@remixmate/cli 0.9.20 → 0.9.21

package/dist/capabilities.d.ts

@@ -18,6 +18,9 @@ export interface ModelConstraints {
     durationMax?: number;
     durationDefault?: number;
     refImageMax?: number;
+    /** Omni-modal reference caps (Seedance 2.0): videos and audio clips per request. */
+    refVideoMax?: number;
+    refAudioMax?: number;
     sizes?: string[];
     /** aspect-ratio → [width, height] pixel preset (Seedream). Per model: the same
      *  ratio maps to different pixels on different Seedream variants. */

package/dist/handlers/gen-video.d.ts

@@ -11,7 +11,9 @@
  * server-side, so an unknown value still passes through to the backend.
  *
  * Local image paths for first/last/reference frames are read and base64-encoded
- * into a data: URI; https / data: URIs pass through unchanged.
+ * into a data: URI; https / data: URIs pass through unchanged. Reference videos
+ * and audio are the exception — they must already be public URLs, see
+ * `requirePublicUrls`.
  */
 import type { HandlerContext, HandlerInput } from './index.js';
 export declare function genVideo(input: HandlerInput, ctxIn: HandlerContext): Promise<void>;

package/dist/handlers/gen-video.js

@@ -11,14 +11,16 @@
  * server-side, so an unknown value still passes through to the backend.
  *
  * Local image paths for first/last/reference frames are read and base64-encoded
- * into a data: URI; https / data: URIs pass through unchanged.
+ * into a data: URI; https / data: URIs pass through unchanged. Reference videos
+ * and audio are the exception — they must already be public URLs, see
+ * `requirePublicUrls`.
  */
 import { mmPost, pollUntil, resolveHttpContext, SkillError } from '../http.js';
 import { getCapabilities, matchModel, defaultModel } from '../capabilities.js';
 import { emitProgress } from '../progress.js';
 import { isTrue, resolveImageInput, toNumber, toStringArray } from './shared.js';
 /** Generic, catalog-driven validation. No model names live here. */
-function validateAgainstConstraints(descriptor, duration, ratio, resolution, refCount) {
+function validateAgainstConstraints(descriptor, duration, ratio, resolution, refs) {
     const c = descriptor.constraints;
     const label = descriptor.label || descriptor.id;
     if (c.durations && c.durations.length > 0) {
@@ -37,12 +39,35 @@ function validateAgainstConstraints(descriptor, duration, ratio, resolution, ref
     if (c.resolutions && c.resolutions.length > 0 && !c.resolutions.includes(resolution)) {
         throw new SkillError(`❌ ${label} resolution must be one of: ${c.resolutions.join(', ')}; got: ${resolution}`);
     }
-    if (c.refImageMax !== undefined && refCount > c.refImageMax) {
+    if (c.refImageMax !== undefined && refs.images > c.refImageMax) {
         if (c.refImageMax === 0) {
             throw new SkillError(`❌ ${label} does not support a reference-image array; use --first-frame / --last-frame instead`);
         }
-        throw new SkillError(`❌ ${label} accepts at most ${c.refImageMax} reference images; got: ${refCount}`);
+        throw new SkillError(`❌ ${label} accepts at most ${c.refImageMax} reference images; got: ${refs.images}`);
     }
+    if (c.refVideoMax !== undefined && refs.videos > c.refVideoMax) {
+        throw new SkillError(`❌ ${label} accepts at most ${c.refVideoMax} reference videos; got: ${refs.videos}`);
+    }
+    if (c.refAudioMax !== undefined && refs.audios > c.refAudioMax) {
+        throw new SkillError(`❌ ${label} accepts at most ${c.refAudioMax} reference audio clips; got: ${refs.audios}`);
+    }
+}
+/**
+ * Reference videos / audio must be public https URLs.
+ *
+ * Unlike images, they are NOT inlined as data URIs: the caps are 50 MB per video
+ * and 15 MB per clip, and base64 inflates that by a third before it ever reaches
+ * the gateway. Failing here with the offending path beats a truncated upload or
+ * an opaque 413 three hops downstream.
+ */
+function requirePublicUrls(values, flag) {
+    return values.map((value) => {
+        const url = value.trim();
+        if (!/^https?:\/\//i.test(url)) {
+            throw new SkillError(`❌ ${flag} needs a public http(s) URL (local files are not uploaded), received: ${value}`);
+        }
+        return url;
+    });
 }
 async function pollVideoStatus(ctx, taskId) {
     return pollUntil(async () => {
@@ -69,10 +94,26 @@ export async function genVideo(input, ctxIn) {
     const firstFrame = input.first_frame ? resolveImageInput(String(input.first_frame)) : '';
     const lastFrame = input.last_frame ? resolveImageInput(String(input.last_frame)) : '';
     const references = toStringArray(input.reference).map(resolveImageInput).filter(Boolean);
+    const referenceVideos = requirePublicUrls(toStringArray(input.reference_video).filter(Boolean), '--reference-video');
+    const referenceAudios = requirePublicUrls(toStringArray(input.reference_audio).filter(Boolean), '--reference-audio');
     const prompt = (input.prompt ?? '').trim();
-    const hasVisual = Boolean(firstFrame || lastFrame || references.length > 0);
+    const hasVisual = Boolean(firstFrame || lastFrame || references.length > 0 || referenceVideos.length > 0);
     if (!prompt && !hasVisual) {
-        throw new SkillError('❌ Provide at least one of: a non-empty --prompt, or --first-frame / --last-frame / --reference');
+        throw new SkillError('❌ Provide at least one of: a non-empty --prompt, or --first-frame / --last-frame / --reference / --reference-video');
+    }
+    /**
+     * Two shapes the backend rejects outright; catching them here saves a round
+     * trip and names the flag that caused it.
+     *
+     * - first/last frame pins exact frames, omni-modal reference lets the model
+     *   re-cut — the API has no meaning for both at once;
+     * - audio-only (or text + audio) input is not a supported modality mix.
+     */
+    if ((firstFrame || lastFrame) && (referenceVideos.length > 0 || referenceAudios.length > 0)) {
+        throw new SkillError('❌ --reference-video / --reference-audio cannot be combined with --first-frame / --last-frame; use --reference for images instead');
+    }
+    if (referenceAudios.length > 0 && references.length === 0 && referenceVideos.length === 0) {
+        throw new SkillError('❌ --reference-audio needs at least one --reference image or --reference-video alongside it');
     }
     const ratio = input.ratio ?? '16:9';
     const resolution = input.resolution ?? '720p';
@@ -80,7 +121,11 @@ export async function genVideo(input, ctxIn) {
     const seed = toNumber(input.seed, 'seed');
     // Pre-flight validation only when we recognize the model (have its constraints).
     if (descriptor) {
-        validateAgainstConstraints(descriptor, duration, ratio, resolution, references.length);
+        validateAgainstConstraints(descriptor, duration, ratio, resolution, {
+            images: references.length,
+            videos: referenceVideos.length,
+            audios: referenceAudios.length,
+        });
     }
     const ctx = await resolveHttpContext(ctxIn.skillName, {
         apiBaseUrl,
@@ -103,6 +148,16 @@ export async function genVideo(input, ctxIn) {
         payload.lastFrameImage = lastFrame;
     if (references.length > 0)
         payload.referenceImages = references;
+    if (referenceVideos.length > 0)
+        payload.referenceVideos = referenceVideos;
+    if (referenceAudios.length > 0)
+        payload.referenceAudios = referenceAudios;
+    // Web search only fires on text-only input; sending it alongside attachments
+    // would be a knob the model silently ignores.
+    if (isTrue(input.web_search) && !hasVisual)
+        payload.webSearch = true;
+    if (isTrue(input.return_last_frame))
+        payload.returnLastFrame = true;
     if (input.negative_prompt && String(input.negative_prompt).trim()) {
         payload.negativePrompt = String(input.negative_prompt).trim();
     }

package/dist/manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
-  "version": "0.9.20",
-  "generatedAt": "2026-09-05T03:37:29.567Z",
+  "version": "0.9.21",
+  "generatedAt": "2026-09-05T08:18:35.420Z",
   "skills": [
     {
       "id": "export-jianying",
@@ -302,21 +302,21 @@
       "ui": {
         "primary": [
           "prompt",
+          "reference",
           "model",
-          "size"
+          "size",
+          "n"
         ],
         "advanced": [
-          "n",
-          "reference",
-          "negative_prompt",
-          "image_strength"
+          "negative_prompt"
         ],
         "hidden": [
           "json_output",
+          "watermark",
+          "resolution",
           "seed",
           "guidance_scale",
-          "watermark",
-          "resolution"
+          "image_strength"
         ]
       }
     },
@@ -427,11 +427,12 @@
       },
       "ui": {
         "primary": [
-          "topic",
-          "platform",
-          "duration"
+          "topic"
         ],
-        "advanced": [
+        "advanced": [],
+        "hidden": [
+          "platform",
+          "duration",
           "style",
           "ratio",
           "scenes",
@@ -440,9 +441,7 @@
           "headline",
           "subheadline",
           "carousel_items",
-          "caption_lines"
-        ],
-        "hidden": [
+          "caption_lines",
           "stub_image_url",
           "stub_video_url",
           "skip_asset_generation"
@@ -459,7 +458,8 @@
       "triggers": [
         "Text-to-video, AI-generated clip, \"make a short video of ...\"",
         "Generate video with Doubao / Seedance",
-        "Image-to-video, first-frame / last-frame, reference-image-to-video"
+        "Image-to-video, first-frame / last-frame, reference-image-to-video",
+        "Reference video / reference audio, \"same camera move as this clip\", \"use this track\""
       ],
       "entry": {
         "type": "http",
@@ -510,6 +510,28 @@
             },
             "description": "Reference images: local file path, https URL, or data URI. Up to 9; combinable with first_frame / last_frame."
           },
+          "reference_video": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "Reference videos (https URL only, must be publicly reachable). Up to 3. The model borrows their subject, camera work and style. Cannot be combined with first_frame / last_frame."
+          },
+          "reference_audio": {
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "description": "Reference audio (https URL only, must be publicly reachable). Up to 3. Borrows timbre, melody or dialogue. Needs at least one reference image or video alongside it; cannot be combined with first_frame / last_frame."
+          },
+          "web_search": {
+            "type": "boolean",
+            "description": "Let the model search the web for up-to-date subjects before generating. Text-only input — ignored once any image / video / audio is attached."
+          },
+          "return_last_frame": {
+            "type": "boolean",
+            "description": "Also return the generated clip's last frame, to chain it into the next shot"
+          },
           "generate_audio": {
             "type": "boolean",
             "description": "Generate native audio"
@@ -524,7 +546,7 @@
           },
           "seed": {
             "type": "number",
-            "description": "Random seed. Pass the same seed with the same prompt and model to make a run reproducible."
+            "description": "Random seed, -1 for random. Pass the same seed with the same prompt and model to make a run reproducible."
           },
           "person_generation": {
             "type": "string",
@@ -548,19 +570,23 @@
           "prompt",
           "model",
           "duration",
-          "ratio"
+          "ratio",
+          "resolution"
         ],
         "advanced": [
-          "resolution",
           "first_frame",
           "last_frame",
           "reference",
+          "reference_video",
+          "reference_audio",
           "generate_audio",
-          "camera_fixed"
+          "camera_fixed",
+          "web_search",
+          "return_last_frame",
+          "seed"
         ],
         "hidden": [
           "json_output",
-          "seed",
           "negative_prompt",
           "person_generation"
         ]

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@remixmate/cli",
-  "version": "0.9.20",
+  "version": "0.9.21",
   "description": "AI media generation skills for Claude Code / Codex — 12 skills covering image, video, voice, digital human, web screenshot, web recording, script, template registry, rendering, Jianying export, and video deconstruction.",
   "type": "module",
   "main": "dist/index.js",

package/skills/gen-image/skill.json

@@ -84,21 +84,21 @@
   "ui": {
     "primary": [
       "prompt",
+      "reference",
       "model",
-      "size"
+      "size",
+      "n"
     ],
     "advanced": [
-      "n",
-      "reference",
-      "negative_prompt",
-      "image_strength"
+      "negative_prompt"
     ],
     "hidden": [
       "json_output",
+      "watermark",
+      "resolution",
       "seed",
       "guidance_scale",
-      "watermark",
-      "resolution"
+      "image_strength"
     ]
   }
 }

package/skills/gen-script/skill.json

@@ -97,11 +97,12 @@
   },
   "ui": {
     "primary": [
-      "topic",
-      "platform",
-      "duration"
+      "topic"
     ],
-    "advanced": [
+    "advanced": [],
+    "hidden": [
+      "platform",
+      "duration",
       "style",
       "ratio",
       "scenes",
@@ -110,9 +111,7 @@
       "headline",
       "subheadline",
       "carousel_items",
-      "caption_lines"
-    ],
-    "hidden": [
+      "caption_lines",
       "stub_image_url",
       "stub_video_url",
       "skip_asset_generation"

package/skills/gen-video/SKILL.md

@@ -7,12 +7,14 @@ description: |
   - Text-to-video, AI-generated clip, "make a short video of ..."
   - Generate video with Doubao / Seedance
   - Image-to-video, first-frame / last-frame, reference-image-to-video
+  - Omni-modal reference: borrow the look of a reference image, the camera work of a reference video, or the voice / music of a reference audio clip
 
   Even without an explicit "use AI", any request that turns a description into a moving clip should route here.
 triggers:
   - Text-to-video, AI-generated clip, "make a short video of ..."
   - Generate video with Doubao / Seedance
   - Image-to-video, first-frame / last-frame, reference-image-to-video
+  - Reference video / reference audio, "same camera move as this clip", "use this track"
 ---
 
 # AI Video Generation Skill
@@ -52,10 +54,34 @@ so they are absent from the catalog and `--model veo` will fail.
 | **Duration** | 4–15 seconds (continuous integers) |
 | **First / last frame** | yes |
 | **Reference images** | yes, up to 9 |
+| **Reference videos** | yes, up to 3 (public https URLs) |
+| **Reference audio** | yes, up to 3 (public https URLs) |
 | **Generated audio** | yes |
 | **Fixed camera** | yes |
+| **Web search** | yes, text-only input |
 | **Negative prompt** | ignored (Veo-only parameter) |
 
+4k output exists on the standard tier upstream but is **not offered here** — the credit
+pricing table has no 4k row, so a 4k run would be billed at the 720p rate.
+
+### Two input modes, and they do not mix
+
+- **Pinned frames** — `--first-frame` / `--last-frame` fix the exact opening and closing
+  images. Reference images may be added alongside.
+- **Omni-modal reference** — `--reference` (images) / `--reference-video` / `--reference-audio`
+  hand the model material to borrow from; it decides the framing.
+
+Combining a pinned frame with a reference video or audio is rejected (by the CLI, and by the
+backend). Audio alone is not a valid input either: `--reference-audio` needs at least one
+reference image or video with it.
+
+In the prompt, refer to attachments as **"image 1" / "video 2" / "audio 1"**, numbered per
+type in the order you passed them. That is the only way the model can tell them apart —
+file names and asset ids mean nothing to it.
+
+Reference images and videos containing **real human faces are rejected upstream** by the
+Seedance 2.0 content filter; the run fails before it charges.
+
 ## Auth & environment
 
 No skill-local env file — the executing process inherits the system environment.
@@ -123,6 +149,31 @@ remixmate gen-video \
   --duration 8
 ```
 
+### Omni-modal reference (image + video + audio)
+
+Videos and audio must be public https URLs — unlike images they are not uploaded.
+
+```bash
+remixmate gen-video \
+  --prompt "Keep the first-person framing of video 1 and use audio 1 as the score; the product from image 1 is lifted toward the lens" \
+  --reference ./product.png \
+  --reference-video https://example.com/handheld.mp4 \
+  --reference-audio https://example.com/score.mp3 \
+  --duration 8 \
+  --generate-audio
+```
+
+### Fresh subjects (web search)
+
+Only fires on text-only input; attaching any image / video / audio turns it off.
+
+```bash
+remixmate gen-video \
+  --prompt "<a subject the model may not know: a new product, a current event>" \
+  --web-search \
+  --duration 5
+```
+
 ## Common CLI flags
 
 | Flag | Description | Default |
@@ -135,10 +186,14 @@ remixmate gen-video \
 | `--first-frame` | First-frame image: local path, https URL, or data URI | none |
 | `--last-frame` | Last-frame image | none |
 | `--reference` | Reference image (repeatable, max 9) | none |
+| `--reference-video` | Reference video, public https URL (repeatable, max 3) | none |
+| `--reference-audio` | Reference audio, public https URL (repeatable, max 3) | none |
 | `--generate-audio` | Generate native audio | off |
 | `--camera-fixed` | Fixed camera | off |
+| `--web-search` | Search the web first (text-only input) | off |
+| `--return-last-frame` | Also return the clip's last frame, to chain shots | off |
 | `--negative-prompt` | Negative prompt (Veo only; ignored by Seedance) | none |
-| `--seed` | Random seed | none |
+| `--seed` | Random seed; `-1` = random | none |
 | `--person-generation` | Person policy: `allow_all` / `dont_allow` (Veo) | none |
 | `--api-base-url` | Override API root | see above |
 | `--priv-token` | Override token | see above |

package/skills/gen-video/skill.json

@@ -55,6 +55,28 @@
         },
         "description": "Reference images: local file path, https URL, or data URI. Up to 9; combinable with first_frame / last_frame."
       },
+      "reference_video": {
+        "type": "array",
+        "items": {
+          "type": "string"
+        },
+        "description": "Reference videos (https URL only, must be publicly reachable). Up to 3. The model borrows their subject, camera work and style. Cannot be combined with first_frame / last_frame."
+      },
+      "reference_audio": {
+        "type": "array",
+        "items": {
+          "type": "string"
+        },
+        "description": "Reference audio (https URL only, must be publicly reachable). Up to 3. Borrows timbre, melody or dialogue. Needs at least one reference image or video alongside it; cannot be combined with first_frame / last_frame."
+      },
+      "web_search": {
+        "type": "boolean",
+        "description": "Let the model search the web for up-to-date subjects before generating. Text-only input — ignored once any image / video / audio is attached."
+      },
+      "return_last_frame": {
+        "type": "boolean",
+        "description": "Also return the generated clip's last frame, to chain it into the next shot"
+      },
       "generate_audio": {
         "type": "boolean",
         "description": "Generate native audio"
@@ -69,7 +91,7 @@
       },
       "seed": {
         "type": "number",
-        "description": "Random seed. Pass the same seed with the same prompt and model to make a run reproducible."
+        "description": "Random seed, -1 for random. Pass the same seed with the same prompt and model to make a run reproducible."
       },
       "person_generation": {
         "type": "string",
@@ -93,19 +115,23 @@
       "prompt",
       "model",
       "duration",
-      "ratio"
+      "ratio",
+      "resolution"
     ],
     "advanced": [
-      "resolution",
       "first_frame",
       "last_frame",
       "reference",
+      "reference_video",
+      "reference_audio",
       "generate_audio",
-      "camera_fixed"
+      "camera_fixed",
+      "web_search",
+      "return_last_frame",
+      "seed"
     ],
     "hidden": [
       "json_output",
-      "seed",
       "negative_prompt",
       "person_generation"
     ]