimated per format; formats matching the source ratio are free pass-throughs. Off-grid platform targets (e.g. Google 1.91:1) are not rendered here \u2014 crop them from the nearest ratio with `baker images crop`. Pick `google/gemini-3.1-flash-image-preview` (Nano Banana flash) while iterating, `google/gemini-3-pro-image-preview` (Nano Banana Pro) for final-quality adaptation.",
   inputs: z18.object({ source: ImageRef }).loose(),
   params: ImageAspectAdaptParams,
   outputs: z18.object({ images: z18.array(ImageRef).min(1) }).strict(),
   outputKinds: { images: "image" },
   cost: ({ params }) => {
     const p = params;
-    const count = Array.isArray(p?.formats) ? p.formats.length : 1;
+    const count = Math.max(1, resolveAdaptFormats(p ?? {}).length);
     return {
       credits: count * (p?.model === "google/gemini-3-pro-image-preview" ? 20 : 5),
       seconds_estimate: 30 + 30 * count
@@ -7689,6 +7730,8 @@ export {
   RunAbortedError,
   LayerExecutionError,
   describeFailureReason,
+  AD_FORMAT_PLATFORMS,
+  platformFormats,
   SEEDANCE_DURATIONS,
   ELEVENLABS_MAX_MUSIC_LENGTH_MS,
   IMAGE_GENERATE_MODELS,
@@ -7719,4 +7762,4 @@ export {
   defaultRegistry,
   createEngineFromEnv
 };
-//# sourceMappingURL=chunk-MWR25ZMU.js.map
+//# sourceMappingURL=chunk-UBFU3E7L.js.map