@koda-sl/baker-cli 0.148.0 → 0.149.0-dev.328f015d3

package/README.md

@@ -1643,6 +1643,8 @@ baker images stock "office reaction" --people only
 
 Free tier exists but watermarks previews — pass `--license freemium` to filter to clean free assets explicitly.
 
+An empty result comes back with `hints` naming the filters that narrowed the search plus the fallbacks (`baker images find --sources …`, `baker images generate`); a provider failure returns an `error.fix` pointing at the same exits. `baker images google` does the same, minus the cross-provider fallback (it is the last-resort provider).
+
 **Flags:**
 
 | Flag             | Description                                                                                |
@@ -1724,13 +1726,15 @@ baker images generate "flat geometric mascot, brand palette" \
 | Model | Best for | Aspect ratios | Sizes |
 |---|---|---|---|
 | `google/gemini-3.1-flash-image-preview` **(default)** | Fast iteration, reference editing, extreme aspect ratios (Nano Banana flash) | standard **+** `1:4` `4:1` `1:8` `8:1` | `0.5K`–`4K` |
-| `google/gemini-3.5-flash` | Fast; extreme aspect ratios | standard **+** `1:4` `4:1` `1:8` `8:1` | `0.5K`–`4K` |
 | `google/gemini-3-pro-image-preview` | Highest fidelity (Nano Banana Pro) — strong prompt adherence and reference grounding | standard set | `1K` `2K` `4K` |
-| `openai/gpt-5.4-image-2` | Photoreal + cleanest in-image text — ad/landing reproduction | standard set | `1K` `2K` `4K` |
+| `openai/gpt-image-2` | Photoreal + cleanest in-image text — ad/landing reproduction | standard set **minus** `4:5` `5:4` | *(none — derived from the ratio)* |
+| `openai/gpt-5.4-image-2` | **Legacy** — accepted so canvases authored before the gpt-image-2 switch still re-run. Don't pick it for new work. | standard set | `1K` `2K` `4K` (ignored upstream) |
 | `recraft/recraft-v4.1-pro-vector` | Vector/flat/SVG-style with palette control | standard set | `1K` `2K` `4K` |
 
 Standard aspect ratios: `1:1` `2:3` `3:2` `3:4` `4:3` `4:5` `5:4` `9:16` `16:9` `21:9`.
 
+`openai/gpt-image-2` accepts neither `image_size` nor the `4:5` / `5:4` portrait ratios — OpenAI picks the pixel dimensions from the ratio. To ship a 4:5 Meta feed ad from it, render the hero at `3:4` and adapt with `image_aspect_adapt`; the scaffolders do this for you.
+
 **Flags:**
 
 | Flag | Description |
@@ -2747,7 +2751,7 @@ A re-run with no changes hits the cache for every node — total runtime drops t
       "type": "text_generate",
       "inputs": { "topic": "$ref:topic.text" },
       "params": {
-        "model": "google/gemini-3.5-flash",
+        "model": "google/gemini-3.1-flash-image-preview",
         "prompt": "Write a 6-word tagline for {{topic}}."
       }
     }
@@ -3046,37 +3050,31 @@ Aspect-ratio sets used below:
 
 ---
 
-###### Model: `openai/gpt-5.4-image-2`
+###### Model: `openai/gpt-image-2`
 
-Photorealistic generalist. Optional `reference` image.
+Photorealistic generalist, and the cleanest at rendering text inside the image. Optional `reference` image (up to 16).
 
 | Name | Type | Required | Notes |
 |---|---|---|---|
-| `model` | literal | yes | `"openai/gpt-5.4-image-2"` |
+| `model` | literal | yes | `"openai/gpt-image-2"` |
 | `prompt` | string | yes | non-empty |
-| `aspect_ratio` | enum | no | STD AR |
-| `image_size` | enum | no | `1K \| 2K \| 4K` |
+| `aspect_ratio` | enum | no | GPT AR = `1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9` — **no `4:5` / `5:4`** |
 | `quality` | enum | no | `auto \| low \| medium \| high` — rendering quality; the scaffolder sets `high` for photoreal frames. (Do **not** pass `input_fidelity`: gpt-image-2 forces high fidelity automatically and the param can fail the request.) |
 
+No `image_size`: OpenAI derives the pixel dimensions from the ratio, so a size is ignored. For a portrait ad format, render at `3:4` and adapt.
+
 ```json
 { "id": "hero", "type": "image_generate",
-  "params": { "model": "openai/gpt-5.4-image-2", "prompt": "Photorealistic photo of …", "aspect_ratio": "16:9", "image_size": "2K", "quality": "high" } }
+  "params": { "model": "openai/gpt-image-2", "prompt": "Photorealistic photo of …", "aspect_ratio": "16:9", "quality": "high" } }
 ```
 
-###### Model: `google/gemini-3.5-flash`
-
-Newest Gemini Flash image model. Always returns an image output. Best for fast iteration; supports extreme aspect ratios and the `0.5K` size for cheap previews.
+###### Model: `openai/gpt-5.4-image-2` (legacy)
 
-| Name | Type | Required | Notes |
-|---|---|---|---|
-| `model` | literal | yes | `"google/gemini-3.5-flash"` |
-| `prompt` | string | yes | non-empty |
-| `aspect_ratio` | enum | no | EXTREME AR |
-| `image_size` | enum | no | `0.5K \| 1K \| 2K \| 4K` |
+Kept only so canvases authored before the gpt-image-2 switch still validate and re-run unchanged — `baker canvas rerun` replays a recorded canvas verbatim. It keeps the full standard ratio set (including `4:5` / `5:4`) and still accepts `image_size`, which the provider ignores. Prefer `openai/gpt-image-2` for anything new.
 
 ###### Model: `google/gemini-3.1-flash-image-preview`
 
-Preview-channel Gemini flash. Same param surface as `3.5-flash`.
+Gemini flash image model — the default. Fast iteration, reference editing, extreme aspect ratios, and the `0.5K` size for cheap previews.
 
 | Name | Type | Required | Notes |
 |---|---|---|---|
@@ -3293,7 +3291,7 @@ There is no `prompt` param — the extraction schema is the node. Use `focus` to
       "params": { "model": "~google/gemini-pro-latest" } },
     { "id": "remix", "type": "image_generate",
       "inputs": { "blueprint": "$ref:blueprint.description" },
-      "params": { "model": "openai/gpt-5.4-image-2",
+      "params": { "model": "openai/gpt-image-2",
                   "prompt": "Recreate an image matching this exact blueprint, but swap the product for a ceramic mug:\n{{blueprint}}" } }
   ],
   "output": { "node": "remix", "output": "images" }
@@ -3374,9 +3372,9 @@ Fail-fast: an invalid model selection (wrong count, duplicate or out-of-range pi
 {
   "schema": "baker-canvas/1",
   "nodes": [
-    { "id": "a", "type": "image_generate", "params": { "model": "google/gemini-3.5-flash", "prompt": "hero shot of a ceramic mug, warm morning light" } },
-    { "id": "b", "type": "image_generate", "params": { "model": "google/gemini-3.5-flash", "prompt": "hero shot of a ceramic mug, studio softbox" } },
-    { "id": "c", "type": "image_generate", "params": { "model": "google/gemini-3.5-flash", "prompt": "hero shot of a ceramic mug, dramatic side light" } },
+    { "id": "a", "type": "image_generate", "params": { "model": "google/gemini-3.1-flash-image-preview", "prompt": "hero shot of a ceramic mug, warm morning light" } },
+    { "id": "b", "type": "image_generate", "params": { "model": "google/gemini-3.1-flash-image-preview", "prompt": "hero shot of a ceramic mug, studio softbox" } },
+    { "id": "c", "type": "image_generate", "params": { "model": "google/gemini-3.1-flash-image-preview", "prompt": "hero shot of a ceramic mug, dramatic side light" } },
     { "id": "best", "type": "image_select",
       "inputs": { "images": ["$ref:a.images#0", "$ref:b.images#0", "$ref:c.images#0"] },
       "params": { "model": "~google/gemini-pro-latest", "prompt": "most premium-feeling lighting, no harsh shadows" } }
@@ -4078,7 +4076,7 @@ baker canvas run ./reference-ad.video.canvas.json
 | `--focus <text>` | — | Known provenance/emphasis to ground the deconstruct. |
 | `--deconstruct-model <id>` | `~google/gemini-pro-latest` | Override the `video_deconstruct` model. |
 | `--select-model <id>` | `~google/gemini-flash-latest` | Override the element-selection `text_generate` model. |
-| `--image-model <id>` | `openai/gpt-5.4-image-2` | Override the per-frame `image_generate` model (defaults to the strongest, matching `scaffold-static-ad`). |
+| `--image-model <id>` | `openai/gpt-image-2` | Override the per-frame `image_generate` model (defaults to the strongest, matching `scaffold-static-ad`). |
 | `--video-model <id>` | scored router | Override the `video_generate` model **and skip the router**. Curated roster: `bytedance/seedance-2.0` (workhorse), `google/veo-3.1` (cine ceiling + real-face), `google/veo-3.1-fast` (cheap Veo), `kwaivgi/kling-v3.0-pro` (motion-transfer). |
 | `--real-face` | auto-detected | Force the Veo route for a photoreal human presenter (dodges the ByteDance real-person filter). **Usually unnecessary** — the scaffold auto-detects a photoreal on-camera person/animal cast from the deconstruct and routes it to Veo on its own; set this only to force it when the cast isn't detected. Covers AI-generated photoreal faces too, not just real ones. |
 | `--motion-transfer` | off | Motion driven from a reference / hyper-dynamic → the router picks Kling. |
@@ -4135,7 +4133,7 @@ baker canvas run ./static-ad.canvas.json
 | `--describe-model <id>` | registry default (`~google/gemini-pro-latest`) | Override the `image_describe` model. |
 | `--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. |
+| `--gen-model <id>` | registry default (`openai/gpt-image-2`) | Override the `image_generate` model. |
 | `--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). |

package/dist/{chunk-2F5SCTNS.js → chunk-O3VYLCJK.js}

@@ -7,9 +7,9 @@ import {
   __toESM
 } from "./chunk-RK67WL4O.js";
 
-// ../../node_modules/.pnpm/safe-stable-stringify@2.5.0/node_modules/safe-stable-stringify/index.js
+// ../../.pnpm-store/v10/links/@/safe-stable-stringify/2.5.0/810146e81bae4e3a061fe487864f2fde80c4b03b886877dc0f1fffbc6480b67e/node_modules/safe-stable-stringify/index.js
 var require_safe_stable_stringify = __commonJS({
-  "../../node_modules/.pnpm/safe-stable-stringify@2.5.0/node_modules/safe-stable-stringify/index.js"(exports, module) {
+  "../../.pnpm-store/v10/links/@/safe-stable-stringify/2.5.0/810146e81bae4e3a061fe487864f2fde80c4b03b886877dc0f1fffbc6480b67e/node_modules/safe-stable-stringify/index.js"(exports, module) {
     "use strict";
     var { hasOwnProperty } = Object.prototype;
     var stringify = configure2();
@@ -1070,7 +1070,7 @@ function resolveAdaptFormats(params) {
   return params.formats ?? [];
 }
 
-// ../../node_modules/.pnpm/safe-stable-stringify@2.5.0/node_modules/safe-stable-stringify/esm/wrapper.js
+// ../../.pnpm-store/v10/links/@/safe-stable-stringify/2.5.0/810146e81bae4e3a061fe487864f2fde80c4b03b886877dc0f1fffbc6480b67e/node_modules/safe-stable-stringify/esm/wrapper.js
 var import__ = __toESM(require_safe_stable_stringify(), 1);
 var configure = import__.default.configure;
 var wrapper_default = import__.default;
@@ -1114,10 +1114,12 @@ function normalizeForCanonical(value) {
 // ../canvas-contract/src/registry.ts
 var OPENROUTER_IMAGE_AR = ["1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9"];
 var OPENROUTER_IMAGE_AR_EXTREME = [...OPENROUTER_IMAGE_AR, "1:4", "4:1", "1:8", "8:1"];
+var OPENROUTER_IMAGE_AR_GPT = ["1:1", "2:3", "3:2", "3:4", "4:3", "9:16", "16:9", "21:9"];
 var OPENROUTER_IMAGE_SIZE = ["1K", "2K", "4K"];
 var OPENROUTER_IMAGE_SIZE_EXTENDED = ["0.5K", ...OPENROUTER_IMAGE_SIZE];
 var OPENROUTER_IMAGE_QUALITY = ["auto", "low", "medium", "high"];
 var SEEDANCE_DURATIONS = [4, 5, 6, 8, 10, 12, 15];
+var KLING_DURATIONS = [3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15];
 var ELEVENLABS_OUTPUT_FORMATS = [
   "mp3_22050_32",
   "mp3_44100_32",
@@ -1134,8 +1136,8 @@ var REPLICATE_VIDEO_MIMES = ["video/mp4", "video/webm", "video/quicktime"];
 var DECONSTRUCT_VIDEO_MIMES = ["video/mp4", "video/webm", "video/quicktime"];
 var REPLICATE_AUDIO_MIMES = ["audio/wav", "audio/mpeg", "audio/mp3"];
 var IMAGE_GENERATE_MODELS = [
+  "openai/gpt-image-2",
   "openai/gpt-5.4-image-2",
-  "google/gemini-3.5-flash",
   "google/gemini-3.1-flash-image-preview",
   "google/gemini-3-pro-image-preview",
   "recraft/recraft-v4.1-pro-vector"
@@ -1234,28 +1236,37 @@ var MODEL_REGISTRY = {
     // `seed` is omitted on every entry — OpenRouter's `image_config` schema
     // has no `seed` slot for image-gen (different from video-gen), so passing
     // it would be a silent no-op.
-    "openai/gpt-5.4-image-2": {
-      label: "OpenAI GPT-5.4 Image 2",
+    // The direct image model, not the `gpt-5.4-image-2` chat model that emitted
+    // images as a side effect. Notable capability gaps vs the Gemini entries:
+    // no `image_size` (OpenAI picks the pixel dimensions from the ratio, and a
+    // `resolution` is silently ignored) and the narrower `..._AR_GPT` ratio set.
+    "openai/gpt-image-2": {
+      label: "OpenAI GPT Image 2",
       inputs: [],
       optional_inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES }],
       required: ["prompt"],
       params: {
         prompt: { kind: "string" },
-        aspect_ratio: { kind: "string", enum: OPENROUTER_IMAGE_AR },
-        image_size: { kind: "string", enum: OPENROUTER_IMAGE_SIZE },
+        aspect_ratio: { kind: "string", enum: OPENROUTER_IMAGE_AR_GPT },
         quality: { kind: "string", enum: OPENROUTER_IMAGE_QUALITY }
       }
     },
-    "google/gemini-3.5-flash": {
-      // Newer Gemini flash image model. Always returns an image output.
-      label: "Google Gemini 3.5 Flash (Image)",
+    // LEGACY — kept so canvases authored before the gpt-image-2 switch still
+    // validate and re-run unchanged (`baker canvas rerun` restores a recorded
+    // canvas verbatim, so dropping this model would break every stored creative
+    // that used it). Its param surface is the ORIGINAL one on purpose: unlike
+    // gpt-image-2 it still honors 4:5/5:4, and `image_size` is accepted-then-
+    // ignored upstream rather than rejected. Verified live on /api/v1/images.
+    // Don't reach for it in new work — the scaffolders default to gpt-image-2.
+    "openai/gpt-5.4-image-2": {
+      label: "OpenAI GPT-5.4 Image 2 (legacy)",
       inputs: [],
       optional_inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES }],
       required: ["prompt"],
       params: {
         prompt: { kind: "string" },
-        aspect_ratio: { kind: "string", enum: OPENROUTER_IMAGE_AR_EXTREME },
-        image_size: { kind: "string", enum: OPENROUTER_IMAGE_SIZE_EXTENDED },
+        aspect_ratio: { kind: "string", enum: OPENROUTER_IMAGE_AR },
+        image_size: { kind: "string", enum: OPENROUTER_IMAGE_SIZE },
         quality: { kind: "string", enum: OPENROUTER_IMAGE_QUALITY }
       }
     },
@@ -1402,7 +1413,7 @@ var MODEL_REGISTRY = {
         prompt: { kind: "string" },
         negative_prompt: { kind: "string" },
         aspect_ratio: { kind: "string", enum: ["16:9", "9:16"] },
-        resolution: { kind: "string", enum: ["720p", "1080p"] },
+        resolution: { kind: "string", enum: ["720p", "1080p", "4K"] },
         duration: { kind: "number", enum: [4, 6, 8] },
         seed: { kind: "number" },
         generate_audio: { kind: "boolean" },
@@ -1414,9 +1425,14 @@ var MODEL_REGISTRY = {
     "kwaivgi/kling-v3.0-pro": {
       // Motion-transfer / dynamic multi-shot beats. Reachable through the default
       // OpenRouter gateway (generic video body — no google-vertex block), so it
-      // needs no direct-provider exception. Cost is usage-based (known from the
-      // provider response), so it has no pre-flight cost estimate. `cfg_scale`
-      // trades prompt adherence vs motion freedom; higher = closer to prompt.
+      // needs no direct-provider exception. `cfg_scale` trades prompt adherence
+      // vs motion freedom; higher = closer to prompt.
+      //
+      // Params below are the ones OpenRouter actually advertises for this model
+      // (GET /api/v1/videos/models). Three were wrong before and each was a free
+      // 400 or a silently unsupported knob: it renders 720p ONLY (1080p was
+      // offered and rejected), it takes ANY duration from 3-15s (we allowed just
+      // 5 and 10), and it does not support `seed` at all.
       label: "Kling 3.0",
       inputs: [],
       optional_inputs: [{ kind: "image", mimes: OPENROUTER_IMAGE_MIMES }],
@@ -1426,10 +1442,9 @@ var MODEL_REGISTRY = {
         // over-length prompt fails validate (free) not the billed call.
         prompt: { kind: "string", maxLength: 2500 },
         negative_prompt: { kind: "string" },
-        aspect_ratio: { kind: "string", enum: ["1:1", "16:9", "9:16"] },
-        resolution: { kind: "string", enum: ["720p", "1080p"] },
-        duration: { kind: "number", enum: [5, 10] },
-        seed: { kind: "number" },
+        aspect_ratio: { kind: "string", enum: ["16:9", "9:16", "1:1"] },
+        resolution: { kind: "string", enum: ["720p"] },
+        duration: { kind: "number", enum: KLING_DURATIONS },
         generate_audio: { kind: "boolean" },
         cfg_scale: { kind: "number", min: 0, max: 1 }
       }
@@ -1445,7 +1460,7 @@ var MODEL_REGISTRY = {
         prompt: { kind: "string" },
         negative_prompt: { kind: "string" },
         aspect_ratio: { kind: "string", enum: ["16:9", "9:16"] },
-        resolution: { kind: "string", enum: ["720p", "1080p"] },
+        resolution: { kind: "string", enum: ["720p", "1080p", "4K"] },
         duration: { kind: "number", enum: [4, 6, 8] },
         seed: { kind: "number" },
         generate_audio: { kind: "boolean" },
@@ -1607,6 +1622,36 @@ var MODEL_REGISTRY = {
     }
   }
 };
+function supportsParam(kind, model, param) {
+  return MODEL_REGISTRY[kind]?.[model]?.params[param] !== void 0;
+}
+function supportedAspectRatios(kind, model) {
+  const schema = MODEL_REGISTRY[kind]?.[model]?.params.aspect_ratio;
+  return schema?.kind === "string" ? schema.enum : void 0;
+}
+function ratioValue(ratio) {
+  const [w, h] = ratio.split(":").map(Number);
+  if (!w || !h || !Number.isFinite(w) || !Number.isFinite(h)) return null;
+  return w / h;
+}
+function nearestSupportedAspectRatio(kind, model, target) {
+  const supported = supportedAspectRatios(kind, model);
+  if (!supported || supported.includes(target)) return target;
+  const wanted = ratioValue(target);
+  if (wanted === null) return target;
+  let best = target;
+  let bestDistance = Number.POSITIVE_INFINITY;
+  for (const candidate of supported) {
+    const value = ratioValue(candidate);
+    if (value === null) continue;
+    const distance2 = Math.abs(Math.log(value / wanted));
+    if (distance2 < bestDistance) {
+      bestDistance = distance2;
+      best = candidate;
+    }
+  }
+  return best;
+}
 
 // ../canvas-contract/src/validateParams.ts
 function isManagedNodeKind(nodeType) {
@@ -1737,6 +1782,41 @@ function validateValue(key, value, schema, model) {
   }
 }
 
+// ../canvas-contract/src/videoCost.ts
+var CREDITS_PER_USD = 100;
+var SEEDANCE_USD_PER_SECOND = {
+  "480p": 0.18,
+  "720p": 0.5,
+  "1080p": 0.62,
+  "4k": 0.62
+};
+var DEFAULT_VIDEO_RESOLUTION = "720p";
+var DEFAULT_VIDEO_DURATION_S = 5;
+function isSeedanceModel(model) {
+  return model.startsWith("bytedance/seedance");
+}
+var FALLBACK_USD_PER_SECOND = 0.5;
+function seedanceUsdPerSecond(resolution) {
+  return SEEDANCE_USD_PER_SECOND[resolution ?? DEFAULT_VIDEO_RESOLUTION] ?? FALLBACK_USD_PER_SECOND;
+}
+var USD_PER_SECOND = {
+  "kwaivgi/kling-v3.0-pro": { silent: 0.112, audio: 0.168 },
+  "google/veo-3.1": { silent: 0.2, audio: 0.4 },
+  "google/veo-3.1-fast": { silent: 0.1, audio: 0.12 }
+};
+function estimateVideoCostUsd({ model, duration, resolution, generateAudio }) {
+  const seconds = duration ?? DEFAULT_VIDEO_DURATION_S;
+  if (isSeedanceModel(model)) return seedanceUsdPerSecond(resolution) * seconds;
+  const published = USD_PER_SECOND[model];
+  if (published) return (generateAudio ? published.audio : published.silent) * seconds;
+  const dearestKnownRate = Math.max(...Object.values(SEEDANCE_USD_PER_SECOND));
+  return dearestKnownRate * seconds;
+}
+function estimateVideoCredits(input) {
+  const credits = estimateVideoCostUsd(input) * CREDITS_PER_USD;
+  return Math.ceil(Number(credits.toFixed(6)));
+}
+
 // src/engine/lib/concurrency.ts
 var DEFAULT_CONCURRENCY = 8;
 function resolveConcurrency(...candidates) {
@@ -2533,7 +2613,7 @@ function looksLikeHttpUrl(value) {
 var VEO_PERSON_GENERATION = "allow_adult";
 var VEO_NEGATIVE_PROMPT = "subtitles, captions, on-screen text, watermark, logo, warped face, distorted hands, extra fingers, low quality";
 var VEO_DURATIONS = [4, 6, 8];
-var KLING_DURATIONS = [5, 10];
+var KLING_DURATIONS2 = [5, 10];
 var KLING_NEGATIVE_PROMPT = "warped face, distorted hands, extra fingers, morphing, flicker, on-screen text, watermark, low quality";
 var KLING_CFG_SCALE = 0.7;
 var SPEAKS_PROSE = (line) => `The person speaks to camera; lip-sync follows the dialogue verbatim, with delivery and emotion carried in the wording itself (no bracketed cues). Dialogue: "${line}"`;
@@ -2579,7 +2659,7 @@ var KLING_PROFILE = {
   // Kling takes a negative_prompt PARAM instead (paramDefaults).
   keyframeInstruction: "Preserve the composition and colors of the first frame; animate the motion described.",
   wordBudget: 200,
-  durationSet: KLING_DURATIONS,
+  durationSet: KLING_DURATIONS2,
   paramDefaults: { negative_prompt: KLING_NEGATIVE_PROMPT, cfg_scale: KLING_CFG_SCALE }
 };
 function clipProfileFor(modelId) {
@@ -6991,8 +7071,9 @@ var dialogueNode = delegated({
 // src/engine/nodes/remote/image.ts
 import { z as z17 } from "zod";
 var IMAGE_GENERATE_MODELS2 = [
+  "openai/gpt-image-2",
+  // Legacy — see the registry entry; kept so pre-switch canvases still run.
   "openai/gpt-5.4-image-2",
-  "google/gemini-3.5-flash",
   "google/gemini-3.1-flash-image-preview",
   "google/gemini-3-pro-image-preview",
   "recraft/recraft-v4.1-pro-vector"
@@ -7002,11 +7083,11 @@ var ImageGenerateParams = z17.object({
   prompt: z17.string().min(1),
   aspect_ratio: z17.enum(["1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3", "4:5", "5:4", "21:9", "1:4", "4:1", "1:8", "8:1"]).optional(),
   image_size: z17.enum(["0.5K", "1K", "2K", "4K"]).optional(),
-  // Rendering quality — forwarded into `image_config`. OpenRouter models without a
-  // quality knob ignore it; the registry gates which models accept it (gpt-image, Gemini).
+  // Rendering quality. OpenRouter models without a quality knob ignore it; the
+  // registry gates which models accept it (gpt-image, Gemini).
   quality: z17.enum(["auto", "low", "medium", "high"]).optional(),
-  // Recraft v4 vector controls — forwarded into `image_config`. Registry
-  // rejects them on non-Recraft models.
+  // Recraft v4 vector controls, sent as the provider's own `controls` block.
+  // Registry rejects them on non-Recraft models.
   strength: z17.number().min(0).max(1).optional(),
   rgb_colors: z17.array(z17.array(z17.number().int().min(0).max(255))).optional(),
   background_rgb_color: z17.array(z17.number().int().min(0).max(255)).optional()
@@ -7015,8 +7096,8 @@ var imageGenerateNode = delegated({
   id: "image_generate",
   version: "2.2.0",
   category: "image",
-  summary: "Generate images for ad creatives. Curated model set: GPT-5.4 Image, Gemini 3.5 Flash, Gemini 3.1 Flash Image Preview, Gemini 3 Pro Image, Recraft v4.1 Pro Vector. Per-model param support comes from the canvas-engine model registry.",
-  when_to_use: "Use for hero shots, product photography, illustrations, and vector logos. `recraft/recraft-v4.1-pro-vector` for crisp vector / logo work; `openai/gpt-5.4-image-2` for photorealistic; Gemini variants for fast iteration and editing via the `reference` input. `reference` accepts ONE image or an ARRAY of images \u2014 wire several to combine references in a single generation (e.g. a subject sheet + a font specimen + the original ad). Every reference is forwarded to the model in array order.",
+  summary: "Generate images for ad creatives. Curated model set: GPT Image 2, Gemini 3.1 Flash Image Preview, Gemini 3 Pro Image, Recraft v4.1 Pro Vector. Per-model param support comes from the canvas-engine model registry.",
+  when_to_use: "Use for hero shots, product photography, illustrations, and vector logos. `recraft/recraft-v4.1-pro-vector` for crisp vector / logo work; `openai/gpt-image-2` for photorealistic and in-image text (NOTE: it has no `image_size`, and no 4:5 / 5:4 \u2014 route portrait ad formats through Gemini or `image_aspect_adapt`); Gemini variants for fast iteration, extreme ratios, and editing via the `reference` input. `reference` accepts ONE image or an ARRAY of images \u2014 wire several to combine references in a single generation (e.g. a subject sheet + a font specimen + the original ad). Every reference is forwarded to the model in array order.",
   // `reference` is one image or an ordered array of images. The backend forwards
   // each as a separate `image_url` to the provider (OpenRouter accepts many).
   inputs: z17.object({ reference: z17.union([ImageRef, z17.array(ImageRef).min(1)]).optional() }).loose(),
@@ -7412,12 +7493,30 @@ var videoGenerateNode = delegated({
   inputs: z28.object({
     first_frame: ImageRef.optional(),
     last_frame: ImageRef.optional(),
-    reference: ImageRef.optional()
+    reference: ImageRef.optional(),
+    /**
+     * Reference-to-video: several images the model uses as visual guidance
+     * (this person, this product) instead of an exact opening frame. Mutually
+     * exclusive with `first_frame` — OpenRouter treats a request carrying both
+     * as image-to-video and ignores these, so wire one or the other.
+     */
+    references: z28.array(ImageRef).optional()
   }).loose(),
   params: VideoGenerateParams,
   outputs: z28.object({ video: VideoRef }).strict(),
   outputKinds: { video: "video" },
-  cost: () => ({ credits: 50, seconds_estimate: 120 })
+  // Priced from the shared contract, so `validate`'s quote and the charge the
+  // backend applies come from ONE table. A flat number here under-quoted a
+  // 1080p 8s clip by ~10x, and the agent reads this out to the user as "this
+  // will cost N" before spending it.
+  cost: ({ params }) => ({
+    credits: estimateVideoCredits({
+      model: params.model,
+      duration: params.duration,
+      resolution: params.resolution
+    }),
+    seconds_estimate: 120
+  })
 });
 
 // src/engine/nodes/remote/videoBackgroundRemove.ts
@@ -7872,6 +7971,8 @@ export {
   IMAGE_GENERATE_MODELS,
   DEFAULT_VIDEO_GENERATE_MODEL,
   MODEL_REGISTRY,
+  supportsParam,
+  nearestSupportedAspectRatio,
   resolveConcurrency,
   ulid,
   isPersistedAssetRef,
@@ -7898,4 +7999,4 @@ export {
   defaultRegistry,
   createEngineFromEnv
 };
-//# sourceMappingURL=chunk-2F5SCTNS.js.map
+//# sourceMappingURL=chunk-O3VYLCJK.js.map