@remixmate/cli 0.13.1 → 0.13.3

package/dist/manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
-  "version": "0.13.1",
-  "generatedAt": "2026-10-25T04:48:35.989Z",
+  "version": "0.13.3",
+  "generatedAt": "2026-10-25T14:33:26.570Z",
   "skills": [
     {
       "id": "doc-parse",
@@ -625,6 +625,7 @@
           "motion": {
             "type": "string",
             "enum": [
+              "auto",
               "static",
               "kenburns-in",
               "kenburns-out",
@@ -632,7 +633,7 @@
               "pan-right",
               "float"
             ],
-            "description": "Camera motion for every scene (scenes[].animationHints.motion), replacing the skeleton's alternating push-in / pull-out. **Must** pass when the user picked one: `运镜效果: 缓慢推近（kenburns-in）` → `kenburns-in`."
+            "description": "Camera motion for every scene (scenes[].animationHints.motion), replacing the skeleton's alternating push-in / pull-out. **Must** pass when the user picked one: `运镜效果: 缓慢推近（kenburns-in）` → `kenburns-in`; `运镜效果: 自动搭配（auto）` → `auto` (the template varies the motion scene by scene; do not write animationHints.motion yourself then)."
           },
           "ending_payload": {
             "type": "array",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@remixmate/cli",
-  "version": "0.13.1",
+  "version": "0.13.3",
   "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-script/SKILL.md

@@ -489,7 +489,7 @@ python3 <SkillDir>/scripts/gen_script.py \
 | `--payload KEY=VALUE` | Template-specific card choice, repeatable. `KEY` is a dotted path in `customPayloadSchema` (or `capabilities.frameLevelKeys`), e.g. `<field>=<value>`, `<object>.<field>=<value>`. Value is converted to the declared type (true/false, numbers) and checked against enum / range; undeclared keys are rejected. Written to every scene with sibling keys kept, applied before fit-caption duration estimation. | template default |
 | `--ending-payload KEY=VALUE` | Same as `--payload`, but written only to the ending scene, e.g. `<object>.<field>=<closing line>`. On countdown templates it also appends an ending scene after #1 (it carries the #1 index; fill its narration and the item field `capabilities.countdown.itemProp` names). Errors when the script has no ending scene. | none |
 | `--avatar-id` | Digital-human avatar id (`dh_xxx`) for templates declaring `capabilities.digitalHuman`. Adds asset `asset-avatar` (`type: avatar`, `source: gen-digital-human`, `payload.avatarId`) and sets `visuals.avatar.assetRef` on every scene whose slot reads it — one continuous presenter driven by the narration. Placement: template default, or `--payload digitalHuman.<field>=…` (a photo-only presenter is `--payload digitalHuman.posterUrl=<url>` without this flag). | none |
-| `--motion` | Camera motion for every scene (`animationHints.motion`): `static` / `kenburns-in` / `kenburns-out` / `pan-left` / `pan-right` / `float`. | skeleton alternates in / out |
+| `--motion` | Camera motion for every scene (`animationHints.motion`): `static` / `kenburns-in` / `kenburns-out` / `pan-left` / `pan-right` / `float`. `auto` removes the motion from every scene so the template picks (image-slide rotates push / pan / pull / pan); nothing is locked then. | skeleton alternates in / out |
 | `--font-id` | Font library key (`font.uniq_id`), written to `global.font.fontId`; ab-render resolves and installs the real font at render time. Pass it whenever the user picked a font — the replicate card shows it as `名字（id）`, e.g. `字体: <名字>（<uniqId>）`; pass the id in the parentheses. Never pass a CSS family or the display name: an unknown key falls back to the template font with no error. | template font |
 | `--font-name` | Display name of the picked font → `global.font.fontName` (display only, never used for rendering). Pass it with `--font-id`. | — |
 | `--list-fonts` | Print the live font library (`/font/page`: id, name, lang, category, license) and exit; no script is generated and `--topic` is not needed. The ids it prints are the only valid `--font-id` values — use it when the user asks which fonts exist or names a font without its id. | — |

package/skills/gen-script/scripts/gen_script.py

@@ -1104,7 +1104,38 @@ def _estimate_fit_caption_duration(
     return max(parts) + duration_model.get("tailPaddingSec", 0)
 
 
-def _estimate_fit_images_duration(custom_payload: dict, model: dict | None, fps: int = 30) -> float:
+
+
+_READING_UNIT_RE = re.compile(r"[\u3400-\u9fff\uf900-\ufaff]|[A-Za-z0-9]+")
+
+
+def _reading_units(text: str) -> int:
+    return len(_READING_UNIT_RE.findall(text or ""))
+
+
+def _sequence_floor_frames(sequence: dict, preset_timing: dict, text: str, fps: int) -> int:
+
+
+
+
+
+    min_sec = sequence.get("minSec")
+    if not (isinstance(min_sec, (int, float)) and min_sec > 0):
+        floor = preset_timing.get("readingFloor")
+        units = _reading_units(text)
+        if not isinstance(floor, dict) or units == 0:
+            return 0
+        min_sec = floor["baseSec"] + floor["secPerUnit"] * units
+    return math.floor(min_sec * fps + 0.5)
+
+
+def _estimate_fit_images_duration(custom_payload: dict, model: dict | None, fps: int = 30,
+                                  headline: str = "") -> float:
+
+
+
+
+
 
 
 
@@ -1138,7 +1169,22 @@ def _estimate_fit_images_duration(custom_payload: dict, model: dict | None, fps:
             return max(1, math.floor(item.get("holdSec", item["sourceDurationSec"]) * fps + 0.5))
         return max(min_frames, math.floor(item.get("holdSec", base_hold) * fps + 0.5))
 
-    return sum(item_frames(item) for item in sequence["items"]) / fps
+    frames = [item_frames(item) for item in sequence["items"]]
+    natural = sum(frames)
+
+    title_override = ((sequence.get("text") or {}).get("title") or {}).get("text")
+    candidates = (title_override, custom_payload.get("title"),
+                  (custom_payload.get("templateData") or {}).get("title"), headline)
+    text = next((c for c in candidates if isinstance(c, str) and c.strip()), "")
+    floor_frames = _sequence_floor_frames(sequence, preset_timing, text, fps)
+    if floor_frames > natural:
+        if all(item.get("type") == "video" for item in sequence["items"]):
+            rate = timing.get("floorMinVideoRate")
+            if rate is None:
+                raise ValueError(f"fit-images with a floor requires durationModel.{key}.floorMinVideoRate")
+            floor_frames = min(floor_frames, sum(math.floor(f / rate) for f in frames))
+        natural = max(natural, floor_frames)
+    return natural / fps
 
 
 def _probe_sequence_video_duration(url: str) -> float | None:
@@ -1391,7 +1437,7 @@ def _build_carousel_caption_dsl(
 
     effective_duration = duration
     if duration_strategy == "fit-images":
-        effective_duration = _estimate_fit_images_duration(custom_payload, duration_model)
+        effective_duration = _estimate_fit_images_duration(custom_payload, duration_model, headline=headline)
     if duration_strategy == "fit-caption":
         est = _estimate_fit_caption_duration(custom_payload, duration_model, template_id)
         if est > 0:
@@ -1873,18 +1919,23 @@ def _apply_scene_payload(
 
     writes = _parse_payload_specs(template_config, payload_specs)
     if motion:
-        allowed = ("static", "kenburns-in", "kenburns-out", "pan-left", "pan-right", "float")
+        allowed = ("auto", "static", "kenburns-in", "kenburns-out", "pan-left", "pan-right", "float")
         if motion not in allowed:
             raise ValueError(f"--motion {motion!r}: choose one of: {', '.join(allowed)}")
 
     for scene in dsl.get("scenes", []):
         _write_payload(scene.setdefault("customPayload", {}), writes)
-        if motion:
-            hints = scene.get("animationHints") if isinstance(scene.get("animationHints"), dict) else {}
-            scene["animationHints"] = {**hints, "motion": motion}
+        hints = scene.get("animationHints") if isinstance(scene.get("animationHints"), dict) else None
+        if motion == "auto":
+
+
+            if hints is not None:
+                hints.pop("motion", None)
+        elif motion:
+            scene["animationHints"] = {**(hints or {}), "motion": motion}
     for parts, _ in writes:
         _lock_scene_path(dsl, "customPayload." + ".".join(parts))
-    if motion:
+    if motion and motion != "auto":
         _lock_scene_path(dsl, "animationHints.motion")
 
 
@@ -2817,7 +2868,8 @@ Examples:
     parser.add_argument(
         "--motion", default=None,
         help="Camera motion for every scene (animationHints.motion): static / kenburns-in / kenburns-out / "
-             "pan-left / pan-right / float. Replaces the skeleton's alternating default.",
+             "pan-left / pan-right / float. Replaces the skeleton's alternating default. `auto` removes the "
+             "motion from every scene so the template picks (image-slide rotates push / pan / pull / pan).",
     )
     parser.add_argument("--allow-digital-human", action="store_true", help="Allow digital-human assets")
     parser.add_argument("--avatar-id", default=None, help="Digital-human avatar id (dh_xxx) for templates declaring capabilities.digitalHuman: adds one gen-digital-human asset referenced by every scene's visuals.avatar.assetRef (one continuous presenter driven by the narration). Placement stays the template default unless set with --payload digitalHuman.<field>=...")

package/skills/gen-script/skill.json

@@ -83,6 +83,7 @@
       "motion": {
         "type": "string",
         "enum": [
+          "auto",
           "static",
           "kenburns-in",
           "kenburns-out",
@@ -90,7 +91,7 @@
           "pan-right",
           "float"
         ],
-        "description": "Camera motion for every scene (scenes[].animationHints.motion), replacing the skeleton's alternating push-in / pull-out. **Must** pass when the user picked one: `运镜效果: 缓慢推近（kenburns-in）` → `kenburns-in`."
+        "description": "Camera motion for every scene (scenes[].animationHints.motion), replacing the skeleton's alternating push-in / pull-out. **Must** pass when the user picked one: `运镜效果: 缓慢推近（kenburns-in）` → `kenburns-in`; `运镜效果: 自动搭配（auto）` → `auto` (the template varies the motion scene by scene; do not write animationHints.motion yourself then)."
       },
       "ending_payload": {
         "type": "array",