diff --git a/.agents/notes/README.i18n.yaml b/.agents/notes/README.i18n.yaml
index f92ea2f66d..faf4d69b5b 100644
--- a/.agents/notes/README.i18n.yaml
+++ b/.agents/notes/README.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/README.md
README.md: ae8e4724d610c97d74910d7dec5c95af69e93281
-README.zh.md: a16403ae87cd16d758b8303f42f60ad34b9c1eb3
+README.zh.md: 8cecc7068d9efc5e2ebb78d2301d03633f70f137
diff --git a/.agents/notes/README.zh.md b/.agents/notes/README.zh.md
index a16403ae87..8cecc7068d 100644
--- a/.agents/notes/README.zh.md
+++ b/.agents/notes/README.zh.md
@@ -16,13 +16,13 @@
文件名中的日期是该主题**首次提出**的时间(以 git 历史为准)。Agent Note 之间的交叉引用使用相对 Markdown 链接(`[topic](../../implemented/architecture/2026-…-….md)`),从不使用纯文字或编号,这样既可机械检查,也能在文件夹间移动时保持有效。
-活跃生命周期目录树就是工作清单:浏览其生命周期/类别文件夹,或搜索仓库即可。请勿添加集中式 `INDEX.md`;设计理由见[不设索引的 Agent Note](implemented/process/2026-07-19-remove-generated-agent-note-index.md)。未来指导价值较低的已实施记录会移至下文所述、单独冻结的 [`archived/`](archived/AGENTS.md) 目录树。
+活跃生命周期目录树就是工作清单:浏览其生命周期/类别文件夹,或搜索仓库即可。请勿添加集中式 `INDEX.md`;设计理由见[不设索引的 Agent Note](implemented/process/2026-07-19-remove-generated-agent-note-index.zh.md)。未来指导价值较低的已实施记录会移至下文所述、单独冻结的 [`archived/`](archived/AGENTS.md) 目录树。
## 分类
-每份 Agent Note 属于 `scripts/agent-note-tree.ts` 中封闭集合里的一个路径编码类别;分类门禁拒绝其他文件夹。新增类别需要同时更新规范集合与本节。见[分类 Agent Note](implemented/process/2026-06-20-agent-note-classification.md)。
+每份 Agent Note 属于 `scripts/agent-note-tree.ts` 中封闭集合里的一个路径编码类别;分类门禁拒绝其他文件夹。新增类别需要同时更新规范集合与本节。见[分类 Agent Note](implemented/process/2026-06-20-agent-note-classification.zh.md)。
| 类别 | 覆盖范围 |
|---|---|
@@ -41,7 +41,9 @@
归档路径编码为 `archived/{class}/yyyy-mm-dd-topic-title.md`;其中有意省略 `implemented`,因为只有 implemented Agent Note 可以进入归档。归档变更会移动完整的英文、中文和伴随记录三个文件,保留 `Status: implemented`,在两种语言的文件中紧接该状态行插入相同的 `Archived: YYYY-MM-DD` 行,重新记录伴随记录,并修复或删除入站链接。归档时只允许对内容做这些更改。
-封存后,每组归档文件都永久冻结。禁止编辑、翻译、重新格式化、更新、移动或删除,也不得将其视为当前行为的权威依据。文档门禁会跳过归档源文件,包括其中的出站链接;当活跃文档有意引用历史时,仍可链接到归档 Agent Note。[`verify-archived-agent-notes`](../../scripts/verify-archived-agent-notes.ts) 强制执行封闭的类别目录树、完整的三文件配对、归档元数据、伴随记录 hash,以及仅追加的冻结内容 manifest(元数据清单)。[归档政策 Agent Note](implemented/process/2026-07-26-frozen-agent-note-archive.md) 记录了设计依据。
+封存后,每组归档文件都永久冻结。禁止编辑、翻译、重新格式化、更新、移动或删除,也不得将其视为当前行为的权威依据。文档门禁会跳过归档源文件,包括其中的出站链接;当活跃文档有意引用历史时,仍可链接到归档 Agent Note。[`verify-archived-agent-notes`](../../scripts/verify-archived-agent-notes.ts) 强制执行封闭的类别目录树、完整的三文件配对、归档元数据、伴随记录 hash,以及仅追加的冻结内容 manifest(元数据清单)。[归档政策 Agent Note](implemented/process/2026-07-26-frozen-agent-note-archive.zh.md) 记录了设计依据。
+
+
## 何时需要写一份
@@ -57,7 +59,7 @@
## 文件格式
-每份活跃 Agent Note 遵循统一的文件内格式,由 `pnpm run verify-agent-note-format`([scripts/verify-agent-note-format.ts](../../scripts/verify-agent-note-format.ts),`doc-sync`(文档同步门禁)的一环)强制执行;该格式的设计动机及其否决的替代方案见[统一格式 Agent Note](implemented/process/2026-07-05-uniform-agent-note-format.md)。归档记录保留封存时的格式,并增加上述归档日期行。
+每份活跃 Agent Note 遵循统一的文件内格式,由 `pnpm run verify-agent-note-format`([scripts/verify-agent-note-format.ts](../../scripts/verify-agent-note-format.ts),`doc-sync`(文档同步门禁)的一环)强制执行;该格式的设计动机及其否决的替代方案见[统一格式 Agent Note](implemented/process/2026-07-05-uniform-agent-note-format.zh.md)。归档记录保留封存时的格式,并增加上述归档日期行。
### 头部块
@@ -126,4 +128,4 @@ Status:
### 中文对侧文件
-`.zh.md` 对侧文件按 [i18n 约定](../../docs/i18n/README.md)逐章节与其英文对侧文件保持相同结构;机器检查的头部标记(`# Agent Note: ` 和 `Status:` 行)保持英文原样不翻译。格式门禁跳过 `.zh.md` 文件;配对门禁检查它们的一致性。
+`.zh.md` 对侧文件按 [i18n 约定](../../docs/i18n/README.zh.md)逐章节与其英文对侧文件保持相同结构;机器检查的头部标记(`# Agent Note: ` 和 `Status:` 行)保持英文原样不翻译。格式门禁跳过 `.zh.md` 文件;配对门禁检查它们的一致性。
diff --git a/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.i18n.yaml b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.i18n.yaml
new file mode 100644
index 0000000000..8b40d4a6bb
--- /dev/null
+++ b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-11-plugin-settings-tabs.md: 1f1701e000b891b4fc00bc666f603ee00bae50a7
+2026-08-11-plugin-settings-tabs.zh.md: f76a4a9e2317eb6603b48e1a7e451abdc55e00ff
diff --git a/.agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.md b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.md
similarity index 99%
rename from .agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.md
rename to .agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.md
index 96e4c48926..1f1701e000 100644
--- a/.agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.md
+++ b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.md
@@ -1,6 +1,7 @@
# Agent Note: Feature-owned tabs in Plugins settings
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-11-plugin-settings-tabs.zh.md)
diff --git a/.agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.zh.md b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.zh.md
similarity index 99%
rename from .agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.zh.md
rename to .agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.zh.md
index fa8f462640..f76a4a9e23 100644
--- a/.agents/notes/implemented/architecture/2026-08-11-plugin-settings-tabs.zh.md
+++ b/.agents/notes/archived/architecture/2026-08-11-plugin-settings-tabs.zh.md
@@ -1,6 +1,7 @@
# Agent Note: “插件”设置中的功能自有标签页
Status: implemented
+Archived: 2026-08-22
[English](2026-08-11-plugin-settings-tabs.md) | 中文
diff --git a/.agents/notes/archived/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.i18n.yaml
new file mode 100644
index 0000000000..725855f6c3
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md
+2026-07-31-composer-text-layers-share-one-scrollport.md: eb50673bb5fac50e12b0325c22c67072e130efb6
+2026-07-31-composer-text-layers-share-one-scrollport.zh.md: f0af130d34682fcdfe145eb73b18187ca316c0d2
diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md b/.agents/notes/archived/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md
similarity index 99%
rename from .agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md
rename to .agents/notes/archived/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md
index d01231f706..eb50673bb5 100644
--- a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md
+++ b/.agents/notes/archived/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md
@@ -1,6 +1,7 @@
# Agent Note: The composer's two text layers share one scrollport
Status: implemented
+Archived: 2026-08-20
English | [中文](2026-07-31-composer-text-layers-share-one-scrollport.zh.md)
diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md b/.agents/notes/archived/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md
similarity index 99%
rename from .agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md
rename to .agents/notes/archived/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md
index 3ce8cc05dc..f0af130d34 100644
--- a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md
+++ b/.agents/notes/archived/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md
@@ -1,6 +1,7 @@
# Agent Note: composer 的两层文本共用同一个滚动容器
Status: implemented
+Archived: 2026-08-20
[English](2026-07-31-composer-text-layers-share-one-scrollport.md) | 中文
@@ -24,7 +25,7 @@ composer 的文本由两层叠放绘制(见 [InputBar](../../../../packages/cl
于是浏览器在同一帧、同一个合成器上,把同一个偏移施加给两层。光标与字形的绑定来自结构本身,而不是来自持续维护:没有代码要跑,没有事件要等,也没有任何状态可能落后一帧。滚轮接力处理器保留,只是从 textarea 改挂到滚动容器上,并且仍是这个盒子上唯一的监听。
-Safari 的原生文本控件存在一个引擎例外:跨过软换行阈值的删除可能在镜像层收缩后仍保留原先的行布局。[Safari 软换行恢复](2026-08-13-safari-textarea-soft-wrap-reflow.md)会在绘制前恢复零溢出不变量,而不改变单滚动容器设计。
+Safari 的原生文本控件存在一个引擎例外:跨过软换行阈值的删除可能在镜像层收缩后仍保留原先的行布局。[Safari 软换行恢复](2026-08-13-safari-textarea-soft-wrap-reflow.zh.md)会在绘制前恢复零溢出不变量,而不改变单滚动容器设计。
上一版机制所需要的两样东西随它一起消失:
diff --git a/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.i18n.yaml
new file mode 100644
index 0000000000..4567896a25
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-04-large-history-pagination-call-stack.md: 12e9bbf72c2eea2058bf83fe864e09b4a520d391
+2026-08-04-large-history-pagination-call-stack.zh.md: 288687b05ecdfc2858b4d67e1be199135ea20227
diff --git a/.agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.md b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.md
similarity index 98%
rename from .agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.md
rename to .agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.md
index 28c2212112..12e9bbf72c 100644
--- a/.agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.md
+++ b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.md
@@ -1,6 +1,7 @@
# Agent Note: Large history provenance is scanned without argument expansion
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-04-large-history-pagination-call-stack.zh.md)
diff --git a/.agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md
similarity index 98%
rename from .agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md
rename to .agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md
index 57dde9bdc0..288687b05e 100644
--- a/.agents/notes/implemented/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md
+++ b/.agents/notes/archived/bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md
@@ -1,6 +1,7 @@
# Agent Note: 大规模历史记录的溯源信息通过扫描处理,不做参数展开
Status: implemented
+Archived: 2026-08-22
[English](2026-08-04-large-history-pagination-call-stack.md) | 中文
diff --git a/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.i18n.yaml
new file mode 100644
index 0000000000..a6305c1f5d
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-06-plan-narrow-viewport-regression.md: c42a110bf487ffab8f5975e65a8eb9bff4f1b0ae
+2026-08-06-plan-narrow-viewport-regression.zh.md: 3df4f8aca57a1830d7f8062cefe76ac1afa9c2ce
diff --git a/.agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.md b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.md
similarity index 99%
rename from .agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.md
rename to .agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.md
index 945d014e0c..c42a110bf4 100644
--- a/.agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.md
+++ b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.md
@@ -1,6 +1,7 @@
# Agent Note: narrow-viewport plan chip click-area regression test
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-06-plan-narrow-viewport-regression.zh.md)
diff --git a/.agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md
similarity index 96%
rename from .agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md
rename to .agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md
index 3706012936..3df4f8aca5 100644
--- a/.agents/notes/implemented/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md
+++ b/.agents/notes/archived/bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md
@@ -1,6 +1,7 @@
# Agent Note: 窄视口下 Plan chip 点击区域回归测试
Status: implemented
+Archived: 2026-08-22
[English](2026-08-06-plan-narrow-viewport-regression.md) | 中文
@@ -8,7 +9,7 @@ Status: implemented
外部报告 dsh-external/issues#107(内部聚类为 deepseek-harness#1406)测得视口宽度在 760px 到 850px 之间时 Plan 控件与模型选择器发生重叠,模型选择器覆盖 Plan 控件的点击区域,导致在 800×720 下无法用鼠标退出 Plan 模式。其验收清单要求增加浏览器回归测试,断言 Plan 中心命中 Plan 按钮。
-浏览器回归测试在当前 master 上复现了报告:800×720 下 Plan chip 与模型 trigger 重叠 36.9px,chip 中心命中 trigger 的 label。composer 控制行是 `display: flex; justify-content: space-between` 且 `.trailing { flex: none }`:当控件总宽超过卡片时,可收缩的 `.tools` 组把流内子项留在 `min-width: 0` 的盒内,于是 chip——溢出前最后一个流内子项——被绘制到 trailing 组上方。报告以来 Plan 控件形态已变(select → chip,`c20b988166`/`fe91919346`),控制行也获得过自适应能力(`c8c75ec891`,[web-composer-shared-width-axis](../feature/2026-08-04-web-composer-shared-width-axis.md)),但该行没有换行,重叠在两次重构后依然存在。
+浏览器回归测试在当前 master 上复现了报告:800×720 下 Plan chip 与模型 trigger 重叠 36.9px,chip 中心命中 trigger 的 label。composer 控制行是 `display: flex; justify-content: space-between` 且 `.trailing { flex: none }`:当控件总宽超过卡片时,可收缩的 `.tools` 组把流内子项留在 `min-width: 0` 的盒内,于是 chip——溢出前最后一个流内子项——被绘制到 trailing 组上方。报告以来 Plan 控件形态已变(select → chip,`c20b988166`/`fe91919346`),控制行也获得过自适应能力(`c8c75ec891`,[web-composer-shared-width-axis](../feature/2026-08-04-web-composer-shared-width-axis.zh.md)),但该行没有换行,重叠在两次重构后依然存在。
## 决策
diff --git a/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.i18n.yaml
new file mode 100644
index 0000000000..644cd813ce
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-11-preset-card-description-clamp.md: b9088b46184cde6f000fa39afbfe2d1145137b24
+2026-08-11-preset-card-description-clamp.zh.md: a7a3c4f26a55405715fe017ec3a7deb164432b0e
diff --git a/.agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.md b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.md
similarity index 99%
rename from .agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.md
rename to .agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.md
index 16ebf371d5..b9088b4618 100644
--- a/.agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.md
+++ b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.md
@@ -1,6 +1,7 @@
# Agent Note: Preset cards clamp their description instead of sizing the roster
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-11-preset-card-description-clamp.zh.md)
diff --git a/.agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.zh.md b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.zh.md
similarity index 99%
rename from .agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.zh.md
rename to .agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.zh.md
index 5b7a18f41e..a7a3c4f26a 100644
--- a/.agents/notes/implemented/bug-fix/2026-08-11-preset-card-description-clamp.zh.md
+++ b/.agents/notes/archived/bug-fix/2026-08-11-preset-card-description-clamp.zh.md
@@ -1,6 +1,7 @@
# Agent Note: 预设卡片截断自身描述,而不是由描述决定整份名单的高度
Status: implemented
+Archived: 2026-08-22
[English](2026-08-11-preset-card-description-clamp.md) | 中文
diff --git a/.agents/notes/archived/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.i18n.yaml
new file mode 100644
index 0000000000..804fdb4fb7
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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/implemented/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.md
+2026-08-13-safari-textarea-soft-wrap-reflow.md: 45cb3f39c50c72b44b8ae952ce3a861210e9f00a
+2026-08-13-safari-textarea-soft-wrap-reflow.zh.md: 37409b010c0009edf3c944076ba8c3db1b140de9
diff --git a/.agents/notes/implemented/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.md b/.agents/notes/archived/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.md
similarity index 99%
rename from .agents/notes/implemented/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.md
rename to .agents/notes/archived/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.md
index fb264a8e6f..45cb3f39c5 100644
--- a/.agents/notes/implemented/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.md
+++ b/.agents/notes/archived/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.md
@@ -1,6 +1,7 @@
# Agent Note: Safari textarea soft-wrap shrink recovery
Status: implemented
+Archived: 2026-08-20
English | [中文](2026-08-13-safari-textarea-soft-wrap-reflow.zh.md)
diff --git a/.agents/notes/implemented/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.zh.md b/.agents/notes/archived/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.zh.md
similarity index 96%
rename from .agents/notes/implemented/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.zh.md
rename to .agents/notes/archived/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.zh.md
index 7f55a5260e..37409b010c 100644
--- a/.agents/notes/implemented/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.zh.md
+++ b/.agents/notes/archived/bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.zh.md
@@ -1,12 +1,13 @@
# Agent Note: Safari textarea 软换行收缩恢复
Status: implemented
+Archived: 2026-08-20
[English](2026-08-13-safari-textarea-soft-wrap-reflow.md) | 中文
## 问题
-composer 把光标与选区留在透明的原生 textarea 中,由 backdrop 绘制可见字形,并由隐藏的镜像层决定完整草稿高度。因此,[单滚动容器决策](2026-07-31-composer-text-layers-share-one-scrollport.md)依赖 textarea 不持有可滚动溢出:每次草稿提交后,它的 `scrollHeight` 与 `clientHeight` 相等,`scrollTop` 为零。
+composer 把光标与选区留在透明的原生 textarea 中,由 backdrop 绘制可见字形,并由隐藏的镜像层决定完整草稿高度。因此,[单滚动容器决策](2026-07-31-composer-text-layers-share-one-scrollport.zh.md)依赖 textarea 不持有可滚动溢出:每次草稿提交后,它的 `scrollHeight` 与 `clientHeight` 相等,`scrollTop` 为零。
当 Backspace 让草稿跨过软换行阈值,同时 React 更新镜像层时,Safari 26.5.2 可能保留 textarea 原先的原生行布局。在复现出的两行变一行转换中,镜像层、backdrop、自增高栈和 textarea 盒都变为 28px 高,但 textarea 仍报告 `scrollHeight=52` 与 `scrollTop=20`。光标留在陈旧的原生行中,而 backdrop 已正确绘制为一行。
diff --git a/.agents/notes/archived/bug-fix/2026-08-20-composer-edit-range-from-selection.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-20-composer-edit-range-from-selection.i18n.yaml
new file mode 100644
index 0000000000..0e622c3944
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-20-composer-edit-range-from-selection.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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/implemented/bug-fix/2026-08-20-composer-edit-range-from-selection.md
+2026-08-20-composer-edit-range-from-selection.md: 46eaa0add61bdab9fdcb4fcfd0ec08b44481126d
+2026-08-20-composer-edit-range-from-selection.zh.md: 73a3903ad6c7c0aad55a35aacc5e1396084b6e7a
diff --git a/.agents/notes/archived/bug-fix/2026-08-20-composer-edit-range-from-selection.md b/.agents/notes/archived/bug-fix/2026-08-20-composer-edit-range-from-selection.md
new file mode 100644
index 0000000000..46eaa0add6
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-20-composer-edit-range-from-selection.md
@@ -0,0 +1,48 @@
+# Agent Note: Composer edits carry the range they applied to
+
+Status: implemented
+Archived: 2026-08-20
+
+English | [中文](2026-08-20-composer-edit-range-from-selection.zh.md)
+
+## Problem
+
+The input machine keeps its reference occurrences aligned by reconciling them against one edit range: entries before the range shift, entries after it hold, and an entry the range intersects loses its structured identity and stays behind as ordinary draft text. That last rule is the deliberate meaning of editing inside a reference.
+
+Ordinary typing supplied no range. A controlled textarea's change event carries only the resulting string, so the machine recovered the range by scanning the two drafts for a common prefix and suffix. That recovery is ambiguous whenever the inserted text repeats the text it lands against, and the greedy scan always resolves the ambiguity the same way: it slides the edit as late as the characters allow.
+
+A reference renders as `@` followed by its label, so typing `@` immediately before one produces exactly that collision. The user inserts at the reference's own offset; the scan reports an insertion one character later, inside the reference; reconcile applies the intersect rule and drops the occurrence. Deleting a character in front of such a reference slides the same way.
+
+The draft then still reads correctly to the eye while carrying no structured reference, and submission takes the occurrence-free path that sends the draft verbatim. The host receives the human-facing label instead of the owner's model form and resolves nothing. The serialization guard that exists to prevent exactly this downgrade never runs, because it only fires when an occurrence survives to be serialized.
+
+This became reachable when references [became literal inline text](../feature/2026-07-27-web-file-and-session-references.md). A reference previously occupied one `U+FFFC`, a character no keystroke produces, so the scan had nothing to collide with.
+
+## Decision
+
+`InputBar` records the textarea's selection and `inputType` during `beforeinput` and passes the resulting range to `setDraft`, which the machine already accepts and prefers over its own scan. A textarea exposes the edit no other way — `getTargetRanges()` is empty for form controls.
+
+An edit that replaces a selection reports that selection, and it is the range outright; the inserted length is whatever the draft grew by once the replaced range is accounted for. A caret delete replaces nothing and reports the bare caret, so its range comes from the direction `inputType` names and the number of characters the draft actually lost. The count is measured rather than assumed to be one, because a single caret gesture removes a multi-unit grapheme, a word, or a line just as readily. Chromium, WebKit, and Firefox all report the collapsed caret for `deleteContentBackward` and `deleteContentForward`, and all three derive the same range from it.
+
+Only the `insert` and `delete` families are recorded. A history replay reports wherever the caret happens to sit, which would survive every check while naming the wrong span; ignoring it leaves that path on the scan.
+
+The record is consumed once and cleared. A record whose draft length disagrees with the draft the change reports, a selection past the draft, a shrinking edit over a selection the caret cannot explain, or an undirected delete all yield no range, and the machine falls back to its scan. Paste and the boundary Backspace and Delete gestures already supplied their own ranges and are untouched.
+
+## Testing
+
+Component tests cover the trigger character typed in front of a reference, a caret Backspace, a caret Delete, a caret word delete, and a delete over a selection, asserting in each case that the occurrence survives at the shifted offset. The caret cases fail against the scan-recovered range, and the word case fails against a fixed one-character step.
+
+An assembled browser scenario drives the same gestures as real key presses against the shipped composition, which is the only place the range an engine reports for them can be observed; its golden projects the backdrop's segments, since the decoration layer is aria-hidden and the accessibility tree cannot see the chip. A real composition driven through the browser's IME path reports the composing segment as the selection at every intermediate state, and the reference survives each one.
+
+## Alternatives considered
+
+**Disambiguate the scan with the post-edit caret.** The caret pins which of the textually equivalent readings happened, and the change event already carries it. Rejected because it keeps a reconstruction where an exact fact is available, and it cannot separate the deleted and inserted halves of a replaced selection at all.
+
+**Give references a leading marker no keystroke produces.** A private-use character in place of the literal `@` removes the collision at the representation level, and the reject list for pasted text already names that range. Rejected because it re-adds a character that every serialization, selection, and accessibility path has to strip, to buy what an exact range buys directly, and it would leave ordinary typing reconstructing its range for every other reason.
+
+**Widen reconcile to keep an occurrence when the range only touches its edge.** Rejected because the misattributed offset lands strictly inside the reference, not on its boundary, so the rule change would not reach this defect while making the intersect rule vaguer.
+
+## Consequences
+
+Every native textarea edit that reaches `onChange` now names the range it applied to, so occurrence offsets follow the edit that actually happened rather than one merely consistent with the resulting characters. Draft writes that originate in the facade rather than the DOM — `insertText` and the command-token splices among them — still carry no range and keep the scan, as do the fallbacks above.
+
+The composer now depends on `beforeinput` preceding each value change, and on `inputType` naming the direction of a caret delete. Any future edit path that mutates the value without either silently returns to the scan rather than breaking, which keeps the failure mode the old behavior instead of a wrong range.
diff --git a/.agents/notes/archived/bug-fix/2026-08-20-composer-edit-range-from-selection.zh.md b/.agents/notes/archived/bug-fix/2026-08-20-composer-edit-range-from-selection.zh.md
new file mode 100644
index 0000000000..73a3903ad6
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-20-composer-edit-range-from-selection.zh.md
@@ -0,0 +1,48 @@
+# Agent Note: 输入框的编辑自带它所作用的范围
+
+Status: implemented
+Archived: 2026-08-20
+
+[English](2026-08-20-composer-edit-range-from-selection.md) | 中文
+
+## 问题
+
+输入机器靠一个编辑范围来对齐引用 occurrence:范围之前的条目右移,之后的条目不动,被范围相交的条目失去结构化身份、以普通草稿文本留在原地。最后一条是"在引用内部编辑"的刻意含义。
+
+普通打字不提供范围。受控 textarea 的 change 事件只带结果字符串,于是机器靠扫描两份草稿的公共前后缀来还原范围。只要插入的文本与它落点处的文本重复,这个还原就是有歧义的,而贪心扫描永远以同一种方式消解歧义:把编辑尽量往后滑。
+
+引用渲染为 `@` 加标签,所以紧挨着引用前面打一个 `@` 恰好构成这种撞车。用户在引用自身的偏移处插入;扫描报告的插入位置晚一个字符,落在引用内部;reconcile 执行相交规则,删掉这个 occurrence。删除这类引用前面的一个字符会以同样方式滑动。
+
+此时草稿看上去仍然正确,却已不携带任何结构化引用,提交走的是无 occurrence 的那条路,把草稿原样发出。宿主收到的是给人看的标签而不是所有者的模型形式,什么也解析不出来。专为阻止这种降级而存在的序列化守卫从不运行,因为它只在还有 occurrence 需要序列化时才触发。
+
+这条路径是在引用[变成字面内联文本](../feature/2026-07-27-web-file-and-session-references.md)之后才可达的。此前一个引用占据一个 `U+FFFC`——任何按键都打不出的字符,扫描无从撞车。
+
+## 决策
+
+`InputBar` 在 `beforeinput` 期间记录 textarea 的 selection 与 `inputType`,并把由此得到的范围传给 `setDraft`;机器本就接受该参数,并优先于自身的扫描。textarea 没有别的途径暴露这次编辑——`getTargetRanges()` 对表单控件返回空。
+
+替换一段选区的编辑会报告那段 selection,它直接就是范围;插入长度是扣除被替换范围后草稿增长的量。折叠光标的删除不替换任何东西、只报告光标本身,因此它的范围来自 `inputType` 指明的方向加上草稿实际减少的字符数。这个数量是**测量**得到而非假定为 1,因为一次折叠手势同样可能删掉一个多码元字形、一个词或一整行。Chromium、WebKit 与 Firefox 对 `deleteContentBackward` 和 `deleteContentForward` 都报告折叠光标,三者由此推导出相同的范围。
+
+只有 `insert` 与 `delete` 两族会被记录。历史回放报告的是光标当时碰巧所在的位置,那会通过全部校验却指向错误区间;忽略它即让该路径留在扫描上。
+
+记录只消费一次即清空。记录的草稿长度与 change 报告的草稿不符、selection 越过草稿末尾、选区之上出现光标无法解释的收缩、以及方向不明的删除,这几种情况都不产出范围,机器回落到扫描。粘贴以及边界处的 Backspace 与 Delete 手势本就自带范围,未受影响。
+
+## 测试
+
+组件测试覆盖在引用正前方输入触发字符、折叠 Backspace、折叠 Delete、折叠整词删除,以及选区替换式删除,每种都断言 occurrence 在右移后的偏移处存活。折叠类用例在扫描还原的范围下失败,整词用例在固定一字符步长的实现下失败。
+
+组装层浏览器场景以真实按键对已发布组合驱动同样的手势——那是唯一能观察到引擎为这些手势报告何种范围的地方;其 golden 投影的是 backdrop 的分段,因为装饰层是 aria-hidden 的,无障碍树看不到 chip。经浏览器 IME 路径驱动的真实组合在每个中间态都把组合段报告为 selection,引用在每一步都存活。
+
+## 备选方案
+
+**用编辑后的光标位置消解扫描的歧义。** 光标能钉住若干文本等价读法中真正发生的那一种,而 change 事件本就携带它。拒绝:在已有精确事实可用时仍保留一次重建,而且它根本无法把"替换一段选区"拆成删除与插入两半。
+
+**给引用一个按键打不出的前导标记。** 用私有区字符取代字面 `@`,在表示层消除撞车,而粘贴文本的剔除名单本就点名了那个区段。拒绝:为了换取一个精确范围本就能直接换到的东西,却重新引入一个必须在所有序列化、选择和无障碍路径上剥离的字符,而且普通打字仍会因为其他原因继续重建自己的范围。
+
+**放宽 reconcile,让范围只触及边缘时保留 occurrence。** 拒绝:误判出的偏移严格落在引用内部而非边界上,规则放宽够不到这个缺陷,只会让相交规则本身更含糊。
+
+## 后果
+
+每一次经 `onChange` 到达的原生 textarea 编辑现在都指明它作用的范围,因此 occurrence 偏移跟随的是真实发生的编辑,而不是某个仅仅与结果字符一致的编辑。源自 facade 而非 DOM 的草稿写入——`insertText` 和命令 token 的替换等——仍不带范围并保留扫描,上述各类回落同样如此。
+
+输入框由此依赖 `beforeinput` 先于每次取值变更发生,并依赖 `inputType` 指明折叠删除的方向。未来任何绕过其中之一改写取值的编辑路径会静默回落到扫描而不是出错,也就是说失效模式退回旧行为,而不是一个错误的范围。
diff --git a/.agents/notes/archived/bug-fix/2026-08-20-composer-reference-decoration-keys.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-20-composer-reference-decoration-keys.i18n.yaml
new file mode 100644
index 0000000000..95cb9c6827
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-20-composer-reference-decoration-keys.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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/implemented/bug-fix/2026-08-20-composer-reference-decoration-keys.md
+2026-08-20-composer-reference-decoration-keys.md: 316d45841c658d3d65246fb7425526b10e2f6bf3
+2026-08-20-composer-reference-decoration-keys.zh.md: 90ac7c8011bb7f7f45312c25ffccb7dbbbb70505
diff --git a/.agents/notes/archived/bug-fix/2026-08-20-composer-reference-decoration-keys.md b/.agents/notes/archived/bug-fix/2026-08-20-composer-reference-decoration-keys.md
new file mode 100644
index 0000000000..316d45841c
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-20-composer-reference-decoration-keys.md
@@ -0,0 +1,40 @@
+# Agent Note: Composer reference decorations key by draft-order ordinal
+
+Status: implemented
+Archived: 2026-08-20
+
+English | [中文](2026-08-20-composer-reference-decoration-keys.zh.md)
+
+## Problem
+
+The composer backdrop renders the draft as an array of segments: plain strings, a leading claim-token mark, one element per structured reference, and one mark per plain-text reference range. React reconciles that array by key.
+
+Structured references carry an identity — the occurrence table mints an `occurrenceId` that survives every edit — so their chips key by it. Plain-text reference ranges have no such identity: `scanTextRefs` re-derives them from the draft on every render, and nothing outside that scan remembers a range between two keystrokes.
+
+Keying those ranges by their draft offset made the key change whenever earlier text changed length. React then treated the range as a different element, unmounted the mark with its nested spans and inline glyph, and mounted a replacement. Every character typed or deleted ahead of a reference rebuilt every reference after the caret, and the work grew with the reference count. [Directory-syntax ranges](../feature/2026-07-27-web-file-and-session-references.md) made that path routine: they match on `@path/` syntax without a lexicon, and each one renders an icon.
+
+## Decision
+
+A plain-text reference mark keys by its index in the offset-sorted `textRefs` list, computed where the boundary list is assembled so a skipped boundary cannot shift it. The scan already returns the ranges in draft order, so the ordinal names the render slot a range occupies, which is the only identity a scan-derived range has.
+
+Structured chips keep `occurrenceId`. The two key strategies differ because the two range kinds differ in identity, not by oversight: a range the occurrence table owns keeps its node across reordering, and a range only a scan knows keeps its node across offset shifts.
+
+A range that stops matching the scan still loses its decoration, because it disappears from `textRefs` and the ordinal it held no longer exists.
+
+## Testing
+
+A component test holds the mark element and its glyph, types a character ahead of the range, and asserts the same nodes are still mounted; it then edits the token out of match shape and asserts the decoration is gone. The test fails against an offset-derived key.
+
+## Alternatives considered
+
+**Key by the range text.** Rejected: duplicate references collide on one key, and editing inside a range changes its key, which reintroduces the remount this fixes.
+
+**Give scan-derived ranges an identity table.** Rejected: it adds mutable state whose only consumer is a render key, and the scan would have to diff against the previous draft to maintain it. An edit that breaks a match simply dropping the range on the next scan is what keeps `scanTextRefs` a pure derivation.
+
+**Drop the keys and let React match by position.** Rejected: React requires keys on elements inside an array, and the plain string segments between them already match by index, so an unkeyed element warns without changing the outcome.
+
+## Consequences
+
+Typing ahead of a reference updates text nodes only; the mark and its icon stay mounted. The backdrop's per-keystroke DOM work no longer scales with the number of references in the draft.
+
+Because the key names a position, inserting a reference ahead of existing ones reuses the earlier nodes with new content instead of re-creating them. That is correct for these marks, which hold no focus, selection, or animation state, and it is the condition any future decoration on this layer meets before it keys by ordinal.
diff --git a/.agents/notes/archived/bug-fix/2026-08-20-composer-reference-decoration-keys.zh.md b/.agents/notes/archived/bug-fix/2026-08-20-composer-reference-decoration-keys.zh.md
new file mode 100644
index 0000000000..90ac7c8011
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-20-composer-reference-decoration-keys.zh.md
@@ -0,0 +1,40 @@
+# Agent Note: 输入框引用装饰按草稿顺序序号取 key
+
+Status: implemented
+Archived: 2026-08-20
+
+[English](2026-08-20-composer-reference-decoration-keys.md) | 中文
+
+## 问题
+
+输入框 backdrop 把草稿渲染成一组片段:纯文本字符串、开头的 claim token 标记、每个结构化引用一个元素、每个纯文本引用范围一个标记。React 按 key 协调这个数组。
+
+结构化引用带有身份——occurrence 表铸造的 `occurrenceId` 在任何编辑后都保持不变——因此它们的 chip 用它作 key。纯文本引用范围没有这种身份:`scanTextRefs` 在每次渲染时从草稿重新推导它们,扫描之外没有任何东西在两次按键之间记住某个范围。
+
+用草稿偏移量给这些范围取 key,会让前面文本长度一变 key 就变。React 于是把该范围当作另一个元素,卸载带嵌套 span 和内联图标的标记,再挂载一个替代品。在引用前面输入或删除任意字符,都会重建光标之后的每一个引用,工作量随引用数量增长。[目录语法范围](../feature/2026-07-27-web-file-and-session-references.zh.md)让这条路径成为常态:它们按 `@path/` 语法匹配,不依赖 lexicon,而且每个都渲染一个图标。
+
+## 决策
+
+纯文本引用标记以它在按偏移排序的 `textRefs` 列表中的下标作 key,在组装 boundary 列表处计算,因此被跳过的 boundary 不会让它偏移。扫描本身已按草稿顺序返回范围,所以该序号命名的是范围占据的渲染槽位,而这正是扫描推导出的范围唯一拥有的身份。
+
+结构化 chip 保留 `occurrenceId`。两种 key 策略不同,是因为两类范围的身份不同,而非疏漏:occurrence 表拥有的范围在重排后保住自己的节点,只有扫描知道的范围在偏移变化后保住自己的节点。
+
+不再匹配扫描规则的范围仍然失去装饰,因为它从 `textRefs` 中消失,它占据的序号也不复存在。
+
+## 测试
+
+组件测试持有标记元素及其图标,在范围之前输入一个字符,断言仍是同一批节点;随后把 token 编辑成不再匹配的形态,断言装饰消失。该测试在偏移量 key 下失败。
+
+## 备选方案
+
+**按范围文本取 key。** 拒绝:重复引用会撞同一个 key,且在范围内部编辑会改变 key,重新引入本次修复消除的重挂载。
+
+**为扫描推导的范围建立身份表。** 拒绝:这会引入唯一消费者是渲染 key 的可变状态,而且扫描必须与上一版草稿做 diff 才能维护它。破坏匹配的编辑在下一次扫描时直接丢掉该范围,正是这一点让 `scanTextRefs` 保持为纯推导。
+
+**去掉 key,让 React 按位置匹配。** 拒绝:React 要求数组内的元素带 key,而它们之间的纯文本片段本就按下标匹配,因此无 key 元素只会告警,不改变结果。
+
+## 后果
+
+在引用之前输入只更新文本节点;标记及其图标保持挂载。backdrop 每次按键的 DOM 工作量不再随草稿中的引用数量增长。
+
+由于 key 命名的是位置,在已有引用之前插入新引用会以新内容复用先前的节点,而不是重建它们。对这些不持有焦点、选择区或动画状态的标记而言这是正确的,这也是该图层上任何未来装饰按序号取 key 前需要满足的条件。
diff --git a/.agents/notes/archived/bug-fix/2026-08-24-system-prompt-section-order-ties.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-24-system-prompt-section-order-ties.i18n.yaml
new file mode 100644
index 0000000000..b01341e7d2
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-24-system-prompt-section-order-ties.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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/implemented/bug-fix/2026-08-24-system-prompt-section-order-ties.md
+2026-08-24-system-prompt-section-order-ties.md: d92756e751e893b1d03b8892ef71ff9faac9d2c6
+2026-08-24-system-prompt-section-order-ties.zh.md: 4a822b7925a38feb254dbc534fc6153c76a93e19
diff --git a/.agents/notes/archived/bug-fix/2026-08-24-system-prompt-section-order-ties.md b/.agents/notes/archived/bug-fix/2026-08-24-system-prompt-section-order-ties.md
new file mode 100644
index 0000000000..d92756e751
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-24-system-prompt-section-order-ties.md
@@ -0,0 +1,28 @@
+# Agent Note: Equal-order system-prompt sections render in activation order
+
+Status: implemented
+Archived: 2026-08-25
+
+English | [中文](2026-08-24-system-prompt-section-order-ties.zh.md)
+
+## Problem
+
+`SystemPromptRegistry` sorts sections by `order` with a stable sort, so equal orders render in plugin-activation order. `tool:cordis` and `tool:workflow` both declared `order: 115`, while their activation order varies between clean platform compositions. ACP and SDK snapshot replays could therefore assemble the same sections in a different order from their committed `system-prompt.expected.md` files.
+
+## Decision
+
+Give the affected sequence distinct values without changing its established relative order: `tool:cordis` stays at 115, `tool:workflow` uses 115.5, `tool:ralph` stays at 116, continuable subagent guidance stays at 116.5, and child-report guidance stays at 117. Prompt text and tool schemas remain unchanged.
+
+## Alternatives considered
+
+**Normalize section order in the snapshot harness.** Rejected because the runtime, request header, and model prompt would remain sensitive to activation timing while only the fixture comparison hid the difference.
+
+**Tie-break equal orders by section name in the registry.** Rejected because it would silently reorder every existing tie. Explicit orders keep each model-visible placement local to the contributing plugin.
+
+## Consequences
+
+The Cordis and workflow guidance has a platform-independent order while Ralph remains before continuable subagent and child-report guidance. Prompt-section placements that require a stable relative position need distinct `order` values; other equal-order sections retain activation-order semantics and are outside this decision.
+
+## Testing
+
+The keyless ACP and SDK snapshot replays pin Cordis before workflow and preserve the workflow, Ralph, continuable-subagent, and child-report sequence. The full snapshot suite verifies the refreshed fixtures.
diff --git a/.agents/notes/archived/bug-fix/2026-08-24-system-prompt-section-order-ties.zh.md b/.agents/notes/archived/bug-fix/2026-08-24-system-prompt-section-order-ties.zh.md
new file mode 100644
index 0000000000..4a822b7925
--- /dev/null
+++ b/.agents/notes/archived/bug-fix/2026-08-24-system-prompt-section-order-ties.zh.md
@@ -0,0 +1,28 @@
+# Agent Note: 等序系统提示词分段按激活顺序渲染
+
+Status: implemented
+Archived: 2026-08-25
+
+[English](2026-08-24-system-prompt-section-order-ties.md) | 中文
+
+## Problem
+
+`SystemPromptRegistry` 使用稳定排序按 `order` 排列分段,因此相同 order 的分段会按插件激活顺序渲染。`tool:cordis` 与 `tool:workflow` 都声明了 `order: 115`,但两者在不同平台的全新组合中激活顺序不同。因此,ACP(Agent Client Protocol)与 SDK 的快照回放可能把相同分段组装成不同于已提交 `system-prompt.expected.md` 文件的顺序。
+
+## Decision
+
+在不改变既有相对顺序的前提下,为受影响的分段序列指定互不相同的 order:`tool:cordis` 保持 115,`tool:workflow` 使用 115.5,`tool:ralph` 保持 116,可继续运行的子代理指引保持 116.5,子代理报告指引保持 117。提示词文本与工具 schema 保持不变。
+
+## Alternatives considered
+
+**在快照 harness 中规范化分段顺序。** 已否决,因为运行时、请求标头和模型提示词仍然受激活时序影响,只有 fixture 比较会隐藏差异。
+
+**在注册表中用分段名称打破并列。** 已否决,因为这会静默重排每一组现有并列。显式 order 让每个模型可见位置都由贡献该分段的插件就地决定。
+
+## Consequences
+
+Cordis 与 workflow 指引具有不依赖平台的顺序,同时 Ralph 仍排在可继续运行的子代理指引和子代理报告指引之前。需要稳定相对位置的提示词分段必须使用互不相同的 `order`;其他等序分段仍采用激活顺序,不属于本决策的范围。
+
+## Testing
+
+无密钥 ACP 与 SDK 快照回放会固定 Cordis 排在 workflow 之前,并保留 workflow、Ralph、可继续运行的子代理和子代理报告指引的顺序。完整快照套件验证刷新的 fixture。
diff --git a/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.i18n.yaml b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.i18n.yaml
new file mode 100644
index 0000000000..87a43d82ca
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-07-30-versioned-gui-welcome-onboarding.md: 370793dd4e6d744ea61fc9319a94728dbbf3e1fe
+2026-07-30-versioned-gui-welcome-onboarding.zh.md: 7b99377d00127174d5bfd8d080107c2cb67e6fff
diff --git a/.agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.md b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.md
similarity index 99%
rename from .agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.md
rename to .agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.md
index 9c8684c051..370793dd4e 100644
--- a/.agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.md
+++ b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.md
@@ -1,6 +1,7 @@
# Agent Note: Versioned GUI welcome onboarding
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-07-30-versioned-gui-welcome-onboarding.zh.md)
diff --git a/.agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md
similarity index 91%
rename from .agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md
rename to .agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md
index 52c35bf46e..7b99377d00 100644
--- a/.agents/notes/implemented/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md
+++ b/.agents/notes/archived/feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md
@@ -1,6 +1,7 @@
# Agent Note: 版本化 GUI 欢迎引导
Status: implemented
+Archived: 2026-08-22
[English](2026-07-30-versioned-gui-welcome-onboarding.md) | 中文
@@ -10,9 +11,9 @@ GUI 的凭据引导从 DeepSeek 专用的就绪状态检查开始,但内部测
## 决策
-**设置外壳协调有序步骤。** `settings.onboarding` 仍是根作用域 list,但 `ui-settings` 会把其中各条目的 id 和顺序投影到一个协调器中,并且只挂载第一个未完成的步骤。当前注册方会收到 `complete()` 和 `openSection(id)`;所有权转移前,不会挂载后续步骤。`ui-settings-models` 现在以顺序 `-100` 注册恢复后的欢迎声明,以顺序 `0` 注册 DeepSeek 条件式凭据步骤;两者当前的共用展示由[共用弹窗引导决策](2026-08-13-shared-modal-product-onboarding.md)持有。
+**设置外壳协调有序步骤。** `settings.onboarding` 仍是根作用域 list,但 `ui-settings` 会把其中各条目的 id 和顺序投影到一个协调器中,并且只挂载第一个未完成的步骤。当前注册方会收到 `complete()` 和 `openSection(id)`;所有权转移前,不会挂载后续步骤。`ui-settings-models` 现在以顺序 `-100` 注册恢复后的欢迎声明,以顺序 `0` 注册 DeepSeek 条件式凭据步骤;两者当前的共用展示由[共用弹窗引导决策](2026-08-13-shared-modal-product-onboarding.zh.md)持有。
-**产品欢迎步骤按版本管理并归功能插件所有。** 该声明曾由[移除首次启动内测声明](../simplification/2026-08-13-remove-first-run-beta-notice.md)历史决策移除,现在以新的测试阶段文案恢复在 `ui-settings-models` 中。`ui-settings-general` 仍不注册任何引导步骤;持有当前两个步骤的插件也持有文案、store 和共用弹窗。
+**产品欢迎步骤按版本管理并归功能插件所有。** 该声明曾由[移除首次启动内测声明](../simplification/2026-08-13-remove-first-run-beta-notice.zh.md)历史决策移除,现在以新的测试阶段文案恢复在 `ui-settings-models` 中。`ui-settings-general` 仍不注册任何引导步骤;持有当前两个步骤的插件也持有文案、store 和共用弹窗。
**持久化的 `ui-onboarding` 分节持有确认状态。** 宿主端在 user-settings seam 中注册它,存入当前 `$DSH_HOME/settings.yaml`;当前欢迎 store 通过既有公开 settings API 读写其中的 `welcomeNoticeVersion`。connection 插件通过 `ctx.connection.isLoopback` 统一发布当前页面是否使用 loopback authority;hostname 判定留在 connection 包内,其他客户端插件只消费服务状态,而不导入其实现。API Proxy 在可配置提供方 namespace 之外,通过封闭的允许列表暴露这一个产品 namespace,同时不会把它的变更视为模型目录失效事件。
diff --git a/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.i18n.yaml b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.i18n.yaml
new file mode 100644
index 0000000000..4cb64e37c0
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-06-bundled-dsh-badge-skill.md: 2909736d53f8aff41ca69e705de44657bc1b4f1e
+2026-08-06-bundled-dsh-badge-skill.zh.md: de85e9476d3945cd13335ef596243bc2a126ae55
diff --git a/.agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.md b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.md
similarity index 98%
rename from .agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.md
rename to .agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.md
index 4c6fbdcb76..2909736d53 100644
--- a/.agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.md
+++ b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.md
@@ -1,6 +1,7 @@
# Agent Note: Bundled dsh badge skill
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-06-bundled-dsh-badge-skill.zh.md)
diff --git a/.agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.zh.md b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.zh.md
similarity index 83%
rename from .agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.zh.md
rename to .agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.zh.md
index f249c31f6e..de85e9476d 100644
--- a/.agents/notes/implemented/feature/2026-08-06-bundled-dsh-badge-skill.zh.md
+++ b/.agents/notes/archived/feature/2026-08-06-bundled-dsh-badge-skill.zh.md
@@ -1,12 +1,13 @@
# Agent Note: 内置 dsh 徽章 skill
Status: implemented
+Archived: 2026-08-22
[English](2026-08-06-bundled-dsh-badge-skill.md) | 中文
## 问题
-[Cordis 教程](../../../../docs/cordis-tutorial/index.md)的各个页面都使用官方「powered by dsh」徽章,但交付的 CLI(命令行界面)既没有用于在其他位置应用同样署名的可复用指令,也没有可显式选择加入的提供方。
+[Cordis 教程](../../../../docs/cordis-tutorial/index.zh.md)的各个页面都使用官方「powered by dsh」徽章,但交付的 CLI(命令行界面)既没有用于在其他位置应用同样署名的可复用指令,也没有可显式选择加入的提供方。
## 决策
diff --git a/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.i18n.yaml b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.i18n.yaml
new file mode 100644
index 0000000000..7459c96dae
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-07-workspace-picker-composer-entry.md: 023cbe09dd75015a1555103642d1b66ce75aafc9
+2026-08-07-workspace-picker-composer-entry.zh.md: 6b84885b11fb5372a51d620b40ea7d24fe7e45a2
diff --git a/.agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.md b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.md
similarity index 99%
rename from .agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.md
rename to .agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.md
index dc9c26c291..023cbe09dd 100644
--- a/.agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.md
+++ b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.md
@@ -1,6 +1,7 @@
# Agent Note: The no-Workspace composer opens the existing picker
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-07-workspace-picker-composer-entry.zh.md)
diff --git a/.agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.zh.md b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.zh.md
similarity index 89%
rename from .agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.zh.md
rename to .agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.zh.md
index 585c59b123..6b84885b11 100644
--- a/.agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.zh.md
+++ b/.agents/notes/archived/feature/2026-08-07-workspace-picker-composer-entry.zh.md
@@ -1,12 +1,13 @@
# Agent Note: 未选择 Workspace 时从编辑器打开现有选择器
Status: implemented
+Archived: 2026-08-22
[English](2026-08-07-workspace-picker-composer-entry.md) | 中文
## 问题
-[Session scope 决策](../architecture/2026-07-25-web-client-session-scope-and-provide-channel.md)会在 Workspace 存在前保留同一个常驻编辑器,但 textarea 处于禁用状态,只有较小的 Workspace chip 能打开选择器。用户首次点击最显眼、也最熟悉的输入区域时,界面不会响应,尽管同一界面已有继续操作的入口。
+[Session scope 决策](../architecture/2026-07-25-web-client-session-scope-and-provide-channel.zh.md)会在 Workspace 存在前保留同一个常驻编辑器,但 textarea 处于禁用状态,只有较小的 Workspace chip 能打开选择器。用户首次点击最显眼、也最熟悉的输入区域时,界面不会响应,尽管同一界面已有继续操作的入口。
## 决策
diff --git a/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.i18n.yaml b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.i18n.yaml
new file mode 100644
index 0000000000..27eba69e62
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-10-creator-guidance-introduce-cue.md: 2954bb9dca6bd5359ab3ed4b7e32bd8336709a10
+2026-08-10-creator-guidance-introduce-cue.zh.md: 4f818b3a444cbc7bbd4355ac8e7a883aaa4bfa51
diff --git a/.agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.md b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.md
similarity index 99%
rename from .agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.md
rename to .agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.md
index 888fee7b3d..2954bb9dca 100644
--- a/.agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.md
+++ b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.md
@@ -1,6 +1,7 @@
# Agent Note: Creator guidance lands as an introduce cue on the preset chip
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-10-creator-guidance-introduce-cue.zh.md)
diff --git a/.agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.zh.md b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.zh.md
similarity index 99%
rename from .agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.zh.md
rename to .agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.zh.md
index d80260abd1..4f818b3a44 100644
--- a/.agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.zh.md
+++ b/.agents/notes/archived/feature/2026-08-10-creator-guidance-introduce-cue.zh.md
@@ -1,6 +1,7 @@
# Agent Note: 创造模式引导以介绍动效落在预设 chip 上
Status: implemented
+Archived: 2026-08-22
[English](2026-08-10-creator-guidance-introduce-cue.md) | 中文
diff --git a/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.i18n.yaml b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.i18n.yaml
new file mode 100644
index 0000000000..6fc55e3a3e
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-11-collapsible-ask-user-question-card.md: 08e87b0d1f05f47c5bc87ef9b32cab05ef229e5c
+2026-08-11-collapsible-ask-user-question-card.zh.md: fd3b838ff174dcdb3d4994fe30b193d63f5c4d15
diff --git a/.agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.md b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.md
similarity index 99%
rename from .agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.md
rename to .agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.md
index 5c7e62749e..08e87b0d1f 100644
--- a/.agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.md
+++ b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.md
@@ -1,6 +1,7 @@
# Agent Note: Collapsible Ask-User Question Card
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-11-collapsible-ask-user-question-card.zh.md)
diff --git a/.agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.zh.md b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.zh.md
similarity index 99%
rename from .agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.zh.md
rename to .agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.zh.md
index 5f4b5851e4..fd3b838ff1 100644
--- a/.agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.zh.md
+++ b/.agents/notes/archived/feature/2026-08-11-collapsible-ask-user-question-card.zh.md
@@ -1,6 +1,7 @@
# Agent Note: 可收起的提问卡片
Status: implemented
+Archived: 2026-08-22
[English](2026-08-11-collapsible-ask-user-question-card.md) | 中文
diff --git a/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.i18n.yaml b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.i18n.yaml
new file mode 100644
index 0000000000..da756e7493
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-11-web-export-command-and-dialog.md: aba9048f26237ea01e861a5ee6e31b89429629c8
+2026-08-11-web-export-command-and-dialog.zh.md: be4a3a53b1ff75cfbe176e258fb6a73e5abfee22
diff --git a/.agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.md b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.md
similarity index 99%
rename from .agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.md
rename to .agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.md
index d28925500a..aba9048f26 100644
--- a/.agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.md
+++ b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.md
@@ -1,6 +1,7 @@
# Agent Note: Web `/export` shares the streamed Session ZIP download
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-11-web-export-command-and-dialog.zh.md)
diff --git a/.agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.zh.md b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.zh.md
similarity index 99%
rename from .agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.zh.md
rename to .agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.zh.md
index a9a9c4a5cc..be4a3a53b1 100644
--- a/.agents/notes/implemented/feature/2026-08-11-web-export-command-and-dialog.zh.md
+++ b/.agents/notes/archived/feature/2026-08-11-web-export-command-and-dialog.zh.md
@@ -1,6 +1,7 @@
# Agent Note: Web `/export` 共用流式 Session ZIP 下载
Status: implemented
+Archived: 2026-08-22
[English](2026-08-11-web-export-command-and-dialog.md) | 中文
diff --git a/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml
new file mode 100644
index 0000000000..a4c2d4ce83
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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/archived/feature/2026-08-18-product-subagent-failure-facts.md
+2026-08-18-product-subagent-failure-facts.md: b1d80cf66172ac67d38dbad873fa4cbd970a775c
+2026-08-18-product-subagent-failure-facts.zh.md: df4b14b4a243f7768240678b8d434c7aef7d48a7
diff --git a/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.md b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.md
new file mode 100644
index 0000000000..b1d80cf661
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.md
@@ -0,0 +1,81 @@
+# Agent Note: Product subagents expose bounded structured failure facts
+
+Status: implemented
+Archived: 2026-08-21
+
+English | [中文](2026-08-18-product-subagent-failure-facts.zh.md)
+
+## Problem
+
+The [Claude Code and Codex product providers](2026-08-04-claude-code-and-codex-subagent-backends.md) receive structured product failures, but a published run historically flattened most of them to the shared `error` stop reason. Product logs retained detail that the foreground parent and a [one-shot background Job](2026-08-12-product-subagent-one-shot-background-tasks.md) could not use to distinguish a product limit, an execution failure, or an early process exit.
+
+Copying SDK error text, app-server payloads, or stderr into the result would expose task text, paths, environment values, credentials, or product internals. Adding shared error fields would also make the provider-neutral [subagent seam](2026-06-21-subagent-capability-seam.md) own product version vocabularies that change independently.
+
+## Decision
+
+Each product Provider owns the mapping from its pinned official structured failures, current operation, and managed process outcome to one fixed safe diagnostic line. `SubagentResult` remains unchanged: consumers receive the existing bounded `diagnostic` string and do not parse its product-private fields. The [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) supersedes this note's complete Claude Code subtype mirror; this note continues to own the current detailed Codex categories until that provider adopts the same simplification.
+
+### Safe diagnostic
+
+The structured line has this fixed order:
+
+```text
+Product subagent failure (product: ; stage: ; category: ; HTTP status: ; exit code: ; signal: )
+```
+
+The Provider omits unavailable optional fields. Exit code and signal are independent facts and are each retained when observed. A contributing permission decision from the [non-interactive permissions decision](2026-08-15-product-subagent-noninteractive-permissions.md) follows the structured line; the latest safe permission fact remains operation-local. The shared result boundary limits the complete text to 4096 UTF-8 bytes.
+
+Successful results and local cancellation expose no failure fact. Raw product errors, stderr, tool input, paths, environment values, credentials, and protocol payloads never enter the diagnostic. Startup and cleanup rejections use the same safe line in their Error message. Original failures remain on internal cause chains; Provider Host logs and forwarded stderr remain product-local observation only.
+
+### Claude Code facts
+
+The [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) exclusively owns Claude Code categories, stages, process facts, permission ordering, and verification for Agent SDK 0.3.241 and Claude Code 2.1.241. This note carries no separate Claude category contract.
+
+### Codex facts
+
+Codex app-server 0.147.0 defines eleven string categories and five object variants. The Provider preserves `contextWindowExceeded`, `sessionBudgetExceeded`, `usageLimitExceeded`, `serverOverloaded`, `cyberPolicy`, `internalServerError`, `unauthorized`, `badRequest`, `threadRollbackFailed`, `sandboxError`, and `other`. It also preserves `httpConnectionFailed`, `responseStreamConnectionFailed`, `responseStreamDisconnected`, `responseTooManyFailedAttempts`, and `activeTurnNotSteerable`; the four connection/stream variants retain numeric `httpStatusCode`, while the active-turn variant does not expose `turnKind`. Unknown strings, objects with another variant set, malformed values, and unclassified exceptions use `unknown`.
+
+| Stage | Owned operation | Observable failure |
+| --- | --- | --- |
+| `initialize` | App-server spawn and initialize/initialized handshake | `start()` rejects with fixed safe facts and any process outcome already observed |
+| `thread-start` | Ephemeral `thread/start` request and response validation | `start()` rejects with the thread stage and any available process outcome |
+| `turn-start` | Published `turn/start` request, provisional ids, and early frames | The run resolves as `error` with a safe unknown fallback when no structured category exists |
+| `turn` | Terminal notification, final-answer selection, and error-info mapping | The complete category and optional HTTP status reach the non-completed result |
+| `process` | Managed app-server exits before another terminal path settles | The run resolves as `error` with `process-exit` and any available code and signal |
+| `teardown` | Wire close and process-tree release | `dispose()` rejects independently; startup rollback aggregation exposes both startup and teardown lines |
+
+`contextWindowExceeded` remains `max-tokens`; every other known or unknown Codex category remains `error`, and `cyberPolicy` does not become `refusal`.
+
+### Ownership and lifecycle
+
+| Fact or resource | Owner | Consumer behavior |
+| --- | --- | --- |
+| Codex error category | Codex Provider over its pinned official app-server | The Provider preserves its current structured category and uses `unknown` outside the recognized set |
+| Current failure stage | Product Provider operation | Derived at the failure site; never persisted or used as a recovery state |
+| Exit code and signal | `dsh-subprocess` process handle | The Provider displays observed values without inferring missing ones |
+| Diagnostic bytes and delivery | `dsh-subagent`, foreground tool, and Job runtime | The same bounded text is presented separately from assistant output in both scheduling modes |
+| Raw product failure | Product runtime, internal cause chain, and Host observation | It remains internal and never becomes model-visible result text |
+
+## Verification
+
+Claude Code verification is owned by the [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md). Codex package tests pin all sixteen current error-info variants, HTTP status presence and absence, all six stages, unknown fallback, stop-reason preservation, permission ordering, sanitization, cancellation, concurrency, and cleanup aggregation. The real app-server fixture produces an actual Codex `internalServerError` and covers process/protocol failure and whole-tree quiescence. The keyless ACP snapshot records the Codex diagnostic in foreground error output, a background completion notice, and `job_output`.
+
+## Alternatives considered
+
+**Return raw SDK errors, app-server payloads, or stderr.** These values can contain commands, paths, workspace content, environment values, credentials, or upstream prose. A fixed allowlisted mapping preserves actionable facts without expanding the model-visible trust boundary.
+
+**Add a shared product-error enum or structured result fields.** Claude Code and Codex version their error unions independently. A shared enum would duplicate those authorities and force unrelated Providers and consumers to track product releases.
+
+**Parse generic stderr and exception messages.** Free-form text is neither stable nor safe. Only pinned structured product fields and the managed process outcome qualify as diagnostic input.
+
+**Persist stages or add a recovery controller.** The stage is derived from the current call site only when a failure is reported. Persistence, retries, resume, and remediation need separate ownership and user contracts.
+
+**Map product limits to new shared stop reasons.** Claude Code turn and budget limits are not token-window exhaustion, and an error category does not establish refusal semantics. Existing stop reasons remain unchanged.
+
+## Consequences
+
+The parent can distinguish the current Codex budget, usage, service, policy, request, connection, stream, rollback, sandbox, and active-turn categories without receiving raw product text. The [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) owns the corresponding Claude result. Foreground and background scheduling preserve the same fact because both consume one `SubagentResult`.
+
+The diagnostic is display text rather than a new public protocol. Callers may present it but must not branch on its punctuation or product-private category names. A pinned product-version upgrade revalidates the Provider mapping and evidence without requiring every official error member to remain model-visible.
+
+This decision adds no product session persistence, retry policy, recovery state, stderr classifier, authentication or configuration taxonomy, progress stream, or human interaction path.
diff --git a/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.zh.md b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.zh.md
new file mode 100644
index 0000000000..df4b14b4a2
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.zh.md
@@ -0,0 +1,81 @@
+# Agent Note: 产品 subagent 公开有界结构化失败事实
+
+Status: implemented
+Archived: 2026-08-21
+
+[English](2026-08-18-product-subagent-failure-facts.md) | 中文
+
+## Problem
+
+[Claude Code 与 Codex 产品提供方](2026-08-04-claude-code-and-codex-subagent-backends.zh.md)会收到结构化产品失败,但已发布运行以往会把其中大多数压成共享的 `error` 终止原因。产品日志保留了细节,前台父 agent 与[一次性后台 Job](2026-08-12-product-subagent-one-shot-background-tasks.zh.md)却无法据此区分产品限制、执行失败或进程提前退出。
+
+若把 SDK 错误文本、app-server payload 或 stderr 复制进结果,就会暴露任务文本、路径、环境值、凭证或产品内部信息。若增加共享错误字段,又会让提供方无关的 [subagent seam](2026-06-21-subagent-capability-seam.zh.md)拥有彼此独立变化的产品版本词汇。
+
+## Decision
+
+每个产品提供方分别拥有从锁定版本官方结构化失败、当前操作和受管进程结果到一行固定安全诊断的映射。`SubagentResult` 保持不变:消费方仍接收现有的有界 `diagnostic` 字符串,而且不解析其中由产品私有的字段。[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)已经取代本说明对 Claude Code 完整 subtype 的镜像;在 Codex 采用同一简化前,本说明继续负责其当前详细类别。
+
+### 安全诊断
+
+结构化行采用以下固定顺序:
+
+```text
+Product subagent failure (product: ; stage: ; category: ; HTTP status: ; exit code: ; signal: )
+```
+
+提供方会省略不可用的可选字段。退出码与信号是相互独立的事实,只要已观测到就分别保留。来自[非交互权限决策](2026-08-15-product-subagent-noninteractive-permissions.zh.md)且参与失败的权限决定会跟在结构化行之后;最新的安全权限事实仍只属于当前操作。共享结果边界会把完整文本限制在 4096 个 UTF-8 字节以内。
+
+成功结果与本地取消都不公开失败事实。原始产品错误、stderr、工具输入、路径、环境值、凭证和协议 payload 绝不会进入诊断。启动与清理拒绝会在 Error 消息中使用同一安全行。原始失败保留在内部 cause 链中;提供方 Host 日志与转发的 stderr 也只作为产品本地观测。
+
+### Claude Code 事实
+
+[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)独占负责 Agent SDK 0.3.241 与 Claude Code 2.1.241 的 Claude Code 类别、阶段、进程事实、权限顺序与验证。本说明不再承载独立的 Claude 类别约定。
+
+### Codex 事实
+
+Codex app-server 0.147.0 定义十一种字符串类别与五种对象 variant。提供方会保留 `contextWindowExceeded`、`sessionBudgetExceeded`、`usageLimitExceeded`、`serverOverloaded`、`cyberPolicy`、`internalServerError`、`unauthorized`、`badRequest`、`threadRollbackFailed`、`sandboxError` 和 `other`。它还会保留 `httpConnectionFailed`、`responseStreamConnectionFailed`、`responseStreamDisconnected`、`responseTooManyFailedAttempts` 与 `activeTurnNotSteerable`;四种连接/stream variant 会保留数值 `httpStatusCode`,而 active-turn variant 不公开 `turnKind`。未知字符串、同时含其他 variant 的对象、格式错误值与未分类异常统一使用 `unknown`。
+
+| 阶段 | 归属操作 | 可观察失败 |
+| --- | --- | --- |
+| `initialize` | App-server spawn 与 initialize/initialized 握手 | `start()` 以固定安全事实和已经观测到的进程结果拒绝 |
+| `thread-start` | 临时 `thread/start` 请求与响应校验 | `start()` 以线程阶段和可用进程结果拒绝 |
+| `turn-start` | 已发布 `turn/start` 请求、暂定 id 与早到 frame | 没有结构化类别时,运行以 `error` 和安全 unknown 回退兑现 |
+| `turn` | 终态通知、最终答案选择与 error-info 映射 | 完整类别与可选 HTTP status 进入非完成结果 |
+| `process` | 受管 app-server 在另一终态路径结算前退出 | 运行以 `error` 兑现,并携带 `process-exit` 以及可用的退出码与信号 |
+| `teardown` | Wire 关闭与进程树释放 | `dispose()` 独立拒绝;启动回滚聚合会同时公开启动与 teardown 两行 |
+
+`contextWindowExceeded` 仍是 `max-tokens`;其他所有已知或未知 Codex 类别仍是 `error`,`cyberPolicy` 不会变成 `refusal`。
+
+### 所有权与生命周期
+
+| 事实或资源 | Owner | 消费方行为 |
+| --- | --- | --- |
+| Codex 错误类别 | Codex 提供方及其锁定的官方 app-server | 提供方保留当前结构化类别,并在已识别集合之外使用 `unknown` |
+| 当前失败阶段 | 产品提供方操作 | 只在失败点派生;绝不持久化,也不作为恢复状态 |
+| 退出码与信号 | `dsh-subprocess` 进程句柄 | 提供方展示已观测值,不推测缺失值 |
+| 诊断字节与送达 | `dsh-subagent`、前台工具与 Job 运行时 | 两种调度模式都把同一份有界文本与 assistant 输出分开呈现 |
+| 原始产品失败 | 产品运行时、内部 cause 链与 Host 观测 | 只保留在内部,绝不成为模型可见的结果文本 |
+
+## Verification
+
+Claude Code 验证由[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)负责。Codex 包测试固定当前全部十六种 error-info variant、HTTP status 存在与缺失、六个阶段、unknown 回退、终止原因保持不变、权限顺序、脱敏、取消、并发与清理聚合。真实 app-server fixture 会产生实际 Codex `internalServerError`,并覆盖进程/协议失败与整棵进程树完全停稳。无密钥 ACP snapshot 会在前台错误输出、后台完成通知和 `job_output` 中记录 Codex 诊断。
+
+## Alternatives considered
+
+**返回原始 SDK 错误、app-server payload 或 stderr。** 这些值可能包含命令、路径、工作区内容、环境值、凭证或上游文本。固定白名单映射可以保留可操作事实,同时不扩大模型可见的信任边界。
+
+**增加共享产品错误 enum 或结构化结果字段。** Claude Code 与 Codex 各自独立版本化错误联合。共享 enum 会复制这些权威,并迫使无关提供方和消费方跟随产品版本。
+
+**解析通用 stderr 与异常消息。** 自由文本既不稳定也不安全。只有锁定版本产品提供的结构化字段和受管进程结果可以成为诊断输入。
+
+**持久化阶段或增加恢复控制器。** 阶段只在报告失败时从当前调用点派生。持久化、重试、resume 与修复需要独立的所有权和用户约定。
+
+**把产品限制映射为新的共享终止原因。** Claude Code 的轮次和预算限制并不表示 token 窗口耗尽,错误类别也不能证明拒绝语义。既有终止原因保持不变。
+
+## Consequences
+
+父 agent 可以区分当前 Codex 的预算、用量、服务、策略、请求、连接、stream、回滚、sandbox 与 active-turn 类别,而不会收到原始产品文本。[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)负责对应的 Claude 结果。前台与后台调度会保留同一事实,因为二者都消费同一个 `SubagentResult`。
+
+诊断只是展示文本,不是新的公开协议。调用方可以呈现它,但不得根据其标点或产品私有类别名称进行分支。锁定产品版本升级时必须重新验证提供方映射与证据,但不要求每个官方错误成员都继续模型可见。
+
+本决策不增加产品会话持久化、重试策略、恢复状态、stderr 分类器、身份验证或配置分类体系、进度流或人工交互路径。
diff --git a/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.i18n.yaml b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.i18n.yaml
new file mode 100644
index 0000000000..d001e4a95c
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-18-web-home-path-tilde.md: 108674740c804a42ec3b0491505186215a9d9fcd
+2026-08-18-web-home-path-tilde.zh.md: 1f742158f62b9b7fbb8eae8be35c13adc95f3a09
diff --git a/.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.md b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.md
similarity index 99%
rename from .agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.md
rename to .agents/notes/archived/feature/2026-08-18-web-home-path-tilde.md
index b148833bab..108674740c 100644
--- a/.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.md
+++ b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.md
@@ -1,6 +1,7 @@
# Agent Note: Web UI abbreviates POSIX home paths as `~`
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-18-web-home-path-tilde.zh.md)
diff --git a/.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.zh.md b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.zh.md
similarity index 99%
rename from .agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.zh.md
rename to .agents/notes/archived/feature/2026-08-18-web-home-path-tilde.zh.md
index 9d15cd6dca..1f742158f6 100644
--- a/.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.zh.md
+++ b/.agents/notes/archived/feature/2026-08-18-web-home-path-tilde.zh.md
@@ -1,6 +1,7 @@
# Agent Note: Web UI abbreviates POSIX home paths as `~`
Status: implemented
+Archived: 2026-08-22
[English](2026-08-18-web-home-path-tilde.md) | 中文
diff --git a/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.i18n.yaml b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.i18n.yaml
new file mode 100644
index 0000000000..fbbf621db9
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-19-high-cache-hit-decimal-display.md: 83c031bd1049ec26029d2e9ba0dc5cd623c3f867
+2026-08-19-high-cache-hit-decimal-display.zh.md: 62f27e39d37cf2445ac6796030092e892d82b581
diff --git a/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.md b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.md
new file mode 100644
index 0000000000..83c031bd10
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.md
@@ -0,0 +1,51 @@
+# Agent Note: High cache-hit decimal display
+
+Status: implemented
+Archived: 2026-08-22
+
+English | [中文](2026-08-19-high-cache-hit-decimal-display.zh.md)
+
+## Problem
+
+The Web conversation stats line rounded every non-empty cache-hit ratio to an integer. Once the actual ratio passed 99%, the display hid further progress, and a ratio of at least 99.5% appeared as 100% even while uncached input or cache writes remained.
+
+Users therefore could not distinguish a nearly complete cache hit from a true full hit.
+
+## Decision
+
+`StatsLine` continues to derive the ratio from the whole-session `tokenUsage` projection owned by `@deepseek-ai/dsh-token-meter`; the projection remains the only owner of the uncached-input, cache-read, cache-write, and output counts ([projection decision](../architecture/2026-07-29-projected-token-usage-and-request-context.md)). The presentation layer changes only the text inserted into the existing `stats.cacheHit` locale template.
+
+| Actual ratio | Display |
+|---|---|
+| No billed input | Cache-hit group omitted |
+| Integer rounding is below 100% | Rounded integer |
+| Non-full ratio whose current rounding is 100% | Minimum decimal precision whose rounded result is below 100% |
+| 100% | `100%` |
+
+Every non-empty ratio starts at zero decimal places. A non-full ratio increases precision one place at a time only while rounding would produce 100%, so `99.1%` and `99.49%` remain `99%`, while `99.5%`, `99.95%`, and `99.995%` retain one, two, and three decimal places respectively. `StatsLine` uses exact small-factor comparisons over the safe-integer token counts, then scales the near-full gap only while the intermediate remains within that range. This avoids floating-point tie errors without imposing a precision cap or substitute label. A full hit does not carry a redundant decimal. The same derived string feeds the inline row and its overflow tooltip.
+
+## Ownership and lifecycle
+
+Token-meter continues to fold usage from the complete durable session log. `StatsLine` performs a synchronous display derivation whenever the standard projection value changes. It introduces no setting, stored percentage, event, wire field, client state, or recovery path.
+
+Live updates, reload replay, and reconnect recovery all restore the same `tokenUsage` counts and run the same display function. A missing projection still omits every token group, and a zero input denominator still omits only the cache-hit group.
+
+## Verification
+
+The component spec pins the zero denominator, ordinary integer rounding, half-step rounding at several decimal precisions, each precision boundary through three decimal places, a near-full cumulative sample that needs fourteen decimal places, the true `100%` result, both locales, and equality between inline and tooltip values. The assembled `lifecycle-chrome` replay sidecar selects `9,950 / 10,000 = 99.5%` as a deterministic ratio that integer rounding would misreport as 100% while the base session fixture remains recordable; the live assertion and post-reload browser snapshot both display `99.5%` without another model call.
+
+## Alternatives considered
+
+**Keep integer rounding for every ratio.** Rejected because it hides all movement above 99% and still reports some non-full hits as 100%.
+
+**Truncate the high band to one decimal.** Rejected because `99.95%`, `99.995%`, and still closer ratios all collapse to `99.9%` instead of retaining the minimum precision that distinguishes them from a full hit.
+
+**Cap precision and use a substitute such as `<100%`.** Rejected because the exact cumulative counts can produce the required numeric result, and a cap would make display behavior depend on an arbitrary presentation limit.
+
+**Show one decimal at every ratio.** Rejected because the additional low-band motion adds noise and changes the established display where integer precision is sufficient.
+
+**Persist a display percentage in token-meter.** Rejected because the projection already carries the exact counts, while presentation precision belongs to the Web stats line. A second stored value would duplicate derivable state and expand replay and wire responsibilities.
+
+## Consequences
+
+High cache-hit sessions remain visually stable until integer rounding would falsely report a full hit, then expose only the decimal places needed to preserve that distinction. Extremely close non-full ratios can therefore produce long decimal strings; this is the accepted cost of having no arbitrary precision cap or nonnumeric fallback. Every delivery and recovery path stays on the existing durable projection lifecycle.
diff --git a/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.zh.md b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.zh.md
new file mode 100644
index 0000000000..62f27e39d3
--- /dev/null
+++ b/.agents/notes/archived/feature/2026-08-19-high-cache-hit-decimal-display.zh.md
@@ -0,0 +1,51 @@
+# Agent Note: 高缓存命中率的小数显示
+
+Status: implemented
+Archived: 2026-08-22
+
+[English](2026-08-19-high-cache-hit-decimal-display.md) | 中文
+
+## 问题
+
+Web 会话统计行会把所有非空缓存命中率舍入为整数。真实比率超过 99% 后,显示会隐藏后续提升;比率达到 99.5% 时,即使仍有未缓存输入或缓存写入,也会显示为 100%。
+
+用户因此无法区分接近完整的缓存命中与真实满命中。
+
+## 决策
+
+`StatsLine` 继续从 `@deepseek-ai/dsh-token-meter` 所拥有的完整会话 `tokenUsage` 投影派生比率;该投影仍是未缓存输入、缓存读取、缓存写入与输出计数的唯一所有方([投影决策](../architecture/2026-07-29-projected-token-usage-and-request-context.zh.md))。展示层只改变插入现有 `stats.cacheHit` locale 模板的文本。
+
+| 真实比率 | 显示结果 |
+|---|---|
+| 没有计费输入 | 省略缓存命中分组 |
+| 整数舍入结果低于 100% | 舍入后的整数 |
+| 当前舍入结果为 100% 的非满命中 | 舍入结果低于 100% 所需的最少小数位 |
+| 100% | `100%` |
+
+所有非空比率都从零位小数开始。非满命中只有在舍入结果会成为 100% 时才逐位增加精度,因此 `99.1%` 与 `99.49%` 仍显示为 `99%`,而 `99.5%`、`99.95%` 与 `99.995%` 分别保留一位、两位与三位小数。`StatsLine` 对安全整数 token 计数执行精确的小因子比较,并且只在中间值仍处于该范围内时缩放接近满命中的差值。该算法既避开浮点临界值误差,也不设置精度上限或替代文案。真实满命中不会携带多余的小数。同一份派生字符串同时用于行内统计与溢出 tooltip。
+
+## 归属与生命周期
+
+token-meter 继续从完整持久会话日志折叠用量。标准投影值变化时,`StatsLine` 同步派生显示文本。本决策不引入设置、持久百分比、事件、协议字段、客户端状态或恢复路径。
+
+实时更新、刷新回放与重连恢复都会还原同一组 `tokenUsage` 计数,并运行同一个显示函数。投影缺失时仍会省略全部 token 分组;输入分母为零时仍只省略缓存命中分组。
+
+## 验证
+
+组件测试固定了零分母、普通整数舍入、多个小数精度上的半步舍入、直至三位小数的各个精度边界、需要十四位小数的近满累计样本、真实 `100%`、两种 locale,以及行内值与 tooltip 值的一致性。组装后的 `lifecycle-chrome` replay sidecar 将 `9,950 / 10,000 = 99.5%` 选作确定性测试输入;该比率按整数舍入会误报为 100%,同时基础会话 fixture 仍可重录。活跃页面断言与刷新后的浏览器快照都会显示 `99.5%`,且不会产生额外模型调用。
+
+## 备选方案
+
+**对所有比率继续使用整数舍入。** 不予采纳,因为它会隐藏 99% 以上的全部变化,并继续把部分非满命中显示为 100%。
+
+**把高位区间向下截取到一位小数。** 不予采纳,因为 `99.95%`、`99.995%` 以及更接近满命中的比率都会坍缩为 `99.9%`,无法保留区分真实满命中所需的最少精度。
+
+**限制精度并使用 `<100%` 等替代文案。** 不予采纳,因为精确累计计数能够产生所需的数值结果,而精度上限会让显示行为依赖任意的展示限制。
+
+**所有比率都显示一位小数。** 不予采纳,因为低位区间的额外变化会增加无效抖动,并改变整数精度已经足够的既有显示。
+
+**在 token-meter 中持久化显示百分比。** 不予采纳,因为投影已经携带精确计数,而展示精度属于 Web 统计行。第二个持久值会复制可派生状态,并扩大回放与协议职责。
+
+## 后果
+
+高缓存命中率会保持稳定的整数显示,直到整数舍入会错误地报告满命中;此时界面只展示维持区分所需的小数位。极接近满命中的非满比率可能因此产生较长的小数字符串,这是不设置任意精度上限或非数值回退所接受的代价。所有交付与恢复路径继续沿用既有持久投影生命周期。
diff --git a/.agents/notes/archived/manifest.json b/.agents/notes/archived/manifest.json
index 2c9391bc96..479a150d56 100644
--- a/.agents/notes/archived/manifest.json
+++ b/.agents/notes/archived/manifest.json
@@ -43,6 +43,9 @@
"architecture/2026-07-28-dsh-native-typescript-source-launch.i18n.yaml": "sha256:af071e07bce5d9bc8f3df65fed9dcd9b3779a98c5864badbd530363bda021b55",
"architecture/2026-07-28-dsh-native-typescript-source-launch.md": "sha256:1b56e3454277ace713e2a01c4da538c756c45bf633fd24d7b16443d584afac5d",
"architecture/2026-07-28-dsh-native-typescript-source-launch.zh.md": "sha256:8c0f97472c2c89d2c19ae5cfa68c6e67f32b50960b08b60b46496f78ea6ffad1",
+ "architecture/2026-08-11-plugin-settings-tabs.i18n.yaml": "sha256:0365da2b317fc5f94dd190064198565f4c624afc91d2e62161ab9170f79d11bc",
+ "architecture/2026-08-11-plugin-settings-tabs.md": "sha256:fdd92cfe55b6c4cd31b3f768dd46a2ecf129a04c9818249cbdd33857cf722bbf",
+ "architecture/2026-08-11-plugin-settings-tabs.zh.md": "sha256:8993df1a0178aba1ea35c460ee67c522900344a4b386287bba9dfac2bfb87efa",
"bug-fix/2026-07-20-code-mode-result-card-completeness.i18n.yaml": "sha256:1035dae11d049d32ab09fd7d4f950eceae44bf46ba498b3cfaf3c75102b9fb64",
"bug-fix/2026-07-20-code-mode-result-card-completeness.md": "sha256:6ca2c9d4df98be18813ef38b7462db880900b5bcd6944fbcd1b8f2258006b93e",
"bug-fix/2026-07-20-code-mode-result-card-completeness.zh.md": "sha256:ed85fa7f935e5f525d566bc37a92014614983e649c75de9a9f244939097a7991",
@@ -85,6 +88,9 @@
"bug-fix/2026-07-30-web-details-default-closed.i18n.yaml": "sha256:2af5559d727f3e4afdd4946eaf89ac212c81db611db78dbd9bfabb1c4661db17",
"bug-fix/2026-07-30-web-details-default-closed.md": "sha256:27a280a817c8048718bb22927e7d9572cf99ffd0c044631e99e0fd6ea236876f",
"bug-fix/2026-07-30-web-details-default-closed.zh.md": "sha256:e047c7d02cf4b95b0c7f78f4b79af254091294b05cc75e98a8bb860ae2074189",
+ "bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.i18n.yaml": "sha256:36fc626dcbf1e276a36713e85860752cef0b36a5881f2493bdeb6d9654621b02",
+ "bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md": "sha256:3ece47f91ee5f7354ef73ca0562aafeec19f89a19d9a64c9e0a565fe6d8c2049",
+ "bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md": "sha256:578e772ecbc1a4a39bddbb0a9f3fdbf67c70ff8c8952cc80d2caa3d8b76e9b36",
"bug-fix/2026-07-31-hero-visible-while-blank-session-opens.i18n.yaml": "sha256:42218a762ce0141d3cb43deb6c688d3705cdc4405e03851d486c78f3d25b70ef",
"bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md": "sha256:a40992e89736131f5c487e5357848f14accd06e135dbec9ce242c968a5b11d43",
"bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md": "sha256:e0cc576bc1c196affc9220ddabf15d735c347029c530c56454f0e585979101e1",
@@ -94,12 +100,33 @@
"bug-fix/2026-08-03-tui-long-session-render-costs.i18n.yaml": "sha256:f65f7bf8fc84c7a1f022ee393c8d969c06d9bde8bed3a0206de86fb35b246ac6",
"bug-fix/2026-08-03-tui-long-session-render-costs.md": "sha256:6ecf2ef831f527f361ade18a882d79bc6eccf15cc676d05728e7753f41cde051",
"bug-fix/2026-08-03-tui-long-session-render-costs.zh.md": "sha256:5f44e707b332e13fa06d625212173ea055c1c3c0aee60888435a0ff099ec6037",
+ "bug-fix/2026-08-04-large-history-pagination-call-stack.i18n.yaml": "sha256:9bb1ceec013521116ee73eb9ec28c5708ae9520d6e53dcd4a3621fd2283b215c",
+ "bug-fix/2026-08-04-large-history-pagination-call-stack.md": "sha256:38c5afd347b131abd6b73634d25210d593bcb1fd72c7ba501bad0b33fb639810",
+ "bug-fix/2026-08-04-large-history-pagination-call-stack.zh.md": "sha256:2a2790b3b3400c747e20b998edfa96788b4035ccfa5fd4100dbc9a0e694ed30e",
+ "bug-fix/2026-08-06-plan-narrow-viewport-regression.i18n.yaml": "sha256:fe0539da9ce4015c6deaf585350e586e99d86e0073a36e131b6f1f62cc13382b",
+ "bug-fix/2026-08-06-plan-narrow-viewport-regression.md": "sha256:ccecdf52213dd1f6ab9935db31906520b83a7d9166f612376877d612230d1331",
+ "bug-fix/2026-08-06-plan-narrow-viewport-regression.zh.md": "sha256:be10805f0cd5a4f0812c883ab7f3e1e9396b579be455696d5cd726434a26b3e1",
"bug-fix/2026-08-10-web-favicon-dark-mode.i18n.yaml": "sha256:859c4399f9a017a68ba89552fdafa05e73c0599d94cee9551c84ea5b749a14f3",
"bug-fix/2026-08-10-web-favicon-dark-mode.md": "sha256:4d17e247abd76ae3aed5fb4e075fd66a2838292f89f7021c82a79fe37ed905e6",
"bug-fix/2026-08-10-web-favicon-dark-mode.zh.md": "sha256:7bbff8a3b7061c127afcc75cd2a8043b02a999b78c0180edd8f7e4807fcfe71d",
+ "bug-fix/2026-08-11-preset-card-description-clamp.i18n.yaml": "sha256:d50452503b59aa22c81617888f9391f31f12a779c4b18efb2b4b6de1bd9702a6",
+ "bug-fix/2026-08-11-preset-card-description-clamp.md": "sha256:7eb8db697f3ad3dea8c0a6045331c05730a010404a89e2b08348cb7b0fad26c8",
+ "bug-fix/2026-08-11-preset-card-description-clamp.zh.md": "sha256:6d2f7b55ce02275a45adfdd853805e7daf2d6534929b77beb86685a54fc34f85",
"bug-fix/2026-08-12-collapsed-sidebar-shared-entry-motion.i18n.yaml": "sha256:3ce4f6e39e173fc304bf64deca9c95bcddc1dbb492e065ca8c267a7a40788588",
"bug-fix/2026-08-12-collapsed-sidebar-shared-entry-motion.md": "sha256:7b169aa4543edfc965de5a8b7b9e60aa9d9d5218693cd0b57908e2d482280723",
"bug-fix/2026-08-12-collapsed-sidebar-shared-entry-motion.zh.md": "sha256:88db36c698800bf55c3c7531d6f92665576d978c29c15ff7d74215fb93376cb1",
+ "bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.i18n.yaml": "sha256:23c26323f92a2172fd30fd724177b84d012cf4e18f1eff79ab092d4e0687ad4e",
+ "bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.md": "sha256:f9edea8501df36d444d84790ef9b0ae5bed4283a9cc5a5403800b80908f3db39",
+ "bug-fix/2026-08-13-safari-textarea-soft-wrap-reflow.zh.md": "sha256:ddcf6bb67823d19dc98964fcb9d663a10bcf663573394cfd7b235d9801d6525a",
+ "bug-fix/2026-08-20-composer-edit-range-from-selection.i18n.yaml": "sha256:c91ed2d9cb2a9891011fcbbe46885bc1808e36831279d56bc5cea0b9b1515b55",
+ "bug-fix/2026-08-20-composer-edit-range-from-selection.md": "sha256:e36920dee0318a35eaf49bff8c574698902f3be51d6115d40a3f97fa1436bd47",
+ "bug-fix/2026-08-20-composer-edit-range-from-selection.zh.md": "sha256:41f44adc93797cf9073f19f954b6ac87147a2e6806f1ad051c80c3423f0175ae",
+ "bug-fix/2026-08-20-composer-reference-decoration-keys.i18n.yaml": "sha256:cadf1de336aa2756d1bc1c20c7679449390b0a7a4217fe9602996801b6bc1958",
+ "bug-fix/2026-08-20-composer-reference-decoration-keys.md": "sha256:0093eabd710f10ae1faca53be01c9404a9d63cf6a2cf4dbf226e458e6315e201",
+ "bug-fix/2026-08-20-composer-reference-decoration-keys.zh.md": "sha256:a5fb2a748cf6ff8353d536448a5469e731157ccc2d0bb43210ea5dc44dd8ed31",
+ "bug-fix/2026-08-24-system-prompt-section-order-ties.i18n.yaml": "sha256:f7a20bddd4544738ec0dbbfc52ea931f42317defa1674beb9a3c0daebd52fc2d",
+ "bug-fix/2026-08-24-system-prompt-section-order-ties.md": "sha256:108a97346eb7a62f1ab01f48dbb9fdd965e8991f53e382b0f501b916af0e9e23",
+ "bug-fix/2026-08-24-system-prompt-section-order-ties.zh.md": "sha256:3deaddfcf9736b3ff8d61b51093d7e46fdcc86103705033e4aa4c9d043794b16",
"feature/2026-06-14-acp-agent-client-protocol.i18n.yaml": "sha256:006795baa43ae962a8d125cc0f1e9f134bc2ee9fb758b6e7669e3fa0126e1918",
"feature/2026-06-14-acp-agent-client-protocol.md": "sha256:6828c0af74bb3fb96206ca6b21c0e56a000b50e4744aad4bc2c05092f3a5a31b",
"feature/2026-06-14-acp-agent-client-protocol.zh.md": "sha256:ba104e841a1fb84edbd3b6c8119d50445b7785255a7a8d13bb9ac8a2cb4d2e69",
@@ -241,6 +268,9 @@
"feature/2026-07-30-tui-details-command.i18n.yaml": "sha256:033cea6df0a16fc68cbdb435babdc6e75c1199a8e70e1a71d87c800c40f5a044",
"feature/2026-07-30-tui-details-command.md": "sha256:a13478d4e55ec6d358209b51b541413ec75d0e20dfc22196ace28020f03f0c2d",
"feature/2026-07-30-tui-details-command.zh.md": "sha256:de9c449b98468cef34ce4f9a9d2a854a5d8905eecd61f80e27a9a0e4495e9901",
+ "feature/2026-07-30-versioned-gui-welcome-onboarding.i18n.yaml": "sha256:3d453f1a8f1a642ed569d1900009b785e582614bcabf9fede566ecbd9842e3ef",
+ "feature/2026-07-30-versioned-gui-welcome-onboarding.md": "sha256:cfaa38cfec722ac3792a4770f7733372805a6c0571f4f08519f367976b0d2379",
+ "feature/2026-07-30-versioned-gui-welcome-onboarding.zh.md": "sha256:0ce0e4616580c583725aa3d28063dc009889d7f0a260a3cdda53ff48721c1ae4",
"feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml": "sha256:4c3fc380b0512ad7c00baacd0ac610e1a78ae45374311d9bd43bab6b5e29e630",
"feature/2026-07-30-versioned-tui-first-run-welcome.md": "sha256:296f153e6c839f3743078e4f5aab3b2befc211c934835238668c57bdeae52231",
"feature/2026-07-30-versioned-tui-first-run-welcome.zh.md": "sha256:82871a9cca1fec46bb08a5b39daad28a44bb2419dea367b4ae41af3cf07bfa65",
@@ -259,9 +289,33 @@
"feature/2026-07-31-web-cards-toolrow.i18n.yaml": "sha256:f9a6ab72a77934cdcc02167c7313f08d7e9925362017b34bed7ad56c8c70fbaa",
"feature/2026-07-31-web-cards-toolrow.md": "sha256:5058f7cec4497d1cb0a5c8e77b88fddacac6eead034f3edec88e8514919b8a3e",
"feature/2026-07-31-web-cards-toolrow.zh.md": "sha256:ba84ef2e1be61211ab5ba6950b78ede3d3a979f252bc068d3e04e2c025f7bc03",
+ "feature/2026-08-06-bundled-dsh-badge-skill.i18n.yaml": "sha256:4b568d89976a71b7b3864e13b36925bf055479213739ffd4ac81614e00e93e36",
+ "feature/2026-08-06-bundled-dsh-badge-skill.md": "sha256:7b67f7c09b7e2b2ca756983a8951dad3a15786b8cd3adc6e819f316c67d31b2c",
+ "feature/2026-08-06-bundled-dsh-badge-skill.zh.md": "sha256:dcc0acb2dca596196ac034a8e86a644131c5b7fb09b184ec9d8493f93019d2b1",
+ "feature/2026-08-07-workspace-picker-composer-entry.i18n.yaml": "sha256:24a8bb2956371c7c840a662ac16dffbe04a6bb40a7296d01db86cb85da58d238",
+ "feature/2026-08-07-workspace-picker-composer-entry.md": "sha256:036212fbae6f5d7194e8c7fc9b1e7cd1c35251e9c227e895834a7d00bd5f69f8",
+ "feature/2026-08-07-workspace-picker-composer-entry.zh.md": "sha256:fb65c3330e8324f90d1270345e1ac941fc800e8caaf3b4bbee1bbb743f713262",
"feature/2026-08-08-dsh-run-headless-command.i18n.yaml": "sha256:1c2b4c5b61b9263b6267275d6fc69faeaad3cc887f0728a7ed4172d817af812b",
"feature/2026-08-08-dsh-run-headless-command.md": "sha256:7695fe7fd322377d5986f14e35f13337f4cd376405c758218a81230f6d182d1c",
"feature/2026-08-08-dsh-run-headless-command.zh.md": "sha256:113c14a36c64d2facc8ae46f37c7aa76359d8cacb9c18fcba26a723f15d036fb",
+ "feature/2026-08-10-creator-guidance-introduce-cue.i18n.yaml": "sha256:74f519839f0cf82c7304bdeae41ae1cab8bb930bfb94f79ab44708acd3b72128",
+ "feature/2026-08-10-creator-guidance-introduce-cue.md": "sha256:3e25409dda498de150de18943ee332e1760963e377a40a365902b66f667fdc9f",
+ "feature/2026-08-10-creator-guidance-introduce-cue.zh.md": "sha256:203847010cab9e9d13c3969f17921d3a5aa0d69377eccfef555c7ff96572f162",
+ "feature/2026-08-11-collapsible-ask-user-question-card.i18n.yaml": "sha256:9c0873bbb1437bcd5025f5859e1dc447a6b936f19c2c2ad2250521a3aa773a12",
+ "feature/2026-08-11-collapsible-ask-user-question-card.md": "sha256:4f3b3f5d7020fefbbac8a3c36a97642721ef14a0476a7d8117bde8a128d25f42",
+ "feature/2026-08-11-collapsible-ask-user-question-card.zh.md": "sha256:e7186c92f77d337a875f981ae39b16331a1c5466a948415bcacfe108ad98fb63",
+ "feature/2026-08-11-web-export-command-and-dialog.i18n.yaml": "sha256:db7d523a2a1f82a86f532661bd2953ee8538d971d91f886e4bd4e0d88f7226b2",
+ "feature/2026-08-11-web-export-command-and-dialog.md": "sha256:ec44b47589ca7924018dc24f7fa73379a97b8f053d9e8ccce2aebb600230e47b",
+ "feature/2026-08-11-web-export-command-and-dialog.zh.md": "sha256:ad28e67d397c87300cfe1705ba3d206cc4d054e07f5647c095c718ac8cf4ec98",
+ "feature/2026-08-18-product-subagent-failure-facts.i18n.yaml": "sha256:0aa7a873fdd878ee7f4b0a850ecf16d7b652b4f85de979acb7efcdf90883b6c1",
+ "feature/2026-08-18-product-subagent-failure-facts.md": "sha256:f7e05703c44106359798e6e4b76e442a4107b62ff0363554382d4767e4806788",
+ "feature/2026-08-18-product-subagent-failure-facts.zh.md": "sha256:19d2619fb5b5c6e40305dd82432d837357afa433ab735504ec204a2c25582ce6",
+ "feature/2026-08-18-web-home-path-tilde.i18n.yaml": "sha256:f151e3e3514f59784fc646c2feb3075dc954c65110d48c2cc482ad486fc0b86f",
+ "feature/2026-08-18-web-home-path-tilde.md": "sha256:8c7ecf120ff8c81826160acab5fc906a2a0a14213bcd2958343cfea47328d68e",
+ "feature/2026-08-18-web-home-path-tilde.zh.md": "sha256:3486c5b42aed5bcadf12c62c5e1e6cf7c1b493fc1085ad7d154cdf2ec34076cc",
+ "feature/2026-08-19-high-cache-hit-decimal-display.i18n.yaml": "sha256:c2cb839ed676040ed62153c2aab65b677fa59739f69253af50246e79a2347620",
+ "feature/2026-08-19-high-cache-hit-decimal-display.md": "sha256:08cb68bfc379da47a05b816afac26126146d36d6248350d4380f7cb98607d573",
+ "feature/2026-08-19-high-cache-hit-decimal-display.zh.md": "sha256:9d7afe3e2fc3029fbccc643b432a01bcb3b5671750adb6945ac414ec843ca063",
"process/2026-06-11-doc-sync-enforcement.i18n.yaml": "sha256:33b6d5874427bd7a2bd82e7e2f4f482b12448b2464aef15a9c57975edb48554d",
"process/2026-06-11-doc-sync-enforcement.md": "sha256:aa2fe83d519fc30d48dff19e596e83c8922aacc9e063e14fe2cc35b769b9100e",
"process/2026-06-11-doc-sync-enforcement.zh.md": "sha256:698017bd35f030fdea3eac51df9e43138c48140f504739d687b7251d13fced2b",
@@ -322,6 +376,9 @@
"process/2026-08-08-review-driven-issue-lifecycle-triggers.i18n.yaml": "sha256:4c28c59d3fc323e7cd01eff31f1fe759834719c5bede1e82b39f868970bf856d",
"process/2026-08-08-review-driven-issue-lifecycle-triggers.md": "sha256:1b0514de5d030170e91e12e4d6ba788a9247f840e82700faa385a1c0c76ab857",
"process/2026-08-08-review-driven-issue-lifecycle-triggers.zh.md": "sha256:028d78d61f603d8bac64c4cce20b393a78f8e029d3bb4976e79a47ecaefa6032",
+ "process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml": "sha256:dde0041399b253e3758045f0858488db8178ffc563ce889c8b396c87af6c3730",
+ "process/2026-08-12-documentation-site-navigation-and-chrome.md": "sha256:56cb836ed862378afd33eb5c1a9dc159958b35a0aed3bf4336fcf26ab0b84b8b",
+ "process/2026-08-12-documentation-site-navigation-and-chrome.zh.md": "sha256:f2dd4adde38a09fe312866a1e6dad0f465684d809287862f40f1a488acd4fe18",
"simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.i18n.yaml": "sha256:ad3d1263cb0051b885173bf064de62065e2c646ccaae2d7250723da3b4eab90c",
"simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md": "sha256:8fb061d51c8c23b47d2367814bab3623c6d5b972f38d207a273caa9030b579bd",
"simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md": "sha256:2ffeaca91f82844a5616d6dcce6b4af514bb8a7c46f78e47f668b204ac6edc04",
@@ -406,6 +463,18 @@
"simplification/2026-08-03-explicit-config-dsh-entrypoint.i18n.yaml": "sha256:5466161f3fb8f2e8117fe8ff242675cc9fe9ef264d1e29b9bc586891c73c051a",
"simplification/2026-08-03-explicit-config-dsh-entrypoint.md": "sha256:f23accae7d05c2e75cb73ec69b492307f1ce7526ecfa9f6b12a621e02fd1a0c3",
"simplification/2026-08-03-explicit-config-dsh-entrypoint.zh.md": "sha256:a32d2c6ecf748a16a2c35b59cd2da2fda75769e3ab24be6a2e026d8655466db4",
+ "simplification/2026-08-11-cmdline-program-action.i18n.yaml": "sha256:e33b6dee66e23beabf03275e4e4f15134d23a82740ae7be6afd28c11c3163fca",
+ "simplification/2026-08-11-cmdline-program-action.md": "sha256:e6a274bd92a35c98ea24704161b408507876de3162c0f640b4bc70a86ab4d86f",
+ "simplification/2026-08-11-cmdline-program-action.zh.md": "sha256:bd213ad65ea6129c5360f28b2f52e6f3e224a58d07f56da190702939e7b402ee",
+ "simplification/2026-08-11-quickstart-documentation-home.i18n.yaml": "sha256:548c0ff16d40fed3b3318b0b9a26e11d53a60582ff457098a212fc64e7d67eac",
+ "simplification/2026-08-11-quickstart-documentation-home.md": "sha256:21946a828417aca4a214a874a35e88fe5a3e5989c330421f3849937b35bb9a9b",
+ "simplification/2026-08-11-quickstart-documentation-home.zh.md": "sha256:cb292a428d427cf36aff0a184347f0ab653331edb874daf3c5b58a0d1f8e6964",
+ "simplification/2026-08-13-remove-first-run-beta-notice.i18n.yaml": "sha256:51267b74e39544991bfe606e3f749a26914162e454cf357f26223a6ed8de5fad",
+ "simplification/2026-08-13-remove-first-run-beta-notice.md": "sha256:7ef5c712b8dff1152becee6a3f800acd5f7589d7b000f01544f57b175660bcc1",
+ "simplification/2026-08-13-remove-first-run-beta-notice.zh.md": "sha256:f899c79f838b97d1eea4a118de2cf00a97bae910d86d4aabdc447b4e02fb585f",
+ "simplification/2026-08-19-knip-config-cleanup.i18n.yaml": "sha256:ca8f5726aed57ce376c3fbd8b70113e235f3ba37dbf290683157fb4bf143ab13",
+ "simplification/2026-08-19-knip-config-cleanup.md": "sha256:18c61713b3358d3019dac096afc26ce8e5189002f626b25e858dfc5e6f626c8d",
+ "simplification/2026-08-19-knip-config-cleanup.zh.md": "sha256:b8ff16089c1a331603bb80278544c637cb16c1fa3bcfca3c5e1187152a1a0947",
"testing/2026-06-20-remove-redundant-snapshot-log-expected-output.i18n.yaml": "sha256:4177012c0821a8c22499852ecdf096af56d7263cb91c5d9d1bcd552cc26a3e00",
"testing/2026-06-20-remove-redundant-snapshot-log-expected-output.md": "sha256:45234e7cc04b6010c6141f8d5924c04547300098f96262d423c50108e7c7011a",
"testing/2026-06-20-remove-redundant-snapshot-log-expected-output.zh.md": "sha256:15e5a4ad3dee0bb711480cabe45cd97ec37bbdba19c2c2b47d1e9c203b07a48b",
@@ -429,6 +498,9 @@
"testing/2026-07-18-tui-terminal-state-snapshots.zh.md": "sha256:26750f240f6c8a7b28746f62fe161b357e9c5dd52867cc7037399f1ed6ff37fa",
"testing/2026-07-26-execa-for-test-subprocess-plumbing.i18n.yaml": "sha256:dd45cddb591b892739b75b0c180bde7f14008f4769227b863571475be295e1e0",
"testing/2026-07-26-execa-for-test-subprocess-plumbing.md": "sha256:1f45a69d0a7367ec5afbf112a77b355339b35270af8ff52696bee879cdf770d3",
- "testing/2026-07-26-execa-for-test-subprocess-plumbing.zh.md": "sha256:8a24bdc8376373d7a97f65cefc07078824bf918d6a9934056a025ecfafe8634b"
+ "testing/2026-07-26-execa-for-test-subprocess-plumbing.zh.md": "sha256:8a24bdc8376373d7a97f65cefc07078824bf918d6a9934056a025ecfafe8634b",
+ "testing/2026-08-12-required-python-runtime-pull-request-ci.i18n.yaml": "sha256:741e7e58e5e8a9c82d901c4a16a70cea9bd256eac0e94179b5a24a231bb9fe1f",
+ "testing/2026-08-12-required-python-runtime-pull-request-ci.md": "sha256:1f1273d7a550667533e29c76efd148aebf57581a91729c877b44a5e43a52d9ad",
+ "testing/2026-08-12-required-python-runtime-pull-request-ci.zh.md": "sha256:6b9bf126c6b83d9b21e135d38df677c0d5623168b4353c6ddb706f76762c2193"
}
}
diff --git a/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml
new file mode 100644
index 0000000000..439c0c1d47
--- /dev/null
+++ b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-12-documentation-site-navigation-and-chrome.md: f33f017d54bcbb3583f37be27dcd6c69952bc66a
+2026-08-12-documentation-site-navigation-and-chrome.zh.md: 7f3ff5c829c561167d8e2475cd1c2adf050975be
diff --git a/.agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.md b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.md
similarity index 99%
rename from .agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.md
rename to .agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.md
index 03cd44b94f..f33f017d54 100644
--- a/.agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.md
+++ b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.md
@@ -1,6 +1,7 @@
# Agent Note: Documentation-site navigation and repository chrome
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-12-documentation-site-navigation-and-chrome.zh.md)
diff --git a/.agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md
similarity index 99%
rename from .agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md
rename to .agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md
index d0972f909e..7f3ff5c829 100644
--- a/.agents/notes/implemented/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md
+++ b/.agents/notes/archived/process/2026-08-12-documentation-site-navigation-and-chrome.zh.md
@@ -1,6 +1,7 @@
# Agent Note: 文档站导航与仓库 chrome
Status: implemented
+Archived: 2026-08-22
[English](2026-08-12-documentation-site-navigation-and-chrome.md) | 中文
diff --git a/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.i18n.yaml b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.i18n.yaml
new file mode 100644
index 0000000000..69735dfe18
--- /dev/null
+++ b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-11-cmdline-program-action.md: 96cbe2342eef90e68dece3c78b12a2de1bbea7c0
+2026-08-11-cmdline-program-action.zh.md: f5a9fea1447c78c9f099d3b54acd5b90a21aa503
diff --git a/.agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.md b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.md
similarity index 99%
rename from .agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.md
rename to .agents/notes/archived/simplification/2026-08-11-cmdline-program-action.md
index 40c4dae1d3..96cbe2342e 100644
--- a/.agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.md
+++ b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.md
@@ -1,6 +1,7 @@
# Agent Note: parseCmdline runs the program's own commander action
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-11-cmdline-program-action.zh.md)
diff --git a/.agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.zh.md b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.zh.md
similarity index 85%
rename from .agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.zh.md
rename to .agents/notes/archived/simplification/2026-08-11-cmdline-program-action.zh.md
index 91036f1c52..f5a9fea144 100644
--- a/.agents/notes/implemented/simplification/2026-08-11-cmdline-program-action.zh.md
+++ b/.agents/notes/archived/simplification/2026-08-11-cmdline-program-action.zh.md
@@ -1,12 +1,13 @@
# Agent Note: parseCmdline 运行 program 自己的 commander action
Status: implemented
+Archived: 2026-08-22
[English](2026-08-11-cmdline-program-action.md) | 中文
## Problem
-`dsh-cmdline`([应用自有命令行](../architecture/2026-08-06-app-owned-command-line.md))的 `parseCmdline` 曾带着一个自造的回调:`CmdlinePlan = (program, ctx) => T`,在解析成功后于该适配器的 catch 之内调用,使 plan 的 `program.error(...)` 与 help/解析错误共用同一条退出路径;它还带有只被测试使用、类型不健全的默认值 `(() => ({}) as T)`,以及没有任何 plan 读取的 `ctx` 参数。这整条接缝复制了 commander 本就定义的席位:命令的 action 处理器在 `parse` 内部运行,从中抛出的 `program.error(...)` 与语法拒绝一样遵循 `exitOverride`。
+`dsh-cmdline`([应用自有命令行](../architecture/2026-08-06-app-owned-command-line.zh.md))的 `parseCmdline` 曾带着一个自造的回调:`CmdlinePlan = (program, ctx) => T`,在解析成功后于该适配器的 catch 之内调用,使 plan 的 `program.error(...)` 与 help/解析错误共用同一条退出路径;它还带有只被测试使用、类型不健全的默认值 `(() => ({}) as T)`,以及没有任何 plan 读取的 `ctx` 参数。这整条接缝复制了 commander 本就定义的席位:命令的 action 处理器在 `parse` 内部运行,从中抛出的 `program.error(...)` 与语法拒绝一样遵循 `exitOverride`。
## Decision
diff --git a/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.i18n.yaml b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.i18n.yaml
new file mode 100644
index 0000000000..9ad4e8aacb
--- /dev/null
+++ b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-11-quickstart-documentation-home.md: 653c702eba4c90e52ee0539959d926ae23a98e6c
+2026-08-11-quickstart-documentation-home.zh.md: 3d21566f9e4a822d095a115a5e65bfbaa3f947df
diff --git a/.agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.md b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.md
similarity index 99%
rename from .agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.md
rename to .agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.md
index 3fd98843fc..653c702eba 100644
--- a/.agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.md
+++ b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.md
@@ -1,6 +1,7 @@
# Agent Note: Route documentation roots to quick start
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-11-quickstart-documentation-home.zh.md)
diff --git a/.agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.zh.md b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.zh.md
similarity index 88%
rename from .agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.zh.md
rename to .agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.zh.md
index 2e3890f858..3d21566f9e 100644
--- a/.agents/notes/implemented/simplification/2026-08-11-quickstart-documentation-home.zh.md
+++ b/.agents/notes/archived/simplification/2026-08-11-quickstart-documentation-home.zh.md
@@ -1,6 +1,7 @@
# Agent Note: 将文档根路由指向快速开始
Status: implemented
+Archived: 2026-08-22
[English](2026-08-11-quickstart-documentation-home.md) | 中文
@@ -12,7 +13,7 @@ Status: implemented
每个 locale 根路由都是重定向页面。`/` 将读者导向 `./guide/quickstart`,`/en/` 则把同一相对目标解析为 `/en/guide/quickstart`。当网站托管在源站的子路径下时,相对目标仍会保留配置的 `DOCS_BASE`。
-重定向由 `docs/user/index.md` 与 `docs/user/index.zh.md` 的 VitePress frontmatter 维护。对于 locale 首页,[文档网站投影器](../process/2026-07-13-documentation-site-projection.md)只发布这段 frontmatter,因此权威 Markdown 保留中英文语言切换行,且不会渲染第二个首页。投影器测试验证两个 locale 根路由都使用相对于各自 locale 的同一快速开始目标。
+重定向由 `docs/user/index.md` 与 `docs/user/index.zh.md` 的 VitePress frontmatter 维护。对于 locale 首页,[文档网站投影器](../process/2026-07-13-documentation-site-projection.zh.md)只发布这段 frontmatter,因此权威 Markdown 保留中英文语言切换行,且不会渲染第二个首页。投影器测试验证两个 locale 根路由都使用相对于各自 locale 的同一快速开始目标。
文档网站不承载产品定位和功能摘要。快速开始页面仍提供指南、开发、参考、搜索和 locale 导航。
diff --git a/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.i18n.yaml b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.i18n.yaml
new file mode 100644
index 0000000000..abe87647e3
--- /dev/null
+++ b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-13-remove-first-run-beta-notice.md: 535d0a20a5805c137551e6047f40fc5cf53153b8
+2026-08-13-remove-first-run-beta-notice.zh.md: 20626bbd9d0bd13c00d4ee66f5dbc267c2e92082
diff --git a/.agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.md b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.md
similarity index 99%
rename from .agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.md
rename to .agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.md
index 21396eb9cc..535d0a20a5 100644
--- a/.agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.md
+++ b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.md
@@ -1,6 +1,7 @@
# Agent Note: Remove the first-run beta notice
Status: implemented
+Archived: 2026-08-22
English | [中文](2026-08-13-remove-first-run-beta-notice.zh.md)
diff --git a/.agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.zh.md b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.zh.md
similarity index 75%
rename from .agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.zh.md
rename to .agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.zh.md
index 2818343804..20626bbd9d 100644
--- a/.agents/notes/implemented/simplification/2026-08-13-remove-first-run-beta-notice.zh.md
+++ b/.agents/notes/archived/simplification/2026-08-13-remove-first-run-beta-notice.zh.md
@@ -1,16 +1,17 @@
# Agent Note: 移除首次启动内测声明
Status: implemented
+Archived: 2026-08-22
[English](2026-08-13-remove-first-run-beta-notice.md) | 中文
## 问题
-GUI 每次首启都会先显示占满视口的内测声明:内部测试的定位表述,加上通过 `DSH_TELEMETRY_MODE` 开启 Session Log 上传的说明。会话遥测在 mode 未设置时已解析为 `DISABLED`([遥测默认关闭](../feature/2026-08-10-telemetry-default-off.md)),因此引导流程中关于遥测的全部内容就是一段教用户如何开启的提示,而内部测试的定位表述本身也不应出现在发布版本里。
+GUI 每次首启都会先显示占满视口的内测声明:内部测试的定位表述,加上通过 `DSH_TELEMETRY_MODE` 开启 Session Log 上传的说明。会话遥测在 mode 未设置时已解析为 `DISABLED`([遥测默认关闭](../feature/2026-08-10-telemetry-default-off.zh.md)),因此引导流程中关于遥测的全部内容就是一段教用户如何开启的提示,而内部测试的定位表述本身也不应出现在发布版本里。
## 决策
-本决策当时把首启声明从组装后的产品中整体移除,而不是改写。`ui-settings-general` 不再注册任何 `settings.onboarding` 步骤;声明组件、确认 store、文案所有者文件和 locale 键均被删除,Host 则保留 `ui-onboarding` namespace,使既有设置文档继续有效。后续的[共用弹窗产品引导](../feature/2026-08-13-shared-modal-product-onboarding.md)在 `ui-settings-models` 中恢复了一份新的简洁测试阶段声明,复用该字段与后端契约,但不会恢复已移除的接管式布局或遥测说明。遥测的开启仍是显式的部署环境变量选择,记录在 [CLI reference README](../../../../apps/cli/reference/README.md) 中;恢复后的声明不涉及如何开启遥测。
+本决策当时把首启声明从组装后的产品中整体移除,而不是改写。`ui-settings-general` 不再注册任何 `settings.onboarding` 步骤;声明组件、确认 store、文案所有者文件和 locale 键均被删除,Host 则保留 `ui-onboarding` namespace,使既有设置文档继续有效。后续的[共用弹窗产品引导](../feature/2026-08-13-shared-modal-product-onboarding.zh.md)在 `ui-settings-models` 中恢复了一份新的简洁测试阶段声明,复用该字段与后端契约,但不会恢复已移除的接管式布局或遥测说明。遥测的开启仍是显式的部署环境变量选择,记录在 [CLI reference README](../../../../apps/cli/reference/README.zh.md) 中;恢复后的声明不涉及如何开启遥测。
## 曾考虑的替代方案
diff --git a/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.i18n.yaml b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.i18n.yaml
new file mode 100644
index 0000000000..6612299cc4
--- /dev/null
+++ b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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
+2026-08-19-knip-config-cleanup.md: 56426aeb7ff53caf7828b3f252269559e596940d
+2026-08-19-knip-config-cleanup.zh.md: a74fa831f2301d9b95d5e34b003585293501c874
diff --git a/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.md b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.md
new file mode 100644
index 0000000000..56426aeb7f
--- /dev/null
+++ b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.md
@@ -0,0 +1,32 @@
+# Agent Note: Deleted stale and duplicative knip.json workspace entries
+
+Status: implemented
+Archived: 2026-08-22
+
+English | [中文](2026-08-19-knip-config-cleanup.zh.md)
+
+## Problem
+
+`knip.json` carried workspace entries that did no work. Some pointed at packages that no longer exist, and some duplicated the `packages/*/*` glob default exactly. Both kinds made the file larger — 790 lines — and signaled a config that had outgrown the packages it described, so a reader could not tell which entries protected real behavior and which were inert.
+
+## Decision
+
+Deleted 15 `workspaces` entries: 2 stale keys naming packages absent from the working tree and from `HEAD`, and 13 entries whose `entry`/`project` values were byte-identical to the `packages/*/*` glob default.
+
+- Stale keys: `packages/util/home` (removed in `4a09d9b34d`, the harness-home resolver collapse) and `packages/client/web-ui` (no directory and no git history, an orphan key). knip 6.16 does not flag stale workspace keys — that stability check arrived in knip 6.18 — so these were inert config that only deleted when their packages disappeared.
+- Glob-duplicate entries: `packages/host/webserver`, `packages/client/runtime`, `packages/core/tools`, `packages/context/tmux-context`, `packages/util/timeout`, `packages/util/output-retention`, `packages/goal/goal-round-driver`, `packages/goal/tool-goal`, `packages/util/home-paths`, `packages/fs/tool-fs-search`, `packages/client/ui-settings`, `packages/client/modules`, `packages/client/hmr`. Each declared exactly `entry: ["tests/**/*.spec.ts"]` and `project: ["src/**/*.ts", "tests/**/*.ts"]`, which equals the `packages/*/*` glob, and each package still exists, so the glob now covers it identically.
+
+The change is a deletion only: `knip.json` went from 790 to 655 lines with no behavioral change. `pnpm run knip` runs clean (zero issues, exit 0) before and after, because knip selects one workspace config per matched key (`getConfigKeyForWorkspace` uses specificity, not array merge), so a removed entry either lost an unresolvable target or fell back to an identical glob config.
+
+## Alternatives considered
+
+- Fold `zod` and other workspace-level `ignoreDependencies` up to the root. Rejected: the root `ignoreDependencies` is a repository-wide fallback, and these exemptions are deliberately workspace-scoped (the README of `cordis-host-runner` records why `src` cannot import the flagged dependency while the generated TypeRT face in `lib` needs it). Widening scope would mask a genuinely misplaced dependency in any future package.
+- Upgrade knip to 6.18+ to get an automatic stale-workspace check. Deferred: 6.32.2 (latest at the time) re-flags many `@deepseek-ai/...` test dependencies as unused, i.e. it changes analysis semantics, not just adds hints. That is a separate dependency-upgrade decision with its own CI blast radius, not part of this cleanup.
+- Keep the entries as documentation of intent. Rejected: an entry identical to the glob it sits under documents nothing beyond the glob itself, and a key naming an absent package actively misleads.
+
+## Consequences
+
+- `knip.json` is 135 lines shorter and names only packages that exist with config that differs from the glob default.
+- Still-explicit entries (54) all carry a real reason to differ — an `e2e`/fixture/tsx `entry`, a `project` outside the default, or a workspace-scoped `ignoreDependencies`.
+- knip 6.16 cannot itself detect the next stale key, so a package removal must still remember to drop its `knip.json` key; upgrading to 6.18+ (after the analysis-semantics change is separately assessed) restores that guard.
+- This realizes the "never a restatement of the default stanza" criterion of the package-inventory proposal ([topic](../../proposed/process/2026-06-20-discover-package-inventory.md)); its remaining items — the e2e entry folding and the generated inventory — stay open there.
diff --git a/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.zh.md b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.zh.md
new file mode 100644
index 0000000000..a74fa831f2
--- /dev/null
+++ b/.agents/notes/archived/simplification/2026-08-19-knip-config-cleanup.zh.md
@@ -0,0 +1,32 @@
+# Agent Note: 删除 knip.json 中失效与重复的 workspace 条目
+
+Status: implemented
+Archived: 2026-08-22
+
+[English](2026-08-19-knip-config-cleanup.md) | 中文
+
+## 问题
+
+`knip.json` 携带了大量不产生任何作用的 workspace 条目。其中一些指向已经不复存在的包,另一些与 `packages/*/*` 通配默认完全重复。这两类都让文件变大——790 行——并显现出配置已经超出了它所描述的包:读者无法分辨哪些条目在保护真实行为、哪些是惰性的。
+
+## 决策
+
+删除了 15 个 `workspaces` 条目:2 个指向工作树与 `HEAD` 中都不存在的包的失效键,以及 13 个 `entry`/`project` 与 `packages/*/*` 通配默认逐字节相同的条目。
+
+- 失效键:`packages/util/home`(在 `4a09d9b34d`,harness home 解析器的合并改动中删除)和 `packages/client/web-ui`(无对应目录、无 git 历史,是孤儿键)。knip 6.16 不会标记失效的 workspace 键——这项稳定性检查在 knip 6.18 才引入——所以这些是本应在包消失时一并删除、却残留的惰性配置。
+- 通配重复条目:`packages/host/webserver`、`packages/client/runtime`、`packages/core/tools`、`packages/context/tmux-context`、`packages/util/timeout`、`packages/util/output-retention`、`packages/goal/goal-round-driver`、`packages/goal/tool-goal`、`packages/util/home-paths`、`packages/fs/tool-fs-search`、`packages/client/ui-settings`、`packages/client/modules`、`packages/client/hmr`。每个都恰好声明了 `entry: ["tests/**/*.spec.ts"]` 和 `project: ["src/**/*.ts", "tests/**/*.ts"]`,与 `packages/*/*` 通配相等,且这些包仍然存在,因此通配现在以完全相同的方式覆盖它们。
+
+本改动只做删除:`knip.json` 从 790 行降到 655 行,行为不变。`pnpm run knip` 在改动前后都干净通过(零问题、退出码 0),因为 knip 为每个已匹配的键选取一条 workspace 配置(`getConfigKeyForWorkspace` 按特定优先、不做数组合并),所以被删条目要么丢掉了无法解析的目标,要么回退到一个完全相同的通配配置。
+
+## 备选方案
+
+- 把 `zod` 及其它 workspace 级 `ignoreDependencies` 上提到根级。否决:根级 `ignoreDependencies` 是全仓库兜底,而这些豁免是刻意限定在 workspace 的(`cordis-host-runner` 的 README 记录了为什么 `src` 无法 import 被标记的依赖、而生成的 `lib` 里的 TypeRT 契约面需要它)。扩大作用域会掩盖未来任何包里真正放错位置的依赖。
+- 升级 knip 到 6.18+ 以获得自动的失效 workspace 检查。延后:撰写时的最新版 6.32.2 会把大量 `@deepseek-ai/...` 测试依赖重新标记为未使用——也就是改变了分析语义,而不仅是新增提示。那是独立的依赖升级决定,带自己的 CI 影响面,不属于本次清理。
+- 保留这些条目作为意图的文档。否决:与它挂在下面的通配完全相同的条目,除了通配本身外不记录任何东西;而指向不存在包的键确实会误导人。
+
+## 结果
+
+- `knip.json` 缩短了 135 行,并且只列出确实存在、且配置与通配默认有差异的包。
+- 仍然显式的条目(54 个)都带有真实的特例理由——`e2e`/fixture/tsx 的 `entry`、超出默认的 `project`、或 workspace 级的 `ignoreDependencies`。
+- knip 6.16 自身无法检测下一个失效键,因此删除包时仍须记得清理它的 `knip.json` 键;升级到 6.18+(在分析语义的改动被单独评估之后)会恢复这道守卫。
+- 本改动落实了包清单提案中「绝不复述默认 stanza」的标准([议题](../../proposed/process/2026-06-20-discover-package-inventory.zh.md));其剩余项——e2e 入口折叠与生成的清单——仍在提案中保持开放。
diff --git a/.agents/notes/archived/testing/2026-08-12-required-python-runtime-pull-request-ci.i18n.yaml b/.agents/notes/archived/testing/2026-08-12-required-python-runtime-pull-request-ci.i18n.yaml
new file mode 100644
index 0000000000..d6f71ad4c3
--- /dev/null
+++ b/.agents/notes/archived/testing/2026-08-12-required-python-runtime-pull-request-ci.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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/implemented/testing/2026-08-12-required-python-runtime-pull-request-ci.md
+2026-08-12-required-python-runtime-pull-request-ci.md: e7da767f22634bd50bc4fd38b1de34677c4124e7
+2026-08-12-required-python-runtime-pull-request-ci.zh.md: 702125b0da864eb35f1fe870748cc0e314b01a39
diff --git a/.agents/notes/implemented/testing/2026-08-12-required-python-runtime-pull-request-ci.md b/.agents/notes/archived/testing/2026-08-12-required-python-runtime-pull-request-ci.md
similarity index 99%
rename from .agents/notes/implemented/testing/2026-08-12-required-python-runtime-pull-request-ci.md
rename to .agents/notes/archived/testing/2026-08-12-required-python-runtime-pull-request-ci.md
index 61b1e832be..e7da767f22 100644
--- a/.agents/notes/implemented/testing/2026-08-12-required-python-runtime-pull-request-ci.md
+++ b/.agents/notes/archived/testing/2026-08-12-required-python-runtime-pull-request-ci.md
@@ -1,6 +1,7 @@
# Agent Note: Required Python runtime pull-request validation
Status: implemented
+Archived: 2026-08-23
English | [中文](2026-08-12-required-python-runtime-pull-request-ci.zh.md)
diff --git a/.agents/notes/implemented/testing/2026-08-12-required-python-runtime-pull-request-ci.zh.md b/.agents/notes/archived/testing/2026-08-12-required-python-runtime-pull-request-ci.zh.md
similarity index 83%
rename from .agents/notes/implemented/testing/2026-08-12-required-python-runtime-pull-request-ci.zh.md
rename to .agents/notes/archived/testing/2026-08-12-required-python-runtime-pull-request-ci.zh.md
index 92bf80688d..702125b0da 100644
--- a/.agents/notes/implemented/testing/2026-08-12-required-python-runtime-pull-request-ci.zh.md
+++ b/.agents/notes/archived/testing/2026-08-12-required-python-runtime-pull-request-ci.zh.md
@@ -1,6 +1,7 @@
# Agent Note: 必需的 Python 运行时拉取请求验证
Status: implemented
+Archived: 2026-08-23
[English](2026-08-12-required-python-runtime-pull-request-ci.md) | 中文
@@ -12,9 +13,9 @@ Status: implemented
每个拉取请求都在 [CI](../../../../.github/workflows/ci.yml) 中运行必需的 `python-runtime` 作业。该作业不使用路径过滤,调用共享的[单文件可执行程序构建器](../../../../.github/workflows/build-exe-for-python-sdk.yml)构建 `node24-linux-x64`,并参与 `all checks passed`。被调用的工作流会构建真实可执行文件,运行全部无密钥 Python 完整轮次和直接二进制场景(包括两份检入的快照),构建 SDK 与运行时 wheel 包,将二者安装进干净的虚拟环境,检查可执行文件与原生 addon 的 GLIBC 依赖,并在 manylinux 2.28 容器中运行已安装的 wheel 包。
-必需作业与 [Python 发布工作流](../process/2026-08-11-python-publication-workflow.md)共用同一构建器。其并发键包含调用方工作流,因此同一 ref 上的必需 CI 与显式完整发布验证不会互相取消。完整的 linux-x64、linux-arm64 和 macos-arm64 矩阵仍属于发布验证:平台无关的运行时、SDK 与快照行为只需要一个阻断合并的原生载体,而架构相关的可执行文件、addon、wheel 包标签与部署目标行为在发布前仍需要全部发布目标验证。
+必需作业与 [Python 发布工作流](../process/2026-08-11-python-publication-workflow.zh.md)共用同一构建器。其并发键包含调用方工作流,因此同一 ref 上的必需 CI 与显式完整发布验证不会互相取消。完整的 linux-x64、linux-arm64 和 macos-arm64 矩阵仍属于发布验证:平台无关的运行时、SDK 与快照行为只需要一个阻断合并的原生载体,而架构相关的可执行文件、addon、wheel 包标签与部署目标行为在发布前仍需要全部发布目标验证。
-进阶 exe 快照会在比较前规范化不透明的会话、消息、subagent 和工作流运行标识符。因此,新增的持久化工作流事件会改变经过审阅的预期输出,但不会把随机运行标识符写入其中。极简场景的[模型可见快照](2026-08-13-python-minimal-model-visible-snapshot.md)覆盖了这份快照所占位化的已组装系统提示词、工具 schema 与消息列表。
+进阶 exe 快照会在比较前规范化不透明的会话、消息、subagent 和工作流运行标识符。因此,新增的持久化工作流事件会改变经过审阅的预期输出,但不会把随机运行标识符写入其中。极简场景的[模型可见快照](2026-08-13-python-minimal-model-visible-snapshot.zh.md)覆盖了这份快照所占位化的已组装系统提示词、工具 schema 与消息列表。
## 曾考虑的替代方案
diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml
index 0c0e629d26..98850aed4c 100644
--- a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.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/implemented/architecture/2026-06-11-content-block-vocabulary.md
-2026-06-11-content-block-vocabulary.md: a31df6a7d16ea7cba649702fdb474dab34533c1b
-2026-06-11-content-block-vocabulary.zh.md: 5ac882e9de7dea02cc6534aee99c46869cc9363f
+2026-06-11-content-block-vocabulary.md: d7d3f6b43a3f65d1421f026e5b6c2cc1ba1eadd2
+2026-06-11-content-block-vocabulary.zh.md: ed4f915dff6dcb6dbc91400f9bfa5384253aea7b
diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md
index a31df6a7d1..d7d3f6b43a 100644
--- a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md
+++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md
@@ -25,4 +25,4 @@ In-session context injection (`context/message`) and mid-turn steering originall
- Multimodal blocks return only with coordinated adapter, UI, and compaction support; see [the drop-image Agent Note](../../archived/simplification/2026-07-04-drop-image-content-block.md).
- Cache hints and assistant prefill remain absent until a shipping adapter can honor them; see the [producer-less variants](../../archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md) and [inert request knobs](../../archived/simplification/2026-07-04-drop-inert-request-knobs.md) Agent Notes.
- Every adapter pays a translation cost; the first real adapters have since validated the streaming protocol, and new adapters should continue proving their provider-specific mapping in adapter-local tests.
-- IDs that cross package boundaries are branded (`CallId`, the shared agent/session `SessionId`) — nominal typing at zero runtime cost.
+- IDs that cross package boundaries are branded (`ToolCallId`, the shared agent/session `SessionId`) — nominal typing at zero runtime cost.
diff --git a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md
index 5ac882e9de..ed4f915dff 100644
--- a/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md
@@ -12,7 +12,7 @@ harness 需要一套统一的内部消息语言,供 agent loop(智能体循
自主拥有词汇:消息是类型化内容块的数组(`text`、`reasoning`、`tool-call`、`tool-result`),其联合类型派生自可合并扩展的 `ContentBlockMap`,插件通过声明合并添加新的块类型。同一可合并扩展映射模式为所有「字符串化」字段提供类型(`MessageSource`、`FinishReason`、`TurnTrigger`、`TurnEndReason`)。流式输出采用原始分片协议;`BlockAssembler` 是唯一的共享组装实现。适配器负责转换为提供方的协议格式(wire format)——映射成本留在适配器中,正是它该在的地方。
-会话内上下文注入(`context/message`)和轮次中途 steering(中途引导)最初渲染为带标签的 user-role 信封(system-reminder 模式),而非引入新角色,因此适配器无需承担额外负担。如今两者都投影为无包装的普通用户内容;见[注入内容信封 Agent Note](../simplification/2026-07-20-unwrap-injected-content-envelopes.md)。实际适配器验证已确认此渲染方式符合当前 DeepSeek 的行为;如果未来某提供方出现不兼容,应在该适配器内处理,而非引入新的规范角色。
+会话内上下文注入(`context/message`)和轮次中途 steering(中途引导)最初渲染为带标签的 user-role 信封(system-reminder 模式),而非引入新角色,因此适配器无需承担额外负担。如今两者都投影为无包装的普通用户内容;见[注入内容信封 Agent Note](../simplification/2026-07-20-unwrap-injected-content-envelopes.zh.md)。实际适配器验证已确认此渲染方式符合当前 DeepSeek 的行为;如果未来某提供方出现不兼容,应在该适配器内处理,而非引入新的规范角色。
## 曾考虑的替代方案
@@ -25,4 +25,4 @@ harness 需要一套统一的内部消息语言,供 agent loop(智能体循
- 多模态块只有在适配器、UI 和上下文压缩(context compaction)三方协同支持后才会回归;见 [drop-image Agent Note](../../archived/simplification/2026-07-04-drop-image-content-block.md)。
- 缓存提示与 assistant prefill 在有实际适配器能兑现之前保持缺席;见[无生产者的词汇变体](../../archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)与[无端到端可用路径的请求旋钮](../../archived/simplification/2026-07-04-drop-inert-request-knobs.md) Agent Note。
- 每个适配器都需承担翻译成本;首批真实适配器已验证了流式输出协议,新适配器应继续在适配器本地测试中验证其提供方特有的映射。
-- 跨包边界的 ID 使用品牌类型(`CallId`、agent 与会话共享的 `SessionId`)——零运行时开销的名义类型。
+- 跨包边界的 ID 使用品牌类型(`ToolCallId`、agent 与会话共享的 `SessionId`)——零运行时开销的名义类型。
diff --git a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml
index e5c589dbf9..44272f7ca1 100644
--- a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.md
2026-06-11-dev-invariants-over-deep-readonly.md: 66980f1ee09c6112f72786d6c3a147aadbc57f6c
-2026-06-11-dev-invariants-over-deep-readonly.zh.md: 0d694ea84e1b7c265491e9adb64757378b4185f1
+2026-06-11-dev-invariants-over-deep-readonly.zh.md: 576e53e0b27e65f6fa071ff649509223a7bc30ff
diff --git a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md
index 0d694ea84e..576e53e0b2 100644
--- a/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-11-dev-invariants-over-deep-readonly.zh.md
@@ -32,7 +32,7 @@ TypeScript readonly 类型不是充分的运行时边界。它们在程序运行
### 包拥有的不变式配套插件检查关系
-`dsh-invariants` 注册可配置的 `ctx.invariants` 服务,本身不包含产品检查。每个包发布一个 `./invariant` 所有权配套插件;`dsh-session`、`dsh-agent`、`dsh-scope` 和 `dsh-agent-loop` 目前添加需要跟踪状态或观察另一个 seam 的规则:单调递增的序列号、轮次与步骤嵌套、工具调用/结果配对、合法的 agent(智能体)状态转换、主体正确的作用域分发,以及循环构建的请求与从其会话日志前缀重建的请求之间的相等性。全局启用和包名 regex 过滤器归该服务所有(见[包拥有的不变式服务](2026-07-19-package-owned-invariant-service.md))。
+`dsh-invariants` 注册可配置的 `ctx.invariants` 服务,本身不包含产品检查。每个包发布一个 `./invariant` 所有权配套插件;`dsh-session`、`dsh-agent`、`dsh-scope` 和 `dsh-agent-loop` 目前添加需要跟踪状态或观察另一个 seam 的规则:单调递增的序列号、轮次与步骤嵌套、工具调用/结果配对、合法的 agent(智能体)状态转换、主体正确的作用域分发,以及循环构建的请求与从其会话日志前缀重建的请求之间的相等性。全局启用和包名 regex 过滤器归该服务所有(见[包拥有的不变式服务](2026-07-19-package-owned-invariant-service.zh.md))。
当会话配套插件附加到已有会话或以种子记录初始化的会话时,它回放不可变日志以重建跟踪状态。服务为每项贡献提供一个可 dispose(资源释放)的子 fiber,因此轮次中途热重载是安全的,同时不赋予诊断逻辑对会话存储的所有权。
diff --git a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml
index 760c3fd099..868d215253 100644
--- a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.md
2026-06-11-event-sourced-sessions.md: b6d17d2db1d9b489f3d4224683b61e62be485014
-2026-06-11-event-sourced-sessions.zh.md: a78349ea2385b3c9d32870757bb607f15996196d
+2026-06-11-event-sourced-sessions.zh.md: 11e5740dc2636fc002ed7158167b1dfbb39a971d
diff --git a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md
index a78349ea23..11e5740dc2 100644
--- a/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-11-event-sourced-sessions.zh.md
@@ -24,5 +24,5 @@ MVP 要求严格的基于事件的追踪,以及完全可回放的会话(严
- 回放、追踪与遥测在结构上得到保证,而非事后附加。
- 持久化仍是插件关注点;内存存储随 dsh-session 一起提供。
-- 事件词汇可通过合并扩展(插件可添加如压缩(compaction)事件);[会话持久化](2026-06-14-session-persistence.md)在日志具备持久性后固定了其结构。
+- 事件词汇可通过合并扩展(插件可添加如压缩(compaction)事件);[会话持久化](2026-06-14-session-persistence.zh.md)在日志具备持久性后固定了其结构。
- 派生成本随日志长度增长,压缩(dsh-compaction)是预期的缓解手段,而不是改写日志。
diff --git a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml
index 8e97d86ccf..57843018c6 100644
--- a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md
2026-06-11-microkernel-event-taxonomy.md: 6cacbc30f29c863de0f8ddfa4df7251a64bc80ca
-2026-06-11-microkernel-event-taxonomy.zh.md: 2e43b57d62d8fca692ffab379d1841e6a3e61fad
+2026-06-11-microkernel-event-taxonomy.zh.md: 1c7919392b835c491b9dc606d46f638a708d2948
diff --git a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md
index 2e43b57d62..1c7919392b 100644
--- a/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-11-microkernel-event-taxonomy.zh.md
@@ -25,7 +25,7 @@ Status: implemented
## 后果
-- 每个 MVP 功能都映射到一个监听器([功能→机制映射](../../../../docs/cookbook/extension-cookbook.md#the-feature--mechanism-map)是证明义务,保持更新)。
+- 每个 MVP 功能都映射到一个监听器([功能→机制映射](../../../../docs/cookbook/extension-cookbook.zh.md#the-feature--mechanism-map)是证明义务,保持更新)。
- HMR 与 dispose 无需额外工作:监听器和注册均为 Cordis effect。
- waterfall 语义(调用 `next()` 或短路)不直观,需要教学——在 AGENTS.md 中记录,并由组合测试覆盖。
- 循环必须具备防御性:插件异常在轮次级别被隔离,来自任何扩展点的 steering(中途引导)永远不会被搁置(有回归测试保障)。
diff --git a/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.i18n.yaml
index 2e6f1ad2df..821a220d9a 100644
--- a/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.md
2026-06-11-runtime-arg-validation.md: 520823c76f147205805d306e97b5461f38b84c35
-2026-06-11-runtime-arg-validation.zh.md: 0a6ef40c93ec3550d6e991836950be849e86ede7
+2026-06-11-runtime-arg-validation.zh.md: bc2f743300be78cc2a01f027d5aca81fcb18b468
diff --git a/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.zh.md b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.zh.md
index 0a6ef40c93..bc2f743300 100644
--- a/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-11-runtime-arg-validation.zh.md
@@ -6,7 +6,7 @@ Status: implemented
## 问题
-`defineTool`([统一 schema DSL](2026-07-20-unified-json-value-schema-dsl.md))为工具作者的 `execute(args)` 提供了经 `InferArgs` 映射的类型化参数。但该类型只是对运行时值的编译期声明,而这个值实际上是模型生成的 JSON:没有任何机制强制模型遵守 schema,因此畸形调用(缺少必需键、声明为数字的位置传入字符串,或字面量超出声明的集合)会以「仅在名义上类型化」的状态到达 `execute`。工具函数体随后要么在处理结构错误的数据时崩溃,要么在不报错的情况下行为异常。
+`defineTool`([统一 schema DSL](2026-07-20-unified-json-value-schema-dsl.zh.md))为工具作者的 `execute(args)` 提供了经 `InferArgs` 映射的类型化参数。但该类型只是对运行时值的编译期声明,而这个值实际上是模型生成的 JSON:没有任何机制强制模型遵守 schema,因此畸形调用(缺少必需键、声明为数字的位置传入字符串,或字面量超出声明的集合)会以「仅在名义上类型化」的状态到达 `execute`。工具函数体随后要么在处理结构错误的数据时崩溃,要么在不报错的情况下行为异常。
## 决策
@@ -17,8 +17,8 @@ Status: implemented
## 后果
- 模型会收到有关自身畸形调用的可操作反馈,而不是遭遇不透明的崩溃,弥合了 `InferArgs` 的承诺与运行时现实之间的鸿沟。
-- 校验器与 `InferArgs` 必须保持一致;一项[属性测试](../testing/2026-06-11-property-based-testing.md)生成满足 spec 的参数并断言它们通过 `validateArgs`(同时通过针对性改坏参数来断言其会被拒绝),通过自动化检查消除这种漂移风险。
-- `ToolArgsError` 是[结构化错误分类体系](2026-06-11-structured-error-taxonomy.md)中 `HarnessError` 的子类,保留其 `code` 字段;读取 `.message` 的调用方不受该层级结构影响。
+- 校验器与 `InferArgs` 必须保持一致;一项[属性测试](../testing/2026-06-11-property-based-testing.zh.md)生成满足 spec 的参数并断言它们通过 `validateArgs`(同时通过针对性改坏参数来断言其会被拒绝),通过自动化检查消除这种漂移风险。
+- `ToolArgsError` 是[结构化错误分类体系](2026-06-11-structured-error-taxonomy.zh.md)中 `HarnessError` 的子类,保留其 `code` 字段;读取 `.message` 的调用方不受该层级结构影响。
- 校验开销相对于一次模型调用可忽略不计。
diff --git a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml
index 106164a71c..1c4eadabc1 100644
--- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.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/implemented/architecture/2026-06-13-capability-seams.md
-2026-06-13-capability-seams.md: 2a166278ea454895177fa12b58f5493276f19cd1
-2026-06-13-capability-seams.zh.md: 0874af5826960ab9e718eb07b00c12b446edfd78
+2026-06-13-capability-seams.md: 46a2c39e927e859c7eb95956d8586f3bf04c7b1c
+2026-06-13-capability-seams.zh.md: f44e3e68d2153149435b0fd0aaa5fd121cf3ecad
diff --git a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md
index 2a166278ea..46a2c39e92 100644
--- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md
+++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.md
@@ -6,7 +6,7 @@ English | [中文](2026-06-13-capability-seams.zh.md)
## Problem
-The harness has swappable capabilities — bash execution today, sandboxed/remote executors and alternative model providers tomorrow. A capability has three concerns that change at different rates and for different reasons: the *contract* (what the capability is), the *implementation* (how it runs), and the *consumer API* (what the model and other plugins program against). Bundling them in one package couples those rates of change — swapping a local executor for a sandboxed one would churn the tool schemas the model sees, even though the model-facing contract never changed.
+The harness has swappable capabilities, including shell execution and model providers. A capability has three concerns that change at different rates and for different reasons: the *contract* (what the capability is), the *implementation* (how it runs), and the *consumer API* (what the model and other plugins program against). Bundling them in one package couples those rates of change — swapping a local executor for a sandboxed one would churn the tool schemas the model sees, even though the model-facing contract never changed.
This is distinct from "who provides vs. needs a capability at runtime", which Cordis already answers with services + `inject` (a provider registers `ctx.shell`; a consumer declares `inject: ['bash']` and its fiber pends until the service exists). That mechanism is necessary but doesn't dictate package boundaries; this Agent Note does.
diff --git a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md
index 0874af5826..f44e3e68d2 100644
--- a/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-13-capability-seams.zh.md
@@ -6,7 +6,7 @@ Status: implemented
## 问题
-harness 具有可替换的能力:当前是 bash 执行,未来会有沙箱化/远程执行器和替代模型提供方。一项能力涉及三个关注点,它们以不同速率、因不同原因变化:*约定*(这项能力是什么)、*实现*(它如何运行)、*消费方 API*(模型和其他插件面向什么编程)。将三者捆绑在一个包中会耦合这些变化速率——把本地执行器换成沙箱化执行器时,模型看到的工具 schema 也会被搅动,尽管面向模型的约定从未改变。
+harness 具有可替换的能力,包括 shell 执行和模型提供方。一项能力涉及三个关注点,它们以不同速率、因不同原因变化:*约定*(这项能力是什么)、*实现*(它如何运行)、*消费方 API*(模型和其他插件面向什么编程)。将三者捆绑在一个包中会耦合这些变化速率——把本地执行器换成沙箱化执行器时,模型看到的工具 schema 也会被搅动,尽管面向模型的约定从未改变。
这与「谁在运行时提供、谁需要一项能力」是不同的问题,后者 Cordis 已通过服务 + `inject` 解决(提供方注册 `ctx.shell`;消费方声明 `inject: ['bash']`,其 fiber 挂起直到服务存在)。该机制是必要的,但不决定包的边界;本 Agent Note 决定的是包的边界。
@@ -26,7 +26,7 @@ Service Provider 与 Consumer 由此独立演进:沙箱化执行器替换 `dsh
## 术语:seam 指三者组合,而非接口
-一个 **seam** 是完整的能力——三个角色合在一起:**Service Definition**(拥有 `ctx.` 和词汇的 Cordis `Service`)、一个或多个 **Service Provider**,以及一个或多个 **Consumer**。`packages/shell` 是规范范例——`dsh-shell` / `dsh-bash-local`+`dsh-bash-sandbox` / `dsh-tool-bash`。一个包可以承担多个角色,但单个角色本身不是 seam。「seam」一词严格保留给这种完整能力;命名其中一个组成部分时,应使用其角色、类、服务、约定或扩展点。[术语表](../../../../docs/glossary.md#capability-seam)是规范条目。
+一个 **seam** 是完整的能力——三个角色合在一起:**Service Definition**(拥有 `ctx.` 和词汇的 Cordis `Service`)、一个或多个 **Service Provider**,以及一个或多个 **Consumer**。`packages/shell` 是规范范例——`dsh-shell` / `dsh-bash-local`+`dsh-bash-sandbox` / `dsh-tool-bash`。一个包可以承担多个角色,但单个角色本身不是 seam。「seam」一词严格保留给这种完整能力;命名其中一个组成部分时,应使用其角色、类、服务、约定或扩展点。[术语表](../../../../docs/glossary.zh.md#capability-seam)是规范条目。
## 曾考虑的替代方案
@@ -35,4 +35,4 @@ Service Provider 与 Consumer 由此独立演进:沙箱化执行器替换 `dsh
## 后果
-分离角色会增加包和样板代码(`package.json`、`tsconfig`、README 和注入接线)。换来的是:Service Provider 与 Consumer 独立发布和版本管理,新后端永远不会波及面向模型的约定。[AGENTS.md](../../../../AGENTS.md) 和 [architecture.md](../../../../docs/architecture.md) 载有这项规则;bash 三件套是参考模板。本 Agent Note 记录为什么独立变化的角色通常需要拆分,而确实共享的关注点可以保持合并。
+分离角色会增加包和样板代码(`package.json`、`tsconfig`、README 和注入接线)。换来的是:Service Provider 与 Consumer 独立发布和版本管理,新后端永远不会波及面向模型的约定。[AGENTS.md](../../../../AGENTS.md) 和 [architecture.md](../../../../docs/architecture.zh.md) 载有这项规则;bash 三件套是参考模板。本 Agent Note 记录为什么独立变化的角色通常需要拆分,而确实共享的关注点可以保持合并。
diff --git a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml
index d44279eb42..3af4789414 100644
--- a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.md
2026-06-13-twin-llm-adapters.md: a4c87325a0b0d1ebe6cf8f95672e5de74ef37d57
-2026-06-13-twin-llm-adapters.zh.md: 2af7e7cca4d4c40e18cece1a4dd5c9cdb11901c8
+2026-06-13-twin-llm-adapters.zh.md: 36996750a16cc95393d727cffee3bcc53573eaf2
diff --git a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md
index 2af7e7cca4..36996750a1 100644
--- a/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-13-twin-llm-adapters.zh.md
@@ -6,7 +6,7 @@ Status: implemented
## 问题
-`dsh-llm` 拥有一套提供方无关的流式词汇:`StreamChunk` 协议(`block-start`、`text-delta`、`reasoning-delta`、`tool-call-delta`、`block-end`、`usage`、`finish`)以及内容块类型([内容块词汇](2026-06-11-content-block-vocabulary.md))。如果词汇仅针对单个适配器定义,就有可能将该适配器的特异行为固化到「中立」约定中:唯一实现碰巧做了什么,什么就成为事实上的规范;在第二个提供方到来之前,抽象层未经验证——而届时修复这种泄漏的代价已经很高。
+`dsh-llm` 拥有一套提供方无关的流式词汇:`StreamChunk` 协议(`block-start`、`text-delta`、`reasoning-delta`、`tool-call-delta`、`block-end`、`usage`、`finish`)以及内容块类型([内容块词汇](2026-06-11-content-block-vocabulary.zh.md))。如果词汇仅针对单个适配器定义,就有可能将该适配器的特异行为固化到「中立」约定中:唯一实现碰巧做了什么,什么就成为事实上的规范;在第二个提供方到来之前,抽象层未经验证——而届时修复这种泄漏的代价已经很高。
## 决策
diff --git a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml
index 61f9754431..8f9aa62e49 100644
--- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-14-session-persistence.md
2026-06-14-session-persistence.md: 62228bd2f5b25b13880a563818d08f3a2d52d956
-2026-06-14-session-persistence.zh.md: b10ceebd95d4d05ae3f7ea620183ad8fffd074ee
+2026-06-14-session-persistence.zh.md: ebf004333c383336cd025aa8a4aabc9d1e07f0e5
diff --git a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md
index b10ceebd95..ebf004333c 100644
--- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md
@@ -8,28 +8,28 @@ Status: implemented
会话此前仅存在于内存中。示例插件 `session-jsonl.ts`(在两个示例中逐字节重复)是只写的遥测:它缓冲 `session/event` 并追加 JSON 行,没有读取/回放路径,没有崩溃安全性(无 fsync、无原子写入、dispose(资源释放)时采用 fire-and-forget 方式排空),没有列表功能,也没有格式版本控制。没有任何机制能将磁盘上的历史会话重新注入到活跃的 agent(智能体)中,因此持久恢复、持久 fork 以及宿主侧的会话浏览都无法实现。
-[事件溯源模型](2026-06-11-event-sourced-sessions.md)将仅追加日志作为唯一真源,并从中派生 LLM(大语言模型)历史。持久化必须忠实于这一设计:直接持久化现有的 `SessionEvent`,不引入需要来回转换的并行「持久化消息」类型。后端也必须可替换——当前用文件存储,以后用数据库存储——并由同一接口封装。
+[事件溯源模型](2026-06-11-event-sourced-sessions.zh.md)将仅追加日志作为唯一真源,并从中派生 LLM(大语言模型)历史。持久化必须忠实于这一设计:直接持久化现有的 `SessionEvent`,不引入需要来回转换的并行「持久化消息」类型。后端也必须可替换——当前用文件存储,以后用数据库存储——并由同一接口封装。
## 决策
-持久化是一个具有抽象 Service Definition 的**能力 seam**([能力 seam](2026-06-13-capability-seams.md),`dsh-shell` 模板),而非循环或核心逻辑:
+持久化是一个具有抽象 Service Definition 的**能力 seam**([能力 seam](2026-06-13-capability-seams.zh.md),`dsh-shell` 模板),而非循环或核心逻辑:
1. **接口**(`dsh-session-persistence`,`ctx.sessionPersistence`):一个抽象的 `SessionPersistence` 服务,提供 `locate`/`create`/`append`/`prepare`/`load`/`inspect`/`readFrom`/`list`/`listSnapshots`。其持久化单元就是现有的 `SessionEvent`(`{ type, seq, time, data }`),原样复用,无转换类型。
-2. **实现**(`dsh-session-persistence-jsonl`):每个会话一个仅追加的逻辑 JSONL 日志:先是一行 `SessionHeader`,随后是无损表示连续 `SessionEvent` 流的存储记录。符合条件的 `assistant/chunk` 增量连续段默认使用打包行;[带校验和的 Zstandard 帧](2026-07-19-zstandard-jsonl-session-logs.md)是默认物理编码,也可通过配置使用原始行。
+2. **实现**(`dsh-session-persistence-jsonl`):每个会话一个仅追加的逻辑 JSONL 日志:先是一行 `SessionHeader`,随后是无损表示连续 `SessionEvent` 流的存储记录。符合条件的 `assistant/chunk` 增量连续段默认使用打包行;[带校验和的 Zstandard 帧](2026-07-19-zstandard-jsonl-session-logs.zh.md)是默认物理编码,也可通过配置使用原始行。
长期有效、存在争议的关键选择:
- **规范的持久日志无损保留每个 `SessionEvent`,包括 `assistant/chunk`。** JSONL 存储可以将一段连续的增量事件编码为一条打包行,但逻辑读取方会重建精确的事件边界、序号与时间戳。`deriveMessages()` 跳过分片,而过滤分片的方案(Codex 的 `policy.rs`)很有吸引力,但 `seq = log.length` 以及 `events[i].seq === i` 验证要求*连续*的逻辑日志;过滤掉分片会留下空洞,同时破坏约定和恢复功能。基于分片过滤的投影可以作为派生视图在后续实现(带有自己的重新编号),但它不是规范日志。
-- **仅追加;崩溃的轮次被关闭,而非截断。** 已刷写的事件永不被重写。[语义检查点策略](../bug-fix/2026-07-21-semantic-session-checkpoints.md)会在调用模型前排空请求、在调用工具前排空已记录的顶层调用,并在步骤结束后排空完整的响应/结果批次;循环则排空最终轮次边界。由于一个被中断的轮次可能包含大量有效工作,冷检查会保留其连续、可解析的事件,并在内存逻辑视图中为未应答的 assistant 调用添加按风险分类的错误结果、补一个缺失的 `step/end`,以及带 `{ kind: 'interrupted' }` 的 `turn/end`。`prepare` 或 `load` 在返回可恢复视图前提交这些收尾事件;合成结果保证恢复后的提供方 transcript(文本记录)仍然有效。只有不完整的最后一条记录会在提交修复时被丢弃;在最后一个真实 `turn/end` 处或之前出现解析错误或序号间隙,属于数据损坏,会使该会话不可加载。
+- **仅追加;崩溃的轮次被关闭,而非截断。** 已刷写的事件永不被重写。[语义检查点策略](../bug-fix/2026-07-21-semantic-session-checkpoints.zh.md)会在调用模型前排空请求、在调用工具前排空已记录的顶层调用,并在步骤结束后排空完整的响应/结果批次;循环则排空最终轮次边界。由于一个被中断的轮次可能包含大量有效工作,冷检查会保留其连续、可解析的事件,并在内存逻辑视图中为未应答的 assistant 调用添加按风险分类的错误结果、补一个缺失的 `step/end`,以及带 `{ kind: 'interrupted' }` 的 `turn/end`。`prepare` 或 `load` 在返回可恢复视图前提交这些收尾事件;合成结果保证恢复后的提供方 transcript(文本记录)仍然有效。只有不完整的最后一条记录会在提交修复时被丢弃;在最后一个真实 `turn/end` 处或之前出现解析错误或序号间隙,属于数据损坏,会使该会话不可加载。
- **文件后端为规范实现,数据库后端为经过验证的直接替换。** `SessionEvent` 1:1 映射到一行 `(session_id, seq, type, time, data)`:`append` 是 INSERT(在一个断言连续 seq 约定的事务中),读取使用 SELECT … ORDER BY seq。`dsh-session-persistence-sqlite` 正是如此:一个 `SessionPersistence` 子类,接口无变化(opencode 在 SQLite/WAL 上采用的正是这种接口形态),且通过与 JSONL 后端相同的 `runPersistenceContract` 测试套件。该约定以相同的语义约束两个后端(惰性物化、逻辑关闭中断轮次、修复只提交一次、连续 seq),一次表达在文件字节上,一次表达在数据库行上。其数据库拥有专用的 application id 与单调递增的 schema 版本。系统会在一个事务中为全新文件创建所有表并写入这两个 header 值;未版本化文件若带有任何用户定义的 schema 对象或应用标识、当前版本文件若带有外部应用标识,以及任何非当前版本文件,都会在修改日志模式之前被拒绝。
-- **元数据在日志之外。** 格式版本、cwd 和谱系是存储关注点,不是可回放的对话状态,因此它们存放在 `dsh-session` 拥有的 `SessionHeader` 中,并通过新的只读属性 `session.header` 附加到 `Session` 上——永远不进入 `SessionEventMap`,永远不到达 `deriveMessages()`。`createdAt` 是以 Unix epoch 毫秒表示的非负安全整数:运行时创建和持久化注册会拒绝小数值,JSONL 会验证解码后的 header,SQLite 则将其存入严格的 `INTEGER` 列。替代方案(一个可合并扩展的 `session/meta` 事件作为日志第 0 行)被否决:日志内事件会自然随 seed/fork 的会话携带,但元数据不是可回放状态,因此显式的日志外 header 边界是更清晰的取舍。(header 最初被拆分为不可变的 `SessionHeader` 加可变的 `SessionSummary`,二者的联合类型为 `SessionMeta`;可变 summary 后来因属于死状态而被移除——见 [移除可变会话摘要](../simplification/2026-06-19-drop-mutable-session-summary.md)。)
-- **`ctx.agents.create()` 和 `ctx.agents.resume()` 是异步工厂;恢复还跨越持久化边界。** `ctx.agents.resume({ resumeSessionId })` 通过 `ctx.sessionPersistence.prepare()` 取得精确的未发布 Session,以持久化 id 发布它,并继续其投影。[Session 准备阶段决策](2026-08-05-session-preparation.md)定义历史检查与恢复之间的复用。agent loop(智能体循环)不会硬注入 `sessionPersistence`(那样会让非持久化的演示永远挂起);当它不存在时,`resume` 会以明确的错误拒绝。
+- **元数据在日志之外。** 格式版本、cwd 和谱系是存储关注点,不是可回放的对话状态,因此它们存放在 `dsh-session` 拥有的 `SessionHeader` 中,并通过新的只读属性 `session.header` 附加到 `Session` 上——永远不进入 `SessionEventMap`,永远不到达 `deriveMessages()`。`createdAt` 是以 Unix epoch 毫秒表示的非负安全整数:运行时创建和持久化注册会拒绝小数值,JSONL 会验证解码后的 header,SQLite 则将其存入严格的 `INTEGER` 列。替代方案(一个可合并扩展的 `session/meta` 事件作为日志第 0 行)被否决:日志内事件会自然随 seed/fork 的会话携带,但元数据不是可回放状态,因此显式的日志外 header 边界是更清晰的取舍。(header 最初被拆分为不可变的 `SessionHeader` 加可变的 `SessionSummary`,二者的联合类型为 `SessionMeta`;可变 summary 后来因属于死状态而被移除——见 [移除可变会话摘要](../simplification/2026-06-19-drop-mutable-session-summary.zh.md)。)
+- **`ctx.agents.create()` 和 `ctx.agents.resume()` 是异步工厂;恢复还跨越持久化边界。** `ctx.agents.resume({ resumeSessionId })` 通过 `ctx.sessionPersistence.prepare()` 取得精确的未发布 Session,以持久化 id 发布它,并继续其投影。[Session 准备阶段决策](2026-08-05-session-preparation.zh.md)定义历史检查与恢复之间的复用。agent loop(智能体循环)不会硬注入 `sessionPersistence`(那样会让非持久化的演示永远挂起);当它不存在时,`resume` 会以明确的错误拒绝。
## 曾考虑的替代方案
上述每个关键选择都在陈述处记录了被否决的替代方案:**过滤分片的规范日志**(Codex 的 `policy.rs` 形式)破坏连续 seq 约定;**截断崩溃的轮次**会静默销毁长时间自主运行中的真实工作;**日志内 `session/meta` 事件作为第 0 行**——元数据不是可回放状态;**有限的非整数 `createdAt` 值**没有生产方,且与整数 Unix 毫秒存储及查询列不一致;**接受非全新的未版本化 SQLite 文件**可能覆盖无关对象或应用标识;**将 `sessionPersistence` 硬注入循环**会让非持久化的演示永远挂起。
-格式版本控制:header 携带一个 `version`;冷读取拒绝任何非当前版本。预发布阶段的会话格式仍固定为 `SESSION_FORMAT_VERSION = 0`,不承诺广泛兼容;当持久化用户数据确有需要时,协调器可以负责显式且范围受限的导入升级([消息标识机制引入前的消息恢复](../bug-fix/2026-07-28-load-pre-identity-session-messages.md))。仅追加 + 刷写对尾部的不完整写入具有健壮性(冷准备时可容忍),但无法抵御未使用 fsync 时在行写入中途断电;数据库/WAL 后端是该场景下更强的选项。
+格式版本控制:header 携带一个 `version`;冷读取拒绝任何非当前版本。预发布阶段的会话格式仍固定为 `SESSION_FORMAT_VERSION = 0`,不承诺广泛兼容;当持久化用户数据确有需要时,协调器可以负责显式且范围受限的导入升级([消息标识机制引入前的消息恢复](../bug-fix/2026-07-28-load-pre-identity-session-messages.zh.md))。仅追加 + 刷写对尾部的不完整写入具有健壮性(冷准备时可容忍),但无法抵御未使用 fsync 时在行写入中途断电;数据库/WAL 后端是该场景下更强的选项。
## 后果
diff --git a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml
index 9898684b9e..c3984a9fa9 100644
--- a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md
2026-06-17-filesystem-capability-seam.md: 6265aebf5e7ffdd4ec4dc0083aa55adb34ee78a1
-2026-06-17-filesystem-capability-seam.zh.md: 024421ed59fa1e6c29bcc12ab51f69ac19a0c231
+2026-06-17-filesystem-capability-seam.zh.md: f0f1cb132fe06ebf669f0310f0066f4fdd36ad0b
diff --git a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md
index 024421ed59..f0f1cb132f 100644
--- a/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.zh.md
@@ -20,7 +20,7 @@ harness 已有一个具体的 `bash` 能力 seam(`dsh-shell` / `dsh-bash-local
## 决策
-文件系统访问是一个一等的能力 seam,遵循[能力 seam Agent Note](2026-06-13-capability-seams.md):
+文件系统访问是一个一等的能力 seam,遵循[能力 seam Agent Note](2026-06-13-capability-seams.zh.md):
1. `@deepseek-ai/dsh-fs`(`packages/fs/fs`)拥有抽象的 `ctx.fs` 服务、文件系统词汇类型,以及 `fs/*` 策略事件词汇。
2. `@deepseek-ai/dsh-fs-local`(`packages/fs/fs-local`)提供第一个实现,以本地文件系统为后端。
@@ -28,7 +28,7 @@ harness 已有一个具体的 `bash` 能力 seam(`dsh-shell` / `dsh-bash-local
Consumer 包仅依赖 Service Definition 包,从不依赖 `dsh-fs-local`。需要不同后端的部署只需为 `ctx.fs` 加载不同的提供方,无需改动工具 schema 或面向模型的提示词引导。
-读后写/编辑与观测状态策略是第四个包 `@deepseek-ai/dsh-fs-observation-policy`(`packages/fs/fs-observation-policy`),通过 `fs/*` 事件门控贡献,而非挂在 `ctx.fs` 上;加载 `dsh-tool-fs` 的部署同时加载 `dsh-fs-observation-policy` 以获得读后写/编辑能力。本决策确立了由三个包构成的边界;策略从提供方基类拆出的决策由 [拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) 做出,其以事件门控插件(而非方法服务)实现的方式由 [事件门控 Agent Note](2026-06-26-file-context-as-event-gate.md) 做出。
+读后写/编辑与观测状态策略是第四个包 `@deepseek-ai/dsh-fs-observation-policy`(`packages/fs/fs-observation-policy`),通过 `fs/*` 事件门控贡献,而非挂在 `ctx.fs` 上;加载 `dsh-tool-fs` 的部署同时加载 `dsh-fs-observation-policy` 以获得读后写/编辑能力。本决策确立了由三个包构成的边界;策略从提供方基类拆出的决策由 [拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.zh.md) 做出,其以事件门控插件(而非方法服务)实现的方式由 [事件门控 Agent Note](2026-06-26-file-context-as-event-gate.zh.md) 做出。
第一个后端有意仅限本地:`dsh-fs-local` 基于宿主文件系统实现 `ctx.fs`。未来的兄弟后端可在同一接口之后提供沙箱、远程、虚拟或项目作用域的文件系统。
@@ -36,7 +36,7 @@ Consumer 包仅依赖 Service Definition 包,从不依赖 `dsh-fs-local`。需
文件系统权限和沙箱并非此拆分所隐含。本地后端从其配置的基目录解析相对路径,但路径包含约束策略是独立的决策:要么由更严格的 `ctx.fs` 实现强制执行,要么由权限/沙箱插件包装 `tools/execute` 并在调用到达消费方之前否决。
-读后写/编辑与观测状态属于 `dsh-fs-observation-policy`,而非 `ctx.fs`。通过 `fs/*` 事件门控,策略按不透明 actor 记录版本,并提供可选的变更期望;提供方原子性地强制新鲜度。`dsh-tool-fs` 发出事件但不依赖策略。见[拆分文件系统 seam](../simplification/2026-06-26-fsspec-style-fs-seam.md)和[事件门控插件](2026-06-26-file-context-as-event-gate.md) Agent Note。
+读后写/编辑与观测状态属于 `dsh-fs-observation-policy`,而非 `ctx.fs`。通过 `fs/*` 事件门控,策略按不透明 actor 记录版本,并提供可选的变更期望;提供方原子性地强制新鲜度。`dsh-tool-fs` 发出事件但不依赖策略。见[拆分文件系统 seam](../simplification/2026-06-26-fsspec-style-fs-seam.zh.md)和[事件门控插件](2026-06-26-file-context-as-event-gate.zh.md) Agent Note。
## 包拓扑
@@ -84,7 +84,7 @@ Consumer 包仅依赖 Service Definition 包,从不依赖 `dsh-fs-local`。需
- 不透明的 `targetKey`,用于陈旧守护和文件状态查找。本地后端可能使用类似 realpath 的键;远程后端可能使用工作区 URI 或文件 id。消费方禁止解析或假设它是本地绝对路径。
- `displayPath`,用于面向模型/UI 的输出。根据后端不同,它可能是本地绝对路径、工作区相对路径或远程 URI。
-即使另一项能力共享提供方的执行环境,`targetKey` 仍保持不透明。这类消费方通过提供方的 `processPath(target)`、`fileUrl(target)` 或 `contains(parent, child)` 获取所需事实;[可移植执行环境决策](2026-07-28-portable-execution-world-consumers.md)说明这些事实为何属于文件系统 seam。
+即使另一项能力共享提供方的执行环境,`targetKey` 仍保持不透明。这类消费方通过提供方的 `processPath(target)`、`fileUrl(target)` 或 `contains(parent, child)` 获取所需事实;[可移植执行环境决策](2026-07-28-portable-execution-world-consumers.zh.md)说明这些事实为何属于文件系统 seam。
读取和变更结果必须包含不透明的文件 `version`。本地后端从 bigint stat 元数据(`dev`、`ino`、`size`、`mtimeNs` 和 `ctimeNs`)派生令牌,因此同大小重写和 inode 替换都会可靠地使消费方失效;远程后端可以使用 revision id 或类似 hash 的令牌。`dsh-fs-observation-policy` 插件记录版本用于陈旧检查;消费方可以展示相关元数据但禁止解释版本令牌。
@@ -140,7 +140,9 @@ Consumer 包仅依赖 Service Definition 包,从不依赖 `dsh-fs-local`。需
- **面向模型的工具直接基于 `node:fs`**:工具包将同时承担执行策略、路径解析、原子写入、文本解码和编辑语义,耦合问题部分所列的三个独立变化的关注点,且任何后端替换都会搅动 schema。
- **单一合并包 `dsh-fs-tools`**:seam 之前的形态;以与 bash 相同的 Service Definition / Service Provider / Consumer 拆分理由否决,且合并名称从未成为公开 API。
-- **观测状态放在 `ctx.fs` 上**:本 Agent Note 最初落地的形态;被 [拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) 和 [事件门控 Agent Note](2026-06-26-file-context-as-event-gate.md) 取代:沙箱/远程后端不应继承面向模型的观测策略,因此提供方只保留版本令牌和可选的版本守护变更。
+- **观测状态放在 `ctx.fs` 上**:本 Agent Note 最初落地的形态;被 [拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.zh.md) 和 [事件门控 Agent Note](2026-06-26-file-context-as-event-gate.zh.md) 取代:沙箱/远程后端不应继承面向模型的观测策略,因此提供方只保留版本令牌和可选的版本守护变更。
+
+
## 后果
diff --git a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.i18n.yaml
index 0ecda2484f..03a0440ca1 100644
--- a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.md
2026-06-18-agent-lifecycle-and-ownership-contracts.md: 9bc558bfce75892b0ebdb80e9f8735d440cabaf4
-2026-06-18-agent-lifecycle-and-ownership-contracts.zh.md: 65e0018c3f2ba56043898050c8e0b49929f8e7e7
+2026-06-18-agent-lifecycle-and-ownership-contracts.zh.md: bbd0a7219f902e5ead4d190c58e9a5d4da2131fd
diff --git a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.zh.md b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.zh.md
index 65e0018c3f..bbd0a7219f 100644
--- a/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-contracts.zh.md
@@ -14,7 +14,7 @@ ACP(Agent Client Protocol)与 tool-bash 的若干限制是同一个所有权
### 1. 队列感知的 `Agent.cancel(cause?)`
-`Agent` 接口新增 `cancel()` 动词——唯一的公开停止原语。(它最初与范围更窄、仅作用于步骤的 `abort()` 一同交付;后者后来因无人使用而移除,使 `cancel()` 成为唯一公开的停止工作方式。)它清空 inbox 的 queued + steering FIFO,在存在活跃轮次时中止它,并保留一个不带 cause 的 pre-run 标记,使在被领取前被取消的提示词永不运行,而后来的提示词仍保持独立。有效调用会在清空或中止前发出 `agent/cancel-requested`,携带类型化的 `user | parent` cause;空闲取消不发出任何事件,也不会使下一条提示词搁浅。`whenIdle()` 会在取消后达到完全停稳,ACP 的 `session/cancel` 映射到 `user`。[显式轮次取消决策](2026-07-16-explicit-turn-cancellation.md)规定了当前的 cause、signal 生命周期与协作式结算约定。
+`Agent` 接口新增 `cancel()` 动词——唯一的公开停止原语。(它最初与范围更窄、仅作用于步骤的 `abort()` 一同交付;后者后来因无人使用而移除,使 `cancel()` 成为唯一公开的停止工作方式。)它清空 inbox 的 queued + steering FIFO,在存在活跃轮次时中止它,并保留一个不带 cause 的 pre-run 标记,使在被领取前被取消的提示词永不运行,而后来的提示词仍保持独立。有效调用会在清空或中止前发出 `agent/cancel-requested`,携带类型化的 `user | parent` cause;空闲取消不发出任何事件,也不会使下一条提示词搁浅。`whenIdle()` 会在取消后达到完全停稳,ACP 的 `session/cancel` 映射到 `user`。[显式轮次取消决策](2026-07-16-explicit-turn-cancellation.zh.md)规定了当前的 cause、signal 生命周期与协作式结算约定。
### 2. `AgentHandle` 异步释放器
@@ -43,7 +43,7 @@ bash 所有者 token 比较依赖共享的 `Agent.id`/`SessionId` 在存活 agen
- **公开的 `BashTask.owner` 字段**而非 `ShellExecutor.ownerOf(id)` Service Definition 方法:否决。一条读取路径即可,无需冗余 API。
- **为 agent 的会话生命周期使用兄弟 Cordis effect**:否决。fiber 卸载时并发释放兄弟 effect(`Promise.all`),store 拥有的 append 发布钩子的移除与循环的关闭 `session/flush` 产生竞争;单一复合 effect 的有序 LIFO 链才能在两条释放路径上都捕获关闭的 `turn/end`。
-- **在 `cancel()` 之外另设一个仅中止步骤的 `abort()`**:最初发布过,后因无人使用而移除;`cancel()` 是唯一的公开停止原语(见[公开停止接口 Agent Note](../simplification/2026-06-20-public-agent-stop-api.md))。
+- **在 `cancel()` 之外另设一个仅中止步骤的 `abort()`**:最初发布过,后因无人使用而移除;`cancel()` 是唯一的公开停止原语(见[公开停止接口 Agent Note](../simplification/2026-06-20-public-agent-stop-api.zh.md))。
## 后果
diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml
index 38a665a0fd..5148c8a648 100644
--- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.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/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md
-2026-06-18-shared-persistence-write-coordinator.md: 93b6cd1bd058499e71948d3909de8e4c076b445e
-2026-06-18-shared-persistence-write-coordinator.zh.md: 9e1bc736d4dba5e59b763710976425fa0ae76c30
+2026-06-18-shared-persistence-write-coordinator.md: 8392ec726ff44e8a7173f48ef7d5cc4826b7e882
+2026-06-18-shared-persistence-write-coordinator.zh.md: e160f29247ae5cd02aaa8388c141faec64001857
diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md
index 93b6cd1bd0..8392ec726f 100644
--- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md
+++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.md
@@ -16,15 +16,20 @@ Composition, not inheritance. The coordinator is a concrete class the backend ho
The coordinator holds one lifecycle entry for each exact live `Session`: initialization plus a package-private write controller that owns pending events, a fixed batching deadline, the active write, failure retention, and the shared flush barrier. Each `session/event` enters that bounded write path, and `session/flush` bypasses the wait to observe quiescence. The [flush-controller simplification](../simplification/2026-07-23-collapse-persistence-flush-state.md) owns controller consolidation; the [bounded batching decision](2026-08-08-bounded-session-persistence-write-batching.md) owns scheduling cadence.
+Creation borrows the exact `Session.events` snapshot as its persistence seed. `Session` has already detached, validated, and deeply frozen every event, and the snapshot array remains stable when later appends replace the cached view. The coordinator and its backend hooks only read this typed in-process value, so cloning the complete log again would duplicate the ownership work described by the [agent-scope runtime decision](2026-07-12-agent-scope-runtime-design.md#session-append-materialize-validate-commit-notify). Public persistence `append()` still snapshots caller-owned input at its API boundary.
+
+Prepared-session suffixes and events admitted to the write-behind queue retain their existing copies. Those paths establish asynchronous queue ownership one suffix or event at a time and have no measured whole-log clone cost; removing their copies remains a separate ownership audit rather than part of creation-seed borrowing.
+
The coordinator retires a session from `session/disposed`: it waits for the controller's initialization and current flush, serializes a final drain, and removes the controller and owned per-id state only after success. A failure leaves the controller discoverable for backend teardown to retry. Settled per-id chain tails remove themselves only when they are still current, so a completion cannot erase a newer operation for the same id. Backend teardown unregisters write-path listeners, flushes every remaining controller, awaits per-id operations, and then closes the backend.
### The hook interface (`PersistenceBackend`)
-Five required members plus an optional lifecycle hook form the only boundary between the coordinator and storage:
+Five required members plus optional empty-materialization and lifecycle hooks form the only boundary between the coordinator and storage:
- `name` — backend label for the dispose-failure `AggregateError`.
- `loadStored(id)` — read one stored prefix by id across every storage scope (every JSONL project directory; SQLite's id is globally unique). Preparation, logical load/inspection, physical suffix reads, live adoption, and the create-collision probe share this lookup. The coordinator asserts the returned id and rejects a stored/live cwd mismatch before repair or state publication.
-- `appendBatch(meta, events, isMaterialized)` — durably append a contiguous batch, lazily materializing the session ATOMICALLY when not yet materialized (the materialize-write and the first event batch must commit together — a crash between them must not leave a materialized-but-empty session; this is why there is no separate `materialize` hook).
+- `appendBatch(meta, events, isMaterialized)` — durably append a contiguous batch, lazily materializing the session ATOMICALLY when not yet materialized. Ordinary creation therefore cannot leave an abandoned materialized-but-empty session.
+- `materializeHeader?(meta)` — explicitly persist a header-only session for `SessionPersistence.ensureMaterialized(session)`. This is reserved for a lifecycle frontend that treats an empty session itself as a resumable durable resource; [standard ACP automation controls](../feature/2026-08-22-standard-acp-automation-controls.md) are the first consumer. Backends that support that lifecycle implement the hook; lazy creation remains the default.
- `commitRepair(meta, tornMarker, closers)` — make a crash repair durable: truncate the torn tail (iff `tornMarker !== undefined`) and append `closers`. **NOT required to be atomic** — JSONL legitimately truncates-then-appends in two fsync'd steps, SQLite does DELETE+INSERT in one transaction. Used by `prepare`/`load` (truncate + synthetic closers) and live-adoption (truncate only, `closers = []`).
- `list()` — list all stored metadata.
- `close?()` — optional lifecycle teardown (SQLite closes its db handle; JSONL omits it), awaited in the dispose effect AFTER the quiescence drain so a close failure never masks a drain error.
diff --git a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md
index 9e1bc736d4..e160f29247 100644
--- a/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-18-shared-persistence-write-coordinator.zh.md
@@ -14,17 +14,22 @@ Status: implemented
组合,而非继承。协调器是后端持有的具体类,不是后端继承的基类。协调器让非常规后端与继承层级作斗争的风险由此规避:后端只暴露钩子,无法触及协调器的私有编排状态。第三方后端仍然可以完全不使用协调器、直接实现抽象服务,包括不可变逻辑检查,以及通过 `load` 实现的默认准备回退。
-协调器为每个存活的 `Session` 实例持有一个生命周期条目:初始化,加上一个包私有写入控制器,后者负责待处理事件、固定批处理截止时间、活跃写入、失败保留和共享 flush 屏障。每个 `session/event` 都进入这条有界写入路径,`session/flush` 则绕过等待以观察完全停稳。控制器归并由 [flush 控制器简化](../simplification/2026-07-23-collapse-persistence-flush-state.md)定义;调度节奏由[有界批处理决策](2026-08-08-bounded-session-persistence-write-batching.md)定义。
+协调器为每个存活的 `Session` 实例持有一个生命周期条目:初始化,加上一个包私有写入控制器,后者负责待处理事件、固定批处理截止时间、活跃写入、失败保留和共享 flush 屏障。每个 `session/event` 都进入这条有界写入路径,`session/flush` 则绕过等待以观察完全停稳。控制器归并由 [flush 控制器简化](../simplification/2026-07-23-collapse-persistence-flush-state.zh.md)定义;调度节奏由[有界批处理决策](2026-08-08-bounded-session-persistence-write-batching.zh.md)定义。
+
+创建流程将 `Session.events` 的原始快照借作持久化种子。`Session` 已经分离、验证并深度冻结每个事件,后续追加会替换缓存视图,因此该快照数组保持稳定。协调器及其后端钩子只读取这个有类型的进程内值;再次克隆完整日志会重复 [agent scope 运行时决策](2026-07-12-agent-scope-runtime-design.zh.md#session-append-materialize-validate-commit-notify)规定的所有权工作。持久化服务的公开 `append()` 仍在 API 边界为调用方拥有的输入创建快照。
+
+已准备 Session 的后缀,以及进入 write-behind 队列的事件,仍保留现有复制。这些路径会逐个后缀或事件建立异步队列所有权,且没有已测得的完整日志克隆成本;移除这些复制属于单独的所有权审计,不属于创建种子的借用决策。
协调器通过 `session/disposed` 退役会话:它等待控制器完成初始化和当前 flush,串行执行最后一次排空,且仅在成功后才移除控制器与其拥有的每 id 状态。失败时保持控制器可被找到,以供后端 teardown(拆除)重试。每个 id 的已结算链尾仅在其仍是当前链尾时才移除自身,因此旧操作完成后不会抹除同一 id 的新操作。后端 teardown 会注销写入路径监听器、flush 每个剩余的控制器、等待所有按 id 串行化的操作,最后关闭后端。
### 钩子接口(`PersistenceBackend`)
-五个必需成员加一个可选的生命周期钩子,构成协调器与存储之间唯一的边界:
+五个必需成员加可选的空会话实体化与生命周期钩子,构成协调器与存储之间唯一的边界:
- `name`——后端标签,用于 dispose 失败时的 `AggregateError`。
- `loadStored(id)`——按 id 跨所有存储范围读取一个已存储前缀(JSONL 的所有项目目录;SQLite 的 id 全局唯一)。准备、逻辑加载/检查、物理后缀读取、存活会话接管与创建碰撞探测共用此查找。协调器会断言返回的 id,并在修复或发布状态之前拒绝已存储记录与存活会话的 cwd 不匹配。
-- `appendBatch(meta, events, isMaterialized)`——持久追加一个连续批次,在尚未物化时原子地惰性物化会话(物化写入与首批事件必须一起提交——二者之间发生崩溃时,不得留下一个已物化但为空的会话;这就是为什么没有单独的 `materialize` 钩子)。
+- `appendBatch(meta, events, isMaterialized)`——持久追加一个连续批次,在尚未物化时原子地惰性物化会话。因此,普通创建不会留下被放弃的已物化空会话。
+- `materializeHeader?(meta)`——为 `SessionPersistence.ensureMaterialized(session)` 显式持久化仅含 header 的会话。它只供把空会话本身视为可恢复持久资源的生命周期前端使用;[标准 ACP 自动化控制](../feature/2026-08-22-standard-acp-automation-controls.zh.md)是第一个 consumer。支持该生命周期的后端实现此钩子;惰性创建仍是默认行为。
- `commitRepair(meta, tornMarker, closers)`——使崩溃修复持久化:截断损坏的尾部(当且仅当 `tornMarker !== undefined`)并追加 `closers`。**不要求原子性**——JSONL 合理地分两步 fsync(先截断再追加),SQLite 在一个事务中完成 DELETE+INSERT。用于 `prepare`/`load`(截断 + 合成收尾事件)和存活会话接管(仅截断,`closers = []`)。
- `list()`——列出所有已存储的元数据。
- `close?()`——可选的生命周期清理(SQLite 关闭 db 句柄;JSONL 省略),在 dispose effect 中于排空至完全停稳之后被 await,因此 close 失败不会掩盖排空错误。
@@ -44,4 +49,4 @@ Status: implemented
## 后果
-协调器增加了一层间接、一个不透明的 torn marker、脱离会话生命周期的退役任务,以及有界的已准备 Session 状态,但将此前每个后端重复的、对正确性要求很高的编排逻辑集中到一处。会话 dispose 仍是仅观察事件,因此会话所有者不会等待持久化退役;协调器会收容失败、在存活控制器中保留待处理事件,并以后端 teardown 为完全停稳边界。其钩子面保持窄小:标识校验、接管、碰撞检查、准备与不可变检查共用 `loadStored`;物化保持在 `appendBatch` 内原子完成;列举绕过协调器。读模型使用 `inspect` 而非 `load`,因此观察已持久化但仍开放的轮次时不会提交中断收尾事件;复用、预留与发布由 [Session 准备阶段决策](2026-08-05-session-preparation.md)定义。新后端只需实现存储原语,而无需复制有界写入生命周期。
+协调器增加了一层间接、一个不透明的 torn marker、脱离会话生命周期的退役任务,以及有界的已准备 Session 状态,但将此前每个后端重复的、对正确性要求很高的编排逻辑集中到一处。会话 dispose 仍是仅观察事件,因此会话所有者不会等待持久化退役;协调器会收容失败、在存活控制器中保留待处理事件,并以后端 teardown 为完全停稳边界。其钩子面保持窄小:标识校验、接管、碰撞检查、准备与不可变检查共用 `loadStored`;物化保持在 `appendBatch` 内原子完成;列举绕过协调器。读模型使用 `inspect` 而非 `load`,因此观察已持久化但仍开放的轮次时不会提交中断收尾事件;复用、预留与发布由 [Session 准备阶段决策](2026-08-05-session-preparation.zh.md)定义。新后端只需实现存储原语,而无需复制有界写入生命周期。
diff --git a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml
index b7e2678928..1e1545bb12 100644
--- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.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/implemented/architecture/2026-06-20-branded-ids.md
-2026-06-20-branded-ids.md: 29b258b21240c92e74051339f0939a8e70933099
-2026-06-20-branded-ids.zh.md: 288125764d4b279c79b7469080bb0c9f2efdc709
+2026-06-20-branded-ids.md: 6443608c76fe42be74a2b8fe8a27669b09951a49
+2026-06-20-branded-ids.zh.md: f13d999aadf4dba7f2c7d31bb2739deae4a0991f
diff --git a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md
index 29b258b212..6443608c76 100644
--- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md
+++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.md
@@ -6,13 +6,13 @@ English | [中文](2026-06-20-branded-ids.zh.md)
## Problem
-The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared agent/session `SessionId` (`packages/core/session/src/types.ts`) using the `Branded = string & { readonly [BRAND]: B }` machinery (owned by the type-only `@deepseek-ai/dsh-brand` package at `packages/util/brand/` — see its [README](../../../../packages/util/brand/README.md)) and a zero-cost cast factory per type. `dsh-brand` also states the governing policy: *"Branding is for ids that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker today.
+The harness brands `ToolCallId` (`packages/llm/llm/src/brand.ts`) and the shared agent/session `SessionId` (`packages/core/session/src/types.ts`) using the `Branded = string & { readonly [BRAND]: B }` machinery (owned by the type-only `@deepseek-ai/dsh-brand` package at `packages/util/brand/` — see its [README](../../../../packages/util/brand/README.md)) and a zero-cost cast factory per type. `dsh-brand` also states the governing policy: *"Branding is for ids that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker.
**Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-job id is a plain `string`: `BashTask.id: string` (`packages/shell/shell/src/types.ts`), carried as `string` through the whole executor seam (`ShellExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/shell/shell/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateJobId`, `assertTaskAccess`, the `job_id` schema arg in `packages/shell/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/shell/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash job id and a session id are trivially swappable at a call site and the compiler says nothing. It is a model-facing id (the model passes `job_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input.
The bash **owner token** is the related sub-case: `ShellExecRequest.owner?: string` and `ShellExecSpec.owner: string | undefined` (`packages/shell/shell/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's shared `Agent.id`/`SessionId` (`callerToken = (exec) => exec.agent?.id` in `packages/shell/tool-bash/src/index.ts`) wearing a different seam-local name. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the shared id alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md).
-**Gap 2 — brand erosion at the boundaries of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), tool-presentation call-id maps, ACP's session records, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized.
+**Gap 2 — brand erosion at the boundaries of the *already-branded* IDs.** Even `ToolCallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), tool-presentation call-id maps, ACP's session records, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized.
## Decision
@@ -22,7 +22,7 @@ A type-only change. Brands are zero-cost casts; nothing about runtime behavior,
- **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/shell/shell/src/types.ts`; type `ShellExecRequest.owner` / `ShellExecSpec.owner` / `ShellExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's shared `id` (`SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash Service Definition never imports `dsh-session`. (Rationale in the next section.)
-- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the change and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields.
+- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the change and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields.
Illustrative shape (the factory pattern is identical to the three existing brands):
@@ -56,11 +56,11 @@ Kept deliberately narrow per the "not every string needs a brand" policy. Each o
- **`ToolName`** (the `ToolRuntime` key) — author-defined, human-readable, and rarely confused with another id; the weakest candidate, likely not worth a brand.
- **`ErrorCode`** (`HarnessError.code`) — a closed vocabulary (`ABORTED`, `NO_ADAPTER`, …), not a per-instance id; better served by a string-literal union than a brand, if anything.
- **Numeric ordinals** — turn number, step number, and the event `seq` are `number`, not `string`, so `Branded` does not apply; a parallel `number & { readonly [BRAND]: B }` variant could brand them, but they are positional ordinals rarely passed across boundaries, so the payoff is low.
-- **Validated construction** — the brand factories are pure casts with no runtime check, and every boundary (ACP `sessionId`, provider-issued `call.id`, the empty-string fallback in `dsh-llm-deepseek`) trusts the raw string today. A `SessionId.parse()` / `isValid()` companion that throws on malformed input at boundaries is a genuine gap, but it is a *runtime-behavior* change with its own design (what is "malformed"? what happens on failure?) and belongs in its own decision, not bundled into this type-only change.
+- **Validated construction** — the brand factories are pure casts with no runtime check, and every boundary (ACP `sessionId`, provider-issued `call.id`, the empty-string fallback in `dsh-llm-deepseek`) trusts the raw string. A `SessionId.parse()` / `isValid()` companion that throws on malformed input at boundaries is a genuine gap, but it is a *runtime-behavior* change with its own design (what is "malformed"? what happens on failure?) and belongs in its own decision, not bundled into this type-only change.
## Verification
-The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-shell` and threaded end-to-end (Service Definition, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing tool) with no `dsh-shell` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`CallId`/`SessionId`/`BashTaskId`) is keyed by bare `string`; public method params and exported signatures keep the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `job_id`), never as scattered `as` casts.
+The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-shell` and threaded end-to-end (Service Definition, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing tool) with no `dsh-shell` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`ToolCallId`/`SessionId`/`BashTaskId`) is keyed by bare `string`; public method params and exported signatures keep the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `job_id`), never as scattered `as` casts.
## Consequences
diff --git a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md
index 288125764d..f13d999aad 100644
--- a/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-20-branded-ids.zh.md
@@ -6,13 +6,13 @@ Status: implemented
## 问题
-harness 使用 `Branded = string & { readonly [BRAND]: B }` 机制,为 `CallId`(`packages/llm/llm/src/brand.ts`)和 agent(智能体)/会话共享的 `SessionId`(`packages/core/session/src/types.ts`)做 brand 处理;该机制由纯类型包 `@deepseek-ai/dsh-brand` 拥有,位于 `packages/util/brand/`,见其 [README](../../../../packages/util/brand/README.md),并为每个类型提供零开销的 cast 工厂。`dsh-brand` 还声明了治理策略:*「Branding 用于跨包边界且可能被混淆的 id;不是每个 string 都需要 brand。」* 这条策略是正确的;问题在于它只落实了一半。两处缺口使得结构相同但语义错误的 string 今天仍能通过类型检查器。
+harness 使用 `Branded = string & { readonly [BRAND]: B }` 机制,为 `ToolCallId`(`packages/llm/llm/src/brand.ts`)和 agent(智能体)/会话共享的 `SessionId`(`packages/core/session/src/types.ts`)做 brand 处理;该机制由纯类型包 `@deepseek-ai/dsh-brand` 拥有,位于 `packages/util/brand/`,见其 [README](../../../../packages/util/brand/README.zh.md),并为每个类型提供零开销的 cast 工厂。`dsh-brand` 还声明了治理策略:*「Branding 用于跨包边界且可能被混淆的 id;不是每个 string 都需要 brand。」* 这条策略是正确的;问题在于它只落实了一半。两处缺口使得结构相同但语义错误的 string 仍能通过类型检查器。
**缺口 1:bash seam 中未 brand 的跨边界 ID。** 后台 job id 是普通 `string`:`BashTask.id: string`(`packages/shell/shell/src/types.ts`),作为 `string` 贯穿整个执行器 seam(`packages/shell/shell/src/index.ts` 中的 `ShellExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)`),再由面向模型的工具以 `string` 校验并传递(`validateJobId`、`assertTaskAccess`、`packages/shell/tool-bash/src/index.ts` 中 `job_id` 的 schema 参数)。它由每执行器计数器生成——`packages/shell/bash-local/src/index.ts` 中的 `` `bash-${this.nextTaskId++}` ``——其形状与 `SessionId` 的默认值**完全相同,都是 `name-N`**(`packages/core/session/src/index.ts` 中的 `` `session-${++counter}` ``)。bash job id 和会话 id 在调用点轻易就能互换,而编译器毫无反应。它是面向模型的 id(模型会把 `job_id` 传回 `bash_output`/`bash_kill`),所以该混淆可由不受信任的输入触达。
-bash **owner token** 是相关的子情形:`ShellExecRequest.owner?: string` 和 `ShellExecSpec.owner: string | undefined`(`packages/shell/shell/src/types.ts`)被文档描述为刻意*不透明*的隔离键,但在所有实际调用方中,该值就是所属 agent 共享的 `Agent.id`/`SessionId`(`callerToken = (exec) => exec.agent?.id`,位于 `packages/shell/tool-bash/src/index.ts`),只是披着另一个 seam 本地名称。它被用于访问控制比较(`owner !== callerToken(exec)`),因此一个不匹配但类型正确的 string 在此处就是跨会话隔离 bug,而当前类型系统无法捕获。这正是[统一 agent/session 标识决策](../simplification/2026-06-20-unify-agent-and-session-id.md)覆盖的共享 id 别名。
+bash **owner token** 是相关的子情形:`ShellExecRequest.owner?: string` 和 `ShellExecSpec.owner: string | undefined`(`packages/shell/shell/src/types.ts`)被文档描述为刻意*不透明*的隔离键,但在所有实际调用方中,该值就是所属 agent 共享的 `Agent.id`/`SessionId`(`callerToken = (exec) => exec.agent?.id`,位于 `packages/shell/tool-bash/src/index.ts`),只是披着另一个 seam 本地名称。它被用于访问控制比较(`owner !== callerToken(exec)`),因此一个不匹配但类型正确的 string 在此处就是跨会话隔离 bug,而当前类型系统无法捕获。这正是[统一 agent/session 标识决策](../simplification/2026-06-20-unify-agent-and-session-id.zh.md)覆盖的共享 id 别名。
-**缺口 2:*已经 brand* 的 ID 在边界处被侵蚀。** 就连 `CallId` 和 `SessionId` 也恰好在最容易混淆的地方退化为裸 `string`:注册表/store 键类型和公开方法参数。代表性位置包括会话存储、agent 注册表(二者都以共享的 `SessionId` 为键)、工具展示层的 call-id map、ACP(Agent Client Protocol)的会话记录,以及持久化协调器。在集合键处丢弃 brand,会让既有 brand 在查找时毫无价值;它们的价值只实现了一部分。
+**缺口 2:*已经 brand* 的 ID 在边界处被侵蚀。** 就连 `ToolCallId` 和 `SessionId` 也恰好在最容易混淆的地方退化为裸 `string`:注册表/store 键类型和公开方法参数。代表性位置包括会话存储、agent 注册表(二者都以共享的 `SessionId` 为键)、工具展示层的 call-id map、ACP(Agent Client Protocol)的会话记录,以及持久化协调器。在集合键处丢弃 brand,会让既有 brand 在查找时毫无价值;它们的价值只实现了一部分。
## 决策
@@ -22,7 +22,7 @@ bash **owner token** 是相关的子情形:`ShellExecRequest.owner?: string`
- **铸造独立的 `OwnerToken` brand。** 在 `packages/shell/shell/src/types.ts` 中添加 `OwnerToken = Branded<'OwnerToken'>`;将 `ShellExecRequest.owner` / `ShellExecSpec.owner` / `ShellExecutor.ownerOf` 的类型标注为 `OwnerToken | undefined`。`dsh-tool-bash` 消费方在边界处将 agent 共享的 `id`(`SessionId`)cast 为 `OwnerToken`——这是两套词汇唯一交汇的地方。bash Service Definition 从不导入 `dsh-session`。(理由见下一节。)
-- **阻止 brand 侵蚀。** 将既有 brand 传播到缺口 2 列出的 `Map` 键类型和公开方法参数中:`Map`、`Map`、`get(id: SessionId)`、`Map`、ACP 的 `SessionId` surface、协调器的 `Map`。这是变更中机械量最大的部分,也是让*既有* brand 在查找处真正发挥作用(而不仅仅标注在结构体字段上)的关键。
+- **阻止 brand 侵蚀。** 将既有 brand 传播到缺口 2 列出的 `Map` 键类型和公开方法参数中:`Map`、`Map`、`get(id: SessionId)`、`Map`、ACP 的 `SessionId` surface、协调器的 `Map`。这是变更中机械量最大的部分,也是让*既有* brand 在查找处真正发挥作用(而不仅仅标注在结构体字段上)的关键。
示意形状(工厂模式与已有的三个 brand 完全一致):
@@ -56,14 +56,14 @@ export function OwnerToken(id: string): OwnerToken {
- **`ToolName`**(`ToolRuntime` 的键):由作者定义、人类可读,且很少与其他 id 混淆;最弱的候选,可能不值得加 brand。
- **`ErrorCode`**(`HarnessError.code`):一个封闭词汇(`ABORTED`、`NO_ADAPTER`……),不是逐实例的 id;如果要做,string 字面量联合类型比 brand 更合适。
- **数值序号**:轮次号、步骤号和事件 `seq` 是 `number` 而非 `string`,`Branded` 不适用;可以用并行的 `number & { readonly [BRAND]: B }` 变体来 brand 它们,但它们是位置序号、很少跨边界传递,收益较低。
-- **带校验的构造**:brand 工厂是纯 cast,无运行时检查,且每个边界(ACP `sessionId`、提供方签发的 `call.id`、`dsh-llm-deepseek` 中的空字符串回退)今天都信任裸 string。一个在边界处对格式错误的输入抛异常的 `SessionId.parse()` / `isValid()` 配套工具确实是缺口,但它是*运行时行为*变更,有自己的设计问题(什么算「格式错误」?失败时会怎样?),应在独立决策中处理,不应捆绑进这次纯类型变更。
+- **带校验的构造**:brand 工厂是纯 cast,无运行时检查,且每个边界(ACP `sessionId`、提供方签发的 `call.id`、`dsh-llm-deepseek` 中的空字符串回退)都信任裸 string。一个在边界处对格式错误的输入抛异常的 `SessionId.parse()` / `isValid()` 配套工具确实是缺口,但它是*运行时行为*变更,有自己的设计问题(什么算「格式错误」?失败时会怎样?),应在独立决策中处理,不应捆绑进这次纯类型变更。
## 验证
-已落地的不变式如下:`BashTaskId` 和 `OwnerToken` 定义在 `dsh-shell` 中,并端到端贯穿 Service Definition、`dsh-bash-local` 生成点与 `dsh-tool-bash` 面向模型的工具,且 `dsh-shell` 未添加对 `dsh-session` 的依赖;没有任何以范围内 brand id(`CallId`/`SessionId`/`BashTaskId`)为键的集合使用裸 `string`;公开方法参数和导出签名保留 brand;每个原始 string 进入的边界(提供方 call id、ACP 会话 id、模型提供的 `job_id`)都通过 cast 工厂构造 brand,而不是散落的 `as` cast。
+已落地的不变式如下:`BashTaskId` 和 `OwnerToken` 定义在 `dsh-shell` 中,并端到端贯穿 Service Definition、`dsh-bash-local` 生成点与 `dsh-tool-bash` 面向模型的工具,且 `dsh-shell` 未添加对 `dsh-session` 的依赖;没有任何以范围内 brand id(`ToolCallId`/`SessionId`/`BashTaskId`)为键的集合使用裸 `string`;公开方法参数和导出签名保留 brand;每个原始 string 进入的边界(提供方 call id、ACP 会话 id、模型提供的 `job_id`)都通过 cast 工厂构造 brand,而不是散落的 `as` cast。
## 后果
-- **两个接口面的机械性改动。** 传播 brand 涉及 bash seam(Service Definition + Service Provider + Consumer)以及 ACP 会话 id 接口和持久化协调器。改动面广但严重度低:遗漏的位置是编译错误而非静默 bug。从可观察行为看,这是一项纯类型变更——无快照或 e2e 行为差异。它与[统一 agent/会话标识决策](../simplification/2026-06-20-unify-agent-and-session-id.md)相邻,因为二者都触及会话 id / owner-token 边界;`OwnerToken` 出于上述解耦理由仍与统一后的 id 保持独立。
+- **两个接口面的机械性改动。** 传播 brand 涉及 bash seam(Service Definition + Service Provider + Consumer)以及 ACP 会话 id 接口和持久化协调器。改动面广但严重度低:遗漏的位置是编译错误而非静默 bug。从可观察行为看,这是一项纯类型变更——无快照或 e2e 行为差异。它与[统一 agent/会话标识决策](../simplification/2026-06-20-unify-agent-and-session-id.zh.md)相邻,因为二者都触及会话 id / owner-token 边界;`OwnerToken` 出于上述解耦理由仍与统一后的 id 保持独立。
- **Brand 不做校验。** Brand 是混淆防护,不是正确性证明:一个*错误的*会话 id 只要仍是格式正确的 string,就和以前一样能通过类型检查器。本决策不关闭这个缺口(见「不在范围内」)——它只阻止这类*类别*错误:传入错误*种类*的 id。
- **「在哪里停下」仍是判断题。** 为 `BashTaskId` 加 brand 但不为 `ToolName` 加,为 `OwnerToken` 加但不为 `ModelId` 加,是对哪些 string「可能被混淆」的品味判断。合理的评审者可能想要更多或更少;`brand.ts` 中的策略是裁决依据,本决策倾向于面向模型或用于访问控制的 id。
diff --git a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml
index 477c6df3ae..7d4ccbd4e1 100644
--- a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md
2026-06-20-generic-long-running-tool-runtime.md: 7db43323dd83f8e99698a7163412c9b33a607dfb
-2026-06-20-generic-long-running-tool-runtime.zh.md: efd306cc8d3b82749635dde302af45235c27b431
+2026-06-20-generic-long-running-tool-runtime.zh.md: 040ea6a01e97c9dc1d93e8f3a0fd9c1f4b0f31fc
diff --git a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md
index efd306cc8d..040ea6a01e 100644
--- a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.zh.md
@@ -19,13 +19,13 @@ Status: implemented
长时间运行工具是生产方。`dsh-tool-bash` 将 `ShellProcess` 适配为增量输出与进程取消;`dsh-tool-subagent` 将子运行适配为最终输出与子运行释放。bash 与 subagent 能力 seam 保持独立,不依赖会话或任务注册表。
-`JobRegistry` 是 `@deepseek-ai/dsh-jobs` 中的 Service Definition;进程内 Service Provider 是 `@deepseek-ai/dsh-jobs-local` 中的 `LocalJobRegistry`(该拆分记录在[任务注册表约定 Agent Note](2026-07-26-job-registry-seam.md)中)。
+`JobRegistry` 是 `@deepseek-ai/dsh-jobs` 中的 Service Definition;进程内 Service Provider 是 `@deepseek-ai/dsh-jobs-local` 中的 `LocalJobRegistry`(该拆分记录在[任务注册表约定 Agent Note](2026-07-26-job-registry-seam.zh.md)中)。
## 运行时约定
-字面类型见[任务子系统页面](../../../../docs/subsystems/jobs.md)。生产方调用 `ctx.jobs.start()`,传入 kind、label、可选的所属 `Agent`、可选的正数 `outputLimitBytes` 与一个 `run()` 函数。运行时会在调用 `run()` 前完成所有可能失败的预检工作,并且只调用一次。`run()` 返回钩子后,注册过程不会再执行可能失败的步骤而直接提交;生产方无法启动没有可收集 job id 的工作。
+字面类型见[任务子系统页面](../../../../docs/subsystems/jobs.zh.md)。生产方调用 `ctx.jobs.start()`,传入 kind、label、可选的所属 `Agent`、可选的正数 `outputLimitBytes` 与一个 `run()` 函数。运行时会在调用 `run()` 前完成所有可能失败的预检工作,并且只调用一次。`run()` 返回钩子后,注册过程不会再执行可能失败的步骤而直接提交;生产方无法启动没有可收集 job id 的工作。
-进程内 Service Provider 还拥有有界准入,其理由记录在[有界后台任务准入决策](../bug-fix/2026-08-11-bounded-background-job-admission.md)中。它的 `maxConcurrentJobsPerOwner` 配置必须是正的安全整数,默认值为 `10`;`start()` 从 `running` 与 `stopping` 记录派生每个确切 `Agent` 对象的活动数量,而全部无 owner 任务共享一个服务级桶。容量拒绝发生在 `run()` 与 id 分配之前,处于 stopping 的任务只有在生产方 `done` 结算时才释放名额。Service Provider 不排队或抢占任务,也不保留第二份可变计数。
+进程内 Service Provider 还拥有有界准入,其理由记录在[有界后台任务准入决策](../bug-fix/2026-08-11-bounded-background-job-admission.zh.md)中。它的 `maxConcurrentJobsPerOwner` 配置必须是正的安全整数,默认值为 `10`;`start()` 从 `running` 与 `stopping` 记录派生每个确切 `Agent` 对象的活动数量,而全部无 owner 任务共享一个服务级桶。容量拒绝发生在 `run()` 与 id 分配之前,处于 stopping 的任务只有在生产方 `done` 结算时才释放名额。Service Provider 不排队或抢占任务,也不保留第二份可变计数。
`outputLimitBytes` 是生产方拥有的呈现策略,而非注册表缓冲区。注册表校验该值,并将其原样投影到 `JobSnapshot`;通用任务控制器添加自身的状态或通知元数据后,再将该上限应用于完整的面向模型输出。省略该值时保持现有控制器行为,因此运行时不会向无关的生产方类别施加隐式默认值。
@@ -79,7 +79,7 @@ job id 在运行时全局可见且可预测,因此注册表会授权每次访
流式读取共享一个任务作用域内的消费游标,因为所属模型是预期读取方。UI 或多个独立读取方需要单独的非消费式观察 API;共享该游标会让读取方彼此消费对方的输出。
-系统提示词要求模型保留 job id、在后台工作运行时继续处理独立工作而非忙轮询或重复启动同一任务、在给出最终答案前收集相关任务,并终止不再重要的工作。完成时,系统会向确切所有者的会话交付一条已记录的消息:繁忙的所有者走注入,空闲的所有者会被唤醒,其有界策略由[空闲所有者唤醒决策](../feature/2026-08-11-background-job-completion-wakes-an-idle-owner.md)负责。
+系统提示词要求模型保留 job id、在后台工作运行时继续处理独立工作而非忙轮询或重复启动同一任务、在给出最终答案前收集相关任务,并终止不再重要的工作。完成时,系统会向确切所有者的会话交付一条已记录的消息:繁忙的所有者走注入,空闲的所有者会被唤醒,其有界策略由[空闲所有者唤醒决策](../feature/2026-08-11-background-job-completion-wakes-an-idle-owner.zh.md)负责。
当读取或等待交付终止任务、尚在等待的等待方在结算时认领了投递,或模型显式终止任务时,运行时将终止任务标为 `reported`。已报告的任务不会注入冗余的完成通知。监听器失败会独立记录,不会阻止后续监听器,也不会被等待方或资源销毁过程等待。当快照携带 `outputLimitBytes` 时,`dsh-tool-jobs` 会保持 UTF-8 边界,并复用生产方已有的截断标记,而不会重复添加。读取会为状态后缀预留空间并保留输出尾部;完成通知会先为稳定的 `background job ` 前缀与 `job_output` 指令预留空间,再截断可变的 kind、label、status、detail,乃至截断标记本身,因此 PTY 的最小上限仍能标识需要收集的任务。任务控制器在策略有机会拒绝或短路分发之前,于最先执行的 pre-execute 监听器中解析调用方可见的生产方上限;随后通过任务定义最后一道的 `finalizeContent` 回调应用该上限,使规范化的工具错误、外层流水线失败与单文本策略结果都无法绕过该边界;经特意结构化的多块策略结果仍由策略拥有其形状与大小。
@@ -105,7 +105,7 @@ bash seam 暴露 `resolve`、`run` 和 `start`。`start(spec)` 返回一个 `She
### 立即抽象任务运行时后端
-当前 `JobStart.run()` 约定传入进程内回调与确切的 `Agent` 对象。持久化后端会改变身份、重启、所有权与观察语义,因此在引入之时注册表保持为单一具体服务,而非固化错误的边界。[任务注册表约定 Agent Note](2026-07-26-job-registry-seam.md)后来在不改变这些进程内语义的前提下,将约定与进程内实现分离。
+当前 `JobStart.run()` 约定传入进程内回调与确切的 `Agent` 对象。持久化后端会改变身份、重启、所有权与观察语义,因此在引入之时注册表保持为单一具体服务,而非固化错误的边界。[任务注册表约定 Agent Note](2026-07-26-job-registry-seam.zh.md)后来在不改变这些进程内语义的前提下,将约定与进程内实现分离。
### 由消费方负责授权或清理事件
@@ -131,7 +131,7 @@ bash seam 暴露 `resolve`、`run` 和 `start`。`start(spec)` 返回一个 `She
## 后果
-bash 命令与 subagent 共享一套 id 词汇、列表、通知格式、提示词习惯和控制工具。新的长时间运行生产方只需实现执行钩子,而不必再实现一套注册表与工具族。[工具实操手册](../../../../docs/cookbook/adding-a-tool.md)将生产方指向本约定。
+bash 命令与 subagent 共享一套 id 词汇、列表、通知格式、提示词习惯和控制工具。新的长时间运行生产方只需实现执行钩子,而不必再实现一套注册表与工具族。[工具实操手册](../../../../docs/cookbook/adding-a-tool.zh.md)将生产方指向本约定。
单个确切 owner 无法再无限增加进程内由 Task 承载的工作,另一个 owner 也不会消耗它的额度。取消请求会继续占用容量,直到生产方真正释放资源,因此用新工作替换缓慢停止的任务不会突破已配置的实时资源预算。
diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml
index f9b830c3b7..dcaeb8c34b 100644
--- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.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/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md
-2026-06-21-bounded-llm-request-recovery.md: 3a91d77fe9c08fbcc3afdce4dad9a38e288b4723
-2026-06-21-bounded-llm-request-recovery.zh.md: a6b342b19236251e638242c1e9df6b3d6ed557c0
+2026-06-21-bounded-llm-request-recovery.md: e725a025f2d8b0d5e8eaf4137f07d8eab4448bf4
+2026-06-21-bounded-llm-request-recovery.zh.md: 9e2263b05888797eaaaeb82859730d1c4a728cea
diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md
index 3a91d77fe9..e725a025f2 100644
--- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md
+++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md
@@ -4,13 +4,13 @@ Status: implemented
English | [中文](2026-06-21-bounded-llm-request-recovery.zh.md)
-The [per-provider request retry policy](../feature/2026-07-24-provider-retry-policies.md) extends this foundation with exact-provider configuration and an explicit unbounded mode. This note continues to own structured failure facts, the closed-step recovery boundary, normal mode's transient defaults, visible single attempts, and durable retry status. [Terminal LLM stream failures](2026-07-29-terminal-llm-stream-failures.md) supersedes its thrown-error identity and stream-sidecar mechanism.
+The [per-provider request retry policy](../feature/2026-07-24-provider-retry-policies.md) extends this foundation with exact-provider configuration and an explicit unbounded mode. This note continues to own structured failure facts, the failed-attempt recovery boundary, normal mode's transient defaults, visible single attempts, and durable retry status. [Terminal LLM stream failures](2026-07-29-terminal-llm-stream-failures.md) supersedes its thrown-error identity and stream-sidecar mechanism.
## Problem
Provider adapters can fail by throwing during dispatch or iteration or by ending with `finish { kind: 'error' | 'aborted' }`. The final adapter boundary normalizes thrown values to that terminal finish protocol before `dsh-agent-loop` receives them; middleware and result-processing defects remain thrown. The loop offers a terminal model-request failure to `agent/request-error`. An unhandled failure is terminal; a handling listener repairs policy-owned state, returns `{ kind: 'retry' }`, and stops waterfall delegation. The [retry-action decision](../simplification/2026-07-27-request-error-retry-action.md) owns this return contract.
-That boundary is already safe for another request attempt. Raw `assistant/chunk` events carry the failed `turn` and `step`, message derivation ignores them unless a successful `assistant/message` cites them, tool calls are dispatched only after a successful terminal finish and assembly, and a retry opens a new numbered turn from the durable log. The harness therefore does not need a second response lifecycle or tentative-output protocol to keep two attempts separate.
+That boundary is already safe for another request attempt. Raw `assistant/chunk` events carry the failed `turn` and `step`, message derivation ignores them unless a successful `assistant/message` cites them, tool calls are dispatched only after a successful terminal finish and assembly, and a retry reconstructs its next attempt from the durable log. The harness therefore does not need a second response lifecycle or tentative-output protocol to keep two attempts separate.
The prior boundary left three narrower gaps.
@@ -52,7 +52,7 @@ The shared transient-code set is intentionally small: adapter mappings for `RATE
`@deepseek-ai/dsh-llm-retry` is a function plugin that listens to `agent/request-error`. It introduces no service or new loop branch; the agent-loop package changes only the data carried through its existing failed-step recovery control flow.
-The `agent/request-error` waterfall carries the current `LlmFailure`, an immutable list of prior failures that authorized retry turns in the consecutive recovery sequence, and the serving registration's immutable retry policy. The loop transports but does not interpret that policy, owns the consecutive failure history, and clears it after a successful model request. Normal `dsh-llm-retry` policy counts durable retry records scheduled by the same exact-provider policy, while `dsh-compaction-basic` keeps its own context-overflow budget. Alternating transient and context-overflow failures therefore consume their owning finite budgets independently; the maximum request count is one plus the sum of the loaded finite budgets.
+The `agent/request-error` waterfall carries the current `LlmFailure`, an immutable list of prior failures that authorized retries in the consecutive recovery sequence, and the serving registration's immutable retry policy. The loop transports but does not interpret that policy, owns the consecutive failure history, and clears it after a successful model request. Normal `dsh-llm-retry` policy counts durable retry records scheduled by the same exact-provider policy, while `dsh-compaction-basic` keeps its own context-overflow budget. Alternating transient and context-overflow failures therefore consume their owning finite budgets independently; the maximum request count is one plus the sum of the loaded finite budgets.
The [provider-policy decision](../feature/2026-07-24-provider-retry-policies.md) owns the current configuration shape. Provider adapters register their nested `retryPolicy`; omission uses normal defaults: two transient retries, a 500 millisecond initial delay, a 10 second delay cap, 10 percent jitter, and the five transient codes above. The count and delay bounds match the conservative edge of the inspected implementations: [OpenCode uses two request retries with 500 ms/10 s bounds](https://github.com/anomalyco/opencode/blob/9976269ab1accfc9f9dc98a4a688c516934de422/%70ackages/llm/src/route/executor.ts#L36-L39), [Pi separates three agent-level retries from provider retries and defaults provider retries to zero](https://github.com/earendil-works/pi/blob/3da591ab74ab9ab407e72ed882600b2c851fae21/%70ackages/coding-agent/docs/settings.md#L139-L147), and [Codex uses finite request/stream budgets plus a five-minute idle timeout](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/model-provider-info/src/lib.rs#L25-L33). Ten percent follows [Codex's bounded jitter](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/codex-client/src/retry.rs#L40-L47).
@@ -68,7 +68,7 @@ The agent-spine demo bundle loads the plugin so the shared stdio/TUI, one-shot C
### Make one layer own visible attempts
-Adapters perform one provider request per `stream()` call. The pi-ai adapter removes public `maxRetries` and `maxRetryDelayMs` profile fields and disables library retries; the hand-written adapter keeps its current single-attempt behavior. This prevents an SDK budget from multiplying the agent budget and ensures every transient retry is represented by a closed failed step plus `llm/retry`.
+Adapters perform one provider request per `stream()` call. The pi-ai adapter removes public `maxRetries` and `maxRetryDelayMs` profile fields and disables library retries; the hand-written adapter keeps its current single-attempt behavior. This prevents an SDK budget from multiplying the agent budget and ensures every transient retry is represented by its recorded failed attempt plus `llm/retry`.
`ctx.llm.stream()` remains the raw one-attempt waterfall. Direct callers such as compaction summarization receive the structured failure but do not gain automatic retry, because they have no agent step boundary or general durable place to separate attempts. A future direct-call consumer may justify a buffering helper that retries only before emitting a chunk; this decision adds no such helper.
@@ -82,9 +82,9 @@ Boundary tests prove termination at both actual transports. The hand-written ada
### Keep attempts separate in the existing log
-A failed attempt may leave `assistant/chunk` events in its closed step, but it never appends `assistant/message` and never dispatches a tool. A retry closes the failed turn, opens the next numbered turn, reconstructs the request from the durable surface, and produces its own chunks. UIs may render live chunks while a step is open, then mark or clear that transient view when `llm/retry` identifies the failed step or `turn/end` records failure. Web validates the complete retry payload contract, clears the failed partial at `llm/retry`, projects consecutive retry-turn events into one stable row updated to the latest attempt, and derives scheduled, started, or cancelled status from subsequent turn facts. Its countdown anchors the scheduled delay to browser receipt rather than the Host event clock, uses ceiling-rounded seconds with a one-second floor, animates only while unresolved, and keeps exact latest failure details collapsed behind the row. Retry nodes anchor their own trajectory turn even when the failed attempt has no assistant node. Message derivation continues to ignore the failed chunks, and Web applies the same projection during history rebuild so refreshing cannot resurrect discarded partials or duplicate retry rows.
+A failed attempt may leave `assistant/chunk` events in its step, but it never appends `assistant/message` and never dispatches a tool. A retry continues inside the failing turn and step, reconstructs the request from the durable surface, and produces its own chunks; only the final outcome closes the turn. UIs may render live chunks while a step is open, then mark or clear that transient view when `llm/retry` identifies the failed attempt or `turn/end` records failure. Web validates the complete retry payload contract, clears the failed partial at `llm/retry`, projects each producer-correlated `retryId` chain into one stable row updated to the latest attempt, and derives scheduled, started, or cancelled status from `llm/retry-started` and the owning turn and step boundaries' closure. Its countdown anchors the scheduled delay to browser receipt rather than the Host event clock, uses ceiling-rounded seconds with a one-second floor, animates only while unresolved, and keeps exact latest failure details collapsed behind the row. Retry nodes anchor their own trajectory turn even when the failed attempt has no assistant node. Message derivation continues to ignore the failed chunks, and Web applies the same projection during history rebuild so refreshing cannot resurrect discarded partials or duplicate retry rows.
-If recovery is exhausted, the final failure is stored once on `turn/end.reason` with the structured facts. Web derives one `turn-error` node at that sequence position and renders its display-safe message and optional code inline; AUTH projections replace provider copy that may echo credential fragments with `API key is invalid`, while the raw diagnostic remains in the session log. The same fold runs for live events and history replay. If transient recovery continues, `llm/retry` is the durable home for that attempt's failure and delay, so its failed turn does not also gain a terminal error row. No standalone final-error event or response-id vocabulary is added.
+If recovery is exhausted, the final failure is stored once on `turn/end.reason` with the structured facts. Web derives one `turn-error` node at that sequence position and renders its display-safe message and optional code inline; AUTH projections replace provider copy that may echo credential fragments with `API key is invalid`, while the raw diagnostic remains in the session log. The same fold runs for live events and history replay. While transient recovery continues, `llm/retry` is the durable home for each intermediate failure and delay; the terminal row exists only once `turn/end` records the error, and because exhausted recovery shares the failing turn, the turn's retry history never suppresses that row — the settled retry chain and the terminal error render side by side. No standalone final-error event or response-id vocabulary is added.
## Out of scope
@@ -114,15 +114,15 @@ If recovery is exhausted, the final failure is stored once on `turn/end.reason`
- Each provider adapter validates its nested retry policy at Loader startup, and `ctx.llm` captures it with the route; normal mode delegates ineligible paths and makes at most `maxRetries + 1` provider requests when no other policy applies.
- HMR-during-backoff tests prove disposal unregisters the listener, aborts and awaits its captured callbacks, emits no retry decision after disposal, and leaves no timer or promise alive.
- Pure unit tests cover transient-code selection, exponential backoff and jitter bounds, valid and over-cap `Retry-After`, exhausted budgets, deterministic timer/random hooks, and abort during backoff.
-- Real agent-loop tests cover failure before chunks, partial chunks then failure, thrown and in-band failures, retry to success in a new turn, exhaustion to structured `turn/end.reason`, and composition with `dsh-compaction-basic` context-overflow recovery.
+- Real agent-loop tests cover failure before chunks, partial chunks then failure, thrown and in-band failures, retry to success inside the same turn, exhaustion to structured `turn/end.reason`, and composition with `dsh-compaction-basic` context-overflow recovery.
- The partial-chunk integration test proves failed chunks remain attributed to the failed step, no assistant message or tool side effect is committed for that step, and the successful retry records its own chunk seqs and provider/model route.
-- The plugin-owned `llm/retry` event is non-surface, survives JSONL and SQLite round trips, is ignored by message derivation, and drives TUI and Web retraction plus scheduled-retry rendering. Client tests cover complete wire validation, clock-independent countdown, cancellation versus completed retry labels, and trajectory attribution; keyless UI snapshots cover Web scheduling and success, a real Web composition test covers partial transport failure through recovery, and ACP automation snapshots confirm that a discarded attempt stays off the wire while the recovered reply is emitted.
+- The plugin-owned `llm/retry` event is non-surface, survives JSONL and SQLite round trips, is ignored by message derivation, and drives TUI and Web retraction plus scheduled-retry rendering. Client tests cover complete wire validation, clock-independent countdown, cancellation versus completed retry labels, and trajectory attribution; keyless UI snapshots cover Web scheduling and success, real Web composition tests cover partial transport failure through recovery and exhausted recovery's terminal error row beside the settled retry chain, and ACP automation snapshots confirm that a discarded attempt stays off the wire while the recovered reply is emitted.
- Idle-watchdog tests prove the stable signal is rearmed only while `next()` is outstanding, disarmed during consumer think time and in `finally`, and classified separately from a total-call deadline and an earlier caller abort; adapter tests prove the signal stops the underlying request rather than merely detaching it.
- Direct `ctx.llm.stream()` callers remain single-attempt and receive the same structured failure facts.
## Consequences
-- Every retry attempt is visible as a closed failed turn plus `llm/retry`, and adapter-level single-attempt behavior prevents hidden SDK retries from multiplying policy decisions. A retry can still duplicate provider billing even when no chunk arrived; normal mode limits that risk, while explicit always mode accepts it until cancellation or success.
+- Every retry attempt is visible inside its owning turn as the failed attempt's chunks plus `llm/retry`, and adapter-level single-attempt behavior prevents hidden SDK retries from multiplying policy decisions. A retry can still duplicate provider billing even when no chunk arrived; normal mode limits that risk, while explicit always mode accepts it until cancellation or success.
- Provider SDKs may hide status or retry headers. Those adapters retain the stable facts they expose and otherwise use a coarse code rather than letting recovery policy parse fragile text.
- Durable retry events expand the session protocol and UI state machine. Shipping the event and its consumer together prevents an unused telemetry vocabulary, but later schema changes still require persistence and replay work.
- Clearing a failed step's live chunks can visibly retract output. That is preferable to presenting discarded text or partial tool JSON as committed history, and snapshots pin the transition.
@@ -136,3 +136,4 @@ If recovery is exhausted, the final failure is stored once on `turn/end.reason`
- [Timeout deadline library](../../implemented/architecture/2026-07-06-timeout-deadline-library.md) separates shared deadline classification from capability-owned termination.
- [After-call compaction pressure and context-overflow recovery](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md) owns the current closed-step request-recovery extension point and bounded overflow retry.
- [Provider-routed LLM adapters](../../implemented/architecture/2026-07-14-provider-routed-llm-adapters.md) owns explicit provider/model routing and the one-adapter-per-provider invariant.
+- [Terminal turn errors survive same-turn retry history](../bug-fix/2026-08-20-turn-error-survives-same-turn-retry-history.md) owns the removal of the Web retry-history suppression that hid exhausted recovery's terminal error row.
diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md
index a6b342b192..9e2263b058 100644
--- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md
@@ -4,13 +4,13 @@ Status: implemented
[English](2026-06-21-bounded-llm-request-recovery.md) | 中文
-[按提供方配置的请求重试策略](../feature/2026-07-24-provider-retry-policies.md)在此基础上增加了确切提供方配置与显式无界 mode。本说明继续负责结构化失败事实、已关闭步骤的恢复边界、normal mode 的暂时性默认值、可见的单次尝试和持久重试状态。[LLM(大语言模型)流的终止失败](2026-07-29-terminal-llm-stream-failures.md)取代了其中关于抛出错误身份和流 sidecar 的机制。
+[按提供方配置的请求重试策略](../feature/2026-07-24-provider-retry-policies.zh.md)在此基础上增加了确切提供方配置与显式无界 mode。本说明继续负责结构化失败事实、失败尝试的恢复边界、normal mode 的暂时性默认值、可见的单次尝试和持久重试状态。[LLM(大语言模型)流的终止失败](2026-07-29-terminal-llm-stream-failures.zh.md)取代了其中关于抛出错误身份和流 sidecar 的机制。
## 问题
-提供方适配器可能在分发或迭代时抛出异常,也可能以 `finish { kind: 'error' | 'aborted' }` 结束。最终适配器边界会在 `dsh-agent-loop` 接收前把抛出值规范化为该终止 finish 协议;middleware 与结果处理缺陷仍会抛出。loop 会将终止模型请求失败交给 `agent/request-error`。未被处理的失败是终态;处理失败的监听器修复策略自有状态,返回 `{ kind: 'retry' }`,并停止 waterfall(瀑布式事件)委托。[重试动作决策](../simplification/2026-07-27-request-error-retry-action.md)规定这一返回约定。
+提供方适配器可能在分发或迭代时抛出异常,也可能以 `finish { kind: 'error' | 'aborted' }` 结束。最终适配器边界会在 `dsh-agent-loop` 接收前把抛出值规范化为该终止 finish 协议;middleware 与结果处理缺陷仍会抛出。loop 会将终止模型请求失败交给 `agent/request-error`。未被处理的失败是终态;处理失败的监听器修复策略自有状态,返回 `{ kind: 'retry' }`,并停止 waterfall(瀑布式事件)委托。[重试动作决策](../simplification/2026-07-27-request-error-retry-action.zh.md)规定这一返回约定。
-该边界已能安全地再次发起请求。原始 `assistant/chunk` 事件携带失败的 `turn` 和 `step`;除非某条成功的 `assistant/message` 引用这些事件,否则消息派生会忽略它们。只有终止性 finish 成功且组装完成后,系统才会分发工具调用;重试则会从持久日志开启新的编号轮次。因此,harness 无需引入第二套响应生命周期或暂定输出协议,即可分隔两次尝试。
+该边界已能安全地再次发起请求。原始 `assistant/chunk` 事件携带失败的 `turn` 和 `step`;除非某条成功的 `assistant/message` 引用这些事件,否则消息派生会忽略它们。只有终止性 finish 成功且组装完成后,系统才会分发工具调用;重试则会从持久日志重建下一次尝试。因此,harness 无需引入第二套响应生命周期或暂定输出协议,即可分隔两次尝试。
此前的边界还留有三个较窄的缺口。
@@ -46,15 +46,15 @@ agent loop(智能体循环)会将终止 finish 的 `LlmFailure` 传给 `agen
适配器会先提取结构化事实,再回退到消息检查。它们会验证 HTTP 状态,将 `Retry-After` 的秒数或日期解析为正的有限毫秒延迟,在提供方公开请求 id 时将其品牌化,并区分自身超时与调用方中止。提供方专用 code 和消息可以细化映射,但恢复监听器不会解析它们。
-共享的暂时性 code 集有意保持很小:适配器针对 `RATE_LIMIT` 和 `SERVER` 的映射,远程失败使用的显式 `TIMEOUT` 和 `TRANSPORT` code,以及提供方响应已完成却没有内容块时使用的 `EMPTY_RESPONSE`。两个适配器都会把最后一种情况归类为错误 finish;详见[空模型响应可重试](../bug-fix/2026-07-24-empty-model-response-is-retryable.md)。身份验证、配额、无效请求、上下文溢出、协议、中止和未知失败都保留不同的稳定 code,且默认不属于暂时性失败。新增 code 需要适配器 fixture(测试前置数据)和已记录的策略决策;无需扩展第二个失败类枚举。
+共享的暂时性 code 集有意保持很小:适配器针对 `RATE_LIMIT` 和 `SERVER` 的映射,远程失败使用的显式 `TIMEOUT` 和 `TRANSPORT` code,以及提供方响应已完成却没有内容块时使用的 `EMPTY_RESPONSE`。两个适配器都会把最后一种情况归类为错误 finish;详见[空模型响应可重试](../bug-fix/2026-07-24-empty-model-response-is-retryable.zh.md)。身份验证、配额、无效请求、上下文溢出、协议、中止和未知失败都保留不同的稳定 code,且默认不属于暂时性失败。新增 code 需要适配器 fixture(测试前置数据)和已记录的策略决策;无需扩展第二个失败类枚举。
### 将重试策略放在现有失败步骤扩展点上
`@deepseek-ai/dsh-llm-retry` 是监听 `agent/request-error` 的函数插件。它不引入服务或新的循环分支;agent-loop 包仅会更改通过现有失败步骤恢复控制流携带的数据。
-`agent/request-error` waterfall 携带当前 `LlmFailure`、在连续恢复序列中授权重试轮次的不可变先前失败列表,以及提供服务的注册项所携带的不可变重试策略。循环只传递而不解释该策略;它拥有连续失败历史,并在模型请求成功后清除。`dsh-llm-retry` 的 normal 策略统计由同一项确切提供方策略安排的持久重试记录,`dsh-compaction-basic` 则维护自己的上下文溢出预算。因此,暂时性失败与上下文溢出交替出现时,会各自独立消耗其有限预算;最大请求数等于 1 加上所有已加载有限预算之和。
+`agent/request-error` waterfall 携带当前 `LlmFailure`、在连续恢复序列中授权重试的不可变先前失败列表,以及提供服务的注册项所携带的不可变重试策略。循环只传递而不解释该策略;它拥有连续失败历史,并在模型请求成功后清除。`dsh-llm-retry` 的 normal 策略统计由同一项确切提供方策略安排的持久重试记录,`dsh-compaction-basic` 则维护自己的上下文溢出预算。因此,暂时性失败与上下文溢出交替出现时,会各自独立消耗其有限预算;最大请求数等于 1 加上所有已加载有限预算之和。
-当前配置形状由[提供方策略决策](../feature/2026-07-24-provider-retry-policies.md)规定。提供方适配器会注册嵌套的 `retryPolicy`;省略时使用 normal 默认值:两次暂时性重试、500 毫秒初始延迟、10 秒延迟上限、10% 抖动,以及上述五个暂时性 code。计数与延迟边界参考了所调查实现中较保守的一端:[OpenCode 使用两次请求重试,延迟边界为 500 毫秒/10 秒](https://github.com/anomalyco/opencode/blob/9976269ab1accfc9f9dc98a4a688c516934de422/%70ackages/llm/src/route/executor.ts#L36-L39);[Pi 将三次 agent 级重试与提供方重试分开,且提供方重试默认为零](https://github.com/earendil-works/pi/blob/3da591ab74ab9ab407e72ed882600b2c851fae21/%70ackages/coding-agent/docs/settings.md#L139-L147);[Codex 使用有限请求/流预算以及五分钟空闲超时](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/model-provider-info/src/lib.rs#L25-L33)。10% 抖动参考 [Codex 的有界抖动](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/codex-client/src/retry.rs#L40-L47)。
+当前配置形状由[提供方策略决策](../feature/2026-07-24-provider-retry-policies.zh.md)规定。提供方适配器会注册嵌套的 `retryPolicy`;省略时使用 normal 默认值:两次暂时性重试、500 毫秒初始延迟、10 秒延迟上限、10% 抖动,以及上述五个暂时性 code。计数与延迟边界参考了所调查实现中较保守的一端:[OpenCode 使用两次请求重试,延迟边界为 500 毫秒/10 秒](https://github.com/anomalyco/opencode/blob/9976269ab1accfc9f9dc98a4a688c516934de422/%70ackages/llm/src/route/executor.ts#L36-L39);[Pi 将三次 agent 级重试与提供方重试分开,且提供方重试默认为零](https://github.com/earendil-works/pi/blob/3da591ab74ab9ab407e72ed882600b2c851fae21/%70ackages/coding-agent/docs/settings.md#L139-L147);[Codex 使用有限请求/流预算以及五分钟空闲超时](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/model-provider-info/src/lib.rs#L25-L33)。10% 抖动参考 [Codex 的有界抖动](https://github.com/openai/codex/blob/0fb559f0f6e231a88ac02ea002d3ecd248e2b515/codex-rs/codex-client/src/retry.rs#L40-L47)。
对于预算未耗尽的合格失败,从 1 开始的暂时性重试计数使用有界指数退避。有效的 `providerRetryAfterMs` 只有在不超过 `maxDelayMs` 时才会取代指数退避;提供方延迟更长时,系统会委托给下一监听器,而不会违反提供方指令提前重试。本地退避乘以 `[1 - jitterRatio, 1 + jitterRatio]` 内的注入随机因子,并将最终值限制到 `maxDelayMs`;提供方延迟不加抖动。
@@ -68,7 +68,7 @@ agent-spine 演示组合包加载该插件,因此共享的 stdio/TUI、一次
### 由单一层负责可见的尝试
-适配器每次调用 `stream()` 只执行一次提供方请求。pi-ai 适配器移除公开的 `maxRetries` 和 `maxRetryDelayMs` profile 字段,并禁用库内部重试;手写适配器保持现有的单次尝试行为。这样既避免 SDK 预算成倍放大 agent 预算,又能确保每次暂时性重试都由一个已关闭的失败步骤加 `llm/retry` 表示。
+适配器每次调用 `stream()` 只执行一次提供方请求。pi-ai 适配器移除公开的 `maxRetries` 和 `maxRetryDelayMs` profile 字段,并禁用库内部重试;手写适配器保持现有的单次尝试行为。这样既避免 SDK 预算成倍放大 agent 预算,又能确保每次暂时性重试都由其记录在案的失败尝试加 `llm/retry` 表示。
`ctx.llm.stream()` 仍是原始的单次尝试 waterfall。压缩(compaction)摘要等直接调用方会收到结构化失败,但不会自动获得重试,因为它们没有 agent 步骤边界,也没有可供分隔尝试的通用持久位置。未来的直接调用消费方可能会需要一个缓冲辅助函数,仅在尚未发出任何分片时重试;本决策不增加此类辅助函数。
@@ -82,9 +82,9 @@ agent-spine 演示组合包加载该插件,因此共享的 stdio/TUI、一次
### 在现有日志中分隔尝试
-一次失败尝试可以在已关闭的步骤中留下 `assistant/chunk` 事件,但绝不会追加 `assistant/message`,也不会分发工具。重试会关闭失败轮次,开启下一个编号轮次,从持久表层重建请求,并生成自己的分片。步骤仍处于打开状态时,UI 可以渲染实时分片;当 `llm/retry` 标识失败步骤,或 `turn/end` 记录失败时,UI 再标记或清除这份暂时视图。Web 会验证完整的重试载荷约定,在 `llm/retry` 到达时清除失败的部分输出,将连续重试轮次的事件投影为稳定的一行,并用最新一次尝试更新该行,再从后续轮次事实派生 scheduled、started 或 cancelled 状态。倒计时以浏览器收到事件的时刻为计划延迟的起点,而不是使用 Host 事件时钟;它按向上取整且不低于 1 秒的秒数显示,仅在重试尚未结束时显示动画,并把最近一次失败的准确详情折叠在该行之后。即使失败尝试没有 assistant 节点,重试节点也会锚定自身的轨迹轮次。消息派生仍会忽略失败分片;Web 在重建历史时也会应用同一投影,因此刷新页面不会让已丢弃的部分输出重新出现,也不会生成重复的重试行。
+一次失败尝试可以在其步骤中留下 `assistant/chunk` 事件,但绝不会追加 `assistant/message`,也不会分发工具。重试在失败的轮次与步骤内继续,从持久表层重建请求,并生成自己的分片;只有最终结果才会关闭该轮次。步骤仍处于打开状态时,UI 可以渲染实时分片;当 `llm/retry` 标识失败尝试,或 `turn/end` 记录失败时,UI 再标记或清除这份暂时视图。Web 会验证完整的重试载荷约定,在 `llm/retry` 到达时清除失败的部分输出,将每条生产方关联的 `retryId` 重试链投影为稳定的一行,并用最新一次尝试更新该行,再从 `llm/retry-started` 与所属轮次、步骤边界的关闭派生 scheduled、started 或 cancelled 状态。倒计时以浏览器收到事件的时刻为计划延迟的起点,而不是使用 Host 事件时钟;它按向上取整且不低于 1 秒的秒数显示,仅在重试尚未结束时显示动画,并把最近一次失败的准确详情折叠在该行之后。即使失败尝试没有 assistant 节点,重试节点也会锚定自身的轨迹轮次。消息派生仍会忽略失败分片;Web 在重建历史时也会应用同一投影,因此刷新页面不会让已丢弃的部分输出重新出现,也不会生成重复的重试行。
-如果恢复预算耗尽,最终失败会连同结构化事实在 `turn/end.reason` 中存储一次。Web 会在该序列位置派生一个 `turn-error` 节点,并内联渲染适合展示的消息与可选错误码;AUTH 投影会把可能回显凭据片段的提供方文案替换为 `API key is invalid`,原始诊断仍保留在会话日志中。实时事件和历史回放使用同一套折叠逻辑。如果暂时性恢复继续,`llm/retry` 就是该次尝试的失败与延迟的持久归属位置,因此该失败轮次不会再获得终态错误行。本决策不增加独立的最终错误事件或响应 id 词汇。
+如果恢复预算耗尽,最终失败会连同结构化事实在 `turn/end.reason` 中存储一次。Web 会在该序列位置派生一个 `turn-error` 节点,并内联渲染适合展示的消息与可选错误码;AUTH 投影会把可能回显凭据片段的提供方文案替换为 `API key is invalid`,原始诊断仍保留在会话日志中。实时事件和历史回放使用同一套折叠逻辑。暂时性恢复继续期间,`llm/retry` 是每次中间失败与延迟的持久归属位置;终态错误行只在 `turn/end` 记录错误后才存在,而由于耗尽的恢复与失败共享同一轮次,该轮次的重试历史绝不会抑制这一行——定格的重试链与终态错误并列渲染。本决策不增加独立的最终错误事件或响应 id 词汇。
## 不在范围内
@@ -100,7 +100,7 @@ agent-spine 演示组合包加载该插件,因此共享的 stdio/TUI、一次
- **向 `dsh-llm` 增加响应开始、中断、丢弃、失败和提交事件**:拒绝采用,因为 agent 日志已经分隔原始分片、成功消息和编号尝试。第二套状态机会重复归属关系,又不能支持有界的同路由重试。
- **增加逻辑路由、能力矩阵和故障转移选择**:拒绝采用,因为当前请求已经显式指定提供方和模型,每个提供方由一个适配器负责,而且没有当前消费方要求自动回退或能够证明语义兼容性。
- **把 `retryable` 或 `failover` 放在 `LlmFailure` 上**:拒绝采用,因为适配器报告事实,部署策略决定动作。同一个 429 可以在交互式组合包中重试,也可以在成本受限的批处理中被拒绝。
-- **只要调用方仍处于活跃状态就无限重试**:[按提供方配置的策略](../feature/2026-07-24-provider-retry-policies.md)对显式 `always` 配置项推翻了这项拒绝,同时保留有界的 normal mode 作为默认值。
+- **只要调用方仍处于活跃状态就无限重试**:[按提供方配置的策略](../feature/2026-07-24-provider-retry-policies.zh.md)对显式 `always` 配置项推翻了这项拒绝,同时保留有界的 normal mode 作为默认值。
- **只通过进程 logger 记录重试状态**:拒绝采用,因为进程日志无法重建会话行为,也不能驱动回放后的 UI 状态。
- **只保留扁平 code**:拒绝采用,因为重试延迟和提供方请求 id 是结构化的提供方事实,而当不同协议失败共用一个稳定 code 时,诊断还需要 HTTP 状态。
@@ -114,15 +114,15 @@ agent-spine 演示组合包加载该插件,因此共享的 stdio/TUI、一次
- 每个提供方适配器都在 Loader 启动时验证其嵌套重试策略,`ctx.llm` 则将该策略与路由一同捕获;normal mode 会委托不合格路径,而且在没有其他策略时最多发起 `maxRetries + 1` 次提供方请求。
- 退避期间执行 HMR 的测试证明:dispose 过程会注销监听器、中止并等待其捕获的回调,dispose 后不发出重试决策,也不留下存活的定时器或 promise。
- 纯单元测试覆盖暂时性 code 选择、指数退避和抖动边界、有效及超出上限的 `Retry-After`、耗尽的预算、确定性定时器/随机数钩子,以及退避期间中止。
-- 真实 agent-loop 测试覆盖分片前失败、部分分片后失败、抛出及带内失败、在新轮次中重试至成功、耗尽后写入结构化 `turn/end.reason`,以及与 `dsh-compaction-basic` 上下文溢出恢复的组合。
+- 真实 agent-loop 测试覆盖分片前失败、部分分片后失败、抛出及带内失败、在同一轮次内重试至成功、耗尽后写入结构化 `turn/end.reason`,以及与 `dsh-compaction-basic` 上下文溢出恢复的组合。
- 部分分片集成测试证明:失败分片仍归属于失败步骤,该步骤不会提交 assistant 消息或工具副作用,成功的重试会记录自己的分片 seq 和提供方/模型路由。
-- 插件拥有的不进入表层的 `llm/retry` 事件可在 JSONL 和 SQLite 往返后保留,被消息派生忽略,并驱动 TUI 和 Web 撤回及计划重试渲染。客户端测试覆盖完整的 wire 验证、独立于时钟的倒计时、已取消与已完成重试标签的区别以及轨迹归属;无密钥 UI 快照覆盖 Web 的调度与成功,真实 Web 组合测试覆盖部分传输失败直至恢复,ACP 自动化快照确认,被丢弃的尝试不会通过协议发出,而恢复后的回复会正常发出。
+- 插件拥有的不进入表层的 `llm/retry` 事件可在 JSONL 和 SQLite 往返后保留,被消息派生忽略,并驱动 TUI 和 Web 撤回及计划重试渲染。客户端测试覆盖完整的 wire 验证、独立于时钟的倒计时、已取消与已完成重试标签的区别以及轨迹归属;无密钥 UI 快照覆盖 Web 的调度与成功,真实 Web 组合测试覆盖部分传输失败直至恢复,以及耗尽后终态错误行与定格重试链并列的画面,ACP 自动化快照确认,被丢弃的尝试不会通过协议发出,而恢复后的回复会正常发出。
- 空闲看门狗测试证明:只有 `next()` 尚未完成时才会重新布防稳定信号;在消费方思考期间及 `finally` 中会解除布防;它与总调用 deadline 以及更早发生的调用方中止分开分类。适配器测试证明该信号会终止底层请求,而不只是与其脱离。
- `ctx.llm.stream()` 的直接调用方仍只尝试一次,并收到相同的结构化失败事实。
## 后果
-- 每次重试尝试都以一个已关闭失败轮次加 `llm/retry` 的形式可见,适配器级的单次尝试行为会防止隐藏的 SDK 重试成倍增加策略决策。即使没有分片到达,重试仍可能造成提供方重复计费;normal mode 会限制此风险,而显式 always mode 会接受它,直至取消或成功。
+- 每次重试尝试都在其所属轮次内以失败尝试的分片加 `llm/retry` 的形式可见,适配器级的单次尝试行为会防止隐藏的 SDK 重试成倍增加策略决策。即使没有分片到达,重试仍可能造成提供方重复计费;normal mode 会限制此风险,而显式 always mode 会接受它,直至取消或成功。
- 提供方 SDK 可能隐藏状态或重试标头。适配器会保留 SDK 公开的稳定事实,否则使用粗粒度 code,而不会让恢复策略解析脆弱的文本。
- 持久重试事件扩展了会话协议和 UI 状态机。事件与其消费方一同交付,可避免产生无人使用的遥测词汇;但以后更改 schema 仍需要同步完成持久化和回放工作。
- 清除失败步骤的实时分片可能会明显撤回输出。与把丢弃的文本或不完整工具 JSON 呈现为已提交历史相比,这是更好的选择;快照固定这一转换。
@@ -131,8 +131,9 @@ agent-spine 演示组合包加载该插件,因此共享的 stdio/TUI、一次
## 相关资料
-- [结构化错误分类体系](../../implemented/architecture/2026-06-11-structured-error-taxonomy.md)负责稳定、可供机器路由的 code 与 cause chaining。
-- [可重建请求](../../implemented/architecture/2026-07-05-reconstructable-requests.md)使提供方/模型和完整请求输入在分发前持久化。
-- [超时 deadline 库](../../implemented/architecture/2026-07-06-timeout-deadline-library.md)将共享的 deadline 分类与能力自身拥有的终止操作分开。
-- [调用后压缩压力与上下文溢出恢复](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)负责当前已关闭步骤的请求恢复扩展点与有界溢出重试。
-- [提供方路由的 LLM 适配器](../../implemented/architecture/2026-07-14-provider-routed-llm-adapters.md)负责显式提供方/模型路由与每个提供方仅有一个适配器的不变量。
+- [结构化错误分类体系](../../implemented/architecture/2026-06-11-structured-error-taxonomy.zh.md)负责稳定、可供机器路由的 code 与 cause chaining。
+- [可重建请求](../../implemented/architecture/2026-07-05-reconstructable-requests.zh.md)使提供方/模型和完整请求输入在分发前持久化。
+- [超时 deadline 库](../../implemented/architecture/2026-07-06-timeout-deadline-library.zh.md)将共享的 deadline 分类与能力自身拥有的终止操作分开。
+- [调用后压缩压力与上下文溢出恢复](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md)负责当前已关闭步骤的请求恢复扩展点与有界溢出重试。
+- [提供方路由的 LLM 适配器](../../implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md)负责显式提供方/模型路由与每个提供方仅有一个适配器的不变量。
+- [Terminal turn errors survive same-turn retry history](../bug-fix/2026-08-20-turn-error-survives-same-turn-retry-history.zh.md)负责移除曾藏掉耗尽恢复终态错误行的 Web 重试历史抑制。
diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml
index 687743c0a4..2b6c63d334 100644
--- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.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/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md
-2026-06-21-mandatory-app-attribution-headers.md: 479d3a46dc41c5cc9ae9b77b81dbef3d6524370b
-2026-06-21-mandatory-app-attribution-headers.zh.md: 75162604623099d50ca87aafd5d45567e2121789
+2026-06-21-mandatory-app-attribution-headers.md: 9e0c029dc03c722512680a563c24e470128ee322
+2026-06-21-mandatory-app-attribution-headers.zh.md: 1427daf8f6065ec2dee324075a8381a625d9e960
diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md
index 479d3a46dc..9e0c029dc0 100644
--- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md
+++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md
@@ -42,7 +42,7 @@ Wire mapping (`attributionHeaders`; header names lowercase in code - HTTP field
|---|---|
| All HTTP-based adapters | `User-Agent: {product}/{version} (+{url})` - the parenthesized `+url` comment stays within RFC 9110's conservative product/comment syntax. |
| Direct DeepSeek endpoint | `User-Agent` for app attribution; `x-deepseek-harness-user-id` and conditional `x-deepseek-harness-session-id` are separate request identity under the DeepSeek-specific decision. Do not send OpenRouter-only headers unless DeepSeek documents an equivalent contract. |
-| OpenRouter endpoints | `User-Agent` only for now. Do not send `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, or `X-OpenRouter-Categories` under this decision. |
+| OpenRouter endpoints | `User-Agent` only. This decision excludes `HTTP-Referer`, `X-OpenRouter-Title`, `X-Title`, and `X-OpenRouter-Categories`. |
| Future providers | `User-Agent` only unless a later provider-specific Agent Note accepts additional headers. Do not reuse `HTTP-Referer` by analogy. |
Endpoint detection is not part of this Agent Note because no endpoint-specific mapping is accepted here. If OpenRouter support lands later, detection must be explicit: either a dedicated OpenRouter provider package or an explicit `provider: 'openrouter'` / `attributionTarget: 'openrouter'` config, not arbitrary path fragments or model names.
diff --git a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md
index 7516260462..1427daf8f6 100644
--- a/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.zh.md
@@ -6,7 +6,7 @@ Status: implemented
## 问题
-LLM(大语言模型)提供方请求应当标识发出请求的产品。这对提供方侧的技术支持、滥用调查、兼容性调试和流量分析都有价值。在本 Agent Note 之前,harness 只做了部分工作:手写的 DeepSeek 适配器发送了一个手动复制的 `User-Agent` 常量(`packages/llm/llm-deepseek/src/adapter.ts`),而基于 pi-ai 的孪生适配器则完全不发送 harness 自有的头部(`packages/llm/llm-pi-ai/src/adapter.ts`)。因此新适配器可以悄无声息地省略归属标识,而基于库的适配器也可能与手写适配器产生偏差——尽管[孪生适配器 Agent Note](2026-06-13-twin-llm-adapters.md) 的存在正是为了确保两种实现中的提供方约定真实可靠。
+LLM(大语言模型)提供方请求应当标识发出请求的产品。这对提供方侧的技术支持、滥用调查、兼容性调试和流量分析都有价值。在本 Agent Note 之前,harness 只做了部分工作:手写的 DeepSeek 适配器发送了一个手动复制的 `User-Agent` 常量(`packages/llm/llm-deepseek/src/adapter.ts`),而基于 pi-ai 的孪生适配器则完全不发送 harness 自有的头部(`packages/llm/llm-pi-ai/src/adapter.ts`)。因此新适配器可以悄无声息地省略归属标识,而基于库的适配器也可能与手写适配器产生偏差——尽管[孪生适配器 Agent Note](2026-06-13-twin-llm-adapters.zh.md) 的存在正是为了确保两种实现中的提供方约定真实可靠。
直接触发因素来自 OpenRouter 的[应用归属](https://openrouter.ai/docs/app-attribution)文档。OpenRouter 根据 `HTTP-Referer` 加上用于展示和分类的头部来创建应用页面和排名。这有价值,但它不是 HTTP 标准中的应用身份机制。风险在于:把 OpenRouter 的精确头部集当作通用标准来采纳,然后将提供方特有的头部泄漏到直连 DeepSeek 的请求、未来的 OpenAI/Anthropic/Vertex 适配器、测试服务器或无限期记录未知字段的代理中。
@@ -24,7 +24,7 @@ LLM(大语言模型)提供方请求应当标识发出请求的产品。这
## 决策
-在 LLM 适配器边界,提供方无关的应用归属是强制的,且仅使用标准 `User-Agent` 头部。规则:每个产品级 LLM 适配器在每个提供方 HTTP 请求上发送一个静态、非机密的应用身份,且每个适配器都有测试证明 `User-Agent` 到达了线路(mock 服务器断言收到的头部;对于基于库的适配器,通过库的头部钩子馈入同一个 mock 服务器断言)。这条规则约束应用归属,不约束提供方特有的请求身份;[DeepSeek 请求身份决策](../feature/2026-08-11-deepseek-request-user-id-header.md)另行负责其用户与会话头部。
+在 LLM 适配器边界,提供方无关的应用归属是强制的,且仅使用标准 `User-Agent` 头部。规则:每个产品级 LLM 适配器在每个提供方 HTTP 请求上发送一个静态、非机密的应用身份,且每个适配器都有测试证明 `User-Agent` 到达了线路(mock 服务器断言收到的头部;对于基于库的适配器,通过库的头部钩子馈入同一个 mock 服务器断言)。这条规则约束应用归属,不约束提供方特有的请求身份;[DeepSeek 请求身份决策](../feature/2026-08-11-deepseek-request-user-id-header.zh.md)另行负责其用户与会话头部。
OpenRouter 应用归属刻意未实现。`HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 和 `X-OpenRouter-Categories` 是 OpenRouter 特有的产品展示头部,不是提供方无关的模型请求归属。它们可以后续由 OpenRouter 适配器或显式 OpenRouter 模式提出,附带自己的隐私/产品决策、测试和文档。在此之前,即使请求指向 OpenRouter,也只发送本决策定义的共享 `User-Agent` 归属。
@@ -42,7 +42,7 @@ OpenRouter 应用归属刻意未实现。`HTTP-Referer`、`X-OpenRouter-Title`
|---|---|
| 所有基于 HTTP 的适配器 | `User-Agent: {product}/{version} (+{url})`——括号中的 `+url` 注释符合 RFC 9110 保守的 product/comment 语法。 |
| 直连 DeepSeek 端点 | `User-Agent` 用于应用归属;`x-deepseek-harness-user-id` 与条件性的 `x-deepseek-harness-session-id` 由 DeepSeek 特有决策作为独立请求身份管理。除非 DeepSeek 文档化了等效约定,否则不发送 OpenRouter 特有头部。 |
-| OpenRouter 端点 | 目前仅 `User-Agent`。本决策下不发送 `HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 或 `X-OpenRouter-Categories`。 |
+| OpenRouter 端点 | 仅发送 `User-Agent`。本决策排除 `HTTP-Referer`、`X-OpenRouter-Title`、`X-Title` 与 `X-OpenRouter-Categories`。 |
| 未来提供方 | 仅 `User-Agent`,除非后续提供方特有的 Agent Note 接受额外头部。不要类比复用 `HTTP-Referer`。 |
端点检测不在本 Agent Note 范围内,因为此处不接受任何端点特有的映射。如果后续支持 OpenRouter,检测必须是显式的:要么是专门的 OpenRouter 提供方包,要么是显式的 `provider: 'openrouter'` / `attributionTarget: 'openrouter'` 配置,而非任意路径片段或模型名称。
diff --git a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml
index bc92549f44..bbdb39100a 100644
--- a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.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/implemented/architecture/2026-06-24-web-capability-seam.md
-2026-06-24-web-capability-seam.md: 7e7b09f19864bd2ad8ad9d69579c1d5c79600cde
-2026-06-24-web-capability-seam.zh.md: d6051eec498edb640773ba367038581cebd1f654
+2026-06-24-web-capability-seam.md: 8c6c088ea5d7345f9955892b2d6054cfae518bbd
+2026-06-24-web-capability-seam.zh.md: 4921c4a4647d180dbb00e6493a19d38584f99bdc
diff --git a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md
index 7e7b09f198..8c6c088ea5 100644
--- a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md
+++ b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.md
@@ -199,7 +199,7 @@ Full page retrieval remains the job of `web_fetch(url)`. Search snippets are dis
## Fetch request and result schema
-The `web_fetch` implementation is an anonymous public HTTP(S) fetch provider, `http`. It fetches bytes from a concrete URL, applies the basic transport hygiene below (http/https-only, credential rejection, byte/time caps, cross-origin redirect blocking), decodes textual content, and returns only the minimal model-useful result: final URL, status code, body, and truncation. It carries no browser cookies, editor credentials, git credentials, internal auth tokens, or implicit access to private services. (Full SSRF / private-network blocking is deferred — see [Deferred work](#deferred-work).)
+The `web_fetch` implementation is an anonymous public HTTP(S) fetch provider, `http`. It fetches bytes from a concrete URL, resolves and pins public destinations, applies the transport hygiene below, decodes textual content, and returns only the minimal model-useful result: final URL, status code, body, and truncation. It carries no browser cookies, editor credentials, git credentials, internal auth tokens, or implicit access to private services.
The seam request stays smaller than OpenCode's model-facing tool:
@@ -235,12 +235,14 @@ The provider owns safe resource retrieval: URL validation, HTTP transport, redir
The fetch provider's resource controls:
- Only `http:` and `https:` URLs are accepted; credentials in URLs are rejected.
+- A literal address or the complete result of one hostname lookup must contain only globally reachable unicast IPv4 or IPv6 destinations. IPv6 resolution also discovers the active DNS64 prefix and rejects NAT64 addresses that translate to non-public IPv4. Loopback, private, link-local, carrier-grade NAT, multicast, reserved, transition, translation, and private IPv4-mapped IPv6 addresses are rejected.
+- The request retains that validated address set in an Undici lookup callback instead of resolving the hostname again. The original hostname remains the HTTP Host and TLS SNI value, while DNS rebinding cannot replace the connection destination after validation.
- Maximum URL length, response byte cap, decoded body character cap, timeout, and redirect hop cap are enforced.
- Abort signals propagate through network fetches and expensive decoding.
-- Only same-origin redirects are followed automatically; a cross-origin redirect fails with `WEB_REDIRECT_BLOCKED`, requiring a fresh tool call and therefore a fresh provider/permission decision. (Claude Code's WebFetch uses this same model — it does not auto-follow a cross-host redirect; it returns the redirect target to the model for a fresh call.)
+- Only same-origin redirects are followed automatically; each followed hop performs a fresh public-address lookup and pins its own connection. A cross-origin redirect fails with `WEB_REDIRECT_BLOCKED`, requiring a fresh tool call and fresh public-address validation. (Claude Code's WebFetch uses this same model — it does not auto-follow a cross-host redirect; it returns the redirect target to the model for a fresh call.)
- Requests carry an explicit product user agent rather than silently impersonating a browser.
-SSRF / private-network protection (blocking private, loopback, link-local, multicast, and otherwise non-public destinations, with DNS-resolve-then-validate to defeat rebinding and per-hop re-validation on redirects) is **deferred** — see [Deferred work](#deferred-work). Until it lands, `web_fetch` is an SSRF primitive and must not be enabled in a deployment that can reach sensitive internal network targets.
+The provider rejects an entire DNS answer set when any address is not public instead of silently filtering the unsafe members. This fail-closed rule prevents connection-family selection or fallback from reaching an address that did not satisfy the public-network policy.
## Tool consumer behavior
@@ -252,7 +254,7 @@ Tool registration is a minimal stable sync: on plugin startup the `dsh-tool-web`
Provider availability changes affect execution results and diagnostics, not whether the model-facing schema exists. If a product wants no web tools at all, it disables `dsh-tool-web` or the individual web tool in config; if it wants web tools but the backend is misconfigured, the model sees a structured tool error at execution time.
-The prompt guidance explains the semantic split — `web_search` for discovery and current information, `web_fetch` when the model needs the content of a specific URL — and the prompt and tool result tell the model to cite relevant URLs with markdown links.
+The prompt guidance explains the semantic split — `web_search` for discovery and current information, `web_fetch` when the model needs the content of a specific URL — and the prompt and tool result tell the model to cite relevant URLs with markdown links. Every successful result labels provider-controlled text as external untrusted data. Fetch conversion removes active and hidden HTML content; unsafe conversion returns a fixed omission marker rather than raw HTML.
The model-facing output is text-first because tool results are `ContentBlock[]`, but the seam outcome stays structured so UI presentation and future adapters do not have to scrape rendered text.
@@ -308,6 +310,18 @@ Rejected for the first version. Those providers often return extracted or summar
Rejected for the seam. `prompt` turns fetch into LLM summarization and couples public-web retrieval to a model provider. The harness seam should fetch and decode deterministically; `dsh-tool-web` can later offer summaries as a presentation mode without making `ctx.web` depend on `ctx.llm`.
+### Validate DNS and then call an ordinary fetch
+
+Rejected because an ordinary fetch resolves the hostname again when it opens the connection. An attacker can return a public address during validation and a private address during the second lookup. Passing the validated answer set through the connection's lookup callback closes that rebinding interval while preserving hostname-based HTTP and TLS behavior.
+
+### Block private-looking hostname strings without pinning resolved addresses
+
+Rejected because hostname syntax does not establish the connection destination: an arbitrary public-looking name can resolve to loopback, a private range, or a cloud metadata address. Address classification belongs after resolution, and every address available to connection fallback must pass it.
+
+### Require per-call approval before public fetches
+
+Rejected for the shipped presets. Public-address validation blocks SSRF destinations, while per-call confirmation would interrupt ordinary browsing without controlling public data egress reliably: a model can reach the same public network through mounted shell tools. Deployments that require a dedicated confirmation step can add a `tools/pre-execute` policy or disable `web_fetch`.
+
## Consequences
**The search schema is deliberately thin.** Exa and Perplexity both expose useful provider-specific controls; a control is added only once it can be defined provider-neutrally and enforced honestly by both tool registration and provider execution.
@@ -318,19 +332,16 @@ Rejected for the seam. `prompt` turns fetch into LLM summarization and couples p
**Provider state can change after startup.** A tool can be visible in the request assembled at step start and lose its provider before execution. The execution path resolves again and fails with a structured error.
-**Fetch is a network boundary, not just a read-only tool.** `web_fetch` can reach sensitive network targets or exfiltrate data through URLs. Only the basic transport hygiene ships (http/https-only, credential rejection, byte/time caps, cross-origin redirect blocking); SSRF / private-network blocking is deferred (see [Deferred work](#deferred-work)), so until it lands `web_fetch` must not be enabled where it can reach internal targets.
+**Fetch is a network boundary, not just a read-only tool.** Public-address validation and connection pinning prevent `web_fetch` from reaching non-public destinations, but a model can still disclose data through a public URL and fetched text remains untrusted model input. The shipped `cordis`, `code`, and `standard` presets expose `web_fetch` in every sandbox and approval mode without per-call confirmation.
**Large web content can damage context quality.** Providers enforce byte/character caps and report `truncated`; `tool-web` formats bounded model output with clear continuation or follow-up guidance.
## Deferred work
-- SSRF / private-network protection for `web_fetch`: block private, loopback, link-local, multicast, and otherwise non-public destinations so `web_fetch` is not an SSRF primitive. Doing it correctly is more than a URL-string check — it needs DNS-resolve-then-connect-to-the-validated-IP (to defeat DNS rebinding / TOCTOU), per-hop re-validation across redirects, and IPv6 edge handling (private ranges, IPv4-mapped addresses). Neither reference implementation surveyed does IP-level blocking (OpenCode does a prefix check then fetches; Claude Code relies on a centralized hostname blocklist plus a "private URLs will fail" prompt), so there is no implementation to copy and this is the harness's only SSRF defense — it warrants its own focused design/spike. Until it lands, `web_fetch` must only be enabled in deployments that cannot reach sensitive internal targets.
- A `pdf` `WebFetchBody` kind: the `http` provider decodes text-extractable PDFs (best-effort, capped, `truncated`) into a `{ kind: 'pdf'; content; pageCount? }` arm, and `tool-web` renders it. This is fetch, not `web_extract` — PDF retrieval is a concrete HTTP 200 plus deterministic local decoding, not provider-side extraction of a non-HTTP resource. Adding it is a coordinated change across `dsh-web` (declare the arm), the provider (decode + narrow "binary rejection" to "reject binary except text-extractable PDF"; scanned/image PDFs needing OCR stay out of scope), and `tool-web` (render). The closed `WebFetchBody` union makes the consumer side fail to compile until the new arm is handled.
- Provider-backed extraction as a separate `web_extract` capability, rather than widening `web_fetch` silently.
-- Permission policy integration: the permission system now exists ([sandbox and approval](../feature/2026-07-06-sandbox.md), [web permission presets](../feature/2026-07-23-web-permission-and-approval.md)) but bundles only sandbox mode and approval policy; web permission policy remains unintegrated.
- Provider-neutral search controls beyond `query` and `maxResults`, once Exa and Perplexity can both honor them honestly.
## Open questions
- Should product app packages probe web configuration at startup (treating `WEB_PROVIDER_CONFIGURED_MISSING`, `WEB_PROVIDER_CONFIGURED_UNAVAILABLE`, and `WEB_PROVIDER_AMBIGUOUS` as fatal when web is explicitly configured), or leave misconfiguration to surface at the first execution?
-- Where should permission policy for public web access live in the shipped permission system ([sandbox and approval](../feature/2026-07-06-sandbox.md), [web permission presets](../feature/2026-07-23-web-permission-and-approval.md)): a dedicated web permission plugin on `tools/execute`, provider config, or both?
diff --git a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md
index d6051eec49..4921c4a464 100644
--- a/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-24-web-capability-seam.zh.md
@@ -16,7 +16,7 @@ harness 需要面向模型的 web 工具,但不能将模型约定绑定到某
## 决策
-Web 访问是一个一等能力 seam,遵循[能力 seam Agent Note](2026-06-13-capability-seams.md):
+Web 访问是一个一等能力 seam,遵循[能力 seam Agent Note](2026-06-13-capability-seams.zh.md):
1. `@deepseek-ai/dsh-web`(`packages/web/web`)拥有 `ctx.web`、提供方注册、提供方选择、共享的请求/结果词汇,以及 web 特有的错误。
2. 提供方包实现具体后端并向 `ctx.web` 注册能力,例如 `@deepseek-ai/dsh-web-search-exa`、`@deepseek-ai/dsh-web-search-perplexity`、`@deepseek-ai/dsh-web-search-deepseek` 和 `@deepseek-ai/dsh-web-fetch-http`。
@@ -199,7 +199,7 @@ Exa 搜索将提供方扁平 `results[]` 的每一项映射为 `WebSearchSource`
## Fetch 请求与结果 schema
-`web_fetch` 的实现是一个匿名公开 HTTP(S) fetch 提供方 `http`。它从具体 URL 获取字节,应用下述基本传输卫生措施(仅 http/https、拒绝 URL 中的凭证、字节/时间上限、跨源重定向阻断),解码文本内容,并仅返回最小的模型可用结果:最终 URL、状态码、正文和截断标志。它不携带浏览器 cookie、编辑器凭证、git 凭证、内部认证令牌,也不隐式访问私有服务。(完整的 SSRF/私有网络阻断推迟——见[推迟工作](#deferred-work)。)
+`web_fetch` 的实现是一个匿名公开 HTTP(S) fetch 提供方 `http`。它从具体 URL 获取字节,解析并固定公开目的地址,应用下述传输卫生措施,解码文本内容,并仅返回最小的模型可用结果:最终 URL、状态码、正文和截断标志。它不携带浏览器 cookie、编辑器凭证、git 凭证、内部认证令牌,也不隐式访问私有服务。
seam 请求比 OpenCode 的面向模型工具更小:
@@ -235,12 +235,14 @@ export type WebFetchBody =
fetch 提供方的资源控制:
- 仅接受 `http:` 和 `https:` URL;拒绝 URL 中的凭证。
+- 字面 IP 地址或 hostname 一次解析得到的完整结果只能包含全球可达的单播 IPv4 或 IPv6 目的地址。IPv6 解析还会发现当前 DNS64 前缀,并拒绝转换到非公开 IPv4 的 NAT64 地址。loopback、私有、link-local、运营商级 NAT、多播、保留、过渡、转换和映射到私有 IPv4 的 IPv6 地址都会被拒绝。
+- 请求通过 Undici lookup 回调保留这一组已验证地址,不会再次解析 hostname。原 hostname 仍作为 HTTP Host 与 TLS SNI 值,而 DNS rebinding 无法在验证后替换连接目的地址。
- 强制执行最大 URL 长度、响应字节上限、解码正文字符上限、超时和重定向跳数上限。
- Abort 信号传播到网络获取和高开销解码。
-- 仅自动跟随同源重定向;跨源重定向以 `WEB_REDIRECT_BLOCKED` 失败,要求一次新的工具调用,从而触发新的提供方/权限决策。(Claude Code 的 WebFetch 使用同样的模型——它不自动跟随跨主机重定向,而是将重定向目标返回给模型以发起新调用。)
+- 仅自动跟随同源重定向;每个跟随的跳转都会重新解析公开地址,并把自己的连接固定到解析结果。跨源重定向以 `WEB_REDIRECT_BLOCKED` 失败,要求一次新的工具调用和新的公开地址校验。(Claude Code 的 WebFetch 使用同样的模型——它不自动跟随跨主机重定向,而是将重定向目标返回给模型以发起新调用。)
- 请求携带显式的产品 User-Agent,而非静默伪装浏览器。
-SSRF/私有网络防护(阻断私有、回环、链路本地、多播及其他非公开目的地,通过先 DNS 解析再验证 IP 来防御 rebinding,并在重定向的每一跳重新验证)**推迟**——见[推迟工作](#deferred-work)。在其落地之前,`web_fetch` 是一个 SSRF 原语,不得在能触达敏感内部网络目标的部署中启用。
+只要 DNS 完整解析结果中存在任一非公开地址,提供方就会拒绝整个结果,而不是静默过滤不安全成员。该 fail-closed 规则可防止连接的地址族选择或回退触及未满足公开网络策略的地址。
## 工具消费方行为
@@ -252,7 +254,7 @@ SSRF/私有网络防护(阻断私有、回环、链路本地、多播及其他
提供方可用性变化影响执行结果和诊断信息,而非面向模型的 schema 是否存在。如果产品完全不需要 web 工具,在配置中禁用 `dsh-tool-web` 或单个 web 工具即可;如果需要 web 工具但后端配置有误,模型在执行时看到结构化的工具错误。
-提示词引导解释了语义分工——`web_search` 用于发现和获取当前信息,`web_fetch` 用于模型需要特定 URL 内容的场景——提示词和工具结果告诉模型用 Markdown 链接引用相关 URL。
+提示词引导解释了语义分工——`web_search` 用于发现和获取当前信息,`web_fetch` 用于模型需要特定 URL 内容的场景——提示词和工具结果告诉模型用 Markdown 链接引用相关 URL。每个成功结果都会把提供方控制的文本标记为外部不可信数据。抓取转换会移除主动内容与隐藏 HTML 内容;无法安全转换时返回固定省略标记,而非原始 HTML。
面向模型的输出以文本为先,因为工具结果是 `ContentBlock[]`,但 seam 的产出保持结构化,以便 UI 展示和未来的适配器无需解析渲染后的文本。
@@ -280,7 +282,7 @@ SSRF/私有网络防护(阻断私有、回环、链路本地、多播及其他
## 测试
-每一层在自己的边界处固定:`dsh-web` 中的注册/选择/截断/abort 约定与 `WebError` 码;每个提供方基于录制的 fixture(测试前置数据)的请求/响应映射(Perplexity fixture 包含纯 URL 引用,以保持可选 source 字段的诚实性),加上每个真实提供方的自跳过带密钥冒烟测试;`web-fetch-http` 中的真实本地 HTTP 行为;`dsh-tool-web` 中通过真实工具注册表的启用驱动注册、结构化执行错误和结果格式化。一个真实 Loader 冒烟测试守护两种导出形状([事故复盘(postmortem) 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.md)):`dsh-web` 是默认导出的服务,而提供方和 `tool-web` 是命名空间插件,误加 `export default` 会丢失 `inject`。
+每一层在自己的边界处固定:`dsh-web` 中的注册/选择/截断/abort 约定与 `WebError` 码;每个提供方基于录制的 fixture(测试前置数据)的请求/响应映射(Perplexity fixture 包含纯 URL 引用,以保持可选 source 字段的诚实性),加上每个真实提供方的自跳过带密钥冒烟测试;`web-fetch-http` 中的真实本地 HTTP 行为;`dsh-tool-web` 中通过真实工具注册表的启用驱动注册、结构化执行错误和结果格式化。一个真实 Loader 冒烟测试守护两种导出形状([事故复盘(postmortem) 0001](../../../../docs/postmortem/0001-acp-default-export-drops-inject.zh.md)):`dsh-web` 是默认导出的服务,而提供方和 `tool-web` 是命名空间插件,误加 `export default` 会丢失 `inject`。
## 曾考虑的替代方案
@@ -308,6 +310,18 @@ SSRF/私有网络防护(阻断私有、回环、链路本地、多播及其他
在 seam 层面否决。`prompt` 将 fetch 变成 LLM 摘要,并将公开 web 获取耦合到模型提供方。harness seam 应当确定性地获取和解码;`dsh-tool-web` 日后可以将摘要作为展示模式提供,而无需让 `ctx.web` 依赖 `ctx.llm`。
+### 验证 DNS 后调用普通 fetch
+
+否决,因为普通 fetch 在打开连接时会再次解析 hostname。攻击者可以在验证时返回公开地址,在第二次解析时返回私有地址。把已验证解析结果通过连接的 lookup 回调传入,可以在保留基于 hostname 的 HTTP 与 TLS 行为的同时关闭这一 rebinding 时间窗口。
+
+### 只阻断看起来像私网的 hostname 字符串,不固定解析地址
+
+否决,因为 hostname 语法无法确定连接目的地址:任意看似公开的名称都可能解析到 loopback、私有网段或云 metadata 地址。地址分类必须在解析后执行,连接回退可使用的每个地址都必须通过校验。
+
+### 在公开抓取前要求逐次审批
+
+已交付的 preset 不采用这一方案。公开地址校验会阻断 SSRF 目的地址,而逐次确认会打断普通浏览,却不能可靠控制公开数据出站:模型可以通过已挂载的 shell 工具访问同一公开网络。要求专门确认步骤的部署可以添加 `tools/pre-execute` 策略或禁用 `web_fetch`。
+
## 后果
**搜索 schema 刻意精简。** Exa 和 Perplexity 都暴露了有用的提供方特有控制;只有当某个控制能以提供方无关的方式定义、且工具注册和提供方执行都能诚实遵守时,才会添加。
@@ -318,7 +332,7 @@ SSRF/私有网络防护(阻断私有、回环、链路本地、多播及其他
**提供方状态可能在启动后变化。** 一个工具可能在步骤开始时组装的请求中可见,但在执行前失去其提供方。执行路径重新解析并以结构化错误失败。
-**Fetch 是网络边界,不仅仅是只读工具。** `web_fetch` 能触达敏感网络目标或通过 URL 外泄数据。仅交付基本传输卫生措施(仅 http/https、拒绝凭证、字节/时间上限、跨源重定向阻断);SSRF/私有网络阻断推迟(见[推迟工作](#deferred-work)),因此在其落地之前,`web_fetch` 不得在能触达内部目标的环境中启用。
+**Fetch 是网络边界,不仅仅是只读工具。** 公开地址校验与连接固定可防止 `web_fetch` 触达非公开目的地址,但模型仍可通过公开 URL 泄露数据,抓取文本也仍是不受信任的模型输入。已交付的 `cordis`、`code` 与 `standard` preset 会在所有 sandbox 和审批模式下暴露 `web_fetch`,无需逐次确认。
**大量 web 内容可能损害上下文质量。** 提供方强制执行字节/字符上限并报告 `truncated`;`tool-web` 格式化有界的模型输出,附带清晰的继续或后续引导。
@@ -326,13 +340,10 @@ SSRF/私有网络防护(阻断私有、回环、链路本地、多播及其他
## 推迟工作
-- `web_fetch` 的 SSRF/私有网络防护:阻断私有、回环、链路本地、多播及其他非公开目的地,使 `web_fetch` 不再是 SSRF 原语。正确实现不仅仅是 URL 字符串检查——需要先 DNS 解析再连接到已验证的 IP(防御 DNS rebinding/TOCTOU)、跨重定向的每跳重新验证,以及 IPv6 边缘处理(私有范围、IPv4 映射地址)。所调研的参考实现均未做 IP 级阻断(OpenCode 做前缀检查后直接 fetch;Claude Code 依赖集中式主机名黑名单加「私有 URL 会失败」的提示词),因此没有可复制的实现,且这是 harness 唯一的 SSRF 防线——值得一次专门的设计/spike。在其落地之前,`web_fetch` 只能在无法触达敏感内部目标的部署中启用。
- `pdf` `WebFetchBody` 类别:`http` 提供方将可文本提取的 PDF 解码(尽力而为、有上限、`truncated`)为 `{ kind: 'pdf'; content; pageCount? }` 分支,`tool-web` 渲染它。这是 fetch 而非 `web_extract`——PDF 获取是具体的 HTTP 200 加确定性的本地解码,不是提供方侧对非 HTTP 资源的提取。添加它是跨 `dsh-web`(声明分支)、提供方(解码 + 将「二进制拒绝」收窄为「拒绝二进制,但可文本提取的 PDF 除外」;需要 OCR 的扫描/图片 PDF 不在范围内)和 `tool-web`(渲染)的协调变更。封闭的 `WebFetchBody` 联合类型使消费方在新分支被处理之前编译失败。
- 提供方支撑的提取作为独立的 `web_extract` 能力,而非静默扩展 `web_fetch`。
-- 权限策略集成:权限系统现已存在([沙箱与审批](../feature/2026-07-06-sandbox.md)、[web 权限预设](../feature/2026-07-23-web-permission-and-approval.md)),但只捆绑了沙箱模式与审批策略;web 权限策略仍未集成。
- `query` 和 `maxResults` 之外的提供方无关搜索控制,待 Exa 和 Perplexity 都能诚实遵守时再添加。
## 开放问题
- 产品应用包是否应在启动时探测 web 配置(当 web 被显式配置时将 `WEB_PROVIDER_CONFIGURED_MISSING`、`WEB_PROVIDER_CONFIGURED_UNAVAILABLE` 和 `WEB_PROVIDER_AMBIGUOUS` 视为致命错误),还是将配置错误留到首次执行时浮出?
-- 在已交付的权限系统([沙箱与审批](../feature/2026-07-06-sandbox.md)、[web 权限预设](../feature/2026-07-23-web-permission-and-approval.md))中,公开 web 访问的权限策略应放在哪里:`tools/execute` 上的专用 web 权限插件、提供方配置,还是两者兼有?
diff --git a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml
index c49cd144b9..421739cb57 100644
--- a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md
2026-06-26-file-context-as-event-gate.md: a8316741c3ce8548db5b5def431425589994995c
-2026-06-26-file-context-as-event-gate.zh.md: 78b1b759edc0340fd7be103fc9bfec0b125e0800
+2026-06-26-file-context-as-event-gate.zh.md: 618985f33073cf9fd69cf2c7fda7112d9752468f
diff --git a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md
index 78b1b759ed..618985f330 100644
--- a/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.zh.md
@@ -6,7 +6,7 @@ Status: implemented
## 问题
-[拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) 在面向模型的工具与 `ctx.fs` 提供方之间放置了 `ctx.fileContext`:`dsh-tool-fs` 注入 `fileContext`,并将每次 `read`/`write`/`edit` 路由到它的方法。这使得 `fileContext` **位于关键路径上且不可省略**。工具不经过它就无法访问 `ctx.fs`,策略层掌控着 fs I/O 和读取窗口,而一个不需要观测状态策略的部署也无法简单地移除该包——`dsh-tool-fs` 会因无法解析 `ctx.fileContext` 而失败。
+[拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.zh.md) 在面向模型的工具与 `ctx.fs` 提供方之间放置了 `ctx.fileContext`:`dsh-tool-fs` 注入 `fileContext`,并将每次 `read`/`write`/`edit` 路由到它的方法。这使得 `fileContext` **位于关键路径上且不可省略**。工具不经过它就无法访问 `ctx.fs`,策略层掌控着 fs I/O 和读取窗口,而一个不需要观测状态策略的部署也无法简单地移除该包——`dsh-tool-fs` 会因无法解析 `ctx.fileContext` 而失败。
这把三件本应可分离的事情耦合在了一起:
@@ -33,7 +33,7 @@ provider dsh-fs-local local implementation of ctx.fs
该模型是叠加式的:裸 `ctx.fs` 执行原子化、无约束的文本 I/O,而 `dsh-fs-observation-policy` 叠加观测状态、先读后编辑和版本守卫。因此移除策略层后工具仍可用,只是不受约束。正式发布的 agent(智能体)配置会加载策略;裸模式的存在是为了让策略在服务边界保持可选,而非作为正常部署姿态。
-[文件系统缺失观测后续决策](../bug-fix/2026-08-09-filesystem-absence-observation.md)把记录载荷从仅表示成功的版本细化为显式的存在/缺失状态,并要求带防护的创建以不替换方式发布。事件门控归属与无 I/O 策略边界保持不变。
+[文件系统缺失观测后续决策](../bug-fix/2026-08-09-filesystem-absence-observation.zh.md)把记录载荷从仅表示成功的版本细化为显式的存在/缺失状态,并要求带防护的创建以不替换方式发布。事件门控归属与无 I/O 策略边界保持不变。
`dsh-tool-fs` 不再注入 `fileContext`。它注入 `fs` 和 `tools`/`systemPrompt`。
@@ -152,7 +152,7 @@ interface Events {
## 取代关系
-本 Agent Note 修正——而非推翻——[拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md)。四层拆分、提供方约定和新鲜度*策略*均保留。变更的是**工具与策略层之间的耦合方式**:强制性方法服务变为插件拥有的事件门控,fs I/O + 读取窗口从 `fileContext` 上移至 `dsh-tool-fs`。拆分文件系统 seam Agent Note 中关于 `dsh-tool-fs` 注入 `fileContext` 以及 `fileContext` 拥有 `read`/`write`/`edit` 的描述已在同一变更中更新。
+本 Agent Note 修正——而非推翻——[拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.zh.md)。四层拆分、提供方约定和新鲜度*策略*均保留。变更的是**工具与策略层之间的耦合方式**:强制性方法服务变为插件拥有的事件门控,fs I/O + 读取窗口从 `fileContext` 上移至 `dsh-tool-fs`。拆分文件系统 seam Agent Note 中关于 `dsh-tool-fs` 注入 `fileContext` 以及 `fileContext` 拥有 `read`/`write`/`edit` 的描述已在同一变更中更新。
## 验证
@@ -160,7 +160,7 @@ interface Events {
## 曾考虑的替代方案
-- **保留 `ctx.fileContext` 作为关键路径上的方法服务**——[拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.md) 最初落地的形态;否决,因为工具无法在没有策略层的情况下运行,使策略对基本操作是承重性的,而非可选的收紧。
+- **保留 `ctx.fileContext` 作为关键路径上的方法服务**——[拆分文件系统 seam Agent Note](../simplification/2026-06-26-fsspec-style-fs-seam.zh.md) 最初落地的形态;否决,因为工具无法在没有策略层的情况下运行,使策略对基本操作是承重性的,而非可选的收紧。
- **策略侧版本检查**(`dsh-fs-observation-policy` 在其 waterfall 处理器中 stat 并比较版本)——否决,因为该检查与工具实际写入之间存在 TOCTOU 间隙;提供方的 mutation 临界区是唯一无竞态的位置,因此策略只选择 CAS 基准并对先前观测进行门控。
- **每工具 `/read`/`/write`/`/edit` 子路径插件**——实现时放弃:没有消费方需要单工具部署,且子路径发布迫使引入兄弟工具包都不需要的定制 `tsdown`/`tsconfig`/`files`/workspace-constraint 处理;每工具的注册辅助函数仍作为根插件组合的内部模块保留。
diff --git a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-api.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-api.i18n.yaml
index 7a5d35f882..04eec8e0e1 100644
--- a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-api.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-api.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-api.md
2026-06-30-bash-stdin-env-trusted-plugin-api.md: 41be63fff598587ee9b873cf7edf51da788bc02a
-2026-06-30-bash-stdin-env-trusted-plugin-api.zh.md: 4f0338cbb6a265ff629a81e9c9a12c4456941ba0
+2026-06-30-bash-stdin-env-trusted-plugin-api.zh.md: 60721539d9d37857e145e289bb262482588139bf
diff --git a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-api.zh.md b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-api.zh.md
index 4f0338cbb6..60721539d9 100644
--- a/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-api.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-api.zh.md
@@ -8,7 +8,7 @@ Status: implemented
钩子子系统以 Claude Code 和 Codex 的方式运行外部钩子命令:钩子是一条 shell 命令,通过 **stdin 上的 JSON** 接收事件载荷,并从若干**环境变量**(`CLAUDE_PROJECT_DIR`、`CLAUDE_PLUGIN_ROOT`、`PLUGIN_ROOT`……)读取上下文。harness 已经在 `ctx.shell` 能力 seam 后面有一个完善的命令执行器([dsh-shell](../../../../packages/shell/shell) → [dsh-bash-local](../../../../packages/shell/bash-local)),具备进程组终止、输出截断/spill 处理和凭证擦除功能。复用它来执行钩子意味着钩子桥接层无需重新实现子进程底层机制——但该 seam 此前无法写入 stdin 或设置额外 env。本次变更添加这两个输入。
-`stdin` 和 `env` 不构成新的模型能力,因为普通 shell 语法已经能提供两者。环境凭证由 `dsh-bash-local` 的子环境擦除机制保护,而非靠隐藏这些 Service Definition 字段;模型工具参数是静态 JSON,不会展开 shell 变量。因此这些字段服务于受信的进程内调用方(如钩子桥接层),它们需要传递结构化输入和 `CLAUDE_*` 变量,而不必将其嵌入模型可见的 shell 文本。环境变量规则见 [defensive-patterns.md](../../../../docs/defensive-patterns.md)。
+`stdin` 和 `env` 不构成新的模型能力,因为普通 shell 语法已经能提供两者。环境凭证由 `dsh-bash-local` 的子环境擦除机制保护,而非靠隐藏这些 Service Definition 字段;模型工具参数是静态 JSON,不会展开 shell 变量。因此这些字段服务于受信的进程内调用方(如钩子桥接层),它们需要传递结构化输入和 `CLAUDE_*` 变量,而不必将其嵌入模型可见的 shell 文本。环境变量规则见 [defensive-patterns.md](../../../../docs/defensive-patterns.zh.md)。
## 决策
@@ -16,7 +16,7 @@ Status: implemented
三个有意为之的选择:
-1. **模型侧工具不暴露 `stdin` 和 `env`。** Shell 语法已覆盖这些需求,重复参数只会增加接口面而不带来权限隔离。工具仅从声明的模型参数、signal 和 owner 构建请求;受信的进程内调用方可以直接设置请求字段。harness 自有变量使用[托管环境决策](../feature/2026-07-10-agent-session-identity-and-log-location.md)规定的独立 `dshEnv` 通道,因此普通 `env` 无法替换它们。
+1. **模型侧工具不暴露 `stdin` 和 `env`。** Shell 语法已覆盖这些需求,重复参数只会增加接口面而不带来权限隔离。工具仅从声明的模型参数、signal 和 owner 构建请求;受信的进程内调用方可以直接设置请求字段。harness 自有变量使用[托管环境决策](../feature/2026-07-10-agent-session-identity-and-log-location.zh.md)规定的独立 `dshEnv` 通道,因此普通 `env` 无法替换它们。
2. **`env` 在凭证擦除之后合并,因此调用方显式设置的条目即使具有凭证形态的名称也会胜出。** 后续的托管命名空间决策负责管理 `DSH_*`:这类环境条目会被移除,受信的 `dshEnv` 最后合并,因此普通 `env` 条目永远无法顶掉托管值。完整顺序为 `scrub(process.env, including DSH_*)` → `ENV_OVERRIDES` → 普通 `env` → `dshEnv`。
@@ -30,4 +30,4 @@ Status: implemented
## 后果
-钩子桥接层通过既有的 bash seam 传递 JSON 载荷和钩子特定变量,保留其进程组终止、截断和 spill 行为。面向模型的行为不变,bash 工具仍是模型调用请求构建的唯一所有者。相关词汇定义见 [bash 数据结构参考](../../../../docs/subsystems/shell.md)。
+钩子桥接层通过既有的 bash seam 传递 JSON 载荷和钩子特定变量,保留其进程组终止、截断和 spill 行为。面向模型的行为不变,bash 工具仍是模型调用请求构建的唯一所有者。相关词汇定义见 [bash 数据结构参考](../../../../docs/subsystems/shell.zh.md)。
diff --git a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml
index 171f33fe17..feb512101f 100644
--- a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md
2026-06-30-event-domain-semantics.md: 70da718b5471ce309a090c8aade3e7290cc949dc
-2026-06-30-event-domain-semantics.zh.md: 6795e1f6f583d6fe7d34efc5e1619da38ab1c89f
+2026-06-30-event-domain-semantics.zh.md: c3b12a167da0a41b792914d82a675a98b3a0b860
diff --git a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md
index 6795e1f6f5..c3b12a167d 100644
--- a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md
+++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md
@@ -6,7 +6,7 @@ Status: implemented
## 问题
-harness 通过 Cordis 事件分类体系扩展 agent loop(智能体循环)(见[微内核事件分类体系 Agent Note](2026-06-11-microkernel-event-taxonomy.md))。随着该分类体系的增长,三个事件域之间的界限变得模糊:
+harness 通过 Cordis 事件分类体系扩展 agent loop(智能体循环)(见[微内核事件分类体系 Agent Note](2026-06-11-microkernel-event-taxonomy.zh.md))。随着该分类体系的增长,三个事件域之间的界限变得模糊:
- `session/*` 承载持久的、事件溯源的日志(`SessionEventMap`)。
- `agent/*` 承载运行时实时信号,向插件传递 `Agent` 句柄。
@@ -26,14 +26,14 @@ harness 通过 Cordis 事件分类体系扩展 agent loop(智能体循环)
**边界规则:** 持久的、可回放的事实是 `SessionEvent`;实时拦截或瞬态/活对象信号是 `agent`/`tools` Cordis 事件。轮次或步骤边界是持久事实,因此存在于会话日志中并从 `session/event` 源读取——不会被镜像为 `agent/*` emit。
-**将规则应用于边界镜像:** 全部四个边界镜像——`agent/turn-start`、`agent/turn-end`、`agent/step-start`、`agent/step-end`——被**移除**。没有生产消费方需要在边界处获取活的 `Agent`:ACP(Agent Client Protocol)桥接将其进行中的提示词与精确对应的 `session/event` `turn/start`/`turn/end` 事件对关联,其他 transcript 消费方同样从持久流派生边界。见[移除边界镜像事件 Agent Note](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md),该决策由它负责。移除 emit 也简化了循环的 `closeStep`/`closeTurn`(各只需一次 append,无需配对 emit)。
+**将规则应用于边界镜像:** 全部四个边界镜像——`agent/turn-start`、`agent/turn-end`、`agent/step-start`、`agent/step-end`——被**移除**。没有生产消费方需要在边界处获取活的 `Agent`:ACP(Agent Client Protocol)桥接将其进行中的提示词与精确对应的 `session/event` `turn/start`/`turn/end` 事件对关联,其他 transcript 消费方同样从持久流派生边界。见[移除边界镜像事件 Agent Note](../simplification/2026-06-20-remove-agent-boundary-mirror-events.zh.md),该决策由它负责。移除 emit 也简化了循环的 `closeStep`/`closeTurn`(各只需一次 append,无需配对 emit)。
## 后果
- 循环不再 emit 任何边界镜像;`closeStep` 仅追加 `step/end`,`closeTurn` 仅追加 `turn/end`。`Session.append` 负责 post-commit observer 隔离,因此抛出异常的边界 observer 无法改变轮次结果或饿死后续消费方;事件接纳失败或内部校验失败仍会在边界进入日志之前向外抛出。
- 之前通过已移除 emit 观察边界的测试,现在观察持久的 `turn/start`/`turn/end`/`step/start`/`step/end` 会话事件——它们所锁定的行为(边界顺序、步骤计数)不变;只是读取的源移到了规范源。那些测试*抛出异常的轮次边界 emit 监听器*的用例被删除,因为该代码路径不再存在(没有 emit 可供抛出)。按照 [AGENTS.md「测试记录行为,而非黄金真相」](../../../../AGENTS.md),行为与其测试一同迁移(或一同消亡)。
- 循环仅在 `append('step/start')` 返回后才标记步骤已打开(`stepOpen = true`)。内部分发校验在日志推入之前运行,可能在不打开步骤的情况下拒绝;post-commit `session/event` observer 的失败被隔离在 `Session.append` 内部。因此该标记精确表示已提交的、欠一个后续 `step/end` 的边界。
-- 完整实现见[简化 Agent Note「停止将持久边界镜像为 agent 事件」](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md):全部四个边界镜像被移除,所有消费方从 `session/event` 读取边界。`agent/steering`(不是边界镜像)不在该 Agent Note 范围内,由其后续 Agent Note [移除 `agent/steering` 镜像 emit](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md) 单独移除——它镜像的是持久的中途 steering `user/message`。
+- 完整实现见[简化 Agent Note「停止将持久边界镜像为 agent 事件」](../simplification/2026-06-20-remove-agent-boundary-mirror-events.zh.md):全部四个边界镜像被移除,所有消费方从 `session/event` 读取边界。`agent/steering`(不是边界镜像)不在该 Agent Note 范围内,由其后续 Agent Note [移除 `agent/steering` 镜像 emit](../../archived/simplification/2026-07-04-remove-agent-steering-mirror.md) 单独移除——它镜像的是持久的中途 steering `user/message`。
- 生成的 Cordis 事件表面(`docs/subsystems/` 各页)不再列出镜像事件。
diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml
index fa8401fdc8..933b3d2826 100644
--- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.md
2026-07-02-tool-render-intent-union.md: 52626d3d9200146df95aee7836d37bbaf7e6a9ec
-2026-07-02-tool-render-intent-union.zh.md: 43fda366694aecda07b276d34c882e75d6b4aa95
+2026-07-02-tool-render-intent-union.zh.md: bc91b89c53c3c43b6c483dc0d4876a00f5a936b7
diff --git a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md
index 43fda36669..bc91b89c53 100644
--- a/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-02-tool-render-intent-union.zh.md
@@ -4,7 +4,7 @@ Status: implemented
[English](2026-07-02-tool-render-intent-union.md) | 中文
-> render-intent 联合类型对 UI 传输层仍然有效;其 ACP(Agent Client Protocol)映射已被 [ACP 作为仅面向自动化的协议](../simplification/2026-07-23-acp-automation-only-protocol.md)取代。
+> render-intent 联合类型对 UI 传输层仍然有效;其 ACP(Agent Client Protocol)映射已被 [ACP 作为仅面向自动化的协议](../simplification/2026-07-23-acp-automation-only-protocol.zh.md)取代。
## 问题
@@ -78,5 +78,5 @@ terminal 意图只用于展示。harness 仍通过自身的 bash 服务执行命
## 相关
- 取代早先被否决的折叠工具自有呈现提案(已否决——「等两个真实工具和两个真实消费方,然后做带标签 render-intent 联合类型」)中的推迟决定。该条件现已满足;本 Agent Note 即为那个联合类型。
-- 被[结果时已应用 hunk 差异](../../archived/architecture/2026-07-02-result-time-applied-hunk-diffs.md)(已归档)扩展:后者添加了一个持久化的 `meta` 通道,使 write/edit 在结果时输出 `DiffResultView`(应用后的变更:带上下文行的 contextual hunk / 每个 `replace_all` 位点一个,或创建时的整文件 diff)——值/呈现拆分与持久化的 `presentationMeta` 通道现由[规范工具输出约定](2026-07-20-canonical-tool-output-contract.md)拥有。
+- 被[结果时已应用 hunk 差异](../../archived/architecture/2026-07-02-result-time-applied-hunk-diffs.md)(已归档)扩展:后者添加了一个持久化的 `meta` 通道,使 write/edit 在结果时输出 `DiffResultView`(应用后的变更:带上下文行的 contextual hunk / 每个 `replace_all` 位点一个,或创建时的整文件 diff)——值/呈现拆分与持久化的 `presentationMeta` 通道现由[规范工具输出约定](2026-07-20-canonical-tool-output-contract.zh.md)拥有。
- 将 `ToolTerminal` 折入当前 UI 传输层使用的带标签 `terminal` 视图。
diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml
index 800449486f..fcdffd69cd 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.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/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
-2026-07-05-prompt-variables-and-tool-guidance-ownership.md: 9a53619d9510e3f4fa561f8420b2da3bedbbf4bb
-2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md: 6174f277f0a4e8c46ff8d732411f28b4ea97728c
+2026-07-05-prompt-variables-and-tool-guidance-ownership.md: 361184fa7dbdaccd49ac19235c016daf5eb5ca53
+2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md: 6b462572883fb69ca64f2babf28974ae59e7bd74
diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
index 9a53619d95..361184fa7d 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
+++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md
@@ -32,7 +32,7 @@ Plugins register `{{name}}` values through `ctx.systemPrompt.variable(name, prov
### Persona as the order-0 section
-`dsh-system-prompt` owns `harness:identity` at order `-100` and the configured `deployment:persona` at order 0, so both survive a replacement loop. Prompt rendering has one path, `renderPrompt(assembly)`, and the routed request header therefore records the exact prompt later replayed by `ctx.tokenMeter` for compaction pressure. An agent-scoped `deployment:persona` shadows the global default and lets subagent providers install a persona before publication. The conventional order bands are identity `-100`, persona `0`, and tool guidance `100–199`.
+`dsh-system-prompt` owns `harness:identity` at first-party order `-1000` and the configured `deployment:persona` at order 0, so both survive a replacement loop. Prompt rendering has one path, `renderPrompt(assembly)`, and the routed request header therefore records the exact prompt later replayed by `ctx.tokenMeter` for compaction pressure. An agent-scoped `deployment:persona` shadows the global default and lets subagent providers install a persona before publication. The [first-party order allocation](2026-08-25-sparse-first-party-prompt-section-orders.md) owns the sparse named placements for identity, policy, tool guidance, generated protocol, and final-output obligations.
### Tool guidance ownership
diff --git a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md
index 6174f277f0..6b46257288 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md
@@ -32,7 +32,7 @@ Status: implemented
### Persona 作为 order-0 section
-`dsh-system-prompt` 拥有 order 为 `-100` 的 `harness:identity` 和 order 为 0 的配置 `deployment:persona`,因此两者在循环被替换时仍然存活。提示词渲染只有一条路径 `renderPrompt(assembly)`,已路由请求 header 因此会记录准确的提示词,稍后由 `ctx.tokenMeter` 为压缩(compaction)压力回放。agent 作用域的 `deployment:persona` 遮蔽全局默认值,允许 subagent 提供方在发布前安装 persona。约定的 order 区间为:identity `-100`、persona `0`、工具指导 `100–199`。
+`dsh-system-prompt` 拥有 first-party order 为 `-1000` 的 `harness:identity` 和 order 为 0 的配置 `deployment:persona`,因此两者在循环被替换时仍然存活。提示词渲染只有一条路径 `renderPrompt(assembly)`,已路由请求 header 因此会记录准确的提示词,稍后由 `ctx.tokenMeter` 为压缩(compaction)压力回放。agent 作用域的 `deployment:persona` 遮蔽全局默认值,允许 subagent 提供方在发布前安装 persona。[first-party 顺序分配](2026-08-25-sparse-first-party-prompt-section-orders.zh.md)规定身份、策略、工具指导、生成协议和最终输出义务的稀疏具名位置。
### 工具指导归属
@@ -40,7 +40,7 @@ Status: implemented
### Subagent 对话历史描述符
-`SubagentProvider.inheritsParentContext` 描述的是对话历史初始化,而非作用域、服务、工具或权限。spawn 和 ACP 将其设为 `false`;fork 设为 `true`。`dsh-tool-subagent` 根据该标志派生工具描述和提示词参数描述,包括 fork 继承已完成轮次但不继承进行中轮次这一点。提供方生命周期事件使该措辞与响应式提供方注册保持同步;其设计动机见[提供方生命周期事件 Agent Note](2026-07-05-subagent-provider-lifecycle-events.md)。
+`SubagentProvider.inheritsParentContext` 描述的是对话历史初始化,而非作用域、服务、工具或权限。spawn 和 ACP 将其设为 `false`;fork 设为 `true`。`dsh-tool-subagent` 根据该标志派生工具描述和提示词参数描述,包括 fork 继承已完成轮次但不继承进行中轮次这一点。提供方生命周期事件使该措辞与响应式提供方注册保持同步;其设计动机见[提供方生命周期事件 Agent Note](2026-07-05-subagent-provider-lifecycle-events.zh.md)。
## 曾考虑的替代方案
@@ -49,7 +49,7 @@ Status: implemented
- **在每个 persona 中手写模型名称**:与上方一行的 `model:` 键重复,配置修改后静默失实;正是本决策要治愈的病症。
- **宽松插值(未知引用保留原样或替换为空)**:一个拼写错误 `{{modle}}`(或一个空洞)会被发送给模型,直到 transcript(文本记录)审查时才会被发现。
- **在配置中为每个 subagent 实例编写措辞**:面向模型的行文回到每个部署 × 实例中,重蹈在 leaf YAML 中手写指导的漂移。**根据提供方名称选择措辞**:`providerName` 本身是配置,重命名提供方后会静默获得错误的措辞。
-- **在 `apply` 时解析提供方(加载顺序要求)**与**仅用 section 承载 subagent 措辞(在 assemble 时惰性解析)**:提供方生命周期事件的替代方案;两者均在[提供方生命周期事件 Agent Note](2026-07-05-subagent-provider-lifecycle-events.md)中被否决。
+- **在 `apply` 时解析提供方(加载顺序要求)**与**仅用 section 承载 subagent 措辞(在 assemble 时惰性解析)**:提供方生命周期事件的替代方案;两者均在[提供方生命周期事件 Agent Note](2026-07-05-subagent-provider-lifecycle-events.zh.md)中被否决。
## 不在范围内
diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml
index b2478911dc..a9d00bc3b9 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.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/implemented/architecture/2026-07-05-reconstructable-requests.md
-2026-07-05-reconstructable-requests.md: 63146fa2d392a45543daa32ce2b00158782fddb2
-2026-07-05-reconstructable-requests.zh.md: 94c1d323be0107eb8b6072a05d1e8832ebd1fffc
+2026-07-05-reconstructable-requests.md: 3786de02d06c0b6c094297ae89ac3f84053e408d
+2026-07-05-reconstructable-requests.zh.md: 851045aca7dababd0da859f3b04b721c65382fc3
diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md
index 63146fa2d3..3786de02d0 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md
+++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.md
@@ -22,9 +22,9 @@ Prefix-cache stability is corollary #1, not the headline: an append-only log pro
**Messages.** `Session.deriveMessages()` is cached: each surface entry is projected exactly once, when first seen, through the public per-event function `deriveEventMessage(event)`; a surface rewrite (a compaction `replace` — `SurfaceManager.replaceGeneration`) rebuilds. Callers get a fresh array per call over shared, deep-frozen messages: mutating logged history through a projection is unrepresentable (it throws), replacing the old clone-per-call isolation. External reconstructors fold the same public function over a log prefix, so no two paths can disagree.
-`EpochHeader` records the request's non-history state: call config, rendered system prompt, and tool schemas, with empty values canonicalized to absence. `request/header` always writes a full snapshot: the first loop instance uses reason `initial`, later instances use `resume`, and an in-instance change uses `change`. `foldRequestHeader` selects the latest snapshot. Legacy `request/header-delta` events and the removed `fallback` reason are rejected when appended or loaded.
+`EpochHeader` records the request's non-history state: call config, rendered system prompt, and tool schemas, with empty values canonicalized to absence. Adapter-supplied effort and token defaults retain their `adapterDefaults` provenance; a Web model selection restored from the log omits an adapter-owned effort so the next resolution cannot reclassify the same effective config as an explicit selection and a false change. `request/header` always writes a full snapshot: the first loop instance uses reason `initial`, later instances use `resume`, an in-instance change uses `change`, and an unchanged envelope beginning an explicitly declared message series or following a surface replacement uses `series`. A `change` snapshot carries `startsSeries: true` when the changed request also starts a series, preserving the two independent facts without a duplicate header. Ordinary append-only later Turns, further same-series Steps, and retries inherit the latest snapshot. `foldRequestHeader` selects the latest snapshot. Legacy `request/header-delta` events and the removed `fallback` reason are rejected when appended or loaded.
-Each proposed step first claims its inbox batch and runs `agent/pre-step`. Rejection opens no step; enter opens `step/start` and records the final message batch as `user/message` events. The step then assembles the system prompt and tools, while `agent/request` may replace only the frozen call-config seed. The loop records the owed full header snapshot, builds `GenerateOptions` from derived messages and that header, and deep-freezes it while leaving `AbortSignal` live. The first call config starts from explicit `AgentOptions`, preserving fork overrides and resume reconfiguration; later calls start from the folded header.
+Each proposed step first claims its inbox batch and runs `agent/pre-step`. Rejection opens no step; enter opens `step/start`, records the final message batch as `user/message` events, and may use `startsRequestSeries: true` to declare a distinct series. The step then assembles the system prompt and tools, while `agent/request` may replace only the frozen call-config seed. The loop records the owed initial, resume, change, or series full snapshot, builds `GenerateOptions` from derived messages and that header, and deep-freezes it while leaving `AbortSignal` live. The first call config starts from explicit `AgentOptions`, preserving fork overrides and resume reconfiguration; later calls start from the folded header.
**The open step is the reconstruction boundary.** Its entered `user/message` batch and any newly written `request/header` precede request dispatch. Injection after the atomic claim joins a later request, while a listener that must affect this request returns messages through `agent/pre-step`. Header reconstruction selects the step's `request/header`, or carries the prior snapshot when no new header is written.
@@ -42,6 +42,7 @@ Like MiniCode, the conversation advances append-only and resets only when model-
- **Detect-and-report** (compare consecutive requests, warn on divergence): catches violations after the fact; a violating request is still constructible and ships. Rejected for interface-level unrepresentability.
- **Event-driven assembly** (re-render only on change signals): a missed-signal bug class — a tool registered mid-session emits `tools/change`, not `system-prompt/change`, and a third-party provider may emit nothing. Per-step render + value compare is robust with zero signal discipline.
- **A custom header-delta codec** (system line edits, name-keyed tool edits, whole config/prefix replacements): reduced repeated bytes but duplicated the representation and its diff/apply/fallback machinery. Full snapshots retain one replay representation.
+- **A lightweight series marker referencing the previous header**: reduced repeated prompt and tool bytes, but a window beginning at that marker could not render or reconstruct the request without fetching its predecessor. A self-contained full snapshot preserves one representation for persistence, partial history, and snapshot pinning.
- **Narrative changed-field lists on header snapshots**: derivable by comparing consecutive snapshots. The `reason` remains because an instance boundary is not derivable from the snapshot values.
## Consequences
@@ -51,5 +52,6 @@ Like MiniCode, the conversation advances append-only and resets only when model-
- What still costs full price at the provider is inherent and logged: compaction (its `compaction/*` events and replacement entry), a real prompt, tool, or config change (`request/header` with reason `change`), or a process boundary with drift (a differing `resume` snapshot). The provider's own reasoning-content exclusion is managed server-side.
- `agent/pre-step` is the current-request message channel; direct inbox mutation is the eventual later-request channel.
- Tool-result trimming needs no new mechanism: a logged single-entry surface replace (`start === end`) carrying a trimmed `tool/result` under the same `callId` — compaction-family, replay-correct, cache-bust batched by the same pressure logic.
-- Session logs grow one `request/header` snapshot per loop instance plus snapshots on real changes. This is larger than a delta codec but small beside chunk-heavy logs and retains one replay representation. `SESSION_FORMAT_VERSION` stays `0`; legacy delta events are rejected rather than migrated.
-- Snapshot expected outputs changed once (every transcript gains its header events); the fs-writing fixtures are stored in the normalized authored form with cwd-relative tool arguments, because replay only round-trips cwd-independent argument paths.
+- Unreadable referenced attachment objects still fail model requests; [automatic attachment quarantine](../../proposed/bug-fix/2026-08-20-attachment-read-quarantine.md) records the proposed recovery without weakening byte-exact reconstruction.
+- Session logs grow one `request/header` snapshot per loop instance, real change, and later model-message series. Repeating the full system prompt and tool catalog is larger than a delta codec but small beside chunk-heavy logs and retains one self-contained replay representation. `SESSION_FORMAT_VERSION` stays `0`; legacy delta events are rejected rather than migrated.
+- Snapshot fixtures include each repeated series header. Keyless refresh owns those deterministic log changes, while the snapshot harness pins prompt and tool sidecars only for the initial and actual change revisions and reuses the current revision for `series` snapshots. Filesystem-writing fixtures remain in normalized authored form with cwd-relative tool arguments because replay only round-trips cwd-independent argument paths.
diff --git a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md
index 94c1d323be..851045aca7 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-05-reconstructable-requests.zh.md
@@ -22,9 +22,9 @@ Status: implemented
**消息。** `Session.deriveMessages()` 带缓存:每个 surface 条目在首次出现时通过公开的逐事件函数 `deriveEventMessage(event)` 精确投影一次;surface 重写(压缩的 `replace`,即 `SurfaceManager.replaceGeneration`)触发重建。调用方每次获得一个新数组,底层是共享的深度冻结消息:通过投影变异已记录的历史是不可表达的(会抛异常),取代了旧的逐次调用克隆隔离。外部重建器对日志前缀折叠同一个公开函数,因此不可能有两条路径产生分歧。
-`EpochHeader` 记录请求的非历史状态:调用配置、渲染后的系统提示词和工具 schema,空值规范化为缺失。`request/header` 始终写入完整快照:首个循环实例使用 reason `initial`,后续实例使用 `resume`,实例内变更使用 `change`。`foldRequestHeader` 选择最新快照。旧的 `request/header-delta` 事件和已移除的 `fallback` reason 在追加或加载时都会被拒绝。
+`EpochHeader` 记录请求的非历史状态:调用配置、渲染后的系统提示词和工具 schema,空值规范化为缺失。适配器提供的推理强度与 token 默认值会保留其 `adapterDefaults` 来源信息;Web 从日志恢复模型选择时会省略适配器持有的推理强度,因此下一次解析不会把相同的有效配置重新归类为显式选择并产生虚假变更。`request/header` 始终写入完整快照:首个循环实例使用 reason `initial`,后续实例使用 `resume`,实例内变更使用 `change`,内容未变的封装显式开启消息序列或跟随表层替换时使用 `series`。如果发生变化的请求同时开启序列,`change` 快照会携带 `startsSeries: true`,无需重复 header 即可保留这两个独立事实。普通的仅追加后续 Turn、同一序列内后续的 Step 与重试沿用最新快照。`foldRequestHeader` 选择最新快照。旧的 `request/header-delta` 事件和已移除的 `fallback` reason 在追加或加载时都会被拒绝。
-每个拟议步骤先领取其 inbox 批次,再运行 `agent/pre-step`。reject 不打开步骤;enter 打开 `step/start`,并把最终消息批次记录为 `user/message` 事件。随后步骤组装系统提示词与工具,`agent/request` 只能替换冻结的调用配置种子。循环记录所需的完整 header 快照,从派生消息与该 header 构建 `GenerateOptions`,对其深度冻结但保持 `AbortSignal` 活跃。首次调用配置从显式的 `AgentOptions` 出发,保留 fork 覆盖和恢复重配置;后续调用从折叠后的 header 出发。
+每个拟议步骤先领取其 inbox 批次,再运行 `agent/pre-step`。reject 不打开步骤;enter 打开 `step/start`,把最终消息批次记录为 `user/message` 事件,并可使用 `startsRequestSeries: true` 声明独立序列。随后步骤组装系统提示词与工具,`agent/request` 只能替换冻结的调用配置种子。循环记录所需的 initial、resume、change 或 series 完整快照,从派生消息与该 header 构建 `GenerateOptions`,对其深度冻结但保持 `AbortSignal` 活跃。首次调用配置从显式的 `AgentOptions` 出发,保留 fork 覆盖和恢复重配置;后续调用从折叠后的 header 出发。
**已打开步骤是重建边界。** 进入步骤的 `user/message` 批次与任何新写入的 `request/header` 都位于请求分派之前。原子领取后发生的注入加入后续请求;必须影响本次请求的监听器则通过 `agent/pre-step` 返回消息。header 重建选择该步骤的 `request/header`,或在无新 header 写入时沿用前一个快照。
@@ -42,6 +42,7 @@ Status: implemented
- **检测并报告**(比较连续请求,发散时告警):事后捕获违规;违规请求仍可构造并发出。因违规必须在接口层面不可表达而否决。
- **事件驱动组装**(仅在变更信号时重新渲染):存在漏信号的 bug 类别——会话中途注册的工具发出 `tools/change` 而非 `system-prompt/change`,第三方提供方可能什么都不发。逐步骤渲染加值比较在零信号纪律下即可稳健工作。
- **自定义 header-delta 编解码器**(系统行编辑、按名称键控的工具编辑、完整配置/前缀替换):减少了重复字节,却复制了表示及其 diff/apply/fallback 机制。完整快照只保留一种回放表示。
+- **引用前一个 header 的轻量 series 标记**:减少重复的提示词与工具字节,但从该标记开始的窗口若不再读取前序,就无法渲染或重建请求。自包含的完整快照让持久化、局部历史和快照固定共用一种表示。
- **Header 快照上的叙事性变更字段列表**:可以通过比较连续快照推导。`reason` 仍保留,因为实例边界无法从快照值推导。
## 后果
@@ -51,5 +52,6 @@ Status: implemented
- 在提供方处仍需全价计算的内容是固有的且已记录的:压缩(其 `compaction/*` 事件和替换条目)、真正的提示词、工具或配置变更(reason 为 `change` 的 `request/header`),或带漂移的进程边界(不同的 `resume` 快照)。提供方自身的 reasoning-content 排除由服务端管理。
- `agent/pre-step` 是当前请求的消息通道;直接修改 inbox 则是最终进入后续请求的通道。
- 工具结果裁剪无需新机制:一个已记录的单条目 surface replace(`start === end`),携带同一 `callId` 下裁剪后的 `tool/result`——属压缩家族,回放正确,缓存失效由相同的压力逻辑批量处理。
-- 会话日志每个循环实例增长一个 `request/header` 快照,并在真正变更时增加快照。它比 delta 编解码器更大,但相对分片密集型日志仍然很小,并只保留一种回放表示。`SESSION_FORMAT_VERSION` 保持 `0`;旧的 delta 事件被拒绝而非迁移。
-- 快照预期输出变更一次(每个 transcript(文本记录)增加其 header 事件);写入文件系统的 fixture(测试前置数据)以规范化的撰写形式存储,工具参数使用 cwd 相对路径,因为回放只对 cwd 无关的参数路径做往返。
+- 无法读取的被引用附件对象仍会让模型请求失败;[附件自动隔离](../../proposed/bug-fix/2026-08-20-attachment-read-quarantine.zh.md)记录了不削弱字节精确重建的拟议恢复方案。
+- 会话日志会为每个循环实例、真实变更和后续模型消息序列增加一个 `request/header` 快照。重复完整系统提示词与工具目录比 delta 编解码器更大,但相对分片密集型日志仍然很小,并保留一种自包含的回放表示。`SESSION_FORMAT_VERSION` 保持 `0`;旧的 delta 事件被拒绝而非迁移。
+- 快照 fixture 包含每个重复的 series header。无密钥 refresh 负责这些确定性日志变化;快照 harness 只为 initial 与真实 change 修订固定提示词和工具 sidecar,并让 `series` 快照复用当前修订。写入文件系统的 fixture 继续以规范化的撰写形式存储,工具参数使用 cwd 相对路径,因为回放只对 cwd 无关的参数路径做往返。
\ No newline at end of file
diff --git a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.i18n.yaml
index 336d9669ed..a66c6f6065 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md
2026-07-05-subagent-provider-lifecycle-events.md: 503c0d638785e3a4944c8903b8d7d469c68b1881
-2026-07-05-subagent-provider-lifecycle-events.zh.md: e7d1d8c398a6d77efb2dbccc365e0040f38f2d33
+2026-07-05-subagent-provider-lifecycle-events.zh.md: d9d15b4ff688506b84b81c8649e1de4ce50e086d
diff --git a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.zh.md b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.zh.md
index e7d1d8c398..d9d15b4ff6 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.zh.md
@@ -6,9 +6,9 @@ Status: implemented
## 问题
-[提示词变量 Agent Note](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) 让 `dsh-tool-subagent` 从其提供方派生面向模型的措辞:`SubagentProvider.inheritsParentContext`(spawn 和 ACP(Agent Client Protocol)为 `false`,fork 为 `true`)同时驱动工具描述和 `prompt` 参数描述,使 fork 工具不再在上下文继承问题上对模型撒谎。这一修复引入了跨 fiber 的数据依赖:工具描述在工具注册时固定(这是有意为之——描述是 tool-choice 引导所在之处),但提供方在自己的插件 fiber 上到达,时机不确定。
+[提示词变量 Agent Note](2026-07-05-prompt-variables-and-tool-guidance-ownership.zh.md) 让 `dsh-tool-subagent` 从其提供方派生面向模型的措辞:`SubagentProvider.inheritsParentContext`(spawn 和 ACP(Agent Client Protocol)为 `false`,fork 为 `true`)同时驱动工具描述和 `prompt` 参数描述,使 fork 工具不再在上下文继承问题上对模型撒谎。这一修复引入了跨 fiber 的数据依赖:工具描述在工具注册时固定(这是有意为之——描述是 tool-choice 引导所在之处),但提供方在自己的插件 fiber 上到达,时机不确定。
-如果在工具插件的 `apply` 时刻解析提供方,就会产生一个隐式的加载顺序要求(「在 cordis.yml 中把后端列在工具前面」)。这个要求不成立,因为 Cordis Loader 并发启动同级条目,且 `Entry.init()` 不会等待激活完成:延迟到达的后端即使列在前面,也可能让工具 fiber 失败。Loader 不提供同级顺序保证——「异步状态不是同步状态」(见[防御性模式](../../../../docs/defensive-patterns.md))。
+如果在工具插件的 `apply` 时刻解析提供方,就会产生一个隐式的加载顺序要求(「在 cordis.yml 中把后端列在工具前面」)。这个要求不成立,因为 Cordis Loader 并发启动同级条目,且 `Entry.init()` 不会等待激活完成:延迟到达的后端即使列在前面,也可能让工具 fiber 失败。Loader 不提供同级顺序保证——「异步状态不是同步状态」(见[防御性模式](../../../../docs/defensive-patterns.zh.md))。
## 决策
@@ -31,6 +31,6 @@ Status: implemented
## 后果
- 从命名提供方派生状态的消费方响应 `subagent/provider-added`/`-removed` 事件,而非在 `apply` 时读取注册表;`dsh-tool-subagent` 是参考实现。
-- **添加时大声失败;移除时按监听器隔离。** 添加监听器可以回滚注册。移除在 disposal 期间运行,因此单个监听器抛异常只会被记录日志,不会饿死后续镜像或干扰拆解流程。`start()` 仍在每次运行时按名称解析提供方,防止陈旧工具调用已移除的后端。见[事件目录](../../../../docs/subsystems/subagent.md#cordis-surface)与[生产者/消费方映射](../../../../docs/event-producer-consumer.md)。
+- **添加时大声失败;移除时按监听器隔离。** 添加监听器可以回滚注册。移除在 disposal 期间运行,因此单个监听器抛异常只会被记录日志,不会饿死后续镜像或干扰拆解流程。`start()` 仍在每次运行时按名称解析提供方,防止陈旧工具调用已移除的后端。见[事件目录](../../../../docs/subsystems/subagent.zh.md#cordis-surface)与[生产者/消费方映射](../../../../docs/event-producer-consumer.zh.md)。
- **工具不存在的窗口期。** 在后端 disposal 与重新注册之间(HMR 重载期间),模型看不到 subagent 工具。这是诚实的状态——替代方案是一个向空处分发的工具——工具注册表发出的 `tools/change` 事件会使提示词组装保持最新状态。
- **两个等待中的 fiber 共享同一 `toolName` 是无效配置,被延迟捕获。** 如果两个 `dsh-tool-subagent` 加载实例分别指定了不同的提供方但相同的 `toolName`,两者都会等待,先到达的提供方先注册;第二次注册仅在其提供方到达时才抛异常。插件中的 `TODO(subagent-dup-toolname)` 记录了这一影响范围;工具注册表的重名拒绝机制仍是最终防线。
diff --git a/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.i18n.yaml
index cf8eaf225c..cc278292d9 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.md
2026-07-05-windows-jsonl-durable-publish.md: 546cde6086f3c84e22b4d4de144a48bb3425cd4e
-2026-07-05-windows-jsonl-durable-publish.zh.md: 205460bcd374bd351cfdf541eb4041c09461229d
+2026-07-05-windows-jsonl-durable-publish.zh.md: b99032e9d7e72e2028f39c5af91659278fd81343
diff --git a/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.zh.md b/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.zh.md
index 205460bcd3..b99032e9d7 100644
--- a/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-05-windows-jsonl-durable-publish.zh.md
@@ -28,7 +28,7 @@ Windows 通过持久的暂存发布来创建缺失目录:创建一个以固定
## 影响
-该后端在各平台上维持同一项外部约定:首次追加要么把完整日志发布到最终名称,要么失败且不覆盖已有日志。平台分流只是实现细节;`SessionPersistence` API 和 JSONL 逻辑记录格式均不改变。后续的 [Zstandard 编码决策](2026-07-19-zstandard-jsonl-session-logs.md)会先作用于不透明字节,然后才由任一平台执行发布。
+该后端在各平台上维持同一项外部约定:首次追加要么把完整日志发布到最终名称,要么失败且不覆盖已有日志。平台分流只是实现细节;`SessionPersistence` API 和 JSONL 逻辑记录格式均不改变。后续的 [Zstandard 编码决策](2026-07-19-zstandard-jsonl-session-logs.zh.md)会先作用于不透明字节,然后才由任一平台执行发布。
Windows 测试会在原生 Windows 上执行真实的 Win32 发布路径。断电行为属于 API 约定属性,单元测试无法证明;可测试的不变量包括:Windows 物化不会调用目录 fsync、最终路径冲突会失败、达到最大长度的目标路径组件仍可物化、临时日志在发布前已经执行 fsync,并且生成的日志可以正常加载。
diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml
index e7e49aa115..66dd29f3a4 100644
--- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.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/implemented/architecture/2026-07-06-timeout-deadline-library.md
-2026-07-06-timeout-deadline-library.md: 38f048d16ecba0e5278ae34b0c88b7889dcfa47a
-2026-07-06-timeout-deadline-library.zh.md: e8b0ab62b19d931c33027d5e6c9919804e80aa99
+2026-07-06-timeout-deadline-library.md: 95adc41bffff6d7711685ebc52cb73b2b455df41
+2026-07-06-timeout-deadline-library.zh.md: 8b7b18a2d1e7757102afc81bea03245de2707d86
diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md
index 38f048d16e..95adc41bff 100644
--- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md
+++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.md
@@ -8,7 +8,7 @@ English | [中文](2026-07-06-timeout-deadline-library.zh.md)
Timeout handling was drifting apart across the tool-bearing capabilities, and the divergence was not superficial — it was the same logic re-implemented three ways, each with its own subtle correctness burden.
-- **bash** (then in the bash-local implementation's `run.ts`) had a full, correct timeout inside the process plumbing: a config-clamped `timeoutMs`, two independent triggers — a `killTimer` for the timeout and an `onAbort` listener for upstream cancellation — each calling one `kill()` closure that escalates SIGTERM→grace→SIGKILL on the process group, and two orthogonal outcome booleans (`timedOut`, `aborted`) latched independently. After this consolidation, the plumbing — today [packages/subprocess/subprocess-local/src/spawn.ts](../../../../packages/subprocess/subprocess-local/src/spawn.ts) — only reacts to aborts; [packages/shell/bash-local/src/index.ts](../../../../packages/shell/bash-local/src/index.ts) owns the fused deadline and the `timedOut`/`aborted` classification.
+- **bash** (then in the bash-local implementation's `run.ts`) had a full, correct timeout inside the process plumbing: a config-clamped `timeoutMs`, two independent triggers — a `killTimer` for the timeout and an `onAbort` listener for upstream cancellation — each calling one `kill()` closure that escalates SIGTERM→grace→SIGKILL on the process group, and two orthogonal outcome booleans (`timedOut`, `aborted`) latched independently. After this consolidation, the plumbing — [packages/subprocess/subprocess-local/src/spawn.ts](../../../../packages/subprocess/subprocess-local/src/spawn.ts) — only reacts to aborts; [packages/shell/bash-local/src/index.ts](../../../../packages/shell/bash-local/src/index.ts) owns the fused deadline and the `timedOut`/`aborted` classification.
- **web_fetch** ([packages/web/web-fetch-http/src/provider.ts](../../../../packages/web/web-fetch-http/src/provider.ts)) had a correct but *hand-rolled* timeout: it constructed an `AbortController`, wired `setTimeout(() => controller.abort(new WebError(…, 'WEB_FETCH_TIMEOUT')))`, manually added and removed the upstream-signal listener, cleared the timer in a `finally`, and recovered the timeout reason from `signal.reason` in a `translateAbortOrNetwork` helper because the reader surfaces a bare `AbortError`.
- **web_search** ([packages/web/tool-web/src/search.ts](../../../../packages/web/tool-web/src/search.ts)) had **no timeout at all**: `WebSearchRequest` ([packages/web/web/src/types.ts](../../../../packages/web/web/src/types.ts)) carries no `timeoutMs` field, and each provider's `search()` only forwards `exec.signal`. (web_search stays untimed here — see Consequences.)
diff --git a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md
index e8b0ab62b1..8b7b18a2d1 100644
--- a/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-06-timeout-deadline-library.zh.md
@@ -8,7 +8,7 @@ Status: implemented
超时处理在各个承载工具的能力之间逐渐分化,而且这种分化并非表面的:同一套逻辑被以三种方式重新实现,各自带有微妙的正确性负担。
-- **bash**(当时位于 bash-local 实现的 `run.ts`)在进程管道内部有一套完整、正确的超时实现:一个经配置钳位的 `timeoutMs`,两个独立触发器(用于超时的 `killTimer` 和用于上游取消的 `onAbort` 监听器),各自调用同一个 `kill()` 闭包对进程组执行 SIGTERM→宽限期→SIGKILL 升级,以及两个正交的结果布尔值(`timedOut`、`aborted`)独立锁存。经此次整合之后,这套管道——今天位于 [packages/subprocess/subprocess-local/src/spawn.ts](../../../../packages/subprocess/subprocess-local/src/spawn.ts)——只响应中止;[packages/shell/bash-local/src/index.ts](../../../../packages/shell/bash-local/src/index.ts) 拥有融合的 deadline 以及 `timedOut`/`aborted` 分类。
+- **bash**(当时位于 bash-local 实现的 `run.ts`)在进程管道内部有一套完整、正确的超时实现:一个经配置钳位的 `timeoutMs`,两个独立触发器(用于超时的 `killTimer` 和用于上游取消的 `onAbort` 监听器),各自调用同一个 `kill()` 闭包对进程组执行 SIGTERM→宽限期→SIGKILL 升级,以及两个正交的结果布尔值(`timedOut`、`aborted`)独立锁存。经此次整合之后,这套管道——位于 [packages/subprocess/subprocess-local/src/spawn.ts](../../../../packages/subprocess/subprocess-local/src/spawn.ts)——只响应中止;[packages/shell/bash-local/src/index.ts](../../../../packages/shell/bash-local/src/index.ts) 拥有融合的 deadline 以及 `timedOut`/`aborted` 分类。
- **web_fetch**([packages/web/web-fetch-http/src/provider.ts](../../../../packages/web/web-fetch-http/src/provider.ts))有一套正确但*手写*的超时:构造一个 `AbortController`,连接 `setTimeout(() => controller.abort(new WebError(…, 'WEB_FETCH_TIMEOUT')))`,手动添加和移除上游信号监听器,在 `finally` 中清除定时器,并在 `translateAbortOrNetwork` 辅助函数中从 `signal.reason` 恢复超时原因(因为 reader 只抛出裸 `AbortError`)。
- **web_search**([packages/web/tool-web/src/search.ts](../../../../packages/web/tool-web/src/search.ts))**完全没有超时**:`WebSearchRequest`([packages/web/web/src/types.ts](../../../../packages/web/web/src/types.ts))不携带 `timeoutMs` 字段,各提供方的 `search()` 只转发 `exec.signal`。(web_search 在本次设计中保持无超时——见「后果」。)
@@ -103,7 +103,7 @@ export function timeoutOf(x: AbortSignal | { reason?: unknown }, code?: string):
- `AbortSignal.any` 和 `using`/`Symbol.dispose` 在此首次进入本仓库(Node ≥ 24 基线,已满足)。
- 模型流现在共享一个可重启的定时器约定,不会把滑动的空闲间隔变成总调用截止时间,也不会计入消费方思考时间。能够观察到带外传输活动的适配器可以对尚未结算的 demand 调用 `pulse()`;被屏蔽的活动对 watchdog 仍不可见。该原语仍然只做通知;适配器测试证明其传输观察到稳定信号并终止。
-以下内容不在本次范围内,列出以标明边界:`web_search` 可以在其工具 schema 和快照覆盖规划完成后获得可选的面向模型的 `timeout_ms`;基于 ripgrep 的文件系统发现工具([打包的 ripgrep 搜索](2026-08-01-packaged-ripgrep-search.md))通过 `dsh-tool-call-timeout-policy` 和 `exec.signal` 消费同样的提供方自有 deadline 形状;`tools/execute` waterfall(瀑布式事件)中间件可以通过驱动 `exec.signal` 为每次工具调用设置默认 deadline——那将是一个*消费*本库的插件,仍然只做通知,硬终止仍是各能力自己的事。
+以下内容不在本次范围内,列出以标明边界:`web_search` 可以在其工具 schema 和快照覆盖规划完成后获得可选的面向模型的 `timeout_ms`;基于 ripgrep 的文件系统发现工具([打包的 ripgrep 搜索](2026-08-01-packaged-ripgrep-search.zh.md))通过 `dsh-tool-call-timeout-policy` 和 `exec.signal` 消费同样的提供方自有 deadline 形状;`tools/execute` waterfall(瀑布式事件)中间件可以通过驱动 `exec.signal` 为每次工具调用设置默认 deadline——那将是一个*消费*本库的插件,仍然只做通知,硬终止仍是各能力自己的事。
## 曾考虑的替代方案
diff --git a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.i18n.yaml
index 5e943fed2b..554114fff0 100644
--- a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.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/implemented/architecture/2026-07-06-tool-result-retention-library.md
-2026-07-06-tool-result-retention-library.md: 8d938db8f5fa78398a39e97cc877308200f7d60f
-2026-07-06-tool-result-retention-library.zh.md: 0b2fe841beed21511c4088732713d3fd9fd9048f
+2026-07-06-tool-result-retention-library.md: 464e3d51a0051487b7c29f0c01a11acb91d160e5
+2026-07-06-tool-result-retention-library.zh.md: 49361eec4b649d2d68dc36929baa0f9ff580eb68
diff --git a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md
index 8d938db8f5..464e3d51a0 100644
--- a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md
+++ b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.md
@@ -16,7 +16,7 @@ The shared abstraction the tools need is **retention**, not generic collection.
The library has two independent retainers:
-- `ItemRetainer` handles ordered logical units such as paths, grep matches, or search sources. It supports `head` retention only in v1, while keeping the retainer shape open to additional retention strategies later.
+- `ItemRetainer` handles ordered logical units such as paths, grep matches, or search sources. It supports only `head` retention, while keeping the retainer shape open to additional strategies.
- `TextRetainer` handles byte-oriented text streams such as bash stdout/stderr or web response bodies. It supports `head`, `tail`, and `headTail` retention while preserving UTF-8 boundaries at `finish()`.
Both retainers return a small `PushDecision` after each `push()` so callers can tell whether that unit/chunk was fully retained and whether the accumulated result is now truncated. Omission counts are exact because callers keep feeding every observed item/chunk.
@@ -95,7 +95,7 @@ type TextRetentionStrategy =
### Tool mapping
-`read` is intentionally outside the v1 retention library. Its `read-render` helper owns a file-specific pagination contract: `offset` / `limit`, line numbers, `totalLines`, offset-out-of-range errors, per-line preview truncation, and a selected-output byte cap that can stop scanning mid-window. That is a line-window renderer, not a generic retention primitive. It may share future neutral notice helpers, but it should not pass its already-selected window through `ItemRetainer`.
+`read` is intentionally outside the retention library. Its `read-render` helper owns a file-specific pagination contract: `offset` / `limit`, line numbers, `totalLines`, offset-out-of-range errors, per-line preview truncation, and a selected-output byte cap that can stop scanning mid-window. That is a line-window renderer, not a generic retention primitive. It may share future neutral notice helpers, but it should not pass its already-selected window through `ItemRetainer`.
`FsGlobEntry` and `FlatGrepMatch` below are the intended discovery-tool item shapes, not existing retention-library exports. `FsGlobEntry` is one backend-derived path, and `FlatGrepMatch` is one ungrouped grep match before the backend groups retained matches by file.
@@ -142,15 +142,15 @@ The formatter hook is deliberately small: a tool turns a `RetentionNotice` into
**Boundaries the library holds.** `truncated` means the retainer omitted otherwise-available content because of a budget; it never means the upstream was incomplete. Tool-specific states — `incomplete`, permission failures, provider partial failures, binary skips, bash spill-path recovery, invalid UTF-8 — stay in tool-domain fields, outside the retainer. When a future change migrates a tool, that package's README and tests must prove the model-facing result text is unchanged except for deliberate notice wording.
-**Tradeoffs accepted.** The v1 API deliberately supports only item `head` retention and text `head` / `tail` / `headTail`; windows, grouped budgets, sort-aware caps, and upstream-stop control wait until a second consumer proves the need. Text retention counts bytes for process/body safety, leaving character- and line-level preview budgets as separate tool-owned concerns.
+**Tradeoffs accepted.** The API deliberately supports only item `head` retention and text `head` / `tail` / `headTail`; windows, grouped budgets, sort-aware caps, and upstream-stop control wait until a second consumer proves the need. Text retention counts bytes for process/body safety, leaving character- and line-level preview budgets as separate tool-owned concerns.
## Alternatives considered
**Post-hoc `truncate(text)` only.** Rejected: it matches Codex's history/tool-output truncation use case but loses item counts, grouping boundaries, UTF-8-safe byte windows, and exact omission metadata.
-**One generic `Collector` with pluggable callbacks.** Rejected for v1: it hides the two important resource modes. Logical item retention counts items; text retention counts bytes and preserves UTF-8 boundaries. Separate `ItemRetainer` and `TextRetainer` names make that difference explicit while keeping the API small.
+**One generic `Collector` with pluggable callbacks.** Rejected: it hides the two important resource modes. Logical item retention counts items; text retention counts bytes and preserves UTF-8 boundaries. Separate `ItemRetainer` and `TextRetainer` names make that difference explicit while keeping the API small.
-**Put `read` windowing behind `ItemRetainer`.** Rejected for v1: `read` is the only current window consumer, and its semantics are file pagination rather than generic retention. A single `Omitted` count cannot represent both sides of a line window, and `read` also carries `totalLines`, offset-range errors, per-line preview truncation, and a byte cap over selected output. Keeping `read-render` tool-owned avoids growing the shared library around one special case.
+**Put `read` windowing behind `ItemRetainer`.** Rejected: `read` is the only shipped window consumer, and its semantics are file pagination rather than generic retention. A single `Omitted` count cannot represent both sides of a line window, and `read` also carries `totalLines`, offset-range errors, per-line preview truncation, and a byte cap over selected output. Keeping `read-render` tool-owned avoids growing the shared library around one special case.
**Make truncation part of `ToolExecutionResult`.** Rejected: the tool registry would have to understand tool-specific recovery guidance, grouping, line numbering, exit status, and provider semantics. Retention is a library used by a tool's Native renderer; the model-facing projection remains tool-owned while the [canonical value](2026-07-20-canonical-tool-output-contract.md) may retain the complete acquired result.
diff --git a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md
index 0b2fe841be..49361eec4b 100644
--- a/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-06-tool-result-retention-library.zh.md
@@ -16,7 +16,7 @@ Status: implemented
该库包含两个相互独立的 retainer:
-- `ItemRetainer` 处理有序逻辑单元,例如路径、grep 匹配项或搜索来源。v1 只支持 `head` 保留,同时维持 retainer 形态,以便未来加入其他保留策略。
+- `ItemRetainer` 处理有序逻辑单元,例如路径、grep 匹配项或搜索来源。它只支持 `head` 保留,同时维持 retainer 形态,以便未来加入其他保留策略。
- `TextRetainer` 处理面向字节的文本流,例如 bash stdout/stderr 或 web 响应正文。它支持 `head`、`tail` 和 `headTail` 保留,并在 `finish()` 时维持 UTF-8 边界。
两个 retainer 都会返回一个小型 `PushDecision`;每次调用 `push()` 后,调用方都能得知该单元/分片是否完整保留,以及累积结果此时是否已被截断。因为调用方会继续输入每一个已观察到的条目/分片,所以省略计数是精确的。
@@ -95,7 +95,7 @@ type TextRetentionStrategy =
### 工具映射
-`read` 被有意排除在 v1 保留库之外。它的 `read-render` 辅助函数拥有文件专用的分页约定:`offset`/`limit`、行号、`totalLines`、offset 越界错误、逐行预览截断,以及能够在窗口中途停止扫描的所选输出字节上限。这是行窗口渲染器,不是通用保留原语。它未来可以共享中性的提示辅助函数,但不应把已经选定的窗口再传入 `ItemRetainer`。
+`read` 被有意排除在保留库之外。它的 `read-render` 辅助函数拥有文件专用的分页约定:`offset`/`limit`、行号、`totalLines`、offset 越界错误、逐行预览截断,以及能够在窗口中途停止扫描的所选输出字节上限。这是行窗口渲染器,不是通用保留原语。它未来可以共享中性的提示辅助函数,但不应把已经选定的窗口再传入 `ItemRetainer`。
下文的 `FsGlobEntry` 与 `FlatGrepMatch` 是预期由发现工具使用的条目形态,不是现有保留库的导出。`FsGlobEntry` 是一个由后端派生的路径;`FlatGrepMatch` 是后端将保留匹配项按文件分组之前的一条未分组 grep 匹配。
@@ -103,7 +103,7 @@ type TextRetentionStrategy =
`grep` 在分组前使用 `ItemRetainer`,并将其配置为 `{ kind: 'head', maxItems: grepMaxMatches }`。执行器解析 ripgrep 输出、映射路径、应用逐行预览截断,并输入扁平匹配项。调用 `finish()` 后,工具按文件对保留的匹配项分组;如果行内结果达到上限,还可以通过 spill seam 保存完整匹配列表。分组不属于 retainer,因为上限针对匹配总数,而不是文件数;逐匹配项的预览截断和 `incomplete` 也与结果级保留相互独立。
-`bash` 可以使用 `TextRetainer`,配置为 `tail` 或 `headTail`,并读取至进程结束。bash 执行器仍负责 spill 文件、退出状态、信号、超时与后台任务行为;保留辅助函数只在需要该行为时替换临时实现的内存首尾核算。长时间运行任务的所有权与[通用长时间运行工具的运行时](2026-06-20-generic-long-running-tool-runtime.md)相互独立。
+`bash` 可以使用 `TextRetainer`,配置为 `tail` 或 `headTail`,并读取至进程结束。bash 执行器仍负责 spill 文件、退出状态、信号、超时与后台任务行为;保留辅助函数只在需要该行为时替换临时实现的内存首尾核算。长时间运行任务的所有权与[通用长时间运行工具的运行时](2026-06-20-generic-long-running-tool-runtime.zh.md)相互独立。
`web_fetch` 可以使用 `TextRetainer`,配置为 `head` 或 `headTail`;如果提供方必须在内部读取和解码,也可以保留由提供方负责的正文上限。无论采用哪种方式,fetch 结果中的 `truncated` 仍是提供方/工具事实,该库只提供保留文本与省略元数据。
@@ -138,20 +138,20 @@ const formatGrepNotice = (notice: RetentionNotice): string =>
**已交付内容。** `@deepseek-ai/dsh-output-retention` 导出 `ItemRetainer`、`TextRetainer`、结果类型(`RetainedItems`、`RetainedText`)、策略类型(`ItemRetentionStrategy`、`TextRetentionStrategy`)、`Omitted`、`PushDecision`、`RetentionNotice`,以及中性的提示辅助函数 `describeOmitted`/`formatRetentionNotice`,且不依赖 Cordis 或任何工具包。单元测试覆盖具有精确省略计数的条目头部保留、文本头部保留、文本尾部保留、首尾字节保留、零预算、UTF-8 边界处理(2、3、4 字节码位,以及每个裁切位置上的无效起始字节)和未知省略量的措辞。
-**已记录但尚未迁移的内容。** `glob`、`grep`、`bash`、`web_fetch` 与 `web_search` 的映射已记录在[包 README](../../../../packages/util/output-retention/README.md) 中,但本次改动并未把每个工具都迁移到该库;迁移工作刻意留作独立的后续任务。`read` 被明确记录为不在范围内:其 `read-render` 行窗口约定(`offset`/`limit`、`totalLines`、offset 范围错误、逐行预览截断,以及针对所选窗口的字节上限)不属于通用保留,而一个 `Omitted` 计数也无法同时表达行窗口两侧。
+**已记录但尚未迁移的内容。** `glob`、`grep`、`bash`、`web_fetch` 与 `web_search` 的映射已记录在[包 README](../../../../packages/util/output-retention/README.zh.md) 中,但本次改动并未把每个工具都迁移到该库;迁移工作刻意留作独立的后续任务。`read` 被明确记录为不在范围内:其 `read-render` 行窗口约定(`offset`/`limit`、`totalLines`、offset 范围错误、逐行预览截断,以及针对所选窗口的字节上限)不属于通用保留,而一个 `Omitted` 计数也无法同时表达行窗口两侧。
**该库维持的边界。** `truncated` 表示 retainer 因预算省略了原本可用的内容,绝不表示上游不完整。工具专用状态,包括 `incomplete`、权限失败、提供方局部失败、跳过二进制文件、bash spill 路径恢复和无效 UTF-8,均留在工具领域字段中、位于 retainer 之外。未来改动迁移某项工具时,该包的 README 与测试必须证明,除了有意改变的提示措辞外,模型可见的结果文本没有变化。
-**接受的取舍。** v1 接口刻意只支持条目的 `head` 保留,以及文本的 `head`/`tail`/`headTail` 保留;窗口、分组预算、感知排序的上限和上游停止控制,要等第二个消费方证明需求后再引入。文本保留按字节计数,以保障进程/正文安全;字符级和行级预览预算继续由具体工具负责。
+**接受的取舍。**接口刻意只支持条目的 `head` 保留,以及文本的 `head`/`tail`/`headTail` 保留;窗口、分组预算、感知排序的上限和上游停止控制,要等第二个消费方证明需求后再引入。文本保留按字节计数,以保障进程/正文安全;字符级和行级预览预算继续由具体工具负责。
## 考虑过的替代方案
**只进行事后 `truncate(text)`。** 不予采纳:它适合 Codex 的历史/工具输出截断场景,却会丢失条目计数、分组边界、UTF-8 安全的字节窗口与精确省略元数据。
-**使用一个带可插拔回调的通用 `Collector`。** v1 不予采纳,因为它会掩盖两种重要的资源模式。逻辑条目保留按条目计数;文本保留按字节计数并维持 UTF-8 边界。独立的 `ItemRetainer` 与 `TextRetainer` 名称明确表达这种差异,同时保持 API 精简。
+**使用一个带可插拔回调的通用 `Collector`。**不予采纳,因为它会掩盖两种重要的资源模式。逻辑条目保留按条目计数;文本保留按字节计数并维持 UTF-8 边界。独立的 `ItemRetainer` 与 `TextRetainer` 名称明确表达这种差异,同时保持 API 精简。
-**把 `read` 窗口交给 `ItemRetainer`。** v1 不予采纳:`read` 是当前唯一的窗口消费方,其语义属于文件分页,而不是通用保留。一个 `Omitted` 计数无法表示行窗口两侧,而且 `read` 还携带 `totalLines`、offset 范围错误、逐行预览截断和针对所选输出的字节上限。让 `read-render` 由工具所有,可以避免共享库围绕一项特例膨胀。
+**把 `read` 窗口交给 `ItemRetainer`。**不予采纳:`read` 是唯一已交付的窗口消费方,其语义属于文件分页,而不是通用保留。一个 `Omitted` 计数无法表示行窗口两侧,而且 `read` 还携带 `totalLines`、offset 范围错误、逐行预览截断和针对所选输出的字节上限。让 `read-render` 由工具所有,可以避免共享库围绕一项特例膨胀。
-**让截断成为 `ToolExecutionResult` 的一部分。** 不予采纳:工具注册表将不得不理解工具专用的恢复指引、分组、行号、退出状态和提供方语义。保留是由工具的 Native renderer(原生渲染器)使用的库;模型可见投影继续由工具所有,而[规范值](2026-07-20-canonical-tool-output-contract.md)可以保留完整的已采集结果。
+**让截断成为 `ToolExecutionResult` 的一部分。** 不予采纳:工具注册表将不得不理解工具专用的恢复指引、分组、行号、退出状态和提供方语义。保留是由工具的 Native renderer(原生渲染器)使用的库;模型可见投影继续由工具所有,而[规范值](2026-07-20-canonical-tool-output-contract.zh.md)可以保留完整的已采集结果。
**在每个面向模型的工具 schema 中公开上限。** 不作为默认方案:Claude Code 的 grep 公开 `head_limit`/`offset`,但本 harness 会把常规预算保留为部署配置,除非模型确实需要控制分页。未来可以为具体工具增加类似 read 的续传字段;它不属于共享保留原语。
diff --git a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml
index 10a29ee499..373b1293ce 100644
--- a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.md
2026-07-07-tool-call-timeout-policy.md: 92618cc8c761b38d7e516c9d00eb3de1c37831a8
-2026-07-07-tool-call-timeout-policy.zh.md: cc633ceaa3840331826f6475e603e78a98f0afd2
+2026-07-07-tool-call-timeout-policy.zh.md: 0303fadd134c6eb8c41449823b62f1458f4523ba
diff --git a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md
index cc633ceaa3..0303fadd13 100644
--- a/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-07-tool-call-timeout-policy.zh.md
@@ -6,7 +6,7 @@ Status: implemented
## 问题
-[超时/截止时间 Agent Note](2026-07-06-timeout-deadline-library.md) 将计时与分类原语提取到了 `@deepseek-ai/dsh-timeout`,但超时策略仍然附着在各个能力和面向模型的 schema 上。`bash` 暴露了 `timeoutMs`;`web_fetch` 暴露了 `timeout_ms`;`web_search` 没有面向模型的超时参数,尽管提供方已经遵循 `exec.signal`;未来的 grep/glob 工具要么直接导入超时库,要么自行发明超时策略。对于一个插件 SDK 来说,这是错误的编写范式:工具作者通常只需将 `exec.signal` 转发给其调用的实现,而部署策略来决定预算。
+[超时/截止时间 Agent Note](2026-07-06-timeout-deadline-library.zh.md) 将计时与分类原语提取到了 `@deepseek-ai/dsh-timeout`,但超时策略仍然附着在各个能力和面向模型的 schema 上。`bash` 暴露了 `timeoutMs`;`web_fetch` 暴露了 `timeout_ms`;`web_search` 没有面向模型的超时参数,尽管提供方已经遵循 `exec.signal`;未来的 grep/glob 工具要么直接导入超时库,要么自行发明超时策略。对于一个插件 SDK 来说,这是错误的编写范式:工具作者通常只需将 `exec.signal` 转发给其调用的实现,而部署策略来决定预算。
与此同时,仓库中并非所有超时都是面向模型的工具调用预算。钩子通过直接调用 `ctx.shell` 执行命令钩子,而非通过 `ctx.tools.execute()`;`bash` 模型工具通过同一个后端复用前台执行、后台启动、后台轮询和钩子复用。一步到位地将所有超时移入工具插件会混淆这些路径,并有破坏钩子超时语义的风险。
@@ -16,7 +16,7 @@ Status: implemented
- `@deepseek-ai/dsh-timeout` 仍是拥有 `deadline()` 和 `timeoutOf()` 的共享库。
- `@deepseek-ai/dsh-tools` 在 `tools/pre-execute` 和 `tools/post-execute` 之间有一个环绕分发的 waterfall(瀑布式事件)`tools/execute`。
-- [仓库命名约定](2026-08-11-repository-naming-contract-and-rename-ledger.md)使用 `@deepseek-ai/dsh-tool-call-timeout-policy`,准确说明该策略所限制的操作。插件从 runtime 读取每个工具声明的 `timeoutMs`,并通过派生新的 `exec.signal` 来包装有此声明的调用。
+- [仓库命名约定](2026-08-11-repository-naming-contract-and-rename-ledger.zh.md)使用 `@deepseek-ai/dsh-tool-call-timeout-policy`,准确说明该策略所限制的操作。插件从 runtime 读取每个工具声明的 `timeoutMs`,并通过派生新的 `exec.signal` 来包装有此声明的调用。
执行流水线如下:
@@ -52,7 +52,7 @@ catch 是基础 `next`(而非 waterfall 之外的东西)这一点至关重
searchTimeoutMs: 30000
```
-超时放在工具定义上而非自由文本名称映射中,消除了拼错名称导致策略不生效的问题。`defineTool` 校验预算为正有限数。分发期间,执行器派生截止信号并将其赋给 `exec.signal`;注册表依据[工具取消约定](2026-07-19-cooperative-tool-cancellation.md),在执行工具体之前将该截止信号与调用方的原始信号融合。执行器随后恢复调用方信号,并将自身的超时转换为 `TOOL_TIMEOUT`;没有预算的工具原样通过。
+超时放在工具定义上而非自由文本名称映射中,消除了拼错名称导致策略不生效的问题。`defineTool` 校验预算为正有限数。分发期间,执行器派生截止信号并将其赋给 `exec.signal`;注册表依据[工具取消约定](2026-07-19-cooperative-tool-cancellation.zh.md),在执行工具体之前将该截止信号与调用方的原始信号融合。执行器随后恢复调用方信号,并将自身的超时转换为 `TOOL_TIMEOUT`;没有预算的工具原样通过。
信号替换采用**就地修改 `exec.signal`** 的方式,而非向 `next()` 传递新对象。Cordis 的 waterfall `next()` 忽略传入的任何参数,并以共享的 payload 数组重新调用下游监听器(`vendor/cordis/src/events.ts`),因此修改共享对象是包装器向注册表提供截止信号的方式。注册表会在进入工具体前再次融合已捕获的调用方信号;插件则在 `finally` 中将 `exec.signal` 恢复为调用方的原始值,使 `tools/post-execute` 永远不会看到本插件的截止信号。
diff --git a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml
index efed9ca5ea..20d0e4f85c 100644
--- a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md
2026-07-08-agent-scope-contexts.md: eb3f6f247bac1a1d81aa2644132c7b9cc04d602c
-2026-07-08-agent-scope-contexts.zh.md: fe82ac18d07de97330e86461e6bdf86edc37d2ae
+2026-07-08-agent-scope-contexts.zh.md: a0f4ffb0ef80dd2fc1ee61c9ab3f4730c28c687e
diff --git a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md
index fe82ac18d0..a0f4ffb0ef 100644
--- a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.zh.md
@@ -16,7 +16,7 @@ Status: implemented
每个存活的 agent 拥有一个扁平的注册层,通过 `agent.ctx` 暴露。代码通过拥有某项贡献的上下文进行注册;具备作用域感知的服务将部署全局注册与恰好一个匹配的 agent 层合并;操作从其真实 agent 选择该层;该层在 agent 的完整发布生命周期内存在。
-Cordis 是 SDK 底层的插件框架。Cordis **上下文**是插件用来访问服务和注册效果的对象,效果的清理跟随该上下文。[Cordis 入门](../../../../docs/cordis-primer.md)对该框架有更详细的说明。
+Cordis 是 SDK 底层的插件框架。Cordis **上下文**是插件用来访问服务和注册效果的对象,效果的清理跟随该上下文。[Cordis 入门](../../../../docs/cordis-primer.zh.md)对该框架有更详细的说明。
对大多数贡献者而言,完整约定是四条规则:
@@ -45,7 +45,7 @@ flowchart LR
缺失的交叉边即隔离规则:Agent A 的本地注册不会进入 Agent B 的视图,父级的注册也不会仅因父级拥有子级的生命周期就进入子级。
-配套的[运行时设计 Agent Note](2026-07-12-agent-scope-runtime-design.md) 阐述了实现与正确性推理。[subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) 负责独立的 `persona`、`toolFilter` 和 `maxDepth` 功能。
+配套的[运行时设计 Agent Note](2026-07-12-agent-scope-runtime-design.zh.md) 阐述了实现与正确性推理。[subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.zh.md) 负责独立的 `persona`、`toolFilter` 和 `maxDepth` 功能。
### 注册来源决定可见性与清理
@@ -104,7 +104,7 @@ setup 接收一个完整的受信 Cordis 上下文,因此可以组合普通插
在 Cordis 层面,`Scoped` 是一个不透明的路由接收器。它携带用于选择监听器的过滤器,但本身不是领域对象。因此事件签名将真实的 `Agent`、工具执行、审批请求或其他主体作为显式参数保留,供监听器检查。
-以 `{ global: true }` 注册的监听器有意绕过上下文受众过滤,但其清理仍跟随注册上下文。注册表成员变更通知保持不过滤,因为它们描述的是共享注册表状态而非某个 agent 的操作。详尽的事件参考是各[子系统页面](../../../../docs/subsystems/core.md)上生成的 `cordis-surface` 区块的集合——每个事件作用域在其所属页面上(`agent/*` 与 `agent-loop/*` 在 core.md 本页)。
+以 `{ global: true }` 注册的监听器有意绕过上下文受众过滤,但其清理仍跟随注册上下文。注册表成员变更通知保持不过滤,因为它们描述的是共享注册表状态而非某个 agent 的操作。详尽的事件参考是各[子系统页面](../../../../docs/subsystems/core.zh.md)上生成的 `cordis-surface` 区块的集合——每个事件作用域在其所属页面上(`agent/*` 与 `agent-loop/*` 在 core.md 本页)。
### 创建最后发布,dispose 最后撤销
@@ -138,6 +138,8 @@ flowchart TB
detach --> revoke["Dispose the agent scope"]
```
+
+
## 安全与权限是非目标
agent 作用域组合的是受信的同进程注册。它不沙箱化插件、不定义父到子的权限格、不在创建时冻结授权、也不保证子级不能做超出父级的事。
@@ -146,6 +148,8 @@ agent 作用域组合的是受信的同进程注册。它不沙箱化插件、
需要非升权保证的部署需要独立的权限表示、传播规则和执行检查。父级子集授权、创建时授权快照、显式未来授权 API,以及通用的能力/输出/终止标签均不在本决策范围内。
+
+
## 曾考虑的替代方案
被否决的设计要么将可见性与清理分离,要么只覆盖一类注册,要么重复共享基础设施,要么将生命周期所有权与继承混为一谈。
diff --git a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml
index 5f9f8ba421..f1135aa2b3 100644
--- a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-08-tool-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/implemented/architecture/2026-07-08-tool-output-spill-files.md
-2026-07-08-tool-output-spill-files.md: 4d1d4b7b665f34b362df2f8c8aeb06d96bf2668f
-2026-07-08-tool-output-spill-files.zh.md: 1a3387830861c6d05318024870325523b8eeee36
+2026-07-08-tool-output-spill-files.md: 915e22f1245adb6f7cfc7d358e9d5802531bab63
+2026-07-08-tool-output-spill-files.zh.md: 8d08b05483a302f4188506531da6f507931bea9c
diff --git a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md
index 4d1d4b7b66..915e22f124 100644
--- a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md
+++ b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.md
@@ -35,7 +35,7 @@ interface SpillStore {
interface SpillSource {
toolName: string
- callId: CallId
+ callId: ToolCallId
label: string
}
@@ -57,7 +57,7 @@ interface SpillRef {
`SpillLocator` is a [branded](../../../../packages/util/brand) model-facing handle returned by the backend. The local backend renders it as a filesystem path; a remote or database backend can render a URI, key, or command token. Consumers treat it as opaque and render it with `retrievalHint` instead of assuming `read` is always the right retrieval mechanism. `SpillOwner.sessionId` is the save-time storage namespace: forked sessions inherit existing spill locators from the seeded log without copying or re-owning them, and new spills after the fork use the child session id. A retention-period cleanup may expire old locators with other old session artifacts; the spill seam does not define a per-session cleanup policy.
-`dsh-spill-local` owns only storage details: session-scoped directory selection, safe names, path-traversal protection, the write, and returning `{ locator, bytes, retrievalHint }`. It does not own retention policy, tool-result replacement, search, or file inspection. Files land at `/session-/-`, where `root` is a configured path or a lazily-created private (0700) per-process temp dir, the session subdir is a short `sha256(sessionId)` prefix, and the leaf is a random hex prefix plus the caller's `suggestedName` sanitized to one path segment (mirrors the JSONL backend's `encodeSegment`). The write is `open(path, 'wx', 0o600)` — exclusive and owner-only, so a planted symlink cannot redirect it. The locator is the path, and the retrieval hint tells the model it can use `read` or `grep` on that path.
+`dsh-spill-local` owns storage details: session-scoped directory selection, safe names, path-traversal protection, the write, local artifact lifetime, and returning `{ locator, bytes, retrievalHint }`. It does not own tool-result replacement, model-facing preview policy, search, file inspection, or a seam-wide/per-session retention policy. Files land at `/session-/-`, where `root` is a configured path or a lazily-created private (0700) per-process temp dir, the session subdir is a short `sha256(sessionId)` prefix, and the leaf is a random hex prefix plus the caller's `suggestedName` sanitized to one path segment (mirrors the JSONL backend's `encodeSegment`). The write is `open(path, 'wx', 0o600)` — exclusive and owner-only, so a planted symlink cannot redirect it. The locator is the path, and the retrieval hint tells the model it can use `read` or `grep` on that path. Its one-shot startup cleanup applies the backend-specific artifact lifetime described in the [local spill cleanup note](./2026-07-17-local-spill-startup-cleanup.md).
### Spill policy
@@ -147,8 +147,8 @@ Those cases can consume `ctx.spillStore` directly in later work. They are not pa
## Non-goals
-- No new model-facing `artifact_read` or `artifact_search` tool in v1.
-- No per-tool retention configuration in v1.
+- This decision adds no model-facing `artifact_read` or `artifact_search` tool.
+- This decision adds no per-tool retention configuration.
- No model-facing timeout/truncation arguments.
- No migration of `read` output into spill files.
- No replacement for provider/resource caps such as `web-fetch-http.maxBodyChars`.
@@ -160,7 +160,8 @@ Those cases can consume `ctx.spillStore` directly in later work. They are not pa
- Tool-owned spill for subagent rollouts (`await run.result`, read in-process child session before `run.dispose()`, save JSONL).
- Per-tool opt-out or per-tool policy declarations if the built-in `read` skip is insufficient.
- Remote or database storage backends for ACP or remote environments where a local path is not meaningful.
-- Cleanup and retention policy for old spill files, likely tied to session cleanup.
+
+Cleanup shipped for the local backend as a one-shot startup sweep, not tied to session deletion — see the [startup-cleanup Agent Note](./2026-07-17-local-spill-startup-cleanup.md). The seam still defines no per-session cleanup policy; retention is a backend concern.
## Testing
@@ -174,9 +175,9 @@ Those cases can consume `ctx.spillStore` directly in later work. They are not pa
The default policy only sees final formatted text. It cannot preserve provider-internal content that was already capped or runtime artifacts that were never part of the result. This is acceptable for the first cut because the showcase is final-result spill, not early spill; tool-owned early spill remains deferred work.
-Returning real paths from the local backend keeps v1 simple and matches proven agent-tool behavior, while the seam itself only promises an opaque locator plus retrieval hint so remote backends can return non-file locators.
+Returning real paths keeps the local backend simple and matches proven agent-tool behavior, while the seam itself only promises an opaque locator plus retrieval hint so remote backends can return non-file locators.
-The local-backend value proposition depends on the existing `read`/`grep` tools being able to inspect the returned local path, even when the spill directory is outside the session cwd. That holds today because the filesystem policy records observations and write guards but does not confine reads to the workspace. A future workspace-confinement policy must either allow local spill paths explicitly or use a non-file spill backend whose retrieval hint points at a supported reader.
+The local-backend value proposition depends on the existing `read`/`grep` tools being able to inspect the returned local path, even when the spill directory is outside the session cwd. That holds because the filesystem policy records observations and write guards but does not confine reads to the workspace. A future workspace-confinement policy must either allow local spill paths explicitly or use a non-file spill backend whose retrieval hint points at a supported reader.
**Snapshot gap.** No ACP snapshot scenario covers the transcript-visible `web_fetch` spill notice yet. The ACP snapshot harness replays keyless and cannot hit the live web, and a `web_fetch` spill requires a real over-cap HTTP body; a deterministic scenario would need a seeded loopback fetch target the replay tree does not currently wire (the examples do not load `tool-web` at all). The behavior is covered instead by the `dsh-tool-web` integration test against a loopback server. Closing the gap is follow-up work: wire `tool-web` + a seeded fetch target into the ACP example, then record a `web-fetch-spill` scenario.
@@ -184,7 +185,7 @@ The policy can become too large if it starts owning tool-specific semantics. It
## Alternatives considered
-**Require each tool to opt in with a retention declaration.** Rejected for v1: the goal is a default behavior similar to Claude Code's generic tool-result persistence. A single `maxInlineBytes` deployment knob is enough to prove the shape.
+**Require each tool to opt in with a retention declaration.** Rejected: the goal is a default behavior similar to Claude Code's generic tool-result persistence. A single `maxInlineBytes` deployment knob is enough to prove the shape.
**Make `tool-results` a broad tool-result platform.** Rejected: a broad package name invites retention policy, result replacement, preview wording, search, and early spill into one seam. The shared storage part is smaller: save text and return a locator plus retrieval hint.
diff --git a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md
index 1a33878308..8d08b05483 100644
--- a/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-08-tool-output-spill-files.zh.md
@@ -8,9 +8,9 @@ Status: implemented
工具输出需要有界的模型可见预览,但部分超大结果仍可能在之后有用。抓取的页面正文或冗长的工具响应不应完整占用下一次模型请求,但模型应能使用现有文件读取工具,在之后查看经过格式化的完整结果。
-这项改动之前的行为并不一致。`dsh-bash-local` 已经会在内存尾部溢出时,把完整 stdout/stderr 流写入私有的临时 spill 文件;普通文本工具结果则仍以内联形式返回,除非工具自行实现上限。[工具结果保留库](2026-07-06-tool-result-retention-library.md)负责预览机制,但不负责存储,也不负责把这些机制应用于最终工具结果的执行流水线策略。
+这项改动之前的行为并不一致。`dsh-bash-local` 已经会在内存尾部溢出时,把完整 stdout/stderr 流写入私有的临时 spill 文件;普通文本工具结果则仍以内联形式返回,除非工具自行实现上限。[工具结果保留库](2026-07-06-tool-result-retention-library.zh.md)负责预览机制,但不负责存储,也不负责把这些机制应用于最终工具结果的执行流水线策略。
-其形态与超时策略设计一致:工具作者声明规范值与 Native renderer(原生渲染器),由策略插件在渲染后的内容上执行部署默认的上下文预算。工具仍可在提供方采集上限处提前 spill;由工具负责的展示 spill 可以保留已完整采集的规范值,而只替换展示内容。[规范工具输出约定](2026-07-20-canonical-tool-output-contract.md)规定了这项区分。
+其形态与超时策略设计一致:工具作者声明规范值与 Native renderer(原生渲染器),由策略插件在渲染后的内容上执行部署默认的上下文预算。工具仍可在提供方采集上限处提前 spill;由工具负责的展示 spill 可以保留已完整采集的规范值,而只替换展示内容。[规范工具输出约定](2026-07-20-canonical-tool-output-contract.zh.md)规定了这项区分。
## 决策
@@ -35,7 +35,7 @@ interface SpillStore {
interface SpillSource {
toolName: string
- callId: CallId
+ callId: ToolCallId
label: string
}
@@ -57,7 +57,7 @@ interface SpillRef {
`SpillLocator` 是一个[品牌化的](../../../../packages/util/brand)模型可见句柄,由后端返回。本地后端将其渲染为文件系统路径;远程或数据库后端可以渲染 URI、键或命令 token。消费方把它视为不透明值,并使用 `retrievalHint` 渲染,而不是假定 `read` 始终是正确的检索机制。`SpillOwner.sessionId` 是保存时的存储命名空间:fork 后的会话会从种子日志继承已有的 spill 定位符,无需复制它们或重新取得所有权;fork 后的新 spill 使用子会话 id。保留期清理可以连同其他旧会话产物一起使旧定位符失效;spill seam 不定义逐会话的清理策略。
-`dsh-spill-local` 只负责存储细节:选择会话作用域的目录、安全名称、防止路径遍历、执行写入,以及返回 `{ locator, bytes, retrievalHint }`。它不负责保留策略、工具结果替换、搜索或文件检查。文件写入 `/session-/-`:`root` 是配置路径,或延迟创建的私有(0700)进程级临时目录;会话子目录是 `sha256(sessionId)` 的短前缀;叶节点由随机十六进制前缀与调用方的 `suggestedName` 组成,后者会被清理成单一路径段(与 JSONL 后端的 `encodeSegment` 一致)。系统使用 `open(path, 'wx', 0o600)` 写入,确保独占且仅所有者可访问,因此预先植入的符号链接无法重定向写入。定位符就是该路径,检索提示则告知模型可以在该路径上使用 `read` 或 `grep`。
+`dsh-spill-local` 负责存储细节:选择会话作用域的目录、安全名称、防止路径遍历、执行写入、本地产物生命周期,以及返回 `{ locator, bytes, retrievalHint }`。它不负责工具结果替换、模型可见的预览策略、搜索、文件检查,也不定义 seam 级或逐会话保留策略。文件写入 `/session-/-`:`root` 是配置路径,或延迟创建的私有(0700)进程级临时目录;会话子目录是 `sha256(sessionId)` 的短前缀;叶节点由随机十六进制前缀与调用方的 `suggestedName` 组成,后者会被清理成单一路径段(与 JSONL 后端的 `encodeSegment` 一致)。系统使用 `open(path, 'wx', 0o600)` 写入,确保独占且仅所有者可访问,因此预先植入的符号链接无法重定向写入。定位符就是该路径,检索提示则告知模型可以在该路径上使用 `read` 或 `grep`。它的一次性启动清理会应用[本地 spill 清理说明](./2026-07-17-local-spill-startup-cleanup.zh.md)所述的后端专属产物生命周期。
### spill 策略
@@ -147,8 +147,8 @@ ctx.tools.register(defineTool({
## 非目标
-- v1 不增加面向模型的 `artifact_read` 或 `artifact_search` 工具。
-- v1 不增加逐工具的保留配置。
+- 本决策不增加面向模型的 `artifact_read` 或 `artifact_search` 工具。
+- 本决策不增加逐工具的保留配置。
- 不增加面向模型的超时/截断参数。
- 不把 `read` 输出迁移到 spill 文件。
- 不取代 `web-fetch-http.maxBodyChars` 等提供方/资源上限。
@@ -160,7 +160,8 @@ ctx.tools.register(defineTool({
- 由工具负责的 subagent 执行轨迹 spill(`await run.result`,在 `run.dispose()` 前读取进程内子会话,保存 JSONL)。
- 如果内置的 `read` 跳过规则不足,再增加逐工具选择退出或逐工具策略声明。
- 面向 ACP(Agent Client Protocol)或远程环境的远程/数据库存储后端,因为本地路径在这些环境中没有意义。
-- 旧 spill 文件的清理和保留策略,很可能与会话清理绑定。
+
+本地后端通过一次性启动扫描清理旧文件,而不是绑定到会话删除——参见[启动清理 Agent Note](./2026-07-17-local-spill-startup-cleanup.zh.md)。seam 仍未定义逐会话清理策略;保留策略属于后端。
## 测试
@@ -174,9 +175,9 @@ ctx.tools.register(defineTool({
默认策略只能看见最终格式化文本。它无法保留已经由提供方限制的内部内容,也无法保留从未成为结果一部分的运行时产物。第一版聚焦最终结果 spill 而不是提前 spill,因此可以接受这一限制;由工具负责的提前 spill 仍属于后续工作。
-本地后端返回真实路径,使 v1 保持简单并符合已经验证的 agent(智能体)工具行为;seam 本身只承诺一个不透明定位符加检索提示,所以远程后端可以返回非文件定位符。
+本地后端返回真实路径,使其保持简单并符合已经验证的 agent(智能体)工具行为;seam 本身只承诺一个不透明定位符加检索提示,所以远程后端可以返回非文件定位符。
-本地后端的价值取决于现有 `read`/`grep` 工具能否检查返回的本地路径,即使 spill 目录位于会话 cwd 之外。目前这一条件成立,因为文件系统策略会记录观察结果并设置写保护,但不会把读取限制在工作区内。未来的工作区限制策略必须显式允许本地 spill 路径,或改用检索提示指向受支持读取器的非文件 spill 后端。
+本地后端的价值取决于现有 `read`/`grep` 工具能否检查返回的本地路径,即使 spill 目录位于会话 cwd 之外。这一条件成立,因为文件系统策略会记录观察结果并设置写保护,但不会把读取限制在工作区内。未来的工作区限制策略必须显式允许本地 spill 路径,或改用检索提示指向受支持读取器的非文件 spill 后端。
**快照缺口。** 目前没有 ACP 快照场景覆盖 transcript(文本记录)可见的 `web_fetch` spill 提示。ACP 快照 harness 在无密钥环境中回放,无法访问实时 web,而 `web_fetch` spill 需要一个真实的超上限 HTTP 正文;确定性场景需要一个预置的 loopback fetch 目标,但当前回放树尚未接线(示例根本没有加载 `tool-web`)。该行为改由 `dsh-tool-web` 针对 loopback server 的集成测试覆盖。弥补该缺口属于后续工作:把 `tool-web` 和预置 fetch 目标接入 ACP 示例,然后录制 `web-fetch-spill` 场景。
@@ -184,7 +185,7 @@ ctx.tools.register(defineTool({
## 考虑过的替代方案
-**要求每个工具通过保留声明选择加入。** v1 不予采纳,因为目标是实现类似 Claude Code 通用工具结果持久化的默认行为。只需一个 `maxInlineBytes` 部署配置项即可验证该形态。
+**要求每个工具通过保留声明选择加入。**不予采纳,因为目标是实现类似 Claude Code 通用工具结果持久化的默认行为。只需一个 `maxInlineBytes` 部署配置项即可验证该形态。
**把 `tool-results` 建成宽泛的工具结果平台。** 不予采纳:宽泛的包名会诱使系统把保留策略、结果替换、预览措辞、搜索和提前 spill 合并进一个 seam。可共享的存储部分更小:保存文本,并返回定位符与检索提示。
diff --git a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml
index 0321d494a0..ec2f5318d6 100644
--- a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md
2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 89c8917484c11057ff2e6b55e2311e83f724f7ed
-2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 96f7aa1b0ea4e44ca6318caca2c785d898b1d00d
+2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 48f954f2c4720894548ecab387965d3a3d1799b0
diff --git a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md
index 96f7aa1b0e..48f954f2c4 100644
--- a/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md
@@ -22,9 +22,9 @@ Compact-basic 会在每个拟议请求之前包装 `agent/pre-step`。在续步
### 请求恢复只覆盖最终模型边界
-`agent/request-error` 表示来自最终适配器边界的终止失败。适配器选择、分发、iterator 构造与迭代抛出会在 agent loop(智能体循环)消费前成为终止 `error` 或 `aborted` finish;适配器直接发出的终止 finish 进入同一路径。提示词装配、请求 middleware、请求日志、结果处理、工具、step 监听器与清理仍属于普通失败。[LLM(大语言模型)流的终止失败](2026-07-29-terminal-llm-stream-failures.md)规定这一规范化边界。
+`agent/request-error` 表示来自最终适配器边界的终止失败。适配器选择、分发、iterator 构造与迭代抛出会在 agent loop(智能体循环)消费前成为终止 `error` 或 `aborted` finish;适配器直接发出的终止 finish 进入同一路径。提示词装配、请求 middleware、请求日志、结果处理、工具、step 监听器与清理仍属于普通失败。[LLM(大语言模型)流的终止失败](2026-07-29-terminal-llm-stream-failures.zh.md)规定这一规范化边界。
-恢复运行前,失败 step 已经关闭。负责处理的监听器修复持久状态、返回 `{ kind: 'retry' }`,并停止 waterfall(瀑布式事件)委托。循环随后关闭失败 turn,并从持久日志开启一个重试 turn,中间不发布空闲通知。重试策略与尝试计数由插件自己拥有;compaction-basic 在链路到达终态 `agent/settled` 时清除对应 agent 的溢出计数。两个 DeepSeek 适配器都把识别出的提供方上下文限制错误规范化为 `CONTEXT_WINDOW_EXCEEDED`。[重试动作决策](../simplification/2026-07-27-request-error-retry-action.md)规定这一返回边界。
+恢复运行前,失败 step 已经关闭。负责处理的监听器修复持久状态、返回 `{ kind: 'retry' }`,并停止 waterfall(瀑布式事件)委托。循环随后关闭失败 turn,并从持久日志开启一个重试 turn,中间不发布空闲通知。重试策略与尝试计数由插件自己拥有;compaction-basic 在链路到达终态 `agent/settled` 时清除对应 agent 的溢出计数。两个 DeepSeek 适配器都把识别出的提供方上下文限制错误规范化为 `CONTEXT_WINDOW_EXCEEDED`。[重试动作决策](../simplification/2026-07-27-request-error-retry-action.zh.md)规定这一返回边界。
如果取消发生在 assistant 工具调用已经持久化之后、所有调用完成分发之前,循环会为每个尚未分发的调用记录一对合成的 `tool/call` 与 aborted `tool/result`,随后进入正常中止路径。因此,表层不会仅因取消赢得竞态而留下孤立的持久工具调用。
@@ -58,4 +58,4 @@ Compact-basic 会在每个拟议请求之前包装 `agent/pre-step`。在续步
代价是在共享 pre-step waterfall 中执行压力工作,并需要适配器持续维护溢出分类。提供方措辞与启发式字符密度仍是维护风险。表层压缩依然无法修复仅信封本身就超出窗口的情况,也不能拆分不可分割的非工具节点,或修复不可剪枝的剩余部分仍然过大的工具单元。若可移除的文本工具结果是主要体积,可选剪枝器仍可修复原本不可分割的工具配对。
-[已领取 pre-step 生命周期](2026-07-31-claimed-pre-step-inbox-lifecycle.md)取代了本记录原先的 post-step 触发方式。服务拆分、独立 token meter、平衡范围约定、日志中记录的锁、摘要替换与唯一 `summarize()` 子类 hook 均保持不变。
+[已领取 pre-step 生命周期](2026-07-31-claimed-pre-step-inbox-lifecycle.zh.md)取代了本记录原先的 post-step 触发方式。服务拆分、独立 token meter、平衡范围约定、日志中记录的锁、摘要替换与唯一 `summarize()` 子类 hook 均保持不变。
diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml
index 21c607072c..83638635ad 100644
--- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.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/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md
-2026-07-10-single-file-executable-sdk-runtime-distribution.md: 40433d99e5d1aa569c3fdf094a280d3de62ad588
-2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: 54030fa4b0742fbc282bc327b0ca22747e6a20bd
+2026-07-10-single-file-executable-sdk-runtime-distribution.md: c152345772826ec4e2dbfd238726c429418c7897
+2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: ea5e457afd761cb5071f8b584ef10fa7ffaa8210
diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md
index 40433d99e5..c152345772 100644
--- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md
+++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md
@@ -23,40 +23,40 @@ The exe is packaged with the **`--sea` (enhanced SEA) mode** of [@yao-pkg/pkg](h
Terminology reminder: pkg's `/snapshot` VFS has nothing to do with this repo's testing-system "snapshot" (ACP replay expected outputs, `$DSH_SNAPSHOT`); this document says "VFS" for the former.
-### The serving interface is a plugin: the two packages sdk/server + examples/jsonrpc-demo
+### The serving interface is a plugin inside the dsh application
-The deterministic protocol implementation (`server.ts` / `transport.ts`) lands as two packages on the existing `acp/acp` + `examples/acp-demo` pattern — the serving surface is itself a plugin:
+The deterministic serving surface is a plugin selected by the packaged `dsh` application:
- [`packages/sdk/server`](../../../../packages/sdk/server/README.md) (`@deepseek-ai/dsh-sdk-jsonrpc-server`): the pure protocol plugin; on apply it mounts `HarnessSdkJsonRpcServer` plus a line-delimited JSON-RPC transport on the process stdio, with disposal through `ctx.effect()`. Whether to serve is decided by `cordis.yml`; a yml that does not mount it is a legitimate process that does not serve. Protocol-level exit belongs to the plugin (after answering and flushing the `shutdown` response it disposes the root runtime so persistence drains, then `exit(0)`; an HMR-style unload only stops the service without exiting the process).
-- [`packages/examples/jsonrpc-demo`](../../../../packages/examples/jsonrpc-demo/README.md) (`@deepseek-ai/dsh-sdk-jsonrpc-demo`): a thin app bin — `installFailLoud` + `loadEnv` + config discovery + `boot()` from [`dsh-app-boot`](../../../../packages/boot/app-boot/src/index.ts), done once boot completes; the server is brought up by the `dsh-sdk-jsonrpc-server` entry in the yml. Its only dependency is app-boot. Process-level exit belongs to the bin (stdin EOF/SIGTERM → dispose then 0, SIGINT → 130).
+- [`apps/cli`](../../../../apps/cli/README.md) (`@deepseek-ai/dsh`): the packaged application entry; its `sdk` profile mounts `dsh-sdk-jsonrpc-server`, and the CLI owns environment layering, profile composition, stdin/signal shutdown, and process exit.
-Config discovery has two channels and fails loudly when both are missing: the `DSH_CORDIS_CONFIG` environment variable first (the SDK client convention), then an argv positional argument; no default path and no built-in fallback whatsoever — "the plugins actually booted are decided by an external cordis.yml" is a hard semantic.
+The Python client supplies an explicit Harness home and selects the `sdk` profile plus ordered patch files. A missing home, profile, bundle, or server row fails loudly; there is no external complete-config fallback. The [Python profile-runtime decision](2026-08-23-python-sdk-dsh-profile-runtime.md) owns this application surface.
### Plugin resolution: the VFS holds a real package tree, the closure manifest IS the deploy root
Inside the exe's VFS sits a **real package tree in build-artifact form** (each package's `lib/` plus a real `node_modules`). The packaged JSON-RPC entry supplies its installed harness base to app-boot's root Include: relative plugin specifiers resolve from the external configuration directory, while bare package names resolve from the VFS, so a configuration inside another Node project cannot shadow the packaged plugin set. The ordinary development bin leaves bare packages configuration-owned. Bare specifiers in the packaged entry resolve upward along `node_modules` from the entry's position inside the VFS and land inside the VFS naturally. The closed set needs no allowlist code — the set is whatever the VFS has installed, and importing a name outside the set fails.
-The deploy root is [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json) (`dsh-jsonrpc-agent-pkg`, a pnpm workspace member and a zero-code pure dependency manifest) — the unified source of truth for "which plugins the exe ships" and "what the Python runtime distributes". Adding a plugin to the exe = adding one dependency line to the manifest and repackaging. [`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) reads every shipped `apps/cli/config/agent-presets/*/agent.cordis.yml`, evaluates `disabled` conditions that compare `process.platform` for every target in `python/sdk-runtime/platforms.json`, and requires each active workspace plugin at the runtime root through an explicit `workspace:` dependency. It also traverses every workspace package covered by that manifest and requires every non-optional workspace peer, reporting the complete preset or referencing-package → missing-dependency chain; unknown platform conditions remain active so a plugin cannot be omitted by an unsupported expression. `pnpm run hygiene`, CI static, and the single-exe build run it before packaging. Deploy also packs by each package's `files`, so the shared chunks tsdown splits out must be covered by `files`.
+The deploy root is [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json) (`dsh-python-runtime-closure`, a pnpm workspace member and a zero-code pure dependency manifest) — the unified source of truth for "which plugins the exe ships" and "what the Python runtime distributes". Adding a plugin to the exe = adding one dependency line to the manifest and repackaging. [`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) reads every shipped `packages/preset/agent-presets/presets/*/agent.cordis.yml`, evaluates `disabled` conditions that compare `process.platform` for every target in `python/sdk-runtime/platforms.json`, and requires each active workspace plugin at the runtime root through an explicit `workspace:` dependency. It also traverses every workspace package covered by that manifest and requires every non-optional workspace peer, reporting the complete preset or referencing-package → missing-dependency chain; unknown platform conditions remain active so a plugin cannot be omitted by an unsupported expression. `pnpm run hygiene`, CI static, and the single-exe build run it before packaging. Deploy also packs by each package's `files`, so the shared chunks tsdown splits out must be covered by `files`.
The deploy root includes `@deepseek-ai/dsh-mcp-client` as an explicitly supported custom-configuration plugin even though no shipped preset mounts it. An external config can therefore connect to user-supplied stdio and Streamable HTTP MCP servers and register their tools; the distribution does not carry those servers or extend the bridge to MCP Resources and Prompts. The executable and installed-wheel smokes start a temporary stdio server, discover its tool, and complete one model-requested call.
### Build pipeline and artifacts
-[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts): runtime closure verification → `pnpm run build` → (after clearing) `pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **directly into** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → restore any direct workspace package that legacy deploy hoisted back under the source manifest's `node_modules`, omitting its package-local dependency tree and rejecting any remaining manifest gap → replace every staged dependency symlink with its target bytes, remove package-manager `.bin` links, and fail if any symlink remains → inject the pkg configuration (`bin` points at `node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js` inside the closure, `assets` is a full glob — dynamic import is invisible to pkg's static analysis, so everything must be packed in explicitly) → stage the target `node-pty` addon → one `pkg --sea` per target → the executables `dsh-jsonrpc-agent-pkg--` land in `dist-exe/` and are copied back into the runtime directory. Linux installs build `pty.node` from source; CI rebuilds that addon inside the matching manylinux 2.28 container before packaging, and the builder copies it from the root install into the staged closure because legacy deploy omits that side-effect directory. Every target copies its native `@vscode/ripgrep` binary beside the executable as the required `-rg` sidecar; pkg runtimes select that sidecar through `process.pkg`, while ordinary Node execution uses `@vscode/ripgrep` directly. macOS uses its target prebuild and also emits the required `-spawn-helper`. CI treats these products as intermediate test inputs and retains their platform wheels. All four deploy flags are grounded in measurement: `--legacy` is the mandatory path with inject-workspace-packages off; hoisted gives pkg a stable single-instance layout that the explicit materialization pass makes symlink-free; disabling automatic peer installation prevents undeclared peers from expanding the closure; link-workspace-packages selects direct workspace dependencies. [`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) overrides the transitive `@deepseek-ai/cosmokit` and `@deepseek-ai/schemastery` semver requests to the pinned vendor sources so legacy deploy never resolves those unpublished names from a registry.
+[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts): runtime closure verification → `pnpm run build` → (after clearing) `pnpm --filter dsh-python-runtime-closure deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **directly into** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → restore direct workspace packages omitted by legacy deploy and reject any remaining manifest gap → replace staged dependency symlinks with their target bytes, remove package-manager `.bin` links, and fail if any symlink remains → inject pkg configuration whose bin is `node_modules/@deepseek-ai/dsh/lib/bin.js` and whose assets cover dynamic profile, bundle, frontend, preset, native-library, and configuration reads → stage the target `node-pty` addon → invoke `pkg --sea` once per target → write `deepseek-harness-sdk-runtime--` under `dist-exe/` and copy it into the runtime directory. Linux CI rebuilds `pty.node` inside the matching manylinux 2.28 container because legacy deploy omits that install side effect. Every target copies its native `@vscode/ripgrep` binary beside the executable as the required `-rg` sidecar; pkg runtimes select that sidecar through `process.pkg`, while ordinary Node execution uses `@vscode/ripgrep` directly. macOS uses its target prebuild and also emits the required `-spawn-helper`. All four deploy flags are grounded in measurement: `--legacy` is the mandatory path with inject-workspace-packages off; hoisted gives pkg a stable single-instance layout that the explicit materialization pass makes symlink-free; disabling automatic peer installation prevents undeclared peers from expanding the closure; link-workspace-packages selects direct workspace dependencies. [`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) overrides the transitive `@deepseek-ai/cosmokit` and `@deepseek-ai/schemastery` semver requests to the pinned vendor sources so legacy deploy never resolves those unpublished names from a registry.
-CI: [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml), called for linux-x64 by the [required Python runtime pull-request validation](../testing/2026-08-12-required-python-runtime-pull-request-ci.md), triggered explicitly by `workflow_dispatch` or the `build-exe` label for selected targets, and called for all targets by the [public publication workflow](../process/2026-08-11-python-publication-workflow.md). Native builds run on linux-x64 / linux-arm64 (`ubuntu-24.04-arm`) / macos-arm64, with `~/.pkg-cache` cached, and pkg handles macOS ad-hoc signing. Each leg drives a mock SSE model through the SDK with the default config and a custom `cordis.yml`, drives the exe directly over NDJSON JSON-RPC, verifies the JSONL and final response, and installs release-shaped wheels into a clean venv without `runtime_bin`; Linux additionally inspects both the executable and native addon's GLIBC requirements and runs in a manylinux 2.28 container, while macOS verifies that the executable's deployment target fits the wheel tag. A full three-target run retains four artifacts, each containing one release file: the platform-independent SDK wheel and three native runtime wheels; a subset dispatch retains the SDK wheel and selected runtime wheels. Bare executables and source bundles remain intermediate test inputs. [`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) accepts `python-v` tag pipelines whose version matches the root `package.json`, builds one SDK wheel and three native runtime wheels, then a single serialized job checks and publishes all four to the project PyPI registry. Windows is a non-goal.
+CI: [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml) is called for all four targets by the [installed-wheel Python runtime pull-request validation](../testing/2026-08-23-installed-python-wheel-black-box-ci.md) and the [public publication workflow](../process/2026-08-11-python-publication-workflow.md); `workflow_dispatch` can still select a subset. Native builds run on linux-x64 / linux-arm64 (`ubuntu-24.04-arm`) / macos-arm64 / win-x64 (`windows-2025`), with `~/.pkg-cache` cached where applicable, and pkg handles macOS ad-hoc signing. Each leg installs the release-shaped SDK and runtime wheels into a clean venv outside the checkout, proves their package and executable provenance, then drives the complete keyless scenario set through the public SDK and direct NDJSON JSON-RPC. Trusted pull requests additionally run a real DeepSeek two-turn tool smoke on every target; fork and Dependabot heads receive no key. Linux inspects the executable and native addon's GLIBC requirements and runs an additional manylinux 2.28 smoke, while macOS verifies that the executable's deployment target fits the wheel tag. A full four-target run retains five artifacts, each containing one release file: the platform-independent SDK wheel and four native runtime wheels; a subset dispatch retains the SDK wheel and selected runtime wheels. Bare executables and source bundles remain intermediate test inputs. [`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) accepts `python-v` tag pipelines whose version matches the root `package.json`, builds one SDK wheel and four native runtime wheels, then a single serialized job checks and publishes all five to the project PyPI registry. The [Windows x64 runtime decision](2026-08-23-python-sdk-windows-x64-runtime.md) owns the fourth target and the explicit exclusion of Windows arm64.
### Python SDK distribution: two carriers, exe for production, node for development
-The Python SDK lives at [`python/`](../../../../python/README.md): `python/sdk` (the client) + `python/sdk-runtime` (the runtime carrier package). The runtime package's data directory holds the checked-in default `runtime/cordis.yml`, the build-injected platform exe with its required `-rg` sidecar and optional macOS helper, and the build-injected `runtime/node/` closure tree. `resolve_bundled_launch_args()` automatic resolution **finds the exe only**; the node carrier is enabled only by an explicit `DSH_RUNTIME_MODE=node` (running `runtime/node/node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js`, requiring a system node ≥22.19), positioned as the development-verification channel for members of this repo, and does not enter wheel distributions.
+The Python SDK lives at [`python/`](../../../../python/README.md): `python/sdk` is the client and `python/sdk-runtime` is the runtime carrier package. The runtime package's data directory holds the build-injected platform executable with its required `-rg` sidecar and optional macOS helper, plus the build-injected `runtime/node/` closure tree for repository development. `resolve_bundled_launch_args()` selects the executable by default; explicit `DSH_RUNTIME_MODE=node` runs `runtime/node/node_modules/@deepseek-ai/dsh/lib/bin.js` on system Node 22.19 or newer. The node carrier never enters wheel distributions, and neither carrier uses a checked-in complete `cordis.yml`.
-[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) reads the authoritative `X.Y.Z` or prerelease version from the repository root `package.json`, converts prereleases to their PEP 440 spelling, and stages both packages at that wheel version, with `deepseek-harness-sdk` depending exactly on the matching `deepseek-harness-runtime-bin`. An optional `python-v` release tag is a consistency assertion and is rejected when it differs from the repository version; the source `pyproject.toml` development sentinel never determines a release version. Staging also carries the repository license into both wheels and the third-party notices into the bundled runtime wheel. The SDK is a `py3-none-any` wheel; each wheel-only runtime package contains one exe and its architecture-matched `-rg` sidecar, and the macOS wheel also contains its architecture-matched spawn helper. Runtime wheels use one of `py3-none-manylinux_2_28_x86_64`, `py3-none-manylinux_2_28_aarch64`, or the conservative `py3-none-macosx_14_0_arm64` tag for the Node 24 executable's macOS 13.5 deployment target; the Hatch hook rejects sdists, universal tags, mixed-platform payloads, missing or extra sidecars, and unsupported platforms.
+[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) reads the authoritative `X.Y.Z` or prerelease version from the repository root `package.json`, converts prereleases to their PEP 440 spelling, and stages both packages at that wheel version, with `deepseek-harness-sdk` depending exactly on the matching `deepseek-harness-runtime-bin`. An optional `python-v` release tag is a consistency assertion and is rejected when it differs from the repository version; the source `pyproject.toml` development sentinel never determines a release version. Staging also carries the repository license into both wheels and the third-party notices into the bundled runtime wheel. The SDK is a `py3-none-any` wheel; each wheel-only runtime package contains one exe and its architecture-matched ripgrep sidecar, and the macOS wheel also contains its architecture-matched spawn helper. Runtime wheels use `py3-none-manylinux_2_28_x86_64`, `py3-none-manylinux_2_28_aarch64`, the conservative `py3-none-macosx_14_0_arm64` tag for the Node 24 executable's macOS 13.5 deployment target, or `py3-none-win_amd64`; the Hatch hook rejects sdists, universal tags, mixed-platform payloads, missing or extra sidecars, and unsupported platforms.
-The exe's "must be explicitly configured" hard semantic is unchanged; the zero-config experience is restored by the wrapper: when the caller gave no `cordis`, named no explicit runtime, and the environment has no `DSH_CORDIS_CONFIG`, the client explicitly injects the checked-in default `cordis.yml` (agent-core + preloaded llm-deepseek + JSONL persistence + bash-local + the `dsh-sdk-jsonrpc-server` serving entry, with `!!js` environment-variable fallbacks) via `DSH_CORDIS_CONFIG`.
+The Python client launches the packaged `dsh` command with the selected profile (`sdk` by default), ordered patch files, and an explicit Harness home. The profile owns JSON-RPC serving and application composition; missing homes, profiles, bundles, patches, and server rows fail without an external complete-config fallback.
### Naming lineage
-`@deepseek-ai/dsh-sdk-jsonrpc-demo` (the package) → `dsh-jsonrpc-agent` (the bin) → `dsh-jsonrpc-agent-pkg` (the closure manifest; no scope prefix, deliberately sidestepping the constraints' package-shape rules for `@deepseek-ai/dsh-*`) → `dsh-jsonrpc-agent-pkg--` (the exe artifacts). The wire `serverInfo.name` stays `deepseek-harness-sdk-runtime` (a protocol-stable value); the Python distribution names are `deepseek-harness-sdk` / `deepseek-harness-runtime-bin`, while the import modules remain `deepseek_harness` / `deepseek_harness_runtime`.
+`dsh-python-runtime-closure` is the private deploy manifest and `deepseek-harness-sdk-runtime--` is the executable family. The wire `serverInfo.name` is `deepseek-harness-sdk-runtime`; the Python distribution names are `deepseek-harness-sdk` / `deepseek-harness-runtime-bin`, while the import modules are `deepseek_harness` / `deepseek_harness_runtime`.
## Disposition of worker-style plugins
@@ -64,7 +64,7 @@ The exe's "must be explicitly configured" hard semantic is unchanged; the zero-c
## Testing
-The verification surface has three tiers. Mechanism tier: the measured conclusions for the `--sea` chain are embedded in the Decision sections (ESM dynamic import inside the VFS, single cordis instance, fail-loud config chain, `node:sqlite`, macOS ad-hoc signing runs). SDK tier: the complete keyless pytest suite covers the client protocol against a fake runtime peer, subprocess cleanup, absolute cwd propagation, dual-carrier launch, and carrier resolution; root CI runs it on Python 3.10. End-to-end tier: every platform build completes a turn against a mock endpoint through the default SDK path, a custom config, the checked-in standalone minimal composition, and the direct binary protocol, with final text and JSONL checked. The minimal run asserts its exact system prompt and two-tool catalog, retains Bash state across calls, and invokes the editor. The custom config additionally drives `run_code` and a zero-agent `workflow` through their real worker files inside the packaged VFS. The filesystem-search scenario requires the model to call both `glob` and `grep` through the target-native `-rg` sidecar. The MCP scenario starts a temporary external stdio server, deliberately delays its initial `tools/list` response, then immediately starts the first SDK prompt; the prompt must see and call the discovered tool, proving that `initialize` is a real Loader-settlement readiness boundary rather than a timing sleep. The same build leg runs a committed executable-specific snapshot through the Python SDK: a keyless scripted model mounts a Cordis plugin that registers a tool, invokes that tool from `run_code`, runs a direct spawn subagent and a workflow that starts a second spawn child, then unmounts the plugin. The fixture explicitly disables its unused bundled Bash and local skill discovery so its tool set does not depend on repository-external state, and the comparison normalizes opaque message, agent, workflow-run, and session IDs across the SDK result and notification stream plus the parent and two child JSONL logs. This harness stays separate from ACP's `pnpm run test:snapshot` because the protocols and build artifacts differ. The platform wheel is then installed in a clean venv and run without `runtime_bin`.
+The verification surface has three tiers. Mechanism tier: the measured conclusions for the `--sea` chain are embedded in the Decision sections (ESM dynamic import inside the VFS, single cordis instance, fail-loud config chain, `node:sqlite`, macOS ad-hoc signing runs). SDK tier: the complete keyless pytest suite covers the client protocol against a fake runtime peer, subprocess cleanup, absolute cwd propagation, dual-carrier launch, and carrier resolution; root CI runs it on Python 3.10. End-to-end tier: every platform build installs both wheels into a clean venv outside the checkout, proves matching versions and installed module/executable locations, then completes turns against a mock endpoint through the default SDK path, a custom config, the checked-in standalone minimal composition, and the direct binary protocol, with final text and JSONL checked. The minimal run asserts its exact system prompt and two-tool catalog, retains Bash state across calls, and invokes the editor. The custom config additionally drives `run_code` and a zero-agent `workflow` through their real worker files inside the packaged VFS. The filesystem-search scenario requires the model to call both `glob` and `grep` through the target-native `-rg` sidecar. The MCP scenario starts a temporary external stdio server, deliberately delays its initial `tools/list` response, then immediately starts the first SDK prompt; the prompt must see and call the discovered tool, proving that `initialize` is a real Loader-settlement readiness boundary rather than a timing sleep. The same installed run compares a committed executable-specific snapshot through the Python SDK: a keyless scripted model mounts a Cordis plugin that registers a tool, invokes that tool from `run_code`, runs a direct spawn subagent and a workflow that starts a second spawn child, then unmounts the plugin. The fixture explicitly disables its unused bundled Bash and local skill discovery so its tool set does not depend on repository-external state, and the comparison normalizes opaque message, agent, workflow-run, and session IDs across the SDK result and notification stream plus the parent and two child JSONL logs. Trusted pull requests add a real-provider two-turn file write/read whose external bytes, tool calls, completed reasons, and persisted log must agree. This harness stays separate from ACP's `pnpm run test:snapshot` because the protocols and build artifacts differ.
Manual-driving caveat: the bin treats stdin EOF as "the client is gone" and disposes immediately, so a short-lived pipe aborts an in-flight turn — pipe-driven runs must keep stdin open until the turn ends.
diff --git a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md
index 54030fa4b0..ea5e457afd 100644
--- a/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md
@@ -23,40 +23,40 @@ exe 使用 [@yao-pkg/pkg](https://github.com/yao-pkg/pkg)(vercel/pkg 归档后
术语提醒:pkg 的 `/snapshot` VFS 与本仓库测试体系的「快照」(ACP(Agent Client Protocol)回放预期输出、`$DSH_SNAPSHOT`)无关,本文用「VFS」指前者。
-### 对外服务接口也是插件:sdk/server + examples/jsonrpc-demo 两个包
+### 对外服务接口是 dsh 应用中的插件
-确定性协议实现(`server.ts` / `transport.ts`)按 `acp/acp` + `examples/acp-demo` 的既有模式落为两包——对外服务接口本身也是插件:
+确定性服务接口由打包后的 `dsh` 应用选择为插件:
-- [`packages/sdk/server`](../../../../packages/sdk/server/README.md)(`@deepseek-ai/dsh-sdk-jsonrpc-server`):纯协议插件;执行 `apply` 时,在进程 stdio 上挂载 `HarnessSdkJsonRpcServer` 与按行分隔的 JSON-RPC 传输层,资源释放走 `ctx.effect()`。是否提供服务由 `cordis.yml` 决定;未挂载该插件的配置会启动一个不提供此服务的合法进程。协议级退出归插件所有(应答并确保 `shutdown` 响应发送完毕后,对根运行时执行 dispose(资源释放),让待处理的持久化操作完成,再调用 `exit(0)`;HMR(热模块替换)式卸载只停止服务,不退出进程)。
-- [`packages/examples/jsonrpc-demo`](../../../../packages/examples/jsonrpc-demo/README.md)(`@deepseek-ai/dsh-sdk-jsonrpc-demo`):轻量应用入口——`installFailLoud` + `loadEnv` + 配置发现 + [`dsh-app-boot`](../../../../packages/boot/app-boot/src/index.ts) 的 `boot()`;`boot()` 完成后入口即完成,服务器由 `cordis.yml` 中的 `dsh-sdk-jsonrpc-server` 条目启动。它只依赖 `app-boot`。进程级退出归 `bin` 所有(stdin EOF/SIGTERM → dispose 后返回 0,SIGINT → 130)。
+- [`packages/sdk/server`](../../../../packages/sdk/server/README.zh.md)(`@deepseek-ai/dsh-sdk-jsonrpc-server`):纯协议插件;执行 `apply` 时,在进程 stdio 上挂载 `HarnessSdkJsonRpcServer` 与按行分隔的 JSON-RPC 传输层,资源释放走 `ctx.effect()`。是否提供服务由 `cordis.yml` 决定;未挂载该插件的配置会启动一个不提供此服务的合法进程。协议级退出归插件所有(应答并确保 `shutdown` 响应发送完毕后,对根运行时执行 dispose(资源释放),让待处理的持久化操作完成,再调用 `exit(0)`;HMR(热模块替换)式卸载只停止服务,不退出进程)。
+- [`apps/cli`](../../../../apps/cli/README.zh.md)(`@deepseek-ai/dsh`):打包后的应用入口;其 `sdk` profile 挂载 `dsh-sdk-jsonrpc-server`,CLI 负责环境分层、profile 组合、stdin/signal 关闭与进程退出。
-配置发现有两个通道,均缺失时立即报错:优先使用 `DSH_CORDIS_CONFIG` 环境变量(SDK 客户端约定),其次使用 argv 位置参数;没有默认路径或内置回退——「实际启动的插件由外部 `cordis.yml` 决定」是硬语义。
+Python 客户端提供显式 Harness home,并选择 `sdk` profile 与有序 patch 文件。缺失 home、profile、bundle 或 server 配置项都会明确失败;不存在外部完整配置回退。[Python profile 运行时决策](2026-08-23-python-sdk-dsh-profile-runtime.zh.md)负责该应用接口。
### 插件解析:VFS 装载真实包树,闭包 manifest(元数据清单)就是部署根目录
exe 的 VFS 内是**构建产物形态的真实包树**(各包的 `lib/` + 真实 `node_modules`)。打包专用 JSON-RPC 入口会向 app-boot 的根 Include 提供自身已安装 harness 的基准位置:相对插件说明符从外部配置目录解析,裸包名则从 VFS 解析,因此位于另一个 Node 项目内的配置无法遮蔽已打包的插件集合。普通开发 bin 仍由配置项目提供裸包。打包入口中的裸包名从该入口在 VFS 内的位置沿 `node_modules` 向上解析,自然落在 VFS 内。封闭集不需要白名单代码——VFS 中安装了什么,集合中就有什么;`import()` 集合外的名称会失败。
-部署根目录是 [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json)(`dsh-jsonrpc-agent-pkg`,pnpm 工作区成员、零代码纯依赖 manifest),也是「exe 安装哪些插件」与「Python 运行时分发什么」的统一真源。向 exe 添加插件,就是在 manifest 中增加一行依赖后重新打包。[`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) 读取每个已发布的 `apps/cli/config/agent-presets/*/agent.cordis.yml`,针对 `python/sdk-runtime/platforms.json` 中的每个目标解析比较 `process.platform` 的 `disabled` 条件,并要求该目标启用的每个工作区插件都通过显式的 `workspace:` 依赖列在运行时根目录。它还遍历该 manifest 覆盖的全部工作区包,要求每个非可选的工作区对等依赖(peer dependency)都显式列出,并报告“preset 或引用包 → 缺失依赖”的完整链路;无法识别的平台条件会保持启用,避免因不支持的表达式遗漏插件。`pnpm run hygiene`、CI 静态检查与 single-exe 构建都会在打包前运行该门禁。部署还会依据各包的 `files` 字段打包,因此 tsdown 拆出的共享分片必须被 `files` 覆盖。
+部署根目录是 [`python/sdk-runtime/package.json`](../../../../python/sdk-runtime/package.json)(`dsh-python-runtime-closure`,pnpm 工作区成员、零代码纯依赖 manifest),也是「exe 安装哪些插件」与「Python 运行时分发什么」的统一真源。向 exe 添加插件,就是在 manifest 中增加一行依赖后重新打包。[`scripts/verify-runtime-closure.ts`](../../../../scripts/verify-runtime-closure.ts) 读取每个已发布的 `packages/preset/agent-presets/presets/*/agent.cordis.yml`,针对 `python/sdk-runtime/platforms.json` 中的每个目标解析比较 `process.platform` 的 `disabled` 条件,并要求该目标启用的每个工作区插件都通过显式的 `workspace:` 依赖列在运行时根目录。它还遍历该 manifest 覆盖的全部工作区包,要求每个非可选的工作区对等依赖(peer dependency)都显式列出,并报告“preset 或引用包 → 缺失依赖”的完整链路;无法识别的平台条件会保持启用,避免因不支持的表达式遗漏插件。`pnpm run hygiene`、CI 静态检查与 single-exe 构建都会在打包前运行该门禁。部署还会依据各包的 `files` 字段打包,因此 tsdown 拆出的共享分片必须被 `files` 覆盖。
部署根目录显式包含 `@deepseek-ai/dsh-mcp-client`,将其作为自定义配置可用的插件,即使随附 preset 均未挂载该插件。外部配置因此可以连接由用户提供的 stdio 与 Streamable HTTP MCP server 并注册其工具;分发物不包含这些 server,也不将桥接范围扩展到 MCP Resources 和 Prompts。可执行程序与已安装 wheel 包的冒烟测试会启动临时 stdio server,发现其工具,并完成一次由模型请求的调用。
### 构建流水线与产物
-[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts):运行时闭包校验 → `pnpm run build` →(清空后)`pnpm --filter dsh-jsonrpc-agent-pkg deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **直接写入** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → 恢复被 legacy deploy 提升回源 manifest 的 `node_modules` 下的任何直接工作区包,同时省略其包内依赖树,并拒绝剩余的 manifest 缺口 → 将暂存依赖中的每个符号链接替换为目标文件内容,删除包管理器的 `.bin` 链接,并在仍有任何符号链接时失败 → 注入 pkg 配置(`bin` 指向闭包内的 `node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js`;`assets` 使用全量 glob,因为动态 `import()` 对 pkg 静态分析不可见,必须显式打入全部内容)→ 暂存目标平台的 `node-pty` addon → 每个构建目标调用一次 `pkg --sea` → 可执行文件 `dsh-jsonrpc-agent-pkg--` 写入 `dist-exe/`,并拷回运行时目录。Linux 安装会从源码构建 `pty.node`;CI 会在打包前进入匹配架构的 manylinux 2.28 容器重新构建该 addon,而 `--legacy` 部署会省略这一副作用目录,因此构建器会把它从根安装目录复制到暂存闭包。每个目标都会把对应的原生 `@vscode/ripgrep` 二进制复制到可执行文件旁,作为必需的 `-rg` 伴随文件;pkg 运行时通过 `process.pkg` 选择该伴随文件,普通 Node 执行则直接使用 `@vscode/ripgrep`。macOS 使用对应目标的预构建产物,并额外生成所需的 `-spawn-helper`。CI 将这些产物作为测试中间输入,只保留对应平台的 wheel 包。四个部署标志都有实测依据:未启用 `inject-workspace-packages` 时必须使用 `--legacy`;`hoisted` 为 pkg 提供稳定的单实例布局,再由显式物化步骤消除符号链接;关闭对等依赖自动安装可防止未声明的对等依赖扩大闭包;`link-workspace-packages` 选择直接工作区依赖。[`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) 将传递的 `@deepseek-ai/cosmokit` 与 `@deepseek-ai/schemastery` semver 请求覆盖到固定的 vendor 源码,使 legacy deploy 不会从注册表解析这些未发布名称。
+[`scripts/build-exe-for-python-sdk.ts`](../../../../scripts/build-exe-for-python-sdk.ts):运行时闭包校验 → `pnpm run build` →(清空后)`pnpm --filter dsh-python-runtime-closure deploy --legacy --prod --config.node-linker=hoisted --config.auto-install-peers=false --config.link-workspace-packages=true` **直接写入** `python/sdk-runtime/src/deepseek_harness_runtime/runtime/node/` → 恢复 legacy deploy 遗漏的直接工作区包,并拒绝剩余的 manifest 缺口 → 将暂存依赖中的符号链接替换为目标文件内容,删除包管理器的 `.bin` 链接,并在仍有任何符号链接时失败 → 注入 pkg 配置,其中 bin 为 `node_modules/@deepseek-ai/dsh/lib/bin.js`,assets 覆盖动态读取的 profile、bundle、前端、preset、原生库与配置文件 → 暂存目标平台的 `node-pty` addon → 每个构建目标调用一次 `pkg --sea` → 将 `deepseek-harness-sdk-runtime--` 写入 `dist-exe/` 并拷回运行时目录。Linux CI 会在匹配的 manylinux 2.28 容器中重新构建 `pty.node`,因为 legacy deploy 会遗漏这一安装副作用。每个目标都会把对应的原生 `@vscode/ripgrep` 二进制复制到可执行文件旁,作为必需的 `-rg` 伴随文件;pkg 运行时通过 `process.pkg` 选择该伴随文件,普通 Node 执行则直接使用 `@vscode/ripgrep`。macOS 使用对应目标的预构建产物,并额外生成所需的 `-spawn-helper`。四个部署标志都有实测依据:未启用 `inject-workspace-packages` 时必须使用 `--legacy`;`hoisted` 为 pkg 提供稳定的单实例布局,再由显式物化步骤消除符号链接;关闭对等依赖自动安装可防止未声明的对等依赖扩大闭包;`link-workspace-packages` 选择直接工作区依赖。[`pnpm-workspace.yaml`](../../../../pnpm-workspace.yaml) 将传递的 `@deepseek-ai/cosmokit` 与 `@deepseek-ai/schemastery` semver 请求覆盖到固定的 vendor 源码,使 legacy deploy 不会从注册表解析这些未发布名称。
-CI 使用 [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml):[必需的 Python 运行时拉取请求验证](../testing/2026-08-12-required-python-runtime-pull-request-ci.md)调用它构建 linux-x64,手动派发 `workflow_dispatch` 或 PR(Pull Request)的 `build-exe` 标签可以显式选择构建目标,[公开发布工作流](../process/2026-08-11-python-publication-workflow.md)则调用它构建全部目标。linux-x64、linux-arm64(`ubuntu-24.04-arm`)和 macos-arm64 三个平台分别进行原生构建,并缓存 `~/.pkg-cache`;macOS 的 ad-hoc 签名由 pkg 处理。每个平台都使用 mock SSE(Server-Sent Events)模型,分别通过默认配置和自定义 `cordis.yml` 驱动 SDK,再通过 NDJSON JSON-RPC 直接驱动 exe,校验 JSONL 与最终响应;最后把发布形态的 wheel 包安装到干净的 venv 中,并在不传 `runtime_bin` 的情况下运行。Linux 还会检查可执行文件和原生 addon 各自的 GLIBC 依赖,并在 manylinux 2.28 容器中运行;macOS 则验证可执行文件的部署目标符合 wheel 包标签。完整构建三个目标时保留 4 个产物,每个产物只含一个发布文件:平台无关的 SDK wheel 包与 3 个原生运行时 wheel 包;手动选择部分目标时保留 SDK wheel 与所选运行时 wheel。裸 exe 与源码包只作为测试中间输入。[`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) 只接受版本与根目录 `package.json` 匹配的 `python-v` 标签流水线,构建一个 SDK wheel 包和 3 个原生运行时 wheel 包,再由单个串行任务校验并将这 4 个文件发布到项目的 PyPI 注册表。Windows 不在目标范围内。
+CI 使用 [`.github/workflows/build-exe-for-python-sdk.yml`](../../../../.github/workflows/build-exe-for-python-sdk.yml):[安装后 wheel Python 运行时拉取请求验证](../testing/2026-08-23-installed-python-wheel-black-box-ci.zh.md)与[公开发布工作流](../process/2026-08-11-python-publication-workflow.zh.md)都会调用它构建全部四个目标;`workflow_dispatch` 仍可选择部分目标。linux-x64、linux-arm64(`ubuntu-24.04-arm`)、macos-arm64 与 win-x64(`windows-2025`)分别进行原生构建,并在适用平台缓存 `~/.pkg-cache`;macOS 的 ad-hoc 签名由 pkg 处理。每个平台都把发布形态的 SDK wheel 包与运行时 wheel 包安装到 checkout 外的干净 venv,证明包与可执行文件来源,再通过公开 SDK 与直接 NDJSON JSON-RPC 运行完整 keyless 场景。可信拉取请求还会在每个目标上运行真实 DeepSeek 双轮工具冒烟测试;fork 与 Dependabot head 不会获得密钥。Linux 会检查可执行文件和原生 addon 各自的 GLIBC 依赖,并额外运行 manylinux 2.28 冒烟测试;macOS 则验证可执行文件的部署目标符合 wheel 包标签。完整构建四个目标时保留 5 个产物,每个产物只含一个发布文件:平台无关的 SDK wheel 包与 4 个原生运行时 wheel 包;手动选择部分目标时保留 SDK wheel 与所选运行时 wheel。裸 exe 与源码包只作为测试中间输入。[`.gitlab-ci.yml`](../../../../.gitlab-ci.yml) 只接受版本与根目录 `package.json` 匹配的 `python-v` 标签流水线,构建一个 SDK wheel 包和 4 个原生运行时 wheel 包,再由单个串行任务校验并将这 5 个文件发布到项目的 PyPI 注册表。[Windows x64 运行时决策](2026-08-23-python-sdk-windows-x64-runtime.zh.md)负责第四个目标及对 Windows arm64 的明确排除。
### Python SDK 分发:双载体,exe 用于生产,`node` 用于开发
-Python SDK 位于 [`python/`](../../../../python/README.md):`python/sdk` 是客户端,`python/sdk-runtime` 是运行时载体包。运行时包的数据目录包含检入的默认 `runtime/cordis.yml`、构建注入的平台 exe 及其必需的 `-rg` 伴随文件和可选的 macOS helper,以及构建注入的 `runtime/node/` 闭包树。`resolve_bundled_launch_args()` 的自动解析**只查找 exe**;`node` 载体仅在显式设置 `DSH_RUNTIME_MODE=node` 时启用(运行 `runtime/node/node_modules/@deepseek-ai/dsh-sdk-jsonrpc-demo/lib/packaged-bin.js`,需要系统 Node ≥22.19),定位为本仓库成员的开发验证通道,不随 wheel 包分发。
+Python SDK 位于 [`python/`](../../../../python/README.zh.md):`python/sdk` 是客户端,`python/sdk-runtime` 是运行时载体包。运行时包的数据目录包含构建注入的平台可执行文件及其必需的 `-rg` 伴随文件和可选的 macOS helper,以及供仓库开发使用的构建注入 `runtime/node/` 闭包树。`resolve_bundled_launch_args()` 默认选择可执行文件;显式设置 `DSH_RUNTIME_MODE=node` 会在系统 Node 22.19 或更高版本上运行 `runtime/node/node_modules/@deepseek-ai/dsh/lib/bin.js`。node 载体从不进入 wheel 分发,两种载体都不使用检入的完整 `cordis.yml`。
-[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) 从仓库根目录的 `package.json` 读取权威的 `X.Y.Z` 或预发布版本,把预发布版本转换为 PEP 440 写法,并以该 wheel 包版本暂存两个包,让 `deepseek-harness-sdk` 精确依赖匹配版本的 `deepseek-harness-runtime-bin`。可选的 `python-v` 发布标签只是一项一致性断言,与仓库版本不同时会被拒绝;源码 `pyproject.toml` 中的开发占位版本从不决定发布版本。暂存过程还会把仓库许可证放入两个 wheel 包,并把第三方声明放入内置运行时 wheel 包。SDK 是 `py3-none-any` wheel 包;每个只提供 wheel 包的运行时包都包含一个 exe 及其架构匹配的 `-rg` 伴随文件,macOS wheel 包还包含与其架构匹配的 spawn helper。运行时 wheel 包使用 `py3-none-manylinux_2_28_x86_64`、`py3-none-manylinux_2_28_aarch64`,或针对 Node 24 可执行文件 macOS 13.5 部署目标而保守选择的 `py3-none-macosx_14_0_arm64` 标签;Hatch 钩子拒绝 sdist、通用标签、混合平台载荷、伴随文件缺失或多余,以及不支持的平台。
+[`scripts/build-python-release.py`](../../../../scripts/build-python-release.py) 从仓库根目录的 `package.json` 读取权威的 `X.Y.Z` 或预发布版本,把预发布版本转换为 PEP 440 写法,并以该 wheel 包版本暂存两个包,让 `deepseek-harness-sdk` 精确依赖匹配版本的 `deepseek-harness-runtime-bin`。可选的 `python-v` 发布标签只是一项一致性断言,与仓库版本不同时会被拒绝;源码 `pyproject.toml` 中的开发占位版本从不决定发布版本。暂存过程还会把仓库许可证放入两个 wheel 包,并把第三方声明放入内置运行时 wheel 包。SDK 是 `py3-none-any` wheel 包;每个只提供 wheel 包的运行时包都包含一个 exe 及其架构匹配的 ripgrep 伴随文件,macOS wheel 包还包含与其架构匹配的 spawn helper。运行时 wheel 包使用 `py3-none-manylinux_2_28_x86_64`、`py3-none-manylinux_2_28_aarch64`、针对 Node 24 可执行文件 macOS 13.5 部署目标而保守选择的 `py3-none-macosx_14_0_arm64` 标签,或 `py3-none-win_amd64`;Hatch 钩子拒绝 sdist、通用标签、混合平台载荷、伴随文件缺失或多余,以及不支持的平台。
-exe「必须显式配置」的硬语义不变;零配置体验由包装层恢复:调用方没有提供 `cordis`、没有显式指定运行时,且环境中没有 `DSH_CORDIS_CONFIG` 时,客户端将检入的默认 `cordis.yml`(`agent-core` + 预载的 `llm-deepseek` + JSONL 持久化 + `bash-local` + `dsh-sdk-jsonrpc-server` 对外服务条目,并通过 `!!js` 使用环境变量兜底)显式注入 `DSH_CORDIS_CONFIG`。
+Python 客户端使用所选 profile(默认 `sdk`)、有序 patch 文件和显式 Harness home 启动打包后的 `dsh` 命令。Profile 负责 JSON-RPC 服务和应用组合;缺失 home、profile、bundle、patch 或 server 配置项都会失败,不存在外部完整配置回退。
### 命名血统
-`@deepseek-ai/dsh-sdk-jsonrpc-demo`(包)→ `dsh-jsonrpc-agent`(`bin`)→ `dsh-jsonrpc-agent-pkg`(闭包 manifest;没有作用域前缀,刻意避开 `constraints` 对 `@deepseek-ai/dsh-*` 的包形状规则)→ `dsh-jsonrpc-agent-pkg--`(exe 产物)。协议字段 `serverInfo.name` 保持为 `deepseek-harness-sdk-runtime`(协议稳定值);Python 分发包名为 `deepseek-harness-sdk` / `deepseek-harness-runtime-bin`,导入模块名仍为 `deepseek_harness` / `deepseek_harness_runtime`。
+`dsh-python-runtime-closure` 是私有部署 manifest,`deepseek-harness-sdk-runtime--` 是可执行文件族。协议字段 `serverInfo.name` 是 `deepseek-harness-sdk-runtime`;Python 分发包名是 `deepseek-harness-sdk` / `deepseek-harness-runtime-bin`,导入模块名是 `deepseek_harness` / `deepseek_harness_runtime`。
## 工作线程插件
@@ -64,7 +64,7 @@ exe 内支持 `dsh-workflow-worker-thread` 与 `dsh-code-runtime-worker-thread`
## 测试
-验证面分三层。机制层:`--sea` 链路的实测结论内嵌在「决策」各节(VFS 内 ESM 动态 `import()`、单一 Cordis 实例、明确报错的配置链路、`node:sqlite`、macOS ad-hoc 签名可运行)。SDK 层:完整的无密钥 pytest 套件以 mock 运行时对端覆盖客户端协议、子进程清理、绝对 `cwd` 传递、双载体启动与载体解析;根 CI 在 Python 3.10 上运行全部用例。端到端层:每个平台构建都通过默认 SDK 路径、自定义配置、仓库内置的独立 minimal 组合和直接二进制协议,对 mock 端点完成一个轮次,并校验最终文本与 JSONL。minimal 运行会断言其精确系统提示词与双工具目录,跨调用保留 Bash 状态,并调用编辑器。自定义配置还会通过打包进 VFS 的真实工作线程文件执行 `run_code` 和不启动 agent 的 `workflow`。文件系统搜索场景要求模型通过目标平台的 `-rg` 伴随文件调用 `glob` 与 `grep`。MCP 场景会启动临时外部 stdio server,刻意延迟首次 `tools/list` 响应,随后立即启动第一个 SDK 提示词;该提示词必须看到并调用已发现的工具,从而证明 `initialize` 是真正以 Loader 插件树完全稳定为准的就绪边界,而不是依赖定时 sleep。同一构建任务还会经 Python SDK 运行一组检入的 exe 专用快照:无密钥脚本化模型挂载一个会注册工具的 Cordis 插件,从 `run_code` 调用该工具,运行一个直接 spawn 的 subagent 和一个会通过 spawn 启动第二个 subagent 的工作流,随后卸载该插件。该 fixture(测试前置数据)会显式禁用组合包中未使用的 Bash 和本地 skill(技能)发现,使其工具集不依赖仓库外部状态;比较时会规范化 SDK 结果与通知流,以及父会话和两个子会话 JSONL 日志中不透明的消息、agent、工作流运行与会话 ID。该 harness 与 ACP 的 `pnpm run test:snapshot` 保持独立,因为二者的协议和构建产物不同。随后把平台 wheel 包安装进干净的 venv,并在不传 `runtime_bin` 的情况下运行。
+验证面分三层。机制层:`--sea` 链路的实测结论内嵌在「决策」各节(VFS 内 ESM 动态 `import()`、单一 Cordis 实例、明确报错的配置链路、`node:sqlite`、macOS ad-hoc 签名可运行)。SDK 层:完整的无密钥 pytest 套件以 mock 运行时对端覆盖客户端协议、子进程清理、绝对 `cwd` 传递、双载体启动与载体解析;根 CI 在 Python 3.10 上运行全部用例。端到端层:每个平台构建都会把两个 wheel 包安装进 checkout 外的干净 venv,证明版本相同以及已安装模块/可执行文件的位置,再通过默认 SDK 路径、自定义配置、仓库内置的独立 minimal 组合和直接二进制协议,对 mock 端点完成轮次,并校验最终文本与 JSONL。minimal 运行会断言其精确系统提示词与双工具目录,跨调用保留 Bash 状态,并调用编辑器。自定义配置还会通过打包进 VFS 的真实工作线程文件执行 `run_code` 和不启动 agent 的 `workflow`。文件系统搜索场景要求模型通过目标平台的 `-rg` 伴随文件调用 `glob` 与 `grep`。MCP 场景会启动临时外部 stdio server,刻意延迟首次 `tools/list` 响应,随后立即启动第一个 SDK 提示词;该提示词必须看到并调用已发现的工具,从而证明 `initialize` 是真正以 Loader 插件树完全稳定为准的就绪边界,而不是依赖定时 sleep。同一项安装后运行还会经 Python SDK 比较一组检入的 exe 专用快照:无密钥脚本化模型挂载一个会注册工具的 Cordis 插件,从 `run_code` 调用该工具,运行一个直接 spawn 的 subagent 和一个会通过 spawn 启动第二个 subagent 的工作流,随后卸载该插件。该 fixture(测试前置数据)会显式禁用组合包中未使用的 Bash 和本地 skill(技能)发现,使其工具集不依赖仓库外部状态;比较时会规范化 SDK 结果与通知流,以及父会话和两个子会话 JSONL 日志中不透明的消息、agent、工作流运行与会话 ID。可信拉取请求会增加真实提供方双轮文件写入/读取,并要求外部字节、工具调用、已完成原因与持久化日志一致。该 harness 与 ACP 的 `pnpm run test:snapshot` 保持独立,因为二者的协议和构建产物不同。
手工驱动注意:`bin` 将 stdin EOF 视为「客户端已离开」并立即 dispose,生命周期较短的管道会中止进行中的轮次——管道驱动必须保持 stdin 打开,直到轮次结束。
diff --git a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml
index 02aeec5ad6..7d8d2db1cf 100644
--- a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md
2026-07-12-agent-scope-runtime-design.md: 9d70b8048b1d2bb50290d34158d9deb329d5e15e
-2026-07-12-agent-scope-runtime-design.zh.md: a505f5337559294795c1080937c6079cee235baa
+2026-07-12-agent-scope-runtime-design.zh.md: 278bcede47fee9f67d3d2d2d7135e5357c120161
diff --git a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md
index a505f53375..278bcede47 100644
--- a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.zh.md
@@ -6,7 +6,7 @@ Status: implemented
## 问题
-[agent(智能体)作用域约定](2026-07-08-agent-scope-contexts.md)对贡献者而言很简单:通过 `agent.ctx` 注册,解析出一个全局加单 agent 的视图,仅在 setup 完成后发布,并保持作用域直到工作停止。运行时必须在协作式插件框架、异步创建、可重入监听器、持久化会话提交以及 worker 或进程故障等场景下维护这份约定。
+[agent(智能体)作用域约定](2026-07-08-agent-scope-contexts.zh.md)对贡献者而言很简单:通过 `agent.ctx` 注册,解析出一个全局加单 agent 的视图,仅在 setup 完成后发布,并保持作用域直到工作停止。运行时必须在协作式插件框架、异步创建、可重入监听器、持久化会话提交以及 worker 或进程故障等场景下维护这份约定。
主要的设计风险是为每个竞态条件引入第二套机制。独立的预留、就绪哨兵、取消中继、快照层和保护注册表可能镜像同一个事实,直到没有读者能分辨哪个才是权威的。这些机制还会诱使运行时把可信的类型化调用当作敌对的序列化边界来处理。
@@ -30,7 +30,7 @@ Status: implemented
本 Agent Note 余下部分按依赖顺序展开这些选择:Cordis 机制、作用域路由、创建与会话提交、工具与提示词、subagent 与工作流,最后是可执行检查。
-[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.md) 仍然是贡献者约定。独立的 [subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) 拥有 `persona`、`toolFilter` 和 `maxDepth`;本文仅讨论它们的 setup 如何融入生命周期。
+[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.zh.md) 仍然是贡献者约定。独立的 [subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.zh.md) 拥有 `persona`、`toolFilter` 和 `maxDepth`;本文仅讨论它们的 setup 如何融入生命周期。
## Cordis 模型:上下文、fiber、effect、receiver 与 waterfall
@@ -58,6 +58,8 @@ Cordis 使用 dispatch receiver(`this`)过滤监听器,而 harness 的监
Cordis waterfall 是中间件风格的 dispatch。每个监听器接收 `next()`:调用它则委托给剩余监听器和基础操作,不调用则短路或替换下游结果。Waterfall 驱动提示词组装和工具策略;普通 emit 事件同步通知,parallel 事件等待所有监听器但没有否决结果。
+
+
## 作用域路由:一个不透明键选择一层
scope 包实现了 Cordis 路由所需的最小对象。其载体仅持有一个组合的服务过滤器和作用域谓词,而包私有地记录不透明键,并单独暴露会等待作用域 fiber 完全停稳的 disposer。
@@ -72,7 +74,7 @@ Receiver 是一个小型载体而非领域对象的透明代理。需要 agent
### 注册表读取叠加一个精确 layer
-作用域感知的注册表使用 `ScopedLayers`,拥有一个即时创建的全局 aggregate 和按标识键惰性创建的 aggregate。读取解析全局 layer 和至多一个精确局部 layer;它不创建状态,也从不遍历父级链。注册可见性与 Cordis effect 所有权都从同一个上下文派生,而回收会等待具体 layer 的完整 aggregate 变空(见[决策](2026-07-12-scoped-layers-store.md))。
+作用域感知的注册表使用 `ScopedLayers`,拥有一个即时创建的全局 aggregate 和按标识键惰性创建的 aggregate。读取解析全局 layer 和至多一个精确局部 layer;它不创建状态,也从不遍历父级链。注册可见性与 Cordis effect 所有权都从同一个上下文派生,而回收会等待具体 layer 的完整 aggregate 变空(见[决策](2026-07-12-scoped-layers-store.zh.md))。
每个服务保留其领域规则。命名 command 和提示词视图使用共享的、保持插入顺序的 shadow 合并;工具保留更丰富的 resolver,因为限制会在加入局部工具前过滤全局工具,保留的 Code Mode transport 则单独插入。提示词变量和工具 guard 保持实时迭代,而工具提供方成员关系按每次 assembly 物化。Scope 提供存储生命周期和命名遮蔽,而非通用的注册表视图。
@@ -158,6 +160,8 @@ sequenceDiagram
此顺序让最终的 agent 和会话事件能使用匹配的作用域监听器,并使持久化观察者在最终刷新完成前保持附加。作用域 dispose 放在最后,因为注册撤销是外部可见的生命期边界。
+
+
## 会话追加:物化、验证、提交、通知
会话事件跨越持久化边界,因此追加操作拥有其数据。算法的其余部分使用一条已附加的注册表条目和一个提交点。
@@ -208,7 +212,7 @@ Session 头部、种子和追加的事件是无损 JSON 数据。Session 构造
私有解析器应用当前展示模式、活跃的全局限制、精确的局部叠加和局部遮蔽。Schema、查找、执行、Code Mode SDK 生成和限制验证都使用该解析器或其限制前的全局名称视图。
-[subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.md#tool-filtering-is-one-live-global-view-rule) 拥有用户可见的 allow/deny 语义。实现要求是一致性:被过滤掉的全局工具不能通过另一条查找路径仍可执行,局部遮蔽的定义就是被展示和执行的同一个定义。
+[subagent 组合控制 Agent Note](../feature/2026-07-12-subagent-persona-tool-filter-and-depth.zh.md#tool-filtering-is-one-live-global-view-rule) 拥有用户可见的 allow/deny 语义。实现要求是一致性:被过滤掉的全局工具不能通过另一条查找路径仍可执行,局部遮蔽的定义就是被展示和执行的同一个定义。
`ToolRestriction` 接受 readonly 的 allow/deny 名称并将其编译为内部集合。多个限制取交集。公开的 `visible()` 和 `knownNames()` 方法是不必要的,因为只有注册表需要中间视图。
@@ -230,6 +234,8 @@ SystemPrompt 首先将全局加 agent 的段、变量和工具提供方解析为
Scope 直接解决了真正的隔离问题。结构化输出贡献注册在子级的精确作用域中,而 Code Mode 从同一个已解析的工具视图派生其传输和 SDK。第二套命名保护系统需要另一套所有权和碰撞规则来覆盖任意 schema 提供方(包括有意贡献重复名称的提供方),却不创建新的信任边界。
+
+
### 结构化输出仅提交权威结果
结构化输出将子作用域组合与两阶段执行提交相结合。子级在发布前注册其 `structured_output` 工具和指令;可信的 assembly 监听器可以变换这些普通贡献,并有责任在期望子级完成时保持协议。工具体验证候选值并按当前 `ToolExecution` 暂存,但成功捕获仅由不可变的 `tools/result` 观察决定。
@@ -242,6 +248,8 @@ Scope 直接解决了真正的隔离问题。结构化输出贡献注册在子
纯 Code Mode 的注册表贡献从原生 wire schema 中省略 `structured_output`,并通过生成的 SDK 暴露它。Assembly waterfall 可以有意改变该展示;执行仍然针对子作用域定义进行验证,监听器拥有其创建的任何替代模型可见路由的一致性。
+
+
### 三个执行边界有意设为单向
提示词组装有意是协作式的,但三个执行事实在其可扩展阶段之后需要单向结算:
@@ -266,7 +274,7 @@ subagent 启动有一次所有权转移。提供方拥有未发布资源,直
### 服务约定有一个取消通道
-`SubagentProvider.start()` 和 `SubagentRuntime.start()` 返回 `Promise`。Promise 会在后端跨过发布边界后兑现,因此调用方和 `subagent/start` 观察者从不需要第二个 `run.started` promise。提供方工作如果在发布前失败,`start()` 就会被拒绝;发布后的提示词、轮次、取消与基础设施结果会通过 `SubagentRun.result` 结算,且不会隐藏 child id,这也是[持久化目录决策](../feature/2026-07-22-durable-subagent-catalog-and-list-agents.md)所要求的约定。
+`SubagentProvider.start()` 和 `SubagentRuntime.start()` 返回 `Promise`。Promise 会在后端跨过发布边界后兑现,因此调用方和 `subagent/start` 观察者从不需要第二个 `run.started` promise。提供方工作如果在发布前失败,`start()` 就会被拒绝;发布后的提示词、轮次、取消与基础设施结果会通过 `SubagentRun.result` 结算,且不会隐藏 child id,这也是[持久化目录决策](../feature/2026-07-22-durable-subagent-catalog-and-list-agents.zh.md)所要求的约定。
`SubagentStartRequest.signal` 是必需的。中止它会在启动期间,以及已发布 run 的剩余就绪或轮次工作中请求取消。`SubagentRun.dispose()` 也请求取消并等待完全停稳。没有单独的公开 `run.cancel()` 通道。
@@ -292,6 +300,8 @@ Start 仅在 `initialize` 和 `newSession` 成功后才 resolve。Abort、spawn
Worker 和子进程桥接比同进程注册表需要更多状态,因为消息、进程死亡和清理可以独立结算。它们的状态围绕这些真实事实组织,而非重复的取消协议。
+
+
### 工作流子级是待定 start 或已发布记录
工作流宿主保持待定的提供方 start promise 和已发布的子级记录。子级仅在异步 `SubagentRuntime.start()` 兑现时才从待定变为已发布;被拒绝的 start 清理其部分提供方工作且不产生子级生命周期对。
@@ -308,7 +318,7 @@ Worker 边界仍然序列化请求和结果。宿主保留首个终端结果仲
### ACP 提示词结算不依赖更新投递
-[仅面向自动化的 ACP 桥接层](../simplification/2026-07-23-acp-automation-only-protocol.md)直接将一个进行中的提示词与其观察到的用户消息轮次关联。它不从日志水位线扫描,也不使用会话状态作为第二个调和预言机。
+[仅面向自动化的 ACP 桥接层](../simplification/2026-07-23-acp-automation-only-protocol.zh.md)直接将一个进行中的提示词与其观察到的用户消息轮次关联。它不从日志水位线扫描,也不使用会话状态作为第二个调和预言机。
即使已提交消息的更新无法送达客户端,会话事件监听器也会从匹配的 `turn/end` 结算关联。因此更新投递不能让会话永久处于进行中状态。ACP 创建由服务器分配 id 的全新会话,并拥有由此产生的每个 agent 句柄,直到连接拆除。
@@ -330,13 +340,13 @@ TypeScript 无法管控 JavaScript 强制转换、直接 Cordis dispatch、进
### 生成的产物使公开约定保持对齐
-事件目录、服务目录、生产者/消费方矩阵、配置目录、模块图、工具目录、type-equiv 块和作用域事件解析器映射都是从源码生成或受新鲜度门禁约束的。[TypeScript 语义门禁 Agent Note](../process/2026-07-14-typescript-program-backed-semantic-gates.md) 拥有 Program 构造、语义事件发现和解析器生成规则。
+事件目录、服务目录、生产者/消费方矩阵、配置目录、模块图、工具目录、type-equiv 块和作用域事件解析器映射都是从源码生成或受新鲜度门禁约束的。[TypeScript 语义门禁 Agent Note](../process/2026-07-14-typescript-program-backed-semantic-gates.zh.md) 拥有 Program 构造、语义事件发现和解析器生成规则。
行为测试固定了作用域路由和 dispose、最终写入注册表时的碰撞清理、发布回滚、有序完全停稳、持久化前/后提交行为、跨展示和执行的活跃工具过滤、协作式提示词组装、原生和 Code Mode 中的结构化输出提交、异步 subagent 启动和信号取消、worker 终端仲裁、ACP 结算和进程拆除。
## 曾考虑的替代方案
-[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.md#alternatives-considered) 拥有公开扁平作用域约定的替代方案。此处的替代方案关注实现形态。
+[7 月 8 日 Agent Note](2026-07-08-agent-scope-contexts.zh.md#alternatives-considered) 拥有公开扁平作用域约定的替代方案。此处的替代方案关注实现形态。
### 使用透明代理作为作用域载体
@@ -389,4 +399,4 @@ Worker 消息、进程死亡和持久化输入确实跨越所有权和序列化
该设计信任同进程中的类型化插件。它不防御任意强制转换、有状态 getter、违反 readonly 约定的修改,或插件有意在支持的组合 API 之外使用环境服务访问。
-[安全与权限非目标](2026-07-08-agent-scope-contexts.md#security-and-authority-are-non-goals)仍然是根本性的。这些机制证明注册组合、发布和生命期所有权;它们不证明隔离或父到子的非升权。
+[安全与权限非目标](2026-07-08-agent-scope-contexts.zh.md#security-and-authority-are-non-goals)仍然是根本性的。这些机制证明注册组合、发布和生命期所有权;它们不证明隔离或父到子的非升权。
diff --git a/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.i18n.yaml
index 86871f2bcd..205c3c4e39 100644
--- a/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.md
2026-07-12-scoped-layers-store.md: 221711748007d5f909aec3fdfcf3919884d11cdb
-2026-07-12-scoped-layers-store.zh.md: 7f3ad11e23f02eeafe955efe08525bda8a9e9996
+2026-07-12-scoped-layers-store.zh.md: 97ad637b91a2b9b2cad9847d8b4cdbe23ff14a48
diff --git a/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.zh.md b/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.zh.md
index 7f3ad11e23..97ad637b91 100644
--- a/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-12-scoped-layers-store.zh.md
@@ -6,7 +6,7 @@ Status: implemented
## 问题
-agent(智能体)作用域机制([决策](2026-07-08-agent-scope-contexts.md)、[运行时设计](2026-07-12-agent-scope-runtime-design.md))让支持作用域的注册表反复呈现同一种形态:一个全局注册层,加上一个与具体 agent 精确对应的层。七个注册门面都采用这一形态:`tools.register`、`tools.restrict` 和 `tools.guard`(位于 `dsh-tools`);`SystemPrompt.section`、`SystemPrompt.tools` 和 `SystemPrompt.variable`(位于 `dsh-system-prompt`);以及 `CommandRuntime.register`(位于 `dsh-commands`)。
+agent(智能体)作用域机制([决策](2026-07-08-agent-scope-contexts.zh.md)、[运行时设计](2026-07-12-agent-scope-runtime-design.zh.md))让支持作用域的注册表反复呈现同一种形态:一个全局注册层,加上一个与具体 agent 精确对应的层。七个注册门面都采用这一形态:`tools.register`、`tools.restrict` 和 `tools.guard`(位于 `dsh-tools`);`SystemPrompt.section`、`SystemPrompt.tools` 和 `SystemPrompt.variable`(位于 `dsh-system-prompt`);以及 `CommandRuntime.register`(位于 `dsh-commands`)。
如果没有共享原语,每个门面都要围绕自己的领域状态重复相同的生命周期编排:从调用方上下文导出可见性,按需创建专属容器,把属主绑定到同一个 Cordis fiber,先装入 undo 再通知观察者,原样返回 Cordis 的 disposer,并回收空的专属状态。各自分离的映射与集合类型也会让服务缺少一个表示某个 scope 完整贡献的对象。
diff --git a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml
index 3f4683f480..34523f2723 100644
--- a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md
2026-07-14-provider-routed-llm-adapters.md: 78c8d6788006c503b532ff2bbddd30342415f0a4
-2026-07-14-provider-routed-llm-adapters.zh.md: 5e73cab5f1f2b1296c9a486d1c833e95bb5674a0
+2026-07-14-provider-routed-llm-adapters.zh.md: af8bc4fe27a50d47d7b49b51eada67afe889fc13
diff --git a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md
index 5e73cab5f1..af8bc4fe27 100644
--- a/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md
@@ -20,7 +20,7 @@ Status: implemented
`GenerateOptions` 与 `LlmCallConfig` 在 `model: string` 之外携带 `provider: string`,`AgentOptions` 则携带对应的可选创建字段。只有两个值都非空时,agent loop(智能体循环)请求才有效;两个值也都会写入请求头日志。`agent/request` 可以在任意步骤返回替换后的字段组合,因此会话可以切换提供方与模型,无需改变 Cordis 插件生命周期。
-`LlmRuntime` 按提供方注册和解析适配器。`registerAdapter(providers, adapter)` 在修改注册表前检查整个提供方列表,遇到重复项时返回 `DUPLICATE_ADAPTER`,并以一个 effect 为单位整体 dispose(资源释放)。模型 ID 不作为注册键;仍由选中的适配器负责验证或转发。后续的 [LLM 目录与 ACP 模型选择 Agent Note](2026-07-15-llm-model-catalog-and-acp-selection.md) 增加了建议性的 `listProviders()` / `listModels()` 发现接口,但不会把目录成员关系变成请求校验规则。
+`LlmRuntime` 按提供方注册和解析适配器。`registerAdapter(providers, adapter)` 在修改注册表前检查整个提供方列表,遇到重复项时返回 `DUPLICATE_ADAPTER`,并以一个 effect 为单位整体 dispose(资源释放)。模型 ID 不作为注册键;仍由选中的适配器负责验证或转发。后续的 [LLM 目录与 ACP 模型选择 Agent Note](2026-07-15-llm-model-catalog-and-acp-selection.zh.md) 增加了建议性的 `listProviders()` / `listModels()` 发现接口,但不会把目录成员关系变成请求校验规则。
在一个 Cordis 上下文中,一个提供方只能有一个适配器所有者。`dsh-llm-deepseek` 注册 `deepseek`;`dsh-llm-pi-ai` 也可以注册 `deepseek`,但同时加载两个所有者属于配置错误,不采用顺序规则或回退行为。若部署选择手写的 DeepSeek 实现,需从 pi-ai 配置中排除 `deepseek`;若部署选择 pi-ai 的 DeepSeek 实现,则不挂载 `dsh-llm-deepseek`。
@@ -40,11 +40,11 @@ pi-ai 的通用流选项不支持停止序列。若 Harness `stop` 选项已定
助手消息携带请求的 `provider` 和 `model`,以及可选的 JSON 可序列化适配器回放状态。成功的 `assistant/message` 会话事件记录这些字段,`deriveMessages()` 返回助手消息时也会包含它们。用户、系统、上下文与工具结果消息不携带助手路由字段。提供方/模型字段是 agent loop 的权威数据;适配器仅拥有其不透明回放状态 payload。
-成功的终止 `finish` 分片可以以 `ReplayEnvelope` 形式携带回放状态:不透明的响应级元数据,加上与发射块序列对齐的可选逐块条目。`BlockAssembler` 对内容与元数据只做一次保留/丢弃决定——max-token 组装丢弃工具调用时,数据同一位置的条目一并丢弃——因此 agent loop 附加到已组装助手消息模型来源中的状态始终描述存储的块,见 [max-token 回放状态对齐决定](../bug-fix/2026-08-15-max-token-replay-state-alignment.md)。agent loop 不公开响应改写钩子。错误或中止响应不会生成正常助手消息,因此不会进入后续模型历史。
+成功的终止 `finish` 分片可以以 `ReplayEnvelope` 形式携带回放状态:不透明的响应级元数据,加上与发射块序列对齐的可选逐块条目。`BlockAssembler` 对内容与元数据只做一次保留/丢弃决定——max-token 组装丢弃工具调用时,数据同一位置的条目一并丢弃——因此 agent loop 附加到已组装助手消息模型来源中的状态始终描述存储的块,见 [max-token 回放状态对齐决定](../bug-fix/2026-08-15-max-token-replay-state-alignment.zh.md)。agent loop 不公开响应改写钩子。错误或中止响应不会生成正常助手消息,因此不会进入后续模型历史。
pi-ai 回放状态用其成功 `AssistantMessage` 的带版本最小投影填充该结构:一个响应半区(源 API/提供方/模型、响应 ID/模型、停止原因),以及逐块的文本签名、thinking 签名和工具调用签名。它不会重复 Harness 内容块中已有的文本或工具参数,也不包含诊断信息、时间戳、用量或错误。后续请求中,只有历史提供方和目标提供方当前归同一个适配器实例所有时,`LlmRuntime` 才会把回放状态交给目标适配器。适配器在能够恢复历史响应时,将 Harness 记录的内容与回放状态组合,并负责所需的跨模型或跨提供方转换。持久化内容保持权威:适配器收到无法使用的回放状态——未知 kind 或版本、格式错误的元数据、或与内容不再匹配的块结构——会把该消息降级为提供方无关转换并带出诊断;其他适配器只能收到提供方无关的内容以及提供方/模型字段。
-该状态属于模型可见的回放输入,因此遵循现有的[请求可重建规则](2026-07-05-reconstructable-requests.md):它同时存在于终止 `finish` 分片和驱动派生的已组装 `assistant/message` 模型来源中。恢复和 fork 会原样保留该状态。压缩(compaction)遮蔽助手消息时,也会从活动 surface 中移除其回放状态;摘要属于普通的提供方无关内容。
+该状态属于模型可见的回放输入,因此遵循现有的[请求可重建规则](2026-07-05-reconstructable-requests.zh.md):它同时存在于终止 `finish` 分片和驱动派生的已组装 `assistant/message` 模型来源中。恢复和 fork 会原样保留该状态。压缩(compaction)遮蔽助手消息时,也会从活动 surface 中移除其回放状态;摘要属于普通的提供方无关内容。
### 在所有请求生产方中传播目标
diff --git a/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml
index 458999f905..570b68263c 100644
--- a/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.md
2026-07-15-agent-initiator-scope.md: 63540c0ec6b29a10613e01f1ed9ced24e8f2d277
-2026-07-15-agent-initiator-scope.zh.md: a0e3638081d875adc2412191829ab84c8dcd697c
+2026-07-15-agent-initiator-scope.zh.md: 3ea893aa5f6992bf09965436c1db3144d2fae5ac
diff --git a/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md
index a0e3638081..3ea893aa5f 100644
--- a/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md
@@ -12,7 +12,7 @@ harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负
## 决策
-必需的 `ctx.agents` 服务使用 Node `AsyncLocalStorage` 携带发起 Agent。它直接存储同一个 `Agent`,不引入只有一个字段的帧;另一个私有运行标记只记录嵌套边界的谱系,供 teardown 记账使用,不携带身份。[核心数据目录](../../../../docs/subsystems/core.md#initiating-agent)标明了所携带的类型。
+必需的 `ctx.agents` 服务使用 Node `AsyncLocalStorage` 携带发起 Agent。它直接存储同一个 `Agent`,不引入只有一个字段的帧;另一个私有运行标记只记录嵌套边界的谱系,供 teardown 记账使用,不携带身份。[核心数据目录](../../../../docs/subsystems/core.zh.md#initiating-agent)标明了所携带的类型。
`currentInitiator()` 用于可选读取,`requireInitiator()` 抛出 `no initiating agent is active`,`withInitiator(agent, operation)` 保留操作返回的同步值或 Promise 本身。`withoutInitiator(operation)` 会建立清空边界,供不得继承 Agent 的工作使用。会话仍通过 `agent.session` 推导;轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。
@@ -28,7 +28,7 @@ harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负
宿主感知的传输层可以从 `ctx.agents.requireInitiator().session.id` 推导由部署方拥有的 `X-Harness-Session-Id` 等请求头;模型可见 schema 和参数中不包含该请求头。本决策不让现有生产 MCP 或 Web 传输层采用此请求头。测试替身传输层用于证明可信边界,而不会把宿主路由策略分配给现有的提供方无关 seam。
-本决策扩展 [Agent 注册作用域约定](2026-07-08-agent-scope-contexts.md)及其[运行时设计](2026-07-12-agent-scope-runtime-design.md),不会改变其中 `agent.ctx` 的静态含义。
+本决策扩展 [Agent 注册作用域约定](2026-07-08-agent-scope-contexts.zh.md)及其[运行时设计](2026-07-12-agent-scope-runtime-design.zh.md),不会改变其中 `agent.ctx` 的静态含义。
## 验证
diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml
index 69af08605c..eb7a9adfab 100644
--- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.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/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md
-2026-07-15-llm-model-catalog-and-acp-selection.md: 3dddbe7e9fae74e4ce1ec1c8e93a40c3352b5a54
-2026-07-15-llm-model-catalog-and-acp-selection.zh.md: 145fd0bc379ff8132d09ec628b6381a18f755cfa
+2026-07-15-llm-model-catalog-and-acp-selection.md: fef23711a9214eae414809833bcd9ee9e26105ae
+2026-07-15-llm-model-catalog-and-acp-selection.zh.md: 85e9fa35ac99b72a7df207fdb4971b57cf6dc525
diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md
index 3dddbe7e9f..fef23711a9 100644
--- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md
+++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md
@@ -4,7 +4,7 @@ Status: implemented
English | [中文](2026-07-15-llm-model-catalog-and-acp-selection.zh.md)
-> The catalog decision remains current. Per-session ACP model selection is superseded by [ACP as an automation-only protocol](../simplification/2026-07-23-acp-automation-only-protocol.md).
+> The catalog and scoped-selection decisions remain current. The temporary removal of ACP selection is superseded by [standard ACP v1 automation controls](../feature/2026-08-22-standard-acp-automation-controls.md), which exposes the catalog through standard session configuration without restoring UI projections.
## Problem
@@ -24,17 +24,17 @@ ACP selection must also preserve the provider dimension. The same model id may a
Catalog membership is advisory. It drives selectors and diagnostics but never changes `stream()` routing and never rejects an otherwise valid request. Provider ownership remains exclusive and lifecycle-bound; model ids remain request-time adapter input.
-`dsh-llm-pi-ai` maps the configured provider's installed `getModels(provider)` entries into the neutral catalog. Its existing request-time catalog lookup remains authoritative and still rejects unknown models with `UNKNOWN_MODEL`. `dsh-llm-deepseek` accepts an optional `models` config containing display entries, defaulting to `deepseek-v4-flash` named `DeepSeek-V4-Flash` and `deepseek-v4-pro` named `DeepSeek-V4-Pro`. An explicit list replaces those defaults and an empty list disables discovery. The entries improve selector UX for known public or private models, while every unlisted model id continues to pass through unchanged.
+`dsh-llm-pi-ai` maps the configured provider's installed `getModels(provider)` entries into the neutral catalog. Its existing request-time catalog lookup remains authoritative and still rejects unknown models with `UNKNOWN_MODEL`. `dsh-llm-deepseek` accepts an optional `models` config containing display entries, defaulting to `deepseek-v4-flash` named `DeepSeek-V4-Flash`, `deepseek-v4-pro` named `DeepSeek-V4-Pro`, and image-capable `deepseek-v4-flash-vision-exp` named `DeepSeek-V4-Flash-Vision-Exp`. An explicit list replaces those defaults and an empty list disables discovery. The entries improve selector UX for known public or private models, while every unlisted model id continues to pass through unchanged.
### Per-session selection in the front end
-A selection is owned by the front end that offers it (today the TUI `/model` selector), never by `LlmRuntime` or `AgentOptions`: those are deployment-wide or creation-wide objects, and mutating them would couple concurrent sessions. Each opaque choice carries the full provider/model pair, because the same model id may appear under multiple routes.
+A selection is owned by the front end that offers it, never by `LlmRuntime` or `AgentOptions`: those are deployment-wide or creation-wide objects, and mutating them would couple concurrent sessions. Each opaque choice carries the full provider/model pair, because the same model id may appear under multiple routes.
-The ACP automation transport is not a catalog consumer. Its deployment config supplies one optional provider/model target for newly created agents, and it advertises no model selector or configuration-option interface.
+The ACP automation transport consumes the advisory catalog through standard session configuration options. Its deployment config still supplies the initial provider/model target; each session owns an opaque provider/model choice and a dependent exact-model reasoning-effort choice. Adapter topology changes publish the complete option state. Catalog absence never invalidates the configured route: the current unlisted route is synthesized into the choices.
### Prompt/request consistency and durability
-`installModelSelection` (in `dsh-agent`) installs scoped `system-prompt/assemble` and `agent/request` listeners for a front-end-owned selection. Prompt assembly snapshots the selected pair once per step, overwrites the assembled `provider` and `model` variables after downstream prompt listeners, and the request listener applies that same snapshot after downstream request listeners. A selection during asynchronous assembly therefore starts on the next step rather than splitting prompt text from routing. Other call-config fields remain untouched.
+`installModelSelection` (in `dsh-agent`) installs scoped `system-prompt/assemble` and `agent/request` listeners for a front-end-owned selection. Ordinary consumers snapshot the selection once per step. ACP associates its admission snapshot with the identified message in the per-session module until inbox claim, then pins that selection for the complete admitted turn, so asynchronous image admission, prompt variables, and every request step remain aligned without changing the durable user source. A concurrent selection starts on the next ACP turn. Other call-config fields remain untouched.
The request header remains the durable source of truth. When a selection is actually used, the existing full `request/header` snapshot records it, and a front end initializes its selection from the folded last request header before falling back to creation options. A selection that is never used by a request is intentionally in-memory only because it never became model-visible state.
@@ -53,10 +53,10 @@ The request header remains the durable source of truth. When a selection is actu
- Any adapter can expose a dynamic model list without leaking provider-library types into the LLM Service Definition.
- Catalog consumers must treat absence as “not advertised,” never “invalid request.”
- pi-ai adapters expose their installed provider catalogs; hand-written DeepSeek deployments list known choices explicitly and retain arbitrary model support.
-- Human-facing catalog consumers own their selection interaction. ACP uses its fixed deployment target and does not widen the protocol with model discovery.
+- Each catalog consumer owns its selection interaction. ACP uses standard session configuration options and emits no DSH-specific selector or UI metadata.
- Request headers remain compatible with the provider-routed session shape; no new JSONL event or format version is required.
- A catalog read can be asynchronous, and every caller receives detached values.
## Testing
-Unit coverage validates catalog detachment and malformed metadata, pi-ai and DeepSeek catalog projection, provider/model request routing, and prompt-variable alignment; per-agent isolation follows from installing the listeners on the agent-scoped context. ACP transport tests validate fixed provider/model forwarding independently of catalog discovery; the TUI suite covers selector interaction and header-based restoration.
+Unit coverage validates catalog detachment and malformed metadata, pi-ai and DeepSeek catalog projection, provider/model request routing, and prompt-variable alignment; per-agent isolation follows from installing the listeners on the agent-scoped context. ACP tests validate grouped discovery, invalid and concurrent changes, topology updates, header-based restoration, per-turn route pinning, and image-route consistency; human clients test their own selector presentation.
diff --git a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md
index 145fd0bc37..85e9fa35ac 100644
--- a/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md
@@ -4,7 +4,7 @@ Status: implemented
[English](2026-07-15-llm-model-catalog-and-acp-selection.md) | 中文
-> 目录决策仍然有效。ACP(Agent Client Protocol)会话级模型选择已由 [ACP 作为仅面向自动化的协议](../simplification/2026-07-23-acp-automation-only-protocol.md)取代。
+> Catalog 和 scoped selection 决策仍然有效。ACP selection 的暂时移除已由[标准 ACP v1 自动化控制](../feature/2026-08-22-standard-acp-automation-controls.zh.md)取代;后者通过标准会话配置公开 catalog,但不会恢复 UI 投影。
## 问题
@@ -24,17 +24,17 @@ ACP 选择还必须保留提供方维度。同一个模型 ID 可能存在于多
目录成员关系仅提供建议。它驱动选择器与诊断,但不会改变 `stream()` 路由,也不会拒绝原本有效的请求。提供方所有权仍然具有排他性并绑定生命周期;模型 ID 仍是请求时传给适配器的输入。
-`dsh-llm-pi-ai` 将已配置提供方的 `getModels(provider)` 返回的已安装条目映射为提供方无关的目录。其现有请求时目录查询仍是权威依据,未知模型仍以 `UNKNOWN_MODEL` 失败。`dsh-llm-deepseek` 接受包含展示条目的可选 `models` 配置,默认包含名为 `DeepSeek-V4-Flash` 的 `deepseek-v4-flash` 和名为 `DeepSeek-V4-Pro` 的 `deepseek-v4-pro`。显式列表会替换这些默认值,空列表则关闭发现。这些条目改善已知公开或私有模型的选择体验,而所有未列出的模型 ID 仍会原样透传。
+`dsh-llm-pi-ai` 将已配置提供方的 `getModels(provider)` 返回的已安装条目映射为提供方无关的目录。其现有请求时目录查询仍是权威依据,未知模型仍以 `UNKNOWN_MODEL` 失败。`dsh-llm-deepseek` 接受包含展示条目的可选 `models` 配置,默认包含名为 `DeepSeek-V4-Flash` 的 `deepseek-v4-flash`、名为 `DeepSeek-V4-Pro` 的 `deepseek-v4-pro`,以及名为 `DeepSeek-V4-Flash-Vision-Exp`、支持图片输入的 `deepseek-v4-flash-vision-exp`。显式列表会替换这些默认值,空列表则关闭发现。这些条目改善已知公开或私有模型的选择体验,而所有未列出的模型 ID 仍会原样透传。
### 前端内的会话级选择
-选择由提供它的前端拥有(今天是 TUI 的 `/model` 选择器),而不由 `LlmRuntime` 或 `AgentOptions` 拥有:它们是部署级或创建级对象,改动它们会把并发会话耦合在一起。每个不透明选项都携带完整的提供方/模型对,因为同一模型 ID 可能出现在多个路由下。
+选择由提供它的前端拥有,而不由 `LlmRuntime` 或 `AgentOptions` 拥有:它们是部署级或创建级对象,改动它们会把并发会话耦合在一起。每个不透明选项都携带完整的提供方/模型对,因为同一模型 ID 可能出现在多个路由下。
-ACP 自动化传输层不是目录消费方。它通过部署配置为新创建的 agent 提供一个可选的提供方/模型目标,不展示模型选择器或配置选项接口。
+ACP 自动化传输层通过标准会话配置选项消费建议性 catalog。部署配置仍提供初始提供方/模型目标;每个会话拥有一个不透明的提供方/模型选择,以及一个依赖确切模型的 reasoning-effort 选择。Adapter 拓扑变化会公布完整选项状态。Catalog 中缺少条目不会使配置路由失效:当前未列出的路由会合成到选项中。
### 提示词/请求一致性与持久化
-`installModelSelection`(位于 `dsh-agent`)为前端拥有的选择安装 agent 作用域的 `system-prompt/assemble` 与 `agent/request` 监听器。提示词组装在每个步骤对所选组合做一次快照,在下游提示词监听器之后覆写组装出的 `provider` 与 `model` 变量;请求监听器在下游请求监听器之后应用同一快照。因此,发生在异步组装期间的选择会从下一个步骤生效,而不会让提示词文本与路由分裂。其他调用配置字段保持不变。
+`installModelSelection`(位于 `dsh-agent`)为前端拥有的选择安装 agent 作用域的 `system-prompt/assemble` 与 `agent/request` 监听器。普通 consumer 每个步骤快照一次选择。ACP 会在 per-session 模块中把准入快照与已识别消息关联到 inbox claim 时刻,再在完整已准入轮次中固定该选择,使异步图片准入、提示词变量和每个请求步骤保持一致,同时不改变持久用户 source。并发选择变更从下一个 ACP 轮次开始。其他调用配置字段保持不变。
请求头仍是持久化的真源。当某个选择真正被使用时,现有的完整 `request/header` 快照会记录它;前端先从折叠后的最后一个请求头初始化其选择,然后才回退到创建选项。从未被请求使用的选择有意只保留在内存中,因为它从未成为模型可见状态。
@@ -53,10 +53,10 @@ ACP 自动化传输层不是目录消费方。它通过部署配置为新创建
- 任意适配器都能暴露动态模型列表,无需把提供方库类型泄漏到 LLM Service Definition。
- 目录消费方必须把缺失理解为「未展示」,而不是「请求无效」。
- pi-ai 适配器会暴露其已安装的提供方目录;手写 DeepSeek 部署显式列出已知选项,同时保留对任意模型的支持。
-- 面向人类的目录消费方拥有各自的选择交互。ACP 使用固定部署目标,不会为模型发现扩大协议范围。
+- 每个 catalog consumer 拥有自己的选择交互。ACP 使用标准会话配置选项,不发出 DSH 专用 selector 或 UI 元数据。
- 请求头与基于提供方路由的会话形态保持兼容;不需要新的 JSONL 事件或格式版本。
- 目录读取可以是异步的,且每个调用方都会收到值的独立副本。
## 测试
-单元测试覆盖目录值副本与格式错误的元数据、pi-ai 和 DeepSeek 目录投影、提供方/模型请求路由,以及提示词变量对齐;监听器安装在 agent 作用域的上下文中,因此能够实现 agent 间隔离。ACP 传输测试独立验证固定提供方/模型的转发行为;TUI 套件覆盖选择器交互与基于请求头的恢复。
+单元测试覆盖 catalog 值副本与格式错误的元数据、pi-ai 和 DeepSeek catalog 投影、提供方/模型请求路由,以及提示词变量对齐;监听器安装在 agent 作用域的上下文中,因此能够实现 agent 间隔离。ACP 测试覆盖分组发现、无效和并发变更、拓扑更新、基于请求 header 的恢复、逐轮路由固定以及图片路由一致性;人工客户端测试自己的 selector 展示。
diff --git a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml
index aee9c76d55..277e0b097d 100644
--- a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.md
2026-07-15-lsp-capability-seam.md: 90f9daf4b890bd53621916e492d4d82baaa3e8cc
-2026-07-15-lsp-capability-seam.zh.md: b85b478b25a375b04e1301d893e53198554641e3
+2026-07-15-lsp-capability-seam.zh.md: bdb5e812e94a4aec4402fe83ca9c818bfa00f9f9
diff --git a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md
index b85b478b25..bdb5e812e9 100644
--- a/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-15-lsp-capability-seam.zh.md
@@ -79,7 +79,7 @@ interface LspService {
映射键规范化为带前导点的小写扩展名,并按 `filePath` 的最后一个扩展名选择;语言 id 仅用于文档同步。seam 中的位置和范围从零开始按 UTF-16 计数。`findReferences` 始终包含声明:提供方在内部执行该约束,本地映射设置 `context.includeDeclaration: true`,调用方不能配置。封闭结果联合将导航统一为位置,将 `hover` 统一为内容或 `null`;导航结果携带提供方的规范工作区 URI,使消费方在执行世界的命名空间内相对化文件 URI。seam 不公开协议类型、进程或文档控制,也不提供通用请求逃生口。
-`dsh-lsp-stdio` 负责服务器配置、JSON-RPC、进程与临时文档状态和协议转换。它通过 `ctx.fs` 读取,通过 `ctx.subprocess` 启动,只依赖二者的 Service Definition 包而非具体提供方;[可移植执行环境决策](2026-07-28-portable-execution-world-consumers.md)负责定义这种配对。服务器表的键是提供方 id。插件在注册前解析每个服务器的本地设置;如果后续映射无效或发生冲突,插件会撤销此前的注册,并为每个提供方保留独立进程池。`dsh-tool-lsp` 在运行时只注入 `tools`、`lsp` 和 `systemPrompt`,通过包内的 `sessionCwd(exec)` 辅助函数从 `exec.agent?.session.header.cwd` 取得工作区,其取值方式与文件系统工具一致,也不导入提供方。
+`dsh-lsp-stdio` 负责服务器配置、JSON-RPC、进程与临时文档状态和协议转换。它通过 `ctx.fs` 读取,通过 `ctx.subprocess` 启动,只依赖二者的 Service Definition 包而非具体提供方;[可移植执行环境决策](2026-07-28-portable-execution-world-consumers.zh.md)负责定义这种配对。服务器表的键是提供方 id。插件在注册前解析每个服务器的本地设置;如果后续映射无效或发生冲突,插件会撤销此前的注册,并为每个提供方保留独立进程池。`dsh-tool-lsp` 在运行时只注入 `tools`、`lsp` 和 `systemPrompt`,通过包内的 `sessionCwd(exec)` 辅助函数从 `exec.agent?.session.header.cwd` 取得工作区,其取值方式与文件系统工具一致,也不导入提供方。
## 面向模型的约定
diff --git a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml
index 47e7156ab8..6ad1773f6f 100644
--- a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.md
2026-07-15-replay-token-meter-service.md: 10261189fca621b305b3ec6347b54471d81c8ba3
-2026-07-15-replay-token-meter-service.zh.md: 4e460b3c32630f205f447a16205bd4c9b1d89faf
+2026-07-15-replay-token-meter-service.zh.md: 370d3cf932d37702c5298bc79e9dc8f5a37835b9
diff --git a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md
index 4e460b3c32..370d3cf932 100644
--- a/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md
@@ -16,7 +16,7 @@ Status: implemented
`@deepseek-ai/dsh-token-meter` 是 `packages/llm/` 下的单个具体包,并注册 `ctx.tokenMeter`。在第二种实现出现之前,它不会被拆成接口与后端。`TokenMeter` 本身公开 `measure(session, requestHeader?)` 与 `estimateMessage(message)`;消费方直接调用这个单例服务。
-服务没有配置。估算采用固定的每 token 四个字符启发式规则,并加上结构开销。服务不提供模型 profile、容量设置、密度设置、分词器后端或语言专用策略。对精确提供方/模型容量的查询由适配器单独负责,具体见[路由模型上下文与压缩策略 Agent Note](2026-07-20-routed-model-context-and-compaction-policy.md)。
+服务没有配置。估算采用固定的每 token 四个字符启发式规则,并加上结构开销。服务不提供模型 profile、容量设置、密度设置、分词器后端或语言专用策略。对精确提供方/模型容量的查询由适配器单独负责,具体见[路由模型上下文与压缩策略 Agent Note](2026-07-20-routed-model-context-and-compaction-policy.zh.md)。
### 逐会话回放折叠
diff --git a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml
index 342f2073ea..fcca895513 100644
--- a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md
2026-07-16-explicit-turn-cancellation.md: 86faad9929d3eb5b00e66bb1c46a2e35b135d954
-2026-07-16-explicit-turn-cancellation.zh.md: 5397b368628c196efc2b35c00855267246ac6e85
+2026-07-16-explicit-turn-cancellation.zh.md: acf56e0629668a227324045ffd0521619dc45f33
diff --git a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md
index 5397b36862..acf56e0629 100644
--- a/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md
@@ -8,7 +8,7 @@ Status: implemented
取消是一种生命周期短于 Agent(智能体)驱动器的控制能力。自由文本字符串无法完整区分所有调用方,步骤级控制器也无法中断提示词提交、提示词组装、继续决策或轮次终止策略。持久化 `Error`、`AbortSignal.reason` 或后端私有对象还会向持久化回放暴露不稳定的运行时细节。
-[发起 Agent 作用域决策](2026-07-15-agent-initiator-scope.md)有意让 AsyncLocalStorage 只携带同一个 Agent。若把轮次、步骤或 signal 状态加入这个与驱动器同生命周期的边界,陈旧的异步后代就会看似仍对后续轮次拥有权限。因此,取消需要一个轮次归属方并显式传播,且不创建另一套环境上下文或公开的轮次包装层。
+[发起 Agent 作用域决策](2026-07-15-agent-initiator-scope.zh.md)有意让 AsyncLocalStorage 只携带同一个 Agent。若把轮次、步骤或 signal 状态加入这个与驱动器同生命周期的边界,陈旧的异步后代就会看似仍对后续轮次拥有权限。因此,取消需要一个轮次归属方并显式传播,且不创建另一套环境上下文或公开的轮次包装层。
## 决策
@@ -18,9 +18,9 @@ Agent 拥有仅用于运行时的 `AgentCancelCause` 联合类型 `{ kind: 'user
AgentLoop 为每个待启动轮次私有地持有一个 `TurnCancellation`。它在通知 `agent/status = running` 前安装该持有者,使其中唯一的 `AbortController` 持续覆盖 inbox 领取、`agent/pre-step`、提示词组装、每个步骤、模型与工具执行以及 `agent/turn-stopping`;随后在发布 `turn/end` 前立即清除所安装的那个持有者。因此,即使驱动器状态可能在持久化刷新结算前保持 `running`,终态事件观察者及其后的持久化刷新也无法取消已完成的轮次工作。所有参与的方法、事件和请求值都会收到同一个显式 signal;下一个轮次会收到全新的 signal。
-对于轮次被认领前已取消的排队工作,驱动器只保留一个不携带取消原因的运行前标记。实际生效的 `cancel()` 会先发出仅供观察的 `agent/cancel-requested` 通知并携带最终确定的类型化取消原因,然后才清除排队工作和 steering(中途引导)工作或中止持有者;通知失败不能阻止此次停止,空闲状态下调用则不发出任何通知。通知观察者同步加入队列的工作也会被这次清除,而稍后由 signal 中止观察者加入队列的工作会被锁存,并在被中止的活动收敛到空闲时执行——`disposed` 取消则将其停放([取消收敛窗口唤醒锁存](../bug-fix/2026-08-07-cancel-convergence-wake-latch.md))。若 `running` 监听器同步取消旧工作并发送替代提示词,驱动器会丢弃已中止的持有者,并为替代提示词创建全新的持有者。同一活跃持有者上的重复取消遵循首次请求优先,后续调用仍可清除新入队的待处理工作。
+对于轮次被认领前已取消的排队工作,驱动器只保留一个不携带取消原因的运行前标记。实际生效的 `cancel()` 会先发出仅供观察的 `agent/cancel-requested` 通知并携带最终确定的类型化取消原因,然后才清除排队工作和 steering(中途引导)工作或中止持有者;通知失败不能阻止此次停止,空闲状态下调用则不发出任何通知。通知观察者同步加入队列的工作也会被这次清除,而稍后由 signal 中止观察者加入队列的工作会被锁存,并在被中止的活动收敛到空闲时执行——`disposed` 取消则将其停放([取消收敛窗口唤醒锁存](../bug-fix/2026-08-07-cancel-convergence-wake-latch.zh.md))。若 `running` 监听器同步取消旧工作并发送替代提示词,驱动器会丢弃已中止的持有者,并为替代提示词创建全新的持有者。同一活跃持有者上的重复取消遵循首次请求优先,后续调用仍可清除新入队的待处理工作。
-显式事件签名传递单个 payload 对象:agent 作用域事件在 payload 中携带 `agent` 和 `signal`,`next` 位于最后;其余 API 保持 `signal` 紧邻 waterfall(瀑布式事件)的最终 `next` 之前。`PreStepContext` 与 `RequestFailureContext` 已退役,其字段并入 `agent/pre-step` 与 `agent/request-error` 的 payload([payload-object 事件](2026-08-06-agent-event-payload-objects.md))。进入 pre-step 时、请求配置、请求错误恢复、模型生成、工具执行、审批、轮次停止以及 subagent 或工作流请求都会收到当前 signal。钩子桥接器也必须提供 `RunHookOptions.signal`,使轮次取消能够到达 Bash 执行器终止进程组并等待其退出的边界。`SystemPrompt.assemble()` 在 `AssembleContext` 中携带 `signal?: AbortSignal`,因为该对象是显式请求值,也可表示轮次之外不携带 signal 的组装。监听器可以配合该 signal 取消,但不得保留它来控制其他轮次。
+显式事件签名传递单个 payload 对象:agent 作用域事件在 payload 中携带 `agent` 和 `signal`,`next` 位于最后;其余 API 保持 `signal` 紧邻 waterfall(瀑布式事件)的最终 `next` 之前。`PreStepContext` 与 `RequestFailureContext` 已退役,其字段并入 `agent/pre-step` 与 `agent/request-error` 的 payload([payload-object 事件](2026-08-06-agent-event-payload-objects.zh.md))。进入 pre-step 时、请求配置、请求错误恢复、模型生成、工具执行、审批、轮次停止以及 subagent 或工作流请求都会收到当前 signal。钩子桥接器也必须提供 `RunHookOptions.signal`,使轮次取消能够到达 Bash 执行器终止进程组并等待其退出的边界。`SystemPrompt.assemble()` 在 `AssembleContext` 中携带 `signal?: AbortSignal`,因为该对象是显式请求值,也可表示轮次之外不携带 signal 的组装。监听器可以配合该 signal 取消,但不得保留它来控制其他轮次。
`ctx.agents` 仍只携带发起 Agent。环境中的 Agent 并不代表存活、当前轮次或取消权限。cause 读取器是 loop 私有的,它直接陈述机器私有的 slot 不变量(只有 `cancel()` 会中止轮次控制器,且总是携带规范的冻结 cause),而不是对 reason 做结构化再校验;不存在从任意 signal 读取 cause 的公开辅助函数。并发 Agent 会同时隔离各自的发起方身份和轮次 signal;子驱动会遮蔽父发起方,而父请求 signal 仍通过 subagent seam 传递。
diff --git a/.agents/notes/implemented/architecture/2026-07-17-local-spill-startup-cleanup.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-17-local-spill-startup-cleanup.i18n.yaml
new file mode 100644
index 0000000000..06f4d81cb0
--- /dev/null
+++ b/.agents/notes/implemented/architecture/2026-07-17-local-spill-startup-cleanup.i18n.yaml
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# 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/implemented/architecture/2026-07-17-local-spill-startup-cleanup.md
+2026-07-17-local-spill-startup-cleanup.md: fc64938c1af07d9dd0d7ecec379115d22d1e2464
+2026-07-17-local-spill-startup-cleanup.zh.md: 583a33ead84f552c67e2e770a8b3fabc3ce88120
diff --git a/.agents/notes/implemented/architecture/2026-07-17-local-spill-startup-cleanup.md b/.agents/notes/implemented/architecture/2026-07-17-local-spill-startup-cleanup.md
new file mode 100644
index 0000000000..fc64938c1a
--- /dev/null
+++ b/.agents/notes/implemented/architecture/2026-07-17-local-spill-startup-cleanup.md
@@ -0,0 +1,37 @@
+# Agent Note: One-shot startup cleanup for local spill files
+
+Status: implemented
+
+English | [中文](2026-07-17-local-spill-startup-cleanup.zh.md)
+
+## Problem
+
+The local spill backend never deleted the full tool results it wrote. Every oversized result added another file, so configured roots grew without bound and default per-process `dsh-spill-*` roots accumulated across runs. Immediate deletion is wrong because persisted, resumed, and forked sessions may still reference a locator. The [tool output spill policy](./2026-07-08-tool-output-spill-files.md) needs a bounded local-storage lifetime.
+
+## Decision
+
+`dsh-spill-local` runs one best-effort cleanup sweep after activation. It does not delay service availability, is owned by the plugin fiber (a single `ctx.effect` whose generator launches the sweep and yields an async disposer that awaits it), and is awaited during disposal so no sweep I/O outlives the fiber. There is no recurring timer and no separate process.
+
+A `cleanupPeriodDays` config defaults to `30`; `0` disables cleanup. Schemastery rejects a negative or fractional value at load. The sweep scans the configured/active root plus any prior default `dsh-spill-*` temp roots discovered under the OS temp dir and deletes regular files whose `mtime` is strictly older than `now − cleanupPeriodDays`. It prunes every empty session directory but removes the root itself only for a discovered prior-default root; writes recreate a session directory if pruning races them. Root aliases are de-duplicated by device/inode identity, with the configured identity overriding a discovered match as active and non-prunable. It uses `lstat`, so a symlink is never followed or deleted; unrelated entries (non-`session-` directories, special files) are skipped. Every filesystem failure is caught and logged through `ctx.logger.warn`, and a warning-sink exception is also contained — the sweep never throws, so it cannot reject activation or a concurrent spill write.
+
+Path-based deletion is restricted to directories an untrusted local OS user cannot replace during the scan. On POSIX, every root and session directory must be owned by the current user and not writable by group or others; the root's ancestor path must also be non-writable or protected by a sticky directory such as `/tmp`. Discovery rejects symlinks, while a configured symlink may resolve to a trusted target and participates in identity de-duplication. An unsafe path is skipped with a warning. The same-user account remains the trust boundary, consistent with the backend's private local-storage model.
+
+The ctx-free sweep mechanics live in `packages/spill/spill-local/src/cleanup.ts` (`sweepSpillRoots`, `discoverDefaultRoots`), unit-testable without a `ctx`; `store.ts` owns root naming, path derivation, and writes, while the service in `src/index.ts` owns the config, cutoff, and fiber-owned launch/await.
+
+## Alternatives considered
+
+**Run a periodic timer.** Rejected because it adds timer lifecycle, overlap control, and another interval knob. A long-lived process may retain files until restart.
+
+**Delete spills on session disposal.** Rejected because durable sessions, resumes, and forks retain locators.
+
+**Delete old session directories recursively.** Rejected because a concurrent process may create a fresh spill after the age check. Per-file expiry preserves fresh writes.
+
+**Tie cleanup to session-persistence deletion.** Rejected because the persistence seam has no common deletion lifecycle, while the local backend also owns independent temporary roots.
+
+## Consequences
+
+Cleanup cost the backend a startup sweep and a config knob, and bought a bounded local-storage lifetime without a timer, a daemon, or a session-lifecycle coupling. Concurrent processes may duplicate startup I/O; strict filtering and idempotent file deletion keep this safe. A long-lived process is not cleaned again until restart, and retention deliberately makes old model-visible locators stale only once they age past the cutoff. The seam itself still defines no retention policy — this is a local-backend concern.
+
+## Testing
+
+`dsh-spill-local` unit tests cover the exact age boundary, `cleanupPeriodDays: 0` disabling, empty-session and discovered-root pruning, symlink/unrelated-entry skipping, configured-plus-discovered-root coverage, filesystem-identity de-duplication through a configured symlink, unsafe POSIX root/session rejection, load-time config validation, filesystem- and warning-sink-failure containment, and the quiescence contract. A separate test boots the plugin through the real Loader and a cordis.yml, then observes configured expiry and directory pruning after disposal.
diff --git a/.agents/notes/implemented/architecture/2026-07-17-local-spill-startup-cleanup.zh.md b/.agents/notes/implemented/architecture/2026-07-17-local-spill-startup-cleanup.zh.md
new file mode 100644
index 0000000000..583a33ead8
--- /dev/null
+++ b/.agents/notes/implemented/architecture/2026-07-17-local-spill-startup-cleanup.zh.md
@@ -0,0 +1,37 @@
+# Agent Note: 本地 spill 文件的一次性启动清理
+
+Status: implemented
+
+[English](2026-07-17-local-spill-startup-cleanup.md) | 中文
+
+## 问题
+
+本地 spill 后端从不删除它写下的完整工具结果。每个超限结果都会新增一个文件,因此配置的根目录会无限增长,而每进程默认的 `dsh-spill-*` 根目录也会跨多次运行不断累积。立即删除是错误的,因为已持久化、已恢复和已 fork 的会话仍可能引用某个 locator。[工具输出 spill 策略](./2026-07-08-tool-output-spill-files.zh.md)需要一个有界的本地存储生命周期。
+
+## 决策
+
+`dsh-spill-local` 在激活后运行一次尽力而为的清理扫描。它不延迟服务可用性,由插件 fiber 拥有(一个 `ctx.effect`,其生成器启动该扫描并让出一个等待它的异步 disposer),并在 dispose 期间被等待,因此没有扫描 I/O 会存活到 fiber 之后。既没有周期性定时器,也没有独立进程。
+
+`cleanupPeriodDays` 配置默认为 `30`;`0` 会禁用清理。Schemastery 会在加载时拒绝负数或小数。扫描会遍历配置的/活动的根目录,以及在 OS 临时目录下发现的任何先前默认 `dsh-spill-*` 临时根目录,并删除 `mtime` 严格早于 `now − cleanupPeriodDays` 的常规文件。它会修剪所有空会话目录,但只删除发现的先前默认根目录本身;如果修剪与写入发生竞争,写入操作会重新创建会话目录。根目录别名按设备/inode 身份去重,配置目录的身份会覆盖发现的匹配项,并标记为活动且不可删除。扫描使用 `lstat`,因此符号链接绝不会被跟随或删除;无关条目(非 `session-` 目录、特殊文件)会被跳过。每一次文件系统失败都会被捕获并通过 `ctx.logger.warn` 记录,警告接收方抛出的异常也会被兜底——扫描绝不抛出,因此它无法让激活失败,也无法影响并发的 spill 写入。
+
+基于路径的删除仅限于不受信任的本地 OS 用户无法在扫描期间替换的目录。在 POSIX 上,每个根目录和会话目录都必须由当前用户拥有,且组用户和其他用户不可写;根目录的祖先路径也必须不可写,或由 `/tmp` 这类 sticky 目录保护。发现过程拒绝符号链接,而配置的符号链接可以解析到可信目标并参与身份去重。不安全路径会被跳过并记录警告。与后端的私有本地存储模型一致,同一用户账号仍是信任边界。
+
+无 ctx 依赖的扫描机制位于 `packages/spill/spill-local/src/cleanup.ts`(`sweepSpillRoots`、`discoverDefaultRoots`),无需 `ctx` 即可做单元测试;`store.ts` 负责根目录命名、路径推导与写入,而 `src/index.ts` 中的服务负责配置、截止时间以及 fiber 拥有的启动/等待。
+
+## 考虑过的替代方案
+
+**运行周期性定时器。** 已否决,因为它引入了定时器生命周期、重叠控制以及又一个间隔旋钮。长期运行的进程可能会保留文件直到重启。
+
+**在会话 dispose 时删除 spill。** 已否决,因为持久会话、恢复和 fork 都会保留 locator。
+
+**递归删除旧的会话目录。** 已否决,因为并发进程可能在年龄检查之后创建一个新的 spill。按文件过期可保留新写入。
+
+**将清理绑定到会话持久化删除。** 已否决,因为持久化 seam 没有共同的删除生命周期,而本地后端还独立拥有临时根目录。
+
+## 后果
+
+清理让后端付出了一次启动扫描和一个配置旋钮的代价,换来了无需定时器、守护进程或会话生命周期耦合的有界本地存储生命周期。并发进程可能重复启动 I/O;严格的过滤与幂等的文件删除保证了这一点的安全。长期运行的进程在重启前不会再次被清理,而这种保留是刻意的——旧的模型可见 locator 只有在超过截止时间后才会失效。seam 本身仍不定义任何保留策略——这是本地后端的关切。
+
+## 验证
+
+`dsh-spill-local` 单元测试覆盖了精确年龄边界、`cleanupPeriodDays: 0` 的禁用、空会话目录与发现根目录的修剪、符号链接/无关条目的跳过、配置根加发现根的覆盖、经配置符号链接验证的文件系统身份去重、不安全 POSIX 根目录/会话目录拒绝、加载期配置校验、文件系统与警告接收方故障兜底,以及静止契约。另一个测试会通过真实 Loader 和 cordis.yml 启动插件,并在 dispose 后观察按配置执行的过期与目录修剪。
diff --git a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml
index e772ff9036..29807cfb7c 100644
--- a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.i18n.yaml
@@ -3,4 +3,4 @@
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md
2026-07-19-cooperative-tool-cancellation.md: 781202688a5cbcd7076ee694fc7dd9489683d8e8
-2026-07-19-cooperative-tool-cancellation.zh.md: a5ce2e671e92f4758ddeb3d3556d8af574467f7f
+2026-07-19-cooperative-tool-cancellation.zh.md: ec35734eef91c5c774d1be814b221e9fdb8f65fa
diff --git a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md
index a5ce2e671e..ec35734eef 100644
--- a/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.zh.md
@@ -42,7 +42,7 @@ Status: implemented
工具主体一旦启动,注册表就会等待它完成。取消通过融合信号到达工具主体,但注册表不会与其 promise 竞速或丢弃该 promise。协作式实现会停止自身工作或继续转发取消,并在所持有的工作完全停稳后完成;不协作的同进程实现可能让注册表无限期保持等待。进程、worker、网络和提供方层仍负责各自的终止机制。
-这项决策只要求工具调用边界携带取消信号。让工具主体可达的异步能力也必须接收信号,属于另一项迁移,见提议中的[工具可达能力 seam 中的必填取消](../../proposed/architecture/2026-07-19-required-cancellation-through-tool-capability-seams.md)。
+这项决策只要求工具调用边界携带取消信号。让工具主体可达的异步能力也必须接收信号,属于另一项迁移,见提议中的[工具可达能力 seam 中的必填取消](../../proposed/architecture/2026-07-19-required-cancellation-through-tool-capability-seams.zh.md)。
## 验证
@@ -62,7 +62,7 @@ Status: implemented
**禁止环绕包装层替换信号。** 不予采纳,因为截止时间和嵌套操作作用域需要词法派生信号。捕获并融合调用方信号既保留组合能力,也不允许切断调用方取消。
-**让工具 promise 与取消竞速。** 不予采纳,因为这种方式会在副作用仍可能存活时报告完成,违反[dispose(资源释放)必须完全停稳的规则](../../../../docs/defensive-patterns.md#dispose-must-reach-quiescence-not-just-request-it)。
+**让工具 promise 与取消竞速。** 不予采纳,因为这种方式会在副作用仍可能存活时报告完成,违反[dispose(资源释放)必须完全停稳的规则](../../../../docs/defensive-patterns.zh.md#dispose-must-reach-quiescence-not-just-request-it)。
## 后果
diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml
index b864b41f76..38e07804b7 100644
--- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.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/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md
-2026-07-19-gui-layering-and-rpc-protocol.md: 620803668e88f5a462ab2a75e6e916a85d433ed6
-2026-07-19-gui-layering-and-rpc-protocol.zh.md: 8145b6e5af149f79b45e03c80aeea90da90b3729
+2026-07-19-gui-layering-and-rpc-protocol.md: 372bf4926011835999ebae9b1e2d1f5beb8eb663
+2026-07-19-gui-layering-and-rpc-protocol.zh.md: ecce57c01c155c2a0b19b7729da13c39d1a520a6
diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md
index 620803668e..372bf49260 100644
--- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md
+++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md
@@ -209,7 +209,7 @@ The same domain tree as `ApiProxy`, but unary methods **take the business payloa
### The instance-level envelope observation aspect
-All four quadrant full forms pass through `onEnvelope`; the base implementation is an **instance-owned microtask-batched buffer** (frame storms must not disturb consumers per frame; module-level state would leak across instances/tests, hence instance-owned). Observers subscribe via `subscribeEnvelopes(listener)` (receiving whole batches as `readonly RpcMessage[]`, returning an unsubscribe function); a listener throw is isolated (observation must never bite the carrier). With no subscribers the buffering costs nothing. No shipped consumer subscribes today — the aspect is the designated seat for wire diagnostics (the retired RPC debug panel was its first consumer, and a future one plugs in without touching the carrier).
+All four quadrant full forms pass through `onEnvelope`; the base implementation is an **instance-owned microtask-batched buffer** (frame storms must not disturb consumers per frame; module-level state would leak across instances/tests, hence instance-owned). Observers subscribe via `subscribeEnvelopes(listener)` (receiving whole batches as `readonly RpcMessage[]`, returning an unsubscribe function); a listener throw is isolated (observation must never bite the carrier). With no subscribers the buffering costs nothing. No shipped consumer subscribes — the aspect is the designated seat for wire diagnostics (the retired RPC debug panel was its first consumer, and a future one plugs in without touching the carrier).
### The subclass table (transport carriage)
diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md
index 8145b6e5af..ecce57c01c 100644
--- a/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.zh.md
@@ -4,7 +4,7 @@ Status: implemented
[English](2026-07-19-gui-layering-and-rpc-protocol.md) | 中文
-> 分工线:本篇 = 分层模型 + 通道无关的 RPC 协议;协议的 Web 实现由 HTTP 上行加 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.md)组成,浏览器对象层见 [Web 客户端架构笔记](2026-07-19-gui-web-client-architecture.md)。
+> 分工线:本篇 = 分层模型 + 通道无关的 RPC 协议;协议的 Web 实现由 HTTP 上行加 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.zh.md)组成,浏览器对象层见 [Web 客户端架构笔记](2026-07-19-gui-web-client-architecture.zh.md)。
## Problem
@@ -23,13 +23,13 @@ Status: implemented
目录按照如下分层:
- `packages/host/*`:包只提供 Host 侧能力(代表了以现在 Harness 实体插件系统为主体的 Node.js 代码核心工程),除此之外,还包含
- 统一后端协议(fetch、HTTP、流式接口等)定义和支持,见本篇「消息协议」起各节
-- `packages/client/*`:包只提供 Client 侧能力,每包单边不混。这里住三类包(两条轴归 [client 插件装载笔记](2026-07-23-client-plugin-loading-model.md) 所有):
+- `packages/client/*`:包只提供 Client 侧能力,每包单边不混。这里住三类包(两条轴归 [client 插件装载笔记](2026-07-23-client-plugin-loading-model.zh.md) 所有):
- **纯库**(`ui-slots`、`ui-primitives`,外加内核包 `loader`):普通根入口包,静态打包进壳;两个客户端库播种进模块表。
- **静态到达 entry 包**(`connection`、`runtime`、`ui-theme`、`i18n`、`hmr`):无 `dsh.client` 键、无浏览器 bundle——壳把它们的 `src/client/` 半边打进自己的 bundle 并向 `ctx.modules` 登记;它们与其余单元一样,作为 host 独家撰写的图里的 entry 受治理。
- **fetch 到达插件包**(`ui-layout`、`ui-sidebar`、`ui-conversation`、`ui-trajectory`):双入口——根入口是 node 半边(空 `apply`,其存在是为了让 host Loader 管辖生命周期、让 web 插件注册表发现 package.json 的 `dsh.client` 声明);实现住在 `src/client/` 下,经 `./client` 子路径发布(tsdown 闭包工厂 bundle)。跨插件消费 `/client` 只限类型;值层面的协作走 cordis 服务。
- `apps/` 作为对外导出的应用入口,可以由 Client / Host 混合组装。
- `apps/web`(`dsh-web-frontend`)是 vite 应用:`dsh-client-web` 导出的壳 API 之上的一层薄 `main.ts`。
- - `apps/cli`(`@deepseek-ai/dsh`)分发命令:`dsh web` = Host + webserver + 构建出的 `dsh-web-frontend` dist;`dsh --profile headless` = [直接使用核心 Agent/Session 的入口](2026-08-09-headless-direct-core-entry-point.md),不含 Host、HTTP 或浏览器层。
+ - `apps/cli`(`@deepseek-ai/dsh`)分发命令:`dsh web` = Host + webserver + 构建出的 `dsh-web-frontend` dist;`dsh --profile headless` = [直接使用核心 Agent/Session 的入口](2026-08-09-headless-direct-core-entry-point.zh.md),不含 Host、HTTP 或浏览器层。
- 将来的 Electron 应用经由 IPC fetch 载体复用同一套 web client 包。
```
@@ -50,9 +50,9 @@ harness core packages ──────────────────┘
- `runtime → apiproxy` 单向;apiproxy 仅依赖类型定义。
- client 侧包**永不 import** host 侧包的运行时(只吃 `/api`、`/client` 两个浏览器安全子路径)。
- `webserver` 不依赖 `runtime`:它提供 `{ fetch }` 特定实现 ——「webserver ← runtime」只是运行时注入关系,不是包依赖。
-- client 侧跨包 import 插件包一律走 `/client` 子路径,且插件包之间只限类型 import——跨插件值 import 在 tsdown 纯度门禁处即构建错误(值层面的协作走 cordis 服务;边规则归 [client 插件装载笔记](2026-07-23-client-plugin-loading-model.md) 所有)。
+- client 侧跨包 import 插件包一律走 `/client` 子路径,且插件包之间只限类型 import——跨插件值 import 在 tsdown 纯度门禁处即构建错误(值层面的协作走 cordis 服务;边规则归 [client 插件装载笔记](2026-07-23-client-plugin-loading-model.zh.md) 所有)。
-TypeScript 以 solution 根引用的**两个聚合 program** 检查(`tsconfig.json` = solution;`tsconfig.host.json` = host 侧 + 测试,排除 `packages/client`;`tsconfig.client.json` = client 各包及其测试):两侧在相同键(`sessions`、`loader`)下以不同服务合并 cordis `Context` 接口,单一 program 会同时看到两份声明合并而报冲突。共享叶子包(session/llm/tools/apiproxy 等)只构建一次,由两个 program 共同引用([拓扑](../process/2026-07-22-tsconfig-solution-root-two-aggregates.md))。
+TypeScript 以 solution 根引用的**两个聚合 program** 检查(`tsconfig.json` = solution;`tsconfig.host.json` = host 侧 + 测试,排除 `packages/client`;`tsconfig.client.json` = client 各包及其测试):两侧在相同键(`sessions`、`loader`)下以不同服务合并 cordis `Context` 接口,单一 program 会同时看到两份声明合并而报冲突。共享叶子包(session/llm/tools/apiproxy 等)只构建一次,由两个 program 共同引用([拓扑](../process/2026-07-22-tsconfig-solution-root-two-aggregates.zh.md))。
协议侧:TS interface(`packages/host/apiproxy/src/api/`,零 Node 依赖,浏览器可 import);wire 消息统一为**双向模型**——每条逻辑消息按「谁发起 × request/response」分类(两轴四格,后文称四象限),与物理通道解耦;客户端统一继承 `AbstractApiClient`(协议不变量全在基类,平台差异只是 `doFetch` 传输切面)。
@@ -167,7 +167,7 @@ export type ResponseValue =
### 帧(server→client,具名 union)
-两条逻辑流:mux 流(`/api/events.mux`,全 session 聚合)与 host 流(`/api/events.host`,host 级事件)。浏览器通过每流一条下行 WebSocket 消费,进程内 fetch 载体以 SSE 保持同构;物理边界见 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.md)。帧示例一行:
+两条逻辑流:mux 流(`/api/events.mux`,全 session 聚合)与 host 流(`/api/events.host`,host 级事件)。浏览器通过每流一条下行 WebSocket 消费,进程内 fetch 载体以 SSE 保持同构;物理边界见 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.zh.md)。帧示例一行:
| 帧 type | 载荷 | 何时发 |
|---|---|---|
@@ -207,14 +207,14 @@ export type ResponseValue =
### 实例级 envelope 观测切面
-四象限全形均过 `onEnvelope`;基类实现是**实例持有的微任务合批缓冲**(帧风暴不逐帧惊扰消费方;模块级状态会跨实例/测试泄漏,故实例持有)。观测者经 `subscribeEnvelopes(listener)` 订阅(收整批 `readonly RpcMessage[]`,返回退订函数);listener 抛异常被隔离(观测不得反噬载体)。无订阅者时零缓冲成本。当前没有任何现役消费方订阅——该切面是 wire 诊断的预留位(已退役的 RPC 调试面板是它的首个消费方,将来的诊断消费方接入时不动载体)。
+四象限全形均过 `onEnvelope`;基类实现是**实例持有的微任务合批缓冲**(帧风暴不逐帧惊扰消费方;模块级状态会跨实例/测试泄漏,故实例持有)。观测者经 `subscribeEnvelopes(listener)` 订阅(收整批 `readonly RpcMessage[]`,返回退订函数);listener 抛异常被隔离(观测不得反噬载体)。无订阅者时零缓冲成本。没有任何已交付消费方订阅——该切面是 wire 诊断的预留位(已退役的 RPC 调试面板是它的首个消费方,将来的诊断消费方接入时不动载体)。
### 子类表(传输承载)
| 子类 | 所在包 | doFetch | 用途 |
|---|---|---|---|
| `InProcessApiClient` | apiproxy 本包 | 注入的 `{ fetch }` handler | **同构点**:`new InProcessApiClient(toFetchHandler(api))` 全程不过网络但真跑 wire 序列化/zod/SSE 帧;载体测试与调用方可以在不打开端口的情况下运行这套协议,而产品 `dsh --profile headless` 直接驱动 core |
-| `WebApiClient` | dsh-client-connection | `globalThis.fetch` 上行 + 每逻辑流一条同源 WebSocket 下行 | 浏览器客户端;物理边界见 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.md) |
+| `WebApiClient` | dsh-client-connection | `globalThis.fetch` 上行 + 每逻辑流一条同源 WebSocket 下行 | 浏览器客户端;物理边界见 [WebSocket 下行载体](2026-08-04-websocket-downlink-carrier.zh.md) |
| `FixtureApiClient` | dsh-client-connection | 不用(协议层覆写) | 无 server 的 UI 开发(`?fixture`):覆写 `callUnary`/`openMux`/`openHost`/`respond` 虚方法,自己就是假 server(帧 rpcId 由它 mint,语义自洽) |
| IPC 桥子类(假想示例——尚无此形态) | Electron 壳 | IPC 序列化往返 | 只需换 doFetch,约定/基类零改 |
diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.i18n.yaml
index 2d5aaa3a25..b80381f031 100644
--- a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.i18n.yaml
+++ b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.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/implemented/architecture/2026-07-19-gui-web-client-architecture.md
-2026-07-19-gui-web-client-architecture.md: 8b4f940299cbba78d403c34b1e5fc9740e44f2c2
-2026-07-19-gui-web-client-architecture.zh.md: a86f9d6f71bed0ce147ffee39bd921037d6c1c4c
+2026-07-19-gui-web-client-architecture.md: 4448fd5c6871d67b30b71cfe4377682639704235
+2026-07-19-gui-web-client-architecture.zh.md: e8a8121a1a495db7f5392e288f3bcada92c70495
diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md
index 8b4f940299..4448fd5c68 100644
--- a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md
+++ b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.md
@@ -48,7 +48,7 @@ There is no component registration model besides slots — the former view and t
**Scope addressing** mirrors the host's agent-scope idiom: services are root singletons whose methods take no sessionId — they read the caller's scope mark (`scopeOf(ctx)`). Inside a session scope, `ctx.conversation.send('hi', 'queue')` targets that session; cross-session calls re-target by switching ctx (`ctx.sessions.scope(id)!.conversation.send(...)`); calling a scoped method from root ctx throws. Client session scopes are minted like host agent scopes (a no-op plugin fiber + a scope-key extend), built lazily on first viewing and torn down only when the session is removed and unwatched — host-session death alone does not tear a scope (it freezes into a read-only viewport).
-## The data object layer (`packages/client/runtime/src/client/sessions/`)
+## The data object layer (`packages/api/session-controller/src/client/`)
Frames enter, snapshots exit, the Conversation assembler sits between — React-free (zero React imports, grep-assertable):
diff --git a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.zh.md b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.zh.md
index a86f9d6f71..e8a8121a1a 100644
--- a/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.zh.md
+++ b/.agents/notes/implemented/architecture/2026-07-19-gui-web-client-architecture.zh.md
@@ -4,7 +4,7 @@ Status: implemented
[English](2026-07-19-gui-web-client-architecture.md) | 中文
-> 分工线:通道无关的分层模型与 RPC 协议(消息模型/类型体系/约定面/客户端基类)见 [分层与 RPC 协议笔记](2026-07-19-gui-layering-and-rpc-protocol.md);本篇 = 浏览器侧:client cordis 树如何装载、UI 插件如何经 slot 与服务组合、React-free 对象层如何以不可变快照供给 React。
+> 分工线:通道无关的分层模型与 RPC 协议(消息模型/类型体系/约定面/客户端基类)见 [分层与 RPC 协议笔记](2026-07-19-gui-layering-and-rpc-protocol.zh.md);本篇 = 浏览器侧:client cordis 树如何装载、UI 插件如何经 slot 与服务组合、React-free 对象层如何以不可变快照供给 React。
## Problem
@@ -30,25 +30,25 @@ Status: implemented
## client cordis 树与装载链
-装载链——两类包(普通包 vs dsh.client 插件)、模块系统/插件治理器之分、host 独家撰写的带修订号 entry 图之上的双阶段 boot、热重载——归 [client 插件装载笔记](2026-07-23-client-plugin-loading-model.md) 所有。本篇赖以立足的事实:浏览器启动与 host 相同的 vendored `@cordisjs/plugin-loader`,由 client 模块系统(`ctx.modules`,`packages/client/modules`)填上其 `internal` 约定;凡带产品行为的单元都是 host 独家撰写的 `__DSH_BOOT__` 图里的 entry——每个生产插件包(含基础设施)都携带 `dsh.client` 声明、以 fetch 到达的 `./client` tsdown 闭包 bundle 供给,`immediately` 行的差别仅在 boot 第一阶段预取,而普通包(react 家族、cordis、尚未升格的库)保持打进壳、已播种、对图不可见;bundle 执行 `window.__ModuleLoader__.load({ id, factory })`,其 `require` 由 lazy CJS 模块表应答(种子词条 + 已登记工厂,首次 require 时物化并记忆化——跨插件值 import 是构建错误,协作走 cordis 服务);全局样式与 CSS Modules 都内联在其持有插件的 bundle 中,物化时注入为 `