@remixmate/cli 0.9.14 → 0.9.16

package/skills/gen-video/SKILL.md

@@ -23,7 +23,9 @@ Wraps ab-api's `POST /model/genVideo` (the same endpoint the web "Lingchuang AI
 
 ## Models
 
-Aligned with the handler's `MODEL_ALIASES` and the frontend `AI_VIDEO_MODELS`:
+The authoritative roster — ids, aliases and per-model limits — lives in the backend catalog
+(`/model/capabilities`), which the CLI fetches at runtime. The table below mirrors it; when the
+two disagree, the catalog wins.
 
 | LiteLLM `model` | Display name | Provider | Duration | Notes |
 |-----------------|--------------|----------|----------|-------|
@@ -33,8 +35,8 @@ Aligned with the handler's `MODEL_ALIASES` and the frontend `AI_VIDEO_MODELS`:
 
 **Model shortcuts** (`--model` / `-m` accepts these directly):
 - `seedance` / `seedance-1.5` / `seedance-1.5-pro` → Seedance 1.5 Pro
-- `veo` / `veo-3.1` → Veo 3.1
-- `veo-fast` / `veo-3.1-fast` → Veo 3.1 Fast
+- `veo` / `veo-3.1` / `veo-3.1-generate` → Veo 3.1
+- `veo-fast` / `veo-3.1-fast` / `veo-3.1-fast-generate` → Veo 3.1 Fast
 
 ### Per-model parameter ranges
 
@@ -150,6 +152,18 @@ remixmate gen-video \
 - Describe motion explicitly.
 - Example: `"At sunrise, an aerial drone shot of a futuristic city, golden light on glass facades, mist swirling, 4K ultra-clear"`.
 
+## Credits
+
+Every run charges credits. The CLI prints a footer on stdout when it does:
+
+```
+💳 Charged 31 credits · balance 1,240
+```
+
+Relay it to the user whenever it appears — it is the only signal they get about what a
+generation cost, and the balance is the only warning before a run fails with
+`insufficient_credits`. Do not drop it from your summary.
+
 ## Error handling
 
 - **401** / **token missing** (non-OpenClaw): set `PRIV_TOKEN`.

package/skills/gen-video/skill.json

@@ -12,14 +12,22 @@
     "type": "object",
     "properties": {
       "prompt": { "type": "string", "description": "Video description" },
-      "model": { "type": "string", "description": "Model: seedance / veo / veo-fast" },
+      "model": { "type": "string", "description": "Model: 'seedance' (default; 4-12s, adaptive/21:9 ratios, fixed camera), 'veo' (4/6/8s, native audio, up to 4k, reference images), or 'veo-fast' (faster Veo variant for iteration)" },
       "duration": { "type": "number", "description": "Duration in seconds" },
       "ratio": { "type": "string", "description": "Aspect ratio" },
       "resolution": { "type": "string", "description": "Resolution" },
       "first_frame": { "type": "string", "description": "First-frame image path or URL" },
       "last_frame": { "type": "string", "description": "Last-frame image path or URL" },
-      "reference": { "type": "string", "description": "Reference image (Veo only)" },
+      "reference": {
+        "type": "array",
+        "items": { "type": "string" },
+        "description": "Reference images: local file path, https URL, or data URI. Veo only, max 3 — Seedance rejects them, use first_frame / last_frame instead."
+      },
       "generate_audio": { "type": "boolean", "description": "Generate native audio" },
+      "camera_fixed": { "type": "boolean", "description": "Lock the camera in place (Seedance)" },
+      "negative_prompt": { "type": "string", "description": "Content to steer away from (Veo)" },
+      "seed": { "type": "number", "description": "Random seed. Pass the same seed with the same prompt and model to make a run reproducible." },
+      "person_generation": { "type": "string", "enum": ["allow_all", "dont_allow"], "description": "Whether the model may render people (Veo). Omit to use the backend default." },
       "json_output": { "type": "boolean", "description": "Emit a JSON result ({ url }) instead of human-readable output" }
     },
     "required": ["prompt"]

package/skills/gen-video/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "339",
   "version": "V8",
-  "skillDescription": "AI 生视频技能，根据文字描述生成素材视频（调用 ab-api /model/genVideo，支持 Seedance 与 Veo）。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- AI 生视频、文生视频、文字生成视频、生成一段视频、AI 制作视频\n- 使用 doubao / 豆包 / seedance、Veo、Google 等生成视频\n- 用户提供视频提示词并希望生成视频\n- 图生视频、首帧生成视频、参考图生成视频\n\n即使用户没有明确说「使用 AI」，只要他们想要根据描述生成视频，也要使用本 skill。"
+  "skillDescription": "AI video generation skill: produce a short clip from a text prompt. Backed by ab-api's `/model/genVideo` (Seedance and Veo families).\n\nUse this skill immediately whenever the user asks for any of:\n- Text-to-video, AI-generated clip, \"make a short video of ...\"\n- Generate video with Doubao / Seedance / Veo / Google\n- Image-to-video, first-frame / last-frame, reference-image-to-video\n\nEven without an explicit \"use AI\", any request that turns a description into a moving clip should route here."
 }

package/skills/gen-voice/SKILL.md

@@ -21,7 +21,7 @@ Wraps ab-api's unified `POST /tool/tts` with `provider: "minimax"` (the same end
 
 ## Auth & environment
 
-There is no skill-local env file — the executing process inherits the system environment. Examples below say `python`; on macOS you may need `python3`.
+There is no skill-local env file — the executing process inherits the system environment.
 
 - **Enterprise OpenClaw**: auth is already injected, **no need** to set `PRIV_TOKEN` / `--priv-token`.
 - **Other environments**: configure the token. See the Tianyan privateToken doc internally. Without a token, non-interactive runs fail; interactive runs prompt.
@@ -95,6 +95,18 @@ remixmate gen-voice --text "<text-to-synthesize>" --json-output
 | Voice-over / narration | 1.0–1.2 |
 | Fast announcement | 1.2–1.5 |
 
+## Credits
+
+Every run charges credits. The CLI prints a footer on stdout when it does:
+
+```
+💳 Charged 31 credits · balance 1,240
+```
+
+Relay it to the user whenever it appears — it is the only signal they get about what a
+generation cost, and the balance is the only warning before a run fails with
+`insufficient_credits`. Do not drop it from your summary.
+
 ## Error handling
 
 - **401** / **token missing** (non-OpenClaw): set `PRIV_TOKEN`.

package/skills/gen-voice/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "338",
   "version": "V7",
-  "skillDescription": "语音合成（TTS）技能，将文字转为语音音频（调用 ab-api 统一 /tool/tts，provider=minimax，基于 Minimax TTS）。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- AI 配音、语音合成、文字转语音、TTS、文本转音频、生成语音\n- 使用 minimax 语音合成\n- 用户想要将一段文字朗读出来、生成音频\n\n即使用户没有明确说「使用 AI」，只要他们想要将文字转为语音，也要使用本 skill。"
+  "skillDescription": "Text-to-speech (TTS) skill: synthesize narration audio from text via ab-api's unified `/tool/tts` endpoint with `provider: \"minimax\"` (Minimax TTS).\n\nUse this skill immediately whenever the user asks for any of:\n- AI voice-over, TTS, text-to-speech, generate narration audio\n- Use Minimax for speech synthesis\n- Read a piece of text aloud / produce an audio file from text\n\nEven when the user does not explicitly say \"AI\", any request that turns text into speech should route here."
 }

package/skills/prepare-video-assets/SKILL.md

@@ -195,6 +195,18 @@ The Asset Resolver handles each `AssetRef` in this order:
 4. **Parallel generation**: assets of the same type are generated in parallel; different types are sequenced by dependency.
 5. **Cache reuse**: assets with the same payload are checked against `asset-cache-dir` to avoid duplicate generation.
 
+## Credits
+
+Every run charges credits. The CLI prints a footer on stdout when it does:
+
+```
+💳 Charged 31 credits · balance 1,240
+```
+
+Relay it to the user whenever it appears — it is the only signal they get about what a
+generation cost, and the balance is the only warning before a run fails with
+`insufficient_credits`. Do not drop it from your summary.
+
 ## Error handling
 
 - **DSL validation failed**: pre-validate with `gen-script --validate`.

package/skills/prepare-video-assets/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "476",
   "version": "V1",
-  "skillDescription": "Asset-preparation skill (Phase 1 of the two-phase video pipeline). 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."
+  "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/SKILL.md

@@ -210,6 +210,18 @@ The Remotion render project lives at the monorepo root under `<monorepo-root>/re
 - Production (default): the client uses `https://api-render.remixmate.com` when `REMOTION_RENDER_API_URL` is unset — no config needed.
 - Local debugging: in the renderer directory run `npm install && npm run server:dev`, then point the client at it with `REMOTION_RENDER_API_URL=http://localhost:3000`.
 
+## Credits
+
+Every run charges credits. The CLI prints a footer on stdout when it does:
+
+```
+💳 Charged 31 credits · balance 1,240
+```
+
+Relay it to the user whenever it appears — it is the only signal they get about what a
+generation cost, and the balance is the only warning before a run fails with
+`insufficient_credits`. Do not drop it from your summary.
+
 ## Error handling
 
 - **`job_id` missing or not assets-ready**: the script exits non-zero with a message like "render job N is not in assets-ready state". The agent should call `prepare_video_assets` again with the updated DSL to regenerate, then re-call this skill with the new `job_id`.

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

@@ -24,6 +24,7 @@
 """
 
 import argparse
+import atexit
 import builtins
 import json
 import os
@@ -356,6 +357,62 @@ def LogPrint(*args, sep=" ", end="\n", file=None, flush=False):
     builtins.print(f"[{stamp}] {message}", end=end, file=file, flush=flush)
 
 
+# ─── 扣费汇总 ────────────────────────────────────────────────────────────────
+# 一条视频管线的花费分散在多处：每个 gen-image / gen-voice / gen-video /
+# gen-digital-human 子进程各扣一次，渲染再通过 saveManifest 扣一次。子进程是
+# capture_output 起的，它们自己打的 💳 页脚会被吞掉，所以这里把子进程 stdout 里的
+# billing 事件抓出来累加，最后统一报一次总账——否则用户跑完一整条管线，只知道视频
+# 好了，不知道花了多少积分。
+_BILLING: dict = {"credits": 0, "balance": None}
+
+
+def absorb_child_billing(stdout: str) -> None:
+    """从子 skill 的 stdout 里收集 `__progress__` billing 事件（见 CLI src/billing.ts）。"""
+    for line in (stdout or "").splitlines():
+        line = line.strip()
+        if not line.startswith("{") or "__progress__" not in line:
+            continue
+        try:
+            event = json.loads(line)
+        except json.JSONDecodeError:
+            continue
+        if not isinstance(event, dict) or event.get("phase") != "billing":
+            continue
+        credits = event.get("credits")
+        if not isinstance(credits, (int, float)) or credits <= 0:
+            continue
+        _BILLING["credits"] += int(credits)
+        balance = event.get("balance")
+        if isinstance(balance, (int, float)):
+            _BILLING["balance"] = int(balance)
+
+
+def print_billing_footer() -> None:
+    """收尾时报一次总账。通过 atexit 注册，所以 sys.exit / 中途失败也会打印
+    ——已经发生的扣费不该因为后面某一步失败就不告知用户。
+
+    走 stdout 而不是 stderr：ab-agent 交给 LLM 的是 `result.stdout || result.stderr`
+    （mcp-tools.ts），只写 stderr 在托管 agent 里等于不可见。
+    """
+    credits = _BILLING["credits"]
+    balance = _BILLING["balance"]
+    try:
+        import render_job_client  # type: ignore
+
+        job_billing = render_job_client.billing_summary()
+        if job_billing.get("credits"):
+            credits += int(job_billing["credits"])
+            # saveManifest（渲染扣费）在管线里排最后，它带回的余额最新。
+            if job_billing.get("balance") is not None:
+                balance = int(job_billing["balance"])
+    except Exception:  # noqa: BLE001 — 报账失败绝不能影响已完成的渲染
+        pass
+    if credits <= 0:
+        return
+    suffix = f" · balance {balance:,}" if balance is not None else ""
+    builtins.print(f"\n💳 Charged {credits:,} credits{suffix}", flush=True)
+
+
 def sync_chrome_headless_vendor(renderer_dir: str, render_plan: dict) -> None:
     """Chrome Headless vendor 同步——实现已抽到独立模块 ``_chrome_vendor``。
 
@@ -758,6 +815,7 @@ def resolve_asset_image(asset: dict, private_token: str, timeout: int) -> dict:
 
     try:
         result = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout, stdin=subprocess.DEVNULL)
+        absorb_child_billing(result.stdout)
         if result.returncode == 0:
             for line in reversed(result.stdout.strip().split("\n")):
                 line = line.strip()
@@ -809,6 +867,7 @@ def resolve_asset_audio(asset: dict, private_token: str, timeout: int) -> dict:
 
     try:
         result = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout, stdin=subprocess.DEVNULL)
+        absorb_child_billing(result.stdout)
         if result.returncode == 0:
             for line in reversed(result.stdout.strip().split("\n")):
                 line = line.strip()
@@ -854,6 +913,7 @@ def resolve_asset_video(asset: dict, private_token: str, timeout: int) -> dict:
 
     try:
         result = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout, stdin=subprocess.DEVNULL)
+        absorb_child_billing(result.stdout)
         if result.returncode == 0:
             for line in reversed(result.stdout.strip().split("\n")):
                 line = line.strip()
@@ -893,6 +953,7 @@ def resolve_asset_digital_human(asset: dict, private_token: str, timeout: int) -
     dh_timeout = max(timeout, 660)
     try:
         result = subprocess.run(cmd, capture_output=True, text=True, timeout=dh_timeout, stdin=subprocess.DEVNULL)
+        absorb_child_billing(result.stdout)
         if result.returncode == 0:
             for line in reversed(result.stdout.strip().split("\n")):
                 line = line.strip()
@@ -1892,6 +1953,8 @@ def _log_render_plan_summary(render_plan: dict) -> None:
 
 
 def main():
+    # 无论正常结束、sys.exit 还是中途失败，都在最后报一次积分账（无扣费时静默）。
+    atexit.register(print_billing_footer)
     parser = argparse.ArgumentParser(
         description="Video render tool — DSL + TemplateBinding → Remotion video.",
         formatter_class=argparse.RawDescriptionHelpFormatter,

package/skills/render-video/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "473",
   "version": "V19",
-  "skillDescription": "Final-render skill (Phase 3 of the two-phase video pipeline). Loads a persisted RenderPlan by job_id and drives Remotion to produce the final video. Assets must already be generated via prepare_video_assets."
+  "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/template-registry/scripts/render_job_client.py

@@ -37,6 +37,31 @@ def _make_headers(priv_token: str) -> dict:
     return headers
 
 
+# ─── 扣费回传 ────────────────────────────────────────────────────────────────
+# ab-api 会在扣了积分的成功响应上挂 billing 字段（见 core.Success）。渲染积分是在
+# /renderJob/saveManifest 里扣的，所以这里是渲染花费唯一的可见入口——累加起来交给
+# render_video.py 在收尾时统一告知用户。
+_BILLING: dict = {"credits": 0, "balance": None}
+
+
+def _record_billing(result: dict) -> None:
+    billing = result.get("billing")
+    if not isinstance(billing, dict):
+        return
+    credits = billing.get("credits")
+    if not isinstance(credits, (int, float)) or credits <= 0:
+        return
+    _BILLING["credits"] += int(credits)
+    balance = billing.get("balance")
+    if isinstance(balance, (int, float)):
+        _BILLING["balance"] = int(balance)
+
+
+def billing_summary() -> dict:
+    """本进程通过本模块产生的累计扣费：{"credits": int, "balance": int|None}。"""
+    return dict(_BILLING)
+
+
 def _post(path: str, payload: dict, priv_token: str, timeout: int = 30) -> dict:
     """发送 POST 请求并返回响应 data 字段；失败时抛出 RuntimeError。"""
     url = f"{_api_base()}{path}"
@@ -50,6 +75,8 @@ def _post(path: str, payload: dict, priv_token: str, timeout: int = 30) -> dict:
     except urllib.error.URLError as e:
         raise RuntimeError(f"network request failed ({path}): {e.reason}") from e
 
+    _record_billing(result)
+
     if result.get("code") != 0:
         msg = result.get("msg") or result.get("message") or "unknown error"
         raise RuntimeError(f"API returned an error [{path}]: {msg}")

package/skills/template-registry/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "475",
   "version": "V13",
-  "skillDescription": "视频模板仓库（列表查询）。存储所有视频模板定义，对外只暴露「列出可用模板」一个能力；DSL→TemplateBinding 的绑定逻辑已内嵌进 prepare-video-assets，不再作为独立步骤暴露。同时是跨 skill 共享 Python 库（registry_loader / match_template / template_paths / video_dsl 等）的存放位置。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- 查看可用模板、列出所有模板"
+  "skillDescription": "Video-template registry skill. Stores every video-template definition and lists the available templates (templateId / name / aspect ratio / style tags).\n\nUse this skill as soon as the user mentions any of these intents:\n- View available templates / list every template\n\nNote: DSL→TemplateBinding is no longer a separate exposed step — once prepare_video_assets receives a template_id it builds the binding internally."
 }

package/skills/video-parser/version.json

@@ -3,5 +3,5 @@
   "repoName": "agent-skill-media-maker",
   "skillId": "553",
   "version": "V2",
-  "skillDescription": "视频解构技能，将视频拆解为可复用的内容资产（音频、ASR 文本、关键帧、场景分段）。\n\n当用户提到以下任何需求时，立即使用本 skill：\n- 视频解构、视频拆解、视频分析、解析视频\n- 提取关键帧、提取视频文案、视频转文字\n- 视频内容资产、视频素材提取\n\n即使用户没有明确说「解构」，只要他们想要从视频中提取文案、关键帧或结构化信息，也要使用本 skill。"
+  "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."
 }