@starreel/mcp 0.1.151 → 0.1.153

package/SKILL.md

@@ -376,6 +376,19 @@ content that will be rejected.
    **9.4%** of the time versus **40.2%** with one. `generate_shot_frame` does accept
    `allow_missing_terminal: true` for the rare shot that genuinely should barely change,
    but reach for the text fix first.
+   **If frames keep getting the head count or the subject wrong** (a hand / prop insert
+   drawn or judged as a full person, an off-screen speaker counted as visible, precheck or
+   frame review repeatedly complaining about how many people are in shot), the shot's
+   composition contract is wrong. You cannot read or edit that contract directly, and the
+   completion passes only fill empty contracts, so editing text alone does not reach it.
+   Fix the shot with `update_shot` first (who is on screen; mark voice-only speakers with
+   `character_presence: voice_only`; unbind people who should not appear), then call
+   `rederive_shot_contract` (one metered text call — tell the customer). It returns only an
+   `outcome`: `updated` means the new contract is live (regenerate that shot's frames, quote
+   first); `unchanged` usually means the text still says the same thing; `rejected` /
+   `no_candidate` keep the old contract — make the text more explicit and retry; `stale`
+   means the shot was edited while it ran, so nothing was written — call it again. An
+   `updated` result voids unconsumed frame / video quotes covering that shot (re-quote).
    **If an emotional shot comes out with a blank, neutral face**, set the expression
    explicitly: `update_shot` with `expression_hint` (one concrete sentence about the
    face, ≤120 characters, written as what the face *does* — not "don't smile"), then

package/dist/i18n/tools.zh-CN.json

@@ -131,6 +131,7 @@
   "get_voice_consistency": "查声线一致性扫描的进度与逐镜结果（scan_voice_consistency 启动的）。免费。summary.voice_mismatch=声音不像该角色声线锚的镜号（重点看）；dialogue_issues=台词没念完/念错/多出说话声的镜；not_scanned_or_stale=还没扫或视频换过需重扫。speaker_verdict=uncertain 表示人声太短判不了，不是问题。声线不一致的镜：先用 get_pipeline_status 的 native_voice_anchor 确认角色已绑声线，再 regenerate_shot_video 重出。",
   "scan_dialogue_coverage": "★客户报「话没说完就切 / 台词只念了一半」时先跑这个。默认**免费零扣费**(只读已落库的转录审计结果)。把该集每个原声镜的视频音轨与台词做词级比对,按族给出结论:truncated(念到一半就停) / off_script(念的大半不是台词:自说自话、重复上一镜、只有环境音) / extra_speech(台词念全了但还多念) / minor_gap(零星缺词,属转写误差,不必管) / ok。★判读:三个可上报的族**处置方向不同**,别一律加长镜头——实测镜长够的镜里仍有 21% 没念全,「太短」很少是真因(平台保存分镜时已按台词自动抬时长)。truncated/off_script 的正解都是 regenerate_shot_video(厂商每次说多少是随机的,重掷常能拿到整句);同一剧反复 off_script 则换引擎。★never_audited 是本报告最重要的一栏:那些镜从没被检测过,「没测过」不等于「没问题」。rescan=true 会对它们补跑 ASR 比对(耗算力、非瞬时,limit 控制单次上限),默认不跑。TTS 配音镜不在范围内(TTS 必然念全,低覆盖率只会是转写误差)。同一集若还伴随「切太快」,那是另一回事,跑 scan_intra_shot_cuts。",
   "update_shot": "逐镜编辑:改单个分镜的文本内容(景别/动作/台词/画面描述/运镜等)、面部表情(expression_hint)、时长(duration)、成片变速(speed_factor)、角色绑定(character_ids)、画外音标记(character_presence)与服装绑定(active_wardrobe_id / appearance_wardrobes)。只传要改的字段、其余不动。★改镜(成功或被拒)都会作废覆盖本镜的未消费报价,生成时回 409 QUOTE_INVALIDATED——先改成功、回读核对,再报价。**免费**(纯文本写库)。★改 dialogue 会自动失效本镜已生成的 TTS 配音与字幕(需重出 tts);改文本不会自动重出图/视频,如需让画面跟上文本改动,改完再 regen 对应镜。用 get_storyboards 查改后结果(每镜带 character_ids / character_bindings / scene_id / prop_ids / active_wardrobe_id / appearance_wardrobes)。★★【换衣服改这里,不是改文字】出图穿什么由**服装绑定**决定:单人镜用 active_wardrobe_id(整镜一件),多人同框各穿各的用 appearance_wardrobes(逐角色)。把「穿某某衣服」写进 description/action 不会换衣服。服装 id 用 list_wardrobe 查;改完不会自动重出图,要让画面跟上需重生本镜首帧再重生视频。★★原声镜(厂商原生音频)改 dialogue 后,本镜视频会被标记「待重生」——因为台词是**烤进视频人声**的,不重生就终拼,成片里念的仍是改动前的台词(典型现象:台词像是跑到了别的镜头上)。compose_episode 会以 advisory `stale_video_after_edit` 列出这些镜;正确处置是先 regenerate_shot_video 再终拼。★也可直接改本镜的四条提示词正文(image_prompt/video_prompt/first_frame_prompt/last_frame_prompt):改前先用 get_shot_prompts 读现值,别凭空覆盖——正文里的 @char:N / @scene:M 是出图时的补充参考标记,照原样保留即可。★注入谁的定妆图由 character_ids 决定、背景由 scene_id 决定:删标记不会让已绑定的人从画面消失,要让某人不出现就改 character_ids,他只有声音(画外音)就用 character_presence 标 voice_only;反过来别给未绑定的角色写 @char 标记——会把他的图注入进来。★★【出尾帧被拦下就是来改这里】出尾帧若报「此镜标为状态改变,但没有任何地方说明结束时是什么样子」(TERMINAL_DESC_GATE),修法是把**结束时画面是什么样**写进本镜 last_frame_prompt,然后重新出尾帧。别去重试出图——这类镜(action_motion_class=state_change 却没写终态)的尾帧历史成功率 9.4%,有终态描述的是 40.2%;不补描述就重生,送厂商的提示词里根本没有终态段,画出来仍和首帧一样、还是会被拒,而每次重生都照常扣费。get_shot_prompts 的 terminal_desc_missing=true 就是这个信号。",
+  "rederive_shot_contract": "按本镜**当前**的正文与角色绑定,让平台重新推导构图契约(画面里可见几人、主体是人物还是局部/道具、景别)。契约本身不对外,读不到也改不了;本工具只回结论 outcome:updated(已改并生效)/ unchanged(推出来和原来一样)/ rejected(推出来自相矛盾,未采用,原契约保留)/ no_candidate(没拿到可用结果,原契约保留)/ stale(推导期间本镜又被改过,结果未写入,改完再调一次),附 note 说下一步。点数不足回 402。★什么时候用:出图/预检/审核反复说人数不对、局部镜(手部/道具特写)被当成完整人物出图或审核,而你已经改过正文或绑定——补全器只填空、不覆盖已有契约,不调本工具改动不会进契约。★正确顺序:先 update_shot 把画面写对(谁在画面里、谁只出声音用 character_presence 标 voice_only、不该出现的人从 character_ids 解绑),再调本工具;不改正文直接调多半回 unchanged。★一次文本 AI 调用,按 token 后付(与 autofill_storyboards 同链路),调用前告知客户。★只改契约这一个字段,不碰台词/提示词/其它专业字段;已出的首尾帧不会自动重出,要让画面跟上需对本镜重新出帧(先报价)。★updated 会作废本镜及同集未消费的出帧/出视频报价,之后要重新报价。",
   "get_shot_prompts": "读某一镜的四条提示词**正文**(image_prompt=首帧画面 / video_prompt=动态表演 / first_frame_prompt=开始时什么样 / last_frame_prompt=结束时什么样),供直接微调后用 update_shot 写回。免费。★回执里的 terminal_desc_missing=true 表示本镜标为「状态改变」却三处都没说终态——出尾帧会被前置闸拦下,修法是把结束状态写进 last_frame_prompt(别重试出图,重试必然重复被拒且照常扣费)。★同时回 expression_hint(本镜作者指定的面部表情,null=未指定、由平台按台词反推),改它用 update_shot。expression_inferred 是拆镜 AI 在剧本没写神态时按本镜内容推断的表情(只读;null=没推断,或本镜台词/动作/氛围/描述/强度改过、推断已过期不再使用);它优先级低于 expression_hint——推断不合意就用 update_shot 写 expression_hint 覆盖它。★逐镜按需:改哪镜读哪镜(整集列表 get_storyboards 不含提示词)。★返回的 asset_tokens 是正文里的补充参考标记(@char:N / @scene:M),改写时原样保留即可:本镜注入谁的定妆图由绑定决定(get_storyboards 的 character_ids / scene_id),删标记不会让已绑定的人消失;带 #变体 的标记是那张变体图的唯一来源;给未绑定的角色写标记会把他的图注入进来。★这是分镜表里的正文层;出图/出视频时平台还会在其上拼身份锚、一致性约束与参考图指令(不在此处,也无需你写)。改完提示词不会自动重出图/视频,要让画面跟上得再 regen 对应镜。",
   "rerender_episode": "按当前 timeline 重拼成片(改完镜/裁剪后用)。**免费**(纯 ffmpeg+COS),后台异步。",
   "replace_shot_dialogue": "换某镜对白音色/声线(转写+克隆重配)。**同步调用**,约 1 分钟返回产物,按用量后付不欠费。要求本镜有原声视频+角色声线定妆音。★它也是「这一镜台词没念完/念了别的」最经济的修法:用克隆音重配整句并静音原声段,**不重新生成视频**——按 TTS 档(千字符)计费,比 regenerate_shot_video(720p 212 点/秒)低几个数量级。代价:画面口型是按原音演的,换音后可能对不上;口型看不清的镜(背身/远景/画外)几乎无损,大特写慎用。★产物自动写回该镜(返回 persisted:true),但写回 ≠ 进成片:以 get_dialogue_repair_status 的 productEffective 为准——true 就 rerender_episode 重拼;false 时按 pendingCompose 先补合成再重拼,否则成片仍是旧音频。★该镜已有对口型产物时,成片优先用对口型版,换轨不会生效。整集批量用 repair_episode_dialogue。\n★写回前会对产物复核(与 scan_dialogue_coverage 同一判据):换完仍断音(truncated)、重复念/多念(extra_speech)、念的不是台词(off_script)→ **不写回**、本次费用自动退回,返回错误说明哪一类——这类镜换音修不好,改用 regenerate_shot_video。成功时返回 verify:verified=false 表示没判出来(转写失败/台词太短),照常写回但没复核过,自己听一下。",

package/dist/tools/produce.js

@@ -1607,6 +1607,17 @@ export function registerProduceTools(server, client) {
         const payload = Object.fromEntries(Object.entries(fields).filter(([, v]) => v !== undefined));
         return jsonResult(await client.producePut(`/storyboards/${storyboard_id}`, payload));
     });
+    server.tool('rederive_shot_contract', '按本镜**当前**的正文与角色绑定,让平台重新推导构图契约(画面里可见几人、主体是人物还是局部/道具、景别)。' +
+        '契约本身不对外,读不到也改不了;本工具只回结论 outcome:updated(已改并生效)/ unchanged(推出来和原来一样)/ ' +
+        'rejected(推出来自相矛盾,未采用,原契约保留)/ no_candidate(没拿到可用结果,原契约保留)/ ' +
+        'stale(推导期间本镜又被改过,结果未写入,改完再调一次),附 note 说下一步。点数不足回 402。' +
+        '★什么时候用:出图/预检/审核反复说人数不对、局部镜(手部/道具特写)被当成完整人物出图或审核,' +
+        '而你已经改过正文或绑定——补全器只填空、不覆盖已有契约,不调本工具改动不会进契约。' +
+        '★正确顺序:先 update_shot 把画面写对(谁在画面里、谁只出声音用 character_presence 标 voice_only、' +
+        '不该出现的人从 character_ids 解绑),再调本工具;不改正文直接调多半回 unchanged。' +
+        '★一次文本 AI 调用,按 token 后付(与 autofill_storyboards 同链路),调用前告知客户。' +
+        '★只改契约这一个字段,不碰台词/提示词/其它专业字段;已出的首尾帧不会自动重出,要让画面跟上需对本镜重新出帧(先报价)。' +
+        '★updated 会作废本镜及同集未消费的出帧/出视频报价,之后要重新报价。', { storyboard_id: z.number().int().positive() }, async ({ storyboard_id }) => jsonResult(await client.producePost(`/storyboards/${storyboard_id}/rederive-contract`, {})));
     server.tool('get_shot_prompts', '读某一镜的四条提示词**正文**(image_prompt=首帧画面 / video_prompt=动态表演 / ' +
         'first_frame_prompt=开始时什么样 / last_frame_prompt=结束时什么样),供直接微调后用 update_shot 写回。免费。' +
         '★回执里的 terminal_desc_missing=true 表示本镜标为「状态改变」却三处都没说终态——' +

package/openapi.json

@@ -2,8 +2,8 @@
   "openapi": "3.1.0",
   "info": {
     "title": "StarReel Production API",
-    "version": "0.1.151",
-    "description": "Turn a script into a finished, downloadable short-drama episode over REST.\n\nPipeline: script → AI rewrite → cast/scenes/props extraction → storyboards → portraits & sheets + scene plates → 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. For images the quote is a *range* — models billed per reference image are priced before those are assembled, so `estimated_points` is the upper bound (size the balance by it and a run never dies half-way) and `typical_points` is the usual cost; fixed-price models return the two equal. 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 v0.1.151 tool surface (operationIds match MCP tool names 1:1)."
+    "version": "0.1.153",
+    "description": "Turn a script into a finished, downloadable short-drama episode over REST.\n\nPipeline: script → AI rewrite → cast/scenes/props extraction → storyboards → portraits & sheets + scene plates → 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. For images the quote is a *range* — models billed per reference image are priced before those are assembled, so `estimated_points` is the upper bound (size the balance by it and a run never dies half-way) and `typical_points` is the usual cost; fixed-price models return the two equal. 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 v0.1.153 tool surface (operationIds match MCP tool names 1:1)."
   },
   "servers": [
     {
@@ -12760,6 +12760,64 @@
         }
       }
     },
+    "/storyboards/{storyboard_id}/rederive-contract": {
+      "post": {
+        "operationId": "rederive_shot_contract",
+        "summary": "按本镜**当前**的正文与角色绑定,让平台重新推导构图契约(画面里可见几人、主体是人物还是局部/道具、景别)",
+        "description": "按本镜**当前**的正文与角色绑定,让平台重新推导构图契约(画面里可见几人、主体是人物还是局部/道具、景别)。契约本身不对外,读不到也改不了;本工具只回结论 outcome:updated(已改并生效)/ unchanged(推出来和原来一样)/ rejected(推出来自相矛盾,未采用,原契约保留)/ no_candidate(没拿到可用结果,原契约保留)/ stale(推导期间本镜又被改过,结果未写入,改完再调一次),附 note 说下一步。点数不足回 402。★什么时候用:出图/预检/审核反复说人数不对、局部镜(手部/道具特写)被当成完整人物出图或审核,而你已经改过正文或绑定——补全器只填空、不覆盖已有契约,不调本工具改动不会进契约。★正确顺序:先 update_shot 把画面写对(谁在画面里、谁只出声音用 character_presence 标 voice_only、不该出现的人从 character_ids 解绑),再调本工具;不改正文直接调多半回 unchanged。★一次文本 AI 调用,按 token 后付(与 autofill_storyboards 同链路),调用前告知客户。★只改契约这一个字段,不碰台词/提示词/其它专业字段;已出的首尾帧不会自动重出,要让画面跟上需对本镜重新出帧(先报价)。★updated 会作废本镜及同集未消费的出帧/出视频报价,之后要重新报价。",
+        "tags": [
+          "storyboards"
+        ],
+        "parameters": [
+          {
+            "name": "storyboard_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "integer",
+              "exclusiveMinimum": 0
+            }
+          }
+        ],
+        "requestBody": {
+          "required": false,
+          "content": {
+            "application/json": {
+              "schema": {
+                "type": "object",
+                "properties": {}
+              }
+            }
+          }
+        },
+        "responses": {
+          "200": {
+            "description": "StarReel envelope",
+            "content": {
+              "application/json": {
+                "schema": {
+                  "type": "object",
+                  "properties": {
+                    "code": {
+                      "type": "integer"
+                    },
+                    "message": {
+                      "type": "string"
+                    },
+                    "data": {
+                      "description": "Operation result payload"
+                    }
+                  }
+                }
+              }
+            }
+          },
+          "402": {
+            "description": "Insufficient prepaid balance (never overdrafts); response carries `needed` points"
+          }
+        }
+      }
+    },
     "/storyboards/{storyboard_id}/regen/generate": {
       "post": {
         "operationId": "regenerate_shot_video",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@starreel/mcp",
-  "version": "0.1.151",
+  "version": "0.1.153",
   "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": "0.1.151",
+  "version": "0.1.153",
   "websiteUrl": "https://starreel.ai",
   "packages": [
     {
       "registryType": "npm",
       "identifier": "@starreel/mcp",
-      "version": "0.1.151",
+      "version": "0.1.153",
       "transport": {
         "type": "stdio"
       },