reelforge 1.20.0 → 1.20.2

package/README.md

@@ -1,295 +1,295 @@
-# reelforge
-
-> Turn a topic or script into a finished vertical video — narration, visuals, and subtitles, assembled for you. Every capability is a command, with `--help` at every level.
-
-## Install
-
-```bash
-npm install -g reelforge
-```
-
-Or use directly without install:
-
-```bash
-npx reelforge <command>
-```
-
-After install, two binaries are on your `PATH` — `reelforge` and the short alias `rf`. Both behave identically; the docs use `rf` from here on.
-
-```bash
-rf --version            # same as `reelforge --version`
-```
-
-## Quick start
-
-The CLI ships pointing at the hosted service. Log in once, then call:
-
-```bash
-npm install -g reelforge
-rf login                                       # opens browser; headless? rf login <api_key>
-rf whoami                                      # balance + api_keys
-rf create "为什么我们还没找到外星文明？"          # auto-saves to ./<title>-<id>.mp4 in cwd
-```
-
-That's the whole story — no server to run.
-
-### Output behavior
-
-| invocation | result |
-|---|---|
-| `rf create "..."` | Saves to `./<sanitized-title>-<task_id_short>.mp4`, prints the path |
-| `rf create "..." -o ./videos/space.mp4` | Saves to that exact path (must include filename, not just a directory) |
-| `rf create "..." --no-download` | Skips local save, prints JSON result with `video_url` |
-| `rf create "..." \| jq .video_url` | When stdout is piped, download is skipped automatically |
-
-## Global options
-
-| flag | description |
-|---|---|
-| `-s, --server <url>` | Server URL (overrides `$REELFORGE_SERVER`; defaults to the hosted service) |
-| `-k, --api-key <key>` | API key (overrides `$REELFORGE_API_KEY` and `reelforge login` saved key) |
-| `--json` | Output raw JSON instead of pretty text — pipe-friendly |
-| `--quiet` | Suppress informational messages on stderr |
-| `-v, --version` | Show CLI version |
-| `-h, --help` | Show help (works on every sub-command) |
-
-## Command map
-
-Run `rf <command> --help` for full details on any of these.
-
-### Core capabilities
-
-| command | what it does |
-|---|---|
-| `llm chat -p <text>` | Send one prompt to the configured model |
-| `llm presets` | List built-in model presets |
-| `tts ... -t <text> -o out.mp3` | Text-to-speech (free local + cloud voice options) |
-| `tts voices [--locale zh]` | List supported voices |
-| `images generate -p <prompt>` | Image generation |
-
-### Content / audio / subtitle atomics
-
-| command | what it does |
-|---|---|
-| `content scene-plan -t <topic>` | Single LLM call: title + master script + per-scene image prompts (replaces the old narration / split / image-prompts / title trio) |
-| `content scene-plan --script <text-or-@file>` | Same, but the user supplies the script verbatim — LLM only segments and writes image prompts |
-| `audio transcribe -f <file>` / `--url <url>` | Speech-to-text with word + segment timestamps |
-| `subtitles split -t <text-or-@file>` | Deterministic tiered-punctuation subtitle line splitter (pure function, zero billing) |
-
-### Composition
-
-| command | what it does |
-|---|---|
-| `templates list [--size 1080x1920] [--type image]` | List HTML frame templates |
-| `templates preview <keyOrPath> [-o out.png]` | Render a preview from a preset key **or your own local .html file** |
-| `templates show <key> [-o file.html]` | Print or save the source HTML of any preset — copy it as a starting point for a custom template |
-| `frames render -t <keyOrPath> --title ... --text ...` | Render a single composed frame to PNG. `-t` accepts a preset key **or a local .html path** |
-| `compositions concat <v1> <v2> -o out.mp4` | FFmpeg concat (+ optional BGM) |
-| `compositions bgm -i video.mp4 --bgm bgm.mp3 -o out.mp4` | Add background music |
-| `compositions image-to-video -i img.png -a aud.mp3 -o out.mp4` | Build video from image + audio |
-| `compositions overlay -v video.mp4 --overlay overlay.png -o out.mp4` | Overlay PNG on video |
-
-### End-to-end pipelines
-
-All `pipelines *` commands submit an **async task** and (by default) poll until it finishes with a live progress indicator on stderr. Use `--no-wait` to return immediately with a `task_id`, then `rf tasks wait <id>` later.
-
-The standard pipeline turns a topic or script into a finished vertical video — narration, visuals, and subtitles are generated and assembled for you. One continuous narration track; visuals cut at scene boundaries; subtitles cut at line boundaries.
-
-| command | what it does |
-|---|---|
-| `pipelines standard -t <topic>` (or `--script <text>`) | Audio-first pipeline; `-d/--duration` and `-p/--pace` are the two main knobs |
-
-#### Composition knobs
-
-Three independent axes — mix and match as you like:
-
-| flag | values | default | what changes |
-|---|---|---|---|
-| `--motion` | `off` / `lite` / `max` | `lite` | per-scene zoompan + crossfade intensity |
-| `--layout` | `full` / `blur-bg` / `letterbox` | `full` | how the image sits in the canvas |
-| `--subtitle-style` | `plate` / `stroke` / `cinema` | `plate` | subtitle look |
-
-**Layout presets**:
-- `full` — image fills the whole 1080×1920 canvas. Generates a 1080×1920 image. High-impact; best for human portraits, landscapes, 9:16-native content.
-- `blur-bg` — image at 1080×1080 centered, top/bottom is a gaussian-blurred copy of the **same image** moving in sync with the foreground. Generates a 1080×1080 image (cheaper + no wasted pixels). Best for charts, screenshots, non-9:16 source content (小红书 / 抖音 style).
-- `letterbox` — image at 1080×1080 centered, top/bottom is a solid matte (CSS color). Generates a 1080×1080 image. Cinematic / calm. Customize the matte with `--layout-matte-color "#1a1a1a"` (default `black`).
-
-Examples:
-```bash
-rf create "财经日报" --layout blur-bg                              # 小红书 / 抖音
-rf create "纪录片片段" --layout letterbox --motion max             # 电影感
-rf create "..." --layout letterbox --layout-matte-color "#1a1a1a" # 柔和黑
-```
-
-### Resources
-
-| command | what it does |
-|---|---|
-| `bgm list / upload <file> / delete <name>` | Manage background music |
-| `files list / upload <file> / download <path> / delete <path>` | Manage user assets |
-
-### System
-
-| command | what it does |
-|---|---|
-| `config get` | Read server config (keys masked) |
-| `config set <key> <value>` | Update a dotted-path setting (e.g. `llm.api_key sk-xxx`) |
-| `config patch <file>` | Apply a JSON-merge patch |
-| `tasks list [--status running]` | List recent tasks |
-| `tasks get <id>` / `tasks wait <id>` / `tasks cancel <id>` | Task lifecycle |
-| `history list / get <id> / delete <id>` | Browse / delete completed runs |
-| `health` | Server health + capability check |
-
-### Heavy brand customization (custom overlay templates)
-
-`--motion` / `--layout` / `--subtitle-*` / `--brand-*` cover the common cases. For full visual identity ownership (custom path bar, accent decorations, light theme, footer block, etc.) pass a custom overlay HTML via `--frame-template <local.html | preset_key>`:
-
-```bash
-rf templates show 1080x1920/default.html -o ./my-brand.html
-# ...edit my-brand.html (change colors, add structure, etc.)...
-rf create "我的视频" --frame-template ./my-brand.html
-```
-
-**Contract for custom HTML**:
-
-- Canvas is **1080×1920** (pipeline-fixed; don't declare a different size in `<meta>`).
-- Background must be **transparent** — the scene image is composited by the renderer outside the HTML layer.
-- **`{{image}}` no longer exists.** Using `<img src="{{image}}">` is a hard error at submit time. The image is composited by the renderer.
-- The pipeline injects these placeholders for you:
-
-| Placeholder | What it is |
-|---|---|
-| `{{title}}` `{{text}}` | per-frame content |
-| `{{index}}` `{{total}}` | "scene N of M" — `{{total}}` is the LLM-decided scene count, don't hardcode |
-| `{{layout}}` | `"full"` / `"blur-bg"` / `"letterbox"` — react via `body[data-layout="..."]` CSS to put title/subtitle in the matte zones when layout ≠ full |
-| `{{subtitle_style}}` `{{subtitle_color}}` `{{subtitle_background}}` | subtitle preset + overrides |
-| `{{brand_position}}` `{{brand_handle}}` `{{brand_slogan}}` `{{brand_logo}}` `{{brand_color}}` | brand-chrome inputs (use or ignore as you like) |
-
-Inline HTML is hard-capped at 2 MB. The audio + motion + character-ref + scene-plan stages all keep working identically — only the overlay layer is yours.
-
-**Publishing to short-video platforms (Douyin / TikTok / WeChat Channels)** — the default composition renders to the full 1080×1920 canvas, but those apps overlay UI on top/bottom/right and cover-crop ~96-180px on each side on taller phones. ReelForge does NOT bake platform-specific padding into the renderer. Look up reference safe-zone numbers + recommended `--media-anchor-y` values per platform:
-
-```bash
-rf platform                  # overview table for all platforms
-rf platform 抖音              # detail + anchor variants (alias of douyin)
-rf platform tiktok
-rf platform wechat           # 视频号
-```
-
-## Examples
-
-```bash
-# 1. One-click out a video (45s default, AI writes the script)
-rf create "为什么我们还没找到外星文明？"
-
-# 2. Longer video with a slower visual rhythm
-rf create "深夜便利店的灯光" -d 90 -p slow
-
-# 3. Your own script — no narration-splitting on your side, the pipeline handles it
-rf create --script @./my-script.txt
-rf create --script "雨水缓缓滑落在玻璃窗上，像是无声的泪珠。"
-
-# 4. Preview-first workflow: scrub the storyboard in the browser
-#    before paying for the MP4 render. Finalize with `rf render` when satisfied.
-rf create "..." --preview-only          # opens browser studio
-rf render <task-id>                     # produce the MP4
-
-# 5. Push the image square up to grow the bottom matte (抖音 long-description
-#    case); subtitle position follows the image automatically.
-rf create "..." --layout blur-bg --media-anchor-y 0.40
-#  See `rf platform 抖音` for the safe range and per-scenario recommendations.
-
-# 6. Encoder budget — pick a quality preset or set an exact bitrate.
-rf create "..." --quality draft         # ~1 Mbps, ~3-4× smaller than default
-rf create "..." --video-bitrate 750k    # exact bitrate
-rf create "..." --crf 28                # fine-grained control
-
-# 7. Pick a built-in visual style preset
-rf create "美食教程" --style photorealistic
-
-# 5. Pipeline form with explicit output path
-rf pipelines standard \
-  --script @./script.txt \
-  --frame-template 1080x1920/image_default.html \
-  -p normal -o smoke.mp4
-
-# 6. Inspect existing tasks & redownload a finished video
-rf tasks list --limit 5
-rf history get <task-id> --download recovered.mp4
-
-# 7. Atomics for stand-alone use
-rf content scene-plan -t "雨天的玻璃窗" -d 45 --json | jq .scenes
-rf audio transcribe -f narration.mp3 --json | jq '.words[:5]'
-rf subtitles split -t @./narration.txt --min 10 --hard-max 24
-
-# 8. JSON pipe for automation
-rf llm presets --json | jq '.[].defaultModel'
-
-# 9. Use your own HTML template (no PR/release needed)
-#     Any --frame-template that points to a local .html file is read and sent
-#     inline. Declare size inside the file via
-#       <meta name="template:width"  content="1080">
-#       <meta name="template:height" content="1920">
-#     or pass --frame-template-size 1080x1920.
-rf templates show 1080x1920/image_default.html -o my-brand.html   # copy a preset
-# ...edit my-brand.html to suit your style...
-rf templates preview ./my-brand.html --title "Hello" -o preview.png
-rf frames render -t ./my-brand.html --values '{"author":"Alice"}' -o frame.png
-rf pipelines standard -t "宠物" --frame-template ./my-brand.html -o final.mp4
-```
-
-### Custom HTML templates
-
-Easiest way to start: grab a preset as a reference.
-
-```bash
-rf templates list                                                  # see all keys
-rf templates show 1080x1920/static_default.html                    # print to stdout
-rf templates show 1080x1920/image_default.html -o my-brand.html    # save and edit
-```
-
-`{{title}}`, `{{text}}`, `{{image}}`, `{{index}}`, `{{total}}` are reserved built-ins auto-injected by the pipeline; everything else uses the `{{name:type=default}}` DSL (`type` ∈ `text|number|color|bool`). Pass extras through `--values '{"author":"Alice"}'` (or `template_params` on the pipeline API).
-
-- `{{index}}` — current scene number, 1-based
-- `{{total}}` — scene count the LLM actually produced (use this for "scene N of M" badges; don't hardcode in `template_params`, the scene count is decided at runtime)
-
-#### Template type — does the pipeline generate an AI image per scene?
-
-When you ship an inline template through `rf create` / `rf pipelines standard`, ReelForge needs to know whether each scene should kick off image generation. Resolution priority (high → low):
-
-1. Explicit flag — `--frame-template-type image|static|asset` (or `frame_template_type` in the API body).
-2. Inside the HTML — `<meta name="template:type" content="image">` (or `static` / `asset`).
-3. **Default: `image`** — best practice for zero-config users. If your template doesn't reference scene imagery (pure-text card, etc.), declare `static` explicitly to skip image generation and its cost.
-
-The placeholder `{{image}}` no longer doubles as a type signal — declare type explicitly.
-
-Limits and safety:
-
-- Max 2 MB per inline HTML.
-- The render sandbox blocks `file://`, loopback / private / link-local IPs, CGNAT range, cloud-metadata, and `*.local` / `*.internal` hostnames. So your template can only reference public `https`/`http` resources or `data:` URIs.
-- If the CLI is talking to a hosted server, local-path `--image` won't reach the server; either upload to `rf files upload` first or use an HTTPS URL / data: URI.
-
-#### API field reference
-
-| endpoint | inline HTML field | size field | type field |
-|---|---|---|---|
-| `POST /api/v1/frames/render` | `template_html` | `size` | — (n/a, no image generation) |
-| `POST /api/v1/templates/preview` | `template_html` | `size` | — |
-| `POST /api/v1/pipelines/standard` | `frame_template_inline` | `frame_template_size` | `frame_template_type` |
-
-The pipeline endpoint uses the `frame_template_*` prefix because it already has a `frame_template` field (preset key). The single-frame endpoints use the shorter `template_html` because they don't.
-
-## Tip — getting unstuck
-
-Every level has `--help`:
-
-```bash
-rf --help                     # top-level overview
-rf pipelines --help           # list of pipelines
-rf pipelines standard --help  # full option reference
-rf tts edge --help            # one specific command
-```
-
-## License
-
-Apache-2.0
+# reelforge
+
+> Turn a topic or script into a finished vertical video — narration, visuals, and subtitles, assembled for you. Every capability is a command, with `--help` at every level.
+
+## Install
+
+```bash
+npm install -g reelforge
+```
+
+Or use directly without install:
+
+```bash
+npx reelforge <command>
+```
+
+After install, two binaries are on your `PATH` — `reelforge` and the short alias `rf`. Both behave identically; the docs use `rf` from here on.
+
+```bash
+rf --version            # same as `reelforge --version`
+```
+
+## Quick start
+
+The CLI ships pointing at the hosted service. Log in once, then call:
+
+```bash
+npm install -g reelforge
+rf login                                       # opens browser; headless? rf login <api_key>
+rf whoami                                      # balance + api_keys
+rf create "为什么我们还没找到外星文明？"          # auto-saves to ./<title>-<id>.mp4 in cwd
+```
+
+That's the whole story — no server to run.
+
+### Output behavior
+
+| invocation | result |
+|---|---|
+| `rf create "..."` | Saves to `./<sanitized-title>-<task_id_short>.mp4`, prints the path |
+| `rf create "..." -o ./videos/space.mp4` | Saves to that exact path (must include filename, not just a directory) |
+| `rf create "..." --no-download` | Skips local save, prints JSON result with `video_url` |
+| `rf create "..." \| jq .video_url` | When stdout is piped, download is skipped automatically |
+
+## Global options
+
+| flag | description |
+|---|---|
+| `-s, --server <url>` | Server URL (overrides `$REELFORGE_SERVER`; defaults to the hosted service) |
+| `-k, --api-key <key>` | API key (overrides `$REELFORGE_API_KEY` and `reelforge login` saved key) |
+| `--json` | Output raw JSON instead of pretty text — pipe-friendly |
+| `--quiet` | Suppress informational messages on stderr |
+| `-v, --version` | Show CLI version |
+| `-h, --help` | Show help (works on every sub-command) |
+
+## Command map
+
+Run `rf <command> --help` for full details on any of these.
+
+### Core capabilities
+
+| command | what it does |
+|---|---|
+| `llm chat -p <text>` | Send one prompt to the configured model |
+| `llm presets` | List built-in model presets |
+| `tts ... -t <text> -o out.mp3` | Text-to-speech (free local + cloud voice options) |
+| `tts voices [--locale zh]` | List supported voices |
+| `images generate -p <prompt>` | Image generation |
+
+### Content / audio / subtitle atomics
+
+| command | what it does |
+|---|---|
+| `content scene-plan -t <topic>` | Single LLM call: title + master script + per-scene image prompts (replaces the old narration / split / image-prompts / title trio) |
+| `content scene-plan --script <text-or-@file>` | Same, but the user supplies the script verbatim — LLM only segments and writes image prompts |
+| `audio transcribe -f <file>` / `--url <url>` | Speech-to-text with word + segment timestamps |
+| `subtitles split -t <text-or-@file>` | Deterministic tiered-punctuation subtitle line splitter (pure function, zero billing) |
+
+### Composition
+
+| command | what it does |
+|---|---|
+| `templates list [--size 1080x1920] [--type image]` | List HTML frame templates |
+| `templates preview <keyOrPath> [-o out.png]` | Render a preview from a preset key **or your own local .html file** |
+| `templates show <key> [-o file.html]` | Print or save the source HTML of any preset — copy it as a starting point for a custom template |
+| `frames render -t <keyOrPath> --title ... --text ...` | Render a single composed frame to PNG. `-t` accepts a preset key **or a local .html path** |
+| `compositions concat <v1> <v2> -o out.mp4` | FFmpeg concat (+ optional BGM) |
+| `compositions bgm -i video.mp4 --bgm bgm.mp3 -o out.mp4` | Add background music |
+| `compositions image-to-video -i img.png -a aud.mp3 -o out.mp4` | Build video from image + audio |
+| `compositions overlay -v video.mp4 --overlay overlay.png -o out.mp4` | Overlay PNG on video |
+
+### End-to-end pipelines
+
+All `pipelines *` commands submit an **async task** and (by default) poll until it finishes with a live progress indicator on stderr. Use `--no-wait` to return immediately with a `task_id`, then `rf tasks wait <id>` later.
+
+The standard pipeline turns a topic or script into a finished vertical video — narration, visuals, and subtitles are generated and assembled for you. One continuous narration track; visuals cut at scene boundaries; subtitles cut at line boundaries.
+
+| command | what it does |
+|---|---|
+| `pipelines standard -t <topic>` (or `--script <text>`) | Audio-first pipeline; `-d/--duration` and `-p/--pace` are the two main knobs |
+
+#### Composition knobs
+
+Three independent axes — mix and match as you like:
+
+| flag | values | default | what changes |
+|---|---|---|---|
+| `--motion` | `off` / `lite` / `max` | `lite` | per-scene zoompan + crossfade intensity |
+| `--layout` | `full` / `blur-bg` / `letterbox` | `full` | how the image sits in the canvas |
+| `--subtitle-style` | `plate` / `stroke` / `cinema` | `plate` | subtitle look |
+
+**Layout presets**:
+- `full` — image fills the whole 1080×1920 canvas. Generates a 1080×1920 image. High-impact; best for human portraits, landscapes, 9:16-native content.
+- `blur-bg` — image at 1080×1080 centered, top/bottom is a gaussian-blurred copy of the **same image** moving in sync with the foreground. Generates a 1080×1080 image (cheaper + no wasted pixels). Best for charts, screenshots, non-9:16 source content (小红书 / 抖音 style).
+- `letterbox` — image at 1080×1080 centered, top/bottom is a solid matte (CSS color). Generates a 1080×1080 image. Cinematic / calm. Customize the matte with `--layout-matte-color "#1a1a1a"` (default `black`).
+
+Examples:
+```bash
+rf create "财经日报" --layout blur-bg                              # 小红书 / 抖音
+rf create "纪录片片段" --layout letterbox --motion max             # 电影感
+rf create "..." --layout letterbox --layout-matte-color "#1a1a1a" # 柔和黑
+```
+
+### Resources
+
+| command | what it does |
+|---|---|
+| `bgm list / upload <file> / delete <name>` | Manage background music |
+| `files list / upload <file> / download <path> / delete <path>` | Manage user assets |
+
+### System
+
+| command | what it does |
+|---|---|
+| `config get` | Read server config (keys masked) |
+| `config set <key> <value>` | Update a dotted-path setting (e.g. `llm.api_key sk-xxx`) |
+| `config patch <file>` | Apply a JSON-merge patch |
+| `tasks list [--status running]` | List recent tasks |
+| `tasks get <id>` / `tasks wait <id>` / `tasks cancel <id>` | Task lifecycle |
+| `history list / get <id> / delete <id>` | Browse / delete completed runs |
+| `health` | Server health + capability check |
+
+### Heavy brand customization (custom overlay templates)
+
+`--motion` / `--layout` / `--subtitle-*` / `--brand-*` cover the common cases. For full visual identity ownership (custom path bar, accent decorations, light theme, footer block, etc.) pass a custom overlay HTML via `--frame-template <local.html | preset_key>`:
+
+```bash
+rf templates show 1080x1920/default.html -o ./my-brand.html
+# ...edit my-brand.html (change colors, add structure, etc.)...
+rf create "我的视频" --frame-template ./my-brand.html
+```
+
+**Contract for custom HTML**:
+
+- Canvas is **1080×1920** (pipeline-fixed; don't declare a different size in `<meta>`).
+- Background must be **transparent** — the scene image is composited by the renderer outside the HTML layer.
+- **`{{image}}` no longer exists.** Using `<img src="{{image}}">` is a hard error at submit time. The image is composited by the renderer.
+- The pipeline injects these placeholders for you:
+
+| Placeholder | What it is |
+|---|---|
+| `{{title}}` `{{text}}` | per-frame content |
+| `{{index}}` `{{total}}` | "scene N of M" — `{{total}}` is the LLM-decided scene count, don't hardcode |
+| `{{layout}}` | `"full"` / `"blur-bg"` / `"letterbox"` — react via `body[data-layout="..."]` CSS to put title/subtitle in the matte zones when layout ≠ full |
+| `{{subtitle_style}}` `{{subtitle_color}}` `{{subtitle_background}}` | subtitle preset + overrides |
+| `{{brand_position}}` `{{brand_handle}}` `{{brand_slogan}}` `{{brand_logo}}` `{{brand_color}}` | brand-chrome inputs (use or ignore as you like) |
+
+Inline HTML is hard-capped at 2 MB. The audio + motion + character-ref + scene-plan stages all keep working identically — only the overlay layer is yours.
+
+**Publishing to short-video platforms (Douyin / TikTok / WeChat Channels)** — the default composition renders to the full 1080×1920 canvas, but those apps overlay UI on top/bottom/right and cover-crop ~96-180px on each side on taller phones. ReelForge does NOT bake platform-specific padding into the renderer. Look up reference safe-zone numbers + recommended `--media-anchor-y` values per platform:
+
+```bash
+rf platform                  # overview table for all platforms
+rf platform 抖音              # detail + anchor variants (alias of douyin)
+rf platform tiktok
+rf platform wechat           # 视频号
+```
+
+## Examples
+
+```bash
+# 1. One-click out a video (45s default, AI writes the script)
+rf create "为什么我们还没找到外星文明？"
+
+# 2. Longer video with a slower visual rhythm
+rf create "深夜便利店的灯光" -d 90 -p slow
+
+# 3. Your own script — no narration-splitting on your side, the pipeline handles it
+rf create --script @./my-script.txt
+rf create --script "雨水缓缓滑落在玻璃窗上，像是无声的泪珠。"
+
+# 4. Preview-first workflow: scrub the storyboard in the browser
+#    before paying for the MP4 render. Finalize with `rf render` when satisfied.
+rf create "..." --preview-only          # opens browser studio
+rf render <task-id>                     # produce the MP4
+
+# 5. Push the image square up to grow the bottom matte (抖音 long-description
+#    case); subtitle position follows the image automatically.
+rf create "..." --layout blur-bg --media-anchor-y 0.40
+#  See `rf platform 抖音` for the safe range and per-scenario recommendations.
+
+# 6. Encoder budget — pick a quality preset or set an exact bitrate.
+rf create "..." --quality draft         # ~1 Mbps, ~3-4× smaller than default
+rf create "..." --video-bitrate 750k    # exact bitrate
+rf create "..." --crf 28                # fine-grained control
+
+# 7. Pick a built-in visual style preset
+rf create "美食教程" --style photorealistic
+
+# 5. Pipeline form with explicit output path
+rf pipelines standard \
+  --script @./script.txt \
+  --frame-template 1080x1920/image_default.html \
+  -p normal -o smoke.mp4
+
+# 6. Inspect existing tasks & redownload a finished video
+rf tasks list --limit 5
+rf history get <task-id> --download recovered.mp4
+
+# 7. Atomics for stand-alone use
+rf content scene-plan -t "雨天的玻璃窗" -d 45 --json | jq .scenes
+rf audio transcribe -f narration.mp3 --json | jq '.words[:5]'
+rf subtitles split -t @./narration.txt --min 10 --hard-max 24
+
+# 8. JSON pipe for automation
+rf llm presets --json | jq '.[].defaultModel'
+
+# 9. Use your own HTML template (no PR/release needed)
+#     Any --frame-template that points to a local .html file is read and sent
+#     inline. Declare size inside the file via
+#       <meta name="template:width"  content="1080">
+#       <meta name="template:height" content="1920">
+#     or pass --frame-template-size 1080x1920.
+rf templates show 1080x1920/image_default.html -o my-brand.html   # copy a preset
+# ...edit my-brand.html to suit your style...
+rf templates preview ./my-brand.html --title "Hello" -o preview.png
+rf frames render -t ./my-brand.html --values '{"author":"Alice"}' -o frame.png
+rf pipelines standard -t "宠物" --frame-template ./my-brand.html -o final.mp4
+```
+
+### Custom HTML templates
+
+Easiest way to start: grab a preset as a reference.
+
+```bash
+rf templates list                                                  # see all keys
+rf templates show 1080x1920/static_default.html                    # print to stdout
+rf templates show 1080x1920/image_default.html -o my-brand.html    # save and edit
+```
+
+`{{title}}`, `{{text}}`, `{{image}}`, `{{index}}`, `{{total}}` are reserved built-ins auto-injected by the pipeline; everything else uses the `{{name:type=default}}` DSL (`type` ∈ `text|number|color|bool`). Pass extras through `--values '{"author":"Alice"}'` (or `template_params` on the pipeline API).
+
+- `{{index}}` — current scene number, 1-based
+- `{{total}}` — scene count the LLM actually produced (use this for "scene N of M" badges; don't hardcode in `template_params`, the scene count is decided at runtime)
+
+#### Template type — does the pipeline generate an AI image per scene?
+
+When you ship an inline template through `rf create` / `rf pipelines standard`, ReelForge needs to know whether each scene should kick off image generation. Resolution priority (high → low):
+
+1. Explicit flag — `--frame-template-type image|static|asset` (or `frame_template_type` in the API body).
+2. Inside the HTML — `<meta name="template:type" content="image">` (or `static` / `asset`).
+3. **Default: `image`** — best practice for zero-config users. If your template doesn't reference scene imagery (pure-text card, etc.), declare `static` explicitly to skip image generation and its cost.
+
+The placeholder `{{image}}` no longer doubles as a type signal — declare type explicitly.
+
+Limits and safety:
+
+- Max 2 MB per inline HTML.
+- The render sandbox blocks `file://`, loopback / private / link-local IPs, CGNAT range, cloud-metadata, and `*.local` / `*.internal` hostnames. So your template can only reference public `https`/`http` resources or `data:` URIs.
+- If the CLI is talking to a hosted server, local-path `--image` won't reach the server; either upload to `rf files upload` first or use an HTTPS URL / data: URI.
+
+#### API field reference
+
+| endpoint | inline HTML field | size field | type field |
+|---|---|---|---|
+| `POST /api/v1/frames/render` | `template_html` | `size` | — (n/a, no image generation) |
+| `POST /api/v1/templates/preview` | `template_html` | `size` | — |
+| `POST /api/v1/pipelines/standard` | `frame_template_inline` | `frame_template_size` | `frame_template_type` |
+
+The pipeline endpoint uses the `frame_template_*` prefix because it already has a `frame_template` field (preset key). The single-frame endpoints use the shorter `template_html` because they don't.
+
+## Tip — getting unstuck
+
+Every level has `--help`:
+
+```bash
+rf --help                     # top-level overview
+rf pipelines --help           # list of pipelines
+rf pipelines standard --help  # full option reference
+rf tts edge --help            # one specific command
+```
+
+## License
+
+Apache-2.0

package/bin/reelforge.js

@@ -1,8 +1,8 @@
-#!/usr/bin/env node
-// Thin shim so `reelforge` (alias `rf`) is invokable globally. The actual
-// implementation is bundled to dist/ by `npm run build`.
-import("../dist/index.js").catch((err) => {
-  // eslint-disable-next-line no-console
-  console.error(err?.stack || err);
-  process.exit(1);
-});
+#!/usr/bin/env node
+// Thin shim so `reelforge` (alias `rf`) is invokable globally. The actual
+// implementation is bundled to dist/ by `npm run build`.
+import("../dist/index.js").catch((err) => {
+  // eslint-disable-next-line no-console
+  console.error(err?.stack || err);
+  process.exit(1);
+});

package/dist/commands/compose.js

@@ -59,35 +59,35 @@ async function readAsDataUri(specPath, baseDir) {
     const buf = await fs.readFile(abs);
     return { dataUri: `data:${mime};base64,${buf.toString("base64")}`, bytes: buf.byteLength };
 }
-const EXAMPLE_SPEC_HINT = `{
-  "experimental": "compose.v2",
-  "audio": { "narration": "./narration.mp3" },
-  "scenes": [
-    { "start_sec": 0,  "end_sec": 5,  "image": "./s1.png",  "motion": "zoom-in"   },
-    { "start_sec": 5,  "end_sec": 11, "video": "./clip.mp4", "muted": true        }
-  ],
-  "subtitles": [
-    { "start_sec": 0, "end_sec": 5,  "text": "为什么咖啡因让人精神" },
-    { "start_sec": 5, "end_sec": 11, "text": "原来它跟睡眠物质是同一把钥匙" }
-  ],
-  "title": "咖啡因的真相"
+const EXAMPLE_SPEC_HINT = `{
+  "experimental": "compose.v2",
+  "audio": { "narration": "./narration.mp3" },
+  "scenes": [
+    { "start_sec": 0,  "end_sec": 5,  "image": "./s1.png",  "motion": "zoom-in"   },
+    { "start_sec": 5,  "end_sec": 11, "video": "./clip.mp4", "muted": true        }
+  ],
+  "subtitles": [
+    { "start_sec": 0, "end_sec": 5,  "text": "为什么咖啡因让人精神" },
+    { "start_sec": 5, "end_sec": 11, "text": "原来它跟睡眠物质是同一把钥匙" }
+  ],
+  "title": "咖啡因的真相"
 }`;
-const EXAMPLE_SPEC_V3_HINT = `{
-  "experimental": "compose.v3",
-  "audio": { "tts_voice": "熊小二" },
-  "scenes": [
-    {
-      "video": "./s1.mp4", "muted": true,
-      "narration": ["今天热得不行", "我跑厕所睡觉"],
-      "intro_title": "热到躲厕所"
-    },
-    {
-      "image": "./splash.jpg",
-      "narration": ["主人你找拖鞋去吧"]
-    }
-  ],
-  "subtitle_style": "stroke",
-  "title": "贼喵被抓现行"
+const EXAMPLE_SPEC_V3_HINT = `{
+  "experimental": "compose.v3",
+  "audio": { "tts_voice": "熊小二" },
+  "scenes": [
+    {
+      "video": "./s1.mp4", "muted": true,
+      "narration": ["今天热得不行", "我跑厕所睡觉"],
+      "intro_title": "热到躲厕所"
+    },
+    {
+      "image": "./splash.jpg",
+      "narration": ["主人你找拖鞋去吧"]
+    }
+  ],
+  "subtitle_style": "stroke",
+  "title": "贼喵被抓现行"
 }`;
 export function registerCompose(program) {
     program

package/dist/commands/create.js

@@ -154,8 +154,6 @@ function optsToBody(opts) {
         out.asr_model = opts.asrModel;
     if (opts.imageModel !== undefined)
         out.image_model = opts.imageModel;
-    if (opts.promptPrefix !== undefined)
-        out.prompt_prefix = opts.promptPrefix;
     if (opts.style !== undefined)
         out.style = opts.style;
     if (opts.characterRef !== undefined)
@@ -168,8 +166,6 @@ function optsToBody(opts) {
         out.video_fps = opts.videoFps;
     if (opts.quality !== undefined)
         out.quality = opts.quality;
-    if (opts.crf !== undefined && Number.isFinite(opts.crf))
-        out.crf = opts.crf;
     if (opts.videoBitrate !== undefined)
         out.video_bitrate = opts.videoBitrate;
     if (opts.motion !== undefined)
@@ -188,10 +184,6 @@ function optsToBody(opts) {
         out.bgm_volume = opts.bgmVolume;
     if (opts.subtitleStyle !== undefined)
         out.subtitle_style = opts.subtitleStyle;
-    if (opts.subtitleColor !== undefined)
-        out.subtitle_color = opts.subtitleColor;
-    if (opts.subtitleBackground !== undefined)
-        out.subtitle_background = opts.subtitleBackground;
     if (opts.subtitleBottom !== undefined && Number.isFinite(opts.subtitleBottom))
         out.subtitle_bottom_px = opts.subtitleBottom;
     if (opts.profile !== undefined && opts.profile.trim())
@@ -230,10 +222,6 @@ function optsToBody(opts) {
         cover.base = opts.coverBase;
     if (Object.keys(cover).length > 0)
         out.cover = cover;
-    if (opts.segmentMinChars !== undefined)
-        out.segment_min_chars = opts.segmentMinChars;
-    if (opts.segmentMaxChars !== undefined)
-        out.segment_max_chars = opts.segmentMaxChars;
     if (opts.previewOnly)
         out.preview_only = true;
     return out;
@@ -283,7 +271,6 @@ export function registerCreate(program) {
         .option("-d, --duration <sec>", "target video duration in seconds (generate mode only; default 45). LLM aims for ~duration × 5 chars of narration.", (v) => parseInt(v, 10))
         .option("-p, --pace <pace>", "visual rhythm hint passed to the LLM: slow | normal | fast (default normal). LLM still decides the actual scene count from semantic structure.")
         .option("--image-model <id>", "image model (rx-image-z | rx-image-flux | rx-image-qwen | rx-image-qwen-edit). Auto-switches to the edit-capable model when --character-ref is set.")
-        .option("--prompt-prefix <text>", "raw style prefix prepended to every image prompt (overrides --style)")
         .option("--style <preset>", "image style preset id — server-expanded. 用户不知道选哪个时,agent 应该先跑 `rf styles list --json` 把每个风格的 preview_url(同一灯塔在 17 种风格下的对比图)给用户看,让用户照图选。仅看 id 列表用户和你都猜不准实际出图长啥样")
         .option("--character-ref <urlOrPath>", "reference image of the main character — locks identity across scenes. URL, data: URI, or local png/jpg/webp path (auto-encoded). Auto-enables the edit-capable image model.")
         .option("--motion <preset>", "per-scene image animation intensity. See 'Motion presets' below. Default: lite.")
@@ -294,8 +281,6 @@ export function registerCreate(program) {
         .option("--bgm-volume <0..1>", "BGM mix volume (0=silent, 1=full). Default 0.15 keeps narration intelligible.", (v) => Number(v))
         .option("--no-bgm", "disable background music for this render")
         .option("--subtitle-style <preset>", "subtitle visual style. See 'Subtitle styles' below. Default: plate.")
-        .option("--subtitle-color <css>", "override subtitle text color, e.g. '#ffeb3b'. Omit for preset default.")
-        .option("--subtitle-background <css>", "override plate-preset background, e.g. 'rgba(20,30,80,0.75)'. Other presets ignore.")
         .option("--subtitle-bottom <px>", "override the subtitle bottom offset in px (default 400, the lower-third position). blur-bg/letterbox images move up to clear it.", (v) => parseInt(v, 10))
         .option("--profile <id>", "视频的「场景」(垂类):plain(默认,纯 AI 图,无组件)| finance(财经/金融,数据组件 + 鎏金深蓝)| mindset(财商认知,认知组件 + 暖纸黏土)| general(通用组件,中性皮)。选了 profile 即带出它的组件、配色、配图风、封面与字幕默认,可被其他 flag 覆盖。")
         .option("--subtitle-translate <lang>", "双语字幕:把每条字幕翻译成指定语言,以小一号文字显示在主字幕下方,如 'en'(英文)/ 'ja'(日文)。开启后字幕分段自动变短(主字幕保持单行)。默认:开(en);传 'off' 关闭(也可覆盖 recipe 设置)")
@@ -317,12 +302,9 @@ export function registerCreate(program) {
         .option("--llm-model <id>", "override the LLM model used for scene-plan")
         .option("--tts-model <id>", "override the TTS model (defaults to the server's)")
         .option("--asr-model <id>", "override the ASR model (defaults to the server's)")
-        .option("--segment-min-chars <N>", "subtitle SEGMENT (分段) min chars (default 10). A segment is one on-screen subtitle unit, not a visual line — visual wrapping is automatic.", (v) => parseInt(v, 10))
-        .option("--segment-max-chars <N>", "subtitle SEGMENT (分段) max chars (default 28 ≈ 2 visual lines at 820px safe width). HTML clamps display to 2 lines + ellipsis.", (v) => parseInt(v, 10))
         .option("--video-fps <n>", "output video fps (default 24 — cinema-standard, ~20% faster render vs 30; pass 30 if you want smoother motion)", (v) => parseInt(v, 10))
-        .option("--quality <preset>", "encoder quality preset: draft | standard (default) | high. draft shrinks output ~3-4× vs standard (~3 Mbps) at slight visible quality cost; high is the opposite. Mutually exclusive with --crf and --video-bitrate.")
-        .option("--crf <N>", "constant rate factor 0-51 (lower = higher quality). Bypasses --quality preset's bitrate choice. Mutually exclusive with --video-bitrate.", (v) => parseInt(v, 10))
-        .option("--video-bitrate <rate>", "目标视频码率,如 '750k' / '1M' / '2M'。用于命中文件大小预算。和 --crf 二选一。")
+        .option("--quality <preset>", "encoder quality preset: draft | standard (default) | high. draft shrinks output ~3-4× vs standard (~3 Mbps); high is the opposite. Mutually exclusive with --video-bitrate.")
+        .option("--video-bitrate <rate>", "目标视频码率,如 '750k' / '1M' / '2M'。用于命中文件大小预算。")
         .option("--recipe <file>", "load defaults from a JSON recipe file (CLI flags still override)")
         .option("--redo", "replay last successful create from ~/.reelforge/last-create.json")
         .option("--dry-run", "print the final request body + estimated units; do NOT submit")
@@ -385,8 +367,6 @@ export function registerCreate(program) {
         "  plate    semi-transparent black plate + white text (CapCut default; safest readability)",
         "  stroke   bold white text with black stroke + shadow, no plate (抖音网红风)",
         "  cinema   bottom black gradient backdrop + lighter text (film / documentary look)",
-        "  · use --subtitle-color / --subtitle-background to override the preset's colors",
-        "    e.g. --subtitle-color '#ffeb3b' --subtitle-background 'rgba(20,30,80,0.75)'",
         "",
         "Brand chrome (--brand-* flags or config.video.default_brand):",
         "  Adds a constant @handle / slogan / logo block in a frame corner.",
@@ -402,8 +382,7 @@ export function registerCreate(program) {
         "",
         "Image style presets (--style <preset>) — server expands id → prompt prefix:",
         formatStylePresetsList(),
-        "  · Pass --prompt-prefix to override with a custom string (always wins).",
-        "  · Omit both to let the LLM pick a per-video style automatically.",
+        "  · Omit --style to let the LLM pick a per-video style automatically.",
         "  · Run `rf styles list` to query the server's live catalog.",
         "",
         "Output behavior:",

package/package.json

@@ -1,44 +1,44 @@
-{
-  "name": "reelforge",
-  "version": "1.20.0",
-  "description": "AI 视频生成 CLI。一句话主题或自己的脚本 → 自动出抖音/TikTok/视频号竖屏 MP4。安装即用：`reelforge` 或短别名 `rf`。",
-  "license": "Apache-2.0",
-  "type": "module",
-  "bin": {
-    "reelforge": "./bin/reelforge.js",
-    "rf": "./bin/reelforge.js"
-  },
-  "files": [
-    "bin",
-    "dist",
-    "README.md"
-  ],
-  "engines": {
-    "node": ">=22"
-  },
-  "scripts": {
-    "build": "tsc -p tsconfig.json && node scripts/copy-docs.mjs",
-    "dev": "tsc -p tsconfig.json --watch",
-    "typecheck": "tsc -p tsconfig.json --noEmit",
-    "clean": "rimraf dist",
-    "prepublishOnly": "npm run clean && npm run build"
-  },
-  "dependencies": {
-    "commander": "^12.1.0",
-    "kleur": "^4.1.5"
-  },
-  "devDependencies": {
-    "@types/node": "^20.14.0",
-    "rimraf": "^6.0.1",
-    "typescript": "^5.5.0"
-  },
-  "keywords": [
-    "reelforge",
-    "ai-video",
-    "douyin",
-    "tiktok",
-    "shorts",
-    "vertical-video",
-    "cli"
-  ]
-}
+{
+  "name": "reelforge",
+  "version": "1.20.2",
+  "description": "AI 视频生成 CLI。一句话主题或自己的脚本 → 自动出抖音/TikTok/视频号竖屏 MP4。安装即用：`reelforge` 或短别名 `rf`。",
+  "license": "Apache-2.0",
+  "type": "module",
+  "bin": {
+    "reelforge": "./bin/reelforge.js",
+    "rf": "./bin/reelforge.js"
+  },
+  "files": [
+    "bin",
+    "dist",
+    "README.md"
+  ],
+  "engines": {
+    "node": ">=22"
+  },
+  "scripts": {
+    "build": "tsc -p tsconfig.json && node scripts/copy-docs.mjs",
+    "dev": "tsc -p tsconfig.json --watch",
+    "typecheck": "tsc -p tsconfig.json --noEmit",
+    "clean": "rimraf dist",
+    "prepublishOnly": "npm run clean && npm run build"
+  },
+  "dependencies": {
+    "commander": "^12.1.0",
+    "kleur": "^4.1.5"
+  },
+  "devDependencies": {
+    "@types/node": "^20.14.0",
+    "rimraf": "^6.0.1",
+    "typescript": "^5.5.0"
+  },
+  "keywords": [
+    "reelforge",
+    "ai-video",
+    "douyin",
+    "tiktok",
+    "shorts",
+    "vertical-video",
+    "cli"
+  ]
+}