@c4a/context 0.7.4 → 0.7.5

package/README.md

@@ -54,8 +54,10 @@ export default defineProject({
 ```
 
 The Context lifecycle discovers or updates `src/indexers.yaml`, runs the
-selected Provider, presents readable Candidate pages for Review, writes only
-approved knowledge, and then builds declared packages.
+selected Provider in bounded batches of independently recoverable semantic
+tasks, presents readable Candidate pages for Review, writes only approved
+knowledge, and then builds declared packages. Batch keys and runtime timing
+never enter knowledge identity or package output.
 
 ## Public surface
 
@@ -83,8 +85,8 @@ Approved pages live under `knowledge/<collection>/`. Paths and filenames are
 reader-oriented, for example:
 
 ```text
-knowledge/codeindex/tux-web/avatar.md
-knowledge/architecture/tux-official-docs/react-lynx-input-fields.md
+knowledge/codeindex/ui-kit/avatar.md
+knowledge/architecture/product-guides/component-input-fields.md
 ```
 
 Workspace pages keep only metadata required to rebuild or update knowledge.
@@ -111,4 +113,3 @@ build. Source registries, `src/index.ts`, `src/indexers.yaml`, approved
 - [Indexer Provider Protocol](./docs/reference/indexer-provider-protocol.md)
 - [Package Outputs](./docs/guides/package-outputs.md)
 - [Package Templates](./docs/reference/package-templates.md)
-

package/README.zh-CN.md

@@ -52,8 +52,9 @@ export default defineProject({
 });
 ```
 
-Context 生命周期负责发现或更新 `src/indexers.yaml`、运行选中的 Provider、展示可读
-Candidate 供审核、只写入批准后的知识，最后构建声明的知识包。
+Context 生命周期负责发现或更新 `src/indexers.yaml`，以有界批次运行彼此独立、可恢复
+的语义任务，展示可读 Candidate 供审核，只写入批准后的知识，最后构建声明的知识包。
+批次标识和运行耗时不会进入知识身份或知识包产物。
 
 ## 主要 API
 
@@ -78,8 +79,8 @@ Indexer Provider 的实现依赖，工作区不再把它们包装成项目阶段
 批准后的知识位于 `knowledge/<collection>/`，目录和文件名面向人阅读，例如：
 
 ```text
-knowledge/codeindex/tux-web/avatar.md
-knowledge/architecture/tux-official-docs/react-lynx-input-fields.md
+knowledge/codeindex/ui-kit/avatar.md
+knowledge/architecture/product-guides/component-input-fields.md
 ```
 
 工作区页面只保留后续重建或更新所需的元数据。`dist/` 中的知识包页面使用更小的
@@ -104,4 +105,3 @@ knowledge/architecture/tux-official-docs/react-lynx-input-fields.md
 - [Indexer Provider 协议](./docs/reference/indexer-provider-protocol.md)
 - [知识包输出](./docs/guides/package-outputs.md)
 - [知识包模板](./docs/reference/package-templates.md)
-

package/docs/guides/agent-guide.md

@@ -40,11 +40,20 @@ Skill identities and semantic Indexer entries, and let the CLI perform routing,
 resolution, staging, validation, and atomic registry apply. External resolver
 results and non-allowlisted program decisions resume through subsequent
 `complete-current` Routes; do not invoke the low-level Provider commands.
-For Partition, Author, and Composer steps, read the Route-selected instructions
-and Authorized Workset View, return only the compact semantic value requested
-by the current schema, and submit it with the Route's single
-`context action complete-current` command. Do not create a helper script or
-construct internal Result, digest, receipt, Fact, or evidence-binding objects.
+For Partition and Author steps, one Route may contain several independent
+`tasks`. Read the shared instructions once, read each task's Authorized Workset
+View, and return one `results[]` item for every task key in that batch. Submit
+the whole batch with the Route's single `context action complete-current`
+command; a successful completion already carries the next prepared batch or
+the next lifecycle boundary. Do not materialize instructions or Views with
+separate commands, create a helper script, or construct internal Result,
+digest, receipt, Fact, or evidence-binding objects.
+
+The batch is only a transport boundary. Keep every task's semantic answer,
+failure and retry independent, and do not combine unrelated Subjects merely
+because they arrived together. Partition Views intentionally emphasize public
+anchors and compact file context; Author Views add the source-backed supporting
+facts needed for reader content.
 
 Parser packages are Provider internals. Do not expose parser choice as an
 extra user workflow unless it changes coverage or requires executable code the
@@ -68,6 +77,7 @@ outline after all Partition shards converge; the second checks the final
 reader-facing Candidate set. Ordinary mode presents both to the user. Fully
 managed mode lets the Agent resolve both with current-conversation authority.
 A destructive or ambiguous layout change is separate and always human-only.
+Intermediate execution batches never create additional user approvals.
 
 ## Quality bar
 

package/docs/guides/code-indexer-skill-authoring.md

@@ -105,6 +105,20 @@ rules, metric operators and thresholds.
     instructions append → one template override → program extension →
     restricted replace. Document the proof and exit condition at every step;
     see [Provider selection and customization](./indexer-provider-and-customization.md).
+24. **Batch neutrality.** Write instructions for one semantic task and accept
+    that Context may transport several independent tasks in one Agent step.
+    Never derive identity, ordering, ownership or evidence scope from a task
+    key or batch position. Partition should decide consumer-facing ownership
+    from public anchors and unresolved material; detailed supporting Facts are
+    consumed in the bounded Author View rather than copied into every
+    Partition decision.
+
+For behavioral explanations, the Author View also supplies `source-text`
+items with the authorized source lines. Each merged range links to existing
+source-span dependency nodes through `source_span_refs`; use those nodes for
+evidence bindings. These process-local snippets are reading material, not new
+Facts or reader-page metadata. Do not reopen the repository or infer behavior
+from a locator alone when the supplied lines do not establish it.
 
 ## Result and composition rules
 

package/docs/guides/indexer-provider-and-customization.md

@@ -12,27 +12,38 @@ authority. A Provider-only project does not create `src/indexer/`.
 
 ## Selection flow
 
+Follow `workflow.current` from `context status --format json` or `context run`.
+When the registry is missing, the Route names `src/indexers.yaml` in
+`configuration`: declare the confirmed requirements with `indexers: []`, then
+re-evaluate. The next Route supplies the Provider selection input and completion
+command. An unconfigured project does not begin Partition or require a fabricated
+primary owner. `run --managed --until blocked-or-complete` stops at the same
+configuration or semantic input boundary; it does not make those decisions.
+
 1. Inspect and confirm the complete `IndexRequirementSet`. A Provider,
    registry entry or Result may strengthen it but cannot remove targets,
    questions, evidence obligations or required owner cells.
-2. Run `context indexer catalog --format json` and report those CLI-bundled
-   entry Skills together with Indexer Skills already visible to the Host.
-   When the Host exposes an exact Skill root, read only its `SKILL.md`
-   frontmatter and sibling `context-indexer.yaml`; the manifest version is
-   authoritative and `metadata.context-provider-version` must match it. Group
-   the same Skill name and exact version into one conversational item with all
-   observed source types. An installed projection of an identical CLI-bundled
-   identity is not a second Provider; different versions remain distinct. Do
-   not scan `.claude`, `.codex`, `.agents` or arbitrary user directories.
-3. Route the path-free visible identities with
-   `context indexer route-indexer-provider-selection`. Try the applicable
-   community fallback once when the Route requests it.
-4. Statically validate the returned selection proposal before a Host resolves
-   any Bundle. Resolve only the emitted exact requests, then stage and validate
-   the complete content ledger.
-5. Apply the registry and any declared customization through the staged,
-   CAS-bound project proposal. A successful static report is not write or
-   execution authority.
+2. Select applicable Providers from the Host-visible Skills and the CLI-bundled
+   catalog already in the current Action input. No separate catalog command,
+   installed-Skill inventory, discovery report, or discovery-only confirmation
+   is required. Use the supplied exact identity and cli-bundled distribution
+   for shipped Providers, even when their Skills are also visible to the Host.
+   For a relevant external Skill, read only its exact Host-exposed frontmatter
+   and sibling `context-indexer.yaml` needed for selection. Do not guess versions
+   or scan `.claude`, `.codex`, `.agents` or arbitrary user directories. Different
+   versions remain distinct; discovery order is not selection precedence.
+3. Submit the semantic `indexers` and any relevant non-CLI `host_visible_skills`
+   through the current Route's `context action complete-current` command. The
+   latter may be empty; it is not an inventory or an additional discovery step.
+4. The CLI performs routing, validation, resolution and staging internally.
+   Shipped Providers load directly from this CLI release; only external
+   Providers may require the returned Host resolution Action. Follow the
+   current Route if a distribution is missing, a version conflicts, or program
+   execution needs authorization. Do not call the low-level commands below as
+   a second production workflow.
+5. The CLI atomically applies the validated registry and any declared
+   customization. A successful static report alone is not write or execution
+   authority. Resume from the returned current Route.
 
 Every required requirement/domain/source/module cell has exactly one primary
 owner. Read scope may overlap for supporting profiles, extensions and
@@ -97,8 +108,9 @@ These outcomes all point back to this guide:
 
 ## Debugging commands
 
-Use `--help` for the current payload schema and copy Route-returned commands
-when available:
+These are diagnostic/manual primitives, not a checklist for normal selection.
+Use them only for an explicit diagnostic or a returned recovery. Use `--help`
+for the current payload schema and prefer Route-returned commands:
 
 ```bash
 context indexer catalog --format json

package/docs/guides/markdown-indexer-skill-authoring.md

@@ -96,6 +96,15 @@ content Review. There is no answer-only operation or evidence-specific Review.
 A blocking gap closes only through current source or an explicit non-delegable
 requirement change.
 
+## Bounded execution
+
+Each captured document remains an independently recoverable Partition input,
+but Context may transport several documents in one bounded Agent step. Return
+one result for every supplied task key and let global convergence merge
+documents that establish the same Subject. Batch order, filename order and
+heading order never create Subject identity. Author and Review use the same
+bounded transport rule without adding intermediate user approvals.
+
 ## Markdown author fixture checklist
 
 Release fixtures should cover: