target_type: generation_context
中文名: 生成上下文
domain: ai_context
scope: agent
本体分组: 配套
状态: 启用
判据: AI 上下文组装与输出合同的结构模具,运行时对象、用户不可见
实例落点: 以 read-context 的 JSON 上下文与 Markdown manifest 回显落 works/*/评审/,不建知识卡
严格合同:
  版本:
    WriterContext: writer-context-v1
    WriterOutput: writer-output-v1
    RetrievalPlan: writer-retrieval-plan-v1
    RetrievalManifest: writer-retrieval-manifest-v1
  规范化: UTF-8、Unicode NFC、LF 换行、对象键排序、无额外空白
  身份规则: runId、generatedAt、timestamp、executionNode 不参与检索与上下文身份
  未知字段: 拒绝
  WriterContext必填字段:
    - schemaVersion
    - runId
    - attempt
    - mode
    - purpose
    - qualityPolicyVersion
    - workId
    - targetChapter
    - asOf
    - contextSnapshot
    - sourceVersion
    - authorizationSnapshot
    - sourceStatus
    - retrievalPlan
    - retrievalManifest
    - fineOutline
    - narrativeState
    - factEvidence
    - proseEvidence
    - patternReferences
    - evidenceCoverage
    - outputContract
    - tokenBudget
    - omittedSources
    - acceptanceEligible
  WriterContext可选字段:
    evidenceStrategy:
      枚举: [production_dual_evidence, historical_prose_only, card_index_only, card_index_plus_prose]
      约束: 生产固定 production_dual_evidence；card_index_only 仅诊断可跳过连续前四章基线
    indexHints:
      每项严格字段: [cardId, name, type, content, sourceId, sourceVersion, asOf]
      来源: retrieval_result.indexHints,覆盖同批检索命中的全部冻结卡,不以 sourceRefs 是否存在为准
      约束: 仅 mode=diagnostic_only、purpose 为 evaluation/diagnostic、acceptanceEligible=false；生产硬拒绝；asOf 不得越过上下文冻结线
  WriterOutput必填字段:
    - schemaVersion
    - runId
    - attempt
    - mode
    - qualityPolicyVersion
    - contextSnapshotId
    - contextSnapshotSha256
    - candidateVersion
    - candidateSha256
    - acceptanceEligible
    - candidateBody
    - claimLedger
    - evidenceRequests
    - newSettingDeclarations
    - selfCheck
  双证据:
    factEvidence来源: [historical_prose, formal_setting, canonical_state, fine_outline_declared_new]
    proseEvidence来源: 历史 Canonical 原文,必须带章号、块、字符区间与内容哈希
    indexHints用途: 只用于诊断卡索引替代效应,卡负责定位原文而不替代原文事实,不是事实证据,claimLedger不得引用
  接受边界: evaluation、diagnostic、diagnostic_only 一律 acceptanceEligible=false
  稳定排序: score DESC, sourceVersion ASC, sourceId ASC, sourceOffset ASC
实现校验器: muse/lifecycle/context/skills/准备任务上下文/scripts/writer_contract.py