@oh-story/dsh 0.1.3 → 0.1.4

package/lib/drama/skills/short-drama-review/references/production-quality-gates.md

@@ -18,7 +18,7 @@
 
 ## 一、先分清什么问题必须阻断
 
-- `structural_invariant`：引用、哈希、明确时长、同一区间摄影机指令冲突、已声明
+- `structural_invariant`：可见引用、明确时长、同一区间摄影机指令冲突、已声明
   起点/终点不一致等可以直接证明的问题；本地检查可以阻断。
 - `reviewed_invariant`：剧情意义是否丢失、人物反应是否承接后果、动作是否可执行、
   指令是否被改写；审查者引用资料给 `REVISE`。
@@ -38,7 +38,7 @@
 
 检查：
 
-- 原文覆盖表是否为每个制作相关段落说明去向；
+- 是否能从剧本的每个制作相关段落直接追到承担它的镜头或声音；
 - 每个有明确来源的动作是否只实现一次；
 - 关键结果落地后，观众是否能看到受影响者的反应或后果；
 - 重新编组前后，原文段落、镜头目的、起点/终点与声音引用是否仍相同。
@@ -55,7 +55,7 @@
 先核对负责环节的起止边界和资产版本；若剧情确实需要变化，向对应技能
 请求状态或镜头修改，不在提示词里偷偷补故事。
 
-选择性环境变换还要核对 `VID-11`：触发、准确目标范围、结束几何/状态与 `preserve_set`
+选择性环境变换还要核对 `VID-11`：触发、准确目标范围、结束几何/状态与保持项
 是否同时存在；相邻但非目标的人物、道具、文字承载面和空间锚点是否保持原位置、数量与
 状态。只写“门消失”“地面折叠”而不写留下什么及什么必须不变，属于无法确认能否执行的问题。
 
@@ -79,14 +79,14 @@
 
 ### 6. 版本和执行状态冒充内容权威
 
-同一集、镜头或提示词可能保留多个历史版本。审查前先沿 `sources` 声明的 owner、artifact、
-引用的 record ID 解析**当前权威版本**；文件更新时间、编号大小、默认展示项或最近一次执行状态
-只能帮助定位候选，不能替代 creator acceptance。下游引用旧版本时，即使内容看似合理也要
-先报告 stale binding，而不是把旧稿重新解释成现行要求。
+同一集、镜头或提示词可能保留多个历史版本。审查前先读取当前 creator-visible 文档，并按文件名、
+标题 ID 和文中明确写出的母版/替代关系判断当前版本；文件更新时间、编号大小、默认展示项或最近一次
+执行状态只能帮助定位，不能替代创作者当前决定。下游仍引用旧标题时，即使内容看似合理也要报告
+版本引用过期，而不是把旧稿重新解释成现行要求。
 
 生成或处理任务的技术状态只说明某次执行结束到哪一步，不证明语义质量。任何状态为成功的
-历史记录都必须写明当时准确的提示词记录、资产/镜头 refs 与配置；审查仍比较这些文字是否
-覆盖当前 accepted artifact。没有看过媒体时，不得从技术状态、重试次数或结果地址声称画面、
+历史记录都必须写明当时准确的提示词标题、资产/镜头引用与配置；审查仍比较这些文字是否
+覆盖当前创作者可见文档。没有看过媒体时，不得从技术状态、重试次数或结果地址声称画面、
 表演、文字和连续性已经正确。
 
 ## 三、指令优先级与改写回归（REV-09）
@@ -126,11 +126,10 @@
 不能证明提示词覆盖了原动作、反应、台词与已确认的项目指令。审查者必须比较
 改写前后必须保留的内容。
 
-缩短修改若形成补拍或替代版，必须在 `coverage_scope` 标明 `pickup/alternate`、同一文件内
-的母版或补充运动记录 ID，并把每项原文要求对应到当前运动字段或说明去向。普通母版省略
-`coverage_scope`，不为“没有版本关系”制造占位账目。
-补拍默认不替代母版；替代版只能提出替代请求，最终决定由下游审查结论
-指名替代版或母版的记录，不能回写运动规格制造循环引用。若有内容丢失，再由
+缩短修改若形成补拍或替代版，必须在 `视频提示词.md` 中标明版本类型、同一文件内的母版或补充
+`MOTION-...` 标题，并把每项原文要求对应到当前版本或说明去向。普通母版不为“没有版本关系”制造
+占位账目。补拍默认不替代母版；替代版只能提出替代请求，最终由审查结论直接指名保留哪一个标题，
+不能让两个版本互相声明对方才是当前版本。若有内容丢失，再由
 分镜或视频提示词技能决定保留其他镜头、拆镜、延长、删减或请求上游修改。
 
 ## 四、各环节证据问题
@@ -155,8 +154,8 @@
   `no-text` 删除参考像素？
 - 每张参考图的 `role`、可参考内容与不可照搬内容是否明确？构图、尺度或效果参考有没有
   改写本来不该由它决定的身份、内容、文字或状态？
-- 像素、文字、水印或裁切检查是否有准确的观察记录；没有时是否保持 `unverified`，
-  而不是从 JSON 引用或负面词推断已经看过输入参考图？
+- 像素、文字、水印或裁切检查是否有准确的观察记录；没有时是否明确写“未观察”，
+  而不是从文件引用或负面词推断已经看过输入参考图？
 - 定点修改是否写准确目标、`changes` 与 `preserve_set`？
 - 同一地点在同一时间/天气 state 下的各观察方向板，主光来源、冷暖主次、光比方向与实际
   灯具开关是否对齐（`IMG-10`）？不一致时是否有已记录的成因与对应 delta？逐板单独看

package/lib/drama/skills/short-drama-review/references/project-calibration.md

@@ -9,15 +9,13 @@
 - `generated_result`：某个准确提示词/规格版本、参考槽位集合和制作配置下的结果观察；它可以支持
   项目内校准，但不能自动变成跨项目、跨配置或跨制作方式的定律。
 
-两种记录都要写明被观察的媒体、观察方法、准确文本 refs、观察区域/时间段、限制与观察者。
-`generated_result` 还要绑定 `prompt_or_spec_refs`、每个稳定 `slot_id/order`、production profile
-与 `valid_only_for`。模板见核心的生产观察记录；审查只读取项目提供的记录，不在公开运行时找数据。
-`evidence_state: active` 只表示这份有界观察仍可作为证据使用，不表示内容被接受或质量通过；
-证据被撤回、被观察的媒体已经换过或来源无法复核时，不沿用该记录做校准，而是保留历史并另记失效原因。
-不要给观察套用创作产物的 `candidate/accepted` 状态。
-实际项目记录建议放在受保护的 `输入/production-observations.jsonl`（legacy 项目为
-`inputs/production-observations.jsonl`），由创作者或获授权观察者提供；它不属于任何 skill 的
-可发布产物，也不进入文本交付包。公共 `assets/production-observation.example.jsonl` 只是空白示例。
+两种记录都要写明被观察的媒体、观察方法、准确的文档标题引用、观察区域/时间段、限制与观察者。
+生成结果还要写明对应提示词或镜头标题、参考图顺序、制作形态/配置和结论适用范围。审查只读取
+项目提供的记录，不在公开运行时找数据。记录仍可使用只代表这份有界观察可复核，不表示创作内容
+已接受或质量通过；证据被撤回、媒体已经换过或来源无法复核时，不沿用它做校准，并写明失效原因。
+
+实际项目记录可以由创作者放在受保护的 `原始资料/生产观察.md`，也可以直接在当前请求中提供；它不属于
+五份单集创作文档，也不进入文本交付包。
 
 ## 选择有内容代表性的试跑
 

package/lib/drama/skills/short-drama-review/references/review-method.md

@@ -19,9 +19,9 @@
 
 ## Review scope
 
-Start from the current artifact files and accepted creator constraints. Prefer an uninvolved reviewer or isolated
-context when available; otherwise perform an honest self-check. The project CLI stores only a verdict, optional
-reviewer label and note. It does not authenticate reviewer identity or require runtime provenance.
+Start from the current creator-visible files and the constraints the creator has explicitly chosen. Prefer an
+uninvolved reviewer or isolated context when available; otherwise perform an honest self-check and say so in the
+review Markdown. A reviewer label is disclosure, not authenticated identity.
 
 If a target changes during review, reread that target before recording the verdict. Do not recursively invalidate
 unrelated findings.
@@ -30,11 +30,11 @@ unrelated findings.
 
 Mechanical examples:
 
-- invalid JSON/JSONL, missing or duplicate IDs, unresolved references;
+- missing or duplicate Markdown IDs, broken links or unresolved references;
 - unknown asset variants or contradictory camera flags;
 - explicit segments not matching their declared duration;
 - readable text conflicting with the accepted text policy;
-- owner writing outside its authority;
+- a stage document silently taking over facts owned by another document;
 - delivery containing private or unapproved material.
 
 Semantic examples:
@@ -51,7 +51,7 @@ Semantic examples:
 A useful finding contains:
 
 1. stable diagnostic/rule ID when one exists;
-2. project-relative target plus record, field, block or shot when useful;
+2. project-relative file plus heading ID, line number or shot when useful;
 3. bounded quotation or conflicting facts;
 4. audience, continuity or production impact;
 5. required outcome and preserve set, not ghostwritten replacement prose;
@@ -60,9 +60,8 @@ A useful finding contains:
 “The dialogue is weak” is invalid. A finding should identify the exact exchange, say what fails to change, and tell
 the write owner what outcome must be restored.
 
-A findings or verdict file declares each upstream snapshot once under `sources`, and every reference names that
-snapshot key plus the record. Those source references are archival review metadata, not lifecycle inputs and not proof
-of reviewer independence.
+The review Markdown cites the current file name, heading ID, line number or a necessary short quotation directly.
+It does not copy upstream snapshots, invent record IDs or create another version of the source material.
 
 ## Cross-layer synthesis
 

package/lib/drama/skills/short-drama-review/references/rubric-assets-prompts.md

@@ -26,32 +26,28 @@ creator-approved idealization or deliberate counter-casting remains a taste choi
 
 ### Voice direction (optional, `AST-07`–`AST-12`)
 
-Only reviewed when a project records `voice_direction`. Timbre is carried by a
-bound reference recording, not by prose: identity is the reference binding plus
-the accepted pronunciations, and the text alongside it exists to select or judge
-a candidate, never to stand in for one.
+Only reviewed when `视觉设定.md` records a voice direction. Timbre is carried by a
+named reference recording, not by prose: identity is the reference plus the
+creator's current pronunciation choices, and the text alongside it exists to
+select or judge a voice, never to stand in for one.
 
 Fail when:
 
 - a project has no reference and a paragraph of adjectives is standing in for
-  identity — that record must read `reference: null` and 待选型 instead;
+  identity — the voice section must say `待选型` instead;
 - a binding omits what it controls and what it must not, or lets the take's
   emotion, the recording space (reverb, mic distance) or background noise into
   identity (`AST-08`);
 - a claim about what is audible in a reference has no creator description and no
-  authorized listening observation, yet admission is not `unverified` (`AST-09`);
-- one proper noun appears with two accepted spellings anywhere in the 设定集
+  authorized listening observation, yet is written as established fact (`AST-09`);
+- one proper noun appears with two accepted spellings anywhere in `视觉设定.md`
   (`AST-10`) — this one is structural and blocks;
 - two characters designed together are bound to confusable references and no
   distinguishing trait names the nearest neighbour (`AST-11`);
 - a selection criterion is an emotion word, carries no counter-example, or the
   list has grown past a handful (`AST-12`);
 - reference audio bytes, a provider parameter, a model name, a task field or a
-  URL appear in the 设定集 or the delivery package.
-
-The rendered `voice-casting.md` is a cache. A finding against it is a finding
-against the accepted record it projects, routed to assets — never a request to
-hand-edit the derived text.
+  URL appear in `视觉设定.md` or the delivery package.
 
 ### Location / View
 
@@ -107,7 +103,7 @@ apply type-specific criteria:
 - prop has no scale or text state;
 - negative constraints contradict the required visible fact;
 - edit request says “make better” without target/change/preserve;
-- rendered Markdown differs from accepted structured spec;
+- `图片提示词.md` contradicts the current identity, state or text policy in `视觉设定.md`;
 - private URL, source ID, provider task field, or operator complaint leaks in.
 - “use the whole reference” does not say what may or may not be copied.
 

package/lib/drama/skills/short-drama-review/references/rubric-story-script.md

@@ -24,9 +24,30 @@
 - What pressure is active at the opening?
 - What does the protagonist want now, and what resists it?
 - Which choice/action causes the directional turn?
+- If the episode frames that turn as a consequential choice, what live value does each
+  executable direction protect, and what cost is newly caused by the action (`SCR-13`)?
+  If it is an ordinary decision or single-path pursuit, leave this test inactive rather
+  than manufacturing a dilemma.
+- Conditional does not mean cursory: when the episode itself foregrounds a choice,
+  evidence carrier, deadline, or rule, does resistance, action, and consequence dramatize
+  it, rather than merely naming it in dialogue?
+- Could a viewer identify those stakes from the screenplay alone, without access to
+  the upstream brief or episode card?
+- Do explicit brief facts, must/forbid constraints, genre contract, and required exit state
+  outrank craft defaults, or did the screenplay invent precision, records, resources,
+  procedures, relationships, or mechanisms merely to display a rule?
+- When a choice cost or deadline is essential, was it perceptible before the decision,
+  or invented at decision time by a convenient new condition?
 - What part of the promised experience is delivered before the outgoing hook?
 - What exact state enters the next episode?
 - Before the outgoing hook, what local dramatic result has already landed?
+- Which behavior, relationship history, line, silence, spatial choice, or object makes the
+  protagonist's private reason legible? Do not require a recurring object when another
+  carrier already does the work.
+- Does the ending fulfill the episode's viewing contract through consequence, relationship,
+  irony, afterimage, atmosphere, or intentional openness? A new external event is optional.
+- If the ending declares a path closed or a consequence irreversible, do later beats
+  accidentally contradict that claim without presenting an intentional new change?
 - Whose choice caused that result (`STY-13`)? If it arrived by outside force, cite the
   protagonist's earlier action that made it arrive now, and what they did with it.
   A protagonist who only endures until rescue is this episode's audience, not its lead.
@@ -78,6 +99,18 @@ What is reportable:
 - Do world truth, character beliefs, and audience knowledge remain separate?
 - For each evidence carrier, what claim does it directly support, and which identity,
   cause, motive, or mechanism remains an unresolved inference (`STY-15`)?
+- When a major belief change hinges on contested evidence, is the response limited to
+  what was proved, or does the story intentionally preserve/delay uncertainty (`SCR-14`)?
+  Leave this test inactive for uncontested facts, comic misunderstanding, subjective
+  narration, or clues whose ambiguity is the intended effect.
+- When contested evidence is a primary episode engine, does at least one visible state
+  change alter which explanations remain live or alter the next action, rather than
+  leaving every increment to verbal report? Photographing, bagging, numbering, or logging
+  is not a dramatic turn by itself. Once the required inference changes, does testing stop
+  unless another live counter-explanation would genuinely change the next action?
+- If a proof claim depends on continuity such as connection, sealing, position, time, or
+  lack of contact, did preceding action preserve that exact property? A continuity label
+  may carry forward a shown state; it cannot prove that an unseen event or contact never occurred.
 - Does active serial memory preserve character/relationship state, information
   permissions, setup debt, rhythm direction, and the exact physical handoff?
 - Do external pressure and emotional load rise, fall, or diverge for a reason?
@@ -88,16 +121,20 @@ dialogue quota.
 
 ## Scene test
 
-For each scene ask:
+For a scene organized around active pursuit or conflict, ask:
 
 1. Why must it exist?
 2. Whose agenda organizes it?
 3. What force opposes that agenda?
-4. What becomes visible, known, decided, owned, risked, or irreversible?
+4. What traceable fact, leverage change, cost, authority, or choice makes the prior
+   strategy fail? An opponent merely becoming silent or leaving is not enough.
 5. What exit state pressures the next scene?
 
-A quiet scene can pass when pressure and change are legible. A loud scene can fail
-when nothing changes.
+A quiet scene can pass when pressure and change are legible. Atmospheric, ritual,
+montage, transition, and consequence-processing scenes may instead justify their
+function through a necessary change in knowledge, relationship, pressure, rhythm,
+or production state; do not invent an opponent or strategy failure merely to make
+them fit this checklist. A loud scene can fail when nothing changes.
 
 ## Action and production meaning
 
@@ -107,6 +144,42 @@ when nothing changes.
 - Are exact on-screen text, prop text, SFX, VO/OS, and transitions tagged?
 - Does prose avoid camera/prompt boilerplate while retaining production-critical
   facts?
+- Do supporting characters who receive substantial dramatic emphasis have a goal, judgment,
+  or strategy of their own? Incidental, transactional, choral, and environmental roles need
+  not all alter the main plot.
+- Does a central participant who supplies the main leverage, opposition, or cost remain
+  strategically present through the turn and response, rather than becoming a passive prop
+  once the protagonist acts?
+- If that participant's leverage disappears, what already-established action, spatial fact,
+  authority, relationship, or choice made it disappear? Do not infer neutralization merely
+  from the protagonist completing one step.
+- When a literal precise deadline is foregrounded and audience-auditable, does its action
+  chain fit, or does the screenplay make compression, changed method, changed objective,
+  or failure legible (`SCR-16`)? Qualitative urgency must not be upgraded into invented
+  minutes, timestamps, notifications, or records. Do not apply a real-time test to montage,
+  ellipsis, subjective time, or declared stylization.
+- When the brief defines a limited number of attempts, turns, breaths, beats, or other units,
+  does each unit end with its required visible state (`SCR-17`)? Labels, counts, requests,
+  authorization, preparation, and cleanup after the boundary do not substitute for completion;
+  an intentional failure or partial result may count when it is legible at that boundary.
+- When exact timestamps share one literal continuity, are they mutually consistent?
+- When the current date is necessary to a conclusion, is it supported by a current source?
+- Does a compressed process retain only the steps that change strategy, relationship,
+  risk, or result, instead of listing interchangeable operations?
+- When multiple carriers repeat one pressure or fact, does each add rhythm, viewpoint,
+  irony, misdirection, or consequence? If not, which one is redundant?
+- Does a solution use established resources and still confront the core obstacle, rather
+  than erase it with a newly invented convenience?
+- Even when a resource is established, does it change the problem without conveniently
+  performing the character's hardest dramatic work for them?
+- Does an outside response increase or transform pressure in a way grounded in the work's
+  established world, rather than suddenly forgiving, rewarding, or rescuing the character
+  to make the ending easy?
+- After a mechanism becomes visually clear, does dialogue change the relationship or
+  narrow the claim instead of explaining the same mechanism again?
+- When the brief gives a target duration but the project has no pacing rates, has the
+  writer still performed a real-time read/action pass and removed obviously excessive
+  repeated verification, date exposition, or equivalent closing beats?
 
 ## Dialogue
 
@@ -162,3 +235,30 @@ the benefit is not, and the mark exists precisely so the strong version can stay
 - generic emotion adjectives replace visible performance;
 - every character explains the plot in the same voice;
 - downstream production requirement was never marked in screenplay truth.
+- a redundant `[连续性]` tag repeats an exit state already explicit in the final action;
+- a story-critical ending state appears without a prior transition;
+- the script uses atmosphere, silence, or a black frame to avoid landing a result the episode
+  promised, rather than as an intentional ending form;
+- a beat is sold as a consequential choice after one direction has already become valueless
+  or impossible (`SCR-13`);
+- contested evidence produces a broader conclusion than the evidence or intentionally
+  incomplete verification supports (`SCR-14`);
+- a claimed proof relies on a continuity property the preceding action already destroyed,
+  or on a continuity label asserting an unseen negative event;
+- a local payoff erases its established residue or replaces meaning with a slogan (`SCR-15`);
+- a cost framed as central pressure automatically resets at success, leaving no material
+  effect on ability, body, resource, relationship, or next action;
+- a central participant supplies the opening leverage or cost but becomes a passive prop
+  through the decisive action;
+- the core opposing force disappears only because its holder becomes silent, stops acting,
+  or leaves, without a traceable loss of leverage, accepted cost, or changed strategy;
+- a literal, audience-auditable deadline succeeds only through unexplained speed, or
+  qualitative urgency is upgraded into invented precise timing (`SCR-16`);
+- a limited unit is counted before its required state completes, with the completion moved
+  outside the boundary (`SCR-17`);
+- a newly invented resource, permission, or ability removes the central obstacle;
+- a limited result is renamed as a broader success or truth than the scene demonstrated;
+- repeated carriers restate one pressure without adding viewpoint, rhythm, irony, or consequence;
+- a second same-direction decision, closing line, or maxim merely translates a change,
+  punchline, or metaphor that the preceding action already completed;
+- post-result action unintentionally contradicts a consequence the screenplay called irreversible.

package/lib/drama/skills/short-drama-review/references/rubric-visual-motion.md

@@ -23,7 +23,7 @@
   genuinely differ — in knowledge timing, audience alignment, performance space,
   strongest image, landing, losses, or production fit?
 - Does the formal plan bind the approach the creator selected, rather than the first draft?
-- When a `scene_visual_plan` exists: do its start/end audience positions, spatial
+- When a scene visual plan was used: do its start/end audience positions, spatial
   pressure, camera rhythm, reaction landing, and sound movement carry **one** dramatic turn?
 - Does that plan stay clear of owning shot boundaries? (Ordinary scenes need no plan
   merely to satisfy a form.)
@@ -34,7 +34,7 @@
 - Are Location/View, axis, screen direction, eyelines, entrances, positions,
   hands, and props coherent?
 - Are exact asset variants bound?
-- Does `audience_visibility` expose every fact this shot must carry while protecting
+- Does the shot expose every fact it must carry while protecting
   facts the source withholds until a later action or cut?
 - Do crop, occlusion, focus, back view, and offscreen space serve that information
   permission rather than accidentally reveal or conceal it?
@@ -42,7 +42,7 @@
 ## Frozen keyframe
 
 - Can all described facts exist in one still instant?
-- Does it project the authoritative shot start boundary?
+- Does it project the start state written for this shot?
 - Are focal hierarchy, composition, camera/lens, geography, pose/gaze/hands/prop,
   expression, and light legible?
 - Does it avoid ordered actions, performance arcs, camera moves, or transforming
@@ -56,15 +56,13 @@
 - In multi-character motion: do the actors who actually change have distinct,
   readable triggers, choices, leaks, or landings — as this shot needs, not one
   identical arc per actor?
-- Is `attention_handoffs` used only where attention truly transfers, rather than for
+- Is attention handed off only where it truly transfers, rather than for
   synchronized reaction?
-- Does the derived text-readiness view cite accepted inputs and real blocking gaps?
-- Does it avoid any claim about generated media quality, and avoid persisting a second
-  readiness truth inside each motion record?
+- Does any text-readiness claim cite the current creator-visible inputs and a real blocking gap?
+- Does it avoid any claim about generated media quality or create a second readiness truth?
 - Is camera behavior coherent and motivated?
 - Are environment motion, dialogue, SFX, and audio included only when relevant?
-- Does the end report match storyboard `end_boundary` and feed no unauthorized
-  write into the next shot?
+- Does the described end match the storyboard's written end state without rewriting the next shot?
 - When a reference frame carries appearance/composition, does motion prose avoid
   dumping the full visual 设定集?
 - Does every claim about text-bearing reference pixels cite a creator/reference-owner
@@ -78,12 +76,10 @@
 
 For a pickup or alternate, ask these separately:
 
-- Does `coverage_scope` bind each exact source obligation?
-- Is every obligation mapped to a current motion field or an explicit disposition?
-- Are the exact master/supplement record IDs named?
-- Is supersession only *requested* here? Only a downstream verdict may bind fixed
-  alternate/master records and decide it — see the
-  [supersession decision example](../assets/supersession-decision.example.json).
+- Does the pickup/alternate name its master by visible `MOTION-...` heading?
+- Is every source obligation assigned to the master, this version, another named version or a requested storyboard revision?
+- Are the changed items and the items that must remain unchanged explicit?
+- Is replacement only requested here? The review Markdown decides whether the master remains primary or the alternate replaces it.
 
 For music, ask these separately (`VID-14`):
 
@@ -136,7 +132,7 @@ ellipsis, dream, or deliberate disorientation.
 - every emotional beat uses the same close-up/push template;
 - provider batching is mistaken for editorial shot structure.
 - a narrowed pickup silently replaces the master and drops dialogue, reaction,
-  reveal, end-boundary, or accepted-directive obligations.
+  reveal, end-state, or creator-directive obligations.
 
 ## Production-risk and authorized-observation checklist (REV-08)
 
@@ -145,9 +141,9 @@ ellipsis, dream, or deliberate disorientation.
 并把该记录作为外部证据引用。没有观察记录时保持结果未知，不从任务成功、结果地址或提示词
 存在推断成片质量。
 
-需要项目校准时，先区分 `input_reference` 与 `generated_result`。后一种观察只有在绑定准确
-prompt/spec 记录、稳定 reference slots、production profile/config、观察方法和限制时才可引用；
-finding 同时给出最小 `change_set` 与 `preserve_set`，并保持结论只在该项目和版本条件下有效。
+需要项目校准时，先区分输入参考与生成结果。后一种观察只有在绑定准确的提示词/镜头标题、参考顺序、
+制作形态/配置、观察方法和限制时才可引用；finding 同时给出最小修改项与保持项，并保持结论只在该项目
+和版本条件下有效。
 
 短剧生产中需要防范的文字风险或获授权观察包括：
 

package/lib/drama/skills/short-drama-review/references/stage-contract.md

@@ -1,68 +1,9 @@
 # 审查阶段契约
 
-## 目录
+本阶段只拥有审查结论与修订要求，不改写 owner 来源。需要落盘时使用创作者可读 Markdown，引用当前
+文件名、标题 ID、行号或短引文；不建立 JSON/JSONL、来源快照、哈希或接受状态。
 
-- [独立运行与项目集成](#独立运行与项目集成)
-- [所有权边界](#所有权边界)
-- [制作形态需要什么](#制作形态需要什么)
-- [参考媒体与补拍](#参考媒体与补拍)
-- [本阶段规则](#本阶段规则)
-
-本文件是本技能的自包含契约：预检、所有权、形态输入与规则表都在这里，
-不需要读取其他技能的文件。
-
-## 独立运行与项目集成
-
-本技能可以单独安装并运行；下面几条说明项目工具存在时怎样集成。
-
-1. **读取直接输入**：只读取用户明确提供或当前任务实际需要的文件，不批量加载整个项目。
-2. **可选项目集成**：若存在 `short-drama.json` 且 core 项目工具可用，可以运行
-   `python3 <core>/scripts/project_tool.py status <project>`，使用返回的目录布局和语言设置；
-   core 不可用时，直接基于已提供输入产出本阶段文件。
-3. **可选发布生命周期**：项目工具可用时，用 `publish` 原子发布并用 `--input <path>`
-   声明直接输入；`accept`、`review` 与 `package` 继续承担确认、复核与交付。
-4. **保持职责分离**：创作者确认、内容修订和复核是不同动作；reviewer 提修改要求，负责人改文件。
-
-## 所有权边界
-
-- **本阶段拥有**：审查问题、审查结论与修订请求；证据指向被审查的产物与其中的准确记录。
-- **本阶段继承**：精确的 artifact 引用、已接受限制与创作者覆盖。
-- **本阶段不越权**：不修改负责人的来源文件，不用个人偏好替代证据，也不把 owner 修订动作
-  冒充审查动作。Self-review may record any evidence-supported verdict when it is labeled honestly.
-  Prefer an uninvolved reviewer to reduce confirmation bias, but never retry isolation as a completion strategy.
-
-## 制作形态需要什么
-
-视觉风格不是贴在提示词前面的标签。创作者已接受的视觉方向与制作形态由项目层决定并传入，
-**本技能不加载形态卡，也不自行选择形态**；本节只说明本阶段需要形态回答什么、以及拿到
-答案后投影成哪些字段。
-
-形态决定属于 `craft_default`：创作者说明理由即可覆盖。形态不能创造新的
-`structural_invariant`，也不能改写身份、地理、持物归属与可读文字政策。审查者不得单凭
-形态偏好阻断交付。
-
-不要用“加一句风格前缀”处理形态差异。前缀只改变检索标签；形态改变的是**必须出现和
-可以省略的字段**，只有后者会被执行，也只有后者能被审查。
-
-本阶段对形态只问一件事：**叙事职责是否真的落到了本形态可执行的字段**——形、层、
-材质、光、动作或声音。
-
-检查时不问“有没有写风格名”，而问：连续性必带项是否按本形态取舍、而不是照抄别的形态；
-同一决定是否只由一个负责人写入。已选择的形态或单镜预算不可执行时，回到对应负责人请求
-批准，不把拆镜或换形态默认为已经授权的替代。
-
-## 参考媒体与补拍
-
-- **参考图能决定什么要逐张写明**：每张参考的用途、可以照搬什么、不可以照搬什么。身份参考
-  不自动决定构图；构图、尺度或效果参考不自动带入图中人物、服装、文字、道具与故事状态。
-- **像素主张需要证据**：关于参考图上可见内容（尤其文字、水印、标牌、界面）的断言，必须
-  来自创作者/参考图权利人的可核对说明，或运行环境获授权后形成的输入参考观察记录，并绑定
-  被检查的字节。两者都没有时保持 `unverified`，负面提示词不能代替证据。
-- **观众揭示时机**：某一事实何时可被观众看到，由已接受的可见性决定绑定其来源、载体、
-  权限、触发与保护方式。构图既不能提前泄露该事实，也不能遮掉本环节必须传达的载体。
-- **母版、补拍与替代**：补拍默认只补充、不替代母版。普通母版不增加版本范围字段；只有
-  补拍/替代版才声明 `pickup | alternate`，用同一文件内稳定的记录 ID 说明母版与补充关系，并把每项原文要求对应到当前字段或说明
-  去向。只有下游审查结论才能批准替代，不得回写形成循环引用。
+审查可以由独立 reviewer 或明确标注的自检完成。媒体不可见时保持未知；外部生产仍需要自己的显式确认。
 
 ## 本阶段规则
 
@@ -71,7 +12,7 @@
 | ID | Class | Knowledge |
 |---|---|---|
 | REV-01 | structural_invariant | Run mechanical checks before spending creative review attention. |
-| REV-02 | structural_invariant | A finding binds its target through the file's `sources` declaration (`src` plus record), and includes evidence, impact, required fix, owner, severity, and status. |
+| REV-02 | structural_invariant | A finding names a visible file and heading/shot/prompt ID, and includes evidence, impact, required fix, owner, severity and status. |
 | REV-03 | reviewed_invariant | Semantic invention cites the source fact and conflicting downstream fact. |
 | REV-04 | craft_default | Prefer a reviewer who did not author the current targets; disclose self-review, and keep reviewer findings separate from owner edits. |
 | REV-05 | craft_default | Diagnose repeated structure or generic language with location and impact; do not label output merely "AI-ish". |