@starreel/mcp 0.1.70 → 0.1.71
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 +10 -0
- package/dist/tools/produce.js +4 -0
- package/openapi.json +3 -3
- package/package.json +1 -1
- package/server.json +2 -2
package/SKILL.md
CHANGED
|
@@ -214,6 +214,16 @@ content that will be rejected.
|
|
|
214
214
|
on hailuo-3 / wan3.0 / wan3.0-prime — `edit_video_shot` rejects
|
|
215
215
|
`start_sec`/`end_sec` on them. `edit_video_shot` also takes a per-call
|
|
216
216
|
`model` so one shot can be edited on a different engine than the drama's.
|
|
217
|
+
**Negative phrasing backfires.** If the receipt carries
|
|
218
|
+
`edit_instruction_negation_advisory`, the instruction contained phrases like
|
|
219
|
+
"don't use X" / "不能采用X". Video models read nouns as positive cues, so the
|
|
220
|
+
thing you forbade is often exactly what gets performed — the forbidden item is
|
|
221
|
+
the most salient one in the model's prior. It is advisory only (the job was
|
|
222
|
+
submitted), but on the next pass **replace the negation with a positive
|
|
223
|
+
description** — state what the shot should do (the opening gesture, where the
|
|
224
|
+
hands are, the beat timing). Measured: an instruction saying "do not use the
|
|
225
|
+
reference image's raised-arm pose" produced exactly that raised arm at the
|
|
226
|
+
opening, overriding the source video's motion.
|
|
217
227
|
**How to choose (guide the customer proactively)**: ① realistic live-action
|
|
218
228
|
dramas → `seedance-2.5` (best instruction-following and face detail), or
|
|
219
229
|
`hailuo-3` to cut cost to ~1/3 (slower, ~6 min/shot); ② stylized / animated /
|
package/dist/tools/produce.js
CHANGED
|
@@ -931,6 +931,10 @@ export function registerProduceTools(server, client) {
|
|
|
931
931
|
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。' +
|
|
932
932
|
'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);' +
|
|
933
933
|
'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。' +
|
|
934
|
+
'\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」)。' +
|
|
935
|
+
'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。' +
|
|
936
|
+
'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),' +
|
|
937
|
+
'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。' +
|
|
934
938
|
'\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。' +
|
|
935
939
|
'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。' +
|
|
936
940
|
CONFIRM_HINT, {
|
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 → 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.
|
|
5
|
+
"version": "0.1.71",
|
|
6
|
+
"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)."
|
|
7
7
|
},
|
|
8
8
|
"servers": [
|
|
9
9
|
{
|
|
@@ -8244,7 +8244,7 @@
|
|
|
8244
8244
|
"post": {
|
|
8245
8245
|
"operationId": "edit_video_shot",
|
|
8246
8246
|
"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",
|
|
8247
|
-
"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★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。",
|
|
8247
|
+
"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。",
|
|
8248
8248
|
"tags": [
|
|
8249
8249
|
"storyboards"
|
|
8250
8250
|
],
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@starreel/mcp",
|
|
3
|
-
"version": "0.1.
|
|
3
|
+
"version": "0.1.71",
|
|
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": "0.1.71",
|
|
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": "0.1.71",
|
|
12
12
|
"transport": {
|
|
13
13
|
"type": "stdio"
|
|
14
14
|
},
|