@starreel/mcp 0.1.69 → 0.1.71

package/SKILL.md

@@ -72,7 +72,8 @@ announces a condensed version as MCP `instructions` at connect time.
 | A finished **shot list** (per-shot seconds / shot size / camera move) | `get_storyboard_table_spec` (the contract: shot-size / camera-move vocabulary, body layout, text-card syntax, a prompt for the external AI) → `check_storyboard_table` (same parser as the import; clear `errors`, read every `warning` — a missing duration, an unrecognised shot size or an empty body all get imported as-is) → `import_storyboard_table` (defaults to `auto_complete`: one background batch fills the professional fields and expands every shot's platform-built base description into full image / video prompts — metered text, tell the customer first; `auto_complete: false` imports only) → `get_autofill_status` until `done` → `review_storyboards` | `rewrite_script` + `generate_storyboards` — strips every production parameter (measured: 8 shots / 36 s became 20 shots / 109 s); importing without the check; reviewing before the completion batch finishes (the token expires when shots change) |
 | **Structured data** — their own tool / spreadsheet export, or an external AI producing JSON (cast + scenes + shots in one go) | `get_bulk_import_spec` (contract + template + worked example + enums, same source as the validator) → `check_bulk_import` (same zod schema; unresolved character / scene references, dead shots and stage directions inside dialogue are surfaced) → `bulk_import_storyboards` (`mode: "replace"` only with the customer's explicit OK; defaults to `auto_complete`: professional fields for every shot, full image / video prompts only for shots that had no `image_prompt` — prompts you supply yourself are kept verbatim — metered text, tell the customer first) → `get_autofill_status` until `done` → `review_storyboards` | converting the JSON to text for `import_storyboard_table`; hand-building shots with `update_shot`; reviewing before the completion batch finishes |
 | Their own portraits / scene / prop / shot images | `upload_image` · `set_character_portrait` · `upload_scene_image` · `upload_prop_sheet` · `upload_shot_frame` | rendering a "fix" elsewhere and uploading it — use `generate_shot_frame` |
-| Their own **footage** for a shot (screen recording, product b-roll, an existing clip) | `upload_shot_footage` → that shot is no longer AI-generated (frames/video skipped, final cut uses the clip as-is, duration written back from the clip); `clear_shot_footage` to revert | pasting an externally AI-generated clip to "fix" a shot — it carries none of this film's identity / style anchors; use `regenerate_shot_video` instead |
+| Their own **footage** for a shot (screen recording, product b-roll, an existing clip) | `upload_shot_footage` → that shot is no longer AI-generated (frames/video skipped, final cut uses the clip as-is, duration written back from the clip); **it overwrites whatever AI video that shot already had**, and afterwards every AI video call on it (including `edit_video_shot`) is refused with **409** until you `clear_shot_footage` or pass `replace_user_footage: true` | pasting an externally AI-generated clip to "fix" a shot — it carries none of this film's identity / style anchors; use `regenerate_shot_video` instead |
+| A clip that should **drive the motion** of an AI shot (a blocking/previz pass, a dance or action reference) | `edit_video_shot` with `reference_video_urls` — the shot keeps its AI video and borrows the clip's movement. To make the clip itself the source and restyle it in place, `upload_shot_footage` it first, then `edit_video_shot` with `replace_user_footage: true` | `upload_shot_footage` alone — that registers the clip as the finished shot, so nothing gets restyled and every later AI call on it returns 409 |
 | A scene plate that came out wrong (backdrop, era, light, layout) | `get_scene_prompt` → `update_scene` (`image_prompt`) → `regenerate_scene_image`; already-rendered shot frames still anchor on the old plate, so regenerate those shots too | re-running `generate_scene_images` (it only fills scenes that have **no** plate — it will not touch this one) |
 | A voice sample / a required voice | `clone_voice` → `speak_with_voice` → `set_character_voice` / `assign_voices` | cloning without the rights-holder's consent |
 | A song + lyrics | `create_drama` (`project_type: "mv"`) → `set_mv_lyrics` → `generate_mv_story` → `generate_mv_script` | `rewrite_script` (blocked for MV) |
@@ -213,6 +214,16 @@ content that will be rejected.
    on hailuo-3 / wan3.0 / wan3.0-prime — `edit_video_shot` rejects
    `start_sec`/`end_sec` on them. `edit_video_shot` also takes a per-call
    `model` so one shot can be edited on a different engine than the drama's.
+   **Negative phrasing backfires.** If the receipt carries
+   `edit_instruction_negation_advisory`, the instruction contained phrases like
+   "don't use X" / "不能采用X". Video models read nouns as positive cues, so the
+   thing you forbade is often exactly what gets performed — the forbidden item is
+   the most salient one in the model's prior. It is advisory only (the job was
+   submitted), but on the next pass **replace the negation with a positive
+   description** — state what the shot should do (the opening gesture, where the
+   hands are, the beat timing). Measured: an instruction saying "do not use the
+   reference image's raised-arm pose" produced exactly that raised arm at the
+   opening, overriding the source video's motion.
    **How to choose (guide the customer proactively)**: ① realistic live-action
    dramas → `seedance-2.5` (best instruction-following and face detail), or
    `hailuo-3` to cut cost to ~1/3 (slower, ~6 min/shot); ② stylized / animated /

package/dist/tools/produce.js

@@ -903,6 +903,11 @@ export function registerProduceTools(server, client) {
         '登记后该镜不再 AI 出图/出视频（generate_videos 会跳过它,单镜重生会被拒),终拼原样使用,镜头时长按素材真实长度回写,' +
         '首/尾帧从素材抽帧供帧链与预览用。免费。适用:宣传片里的到账界面录屏、后台大屏实录、产品实拍、客户已有的成片片段。' +
         '⚠️ 别用它把外部 AI 生成的视频贴进来"改画面"——那不带本片身份锚/画风锚,人物·画风必漂;要改画面走 regenerate_shot_video。' +
+        '⚠️★**会覆盖这一镜已有的 AI 成片**(video_url 被替换成你传的素材;旧成片仍在但不再是本镜的在用视频,终拼将拼进素材)。' +
+        '⚠️★**要拿一段视频当「动作/运镜参考」让 AI 照着重绘,用的不是本工具**——那是 edit_video_shot 的 reference_video_urls' +
+        '(或 generate_videos 的参考视频通道)。本工具的语义是「这段视频**就是**成片本身,不再生成」。' +
+        '两者传的是同一个文件,结果天差地别:走本工具会让该镜从此被出视频守卫拒(含 edit_video_shot),' +
+        '得先 clear_shot_footage 或显式 replace_user_footage 才能继续。' +
         '要换回 AI 生成请先 clear_shot_footage。', {
         storyboard_id: z.number().int().positive(),
         file_path: z.string().describe('本地视频路径(mp4/mov/webm/m4v,≤300MB)'),
@@ -926,6 +931,12 @@ export function registerProduceTools(server, client) {
     server.tool('edit_video_shot', '确认后就地编辑某镜视频:按 instruction 改,可带参考图/视频/音频,或用 start_sec/end_sec 做区间替换。' +
         '可用 model 为本次编辑单独选引擎(与剧引擎可不同):hailuo-3=MiniMax H3 强保真编辑约1/3成本;wan3.0/wan3.0-prime=WAN 3.0 强语义编辑约4折(环境可能跟随指令扩写);' +
         'H3/WAN 均不支持 start_sec/end_sec 区间(传了会 400),编辑/续写的输入视频在 H3/WAN 上另按秒计费。' +
+        '\n★回执里出现 `edit_instruction_negation_advisory` = 你的指令里有**否定式约束**(「不能采用X」「不要出现X」)。' +
+        '视频模型把名词当正向线索,写「不要 X」往往反而把 X 演出来——被否定的那个动作/物件恰恰是模型先验里最显眼的。' +
+        '这不是拦截,任务已照常提交;但**下一轮改指令时务必删掉否定句,改成正向描述**(把该做什么写具体:起手动作、手的位置、每一拍的时值),' +
+        '否则同一个毛病会一直复现。已实测:客户写「不能采用参考图举手单脚的静态舞姿」,成片开头的抬臂手势就被参考图那个举手带跑了。' +
+        '\n★收到 **409「本镜是用户上传的实拍素材」** = 这一镜被 upload_shot_footage 登记成了实拍素材镜,不是模型或引擎的问题,换引擎重试无用。' +
+        '两条出路:要以该素材为源做 AI 重绘 → 带 replace_user_footage=true 重发;要恢复成普通 AI 镜 → 先 clear_shot_footage。' +
         CONFIRM_HINT, {
         storyboard_id: z.number().int().positive(),
         quote_id: z.string().describe('来自 quote_edit_video_shot'),
@@ -936,13 +947,23 @@ export function registerProduceTools(server, client) {
         reference_audio_urls: z.array(z.string()).max(3).optional(),
         start_sec: z.number().optional().describe('区间替换起点秒'),
         end_sec: z.number().optional().describe('区间替换终点秒'),
+        replace_user_footage: z.boolean().optional().describe('本镜是实拍素材镜(upload_shot_footage 传过)时,显式允许以它为源做编辑并用 AI 产物覆盖它。' +
+            '不传则被守卫拒(409,带中文出路)。想保留素材就别传,改用 clear_shot_footage 换回 AI 生成。'),
     }, async ({ storyboard_id, ...rest }) => jsonResult(await client.producePost(`/storyboards/${storyboard_id}/edit/generate`, rest)));
     server.tool('quote_regenerate_shot_video', '报价:重生某镜视频要多少点。返回 quote_id。零扣费。', { storyboard_id: z.number().int().positive() }, async ({ storyboard_id }) => jsonResult(await client.producePost(`/storyboards/${storyboard_id}/regen/quote`)));
-    server.tool('regenerate_shot_video', '确认后重生某镜视频(可选新 prompt)。' + CONFIRM_HINT, {
+    server.tool('regenerate_shot_video', '确认后重生某镜视频(可选新 prompt)。' +
+        '\n★收到 **409「本镜是用户上传的实拍素材」** = 该镜被 upload_shot_footage 登记成实拍素材镜,不是模型问题,换引擎无用;' +
+        '要用 AI 视频覆盖它就带 replace_user_footage=true,要保留素材就别重生。' +
+        CONFIRM_HINT, {
         storyboard_id: z.number().int().positive(),
         quote_id: z.string().describe('来自 quote_regenerate_shot_video'),
         prompt: z.string().optional().describe('可选:覆盖该镜视频 prompt'),
-    }, async ({ storyboard_id, quote_id, prompt }) => jsonResult(await client.producePost(`/storyboards/${storyboard_id}/regen/generate`, prompt ? { quote_id, prompt } : { quote_id })));
+        replace_user_footage: z.boolean().optional().describe('本镜是实拍素材镜时,显式允许用 AI 重生的视频覆盖它(不传则被守卫拒 409)。'),
+    }, async ({ storyboard_id, quote_id, prompt, replace_user_footage }) => jsonResult(await client.producePost(`/storyboards/${storyboard_id}/regen/generate`, {
+        quote_id,
+        ...(prompt ? { prompt } : {}),
+        ...(replace_user_footage !== undefined ? { replace_user_footage } : {}),
+    })));
     server.tool('split_shot', '把某镜按首尾帧拆成两镜(结构操作)。免费。', { storyboard_id: z.number().int().positive() }, async ({ storyboard_id }) => jsonResult(await client.producePost(`/storyboards/${storyboard_id}/split`)));
     server.tool('trim_shot', '裁剪某镜时长(in_ms/out_ms)。免费;返回后需 rerender_episode 重拼成片。', {
         storyboard_id: z.number().int().positive(),

package/openapi.json

@@ -2,8 +2,8 @@
   "openapi": "3.1.0",
   "info": {
     "title": "StarReel Production API",
-    "version": "0.1.69",
-    "description": "Turn a script into a finished, downloadable short-drama episode over REST.\n\nPipeline: script → AI rewrite → cast/scenes/props extraction → portraits & sheets → storyboards → keyframes → video shots → TTS → final cut (.mp4).\n\n**Billing is prepaid and agent-safe**: big-ticket stages are quote-then-generate (`quote_*` returns a `quote_id`; for video, quote == actual charge). Insufficient balance returns 402 — nothing half-runs and the account never goes negative.\n\nAuth: exchange your API key at `POST /v1/agent/token` for a 15-minute bearer token.\n\nGenerated from the @starreel/mcp v0.1.69 tool surface (operationIds match MCP tool names 1:1)."
+    "version": "0.1.71",
+    "description": "Turn a script into a finished, downloadable short-drama episode over REST.\n\nPipeline: script → AI rewrite → cast/scenes/props extraction → portraits & sheets → storyboards → keyframes → video shots → TTS → final cut (.mp4).\n\n**Billing is prepaid and agent-safe**: big-ticket stages are quote-then-generate (`quote_*` returns a `quote_id`; for video, quote == actual charge). Insufficient balance returns 402 — nothing half-runs and the account never goes negative.\n\nAuth: exchange your API key at `POST /v1/agent/token` for a 15-minute bearer token.\n\nGenerated from the @starreel/mcp v0.1.71 tool surface (operationIds match MCP tool names 1:1)."
   },
   "servers": [
     {
@@ -8244,7 +8244,7 @@
       "post": {
         "operationId": "edit_video_shot",
         "summary": "确认后就地编辑某镜视频:按 instruction 改,可带参考图/视频/音频,或用 start_sec/end_sec 做区间替换",
-        "description": "确认后就地编辑某镜视频:按 instruction 改,可带参考图/视频/音频,或用 start_sec/end_sec 做区间替换。可用 model 为本次编辑单独选引擎(与剧引擎可不同):hailuo-3=MiniMax H3 强保真编辑约1/3成本;wan3.0/wan3.0-prime=WAN 3.0 强语义编辑约4折(环境可能跟随指令扩写);H3/WAN 均不支持 start_sec/end_sec 区间(传了会 400),编辑/续写的输入视频在 H3/WAN 上另按秒计费。⚠️ 批量报价确认流程:先调对应的 quote_* 工具,把返回的 estimated_points 原样告诉用户,用户明确同意后,才用返回的 quote_id 调本工具。不要擅自确认。",
+        "description": "确认后就地编辑某镜视频:按 instruction 改,可带参考图/视频/音频,或用 start_sec/end_sec 做区间替换。可用 model 为本次编辑单独选引擎(与剧引擎可不同):hailuo-3=MiniMax H3 强保真编辑约1/3成本;wan3.0/wan3.0-prime=WAN 3.0 强语义编辑约4折(环境可能跟随指令扩写);H3/WAN 均不支持 start_sec/end_sec 区间(传了会 400),编辑/续写的输入视频在 H3/WAN 上另按秒计费。\n★回执里出现 `edit_instruction_negation_advisory` = 你的指令里有**否定式约束**(「不能采用X」「不要出现X」)。视频模型把名词当正向线索,写「不要 X」往往反而把 X 演出来——被否定的那个动作/物件恰恰是模型先验里最显眼的。这不是拦截,任务已照常提交;但**下一轮改指令时务必删掉否定句,改成正向描述**(把该做什么写具体:起手动作、手的位置、每一拍的时值),否则同一个毛病会一直复现。已实测:客户写「不能采用参考图举手单脚的静态舞姿」,成片开头的抬臂手势就被参考图那个举手带跑了。\n★收到 **409「本镜是用户上传的实拍素材」** = 这一镜被 upload_shot_footage 登记成了实拍素材镜,不是模型或引擎的问题,换引擎重试无用。两条出路:要以该素材为源做 AI 重绘 → 带 replace_user_footage=true 重发;要恢复成普通 AI 镜 → 先 clear_shot_footage。⚠️ 批量报价确认流程:先调对应的 quote_* 工具,把返回的 estimated_points 原样告诉用户,用户明确同意后,才用返回的 quote_id 调本工具。不要擅自确认。",
         "tags": [
           "storyboards"
         ],
@@ -8309,6 +8309,9 @@
                   },
                   "end_sec": {
                     "type": "number"
+                  },
+                  "replace_user_footage": {
+                    "type": "boolean"
                   }
                 },
                 "required": [
@@ -8836,7 +8839,7 @@
       "post": {
         "operationId": "regenerate_shot_video",
         "summary": "确认后重生某镜视频(可选新 prompt)",
-        "description": "确认后重生某镜视频(可选新 prompt)。⚠️ 批量报价确认流程:先调对应的 quote_* 工具,把返回的 estimated_points 原样告诉用户,用户明确同意后,才用返回的 quote_id 调本工具。不要擅自确认。",
+        "description": "确认后重生某镜视频(可选新 prompt)。\n★收到 **409「本镜是用户上传的实拍素材」** = 该镜被 upload_shot_footage 登记成实拍素材镜,不是模型问题,换引擎无用;要用 AI 视频覆盖它就带 replace_user_footage=true,要保留素材就别重生。⚠️ 批量报价确认流程:先调对应的 quote_* 工具,把返回的 estimated_points 原样告诉用户,用户明确同意后,才用返回的 quote_id 调本工具。不要擅自确认。",
         "tags": [
           "storyboards"
         ],
@@ -8864,6 +8867,9 @@
                   },
                   "prompt": {
                     "type": "string"
+                  },
+                  "replace_user_footage": {
+                    "type": "boolean"
                   }
                 },
                 "required": [

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@starreel/mcp",
-  "version": "0.1.69",
+  "version": "0.1.71",
   "mcpName": "ai.starreel/starreel",
   "description": "StarReel MCP server — drive the AI short-drama production pipeline (script → storyboards → frames → video → final cut) from Claude, Cursor, or any MCP client",
   "license": "MIT",

package/server.json

@@ -2,13 +2,13 @@
   "$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
   "name": "ai.starreel/starreel",
   "description": "Turn a script into a finished, downloadable short-drama episode — via MCP or REST.",
-  "version": "0.1.69",
+  "version": "0.1.71",
   "websiteUrl": "https://starreel.ai",
   "packages": [
     {
       "registryType": "npm",
       "identifier": "@starreel/mcp",
-      "version": "0.1.69",
+      "version": "0.1.71",
       "transport": {
         "type": "stdio"
       },