@starreel/mcp 0.1.56 → 0.1.57

package/SKILL.md

@@ -70,12 +70,12 @@ announces a condensed version as MCP `instructions` at connect time.
 | A finished screenplay (scene headers + dialogue lines) | `set_script` → `rewrite_script` (auto two-pass fidelity: dialogue byte-locked) → `review_script`; force with `rewrite_pipeline: "two_pass"`, `fidelity_enforce: 1` | pasting it into `edit_rewritten_script` (400) |
 | Wants to rewrite on another AI / says our rewrite "changed too much" | `get_script_format_spec` → external rewrite → `check_script_format` → `adopt_external_script` (exit A) or `set_script` + `rewrite_script` (exit B) | skipping the check; `edit_rewritten_script` |
 | 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` — 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`; sending `image_prompt` / `video_prompt` (ignored — the platform builds them); reviewing before the completion batch finishes |
+| **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` |
 | 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) |
 | A product / brand | `create_drama` (`project_type: "ad"` or `"brand_film"`) → `add_product` → `generate_product_sheet` | writing brand copy as dialogue (it gets spoken) |
-| Generated shots / a cut that needs changes | `scan_dialogue_coverage` / `scan_intra_shot_cuts` first, then `update_shot` · `replace_shot_dialogue` · `repair_episode_dialogue` · `split_shot` · `trim_shot` · `regenerate_shot_video` · `edit_video_shot` → `rerender_episode` | re-composing to fix what a clip *says* |
+| Generated shots / a cut that needs changes | `scan_dialogue_coverage` / `scan_intra_shot_cuts` first, then `get_shot_prompts` · `update_shot` · `replace_shot_dialogue` · `repair_episode_dialogue` · `split_shot` · `trim_shot` · `regenerate_shot_video` · `edit_video_shot` → `rerender_episode` | re-composing to fix what a clip *says* |
 | Wants to assemble the cut themselves | `export_handoff_pack` → `get_handoff_toolchain` | `compose_episode` (pick one) |
 | A multi-language release | `translate_subtitles` · `subtitle_secondary_lang` in project settings | — |
 
@@ -400,6 +400,16 @@ props in the wardrobe segment, missing `[SFX]`/`[BGM]`, group-shot head counts.
 Storyboard-level issues do **not** need a script edit at all: use
 `update_shot` / `replace_shot_dialogue`.
 
+When the frame or the motion is off in a way the business text cannot express,
+edit the shot's prompt bodies directly: `get_shot_prompts` reads the current
+`image_prompt` / `video_prompt` for one shot, `update_shot` writes them back.
+Keep the `@char:N` / `@scene:M` markers the response lists under `asset_tokens`
+— they are what pulls each character's portrait and each scene's plate into the
+render; drop one and that reference silently stops being sent. The prompt body
+is only the part you write: the platform still layers identity anchors and
+consistency constraints on top at generation time. Editing a prompt does not
+re-generate anything — regenerate the shot afterwards.
+
 ## Failure playbook
 
 Failures surface as a human-readable `message` (MCP throws `Error(message)`;

package/dist/tools/guide-data.js

@@ -66,10 +66,10 @@ export const ENTRY_POINTS = [
         use: [
             'get_bulk_import_spec(契约 + 模板 + 成品示例 + 枚举与上限,与校验器同源)',
             'check_bulk_import(同一份 zod 校验;引用不到的角色/场景、死镜、台词里的舞台指示都会报出来)',
-            'bulk_import_storyboards(mode=merge 更新/保留,replace 替换全部需客户明确同意;prompt 字段由平台生成)',
+            'bulk_import_storyboards(mode=merge 更新/保留,replace 替换全部需客户明确同意;自带的 image_prompt/video_prompt 逐字照用,没填的镜平台拼基础描述)',
         ],
         avoid: '别把 JSON 转成文本再走 import_storyboard_table,也别一条条 update_shot 手建——结构化数据就走结构化通道。',
-        note: '通过 MCP 导入时 image_prompt/video_prompt/frame_visual_contract 会被忽略,平台拼基础描述;导入默认带 auto_complete(后台 AI 填专业字段,并只给平台拼基础描述的镜扩写出图/视频提示词,文本步后付、调用前告知客户)——回执 started 后 `get_autofill_status` 轮询到 done 再 `review_storyboards`。',
+        note: '自带 image_prompt/video_prompt 会逐字保留(只有 frame_visual_contract 这个内部帧契约被忽略),没填的镜平台拼基础描述;导入默认带 auto_complete(后台 AI 填专业字段,并只给平台拼基础描述的镜扩写出图/视频提示词,文本步后付、调用前告知客户)——回执 started 后 `get_autofill_status` 轮询到 done 再 `review_storyboards`。',
         free: false,
         flow: 'get_bulk_import_spec → check_bulk_import(errors 清零) → bulk_import_storyboards(默认 auto_complete) → get_autofill_status 到 done → review_storyboards',
     },
@@ -124,7 +124,8 @@ export const ENTRY_POINTS = [
         use: [
             'scan_dialogue_coverage(先定病因:话没说完/念错/走到别的镜;免费)',
             'scan_intra_shot_cuts(「切太快」先看厂商有没有在单镜内自行硬切;免费)',
-            'update_shot(景别/动作/台词/运镜等文本字段;character_ids 全量覆盖)',
+            'get_shot_prompts(读某镜的出图/视频提示词正文,免费;改提示词前先读现值)',
+            'update_shot(景别/动作/台词/运镜等文本字段;image_prompt/video_prompt 提示词正文;character_ids 全量覆盖)',
             'replace_shot_dialogue',
             'repair_episode_dialogue(换音频不重生视频,按 TTS 费率,比重生便宜几个数量级)',
             'split_shot',

package/dist/tools/produce.js

@@ -374,7 +374,7 @@ export function registerProduceTools(server, client) {
         '★与 import_storyboard_table(文本一镜一行)的分工:数据本来就是结构化的走 JSON;客户手上是文本分镜表走那条。' +
         '★契约要点:顶层 { mode, episode_meta?, characters?[], scenes?[], storyboards[] };characters 按 name 去重、scenes 按 location+time 去重、storyboards 按 storyboard_number 去重;' +
         'bound_characters 引用 characters[].name(或本剧已有角色名)、scene_ref 引用 scenes[] 的 location+time——引用不到会**静默跳过**;每镜 action/description 至少一个;dialogue 是 `说话人：台词`、别写舞台指示(会被念出来);' +
-        'image_prompt/video_prompt 可不填(平台拼基础描述),**通过 MCP 导入时这两个字段与 frame_visual_contract 会被忽略**(prompt 工程由平台生成)。', {}, async () => jsonResult(await client.produceGet('/bulk-import/spec')));
+        'image_prompt/video_prompt 可不填(没填的镜由平台按景别+场景+光线+action 拼基础描述);填了就**逐字照用**,平台不覆盖。frame_visual_contract 是内部帧契约,导入时忽略。', {}, async () => jsonResult(await client.produceGet('/bulk-import/spec')));
     server.tool('check_bulk_import', '**导入前的 JSON 自检**:用导入端点**同一份 zod schema** 校验,再把导入路由的"静默行为"变成 warning。返回 errors / warnings / stats(镜数·总秒·角色·场景·mode·promptsToBuild)。免费·不落库·可反复跑。' +
         '★errors = 导入会 400 或会出错覆盖的:不是合法 JSON / schema 不过(逐条带 path,如 storyboards[2].shot_type)/ 镜号重复 + 残留 <...> 占位符;必须清零。' +
         '★warnings = 导入照常但会缺东西或有副作用的:bound_characters/scene_ref 引用不到(静默跳过)/ 没有 action+description(死镜)/ dialogue 含镜头语言(会被念出来)/ 单镜>15 秒 / 镜号跳号 / mode=replace(替换本集全部分镜)/ 全无角色绑定(人物会漂)。' +
@@ -382,7 +382,8 @@ export function registerProduceTools(server, client) {
     server.tool('bulk_import_storyboards', '把一份结构化 JSON 一次性建成本集的角色 / 场景 / 分镜(按 name / location+time / storyboard_number 去重更新)。免费·确定性·不调 AI。' +
         '★三步走:① get_bulk_import_spec 取契约与成品示例;② check_bulk_import 自检到 errors 清零;③ 再调本工具。' +
         '★mode=merge(默认)保留未提到的镜;mode=replace 替换本集**全部**分镜(旧镜与已生成图/视频归档可恢复、不会自动重挂)——replace 必须先得到客户明确同意。' +
-        '★image_prompt / video_prompt / frame_visual_contract 在门面被剥掉:prompt 工程由平台生成(缺省按景别+场景+光线+action 拼基础描述,回执 base_prompts_built 是拼了几镜);想更专业用 enhance_shot_prompts。' +
+        '★image_prompt / video_prompt 想自己写就直接写在每镜里,**逐字照用不被覆盖**;没填的镜平台拼基础描述(回执 base_prompts_built 是拼了几镜),导入后可用 get_shot_prompts 读、update_shot 改。' +
+        '(frame_visual_contract 是内部帧契约,导入时忽略。)' +
         '★导入后:语速律会抬高装不下台词的镜(回执 speech_duration_raised / speech_duration_overflow)。' +
         '★导入后**默认自动补全**(auto_complete,跟随剧目「自动补齐辅助资产」开关、默认开):同一后台批次给全镜 AI 填空专业字段(只填空),' +
         '并只给**没填 image_prompt、由平台拼了基础描述**的镜扩写完整出图/视频提示词(客户自己写的绝不覆盖;回执 auto_complete.prompt_shots)。' +
@@ -762,7 +763,9 @@ export function registerProduceTools(server, client) {
         '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。' +
         '★★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。', {
+        '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。' +
+        '★也可直接改本镜的两条提示词正文(image_prompt/video_prompt):改前先用 get_shot_prompts 读现值,' +
+        '别凭空覆盖——正文里的 @char:N / @scene:M 是角色/场景参考图的引用标记,删掉本镜就不注入对应定妆图/场景图(形象漂移)。', {
         storyboard_id: z.number().int().positive(),
         character_ids: z.array(z.number().int().positive()).optional()
             .describe('本镜出场角色 ID 列表(★全量覆盖式,非增量,漏传的角色会被解绑)。决定出图时注入哪些角色的定妆图/设定图——非人角色(动物/生物)也必须绑定,否则形象会漂移。id 必须来自当前集已关联角色'),
@@ -778,10 +781,18 @@ export function registerProduceTools(server, client) {
         atmosphere: z.string().optional().describe('氛围'),
         director_note: z.string().optional().describe('导演注释'),
         shot_intent: z.string().optional().describe('这镜为什么存在(叙事意图)'),
+        image_prompt: z.string().optional().describe('首帧画面提示词**正文**(全量覆盖本镜现值)。★先 get_shot_prompts 读现值再改;★原样保留其中的 @char:N / @scene:M 引用标记,删了就不注入对应定妆图/场景图。出图时平台会在正文之上再拼身份锚与一致性约束,不必你写'),
+        video_prompt: z.string().optional().describe('视频(动态/运镜/表演)提示词**正文**(全量覆盖本镜现值)。★同 image_prompt:先读现值、保留 @char/@scene 标记'),
     }, async ({ storyboard_id, ...fields }) => {
         const payload = Object.fromEntries(Object.entries(fields).filter(([, v]) => v !== undefined));
         return jsonResult(await client.producePut(`/storyboards/${storyboard_id}`, payload));
     });
+    server.tool('get_shot_prompts', '读某一镜的两条提示词**正文**(image_prompt=首帧画面 / video_prompt=动态表演),供直接微调后用 update_shot 写回。免费。' +
+        '★逐镜按需:改哪镜读哪镜(整集列表 get_storyboards 是纯进度视图,不含提示词)。' +
+        '★返回的 asset_tokens 是正文里的角色/场景参考图引用标记(@char:N / @scene:M)——改写时原样保留,' +
+        '删掉本镜就不注入对应定妆图/场景图,画面会漂。' +
+        '★这是分镜表里的正文层;出图/出视频时平台还会在其上拼身份锚、一致性约束与参考图指令(不在此处,也无需你写)。' +
+        '改完提示词不会自动重出图/视频,要让画面跟上得再 regen 对应镜。', { storyboard_id: z.number().int().positive() }, async ({ storyboard_id }) => jsonResult(await client.produceGet(`/storyboards/${storyboard_id}/prompts`)));
     server.tool('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。', { episode_id: z.number().int().positive() }, async ({ episode_id }) => jsonResult(await client.producePost(`/episodes/${episode_id}/re-render`)));
     server.tool('replace_shot_dialogue', '换某镜对白音色/声线(转写+克隆重配)。后台异步,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,' +

package/openapi.json

@@ -2,8 +2,8 @@
   "openapi": "3.1.0",
   "info": {
     "title": "StarReel Production API",
-    "version": "0.1.56",
-    "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 v0.1.56 tool surface (operationIds match MCP tool names 1:1)."
+    "version": "0.1.57",
+    "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 v0.1.57 tool surface (operationIds match MCP tool names 1:1)."
   },
   "servers": [
     {
@@ -152,7 +152,7 @@
       "get": {
         "operationId": "get_bulk_import_spec",
         "summary": "取**批量导入 JSON 的格式契约**:markdown 范本全文 + template(占位符模板,<",
-        "description": "取**批量导入 JSON 的格式契约**:markdown 范本全文 + template(占位符模板,<...> 必须替换) + filled_example(成品对照,可直接照结构填) + external_prompt(转发给外部 AI/自己工具的任务提示词) + checklist + enums(mode/role/char_type/shot_type/action_motion_class 的合法值,与校验器同源) + limits(数组与字段上限)。免费·静态·不扣费。★什么时候用:客户能从自己的工具/表格导出结构化数据、或要让外部 AI 直接产出 JSON 一次建好角色+场景+分镜时——**在 bulk_import_storyboards 之前**先调它。★与 import_storyboard_table(文本一镜一行)的分工:数据本来就是结构化的走 JSON;客户手上是文本分镜表走那条。★契约要点:顶层 { mode, episode_meta?, characters?[], scenes?[], storyboards[] };characters 按 name 去重、scenes 按 location+time 去重、storyboards 按 storyboard_number 去重;bound_characters 引用 characters[].name(或本剧已有角色名)、scene_ref 引用 scenes[] 的 location+time——引用不到会**静默跳过**;每镜 action/description 至少一个;dialogue 是 `说话人：台词`、别写舞台指示(会被念出来);image_prompt/video_prompt 可不填(平台拼基础描述),**通过 MCP 导入时这两个字段与 frame_visual_contract 会被忽略**(prompt 工程由平台生成)。",
+        "description": "取**批量导入 JSON 的格式契约**:markdown 范本全文 + template(占位符模板,<...> 必须替换) + filled_example(成品对照,可直接照结构填) + external_prompt(转发给外部 AI/自己工具的任务提示词) + checklist + enums(mode/role/char_type/shot_type/action_motion_class 的合法值,与校验器同源) + limits(数组与字段上限)。免费·静态·不扣费。★什么时候用:客户能从自己的工具/表格导出结构化数据、或要让外部 AI 直接产出 JSON 一次建好角色+场景+分镜时——**在 bulk_import_storyboards 之前**先调它。★与 import_storyboard_table(文本一镜一行)的分工:数据本来就是结构化的走 JSON;客户手上是文本分镜表走那条。★契约要点:顶层 { mode, episode_meta?, characters?[], scenes?[], storyboards[] };characters 按 name 去重、scenes 按 location+time 去重、storyboards 按 storyboard_number 去重;bound_characters 引用 characters[].name(或本剧已有角色名)、scene_ref 引用 scenes[] 的 location+time——引用不到会**静默跳过**;每镜 action/description 至少一个;dialogue 是 `说话人：台词`、别写舞台指示(会被念出来);image_prompt/video_prompt 可不填(没填的镜由平台按景别+场景+光线+action 拼基础描述);填了就**逐字照用**,平台不覆盖。frame_visual_contract 是内部帧契约,导入时忽略。",
         "tags": [
           "bulk-import"
         ],
@@ -4775,7 +4775,7 @@
       "post": {
         "operationId": "bulk_import_storyboards",
         "summary": "把一份结构化 JSON 一次性建成本集的角色 / 场景 / 分镜(按 name / location+time / storyboard_number 去重更新)",
-        "description": "把一份结构化 JSON 一次性建成本集的角色 / 场景 / 分镜(按 name / location+time / storyboard_number 去重更新)。免费·确定性·不调 AI。★三步走:① get_bulk_import_spec 取契约与成品示例;② check_bulk_import 自检到 errors 清零;③ 再调本工具。★mode=merge(默认)保留未提到的镜;mode=replace 替换本集**全部**分镜(旧镜与已生成图/视频归档可恢复、不会自动重挂)——replace 必须先得到客户明确同意。★image_prompt / video_prompt / frame_visual_contract 在门面被剥掉:prompt 工程由平台生成(缺省按景别+场景+光线+action 拼基础描述,回执 base_prompts_built 是拼了几镜);想更专业用 enhance_shot_prompts。★导入后:语速律会抬高装不下台词的镜(回执 speech_duration_raised / speech_duration_overflow)。★导入后**默认自动补全**(auto_complete,跟随剧目「自动补齐辅助资产」开关、默认开):同一后台批次给全镜 AI 填空专业字段(只填空),并只给**没填 image_prompt、由平台拼了基础描述**的镜扩写完整出图/视频提示词(客户自己写的绝不覆盖;回执 auto_complete.prompt_shots)。文本步按 token 后付,**调用前告知客户**;只想导入传 auto_complete:false。回执 started=true 后用 get_autofill_status 轮询到 done **再** review_storyboards。",
+        "description": "把一份结构化 JSON 一次性建成本集的角色 / 场景 / 分镜(按 name / location+time / storyboard_number 去重更新)。免费·确定性·不调 AI。★三步走:① get_bulk_import_spec 取契约与成品示例;② check_bulk_import 自检到 errors 清零;③ 再调本工具。★mode=merge(默认)保留未提到的镜;mode=replace 替换本集**全部**分镜(旧镜与已生成图/视频归档可恢复、不会自动重挂)——replace 必须先得到客户明确同意。★image_prompt / video_prompt 想自己写就直接写在每镜里,**逐字照用不被覆盖**;没填的镜平台拼基础描述(回执 base_prompts_built 是拼了几镜),导入后可用 get_shot_prompts 读、update_shot 改。(frame_visual_contract 是内部帧契约,导入时忽略。)★导入后:语速律会抬高装不下台词的镜(回执 speech_duration_raised / speech_duration_overflow)。★导入后**默认自动补全**(auto_complete,跟随剧目「自动补齐辅助资产」开关、默认开):同一后台批次给全镜 AI 填空专业字段(只填空),并只给**没填 image_prompt、由平台拼了基础描述**的镜扩写完整出图/视频提示词(客户自己写的绝不覆盖;回执 auto_complete.prompt_shots)。文本步按 token 后付,**调用前告知客户**;只想导入传 auto_complete:false。回执 started=true 后用 get_autofill_status 轮询到 done **再** review_storyboards。",
         "tags": [
           "episodes"
         ],
@@ -6148,7 +6148,7 @@
       "put": {
         "operationId": "update_shot",
         "summary": "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)与角色绑定(character_ids)",
-        "description": "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)与角色绑定(character_ids)。只传要改的字段、其余不动。**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。★★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。",
+        "description": "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)与角色绑定(character_ids)。只传要改的字段、其余不动。**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。★★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。★也可直接改本镜的两条提示词正文(image_prompt/video_prompt):改前先用 get_shot_prompts 读现值,别凭空覆盖——正文里的 @char:N / @scene:M 是角色/场景参考图的引用标记,删掉本镜就不注入对应定妆图/场景图(形象漂移)。",
         "tags": [
           "storyboards"
         ],
@@ -6212,6 +6212,12 @@
                   },
                   "shot_intent": {
                     "type": "string"
+                  },
+                  "image_prompt": {
+                    "type": "string"
+                  },
+                  "video_prompt": {
+                    "type": "string"
                   }
                 }
               }
@@ -6727,6 +6733,53 @@
         }
       }
     },
+    "/storyboards/{storyboard_id}/prompts": {
+      "get": {
+        "operationId": "get_shot_prompts",
+        "summary": "读某一镜的两条提示词**正文**(image_prompt=首帧画面 / video_prompt=动态表演),供直接微调后用 update_shot 写回",
+        "description": "读某一镜的两条提示词**正文**(image_prompt=首帧画面 / video_prompt=动态表演),供直接微调后用 update_shot 写回。免费。★逐镜按需:改哪镜读哪镜(整集列表 get_storyboards 是纯进度视图,不含提示词)。★返回的 asset_tokens 是正文里的角色/场景参考图引用标记(@char:N / @scene:M)——改写时原样保留,删掉本镜就不注入对应定妆图/场景图,画面会漂。★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。",
+        "tags": [
+          "storyboards"
+        ],
+        "parameters": [
+          {
+            "name": "storyboard_id",
+            "in": "path",
+            "required": true,
+            "schema": {
+              "type": "integer",
+              "exclusiveMinimum": 0
+            }
+          }
+        ],
+        "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": "0.1.56",
+  "version": "0.1.57",
   "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": "0.1.56",
+  "version": "0.1.57",
   "websiteUrl": "https://starreel.ai",
   "packages": [
     {
       "registryType": "npm",
       "identifier": "@starreel/mcp",
-      "version": "0.1.56",
+      "version": "0.1.57",
       "transport": {
         "type": "stdio"
       },