@starreel/mcp 0.1.99 → 0.1.100
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/SKILL.md +3 -1
- package/dist/tools/guide-data.js +1 -1
- package/dist/tools/produce.js +4 -3
- package/openapi.json +4 -4
- package/package.json +1 -1
- package/server.json +2 -2
package/SKILL.md
CHANGED
|
@@ -301,7 +301,9 @@ content that will be rejected.
|
|
|
301
301
|
frames generated through this API (`generate_frames` / `generate_shot_frame`) do not
|
|
302
302
|
trigger it, so an API-driven episode has usually never been joined.
|
|
303
303
|
`get_storyboards` reports every shot's `seam_state` (the seam between it and the shot
|
|
304
|
-
before it): act on `unchained` (marked continuous
|
|
304
|
+
before it): act on `unchained` (marked continuous and never joined — or a join the
|
|
305
|
+
platform started whose regenerated first frame never landed: rejected, failed, or still
|
|
306
|
+
generating) and `broken` (joined,
|
|
305
307
|
but the platform's continuity check says it doesn't hold — `seam_failed_dims` names
|
|
306
308
|
which of characters / wardrobe / props / lighting / scene broke). Leave `intended`
|
|
307
309
|
(hard cut, scene or time change, big shot-size jump, insert shot, customer upload) and
|
package/dist/tools/guide-data.js
CHANGED
|
@@ -227,7 +227,7 @@ export const PIPELINE = [
|
|
|
227
227
|
'★开跑前用 `get_pipeline_status` 核对 generate_scene_images 的 completed/total——缺基板照样能出帧,' +
|
|
228
228
|
'但背景从每个场景的首镜起就开始漂;`review_storyboards` 也会把缺口报成 scene_plate_missing。' +
|
|
229
229
|
'★首尾帧补齐后、出视频前**接缝**:逐镜出帧不会触发平台的自动帧链,镜与镜之间多半没接过。' +
|
|
230
|
-
'`get_storyboards` 看每镜 seam_state(unchained
|
|
230
|
+
'`get_storyboards` 看每镜 seam_state(unchained=标了连续却没接、或衔接重生没落地,broken=接过没接上),' +
|
|
231
231
|
'整集用 `chain_frames` 先 dry_run:true 报计划与预估(copy 免费、reframe 每道一张图)、客户确认后执行——' +
|
|
232
232
|
'已接好的缝不进计划,重复执行不重复扣费;只补个别缝用 `chain_shot_from_prev`(免费,同景别延续)' +
|
|
233
233
|
'或 `chain_shot_from` mode=reframe(报价后执行,保景别)。`review_frames` 会把两类缝报成 seam_unchained / seam_broken。',
|
package/dist/tools/produce.js
CHANGED
|
@@ -546,11 +546,12 @@ export function registerProduceTools(server, client) {
|
|
|
546
546
|
'改绑用 update_shot 的 character_ids(★全量覆盖,先从这里读现值再改,漏传即解绑)与 character_presence;' +
|
|
547
547
|
'改完再读一次本工具核对。character_bindings 缺席 = 这次没读到(不是没绑),空数组才是没绑。' +
|
|
548
548
|
'★每镜带 **seam_state**(本镜与上一镜的镜间接缝,与官网帧时间线同一判据):' +
|
|
549
|
-
'ok=已续接(
|
|
549
|
+
'ok=已续接(首帧就是上镜尾帧,或平台做过首尾帧衔接且已落地) / ' +
|
|
550
|
+
'unchained=该连续却没接上(标了连续从没接过,或平台发起的衔接重生没落地:被拒/失败/还在生成——本镜 frame_status 会是 failed/processing) / ' +
|
|
550
551
|
'broken=接过但没接上(seam_failed_dims 给出哪几维不连续:characters/wardrobe/props/lighting/scene) / ' +
|
|
551
552
|
'intended=有意切换(硬切/换场/时间跳跃/景别大跳/插入镜/外部上传帧),不用管 / missing=两侧帧没齐 / ' +
|
|
552
553
|
'unknown=没标意图也没接过(系统没判,不是有问题) / na=首镜或旁白卡。' +
|
|
553
|
-
'seam_audit_status=pending
|
|
554
|
+
'seam_audit_status=pending 表示衔接已落地、平台的衔接审计还没出结论。' +
|
|
554
555
|
'出视频前只需处理 unchained 与 broken:整集用 chain_frames(先 dry_run),单道用 chain_shot_from_prev / chain_shot_from。', { episode_id: z.number().int().positive() }, async ({ episode_id }) => jsonResult(await client.produceGet(`/episodes/${episode_id}/storyboards`)));
|
|
555
556
|
// ---------- 在途运行状态(免费):区分「还在跑」和「已经死了」----------
|
|
556
557
|
server.tool('get_run_status', '(★免费·长耗时操作后必用)查这一集当前有没有 agent 正在跑。' +
|
|
@@ -653,7 +654,7 @@ export function registerProduceTools(server, client) {
|
|
|
653
654
|
'孤儿角色变体、场景图被人物污染。★generate_videos 之前必须先跑本工具——出视频是全链最贵的一步,' +
|
|
654
655
|
'拿着漂移的首帧整集出视频是最典型的废片形态。按 findings.action 修完(多为 generate_character_portraits / ' +
|
|
655
656
|
'generate_shot_frame 单镜重生)再复审。' +
|
|
656
|
-
'★还会报**镜间接缝**(warning,不拦):code=seam_unchained(
|
|
657
|
+
'★还会报**镜间接缝**(warning,不拦):code=seam_unchained(标了连续却从没做过首尾帧衔接,或发起的衔接重生没落地)/' +
|
|
657
658
|
'seam_broken(接过但没接上),shots 是「与上一镜的缝有问题」的那一镜。出视频前修最便宜——视频按首帧生成,' +
|
|
658
659
|
'首帧与上镜尾帧对不上,成片就是一次跳切。修法看 action(整集 chain_frames 先 dry_run;单道 chain_shot_from_prev / chain_shot_from)。', { episode_id: z.number().int().positive() }, async ({ episode_id }) => jsonResult(await client.producePost(`/episodes/${episode_id}/review/frames`)));
|
|
659
660
|
server.tool('review_all', '(推荐·免费)三层一次跑完的整体体检:剧本+分镜+镜头图片。开工前摸底、交付前复查用。' +
|
package/openapi.json
CHANGED
|
@@ -2,8 +2,8 @@
|
|
|
2
2
|
"openapi": "3.1.0",
|
|
3
3
|
"info": {
|
|
4
4
|
"title": "StarReel Production API",
|
|
5
|
-
"version": "0.1.
|
|
6
|
-
"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.
|
|
5
|
+
"version": "0.1.100",
|
|
6
|
+
"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 v0.1.100 tool surface (operationIds match MCP tool names 1:1)."
|
|
7
7
|
},
|
|
8
8
|
"servers": [
|
|
9
9
|
{
|
|
@@ -5547,7 +5547,7 @@
|
|
|
5547
5547
|
"post": {
|
|
5548
5548
|
"operationId": "review_frames",
|
|
5549
5549
|
"summary": "【第③道硬闸·免费】审查镜头图片层:角色身份锚覆盖(缺定妆图的角色在镜头里必漂)、出图失败率、孤儿角色变体、场景图被人物污染",
|
|
5550
|
-
"description": "【第③道硬闸·免费】审查镜头图片层:角色身份锚覆盖(缺定妆图的角色在镜头里必漂)、出图失败率、孤儿角色变体、场景图被人物污染。★generate_videos 之前必须先跑本工具——出视频是全链最贵的一步,拿着漂移的首帧整集出视频是最典型的废片形态。按 findings.action 修完(多为 generate_character_portraits / generate_shot_frame 单镜重生)再复审。★还会报**镜间接缝**(warning,不拦):code=seam_unchained(
|
|
5550
|
+
"description": "【第③道硬闸·免费】审查镜头图片层:角色身份锚覆盖(缺定妆图的角色在镜头里必漂)、出图失败率、孤儿角色变体、场景图被人物污染。★generate_videos 之前必须先跑本工具——出视频是全链最贵的一步,拿着漂移的首帧整集出视频是最典型的废片形态。按 findings.action 修完(多为 generate_character_portraits / generate_shot_frame 单镜重生)再复审。★还会报**镜间接缝**(warning,不拦):code=seam_unchained(标了连续却从没做过首尾帧衔接,或发起的衔接重生没落地)/seam_broken(接过但没接上),shots 是「与上一镜的缝有问题」的那一镜。出视频前修最便宜——视频按首帧生成,首帧与上镜尾帧对不上,成片就是一次跳切。修法看 action(整集 chain_frames 先 dry_run;单道 chain_shot_from_prev / chain_shot_from)。",
|
|
5551
5551
|
"tags": [
|
|
5552
5552
|
"episodes"
|
|
5553
5553
|
],
|
|
@@ -6263,7 +6263,7 @@
|
|
|
6263
6263
|
"get": {
|
|
6264
6264
|
"operationId": "get_storyboards",
|
|
6265
6265
|
"summary": "读某一集的分镜列表(供审阅/查进度)",
|
|
6266
|
-
"description": "读某一集的分镜列表(供审阅/查进度)。含每镜首帧(first_frame_image)与视频(video_url)是否就绪。★每镜带**台词与说话人**:dialogue(原文,无台词为 null)、dialogue_lines([{speaker,text}] 逐行,与字幕/配音同一个解析器拆的——这里的 speaker 就是成片里被配音的那个;舞台提示已剥),以及 is_key_moment(1=关键镜,走高端图模)与 emotion_intensity(1-10)。核对「台词有没有丢/谁说的/关键镜是哪几镜/情绪曲线」用这一次调用即可,不用逐镜拉;update_shot 改完台词也在这里核对。画面/视频/首尾帧提示词仍只在 get_shot_prompts 逐镜读。★每镜还带**结构化状态**:frame_status/video_status(ready/pending/authorizing/rejected/failed/none/not_required)、★not_required=旁白/片尾卡镜:帧与视频由成片层渲染,本镜不需要生成——数补齐进度时把它当已完成,别重试。fail_reason(sensitive/text_sensitive/copyright/face_mismatch/account_overdue/quota_full/authorizing/insufficient_credits/transient/repeat_rejected/pair_collateral)、retryable(true=可重试;false=改内容换图,重试无效)、fail_hint(人读文案)。照 retryable 判该重试还是该改内容,别解析中文。★pair_collateral=同镜另一帧未通过、本帧随批结束——**本帧自身没被判不合格,别去改它**:有 reopen_pair_id 就用它只重掷有过错的一侧,否则直接重生本镜。★若某镜带 degraded_frames:[{frame_type,reason,reason_label,since,hint}],表示该帧是系统在同因连拒熔断后**放行**的(判据照记未拒),URL 上与干净帧无区别但需人工复核;不满意按 hint 修正输入后 generate_shot_frame 重生该帧。★terminal_desc_missing=true:该镜标为「状态改变」却三处都没说结束时什么样——**出尾帧前**就能看出来,现在整集一次拿到(此前只有 get_shot_prompts 能逐镜问,一集几十次没人会去问)。先 update_shot 把结束状态写进 last_frame_prompt 再出尾帧:照现状硬出的历史成功率 9.4%,写了终态的 40.2%,而每次被拒都照常扣费。确实该「几乎不变」的镜才用 generate_shot_frame 的 allow_missing_terminal 放行。★first_frame_source/last_frame_source='upload' 表示该帧是**外部上传图**(绕开了身份锚/画风锚/best-of-N/帧审计整条质量链路)——人物·服装·画风漂移排查先看这些镜;外部图导致的漂移不是平台生成质量问题,修复正路是删掉外部图改走 generate_shot_frame 平台重生。★若某镜带 reopen_pair_id:该镜首尾帧同时生成时只有一侧真的有问题、另一侧是无辜陪拒,原样传给 generate_shot_frame 的 reopen_pair_id 参数可以只重掷有问题的那一侧(省一半算力/费用,不会拿去生成一张这次根本没打算重做的图)。没有这个字段就按 fail_reason/retryable 走常规重试。免费。★每镜还带**绑定**(只有 ID):character_ids(本镜绑定的角色)、character_bindings[{character_id,presence}](presence=on_screen 在画面 / voice_only 只有声音、不进画面)、scene_id、prop_ids、active_wardrobe_id。出图注入谁的定妆图/哪张场景图/哪些道具图由这几项决定;角色名对照 get_characters、道具名对照 get_props。改绑用 update_shot 的 character_ids(★全量覆盖,先从这里读现值再改,漏传即解绑)与 character_presence;改完再读一次本工具核对。character_bindings 缺席 = 这次没读到(不是没绑),空数组才是没绑。★每镜带 **seam_state**(本镜与上一镜的镜间接缝,与官网帧时间线同一判据):ok=已续接(
|
|
6266
|
+
"description": "读某一集的分镜列表(供审阅/查进度)。含每镜首帧(first_frame_image)与视频(video_url)是否就绪。★每镜带**台词与说话人**:dialogue(原文,无台词为 null)、dialogue_lines([{speaker,text}] 逐行,与字幕/配音同一个解析器拆的——这里的 speaker 就是成片里被配音的那个;舞台提示已剥),以及 is_key_moment(1=关键镜,走高端图模)与 emotion_intensity(1-10)。核对「台词有没有丢/谁说的/关键镜是哪几镜/情绪曲线」用这一次调用即可,不用逐镜拉;update_shot 改完台词也在这里核对。画面/视频/首尾帧提示词仍只在 get_shot_prompts 逐镜读。★每镜还带**结构化状态**:frame_status/video_status(ready/pending/authorizing/rejected/failed/none/not_required)、★not_required=旁白/片尾卡镜:帧与视频由成片层渲染,本镜不需要生成——数补齐进度时把它当已完成,别重试。fail_reason(sensitive/text_sensitive/copyright/face_mismatch/account_overdue/quota_full/authorizing/insufficient_credits/transient/repeat_rejected/pair_collateral)、retryable(true=可重试;false=改内容换图,重试无效)、fail_hint(人读文案)。照 retryable 判该重试还是该改内容,别解析中文。★pair_collateral=同镜另一帧未通过、本帧随批结束——**本帧自身没被判不合格,别去改它**:有 reopen_pair_id 就用它只重掷有过错的一侧,否则直接重生本镜。★若某镜带 degraded_frames:[{frame_type,reason,reason_label,since,hint}],表示该帧是系统在同因连拒熔断后**放行**的(判据照记未拒),URL 上与干净帧无区别但需人工复核;不满意按 hint 修正输入后 generate_shot_frame 重生该帧。★terminal_desc_missing=true:该镜标为「状态改变」却三处都没说结束时什么样——**出尾帧前**就能看出来,现在整集一次拿到(此前只有 get_shot_prompts 能逐镜问,一集几十次没人会去问)。先 update_shot 把结束状态写进 last_frame_prompt 再出尾帧:照现状硬出的历史成功率 9.4%,写了终态的 40.2%,而每次被拒都照常扣费。确实该「几乎不变」的镜才用 generate_shot_frame 的 allow_missing_terminal 放行。★first_frame_source/last_frame_source='upload' 表示该帧是**外部上传图**(绕开了身份锚/画风锚/best-of-N/帧审计整条质量链路)——人物·服装·画风漂移排查先看这些镜;外部图导致的漂移不是平台生成质量问题,修复正路是删掉外部图改走 generate_shot_frame 平台重生。★若某镜带 reopen_pair_id:该镜首尾帧同时生成时只有一侧真的有问题、另一侧是无辜陪拒,原样传给 generate_shot_frame 的 reopen_pair_id 参数可以只重掷有问题的那一侧(省一半算力/费用,不会拿去生成一张这次根本没打算重做的图)。没有这个字段就按 fail_reason/retryable 走常规重试。免费。★每镜还带**绑定**(只有 ID):character_ids(本镜绑定的角色)、character_bindings[{character_id,presence}](presence=on_screen 在画面 / voice_only 只有声音、不进画面)、scene_id、prop_ids、active_wardrobe_id。出图注入谁的定妆图/哪张场景图/哪些道具图由这几项决定;角色名对照 get_characters、道具名对照 get_props。改绑用 update_shot 的 character_ids(★全量覆盖,先从这里读现值再改,漏传即解绑)与 character_presence;改完再读一次本工具核对。character_bindings 缺席 = 这次没读到(不是没绑),空数组才是没绑。★每镜带 **seam_state**(本镜与上一镜的镜间接缝,与官网帧时间线同一判据):ok=已续接(首帧就是上镜尾帧,或平台做过首尾帧衔接且已落地) / unchained=该连续却没接上(标了连续从没接过,或平台发起的衔接重生没落地:被拒/失败/还在生成——本镜 frame_status 会是 failed/processing) / broken=接过但没接上(seam_failed_dims 给出哪几维不连续:characters/wardrobe/props/lighting/scene) / intended=有意切换(硬切/换场/时间跳跃/景别大跳/插入镜/外部上传帧),不用管 / missing=两侧帧没齐 / unknown=没标意图也没接过(系统没判,不是有问题) / na=首镜或旁白卡。seam_audit_status=pending 表示衔接已落地、平台的衔接审计还没出结论。出视频前只需处理 unchained 与 broken:整集用 chain_frames(先 dry_run),单道用 chain_shot_from_prev / chain_shot_from。",
|
|
6267
6267
|
"tags": [
|
|
6268
6268
|
"episodes"
|
|
6269
6269
|
],
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@starreel/mcp",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.100",
|
|
4
4
|
"mcpName": "ai.starreel/starreel",
|
|
5
5
|
"description": "StarReel MCP server — drive the AI short-drama production pipeline (script → storyboards → frames → video → final cut) from Claude, Cursor, or any MCP client",
|
|
6
6
|
"license": "MIT",
|
package/server.json
CHANGED
|
@@ -2,13 +2,13 @@
|
|
|
2
2
|
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
|
|
3
3
|
"name": "ai.starreel/starreel",
|
|
4
4
|
"description": "Turn a script into a finished, downloadable short-drama episode — via MCP or REST.",
|
|
5
|
-
"version": "0.1.
|
|
5
|
+
"version": "0.1.100",
|
|
6
6
|
"websiteUrl": "https://starreel.ai",
|
|
7
7
|
"packages": [
|
|
8
8
|
{
|
|
9
9
|
"registryType": "npm",
|
|
10
10
|
"identifier": "@starreel/mcp",
|
|
11
|
-
"version": "0.1.
|
|
11
|
+
"version": "0.1.100",
|
|
12
12
|
"transport": {
|
|
13
13
|
"type": "stdio"
|
|
14
14
|
},
|