@starreel/mcp 0.1.71 → 0.1.73

package/SKILL.md

@@ -143,8 +143,11 @@ content that will be rejected.
 3. **`retryable` decides retry-vs-change — never blind-retry.** On failure read
    the structured `fail_reason` / `retryable` (from `get_storyboards`) or the
    `message` / `error.type`. `retryable:false` (moderation, copyright, quota,
-   overdue) → change the content or stop; retrying is useless. `retryable:true`
-   (KYC-queuing, rate-limit, transient) → back off, then retry.
+   overdue, `needs_content_fix`) → change the content or stop; retrying is useless.
+   `retryable:true` (KYC-queuing, rate-limit, `transient`) → back off, then retry.
+   `contract_rejected` is retryable **but is not a network blip**: it is a content
+   or contract conflict that a re-roll clears about a third of the time. Retry once
+   or twice, then read `fail_hint` and change the shot — do not keep re-rolling.
 
 4. **Content must be compliant.** Do not generate copyrighted characters,
    trademarks, real-person likenesses, or sensitive content. On a moderation /
@@ -475,8 +478,10 @@ Map the reason to an action:
 | `quota_full` | false | Platform vendor-asset quota exhausted | Retry won't help — contact ops |
 | `insufficient_credits` | false | Balance too low for this call | Stop, prompt to recharge (402) |
 | `authorizing` | true | Face frame queuing for KYC (not a rejection) | Wait ~1 min, retry |
-| `transient` | true | BestOfN / quality-gate / rate-limit / network | Back off, retry |
-| `repeat_rejected` | false | Same shot rejected for the same reason until the circuit breaker tripped (auto-clears after 24 h) | Change the prompt / references / contract **first**; a blind retry is a full-price repeat of the same rejection |
+| `transient` | true | BestOfN / quality-gate / rate-limit / network, or the audit itself failed to run | Back off, retry |
+| `contract_rejected` | true | A **content/contract** rejection (era, composition, shot size, head-count, readable text…) — **not** a network blip. Measured: a blind re-roll clears it about a third of the time | Retry once or twice; if the same reason keeps coming back, read `fail_hint` and change the shot (see *What you can actually change* below) instead of re-rolling |
+| `needs_content_fix` | false | A content/contract conflict that a re-roll almost never clears (measured ≤10%) — most often the character's wardrobe/accessory record conflicting with the approved portrait | Change the shot description / character record **first**, then regenerate. A blind retry is a full-price repeat |
+| `repeat_rejected` | false | Same shot rejected for the same reason until the circuit breaker tripped (auto-clears after 24 h) | Change the prompt / references / shot design **first** (see *What you can actually change* below); a blind retry is a full-price repeat of the same rejection |
 | `pair_collateral` | true | The **other** frame of this shot failed its audit; this frame was never judged bad — it was only closed out with the batch | Do **not** edit this frame. If the shot carries `reopen_pair_id`, pass it to `generate_shot_frame` to redo only the faulty side; otherwise regenerate the shot |
 | `unknown` | false | Unclassified | Read `fail_hint`; don't auto-retry |
 
@@ -486,6 +491,41 @@ repeatedly** (the verdict is recorded, not enforced) — the URL looks like any
 frame, but it needs a human look. If it is not acceptable, fix the input the
 `hint` names and regenerate that frame with `generate_shot_frame`.
 
+### What you can actually change when a shot keeps getting rejected
+
+**There is no tool that edits `frame_visual_contract`, and there is not meant to
+be.** It is an internal per-frame contract (subject mode, visible head-count,
+framing) derived by the platform; it drives a dozen downstream judgements, so the
+facade deliberately strips it from every write path. Do not go looking for it,
+and do not tell the customer to "fix the contract" — they cannot, and neither can
+you. What you *can* change, in the order worth trying:
+
+1. **`update_shot`** — `shot_type`, `description`, `action`, and the two prompt
+   bodies. This is usually the real fix: a shot whose `image_prompt` describes a
+   head-and-shoulders portrait but whose `shot_type` says 特写 will keep failing
+   the shot-size gate until one of the two is corrected to match the other.
+2. **`character_ids`** on that shot — binding is *narrative* attribution, but an
+   over-bound shot inflates what the frame audit expects to see.
+3. **References** — `set_character_portrait` / wardrobe records, when the
+   rejection is identity- or costume-shaped.
+4. **`run_precheck` — and run it *after* the failures too, not only before.**
+   Its description sells it as a pre-flight check, but it is just as useful once
+   a shot is already stuck: it reports the repeat-rejection circuit breaker and
+   contract self-inconsistency for shots that have been failing. Then
+   `plan_precheck_fix` → show the customer → `apply_precheck_fix`.
+
+Two contract conflicts the platform now resolves **by itself** (v0.9.1868), so
+they are never something to act on: a part/prop/environment shot that also
+declares visible people, and a tight-framing shot that declares more people than
+the frame can hold. Both are silently normalised at read time.
+
+If a shot still will not come out, say so plainly and leave it — **do not send
+the customer to an outside image tool.** Frames made elsewhere bypass the
+identity anchor, reference assembly, best-of-N and frame audit, so faces,
+wardrobe and art style drift; the customer will read that drift as *the
+platform's* quality. `upload_shot_frame` exists for genuinely external artwork,
+not as an escape hatch from a rejection loop.
+
 Three action classes, one decision: **moderation / identity / copyright → change
 content**; **overdue / token → not self-healable (tell user / wait)**; **network
 / timeout / transient → retry**. Failed spends are auto-refunded (pre-hold →

package/dist/tools/produce.js

@@ -496,6 +496,9 @@ export function registerProduceTools(server, client) {
         '★**怎么改不用你猜**:调 plan_precheck_fix 让平台算出提案(哪一镜、把什么改成什么),' +
         '讲给客户、客户点头后用 apply_precheck_fix 落库——比你自己用 update_shot 盲改稳,' +
         '那条路绕开了乐观锁与落库前复核。部分类别系统不替你改(提案里的 blocked),那些才需要人工调。\n' +
+        '★★**镜已经反复出不来时也回来跑这个**——本工具不只是事前预检。' +
+        '它同时报「同镜同因连拒已熔断(repeat-reject,24h 自动解除)」与「帧契约自相矛盾」,' +
+        '那正是"这一镜怎么重掷都出不来"的答案。**别盲重掷**:熔断在档时每次重掷都是全价重复同一个拒绝。\n' +
         '⚠️ 它**不**检查首帧是否处在"动作发生前"(平台暂无该契约字段),也不替代 get_health_report。', { episode_id: z.number().int().positive() }, async ({ episode_id }) => jsonResult(await client.produceGet(`/episodes/${episode_id}/precheck`)));
     server.tool('plan_precheck_fix', '让平台**算出**该怎么改 run_precheck 揪出的「指令自相矛盾」类问题(第①步,只算不改)。'
         + '按文本用量计费(很小),不走报价确认。\n'
@@ -538,7 +541,10 @@ export function registerProduceTools(server, client) {
         '把 findings 逐条告诉客户、按 action 修完(改稿走 edit_rewritten_script)后复审,再拿 review_token 往下走。', { episode_id: z.number().int().positive() }, async ({ episode_id }) => jsonResult(await client.producePost(`/episodes/${episode_id}/review/script`)));
     server.tool('review_storyboards', '【第②道硬闸·免费】审查分镜:禁区词(会被厂商审核拒、白扣费)、镜头时长分布、相邻构图重复、' +
         '同场景角色站位漂移、情绪曲线峰谷、关键镜标记。★generate_frames 之前必须先跑本工具——' +
-        '分镜里的问题一旦整集出图就变成整集废图,单镜修不回来。按 findings.action 用 update_shot/split_shot 修完再复审。', { episode_id: z.number().int().positive() }, async ({ episode_id }) => jsonResult(await client.producePost(`/episodes/${episode_id}/review/storyboards`)));
+        '分镜里的问题一旦整集出图就变成整集废图,单镜修不回来。按 findings.action 用 update_shot/split_shot 修完再复审。' +
+        '★code=forbidden_term 的 finding 带 `terms` 字段(命中的具体词,如「背景音乐」「强光」)与 `shots`(镜号),' +
+        '照着这两个去 update_shot 改掉即可,不用逐字猜。' +
+        '★禁区词判**否定语义**:写「无背景音乐」「不要配乐」不算违规(那是在遵守约束),不必为此改稿。', { episode_id: z.number().int().positive() }, async ({ episode_id }) => jsonResult(await client.producePost(`/episodes/${episode_id}/review/storyboards`)));
     server.tool('review_frames', '【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 / ' +
@@ -572,6 +578,10 @@ export function registerProduceTools(server, client) {
         '★响应里的 frames_planned 是**计划数,不是已成功数**——本接口在后台派发循环开跑之前就返回了。' +
         '真实进度只看 get_storyboards 的 first_frame_image / get_jobs 的逐条生成记录;' +
         '余额不足(402)会中止整批,此时轮询再久也不会有结果,应去查余额而不是继续等。' +
+        '★★**个别镜反复出不来、其余镜都好了**:那不是等得不够久,是这几镜被内容闸连拒。' +
+        '看 get_storyboards 的 fail_reason(repeat_rejected / needs_content_fix / contract_rejected),' +
+        '然后**跑 run_precheck**(事后也能跑,会告诉你是哪种矛盾),按它的提示用 update_shot 改景别/描述/绑定角色再重生。' +
+        '别继续 generate_frames 空转,也别把客户支去外部工具做图——外部图绕开身份锚与帧审计,人脸服装画风必漂。' +
         REVIEW_GATE_HINT('review_storyboards', '分镜') + CONFIRM_HINT, {
         episode_id: z.number().int().positive(),
         quote_id: z.string().describe('来自 quote_frames'),
@@ -1229,7 +1239,14 @@ export function registerProduceTools(server, client) {
         '★覆盖式:出好后本场旧图被换掉(要留档先 get_scene_prompt/资产列表拿旧图 URL)。' +
         '★已生成的镜头帧不会自动跟着重出——它们仍拿旧场景图当背景锚,要跟上得逐镜重出。' +
         '★与 generate_scene_images 的区别:那个是整剧批量、只补**缺图**的场景,已有图的一律跳过;' +
-        '这个是单场景强制重出。客户自己上传过的场景图也会被覆盖,先确认是不是要保留。', { scene_id: z.number().int().positive() }, async ({ scene_id }) => jsonResult(await client.producePost(`/scenes/${scene_id}/image/regenerate`)));
+        '这个是单场景强制重出。客户自己上传过的场景图也会被覆盖,先确认是不是要保留。' +
+        '★episode_id 通常不必传(平台按场景归属、再按引用它的分镜自动推导)。' +
+        '只有回执报「本场景被多集分镜共用」时才需要点名:那说明同一地点跨集复用,' +
+        '平台不猜该按哪一集的时代/世界观出图——猜错就是画面年代静默错掉。', {
+        scene_id: z.number().int().positive(),
+        episode_id: z.number().int().positive().optional()
+            .describe('按哪一集的时代/世界观 brief 出图。通常不必传;跨集共用的场景被要求时才传'),
+    }, async ({ scene_id, episode_id }) => jsonResult(await client.producePost(`/scenes/${scene_id}/image/regenerate`, episode_id ? { episode_id } : {})));
     server.tool('delete_scene', '删除一个场景。免费。', { scene_id: z.number().int().positive() }, async ({ scene_id }) => jsonResult(await client.produceDelete(`/scenes/${scene_id}`)));
     server.tool('generate_character_sheet', '给**单个**角色出三视图设定图(镜头一致性根锚,所有镜头帧都会引用;比定妆图更完整)。整集批量用 generate_character_sheets。' +
         '前置:该角色已有定妆图。图片步,按用量后付不欠费。', { character_id: z.number().int().positive(), episode_id: z.number().int().positive().optional() }, async ({ character_id, episode_id }) => jsonResult(await client.producePost(`/characters/${character_id}/sheet`, episode_id ? { episode_id } : {})));

package/openapi.json

@@ -2,8 +2,8 @@
   "openapi": "3.1.0",
   "info": {
     "title": "StarReel Production API",
-    "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)."
+    "version": "0.1.73",
+    "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 v0.1.73 tool surface (operationIds match MCP tool names 1:1)."
   },
   "servers": [
     {
@@ -4113,7 +4113,7 @@
       "post": {
         "operationId": "generate_frames",
         "summary": "确认后批量出帧:后台异步",
-        "description": "确认后批量出帧:后台异步。用 get_storyboards 轮询,first_frame_image/last_frame_image 逐镜填充即完成。★图片生成较慢——每张几十秒到数分钟(尤其高清模型),整集可能十几分钟。轮询看 frame_status:**pending=还在生成(继续耐心等,别当失败、别重复调 generate_frames,重复触发=白花钱)**、ready=完成、failed=才是真失败。别因为「等了一会儿还没出」就判定生成失败或重试。出视频前必须先出帧,否则视频会退化成无一致性锚点的画面。frame_type 要与 quote_frames 用的一致(默认 first_frame)。★这是**批量补缺帧**:只给「缺该帧」的镜出图,已有首帧的镜会跳过——这是正常设计、不是\"系统拒绝重出\"。要**重出/重画某一镜已有的帧**(如换了定妆图要让新图生效),用 generate_shot_frame(单镜重生,平台带身份锚),不是这个工具、更不是自制图 upload_shot_frame。★尾帧能批量出:frame_type=last_frame 会给「已有首帧且缺尾帧」的镜批量补尾帧(尾帧只在想固定某镜结尾画面/大运镜时才需,常规只出首帧)。★响应里的 frames_planned 是**计划数,不是已成功数**——本接口在后台派发循环开跑之前就返回了。真实进度只看 get_storyboards 的 first_frame_image / get_jobs 的逐条生成记录;余额不足(402)会中止整批,此时轮询再久也不会有结果,应去查余额而不是继续等。\n★【分镜审查硬闸·免费】本步前必须先调 review_storyboards:把返回的 findings 逐条原样告诉客户(每条带 code=问题类型、shots=命中镜号、action=该调哪个工具修),再把 review_token 传进本工具。未审查会被 400 拒。审查后又改了内容 → token 自动失效,复审一次即可(仍免费)。有 error 时默认拦截;客户知情并坚持照现状继续,才带 acknowledge_review:true——带病推进大概率产出废片且照常扣费,不要替客户做这个决定。⚠️ 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": "确认后批量出帧:后台异步。用 get_storyboards 轮询,first_frame_image/last_frame_image 逐镜填充即完成。★图片生成较慢——每张几十秒到数分钟(尤其高清模型),整集可能十几分钟。轮询看 frame_status:**pending=还在生成(继续耐心等,别当失败、别重复调 generate_frames,重复触发=白花钱)**、ready=完成、failed=才是真失败。别因为「等了一会儿还没出」就判定生成失败或重试。出视频前必须先出帧,否则视频会退化成无一致性锚点的画面。frame_type 要与 quote_frames 用的一致(默认 first_frame)。★这是**批量补缺帧**:只给「缺该帧」的镜出图,已有首帧的镜会跳过——这是正常设计、不是\"系统拒绝重出\"。要**重出/重画某一镜已有的帧**(如换了定妆图要让新图生效),用 generate_shot_frame(单镜重生,平台带身份锚),不是这个工具、更不是自制图 upload_shot_frame。★尾帧能批量出:frame_type=last_frame 会给「已有首帧且缺尾帧」的镜批量补尾帧(尾帧只在想固定某镜结尾画面/大运镜时才需,常规只出首帧)。★响应里的 frames_planned 是**计划数,不是已成功数**——本接口在后台派发循环开跑之前就返回了。真实进度只看 get_storyboards 的 first_frame_image / get_jobs 的逐条生成记录;余额不足(402)会中止整批,此时轮询再久也不会有结果,应去查余额而不是继续等。★★**个别镜反复出不来、其余镜都好了**:那不是等得不够久,是这几镜被内容闸连拒。看 get_storyboards 的 fail_reason(repeat_rejected / needs_content_fix / contract_rejected),然后**跑 run_precheck**(事后也能跑,会告诉你是哪种矛盾),按它的提示用 update_shot 改景别/描述/绑定角色再重生。别继续 generate_frames 空转,也别把客户支去外部工具做图——外部图绕开身份锚与帧审计,人脸服装画风必漂。\n★【分镜审查硬闸·免费】本步前必须先调 review_storyboards:把返回的 findings 逐条原样告诉客户(每条带 code=问题类型、shots=命中镜号、action=该调哪个工具修),再把 review_token 传进本工具。未审查会被 400 拒。审查后又改了内容 → token 自动失效,复审一次即可(仍免费)。有 error 时默认拦截;客户知情并坚持照现状继续,才带 acknowledge_review:true——带病推进大概率产出废片且照常扣费,不要替客户做这个决定。⚠️ 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": [
           "episodes"
         ],
@@ -4755,7 +4755,7 @@
       "get": {
         "operationId": "run_precheck",
         "summary": "(★推荐·免费质量闸)出图/出视频前跑生成前预检,把会被拒的镜提前揪出",
-        "description": "(★推荐·免费质量闸)出图/出视频前跑生成前预检,把会被拒的镜提前揪出。免费、不扣费。强烈建议 generate_frames/generate_videos 前调,防白花钱被拒。\n查这几类:①真人肖像/克隆音色授权 ②图像审核高危词 ③配音覆盖与大空档 ④**指令自相矛盾(kind=prompt-conflict)**——同一镜里互斥的要求(如宽景别却标了特写主体、既要站立又要坐姿),这类镜**任何正确的图都满足不了**,不改就会反复被拒并反复扣费,出现时应先按提示改分镜再出图,而不是重试。\n★**怎么改不用你猜**:调 plan_precheck_fix 让平台算出提案(哪一镜、把什么改成什么),讲给客户、客户点头后用 apply_precheck_fix 落库——比你自己用 update_shot 盲改稳,那条路绕开了乐观锁与落库前复核。部分类别系统不替你改(提案里的 blocked),那些才需要人工调。\n⚠️ 它**不**检查首帧是否处在\"动作发生前\"(平台暂无该契约字段),也不替代 get_health_report。",
+        "description": "(★推荐·免费质量闸)出图/出视频前跑生成前预检,把会被拒的镜提前揪出。免费、不扣费。强烈建议 generate_frames/generate_videos 前调,防白花钱被拒。\n查这几类:①真人肖像/克隆音色授权 ②图像审核高危词 ③配音覆盖与大空档 ④**指令自相矛盾(kind=prompt-conflict)**——同一镜里互斥的要求(如宽景别却标了特写主体、既要站立又要坐姿),这类镜**任何正确的图都满足不了**,不改就会反复被拒并反复扣费,出现时应先按提示改分镜再出图,而不是重试。\n★**怎么改不用你猜**:调 plan_precheck_fix 让平台算出提案(哪一镜、把什么改成什么),讲给客户、客户点头后用 apply_precheck_fix 落库——比你自己用 update_shot 盲改稳,那条路绕开了乐观锁与落库前复核。部分类别系统不替你改(提案里的 blocked),那些才需要人工调。\n★★**镜已经反复出不来时也回来跑这个**——本工具不只是事前预检。它同时报「同镜同因连拒已熔断(repeat-reject,24h 自动解除)」与「帧契约自相矛盾」,那正是\"这一镜怎么重掷都出不来\"的答案。**别盲重掷**:熔断在档时每次重掷都是全价重复同一个拒绝。\n⚠️ 它**不**检查首帧是否处在\"动作发生前\"(平台暂无该契约字段),也不替代 get_health_report。",
         "tags": [
           "episodes"
         ],
@@ -5282,7 +5282,7 @@
       "post": {
         "operationId": "review_storyboards",
         "summary": "【第②道硬闸·免费】审查分镜:禁区词(会被厂商审核拒、白扣费)、镜头时长分布、相邻构图重复、同场景角色站位漂移、情绪曲线峰谷、关键镜标记",
-        "description": "【第②道硬闸·免费】审查分镜:禁区词(会被厂商审核拒、白扣费)、镜头时长分布、相邻构图重复、同场景角色站位漂移、情绪曲线峰谷、关键镜标记。★generate_frames 之前必须先跑本工具——分镜里的问题一旦整集出图就变成整集废图,单镜修不回来。按 findings.action 用 update_shot/split_shot 修完再复审。",
+        "description": "【第②道硬闸·免费】审查分镜:禁区词(会被厂商审核拒、白扣费)、镜头时长分布、相邻构图重复、同场景角色站位漂移、情绪曲线峰谷、关键镜标记。★generate_frames 之前必须先跑本工具——分镜里的问题一旦整集出图就变成整集废图,单镜修不回来。按 findings.action 用 update_shot/split_shot 修完再复审。★code=forbidden_term 的 finding 带 `terms` 字段(命中的具体词,如「背景音乐」「强光」)与 `shots`(镜号),照着这两个去 update_shot 改掉即可,不用逐字猜。★禁区词判**否定语义**:写「无背景音乐」「不要配乐」不算违规(那是在遵守约束),不必为此改稿。",
         "tags": [
           "episodes"
         ],
@@ -7693,7 +7693,7 @@
       "post": {
         "operationId": "regenerate_scene_image",
         "summary": "按当前提示词重出**这一场**的场景图(改完 image_prompt 让画面跟上)",
-        "description": "按当前提示词重出**这一场**的场景图(改完 image_prompt 让画面跟上)。图片步,按用量后付不欠费。★覆盖式:出好后本场旧图被换掉(要留档先 get_scene_prompt/资产列表拿旧图 URL)。★已生成的镜头帧不会自动跟着重出——它们仍拿旧场景图当背景锚,要跟上得逐镜重出。★与 generate_scene_images 的区别:那个是整剧批量、只补**缺图**的场景,已有图的一律跳过;这个是单场景强制重出。客户自己上传过的场景图也会被覆盖,先确认是不是要保留。",
+        "description": "按当前提示词重出**这一场**的场景图(改完 image_prompt 让画面跟上)。图片步,按用量后付不欠费。★覆盖式:出好后本场旧图被换掉(要留档先 get_scene_prompt/资产列表拿旧图 URL)。★已生成的镜头帧不会自动跟着重出——它们仍拿旧场景图当背景锚,要跟上得逐镜重出。★与 generate_scene_images 的区别:那个是整剧批量、只补**缺图**的场景,已有图的一律跳过;这个是单场景强制重出。客户自己上传过的场景图也会被覆盖,先确认是不是要保留。★episode_id 通常不必传(平台按场景归属、再按引用它的分镜自动推导)。只有回执报「本场景被多集分镜共用」时才需要点名:那说明同一地点跨集复用,平台不猜该按哪一集的时代/世界观出图——猜错就是画面年代静默错掉。",
         "tags": [
           "scenes"
         ],
@@ -7708,6 +7708,22 @@
             }
           }
         ],
+        "requestBody": {
+          "required": false,
+          "content": {
+            "application/json": {
+              "schema": {
+                "type": "object",
+                "properties": {
+                  "episode_id": {
+                    "type": "integer",
+                    "exclusiveMinimum": 0
+                  }
+                }
+              }
+            }
+          }
+        },
         "responses": {
           "200": {
             "description": "StarReel envelope",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@starreel/mcp",
-  "version": "0.1.71",
+  "version": "0.1.73",
   "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": "0.1.71",
+  "version": "0.1.73",
   "websiteUrl": "https://starreel.ai",
   "packages": [
     {
       "registryType": "npm",
       "identifier": "@starreel/mcp",
-      "version": "0.1.71",
+      "version": "0.1.73",
       "transport": {
         "type": "stdio"
       },