@remixmate/cli 0.9.60 → 0.9.62

package/dist/manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
-  "version": "0.9.60",
-  "generatedAt": "2026-09-30T02:10:05.308Z",
+  "version": "0.9.62",
+  "generatedAt": "2026-09-30T08:05:32.139Z",
   "skills": [
     {
       "id": "doc-parse",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@remixmate/cli",
-  "version": "0.9.60",
+  "version": "0.9.62",
   "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/prepare-video-assets/version.json

@@ -2,6 +2,6 @@
   "skillName": "prepare-video-assets",
   "repoName": "agent-skill-media-maker",
   "skillId": "476",
-  "version": "V6",
+  "version": "V7",
   "skillDescription": "Asset-preparation skill: resolves and generates every asset (image / audio / video) referenced by a Video DSL, persists a RenderPlan to the database, and returns a `job_id` for the subsequent `render_video` call.\n\nUse this skill as soon as the user mentions any of these intents:\n- Generate / prepare video assets, resolve assets, render-ready\n- \"Make me a video about X\" (the agent calls gen_script → prepare_video_assets → render_video)\n- Regenerate one asset (image / audio) for a specific scene\n\nNext step: after the user confirms the resolved assets, call `render_video` with the `job_id` returned by this skill.\n\n⚠️ Stop-and-confirm gate: this skill runs only after the user has confirmed the script, and after it returns you must show the resolved assets and wait for the user's explicit confirmation. Never call `render_video` in the same turn."
 }

package/skills/render-video/scripts/_video_probe.py

@@ -175,3 +175,58 @@ def probe_video_duration(url: str) -> Optional[float]:
         return content_length_estimate
 
     return None
+
+
+def probe_video_meta(url: str, timeout: float = 20.0) -> dict:
+    """Probe a remote video's pixel size and duration with ffprobe (reads the URL directly).
+
+    Returns ``{"width": int, "height": int, "duration_ms": int}`` with only the fields it
+    could read; ``{}`` when ffprobe is missing or the probe fails. Callers treat every
+    field as optional.
+
+    为什么要：数字人盒子的宽高比缺省按 3:4 算，而克隆素材多是 9:16 左右的竖版
+    （实测 720×1264）。资产上没有宽高时，模板用 3:4 的盒子 object-fit: cover 裁掉
+    人物的头顶和下半身（conv_XKTQxEBLdZy3i_jIB7IG）。
+    """
+    try:
+        result = subprocess.run(
+            [
+                "ffprobe", "-v", "quiet", "-print_format", "json",
+                "-select_streams", "v:0", "-show_streams", "-show_format", url,
+            ],
+            capture_output=True, text=True, timeout=timeout, stdin=subprocess.DEVNULL,
+        )
+    except (FileNotFoundError, OSError, subprocess.TimeoutExpired) as e:
+        _log(f"   ⚠️  video meta probe unavailable: {type(e).__name__}")
+        return {}
+    if result.returncode != 0:
+        return {}
+    try:
+        info = json.loads(result.stdout or "{}")
+    except json.JSONDecodeError:
+        return {}
+
+    meta: dict = {}
+    streams = info.get("streams") or []
+    if streams:
+        s = streams[0]
+        w, h = s.get("width"), s.get("height")
+        if isinstance(w, int) and isinstance(h, int) and w > 0 and h > 0:
+            # 手机素材常带 90° / 270° 旋转元数据：播放器按旋转后的方向显示。
+            rotation = 0
+            for side in s.get("side_data_list") or []:
+                if isinstance(side.get("rotation"), (int, float)):
+                    rotation = int(side["rotation"])
+            tags_rot = (s.get("tags") or {}).get("rotate")
+            if tags_rot and str(tags_rot).lstrip("-").isdigit():
+                rotation = int(tags_rot)
+            if abs(rotation) % 180 == 90:
+                w, h = h, w
+            meta["width"], meta["height"] = w, h
+    try:
+        dur = float((info.get("format") or {}).get("duration") or 0)
+        if dur > 0:
+            meta["duration_ms"] = int(round(dur * 1000))
+    except (TypeError, ValueError):
+        pass
+    return meta

package/skills/render-video/scripts/render_video.py

@@ -1182,7 +1182,16 @@ def resolve_asset_digital_human(asset: dict, private_token: str, timeout: int) -
             for line in reversed(result.stdout.strip().split("\n")):
                 line = line.strip()
                 if line.startswith("http"):
-                    return {"status": "generated", "url": line}
+                    out = {"status": "generated", "url": line}
+                    # 宽高 / 时长写回资产：模板按它定盒子比例（缺省 3:4 会裁人），
+                    # 按时长决定 onEnd=hide/loop 何时生效。探测失败不影响生成结果。
+                    from _video_probe import probe_video_meta
+                    meta = probe_video_meta(line)
+                    if meta.get("width") and meta.get("height"):
+                        out["width"], out["height"] = meta["width"], meta["height"]
+                    if meta.get("duration_ms"):
+                        out["duration_ms"] = meta["duration_ms"]
+                    return out
         return {"status": "failed", "error": result.stderr.strip()[:1000]}
     except subprocess.TimeoutExpired:
         return {"status": "failed", "error": f"Digital human generation timed out after {dh_timeout}s"}
@@ -1263,6 +1272,11 @@ def _resolve_single_asset(
             asset["generatedBy"]["completedAt"] = now_iso()
             if result.get("audio_length_ms") is not None:
                 asset["duration"] = result["audio_length_ms"]
+            # 视频类资产（数字人）：ms 时长 + 像素尺寸，模板的 ResolvedAsset 契约同名字段。
+            if result.get("duration_ms") is not None:
+                asset["duration"] = result["duration_ms"]
+            if result.get("width") and result.get("height"):
+                asset["width"], asset["height"] = result["width"], result["height"]
             if result.get("subtitles"):
                 asset["ttsSubtitles"] = result["subtitles"]
             # Propagate structured-narration metadata onto the resolved
@@ -2950,6 +2964,23 @@ Examples:
             for asset in image_assets:
                 url = asset.get("url", "")
                 print(f"   {asset['assetId']:<25} {url}")
+
+        # 数字人段也要列出来：模型按这里写成片总结。线上出过 DSL 里没有数字人、
+        # 模型却照着自己的意图汇报「数字人出镜」的事（conv_lvFaCClP7HrW5gDOZU1e），
+        # 没有这一节时它无从核对。没有数字人时明说，而不是什么都不打。
+        avatar_assets = [a for a in render_plan.get("resolvedAssets", []) if a.get("type") == "avatar"]
+        avatar_scenes: dict = {}
+        for entry in render_plan.get("timeline", []):
+            ref = (entry.get("props") or {}).get("avatarAssetId")
+            if ref:
+                avatar_scenes.setdefault(ref, []).append(entry.get("sceneId", "?"))
+        if avatar_assets:
+            print(f"\n🧑 Digital-human segments:")
+            for asset in avatar_assets:
+                scenes_on = ", ".join(avatar_scenes.get(asset["assetId"], [])) or "(no scene)"
+                print(f"   {asset['assetId']:<25} {asset.get('status', '?'):<10} scenes: {scenes_on}  {asset.get('url', '')}")
+        else:
+            print(f"\n🧑 Digital-human segments: none (this render has no presenter)")
         # ─────────────────────────────────────────────────────────────────────
 
         if failed > 0:

package/skills/render-video/version.json

@@ -2,6 +2,6 @@
   "skillName": "render-video",
   "repoName": "agent-skill-media-maker",
   "skillId": "473",
-  "version": "V34",
+  "version": "V35",
   "skillDescription": "Final-render skill: loads a persisted RenderPlan by `job_id` and drives the Remotion engine to produce the final video.\n\nUse this skill as soon as the user mentions any of these intents (after assets are already prepared):\n- Render the video, composite the video, export the video\n- Turn the prepared assets into the final clip\n- Render with Remotion\n\nPrerequisite: assets must already be generated via `prepare_video_assets`. This skill never resolves or regenerates assets — pass it a `job_id` from a previous `prepare_video_assets` call.\n\n⚠️ Stop-and-confirm gate: never call this skill until the user has explicitly confirmed the assets prepared by `prepare_video_assets`. If those assets were prepared in the current turn and the user has not replied since, stop and ask instead of rendering."
 }