@remixmate/cli 0.9.17 → 0.9.19

package/skills/gen-script/skill.json

@@ -6,39 +6,116 @@
   "title": "Video Script Generation",
   "description": "Video script generation: turn a topic into a structured Video DSL (JSON) that describes the full video — scene structure, asset requirements, and narrative flow.",
   "auth": "none",
-  "envVars": ["DEFAULT_IMAGE_MODEL", "DEFAULT_VIDEO_MODEL", "STUB_IMAGE_URL", "STUB_VIDEO_URL"],
+  "envVars": [
+    "DEFAULT_IMAGE_MODEL",
+    "DEFAULT_VIDEO_MODEL",
+    "STUB_IMAGE_URL",
+    "STUB_VIDEO_URL"
+  ],
   "scriptPath": "scripts/gen_script.py",
   "parameters": {
     "type": "object",
     "properties": {
-      "topic": { "type": "string", "description": "Video topic (required)" },
+      "topic": {
+        "type": "string",
+        "description": "Video topic (required)"
+      },
       "platform": {
         "type": "string",
-        "enum": ["douyin", "xiaohongshu", "bilibili", "wechat", "youtube", "generic"],
+        "enum": [
+          "douyin",
+          "xiaohongshu",
+          "bilibili",
+          "wechat",
+          "youtube",
+          "generic"
+        ],
         "description": "Target platform"
       },
-      "duration": { "type": "number", "description": "Target duration in seconds" },
-      "style": { "type": "string", "description": "Style tag" },
-      "ratio": { "type": "string", "description": "Aspect ratio, e.g. 16:9 or 9:16" },
-      "scenes": { "type": "number", "description": "Scene count" },
-      "voice_id": { "type": "string", "description": "Narration voice id. Default depends on the bound template's outputLanguage; query gen_voice with list_voices=true to see available ids." },
-      "template_id": { "type": "string", "description": "Template id (e.g. html-slide). The template owns outputLanguage and may also declare a defaultVoiceId; both flow into the produced DSL." },
-      "headline": { "type": "string", "description": "On-screen headline (recommended 4-12 chars / ~3 words). Stored at meta.headline and pushed into every scene's textLayers[role=headline] so the template can render it as the top big-text. **Must** be set when the user explicitly provided a headline / main title; without it, headline falls back to the long-form topic and overflows the top text layer." },
-      "subheadline": { "type": "string", "description": "On-screen subheadline (project name / slogan / source, e.g. 'Pixelle-Video'). Stored at meta.subheadline and pushed into every scene's textLayers[role=subheadline] so the template can render it as the top small-text. **Must** be set when the user explicitly provided a subtitle / project name. Note: this is the on-screen subheadline, not the CC subtitle (global.subtitle) — they are independent." },
+      "duration": {
+        "type": "number",
+        "description": "Target duration in seconds"
+      },
+      "style": {
+        "type": "string",
+        "description": "Style tag"
+      },
+      "ratio": {
+        "type": "string",
+        "description": "Aspect ratio, e.g. 16:9 or 9:16"
+      },
+      "scenes": {
+        "type": "number",
+        "description": "Scene count"
+      },
+      "voice_id": {
+        "type": "string",
+        "description": "Narration voice id. Default depends on the bound template's outputLanguage; query gen_voice with list_voices=true to see available ids."
+      },
+      "template_id": {
+        "type": "string",
+        "description": "Template id (e.g. html-slide). The template owns outputLanguage and may also declare a defaultVoiceId; both flow into the produced DSL."
+      },
+      "headline": {
+        "type": "string",
+        "description": "On-screen headline (recommended 4-12 chars / ~3 words). Stored at meta.headline and pushed into every scene's textLayers[role=headline] so the template can render it as the top big-text. **Must** be set when the user explicitly provided a headline / main title; without it, headline falls back to the long-form topic and overflows the top text layer."
+      },
+      "subheadline": {
+        "type": "string",
+        "description": "On-screen subheadline (project name / slogan / source, e.g. 'Pixelle-Video'). Stored at meta.subheadline and pushed into every scene's textLayers[role=subheadline] so the template can render it as the top small-text. **Must** be set when the user explicitly provided a subtitle / project name. Note: this is the on-screen subheadline, not the CC subtitle (global.subtitle) — they are independent."
+      },
       "carousel_items": {
         "type": "array",
-        "items": { "type": "string" },
+        "items": {
+          "type": "string"
+        },
         "description": "Media URLs for the template's image/video carousel (e.g. spotlight-card's middle carousel). When provided together with a template_id whose capabilities.payloadStyle=carousel-caption, these URLs are placed directly into customPayload.carousel.items as existing assets — NO AI image generation is triggered. **Must** pass when the user explicitly provides image/video URLs for carousel-style templates (spotlight-card, etc.). Each element is a full URL string."
       },
       "caption_lines": {
         "type": "array",
-        "items": { "type": "string" },
+        "items": {
+          "type": "string"
+        },
         "description": "Bottom typewriter text lines for templates that support a caption/typewriter area (e.g. spotlight-card). Each element is one line of text. Supports **emphasis** syntax (rendered with accent color). **Must** pass when the user explicitly provides bullet-point text / bottom copy for the video."
       },
-      "stub_image_url": { "type": "string", "description": "Test-mode image stub URL. Only pass when the user explicitly says things like 'just testing / don't actually generate / use a placeholder image / stub URL / save credits' AND provides a concrete URL. With this set, every image AssetRef in the produced DSL is written as source=existing, status=generated, url=<this URL> — no gen-image call. Do not pass otherwise; if the user expressed the intent without a URL, ask for one — do not invent one." },
-      "stub_video_url": { "type": "string", "description": "Test-mode video stub URL. Only pass when the user explicitly says things like 'just testing / don't actually generate the video / placeholder clip / save credits' AND provides a concrete URL. With this set, every video AssetRef in the produced DSL is written as source=existing, status=generated, url=<this URL> — no gen-video call. Do not pass otherwise; if the user expressed the intent without a URL, ask for one — do not invent one." },
-      "skip_asset_generation": { "type": "boolean", "description": "All-in-one switch for downstream agents (e.g. template-creator) that only want the DSL shape: every produced AssetRef is marked as already generated with placeholder URLs (image: https://placeholder.local/stub.png, video: stub.mp4, audio: stub.mp3). Implies the equivalent of --stub-image-url + --stub-video-url with sentinel defaults plus the same rewrite for gen-voice / gen-digital-human assets. Useful when the agent only needs to inspect DSL structure or feed it into try_render_local with all assets pre-stubbed." }
+      "stub_image_url": {
+        "type": "string",
+        "description": "Test-mode image stub URL. Only pass when the user explicitly says things like 'just testing / don't actually generate / use a placeholder image / stub URL / save credits' AND provides a concrete URL. With this set, every image AssetRef in the produced DSL is written as source=existing, status=generated, url=<this URL> — no gen-image call. Do not pass otherwise; if the user expressed the intent without a URL, ask for one — do not invent one."
+      },
+      "stub_video_url": {
+        "type": "string",
+        "description": "Test-mode video stub URL. Only pass when the user explicitly says things like 'just testing / don't actually generate the video / placeholder clip / save credits' AND provides a concrete URL. With this set, every video AssetRef in the produced DSL is written as source=existing, status=generated, url=<this URL> — no gen-video call. Do not pass otherwise; if the user expressed the intent without a URL, ask for one — do not invent one."
+      },
+      "skip_asset_generation": {
+        "type": "boolean",
+        "description": "All-in-one switch for downstream agents (e.g. template-creator) that only want the DSL shape: every produced AssetRef is marked as already generated with placeholder URLs (image: https://placeholder.local/stub.png, video: stub.mp4, audio: stub.mp3). Implies the equivalent of --stub-image-url + --stub-video-url with sentinel defaults plus the same rewrite for gen-voice / gen-digital-human assets. Useful when the agent only needs to inspect DSL structure or feed it into try_render_local with all assets pre-stubbed."
+      }
     },
-    "required": ["topic"]
+    "required": [
+      "topic"
+    ]
+  },
+  "ui": {
+    "primary": [
+      "topic",
+      "platform",
+      "duration"
+    ],
+    "advanced": [
+      "style",
+      "ratio",
+      "scenes",
+      "voice_id",
+      "template_id",
+      "headline",
+      "subheadline",
+      "carousel_items",
+      "caption_lines"
+    ],
+    "hidden": [
+      "stub_image_url",
+      "stub_video_url",
+      "skip_asset_generation"
+    ]
   }
 }

package/skills/gen-video/skill.json

@@ -87,5 +87,27 @@
     "required": [
       "prompt"
     ]
+  },
+  "ui": {
+    "primary": [
+      "prompt",
+      "model",
+      "duration",
+      "ratio"
+    ],
+    "advanced": [
+      "resolution",
+      "first_frame",
+      "last_frame",
+      "reference",
+      "generate_audio",
+      "camera_fixed",
+      "negative_prompt"
+    ],
+    "hidden": [
+      "json_output",
+      "seed",
+      "person_generation"
+    ]
   }
 }

package/skills/gen-voice/skill.json

@@ -45,5 +45,19 @@
       }
     },
     "required": []
+  },
+  "ui": {
+    "primary": [
+      "text",
+      "voice_id"
+    ],
+    "advanced": [
+      "speed"
+    ],
+    "hidden": [
+      "json_output",
+      "list_voices",
+      "local"
+    ]
   }
 }

package/skills/render-video/SKILL.md

@@ -114,7 +114,17 @@ python3 <SkillDir>/scripts/render_video.py --render-plan <path>.render-plan.json
 python3 <SkillDir>/scripts/render_video.py --job-id 42 --upload-title "My video"
 ```
 
-After rendering, the script auto-uploads by default; `render-manifest.json` then contains an `upload.fileUrl` field. **Prefer `upload.playbackUrl`** (transcoded) over `upload.fileUrl` (raw VOD) when surfacing the URL to a user.
+After rendering, the script auto-uploads by default; `render-manifest.json` then contains an
+`upload.fileUrl` field, and `upload.playbackUrl` (transcoded) once VOD processing finishes.
+
+**Do not retype the video URL into your reply.** On success the script prints a structured
+`__render_video_asset__` line; the host reads the authoritative URL from there and renders a
+player for the user. Tell the user the video is ready — the player appears on its own.
+
+Reproducing a 32-char opaque URL from memory is unreliable: on 2026-08-30 a single character
+was dropped (`…c1c20102` → `…c1c2012`), so the user got a 404 while the file sat fine on the
+CDN. The URL in your prose is redundant with the structured asset and is the only copy that
+can be wrong — the UI now renders it as plain, non-clickable text for exactly this reason.
 
 ### Render but skip the upload
 

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

@@ -2413,6 +2413,26 @@ Examples:
             effective_playback = playback_url or remote_url
             if effective_playback and not effective_playback.startswith("vod://"):
                 print(f"\n🎬 Video playback URL: {effective_playback}")
+
+                # 结构化资产标记 —— 宿主（ab-agent）据此把权威 URL 作为 attachment
+                # 下发前端渲染播放器，绕开模型正文。
+                #
+                # 为什么必须绕开：模型复述 32 位不透明 hex 会出错。2026-08-30 实测一次
+                # 成片链接被吞掉一个字符（…c1c20102 → …c1c2012），用户拿到 404，
+                # 而文件本身好好地在 CDN 上。约定与 web-screenshot/scripts/record.py
+                # 的 __web_record_asset__ 一致。
+                #
+                # 只在拿到**非 vod:// 的真实播放地址**时才打标记（上面的 if 已保证）：
+                # playbackUrl 来自 VOD 轮询，可能超时未就绪。宁可前端没有内联播放器
+                # （用户仍可从成片面板看），也不要再给出一条不可用的地址。
+                asset = {"url": effective_playback}
+                cover = upload_info.get("coverUrl")
+                if cover:
+                    asset["coverUrl"] = cover
+                total_duration = (render_plan.get("renderConfig") or {}).get("totalDuration")
+                if isinstance(total_duration, (int, float)) and total_duration > 0:
+                    asset["durationSec"] = total_duration
+                print("__render_video_asset__ " + json.dumps(asset, ensure_ascii=False))
         else:
             LogPrint(f"   Video: {output_path}", file=sys.stderr)
         if args.save_job:

package/skills/render-video/skill.json

@@ -7,6 +7,7 @@
   "description": "Loads a persisted RenderPlan by job_id and drives the Remotion engine to produce the final video. Assets must already be generated via prepare_video_assets — this skill never resolves or regenerates assets.",
   "auth": "required",
   "createsTake": true,
+  "createsTakeUnless": ["resolve_only"],
   "envVars": [
     "PRIV_TOKEN",
     "MM_API_BASE_URL",

package/skills/video-parser/skill.json

@@ -40,5 +40,18 @@
     "required": [
       "url"
     ]
+  },
+  "ui": {
+    "primary": [
+      "url"
+    ],
+    "advanced": [
+      "scene_threshold",
+      "skip_asr",
+      "skip_keyframes"
+    ],
+    "hidden": [
+      "json_output"
+    ]
   }
 }

package/skills/web-record/skill.json

@@ -147,5 +147,43 @@
     "required": [
       "url"
     ]
+  },
+  "ui": {
+    "primary": [
+      "url",
+      "duration",
+      "scroll_through"
+    ],
+    "advanced": [
+      "device",
+      "viewport",
+      "max_duration",
+      "stop_when_selector",
+      "stop_when_hidden",
+      "scroll_step",
+      "scroll_interval",
+      "scroll_pause_top",
+      "scroll_pause_bottom",
+      "color_scheme",
+      "wait_for_selector",
+      "wait_for_timeout",
+      "vod_title",
+      "cover_at_sec",
+      "browser"
+    ],
+    "hidden": [
+      "output",
+      "storyboard",
+      "template",
+      "param",
+      "list_templates",
+      "user_agent",
+      "timeout",
+      "ignore_https_errors",
+      "storage_state",
+      "cookies",
+      "no_upload",
+      "keep_webm"
+    ]
   }
 }

package/skills/web-screenshot/skill.json

@@ -76,5 +76,26 @@
     "required": [
       "url"
     ]
+  },
+  "ui": {
+    "primary": [
+      "url",
+      "full_page"
+    ],
+    "advanced": [
+      "selector",
+      "device",
+      "viewport",
+      "wait_for_selector",
+      "wait_for_timeout",
+      "browser",
+      "clip",
+      "annotate",
+      "output"
+    ],
+    "hidden": [
+      "storage_state",
+      "cookies"
+    ]
   }
 }