@c4a/context-cli 0.7.8 → 0.7.9

package/indexers/bundles/context-code-indexer/templates/articles/q05.md

@@ -2,6 +2,18 @@
 id: context.article.q05
 kind: procedure
 media-type: text/markdown
+program:
+  article: q05
+  policies:
+    - compact
+    - standard
+    - expanded
+  sections:
+    requirements: 数据需求
+    preparation: 准备入口
+    isolation: 环境和隔离
+    lifecycle: 数据生命周期
+    verification: 验证和清理
 ---
 
 # Q05 测试数据与环境

package/indexers/bundles/context-code-indexer/templates/articles/q06.md

@@ -2,6 +2,18 @@
 id: context.article.q06
 kind: procedure
 media-type: text/markdown
+program:
+  article: q06
+  policies:
+    - compact
+    - standard
+    - expanded
+  sections:
+    tasks: 任务到工具
+    prerequisites: 接入前提
+    operations: 常用操作
+    results: 结果解释
+    references: 代码与文档入口
 ---
 
 # Q06 工具与排障工具箱

package/indexers/bundles/context-code-indexer/templates/articles/s01.md

@@ -2,6 +2,20 @@
 id: context.article.s01
 kind: procedure
 media-type: text/markdown
+program:
+  article: s01
+  policies:
+    - compact
+    - standard
+    - expanded
+  sections:
+    scope: 服务定位
+    startup: 接入和启动
+    architecture: 架构分层
+    capabilities: 核心能力与接口
+    dependencies: 模型和依赖摘要
+    index: 知识索引
+    sources: 源码位置
 ---
 
 # S01 服务概览

package/indexers/bundles/context-code-indexer/templates/articles/s02.md

@@ -2,6 +2,19 @@
 id: context.article.s02
 kind: procedure
 media-type: text/markdown
+program:
+  article: s02
+  policies:
+    - compact
+    - standard
+    - expanded
+  sections:
+    scope: 协议与范围
+    catalog: 能力与入口表
+    authority: 权威契约
+    implementation: 调用方与实现
+    references: 详情导航
+  contract_table: contract_api
 ---
 
 # S02 API 目录

package/indexers/bundles/context-code-indexer/templates/articles/s03.md

@@ -2,6 +2,21 @@
 id: context.article.s03
 kind: procedure
 media-type: text/markdown
+program:
+  article: s03
+  policies:
+    - compact
+    - standard
+    - expanded
+  sections:
+    entry: 用途与入口
+    validation: 请求和边界校验
+    steps: 处理步骤
+    downstream: 数据与下游操作
+    response: 响应与错误
+    concurrency: 并发与幂等
+    references: 调用方与入口
+  contract_table: contract_api
 ---
 
 # S03 API／操作详情

package/indexers/bundles/context-code-indexer/templates/articles/s04.md

@@ -2,6 +2,20 @@
 id: context.article.s04
 kind: procedure
 media-type: text/markdown
+program:
+  article: s04
+  policies:
+    - compact
+    - standard
+    - expanded
+  sections:
+    scope: 领域范围
+    catalog: 实体与概念表
+    entities: 核心实体
+    relations: 已证实关系
+    states: 状态与转移
+    rules: 业务约束
+    references: 实现与资料
 ---
 
 # S04 领域模型

package/indexers/bundles/context-code-indexer/templates/articles/s05.md

@@ -2,6 +2,19 @@
 id: context.article.s05
 kind: procedure
 media-type: text/markdown
+program:
+  article: s05
+  policies:
+    - compact
+    - standard
+    - expanded
+  sections:
+    scope: 存储职责
+    models: 表与持久化对象
+    queries: 查询和索引
+    cache: 缓存与锁
+    consistency: 事务与一致性
+    references: 读写入口
 ---
 
 # S05 数据模型

package/indexers/bundles/context-code-indexer/templates/articles/s06.md

@@ -2,6 +2,19 @@
 id: context.article.s06
 kind: procedure
 media-type: text/markdown
+program:
+  article: s06
+  policies:
+    - compact
+    - standard
+    - expanded
+  sections:
+    overview: 依赖概览
+    requests: RPC 与 HTTP
+    events: 事件与任务
+    storage: 存储及配置服务
+    initialization: 初始化与选择
+    failures: 故障边界和下一步
 ---
 
 # S06 外部依赖

package/indexers/bundles/context-code-indexer/templates/articles/s07.md

@@ -2,6 +2,20 @@
 id: context.article.s07
 kind: procedure
 media-type: text/markdown
+program:
+  article: s07
+  policies:
+    - compact
+    - standard
+    - expanded
+  sections:
+    triggers: 职责与触发源
+    registration: 注册与订阅
+    payload: Payload 与过滤
+    processing: 处理链路
+    retry: 重试幂等与并发
+    reconciliation: 检查点补偿与对账
+    operations: 运行和观测入口
 ---
 
 # S07 事件、任务与对账

package/indexers/bundles/context-code-indexer/templates/contract-source.md

@@ -71,3 +71,52 @@ must contain exact contract identities and source locators, not just filenames.
 
 Revise or stop when authority cannot be distinguished from a generated copy,
 imports or versions are unresolved, or compatibility claims are not declared.
+
+## Overview maps for a selected contract family
+
+When the user chooses a bounded overview, organize the page as scope/version,
+contract-family map, representative operations, active consumers, lookup procedure,
+change/generation entrypoints and unread boundaries. Separate API entry schemas,
+domain contracts, runtime RPC/message boundaries and common models when the source
+actually distinguishes them. Do not force these layers onto an unrelated schema.
+
+A useful family row contains purpose, authoritative directory/file, known consumer
+and the next lookup. A representative operation row can connect reader action,
+external operation identity, schema Service/Method and implementation locator;
+mark an unknown hop as a question, never a proven call. Count only with a recorded
+file-set boundary or reproducible inventory; a few examples cannot establish
+complete coverage or a total operation count. Cross-file imports needed to explain
+a selected type are supporting evidence, not automatic new article subjects.
+
+For large groups, directory routes with scoped searches are preferable to thousands
+of file rows. Give an actual lookup example and what to do when no match is found.
+A short article does not imply cheap extraction: the confirmed overview treatment
+must first be expressible in the actual source/production configuration. This
+writing template does not change parser depth. If the current contract profile
+would still prepare the entire source, resolve that scope before proceeding;
+do not silently select another profile or claim deferred parsing already happened.
+
+## Prefer linked definitions over schema transcription
+
+For entry-first knowledge, avoid exhaustive IDL reading and rewriting. Start with
+consumer/generator configuration and known operation identities; inspect only the
+definitions needed for the actual claim. A file locator does not prove its fields
+or runtime use. Keep complete schema bodies out of Markdown unless a short excerpt
+is necessary to explain the reader's question. Do not modify authoritative IDL.
+
+A source-backed attachment is useful only when an article explicitly needs and
+links that exact definition. Repository presence alone never selects an asset.
+If a supported source-resource projection exists, use its registered source,
+revision, relative path and byte digest; never copy the entire IDL tree or hand-write
+knowledge/assets. Otherwise retain a versioned source locator and state that the
+offline attachment is unavailable. The existing document-attachment mechanism is
+not proof that repository files have been registered as source assets.
+
+An attached IDL remains source evidence, not a second authoritative contract or
+an instruction to create another article. Include dependencies are added only
+when needed for the documented use; distinguish a readable excerpt from a complete,
+compilable schema bundle. Do not claim the attachment compiles unless verified.
+Source byte changes must invalidate the affected resource and dependent evidence;
+unchanged bytes can reuse the resource. A repository revision change alone does
+not prove a changed definition, and source bytes changing do not prove a breaking
+API change. Preserve source identity even when identical bytes share storage.

package/indexers/bundles/context-code-indexer/templates/derived-generated-source.md

@@ -115,3 +115,18 @@ material-question proposal until the missing authority is provided.
 - the plan duplicates upstream reference material without consumer value;
 - legacy replacement or deprecation claims are inferred rather than evidenced;
 - generated symbols dominate projected pages.
+
+## Compact collection map
+
+For a confirmed homogeneous collection, group by observed purpose and consumers,
+not one page per generated file. Explain the source of truth, local output boundary,
+representative shapes, scoped lookup, regeneration and what remains unread. Count
+physical copies separately from unique contracts: the same model copied into several
+applications is not several independent interfaces. An import path containing an
+upstream repository name does not prove an additional checkout or runtime call.
+
+A generator marker is evidence of provenance, not proof that the whole tree is
+irrelevant. Preserve the supported consumer surface and maintained overlays.
+Handwritten homogeneous handlers/configurations use their own semantic profile;
+do not call them generated just to compress their article output. The same map
+style can be used without changing provenance or pretending all files were read.

package/indexers/bundles/context-code-indexer/templates/monorepo-container.md

@@ -122,3 +122,12 @@ but should not override declared workspace ownership or package boundaries.
 - child ownership or source-of-truth boundaries are ambiguous;
 - generated/cache/vendor directories dominate projected output;
 - dependencies are inferred solely from names without manifest or graph proof.
+
+## Uneven depth without losing navigation
+
+Give important modules a concrete responsibility and first source entry; group
+less central modules into a categorized directory map with lookup instructions.
+State which were inspected deeply and which only have inventory/manifest evidence.
+Do not force all modules to have equally long pages or fabricate handler, DAO,
+configuration or test directories from framework conventions. Keep this shared
+map as the topology owner; child articles explain their differences and link back.