@remixmate/cli 0.9.59 → 0.9.61

package/dist/manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
-  "version": "0.9.59",
-  "generatedAt": "2026-09-29T12:43:37.496Z",
+  "version": "0.9.61",
+  "generatedAt": "2026-09-30T06:42:11.032Z",
   "skills": [
     {
       "id": "doc-parse",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@remixmate/cli",
-  "version": "0.9.59",
+  "version": "0.9.61",
   "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/export-jianying/scripts/gen_jianying_draft.py

@@ -728,15 +728,14 @@ def _encode_url(raw_url: str) -> str:
     return urllib.parse.urlunparse(parsed._replace(path=encoded_path))
 
 
-def _url_without_query(raw_url: str) -> str:
-    """日志里只打对象地址：带签名的 query（Signature / OSSAccessKeyId）不进日志。"""
-    parsed = urllib.parse.urlparse(raw_url)
-    return urllib.parse.urlunparse(parsed._replace(query="", fragment=""))
+class DraftUploadError(RuntimeError):
+    """后处理 ZIP 传回失败。调用方据此降级为交付后端原始 ZIP，而不是整次导出失败。"""
 
 
 def upload_draft_zip(zip_path: str, file_name: str) -> str:
     """
     把后处理过的 ZIP 传回 ab-api（POST /file/uploadJianYingDraft），返回带签名的下载地址。
+    失败抛 DraftUploadError（带 HTTP 状态码 / 业务 msg）。
 
     为什么必须传回：后处理（字幕样式 / textLayers）是在跑脚本的这台机器上做的。
     服务端 agent 的本地文件用户拿不到，不传回的话用户下载到的仍是后端生成的原始 ZIP，
@@ -771,28 +770,32 @@ def upload_draft_zip(zip_path: str, file_name: str) -> str:
     )
     try:
         with urllib.request.urlopen(req, timeout=600) as resp:
-            result = json.loads(resp.read().decode("utf-8"))
+            raw = resp.read().decode("utf-8", errors="replace")
     except urllib.error.HTTPError as e:
-        print(f"❌ draft upload failed (HTTP {e.code})", file=sys.stderr)
-        sys.exit(1)
+        # 网关（413 请求体过大、404 路由未上线）返回的是 HTML，只取一小段帮定位。
+        snippet = e.read().decode("utf-8", errors="replace")[:200].replace("\n", " ")
+        raise DraftUploadError(f"HTTP {e.code} {e.reason}: {snippet}") from e
     except (urllib.error.URLError, OSError, ConnectionError) as e:
-        print(f"❌ draft upload failed: {e}", file=sys.stderr)
-        sys.exit(1)
+        raise DraftUploadError(f"network error: {e}") from e
 
+    try:
+        result = json.loads(raw)
+    except json.JSONDecodeError as e:
+        raise DraftUploadError(f"non-JSON response: {raw[:200]}") from e
     if result.get("code") != 0:
-        print(f"❌ draft upload failed: {result.get('msg', 'unknown error')}", file=sys.stderr)
-        sys.exit(1)
+        raise DraftUploadError(f"API error: {result.get('msg', 'unknown error')}")
     url = (result.get("data") or {}).get("downloadUrl", "")
     if not url:
-        print("❌ draft upload succeeded but no download URL was returned", file=sys.stderr)
-        sys.exit(1)
+        raise DraftUploadError("upload succeeded but no download URL was returned")
     print("   ✅ uploaded")
     return url
 
 
 def download_zip(download_url: str, output_path: str) -> None:
     """下载 ZIP 文件到本地"""
-    print(f"\n⬇️  Downloading draft ZIP: {_url_without_query(download_url)}")
+    # 不打印地址：去掉签名的地址打开就是 403，而模型会把 stdout 里任何像链接的东西
+    # 转交给用户（conv_U9oYmHmE1iJbx2qETDuh 就是把这一行当成了下载链接）。
+    print("\n⬇️  Downloading draft ZIP for post-processing...")
     safe_url = _encode_url(download_url)
     try:
         urllib.request.urlretrieve(safe_url, output_path)
@@ -1203,11 +1206,19 @@ Scene fields:
     elif args.scenes and conversation_id:
         # 手写 scenes 时模型只能从聊天记录里拼素材 URL，而多轮之间它看不到之前的工具结果，
         # 很容易拼出过期的旧版素材（线上会话里就是把用户改过的 v3 配音换回了 v1）。
-        print(
-            "⚠️  --scenes was hand-written; omit --scenes/--from-job-id to export the latest prepared "
-            "render job of this conversation instead of URLs copied from chat history",
-            file=sys.stderr,
-        )
+        #
+        # 只在会话里**真有**准备好的任务时才提醒：纯数字人 / 纯生图的会话没有 RenderPlan，
+        # 手写 scenes 是唯一的路，这时提醒只会让模型怀疑自己（conv_U9oYmHmE1iJbx2qETDuh）。
+        try:
+            latest = _render_job_client().latest_job(conversation_id, PRIVATE_TOKEN)
+        except RuntimeError:
+            latest = None
+        if latest:
+            print(
+                f"⚠️  --scenes was hand-written, but this conversation has a prepared render job "
+                f"(jobId={latest['jobId']}); omit --scenes to export it instead of URLs copied from chat history",
+                file=sys.stderr,
+            )
 
     # --from-job-id 模式：从数据库加载 RenderPlan
     if args.from_job_id:
@@ -1291,11 +1302,13 @@ Scene fields:
     print(f"\n🎉 Jianying draft generated successfully!")
     print(f"   filename: {file_name}")
 
+    # 在 agent 里（有 CONVERSATION_ID）本地文件落在服务器上，用户拿不到：除非显式给了
+    # --output，否则不留副本。conv_U9oYmHmE1iJbx2qETDuh 一次导出在服务器 cwd 里留了 3 个 5MB 的 ZIP。
+    keep_local = bool(args.output) or (not args.no_download and not conversation_id)
+    styled = True
     output_path = ""
     if needs_postprocess:
-        # 后处理必须先把 ZIP 拿到本地。--no-download 时落到临时文件，传回后删掉，
-        # 不在跑脚本的机器（常常是服务器）上留垃圾。
-        keep_local = not args.no_download
+        # 后处理必须先把 ZIP 拿到本地；不保留副本时落到临时文件，用完删掉。
         if keep_local:
             output_path = args.output or f"jianying_draft_{int(time.time())}.zip"
         else:
@@ -1306,15 +1319,25 @@ Scene fields:
             postprocess_draft_zip(output_path, scenes)
             # 用户拿到的链接必须指向后处理之后的版本，否则字幕样式 / textLayers 全部丢失。
             download_url = upload_draft_zip(output_path, file_name)
+        except DraftUploadError as e:
+            # 降级而不是失败：后端生成的原始 ZIP 已经包含素材、配音和字幕文本，只是没有
+            # 套字幕样式 / textLayers。整次失败的话模型只会原样重试（每次再生成一遍草稿），
+            # 用户什么都拿不到。
+            styled = False
+            print(f"⚠️  could not upload the styled draft ({e}); delivering the backend draft instead.", file=sys.stderr)
+            print("   subtitle text is included, but the pill subtitle style / textLayers were NOT applied. "
+                  "Do not retry the same call; report this to the user.", file=sys.stderr)
         finally:
             if not keep_local and os.path.exists(output_path):
                 os.remove(output_path)
                 output_path = ""
-    elif not args.no_download:
+    elif keep_local:
         output_path = args.output or f"jianying_draft_{int(time.time())}.zip"
         download_zip(download_url, output_path)
 
     print_draft_summary(scenes, args.width, args.height, draft_root_path)
+    if needs_postprocess:
+        print(f"   subtitle styling applied: {'yes' if styled else 'NO (upload failed, backend draft delivered)'}")
     print(f"\n   download URL: {download_url}")
     if output_path:
         print(f"   local file: {output_path}")

package/skills/export-jianying/version.json

@@ -2,6 +2,6 @@
   "skillName": "export-jianying",
   "repoName": "agent-skill-media-maker",
   "skillId": "554",
-  "version": "V6",
+  "version": "V7",
   "skillDescription": "Jianying (CapCut) draft-generation skill. Packages asset URLs into a draft ZIP that Jianying can import; supports automatic conversion from a RenderPlan (calls ab-api /file/generateJianYing).\n\nUse this skill as soon as the user mentions any of these intents:\n- Export to Jianying, Jianying draft, package for Jianying, import into Jianying\n- Export materials to the Jianying format, generate a Jianying project\n- Bundle video / image / audio into a Jianying draft\n- Export a Jianying draft from a RenderPlan\n\nEven when the user does not say \"Jianying\" explicitly, use this skill whenever they want to package materials into a draft that can be edited in Jianying."
 }

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/render_video.py

@@ -1516,7 +1516,12 @@ def resolve_digital_human_segments(
                     else:
                         local = dhs.concat_drive_audio(pieces, out_dir, asset_id, ffmpeg)
                         from upload_video import upload_media_file
-                        url = upload_media_file(local, title=f"digital-human drive {asset_id}")["fileUrl"]
+                        url = upload_media_file(
+                            local,
+                            title=f"digital-human drive {asset_id}",
+                            role="dh_drive_audio",
+                            retention="intermediate",
+                        )["fileUrl"]
                         total = sum(p["durationSec"] for p in pieces)
                         log(f"{asset_id}: drive audio for {len(pieces)} scene(s), {total:.1f}s")
                 payload["audioUrl"] = url
@@ -2945,6 +2950,23 @@ 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:
@@ -3064,11 +3086,18 @@ Examples:
 
                 upload_title = upload_title_hint
                 LogPrint(f"\n📤 Uploading video to OSS...", file=sys.stderr)
-                upload_result = upload_media_file(file_path=output_path, title=upload_title)
+                upload_result = upload_media_file(
+                    file_path=output_path,
+                    title=upload_title,
+                    role="final_video",
+                    retention="output",
+                )
                 manifest["upload"] = {
                     "fileUrl": upload_result["fileUrl"],
                     "title": upload_title,
                     "uploadedAt": now_iso(),
+                    # ab-api 保存 manifest 时按 fileId 给成片建语义卡 / 片段 / 血缘
+                    "fileId": upload_result.get("fileId"),
                 }
                 if manifest_path:
                     save_json(manifest, manifest_path)

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

@@ -8,9 +8,11 @@
   `<MM_API_BASE_URL>/file/uploadMediaFile`，解析响应 JSON，输出 fileUrl。
 
 用法:
-  python3 upload_video.py --file output/video.mp4
-  python3 upload_video.py --file output/video.mp4 --title "我的视频"
-  python3 upload_video.py --file output/video.mp4 --json-output
+  python3 upload_video.py --file output/video.mp4 --role final_video
+  python3 upload_video.py --file output/video.mp4 --role final_video --title "我的视频"
+  python3 upload_video.py --file output/video.mp4 --role final_video --json-output
+
+环境变量 PRIV_TOKEN 必填（接口在 ab-api 私有组，产物落素材表并归到调用者名下）。
 
 环境变量:
   MM_API_BASE_URL - API 根地址（默认 MM_API_BASE_URL 环境变量或 https://api-agent.remixmate.ai/api）
@@ -39,9 +41,9 @@ def _guess_content_type(file_path: str) -> str:
     return ctype or "application/octet-stream"
 
 
-def _build_multipart_body(file_path: str, title: str = None) -> (bytes, str):
+def _build_multipart_body(file_path: str, fields: dict) -> (bytes, str):
     """
-    手动构建 multipart/form-data body。
+    手动构建 multipart/form-data body。fields 里值为空的字段不发。
 
     返回 (body_bytes, content_type_header)。
     """
@@ -49,12 +51,13 @@ def _build_multipart_body(file_path: str, title: str = None) -> (bytes, str):
     crlf = b"\r\n"
     parts = []
 
-    # title 字段（可选）
-    if title:
+    for name, value in fields.items():
+        if value in (None, ""):
+            continue
         parts.append(("--" + boundary).encode("utf-8"))
-        parts.append(b'Content-Disposition: form-data; name="title"')
+        parts.append(f'Content-Disposition: form-data; name="{name}"'.encode("utf-8"))
         parts.append(b"")
-        parts.append(title.encode("utf-8"))
+        parts.append(str(value).encode("utf-8"))
 
     # file 字段
     file_name = os.path.basename(file_path)
@@ -87,13 +90,21 @@ def upload_media_file(
     api_base_url: str = None,
     title: str = None,
     timeout: int = 600,
+    *,
+    role: str,
+    retention: str = None,
 ) -> dict:
     """
-    将本地媒体文件以 multipart/form-data 形式上传到 ab-api。
+    将本地媒体文件以 multipart/form-data 形式上传到 ab-api，并落素材表。
+
+    role 必填：素材语义角色（final_video / dh_drive_audio / source_audio ...），由调用方
+    按「这是什么」声明——ab-api 不再按文件类型猜。retention 可选（intermediate / output / user）。
 
-    返回服务端 data 字段，通常形如 {"fileUrl": "https://..."}。
+    返回服务端 data 字段，形如 {"fileUrl": "https://...", "fileId": 123, "fileUid": "file_xxx"}。
     上传失败会抛出异常。
     """
+    if not role:
+        raise ValueError("upload_media_file: role is required")
     if not os.path.exists(file_path):
         raise FileNotFoundError(f"file not found: {file_path}")
 
@@ -101,14 +112,22 @@ def upload_media_file(
     url = f"{api_base_url}/file/uploadMediaFile"
 
     file_size = os.path.getsize(file_path)
-    print(f"📤 Uploading: {file_path} ({file_size / 1024 / 1024:.2f} MB)", file=sys.stderr)
+    print(f"📤 Uploading: {file_path} ({file_size / 1024 / 1024:.2f} MB, role={role})", file=sys.stderr)
     print(f"   target: {url}", file=sys.stderr)
 
-    body, content_type = _build_multipart_body(file_path, title=title)
+    body, content_type = _build_multipart_body(
+        file_path, {"title": title, "role": role, "retention": retention}
+    )
+    # 该接口在 ab-api 私有组：产物要落素材表、归到调用者名下，必须带 PrivToken。
     headers = {
         "Content-Type": content_type,
         "Content-Length": str(len(body)),
+        "X-Priv-Token": os.environ.get("PRIV_TOKEN", ""),
+        "x-invoke-skill": "render-video",
     }
+    conversation_id = os.environ.get("CONVERSATION_ID", "")
+    if conversation_id:
+        headers["x-conversation-id"] = conversation_id
 
     # Use http.client directly to avoid urllib RemoteDisconnected issues
     # with servers that return 'connection: close'
@@ -161,6 +180,17 @@ def main():
     parser = argparse.ArgumentParser(description="Upload a media file to ab-api / Alibaba Cloud OSS")
     parser.add_argument("--file", required=True, help="Local file path")
     parser.add_argument("--title", default=None, help="File title (optional, defaults to filename)")
+    parser.add_argument(
+        "--role",
+        required=True,
+        help="Asset role, e.g. final_video / dh_drive_audio / source_audio (required)",
+    )
+    parser.add_argument(
+        "--retention",
+        default=None,
+        choices=["intermediate", "output", "user"],
+        help="Retention policy (optional)",
+    )
     parser.add_argument(
         "--api-base-url",
         default=None,
@@ -177,6 +207,8 @@ def main():
             api_base_url=args.api_base_url,
             title=args.title,
             timeout=args.timeout,
+            role=args.role,
+            retention=args.retention,
         )
     except Exception as e:
         print(f"❌ {e}", file=sys.stderr)

package/skills/render-video/version.json

@@ -2,6 +2,6 @@
   "skillName": "render-video",
   "repoName": "agent-skill-media-maker",
   "skillId": "473",
-  "version": "V33",
+  "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."
 }

package/skills/video-parser/scripts/deconstruct_video.py

@@ -197,6 +197,13 @@ def upload_audio(audio_path: str) -> str:
     body += b'Content-Disposition: form-data; name="title"\r\n\r\n'
     body += filename.encode()
     body += b"\r\n"
+    # role / retention：ab-api 落素材表时必填角色。抽离音频只为 ASR，属中间产物；
+    # 源视频是第三方的，检索侧据 role 默认排除（license=third_party_unknown）。
+    for name, value in (("role", "source_audio"), ("retention", "intermediate")):
+        body += f"--{boundary}\r\n".encode()
+        body += f'Content-Disposition: form-data; name="{name}"\r\n\r\n'.encode()
+        body += value.encode()
+        body += b"\r\n"
     # 结束
     body += f"--{boundary}--\r\n".encode()
 
@@ -207,6 +214,8 @@ def upload_audio(audio_path: str) -> str:
     }
     if AGENT_NAME:
         headers["x-invoke-agent"] = AGENT_NAME
+    if os.environ.get("CONVERSATION_ID"):
+        headers["x-conversation-id"] = os.environ["CONVERSATION_ID"]
 
     req = urllib.request.Request(url, data=body, headers=headers, method="POST")
 

package/skills/video-parser/version.json

@@ -2,6 +2,6 @@
   "skillName": "video-parser",
   "repoName": "agent-skill-media-maker",
   "skillId": "553",
-  "version": "V2",
+  "version": "V3",
   "skillDescription": "Video deconstruction skill. Splits a video into reusable content assets — audio, ASR transcript, scene segments, keyframe images.\n\nUse this skill as soon as the user mentions any of these intents:\n- Deconstruct / split / analyze / parse a video\n- Extract keyframes, extract the script from a video, transcribe a video\n- Pull content assets or raw material out of a video\n\nEven when the user does not say \"deconstruct\" explicitly, use this skill whenever they want to extract script text, keyframes, or structured information from a video."
 }

package/skills/web-screenshot/scripts/_media_upload.py

@@ -83,6 +83,8 @@ def _submit(
         "coverAtSec": str(cover_at_sec),
         "resolveCdn": "1" if resolve_cdn else "0",
         "ext": ext,
+        # 素材角色：ab-api 按它落 file.role（录屏贡献 video_clip 能力、按成品保留）
+        "role": "screen_record",
     }
     if title:
         query["title"] = title
@@ -230,4 +232,79 @@ def finalize_recording(
     )
 
 
-__all__ = ["finalize_recording", "FinalizeError"]
+DEFAULT_ABAPI_BASE_URL = "https://api-agent.remixmate.ai/api"
+
+# 分镜里承载「画面在讲什么」的文本字段（caption / title-card / type 等场景）
+_STORY_TEXT_KEYS = ("title", "subtitle", "text", "caption", "label", "content")
+
+
+def storyboard_text(story: Optional[dict]) -> str:
+    """把分镜里的可读文本收成一段：标题卡、字幕条、打字内容等，按场景顺序拼接。
+
+    录屏本身没有旁白，这段文本就是它最便宜的语义——生产者手上现成有，不需要 ASR。
+    """
+    if not isinstance(story, dict):
+        return ""
+    parts: list[str] = []
+    for scene in story.get("scenes") or []:
+        if not isinstance(scene, dict):
+            continue
+        for key in _STORY_TEXT_KEYS:
+            val = scene.get(key)
+            if isinstance(val, str) and val.strip():
+                parts.append(val.strip())
+    seen: set[str] = set()
+    out = [p for p in parts if not (p in seen or seen.add(p))]
+    return "\n".join(out)
+
+
+def annotate_asset(
+    *,
+    private_token: str,
+    file_id: Optional[int],
+    file_url: str,
+    text: str,
+    source_url: str,
+    duration_sec: Optional[float],
+    request_timeout: float = 30.0,
+) -> None:
+    """把录屏的语义写进 ab-api 素材库（POST /asset/annotate）：分镜文本 + 来源页面。
+
+    分镜里没有逐场景时间戳，整条录屏作为一个片段。失败抛 FinalizeError，调用方只记日志——
+    语义是附加信息，不能让「录屏已完成」失败。见 ab-platform/docs/asset-semantic-library-design.md §6.1。
+    """
+    if not private_token or not (file_id or file_url):
+        return
+    base = (os.environ.get("MM_API_BASE_URL") or DEFAULT_ABAPI_BASE_URL).rstrip("/")
+    payload: dict = {"provenance": {"sourceUrl": source_url, "producer": SKILL_NAME}}
+    if file_id:
+        payload["fileId"] = int(file_id)
+    else:
+        payload["fileUrl"] = file_url
+    if text:
+        payload["text"] = text
+        if isinstance(duration_sec, (int, float)) and duration_sec > 0:
+            payload["segments"] = [
+                {"startSec": 0, "endSec": round(float(duration_sec), 2), "text": text, "shot": "screen_record"}
+            ]
+    headers = _headers(
+        private_token,
+        content_type="application/json",
+        conversation_id=os.environ.get("CONVERSATION_ID") or None,
+    )
+    req = urllib.request.Request(
+        f"{base}/asset/annotate",
+        data=json.dumps(payload, ensure_ascii=False).encode("utf-8"),
+        headers=headers,
+        method="POST",
+    )
+    try:
+        with urllib.request.urlopen(req, timeout=request_timeout) as resp:
+            result = json.loads(resp.read().decode("utf-8"))
+    except (urllib.error.URLError, OSError) as exc:
+        raise FinalizeError(f"/asset/annotate 网络错误: {exc}") from exc
+    if result.get("code") != 0:
+        raise FinalizeError(f"/asset/annotate code={result.get('code')}: {result.get('msg')}")
+
+
+__all__ = ["finalize_recording", "FinalizeError", "annotate_asset", "storyboard_text"]

package/skills/web-screenshot/scripts/record.py

@@ -23,7 +23,12 @@ from _media_screenshot import (  # noqa: E402
     template,
     trim,
 )
-from _media_upload import finalize_recording  # noqa: E402
+from _media_upload import (  # noqa: E402
+    FinalizeError,
+    annotate_asset,
+    finalize_recording,
+    storyboard_text,
+)
 
 
 def main() -> None:
@@ -253,6 +258,19 @@ def main() -> None:
     vod_ref = result.get("vodRef") or ""
     file_id = result.get("fileId")
 
+    # 语义入库：分镜文本 + 来源页面。失败只提示，不影响录屏结果。
+    try:
+        annotate_asset(
+            private_token=priv_token,
+            file_id=file_id,
+            file_url=cdn_url,
+            text=storyboard_text(story),
+            source_url=cfg.get("url", ""),
+            duration_sec=duration if isinstance(duration, (int, float)) else None,
+        )
+    except FinalizeError as e:
+        print(f"[record] 录屏语义写入素材库失败（不影响录屏）：{e}", file=sys.stderr)
+
     # 上传成功，默认删本地 webm（VOD 已持有），除非 --keep-webm
     if not args.keep_webm:
         try:

package/skills/web-screenshot/version.json

@@ -2,6 +2,6 @@
   "skillName": "web-screenshot",
   "repoName": "agent-skill-media-maker",
   "skillId": "555",
-  "version": "V6",
+  "version": "V7",
   "skillDescription": "Web-page screenshot skill (still images only, png/jpg), built on Playwright Python — captures any URL to a local image file.\nSupports: full-page / viewport / element / region capture, device emulation, waiting for dynamic content, hiding or masking distracting elements, and static annotations (highlight box / arrow / caption / numbered sequence / redact / code-line highlight).\n\nImages only (`.png` / `.jpg`). For video (`.webm` / screen recording / storyboard clips) use web-record / `web_record`.\n\nUse this skill immediately whenever the user asks for any of:\n- Web page screenshot, screen capture, full-page screenshot, long screenshot\n- Capture a specific element / region, partial screenshot, focus on an area\n- Hide or mask elements before capturing (cookie banner, sensitive information)\n- Annotate a still screenshot (highlight box / arrow / label / caption bar / numbering)\n- Highlight lines L5-L20 of a file and screenshot it\n- Wait for an element to appear, then capture\n- Mobile / device-emulated screenshot (iPhone / Pixel, etc.)\n- Capture with cookies / a logged-in session / storageState\n\nEven when the user does not say \"playwright\", any request to screenshot a URL and get a local image file should route here."
 }