refactor: apply repository naming contract

Apply the accepted pre-release package, service, type, directory, and role renames as one repository-wide change.

.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md
-2026-06-20-drop-bash-output-spill-files.md: b2bd1a04ee1524bab29814ffa7c22712a83ee5f7
+2026-06-20-drop-bash-output-spill-files.md: 55bd0dff02f5a09ceb5e557bbe6ddcf36f7791fe
 2026-06-20-drop-bash-output-spill-files.zh.md: ce12eb919c728d856926d6b2441abc26548b615e

.agents/notes/rejected/simplification/2026-06-20-drop-bash-output-spill-files.md

@@ -8,13 +8,13 @@ English | [中文](2026-06-20-drop-bash-output-spill-files.zh.md)
 
 `dsh-bash-local` keeps bounded in-memory output and spills large stdout/stderr streams into private temp files. That requires a private directory, random owner-only file creation, close-failure handling, byte-offset incremental reads, lossy read reporting, path rendering in model-facing text, and cleanup discipline. The tool then tells the model to read a local spill path when output was truncated.
 
-This solves a real problem, but in a narrow and leaky way. A spill path is a process-local filesystem artifact exposed to model output, not a durable harness artifact with scoped access, retention, or UI affordances. It also complicates background-task reads because a lossy incremental read has to point at one or two spill files.
+This solves a real problem, but in a narrow and leaky way. A spill path is a process-local filesystem artifact exposed to model output, not a durable harness artifact with scoped access, retention, or UI affordances. It also complicates background-job reads because a lossy incremental read has to point at one or two spill files.
 
 ## Proposal
 
 Keep tail truncation, drop full-output spill files. A bash result contains the bounded tail plus a clear truncation marker; no path is emitted. If users need full-output recovery, add a generic artifact/blob service with explicit ownership, cleanup, and UI rendering, then let bash attach large outputs to that service.
 
-This proposal can land independently of [a generic long-running tool runtime](../../implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md). If background tasks stay, `bash_output` should still report that output was dropped, but without advertising a spill path.
+This proposal can land independently of [a generic long-running tool runtime](../../implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md). If background jobs stay, `bash_output` should still report that output was dropped, but without advertising a spill path.
 
 ## Acceptance criteria
 

.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-api.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-api.md
-2026-07-12-prune-unused-skill-registry-api.md: ce4160445cf36c0ee26ae575b5dcf7be6e931c01
-2026-07-12-prune-unused-skill-registry-api.zh.md: 2366dc826e962c1f9f1ab058003a909f1ae4a1d0
+2026-07-12-prune-unused-skill-registry-api.md: c84c6d8d61e13ebe7e1a5d3d29260637e38dbf9f
+2026-07-12-prune-unused-skill-registry-api.zh.md: 123f7787b8e770851b4a8a9e765ce3792bee4f02

.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-api.md

@@ -10,7 +10,7 @@ The skill service's embedded-runtime subsystem has zero production caller of `ct
 
 ## Proposal
 
-Remove `SkillService.register()`, `SkillRegistration`, the runtime pseudo-provider and reserved-name rules, runtime revisions/cache branches, and runtime-only source/rank normalization. Tests that need an embedded skill register a small real provider. Retain `providerRevision` as the in-flight discovery epoch, but key completed catalogs by cwd alone: every provider mutation synchronously clears the cache, and the post-await revision comparison already prevents inserting stale work. Remove `whenToUse`, `SkillCandidate.path`, and `SkillDefinition.path` from the skill contract and local-provider copies while retaining provider locator/root paths; retain `metadata`, `disableModelInvocation`, `source`, `provider`, `locator`, and `resourceBase` as either deliberate extension vocabulary or production-consumed fields.
+Remove `SkillRegistry.register()`, `SkillRegistration`, the runtime pseudo-provider and reserved-name rules, runtime revisions/cache branches, and runtime-only source/rank normalization. Tests that need an embedded skill register a small real provider. Retain `providerRevision` as the in-flight discovery epoch, but key completed catalogs by cwd alone: every provider mutation synchronously clears the cache, and the post-await revision comparison already prevents inserting stale work. Remove `whenToUse`, `SkillCandidate.path`, and `SkillDefinition.path` from the skill contract and local-provider copies while retaining provider locator/root paths; retain `metadata`, `disableModelInvocation`, `source`, `provider`, `locator`, and `resourceBase` as either deliberate extension vocabulary or production-consumed fields.
 
 Amend the skill-system Agent Note, README, JSDoc, catalogs, and tests. Agent-scoped system-prompt sections, tool providers, and variables are explicitly outside this proposal: the [agent-scope contributor contract](../../implemented/architecture/2026-07-08-agent-scope-contexts.md) intentionally allows all three to be registered during `setup(agentCtx)` through the agent-owned context, so absence of a fixed in-repo scoped registration is not evidence of non-consumption.
 

.agents/notes/rejected/simplification/2026-07-12-prune-unused-skill-registry-api.zh.md

@@ -10,7 +10,7 @@ skill（技能）服务的嵌入式运行时子系统中，`ctx.skills.register(
 
 ## 提案
 
-移除 `SkillService.register()`、`SkillRegistration`、运行时伪提供方及保留名称规则、运行时 revision/缓存分支，以及仅用于运行时的 source/rank 规范化逻辑。需要嵌入式 skill 的测试改为注册一个小型真实提供方。保留 `providerRevision` 作为进行中发现操作的 epoch，但已完成的目录缓存仅以 cwd 为键：每次提供方变更同步清除缓存，await 之后的 revision 比较已能阻止插入陈旧结果。从 skill 约定和本地提供方副本中移除 `whenToUse`、`SkillCandidate.path` 与 `SkillDefinition.path`，同时保留提供方的 locator/root 路径；保留 `metadata`、`disableModelInvocation`、`source`、`provider`、`locator` 和 `resourceBase`，因为它们要么是有意开放的扩展词汇，要么是生产消费的字段。
+移除 `SkillRegistry.register()`、`SkillRegistration`、运行时伪提供方及保留名称规则、运行时 revision/缓存分支，以及仅用于运行时的 source/rank 规范化逻辑。需要嵌入式 skill 的测试改为注册一个小型真实提供方。保留 `providerRevision` 作为进行中发现操作的 epoch，但已完成的目录缓存仅以 cwd 为键：每次提供方变更同步清除缓存，await 之后的 revision 比较已能阻止插入陈旧结果。从 skill 约定和本地提供方副本中移除 `whenToUse`、`SkillCandidate.path` 与 `SkillDefinition.path`，同时保留提供方的 locator/root 路径；保留 `metadata`、`disableModelInvocation`、`source`、`provider`、`locator` 和 `resourceBase`，因为它们要么是有意开放的扩展词汇，要么是生产消费的字段。
 
 同步修订 skill 系统 Agent Note、README、JSDoc、目录文件与测试。agent（智能体）作用域的系统提示词段、工具提供方和变量明确不在本提案范围内：[agent 作用域贡献者约定](../../implemented/architecture/2026-07-08-agent-scope-contexts.md)有意允许在 `setup(agentCtx)` 期间通过 agent 拥有的上下文注册这三者，因此仓库内没有固定的作用域注册并不能证明它们未被使用。
 

.agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.md
-2026-07-19-fold-compaction-package-split.md: 8bd83c389454092171633af806178ef8a9a74c72
-2026-07-19-fold-compaction-package-split.zh.md: 7f3e1622cc576d0d6c1d7c7cf171e9c7ccbb77f5
+2026-07-19-fold-compaction-package-split.md: 17d2ff5b8b663131eb3548dbf32d9489ca174f6b
+2026-07-19-fold-compaction-package-split.zh.md: a9d85723ea849519951a2a68f25ada367d2af481

.agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.md

@@ -6,13 +6,13 @@ English | [中文](2026-07-19-fold-compaction-package-split.zh.md)
 
 ## Problem
 
-Compaction is split between `@deepseek-ai/dsh-compact`, which owns an abstract two-method service and shared types, and `@deepseek-ai/dsh-compact-basic`, which owns the only complete provider. Shipped configurations load only the basic package, and no production package independently consumes the Service Definition package except that provider.
+Compaction is split between `@deepseek-ai/dsh-compaction`, which owns an abstract two-method service and shared types, and `@deepseek-ai/dsh-compaction-basic`, which owns the only complete provider. Shipped configurations load only the basic package, and no production package independently consumes the Service Definition package except that provider.
 
 The split adds a package manifest, README, project boundary, dependency edge, abstract forwarding class, generated catalog entries, and composition wiring without demonstrating backend substitution. The [capability-seam decision](../../implemented/architecture/2026-06-13-capability-seams.md) requires a real interface, implementation, and consumer rather than a preemptive split; the [compaction decision](../../implemented/feature/2026-06-18-compaction-capability-seam.md) records that its independent consumer was deferred.
 
 ## Proposal
 
-Move the basic implementation into `@deepseek-ai/dsh-compact` and remove `@deepseek-ai/dsh-compact-basic`. Keep `ctx.compact`, `CompactionResult`, the shared transcript and tool-pairing helpers, the existing configuration, and the concrete compaction algorithm in one package.
+Move the basic implementation into `@deepseek-ai/dsh-compaction` and remove `@deepseek-ai/dsh-compaction-basic`. Keep `ctx.compaction`, `CompactionResult`, the shared transcript and tool-pairing helpers, the existing configuration, and the concrete compaction algorithm in one package.
 
 Preserve `summarize()` as a protected customization hook. A deployment-specific summarizer can subclass or intercept the existing LLM call without requiring a second capability package. Reintroduce a separate Service Definition package only when a second complete backend and an independent Consumer need substitution.
 
@@ -22,16 +22,16 @@ Amend the implemented compaction decision and the [recallable-compaction proposa
 
 **Keep the split because a remote or recall backend may arrive.** A possible future implementation does not justify the current package boundary. Recall adds a consumer of compaction results, not necessarily another implementation, and a remote summarizer can use the protected hook.
 
-**Move the provider package name onto the Service Definition package.** Keeping `compact-basic` as the surviving name would make the product service appear to be one optional backend. `compact` is the stable service identity already used by `ctx.compact` and is the clearer single-package owner.
+**Move the provider package name onto the Service Definition package.** Keeping `compaction-basic` as the surviving name would make the product service appear to be one optional backend. `compact` is the stable service identity already used by `ctx.compaction` and is the clearer single-package owner.
 
 ## Acceptance criteria
 
-- `@deepseek-ai/dsh-compact-basic` and its workspace/package metadata are removed.
-- `@deepseek-ai/dsh-compact` owns the current configuration, plugin class, algorithm, types, events, and shared helpers.
+- `@deepseek-ai/dsh-compaction-basic` and its workspace/package metadata are removed.
+- `@deepseek-ai/dsh-compaction` owns the current configuration, plugin class, algorithm, types, events, and shared helpers.
 - Existing deployments can load the surviving package with equivalent configuration and model-visible behavior.
 - Automatic and manual compaction preserve cancellation, locking, token accounting, tool pairing, durable events, cited source-event seqs, retry convergence, and transcript rendering.
 - Loader composition, unit, runaway-turn, cancellation, snapshot, and real-model compaction tests pass; generated catalogs and module graphs are current.
 
 ## Risks
 
-This is an intentional pre-release package-name contraction. Embedders loading `@deepseek-ai/dsh-compact-basic` must switch packages, and future backend substitution would require extracting a boundary again. The cost is acceptable only while one complete implementation exists; acceptance should be revisited if a second backend lands first.
+This is an intentional pre-release package-name contraction. Embedders loading `@deepseek-ai/dsh-compaction-basic` must switch packages, and future backend substitution would require extracting a boundary again. The cost is acceptable only while one complete implementation exists; acceptance should be revisited if a second backend lands first.

.agents/notes/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md

@@ -6,13 +6,13 @@ Status: rejected — 计划增加更多压缩后端，因此 Service Definition
 
 ## 问题
 
-压缩（compaction）目前拆分在两个包中：`@deepseek-ai/dsh-compact` 拥有一个含两个方法的抽象服务和共享类型，`@deepseek-ai/dsh-compact-basic` 拥有唯一的完整提供方。交付配置只加载 basic 包，除了该提供方外，没有生产包独立消费 Service Definition 包。
+压缩（compaction）目前拆分在两个包中：`@deepseek-ai/dsh-compaction` 拥有一个含两个方法的抽象服务和共享类型，`@deepseek-ai/dsh-compaction-basic` 拥有唯一的完整提供方。交付配置只加载 basic 包，除了该提供方外，没有生产包独立消费 Service Definition 包。
 
 该拆分增加了一份包 manifest（元数据清单）、README、项目边界、依赖边、抽象转发类、生成目录项和组合接线，却没有实际的后端替换用例。[能力 seam 决策](../../implemented/architecture/2026-06-13-capability-seams.md)要求接口、实现和消费方都必须真实存在，而不能预先拆分；[压缩决策](../../implemented/feature/2026-06-18-compaction-capability-seam.md)也记录了独立消费方的实现仍被推迟。
 
 ## 提案
 
-把 basic 实现移入 `@deepseek-ai/dsh-compact`，并删除 `@deepseek-ai/dsh-compact-basic`。`ctx.compact`、`CompactionResult`、共享 transcript（文本记录）和工具配对辅助方法、现有配置以及具体压缩算法都由一个包负责。
+把 basic 实现移入 `@deepseek-ai/dsh-compaction`，并删除 `@deepseek-ai/dsh-compaction-basic`。`ctx.compaction`、`CompactionResult`、共享 transcript（文本记录）和工具配对辅助方法、现有配置以及具体压缩算法都由一个包负责。
 
 保留 `summarize()` 作为受保护的自定义钩子。部署专用的摘要器可以通过继承或拦截现有 LLM（大语言模型）调用完成定制，无需第二个能力包。只有在第二个完整后端与独立消费方确实需要替换实现时，才重新引入独立的 Service Definition 包。
 
@@ -22,16 +22,16 @@ Status: rejected — 计划增加更多压缩后端，因此 Service Definition
 
 **为可能出现的远程或回忆后端保留拆分。** 一种可能的未来实现不足以支撑当前包边界。回忆功能会增加压缩结果的消费方，但不一定增加另一种实现；远程摘要器也可以使用受保护钩子。
 
-**将提供方包名用于 Service Definition 包。** 如果保留 `compact-basic` 作为最终名称，产品服务会看起来像一个可选后端。`compact` 已经是 `ctx.compact` 使用的稳定服务标识，更适合作为单包所有者。
+**将提供方包名用于 Service Definition 包。** 如果保留 `compaction-basic` 作为最终名称，产品服务会看起来像一个可选后端。`compact` 已经是 `ctx.compaction` 使用的稳定服务标识，更适合作为单包所有者。
 
 ## 验收标准
 
-- 删除 `@deepseek-ai/dsh-compact-basic` 及其工作区和包元数据。
-- `@deepseek-ai/dsh-compact` 拥有当前配置、插件类、算法、类型、事件和共享辅助方法。
+- 删除 `@deepseek-ai/dsh-compaction-basic` 及其工作区和包元数据。
+- `@deepseek-ai/dsh-compaction` 拥有当前配置、插件类、算法、类型、事件和共享辅助方法。
 - 现有部署可以使用等效配置加载保留的包，模型可见行为等效。
 - 自动压缩和手动压缩保留取消、锁、token 用量、工具配对、持久事件、引用的来源事件 seq、重试收敛和 transcript 渲染行为。
 - loader 组合、单元、失控轮次、取消、快照和真实模型压缩测试全部通过；生成目录与模块图保持最新。
 
 ## 风险
 
-这是一项有意实施的预发布包名收缩。加载 `@deepseek-ai/dsh-compact-basic` 的嵌入方必须切换包，未来的后端替换也需要重新提取边界。只有在仍然只有一个完整实现时，这项代价才可接受；如果第二个后端先行落地，应重新评估是否接纳本提案。
+这是一项有意实施的预发布包名收缩。加载 `@deepseek-ai/dsh-compaction-basic` 的嵌入方必须切换包，未来的后端替换也需要重新提取边界。只有在仍然只有一个完整实现时，这项代价才可接受；如果第二个后端先行落地，应重新评估是否接纳本提案。

.agents/notes/rejected/simplification/2026-07-26-builtin-timer-promises-for-hand-rolled-sleeps.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/rejected/simplification/2026-07-26-builtin-timer-promises-for-hand-rolled-sleeps.md
-2026-07-26-builtin-timer-promises-for-hand-rolled-sleeps.md: 475fd632cd4f75c966d4693e049edd48a1301992
-2026-07-26-builtin-timer-promises-for-hand-rolled-sleeps.zh.md: dfd7cdb3d4a6c5231f75db6c422a32bc6b7f080a
+2026-07-26-builtin-timer-promises-for-hand-rolled-sleeps.md: 8c46de37cbb936f31dc498b2100a031610b6d1e7
+2026-07-26-builtin-timer-promises-for-hand-rolled-sleeps.zh.md: 4795abff037ee19a7407cae02aee71ec3abcca44

.agents/notes/rejected/simplification/2026-07-26-builtin-timer-promises-for-hand-rolled-sleeps.md

@@ -6,19 +6,19 @@ English | [中文](2026-07-26-builtin-timer-promises-for-hand-rolled-sleeps.zh.m
 
 ## Problem
 
-Three packages hand-roll promise-wrapped timers that the `node:timers/promises` builtin already provides, while other packages (`dsh-llm-mock-server` `pause()`, `dsh-lsp-local`, `dsh-acp-snapshot`) already use the builtin — so the hand-rolled copies are also a consistency gap:
+Three packages hand-roll promise-wrapped timers that the `node:timers/promises` builtin already provides, while other packages (`dsh-llm-mock-server` `pause()`, `dsh-lsp-stdio`, `dsh-acp-snapshot`) already use the builtin — so the hand-rolled copies are also a consistency gap:
 
 - `packages/llm/llm-retry/src/index.ts` `cancellableDelay()` (~14 lines): `new Promise` + `setTimeout` + manual abort-listener add/remove, resolving `true` on elapse and `false` on abort, consumed once for the backoff wait.
-- `packages/workflow/workflow-workerthread/src/host.ts` `sleep()` (~7 lines): promise-wrapped unref'd `setTimeout` used as the dispose-grace bound.
-- `packages/pty/pty-local/src/session.ts` `delay()` (~4 lines): bare promise-wrapped `setTimeout` used in polling/teardown waits.
+- `packages/workflow/workflow-worker-thread/src/host.ts` `sleep()` (~7 lines): promise-wrapped unref'd `setTimeout` used as the dispose-grace bound.
+- `packages/terminal/terminal-bash/src/session.ts` `delay()` (~4 lines): bare promise-wrapped `setTimeout` used in polling/teardown waits.
 
 ## Proposal
 
 Replace all three with `import { setTimeout } from 'node:timers/promises'`:
 
 - llm-retry: `try { await setTimeout(delayMs, undefined, { signal }); /* retry */ } catch { /* abort → fail */ }` — with a signal, the promise rejects only with the abort error, and a pre-aborted signal rejects immediately; behavior is identical, including timer clearing on abort. The empty `catch` names the abort rejection per the repo's empty-catch rule.
-- workflow-workerthread: `setTimeout(ms, undefined, { ref: false })` — exact semantics including not holding the event loop open.
-- pty-local: `import { setTimeout as delay } from 'node:timers/promises'` — identical signature, call sites unchanged.
+- workflow-worker-thread: `setTimeout(ms, undefined, { ref: false })` — exact semantics including not holding the event loop open.
+- terminal-bash: `import { setTimeout as delay } from 'node:timers/promises'` — identical signature, call sites unchanged.
 
 No dedicated tests pin the helpers themselves; the packages' behavior suites keep passing.
 
@@ -30,7 +30,7 @@ No dedicated tests pin the helpers themselves; the packages' behavior suites kee
 ## Acceptance criteria
 
 - None of the three packages defines a promise-wrapped `setTimeout` helper; all import from `node:timers/promises`.
-- The `llm-retry`, `workflow-workerthread`, and `pty-local` test suites pass unchanged (behavioral parity).
+- The `llm-retry`, `workflow-worker-thread`, and `terminal-bash` test suites pass unchanged (behavioral parity).
 
 ## Risks
 

.agents/notes/rejected/simplification/2026-07-26-builtin-timer-promises-for-hand-rolled-sleeps.zh.md

@@ -6,19 +6,19 @@ Status: rejected — 实现（PR #679）证伪了行为等价前提：vitest 的
 
 ## 问题
 
-三个包手写了用 promise 包装的定时器，而 `node:timers/promises` 内置模块早已提供同等能力；其他包（`dsh-llm-mock-server` 的 `pause()`、`dsh-lsp-local`、`dsh-acp-snapshot`）已经在使用该内置模块，因此这些手写副本同时也是一处一致性缺口：
+三个包手写了用 promise 包装的定时器，而 `node:timers/promises` 内置模块早已提供同等能力；其他包（`dsh-llm-mock-server` 的 `pause()`、`dsh-lsp-stdio`、`dsh-acp-snapshot`）已经在使用该内置模块，因此这些手写副本同时也是一处一致性缺口：
 
 - `packages/llm/llm-retry/src/index.ts` 的 `cancellableDelay()`（约 14 行）：`new Promise` + `setTimeout` + 手动添加和移除中止监听器，定时器触发时 resolve 为 `true`、被中止时 resolve 为 `false`，仅在退避等待处消费一次。
-- `packages/workflow/workflow-workerthread/src/host.ts` 的 `sleep()`（约 7 行）：promise 包装、已 unref 的 `setTimeout`，用作 dispose（资源释放）宽限的时间上界。
-- `packages/pty/pty-local/src/session.ts` 的 `delay()`（约 4 行）：朴素的 promise 包装 `setTimeout`，用于轮询与拆卸等待。
+- `packages/workflow/workflow-worker-thread/src/host.ts` 的 `sleep()`（约 7 行）：promise 包装、已 unref 的 `setTimeout`，用作 dispose（资源释放）宽限的时间上界。
+- `packages/terminal/terminal-bash/src/session.ts` 的 `delay()`（约 4 行）：朴素的 promise 包装 `setTimeout`，用于轮询与拆卸等待。
 
 ## 提案
 
 用 `import { setTimeout } from 'node:timers/promises'` 替换这三处实现：
 
 - llm-retry：`try { await setTimeout(delayMs, undefined, { signal }); /* retry */ } catch { /* abort → fail */ }`。传入 signal 后，该 promise 只会因中止错误而拒绝，已提前中止的 signal 则立即拒绝；行为完全一致，包括中止时清除定时器。按仓库的空 catch 规则，这个空 `catch` 注明其吞下的是 abort 拒绝。
-- workflow-workerthread：`setTimeout(ms, undefined, { ref: false })`，语义完全等价，包括不会让事件循环保持存活。
-- pty-local：`import { setTimeout as delay } from 'node:timers/promises'`，签名完全相同，调用点无需改动。
+- workflow-worker-thread：`setTimeout(ms, undefined, { ref: false })`，语义完全等价，包括不会让事件循环保持存活。
+- terminal-bash：`import { setTimeout as delay } from 'node:timers/promises'`，签名完全相同，调用点无需改动。
 
 没有专属测试固定这些辅助函数本身；各包的行为测试套件继续通过。
 
@@ -30,7 +30,7 @@ Status: rejected — 实现（PR #679）证伪了行为等价前提：vitest 的
 ## 验收标准
 
 - 这三个包都不再各自定义 promise 包装的 `setTimeout` 辅助函数，而是都从 `node:timers/promises` 导入。
-- `llm-retry`、`workflow-workerthread` 与 `pty-local` 的测试套件原样通过（行为等价）。
+- `llm-retry`、`workflow-worker-thread` 与 `terminal-bash` 的测试套件原样通过（行为等价）。
 
 ## 风险
 

.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md
-2026-07-26-dependency-swaps-rejected-by-nih-audit.md: c3422a9c8b4d60b4795aed5108923ac3446b0a46
-2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md: 95f94f90f1a3d88c265d1f3b79a2dbb330aaa144
+2026-07-26-dependency-swaps-rejected-by-nih-audit.md: c834142bccaeca2f7407c984767f5aa0af88bc22
+2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md: f5dbaf489a6c6133bf6398962c059c4c5a3d19f2

.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md

@@ -14,9 +14,9 @@ Adopt the following dependency swaps. Rejected — per-item evidence below; a fu
 
 **Protocol and parsing:**
 
-- **`vscode-jsonrpc` for LSP base-protocol framing/correlation** (`lsp-local`): the swappable core is ~255 of ~1,800 src lines; the package cannot express the configured `maxMessageBytes` incoming-size bound (restoring it means rebuilding the deleted framing), inverts the cancel-grace teardown semantics (`raceAbort` rejects immediately then tears down; vscode-jsonrpc keeps the promise pending), errors on pre-header stdout banners real servers emit, and is CJS in an ESM-everywhere repo. The [LSP seam note](../../implemented/architecture/2026-07-15-lsp-capability-seam.md) assigns JSON-RPC ownership to `dsh-lsp-local`; this audit is the explicit on-record weighing of the dependency it lacked.
-- **`vscode-languageserver-types` for lsp-local's wire-type subset**: ~80 type lines and ~45 guard lines, but upstream guards differ in both directions (accept `uri: undefined` the repo must reject; require `targetRange` the repo tolerates absent), and the initialize-result shapes live in `vscode-languageserver-protocol`, dragging `vscode-jsonrpc` in as a runtime dep — ~1 MB for 80 spec-exact lines.
-- **`json-rpc-2.0` for `dsh-jsonrpc`**: deletable correlation/dispatch is real (~100–130 lines) but the NDJSON wire must stay bit-identical for the hand-rolled Python SDK client, the package is single-maintainer, and the [GUI RPC note](../../implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md) already treats this package as a frozen narrow surface. `vscode-jsonrpc` is a worse fit still (Content-Length framing, cancellation vocabulary the protocol lacks).
+- **`vscode-jsonrpc` for LSP base-protocol framing/correlation** (`lsp-stdio`): the swappable core is ~255 of ~1,800 src lines; the package cannot express the configured `maxMessageBytes` incoming-size bound (restoring it means rebuilding the deleted framing), inverts the cancel-grace teardown semantics (`raceAbort` rejects immediately then tears down; vscode-jsonrpc keeps the promise pending), errors on pre-header stdout banners real servers emit, and is CJS in an ESM-everywhere repo. The [LSP seam note](../../implemented/architecture/2026-07-15-lsp-capability-seam.md) assigns JSON-RPC ownership to `dsh-lsp-stdio`; this audit is the explicit on-record weighing of the dependency it lacked.
+- **`vscode-languageserver-types` for lsp-stdio's wire-type subset**: ~80 type lines and ~45 guard lines, but upstream guards differ in both directions (accept `uri: undefined` the repo must reject; require `targetRange` the repo tolerates absent), and the initialize-result shapes live in `vscode-languageserver-protocol`, dragging `vscode-jsonrpc` in as a runtime dep — ~1 MB for 80 spec-exact lines.
+- **`json-rpc-2.0` for `dsh-sdk-jsonrpc-server`**: deletable correlation/dispatch is real (~100–130 lines) but the NDJSON wire must stay bit-identical for the hand-rolled Python SDK client, the package is single-maintainer, and the [GUI RPC note](../../implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md) already treats this package as a frozen narrow surface. `vscode-jsonrpc` is a worse fit still (Content-Length framing, cancellation vocabulary the protocol lacks).
 - **`jsonrpcclient` for the Python SDK client**: v4 builds/parses messages only — ~20 lines — while the 500 lines that matter (subprocess lifecycle, threaded reader, id correlation, bidirectional server-role responses) stay; the library is in low-maintenance mode.
 - **`eventsource-parser` for apiproxy's `readSse`**: only ~15 lines of framing are deletable, both wire ends are in-repo so spec conformance is moot, and it would add a dep to a browser-safe package. (Contrast with the [archived llm-deepseek dependency decision](../../archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md), where a real provider sits across the wire.)
 
@@ -32,7 +32,7 @@ Adopt the following dependency swaps. Rejected — per-item evidence below; a fu
 
 - **Ajv for the tools JSON Schema validator**: the [schema-DSL note](../../implemented/architecture/2026-07-20-unified-json-value-schema-dsl.md) explicitly rejected accepting a larger schema language; the validator also does realm-intrinsic prototype checks Ajv does not.
 - **`structuredClone` for session `snapshotJsonValue`/`isJsonValue`**: it is a validator + detacher enforcing the lossless-JSON boundary with single-read-per-getter and cross-realm intrinsic checks; `structuredClone` accepts Map/Date/-0 and enforces nothing. Same for the deliberately dependency-free `code-runtime-worker` mirror hardened against a model-mutated realm.
-- **`fast-deep-equal` for session surface `isDeepEqualJson`** and **`safe-stable-stringify` for repeat-tool-guard canonicalization**: both swaps work mechanically but each trades ~17–20 commented, tested lines for the first external runtime dependency of a core package — negative net at this size.
+- **`fast-deep-equal` for session surface `isDeepEqualJson`** and **`safe-stable-stringify` for repeat-tool-reminder canonicalization**: both swaps work mechanically but each trades ~17–20 commented, tested lines for the first external runtime dependency of a core package — negative net at this size.
 - **zod/valibot for durable-event strict decoders** (goal fold, tool-ralph, session): exact-key fail-loud decoders at durable boundaries with event-specific messages; a second schema library beside repo-standard schemastery is a policy change, not a deletion.
 - **`gpt-tokenizer`/tiktoken for token-meter**: the [replay-token-meter note](../../implemented/architecture/2026-07-15-replay-token-meter-service.md) explicitly rejected tokenizer backends; a GPT BPE is also the wrong tokenizer for DeepSeek models, and ~350 of the package's lines are replay-fold bookkeeping no tokenizer covers.
 - **`partial-json` for streamed tool-call arguments**: nothing to replace — arguments stay raw JSON strings end-to-end by documented contract; `JSON.parse` runs only on complete payloads.
@@ -54,7 +54,7 @@ Adopt the following dependency swaps. Rejected — per-item evidence below; a fu
 
 - **`msw` for llm-mock-server**: the server exists to fault the wire — socket destroy, mid-SSE disconnect, stall, pre-listen refusal — for real HTTP adapters and subprocesses; in-process interception can express none of that. [Wire-fault-server note](../../implemented/testing/2026-07-25-scriptable-llm-wire-fault-server.md) owns the design.
 - **`hono`/`sirv` for host/webserver**: the core is a disposer-based dynamic route registry (registrations-are-effects contract, HMR unregistration) plus index-HTML transform taps; hono routers are add-only, and static middleware cannot serve the transformed index. ~244 lines total, genuinely small.
-- **`@mozilla/readability`/`iconv-lite` for web-fetch-local**: the provider returns raw HTML; charset handling is already the builtin `TextDecoder`; MIME parsing is ~11 lines; redirect following is same-origin security policy.
+- **`@mozilla/readability`/`iconv-lite` for web-fetch-http**: the provider returns raw HTML; charset handling is already the builtin `TextDecoder`; MIME parsing is ~11 lines; redirect following is same-origin security policy.
 
 **SQLite and storage:**
 

.agents/notes/rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.zh.md

@@ -14,9 +14,9 @@ Status: rejected — 下列每一项替换在证据上都未达到净简化门
 
 **协议与解析：**
 
-- **以 `vscode-jsonrpc` 承担 LSP 基础协议的分帧/关联**（`lsp-local`）：可替换的核心只占 src 约 1,800 行中的约 255 行；该包无法表达已配置的 `maxMessageBytes` 入站大小上限（要恢复它就得重建被删掉的分帧代码），反转了取消宽限期的拆除语义（`raceAbort` 立即 reject 再拆除；vscode-jsonrpc 让 promise 保持挂起），会在真实服务器输出的 header 前 stdout 横幅上报错，而且在这个全面采用 ESM 的仓库里它是 CJS。[LSP seam 决策](../../implemented/architecture/2026-07-15-lsp-capability-seam.md)把 JSON-RPC 的所有权划给 `dsh-lsp-local`；本次审计正是对该决策当时缺失的这项依赖权衡的明文记录。
-- **以 `vscode-languageserver-types` 承担 lsp-local 的协议类型子集**：约 80 行类型加约 45 行守卫，但上游守卫在两个方向上都与本仓库不一致（接受本仓库必须拒绝的 `uri: undefined`；强制要求本仓库容忍缺失的 `targetRange`），而且 initialize 结果的形状住在 `vscode-languageserver-protocol` 里，会把 `vscode-jsonrpc` 拖成运行时依赖——为 80 行严格贴合规范的代码付出约 1 MB。
-- **以 `json-rpc-2.0` 替换 `dsh-jsonrpc`**：可删除的关联/分发代码确实存在（约 100–130 行），但 NDJSON 协议格式（wire format）必须与手写的 Python SDK 客户端逐位一致，该包只有单一维护者，且 [GUI RPC 决策](../../implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md)已把这个包当作冻结的窄接口面对待。`vscode-jsonrpc` 更不合适（Content-Length 分帧、该协议并不具备的取消词汇）。
+- **以 `vscode-jsonrpc` 承担 LSP 基础协议的分帧/关联**（`lsp-stdio`）：可替换的核心只占 src 约 1,800 行中的约 255 行；该包无法表达已配置的 `maxMessageBytes` 入站大小上限（要恢复它就得重建被删掉的分帧代码），反转了取消宽限期的拆除语义（`raceAbort` 立即 reject 再拆除；vscode-jsonrpc 让 promise 保持挂起），会在真实服务器输出的 header 前 stdout 横幅上报错，而且在这个全面采用 ESM 的仓库里它是 CJS。[LSP seam 决策](../../implemented/architecture/2026-07-15-lsp-capability-seam.md)把 JSON-RPC 的所有权划给 `dsh-lsp-stdio`；本次审计正是对该决策当时缺失的这项依赖权衡的明文记录。
+- **以 `vscode-languageserver-types` 承担 lsp-stdio 的协议类型子集**：约 80 行类型加约 45 行守卫，但上游守卫在两个方向上都与本仓库不一致（接受本仓库必须拒绝的 `uri: undefined`；强制要求本仓库容忍缺失的 `targetRange`），而且 initialize 结果的形状住在 `vscode-languageserver-protocol` 里，会把 `vscode-jsonrpc` 拖成运行时依赖——为 80 行严格贴合规范的代码付出约 1 MB。
+- **以 `json-rpc-2.0` 替换 `dsh-sdk-jsonrpc-server`**：可删除的关联/分发代码确实存在（约 100–130 行），但 NDJSON 协议格式（wire format）必须与手写的 Python SDK 客户端逐位一致，该包只有单一维护者，且 [GUI RPC 决策](../../implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md)已把这个包当作冻结的窄接口面对待。`vscode-jsonrpc` 更不合适（Content-Length 分帧、该协议并不具备的取消词汇）。
 - **以 `jsonrpcclient` 承担 Python SDK 客户端**：v4 只做消息的构造/解析——约 20 行——而真正要紧的 500 行（子进程生命周期、线程化读取器、id 关联、双向的服务端角色应答）全都保留；该库处于低维护模式。
 - **以 `eventsource-parser` 替换 apiproxy 的 `readSse`**：可删除的分帧只有约 15 行，线路两端都在仓库内，规范符合性无关紧要，而且这会给一个浏览器安全的包添加依赖。（对比[已归档的 llm-deepseek 依赖决策](../../archived/simplification/2026-07-26-eventsource-parser-for-deepseek-sse.md)：那里线路对面是真实的提供方。）
 
@@ -32,7 +32,7 @@ Status: rejected — 下列每一项替换在证据上都未达到净简化门
 
 - **以 Ajv 承担 tools 的 JSON Schema 校验器**：[schema DSL 决策](../../implemented/architecture/2026-07-20-unified-json-value-schema-dsl.md)已明确否决接纳更大的 schema 语言；这个校验器还会做 Ajv 不做的、针对 realm 内建原型的检查。
 - **以 `structuredClone` 替换会话的 `snapshotJsonValue`/`isJsonValue`**：它是校验器加分离器，以「每个 getter 只读一次」和跨 realm 内建对象检查强制执行无损 JSON 边界；`structuredClone` 接受 Map/Date/-0，什么都不强制。有意保持零依赖、针对被模型篡改的 realm 做过加固的 `code-runtime-worker` 镜像实现同理。
-- **以 `fast-deep-equal` 替换会话接口面的 `isDeepEqualJson`**、**以 `safe-stable-stringify` 承担 repeat-tool-guard 的规范化**：两项替换在机械层面都可行，但每一项都是拿约 17–20 行带注释、有测试的代码，去换一个核心包的第一个外部运行时依赖——在这个体量上是净亏损。
+- **以 `fast-deep-equal` 替换会话接口面的 `isDeepEqualJson`**、**以 `safe-stable-stringify` 承担 repeat-tool-reminder 的规范化**：两项替换在机械层面都可行，但每一项都是拿约 17–20 行带注释、有测试的代码，去换一个核心包的第一个外部运行时依赖——在这个体量上是净亏损。
 - **以 zod/valibot 承担持久事件的严格解码器**（goal fold、tool-ralph、session）：它们是位于持久化边界、键集精确匹配、失败即明确报错、带事件专属报错信息的解码器；在仓库标准 schemastery 之外再放一个 schema 库是政策变更，不是删除。
 - **以 `gpt-tokenizer`/tiktoken 替换 token-meter**：[回放 token 计量决策](../../implemented/architecture/2026-07-15-replay-token-meter-service.md)已明确否决分词器后端；GPT 的 BPE 对 DeepSeek 模型来说也是错误的分词器，而且这个包约 350 行是回放折叠簿记，任何分词器都覆盖不了。
 - **以 `partial-json` 处理流式工具调用参数**：无可替换——按已记录的约定，参数端到端保持为原始 JSON 字符串；`JSON.parse` 只在完整载荷上运行。
@@ -54,7 +54,7 @@ Status: rejected — 下列每一项替换在证据上都未达到净简化门
 
 - **以 `msw` 替换 llm-mock-server**：这个服务器的存在意义就是在线路上制造故障——socket 销毁、SSE（Server-Sent Events）中途断连、停滞、监听前拒绝——服务对象是真实的 HTTP 适配器和子进程；进程内拦截一样都表达不了。设计归[线路故障服务器决策](../../implemented/testing/2026-07-25-scriptable-llm-wire-fault-server.md)所有。
 - **以 `hono`/`sirv` 承担 host/webserver**：核心是基于 disposer 的动态路由注册表（「注册即效果」约定、HMR 反注册）加 index HTML 变换挂点；hono 的路由器只增不减，静态中间件也无法伺服变换后的 index。总共约 244 行，确实很小。
-- **以 `@mozilla/readability`/`iconv-lite` 承担 web-fetch-local**：该提供方返回原始 HTML；字符集处理已经是内置的 `TextDecoder`；MIME 解析约 11 行；重定向跟随是同源安全策略。
+- **以 `@mozilla/readability`/`iconv-lite` 承担 web-fetch-http**：该提供方返回原始 HTML；字符集处理已经是内置的 `TextDecoder`；MIME 解析约 11 行；重定向跟随是同源安全策略。
 
 **SQLite 与存储：**