diff --git a/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml new file mode 100644 index 0000000000..f64a48f00f --- /dev/null +++ b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.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/architecture/2026-07-22-tui-interactive-extension-service.md +2026-07-22-tui-interactive-extension-service.md: e523361ceb920d2848369d7d3cf1093765d296d4 +2026-07-22-tui-interactive-extension-service.zh.md: 23c46f6bc18d576912aaa648b26877873ea60eda diff --git a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md rename to .agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.md index 86cb397483..e523361ceb 100644 --- a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md +++ b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.md @@ -1,6 +1,7 @@ # Agent Note: Effect-owned TUI interactive extensions Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-22-tui-interactive-extension-service.zh.md) diff --git a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.zh.md b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.zh.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.zh.md rename to .agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.zh.md index d53f526a07..23c46f6bc1 100644 --- a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.zh.md +++ b/.agents/notes/archived/architecture/2026-07-22-tui-interactive-extension-service.zh.md @@ -1,6 +1,7 @@ # Agent Note: 由 effect 持有的 TUI 交互扩展 Status: implemented +Archived: 2026-08-04 [English](2026-07-22-tui-interactive-extension-service.md) | 中文 diff --git a/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.i18n.yaml b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.i18n.yaml new file mode 100644 index 0000000000..0d20a831f8 --- /dev/null +++ b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.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/architecture/2026-07-27-tui-chat-channel-module-split.md +2026-07-27-tui-chat-channel-module-split.md: 3cf9548d4d9d1b845bee5f7137d79a490827b082 +2026-07-27-tui-chat-channel-module-split.zh.md: d5de02bd0f7090c24ccfc5dabbbadff9ff42174e diff --git a/.agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.md b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.md rename to .agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.md index 56b345b670..3cf9548d4d 100644 --- a/.agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.md +++ b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.md @@ -1,6 +1,7 @@ # Agent Note: dsh-tui chat channel module split Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-tui-chat-channel-module-split.zh.md) diff --git a/.agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.zh.md b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.zh.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.zh.md rename to .agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.zh.md index d74844a762..d5de02bd0f 100644 --- a/.agents/notes/implemented/architecture/2026-07-27-tui-chat-channel-module-split.zh.md +++ b/.agents/notes/archived/architecture/2026-07-27-tui-chat-channel-module-split.zh.md @@ -1,6 +1,7 @@ # Agent Note: dsh-tui 聊天通道模块拆分 Status: implemented +Archived: 2026-08-04 [English](2026-07-27-tui-chat-channel-module-split.md) | 中文 diff --git a/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.i18n.yaml b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.i18n.yaml new file mode 100644 index 0000000000..135a8442d2 --- /dev/null +++ b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.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/architecture/2026-07-28-consolidated-tui-presentation.md +2026-07-28-consolidated-tui-presentation.md: c772985a11bc61c2bfcbb4422cae219966246163 +2026-07-28-consolidated-tui-presentation.zh.md: c96fd105bc4ff6632017b16a8b7a0e8f448449bd diff --git a/.agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.md b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.md similarity index 96% rename from .agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.md rename to .agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.md index f87d543a69..c772985a11 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.md +++ b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.md @@ -1,6 +1,7 @@ # Agent Note: Consolidated TUI presentation and navigation Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-28-consolidated-tui-presentation.zh.md) @@ -26,7 +27,7 @@ A tool card has one colored `Tool / ` status header over one dim body. Pre Injected context renders as prose in `ContextCardComponent`, not through the XML tree renderer. Exact matched outer `` lines are stripped, but mismatched, unpaired, or inline tag-like text remains verbatim. Model-facing content is unchanged. Folding uses the shared `preview` helper after body assembly, so it depends only on row count, never parser success or payload characters. -`Ctrl+O` cycles collapsed, expanded, and hidden. Tool cards disappear in the hidden state together with their card-owned leading gap. Context cards participate in collapsed and expanded states but fall back to collapsed while tools are hidden, because injected instructions are not disposable tool traffic. +`Ctrl+O` cycles collapsed, expanded, and hidden. Tool cards disappear in the hidden state together with their card-owned leading gap. Context cards participate in collapsed and expanded states but fall back to collapsed while tools are hidden, because injected instructions are not disposable tool traffic. The hidden phase additionally folds each turn's assistant steps into one message; the [hidden-mode assistant fold Agent Note](../feature/2026-07-29-tui-hidden-mode-assistant-fold.md) owns that rule. ### Cross-workspace resume diff --git a/.agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.zh.md b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.zh.md similarity index 96% rename from .agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.zh.md rename to .agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.zh.md index 005e408f0e..c96fd105bc 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.zh.md +++ b/.agents/notes/archived/architecture/2026-07-28-consolidated-tui-presentation.zh.md @@ -1,6 +1,7 @@ # Agent Note: 统一的 TUI 呈现与导航 Status: implemented +Archived: 2026-08-04 [English](2026-07-28-consolidated-tui-presentation.md) | 中文 @@ -26,7 +27,7 @@ Status: implemented 注入上下文由 `ContextCardComponent` 按普通文本呈现，不经过 XML 树渲染器。仅移除精确配对的外层 `` 行；不匹配、单边或正文内类似标签的文本都原样保留。面向模型的内容不变。折叠在正文组装完成后使用共享 `preview` 辅助函数，因此只取决于行数，不依赖解析是否成功或载荷包含哪些字符。 -`Ctrl+O` 在折叠、展开和隐藏之间循环。隐藏状态会连同卡片自有的前导间距一起移除工具卡片。上下文卡片参与折叠和展开状态，但工具隐藏时回到折叠状态，因为注入指令不是可丢弃的工具流量。 +`Ctrl+O` 在折叠、展开和隐藏之间循环。隐藏状态会连同卡片自有的前导间距一起移除工具卡片。上下文卡片参与折叠和展开状态，但工具隐藏时回到折叠状态，因为注入指令不是可丢弃的工具流量。隐藏阶段还会把每个轮次的 assistant 步骤折叠为一条消息；该规则由[隐藏模式 assistant 折叠 Agent Note](../feature/2026-07-29-tui-hidden-mode-assistant-fold.md)负责。 ### 跨工作区恢复 diff --git a/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.i18n.yaml new file mode 100644 index 0000000000..05d62eea95 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.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/bug-fix/2026-07-23-tui-generic-card-markdown.md +2026-07-23-tui-generic-card-markdown.md: 5c092c4d5ffbc566074f9b280d3fbc207d645ec7 +2026-07-23-tui-generic-card-markdown.zh.md: 93e6388c64e69d9028822ce65f9eda368ed26e7d diff --git a/.agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.md b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.md similarity index 98% rename from .agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.md rename to .agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.md index 494ba58048..5c092c4d5f 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.md +++ b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.md @@ -1,6 +1,7 @@ # Agent Note: TUI generic-card Markdown rendering Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-23-tui-generic-card-markdown.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md similarity index 98% rename from .agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md rename to .agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md index 214edd00f5..93e6388c64 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-23-tui-generic-card-markdown.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 通用卡片的 Markdown 渲染 Status: implemented +Archived: 2026-08-04 [English](2026-07-23-tui-generic-card-markdown.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.i18n.yaml new file mode 100644 index 0000000000..2ac19448b5 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.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/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md +2026-07-24-tui-turn-end-stop-reason-notices.md: 62784ed7cd085ada49b2e0e3d9d809c33a2af917 +2026-07-24-tui-turn-end-stop-reason-notices.zh.md: 162ba4ed44c98bfe00153b7acf69424784f92f5e diff --git a/.agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md rename to .agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md index 7c783ce5a3..62784ed7cd 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md +++ b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md @@ -1,6 +1,7 @@ # Agent Note: TUI presents a reason for every turn-end kind Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-24-tui-turn-end-stop-reason-notices.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md rename to .agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md index 4a98352577..162ba4ed44 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 为每种轮次结束 kind 呈现原因 Status: implemented +Archived: 2026-08-04 [English](2026-07-24-tui-turn-end-stop-reason-notices.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.i18n.yaml new file mode 100644 index 0000000000..c7d248fb65 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.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/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md +2026-07-27-tool-card-single-row-fields-inline.md: 23989e08ac7e32097212bf951461ca1d4213f729 +2026-07-27-tool-card-single-row-fields-inline.zh.md: 8358f7b8dff67c0d3f459d08bf37e3a47f276107 diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md rename to .agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md index e04110ed74..23989e08ac 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.md @@ -1,6 +1,7 @@ # Agent Note: Tool-card single-row fields render inline Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-tool-card-single-row-fields-inline.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md rename to .agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md index ac532ec6eb..8358f7b8df 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md @@ -1,6 +1,7 @@ # Agent Note: 工具卡片的单行字段以内联方式渲染 Status: implemented +Archived: 2026-08-04 [English](2026-07-27-tool-card-single-row-fields-inline.md) | 中文 diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.i18n.yaml similarity index 66% rename from .agents/notes/implemented/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.i18n.yaml rename to .agents/notes/archived/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.i18n.yaml index a8472075e4..635e3fca62 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.i18n.yaml +++ b/.agents/notes/archived/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.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/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.md -2026-07-27-tui-diff-card-redundant-path-header.md: 708e543ff079828b4929d2a50ac697a9c846608a -2026-07-27-tui-diff-card-redundant-path-header.zh.md: 863868ae707f37689bbc202267c5470d8c3163e9 +2026-07-27-tui-diff-card-redundant-path-header.md: 608a11892a20d020087180175eff847021dc0554 +2026-07-27-tui-diff-card-redundant-path-header.zh.md: bf7f1c1eeb994f9940b5f7dfb7db72d422293bd4 diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.md b/.agents/notes/archived/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.md rename to .agents/notes/archived/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.md index 708e543ff0..608a11892a 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.md @@ -1,6 +1,7 @@ # Agent Note: TUI diff card dropped the duplicated file path Status: implemented +Archived: 2026-07-31 English | [中文](2026-07-27-tui-diff-card-redundant-path-header.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.zh.md b/.agents/notes/archived/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.zh.md rename to .agents/notes/archived/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.zh.md index 863868ae70..bf7f1c1eeb 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-tui-diff-card-redundant-path-header.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI diff 卡片重复打印文件路径 Status: implemented +Archived: 2026-07-31 [English](2026-07-27-tui-diff-card-redundant-path-header.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.i18n.yaml new file mode 100644 index 0000000000..e230947bf4 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.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/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md +2026-07-27-tui-step-timing-trails-tool-cards.md: 00256fc0f1c0e9469d0dd4e8567fdbc4a48dcaff +2026-07-27-tui-step-timing-trails-tool-cards.zh.md: a566b521923fecb47c721617ac1b4a5fffce7a0f diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md rename to .agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md index 82f46b44d3..00256fc0f1 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md @@ -1,6 +1,7 @@ # Agent Note: TUI step timing trails the step's last message Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-tui-step-timing-trails-tool-cards.zh.md) diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md similarity index 99% rename from .agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md rename to .agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md index 885b232973..a566b52192 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md +++ b/.agents/notes/archived/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 步骤计时跟在该步骤最后一条消息之后 Status: implemented +Archived: 2026-08-04 [English](2026-07-27-tui-step-timing-trails-tool-cards.md) | 中文 diff --git a/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.i18n.yaml new file mode 100644 index 0000000000..025b6610a9 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.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/bug-fix/2026-07-30-tui-adapter-registration-race.md +2026-07-30-tui-adapter-registration-race.md: 051f5e6af5d7fd6c0096c84af064d065dd6f8983 +2026-07-30-tui-adapter-registration-race.zh.md: 1706acb1d23bab987333a7ac0b5e2695226c1af5 diff --git a/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.md b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.md new file mode 100644 index 0000000000..051f5e6af5 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.md @@ -0,0 +1,30 @@ +# Agent Note: TUI model-context resolution defers on the adapter-registration race + +Status: implemented +Archived: 2026-08-04 + +English | [中文](2026-07-30-tui-adapter-registration-race.zh.md) + +## Problem + +Cordis activates plugins by service availability, not configuration order, so the TUI (whose `inject` requires only the `llm` service) can mount before a configured adapter plugin such as `dsh-llm-pi-ai` finishes registering its provider routes. The TUI's model controller resolves the selected model's context window immediately on mount; when the agent's route pointed at a not-yet-registered provider, `resolveModelInfo` rejected with `NO_ADAPTER` and every fresh session printed `Could not resolve model context: no adapter registered for provider "…"` — a spurious error for a fully working configuration (the adapter registered milliseconds later, and chatting worked). + +## Decision + +The TUI model controller treats a `NO_ADAPTER` rejection of its context-window resolution as a transient state rather than an error: it parks the resolution silently and re-resolves on the next `llm/adapters-updated` commit — the payload-free registry notification `LlmService` already fires at every route commit point. A commit that still lacks the route parks the wait again, so unrelated topology changes stay silent. Any target change re-enters the resolution and clears the pending wait, so the deferred state can never go stale against the current selection; every other resolution error still prints the notice. + +## Alternatives considered + +**Have the TUI wait for boot to settle before resolving.** The TUI has no Loader dependency (tests and embedders run without one) and "settled" is not observable from inside a plugin; adding a Loader coupling for one cosmetic resolution inverts the dependency direction. + +**Poll or retry with a timer.** A timer guesses at activation latency, still mis-prints on a slow adapter, and adds a tunable with no owner. The registry already announces every commit through `llm/adapters-updated`; subscribing is precise and free. + +**Order the config so adapters load first.** Row order carries no load semantics in the Loader (activation is service-driven by design), so this cannot be expressed in configuration. + +**Suppress NO_ADAPTER errors entirely.** A permanently missing adapter (typo in the provider name) would then never surface in the context-window path. Deferring keeps the signal: a wrong provider name still shows `model unset`-like behavior in the selector and fails loudly at dispatch, while the startup race resolves itself. + +**Resolve the context window per submitted message instead of at mount.** The send path already resolves per step (`prepareCall()`), and the indicator is displayed continuously, not only when sending; per-submit display resolution would leave the indicator blank until the first message and re-run adapter I/O for a value that only changes on route changes. + +## Consequences + +A genuinely misconfigured provider no longer prints the context-resolution error at startup — it surfaces at first dispatch instead, which is where the failure is actionable. The controller subscribes to every `llm/adapters-updated` commit but acts only while a wait is parked; the listener's disposer is released by the channel's `detachListeners()` through the controller's `detach()`, symmetric with the sibling channel listeners. Covered by three TUI tests: the deferred resolution stays silent through an unrelated commit and completes when the route's commit arrives, a target change drops the stale wait, and after channel detach a registry commit no longer re-enters resolution. diff --git a/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.zh.md b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.zh.md new file mode 100644 index 0000000000..1706acb1d2 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-30-tui-adapter-registration-race.zh.md @@ -0,0 +1,30 @@ +# Agent Note: TUI 模型上下文解析在适配器注册竞争时延后重试 + +Status: implemented +Archived: 2026-08-04 + +[English](2026-07-30-tui-adapter-registration-race.md) | 中文 + +## Problem + +Cordis 按服务可用性而非配置顺序激活插件，因此 TUI（其 `inject` 只要求 `llm` 服务）可能在 `dsh-llm-pi-ai` 这类已配置的适配器插件完成提供方路由注册之前就挂载。TUI 的模型控制器在挂载时立即解析所选模型的上下文窗口；当 agent 的路由指向尚未注册的提供方时，`resolveModelInfo` 以 `NO_ADAPTER` 拒绝，于是每个新会话都会打印 `Could not resolve model context: no adapter registered for provider "…"` —— 对一份完全正常的配置报出的虚假错误（适配器几毫秒后就完成注册，对话也一切正常）。 + +## Decision + +TUI 模型控制器把上下文窗口解析中的 `NO_ADAPTER` 拒绝视为瞬态状态而非错误：静默搁置这次解析，并在下一次 `llm/adapters-updated` 提交时重新解析——这是 `LlmService` 本就在每个路由提交点发出的无载荷注册表通知。若某次提交仍缺少该路由，等待会被再次搁置，因此无关的拓扑变化保持沉默。任何目标变更都会重新进入解析并清除挂起的等待，因此延后状态绝不会相对当前选择变陈旧；其他所有解析错误仍照常打印通知。 + +## Alternatives considered + +**让 TUI 等启动结算后再解析。** TUI 不依赖 Loader（测试和嵌入方在没有 Loader 的环境下运行），而且"已结算"在插件内部不可观测；为一次外观性的解析引入 Loader 耦合会颠倒依赖方向。 + +**用定时器轮询或重试。** 定时器只能猜测激活延迟，遇到慢适配器仍会误报，还会引入一个没有归属者的可调参数。注册表本就通过 `llm/adapters-updated` 公告每次提交；订阅它既精确又零成本。 + +**调整配置顺序让适配器先加载。** Loader 中行顺序不承载加载语义（激活按设计由服务驱动），因此这无法用配置表达。 + +**彻底压制 NO_ADAPTER 错误。** 那样的话，永久缺失的适配器（提供方名字拼错）在上下文窗口路径上就永远不会暴露。延后重试保留了信号：错误的提供方名字仍会在选择器中表现出类似 `model unset` 的行为，并在分派时大声失败，而启动竞争则自行化解。 + +**改为在每次提交消息时解析上下文窗口，而不是在挂载时。** 发送路径本就按步解析（`prepareCall()`），且指示器是持续显示的，不只在发送时；按提交解析显示值会让指示器在首条消息之前一直空白，并为一个仅在路由变化时才变的值反复执行适配器 I/O。 + +## Consequences + +真正配置错误的提供方不再在启动时打印上下文解析错误——它改在首次分派时暴露，那才是该失败可以被处理的地方。控制器订阅每次 `llm/adapters-updated` 提交，但只在有等待被搁置时才动作；监听器的 disposer 经由控制器的 `detach()` 在频道的 `detachListeners()` 中释放，与同级频道监听器保持对称。由三个 TUI 测试覆盖：延后的解析在无关提交中保持沉默、在该路由的提交到来时完成；目标变更丢弃陈旧等待；频道 detach 之后注册表提交不再重新进入解析。 diff --git a/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.i18n.yaml b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.i18n.yaml new file mode 100644 index 0000000000..b3414c0f98 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.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/bug-fix/2026-07-31-tui-diff-context-line-accounting.md +2026-07-31-tui-diff-context-line-accounting.md: 5172069c7def39808b018030b630ea4313bd7038 +2026-07-31-tui-diff-context-line-accounting.zh.md: b9a9863f05d1c5b829facdc850eccc7a321a76ab diff --git a/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.md b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.md new file mode 100644 index 0000000000..5172069c7d --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.md @@ -0,0 +1,34 @@ +# Agent Note: TUI diff context lines stay neutral + +Status: implemented +Archived: 2026-08-04 + +English | [中文](2026-07-31-tui-diff-context-line-accounting.zh.md) + +## Problem + +Result-time filesystem diffs carry the applied change with three surrounding context lines in each `FileDiff.oldText` and `FileDiff.newText`. The TUI rendered every old-side row as removed and every new-side row as added, including the identical context present on both sides. A one-line edit therefore appeared as seven removals plus seven additions, and the footer repeated those inflated totals. + +## Decision + +The TUI compares each `FileDiff` whose old and new text are both available. Added and removed rows retain their green `+` and red `-` markers; equal context rows use the recessed body tone with a neutral two-space prefix. The footer sums only the rows classified as added or removed. `maxDiffEditLength` bounds the exact comparison by its combined added and removed line count; the default is 1000. Exceeding the bound renders the complete old side as removed and the complete new side as added, marks the footer approximate, and caches that result so redraws do not repeat the comparison. A tool result clears the pending-view cache before deriving the settled view, including when a presenter mutates and reuses the same view object. + +When `oldText` is `null`, the renderer cannot distinguish a create from a pending overwrite or an argument fallback whose prior text is unavailable. It therefore shows every non-empty new-side row as added, without claiming those rows were absent from an existing file. Empty new content renders no synthetic added row. + +This remains a consumer-side interpretation of the existing `FileDiff` contract. Filesystem tools continue to persist contextual before/after snippets, so other consumers keep their placement context and existing session logs replay with corrected TUI presentation. The TUI uses the same maintained `diff` package as `dsh-tool-fs` instead of introducing a second line-diff implementation. + +## Alternatives considered + +**Remove context from filesystem result metadata.** Rejected: contextual applied hunks are intentional producer output used by capable editors, and changing them would weaken every consumer while leaving old session logs misleading in the TUI. + +**Extend `FileDiff` with persisted per-line tags.** Rejected: the tags can be derived deterministically from the existing before/after pair; persisting them would widen the cross-package and session-log contract solely for one renderer. + +**Match equal lines by position without a diff algorithm.** Rejected: insertions and deletions shift subsequent context, so positional pairing would misclassify valid hunks. + +**Run every comparison to completion.** Rejected: pending tool views can contain unrestricted model-authored old and new strings, and an unbounded Myers comparison can block the synchronous terminal renderer. + +## Consequences + +TUI diff cards distinguish evidence-bearing context from the mutation itself, and an exact `+A -R` footer reports the actual line delta. Replaying an existing contextual diff gains the corrected rendering without a migration. Result-time filesystem hunks are context-bounded; unrestricted pending views either complete within the configured edit-length budget or degrade to an explicitly approximate linear rendering. + +The focused TUI tests cover neutral context, exact totals, an empty create, bounded fallback, result-time cache invalidation, and redraw cache reuse. The assembled `advanced-cards` terminal snapshots pin the neutral context style, semantic change colors, exact footer, and approximate fallback through collapsed and expanded card states. diff --git a/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.zh.md b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.zh.md new file mode 100644 index 0000000000..b9a9863f05 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-07-31-tui-diff-context-line-accounting.zh.md @@ -0,0 +1,34 @@ +# Agent Note: TUI diff 上下文行保持中性 + +Status: implemented +Archived: 2026-08-04 + +[English](2026-07-31-tui-diff-context-line-accounting.md) | 中文 + +## 问题 + +文件系统 diff 返回结果时，每个 `FileDiff.oldText` 和 `FileDiff.newText` 都会包含已应用的变更及其前后各 3 行上下文。TUI 将旧侧的每一行都渲染为删除行，将新侧的每一行都渲染为新增行，其中包括两侧相同的上下文。因此，一行编辑会显示为删除 7 行并新增 7 行，页脚还会重复这些虚高的合计值。 + +## 决策 + +TUI 会比较每个变更前后文本均可用的 `FileDiff`。新增行和删除行仍分别使用绿色 `+` 和红色 `-` 标记；相同的上下文行则使用弱化的正文色调，并带有由两个空格构成的中性前缀。页脚只汇总归类为新增或删除的行。`maxDiffEditLength` 以新增行与删除行的合计数为精确比较设置上限，默认值为 1000。超过上限时，TUI 会把完整旧侧渲染为删除内容、把完整新侧渲染为新增内容，将页脚标记为近似结果，并缓存该结果，避免后续重绘重复比较。工具结果会在派生已结算视图前清除待处理视图缓存，即使 presenter 修改并复用同一个视图对象也一样。 + +当 `oldText` 为 `null` 时，渲染器无法区分文件创建、待处理覆写，以及旧文本不可用的参数回退。因此，它会把新侧的每个非空行显示并计作新增行，但不会声称这些行原先不存在于已有文件中。新内容为空时，不会渲染虚构的新增行。 + +该行为仍然只是消费方对现有 `FileDiff` 契约的解释。文件系统工具仍会持久化带上下文的变更前后片段，因此其他消费方仍能获得定位上下文，已有会话日志在回放时也会采用修正后的 TUI 呈现。TUI 与 `dsh-tool-fs` 共用同一个受维护的 `diff` 包（package），无需引入第二套逐行 diff 实现。 + +## 考虑过的替代方案 + +**从文件系统结果元数据中移除上下文。** 不予采纳：带上下文的已应用 hunk 是有意保留的生产方输出，供具备相应能力的编辑器使用；更改这些内容会让所有消费方丢失信息，同时旧会话日志在 TUI 中仍会产生误导。 + +**为 `FileDiff` 扩展持久化的逐行标签。** 不予采纳：这些标签可以根据现有的变更前后文本对确定性派生；仅为一个渲染器持久化标签，会扩大跨包契约和会话日志契约。 + +**不使用 diff 算法，按位置匹配相同行。** 不予采纳：插入和删除会使后续上下文发生位移，因此按位置配对会把有效 hunk 错误分类。 + +**让所有比较都运行至完成。** 不予采纳：待处理工具视图可能包含由模型生成且长度不受限制的新旧字符串，无界的 Myers 比较可能阻塞同步终端渲染器。 + +## 后果 + +TUI diff 卡片会区分用于佐证的上下文与变更本身，精确的 `+A -R` 页脚会报告实际的行变更量。回放已有的上下文 diff 无需迁移即可获得修正后的渲染。结果时刻的文件系统 hunk 受上下文范围限制；不受限制的待处理视图要么在配置的编辑长度预算内完成比较，要么降级为明确标注为近似结果的线性渲染。 + +聚焦的 TUI 测试覆盖中性上下文、精确合计值、空文件创建、有界回退、结果到达时的缓存失效和重绘缓存复用。组装后的 `advanced-cards` 终端快照在卡片折叠和展开状态下固定了中性上下文样式、变更行的语义色彩、精确结果页脚和近似回退。 diff --git a/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.i18n.yaml b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.i18n.yaml new file mode 100644 index 0000000000..f5b795742e --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.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/bug-fix/2026-08-03-tui-long-session-render-costs.md +2026-08-03-tui-long-session-render-costs.md: 2f6e909aa280cf72cd15a635a64c80aee6cd0cf1 +2026-08-03-tui-long-session-render-costs.zh.md: eeff7bc33df1f6e69d749c590953a42675a4d688 diff --git a/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.md b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.md new file mode 100644 index 0000000000..2f6e909aa2 --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.md @@ -0,0 +1,34 @@ +# Agent Note: TUI long-session render costs — shared step-timing scan and card line caches + +Status: implemented +Archived: 2026-08-04 + +English | [中文](2026-08-03-tui-long-session-render-costs.zh.md) + +## Problem + +On a long resumed session (196k events, 2.2k steps, 1.8k tool cards) the TUI took ~12 s to render the transcript and ~800 ms to echo one keystroke. Profiling attributed both to the render path, not to session load (zstd + parse + surface seed is ~1.7 s): + +- Every step's timing footer called `stepTimingAt`, which replayed the whole event log from index 0 per footer — O(steps × events) on the initial render, ~6 s of CPU. +- pi-tui re-renders every component each frame and relies on per-component line caches (its own `Text`/`Markdown` cache by `(text, width)`). `ToolCardComponent.render()` and `ContextCardComponent.render()` built throwaway `new Text(...)`/`new Markdown(...)` instances inside `render(width)`, so every frame — every keystroke — re-wrapped every settled card's output. + +## Decision + +`packages/ui/tui/src/chat/timing.ts` replaces `stepTimingAt` with `StepTimingTracker`: one accumulator per chat mount, created in `createTuiChat` and threaded through `StreamingAssistantComponent` into each `StepTimingComponent`. A query advances a cursor over events appended since the previous query and keeps per-step bucket state in a map, so all footers together cost O(events). The open bucket is accumulated to the query clock at lookup, and a step is pinned at its `step/end`. The tracker requires the append-only session log (the `seq = log length` contract). + +`ToolCardComponent` and `ContextCardComponent` cache their rendered rows keyed by width. The cache drops on every state mutator (`updateResult`, `setVisibility`, `setExpanded`) and on `invalidate()` (pi-tui's tree-wide cascade), so a state change always re-renders; everything else — including every keystroke frame — returns the cached rows. This restores upstream pi's own component convention (persistent child components plus explicit `cachedWidth`/`cachedLines` where rendering is custom, e.g. pi `coding-agent` `bash.ts`), which the imperative `render(width)` bodies here had silently defeated. + +Measured on the 196k-event session (tmux, 200×50): resume prompt-ready 12.2 s → 7.2 s; per-keystroke echo 796 ms median → 17 ms (fresh-session parity). + +## Alternatives considered + +- **Index `step/start` offsets, keep per-footer replay** — removes the `findIndex` but each footer still scans its step's span from a shared array; the tracker's single shared pass is the same complexity win with less bookkeeping. +- **Restructure the cards into persistent pi-tui child components** (upstream pi's primary style) — equivalent steady-state cost, but a larger diff across card state handling for no additional win over the width-keyed cache. +- **Cache inside pi-tui's `Container.render`** — wrong layer: the vendored patch surface would grow, and the contract (components own their caches) already exists upstream. + +## Consequences + +- Typing latency no longer scales with total tool output; the residual per-frame cost is pi-tui's tree traversal and row concatenation, linear in rendered rows. Resume render cost is now dominated by pi-tui's one-time initial layout (~4 s at 196k events) plus load (~1.7 s), both linear. +- The tracker consumes event times as logged and drops the removed implementation's mid-scan `time > at` cutoff, which per-footer `at` values make impossible in a shared scan; under a backward wall-clock step each bucket clamps at zero, which can differ from the old cutoff's totals. +- Card `render()` is no longer a pure function of `(state, width)` per call — mutators must drop `linesCache`. A new mutator that forgets to do so shows stale rows; the cache tests in `packages/ui/tui/tests/transcript-card-cache.spec.ts` pin the contract for the existing mutators. +- `StepTimingTracker` assumes step coordinates are not reused after `step/end`; a duplicate `step/start` for a closed step is ignored rather than restarting the step. diff --git a/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.zh.md b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.zh.md new file mode 100644 index 0000000000..eeff7bc33d --- /dev/null +++ b/.agents/notes/archived/bug-fix/2026-08-03-tui-long-session-render-costs.zh.md @@ -0,0 +1,34 @@ +# Agent Note: TUI 长会话渲染开销：共享步骤耗时扫描与卡片行缓存 + +Status: implemented +Archived: 2026-08-04 + +[English](2026-08-03-tui-long-session-render-costs.md) | 中文 + +## 问题 + +在一个恢复后的长会话（196k 条事件、2.2k 个步骤、1.8k 张工具卡片）中，TUI 渲染 transcript（文本记录）耗时约 12 秒，回显一次按键耗时约 800 毫秒。性能剖析表明，两项耗时都来自渲染路径，而非会话加载（zstd + 解析 + 表层播种约为 1.7 秒）： + +- 每个步骤的耗时页脚都会调用 `stepTimingAt`，而它会针对每个页脚从索引 0 起回放整个事件日志，因此初次渲染的复杂度为 O(步骤数 × 事件数)，占用约 6 秒 CPU 时间。 +- pi-tui 每一帧都会重新渲染所有组件，并依赖各组件自己的行缓存（它的 `Text`/`Markdown` 会按 `(text, width)` 缓存）。`ToolCardComponent.render()` 和 `ContextCardComponent.render()` 构造用后即弃的 `new Text(...)`/`new Markdown(...)` 实例，且构造发生在 `render(width)` 内，因此每一帧，也就是每次按键，都会重新对每张已结算卡片的输出进行折行。 + +## 决策 + +`packages/ui/tui/src/chat/timing.ts` 不再使用 `stepTimingAt`，改用 `StepTimingTracker`：每次挂载聊天界面时在 `createTuiChat` 中创建一个累加器，再经 `StreamingAssistantComponent` 传入每个 `StepTimingComponent`。每次查询都会推进游标，扫描上次查询后追加的事件，并在一个映射表中保存各步骤的 bucket 状态，因此所有页脚合计只需 O(事件数)。查询时，系统把未闭合 bucket 累加到查询时刻；步骤在其 `step/end` 处固定。该跟踪器要求会话日志仅追加，即遵守 `seq = log length` 契约。 + +`ToolCardComponent` 和 `ContextCardComponent` 按宽度键控缓存渲染行。调用任一状态修改方法（`updateResult`、`setVisibility`、`setExpanded`）或 `invalidate()`（pi-tui 的全树级联）时会清空缓存，因此状态变化一定会重新渲染；其他情况，包括每一次按键帧，都会返回缓存行。这恢复了上游 pi 自身的组件惯例：使用常驻子组件；自定义渲染时显式使用 `cachedWidth`/`cachedLines`，例如 pi `coding-agent` 的 `bash.ts`。而这里命令式的 `render(width)` 函数体此前让这套惯例失效。 + +在该 196k 条事件的会话上测得（tmux，200×50）：恢复后提示符就绪耗时从 12.2 秒降至 7.2 秒；每次按键的回显耗时中位数从 796 毫秒降至 17 毫秒（与新会话持平）。 + +## 曾考虑的替代方案 + +- **索引 `step/start` 偏移量，保留逐页脚回放**：这会消除 `findIndex`，但每个页脚仍要从共享数组扫描所属步骤的区间；跟踪器的一次共享遍历以更少的额外状态记录取得相同的复杂度改进。 +- **把卡片重构为常驻 pi-tui 子组件**（上游 pi 的主要风格）：稳定状态下成本相同，但卡片状态处理所需改动更大，相较按宽度键控的缓存并无额外收益。 +- **在 pi-tui 的 `Container.render` 内缓存**：层级不对：对第三方内嵌代码的补丁范围会扩大，而上游已经约定由组件拥有各自的缓存。 + +## 后果 + +- 输入延迟不再随工具输出总量增长；剩余的每帧成本是 pi-tui 的树遍历与行拼接，与渲染行数呈线性关系。恢复时的渲染成本现由 pi-tui 的一次性初始布局（196k 条事件时约 4 秒）与加载（约 1.7 秒）主导，两者均为线性。 +- 该跟踪器直接采用日志记录的事件时间，不再像已移除的实现那样，在扫描中途遇到 `time > at` 时截断；由于每个页脚的 `at` 值不同，共享扫描无法采用这种截断；挂钟时间倒退时，每个 bucket 都以零为下限，所得总计值可能与旧截断下的总计值不同。 +- 卡片的 `render()` 不再是每次调用时 `(state, width)` 的纯函数，状态修改方法必须清空 `linesCache`。若新增状态修改方法时忘记清空，界面会显示陈旧行；`packages/ui/tui/tests/transcript-card-cache.spec.ts` 中的缓存测试固定了现有状态修改方法的契约。 +- `StepTimingTracker` 假定步骤坐标在 `step/end` 后不会复用；对已关闭步骤重复出现的 `step/start` 会被忽略，不会重新启动该步骤。 diff --git a/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml new file mode 100644 index 0000000000..c44bf6e177 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.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/2026-07-17-dedicated-full-screen-tui-front-door.md +2026-07-17-dedicated-full-screen-tui-front-door.md: 1a04e738a2810abdb4bac81aebe9b23db404879e +2026-07-17-dedicated-full-screen-tui-front-door.zh.md: 75fc3d47aa258fa6db767b1049194663148d1afa diff --git a/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.md similarity index 79% rename from .agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md rename to .agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.md index c011a0284e..1a04e738a2 100644 --- a/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md +++ b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.md @@ -1,11 +1,14 @@ # Agent Note: Dedicated full-screen TUI front door Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-17-dedicated-full-screen-tui-front-door.zh.md) ## Problem +The reusable TUI package remains implemented, but [`dsh` no longer ships it as an application entrypoint](../simplification/2026-08-03-explicit-config-dsh-entrypoint.md). This note continues to own the package boundary and terminal behavior; the later note owns product composition. + At the time this front door was introduced, the line-oriented agent handled pipes and ordinary terminals, but a full-screen coding interface had to own raw input, differential screen drawing, cursor state, overlays, and terminal restoration. Combining those contracts in one UI plugin would have coupled a stream-oriented path to a TTY-only lifecycle. The later [redundant-agent removal](../simplification/2026-07-20-remove-stdio-and-echo-agents.md) removes that line agent; this Note continues to own the TUI design. The interactive channel must remain a Cordis plugin over the same agent, session, tool, and user-interaction services as every other front door. It needs to resume durable history, follow compaction replacements, display tool-owned presentation, and restore the terminal on startup failure and disposal. A standalone chat application or a second agent composition would duplicate behavior outside the plugin graph. @@ -14,9 +17,9 @@ The interactive channel must remain a Cordis plugin over the same agent, session DeepSeek Harness ships [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) as a dedicated Cordis plugin. It owns terminal input and presentation only; agent lifecycle, session persistence, tool execution, and the model-facing question tool remain separate composition entries. The plugin requires both stdin and stdout to be TTYs and fails instead of silently changing to line-oriented behavior. -There is one terminal front door. `@deepseek-ai/dsh-tui` mounts before the configured agent, and `apps/cli/config/tui.cordis.yml` — an overlay over the shared `base.cordis.yml` — owns the interactive coding composition. Non-interactive tasks use the official headless surface; ACP remains a separate automation protocol and owns the supported Code Mode demo. +The package is a terminal front door, not a complete application. A host mounts `@deepseek-ai/dsh-tui` before its configured agent and composes the backends, tools, and policies around it. The product CLI currently ships no terminal composition; non-interactive tasks use headless mode, Web owns the installed human surface, and ACP remains a separate automation protocol. -The selected front door receives the exact generated or resumed `SessionId` used by the pre-created agent. It mounts before the agent composition, waits for the matching root agent, and enters full-screen mode only after that agent exists. A matching `agent-loop/config-start-failed` event is therefore reported before screen takeover and exits with status 1. +The host supplies the exact generated or resumed `SessionId` used by its pre-created agent. The TUI waits for the matching root agent and enters full-screen mode only after that agent exists. A matching `agent-loop/config-start-failed` event is therefore reported before screen takeover. ### Session projection and interaction @@ -34,18 +37,18 @@ The built-in palette uses standard 16-color ANSI foregrounds and SGR attributes, ## Verification -The implemented [TUI terminal-state snapshot Agent Note](../testing/2026-07-18-tui-terminal-state-snapshots.md) owns the four-layer verification contract: direct behavior tests, transient semantic terminal snapshots, recorded JSONL journeys through production tools, and Loader/PTY smoke tests. The package README owns configuration, commands, model-visible effects, and current limitations. +The implemented [TUI terminal-state snapshot Agent Note](../testing/2026-07-18-tui-terminal-state-snapshots.md) owns the package verification contract: direct behavior tests and semantic terminal snapshots. A deployment shipping this front door owns its assembled transcript and process/PTY acceptance. The package README owns configuration, commands, model-visible effects, and current limitations. ## Alternatives considered - **Keep readline and full-screen modes inside `@deepseek-ai/dsh-stdio`** — rejected because line-oriented output and differential TTY rendering have different dependencies, input rules, logging ownership, and teardown obligations. Separate packages keep the pipe-safe contract small and explicit. -- **Let the TUI plugin silently downgrade when either stream is not a TTY** — rejected because a fallback hides deployment mistakes and changes interaction semantics. The app bundle may select a front door with `auto`; an explicitly mounted TUI fails loud. -- **Keep TUI wiring and tests under the readline `repl-agent` leaf** — rejected because one leaf would represent two distinct front doors and break symmetry with `acp-agent`. A dedicated `tui-agent` leaf owns TUI overlays and tests while reusing the repl-agent backend composition. +- **Let the TUI plugin silently downgrade when either stream is not a TTY** — rejected because a fallback hides deployment mistakes and changes interaction semantics. A host may select a different front door; an explicitly mounted TUI fails loud. +- **Keep TUI wiring and tests under the readline `repl-agent` leaf** — rejected at the time because one leaf would represent two distinct front doors. The later product-entrypoint removal deleted that application wiring while retaining the package boundary. - **Mutate `agent.options` when `/model` runs** — rejected because creation options do not provide an atomic boundary between asynchronous prompt assembly and request routing. Agent-scoped waterfalls preserve immutable creation input and snapshot the selected pair for each step. ## Consequences -- Interactive terminal work has a stateful Markdown, card, plan, and question interface with no second terminal protocol to keep aligned. +- Deployments that mount the TUI gain a stateful Markdown, card, plan, and question interface with no second terminal protocol to keep aligned. - The TUI carries a pi-tui dependency and a strict TTY requirement; non-TTY deployments use the Headless app or a structured protocol. - Session projection makes resume consistent with the durable conversation, but one configured session owns the transcript and editor. - Tool packages extend terminal cards through their existing presentation methods without adding tool-specific branches to the TUI. diff --git a/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md similarity index 81% rename from .agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md rename to .agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md index 5aea4ac0c5..75fc3d47aa 100644 --- a/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md +++ b/.agents/notes/archived/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md @@ -1,11 +1,14 @@ # Agent Note: 独立的全屏 TUI 入口 Status: implemented +Archived: 2026-08-04 [English](2026-07-17-dedicated-full-screen-tui-front-door.md) | 中文 ## 问题 +可复用的 TUI 包（package）仍然保留实现，但 [`dsh` 不再将其作为应用入口交付](../simplification/2026-08-03-explicit-config-dsh-entrypoint.md)。本记录继续负责包边界和终端行为；后续记录负责产品组合。 + 在本入口引入时，面向行的 agent 负责 pipe 与普通终端，但全屏 coding 界面必须负责原始输入、差分绘制、光标状态、浮层和终端恢复。把这两类契约合并到一个 UI 插件中，会迫使面向 stream 的路径依赖仅适用于 TTY 的生命周期。后续的[移除重复 agent 决策](../simplification/2026-07-20-remove-stdio-and-echo-agents.md)移除了这个面向行 agent；本 Note 继续负责 TUI 设计。 交互通道必须继续作为 Cordis 插件，使用与其他入口相同的 agent（智能体）、会话、工具和用户交互服务。它需要恢复持久历史、跟随压缩替换、显示工具自有的呈现内容，并在启动失败和资源释放时恢复终端。独立聊天应用或第二套 agent 组合会在插件图之外重复实现这些行为。 @@ -14,9 +17,9 @@ Status: implemented DeepSeek Harness 将 [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) 作为独立的 Cordis 插件交付。该插件只负责终端输入与呈现；agent 生命周期、会话持久化、工具执行以及模型可见的提问工具仍由不同组合项负责。插件要求 stdin 和 stdout 均为 TTY；条件不满足时会失败，不会静默切换为逐行输出。 -只有一个终端入口。`@deepseek-ai/dsh-tui` 在已配置 agent 之前挂载，而 `apps/cli/config/tui.cordis.yml`——叠加在共享 `base.cordis.yml` 之上的 overlay——拥有交互式 coding 组装。非交互任务使用官方 headless 界面；ACP 仍是独立的自动化协议，并拥有受支持的 Code Mode demo。 +该包是终端入口，而不是完整应用。宿主在已配置 agent 之前挂载 `@deepseek-ai/dsh-tui`，并围绕它组合后端、工具和策略。产品 CLI 目前不交付终端组合；非交互任务使用 headless 模式，Web 是已安装产品中面向人的界面，而 ACP 仍是独立的自动化协议。 -所选入口接收预创建 agent 使用的同一个新建或恢复 `SessionId`。入口先于 agent 组合挂载，等待相符的根 agent 出现，然后才进入全屏模式。因此，相符的 `agent-loop/config-start-failed` 事件会在接管屏幕前报告，并以状态码 1 退出。 +宿主提供其预创建 agent 使用的同一个新建或恢复 `SessionId`。TUI 等待相符的根 agent 出现，然后才进入全屏模式。因此，相符的 `agent-loop/config-start-failed` 事件会在接管屏幕前报告。 ### 会话投影与交互 @@ -34,18 +37,18 @@ agent 空闲时，编辑器输入调用 `agent.send()`；轮次运行中则调 ## 验证 -已实现的 [TUI 终端状态快照 Agent Note](../testing/2026-07-18-tui-terminal-state-snapshots.md) 规定四层验证契约：直接行为测试、瞬态语义终端快照、通过生产工具执行的已录制 JSONL 流程，以及 Loader/PTY 冒烟测试。包（package）README 负责记录配置、命令、模型可见效果和当前限制。 +已实现的 [TUI 终端状态快照 Agent Note](../testing/2026-07-18-tui-terminal-state-snapshots.md) 规定包验证契约：直接行为测试和语义终端快照。交付该入口的部署负责其组装后 transcript 和进程／PTY 验收。包 README 负责记录配置、命令、模型可见效果和当前限制。 ## 曾考虑的替代方案 - **把 readline 与全屏模式都保留在 `@deepseek-ai/dsh-stdio` 中**：不予采纳，因为逐行输出和差分 TTY 渲染具有不同的依赖、输入规则、日志所有权和资源清理义务。拆分为独立包可以让管道安全契约保持精简、明确。 -- **当任一进程流不是 TTY 时，让 TUI 插件静默降级**：不予采纳，因为回退会掩盖部署错误并改变交互语义。应用包可以通过 `auto` 选择入口；明确挂载的 TUI 会快速失败。 -- **把 TUI 接线与测试保留在 readline `repl-agent` 叶节点下**：不予采纳，因为一个叶节点会代表两个不同入口，也会破坏它与 `acp-agent` 的对称性。独立的 `tui-agent` 叶节点负责 TUI 浮层和测试，同时复用 repl-agent 的后端组合。 +- **当任一进程流不是 TTY 时，让 TUI 插件静默降级**：不予采纳，因为回退会掩盖部署错误并改变交互语义。宿主可以选择其他入口；明确挂载的 TUI 会快速失败。 +- **把 TUI 接线与测试保留在 readline `repl-agent` 叶节点下**：当时不予采纳，因为一个叶节点会代表两个不同入口。后续移除产品入口时删除了该应用接线，但保留了包边界。 - **在 `/model` 运行时修改 `agent.options`**：不予采纳，因为创建选项无法在异步 prompt 组装与请求路由之间提供原子边界。agent 作用域内的 waterfall 会在保持创建输入不可变的同时，为每个 step 快照一次选中的字段组合。 ## 后果 -- 交互式终端拥有带状态的 Markdown、卡片、计划和提问界面，无需再对齐第二套终端协议。 +- 挂载 TUI 的部署会获得带状态的 Markdown、卡片、计划和提问界面，无需再对齐第二套终端协议。 - TUI 会引入 pi-tui 依赖并严格要求 TTY；非 TTY 部署使用 Headless app 或结构化协议。 - 会话投影使恢复与持久会话保持一致，但只有一个已配置会话拥有 transcript 和编辑器。 - 工具包通过既有呈现方法扩展终端卡片，无需在 TUI 中增加工具专用分支。 diff --git a/.agents/notes/archived/feature/2026-07-20-windows-tui-support.i18n.yaml b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.i18n.yaml new file mode 100644 index 0000000000..52f5e24a1b --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.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/2026-07-20-windows-tui-support.md +2026-07-20-windows-tui-support.md: 9308df7fb43378610cb2d480324c55bff07ea108 +2026-07-20-windows-tui-support.zh.md: 8b4a1eb4cef3056b47b911a07ed62202b52d1f73 diff --git a/.agents/notes/implemented/feature/2026-07-20-windows-tui-support.md b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-20-windows-tui-support.md rename to .agents/notes/archived/feature/2026-07-20-windows-tui-support.md index 6b728486dd..9308df7fb4 100644 --- a/.agents/notes/implemented/feature/2026-07-20-windows-tui-support.md +++ b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.md @@ -1,6 +1,7 @@ # Agent Note: Support the TUI on Windows Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-20-windows-tui-support.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-20-windows-tui-support.zh.md b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-20-windows-tui-support.zh.md rename to .agents/notes/archived/feature/2026-07-20-windows-tui-support.zh.md index 2b53b05ff6..8b4a1eb4ce 100644 --- a/.agents/notes/implemented/feature/2026-07-20-windows-tui-support.zh.md +++ b/.agents/notes/archived/feature/2026-07-20-windows-tui-support.zh.md @@ -1,6 +1,7 @@ # Agent Note: 在 Windows 上支持 TUI Status: implemented +Archived: 2026-08-04 [English](2026-07-20-windows-tui-support.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-21-tui-resume-command.i18n.yaml b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.i18n.yaml new file mode 100644 index 0000000000..e6628da8c3 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.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/2026-07-21-tui-resume-command.md +2026-07-21-tui-resume-command.md: de6c488b51b300705b33db13b8959b8114fdd025 +2026-07-21-tui-resume-command.zh.md: d7639c7a51fc5c35f10c514356ceb79d9c1ca76a diff --git a/.agents/notes/implemented/feature/2026-07-21-tui-resume-command.md b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.md similarity index 87% rename from .agents/notes/implemented/feature/2026-07-21-tui-resume-command.md rename to .agents/notes/archived/feature/2026-07-21-tui-resume-command.md index c8cb855378..de6c488b51 100644 --- a/.agents/notes/implemented/feature/2026-07-21-tui-resume-command.md +++ b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.md @@ -1,6 +1,7 @@ # Agent Note: Product-level TUI session resume Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-21-tui-resume-command.zh.md) @@ -36,4 +37,4 @@ The exit line is a launcher-owned context slot rather than a config template, an ## Testing -TUI tests cover keyboard navigation, title/id search, search-clear/cancel behavior, running-agent refusal, refusal of the current session and sessions already live in this runtime, route absence, corrupt rows, preflight revalidation, the no-host warning, and stop-before-handoff ordering. Session-query tests pin detached full-log validation. Agent-loop resume tests pin exact identity and history; title, todo, and goal replay suites pin restored projections and disarmed goal activation. The keyless TUI snapshot owns the full-viewport selector and its IME cursor anchor, and a real PTY smoke covers search plus handoff. +TUI package tests cover keyboard navigation, title/id search, search-clear/cancel behavior, running-agent refusal, refusal of the current session and sessions already live in this runtime, route absence, corrupt rows, preflight revalidation, the no-host warning, and stop-before-handoff ordering. Session-query tests pin detached full-log validation. Agent-loop resume tests pin exact identity and history; title, todo, and goal replay suites pin restored projections and disarmed goal activation. The package semantic snapshot owns the full-viewport selector and its IME cursor anchor; a deployment shipping the TUI owns its process and PTY handoff acceptance. diff --git a/.agents/notes/implemented/feature/2026-07-21-tui-resume-command.zh.md b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.zh.md similarity index 86% rename from .agents/notes/implemented/feature/2026-07-21-tui-resume-command.zh.md rename to .agents/notes/archived/feature/2026-07-21-tui-resume-command.zh.md index 2a7e74d110..d7639c7a51 100644 --- a/.agents/notes/implemented/feature/2026-07-21-tui-resume-command.zh.md +++ b/.agents/notes/archived/feature/2026-07-21-tui-resume-command.zh.md @@ -1,6 +1,7 @@ # Agent Note: 产品级 TUI 会话恢复 Status: implemented +Archived: 2026-08-04 [English](2026-07-21-tui-resume-command.md) | 中文 @@ -36,4 +37,4 @@ Status: implemented ## Testing -TUI 测试覆盖键盘导航、标题／id 搜索、清空搜索后再取消、agent 运行期间拒绝恢复、拒绝恢复当前会话和已在本运行时中处于活跃状态的会话、路由缺失、损坏的候选行、预检复查、无宿主时的告警，以及停止终端先于宿主交接的顺序。session-query 测试固定脱离运行时的完整日志验证。agent-loop 恢复测试固定会话身份和历史完全一致；标题、待办事项和目标回放测试套件固定这些投影均可恢复，且目标激活状态已经解除。无密钥 TUI 快照固定全屏选择页和输入法光标锚点，真实 PTY smoke 则覆盖搜索与交接。 +TUI 包（package）测试覆盖键盘导航、标题／id 搜索、清空搜索后再取消、agent 运行期间拒绝恢复、拒绝恢复当前会话和已在本运行时中处于活跃状态的会话、路由缺失、损坏的候选行、预检复查、无宿主时的告警，以及停止终端先于宿主交接的顺序。session-query 测试固定脱离运行时的完整日志验证。agent-loop 恢复测试固定会话身份和历史完全一致；标题、待办事项和目标回放测试套件固定这些投影均可恢复，且目标激活状态已经解除。包级语义快照固定全屏选择页和输入法光标锚点；交付 TUI 的部署负责其进程与 PTY 交接验收。 diff --git a/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.i18n.yaml b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.i18n.yaml new file mode 100644 index 0000000000..a8a6577e01 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.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/2026-07-21-tui-skill-slash-command.md +2026-07-21-tui-skill-slash-command.md: e151f92d0d9eb1486bcf21498fb73ba156edd861 +2026-07-21-tui-skill-slash-command.zh.md: ac1c4da948dcbd6b01bdb6e62d66d5f704c0b132 diff --git a/.agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.md b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.md similarity index 82% rename from .agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.md rename to .agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.md index 872e1f1097..e151f92d0d 100644 --- a/.agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.md +++ b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.md @@ -1,6 +1,7 @@ # Agent Note: TUI skill slash command Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-21-tui-skill-slash-command.zh.md) @@ -30,4 +31,4 @@ Autocomplete filters the invocation-neutral `list()` result with `isUserInvocabl ## Consequences -Manual invocation always reloads the full skill body: the TUI does not detect a skill already present in the conversation, so a repeated `/skill:` appends its instructions again — acceptable because re-injection is sometimes the intent, and documented under the package README's Known Limitations. The two-renderer duplication is a standing maintenance cost accepted above. The `` wrapper is stable model-visible text and is pinned verbatim in unit tests against a real `SkillService`; the help-panel line is pinned by the `errors-and-help` terminal snapshot. Autocomplete population and the disposed-lookup and failed-lookup branches are covered by unit tests that mount the real registry or a controllable service. End-to-end delivery is proven by a dedicated real-composition test: the `examples/tui-agent` keyless PTY smoke (`tui-keyless-smoke.e2e.ts`) boots the production TUI/agent/skill stack through the Loader under a genuine pseudo-terminal with only the model scripted, drops a fixture skill under the agents-home `skills/` root, types `/skill:` as live keystrokes, and asserts the scripted adapter echoes the fixture's body marker only when the rendered `` block arrives — exercising `ctx.get('skills')` resolution in the shipped tree, the client-side parse, the local provider load, and the user turn reaching the model together. That fixture's frontmatter description avoids a `: ` colon-space so its YAML stays a plain scalar; an invalid-frontmatter skill is silently dropped during discovery. +Manual invocation always reloads the full skill body: the TUI does not detect a skill already present in the conversation, so a repeated `/skill:` appends its instructions again — acceptable because re-injection is sometimes the intent, and documented under the package README's Known Limitations. The two-renderer duplication is a standing maintenance cost accepted above. The `` wrapper is stable model-visible text and is pinned verbatim in package tests against a real `SkillService`; the package semantic matrix pins the help-panel line. Autocomplete population, user-only discovery, delivery to idle and running agents, and the disposed-lookup and failed-lookup branches are covered by package tests that mount the real registry or a controllable service. The removed product TUI's keyless PTY smoke formerly covered the assembled Loader path; a future terminal deployment owns that application-level scenario. diff --git a/.agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.zh.md b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.zh.md similarity index 80% rename from .agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.zh.md rename to .agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.zh.md index 772e25745e..ac1c4da948 100644 --- a/.agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.zh.md +++ b/.agents/notes/archived/feature/2026-07-21-tui-skill-slash-command.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI skill slash command Status: implemented +Archived: 2026-08-04 [English](2026-07-21-tui-skill-slash-command.md) | 中文 @@ -30,4 +31,4 @@ TUI 通过 `ctx.get('skills')` 读取 skill 服务，而非声明式注入，因 ## Consequences -手动调用总是重新加载完整的 skill 正文：TUI 不会检测某个 skill 是否已在对话中出现，因此重复的 `/skill:` 会再次追加其指令——这可以接受，因为重新注入有时正是意图所在，且已在本包 README 的已知限制中说明。上文接受的双渲染器重复是一项长期维护成本。`` 包裹是稳定的、模型可见的文本，并在单元测试中针对一个真实的 `SkillService` 逐字固定；帮助面板那一行由 `errors-and-help` 终端快照固定。自动补全的填充、dispose 后查找分支、以及查找失败分支，都由挂载真实注册表或可控服务的单元测试覆盖。端到端的投递由一项专门的真实组合测试证明：`examples/tui-agent` 的无密钥 PTY 冒烟测试（`tui-keyless-smoke.e2e.ts`）在真实伪终端下经由 loader 引导生产环境的 TUI/agent/skill 栈，仅对模型进行脚本化，把一个夹具 skill 放入 agents home 的 `skills/` 根下，以真实按键输入 `/skill:`，并断言：只有当渲染出的 `` 文本块抵达时，脚本化适配器才会回显该夹具的正文标记——从而一并演练了 `ctx.get('skills')` 在发布树中的解析、客户端解析、本地 provider 的加载，以及用户回合抵达模型。该夹具的 frontmatter 描述避免出现 `: ` 冒号加空格，使其 YAML 保持为纯标量；frontmatter 无效的 skill 会在发现阶段被静默丢弃。 +手动调用总是重新加载完整的 skill 正文：TUI 不会检测某个 skill 是否已在对话中出现，因此重复的 `/skill:` 会再次追加其指令——这可以接受，因为重新注入有时正是意图所在，且已在本包 README 的已知限制中说明。上文接受的双渲染器重复是一项长期维护成本。`` 包装层是稳定的、模型可见的文本，并在包测试中针对一个真实的 `SkillService` 逐字固定；包语义矩阵固定帮助面板中的这一行。自动补全填充、仅限用户的发现、向空闲及运行中 agent 投递，以及 dispose 后查找和查找失败分支，都由挂载真实注册表或可控服务的包测试覆盖。已移除的产品 TUI 的无密钥 PTY 冒烟测试过去覆盖组装后的 Loader 路径；未来的终端部署负责该应用级场景。 diff --git a/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.i18n.yaml b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.i18n.yaml new file mode 100644 index 0000000000..5e79c40332 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.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/2026-07-23-tui-file-reference-autocomplete.md +2026-07-23-tui-file-reference-autocomplete.md: 3ceda81858bc3364a2c4ac5b91d599b23479412a +2026-07-23-tui-file-reference-autocomplete.zh.md: c0b947edf6df42d27f5fee40d95eb073029e32b1 diff --git a/.agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.md b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.md similarity index 96% rename from .agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.md rename to .agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.md index 1a13600921..3ceda81858 100644 --- a/.agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.md +++ b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.md @@ -1,6 +1,7 @@ # Agent Note: TUI file-reference autocomplete Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-23-tui-file-reference-autocomplete.zh.md) @@ -30,4 +31,4 @@ Structured session mentions keep their existing snapshot preparation. Unlike fil Users can discover and insert paths without making selection itself expensive or model-visible beyond the path. The model preserves agency over whether to inspect a file, and any inspection remains reconstructable through the logged tool transcript. The fixed instruction slightly enlarges TUI system prompts when `read` is present, and content-requiring requests take an additional tool round trip. -Completion is deliberately bounded and advisory: very large workspaces may omit paths beyond the configured index cap, ignored files may still appear, and remote or virtual filesystem deployments must align the TUI host working directory with the `read` namespace or supply a different completion surface. Package tests pin token grammar, ranking, bounds, cancellation, invalidation, and path-only submission; terminal snapshots and the real Loader PTY smoke pin the visible menu and keyboard completion. +Completion is deliberately bounded and advisory: very large workspaces may omit paths beyond the configured index cap, ignored files may still appear, and remote or virtual filesystem deployments must align the TUI host working directory with the `read` namespace or supply a different completion surface. Package tests pin token grammar, ranking, bounds, cancellation, invalidation, path-only submission, the visible menu, and keyboard completion; a deployment shipping the TUI owns its Loader and PTY acceptance. diff --git a/.agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.zh.md b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.zh.md similarity index 95% rename from .agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.zh.md rename to .agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.zh.md index 410f0d49db..c0b947edf6 100644 --- a/.agents/notes/implemented/feature/2026-07-23-tui-file-reference-autocomplete.zh.md +++ b/.agents/notes/archived/feature/2026-07-23-tui-file-reference-autocomplete.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 文件引用自动补全 Status: implemented +Archived: 2026-08-04 [English](2026-07-23-tui-file-reference-autocomplete.md) | 中文 @@ -30,4 +31,4 @@ TUI 维护一个有容量上限且可取消的主机工作区路径索引，以 用户可以发现并插入路径，而选择操作本身不会带来高开销，对模型可见的内容也仅限路径。模型仍可自行决定是否检查文件，任何检查都能通过已记录的工具 transcript 重建。存在 `read` 时，固定指令会略微增大 TUI 系统提示词；需要文件内容的请求还会增加一次工具往返。 -补全有意采用有界的提示性设计：超大型工作区可能省略超过配置索引上限的路径，被忽略的文件仍可能出现，远程或虚拟文件系统部署必须让 TUI 的主机工作目录与 `read` 命名空间对齐，否则需要提供不同的补全接口。包（package）测试固定 token 语法、排序、边界、取消、失效和仅提交路径的行为；终端快照与真实 Loader PTY 冒烟测试固定可见菜单和键盘补全。 +补全有意采用有界的提示性设计：超大型工作区可能省略超过配置索引上限的路径，被忽略的文件仍可能出现，远程或虚拟文件系统部署必须让 TUI 的主机工作目录与 `read` 命名空间对齐，否则需要提供不同的补全接口。包（package）测试固定 token 语法、排序、边界、取消、失效、仅提交路径的行为、可见菜单和键盘补全；交付 TUI 的部署负责其 Loader 与 PTY 验收。 diff --git a/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.i18n.yaml b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.i18n.yaml new file mode 100644 index 0000000000..0322b85af5 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.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/2026-07-23-tui-status-prompt-tools.md +2026-07-23-tui-status-prompt-tools.md: b8e5e9fc4fd8f9d6dafa689512ef991ee1013b39 +2026-07-23-tui-status-prompt-tools.zh.md: 3d10073b4332609371fdd1ebed7486970b439251 diff --git a/.agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.md b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.md similarity index 87% rename from .agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.md rename to .agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.md index 42524d021d..b8e5e9fc4f 100644 --- a/.agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.md +++ b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.md @@ -1,6 +1,7 @@ # Agent Note: TUI status inspects model request inputs Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-23-tui-status-prompt-tools.zh.md) @@ -26,4 +27,4 @@ The command can run prompt providers and assembly listeners, just like request p ## Testing -Unit coverage pins scoped assembly output, ordered tool names, empty labels, and terminal-control escaping. The keyless TUI smoke and terminal snapshot exercise `/status` through the assembled application. +Package behavior tests pin scoped assembly output, ordered tool names, empty labels, and terminal-control escaping. The package semantic snapshots exercise `/status` at normal and narrow widths; a deployment shipping the TUI owns its assembled process acceptance. diff --git a/.agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.zh.md b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.zh.md similarity index 87% rename from .agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.zh.md rename to .agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.zh.md index 5a33e19e97..3d10073b43 100644 --- a/.agents/notes/implemented/feature/2026-07-23-tui-status-prompt-tools.zh.md +++ b/.agents/notes/archived/feature/2026-07-23-tui-status-prompt-tools.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 状态检查模型请求输入 Status: implemented +Archived: 2026-08-04 [English](2026-07-23-tui-status-prompt-tools.md) | 中文 @@ -26,4 +27,4 @@ Status: implemented ## 测试 -单元测试固定按作用域组装的输出、工具名称顺序、空值标签和终端控制字符转义。无密钥 TUI 冒烟测试与终端快照通过完整组装的应用执行 `/status`。 +包（package）行为测试固定按作用域组装的输出、工具名称顺序、空值标签和终端控制字符转义。包级语义快照在正常宽度和窄宽度下执行 `/status`；交付 TUI 的部署负责其组装后的进程验收。 diff --git a/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.i18n.yaml b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.i18n.yaml new file mode 100644 index 0000000000..29edf8a739 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.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/2026-07-24-configurable-tui-prompt-theme.md +2026-07-24-configurable-tui-prompt-theme.md: 918eaa617811049a5caa4b9f43a8cc12854471c3 +2026-07-24-configurable-tui-prompt-theme.zh.md: eccfed00c3fe866291d2f18bd7cecf117296bd58 diff --git a/.agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.md b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.md similarity index 93% rename from .agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.md rename to .agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.md index f8815c6c19..918eaa6178 100644 --- a/.agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.md +++ b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.md @@ -1,6 +1,7 @@ # Agent Note: TUI prompt themes compose mutable plugin values Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-24-configurable-tui-prompt-theme.zh.md) @@ -36,4 +37,4 @@ Changing `inputPrompt` through a registered value preserves editor text, cursor, ## Testing -Registry tests pin validation, duplicate rejection, updates, unavailable values, coalesced-notification containment, unsubscribe, disposal, interpolation, trailing-literal retention, whitespace cleanup, and ANSI preservation. TUI tests pin nested theme defaults, custom templates, out-of-band value redraw, mutable redraw, Powerline-capable fragments, dynamic input-prefix width, and the static running placeholder. The assembled TUI demo test pins service load order and config forwarding. +Registry tests pin validation, duplicate rejection, updates, unavailable values, coalesced-notification containment, unsubscribe, disposal, interpolation, trailing-literal retention, whitespace cleanup, and ANSI preservation. TUI package tests pin service availability, nested theme defaults, config forwarding, custom templates, out-of-band value redraw, mutable redraw, Powerline-capable fragments, dynamic input-prefix width, and the static running placeholder. A deployment shipping the TUI owns assembled load-order acceptance. diff --git a/.agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.zh.md b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.zh.md similarity index 92% rename from .agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.zh.md rename to .agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.zh.md index 831471860a..eccfed00c3 100644 --- a/.agents/notes/implemented/feature/2026-07-24-configurable-tui-prompt-theme.zh.md +++ b/.agents/notes/archived/feature/2026-07-24-configurable-tui-prompt-theme.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 提示符主题组合可变的插件值 Status: implemented +Archived: 2026-08-04 [English](2026-07-24-configurable-tui-prompt-theme.md) | 中文 @@ -36,4 +37,4 @@ TUI 主题把 `color`、`truecolor`、`leftPrompt`、`rightPrompt`、`inputPromp ## 测试 -注册表测试固定校验、重名拒绝、更新、不可用值、合并通知的容错、取消订阅、dispose、插值、尾随字面保留、空白清理与 ANSI 保留等行为。TUI 测试固定嵌套主题默认值、自定义模板、带外值重绘、可变重绘、支持 Powerline 的片段、动态输入前缀宽度以及运行状态下的静态占位文本。组装后的 TUI 演示测试固定服务加载顺序与配置转发。 +注册表测试固定校验、重名拒绝、更新、不可用值、合并通知的容错、取消订阅、dispose、插值、尾随字面保留、空白清理与 ANSI 保留等行为。TUI 包（package）测试固定服务可用性、嵌套主题默认值、配置转发、自定义模板、带外值重绘、可变重绘、支持 Powerline 的片段、动态输入前缀宽度以及运行状态下的静态占位文本。交付 TUI 的部署负责组装后的加载顺序验收。 diff --git a/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.i18n.yaml b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.i18n.yaml new file mode 100644 index 0000000000..90558a3d22 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.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/2026-07-24-tui-question-dialog-multiline.md +2026-07-24-tui-question-dialog-multiline.md: 9f1e75325942f28d69d9cadadf938c0f0b5e3ae5 +2026-07-24-tui-question-dialog-multiline.zh.md: bd112898367e7a7dd940f2b5fa76e531029ab803 diff --git a/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.md b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.md new file mode 100644 index 0000000000..9f1e753259 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.md @@ -0,0 +1,42 @@ +# Agent Note: TUI QuestionDialog renders options across multiple lines + +Status: implemented +Archived: 2026-08-04 + +English | [中文](2026-07-24-tui-question-dialog-multiline.zh.md) + +## Problem + +`ctx.userInteraction.ask()` must keep question text, supporting `detail`, option labels, descriptions, validation, and controls readable inside configured width and height bounds. The question panel also belongs directly above the editor: placing it at the terminal edge separates the pending decision from both the transcript that prompted it and the input that follows it. + +## Decision + +The TUI renders a pending question as an inline modal between the transcript/status area and the editor while retaining the shared FIFO with model and plugin overlays: + +- `InlineModalComponent` applies `questionDialogWidth` and `questionDialogMaxHeight` inside the normal component flow. The effective question height is additionally clamped to the current viewport after reserving the editor, so the editor remains below the question during resize. +- `renderOptionBlock` wraps each label beneath its cursor/number prefix and renders the muted description on separately wrapped, equally indented lines. The progress header, question, custom-answer hint, validation text, and final rows are width-bounded as well; the final ellipsis clamp is only a safety boundary for prefixes or other indivisible content. The explicit `↑ N lines hidden` fallback is reserved for a viewport below the configured minimum, where the whole semantic layout cannot fit. +- When question text or `detail` exceeds the header allocation, the header becomes a paged line viewport with its own `… lines A-B/N • PgUp/PgDn` status row. Page Up and Page Down traverse both line viewports: forward navigation exhausts the header/detail pages before entering oversized selected-option pages, and backward navigation reverses that order. This keeps plan-review detail reachable rather than leaving it behind the height clamp. +- The option-line budget subtracts padding, header, position, and footer rows before `windowBlocks` runs. The window obeys both `maxQuestionOptions` and the remaining row budget, keeps the selected option visible, and renders omitted options as `↑ N more` / `↓ N more` markers. If fixed chrome would leave fewer than four option rows, the compact header becomes the line pager so selected content, paging status, and both option markers still fit. +- When one selected block exceeds its allocation, it becomes a line viewport with a `lines A-B/N • PgUp/PgDn` status row. Page Up and Page Down expose every wrapped line without allowing the block to hide the option markers, validation, or controls. + +Package tests pin count and height bounds, header and selected-block paging order, narrow-width wrapping, selection behavior, and placement relative to retained editor input. Semantic TUI snapshots pin the assembled terminal layout, header/detail and selected-option page transitions, and validation state. + +## Alternatives considered + +**Ellipsis-only horizontal truncation.** Keeping one option per row would signal lost text without making the description readable and would not address vertical bounds. The implementation wraps readable content and retains an ellipsis only as a final safety boundary. + +**Wrap the combined label and description.** A composite row couples their widths, so either side can starve the other. Separate lines keep both widths predictable. + +**Keep the question as a bottom-edge overlay.** A terminal-edge anchor can place the panel after the editor or cover lower chrome, depending on transcript and viewport height. The inline modal preserves ordering while the modal manager retains focus and FIFO ownership. + +**Push the bounds into pi-tui.** Generic overlay slicing cannot identify option boundaries, selected content, controls, or the inline editor relationship. The owning dialog therefore applies semantic count, row, and paging rules. + +**Use only the option-count cap.** `maxQuestionOptions` remains a public count bound, but it cannot contain wrapped blocks by itself. The dialog enforces the count and row bounds together. + +## Consequences + +- Descriptions consume additional rows, so fewer options can be visible than `maxQuestionOptions`; markers state the omitted option counts. +- Long question text and plan-review detail remain reachable inside a height-bounded panel, at the cost of sharing Page Up and Page Down with selected-option paging. +- An oversized selected block reserves one status row and requires Page Up or Page Down to read beyond the current line page. +- The inline question can displace older transcript rows from a short viewport. Below the configured minimum height, the final fallback can collapse upper rows behind an explicit hidden-line marker so the input controls and editor remain available. +- The model-facing schema, selected labels, abort/cancel behavior, and ACP elicitation path are unchanged. diff --git a/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.zh.md b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.zh.md new file mode 100644 index 0000000000..bd11289836 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-24-tui-question-dialog-multiline.zh.md @@ -0,0 +1,42 @@ +# Agent Note: TUI QuestionDialog 以多行方式渲染选项 + +Status: implemented +Archived: 2026-08-04 + +[English](2026-07-24-tui-question-dialog-multiline.md) | 中文 + +## 问题 + +`ctx.userInteraction.ask()` 必须确保问题正文、`detail` 补充内容、选项标签、描述、校验信息和控件在已配置的宽度与高度边界内均可读。问题面板也直接位于编辑器上方：若将其置于终端边缘，待处理决策就会同时脱离触发该决策的 transcript（文本记录）和后续输入。 + +## 决策 + +TUI 将待处理问题渲染为位于 transcript／状态区域与编辑器之间的内联模态框，同时仍与模型浮层和插件浮层共享 FIFO： + +- `InlineModalComponent` 在正常组件流内应用 `questionDialogWidth` 和 `questionDialogMaxHeight`。系统在为编辑器预留空间后，还会根据当前视口限制问题的实际高度，因此调整窗口大小时，编辑器仍位于问题下方。 +- `renderOptionBlock` 将每个标签换行到光标／编号前缀下方，并在另行换行且缩进相同的行上渲染弱化的描述。进度标题、问题、自定义答案提示、校验文本和末尾行也受宽度边界约束；最终的省略号截断仅作为前缀或其他不可拆分内容的安全边界。明确的 `↑ N lines hidden` 回退仅用于低于已配置最小值、无法容纳完整语义布局的视口。 +- 当问题正文或 `detail` 超出头部分配的空间时，头部会成为带有独立 `… lines A-B/N • PgUp/PgDn` 状态行的分页行视口。Page Up 和 Page Down 会遍历这两个行视口：向前导航先翻完问题正文／`detail` 页面，再进入超大选中选项页面；向后导航则采用相反顺序。这样可确保计划评审的 `detail` 内容始终可达，而不会被高度边界挡住。 +- 在 `windowBlocks` 运行前，选项行预算会扣除内边距、标题行、位置行和页脚行。窗口同时遵守 `maxQuestionOptions` 和剩余行预算，保持选中项可见，并将省略的选项渲染为 `↑ N more`／`↓ N more` 标记。若固定界面元素会使选项行少于四行，紧凑头部会转为行分页器，从而容纳选中内容、分页状态和上下两个选项标记。 +- 当一个选中块超出分配空间时，它会成为带有 `lines A-B/N • PgUp/PgDn` 状态行的行视口。Page Up 和 Page Down 可展示每一行已换行内容，同时防止该块遮住选项标记、校验信息或控件。 + +包（package）测试固定数量和高度边界、头部与选中块的分页顺序、窄宽度换行、选择行为，以及问题相对于保留的编辑器输入的位置。语义 TUI 快照固定组装后的终端布局、头部／详情与选中选项的分页转换，以及校验状态。 + +## 备选方案 + +**仅用省略号进行横向截断。** 保持每个选项占一行，只能提示文本有所丢失，无法使描述变得可读，也无法处理纵向边界。该实现会对可读内容换行，仅将省略号保留为最终安全边界。 + +**将标签与描述合并后换行。** 组合行会将两者的宽度耦合在一起，任一方都可能挤占另一方的空间。分行渲染可使二者的宽度保持可预测。 + +**将问题保留为终端底边浮层。** 根据 transcript 和视口高度，锚定在终端边缘的面板可能出现在编辑器之后，也可能遮盖下方界面元素。内联模态框可保留顺序，同时由模态管理器继续负责焦点和 FIFO 所有权。 + +**将边界处理下推至 pi-tui。** 通用浮层切片无法识别选项边界、选中内容、控件或内联编辑器关系。因此，负责该语义的对话框会应用数量、行数和分页规则。 + +**仅使用选项数量上限。** `maxQuestionOptions` 仍是公开的数量边界，但仅靠它无法容纳已换行的块。对话框会同时执行数量边界和行数边界。 + +## 后果 + +- 描述会占用额外行，因此可见选项数可能少于 `maxQuestionOptions`；标记会说明省略的选项数量。 +- 较长的问题正文和计划评审 `detail` 在受高度约束的面板内仍然可达，代价是 Page Up 和 Page Down 需要与选中选项分页共用。 +- 超出空间的选中块会预留一行状态信息；若要阅读当前页面之外的行，必须使用 Page Up 或 Page Down。 +- 在较矮的视口内，内联问题可能将较早的 transcript 行挤出可见区域。低于已配置最小高度时，最终回退可能将上部行折叠到明确的隐藏行标记之后，从而让输入控件和编辑器仍然可用。 +- 面向模型的 schema、选中的标签、中止／取消行为，以及 ACP（Agent Client Protocol）的 elicitation 路径均保持不变。 diff --git a/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.i18n.yaml b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.i18n.yaml new file mode 100644 index 0000000000..a78bd1a593 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.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/2026-07-24-tui-shell-prompt-editor.md +2026-07-24-tui-shell-prompt-editor.md: a3707d3fcd0ae30517083ed388eb38cb3b92cad7 +2026-07-24-tui-shell-prompt-editor.zh.md: ca050e2000ff772389086b5023935c816ec1154e diff --git a/.agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.md b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.md rename to .agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.md index bba03e788b..a3707d3fcd 100644 --- a/.agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.md +++ b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.md @@ -1,6 +1,7 @@ # Agent Note: TUI shell-prompt editor Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-24-tui-shell-prompt-editor.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.zh.md b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.zh.md rename to .agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.zh.md index 1897d11292..ca050e2000 100644 --- a/.agents/notes/implemented/feature/2026-07-24-tui-shell-prompt-editor.zh.md +++ b/.agents/notes/archived/feature/2026-07-24-tui-shell-prompt-editor.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI shell 提示符编辑器 Status: implemented +Archived: 2026-08-04 [English](2026-07-24-tui-shell-prompt-editor.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.i18n.yaml b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.i18n.yaml new file mode 100644 index 0000000000..2d8d84405a --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.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/2026-07-27-assistant-timing-header-trailing.md +2026-07-27-assistant-timing-header-trailing.md: 2ef926cff989499aa05ebfa781eea10399c69d18 +2026-07-27-assistant-timing-header-trailing.zh.md: 282ac1e65b3c4e185839d3c6b70a085f685e8013 diff --git a/.agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.md b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.md similarity index 98% rename from .agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.md rename to .agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.md index a315a0620c..2ef926cff9 100644 --- a/.agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.md +++ b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.md @@ -1,6 +1,7 @@ # Agent Note: Assistant timing line renders after the message body Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-assistant-timing-header-trailing.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.zh.md b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.zh.md similarity index 98% rename from .agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.zh.md rename to .agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.zh.md index 84b8612337..282ac1e65b 100644 --- a/.agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.zh.md +++ b/.agents/notes/archived/feature/2026-07-27-assistant-timing-header-trailing.zh.md @@ -1,6 +1,7 @@ # Agent Note: Assistant timing line renders after the message body Status: implemented +Archived: 2026-08-04 [English](2026-07-27-assistant-timing-header-trailing.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.i18n.yaml b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.i18n.yaml new file mode 100644 index 0000000000..0ceac7c49a --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.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/2026-07-27-tui-running-glyph-smooth-fade.md +2026-07-27-tui-running-glyph-smooth-fade.md: 09a944a5e39d407713da5665a3dd32a171a04bc1 +2026-07-27-tui-running-glyph-smooth-fade.zh.md: 5fc6a7e490670ce02d011651741a952cfb97dcce diff --git a/.agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.md b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.md rename to .agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.md index e4c8fee399..09a944a5e3 100644 --- a/.agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.md +++ b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.md @@ -1,6 +1,7 @@ # Agent Note: Dim-gray pulse for the running prompt glyph Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-tui-running-glyph-smooth-fade.zh.md) diff --git a/.agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md rename to .agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md index 25bda3d549..5fc6a7e490 100644 --- a/.agents/notes/implemented/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md +++ b/.agents/notes/archived/feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md @@ -1,6 +1,7 @@ # Agent Note: Dim-gray pulse for the running prompt glyph Status: implemented +Archived: 2026-08-04 [English](2026-07-27-tui-running-glyph-smooth-fade.md) | 中文 diff --git a/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.i18n.yaml b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.i18n.yaml new file mode 100644 index 0000000000..8653f43d71 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.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/2026-07-27-tui-tool-card-header.md +2026-07-27-tui-tool-card-header.md: f054ca378481be477ac2d261423c3e6af2035b2a +2026-07-27-tui-tool-card-header.zh.md: bf3bf39662f8cc04a28d8f5ea411077bb190c59a diff --git a/.agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.md b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.md similarity index 93% rename from .agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.md rename to .agents/notes/archived/feature/2026-07-27-tui-tool-card-header.md index 13f5e7fec1..f054ca3784 100644 --- a/.agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.md +++ b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.md @@ -1,6 +1,7 @@ # Agent Note: Fixed `Tool / ` header for tool-call cards Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-tui-tool-card-header.zh.md) @@ -32,4 +33,4 @@ A tool call now shows its identity in one stable place, and status reads as one ## Testing -`packages/ui/tui/tests/tui.spec.ts` pins the new header (`Tool / `), the dropped diff title, the relocated generic title, and the `· N file(s)` footer. The keyless terminal snapshots under `packages/ui/tui/tests/snapshots/` and `examples/tui-agent/tests/snapshots/` — rendered through the real assembled TUI and a pseudo-terminal — were re-recorded and show the new cards for read, bash (described and undescribed), edit, and the other tools. +`packages/ui/tui/tests/tui.spec.ts` pins the new header (`Tool / `), the dropped diff title, the relocated generic title, and the `· N file(s)` footer. Package semantic snapshots cover the card families in a headless terminal. The deleted application journeys formerly supplied assembled tool executions; a future terminal deployment owns equivalent transcript coverage. diff --git a/.agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.zh.md b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.zh.md similarity index 93% rename from .agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.zh.md rename to .agents/notes/archived/feature/2026-07-27-tui-tool-card-header.zh.md index 85f9f1244a..bf3bf39662 100644 --- a/.agents/notes/implemented/feature/2026-07-27-tui-tool-card-header.zh.md +++ b/.agents/notes/archived/feature/2026-07-27-tui-tool-card-header.zh.md @@ -1,6 +1,7 @@ # Agent Note: Fixed `Tool / ` header for tool-call cards Status: implemented +Archived: 2026-08-04 [English](2026-07-27-tui-tool-card-header.md) | 中文 @@ -32,4 +33,4 @@ TUI 曾把每次工具调用渲染为 `{glyph} {title}`，其中 `title` 是 pre ## Testing -`packages/ui/tui/tests/tui.spec.ts` 固定了新表头（`Tool / `）、弃用的 diff 标题、迁移后的 generic 标题以及 `· N file(s)` 页脚。`packages/ui/tui/tests/snapshots/` 与 `examples/tui-agent/tests/snapshots/` 下的无密钥终端快照——经由真实组装的 TUI 与伪终端渲染——已重新录制，展示了 read、bash（有描述与无描述）、edit 及其他工具的新卡片。 +`packages/ui/tui/tests/tui.spec.ts` 固定了新表头（`Tool / `）、弃用的 diff 标题、迁移后的 generic 标题以及 `· N file(s)` 页脚。包级语义快照在无界面终端中覆盖各类卡片。已删除的应用流程此前提供组装后的工具执行；未来的终端部署负责提供等价的 transcript 覆盖。 diff --git a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml similarity index 67% rename from .agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml rename to .agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml index c60a7f0127..8feded0ad4 100644 --- a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml +++ b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.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/feature/2026-07-28-dsh-guided-skill-session-commands.md -2026-07-28-dsh-guided-skill-session-commands.md: a11807dca9ad1640857cd95a8b528df691b8a27e -2026-07-28-dsh-guided-skill-session-commands.zh.md: e48420ed77496d8c336031473364f9008fccced7 +2026-07-28-dsh-guided-skill-session-commands.md: 454d090a55db8987f8e4987aba67deff1b21b1a0 +2026-07-28-dsh-guided-skill-session-commands.zh.md: 64dad4e39c6fd3e3341313c3f8dd2b04947695cf diff --git a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.md b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.md similarity index 89% rename from .agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.md rename to .agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.md index a11807dca9..454d090a55 100644 --- a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.md +++ b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.md @@ -1,6 +1,7 @@ # Agent Note: `dsh migrate`/`dsh upgrade` seed the first turn with a skill Status: implemented +Archived: 2026-08-03 English | [中文](2026-07-28-dsh-guided-skill-session-commands.zh.md) @@ -16,7 +17,7 @@ The seed reuses the existing TUI skill path, not a new one. `createTuiChat` alre **Freshness is gated in the launcher, not the TUI.** `runSkillSession` always mints a fresh session and provides the slot only when `resumeSessionId === undefined`, so a later `dsh --resume ` of that session is an ordinary TUI session with no re-injection. The TUI stays generic: it invokes whatever skill it is handed, once, at startup. -**`migrate`/`upgrade` take no options.** Unlike `meta`, they carry no `--resume`, `--config`, or `-p`; a guided fresh-session entry has nothing to resume or reconfigure. Any leaked default-surface option fails loud, matching the `web`/`meta` rejection pattern in the Commander adapter. The two modes share one `SkillSessionInvocation` discriminant (`mode: 'migrate' | 'upgrade'`); `bin.ts` maps the mode to `dsh-${mode}`. +**`migrate`/`upgrade` take no default-surface options** (`upgrade` additionally carries the [experimental gate](2026-07-31-experimental-subcommand-gate.md)'s `--experimental`). They carry no `--resume`, `--config`, or `-p`; a guided fresh-session entry has nothing to resume or reconfigure. Any leaked default-surface option fails loud, matching the `web`/`meta` rejection pattern in the Commander adapter. The two modes share one `SkillSessionInvocation` discriminant (`mode: 'migrate' | 'upgrade'`); `bin.ts` maps the mode to `dsh-${mode}`. The `dsh-migrate` skill is bundled under `skills/` (shipped through `DSH_BUNDLED_SKILL_DIR`, like `dsh-upgrade`). It asks which source agent (opencode/pi/Claude Code/Codex) if unstated, then maps each capability — workspace instructions, personal overlay, skills, hooks, MCP, API/env — to its DSH equivalent, grounded in the actual repo surfaces (the `hooks-claude`/`hooks-codex` bridges, `~/.dsh/{config.yaml,.env,AGENTS.md,skills/}`, `AGENTS.md`/`CLAUDE.md`, `mcporter`), and states plainly when a capability has no equivalent. diff --git a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md similarity index 88% rename from .agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md rename to .agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md index e48420ed77..64dad4e39c 100644 --- a/.agents/notes/implemented/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md +++ b/.agents/notes/archived/feature/2026-07-28-dsh-guided-skill-session-commands.zh.md @@ -1,6 +1,7 @@ -# Agent Note：`dsh migrate`/`dsh upgrade` 以 skill 播种首轮 +# Agent Note: `dsh migrate`/`dsh upgrade` 以 skill 播种首轮 Status: implemented +Archived: 2026-08-03 [English](2026-07-28-dsh-guided-skill-session-commands.md) | 中文 @@ -16,7 +17,7 @@ Status: implemented **新鲜性在启动器而非 TUI 中把关。** `runSkillSession` 总是创建全新会话，且仅在 `resumeSessionId === undefined` 时提供该槽，因此之后 `dsh --resume ` 恢复该会话时是普通 TUI 会话，不会重复注入。TUI 保持通用：它只是把接到的 skill 在启动时调用一次。 -**`migrate`/`upgrade` 不接受任何选项。** 与 `meta` 不同，它们不带 `--resume`、`--config` 或 `-p`；引导式全新会话入口没有可恢复或可重配置的内容。任何泄漏的默认界面选项都会明确报错，与 Commander 适配器中 `web`/`meta` 的拒绝模式一致。两个 mode 共用一个 `SkillSessionInvocation` 判别式（`mode: 'migrate' | 'upgrade'`）；`bin.ts` 将 mode 映射为 `dsh-${mode}`。 +**`migrate`/`upgrade` 不接受任何默认界面选项**（`upgrade` 另带[实验性门槛](2026-07-31-experimental-subcommand-gate.md)的 `--experimental`）。它们不带 `--resume`、`--config` 或 `-p`；引导式全新会话入口没有可恢复或可重配置的内容。任何泄漏的默认界面选项都会明确报错，与 Commander 适配器中 `web`/`meta` 的拒绝模式一致。两个 mode 共用一个 `SkillSessionInvocation` 判别式（`mode: 'migrate' | 'upgrade'`）；`bin.ts` 将 mode 映射为 `dsh-${mode}`。 `dsh-migrate` skill 内置于 `skills/`（经 `DSH_BUNDLED_SKILL_DIR` 交付，与 `dsh-upgrade` 相同）。若未说明源 agent，它会先询问是哪个（opencode/pi/Claude Code/Codex），再把每项能力——workspace 指令、个人覆盖、skills、hooks、MCP、API/env——映射到对应的 DSH 等价物，并基于仓库实际的表面（`hooks-claude`/`hooks-codex` 桥、`~/.dsh/{config.yaml,.env,AGENTS.md,skills/}`、`AGENTS.md`/`CLAUDE.md`、`mcporter`）落地；当某能力无等价物时明确说明。 diff --git a/.agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml similarity index 68% rename from .agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml rename to .agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml index 1a7c941216..1df1788849 100644 --- a/.agents/notes/implemented/feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml +++ b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.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/feature/2026-07-28-dsh-meta-source-workspace.md -2026-07-28-dsh-meta-source-workspace.md: d65e0e6ff092b63931dd58c52fa76fb76a071dff -2026-07-28-dsh-meta-source-workspace.zh.md: 72a0c65e6eeda7d63dccc2306a3d7625cdb54362 +2026-07-28-dsh-meta-source-workspace.md: 1e433bb50ae5cd5cc893e867d0f4b6edce2bf168 +2026-07-28-dsh-meta-source-workspace.zh.md: 95b1edabbbac2e78d09097db614ee4e5d1b33bf7 diff --git a/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.md b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.md new file mode 100644 index 0000000000..1e433bb50a --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.md @@ -0,0 +1,42 @@ +# Agent Note: `dsh meta` boots the TUI over the harness checkout + +Status: implemented +Archived: 2026-08-03 + +English | [中文](2026-07-28-dsh-meta-source-workspace.zh.md) + +## Problem + +`dsh` treats the invoking directory as the workspace, which is what makes it useful on arbitrary projects. Working on dsh itself therefore means `cd`-ing to the checkout first — and the checkout is not a memorable path: the source install keeps it under a container directory as a timestamped staging worktree (`~/.dsh/source/staging-`) behind a `current` symlink, so the target moves on every upgrade. The agent is already *told* where its source lives by the `harness:source` prompt section, and the `cordis` toolset can modify that runtime, but the human still had to locate the directory by hand to start a session there. + +## Decision + +`dsh meta` boots the ordinary TUI with the harness checkout as the workspace, from any directory. + +The target is `SOURCE_ROOT` in `apps/cli/src/tui.ts` — `fileURLToPath(new URL('../../..', import.meta.url))`, three hops up from `apps/cli/{src,lib}` — the same constant the `harness:source` prompt section already names, so the workspace and the path advertised to the model cannot drift. It follows the launcher's real path, so a PATH symlink through `current` resolves to whichever staging worktree is active. + +The mechanism is one `process.chdir(workspace)` inside `runTui`, guarded by an optional third parameter that only the `meta` dispatch passes. The cwd *is* the workspace seam in the shipped tree: `examples/tui-agent/cordis.yml` derives the session cwd (`!!js process.cwd()`), the `./.sessions` persistence root, and the HMR watch root (`root: ['.']`) from it, so one chdir moves all three together and meta sessions land in the checkout's gitignored `.sessions/`. It runs after both `.env` layers are loaded — the bin's invoking-directory load and the personal one — so the ambient > project > personal precedence is untouched. `DEFAULT_CONFIG` and `SOURCE_ROOT` are absolute and TUI mode passes no snapshot mode, so config resolution is chdir-independent. + +`meta` always starts a fresh session and accepts no default-surface options; its only option is the [experimental gate](2026-07-31-experimental-subcommand-gate.md)'s `--experimental`. `--config` would boot a foreign tree against the harness workspace, which is the default surface's `--config` case rather than this command; `-p` is not interactive, and resume re-enters the persisted session's own workspace through `dsh --resume `. Any leaked default-surface option fails loud. + +## Testing + +`apps/cli/tests/args.spec.ts` pins routing for `meta`, rejection of every leaked default-surface option, and rejection of the former `experimental-meta` name. The dispatch itself is composition inside `bin.ts`'s existing `v8 ignore` block. + +There is no keyless PTY smoke for this mode. The smoke harness gives each run a temp cwd, but `dsh meta` deliberately chdirs to the real checkout, so a smoke would write `.sessions/` into the live tree mid-test. Covering it properly needs an injectable target directory — a test-only seam this note declines to add for a one-line chdir. + +The mode was verified interactively instead. Launched from `$HOME`, a `pwd` tool call reports the checkout, git resolves to its branch, the session log lands under the checkout's `.sessions/` (leaving `~/.sessions` untouched and the tree free of unignored residue), and plain `dsh` from another directory still uses the invoking one. + +## Alternatives considered + +**Thread an explicit workspace through `boot` and the config tree.** Avoids mutating process-wide state, but the shipped config reads the cwd in three places (`!!js process.cwd()`, `persistenceRoot`, HMR `root`), so each would need its own new plumbing and config key to stay consistent. `chdir` before boot expresses "this is the workspace" once, at the seam that already means it. + +**An `--experimental-meta` flag on the default surface.** Rejected: the default surface is option-only so that subcommands do not collide with a positional, and a flag that silently relocates the workspace reads as a modifier of the current directory rather than a different target. `meta` alongside `web` matches the existing shape. + +**Resolve `~/.dsh/source/current` instead of the launcher's own path.** Rejected: it would diverge from the `harness:source` prompt path whenever a non-installed checkout's `bin/dsh` is invoked directly, telling the model one source root while working in another. + +## Consequences + +Starting a session on dsh's own source is `dsh meta --experimental` from anywhere (or bare `dsh meta` under `DSH_EXPERIMENTAL=1`), and the workspace is guaranteed to be the same checkout the model is told about. The command always starts fresh; an ordinary `dsh --resume ` later restores the session and enters its persisted workspace. + +`runTui` gains an optional third parameter, so the workspace override is visible at the one function that owns TUI composition rather than hidden in a second copy of it. diff --git a/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.zh.md b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.zh.md new file mode 100644 index 0000000000..95b1edabbb --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-28-dsh-meta-source-workspace.zh.md @@ -0,0 +1,42 @@ +# Agent Note: `dsh meta` 以 harness 检出为 workspace 启动 TUI + +Status: implemented +Archived: 2026-08-03 + +[English](2026-07-28-dsh-meta-source-workspace.md) | 中文 + +## Problem + +`dsh` 把调用目录视为 workspace，这正是它能作用于任意项目的原因。但因此，开发 dsh 自身就得先 `cd` 到检出目录——而该目录并不是一个好记的路径：源码安装会把它放在一个容器目录下、作为带时间戳的 staging 工作树（`~/.dsh/source/staging-`），并由 `current` 符号链接指向，因此每次升级后目标都会变化。`harness:source` 提示词段已经*告知* agent 其源码位置，`cordis` 工具集也能修改该运行时，但人类仍需手工定位该目录才能在其中开始会话。 + +## Decision + +`dsh meta` 在任意目录下都以 harness 检出为 workspace 启动普通 TUI。 + +目标是 `apps/cli/src/tui.ts` 中的 `SOURCE_ROOT`——`fileURLToPath(new URL('../../..', import.meta.url))`，从 `apps/cli/{src,lib}` 向上三级——与 `harness:source` 提示词段所用的常量完全相同，因此 workspace 与告知模型的路径不可能发生偏离。它跟随启动器的真实路径，所以经由 `current` 的 PATH 符号链接会解析到当前生效的那个 staging 工作树。 + +机制是 `runTui` 内的一次 `process.chdir(workspace)`，由一个可选第三参数把守，只有 `meta` 分派会传入。在已交付的配置树中，cwd *就是* workspace 的接缝：`examples/tui-agent/cordis.yml` 由它派生出会话 cwd（`!!js process.cwd()`）、`./.sessions` 持久化根目录以及 HMR 监视根目录（`root: ['.']`），因此一次 chdir 会让三者一并移动，meta 会话则落在检出目录中被 gitignore 的 `.sessions/` 内。它在两层 `.env` 都加载之后执行——bin 对调用目录的加载与个人层加载——因此“环境中已有的值 > 项目 > 个人”的优先级不受影响。`DEFAULT_CONFIG` 与 `SOURCE_ROOT` 都是绝对路径，且 TUI 模式不传 snapshot mode，所以配置解析与 chdir 无关。 + +`meta` 始终启动新会话，且不接受任何默认界面选项；它唯一的选项是[实验性门槛](2026-07-31-experimental-subcommand-gate.md)的 `--experimental`。`--config` 会针对 harness workspace 启动其他配置树，那是默认界面的 `--config` 场景，而不是该命令的场景；`-p` 并非交互式，恢复则通过 `dsh --resume ` 重新进入已持久化会话自身的 workspace。任何泄漏的默认界面选项都会明确报错。 + +## Testing + +`apps/cli/tests/args.spec.ts` 钉住 `meta` 的路由、对每个泄漏的默认界面选项的拒绝，以及对旧名称 `experimental-meta` 的拒绝。该分派本身是 `bin.ts` 既有 `v8 ignore` 块内的组合代码。 + +该 mode 没有 keyless PTY 冒烟测试。冒烟框架会为每次运行提供临时 cwd，但 `dsh meta` 刻意 chdir 到真实检出目录，因此冒烟测试会在测试中途把 `.sessions/` 写入实际工作树。要正确覆盖它需要一个可注入的目标目录——为了一行 chdir 而引入的测试专用 seam，本 note 不予采纳。 + +取而代之的是交互式验证。从 `$HOME` 启动后，`pwd` 工具调用报告的是该检出目录，git 解析到其分支，会话日志落在该检出的 `.sessions/` 下（`~/.sessions` 未被触及，工作树也没有未被忽略的残留），并且从其他目录运行的普通 `dsh` 仍使用调用目录。 + +## Alternatives considered + +**通过 `boot` 与配置树显式传递 workspace。** 这可避免修改进程级状态，但已交付的配置在三处读取 cwd（`!!js process.cwd()`、`persistenceRoot`、HMR `root`），每一处都需要各自新增管线与配置键才能保持一致。启动前 chdir 只在本就表达该含义的接缝上表达一次“这就是 workspace”。 + +**在默认界面上加一个 `--experimental-meta` 标志。** 拒绝：默认界面是纯选项形式，以免子命令与位置参数冲突；而一个会静默改变 workspace 的标志读起来像是对当前目录的修饰，而非另一个目标。`meta` 与 `web` 并列符合既有形态。 + +**解析 `~/.dsh/source/current` 而非启动器自身路径。** 拒绝：当直接调用某个非安装检出的 `bin/dsh` 时，它会与 `harness:source` 提示词路径产生偏离——告知模型一个源码根目录，却在另一个目录中工作。 + +## Consequences + +在 dsh 自身源码上开启会话变成了在任意位置执行 `dsh meta --experimental`（在 `DSH_EXPERIMENTAL=1` 下可直接执行 `dsh meta`），且该 workspace 必然就是告知模型的那个检出目录。该命令始终启动新会话；之后，普通的 `dsh --resume ` 会恢复该会话并进入其已持久化的 workspace。 + +`runTui` 新增一个可选第三参数，因此 workspace 覆盖是在拥有 TUI 组合逻辑的那唯一一个函数上可见的，而不是隐藏在它的第二份副本中。 diff --git a/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.i18n.yaml b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.i18n.yaml new file mode 100644 index 0000000000..4c92c6521f --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.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/2026-07-29-tui-hidden-mode-assistant-fold.md +2026-07-29-tui-hidden-mode-assistant-fold.md: 53cd3d812212f8a72c56165c37b806cae58f37f6 +2026-07-29-tui-hidden-mode-assistant-fold.zh.md: cf3644478588bbba955fb6539dd99744ef6eb84c diff --git a/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.md b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.md new file mode 100644 index 0000000000..53cd3d8122 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.md @@ -0,0 +1,26 @@ +# Agent Note: TUI hidden mode folds a turn's assistant steps into one message + +Status: implemented +Archived: 2026-08-04 + +English | [中文](2026-07-29-tui-hidden-mode-assistant-fold.zh.md) + +## Problem + +Ctrl+O's hidden phase ([consolidated TUI presentation](../architecture/2026-07-28-consolidated-tui-presentation.md)) drops tool cards so the transcript reads as a conversation, but each model step still rendered its own `Assistant` header. A multi-step turn (text → tools → text) therefore showed several consecutive `Assistant` blocks with nothing between them — the removed tool cards were the only thing that had justified the repeated headers. Codex-style conversation-only reading wants one assistant message per turn. + +## Decision + +Hidden mode is also a fold rule, applied purely as TUI presentation: per turn, the first step whose rendered content is visible (text, or reasoning while reasoning display is on) owns the turn's single `Assistant` header; every other step renders as a headerless continuation, and a step with no visible body renders nothing at all — a tool-only step neither consumes the header nor leaves a blank segment. Collapsed and expanded phases keep per-step headers; leaving hidden restores them. + +Mechanics: `StreamingAssistantComponent` carries its `StepPosition` and a `setFoldedContinuation` presentation flag; `createTuiChat` keeps a per-turn list of step components and re-derives the fold on Ctrl+O, on each streamed text/reasoning chunk, on message settle, and on retraction of a failed stream (which may hand the header to the next step). Transcript rebuild clears the map and replays the log, so resume, compaction replacement, resize, and theme swaps converge on the same fold. Step timing footers keep their per-step ownership and are unaffected. + +## Alternatives considered + +- **Merge steps into one component** — collides with per-step streaming lifecycle, retry retraction, and timing footers; the flag on existing components changes only the header/spacer. +- **Fold in the session log or `deriveMessages`** — mutates durable/model-visible history for a UI reading mode; the log stays step-shaped. +- **Always fold (all visibility phases)** — collapsed/expanded interleave tool cards between steps, where per-step headers delimit which output belongs to which step. + +## Consequences + +Hidden mode now reads as one assistant message per turn; turns stay separated by their headers. The fold is recomputed state, never stored, so no session or persistence format changes. Coverage: TUI unit specs for the Ctrl+O cycle header counts, tool-only first step header handoff, per-turn separation, and live streaming + rebuild convergence; keyless snapshot `tool-cards-hidden-folded` pins the folded frame. diff --git a/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.zh.md b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.zh.md new file mode 100644 index 0000000000..cf36444785 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-29-tui-hidden-mode-assistant-fold.zh.md @@ -0,0 +1,26 @@ +# Agent Note: TUI 隐藏模式把一个轮次的 assistant 步骤折叠为一条消息 + +Status: implemented +Archived: 2026-08-04 + +[English](2026-07-29-tui-hidden-mode-assistant-fold.md) | 中文 + +## 问题 + +Ctrl+O 的隐藏阶段（[整合的 TUI 展示](../architecture/2026-07-28-consolidated-tui-presentation.md)）去掉工具卡片，让 transcript（文本记录）读作一段对话，但每个模型步骤仍渲染自己的 `Assistant` 标题。因此一个多步骤轮次（文本 → 工具 → 文本）会显示多个连续、之间空无一物的 `Assistant` 区块——被移除的工具卡片正是重复标题曾经的唯一理由。Codex 风格的纯对话阅读需要每轮次一条 assistant 消息。 + +## 决定 + +隐藏模式同时也是一条折叠规则，且纯粹作为 TUI 展示实现：在每个轮次内，第一个渲染内容可见（有文本，或在 reasoning 显示开启时有 reasoning）的步骤拥有该轮次唯一的 `Assistant` 标题；其余步骤渲染为无标题的续段，没有可见正文的步骤则完全不渲染——仅有工具调用的步骤既不占用标题，也不留下空白段。折叠与展开阶段保留每步各自的标题；离开隐藏阶段会恢复它们。 + +机制：`StreamingAssistantComponent` 携带自己的 `StepPosition` 和一个 `setFoldedContinuation` 展示标志；`createTuiChat` 维护每轮次的步骤组件列表，并在 Ctrl+O、每个流式 text/reasoning chunk、消息结算，以及失败流被撤回（可能把标题移交给下一个步骤）时重新推导折叠。transcript 重建会清空该映射并重放日志，因此恢复、压缩替换、调整尺寸和主题切换收敛到同一折叠结果。步骤计时页脚保持按步骤归属，不受影响。 + +## 考虑过的替代方案 + +- **把多个步骤合并为一个组件**——与按步骤的流式生命周期、重试撤回和计时页脚冲突；在现有组件上加标志只改变标题与前导间距。 +- **在会话日志或 `deriveMessages` 中折叠**——为一种 UI 阅读模式改变持久 / 模型可见的历史；日志保持按步骤的形状。 +- **所有可见性阶段都折叠**——折叠 / 展开阶段在步骤之间穿插工具卡片，此时每步的标题用来划分哪段输出属于哪个步骤。 + +## 后果 + +隐藏模式现在每轮次读作一条 assistant 消息；轮次之间仍由各自的标题分隔。折叠是重新计算的状态，从不存储，因此会话与持久化格式没有变化。覆盖：TUI 单元测试覆盖 Ctrl+O 循环的标题计数、仅工具的首步骤标题移交、按轮次分隔，以及实时流式 + 重建收敛；无密钥快照 `tool-cards-hidden-folded` 固定折叠后的帧。 diff --git a/.agents/notes/implemented/feature/2026-07-24-tui-banner-model-deduplication.i18n.yaml b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.i18n.yaml similarity index 56% rename from .agents/notes/implemented/feature/2026-07-24-tui-banner-model-deduplication.i18n.yaml rename to .agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.i18n.yaml index 8cb52df982..aad3f3c42f 100644 --- a/.agents/notes/implemented/feature/2026-07-24-tui-banner-model-deduplication.i18n.yaml +++ b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.i18n.yaml @@ -1,6 +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/feature/2026-07-24-tui-banner-model-deduplication.md -2026-07-24-tui-banner-model-deduplication.md: afd370a8762d8e6c17c61d50c95d68998a063df5 -2026-07-24-tui-banner-model-deduplication.zh.md: 86a3cdb0e714642253162f1fe062e19bdc40bbe4 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-compaction-progress-visibility.md +2026-07-30-compaction-progress-visibility.md: e0d44c8616661161f6a99b54e3fe75a75dd5b9ad +2026-07-30-compaction-progress-visibility.zh.md: 5b181da16280393db9da5bc00127e71de1d9341a diff --git a/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.md b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.md new file mode 100644 index 0000000000..e0d44c8616 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.md @@ -0,0 +1,50 @@ +# Agent Note: Live standalone compaction progress in the terminal + +Status: implemented +Archived: 2026-08-04 + +English | [中文](2026-07-30-compaction-progress-visibility.zh.md) + +## Problem + +A standalone manual compaction runs between turns while the agent remains idle. The TUI's turn-phase indicator therefore kept its plain `>` caret throughout the slow summary operation, and a failed attempt produced no transcript row because no replacement checkpoint landed. The liveness presentation needs to reuse the existing status indicator without introducing a second animated status location. + +The durable log can retain an unmatched `compact/start` after a process dies. That orphan is useful recovery evidence, but it is not proof that work is running in the current process; replaying it as progress would leave resumed sessions with a permanent phantom indicator. + +## Decision + +The TUI treats the live standalone `compact/start { turn: null }` to matching `compact/end` bracket as the source of in-flight compaction presentation. A module-local `compacting` cell records the render-clock start and owns one animation timer. A fixed row above the prompt renders `Context being compacted ` from that clock, the existing one-cell running status indicator renders `⊙` through the same fade and throb path as turn-phase glyphs, and the terminal progress bit remains active until the bracket closes. + +`runningPhaseGlyph` owns the choice among turn-phase glyphs, `⊙`, and the idle caret. Turn-phase glyphs take precedence because numbered compaction brackets are enclosed by a running turn whose phase already lights the indicator. The fixed row is outside the transcript and owns neither a spinner nor another timer; it collapses when empty. The compaction cell does not change the idle editor border, hint, or steering badge, so prompts remain visibly accepted while standalone compaction reserves turn admission. + +The cell is live-only. Mount and transcript replay never scan history for an unmatched start; only a `session/event` notification observed by the mounted TUI can open it. Turn-status transitions preserve the cell, while terminal teardown clears its timer and progress bit. + +On `compact/end`, the TUI clears the cell before starting the ordinary glyph fade-out. An end carrying `error` adds `Compaction failed: ` as a warning. Successful completion remains represented by the landed replacement's transcript marker, and duration remains derivable from the matching durable start and end timestamps without another settled row. + +This decision partially supersedes only the progress-related deferred clauses in the [terminal transcript decision](../bug-fix/2026-07-29-human-transcript-append-origin.md) and [browser transcript decision](../bug-fix/2026-07-30-web-transcript-log-ordered-projection.md): progress does not require marker scale or a replacement-rendering refactor. Both notes remain active and continue to own append-origin transcript projection and landed checkpoint markers. The [queued manual compaction decision](2026-07-30-queued-manual-compaction.md) remains the owner of bracket ordering, locking, and stale-orphan classification. + +## Alternatives considered + +**Add `progressLabel` to `CommandDefinition` and a second TUI status controller, as explored in PR #669.** Rejected because command metadata is not the compaction lifecycle authority, automatic compaction does not originate from a human command, and two status controllers can disagree about the same indicator. + +**Add `compacting` to `TurnPhase`, as explored in PR #669.** Rejected because standalone compaction deliberately has no turn, while numbered compaction already has a visible running-turn phase. + +**Add a fifth `TimingBucket`.** Rejected because timing buckets partition an open model step and feed its transcript footer. Standalone compaction has no step transition, and a new bucket would add a meaningless compaction column to every step total. + +**Share one timer among running, fading, and compaction states.** Rejected because fade-out owns a self-terminating timer, while live compaction has an independent open/close lifetime. Sharing would restructure the reviewed animation state machine without removing an actual concurrent timer. + +**Scan the log for an unmatched `compact/start`.** Rejected because a stale orphan from an earlier process lifecycle is expected durable history. Only the live notification proves current work. + +**Use a generic command-running indicator.** Rejected for this behavior because the compaction bracket is the more precise source and also covers non-command paths. A future generic command indicator belongs to the `command/run` / `command/done` lifecycle. + +**Add an animated compaction row to the transcript.** Rejected because it creates a second status animation point for the same lifecycle. The existing one-cell indicator owns liveness, while the landed marker and failure warning own settled transcript presentation. + +**Print a success notice with duration.** Rejected because the landed replacement already supplies the completion marker. The bracket timestamps preserve duration for a future presentation that justifies another transcript row. + +## Consequences + +Manual compaction has a named elapsed-time display above the prompt while the agent is idle, failure has a direct warning, and a resumed orphan never looks active. The prompt indicator remains one terminal cell wide, while the row and indicator reuse the existing status animation, semantic palette, and terminal-progress lifecycle. + +The live cell and timer are additional process-local state, cleared on both bracket close and TUI teardown. This is intentionally not reconstructible presentation state: durable history supplies the successful marker and timing facts, while current-process observation alone supplies liveness. + +The package-level TUI tests pin standalone start, elapsed-time refresh, single-indicator presentation, numbered-start exclusion, fade-out, failure warning, idle-status preservation, running-turn precedence, orphaned resume, and timer disposal. The removed product TUI scenario formerly observed `Context being compacted 1.0s` and `dsh ⊙` across a held real summary boundary; a future terminal deployment owns that assembled journey. diff --git a/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.zh.md b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.zh.md new file mode 100644 index 0000000000..5b181da162 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-compaction-progress-visibility.zh.md @@ -0,0 +1,50 @@ +# Agent Note: 终端中的实时独立压缩进度 + +Status: implemented +Archived: 2026-08-04 + +[English](2026-07-30-compaction-progress-visibility.md) | 中文 + +## 问题 + +独立手动压缩（compaction）在轮次之间运行，此时 agent（智能体）保持空闲。因此，在缓慢的摘要操作期间，TUI 的轮次阶段指示器始终显示普通的 `>` 光标；尝试失败时，由于没有替换检查点落地，也不会产生 transcript（文本记录）行。运行状态显示需要复用现有的状态指示器，不能再设置第二处带动画的状态显示。 + +进程终止后，持久日志中可能保留未匹配的 `compact/start`。该未匹配标记是有用的恢复证据，但无法证明当前进程中有工作正在运行；若将其回放为进度，恢复后的会话便会永久显示虚假的进度指示。 + +## 决策 + +TUI 将实时独立的 `compact/start { turn: null }` 与匹配的 `compact/end` 组成的标记对，作为显示进行中压缩状态的真源。模块局部的 `compacting` 状态记录渲染时钟的起始时间，并独占一个动画定时器。提示词上方的固定行根据该时钟渲染 `Context being compacted `，现有的单格运行状态指示器通过与轮次阶段字形相同的明暗渐变和呼吸律动路径渲染 `⊙`，终端进度标志位会保持活跃，直至标记对闭合。 + +`runningPhaseGlyph` 负责在轮次阶段字形、`⊙` 和空闲光标之间作出选择。轮次阶段字形的优先级更高，因为带编号的压缩标记对处于运行中的轮次内，该轮次的阶段已经激活指示器。该固定行位于 transcript 之外，不带 spinner，也不另设定时器；内容为空时会折叠。压缩状态不会改变空闲编辑器边框、提示或 steering（中途引导）徽标，因此，在独立压缩预留轮次准入期间，界面仍会明确显示提示词已获接纳。 + +该状态只反映实时事件。挂载和 transcript 回放绝不会扫描历史以查找未匹配的 start；只有已挂载的 TUI 观察到 `session/event` 通知，才能开启它。轮次状态转换会保留该状态，而终端清理会清除其定时器和进度标志位。 + +收到 `compact/end` 时，TUI 会先清除状态，再启动普通字形的淡出。携带 `error` 的结束事件会以警告形式添加 `Compaction failed: `。成功完成仍由已落地替换项的 transcript 标记呈现；无需再添加已结算的行，也可从匹配且已持久记录的开始与结束时间戳推导持续时间。 + +本决策仅部分取代[终端 transcript 决策](../bug-fix/2026-07-29-human-transcript-append-origin.md)和[浏览器 transcript 决策](../bug-fix/2026-07-30-web-transcript-log-ordered-projection.md)中与进度相关的延期条款：进度显示不要求标记携带规模信息，也不要求重构替换项渲染。两份记录均保持活动状态，并继续负责基于追加来源的 transcript 投影和已落地检查点标记。[排队式手动压缩决策](2026-07-30-queued-manual-compaction.md)继续负责标记对顺序、锁定机制和陈旧未匹配标记分类。 + +## 曾考虑的替代方案 + +**按照 PR（Pull Request）#669 中探索的方案，为 `CommandDefinition` 添加 `progressLabel` 和第二个 TUI 状态控制器。** 不予采用：命令元数据并非压缩生命周期的权威依据，自动压缩并非由人工命令发起，两个状态控制器也可能对同一个指示器给出不一致状态。 + +**按照 PR #669 中探索的方案，将 `compacting` 添加到 `TurnPhase`。** 不予采用：独立压缩按设计没有轮次，而带编号的压缩已经具有可见的运行轮次阶段。 + +**添加第五个 `TimingBucket`。** 不予采用：计时分桶用于划分一个开放模型步骤内的时间，并为其 transcript 页脚提供数据。独立压缩没有步骤转换，新分桶会在每个步骤总计中加入一个没有意义的压缩列。 + +**让运行、淡出和压缩状态共享一个定时器。** 不予采用：淡出过程独占一个会自行终止的定时器，而实时压缩有独立的开启与闭合生命周期。共享定时器会重构已经评审的动画状态机，却不能消除实际存在的并发定时器。 + +**扫描日志，查找未匹配的 `compact/start`。** 不予采用：来自先前进程生命周期的陈旧未匹配标记是预期的持久历史。只有实时通知才能证明当前进程正在执行工作。 + +**使用通用的命令运行指示器。** 本行为不采用该方案，因为压缩标记对是更精确的真源，并且还覆盖非命令路径。未来若实现通用命令指示器，应归属于 `command/run` 和 `command/done` 生命周期。 + +**在 transcript 中添加动画压缩行。** 不予采用：这会为同一个生命周期设置第二处状态动画显示。现有的单格指示器负责显示运行状态，而已落地标记和失败警告负责已结算的 transcript 呈现。 + +**打印包含持续时间的成功通知。** 不予采用：已落地的替换项已经提供完成标记。标记对的时间戳保留了持续时间，可供未来能够证明新增 transcript 行合理的展示方式使用。 + +## 后果 + +手动压缩在 agent 空闲时会在提示词上方显示带名称的已用时间，失败会直接产生警告，恢复会话时的陈旧未匹配标记绝不会显示为活动状态。提示符指示器保持一个终端字符单元宽，状态行和指示器则复用现有的状态动画、语义调色板和终端进度生命周期。 + +实时状态及其定时器是额外的进程局部状态，在标记对闭合和 TUI 清理这两种情况下都会清除。按设计，这种显示状态不可重建：持久历史提供成功标记与计时事实，只有当前进程的观察才能提供运行中状态。 + +包（package）级 TUI 测试固定了以下行为：独立开始事件、已用时间刷新、单指示器呈现、排除带编号的开始事件、淡出、失败警告、保留空闲状态、运行轮次优先级、存在未匹配标记时的恢复，以及定时器释放。已移除的产品 TUI 场景此前会在真实摘要边界保持开放期间观察到 `Context being compacted 1.0s` 和 `dsh ⊙`；未来的终端部署负责该组装流程。 diff --git a/.agents/notes/archived/feature/2026-07-30-tui-details-command.i18n.yaml b/.agents/notes/archived/feature/2026-07-30-tui-details-command.i18n.yaml new file mode 100644 index 0000000000..f3b185bbde --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-tui-details-command.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/2026-07-30-tui-details-command.md +2026-07-30-tui-details-command.md: b17cd493fc0c47d7484714f72f418266cd006353 +2026-07-30-tui-details-command.zh.md: ef2a682db1248dfc97fd6ccaa4260b4b9d1a0861 diff --git a/.agents/notes/archived/feature/2026-07-30-tui-details-command.md b/.agents/notes/archived/feature/2026-07-30-tui-details-command.md new file mode 100644 index 0000000000..b17cd493fc --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-tui-details-command.md @@ -0,0 +1,35 @@ +# Agent Note: /details command for transcript detail state + +Status: implemented +Archived: 2026-08-04 + +English | [中文](2026-07-30-tui-details-command.zh.md) + +## Problem + +The TUI's transcript detail state — tool-card visibility (`collapsed`/`expanded`/`hidden`, per the [consolidated TUI presentation](../architecture/2026-07-28-consolidated-tui-presentation.md)) and reasoning-block display — was reachable only through the Ctrl+O cycle and the Ctrl+R toggle. A user who wants a specific mode must cycle through the others, cannot set both dimensions in one action, and has no way to query the current state; a terminal that swallows those control keys has no fallback at all. + +## Decision + +`dsh-tui` registers `/details` beside its other agent-scoped commands. Bare `/details` opens `DetailsDialog`, a centered keyboard toggle with one entry per dimension — `Tool cards` and `Reasoning` — showing the live values: Tab cycles the highlighted entry and applies the change immediately, so the transcript behind the dialog is the preview, and Enter, Esc, or Ctrl+C closes; its width is the `detailsDialogWidth` config key and a second `/details` replaces an open selector, mirroring the `/model` overlay. Arguments name target states directly: `collapsed|expanded|hidden` jumps tool cards to that phase, `reasoning on|off` sets reasoning display, bare `reasoning` toggles it, and directives combine in one invocation. An unknown token returns a command error carrying the usage line. Every entry mutates the same closure state as the shortcuts, refactored so the cycle and toggle are thin wrappers over `setToolsVisibility`/`setReasoning`; the shortcuts and their notices are unchanged. + +A combined invocation applies reasoning before visibility because `setReasoning` rebuilds the transcript from session events, which drops non-durable notice components; applying it last would erase the just-appended visibility notice. + +The reasoning rebuild exposed a replay defect that this change fixes in `renderEvent`: the live path cleared a settled `StreamingAssistantComponent` before a later `assistant/message` of the same step (so the second message got a fresh component), but `rebuildTranscript` replay reused the settled component and `settle()` overwrote its content, silently dropping the earlier message's text. The settled check now lives in `renderEvent`'s `assistant/message` case — one home for both paths — and the previously wrong `untrusted-controls` snapshot (an empty `Assistant` header where reasoning and text had been dropped) was re-recorded with the content present. + +## Alternatives considered + +**Cycle on bare `/details`, mirroring Ctrl+O.** Rejected: the command's value over the shortcut is naming an absolute state; a cycling command is the shortcut with more keystrokes, and bare invocation is more useful as the selector, which shows the current state while offering every target. + +**Bare `/details` as a text-only state report.** Shipped first, replaced by the selector: the report answered "where am I" but still required a second, argument-spelling invocation to change anything, while the selector shows the same state and applies a change in one interaction. The textual grammar remains for scripts, muscle memory, and combined two-dimension changes. + +**Separate `/tools` and `/reasoning` commands.** Rejected: both dimensions are one presentation concern ("how much detail does the transcript show"), and a single command keeps the registry and `/help` list small while allowing one combined invocation. + +**Config-key defaults per mode.** Out of scope: `showReasoning` already exists as config; the command is runtime state on top of it, matching the shortcuts. + +## Consequences + +- A user can jump to any detail mode, set both dimensions at once, and see the current state in the selector — including on terminals that intercept Ctrl+O/Ctrl+R. +- The parser accepts order-free tokens, so `/details reasoning expanded` toggles reasoning and expands cards; last directive wins per dimension. This leniency is deliberate and documented in the README. +- The selector has no pending state or cancel: every Tab is a real, already-notified change, and closing never reverts. A user who over-cycles simply Tabs on to the wanted value. +- Transcript rebuilds no longer lose assistant messages when a step carries more than one `assistant/message` event; the `details-command` snapshot pins the argument surface and the fixed replay, and `details-selector` pins the open toggle right after a Tab applied `hidden` -> `collapsed`, including the restored tool card behind it. diff --git a/.agents/notes/archived/feature/2026-07-30-tui-details-command.zh.md b/.agents/notes/archived/feature/2026-07-30-tui-details-command.zh.md new file mode 100644 index 0000000000..ef2a682db1 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-tui-details-command.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 用于 transcript 细节状态的 /details 命令 + +Status: implemented +Archived: 2026-08-04 + +[English](2026-07-30-tui-details-command.md) | 中文 + +## Problem + +TUI 的 transcript（文本记录）细节状态——工具卡片可见性（`collapsed`/`expanded`/`hidden`，见[整合的 TUI 展示](../architecture/2026-07-28-consolidated-tui-presentation.md)）与 reasoning 块显示——过去只能通过 Ctrl+O 循环和 Ctrl+R 切换来触达。想要某个特定模式的用户必须循环经过其他模式，无法一次操作同时设置两个维度，也无法查询当前状态；吞掉这些控制键的终端更是完全没有替代途径。 + +## Decision + +`dsh-tui` 在其他 agent 作用域命令旁注册 `/details`。裸 `/details` 打开 `DetailsDialog`：一个居中的键盘开关，每个维度一个条目——`Tool cards` 与 `Reasoning`——显示实时值：Tab 循环高亮条目并立即应用变更，对话框背后的 transcript 即是预览，Enter、Esc 或 Ctrl+C 关闭；其宽度由配置键 `detailsDialogWidth` 决定，选择器打开时再次执行 `/details` 会替换它，与 `/model` 浮层一致。参数直接命名目标状态：`collapsed|expanded|hidden` 让工具卡片跳到该阶段，`reasoning on|off` 设置 reasoning 显示，裸 `reasoning` 切换它，且指令可在一次调用中组合。未知 token 返回携带用法行的命令错误。每个入口改动的都是与快捷键相同的闭包状态，重构后循环与切换成为 `setToolsVisibility`/`setReasoning` 之上的薄封装；快捷键及其通知保持不变。 + +组合调用先应用 reasoning 再应用可见性，因为 `setReasoning` 会从会话事件重建 transcript，而重建会丢弃非持久的通知组件；若最后才应用它，会抹掉刚追加的可见性通知。 + +reasoning 重建暴露了一个重放缺陷，本变更在 `renderEvent` 中修复：实时路径会在同一步骤的后续 `assistant/message` 之前清除已结算的 `StreamingAssistantComponent`（因此第二条消息获得新组件），但 `rebuildTranscript` 重放复用了已结算组件，`settle()` 覆盖其内容，静默丢掉了前一条消息的文本。已结算检查现在位于 `renderEvent` 的 `assistant/message` 分支——两条路径共用一个归属地——此前错误的 `untrusted-controls` 快照（reasoning 与文本被丢弃后只剩空 `Assistant` 标题）已重录为包含内容的版本。 + +## Alternatives considered + +**裸 `/details` 像 Ctrl+O 一样循环。** 否决：命令相对快捷键的价值在于命名绝对状态；循环命令只是按键更多的快捷键，裸调用作为选择器更有用——它在展示当前状态的同时提供所有目标。 + +**裸 `/details` 仅输出文本状态报告。** 首版如此实现，后被选择器取代：报告回答了“我在哪”，但改变任何东西仍需第二次、拼写参数的调用；选择器展示同样的状态并在一次交互中应用变更。文本语法保留给脚本、肌肉记忆和两维组合变更。 + +**拆分 `/tools` 与 `/reasoning` 两个命令。** 否决：两个维度同属一个展示关注点（“transcript 显示多少细节”），单一命令让注册表与 `/help` 列表更小，同时允许一次组合调用。 + +**按模式提供配置键默认值。** 超出范围：`showReasoning` 已作为配置存在；命令是其上的运行时状态，与快捷键一致。 + +## Consequences + +- 用户可以跳到任意细节模式、一次设置两个维度，并在选择器中看到当前状态——包括在拦截 Ctrl+O/Ctrl+R 的终端上。 +- 解析器接受无序 token，因此 `/details reasoning expanded` 会切换 reasoning 并展开卡片；每个维度以最后一个指令为准。这一宽松是刻意的，并记录在 README 中。 +- 选择器没有待定状态与取消：每次 Tab 都是已生效、已通知的真实变更，关闭从不回退。循环过头的用户继续 Tab 到想要的值即可。 +- 当一个步骤携带多条 `assistant/message` 事件时，transcript 重建不再丢失 assistant 消息；`details-command` 快照固定参数表面与修复后的重放，`details-selector` 固定 Tab 将 `hidden` 应用为 `collapsed` 后仍打开的开关，包括其背后恢复显示的工具卡片。 diff --git a/.agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.i18n.yaml b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml similarity index 55% rename from .agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.i18n.yaml rename to .agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml index 629476cf8e..d73372fda8 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-consolidated-tui-presentation.i18n.yaml +++ b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.i18n.yaml @@ -1,6 +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/2026-07-28-consolidated-tui-presentation.md -2026-07-28-consolidated-tui-presentation.md: f87d543a698d6e77abf9120c6579100df4b60b64 -2026-07-28-consolidated-tui-presentation.zh.md: 005e408f0e75207027315546942f9eab57d595d1 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.md +2026-07-30-versioned-tui-first-run-welcome.md: c032785a34455e868c2643bc58aafcb0e4916592 +2026-07-30-versioned-tui-first-run-welcome.zh.md: 0f3e684baeaed178ce3d7590590d0086f345e461 diff --git a/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.md b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.md new file mode 100644 index 0000000000..c032785a34 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.md @@ -0,0 +1,44 @@ +# Agent Note: Versioned TUI first-run welcome + +Status: implemented +Archived: 2026-08-03 + +English | [中文](2026-07-30-versioned-tui-first-run-welcome.zh.md) + +## Problem + +The shipped `dsh` terminal starts directly in the editor and gives first-time internal testers no durable orientation about the product's maturity or feedback channel. The existing one-line `welcome` banner subtitle cannot carry the supplied notice without crowding the normal session header, and putting onboarding in the session log would create a user turn or model-visible context that is unrelated to the user's work. + +The notice also needs a recognizable DeepSeek composition without copying another product's startup art or maintaining a hand-drawn approximation that drifts from the official mark. + +## Decision + +The official `dsh` launcher owns one versioned acknowledgement marker under the resolved `DSH_HOME`. It checks the immutable marker before boot, then mounts an effect-owned consumer of `ctx.tui.openOverlay()` only after the real TUI service is available. Enter is the sole acknowledgement action: the plugin creates and synchronizes the fixed per-version marker before closing. Escape and unrecognized input leave the overlay open; Ctrl+C and Ctrl+D use the normal exit path without acknowledging. Disposal waits for an acknowledgement already started by Enter, while disposal or process exit before Enter writes nothing. The version is part of the marker filename, so incrementing the centrally owned notice version presents materially revised copy once without migrating or rewriting an aggregate settings document. + +The marker is launcher state rather than session persistence because eligibility spans sessions and workspaces but is scoped to one Harness home. Each Enter syncs a random same-directory file before atomically replacing the fixed marker; concurrent launches publish the same immutable fact, so same-value last-writer-wins replacement has no lost-update shape and needs no lock or dependency on the settings stack. The notice never appends a session event, injects model context, or creates a user turn; resume therefore presents it only when the same Harness home has not acknowledged that version and never replays it from the session log. + +The supplied official `24x24` DeepSeek SVG is committed as the visual source. Static full, compact, and minimal terminal rasters sample that exact path at decreasing square resolutions; they do not redraw the contour. Unicode `▀`/`▄`/`█` cells preserve two vertical source pixels per terminal cell, while an explicitly ASCII-only locale uses the bit-equivalent `'`/`_`/`#` fallback. ANSI styling stays outside both the SVG and editable copy: `ctx.tui` supplies a semantic `brand` role, using the official `#4D6BFE` ink when truecolor is available, standard ANSI blue otherwise, and plain text when color is disabled. The normal startup banner retains its existing gradient. + +The overlay is centered and consumes the available terminal width, while its height follows actual content and treats 90% of the viewport only as an upper bound. Wide terminals place the full icon beside the title and prose; medium and narrow terminals stack the compact or minimal icon above them; low height removes the icon before reducing prose space. The prose scrolls while the title and only action remain fixed. Every locale uses the same centrally owned Chinese copy, and the quotation is promoted to its own visual paragraph without changing that string. Closing through Enter returns modal ownership to the existing FIFO manager, which restores the editor and leaves the normal startup banner, transcript, and focus behavior intact. + +## Verification + +Focused unit coverage pins the supplied SVG and Chinese copy hashes, version bumps, exclusive concurrent acknowledgement, malformed markers, persistence retry, Escape behavior, ASCII fallback, width-tier selection, bounded rendering, and low-height scrolling. Real Loader/PTY cases cover 60, 80, 120, and 160 columns plus a low-height viewport, emit semantic terminal snapshots, prove first launch then second-launch suppression under one `DSH_HOME`, and prove a resumed session appends no notice-derived user message or turn; ordinary terminal-exit lifecycle events remain unchanged. + +## Alternatives considered + +**Reuse the TUI `welcome` subtitle.** It is one transient header line whose normal job is to identify an untitled session. The required prose and action would either be clipped or permanently crowd ordinary launches. + +**Copy Claude Code's startup art or composition.** Its strong hierarchy is useful product evidence, but its graphic, layout, and brand treatment belong to another product. The official DeepSeek SVG provides a direct brand source, and the terminal composition is derived independently around this notice's copy and responsive constraints. + +**Hand-draw an original whale.** A freehand silhouette can be recognizable yet still disagree with the official mark's body, internal negative space, fin, and tail. Exact-path raster sampling keeps the terminal limitation explicit and makes every tier traceable to one source asset. + +**Store a boolean in session events or a shared settings document.** Session state has the wrong lifetime and would pollute replay or model-visible history. An aggregate document would require cross-process read-modify-write locking for one immutable fact; an atomically replaced version marker has no lost-update shape. + +**Allow Escape or a later-reminder action.** Either would make dismissal indistinguishable from acknowledgement or introduce reminder policy that the notice does not need. Normal process exit remains the abort path and leaves the version unacknowledged. + +## Consequences + +Each Harness home receives the notice once per copy version, only after a successful Enter acknowledgement. Maintainers can edit the all-locale Chinese wording and version in one small owner file, and can update the official SVG and derived static rasters in their separate visual owner without chasing snapshots for full prose copies. + +The terminal cannot display SVG vectors directly, so its faithful representation is resolution-bounded. Smaller tiers preserve the sampled silhouette but necessarily lose fine detail; low-height terminals prefer readable prose and an always-reachable action over brand art. The marker format is intentionally one-file-per-version during the pre-release period; old markers are harmless and no compatibility reader is required. diff --git a/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.zh.md b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.zh.md new file mode 100644 index 0000000000..0f3e684bae --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-30-versioned-tui-first-run-welcome.zh.md @@ -0,0 +1,44 @@ +# Agent Note: 版本化 TUI 首次运行欢迎页 + +Status: implemented +Archived: 2026-08-03 + +[English](2026-07-30-versioned-tui-first-run-welcome.md) | 中文 + +## 问题 + +已交付的 `dsh` 终端会直接进入编辑器，没有为首次使用的内部测试者提供持久的产品成熟度说明或反馈渠道指引。现有单行 `welcome` banner 副标题无法容纳指定通知，否则会挤占正常的会话 header；如果把 onboarding 写入会话日志，还会创建一个与用户工作无关的用户轮次或模型可见上下文。 + +该通知还需要形成具有辨识度的 DeepSeek 视觉构图，同时不能复制其他产品的启动图形，也不能维护一份会偏离官方标志的手绘近似图。 + +## 决策 + +官方 `dsh` 启动器在解析后的 `DSH_HOME` 下持有一个版本化确认标记。它会在启动前检查该不可变标记，并仅在真实 TUI 服务可用后，挂载一个由 effect 持有的 `ctx.tui.openOverlay()` 消费方。Enter 是唯一确认操作：插件先创建并同步固定的逐版本标记，再关闭浮层。Escape 和无法识别的输入会让浮层保持打开；Ctrl+C 与 Ctrl+D 通过普通退出路径离开且不确认。资源释放会等待已经由 Enter 启动的确认任务；在按 Enter 前进行资源释放或退出进程不会写入任何内容。版本号属于标记文件名的一部分，因此只需递增集中持有的通知版本，即可让有实质修改的文案重新展示一次，无需迁移或改写聚合设置文档。 + +该标记属于启动器状态，而非会话持久化，因为展示资格跨越会话与 workspace，但作用域仅限一个 Harness 主目录。每次 Enter 都会先同步一个同目录随机文件，再以原子方式替换固定标记；并发启动发布的是同一个不可变事实，因此同值的最后写入者胜出不会丢失更新，也无需加锁或依赖设置栈。该通知绝不追加会话事件、注入模型上下文或创建用户轮次；因此，恢复会话只会在同一个 Harness 主目录尚未确认该版本时展示通知，也绝不会从会话日志中回放通知。 + +指定的官方 `24x24` DeepSeek SVG 作为视觉真源提交。静态的完整、紧凑和最小终端栅格图以逐级降低的方形分辨率对该精确路径取样，不会重新绘制轮廓。Unicode `▀`/`▄`/`█` 单元格让每个终端单元格保留两个垂直方向的源像素；明确仅支持 ASCII 的 locale 则使用位级等价的 `'`/`_`/`#` 回退。ANSI 样式与 SVG 和可编辑文案完全分离：`ctx.tui` 提供语义化 `brand` 角色，在真彩色可用时使用官方 `#4D6BFE` 色值，否则使用标准 ANSI 蓝色；禁用颜色时则使用纯文本。普通启动 banner 保留现有渐变。 + +浮层居中显示，并使用可用的终端宽度；高度则跟随实际内容，仅将 viewport 的 90% 作为上限。宽终端将完整图标置于标题与正文旁边；中等和窄终端把紧凑或最小图标堆叠在正文上方；高度不足时，先移除图标，再减少正文空间。正文可以滚动，而标题和唯一操作保持固定。所有 locale 共用同一份集中持有的中文文案，引用内容会提升为独立的视觉段落，但不会改变该字符串。通过 Enter 关闭浮层后，模态所有权会交还给现有 FIFO 管理器；该管理器恢复编辑器，同时保持正常的启动 banner、transcript（文本记录）和焦点行为不变。 + +## 验证 + +聚焦单元测试固定指定 SVG 与中文文案的 hash、版本递增、并发独占确认、格式错误的标记、持久化重试、Escape 行为、ASCII 回退、宽度分级选择、有界渲染和低高度滚动。真实 Loader/PTY 用例覆盖 60、80、120、160 列以及一个低高度 viewport，产出语义终端快照，证明同一个 `DSH_HOME` 下首次启动后再次启动会抑制展示，并证明恢复会话不会追加任何由通知衍生的用户消息或轮次；普通终端退出的生命周期事件保持不变。 + +## 曾考虑的替代方案 + +**复用 TUI 的 `welcome` 副标题。** 它是一行瞬态 header，正常职责是标识无标题会话。所需正文和操作要么会被裁剪，要么会永久挤占普通启动界面。 + +**复制 Claude Code 的启动图形或构图。** 其清晰的视觉层级是有用的产品证据，但图形、布局和品牌处理属于另一个产品。官方 DeepSeek SVG 提供直接的品牌来源，而终端构图围绕本通知的文案与响应式约束独立推导。 + +**手绘原创鲸鱼。** 自由绘制的轮廓可以具有辨识度，却仍可能与官方标志的身体、内部负空间、鳍和尾部不一致。对精确路径进行栅格取样，可以明确呈现终端限制，并让每个分级都能追溯到同一个源资产。 + +**在会话事件或共享设置文档中存储布尔值。** 会话状态的生命周期不正确，还会污染回放或模型可见历史。聚合文档为记录一个不可变事实，需要承担跨进程读取、修改、写入锁；以原子方式替换的版本标记不存在更新丢失问题。 + +**允许 Escape 或稍后提醒操作。** 两者都会让取消与确认无法区分，或引入本通知并不需要的提醒策略。正常退出进程仍是中止路径，并会让该版本保持未确认状态。 + +## 后果 + +每个 Harness 主目录在每个文案版本中都会收到一次通知，且仅在用户成功按 Enter 确认后停止展示。维护者可以在一个小型 owner 文件中编辑所有 locale 共用的中文文案和版本，也可以在独立的视觉 owner 中更新官方 SVG 与衍生静态栅格图，无需到各个快照中查找完整正文副本。 + +终端无法直接显示 SVG 矢量图，因此其忠实呈现受分辨率限制。较小分级会保留取样后的轮廓，但必然损失精细细节；低高度终端优先保障正文可读和操作始终可达，而非展示品牌图形。在预发布阶段，标记格式有意采用每个版本一个文件；旧标记无害，也无需兼容性读取器。 diff --git a/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.i18n.yaml b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.i18n.yaml new file mode 100644 index 0000000000..5db76248b3 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.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/feature/2026-07-31-experimental-subcommand-gate.md +2026-07-31-experimental-subcommand-gate.md: a12c93935805a9ab19d4a15905f90783851eabba +2026-07-31-experimental-subcommand-gate.zh.md: ee05ec2c1c488e9d815bc150135202963f030ae7 diff --git a/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.md b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.md new file mode 100644 index 0000000000..a12c939358 --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.md @@ -0,0 +1,36 @@ +# Agent Note: experimental subcommands gate behind `--experimental` or `DSH_EXPERIMENTAL=1` + +Status: implemented +Archived: 2026-08-03 + +English | [中文](2026-07-31-experimental-subcommand-gate.zh.md) + +## Problem + +The `meta` and `upgrade` entry points carried their experimental status in their names: `dsh experimental-meta` and `dsh experimental-upgrade`. The prefix made every invocation verbose, and renaming a command at stabilization would break every reference to it — muscle memory, scripts, and docs alike. The status belongs in an opt-in gate, not in the name. + +## Decision + +`dsh experimental-meta` is `dsh meta` and `dsh experimental-upgrade` is `dsh upgrade`. Each runs only when the invocation passes its `--experimental` flag or the environment carries `DSH_EXPERIMENTAL=1`; otherwise the command fails loud on stderr with exit 1, naming both opt-ins. Per the pre-release stance, the old names are gone with no aliases, and `args.spec.ts` pins their rejection. + +The gate has two halves with one owner each. The per-invocation half is a Commander `--experimental` option on each experimental subcommand, checked inside its action after the leaked-parent-option rejection. The environment half is a boolean `parseDshArgs` parameter: `bin.ts` reads `process.env.DSH_EXPERIMENTAL === '1'` at the process boundary (after `loadEnv`, so a project `.env` can set it) and passes the result down, so the parser's environment dependency is explicit in its signature and the tests need no env mutation. `1` is the only enabling value — the variable is an explicit opt-in, not a truthiness check. + +Stabilizing a command later means deleting its `--experimental` option and `requireExperimental` call; the name does not move. + +## Testing + +`args.spec.ts` pins both admit paths, bare-name rejection, old-name rejection, and leaked-option rejection under the env opt-in. `built-bin.e2e.ts` proves the assembled entry end to end: the gate diagnostic on stderr with exit 1, and that `--experimental`, `DSH_EXPERIMENTAL=1`, but not `DSH_EXPERIMENTAL=0`, reach the TUI's piped-stdio refusal — the next gate past this one. Both gated commands were also verified interactively in tmux: `dsh meta --experimental` and `DSH_EXPERIMENTAL=1 dsh meta` boot the TUI over the checkout, and `DSH_EXPERIMENTAL=1 dsh upgrade` seeds the `dsh-upgrade` skill. + +## Alternatives considered + +**Keep the `experimental-` name prefix.** Rejected by the user's direction: the prefix taxes every invocation, and stabilization would be a breaking rename instead of deleting a gate. + +**A parent-level `--experimental` flag (`dsh --experimental meta`).** Rejected: the default surface is deliberately option-only with `enablePositionalOptions`, so parent options that leak across the subcommand boundary are treated as mistyped invocations. A parent flag consumed only by two subcommands would be exactly the leaked-option shape the adapter rejects everywhere else. + +**Read `process.env` inside `parseDshArgs`.** Rejected: the repo validates at the process boundary and keeps typed seams pure; tests would have to mutate and restore `process.env` around each case. + +**Accept any non-empty `DSH_EXPERIMENTAL`.** Rejected: the telemetry switch prefers off-by-mistake for a privacy control, but an experimental gate is an acknowledgement — `DSH_EXPERIMENTAL=0` must not enable the commands it names. + +## Consequences + +Daily invocations shorten to `dsh meta --experimental` and `dsh upgrade --experimental`, and a developer who sets `DSH_EXPERIMENTAL=1` in their environment gets the bare `dsh meta`/`dsh upgrade`. `dsh --help` marks both commands `(experimental)`. The gate costs one extra flag or env var until a command stabilizes, at which point the gate is deleted and the name is already final. diff --git a/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.zh.md b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.zh.md new file mode 100644 index 0000000000..ee05ec2c1c --- /dev/null +++ b/.agents/notes/archived/feature/2026-07-31-experimental-subcommand-gate.zh.md @@ -0,0 +1,36 @@ +# Agent Note: 实验性子命令由 `--experimental` 或 `DSH_EXPERIMENTAL=1` 把守 + +Status: implemented +Archived: 2026-08-03 + +[English](2026-07-31-experimental-subcommand-gate.md) | 中文 + +## Problem + +`meta` 与 `upgrade` 两个入口把实验性状态写在名字里：`dsh experimental-meta` 和 `dsh experimental-upgrade`。前缀让每次调用都变得冗长，而在稳定时重命名命令会破坏对它的所有引用——肌肉记忆、脚本与文档皆然。这种状态应当由一个显式选择加入的门槛承载，而不是由名字承载。 + +## Decision + +`dsh experimental-meta` 改为 `dsh meta`，`dsh experimental-upgrade` 改为 `dsh upgrade`。二者只有在调用时传入各自的 `--experimental` 标志、或环境中带有 `DSH_EXPERIMENTAL=1` 时才会运行；否则命令在 stderr 上明确报错并以退出码 1 结束，同时指明两种选择加入方式。依据发布前立场，旧名称已移除且没有别名，`args.spec.ts` 钉住了对它们的拒绝。 + +该门槛分为两半，各有其归属。按调用的一半是每个实验性子命令上的 Commander `--experimental` 选项，在其 action 内、泄漏父级选项的拒绝之后检查。环境的一半是 `parseDshArgs` 的一个布尔参数：`bin.ts` 在进程边界读取 `process.env.DSH_EXPERIMENTAL === '1'`（在 `loadEnv` 之后，因此项目 `.env` 也可以设置它）并向下传递结果，因此解析器对环境的依赖显式体现在签名中，测试也无需改动环境变量。`1` 是唯一的启用值——该变量是显式的选择加入，而不是真值判断。 + +之后要稳定某个命令，只需删除它的 `--experimental` 选项和 `requireExperimental` 调用；名字不再变动。 + +## Testing + +`args.spec.ts` 钉住两条准入路径、裸名称拒绝、旧名称拒绝，以及在环境选择加入下对泄漏选项的拒绝。`built-bin.e2e.ts` 端到端地证明组装后的入口：stderr 上的门槛诊断与退出码 1，以及 `--experimental`、`DSH_EXPERIMENTAL=1`（而非 `DSH_EXPERIMENTAL=0`）会到达 TUI 的管道 stdio 拒绝——即此门之后的下一道关卡。两个被把守的命令还在 tmux 中做了交互式验证：`dsh meta --experimental` 与 `DSH_EXPERIMENTAL=1 dsh meta` 以检出目录为 workspace 启动 TUI，`DSH_EXPERIMENTAL=1 dsh upgrade` 播种 `dsh-upgrade` skill。 + +## Alternatives considered + +**保留 `experimental-` 名称前缀。** 按用户的指示拒绝：前缀让每次调用都付出代价，稳定时也会变成破坏性的重命名，而不是删除一个门槛。 + +**父级 `--experimental` 标志（`dsh --experimental meta`）。** 拒绝：默认界面刻意保持纯选项形式并启用 `enablePositionalOptions`，跨子命令边界泄漏的父级选项都被视为拼错的调用。一个只被两个子命令消费的父级标志，恰恰就是适配器在其他所有地方都拒绝的泄漏选项形态。 + +**在 `parseDshArgs` 内部读取 `process.env`。** 拒绝：本仓库在进程边界做验证，并保持类型化接缝的纯粹性；否则测试必须在每个用例前后修改并恢复 `process.env`。 + +**接受任何非空的 `DSH_EXPERIMENTAL`。** 拒绝：遥测开关作为隐私控制倾向于误关而非误开，但实验性门槛是一种确认——`DSH_EXPERIMENTAL=0` 绝不能启用它所指名的命令。 + +## Consequences + +日常调用缩短为 `dsh meta --experimental` 和 `dsh upgrade --experimental`；在环境中设置了 `DSH_EXPERIMENTAL=1` 的开发者可以直接使用 `dsh meta`/`dsh upgrade`。`dsh --help` 将这两个命令标注为 `(experimental)`。在命令稳定之前，门槛的代价是一个额外的标志或环境变量；稳定时删除门槛即可，名字已是最终形态。 diff --git a/.agents/notes/archived/manifest.json b/.agents/notes/archived/manifest.json index e46d7c34cd..58928312af 100644 --- a/.agents/notes/archived/manifest.json +++ b/.agents/notes/archived/manifest.json @@ -25,12 +25,21 @@ "architecture/2026-07-05-windows-fs-permissions.i18n.yaml": "sha256:7e61ee9bbd9de4bf3285a6f250d9625bd062e5fb90279dbffd64c820f1f7fe6b", "architecture/2026-07-05-windows-fs-permissions.md": "sha256:03734da511eae3b0736f7cad73d9da76ae2f69f9d5ed09089b0121ccb135a861", "architecture/2026-07-05-windows-fs-permissions.zh.md": "sha256:454848057ea905fe76c88d17264e71e71fb685f08f82088de6976878372865c3", + "architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml": "sha256:1b4822af5c8d642b73e3a0b04fb0a1dea9f50d0147046fbef53f5e49c030fb91", + "architecture/2026-07-22-tui-interactive-extension-service.md": "sha256:ca6b2774f4821e66f7c8397f20fcd34926728ded853fa48cbe451db7a8d2f883", + "architecture/2026-07-22-tui-interactive-extension-service.zh.md": "sha256:5b060c7626ee796c27108be7467a5e4be0677d7525d383336e7ec31ddce5c303", "architecture/2026-07-23-unified-session-query-service.i18n.yaml": "sha256:e8733b6543d9602ec206a087d9e89815f041f60fb57e93bee80e1309b9f03067", "architecture/2026-07-23-unified-session-query-service.md": "sha256:28d003686f29ec5e072e51e73da353575bcdcba5af20fefdfad88340e1ddd32c", "architecture/2026-07-23-unified-session-query-service.zh.md": "sha256:cfbe6525bc3b072fbc6db6bdca7a4d8cb4fc5507b1655bebc6af0589ed29ed31", "architecture/2026-07-24-dsh-commander-argument-adapter.i18n.yaml": "sha256:cf99eda0e58b49630d5f95792459d7095666fafbef61f614165d5cdd031b7118", "architecture/2026-07-24-dsh-commander-argument-adapter.md": "sha256:705654c8a43bcd199f72c21a77d24ca8bfa02447aff1c7f3e4e820be61dcd562", "architecture/2026-07-24-dsh-commander-argument-adapter.zh.md": "sha256:3844f02d7659d18caf5d39e1131ed775c789cbf92dc44b4a446c7d6468aa5d00", + "architecture/2026-07-27-tui-chat-channel-module-split.i18n.yaml": "sha256:7b9dbe8b4a340640610abe7e54fb29492d77a187c176996a53d0e1fc7c8e1945", + "architecture/2026-07-27-tui-chat-channel-module-split.md": "sha256:3e2cd43f306a18b3eaf9bac23e6bdc3a5dbdc7388b7c399ce71e4f71b8f71d2a", + "architecture/2026-07-27-tui-chat-channel-module-split.zh.md": "sha256:d6b84fdcd91a2693b72cf6884b3a0c39e56e571b2b694f630805d894a6ba292f", + "architecture/2026-07-28-consolidated-tui-presentation.i18n.yaml": "sha256:1eb43c420a21b7a3adf0aa5274d9aa597187630a29d7e535c5e266f82e803665", + "architecture/2026-07-28-consolidated-tui-presentation.md": "sha256:e6fa4ea0c9d1d94942ab98de47c554f4e8aa3b639a1cce52113107b1dbb0f4b0", + "architecture/2026-07-28-consolidated-tui-presentation.zh.md": "sha256:01814434482a84ebd7f672eb5c26fc468b568e773452563bf39ba52ad25d054a", "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", @@ -43,9 +52,33 @@ "bug-fix/2026-07-23-thinking-row-disclosure-target.i18n.yaml": "sha256:fd926967311f30ea4a222e88b845f95d74af75d1e94b24ebef59186593b9ca78", "bug-fix/2026-07-23-thinking-row-disclosure-target.md": "sha256:92815c170972b1b91c3d75dd0c846c070805ec1e99ce368b6aae37b048e19869", "bug-fix/2026-07-23-thinking-row-disclosure-target.zh.md": "sha256:0e09f5f5e14d74214e5157ceb5859c866bab6de701c47e2ce5c450866d75aecf", + "bug-fix/2026-07-23-tui-generic-card-markdown.i18n.yaml": "sha256:51fec8e6d7a998fd6189e70d32a6be293500abc8435b23257449e6f6d15a0053", + "bug-fix/2026-07-23-tui-generic-card-markdown.md": "sha256:7dda1114a392737465837e014059c1049da37330e3069b74f6e2ea34eccbce6e", + "bug-fix/2026-07-23-tui-generic-card-markdown.zh.md": "sha256:5040a1aaa8ff9dddeeb572a628410a79d870a90f84be00bf421e4b63e1974a4b", + "bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.i18n.yaml": "sha256:8ac9e40a4a7ac1f526b5a23656579414322bd947d991cfc02c0be0e1aacf2d68", + "bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.md": "sha256:5a1f6ba4baf25ad412eda3601ee074aeb607388da0375979797797a81eeba9da", + "bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.zh.md": "sha256:a7bbc530b9fc5e31ceb0f72d87edc720a0bd04ce7613b2ca9f9704cd5e7f682e", "bug-fix/2026-07-26-intent-draft-same-tick-echo.i18n.yaml": "sha256:c623947c4fa00e6d4b51792c7972ba09582bbcb7605beb373725c0dd666f2c81", "bug-fix/2026-07-26-intent-draft-same-tick-echo.md": "sha256:fa8b1417b2cdd3deecbf8e55bdddd73dd3a8c6e3486fd399b0b8bdf317e56373", "bug-fix/2026-07-26-intent-draft-same-tick-echo.zh.md": "sha256:00ce72552dbaa11562fbc541343a5d33f9449edabbe6dd354eb879a7d4d530f8", + "bug-fix/2026-07-27-tool-card-single-row-fields-inline.i18n.yaml": "sha256:4b94aded16c60628d22414dce524e8a98a8af4fff298805ee7efc63cae02c90d", + "bug-fix/2026-07-27-tool-card-single-row-fields-inline.md": "sha256:40adcd522a9a2eeacc6f2b0196d1f24888a4f57830b7490a3be3d78c86c4e968", + "bug-fix/2026-07-27-tool-card-single-row-fields-inline.zh.md": "sha256:a79d56c9b781442ee596b47707d1a8c80abcd6466094b01802189c8e55f16da7", + "bug-fix/2026-07-27-tui-diff-card-redundant-path-header.i18n.yaml": "sha256:8613a1cfcf4b9c7fafa78a8d8565e2a65ef0335b7b826af9b2bb32097836af55", + "bug-fix/2026-07-27-tui-diff-card-redundant-path-header.md": "sha256:1bd344aec5454d2a2d6e1e6a32eff035c4a99c3df409f2624b39fd32e23ee402", + "bug-fix/2026-07-27-tui-diff-card-redundant-path-header.zh.md": "sha256:0a1747006efb1a4b67feceb9b627a437a0f023158e90ae86e1fe8aef76485384", + "bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.i18n.yaml": "sha256:280b93ece72662501f65edd58a00cdafb5b5941e4ef1314d7198fab18950cb03", + "bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.md": "sha256:112bdbde16b6023eeb5b8a79cd2a711385e7198d51bbfc0520e9612acaa95c8a", + "bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.zh.md": "sha256:fc4e7f778ea63c4583cf81132c264cf6c4b9cc3e1818778061b0497ff16b8ef6", + "bug-fix/2026-07-30-tui-adapter-registration-race.i18n.yaml": "sha256:50b7a32e11591719c249258ecc2ec0f45e58f1a04050d2e53f6e2650f58ba137", + "bug-fix/2026-07-30-tui-adapter-registration-race.md": "sha256:7e17eb1dd8f92e1efb7a18477df277b13580840b473ffe8a5309fc70ec3cfa3e", + "bug-fix/2026-07-30-tui-adapter-registration-race.zh.md": "sha256:efcbd3d82af6a58677efe1a0580edd715945b6a93418fde47badac9c01a29866", + "bug-fix/2026-07-31-tui-diff-context-line-accounting.i18n.yaml": "sha256:cd39ae2646fdc6827bf29a63953b5463faa37d5b404ae8cc3c0913c47bc92d0c", + "bug-fix/2026-07-31-tui-diff-context-line-accounting.md": "sha256:57066bccd22c2dc2c3546b363de73d13b55ff8683ee12b17a81ed2bcf536645b", + "bug-fix/2026-07-31-tui-diff-context-line-accounting.zh.md": "sha256:a658d886c5eb203f5f30a6fac70ad18e4a24cf756746254723d8f1d144653c04", + "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", "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", @@ -76,9 +109,15 @@ "feature/2026-07-14-time-context-plugin.i18n.yaml": "sha256:670c093817c77e093562e02f43984d42ed44ebcced7c91d09366839e412d05e1", "feature/2026-07-14-time-context-plugin.md": "sha256:618b121da38a8b610bcadaecf121ca823b2c8c13598c012b350c214b82fd238f", "feature/2026-07-14-time-context-plugin.zh.md": "sha256:1e9eee8ba427a6f2ee08c79e2fcb33c0948e67a80758fdf9f8c9f7dff9aea361", + "feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml": "sha256:c04ec462f846887f349ffeb48aef8febf50f06903e7177ffd7679a694f6c1a57", + "feature/2026-07-17-dedicated-full-screen-tui-front-door.md": "sha256:feb70faaad016965e8cc1bd7339947e48937fb3e8ea1425dada581073396f50c", + "feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md": "sha256:71e4a4abf01e5fc46f7da60e0a66bca659c1ee3c4ea2c4bc20587844f33920fe", "feature/2026-07-20-tui-startup-slogans.i18n.yaml": "sha256:265d1fd79dae6c785201c81ffe2de3baa9fe9e3b6c0f84aac79c90f4040ced15", "feature/2026-07-20-tui-startup-slogans.md": "sha256:aaaab4b419d35ce24317b7730f15af0029878bf3d17c6f184b05138c2cd44930", "feature/2026-07-20-tui-startup-slogans.zh.md": "sha256:01fba568cd92e9c54857f6dba1a3a5a6a4d0e906f36915d7e64682e67d456708", + "feature/2026-07-20-windows-tui-support.i18n.yaml": "sha256:fa7253a8e20308b216c21d201720a4b7d6b74ccc9a650c0d30081c9e5b6bf04c", + "feature/2026-07-20-windows-tui-support.md": "sha256:abf80ade38ec4d9e558c0fa9b0ecc8877acc18442f4ed945ebc2f4b153d85087", + "feature/2026-07-20-windows-tui-support.zh.md": "sha256:6690a7693b8a4c8ce495c13ae84d9dc81f41c691d217db3152ea0d926dffa0f8", "feature/2026-07-21-dsh-system-prompt-source-path.i18n.yaml": "sha256:22efaf3237425fecbac1b40a444454e0fc244a3c85c2f6a14535de22ea777719", "feature/2026-07-21-dsh-system-prompt-source-path.md": "sha256:5fa554932c62a8bbd5a619581710d7f8b6b65d79ec1e340129cda96d279c5ae3", "feature/2026-07-21-dsh-system-prompt-source-path.zh.md": "sha256:995cd593074881c72510a6af3ba80108bbf986d49508cce9f698c2fcb493fd23", @@ -106,6 +145,12 @@ "feature/2026-07-21-tui-reload-command.i18n.yaml": "sha256:9be416ccd681aed0781fdfd2c44c4821c1e45f2a0deccb1f2b47d46163bde488", "feature/2026-07-21-tui-reload-command.md": "sha256:b8616457822ae87c90062308bc8c0d2badd5f368092ec65847d0d9520b1ac372", "feature/2026-07-21-tui-reload-command.zh.md": "sha256:c24bfcb0df13977a9c11c4d0fe433169e535b5f764995b668430dbb14a8e6b33", + "feature/2026-07-21-tui-resume-command.i18n.yaml": "sha256:50526c2ec1bf5fe4f2f912e70fc8145f6978907f80f9d716ca3bcb17cd028933", + "feature/2026-07-21-tui-resume-command.md": "sha256:821cfee22ff6ed491807ecca492538e2dd18ce4b00e7c09b6f4e8604cb02b97b", + "feature/2026-07-21-tui-resume-command.zh.md": "sha256:7fe8e638df0f1977bb93a9efd973d4f69a19ad48e43dae6b1bc8eb70758a561b", + "feature/2026-07-21-tui-skill-slash-command.i18n.yaml": "sha256:c711fd237649c81705a6bc5b20d7b4585ced3166acbc8cc3c2877d97bb386edf", + "feature/2026-07-21-tui-skill-slash-command.md": "sha256:b2904829540a1801852e072937dc259830e93f0c719590da0a189879aca1d7a6", + "feature/2026-07-21-tui-skill-slash-command.zh.md": "sha256:350ed930218b5c4dfb721ebaceac419f4cb2c73f047c004747ba01535a77cab5", "feature/2026-07-21-tui-steering-queue-badge.i18n.yaml": "sha256:a029da558a6e14e1f13269960b98273ca9af0141579967acfbc19b656775f4a5", "feature/2026-07-21-tui-steering-queue-badge.md": "sha256:9aabd68c8910fdc7e7b05674492ddb8dc9285dd691fe554adcb84026fb846cc8", "feature/2026-07-21-tui-steering-queue-badge.zh.md": "sha256:919fd737866c3700f945751628071dab89eabdbf8f809deab93b9e6fbe2c8c59", @@ -115,15 +160,60 @@ "feature/2026-07-23-trajectory-step-cell.i18n.yaml": "sha256:fe2e935a0affdef877902a40d9861ef5f55b30f40650469f6a52a4d45a92793f", "feature/2026-07-23-trajectory-step-cell.md": "sha256:185e3b87174cb6d2f2d2271fd2a74b1517d03e8570be602570d027bf6002d106", "feature/2026-07-23-trajectory-step-cell.zh.md": "sha256:51f46be43d2f5c4f78a05ed9aeec92d1f33ac988f45cf24d35528e9c43828ef3", + "feature/2026-07-23-tui-file-reference-autocomplete.i18n.yaml": "sha256:f95d9b37369ca8a0eecb07784759e94b5e0e85b7565c7256008c2f9db0d0c157", + "feature/2026-07-23-tui-file-reference-autocomplete.md": "sha256:5a6fd182d9080d757b4ad565e98233b0f128589cbfa6d741dc76a7cc0f41b5c6", + "feature/2026-07-23-tui-file-reference-autocomplete.zh.md": "sha256:8676fd1f57fd705c25f8c37fbfd91126a85387d5b6261d22470b035723a6ad73", + "feature/2026-07-23-tui-status-prompt-tools.i18n.yaml": "sha256:e8072d6661c91b43d13ef88b69fc49b9a312a7b5cb0b6f0171c0fdafc36b0435", + "feature/2026-07-23-tui-status-prompt-tools.md": "sha256:0dd669c70ac34024b389d76c81dcf4f1d5b747f56b7d6d82587c8c15a421c0a2", + "feature/2026-07-23-tui-status-prompt-tools.zh.md": "sha256:6a488b18e1516887d6073375651fba59c3a266b888f9ca2d4804f6681838059b", + "feature/2026-07-24-configurable-tui-prompt-theme.i18n.yaml": "sha256:694de3851ca1e3de76c4f4fb7f3581ad0df568a99046c905f56d24a54407a5ba", + "feature/2026-07-24-configurable-tui-prompt-theme.md": "sha256:694136b6d9bf7de25c240c373cb268cf798f8617c206d53c1d0ef7443e75adeb", + "feature/2026-07-24-configurable-tui-prompt-theme.zh.md": "sha256:ee083f864bf6915a887b7883d14a6662ff6ecb4e702f4ac0f583d0c8f823bf50", "feature/2026-07-24-new-session-clears-to-empty-state.i18n.yaml": "sha256:978638cbf18bc6dce9fea0817654f41cc307f99004a637b85a63ae2208fe9095", "feature/2026-07-24-new-session-clears-to-empty-state.md": "sha256:b6b71d3883a167056070713e3dffb5046de953bdd218074d17c88e7690e03d83", "feature/2026-07-24-new-session-clears-to-empty-state.zh.md": "sha256:82a80b48337487029acd05a0137d268f0850f46801fa44a0e62733cacd00d5e9", + "feature/2026-07-24-tui-question-dialog-multiline.i18n.yaml": "sha256:b8a90f13f579c17476e94740079ac2e058f2a97ec4d723fe2841398426129858", + "feature/2026-07-24-tui-question-dialog-multiline.md": "sha256:0bf07eb8731cf6928db275f160ba36b07ce93d53873eec2fb6dcaabaa0c57f76", + "feature/2026-07-24-tui-question-dialog-multiline.zh.md": "sha256:85f5dedc794014152792557158b826650b147fe6d439e71ea23c115d2c2c84de", + "feature/2026-07-24-tui-shell-prompt-editor.i18n.yaml": "sha256:f40b5ba2d22e3a52fea2d3d0f3f481ef710764c3ec4379e7c859f52c61434b1b", + "feature/2026-07-24-tui-shell-prompt-editor.md": "sha256:7bbb99108a7dfe219c031f77cafa5bbcfacd1dd05080822fe11e0ca58da4b3f5", + "feature/2026-07-24-tui-shell-prompt-editor.zh.md": "sha256:6e20225724941290bbdc9af86d4f91e1beb93bde5c2d67144f0a32c4abb30e7b", "feature/2026-07-26-code-mode-trajectory-waterfall-spans.i18n.yaml": "sha256:916525fdc3a12061928380fd8f7b81cd9763a7873663aad564843fccab0ccedc", "feature/2026-07-26-code-mode-trajectory-waterfall-spans.md": "sha256:a822963e4c34c9737681d6d70d8167731d4350e66ef7f356684ad096c04fa7ab", "feature/2026-07-26-code-mode-trajectory-waterfall-spans.zh.md": "sha256:ef01163adf1245f75cc8291db70d389314dee43b6bff958a9da49b097531218d", + "feature/2026-07-27-assistant-timing-header-trailing.i18n.yaml": "sha256:e5a8aa9e5194dae6f4369299a64acae2c751d7f85e457e8dec1c14e1dbcee3e9", + "feature/2026-07-27-assistant-timing-header-trailing.md": "sha256:85fac4a712ac5b4d61c224eddede08edb27db2e3718321c094a55034c75ce984", + "feature/2026-07-27-assistant-timing-header-trailing.zh.md": "sha256:260d115d2da429eeac73b7256944e60cb03a93714f5d13b5e219dff316f5a958", + "feature/2026-07-27-tui-running-glyph-smooth-fade.i18n.yaml": "sha256:e440b7f4800f722f1a0f9d089081ac19a7fbf809cb75136566ae363b4aa0aab9", + "feature/2026-07-27-tui-running-glyph-smooth-fade.md": "sha256:cc58dce4788c8478c97ce589e4519cfb1b6a6cc3ec46d263f3038823231e5ae5", + "feature/2026-07-27-tui-running-glyph-smooth-fade.zh.md": "sha256:c1735d5bd4b5e75989a9aead8af29136e7fadc01e79fb8c8cc68601a31fbf94a", + "feature/2026-07-27-tui-tool-card-header.i18n.yaml": "sha256:1ed2c377f6d2c589195a00e84f92e6511b9a0793a2684a75ec3a0ca1f2b98670", + "feature/2026-07-27-tui-tool-card-header.md": "sha256:ebb3d913960cdb0949a753c5811bd7d68a96f64f3b0549cd2ab7e4997b6b2d28", + "feature/2026-07-27-tui-tool-card-header.zh.md": "sha256:402a619dce15534fbf88a59361b693eeb2121584fbb2e7af4e93eeaccaf2d0ea", "feature/2026-07-27-user-message-icon-actions.i18n.yaml": "sha256:b33e480f19ec58c8c60417a6c03999953d463ca54606a5ac80ec528edf57c49b", "feature/2026-07-27-user-message-icon-actions.md": "sha256:b6332e67c6dad0a3fcdb597cec9e4dc32b44ad33665f39c1a50501cf38d3f5ad", "feature/2026-07-27-user-message-icon-actions.zh.md": "sha256:0fc824eac66a18063f7098e1c395c09b580d5a30b96f2b856608c084212c2ac2", + "feature/2026-07-28-dsh-guided-skill-session-commands.i18n.yaml": "sha256:cf56e0ff7f2af7a5b50b27818fddb66a0c5300de98fc5733673ce094cd14bb22", + "feature/2026-07-28-dsh-guided-skill-session-commands.md": "sha256:9234465259f89fbedd5dfc07f26acbc9e48e16ce829cc6ada672c4d597b0b255", + "feature/2026-07-28-dsh-guided-skill-session-commands.zh.md": "sha256:57ee966476f755c1a6832d35d5f045f9d9e63a97a824e8a3723ba914502ade7f", + "feature/2026-07-28-dsh-meta-source-workspace.i18n.yaml": "sha256:f7c6b5db53c32c7475f4f6bb3ae189ed8d67f2163196ab315d6f81fde3aa37d9", + "feature/2026-07-28-dsh-meta-source-workspace.md": "sha256:ee8b2f6055b27957fa27258f26a07183b7102933af68c64d0df418e32d3d8754", + "feature/2026-07-28-dsh-meta-source-workspace.zh.md": "sha256:0b10db368e04c24be03569a56ec4b69fed66b70c39a3c4f168b5f1c912efcd96", + "feature/2026-07-29-tui-hidden-mode-assistant-fold.i18n.yaml": "sha256:0865835802348b730542adbe6b7db613750f3786993c6a14dbb2f47686c13c70", + "feature/2026-07-29-tui-hidden-mode-assistant-fold.md": "sha256:a5fefebd802e2d9c3c79c7852c1c34c7bbef3f2ac2150d224608b9ec44e966ad", + "feature/2026-07-29-tui-hidden-mode-assistant-fold.zh.md": "sha256:21bccd1e07ec8dc73b618f428461848bb90b6235afe0b842afb0afab2d5cc575", + "feature/2026-07-30-compaction-progress-visibility.i18n.yaml": "sha256:4c2267054ad5d73aecc8d39d138a0cb532981b33175252e67252d07c3314b0f5", + "feature/2026-07-30-compaction-progress-visibility.md": "sha256:2dfe07244cd784f27a9e5850801d40e96eae21a20ba10aaf56f9a793cdf5b505", + "feature/2026-07-30-compaction-progress-visibility.zh.md": "sha256:6180b8aff0536147ab6ed6a78ecdbe1448fd12d89407746ecb1c7c05c73d4d60", + "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-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", + "feature/2026-07-31-experimental-subcommand-gate.i18n.yaml": "sha256:d223669bebbf6ea65b4ec636e8e7ed618eff389117335946be713897151c6968", + "feature/2026-07-31-experimental-subcommand-gate.md": "sha256:8fdee37340f7e72397cf2f440a2ca70639a987d07f0c2102e02e79c0fec4bfeb", + "feature/2026-07-31-experimental-subcommand-gate.zh.md": "sha256:bcdec0f82319670a1d1de54a27b103b5e2d86306b884a5f9f415b89cd5a373f4", "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", @@ -229,6 +319,9 @@ "simplification/2026-07-26-consolidate-gate-scripts-on-existing-deps.i18n.yaml": "sha256:7acf002ea8c1533f052c7bfc0c4e3da013ecf43c5872866a3ee4a8c2691c5e33", "simplification/2026-07-26-consolidate-gate-scripts-on-existing-deps.md": "sha256:f18a913096b7defd2192c4bac888a33f68075c3662703a0e28a6146897d17777", "simplification/2026-07-26-consolidate-gate-scripts-on-existing-deps.zh.md": "sha256:ff48a37673c97059536fe5b61aff746133eac682145550badb049eb5c83b097c", + "simplification/2026-07-27-copyable-transcript-no-gutter-bar.i18n.yaml": "sha256:821f96f3e203e03b80553c07b10a511926bb5014be95c7df6bffb30c8e226d31", + "simplification/2026-07-27-copyable-transcript-no-gutter-bar.md": "sha256:4b6aa150bbc8a4da0acac4d20f5fb8c2b77fef7e9c4c4dba8fd8e84dec36d619", + "simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md": "sha256:5225e627ff301be171434a5b9f18905fe1578f50eb2d4bf9998e126aba6cc3e3", "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", @@ -246,6 +339,9 @@ "testing/2026-07-06-pin-request-header-content-in-one-scenario.zh.md": "sha256:cac75d4475666239bbe0030b90c0fa7cc66024af5b9f8ef217e53018be64890e", "testing/2026-07-08-shared-acp-snapshot-package.i18n.yaml": "sha256:fc37fcdfe8744f8c8f39eda3f494eed25ee8c4d5322d1f3f671eabd2c5d7026e", "testing/2026-07-08-shared-acp-snapshot-package.md": "sha256:285b4a3c0b1ef7a837e6713cf0192ddc8a26101f6737fa3923682a9e91350c50", - "testing/2026-07-08-shared-acp-snapshot-package.zh.md": "sha256:02da3f910c2060f70038a0d86a7ddae4a8890905600440e1373412f54fbdcea8" + "testing/2026-07-08-shared-acp-snapshot-package.zh.md": "sha256:02da3f910c2060f70038a0d86a7ddae4a8890905600440e1373412f54fbdcea8", + "testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml": "sha256:c1a22174274b9f34ef4368039b3547f221507b040bd51b87af73a2722ee6b4d2", + "testing/2026-07-18-tui-terminal-state-snapshots.md": "sha256:9a7fdcbeafc34376cb049b9668e0f4e9e541f523116fb11c3af9d35c2963e908", + "testing/2026-07-18-tui-terminal-state-snapshots.zh.md": "sha256:26750f240f6c8a7b28746f62fe161b357e9c5dd52867cc7037399f1ed6ff37fa" } } diff --git a/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.i18n.yaml b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.i18n.yaml new file mode 100644 index 0000000000..c7ce910e5f --- /dev/null +++ b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.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/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md +2026-07-27-copyable-transcript-no-gutter-bar.md: a4eca191d28a834b05a6839997aab602852912c0 +2026-07-27-copyable-transcript-no-gutter-bar.zh.md: b1f661cb76bb879e414a0dcfd08fc9349ae070c7 diff --git a/.agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md rename to .agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md index 659b7d2f2f..a4eca191d2 100644 --- a/.agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md +++ b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.md @@ -1,6 +1,7 @@ # Agent Note: Copyable TUI transcript without gutter bars Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-27-copyable-transcript-no-gutter-bar.zh.md) diff --git a/.agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md similarity index 99% rename from .agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md rename to .agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md index 5c43169ba3..b1f661cb76 100644 --- a/.agents/notes/implemented/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md +++ b/.agents/notes/archived/simplification/2026-07-27-copyable-transcript-no-gutter-bar.zh.md @@ -1,6 +1,7 @@ # Agent Note: 无 gutter bar 的可复制 TUI transcript Status: implemented +Archived: 2026-08-04 [English](2026-07-27-copyable-transcript-no-gutter-bar.md) | 中文 diff --git a/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml new file mode 100644 index 0000000000..4d5f9581c3 --- /dev/null +++ b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.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/testing/2026-07-18-tui-terminal-state-snapshots.md +2026-07-18-tui-terminal-state-snapshots.md: eef9777c1f3d19c03985c0d105223960dd7d4878 +2026-07-18-tui-terminal-state-snapshots.zh.md: 50d2e1b81762538a08abda5608a7d26f2dd0b841 diff --git a/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.md similarity index 55% rename from .agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md rename to .agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.md index b8e6f77d96..eef9777c1f 100644 --- a/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md +++ b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.md @@ -1,6 +1,7 @@ # Agent Note: Snapshot semantic terminal state for the TUI Status: implemented +Archived: 2026-08-04 English | [中文](2026-07-18-tui-terminal-state-snapshots.zh.md) @@ -10,26 +11,24 @@ The TUI is a stateful renderer. Its user-visible result depends on ANSI parsing, Component-line snapshots stop before ANSI reaches a terminal and miss cursor movement, clearing, styling, overlay composition, and reflow. Raster screenshots include font and platform rendering noise that is unrelated to the TUI contract. A completed flow built by directly appending plausible session events has another blind spot: it proves the renderer accepts those shapes, not that the production agent loop and tool implementations produce them. -The TUI therefore needs a deterministic, reviewable representation of terminal state, recorded model journeys that execute the real downstream stack, and a smaller test at the real process and PTY boundary. +The reusable TUI therefore needs a deterministic, reviewable representation of terminal state. A product deployment that ships it additionally needs recorded model journeys through the assembled stack and a smaller test at the real process and PTY boundary. ## Decision -TUI coverage has four complementary layers: +Reusable TUI coverage has two complementary package layers: 1. `packages/ui/tui/tests/tui.spec.ts` tests event mapping, input routing, disposal, and error behavior directly. 2. `packages/ui/tui/tests/tui.snapshot.ts` mounts the production TUI against a headless terminal emulator for transient states that a completed session log cannot retain: in-flight streaming, pending tool calls, overlays, expansion, compaction reflow, errors, and shutdown. -3. `examples/tui-agent/tests/tui.snapshot.ts` replays committed JSONL session logs through the production agent loop and real tools, then compares the resulting semantic terminal state. -4. `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` boots the real Loader composition in a PTY, drives a scripted conversation through streaming and `ask_user_question`, and verifies startup, input, exit, failure reporting, and terminal restoration. -The runnable TUI is the shipped `apps/cli` composition: the shared `base.cordis.yml` plus the `tui.cordis.yml` overlay, which owns the interactive coding backends, tools, and front door. TUI snapshots and PTY tests live in `apps/cli/tests/`. The [redundant-agent removal](../simplification/2026-07-20-remove-stdio-and-echo-agents.md) owns this consolidation. +The [explicit-config entrypoint decision](../simplification/2026-08-03-explicit-config-dsh-entrypoint.md) removed the product TUI composition, recorded application journeys, and PTY suite. A deployment shipping a terminal front door owns those assembled-application layers; package tests do not claim that product coverage. -### Recorded-session replay +### Removed application replay -Each example-level scenario directory owns `session.jsonl`, optional child logs `session..jsonl`, and `terminal.expected.txt`. The primary log supplies user-authored `user/message` prompts and the recorded `assistant/chunk` sequence. `dsh-llm-replay` derives one model-call script per session, binds child logs to fresh child sessions, and is the only mocked boundary. The agent loop, bash and filesystem implementations, Code Mode worker, subagent provider, workflow worker, Cordis tools, presenters, and TUI are production implementations. +The deleted application suite gave each scenario `session.jsonl`, optional child logs `session..jsonl`, and `terminal.expected.txt`. The primary log supplied user-authored `user/message` prompts and the recorded `assistant/chunk` sequence. `dsh-llm-replay` derived one model-call script per session and was the only mocked boundary; the agent loop, tools, workers, presenters, and TUI were production implementations. -The suite rejects a journey when its tool-call sequence differs, an expected event count is missing, a tool result is an error, a turn ends in error, a workflow lifecycle is incomplete, or the live child-session count differs from the fixture set. These assertions prevent an attractive terminal expected output from hiding a failed or bypassed production path. +That suite rejected a journey when its tool-call sequence differed, an expected event count was missing, a tool result was an error, a turn ended in error, a workflow lifecycle was incomplete, or the live child-session count differed from the fixture set. These checks remain the acceptance pattern for any future terminal deployment; they are no longer shipped fixtures. -The live-model fixtures use `DSH_SNAPSHOT=record`; record mode rewrites their primary and child JSONL logs and terminal expected outputs. The deterministic Cordis toolchain keeps an authored complete JSONL script because reliably coercing a live model through five exact tool boundaries and two children is not a stable recording contract. `DSH_SNAPSHOT=refresh` replays every committed script keylessly and rewrites only derived terminal expected outputs. Plain replay compares without writing, and unknown mode values fail loud. +The removed recording workflow used `DSH_SNAPSHOT=record` for model journeys and `DSH_SNAPSHOT=refresh` for derived terminal output. Removing the product entrypoint also removed those modes from the repository snapshot lane; reusable TUI snapshots are authored directly from package scenarios. ### Semantic terminal projection @@ -43,13 +42,6 @@ Every checkpoint enforces theme independence across the complete terminal state: | Layer | Scenario | Contract pinned | |---|---|---| -| Recorded journey | Multi-turn conversation | Recorded reasoning/text chunks, two input turns, retained history, token totals, and idle editor state | -| Recorded journey | Todo plan | Real `todo_write` execution, result card, and persistent plan rendering | -| Recorded journey | Bash terminal card | Real local executor output, description, exit status, and completed terminal card | -| Recorded journey | Parallel filesystem reads | Two calls from one assistant message, real file contents, ordering, and separate completed cards | -| Recorded journey | Code Mode | Real `run_code` worker execution, two `tool/code-dispatch` events, captured program output, and completed card | -| Recorded journey | Dynamic workflow | Real workflow worker, phase lifecycle, replayed child session, structured return value, and completed card | -| Recorded journey | Cordis dynamic toolchain | Real mount, Code Mode inspect, direct subagent, workflow child, unmount, and all production presenters | | Transient state | Streaming and pending advanced calls | In-flight reasoning/text plus pending Code Mode, workflow, and Cordis cards that disappear from completed logs | | Transient state | Cards, interaction, layout, failure, and shutdown | Collapsed/expanded card families, question validation, compaction replacement, resize reflow, help/errors, cursor restoration, and terminal stop | @@ -58,13 +50,13 @@ Every checkpoint enforces theme independence across the complete terminal state: - **Snapshot raw terminal writes** — rejected because differential rendering may change write boundaries without changing the screen, while cursor and clear sequences are unreadable in review. - **Snapshot component render lines before terminal output** — rejected because it does not test ANSI parsing, cursor movement, overlays, viewport behavior, or independent components in one frame. - **Build every completed flow by appending session events** — rejected because a hand-authored event sequence can drift from the agent loop, tool execution, child-session binding, or worker behavior while its presentation test stays green. Direct event construction remains limited to transient renderer states. -- **Reuse ACP stdout expected outputs as the TUI oracle** — rejected because a recorded model journey is transport-neutral but its presentation is not. TUI scenarios own terminal expected outputs while using the same JSONL replay vocabulary. +- **Reuse ACP stdout expected outputs as the TUI oracle** — rejected because a recorded model journey is transport-neutral but its presentation is not. A terminal deployment owns its expected output while it may reuse the same JSONL replay vocabulary. - **Commit raster screenshots** — rejected because fonts, glyph metrics, antialiasing, and host terminal themes make them platform-sensitive and make semantic style changes difficult to review. - **Use only PTY end-to-end tests** — rejected because raw PTY output is a stream of historical drawing operations, not queryable final state. PTY tests retain the real Loader/input/teardown boundary, while the emulator owns broad state coverage. ## Consequences -- Completed advanced snapshots now fail when the real Code Mode, workflow, subagent, filesystem, bash, or Cordis path breaks, rather than accepting a fabricated result event. +- Package snapshots fail when TUI event mapping or presentation breaks; they do not substitute for an assembled application's tool-path transcript. - TUI visual regressions produce readable cell-and-style diffs, while JSONL fixtures retain the exact model chunks that made the production path execute. -- The emulator uses xterm's proposed buffer API. An xterm upgrade requires rerunning and reviewing the semantic projection; terminal-specific behavior still needs the PTY smoke. -- Expected outputs deliberately encode wrapping and viewport behavior at fixed sizes. Intentional layout changes use keyless refresh, while model-journey changes use record mode and review both JSONL and terminal diffs. +- The emulator uses xterm's proposed buffer API. An xterm upgrade requires rerunning and reviewing the semantic projection; terminal-specific behavior still needs a PTY smoke owned by the deployment that ships it. +- Expected outputs deliberately encode wrapping and viewport behavior at fixed sizes. Intentional layout changes update and review the package semantic snapshots. diff --git a/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.zh.md similarity index 56% rename from .agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md rename to .agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.zh.md index 1b2f6b58e5..50d2e1b817 100644 --- a/.agents/notes/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md +++ b/.agents/notes/archived/testing/2026-07-18-tui-terminal-state-snapshots.zh.md @@ -1,6 +1,7 @@ # Agent Note: TUI 语义终端状态快照 Status: implemented +Archived: 2026-08-04 [English](2026-07-18-tui-terminal-state-snapshots.md) | 中文 @@ -10,26 +11,24 @@ TUI 是有状态的渲染器。用户最终看到的结果取决于 ANSI 解析 组件行快照止于 ANSI 进入终端之前，无法覆盖光标移动、清屏、样式、浮层组合和重排。栅格截图会带入与 TUI 契约无关的字体和平台渲染噪声。直接追加看似合理的会话事件来构造完整流程还存在另一处盲区：这种测试只能证明渲染器接受这些数据形态，无法证明生产环境的 agent loop（智能体循环）和工具实现会生成这些事件。 -因此，TUI 既需要确定、便于评审的终端状态表示，也需要通过已录制模型流程执行真实下游组件，并保留一项范围更小、覆盖真实进程与 PTY 边界的测试。 +因此，可复用 TUI 需要确定、便于评审的终端状态表示。交付它的产品部署还需要通过组装后的技术栈运行已录制模型流程，并保留一项范围更小、覆盖真实进程与 PTY 边界的测试。 ## 决策 -TUI 覆盖分为四个互补层次： +可复用 TUI 的覆盖分为两个互补的包级层次： 1. `packages/ui/tui/tests/tui.spec.ts` 直接测试事件映射、输入路由、资源释放和错误行为。 2. `packages/ui/tui/tests/tui.snapshot.ts` 将生产 TUI 挂载到无界面终端模拟器，覆盖完整会话日志无法保留的瞬态：进行中的流式输出、待完成工具调用、浮层、展开状态、压缩重排、错误和关闭过程。 -3. `examples/tui-agent/tests/tui.snapshot.ts` 通过生产 agent loop 和真实工具回放已提交的 JSONL 会话日志，再比较生成的语义终端状态。 -4. `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` 在 PTY 中启动真实 Loader 组合，驱动一段经过流式输出和 `ask_user_question` 的脚本化会话，并验证启动、输入、退出、失败报告和终端恢复。 -可运行 TUI 就是交付的 `apps/cli` 组合：共享的 `base.cordis.yml` 加 `tui.cordis.yml` overlay，后者拥有交互式 coding 后端、工具与前端入口。TUI 快照和 PTY 测试位于 `apps/cli/tests/`。[移除重复 agent 的决策](../simplification/2026-07-20-remove-stdio-and-echo-agents.md)负责此次整合。 +[显式配置入口决策](../simplification/2026-08-03-explicit-config-dsh-entrypoint.md)移除了产品 TUI 组合、已录制应用流程和 PTY 测试套件。交付终端入口的部署负责这些组装应用层；包测试不声称提供产品覆盖。 -### 已录制会话回放 +### 已移除的应用回放 -每个示例级场景目录都包含 `session.jsonl`、可选的子会话日志 `session..jsonl`，以及 `terminal.expected.txt`。主日志提供用户来源的 `user/message` 提示词和已录制的 `assistant/chunk` 序列。`dsh-llm-replay` 为每个会话派生一份模型调用脚本，并将子日志绑定到新建的子会话；这是测试中唯一的 mock 边界。agent loop、bash 与文件系统实现、Code Mode worker、subagent 提供方、工作流 worker、Cordis 工具、呈现器和 TUI 都使用生产实现。 +已删除的应用测试套件为每个场景提供 `session.jsonl`、可选的子会话日志 `session..jsonl`，以及 `terminal.expected.txt`。主日志提供用户来源的 `user/message` 提示词和已录制的 `assistant/chunk` 序列。`dsh-llm-replay` 为每个会话派生一份模型调用脚本，并且是测试中唯一的 mock 边界；agent loop、工具、worker、呈现器和 TUI 都使用生产实现。 -如果工具调用顺序不符、预期事件数量不足、工具结果报错、轮次以错误结束、工作流生命周期不完整，或者实时子会话数量与 fixture（测试前置数据）集合不一致，测试都会失败。即使终端预期输出表面正确，这些断言也能阻止失败或被绕过的生产路径混入结果。 +如果工具调用顺序不符、预期事件数量不足、工具结果报错、轮次以错误结束、工作流生命周期不完整，或者实时子会话数量与 fixture（测试前置数据）集合不一致，该测试套件都会拒绝流程。这些检查仍是未来任何终端部署的验收模式；它们已不再作为 fixture 交付。 -真实模型 fixture 通过 `DSH_SNAPSHOT=record` 更新；录制模式会重写其主会话与子会话 JSONL 日志以及终端预期输出。确定性的 Cordis 工具链保留一份人工编写的完整 JSONL 脚本，因为要求真实模型稳定经过五个指定工具边界和两个子会话并不是可靠的录制契约。`DSH_SNAPSHOT=refresh` 会无密钥回放所有已提交脚本，并且只重写派生的终端预期输出。普通回放只比较而不写入，未知模式值会快速失败。 +已移除的录制工作流使用 `DSH_SNAPSHOT=record` 录制模型流程，使用 `DSH_SNAPSHOT=refresh` 更新派生的终端输出。移除产品入口时也从仓库快照通道中移除了这些模式；可复用 TUI 快照直接由包级场景编写。 ### 语义终端投影 @@ -43,13 +42,6 @@ TUI 覆盖分为四个互补层次： | 层次 | 场景 | 固定的契约 | |---|---|---| -| 已录制流程 | 多轮会话 | 已录制的推理与文本分片、两轮输入、保留历史、token 总量和空闲编辑器状态 | -| 已录制流程 | Todo 计划 | 真实 `todo_write` 执行、结果卡片和持久计划渲染 | -| 已录制流程 | Bash 终端卡片 | 真实本地执行器输出、说明、退出状态和已完成终端卡片 | -| 已录制流程 | 并行文件读取 | 同一条 assistant 消息中的两次调用、真实文件内容、顺序和两个独立完成卡片 | -| 已录制流程 | Code Mode | 真实 `run_code` worker 执行、两条 `tool/code-dispatch` 事件、捕获的程序输出和已完成卡片 | -| 已录制流程 | 动态工作流 | 真实工作流 worker、阶段生命周期、回放的子会话、结构化返回值和已完成卡片 | -| 已录制流程 | Cordis 动态工具链 | 真实挂载、Code Mode 检查、直接 subagent、工作流子会话、卸载和全部生产呈现器 | | 瞬态 | 流式输出与待完成高级调用 | 进行中的推理和文本，以及完整日志中不会保留的待完成 Code Mode、工作流和 Cordis 卡片 | | 瞬态 | 卡片、交互、布局、失败和关闭 | 折叠与展开的卡片族、问题校验、压缩替换、尺寸重排、帮助与错误、光标恢复和终端停止 | @@ -58,13 +50,13 @@ TUI 覆盖分为四个互补层次： - **快照原始终端写入**：不予采纳，因为差分渲染可能在画面不变时改变写入边界，而且光标与清屏序列难以评审。 - **快照进入终端输出之前的组件渲染行**：不予采纳，因为它无法测试 ANSI 解析、光标移动、浮层、视口行为，也无法测试独立组件在同一帧中的相互作用。 - **通过追加会话事件构造所有完整流程**：不予采纳，因为人工编写的事件序列可能与 agent loop、工具执行、子会话绑定或 worker 行为发生偏差，但呈现测试仍然保持绿色。直接构造事件只用于渲染器瞬态。 -- **复用 ACP stdout 预期输出作为 TUI 判定依据**：不予采纳，因为已录制模型流程与传输方式无关，其呈现方式却并非如此。TUI 场景使用同一套 JSONL 回放词汇，但拥有独立的终端预期输出。 +- **复用 ACP stdout 预期输出作为 TUI 判定依据**：不予采纳，因为已录制模型流程与传输方式无关，其呈现方式却并非如此。终端部署拥有自己的预期输出，同时可以复用同一套 JSONL 回放词汇。 - **提交栅格截图**：不予采纳，因为字体、字形度量、抗锯齿和宿主终端主题会使结果依赖平台，也会增加语义样式变更的评审难度。 - **只使用 PTY 端到端测试**：不予采纳，因为原始 PTY 输出是一系列历史绘制操作，而不是可查询的最终状态。PTY 测试保留真实 Loader、输入与清理边界，模拟器负责广泛的状态覆盖。 ## 后果 -- 当真实 Code Mode、工作流、subagent、文件系统、bash 或 Cordis 路径损坏时，已完成高级快照会失败，不会继续接受伪造的结果事件。 +- 当 TUI 事件映射或呈现损坏时，包快照会失败；它们不能代替组装应用的工具路径 transcript。 - TUI 视觉回归会产生便于阅读的单元格和样式 diff，而 JSONL fixture 会保留触发生产路径的确切模型分片。 -- 模拟器使用 xterm 的拟议缓冲区 API。升级 xterm 时必须重新运行并评审语义投影；终端特有行为仍需由 PTY 冒烟测试覆盖。 -- 预期输出有意固定指定尺寸下的换行与视口行为。预期布局变更使用无密钥刷新；模型流程变更使用录制模式，并同时评审 JSONL 与终端 diff。 +- 模拟器使用 xterm 的拟议缓冲区 API。升级 xterm 时必须重新运行并评审语义投影；终端特有行为仍需由交付该终端的部署所拥有的 PTY 冒烟测试覆盖。 +- 预期输出有意固定指定尺寸下的换行与视口行为。预期布局变更会更新并评审包级语义快照。 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 db80fbcfa9..341ea482c0 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 @@ -1,6 +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 -2026-06-20-generic-long-running-tool-runtime.md: 313d687b49da0d08b0ec321bcb655b642f7a5af3 -2026-06-20-generic-long-running-tool-runtime.zh.md: 6be129b7b16ff01d73dc94f7ce6d299ee2c10e55 +# 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: cb9d9487cd274696ae20dddab8c6888b4cf4b833 +2026-06-20-generic-long-running-tool-runtime.zh.md: 77538105ba2841479238045327de493c5a835b7f diff --git a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md index 313d687b49..cb9d9487cd 100644 --- a/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md +++ b/.agents/notes/implemented/architecture/2026-06-20-generic-long-running-tool-runtime.md @@ -93,7 +93,7 @@ The bash seam exposes `resolve`, `run`, and `start`. `start(spec)` returns a `Ba For background bash, `dsh-tool-bash` registers the calling agent as owner. Its hooks map `kill()` to cancellation, `done` to a completed or killed `TaskOutcome`, and `readOutput()` to the process's bounded incremental output plus spill and sandbox notices. Generic task tools own ids, status lines, listing, waiting, and completion notices. -For background subagents, `dsh-tool-subagent` creates a task-owned `AbortController` and begins provider startup inside the task starter. Cancellation aborts the same signal before or after provider readiness. `done` awaits both the child result and child disposal, maps completed output to a final result, maps abort to `killed`, and maps other stop reasons or infrastructure failures to `failed`. Intermediate child history remains in the child session and is not exposed through `readOutput()`. +For background subagents, `dsh-tool-subagent` creates a task-owned `AbortController` and begins provider startup inside the task starter. Cancellation aborts the same signal before or after provider publication. `done` awaits both the child result and child disposal, maps completed output to a final result, maps abort to `killed`, and maps other stop reasons or infrastructure failures to `failed`. Intermediate child history remains in the child session and is not exposed through `readOutput()`. ## Alternatives considered 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 6be129b7b1..77538105ba 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 @@ -93,7 +93,7 @@ bash seam 暴露 `resolve`、`run` 和 `start`。`start(spec)` 返回一个 `Bas 对于后台 bash，`dsh-tool-bash` 将调用方 agent 注册为所有者。其钩子将 `kill()` 映射为取消，将 `done` 映射为 completed 或 killed 的 `TaskOutcome`，并将 `readOutput()` 映射为进程的有界增量输出，以及溢出文件与沙箱通知。通用任务工具拥有 id、状态行、列表、等待和完成通知。 -对于后台 subagent，`dsh-tool-subagent` 创建由任务拥有的 `AbortController`，并在任务 starter 内启动提供方。无论提供方就绪前后，取消都会中止同一个 signal。`done` 同时等待子运行结果和子运行释放，将已完成输出映射为最终结果，将中止映射为 `killed`，并将其他停止原因或基础设施失败映射为 `failed`。中间子历史保留在子会话中，不通过 `readOutput()` 暴露。 +对于后台 subagent，`dsh-tool-subagent` 创建由任务拥有的 `AbortController`，并在任务 starter 内启动提供方。无论提供方发布前后，取消都会中止同一个 signal。`done` 同时等待子运行结果和子运行释放，将已完成输出映射为最终结果，将中止映射为 `killed`，并将其他停止原因或基础设施失败映射为 `failed`。中间子历史保留在子会话中，不通过 `readOutput()` 暴露。 ## 备选方案 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 8193e5e839..bf6f030683 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: 5c76ed5d754ea40f41dff78cb56ee7fc139a32b1 -2026-06-21-bounded-llm-request-recovery.zh.md: 1fa56f3fe0405cab663c2843d423a78d910170dd +2026-06-21-bounded-llm-request-recovery.md: 24725dcf300cf69e9cc72580d0c8afe937d4e2b9 +2026-06-21-bounded-llm-request-recovery.zh.md: 5f03a65b00be8d3349addce82e4f3faa2af1fe7e 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 5c76ed5d75..24725dcf30 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 @@ -84,7 +84,7 @@ Boundary tests prove termination at both actual transports. The hand-written ada 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. -If recovery is exhausted, the final failure is stored once on `turn/end.reason` with the structured facts. If transient recovery continues, `llm/retry` is the durable home for that attempt's failure and delay. 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. 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. ## Out of scope 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 1fa56f3fe0..5f03a65b00 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 @@ -84,7 +84,7 @@ agent-spine 演示组合包加载该插件，因此共享的 stdio/TUI、一次 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契约，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。 -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。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。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。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。 ## 不在范围内 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 67955d377d..cdee6ab259 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 @@ -1,6 +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 -2026-07-08-agent-scope-contexts.md: e4c076189a8e8a438b561232d3779ad1f6ab0d08 -2026-07-08-agent-scope-contexts.zh.md: 35e725e43d402b048daf12c3b4be384b3fd2d2ce +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md +2026-07-08-agent-scope-contexts.md: 5e09bdbcae1e57e6b65eb7d1720a6e7a7f758a9f +2026-07-08-agent-scope-contexts.zh.md: 4714045f28e0386a3a53b53437d063462e75a9f1 diff --git a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md index e4c076189a..5e09bdbcae 100644 --- a/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md +++ b/.agents/notes/implemented/architecture/2026-07-08-agent-scope-contexts.md @@ -108,11 +108,11 @@ A listener registered with `{ global: true }` deliberately bypasses contextual a ### Creation publishes last and disposal revokes last -`ctx.agents.create()` and `resume()` build an unpublished session, scope, agent, and driver. They await `setup`, admit the final session and agent entries, announce them in order, start the loop, and only then return a handle. +`ctx.agents.create()` and `resume()` build an unpublished session, scope, agent, and driver. They await `setup`, synchronously invoke its optional `AgentSetupCommit`, admit the final session and agent entries, announce them in order, start the loop, and only then return a handle. The commit lets mutable provisioning revalidate at the exact publication boundary after every setup await; a throw rolls the private transaction back before either identity is announced, while revocation after a successful commit is ordinary live teardown. An optional creation signal cancels work only while create or resume is pending. After the promise resolves, the returned `AgentHandle` owns explicit disposal. -If loading, setup, admission, or publication fails, the private transaction rolls back everything it prepared. Concurrent operations using the same caller-supplied live ID may both reach setup, but final registry entry admits only one; every loser rejects and cleans its private resources. Sequential reuse after awaited disposal remains valid. +If loading, setup, the optional setup commit, admission, or publication fails, the private transaction rolls back everything it prepared. Concurrent operations using the same caller-supplied live ID may both reach setup, but final registry entry admits only one; every loser rejects and cleans its private resources. Sequential reuse after awaited disposal remains valid. `AgentHandle.dispose()` reverses the boundary. It deactivates creation or driving, waits for synchronous publication to unwind, stops and drains the driver and final session flushes, detaches the agent and session, and finally disposes the scope. Repeated or racing disposal requests join one completion promise. @@ -122,12 +122,14 @@ The calling Cordis context and the concrete AgentLoop factory are structural co- flowchart TB request["Create or resume"] --> privateWorld["Build private session, scope, agent, and driver"] privateWorld --> setup["Await composition through agent.ctx"] - setup --> admission["Admit final session and agent entries"] + setup --> setupCommit["Commit optional mutable provisioning"] + setupCommit --> admission["Admit final session and agent entries"] admission --> publish["Announce lifecycle and start the driver"] publish --> live["Return AgentHandle"] privateWorld -->|"failure, cancellation, or owner loss"| rollback["Rollback private work"] setup -->|"failure, cancellation, or owner loss"| rollback + setupCommit -->|"revalidation failure or owner loss"| rollback admission -->|"duplicate or owner loss"| rollback publish -->|"listener failure or owner loss"| rollback live -->|"handle or owner disposal"| quiesce["Stop and drain work"] @@ -166,6 +168,6 @@ Parentage describes lifetime and conversation lineage, not a universal merge pol ## Consequences -Contributors use one familiar pattern: register shared behavior through a plugin context, register local behavior through `agent.ctx`, select the real agent on operations, and dispose the returned handle. Setup is atomic from an observer's perspective, and teardown preserves local behavior until work stops. +Contributors use one familiar pattern: register shared behavior through a plugin context, register local behavior through `agent.ctx`, select the real agent on operations, and dispose the returned handle. Setup and its optional publication commit are atomic from an observer's perspective, and teardown preserves local behavior until work stops. The cost is explicit subject selection, asynchronous programmatic creation, and service-specific scope adoption. Flat registration scope is intentionally not authority, and subagent composition controls remain a separate feature rather than hidden scope semantics. 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 35e725e43d..4714045f28 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 @@ -108,11 +108,11 @@ setup 接收一个完整的受信 Cordis 上下文，因此可以组合普通插 ### 创建最后发布，dispose 最后撤销 -`ctx.agents.create()` 和 `resume()` 构建未发布的会话、作用域、agent 和驱动器。它们等待 `setup`，准入最终的会话和 agent 条目，按序公告，启动循环，然后才返回 handle。 +`ctx.agents.create()` 和 `resume()` 构建未发布的会话、作用域、agent 和驱动器。它们等待 `setup`，同步调用其可选的 `AgentSetupCommit`，准入最终的会话和 agent 条目，按序公告，启动循环，然后才返回 handle。该提交操作让可变的配置状态在所有 setup 的 await 均结算后，于确切的发布边界重新校验；若其抛出异常，则会在公告任何一个身份前回滚私有事务，而成功提交后的撤销属于普通的实时拆卸。 可选的创建信号仅在创建或恢复挂起期间取消工作。promise resolve 后，返回的 `AgentHandle` 拥有显式 dispose 权。 -如果加载、setup、准入或发布失败，私有事务回滚其准备的一切。使用同一个调用方提供的存活 ID 的并发操作可能都到达 setup，但最终注册表条目只准入一个；每个失败者拒绝并清理其私有资源。在等待 dispose 完成后的顺序复用仍然有效。 +如果加载、setup、可选的 setup 提交、准入或发布失败，私有事务回滚其准备的一切。使用同一个调用方提供的存活 ID 的并发操作可能都到达 setup，但最终注册表条目只准入一个；每个失败者拒绝并清理其私有资源。在等待 dispose 完成后的顺序复用仍然有效。 `AgentHandle.dispose()` 反转边界。它停用创建或驱动，等待同步发布解除，停止并排空驱动器和最终会话刷写，分离 agent 和会话，最后 dispose 作用域。重复或竞争的 dispose 请求合并为一个完成 promise。 @@ -122,12 +122,14 @@ setup 接收一个完整的受信 Cordis 上下文，因此可以组合普通插 flowchart TB request["Create or resume"] --> privateWorld["Build private session, scope, agent, and driver"] privateWorld --> setup["Await composition through agent.ctx"] - setup --> admission["Admit final session and agent entries"] + setup --> setupCommit["Commit optional mutable provisioning"] + setupCommit --> admission["Admit final session and agent entries"] admission --> publish["Announce lifecycle and start the driver"] publish --> live["Return AgentHandle"] privateWorld -->|"failure, cancellation, or owner loss"| rollback["Rollback private work"] setup -->|"failure, cancellation, or owner loss"| rollback + setupCommit -->|"revalidation failure or owner loss"| rollback admission -->|"duplicate or owner loss"| rollback publish -->|"listener failure or owner loss"| rollback live -->|"handle or owner disposal"| quiesce["Stop and drain work"] @@ -166,6 +168,6 @@ agent 作用域组合的是受信的同进程注册。它不沙箱化插件、 ## 后果 -贡献者使用一种熟悉的模式：通过插件上下文注册共享行为，通过 `agent.ctx` 注册本地行为，在操作中选择真实 agent，dispose 返回的 handle。从观察者角度看 setup 是原子的，拆除则保留本地行为直到工作停止。 +贡献者使用一种熟悉的模式：通过插件上下文注册共享行为，通过 `agent.ctx` 注册本地行为，在操作中选择真实 agent，dispose 返回的 handle。从观察者角度看，setup 及其可选的发布提交是原子的，拆除则保留本地行为直到工作停止。 代价是显式的主体选择、异步的编程式创建，以及服务需要逐个采纳作用域。扁平注册作用域有意不等同于权限，subagent 组合控制作为独立功能存在，而非隐藏的作用域语义。 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 cbaedf3ab9..d05f034c0f 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 @@ -1,6 +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 -2026-07-12-agent-scope-runtime-design.md: 232fc02d66411b5ee8a21943795a3be4713bf238 -2026-07-12-agent-scope-runtime-design.zh.md: 39d558f8cde0183a3590d268aca36ea85e5f5c63 +# 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: d6b865977a76061784c88dbad089fa5963be8c7e +2026-07-12-agent-scope-runtime-design.zh.md: 5b6b9b1ca582d83a267a30f8f76e38ea87d52e9b diff --git a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md index 232fc02d66..d6b865977a 100644 --- a/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md +++ b/.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md @@ -260,19 +260,19 @@ Skill registry definitions and approval policies are readonly same-process contr Skill still validates external skill files and parsed provider output, routes catalogs through the calling agent's tool view, and disposes registrations exactly. Approval still resolves policy, observes cancellation, routes `approval/request` by `request.agent`, records the durable audit pair, and contains answerer and post-commit observer failures. -## Subagents: readiness is the start promise +## Subagents: publication is the start promise -Subagent startup has one ownership transfer. The provider owns partial resources until its start promise fulfills with a ready published run; the caller owns the returned run and must dispose it. +Subagent startup has one ownership transfer. The provider owns unpublished resources until its start promise fulfills with a published run; the caller owns the returned run and must dispose it. ### The service contract has one cancellation channel -`SubagentProvider.start()` and `SubagentService.start()` return `Promise`. The promise fulfills only after the backend has established the child it promises, so callers and `subagent/start` observers never need a second `run.started` readiness promise. +`SubagentProvider.start()` and `SubagentService.start()` return `Promise`. The promise fulfills after the backend crosses its publication boundary, so callers and `subagent/start` observers never need a second `run.started` promise. Provider work that fails before publication rejects `start()`; prompt, turn, cancellation, and infrastructure outcomes after publication settle through `SubagentRun.result` without hiding the child id, as required by the [durable catalog decision](../feature/2026-07-22-durable-subagent-catalog-and-list-agents.md). -`SubagentStartRequest.signal` is required. Aborting it requests cancellation during startup and after readiness. `SubagentRun.dispose()` also requests cancellation and awaits quiescence. There is no separate public `run.cancel()` channel. +`SubagentStartRequest.signal` is required. Aborting it requests cancellation during startup and across the published run's remaining readiness or turn work. `SubagentRun.dispose()` also requests cancellation and awaits quiescence. There is no separate public `run.cancel()` channel. -Optional `sendMessage()` supports a live backend that can accept steering. Optional `resume()` returns `Promise` because the resumed child has the same asynchronous readiness boundary. +Continuable conversations use their separate creation and follow-up operations and have no `SubagentRun`; their manager owns each resident `AgentHandle`. -The service validates provider capabilities and request semantics before calling the provider. A provider rejection cleans any partial resources before the rejection escapes and emits no `subagent/start`/`subagent/end` pair. After fulfillment, the service attaches result observation, emits scoped start, and returns the run. Provider removal prevents later starts but does not revoke a run already accepted by the provider. +The service validates provider capabilities and request semantics before calling the provider. A provider rejection cleans unpublished resources before the rejection escapes and emits no `subagent/start`/`subagent/end` pair. After fulfillment, the service attaches result observation, emits scoped start, and returns the run; a post-publication result rejection closes that pair. Provider removal prevents later starts but does not revoke a run already accepted by the provider. ### In-process providers reuse the core transaction @@ -318,7 +318,7 @@ The design is enforced at types, runtime escape points, generated contracts, and ### Types make the ordinary path hard to misuse -Readonly contracts describe borrowed same-process values. `Scoped` marks event receivers, `agentEvents()` fuses carrier and subject, tool inputs omit registry-owned tokens, and subagent async return types expose readiness directly. +Readonly contracts describe borrowed same-process values. `Scoped` marks event receivers, `agentEvents()` fuses carrier and subject, tool inputs omit registry-owned tokens, and subagent async return types expose publication and settlement directly. TypeScript cannot govern JavaScript casts, direct Cordis dispatch, process messages, or durable files, so runtime enforcement remains at those escape points. @@ -356,7 +356,7 @@ Parallel sentinels can all mirror whether one operation is live. One transaction ### Keep synchronous subagent start plus `run.started` -This splits provider acceptance from readiness and forces every consumer to register a partial run, attach result observation, await readiness, and clean up readiness failure. An async start promise makes provider-to-caller ownership transfer the readiness boundary itself. +This splits provider acceptance from publication and forces every consumer to register a partial run, attach result observation, await publication, and clean up publication failure. An async start promise keeps provider-to-caller ownership transfer at publication; the existing result promise owns any remaining readiness instead of adding another lifecycle promise. ### Restore selected prompt or tool contributions after assembly @@ -378,7 +378,7 @@ The implementation is smaller and its proof follows the same shape as its owners - Durable, queued, model, worker, process, and wire values are owned at their real boundary; typed same-process values follow readonly contracts. - ToolRegistry's presentation, lookup, and execution resolve the same live view before expert assembly transforms, and committed results have one immutable observation point. - Registry contributions are deterministic inputs, while the trusted assembly waterfall owns the final model-visible composition. -- Subagent start returns only a ready run, required signals cancel pending or live work, and disposal reaches the backend's quiescence contract. +- Subagent start returns only a published run, required signals cancel pending or live work, and disposal reaches the backend's quiescence contract. - Worker/process result precedence and cleanup remain correct under death, late messages, and bounded teardown. ### Costs and limits 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 39d558f8cd..5b6b9b1ca5 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 @@ -260,19 +260,19 @@ Skill 注册表定义和 approval 策略是 readonly 的同进程契约。它们 Skill 仍然验证外部 skill 文件和解析的提供方输出，通过调用 agent 的工具视图路由目录，并精确 dispose 注册。Approval 仍然解析策略、观察取消、按 `request.agent` 路由 `approval/request`、记录持久化审计对，并隔离应答者和提交后观察者的失败。 -## Subagent：就绪即 start promise +## Subagent：发布即 start promise -Subagent 启动有一次所有权转移。提供方拥有部分资源直到其 start promise 以一个就绪的已发布 run 兑现；调用方拥有返回的 run 并必须 dispose 它。 +Subagent 启动有一次所有权转移。提供方拥有未发布资源，直到其 start promise 以一个已发布 run 兑现；调用方拥有返回的 run 并必须 dispose 它。 ### 服务契约有一个取消通道 -`SubagentProvider.start()` 和 `SubagentService.start()` 返回 `Promise`。Promise 仅在后端建立了它所承诺的子级之后才兑现，因此调用方和 `subagent/start` 观察者从不需要第二个 `run.started` 就绪 promise。 +`SubagentProvider.start()` 和 `SubagentService.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)所要求的契约。 -`SubagentStartRequest.signal` 是必需的。中止它会在启动期间和就绪之后请求取消。`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。 +`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。 -可选的 `sendMessage()` 支持能接受 steering 的活跃后端。可选的 `resume()` 返回 `Promise`，因为恢复的子级有相同的异步就绪边界。 +可继续对话使用各自独立的创建和后续操作，并且没有 `SubagentRun`；其管理器拥有每个驻留中的 `AgentHandle`。 -服务在调用提供方之前验证提供方能力和请求语义。提供方拒绝在拒绝逃出之前清理所有部分资源，且不发射 `subagent/start`/`subagent/end` 对。兑现之后，服务附加结果观察、发射作用域 start 并返回 run。提供方移除阻止后续 start，但不撤销提供方已接受的 run。 +服务在调用提供方之前验证提供方能力和请求语义。提供方 rejection 在逃出之前清理未发布资源，且不发射 `subagent/start`/`subagent/end` 对。兑现之后，服务附加结果观察、发射作用域 start 并返回 run；发布后的结果 rejection 会结束该事件对。提供方移除会阻止后续 start，但不撤销提供方已接受的 run。 ### 进程内提供方复用核心事务 @@ -318,7 +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 ### 类型使常规路径难以误用 -Readonly 契约描述借用的同进程值。`Scoped` 标记事件接收器，`agentEvents()` 融合载体和主体，工具输入省略注册表拥有的 token，subagent 异步返回类型直接暴露就绪性。 +Readonly 契约描述借用的同进程值。`Scoped` 标记事件接收器，`agentEvents()` 融合载体和主体，工具输入省略注册表拥有的 token，subagent 异步返回类型直接暴露发布与结算。 TypeScript 无法管控 JavaScript 强制转换、直接 Cordis dispatch、进程消息或持久化文件，因此运行时强制保留在这些逃逸点。 @@ -356,7 +356,7 @@ TypeScript 无法管控 JavaScript 强制转换、直接 Cordis dispatch、进 ### 保留同步 subagent start 加 `run.started` -这将提供方接受与就绪分离，迫使每个消费方注册部分 run、附加结果观察、等待就绪并清理就绪失败。异步 start promise 使提供方到调用方的所有权转移本身成为就绪边界。 +这将提供方接受与发布分离，迫使每个消费方注册部分 run、附加结果观察、等待发布并清理发布失败。异步 start promise 将提供方到调用方的所有权转移保持在发布边界；现有的结果 promise 负责所有剩余就绪工作，无需增加另一个生命周期 promise。 ### 在 assembly 之后恢复选定的提示词或工具贡献 @@ -378,7 +378,7 @@ Worker 消息、进程死亡和持久化输入确实跨越所有权和序列化 - 持久化、队列、模型、worker、进程和协议格式的值在其真实边界处被拥有；类型化的同进程值遵循 readonly 契约。 - ToolRegistry 的展示、查找和执行在专家 assembly 变换之前解析相同的活跃视图，已提交的结果有一个不可变的观察点。 - 注册表贡献是确定性输入，而可信的 assembly waterfall 拥有最终的模型可见组合。 -- Subagent start 仅返回就绪的 run，必需的 signal 取消待定或活跃的工作，dispose 到达后端的完全停稳契约。 +- Subagent start 仅返回已发布的 run，必需的 signal 取消待定或活跃的工作，dispose 到达后端的完全停稳契约。 - Worker/进程结果优先级和清理在死亡、迟到消息和有界拆除下保持正确。 ### 代价与局限 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 e603129715..ca90cebb0e 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: b7081591cf7e5e3c586c74c5a71b4317376135cb -2026-07-19-gui-layering-and-rpc-protocol.zh.md: 89557182ca7781f4fb59b8daf866aaca96cf20ee +2026-07-19-gui-layering-and-rpc-protocol.md: 7ad2a2403eb9962b369b016070e8ca378ed55c60 +2026-07-19-gui-layering-and-rpc-protocol.zh.md: 90850c469f1444e7f6cd105551e6cc21920e91d9 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 b7081591cf..7ad2a2403e 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 @@ -184,7 +184,7 @@ The remaining frame types are not re-copied here; the full unions are `MuxFrame` - **History = event replay**: one fold (client side); history pagination and live increments share one code path; the server maintains no second materialized-snapshot system. History **page boundaries align to message boundaries** (never cut mid-message; chunks group with their finalized message), and the tail page includes the in-flight partial's chunks. - **Prompt correlation**: the prompt's rpcId rides MessageSource (`'user-rpc'`) into the `user/message` event; the client uses it to promote the optimistic echo. - **Reconnect = rebuild**: no resume cursor (`mux`'s `since` signature is a reserved seat, ignored if passed); on disconnect reopen the stream + refetch history; compare `subscribed.lastSeq` with the history tail seq and backfill once if there is a seam. -- **Cold sessions resume implicitly**: when `history`/`prompt` hits an unattached session the impl auto-resumes, deduplicating concurrent triggers with an in-flight table; attachment status is not exposed to clients (`running` already covers it). +- **Cold session handling follows ownership**: `session.history` and the source read for `session.fork` inspect persistence without an Agent, while Agent-bound ordinary-session methods such as `prompt` resume through a deduplicated in-flight table. Session-backed subagents reject that generic resume path, and attachment status is not exposed to clients (`running` already covers it). - **Approvals/questions**: the requested frame mints a stable rpcId on acceptance; first answer wins, and the host's in-memory pending table (keyed by rpcId) is the only referee; after a mux reopen, still-pending requested frames replay after the subscribed frame (rpcId reused verbatim — refresh recovery). The audit events `approval/asked`/`decided` continue through the durable log — frames = the live control plane, events = the durable audit. **Status**: the contract and frame types are shipped; the host-side pending table/wire answerer is unimplemented (`respond` in `api-proxy.ts` is a stub, always `not-pending`); PendingCard v1 is display-only. - **No protocol version**: client and host release bound together; `host.describe` has no protocolVersion field; introduce one when an independently released client appears. - **Reserved-seam discipline**: the map holds only implemented methods; an unknown method fails loud at envelope parse (`bad-request`) — no not-implemented fallback code. The reservation list (implementing = copy the signature into the domain interface + add the map row + add the schema pair): `session.fork`, `prompt.mode` gaining `'inject'`, `task.list`, `host.listModels`, describe gaining `hostInstanceId`. (`session.rename` graduated from this list: it appends a user-source `session/title` event.) 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 89557182ca..90850c469f 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 @@ -182,7 +182,7 @@ export type ResponseValue = - **历史 = 事件重放**：一套 fold（client 侧），历史分页与 live 增量同一条代码路径；server 不做物化快照第二套。history **页边界对齐消息边界**（绝不从消息中间截断；chunk 随定稿消息归组），尾页含进行中 partial 的 chunk。 - **prompt 关联**：prompt 的 rpcId 经 MessageSource（`'user-rpc'`）透传进 `user/message` 事件，client 以此把乐观回显转正。 - **重连 = 重建**：不做续传 cursor（`mux` 的 `since` 签名留座、传了忽略）；断线重开流 + 重拉 history；`subscribed.lastSeq` 与 history 尾 seq 比对，有缝再补拉一次。 -- **冷 session 隐式 resume**：`history`/`prompt` 命中未 attach 的 session 时 impl 自动 resume，并发触发用在途表去重；attach 与否不对客暴露（`running` 已覆盖）。 +- **冷会话处理遵循所有权**：`session.history` 与 `session.fork` 的源端读取会在不获取 Agent 的情况下检查持久化存储，而绑定到 Agent 的普通会话方法（如 `prompt`）则通过在途表去重后恢复会话。由会话支撑的 subagent 会拒绝这条通用恢复路径，且附加状态不对客户端暴露（`running` 已经覆盖）。 - **审批/问答**：requested 帧受理时 mint 稳定 rpcId；先到先赢，host 内存 pending 表（keyed by rpcId）是唯一裁判；mux 重开后在 subscribed 帧后重放仍 pending 的 requested 帧（rpcId 原样复用，刷新恢复）。审计事件 `approval/asked`/`decided` 照旧走 durable 日志——帧=live 控制面，事件=durable 审计。**现状**：契约与帧类型已 shipped，host 侧 pending 表/wire answerer 未实现（`api-proxy.ts` 的 `respond` 是 stub，恒回 `not-pending`）；PendingCard v1 只展示。 - **不设协议版本**：client 与 host 绑定发布，`host.describe` 无 protocolVersion 字段；出现独立发布的 client 时再引入。 - **预留接缝纪律**：map 只含已实现方法，未知 method 在信封 parse 即 fail loud（`bad-request`），不设 not-implemented 兜底码。预留清单（实现时把签名抄进域接口+map 加行+schema 加对即升格）：`session.fork`、`prompt.mode` 加 `'inject'`、`task.list`、`host.listModels`、describe 加 `hostInstanceId`。（`session.rename` 已从本清单毕业：追加 user 来源的 `session/title` 事件。） 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 e4b0447cdd..61e6a93e23 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 @@ -1,6 +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 -2026-07-19-gui-web-client-architecture.md: cfc2a7e62358e6282148b2d024ef3b162a903642 -2026-07-19-gui-web-client-architecture.zh.md: b5b082c25f664cfcb0ddd3fcc6c4cd3d58472218 +# 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: b1f777172774f1cf8fef4d9494f15b38064d0c73 +2026-07-19-gui-web-client-architecture.zh.md: e43151b7d5ff096d574c786e3aae107523d22c96 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 cfc2a7e623..b1f7771727 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 @@ -44,13 +44,13 @@ Implementation homes: registry core and the props-share types in `packages/clien A service is a plugin's only API surface toward other plugins (UI components and injection faces are not APIs; a plugin nobody calls mounts no service — ui-trajectory is the minimal-plugin exemplar: no ctx service, only view-slot registrations). The roster: `ctx.connection` (api client + stream handles), `ctx.slots` (registry wrapper emitting `slots/changed`, render entry, renderer install seam), `ctx.sessions` (list store, current-session state, scope tree), `ctx.loader`, `ctx.theme`, `ctx.i18n`, `ctx.layout` (cross-plugin view navigation), `ctx.conversation` (send/cancel/startSession). Viewing state that used to live in service stores (panel widths, selection, drafts) now lives in entry-declared stores per the [slot system standard](2026-07-22-slot-type-chain-implementation.md). -There is no registration model besides slots — the former view and tool rings both dissolved into it. Conversation views are entries of the `'conversation.view'` list slot ui-conversation declares, tab metadata rides the registration options (`id`/`order`/`label`), and per-view chrome lives inside the view components themselves. A tool row is a keyed child slot each view declares for itself — today `'conversation.chat.toolview'` (keyed/session), declared by the chat entry's `children` table; the key space is runtime-open (SlotMap declares slots, never keys), which is what the tool ring's open tool-name set required. The render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback`; the owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails`), and `ToolRowProps` composes it with the session standard kit for registrant components. Registrants are plain plugins with zero dedicated machinery: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`, with `inject: ['slots', 'conversation']` as the load-order seam (the conversation service being present guarantees the slot is declared). Session-dimension differentiation happens inside the component — `useSessions` reading `parentId` — not in registry predicates; interaction drafts and other row state ride the ordinary store seat. Trajectory/waterfall get same-shaped slots (names fixed by the slot-naming discipline `..`, one shared owner type) that land with their own row render sites — RendersCheck rejects a declaration nobody renders, so the two slots cannot be declared early. +There is no registration model besides slots — the former view and tool rings both dissolved into it. Conversation views are entries of the `'conversation.view'` list slot ui-conversation declares, tab metadata rides the registration options (`id`/`order`/`label`), and per-view chrome lives inside the view components themselves. A tool row is a keyed child slot each view declares for itself — today `'conversation.chat.toolview'` (keyed/session), declared by the chat entry's `children` table; the key space is runtime-open (SlotMap declares slots, never keys), which is what the tool ring's open tool-name set required. The render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback`; the owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails`), and `ToolRowProps` composes it with the session standard kit for registrant components. Registrants are plain plugins with zero dedicated machinery: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`, with `inject: ['slots', 'conversation']` as the load-order seam (the conversation service being present guarantees the slot is declared). Interaction drafts and other row state ride the ordinary store seat. Trajectory/waterfall get same-shaped slots (names fixed by the slot-naming discipline `..`, one shared owner type) that land with their own row render sites — RendersCheck rejects a declaration nobody renders, so the two slots cannot be declared early. **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/`) -Frames enter, snapshots exit, the fold sits between — React-free (zero React imports, grep-assertable): +Frames enter, snapshots exit, the projection sits between — React-free (zero React imports, grep-assertable): ``` mux/host 帧（ConnectionController 泵入，sinks 注入） @@ -62,17 +62,17 @@ SessionManager.handleMuxEnvelope / handleHostEnvelope Session.handleMuxEnvelope ──► events 窗口（seq 连续升序） │ │ 定稿事件 │ chunk │ ▼ ▼ - │ FoldAdapter PartialAccumulator + │ TranscriptAdapter PartialAccumulator │ （→ nodes） （→ partial） ▼ Notifier 微任务合批 ──► ConversationSnapshot 缓存 ──uSES──► 组件 ``` -- **Session** (session.ts): lazily built, resident — once created it keeps eating frames in the background, so switching away and back renders instantly. Operations: `prompt`/`cancel` (RPC passthrough; failures land in the snapshot's `promptError`), `open` (pull the tail history page, idempotent), `loadOlder` (upward paging, reentry-guarded), `resync` (reconnect = clear the window and rerun open). Subscription: `subscribe`/`getSnapshot` (always the cached reference) — `implements ObservableSnapshot`, with `useSelector = bindSnapshotSelector(this)` attached at construction, so a Session is directly a uSES source. Frame dispatch is one switch: `session/event` frames dedup by seq (the only dedup key), buffer while open is in flight, otherwise append + incremental fold; open/stitch merges the live buffer by seq and backfills once if `subscribed.lastSeq` outruns the window tail. -- **ConversationSnapshot** (conversation.ts): the immutable snapshot contract — `nodes` (folded, surface-ordered), `partial`, `runningCalls`, `pending`, `running`, `removed`, `openState`, `hasMore`, `promptError` and kin. **Reference discipline** (the premise of memo and uSES): the top-level object is fresh on every change; the nodes array is rebuilt but element references come from the cache; unchanged substructures reuse the previous snapshot's references. +- **Session** (session.ts): lazily built, resident — once created it keeps eating frames in the background, so switching away and back renders instantly. Operations: `prompt`/`cancel` (RPC passthrough; failures land in the snapshot's `promptError`), `open` (pull the tail history page, idempotent), `loadOlder` (upward paging, reentry-guarded), `resync` (reconnect = clear the window and rerun open). Subscription: `subscribe`/`getSnapshot` (always the cached reference) — `implements ObservableSnapshot`, with `useSelector = bindSnapshotSelector(this)` attached at construction, so a Session is directly a uSES source. Frame dispatch is one switch: `session/event` frames dedup by seq (the only dedup key), buffer while open is in flight, otherwise append + incremental projection; open/stitch merges the live buffer by seq and backfills once if `subscribed.lastSeq` outruns the window tail. +- **ConversationSnapshot** (conversation.ts): the immutable snapshot contract — `nodes` (the human transcript, log-ordered), `partial`, `runningCalls`, `pending`, `running`, `removed`, `openState`, `hasMore`, `promptError` and kin. **Reference discipline** (the premise of memo and uSES): the top-level object is fresh on every change; an unchanged nodes projection keeps the same array reference, while a changed flow returns a new array that reuses unchanged element references; unchanged substructures reuse the previous snapshot's references. - **SessionManager** (manager.ts): instance cluster + frame entry + the session list. sessionId-bearing frames go only to existing instances (a mux broadcast must not instantiate every session); approval/question `requested` frames are the exception — they never land in history, so they buffer in `pendingBuffers` and replay on instantiation. - **Notifier** (notifier.ts): two channels chosen by change source. `markDirty()` (default; frame-driven changes always) batches per microtask — N changes, one notification, one re-render; the flush rebuilds the snapshot cache before notifying. `notifyNow()` (only direct echoes of user gestures) rebuilds and notifies in the same tick — controlled inputs roll the DOM back and jump the caret if their echo defers to a microtask. Frame-driven code using notifyNow collapses batching back to per-frame renders; banned. -- **FoldAdapter / PartialAccumulator**: the fold reuses the core SurfaceManager (`@deepseek-ai/dsh-session/surface`), padding sentinel events so a paged window starting at seq > 0 satisfies the core's `seq === index` assertion; a cross-window replace degrades to a tolerant linear scan and sets `foldDegraded`. Chunks stay out of the fold entirely (O(1) skip): the accumulator folds StreamChunks into `AssistantBlock[]`, a delta swapping only that block's reference, and the finalizing message discards the accumulator in the same batch (no flicker on promotion). Cost model: one chunk = one string concatenation + a dirty mark; an unsubscribed Session under a frame storm costs only the mark. +- **TranscriptAdapter / PartialAccumulator**: the transcript is the append-origin surface projected in log order (`isAppendSurfaceEvent` from `@deepseek-ai/dsh-session/surface`) plus one marker per landed compaction checkpoint — never the model surface, which shadows replaced ranges and would erase conversation the reader already saw. Node order is seq-monotonic by construction, so there is no core `seq === index` assertion to satisfy and no degradation branch. Chunks contribute no node (O(1) skip): the accumulator folds StreamChunks into `AssistantBlock[]`, a delta swapping only that block's reference, and the finalizing message discards the accumulator in the same batch (no flicker on promotion). Cost model: one chunk = one string concatenation + a dirty mark; an unsubscribed Session under a frame storm costs only the mark. - **ConnectionController** (in `packages/client/connection`): opens the mux/host streams, pumps with for-await, reconnects with exponential backoff (500ms doubling to 10s, jitter, unlimited) behind a generation fence; sinks are injected one-way (the Controller does not know Session). Reconnect = rebuild: `onConnected` → list refresh + per-open-session resync. The object layer faces only `IApiClient`; the Web carriage (HTTP POST for the two client→server quadrants, SSE for the two server→client) and the client class family are the layering RFC's territory. ## The React face (`packages/client/web-react`) 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 b5b082c25f..e43151b7d5 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 @@ -44,7 +44,7 @@ slot 体系有自己的 RFC——[slot 体系标准](2026-07-22-slot-type-chain- 服务是插件对其他插件的唯一 API 面（UI 组件与注入面都不是 API；无人调用的插件不挂服务——ui-trajectory 即最小插件样板：无 ctx 服务，只做视图坑注册）。名册：`ctx.connection`（api client + 流句柄）、`ctx.slots`（注册表包装层，发 `slots/changed`，渲染入口，渲染器安装缝）、`ctx.sessions`（列表 store、当前会话状态、scope 树）、`ctx.loader`、`ctx.theme`、`ctx.i18n`、`ctx.layout`（跨插件视图导航）、`ctx.conversation`（send/cancel/startSession）。过去住在服务 store 里的观看态（面板宽、选中、草稿）现按 [slot 体系标准](2026-07-22-slot-type-chain-implementation.md) 住 entry 声明的 store。 -slot 之外不存在第二种注册模型——原视图环与工具环都已溶解进来。会话视图即 ui-conversation 声明的 `'conversation.view'` list 坑的 entry，tab 元数据随注册 options（`id`/`order`/`label`）走，per-view chrome 住视图组件自身。工具行是各视图自己声明的 keyed 子槽——今天是 `'conversation.chat.toolview'`（keyed/session），由 chat 条目的 `children` 表声明；key 空间运行时开放（SlotMap 声明槽、从不声明 key），这正是工具环「tool 名开放集」的原需求。渲染点逐行以 `entryKey: toolName` 分发、以 `GenericToolCard` 作调用点 `fallback`；owner 载荷是统一的 `ToolRowOwnerProps`（`callId`/`toolName`/`block`/`openDetails`），`ToolRowProps` 把它与 session 标配 kit 预组合供注册方组件取用。注册方就是普通插件、零专用设施：`ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`，以 `inject: ['slots', 'conversation']` 作加载序缝（conversation 服务在场即保证槽已声明）。会话维差异化在组件内完成——`useSessions` 读 `parentId`——不走注册表谓词；交互草稿等行内状态走普通 store 席位。trajectory/waterfall 得同形槽（槽名按槽名纪律 `<域>.<条目>.<孔位>` 已定死，共用一张 owner 类型），随各自的行渲染点落地——RendersCheck 拒绝无人渲染的声明，两槽无法提前声明。 +slot 之外不存在第二种注册模型——原视图环与工具环都已溶解进来。会话视图即 ui-conversation 声明的 `'conversation.view'` list 坑的 entry，tab 元数据随注册 options（`id`/`order`/`label`）走，per-view chrome 住视图组件自身。工具行是各视图自己声明的 keyed 子槽——今天是 `'conversation.chat.toolview'`（keyed/session），由 chat 条目的 `children` 表声明；key 空间运行时开放（SlotMap 声明槽、从不声明 key），这正是工具环「tool 名开放集」的原需求。渲染点逐行以 `entryKey: toolName` 分发、以 `GenericToolCard` 作调用点 `fallback`；owner 载荷是统一的 `ToolRowOwnerProps`（`callId`/`toolName`/`block`/`openDetails`），`ToolRowProps` 把它与 session 标配 kit 预组合供注册方组件取用。注册方就是普通插件、零专用设施：`ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`，以 `inject: ['slots', 'conversation']` 作加载序缝（conversation 服务在场即保证槽已声明）。交互草稿等行内状态走普通 store 席位。trajectory/waterfall 得同形槽（槽名按槽名纪律 `<域>.<条目>.<孔位>` 已定死，共用一张 owner 类型），随各自的行渲染点落地——RendersCheck 拒绝无人渲染的声明，两槽无法提前声明。 **scope 寻址**与 host 侧 agent scope 惯例同构：服务是 root 单例，方法不收 sessionId——它们读调用方 ctx 上的 scope 标（`scopeOf(ctx)`）。在会话 scope 内，`ctx.conversation.send('hi', 'queue')` 自动打到该会话；跨会话调用换 ctx 定向（`ctx.sessions.scope(id)!.conversation.send(...)`）；从 root ctx 直接调 scoped 方法即 throw。client 会话 scope 的铸造方式与 host agent scope 相同（no-op 插件 fiber + scope 键 extend），首次观看时惰性建，只有会话被移除且无人观看才拆——仅 host 会话死亡不拆 scope（冻结为只读视窗）。 @@ -62,17 +62,17 @@ SessionManager.handleMuxEnvelope / handleHostEnvelope Session.handleMuxEnvelope ──► events 窗口（seq 连续升序） │ │ 定稿事件 │ chunk │ ▼ ▼ - │ FoldAdapter PartialAccumulator + │ TranscriptAdapter PartialAccumulator │ （→ nodes） （→ partial） ▼ Notifier 微任务合批 ──► ConversationSnapshot 缓存 ──uSES──► 组件 ``` -- **Session**（session.ts）：懒建、常驻——建成后在后台持续吃帧，切走切回秒显。操作面：`prompt`/`cancel`（RPC 透传；失败落进快照的 `promptError`）、`open`（拉尾页 history，幂等）、`loadOlder`（向上翻页，防重入）、`resync`（重连 = 清窗口重跑 open）。订阅面：`subscribe`/`getSnapshot`（恒返缓存引用）——`implements ObservableSnapshot`，构造时挂 `useSelector = bindSnapshotSelector(this)`，Session 本身就是 uSES 源。帧分发是一个 switch：`session/event` 帧按 seq 去重（唯一去重键），open 在途时缓冲，否则追加 + 增量 fold；open/缝合按 seq 合并 live 缓冲并去重，`subscribed.lastSeq` 超出窗口尾则回补一次。 -- **ConversationSnapshot**（conversation.ts）：不可变快照契约——`nodes`（fold 产物，surface 序）、`partial`、`runningCalls`、`pending`、`running`、`removed`、`openState`、`hasMore`、`promptError` 等。**引用纪律**（memo 与 uSES 的前提）：顶层对象每变必新；nodes 数组重建但元素引用来自缓存；未变的子结构复用上一快照的引用。 +- **Session**（session.ts）：懒建、常驻——建成后在后台持续吃帧，切走切回秒显。操作面：`prompt`/`cancel`（RPC 透传；失败落进快照的 `promptError`）、`open`（拉尾页 history，幂等）、`loadOlder`（向上翻页，防重入）、`resync`（重连 = 清窗口重跑 open）。订阅面：`subscribe`/`getSnapshot`（恒返缓存引用）——`implements ObservableSnapshot`，构造时挂 `useSelector = bindSnapshotSelector(this)`，Session 本身就是 uSES 源。帧分发是一个 switch：`session/event` 帧按 seq 去重（唯一去重键），open 在途时缓冲，否则追加 + 增量投影；open/缝合按 seq 合并 live 缓冲并去重，`subscribed.lastSeq` 超出窗口尾则回补一次。 +- **ConversationSnapshot**（conversation.ts）：不可变快照契约——`nodes`（人类对话记录，日志序）、`partial`、`runningCalls`、`pending`、`running`、`removed`、`openState`、`hasMore`、`promptError` 等。**引用纪律**（memo 与 uSES 的前提）：顶层对象每变必新；未变化的 nodes 投影保持同一数组引用，消息流变化时返回新数组并复用未变化的元素引用；未变的子结构复用上一快照的引用。 - **SessionManager**（manager.ts）：实例簇 + 帧总入口 + 会话列表。带 sessionId 的帧只投已存在实例（mux 广播不得把每个会话都实例化）；例外是审批/问答 `requested` 帧——它们不落 history、open 无法回补，故缓冲进 `pendingBuffers`，实例化时回放。 - **Notifier**（notifier.ts）：两条通知通道，按变更来源取用。`markDirty()`（默认；帧驱动一律用它）按微任务合批——N 次变更、一次通知、一次重渲染；flush 先重建快照缓存再通知。`notifyNow()`（仅用户手势的直接回响）同 tick 重建并通知——受控输入的回响若延到微任务，DOM 会回滚、光标跳尾。帧驱动代码用 notifyNow 会让合批塌回逐帧渲染；禁。 -- **FoldAdapter / PartialAccumulator**：fold 复用核心 SurfaceManager（`@deepseek-ai/dsh-session/surface`），垫哨兵事件使 seq > 0 起头的分页窗口满足核心的 `seq === index` 断言；跨窗口 replace 时降级为容错线性扫描并置 `foldDegraded`。分片完全不进 fold（O(1) 跳过）：累积器把 StreamChunk 折叠成 `AssistantBlock[]`，一次增量只换该块引用；定稿消息到达即在同一批内弃掉累积器（提升无闪烁）。成本模型：一个分片 = 一次字符串拼接 + 一个脏标记；帧风暴下未订阅的 Session 只花那个标记。 +- **TranscriptAdapter / PartialAccumulator**：对话记录是按日志顺序投影的 append 来源 surface（`@deepseek-ai/dsh-session/surface` 的 `isAppendSurfaceEvent`），外加每次落地的压缩检查点一个标记——绝不用模型 surface，后者遮蔽被替换的范围，会抹掉读者已经看过的对话。节点顺序天然按 seq 单调，因此既无核心 `seq === index` 断言需要满足，也没有降级分支。分片不贡献任何节点（O(1) 跳过）：累积器把 StreamChunk 折叠成 `AssistantBlock[]`，一次增量只换该块引用；定稿消息到达即在同一批内弃掉累积器（提升无闪烁）。成本模型：一个分片 = 一次字符串拼接 + 一个脏标记；帧风暴下未订阅的 Session 只花那个标记。 - **ConnectionController**（在 `packages/client/connection`）：开 mux/host 双流、for-await 泵入，代际围栏之内指数退避重连（500ms 翻倍至 10s 封顶、抖动、无限重试）；sinks 单向注入（Controller 不认识 Session）。重连 = 重建：`onConnected` → 列表刷新 + 各已打开会话 resync。对象层只面向 `IApiClient`；Web 承载（HTTP POST 载两个 client→server 象限、SSE 载两个 server→client 象限）与客户端类族归分层 RFC 属地。 ## React 面（`packages/client/web-react`） diff --git a/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.i18n.yaml index a3e8c3ad8a..3c005a6deb 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.i18n.yaml @@ -1,6 +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 -2026-07-19-package-owned-invariant-service.md: 2443a8f7d04b96f51bb798130078a7457f78b2a1 -2026-07-19-package-owned-invariant-service.zh.md: 3c71d3b7f99a507d4c0236b7ef6dc0794814cdc8 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.md +2026-07-19-package-owned-invariant-service.md: e32efe9f6b3ce6b782c61db56d928e87c160dc9a +2026-07-19-package-owned-invariant-service.zh.md: 60edaa3f6009acc516017683232ca0c07f64ec0d diff --git a/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.md b/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.md index 2443a8f7d0..e32efe9f6b 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.md +++ b/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.md @@ -8,7 +8,7 @@ English | [中文](2026-07-19-package-owned-invariant-service.zh.md) Runtime invariant checks span session traces, agent state, scoped dispatch, and request reconstruction. Putting all checks in one diagnostics package makes that package import product vocabularies from unrelated domains, centralizes tests away from their owners, and requires the central package to change whenever a product package adds or removes a check. -Deployments also need more than presence or absence of one plugin. A standard composition should carry the known invariant contributions while permitting a global off switch and package-selective diagnostics. Selection must remain stable when a package loads later or reloads under HMR, and disabled contributions must not allow two plugins to claim the same package name silently. +Deployments that opt into diagnostics need more than presence or absence of one plugin. Such a composition carries the known invariant contributions while permitting a global off switch and package-selective diagnostics. Selection must remain stable when a package loads later or reloads under HMR, and disabled contributions must not allow two plugins to claim the same package name silently. Package ownership must also be exhaustive. Without a mechanical repository rule, a new package can omit the companion, dependency, or publication wiring and remain invisible to diagnostics until a maintainer notices the gap. @@ -72,9 +72,9 @@ These four owners supplied the initial stateful checks. The follow-up runtime-co The generated scoped-event subject resolver lives in `dsh-scope`, beside the contract and invariant that consume it. `gen-scoped-events` uses the root TypeScript Program to enumerate `this: Scoped` declarations, infer routing-key types from real `scopeTarget(base, key)` calls, and require one unambiguous payload subject or an explicit unsupported marker. The committed runtime map imports no event-owner package, so semantic completeness does not expand either the service or scope package's runtime closure. -### Standard composition and SDK output +### Example composition and SDK output -The standard agent spine mounts the service and all four stateful companion subpaths, forwarding `enabled`, `package_allowlist`, and `package_blocklist` to the service. Generated SDK Cordis composition emits the same entries. A subpath entry adds its installable root npm package rather than treating the subpath as a package name. +The example agent spine mounts the service and all four stateful companion subpaths, forwarding `enabled`, `package_allowlist`, and `package_blocklist` to the service. Generated SDK Cordis composition emits the same entries. A subpath entry adds its installable root npm package rather than treating the subpath as a package name. The shipped `dsh` TUI and Web config trees omit the service and companions under the [shipped-config decision](../simplification/2026-08-03-omit-invariants-from-shipped-config.md). Workspace constraints recognize the separate invariant bundle, and package exports, project references, build configuration, dependency declarations, and the lockfile describe the same publication surface. Generated config catalogs, module graphs, and API documentation derive from those sources. @@ -97,7 +97,7 @@ Every Vitest configuration loads a test host that mounts an explicitly enabled s - Product packages own and test their relational assertions while the service stays product-independent. - Every package pays the publication and dependency cost of a companion; only owners with a meaningful runtime relationship add listener or trace-state cost. -- Standard compositions can disable all checks or select package names without changing their plugin tree. +- Compositions that mount the diagnostics can disable all checks or select package names without changing their plugin tree. - Explicit companion entries make diagnostic cost and ownership visible in Cordis config and package exports. - One selected executable contribution adds one child fiber and its listener/state cost; a selected empty contribution has no listener or trace-state cost, while filtered registrations retain only name ownership. - Regex sources are deployment configuration and remain fixed until the service reloads. diff --git a/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.zh.md b/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.zh.md index 3c71d3b7f9..60edaa3f60 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-package-owned-invariant-service.zh.md @@ -8,7 +8,7 @@ Status: implemented 运行时不变式检查跨越会话轨迹、agent 状态、作用域 dispatch 和请求重建。如果所有检查都放在一个诊断包中，该包就必须导入彼此无关的产品领域词汇，测试也会离开真正的所有者；任何产品包新增或移除检查时，都要修改中央包。 -部署还需要比“是否加载一个插件”更细的控制。标准组合应携带已知的不变式贡献，同时允许全局关闭或按包选择诊断。包稍后加载或在 HMR 下重载时，选择结果必须保持稳定；被过滤的贡献也不能让两个插件静默占用同一个包名。 +选择启用诊断的部署还需要比“是否加载一个插件”更细的控制。这类组合会携带已知的不变式贡献，同时允许全局关闭或按包选择诊断。包稍后加载或在 HMR 下重载时，选择结果必须保持稳定；被过滤的贡献也不能让两个插件静默占用同一个包名。 包所有权还必须覆盖完整。若没有机械化的仓库规则，新包可能遗漏伴随插件、依赖或发布配置，并一直不会进入诊断范围，直到维护者发现这一缺口。 @@ -72,9 +72,9 @@ blocklist 匹配优先于 allowlist 匹配。每个条目都是区分大小写 生成的 scoped event 主体解析表位于 `dsh-scope`，与消费它的契约和不变式相邻。`gen-scoped-events` 使用根 TypeScript Program 枚举 `this: Scoped` 声明，从真实 `scopeTarget(base, key)` 调用推断路由键类型，并要求唯一、无歧义的 payload 主体或显式 unsupported 标记。提交的运行时映射不导入事件所有者包，因此语义完整性不会扩大服务包或 scope 包的运行时依赖闭包。 -### 标准组合与 SDK 输出 +### 示例组合与 SDK 输出 -标准 agent spine 会挂载服务和四个有状态伴随子路径，并把 `enabled`、`package_allowlist` 与 `package_blocklist` 转发给服务。生成的 SDK Cordis 组合输出相同条目。子路径条目添加可安装的根 npm 包，而不会把子路径误当成包名。 +示例 agent spine 会挂载服务和四个有状态伴随子路径，并把 `enabled`、`package_allowlist` 与 `package_blocklist` 转发给服务。生成的 SDK Cordis 组合输出相同条目。子路径条目添加可安装的根 npm 包，而不会把子路径误当成包名。根据[交付配置决策](../simplification/2026-08-03-omit-invariants-from-shipped-config.md)，交付的 `dsh` TUI 与 Web 配置树会省略该服务及其伴随插件。 Workspace 约束识别独立的不变式 bundle；包 exports、项目引用、构建配置、依赖声明和 lockfile 描述同一发布表面。生成的配置目录、模块图和 API 文档都从这些源派生。 @@ -97,7 +97,7 @@ Workspace 约束识别独立的不变式 bundle；包 exports、项目引用、 - 产品包拥有并测试自己的关系断言，服务保持与产品无关。 - 每个包都承担 companion 的发布与依赖成本；只有具备有意义运行时关系的所有者才增加 listener 或 trace 状态成本。 -- 标准组合无需改变插件树即可关闭全部检查或按包名选择。 +- 挂载诊断的组合无需改变插件树即可关闭全部检查或按包名选择。 - 显式伴随条目让诊断成本和所有权在 Cordis 配置与包 export 中可见。 - 每个选中的可执行贡献增加一个子 fiber 及其 listener/状态成本；选中的空贡献不增加 listener 或 trace 状态成本，被过滤注册则只保留包名占用。 - 正则表达式源属于部署配置，在服务重载前保持固定。 diff --git a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml index ba5bae421d..d63e6d4b88 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml @@ -1,6 +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 -2026-07-19-zstandard-jsonl-session-logs.md: 74430624c771a265fb281e588e28733bc55d3eb6 -2026-07-19-zstandard-jsonl-session-logs.zh.md: b22275d1a7c54a743b11f4396318dd87e4f5b42a +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md +2026-07-19-zstandard-jsonl-session-logs.md: 287ec94a91101850e9343d36ffd27870daf1333b +2026-07-19-zstandard-jsonl-session-logs.zh.md: 4e578432640651de1eb1977229b7cdd462766c24 diff --git a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md index 74430624c7..287ec94a91 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md +++ b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md @@ -28,11 +28,11 @@ First materialization compresses the two initial frames before opening the tempo ### Read, listing, and crash recovery -A frame-boundary scanner reads the standard magic, variable header fields, block headers and payload sizes, and optional checksum trailer. It does not interpret compressed blocks. Complete frames are decompressed independently and sequentially, which validates their checksums, and their plaintext is passed to the existing JSONL scanner. A checksum/decompression failure in any complete frame, a malformed complete-frame JSONL tail, or invalid frame structure is corruption and rejects. +A frame-boundary scanner reads the standard magic, variable header fields, block headers and payload sizes, and optional checksum trailer. It does not interpret compressed blocks. Complete frames are decompressed independently and sequentially with Node's default `ZSTD_e_end`, which requires frame completion and validates their checksums, and their plaintext is passed to the existing JSONL scanner. A checksum/decompression failure in any complete frame, a malformed complete-frame JSONL tail, or invalid frame structure is corruption and rejects. Listing reads in bounded chunks only until the first complete frame is available, validates and decompresses that header frame, and never reads an event frame. The dedicated header frame therefore preserves metadata-only listing even for very large session logs. -EOF inside the final frame is a recoverable torn tail. Node's decoder is given the available frame prefix; every complete newline-terminated event it emits is retained. Repair truncates from that frame's starting byte and appends one new checksummed frame containing the recovered complete events followed by the coordinator's synthetic tool, step, and turn closers. If the tear occurs before any complete event is decodable, repair drops the partial frame and retains all prior complete frames. +EOF inside the final frame is a recoverable torn tail. After the scanner establishes that boundary, a dedicated prefix decoder uses `finishFlush: ZSTD_e_flush` so Node emits available plaintext without requiring frame or checksum completion; every complete newline-terminated event it emits is retained. Repair truncates from that frame's starting byte and appends one new checksummed frame containing the recovered complete events followed by the coordinator's synthetic tool, step, and turn closers. If the tear occurs before any complete event is decodable, repair drops the partial frame and retains all prior complete frames. ### Consumers and verification diff --git a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md index b22275d1a7..4e57843264 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md @@ -28,11 +28,11 @@ JSONL 持久化后端会逐字保留每个 `SessionEvent`，其中包括数量 ### 读取、列举与崩溃恢复 -帧边界扫描器会读取标准魔数、可变头字段、块头与负载长度，以及可选校验和尾部，但不会解释压缩块。后端独立且按顺序解压完整帧，由此验证各帧校验和，再把明文交给既有 JSONL 扫描器。任何完整帧的校验和或解压失败、完整帧中畸形的 JSONL 尾部，或者无效帧结构都属于损坏并拒绝加载。 +帧边界扫描器会读取标准魔数、可变头字段、块头与负载长度，以及可选校验和尾部，但不会解释压缩块。后端使用 Node 默认的 `ZSTD_e_end` 独立且按顺序解压完整帧；该模式要求帧完整并验证各帧校验和，再把明文交给既有 JSONL 扫描器。任何完整帧的校验和或解压失败、完整帧中畸形的 JSONL 尾部，或者无效帧结构都属于损坏并拒绝加载。 列举只按有界分片读取到第一个完整帧可用为止，验证并解压该头部帧，绝不读取事件帧。因此，即使会话日志很大，专用头部帧仍能维持仅元数据列举。 -最终帧内部遇到 EOF 属于可恢复的撕裂尾部。后端把已有帧前缀交给 Node 解码器，并保留其产出的每个完整、以换行结束的事件。修复从该帧起始字节截断，再追加一个新的带校验和帧，其中依次包含恢复出的完整事件，以及协调器生成的工具、步骤与轮次闭合事件。如果撕裂位置尚不足以解码任何完整事件，修复会丢弃该不完整帧并保留此前全部完整帧。 +最终帧内部遇到 EOF 属于可恢复的撕裂尾部。扫描器确定该边界后，专用前缀解码器会使用 `finishFlush: ZSTD_e_flush`，使 Node 不必等到帧结束或读到完整校验和就能产出已有明文；其中每个完整且以换行结束的事件都会保留。修复从该帧起始字节截断，再追加一个新的带校验和帧，其中依次包含恢复出的完整事件，以及协调器生成的工具、步骤与轮次闭合事件。如果撕裂位置尚不足以解码任何完整事件，修复会丢弃该不完整帧并保留此前全部完整帧。 ### 消费方与验证 diff --git a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml deleted file mode 100644 index 0b599bc639..0000000000 --- a/.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# 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 -2026-07-22-tui-interactive-extension-service.md: 86cb39748358882d26766467d08f4f43510c1cc2 -2026-07-22-tui-interactive-extension-service.zh.md: d53f526a07b20fcff7086a1f501558d23e7eea8a diff --git a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.i18n.yaml index 2cba925d67..20745458d6 100644 --- a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.i18n.yaml @@ -1,6 +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 -2026-07-23-toolview-dissolution.md: 80c2688b152d1afe1236d4815633a5bf024db1d2 -2026-07-23-toolview-dissolution.zh.md: 928c5f445d601b2246d3ae2f9360232643814468 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.md +2026-07-23-toolview-dissolution.md: 406e5c181aabb635f9d6dcb12d8a9b8b6697368e +2026-07-23-toolview-dissolution.zh.md: 311affcbd9605ff81b78e974f75ee83328d93f68 diff --git a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.md b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.md index 80c2688b15..406e5c181a 100644 --- a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.md +++ b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.md @@ -14,13 +14,13 @@ After the view ring dissolved into the slot system, the client kept exactly one The tool ring is gone as independent infrastructure: a tool row is a **keyed child slot each view declares for itself**, and the client has exactly one registration model. The justification above was hollow — a keyed slot's *key space* is already runtime-open (SlotMap declares slots, never keys; the ask-user composer's `key: 'question'` was the precedent), so the open tool-name set fits `entryKey` dispatch natively. -Shipped shape (current-state narrative also in the [architecture note](2026-07-19-gui-web-client-architecture.md)): the chat entry's `children` table declares `'conversation.chat.toolview'` (keyed/session); the render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback` (the default card is domain property; the fallback option is ordinary renderSlot grammar). The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails` — details being a session-level facility, not chat-private), and `ToolRowProps` pre-composes it with the session standard kit for registrant components. A registrant is a plain plugin: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)` with `inject: ['slots', 'conversation']` as the load-order seam — apply mounts `ConversationService` *after* the chat registration, so the service being present guarantees the slot is declared, by construction. Session-dimension differentiation happens inside the component (`useSessions` reading `parentId` — the decision sits where all the information already is); the bash sample is the third-party-posture exemplar and paints the same ToolRow chrome as Think (`Bash · {description}`, with a scoped badge only in child sessions). Trajectory/waterfall toolview slots share this exact shape (names fixed by the slot-naming discipline `..`, one shared owner type) and land with their own row render sites — RendersCheck rejects a declaration nobody renders, so the type system, not convention, blocks early empty declarations. +Shipped shape (current-state narrative also in the [architecture note](2026-07-19-gui-web-client-architecture.md)): the chat entry's `children` table declares `'conversation.chat.toolview'` (keyed/session); the render site dispatches per row via `entryKey: toolName` with `GenericToolCard` as the call-site `fallback` (the default card is domain property; the fallback option is ordinary renderSlot grammar). The owner payload is the uniform `ToolRowOwnerProps` (`callId`/`toolName`/`block`/`openDetails` — details being a session-level facility, not chat-private), and `ToolRowProps` pre-composes it with the session standard kit for registrant components. A registrant is a plain plugin: `ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)` with `inject: ['slots', 'conversation']` as the load-order seam — apply mounts `ConversationService` *after* the chat registration, so the service being present guarantees the slot is declared, by construction. The bash sample is the third-party-posture exemplar and paints the same ToolRow chrome as Think (`Bash · {description}`). Trajectory/waterfall toolview slots share this exact shape (names fixed by the slot-naming discipline `..`, one shared owner type) and land with their own row render sites — RendersCheck rejects a declaration nobody renders, so the type system, not convention, blocks early empty declarations. Registry-era responsibilities all have successor homes: inject caching and row error isolation ride the framework renderer (entry×scope cache, per-entry `SlotErrorBoundary`); subscribe/getVersion ride the slot core's per-key version machinery; the future "store seat" is the ordinary store seat keyed slots already have (interaction-draft durability is its first named consumer); miss fallback is the call-site `fallback` option. ## Accepted semantic changes -Four behavioral deltas were accepted deliberately, not overlooked. Cross-view appearance is per-view registration — a row must adapt to each view's layout anyway, so one registration per view is the correct coupling, and reuse is the same component in two register calls. Same-key double registration is a loud throw where the registry let later-wins silently override — a discipline correction, not a loss. Session-dimension dispatch moved from registry predicates into the component. Registry-level shape override by third parties (a scoped registration shadowing a global one) has no equivalent; a real future need routes through key-naming conventions or a small in-component resolver, never a revived parallel registry. +Four behavioral deltas were accepted deliberately, not overlooked. Cross-view appearance is per-view registration — a row must adapt to each view's layout anyway, so one registration per view is the correct coupling, and reuse is the same component in two register calls. Same-key double registration is a loud throw where the registry let later-wins silently override — a discipline correction, not a loss. Session-dimension dispatch, when a row needs it, belongs inside the component (the standard kit already carries `useSessions`), not in registry predicates — there is no shipped session-variant exemplar today. Registry-level shape override by third parties (a scoped registration shadowing a global one) has no equivalent; a real future need routes through key-naming conventions or a small in-component resolver, never a revived parallel registry. ## Alternatives considered diff --git a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.zh.md b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.zh.md index 928c5f445d..311affcbd9 100644 --- a/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-23-toolview-dissolution.zh.md @@ -14,13 +14,13 @@ Status: implemented 工具环作为独立基础设施已消失：工具行是**各视图为自己声明的 keyed 子槽**，client 全域只剩一种注册模型。上述理由是空的——keyed slot 的 *key 空间*本就运行时开放（SlotMap 声明槽、从不声明 key；ask-user composer 的 `key: 'question'` 即先例），开放的 tool 名集合天然适配 `entryKey` 分发。 -落地形态（现状叙述同见[架构注](2026-07-19-gui-web-client-architecture.md)）：chat 条目的 `children` 表声明 `'conversation.chat.toolview'`（keyed/session）；渲染点逐行以 `entryKey: toolName` 分发、以 `GenericToolCard` 作调用点 `fallback`（默认卡片是域产权；fallback 选项就是普通 renderSlot 文法）。owner 载荷是统一的 `ToolRowOwnerProps`（`callId`/`toolName`/`block`/`openDetails`——details 是会话级设施，非 chat 私货），`ToolRowProps` 把它与 session 标配 kit 预组合供注册方组件取用。注册方就是普通插件：`ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`，以 `inject: ['slots', 'conversation']` 作加载序缝——apply 把 `ConversationService` 挂在 chat 注册*之后*，故服务在场即保证槽已声明，构造使然。会话维差异化在组件内完成（`useSessions` 读 `parentId`——决策放在已有全部信息的地方）；bash 样例即第三方姿态的样板，并与 Think 绘制同一套 ToolRow chrome（`Bash · {description}`，scoped badge 仅出现在子会话）。trajectory/waterfall 的 toolview 槽共用这套形状（槽名按槽名纪律 `<域>.<条目>.<孔位>` 定死，共用一张 owner 类型），随各自的行渲染点落地——RendersCheck 拒绝无人渲染的声明，挡住提前空声明的是类型系统而非约定。 +落地形态（现状叙述同见[架构注](2026-07-19-gui-web-client-architecture.md)）：chat 条目的 `children` 表声明 `'conversation.chat.toolview'`（keyed/session）；渲染点逐行以 `entryKey: toolName` 分发、以 `GenericToolCard` 作调用点 `fallback`（默认卡片是域产权；fallback 选项就是普通 renderSlot 文法）。owner 载荷是统一的 `ToolRowOwnerProps`（`callId`/`toolName`/`block`/`openDetails`——details 是会话级设施，非 chat 私货），`ToolRowProps` 把它与 session 标配 kit 预组合供注册方组件取用。注册方就是普通插件：`ctx.slots.register({ name: 'conversation.chat.toolview', key: '', inject? }, Row)`，以 `inject: ['slots', 'conversation']` 作加载序缝——apply 把 `ConversationService` 挂在 chat 注册*之后*，故服务在场即保证槽已声明，构造使然。bash 样例即第三方姿态的样板，并与 Think 绘制同一套 ToolRow chrome（`Bash · {description}`）。trajectory/waterfall 的 toolview 槽共用这套形状（槽名按槽名纪律 `<域>.<条目>.<孔位>` 定死，共用一张 owner 类型），随各自的行渲染点落地——RendersCheck 拒绝无人渲染的声明，挡住提前空声明的是类型系统而非约定。 registry 时代的职责各有后继居所：inject 缓存与行错误隔离乘框架渲染器（entry×scope 缓存、per-entry `SlotErrorBoundary`）；subscribe/getVersion 乘 slot core 的 per-key 版本机；将来的「store 席位」就是 keyed slot 本就拥有的普通 store 席位（交互草稿耐久性是其首个具名消费者）；miss 兜底即调用点 `fallback` 选项。 ## 接受的语义变化 -四项行为增量是刻意接受而非疏漏。跨视图出场=逐视图注册——行本须适配各视图版式，一视图一注册是正确耦合，复用即同一组件写两次 register。同 key 重复注册从注册表的 later-wins 静默覆盖变为 loud throw——纪律修正而非损失。会话维分发从注册表谓词移入组件。第三方在 registry 级覆盖形态（scoped 注册压过 global）不复存在；真出现的未来需求走 key 命名空间约定或组件内小 resolver，永不复活平行注册表。 +四项行为增量是刻意接受而非疏漏。跨视图出场=逐视图注册——行本须适配各视图版式，一视图一注册是正确耦合，复用即同一组件写两次 register。同 key 重复注册从注册表的 later-wins 静默覆盖变为 loud throw——纪律修正而非损失。会话维分发若行需要，归组件内部（标配 kit 已带 `useSessions`），不走注册表谓词——今天没有已落地的会话变体样例。第三方在 registry 级覆盖形态（scoped 注册压过 global）不复存在；真出现的未来需求走 key 命名空间约定或组件内小 resolver，永不复活平行注册表。 ## Alternatives considered diff --git a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.i18n.yaml index b1a81228cf..45e1c99967 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.i18n.yaml @@ -1,6 +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 -2026-07-24-single-harness-home-resolver.md: 10ed0e9f1fd6ac4630d92a66953fdf1d52b3b5f1 -2026-07-24-single-harness-home-resolver.zh.md: 1ce56281357595de134ddea285c8c2e0c1801ce9 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.md +2026-07-24-single-harness-home-resolver.md: 159ba88b7b4a8d50f1be2cbe5d9162a654014e16 +2026-07-24-single-harness-home-resolver.zh.md: 62046abca48a3c2b07fde4180031dc2186dc101f diff --git a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.md b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.md index 10ed0e9f1f..159ba88b7b 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.md +++ b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.md @@ -22,7 +22,7 @@ One resolver owns the harness home, in `@deepseek-ai/dsh-paths`, single-root: explicit configured path > $DSH_HOME > ~/.dsh ``` -An empty or whitespace-only `$DSH_HOME` is treated as unset, matching the guard telemetry's old resolver carried: without it `resolve('')` would silently place the home at the current working directory. The harness keeps all user data under one root; there is no XDG config/data/cache split. `dshHomeDisplay()` names a resolved root symbolically for user-facing paths — `~/.dsh` for the default home, `$DSH_HOME` for any configured home — so the user-global `AGENTS.md` label never leaks an absolute machine path. It replaces workspace-context's bespoke default-vs-`$DSH_HOME` check. +An empty or whitespace-only `$DSH_HOME` is treated as unset, matching the guard telemetry's old resolver carried: without it `resolve('')` would silently place the home at the current working directory. The harness keeps all user data under one root; there is no XDG config/data/cache split. `dshHomePath(...segments)` joins deployment-owned children onto that root, and `dsh-app-boot` exposes it to Loader `!!js` config expressions before mounting entries, so shipped compositions derive `sessions` and `storages` without copying the resolver. `dshHomeDisplay()` names a resolved root symbolically for user-facing paths — `~/.dsh` for the default home, `$DSH_HOME` for any configured home — so the user-global `AGENTS.md` label never leaks an absolute machine path. It replaces workspace-context's bespoke default-vs-`$DSH_HOME` check. `@deepseek-ai/dsh-home` is deleted. Its three importers (`dsh-tool-bash`, `dsh-skill-local`, `dsh-agent-spine-demo`) now import `resolveDshHome` from `dsh-paths`. `dsh-telemetry`'s `globalConfigDir` delegates to `resolveDshHome`, dropping its second resolver, the `DSH_CONFIG_HOME` override, the XDG/`%APPDATA%` branches, and the `deepseek-harness` namespace; the anonymous id now lives directly under the harness home. diff --git a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.zh.md b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.zh.md index 1ce5628135..62046abca4 100644 --- a/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-24-single-harness-home-resolver.zh.md @@ -22,7 +22,7 @@ Status: implemented explicit configured path > $DSH_HOME > ~/.dsh ``` -空或仅含空白的 `$DSH_HOME` 被当作未设置处理，这与 telemetry 旧解析器所带的保护一致：若无此保护，`resolve('')` 会悄悄把 home 落在当前工作目录。harness 把所有用户数据都放在同一个根目录下；不存在 XDG 的 config/data/cache 拆分。`dshHomeDisplay()` 为面向用户的路径以符号形式命名已解析的根目录——默认 home 显示为 `~/.dsh`，任何已配置的 home 显示为 `$DSH_HOME`——这样面向用户全局的 `AGENTS.md` 标签就绝不会泄露机器上的绝对路径。它取代了 workspace-context 中自定义的"默认值 vs `$DSH_HOME`"判断。 +空或仅含空白的 `$DSH_HOME` 被当作未设置处理，这与 telemetry 旧解析器所带的保护一致：若无此保护，`resolve('')` 会悄悄把 home 落在当前工作目录。harness 把所有用户数据都放在同一个根目录下；不存在 XDG 的 config/data/cache 拆分。`dshHomePath(...segments)` 将部署负责的子路径拼接到该根目录下，`dsh-app-boot` 在挂载条目前向 Loader `!!js` 配置表达式暴露它，因此出厂组合无需复制解析器即可派生 `sessions` 和 `storages`。`dshHomeDisplay()` 为面向用户的路径以符号形式命名已解析的根目录——默认 home 显示为 `~/.dsh`，任何已配置的 home 显示为 `$DSH_HOME`——这样面向用户全局的 `AGENTS.md` 标签就绝不会泄露机器上的绝对路径。它取代了 workspace-context 中自定义的"默认值 vs `$DSH_HOME`"判断。 `@deepseek-ai/dsh-home` 被删除。它的三个引用方（`dsh-tool-bash`、`dsh-skill-local`、`dsh-agent-spine-demo`）现在从 `dsh-paths` 导入 `resolveDshHome`。`dsh-telemetry` 的 `globalConfigDir` 转而委托给 `resolveDshHome`，去掉了它的第二个解析器、`DSH_CONFIG_HOME` 覆盖项、XDG/`%APPDATA%` 分支以及 `deepseek-harness` 命名空间；匿名 id 现在直接存放在 harness home 之下。 diff --git a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.i18n.yaml index 09ab4376b5..52c7c71e1a 100644 --- a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.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/2026-07-25-web-input-machine-and-slash-pipeline.md -2026-07-25-web-input-machine-and-slash-pipeline.md: c3deadb34d3a633525dde701c92bcc98c05e5d6e -2026-07-25-web-input-machine-and-slash-pipeline.zh.md: 7a6988423dcdffebb0a28735146439c8ade0a862 +2026-07-25-web-input-machine-and-slash-pipeline.md: 977df6508e1a1cd54cf1ddb469a6bfb835f60071 +2026-07-25-web-input-machine-and-slash-pipeline.zh.md: 929a885bf54a31605805814ba1e15c901e560434 diff --git a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.md b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.md index c3deadb34d..977df6508e 100644 --- a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.md +++ b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.md @@ -72,7 +72,7 @@ A trigger/menu/pick pipeline with zero knowledge of "commands": - Each materialized Session has exactly one `SessionInputShell` (the facade), created and torn down with the session scope; with no session, no input machine is built. `ConversationRoot` is itself the `session-maybe` resident shell, holding HeroShell, the Workspace picker, the composer stack, and the chain-fallback frame. - The composer bar is one `session-maybe` slot entry rendered unconditionally: with no session the same InputBar renders inert (machine faces absent, `disabled` owner prop), and once `connectWorkspace` returns a blank session the same instance goes live — the textarea DOM survives the no-session → blank transition and every later phase flip; `ConversationRoot`, the Hero, and the layout skeleton hold throughout. - ConversationRoot's Hero criterion is `sessionId === undefined || (composerPhase === 'blank' && (openState === 'open' || openState === 'loading'))`. The first submit enters engaging synchronously, and a failure keeps the composer and the error context rather than falling back to the blank Hero; the sidebar's blank bit flips false only after a prompt is successfully accepted. -- Sending unifies in the hub defaultSink: after an optimistic draft clear it goes only through `session.prompt {mode:'queue'|'steer'}`; backfill happens only when it fails and the live draft is still empty — a user who has kept typing is never overwritten. No Draft materialize or attach transaction exists. +- Sending unifies in the hub defaultSink: after an optimistic draft clear it goes only through `session.prompt` with `mode:'queue'` (the Web UI has no steer entry; host-wire `mode:'steer'` remains outside this machine); backfill happens only when it fails and the live draft is still empty — a user who has kept typing is never overwritten. No Draft materialize or attach transaction exists. - When the blank Hero re-picks the Workspace, the shell calls `connectWorkspace`; if the target session differs, the non-empty draft moves from the current shell to the target shell before the new id is opened, and the old blank session survives but is no longer current. - The Notifier's two-bit contract: `dirty` (snapshot freshness, clearable by an `ensureFresh` pull) and `notifyPending` (notification debt, cleared only by a flush) are mutually independent — a pull must not swallow a push, and object-layer push subscribers (watchTransaction) depend on this guarantee. diff --git a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.zh.md b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.zh.md index 7a6988423d..929a885bf5 100644 --- a/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.zh.md @@ -72,7 +72,7 @@ occurrence 表与 chip 三投影： - 每个实体 Session 只有一个 `SessionInputShell`（facade），随 session scope 创建和拆除；无 session 时不造 input machine。`ConversationRoot` 自身是 `session-maybe` 常驻外壳，持有 HeroShell、Workspace picker、composer stack 与 chain fallback 外框。 - composer bar 是一个无条件渲染的 `session-maybe` slot entry：无 session 时同一个 InputBar 以惰性态渲染（machine face 缺席、`disabled` owner prop），`connectWorkspace` 返回 blank session 后同一实例转为 live——textarea DOM 在无 session → blank 切换及其后每次 phase 翻转中都不重建；`ConversationRoot`、Hero 与布局骨架全程保持。 - ConversationRoot 的 Hero 判据是 `sessionId === undefined || (composerPhase === 'blank' && (openState === 'open' || openState === 'loading'))`。首次 submit 同步进入 engaging，失败也保留 composer 与错误上下文，不退回 blank Hero；sidebar 的 blank 位只在 prompt 成功受理后翻 false。 -- 发送统一在 hub defaultSink：乐观清稿后只走 `session.prompt {mode:'queue'|'steer'}`；失败且 live draft 仍为空才回填，用户已经继续输入则不覆盖。不存在 Draft materialize 或 attach 事务。 +- 发送统一在 hub defaultSink：乐观清稿后只走 `session.prompt` 且固定 `mode:'queue'`（Web UI 无 steer 入口；host 线缆上的 `mode:'steer'` 不经此 machine）；失败且 live draft 仍为空才回填，用户已经继续输入则不覆盖。不存在 Draft materialize 或 attach 事务。 - blank Hero 改选 Workspace 时，外壳调用 `connectWorkspace`；目标 session 不同时把非空 draft 从当前 shell 搬到目标 shell，再 open 新 id，旧 blank session 留存但不再 current。 - Notifier 双位契约：`dirty`（快照新鲜度，`ensureFresh` 拉取可清）与 `notifyPending`（通知欠账，只有 flush 清）各自独立——拉取不得吞推送，对象层推订阅者（watchTransaction）依赖这一保证。 diff --git a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.i18n.yaml index 27911294a6..048536527a 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-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/2026-07-28-directory-picker-capability-seam.md -2026-07-28-directory-picker-capability-seam.md: 495062f910785e1bb2f421dbb25c01c399d45567 -2026-07-28-directory-picker-capability-seam.zh.md: 62fc87212ab627ea8819dab55e3a769b4a5afc42 +2026-07-28-directory-picker-capability-seam.md: 01968990db81852dbf965a90fc151bab357ecb55 +2026-07-28-directory-picker-capability-seam.zh.md: ffbb939eabcca3e16711a4cadcadad50660a9e04 diff --git a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.md b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.md index 495062f910..01968990db 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.md +++ b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.md @@ -12,7 +12,7 @@ The web GUI's "Open local folder" flow was hardwired to one interaction: `host.p A three-package capability seam in `packages/host/` — `directory-picker` (interface), `directory-picker-native`, `directory-picker-browse` (backends) — with one contract method: `capability()` returns a **discriminated union**, `{ kind: 'native', pick(signal) }` or `{ kind: 'browse', list(path?), createDirectory(path, name) }`. The gateway (`dsh-host-apiproxy`) injects `directoryPicker`, serves the matching RPCs, and answers `directory-picker-unavailable` for the other kind. The union is discriminated because the backends differ in *interaction shape* — flattening them into one method set would force every backend to fake the other's shape. -**The client side is slot-composed, not advertisement-branched.** ui-workspace's two trigger surfaces each declare a `single` directory-flow hole (`conversation.hero.workspace.directoryFlow` / `sidebar.workspaces.directoryFlow`; two keys because a hole has exactly one declaring slot entry — same owner contract, same occupant). Backend packages are **dual-face**: the browser half registers the matching interaction into both holes — `-native` a renderless occupant driving `host.pickDirectory`, `-browse` the in-app Select Workspace Directory dialog. The hole's owner conversation (`open`/`busy`/`onPicked`/`onCancel`/`onError`) carries the whole exchange: ui-workspace keeps the trigger (menu entry rendered only while the hole is occupied) and the adoption (`createWorkspace({path})`, conflict/error dialog, Choose again), the occupant owns everything between `open` and the picked path. One `cordis.yml` row therefore swaps the host capability and the client flow together; a mismatch is impossible by construction, and mounting two flow packages fails at client load (`single` hole). The earlier `host.describe.directoryPicker` advertisement and the client's kind branching are deleted — with composition wiring both sides, a wire fact for the client to branch on had no remaining consumer. The hole registry (`ctx.slots.entries`) replaces it as the per-menu-open occupancy read. +**The client side is slot-composed, not advertisement-branched.** ui-workspace's two trigger surfaces each declare a `single` directory-flow hole (`conversation.hero.workspace.directoryFlow` / `sidebar.workspaces.directoryFlow`; two keys because a hole has exactly one declaring slot entry — same owner contract, same occupant). Backend packages are **dual-face**: the browser half registers the matching interaction into both holes — `-native` a renderless occupant driving `host.pickDirectory`, `-browse` the in-app Select Workspace Directory dialog. The hole's owner conversation (`open`/`busy`/`onPicked`/`onCancel`/`onError`) carries the whole exchange: ui-workspace keeps the trigger (menu entry rendered only while the hole is occupied) and the adoption (`createWorkspace({path})`, retryable error dialog, Choose again), the occupant owns everything between `open` and the picked path. One `cordis.yml` row therefore swaps the host capability and the client flow together; a mismatch is impossible by construction, and mounting two flow packages fails at client load (`single` hole). The earlier `host.describe.directoryPicker` advertisement and the client's kind branching are deleted — with composition wiring both sides, a wire fact for the client to branch on had no remaining consumer. The hole registry (`ctx.slots.entries`) replaces it as the per-menu-open occupancy read. Placement and policy rulings folded into this decision: @@ -20,7 +20,8 @@ Placement and policy rulings folded into this decision: - **Dependency survey (hand-roll vs adopt).** Node's stdlib *is* the maintained cross-platform OS layer (`readdir(withFileTypes)`, `homedir`, path semantics); surveyed alternatives fail the dependency bar — file-manager packages (`node-file-manager`, `files-and-folders`, Syncfusion's provider) are whole HTTP apps (fit), drive-letter helpers (`drivelist` native addon, `windows-drive-letters` ~7y stale) fail health/proportionality. The browse backend is a thin adapter over stdlib. - **Hidden entries: return-and-flag.** The host stamps `hidden` (POSIX dot convention) and returns everything; the client filters. Display policy stays client-side, and the show-hidden toggle shipped as exactly that client-only change: a fixed-label footer toggle whose state lives in the pressed presentation (`aria-pressed` + check glyph), a dot-led path-draft prefix reveals the hidden entries it names, and the current selection is exempt from both the hidden and the prefix filter (it anchors the two-pane view). Windows' `FILE_ATTRIBUTE_HIDDEN` is not exposed by dirents — documented limitation until a native probe pays for itself. - **Path-editor cancel scope: the dialog card.** The browse client's path editor cancels on Escape and on focus leaving the card, both observed at a card-scope wrapper rather than the input — after Tab parks focus on a filtered row the input is off the event path, yet Escape must collapse the editor (not the dialog) and a later focus departure must still cancel. Non-cancel exemptions: window/tab focus loss, in-card focus moves, and pointer paths (rows and the toggle suppress focus steal on mousedown while editing). Separators for seeding and draft-tail filtering are inferred from `listing.home`; the wire-field alternative below records the deferred authoritative form. Combobox semantics between the editor and the list it filters (`aria-expanded`/`aria-controls`/active-descendant, result announcements) are likewise deferred — today they read to assistive tech as separate widgets. -- **Navigation lands selection-anchored, quiet, and bounded.** Away from the display root (the same collapse the crumb header renders, so crumbs and pane shape never disagree), the landing is two-pane: the target's actual parent-level entry re-selected (platform case folding on Windows), its children on the right, so a crumb jump reads as stepping back one pane rather than collapsing to a single column. Target and parent legs land as **one frame** when the parent leg settles within the 200ms wait bound — the stale view keeps rendering until then, so navigation swaps the panes without an intermediate single-pane flash — and past the bound the target commits alone at once (an Enter-submitted navigation is never held hostage by a stalled parent) with the late parent leg upgrading the landing in place. The parent leg runs under the landing's supersession scope and is aborted on the wire by any newer intent (Escape inside the landing window therefore withdraws the whole navigation); a failed parent leg, or a truncated parent window lacking the target, leaves the single-pane landing — the upgrade must never orphan the selection it exists to anchor. The loading indicator follows the same quiet rule: it floats over the content's bottom-right corner (never a layout-shifting row; the truncated/error rows own the bottom left and keep rendering through a scan) and only once a scan outlives a 300ms silence window, so a local listing swaps with nothing shown at all. Row picks are deliberately exempt from the one-frame rule: a pick's immediate pane split is its selected-state feedback (aria-current, crumbs following), while a navigation has nothing to acknowledge the click but the swap itself. Both timing constants are calibrated for local enumeration; a remote deployment (one RPC per level, commonly 100–400ms) would sit inside the silence window with no pressed state on the crumbs — revisit the window or add pressed feedback when a remote consumer lands. +- **The path editor advertises itself, and the panes follow the draft.** The click-to-edit zone is not invisible: a pencil glyph sits at the bar's right edge and hover/focus lights the WHOLE bar in the editor's own box — the bar carries the outline and padding in both modes, so the hover previews exactly the field the click produces and nothing resizes when zone and input swap. While the editor is open the panes track the draft instead of whatever level happened to be listed when it opened — the final segment prefix-filters the level its directory part names, a tail nobody matches releases the filter (a name still being spelled must not empty the pane it is being spelled into), and any other directory part is scanned after a 250ms rest and lands through the same selection-anchored, two-pane landing every navigation uses, so typing a path moves the Miller view exactly as a crumb jump does — typing deeper descends, erasing segments walks back up — without leaving the editor. **The pane arity is the invariant**: the last pane always lists the level the path names, with its parent beside it and nothing but a display root listing alone. Skipping the scan whenever *any* pane happened to list the directory was the cheaper rule and the wrong one — erasing a segment then left the level being typed on the left with its own child pane still standing to its right, so the panes stopped reading as "where I am, and where I came from". Only the last pane's own tail costs no scan. One landing shape, two callers: a submitted path closes the editor and announces failures, the draft-following scan keeps both to itself. That scan is speculative — half-typed directories are unreadable most of the time — so a failure keeps the last readable panes and stays silent. Enter remains the authoritative commit: it owns the view from submission until landing (a debounce timer armed by the same keystrokes is held back rather than superseding the navigation, and a rejected submission stays held until the next edit) and it alone surfaces the failure. Two consequences are deliberate. The wait is keyed on the draft, not on the directory part it names, so a keystroke that superseded an in-flight scan re-arms one and an edit after a rejected submission releases the hold; the panes it reads are a ref rather than a dependency, or the landing would re-arm the wait and a host answering with a differently spelled path would scan forever. And a walk is not rewound: closing the editor — cancellation included — leaves the panes where the draft took them, named by the crumbs and followed by Open's fallback target, because the operator watched them move. A landing that unmounts the row a keyboard operator Tabbed onto re-parks focus on the editor, since the Modal has no focus trap. Two further rules keep one keystroke to one movement: the walk waits BOTH legs out rather than taking the submitted-navigation wait bound (nothing waits on a speculative scan, so landing single-pane and upgrading would be the very flash this exists to avoid, and it would strand the two-pane view whenever a tail keystroke aborted a slow parent leg), and the tail filters only the LAST pane — narrowing a pane the draft has walked away from would move the view once as it narrows and again as its landing replaces it. A level also keeps answering the directory text that produced it (`scanned`), because the Host resolves what it is given: `..` segments and, on Windows, forward slashes reach a level whose own path spells the request differently, and without the memo those drafts would rescan on every keystroke and never filter. +- **Navigation lands selection-anchored, quiet, and bounded.** Away from the display root (the same collapse the crumb header renders, so crumbs and pane shape never disagree), the landing is two-pane: the target's actual parent-level entry re-selected (platform case folding on Windows), its children on the right, so a crumb jump reads as stepping back one pane rather than collapsing to a single column. Target and parent legs land as **one frame** when the parent leg settles within the 200ms wait bound — the stale view keeps rendering until then, so navigation swaps the panes without an intermediate single-pane flash — and past the bound the target commits alone at once (an Enter-submitted navigation is never held hostage by a stalled parent) with the late parent leg upgrading the landing in place. The parent leg runs under the landing's supersession scope and is aborted on the wire by any newer intent (Escape inside the landing window therefore withdraws the whole navigation); a failed parent leg, or a truncated parent window lacking the target, leaves the single-pane landing — the upgrade must never orphan the selection it exists to anchor. The loading indicator follows the same quiet rule: it floats over the content's bottom-right corner (never a layout-shifting row; the truncated/error rows own the bottom left and keep rendering through a scan) and only once a scan outlives a 300ms silence window, so a local listing swaps with nothing shown at all. Row picks are deliberately exempt from the one-frame rule: a pick's immediate pane split is its selected-state feedback (aria-current, crumbs following), while a navigation has nothing to acknowledge the click but the swap itself. All three timing constants — the 200ms parent-leg bound, the 300ms silence window, and the editor's 250ms draft rest — are calibrated for local enumeration; a remote deployment (one RPC per level, commonly 100–400ms) would sit inside the silence window with no pressed state on the crumbs, and would pay rest plus RPC before the panes follow a typed path — revisit all three together when a remote consumer lands. - **Symlinks: follow for enterability.** `stat` probes symlinks (broken/cyclic → skipped); crumbs keep the logical path the operator navigated, and `workspace.create` already canonicalizes via realpath at adoption. - **Listing levels are bounded, and streamed.** One `list` call returns at most `maxEntries` rows (config, default 1000 — GitHub's web-UI directory-listing bound). The level streams via `opendir` into a name-sorted window of `maxEntries + 1` candidates, so memory stays O(maxEntries) and enterability probing touches only windowed candidates; the wire `DirectoryListing` carries a required `truncated` flag so the client states incompleteness instead of silently missing tail entries. A windowed broken symlink is not backfilled from beyond the window — the eviction already marks the level truncated. Window insertion is binary with an O(1) full-window tail rejection (an oversized level must not pay a window scan per dirent), and `list(path, signal)` threads the carrier's request signal so a scan of a stalled network directory cannot outlive a disconnected caller — every await in the scan (open, each read, each symlink probe) races the signal, an aborted exit abandons rather than awaits the close (Node queues close behind in-flight reads), and abandoned settlements are swallowed so cleanup can never surface as an unhandled rejection. An unbounded level is a memory/responsiveness hole for large or adversarial directories. - **Whole-filesystem scope, no roots config.** `workspace.create` accepts arbitrary paths and the API serves bash-driving methods, so a browse root would be UX scoping, not a boundary; configurability without a consumer fails the evidence bar. Deferred until a deployment needs it. @@ -34,6 +35,9 @@ Placement and policy rulings folded into this decision: - **Adopting a file-manager/drive-enumeration dependency.** Rejected per the survey above; recorded here as the dependency policy requires. - **A flip-label show-hidden toggle ("Hide hidden files").** Rejected: a flipping action label is ambiguous between state and action and doubles the negative; the fixed label with a pressed presentation states both at once. - **Pure relatedTarget blur cancellation (no mousedown suppression).** Rejected: Safari does not focus buttons on pointer down, so a click's focusout carries a null `relatedTarget` and would cancel the editor before the click lands; editing-scoped mousedown suppression plus the card-anchored relatedTarget guard covers pointer and keyboard paths together. +- **A permanently visible path input above the Miller view.** Rejected: the breadcrumb is already the "where am I" reading, and a second always-present field duplicates it while costing a row of a 500px card that the columns need. The glyph plus the hover-lit zone puts the affordance on the bar that already answers the question. +- **Scanning the draft on every keystroke, or only on Enter.** Per keystroke: walking one path segment issues a listing per character, most of them for directories the operator is typing through, not at. Only on Enter (what shipped first): the panes and the typed text disagreed for the whole edit — the complaint this bullet answers. The 250ms rest keeps one scan per directory the typing actually settles on. +- **Emptying a pane on a prefix miss (what shipped first).** Rejected: mid-name the miss is the normal state, so the pane blanked exactly while the operator needed it to confirm the name; releasing the filter keeps the level readable and costs only the transient wideness. - **A wire `separator` field on `DirectoryListing` (host stamps `path.sep`).** Deferred, not rejected: it is the authoritative form — a POSIX home directory containing a backslash defeats the `listing.home` heuristic — but it touches the seam type and every backend; the browse client's `separatorOf` carries a TODO pointing at this alternative until a wire change is next scheduled. ## Consequences diff --git a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.zh.md b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.zh.md index 62fc87212a..ffbb939eab 100644 --- a/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-28-directory-picker-capability-seam.zh.md @@ -12,7 +12,7 @@ web GUI 的"打开本地文件夹"流程被焊死在一种交互上：`host.pick 在 `packages/host/` 落一个三包能力 seam——`directory-picker`（接口）、`directory-picker-native`、`directory-picker-browse`（后端）——唯一契约方法 `capability()` 返回**可辨识联合**：`{ kind: 'native', pick(signal) }` 或 `{ kind: 'browse', list(path?), createDirectory(path, name) }`。网关（`dsh-host-apiproxy`）注入 `directoryPicker`，提供对应的 RPC，另一种 kind 的调用以 `directory-picker-unavailable` 应答。联合之所以可辨识，是因为后端差异在**交互形态**——压平成统一方法集会逼每个后端伪装另一方的形态。 -**client 侧靠 slot 组合，而非按广播分支。** ui-workspace 的两个触发表层各自声明一个 `single` 目录流洞（`conversation.hero.workspace.directoryFlow`／`sidebar.workspaces.directoryFlow`；之所以是两个 key，是因为一个洞只有一个声明它的 slot entry——owner 契约相同、占用者相同）。后端包是**双面包**：browser half 把匹配的交互注册进两个洞——`-native` 是驱动 `host.pickDirectory` 的无渲染占用者，`-browse` 是应用内的选择工作区目录对话框。洞的 owner 会话（`open`/`busy`/`onPicked`/`onCancel`/`onError`）承载整个交换：ui-workspace 保留触发（菜单入口仅在洞被占用时渲染）与接纳（`createWorkspace({path})`、冲突／错误对话框、重新选择），占用者持有从 `open` 到所选路径之间的一切。因此一行 `cordis.yml` 同时切换宿主能力与 client 流程；错配在构造上不可能，同时挂两个流程包会在 client 加载期失败（`single` 洞）。早先的 `host.describe.directoryPicker` 广播与客户端 kind 分支被删除——组合已经接好两侧后，供客户端分支用的 wire 事实不再有任何消费者。洞注册表（`ctx.slots.entries`）取而代之，成为每次打开菜单的占用读取。 +**client 侧靠 slot 组合，而非按广播分支。** ui-workspace 的两个触发表层各自声明一个 `single` 目录流洞（`conversation.hero.workspace.directoryFlow`／`sidebar.workspaces.directoryFlow`；之所以是两个 key，是因为一个洞只有一个声明它的 slot entry——owner 契约相同、占用者相同）。后端包是**双面包**：browser half 把匹配的交互注册进两个洞——`-native` 是驱动 `host.pickDirectory` 的无渲染占用者，`-browse` 是应用内的选择工作区目录对话框。洞的 owner 会话（`open`/`busy`/`onPicked`/`onCancel`/`onError`）承载整个交换：ui-workspace 保留触发（菜单入口仅在洞被占用时渲染）与接纳（`createWorkspace({path})`、可重试的错误对话框、重新选择），占用者持有从 `open` 到所选路径之间的一切。因此一行 `cordis.yml` 同时切换宿主能力与 client 流程；错配在构造上不可能，同时挂两个流程包会在 client 加载期失败（`single` 洞）。早先的 `host.describe.directoryPicker` 广播与客户端 kind 分支被删除——组合已经接好两侧后，供客户端分支用的 wire 事实不再有任何消费者。洞注册表（`ctx.slots.entries`）取而代之，成为每次打开菜单的占用读取。 并入本决策的位置与策略裁决： @@ -20,7 +20,8 @@ web GUI 的"打开本地文件夹"流程被焊死在一种交互上：`host.pick - **依赖调研（手写 vs 引入）。** Node 标准库本身就是维护中的跨平台 OS 层（`readdir(withFileTypes)`、`homedir`、路径语义）；调研过的替代品都过不了依赖门槛——文件管理器包（`node-file-manager`、`files-and-folders`、Syncfusion 的 provider）是整套 HTTP 应用（契合度不过），盘符工具（原生插件 `drivelist`、约七年未更的 `windows-drive-letters`）健康度／比例失当。browse 后端是标准库上的薄适配。 - **隐藏条目：返回并打标。** 宿主标注 `hidden`（POSIX 点前缀约定）并返回全部条目；客户端过滤。展示策略留在客户端，"显示隐藏"开关正是作为这一纯客户端改动落地：标签固定的 footer 开关，其状态由按下态呈现承载（`aria-pressed` + 勾选符号）；以点开头的路径草稿前缀会显出它所指名的隐藏条目；当前选中项则不受隐藏与前缀两种过滤影响（它锚定着双栏视图）。Windows 的 `FILE_ATTRIBUTE_HIDDEN` 不被 dirent 暴露——记为限制，直到原生探测值回其成本。 - **路径编辑器的取消范围：对话框卡片。** browse 客户端的路径编辑器在按 Escape 与焦点离开卡片时取消，两者都在卡片范围的包装层而非输入框上监听——Tab 把焦点停到某个过滤命中的行之后，输入框已不在事件路径上，但 Escape 仍须收起编辑器（而非对话框），其后的焦点离开也仍须取消。不取消的豁免：窗口／标签页失焦、卡片内焦点移动，以及指针路径（编辑期间行与开关在 mousedown 时抑制焦点夺取）。预填与草稿末段过滤所用的分隔符从 `listing.home` 推断；下文的线上字段替代方案记录了被延期的权威形态。编辑器与其过滤的列表之间的 combobox 语义（`aria-expanded`／`aria-controls`／active-descendant、结果播报）同样被延期——目前二者在辅助技术看来是彼此独立的控件。 -- **导航以选中项为锚、安静且有界地落地。** 在展示根之外（与 crumb 头部渲染的是同一塌缩，因此 crumb 与分栏形态永不相左），落地即双栏：重新选中目标在父层级中的实际条目（Windows 上按平台惯例折叠大小写），右侧展示其子项，因此 crumb 跳转读作后退一栏，而不是塌缩成单列。父层级这一程在 200ms 等待上限内落定时，目标与父层级两程以**同一帧**落地——在此之前陈旧视图持续渲染，导航换栏时因此没有中间的单栏闪现——超出该上限则目标即刻单独提交（Enter 提交的导航绝不会被滞塞的父层级扣作人质），迟到的父层级这一程再就地升级这次落地。父层级这一程在落地的 supersession 范围下运行，任何较新的意图都会在线上将其中止（因此在落地窗口内按 Escape 即撤回整次导航）；父层级这一程失败，或被截断的父窗口缺少目标时，都保留单栏落地——升级的存在正是为了锚定选中项，绝不能反而让它悬空。加载指示器遵循同一安静规则：它浮于内容右下角（绝不是会挪动布局的一行；截断／错误行占据左下角，并在扫描期间持续渲染），且仅在扫描超出 300ms 静默窗口后才出现，因此本地列举切换时什么也不显示。行选取被刻意豁免于同一帧规则：选取后立即分栏本身就是其选中态反馈（aria-current、crumb 跟随），而导航除了换栏本身没有任何东西可确认这次点击。两个时序常量都按本地列举校准；远程部署（每层级一次 RPC，通常 100–400ms）会落在静默窗口之内、crumb 上却没有按下态——待远程消费方落地时，重新审视该窗口或补上按下反馈。 +- **路径编辑器自我点明，各栏跟随草稿。** 点击即编辑的区域不再是隐形的：栏右端坐着一枚铅笔图标，悬停／聚焦时**整条栏**以编辑器自身的那只框亮起——轮廓与内边距在两种模式下都由栏承载，于是悬停预览的正是点击后出现的那只输入框，区域与输入框互换时也没有任何尺寸变化。编辑器打开期间，各栏跟随草稿，而不是停在它打开那一刻恰好列出的层级——末段对其目录部分所指的层级做前缀过滤，无一匹配的末段解除过滤（还在拼写中的名字不该把正在拼写它的那一栏清空），而其余任何目录部分都会在停顿 250ms 后被扫描，并经由每次导航共用的那套以选中项为锚的双栏落地落定，于是键入路径移动 Miller 视图的方式与 crumb 跳转完全一致——继续键入即下潜、删掉末段即上退——全程不必离开编辑器。**分栏个数才是不变量**：最后一栏永远是路径所指的那一层，其上一层在它旁边，只有展示根会独占一栏。"只要任意一栏碰巧列出了该目录就跳过扫描"是更省事、也是错的规则——删掉一段之后，正在键入的那一层会留在左栏，而它自己的子栏仍立在右边，于是两栏不再读作"我在哪儿、我从哪儿来"。只有最后一栏自己的末段不需要扫描。一种落地形态、两个调用方：提交的路径关闭编辑器并呈现失败，草稿跟随扫描则两者都不做。该扫描是推测性的——键入到一半的目录多数时候读不出来——因此失败时保留最后一次可读的分栏并保持沉默。Enter 仍是权威提交：自提交至落地由它独占视图（同一批按键武装的防抖计时器会被扣住，而不是顶掉这次导航；提交被拒后仍扣住，直到下一次编辑），也只有它把失败呈现出来。有两点是刻意为之。等待以草稿为键，而非以它指名的目录部分为键，于是顶掉在飞扫描的那次按键会重新武装等待，被拒提交之后的编辑也能释放那道扣留；而它读取的分栏是 ref 而非依赖，否则落地会重新武装等待，遇到以不同拼写作答的宿主便会永远扫描下去。以及，走过的路不回退：关闭编辑器——包括取消——都把分栏留在草稿带到的地方，由面包屑指明、Open 的兜底目标随之而动，因为操作者亲眼看着它们移动。若落地卸载了键盘操作者 Tab 停留的那一行，焦点会被重新停回编辑器——Modal 并没有焦点陷阱。另有两条规则保证一次按键只让视图移动一次：这段行走会**等齐两程**，而不套用提交导航的等待上限（推测性扫描没有任何东西在等它，先落单栏再升级恰恰就是它要避免的那次闪动，而且一旦末段按键中止了缓慢的父层级这一程，双栏视图就会永久丢失）；末段也只过滤**最后一栏**——去收窄一个草稿已经走开的分栏，会让视图先因收窄动一次、再因它自己的落地动一次。此外，层级会持续应答产生它的那段目录文本（`scanned`），因为宿主会规范化它收到的东西：`..` 段与 Windows 的正斜杠都会抵达一个自身路径拼写不同的层级；没有这份记忆，这类草稿会每敲一键就重扫一次，而且永远过滤不了。 +- **导航以选中项为锚、安静且有界地落地。** 在展示根之外（与 crumb 头部渲染的是同一塌缩，因此 crumb 与分栏形态永不相左），落地即双栏：重新选中目标在父层级中的实际条目（Windows 上按平台惯例折叠大小写），右侧展示其子项，因此 crumb 跳转读作后退一栏，而不是塌缩成单列。父层级这一程在 200ms 等待上限内落定时，目标与父层级两程以**同一帧**落地——在此之前陈旧视图持续渲染，导航换栏时因此没有中间的单栏闪现——超出该上限则目标即刻单独提交（Enter 提交的导航绝不会被滞塞的父层级扣作人质），迟到的父层级这一程再就地升级这次落地。父层级这一程在落地的 supersession 范围下运行，任何较新的意图都会在线上将其中止（因此在落地窗口内按 Escape 即撤回整次导航）；父层级这一程失败，或被截断的父窗口缺少目标时，都保留单栏落地——升级的存在正是为了锚定选中项，绝不能反而让它悬空。加载指示器遵循同一安静规则：它浮于内容右下角（绝不是会挪动布局的一行；截断／错误行占据左下角，并在扫描期间持续渲染），且仅在扫描超出 300ms 静默窗口后才出现，因此本地列举切换时什么也不显示。行选取被刻意豁免于同一帧规则：选取后立即分栏本身就是其选中态反馈（aria-current、crumb 跟随），而导航除了换栏本身没有任何东西可确认这次点击。三个时序常量——200ms 父层级上限、300ms 静默窗口，以及编辑器的 250ms 草稿停顿——都按本地列举校准；远程部署（每层级一次 RPC，通常 100–400ms）会落在静默窗口之内、crumb 上却没有按下态，而且要先付停顿再付 RPC 分栏才跟上——待远程消费方落地时，三者一并重新审视。 - **符号链接：为可进入性而跟随。** 用 `stat` 探测符号链接（断链／循环→跳过）；面包屑保留操作者导航的逻辑路径，`workspace.create` 在接纳时本就做 realpath 规范化。 - **列举层级有上限，且流式处理。** 单次 `list` 至多返回 `maxEntries` 行（配置项，默认 1000——GitHub 网页端目录列举的同一上限）。层级经 `opendir` 流入一个按名排序、容量 `maxEntries + 1` 的候选窗口，内存保持 O(maxEntries)，可进入性探测只触及窗口内候选；线上 `DirectoryListing` 携带必填的 `truncated` 标志，让客户端明示不完整而不是静默缺尾。窗口内的断链符号链接不从窗口外回填——发生过驱逐本身已把层级标记为截断。窗口插入为二分查找、满窗尾部单次比较即拒绝（超大层级不能为每个 dirent 付出一次全窗扫描），且 `list(path, signal)` 透传载体的请求信号，滞塞网络目录的扫描不会在调用方断连后继续存活——扫描中的每个 await（打开、每次读取、每次符号链接探测）都与信号赛跑，中止路径放弃而非等待 close（Node 会把 close 排在在飞读取之后），被放弃的 settlement 全部吞掉，清理不会以未处理拒绝的形式冒出。无上限的层级对超大或恶意构造的目录就是内存／响应性漏洞。 - **全盘可浏览，不做 roots 配置。** `workspace.create` 接受任意路径且 API 本就提供驱动 bash 的方法，浏览根只会是 UX 范围而非边界；没有消费方的可配置性过不了证据门槛。等到有部署需要再做。 @@ -34,6 +35,9 @@ web GUI 的"打开本地文件夹"流程被焊死在一种交互上：`host.pick - **引入文件管理器／盘符枚举依赖。** 按上文调研否决；依赖政策要求记录于此。 - **动作标签随状态翻转的"显示隐藏"开关（"隐藏隐藏文件"）。** 否决：会翻转的动作标签在状态与动作之间有歧义，还把否定叠了两层；固定标签加按下态呈现一次说清两者。 - **纯 relatedTarget 失焦取消（不做 mousedown 抑制）。** 否决：Safari 在指针按下时不给按钮聚焦，点击触发的 focusout 因而携带空 `relatedTarget`，会在点击落地前就取消编辑器；编辑期作用的 mousedown 抑制加上锚定卡片的 relatedTarget 守卫才能同时覆盖指针与键盘路径。 +- **在 Miller 视图上方常驻一个路径输入框。** 否决：面包屑本就在回答"我在哪儿"，再常驻一个字段是重复回答，还要从 500px 卡片里挪走一行——那是列需要的高度。图标加悬停亮起的区域，把这个入口放在了已经回答该问题的那一栏上。 +- **每敲一个键就扫描草稿，或只在 Enter 时扫描。** 每键扫描：走完一段路径就是每个字符一次列举，其中多数目录操作者只是路过而非停留。只在 Enter 时扫描（最初落地的行为）：整个编辑过程中各栏与所键入文本各说各话——正是本条所回应的抱怨。250ms 的停顿把扫描收敛为"键入真正停下来的每个目录一次"。 +- **前缀无一匹配时清空该栏（最初落地的行为）。** 否决：名字敲到一半时"无匹配"才是常态，于是恰恰在操作者需要它确认名字时把栏清空了；解除过滤保住了层级的可读性，代价只是短暂的宽松。 - **在 `DirectoryListing` 上增设线上 `separator` 字段（宿主标注 `path.sep`）。** 延期而非否决：它才是权威形态——含反斜杠的 POSIX 家目录会击穿 `listing.home` 启发式——但它触及 seam 类型与每个后端；browse 客户端的 `separatorOf` 挂着指向本方案的 TODO，直到下次安排线上变更。 ## 后果 diff --git a/.agents/notes/implemented/architecture/2026-07-28-launcher-owned-resume-identity.md b/.agents/notes/implemented/architecture/2026-07-28-launcher-owned-resume-identity.md deleted file mode 100644 index e114317163..0000000000 --- a/.agents/notes/implemented/architecture/2026-07-28-launcher-owned-resume-identity.md +++ /dev/null @@ -1,64 +0,0 @@ -# Agent Note: Launcher-owned session identity and exit line - -Status: implemented - -English | [中文](2026-07-28-launcher-owned-resume-identity.zh.md) - -## Problem - -Two facts a launcher owns were shipped as deployment config keys on the TUI app bundle: `resumeSessionId` (which session `main` binds to) and `resumeCommand` (the exit hint template, with `{session}` interpolated). Neither varies by deployment — both are properties of how the process was invoked, which only the launcher knows. - -Routing them through YAML made them silently droppable. `@cordisjs/plugin-include` applies a targeted patch by replacing whole top-level keys (`target[key] = value`), so a personal `~/.dsh/config.yaml` patching the `tui-agent` entry's `config` replaces the shipped block entirely. A user overlay written to change provider and model therefore deleted every resume key it did not restate, and nothing reported it: absent `resumeCommand` legitimately means "no fallback configured". - -Both failures were live in one real overlay. The exit hint stopped printing, because the overlay omitted `resumeCommand`. Worse, the overlay carried `resumeSessionId: !!js process.env.RESUME_SESSION_ID` — a stale line from before [the env-var bridge was removed](../../archived/architecture/2026-07-24-dsh-commander-argument-adapter.md) — which overwrote the shipped `!!js "typeof resumeSessionId === 'string' ? …"` intake with a read of a variable nothing sets. `dsh --resume ` then started a *fresh* session and said nothing, reproduced directly: the banner showed a newly minted id, not the requested one. The [`dsh meta`](../feature/2026-07-28-dsh-meta-source-workspace.md) note had recorded this silent resume as an unexplained pre-existing defect; the overlay's shallow replacement is the cause. - -A config key cannot express these facts safely, because the deployment is not the authority on them. - -## Decision - -Session identity and the exit line are launcher-owned context slots, provided before any Loader entry mounts. Neither appears in any `cordis.yml` nor in any plugin's `Config`. - -Both sit beside the existing `tuiResumeHost` host capability, which set the precedent — a resume host has always been a provided capability rather than config. Each slot is declared by the package that consumes it: - -- `CONFIGURED_AGENT_IDENTITIES_KEY` (`dsh-agent-loop`) carries launcher identities keyed by configured-agent `id`, each a `LauncherAgentIdentity` (`{ id: SessionId, resume: boolean }`). `agent-loop` applies the matching identity over its configured agent, replacing both identity keys, and takes the history-loading `resumeSessionId` path only when `resume` is set, because that path requires an existing log and fails loud without one. An absent slot leaves the configured identity untouched. The `tui` row resolves the same id through its own `sessionId` key, so the front door renders exactly the agent that was bound. -- `TUI_GOODBYE_MESSAGE_KEY` (`dsh-tui`) carries the complete line printed once the terminal is released on exit. Absent prints nothing. - -Identity belongs to `agent-loop` because that is the plugin which creates configured agents, and because a patch replaces a row's whole `config`: an overlay repointing the agent row's model route would erase a launcher-set identity key. See [the shared-base overlay note](../simplification/2026-07-29-shared-base-config-overlays.md). - -`apps/cli` mints or selects the id and builds the line from the invocation it is reproducing, sharing one `resumeArgs` helper with the `/resume` execve handoff so the printed command and the in-place handoff cannot diverge. The line now names `--config` when one was passed, and reproduces `dsh meta --resume ` in meta mode — closing the mode-aware hint deferred by the `dsh meta` note, where a copied hint previously only worked from the checkout. - -**`ctx.provide` is the only channel from launcher argv into a Loader-mounted plugin.** Config `!!js` expressions evaluate as `with (entry.ctx) { eval(expr) }` (`vendor/loader/src/config/utils.ts`), so a bare identifier resolves against the entry's context and nothing else reaches it. The slot therefore cannot be removed while the app bundle is mounted from YAML; what changes is that it is now internal launcher↔app plumbing instead of a documented key a config author must wire correctly. - -The message is a plain string, not a callback. That forces the launcher to know the id before boot, which is why minting moved out of the app bundle — and it keeps exit free of awaited work after the terminal is released. - -The TUI owns rendering, not wording: it applies `displayText` before its own `palette.muted`, so a hostile `--config` path cannot inject terminal escapes into the exit line. Sanitizing means the launcher cannot embed its own ANSI. - -## Alternatives considered - -**Keep the keys and add built-in defaults in the app bundle.** Rejected: a default in code survives an overlay, but two ways to state one fact remain, and a config author can still set the key wrong — which is exactly how the stale `process.env.RESUME_SESSION_ID` line disabled resume. - -**Merge the app bundle into `apps/cli` and delete the slot entirely.** Rejected here, then [adopted later](../simplification/2026-07-29-shared-base-config-overlays.md) in a form this note did not consider: the composition moved into flat config files (`apps/cli/config/base.cordis.yml` plus a per-surface overlay) rather than into CLI code, so it never entered the `v8 ignore` process-wiring block, and the overlay extension points survive as ordinary row patches. The slot itself was not deleted — it moved to `dsh-agent-loop`, because a launcher fact still cannot travel through a replaceable config key. - -**Put the goodbye message on `TuiResumeHost`.** Rejected: an exit line is not a handoff capability, and a host that cannot replace its process may still want to print one. They are independent slots. - -**Have the host supply only the command text and let the TUI keep the `To resume this session:` prefix.** Rejected: the TUI would retain resume vocabulary for a string it no longer understands, and meta mode proves the launcher is the only component that knows what the command should say. - -**Let the TUI keep suppressing the line until the session is durably persisted.** Rejected: that check is why the exit path queried persistence and swallowed listing failures. A plain string cannot consult persistence, and misuse now fails loud through `agent-loop/config-start-failed` rather than silently resuming nothing. - -**A callback (`goodbyeMessage(agent)`) so the host could decide at exit time.** Rejected: it restores async work after `ui.stop()`, reintroducing a hang risk during teardown for a string that is already knowable at boot. - -## Consequences - -- Removing two published `Config` keys is a breaking config change: a stale config naming either now fails schema validation at boot instead of degrading silently. Intended, and acceptable pre-release. -- `TuiResumeHost` is unchanged, but `TuiRuntime` gains `goodbyeMessage`; `apps/cli` is the only provider. -- The exit line prints even for a session with no log (launch, quit immediately). Using it then fails loud rather than starting a surprise session. This is the deliberate cost of dropping the persistence check. -- `dsh-tui` no longer reads `sessionPersistence` at all: `currentResumeCommand`, `listWorkspaceSessions`, and its swallowed-error path are deleted, and the `/resume` selector's `sessionQuery` reads are now the only session discovery in the TUI. -- The launcher mints session ids for its own app, so a non-CLI host that provides no slot keeps the bundle's own minting. - -## Testing - -`packages/ui/tui/tests/tui.spec.ts` pins the printed line, the absent-slot silence, and escape sanitization of a hostile message; the former two exit-suppression tests are replaced, since suppression is the behavior this change removes. `packages/core/agent-loop/tests/` drives the identity slot for the resume, launcher-minted, and no-slot cases. - -The load-bearing coverage is `apps/cli/tests/tui-keyless-smoke.e2e.ts`, which launches the real `apps/cli/src/bin.ts` in a PTY: one test asserts the exit line carries `--config`, and a regression test seeds a personal `config.yaml` that replaces the entire `agent-loop` config block and asserts the line still prints — encoding "an overlay cannot drop resume" as an executed contract rather than a comment. - -Verified live in tmux against the real personal overlay: the defect reproduced on unmodified staging (requested id ignored, fresh id in the banner), and on this branch the same overlay yields a printed exit line, a `--resume` that restores the prior turn, and a `/resume` selector marking the session `current · live · persisted`. A wrong id now fails loud. diff --git a/.agents/notes/implemented/architecture/2026-07-28-launcher-owned-resume-identity.zh.md b/.agents/notes/implemented/architecture/2026-07-28-launcher-owned-resume-identity.zh.md deleted file mode 100644 index e4078023cb..0000000000 --- a/.agents/notes/implemented/architecture/2026-07-28-launcher-owned-resume-identity.zh.md +++ /dev/null @@ -1,64 +0,0 @@ -# Agent Note：由启动器持有的会话身份与退出行 - -Status: implemented - -[English](2026-07-28-launcher-owned-resume-identity.md) | 中文 - -## Problem - -有两项本应由启动器持有的事实，却被作为 TUI 应用组合包上的部署配置键交付：`resumeSessionId`（`main` 绑定到哪个会话）与 `resumeCommand`（退出提示的模板，其中 `{session}` 会被插值）。二者都不随部署而变——它们都是进程被如何调用的属性，而这一点只有启动器知道。 - -把它们经由 YAML 传递，使其可被静默丢弃。`@cordisjs/plugin-include` 施加定向补丁的方式是替换整个顶层键（`target[key] = value`），因此一份对 `tui-agent` 条目的 `config` 打补丁的个人 `~/.dsh/config.yaml`，会把交付时的整块内容整体替换掉。于是，一份为改动 provider 和 model 而写的用户 overlay，会删掉它未重述的每一个 resume 键，且没有任何东西报告这一点：缺失 `resumeCommand` 合法地意味着「未配置回退」。 - -两处失效在同一份真实的 overlay 中同时存在。退出提示不再打印，因为该 overlay 省略了 `resumeCommand`。更糟的是，该 overlay 带着 `resumeSessionId: !!js process.env.RESUME_SESSION_ID`——一行来自 [env 变量桥被移除](../../archived/architecture/2026-07-24-dsh-commander-argument-adapter.md)之前的陈旧代码——它用一次对某个无人设置的变量的读取，覆盖掉了交付时的 `!!js "typeof resumeSessionId === 'string' ? …"` 入口。此后 `dsh --resume ` 会开启一个*全新*会话且什么都不说，并被直接复现：banner 显示的是一个新铸造的 id，而非所请求的那个。[`dsh meta`](../feature/2026-07-28-dsh-meta-source-workspace.md) note 曾把这次静默的 resume 记为一处无法解释的既有缺陷；而 overlay 的浅层替换正是其成因。 - -一个配置键无法安全地表达这些事实，因为部署方并非它们的权威。 - -## Decision - -会话身份与退出行是由启动器持有的上下文槽位，在任何 Loader 条目挂载之前提供。二者都不出现在任何 `cordis.yml` 中，也不出现在任何插件的 `Config` 中。 - -这两个槽位与既有的 `tuiResumeHost` 宿主能力并列，后者确立了先例——resume 宿主一直是一项被提供的能力，而非配置。每个槽位都由消费它的包声明： - -- `CONFIGURED_AGENT_IDENTITIES_KEY`（`dsh-agent-loop`）按所配置 agent 的 `id` 承载启动器身份，每项为一个 `LauncherAgentIdentity`（`{ id: SessionId, resume: boolean }`）。`agent-loop` 将匹配的身份覆盖到其所配置的 agent 上，替换两个身份键；并且仅当 `resume` 被置位时才走加载历史的 `resumeSessionId` 路径，因为该路径要求存在一份日志、否则会明确报错。槽位缺失则保留配置中的身份不变。`tui` 配置项通过自身的 `sessionId` 键解析同一个 id，因此前端入口渲染的正是被绑定的那个 agent。 -- `TUI_GOODBYE_MESSAGE_KEY`（`dsh-tui`）承载退出时终端释放后打印一次的完整行。缺失则什么都不打印。 - -身份归属于 `agent-loop`，因为它才是创建所配置 agent 的插件；也因为 patch 会整体替换配置项的 `config`：重新指向 agent 配置项模型路由的 overlay 会抹掉启动器设置的身份键。参见[共享 base overlay note](../simplification/2026-07-29-shared-base-config-overlays.md)。 - -`apps/cli` 铸造或选定 id，并依据它所复现的那次调用构建该行，与 `/resume` 的 execve 移交共用同一个 `resumeArgs` 助手，从而使打印出的命令与原地移交不会分歧。该行现在会在传入了 `--config` 时命名它，并在 meta 模式下复现 `dsh meta --resume `——从而收口了 `dsh meta` note 所推迟的随 mode 变化的提示，在那里被复制的提示此前只有在检出目录中才有效。 - -**`ctx.provide` 是从启动器 argv 进入被 Loader 挂载的插件的唯一通道。** 配置的 `!!js` 表达式会以 `with (entry.ctx) { eval(expr) }`（`vendor/loader/src/config/utils.ts`）求值，因此一个裸标识符会针对该条目的上下文解析，别无它物可达。于是只要应用 bundle 仍从 YAML 挂载，这个槽位就无法被移除；变化之处在于它现在是启动器↔应用之间的内部管线，而不再是一个配置作者必须正确接线的、有文档记载的键。 - -该消息是一个纯字符串，而非回调。这迫使启动器在启动前就知道 id，也正是铸造从应用 bundle 中移出的原因——并且它让退出在终端释放之后免于任何被 await 的工作。 - -TUI 持有渲染，而非措辞：它在自己的 `palette.muted` 之前先应用 `displayText`，因此一个恶意的 `--config` 路径无法把终端转义序列注入退出行。做净化意味着启动器无法嵌入自己的 ANSI。 - -## Alternatives considered - -**保留这些键，并在应用组合包中加入内建默认值。** 拒绝：代码中的默认值能在 overlay 下存活，但表达同一事实的两种途径依然并存，而配置作者仍可把键设错——这正是那行陈旧的 `process.env.RESUME_SESSION_ID` 使 resume 失效的方式。 - -**把应用组合包合并进 `apps/cli` 并彻底删除该槽位。** 此处拒绝，但后来以本 note 未曾设想的形式[被采纳](../simplification/2026-07-29-shared-base-config-overlays.md)：组合被搬进平铺的配置文件（`apps/cli/config/base.cordis.yml` 加各 surface 一份 overlay），而非搬进 CLI 代码，因此从未进入 `v8 ignore` 进程接线块，overlay 的扩展点也作为普通配置项 patch 保留了下来。槽位本身并未被删除——它迁移到了 `dsh-agent-loop`，因为启动器的事实依然不能经由一个可被整体替换的配置键传递。 - -**把 goodbye 消息放到 `TuiResumeHost` 上。** 拒绝：退出行不是一项移交能力，而一个无法替换自身进程的宿主仍可能想要打印一行。它们是相互独立的槽位。 - -**让宿主只提供命令文本，而由 TUI 保留 `To resume this session:` 前缀。** 拒绝：TUI 将为一个它已不再理解的字符串保留 resume 词汇，而 meta 模式证明启动器才是唯一知道该命令应当说什么的组件。 - -**让 TUI 继续在会话被持久化之前抑制该行。** 拒绝：这项检查正是退出路径要查询持久化并吞掉列举失败的原因。一个纯字符串无法查询持久化，而误用现在会经由 `agent-loop/config-start-failed` 明确报错，而不是静默地恢复了个空。 - -**用一个回调（`goodbyeMessage(agent)`）让宿主能在退出时决定。** 拒绝：它会在 `ui.stop()` 之后恢复异步工作，为一个在启动时就已可知的字符串，重新引入拆解期间的挂起风险。 - -## Consequences - -- 移除两个已发布的 `Config` 键是一次破坏性配置变更：一份命名了任一键的陈旧配置，现在会在启动时的 schema 校验中明确报错，而不再静默降级。这是有意为之，且在预发布阶段可以接受。 -- `TuiResumeHost` 保持不变，但 `TuiRuntime` 新增 `goodbyeMessage`；`apps/cli` 是唯一的提供方。 -- 即便某会话没有日志（启动后立即退出），退出行也会打印。此时使用它会明确报错，而不是开启一个意外的会话。这是丢弃持久化检查的有意代价。 -- `dsh-tui` 完全不再读取 `sessionPersistence`：`currentResumeCommand`、`listWorkspaceSessions` 及其吞错路径都被删除，`/resume` 选择器的 `sessionQuery` 读取如今是 TUI 中唯一的会话发现途径。 -- 启动器为其自身的应用铸造会话 id，因此一个不提供任何槽位的非 CLI 宿主，仍保留 bundle 自带的铸造逻辑。 - -## Testing - -`packages/ui/tui/tests/tui.spec.ts` 钉住打印出的行、槽位缺失时的静默，以及对恶意消息的转义净化；此前那两个退出抑制测试被替换，因为抑制正是本次改动移除的行为。`packages/core/agent-loop/tests/` 为 resume、启动器铸造与无槽位三种情形驱动身份槽位。 - -承重的覆盖是 `apps/cli/tests/tui-keyless-smoke.e2e.ts`，它在一个 PTY 中拉起真实的 `apps/cli/src/bin.ts`：一个测试断言退出行携带 `--config`，一个回归测试植入一份个人 `config.yaml` 来替换整块 `agent-loop` 配置块并断言该行仍会打印——把「overlay 不能丢掉 resume」编码为一条被执行的契约，而非一句注释。 - -在 tmux 中针对真实的个人 overlay 做过实测：该缺陷在未修改的 staging 上复现（所请求的 id 被忽略，banner 里是新的 id），而在本分支上同一份 overlay 会产出一行打印的退出行、一个能恢复上一轮次的 `--resume`，以及一个把该会话标记为 `current · live · persisted` 的 `/resume` 选择器。错误的 id 现在会明确报错。 diff --git a/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.i18n.yaml new file mode 100644 index 0000000000..047cccbce3 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.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/2026-07-29-projected-token-usage-and-request-context.md +2026-07-29-projected-token-usage-and-request-context.md: 1e2c5ff067928620dee3d0937c247bec245e34f2 +2026-07-29-projected-token-usage-and-request-context.zh.md: 811d92e134b1df0fc6725e6c8d38b37efb57b3aa diff --git a/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md new file mode 100644 index 0000000000..1e2c5ff067 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md @@ -0,0 +1,59 @@ +# Agent Note: Projected token usage and context occupancy + +Status: implemented + +English | [中文](2026-07-29-projected-token-usage-and-request-context.zh.md) + +## Problem + +The Web stats line derived token totals from the currently loaded conversation nodes. That window is paged, so scrolling changed the totals, and compaction replaces visible content without preserving the billing behind it. Durable provider billing needs a source that survives both. + +Context occupancy needs a numerator and a denominator that no existing surface carried to the browser: the prompt size of the latest request, and the capacity of the route it used. + +## Decision + +Both values are ordinary durable session-projection state. `@deepseek-ai/dsh-token-meter` registers two units when `ctx.sessionProjections` is present. + +`tokenUsage` folds the complete durable log into uncached input, output, cache-read, and cache-write buckets. An `assistant/chunk` usage sample survives a later failed request; an `assistant/message` usage value for the same `(turn, step)` replaces the earlier sample instead of double-counting it. Reasoning stays an output subdivision. Compaction and surface replacement do not erase earlier billing. + +`contextPressure` carries optional `pressureTokens` — the newest provider-reported prompt size, summing uncached input plus cache reads and writes, excluding output — and optional `contextWindow` from the newest `request/context` record. Neither field is synthesized before its source exists. + +`request/context` is a new log-only session event recording registration-bound metadata for the route a request resolved to. AgentLoop appends it inside the step beside `request/header`, from the context metadata `prepareCall()` now returns alongside the resolved config — the same registration-bound lookup that already validated reasoning, so no second resolve happens. It is skipped when provider, model, and capacity all match the previous record. A route whose adapter advertises no capacity is recorded with `contextWindow` absent, clearing an older route's denominator. + +Capacity deliberately stays out of `EpochHeader`. That type is the reconstruction contract — what a request was built from — and `headerEquals` compares it field-wise to decide whether a snapshot is a real `change`. Capacity is adapter metadata describing a route, so placing it there would let a capacity change masquerade as a request-envelope change and would drag it into the loop's reconstruction invariant. + +Both units ride the standard projection lifecycle: history tail baselines, `session/projection` live frames, higher-seq-wins client storage, JSON checkpoints, cache recovery, and unit unload. There is no token-specific history field, mux frame, projector, revision counter, or client fence. + +The Web `StatsLine` reads both through the standard `useProjection` seat. Window nodes still supply turn and step counts plus LLM and tool wall times — those answer "what is on screen" and are correctly window-scoped. Durable token and context groups remain when compaction leaves no visible assistant step. Cache writes count in billed input and in the cache-hit denominator. A deployment without token-meter drops the token groups; occupancy stays hidden until both pressure and capacity are known. + +## Context occupancy is approximate, and that is the decision + +`pressureTokens` and `contextWindow` are independent last-wins fields, not one atomic observation. Switching models pairs a fresh capacity with the previous route's pressure until the next request reports usage, and the numerator describes the last request rather than the surface as it currently stands. + +This was accepted deliberately. An occupancy percentage is a user-facing reference figure: nothing in the harness makes decisions from it, and compaction reads `measure()` directly instead. The TUI status line has always computed occupancy this way, dividing a `measure()` total by a capacity resolved separately for the selected model — so an atomic variant here would have been the outlier, not the norm. + +Reviewers should not treat the non-atomicity as a defect awaiting a fix. A consumer that genuinely needs an exact same-boundary figure should call `ctx.tokenMeter.measure()` at its own request boundary, where both values are available together, rather than read this projection. + +## Alternatives considered + +**An atomic request-boundary snapshot delivered as a transient mux frame (implemented, then rejected).** An earlier revision of this branch emitted `session/model-request`: one non-replayable frame carrying `contextTokens` and `contextWindow` measured at the same `agent/model-request` boundary. Being the only non-replayable class on the mux stream is what broke it. Host and mux are independent SSE streams with no cross-stream ordering, so a request emitted before a removal could arrive after `host/session-removed` and revive a dead session's telemetry, while a legitimate request for a new lifecycle reusing the same id could be fenced by a late removal. `session/subscribed` is not lifecycle proof — it says a queue began subscribing to an id, not that a new in-memory session replaced an older one — and `lastSeq` is a durable watermark two lifecycles can share. A correct fix required a monotonic lifecycle generation on the frame, on subscription, and on removal, plus a client watermark comparison. + +That cost bought a worse display: occupancy went blank after every reconnect and never moved while a conversation grew. It also made ApiProxy a measurement site calling the O(surface) `measure()` on every request, and expressed reconnect state through a synthetic `cancelled` open error the UI had to special-case. + +**Fold the loaded node window in React.** Cannot survive pagination or compaction, and makes a presentation package reconstruct log semantics. + +**Publish usage only with final assistant messages.** A request that reports a usage chunk and then fails would lose its billing. + +**Resolve capacity inside token-meter.** The package documents itself as independent of model routing and is otherwise a pure reader that never appends to the log. AgentLoop already holds the resolved metadata where the header is written. + +**Extend the `session.models` RPC with capacity.** The handler already resolves and discards it, so the field is nearly free — but `StatsLine` lives in `ui-conversation` while the model directory lives in `ui-model`, and `ui-conversation` cannot depend on `ui-model`. Delivering it would have required either a second dock entry splitting one text row across two plugins, or a cross-plugin store write. + +**Add a context circle beside the model selector.** That placement suggests selected-model state. The stats line carries the figure without a duplicate UI or data path. + +## Consequences + +Token totals stay stable across pagination, compaction, replay, restart, and reconnect, because they are ordinary durable projection state recovered through the generic paths. The cross-stream reordering race is gone by construction rather than fenced. + +Occupancy is approximate in the ways documented above. It is available immediately after restore or reconnect, since both fields are durable, at the cost of describing the last recorded request rather than an exact current boundary. + +Each session log gains one small `request/context` record per route or advertised-capacity change. The token-meter projection is the canonical owner of durable session-projection usage semantics; the TUI retains its live per-step map because it does not mount the generic projection seam, and the standalone browser fixture mirrors the unit. ApiProxy carries no token-specific code, owns no per-session metrics cache, and performs no measurement. The browser keeps two generic projection values and no connection-local telemetry, and streaming text deltas still do not force the stats line to recompute. diff --git a/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.zh.md b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.zh.md new file mode 100644 index 0000000000..811d92e134 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.zh.md @@ -0,0 +1,59 @@ +# Agent Note: token 用量投影与上下文占用率 + +Status: implemented + +[English](2026-07-29-projected-token-usage-and-request-context.md) | 中文 + +## 问题 + +Web 统计行原先从当前已加载的会话节点推导 token 总量。该窗口是分页的，因此滚动会改变总量；压缩（compaction）又会替换可见内容，而不保留其背后的计费用量。持久的提供方计费用量需要一个能同时经受这两者的数据源。 + +上下文占用率需要一个分子和一个分母，而这两者都不曾由任何既有接口送达浏览器：最新一个请求的提示词规模，以及该请求所用路由的容量。 + +## 决策 + +这两个值都是普通的持久会话投影状态。当 `ctx.sessionProjections` 存在时，`@deepseek-ai/dsh-token-meter` 会注册两个单元。 + +`tokenUsage` 将完整持久日志归并为未缓存输入、输出、缓存读取和缓存写入四类计数项。即使后续请求失败，`assistant/chunk` 用量样本仍会保留；同一 `(turn, step)` 的 `assistant/message` 用量值会替换先前样本，不会重复计数。推理（reasoning）仍是输出的细分项。压缩和表层替换不会抹除先前的计费用量。 + +`contextPressure` 携带可选的 `pressureTokens`（提供方报告的最新提示词规模，为未缓存输入加缓存读取与写入之和，不含输出），以及来自最新一条 `request/context` 记录的可选 `contextWindow`。在各自来源出现前，两个字段都不会被合成。 + +`request/context` 是新增的仅入日志会话事件，记录请求所解析到的路由的、绑定注册项的元数据。AgentLoop 在步骤内紧随 `request/header` 追加它，数据取自 `prepareCall()` 现在与已解析配置一并返回的上下文元数据：正是那次已经校验过推理的、绑定注册项的查询，因此不会发生第二次解析。当提供方、模型和容量都与上一条记录相同时会跳过。适配器不公布容量的路由会以缺失 `contextWindow` 的形式记录，从而清除较早路由的分母。 + +容量刻意不进入 `EpochHeader`。该类型是重建契约，即请求由什么构建而成，而 `headerEquals` 会逐字段比较它，以判定某个快照是否真的是一次 `change`。容量是描述路由的适配器元数据，把它放进去会让容量变化伪装成请求封装的变化，还会把它拖进 AgentLoop 的重建不变式。 + +两个单元都沿用标准投影生命周期：历史尾页基线、`session/projection` 实时帧、seq 高者胜的客户端存储、JSON 检查点、缓存恢复和单元卸载。系统没有任何 token 专用的历史字段、mux 帧、投影器、修订计数器或客户端栅栏。 + +Web `StatsLine` 通过标准 `useProjection` 席位读取两者。窗口内节点仍提供轮次和步骤计数，以及 LLM（大语言模型）与工具的墙钟时间：它们回答的是「屏幕上有什么」，按窗口作用域正是正确的。压缩使可见 assistant 步骤归零后，持久 token 与上下文分组仍会保留。缓存写入会计入计费输入和缓存命中率分母。未部署 token-meter 时会去掉 token 分组；只有压力与容量都已知时才显示占用率。 + +## 上下文占用率是近似值，而这正是决策本身 + +`pressureTokens` 与 `contextWindow` 是两个各自后者胜的独立字段，不是一次原子观测。切换模型时，新容量会与上一路由的压力配对，直到下一个请求报告用量为止；分子描述的是最后一个请求，而不是此刻的表层。 + +这是刻意接受的结果。占用率百分比是面向用户的参考数字：harness 中没有任何环节依据它做决策，压缩改为直接读取 `measure()`。TUI 状态行一直以这种方式计算占用率，即用 `measure()` 总量除以为所选模型单独解析出的容量；因此在这里做成原子版本才是异类，而不是常态。 + +评审人不应把这种非原子性当作待修的缺陷。确实需要同一边界精确数字的消费方，应在自己的请求边界调用 `ctx.tokenMeter.measure()`，那里两个值同时可得，而不是读取该投影。 + +## 备选方案 + +**以临时 mux 帧交付请求边界上的原子快照（已实现，随后否决）。** 本分支较早的一个修订版会发出 `session/model-request`：一个不可回放的帧，携带在同一个 `agent/model-request` 边界测得的 `contextTokens` 与 `contextWindow`。真正让它失效的，是它成了 mux 流上唯一的不可回放类别。Host 流与 mux 流是两条独立的 SSE（Server-Sent Events）流，彼此之间没有顺序保证：在移除之前发出的请求可能在 `host/session-removed` 之后才到达，让一个已死会话的遥测数据复活；而复用同一 id 的新生命周期的合法请求，又可能被一条迟到的移除拦下。`session/subscribed` 不能证明生命周期：它只说明某个队列开始订阅某个 id，而不说明新的内存会话替换了较早的会话；`lastSeq` 则是两个生命周期可以共用的持久水位线。正确的修法需要在帧上、订阅上和移除上都带一个单调递增的生命周期代次，再加上一次客户端水位线比较。 + +这份代价换来的是更差的显示：占用率在每次重连后变为空白，而且会话增长期间从不移动。它还把 ApiProxy 变成一个测量点，每个请求都要调用 O(surface) 的 `measure()`，并通过一个 UI 必须特殊处理的、连接打开时的合成 `cancelled` 错误来表达重连状态。 + +**在 React 中归并已加载的节点窗口。** 无法跨分页或压缩保留数据，还会迫使展示包（package）重建日志语义。 + +**仅随最终 assistant 消息发布用量。** 如果请求报告一个用量分片后失败，就会丢失自己的计费用量。 + +**在 token-meter 内部解析容量。** 该包自述与模型路由无关，且在其他方面是一个从不向日志追加内容的纯读取方。AgentLoop 在写入请求头的位置已经持有已解析的元数据。 + +**为 `session.models` RPC 增加容量字段。** 其处理器已经解析出容量又将其丢弃，因此这个字段几乎是免费的；但 `StatsLine` 位于 `ui-conversation`，模型目录位于 `ui-model`，而 `ui-conversation` 不能依赖 `ui-model`。要送达它，就得增加第二个 dock 条目、把一行文本拆到两个插件里，或者做一次跨插件的 store 写入。 + +**在模型选择器旁增加上下文圆环。** 该位置会让人以为这是所选模型的状态。统计行可以承载该数字，无需引入重复的 UI 或数据路径。 + +## 后果 + +token 总量在分页、压缩、回放、重启和重连期间保持稳定，因为它们是通过通用路径恢复的普通持久投影状态。跨流重排序竞态从构造上就不存在，而不是被栅栏挡住。 + +占用率在上文记录的意义上是近似值。由于两个字段都是持久的，它在恢复或重连后立即可用；代价是它描述的是最后一条已记录的请求，而不是精确的当前边界。 + +每个会话日志会为每次路由或已公布容量变化增加一条小型 `request/context` 记录。token-meter 投影是持久会话投影用量语义的正典所有方；TUI 未挂载通用投影 seam，因此保留自己的实时逐步骤 map，而独立浏览器 fixture 会镜像该单元。ApiProxy 不携带任何 token 专用代码，不拥有逐会话指标缓存，也不执行测量。浏览器只保留两个通用投影值，不保留连接本地的遥测数据；流式文本增量仍不会迫使统计行重新计算。 diff --git a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.i18n.yaml index a56a91c980..2efe235e28 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.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/2026-07-30-client-locale-full-rollout.md -2026-07-30-client-locale-full-rollout.md: c080d9f240d4533ecd9694ceecfada8662c46425 -2026-07-30-client-locale-full-rollout.zh.md: 062d982e3d7ea62f3ca4c8fedb842e8336f0852c +2026-07-30-client-locale-full-rollout.md: 09baf5876029295f7a80b6a0fe6a6395d98f406c +2026-07-30-client-locale-full-rollout.zh.md: 806916aea15a21fd24fdfc4654976b3c4577a675 diff --git a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.md b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.md index c080d9f240..09baf58760 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.md +++ b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.md @@ -14,7 +14,7 @@ After the typed locale standard seat landed (`locale:` on register → framework **Component copy rides the standard `t` seat; deep children take `t` as a plain prop** typed `XxxProps['t']`. The dictionary canon is unchanged: `zh satisfies Record` is the key source and `en satisfies Record` locks bilingual balance. -**Zero-cordis atoms (ui-primitives) take copy as props**: `labels` on `TerminalBlock`/`JsonTree`, `copyLabel`/`copiedLabel` on `CodeBlock`, `codeLabels` on `MarkdownText`, `truncatedLabel` on `JsonBlock`, `label` on `ConnectionBanner`, `closeLabel` on `Modal` — defaults are the previous hardcoded strings, so a consumer passing nothing renders byte-identical output. Localized plugins pass dictionary-driven labels from their own `t` seat; call sites passing object props memoize them on the `t` identity (`MarkdownText` caches its component table on the `codeLabels` identity). +**Zero-cordis atoms (ui-primitives) take copy as props**: `copyLabel`/`copiedLabel` on `HoverCard`, `labels` on `TerminalBlock`/`JsonTree`, `copyLabel`/`copiedLabel` on `CodeBlock`, `codeLabels` on `MarkdownText`, `truncatedLabel` on `JsonBlock`, `label` on `ConnectionBanner`, `closeLabel` on `Modal` — defaults are the previous hardcoded strings, so a consumer passing nothing renders byte-identical output. Localized plugins pass dictionary-driven labels from their own `t` seat; call sites passing object props memoize them on the `t` identity (`MarkdownText` caches its component table on the `codeLabels` identity). **The non-translation boundary (deliberate decisions, not debt):** @@ -25,7 +25,7 @@ After the typed locale standard seat landed (`locale:` on register → framework **Derivation layers stay pure; localization happens at render.** ui-workspace's `relativeTime` returns structured `{unit, n}` composed with dictionary templates by the renderer; blank sessions and the Ungrouped bucket keep their stored titles, with the renderer substituting localized copy off the `blank` flag / absent `workspaceId`; **blank rows are excluded from search entirely** (a bilingual display title cannot match a single-language query stably). Dates use no Intl: format templates live in the dictionaries (message clock `clock.md`/`clock.ymd`, workspace hover `date.ymd`) and the formatters take `t` as a parameter, staying pure. -**Test and e2e doctrine**: `makeTranslate(...dicts)` (dsh-client-test-runtime) mirrors the service lookup chain (first-dict-wins, key fallback, `{name}` interpolation); component specs stub the `t` seat with it, typed against real props seats. Web e2e uniformly opens through `newEnglishPage` (pins `dsh.locale=en` before boot) and the built-boot snapshot pins the same — goldens are immune to localization migrations; the settings language-switch scenario deliberately bypasses the helper to cover the zh default. +**Test and e2e doctrine**: `makeTranslate(...dicts)` (dsh-client-test-runtime) mirrors the service lookup chain (first-dict-wins, key fallback, `{name}` interpolation); component specs stub the `t` seat with it, typed against real props seats. Web e2e uniformly opens through `newEnglishPage` (pins `dsh.locale=en` before boot) and the built-boot snapshot pins the same — goldens are immune to localization migrations; the settings language-switch scenario bypasses the helper and opens a `zh-CN` browser, since the initial locale follows `navigator` ([browser-derived initial locale](../feature/2026-07-31-browser-derived-initial-locale.md)). The "apply layer subscribes to `locale/change` and re-registers for fresh labels" mechanism in the [settings/locale/theme layering note](../../proposed/architecture/2026-07-25-client-settings-locale-theme.md) is superseded by this decision (thunk + revision lifecycle). diff --git a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.zh.md b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.zh.md index 062d982e3d..806916aea1 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-30-client-locale-full-rollout.zh.md @@ -14,7 +14,7 @@ typed locale 标准席位（`locale:` 注册声明 → 框架注入强类型 `t` **组件文案走标准 `t` 席位；深层子组件用 prop 下传**，类型写 `XxxProps['t']`。字典规范形态不变：`zh satisfies Record` 为 key 源、`en satisfies Record` 锁双语平衡。 -**zero-cordis 原子组件（ui-primitives）文案 props 化**：`TerminalBlock`/`JsonTree` 的 `labels`、`CodeBlock` 的 `copyLabel`/`copiedLabel`、`MarkdownText` 的 `codeLabels`、`JsonBlock` 的 `truncatedLabel`、`ConnectionBanner` 的 `label`、`Modal` 的 `closeLabel`——默认值即原硬编码字符串，不传 props 的消费者渲染逐字节不变。已本地化的插件从自己的 `t` 席位传字典驱动的 label；传对象 props 的调用点按 `t` 身份 memo（`MarkdownText` 的组件表按 `codeLabels` 身份缓存）。 +**zero-cordis 原子组件（ui-primitives）文案 props 化**：`HoverCard` 的 `copyLabel`/`copiedLabel`、`TerminalBlock`/`JsonTree` 的 `labels`、`CodeBlock` 的 `copyLabel`/`copiedLabel`、`MarkdownText` 的 `codeLabels`、`JsonBlock` 的 `truncatedLabel`、`ConnectionBanner` 的 `label`、`Modal` 的 `closeLabel`——默认值即原硬编码字符串，不传 props 的消费者渲染逐字节不变。已本地化的插件从自己的 `t` 席位传字典驱动的 label；传对象 props 的调用点按 `t` 身份 memo（`MarkdownText` 的组件表按 `codeLabels` 身份缓存）。 **不翻译边界（刻意决定，不是欠账）：** @@ -25,7 +25,7 @@ typed locale 标准席位（`locale:` 注册声明 → 框架注入强类型 `t` **派生层保持纯函数，本地化只在渲染层**：ui-workspace 的 `relativeTime` 返回结构化 `{unit, n}` 由渲染组合字典模板；blank 会话/未分组桶的存储标题不变，渲染按 `blank` 标志/`workspaceId` 缺席替换本地化文案；**搜索态 blank 行一律排除**（双语标题无法与单语查询稳定匹配）。日期不引 Intl：格式模板进字典（消息时钟 `clock.md`/`clock.ymd`，workspace hover `date.ymd`），格式化函数吃 `t` 参数保持纯。 -**测试与 e2e 口径**：`makeTranslate(...dicts)`（dsh-client-test-runtime）镜像服务查找链（首个命中字典胜出、key 兜底、`{name}` 插值），组件测试的 `t` 桩统一用它并以真实 props 席位定型。web e2e 统一 `newEnglishPage`（boot 前钉 `dsh.locale=en`），built-boot snapshot 同样钉 en——golden 对语言迁移免疫；settings 语言切换用例刻意绕开该 helper 覆盖 zh 默认态。 +**测试与 e2e 口径**：`makeTranslate(...dicts)`（dsh-client-test-runtime）镜像服务查找链（首个命中字典胜出、key 兜底、`{name}` 插值），组件测试的 `t` 桩统一用它并以真实 props 席位定型。web e2e 统一 `newEnglishPage`（boot 前钉 `dsh.locale=en`），built-boot snapshot 同样钉 en——golden 对语言迁移免疫；settings 语言切换用例绕开该 helper 并开启 `zh-CN` 浏览器，因为初始 locale 跟随 `navigator`（[由浏览器推导初始 locale](../feature/2026-07-31-browser-derived-initial-locale.md)）。 [settings/locale/theme 分层 Note](../../proposed/architecture/2026-07-25-client-settings-locale-theme.md) 中"apply 层订阅 `locale/change` 重注册刷新 label"的机制已被本决定取代（thunk + revision 生命周期）。 diff --git a/.agents/notes/implemented/architecture/2026-07-30-package-manager-native-repository-cache.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-package-manager-native-repository-cache.i18n.yaml new file mode 100644 index 0000000000..6c888c7cad --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-package-manager-native-repository-cache.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/2026-07-30-package-manager-native-repository-cache.md +2026-07-30-package-manager-native-repository-cache.md: f8a6706065a936ca4a9abf2a50d266a60f09b252 +2026-07-30-package-manager-native-repository-cache.zh.md: b1fea3d655f8d7aeb466744dc27bbf4ba69993ec diff --git a/.agents/notes/implemented/architecture/2026-07-30-package-manager-native-repository-cache.md b/.agents/notes/implemented/architecture/2026-07-30-package-manager-native-repository-cache.md new file mode 100644 index 0000000000..f8a6706065 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-package-manager-native-repository-cache.md @@ -0,0 +1,47 @@ +# Agent Note: Package-manager-native repository cache + +Status: implemented + +English | [中文](2026-07-30-package-manager-native-repository-cache.zh.md) + +## Problem + +A standalone Harness app cannot rely on a developer-owned SDK project to declare and install repository dependencies. Loading a configured GitHub repository therefore needs a persistent fetch, preparation, and cache boundary, but implementing Git transport, hosted-source syntax, package preparation, and a content store inside DSH would duplicate a package manager. Requiring a separately installed package manager would make a config-only feature depend on host setup. + +The cache also needs an update identity. A mutable branch name cannot both remain permanently cached and reflect later commits without an independent refresh protocol. + +## Decision + +Vendored `@cordisjs/plugin-loader/repository` exports `RepositoryCache`, a generic Node-only package helper with no DSH plugin-format knowledge. Keeping it on a subpath prevents browser consumers of the Loader's main entry from traversing Node filesystem and child-process imports. The caller supplies a package-manager-native source specifier and a cache root. DSH-specific callers own accepted source syntax, path selection, and the cache-root location; the [SDK project dependency workflow](../../proposed/feature/2026-07-17-sdk-follow-up-capabilities.md#external-cordis-plugin-installation) remains a separate path owned by the developer project's selected package manager. + +The Loader carries an exact runtime dependency on `pnpm@11.7.0` and invokes that package's JavaScript entry with the current Node executable. It never discovers a global executable or delegates through Corepack. Each cache miss creates an isolated project with one dependency named `repository`; pnpm owns Git/GitHub resolution, fetching, its content-addressed store, dependency installation, and lifecycle scripts in the repository's dependency graph. + +The isolated workspace sets `dangerouslyAllowAllBuilds: true`. A configured repository and its dependency graph are trusted executable code: lifecycle scripts may run before DSH reads any declared assets. The child receives ordinary host process state needed by Git and pnpm, but ambient credential-shaped (`KEY`, `PASSWORD`, `SECRET`, `TOKEN`) variables are removed. No OAuth, token forwarding, or private-repository authentication contract is added. + +The SHA-256 of the exact specifier names the cache entry. Concurrent same-process requests share one task. Installation occurs in a sibling temporary directory; only a successful install with a package directory and marker is atomically renamed into the final key. Failed staging is removed, and a competing process's already-published valid entry wins. A later process validates the marker and package directory before returning the stable `node_modules/repository` path. + +An identical specifier permanently reuses its published entry. The caller changes the ref or another part of the specifier to request a new generation; the cache does not poll remotes, reinterpret mutable refs, expire entries, or garbage-collect old generations. + +## Alternatives considered + +**Implement GitHub download, archive extraction, preparation, and caching directly.** Rejected under the [dependency policy](../process/2026-07-26-dependencies-over-hand-rolling.md): pnpm already owns hosted Git syntax, Git execution, lifecycle policy, and a shared content store. A second resolver would add more code while still needing package semantics. + +**Require `pnpm` on `PATH` or invoke Corepack.** Rejected because changing one app config must be sufficient on every supported installation. Pinning and shipping the CLI also makes the preparation policy reviewable and independent of the host's package-manager version. + +**Resolve a branch or tag again on every startup.** Rejected because it turns startup into a network refresh, changes code without a config diff, and makes rollback depend on remote state. Explicit ref changes preserve auditability even when a user deliberately chooses a mutable ref. + +**Disable repository lifecycle scripts.** Rejected because common plugin repositories need a declarative `prepare` step to validate and package their plugin subdirectory. The trust boundary is explicit configuration of executable source, not an incomplete illusion that only static files can run. + +**Introduce a Cordis repository service.** Rejected because cache lookup has no runtime contribution registry or provider variation. A small helper lets the later host own Cordis lifecycle and HMR without adding a service seam prematurely. + +## Consequences + +- Standalone apps carry pnpm's approximately 18.6 MB unpacked runtime instead of requiring a global tool or owning a Git/package implementation. +- A repository author may use ordinary package preparation, and a malicious configured repository or dependency can execute code with the scrubbed child environment and the user's filesystem authority. +- Exact specifiers make startup deterministic after the first successful install; changing cached code requires a config/ref change. +- Failed installs leave no published cache entry and may be retried. Published corruption fails loud instead of silently reinstalling under the same identity. +- Cache generations consume disk until a future explicit cache-management policy removes them. + +## Testing + +`packages/ui/app-boot/tests/repository-cache.spec.ts` covers same-process single-flight, cross-instance cache reuse, exact-specifier separation, failed-stage cleanup and retry, and boundary validation. Its real local-Git case invokes the bundled pnpm, runs the fixture repository's `prepare` script, and reads the prepared file from the installed cache entry without network access. diff --git a/.agents/notes/implemented/architecture/2026-07-30-package-manager-native-repository-cache.zh.md b/.agents/notes/implemented/architecture/2026-07-30-package-manager-native-repository-cache.zh.md new file mode 100644 index 0000000000..b1fea3d655 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-package-manager-native-repository-cache.zh.md @@ -0,0 +1,47 @@ +# Agent Note: 包管理器原生仓库缓存 + +Status: implemented + +[English](2026-07-30-package-manager-native-repository-cache.md) | 中文 + +## 问题 + +独立运行的 Harness 应用不能依赖开发者自有的 SDK 工程来声明并安装仓库依赖。因此，加载配置中的 GitHub 仓库需要一道持久的获取、准备与缓存边界；但如果在 DSH 内实现 Git 传输、托管来源语法、包（package）准备流程和内容存储，就会重复实现包管理器。若要求用户另行安装包管理器，则只需修改配置即可使用的功能还会依赖宿主环境的额外配置。 + +缓存还需要明确更新标识。若没有独立的刷新协议，可变分支名无法既永久缓存，又反映后续 commit。 + +## 决策 + +vendor 中的 `@cordisjs/plugin-loader/repository` 导出 `RepositoryCache`：一个不包含 DSH 插件格式知识、仅限 Node 使用的通用包辅助工具。把它保留在子路径上，可以避免 Loader 主入口的浏览器消费方在解析依赖时遍历到 Node 文件系统和子进程 import。调用方提供包管理器原生的来源 specifier 和缓存根目录。DSH 专属调用方负责规定可接受的来源语法、路径选择与缓存根目录位置；[SDK 工程依赖工作流](../../proposed/feature/2026-07-17-sdk-follow-up-capabilities.md#external-cordis-plugin-installation)仍是另一条路径，由开发者工程选定的包管理器负责。 + +Loader 将 `pnpm@11.7.0` 作为固定版本的运行时依赖，并使用当前 Node 可执行文件调用该包的 JavaScript 入口。它绝不探测全局可执行文件，也不经 Corepack 调用。每次缓存未命中都会创建一个隔离工程，其中只有一个名为 `repository` 的依赖；Git 与 GitHub 来源的解析和获取、pnpm 自身的内容寻址 store、依赖安装，以及仓库依赖图中的生命周期脚本均由 pnpm 负责。 + +隔离工作区设置 `dangerouslyAllowAllBuilds: true`。用户配置的仓库及其依赖图都属于受信任的可执行代码：DSH 读取任何已声明资产之前，生命周期脚本就可能运行。子进程会收到 Git 与 pnpm 所需的常规宿主进程状态，但会移除环境中名称形似凭据（`KEY`、`PASSWORD`、`SECRET`、`TOKEN`）的变量。该机制不新增 OAuth、token 转发或私有仓库认证契约。 + +缓存项以精确 specifier 的 SHA-256 命名。同一进程内针对相同 specifier 的并发请求共享一项任务。安装在同级临时目录中进行；只有安装成功且存在包目录和标记时，系统才会把暂存目录原子重命名为最终键对应的目录。失败的暂存目录会被删除；如果另一进程已发布有效项，则以该项为准。后续进程会先校验标记与包目录，再返回稳定的 `node_modules/repository` 路径。 + +相同的 specifier 会永久复用已发布项。调用方通过修改 ref 或 specifier 的其他部分来请求新的缓存代次；缓存不会轮询远端、重新解释可变 ref、让条目过期，也不会垃圾回收旧代次。 + +## 曾考虑的替代方案 + +**直接实现 GitHub 下载、归档解压、准备与缓存。** 根据[依赖政策](../process/2026-07-26-dependencies-over-hand-rolling.md)不予采纳：pnpm 已负责托管 Git 语法、Git 执行、生命周期政策和共享内容存储。第二套解析器会增加更多代码，却仍需实现包语义。 + +**要求 `pnpm` 位于 `PATH` 上，或调用 Corepack。** 不予采纳：在每种受支持的安装形态中，只修改一份应用配置就必须足以启用该功能。固定并随应用分发 CLI（命令行界面）还能使准备政策可供评审，并与宿主的包管理器版本无关。 + +**每次启动都重新解析分支或 tag。** 不予采纳：这会把启动变成网络刷新，在配置 diff 未变化时更改代码，并让回滚依赖远端状态。即使用户有意选择可变 ref，显式修改 ref 仍能保持可审计性。 + +**禁用仓库生命周期脚本。** 不予采纳：常见插件仓库需要声明式 `prepare` 步骤来校验并打包插件子目录。信任边界是显式配置可执行来源，而不是营造一种不完整的假象，仿佛只有静态文件能够运行。 + +**引入 Cordis 仓库服务。** 不予采纳：缓存查找没有运行时贡献注册表，也不存在提供方变体。小型 helper 让后续宿主负责 Cordis 生命周期与 HMR（热模块替换），无需过早新增服务 seam。 + +## 后果 + +- 独立应用随附 pnpm 约 18.6 MB 的解压后运行时，不要求全局工具，也无需自行实现 Git 与包处理。 +- 仓库作者可以使用常规包准备流程；恶意的已配置仓库或依赖可以在经过上述清理的子进程环境中，以用户的文件系统权限执行代码。 +- 精确 specifier 使首次安装成功后的启动具有确定性；更改缓存代码必须修改配置或 ref。 +- 安装失败不会留下已发布缓存项，可以再次重试。已发布缓存损坏时会明确报错，而不会在同一标识下静默重装。 +- 缓存代次会持续占用磁盘，直到未来有明确的缓存管理政策将其移除。 + +## 测试 + +`packages/ui/app-boot/tests/repository-cache.spec.ts` 覆盖同进程 single-flight、跨实例缓存复用、精确 specifier 隔离、失败暂存清理与重试，以及边界校验。其真实本地 Git 用例会调用随附的 pnpm，运行 fixture（测试前置数据）仓库的 `prepare` 脚本，并在不访问网络的情况下，从已安装缓存项中读取准备后的文件。 diff --git a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.i18n.yaml index cc25329fed..55efb87b8f 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.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/2026-07-30-session-end-seed-log-boundary.md -2026-07-30-session-end-seed-log-boundary.md: 268646e192d0b8e0a5dde03957a18ef155b7038e -2026-07-30-session-end-seed-log-boundary.zh.md: dca87e16de5e567ff85d2b32b8243f76ebed1c4a +2026-07-30-session-end-seed-log-boundary.md: 9d0685876b4d1bac339961c67ab08f620e499464 +2026-07-30-session-end-seed-log-boundary.zh.md: 8fa9625ea6c58b0b07d964ef2580b670893a3d75 diff --git a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md index 268646e192..9d0685876b 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md +++ b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.md @@ -20,7 +20,7 @@ A bracket owner reads it positionally: an unmatched opening marker before `sessi The constructor is the placement because it is the single waist every seeded session passes through. All six entry points reach it: `agents.resume()`, config-driven startup on a persisted id (`restoreOrCreateConfigured`), `sessions.fork()`, a subagent fork child, `coordinator.adopt()`'s live-prefix path, and a bare `sessions.create(id, {seed})`. A boundary written at persistence load would miss both fork paths — and a forked child inheriting a still-running parent's open `compact/start` is precisely the case that must be classifiable. A boundary written at loop start would miss `fork()` and `adopt()`, and would have to fire on `SessionStartSource: 'startup'`, which is what a fork child publishes, so that field would stop discriminating. -Two guards keep the marker precise. An omitted seed writes nothing because the session is fresh. A seed already ending in one is not re-marked, which makes the write idempotent. Idempotence is load-bearing rather than tidiness — `agentFor()` resumes a cold session on first touch, so merely opening one in a client is a pickup, and without the guard browsing would grow a log by one event per visit. +Two guards keep the marker precise. An omitted seed writes nothing because the session is fresh. A seed already ending in one is not re-marked, which makes the write idempotent. Idempotence is load-bearing rather than tidiness: each Agent-bound pickup of a cold session passes through `agentFor()`, and without the guard repeated controls would grow the log even when they perform no work. The inspection-only `session.history` and `session.fork` source paths do not create this boundary in the source. ## Persistence needs no changes @@ -52,4 +52,4 @@ Cost: a seeded session's log is one event longer, including an empty resumed log `session/end-seed` joins the on-disk vocabulary. Under the pre-release stance (`SESSION_FORMAT_VERSION` pinned at `0`, no compatibility promise) older logs simply lack it, and a log without a boundary correctly classifies nothing as constructor-seed history. -Not built here: no plugin reads the boundary yet. Wiring the compaction seam's staleness check to it is the follow-up that motivated this boundary; the predicate helper belongs with that seam, where a real consumer decides its shape, rather than shipping into core untested against one. +The [queued manual compaction decision](../feature/2026-07-30-queued-manual-compaction.md) now supplies the first consumer. Its tail scan independently finds the unmatched `compact/start` and newest end-seed, treats only a start after that boundary as live, and clears the invariant trace on the same replay transition. The predicate remains in the compaction package rather than becoming a generic core helper. diff --git a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md index dca87e16de..8fa9625ea6 100644 --- a/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-30-session-end-seed-log-boundary.zh.md @@ -20,7 +20,7 @@ Status: implemented 选择构造函数，是因为它是每一个带种子会话都必经的唯一收窄处。全部六个入口都会到达它：`agents.resume()`、在已持久化 id 上的配置驱动启动（`restoreOrCreateConfigured`）、`sessions.fork()`、子代理 fork 子会话、`coordinator.adopt()` 的实时前缀路径，以及裸的 `sessions.create(id, {seed})`。在持久化加载时写入的边界会漏掉两条 fork 路径——而一个继承了仍在运行的父会话开放 `compact/start` 的 fork 子会话，恰恰是必须可判定的场景。在 loop 启动时写入的边界会漏掉 `fork()` 与 `adopt()`，并且不得不在 `SessionStartSource: 'startup'` 上触发——那正是 fork 子会话发布的取值，于是该字段将不再具有区分力。 -两条守卫让这个标记保持精确。省略种子时不写入任何内容，因为这是全新会话。种子本身已以该事件结尾时不会重复标记，这让写入具备幂等性。幂等性是承重的，而不是为了整洁——`agentFor()` 会在首次触碰时恢复一个冷会话，因此在客户端里仅仅打开一个会话就是一次接手；没有这条守卫，浏览会让日志每访问一次就增长一个事件。 +两条守卫让这个标记保持精确。省略种子时不写入任何内容，因为这是全新会话。种子本身已以该事件结尾时不会重复标记，这让写入具备幂等性。幂等性是承重的，而不是为了整洁：每次绑定到 Agent 的冷会话接手都会经过 `agentFor()`；没有这条守卫，重复的控件操作即使没有执行任何工作，也会让日志增长。只执行检查的 `session.history` 与 `session.fork` 源端路径不会在源会话中创建这条边界。 ## 持久化无需任何改动 @@ -52,4 +52,4 @@ Status: implemented `session/end-seed` 加入了落盘词汇表。在预发布立场下（`SESSION_FORMAT_VERSION` 固定为 `0`，不作兼容承诺），更旧的日志只是没有它，而没有边界的日志会正确地判定没有任何内容属于构造种子历史。 -此处未做：还没有任何插件读取该边界。把压缩 seam 的陈旧性检查接到它上面，是催生这条边界的后续工作；谓词辅助函数应当归属那个 seam——在那里由真实消费方决定它的形状——而不是未经真实消费方检验就先落进核心。 +[排队手动压缩决策](../feature/2026-07-30-queued-manual-compaction.md)如今提供了第一个消费方。其尾部扫描会分别查找未匹配的 `compact/start` 与最新 end-seed，只把位于该边界之后的 start 视为活动锁，并在同一个回放转换上清除不变量追踪状态。该谓词仍位于压缩包中，不会成为通用核心辅助函数。 diff --git a/.agents/notes/implemented/architecture/2026-07-30-static-repository-plugin-format.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-30-static-repository-plugin-format.i18n.yaml new file mode 100644 index 0000000000..6319b99fb2 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-static-repository-plugin-format.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/2026-07-30-static-repository-plugin-format.md +2026-07-30-static-repository-plugin-format.md: c9d755b925a6ea05eed71e75803397d2672df9f4 +2026-07-30-static-repository-plugin-format.zh.md: 361de64d2e98b9fb4ac42963e4ae48e77fbc7016 diff --git a/.agents/notes/implemented/architecture/2026-07-30-static-repository-plugin-format.md b/.agents/notes/implemented/architecture/2026-07-30-static-repository-plugin-format.md new file mode 100644 index 0000000000..c9d755b925 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-static-repository-plugin-format.md @@ -0,0 +1,49 @@ +# Agent Note: Static repository Plugin format + +Status: implemented + +English | [中文](2026-07-30-static-repository-plugin-format.zh.md) + +## Problem + +A repository that already contains reusable skills or an MCP server declaration should be usable by standalone Harness applications without becoming a Harness SDK project or rewriting its existing layout. Popular repositories must be able to add one `.dsh-plugin` directory while keeping their current skills and `.mcp.json` elsewhere in the tree. At the same time, treating an arbitrary repository entry point as a Cordis Plugin would make every repository a new unrestricted runtime extension surface and would bypass the existing skill and MCP lifecycle owners. + +The [package-manager-native repository cache](2026-07-30-package-manager-native-repository-cache.md) prepares an exact package source but intentionally knows nothing about DSH formats. This layer therefore needs a package-manager-compatible authoring format, a deterministic prepared artifact, and a Cordis composition that stays transactional under Loader disposal and replacement. + +## Decision + +`@deepseek-ai/dsh-repository-plugin` owns a restricted `.dsh-plugin` package format with two contribution kinds only: skill roots and one common `.mcp.json`. Its package metadata uses `package.json#dsh.skills` for relative skill-root paths and `package.json#dsh.mcpServers` for the relative MCP document path. At least one is required. Each path may leave `.dsh-plugin` to reuse repository content but must remain beneath the directory containing that `.dsh-plugin`; a nested selectable Plugin therefore owns the adjacent subtree above its package without gaining access to unrelated host paths. + +The `.dsh-plugin` package declares `dsh-plugin-prepare` as its ordinary package-manager `prepare` script. The helper validates metadata and source types, strictly parses `.mcp.json`, copies static assets into `dsh-plugin-assets`, and writes `dsh-plugin.mjs`. The `.mjs` extension avoids imposing `type: module` on repository-authored package metadata. The generated module is a fixed import-free template containing only a normalized manifest, an `inject` list derived from it (`loader`, plus `skills` and/or `tools` per the declared capabilities, so the wrapper fiber gates on the services its children need), and delegation to the `dsh-repository-plugin` Loader builtin. Preparation never discovers, transpiles, bundles, or preserves a custom repository entry point. + +Loading the DSH package registers that builtin as an effect. A generated wrapper mounts the builtin as its child with `import.meta.url`, so all contributions belong to the wrapper fiber and disappear on Loader removal or rollback. The builtin revalidates the prepared manifest and path containment before reading assets. It composes the existing implementations rather than registering skills or MCP tools itself. + +Each prepared skill set mounts `dsh-skill-local` with a unique `repository:` provider name, only the copied custom roots, and watching disabled. `dsh-skill-local` therefore gains two general configuration fields: `providerName` and `includeDefaultRoots`. Their defaults preserve its existing single local provider; repository instances set a distinct name and exclude project/user roots so multiple instances neither collide nor duplicate host-local discovery. + +Each `.mcp.json` server becomes one existing `dsh-mcp-client` child. The adapter accepts the common root `{ "mcpServers": ... }`; stdio definitions allow only optional `type: "stdio"`, `command`, `args`, and `env`, while HTTP definitions allow only `type: "http"`, `url`, and `headers`. Exact `${NAME}` process-environment references expand at runtime, after cache preparation; missing names fail Plugin load. HTTP maps to the client's Streamable HTTP transport, and stdio uses the prepared package directory as `cwd`. The existing client alone owns connection attempts, failure logging, remote tool synchronization, tool calls, and disconnects. Consequently an MCP connection failure keeps its established successful-plugin/no-tools behavior and is not reclassified as a repository preparation or Loader failure. + +Unknown MCP fields reject. This intentionally excludes OAuth, `auth` objects, `CLAUDE_PLUGIN_ROOT`, and a broader Claude compatibility contract. Hooks, commands, agents, apps, arbitrary Cordis code, marketplaces, and discovery are also unsupported. Repository subdirectory selection and GitHub source configuration belong to the [standalone app integration](../feature/2026-07-30-config-only-repository-plugins.md), not this format package. + +## Alternatives considered + +**Load a repository's own Cordis entry point.** Rejected because it makes the advertised static format an unrestricted code-loading API, requires repository authors to depend on Harness internals, and duplicates the ordinary SDK/plugin-dependency path. + +**Teach generated wrappers to implement skills and MCP directly.** Rejected because copied runtime code would drift from `dsh-skill-local` and `dsh-mcp-client`, especially their provider invalidation, tool synchronization, failure, and teardown contracts. + +**Import Harness packages from each generated wrapper.** Rejected because repository packages should not resolve or version the application's internal dependency graph. A Loader builtin supplies one app-owned implementation and keeps generated wrappers import-free. + +**Watch prepared repository assets.** Rejected because an exact repository cache generation is immutable. Ref, subdirectory, or configuration changes select a new generation; a second watcher would create an unowned refresh identity. + +**Treat MCP connect failures as Loader update failures.** Rejected because the existing MCP client deliberately contains connect failures and exposes no tools. Changing that semantic only for repository sources would create two failure contracts for the same server configuration. + +## Consequences + +- Existing skill/MCP repositories can add a small `.dsh-plugin/package.json` without relocating their assets or adopting an SDK project. +- Prepared output is deterministic static glue, while the configured repository and its dependency lifecycle remain trusted executable package-manager input rather than a sandbox. +- Multiple repository Plugins coexist through provider names and ordinary MCP server-name uniqueness; duplicate names fail through their existing registries and participate in Loader rollback. +- Cached source edits do not appear live. Another exact source/ref/path/config selection is required. +- Adding another contribution kind requires an explicit format and DSH-owned runtime consumer; it cannot arrive as repository JavaScript by accident. + +## Testing + +Focused tests prepare skills and MCP metadata, prove the emitted wrapper contains no imports, reject Work IQ-style OAuth fields, map Expo-style HTTP and DataJunction-style stdio plus environment values, and exercise missing variables. A real Loader test mounts a generated wrapper through the registered builtin, reads its skill through `ctx.skills`, removes the Loader entry, and observes provider cleanup. The keyless headless example loads a checked-in prepared wrapper through its real `cordis.yml` and snapshots the repository skill's logged model catalog row. diff --git a/.agents/notes/implemented/architecture/2026-07-30-static-repository-plugin-format.zh.md b/.agents/notes/implemented/architecture/2026-07-30-static-repository-plugin-format.zh.md new file mode 100644 index 0000000000..361de64d2e --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-07-30-static-repository-plugin-format.zh.md @@ -0,0 +1,49 @@ +# Agent Note：静态 repository Plugin 格式 + +状态：已实现 + +[English](2026-07-30-static-repository-plugin-format.md) | 中文 + +## 问题 + +一个已经包含可复用 skills 或 MCP server 声明的仓库，应当能被独立 Harness 应用使用，而不必先变成 Harness SDK 项目，也不应被迫改写现有布局。常见仓库只需新增一个 `.dsh-plugin` 目录，同时仍可把原有 skills 与 `.mcp.json` 放在仓库其他位置。与此同时，如果把任意仓库入口都当作 Cordis Plugin，就会让每个仓库成为新的无限制运行时扩展表面，并绕过现有的 skill 与 MCP 生命周期所有者。 + +[Package-manager-native repository cache](2026-07-30-package-manager-native-repository-cache.md) 会准备一个精确 package source，但有意不了解任何 DSH 格式。因此本层需要一种兼容 package manager 的创作格式、确定性的已准备产物，以及在 Loader dispose 和替换期间仍保持事务性的 Cordis 组合。 + +## 决策 + +`@deepseek-ai/dsh-repository-plugin` 负责一个受限的 `.dsh-plugin` package 格式，且只允许两类贡献：skill 根和一个通用 `.mcp.json`。Package metadata 使用 `package.json#dsh.skills` 声明相对 skill 根路径，使用 `package.json#dsh.mcpServers` 声明相对 MCP 文档路径；两者至少需要一个。路径可以离开 `.dsh-plugin` 以复用仓库内容，但必须留在包含该 `.dsh-plugin` 的目录之下；因此，一个嵌套且可选择的 Plugin 可以拥有其 package 上方相邻的子树，却不能访问无关宿主路径。 + +`.dsh-plugin` package 把 `dsh-plugin-prepare` 声明为普通 package-manager `prepare` 脚本。Helper 会校验 metadata 与源码类型，严格解析 `.mcp.json`，把静态资源复制到 `dsh-plugin-assets`，并写入 `dsh-plugin.mjs`。`.mjs` 扩展名避免强迫仓库作者在 package metadata 中设置 `type: module`。生成模块来自固定、无 import 的模板，只包含规范化 manifest、由 manifest 派生的 `inject` 列表（`loader`，加上按声明能力加入的 `skills`／`tools`，使包装 fiber 在其子插件所需服务上门控），以及对 `dsh-repository-plugin` Loader builtin 的委托。准备阶段永远不会发现、转译、打包或保留自定义仓库入口。 + +加载 DSH package 会以 effect 方式注册该 builtin。生成的包装模块使用 `import.meta.url` 把 builtin 挂载为自己的子级，因此所有贡献都归属于包装 fiber，并在 Loader 移除或回滚时消失。Builtin 会在读取资源前重新校验已准备 manifest 与路径包含关系。它只组合现有实现，而不自行注册 skills 或 MCP 工具。 + +每份已准备 skill 集合都会挂载 `dsh-skill-local`，使用唯一的 `repository:` 提供方名称、仅包含复制后的自定义根，并禁用监视。因此 `dsh-skill-local` 新增两个通用配置字段：`providerName` 和 `includeDefaultRoots`。默认值保持原有单一本地提供方行为；repository 实例设置不同名称并排除项目／用户根，使多个实例既不冲突，也不会重复宿主本地发现。 + +`.mcp.json` 中的每个 server 都变成一个现有 `dsh-mcp-client` 子级。适配层接受通用根对象 `{ "mcpServers": ... }`；stdio 定义只允许可选的 `type: "stdio"`、`command`、`args` 与 `env`，HTTP 定义只允许 `type: "http"`、`url` 与 `headers`。严格的 `${NAME}` 进程环境变量引用在运行时、cache 准备之后展开；缺失变量会使 Plugin 加载失败。HTTP 映射到 client 的 Streamable HTTP transport，stdio 使用已准备 package 目录作为 `cwd`。只有现有 client 负责连接尝试、失败日志、远端工具同步、工具调用和断开。因此 MCP 连接失败会继续沿用“Plugin 成功但不注册工具”的既有行为，不会被重新分类为 repository 准备或 Loader 失败。 + +未知 MCP 字段会被拒绝。这里有意排除 OAuth、`auth` 对象、`CLAUDE_PLUGIN_ROOT` 和更广泛的 Claude 兼容契约。Hooks、commands、agents、apps、任意 Cordis 代码、marketplace 和发现同样不受支持。Repository 子目录选择与 GitHub 源配置属于[独立应用集成](../feature/2026-07-30-config-only-repository-plugins.md)，而不是本格式 package。 + +## 考虑过的替代方案 + +**加载仓库自己的 Cordis 入口。** 拒绝，因为这会把宣传为静态的格式变成无限制代码加载 API，要求仓库作者依赖 Harness 内部实现，并重复普通 SDK／Plugin dependency 路径。 + +**让生成包装模块直接实现 skills 和 MCP。** 拒绝，因为复制的运行时代码会与 `dsh-skill-local` 和 `dsh-mcp-client` 漂移，尤其是提供方失效、工具同步、失败和 teardown 契约。 + +**让每个生成包装模块 import Harness package。** 拒绝，因为 repository package 不应解析或锁定应用的内部依赖图。Loader builtin 提供一份由 app 所有的实现，并让生成包装模块保持无 import。 + +**监视已准备 repository 资源。** 拒绝，因为一个精确 repository cache generation 是不可变的。Ref、子目录或配置变化会选择新 generation；第二套 watcher 会创造一套没有所有者的刷新身份。 + +**把 MCP 连接失败当作 Loader 更新失败。** 拒绝，因为现有 MCP client 有意收束连接失败并不暴露工具。只对 repository source 改变该语义，会让同一 server 配置拥有两套失败契约。 + +## 后果 + +- 现有 skill／MCP 仓库可以新增一个很小的 `.dsh-plugin/package.json`，无需移动资源或采用 SDK 项目。 +- 已准备输出是确定性的静态胶水；已配置仓库及其依赖生命周期仍是受信任的可执行 package-manager 输入，而非 sandbox。 +- 多个 repository Plugin 通过提供方名称和普通 MCP server-name 唯一性共存；重复名称经现有 registry 失败，并参与 Loader 回滚。 +- Cache 内的源码编辑不会实时出现；必须选择另一个精确 source／ref／path／config。 +- 新增贡献类型必须提供显式格式和 DSH 自有运行时消费方；它不能意外以 repository JavaScript 形式进入。 + +## 测试 + +聚焦测试会准备 skills 与 MCP metadata，证明生成包装模块不含 import，拒绝 Work IQ 风格的 OAuth 字段，映射 Expo 风格 HTTP 与 DataJunction 风格 stdio 及环境变量，并覆盖缺失变量。真实 Loader 测试通过已注册 builtin 挂载生成包装模块，经 `ctx.skills` 读取其 skill，移除 Loader 条目并观察提供方清理。Keyless headless 示例通过真实 `cordis.yml` 加载一份签入的已准备包装模块，并快照 repository skill 写入日志的模型目录行。 diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.i18n.yaml new file mode 100644 index 0000000000..f63372c8b4 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.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/2026-08-01-packaged-ripgrep-search.md +2026-08-01-packaged-ripgrep-search.md: 7c515618a18b61bd90177a6fdf19bbd52e564209 +2026-08-01-packaged-ripgrep-search.zh.md: f2b1a12c737f772bff6a6c91c17f7453dbc89748 diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md new file mode 100644 index 0000000000..7c515618a1 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.md @@ -0,0 +1,38 @@ +# Agent Note: Packaged ripgrep spawn for glob/grep + +Status: implemented + +English | [中文](2026-08-01-packaged-ripgrep-search.zh.md) + +> Supersedes [bash-backed grep/glob discovery](../../archived/feature/2026-07-09-bash-backed-grep-glob-discovery.md): the v1 decision's explicitly deferred alternative — directly spawning ripgrep — is now what ships. + +## Problem + +The `glob`/`grep` tools ran through the bash executor seam, which made a system `rg` install a host dependency. On Windows and container images there is no `rg` on `PATH` by default, so the tools silently vanished there; a deployment could only discover that from the load-time probe warning. The bash seam also forced the whole model-visible argument surface through one shell-quoting helper, because a shell sat between the tool and ripgrep — the [bash-backed note](../../archived/feature/2026-07-09-bash-backed-grep-glob-discovery.md) recorded that coupling as the v1 trade-off and named direct spawn as the reasonable follow-up if the shell-string domain ever proved too sensitive. It did: every model value had to survive POSIX single-quoting, the probe had to be scripted in tests, and the executor's own timeout classification duplicated what the cooperative tool-timeout policy already owns. + +## Decision + +`@deepseek-ai/dsh-tool-fs-search` now runs the PACKAGED ripgrep binary (`@vscode/ripgrep`, an npm dependency whose optional platform packages ship the binary) through the `ctx.subprocess` seam: `runRipgrep()` spawns `rgPath` with a plain argv vector prefixed by `--no-config`, collect-mode stdout/stderr, `graceMs`, and `exec.signal` forwarded. `rgPath` resolves lazily at the first call (memoized per process): `@vscode/ripgrep` resolves its platform package at module evaluation, so a static import would turn a missing or corrupt platform package (`--omit=optional`, partial install) into a Loader-composition failure — the load-time failure mode this change exists to remove. There is no shell layer, so the shell-quoting boundary is gone from execution; the `singleQuote` helper and its shell-spawning tests are deleted with it. The raw streams request the seam's diagnostic-tail collect shape (no spill files — the tool never reads a raw spill path; a lossy stdout read fails as `SEARCH_RAW_OUTPUT_OVERFLOW`). The terminate grace and the stderr tail budget are validated `Config` fields (`graceMs` default 3000, `stderrMaxBytes` default 64 KiB), no longer inherited from bash-local's config. Registration is unconditional — the load-time `command -v rg` probe and the conditional registration decision are deleted, and with them the "rg not found" warning. The package injects `tools`, `systemPrompt`, and `subprocess`. + +Exit semantics stay tool-owned: exit 0 is success with results, exit 1 is a successful empty search, anything else classifies into the existing `SEARCH_*` vocabulary (invalid pattern, launch failure, signal kill, raw-output overflow). Timeout is the cooperative tool-call budget attached to the tool definitions: `@deepseek-ai/dsh-timeout-policy` aborts `exec.signal`, the subprocess seam's terminate escalation provides the hard kill, and the tool reports `SEARCH_ABORTED`. The working directory is the session header cwd when present, else `process.cwd()` — there is no executor config to default through anymore, so the tool owns the fallback. + +The `fs-glob-sampling` ACP snapshot scenario now executes the real packaged binary against a prepared workspace whose fixed mtimes pin the `--sort=modified` order, replacing the PATH-injected `rg` stand-in (POSIX-only, because the displayed paths carry `/` separators the session-log comparison cannot normalize). + +## Alternatives considered + +**Keep the bash seam and probe, but document `rg` as a required host dependency.** Rejected: the host dependency is exactly the failure this change removes, and Windows support for the discovery tools was the point of the exercise; a documented requirement is still a requirement. + +**Make `rgPath` injectable (a config field or env override) so tests and snapshots keep substituting a stand-in binary.** Rejected: it adds a public deployment surface whose only consumer would be test seams, and the real binary is deterministic enough to pin directly through fixture mtimes — the packaged binary is the deployment, so tests should exercise it. + +**Switch to a pure-JS glob/search engine (e.g. `picomatch`/`tinyglobby`).** Rejected: the [dependency-swaps audit](../../rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md) already rejected that on the "no glob engine exists" evidence; ripgrep semantics (`--sort=modified`, VCS pruning, JSON transport, regex dialect) are the tool contract. + +## Consequences + +- The discovery tools work on every platform the packaged binary covers (darwin/linux/win32, x64/arm64) with no host install; the shipped TUI/Web rosters gain `glob`/`grep` as fixed members ([even-out-shipped-tool-rosters](../feature/2026-07-31-even-out-shipped-tool-rosters.md)). +- The shell-string attack surface is gone: hostile patterns are inert argv elements, pinned by the integration suite, which now runs on Windows too (it previously self-skipped without a system `rg`). +- The spawn is unconfined (a plain `ctx.subprocess` call), so `--no-config` is prepended: a host `RIPGREP_CONFIG_PATH` (or an `rg.conf` beside the binary) can otherwise inject a `--pre` preprocessor that executes an arbitrary command for every matched file. With `--no-config`, no config file — and therefore no preprocessor — can reach the search. +- The raw-output overflow path changed shape: the old bash-backed route inherited bash-local's always-on spill and could leave an unread multi-megabyte temp file; the subprocess seam now collects without spill, and overflow is a pure error (`SEARCH_RAW_OUTPUT_OVERFLOW`, "narrow pattern, path, or include and retry") with zero content returned. +- Load-time failure modes changed: a broken subprocess seam now fails the first search call (`SEARCH_FAILED`) instead of failing plugin load through the probe; a missing binary is a launch failure with the packaged path, not a PATH problem. +- The integration suite's fixture dropped a filename Windows cannot represent (`"` in a name), keeping the suite replayable on every platform. +- Regenerating `THIRD_PARTY_NOTICES.md` surfaced a latent generator bug the new dependency made visible: Node's `fs.globSync` returns OS-native separators, so on Windows the `/`-suffixed dev-area prefixes in the notices tiering never matched and dev-only packages (test tooling, support leaves) were mis-tiered as runtime. The generator now normalizes manifest paths at ingestion, and the notices are platform-independent. +- The `@vscode/ripgrep` dependency adds its MIT row to the runtime tier, and pnpm 11's truncated virtual-store directory names needed a content-scan fallback in the notices generator's metadata lookup. diff --git a/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md new file mode 100644 index 0000000000..f2b1a12c73 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-01-packaged-ripgrep-search.zh.md @@ -0,0 +1,38 @@ +# Agent Note: glob/grep 改用打包的 ripgrep 二进制直接 spawn + +Status: implemented + +[English](2026-08-01-packaged-ripgrep-search.md) | 中文 + +> 取代 [bash 承载的 grep/glob 发现工具](../../archived/feature/2026-07-09-bash-backed-grep-glob-discovery.md)：v1 决策中明确延期的方案——直接 spawn ripgrep——现在成为实际交付的实现。 + +## 问题 + +`glob`/`grep` 工具经由 bash 执行器 seam 运行，这使系统 `rg` 安装成为宿主依赖。Windows 和容器镜像的 `PATH` 默认没有 `rg`，工具在那里会静默消失；部署方只能从加载期探针警告里发现这一点。bash seam 还迫使整个模型可见参数面经过一个 shell 引号工具，因为工具与 ripgrep 之间隔着一层 shell——[bash 承载决策](../../archived/feature/2026-07-09-bash-backed-grep-glob-discovery.md) 把这种耦合记为 v1 的取舍，并把直接 spawn 列为 shell 字符串域一旦被证明过于敏感时的合理后续。它确实被证明了：每个模型值都要经受 POSIX 单引号转义，探针要在测试里脚本化，执行器自身的超时分类还与协作式工具超时策略已有的职责重复。 + +## 决策 + +`@deepseek-ai/dsh-tool-fs-search` 现在运行 PACKAGED（打包的）ripgrep 二进制（`@vscode/ripgrep`，一个 npm 依赖，其可选平台包随附二进制），经由 `ctx.subprocess` seam：`runRipgrep()` 以纯 argv 向量 spawn `rgPath`，向量前缀 `--no-config`，配以 collect 模式 stdout/stderr、`graceMs` 与转发的 `exec.signal`。`rgPath` 在首次调用时懒解析（进程内 memoize）：`@vscode/ripgrep` 在模块求值阶段解析其平台包，静态导入会把平台包缺失/损坏（`--omit=optional`、安装不全）变成 Loader 组合加载失败——这正是本次改动要消除的加载期失败模式。不再有 shell 层，执行路径上的 shell 引号边界随之消失；`singleQuote` 工具与其 shell spawn 测试一并删除。原始流使用 seam 的诊断尾部 collect 形态（无 spill 文件——工具从不读取原始 spill 路径；lossy stdout 读取以 `SEARCH_RAW_OUTPUT_OVERFLOW` 失败）。终止宽限与 stderr 尾部预算成为经校验的 `Config` 字段（`graceMs` 默认 3000，`stderrMaxBytes` 默认 64 KiB），不再继承自 bash-local 的配置。注册变为无条件——加载期 `command -v rg` 探针与条件注册决策被删除，连同那条 "rg not found" 警告。本包注入 `tools`、`systemPrompt` 与 `subprocess`。 + +退出语义仍由工具拥有：退出码 0 为有结果的成功，1 为成功的空搜索，其余归入既有 `SEARCH_*` 词汇（无效模式、启动失败、信号杀死、原始输出溢出）。超时是挂在工具定义上的协作式工具调用预算：`@deepseek-ai/dsh-timeout-policy` 中止 `exec.signal`，subprocess seam 的终止升级提供硬终止，工具报告 `SEARCH_ABORTED`。工作目录为会话 header cwd（存在时），否则为 `process.cwd()`——不再有执行器配置可供默认化，因此回退由工具自己拥有。 + +`fs-glob-sampling` ACP 快照场景改为执行真实的打包二进制，作用于一个用固定 mtime 钉住 `--sort=modified` 顺序的预制工作区，取代 PATH 注入的 `rg` 替身（仅 POSIX：展示路径携带 `/` 分隔符，会话日志比较无法归一化）。 + +## 备选方案 + +**保留 bash seam 与探针，仅把 `rg` 记为必需宿主依赖。** 否决：宿主依赖正是本次改动要消除的失败模式，而让发现工具支持 Windows 正是此举的目的；写进文档的依赖仍是依赖。 + +**让 `rgPath` 可注入（配置字段或环境变量覆盖），让测试与快照继续替换替身二进制。** 否决：这会新增一个只有测试 seam 会消费的公开部署面，而真实二进制本身足够确定——通过 fixture mtime 即可直接钉住；打包二进制就是部署形态，测试应当拿它来测。 + +**改用纯 JS 的 glob/搜索引擎（如 `picomatch`/`tinyglobby`）。** 否决：[依赖替换审计](../../rejected/simplification/2026-07-26-dependency-swaps-rejected-by-nih-audit.md) 已基于"不存在 glob 引擎"的证据否决过该方向；ripgrep 语义（`--sort=modified`、VCS 剪枝、JSON 传输、正则方言）就是工具契约。 + +## 后果 + +- 发现工具在打包二进制覆盖的每个平台（darwin/linux/win32，x64/arm64）上开箱即用，无需宿主安装；交付的 TUI/Web 工具清单把 `glob`/`grep` 变为固定成员（见 [拉平交付的工具清单](../feature/2026-07-31-even-out-shipped-tool-rosters.md)）。 +- shell 字符串攻击面消失：恶意模式只是惰性 argv 元素，由集成套件钉住；该套件现在也在 Windows 上运行（此前没有系统 `rg` 时它自行跳过）。 +- spawn 不受沙箱约束（普通的 `ctx.subprocess` 调用），因此前缀 `--no-config`：宿主的 `RIPGREP_CONFIG_PATH`（或二进制旁的 `rg.conf`）否则可注入 `--pre` 预处理器，对每个匹配文件执行任意命令。加上 `--no-config` 后，任何配置文件——因而任何预处理器——都无法触及搜索。 +- 原始输出溢出路径的形态改变：旧的 bash 承载路径继承了 bash-local 常开的 spill，可能留下没人读的多 MB 临时文件；subprocess seam 现在无 spill 收集，溢出是纯粹的错误（`SEARCH_RAW_OUTPUT_OVERFLOW`，"narrow pattern, path, or include and retry"），不返回任何内容。 +- 加载期失败模式改变：subprocess seam 损坏现在让首次搜索调用失败（`SEARCH_FAILED`），而非通过探针使插件加载失败；二进制缺失是带打包路径的启动失败，而不是 PATH 问题。 +- 集成套件的 fixture 去掉了 Windows 无法表示的文件名（名称含 `"`），保证套件在每个平台都能重放。 +- 重新生成 `THIRD_PARTY_NOTICES.md` 暴露了一个由新依赖带出的潜在生成器 bug：Node 的 `fs.globSync` 返回操作系统原生分隔符，因此在 Windows 上 notices 分层中带 `/` 后缀的 dev 区前缀永远匹配不上，dev-only 包（测试工具、support 叶子）被错分为 runtime。生成器现在在入口处归一化清单路径，notices 与平台无关。 +- `@vscode/ripgrep` 依赖为 runtime 层增加其 MIT 行；pnpm 11 截断的虚拟存储目录名需要在 notices 生成器的元数据查找中增加内容扫描回退。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.i18n.yaml index b16ef70d7c..6f4a6d363d 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.i18n.yaml @@ -1,6 +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 -2026-07-20-config-hot-reload-resilience.md: 1a8e29c603ede50b60199e9151fca58dadcc3d40 -2026-07-20-config-hot-reload-resilience.zh.md: 6c7a421bfa84504a36d5329e13a485bf72cc6b6c +# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.md +2026-07-20-config-hot-reload-resilience.md: 0f15bb0aaacb6e06c416cbe35b44155279497eee +2026-07-20-config-hot-reload-resilience.zh.md: 8a185c1915b5247150d8bb1dd5c42d69bd4f2a35 diff --git a/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.md b/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.md index 1a8e29c603..0f15bb0aaa 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.md +++ b/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.md @@ -6,33 +6,36 @@ English | [中文](2026-07-20-config-hot-reload-resilience.zh.md) ## Problem -The demo apps mount `@cordisjs/plugin-hmr` as a leaf so a running agent picks up `cordis.yml` edits. One bad edit killed the process: `Include.refresh()` rethrew the YAML parse error, the HMR watcher awaits `refresh()` inside an async chokidar callback nobody catches, and the resulting unhandled rejection tripped `dsh-app-boot`'s fail-loud handler — `exit(1)` mid-session, losing the live TUI. Two adjacent defects made even *valid* reloads wrong: a file that parses to `undefined` (empty or mid-write truncated — editors and `sed -i` routinely produce these states) crashed the entry walk instead of reading as invalid, and a re-read never re-applied the include's `config.patches`, so any hot-reload of an overlay-based tree (Code Mode, personal overlays) silently reverted patched entries and removed inserted ones. +An invalid `cordis.yml` edit must not kill a running agent, but preserving the process is insufficient when a valid-looking update partially replaces the Loader tree before a later entry fails. Callers also need to observe a rejected live update without treating the same error as an unhandled boot failure. Personal configuration adds a second requirement: HMR must observe one exact file outside its module roots, including a file or parent directory created after startup. ## Decision -Harden the vendored `@cordisjs/plugin-include` (logged as local modification 8 in [vendor/README.md](../../../../vendor/README.md)) rather than the callers: +The vendored Cordis lifecycle and Loader plugins provide an awaited, compensating config transaction, logged as local modifications 6, 8, and 9 in [vendor/README.md](../../../../vendor/README.md). -- `refresh()` awaits the whole read-and-update and catches failures, logs a warning, and keeps the last good entry tree. A hot-reload is advisory; the invariant is that no file state reachable by an editor may take the process down. -- `read()` rejects a non-array parse result with a `TypeError`, folding the `undefined`-parse case into the same "invalid file" signal, and commits `content`/`data` only after a successful parse — so reverting an edit to the exact last good content correctly reads as "unchanged". -- `refresh()` and the `internal/update` listener apply `this.applyPatches(...)` before `root.update()`, restoring parity with `[Service.init]`. `applyPatches` deep-copies the cached parse (`structuredClone`) instead of mutating it, so repeated application converges and removing a patch reverts to the file's own values. The listener uses the incoming config's `patches` and persists that config itself: it vetoes the fiber restart (children update in place), and `Fiber.update` only assigns `this.config` behind `next()`, so without the explicit assignment the next re-read would re-apply the old overlay. +`Fiber.update()` returns its `internal/update` waterfall result. Config validation remains synchronous, while the default continuation returns the restart promise. Loader entry updates can therefore distinguish validation, import, application, and rollback failure from successful lifecycle settlement. `EntryTree.await()` rechecks service-gated fibers after Loader tasks drain and rejects settled failures; a fiber waiting on an absent service remains a valid pending entry rather than making settlement hang. -Boot-time behavior stays fail-loud and gets a sharper diagnostic: `[Service.init]` falls back to `initial` (or "config file not found") only on `ENOENT`; an existing-but-invalid file now fails with its real parse error instead of being mislabelled as absent or silently overwritten by `initial`. +Loader imports a changed module name before disposing the active fiber. Candidate application is awaited; a failure disposes candidate effects and restores the prior plugin or config. Group reconciliation starts candidates concurrently, awaits every outcome, and restores changed entries, additions, removals, and moves before rejecting. Persistence occurs only after successful programmatic mutation. This is a compensating transaction: lifecycle effects may be briefly visible, and a failed rollback is reported as an `AggregateError` rather than misrepresented as a retained tree. + +Include reads and validates detached candidate content, applies patches to a clone, reconciles the Loader tree, and only then commits cached content and parsed data. `refresh()` rejects to its caller after a parse, validation, application, or rollback failure. Initial load remains fail-loud; only an absent file may use `initial`. A non-array YAML/JSON result is invalid, and both file refresh and Include-config update re-apply patches without mutating the cached parse. + +HMR contains live refresh rejection. Its `registerConfig(filename, refresh)` method watches one exact path from the nearest existing ancestor, serializes and coalesces refreshes, and returns an async disposer that closes the watcher and drains active work. Both exact-path and ordinary config-file refreshes use that queue. A failure is normalized to `Error`, logged, and broadcast through the parallel `hmr/config-update-failed(filename, error)` event; rejecting observers are logged without stopping later refreshes. Creation, change, and removal are observed. ## Alternatives considered -**Catch in the HMR watcher callback instead of `refresh()`.** Rejected: it would leave `refresh()` a trap for every other caller (the `internal/update` path shares the same tree-update logic), and it cannot fix the `undefined`-parse or patch-loss defects, which live inside the include. +**Contain failures inside `Include.refresh()`.** Rejected because it prevents an HMR host from broadcasting the failure and still permits Loader reconciliation to hide partial application. Include owns candidate parsing and commit; HMR owns containment and observation. -**Filter config-file rejections in `installFailLoud`.** Rejected: the fail-loud handler exists to make late load failures visible; teaching it to classify exceptions by origin would silently swallow genuine boot failures and leave the stale-`data` crash in place. +**Restart the process for every config edit.** Rejected because Cordis effects already provide reversible plugin lifecycle, and a syntax error or failed optional plugin must not discard live sessions merely to recover the prior composition. -**A PTY e2e proving the TUI survives a bad edit.** Rejected as the primary gate: the PTY smoke reads the repo's committed `cordis.yml`, so corrupting it in-place is not test-safe, and a temp copy cannot resolve the tree's bare package specifiers. The unit spec drives the exact `refresh()` entry point the watcher calls; the fix was additionally verified manually against the live TUI (bad YAML, empty file, restored file). +**Promise invisible atomic replacement.** Rejected because arbitrary plugin effects cannot be snapshotted. Awaited application plus explicit compensation provides a stable final result without claiming that observers cannot see intermediate lifecycle transitions. ## Consequences -- A bad `cordis.yml` edit now logs `ignoring config reload at ` and the agent keeps running on the last good tree; the next valid edit applies normally. With no logger exporter mounted in the TUI demos the warning is currently invisible on screen — surfacing loader warnings in the TUI is deferred. -- Overlay trees survive base-file reloads with patches intact instead of silently reverting to the unpatched base. -- The vendored include diverges further from upstream; the divergence is logged in the vendor manifest and re-applies on the next sync. -- Known gap, out of scope here: the HMR watcher only handles chokidar `change` events, so editors that replace the file by rename (BSD `sed -i`, `git checkout`) do not trigger a config reload at all; and a reloaded app-entry config does not visibly restart the running TUI (pre-existing on the unmodified tree). +- A failed live refresh rejects internally, retains or restores the last-good tree when compensation succeeds, and broadcasts one typed failure without becoming an unhandled rejection. +- A rollback failure is visible and may leave an entry unavailable; the event and log do not claim otherwise. +- Fibers waiting on declared dependencies remain valid pending entries: lifecycle settlement means no current work failed, not that every dependency exists. +- Exact config watchers add filesystem resources only for registered paths and release them with their owning HMR fiber. +- The vendored Loader, Include, HMR, and core event typing diverge further from upstream; the complete divergence is maintained in the vendor manifest. ## Testing -`packages/ui/app-boot/tests/config-reload.spec.ts` boots real Loader trees against temp configs and pins: an invalid-YAML edit and an empty-file edit both resolve `refresh()` without rejection and keep the previous entry config; a subsequent valid edit applies; an overlay tree re-applies both entry patches and inserted entries on re-read; a hot-update of the include entry's own `patches` applies immediately, survives the next file re-read, and reverts cleanly when the patches are removed. The assertions fail on the unpatched vendored include. +`packages/ui/app-boot/tests/config-reload.spec.ts` boots real temporary Loader/Include trees and covers parse and shape rejection, import-before-dispose, plugin/config restoration, multi-entry rollback, ancestor disablement, overlay convergence, option identity, failed direct-update persistence, and failed programmatic moves. `packages/ui/app-boot/tests/hmr-config.spec.ts` covers existing and missing exact paths, add/change/removal, serialized coalescing, disposal drainage, non-`Error` normalization, failure broadcast, and rejecting-observer containment. `packages/host/webserver/tests/webserver.spec.ts` proves a service-gated startup failure rejects Loader composition with its bind diagnostic, `packages/typert/loader/tests/loader.spec.ts` exercises awaited programmatic removal through a real Loader consumer, and the ACP `pty-tools` snapshot guards concurrent composition from reordering equal-priority prompt sections. diff --git a/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.zh.md b/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.zh.md index 6c7a421bfa..8a185c1915 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-20-config-hot-reload-resilience.zh.md @@ -6,33 +6,36 @@ Status: implemented ## Problem -各示例应用把 `@cordisjs/plugin-hmr` 挂载为叶子配置项，让运行中的 agent 能感知 `cordis.yml` 的编辑。一次错误的编辑就会杀死进程：`Include.refresh()` 把 YAML 解析错误原样抛出，HMR 的文件监听器在一个无人捕获的异步 chokidar 回调里 await `refresh()`，产生的未处理 rejection 触发 `dsh-app-boot` 的快速失败处理器——会话中途 `exit(1)`，正在运行的 TUI 就此丢失。另有两个相邻缺陷让*合法*的重载也出错：解析结果为 `undefined` 的文件（空文件或写入中途被截断的文件——编辑器和 `sed -i` 常态性地产生这类中间状态）会让配置项遍历直接崩溃，而不是被判定为无效文件；并且重新读取时从不重新应用 include 的 `config.patches`，因此对基于 overlay 的配置树（Code Mode、个人 overlay）做任何热重载，都会悄悄把打过补丁的配置项回退、并把插入的配置项移除。 +无效的 `cordis.yml` 编辑不得杀死运行中的 agent（智能体）；但若一次看似有效的更新先部分替换 Loader 树，后续配置项才失败，仅仅保住进程仍不够。调用方还需要能观察到被拒绝的实时更新，同时不能让同一个错误被当作未处理的启动失败。个人配置还带来第二项要求：HMR（热模块替换）必须观察其模块根目录之外的一个确切文件，包括启动后才创建的文件或父目录。 ## Decision -加固 vendor 的 `@cordisjs/plugin-include`（在 [vendor/README.md](../../../../vendor/README.md) 中记录为本地修改第 8 条），而不是修改调用方： +vendor 中的 Cordis 生命周期和 Loader 插件提供可等待、带补偿的配置事务，并在 [vendor/README.md](../../../../vendor/README.md) 中记录为本地修改第 6、8、9 条。 -- `refresh()` await 整个「读取并更新」过程并捕获失败，记录一条警告，并保留上一份完好的配置树。热重载是尽力而为的；不变式是编辑器可能产生的任何文件状态都不得导致进程退出。 -- `read()` 对非数组的解析结果抛出 `TypeError`，把 `undefined` 解析结果并入同一个「无效文件」信号，并且只在解析成功后才提交 `content`/`data`——因此把编辑撤销回与上一份完好内容完全一致时，会正确地判定为「无变化」。 -- `refresh()` 与 `internal/update` 监听器在 `root.update()` 之前调用 `this.applyPatches(...)`，与 `[Service.init]` 保持一致。`applyPatches` 对缓存的解析结果做深拷贝（`structuredClone`）而不是就地修改，因此重复应用会收敛，移除补丁会回退到文件自身的值。监听器使用传入配置中的 `patches` 并自行持久化该配置：它否决 fiber 重启（子配置项就地更新），而 `Fiber.update` 只在 `next()` 之后才赋值 `this.config`，若不显式赋值，下一次重新读取会重新应用旧的 overlay。 +`Fiber.update()` 返回其 `internal/update` waterfall（瀑布式事件）的结果。配置校验保持同步，而默认 continuation 返回重启 promise。因此，Loader 配置项更新可以区分校验、导入、应用和回滚失败，以及生命周期成功完成。`EntryTree.await()` 会在 Loader 任务排空后重新检查受服务门控的 fiber，并在 fiber 已结算为失败时 reject；等待缺失服务的 fiber 仍是有效的 pending 配置项，不会让结算挂起。 -启动期行为保持快速失败并获得更准确的诊断：`[Service.init]` 只在 `ENOENT` 时回退到 `initial`（或「config file not found」）；存在但无效的文件现在会以真实的解析错误失败，而不是被误标为文件缺失、或被 `initial` 静默覆盖。 +Loader 会先导入变化后的模块名，再 dispose（资源释放）活动 fiber。它会 await 候选项的应用；若失败，则 dispose 候选项的 effect，并恢复先前的插件或配置。组内对账会并发启动各候选项，等待每项结果，并会在拒绝前恢复已变更的配置项、添加项、移除项和移动项。只有程序化变更成功后才会持久化。这是一种补偿事务：生命周期 effect 可能短暂可见；回滚失败会报告为 `AggregateError`，而不会被误称为树已保留。 + +Include 读取并校验尚未提交的候选内容，把补丁应用到其副本，对账 Loader 树，然后才提交缓存内容和解析数据。解析、校验、应用或回滚失败后，`refresh()` 会向调用方 reject。初始加载继续快速失败；只有文件不存在时才可以使用 `initial`。YAML/JSON 结果若不是数组即为无效；文件刷新和 Include 配置更新都会重新应用补丁，且不修改缓存的解析结果。 + +HMR 收容实时刷新 rejection。其 `registerConfig(filename, refresh)` 方法从最近的现有祖先目录开始监听一个确切路径，串行化并合并刷新，并返回一个异步 disposer；该 disposer 会关闭 watcher 并排空活跃工作。确切路径和普通配置文件的刷新都使用此队列。失败会被规范化为 `Error`、记入日志，并通过并行事件 `hmr/config-update-failed(filename, error)` 广播；发生 rejection 的观察者会被记录，但不会阻止后续刷新。创建、变更和移除均会被观察。 ## Alternatives considered -**在 HMR 监听回调里捕获，而不是在 `refresh()` 里。** 否决：这会让 `refresh()` 继续成为其他所有调用方的陷阱（`internal/update` 路径共享同一套树更新逻辑），而且无法修复 `undefined` 解析结果与补丁丢失这两个位于 include 内部的缺陷。 +**在 `Include.refresh()` 内收容失败。** 已否决，因为这会使 HMR 宿主无法广播失败，却仍允许 Loader 对账掩盖部分应用。Include 负责候选内容的解析与提交；HMR 负责收容和观察。 -**在 `installFailLoud` 里过滤配置文件相关的 rejection。** 否决：快速失败处理器的存在意义就是让延迟出现的加载失败可见；教它按来源给异常分类会悄悄吞掉真正的启动失败，并且原样保留陈旧 `data` 导致的崩溃。 +**每次编辑配置都重启进程。** 已否决，因为 Cordis effect 已经提供可逆的插件生命周期，而语法错误或可选插件失败不应只为恢复先前的组合就丢弃正在进行的会话。 -**用 PTY e2e 证明 TUI 能在错误编辑后存活。** 否决其作为主要门禁：PTY 冒烟测试读取仓库中已提交的 `cordis.yml`，就地破坏它对测试不安全，而临时副本无法解析该配置树的裸包说明符。单元测试直接驱动监听器所调用的 `refresh()` 入口；此外还对运行中的 TUI 做了人工验证（错误 YAML、空文件、恢复文件）。 +**承诺不可见的原子替换。** 已否决，因为任意插件 effect 无法制作快照。等待应用完成并显式补偿可以得到稳定的最终结果，同时不会声称观察者看不到中间生命周期转换。 ## Consequences -- 现在错误的 `cordis.yml` 编辑会记录 `ignoring config reload at `，agent 继续运行在上一份完好的配置树上；下一次合法编辑正常生效。TUI 示例没有挂载任何日志导出器，这条警告目前不会显示在屏幕上——在 TUI 中呈现 loader 警告的工作暂缓。 -- overlay 配置树在基础文件重载后补丁保持完整，不再悄悄回退到未打补丁的基础配置。 -- vendor 的 include 与上游进一步分叉；该分叉已记录在 vendor 的 manifest 里，下次同步时重新应用。 -- 已知缺口，不在本次范围内：HMR 监听器只处理 chokidar 的 `change` 事件，因此通过重命名替换文件的编辑方式（BSD `sed -i`、`git checkout`）完全不会触发配置重载；应用配置项重载后也不会可见地重启运行中的 TUI（未修改的代码树上即已如此）。 +- 实时刷新失败会在内部 reject；补偿成功时会保留或恢复上一份完好的树，并广播一次类型化失败，而不会成为未处理的 rejection。 +- 回滚失败可见，并可能使一个配置项不可用；事件和日志不会误称其已恢复。 +- 等待已声明依赖的 fiber 仍是有效的 pending 配置项：生命周期完成只表示当前工作均未失败，而不表示每项依赖都存在。 +- 确切配置 watcher 只为已注册路径增加文件系统资源，并随其所属 HMR fiber 一起释放。 +- vendor 中的 Loader、Include、HMR 与核心事件类型定义进一步偏离上游；全部分叉均维护在 vendor manifest（元数据清单）中。 ## Testing -`packages/ui/app-boot/tests/config-reload.spec.ts` 用真实 Loader 树加载临时配置并固定以下行为：无效 YAML 编辑和空文件编辑都让 `refresh()` 正常 resolve 而不产生 rejection，并保留之前的配置项配置；随后的合法编辑正常生效；overlay 配置树在重新读取时重新应用配置项补丁和插入的配置项；对 include 配置项自身 `patches` 的热更新立即生效、在下一次文件重读后依然保持、并在补丁移除后干净地回退。这些断言在未打补丁的 vendor include 上会失败。 +`packages/ui/app-boot/tests/config-reload.spec.ts` 启动真实的临时 Loader/Include 树，并覆盖对解析和形状错误的拒绝、先导入再 dispose、插件/配置恢复、多配置项回滚、祖先禁用、overlay 收敛、option 对象身份、失败的直接更新不持久化以及失败的程序化移动。`packages/ui/app-boot/tests/hmr-config.spec.ts` 覆盖现有和缺失的确切路径、添加/变更/移除、串行化合并、dispose 排空、非 `Error` 值的规范化、失败广播以及对发生 rejection 的观察者的收容。`packages/host/webserver/tests/webserver.spec.ts` 证明受服务门控的启动失败会让 Loader 组合以其 bind 诊断 reject；`packages/typert/loader/tests/loader.spec.ts` 则通过真实 Loader 消费方演练可等待的程序化移除；ACP（Agent Client Protocol）的 `pty-tools` 快照会防止并发组合改变同优先级提示词段的顺序。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.i18n.yaml deleted file mode 100644 index 98dfa90c4d..0000000000 --- a/.agents/notes/implemented/bug-fix/2026-07-23-tui-generic-card-markdown.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# 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 -2026-07-23-tui-generic-card-markdown.md: 494ba580480fa99de54e84025a65bf4589d410f2 -2026-07-23-tui-generic-card-markdown.zh.md: 214edd00f50b88a4e8901b19dcdafc7382399831 diff --git a/.agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.i18n.yaml deleted file mode 100644 index 6d83cc0cf3..0000000000 --- a/.agents/notes/implemented/bug-fix/2026-07-24-tui-turn-end-stop-reason-notices.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# 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 -2026-07-24-tui-turn-end-stop-reason-notices.md: 7c783ce5a347b15d682dbeca03ad5355aca7950b -2026-07-24-tui-turn-end-stop-reason-notices.zh.md: 4a983525779b96c296ac2d621ca5928e7bed61c9 diff --git a/.agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.i18n.yaml deleted file mode 100644 index c246c6fb0d..0000000000 --- a/.agents/notes/implemented/bug-fix/2026-07-27-tui-step-timing-trails-tool-cards.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# 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 -2026-07-27-tui-step-timing-trails-tool-cards.md: 82f46b44d3b939ca89c4508eb948ed584082d9fd -2026-07-27-tui-step-timing-trails-tool-cards.zh.md: 885b232973d20013782dee7ec1e846e7a012b01e diff --git a/.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.i18n.yaml new file mode 100644 index 0000000000..483bfd9e86 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.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/2026-07-28-web-agent-runtime-context.md +2026-07-28-web-agent-runtime-context.md: 449c9d4ba2b144d02dee4b98ae80c86815aec5c1 +2026-07-28-web-agent-runtime-context.zh.md: def1674be5f193739bfb214a24f34590ee075d5f diff --git a/.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.md b/.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.md new file mode 100644 index 0000000000..449c9d4ba2 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.md @@ -0,0 +1,33 @@ +# Agent Note: Web agents receive explicit runtime context + +Status: implemented + +English | [中文](2026-07-28-web-agent-runtime-context.zh.md) + +## Problem + +The shared CLI base configured an empty deployment persona, the Web overlay did not replace it, and the Web launcher added no source or interaction-surface section. A session header recorded its working directory for tools and persistence, but the model prompt did not state that directory or identify the DeepSeek Harness Web GUI. A request such as “change this page's theme” therefore made the agent search the selected project for an unspecified page, even when the user meant the GUI running the session. + +## Decision + +The shared Web/headless overlay (`apps/cli/config/web.cordis.yml`) supplies a concise coding-agent persona containing the resolved `{{model}}` and session `{{cwd}}`. `dsh web` additionally resolves the harness checkout from the launcher's module URL, installs the existing `harness:source` section, and adds an `app:web-surface` section before serving requests. The launcher registers that setup before mounting the config tree; its `systemPrompt` injection therefore installs both sections before later prompt consumers such as the agent loop can activate and emit a request header. The [source-checkout/workdir decision](2026-07-30-source-checkout-workdir-distinction.md) owns the source section's wording and its warning not to infer one path from the other. + +The Web section treats unqualified references to “this page,” “this GUI,” or “this app” as references to the DeepSeek Harness Web GUI. It also states that the browser provides no implicit DOM, route, or screenshot context, so the model can identify the product without claiming visual state it did not receive. The assembled text is logged in `request/header`, preserving the model-visible/logged invariant. + +## Verification + +The focused startup-order test registers a later `systemPrompt` consumer and proves that it observes both launcher sections on its first activation. The keyless fresh-round-trip Web scenario boots the shipped base plus Web overlay, registers the same launcher context as `dsh web`, runs a real session through the HTTP/SSE application, and snapshots the first four system-prompt sections with source and working-directory paths normalized. The snapshot pins the harness identity, source checkout, Web orientation, and resolved coding-agent persona in request order. + +## Alternatives considered + +**Send URL, DOM, or screenshots with every prompt.** The observed failure needed stable product orientation, while the current root URL does not identify a selected component and no visual capture exists in the message contract. Adding dynamic page state would require a separate logged model-input design and is not implied by this fix. + +**Require the session Workspace to be the harness checkout.** Workspace cwd is the user's task target and may legitimately be an empty project or another repository. Conflating it with the application's source location would break that boundary and leave installed or externally launched sessions ambiguous. + +**Put Web wording in the global harness identity.** `dsh-system-prompt` serves TUI, ACP, SDK, and custom deployments that do not run in a browser. The composing Web app owns this surface fact. + +**Change the existing source-location section for every CLI surface.** The source section is shared with TUI and states only the checkout fact. Keeping Web orientation separate preserves that reusable contract and avoids telling headless or terminal agents that they are in a browser. + +## Consequences + +Web requests gain a short stable prompt prefix and may invalidate provider prefix caches once when this change is deployed. Agents can distinguish the GUI source checkout from the selected Workspace and resolve ordinary references to the current app without a clarification round trip. References to a specific visual state remain bounded by the explicit no-DOM/no-route/no-screenshot statement and may still require a path, description, or attachment. diff --git a/.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.zh.md b/.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.zh.md new file mode 100644 index 0000000000..def1674be5 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.zh.md @@ -0,0 +1,33 @@ +# Agent Note: Web agent 获得显式运行时上下文 + +Status: implemented + +[English](2026-07-28-web-agent-runtime-context.md) | 中文 + +## 问题 + +CLI 共享 base 配置了空的部署 persona，Web overlay 没有替换它，而 Web 启动器既未添加源码提示词段，也未添加交互界面提示词段。会话 header 会记录工作目录，供工具与持久化使用，但模型提示词既不说明该目录，也不标识 DeepSeek Harness Web GUI。因此，当用户提出「修改这个页面的主题」之类的请求时，即使用户指的是承载当前会话的 GUI，agent 也只能在所选项目中搜索一个未明确说明的页面。 + +## 决策 + +`apps/cli/config/web.cordis.yml` 这份 Web／无头共享 overlay 提供一段简洁的编码 agent persona，其中包含解析后的 `{{model}}` 与会话 `{{cwd}}`。`dsh web` 还会根据启动器模块的 URL 解析 harness checkout，安装现有的 `harness:source` 提示词段，并在对外提供请求服务前添加 `app:web-surface` 提示词段。启动器会在挂载配置树前注册这项设置；因此，它的 `systemPrompt` 注入会在 agent loop（智能体循环）等后续提示词消费方激活并发出 request header 之前安装这两个提示词段。源码提示词段的措辞，以及其中不得从一条路径推断另一条路径的警告，均由另行记录的[源码 checkout 与工作目录区分决策](2026-07-30-source-checkout-workdir-distinction.md)负责。 + +Web 提示词段把未限定的「这个页面」「这个 GUI」或「这个应用」解释为 DeepSeek Harness Web GUI。同时，它会明确说明浏览器不会隐式提供 DOM、路由或截图上下文，使模型能够识别产品，但不会声称掌握未收到的视觉状态。组装后的文本会记录在 `request/header` 中，从而保持「模型可见内容必须有日志记录」这一不变量。 + +## 验证 + +聚焦启动顺序的测试会注册一个后续的 `systemPrompt` 消费方，并证明该消费方首次激活时就能观察到启动器的两个提示词段。无密钥的 Web fresh-round-trip 场景会启动已交付的 base 与 Web overlay，注册与 `dsh web` 相同的启动器上下文，并通过 HTTP／SSE 应用运行一个真实会话。测试会把源码路径和工作目录规范化，然后对系统提示词的前四个段落生成快照。该快照按请求顺序固定 harness 身份、源码 checkout、Web 界面定位，以及解析后的编码 agent persona。 + +## 考虑过的替代方案 + +**每次提示词都发送 URL、DOM 或截图。** 本次故障只需要稳定的产品定位；当前根 URL 无法标识所选组件，消息契约中也不存在视觉捕获内容。添加动态页面状态需要另行设计可记录的模型输入，不属于本次修复的隐含范围。 + +**要求会话 Workspace 必须是 harness checkout。** Workspace cwd 是用户任务的目标，可以合理地指向空项目或其他仓库。将其与应用源码位置混为一谈会破坏这一边界，并且仍无法消除已安装版本或外部启动会话中的歧义。 + +**把 Web 文案放入全局 harness 身份。** `dsh-system-prompt` 还服务于 TUI、ACP、SDK 和不在浏览器中运行的自定义部署。该界面事实应由组装 Web 应用负责。 + +**为所有 CLI 界面修改现有源码位置提示词段。** TUI 也复用源码位置提示词段，而该段只陈述 checkout 事实。单独保留 Web 界面定位可以维持这份可复用契约，避免错误地告诉无头或终端 agent 它们正处于浏览器中。 + +## 影响 + +Web 请求会增加一段较短且稳定的提示词前缀；部署此变更时，模型提供方的前缀缓存可能失效一次。agent 可以区分 GUI 源码 checkout 与所选 Workspace，并且无需再经过一轮澄清即可解析对当前应用的一般指代。对特定视觉状态的指代仍受「无 DOM／无路由／无截图」这一显式边界约束，必要时仍需用户提供路径、描述或附件。 diff --git a/.agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.i18n.yaml similarity index 58% rename from .agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.i18n.yaml rename to .agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.i18n.yaml index 4574ce7c75..6feeb0e71f 100644 --- a/.agents/notes/implemented/feature/2026-07-21-tui-skill-slash-command.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.i18n.yaml @@ -1,6 +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/feature/2026-07-21-tui-skill-slash-command.md -2026-07-21-tui-skill-slash-command.md: 872e1f109728731e0d55e81a538c81e794724856 -2026-07-21-tui-skill-slash-command.zh.md: 772e25745ea7ab25f715208a9c6b1d10cf0c6e65 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.md +2026-07-28-web-gui-feedback-loop.md: 039d2aebeeef903d10838a46b48e5172f0195126 +2026-07-28-web-gui-feedback-loop.zh.md: 34b6b26d4ce7c7e194e641536fffc503c013188b diff --git a/.agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.md b/.agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.md new file mode 100644 index 0000000000..039d2aebee --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.md @@ -0,0 +1,39 @@ +# Agent Note: Web GUI changes close the loop on the existing URL + +Status: implemented + +English | [中文](2026-07-28-web-gui-feedback-loop.zh.md) + +## Problem + +The Web agent could identify neither the GUI hosting its session nor the URL the user was viewing. The [runtime-context decision](2026-07-28-web-agent-runtime-context.md) supplies the first fact, but a GUI edit still had no executable acceptance target: source edits, artifact builds, a listening process, and the user's existing page were unrelated observations. Repository affordances made a wrong substitute look valid because `apps/web/package.json` exposed `vite` as its `dev` script and bare Vite returned HTTP 200 even though it could not inject `window.__DSH_BOOT__`. + +The [incident post-mortem](../../../../docs/postmortem/0003-web-agent-gui-feedback-loop.md) owns the event-log timeline and why the original checks accepted the wrong page, process, and port. + +## Decision + +`dsh web` publishes one canonical loopback URL and its actual runtime mode as both model-visible orientation and managed shell facts. The `app:web-surface` prompt section says that unqualified references identify this GUI and names the URL; `DSH_WEB_URL` and `DSH_WEB_MODE=production|development` carry the same facts into every foreground or managed background bash call. The section preserves the no-implicit-DOM, route, or screenshot boundary and does not claim that a LAN alias equals the browser's literal address. + +The mode-specific prompt makes the agent, rather than the user, own the hidden startup contract. Production mode defines acceptance as rebuilding the affected artifacts and refreshing the existing URL. Development mode states that `dsh web --dev` activates only the HMR receiver: automatic client-plugin reload additionally requires a same-checkout `pnpm run dev:web` watcher, which the agent verifies before promising no-refresh updates. Shell and other plain-package changes still require rebuild plus refresh. An agent in production mode explains both commands when a user requests no-refresh updates; it does not launch a replacement GUI unless asked. + +The `apps/web` development script and Vite configuration reject serve mode before opening a port. Their diagnostics identify `apps/web` as a build-only shell, explain that only `dsh web` injects `window.__DSH_BOOT__`, and name the production and HMR entry paths. Vite build mode remains unchanged. + +No server restart or replacement is required merely because static artifacts changed. The host reads `index.html` and static assets on each request, while client bundles are also served from their current files with `no-cache`; a refresh of the existing URL is therefore the acceptance path after the relevant shell and plugin bundles are rebuilt. Starting a separate server proves only that a separate server works. If the user explicitly requests another long-running server, the existing managed background-task contract owns its lifecycle and completion notices; shell `&` is not an alternative lifecycle. + +## Verification + +The keyless fresh-round-trip browser scenario boots the shipped production Web composition, drives a real replayed session, snapshots the URL/mode-bearing system-prompt prefix, and invokes the assembled bash tool to prove `$DSH_WEB_URL` and `$DSH_WEB_MODE` match the actual bound runtime. The real CLI smoke launches `dsh web --dev` and captures the provider request, pinning the complete two-command development contract. The `dev:web` watcher test rebuilds an isolated client bundle after a source change; the browser HMR scenario launches `dsh web --dev`, changes an initial production-roster bundle, and observes the new DOM under the same page identity. A real Vite subprocess test requires serve mode to exit naturally with the full-host correction and instruments `Server.listen()` to prove it was never called. The real-Loader webserver test rewrites a static asset after the process binds and proves the same port returns the new bytes. These assertions inspect prompt state, process exit, shell output, DOM identity, and HTTP bytes rather than an agent's success statement. + +## Alternatives considered + +**Extend only the system prompt.** Rejected because it would leave the target unavailable to tools, preserve the misleading bare-Vite path, and fail to prove how an existing process observes rebuilt artifacts. + +**Remove the `apps/web` development script without guarding Vite.** Rejected because `npx vite`, the exact incident command, bypasses package scripts. Serve mode itself must fail. + +**Automatically restart or replace the current Web process after every edit.** Rejected because the static server already reads current artifacts per request, a restart would interrupt the session that requested the edit, and plugin HMR has a separate explicit `dsh web --dev` composition. + +**Send DOM, route, or screenshots with each request.** Deferred to a separate logged-input design. Stable URL identity closes this feedback loop without claiming browser state the host does not receive. + +## Consequences + +Web prompts gain a dynamic URL-and-mode paragraph, so provider prefix reuse now varies by bound port and mode. Bash processes gain two non-secret managed environment variables. Bare Vite can no longer be used as a shell-only visual sandbox; developers use the full host or build mode instead. In exchange, GUI work has one mechanically observable target, the agent can teach the user the exact update behavior of the process actually serving their session, and the unsupported startup path fails before a white screen. The URL/mode contract guides the agent away from replacement ports; it does not prohibit arbitrary shell commands from starting one. diff --git a/.agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.zh.md b/.agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.zh.md new file mode 100644 index 0000000000..34b6b26d4c --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.zh.md @@ -0,0 +1,39 @@ +# Agent Note: Web GUI 改动在现有 URL 上闭环 + +Status: implemented + +[English](2026-07-28-web-gui-feedback-loop.md) | 中文 + +## 问题 + +Web agent（智能体）既无法识别承载当前会话的 GUI，也不知道用户正在查看哪个 URL。[运行时上下文决策](2026-07-28-web-agent-runtime-context.md)提供前一项事实，但 GUI 编辑仍然没有可执行的验收目标：源码编辑、产物构建、监听中的进程与用户已打开的页面只是互不关联的观察结果。仓库提供的入口让错误的替代方案显得合理，因为 `apps/web/package.json` 将 `vite` 暴露为 `dev` 脚本，而裸 Vite 即使无法注入 `window.__DSH_BOOT__`，仍会返回 HTTP 200。 + +[事故复盘](../../../../docs/postmortem/0003-web-agent-gui-feedback-loop.md)集中记录事件日志时间线，并解释原有检查为何会接受错误的页面、进程和端口。 + +## 决策 + +`dsh web` 发布一个规范的回环 URL 及其实际运行时模式，同时将二者作为模型可见的界面定位信息和受管 shell 事实。`app:web-surface` 提示词段说明：未加限定的指代指向此 GUI，并给出 URL；`DSH_WEB_URL` 和 `DSH_WEB_MODE=production|development` 会把同样的事实传入每次前台或受管后台 bash 调用。该段保留「不会隐式获得 DOM、路由或截图」这一边界，也不声称局域网别名等于浏览器中的实际地址。 + +按模式区分的提示词让 agent 而非用户负责隐藏的启动契约。生产模式将验收定义为重新构建受影响的产物并刷新现有 URL。开发模式说明，`dsh web --dev` 只会启用 HMR（热模块替换）接收端：客户端插件要自动重新加载，还需要在同一检出中运行 `pnpm run dev:web` 监听进程，agent 会在承诺无需刷新即可更新前验证这一点。外壳和其他普通包的变更仍然需要重新构建并刷新。生产模式下的 agent 会在用户要求无需刷新即可更新时说明这两个命令；除非用户要求，否则不会启动替代 GUI。 + +`apps/web` 开发脚本和 Vite 配置都会在打开端口前拒绝服务模式。诊断信息会指出 `apps/web` 只是一个仅供构建的外壳，说明只有 `dsh web` 才会注入 `window.__DSH_BOOT__`，并给出生产入口与 HMR 入口路径。Vite 构建模式保持不变。 + +静态产物发生变化时，不需要仅为此重启或替换服务器。宿主会在每次请求时读取 `index.html` 和静态资源，客户端 bundle 也会从当前文件提供，并设置 `no-cache`；因此，重新构建相关外壳与插件 bundle 后，刷新现有 URL 就是验收路径。启动另一个服务器只能证明另一个服务器可用。如果用户明确要求再启动一个长期运行的服务器，则现有受管后台任务契约负责其生命周期和完成通知；shell `&` 不能替代这套生命周期机制。 + +## 验证 + +无密钥的 fresh-round-trip 浏览器场景会启动已交付的生产 Web 组合，驱动真实的回放会话，对包含 URL 和模式的系统提示词前缀生成快照，并调用组装后的 bash 工具，证明 `$DSH_WEB_URL` 和 `$DSH_WEB_MODE` 与实际绑定的运行时一致。真实 CLI 冒烟测试会启动 `dsh web --dev` 并捕获模型提供方请求，从而固定完整的双命令开发契约。`dev:web` watcher 测试会在源码发生变化后重新构建隔离的客户端 bundle；浏览器 HMR 场景会启动 `dsh web --dev`，修改生产初始 roster 中的 bundle，并在页面 identity 不变的情况下观察新 DOM。真实 Vite 子进程测试要求服务模式在给出改用完整宿主的纠正信息后自然退出，并通过插桩 `Server.listen()` 证明它从未被调用。真实 loader Web 服务器测试会在进程完成绑定后改写静态资源，并证明同一端口返回新的字节。这些断言检查提示词状态、进程退出状态、shell 输出、DOM identity 和 HTTP 字节，而不是 agent 的成功声明。 + +## 考虑过的替代方案 + +**仅扩展系统提示词。** 不予采纳，因为这样会让工具仍然无法获得目标，保留具有误导性的裸 Vite 路径，并且无法证明现有进程如何观察重新构建的产物。 + +**删除 `apps/web` 开发脚本，但不为 Vite 添加防护。** 不予采纳，因为事故中实际使用的命令 `npx vite` 会绕过包脚本。服务模式本身必须失败。 + +**每次编辑后自动重启或替换当前 Web 进程。** 不予采纳，因为静态服务器本就会在每次请求时读取当前产物，重启还会中断发起编辑请求的会话，而插件 HMR 已有独立且显式的 `dsh web --dev` 组合。 + +**每次请求都发送 DOM、路由或截图。** 推迟到另行设计的已记录输入机制。稳定的 URL 身份足以闭合本次反馈循环，同时不会声称宿主掌握其未接收的浏览器状态。 + +## 影响 + +Web 提示词会增加一个动态 URL 和模式段落，因此模型提供方的前缀复用会随绑定端口和模式变化。Bash 进程会增加两个非敏感的受管环境变量。裸 Vite 不再能用作只依赖 shell 的视觉沙箱；开发者应改用完整宿主或构建模式。作为交换，GUI 工作有了一个可由机制观察的唯一目标，agent 可以向用户说明实际承载其会话的进程究竟如何更新，不受支持的启动路径也会在出现白屏前失败。URL／模式契约会引导 agent 避免使用替代端口，但不会禁止任意 shell 命令启动替代服务。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.i18n.yaml index edb6ac6e4a..1349e9fd47 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.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/bug-fix/2026-07-29-human-transcript-append-origin.md -2026-07-29-human-transcript-append-origin.md: a296b93d538d9c28bd61ee8fd0530863b4bfd878 -2026-07-29-human-transcript-append-origin.zh.md: 96e0cd1038fe8904dfd4c1eceaae9b25339c5dca +2026-07-29-human-transcript-append-origin.md: 4d8d66ea625d02f098da906ae58af1a2e5e41819 +2026-07-29-human-transcript-append-origin.zh.md: d4c1c4a83d868af5e27d7bda2a22827cf9d6c5b1 diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.md b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.md index a296b93d53..4d8d66ea62 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.md +++ b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.md @@ -24,9 +24,9 @@ No persisted event, RPC envelope, compaction transaction, or model-visible surfa ## Deferred -The browser client still builds its conversation from the model surface through `FoldAdapter`, so compaction still collapses web history to a single context row. The same predicate is the fix there, together with an append-order transcript projection and a marker component; that work is a separate change against `packages/client/runtime` and `packages/client/ui-conversation`. +The browser client is fixed separately, in [the web transcript projection note](2026-07-30-web-transcript-log-ordered-projection.md): it projects the same append-origin transcript in log order and renders a marker component, and it closes the pagination hole this change opened — because `session.history` no longer spends quota on the checkpoint, it never cuts on the checkpoint's provenance group, so a page can carry a checkpoint citing a `surfaceOp.start` outside the window, which the browser's surface fold rejected. That hole predates this change (counting could already run past a checkpoint into the range it shadows), but the old rule accidentally covered the case where the checkpoint was the oldest counted message and pulled the whole shadowed range onto its page. -That work must handle a page whose checkpoint cites a `surfaceOp.start` outside the window: pagination no longer spends quota on the checkpoint, so it never cuts on the checkpoint's provenance group, and `FoldAdapter` pads absent events with a non-surface sentinel — so `SurfaceManager` rejects the range and `nodes()` falls back to `degradedSeqs()` with a logged error. The hole predates this change (counting could already run past a checkpoint into the range it shadows), but the old rule accidentally covered the case where the checkpoint was the oldest counted message and pulled the whole shadowed range onto its page. `degradedSeqs()` — every surface-eligible event in append order — is already close to the transcript projection A2 needs, which is the shape to build deliberately rather than reach as a degradation. Rendering compaction *progress* — a terminal indicator while a compaction runs — needs the bracket-first ordering that the queued manual `/compact` work introduces, and is likewise out of scope here. The marker also carries no scale: the checkpoint's `sourceEventSeqs` already hold the shadowed count, so a count or range would tell a reader how much each row folded. That belongs with progress, where the reader meets the other half of the same information. Whoever takes it should fold the terminal's two replacement branches — replay and the live listener, textually identical and 600 lines apart — into one `renderReplacement(event)` first, so the marker's content has a single home. +The terminal's [archived live compaction progress decision](../../archived/feature/2026-07-30-compaction-progress-visibility.md) uses standalone bracket events to drive the existing one-cell indicator. It does not change the completion marker owned here or add scale: the checkpoint's `sourceEventSeqs` remain available for a separately justified count or range. Progress therefore needs neither marker-content changes nor a prerequisite `renderReplacement(event)` extraction. ## Alternatives considered diff --git a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.zh.md b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.zh.md index 96e0cd1038..d4c1c4a83d 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-29-human-transcript-append-origin.zh.md @@ -24,9 +24,9 @@ Status: implemented ## Deferred -浏览器客户端仍通过 `FoldAdapter` 从模型 surface 构建会话，因此压缩在 Web 端仍会把历史折叠成一行上下文。那里的修复用的是同一个谓词，另需按追加顺序的记录投影与一个标记组件；该工作是针对 `packages/client/runtime` 与 `packages/client/ui-conversation` 的独立变更。 +浏览器客户端在[Web 记录投影笔记](2026-07-30-web-transcript-log-ordered-projection.md)中单独修复：它按日志顺序投影同一份 append 来源记录并渲染一个标记组件，同时闭合本次变更打开的分页缺口——因为 `session.history` 不再为检查点消耗额度，它永远不会按检查点的溯源分组切分，于是一页可以携带一个引用了窗口之外 `surfaceOp.start` 的检查点，而浏览器的 surface fold 会拒绝该范围。这个缺口早于本次变更（此前计数就可能越过检查点进入它所遮蔽的范围），但旧规则恰好覆盖了这样一种情形：检查点是最旧的被计数消息，其溯源分组把整段被遮蔽的范围一起拉到该页。 -该工作必须处理这样一页：其检查点引用的 `surfaceOp.start` 落在窗口之外。分页不再为检查点消耗额度，因此永远不会按检查点的溯源分组切分；而 `FoldAdapter` 会用一个非 surface 的哨兵事件填补缺失事件——于是 `SurfaceManager` 拒绝该范围，`nodes()` 退化为 `degradedSeqs()` 并记录一条错误。这个缺口早于本次变更（此前计数就可能越过检查点进入它所遮蔽的范围），但旧规则恰好覆盖了这样一种情形：检查点是最旧的被计数消息，其溯源分组把整段被遮蔽的范围一起拉到该页。`degradedSeqs()`——按追加顺序的每个 surface 可入事件——已经很接近 A2 所需的记录投影，因此那正是应当刻意构建的形态，而不是作为退化路径被动落到的结果。渲染压缩*进度*——压缩运行期间的终端指示——需要排队式手动 `/compact` 工作引入的“先开括号”顺序，同样不在本次范围内。标记同样不携带规模信息：检查点的 `sourceEventSeqs` 已经包含被遮蔽的数量，因此一个计数或区间可以告诉读者每一行折叠了多少内容。这件事属于进度那一侧，读者正是在那里遇到同一份信息的另一半。接手者应当先把终端里两处替换分支——回放与实时监听器，文本完全相同却相隔 600 行——合并为一个 `renderReplacement(event)`，让标记的内容只有一个归处。 +终端的[已归档实时压缩进度决策](../../archived/feature/2026-07-30-compaction-progress-visibility.md)使用独立标记对中的事件驱动现有的单格指示器。它既不改变本文所负责的完成标记，也不添加规模信息：检查点的 `sourceEventSeqs` 仍可供经另行论证的计数或区间使用。因此，进度显示既不需要修改标记内容，也不以提取 `renderReplacement(event)` 为前置条件。 ## Alternatives considered diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.i18n.yaml index a6db678efa..fa83836e46 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.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/bug-fix/2026-07-30-composer-context-stack-order.md -2026-07-30-composer-context-stack-order.md: 9c269bcaf7fa360b6a5d0e16fd8cda48aa285d66 -2026-07-30-composer-context-stack-order.zh.md: 47288141ea4591b29adde0f85e810fc797740488 +2026-07-30-composer-context-stack-order.md: 150225ce27fa8459703170622cef754b7694e2fc +2026-07-30-composer-context-stack-order.zh.md: f13ffc3c1136707a86ba5636a5b69304a132df01 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.md b/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.md index 9c269bcaf7..150225ce27 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.md +++ b/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.md @@ -10,7 +10,7 @@ Goal, Todo, and Queue contribute independently to the same `conversation.input.d ## Decision -The composer context stack has one canonical ascending order: Goal at `0`, Todo at `10`, and Queue at `20`, followed by the composer bar outside the list. The gaps leave room for future entries to declare their intended position without relying on plugin activation order. +The [Todo-first alignment decision](2026-08-02-todo-first-composer-context-order.md) owns the current ascending order. This note retains the stack contract around that order: numeric gaps leave room for future entries to declare their intended position without relying on plugin activation order, and the composer bar follows the list. `ConversationRoot` owns the 6px space between independent context cards. Goal is a standalone 752×36px card and collapsed Todo is a standalone 752×44px card. Queue is the terminal dock entry: its 776px wrapper contains the same 752px panel column and subtracts the shared gap plus a named 5px layout overlap, so the later composer card paints over only the queue edge. Empty entries render null and consume no gap. @@ -18,7 +18,7 @@ The order and overlap are separate contracts. Registration order establishes sem ## Verification -Registration tests pin all three order values. Browser screenshots cover the full Goal/Todo/Queue matrix, Goal+Todo without Queue, and Queue alone; together they exercise every adjacency: Goal–Todo, Todo–Queue, and Queue–Composer. +Registration tests pin all three order values. The keyless Queue browser scenario renders Todo, Goal, and Queue together, pins their accessibility order, and checks their visible card edges; focused Goal and Queue scenarios cover their independent states. ## Alternatives considered @@ -30,4 +30,4 @@ Registration tests pin all three order values. Browser screenshots cover the ful ## Consequences -The visual hierarchy is stable for every presence combination, and Queue is the only context surface joined to the composer. New input-dock plugins must choose an order relative to Goal `0`, Todo `10`, and Queue `20`; an entry after Queue also requires an explicit decision about which surface owns the composer boundary. +The visual hierarchy is stable for every presence combination, and Queue is the only context surface joined to the composer. New input-dock plugins must choose an order relative to Todo `0`, Goal `10`, and Queue `20`; an entry after Queue also requires an explicit decision about which surface owns the composer boundary. diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.zh.md b/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.zh.md index 47288141ea..f13ffc3c11 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-30-composer-context-stack-order.zh.md @@ -10,7 +10,7 @@ Goal、Todo 与 Queue 独立注册到同一个 `conversation.input.dock` 列表 ## 决策 -composer 上下文堆栈采用唯一规范的升序排列：Goal 为 `0`，Todo 为 `10`，Queue 为 `20`，随后是位于列表外的 composer bar。顺序值之间的空档使未来条目可以声明预期位置，不必依赖插件激活顺序。 +[Todo 优先的对齐决策](2026-08-02-todo-first-composer-context-order.md)规定当前的升序排列。本记录保留围绕该顺序的堆栈契约：数值间隔使未来条目可以声明预期位置，不必依赖插件激活顺序；composer bar 位于列表之后。 `ConversationRoot` 负责独立上下文卡片之间的 6px 间距。Goal 是一张独立的 752×36px 卡片，折叠后的 Todo 是一张独立的 752×44px 卡片。Queue 是末端 dock 条目：其 776px 包装层包含相同的 752px 面板列，并减去共享间距与具名的 5px 布局重叠量，因此后渲染的 composer 卡片只覆盖 Queue 边缘。空条目渲染为 null，不占用间距。 @@ -18,7 +18,7 @@ composer 上下文堆栈采用唯一规范的升序排列：Goal 为 `0`，Todo ## 验证 -注册测试固定了三个顺序值。浏览器截图覆盖完整的 Goal／Todo／Queue 组合矩阵、没有 Queue 的 Goal+Todo，以及仅有 Queue 的情况；这些场景共同覆盖全部相邻关系：Goal–Todo、Todo–Queue 与 Queue–Composer。 +注册测试固定了三个顺序值。无密钥 Queue 浏览器场景同时渲染 Todo、Goal 和 Queue，固定它们的无障碍顺序，并检查其可见卡片边缘；聚焦的 Goal 与 Queue 场景覆盖各自的独立状态。 ## 考虑过的替代方案 @@ -30,4 +30,4 @@ composer 上下文堆栈采用唯一规范的升序排列：Goal 为 `0`，Todo ## 后果 -所有存在组合下的视觉层级都保持稳定，Queue 是唯一与 composer 相接的上下文界面。新的 input-dock 插件必须相对于 Goal `0`、Todo `10` 与 Queue `20` 选择顺序；若条目位于 Queue 之后，还必须明确决定由哪个界面负责 composer 边界。 +所有存在组合下的视觉层级都保持稳定，Queue 是唯一与 composer 相接的上下文界面。新的 input-dock 插件必须相对于 Todo `0`、Goal `10` 与 Queue `20` 选择顺序；若条目位于 Queue 之后，还必须明确决定由哪个界面负责 composer 边界。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.i18n.yaml new file mode 100644 index 0000000000..ed2f7646bc --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.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/2026-07-30-hover-popup-pointer-grace.md +2026-07-30-hover-popup-pointer-grace.md: 3f60c98ec6453b633feebe408cbc0c0c49eedea1 +2026-07-30-hover-popup-pointer-grace.zh.md: db10e156103284383f911684b2c92977a0315275 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.md b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.md new file mode 100644 index 0000000000..3f60c98ec6 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.md @@ -0,0 +1,35 @@ +# Agent Note: Hover popup pointer grace + +Status: implemented + +English | [中文](2026-07-30-hover-popup-pointer-grace.zh.md) + +## Problem + +Both popups the workspace browser rows raise floated out of reach of the pointer. `HoverCard` closed on the first `pointerleave` from its anchor and rendered its card `pointer-events: none`, but the card sits 8px off the anchor's right edge, so every path to it crossed ground belonging to neither and killed the card before it arrived — the full workspace path and session title it exists to show could be read only in passing. The row action menus passed `closeOnPointerLeave`, whose handler sat on the portaled list: aiming back at the `...` trigger that opened the list closed it, and so did any overshoot past a list edge, with no window to come back. + +## Decision + +`usePointerGrace` ([packages/client/ui-primitives/src/pointer-grace.ts](../../../../packages/client/ui-primitives/src/pointer-grace.ts)) owns one cancelable delayed close, shared by both atoms, with `POINTER_GRACE_MS` at 200. Leaving arms the close; coming back cancels it. Transit through an anchor-to-popup gap is therefore survivable, while a pointer that has genuinely moved on still dismisses the popup. + +`HoverCard` arms the grace on leave instead of closing, and its card no longer sets `pointer-events: none`, so resting on the card holds it open. Re-entering while already open cancels the pending close without restarting the dwell, which keeps the card from blinking when the pointer crosses the gap. A press on the card starts a selection instead of dismissing it; only anchor-region presses and an owner flipping `disabled` dismiss immediately, ahead of the grace. + +`Menu` moves pointer-leave dismissal from the portaled list to the wrapper span. React's enter/leave traversal runs over the React tree, so the trigger and the portaled list are one region there: crossing the 4px gap between them, or aiming back at the trigger, no longer counts as leaving. Leaving is only armed while the list is open, and an owner-driven close (selection, Escape, outside click) disarms a pending grace close in an effect keyed on `open` alone — folding that into the outside-click effect would cancel the grace on every re-render, since owners pass a fresh `onClose` closure each time. + +## Alternatives considered + +**Close the popups only on outside click and Escape.** Rejected because both popups are hover-raised and unlabeled as dismissible; leaving them up after the pointer has moved to another row would strand a card over unrelated content. + +**Widen the anchor's hit area to abut the popup.** Rejected because the 8px and 4px offsets are the design's, and an invisible bridge element would have to track every reposition the fixed-positioned popups already do on scroll and resize. + +**Keep the hover card `pointer-events: none` and only add the grace.** Rejected because the pointer resting on the card would then hit whatever is behind it, so the grace would expire and close the card the user had just reached. + +**Give each atom its own timer.** Rejected because the two closes are the same behavior with the same tuning; a shared hook keeps them from drifting apart. + +## Consequences + +The hover card is now hit-testable and covers 244px of whatever it overlays while shown, which is the price of being reachable; it still lives only as long as the pointer is on the row or the card. Row menus survive the round trip between trigger and list, and a menu that closes for its own reason cannot be reopened into a stale pending close. Menus without `closeOnPointerLeave` are untouched — the wrapper handlers are only attached when it is set. + +## Testing + +`packages/client/ui-primitives/tests/hover-card.spec.tsx` and `tests/atoms.spec.tsx` pin the grace boundary, cancel-on-return, no-second-dwell, disarm-on-owner-close, and the no-arming-while-closed case. The reachability gestures themselves — hovering onto the card, and moving between an open list and its trigger — are pinned in the real browser by `apps/web/tests/workspace-management.e2e.ts`, since they depend on hit testing and layout that jsdom does not model. diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.zh.md b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.zh.md new file mode 100644 index 0000000000..db10e15610 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-hover-popup-pointer-grace.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 悬浮弹层的指针宽限期 + +Status: implemented + +[English](2026-07-30-hover-popup-pointer-grace.md) | 中文 + +## 问题 + +工作区浏览器行弹出的两种弹层都处于指针无法抵达的位置。`HoverCard` 在指针离开锚点的第一个 `pointerleave` 上就关闭，其卡片还设置了 `pointer-events: none`；但卡片位于锚点右边缘外 8px 处，因此通往卡片的每条路径都要穿过既不属于锚点也不属于卡片的区域，卡片在指针抵达之前就已被销毁——它本应展示的完整工作区路径和会话标题只能匆匆一瞥。行操作菜单传入了 `closeOnPointerLeave`，而其处理器挂在传送后的列表上：把指针移回打开该列表的 `...` 触发按钮会关闭列表，越过列表边缘的任何一次抖动同样如此，且没有任何折返窗口。 + +## 决策 + +`usePointerGrace`（[packages/client/ui-primitives/src/pointer-grace.ts](../../../../packages/client/ui-primitives/src/pointer-grace.ts)）持有唯一一个可取消的延迟关闭，由两个原子组件共享，`POINTER_GRACE_MS` 为 200。离开会启动关闭，折返则取消它。因此指针可以安全穿越锚点与弹层之间的间隙，而真正移开的指针仍会关闭弹层。 + +`HoverCard` 在离开时启动宽限期而不再立即关闭，其卡片也不再设置 `pointer-events: none`，因此指针停在卡片上即可让它保持打开。在已打开状态下重新进入只取消待执行的关闭，而不重启停留计时，从而避免指针穿越间隙时卡片闪烁。在卡片上按下指针用于开始文本选择，不会关闭卡片；只有锚点区域内的按下和所有者将 `disabled` 置真，才会抢在宽限期之前立即关闭卡片。 + +`Menu` 把指针离开关闭的处理从传送后的列表移到包裹 span 上。React 的 enter/leave 遍历基于 React 树进行，因此触发按钮与传送后的列表在这里属于同一区域：穿越两者之间 4px 的间隙、或把指针移回触发按钮，都不再算作离开。只有在列表打开时才会启动离开关闭；由所有者驱动的关闭（选择、Escape、外部点击）会在一个仅以 `open` 为依赖的 effect 中解除待执行的宽限关闭——若把它折叠进外部点击的 effect，则每次重新渲染都会取消宽限期，因为所有者每次都传入新的 `onClose` 闭包。 + +## 考虑过的替代方案 + +**仅通过外部点击和 Escape 关闭这两种弹层。** 之所以否决：两者都由悬停唤起，且没有可见的关闭标识；在指针已移到其他行之后仍让它们停留，会把卡片遗留在无关内容之上。 + +**扩大锚点的命中区域，使其与弹层相接。** 之所以否决：8px 与 4px 的偏移来自设计稿，而一个不可见的桥接元素还必须跟随这两个固定定位弹层已经在滚动和缩放时执行的每一次重新定位。 + +**保留悬浮卡片的 `pointer-events: none`，只加入宽限期。** 之所以否决：那样指针停在卡片上时命中的是卡片背后的元素，宽限期仍会到期，并关闭用户刚刚够到的卡片。 + +**让两个原子组件各自持有计时器。** 之所以否决：这两处关闭是同一种行为、同一套调参；共享 hook 可以防止它们各自漂移。 + +## 后果 + +悬浮卡片现在可被命中，显示期间会遮挡其覆盖区域的 244px——这是可抵达性的代价；它依然只在指针位于行或卡片上时存在。行菜单现在能承受触发按钮与列表之间的往返，而因自身原因关闭的菜单也不会被残留的待执行关闭重新关掉。未设置 `closeOnPointerLeave` 的菜单不受影响——只有设置该属性时才会挂上包裹层处理器。 + +## 测试 + +`packages/client/ui-primitives/tests/hover-card.spec.tsx` 与 `tests/atoms.spec.tsx` 固定验证宽限期边界、折返取消、不重启停留计时、所有者关闭时解除待执行关闭，以及列表关闭时不启动关闭。可抵达性手势本身——把指针移到卡片上，以及在打开的列表与其触发按钮之间移动——由 `apps/web/tests/workspace-management.e2e.ts` 在真实浏览器中固定验证，因为它们依赖 jsdom 无法建模的命中测试与布局。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-multi-select-custom-answer-composition.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-30-multi-select-custom-answer-composition.i18n.yaml new file mode 100644 index 0000000000..2f06390bdf --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-multi-select-custom-answer-composition.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/2026-07-30-multi-select-custom-answer-composition.md +2026-07-30-multi-select-custom-answer-composition.md: 581beec89a0f0018ec2df687f5dfe1b1b5b86d22 +2026-07-30-multi-select-custom-answer-composition.zh.md: 5c9cb59822aca3fbf49fbbdf522c76f963df3480 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-multi-select-custom-answer-composition.md b/.agents/notes/implemented/bug-fix/2026-07-30-multi-select-custom-answer-composition.md new file mode 100644 index 0000000000..581beec89a --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-multi-select-custom-answer-composition.md @@ -0,0 +1,25 @@ +# Agent Note: Multi-select custom answer composition + +Status: implemented + +English | [中文](2026-07-30-multi-select-custom-answer-composition.zh.md) + +## Problem + +The user-interaction result vocabulary carries selected option labels and optional custom text in separate fields, but its original semantics made them mutually exclusive for every question. On a multi-select question, opening or typing the custom answer discarded labels the user had already selected. The TUI returned only the custom text, and the Web host rejected a client response that preserved both fields. + +## Decision + +For a question with `multiSelect: true`, one answer item may contain both a non-empty `selected` array and non-empty `custom` text. Web drafts preserve both values regardless of whether the user selects an option or types custom text first; the TUI retains pending custom text across option/custom mode switches and projects it with checked labels from either submit mode; and the Web host accepts the combined response after applying its existing id, label, uniqueness, batch, and non-empty-text validation. + +Single-select and optionless questions keep exclusive semantics: custom text overrides any selected option. The result shape remains `{ id, selected, custom? }`, so no wire or tool-output schema changes. + +## Alternatives considered + +**Encode custom text as another `selected` label.** Rejected because it would erase the distinction between caller-provided option labels and human-authored text, weakening validation and forcing consumers to infer which value was custom. + +**Allow `selected` and `custom` together for every question.** Rejected because a single-select question represents one answer; permitting a selected option plus custom text would make its cardinality ambiguous. The combined form is limited to questions that explicitly opt into multiple answers. + +## Consequences + +Multi-select UIs can represent the user's complete answer without discarding either source. Providers and consumers retain the existing DTO, while request-aware validators interpret the allowed combination from `multiSelect`. Web component and assembled-browser coverage, TUI coverage, host-response coverage, and tool-projection coverage pin the combined result. Web, TUI, and tool-projection coverage also retain labels-only answers; assembled keyless TUI coverage pins the combined terminal flow, and single-select host coverage pins the remaining exclusivity rule. diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-multi-select-custom-answer-composition.zh.md b/.agents/notes/implemented/bug-fix/2026-07-30-multi-select-custom-answer-composition.zh.md new file mode 100644 index 0000000000..5c9cb59822 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-multi-select-custom-answer-composition.zh.md @@ -0,0 +1,25 @@ +# Agent Note: 多选题自定义答案组合 + +Status: implemented + +[English](2026-07-30-multi-select-custom-answer-composition.md) | 中文 + +## 问题 + +用户交互结果的词汇分别通过不同字段携带选中的选项标签和可选的自定义文本，但最初的语义要求每个问题的这两个字段互斥。对于多选题，打开自定义答案或输入文本会丢弃用户已选中的标签。TUI 只返回自定义文本，而 Web 宿主会拒绝同时保留两个字段的客户端响应。 + +## 决策 + +对于 `multiSelect: true` 的问题，一个回答项可以同时包含非空 `selected` 数组与非空 `custom` 文本。无论用户先选择选项还是先输入自定义文本，Web 草稿都会保留两个值；TUI 在选项与自定义模式之间切换时会保留待提交的自定义文本，并在任一模式提交时将其与已勾选的标签一同投影；Web 宿主则在应用现有的 id、标签、唯一性、批次和非空文本校验后接受组合响应。 + +单选题和无选项问题仍保持互斥语义：自定义文本会覆盖任何已选中的选项。结果形状仍为 `{ id, selected, custom? }`，因此协议或工具输出 schema 均无需变更。 + +## 考虑过的替代方案 + +**把自定义文本编码为另一个 `selected` 标签。** 不予采纳，因为这样会抹去调用方提供的选项标签与用户填写文本之间的区别，削弱校验，并迫使消费方推断哪个值属于自定义内容。 + +**允许所有问题同时使用 `selected` 与 `custom`。** 不予采纳，因为单选题只表示一个回答；允许选中选项与自定义文本并存会使其基数含义模糊。组合形式仅适用于显式选择多项回答的问题。 + +## 后果 + +多选 UI 可以完整表达用户的回答，不会丢弃任一来源。提供方和消费方继续使用现有 DTO，而请求感知的校验器会根据 `multiSelect` 判断是否允许组合。Web 组件与组装浏览器的覆盖率、TUI 覆盖率、宿主响应覆盖率和工具投影覆盖率共同固定组合结果。Web、TUI 与工具投影覆盖率还固定了仅含标签的回答形态；组装后的无密钥 TUI 覆盖率固定终端中的组合回答流程，单选题的宿主覆盖率则固定其余的互斥规则。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-source-checkout-workdir-distinction.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-30-source-checkout-workdir-distinction.i18n.yaml new file mode 100644 index 0000000000..311c4971d3 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-source-checkout-workdir-distinction.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/2026-07-30-source-checkout-workdir-distinction.md +2026-07-30-source-checkout-workdir-distinction.md: ba6d9dd12b55a54d4ae8d2e91ad83ac3c1dc47fd +2026-07-30-source-checkout-workdir-distinction.zh.md: ffc2ac7baa2b1bb8ce54607638c35869fc338825 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-source-checkout-workdir-distinction.md b/.agents/notes/implemented/bug-fix/2026-07-30-source-checkout-workdir-distinction.md new file mode 100644 index 0000000000..ba6d9dd12b --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-source-checkout-workdir-distinction.md @@ -0,0 +1,33 @@ +# Agent Note: Source checkout paths do not define working directories + +Status: implemented + +English | [中文](2026-07-30-source-checkout-workdir-distinction.zh.md) + +## Problem + +The `harness:source` prompt section follows the [source-location decision](../../archived/feature/2026-07-21-dsh-system-prompt-source-path.md), but its original wording called the checkout “your own source code” without distinguishing that path from the session workspace. In a normal TUI configuration that does not state `{{cwd}}` in its persona, this may be the only fixed absolute path near the start of the system prompt. DeepSeek V4 could therefore answer “what's the workdir?” with the harness checkout instead of determining the session's current working directory. + +A blanket statement that the checkout is not the working directory would also be false. `dsh meta` intentionally makes the source checkout both values. + +## Decision + +The section identifies the path as the “DeepSeek Harness implementation checkout.” It says that the checkout location and current working directory are separate values that may differ, forbids inferring the working directory from the checkout path, directs the model to use `pwd`, and limits the checkout's purpose to inspecting or extending DSH itself. + +The path derivation, global `harness:source` ownership, and `-99` ordering remain unchanged. Describing the values as conceptually separate rather than always unequal keeps the instruction accurate in both ordinary project sessions and `dsh meta`. + +## Verification + +The `dsh-app-boot` unit test pins the exact text and its ordering. The CLI keyless PTY smoke inspects the assembled request header. The TUI `source-checkout-workdir` snapshot mounts the section with `/opt/dsh-source`, asks “what's the workdir?” through a recorded DeepSeek V4 turn, and requires the replayed transcript to run `pwd` and report the generated workspace rather than the checkout. + +## Alternatives considered + +**Say that the checkout is never the working directory.** Rejected because `dsh meta` deliberately makes them the same path. + +**Put the current working directory in the global source section.** Rejected because the source section is launcher-global while the working directory belongs to each session; combining them would duplicate the loop's `cwd` ownership and make a stable source fact vary per agent. + +**Remove the source path from the prompt.** Rejected because self-referential DSH tools still need a reliable checkout location when the launcher starts from an unrelated project. + +## Consequences + +The prompt is longer and a direct working-directory question may spend one inexpensive `pwd` tool call. In exchange, the model no longer treats the harness implementation path as an implicit task workspace, while meta mode remains truthful when both values coincide. diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-source-checkout-workdir-distinction.zh.md b/.agents/notes/implemented/bug-fix/2026-07-30-source-checkout-workdir-distinction.zh.md new file mode 100644 index 0000000000..ffc2ac7baa --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-source-checkout-workdir-distinction.zh.md @@ -0,0 +1,33 @@ +# Agent Note: 源码 checkout 路径不定义工作目录 + +Status: implemented + +[English](2026-07-30-source-checkout-workdir-distinction.md) | 中文 + +## Problem + +`harness:source` 提示词段遵循[源码位置决策](../../archived/feature/2026-07-21-dsh-system-prompt-source-path.md)，但原有措辞把 checkout 称为“你自己的源代码”，却没有区分该路径与会话 workspace。在 persona 不声明 `{{cwd}}` 的普通 TUI 配置中，这可能是系统提示词开头附近唯一固定的绝对路径。因此，DeepSeek V4 可能会直接用 harness checkout 回答“what's the workdir?”，而不是确定会话的当前工作目录。 + +直接断言 checkout 不是工作目录同样不准确。`dsh meta` 会有意让源码 checkout 同时充当这两个值。 + +## Decision + +该提示词段将路径标识为“DeepSeek Harness implementation checkout”。它说明 checkout 位置与当前工作目录是两个可能不同的值，禁止从 checkout 路径推断工作目录，指示模型使用 `pwd`，并限定该 checkout 只用于检查或扩展 DSH 自身。 + +路径推导方式、全局 `harness:source` 所有权和 `-99` 顺序均保持不变。将两者描述为概念上独立、而不是始终不相等，使这条指令在普通项目会话和 `dsh meta` 中都准确。 + +## Verification + +`dsh-app-boot` 单元测试固定了完整文本及其顺序。CLI 无密钥 PTY 冒烟测试检查组装后的请求 header。TUI 的 `source-checkout-workdir` 快照把该提示词段挂载为 `/opt/dsh-source`，通过录制的 DeepSeek V4 turn 提问“what's the workdir?”，并要求回放 transcript 运行 `pwd`，报告生成的 workspace 而不是 checkout。 + +## Alternatives considered + +**声明 checkout 永远不是工作目录。**拒绝：`dsh meta` 会有意让它们指向同一路径。 + +**把当前工作目录写入全局源码提示词段。**拒绝：源码提示词段由 launcher 全局持有，而工作目录属于各个会话；将两者合并会重复 loop 对 `cwd` 的所有权，还会让稳定的源码事实随 agent 变化。 + +**从提示词中删除源码路径。**拒绝：launcher 从无关项目启动时，自引用 DSH 工具仍需要可靠的 checkout 位置。 + +## Consequences + +提示词会变长，直接询问工作目录时可能多花一次廉价的 `pwd` 工具调用。作为交换，模型不再把 harness 实现路径当作隐含的任务 workspace；当 meta 模式使两个值重合时，提示词仍然准确。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.i18n.yaml new file mode 100644 index 0000000000..26108d6850 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.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/2026-07-30-web-transcript-log-ordered-projection.md +2026-07-30-web-transcript-log-ordered-projection.md: 558d60cf6f6638c3e776396dd754d31b95819b28 +2026-07-30-web-transcript-log-ordered-projection.zh.md: 2eb216fd1970700fb54a2aa17ec5ce515869e5b0 diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md new file mode 100644 index 0000000000..558d60cf6f --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.md @@ -0,0 +1,72 @@ +# Agent Note: The browser conversation is a log-ordered human transcript + +Status: implemented + +English | [中文](2026-07-30-web-transcript-log-ordered-projection.zh.md) + +## Problem + +The browser client built its conversation from the model-visible surface: `FoldAdapter` ran the core `SurfaceManager` over the history window and read `surface.nodes`. A successful compaction replaces a surface range with one checkpoint node, so the moment that replacement landed the web flow collapsed every message it shadowed into a single dim context row — conversation the user had already read. Nothing was lost from the log; the defect was entirely in the projection, and [the terminal and the host gateway were fixed the same way](2026-07-29-human-transcript-append-origin.md) while the browser was left for this change. + +Surface order made two further problems structural. It is not seq-ascending after a replacement — `SurfaceManager` splices the high-seq checkpoint into the position of the range it shadows — so log-only nodes merged into that array by numeric seq (slash-command rows, interrupted frozen nodes) could be flushed ahead of the checkpoint and never interleave into the retained tail again. And because pagination no longer spends `maxMessages` quota on replacement copies, a page can now carry a checkpoint whose `surfaceOp.start` lies outside the window; the core fold rejects that range, so `nodes()` fell back to a lenient linear scan behind a `console.error` and published a `foldDegraded` flag describing the failure. + +## Decision + +`TranscriptAdapter` replaces `FoldAdapter` and never consults surface order. It projects the raw window in log order: every append-origin surface event (`isAppendSurfaceEvent`) at its own log position, plus one `CompactionSummaryNode` marker per landed compaction checkpoint. A landed compaction therefore keeps the conversation it shadowed on the model side, and the marker reports where the model stopped seeing that history instead of erasing it. Model-only replacement copies stay out of the transcript: a pruned `tool/result` and a regenerated `assistant/message` rewrite one node for the model and mark no boundary in the conversation. Everything that must send exactly what the model sees keeps reading the surface; this is the human projection, and the two are now separate on both frontends. + +Node order is seq-monotonic by construction, and three things follow. The log-only `command/run` / `command/done` pair folds into `CommandNode`s that splice into an already-monotonic array by seq — no anchors, no reordering. `Session` keeps ownership of interrupted frozen nodes and merges them by their fractional seqs with a plain sort, which is now exactly flow order. And a window whose checkpoint cites a shadowed range outside it has no range to resolve, so the marker renders and nothing is logged. + +`foldDegraded` is gone from `ConversationSnapshot`, and with it the padding sentinels, the `baseSeq` arithmetic they needed, and `degradedSeqs()`. They existed only to satisfy the core fold's `seq === index` assertion and to survive its throw; the fold they describe is no longer run. Deleting the flag is part of the fix, not cleanup after it — `degradedSeqs()` was already almost the log-ordered projection, reached after a thrown error instead of intended. + +The marker's summary text comes from the checkpoint's own `compact/summary` provenance, never from the framed checkpoint payload, which is an instruction envelope written for the model. A window cut that left the provenance outside makes the row non-expandable rather than empty, the same soft-fall as a call-less tool result, and a later page supplying the provenance resolves the text. + +No persisted event, RPC envelope, compaction transaction, or model-visible surface changed, and no migration is required. + +## Recognizing a checkpoint: one declaration, pinned at compile time + +Recognition needs all three conditions, as in the terminal: `event.type === 'user/message'`, the compaction seam's checkpoint plugin source, **and** `isReplacementSurfaceEvent(event)`. A plugin-sourced `user/message` that *appends* is injected context — a session-reference card — not a compaction. + +What is unreachable from a `packages/client/*` program is `dsh-compact`'s **root**, not the package. The root reaches `dsh-session`'s root, whose cordis `Context` merge declares the host `sessions: SessionStore` against the client's `sessions: ISessions` — `TS2717`, the one-program-per-side rule in [development.md](../../../../docs/development.md#typescript-project-layout) — and that holds for a type-only import too, because the collision is a compiler fact rather than a bundler one. + +The repo's answer to exactly this is a cordis-free leaf subpath, and this change adds one: `COMPACT_CHECKPOINT_SOURCE` and `isCompactCheckpointSource` now live in `packages/compact/compact/src/checkpoint.ts`, which imports no cordis and augments no module (the `dsh-commands/brand` / `dsh-llm/message` shape), and the root re-exports both so every host-side consumer — the terminal's chat helpers, `dsh-session-reference`'s projection — is unchanged. The adapter pins its literal to that declaration with a type-only import: + +```ts +import type { COMPACT_CHECKPOINT_SOURCE } from '@deepseek-ai/dsh-compact/checkpoint' +const COMPACT_PLUGIN: typeof COMPACT_CHECKPOINT_SOURCE.plugin = 'compact' +``` + +Renaming the seam's plugin id is now a compile error in the client: `TS2322: Type '"compact"' is not assignable to type '"compaction"'`. The import must stay **type-only** — a value import of any `@deepseek-ai` package that is neither a platform module nor an inline-safe wire layer is rejected by the client purity gate (`packages/client/tsdown.client.ts`), whose own message records that type-only imports are erased and never reach it. A type-only leaf import needs both a `tsconfig.base.json` `paths` entry and `{"path": "../../compact/compact"}` in `packages/client/runtime/tsconfig.json` `references`: composite `rootDir` rules apply to erased imports as well, and without the reference the diagnostic is `TS6059`/`TS6307`. + +`packages/client/runtime/tests/compact-checkpoint-pin.spec.ts` stays as the behavioral half, driving the adapter with a checkpoint built from the canonical **value**. The test value-imports the cordis-free `@deepseek-ai/dsh-compact/checkpoint` leaf and deliberately never loads the compact package root or the host-side `Context` merges reachable through it. + +The divergence from the terminal is therefore narrow: both frontends recognize a checkpoint from the same declaration — the terminal value-imports `isCompactCheckpointSource` host-side, where no gate applies, and the client pins the type. + +## What #835's positional anchors were for, and why they are dissolved rather than lost + +The unmerged manual-compaction-queueing branch fixes the same interleaving bug by recording a per-event anchor — the surface tail at append time — and retargeting shadowed anchors onto the checkpoint. That mechanism exists to make positional anchors survive surface **reordering**. The human transcript is never re-ordered, so anchors have nothing to retarget: the precondition is removed, not the fix discarded. The mechanism is absent from this base and is not authored here. + +## Alternatives considered + +**Value-import the predicate** from the new leaf and add `dsh-compact` to the client `INLINE_SAFE` allowlist. Rejected: the client needs the plugin id, not the predicate — a type is enough, and an erased import never reaches the purity gate, so nothing has to be admitted to it. The allowlist would only matter for a value import, and there it is a poor trade: `INLINE_SAFE` matches on specifier *prefix*, so admitting the package admits its cordis-importing root along with the leaf. + +**A bare shape rule** — any replacement `user/message` is a compaction. Rejected: correct today only because compaction is the sole producer of replacement `user/message`s, with nothing to catch it if that changes. The pinning spec costs one file and removes exactly that risk. + +**Tag the checkpoint host-side** through the projection or wire contract. Rejected: most aligned with the "collaborate through cordis services" rule, but the client folds raw `SessionEvent`s today, so it means a wire contract change out of proportion to one pure predicate. + +**Move frozen-node ownership into the adapter** (`nodes(extraNodes)`), as the unmerged branch does. Rejected: the interrupted nodes come from the `turn/end` sweep `Session` already runs over the window, and with a seq-monotonic transcript the simple shape is correct — the adapter returns nodes, the session merges frozen ones by seq. Widening the adapter's signature would buy nothing and split the sweep from its product. + +**Keep `foldDegraded` as a defensive flag.** Rejected: it described a specific failure of a fold that no longer runs. A flag no consumer can act on, reachable only through a `console.error`, is a false contract. + +## Consequences + +Compaction no longer erases web history; a session compacted several times shows one marker per landed compaction, in log order, and the same window renders identically live and after a cold resume. The pagination hole is closed by construction rather than defended against, and `ConversationSnapshot` loses a published field, which touched thirteen files. + +`ConversationNode` gains an eighth arm, so every exhaustive consumer grew one case: `MessageItem` renders the marker through the new `CompactionItem`, and the trajectory layout widens its no-cell arm so a marker contributes no cell but still advances the duration cursor. + +The performance contract is unchanged and now simpler to state: one append materializes one node, an event that changes no node keeps the previous array reference — so a chunk storm costs nothing and `nodes()` is not even recomputed — and unchanged nodes keep their object identity. The window still grows with session length rather than with the surface, which is the trade the fix exists to make; a compaction used to bound the projection for exactly the long sessions compaction serves. + +The web e2e scenario now seeds a real compaction transaction over its recorded turn, so the aria golden pins both halves of the fix through the real host and a real browser: the recorded prompt and full tool output are still on screen, and one marker sits after them. The seed recording itself is untouched and stays model-authentic — replay derives the compacted turn from the recording's own surface. + +## Deferred + +The terminal's [archived compaction progress decision](../../archived/feature/2026-07-30-compaction-progress-visibility.md) uses the live standalone bracket to drive a one-cell indicator and does not change this browser projection. The marker still carries no **scale**: the checkpoint's `sourceEventSeqs` hold the shadowed count, so a separately justified count or range can be added without coupling it to progress. diff --git a/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.zh.md b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.zh.md new file mode 100644 index 0000000000..2eb216fd19 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-30-web-transcript-log-ordered-projection.zh.md @@ -0,0 +1,72 @@ +# Agent Note: 浏览器会话是按日志顺序投影的人类对话记录 + +Status: implemented + +[English](2026-07-30-web-transcript-log-ordered-projection.md) | 中文 + +## Problem + +浏览器客户端从模型可见的 surface 构建会话：`FoldAdapter` 在历史窗口上运行核心 `SurfaceManager` 并读取 `surface.nodes`。一次成功的压缩会用一个检查点节点替换一段 surface 范围，因此该替换一落地，Web 流就把它所遮蔽的每条消息折叠成一行灰暗的上下文——那是用户已经读过的对话。日志中什么都没丢失；缺陷完全在投影层，而[终端与宿主历史网关已按同一方式修复](2026-07-29-human-transcript-append-origin.md)，浏览器留给了本次变更。 + +surface 顺序还让另外两个问题成为结构性的。一次替换之后它并非按 seq 升序——`SurfaceManager` 把高 seq 的检查点拼接到它所遮蔽范围的位置上——因此按数值 seq 归并进该数组的仅日志节点（斜杠命令行、被打断的冻结节点）可能被冲刷到检查点之前，再也无法交错回保留下来的尾部。而且由于分页不再为 replacement 副本消耗 `maxMessages` 额度，一页现在可以携带一个 `surfaceOp.start` 落在窗口之外的检查点；核心 fold 拒绝该范围，于是 `nodes()` 退回到一次宽容的线性扫描、打印一条 `console.error`，并发布一个描述该失败的 `foldDegraded` 标志。 + +## Decision + +`TranscriptAdapter` 取代 `FoldAdapter`，并且从不查询 surface 顺序。它按日志顺序投影原始窗口：每个 append 来源的 surface 事件（`isAppendSurfaceEvent`）落在它自己的日志位置上，外加每次落地的压缩检查点一个 `CompactionSummaryNode` 标记。于是一次落地的压缩会保留它在模型侧遮蔽掉的对话，标记报告模型从哪里开始看不见那段历史，而不是把它抹掉。仅模型可见的 replacement 副本不进入记录：被裁剪的 `tool/result` 和重新生成的 `assistant/message` 只为模型重写一个节点，不在对话中标记任何边界。凡必须发送模型所见内容的一切仍读 surface；这是人类投影，两者现在在两个前端上都已分离。 + +节点顺序天然按 seq 单调，由此有三个结果。仅日志的 `command/run` / `command/done` 对折叠成 `CommandNode`，按 seq 插入一个本已单调的数组——无锚点，无重排。`Session` 保留被打断的冻结节点的归属，用一次普通排序按其分数 seq 归并，而这现在恰好就是流顺序。检查点所引被遮蔽范围落在窗口之外的窗口没有范围需要解析，因此标记正常渲染且不打印任何日志。 + +`foldDegraded` 从 `ConversationSnapshot` 消失，随之消失的是哨兵填充、它们所需的 `baseSeq` 算术，以及 `degradedSeqs()`。它们的存在只为满足核心 fold 的 `seq === index` 断言并在其抛错时存活；它们所描述的 fold 已不再运行。删除该标志是修复的一部分，而非修复之后的清理——`degradedSeqs()` 本身已几乎就是按日志顺序的投影，只是作为抛错后的落点而非本意到达。 + +标记的摘要文本来自检查点自己的 `compact/summary` 溯源，绝不取自成框的检查点载荷——那是为模型撰写的指令信封。窗口切分把溯源留在窗口外时该行不可展开而非空白，与无调用的工具结果同一种软退让；后续补上溯源的分页会解析出文本。 + +没有任何持久化事件、RPC 信封、压缩事务或模型可见 surface 发生变化，也不需要迁移。 + +## 识别检查点：同一份声明，在编译期钉住 + +识别需要三个条件同时成立，与终端一致：`event.type === 'user/message'`、压缩缝隙的检查点插件来源，**以及** `isReplacementSurfaceEvent(event)`。一条 append 的插件来源 `user/message` 是注入上下文——跨会话引用卡片——不是压缩。 + +从 `packages/client/*` 程序无法到达的是 `dsh-compact` 的**根部**，而不是这个包。根部会到达 `dsh-session` 的根部，后者的 cordis `Context` 合并声明了宿主侧 `sessions: SessionStore`，与客户端的 `sessions: ISessions` 冲突——`TS2717`，即 [development.md](../../../../docs/development.md#typescript-project-layout) 中每侧一个 program 的规则；这一点对仅类型导入同样成立，因为该冲突是编译器事实而非打包器事实。 + +本仓库对这一情形的既有答案是不含 cordis 的叶子子路径，本次变更就新增了一个：`COMPACT_CHECKPOINT_SOURCE` 与 `isCompactCheckpointSource` 现在住在 `packages/compact/compact/src/checkpoint.ts`，它不导入 cordis、也不增强任何模块（即 `dsh-commands/brand` / `dsh-llm/message` 的形状），而包根重新导出两者，因此每个宿主侧消费方——终端的 chat helper、`dsh-session-reference` 的投影——都不需改动。适配器用仅类型导入把它的字面量钉在该声明上： + +```ts +import type { COMPACT_CHECKPOINT_SOURCE } from '@deepseek-ai/dsh-compact/checkpoint' +const COMPACT_PLUGIN: typeof COMPACT_CHECKPOINT_SOURCE.plugin = 'compact' +``` + +重命名缝隙的插件 id 现在会在客户端产生编译错误：`TS2322: Type '"compact"' is not assignable to type '"compaction"'`。该导入必须保持**仅类型**——任何既非平台模块又非 inline-safe wire 层的 `@deepseek-ai` 包值导入都会被客户端纯度门禁（`packages/client/tsdown.client.ts`）拒绝，而它自己的报错信息就记录着仅类型导入会被擦除、永不抵达该门禁。仅类型的叶子导入同时需要 `tsconfig.base.json` 的一条 `paths` 条目和 `packages/client/runtime/tsconfig.json` `references` 中的 `{"path": "../../compact/compact"}`：composite 的 `rootDir` 规则同样适用于被擦除的导入，缺少该引用时的诊断是 `TS6059`/`TS6307`。 + +`packages/client/runtime/tests/compact-checkpoint-pin.spec.ts` 作为行为侧的另一半保留，用由权威**值**构造的检查点驱动适配器。该测试以值导入方式从不含 cordis 的 `@deepseek-ai/dsh-compact/checkpoint` 叶子路径取得该值，并刻意不加载 compact 包根或经由它可达的宿主侧 `Context` 合并。 + +因此与终端的分歧很窄：两个前端都从同一份声明识别检查点——终端在宿主侧值导入 `isCompactCheckpointSource`（那里不适用任何门禁），客户端钉住类型。 + +## #835 的位置锚点是为什么而存在，以及为什么它是被溶解而非丢失 + +尚未合并的排队式手动压缩分支用另一种方式修同一个交错缺陷：为每个事件记录一个锚点——追加时的 surface 尾部——并把被遮蔽的锚点重定向到检查点上。该机制的存在是为了让位置锚点在 surface **重排**中存活。人类对话记录永不被重排，因此锚点没有任何东西需要重定向：前提被移除，修复并未被丢弃。该机制在本基线上并不存在，本次也不撰写它。 + +## Alternatives considered + +**从新叶子值导入该谓词**，并把 `dsh-compact` 加入客户端 `INLINE_SAFE` 白名单。已拒绝：客户端需要的是插件 id，不是谓词——一个类型就够了，而被擦除的导入根本不会抵达纯度门禁，因此无需向它放行任何东西。白名单只在值导入时才有意义，而在那里它是笔糟糕的交换：`INLINE_SAFE` 按标识符*前缀*匹配，因此放行该包会连它那个会导入 cordis 的根部一起放行。 + +**一条纯形状规则**——任何 replacement `user/message` 都是压缩。已拒绝：它今天正确只因为压缩是 replacement `user/message` 的唯一生产者，一旦这点改变便无任何机制能捕获。那个 pin 测试只花一个文件，就精确消除了这一风险。 + +**在宿主侧给检查点打标**，经投影或线协议。已拒绝：这最贴合“经 cordis 服务协作”的规则，但客户端今天折叠的是原始 `SessionEvent`，因此这意味着一次线协议契约变更——为一个纯谓词付出的代价不成比例。 + +**把冻结节点的归属移进适配器**（`nodes(extraNodes)`），像那个未合并分支所做的那样。已拒绝：被打断的节点来自 `Session` 已经在窗口上运行的 `turn/end` 清扫，而在按 seq 单调的记录之上，简单形态就是正确的——适配器返回节点，会话按 seq 归并冻结节点。加宽适配器签名什么也换不到，还会把清扫与它的产物拆开。 + +**把 `foldDegraded` 留作一个防御性标志。** 已拒绝：它描述的是一个已不再运行的 fold 的特定失败。一个消费方无法据以行动、只能通过 `console.error` 到达的标志，是一份虚假契约。 + +## Consequences + +压缩不再抹掉 Web 历史；一个被压缩多次的会话按日志顺序显示每次落地压缩一个标记，而同一窗口在实时与冷恢复之后渲染完全相同。分页缺口是被构造性闭合而非被防御，`ConversationSnapshot` 少了一个已发布字段，这触及十三个文件。 + +`ConversationNode` 增加第八个分支，因此每个穷尽消费方都多一个分支：`MessageItem` 通过新的 `CompactionItem` 渲染标记，trajectory 布局加宽它的“无单元格”分支，使标记不贡献单元格但仍推进耗时游标。 + +性能契约未变，且现在更易表述：一次追加物化一个节点，不改变任何节点的事件保持上一次的数组引用——因此分片风暴零成本、`nodes()` 甚至不会重算——未变化的节点保持其对象标识。窗口仍随会话长度而非随 surface 增长，这正是本修复存在所要做的交换；一次压缩过去恰好为压缩所服务的长会话限制了投影规模。 + +Web e2e 场景现在在它录制的那一轮之上播种一次真实的压缩事务，因此 aria 基准经真实宿主与真实浏览器钉住修复的两半：录制的提问与完整工具输出仍在屏幕上，其后坐着一个标记。录制本身未被触碰、保持模型真实——回放从录制自身的 surface 派生出被压缩的那一轮。 + +## Deferred + +终端的[已归档压缩进度决策](../../archived/feature/2026-07-30-compaction-progress-visibility.md)使用实时独立标记对驱动单格指示器，并不改变此浏览器投影。标记仍不携带**规模**信息：检查点的 `sourceEventSeqs` 保存被遮蔽的数量，因此可以另行论证后添加计数或区间，而无须将其与进度耦合。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.i18n.yaml index 714bbe8763..02c04c4293 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.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/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md -2026-07-31-composer-text-layers-share-one-scrollport.md: f4ba206bfb0c3b798e8ad37690d804d67ff9af3c -2026-07-31-composer-text-layers-share-one-scrollport.zh.md: 0faca3fb2cab9d4e0a9c3673983014f99edc19d8 +2026-07-31-composer-text-layers-share-one-scrollport.md: 35015161ee1e01129eeb7b29214ac7f8fd4e2e32 +2026-07-31-composer-text-layers-share-one-scrollport.zh.md: eccdcf47c36e126954ff37c7a7137f9d422ab3cd diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md index f4ba206bfb..35015161ee 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md +++ b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.md @@ -30,7 +30,7 @@ Two things the previous mechanism needed are gone with it: **The wrap-width premise.** All three layers now resolve their width inside the scrollport, so a scrollbar that consumes layout space costs them the same width by construction. This closes the divergence the superseded note recorded as open and unfixable by any property: WebKit reserved gutter space for the `overflow-y: auto` textarea and not for the `overflow: hidden` layers beside it, laying the textarea out 768 against 776 — worth 2 to 5 wrapped lines on a long draft, i.e. glyphs under the wrong caret on the one engine where it was observable. Measured on the harness after the change, all three layers report one width on all three engines Playwright ships. -**Edits the composer performs itself now ask for the reveal.** Paste, ctrl/meta-Enter newline and cut suppress the native edit — the machine owns the draft and the undo log — and restore the caret with `setSelectionRange`, which reveals nothing: measured in chromium and WebKit, pasting a long block leaves the view where it was while the caret sits at the end of what was pasted. That defect predates this change (Firefox happened to reveal it, in the old geometry only) and is fixed here because one scrollport is what finally makes the reveal ours to perform. The three restores share one helper that measures the caret against the hidden mirror — same draft, same metrics, same wrap width, so a Range collapsed at the caret's index reports where the caret is without a caret API — and scrolls the minimum that brings it inside, which is what the browser does for typing. +**Edits the composer performs itself now ask for the reveal.** Paste and cut suppress the native edit — the machine owns the draft and the undo log — and restore the caret with `setSelectionRange`, which reveals nothing: measured in chromium and WebKit, pasting a long block leaves the view where it was while the caret sits at the end of what was pasted. That defect predates this change (Firefox happened to reveal it, in the old geometry only) and is fixed here because one scrollport is what finally makes the reveal ours to perform. The two restores share one helper that measures the caret against the hidden mirror — same draft, same metrics, same wrap width, so a Range collapsed at the caret's index reports where the caret is without a caret API — and scrolls the minimum that brings it inside, which is what the browser does for typing. One shape needs a rule of its own, because the engines disagree about it: a caret straight after a newline sits on a line with nothing on it to measure, which is where a trailing-newline draft ends. chromium returns **no client rects at all** for the collapsed position — an all-zero box, which would send the reveal the wrong way — firefox reports the line above, and WebKit the right one. The helper therefore measures the newline the caret just left, whose box is the line it came from, and steps one line down; all three then land on the same offset (649 of 652, with the caret's line at 315 inside the 336px box). @@ -66,7 +66,7 @@ Revealing the caret is the one thing that now depends on the browser rather than - On Firefox and WebKit, clicking into a composer whose draft overflows the cap now also scrolls the conversation transcript to its bottom: the caret's scroll-into-view walks past the composer's scrollport up to the transcript scrollport, which a textarea shorter than its box never made it do. Chromium does not. Measured, with `overscroll-behavior: contain` and `contain: paint` both tried and neither stopping the walk — there is no CSS that ends scroll-into-view chaining. Accepted: it scrolls toward the bottom, where the composer already sits, and the alternative is a caret visibly detached from its text on every engine. - Paging and drag-selection are unchanged, both measured old against new. `PageDown`/`PageUp` never moved a textarea's caret in the first place — chromium scrolls a page and leaves `selectionStart` where it was, in both geometries; only the box that scrolls differs. Drag-selecting past the bottom edge still auto-scrolls, and to the same place (chromium 628/628, firefox 625/620, WebKit 170/170 — WebKit's slower autoscroll is equally slow before and after). - The composer's own `focus()` calls pass `preventScroll` — the unlock/session-switch effect and the focus-keeping mousedown on the toolbar buttons — so a focus nobody gestured for cannot move the transcript through the taller textarea's reveal chain. Suppressing that walk hands the caret back to us on the one path where it matters: the composer DOM is reused across sessions, so switching to a longer draft keeps the previous offset while the value swap puts the caret at the new draft's end. Measured on all three engines, that leaves the caret 940px below a box sitting at 0; the effect therefore reveals it in its own scrollport, landing at 625 of 628 — what the old geometry reached at 628 through the browser. The mousedown path needs no reveal: the caret has not moved, and the next keystroke gets the browser's native one. The effect also runs when a draft the user did not type arrives: `ConversationSession` seeds a persisted draft in its own mount effect, which runs AFTER this component's, so the first reveal would otherwise measure an empty mirror and never run again for the draft that then appeared. -- Undo and redo are the one draft-changing path with no caret restore, and so no reveal: the machine replays a previous draft and the DOM selection stays where the browser clamps it. That predates this change and is unchanged by it — named here because the three restores that DO reveal make the omission look deliberate, and the helper is sitting right there if it is ever reported. +- Undo and redo are the one draft-changing path with no caret restore, and so no reveal: the machine replays a previous draft and the DOM selection stays where the browser clamps it. That predates this change and is unchanged by it — named here because the two restores that DO reveal make the omission look deliberate, and the helper is sitting right there if it is ever reported. - Any layer added beside the backdrop belongs INSIDE the scrollport and must be as tall as the draft, or it reintroduces exactly this defect. This is the composer's standing hazard: the two-layer split is load-bearing for chips and highlights, so the coupling has to be structural, not maintained. ## Testing diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md index 0faca3fb2c..eccdcf47c3 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-31-composer-text-layers-share-one-scrollport.zh.md @@ -30,7 +30,7 @@ composer 的文本由两层叠放绘制（见 [InputBar](../../../../packages/cl **折行宽度这一前提。** 现在三层都在滚动容器内部解析自身宽度，因此一条占布局宽度的滚动条对它们的代价由结构保证相等。这也就关闭了被取代的那篇笔记记录为「悬置且没有任何属性能修」的分歧：WebKit 会为 `overflow-y: auto` 的 textarea 预留槽位，却不为它旁边 `overflow: hidden` 的层预留，把 textarea 排成 768 对 776——在长草稿上值 2 到 5 个折行，也就是在唯一能观察到它的那个引擎上把字形放到了错误的光标之下。改动后在独立环境实测，Playwright 自带的三个引擎上三层宽度均一致。 -**由 composer 自己完成的编辑，现在会主动请求回视。** 粘贴、ctrl/meta-Enter 换行与剪切都会抑制原生编辑——草稿与撤销日志归状态机所有——再用 `setSelectionRange` 恢复光标，而这不会带来任何回视：在 chromium 与 WebKit 上实测，粘贴一大段之后视图停在原处，光标却落在所粘内容的末尾。该缺陷早于本次改动（Firefox 只在旧几何下恰好会回视），在此修复，是因为单一滚动容器才终于让「回视」成为我们能自己做的事。三处恢复共用一个 helper：它以隐藏的镜像层为标尺——同一份草稿、同一套度量、同一折行宽度，因此在光标索引处折叠一个 Range 就能报出光标位置，无需任何 caret API——并且只滚动到刚好把该行带进可见范围为止，与浏览器为输入所做的一致。 +**由 composer 自己完成的编辑，现在会主动请求回视。** 粘贴与剪切都会抑制原生编辑——草稿与撤销日志归状态机所有——再用 `setSelectionRange` 恢复光标，而这不会带来任何回视：在 chromium 与 WebKit 上实测，粘贴一大段之后视图停在原处，光标却落在所粘内容的末尾。该缺陷早于本次改动（Firefox 只在旧几何下恰好会回视），在此修复，是因为单一滚动容器才终于让「回视」成为我们能自己做的事。两处恢复共用一个 helper：它以隐藏的镜像层为标尺——同一份草稿、同一套度量、同一折行宽度，因此在光标索引处折叠一个 Range 就能报出光标位置，无需任何 caret API——并且只滚动到刚好把该行带进可见范围为止，与浏览器为输入所做的一致。 有一种形状需要单独的规则，因为引擎之间在这里并不一致：紧跟在换行之后的光标，落在一条没有任何内容可供度量的行上——以换行结尾的草稿正是终止于此。chromium 对这个折叠位置**根本不返回任何 client rect**（一个全零盒子，会把回视带向反方向），firefox 报的是上一行，WebKit 报的才是对的那一行。因此该 helper 改为度量光标刚离开的那个换行——它的盒子就是光标来的那一行——再往下走一行；三者随即落在同一个偏移上（649/652，光标所在行位于 336px 盒内的 315）。 @@ -66,7 +66,7 @@ composer 的文本由两层叠放绘制（见 [InputBar](../../../../packages/cl - 在 Firefox 与 WebKit 上，点进一个草稿超过上限的 composer 现在还会把会话记录滚动到底部：光标的 scroll-into-view 会越过 composer 的滚动容器一路走到会话记录的滚动容器，而一个比自身盒子矮的 textarea 从不会引发这一步。chromium 不会。已实测，并试过 `overscroll-behavior: contain` 与 `contain: paint`，两者都拦不住这次上行——没有任何 CSS 能终止 scroll-into-view 的接力。接受：它滚向底部，而 composer 本来就在底部，而其替代方案是在每个引擎上都出现光标与文字明显分离。 - 翻页与拖拽选区的行为未变，二者均做了新旧对照实测。`PageDown`/`PageUp` 本来就不会移动 textarea 的插入点——chromium 是滚动一页并保持 `selectionStart` 不变，新旧几何皆然，区别只在于滚的是哪个盒子。拖拽选区越过下边缘仍会自动滚动，且落点一致（chromium 628/628、firefox 625/620、WebKit 170/170——WebKit 自动滚动较慢，但改动前后一样慢）。 - composer 自己发起的 `focus()` 全部加了 `preventScroll`——解锁/切会话的 effect,以及工具栏按钮上那个保持焦点的 mousedown——因此一次没有任何手势要求的聚焦，不会再通过更高的 textarea 的回视链把 transcript 挪走。抑制这条链之后，光标就回到了我们手上，而这在一条路径上确实要紧：composer 的 DOM 跨会话复用，因此切到更长的草稿时旧偏移会留着，而换值会把光标放到新草稿的末尾。三引擎实测，这会让光标落在停在 0 的盒子下方 940px 处；于是该 effect 会在自己的滚动容器里把它带回来，落点 625/628——正是旧几何靠浏览器达到的 628。mousedown 那条不需要回视：光标没动过，而下一次敲键会拿到浏览器原生的回视。该 effect 在「用户没有敲过的草稿到达时」同样会跑：`ConversationSession` 在它自己的 mount effect 里注入持久化草稿，而父组件的 mount effect 晚于子组件，否则第一次回视量到的是空镜像，且不会再为随后出现的那份草稿重跑。 -- 撤销/重做是唯一一条改动草稿却不恢复光标、因而也不回视的路径：状态机重放上一版草稿，DOM 选区停在浏览器钳位后的位置。这早于本次改动且未被改动——在此点名，是因为另外三处恢复都会回视，会让这处遗漏看起来像有意为之；真被报告时 helper 就在旁边。 +- 撤销/重做是唯一一条改动草稿却不恢复光标、因而也不回视的路径：状态机重放上一版草稿，DOM 选区停在浏览器钳位后的位置。这早于本次改动且未被改动——在此点名，是因为另外两处恢复都会回视，会让这处遗漏看起来像有意为之；真被报告时 helper 就在旁边。 - 任何新增在 backdrop 旁边的层都属于滚动容器**内部**，并且必须与草稿等高，否则就会重新引入这一缺陷。这是 composer 长期存在的风险点：两层拆分对 chip 与高亮是承重的，因此耦合必须来自结构，而不是靠维护。 ## 测试 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.i18n.yaml new file mode 100644 index 0000000000..7d68e52c82 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.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-english-compaction-checkpoints.md +2026-07-31-english-compaction-checkpoints.md: dc95ed187a6ba5b86800f06ebefb2776995f9421 +2026-07-31-english-compaction-checkpoints.zh.md: 7cd4179430ed775f3807af5a02e81838e495c81e diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.md b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.md new file mode 100644 index 0000000000..dc95ed187a --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.md @@ -0,0 +1,28 @@ +# Agent Note: Compaction checkpoints use an English engineering register + +Status: implemented + +English | [中文](2026-07-31-english-compaction-checkpoints.zh.md) + +## Problem + +A compaction checkpoint becomes part of the next model request's durable prefix. When a multilingual conversation leads the compactor to preserve its narrative material in the conversation language, the checkpoint can introduce a large amount of a language that is absent from the code, tool output, and existing reasoning prefix. That language then persists across later compaction cycles and can influence the conversation model's reasoning register. + +## Decision + +`COMPACTION_INSTRUCTION` requires an English-language internal engineering checkpoint. It asks the model to translate narrative source material as needed while preserving exact literals, including paths, commands, errors, identifiers, signatures, and quoted wording when exactness matters. The checkpoint's headings and terse engineering bullets remain the existing structured format. + +The requirement is integrated into the first sentence of the trailing compaction instruction. The replayed system prompt, tools, and conversation history remain byte-identical to the routed request, so the change retains the prefix-cache reuse owned by the [compaction summary prefix-cache note](2026-07-21-compaction-summary-prefix-cache-reuse.md). + +## Alternatives considered + +- **Leave checkpoint language to the replayed conversation** — rejected: the checkpoint is a durable prompt prefix, so preserving a transient conversational register can amplify it across later compactions. +- **Constrain the conversation model's language** — rejected: the policy is for an internal checkpoint, not the user's visible conversation, and a conversation-wide rule would unnecessarily change normal interaction. +- **Require ASCII-only output** — rejected: ASCII is a character-set constraint rather than an engineering-register constraint and would unnecessarily distort legitimate literals and technical material. +- **Append a separate final English-only sentence** — rejected: stating the requirement in the instruction's opening output contract is shorter and ties it directly to the checkpoint being requested. + +## Consequences + +- New checkpoints normalize narrative context into English while retaining the exact strings that future tool use and code work depend on. +- Existing checkpoint structure, compaction routing, and cache alignment are unchanged; only the final user instruction is different. +- The direct summarization call remains outside transcript snapshots because it emits no `assistant/chunk` events. The real-loop regression instead asserts the exact final instruction received by the summarization request. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.zh.md new file mode 100644 index 0000000000..7cd4179430 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.zh.md @@ -0,0 +1,28 @@ +# Agent Note: 压缩检查点使用英语工程文体 + +Status: implemented + +[English](2026-07-31-english-compaction-checkpoints.md) | 中文 + +## 问题 + +压缩（compaction）检查点会成为下一次模型请求中持久存在的前缀。当多语言对话使压缩器以对话语言保留叙述性材料时，检查点可能引入大量代码、工具输出和既有推理（reasoning）前缀中均未出现的语言内容。该语言随后会在后续压缩周期中持续存在，并影响对话模型的推理文体。 + +## 决策 + +`COMPACTION_INSTRUCTION` 要求生成英语的内部工程检查点。它要求模型在必要时翻译叙述性源材料，同时保留精确的字面量；这包括路径、命令、错误、标识符、签名，以及精确性重要时的引用措辞。检查点的标题及简洁的工程项目符号仍沿用既有的结构化格式。 + +这项要求被整合到尾部压缩指令的第一句话中。回放的系统提示词、工具和对话历史与已路由请求保持字节级一致，因此该变更保留 [compaction summary prefix-cache note](2026-07-21-compaction-summary-prefix-cache-reuse.md) 所确立的前缀缓存复用。 + +## 考虑过的替代方案 + +- **让回放的对话决定检查点语言**——不采纳：检查点是持久的提示词前缀，保留短暂的对话文体可能在后续压缩中放大这种影响。 +- **约束对话模型的语言**——不采纳：该策略针对内部检查点，而不是用户可见的对话；对整个对话施加规则会不必要地改变正常交互。 +- **要求仅输出 ASCII**——不采纳：ASCII 是字符集约束，而非工程文体约束，并会不必要地扭曲合法的字面量和技术材料。 +- **在末尾追加一句独立的仅限英语要求**——不采纳：在指令开头的输出契约中说明该要求更简洁，也直接将其与所请求的检查点绑定。 + +## 后果 + +- 新检查点会将叙述性上下文规范化为英语，同时保留未来工具使用和代码工作所依赖的精确字符串。 +- 既有检查点结构、压缩路由和缓存对齐保持不变；只有最后一条 user 指令不同。 +- 直接摘要调用仍不纳入 transcript（文本记录）快照，因为它不会发出 `assistant/chunk` 事件。真实循环回归改为断言摘要请求收到的精确最终指令。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-fail-loud-releases-the-terminal.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-fail-loud-releases-the-terminal.i18n.yaml new file mode 100644 index 0000000000..4931fa907b --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-fail-loud-releases-the-terminal.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-fail-loud-releases-the-terminal.md +2026-07-31-fail-loud-releases-the-terminal.md: 2a6e7fcbbdd5d35bcf70dee09fdb9e5592486b78 +2026-07-31-fail-loud-releases-the-terminal.zh.md: f75c21cf79b241e6714c10ec7df9ac25f3d978b4 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-fail-loud-releases-the-terminal.md b/.agents/notes/implemented/bug-fix/2026-07-31-fail-loud-releases-the-terminal.md new file mode 100644 index 0000000000..2a6e7fcbbd --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-fail-loud-releases-the-terminal.md @@ -0,0 +1,59 @@ +# Agent Note: fail-loud releases the terminal before exiting + +Status: implemented + +English | [中文](2026-07-31-fail-loud-releases-the-terminal.zh.md) + +## Problem + +A `dsh` launch whose config failed validation printed its diagnostic and returned the user to a broken shell. Typing was invisible, and the next command was mangled by stray text: + +``` +dsh: fatal load failure: ValidationError: invalid config: + - $.providers expected object but got [object Object] (at providers) +$ 1;2;4cecho hello +zsh: command not found: 4cecho +``` + +The Loader mounts entries concurrently, so entry failure order is not startup order. `ui-tui` activates and calls pi-tui's `ProcessTerminal.start()`, which puts stdin in raw mode, enables bracketed paste, and writes the Kitty keyboard-protocol probe — a sequence ending in a Device Attributes query (`ESC [ c`). A sibling entry (here `llm-pi-ai`) then rejects on its own config. At the time, that rejection surfaced as an unhandled rejection, and `installFailLoud` wrote one stderr line and called `process.exit(1)` immediately. (The transactional Loader now settles config-tree failures through `boot()`, which disposes the partial context itself; the release hook remains the guard for rejections `boot()` cannot see — a plugin's detached async work rejecting during or after mounting.) + +Nothing disposed the tree, so `ProcessTerminal.stop()` never ran: raw mode, bracketed paste, and the keyboard protocol stayed set on the shell that outlived the process. The terminal's answer to the Device Attributes query (`1;2;4c`) arrived after exit and was read by the shell as typed input — the literal text above. + +The `/exit` path was never affected, because it disposes the tree and reaches the TUI's own `shutdown()`, which calls `drainInput()` (absorbing the pending reply) and then `ui.stop()`. The defect was that a *failed boot* had no path to that same teardown. + +## Decision + +`installFailLoud` takes an optional `release` teardown, awaited between the diagnostic and the exit: + +- The diagnostic is written **before** the release, so a hanging or failing disposer cannot swallow the reason. +- A latch, not an uninstall, keeps the first rejection the reported one. Removing the listener during teardown would let a second concurrent rejection become uncaught, and Node would kill the process mid-teardown — stranding exactly the terminal state this restores. Later rejections, including the release's own, fall through to the pending exit. +- The release is bounded by `FAIL_LOUD_RELEASE_TIMEOUT_MS` (2s) and its rejection is swallowed. A wedged or failing disposer delays the fatal exit; it never cancels it. That timer stays **referenced**: an `unref()`ed one lets Node reach an empty event loop and exit 0 on the very failure being reported, because an `unhandledRejection` listener suppresses the default fatal exit. +- Omitting `release` keeps the previous behavior exactly, so the ACP, JSON-RPC, and demo bins are unchanged. + +`dsh`'s TUI launcher passes a release that disposes the root context, which runs the TUI's existing `shutdown()` and hands the terminal back. + +The launcher captures the root context in `boot()`'s `prepare` hook rather than from its return value. The rejection arrives while `boot()` is still in flight, so `app.current` assigned after the `await` would still be `undefined` at exactly the moment the hook needs it. `prepare` runs after the Loader installs and before any config-tree entry mounts, which covers the whole window in which an entry can reject. + +## Alternatives considered + +**Reset the terminal from the fail-loud handler** (write `ESC [ ? 2004 l`, pop the keyboard protocol, clear raw mode). This duplicates pi-tui's teardown in a package that owns no terminal, and would drift as pi-tui's startup sequence changes. It also cannot absorb the in-flight Device Attributes reply, which is what corrupts the next prompt — only draining stdin while it is still raw does that. + +**Register a `process.on('exit')` terminal reset in the TUI.** Exit handlers are synchronous, so they cannot await `drainInput()`; the stray reply would still land. It also puts teardown on a global hook rather than the disposal path that already exists. + +**Have the TUI refuse to start until the tree settles.** This serializes a deliberately concurrent Loader and delays first paint for every healthy launch to fix a failure path. + +**Reorder config entries so `llm-pi-ai` mounts before `ui-tui`.** Ordering is not a guarantee the Loader makes, and any future entry could fail after the TUI mounts. + +## Consequences + +A failed boot now costs one tree disposal (bounded at 2s) before exit, and the exit code stays 1. In exchange, a misconfigured `dsh` returns a usable shell instead of one needing `stty sane` or `reset`. + +The guarantee belongs to whichever bin owns the terminal: a surface that grabs terminal state and does not pass `release` reintroduces this defect. `installFailLoud` cannot detect that on its own, since it has no view of what a mounted plugin did to the process. + +## Testing + +`packages/ui/app-boot/tests/app-boot.spec.ts` covers the release contract: the hook is awaited before the exit commits, a rejecting hook still exits 1, a never-settling hook exits after `FAIL_LOUD_RELEASE_TIMEOUT_MS`, and a burst of rejections reports only the first while the release still completes. + +Those fake-process tests cannot observe the two failure modes that matter most — process exit code with a real event loop, and terminal state after exit — so the regression lives in `apps/cli/tests/tui-keyless-smoke.e2e.ts`. It boots the shipped tree in a real PTY over `fixtures/tui-invalid-provider.cordis.yml` (a list-shaped `providers`, the mistake users actually make), expects exit 1, and asserts the captured bytes contain both the labelled boot rejection (`dsh: plugin tree failed to load:`) and `ESC[?2004l`. The same case pins the boot path end to end: it caught the [HMR initial-scan boot deadlock](2026-08-03-hmr-initial-scan-boot-deadlock.md) that silently exited 13 with the terminal stranded. + +Testing policy requires a PTY case whenever terminal teardown changes, and this is it. The `/exit` path keeps its existing assertion that the same reset appears on a clean exit. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-fail-loud-releases-the-terminal.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-fail-loud-releases-the-terminal.zh.md new file mode 100644 index 0000000000..f75c21cf79 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-fail-loud-releases-the-terminal.zh.md @@ -0,0 +1,59 @@ +# Agent Note：fail-loud 在退出前释放终端 + +Status: implemented + +[English](2026-07-31-fail-loud-releases-the-terminal.md) | 中文 + +## Problem + +配置校验失败的 `dsh` 启动会打印诊断信息，然后把用户丢回一个损坏的 shell：输入不可见，下一条命令还会被残留文本弄乱： + +``` +dsh: fatal load failure: ValidationError: invalid config: + - $.providers expected object but got [object Object] (at providers) +$ 1;2;4cecho hello +zsh: command not found: 4cecho +``` + +Loader 并发挂载各个条目，因此条目失败的顺序并不等于启动顺序。`ui-tui` 会先激活并调用 pi-tui 的 `ProcessTerminal.start()`，它把 stdin 置为 raw 模式、启用 bracketed paste，并写出 Kitty 键盘协议探测序列——该序列以一个 Device Attributes 查询（`ESC [ c`）结尾。随后某个同级条目（这里是 `llm-pi-ai`）因自身配置而 rejection。 + +在当时，该 rejection 以未处理 rejection 的形式浮现，而 `installFailLoud` 只写一行 stderr 就立即调用 `process.exit(1)`。（事务化 Loader 现在让配置树失败经 `boot()` 结算，由它自行释放部分构建的上下文；release 回调仍然守护 `boot()` 看不到的 rejection——插件游离的异步工作在挂载期间或挂载之后失败。）没有任何环节释放这棵树，因此 `ProcessTerminal.stop()` 从未执行：raw 模式、bracketed paste 和键盘协议都残留在比进程活得更久的 shell 上。终端对 Device Attributes 查询的回应（`1;2;4c`）在进程退出之后才到达，被 shell 当作用户输入读入——也就是上面那段字面文本。 + +`/exit` 路径从不受影响，因为它会释放整棵树，从而进入 TUI 自身的 `shutdown()`：先 `drainInput()`（吸收尚未返回的响应），再 `ui.stop()`。缺陷在于**启动失败**没有通往这同一套拆卸流程的路径。 + +## Decision + +`installFailLoud` 新增可选的 `release` 拆卸回调，在诊断信息与退出之间被等待： + +- 诊断信息在 release **之前**写出，因此卡住或失败的 disposer 无法吞掉失败原因。 +- 使用闩锁（latch）而非卸载监听器，来保证被报告的始终是第一个 rejection。若在拆卸期间移除监听器，第二个并发 rejection 就会变成未捕获错误，Node 会在拆卸中途杀死进程——恰好残留下本次要恢复的终端状态。后续 rejection（包括 release 自身的）都会落入已挂起的退出流程。 +- release 以 `FAIL_LOUD_RELEASE_TIMEOUT_MS`（2 秒）为上限，且其 rejection 被吞掉。卡住或失败的 disposer 只会延迟致命退出，绝不会取消它。该定时器保持 **referenced**：一旦 `unref()`，Node 就会在事件循环清空后、恰恰在报告这次失败时以 0 退出，因为 `unhandledRejection` 监听器抑制了默认的致命退出。 +- 不传 `release` 时行为与此前完全一致，因此 ACP、JSON-RPC 和各 demo bin 均无变化。 + +`dsh` 的 TUI 启动器传入的 release 会释放根上下文，从而执行 TUI 已有的 `shutdown()` 并把终端交还。 + +启动器在 `boot()` 的 `prepare` 回调中捕获根上下文，而不是取其返回值。rejection 到达时 `boot()` 尚未结算，因此在 `await` 之后赋值的 `app.current` 恰好在回调需要它的那一刻仍是 `undefined`。`prepare` 在 Loader 安装之后、任何配置树条目挂载之前运行，覆盖了条目可能 rejection 的整个窗口。 + +## Alternatives considered + +**在 fail-loud 处理函数里直接重置终端**（写 `ESC [ ? 2004 l`、弹出键盘协议、清除 raw 模式）。这会在一个并不拥有终端的包里重复 pi-tui 的拆卸逻辑，并随 pi-tui 启动序列的变化而漂移。它同样无法吸收尚未返回的 Device Attributes 响应——而这正是弄乱下一个提示符的原因，只有在 stdin 仍处于 raw 模式时排空它才能解决。 + +**在 TUI 中注册 `process.on('exit')` 终端重置。** exit 处理函数是同步的，无法等待 `drainInput()`，残留响应依旧会落到 shell；而且这把拆卸挂到全局钩子上，而非已经存在的释放路径。 + +**让 TUI 等整棵树结算后再启动。** 这会把刻意并发的 Loader 串行化，并为修复一条失败路径而拖慢每一次正常启动的首次绘制。 + +**调整配置顺序，让 `llm-pi-ai` 先于 `ui-tui` 挂载。** 顺序并不是 Loader 提供的保证，而且未来任何条目都可能在 TUI 挂载之后失败。 + +## Consequences + +启动失败现在会在退出前多付出一次树释放的代价（上限 2 秒），退出码仍为 1。作为交换，配置错误的 `dsh` 会交还一个可用的 shell，而不是需要 `stty sane` 或 `reset` 才能恢复的终端。 + +这项保证属于**拥有终端的那个 bin**：任何抢占终端状态却不传 `release` 的界面都会重新引入该缺陷。`installFailLoud` 自身无法察觉这一点，因为它看不到已挂载的插件对进程做了什么。 + +## Testing + +`packages/ui/app-boot/tests/app-boot.spec.ts` 覆盖 release 契约：退出提交前会等待该回调；回调 rejection 时仍退出 1；永不结算的回调会在 `FAIL_LOUD_RELEASE_TIMEOUT_MS` 后退出；以及一连串 rejection 只报告第一个，同时 release 仍能跑完。 + +这些基于假进程的测试无法观测到最关键的两种失败形态——真实事件循环下的进程退出码，以及退出之后的终端状态——因此回归用例放在 `apps/cli/tests/tui-keyless-smoke.e2e.ts`。它在真实 PTY 中以 `fixtures/tui-invalid-provider.cordis.yml`（`providers` 为列表形状，正是用户真实会犯的错误）启动出厂配置树，期望退出码为 1，并断言捕获到的字节流同时包含带标签的启动 rejection（`dsh: plugin tree failed to load:`）与 `ESC[?2004l`。同一用例端到端钉住了启动路径：正是它发现了以 13 静默退出、终端状态被残留的 [HMR 初始扫描启动死锁](2026-08-03-hmr-initial-scan-boot-deadlock.md)。 + +测试规范要求：只要改动终端拆卸，就必须有 PTY 用例——这就是它。`/exit` 路径保留其原有断言，确认正常退出时同样会出现该重置序列。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-fork-anchor-floors-to-event-seq.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-fork-anchor-floors-to-event-seq.i18n.yaml new file mode 100644 index 0000000000..c4a5595fea --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-fork-anchor-floors-to-event-seq.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-fork-anchor-floors-to-event-seq.md +2026-07-31-fork-anchor-floors-to-event-seq.md: 2cc8d66942442aca69c930be880cc41d56bced13 +2026-07-31-fork-anchor-floors-to-event-seq.zh.md: 9f443f3d5165c01c6585d33bd6a37e90e9b3bf95 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-fork-anchor-floors-to-event-seq.md b/.agents/notes/implemented/bug-fix/2026-07-31-fork-anchor-floors-to-event-seq.md new file mode 100644 index 0000000000..2cc8d66942 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-fork-anchor-floors-to-event-seq.md @@ -0,0 +1,35 @@ +# Agent Note: Fork anchor floors to an event seq + +Status: implemented + +English | [中文](2026-07-31-fork-anchor-floors-to-event-seq.zh.md) + +## Problem + +The fork button on a stopped assistant message did nothing at all — no child session, no error, no visible reaction. + +The frozen node behind that message is not a log event. Both the live projection and the history replay mint it with a flow-ordering seq of `turnEnd.seq - 0.9`, placing it strictly after every event of the aborted turn and before the next one, and the chat view hands that node seq to the fork entry point unchanged. `session.fork` accepts a non-negative integer on the wire, so a fractional anchor is rejected as invalid-params before the request reaches the host, and the chat entry's fork call swallows failures. Nothing distinguished the rejection from an inert button. + +The host's cut rule was never the obstacle. An aborted turn ends with a logged `turn/end` carrying reason `aborted`, so it is a completed prefix like any other and the anchor simply never arrived. + +## Decision + +`SessionsService.fork` floors `atSeq` before the RPC. The fractional-seq convention belongs to `dsh-client-runtime`, which mints it in both the live and replay projections, so the same package converts it back to a real event seq at the wire boundary instead of every UI caller remembering to. Integer anchors are unaffected. + +Flooring lands inside the anchor's own turn rather than clipping backward: every turn opens with `turn/start`, so `turnEnd.seq - 1` cannot itself be an earlier turn's `turn/end`. The host's first-`turn/end`-at-or-after rule then closes on the turn the reader clicked, matching the whole-turn semantics the message-level fork button already promised for completed turns. + +The apiproxy fork suite pins the host half of the contract: a floored anchor inside an aborted turn cuts through that turn and seeds the child with it. + +## Alternatives considered + +**Accept fractional `atSeq` on the wire.** Rejected because the host contract is an event seq, not a position on a continuum; the fractional form is one client's rendering convention, and admitting it would leave `atSeq` alone among the seq-carrying payloads in taking non-integers. + +**Hide the fork button on interrupted messages.** Rejected because forking a turn the reader deliberately stopped is one of the strongest reasons to fork at all, and the capability worked host-side the whole time. + +**Floor in the chat entry's `forkAt` adapter.** Rejected because `ui-conversation` consumes the fractional convention without owning it; any second fork entry point would have to rediscover the same conversion. + +## Consequences + +Forking from a stopped turn produces a child seeded through that turn's `turn/end`. The frozen partial text is reconstructed from chunk events and was never an `assistant/message`, so it stays out of the child's model transcript exactly as it stays out of the source's on resume — the child resumes from the same context the source would. + +Fork failures stay silent in the chat entry. This bug survived because that call site discards its rejection; surfacing fork errors in the UI is a separate change. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-fork-anchor-floors-to-event-seq.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-fork-anchor-floors-to-event-seq.zh.md new file mode 100644 index 0000000000..9f443f3d51 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-fork-anchor-floors-to-event-seq.zh.md @@ -0,0 +1,35 @@ +# Agent Note: fork 锚点向下取整到事件 seq + +Status: implemented + +[English](2026-07-31-fork-anchor-floors-to-event-seq.md) | 中文 + +## 问题 + +在已停止的助手消息上点 fork 毫无反应——没有子会话，没有报错，也没有任何可见变化。 + +这条消息背后的冻结节点并不是日志事件。实时投影和历史回放都用 `turnEnd.seq - 0.9` 这个排序坐标来生成它，让它严格落在被中断轮次的所有事件之后、下一轮之前，而 chat 视图原样把这个节点 seq 交给 fork 入口。`session.fork` 在 wire 上只接受非负整数，因此分数锚点在抵达 host 之前就被判为 invalid-params，而 chat 入口的 fork 调用又吞掉了失败。于是被拒绝和按钮失灵在表现上毫无区别。 + +host 的切分规则从来不是障碍。被中止的轮次会记录一条 reason 为 `aborted` 的 `turn/end`，它和其他轮次一样是可切分的完整前缀——只是锚点根本没送到。 + +## 决策 + +`SessionsService.fork` 在发起 RPC 前对 `atSeq` 向下取整。分数 seq 这个约定属于 `dsh-client-runtime`，实时投影和回放投影都由它生成，因此也由同一个包在跨出 wire 边界时把它换回真实事件 seq，而不是要求每个 UI 调用方各自记得转换。整数锚点不受影响。 + +向下取整落在锚点自身所在的轮次内，不会回退：每一轮都以 `turn/start` 开头，所以 `turnEnd.seq - 1` 不可能是上一轮的 `turn/end`。host 随后按「首个位于锚点或其之后的 `turn/end`」收口，命中的正是读者点击的那一轮，与消息级 fork 按钮在已完成轮次上一贯承诺的整轮语义一致。 + +apiproxy 的 fork 用例固定了 host 这一侧的契约：落在被中止轮次内的取整锚点会切穿该轮，并把它种进子会话。 + +## 备选方案 + +**让 wire 接受分数 `atSeq`。** 否决：host 契约要的是事件 seq，而不是连续坐标上的某个位置；分数形式只是某一个客户端的渲染约定，一旦放行，`atSeq` 会成为所有携带 seq 的载荷中唯一容忍非整数的字段。 + +**在已中断的消息上隐藏 fork 按钮。** 否决：从读者主动叫停的那一轮分叉，恰恰是最需要 fork 的场景之一，而 host 侧这个能力一直是好的。 + +**在 chat 入口的 `forkAt` 适配器里取整。** 否决：`ui-conversation` 只是分数约定的消费方，并不拥有它；将来任何第二个 fork 入口都得把同样的转换重新发现一遍。 + +## 影响 + +从已停止的轮次 fork 会得到一个种子切到该轮 `turn/end` 的子会话。被冻结的残缺文本是从 chunk 事件重建出来的，从未成为 `assistant/message`，因此它不会进入子会话的模型上下文——正如源会话恢复时它也不会进入一样，子会话拿到的上下文与源会话一致。 + +fork 失败在 chat 入口仍然是静默的。这个 bug 能存活至今，正是因为该调用点丢弃了自己的 rejection；把 fork 错误呈现到 UI 上是另一件事。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.i18n.yaml new file mode 100644 index 0000000000..12b3982d54 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.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-hero-visible-while-blank-session-opens.md +2026-07-31-hero-visible-while-blank-session-opens.md: b39963beffa403ef6fa44735aa88395a99139751 +2026-07-31-hero-visible-while-blank-session-opens.zh.md: b451d7c00ec7eb8d736134e738d72e5e07fd1b04 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md new file mode 100644 index 0000000000..b39963beff --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md @@ -0,0 +1,35 @@ +# Agent Note: Hero stays visible while a blank session opens + +Status: implemented + +English | [中文](2026-07-31-hero-visible-while-blank-session-opens.zh.md) + +## Problem + +The conversation root has a `settling` phase for a session that is still opening while its composer reads `blank`: the hero-versus-docked outcome is unknowable until history arrives, so the composer seat is hidden (`visibility:hidden`) rather than flashing the centered hero and snapping to the docked bar. Startup auto-selection turned that guard into the defect it was meant to prevent. From the no-workspace hero, `WorkspacesService.startInitialSelection` connects the most recent workspace and opens its blank session; `openState` flips to `loading` the moment `open()` lands, so the center column went blank for the whole history round-trip and then repainted, which reads as a full-page refresh on every launch. + +## Decision + +`ConversationRoot` reads the session list summary's `blank` flag alongside the conversation snapshot and exempts summary-proven blank sessions from settling: `settling` additionally requires `summaryBlank !== true`, and `hero` accepts a blank composer whenever the summary proves the session blank, in every open state rather than only `loading`. A session the list already reports as blank can only land on the hero, so hiding buys nothing and costs the visible flash; the same proof holds before the open starts (`cold`) and after one fails (`error`), where the previous conditions fell through to the active phase and rendered a docked bare composer under chrome `ConversationSession` hides for blank sessions. Whenever the summary does not prove the session blank — a row reporting `blank: false`, or no row at all because the list has not caught up — `summaryBlank` is not `true` and the conservative settling hide is unchanged. + +The summary flag and the snapshot's own `blank` are distinct sources: the snapshot describes the session being opened, the summary is the list row that already exists before the open resolves. Only the latter is available early enough to decide the phase. + +## Alternatives considered + +**Drop the settling phase entirely.** Rejected because it still earns its keep for a session with no summary row: without a prior claim about emptiness, hero-versus-docked is genuinely unknowable and the flash it prevents is the worse one. + +**Delay the `loading` flip until history returns.** Rejected because `openState` is authoritative about the open operation; deferring it to suppress a presentation artifact would misreport the data state to every other consumer. + +**Cross-fade or otherwise animate the settling hide.** Rejected because the column has nothing to show during the round-trip either way — the fix is to not hide content whose outcome is already known, not to decorate the hiding. + +## Deferred + +The no-session→session tree relocation in `ConversationRoot` (the hero/composer subtree moves into the `conversation.session` outlet) still rebuilds the composer DOM on the same transition; removing it means moving `conversation.session` to `session-maybe` scope, a slot-contract change that needs its own proposal. + +Object-layer reference churn found while diagnosing this — no-op projections minting fresh snapshots, the create path projecting twice, `select()` using `notifyNow` from async continuations — is real but independent of the visible flash. + +## Consequences + +Startup auto-selection renders the hero immediately and keeps the composer seat and header visible through the history round-trip, so launching into a recent workspace no longer looks like a page reload. Sessions whose summary does not prove them blank keep the previous settling behavior, so the guard still covers the case it was written for. Skeleton tests pin all three summary shapes: a row reporting `blank: false` settles, an absent row settles, and a summary-proven blank session opening under `loading` renders hero chrome with a live textarea. + +The assembled coverage is `apps/web/tests/startup-auto-selection.e2e.ts` (keyless web browser lane): it registers a workspace, holds the `session.history` response open at the browser's network boundary, and asserts the visible frame while the auto-selected open is in flight — hero phase, hero title, painted composer — plus a recorded phase timeline of exactly `['hero']` for the whole load. Holding the round-trip is what makes it a regression test rather than a race: against a loopback host the open settles too fast to sample, and with the exemption reverted the held window is precisely when the root reports `settling`. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md new file mode 100644 index 0000000000..b451d7c00e --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 空白会话打开期间保持 hero 可见 + +Status: implemented + +[English](2026-07-31-hero-visible-while-blank-session-opens.md) | 中文 + +## 问题 + +会话根节点为"正在打开且 composer 处于 `blank`"的会话保留了一个 `settling` 阶段：在历史记录返回之前，hero 与 docked 的归属不可知，因此宁可隐藏 composer 座位（`visibility:hidden`），也不要先闪出居中的 hero 再跳到底部输入条。启动时的自动选择把这道防护变成了它本要防止的缺陷。从无工作区的 hero 进入时，`WorkspacesService.startInitialSelection` 会连接最近的工作区并打开其空白会话；`open()` 一落地 `openState` 立即翻为 `loading`，中间栏因此在整个历史往返期间保持空白，随后重绘一次——每次启动看起来都像整页刷新。 + +## 决策 + +`ConversationRoot` 在读取会话快照的同时读取会话列表摘要的 `blank` 标志，并让"摘要已证明为空白"的会话豁免 settling：`settling` 额外要求 `summaryBlank !== true`，而 `hero` 在摘要证明会话为空白时接受处于 blank 的 composer——覆盖全部 open state，而非仅 `loading`。列表已报告为空白的会话只可能落到 hero，因此隐藏毫无收益，只换来一次可见闪烁；同一份证明在打开开始之前（`cold`）与打开失败之后（`error`）同样成立，而此前的条件会在这两种状态下落到 active 阶段，在 `ConversationSession` 为空白会话隐藏的外壳之下渲染出一条停靠的裸 composer。只要摘要没有证明会话为空白——无论是报告 `blank: false` 的行，还是列表尚未跟上因而根本没有该行——`summaryBlank` 都不为 `true`，保守的 settling 隐藏行为保持不变。 + +摘要标志与快照自身的 `blank` 是两个不同来源：快照描述正在打开的这个会话，摘要则是在打开操作完成之前就已存在的列表行。只有后者足够早，可用于决定阶段。 + +## 备选方案 + +**彻底移除 settling 阶段。** 否决，因为对没有摘要行的会话它仍有价值：在缺少任何关于"是否为空"的先验断言时，hero 与 docked 的归属确实不可知，而它所防止的那种闪烁更糟糕。 + +**推迟 `loading` 的翻转，直到历史返回。** 否决，因为 `openState` 是打开操作的权威状态；为了压制一个呈现层瑕疵而推迟它，会向其他所有消费者误报数据状态。 + +**为 settling 的隐藏加交叉淡入或其他动画。** 否决，因为无论如何该栏在往返期间都没有内容可展示——正确的修复是不隐藏结局已知的内容，而不是把隐藏装饰得好看些。 + +## 推迟事项 + +`ConversationRoot` 中"无会话→有会话"的树位置迁移（hero/composer 子树移入 `conversation.session` 出口）仍会在同一次转换中重建 composer 的 DOM；消除它意味着把 `conversation.session` 移到 `session-maybe` 作用域，这是一次插槽契约变更，需要单独立项。 + +诊断期间发现的对象层引用抖动——空操作投影铸造出新的快照、创建路径重复投影一次、`select()` 在异步续体中使用 `notifyNow`——确实存在，但与这次可见闪烁相互独立。 + +## 影响 + +启动自动选择会立即渲染 hero，并在整个历史往返期间保持 composer 座位与 header 可见，因此启动进入最近工作区不再像页面重载。摘要未证明为空白的会话保持原有的 settling 行为，这道防护仍覆盖它当初针对的场景。骨架测试固定了摘要的三种形态：报告 `blank: false` 的行进入 settling；根本没有该行同样进入 settling；摘要已证明为空白的会话在 `loading` 期间渲染 hero 外壳与可用的文本框。 + +组装级覆盖是 `apps/web/tests/startup-auto-selection.e2e.ts`（无密钥的 Web 浏览器泳道）：它注册一个工作区，在浏览器网络边界上扣住 `session.history` 的响应，并在自动选择的打开仍在飞行途中断言可见画面——hero 阶段、hero 标题、已绘制的 composer——外加整次加载记录到的阶段时间线恰好为 `['hero']`。扣住这次往返正是它成为回归测试而非竞态的原因：对着回环主机，打开会快到无从采样；而一旦回退这条豁免，被扣住的这段窗口恰恰就是根节点报告 `settling` 的时刻。 diff --git a/.agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml similarity index 55% rename from .agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.i18n.yaml rename to .agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml index dab40896a5..3c6718b975 100644 --- a/.agents/notes/implemented/feature/2026-07-27-assistant-timing-header-trailing.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.i18n.yaml @@ -1,6 +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/feature/2026-07-27-assistant-timing-header-trailing.md -2026-07-27-assistant-timing-header-trailing.md: a315a0620c63f25660220e55cf5187d7117c14d1 -2026-07-27-assistant-timing-header-trailing.zh.md: 84b8612337a345912371e37952195e4602f7ca25 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md +2026-07-31-resume-selector-batch-projection.md: 39146527f13b20813bb6f5d5f1349ecab5724662 +2026-07-31-resume-selector-batch-projection.zh.md: 10333ea7cc5e7f2051c37f3374c5dc061bd0586e diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md new file mode 100644 index 0000000000..39146527f1 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.md @@ -0,0 +1,35 @@ +# Agent Note: Resume selector folds titles only + +Status: implemented + +English | [中文](2026-07-31-resume-selector-batch-projection.zh.md) + +## Problem + +Opening the TUI `/resume` selector called `sessionQuery.readSession()` once per listed session under an unbounded `Promise.all`. Each call re-listed the whole persistence store inside `SessionCorpus.load()` (O(N²) listings), read and decompressed the complete log, replay-validated every event through the `Session` constructor, and deep-cloned the header and events up to three times — all to derive one selector row's title, last-activity time, last `turn/end` label, provider/model route, and goal phase. On a real store (185 sessions, 87 MB compressed, ~353k events) the selector took tens of seconds to open, and the cost grew with total log size rather than session count. + +## Decision + +Selector rows fold nothing but titles, and everything else a row shows comes from metadata: + +- Titles come from the projection system: `session-title` already registers a `title` unit, so a live row reads the registry snapshot, a persisted row reads the durable checkpoint row (`sessionProjectionCache.cachedSnapshot`, zero I/O), and only a row without a usable checkpoint pays a `coldSnapshot` — checkpoint plus a `readFrom` tail, written back so the next scan is zero-I/O. Cold reads are bounded by the TUI `resumeScanConcurrency` config. A composition without the cache falls back to one bounded `readTitleSnapshots` batch over the logs; either path isolates a per-row failure into the disabled "Unreadable session" fallback. +- The activity timestamp never reads a log: a live session uses its last in-memory event time; a persisted session stats the artifact named by the optional `sessionPersistence.locate()` (mtime), falling back to the header's creation time when the backend locates no per-session artifact (SQLite) or the stat fails. Any append moves the mtime, so a mere pickup boundary now floats a browsed session up — accepted as the price of a metadata-only timestamp. +- The last-turn label, provider/model route, and goal phase columns are gone from rows. Route availability is now enforced by the Enter-time preflight, which fully reads and replay-validates the one chosen log through `readSession` before handoff. + +The selector overlay opens synchronously when `/resume` dispatches, before the scan settles: an `undefined` candidate set renders a "Loading sessions…" placeholder, the picker owns terminal input from its first frame, Enter reports that sessions are still loading, and Escape cancels. Closing the overlay aborts the scan through the `AbortSignal` the query methods accept; a signal-ignoring backend's late settlement is dropped by a staleness check. The finished scan swaps rows in through `setCandidates` (clearing a stale still-loading error) without replacing the overlay; a queued activation behind a closing predecessor receives an already-scanned set at construction; one catch spans listing, titles, and mtimes, so any scan failure closes the overlay and reports a notice rather than stranding the loading placeholder. + +No session-query or session-persistence surface changed. The shipped TUI composition gains the projection registry, storage, and projection-cache rows (mirroring the web overlay over the same `storages` root, so checkpoints written by either surface serve both); the first scan over a pre-existing store still reads each log once to seed checkpoints, and every later scan is metadata-only. + +## Alternatives considered + +**Keep per-row route/turn/goal columns via a generic batch projection (`projectSessions`).** Implemented first, then rejected: it still decompressed and parsed every log on every `/resume`, so browsing cost stayed O(total log bytes), and it grew the session-query public API for one consumer. The public seam was reverted; `readTitleSnapshots` keeps using the internal `projectMany` unchanged. + +**Fix only the O(N²) listing inside `SessionCorpus.load()`.** Rejected as the primary fix: the per-candidate full decompress, replay validation, and triple clone dominated on large logs. The redundant pre-listing in `load()` remains a candidate cleanup with error-semantics implications. + +**Surface a last-modified time through `listSnapshots`/`SessionRecord`.** Cleanest seam-wise, but touches the persistence contract, both backends, and the query record shape for what the TUI can already derive from `locate()` plus one stat. Reintroduce if a second consumer needs metadata activity times. + +**A bespoke persisted title index or TUI-local title cache.** Rejected: the session-projection cache already is the owned durable checkpoint system with an invalidation contract (`stateVersion`, identity binding, shrunk-log anchoring); mounting it beats adding a parallel cache. + +## Consequences + +Opening `/resume` performs one listing, one stat per persisted row, and per-row title reads that touch only checkpoint rows and log tails once checkpoints exist — O(session count) metadata instead of O(total log bytes); the fallback path without the cache remains one bounded title pass. Rows show title, timestamp, status, and id only; route problems surface as an Enter-time preflight error instead of a disabled row, and a session that fails replay is caught by preflight rather than the listing. Browsed-then-abandoned sessions float up on their pickup mtime. Fake `sessionQuery` services in TUI tests provide `readTitleSnapshots` alongside `listSessions`/`readSession`, and the test harness forwards an optional `locate`. Because the picker takes focus immediately, starting a second scan requires dismissing the current overlay first — a second `/resume` typed during a scan lands in the search field, which is the intended input capture. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md new file mode 100644 index 0000000000..10333ea7cc --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-resume-selector-batch-projection.zh.md @@ -0,0 +1,35 @@ +# Agent Note: 恢复选择器只折叠标题 + +Status: implemented + +[English](2026-07-31-resume-selector-batch-projection.md) | 中文 + +## Problem + +打开 TUI `/resume` 选择器时，会在一个无界 `Promise.all` 中对每个列出的会话调用一次 `sessionQuery.readSession()`。每次调用都会在 `SessionCorpus.load()` 内部重新列出整个持久化存储（O(N²) 次列表查询）、读取并解压完整日志、通过 `Session` 构造函数对每个事件做回放验证，并将 header 和事件深克隆多达三次——而这一切只为推导一行选择器条目的标题、最近活动时间、最后一个 `turn/end` 标签、提供方/模型路由和目标阶段。在真实存储上（185 个会话、压缩后 87 MB、约 35.3 万个事件），选择器需要数十秒才能打开，且开销随日志总大小而非会话数量增长。 + +## Decision + +选择器行除标题外不折叠任何内容，行内其余信息全部来自元数据： + +- 标题来自投影系统：`session-title` 已注册 `title` 投影单元，因此实时行读取注册表快照，持久化行读取持久 checkpoint 行（`sessionProjectionCache.cachedSnapshot`，零 I/O），只有没有可用 checkpoint 的行才付出一次 `coldSnapshot`——checkpoint 加 `readFrom` 尾部折叠，并写回使下次扫描零 I/O。冷读取受 TUI `resumeScanConcurrency` 配置约束。未挂载缓存的组合回退到一次对日志的有界 `readTitleSnapshots` 批量读取；两条路径都把单行失败隔离为禁用的"Unreadable session"回退。 +- 活动时间戳从不读取日志：实时会话取内存中最后一个事件的时间；持久化会话对可选 `sessionPersistence.locate()` 命名的产物做 stat（mtime），当后端定位不到按会话的产物（SQLite）或 stat 失败时回退到 header 的创建时间。任何追加都会移动 mtime，因此仅仅一次 pickup 边界也会让浏览过的会话上浮——这是元数据时间戳的代价，予以接受。 +- 行内不再有最后轮次标签、提供方/模型路由和目标阶段列。路由可用性改由 Enter 时的预检强制：预检通过 `readSession` 完整读取并回放验证选中的那一份日志后才移交。 + +选择器 overlay 在 `/resume` 分发时同步打开，早于扫描结算：`undefined` 候选集渲染"Loading sessions…"加载占位符，选择器从第一帧起就拥有终端输入，Enter 提示会话仍在加载，Escape 取消。关闭 overlay 会通过查询方法接受的 `AbortSignal` 中止扫描；忽略信号的后端的迟到结算由过期检查丢弃。扫描完成后通过 `setCandidates`（同时清除过期的仍在加载错误）换入行数据，不替换 overlay；排在正在关闭的前任之后的排队激活会在构造时直接收到已扫描的集合；列表查询、标题与 mtime 共用同一个 catch，因此任何扫描失败都会关闭 overlay 并报告通知，而不会让加载占位符悬置。 + +session-query 与 session-persistence 的任何表面都未改变。随附的 TUI 组合新增投影注册表、storage 与投影缓存行（镜像 web overlay，共用同一 `storages` 根，因此任一表面写下的 checkpoint 都服务两者）；对既有存储的首次扫描仍会各读取一次日志以播种 checkpoint，之后的每次扫描都只读元数据。 + +## Alternatives considered + +**通过通用批量投影（`projectSessions`）保留每行的路由/轮次/目标列。** 先实现后否决：它仍在每次 `/resume` 时解压并解析全部日志，浏览开销依旧是 O(日志总字节数)，且为单一消费者扩大了 session-query 公开 API。该公开接缝已回退；`readTitleSnapshots` 继续使用内部 `projectMany`，保持不变。 + +**只修复 `SessionCorpus.load()` 内部的 O(N²) 列表查询。** 作为主要修复被否决：在大日志上，按候选行执行的完整解压、回放验证和三重克隆才是主要开销。`load()` 中的冗余预列表查询仍是一个候选清理项，但涉及错误语义。 + +**通过 `listSnapshots`/`SessionRecord` 暴露最后修改时间。** 从接缝角度最干净，但要触碰持久化契约、两个后端和查询记录形状，而 TUI 已能用 `locate()` 加一次 stat 得到同样的信息。若出现第二个需要元数据活动时间的消费者再引入。 + +**专门的持久化标题索引或 TUI 本地标题缓存。** 否决：session-projection 缓存本身就是自有的持久 checkpoint 系统，并已带失效契约（`stateVersion`、身份绑定、日志收缩锚定）；挂载它优于再造一套并行缓存。 + +## Consequences + +打开 `/resume` 只执行一次列表查询、每个持久化行一次 stat，标题读取在 checkpoint 就绪后只触碰 checkpoint 行和日志尾部——O(会话数) 的元数据开销，而非 O(日志总字节数)；无缓存的回退路径仍是一次有界标题扫描。行内只显示标题、时间戳、状态和 id；路由问题以 Enter 时预检错误的形式出现，而不再是禁用行；回放会失败的会话由预检而非列表阶段拦截。浏览后放弃的会话会因 pickup 的 mtime 上浮。TUI 测试中的伪造 `sessionQuery` 服务在 `listSessions`/`readSession` 之外提供 `readTitleSnapshots`，测试 harness 会转发可选的 `locate`。由于选择器立即接管焦点，启动第二次扫描需要先关闭当前 overlay——扫描期间输入的第二个 `/resume` 会落入搜索字段，这正是预期的输入捕获行为。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-same-basename-workspace-adoption.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-same-basename-workspace-adoption.i18n.yaml new file mode 100644 index 0000000000..990e7e39bb --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-same-basename-workspace-adoption.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-same-basename-workspace-adoption.md +2026-07-31-same-basename-workspace-adoption.md: ed53804ea64df0d61db16e579c3d65af803dbb97 +2026-07-31-same-basename-workspace-adoption.zh.md: 82cfb7d90afca28f8e666742a758fda0202909f3 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-same-basename-workspace-adoption.md b/.agents/notes/implemented/bug-fix/2026-07-31-same-basename-workspace-adoption.md new file mode 100644 index 0000000000..ed53804ea6 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-same-basename-workspace-adoption.md @@ -0,0 +1,37 @@ +# Agent Note: Same-basename Workspace adoption + +Status: implemented + +English | [中文](2026-07-31-same-basename-workspace-adoption.zh.md) + +## Problem + +A Workspace is identified by its stable id and canonical directory path, while its title is mutable display metadata. The registry nevertheless rejected a new canonical path when its basename-derived title matched another Workspace. Common directory layouts such as `/a/xx` and `/b/xx` therefore could not coexist in the Web UI, even though the [domain design](../../proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md) already permits duplicate titles and every client operation addresses a Workspace by id. + +## Decision + +`ctx.workspace.create(path, title?)` treats canonical path as the only uniqueness key. Repeating the same path remains idempotent and preserves the registered title. Different canonical paths create different Workspace records and may share a title; when no title is supplied, each record still derives its title from `basename(path)` without suffixing or rewriting it. + +The Host's `workspace.create({ path })` adoption route inherits that rule. The Workspace manager, picker, grouping tree, selection, rename, deletion, and Session creation continue to use `WorkspaceId`, so equal labels neither merge records nor redirect an operation. The sidebar hover card exposes each canonical path when the labels need disambiguation. + +Explicit naming remains stricter. `workspace.create({ name })` and `workspace.rename` continue to reject a title already registered, as described by [manual Workspace naming](../feature/2026-07-25-session-list-browsing-and-manual-order.md). This prevents a user from deliberately introducing another ambiguous label while accepting collisions imposed by existing directory names. The path-adoption rule supersedes only the title-conflict clauses in the [Workspace product flow](../feature/2026-07-25-workspace-ui-product-flow.md) and [native directory picker](../feature/2026-07-27-native-workspace-directory-picker.md). + +The durable schema does not change: Workspace records already store id, path, and title independently, bootstrap can derive equal basenames, and startup validates duplicate paths rather than titles. + +## Verification + +Workspace registry and Host API tests create two real directories under different parents with the same final segment and assert distinct ids, paths, and durable order. The picker component renders equal labels as separate id-keyed entries. The keyless Web browser scenario adopts both directories through the composed directory flow and observes two registered and rendered Workspaces. + +## Alternatives considered + +**Keep title uniqueness and reject the second directory.** A display label would remain an accidental identity key and ordinary multi-root layouts would stay impossible to register. + +**Suffix colliding titles automatically.** A generated label such as `xx (2)` would no longer be the directory-derived title, would need stable allocation rules across deletion and reload, and would add state solely to conceal an identity mistake. + +**Use the full path as every Workspace title.** This removes the collision but makes the primary navigation label unnecessarily long. The full path remains available in the hover detail while the concise basename stays useful. + +**Permit collisions from explicit rename and create-by-name operations too.** The registry supports that state, but those operations intentionally ask the user to choose a display name. Retaining their conflict response preserves the existing naming guard without blocking filesystem-selected paths. + +## Consequences + +Two Workspace rows may carry the same visible title. They remain independently selectable and actionable because ids own identity; users can inspect the path or rename either row to disambiguate it. An explicit rename cannot select another row's current title, including a title that arose from same-basename adoption. No storage migration or compatibility path is required. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-same-basename-workspace-adoption.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-same-basename-workspace-adoption.zh.md new file mode 100644 index 0000000000..82cfb7d90a --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-same-basename-workspace-adoption.zh.md @@ -0,0 +1,37 @@ +# Agent Note: 接纳 basename 相同的 Workspace + +Status: implemented + +[English](2026-07-31-same-basename-workspace-adoption.md) | 中文 + +## 问题 + +Workspace 的身份由其稳定 id 和规范目录路径确定，标题则是可变的显示元数据。然而，只要新规范路径按 basename 派生出的标题与另一个 Workspace 相同，注册表就会拒绝该路径。因此，`/a/xx` 和 `/b/xx` 等常见目录布局无法同时出现在 Web UI 中，尽管[领域设计](../../proposed/architecture/2026-07-24-domain-kv-storage-and-workspace.md)早已允许标题重复，而且每项客户端操作都通过 id 定位 Workspace。 + +## 决策 + +`ctx.workspace.create(path, title?)` 仅以规范路径作为唯一性键。重复传入同一路径仍保持幂等，并保留已注册的标题。不同的规范路径会创建不同的 Workspace 记录，且可以共用标题；未提供标题时，每条记录仍从 `basename(path)` 派生标题，不添加后缀，也不改写标题。 + +Host 的 `workspace.create({ path })` 接纳入口沿用该规则。Workspace 管理器、选择器、分组树、选择、重命名、删除和 Session 创建仍使用 `WorkspaceId`，因此相同标签既不会合并记录，也不会把操作指向其他记录。需要区分相同标签时，侧边栏悬停详情卡会显示各自的规范路径。 + +显式命名仍采用更严格的规则。`workspace.create({ name })` 和 `workspace.rename` 仍会拒绝已注册的标题，具体见[手动 Workspace 命名](../feature/2026-07-25-session-list-browsing-and-manual-order.md)。这既防止用户主动引入另一个难以区分的标签，又允许既有目录名称造成的重名。路径接纳规则仅取代 [Workspace 产品流](../feature/2026-07-25-workspace-ui-product-flow.md)和[原生目录选择器](../feature/2026-07-27-native-workspace-directory-picker.md)中的标题冲突条款。 + +持久化 schema 未变：Workspace 记录本就分别存储 id、path 和 title，引导初始化可以派生出相同的 basename，启动校验检查的是重复路径而非重复标题。 + +## 验证 + +Workspace 注册表与 Host API 测试会在不同父目录下创建两个末级名称相同的真实目录，并断言其 id 和路径互不相同，且持久顺序正确。选择器组件将相同标签渲染为按 id 区分的独立条目。无密钥 Web 浏览器场景通过组合而成的目录流程接纳这两个目录，并观察到两个 Workspace 均已注册且完成渲染。 + +## 考虑过的替代方案 + +**保持标题唯一，并拒绝第二个目录。** 显示标签仍会意外充当身份键，普通的多根目录布局仍无法注册。 + +**自动为冲突标题添加后缀。** 像 `xx (2)` 这样的生成标签将不再是从目录派生的标题；系统还需要制定跨删除与重载保持稳定的分配规则，并且只为掩盖身份判定错误而增加状态。 + +**将完整路径用作每个 Workspace 的标题。** 这会消除冲突，却使主导航标签不必要地过长。完整路径仍可在悬停详情中查看，而简洁的 basename 仍有价值。 + +**也允许显式重命名和按名称创建操作产生重名。** 注册表支持这种状态，但这些操作本就是明确要求用户选择显示名称。保留冲突响应可维持现有命名防护，同时不阻止从文件系统选取的路径。 + +## 后果 + +两个 Workspace 行可能显示相同的可见标题。id 负责身份，因此两行仍可独立选择和操作；用户可以查看路径或重命名任一行以作区分。显式重命名不能采用另一个行当前使用的标题，即使该标题源自 basename 相同的目录接纳。无需存储迁移或兼容路径。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-web-stop-preserves-queue.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-web-stop-preserves-queue.i18n.yaml new file mode 100644 index 0000000000..c78049cc8d --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-web-stop-preserves-queue.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-web-stop-preserves-queue.md +2026-07-31-web-stop-preserves-queue.md: b8bba45009c126495a8b03ee36d6eb2cccac9a93 +2026-07-31-web-stop-preserves-queue.zh.md: 0e1fffae8819bea81b91fae10c76dbadc78474fe diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-web-stop-preserves-queue.md b/.agents/notes/implemented/bug-fix/2026-07-31-web-stop-preserves-queue.md new file mode 100644 index 0000000000..b8bba45009 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-web-stop-preserves-queue.md @@ -0,0 +1,37 @@ +# Agent Note: Web stop preserves pending Queue + +Status: implemented + +English | [中文](2026-07-31-web-stop-preserves-queue.zh.md) + +## Problem + +The Web stop button reached `session.cancel`, which mapped to broad `agent.cancel({ kind: 'user' })`. During an active turn, ordinary composer submissions are already accepted as independently addressable Queue occurrences. Broad cancellation discarded every occurrence when the user intended to stop only the current generation, conflating turn interruption with the Queue's explicit delete operation. + +The browser cannot repair that loss by resending visible rows. It does not own their live `InboxItemId`, wake policy, or claim race, and a resend can duplicate work that the Host has already claimed. + +## Decision + +`session.cancel` is the Web Host API's active-turn stop for ordinary sessions. It rejects session-backed subagents with `agent-busy`; otherwise it calls `agent.cancel({ kind: 'user' }, { keepInbox: true })`, preserving pending inbox work while cooperatively aborting the current turn. The underlying option preserves queued and steering entries; the Web Queue projection continues to expose only queued entries. + +The AgentLoop starts no concurrent replacement turn. It closes and flushes the interrupted turn, reaches cancellation quiescence, and then claims the next waking queued occurrence through its existing FIFO driver. That claim emits `agent/inbox/dequeue`, so the Host's authoritative `session/queue` snapshot retires the claimed row and leaves the remaining tail visible. The browser neither resends nor promotes any row. Work that ignores cancellation delays this handoff until it settles. + +This mapping changes only the Host `session.cancel` endpoint used by Web clients. The default `Agent.cancel()` contract remains broad, ACP and TUI retain their existing cancellation policies, and `AgentHandle.dispose()` still clears pending work during teardown. Queue row removal remains the explicit Web action for discarding one pending occurrence. + +## Alternatives considered + +**Keep broad cancellation for the stop button.** Rejected because stopping one generation should not destroy independently queued user intent; the Queue already owns explicit deletion. + +**Resend the next row from the browser after cancellation.** Rejected because the Host owns occurrence identity and claim order. Client resubmission can duplicate work, reorder the FIFO, or race an authoritative dequeue. + +**Start the next turn before cancelled work reaches quiescence.** Rejected because two turns would concurrently mutate one session log and share Agent-owned resources. Cooperative cancellation waits truthfully for the active work to settle. + +**Add a wire option for broad versus preserving cancellation.** Rejected until the Web product has a separate “stop and clear Queue” interaction. The existing stop button has one policy, while per-row delete already supplies the current discard control. + +## Verification + +AgentLoop coverage holds an active model stream, queues two waking turns, cancels with `keepInbox`, and pins the aborted-then-completed turn reasons, FIFO user-message order, absence of discard events, and eventual idle state. The keyless Web scenario drives the built composition over HTTP/SSE: it stops one hung turn, observes the next queued occurrence start while the tail remains visible, stops that turn, and observes the final queued occurrence complete. Its accessibility snapshot pins the intermediate preserved-Queue state. + +## Consequences + +Web stop preserves accepted queued intent and advances it automatically after truthful cancellation settlement. Queue rows may remain visible while uncooperative active work winds down, and external steering preserved by the same inbox option can enter the next admitted turn even though Web does not render steering in QueueDock. A future bulk-clear interaction requires an explicit product action rather than overloading stop. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-web-stop-preserves-queue.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-web-stop-preserves-queue.zh.md new file mode 100644 index 0000000000..0e1fffae88 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-07-31-web-stop-preserves-queue.zh.md @@ -0,0 +1,37 @@ +# Agent Note: Web 停止操作保留待处理 Queue + +Status: implemented + +[English](2026-07-31-web-stop-preserves-queue.md) | 中文 + +## 问题 + +Web 停止按钮调用 `session.cancel`，后者映射到广义 `agent.cancel({ kind: 'user' })`。在活动轮次期间，普通 composer 提交已经被接纳为可独立寻址的 Queue 入队项。用户只想停止当前生成时，广义取消却会丢弃所有入队项，混淆了轮次中断与 Queue 的显式删除操作。 + +浏览器无法通过重发可见行修复这一损失。它不拥有这些行的实时 `InboxItemId`、唤醒策略或认领竞态；重发还可能重复 Host 已认领的工作。 + +## 决策 + +`session.cancel` 是 Web Host API 面向普通会话的活动轮次停止操作。它会以 `agent-busy` 拒绝由会话支撑的 subagent；否则会调用 `agent.cancel({ kind: 'user' }, { keepInbox: true })`，在协作式中止当前轮次的同时保留待处理 inbox 工作。底层选项会保留 queued 和 steering 入队项；Web Queue 投影继续只暴露 queued 入队项。 + +AgentLoop 不会启动并发的替代轮次。它会关闭并 flush 被中断的轮次，达到取消的完全停稳，然后通过现有 FIFO 驱动器认领下一个可唤醒的 queued 入队项。该认领会发出 `agent/inbox/dequeue`，因此 Host 的权威 `session/queue` 快照会退役已认领行，并使剩余队尾保持可见。浏览器既不重发，也不提升任何行。忽略取消的工作会延迟这一交接，直到该工作结算。 + +该映射只更改 Web 客户端使用的 Host `session.cancel` 端点。`Agent.cancel()` 默认契约仍为广义取消，ACP 和 TUI 保留既有取消策略，`AgentHandle.dispose()` 在拆卸期间仍会清除待处理工作。移除 Queue 行仍是用于丢弃单个待处理入队项的显式 Web 操作。 + +## 考虑过的替代方案 + +**停止按钮继续使用广义取消。** 之所以否决：停止一次生成不应销毁已独立排队的用户意图；Queue 已拥有显式删除操作。 + +**取消后由浏览器重发下一行。** 之所以否决：Host 拥有入队项标识和认领顺序。客户端重新提交可能重复工作、重排 FIFO，或与权威出队产生竞态。 + +**被取消工作达到完全停稳之前启动下一轮次。** 之所以否决：两个轮次会并发修改同一会话日志，并共享 Agent 拥有的资源。协作式取消会如实等待活动工作结算。 + +**为广义取消与保留式取消添加协议选项。** 之所以否决：在 Web 产品提供独立的「停止并清空 Queue」交互之前，不需要此选项。现有停止按钮只有一项策略，而逐行删除已提供当前的丢弃控件。 + +## 验证 + +AgentLoop 覆盖会保持一个活动模型流，将两个可唤醒轮次排队，使用 `keepInbox` 取消，并固定验证先中止、后完成的轮次原因，FIFO 用户消息顺序，不存在 discard 事件，以及最终空闲状态。无密钥 Web 场景通过 HTTP／SSE 驱动已组装组合：它停止一个卡住的轮次，观察队尾保持可见时下一个 queued 入队项开始，再停止该轮次，并观察最后一个 queued 入队项完成。其可访问性快照固定了中间的 Queue 保留状态。 + +## 后果 + +Web 停止会保留已接纳的排队意图，并在取消如实结算后自动推进。不配合取消的活动工作收尾时，Queue 行可能仍保持可见；由同一 inbox 选项保留的外部 steering 可以进入下一个已接纳轮次，尽管 Web 不会在 QueueDock 中渲染 steering。未来的批量清空交互需要显式的产品操作，而不是过载停止。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.i18n.yaml new file mode 100644 index 0000000000..c8784f5991 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.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/2026-08-02-goal-round-wrapup-message.md +2026-08-02-goal-round-wrapup-message.md: c6bc3d5912b0789efde55880c2be892e98e34a5b +2026-08-02-goal-round-wrapup-message.zh.md: 0a504b4dcc61feb932775b3d9ffd8424f3b0597d diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.md b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.md new file mode 100644 index 0000000000..c6bc3d5912 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.md @@ -0,0 +1,31 @@ +# Agent Note: Goal-round wrap-up message + +Status: implemented + +English | [中文](2026-08-02-goal-round-wrapup-message.zh.md) + +## Problem + +An autonomous goal round that reported `update_goal` `complete` or `blocked` concluded the physical turn at the tool result, so the model never spoke after the call. Sessions ended on a bare `update_goal` card, and internal testers read that as the agent stopping mid-sentence: the model's pre-call text routinely announces a report ("goal achieved, marking complete:") that never arrives, because the standard tool-use expectation is one more assistant message after a tool result and neither the goal-round prompt nor the tool description said the call was terminal. The hard stop came from the [goal-tool decision](../feature/2026-07-19-model-facing-goal-tools.md), whose turn-stop clause this note supersedes. + +## Decision + +A goal-round `complete` or `blocked` success no longer calls `concludeTurn()`. Instead the tool defers one wrap-up context onto its own result: a `{ kind: 'plugin', plugin: 'tool-goal' }`-sourced user message carrying a ``/`` instruction to write a grounded closing message to the user and call no more tools. The turn then ends through the agent loop's ordinary no-tool-calls stop, so no new loop primitive exists and steering semantics are untouched. Direct-human mutations remain uninstructed exactly as before. The cost is one additional model request per goal lifecycle, not per round. + +The instruction wording was selected by A/B sampling on `deepseek-v4-pro` with a reconstructed goal-round transcript: a structured instruction (outcome, verification, artifacts, next steps) consistently beat a minimal "summarize" one on completeness; adding a session-grounding clause shifted unsupported detail from asserted fact to hedged suggestion; and the no-instruction control produced high-variance closings, including confidently fabricated file-level detail. + +Scripting the keyless proof required one snapshot-harness addition: `dsh-llm-replay` resolves `{{fromRequest:}}` placeholders in scripted entries against the live request, because a static sidecar cannot know the randomly minted goal id the model must echo into `update_goal`. + +## Verification + +`tool-goal` package tests pin the injected context (source, tag, objective, no-more-tools clause) and the absent `concludesTurn` for both terminal actions, plus the uninstructed direct-human pause and complete paths, at 100% file coverage. `llm-replay` unit tests pin the placeholder contract: last-match-wins capture, whole-match fallback, and loud failures for unmatched, invalid, and unterminated patterns. The new keyless ACP snapshot `goal-wrapup` drives the shipped application through create → round one → autonomous complete and asserts the plugin-sourced wrap-up injection, the same-turn closing assistant message, and the `completed` turn end in both the durable session log and the ACP stdout stream. + +## Alternatives considered + +- **Surface the completion text on the `update_goal` UI card** — rejected: `complete` carries no free text today, and adding a `summary` argument would route a user-facing report through tool arguments while still cutting off the model's natural post-result message. +- **Keep `concludeTurn()` and add a "one more text-only step" loop primitive** — rejected: new `agent-loop` machinery for behavior the ordinary stop already provides once nothing concludes the turn. +- **Instruct inside the tool result content** — rejected: the goal tools' canonical output is compact JSON consumed programmatically; a prose instruction block inside it would mix the model-facing contract with the tool's replayable value. + +## Consequences + +Every autonomous goal ends with a user-facing closing message instead of a bare tool card, at the cost of one model request per goal lifecycle. `concludeTurn()` keeps its loop semantics but loses its only first-party caller outside subagent structured output. Snapshot scenarios can now script values that only exist at run time via `{{fromRequest:...}}`, which unblocks keyless coverage of any echo-an-id tool flow, goal or otherwise. diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.zh.md b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.zh.md new file mode 100644 index 0000000000..0a504b4dcc --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-02-goal-round-wrapup-message.zh.md @@ -0,0 +1,31 @@ +# Agent Note：Goal Round 收尾消息 + +Status: implemented + +[English](2026-08-02-goal-round-wrapup-message.md) | 中文 + +## 问题 + +自主 Goal Round 报告 `update_goal` `complete` 或 `blocked` 时，物理轮次在工具结果处直接终结，模型在调用之后再无发言机会。会话终止在一张裸的 `update_goal` 卡片上，内测同学的观感是 agent 话说到一半戛然而止：模型调用前的文本通常预告了一份汇报（“目标达成，标记完成：”）却永远没有下文，因为标准 tool-use 预期是工具结果之后还有一条 assistant 消息，而 Goal Round 提示词与工具描述都没有说明这次调用是终点。硬停止来自 [goal 工具决策](../feature/2026-07-19-model-facing-goal-tools.md)，本 note 取代其中的轮次停止条款。 + +## 决策 + +Goal Round 的 `complete` 或 `blocked` 成功不再调用 `concludeTurn()`。工具改为在自己的结果上附带一条收尾上下文：以 `{ kind: 'plugin', plugin: 'tool-goal' }` 为 source 的 user 消息，携带 ``/`` 指令，要求模型向用户写出有依据的收尾消息且不再调用工具。之后轮次经由 agent loop 常规的无工具调用停止路径结束，因此不存在新的 loop 原语，steering 语义不受影响。人类直接变更保持原样、不注入指令。代价是每个 goal 生命周期一次额外模型请求，而非每轮一次。 + +指令措辞通过在 `deepseek-v4-pro` 上用重构的 Goal Round 转录做 A/B 采样选定：结构化指令（结果、验证、产物、后续）在完整度上稳定优于极简“总结一下”；补充“以会话内证据为准”的 grounding 条款让无依据细节从断言事实退为带保留的建议；而无指令对照组的收尾方差很大，包括言之凿凿的文件级细节编造。 + +为让 keyless 证明可脚本化，快照设施补了一项能力：`dsh-llm-replay` 会针对实时请求解析脚本条目中的 `{{fromRequest:}}` 占位符，因为静态伴随文件不可能预知模型必须回填进 `update_goal` 的随机生成 goal id。 + +## 验证 + +`tool-goal` 包测试钉住两个终态 action 注入的上下文（source、标签、objective、禁止再调工具条款）与不存在的 `concludesTurn`，以及人类直接 pause 与 complete 的不注入路径，文件覆盖率 100%。`llm-replay` 单元测试钉住占位符契约：最后一次匹配取胜的捕获、无捕获组时整体匹配回退，以及未匹配、非法、未闭合模式的明确报错。新增 keyless ACP 快照 `goal-wrapup` 驱动成品应用走完 create → 第一轮 → 自主 complete，并在持久会话日志与 ACP stdout 流中同时断言 plugin 来源的收尾注入、同轮内的收尾 assistant 消息与 `completed` 轮次结束。 + +## 曾考虑的替代方案 + +- **在 `update_goal` 的 UI 卡片上展示完成文本** — 拒绝：`complete` 如今不携带任何自由文本；新增 `summary` 参数会让面向用户的汇报走工具参数通道，而且依然砍掉了模型在结果之后的自然发言。 +- **保留 `concludeTurn()` 并新增“再多一步纯文本”的 loop 原语** — 拒绝：为常规停止路径已经能提供的行为（只要没有结果终结轮次）增加新的 `agent-loop` 机制。 +- **把指令写进工具结果内容** — 拒绝：goal 工具的规范输出是被程序化消费的紧凑 JSON；在其中混入散文指令会把模型侧契约和工具的可回放值搅在一起。 + +## Consequences + +每个自主 goal 都以一条面向用户的收尾消息结束，而非一张裸工具卡片，代价是每个 goal 生命周期一次模型请求。`concludeTurn()` 保留其 loop 语义，但在 subagent 结构化输出之外失去了唯一的一方调用者。快照场景现在可以通过 `{{fromRequest:...}}` 脚本化只在运行时才存在的值，为任何“回显 id”类工具流程（不限于 goal）解锁 keyless 覆盖。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-message-fork-actions-require-completed-turn-tail.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-02-message-fork-actions-require-completed-turn-tail.i18n.yaml new file mode 100644 index 0000000000..9ac8e49fe6 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-02-message-fork-actions-require-completed-turn-tail.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/2026-08-02-message-fork-actions-require-completed-turn-tail.md +2026-08-02-message-fork-actions-require-completed-turn-tail.md: f2e7fd67b65a6ce4a86ba3f4405f78842be8f234 +2026-08-02-message-fork-actions-require-completed-turn-tail.zh.md: 2c3feeaa3ef01dbde67faa73257520918996f9c8 diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-message-fork-actions-require-completed-turn-tail.md b/.agents/notes/implemented/bug-fix/2026-08-02-message-fork-actions-require-completed-turn-tail.md new file mode 100644 index 0000000000..f2e7fd67b6 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-02-message-fork-actions-require-completed-turn-tail.md @@ -0,0 +1,29 @@ +# Agent Note: Message fork actions require a completed turn tail + +Status: implemented + +English | [中文](2026-08-02-message-fork-actions-require-completed-turn-tail.zh.md) + +## Problem + +The Web conversation attached branch to the last assistant node with nonempty text in each turn. A later tool result, interrupted reasoning node, or terminal error did not take ownership because those rows have no content-text IconActions. The branch icon could therefore appear beneath an assistant response while more rows from the same turn remained below it. The Host correctly expanded that message anchor through the containing `turn/end`, but the placement made the action look like a message-level cut and the child visibly inherited the same-turn suffix. + +## Decision + +`ConversationSnapshot.turnEnds` retains the completed turn boundaries present in the raw event window. The conversation view walks transcript nodes through each boundary and enables branch only when the boundary's last node is a user message, a durable steering message, or a content-bearing assistant message. Open turns have no eligible message, and a later tool result, reasoning-only interruption, turn error, or other transcript node leaves branch unavailable on earlier messages. The unavailable control stays visible, focusable, and hoverable; `aria-disabled`, a tooltip, and `aria-describedby` explain the completed-tail requirement without sending a Host request. Copy and clock remain available under their existing message chrome, and the Host's completed-turn fork semantics remain unchanged. + +This narrows the message eligibility established by the earlier [Web session fork action decision](../feature/2026-07-27-web-session-fork-actions.md). Session-row forking still selects the latest completed turn, and eligible message actions still pass their event seq through the shared client runtime operation. + +## Alternatives considered + +**Cut the event log at the clicked assistant message.** Rejected because an assistant message can sit inside an open step and can contain tool calls whose results occur later. A raw prefix at that seq is not a balanced turn and may not be a valid provider transcript. + +**Infer completion from `running` or the next user message.** Rejected because retry and steering turns need not align with the next visible user bubble, and a paged window may omit that later bubble. The durable `turn/end` event is the authoritative completion fact. + +**Hide branch from every interrupted turn.** Rejected because an aborted turn is durably closed and its final interrupted text can be the true transcript tail. Eligibility depends on the completed boundary and node order, not the outcome kind. + +**Hide ineligible message controls.** Rejected because a disappearing control does not explain the boundary requirement and shifts otherwise stable message chrome. A focusable unavailable control preserves the affordance while preventing the request. + +## Consequences + +An enabled branch icon denotes the same completed-turn boundary that the Host will copy. In the reported response → tool → interrupted Think shape, the response keeps copy, clock, and a disabled branch control that explains why it cannot act. This change deliberately does not provide same-turn transcript editing or a retry-before-turn operation; the Session-row action remains available when a reader wants to copy the latest completed turn in full. Runtime tests pin boundary projection and reference stability, while conversation tests cover assistant, user-only, and durable-steering tails plus unavailable controls caused by later tool and interrupted reasoning rows. diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-message-fork-actions-require-completed-turn-tail.zh.md b/.agents/notes/implemented/bug-fix/2026-08-02-message-fork-actions-require-completed-turn-tail.zh.md new file mode 100644 index 0000000000..2c3feeaa3e --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-02-message-fork-actions-require-completed-turn-tail.zh.md @@ -0,0 +1,29 @@ +# Agent Note: 消息 fork 操作要求消息位于已完成轮次尾部 + +Status: implemented + +[English](2026-08-02-message-fork-actions-require-completed-turn-tail.md) | 中文 + +## 问题 + +Web 会话把分支操作挂到每个轮次中最后一个文本非空的 assistant 节点上。如果后面还有工具结果、被中断的推理（reasoning）节点或终态错误，这些行也不会接管操作，因为它们没有内容文本 IconActions。因此，分支图标可能出现在 assistant 响应下方，而同一轮次的更多行仍位于其后。Host 会正确地把该消息锚点扩展到其所在的 `turn/end`，但图标位置使操作看起来像在消息级截断，子会话又会明显继承同轮次的后缀。 + +## 决策 + +`ConversationSnapshot.turnEnds` 保留原始事件窗口中的已完成轮次边界。会话视图按各边界遍历 transcript（文本记录）节点，仅当边界的最后一个节点是用户消息、持久 steering（中途引导）消息或含内容的 assistant 消息时才启用分支操作。开放轮次没有符合条件的消息；如果后面还有工具结果、只有推理内容的中断、轮次错误或其他 transcript 节点，较早消息上的分支操作会保持不可用。不可用的控件仍然可见、可聚焦、可悬停；`aria-disabled`、tooltip 与 `aria-describedby` 会说明已完成尾部这一要求，且不会发送 Host 请求。复制和时钟仍可在既有消息 chrome 下使用，Host 按已完成轮次 fork 的语义保持不变。 + +本决策收紧了较早的 [Web 会话 fork 操作决策](../feature/2026-07-27-web-session-fork-actions.md)所定义的消息资格。Session 行 fork 仍选择最新的已完成轮次；符合条件的消息操作仍通过共享 client 运行时操作传递其事件 seq。 + +## 考虑过的替代方案 + +**在点击的 assistant 消息处截断事件日志。** 不予采纳：assistant 消息可能位于尚未结束的步骤内，也可能包含结果随后才出现的工具调用。以该 seq 截取的原始前缀并不是结构完整的轮次，也可能不是有效的提供方 transcript。 + +**从 `running` 或下一条用户消息推断完成状态。** 不予采纳：重试轮次与 steering 轮次不一定和下一个可见用户气泡对齐，分页窗口也可能省略该气泡。持久 `turn/end` 事件才是权威的完成事实。 + +**对每个被中断轮次隐藏分支。** 不予采纳：已中止的轮次会持久关闭，其最终的中断文本可能正是真正的 transcript 尾部。资格取决于已完成边界与节点顺序，而非结果类别。 + +**隐藏不符合条件的消息控件。** 不予采纳：消失的控件无法说明边界要求，还会让本应稳定的消息 chrome 发生位移。保留可聚焦但不可用的控件，既能维持操作提示，也能阻止请求。 + +## 后果 + +启用的分支图标现在表示的已完成轮次边界与 Host 实际复制的边界一致。在所报告的「响应 → 工具 → 被中断的 Think」形态中，响应仍保留复制、时钟，以及一个说明无法操作原因的禁用分支控件。本变更刻意不提供同轮次 transcript 编辑，也不提供轮次前重试操作；当读者希望完整复制最新的已完成轮次时，仍可使用 Session 行操作。运行时测试固定边界投影和引用稳定性，会话测试则覆盖 assistant 尾部、纯用户消息尾部、持久 steering 尾部，以及后续工具行和被中断推理行导致的不可用控件。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.i18n.yaml new file mode 100644 index 0000000000..eeac8a251c --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.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/2026-08-02-todo-first-composer-context-order.md +2026-08-02-todo-first-composer-context-order.md: 26962426c763c6911fc61acab09cdb96725922b1 +2026-08-02-todo-first-composer-context-order.zh.md: a81401ffeb8df5855b584a5727e24067d9fb1e70 diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.md b/.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.md new file mode 100644 index 0000000000..26962426c7 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.md @@ -0,0 +1,33 @@ +# Agent Note: Todo-first composer context order + +Status: implemented + +English | [中文](2026-08-02-todo-first-composer-context-order.zh.md) + +## Problem + +The composer context stack rendered Goal before Todo even though the Harness design orders the current task plan before its ongoing goal and pending Queue. Todo also used the Queue wrapper's 776px width as its visible card width, while Goal and the Queue panel rendered on the shared 752px card column. The result inverted the intended information hierarchy and left Todo wider than both adjacent panels. + +## Decision + +The `conversation.input.dock` list uses one ascending product order: Todo at `0`, Goal at `10`, and Queue at `20`, followed by the composer bar outside the list. Registration order remains the semantic source of truth; the renderer does not hardcode known component ids or repair their order with CSS. + +Todo, Goal, and the visible Queue panel share the 752px card column inside the 800px composer cap. Queue retains a 776px wrapper with 12px transparent inset on each side because that wrapper owns the composer overlap. Todo is a standalone card rather than a wrapper, so its responsive width and maximum width subtract both inset layers directly. Goal uses the same responsive column and caps its inner bar at 752px, preserving matching edges below the desktop cap. + +The [composer stack contract](2026-07-30-composer-context-stack-order.md) continues to own inter-card spacing and Queue's exclusive overlap with the composer. This decision supersedes only that note's Goal-first order. + +## Verification + +Todo and Goal registration tests pin orders `0` and `10`; Queue remains pinned at `20`. The keyless Queue browser scenario renders all three panels concurrently, records their Todo–Goal–Queue accessibility order, and compares their visible bounding boxes at the 1680px desktop baseline and a 640px sub-cap viewport before exercising Queue mutations. + +## Alternatives considered + +**Reorder the known panels inside `ConversationRoot`.** Rejected because `conversation.input.dock` is an extensible ordered list; a hardcoded component inventory would make plugin activation order and rendered order disagree. + +**Use CSS `order` to move Todo visually.** Rejected because accessibility and keyboard order must match the visual hierarchy, and the slot ledger already owns semantic order. + +**Keep Todo at the Queue wrapper width.** Rejected because the Queue wrapper's transparent inset is layout infrastructure for its composer overlap, not part of the visible panel column. + +## Consequences + +The standing task plan appears before the ongoing goal, pending Queue work remains closest to the composer, and all three visible cards share one horizontal edge. Future input-dock plugins choose an explicit position relative to Todo `0`, Goal `10`, and Queue `20`; only Queue owns the terminal wrapper overlap. diff --git a/.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.zh.md b/.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.zh.md new file mode 100644 index 0000000000..a81401ffeb --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-02-todo-first-composer-context-order.zh.md @@ -0,0 +1,33 @@ +# Agent Note: Todo 优先的 composer 上下文顺序 + +Status: implemented + +[English](2026-08-02-todo-first-composer-context-order.md) | 中文 + +## 问题 + +composer 上下文堆栈将 Goal 渲染在 Todo 之前，但 Harness 设计稿把当前任务计划排在进行中的目标和待处理 Queue 之前。Todo 还把 Queue 包装层的 776px 宽度用作自身的可见卡片宽度，而 Goal 和 Queue 面板则渲染在共享的 752px 卡片列上。结果既颠倒了预期的信息层级，也让 Todo 比相邻两个面板更宽。 + +## 决策 + +`conversation.input.dock` 列表采用统一的产品顺序，升序依次为 Todo `0`、Goal `10`、Queue `20`，随后是位于列表外的 composer bar。注册顺序仍是语义真源；渲染器不会硬编码已知组件 id，也不会使用 CSS 修正它们的顺序。 + +Todo、Goal 与可见的 Queue 面板共用 800px composer 宽度上限内的 752px 卡片列。Queue 保留 776px 包装层，并在两侧各留 12px 透明内缩，因为该包装层负责与 composer 重叠。Todo 是独立卡片，而非包装层，因此其响应式宽度和最大宽度都会直接扣除两层内缩。Goal 使用相同的响应式卡片列，并将内层横条的宽度上限设为 752px，从而在低于桌面宽度上限时也保持边缘对齐。 + +[composer 堆栈契约](2026-07-30-composer-context-stack-order.md)继续规定卡片间距，以及仅限 Queue 与 composer 重叠。本决策只取代该记录中 Goal 优先的顺序。 + +## 验证 + +Todo 与 Goal 的注册测试分别固定顺序 `0` 和 `10`；Queue 仍固定为 `20`。无密钥 Queue 浏览器场景同时渲染三个面板，记录 Todo–Goal–Queue 的无障碍顺序，并在 1680px 桌面基线和低于宽度上限的 640px 视口下比较其可见边界框，随后再执行 Queue 变更。 + +## 考虑过的替代方案 + +**在 `ConversationRoot` 内重新排列已知面板。** 不予采纳，因为 `conversation.input.dock` 是可扩展的有序列表；硬编码的组件清单会使插件激活顺序与渲染顺序不一致。 + +**使用 CSS `order` 移动 Todo 的视觉位置。** 不予采纳，因为无障碍顺序和键盘顺序必须与视觉层级一致，而 slot 账本已经负责语义顺序。 + +**让 Todo 保持 Queue 包装层的宽度。** 不予采纳，因为 Queue 包装层的透明内缩是其与 composer 重叠所需的布局基础设施，不属于可见面板列。 + +## 后果 + +当前有效的任务计划显示在进行中的目标之前，待处理 Queue 工作仍最靠近 composer，三张可见卡片共用相同的横向边缘。未来的 input-dock 插件必须相对于 Todo `0`、Goal `10` 和 Queue `20` 选择明确位置；仅 Queue 负责末端包装层与 composer 的重叠。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-03-hmr-initial-scan-boot-deadlock.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-03-hmr-initial-scan-boot-deadlock.i18n.yaml new file mode 100644 index 0000000000..170627ea76 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-03-hmr-initial-scan-boot-deadlock.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/2026-08-03-hmr-initial-scan-boot-deadlock.md +2026-08-03-hmr-initial-scan-boot-deadlock.md: 4b3e259c216d258c321ab06c41225b33ed240d19 +2026-08-03-hmr-initial-scan-boot-deadlock.zh.md: ce1bc8396ac6e7fb6ecb1647fe2b29cdc788c7e1 diff --git a/.agents/notes/implemented/bug-fix/2026-08-03-hmr-initial-scan-boot-deadlock.md b/.agents/notes/implemented/bug-fix/2026-08-03-hmr-initial-scan-boot-deadlock.md new file mode 100644 index 0000000000..4b3e259c21 --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-03-hmr-initial-scan-boot-deadlock.md @@ -0,0 +1,41 @@ +# Agent Note: HMR's initial scan deadlocked a failing boot into a silent exit 13 + +Status: implemented + +English | [中文](2026-08-03-hmr-initial-scan-boot-deadlock.zh.md) + +## Problem + +A `dsh` launch whose config-tree failed validation exited 13 (unsettled top-level await) with no diagnostic at all, and left the TUI's terminal state stranded on the shell — the exact symptom the [fail-loud release](2026-07-31-fail-loud-releases-the-terminal.md) fixed, reintroduced through a different mechanism after the [transactional config reload](2026-07-20-config-hot-reload-resilience.md). + +Two defects compounded: + +1. **Concurrent Include applies corrupt the transactional group update.** The HMR main watcher's chokidar initial scan re-announces every existing file as `add`. Its `add` for the config file triggered `Include.refresh()` while the Include's initial apply was still in flight (`this.content`, the changed-content dedup key, commits only after apply). Two concurrent `EntryGroup.update` calls on one group interleave create and rollback on the same entries, and the Include fiber never settles — `loader.create` hangs, `boot()` neither resolves nor rejects, and Node exits 13 once the loop drains. +2. **Serialized applies alone deadlock the failure rollback.** With Include mutations queued, a failing initial apply rolls back by disposing every mounted entry — including `hmr`, whose teardown drains its refresh tasks. The scan-triggered refresh task sits in the Include queue behind the very apply whose rollback is disposing HMR: rollback waits on HMR, HMR waits on the refresh, the refresh waits on the apply. + +## Decision + +Both halves are fixed in the vendored packages (logged in `vendor/README.md`): + +- `include/src/index.ts` funnels every child-tree mutation — initial apply, refresh, and `internal/update` patch re-application — through one per-Include promise queue. The group's transactional `update` is not reentrant, so serialization is a correctness requirement, not a throughput choice. `refresh()` also reads inside the queue so its changed-content check compares against the predecessor's committed state. +- `hmr/src/index.ts` passes `ignoreInitial: true` to the main watcher. The initial scan only re-announces files boot has just consumed; suppressing it removes both the boot-time refresh and the spurious `add` events for already-loaded modules. `registerConfig()` keeps its own `ignoreInitial: false` watcher because a personal config present at registration must apply exactly once. + +With both in place a failing boot follows the intended path: the single apply fails, the rollback disposes the tree (running the TUI's own shutdown, restoring the terminal), `loader.create` rejects, and `boot()` rethrows the labelled diagnostic with exit 1. + +## Alternatives considered + +**Only `ignoreInitial: true`.** Removes the trigger but leaves the corruption: any genuinely concurrent refresh (a config edit racing a slow apply) still interleaves two group updates and strands the fiber. + +**Only serialization.** Converts the corruption into the rollback deadlock described above; the process still exits 13 silently. + +**Cancel queued refreshes on HMR teardown.** Requires cancellation plumbing through `refreshConfig`'s task loop and the Include queue for a case `ignoreInitial` already removes from every boot; not worth the machinery until a real trigger remains. + +## Consequences + +A config file edit landing inside the watcher's startup scan window is now picked up by the next `change` event rather than the scan itself; steady-state reload behavior is unchanged. + +One latent gap remains: a config edit made during a *failing* initial apply can still queue a refresh that the rollback's HMR teardown waits on — the same deadlock shape with a human-scale trigger window of one failing boot. If that ever bites, the fix is refresh-task cancellation at HMR teardown. + +## Testing + +The `dsh` invalid-provider PTY case in `apps/cli/tests/tui-keyless-smoke.e2e.ts` pins the end-to-end contract: exit 1, the labelled `dsh: plugin tree failed to load:` diagnostic naming `$.providers`, and the bracketed-paste reset proving the tree was disposed. Before this fix the same case observed exit 13 with no diagnostic. Reload behavior stays covered by `packages/ui/app-boot/tests/config-reload.spec.ts` and `packages/ui/app-boot/tests/hmr-config.spec.ts`. diff --git a/.agents/notes/implemented/bug-fix/2026-08-03-hmr-initial-scan-boot-deadlock.zh.md b/.agents/notes/implemented/bug-fix/2026-08-03-hmr-initial-scan-boot-deadlock.zh.md new file mode 100644 index 0000000000..ce1bc8396a --- /dev/null +++ b/.agents/notes/implemented/bug-fix/2026-08-03-hmr-initial-scan-boot-deadlock.zh.md @@ -0,0 +1,41 @@ +# Agent Note：HMR 初始扫描使失败的启动死锁为静默的 exit 13 + +状态：已实现 + +[English](2026-08-03-hmr-initial-scan-boot-deadlock.md) | 中文 + +## 问题 + +当 `dsh` 启动时配置树校验失败，进程以 13 退出（未结算的顶层 await），不输出任何诊断，并把 TUI 的终端状态残留在 shell 上——这正是 [fail-loud release](2026-07-31-fail-loud-releases-the-terminal.md) 修复过的症状，在[事务化配置重载](2026-07-20-config-hot-reload-resilience.md)之后经由另一条机制重新出现。 + +两个缺陷叠加： + +1. **并发的 Include apply 破坏事务化的 group update。** HMR 主 watcher 的 chokidar 初始扫描会把每个已存在的文件重新宣告为 `add`。其中配置文件的 `add` 在 Include 的首次 apply 尚未结束时触发了 `Include.refresh()`（内容去重键 `this.content` 只在 apply 完成后才提交）。同一 group 上两个并发的 `EntryGroup.update` 会在相同条目上交错执行 create 与回滚，导致 Include fiber 永远无法结算：`loader.create` 挂起，`boot()` 既不 resolve 也不 reject，事件循环排空后 Node 以 13 退出。 +2. **仅序列化 apply 会让失败回滚死锁。** 将 Include 的变更排入队列后，首次 apply 失败时的回滚会释放每个已挂载条目——包括 `hmr`，而它的拆卸会等待自身的 refresh 任务排空。扫描触发的 refresh 任务正排在 Include 队列中、位于正在回滚的那次 apply 之后：回滚等 HMR，HMR 等 refresh，refresh 等 apply。 + +## 决定 + +两处修复都落在 vendored 包中（记录于 `vendor/README.md`）： + +- `include/src/index.ts` 将每次子树变更——首次 apply、refresh、`internal/update` 补丁重应用——汇入每个 Include 一条的 promise 队列。group 的事务化 `update` 不可重入，因此序列化是正确性要求，而不是吞吐取舍。`refresh()` 也在队列内读取文件，使其内容变更判断与前一任务提交后的状态比较。 +- `hmr/src/index.ts` 给主 watcher 传入 `ignoreInitial: true`。初始扫描只会重新宣告启动刚刚消费过的文件；抑制它同时消除了启动期 refresh 和对已加载模块的多余 `add` 事件。`registerConfig()` 保留自己 `ignoreInitial: false` 的 watcher，因为注册时已存在的个人配置必须恰好应用一次。 + +两者齐备后，失败的启动走上预期路径：唯一一次 apply 失败，回滚释放整棵树（执行 TUI 自身的 shutdown、恢复终端），`loader.create` reject，`boot()` 重新抛出带标签的诊断并以 1 退出。 + +## 曾考虑的替代方案 + +**只加 `ignoreInitial: true`。** 消除了触发条件，但保留了破坏本身：任何真正并发的 refresh（配置编辑与缓慢的 apply 竞争）仍会交错两次 group update 并使 fiber 悬置。 + +**只做序列化。** 把破坏转化为上述回滚死锁；进程仍然静默地以 13 退出。 + +**在 HMR 拆卸时取消排队中的 refresh。** 需要在 `refreshConfig` 的任务循环和 Include 队列中铺设取消机制，而 `ignoreInitial` 已把该场景从每次启动中移除；在真实触发条件出现之前不值得引入这套机构。 + +## 后果 + +落在 watcher 启动扫描窗口内的配置文件编辑，现在由下一个 `change` 事件而非扫描本身拾取；稳态的重载行为不变。 + +仍留有一个潜在缺口：在一次*失败的*首次 apply 期间进行的配置编辑，仍可能排入一个被回滚的 HMR 拆卸所等待的 refresh——同样的死锁形态，但触发窗口缩小到一次失败启动的人力尺度。若它真的发生，修复方向是在 HMR 拆卸时取消 refresh 任务。 + +## 测试 + +`apps/cli/tests/tui-keyless-smoke.e2e.ts` 中 `dsh` 无效 provider 的 PTY 用例钉住了端到端契约：以 1 退出、带标签的 `dsh: plugin tree failed to load:` 诊断指明 `$.providers`、以及证明整棵树已被释放的 bracketed-paste 复位序列。此修复之前，同一用例观察到的是无诊断的 exit 13。重载行为仍由 `packages/ui/app-boot/tests/config-reload.spec.ts` 与 `packages/ui/app-boot/tests/hmr-config.spec.ts` 覆盖。 diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml index 414c63211a..714b75d942 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-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/feature/2026-06-18-compaction-capability-seam.md -2026-06-18-compaction-capability-seam.md: 3c219b734e148b963fb5857de89c16f28c2bd402 -2026-06-18-compaction-capability-seam.zh.md: b2c7e9720b596705b60a284e6ccf1448a782b7fc +2026-06-18-compaction-capability-seam.md: ef37313bc6fb984689793fa5a3e7ac4d9238ea88 +2026-06-18-compaction-capability-seam.zh.md: 9f123a8c40f303a2635af78cafd34de448e27e03 diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md index 3c219b734e..ef37313bc6 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -18,10 +18,10 @@ Two forces shape the design. First, compaction policy and reusable token measure Per the [capability-seams Agent Note](../architecture/2026-06-13-capability-seams.md), compaction ships as separate packages so the contract, the algorithm, and (later) the consumer surface evolve independently: -1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, the `compact/*` session events, and the canonical checkpoint message source. It declares `compactIfNeeded()` and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. +1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, the `compact/*` session events, the manual failure taxonomy, and the canonical checkpoint message source. It declares `compactIfNeeded()`, `compactNow()`, and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. 2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, post-step pressure, and canonical context-overflow recovery. `summarize()` is its sole subclass hook; pricing and replay stay with the meter. 3. **Model-free companion** — `@deepseek-ai/dsh-compact-tool-result-prune`: a concrete optional service that rewrites oversized current `tool/result` nodes before the backend selects a summary range. It is not a second compaction implementation and does not implement `CompactService`. -4. **Consumer** — deferred. A `/compact` tool and slash command will `inject: ['compact']` and call the contract; they are intentionally out of scope here so the seam settles first. +4. **Human consumer** — `@deepseek-ai/dsh-command-compact` registers argument-free `/compact` through `ctx.commands` and calls the backend-independent `compactNow()` operation. It is direct human control, not a model-facing tool. ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation @@ -29,11 +29,11 @@ The capability-seams Agent Note states the interface package "depends only on co This is not a coupling smell — it is the contract's domain. The "only cordis" guidance was always shorthand for "the interface depends only on what the contract genuinely names, and never on an implementation." `dsh-session` and `dsh-llm` are themselves interface/vocabulary packages, not implementations; `dsh-compact` still imports no backend. The seam's real invariant — *consumers and implementations evolve independently behind an abstract service* — holds intact. -### Abstract `compactIfNeeded` / `compactRegion`, algorithm in the backend +### Three abstract operations, algorithm in the backend -An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold. +An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making all three operations abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the singleton service lets multiple consumers share one per-session replay fold. -`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It reads only the latest durable routed request; no header means no work, while any routed provider/model target uses the singleton estimator. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for manual callers. The default summarizer resolves its target from explicit config, the latest logged routed target, then agent options, and records the provider/model pair after any `llm/stream` routing. It replays the routed request's prefix and appends the compaction directive as a trailing user message so the provider's warm KV cache is reused — see the [summary prefix-cache Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md). The call sets the provider-neutral `GenerateOptions.purpose` to `compaction`; adapters may map that purpose to model-hidden transport metadata, and the DeepSeek adapter sends `x-deepseek-harness-compact: 1`. +`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It reads only the latest durable routed request; no header means no work, while any routed provider/model target uses the singleton estimator. `compactNow(agent, signal)` reserves idle turn admission and performs one useful balanced reduction even below pressure, returning `null` without writes when none exists. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for explicit callers. The default summarizer resolves its target from explicit config, the latest logged routed target, then agent options, and records the provider/model pair after any `llm/stream` routing. It replays the routed request's prefix and appends the compaction directive as a trailing user message so the provider's warm KV cache is reused — see the [summary prefix-cache Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md). The call sets the provider-neutral `GenerateOptions.purpose` to `compaction`; adapters may map that purpose to model-hidden transport metadata, and the DeepSeek adapter sends `x-deepseek-harness-compact: 1`. ### Automatic pressure runs after successful durable step work @@ -91,42 +91,44 @@ The basic backend wraps the summary as established checkpoint context and tags i ### Blocking via a log-recorded lock, plus a crash/recoverable failure taxonomy -The `compact/start … compact/end` bracket is justified, in order of what now does the work: +The `compact/start … compact/end` bracket is justified by two roles: 1. **Crash-detectable orphan + provenance** (primary). Summarization is a slow model call persisted *after* `compact/start`. A crash mid-summarization leaves a `compact/start` with no matching `compact/end` — a detectable orphan. Releasing the lock last (rather than first) converts the crash window from *silent corruption* into that detectable orphan. -2. **Prevents concurrent compaction.** `compactRegion` refuses to start if the current turn holds an unmatched `compact/start`. (The loop is single-threaded across either awaited automatic seam, so this is also a re-entry tripwire — a thrown "already in progress" signals a real bug.) +2. **Prevents concurrent compaction.** Every automatic, manual, and explicit-range entry point refuses a live unmatched `compact/start`. The bracket is the single lock; no process-local mutex duplicates it. -The lock excludes another compaction, not unrelated log-only facts. The basic backend snapshots the token meter's surface nodes after `compact/start` and compares them again after asynchronous summarization; any surface mutation rejects before replacement, while a title or other log-only append leaves the selected span valid. +The lock excludes another compaction, not unrelated facts. Its markers are time points rather than an exclusive container, so idle injected context may appear between a standalone manual start and end. Automatic work requires whole-surface stability inside its turn. Manual work revalidates only the selected positional span, letting append-only context outside it remain visible after replacement. -Two failure paths, both documented: +The lifecycle boundary makes crash state unambiguous: -- **Crash** (the loop dies mid-summarization): a dangling `compact/start`, no closer. Because `compact/*` are **log-only**, the orphan is **inert** — no summary replacement lands. The derived surface remains the durable surface present at `compact/start`: full history when pruning made no replacement, or the already-pruned history when it did. Generic turn-repair (`interruptedTurnClosers`) closes the turn with a synthetic `turn/end`; the orphan sits *before* that `turn/end`, so the turn-scoped in-progress check never sees it and a crash cannot wedge future compaction. -- **Recoverable** (summarization throws but the loop survives): the backend appends `compact/end` with its **`error`** field set and lands no summary replacement. Post-step pressure warns and continues from the latest durable surface — full history if no replacement preceded the attempt, or the pruned surface if pruning already landed. Overflow recovery delegates only before any replacement; generation progress from earlier pruning authorizes a retry from that durable surface unless cancellation or disposal wins. +- **Current lifecycle:** a dangling `compact/start` after the newest `session/end-seed` is the live durable lock and reports busy. +- **Later lifecycle:** a newer constructor-written `session/end-seed` proves that the older unmatched start is stale, so resume, fork, and adoption do not remain wedged by a dead writer. +- **Recoverable failure:** once start lands, the backend makes exactly one `compact/end { error }` attempt. Summary or stability failure leaves the conversation surface unchanged while preserving the failed attempt in the log. If the close append fails, the unmatched start remains intentionally blocking. `compact/end` keeps its `error?` field (mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling). There is no separate `compact/error` event. -**Core session repair stays compaction-agnostic — deliberately.** `interruptedTurnClosers` is never taught about `compact/*`. Teaching it would force every future `xxx/start … xxx/end` plugin pair to patch a core module — exactly the coupling the capability-seam architecture exists to avoid. Because the log-only orphan is inert, no special repair is needed: generic turn-repair plus the inertness of an un-landed surface mutation is sufficient. +**Core session repair stays compaction-agnostic — deliberately.** `interruptedTurnClosers` is never taught about `compact/*`. The general `session/end-seed` lifecycle boundary supplies the evidence the compaction owner needs; the compaction invariant and backend interpret it without adding plugin-specific repair to core. ## Alternatives considered -- **The full algorithm as concrete interface methods** — rejected because it recouples the contract to one retention strategy. Both core methods are abstract; reusable measurement is a separate LLM-family service and `summarize()` is basic's sole hook. +- **The full algorithm as concrete interface methods** — rejected because it recouples the contract to one retention strategy. All three operations are abstract; reusable measurement is a separate LLM-family service and `summarize()` is basic's sole hook. - **Compaction on `agent/request` or provisional `agent/pre-step` inputs** — rejected because neither proves the final durable request and both couple generic lifecycle to compaction-specific envelope data. Post-step replay plus canonical overflow recovery covers both successful and rejected calls. - **A `compact` boolean or untyped request metadata map** — rejected because multiple auxiliary call kinds would become mutually exclusive flags, while an open bag would discard compiler-checked vocabulary. One typed `purpose` discriminant extends with additional call kinds without adding another `GenerateOptions` field. - **A separate `compact/error` event** — rejected: `compact/end` keeps an `error?` field, mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling. -- **Teaching core turn-repair about `compact/*`** — rejected: the log-only orphan is inert, and a core module patched for every future `xxx/start … xxx/end` plugin pair is exactly the coupling the capability-seam architecture exists to avoid. +- **Teaching core turn-repair about `compact/*`** — rejected: the general end-seed boundary already distinguishes prior-lifecycle history, and patching core for every future `xxx/start … xxx/end` pair is exactly the coupling the capability-seam architecture exists to avoid. ## Consequences -- **Packages**: `packages/compact/compact` supplies the interface, `compact-basic` supplies the backend, and `compact-tool-result-prune` supplies optional deterministic rewriting. `packages/llm/token-meter` owns replay-aware measurement independently. The consumer tier is deferred. +- **Packages**: `packages/compact/compact` supplies the interface, `compact-basic` supplies the backend, `compact-tool-result-prune` supplies optional deterministic rewriting, and `command-compact` supplies human `/compact`. `packages/llm/token-meter` owns replay-aware measurement independently. - **Automatic seams**: `agent/post-step` (`@mode serial`) handles successful-call pressure and `agent/request-error` (`@mode waterfall`) handles final request failures after the failed step closes. Generic `agent/pre-step` remains a four-argument checkpoint with no compaction-only prompt/prefix payload. - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. - **`dsh-compact`** owns `COMPACT_CHECKPOINT_SOURCE`, `isCompactCheckpointSource(source)`, `toolPairingBalancedBefore(session, seq)`, and `toolPairingBalancedAfter(session, seq)`. The marker identifies replacement summaries across backend implementations. The cached surface-edge checks prevent `compactRegion` and `compactIfNeeded` from splitting a tool-call/result pair, validate current membership by seq, answer both edges from one per-cut balance sequence, and reject stale or missing seqs and orphan results. -- **`dsh-session`** validates positional replacement, complete provenance, and content-only single-node `tool/result` rewrites through its one surface manager. Its invariant companion treats fresh appended tool results as executions that require an open step and pending call; validated replacements remain turn-enclosed rewrites. -- **Wiring**: `examples/tui-agent/cordis.yml` loads zero-config `dsh-token-meter`, `dsh-compact-tool-result-prune`, then `dsh-compact-basic`; service-wide defaults make the composition usable without repeated numeric policy. +- **`dsh-session`** validates positional replacement, complete provenance, and content-only single-node `tool/result` rewrites through its one surface manager. Its invariant companion treats fresh appended tool results as executions that require an open step and pending call, while the compaction companion owns numeric-turn versus standalone-null bracket relations. +- **Wiring**: `examples/tui-agent/cordis.yml` loads zero-config `dsh-token-meter`, `dsh-compact-tool-result-prune`, `dsh-compact-basic`, then `dsh-command-compact`; service-wide defaults make the composition usable without repeated numeric policy. ## Testing - **Unit:** Real Loader and invariant plugins cover whole-unit retention, pruning configuration and replay, rich-block ordering, metadata preservation, convergence, both `compact/end` outcomes, open-tail refusal, pruning-only and summarized overflow recovery, generation proof, caps, and original-error preservation. - **Loop:** Tests pin post-step after durable tool results and before `step/end`, actual `agent/request` routing, closed failed steps, fresh retry numbering, and complete thrown/in-band overflow → compaction → reconstructed retry composition. +- **Manual:** Admission, marker ordering, injection retention, live/stale orphan classification, cancellation, close/flush failures, command mapping, and the queued TUI journey are pinned without a model key. - **With-key e2e:** A real model and bash session with lowered limits triggers compaction, records a complete `compact/start…end` pair, shrinks the surface, and finishes the task. - **Snapshot gap:** Runaway-turn compaction cannot yet replay because the summarization call records no `assistant/chunk` events or `sessionId`; interleaved summarization-call replay remains follow-up work. diff --git a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md index b2c7e9720b..9f123a8c40 100644 --- a/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md +++ b/.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md @@ -18,10 +18,10 @@ Status: implemented 遵循[能力 seam Agent Note（agent 决策记录）](../architecture/2026-06-13-capability-seams.md)，压缩以独立包（package）发布，使契约、算法和（后续的）消费方 surface 各自独立演进： -1. **接口** — `@deepseek-ai/dsh-compact`：抽象 `CompactService`，拥有 `ctx.compact` 键、`CompactionResult` 词汇、`compact/*` 会话事件以及规范的检查点消息来源。它将 `compactIfNeeded()` 和 `compactRegion()` 声明为**抽象方法**——契约说明压缩*做什么*，而非*怎么做*。 +1. **接口** — `@deepseek-ai/dsh-compact`：抽象 `CompactService`，拥有 `ctx.compact` 键、`CompactionResult` 词汇、`compact/*` 会话事件、手动失败分类体系以及规范的检查点消息来源。它将 `compactIfNeeded()`、`compactNow()` 和 `compactRegion()` 声明为**抽象方法**——契约说明压缩*做什么*，而非*怎么做*。 2. **实现** — `@deepseek-ai/dsh-compact-basic`：具体的 `BasicCompactService`，消费 `ctx.tokenMeter`，并拥有尾→头保留遍历、通过 `ctx.llm.stream()` 生成摘要、surface 替换、锁、步骤后压力处理和规范的上下文溢出恢复。`summarize()` 是其唯一的子类钩子；计价与回放仍归 meter 所有。 3. **无模型配套服务** — `@deepseek-ai/dsh-compact-tool-result-prune`：一个具体的可选服务，在后端选择摘要范围之前，重写当前过大的 `tool/result` 节点。它不是第二种压缩实现，也不实现 `CompactService`。 -4. **消费方** — 推迟。一个 `/compact` 工具和斜杠命令将 `inject: ['compact']` 并调用契约；它们被有意排除在本 Agent Note 范围之外，以便 seam 先稳定下来。 +4. **面向用户的消费方** — `@deepseek-ai/dsh-command-compact` 通过 `ctx.commands` 注册无参数 `/compact`，并调用后端无关的 `compactNow()` 操作。它是供用户直接控制的命令，不是面向模型的工具。 ### 契约依赖 `dsh-session` 和 `dsh-llm`——有意为之的偏离 @@ -29,11 +29,11 @@ Status: implemented 这不是耦合异味，而是契约的领域所在。「仅 cordis」的指导原则一直是「接口仅依赖契约真正需要命名的东西，绝不依赖实现」的简写。`dsh-session` 和 `dsh-llm` 本身是接口/词汇包，不是实现；`dsh-compact` 仍然不导入任何后端。seam 的真正不变式——*消费方和实现在抽象服务背后独立演进*——完好无损。 -### 抽象 `compactIfNeeded` / `compactRegion`，算法在后端 +### 三个抽象操作，算法在后端 -早期草案将完整算法（保留遍历、token 求和、文本提取）作为接口上的具体方法。这会将契约重新耦合到一种策略：想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将两个核心方法都设为抽象，把所有*怎么做*的决策放在后端，并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子；单例服务使多个消费方能够共享逐会话的回放折叠。 +早期草案将完整算法（保留遍历、token 求和、文本提取）作为接口上的具体方法。这会将契约重新耦合到一种策略：想要不同保留策略或事件排序的后端必须与继承来的具体代码对抗。将三个操作都设为抽象，把所有*怎么做*的决策放在后端，并让接口保持为*做什么*的声明。token 测量根本不是压缩钩子；单例服务使多个消费方能够共享逐会话的回放折叠。 -`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求；没有 header 就不执行工作，任何已路由的提供方/模型目标都使用单例估算器。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份，并为手动调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标，并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀，并将压缩指令追加为尾部 user 消息，从而复用提供方的热 KV cache；见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`；适配器可以将此用途映射为对模型隐藏的传输元数据，DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。 +`compactIfNeeded(agent, trigger, signal)` 接受显式的 `'pressure' | 'context-overflow'` 触发原因与取消信号。它只读取最新的持久化已路由请求；没有 header 就不执行工作，任何已路由的提供方/模型目标都使用单例估算器。`compactNow(agent, signal)` 会预留空闲轮次接纳，即使未达到压力也进行一次有效的平衡缩减；不存在这种范围时返回 `null`，且不写入任何内容。`compactRegion(start, end, agent, signal?)` 将 `agent.session` 作为唯一会话身份，并为显式调用方保留可选 signal。默认摘要器依次从显式配置、最新记录的已路由目标和 agent 选项解析目标，并在任何 `llm/stream` 路由后记录提供方/模型对。它回放已路由请求的前缀，并将压缩指令追加为尾部 user 消息，从而复用提供方的热 KV cache；见[摘要前缀缓存 Agent Note](../bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md)。该调用将提供方无关的 `GenerateOptions.purpose` 设为 `compaction`；适配器可以将此用途映射为对模型隐藏的传输元数据，DeepSeek 适配器会发送 `x-deepseek-harness-compact: 1`。 ### 成功的持久步骤工作完成后运行自动压力检查 @@ -91,42 +91,44 @@ compact/end → log-only. Releases the lock (carries `error` on a recoverab ### 通过日志记录的锁实现阻塞，加上崩溃/可恢复失败的分类 -`compact/start … compact/end` 括号的存在理由，按当前实际承担的职责排序： +`compact/start … compact/end` 标记对承担两项职责： 1. **可检测的崩溃孤儿 + 来源追溯**（首要）。摘要生成是一次慢速模型调用，持久化在 `compact/start` *之后*。摘要生成中途崩溃会留下一个没有匹配 `compact/end` 的 `compact/start`——一个可检测的孤儿。最后释放锁（而非最先）将崩溃窗口从*静默损坏*转变为可检测的孤儿。 -2. **防止并发压缩。** 如果当前轮次持有未匹配的 `compact/start`，`compactRegion` 拒绝启动。（循环在任一 awaited 自动 seam 上都是单线程的，因此这也是重入绊线——抛出「already in progress」表示真正的 bug。） +2. **防止并发压缩。** 每个自动、手动和显式范围入口点都会拒绝活动的未匹配 `compact/start`。该标记对就是唯一的锁；没有进程本地 mutex 重复承担同一职责。 -该锁只排除另一项压缩，不排除无关的仅日志事实。基础后端会在 `compact/start` 之后对 token meter 的 surface 节点取快照，并在异步摘要后再次比较；任何 surface 变更都会使替换前的检查失败，而标题或其他仅日志追加不会使已选范围失效。 +该锁只排除另一项压缩，不排除无关事实。其标记是时间点，而不是排他的容器，因此空闲注入的上下文可以出现在独立手动 start 与 end 之间。自动工作要求其轮次内的整个 surface 保持稳定。手动工作只重新验证所选位置 span，使其外部的仅追加上下文在替换后保持可见。 -两种失败路径，均有文档记录： +生命周期边界使崩溃状态含义明确： -- **崩溃**（循环在摘要生成中途死亡）：悬空的 `compact/start`，无关闭事件。由于 `compact/*` 是**仅日志**事件，孤儿是**惰性的**，不会落地摘要替换。派生 surface 保持为 `compact/start` 时已经持久化的 surface：如果修剪未产生替换，就是完整历史；如果已经修剪，就是已修剪历史。通用轮次修复（`interruptedTurnClosers`）用合成的 `turn/end` 关闭轮次；孤儿位于该 `turn/end` *之前*，因此轮次范围内的进行中检查永远看不到它，崩溃不会卡住未来的压缩。 -- **可恢复**（摘要生成抛出异常但循环存活）：后端追加设置了 **`error`** 字段的 `compact/end`，但不落地摘要替换。步骤后压力处理发出警告，并从最新的持久 surface 继续：如果尝试前没有替换，就是完整历史；如果修剪已经落地，就是已修剪 surface。溢出恢复只会在没有任何替换前委托；先前修剪带来的 generation 进展允许从该持久 surface 重试，除非取消或资源释放胜出。 +- **当前生命周期：** 最新 `session/end-seed` 之后悬空的 `compact/start` 是活动的持久锁，并报告 busy。 +- **后续生命周期：** 构造函数写入的较新 `session/end-seed` 证明更早的未匹配 start 已陈旧，因此恢复、fork 和接手不会被已死的写入方持续卡住。 +- **可恢复失败：** start 落地后，后端会恰好尝试一次 `compact/end { error }`。摘要或稳定性失败会保持会话 surface 不变，同时在日志中保留失败尝试。如果追加闭合事件失败，未匹配 start 会继续有意阻塞。 `compact/end` 保留其 `error?` 字段（与 `tool/result` 的自包含错误一致——一个事件即可区分成功与失败，无需关联兄弟事件）。没有单独的 `compact/error` 事件。 -**核心会话修复保持对压缩无感知——这是有意为之。** `interruptedTurnClosers` 从不被教导 `compact/*`。如果教导它，每个未来的 `xxx/start … xxx/end` 插件对都必须修补核心模块——这恰好是能力 seam 架构存在的意义所要避免的耦合。由于仅日志的孤儿是惰性的，不需要特殊修复：通用轮次修复加上未落地 surface 变更的惰性就足够了。 +**核心会话修复保持对压缩无感知——这是有意为之。** `interruptedTurnClosers` 从不被教导 `compact/*`。通用 `session/end-seed` 生命周期边界提供压缩所有方所需的证据；压缩不变量与后端负责解释它，无需向核心添加插件专属修复。 ## 曾考虑的替代方案 -- **完整算法作为接口的具体方法**——否决，因为它将契约重新耦合到一种保留策略。两个核心方法都是抽象的；可复用测量属于单独的 LLM 系列服务，`summarize()` 是 basic 唯一的钩子。 +- **完整算法作为接口的具体方法**——否决，因为它将契约重新耦合到一种保留策略。三个操作都是抽象的；可复用测量属于单独的 LLM 系列服务，`summarize()` 是 basic 唯一的钩子。 - **在 `agent/request` 或临时 `agent/pre-step` 输入上执行压缩**——否决，因为两者都无法证明最终的持久请求，而且都会将通用生命周期耦合到压缩专属的信封数据。步骤后回放与规范溢出恢复同时覆盖成功和被拒绝的调用。 - **`compact` 布尔值或无类型的请求元数据 map**——否决，因为多个辅助调用种类会变成互斥标志，而开放 map 会丢弃由编译器检查的词汇。一个类型化的 `purpose` 判别字段可以扩展其他调用种类，而无需再为 `GenerateOptions` 添加字段。 - **单独的 `compact/error` 事件**——否决：`compact/end` 保留 `error?` 字段，与 `tool/result` 的自包含错误一致——一个事件即可区分成功与失败，无需关联兄弟事件。 -- **教导核心轮次修复识别 `compact/*`**——否决：仅日志的孤儿是惰性的，为每个未来的 `xxx/start … xxx/end` 插件对修补核心模块恰好是能力 seam 架构存在的意义所要避免的耦合。 +- **教导核心轮次修复识别 `compact/*`**——否决：通用 end-seed 边界已经能够区分先前生命周期的历史；为每个未来的 `xxx/start … xxx/end` 插件对修补核心模块，恰好是能力 seam 架构存在的意义所要避免的耦合。 ## 后果 -- **包**：`packages/compact/compact` 提供接口，`compact-basic` 提供后端，`compact-tool-result-prune` 提供可选的确定性重写。`packages/llm/token-meter` 独立拥有回放感知的测量。消费方层推迟。 +- **包**：`packages/compact/compact` 提供接口，`compact-basic` 提供后端，`compact-tool-result-prune` 提供可选的确定性重写，`command-compact` 提供面向用户的 `/compact`。`packages/llm/token-meter` 独立拥有回放感知的测量。 - **自动 seam**：`agent/post-step`（`@mode serial`）处理成功调用的压力，`agent/request-error`（`@mode waterfall`）处理失败步骤关闭后的最终请求失败。通用 `agent/pre-step` 保持为四参数检查点，不携带压缩专属的提示词/前缀 payload。 - **`SessionEventMap`** 通过可合并扩展的声明合并获得 `compact/start` / `compact/summary` / `compact/end`；`SurfaceEventType` **未被**触及。这些是会话事件，不是 cordis `Events`，因此事件分类门禁无需新增条目。 - **`dsh-compact`** 拥有 `COMPACT_CHECKPOINT_SOURCE`、`isCompactCheckpointSource(source)`、`toolPairingBalancedBefore(session, seq)` 与 `toolPairingBalancedAfter(session, seq)`。该标记用于跨后端实现识别替换摘要。带缓存的 surface 边缘检查会防止 `compactRegion` 和 `compactIfNeeded` 拆分工具调用/结果对，按 seq 校验当前成员关系，从每个切割点的一条平衡序列回答两侧边缘，并拒绝陈旧或缺失的 seq 与孤立结果。 -- **`dsh-session`** 通过唯一的 surface 管理器校验位置替换、完整溯源信息和仅内容的单节点 `tool/result` 重写。其不变式配套插件将新追加的工具结果视为执行，要求存在已打开的步骤与待处理调用；已校验的替换仍是位于轮次内的重写。 -- **接线**：`examples/tui-agent/cordis.yml` 依次加载零配置的 `dsh-token-meter`、`dsh-compact-tool-result-prune` 和 `dsh-compact-basic`；服务级默认值使组合无需重复数值策略即可使用。 +- **`dsh-session`** 通过唯一的 surface 管理器校验位置替换、完整溯源信息和仅内容的单节点 `tool/result` 重写。其不变式配套插件将新追加的工具结果视为执行，要求存在已打开的步骤与待处理调用，而压缩配套组件拥有数字轮次归属与独立 `null` 归属标记对之间的关系。 +- **接线**：`examples/tui-agent/cordis.yml` 依次加载零配置的 `dsh-token-meter`、`dsh-compact-tool-result-prune`、`dsh-compact-basic`，然后加载 `dsh-command-compact`；服务级默认值使组合无需重复数值策略即可使用。 ## 测试 - **单元测试：** 使用真实 Loader 和 invariant 插件覆盖完整单元保留、修剪配置与回放、富块顺序、元数据保留、收敛、`compact/end` 的两种结果、开放尾部拒绝、仅修剪与带摘要的溢出恢复、generation 证明、上限和原始错误保留。 - **循环测试：** 测试固定步骤后处理发生在持久工具结果之后、`step/end` 之前，使用实际 `agent/request` 路由，关闭失败步骤，分配新的重试编号，并覆盖完整的抛出/带内溢出 → 压缩 → 重建重试组合。 +- **手动测试：** 无需模型密钥即可固定接纳、标记顺序、注入保留、活动／陈旧未匹配标记分类、取消、闭合／flush 失败、命令映射以及排队 TUI 流程。 - **带密钥 e2e：** 真实模型和 bash 会话在降低的限制下触发压缩，记录完整的 `compact/start…end` 对，缩小 surface，并完成任务。 - **快照缺口：** 失控轮次压缩尚无法回放，因为摘要调用未记录 `assistant/chunk` 事件或 `sessionId`；交错摘要调用的回放仍是后续工作。 diff --git a/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.i18n.yaml index 3d1140f5cf..feb73d00dd 100644 --- a/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.i18n.yaml @@ -1,6 +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 -2026-06-21-subagent-capability-seam.md: 9c17a93751de209e5e4e5a0ca7d7b1d8e5656a47 -2026-06-21-subagent-capability-seam.zh.md: 6294c84a8fa11e492316f4b69048aa5f477aa04f +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md +2026-06-21-subagent-capability-seam.md: 043092884731c403a11b71ef8b5a410e9e5af7e0 +2026-06-21-subagent-capability-seam.zh.md: 6a4a5798199ca7d6d7c011668a319d65a0553208 diff --git a/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md index 9c17a93751..0430928847 100644 --- a/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md +++ b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md @@ -38,12 +38,12 @@ A new package group `packages/subagent/`: ### The primitive: async `start → SubagentRun` -A provider exposes `start(request) → Promise`. Fulfillment publishes a ready child and transfers its run handle to the caller. One signal covers cancellation before and after readiness; `dispose()` cancels remaining work and awaits quiescence. A rejected start cleans partial resources and emits no lifecycle event. `start` is transport-neutral; `spawn` names only the fresh in-process backend. +A provider exposes `start(request) → Promise`. Fulfillment publishes a child and transfers its run handle to the caller. Work that fails before publication rejects `start()`, while prompt, turn, cancellation, and infrastructure outcomes after publication settle through `run.result` without hiding the child id. One signal covers cancellation before and after publication; `dispose()` cancels remaining work and awaits quiescence. A rejected start cleans unpublished resources and emits no lifecycle event, while a post-publication result failure closes the published lifecycle pair. `start` is transport-neutral; `spawn` names only the fresh in-process backend. ### Two kinds of optional capability, discovered two ways - **Start-time features** (`outputSchema`, `depthLimit`, `toolFilter`, `persona`) ride on a static `provider.capabilities` descriptor. The service checks every requested one BEFORE delegating and **rejects loud** (`SubagentError('UNSUPPORTED_CAPABILITY')`) if the provider lacks it — never accepted-then-ignored. They must be checked before a run exists, which is why they cannot be runtime methods. -- **Runtime features** (steering via `sendMessage`, follow-up via `resume`) are **optional methods** on `SubagentRun`. The method's presence IS the capability, and TypeScript narrowing is the discovery mechanism: a consumer cannot call an absent method without narrowing first, so there is no silent-degradation path and no separate flags object to keep in sync. +- **Continuable creation** is the optional `SubagentProvider.prepareContinuable` method; presence is the capability and TypeScript narrowing is the discovery mechanism, so no separate flag can drift from the implementation. The continuation manager owns later delivery and cold resume directly through `AgentHandle`, while one-shot `SubagentRun` has no steering or resume operation, as refined by [continuable subagents](2026-07-28-continuable-subagent-conversations.md). ### Fork vs. fresh are separate backends, not a flag @@ -55,7 +55,7 @@ Each subagent runs in its **own `Session`** (own id, `parentSession` lineage), p ### Synchronous collect (first cut) -`dsh-tool-subagent` passes its execution signal to `start()`, awaits the child result, and disposes the run in `finally`. Non-completed outcomes become error results rather than successful partial output. This foreground consumer does not use the run's optional steering method. +`dsh-tool-subagent` passes its execution signal to `start()`, awaits the child result, and disposes the run before reporting. Non-completed outcomes become error results rather than successful partial output, and independent result and disposal rejections retain both diagnostics. ### Provider selection is config, not model-facing diff --git a/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.zh.md b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.zh.md index 6294c84a8f..6a4a579819 100644 --- a/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.zh.md +++ b/.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.zh.md @@ -38,12 +38,12 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在 ### 原语：异步 `start → SubagentRun` -提供方暴露 `start(request) → Promise`。完成时发布一个就绪的子 agent 并将其运行句柄转交给调用方。一个信号覆盖就绪前后的取消；`dispose()`（资源释放）取消剩余工作并等待完全停稳。启动失败时清理部分资源，不发出生命周期事件。`start` 与传输方式无关；`spawn` 仅指代全新的进程内后端。 +提供方暴露 `start(request) → Promise`。完成时发布一个子 agent，并将其运行句柄转交给调用方。发布前失败的工作会拒绝 `start()`，而发布后的提示词、轮次、取消与基础设施结果会通过 `run.result` 结算，且不会隐藏 child id。同一个信号覆盖发布前后的取消；`dispose()`（资源释放）取消剩余工作并等待完全停稳。启动被拒绝时会清理未发布资源，且不发出生命周期事件；发布后的结果失败则会结束已经发布的生命周期事件对。`start` 与传输方式无关；`spawn` 仅指代全新的进程内后端。 ### 两类可选能力，两种发现方式 - **启动时功能**（`outputSchema`、`depthLimit`、`toolFilter`、`persona`）挂在静态的 `provider.capabilities` 描述符上。服务在委派之前检查每个被请求的功能，如果提供方不支持则**大声拒绝**（`SubagentError('UNSUPPORTED_CAPABILITY')`），绝不接受后静默忽略。这些功能必须在 run 存在之前检查，因此不能是运行时方法。 -- **运行时功能**（通过 `sendMessage` 进行 steering、通过 `resume` 进行后续对话）是 `SubagentRun` 上的**可选方法**。方法的存在本身即为能力，TypeScript 类型收窄即为发现机制：消费方不经收窄就无法调用不存在的方法，因此不存在静默降级路径，也不需要额外的 flags 对象来保持同步。 +- **可继续创建**使用可选的 `SubagentProvider.prepareContinuable` 方法；方法是否存在本身即为能力，TypeScript 类型收窄即为发现机制，因此不需要可能与实现失同步的独立 flag。继续执行管理器直接通过 `AgentHandle` 负责后续投递与从持久化存储恢复，而一次性 `SubagentRun` 没有 steering 或 resume 操作，具体由[可继续 subagent](2026-07-28-continuable-subagent-conversations.md)细化。 ### Fork 与 fresh 是独立后端，而非一个 flag @@ -55,7 +55,7 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在 ### 同步收集（首版） -`dsh-tool-subagent` 将其执行信号传给 `start()`，等待子 agent 结果，并在 `finally` 中 dispose 该 run。非完成态的结果变为错误结果，而非成功的部分输出。这个前台消费方不使用 run 的可选 steering 方法。 +`dsh-tool-subagent` 将其执行信号传给 `start()`，等待子 agent 结果，并在报告前 dispose 该 run。非完成态的结果变为错误结果，而非成功的部分输出；相互独立的结果与 dispose rejection 会保留两项 diagnostic。 ### 提供方选择是配置，不面向模型 diff --git a/.agents/notes/implemented/feature/2026-07-05-skill-system.i18n.yaml b/.agents/notes/implemented/feature/2026-07-05-skill-system.i18n.yaml index ca5cc25241..70dd43d0f6 100644 --- a/.agents/notes/implemented/feature/2026-07-05-skill-system.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-05-skill-system.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/feature/2026-07-05-skill-system.md -2026-07-05-skill-system.md: 242650ec8ba64fd0801a958711d5790fae07b259 -2026-07-05-skill-system.zh.md: da5f4af4b2f8bc0144be0a7ed608de7edd9a9947 +2026-07-05-skill-system.md: 36a2ae220db24c3183253c18957769ab5d5c068c +2026-07-05-skill-system.zh.md: 3a673d44d74ab38732dd5f5bda4d607b174db251 diff --git a/.agents/notes/implemented/feature/2026-07-05-skill-system.md b/.agents/notes/implemented/feature/2026-07-05-skill-system.md index 242650ec8b..36a2ae220d 100644 --- a/.agents/notes/implemented/feature/2026-07-05-skill-system.md +++ b/.agents/notes/implemented/feature/2026-07-05-skill-system.md @@ -52,4 +52,4 @@ The catalog is deterministic for a fixed root set and runtime registration revis ## Deferred -Forked skill contexts (`context: fork`), parameter declarations and hints (`arguments` and `argument-hint`), and per-skill tool constraints (`allowed-tools` and `disallowed-tools`) are outside the shipped contract. The registry, local provider, and model-facing tool do not parse, advertise, or enforce these fields. Direct user invocation ships as a TUI affordance over the shared invocation policy and trusted `get()` primitive; see [the TUI skill slash command](2026-07-21-tui-skill-slash-command.md). +Forked skill contexts (`context: fork`), parameter declarations and hints (`arguments` and `argument-hint`), and per-skill tool constraints (`allowed-tools` and `disallowed-tools`) are outside the shipped contract. The registry, local provider, and model-facing tool do not parse, advertise, or enforce these fields. Direct user invocation shipped as a TUI affordance over the shared invocation policy and trusted `get()` primitive; see [the archived TUI skill slash command](../../archived/feature/2026-07-21-tui-skill-slash-command.md). diff --git a/.agents/notes/implemented/feature/2026-07-05-skill-system.zh.md b/.agents/notes/implemented/feature/2026-07-05-skill-system.zh.md index da5f4af4b2..3a673d44d7 100644 --- a/.agents/notes/implemented/feature/2026-07-05-skill-system.zh.md +++ b/.agents/notes/implemented/feature/2026-07-05-skill-system.zh.md @@ -52,4 +52,4 @@ agent-core 主干包含一个目录贡献者、一个本地提供方和一个面 ## 延后 -Fork 的 skill 上下文（`context: fork`）、参数声明与提示（`arguments` 和 `argument-hint`）、以及逐 skill 的工具约束（`allowed-tools` 和 `disallowed-tools`）不在已交付的契约范围内。注册表、本地提供方和面向模型的工具不解析、不广播、也不执行这些字段。直接用户调用作为 TUI 功能交付，基于共享调用策略和受信的 `get()` 原语；见 [TUI skill 斜杠命令](2026-07-21-tui-skill-slash-command.md)。 +Fork 的 skill 上下文（`context: fork`）、参数声明与提示（`arguments` 和 `argument-hint`）、以及逐 skill 的工具约束（`allowed-tools` 和 `disallowed-tools`）不在已交付的契约范围内。注册表、本地提供方和面向模型的工具不解析、不广播、也不执行这些字段。直接用户调用曾作为 TUI 功能交付，基于共享调用策略和受信的 `get()` 原语；见[已归档的 TUI skill 斜杠命令](../../archived/feature/2026-07-21-tui-skill-slash-command.md)。 diff --git a/.agents/notes/implemented/feature/2026-07-06-approval-seam.i18n.yaml b/.agents/notes/implemented/feature/2026-07-06-approval-seam.i18n.yaml index 51ddb7e70f..48d53f1896 100644 --- a/.agents/notes/implemented/feature/2026-07-06-approval-seam.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-06-approval-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/feature/2026-07-06-approval-seam.md -2026-07-06-approval-seam.md: efb4159d736779af28edc1ae6091de4669c92f31 -2026-07-06-approval-seam.zh.md: 9a4656f30a43473fe90cde9c56d45f48943e5d10 +2026-07-06-approval-seam.md: ae143a41302b7bcd6029345fa91ca4eda837c141 +2026-07-06-approval-seam.zh.md: a66ce804167fd4de5c8dbe51d70c9b038d1ebb17 diff --git a/.agents/notes/implemented/feature/2026-07-06-approval-seam.md b/.agents/notes/implemented/feature/2026-07-06-approval-seam.md index efb4159d73..ae143a4130 100644 --- a/.agents/notes/implemented/feature/2026-07-06-approval-seam.md +++ b/.agents/notes/implemented/feature/2026-07-06-approval-seam.md @@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou # policy: never # deployment default for sessions without an override; 'ask' when omitted ``` -The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its [automation-only bridge](../simplification/2026-07-23-acp-automation-only-protocol.md) registers an answerer that sends `session/request_permission` to the owning client with the exact tool-call id and one-shot allow/reject options. `policy: never` is the unattended stance — every ask auto-rejects deterministically and is stated in the system prompt. `policy` is validated against the closed list at plugin load; anything else throws. +The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its [automation-only bridge](../simplification/2026-07-23-acp-automation-only-protocol.md) registers an answerer that sends `session/request_permission` to the owning client with the exact tool-call id and one-shot allow/reject options. `policy: never` is the unattended stance — every ask auto-rejects deterministically, and the current value joins the runtime-context snapshot. `policy` is validated against the closed list at plugin load; anything else throws. What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision. @@ -63,7 +63,7 @@ Answerers are `approval/request` waterfall listeners. Zero listeners fall throug #### The per-session policy tier -The seam also owns the session-scoped `'ask' | 'never'` policy described by [the sandbox Agent Note](2026-07-06-sandbox.md). Effective policy is folded from logged switches over the deployment default. `'never'` resolves to `rejected` inside `request()` before any answerer can run; `'ask'` dispatches and otherwise falls through to `unavailable`. The prompt states only deterministic `'never'`, switch narration is coalesced, and every request still records the audit pair. +The seam also owns the session-scoped `'ask' | 'never'` policy described by [the sandbox Agent Note](2026-07-06-sandbox.md). Effective policy is folded from logged switches over the deployment default. `'never'` resolves to `rejected` inside `request()` before any answerer can run; `'ask'` dispatches and otherwise falls through to `unavailable`. Both current values join the atomic runtime-context snapshot before each model request, so a policy switch needs no separate narration; every approval request still records the audit pair. #### The ACP answerer @@ -83,7 +83,7 @@ The answerer routes through the bridge's exact-agent ownership check described b Unit tests pin outcomes, first-wins delegation, containment, cancellation, scoped routing, audit pairing, the unbypassable `'never'` policy, tool deny reasons, and ACP ownership/outcome mapping through a real scripted bridge. -Snapshots record allowed and rejected sandbox escalation through `session/request_permission`, plus the `'never'` prompt and policy-switch notice. Unscripted permission prompts cancel and fail closed. +Snapshots record allowed and rejected sandbox escalation through `session/request_permission`, plus the complete `'ask'` and `'never'` runtime-context contributions. Unscripted permission prompts cancel and fail closed. ## Deferred @@ -124,7 +124,7 @@ Costs and accepted limits: - **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two. - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant. - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. A `'never'` parent seeds that override into each in-process child's log ([decision](2026-07-25-subagent-policy-inheritance.md)), so the child is told up front instead of asking into the empty waterfall. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent controller is deferred (§ Deferred). -- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair. +- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the next atomic runtime-context snapshot states the policy; each successful auto-rejection records the audit pair. - **What happens across a hot reload, or when an answerer unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state. - **Where does a client get approval context?** The request carries the exact `callId` and the asker's human-readable `reason`; channel adapters may correlate richer tool-call state without duplicating arguments in the approval seam. diff --git a/.agents/notes/implemented/feature/2026-07-06-approval-seam.zh.md b/.agents/notes/implemented/feature/2026-07-06-approval-seam.zh.md index 9a4656f30a..a66ce80416 100644 --- a/.agents/notes/implemented/feature/2026-07-06-approval-seam.zh.md +++ b/.agents/notes/implemented/feature/2026-07-06-approval-seam.zh.md @@ -25,7 +25,7 @@ Status: implemented # policy: never # deployment default for sessions without an override; 'ask' when omitted ``` -仅有这条条目只提供机制，不提供通道：没有组合应答者时，每次 ask 都解析为 `unavailable`，发起请求的工具调用被拒绝——失败关闭无需配置。组合 ACP 应用（`@deepseek-ai/dsh-acp-demo`，如 [acp-agent 示例的默认树](../../../../examples/acp-agent/README.md)）即可闭环：其[仅面向自动化的桥接层](../simplification/2026-07-23-acp-automation-only-protocol.md)注册一个应答者，向拥有该会话的客户端发送 `session/request_permission`，携带精确的工具调用 id 和一次性 allow/reject 选项。`policy: never` 是无人值守姿态：每次 ask 确定性地自动拒绝，并在系统提示词中声明。`policy` 在插件加载时对照封闭列表校验；非法值直接抛异常。 +仅有这条条目只提供机制，不提供通道：没有组合应答者时，每次 ask 都解析为 `unavailable`，发起请求的工具调用被拒绝——失败关闭无需配置。组合 ACP 应用（`@deepseek-ai/dsh-acp-demo`，如 [acp-agent 示例的默认树](../../../../examples/acp-agent/README.md)）即可闭环：其[仅面向自动化的桥接层](../simplification/2026-07-23-acp-automation-only-protocol.md)注册一个应答者，向拥有该会话的客户端发送 `session/request_permission`，携带精确的工具调用 id 和一次性 allow/reject 选项。`policy: never` 是无人值守姿态：每次 ask 都会被确定性地自动拒绝，当前值也会加入运行时上下文快照。`policy` 在插件加载时对照封闭列表校验；非法值直接抛异常。 组合部署的可观测行为：`allowed-once` 仅允许该次调用继续；拒绝、关闭和通道缺失以三种不同原因拒绝，模型可以区分；轮次内成功的请求会在发起请求的 agent 的会话日志上落一对持久的 `approval/asked`/`approval/decided` 事件；授权不会在发起请求的调用结束后继续存在。空闲时的请求或审计追加失败会拒绝，而不会返回未经审计的决策。 @@ -63,7 +63,7 @@ tool/result "escalated" — this one call ran under the wider mode; the gra #### 每会话策略层 -seam 还拥有[沙箱 Agent Note](2026-07-06-sandbox.md) 所描述的会话级 `'ask' | 'never'` 策略。生效策略由日志中记录的切换在部署默认值之上折叠而成。`'never'` 会在任何应答者运行之前，于 `request()` 内部解析为 `rejected`；`'ask'` 则派发请求，否则一路委派至 `unavailable`。提示词仅声明确定性的 `'never'`，切换叙述会被合并，每个请求仍记录审计对。 +seam 还拥有[沙箱 Agent Note](2026-07-06-sandbox.md) 所描述的会话级 `'ask' | 'never'` 策略。生效策略由日志中记录的切换在部署默认值之上折叠而成。`'never'` 会在任何应答者运行之前，于 `request()` 内部解析为 `rejected`；`'ask'` 则派发请求，否则一路委派至 `unavailable`。两个当前值都会在每次模型请求前加入原子化的运行时上下文快照，因此策略切换无需单独叙述；每次批准请求仍会记录审计对。 #### ACP 应答者 @@ -83,7 +83,7 @@ ACP 桥只应答其会话映射所拥有的精确 agent 对象。它携带既有 单元测试固定结果、先到先得的委派、错误容纳、取消、作用域路由、审计配对、不可绕过的 `'never'` 策略、工具拒绝原因，以及通过真实脚本化桥实现的 ACP 归属/结果映射。 -快照记录通过 `session/request_permission` 批准和拒绝沙箱升级，以及 `'never'` 提示词与策略切换通知。没有脚本化应答的权限提示会取消并失败关闭。 +快照记录通过 `session/request_permission` 批准和拒绝沙箱升级，以及完整的 `'ask'` 与 `'never'` 运行时上下文贡献。没有脚本化应答的权限提示会取消并失败关闭。 ## 延后 @@ -124,7 +124,7 @@ ACP 桥只应答其会话映射所拥有的精确 agent 对象。它携带既有 - **用户关闭提示或轮次在 ask 进行中中止时会发生什么？** 关闭映射为 `cancelled` 并携带自己的拒绝文本。已中止的 signal 直接结算为 `cancelled` 而不派发；ask 进行中的中止丢弃迟到的应答。当两个审计追加都提交时，任一路径都记录恰好一对事件，绝不会两对。 - **如果客户端以 harness 从未提供的选项应答呢？** 除已提供的 `allow_once` 之外的任何选项都映射为 `rejected`——来自不合规客户端的未知 optionId 永远不能授权。 - **subagent 的审批如何路由？** 没有应答者拥有的 agent 穿过整个 waterfall 委派并失败关闭——进程内 subagent 被刻意设计为不可应答。`'never'` 父级会把该覆盖项预置到每个进程内子 agent 的日志中（[决策](2026-07-25-subagent-policy-inheritance.md)），因此子 agent 一开始就会得知，而不是向空的 waterfall 发出 ask。`subagent-acp` 的子侧自动应答是独立的；将子 agent 的 ask 路由到父控制器已延后（§ 延后）。 -- **`policy: 'never'` 在运行时实际改变了什么？** 服务在派发任何应答者之前，将该会话的每次 ask 解析为 `rejected`（在服务内部，因此没有注册顺序能绕过它）；系统提示词声明该策略；切换在边界处被叙述；每次成功的自动拒绝都会记录审计对。 +- **`policy: 'never'` 在运行时实际改变了什么？** 服务在派发任何应答者之前，将该会话的每次 ask 解析为 `rejected`（在服务内部，因此没有注册顺序能绕过它）；下一份原子化的运行时上下文快照会声明该策略；每次成功的自动拒绝都会记录审计对。 - **热重载或应答者在会话中途卸载时会发生什么？** 应答者随其拥有的 fiber 一起 dispose，因此下一次 ask 降级为 `unavailable` 而非挂在死通道上；重新挂载会重新注册应答者，无需追赶状态。 - **客户端从哪里获得审批上下文？** 请求携带精确的 `callId` 和发起方的人类可读 `reason`；通道适配器可自行关联更丰富的工具调用状态，而无需在审批 seam 中重复携带参数。 diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml b/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml index 9311c6cac7..d5727d9c4b 100644 --- a/.agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.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/feature/2026-07-06-sandbox.md -2026-07-06-sandbox.md: 42b78ad8341dd52c4dd146a2207a5ae909d28f1e -2026-07-06-sandbox.zh.md: dfa3349e4d74d6f2c4944414c25fe3726d4a9b5a +2026-07-06-sandbox.md: 4355ab57374f77f1733fff39e2fb4ccadcedaf6b +2026-07-06-sandbox.zh.md: 02c5337555b7466c2bac7fc4774cdd2c945178ae diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.md b/.agents/notes/implemented/feature/2026-07-06-sandbox.md index 42b78ad834..4355ab5737 100644 --- a/.agents/notes/implemented/feature/2026-07-06-sandbox.md +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.md @@ -40,7 +40,7 @@ The swap is invisible to every consumer of `ctx.bash`: the bash tools, hook comm Misconfiguration fails loud: `mode` outside the closed vocabulary is rejected at plugin load, and a host with no usable backend throws the structured `SANDBOX_UNAVAILABLE` — at `confine()` before the command ever spawns — rather than degrading to unconfined execution. `runnerCommand` on `dsh-sandbox-local` is the operator's explicit assertion of a bwrap-compatible runner (chain and probes skipped); it doubles as the deterministic fake-runner seam for keyless tests. -Denied file effects return a `[sandbox: file access denied under mode]` marker and instructions not to work around the denial. A confining executor adds paired `sandbox_permissions` and `justification` fields for one approved retry that must be strictly wider than the session's effective mode. A grant widens only that retry; rejection executes nothing, returns `the user rejected escalating this command to ""`, and permits no re-ask. The prompt does not announce sandbox mode, avoiding preemptive refusal. When `dsh-permission` is composed with a UI adapter, one preset selects both knob values; unmatched values fold to `custom`. The [ACP automation composition](../../../../examples/acp-agent/README.md) does not mount that UI service and selects its deployment mode explicitly. +Denied file effects return a `[sandbox: file access denied under mode]` marker and instructions not to work around the denial. A confining executor adds paired `sandbox_permissions` and `justification` fields for one approved retry that must be strictly wider than the session's effective mode. A grant widens only that retry; rejection executes nothing, returns `the user rejected escalating this command to ""`, and permits no re-ask. The owner-derived runtime context states the current file policy without replacing those enforcement boundaries. When `dsh-permission` is composed with a UI adapter, one preset selects both knob values; unmatched values fold to `custom`. The [ACP automation composition](../../../../examples/acp-agent/README.md) does not mount that UI service and selects its deployment mode explicitly. ### Design detail @@ -72,7 +72,7 @@ Backend profiles share the mode contract but differ in necessary host grants. La `dsh-bash-sandbox` extends `LocalBashExecutor` and hands `ctx.sandbox` the exact `['bash', '-c', command]` argv it is about to spawn. A denial is an orthogonal result fact, conservatively classified from the active runner's stderr dialect. A runner failure outranks denial: foreground execution throws `SANDBOX_UNAVAILABLE`; a settled `BashProcess` stamps `sandbox.runnerFailed`, and the bash producer renders it through generic `task_output`. -The model's view is result facts only: the static tool description explains the denial marker (`[sandbox: file access denied under mode]`), encourages attempting commands that may be denied, and forbids retrying around a denial; when the escalation fields are advertised, a denied result additionally carries the escalation hint itself, so the sanctioned same-turn retry is prompted at the decision point rather than depending on the model recalling the description (§ Escalation). No prompt section states the sandbox mode (§ Per-session modes). +The model sees the current effective file policy in the owner-derived `sandbox:policy` runtime context, while the static tool description explains the denial marker (`[sandbox: file access denied under mode]`), encourages attempting commands that may be denied, and forbids retrying around a denial; when the escalation fields are advertised, a denied result additionally carries the escalation hint itself, so the sanctioned same-turn retry is prompted at the decision point rather than depending on the model recalling the description (§ Escalation). [The current-policy decision](2026-07-30-current-sandbox-policy-context.md) owns the context's rationale and boundaries. #### Escalation: one approved wider retry after a denial @@ -105,7 +105,7 @@ interface SessionEventMap { Each owner exports the same three-piece kit: the event declaration, a pure fold (`effectiveSandboxMode(events)` / `effectiveApprovalPolicy(events)` — a `findLast`, typed to the domain's closed union), and THE write path (`setSandboxMode(session, mode)` / `setApprovalPolicy(session, policy)` — a switch IS its event; nothing mutates state out of band). No shared owner service, no generic facts map, no registry: a third knob copies the ~40-line pattern into its own package. Execution follows the fold on both sides — the bash tool's per-call stamp reads it as the middle rung of the § Escalation precedence chain, and the approval seam's `'never'` gate is [the approval Agent Note](2026-07-06-approval-seam.md)'s side of the same pattern. -Sandbox mode is not narrated in the prompt; denial results report the mode when it matters, avoiding preemptive refusal based on a standing label. Approval policy is different: only `'never'` is stated because automatic rejection otherwise looks like a user decision. Policy-change notices are coalesced and delivered by the next pre-step, with log-derived fallback after restart. The notice source is inferred from event position: a knob event after the last request header is user-driven; unlogged drift is operator or config driven. +Sandbox and approval policy are rendered as ordered contributions to one runtime-context snapshot before every request. The loop records the complete snapshot as a sourced `user/message`; both `'ask'` and `'never'` are explicit, so neither owner needs switch narration or last-told state. **The optional UI surface** is `PermissionService`: a deployment-defined preset table whose entries bundle one sandbox mode with one approval policy. The shipped `workspace-write` and `danger-full-access` presets write through to both domain setters; a knob combination outside the table is reported as `custom`. UI adapters may expose that table as a selector. The automation-only ACP transport advertises no configuration selector and mounts no permission-preset service. @@ -117,10 +117,10 @@ fs/web/todo execute in-process, so their sandbox semantics are policy at their s ### Testing -- **Unit:** pin platform selection and profiles, fail-closed runner classification, per-call mode/root resolution, per-process facts, escalation validation and outcomes, permission preset folding and write-through, and narrator coalescing. +- **Unit:** pin platform selection and profiles, fail-closed runner classification, per-call mode/root resolution, per-process facts, escalation validation and outcomes, permission preset folding and write-through, and runtime-context ordering and materialization. - **Keyless real-runner:** exercise bwrap, Landlock, and Seatbelt against real filesystem effects at provider and bash-consumer layers; one real Cordis context concurrently drives two project sessions through shipped bash and fs tools, proving own-root success and sibling-root denial. Packed-install coverage proves the registry launcher remains executable. CI rejects a silent all-skip. - **With-key:** start the real ACP composition in read-only mode, let a model-driven bash write hit the runner's denial marker, then drive the bridge answerer and disk effect through granted and rejected workspace-write retries; unavailable credentials or runners self-skip. -- **Snapshot:** pin prompt deltas and notices plus both scripted approval branches. A real ACP example scenario places its session under the user home while the deployment fallback points at `/tmp`, then pins a successful deployment-selected workspace-write mutation; this distinguishes session-root resolution from the process fallback without depending on runner-specific denial text. Other snapshots start unconfined so unrelated fixtures remain platform-independent. +- **Snapshot:** pin the atomic current-policy context and both scripted approval branches. A real ACP example scenario places its session under the user home while the deployment fallback points at `/tmp`, then pins both the workspace-write runtime-context message and a successful deployment-selected mutation; this distinguishes session-root resolution from the process fallback without depending on runner-specific denial text. Other snapshots start unconfined so unrelated fixtures remain platform-independent. ## Deferred phases @@ -149,9 +149,9 @@ Each phase gets its full design when picked up, validated against the code at th - **Per-session dynamic tool schemas** — rejected: schemas are registry-global by design (one assembly vocabulary, the pinned-header snapshot contract), and re-registering per session would buy only what the execution-time strict-wider check already guarantees, at the cost of a per-session schema surface and header churn on every switch. - **Hard-match the retry to a prior denial** — rejected: command-string identity is fragile (quoting, `workdir`, env prefixes, a pipeline retried as its failing stage) — false-rejects honest retries or is trivially satisfied; the real boundary is the human seeing command + justification. Revisit only if `allow_always` grant storage ever needs machine-checkable scopes. - **A generic `env/state` facts map with an owner service** — rejected: approval and sandbox compose independently, so neither's state may drag in a third package; single-key folds are one `findLast` each, dissolving the owner service; no invariant spans the knobs, so atomic multi-key patches bought nothing. -- **Narrate via `agent/user-message` + a bus event** — rejected: it presupposes a turn-entry seam that does not exist (the real seam is `agent/prompt-submit`), and pre-step's position serves both the coalesced turn-entry notice and the mid-turn immediacy bound with one listener. -- **A standing prompt statement of the sandbox mode (+ a switch narrator)** — shipped first, then removed on live evidence: with `Bash commands run under the "read-only" file sandbox.` in every request, the model refused to ATTEMPT denied-then-escalatable work (five of twelve turns in the first manual session ended with zero tool calls), turning the sandbox into a soft lockout. The denial marker names the mode at the moment it matters and the escalation fields carry the recovery; the approval knob keeps its statement because an auto-rejection is behaviorally indistinguishable from a human "no". -- **Track "last told" with its own bookkeeping events** — rejected: the `request/header` fold already records the exact prompt the model saw; parsing the closed candidate sentences back replaces a second bookkeeping stream — events are needed only where they ARE the store. +- **Narrate each switch through `agent.inject()` plus a bus event** — rejected: independent notices expose owner ordering and intermediate combinations, while one assembly pass can materialize the complete current state atomically at the request boundary. +- **State sandbox mode in the stable system prompt** — shipped first, then removed on live evidence: with `Bash commands run under the "read-only" file sandbox.` in every request, the model refused to ATTEMPT denied-then-escalatable work (five of twelve turns in the first manual session ended with zero tool calls), turning the sandbox into a soft lockout. The denial marker names the mode at the moment it matters and the escalation fields carry the recovery. The absence decision is superseded by [the current-policy decision](2026-07-30-current-sandbox-policy-context.md); this measurement and causal observation remain the evidence that any replacement must counter-test. +- **Track "last told" with its own bookkeeping events** — rejected: the latest sourced runtime-context `user/message` records the exact full snapshot the model saw. Materializing that snapshot from current owner contributions replaces a second bookkeeping stream — events are needed only where they ARE the store. - **Independent sandbox and approval selectors** — rejected: one deployment-defined permission preset keeps the two policy knobs coherent for UI clients that expose runtime switching. ## Consequences @@ -160,12 +160,12 @@ What shipped pins — the tiers in Testing hold each: - A denied command retried with `sandbox_permissions` + `justification` prompts the user through the composed answerer chain; a grant runs THAT call under the wider mode (result facts say so) while every other call keeps its own effective mode; every non-grant outcome produces its distinct error text and executes nothing. - The escalation fields exist exactly when the mounted executor confines; a request that is not strictly wider than the call's effective mode fails closed with its own text and prompts no one; a deployment with no ApprovalService fails escalating calls closed and leaves plain calls untouched. -- The system prompt never states the sandbox mode (an approval `'never'` policy is the one stated knob), and the whole exchange — headers, knob events, notices, approvals, results — reconstructs from the session log alone, with no event types beyond the two knob events. -- One preset selection records only changed knob values, while a no-op selection records nothing; an approval-policy switch is narrated in at most one coalesced notice, and a committed sandbox switch is honored by the next call's stamp. -- A resumed session's overrides apply with no catch-up state; a default changed while the process was down is narrated before the session's first new request, attributed to the operator. +- One sourced runtime-context message states the complete current sandbox and approval policies atomically; the whole exchange — context snapshots, headers, knob events, approval notices, approvals, and results — reconstructs from the session log alone, with no policy bookkeeping events beyond the two knob events. +- One preset selection records only changed knob values, while a no-op selection records nothing; the next request snapshots both current values atomically, and a committed sandbox switch is honored by the next call's stamp. +- A resumed session's overrides enter its first new runtime-context snapshot with no catch-up state; a composition default changed while the process was down likewise appears in that snapshot. - Two concurrent sessions never see each other's state or notices. - Two concurrent project sessions in one Cordis context resolve independent workspace roots; bash and fs writes succeed inside the calling session's cwd and fail against its neighbor's cwd. -- `agent-loop` is untouched — everything rides `systemPrompt.section`, `SessionEventMap` merging, `agent.inject()`, `agent/step`, `agent/prompt-submit`, and capability-owned policy resolution. +- Policy ownership stays in plugins through `systemPrompt.context`, `SessionEventMap` merging, and capability-owned resolution; the generic loop change materializes every owner's ordered context as one sourced message. Costs and accepted limits: @@ -178,9 +178,8 @@ Costs and accepted limits: - **The model may over-ask.** Escalating without denial grounding, or picking `danger-full-access` where `workspace-write` suffices: the description steers and the enum forces the ladder, but the human prompt is the actual gate; the `approval/asked` reasons make over-asking auditable, and a `prepend` policy answerer can auto-reject patterns a deployment never wants. - **The advertised target set is static while the effective mode is per-session** (schemas are registry-global) — a session already at the widest mode is still offered the fields. Harmless by construction: the strict-wider check at execution, not the enum, is the safety boundary — a non-widening request fails with its own text and never prompts anyone. - **A granted escalation is not a working sandbox.** An unavailable backend still fails closed even for a granted escalation to a confining mode — at `confine()` when the platform has no chain or every probe fails, at execution when an unprobed sole runner refuses (classified as a sandbox failure, not a command failure) — while a granted `danger-full-access` run never touches the provider at all: there the grant, not the probe, is the authority. -- **The approval narrator's restart baseline parses prompt prose.** The closed candidate sentence is owned by the writing module itself, so a wording change is a coordinated writer+parser edit in one file; a session whose headers predate the section silently adopts the current policy without a notice. -- **The approval section is still a dynamic prompt surface** (a `'never'` switch breaks provider prompt-prefix caching for that session). Accepted: policy switches are rare, and a model acting on a stale `'never'` is worse. The sandbox knob no longer touches the prompt at all. -- **The model may hold a stale belief about the sandbox mode** (nothing announces a switch). Accepted deliberately: the next attempt's marker or success corrects it, and the observed failure mode of announcing — preemptive refusal — is worse than one wasted retry. +- **Runtime-context history is append-only.** A policy switch appends a complete superseding snapshot after retained history, preserving the stable system-and-conversation prefix; unchanged state adds no message. +- **Older policy snapshots remain in history.** Each full snapshot explicitly supersedes earlier runtime-context snapshots, so replay and compaction need only retain the latest materialized message. ## FAQ @@ -191,8 +190,8 @@ Costs and accepted limits: - **Does the sandbox restrict network or process visibility?** No — `SandboxMode` claims FILE effects only; the bwrap profile deliberately does not unshare pid, and no backend claims network. Whether network restriction becomes its own knob is left open in § The seam. - **Which tools actually run confined?** OS subprocesses through `ctx.bash` — the bash tools, and hook commands transitively — plus the filesystem tools (`read`/`write`/`edit`) through the sandboxed `ctx.fs` provider (the [cross-family fs sandbox RFC](2026-07-14-cross-family-fs-sandbox.md)): bash confines via the OS runner, fs via an in-process path fence, both keying off the same `ctx.sandboxPolicy` mode. web/todo stay in-process and unfenced (web's only effect is network, outside the file-effect mode vocabulary). - **Does a granted escalation persist?** No. The grant is consumed by the exact foreground or background call that asked; every neighboring call keeps its own effective mode. A later background denial surfaces through `task_output` and may ground a new exact-command retry. -- **When does a runtime mode switch take effect?** Once its session event commits, the very next capability resolution folds and stamps the new mode. The model is not told a standing mode; its next command simply behaves under the new policy, and any denial names that policy at the point of use. -- **What survives a restart — and what if the operator changed the config default while the process was down?** Overrides replay from the session log (`effective = fold ?? config`), so a resumed session keeps its modes with zero catch-up machinery; a default that drifted offline changes behavior the same way a switch does (the approval policy, being stated, is additionally narrated with operator/config attribution). +- **When does a runtime mode switch take effect?** Once its session event commits, the next runtime-context snapshot and the next capability resolution fold the new mode. The sourced context message records what the model was told, and any later denial names the same policy at the point of use. +- **What survives a restart — and what if the operator changed the config default while the process was down?** Overrides replay from the session log (`effective = fold ?? config`), so a resumed session keeps its modes with zero catch-up machinery; a default that drifted offline enters the next full runtime-context snapshot. - **What does `enforcement: 'partial'` on a result mean?** The selected backend enforces the subset its kernel ABI governs — e.g. Landlock before ABI v3 does not govern path truncate — and says so structurally instead of refusing the host; the probe's report line distinguishes the cases. The bwrap and Seatbelt profiles govern every promised file effect by construction, so they always report `full`. ## Prior art diff --git a/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md b/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md index dfa3349e4d..02c5337555 100644 --- a/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md +++ b/.agents/notes/implemented/feature/2026-07-06-sandbox.zh.md @@ -40,7 +40,7 @@ harness 是一个 SDK，因此约束必须是开发者可组合的能力：是 配置错误大声失败：`mode` 不在封闭词汇中时在插件加载时被拒绝；主机上没有可用后端时在 `confine()` 阶段（命令 spawn 之前）抛出结构化的 `SANDBOX_UNAVAILABLE`，而非降级为无约束执行。`dsh-sandbox-local` 上的 `runnerCommand` 是运维人员对一个 bwrap 兼容 runner 的显式断言（跳过链和探测）；它同时充当 keyless 测试的确定性 fake-runner seam。 -被拒绝的文件操作返回 `[sandbox: file access denied under mode]` 标记，并附带不要绕过拒绝的指令。约束执行器添加配对的 `sandbox_permissions` 和 `justification` 字段，用于一次经批准的重试，该重试必须严格宽于会话的有效模式。授权仅放宽该次重试；拒绝则不执行任何内容，返回 `the user rejected escalating this command to ""`，且不允许再次请求。提示词不声明沙箱模式，以避免基于常驻标签的预防性拒绝。当 `dsh-permission` 与某个 UI 适配器一起组合时，一个 preset 同时选定两个旋钮值；不匹配的组合折叠为 `custom`。[ACP 自动化组合](../../../../examples/acp-agent/README.md)不挂载该 UI 服务，而是显式选定其部署模式。 +被拒绝的文件操作返回 `[sandbox: file access denied under mode]` 标记，并附带不要绕过拒绝的指令。约束执行器添加配对的 `sandbox_permissions` 和 `justification` 字段，用于一次经批准的重试，该重试必须严格宽于会话的有效模式。授权仅放宽该次重试；拒绝则不执行任何内容，返回 `the user rejected escalating this command to ""`，且不允许再次请求。由归属方派生的运行时上下文会说明当前文件策略，但不会取代这些强制执行边界。当 `dsh-permission` 与某个 UI 适配器一起组合时，一个 preset 同时选定两个旋钮值；不匹配的组合折叠为 `custom`。[ACP 自动化组合](../../../../examples/acp-agent/README.md)不挂载该 UI 服务，而是显式选定其部署模式。 ### 设计细节 @@ -72,7 +72,7 @@ Landlock launcher 源码和包工作区位于 `native/landlock-run`，与 harnes `dsh-bash-sandbox` 扩展 `LocalBashExecutor`，并把即将 spawn 的确切 `['bash', '-c', command]` argv 交给 `ctx.sandbox`。拒绝是与其他结果正交的事实，依据当前 runner 的 stderr 方言保守分类。Runner 失败优先于拒绝：前台执行抛出 `SANDBOX_UNAVAILABLE`；结算后的 `BashProcess` 会盖章 `sandbox.runnerFailed`，bash 生产者再通过通用 `task_output` 渲染它。 -模型看到的仅是结果事实：静态工具描述解释拒绝标记（`[sandbox: file access denied under mode]`），鼓励尝试可能被拒绝的命令，并禁止绕过拒绝重试；当升级字段被公布时，被拒绝的结果还额外携带升级提示本身，使被认可的同轮次重试在决策点被提示，而非依赖模型回忆描述（§ 升级机制）。没有提示词段落声明沙箱模式（§ 按会话模式）。 +模型会在归属方派生的 `sandbox:policy` 运行时上下文中看到当前有效的文件策略；静态工具描述则解释拒绝标记（`[sandbox: file access denied under mode]`），鼓励尝试可能被拒绝的命令，并禁止绕过拒绝重试。当升级字段被公布时，被拒绝的结果还会携带升级提示本身，使被认可的同轮次重试在决策点获得提示，而非依赖模型回忆描述（§ 升级机制）。[当前策略决策](2026-07-30-current-sandbox-policy-context.md)负责该上下文的理由与边界。 #### 升级机制：拒绝后一次经批准的更宽重试 @@ -105,7 +105,7 @@ interface SessionEventMap { 每个拥有者导出相同的三件套：事件声明、纯 fold（`effectiveSandboxMode(events)` / `effectiveApprovalPolicy(events)`——一个 `findLast`，类型化到领域的封闭联合），以及唯一的写入路径（`setSandboxMode(session, mode)` / `setApprovalPolicy(session, policy)`——切换即其事件；没有任何东西在带外修改状态）。无共享拥有者服务、无通用 facts map、无注册表：第三个旋钮只需将约 40 行模式复制到自己的包中。执行在两侧都遵循 fold——bash 工具的按调用盖章将其作为 § 升级机制优先级链的中间层读取，approval seam 的 `'never'` 门控是[批准 Agent Note](2026-07-06-approval-seam.md) 同一模式的另一侧。 -沙箱模式不在提示词中叙述；拒绝结果在需要时报告模式，避免基于常驻标签的预防性拒绝。批准策略不同：只有 `'never'` 被声明，因为自动拒绝在行为上与用户的「不」无法区分。策略变更通知被合并，由下一个步骤前检查点递送，重启后有基于日志的回退。通知来源从事件位置推断：最后一个 request header 之后的旋钮事件是用户驱动的；未记录的漂移是运维人员或配置驱动的。 +沙箱策略与批准策略会在每次请求前渲染为同一份运行时上下文快照中的有序贡献。循环会将完整快照记录为一条带来源的 `user/message`；`'ask'` 与 `'never'` 都会明确写入，因此两个归属方都无需切换叙述或「上次告知」状态。 **可选的 UI 界面**是 `PermissionService`：一张部署定义的 preset 表，每个条目捆绑一个沙箱模式与一个批准策略。随附的 `workspace-write` 和 `danger-full-access` preset 写入两个领域 setter；preset 表之外的旋钮组合报告为 `custom`。UI 适配器可以把该表暴露为选择器。仅面向自动化的 ACP 传输层不公布任何配置选择器，也不挂载权限 preset 服务。 @@ -117,10 +117,10 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层 ### 测试 -- **单元测试：** 固定平台选择和 profile、失败关闭的 runner 分类、按调用的模式/根目录解析、按进程事实、升级验证和结果、权限 preset fold 和写入透传、以及叙述器合并。 +- **单元测试：** 固定平台选择和 profile、失败关闭的 runner 分类、按调用的模式/根目录解析、按进程事实、升级验证和结果、权限 preset fold 和写入透传、以及运行时上下文排序与具体化。 - **Keyless 真实 runner：** 在提供方和 bash 消费方层面对 bwrap、Landlock 和 Seatbelt 执行真实文件系统效果测试；一个真实 Cordis 上下文通过已交付的 bash 和 fs 工具并发驱动两个项目会话，证明在自身根目录写入成功、在兄弟根目录写入被拒绝。Packed-install 覆盖率证明注册表 launcher 保持可执行。CI 拒绝静默全跳过。 - **With-key：** 以只读模式启动真实 ACP 组合，让模型驱动的 bash 写入命中 runner 的拒绝标记，再通过已授权与被拒绝的 workspace-write 重试驱动 bridge 应答器和磁盘效果；不可用的凭证或 runner 自动跳过。 -- **快照：** 固定提示词 delta 和通知，以及两个脚本化的 approval 分支。一个真实 ACP 示例场景把会话放在用户主目录下，同时让部署后备根目录指向 `/tmp`，然后固定一次成功的、由部署选定的 workspace-write 变更；这能区分会话根目录解析与进程后备值，而不依赖 runner 特定的拒绝文本。其他快照以无约束启动，使无关 fixture（测试前置数据）保持平台无关。 +- **快照：** 固定原子化的当前策略上下文和两个脚本化的 approval 分支。一个真实 ACP 示例场景把会话放在用户主目录下，同时让部署后备根目录指向 `/tmp`，然后固定 workspace-write 运行时上下文消息与一次成功的、由部署选定的变更；这能区分会话根目录解析与进程后备值，而不依赖 runner 特定的拒绝文本。其他快照以无约束启动，使无关 fixture（测试前置数据）保持平台无关。 ## 延迟阶段 @@ -149,9 +149,9 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层 - **按会话动态工具 schema**：否决。schema 设计上是注册表全局的（一套 assembly 词汇、固定 header 快照契约），按会话重新注册只能买到执行时严格放宽检查已保证的东西，代价是按会话的 schema 表面和每次切换的 header 变动。 - **将重试硬匹配到先前的拒绝**：否决。命令字符串同一性脆弱（引号、`workdir`、env 前缀、作为失败阶段重试的管道）——要么误拒诚实的重试，要么被轻易满足；真正的边界是人看到命令 + 理由。仅在 `allow_always` 授权存储需要机器可检查的范围时才重新考虑。 - **通用 `env/state` facts map 加拥有者服务**：否决。approval 和沙箱独立组合，因此任何一方的状态都不应拖入第三个包；单键 fold 各自是一个 `findLast`，拥有者服务自然消解；没有跨旋钮的不变式，因此原子多键补丁无收益。 -- **通过 `agent/user-message` + 总线事件叙述**：否决。它预设了一个不存在的轮次入口 seam（真正的 seam 是 `agent/prompt-submit`），而步骤前检查点的位置使一个监听器能够同时服务合并的轮次入口通知和轮中即时性约束。 -- **提示词中常驻声明沙箱模式（+ 切换叙述器）**：先交付后移除，基于实际证据：当每个请求中都有 `Bash commands run under the "read-only" file sandbox.` 时，模型拒绝尝试被拒绝后可升级的工作（首次手动会话中十二个轮次有五个以零工具调用结束），将沙箱变成了软锁定。拒绝标记在需要时命名模式，升级字段承载恢复路径；批准旋钮保留其声明，因为自动拒绝在行为上与人的「不」无法区分。 -- **用专门的簿记事件追踪「上次告知」**：否决。`request/header` fold 已记录模型看到的确切提示词；将封闭的候选句子解析回来替代了第二条簿记流——事件仅在它们本身即为存储时才需要。 +- **通过 `agent.inject()` 加总线事件逐次叙述切换**：否决。独立通知会暴露归属方顺序和中间组合，而一次组装过程可以在请求边界以原子方式具体化完整的当前状态。 +- **在稳定系统提示词中声明沙箱模式**：先行交付，随后根据线上证据移除：每次请求都带有 `Bash commands run under the "read-only" file sandbox.` 时，模型会拒绝尝试本可在被拒后升级的工作（首次人工会话的十二个轮次中有五个以零工具调用结束），使沙箱变成软锁死。拒绝标记会在相关时刻指出模式，升级字段则承载恢复路径。[当前策略决策](2026-07-30-current-sandbox-policy-context.md)取代了省略策略的决策；这项测量和因果观察仍是任何替代方案必须进行反证测试的依据。 +- **用专门的簿记事件追踪「上次告知」**：否决。最新一条带来源的运行时上下文 `user/message` 会记录模型看到的确切完整快照。根据当前归属方贡献具体化该快照，取代了第二条簿记流——事件仅在它们本身即为存储时才需要。 - **相互独立的沙箱与批准选择器**：否决。一个部署定义的权限 preset 让两个策略旋钮对暴露运行时切换的 UI 客户端保持一致。 ## 后果 @@ -160,12 +160,12 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层 - 被拒绝的命令以 `sandbox_permissions` + `justification` 重试时，通过组合的应答器链提示用户；授权使该次调用在更宽模式下运行（结果事实如此报告），而其他所有调用保持各自的有效模式；每种非授权结果产生各自不同的错误文本且不执行任何内容。 - 升级字段恰好在已挂载的执行器约束时存在；不严格宽于调用有效模式的请求以自身文本失败关闭且不提示任何人；没有 ApprovalService 的部署对升级调用失败关闭，对普通调用不影响。 -- 系统提示词从不声明沙箱模式（批准 `'never'` 策略是唯一被声明的旋钮），且整个交互——header、旋钮事件、通知、批准、结果——仅从会话日志即可重建，除两个旋钮事件外无额外事件类型。 -- 一次 preset 选择只记录发生变化的旋钮值，而无操作的选择不记录任何内容；批准策略切换最多以一条合并通知叙述，已提交的沙箱切换由下一次调用的盖章兑现。 -- 恢复的会话的覆盖直接生效，无需追赶状态；进程停止期间变更的默认值在会话的首个新请求前被叙述，归因于运维人员。 +- 一条带来源的运行时上下文消息会以原子方式声明完整的当前沙箱策略与批准策略；整个交互——上下文快照、header、旋钮事件、批准通知、批准与结果——仅从会话日志即可重建，除两个旋钮事件外没有策略簿记事件。 +- 一次 preset 选择只记录发生变化的旋钮值，而无操作的选择不记录任何内容；下一个请求会把两个当前值共同纳入一份原子快照，已提交的沙箱切换由下一次调用的盖章兑现。 +- 恢复会话的覆盖项会进入其首个新运行时上下文快照，无需追赶状态；进程停止期间变更的组合默认值也会出现在该快照中。 - 两个并发会话永远看不到彼此的状态或通知。 - 同一个 Cordis 上下文中的两个并发项目会话解析各自独立的工作区根目录；bash 和 fs 写入在调用方会话的 cwd 内成功，对其相邻会话的 cwd 则失败。 -- `agent-loop` 未被触及——一切搭载 `systemPrompt.section`、`SessionEventMap` 合并、`agent.inject()`、`agent/step`、`agent/prompt-submit` 和由能力拥有的策略解析。 +- 策略归属仍通过 `systemPrompt.context`、`SessionEventMap` 合并和由能力归属方拥有的解析留在插件中；通用循环变更会将每个归属方的有序上下文具体化为一条带来源的消息。 代价与已接受的限制： @@ -178,9 +178,8 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层 - **模型可能过度请求。** 在没有拒绝依据的情况下升级，或在 `workspace-write` 足够时选择 `danger-full-access`：描述引导且枚举强制阶梯，但人的提示词是实际门控；`approval/asked` 原因使过度请求可审计，且 `prepend` 策略应答器可以自动拒绝部署永远不想要的模式。 - **公布的目标集是静态的，而有效模式是按会话的**（schema 是注册表全局的）——已处于最宽模式的会话仍被提供这些字段。构造上无害：执行时的严格放宽检查（而非枚举）是安全边界——非放宽请求以自身文本失败且不提示任何人。 - **授权的升级不等于可工作的沙箱。** 不可用的后端即使对授权升级到约束模式也仍然失败关闭——在平台没有链或所有探测失败时于 `confine()` 阶段，在未探测的唯一 runner 拒绝时于执行阶段（归类为沙箱失败而非命令失败）——而授权的 `danger-full-access` 运行根本不触及提供方：此时授权（而非探测）是权威。 -- **批准叙述器的重启基线解析提示词文本。** 封闭的候选句子由写入模块本身拥有，因此措辞变更是同一文件中写入器+解析器的协调编辑；header 早于该段落的会话静默采用当前策略而不发通知。 -- **批准段落仍是动态提示词表面**（`'never'` 切换会破坏该会话的提供方提示词前缀缓存）。已接受：策略切换罕见，且模型基于过时的 `'never'` 行动更糟。沙箱旋钮不再触及提示词。 -- **模型可能持有关于沙箱模式的过时信念**（没有任何东西宣布切换）。有意接受：下一次尝试的标记或成功会纠正它，而宣布的观察到的失败模式——预防性拒绝——比一次浪费的重试更糟。 +- **运行时上下文历史仅追加。** 策略切换会在保留的历史之后追加一份用于取代先前快照的完整快照，从而保留稳定的系统与对话前缀；状态不变时不添加消息。 +- **旧策略快照仍保留在历史中。** 每份完整快照都会明确取代更早的运行时上下文快照，因此回放与压缩（compaction）只需保留最新具体化的消息。 ## FAQ @@ -191,8 +190,8 @@ fs/web/todo 在进程内执行，因此它们的沙箱语义是各自 seam 层 - **沙箱限制网络或进程可见性吗？** 不——`SandboxMode` 仅声称文件操作；bwrap profile 刻意不 unshare pid，没有后端声称网络。网络限制是否成为自己的旋钮留在 § seam 中开放。 - **哪些工具实际在约束下运行？** 通过 `ctx.bash` 的 OS 子进程——bash 工具及传递性的钩子命令——再加上通过沙箱化 `ctx.fs` 提供方运行的文件系统工具（`read`/`write`/`edit`，见[跨工具族 fs 沙箱 Agent Note](2026-07-14-cross-family-fs-sandbox.md)）：bash 通过 OS runner 约束，fs 通过进程内路径围栏约束，二者都以同一个 `ctx.sandboxPolicy` 模式为键。web/todo 仍在进程内且不受限制（web 的唯一效果是网络，不在文件效果模式词汇内）。 - **授权的升级会持久化吗？** 不会。授权由发起请求的确切前台或后台调用消费；每个相邻调用保留自己的有效模式。后续的后台拒绝通过 `task_output` 呈现，并且可以作为一次新的精确命令重试的依据。 -- **运行时模式切换何时生效？** 一旦其会话事件提交，紧接着的下一次能力解析就会折叠并盖章新模式。模型不被告知常驻模式；其下一个命令直接在新策略下运行，任何拒绝都会在使用点命名该策略。 -- **重启后什么存活——如果运维人员在进程停止期间改了配置默认值呢？** 覆盖从会话日志回放（`effective = fold ?? config`），因此恢复的会话以零追赶机制保持其模式；离线漂移的默认值以与切换相同的方式改变行为（批准策略因被声明，还额外以运维人员/配置归因叙述）。 +- **运行时模式切换何时生效？** 一旦其会话事件提交，下一个运行时上下文快照与下一次能力解析都会折叠新模式。带来源的上下文消息会记录模型收到的内容，之后的任何拒绝都会在使用点命名同一策略。 +- **重启后什么存活——如果运维人员在进程停止期间改了配置默认值呢？** 覆盖从会话日志回放（`effective = fold ?? config`），因此恢复的会话以零追赶机制保持其模式；离线漂移的默认值会进入下一份完整运行时上下文快照。 - **结果上的 `enforcement: 'partial'` 是什么意思？** 所选后端强制其内核 ABI 管控的子集——例如 ABI v3 之前的 Landlock 不管控路径 truncate——并以结构化方式如此声明而非拒绝主机；探测的报告行区分各种情况。bwrap 和 Seatbelt profile 构造上管控所有承诺的文件操作，因此始终报告 `full`。 ## 先例 diff --git a/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.i18n.yaml b/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.i18n.yaml index fb39bd26db..d50b2323e3 100644 --- a/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.i18n.yaml @@ -1,6 +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 -2026-07-08-background-subagent-tasks.md: 12b34f2a28cfa311a48904cd5396ec16d9123641 -2026-07-08-background-subagent-tasks.zh.md: 58f035a14d55bc0b4e7f670111909074c3f53b2b +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md +2026-07-08-background-subagent-tasks.md: 679c57c3173a32b8cfccc6611b4ba74487e7f7e3 +2026-07-08-background-subagent-tasks.zh.md: 487943ab5cfe78226cde912854099fc56a5833a6 diff --git a/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md b/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md index 12b34f2a28..679c57c317 100644 --- a/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md +++ b/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.md @@ -23,7 +23,7 @@ For a background call, the tool validates the parent and refuses an already-abor The task registration maps the subagent seam as follows: - `kind` is `subagent`, `label` is the model-supplied description, and `owner` is the parent agent. -- `cancel(reason?)` aborts the task-owned controller. The same signal covers pending provider startup and the ready child. +- `cancel(reason?)` aborts the task-owned controller. The same signal covers pending provider startup and the published run's remaining work. - `done` awaits provider startup, the child result, and `run.dispose()`. Completed runs return final text, aborted runs become `killed`, and other stop reasons become `failed`. Startup, result, and disposal failures become failed outcomes rather than rejected task promises. - `readOutput` is absent. While live, `task_output` returns status only; after settlement, it returns final output idempotently. Intermediate child activity remains in the child session. @@ -57,7 +57,7 @@ Streaming child history into the parent would blur the log boundary and make pro ## Testing -Unit coverage pins stop-reason mapping, dispose-before-report behavior, startup and result failures, pre-aborted refusal, detachment from the starting call's signal, cancellation before and after provider readiness, collection through the real task tools, the no-surface preflight fence, missing-runtime failure, and per-instance schema gating. Snapshot coverage pins the model-facing schemas. +Unit coverage pins stop-reason mapping, dispose-before-report behavior, startup and result failures, pre-aborted refusal, detachment from the starting call's signal, cancellation before and after provider publication, collection through the real task tools, the no-surface preflight fence, missing-runtime failure, and per-instance schema gating. Snapshot coverage pins the model-facing schemas. ## Consequences diff --git a/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.zh.md b/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.zh.md index 58f035a14d..487943ab5c 100644 --- a/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.zh.md +++ b/.agents/notes/implemented/feature/2026-07-08-background-subagent-tasks.zh.md @@ -23,7 +23,7 @@ subagent 需要与其他长时间运行的工具相同的启动、收集、列 任务注册按以下方式映射 subagent seam： - `kind` 为 `subagent`，`label` 为模型提供的描述，`owner` 为父 agent（智能体）。 -- `cancel(reason?)` 中止任务自有的控制器。同一个信号同时覆盖尚未完成的提供方启动和已就绪的子级。 +- `cancel(reason?)` 中止任务自有的控制器。同一个信号同时覆盖尚未完成的提供方启动和已发布 run 的剩余工作。 - `done` 等待提供方启动、子级结果和 `run.dispose()`。已完成的运行返回最终文本，已中止的运行变为 `killed`，其他停止原因变为 `failed`。启动、结果和资源释放失败会转换为失败结果，而不是被拒绝的任务 Promise。 - `readOutput` 不存在。任务存活期间，`task_output` 只返回状态；结算后，它以幂等方式返回最终输出。中间的子级活动仍保留在子会话中。 @@ -57,7 +57,7 @@ agent 和日志可能以会话为作用域，但任务注册表和可预测 id ## 测试 -单元测试覆盖固定了停止原因映射、在报告前释放资源、启动与结果失败、对预中止的拒绝、从启动调用信号分离、在提供方就绪前后取消、通过真实任务工具收集、无控制接口的预检防线、运行时缺失失败，以及每实例 schema 开关。快照覆盖固定了面向模型的 schema。 +单元测试覆盖固定了停止原因映射、在报告前释放资源、启动与结果失败、对预中止的拒绝、从启动调用信号分离、在提供方发布前后取消、通过真实任务工具收集、无控制接口的预检防线、运行时缺失失败，以及每实例 schema 开关。快照覆盖固定了面向模型的 schema。 ## 影响 diff --git a/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml b/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml deleted file mode 100644 index 688fe6864a..0000000000 --- a/.agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# 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/feature/2026-07-17-dedicated-full-screen-tui-front-door.md -2026-07-17-dedicated-full-screen-tui-front-door.md: c011a0284ea0efe59693785c038f814a866068ac -2026-07-17-dedicated-full-screen-tui-front-door.zh.md: 5aea4ac0c5a3b29c098c297e514fab49caf643ff diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml index 6cf16c04ad..1f787065ab 100644 --- a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.i18n.yaml @@ -1,6 +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 -2026-07-19-model-facing-goal-tools.md: bc4305af80bb13ceeff1888d489dcd8a00132f94 -2026-07-19-model-facing-goal-tools.zh.md: b07f62aa526902c4b2e9c081777a76ca53783d31 +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md +2026-07-19-model-facing-goal-tools.md: 18235c484194f5daf10556ebfc13bdc2d672be2e +2026-07-19-model-facing-goal-tools.zh.md: cc23a76e5faac2c203052d834ca0a87ca5dbed2a diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md index bc4305af80..18235c4841 100644 --- a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md +++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.md @@ -22,7 +22,7 @@ The prompt tells the model that it may infer goal intent from a direct human req All three tools use exclusive execution so a model-ordered batch observes prior mutations and their new revisions. Results are compact JSON. UI presentation is a pure function of arguments and uses generic read or mutation cards; mutation cards select meaningful action values before the goal id, so accepted fillers cannot blank their input. Activation is reported only as live observation and is never written into replay state. -An autonomous goal round that successfully reports completion or blocking marks its tool result as concluding the physical turn, preventing an unnecessary follow-up request. Direct-human mutations do not conclude the turn: the assistant can acknowledge the change, and concurrent human steering remains available to ordinary stopping checks. +An autonomous goal round that successfully reports completion or blocking defers one wrap-up instruction onto its tool result so the model still addresses the user before the turn ends through the ordinary no-tool-calls stop; the original conclude-at-result stop is superseded by the [goal-round wrap-up decision](../bug-fix/2026-08-02-goal-round-wrapup-message.md). Direct-human mutations receive no instruction: the assistant can acknowledge the change, and concurrent human steering remains available to ordinary stopping checks. ### Execution authority diff --git a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md index b07f62aa52..cc23a76e5f 100644 --- a/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md +++ b/.agents/notes/implemented/feature/2026-07-19-model-facing-goal-tools.zh.md @@ -22,7 +22,7 @@ Status: implemented 三个工具都采用独占执行，使模型排序的批次可以观察此前变更及其新修订号。结果为紧凑 JSON。UI 展示是参数的纯函数，使用通用读取或变更卡片；变更卡片选择输入时，先取有实际意义的操作值，再取目标 id，因此允许的占位值不会使卡片输入留空。激活态仅作为实时观察返回，绝不会写入回放状态。 -自主目标回合成功报告完成或阻塞后，其工具结果会被标记为结束该物理轮次，避免再发起一次不必要的模型请求。直接人类发起的变更不会结束轮次：agent 可以确认该变更，并且并发的人类 steering（中途引导）仍可参与普通的停止检查。 +自主目标回合成功报告完成或阻塞后，其工具结果会附带一条收尾指令，模型仍会在轮次经由常规无工具调用停止路径结束前向用户发言；原先在结果处终结轮次的做法已被[Goal Round 收尾决策](../bug-fix/2026-08-02-goal-round-wrapup-message.md)取代。直接人类发起的变更不会收到指令：agent 可以确认该变更，并且并发的人类 steering（中途引导）仍可参与普通的停止检查。 ### 执行权限 diff --git a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.i18n.yaml b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.i18n.yaml index 11674d7747..e4e9dfb93a 100644 --- a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.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/feature/2026-07-20-dsh-cli-personal-config.md -2026-07-20-dsh-cli-personal-config.md: 3331e36c86002d91fb272868268707fed014d01a -2026-07-20-dsh-cli-personal-config.zh.md: 172d84b075ed7ecc127c317b47e30581db67f89a +2026-07-20-dsh-cli-personal-config.md: 1fa8cda2b34b58cc7a28b722872520b68a9b7009 +2026-07-20-dsh-cli-personal-config.zh.md: e70b8914cf005e0a2e54ba2b29d3b7def84b00db diff --git a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md index 3331e36c86..1fa8cda2b3 100644 --- a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md +++ b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md @@ -12,21 +12,21 @@ A developer's own preferences — which provider and model the TUI uses, persona Two coupled pieces, aligned with the `apps/` assembly tier proposed by the `dsh web` PR (#443): -**The `dsh` CLI (`apps/cli`, npm name `@deepseek-ai/dsh`).** `apps/*` joins the workspaces as the product-assembly tier over `packages/*` libraries. The bin's dispatch reserves `web` and `-p`/`--prompt` for PR #443 (they exit with a pointer) so the two branches merge as a near-union; everything else runs the default surface: the interactive TUI, booting the shipped `examples/tui-agent/cordis.yml` (or an explicit config argument) with the invoking directory as the workspace. The committed `bin/dsh` launcher resolves the checkout through its own real path and runs the bin **from source** through Node's native TypeScript transform plus the app-owned tsconfig-paths loader, so `ln -sf "$(pwd)/bin/dsh" ~/.local/bin/dsh` installs a command that always executes the current working tree. `pnpm run demo:tui` runs the same entry. +**The `dsh` CLI (`apps/cli`, npm name `@deepseek-ai/dsh`).** `apps/*` is the product-assembly tier over `packages/*` libraries. One bin dispatches the default interactive TUI, `-p`/`--prompt` headless turns, and the `web` surface. The TUI boots `examples/tui-agent/cordis.yml` (or `--config`) with the invoking directory as the workspace. The committed `bin/dsh` launcher resolves the checkout through its own real path and runs the app with tsx's ESM hook; the [source-launch decision](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md) owns that contract. `pnpm run demo:tui` runs the same entry. -**Personal config (`dsh-app-boot`).** The personal overlay lives in the Harness home — `$DSH_HOME`, else `~/.dsh` — resolved by the shared [`resolveDshHome`](../architecture/2026-07-24-single-harness-home-resolver.md) (`@deepseek-ai/dsh-paths`), the same single root skills and AGENTS.md resolve against. The official dsh surfaces consume its two optional files; the demo bins boot their committed trees verbatim: +**Personal config (`dsh-app-boot`).** The personal overlay lives in the Harness home — `$DSH_HOME`, else `~/.dsh` — resolved by the shared [`resolveDshHome`](../architecture/2026-07-24-single-harness-home-resolver.md) (`@deepseek-ai/dsh-paths`), the same single root skills and AGENTS.md resolve against. The dsh TUI, Web, and headless surfaces consume its two optional files; the demo bins boot their committed trees verbatim: - `.env` — loaded after the invoking directory's `.env`; `process.loadEnvFile` never overrides, so precedence is ambient > project `.env` > personal `.env`. -- `config.yaml` — a top-level YAML array of `@cordisjs/plugin-include` `PatchOptions`, parsed with the include's own `!!js` dialect (`loadPersonalPatches`) and passed to `boot()`, which forwards it as the root include's `patches`. Patch semantics match the shipped surface overlays: an id-targeted patch replaces the named entry's whole `config`, `insert` appends entries, and an unmatched id is a silent no-op. +- `config.yaml` — a top-level YAML array of `@cordisjs/plugin-include` `PatchOptions`, parsed with the include's own `!!js` dialect (`loadPersonalPatches`) and passed to `boot()`, which forwards it as the root include's `patches`. Patch semantics match the shipped surface overlays: an id-targeted patch replaces the named entry's whole `config`, `insert` appends entries, and an unmatched id is a silent no-op. The [repository Plugin integration](2026-07-30-config-only-repository-plugins.md) uses one shipped row to make an exact GitHub source list a config-only choice. - A missing file means no overlay; a present-but-unreadable, unparsable, or non-array file throws at boot (misconfiguration fails loud, never a silent skip). The PTY smoke's launcher isolates `$DSH_HOME` to a per-test directory, exactly as it already isolates `DSH_AGENTS_HOME`, so a developer's real personal overlay cannot leak into fixtures; only the dsh CLI reads personal config, so no other test launcher needed changes. -Hot-reload interplay: the include re-applies its `patches` on every config re-read (the [config hot-reload resilience Agent Note](../bug-fix/2026-07-20-config-hot-reload-resilience.md)), so a live `cordis.yml` edit keeps the personal overlay applied. +The TUI and Web register the exact personal path through Cordis HMR after boot. Every add, change, or removal transactionally recomposes the full patch list through the launcher's own composition closure, so the fresh personal patches land in the same layer position they booted in. Invalid YAML or a rejected Loader candidate leaves the last good tree active and broadcasts `hmr/config-update-failed(filename, Error)`; the headless surface reads the file once at startup. The Include also re-applies its patches on committed config-file refreshes (the [config hot-reload resilience Agent Note](../bug-fix/2026-07-20-config-hot-reload-resilience.md)). ## Alternatives considered -**A standalone `bin/dsh` wrapper owning the `dsh` name.** Rejected after reading PR #443: that PR establishes `apps/cli` as the `dsh` CLI with subcommand dispatch (`web`, `-p`) and leaves the default slot unclaimed. Two competing `dsh` entrypoints would collide in `$PATH` and in product identity; claiming the default slot inside the same package shape confines the eventual merge conflict to the small dispatch chain. +**A separate `bin/dsh` wrapper owning the `dsh` name.** Rejected because `apps/cli` is the single product CLI for default TUI, headless, and Web dispatch. Two competing entrypoints would collide in `$PATH` and product identity. **A pi-style typed settings file (`defaultProvider`/`defaultModel`/`providers`).** Rejected by the user in favor of patch semantics: the personal file is a cordis overlay over the shipped default config, not a second config vocabulary to own and translate. @@ -38,12 +38,12 @@ Hot-reload interplay: the include re-applies its `patches` on every config re-re ## Consequences -- `dsh` from any directory (and `pnpm run demo:tui`) boots the personal provider/model with zero repo changes; verified end-to-end against a personal Anthropic proxy with Opus 4.8, including a bash tool round trip. -- Because an id-targeted patch replaces the whole `config`, a personal override restates the base fields it keeps and can drift when the base entry changes shape; the loader's entry-not-found/name-mismatch warnings are the only diagnostics. +- `dsh` from any directory (and `pnpm run demo:tui`) can apply personal providers, models, repository Plugins, and other Loader entries with no checkout edit; verified end-to-end against a personal Anthropic proxy with Opus 4.8, including a bash tool round trip. +- Because an id-targeted patch replaces the whole `config`, a personal override restates the base fields it keeps and can drift when the base entry changes shape; the loader's entry-not-found/name-mismatch warnings and [`dsh --dump-config`](2026-07-30-dsh-dump-config.md) (which prints the composed tree those patches produce) are the diagnostics. - Personal patches resolve ids against the booted file's own tree, so nested-include overlays (Code Mode) are not personalized; live-run parity for those leaves is deferred. -- `dsh-app-boot` depends on `js-yaml` (plus a load-only copy of the include's `!!js` YAML type) and, like `apps/cli`, on `@deepseek-ai/dsh-paths` for `resolveDshHome`. -- When PR #443 lands, `apps/cli/src/bin.ts`'s dispatch chain and `apps/cli/package.json`'s dependency list conflict textually; both resolve as unions (their `web`/`-p` branches plus our default-TUI branch). +- `dsh-app-boot` depends on `js-yaml` and imports the include's `!!js` YAML dialect (`entryListSchema`) directly, and, like `apps/cli`, depends on `@deepseek-ai/dsh-paths` for `resolveDshHome`. +- Live watching belongs only to long-running TUI and Web processes. Headless automation gets deterministic startup configuration and exits without retaining a watcher. ## Testing -`packages/ui/app-boot/tests/personal-config.spec.ts` pins `!!js` preservation and end-to-end interpolation through a booted tree, insert entries, the default directory resolving from `$DSH_HOME`, the absent/empty no-op paths, and the three fail-loud shapes (unreadable, unparsable, non-array). `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` boots the dsh bin in a PTY three ways: default config with no overlay, a personal `.env` + `config.yaml` chain whose patched welcome renders in the banner, and an invalid personal file failing the boot loudly. The pre-existing smokes and snapshot suites pass on a machine whose real `~/.dsh` overlay would change the booted model — the isolation, not luck. +`packages/ui/app-boot/tests/personal-config.spec.ts` pins parsing, startup application, exact-path add/failure/recovery/removal, last-good rollback, failure broadcast, and preservation of app-owned patches. `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` boots the real dsh bin with no overlay, a personal environment and UI patch, a config-only cached repository skill, and invalid personal YAML. Test launchers isolate `$DSH_HOME`, so a developer's real overlay cannot leak into fixtures. diff --git a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md index 172d84b075..e70b8914cf 100644 --- a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md +++ b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md @@ -12,21 +12,21 @@ Status: implemented 两个耦合的部分，与 `dsh web` PR（#443）提出的 `apps/` 装配层对齐： -**`dsh` CLI（`apps/cli`，npm 名 `@deepseek-ai/dsh`）。** `apps/*` 作为 `packages/*` 库之上的产品装配层加入 workspaces。bin 的分发把 `web` 和 `-p`/`--prompt` 保留给 PR #443（它们以指引退出），使两个分支能以接近并集的方式合并；其余一切都运行默认表面：交互式 TUI，加载随仓库提供的 `examples/tui-agent/cordis.yml`（或显式的配置参数），并以调用目录为工作区。已提交的 `bin/dsh` 启动器通过自身真实路径解析 checkout，通过 Node 的原生 TypeScript 转换和应用自身持有的 tsconfig-paths loader **从源码**运行该 bin，因此 `ln -sf "$(pwd)/bin/dsh" ~/.local/bin/dsh` 安装的命令永远执行当前工作树。`pnpm run demo:tui` 运行同一入口。 +**`dsh` CLI（`apps/cli`，npm 名 `@deepseek-ai/dsh`）。** `apps/*` 是位于 `packages/*` 库之上的产品组装层。一个 bin 负责分发默认交互式 TUI、`-p`/`--prompt` 无头轮次和 `web` 界面。TUI 以调用目录为 workspace，启动 `examples/tui-agent/cordis.yml`（或 `--config` 指定的配置）。已提交的 `bin/dsh` 启动器通过自身真实路径解析 checkout，并使用 tsx 的 ESM hook 运行应用；该契约由[源码启动决策](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md)维护。`pnpm run demo:tui` 运行同一入口。 -**个人配置（`dsh-app-boot`）。** 个人 overlay 存放在 Harness home——`$DSH_HOME`，否则 `~/.dsh`——由共享的 [`resolveDshHome`](../architecture/2026-07-24-single-harness-home-resolver.md)（`@deepseek-ai/dsh-paths`）解析，与 skills、AGENTS.md 解析所依据的单一根目录相同。dsh 的官方界面消费其中两个可选文件；各示例 bin 仍然逐字节按已提交的配置树启动： +**个人配置（`dsh-app-boot`）。** 个人 overlay 存放在 Harness home——`$DSH_HOME`，否则 `~/.dsh`——由共享的 [`resolveDshHome`](../architecture/2026-07-24-single-harness-home-resolver.md)（`@deepseek-ai/dsh-paths`）解析，与 skills、AGENTS.md 解析所依据的单一根目录相同。dsh 的 TUI、Web 和无头界面使用其中两个可选文件；各示例 bin 仍然逐字节按已提交的配置树启动： - `.env`——在调用目录的 `.env` 之后加载；`process.loadEnvFile` 从不覆盖已有值，因此优先级为环境变量 > 项目 `.env` > 个人 `.env`。 -- `config.yaml`——顶层 YAML 数组，元素为 `@cordisjs/plugin-include` 的 `PatchOptions`，用 include 自己的 `!!js` 方言解析（`loadPersonalPatches`）并传给 `boot()`，由它作为根 include 的 `patches` 转发。补丁语义与交付的 surface overlay 一致：按 id 定位的补丁替换该配置项的整个 `config`，`insert` 追加配置项，未匹配的 id 静默不执行任何操作。 +- `config.yaml`——顶层 YAML 数组，元素为 `@cordisjs/plugin-include` 的 `PatchOptions`，用 include 自己的 `!!js` 方言解析（`loadPersonalPatches`）并传给 `boot()`，由它作为根 include 的 `patches` 转发。补丁语义与交付的 surface overlay 一致：按 id 定位的补丁替换该配置项的整个 `config`，`insert` 追加配置项，未匹配的 id 静默不执行任何操作。[仓库插件集成](2026-07-30-config-only-repository-plugins.md)通过一个已交付配置项，使精确 GitHub 源列表成为纯配置选择。 - 文件缺失即无 overlay；文件存在但不可读、不可解析或非数组则在启动时抛出（配置错误响亮失败，绝不静默跳过）。 PTY 冒烟测试的启动器把 `$DSH_HOME` 隔离到每个测试自己的目录，与它已有的 `DSH_AGENTS_HOME` 隔离方式完全一致，开发者真实的个人 overlay 不可能泄漏进 fixture；只有 dsh CLI 读取个人配置，因此其他测试启动器无需改动。 -与热重载的交互：include 在每次配置重读时重新应用其 `patches`（见[配置热重载韧性 Agent Note](../bug-fix/2026-07-20-config-hot-reload-resilience.md)），因此运行中编辑 `cordis.yml` 后个人 overlay 仍保持生效。 +TUI 和 Web 启动后通过 Cordis HMR（热模块替换）注册确切的个人配置路径。每次新增、变更或移除都会以事务方式通过启动器自己的组合闭包重新组合完整 patch 列表，因此新的个人 patch 落在启动时相同的层次位置。YAML 无效或 Loader 候选被拒时，最后一个可用树保持活动状态，并广播 `hmr/config-update-failed(filename, Error)`；无头界面只在启动时读取该文件。Include 在已提交配置文件刷新时也会重新应用其 patch（见[配置热重载韧性 Agent Note](../bug-fix/2026-07-20-config-hot-reload-resilience.md)）。 ## Alternatives considered -**独立的 `bin/dsh` 包装脚本占有 `dsh` 这个名字。** 读过 PR #443 后否决：该 PR 把 `apps/cli` 确立为带子命令分发（`web`、`-p`）的 `dsh` CLI，并且默认位空缺。两个互相竞争的 `dsh` 入口会在 `$PATH` 和产品身份上冲突；在同一包形态内认领默认位，把最终的合并冲突限制在小小的分发链上。 +**另设一个 `bin/dsh` 包装脚本并由其占用 `dsh` 名称。** 否决，因为 `apps/cli` 是统一的产品 CLI，负责分发默认 TUI、无头和 Web 界面。两个相互竞争的入口会在 `$PATH` 和产品身份上冲突。 **pi 风格的类型化设置文件（`defaultProvider`/`defaultModel`/`providers`）。** 用户否决，选择补丁语义：个人文件是叠加在随仓库提供的默认配置之上的 cordis overlay，而不是需要另行拥有和翻译的第二套配置词汇。 @@ -38,12 +38,12 @@ PTY 冒烟测试的启动器把 `$DSH_HOME` 隔离到每个测试自己的目录 ## Consequences -- 在任意目录运行 `dsh`（以及 `pnpm run demo:tui`）即可零仓库改动地使用个人提供方/模型；已针对个人 Anthropic 代理与 Opus 4.8 端到端验证，包括一次 bash 工具往返。 -- 由于按 id 定位的补丁替换整个 `config`，个人覆盖必须复述它保留的基础字段，并可能随基础配置项形态变化而漂移；loader 的「配置项未找到/名称不匹配」警告是仅有的诊断。 +- 在任意目录运行 `dsh`（以及 `pnpm run demo:tui`），无需修改 checkout，即可应用个人提供方、模型、仓库插件和其他 Loader 配置项；已针对个人 Anthropic 代理与 Opus 4.8 端到端验证，包括一次 bash 工具往返。 +- 由于按 id 定位的补丁替换整个 `config`，个人覆盖必须复述它保留的基础字段，并可能随基础配置项形态变化而漂移；诊断手段是 loader 的「配置项未找到/名称不匹配」警告和 [`dsh --dump-config`](2026-07-30-dsh-dump-config.md)（打印这些补丁合成出的配置树）。 - 个人补丁只在被启动文件自身的树里解析 id，因此嵌套 include 的 overlay（Code Mode）不会被个性化；这些叶子的实际运行等价性暂缓。 -- `dsh-app-boot` 依赖 `js-yaml`（外加一份只用于加载的 include `!!js` YAML 类型副本），并与 `apps/cli` 一样依赖 `@deepseek-ai/dsh-paths` 以获取 `resolveDshHome`。 -- PR #443 落地时，`apps/cli/src/bin.ts` 的分发链与 `apps/cli/package.json` 的依赖列表会产生文本冲突；两者都按并集解决（他们的 `web`/`-p` 分支加上我们的默认 TUI 分支）。 +- `dsh-app-boot` 依赖 `js-yaml`，并直接导入 include 的 `!!js` YAML 方言（`entryListSchema`）；与 `apps/cli` 一样依赖 `@deepseek-ai/dsh-paths` 以获取 `resolveDshHome`。 +- 只有长时间运行的 TUI 和 Web 进程进行实时监视。无头自动化使用确定性的启动配置，退出时不会保留 watcher。 ## Testing -`packages/ui/app-boot/tests/personal-config.spec.ts` 固定 `!!js` 的保留与经真实启动树的端到端插值、insert 配置项、默认目录从 `$DSH_HOME` 解析、缺失/为空的无操作路径，以及三种响亮失败形态（不可读、不可解析、非数组）。`examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` 在 PTY 里以三种方式启动 dsh bin：无 overlay 的默认配置、个人 `.env` + `config.yaml` 链条（打补丁的欢迎语渲染进横幅）、以及无效个人文件导致的响亮启动失败。既有冒烟与快照套件在一台真实 `~/.dsh` overlay 会改变启动模型的机器上通过——靠隔离，不靠运气。 +`packages/ui/app-boot/tests/personal-config.spec.ts` 固定解析、启动时应用、确切路径的新增／失败／恢复／移除、最后可用状态回滚、失败广播以及应用自有 patch 的保留。`examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` 启动真实 dsh bin，覆盖无 overlay、个人环境与 UI patch、纯配置的缓存 repository skill，以及无效个人 YAML。测试启动器会隔离 `$DSH_HOME`，因此开发者的真实 overlay 不会泄漏进 fixture。 diff --git a/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.i18n.yaml b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.i18n.yaml new file mode 100644 index 0000000000..a7d065d42d --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.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/feature/2026-07-21-continuable-background-subagents.md +2026-07-21-continuable-background-subagents.md: 6bbbfb25fb24eba95de888c9d23c79e24fc8535b +2026-07-21-continuable-background-subagents.zh.md: e23fbe67cc2d16a2c01a1b7ed4884008f8932dd4 diff --git a/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.md b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.md new file mode 100644 index 0000000000..6bbbfb25fb --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.md @@ -0,0 +1,127 @@ +# Agent Note: Continuable background subagents + +Status: implemented + +English | [中文](2026-07-21-continuable-background-subagents.zh.md) + +This record is superseded by [Continuable subagents](2026-07-28-continuable-subagent-conversations.md), which replaces its Task-backed activation model, routing, cancellation, and durability semantics with one durable Session plus at most one process-local Activation. Its service-placement and provider-capability policy were already superseded by [Merge subagent control into the subagent service](../simplification/2026-07-26-merge-subagent-control-service.md) and [Intent-named subagent continuation operations](../simplification/2026-07-27-intent-named-subagent-continuation-operations.md). Only the durable child-session and descriptor rationale remains in force. + +## Problem + +The subagent tool treats each delegation as one owned `SubagentRun`: foreground calls and background Tasks collect the result and then dispose the run. Disposal bounds the number of live child Agents and releases their scoped services, listeners, and provider resources. The persisted child session may survive, but the parent has no durable catalog or tool path for discovering that child and starting another turn on it. + +A Task, a run, and a child session have different lifetimes. A Task represents one background turn and has one terminal result. A `SubagentRun` owns one activation of a child. A persisted child session may contain many turns initiated by the parent or a human. Continuation must preserve per-run disposal rather than retain every historical child Agent in memory. + +## Decision + +A continuable background subagent is a durable child session with a series of Task-backed activations. The child session id, transcript, lineage, and declared composition survive in persistence. Each initial or resumed activation creates a fresh Task, `AgentHandle`, and `SubagentRun`, drives one turn, collects its result, and disposes the run before the Task becomes terminal. + +The Task's result and cancellation boundary belong to the child activation, not to whichever caller supplied its first message. Task access is authorized by the parent session id, while the Task registry retains the exact live parent Agent instance for notification and teardown. Parent and human messages therefore share one activation result while the parent remains its runtime owner: + +```text +durable child Session + activation 1: Task 1 -> SubagentRun -> AgentHandle -> dispose + activation 2: Task 2 -> SubagentRun -> AgentHandle -> dispose + activation 3: Task 3 -> SubagentRun -> AgentHandle -> dispose +``` + +Foreground delegation keeps its one-shot behavior. Continuation covers background in-process spawn and fork children. Each `tool-subagent` instance selects `backgroundMode: 'one-shot' | 'continuable'`; configured continuable mode requires the mounted provider's `resume` capability, while a resumable provider may still use one-shot background policy. ACP children remain one-shot until the deferred ACP continuation work below is complete. + +`ctx.subagents` is the only public service. Ordinary `start` stays collection-, Activation-, and persistence-agnostic: it validates provider capabilities, resolves the one-shot descriptor, dispatches one run, observes run lifecycle, and returns a holder-owned run. An injected internal continuation manager owns stable child ids, continuable descriptor persistence and lookup, Activation lifecycle, and routing through `startContinuable` and `followup`; provider preparation uses a private closure before the manager composes the child itself. The provider-bound `@deepseek-ai/dsh-tool-subagent` plugin and human-facing adapters call the intent operations for continuable background work; foreground and one-shot background delegation use ordinary `start`. The globally named model tool is a thin optional adapter in `@deepseek-ai/dsh-tool-subagent-control`, and its presence does not decide whether continuable work starts. Parent-to-child enumeration, the shared one-shot/continuable descriptor identity, and `list_agents` belong to the [durable subagent catalog](2026-07-22-durable-subagent-catalog-and-list-agents.md). + +### Task and cancellation ownership + +The initial background delegation asks `ctx.subagents` to start the child and register its Task. A continuable provider confirms the activation's final session state durable before fulfilling a successful run result. Task settlement awaits that result, calls `run.dispose()` through the continuation manager's settlement path, and only then records the `TaskOutcome`; `task_kill` aborts the active run, whose settlement path still disposes it. A terminal Task therefore leaves the durable child session but no live child Agent. A required durability checkpoint with no installed listener or a failing listener rejects the run with stable code `DURABILITY_FAILED` and the checkpoint failure as its cause; the manager records a failed Task whose detail explains that the latest state was not confirmed persisted and may be unavailable or stale on resume. + +Every later turn creates another Task. Its producer resources cover only that activation, never the child session. It reaches one terminal status, has one result, and is never reopened. The exact live parent Agent remains the Task registry owner: disposing that instance cancels, awaits, and removes its Tasks. Task APIs authorize a caller whose session id matches that owner, but a same-id replacement does not become the notification or teardown target. This preserves the `settleRun()` contract and bounds Task-owned live children by concurrent work rather than historical session count. + +Opening a child session in a human-facing adapter reads its persisted transcript and does not resume an Agent merely to display it. Human input starts or joins the same Task-backed activation used by parent input through the continuation manager. A human-started Task retains the exact currently loaded parent Agent as its notification target, and `task_output` remains the single result path. The existing completion listener injects at most one unsolicited notice while the Task is unreported; `kill`, a terminal read, or a terminal wait may mark it reported and suppress that notice. Human interaction is therefore permitted only while that parent instance remains live. A user-owned conversation that may outlive the parent and explicitly merge a conclusion back belongs to [interactive side sessions](../../proposed/feature/2026-07-08-interactive-side-sessions.md), not this Task-owned lifecycle. + +`TaskService.start()` rejects producers when no Task control surface is attached. A human-facing adapter that accepts child input must therefore attach a Task control surface, or run in a deployment that loads `@deepseek-ai/dsh-tool-tasks`; loading the Task service alone is insufficient. SDK-generated spawn and fork compositions mount `@deepseek-ai/dsh-tasks-local` and `@deepseek-ai/dsh-tool-tasks` with the subagent tools. This dependency is the cost of using the same Task result, cancellation, and notification path for parent- and human-started activations. + +Cancellation always targets the whole current activation. If human and parent messages have joined one turn, either caller's cancellation aborts that turn, disposes its run, and settles its Task as `killed`; the messages do not have independent results or cancellation rights. `followup()` requires the caller's signal, and abort while live steering awaits request admission aborts the activation-owned controller so the provider discards the pending message and the call settles only after the child reaches quiescence. Independent cancellation requires a later message to start a separate turn instead of steering the current one. + +A cold-resume Task creates its activation-owned `AbortController` before descriptor lookup or any provider await; the lookup, direct-parent authorization, and descriptor fold run inside the Task producer, so the same signal covers them and their failures settle that Task as `failed`. A persistence call that has no signal need not stop its underlying I/O, but the continuation manager rechecks cancellation after every such await and cannot begin or publish child work afterward. Before Agent publication, abort makes the provider reject only after its creation transaction has rolled back and reached quiescence. After publication, the provider closes the creation-signal handoff race, attaches the same signal to the live run before returning it, and cancellation stops the child turn. `task_kill` and exact-owner disposal use this path even when provider resume has not returned a `SubagentRun`; Task settlement waits for rollback or run disposal and records `killed` only after the activation is quiescent. + +### Active run association + +The continuation manager keeps a process-local association from child session id to its current Task and, after provider publication, its run. It installs the Task association before awaiting provider start or resume, fills in the returned run, and removes the association only after run disposal and Task terminal publication. This association exists only so parent and human senders can find the same activation; it is not a durable catalog, public `ManagedSubagent`, admission reservation, or run-state machine. + +For a continuable initial activation, the continuation manager allocates the stable child session id before Task creation and passes it as `SubagentProviderStartRequest.continuation`; in-process spawn and fork publish that exact id instead of allocating one internally. Ordinary `SubagentStartRequest` has no continuation field. The background tool returns canonical `{ kind: 'background', taskId, subagentId }`, rendered as `started subagent as task `. The child id names the durable conversation across activations, while the Task id names only the current activation. A failed initial Task or a process exit before the first child flush can leave an **unmaterialized child**: the caller holds a child id without a durable header and descriptor. Later by-id operations report that id as unavailable (the started Task fails with that detail), and durable enumeration omits it. + +Every continuable child turn is admitted through this Task-backed path. A non-terminal Task is the only supported live activation; when no activation exists, its run has already been disposed and the durable child is resumable. Before routing any by-id operation, the continuation manager synchronously compares its association with `ctx.agents.get(childId)`. A registry Agent with no association, or a registry Agent different from the associated `run.localAgent`, is an ownership conflict: the manager fails rather than adopting an idle Agent or attaching an untracked turn. When neither exists, cold resume may proceed; a competing publication after that check still loses at the Agent registry collision boundary. + +Routing follows the Task association. A running Task accepts live delivery through the run's optional confirmed `SubagentRun.steer` capability. An absent Task starts a fresh Task and cold-resumes the child. In-process spawn and fork first synchronously require the child to be `running` and reject an already committed structured capture, then call `Agent.steer()` and await that exact message's admission receipt. The default loop gives every steering item a message-owned receipt and resolves it `admitted` only after `agent/step` and asynchronous prompt assembly succeed, the message is appended, immutable request history is captured, and `step/start` commits; terminal turn policy, cancellation, and disposal resolve pending receipts `rejected`. A non-terminal turn close may carry pending steering into a later queued turn without acknowledging it. Providers must check the live status before `Agent.steer()` so its idle path cannot start a turn outside the observed run. If Task settlement or terminal policy wins after association lookup but before request admission, `steer()` rejects, `send_message` reports the message as not delivered, and that call does not fall through to cold resume; a later retry after Task terminal may start the next activation. + +The continuation manager does not serialize two callers that race a stopped child through paths outside it, nor does it model a separate settling phase between result production and disposal. The synchronous association install before the producer's first await admits one activation per child in this process — a competing `followup` during resume load observes the pending activation and fails explicitly — while a bypassing publication still loses at the Agent registry's same-session collision boundary. Delivery racing startup, cancellation, completion, or cleanup may also fail. These limitations are explicit rather than hidden behind a larger lifecycle abstraction. + +### Model-facing `send_message` + +The model receives one `send_message(subagent_id, message)` tool backed by `SubagentService.followup()`, matching the intent verb on `Agent`. The service operation owns steer-or-resume orchestration and is distinct from the run's `SubagentRun.steer?()`, which only delivers to an already active run. The tool performs no lifecycle routing of its own. It attributes the follow-up as `{ kind: 'coordinator', senderSessionId: parent.id }` and forwards `{ source, signal }`; the service requires both facts in one options object. The source crosses both live steering and cold resume, while cancellation owns only a pending live-delivery wait because a cold-resume Task returns immediately and owns its later cancellation. The child model still receives ordinary user-role content, while the durable source prevents model-generated follow-ups from being classified as direct human input. A human adapter instead supplies `{ kind: 'user' }` and its interaction signal. The tool lives in the separately loaded `@deepseek-ai/dsh-tool-subagent-control` package so provider-bound `@deepseek-ai/dsh-tool-subagent` instances can continue registering distinct delegation tools for spawn, fork, or ACP without registering duplicate global control tools. + +- If the child has a running Task and live-steering capability, the service calls `run.steer(message, source)` and returns the existing Task id; it creates no Task of its own. +- If the child has no running Task, `send_message` creates a fresh Task, cold-resumes the durable session with the message, and returns the new Task id. +- If the active provider cannot accept live delivery, confirmed steering loses its admission race, or a live child exists outside the Task association, `send_message` fails rather than silently starting, resuming, or adopting an untracked turn. + +The service result identifies the route as `steered` with the existing Task id or `started` with the new Task id. Failure is explicit and says that the message was not delivered. The model-facing tool renders these distinctions so timing-dependent routing is observable to the caller. + +A delivered message has no independent result: its effect is reflected in the current Task's eventual result. A started follow-up has the fresh Task's result and existing `task_output` read path. The subagent layer adds no second completion injection. + +Human input uses the same `followup` operation. The UI may display the child transcript and current Task state, while cancellation calls the Task service with the loaded parent as caller. Tool schema and UI adapters are consumers of one service contract rather than separate execution paths. + +### Durable child handle and cold resume + +The continuation manager snapshots every descriptor input with the seam's `snapshotSubagentDescriptor()` (built on [`snapshotJsonValue`](../../../../packages/core/session/src/json.ts)) before Task creation, matching the detached lossless-JSON boundary already used by Agent messages. A child-scoped setup contribution — a prepended one-shot `agent/prompt-submit` listener installed by the in-process driver — appends one model-hidden `subagent/descriptor` event before downstream prompt admission can block or throw. Allowed admission opens the initial child turn afterward; rejected admission leaves the descriptor as a pre-turn log-only fact, and the activation's final required checkpoint persists it. The event carries no `surfaceOp`, remains outside model history, and survives when compaction replaces surface history. A known child id is resumable only when loading that child session yields a supported descriptor in the child's own suffix (after `seedLength`, so a fork seed cannot leak an ancestor's descriptor) and its header identifies the caller as the direct parent. + +The continuable arm of the versioned descriptor (`SUBAGENT_DESCRIPTOR_VERSION` in [descriptor.ts](../../../../packages/subagent/subagent/src/descriptor.ts)) carries `mode: 'continuable'`, the subagent provider name, resolved child `agentOptions.provider` and `agentOptions.model`, and optional `persona` and `toolFilter`. It does not snapshot the merge-extensible `AgentOptions` object: unrelated extension values cannot make continuation fail merely because they are not JSON. It deliberately omits `subagentDepth`; cold resume relies on the persisted header's `delegationDepth` rather than reconstructing depth from the descriptor. `outputSchema` belongs to one activation's result contract rather than durable child composition. The child header remains authoritative for the child id, `cwd`, `parentSession`, `seedLength`, and `delegationDepth`, while the persisted child transcript owns the fork seed and subsequent history. [`delegationDepthOf()`](../../../../packages/subagent/subagent/src/index.ts) takes the maximum of header and runtime values, so reconstructed runtime options may deepen the persisted value but never lower it and a resumed child cannot regain a top-level delegation budget. + +Cold resume cannot depend on an optional method of `SubagentRun`, because that run has been disposed and is not retained across process restart. A run represents one disposable activation and exposes only activation-scoped operations. `SubagentRun.steer?()` names the confirmed live-only capability so it cannot be confused with service orchestration or the model-facing tool. + +The internal continuation manager's resume path loads the known child session, folds its descriptor, authorizes the persisted `parentSession`, and runs inside the Task it creates. It passes a fully resolved `SubagentProviderResumeRequest`, including the Task-owned cancellation signal, through a private service closure whose only responsibility is capability-checked provider dispatch and the ordinary run lifecycle observation used by `start`. The selected `SubagentProvider.resume?()` owns transport-specific reconstruction (in-process: `parent.ctx.agents.resume` under the currently loaded parent scope) and returns a fresh run. Presence of the provider method is the continuation capability, so no redundant capability flag exists. `SubagentService.followup()` chooses between the associated run's `steer?()` operation and this cold-resume path. Neither private provider dispatch nor a provider enumerates durable children or associates Tasks. + +The background tool validates and snapshots descriptor inputs before calling `TaskService.start()`. A synchronous validation failure rejects the tool call and creates no Task. The tool otherwise returns the child and Task ids immediately, without waiting for child publication or descriptor durability. In-process continuable providers perform a final `SessionStore.flush()` after the child becomes idle and before reading the result; `true` confirms at least one durability listener participated, `false` is a required-checkpoint failure, and rejection carries a listener failure. This retries a failed loop checkpoint while the child is still live. If the final confirmation fails, the provider rejects instead of returning unconfirmed output, the continuation manager disposes the run, and the already-created Task settles as `failed` with the durability diagnosis in its detail. Cancellation during the confirmation owns the still-unpublished activation result, so a completed child turn or a later checkpoint failure cannot replace the Task's `killed` outcome. Foreground one-shot runs retain the loop's best-effort checkpoint behavior. In-process spawn and fork reconstruct composition under the currently loaded parent scope. A fork resume loads the child's own persisted transcript, which already contains the completed-turn prefix captured at initial creation; it never forks the parent's newer history again. Resuming a parent does not eagerly resume its children. + +TODO (ACP continuation): persist the remote ACP session id as provider-specific descriptor data and implement `AcpProvider.resume?()` as spawn, initialize, `loadSession`, then prompt. The initial ACP run must verify `initialize.agentCapabilities.loadSession`, and every resumed process must use the same durable backend; replayed history from `loadSession` must not be collected as the new activation's output. Because ACP load support is negotiated per child rather than established solely by the provider method's presence, this follow-up must also define how a start result advertises child-specific continuation before ACP children enter the durable catalog. + +### Result and notification ownership + +Every continuable child activation has exactly one Task and one `TaskOutcome`, regardless of whether the parent or a human supplied the first message. The generic Task reporting contract may inject at most one unsolicited completion notice to the retained parent owner while the Task is unreported; reads, waits, and cancellation may suppress it. Running delivery joins that activation and creates neither a second Task nor a second result. The child transcript remains the human-facing detailed record; Task output remains the parent-facing final result. + +Task records and active-run associations are process-local. Persistence makes the child session resumable after restart, but does not recover an interrupted Task, its result, or its notification. Durable Task recovery is a separate concern. + +## Alternatives considered + +**Retain every background child after Task settlement.** This is the Codex-style resident-session model: follow-up delivery is cheap, but historical children retain Agent scopes, session memory, listeners, and provider resources until an explicit residency limit or eviction policy removes them. Per-activation disposal uses persistence as the continuation boundary and preserves the current resource bound. + +**Let human turns run without Tasks.** A parent message joining such a turn has no Task result or completion notice, and UI cancellation has unclear effects on the parent's contribution. Giving every activation one Task makes completion and cancellation properties of the child turn rather than its initiating caller. + +**Keep one Task for the lifetime of a child session.** A terminal Task cannot naturally become running again, and one result cannot represent multiple turns. Fresh activation-scoped Tasks preserve the generic Task contract. + +**Create a Task for every message.** Steering joins an existing turn and has no independent final result, so a Task created for steering would duplicate the active Task or report a result it does not own. Only a message that starts an activation creates a Task. + +**Split `send_message` and `follow_up`.** Separate delivery operations expose an implementation-state distinction to the model without removing stopped-child races. One operation follows the Claude Code model: deliver to running work or resume a new Task-backed lifecycle. + +**Keep `resume?()` on the disposed run.** Retaining a disposed `SubagentRun` only to call `resume()` makes the old run double as a durable child handle and cannot reconstruct that object after restart. Service dispatch plus provider reconstruction makes the persistence boundary explicit. + +**Put control orchestration on `SubagentService`.** This service-placement alternative is the [merged-service decision](../simplification/2026-07-26-merge-subagent-control-service.md); the [intent-operation refinement](../simplification/2026-07-27-intent-named-subagent-continuation-operations.md) keeps provider start/resume dispatch reusable only inside the service while isolating optional Task and persistence work in an injected internal manager. + +**Add explicit activation phases.** Public `starting`/`running`/`settling` states could describe admission and cleanup precisely, but would add a lifecycle protocol the implementation does not otherwise need. The synchronous association install closes duplicate process-local cold resume without exposing those phases. + +## Testing + +- `packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts` pins the continuable durability boundary: an absent or detached flush listener and a permanent listener failure reject with `DURABILITY_FAILED`, a transient loop-checkpoint failure can succeed on the final confirmation, cancellation owns either final-checkpoint outcome, resume also confirms durability, and foreground runs remain best-effort. `packages/subagent/subagent/tests/continuation.spec.ts` drives the real stack (agent loop, JSONL persistence, spawn/fork providers, Task service, and `ctx.subagents`) keylessly: initial and resumed activations create fresh Tasks and dispose their runs before terminal; the descriptor event is pre-turn, model-hidden, versioned, durable under the service-allocated child id, and survives blocked or throwing initial prompt admission; cancellation, steering, cold follow-up, authorization, ownership conflicts, and resume races retain the contracts described above. +- `packages/subagent/tool-subagent-control/tests/tool-subagent-control.spec.ts` pins the `send_message` schema, coordinator attribution, both route renderings, the not-delivered failure, the no-agent rejection, and HMR disposal. +- `packages/subagent/tool-subagent/tests/tool-subagent.spec.ts` covers the configured background route: continuable mode requires a resumable provider and returns both ids without requiring `send_message`, while one-shot mode keeps the plain Task acknowledgement even when the provider can resume. +- `packages/sdk/helper/tests/project.spec.ts` pins the Task service and model-facing Task controls in generated spawn and fork compositions. +- The keyless ACP snapshot scenario `subagent-continuable` (examples/acp-agent) pins the model-visible transcript: the two-id acknowledgement, a final durability-confirmation failure rendered through `task_output` without unconfirmed child output, and a `send_message` follow-up whose started Task fails with the id unavailable. + +## Consequences + +- Every follow-up after settlement pays persistence load and scoped setup cost; in exchange, live children stay bounded by concurrent work rather than historical session count. Continuable creation fails clearly when persistence is unavailable or the stored composition cannot be reconstructed. +- Two callers may still race a stopped child through paths outside the continuation manager. The Agent registry prevents duplicate same-session publication; a losing Task fails and its message is not delivered. A message may also race cancellation, terminal status publication, or run disposal. Admission is not claimed to be atomic or exactly-once; the synchronous process-local association install closes duplicate cold resume through `followup` without a public lifecycle state machine. +- Driving a continuable child through the ordinary Agent API bypasses its Task association. `ctx.subagents` rejects that live child as an ownership conflict; adapters must display persisted transcripts without loading an Agent and submit human input through `SubagentService.followup()`. +- The active-run association coordinates only one runtime. Concurrent resume from multiple processes is not serialized; that deployment requires a persistence-level lease or compare-and-set operation. +- Human interaction requires the exact parent Agent instance to remain live because owner disposal cancels and removes its Tasks. It also requires an attached Task control surface. Standalone child interaction requires a future separation between Task access ownership and durable notification targeting. +- The background tool returns child and Task ids before child publication and descriptor durability. Startup failure, a failed final durability confirmation, or process exit before the first child flush leaves the Task failed and may leave an unmaterialized or stale child id; by-id control reports missing state as unavailable rather than retroactively changing the tool acknowledgement. +- Persisting explicit composition fields in the child log makes their lossless-JSON and compatibility contract part of resume. Later support for another composition input requires a deliberate descriptor-version change rather than implicitly persisting merge-extensible `AgentOptions` fields. +- Task records and active-run associations are process-local even though child sessions are durable. Restart recovers the session, not in-flight work or its Task notification. diff --git a/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.zh.md b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.zh.md new file mode 100644 index 0000000000..e23fbe67cc --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-21-continuable-background-subagents.zh.md @@ -0,0 +1,127 @@ +# Agent Note: 可继续的后台 subagent + +Status: implemented + +[English](2026-07-21-continuable-background-subagents.md) | 中文 + +本记录已由[可继续的 subagent](2026-07-28-continuable-subagent-conversations.md)取代——后者以一个持久 Session 加至多一个进程内 Activation（驻留期）替换了其基于 Task 的 activation 模型、路由、取消和持久性语义。其服务放置与提供方功能策略此前已由[将 subagent 控制合并到 subagent 服务](../simplification/2026-07-26-merge-subagent-control-service.md)和[以意图命名的 subagent 继续执行操作](../simplification/2026-07-27-intent-named-subagent-continuation-operations.md)取代。仅持久 child 会话与 descriptor 的设计依据仍然有效。 + +## 问题 + +subagent 工具将每次委派视为一个独占的 `SubagentRun`：前台调用和后台 Task 收集结果后 dispose（资源释放）该 run。这种所有权关系能够限制存活 child agent（智能体）的数量，并释放其作用域服务、监听器及提供方资源。持久化的 child 会话可能继续存在，但 parent 缺少持久化目录和工具路径，无法发现该 child 并为其启动另一轮次。 + +Task、run 和 child 会话具有不同的生命周期。一个 Task 表示一轮后台执行，并且只有一个终态结果。一个 `SubagentRun` 拥有 child 的一次激活。一个持久化 child 会话可以包含多个由 parent 或用户发起的轮次。继续执行必须保留逐 run dispose 的约定，而不能把所有历史 child agent 都留在内存中。 + +## 决策 + +一个可继续的后台 subagent，是由一系列 Task 支撑的短期激活共同组成的持久化 child 会话。child session id、transcript（文本记录）、谱系及声明的组合配置均保留在持久化存储中。每次初始激活或恢复激活都会创建新的 Task、`AgentHandle` 和 `SubagentRun`，驱动一个轮次、收集结果，并在 Task 进入终态前 dispose 该 run。 + +Task 的结果和取消边界属于 child 激活，不属于为该激活提供第一条消息的调用方。Task 访问根据 parent session id 授权，而 Task 注册表仍保留当前存活的精确 parent Agent 实例，用于通知与资源清理。因此，只要 parent 仍是运行时 owner，parent 消息和用户消息便会共享同一个激活结果： + +```text +durable child Session + activation 1: Task 1 -> SubagentRun -> AgentHandle -> dispose + activation 2: Task 2 -> SubagentRun -> AgentHandle -> dispose + activation 3: Task 3 -> SubagentRun -> AgentHandle -> dispose +``` + +前台委派保持一次性行为。继续执行覆盖后台的进程内 spawn 和 fork child。每个 `tool-subagent` 实例都会选择 `backgroundMode: 'one-shot' | 'continuable'`；配置为可继续模式时，所挂载提供方必须具备 `resume` 功能，而可恢复的提供方仍可采用一次性后台策略。在下述 ACP（Agent Client Protocol）后续工作完成前，ACP child 仍保持一次性行为。 + +`ctx.subagents` 是唯一的公开服务。普通 `start` 不感知 child 集合、Activation 与持久化：它校验提供方功能、解析一次性描述符、分发一个 run、观察 run 生命周期，并返回由持有方负责的 run。注入的内部继续执行管理器负责管理稳定的 child id、可继续描述符持久化与查找、Activation 生命周期，以及通过 `startContinuable` 和 `followup` 进行的路由；管理器自行组合 child 之前，提供方通过私有闭包提供准备数据。按提供方绑定的 `@deepseek-ai/dsh-tool-subagent` 插件及面向用户的适配器调用这些意图操作来处理可继续后台工作；前台和一次性后台委派使用普通 `start`。全局命名的模型工具是 `@deepseek-ai/dsh-tool-subagent-control` 中的可选轻量适配器，它是否存在不会决定是否启动可继续工作。parent 到 child 的枚举、一次性／可继续模式共享的描述符身份与 `list_agents` 属于[持久化 subagent 目录](2026-07-22-durable-subagent-catalog-and-list-agents.md)。 + +### Task 与取消的所有权 + +初始后台委派请求 `ctx.subagents` 启动 child 并注册其 Task。可继续提供方只有在确认本次激活的最终会话状态已持久化后，才会返回成功的 run 结果。Task 结算流程等待该结果，通过继续执行管理器的结算路径调用 `run.dispose()`，然后才记录 `TaskOutcome`；`task_kill` 中止活跃 run，其结算路径仍会 dispose 该 run。因此，终态 Task 会留下持久化 child 会话，但不会留下存活的 child agent。必需的持久性检查点若没有已安装的监听器或任一监听器失败，run 会以稳定错误码 `DURABILITY_FAILED` 拒绝，并将检查点失败保留为失败原因；管理器会记录失败的 Task，其详情说明最新状态未确认已持久化，因此恢复时可能不可用或已陈旧。 + +后续每个轮次都会创建另一个 Task。该轮 producer 持有的执行资源仅服务于这次激活，不属于 child 会话。它只会到达一次终态、只产生一个结果，也不会重新打开。Task 注册表中当前注册的那个存活 parent agent 实例仍是其 owner：dispose 该实例会取消、等待并移除其 Task。Task API 会授权 session id 与该 owner 匹配的调用方，但 id 相同的替代实例不会成为通知或资源清理目标。这一设计保留 `settleRun()` 契约，并使 Task 所拥有的存活 child 数量受并发工作量限制，而不是随历史会话数量增长。 + +用户界面适配器打开 child 会话时，只读取持久化 transcript，不会仅为展示而恢复 agent。用户输入通过继续执行管理器，启动或加入与 parent 输入相同的 Task 激活。由用户启动的 Task 会保留当前加载的精确 parent Agent 作为通知目标，`task_output` 仍是唯一结果路径。只要 Task 尚未标记为已报告，现有完成监听器最多注入一条主动通知；`kill`、终态读取或终态等待都可能将其标记为已报告，并抑制这条通知。因此，仅允许在该 parent 实例保持存活时进行用户交互。可以比 parent 存活更久、并将结论显式合并回去的用户自有会话属于[交互式 side session](../../proposed/feature/2026-07-08-interactive-side-sessions.md)，不属于这一由 Task 持有的生命周期。 + +如果没有附加 Task 控制面，`TaskService.start()` 会拒绝 producer。因此，接受 child 输入的用户界面适配器必须附加 Task 控制面，或运行于加载了 `@deepseek-ai/dsh-tool-tasks` 的部署中；仅加载 Task 服务并不足够。SDK 生成的 spawn 与 fork 组合在挂载 subagent 工具时，也会挂载 `@deepseek-ai/dsh-tasks-local` 与 `@deepseek-ai/dsh-tool-tasks`。这项依赖是 parent 和用户启动的激活共用 Task 结果、取消和通知路径所付出的代价。 + +取消始终作用于当前完整激活。如果用户消息和 parent 消息已经加入同一个轮次，任一调用方发起取消都会中止该轮次、dispose 其 run，并将对应 Task 结算为 `killed`；这些消息没有独立的结果或取消权。`followup()` 要求调用方提供信号；若在线 steering 正在等待请求准入时该信号被中止，激活自有的 controller 会被中止，以便提供方丢弃待处理消息，并且该调用仅在子 agent 完全停稳后结算。若需要独立取消，后续消息必须另起轮次，而不能加入当前轮次。 + +从持久化存储恢复的 Task 会在查找描述符或等待任何提供方操作之前，创建由本次激活持有的 `AbortController`；描述符查找、直接 parent 鉴权和描述符归并都在该 Task producer 内部执行，因此同一信号覆盖它们，其失败会将该 Task 结算为 `failed`。对于不接受信号的持久化调用，可以让底层 I/O 执行完毕；但继续执行管理器必须在每次这类 await 返回后重新检查取消状态，如已取消，之后不得开始或发布任何 child 工作。在 Agent 发布前收到中止信号时，提供方必须先回滚其创建事务并达到完全停稳状态，然后才让恢复调用以拒绝结束。Agent 发布后，提供方必须消除创建期间移交取消信号时的竞态，在返回前将同一信号附加到存活 run；之后取消会停止 child 轮次。即使提供方的恢复调用尚未返回 `SubagentRun`，`task_kill` 与对确切 owner 实例的 dispose 仍通过这条路径生效。Task 结算会等待回滚或 run dispose 完成，只有在激活完全停稳后才记录 `killed`。 + +### 活跃 run 关联 + +继续执行管理器在进程内维护 child session id 到当前 Task 的关联，并在提供方发布后将 run 填入该关联。它会在等待提供方 start 或 resume 之前安装 Task 关联，填入返回的 run，并且只在 run dispose 完成且 Task 终态发布后才移除该关联。该关联只用于让 parent 发送方和用户发送方找到同一次激活；它不是持久化 child 目录、公开的 `ManagedSubagent`、准入预留或 run 状态机。 + +对于可继续 child 的初始激活，继续执行管理器会在创建 Task 前分配稳定的 child session id，并将其作为 `SubagentProviderStartRequest.continuation` 传递；进程内 spawn 和 fork 会发布这一确切 id，而不是在内部另行分配。普通 `SubagentStartRequest` 不含 continuation 字段。后台工具返回规范的 `{ kind: 'background', taskId, subagentId }`，渲染为 `started subagent as task `。child id 在多次激活中始终指代同一个持久化对话，Task id 则只指代当前激活。初始 Task 失败，或进程在 child 首次 flush 之前退出，都可能留下一个 **unmaterialized child**：调用方持有 child id，但不存在持久化 header 和描述符。后续按 id 的操作会报告该 id 不可用（已启动的 Task 会带着该详情失败），持久化枚举也不会列出它。 + +每个可继续 child 轮次都通过这条由 Task 支撑的路径准入。非终态 Task 是唯一受支持的存活激活；不存在激活时，其 run 已被 dispose，持久化 child 可以恢复。在路由任何按 id 的操作之前，继续执行管理器会同步将自身关联与 `ctx.agents.get(childId)` 比较。如果注册表中的 Agent 没有关联，或者它与所关联的 `run.localAgent` 不同，就属于所有权冲突：管理器会失败，而不会接管 idle Agent 或附加未受跟踪的轮次。二者均不存在时，可以从持久化存储恢复；如果检查后又有竞争方发布，仍会在 Agent 注册表的冲突边界上失败。 + +系统依据 Task 关联进行路由。运行中的 Task 通过 run 可选且提供确认语义的 `SubagentRun.steer` 功能接收在线消息。Task 不存在时，系统创建新 Task，并从持久化存储恢复 child。进程内 spawn 和 fork 会先同步要求 child 处于 `running` 状态，并拒绝已经提交结构化捕获的 child；随后调用 `Agent.steer()`，等待该消息专属的准入回执。默认循环会为每个 steering 项目提供一份归属于该消息的回执；只有在 `agent/step` 与异步提示词组装成功后，系统追加该消息、捕获不可变的请求历史并提交 `step/start`，回执才会解析为 `admitted`。终止型轮次策略、取消和 dispose（资源释放）会将待处理回执解析为 `rejected`。非终止型轮次关闭可以把待处理 steering 带入后续排队轮次，但不会确认其准入。提供方必须在调用 `Agent.steer()` 前检查存活状态，避免其 idle 路径在观察到的 run 之外启动轮次。如果查找关联之后、请求获准之前，Task 结算或终止策略率先完成，`steer()` 会拒绝，`send_message` 会报告消息未送达，而且该次调用不会改用从持久化存储恢复路径；在 Task 终态发布后重试，才可能启动下一次激活。 + +继续执行管理器不会串行化两个通过其外部路径同时争抢已停止 child 的调用方，也不会为结果产生与 dispose 之间的阶段单独建立 settling 状态。在 producer 首次 await 之前同步安装的关联，使本进程内每个 child 只准入一次激活——resume 加载期间竞争的 `followup` 会观察到待处理的激活并显式失败——而绕开该关联的发布仍会在 Agent 注册表相同会话的冲突边界上失败。发送也可能因与启动、取消、完成或清理发生竞态而失败。这些限制是明确的，而非隐藏在更大的生命周期抽象之后。 + +### 面向模型的 `send_message` + +模型获得一个由 `SubagentService.followup()` 支撑的 `send_message(subagent_id, message)` 工具，与 `Agent` 上的意图动词一致。该服务操作负责在 steering 与恢复之间编排；它不同于 run 的 `SubagentRun.steer?()`，后者只能向已活跃的 run 发送消息。工具本身不执行生命周期路由。该工具将后续消息的来源标记为 `{ kind: 'coordinator', senderSessionId: parent.id }`，并转发 `{ source, signal }`；服务要求在一个选项对象中同时提供这两项信息。来源会贯穿在线 steering 和 cold resume 两条路径，而取消只控制尚未完成的在线投递等待，因为 cold resume Task 会立即返回，并自行负责后续取消。child 模型收到的仍是普通的 user role 内容，而持久化的来源信息可防止模型生成的后续消息被归类为直接用户输入。用户适配器则提供 `{ kind: 'user' }` 及其交互信号。该工具位于单独加载的 `@deepseek-ai/dsh-tool-subagent-control` 包中，因此按提供方绑定的 `@deepseek-ai/dsh-tool-subagent` 实例可以继续为 spawn、fork 或 ACP 注册不同的委派工具，而不会重复注册全局控制工具。 + +- 如果 child 存在运行中的 Task 并支持在线消息，服务会调用 `run.steer(message, source)` 并返回现有 task id；它不会创建新 Task。 +- 如果 child 没有运行中的 Task，`send_message` 会创建新 Task，使用该消息从持久化存储恢复会话，并返回新的 task id。 +- 如果活跃提供方无法接收在线消息、带确认语义的 steering 在准入竞态中失败，或 Task 关联之外存在存活 child，`send_message` 会失败，而不会静默启动、恢复或接管未受跟踪的轮次。 + +服务结果将路由标识为 `steered` 并携带现有 task id，或标识为 `started` 并携带新的 task id。失败结果会明确说明消息未送达。面向模型的工具会呈现这些差异，让调用方能够观察由时序决定的实际路由。 + +发送到现有 run 的消息没有独立结果，其效果体现在当前 Task 的最终结果中。启动的后续轮次具有新 Task 的结果，并使用现有 `task_output` 读取路径。subagent 层不会再注入第二份完成通知。 + +用户输入使用同一个 `followup` 操作。UI 可以展示 child transcript 和当前 Task 状态，取消操作则以已加载 parent 作为调用方访问 Task 服务。工具 schema 与 UI 适配器消费同一个服务契约，不建立彼此独立的执行路径。 + +### 持久化 child handle 与从持久化存储恢复 + +继续执行管理器在创建 Task 前，通过 seam 的 `snapshotSubagentDescriptor()`（基于 [`snapshotJsonValue`](../../../../packages/core/session/src/json.ts) 构建）对每项描述符输入建立快照；这一边界与 Agent 消息现有的分离式无损 JSON 边界一致。作用于 child 作用域的 setup contribution——由进程内驱动前置安装的一次性 `agent/prompt-submit` 监听器——会在下游 prompt admission 能够阻止请求或抛出异常之前追加一个对模型隐藏的 `subagent/descriptor` 事件。admission 获准后才会开启 child 的初始轮次；admission 被拒绝时，描述符会作为轮次前的仅日志事实保留，并由该 activation 最终的必需检查点持久化。该事件不携带 `surfaceOp`，不进入模型历史，并在压缩替换 surface 历史时继续保留。只有在加载已知 child id 对应的 child 会话后，能在该 child 自身的后缀中（`seedLength` 之后，因此 fork seed 不会泄露祖先的描述符）得到受支持的描述符，且会话 header 将调用方标识为直接 parent 时，该 id 才可恢复。 + +版本化描述符的可继续分支（[descriptor.ts](../../../../packages/subagent/subagent/src/descriptor.ts) 中的 `SUBAGENT_DESCRIPTOR_VERSION`）携带 `mode: 'continuable'`、subagent 提供方名称、已解析的 child `agentOptions.provider` 和 `agentOptions.model`，以及可选的 `persona` 与 `toolFilter`。它不会对可通过声明合并扩展的 `AgentOptions` 对象建立快照：与此无关的扩展值不会仅因无法表示为 JSON 而导致继续执行失败。描述符会特意省略 `subagentDepth`；从持久化存储恢复时，系统依赖持久化 header 中的 `delegationDepth`，而不根据描述符重建深度。`outputSchema` 属于单次激活的结果契约，不属于持久化 child 组合配置。child header 仍是 child id、`cwd`、`parentSession`、`seedLength` 和 `delegationDepth` 的权威信息，持久化 child transcript 则负责保存 fork seed 和后续历史。[`delegationDepthOf()`](../../../../packages/subagent/subagent/src/index.ts) 会在 header 值和运行时值中取最大值，因此重建后的运行时选项可以加深持久化值，但绝不能降低它，恢复后的 child 无法重新获得顶层委派预算。 + +从持久化存储恢复不能依赖 `SubagentRun` 的可选方法，因为该 run 已被 dispose，并且进程重启后不会保留。run 表示一次可 dispose 的激活，只暴露作用于当前激活的操作。`SubagentRun.steer?()` 这一名称明确指代提供确认语义且仅适用于在线消息的功能，以免该功能与服务编排或面向模型的工具混淆。 + +内部继续执行管理器的恢复路径会加载已知 child 会话、归并其描述符、根据持久化的 `parentSession` 鉴权，并在其创建的 Task 内部运行。它通过私有服务闭包传递完全解析的 `SubagentProviderResumeRequest`，其中包含由 Task 持有的取消信号；该闭包只负责在检查提供方功能后进行分发，并执行 `start` 所使用的普通 run 生命周期观察。选中的 `SubagentProvider.resume?()` 负责传输相关的重建（进程内：在当前加载的 parent 作用域下执行 `parent.ctx.agents.resume`），并返回一个新 run。提供方是否存在该方法本身就是继续执行功能，无需额外功能标志。`SubagentService.followup()` 在关联 run 的 `steer?()` 操作与该持久化恢复路径之间做出选择。私有的提供方分发与提供方本身都不会枚举持久化 child 或关联 Task。 + +后台工具会在调用 `TaskService.start()` 前校验描述符输入并建立快照。同步校验失败会拒绝工具调用，且不会创建 Task。除此之外，工具会立即返回 child id 和 Task id，不等待 child 发布或描述符持久化完成。进程内可继续提供方会在 child 进入 idle 后、读取结果之前执行最终的 `SessionStore.flush()`；返回 `true` 表示至少有一个持久性监听器参与，返回 `false` 表示必需的检查点失败，而拒绝则携带监听器失败。此操作会在 child 仍存活时重试循环中失败的检查点。如果最终确认失败，提供方会拒绝而不返回未经确认的输出，继续执行管理器会 dispose 该 run，已经创建的 Task 会结算为 `failed`，其详情包含持久性诊断。最终确认期间发生取消时，尚未发布的激活结果由取消操作接管；即使 child 轮次已记录为完成，或之后的检查点失败，也不能取代 Task 的 `killed` 结果。前台一次性运行仍保留循环仅尽力执行检查点的行为。进程内 spawn 和 fork 会在当前已加载的 parent 作用域下重建组合配置。恢复 fork 时只加载 child 自己的持久化 transcript，其中已经包含初始创建时捕获的已完成轮次前缀；系统绝不会再次 fork parent 更新后的历史。恢复 parent 不会立即恢复其 child。 + +TODO（ACP 继续执行）：将远端 ACP session id 作为提供方专用描述符数据持久化，并实现 `AcpProvider.resume?()`，依次执行 spawn、initialize、`loadSession` 和 prompt。初始 ACP run 必须检查 `initialize.agentCapabilities.loadSession`，恢复后的每个进程必须使用同一个持久化后端；`loadSession` 回放的历史消息不得计入新激活的输出。由于 ACP 的加载支持是按 child 协商的，不能仅根据提供方是否存在该方法来确定，因此该后续工作还必须定义 start 结果如何声明单个 child 支持继续执行，之后才能将 ACP child 写入持久化目录。 + +### 结果与通知所有权 + +每次可继续 child 激活都恰好拥有一个 Task 和一个 `TaskOutcome`，无论第一条消息由 parent 还是用户提供。只要 Task 尚未标记为已报告，通用 Task 报告契约最多会向保留的 parent owner 注入一条主动完成通知；读取、等待和取消都可能抑制该通知。发送到运行中激活的消息会加入该激活，不会创建第二个 Task 或第二份结果。child transcript 是面向用户的详细记录；Task 输出是面向 parent 的最终结果。 + +Task 记录和活跃 run 关联都位于进程内。持久化使 child 会话可在重启后恢复，但不会恢复中断的 Task、其结果或通知。持久化 Task 恢复属于另一个问题。 + +## 已考虑的替代方案 + +**在 Task 结算后保留所有后台 child。** 这是 Codex 风格的常驻会话模型：发送后续消息成本较低，但历史 child 会持续占用 agent 作用域、会话内存、监听器和提供方资源，直至显式常驻数量上限或淘汰策略将其移除。逐激活 dispose 使用持久化作为继续执行边界，同时保留当前的资源上限。 + +**允许用户轮次不使用 Task。** parent 消息加入此类轮次后，没有对应的 Task 结果或完成通知；UI 取消对 parent 所发消息的影响也不明确。让每次激活都拥有一个 Task，可使完成与取消成为 child 轮次的属性，而不是初始调用方的属性。 + +**在 child 会话整个生命周期内复用一个 Task。** 终态 Task 无法自然地再次进入运行状态，一个结果也无法表示多个轮次。每次激活创建新 Task 可以保留通用 Task 契约。 + +**为每条消息创建 Task。** 发送到现有 run 的消息会加入已有轮次，不产生独立的最终结果；为这类消息创建 Task，会重复当前 Task，或报告一个它并不拥有的结果。只有启动新激活的消息才会创建 Task。 + +**拆分 `send_message` 与 `follow_up`。** 两个独立的投递操作会向模型暴露实现状态差异，却无法消除 child 已停止时的竞态。单一操作采用 Claude Code 模型：向运行中的工作发送消息，或恢复一个由新 Task 支撑的生命周期。 + +**在已 dispose 的 run 上保留 `resume?()`。** 如果仅为调用 `resume()` 而保留已 dispose 的 `SubagentRun`，旧 run 会同时充当持久化 child handle，而且进程重启后无法重建该对象。由服务分发、提供方重建，可明确表达持久化边界。 + +**将控制编排放在 `SubagentService` 上。** 这一服务放置方案即[服务合并决策](../simplification/2026-07-26-merge-subagent-control-service.md)；[意图操作细化](../simplification/2026-07-27-intent-named-subagent-continuation-operations.md)将提供方 start／resume 分发的复用限制在服务内部，同时将可选的 Task 与持久化工作隔离在注入的内部管理器中。 + +**增加显式激活阶段。** 公开的 `starting`／`running`／`settling` 状态可以准确描述准入和清理，但会引入实现本身并不需要的生命周期协议。同步安装关联无需暴露这些阶段，即可消除进程内重复的 cold resume。 + +## 测试 + +- `packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts` 固定可继续执行的持久性边界：缺少 flush 监听器、flush 监听器已脱离或监听器持续失败时，均会以 `DURABILITY_FAILED` 拒绝；循环检查点的瞬时失败可在最终确认成功后继续完成，发生取消时最终检查点无论成功还是失败都由取消优先决定结果，resume 同样会确认持久性，而前台运行仍采用尽力而为策略。`packages/subagent/subagent/tests/continuation.spec.ts` 以无密钥方式驱动真实栈（agent loop、JSONL 持久化、spawn／fork 提供方、Task 服务和 `ctx.subagents`）：初始及恢复后的激活都会创建新 Task，并在进入终态前 dispose 各自的 run；描述符事件位于轮次前、对模型隐藏、带版本、在服务分配的 child id 下持久化，并在初始 prompt admission 阻止请求或抛出异常时仍保留；取消、steering、cold follow-up、授权、所有权冲突与 resume 竞态保留上述契约。 +- `packages/subagent/tool-subagent-control/tests/tool-subagent-control.spec.ts` 固定 `send_message` 的 schema、coordinator 来源标记、两种路由渲染、未送达失败、无 agent 时的拒绝，以及 HMR（热模块替换）dispose。 +- `packages/subagent/tool-subagent/tests/tool-subagent.spec.ts` 覆盖配置的后台路由：可继续模式要求提供方可恢复，并在不要求 `send_message` 的情况下返回两个 id；即使提供方可以恢复，一次性模式仍保持普通的 Task 确认消息。 +- `packages/sdk/helper/tests/project.spec.ts` 固定生成的 spawn 与 fork 组合中的 Task 服务及面向模型的 Task 控制工具。 +- 无密钥 ACP 快照场景 `subagent-continuable`（examples/acp-agent）固定模型可见的 transcript：双 id 确认消息、最终持久性确认失败（该失败通过 `task_output` 呈现，且不包含未经确认的 child 输出），以及一次 `send_message` 后续操作——其已启动的 Task 会带着「id 不可用」失败。 + +## 影响 + +- 每次完成结算后的后续轮次都需要承担持久化加载和作用域 setup 成本；作为交换，存活 child 的数量受并发工作量限制，而不是随历史会话数量增长。持久化不可用或存储的组合配置无法重建时，可继续 child 的创建会明确失败。 +- 两个调用方仍可能通过继续执行管理器外部的路径争抢已停止的 child。Agent 注册表会阻止相同会话的重复发布；失败的 Task 会失败，且其消息不会送达。消息也可能与取消、终态状态发布或 run dispose 发生竞态。准入不承诺原子或恰好执行一次；在进程内同步安装的关联无需公开生命周期状态机，即可通过 `followup` 消除重复的 cold resume。 +- 通过普通 Agent API 驱动可继续 child 会绕过其 Task 关联。`ctx.subagents` 会将该存活 child 视为所有权冲突并拒绝；适配器必须在不加载 Agent 的情况下展示持久化 transcript，并通过 `SubagentService.followup()` 提交用户输入。 +- 活跃 run 关联只能协调一个运行时。多个进程同时恢复时不会串行化；此类部署需要持久化层的租约或 compare-and-set 操作。 +- 用户交互要求作为 owner 的那个精确 parent Agent 实例保持存活，因为 dispose owner 会取消并移除其 Task。用户交互还要求附加 Task 控制面。若要单独与 child 交互，后续必须将 Task 访问所有权与持久化通知目标分离。 +- 后台工具会在 child 发布和描述符持久化之前返回 child id 和 Task id。启动失败、最终持久性确认失败，或进程在 child 首次 flush 之前退出，都会使 Task 失败，并可能留下 unmaterialized 或陈旧的 child id；按 id 的控制操作会将缺失状态报告为不可用，而不会追溯修改工具确认消息。 +- 将显式组合字段持久化到 child 日志后，其无损 JSON 与兼容性契约便成为恢复契约的一部分。后续如需支持其他组合配置输入，必须明确更改描述符版本，不能隐式持久化可通过声明合并扩展的 `AgentOptions` 字段。 +- Task 记录和活跃 run 关联位于进程内，而 child 会话具有持久性。重启会恢复会话，但不会恢复进行中的工作或其 Task 通知。 diff --git a/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.i18n.yaml b/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.i18n.yaml index 176211d25b..e1999f49cb 100644 --- a/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.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/feature/2026-07-22-docked-web-goal-bar.md -2026-07-22-docked-web-goal-bar.md: f014da61d2fa0bf25121c040dae99354ab15de9d -2026-07-22-docked-web-goal-bar.zh.md: f62c6efbb2d330fb7d5ab74138eb781f1a1bc06c +2026-07-22-docked-web-goal-bar.md: 21f200f165acdf370a5896acb8f54afe33a4ee99 +2026-07-22-docked-web-goal-bar.zh.md: eb8e3edda54207b06e25812a38f969e74f342c34 diff --git a/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.md b/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.md index f014da61d2..21f200f165 100644 --- a/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.md +++ b/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.md @@ -10,9 +10,9 @@ The web UI had no goal surface at all: the goal stack shipped with model tools, ## Decision -`GoalBar` (`packages/client/ui-goal/src/client/GoalBar.tsx`) is a props-driven, self-contained component registered first in the composer's input-dock list. Its standalone 752px card follows the composer's horizontal geometry, and every visible state shares one fixed 36px height so switching phases never resizes it. Loading (`goal === undefined`), absent (`goal === null`), and `phase === 'complete'` render nothing — a completed goal is history, not chrome. +`GoalBar` (`packages/client/ui-goal/src/client/GoalBar.tsx`) is a props-driven, self-contained component registered second in the composer's input-dock list, after Todo and before Queue. Its standalone 752px card follows the composer's horizontal geometry, and every visible state shares one fixed 36px height so switching phases never resizes it. Loading (`goal === undefined`), absent (`goal === null`), and `phase === 'complete'` render nothing — a completed goal is history, not chrome. -Visibility drives the label and actions: active shows "Ongoing Goal" with pause/edit/clear; paused shows "Paused Goal" and swaps pause for a resume icon button; blocked shows "Blocked Goal" and carries `blockedReason.message` as the strip's `title` tooltip. Goal creation lives on the `/goal` command, not in the bar. The pencil swaps the strip for an inline edit form prefilled with the current objective: Enter or the check button saves through `GoalBarActions.onEdit(objective)`, Esc cancels, and an all-whitespace objective keeps save disabled. The form closes only when the edit succeeds; a failure preserves the draft and displays the error in the bar. Resume and clear failures are displayed there as well. Clear otherwise calls `onClear` directly with no confirmation — a clear keeps a durable tombstone, so nothing is unrecoverable. An effect keyed on the goal's id drops the edit form when the goal's identity changes, so a surviving draft can never be written over the goal that replaced it. +Visibility drives the label and actions: active shows "Ongoing Goal" with pause/edit/clear; paused shows "Paused Goal" and swaps pause for a resume icon button; blocked shows "Blocked Goal" and carries `blockedReason.message` as the strip's `title` tooltip. Goal creation lives on the `/goal` command, not in the bar. The pencil swaps the strip for an inline edit form prefilled with the current objective: Enter or the check button saves through `GoalBarActions.onEdit(objective)`, Esc cancels, and an all-whitespace objective keeps save disabled. The form closes only when the edit succeeds; a failure preserves the draft and displays the error in the bar. Resume and clear failures are displayed there as well. Clear otherwise calls `onClear` directly with no confirmation — a clear keeps a durable tombstone, so nothing is unrecoverable. Every mutation first acquires a synchronous component-local single-flight latch because React's pending-state render cannot close the same-frame click window. A successful clear also suppresses that exact goal id immediately while the authoritative null projection catches up, so an acknowledged tombstone cannot leave a stale clear control that submits `GOAL_NOT_FOUND`; a failure releases the latch and remains retryable. An effect keyed on the goal's id resets this transient state and drops the edit form when the goal's identity changes, so neither a cleared marker nor a surviving draft can affect the replacement goal. `GoalBarActions` lives in ui-goal's slot contract (`packages/client/ui-goal/src/client/slots.ts`) and carries exactly the rendered verbs: `onEdit`/`onPause`/`onResume`/`onClear`. Each callback asynchronously returns an explicit success/failure result so `GoalBar` owns its transitions and error display. `apply.ts` wires them to the runtime session methods; the runtime session resolves the current goal's compare-and-set ref internally, so the UI passes no ref. @@ -22,7 +22,7 @@ The strip's background is `--dsw-alias-interactive-bg-hover` rather than the moc ## Testing -`packages/client/ui-goal/tests/goalbar.spec.tsx` pins the behavior through props alone: loading/absent/complete render nothing, the active strip renders label/objective and fires clear, the edit form prefills, rejects empty, saves on Enter, cancels on Esc, and resets when the goal's identity changes, the active strip fires pause, the paused strip fires resume, and the blocked strip exposes the reason tooltip. Component failure-path cases prove that a failed edit preserves its draft and that edit/resume/clear errors remain visible in the bar. The skeleton specs mount `ConversationRoot` with and without `goalActions`; the undefined case is seeded with an active goal, so the missing gate — not the missing goal — is what hides the strip. Runtime session specs pin the folded-error results, the live-only in-flight-plus-trailing refetch, and the stale-read guard. A keyless real-browser smoke boots the assembled application through `boot → RPC → runtime → GoalBar` and records an inline snapshot of the rendered label, objective, and actions. +`packages/client/ui-goal/tests/goalbar.spec.tsx` pins the behavior through props alone: loading/absent/complete render nothing, the active strip renders label/objective and fires clear, rapid same-frame clear clicks dispatch once and a successful clear hides before projection convergence, the edit form prefills, rejects empty, saves on Enter, cancels on Esc, and resets when the goal's identity changes, the active strip fires pause, the paused strip fires resume, and the blocked strip exposes the reason tooltip. Component failure-path cases prove that a failed edit preserves its draft and that edit/resume/clear errors remain visible and retryable in the bar. The skeleton specs mount `ConversationRoot` with and without `goalActions`; the undefined case is seeded with an active goal, so the missing gate — not the missing goal — is what hides the strip. Runtime session specs pin the folded-error results, the live-only in-flight-plus-trailing refetch, and the stale-read guard. A keyless real-browser smoke boots the assembled application through `boot → RPC → runtime → GoalBar` and records an inline snapshot of the rendered label, objective, and actions. ## Alternatives considered @@ -34,6 +34,7 @@ The strip's background is `--dsw-alias-interactive-bg-hover` rather than the moc ## Consequences - Goal presence in the web UI is a standalone composer-context strip: sparkle, phase label, truncated objective, and pause/edit/clear (resume replacing pause when paused) — the browser client's first goal surface. +- Goal mutations are single-flight within the component; a successful clear hides its exact goal immediately while projection delivery converges, preventing duplicate CAS errors without making transient UI state authoritative. - The runtime session exposes the goal verbs over RPC with folded transport errors, and refreshes the snapshot's goal on open and on live goal-change meta (coalesced, guarded against stale reads). - Objective editing is reachable from the UI for the first time, through `goal.edit` with the runtime-owned ref; complete remains available to other surfaces (`/goal`, model tools). - `goal === null` renders nothing; the composer carries no persistent create affordance — creation is the `/goal` command's job. diff --git a/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.zh.md b/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.zh.md index f62c6efbb2..eb8e3edda5 100644 --- a/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.zh.md +++ b/.agents/notes/implemented/feature/2026-07-22-docked-web-goal-bar.zh.md @@ -10,9 +10,9 @@ Web UI 此前没有任何目标相关的界面：目标栈已随模型工具、T ## 决策 -`GoalBar`（`packages/client/ui-goal/src/client/GoalBar.tsx`）是一个由 props 驱动的自包含组件，在 composer 的 input-dock 列表中注册为第一个条目。它采用独立的 752px 卡片，遵循 composer 的水平几何；所有可见状态均使用固定的 36px 高度，切换阶段不会改变尺寸。加载中（`goal === undefined`）、无目标（`goal === null`）和 `phase === 'complete'` 时不渲染任何内容：已完成的目标是历史记录，不是常驻界面元素。 +`GoalBar`（`packages/client/ui-goal/src/client/GoalBar.tsx`）是一个由 props 驱动的自包含组件，在 composer 的 input-dock 列表中注册为第二个条目，位于 Todo 之后、Queue 之前。它采用独立的 752px 卡片，遵循 composer 的水平几何；所有可见状态均使用固定的 36px 高度，切换阶段不会改变尺寸。加载中（`goal === undefined`）、无目标（`goal === null`）和 `phase === 'complete'` 时不渲染任何内容：已完成的目标是历史记录，不是常驻界面元素。 -可见性决定标签和操作：active 状态显示 "Ongoing Goal" 并提供暂停／编辑／清除；paused 状态显示 "Paused Goal"，把暂停换成一个恢复图标按钮；blocked 状态显示 "Blocked Goal"，并把 `blockedReason.message` 作为横条的 `title` 悬浮提示。创建目标的入口在 `/goal` 命令上，不在横条里。铅笔图标把横条切换为内联编辑表单，预填当前目标内容：Enter 或勾选按钮通过 `GoalBarActions.onEdit(objective)` 保存，Esc 取消，目标内容全为空白字符时保存按钮保持禁用。编辑成功后表单才会关闭；编辑失败时保留草稿，并在横条中显示错误。恢复和清除失败也显示在横条中。除此之外，清除直接调用 `onClear`，不做确认——清除会保留 durable 墓碑，没有不可恢复的损失。一个以目标 id 为键的 effect 会在目标身份变化时丢弃编辑表单，因此存留的草稿绝不可能覆盖掉替换它的新目标。 +可见性决定标签和操作：active 状态显示 "Ongoing Goal" 并提供暂停／编辑／清除；paused 状态显示 "Paused Goal"，把暂停换成一个恢复图标按钮；blocked 状态显示 "Blocked Goal"，并把 `blockedReason.message` 作为横条的 `title` 悬浮提示。创建目标的入口在 `/goal` 命令上，不在横条里。铅笔图标把横条切换为内联编辑表单，预填当前目标内容：Enter 或勾选按钮通过 `GoalBarActions.onEdit(objective)` 保存，Esc 取消，目标内容全为空白字符时保存按钮保持禁用。编辑成功后表单才会关闭；编辑失败时保留草稿，并在横条中显示错误。恢复和清除失败也显示在横条中。除此之外，清除直接调用 `onClear`，不做确认——清除会保留 durable 墓碑，没有不可恢复的损失。每次变更都会先取得一个同步的组件内 single-flight 锁，因为 React 的 pending 状态渲染无法关闭同一帧内的点击窗口。清除成功后还会立即抑制该 goal id，直到权威的 null 投影追上，因此已确认的墓碑不会留下陈旧的清除控件并再次提交 `GOAL_NOT_FOUND`；失败则释放锁，并且仍可重试。一个以目标 id 为键的 effect 会在目标身份变化时重置瞬态状态并丢弃编辑表单，因此无论已清除标记还是存留草稿，都不会影响替换目标。 `GoalBarActions` 位于 ui-goal 的槽位契约（`packages/client/ui-goal/src/client/slots.ts`），只携带实际渲染的动词：`onEdit`/`onPause`/`onResume`/`onClear`。每个回调都会异步返回显式成功／失败结果，因此 `GoalBar` 自行负责界面转换和错误显示。`apply.ts` 把它们接到运行时会话方法上；运行时会话在内部解析当前目标的 compare-and-set ref，因此 UI 不传 ref。 @@ -22,7 +22,7 @@ Web UI 此前没有任何目标相关的界面：目标栈已随模型工具、T ## 测试 -`packages/client/ui-goal/tests/goalbar.spec.tsx` 仅通过 props 固定这些行为：加载中／无目标／已完成时不渲染；active 横条渲染标签和目标内容并触发清除；编辑表单预填内容、拒绝空值、按 Enter 保存、按 Esc 取消，并在目标身份变化时重置；active 横条触发暂停；paused 横条触发恢复；blocked 横条暴露原因悬浮提示。组件失败路径用例证明编辑失败时保留草稿，并且编辑／恢复／清除错误持续显示在横条中。skeleton 规格测试分别挂载带与不带 `goalActions` 的 `ConversationRoot`；未定义的情形预置了一个 active 目标，因此隐藏横条的是缺失的挂载门，而不是缺失的目标。运行时会话规格测试固定了折叠错误结果、仅 live 的执行中读取加尾随读取，以及陈旧读取守卫。一个无密钥真实浏览器冒烟测试通过 `boot → RPC → runtime → GoalBar` 启动组装后的应用，并以内联快照记录渲染出的标签、目标内容和操作。 +`packages/client/ui-goal/tests/goalbar.spec.tsx` 仅通过 props 固定这些行为：加载中／无目标／已完成时不渲染；active 横条渲染标签和目标内容并触发清除；同一帧内快速连续点击清除只会分发一次，清除成功后横条会在投影收敛前隐藏；编辑表单预填内容、拒绝空值、按 Enter 保存、按 Esc 取消，并在目标身份变化时重置；active 横条触发暂停；paused 横条触发恢复；blocked 横条暴露原因悬浮提示。组件失败路径用例证明编辑失败时保留草稿，并且编辑／恢复／清除错误持续显示在横条中且可重试。skeleton 规格测试分别挂载带与不带 `goalActions` 的 `ConversationRoot`；未定义的情形预置了一个 active 目标，因此隐藏横条的是缺失的挂载门，而不是缺失的目标。运行时会话规格测试固定了折叠错误结果、仅 live 的执行中读取加尾随读取，以及陈旧读取守卫。一个无密钥真实浏览器冒烟测试通过 `boot → RPC → runtime → GoalBar` 启动组装后的应用，并以内联快照记录渲染出的标签、目标内容和操作。 ## 考虑过的替代方案 @@ -34,6 +34,7 @@ Web UI 此前没有任何目标相关的界面：目标栈已随模型工具、T ## 后果 - Web UI 中目标的存在形式是独立的 composer 上下文横条：闪光图标、阶段标签、截断的目标内容，以及暂停／编辑／清除（暂停时恢复取代暂停）——这是浏览器客户端的第一个目标界面。 +- 目标变更在组件内走 single-flight；清除成功后会在投影投递收敛期间立即隐藏与其 id 完全匹配的目标，既防止重复 CAS 错误，又不会把瞬态 UI 状态视为权威。 - 运行时会话通过 RPC 暴露目标动词并折叠传输层错误，且在打开时和 live 目标变更元数据到达时刷新快照中的目标（合并拉取，带陈旧读取守卫）。 - 目标内容首次可以从 UI 编辑，经由 `goal.edit`，ref 由运行时持有；完成对其他界面（`/goal`、模型工具）照常可用。 - `goal === null` 时不渲染任何内容；输入框不提供常驻的创建入口，创建是 `/goal` 命令的职责。 diff --git a/.agents/notes/implemented/feature/2026-07-22-durable-subagent-catalog-and-list-agents.i18n.yaml b/.agents/notes/implemented/feature/2026-07-22-durable-subagent-catalog-and-list-agents.i18n.yaml new file mode 100644 index 0000000000..aefda46d41 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-22-durable-subagent-catalog-and-list-agents.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/feature/2026-07-22-durable-subagent-catalog-and-list-agents.md +2026-07-22-durable-subagent-catalog-and-list-agents.md: 0dd7eebac74689004014248c7178dba540ef4662 +2026-07-22-durable-subagent-catalog-and-list-agents.zh.md: 33b0296cf9914d1975fb1dc84564b498a09bd511 diff --git a/.agents/notes/implemented/feature/2026-07-22-durable-subagent-catalog-and-list-agents.md b/.agents/notes/implemented/feature/2026-07-22-durable-subagent-catalog-and-list-agents.md new file mode 100644 index 0000000000..0dd7eebac7 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-22-durable-subagent-catalog-and-list-agents.md @@ -0,0 +1,109 @@ +# Agent Note: Durable subagent catalog and list_agents + +Status: implemented + +English | [中文](2026-07-22-durable-subagent-catalog-and-list-agents.zh.md) + +## Problem + +Continuable background subagents expose a stable child id and persist reconstruction data in that child's session, so `send_message` can resume a known child without any listing operation. Discovery has two consumers with different needs: a UI may show both one-shot work and continuable conversations, while the model should receive only children on which `send_message` is meaningful. The durable Session and Activation design is owned by [continuable subagents](../../implemented/feature/2026-07-28-continuable-subagent-conversations.md); this note owns the shared durable inventory and the model-facing projection. + +Enumeration must cross-check immutable session lineage, descriptor validity, and the live-preferred session corpus without loading or resuming an Agent merely to display it. Trace lineage supplies candidates but cannot distinguish an ordinary session fork from a subagent, so the child log needs durable classification. The contract must also define how lifecycle mode, missing or corrupt records, deletion, unsupported versions, and repeated child-log loads affect service and tool consumers. + +## Decision + +Parent-to-child enumeration is a service capability with consumer-specific projections. `SubagentService.listChildren(parentSessionId: SessionId)` ([subagent/src/index.ts](../../../../packages/subagent/subagent/src/index.ts)) does the following: + +- use `ctx.sessionQuery.traceSession(parentSessionId)` to obtain the parent's direct live-preferred child sessions; +- read and validate each candidate's `subagent/descriptor` event without activating the child; +- silently omit candidates without a descriptor, and omit a candidate that becomes unavailable or has a corrupt or unsupported descriptor with a per-child diagnostic; +- expose every local session-backed subagent whose supported valid descriptor carries a durable creation `label` and `mode`, regardless of whether its provider is currently registered; +- report corpus activity separately as `running` or `inactive`, without implying completion or resumability; +- return every resulting child in stable `createdAt` ascending, child-id ascending order. + +Every ordinary local start receives a `one-shot` descriptor with an optional caller-owned display label, while the continuation manager persists a labeled `continuable` descriptor containing its additional reconstruction fields. The model-facing delegation tool already owns a short `description` and supplies it for one-shot display; lower-level callers such as workflows need not invent presentation metadata. The model-facing `list_agents` adapter filters the service result to continuable children and maps `inactive` to its existing `complete` presentation; a UI can consume both modes and choose an id-based fallback for unlabeled one-shot history. Descriptor persistence, by-id lookup, direct-parent authorization, and provider-independent cold resume remain owned by the implemented Activation contract. Listing consumes those facts but cannot weaken them or invent a second descriptor representation. + +### Enumeration decision + +The first implementation consumes `ctx.sessionQuery.traceSession(parentSessionId)` and considers only the trace's first-level descendants. The target may be live or persisted; tracing the logical corpus does not load or resume an Agent. Session query already merges `ctx.sessions` with `ctx.sessionPersistence` using live precedence, preserves immutable-header consistency, derives direct-child lineage from `SessionHeader.parentSession`, and sorts siblings by `createdAt` ascending and child id ascending. `listChildren()` does not reproduce that corpus logic or inspect the continuation manager's process-local Activation map. + +Corpus construction precedes per-child descriptor inspection. A failure while building the initial trace, including persistence listing failure, a live/persisted header conflict anywhere in the observed corpus, or invalid target lineage, fails the whole `list_agents` call because no trustworthy candidate set exists. Only failures after a successful trace are isolated to one candidate; "corrupt child" in that per-child contract therefore means corrupt loaded event surface or descriptor data, not a corpus-level header conflict. + +Session lineage is broader than subagent identity: an ordinary `ctx.sessions.fork()` also creates a direct child. The session header gains no `kind` discriminator; each candidate must instead contain exactly one valid `subagent/descriptor` event in its own suffix. `SubagentService.start()` resolves `{ mode: 'one-shot', provider, label? }` before ordinary provider dispatch, while the continuation manager snapshots and seeds `{ mode: 'continuable', ...composition }` during initial child creation. The local in-process one-shot driver appends its resolved descriptor only during initial creation, and cold resume appends no further descriptor; a second event is corruption rather than evidence of another Activation. Agent creation is the one-shot publication boundary: a rejection means no child was published, while prompt, turn, cancellation, and infrastructure outcomes after publication settle through the returned run without hiding its id. The descriptor event is the sole evidence that a traced child is a session-backed subagent. A candidate without it is an ordinary fork, a remote child without a local session record, or another non-subagent session and is omitted without a diagnostic. + +The published logical record is also the activity source: `SessionRecord.live` means `running`, while `live: false, persisted: true` means `inactive`. Activity comes directly from the trace and causes no additional child-log load. `inactive` encodes neither successful completion nor resumability: it may describe settled one-shot history or a continuable child for which `send_message` can materialize another Activation. Conversely, `running` says only that the session is live: a live continuable Agent outside the continuation manager's matching Activation still appears as `running`, but `send_message` rejects it as an ownership conflict. A child is not visible before its session is published, and no process-local Activation entry is added as a second candidate or activity source. Listing is a snapshot that may race publication, disposal, or a later message; `send_message` remains the authoritative delivery-time operation. + +The subagent service keeps `sessionQuery` optional so start and follow-up remain available without it. Its public `listChildren(parentSessionId: SessionId)` method resolves the optional service and dynamically loads the optional session-query runtime only when called; ordinary subagent imports, start, and follow-up therefore do not evaluate that package. Listing belongs directly to `SubagentService`: it interprets the query's lineage, events, and live state without resolving the Activation-based continuation manager or consulting Agent registrations, Activations, or providers, so a deployment with sessions, `subagents`, and `sessionQuery` can list even when `agents` is absent. The method throws `SubagentError` with stable code `SUBAGENT_CONTROL_SESSION_QUERY_UNAVAILABLE` before loading the runtime or doing query work when the query service is absent. `@deepseek-ai/dsh-tool-subagent-control` exports separately loadable tool plugins: the `send_message` adapter requires only `subagents`, while the `list_agents` adapter requires both `subagents` and `sessionQuery` at load. A deployment may therefore use `send_message` without installing or loading session query; the list-tool fiber remains inactive until the required service is available, while another direct service consumer receives the same explicit call-time contract. + +`listChildren(parentSessionId, signal?)` forwards the caller's signal to `traceSession()` and the conditional exact `readEvent()` operation. `listEvents()` has no cancellation parameter, so the listing path checks the signal before and after that await and after each candidate settles. If any query operation rejects after the signal aborts, the service normalizes the result to `SubagentError` with stable code `CANCELLED`; a backend abort error or a diagnostic-mapped query error cannot escape or become a successful partial listing. + +This descriptor-read path is the correctness baseline, not a claim that work is linear only in the number of direct children. Let D be the number of direct-child candidates, C be the number of persisted sessions scanned by each persistence listing, and L_i be the size of candidate i's full log. One corpus trace is followed by `sessionQuery.listEvents(childId)` for every candidate. A candidate with no descriptor is omitted, and one with multiple descriptors is diagnosed without another read; only a candidate with exactly one descriptor is loaded again through `sessionQuery.readEvent({ sessionId: childId, seq })`. The read must return the same immutable session header observed by the trace, including the direct-parent relationship, and its target must still be the located descriptor event; a mismatch is per-child corruption. In the persisted-only worst case, each exact read repeats `persistence.list()`, loads the full child log, and clones its events, for O(D × C + Σ L_i) work up to constant factors; a candidate with exactly one descriptor pays those costs twice, while other candidates pay them once. A live candidate similarly takes one detached in-memory snapshot of its full log, or two when its descriptor is read. Session query resolves persisted candidates through the persistence seam's non-mutating `inspect()` read, which returns the valid stored prefix without repairing a torn tail or closing an interrupted turn, so listing is storage-read-only; repair remains the resume path's concern. The first version accepts these repeated reads as the no-index correctness baseline, but deployments must treat total corpus and child-log size—not only direct-child count—as the capacity constraint. Listing creates no Agent and appends no catalog, descriptor, or repair event. The model-hidden descriptor remains outside the conversation surface and survives compaction, so compacted and uncompacted children must enumerate identically. + +If measured scale later requires an index, that index is derived state: session headers and child descriptors remain authoritative, and rebuilding or corruption fallback must reproduce the same results. An index cannot become a second authorization source or make an unpublished child visible. + +### `list_agents` contract + +`SubagentService.listChildren(parentSessionId: SessionId)` returns `Promise`, one array preserving the trace's candidate order rather than separate child and diagnostic arrays. `SubagentListEntry` is a closed union discriminated by its readonly `kind`: + +- `kind: 'child'` carries readonly `id: SessionId`, `mode: 'one-shot' | 'continuable'`, and `activity: 'running' | 'inactive'`; a continuable child carries `label: string`, while a one-shot child carries `label?: string`; +- `kind: 'diagnostic'` carries readonly `id: SessionId` and `reason: 'corrupt' | 'unsupported' | 'unavailable'`. + +A valid descriptor produces one child entry, a per-child inspection failure produces one diagnostic entry, and a candidate without a descriptor produces no entry. `mode` is durable creation policy; `activity` is a process-local corpus snapshot. Activity is neither `AgentStatus`, the manager's internal Activation state, nor a durable outcome, and the result does not expose the internal `createdAt` sorting key. Exact Activation states and durable outcomes such as successful completion, failure, cancellation, and stop reason require a separate durable activation record and are outside this feature. + +The model-facing `list_agents` tool takes no arguments, derives `parentSessionId` from the current execution Agent, and is a thin adapter in `@deepseek-ai/dsh-tool-subagent-control`. It keeps diagnostics, drops `one-shot` child entries, maps a continuable child's `running` activity to `running` and `inactive` activity to `complete`, then renders ` [] —