Merge remote-tracking branch 'origin/master' into worktree/abort-partial-finalize

.agents/notes/archived/manifest.json

@@ -334,6 +334,9 @@
     "simplification/2026-07-02-remove-stream-chunk-mirror.i18n.yaml": "sha256:eef600eafd70a576b2ac16a74f5dd5010ee601376008a90be10f1da56d746cee",
     "simplification/2026-07-02-remove-stream-chunk-mirror.md": "sha256:0c22a896260c6eb8991cc8babd8172f7b6889fc41bb891d748f34650b3eee5ec",
     "simplification/2026-07-02-remove-stream-chunk-mirror.zh.md": "sha256:ae7a3c2450b16fdf2f8da9e1f83cd987bf387671ecc8ebb76d2e7541695e7ee1",
+    "simplification/2026-07-04-drop-image-content-block.i18n.yaml": "sha256:6af8bc85be1fc23b445b17ff96df69488afa82c7194fcb47beb7a6b7b5a1de6a",
+    "simplification/2026-07-04-drop-image-content-block.md": "sha256:31e619d09405044a4db4951084f8d12417868b8f255ca26a44af0a5a13d43e6b",
+    "simplification/2026-07-04-drop-image-content-block.zh.md": "sha256:8fa6558bbb014a38853796102099ffbd5d8151371d68d40b2bf262ad07f4c976",
     "simplification/2026-07-04-drop-inert-request-knobs.i18n.yaml": "sha256:e4c992a27ae0e37e5ef663c2cddf55eefe20387fd6103bebf655834d8e75e9db",
     "simplification/2026-07-04-drop-inert-request-knobs.md": "sha256:8735c2b868a85b13235e0491a0fa7b9570dd090eef5170324fc5e93782687b67",
     "simplification/2026-07-04-drop-inert-request-knobs.zh.md": "sha256:78b243f5d580f2a6fbbdb7d26574295d6ed74feb8d9bba34bbcdf4aa87624b5c",

.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.i18n.yaml → .agents/notes/archived/simplification/2026-07-04-drop-image-content-block.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/simplification/2026-07-04-drop-image-content-block.md
-2026-07-04-drop-image-content-block.md: 5d0357270973ac20234d8ce72c403f27ce2ad0e0
-2026-07-04-drop-image-content-block.zh.md: a13133059cdf4f6e6e8fe44e313a9795a57c10c9
+2026-07-04-drop-image-content-block.md: 362afbbe7c5c1a3b46b1e8abda3b0fec77d1a0e6
+2026-07-04-drop-image-content-block.zh.md: 07fbbd1f165887bf3305ccfa7ba137656ce0a99c

.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.md → .agents/notes/archived/simplification/2026-07-04-drop-image-content-block.md

@@ -1,6 +1,7 @@
 # Agent Note: Drop the `image` content block until a path can honor it
 
 Status: implemented
+Archived: 2026-08-19
 
 English | [中文](2026-07-04-drop-image-content-block.zh.md)
 

.agents/notes/implemented/simplification/2026-07-04-drop-image-content-block.zh.md → .agents/notes/archived/simplification/2026-07-04-drop-image-content-block.zh.md

@@ -1,6 +1,7 @@
 # Agent Note: 移除 `image` 内容块，直到有路径能真正处理它
 
 Status: implemented
+Archived: 2026-08-19
 
 [English](2026-07-04-drop-image-content-block.md) | 中文
 

.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md
-2026-06-11-content-block-vocabulary.md: 5228724bb9101307db9929aaf7831b477c2a6022
-2026-06-11-content-block-vocabulary.zh.md: b43de335917c6b5304a94b296fcb8253827b0600
+2026-06-11-content-block-vocabulary.md: a31df6a7d16ea7cba649702fdb474dab34533c1b
+2026-06-11-content-block-vocabulary.zh.md: 5ac882e9de7dea02cc6534aee99c46869cc9363f

.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.md

@@ -22,7 +22,7 @@ In-session context injection (`context/message`) and mid-turn steering originall
 ## Consequences
 
 - Reasoning has a core home without provider-specific shapes.
-- Multimodal blocks return only with coordinated adapter, UI, and compaction support; see [the drop-image Agent Note](../simplification/2026-07-04-drop-image-content-block.md).
+- Multimodal blocks return only with coordinated adapter, UI, and compaction support; see [the drop-image Agent Note](../../archived/simplification/2026-07-04-drop-image-content-block.md).
 - Cache hints and assistant prefill remain absent until a shipping adapter can honor them; see the [producer-less variants](../../archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md) and [inert request knobs](../../archived/simplification/2026-07-04-drop-inert-request-knobs.md) Agent Notes.
 - Every adapter pays a translation cost; the first real adapters have since validated the streaming protocol, and new adapters should continue proving their provider-specific mapping in adapter-local tests.
 - IDs that cross package boundaries are branded (`CallId`, the shared agent/session `SessionId`) — nominal typing at zero runtime cost.

.agents/notes/implemented/architecture/2026-06-11-content-block-vocabulary.zh.md

@@ -22,7 +22,7 @@ harness 需要一套统一的内部消息语言，供 agent loop（智能体循
 ## 后果
 
 - 推理（reasoning）在核心层有了归属，无需依赖提供方特有的结构。
-- 多模态块只有在适配器、UI 和上下文压缩（context compaction）三方协同支持后才会回归；见 [drop-image Agent Note](../simplification/2026-07-04-drop-image-content-block.md)。
+- 多模态块只有在适配器、UI 和上下文压缩（context compaction）三方协同支持后才会回归；见 [drop-image Agent Note](../../archived/simplification/2026-07-04-drop-image-content-block.md)。
 - 缓存提示与 assistant prefill 在有实际适配器能兑现之前保持缺席；见[无生产者的词汇变体](../../archived/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)与[无端到端可用路径的请求旋钮](../../archived/simplification/2026-07-04-drop-inert-request-knobs.md) Agent Note。
 - 每个适配器都需承担翻译成本；首批真实适配器已验证了流式输出协议，新适配器应继续在适配器本地测试中验证其提供方特有的映射。
 - 跨包边界的 ID 使用品牌类型（`CallId`、agent 与会话共享的 `SessionId`）——零运行时开销的名义类型。

.agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md
-2026-07-10-single-file-executable-sdk-runtime-distribution.md: fa2f86893b730aa1ba020bd568d268ec8d9d6239
-2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: 509bec18edb9923dd4d60d4ecf30d4fbcd9cc6d5
+2026-07-10-single-file-executable-sdk-runtime-distribution.md: 40433d99e5d1aa569c3fdf094a280d3de62ad588
+2026-07-10-single-file-executable-sdk-runtime-distribution.zh.md: 54030fa4b0742fbc282bc327b0ca22747e6a20bd

.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.md
+2026-08-13-feedback-note-editor-popover.md: 33b7cd84b97ceac7fef1d96f1dee279fbb215800
+2026-08-13-feedback-note-editor-popover.zh.md: b130ab1e9c66372cf2a52bc5e12f65027c64cf51

.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.md

@@ -0,0 +1,43 @@
+# Agent Note: The feedback note editor floats above the transcript in a popover
+
+Status: implemented
+
+English | [中文](2026-08-13-feedback-note-editor-popover.zh.md)
+
+## Problem
+
+The Web surface for message feedback ([#2262](https://github.com/deepseek-harness/deepseek-harness/pull/2262)) contributes its controls to `conversation.chat.assistant-actions`, which renders inside the finalized assistant message's shared IconActions row. That row was one fixed-height `flex` line with `flex-wrap` at its initial `nowrap` and `height: 28px`, sized for 28px icons and a clock. The note editor mounted into it as an inline group holding a `width: 260px` textarea plus Save and Cancel.
+
+A 260px input and two buttons do not fit that line at any window size. Measured against the shipped bundle, the row's scrollable overflow with the editor open was 168px at a 1680px viewport and 444px at 600px — the defect was never a narrow-window edge case, it was present at full-screen desktop. Flex overflow spills past the end of the line, so the items after the editor in flex order were the ones pushed out of the conversation column: the branch action left the column at 600px, and the clock and its run/TTFT/throughput readings left it at 900px. Those controls stay hit-testable while invisible, so no behavioral assertion noticed; the shipped e2e covered rate, note, reload, and retract, and the 24 UI snapshots are width-independent DOM.
+
+The same stylesheet also named four `--dsw-alias-*` tokens that the theme does not define: `border-secondary`, `bg-primary`, `interactive-bg-primary`, and `label-inverse`. An undefined custom property makes its whole declaration invalid at computed-value time, so the textarea shipped with no border and no surface, and Save with neither fill nor a readable label — the editor read as loose text floating in the transcript rather than as an input.
+
+## Decision
+
+The note editor does not enter the row's flex layout at all. It is a popover: a fixed-position panel, portaled to `document.body`, whose coordinates come from the note trigger's rect. The row keeps its single line of icons and the note trigger, so nothing has to shrink, wrap, or reflow around the editor, and no `order` or wrapping is needed anywhere. Portaling out of the conversation column also escapes its `overflow` clip, so the panel cannot be cropped at the scroll edge and it moves with the message it annotates when the transcript scrolls. This reuses the same portal mechanism `ui-primitives/Menu` uses for anchored menus (`ui-subagent`'s catalog popover is built on it): the panel is `position: fixed`, placed from the anchor rect on open, clamped inside the viewport, and re-placed on scroll (capture phase) and resize. That anchoring is shared rather than copied: `ui-primitives/useAnchoredPosition` owns measure-offset-clamp-and-track, and the duplication gate is what forced the extraction — an inline copy of the clamp and its listener pair reported a 10-line clone against `Menu`. `Menu` keeps its own effect because its placement also resolves `side`/`align` variants and an optional caller-supplied anchor rect, which this surface does not need; the hook covers the plain below-the-anchor case both would otherwise spell out.
+
+**The action strip.** The like/dislike buttons and the note trigger stay in the row, unchanged. The trigger is a plain button (`aria-haspopup="dialog"`, `aria-expanded` while open) that shows "Add a note" before a note exists and the note text afterward.
+
+**The popover.** While open, the panel contains the textarea plus Save and Cancel, and any note-save failure, as `role="dialog"` with a title distinct from the textarea's own label so both are addressable by name. It opens beneath the trigger (4px gap), clamps to 12px from the viewport edges, auto-focuses the textarea, and closes on Escape or an outside pointer-down. Closing returns focus to the trigger only when the panel was really open, never on the initial mount (a freshly rendered rated message must not pull focus into its action row). A rating action during an open editor closes the panel. The four undefined tokens are replaced with the ones the theme actually defines, matching the primitives' precedent: `border-l2` and `bg-layer-1` for the input, `button-primary-fill` with `label-primary-foreground` plus a `button-primary-hover` state for Save; the panel surface reuses the Menu card recipe (`--dsw-specific-menu`, `--dsw-shadow-lv3`, inverted hairline `--dsw-alias-border-inverted`, `border-radius: 12px`).
+
+**Failure surfaces split by where the human is looking.** A rating or list-load failure shows beside the buttons in the row, legible whether or not the popover is open. A note-save failure shows inside the popover, next to Save/Cancel, and the panel stays open so the draft survives to be corrected.
+
+## Alternatives considered
+
+**Inline expansion on the row, the editor claiming its own line via a full-width flex basis with the row allowed to wrap** — the approach first shipped on this branch and rejected here. It fixes the geometry (the row reports zero overflow from 1680px down to 600px) but at a visible cost: the branch action and the end clock wrap below the editor while it is open, the row occupies three lines, and the interaction competes for the same horizontal strip the row already fills. That cost is what [#2561](https://github.com/deepseek-harness/deepseek-harness/issues/2561) reported from real use — the row reads as misaligned once the editor expands — and it asked for the popover the chat surface already uses. A popover removes the editor from the row entirely, so the strip and the keyboard tab order are untouched whether the editor is open or not.
+
+**An absolutely-positioned popover not portaled out of the column** — rejected: the conversation column is an `overflow-y: auto` scroller, so a panel laid out inside it is clipped at the scroll edge and does not track the message as the column scrolls. Portaling to `document.body` with fixed placement from the trigger rect is what makes the floating panel viable, exactly as `Menu`'s portal mode and the subagent catalog popover already do.
+
+**A new `belowActions` seam on `MessageIconActions`, rendering the editor as a sibling under the row** — rejected: the slot contract documents `assistant-actions` as rendering *inside* the message's IconActions row, and one entry cannot supply two render sites without widening the host contract for a presentation detail that a portaled popover already expresses without touching the host.
+
+## Consequences
+
+With the editor open the actions row stays a single 28px line with zero overflow and nothing outside the column at every viewport from 1680px down to 600px — because the editor is not in the row to begin with. The panel floats above the transcript inside the viewport and stays anchored to its trigger, escaping the column's overflow clip. The editor is legible as an input in both themes.
+
+`apps/web/tests/message-feedback-layout.e2e.ts` sweeps six viewports with the editor open and pins, per stop, that the row reports one line and zero overflow, that the panel is outside the conversation column (proof it escapes the clip), that it lies within the viewport (proof the clamp holds), and that it sits by its trigger. A committed golden records the relations; reverting to inline (or dropping the portal) fails the geometry assertions. `packages/client/ui-message-feedback/tests/styles.client.spec.ts` checks the tokens against the theme's committed source, that the panel is `position: fixed`, and that it carries no flex sizing (so it cannot rejoin the row), plus the brace balance, following the `ui-settings-models` styles-spec precedent. The unit spec covers rate, note, reload, retract, plus the popover's portal-to-body, Escape/outside-click dismissal, and keep-open-on-inside-click.
+
+The `ui-message-feedback` package adds `@types/react-dom` so the `createPortal` usage typechecks, mirroring `ui-primitives`.
+
+Known limitations are accepted rather than fixed here. A rating click while the panel is open closes it, and the close path returns focus to the note trigger rather than leaving it on the rating button the human just pressed; the same happens when an outside click lands on another focusable control, which the browser focuses before the close returns focus to the trigger. A pointer user does not notice either; a keyboard user feels the focus move. The clamp assumes the panel fits: a panel taller than the viewport makes the upper bound `innerHeight - height - margin` smaller than `margin`, so `top` goes negative and the panel's head is cut off rather than its foot. The panel's three-row textarea carries `resize: vertical`, so a human can drag past that size; `.notePanel` therefore bounds its height at `calc(100vh - 24px)` and scrolls its own content, the counterpart of the existing `max-width` and the same 12px margin the clamp uses. If the rating disappears while the editor is open, the panel unmounts on the `rating !== undefined` guard but `noteOpen` stays true, so the document-level Escape and pointer-down listeners remain attached; should the item reappear through a later resync, the panel returns with the previous draft and without refocusing the textarea. The window is one click or Escape wide, and the save failure it could hide already falls back to the row, so it is left as it is. A failure that lands after the panel was closed and reopened is not written into the new session's panel: its draft was reseeded from the stored note, so an old attempt's error would mislabel it, and the uncommitted content is already gone — the failure is dropped rather than shown. And while the placement replays on scroll, window resize, and the panel's own size changes, jsdom has no layout, so the real geometry is proven by the browser scenario while the unit spec covers the wiring through a `ResizeObserver` stub.
+
+A residual narrow-viewport clock overflow remains below 520px from the clock string alone, unrelated to the feedback surface. The repo has no gate for undefined design tokens, and a scan during this work found more in `ui-agent-preset`, `ui-conversation`, `ui-jobs`, `ui-settings-plugins`, and `ui-tool`; they are untouched here and want their own change.

.agents/notes/implemented/bug-fix/2026-08-13-feedback-note-editor-popover.zh.md

@@ -0,0 +1,43 @@
+# Agent Note：反馈备注编辑器以浮层悬浮在对话记录上方
+
+Status: implemented
+
+[English](2026-08-13-feedback-note-editor-popover.md) | 中文
+
+## Problem
+
+消息反馈的 Web 界面（[#2262](https://github.com/deepseek-harness/deepseek-harness/pull/2262)）把控件贡献给 `conversation.chat.assistant-actions`，该槽位渲染在已定稿助手消息共享的 IconActions 行内。那一行是单条固定高度的 `flex` 线，`flex-wrap` 保持初始值 `nowrap` 且 `height: 28px`，按 28px 图标加一个时钟来定尺寸。备注编辑器作为一个内联组挂进去，内含 `width: 260px` 的 textarea 加 Save 与 Cancel。
+
+一个 260px 输入框加两个按钮在任何窗口尺寸下都装不进那条线。对着已构建产物实测，编辑器打开时该行的可滚动溢出在 1680px 视口下是 168px，在 600px 下是 444px——这个缺陷从来不是窄窗口的边缘情况，在全屏桌面下就已存在。flex 溢出会溢出到线的末端之外，因此按 flex 顺序排在编辑器之后的项被挤出会话列：branch 操作在 600px 时离开列，时钟及其运行时长/TTFT/吞吐读数在 900px 时离开列。这些控件在不可见的同时仍可命中测试，所以没有任何行为断言发现它；已交付的 e2e 覆盖评分、备注、reload 与撤回，而 24 个 UI 快照是与宽度无关的 DOM。
+
+同一张样式表还引用了四个主题并未定义的 `--dsw-alias-*` token：`border-secondary`、`bg-primary`、`interactive-bg-primary` 与 `label-inverse`。未定义的自定义属性会让其所在的整条声明在 computed-value 阶段失效，因此 textarea 交付时既无边框也无底色，Save 既无填充也无可读标签——编辑器读起来像是浮在对话记录里的散落文本，而不是一个输入框。
+
+## Decision
+
+备注编辑器完全不进入行的 flex 布局。它是一个浮层：一张固定定位的面板，portal 到 `document.body`，其坐标来自备注触发按钮的矩形。行保持其单行图标与备注触发按钮，因此没有任何东西需要围绕编辑器收缩、换行或回流，任何地方都不需要 `order` 或换行。portal 出会话列也逃出了列的 `overflow` 裁剪，因此面板不会被滚动边缘裁掉，并且当对话记录滚动时会随它所批注的消息一起移动。这里复用 `ui-primitives/Menu` 为锚定菜单所用的同一套 portal 机制（`ui-subagent` 的 catalog popover 就构建在它之上）：面板 `position: fixed`，打开时从 anchor rect 定位，钳制在视口内，并在滚动（捕获阶段）与缩放时重新定位。这套锚定逻辑是共享而非复制的：`ui-primitives/useAnchoredPosition` 持有「测量—偏移—钳制—跟随」这一件事，而促成这次抽取的正是重复代码门禁——内联的钳制与那对监听器被报为与 `Menu` 的 10 行克隆。`Menu` 保留自己的 effect，因为它的定位还要解析 `side`/`align` 变体与可选的调用方 anchor rect，而本界面不需要这些；该 hook 覆盖的是两边本来都要各写一遍的「锚点正下方」这一简单情形。
+
+**操作条。** 点赞/点踩按钮与备注触发按钮保持原样留在行内。触发按钮是普通 `button`（`aria-haspopup="dialog"`，打开时 `aria-expanded`），在没有备注时显示「补充说明」，已有备注时显示备注文本。
+
+**浮层。** 打开时，面板内含 textarea、Save 与 Cancel，以及任何备注保存失败提示，作为 `role="dialog"`，其标题与 textarea 自身的标签不同，以便两者都能按名称寻址。它在触发按钮下方打开（4px 间距），钳制到距视口边缘 12px，自动聚焦 textarea，并在 Escape 或外部 pointer-down 时关闭。关闭时仅当面板确实曾经打开才把焦点还给触发按钮，绝不会在初始挂载时（新渲染出的一条已评分消息不得把焦点拉进其操作条）。编辑器打开时进行评分操作会关闭面板。四个未定义 token 换成主题确实定义的那些，与 primitives 的既有做法一致：输入框用 `border-l2` 与 `bg-layer-1`，Save 用 `button-primary-fill` 配 `label-primary-foreground` 并加 `button-primary-hover` 状态；面板表面复用 Menu 卡片的配方（`--dsw-specific-menu`、`--dsw-shadow-lv3`、反色发丝线 `--dsw-alias-border-inverted`、`border-radius: 12px`）。
+
+**失败提示按人的视线所落之处拆分。** 评分或列表加载失败显示在按钮旁的图标行里，无论浮层是否打开都清晰可读。备注保存失败显示在浮层内、Save/Cancel 旁，且面板保持打开，以便草稿留存待修正。
+
+## Alternatives considered
+
+**行内展开：编辑器通过整行 flex basis 独占一行，并让行允许换行** — 这是本分支最初交付、在此否决的做法。它修好了几何（行在 1680px 到 600px 报告零溢出），但有可见代价：branch 与末尾时钟在编辑器打开时换行到编辑器下方，行占三行，交互与行本就占满的横向条带争空间。这一代价正是 [#2561](https://github.com/deepseek-harness/deepseek-harness/issues/2561) 在真实使用中反馈的问题——编辑器展开后这一行读起来是错位的——并提出改用 chat 界面已有的弹窗。浮层把编辑器完全移出行，因此无论编辑器是否打开，操作条与键盘 Tab 顺序都不受影响。
+
+**不 portal 出列的绝对定位浮层** — 否决：会话列是 `overflow-y: auto` 的滚动容器，因此在列内布局的面板会被滚动边缘裁掉，且不随列滚动而跟住消息。portal 到 `document.body` 并从触发按钮矩形做固定定位，才让浮动面板可行，正如 `Menu` 的 portal 模式与 subagent catalog popover 已然做到的那样。
+
+**在 `MessageIconActions` 上新增 `belowActions` 接缝，把编辑器作为该行的兄弟节点渲染在下方** — 否决：slot 契约明确记载 `assistant-actions` 渲染在消息 IconActions 行**内部**，且单个条目无法在不为一个展示细节拓宽 Host 契约的前提下提供两个渲染点，而 portal 出的浮层无需触碰 Host 就表达了该细节。
+
+## Consequences
+
+编辑器打开时，操作行保持单条 28px 线，在 1680px 到 600px 的每一档视口都零溢出、零项落在列外——因为编辑器本就不在行里。面板悬浮于对话记录之上、位于视口内，并保持锚定其触发按钮，逃出列溢出裁剪。编辑器在两种主题下都能被辨认为输入框。
+
+`apps/web/tests/message-feedback-layout.e2e.ts` 在编辑器打开时扫描六个视口，并在每一档钉住：行报告单行零溢出、面板位于会话列之外（证明它逃出裁剪）、面板落在视口内（证明钳制有效）、面板紧贴其触发按钮。已提交的 golden 记录这些关系；回退到行内（或去掉 portal）会让几何断言失败。`packages/client/ui-message-feedback/tests/styles.client.spec.ts` 校验 token 与主题已提交的源一致、面板为 `position: fixed`、且不带任何 flex sizing（因此不会重新加入行），并校验大括号平衡，沿用 `ui-settings-models` styles spec 的先例。单元 spec 覆盖评分、备注、reload、撤回，外加浮层的 portal 到 body、Escape/外部点击关闭、以及浮层内部点击保持打开。
+
+`ui-message-feedback` 包新增 `@types/react-dom`，使 `createPortal` 用法能通过类型检查，与 `ui-primitives` 一致。
+
+有若干已知限制在此接受而非修复。面板打开时点击评分会关闭它，而关闭路径把焦点归还给备注触发按钮，而不是留在用户刚按下的评分按钮上；外部点击落在另一个可聚焦控件上时同理——浏览器先把焦点给该控件，随后关闭路径又把它拉回触发按钮。指针用户对两者都无感，键盘用户会察觉焦点移动。钳制假定面板放得下：面板高于视口时，上界 `innerHeight - height - margin` 会小于 `margin`，于是 `top` 变为负值、被裁掉的是面板顶部而非底部。面板里的三行 textarea 带 `resize: vertical`，用户可以拖过这个尺寸，因此 `.notePanel` 把自身高度限制在 `calc(100vh - 24px)` 并自行滚动内容——这是既有 `max-width` 的对应项，用的是与钳制相同的 12px 边距。编辑器打开时若评分消失，面板会因 `rating !== undefined` 守卫卸载，但 `noteOpen` 仍为 true，因此 document 级的 Escape 与 pointer-down 监听继续挂着；若该 item 之后经 resync 重新出现，浮层会带着上一次的草稿回来且不重新聚焦 textarea。该窗口只有一次点击或一次 Escape 那么宽，而它可能遮住的保存失败已经有行内回退，因此保持现状。若失败在面板关闭并重开后才到达，不会写入新会话的面板：其草稿已按已存备注重新播种，旧尝试的错误会误标新草稿，而未提交的内容本就不存在——该失败被丢弃而不展示。以及，定位虽然会在滚动、窗口缩放与面板自身尺寸变化时重放，但 jsdom 没有布局，因此真实几何由浏览器场景证明，单测则通过 `ResizeObserver` stub 覆盖其接线。
+
+520px 以下仍残留仅来自时钟字符串的窄视口溢出，与本界面无关。仓库没有针对未定义设计 token 的门禁；本次工作中的一次扫描在 `ui-agent-preset`、`ui-conversation`、`ui-jobs`、`ui-settings-plugins` 与 `ui-tool` 中又发现更多，本次未触碰，需要单独的改动处理。

.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.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/2026-08-18-request-image-payload-bound.md
-2026-08-18-request-image-payload-bound.md: df10df39d18c7da4660b566e8f0b6a5a60ff8dc1
-2026-08-18-request-image-payload-bound.zh.md: 070f2d194f1459f3f2728fdf9d5d2db2c3a24385
+2026-08-18-request-image-payload-bound.md: 0ec4594888db6157fb8cfd3e7bdb231b842d53c1
+2026-08-18-request-image-payload-bound.zh.md: 17b3fbb09be1aff0036c1cec389d8dd75966e010

.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.md

@@ -10,7 +10,7 @@ Every image in session history is base64-inlined into every model request by the
 
 ## Decision
 
-The pi-ai provider profile carries `maxRequestImageBytes` (default `DEFAULT_MAX_REQUEST_IMAGE_BYTES = 20MiB`, a positive integer, per route, changeable from cordis.yml and the `llm-pi-ai` settings section). At request conversion, `toPiContext` sums the base64 length of every image in history (derived from `ImageAttachmentRef.bytes` without reading data) and, while the sum exceeds the bound, replaces the oldest images with a fixed model-facing placeholder. The placeholder tells the model to read the file again when a path is available or ask the user to attach the image again. The most recent images are omitted last; an image larger than the bound is itself omitted. Offload locations use message and nested block indexes rather than object identity, so replaying the same JSON log produces the same request. Offloaded images are never read from the attachment store. `classifyPiAiError` classifies 413 and specific request-body-cap wording as `INVALID_REQUEST` (resending the same body cannot succeed). Four images admitted at the attachment store's 3.5MiB raw-image default occupy at most 18.67MiB after base64 expansion. The 20MiB request-image default therefore retains four such images and reserves the rest of a 32MiB request for system prompts, history, tools, and JSON. Deployments behind stricter gateways lower the value per route.
+The pi-ai provider profile and direct DeepSeek adapter carry `maxRequestImageBytes` (default `DEFAULT_MAX_REQUEST_IMAGE_BYTES = 20MiB`, a positive integer, changeable from cordis.yml and settings). The provider-neutral `offloadRequestImages` conversion sums the base64 length of every image in history from `ImageAttachmentRef.bytes` without reading data and, while the sum exceeds the bound, replaces the oldest image occurrences with a fixed model-facing placeholder. The placeholder tells the model to read the file again when a path is available or ask the user to attach the image again. The most recent images are omitted last; an image larger than the bound is itself omitted. Occurrence-order replacement does not depend on object identity, so replaying the same JSON log produces the same request. Offloaded images are never read from the attachment store. Both adapters classify 413 as `INVALID_REQUEST`; pi-ai also recognizes specific request-body-cap wording. Four images admitted at the attachment store's 3.5MiB raw-image default occupy at most 18.67MiB after base64 expansion. The 20MiB default therefore retains four such images and leaves headroom under the direct API's 30MiB request limit, while deployments behind stricter gateways lower the value per route.
 
 ## Offload is conversion, not history
 
@@ -26,6 +26,7 @@ The placeholder is model-visible but not logged as a session event. It stays wit
 ## Related
 
 - [Per-side image dimension admission limit](2026-08-17-image-dimension-admission-limit.md) — the admission-layer companion fix; together they close the two observed session-poisoning failures (400 dimension, 413 body size).
+- [Direct DeepSeek vision input](../feature/2026-08-19-direct-deepseek-vision-input.md) — applies this provider-neutral conversion to the official multimodal route.
 
 ## Consequences
 

.agents/notes/implemented/bug-fix/2026-08-18-request-image-payload-bound.zh.md

@@ -10,7 +10,7 @@ pi-ai 适配器把会话历史中的每张图片 base64 内联进每一个模型
 
 ## Decision
 
-pi-ai provider profile 增加 `maxRequestImageBytes`（默认 `DEFAULT_MAX_REQUEST_IMAGE_BYTES = 20MiB`，正整数，按路由生效，可从 cordis.yml 与 `llm-pi-ai` settings 段修改）。请求转换时，`toPiContext` 由 `ImageAttachmentRef.bytes` 推算每张历史图片的 base64 长度（无需读取数据）求和，总和超过上限时从最老的图片开始替换为一段固定的模型可见占位文本。占位文本要求模型在有路径时重新读取文件，否则请用户重新附上图片。越新的图片越晚被省略；单张图片本身超过上限时也会被省略。offload 位置用消息与嵌套块的索引表示，不依赖对象身份，因此重放同一份 JSON 日志会产生相同请求。被 offload 的图片不会从附件存储读取。`classifyPiAiError` 把 413 与明确的请求体上限措辞归类为 `INVALID_REQUEST`（原样重发不可能成功）。四张按附件存储默认上限准入的 3.5MiB 原始图片，经 base64 膨胀后最多占 18.67MiB。20MiB 请求图片默认上限因此可保留四张这样的图片，并在 32MiB 请求内为系统提示词、历史、工具与 JSON 保留其余容量。网关更严格的部署按路由调低该值。
+pi-ai provider profile 与直接 DeepSeek 适配器都提供 `maxRequestImageBytes`（默认 `DEFAULT_MAX_REQUEST_IMAGE_BYTES = 20MiB`，正整数，可从 cordis.yml 与 settings 修改）。提供方无关的 `offloadRequestImages` 转换由 `ImageAttachmentRef.bytes` 推算每张历史图片的 base64 长度（无需读取数据）求和，总和超过上限时从最老的图片出现位置开始替换为一段固定的模型可见占位文本。占位文本要求模型在有路径时重新读取文件，否则请用户重新附上图片。越新的图片越晚被省略；单张图片本身超过上限时也会被省略。按出现顺序替换不依赖对象身份，因此重放同一份 JSON 日志会产生相同请求。被 offload 的图片不会从附件存储读取。两个适配器都把 413 归类为 `INVALID_REQUEST`；pi-ai 还会识别明确的请求体上限措辞。四张按附件存储默认上限准入的 3.5MiB 原始图片，经 base64 膨胀后最多占 18.67MiB。20MiB 默认上限因此可保留四张这样的图片，并在直接 API 的 30MiB 请求上限下留出余量；网关更严格的部署则按路由调低该值。
 
 ## offload 是转换而非历史
 
@@ -26,6 +26,7 @@ pi-ai provider profile 增加 `maxRequestImageBytes`（默认 `DEFAULT_MAX_REQUE
 ## Related
 
 - [图片单边尺寸准入上限](2026-08-17-image-dimension-admission-limit.md)，准入层的配套修复；两者合起来封住已观测到的两类会话毒化故障（400 尺寸、413 请求体）。
+- [直接 DeepSeek 视觉输入](../feature/2026-08-19-direct-deepseek-vision-input.md)把这项提供方无关转换应用于官方多模态路由。
 
 ## Consequences
 

.agents/notes/implemented/bug-fix/2026-08-18-tool-row-file-open-failure.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/2026-08-18-tool-row-file-open-failure.md
+2026-08-18-tool-row-file-open-failure.md: e36552395b992e688fad35b3163b92c9f6189e43
+2026-08-18-tool-row-file-open-failure.zh.md: 72b6026d9eb44c74f13c987996e652008f35a78e

.agents/notes/implemented/bug-fix/2026-08-18-tool-row-file-open-failure.md

@@ -0,0 +1,33 @@
+# Agent Note: Tool-row file-open failures stay visible
+
+Status: implemented
+
+English | [中文](2026-08-18-tool-row-file-open-failure.zh.md)
+
+## Problem
+
+Tool-row path clicks already call `host.openPath` through the chat view's injected `openFile`. The inject swallowed every Host or OS refusal, so a missing desktop opener, a remote or non-loopback carrier, or a path the Host cannot hand off left the row looking successful. The reader had no reason and no second try.
+
+The [file-open-in-OS decision](../feature/2026-07-28-tool-call-file-open-in-os.md) still owns the link gesture and the Host handoff. This note owns only the refusal.
+
+## Decision
+
+The inject returns the `workspaces.openPath` promise. The chat view wraps that opener: a rejection opens an in-page Modal with the thrown text (or the unknown-open fallback when that text is empty) and a Retry that repeats the same path; Cancel, Escape, the close control, and a mask click dismiss it. A later settlement after dismiss is ignored, so a cancelled in-flight refusal cannot reopen the dialog.
+
+The dialog lives on the view that owns the Host call, not on each tool row. Produced-file chips and closing-message mentions use the same wrapper because they already share that opener. The produced-files folder action opens `.`, and that refusal uses the folder title and unknown-open copy.
+
+The Host message is shown as thrown. `WorkspaceRuntime.openPath` prefixes `path open failed: ` onto the wire error; the dialog does not unwrap that prefix.
+
+## Alternatives considered
+
+- **Per-row inline error.** The Host call is conversation-owned and several entries share one opener; a row-local banner would duplicate the same refusal next to every click target.
+- **Toast without retry.** The product ask is the reason *and* a retry entry. The workspace folder-adoption dialog already pairs those two.
+- **Chat-store remount persistence.** A failed open is transient view state. The chat store survives view remounts, so a leftover dialog would return after a tab switch that cannot usefully retry the original gesture.
+
+## Consequences
+
+A silent Host refusal is no longer a success from the reader's seat. Headless or remote deployments that click a path now see why the desktop handoff did not happen. The view holds one extra request-generation counter so dismiss and retry stay race-safe.
+
+## Testing
+
+Package specs cover inject rejection, the dialog copy (Error, non-Error, empty, workspace folder), retry of the same path, cancel, and a settlement that arrives after dismiss. `apps/web/tests/seeded-history.e2e.ts` stubs `host.openPath` to fail over a cold-resumed read row, pins the assembled dialog in `file-open-failure.expected.md`, and asserts the English reason plus a second call with the same payload.

.agents/notes/implemented/bug-fix/2026-08-18-tool-row-file-open-failure.zh.md

@@ -0,0 +1,33 @@
+# Agent Note: Tool-row file-open failures stay visible
+
+Status: implemented
+
+[English](2026-08-18-tool-row-file-open-failure.md) | 中文
+
+## 问题
+
+工具行路径点击已经通过聊天视图注入的 `openFile` 调用 `host.openPath`。inject 吞掉了每一次 Host 或操作系统拒绝，因此缺少桌面打开器、远程或非回环载体、或 Host 无法交接的路径，都会让该行看起来像成功。读者看不到原因，也无法再试一次。
+
+[用系统应用打开文件的决策](../feature/2026-07-28-tool-call-file-open-in-os.md) 仍然拥有链接手势和 Host 交接。本 Agent Note 只拥有拒绝路径。
+
+## 决策
+
+inject 返回 `workspaces.openPath` 的 promise。聊天视图包装该打开器：拒绝时打开页面内 Modal，展示抛出的文本（文本为空时用未知打开回退文案），并提供对同一路径的重试；取消、Escape、关闭控件和点击遮罩会关掉对话框。关闭之后才落到的结果会被忽略，因此已取消的进行中拒绝不能再次打开对话框。
+
+对话框位于 chat 视图（拥有 Host 调用），而不是每个工具行。产物文件标签和收尾消息中的提及已经共用该打开器，因此走同一包装。产物文件的文件夹操作打开 `.`，该拒绝使用文件夹标题和未知打开回退文案。
+
+Host 消息按抛出内容展示。`WorkspaceRuntime.openPath` 会在 wire 错误前加上 `path open failed: ` 前缀；对话框不拆掉该前缀。
+
+## 考虑过的替代方案
+
+- **按行内联错误。** Host 调用由会话拥有，多个入口共用一个打开器；行内横幅会在每个点击目标旁重复同一拒绝。
+- **没有重试的 toast。** 产品要求同时给出原因和重试入口。工作区文件夹采纳对话框已经把这两者配对。
+- **写入 chat store 并跨 remount 保留。** 打开失败是瞬时视图状态。chat store 会在视图 remount 后存活，于是残留对话框会在无法有效重试原手势的页签切换之后回来。
+
+## 后果
+
+从读者一侧看，静默的 Host 拒绝不再等同于成功。无头或远程部署点击路径时，能看到桌面交接为何没有发生。视图多持有一个请求世代计数器，使关闭与重试在竞态下仍然安全。
+
+## 测试
+
+包测试覆盖 inject 拒绝、对话框文案（Error、非 Error、空文本、工作区文件夹）、同一路径重试、取消，以及关闭之后才落到的结果。`apps/web/tests/seeded-history.e2e.ts` 在冷恢复的 read 行上把 `host.openPath` stub 为失败，用 `file-open-failure.expected.md` 钉住组装后的对话框，并断言英文原因以及对同一 payload 的第二次调用。

.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.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-web-multimodal-image-input-and-durable-attachments.md
-2026-07-22-web-multimodal-image-input-and-durable-attachments.md: 6a12380992c3205d6bb3f5701f093b3335fae2f9
-2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md: a8e94154e435a5359e7928d3b11eba7d1aee92f7
+2026-07-22-web-multimodal-image-input-and-durable-attachments.md: 83293fbe9bd4e8a7b4422dbbe8495cf9f48bcdb5
+2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md: 5c524da9cbed7b330c3823812c8a71aed7aa74b0

.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.md

@@ -8,7 +8,7 @@ English | [中文](2026-07-22-web-multimodal-image-input-and-durable-attachments
 
 Before this change, the Web composer accepted only text: `InputBar` received a string draft, `ConversationController.send()` created text content, and the host forwarded that content to the agent. Users could not paste an image, inspect it before sending, submit an image-only prompt, or recover sent images from history.
 
-This is not only a composer gap. Core needs a durable image content block, providers need explicit modality handling, and the session log must reconstruct everything visible to a model. [The previous image-block removal](../../implemented/simplification/2026-07-04-drop-image-content-block.md) rejected a partial design that could silently lose or flatten images. A browser object URL, local path, provider URL, or base64 payload cannot be canonical session content.
+This is not only a composer gap. Core needs a durable image content block, providers need explicit modality handling, and the session log must reconstruct everything visible to a model. [The previous image-block removal](../../archived/simplification/2026-07-04-drop-image-content-block.md) rejected a partial design that could silently lose or flatten images. A browser object URL, local path, provider URL, or base64 payload cannot be canonical session content.
 
 The [Web client architecture](../../implemented/architecture/2026-07-19-gui-web-client-architecture.md) keeps components pure and per-session composer state in `ctx.conversation`; the [GUI layering and RPC protocol](../../implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md) makes durable events the source of truth for both live rendering and history replay. Image intake, persistence, provider conversion, and rendering therefore need one explicit lifecycle.
 
@@ -124,7 +124,7 @@ Model catalog entries gain optional merge-extensible input modality declarations
 
 The host is the authoritative preflight boundary. It resolves the session's latest routed provider/model, falling back through agent options to host defaults; if that model explicitly excludes image input, it rejects the prompt before writing any attachment or event, and the client restores the draft. Image-bearing prompt admission and model selection share one per-agent serial boundary, and a dequeued prompt remains pending until its durable message event publishes ([ordering decision](../bug-fix/2026-07-29-atomic-web-image-admission.md)); a steering carrier gates from its enqueue until its `steering/message` event publishes, closing the outbox hop that never enters the queued mirror. Selection rejects a text-only target while an image is pending publication or remains in the session's current derived history. Compaction can remove old images and make a later text-only selection valid; idle without publication releases a claimed queued carrier, while steering retained in the outbox stays gated until publication or discard. `session.updateQueue` edits accept text content only, so a queue edit cannot inject an image past this admission boundary. Unknown capability proceeds to the adapter guard so uncatalogued model identifiers remain usable. The browser rejects unsupported declared image media types before allocating preview URLs, but it does not snapshot deployment limits or model capability: a handshake snapshot cannot represent a session's current target after `session.selectModel`, and deployment policy may change independently. The host validates the complete batch against current byte, count, aggregate, media, dimension, pixel, and routed-model policy before writing any attachment or event; its rejection announces through the composer's transient toast.
 
-The Pi-AI adapter is the first visual-input route: it resolves `ctx.attachments` at request time, recursively converts each durable image reference including references nested inside tool results, and emits native image content only for models that declare image input. The shipped composition registers Pi-AI OpenAI and Anthropic routes alongside the text-only default DeepSeek route; selecting the active provider/model remains a host composition or profile concern rather than an image-input CLI feature. Request-time service resolution keeps Cordis load order from freezing optional attachment availability. The hand-written DeepSeek adapter throws typed `UNSUPPORTED_CONTENT` for an image anywhere in the request, including nested tool results. No adapter may flatten or skip an image.
+Pi-AI and the direct DeepSeek adapter resolve `ctx.attachments` at request time, recursively convert each durable image reference including references nested inside tool results, and emit native image content only for models that declare image input. The direct route accepts configured image-capable catalog entries but does not advertise a vision model until its endpoint is ready; its Flash, Pro, custom models without an image declaration, and unlisted pass-through ids remain text-only. Request-time service resolution keeps Cordis load order from freezing optional attachment availability. No adapter may flatten or skip a retained image; unsupported roles and models fail with typed `UNSUPPORTED_CONTENT`.
 
 Core supports structured assistant image blocks, but no current production provider route is certified for image output. Any future output-capable adapter must retrieve provider bytes under bounded size and time policy, validate them through the same attachment service, persist them, and only then publish the atomic `ImageBlock`. A URL in assistant Markdown remains text and is never downloaded automatically.
 
@@ -152,7 +152,7 @@ Malformed base64, unsupported or mismatched media, truncated image payloads, exc
 | `packages/attachment/attachment-local` | Private content-addressed storage, complete raster decoding, integrity verification, and configuration. |
 | `packages/llm/llm` | Role-neutral `ImageBlock` and input-modality metadata. |
 | `packages/llm/llm-pi-ai` | Resolve durable supported image input into native provider content. |
-| `packages/llm/llm-deepseek` | Reject image content explicitly. |
+| `packages/llm/llm-deepseek` | Resolve declared official vision input and reject images for text-only models. |
 | `packages/compaction/compaction-basic` | Preserve images in summary input and reject non-text checkpoint output explicitly. |
 | `packages/host/apiproxy` and `packages/bundle/base` | Narrow upload wire, shared batch admission, limits and routed-model preflight, persist-before-event ordering, session-authorized reads, and default profile composition. |
 | `packages/client/connection` and `packages/client/runtime` | Bounded request buffering, wire types, fixture images, prompt uploads, attachment reads, and durable-reference folding. |
@@ -165,7 +165,7 @@ The attachment packages form the interface/implementation side of one capability
 
 ### Implementation
 
-The implemented slice includes the attachment seam and shared batch admission, role-neutral image block, Pi-AI input conversion, DeepSeek rejection, durable Web/ACP/MCP ordering, Web upload/read protocol, conditional ACP image wire support, lossless MCP canonical results with durable image projection, generic Code Mode rich-result forwarding, current image-limit enforcement, bounded Web request bodies, in-memory draft images, paste/drop rail, user and assistant history rendering, single-click preview, compaction handling, and keyless assembled Web and ACP coverage.
+The implemented slice includes the attachment seam and shared batch admission, role-neutral image block, Pi-AI and direct DeepSeek input conversion, durable Web/ACP/MCP ordering, Web upload/read protocol, conditional ACP image wire support, lossless MCP canonical results with durable image projection, generic Code Mode rich-result forwarding, current image-limit enforcement, bounded Web request bodies, in-memory draft images, paste/drop rail, user and assistant history rendering, single-click preview, compaction handling, and keyless assembled Web and ACP coverage.
 
 No compatibility shim is required for the pre-release prompt wire; all call sites and fixtures change with the introducing slice.
 

.agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md

@@ -8,7 +8,7 @@ Status: implemented
 
 在此变更之前，Web 输入区仅接受文本：`InputBar` 接收字符串草稿，`ConversationController.send()` 创建文本内容，宿主再把该内容转发给 agent（智能体）。用户无法粘贴图片、在发送前查看图片、提交仅含图片的提示词，也无法从历史记录中恢复已发送图片。
 
-这不只是输入区功能缺失。核心层需要持久图片内容块，提供方需要明确处理模态，会话日志则必须重建模型可见的全部内容。[此前移除图片块的决策](../../implemented/simplification/2026-07-04-drop-image-content-block.md)否决了可能静默丢失图片或将其展平的不完整设计。浏览器对象 URL、本地路径、提供方 URL 或 base64 数据都不能成为规范会话内容。
+这不只是输入区功能缺失。核心层需要持久图片内容块，提供方需要明确处理模态，会话日志则必须重建模型可见的全部内容。[此前移除图片块的决策](../../archived/simplification/2026-07-04-drop-image-content-block.md)否决了可能静默丢失图片或将其展平的不完整设计。浏览器对象 URL、本地路径、提供方 URL 或 base64 数据都不能成为规范会话内容。
 
 [Web 客户端架构](../../implemented/architecture/2026-07-19-gui-web-client-architecture.md)要求组件保持纯粹，并将每个会话的输入区状态放在 `ctx.conversation` 中；[GUI 分层与 RPC 协议](../../implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md)则要求持久事件成为实时渲染与历史回放的共同真源。因此，图片接收、持久化、提供方转换和渲染需要遵循同一个明确的生命周期。
 
@@ -124,7 +124,7 @@ Base64 只跨越一次协议边界，并在持久化后丢弃。每个入口都
 
 宿主是权威的前置检查边界。它会解析会话最新路由到的提供方和模型，并在缺失时依次回退到 agent 选项和宿主默认值；如果该模型明确排除图片输入，宿主会在写入任何附件或事件前拒绝提示词，客户端则恢复草稿。包含图片的提示词准入与模型选择共用一个逐 agent 的串行边界，而且已经出队的提示词在其持久消息事件发布前仍保持待发布状态（[顺序决策](../bug-fix/2026-07-29-atomic-web-image-admission.md)）；steering 载体则从入队起就参与门槛，直到其 `steering/message` 事件发布为止，堵住了从不进入排队镜像的 outbox 窗口。当图片正等待发布或仍存在于会话当前的派生历史中时，模型选择会拒绝纯文本目标。压缩（compaction）可以移除旧图片，使之后选择纯文本目标变得有效；未发布任何事件即转入空闲时，已认领的 queued 载体会被释放，而保留在 outbox 中的 steering 在发布或丢弃前始终受门槛约束。`session.updateQueue` 的编辑只接受文本内容，因此队列编辑无法绕过该准入边界注入图片。能力未知时继续进入适配器强制检查，使未收录的模型标识符仍然可用。浏览器会在分配预览 URL 前拒绝声明不支持的图片媒体类型，但不会为部署限制或模型能力保留快照：握手快照无法表达 `session.selectModel` 之后会话的当前目标，部署策略也可能独立变化。宿主会根据当前的单张字节数、图片数量、总字节数、媒体类型、尺寸、像素数和路由模型策略校验整个批次，再写入任何附件或事件；其拒绝通过 composer 的短时 toast 播报。
 
-Pi-AI 适配器是首条视觉输入路径：它在请求时解析 `ctx.attachments`，递归转换每个持久图片引用，包括嵌套在工具结果中的引用，并且仅为声明支持图片输入的模型生成提供方原生图片内容。交付的组合会同时注册 Pi-AI OpenAI、Anthropic 路由和仅支持文本的默认 DeepSeek 路由；选择当前提供方／模型仍由宿主组合或配置承担，而不是图片输入 CLI（命令行界面）的功能。在请求时解析服务，可避免 Cordis 加载顺序将可选附件服务的可用性固化。手写 DeepSeek 适配器遇到请求中任何位置的图片时都会抛出类型化的 `UNSUPPORTED_CONTENT` 错误，包括嵌套工具结果中的图片。任何适配器都不得将图片展平或跳过。
+Pi-AI 与直接 DeepSeek 适配器都会在请求时解析 `ctx.attachments`，递归转换每个持久图片引用，包括嵌套在工具结果中的引用，并且仅为声明支持图片输入的模型生成提供方原生图片内容。直接路由接受已配置且支持图片的 catalog 配置项，但在视觉模型端点就绪前不会公布视觉模型；其 Flash、Pro、未声明图片能力的自定义模型和未列出原样传递 id 仍仅支持文本。在请求时解析服务，可避免 Cordis 加载顺序将可选附件服务的可用性固化。任何适配器都不得将保留的图片展平或跳过；不支持的角色与模型会以类型化的 `UNSUPPORTED_CONTENT` 失败。
 
 核心层支持结构化助手图片块，但当前没有任何生产提供方路径通过图片输出认证。未来任何支持输出的适配器都必须在有界的大小和时间策略下获取提供方字节，通过同一个附件服务校验并持久化字节，之后才能以原子方式发布 `ImageBlock`。助手 Markdown 中的 URL 仍是文本，绝不自动下载。
 
@@ -152,7 +152,7 @@ Pi-AI 适配器是首条视觉输入路径：它在请求时解析 `ctx.attachme
 | `packages/attachment/attachment-local` | 私有内容寻址存储、完整光栅解码、完整性校验和配置。 |
 | `packages/llm/llm` | 角色无关的 `ImageBlock` 和输入模态元数据。 |
 | `packages/llm/llm-pi-ai` | 将持久且受支持的图片输入解析为提供方原生内容。 |
-| `packages/llm/llm-deepseek` | 明确拒绝图片内容。 |
+| `packages/llm/llm-deepseek` | 解析已声明的官方视觉输入，并拒绝纯文本模型的图片。 |
 | `packages/compaction/compaction-basic` | 在摘要输入中保留图片，并明确拒绝非文本检查点输出。 |
 | `packages/host/apiproxy` 和 `packages/bundle/base` | 范围狭窄的上传协议、共享批量准入、限制和路由模型前置检查、先持久化再追加事件的顺序、会话授权读取，以及默认 profile 组合。 |
 | `packages/client/connection` 和 `packages/client/runtime` | 有界请求缓冲、协议类型、fixture（测试前置数据）图片、提示词上传、附件读取和持久引用折叠。 |
@@ -165,7 +165,7 @@ Pi-AI 适配器是首条视觉输入路径：它在请求时解析 `ctx.attachme
 
 ### 实现
 
-已实现的范围包括附件服务边界与共享批量准入、角色无关的图片块、Pi-AI 输入转换、DeepSeek 拒绝、Web／ACP／MCP 的持久化顺序、Web 上传与读取协议、条件式 ACP 图片协议支持、无损 MCP 规范结果与持久图片投影、通用 Code Mode 丰富结果转发、当前图片限制执行、大小受限的 Web 请求体、内存草稿图片、粘贴与拖放附件栏、用户与助手历史图片渲染、单击预览、压缩处理，以及组装后无需密钥的 Web 与 ACP 覆盖。
+已实现的范围包括附件服务边界与共享批量准入、角色无关的图片块、Pi-AI 与直接 DeepSeek 输入转换、Web／ACP／MCP 的持久化顺序、Web 上传与读取协议、条件式 ACP 图片协议支持、无损 MCP 规范结果与持久图片投影、通用 Code Mode 丰富结果转发、当前图片限制执行、大小受限的 Web 请求体、内存草稿图片、粘贴与拖放附件栏、用户与助手历史图片渲染、单击预览、压缩处理，以及组装后无需密钥的 Web 与 ACP 覆盖。
 
 预发布提示词协议不需要兼容包装层；引入相应切片时会同时修改所有调用点和 fixture。
 

.agents/notes/implemented/feature/2026-07-28-tool-call-file-open-in-os.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-tool-call-file-open-in-os.md
-2026-07-28-tool-call-file-open-in-os.md: d78cf4da2c1861a66a0cefb24dba785c7cb1279d
-2026-07-28-tool-call-file-open-in-os.zh.md: c13f6e60c0c70a3036f50c678c7b348c91f874c3
+2026-07-28-tool-call-file-open-in-os.md: 08fc51cc3a5d2fb43b67dc158fd1ee789fafdb68
+2026-07-28-tool-call-file-open-in-os.zh.md: 59079533b502d234bafb0b53c123e5895e105833

.agents/notes/implemented/feature/2026-07-28-tool-call-file-open-in-os.md

@@ -23,9 +23,9 @@ File-tool path summaries (`read` / `write` / `edit` args carrying `path` or `fil
 
 ## Consequences
 
-Clicking a file path in a tool row opens that path on the host. Non-file tool rows are inert summaries (expand toggles remain where the row already supported them). Remote or non-loopback clients cannot invoke `host.openPath`.
+Clicking a file path in a tool row opens that path on the host. Non-file tool rows are inert summaries (expand toggles remain where the row already supported them). Remote or non-loopback clients cannot invoke `host.openPath`. A Host or OS refusal is owned by the chat view: it shows the thrown reason and retries the same path ([file-open failure](../bug-fix/2026-08-18-tool-row-file-open-failure.md)).
 
 ## Risks
 
-- Desktop Linux hosts without `xdg-open`, and WSL hosts without working Windows interop (`wslpath` plus `powershell.exe`), fail the RPC; the chat row stays silent while the host returns an internal error.
+- Desktop Linux hosts without `xdg-open`, and WSL hosts without working Windows interop (`wslpath` plus `powershell.exe`), fail the RPC; the chat view shows that Host error and offers retry.
 - Relative paths without a session cwd are forwarded verbatim and may fail on the host.

.agents/notes/implemented/feature/2026-07-28-tool-call-file-open-in-os.zh.md

@@ -23,9 +23,9 @@ Status: implemented
 
 ## 后果
 
-点击工具行中的文件路径会在宿主上打开该路径。非文件工具行只是不可交互的摘要（行内已有的展开开关仍保留）。远程或非回环客户端无法调用 `host.openPath`。
+点击工具行中的文件路径会在宿主上打开该路径。非文件工具行只是不可交互的摘要（行内已有的展开开关仍保留）。远程或非回环客户端无法调用 `host.openPath`。Host 或操作系统拒绝由聊天视图拥有：它展示抛出的原因，并对同一路径提供重试（[打开失败](../bug-fix/2026-08-18-tool-row-file-open-failure.md)）。
 
 ## 风险
 
-- 没有 `xdg-open` 的桌面 Linux 宿主，以及 Windows 互操作（`wslpath` 加 `powershell.exe`）不可用的 WSL 宿主，会使 RPC 失败；聊天行保持静默，宿主返回内部错误。
+- 没有 `xdg-open` 的桌面 Linux 宿主，以及 Windows 互操作（`wslpath` 加 `powershell.exe`）不可用的 WSL 宿主，会使 RPC 失败；聊天视图展示该 Host 错误并提供重试。
 - 没有会话 cwd 时相对路径会原样转发，可能在宿主侧失败。

.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.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/2026-08-04-claude-code-and-codex-subagent-backends.md
-2026-08-04-claude-code-and-codex-subagent-backends.md: a8f500c7fb934b8634456e1618498909f682f0e2
-2026-08-04-claude-code-and-codex-subagent-backends.zh.md: ca35c38617b1ca38757959735b11618559f6f804
+2026-08-04-claude-code-and-codex-subagent-backends.md: 9b47fcf49d47d2c3561245fa1e16ff8c5da0a35c
+2026-08-04-claude-code-and-codex-subagent-backends.zh.md: fcb1aac71be2da9d907ad67867c763e3051baec5

.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md

@@ -12,7 +12,7 @@ The product integrations must not become second owners for task text, cwd, cance
 
 ## Decision
 
-The harness publishes two sibling one-shot provider packages whose default registry names are `codex` and `claude-code`. This note owns their product protocols, result mapping, and process lifecycle; the [named-instance decision](2026-08-18-product-subagent-named-instances.md) owns Profile-selected provider identity and static tool binding, the [production-install exclusion decision](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md) owns their independent optional Bundles and host-plane placement, the [product one-shot background decision](2026-08-12-product-subagent-one-shot-background-tasks.md) owns the model-visible scheduling choice, and the [non-interactive permissions decision](2026-08-15-product-subagent-noninteractive-permissions.md) owns each product Provider's Profile-selected mode and diagnostic production. Both packages accept multiple named instances. Loading either provider starts no product process, and each tool accepts only a standalone text task; product and instance selection remain deployment configuration.
+The harness publishes two sibling one-shot provider packages whose default registry names are `codex` and `claude-code`. This note owns their product protocols, result mapping, and process lifecycle; the [named-instance decision](2026-08-18-product-subagent-named-instances.md) owns Profile-selected provider identity and static tool binding, the [production-install exclusion decision](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md) owns their independent optional Bundles and host-plane placement, the [product one-shot background decision](2026-08-12-product-subagent-one-shot-background-tasks.md) owns the model-visible scheduling choice, the [non-interactive permissions decision](2026-08-15-product-subagent-noninteractive-permissions.md) owns each product Provider's Profile-selected mode and safe permission decisions, and the [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns version-pinned product categories, lifecycle stages, and process outcomes exposed through the same diagnostic. Both packages accept multiple named instances. Loading either provider starts no product process, and each tool accepts only a standalone text task; product and instance selection remain deployment configuration.
 
 Both providers report `inheritsParentContext: false`, advertise no optional start capabilities, and pass the parent Session cwd without copying the parent conversation. Their documented tools use `backgroundMode: 'one-shot'` and `maxDepth: 'provider-managed'`: the consumer keeps foreground collection as the default and may place the same run in the generic Job runtime, while recursion policy stays with the out-of-process product. Every call creates a fresh product process and a non-resumable product conversation. `ctx.subagents` owns named-request resolution and paired lifecycle events; `dsh-tool-subagent` owns model-visible scheduling and foreground-versus-Job adaptation; `ctx.jobs` and `dsh-tool-jobs` own Job ids, state, output, controls, notices, and parent-owner cancellation; each product provider owns native result mapping, while `dsh-subprocess` owns credential scrubbing, process-tree termination, and whole-tree exit observation.
 
@@ -38,11 +38,11 @@ configured tool -> dsh-tool-subagent -> ctx.subagents -> product provider -> pro
 
 Before publication, the provider validates a non-empty text-only task, starts the managed app-server in the parent workspace, completes `initialize` → `initialized`, maps the resolved mode into official `thread/start` fields, and creates an `ephemeral: true` thread. The fixed app-server argv contains no mode or task text. The published run owns exactly one `turn/start`; its thread and turn ids remain private and are never persisted in the parent Session.
 
-`turn/completed` is the authoritative remote terminal fact. The latest `agentMessage` with `phase: "final_answer"` wins, and that selected message must contain nonblank text. When the product emits no explicit final phase, the latest message with `phase: null` is the compatibility fallback and must likewise be nonblank; commentary never replaces either answer. A failed turn with `error.codexErrorInfo: "contextWindowExceeded"` becomes `max-tokens`. A completed turn without an answer, every other failed or interrupted remote turn, malformed required fields in a recognized app-server frame, protocol closure, early process exit, or unknown server request becomes `error`; a permission-related error may additionally carry the shared safe diagnostic. This version has no native refusal terminal and therefore produces no `refusal`. Local cancellation wins its race and remains `aborted` without permission detail.
+`turn/completed` is the authoritative remote terminal fact. The latest `agentMessage` with `phase: "final_answer"` wins, and that selected message must contain nonblank text. When the product emits no explicit final phase, the latest message with `phase: null` is the compatibility fallback and must likewise be nonblank; commentary never replaces either answer. The [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns Codex error-info categories, HTTP status, lifecycle stages, process outcomes, and stop-reason preservation. Local cancellation remains `aborted` without a failure diagnostic.
 
 For command and file approvals, the unattended wire selects a non-approval decision offered by the request, preferring `cancel`; the stable 0.147.0 request shape without an offered-decision list falls back to `decline`. It grants no requested permissions for the turn, answers user-input requests with no answers, and declines MCP elicitation. It records safe categories for those requests, declined command/file items, and `sandboxError`. Codex emits some early `never` rejections and sandbox violations only on structured stderr, so the Provider pipes and forwards stderr unchanged while matching two fixed signatures in a bounded per-run tail; raw stderr never enters the diagnostic. A request with no legal unattended response, or any unknown server request, fails the run instead of waiting for a user interface the provider does not supply.
 
-An unpublished startup failure closes the wire, terminates the acquired process tree, waits for exit, detaches the stderr observer, and then rejects `start()`. Published disposal best-effort interrupts a known turn, closes the wire, ends stdin, invokes the shared termination escalation, waits for whole-tree exit, and detaches the observer. Result failure and teardown failure stay independently observable.
+An unpublished startup failure closes the wire, terminates the acquired process tree, waits for exit, detaches the stderr observer, and then rejects `start()` with its fixed operation stage. Published disposal best-effort interrupts a known turn, closes the wire, ends stdin, invokes the shared termination escalation, waits for whole-tree exit, and detaches the observer. Independent cleanup failure reports `teardown`; when startup and rollback both fail, the aggregate's top message retains both safe stage lines while the underlying causes remain internal.
 
 Codex 0.147.0 speaks the Responses protocol, while DeepSeek's public OpenAI-compatible endpoint speaks Chat Completions. The credentialed Codex e2e therefore uses a loopback-only, test-private bridge for one no-tool nonce request: real Codex sends Responses to the bridge, the bridge forwards the received bearer credential and extracted task to the fixed official DeepSeek endpoint, and it wraps the real text in the minimal Responses SSE lifecycle. The bridge is neither a production proxy nor evidence that Codex connects to DeepSeek Chat Completions natively.
 
@@ -52,9 +52,9 @@ Codex 0.147.0 speaks the Responses protocol, while DeepSeek's public OpenAI-comp
 
 The public configuration contains a non-empty `providerName`, an explicit `env` overlay, a positive finite `disposeGraceMs` no greater than the repository's shared `MAX_TIMER_DELAY_MS`, and a five-value native `permissionMode` that defaults to `dontAsk`. Each named instance retains those resolved values for its own runs. Each run creates its own `AbortController`, sets `persistSession: false`, disables `AskUserQuestion`, and passes the resolved mode to the SDK; only `bypassPermissions` receives the SDK's explicit dangerous confirmation. The provider deliberately omits `settingSources`, so the SDK reads the host's normal user, project, and local Claude settings relative to the parent Session cwd. It neither copies nor filters those settings and does not create or modify login state. Remaining permission prompts are denied, MCP elicitation is declined, and blocking dialogs fail closed instead of waiting for a user interface the provider does not own.
 
-The provider publishes only after both the SDK `Query` and a live managed CLI handle exist. It consumes the complete SDK stream and completes only when a `result` message has `subtype: "success"`, `is_error: false`, and a nonblank `result`, and the iterator then ends normally. Every SDK error subtype, an error-marked success, a missing result, iterator failure, protocol failure, or process failure becomes `error`. When a permission denial or unattended callback contributes to that failure, the result may additionally carry the bounded, non-assistant diagnostic owned by the non-interactive permissions decision. SDK turn, budget, and structured-output limits are not token-window facts, and the SDK exposes no native refusal terminal, so this provider produces neither `max-tokens` nor `refusal`. Local cancellation wins and becomes `aborted` without permission detail.
+The provider publishes only after both the SDK `Query` and a live managed CLI handle exist. It consumes the complete SDK stream and completes only when a `result` message has `subtype: "success"`, `is_error: false`, and a nonblank `result`, and the iterator then ends normally. The [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns every non-success category, stage, process outcome, and its ordering with a contributing permission decision. Local cancellation wins and becomes `aborted` without either diagnostic fact.
 
-Startup rollback and published disposal close the SDK query, abort the per-run controller, invoke shared process-tree termination, and wait for whole-tree exit. `Query.close()` expresses graceful protocol intent but does not replace the subprocess owner's exit proof. Query-close failure, process failure, and teardown failure remain independently observable.
+Startup rollback and published disposal close the SDK query, abort the per-run controller, invoke shared process-tree termination, and wait for whole-tree exit. `Query.close()` expresses graceful protocol intent but does not replace the subprocess owner's exit proof. An unpublished failure exposes only fixed `query-start` facts; a published process failure can expose its independent exit code and signal; an independent cleanup rejection exposes `teardown`. Original SDK, Host, and cleanup errors remain on internal cause chains and logs rather than entering the diagnostic.
 
 The credentialed Claude Code e2e uses the official DeepSeek Claude Code contract directly: the runtime-only DeepSeek key becomes `ANTHROPIC_AUTH_TOKEN`, the fixed official base gains `/anthropic`, and the main and subagent model variables select the documented DeepSeek models. It starts the production provider and real SDK/CLI, requires one random nonce as the complete answer, persists no credential in settings, and waits for every managed handle to exit.
 
@@ -62,11 +62,11 @@ The credentialed Claude Code e2e uses the official DeepSeek Claude Code contract
 
 Each product owns branch-complete package tests, a required keyless real-product spec, a Loader composition e2e, and a credentialed DeepSeek e2e. The keyless product tier uses the exact official distribution under test, a non-empty fake product key, an isolated temporary workspace and product home, and a loopback fixed-answer model. Missing product requests, wrong authentication, altered task text, a non-exact answer, a skipped real product, or a surviving managed handle fails the required test. The Codex Loader fixture exposes two named Codex instances and tools; the Claude Code Loader fixture exposes the default Codex tool plus two named Claude Code instances and tools. Both fixtures include generic Job controls and start neither product process. The credentialed tier starts the same production provider and real product with a runtime-only key, requires a unique nonce from the fixed official DeepSeek service, and proves quiescence again; it self-skips only when a local operator supplied no key, while trusted CI preflights the secret.
 
-The Codex evidence pins `@openai/codex@0.147.0`, `codex-cli 0.147.0`, and all six optional platform aliases. Its real-product spec observes the package-local wrapper argv, exact Bearer key, original task, byte-exact final answer, thread-level `never` overriding ambient `on-request`, automatic-review startup, unattended command rejection with safe diagnostic and no file side effect, explicit dangerous-bypass writing in suite-owned temporary storage, local cancellation, wrapper/native whole-tree exit, and missing-payload failure without host fallback.
+The Codex evidence pins `@openai/codex@0.147.0`, `codex-cli 0.147.0`, and all six optional platform aliases. Its real-product spec observes the package-local wrapper argv, exact Bearer key, original task, byte-exact final answer, native permission modes, explicit dangerous-bypass writing in suite-owned temporary storage, and wrapper/native whole-tree exit. An isolated wrapper fixture proves missing-payload failure without host fallback, two named instances retain separate environments and modes, and production never resolves a host `codex` from `PATH`. The [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns schema, failure, process-outcome, and final presentation evidence.
 
 The Codex credentialed e2e registers the production provider, starts the same real app-server, and requests one random nonce through the test-private bridge described above. It fixes the external endpoint and model, stores no credential or request payload, requires exactly one completed upstream response, compares the trimmed product answer byte-for-byte with the nonce, and waits for every managed handle to exit.
 
-The Claude Code evidence pins Agent SDK 0.3.220, Claude Code 2.1.220, and the identities and versions of all eight SDK platform packages. Its real-product spec lets the SDK select the installed payload, asserts that the shared subprocess argv begins with that package's native CLI, and observes the exact `x-api-key`, original task, byte-exact final answer, an inherited interactive host setting overridden by the safe Provider mode, denied and bypassed writes in suite-owned temporary directories, safe permission diagnostics, process failure, local cancellation, and whole-tree exit. Unit coverage proves that production never resolves host `PATH`, omits the executable override, forwards the SDK-selected Windows `claude.exe` without a batch shim, and surfaces the SDK's missing-payload error without host fallback. This evidence proves the pinned official SDK/CLI integration rather than compatibility with independently installed Claude versions. Loader coverage resolves both products through their optional Bundle patches while starting neither product.
+The Claude Code evidence pins Agent SDK 0.3.220, Claude Code 2.1.220, and all eight SDK platform packages. Its real-product spec lets the SDK select the installed payload, asserts that the shared subprocess argv begins with that package's native CLI, and observes the exact `x-api-key`, original task, byte-exact final answer, native permission modes, suite-owned denied and bypassed writes, and whole-tree exit. Package tests prove that production never resolves host `PATH`, omits the executable override, and forwards the SDK-selected Windows `claude.exe` without a batch shim. This evidence proves the pinned official SDK/CLI integration rather than compatibility with independently installed Claude versions; the [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns failure and process-outcome evidence. Loader coverage resolves both products through their optional Bundle patches while starting neither product.
 
 The Claude Code credentialed e2e maps the key and fixed official endpoint only in the provider's in-memory environment, uses the documented `deepseek-v4-pro[1m]` and `deepseek-v4-flash` model variables, and traverses the production provider, official SDK, and real CLI. It compares the trimmed result with a random nonce and proves whole-tree exit without calling the Messages API directly from the test.
 
@@ -90,6 +90,6 @@ The project owner's distribution authorization is scoped to the official `@anthr
 
 Users delegate through Profile-configured one-shot tools backed by the official product integrations. Explicit Profile installation and host-plane provider placement are owned by the [production-install exclusion decision](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md); named instance identity and tool binding are owned by the [named-instance decision](2026-08-18-product-subagent-named-instances.md); per-Preset tool exposure and foreground-default optional Job scheduling are owned by the [product one-shot background decision](2026-08-12-product-subagent-one-shot-background-tasks.md). This note's provider lifecycle keeps native settings and behavior while shared services retain the sole ownership of job settlement and process-tree quiescence.
 
-Every delegation pays for a fresh product process and independent model context. Successful product payload remains final assistant text; a failed product run may separately expose the shared safe diagnostic. Background scheduling additionally exposes generic Job ids, status, completion notices, and collection or cancellation results. Both products use Bundle-pinned platform CLIs plus native account and workspace settings and the selected Provider permission mode. Credentialed e2e runs also spend external API quota and depend on the official DeepSeek endpoint; deterministic protocol, failure, cancellation, and approval coverage remains in the keyless tier. The providers do not resume sessions, stream progress, accept new human interaction, roll back tool or file side effects, or impose a wall-clock timeout.
+Every delegation pays for a fresh product process and independent model context. Successful product payload remains final assistant text; a failed product run may separately expose the shared safe diagnostic containing provider-owned permission facts or version-pinned structured failure facts. Background scheduling additionally exposes generic Job ids, status, completion notices, and collection or cancellation results. Both products use Bundle-pinned platform CLIs plus native account and workspace settings and the selected Provider permission mode. Credentialed e2e runs also spend external API quota and depend on the official DeepSeek endpoint; deterministic protocol, failure, cancellation, and approval coverage remains in the keyless tier. The providers do not resume sessions, stream progress, accept new human interaction, roll back tool or file side effects, or impose a wall-clock timeout.
 
 Compatibility is pinned by package-level unit coverage, keyless real-product loopback tests, credentialed DeepSeek nonce tests, public Loader composition, built-package and NodeNext consumer checks, generated documentation and notices, and the repository CI matrix. A supported product or DeepSeek endpoint/model baseline change must refresh those facts; production performs no separate runtime version probe.

.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md

@@ -12,7 +12,7 @@ Status: implemented
 
 ## 决策
 
-harness 交付两个同级的一次性提供方包，其默认注册名称分别为 `codex` 与 `claude-code`。本说明负责它们的产品协议、结果映射和进程生命周期；[命名实例决策](2026-08-18-product-subagent-named-instances.md)负责 Profile 选择的提供方身份与静态工具绑定，[生产安装排除决策](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md)负责各自独立的可选 Bundle 与 host plane（宿主平面）放置，[产品一次性后台任务决策](2026-08-12-product-subagent-one-shot-background-tasks.md)负责模型可见的调度选择，[非交互权限决策](2026-08-15-product-subagent-noninteractive-permissions.md)则负责各产品提供方的 Profile 模式选择与诊断生产。两个包都接受多个命名实例。加载任一提供方都不会启动产品进程，而且每个工具只接受独立文本任务；产品与实例选择仍属于部署配置。
+harness 交付两个同级的一次性提供方包，其默认注册名称分别为 `codex` 与 `claude-code`。本说明负责它们的产品协议、结果映射和进程生命周期；[命名实例决策](2026-08-18-product-subagent-named-instances.md)负责 Profile 选择的提供方身份与静态工具绑定，[生产安装排除决策](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md)负责各自独立的可选 Bundle 与 host plane（宿主平面）放置，[产品一次性后台任务决策](2026-08-12-product-subagent-one-shot-background-tasks.md)负责模型可见的调度选择，[非交互权限决策](2026-08-15-product-subagent-noninteractive-permissions.md)负责各产品提供方的 Profile 模式选择与安全权限决定，[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.md)则负责通过同一诊断公开锁定产品版本的类别、生命周期阶段与进程结果。两个包都接受多个命名实例。加载任一提供方都不会启动产品进程，而且每个工具只接受独立文本任务；产品与实例选择仍属于部署配置。
 
 这两个提供方都报告 `inheritsParentContext: false`，不声明任何可选的启动能力，并传递父会话 cwd，但不会复制父级对话。文档所示的工具使用 `backgroundMode: 'one-shot'` 与 `maxDepth: 'provider-managed'`：消费方默认在前台收集结果，也可把同一次运行放入通用 Job 运行时，而递归策略仍由进程外产品负责。每次调用都会创建一个全新的产品进程和一次不可续接的产品对话。`ctx.subagents` 负责具名请求解析与成对生命周期事件；`dsh-tool-subagent` 负责模型可见的调度以及前台与 Job 适配；`ctx.jobs` 和 `dsh-tool-jobs` 负责 Job id、状态、输出、控制、通知与父级 owner 取消；各产品提供方负责原生结果映射，`dsh-subprocess` 则负责凭证清洗、进程树终止以及整棵进程树的退出观测。
 
@@ -38,11 +38,11 @@ configured tool -> dsh-tool-subagent -> ctx.subagents -> product provider -> pro
 
 发布前，提供方会验证非空的纯文本任务，在父级工作区中启动受管的 app-server，完成 `initialize` → `initialized` 握手，把已解析模式映射为官方 `thread/start` 字段，并创建一个 `ephemeral: true` 线程。固定 app-server argv 不包含模式或任务文本。已发布的运行只拥有一次 `turn/start`；其线程 ID 与轮次 ID 保持私有，绝不会持久化到父会话。
 
-`turn/completed` 是权威的远端终止事实。以最后一条带有 `phase: "final_answer"` 的 `agentMessage` 为准，且选中的消息必须包含非空白文本。若产品没有发出明确的最终阶段，则以最后一条 `phase: null` 的消息作为兼容性回退，该消息也必须包含非空白文本；过程说明绝不会取代上述任一答案。带有 `error.codexErrorInfo: "contextWindowExceeded"` 的失败轮次会成为 `max-tokens`。轮次完成却没有答案、其他任何远端失败或中断轮次、已识别的 app-server 帧中必需字段格式错误、协议关闭、进程提前退出或未知的服务器请求，都会产生 `error`；权限相关错误可以额外携带共享安全诊断。本版本没有原生的拒绝终止状态，因此不会产生 `refusal`。本地取消在竞态中胜出并保持为 `aborted`，且不附带权限说明。
+`turn/completed` 是权威的远端终止事实。以最后一条带有 `phase: "final_answer"` 的 `agentMessage` 为准，且选中的消息必须包含非空白文本。若产品没有发出明确的最终阶段，则以最后一条 `phase: null` 的消息作为兼容性回退，该消息也必须包含非空白文本；过程说明绝不会取代上述任一答案。[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.md)负责 Codex error-info 类别、HTTP status、生命周期阶段、进程结果与终止原因保持。本地取消仍是 `aborted` 且不附带失败诊断。
 
 对于命令与文件审批，无人值守的协议连接会从请求给出的决策选项中选择一项不予批准的决策，并优先选择 `cancel`；稳定的 0.147.0 请求形态没有决策选项列表，因此回退到 `decline`。它不授予该轮次请求的任何权限，不向用户输入请求提供任何答案，并拒绝 MCP elicitation。它会记录这些请求、被拒绝的命令／文件 item 与 `sandboxError` 的安全类别。Codex 的部分早期 `never` 拒绝和 sandbox violation 只写入结构化 stderr，因此提供方会 pipe 并原样转发 stderr，同时在每次运行的有界尾部中匹配两个固定签名；原始 stderr 绝不会进入诊断。若请求在无人值守模式下没有合法响应，或是未知服务器请求，此次运行就会失败，而不会等待本提供方没有提供的用户界面。
 
-若启动在发布前失败，提供方会关闭协议连接、终止已获取的进程树、等待其退出、移除 stderr observer，然后拒绝 `start()`。对已发布的运行执行资源释放时，提供方会尽力中断已知轮次、关闭协议连接、结束标准输入、调用共享的逐级终止机制，等待整棵进程树退出，并移除 observer。结果失败与清理失败仍可彼此独立地观察。
+若启动在发布前失败，提供方会关闭协议连接、终止已获取的进程树、等待其退出、移除 stderr observer，然后用固定操作阶段拒绝 `start()`。对已发布的运行执行资源释放时，提供方会尽力中断已知轮次、关闭协议连接、结束标准输入、调用共享的逐级终止机制，等待整棵进程树退出，并移除 observer。独立清理失败会报告 `teardown`；启动与回滚同时失败时，聚合的顶层消息会保留两条安全阶段说明，而底层 cause 仍只在内部可见。
 
 Codex 0.147.0 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端点使用 Chat Completions。因此，带密钥 Codex e2e 会采用一个仅限回环、仅供测试内部使用的桥接层来处理一次不使用工具的随机数请求：真实 Codex 将 Responses 发送到桥接层，桥接层把收到的 Bearer 凭据与提取出的任务转发到固定的 DeepSeek 官方端点，再将真实文本包装进最小化的 Responses SSE（Server-Sent Events）生命周期。该桥接层既不是生产代理，也不能作为 Codex 原生连接 DeepSeek Chat Completions 的证据。
 
@@ -52,9 +52,9 @@ Codex 0.147.0 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端
 
 公开配置包含非空的 `providerName`、显式的 `env` 覆盖项、须为正有限值且不得大于仓库共享 `MAX_TIMER_DELAY_MS` 的 `disposeGraceMs`，以及默认使用 `dontAsk` 的五值原生 `permissionMode`。每个命名实例会为自己的运行保留这些已解析值。每次运行都会创建自己的 `AbortController`，设置 `persistSession: false`、禁用 `AskUserQuestion`，并把已解析模式传给 SDK；只有 `bypassPermissions` 会取得 SDK 的显式危险确认。提供方故意省略 `settingSources`，因此 SDK 会相对于父会话 cwd 读取宿主机常规的用户、项目和本地 Claude 设置。它既不复制也不过滤这些设置，也不会创建或修改登录状态。其余权限提示会被拒绝，MCP elicitation 会被拒绝，阻塞对话会快速失败，而不会等待本提供方不负责的用户界面。
 
-只有在 SDK `Query` 与受管的活动 CLI 句柄都已存在后，提供方才会发布运行。它会消费完整的 SDK 流；只有 `result` 消息具有 `subtype: "success"`、`is_error: false` 和非空白 `result`，且迭代器随后正常结束时，运行才会完成。所有 SDK 错误子类型、标记为错误的成功消息、结果缺失、迭代器失败、协议失败或进程失败都会成为 `error`。当权限拒绝或无人值守回调参与了该失败时，结果还可以携带由非交互权限决策负责的有界、非 assistant 诊断。SDK 的轮次、预算和结构化输出限制不表示 token 窗口耗尽，而且 SDK 没有原生的拒绝终止状态，因此本提供方不会产生 `max-tokens` 或 `refusal`。本地取消会胜出并成为 `aborted`，且不附带权限说明。
+只有在 SDK `Query` 与受管的活动 CLI 句柄都已存在后，提供方才会发布运行。它会消费完整的 SDK 流；只有 `result` 消息具有 `subtype: "success"`、`is_error: false` 和非空白 `result`，且迭代器随后正常结束时，运行才会完成。[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.md)负责所有非成功类别、阶段、进程结果，以及它们与参与失败的权限决定之间的顺序。本地取消会胜出并成为 `aborted`，且不附带这两类诊断事实。
 
-启动回滚和已发布运行的资源释放都会关闭 SDK query、中止该次运行的控制器、调用共享的进程树终止机制，并等待整棵进程树退出。`Query.close()` 表达优雅的协议关闭意图，但不能取代子进程责任方的退出证明。Query 关闭失败、进程失败和清理失败仍可彼此独立地观察。
+启动回滚和已发布运行的资源释放都会关闭 SDK query、中止该次运行的控制器、调用共享的进程树终止机制，并等待整棵进程树退出。`Query.close()` 表达优雅的协议关闭意图，但不能取代子进程责任方的退出证明。未发布失败只公开固定的 `query-start` 事实；已发布进程失败可以分别公开退出码与信号；独立清理拒绝则公开 `teardown`。原始 SDK、Host 与清理错误只保留在内部 cause 链和日志中，不进入诊断。
 
 带密钥 Claude Code e2e 直接使用官方 DeepSeek Claude Code 约定：仅在运行时提供的 DeepSeek 密钥会映射为 `ANTHROPIC_AUTH_TOKEN`，固定的官方基础 URL 会追加 `/anthropic`，主模型与 subagent 模型变量会选择文档所示的 DeepSeek 模型。该测试会启动生产提供方与真实 SDK 和 CLI，要求一个随机数作为完整答案，不会把任何凭据持久化到设置中，并等待所有受管句柄退出。
 
@@ -62,11 +62,11 @@ Codex 0.147.0 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端
 
 每个产品都负责覆盖所有分支的包测试、一项必跑的无密钥真实产品测试、一项 Loader 组合 e2e 和一项带密钥 DeepSeek e2e。无密钥产品层级使用被测的确切官方发行版、非空的伪产品密钥、隔离的临时工作区与产品主目录，以及能返回固定答案的回环模型。产品请求缺失、身份验证错误、任务文本被改动、答案不完全一致、真实产品被跳过或受管句柄仍存活，都会使这项必跑测试失败。Codex Loader fixture 会公开两个命名 Codex 实例与工具；Claude Code Loader fixture 会公开默认 Codex 工具以及两个命名 Claude Code 实例与工具。两个 fixture 都包含通用 Job 控制工具，而且不会启动任何产品进程。带密钥层级会使用仅在运行时提供的密钥启动同一生产提供方与真实产品，要求从固定的 DeepSeek 官方服务取得唯一随机数，并再次证明完全停稳；仅当本地操作者未提供密钥时才会自行跳过，而受信任的 CI 会预检该 secret。
 
-Codex 证据会锁定 `@openai/codex@0.147.0`、`codex-cli 0.147.0` 与六个平台 alias。其真实产品测试会观测包内 wrapper argv、确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、线程级 `never` 对环境中 `on-request` 的覆盖、自动评审启动、带安全诊断且不产生文件副作用的无人值守命令拒绝、测试拥有临时存储中的显式危险绕过写入、本地取消、wrapper／原生整棵进程树退出，以及载荷缺失时不回退宿主命令的失败。
+Codex 证据会锁定 `@openai/codex@0.147.0`、`codex-cli 0.147.0` 与六个平台 alias。其真实产品测试会观测包内 wrapper argv、确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、原生权限模式、测试拥有临时存储中的显式危险绕过写入，以及 wrapper／原生整棵进程树退出。独立 wrapper fixture 会证明载荷缺失时不回退宿主命令，两个命名实例会保留彼此独立的环境与模式，生产环境也不会从 `PATH` 解析宿主 `codex`。[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.md)负责 schema、失败、进程结果与最终呈现证据。
 
 带密钥 Codex e2e 会注册生产提供方，启动同样的真实 app-server，并通过上述测试专用桥接层请求一个随机数。该测试固定外部端点与模型，不存储任何凭据或请求载荷，要求上游恰好完成一次响应，将去除首尾空白后的产品答案与该随机数逐字节比较，并等待所有受管句柄退出。
 
-Claude Code 证据会锁定 Agent SDK 0.3.220、Claude Code 2.1.220，以及八个 SDK 平台包的身份与版本。真实产品测试会让 SDK 选择已安装载荷，断言共享子进程 argv 以该包的原生 CLI 开头，并观测确切的 `x-api-key`、原始任务、逐字节完全一致的最终回答、安全提供方模式对继承的交互式宿主设置的覆盖、测试所拥有临时目录中的拒绝写入与 bypass 写入、安全权限诊断、进程失败、本地取消和整棵进程树退出。单元覆盖会证明生产运行从不解析宿主 `PATH`、省略可执行文件覆盖、直接转发 SDK 所选的 Windows `claude.exe` 而不经过 batch shim，并且在载荷缺失时原样暴露 SDK 错误且不回退宿主 CLI。这项证据证明锁定的官方 SDK/CLI 集成，而不证明与独立安装的 Claude 版本兼容。Loader 覆盖会通过各自的可选 Bundle patch 解析两个产品，且不会启动任一产品。
+Claude Code 证据会锁定 Agent SDK 0.3.220、Claude Code 2.1.220 与八个 SDK 平台包。真实产品测试会让 SDK 选择已安装载荷，断言共享子进程 argv 以该包的原生 CLI 开头，并观测确切的 `x-api-key`、原始任务、逐字节完全一致的最终回答、原生权限模式、测试拥有范围内的拒绝写入与 bypass 写入，以及整棵进程树退出。包测试还会证明生产运行从不解析宿主 `PATH`、省略可执行文件覆盖，并直接转发 SDK 所选的 Windows `claude.exe` 而不经过 batch shim。这项证据证明锁定的官方 SDK/CLI 集成，而不证明与独立安装的 Claude 版本兼容；[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.md)负责失败与进程结果证据。Loader 覆盖会通过各自的可选 Bundle patch 解析两个产品，且不会启动任一产品。
 
 带密钥 Claude Code e2e 仅在提供方的内存环境中映射密钥与固定的官方端点，把模型变量设为文档所示的 `deepseek-v4-pro[1m]` 与 `deepseek-v4-flash`，并实际经过生产提供方、官方 SDK 与真实 CLI。它将去除首尾空白后的结果与一个随机数比较，并证明整棵进程树退出，且测试不会直接调用 Messages API。
 
@@ -90,6 +90,6 @@ Claude Code 证据会锁定 Agent SDK 0.3.220、Claude Code 2.1.220，以及八
 
 用户通过由 Profile 配置、并由官方产品集成支持的一次性工具进行委派。显式 Profile 安装与 host plane 提供方放置由[生产安装排除决策](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md)负责；命名实例身份与工具绑定由[命名实例决策](2026-08-18-product-subagent-named-instances.md)负责；按 Preset 暴露工具以及默认前台且可选通用 Job 的调度方式由[产品一次性后台任务决策](2026-08-12-product-subagent-one-shot-background-tasks.md)负责。本说明规定的提供方生命周期会保留原生设置与行为，而共享服务继续独占作业结算与进程树完全停稳的责任。
 
-每次委派都要承担新建产品进程和独立模型上下文的开销。成功的产品载荷仍只有最终 assistant 文本；失败的产品运行可以另行公开共享安全诊断。后台调度还会额外公开通用 Job id、状态、完成通知以及收集或取消结果。两个产品都使用 Bundle 锁定的平台 CLI，并保留原生账户与工作区设置以及所选提供方权限模式。带密钥 e2e 运行还会消耗外部 API 配额，并依赖 DeepSeek 官方端点；对协议、失败、取消与审批的确定性覆盖仍由无密钥层级承担。提供方不会恢复会话、以流式方式传送进度、接受新的人工交互、回滚工具或文件副作用，也不会施加按实际经过时间触发的超时。
+每次委派都要承担新建产品进程和独立模型上下文的开销。成功的产品载荷仍只有最终 assistant 文本；失败的产品运行可以另行公开共享安全诊断，其中包含由提供方拥有的权限事实，或锁定版本产品提供的结构化失败事实。后台调度还会额外公开通用 Job id、状态、完成通知以及收集或取消结果。两个产品都使用 Bundle 锁定的平台 CLI，并保留原生账户与工作区设置以及所选提供方权限模式。带密钥 e2e 运行还会消耗外部 API 配额，并依赖 DeepSeek 官方端点；对协议、失败、取消与审批的确定性覆盖仍由无密钥层级承担。提供方不会恢复会话、以流式方式传送进度、接受新的人工交互、回滚工具或文件副作用，也不会施加按实际经过时间触发的超时。
 
 兼容性由包级单元测试覆盖率、无密钥真实产品回环测试、带密钥 DeepSeek 随机数测试、公开 Loader 组合、已构建包与 NodeNext 消费方检查、生成的文档与声明以及仓库 CI 矩阵共同锁定。更改受支持的产品基线或 DeepSeek 端点／模型基线时必须刷新这些事实；生产环境不会另行执行运行时版本探测。

.agents/notes/implemented/feature/2026-08-08-pi-ai-per-model-reasoning-declarations.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/2026-08-08-pi-ai-per-model-reasoning-declarations.md
-2026-08-08-pi-ai-per-model-reasoning-declarations.md: b6264feeb724e3693078fa3fc3e3fc16ed01aacb
-2026-08-08-pi-ai-per-model-reasoning-declarations.zh.md: 1b30f7e0c42974c777a535e133a47caa217e2e5e
+2026-08-08-pi-ai-per-model-reasoning-declarations.md: 0e8d5c3ca4017e89332f6b22e4eb0a06062918e6
+2026-08-08-pi-ai-per-model-reasoning-declarations.zh.md: c4c060b21c8b7ee5b11b5e98c8d7da0ba6c032fc

.agents/notes/implemented/feature/2026-08-08-pi-ai-per-model-reasoning-declarations.md

@@ -14,7 +14,7 @@ Two adjacent gaps compounded this. pi-ai decides the reasoning *wire dialect* (`
 
 `PiAiModelProfile` gains `reasoningEfforts`: **each key is a level selectors offer, its value the spelling dispatch sends on the wire**. The declaration translates to pi-ai's `Model.reasoning` + `thinkingLevelMap` with all seven levels decided explicitly — declared levels carry their wire value, undeclared levels are pinned `null` — so the profile author never needs pi-ai's asymmetric defaulting rule (absent means "supported" for the five base levels but "unsupported" for `xhigh`/`max`). `off` is the one three-state key: left out, no Off is offered and an explicit Off request is refused (an effortless request still goes out bare, leaving the provider its default); declared valueless, Off is offered and dispatch sends nothing (the `deepseek` dialect sends `thinking: {type: "disabled"}`); declared with a value, that value goes on the wire. `false` declares a non-reasoning model; an empty declaration is refused rather than guessed at. The spelling for "disable" is `false` rather than `{}` because schemastery materializes an absent dict as `{}` — only a `z.union([z.const(false), dict])` keeps absent, disabled, and declared distinguishable, and a bare `reasoningEfforts:` (YAML null) slips through that union unvalidated, so resolution refuses it explicitly.
 
-`compat.thinkingFormat` and `compat.supportsReasoningEffort` become configurable at two levels — route (its models' default) and model (winning per field) — resolving model → route → installed catalog entry → pi-ai's URL guess. They exist only on `openai-completions` (pi-ai types them nowhere else): a model-level switch on another protocol fails resolution, a route-level default skips such models, and a route with no completions model at all is refused. The two `chat-template` formats stay withheld for want of `chatTemplateKwargs`. Both enums are pinned to pi-ai's types through `Record<UpstreamUnion, true>` drift gates, so a pi-ai upgrade that adds a format fails compilation until the new member is classified (verified against the published 0.84.1 tarball, whose `thinkingFormat` union adds `baseten` over the pinned 0.82.1).
+`compat.thinkingFormat` and `compat.supportsReasoningEffort` become configurable at two levels — route (its models' default) and model (winning per field) — resolving model → route → installed catalog entry → pi-ai's URL guess. `thinkingFormat` is pinned to pi-ai's union through a `Record<UpstreamUnion, true>` drift gate, so a pi-ai upgrade that adds a format fails compilation until the new member is classified (verified against the published 0.84.1 tarball, whose `thinkingFormat` union adds `baseten` over the pinned 0.82.1). Which fields `compat` carries, which protocols take each of them, and how an unreadable key is refused are owned by [[2026-08-18-pi-ai-wire-compat-surface]]; the two-level resolution order above is what that surface generalizes.
 
 `modelOverrides` reshapes individual catalog models without replacing the served set: key = catalog model id, value = a `models` entry minus `id`, materialized by handing the override to the existing entry path so capacities, efforts, compat, and request-default semantics stay identical. Unlike Pi's own config layer, which ignores unknown ids, every override that lands nowhere is refused — beside a `models` list, on a hand-declared route, naming an unknown model, or smuggling an `id` in the value (the schema passes unknown keys through, and a smuggled id would quietly rename the model).
 

.agents/notes/implemented/feature/2026-08-08-pi-ai-per-model-reasoning-declarations.zh.md

@@ -14,7 +14,7 @@ Status: implemented
 
 `PiAiModelProfile` 新增 `reasoningEfforts`：**每个键是选择器提供的一个档位，其值是分派在协议中发送的拼写**。该声明会转换为 pi-ai 的 `Model.reasoning` + `thinkingLevelMap`，七个档位全部显式决定——已声明的档位携带自己的协议值，未声明的档位一律固定为 `null`——因此 profile 作者永远不需要了解 pi-ai 那条不对称的默认规则（键缺席对五个基础档位意味着「支持」，对 `xhigh`/`max` 却意味着「不支持」）。`off` 是唯一的三态键：不写，选择器不提供 Off，显式请求 Off 会被拒绝（不点名档位的请求仍会不带参数地发出，提供方保留自己的默认行为）；声明而不给值，则提供 Off，分派什么也不发送（`deepseek` 方言发送 `thinking: {type: "disabled"}`）；声明并给值，该值就在协议中发送。`false` 声明一个不具备推理能力的模型；空声明会被拒绝，而不是去猜。「禁用」的拼写取 `false` 而非 `{}`，因为 schemastery 会把缺席的字典物化成 `{}`——只有 `z.union([z.const(false), dict])` 才能让缺席、禁用与已声明三态保持可区分；而裸写的 `reasoningEfforts:`（YAML null）会不经校验地从该 union 溜过去，因此解析对它显式拒绝。
 
-`compat.thinkingFormat` 与 `compat.supportsReasoningEffort` 变为两级可配置——路由级（作为其模型的默认值）与模型级（逐字段胜出）——解析顺序为模型 → 路由 → 已安装 catalog 条目 → pi-ai 按 URL 得出的猜测。两者只存在于 `openai-completions` 上（pi-ai 也只在这一协议上为它们建了类型）：在其他协议的模型上设模型级开关会使解析失败，路由级默认值会跳过这类模型，而完全没有 completions 模型的路由则被拒绝。两个 `chat-template` 格式因缺 `chatTemplateKwargs` 而继续保持不开放。两个枚举都经 `Record<UpstreamUnion, true>` 漂移门禁钉在 pi-ai 的类型上，因此新增格式的 pi-ai 升级会编译失败，直到新成员被归类（对照已发布的 0.84.1 tarball 验证过：其 `thinkingFormat` 联合类型相对钉住的 0.82.1 新增了 `baseten`）。
+`compat.thinkingFormat` 与 `compat.supportsReasoningEffort` 变为两级可配置——路由级（作为其模型的默认值）与模型级（逐字段胜出）——解析顺序为模型 → 路由 → 已安装 catalog 条目 → pi-ai 按 URL 得出的猜测。`thinkingFormat` 经 `Record<UpstreamUnion, true>` 漂移门禁钉在 pi-ai 的联合类型上，因此新增格式的 pi-ai 升级会编译失败，直到新成员被归类（对照已发布的 0.84.1 tarball 验证过：其 `thinkingFormat` 联合类型相对钉住的 0.82.1 新增了 `baseten`）。`compat` 承载哪些字段、每个字段由哪些协议接受、以及无法读取的键如何被拒绝，归 [[2026-08-18-pi-ai-wire-compat-surface]] 所有；上面这条两级解析顺序正是该面所推广的东西。
 
 `modelOverrides` 就地重塑单个 catalog 模型而不替换所服务的集合：键 = catalog 模型 id，值 = 去掉 `id` 的 `models` 条目，物化时把覆盖交给既有的条目路径，因此容量、档位、compat 与请求默认值语义完全一致。与忽略未知 id 的 Pi 自有配置层不同，凡是落不到任何地方的覆盖都会被拒绝——与 `models` 列表并存、写在手工声明的路由上、点名未知模型，或在值里夹带 `id`（schema 会放行未知键，被夹带的 id 会悄悄把模型改名）。
 

.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.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/2026-08-15-product-subagent-noninteractive-permissions.md
-2026-08-15-product-subagent-noninteractive-permissions.md: df1f0d9939e951f16070729615a3779f1f7c2ddc
-2026-08-15-product-subagent-noninteractive-permissions.zh.md: 982b4409e08a506dec828db15c8c4aa5fcc36883
+2026-08-15-product-subagent-noninteractive-permissions.md: 8788fba3492e08090dd038fc3e7377f6bd1e29cd
+2026-08-15-product-subagent-noninteractive-permissions.zh.md: 6f254930151abce23f04de4f354bf57ad81bba61

.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md

@@ -44,9 +44,9 @@ The Provider overrides only those thread fields. `CODEX_HOME`, project configura
 
 ### Failure diagnostic
 
-`SubagentResult` carries an optional `diagnostic` for provider-authored, non-assistant failure detail. A Provider removes tool inputs, file contents, environment values, credentials, and raw protocol payloads before producing it. The shared out-of-process result boundary limits the complete text to 4096 UTF-8 bytes and marks truncation without splitting a character.
+`SubagentResult` carries an optional `diagnostic` for provider-authored, non-assistant failure detail. A Provider removes tool inputs, file contents, environment values, credentials, and raw protocol payloads before producing it. The shared out-of-process result boundary limits the complete text to 4096 UTF-8 bytes and marks truncation without splitting a character. The [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns non-permission product categories, lifecycle stages, and process outcomes carried by the same field.
 
-Each product records only the effective mode, request category, unattended decision, and a fixed safe reason. Claude Code derives those facts from SDK callbacks and `permission_denied` messages. Codex derives them from app-server requests, declined items, `sandboxError`, and two fixed permission signatures in a bounded stderr tail; raw stderr is still forwarded to the Host but never copied into the diagnostic. A successful result returns only the strict final answer; local cancellation remains `aborted` without permission detail; an unpublished startup failure still rejects `start()`. When a permission fact contributes to a published run that settles as `error`, the Provider attaches the diagnostic without adding it to assistant output, structured output, or `subagent/end.lastAssistantMessage`.
+Each product's permission fact contains only the effective mode, request category, unattended decision, and a fixed safe reason. Claude Code derives those facts from SDK callbacks and `permission_denied` messages. Codex derives them from app-server requests, declined items, `sandboxError`, and two fixed permission signatures in a bounded stderr tail; raw stderr is still forwarded to the Host but never copied into the diagnostic. Both Providers place their structured failure line before the latest contributing permission fact. A successful result returns only the strict final answer; local cancellation remains `aborted` without permission detail; an unpublished startup failure still rejects `start()`. The Provider never adds either diagnostic fact to assistant output, structured output, or `subagent/end.lastAssistantMessage`.
 
 The foreground consumer presents the stop-reason headline, then the optional diagnostic, then any partial assistant output. The one-shot background adapter stores the same diagnostic beside the stop reason in the failed Job detail. Providers that omit the field retain their previous behavior.
 
@@ -63,7 +63,7 @@ The foreground consumer presents the stop-reason headline, then the optional dia
 
 ## Verification
 
-Package tests pin every allowed and rejected Config value, the exact SDK and app-server field mappings, dangerous confirmations, unattended terminal responses, diagnostic sanitization and UTF-8 bound, successful-result omission, concurrent-run isolation, foreground ordering, Job detail, stderr observer disposal, and process cleanup. The real Claude Agent SDK/CLI fixture proves its safe default, restricted denial, explicit bypass, and whole-tree quiescence. The real Codex app-server fixture proves that thread-level `never` overrides ambient `on-request`, automatic review starts, dangerous bypass writes only inside suite-owned temporary storage, fixed stderr signatures produce safe diagnostics, and the wrapper/native tree exits. Loader composition proves non-default modes can be published without starting either product, and keyless ACP snapshots record the shared diagnostic presentation while the model-facing product tool schemas contain no permission parameter.
+Package tests pin every allowed and rejected Config value, the exact SDK and app-server field mappings, dangerous confirmations, unattended terminal responses, diagnostic sanitization and UTF-8 bound, successful-result omission, concurrent-run isolation, foreground ordering, Job detail, stderr observer disposal, and process cleanup. The real Claude Agent SDK/CLI fixture proves its safe default, restricted denial, explicit bypass, and whole-tree quiescence. The real Codex app-server fixture proves that thread-level `never` overrides ambient `on-request`, automatic review starts, dangerous bypass writes only inside suite-owned temporary storage, fixed stderr signatures produce safe diagnostics, and the wrapper/native tree exits. Loader composition proves non-default modes can be published without starting either product, and the keyless ACP snapshot records each product's failure diagnostic through foreground and Job presentation while the model-facing product tool schemas contain no permission parameter.
 
 ## Alternatives considered
 
@@ -83,6 +83,6 @@ Package tests pin every allowed and rejected Config value, the exact SDK and app
 
 Profiles can select each product's native restricted, automatic, planning/edit-accepting where supported, or bypass behavior before the Provider starts, while both safe defaults never ask a person. Broader modes remain explicit deployment choices and retain their native sandbox consequences.
 
-Permission failures become visible to both foreground parents and one-shot background Jobs without turning infrastructure text into an assistant answer. That diagnostic can enter model context, Job notices, API projections, and Job UI through the ordinary consumer paths, so the Provider must sanitize and bound it before result settlement.
+Permission failures become visible to both foreground parents and one-shot background Jobs without turning infrastructure text into an assistant answer. The same field can also carry the separately owned structured failure facts. It can enter model context, Job notices, API projections, and Job UI through the ordinary consumer paths, so the Provider must sanitize and bound the complete text before result settlement.
 
 The change adds no product session persistence, human approval channel, dynamic permission operation, progress stream, retry policy, or rollback. Other Providers remain valid without producing a diagnostic or exposing a permission-mode Config.

.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md

@@ -44,9 +44,9 @@ Codex 默认使用 `never`，并接受 Codex 0.147.0 公开的三种原生非交
 
 ### 失败诊断
 
-`SubagentResult` 携带可选的 `diagnostic`，用于提供方产生且不属于 assistant 内容的失败说明。提供方在生成它之前会排除工具输入、文件内容、环境值、凭证与原始协议载荷。共享的进程外结果边界会把完整文本限制在 4096 个 UTF-8 字节以内，并在不切断字符的前提下标记截断。
+`SubagentResult` 携带可选的 `diagnostic`，用于提供方产生且不属于 assistant 内容的失败说明。提供方在生成它之前会排除工具输入、文件内容、环境值、凭证与原始协议载荷。共享的进程外结果边界会把完整文本限制在 4096 个 UTF-8 字节以内，并在不切断字符的前提下标记截断。[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.md)负责由同一字段承载的非权限产品类别、生命周期阶段与进程结果。
 
-每个产品都只记录有效模式、请求类别、无人值守决定与固定的安全原因。Claude Code 从 SDK 回调和 `permission_denied` 消息取得这些事实。Codex 从 app-server 请求、被拒绝的 item、`sandboxError` 与每次运行有界 stderr 尾部中的两个固定权限签名取得事实；原始 stderr 仍会转发给 Host，但绝不会复制进诊断。成功结果只返回严格的最终答案；本地取消仍以 `aborted` 结算且不附带权限说明；未发布的启动失败仍会拒绝 `start()`。当一项权限事实参与了已经发布、最终以 `error` 结算的运行时，提供方会附加诊断，但不会把它写入 assistant 输出、结构化输出或 `subagent/end.lastAssistantMessage`。
+每个产品的权限事实都只包含有效模式、请求类别、无人值守决定与固定的安全原因。Claude Code 从 SDK 回调和 `permission_denied` 消息取得这些事实。Codex 从 app-server 请求、被拒绝的 item、`sandboxError` 与每次运行有界 stderr 尾部中的两个固定权限签名取得事实；原始 stderr 仍会转发给 Host，但绝不会复制进诊断。两个提供方都会把结构化失败行放在最新参与失败的权限事实之前。成功结果只返回严格的最终答案；本地取消仍以 `aborted` 结算且不附带权限说明；未发布的启动失败仍会拒绝 `start()`。提供方绝不会把任一诊断事实写入 assistant 输出、结构化输出或 `subagent/end.lastAssistantMessage`。
 
 前台消费方依次呈现终止原因标题、可选诊断和任何部分 assistant 输出。一次性后台适配器会在失败 Job 的 detail 中，把同一诊断与终止原因一起保存。没有填写该字段的提供方保持原有行为。
 
@@ -63,7 +63,7 @@ Codex 默认使用 `never`，并接受 Codex 0.147.0 公开的三种原生非交
 
 ## Verification
 
-包测试固定所有允许与拒绝的 Config 值、准确的 SDK 与 app-server 字段映射、危险确认、无人值守终态、诊断脱敏与 UTF-8 上限、成功结果不携带诊断、并发运行隔离、前台顺序、Job detail、stderr observer 释放和进程清理。真实 Claude Agent SDK/CLI fixture 证明其安全默认、受限拒绝、显式 bypass 与整棵进程树完全停稳。真实 Codex app-server fixture 证明线程级 `never` 覆盖环境中的 `on-request`、自动评审可以启动、危险绕过只在测试拥有的临时存储中写入、固定 stderr 签名产生安全诊断，而且 wrapper／native 进程树会退出。Loader 组装证明非默认模式可以在不启动任一产品的情况下发布；无密钥 ACP snapshot 则记录共享诊断呈现，同时面向模型的产品工具 schema 不包含权限参数。
+包测试固定所有允许与拒绝的 Config 值、准确的 SDK 与 app-server 字段映射、危险确认、无人值守终态、诊断脱敏与 UTF-8 上限、成功结果不携带诊断、并发运行隔离、前台顺序、Job detail、stderr observer 释放和进程清理。真实 Claude Agent SDK/CLI fixture 证明其安全默认、受限拒绝、显式 bypass 与整棵进程树完全停稳。真实 Codex app-server fixture 证明线程级 `never` 覆盖环境中的 `on-request`、自动评审可以启动、危险绕过只在测试拥有的临时存储中写入、固定 stderr 签名产生安全诊断，而且 wrapper／native 进程树会退出。Loader 组装证明非默认模式可以在不启动任一产品的情况下发布；无密钥 ACP snapshot 则记录每个产品的失败诊断如何经过前台与 Job 呈现，同时面向模型的产品工具 schema 不包含权限参数。
 
 ## Alternatives considered
 
@@ -83,6 +83,6 @@ Codex 默认使用 `never`，并接受 Codex 0.147.0 公开的三种原生非交
 
 Profile 可以在提供方启动前选择各产品原生的受限、自动、在产品支持时仅规划／编辑放行，或 bypass 行为，而两个安全默认值都绝不会询问人员。更宽松的模式仍是显式部署选择，并保留其原生沙箱后果。
 
-权限失败会同时到达前台父 agent 和一次性后台 Job，且不会把基础设施文本伪装成 assistant 回答。该诊断可以沿普通消费路径进入模型上下文、Job 通知、API 投影与 Job UI，因此提供方必须在结果结算前完成脱敏和限长。
+权限失败会同时到达前台父 agent 和一次性后台 Job，且不会把基础设施文本伪装成 assistant 回答。同一字段还可以承载由另一项决策负责的结构化失败事实。它可以沿普通消费路径进入模型上下文、Job 通知、API 投影与 Job UI，因此提供方必须在结果结算前对完整文本完成脱敏和限长。
 
 本改动不增加产品会话持久化、人工审批通道、动态权限操作、进度流、重试策略或回滚。其他提供方无需产生诊断或公开权限模式 Config，仍然保持合法。

.agents/notes/implemented/feature/2026-08-17-command-image-attachment-envelope.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/2026-08-17-command-image-attachment-envelope.md
+2026-08-17-command-image-attachment-envelope.md: 328a3fffa1d8db3ac9be42983965ef7f9578dec9
+2026-08-17-command-image-attachment-envelope.zh.md: bb135d218f156aaa36e3f9f52ed36019b68b56c3

.agents/notes/implemented/feature/2026-08-17-command-image-attachment-envelope.md

@@ -0,0 +1,46 @@
+# Agent Note: Command image-attachment envelope
+
+Status: implemented
+
+English | [中文](2026-08-17-command-image-attachment-envelope.zh.md)
+
+## Problem
+
+The Web composer submits one envelope — draft text, attached images, and delivery mode — but the two submission planes consumed it asymmetrically. A plain message rode `defaultSink → conversation.sendSession`, which serialized the images into prompt content and cleared them on success. A claimed slash command rode `claim.submit(args, actx)`, a text-only transaction: `/goal rebuild the cathedral` with four reference photos executed the command, cleared the draft, and silently stranded the images in the composer rail. The model never saw them, and no surface said so. The defect was contract-level, not a missed call site: nothing in the claim, the adjudication, or the host executor modeled attachments, so any command could consume the text half of a submission and drop the rest.
+
+Merging the two planes was not on the table — the [plugin command registration Agent Note](2026-07-19-plugin-command-registration.md) deliberately keeps human commands out of the model plane, and that separation is correct. The gap was that the envelope fractured at the plane fork.
+
+## Decision
+
+The submission envelope is modeled end to end, and every command route either consumes it whole or refuses it loudly.
+
+**Declaration.** `CommandDefinition.input.images: boolean` (absent = false) declares whether composer images may accompany an invocation. The flag rides the frozen `CommandDescriptor` through `commands/list` to every client, onto the minted `CommandClaim` (`images: true`), and into the input machine's published claim snapshot.
+
+**Generic identity, image-specific payload.** Browser drafts and durable references already use `DraftAttachmentId` and `AttachmentId`; the command RPC carries encoded bytes rather than an image identifier. The wire remains `EncodedImageAttachment[]`, and the declaration remains `input.images`, while images are the only non-text attachment with defined admission and model-block semantics.
+
+**Executor enforcement.** `CommandRuntime.execute(agent, line, images, signal)` carries the submission's base64 images (`EncodedImageAttachment` from `@deepseek-ai/dsh-attachment/types`). The executor — not the composer — enforces the declaration: images to a non-declaring command, an absent attachment store, and an exceeded batch limit each settle as a logged `command/done` error before the handler runs. Admission goes through the attachment package's `admitEncodedImages` — the shared wire entry that enforces canonical base64 and delegates batch admission (limits, validation, ordered commit) to `AttachmentStore.saveImages` — so both wire endpoints (prompt RPC and command executor) share one sequence and a rejected batch publishes no durable object. An admitted batch reaches the handler as frozen ordered `ImageBlock`s on `invocation.attachments`.
+
+**Producer-owned model visibility.** The registry never schedules the images itself. `/goal` submits one `agent.followup` user message — image blocks plus the fixed text `Reference images for the goal objective.` — after a successful create or edit, so later goal rounds read the images from ordinary session history and the goal domain stores no attachment state. `/plan <message>` folds the images into its steered text message, while bare `/plan` steers an image-only user message because the images may contain the whole task. Producer control forms with no model input (`/goal pause`, `/plan off`) return a direct error and keep the composer's images in place. The plan projection treats `command/run` as a candidate and drops it on a paired `command/done` error, so a rejected image-carrying `/plan off` cannot leave a pending exit.
+
+**Composer refusal is a visible banner, everything retained.** ui-commands' `matchEnter` receives a `SubmitEnvelope` (image count) from adjudication and throws a localized `notice.imagesUnsupported` refusal for every enter route that cannot consume images: contribution popups, decorated popups, non-declaring claims, and bare detached executes. The input machine publishes one error notice, which the composer renders through its transient Toast banner with draft and images untouched. A pre-claimed submit (space/menu claim) is gated in the facade with the same copy from the `conversation` namespace. On the accepting path the facade serializes the draft images through the hub's `commandImages` plumbing, passes them to `claim.submit`, and clears plus releases them only on a success outcome; an error result (including a producer grammar rejection) keeps them.
+
+## Testing
+
+Registry executor enforcement, admission failure settlement, and frozen invocation attachments are covered in `packages/interaction/commands/tests/commands.spec.ts`; batch admission ordering and limits in `packages/attachment/attachment/tests/admission.spec.ts`; producer behavior in `packages/goal/command-goal/tests/command-goal.spec.ts` and `packages/plan/plan-mode/tests/plan-mode.spec.ts`; client refusal and consumption paths in the ui-commands, ui-conversation, and ui-input-trigger client suites; and the assembled-application flow in the apps/web keyless lanes.
+
+## Alternatives considered
+
+- **Block commands whenever images are attached (no acceptance path)** — rejected: predictable, but `/goal` with reference images is the motivating use case; the user's images would have no route to the model at all.
+- **Auto-send stranded images as a follow-up user message after any command** — rejected: surprising for host-state commands (`/model`, `/compact`), and it moves the message contract from the producer to the composer, against the command registry's "producer owns model-visible work" rule.
+- **Store attachment references in the goal domain and render them into round prompts** — rejected: requires durable goal schema changes and either duplicates image blocks into every round prompt or adds round-one-only prompt shape; the round-prompt invariant would need attachment state. One ordinary logged user message achieves the same model visibility.
+- **Consume images on any command success regardless of grammar** — rejected: `/goal pause` with images attached would silently discard them, recreating the original defect one layer deeper. Consumption is tied to the producer's explicit success, and grammar misfits return errors.
+- **Keep enforcement client-side only** — rejected: schema omission is not enforcement; direct RPC callers could bypass the composer. The executor settles the declaration itself.
+- **Generalize the command wire to a multimedia identifier** — rejected: the two identifiers are already attachment-generic, while the wire transports bytes and its image-specific fields state the admission rules the Host enforces. Files and videos lack shared admission and model-visible semantics, and an untagged multimedia identifier would not supply them. A second supported attachment kind is the reintroduction condition; the command envelope then widens to a tagged attachment union and commands declare the accepted kinds while retaining `AttachmentId`.
+
+## Consequences
+
+- No command route can consume a submission's text and strand its images: the contract forces whole-envelope consumption or a visible refusal, for current and future commands alike.
+- The commands package now depends on `dsh-attachment` and `dsh-llm`, and `commands/execute` carries a required `images` wire parameter — every caller states its envelope explicitly.
+- `/goal` and `/plan` gain reference-image input at the cost of one extra logged user message (goal) and image blocks in the steered message (plan), including an image-only message for bare `/plan`; all are billed like any image prompt.
+- Menu-pick popup flows do not consult the envelope: picking a popup command from the menu while images are attached leaves the images visibly in the rail rather than refusing the interaction. Enter-submission is the enforced envelope boundary.
+- "A rejected batch publishes no durable object" covers exactly the pre-admission settlements (declaration, missing store, batch limit). A handler-level grammar rejection (`/goal pause` with images) and a post-admission cancellation settle AFTER the batch committed, leaving content-addressed objects without a referencing session event — harmless under sha256 dedup and the attachment store's deferred reference-aware GC, but not "no object was written".

.agents/notes/implemented/feature/2026-08-17-command-image-attachment-envelope.zh.md

@@ -0,0 +1,46 @@
+# Agent Note: Command image-attachment envelope
+
+Status: implemented
+
+[English](2026-08-17-command-image-attachment-envelope.md) | 中文
+
+## Problem
+
+Web composer 的一次提交是一个信封——草稿文本、已附加图片、投递模式——但两条提交平面对它的消费是不对称的。普通消息走 `defaultSink → conversation.sendSession`，图片被序列化进 prompt 内容并在成功后清除。被 claim 的斜杠命令走 `claim.submit(args, actx)`，一个纯文本事务：`/goal rebuild the cathedral` 带四张参考照片时，命令执行、草稿清空，图片却静默滞留在 composer 附件栏。模型从未看到它们，也没有任何界面提示。这个缺陷在契约层面而非某个漏掉的调用点：claim、裁决、宿主执行器都没有建模附件，因此任何命令都可能消费提交的文本一半而丢弃其余部分。
+
+合并两个平面从未在考虑范围内——[插件命令注册 Agent Note](2026-07-19-plugin-command-registration.md)刻意让人类命令留在模型平面之外，这个分离是正确的。问题在于信封在平面分叉处被拆散了。
+
+## Decision
+
+提交信封被端到端建模，每条命令路径要么整体消费它，要么响亮拒绝。
+
+**声明。**`CommandDefinition.input.images: boolean`（缺省为 false）声明 composer 图片是否可以随调用提交。该标志随冻结的 `CommandDescriptor` 经 `commands/list` 到达每个客户端，进入铸造出的 `CommandClaim`（`images: true`），再进入输入状态机发布的 claim 快照。
+
+**通用标识，图片专用载荷。**浏览器草稿与持久化引用已经使用 `DraftAttachmentId` 和 `AttachmentId`；命令 RPC 传输的是编码字节，而非图片标识。图片仍是唯一已经定义准入规则和模型块语义的非文本附件，因此 wire 保持 `EncodedImageAttachment[]`，声明保持 `input.images`。
+
+**执行器强制。**`CommandRuntime.execute(agent, line, images, signal)` 携带本次提交的 base64 图片（来自 `@deepseek-ai/dsh-attachment/types` 的 `EncodedImageAttachment`）。强制执行声明的是执行器而非 composer：把图片发给未声明的命令、附件存储缺失、批量超限，都会在处理器运行前以记录在案的 `command/done` 错误结算。准入经由 attachment 包的 `admitEncodedImages`——共享 wire 入口，强制执行规范 base64 并把批量准入（限额、校验、有序提交）委托给 `AttachmentStore.saveImages`——使两个 wire 端点（prompt RPC 与命令执行器）共享同一序列，被拒绝的批量不会发布任何持久化对象。通过准入的批量以冻结的有序 `ImageBlock` 数组挂在 `invocation.attachments` 上交给处理器。
+
+**模型可见性由生产方负责。**注册表自身绝不调度这些图片。`/goal` 在 create 或 edit 成功后通过 `agent.followup` 提交一条用户消息——图片块加固定文本 `Reference images for the goal objective.`——后续 Goal Round 从普通会话历史读取图片，goal 领域不存储附件状态。`/plan <message>` 把图片并入其 steer 的文本消息；不带参数的 `/plan` 则 steer 一条只含图片的用户消息，因为图片可能包含全部任务内容。不会发送模型输入的控制形式（`/goal pause`、`/plan off`）会直接返回错误，composer 的图片原地保留。plan 投影会把 `command/run` 视为候选选择，并在配对的 `command/done` 报错时丢弃它，因此被拒绝的带图 `/plan off` 不会留下待退出状态。
+
+**composer 的拒绝是可见横幅，一切保留。**ui-commands 的 `matchEnter` 从裁决收到 `SubmitEnvelope`（图片数量），对每条无法消费图片的回车路径抛出本地化的 `notice.imagesUnsupported` 拒绝：contribution 弹窗、decoration 弹窗、未声明的 claim、bare 分离执行。输入状态机发布一条错误通知，composer 通过瞬态 Toast 横幅呈现它，草稿与图片不动。已 claim 状态下的提交（空格或菜单 claim）由 facade 用 `conversation` 命名空间的同款文案把关。接受路径上，facade 经 hub 的 `commandImages` 管道序列化草稿图片、传给 `claim.submit`，仅在成功 outcome 后清除并释放；错误结果（包括生产方的语法拒绝）保留它们。
+
+## Testing
+
+注册表执行器强制、准入失败结算、冻结的调用附件由 `packages/interaction/commands/tests/commands.spec.ts` 覆盖；批量准入顺序与限额在 `packages/attachment/attachment/tests/admission.spec.ts`；生产方行为在 `packages/goal/command-goal/tests/command-goal.spec.ts` 与 `packages/plan/plan-mode/tests/plan-mode.spec.ts`；客户端拒绝与消费路径在 ui-commands、ui-conversation、ui-input-trigger 客户端套件；组装后应用流程在 apps/web 的 keyless 通道。
+
+## Alternatives considered
+
+- **附加图片时一律拦截命令（没有接受路径）**——被拒绝：可预测，但带参考图的 `/goal` 正是驱动这次修复的用例，用户的图片将完全没有通往模型的路径。
+- **任何命令后把滞留图片自动作为后续用户消息发送**——被拒绝：对宿主状态命令（`/model`、`/compact`）令人意外，且把消息契约从生产方挪到 composer，违反命令注册表「生产方负责模型可见工作」的规则。
+- **在 goal 领域存储附件引用并渲染进 Round 提示词**——被拒绝：需要持久化 goal schema 变更，且要么把图片块复制进每轮提示词，要么引入仅首轮的提示词形态；round 提示词不变量将需要附件状态。一条普通的已记录用户消息达到同样的模型可见性。
+- **只要命令成功就消费图片，不管语法**——被拒绝：`/goal pause` 带图会把图片静默丢弃，在更深一层重演原始缺陷。消费与生产方的显式成功绑定，语法不匹配返回错误。
+- **只在客户端强制**——被拒绝：schema 省略不是强制执行；直接 RPC 调用方可以绕过 composer。执行器自己结算声明。
+- **把命令 wire 泛化成多媒体标识**——被拒绝：两个标识已经是附件通用类型，wire 传输的是字节，其图片专用字段明确表达了 Host 强制执行的准入规则。文件和视频尚无共同的准入规则与模型可见语义，一个不带类型标记的多媒体标识也无法提供这些信息。出现第二种受支持附件时再引入泛化：命令信封扩展为带类型标记的附件联合类型，命令声明接受的类型，`AttachmentId` 保持不变。
+
+## Consequences
+
+- 任何命令路径都不可能消费提交的文本而滞留图片：契约强制整信封消费或可见拒绝，对现有与未来命令一体适用。
+- commands 包新增对 `dsh-attachment` 与 `dsh-llm` 的依赖，`commands/execute` 携带必填的 `images` wire 参数——每个调用方都显式陈述其信封。
+- `/goal` 与 `/plan` 获得参考图输入，代价是一条额外的已记录用户消息（goal）与 steer 消息中的图片块（plan），其中不带参数的 `/plan` 会产生只含图片的消息；所有这些输入的计费都与常规图片提示词相同。
+- 菜单点选的弹窗流程不查询信封：附有图片时从菜单点选弹窗命令，图片会可见地留在附件栏，而不是拒绝该交互。回车提交是被强制执行的信封边界。
+- 「被拒绝的批量不发布任何持久化对象」只覆盖准入前的三种结算（声明、存储缺失、批量超限）。handler 级语法拒绝（如 `/goal pause` 带图）与准入后取消发生在批量已提交之后，会留下没有会话事件引用的内容寻址对象——在 sha256 去重与附件存储延后的引用感知 GC 下无害，但并非「未写入任何对象」。

.agents/notes/implemented/feature/2026-08-18-pi-ai-wire-compat-surface.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/2026-08-18-pi-ai-wire-compat-surface.md
+2026-08-18-pi-ai-wire-compat-surface.md: 3da2db1ebdf67bcfaf8c872491356b0ef7d0ca89
+2026-08-18-pi-ai-wire-compat-surface.zh.md: ff9870f5863fb96ee026dfab1b96b4e1f3e6e238

.agents/notes/implemented/feature/2026-08-18-pi-ai-wire-compat-surface.md

@@ -0,0 +1,52 @@
+# Agent Note: pi-ai Wire-Compatibility Surface in llm-pi-ai
+
+Status: implemented
+
+English | [中文](2026-08-18-pi-ai-wire-compat-surface.zh.md)
+
+## Problem
+
+pi-ai shapes every request from the provider id and the baseURL — which role carries the system prompt, which field caps output, whether `store` and `stream_options` go out, whether tool definitions carry `strict`. For an endpoint its detection does not recognize, the answer is "this is OpenAI itself": `detectCompat` returns `supportsDeveloperRole: true`, `maxTokensField: "max_completion_tokens"`, `supportsStore: true`. A hand-declared route is by construction an endpoint pi-ai does not ship, so every such route received OpenAI's own request shape.
+
+The adapter offered two of pi-ai's thirty compat fields ([[2026-08-08-pi-ai-per-model-reasoning-declarations]] scoped them to "the switches pi-ai's reasoning dispatch reads"), and `supportsDeveloperRole` fell inside that scope while being absent from it: its send site is `model.reasoning && compat.supportsDeveloperRole`. A hand-declared model declaring `reasoningEfforts` therefore sent its system prompt as `role: "developer"`, which most OpenAI-compatible gateways reject, and no configuration could say otherwise — the gateway could not be connected at all.
+
+Writing the field anyway was worse than unsupported. schemastery passes unknown keys through, and resolution read only two names, so `compat: {supportsDeveloperRole: false}` validated, persisted, and was then dropped: the operator saw an accepted write and an unchanged failure. `maxTokensField` carried the same defect over a wider blast radius, since it shapes every request rather than only a reasoning model's.
+
+## Decision
+
+One drift gate per pi-ai compat type — keyed `Record<keyof OpenAICompletionsCompat | …, CompatDisposition>` — classifies every upstream field as `offer` or `withhold`. Thirty distinct fields, twenty offered. The line is what a private URL can imply: a deployment must be able to state what nothing can infer from an unrecognized endpoint, while a field pi-ai's installed catalog sets for a named vendor stays withheld, because a route reaching for `openRouterRouting` or `deferredToolsMode` is a catalog route that should be named as such and inherit the value.
+
+`PiAiCompatProfile` stays an explicit interface with per-field JSDoc — it is what a configuration surface renders and what `docs/config-catalog.md` pastes — and a type-level `AssertNever` over the symmetric difference proves it names exactly the offered set. The schemastery schema is declared `z<PiAiCompatProfile>`, and `exactOptionalPropertyTypes` is what makes that annotation load-bearing in both directions, so the four faces lock together: an upstream field added, a gate entry missing, an interface field forgotten, or a schema key omitted each fails compilation. Field *types* are derived from upstream rather than restated, and a second proof pins the profile assignable to the upstream compat types, so a widened value union cannot silently narrow what configuration accepts — the cast to `ModelCompat` at materialization would otherwise hide it.
+
+Protocol applicability is per field, and grouping follows the compat *type* rather than the protocol name: pi-ai gives `openai-responses`, `azure-openai-responses`, and `openai-codex-responses` one `OpenAIResponsesCompat`, so a switch settable on one is settable on all three. Keying by protocol name alone refused two shipped catalog routes the fields their own models declare. The protocol set is derived from `Model.compat`'s own conditional, so a release that gives a further protocol a compat type fails the gate list by name. A model-level switch its protocol does not take fails resolution naming what that protocol does offer; a route-level one lands on the models that read it and skips the rest, and is refused only when no model on the route could read it. `chatTemplateKwargs` is offered, which is what makes the two `chat-template` thinking formats nameable; nothing cross-checks that pairing, because the format in force may come from the catalog entry or from pi-ai's detection, neither of which resolution can read.
+
+Three kinds of `compat` key are refused where they are written rather than dropped: one no protocol declares, one a gate withholds, and one written with no value. The check runs over every key before any protocol resolves, so a misspelling fails even on a route whose models never reach the protocol that would have taken it. It reads raw keys deliberately: a withheld or undeclared name is absent from the schema, so schemastery cannot have materialized it and a person wrote it. The valueless case is the one that has to fail rather than be ignored — schemastery passes a YAML bare key through as null, and carrying it forward writes null over the installed catalog's value, leaving pi-ai's `??` reaching for its baseURL detection with the catalog layer skipped entirely. Fields carrying a value are then filtered separately, because schemastery materializes an absent dict as `{}` and `chatTemplateKwargs` is present on every parsed profile whether or not anyone wrote one.
+
+## Where a refusal lands
+
+Every check runs in `resolveProfiles`, which no request path re-enters: the adapter memoizes by raw-snapshot identity and `apply` resolves once eagerly. A refusal therefore reaches `settings.mutate` as `settings-rejected` before persistence, a `cordis.yml` `config:` block as a failed plugin mount, and a stored section as a failed `settings.register` at startup.
+
+An external edit to the settings file is the one path that cannot report: the provider watcher calls `publish()`, which catches a failing section, logs `settings: keeping last good "%s"`, and leaves the namespace serving its previous value. That is the settings seam's behavior for every schema and validator failure, not something this surface introduces, and closing it belongs to that seam rather than here. What changes for compat is the failure model, not the reporting: a key that formerly stayed inert forever now stops the next start.
+
+## Alternatives considered
+
+**Add `supportsDeveloperRole` alone.** It fixes the reported gateway and leaves `maxTokensField` — which shapes every request, not only a reasoning model's — breaking a whole class of endpoints, with the next upstream addition free to lag silently again.
+
+**Offer every upstream field.** pi-ai's own custom-provider documentation converges on a far smaller set, its flagship example naming six, and the remainder are vendor-bound switches its catalog already sets. Exposing `zaiToolStream` or `vercelGatewayRouting` on a hand-declared route offers a knob whose correct use is to not be a hand-declared route.
+
+**Key `compat` by protocol** (`compat: {openai-completions: {…}}`). A hand-declared route has exactly one `api`, so the nesting states what the route already said, and it breaks every profile written against the flat shape for nothing.
+
+**Accept an opaque passthrough dict.** The schema is also the shape a configuration surface renders and the declaration `verify-config-catalog` cross-checks, both of which an unstructured dict defeats; it would also let a responses-only field land on a completions model, which per-field applicability exists to refuse.
+
+**Warn instead of refusing an unknown key.** That is the posture that hid this defect for the life of the surface: an accepted write and an unchanged failure teaches the operator that the switch does not work, not that the name is wrong.
+
+**Suggest a near spelling on an unknown key.** No repository utility computes edit distance, and adding a dependency or hand-rolling one under the per-file coverage gate is disproportionate for a diagnostic. Naming the offered fields answers the same question deterministically: the vocabulary check runs before any protocol resolves, so it names the whole offered set, while the per-protocol refusal narrows to what that protocol takes.
+
+## Consequences
+
+- An OpenAI-compatible gateway that rejects the `developer` role, `max_completion_tokens`, `store`, `stream_options`, or `strict` is now configuration rather than an unreachable provider, and the same holds for an Anthropic-compatible gateway rejecting `temperature` or tool `cache_control`.
+- A pi-ai upgrade that adds a compat field fails the build until someone classifies it, which is how `chatTemplateKwargs` and the `chat-template` formats stopped being a standing exception.
+- Unknown compat keys join every other configuration error's failure model. The improvement over the previous silent drop is bounded by the settings seam: an external file edit still keeps its last good value and warns, so the operator's signal is a restart rather than the write.
+- **Deferred, not closed:** a route that repoints `api` and configures no compat at all keeps the installed entry's `compat` through the model literal's `...base` spread, in the *other* protocol's shape. Fields several compat types share (`supportsLongCacheRetention`, `sendSessionAffinityHeaders`) therefore cross protocols. It predates this surface — the early return it rides existed before — and is left for its own change.
+- **Deferred, not closed:** `publish()` reports a rejected stored section only through `ctx.logger.warn`, with no user-visible channel. It affects every settings namespace and is owned by `dsh-settings`.
+- [[2026-08-08-pi-ai-per-model-reasoning-declarations]] is partially superseded: its compat-scope statements are restated here, while its `reasoningEfforts` shape, the alternatives that shape beat, and `modelOverrides` remain the current authority.

.agents/notes/implemented/feature/2026-08-18-pi-ai-wire-compat-surface.zh.md

@@ -0,0 +1,52 @@
+# Agent Note: pi-ai Wire-Compatibility Surface in llm-pi-ai
+
+Status: implemented
+
+[English](2026-08-18-pi-ai-wire-compat-surface.md) | 中文
+
+## Problem
+
+pi-ai 依据提供方 id 与 baseURL 决定每个请求的形状——系统提示词由哪个角色承载、输出上限写在哪个字段、是否发出 `store` 与 `stream_options`、工具定义是否携带 `strict`。对于其检测无法识别的端点，答案是「这就是 OpenAI 本身」：`detectCompat` 返回 `supportsDeveloperRole: true`、`maxTokensField: "max_completion_tokens"`、`supportsStore: true`。而手工声明的路由按其构造就是 pi-ai 未随附的端点，于是每一条这样的路由都收到了 OpenAI 自己的请求形状。
+
+适配器只开放了 pi-ai 三十个 compat 字段中的两个（[[2026-08-08-pi-ai-per-model-reasoning-declarations]] 把它们限定为「pi-ai 推理分派读取的那些开关」），而 `supportsDeveloperRole` 恰恰落在该作用域之内却不在其中：它的发送点是 `model.reasoning && compat.supportsDeveloperRole`。因此一个声明了 `reasoningEfforts` 的手工声明模型会把系统提示词以 `role: "developer"` 发出——多数 OpenAI 兼容网关会拒绝该角色——而没有任何配置能够更正，该网关根本接不进来。
+
+硬写这个字段比不支持更糟。schemastery 会放行未知键，而解析只读取两个名字，于是 `compat: {supportsDeveloperRole: false}` 通过校验、落盘，随后被丢弃：运维看到的是一次被接受的写入和一个毫无变化的故障。`maxTokensField` 带着同一缺陷、却有更大的波及面，因为它塑造每一个请求，而不只是推理模型的请求。
+
+## Decision
+
+每个 pi-ai compat 类型一张漂移门禁——以 `Record<keyof OpenAICompletionsCompat | …, CompatDisposition>` 为键——把每一个上游字段分类为 `offer` 或 `withhold`。去重后三十个字段，开放二十个。分界线在于私有 URL 能推出什么：凡是无法从未识别端点推断的，部署方必须能够说出口；而 pi-ai 已安装 catalog 为具名厂商设定的字段保持扣留，因为伸手去够 `openRouterRouting` 或 `deferredToolsMode` 的路由，本就是一条应当以该厂商命名、并继承其值的 catalog 路由。
+
+`PiAiCompatProfile` 保持为带逐字段 JSDoc 的显式 interface——它是配置界面所渲染、也是 `docs/config-catalog.md` 所粘贴的东西——并由一个作用在对称差上的类型级 `AssertNever` 证明它恰好命名了开放集。schemastery schema 声明为 `z<PiAiCompatProfile>`，而使这条标注在两个方向上都真正吃劲的是 `exactOptionalPropertyTypes`，于是四个面互锁：上游新增字段、门禁漏一条、interface 忘记一个字段、schema 少一个键，都会在编译期失败。字段的**类型**派生自上游而非重述，另有一条证明把 profile 钉为可赋值给上游 compat 类型，因此被拓宽的值并集不会悄悄收窄配置所接受的范围——否则物化处对 `ModelCompat` 的强转会把它洗掉。
+
+协议适用性逐字段判断，且归组依据是 compat **类型**而非协议名：pi-ai 让 `openai-responses`、`azure-openai-responses` 与 `openai-codex-responses` 共用同一个 `OpenAIResponsesCompat`，因此可设在其中之一的开关，三者皆可设。仅按协议名归组曾使两条随附的 catalog 路由拿不到其自身模型所声明的字段。协议集派生自 `Model.compat` 自身的条件类型，因此某个版本若给别的协议加上 compat 类型，门禁列表会以点名的方式失败。模型级开关若其协议并不接受，解析失败并点名该协议实际提供哪些开关；路由级开关则落在读取它的模型上、跳过其余模型，只有当路由上没有任何模型能读取它时才被拒绝。`chatTemplateKwargs` 予以开放，这正是两个 `chat-template` 思考格式得以命名的前提；两者的配对不做交叉校验，因为实际生效的格式可能来自 catalog 条目或 pi-ai 的检测，而解析读不到那两层。
+
+三类 `compat` 键在其被写下之处遭到拒绝而非丢弃：没有任何协议声明的键、被门禁扣留的键，以及完全没有写值的键。该检查在任何协议解析之前遍历全部键，因此即便路由上的模型永远不会走到那个本会接受它的协议，笔误同样失败。它刻意读取原始键：被扣留或未声明的名字不在 schema 中，所以 schemastery 不可能物化它，写下它的必然是人。无值那一类是必须失败而不能忽略的：schemastery 会把 YAML 裸键放行为 null，照单收下就会用 null 写覆盖已安装 catalog 的值，随后 pi-ai 的 `??` 转而去够它的 baseURL 检测，catalog 这一层被整个跳过。随后再单独过滤携带值的字段，因为 schemastery 会把缺省的 dict 物化成 `{}`，于是无论有没有人写过，`chatTemplateKwargs` 都出现在每一个解析过的 profile 上。
+
+## Where a refusal lands
+
+所有检查都在 `resolveProfiles` 中运行，而请求路径不会重新进入它：适配器按原始快照的标识 memoize，且 `apply` 会主动预先解析一次。因此一次拒绝会以 `settings-rejected` 的形式在落盘之前抵达 `settings.mutate`，以插件挂载失败的形式抵达 `cordis.yml` 的 `config:` 块，以 `settings.register` 启动失败的形式抵达已存的 section。
+
+对 settings 文件的外部编辑是唯一无法报告的路径：提供方监听器调用 `publish()`，它捕获失败的 section、记录 `settings: keeping last good "%s"`，并让该 namespace 继续服务其先前的值。这是 settings seam 对每一种 schema 与校验器失败的既有行为，并非本次开放引入，弥合它属于那个 seam 而不属于此处。对 compat 而言改变的是失败模型而非报告方式：一个从前永远静默无效的键，如今会拦下下一次启动。
+
+## Alternatives considered
+
+**只补 `supportsDeveloperRole`。** 它修好了报告中的那个网关，却放任 `maxTokensField`——它塑造每一个请求，而不只是推理模型的请求——继续拖垮一整类端点，而且下一个上游新增字段依然可以静默落后。
+
+**开放全部上游字段。** pi-ai 自己的 custom-provider 文档收敛到一个小得多的集合，其旗舰示例只点名六个，其余都是其 catalog 已经设定好的厂商绑定开关。在手工声明路由上暴露 `zaiToolStream` 或 `vercelGatewayRouting`，等于提供一个「正确用法是别做手工声明路由」的旋钮。
+
+**把 `compat` 按协议分层**（`compat: {openai-completions: {…}}`）。手工声明路由恰好只有一个 `api`，因此这层嵌套只是复述路由已经说过的事，还白白破坏了所有按扁平形状写下的 profile。
+
+**接受一个不透明的透传 dict。** 该 schema 同时是配置界面渲染的形状、也是 `verify-config-catalog` 交叉校验的声明，无结构的 dict 会同时击溃两者；它还会让 responses 独有的字段落到 completions 模型上，而逐字段适用性正是为拒绝这种情况而存在。
+
+**未知键只告警不拒绝。** 这恰恰是让本缺陷伴随该面存活至今的姿态：一次被接受的写入加一个毫无变化的故障，教给运维的是「这个开关没用」，而不是「这个名字写错了」。
+
+**为未知键给出近似拼写建议。** 仓库中没有计算编辑距离的工具，在逐文件覆盖率门禁之下为一条诊断引入依赖或手搓一个都不成比例。点名开放字段能确定地回答同一个问题：词汇检查跑在任何协议解析之前，因此它列出整个开放集，而按协议的拒绝则收窄到该协议实际接受的字段。
+
+## Consequences
+
+- 拒绝 `developer` 角色、`max_completion_tokens`、`store`、`stream_options` 或 `strict` 的 OpenAI 兼容网关，如今属于配置问题而非无法接入的提供方；拒绝 `temperature` 或工具 `cache_control` 的 Anthropic 兼容网关同理。
+- pi-ai 升级新增 compat 字段会使构建失败，直到有人为它做出分类——`chatTemplateKwargs` 与那两个 `chat-template` 格式正是因此不再是一项长期例外。
+- 未知 compat 键并入了其余所有配置错误的失败模型。相对此前静默丢弃的改善程度受 settings seam 限制：外部文件编辑仍会保留其上一个有效值并告警，因此运维拿到的信号是一次重启，而不是那次写入。
+- **搁置而非解决：** 改指 `api` 且完全未配置 compat 的路由，会经模型字面量的 `...base` 展开保留已安装条目的 `compat`，且形状属于**另一个**协议。多个 compat 类型共有的字段（`supportsLongCacheRetention`、`sendSessionAffinityHeaders`）因而会跨协议串味。它早于本面存在——其所依附的提前返回本就在那里——留给独立的一次改动处理。
+- **搁置而非解决：** `publish()` 对被拒绝的已存 section 只通过 `ctx.logger.warn` 报告，没有面向用户的通道。它影响每一个 settings namespace，归属 `dsh-settings`。
+- [[2026-08-08-pi-ai-per-model-reasoning-declarations]] 被部分取代：其 compat 作用域的陈述在此重述，而其 `reasoningEfforts` 形状、该形状所击败的备选方案以及 `modelOverrides` 仍是当前权威。

.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.md
+2026-08-18-product-subagent-failure-facts.md: 50d8e918f288a6b8a9b90474499b2ed20731643f
+2026-08-18-product-subagent-failure-facts.zh.md: 7dc5a73637c90a1ca1123c86d754f95c68498fd9

.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.md

@@ -0,0 +1,87 @@
+# Agent Note: Product subagents expose bounded structured failure facts
+
+Status: implemented
+
+English | [中文](2026-08-18-product-subagent-failure-facts.zh.md)
+
+## Problem
+
+The [Claude Code and Codex product providers](2026-08-04-claude-code-and-codex-subagent-backends.md) receive structured product failures, but a published run historically flattened most of them to the shared `error` stop reason. Product logs retained detail that the foreground parent and a [one-shot background Job](2026-08-12-product-subagent-one-shot-background-tasks.md) could not use to distinguish a product limit, an execution failure, or an early process exit.
+
+Copying SDK error text, app-server payloads, or stderr into the result would expose task text, paths, environment values, credentials, or product internals. Adding shared error fields would also make the provider-neutral [subagent seam](2026-06-21-subagent-capability-seam.md) own product version vocabularies that change independently.
+
+## Decision
+
+Each product Provider owns the mapping from its pinned official error union, current operation, and managed process outcome to one fixed safe diagnostic line. `SubagentResult` remains unchanged: consumers receive the existing bounded `diagnostic` string and do not parse its product-private fields.
+
+### Safe diagnostic
+
+The structured line has this fixed order:
+
+```text
+Product subagent failure (product: <product>; stage: <stage>; category: <category>; HTTP status: <status>; exit code: <code>; signal: <signal>)
+```
+
+The Provider omits unavailable optional fields. Exit code and signal are independent facts and are each retained when observed. A contributing permission decision from the [non-interactive permissions decision](2026-08-15-product-subagent-noninteractive-permissions.md) follows the structured line; the latest safe permission fact remains operation-local. The shared result boundary limits the complete text to 4096 UTF-8 bytes.
+
+Successful results and local cancellation expose no failure fact. Raw product errors, stderr, tool input, paths, environment values, credentials, and protocol payloads never enter the diagnostic. Startup and cleanup rejections use the same safe line in their Error message. Original failures remain on internal cause chains; Provider Host logs and forwarded stderr remain product-local observation only.
+
+### Claude Code facts
+
+Agent SDK 0.3.220 defines four error subtypes: `error_during_execution`, `error_max_turns`, `error_max_budget_usd`, and `error_max_structured_output_retries`. The Claude Code Provider preserves each exact subtype as the category while keeping the shared stop reason `error`. An error-marked or blank success uses `invalid-success`, a missing result uses `missing-result`, a process exit before an SDK terminal result uses `process-exit`, and an unrecognized value or exception uses `unknown` without copying the value.
+
+| Stage | Owned operation | Observable failure |
+| --- | --- | --- |
+| `query-start` | SDK query construction, native platform-payload startup, and unpublished rollback | `start()` rejects with fixed safe facts and any process outcome observed before rollback |
+| `query-run` | Published SDK message iteration and strict terminal-result validation | The run resolves as `error` with the exact known subtype or a fixed result category |
+| `process` | Managed CLI exits before the SDK supplies a terminal result | The run resolves as `error` with `process-exit` and the available exit code and signal |
+| `teardown` | Query close and managed process-tree release | `dispose()` rejects independently with fixed safe facts after cleanup still reaches its final exit wait |
+
+### Codex facts
+
+Codex app-server 0.147.0 defines eleven string categories and five object variants. The Provider preserves `contextWindowExceeded`, `sessionBudgetExceeded`, `usageLimitExceeded`, `serverOverloaded`, `cyberPolicy`, `internalServerError`, `unauthorized`, `badRequest`, `threadRollbackFailed`, `sandboxError`, and `other`. It also preserves `httpConnectionFailed`, `responseStreamConnectionFailed`, `responseStreamDisconnected`, `responseTooManyFailedAttempts`, and `activeTurnNotSteerable`; the four connection/stream variants retain numeric `httpStatusCode`, while the active-turn variant does not expose `turnKind`. Unknown strings, objects with another variant set, malformed values, and unclassified exceptions use `unknown`.
+
+| Stage | Owned operation | Observable failure |
+| --- | --- | --- |
+| `initialize` | App-server spawn and initialize/initialized handshake | `start()` rejects with fixed safe facts and any process outcome already observed |
+| `thread-start` | Ephemeral `thread/start` request and response validation | `start()` rejects with the thread stage and any available process outcome |
+| `turn-start` | Published `turn/start` request, provisional ids, and early frames | The run resolves as `error` with a safe unknown fallback when no structured category exists |
+| `turn` | Terminal notification, final-answer selection, and error-info mapping | The complete category and optional HTTP status reach the non-completed result |
+| `process` | Managed app-server exits before another terminal path settles | The run resolves as `error` with `process-exit` and any available code and signal |
+| `teardown` | Wire close and process-tree release | `dispose()` rejects independently; startup rollback aggregation exposes both startup and teardown lines |
+
+`contextWindowExceeded` remains `max-tokens`; every other known or unknown Codex category remains `error`, and `cyberPolicy` does not become `refusal`.
+
+### Ownership and lifecycle
+
+| Fact or resource | Owner | Consumer behavior |
+| --- | --- | --- |
+| Product error category | Pinned official SDK or app-server version | The Provider maps only the declared structured union and uses `unknown` outside it |
+| Current failure stage | Product Provider operation | Derived at the failure site; never persisted or used as a recovery state |
+| Exit code and signal | `dsh-subprocess` process handle | The Provider displays observed values without inferring missing ones |
+| Diagnostic bytes and delivery | `dsh-subagent`, foreground tool, and Job runtime | The same bounded text is presented separately from assistant output in both scheduling modes |
+| Raw product failure | Product runtime, internal cause chain, and Host observation | It remains internal and never becomes model-visible result text |
+
+## Verification
+
+Claude Code package tests pin all four SDK subtypes, invalid success, missing result, unknown values and exceptions, all four stages, independent exit code and signal fields, permission-fact ordering, sanitization, successful-result and cancellation omission, concurrent-run isolation, and cleanup completion. Codex package tests pin all sixteen error-info variants, HTTP status presence and absence, all six stages, unknown fallback, stop-reason preservation, permission ordering, sanitization, cancellation, concurrency, and cleanup aggregation. The real SDK/CLI fixture produces an actual Claude `error_max_turns`; the real app-server fixture produces an actual Codex `internalServerError`; both fixtures cover process/protocol failure and whole-tree quiescence. The keyless ACP snapshot records each product's exact diagnostic in foreground error output, a background completion notice, and `job_output`.
+
+## Alternatives considered
+
+**Return raw SDK errors, app-server payloads, or stderr.** These values can contain commands, paths, workspace content, environment values, credentials, or upstream prose. A fixed allowlisted mapping preserves actionable facts without expanding the model-visible trust boundary.
+
+**Add a shared product-error enum or structured result fields.** Claude Code and Codex version their error unions independently. A shared enum would duplicate those authorities and force unrelated Providers and consumers to track product releases.
+
+**Parse generic stderr and exception messages.** Free-form text is neither stable nor safe. Only pinned structured product fields and the managed process outcome qualify as diagnostic input.
+
+**Persist stages or add a recovery controller.** The stage is derived from the current call site only when a failure is reported. Persistence, retries, resume, and remediation need separate ownership and user contracts.
+
+**Map product limits to new shared stop reasons.** Claude Code turn and budget limits are not token-window exhaustion, and an error category does not establish refusal semantics. Existing stop reasons remain unchanged.
+
+## Consequences
+
+The parent can distinguish important Claude Code limits and Codex budget, usage, service, policy, request, connection, stream, rollback, sandbox, and active-turn failures without receiving raw product text. Foreground and background scheduling preserve the same fact because both consume one `SubagentResult`.
+
+The diagnostic is display text rather than a new public protocol. Callers may present it but must not branch on its punctuation or product-private category names. A pinned product-version upgrade must update the Provider mapping and evidence when its official error union changes.
+
+This decision adds no product session persistence, retry policy, recovery state, stderr classifier, authentication or configuration taxonomy, progress stream, or human interaction path.

.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.zh.md

@@ -0,0 +1,87 @@
+# Agent Note: 产品 subagent 公开有界结构化失败事实
+
+Status: implemented
+
+[English](2026-08-18-product-subagent-failure-facts.md) | 中文
+
+## Problem
+
+[Claude Code 与 Codex 产品提供方](2026-08-04-claude-code-and-codex-subagent-backends.md)会收到结构化产品失败，但已发布运行以往会把其中大多数压成共享的 `error` 终止原因。产品日志保留了细节，前台父 agent 与[一次性后台 Job](2026-08-12-product-subagent-one-shot-background-tasks.md)却无法据此区分产品限制、执行失败或进程提前退出。
+
+若把 SDK 错误文本、app-server payload 或 stderr 复制进结果，就会暴露任务文本、路径、环境值、凭证或产品内部信息。若增加共享错误字段，又会让提供方无关的 [subagent seam](2026-06-21-subagent-capability-seam.md)拥有彼此独立变化的产品版本词汇。
+
+## Decision
+
+每个产品提供方分别拥有从锁定版本官方错误联合、当前操作和受管进程结果到一行固定安全诊断的映射。`SubagentResult` 保持不变：消费方仍接收现有的有界 `diagnostic` 字符串，而且不解析其中由产品私有的字段。
+
+### 安全诊断
+
+结构化行采用以下固定顺序：
+
+```text
+Product subagent failure (product: <product>; stage: <stage>; category: <category>; HTTP status: <status>; exit code: <code>; signal: <signal>)
+```
+
+提供方会省略不可用的可选字段。退出码与信号是相互独立的事实，只要已观测到就分别保留。来自[非交互权限决策](2026-08-15-product-subagent-noninteractive-permissions.md)且参与失败的权限决定会跟在结构化行之后；最新的安全权限事实仍只属于当前操作。共享结果边界会把完整文本限制在 4096 个 UTF-8 字节以内。
+
+成功结果与本地取消都不公开失败事实。原始产品错误、stderr、工具输入、路径、环境值、凭证和协议 payload 绝不会进入诊断。启动与清理拒绝会在 Error 消息中使用同一安全行。原始失败保留在内部 cause 链中；提供方 Host 日志与转发的 stderr 也只作为产品本地观测。
+
+### Claude Code 事实
+
+Agent SDK 0.3.220 定义四种错误子类型：`error_during_execution`、`error_max_turns`、`error_max_budget_usd` 和 `error_max_structured_output_retries`。Claude Code 提供方会把每种准确子类型保留为类别，同时维持共享终止原因 `error`。标记为错误或内容空白的成功消息使用 `invalid-success`，缺失结果使用 `missing-result`，SDK 给出终态结果前发生的进程退出使用 `process-exit`，无法识别的值或异常使用 `unknown`，且不会复制原值。
+
+| 阶段 | 归属操作 | 可观察失败 |
+| --- | --- | --- |
+| `query-start` | SDK query 构造、原生平台载荷启动与未发布回滚 | `start()` 以固定安全事实和回滚前已观测到的进程结果拒绝 |
+| `query-run` | 已发布 SDK 消息迭代与严格终态结果校验 | 运行以 `error` 兑现，并携带准确已知子类型或固定结果类别 |
+| `process` | SDK 提供终态结果之前受管 CLI 已退出 | 运行以 `error` 兑现，并携带 `process-exit` 以及可用的退出码和信号 |
+| `teardown` | Query 关闭与受管进程树释放 | `dispose()` 独立拒绝并携带固定安全事实，同时清理仍会完成最终退出等待 |
+
+### Codex 事实
+
+Codex app-server 0.147.0 定义十一种字符串类别与五种对象 variant。提供方会保留 `contextWindowExceeded`、`sessionBudgetExceeded`、`usageLimitExceeded`、`serverOverloaded`、`cyberPolicy`、`internalServerError`、`unauthorized`、`badRequest`、`threadRollbackFailed`、`sandboxError` 和 `other`。它还会保留 `httpConnectionFailed`、`responseStreamConnectionFailed`、`responseStreamDisconnected`、`responseTooManyFailedAttempts` 与 `activeTurnNotSteerable`；四种连接／stream variant 会保留数值 `httpStatusCode`，而 active-turn variant 不公开 `turnKind`。未知字符串、同时含其他 variant 的对象、格式错误值与未分类异常统一使用 `unknown`。
+
+| 阶段 | 归属操作 | 可观察失败 |
+| --- | --- | --- |
+| `initialize` | App-server spawn 与 initialize/initialized 握手 | `start()` 以固定安全事实和已经观测到的进程结果拒绝 |
+| `thread-start` | 临时 `thread/start` 请求与响应校验 | `start()` 以线程阶段和可用进程结果拒绝 |
+| `turn-start` | 已发布 `turn/start` 请求、暂定 id 与早到 frame | 没有结构化类别时，运行以 `error` 和安全 unknown 回退兑现 |
+| `turn` | 终态通知、最终答案选择与 error-info 映射 | 完整类别与可选 HTTP status 进入非完成结果 |
+| `process` | 受管 app-server 在另一终态路径结算前退出 | 运行以 `error` 兑现，并携带 `process-exit` 以及可用的退出码与信号 |
+| `teardown` | Wire 关闭与进程树释放 | `dispose()` 独立拒绝；启动回滚聚合会同时公开启动与 teardown 两行 |
+
+`contextWindowExceeded` 仍是 `max-tokens`；其他所有已知或未知 Codex 类别仍是 `error`，`cyberPolicy` 不会变成 `refusal`。
+
+### 所有权与生命周期
+
+| 事实或资源 | Owner | 消费方行为 |
+| --- | --- | --- |
+| 产品错误类别 | 锁定版本的官方 SDK 或 app-server | 提供方只映射已声明的结构化联合，并对联合外值使用 `unknown` |
+| 当前失败阶段 | 产品提供方操作 | 只在失败点派生；绝不持久化，也不作为恢复状态 |
+| 退出码与信号 | `dsh-subprocess` 进程句柄 | 提供方展示已观测值，不推测缺失值 |
+| 诊断字节与送达 | `dsh-subagent`、前台工具与 Job 运行时 | 两种调度模式都把同一份有界文本与 assistant 输出分开呈现 |
+| 原始产品失败 | 产品运行时、内部 cause 链与 Host 观测 | 只保留在内部，绝不成为模型可见的结果文本 |
+
+## Verification
+
+Claude Code 包测试固定四种 SDK 子类型、无效成功、缺失结果、未知值与异常、四个阶段、相互独立的退出码与信号字段、权限事实顺序、脱敏、成功结果与取消时省略诊断、并发运行隔离和清理完成。Codex 包测试固定全部十六种 error-info variant、HTTP status 存在与缺失、六个阶段、unknown 回退、终止原因保持不变、权限顺序、脱敏、取消、并发与清理聚合。真实 SDK/CLI fixture 会产生真实的 Claude `error_max_turns`，真实 app-server fixture 会产生真实的 Codex `internalServerError`；两个 fixture 都覆盖进程／协议失败与整棵进程树完全停稳。无密钥 ACP snapshot 会在前台错误输出、后台完成通知和 `job_output` 中记录两个产品各自的准确诊断。
+
+## Alternatives considered
+
+**返回原始 SDK 错误、app-server payload 或 stderr。** 这些值可能包含命令、路径、工作区内容、环境值、凭证或上游文本。固定白名单映射可以保留可操作事实，同时不扩大模型可见的信任边界。
+
+**增加共享产品错误 enum 或结构化结果字段。** Claude Code 与 Codex 各自独立版本化错误联合。共享 enum 会复制这些权威，并迫使无关提供方和消费方跟随产品版本。
+
+**解析通用 stderr 与异常消息。** 自由文本既不稳定也不安全。只有锁定版本产品提供的结构化字段和受管进程结果可以成为诊断输入。
+
+**持久化阶段或增加恢复控制器。** 阶段只在报告失败时从当前调用点派生。持久化、重试、resume 与修复需要独立的所有权和用户约定。
+
+**把产品限制映射为新的共享终止原因。** Claude Code 的轮次和预算限制并不表示 token 窗口耗尽，错误类别也不能证明拒绝语义。既有终止原因保持不变。
+
+## Consequences
+
+父 agent 可以区分重要的 Claude Code 限制，以及 Codex 预算、用量、服务、策略、请求、连接、stream、回滚、sandbox 和 active-turn 失败，而不会收到原始产品文本。前台与后台调度会保留同一事实，因为二者都消费同一个 `SubagentResult`。
+
+诊断只是展示文本，不是新的公开协议。调用方可以呈现它，但不得根据其标点或产品私有类别名称进行分支。锁定产品版本升级并改变官方错误联合时，必须同步更新提供方映射与证据。
+
+本决策不增加产品会话持久化、重试策略、恢复状态、stderr 分类器、身份验证或配置分类体系、进度流或人工交互路径。

.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.md
+2026-08-18-web-home-path-tilde.md: b148833bab09eadce4c9c1a362dd99d04eba5977
+2026-08-18-web-home-path-tilde.zh.md: 9d15cd6dca1128927389d5731dff6bf831cffe76

.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.md

@@ -0,0 +1,37 @@
+# Agent Note: Web UI abbreviates POSIX home paths as `~`
+
+Status: implemented
+
+English | [中文](2026-08-18-web-home-path-tilde.zh.md)
+
+## Problem
+
+Workspace hover cards and Tool call summaries showed full POSIX home paths. Those strings are long, repeat the same prefix on every row, and make the sidebar and transcript harder to scan. Windows paths must stay verbatim because `~` is not a Windows filesystem convention.
+
+## Decision
+
+`host.describe` reports the host account `home` as a required field. Client and Host ship together, so the field is required rather than optional. ApiProxy fills it from `homedir()` at describe time.
+
+`abbreviateHomePath` in `dsh-client-runtime` is the display-only helper. It returns `~` or `~/…` when the path is the POSIX home or a descendant, and leaves the path unchanged when `home` is missing, empty, or `/`, when either value is a Windows drive or UNC path, or when the match is only a prefix (`/Users/u` does not claim `/Users/u2`). Tool summaries run workspace-relative shortening first, then this helper, so a path inside the session cwd stays short. `filePath`, Host open, and Workspace hover copy keep the authored filesystem path.
+
+`ui-tool` and `ui-workspace` inject `connection.hostDescription` at their own slot registrations. ChatView does not grow a Host-description hook. The field is required on `ConnectionHandle`; test fakes supply a source whose snapshot may be undefined before connect.
+
+The fixture Host home is `/home/fixture`. A second fixture Workspace at `/home/fixture/Documents/project` lets assembled replay hover `~/Documents/project` without moving the existing `/tmp/fixture` account. TerminalBlock's own prompt-label collapse is unchanged.
+
+## Alternatives considered
+
+**Guess `/Users` or `/home` without the real home.** Rejected because a shared prefix is not an account home, and `/Users/shared` or `/home/src` would abbreviate incorrectly.
+
+**Abbreviate Windows `%USERPROFILE%` as `~` as well.** Rejected because the acceptance rule keeps Windows paths verbatim, and `~` is not how Explorer or `cmd` spell those paths.
+
+**Put the helper in `dsh-home-paths`.** Rejected because that package expands configuration tildes on Node; this helper is a browser display rewrite and must not pull Node `os` into client bundles.
+
+**Thread `home` from ChatView owner props.** Rejected because it enlarges the conversation inject face and every ChatView test harness for a display fact only Tool and Workspace cards consume.
+
+## Consequences
+
+POSIX home-rooted Workspace hover paths and leftover Tool path summaries display as `~`. Copy and open still use the full path. Windows drive and UNC paths never become `~`. A Host that reports `/` as home does not turn the whole filesystem into `~`. Before the first describe, or while reconnecting, the source snapshot is undefined and paths stay unabbreviated.
+
+## Testing
+
+Package tests cover `abbreviateHomePath`, `toolRowModel` / `readCardModel` home abbreviation, Workspace hover display versus copy, and `host.describe` schema plus live `homedir()`. Assembled replay `apps/web/tests/home-path-tilde.snapshot.ts` hovers the fixture home-descendant Workspace. Product-GUI PRs still record a real-browser GIF of the hover card.

.agents/notes/implemented/feature/2026-08-18-web-home-path-tilde.zh.md

@@ -0,0 +1,37 @@
+# Agent Note: Web UI abbreviates POSIX home paths as `~`
+
+Status: implemented
+
+[English](2026-08-18-web-home-path-tilde.md) | 中文
+
+## Problem
+
+Workspace 悬停卡片和 Tool 调用摘要会显示完整的 POSIX 家目录路径。这些字符串很长，每行重复同一前缀，侧边栏和对话记录更难扫读。Windows 路径必须保持原样，因为 `~` 不是 Windows 文件系统约定。
+
+## Decision
+
+`host.describe` 把宿主账户的 `home` 作为必填字段上报。Client 与 Host 一同发布，因此该字段是必填而不是可选。ApiProxy 在 describe 时用 `homedir()` 填入。
+
+`dsh-client-runtime` 中的 `abbreviateHomePath` 是仅用于展示的辅助函数。当路径是 POSIX 家目录或其后代时返回 `~` 或 `~/…`；`home` 缺失、为空或为 `/`，任一侧是 Windows 盘符或 UNC 路径，或只是前缀命中（`/Users/u` 不能收走 `/Users/u2`）时，路径保持不变。Tool 摘要先做工作区相对缩短，再调用该辅助函数，因此会话 cwd 内的路径仍然更短。`filePath`、Host 打开以及 Workspace 悬停复制仍使用作者给出的文件系统路径。
+
+`ui-tool` 与 `ui-workspace` 在各自的 slot 注册上注入 `connection.hostDescription`。ChatView 不增加 Host 描述钩子。该字段在 `ConnectionHandle` 上是必填的；测试假对象提供一个来源，其快照在连接完成前可以为 undefined。
+
+fixture 的 Host 家目录是 `/home/fixture`。第二个 fixture Workspace 位于 `/home/fixture/Documents/project`，组装回放可以悬停出 `~/Documents/project`，而不必移动现有的 `/tmp/fixture` 账户。TerminalBlock 自有的提示符标签折叠保持不变。
+
+## Alternatives considered
+
+**在没有真实 home 的情况下猜测 `/Users` 或 `/home`。** 否决，因为共享前缀不是账户家目录，`/Users/shared` 或 `/home/src` 会被错误缩写。
+
+**同样把 Windows `%USERPROFILE%` 缩写成 `~`。** 否决，因为验收规则要求 Windows 路径保持原样，而且 Explorer 与 `cmd` 并不这样拼写这些路径。
+
+**把辅助函数放进 `dsh-home-paths`。** 否决，因为该包在 Node 上展开配置里的波浪号；本辅助函数是浏览器展示改写，不能把 Node `os` 拉进 client 包。
+
+**从 ChatView owner props 向下传递 `home`。** 否决，因为它会扩大 conversation 注入面和每一份 ChatView 测试夹具，而只有 Tool 与 Workspace 卡片消费这个展示事实。
+
+## Consequences
+
+POSIX 家目录下的 Workspace 悬停路径，以及缩短 cwd 后仍落在家目录里的 Tool 路径摘要，会显示为 `~`。复制与打开仍使用完整路径。Windows 盘符和 UNC 路径永远不会变成 `~`。若 Host 把 `/` 报成 home，不会把整个文件系统收成 `~`。首次 describe 之前或重连期间，来源快照为 undefined，路径保持未缩写。
+
+## Testing
+
+包测试覆盖 `abbreviateHomePath`、`toolRowModel`／`readCardModel` 的家目录缩写、Workspace 悬停展示与复制，以及 `host.describe` schema 与实时 `homedir()`。组装回放 `apps/web/tests/home-path-tilde.snapshot.ts` 悬停 fixture 中位于家目录下的 Workspace。面向产品 GUI 的 PR 仍需录制悬停卡片的真实浏览器 GIF。

.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.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/2026-08-19-direct-deepseek-vision-input.md
+2026-08-19-direct-deepseek-vision-input.md: 5c2f2ea3ff87b58906ce76caf9f611e07f3e2d04
+2026-08-19-direct-deepseek-vision-input.zh.md: 3aea6b6a4f27f7116c1cb935b1719dfbcf7ed8fc

.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.md

@@ -0,0 +1,34 @@
+# Agent Note: Direct DeepSeek vision input
+
+Status: implemented
+
+English | [中文](2026-08-19-direct-deepseek-vision-input.zh.md)
+
+## Problem
+
+DeepSeek vision deployments use the chat-completions image protocol, but the direct `deepseek-official` adapter declares every catalog and pass-through model text-only and rejects every `ImageBlock`. The durable attachment path therefore works only through configurable pi-ai routes, and a deployment cannot pass user uploads or image-bearing tool results through the direct provider.
+
+## Decision
+
+The direct adapter lets a configured model opt in with `inputModalities: [text, image]`; validation rejects empty, unknown, or duplicate modalities. Flash, Pro, unlisted ids, and configured models that omit `inputModalities` remain explicitly text-only. The shipped catalog does not advertise `deepseek-v4-flash-vision-exp` until its model endpoint is ready, so the model selector cannot offer an unavailable route; deployment and snapshot catalogs can enable their exact vision model independently.
+
+The adapter resolves `ctx.attachments` per image request, reads each retained durable reference with the request signal, and serializes verified bytes as ordered OpenAI-compatible `image_url` data URLs. Text-only user messages retain string content. Tool results retain string-only `tool` messages; image-only results use `(see attached image)`, and consecutive retained tool-result images follow in one `user` message beginning `Attached image(s) from tool result:`. System and assistant history images fail with `UNSUPPORTED_CONTENT` before attachment or network I/O.
+
+The direct adapter and pi-ai conversion share the deterministic [request-level image payload bound](../bug-fix/2026-08-18-request-image-payload-bound.md). Both default to 20 MiB of accumulated base64 payload, replace oldest image occurrences with the same fixed placeholder, and never read omitted attachments. Direct HTTP 413 responses are `INVALID_REQUEST`; attachment failures retain their stable attachment code rather than becoming `TRANSPORT`.
+
+Canonical messages continue to store only `ImageAttachmentRef`. Data URLs exist only while preparing one provider request, so no session event, persistence format, API schema, or SDK projection changes. The route accepts PNG, JPEG, WebP, and GIF already admitted by the attachment service. External image URLs, the Files API, and image output remain unsupported.
+
+## Alternatives considered
+
+- **Use only the pi-ai DeepSeek provider.** Its generic multimodal path proves the content conversion, but it does not make the direct official route truthful or usable with the official model id.
+- **Declare the whole provider image-capable.** This would let Flash, Pro, and unknown pass-through ids accept durable images that their exact wire model cannot promise to consume. Capability remains exact-model metadata.
+- **Send images inside `tool` message content.** The documented compatible form keeps tool content a string. A following user message avoids relying on an undocumented multimodal tool-role form while preserving call-result order.
+- **Add external URLs or Files uploads.** Both require new canonical input, authorization, lifetime, cleanup, and replay decisions. Transient base64 uses the existing durable attachment contract without expanding those concerns.
+
+## Verification
+
+Package tests pin model discovery and fallback capabilities, configuration validation and live settings updates, user and tool-result wire messages, all admitted MIME types, cancellation, attachment failures, 413 classification, exact image-bound behavior, and pi-ai equivalence. A keyless assembled ACP request records the native adapter's tool-result data URL and oldest-image placeholder.
+
+## Consequences
+
+Configured DeepSeek vision routes can consume durable user and tool-result images without changing session durability or response streaming. Repeated history still expands request bodies, but deterministic oldest-first offload bounds the dominant payload and leaves headroom below the official 30 MiB request-body limit. Image token pricing remains provider-owned because the official image token formula is not available.

.agents/notes/implemented/feature/2026-08-19-direct-deepseek-vision-input.zh.md

@@ -0,0 +1,34 @@
+# Agent Note: 直接 DeepSeek 视觉输入
+
+Status: implemented
+
+[English](2026-08-19-direct-deepseek-vision-input.md) | 中文
+
+## Problem
+
+DeepSeek 视觉部署使用 chat-completions 图片协议，但直接 `deepseek-official` 适配器把所有 catalog 与原样传递模型都声明为仅文本，并拒绝每一个 `ImageBlock`。因此，持久附件路径只能经可配置 pi-ai 路由工作，部署方无法通过直接提供方传递用户上传或包含图片的工具结果。
+
+## Decision
+
+直接适配器允许已配置模型通过 `inputModalities: [text, image]` 选择加入；校验会拒绝空列表、未知模态或重复模态。Flash、Pro、未列出 id，以及省略 `inputModalities` 的已配置模型仍明确仅支持文本。在模型端点就绪前，随附目录不会公布 `deepseek-v4-flash-vision-exp`，因此模型选择器不会提供不可用路由；部署与 snapshot 目录可以独立启用其确切视觉模型。
+
+适配器会对每个图片请求解析 `ctx.attachments`，用请求 signal 读取每个保留的持久引用，并将校验后的字节按顺序序列化为 OpenAI 兼容的 `image_url` data URL。纯文本 user 消息保留字符串内容。工具结果保留仅字符串的 `tool` 消息；仅含图片的结果使用 `(see attached image)`，连续工具结果中保留的图片随后合并进一条以 `Attached image(s) from tool result:` 开头的 `user` 消息。System 与 assistant 历史图片会在附件或网络 I/O 前以 `UNSUPPORTED_CONTENT` 失败。
+
+直接适配器与 pi-ai 转换共享确定性的[请求级图片载荷上限](../bug-fix/2026-08-18-request-image-payload-bound.md)。两者都以 20 MiB 累计 base64 payload 为默认值，用相同固定占位文本替换最旧的图片出现位置，并且绝不读取被省略的附件。直接 HTTP 413 响应归类为 `INVALID_REQUEST`；附件失败会保留其稳定附件 code，不会变成 `TRANSPORT`。
+
+规范消息继续只存储 `ImageAttachmentRef`。Data URL 只在准备单次提供方请求时存在，因此无需修改会话事件、持久化格式、API schema 或 SDK 投影。路由接受已经由附件服务准入的 PNG、JPEG、WebP 和 GIF。不支持外部图片 URL、Files API 和图片输出。
+
+## Alternatives considered
+
+- **只使用 pi-ai DeepSeek 提供方。** 其通用多模态路径验证了内容转换，但无法让直接官方路由如实公布能力，也无法让它配合官方模型 id 使用。
+- **把整个提供方声明为支持图片。** 这样会让 Flash、Pro 和未知的原样传递 id 接受持久图片，但其确切协议模型无法承诺消费这些图片。能力仍属于确切模型元数据。
+- **在 `tool` 消息内容中发送图片。** 已记录的兼容形式要求工具内容保持字符串。随后发送 user 消息可避免依赖未记录的多模态 tool role 形式，同时保留调用结果顺序。
+- **增加外部 URL 或 Files 上传。** 两者都需要新的规范输入、授权、生命周期、清理和重放决策。瞬态 base64 可以复用现有持久附件约定，不扩展这些问题。
+
+## Verification
+
+包测试固定模型发现与回退能力、配置校验与存活 settings 更新、user 和工具结果协议消息、所有已准入 MIME 类型、取消、附件失败、413 分类、确切图片上限行为和 pi-ai 等价性。无需密钥的组装 ACP 请求会记录原生适配器的工具结果 data URL 与最旧图片占位文本。
+
+## Consequences
+
+已配置的 DeepSeek 视觉路由可以消费持久 user 与工具结果图片，而无需改变会话持久性或响应流。重复历史仍会扩张请求正文，但确定性的最旧优先 offload 会限制主导 payload，并在官方 30 MiB 请求正文上限下保留余量。由于官方图片 token 公式尚不可用，图片 token 定价仍由提供方掌握。

.github/workflows/build-exe-for-python-sdk.yml

@@ -261,17 +261,20 @@ jobs:
           name: deepseek_harness_sdk-${{ needs.plan.outputs.version }}-py3-none-any.whl
           path: dist-python
 
-      - name: Install only the SDK into a clean venv and run zero-config
+      - name: Install local SDK and runtime wheels into a clean venv
         env:
-          VERSION: ${{ needs.plan.outputs.version }}
+          RUNTIME_WHEEL: ${{ steps.runtime.outputs.wheel }}
+          SDK_WHEEL: deepseek_harness_sdk-${{ needs.plan.outputs.version }}-py3-none-any.whl
         run: |
           set -euo pipefail
           python -m venv "$RUNNER_TEMP/dsh-sdk-smoke"
           "$RUNNER_TEMP/dsh-sdk-smoke/bin/python" -m pip install \
-            --find-links dist-python \
-            deepseek-harness-sdk=="$VERSION"
+            "dist-python/$SDK_WHEEL" \
+            "dist-python/$RUNTIME_WHEEL"
           "$RUNNER_TEMP/dsh-sdk-smoke/bin/python" scripts/smoke-python-runtime.py \
             --scenario sdk-default
+          "$RUNNER_TEMP/dsh-sdk-smoke/bin/python" scripts/smoke-python-runtime.py \
+            --scenario sdk-mcp
 
       - name: Check Linux GLIBC requirements
         if: runner.os == 'Linux'
@@ -297,7 +300,8 @@ jobs:
         if: runner.os == 'Linux'
         env:
           RUNNER_ARCH: ${{ runner.arch }}
-          VERSION: ${{ needs.plan.outputs.version }}
+          RUNTIME_WHEEL: ${{ steps.runtime.outputs.wheel }}
+          SDK_WHEEL: deepseek_harness_sdk-${{ needs.plan.outputs.version }}-py3-none-any.whl
         run: |
           set -euo pipefail
           case "$RUNNER_ARCH" in
@@ -305,10 +309,11 @@ jobs:
             ARM64) image=quay.io/pypa/manylinux_2_28_aarch64 ;;
             *) echo "::error::Unsupported Linux runner architecture $RUNNER_ARCH"; exit 1 ;;
           esac
-          docker run --rm -e VERSION -e DSH_TELEMETRY_DISABLED -v "$PWD:/work" -w /work "$image" bash -euxo pipefail -c '
+          docker run --rm -e RUNTIME_WHEEL -e SDK_WHEEL -e DSH_TELEMETRY_DISABLED -v "$PWD:/work" -w /work "$image" bash -euxo pipefail -c '
             /opt/python/cp310-cp310/bin/python -m venv /tmp/dsh-sdk
-            /tmp/dsh-sdk/bin/python -m pip install --find-links /work/dist-python deepseek-harness-sdk=="$VERSION"
+            /tmp/dsh-sdk/bin/python -m pip install "/work/dist-python/$SDK_WHEEL" "/work/dist-python/$RUNTIME_WHEEL"
             /tmp/dsh-sdk/bin/python /work/scripts/smoke-python-runtime.py --scenario sdk-default
+            /tmp/dsh-sdk/bin/python /work/scripts/smoke-python-runtime.py --scenario sdk-mcp
           '
 
       - uses: actions/upload-artifact@v7

.github/workflows/python-release.yml

@@ -68,10 +68,15 @@ jobs:
           print(f"version={release['pep440_version'](repository_version)}")
           PY
 
-      - name: Install and run the published entry path
+      - name: Install local release wheels and run the public entry path
+        env:
+          VERSION: ${{ steps.compatibility-version.outputs.version }}
         run: |
-          python -m pip install --find-links dist "deepseek-harness-sdk==${{ steps.compatibility-version.outputs.version }}"
+          python -m pip install \
+            "dist/deepseek_harness_sdk-$VERSION-py3-none-any.whl" \
+            "dist/deepseek_harness_runtime_bin-$VERSION-py3-none-manylinux_2_28_x86_64.whl"
           python scripts/smoke-python-runtime.py --scenario sdk-default
+          python scripts/smoke-python-runtime.py --scenario sdk-mcp
 
   validate:
     name: Validate release candidate

.gitlab-ci.yml

@@ -45,6 +45,7 @@ sdk-wheel:
     - python -m venv .wheel-smoke
     - .wheel-smoke/bin/python -m pip install --find-links "release/$PLATFORM" --find-links release/sdk deepseek-harness-sdk=="$DSH_WHEEL_VERSION"
     - .wheel-smoke/bin/python scripts/smoke-python-runtime.py --scenario sdk-default
+    - .wheel-smoke/bin/python scripts/smoke-python-runtime.py --scenario sdk-mcp
     - |
       if [ "${PLATFORM#linux-}" != "$PLATFORM" ]; then
         readelf --version-info "$EXE" > glibc-versions.txt
@@ -56,7 +57,7 @@ sdk-wheel:
           linux-arm64) image=quay.io/pypa/manylinux_2_28_aarch64 ;;
           *) echo "Unsupported Linux platform $PLATFORM"; exit 1 ;;
         esac
-        docker run --rm -v "$PWD:/work" -w /work "$image" bash -euxo pipefail -c "/opt/python/cp310-cp310/bin/python -m venv /tmp/dsh-sdk && /tmp/dsh-sdk/bin/python -m pip install --find-links /work/release/$PLATFORM --find-links /work/release/sdk deepseek-harness-sdk==$DSH_WHEEL_VERSION && /tmp/dsh-sdk/bin/python /work/scripts/smoke-python-runtime.py --scenario sdk-default"
+        docker run --rm -v "$PWD:/work" -w /work "$image" bash -euxo pipefail -c "/opt/python/cp310-cp310/bin/python -m venv /tmp/dsh-sdk && /tmp/dsh-sdk/bin/python -m pip install --find-links /work/release/$PLATFORM --find-links /work/release/sdk deepseek-harness-sdk==$DSH_WHEEL_VERSION && /tmp/dsh-sdk/bin/python /work/scripts/smoke-python-runtime.py --scenario sdk-default && /tmp/dsh-sdk/bin/python /work/scripts/smoke-python-runtime.py --scenario sdk-mcp"
       fi
     - |
       if [ "$PLATFORM" = macos-arm64 ]; then

apps/web/tests/command-image-envelope.snapshot.ts

@@ -0,0 +1,97 @@
+// @vitest-environment jsdom
+// The command image-attachment envelope over the BUILT client graph (real
+// bundles via AppWebEntry, keyless FixtureApiClient transport): an enter
+// submission carrying composer images resolves only through a command whose
+// descriptor declares `input.images`. A non-declaring command refuses with
+// one composer error banner and everything retained; a declaring command
+// consumes the images — serialized through the real draft-image chain into
+// the commands/execute payload — and clears the composer on success, including
+// when the image is the whole `/plan` task.
+import { fireEvent, screen, waitFor } from '@testing-library/react'
+import { expect, it } from 'vitest'
+import { installAssembledBootEnv, mountAssembledApp } from './assembled-boot.ts'
+
+installAssembledBootEnv()
+
+/** Open a fresh fixture session and return its composer textarea. */
+async function freshComposer(): Promise<HTMLTextAreaElement> {
+  const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
+  const start = tree.querySelector<HTMLButtonElement>('button[aria-label="New session in fixture"]')
+  if (start === null) throw new Error('fixture Workspace new-session action missing')
+  fireEvent.click(start)
+  return await screen.findByPlaceholderText('Describe what you want to build', {}, { timeout: 10_000 }) as HTMLTextAreaElement
+}
+
+/** Paste one tiny PNG into the composer and wait for its rail thumbnail. */
+async function pasteImage(textarea: HTMLTextAreaElement, name: string): Promise<void> {
+  const image = new File([new Uint8Array([137, 80, 78, 71])], name, { type: 'image/png' })
+  fireEvent.paste(textarea, {
+    clipboardData: {
+      items: [{ kind: 'file', type: 'image/png', getAsFile: () => image }],
+      getData: () => '',
+    },
+  })
+  await waitFor(() => {
+    const rail = document.querySelector('[role="group"][aria-label="Pending images"]')
+    if (rail === null) throw new Error('attachment rail missing')
+    expect([...rail.querySelectorAll('img')].map(img => img.getAttribute('alt'))).toContain(name)
+  }, { timeout: 5_000 })
+}
+
+it('refuses an image-carrying submit to a non-declaring command and keeps draft and images', async () => {
+  mountAssembledApp()
+  const textarea = await freshComposer()
+  await pasteImage(textarea, 'ref.png')
+
+  // /echo is a leadingInput fixture command without `input.images`.
+  fireEvent.change(textarea, { target: { value: '/echo hello' } })
+  fireEvent.keyDown(textarea, { key: 'Enter' })
+
+  // The refusal rides the same transient error banner as other composer
+  // failures; session activity remains on its separate status live region.
+  const notice = await waitFor(() => {
+    const el = [...document.querySelectorAll('[role="alert"]')]
+      .find(candidate => candidate.textContent?.includes('image attachments') ?? false)
+    if (el === undefined) throw new Error('composer refusal banner missing')
+    return el
+  }, { timeout: 5_000 })
+  expect(notice.textContent).toBe('/echo does not accept image attachments; remove them first')
+  expect([...document.querySelectorAll('[role="status"]')]
+    .some(candidate => candidate.textContent?.includes('image attachments') ?? false)).toBe(false)
+  // The whole envelope is retained: draft text and the rail thumbnail.
+  expect(textarea.value).toBe('/echo hello')
+  const rail = document.querySelector('[role="group"][aria-label="Pending images"]')
+  expect([...(rail?.querySelectorAll('img') ?? [])].map(img => img.getAttribute('alt'))).toEqual(['ref.png'])
+})
+
+it('consumes images through a declaring command and clears the composer on success', async () => {
+  mountAssembledApp()
+  const textarea = await freshComposer()
+  await pasteImage(textarea, 'goal-ref.png')
+
+  // /goal declares `input.images` in the fixture catalog; the claim submit
+  // serializes the pasted bytes and the fixture executor admits them.
+  fireEvent.change(textarea, { target: { value: '/goal rebuild the cathedral' } })
+  fireEvent.keyDown(textarea, { key: 'Enter' })
+
+  await waitFor(() => {
+    expect(textarea.value).toBe('')
+    expect(document.querySelector('[role="group"][aria-label="Pending images"]')).toBeNull()
+  }, { timeout: 5_000 })
+})
+
+it('submits a bare /plan with an image as an image-only plan request', async () => {
+  mountAssembledApp()
+  const textarea = await freshComposer()
+  await pasteImage(textarea, 'plan-task.png')
+
+  fireEvent.change(textarea, { target: { value: '/plan' } })
+  fireEvent.keyDown(textarea, { key: 'Enter' })
+
+  await waitFor(() => {
+    expect(textarea.value).toBe('')
+    expect(document.querySelector('[role="group"][aria-label="Pending images"]')).toBeNull()
+  }, { timeout: 5_000 })
+  expect([...document.querySelectorAll('[role="alert"]')]
+    .some(candidate => candidate.textContent?.includes('/plan') ?? false)).toBe(false)
+})

apps/web/tests/home-path-tilde.snapshot.ts

@@ -0,0 +1,45 @@
+// @vitest-environment jsdom
+// Assembled POSIX home-path display: the fixture Host home is `/home/fixture`
+// and a second Workspace lives under it. The sidebar hover card must show
+// `~/Documents/project` while copy still writes the full path.
+import { mkdirSync, writeFileSync } from 'node:fs'
+import { dirname, join } from 'node:path'
+import { act, fireEvent, screen, waitFor, within } from '@testing-library/react'
+import { describe, expect, it } from 'vitest'
+import { installAssembledBootEnv, mountAssembledApp, REFRESHING_GOLDEN } from './assembled-boot.ts'
+
+const EXPECTED = join(process.cwd(), 'apps/web/tests/snapshots/home-path-tilde/workspace-hover.expected.txt')
+
+installAssembledBootEnv()
+
+describe('assembled POSIX home-path display', () => {
+  it('shows the home-descendant Workspace path as ~ and copies the full path', async () => {
+    mountAssembledApp()
+
+    const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
+    const group = (await within(tree).findAllByText('project'))
+      .map(el => el.closest<HTMLElement>('[role="treeitem"]'))
+      .find(el => el?.getAttribute('aria-expanded') !== null)
+    if (group == null) throw new Error('home-descendant Workspace group missing')
+
+    fireEvent.pointerEnter(group.parentElement as HTMLElement)
+    const hoverPath = await waitFor(() => {
+      const found = screen.getByText('~/Documents/project')
+      expect(found).toBeTruthy()
+      return found
+    }, { timeout: 2_000 })
+    expect(screen.queryByText('/home/fixture/Documents/project')).toBeNull()
+    const copy = screen.getByRole('button', { name: 'Copy: /home/fixture/Documents/project' })
+
+    const shape = [
+      `hover=${hoverPath.textContent}`,
+      `copy=${copy.getAttribute('aria-label')}`,
+    ].join('\n') + '\n'
+    if (REFRESHING_GOLDEN) {
+      mkdirSync(dirname(EXPECTED), { recursive: true })
+      writeFileSync(EXPECTED, shape)
+    }
+    await expect(shape).toMatchFileSnapshot(EXPECTED)
+    act(() => { fireEvent.pointerLeave(group.parentElement as HTMLElement) })
+  })
+})

apps/web/tests/message-feedback-layout.e2e.ts

@@ -0,0 +1,336 @@
+// Web e2e scenario: with the feedback note editor open, the assistant IconActions
+// row stays one intact line (no wrapping, nothing pushed out), and the note
+// editor floats above the transcript in a popover that escapes the conversation
+// column's overflow clip and stays inside the viewport.
+//
+// The hazard this pins: a slot-contributed note editor (260px textarea plus
+// Save and Cancel) cannot fit the shared IconActions row at ANY viewport, and an
+// inline expansion made the row wider than the column — full-screen desktop
+// included — so the branch action and the clock were pushed out of view by later
+// flex items. The fix is to not mount the editor in the row at all: it is a
+// popover portaled to document.body and fixed-positioned from the note trigger's
+// rect, so the row keeps its single 28px line of icons and the trigger, and the
+// panel cannot be cropped by the column's overflow because it lives outside it.
+//
+// The sweep records, per viewport, whether the open editor keeps the actions row
+// on one line with zero overflow, whether the panel is outside the column (proof
+// it escapes the clip), whether the panel stays inside the viewport (proof the
+// clamp works), and whether it sits by its trigger. All relations, no absolute
+// pixels: the column width follows the viewport, the sidebar, and the platform's
+// scrollbar, so a golden carrying pixels would document the platform, not the
+// behavior.
+//
+// Zero model calls: a settled transcript is cold-seeded, so nothing streams.
+import { readFile } from 'node:fs/promises'
+import { fileURLToPath } from 'node:url'
+import { join } from 'node:path'
+import type { Browser, Page } from 'playwright'
+import { chromium } from 'playwright'
+import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
+import {
+  compareOrRefreshGolden, launchWebScaffold, seedSession, watchConsole, webSnapshotMode,
+  type WebScaffold,
+} from './scaffold.ts'
+import { newEnglishPage, saveFailureShot } from './support.ts'
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/message-feedback-layout', import.meta.url))
+/**
+ * Committed golden of the popover relations at every stop. Booleans and counts
+ * only, never absolute coordinates.
+ */
+const GEOMETRY_EXPECTED = join(SNAPSHOT_DIR, 'geometry.expected.md')
+const MODE = webSnapshotMode()
+/** Borrowed read-only: this scenario needs any settled assistant message to rate. */
+const SEED = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', import.meta.url))
+const SEED_ID = 'message-feedback-layout-e2e'
+/** Viewport widths from full-screen desktop down to a narrow window. */
+const WIDTHS = [1680, 1280, 1024, 900, 700, 600]
+
+/** One viewport stop: how the row reads with the note editor closed and open, plus the popover's own relations. */
+export interface PopoverMetrics {
+  /** Viewport width the stop was measured at. */
+  width: number
+  /** The row's scrollable overflow with the note editor closed (natural row width). */
+  rowOverflowClosed: number
+  /** The row's scrollable overflow with the note editor open; must equal the closed value. */
+  rowOverflowOpen: number
+  /** Flex lines the row occupies with the note editor open; the editor must not reflow it. */
+  rowLines: number
+  /** Row items whose right edge escapes the column, editor closed. */
+  itemsOutsideColumnClosed: number
+  /** Row items whose right edge escapes the column, editor open; must equal the closed value. */
+  itemsOutsideColumnOpen: number
+  /** True when the portaled panel is NOT inside the column (escapes its overflow clip). */
+  panelOutsideColumn: boolean
+  /** True when the panel lies fully inside the viewport (the clamp holds). */
+  panelWithinViewport: boolean
+  /** Horizontal separation between the panel's left edge and the note trigger's, in px. */
+  panelToTriggerGap: number
+}
+
+/**
+ * Measure the feedback row (and the open popover, when present) at the current
+ * viewport. The same reader serves the closed and open readings so the two
+ * sides differ only by whether the editor is open.
+ * @param page - the page under test.
+ * @param width - the viewport width already applied, recorded with the reading.
+ * @param editorOpen - true to also read the popover's relations; throws if it is absent.
+ * @returns the stop's relations.
+ */
+function measurePopover(page: Page, width: number, editorOpen: boolean): Promise<PopoverMetrics> {
+  return page.evaluate(({ viewportWidth, open }) => {
+    const rated = document.querySelector<HTMLElement>('button[aria-label="Remove rating"]')
+    if (rated === null) throw new Error('no rated feedback control in the DOM')
+    const row = rated.parentElement?.closest<HTMLElement>('div[class*="actions"]') ?? null
+    if (row === null) throw new Error('the IconActions row is not an ancestor of the feedback control')
+    const trigger = row.querySelector<HTMLElement>('button[aria-haspopup="dialog"]')
+    if (trigger === null) throw new Error('the note trigger is not in the row')
+
+    /**
+     * The real flex items of the row. A slot contributor (the feedback strip)
+     * arrives as a `display: contents` wrapper (the `assistant-actions` slot
+     * renders inside a transparent `data-slot` div), which reports an all-zero
+     * rect; a zero box would be miscounted as a phantom flex line. The actual
+     * items are the boxes inside it.
+     * @param element - the row whose items to read.
+     * @returns the real flex-item boxes, in flex/DOM order.
+     */
+    const flexItemBoxes = (element: HTMLElement): DOMRect[] => {
+      const boxes: DOMRect[] = []
+      for (const child of Array.from(element.children)) {
+        const el = child as HTMLElement
+        const rect = el.getBoundingClientRect()
+        if (el.style.display === 'contents') {
+          boxes.push(...flexItemBoxes(el))
+        } else if (rect.height > 0 && rect.width > 0) {
+          boxes.push(rect)
+        }
+      }
+      return boxes
+    }
+    /**
+     * Group items into flex lines by overlapping vertical extent.
+     * @param boxes - the row items' boxes, in DOM order.
+     * @returns the number of distinct lines.
+     */
+    const countFlexLines = (boxes: DOMRect[]): number => {
+      const centres: number[] = []
+      for (const box of boxes) {
+        const centre = box.top + box.height / 2
+        if (!centres.some(known => Math.abs(known - centre) <= box.height / 2)) centres.push(centre)
+      }
+      return centres.length
+    }
+
+    const column = row.closest<HTMLElement>('[data-conversation-scroll]')
+    const columnRight = (column?.getBoundingClientRect().left ?? 0) + (column?.clientWidth ?? 0)
+    const itemRects = flexItemBoxes(row)
+    // A half-pixel tolerance: subpixel layout puts a contained edge a fraction
+    // over the boundary on some device scale factors.
+    const itemsOutsideColumn = itemRects.filter(box => box.right > columnRight + 0.5).length
+    // The editor is a portal, so the row measures identically whether the
+    // editor is open or not; the closed/open fields differ by call so the sweep
+    // can assert a zero delta on them.
+    const overflow = row.scrollWidth - row.clientWidth
+
+    let builder: {
+      panelOutsideColumn: boolean
+      panelWithinViewport: boolean
+      panelToTriggerGap: number
+    }
+    if (!open) {
+      builder = { panelOutsideColumn: true, panelWithinViewport: true, panelToTriggerGap: 0 }
+    } else {
+      const panel = document.body.querySelector<HTMLElement>('[role="dialog"]')
+      if (panel === null) throw new Error('the note popover is not open')
+      const panelBox = panel.getBoundingClientRect()
+      const triggerBox = trigger.getBoundingClientRect()
+      const vw = window.innerWidth
+      const vh = window.innerHeight
+      builder = {
+        // The panel portals out of the column, so the clip cannot reach it.
+        panelOutsideColumn: column === null ? true : !column.contains(panel),
+        panelWithinViewport:
+          panelBox.left >= -0.5
+          && panelBox.right <= vw + 0.5
+          && panelBox.top >= -0.5
+          && panelBox.bottom <= vh + 0.5,
+        // The panel is fixed from the trigger's left, so a zero gap says it is
+        // anchored; a clamp can only widen it.
+        panelToTriggerGap: Math.abs(panelBox.left - triggerBox.left),
+      }
+    }
+
+    return {
+      width: viewportWidth,
+      rowOverflowClosed: overflow,
+      rowOverflowOpen: overflow,
+      rowLines: countFlexLines(itemRects),
+      itemsOutsideColumnClosed: itemsOutsideColumn,
+      itemsOutsideColumnOpen: itemsOutsideColumn,
+      ...builder,
+    }
+  }, { viewportWidth: width, open: editorOpen })
+}
+
+/**
+ * Render the golden body: one line per stop, relations and counts only. The
+ * row-overflow and outside-column readings are deltas (open minus closed) so
+ * the golden records that opening the editor leaves the row untouched, not an
+ * absolute count that many unrelated controls could move.
+ * @param stops - the measured stops, in sweep order.
+ * @returns the golden body, without a trailing newline.
+ */
+function renderGeometry(stops: PopoverMetrics[]): string {
+  return [
+    '# Assistant actions row with the feedback note popover open',
+    '',
+    '| viewport | row overflow delta | row lines | items-outside delta '
+      + '| panel outside the column | panel within the viewport | panel-to-trigger gap |',
+    '| --- | --- | --- | --- | --- | --- | --- |',
+    ...stops.map(stop => `| ${String(stop.width)}px | ${String(stop.rowOverflowOpen - stop.rowOverflowClosed)}px `
+      + `| ${String(stop.rowLines)} | ${String(stop.itemsOutsideColumnOpen - stop.itemsOutsideColumnClosed)} `
+      + `| ${String(stop.panelOutsideColumn)} | ${String(stop.panelWithinViewport)} `
+      + `| ${String(stop.panelToTriggerGap)}px |`),
+  ].join('\n')
+}
+
+describe('web e2e: the feedback note editor floats above the column', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold({})
+    await seedSession(scaffold, await readFile(SEED, 'utf8'), SEED_ID)
+    browser = await chromium.launch()
+    page = await newEnglishPage(browser, 900)
+    tripwire = watchConsole(page)
+    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+  }, 180_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  /**
+   * Open the seeded transcript. The first treeitem is the collapsible group
+   * row; the session itself is the row beneath it.
+   * @returns nothing.
+   */
+  async function openSeededSession(): Promise<void> {
+    const groupRow = page.locator('[role="treeitem"]').first()
+    await groupRow.waitFor({ timeout: 15_000 })
+    if (await groupRow.getAttribute('aria-expanded') !== 'true') await groupRow.click()
+    const sessionRow = page.locator('[role="treeitem"]').nth(1)
+    await sessionRow.waitFor({ timeout: 15_000 })
+    await sessionRow.click()
+  }
+
+  /**
+   * Resize to a viewport and read the row once its width stops moving. The
+   * frame eases its column tracks, so reading straight after a resize can
+   * report the previous viewport's relation.
+   * @param width - viewport width to settle at.
+   * @param editorOpen - whether the note editor is currently open; reads the popover relations when so.
+   * @returns the row's (and popover's) readings at that width.
+   */
+  const settleAt = async (width: number, editorOpen: boolean): Promise<PopoverMetrics> => {
+    await page.setViewportSize({ width, height: 900 })
+    let previous = -1
+    await expect.poll(async () => {
+      const current = await page.evaluate(() =>
+        document.querySelector('[data-conversation-scroll]')?.clientWidth ?? -1)
+      const settled = current === previous
+      previous = current
+      return settled
+    }, { timeout: 10_000 }).toBe(true)
+    // The popover is JS-positioned from the trigger rect and re-places on
+    // resize/scroll, so once the column width stops moving we nudge it to the
+    // final layout; otherwise the panel can sit at a transient position from
+    // mid-resize and the anchor reading would be off.
+    await page.evaluate(() => window.dispatchEvent(new Event('resize')))
+    return measurePopover(page, width, editorOpen)
+  }
+
+  /**
+   * Rate a message, then for every stop read the row once with the note editor
+   * closed and once with it open, handing the SAME measured readings to both
+   * assertions so the golden and the assertions describe one measurement
+   * rather than two runs that could disagree.
+   * @returns the stops in {@link WIDTHS} order.
+   */
+  let swept: Promise<PopoverMetrics[]> | undefined
+  const sweep = (): Promise<PopoverMetrics[]> => {
+    swept ??= (async () => {
+      await openSeededSession()
+      await page.getByText('DONE', { exact: true }).waitFor({ timeout: 30_000 })
+      // The controller defers its list read to the first hover or focus, so the
+      // strip has to be touched before it can be rated.
+      const like = page.getByRole('button', { name: 'Good response' }).first()
+      await like.waitFor({ timeout: 30_000 })
+      await like.scrollIntoViewIfNeeded()
+      await like.hover()
+      await like.click()
+      await page.getByRole('button', { name: 'Remove rating' }).first()
+        .waitFor({ timeout: 15_000 })
+      const noteTrigger = page.getByRole('button', { name: 'Add a note' }).first()
+      const stops: PopoverMetrics[] = []
+      for (const width of WIDTHS) {
+        // Reset to the closed baseline at each stop before opening.
+        if (await noteTrigger.getAttribute('aria-expanded') === 'true') await noteTrigger.click()
+        const closed = await settleAt(width, false)
+        await page.getByRole('button', { name: 'Add a note' }).first().click()
+        await page.getByRole('dialog').waitFor({ timeout: 10_000 })
+        const open = await settleAt(width, true)
+        stops.push({
+          width,
+          rowOverflowClosed: closed.rowOverflowClosed,
+          rowOverflowOpen: open.rowOverflowOpen,
+          rowLines: open.rowLines,
+          itemsOutsideColumnClosed: closed.itemsOutsideColumnClosed,
+          itemsOutsideColumnOpen: open.itemsOutsideColumnOpen,
+          panelOutsideColumn: open.panelOutsideColumn,
+          panelWithinViewport: open.panelWithinViewport,
+          panelToTriggerGap: open.panelToTriggerGap,
+        })
+      }
+      return stops
+    })()
+    return swept
+  }
+
+  it('keeps the actions row untouched by the note popover, which stays in the viewport', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-message-feedback-layout'))
+    const stops = await sweep()
+    for (const stop of stops) {
+      // The popover lives outside the row, so opening it must not change the
+      // row at all. This is the vacuity guard of the whole redesign: an inline
+      // editor would widen or reflow the row, pushing the delta off zero.
+      expect(stop.rowOverflowOpen - stop.rowOverflowClosed, `viewport ${String(stop.width)}`).toBe(0)
+      expect(stop.itemsOutsideColumnOpen - stop.itemsOutsideColumnClosed, `viewport ${String(stop.width)}`).toBe(0)
+      // The row is one 28px line; the editor never forces a reflow.
+      expect(stop.rowLines, `viewport ${String(stop.width)}`).toBe(1)
+      // The panel escapes the column's overflow clip by living outside it.
+      expect(stop.panelOutsideColumn, `viewport ${String(stop.width)}`).toBe(true)
+      // The placement clamps the panel inside the viewport at every width.
+      expect(stop.panelWithinViewport, `viewport ${String(stop.width)}`).toBe(true)
+      // The panel stays anchored to its trigger rather than drifting off.
+      expect(stop.panelToTriggerGap, `viewport ${String(stop.width)}`).toBeLessThanOrEqual(4)
+    }
+    expect(tripwire.pageErrors).toEqual([])
+  }, 180_000)
+
+  it('matches the committed geometry golden', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-message-feedback-layout-golden'))
+    await compareOrRefreshGolden(GEOMETRY_EXPECTED, renderGeometry(await sweep()), MODE)
+  }, 180_000)
+
+  it('kept the console clean', () => {
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+  })
+})

apps/web/tests/navigation-panes.e2e.ts

@@ -12,7 +12,7 @@ import { join } from 'node:path'
 import type { Browser, Page, Response } from 'playwright'
 import { chromium } from 'playwright'
 import { strFromU8, unzipSync } from 'fflate'
-import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, onTestFailed } from 'vitest'
+import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, onTestFailed, vi } from 'vitest'
 import { parseSessionLog } from '@deepseek-ai/dsh-llm-replay'
 import type { SessionEvent } from '@deepseek-ai/dsh-session'
 import {
@@ -415,8 +415,17 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
     // Read summaries are host-open file links; they also must not open details.
     const fileLink = page.locator('[data-variant="read"] button').first()
     await fileLink.waitFor({ timeout: 10_000 })
-    await fileLink.click()
-    await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true')
+    const openPath = vi.spyOn(scaffold.ctx.apiProxy.host, 'openPath')
+      .mockImplementation(async (request, _signal) => ({
+        rpcId: request.rpcId,
+        result: { ok: true, value: { opened: true as const } },
+      }))
+    try {
+      await fileLink.click()
+      await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true')
+    } finally {
+      openPath.mockRestore()
+    }
   }, 60_000)
 
   it.skipIf(MODE === 'record')('renders the bash row as a terminal card in the real browser', async () => {

apps/web/tests/onboarding-deepseek-config.e2e.ts

@@ -224,7 +224,7 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
     expect(document).toContain('name: Private Preview')
     expect(document).toContain('contextWindow: 131072')
     expect(document).toContain('maxTokens: 64000')
-    expect(document).not.toContain('id: deepseek-v4-flash')
+    expect(document).not.toMatch(/^\s*- id: deepseek-v4-flash$/m)
 
     await page.keyboard.press('Escape')
     // A connected Workspace is what puts a live composer — and its model

apps/web/tests/seeded-history.e2e.ts

@@ -14,7 +14,7 @@ import { readFile, writeFile, mkdir } from 'node:fs/promises'
 import { fileURLToPath } from 'node:url'
 import type { Browser, Page } from 'playwright'
 import { chromium } from 'playwright'
-import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
+import { afterAll, beforeAll, describe, expect, it, onTestFailed, vi } from 'vitest'
 import { createUserMessage } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock, Message } from '@deepseek-ai/dsh-llm'
 import { deriveEventMessage, SessionId } from '@deepseek-ai/dsh-session'
@@ -33,6 +33,7 @@ const UI_EXPECTED = fileURLToPath(new URL('./snapshots/seeded-history/ui.expecte
 // Command-row goldens over the same conversation after direct host commands.
 const COMMAND_ROW_EXPECTED = fileURLToPath(new URL('./snapshots/seeded-history/command-row.expected.md', import.meta.url))
 const FEEDBACK_ROW_EXPECTED = fileURLToPath(new URL('./snapshots/seeded-history/feedback-row.expected.md', import.meta.url))
+const FILE_OPEN_FAILURE_EXPECTED = fileURLToPath(new URL('./snapshots/seeded-history/file-open-failure.expected.md', import.meta.url))
 const MODE = webSnapshotMode()
 const SEED_ID = 'seeded-history-web-e2e'
 
@@ -396,12 +397,57 @@ describe('web e2e: seeded history renders through cold resume', () => {
     await fileLink.waitFor({ timeout: 10_000 })
     const frame = page.locator('[style*="grid-template-columns"]').first()
     expect(await frame.getAttribute('data-details-collapsed')).toBe('true')
-    await fileLink.click()
-    await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true')
+    const openPath = vi.spyOn(scaffold.ctx.apiProxy.host, 'openPath')
+      .mockImplementation(async (request, _signal) => ({
+        rpcId: request.rpcId,
+        result: { ok: true, value: { opened: true as const } },
+      }))
+    try {
+      await fileLink.click()
+      await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true')
+    } finally {
+      openPath.mockRestore()
+    }
     // Path label survives from the recorded args (a.txt).
     await expect.poll(() => page.getByText('a.txt', { exact: false }).count(), { timeout: 5_000 }).toBeGreaterThan(0)
   })
 
+  it.skipIf(MODE === 'record')('a Host open refusal keeps the reason and retries the same path', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-file-open-failure'))
+    const fileLink = page.locator('[data-variant="read"] button').first()
+    await fileLink.waitFor({ timeout: 10_000 })
+    const openPath = vi.spyOn(scaffold.ctx.apiProxy.host, 'openPath')
+      .mockImplementation(async (request, _signal) => ({
+        rpcId: request.rpcId,
+        result: {
+          ok: false as const,
+          error: { code: 'internal', message: 'xdg-open is not available', details: {} },
+        },
+      }))
+    try {
+      await fileLink.click()
+      const dialog = page.getByRole('dialog', { name: 'Couldn’t open file' })
+      await dialog.waitFor({ timeout: 5_000 })
+      const snapshot = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd)
+      await compareOrRefreshGolden(FILE_OPEN_FAILURE_EXPECTED, snapshot, MODE)
+      await expect.poll(() => dialog.innerText(), { timeout: 5_000 })
+        .toContain('path open failed: xdg-open is not available')
+      await page.getByRole('button', { name: 'Retry' }).click()
+      await expect.poll(() => openPath.mock.calls.length, { timeout: 5_000 }).toBe(2)
+      expect(openPath.mock.calls[0]![0].payload).toEqual(openPath.mock.calls[1]![0].payload)
+      await page.getByRole('button', { name: 'Cancel' }).click()
+      await expect.poll(() => page.getByRole('dialog', { name: 'Couldn’t open file' }).count(), {
+        timeout: 5_000,
+      }).toBe(0)
+    } finally {
+      // Shared page: a leftover mask blocks later cases even when this one fails.
+      if (await page.getByRole('dialog', { name: 'Couldn’t open file' }).count() > 0) {
+        await page.keyboard.press('Escape')
+      }
+      openPath.mockRestore()
+    }
+  })
+
   it.skipIf(MODE === 'record')('expands the cold-resumed compact summary', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-compaction'))
     const marker = page.getByRole('button', { name: /compact Compacted \d+ history items/ })
@@ -505,6 +551,6 @@ describe('web e2e: seeded history renders through cold resume', () => {
     // stream would have failed the turn loudly. Cleanliness pins the wire.
     expect(tripwire.pageErrors).toEqual([])
     expect(tripwire.warnings).toEqual([])
-    await assertFixtureInventory(SNAPSHOT_DIR, ['command-row.expected.md', 'feedback-row.expected.md', 'seed.jsonl', 'ui.expected.md'])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['command-row.expected.md', 'feedback-row.expected.md', 'file-open-failure.expected.md', 'seed.jsonl', 'ui.expected.md'])
   })
 })

apps/web/tests/snapshots/home-path-tilde/workspace-hover.expected.txt

@@ -0,0 +1,2 @@
+hover=~/Documents/project
+copy=Copy: /home/fixture/Documents/project

apps/web/tests/snapshots/message-feedback-layout/geometry.expected.md

@@ -0,0 +1,10 @@
+# Assistant actions row with the feedback note popover open
+
+| viewport | row overflow delta | row lines | items-outside delta | panel outside the column | panel within the viewport | panel-to-trigger gap |
+| --- | --- | --- | --- | --- | --- | --- |
+| 1680px | 0px | 1 | 0 | true | true | 0px |
+| 1280px | 0px | 1 | 0 | true | true | 0px |
+| 1024px | 0px | 1 | 0 | true | true | 0px |
+| 900px | 0px | 1 | 0 | true | true | 0px |
+| 700px | 0px | 1 | 0 | true | true | 0px |
+| 600px | 0px | 1 | 0 | true | true | 0px |

apps/web/tests/snapshots/seeded-history/file-open-failure.expected.md

@@ -0,0 +1,7 @@
+- dialog "Couldn’t open file":
+  - heading "Couldn’t open file" [level=2]
+  - button "Close":
+    - img
+  - paragraph: "path open failed: xdg-open is not available"
+  - button "Cancel"
+  - button "Retry"

apps/web/tsconfig.json

@@ -60,6 +60,7 @@
     "tests/web-search-round.e2e.ts",
     "tests/message-actions.e2e.ts",
     "tests/message-feedback.e2e.ts",
+    "tests/message-feedback-layout.e2e.ts",
     "tests/markdown-images.e2e.ts",
     "tests/math-rendering.e2e.ts",
     "tests/markdown-cjk-strong.e2e.ts",

docs/config-catalog.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 docs/config-catalog.md
-config-catalog.md: c03f1088745a5746a59b2fbddf60d7b270951371
-config-catalog.zh.md: 4c1f62f7c899dd6bf7c55c33e802859be9e79e5e
+config-catalog.md: 659fe4a89bd36a6b1e7446be07e3e72022fa5d0f
+config-catalog.zh.md: 8b180c96d7d22f13253bc28c580343ccec051a1c

docs/config-catalog.md

@@ -870,6 +870,8 @@ export interface Config {
   models?: DeepSeekCatalogModel[]
   /** Maximum provider idle time while one stream read is outstanding (default five minutes). */
   streamIdleTimeoutMs?: number
+  /** Maximum accumulated base64 image payload per request (default 20 MiB). */
+  maxRequestImageBytes?: number
   /** Provider-owned model-request retry policy; omission uses normal mode with five retries. */
   retryPolicy?: RetryPolicyConfig
 }
@@ -886,12 +888,14 @@ export interface DeepSeekCatalogModel {
   contextWindow?: number
   /** Per-request output cap for this model; omission falls back to the profile's {@link DeepSeekConnectionOptions.maxTokens}. */
   maxTokens?: number
+  /** Accepted request modalities; omission is text-only. */
+  inputModalities?: ModelModality[]
 }
 ```
 
-Depends on: [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts)
+Depends on: [`ModelModality`](../packages/llm/llm/src/index.ts) · [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts)
 
-Source: [`packages/llm/llm-deepseek/src/index.ts:62`](../packages/llm/llm-deepseek/src/index.ts)
+Source: [`packages/llm/llm-deepseek/src/index.ts:66`](../packages/llm/llm-deepseek/src/index.ts)
 
 <a id="deepseek-aidsh-llm-pi-ai"></a>
 
@@ -940,10 +944,11 @@ export interface PiAiProviderProfile {
    */
   modelOverrides?: Record<string, PiAiModelOverride>
   /**
-   * Reasoning-dispatch switches for every `openai-completions` model on this
-   * route; each model's own `compat` overrides per field. What neither sets
-   * keeps the installed catalog entry's value, then pi-ai's baseURL-derived
-   * detection.
+   * pi-ai wire-compatibility switches defaulting every model on this route
+   * whose protocol declares them; each model's own `compat` overrides per
+   * field. What neither sets keeps the installed catalog entry's value, then
+   * pi-ai's own detection. A switch no model on the route could read is
+   * refused rather than left looking applied.
    */
   compat?: PiAiCompatProfile
   /**
@@ -1031,7 +1036,7 @@ export interface PiAiModelProfile {
    * declares the offered levels and their wire spellings.
    */
   reasoningEfforts?: false | PiAiReasoningEfforts
-  /** Reasoning-dispatch switches for this model, winning over the route's. */
+  /** pi-ai wire-compatibility switches for this model, winning over the route's per field; one its protocol does not declare is refused. */
   compat?: PiAiCompatProfile
 }
 
@@ -1045,19 +1050,80 @@ export interface PiAiModelProfile {
 export type PiAiModelOverride = Omit<PiAiModelProfile, 'id'>
 
 /**
- * Reasoning-dispatch compatibility switches, set on the route (its models'
- * default) or per model (winning over the route). Only the switches pi-ai's
- * reasoning dispatch reads are offered; the rest of pi-ai's compat surface
- * keeps its baseURL-derived auto-detection. pi-ai types both fields only on
- * `OpenAICompletionsCompat` — the other wire protocols define their reasoning
- * fields in the protocol itself — so resolution rejects a model-level switch
- * anywhere else, while a route-level default skips past models it cannot fit.
+ * pi-ai wire-compatibility switches, set on the route (its models' default) or
+ * per model (winning over the route, field by field).
+ *
+ * pi-ai decides each of these from the provider id and baseURL when no layer
+ * sets it, and a private gateway's URL says nothing: for an endpoint it does
+ * not recognize the detection answers as though it were OpenAI itself, which
+ * is wrong for most OpenAI-compatible gateways. So every field here is one a
+ * deployment must be able to state because nothing can infer it, while the
+ * fields pi-ai's catalog sets for a named vendor stay withheld.
+ *
+ * A field belongs to the protocols whose upstream compat type declares it: a
+ * model-level switch its protocol does not take fails resolution, and a
+ * route-level one skips past models it cannot fit. "The three Responses
+ * protocols" below means `openai-responses`, `azure-openai-responses`, and
+ * `openai-codex-responses`, which pi-ai gives one shared compat type, so a
+ * switch settable on one is settable on all three.
  */
 export interface PiAiCompatProfile {
-  /** Reasoning parameter format the endpoint expects; absent keeps the catalog entry's, then pi-ai's baseURL-derived guess. */
-  thinkingFormat?: PiAiThinkingFormat
-  /** Whether the endpoint accepts `reasoning_effort`; absent keeps the catalog entry's, then pi-ai's baseURL-derived guess. */
+  /** Whether the endpoint accepts `store`; `openai-completions`. */
+  supportsStore?: boolean
+  /**
+   * Whether the endpoint accepts the `developer` role for the system prompt,
+   * which pi-ai sends only to a reasoning model; `false` keeps `system`.
+   * `openai-completions` and the three Responses protocols.
+   */
+  supportsDeveloperRole?: boolean
+  /** Whether the endpoint accepts `reasoning_effort`; `openai-completions`. */
   supportsReasoningEffort?: boolean
+  /** Whether the endpoint accepts `stream_options: {include_usage: true}`; `openai-completions`. */
+  supportsUsageInStreaming?: boolean
+  /** Which output-cap field the endpoint reads; `openai-completions`. */
+  maxTokensField?: NonNullable<OpenAICompletionsCompat['maxTokensField']>
+  /** Whether tool results must carry `name`; `openai-completions`. */
+  requiresToolResultName?: boolean
+  /** Whether a user message after tool results needs an assistant message between; `openai-completions`. */
+  requiresAssistantAfterToolResult?: boolean
+  /** Whether thinking blocks must travel as text in `<thinking>` delimiters; `openai-completions`. */
+  requiresThinkingAsText?: boolean
+  /** Whether replayed assistant messages need an empty `reasoning_content` while reasoning is on; `openai-completions`. */
+  requiresReasoningContentOnAssistantMessages?: boolean
+  /** Reasoning parameter format the endpoint expects; `openai-completions`. */
+  thinkingFormat?: PiAiThinkingFormat
+  /**
+   * Kwargs sent as `chat_template_kwargs`, which pi-ai reads only under the
+   * two `chat-template` thinking formats; `openai-completions`. Nothing checks
+   * that pairing: the format in force may come from the installed catalog
+   * entry or from pi-ai's own baseURL detection, neither of which resolution
+   * can read, so kwargs set beside another format are sent nowhere.
+   */
+  chatTemplateKwargs?: NonNullable<OpenAICompletionsCompat['chatTemplateKwargs']>
+  /**
+   * Whether the endpoint accepts `strict` in tool definitions;
+   * `openai-completions`, the three Responses protocols, `bedrock-converse-stream`.
+   */
+  supportsStrictMode?: boolean
+  /** Prompt-cache marker convention; `openai-completions`. */
+  cacheControlFormat?: NonNullable<OpenAICompletionsCompat['cacheControlFormat']>
+  /**
+   * Whether the endpoint accepts long prompt-cache retention;
+   * `openai-completions`, the three Responses protocols, `anthropic-messages`.
+   */
+  supportsLongCacheRetention?: boolean
+  /** Whether the endpoint accepts per-tool `eager_input_streaming`; `anthropic-messages`. */
+  supportsEagerToolInputStreaming?: boolean
+  /** Whether the endpoint accepts `cache_control` on tool definitions; `anthropic-messages`. */
+  supportsCacheControlOnTools?: boolean
+  /** Whether the endpoint accepts the `temperature` request field; `anthropic-messages`. */
+  supportsTemperature?: boolean
+  /** Whether to force adaptive thinking regardless of model id; `anthropic-messages`. */
+  forceAdaptiveThinking?: boolean
+  /** Whether to replay an empty thinking signature instead of converting thinking to text; `anthropic-messages`. */
+  allowEmptySignature?: boolean
+  /** Whether the endpoint accepts Anthropic strict tool schemas; `anthropic-messages`. */
+  supportsStrictTools?: boolean
 }
 
 /** One request modality a pi-ai model may accept. */
@@ -1074,21 +1140,12 @@ export type PiAiModality = Model<Api>['input'][number]
 export type PiAiReasoningEfforts = Partial<Record<ModelThinkingLevel, string | null>>
 
 /** One reasoning-dispatch wire format a profile may name. */
-export type PiAiThinkingFormat = Exclude<PiThinkingFormat, WithheldThinkingFormat>
-
-/** The `compat.thinkingFormat` spellings pi-ai accepts on an `openai-completions` model. */
-type PiThinkingFormat = NonNullable<OpenAICompletionsCompat['thinkingFormat']>
-
-/**
- * pi-ai thinking formats a profile cannot name: both drive the request through
- * `chatTemplateKwargs`, which this configuration does not expose.
- */
-type WithheldThinkingFormat = 'chat-template' | 'qwen-chat-template'
+export type PiAiThinkingFormat = NonNullable<OpenAICompletionsCompat['thinkingFormat']>
 ```
 
 Depends on: `Api` (`@earendil-works/pi-ai`) · `CacheRetention` (`@earendil-works/pi-ai`) · `Model` (`@earendil-works/pi-ai`) · `ModelThinkingLevel` (`@earendil-works/pi-ai`) · `OpenAICompletionsCompat` (`@earendil-works/pi-ai`) · [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts) · `ThinkingBudgets` (`@earendil-works/pi-ai`) · `Transport` (`@earendil-works/pi-ai`)
 
-Source: [`packages/llm/llm-pi-ai/src/config.ts:192`](../packages/llm/llm-pi-ai/src/config.ts)
+Source: [`packages/llm/llm-pi-ai/src/config.ts:201`](../packages/llm/llm-pi-ai/src/config.ts)
 
 <a id="deepseek-aidsh-llm-replay"></a>
 
@@ -1379,7 +1436,7 @@ export interface PlanModeConfig {
 }
 ```
 
-Source: [`packages/plan/plan-mode/src/index.ts:70`](../packages/plan/plan-mode/src/index.ts)
+Source: [`packages/plan/plan-mode/src/index.ts:71`](../packages/plan/plan-mode/src/index.ts)
 
 <a id="deepseek-aidsh-pwsh-local"></a>
 
@@ -2114,7 +2171,7 @@ export interface Config {
 export type ClaudeCodePermissionMode = typeof CLAUDE_CODE_PERMISSION_MODES[number]
 ```
 
-Source: [`packages/subagent/subagent-claude-code/src/index.ts:37`](../packages/subagent/subagent-claude-code/src/index.ts)
+Source: [`packages/subagent/subagent-claude-code/src/index.ts:38`](../packages/subagent/subagent-claude-code/src/index.ts)
 
 <a id="deepseek-aidsh-subagent-codex"></a>
 
@@ -2145,7 +2202,7 @@ export type CodexPermissionMode =
   | 'dangerously-bypass-approvals-and-sandbox'
 ```
 
-Source: [`packages/subagent/subagent-codex/src/index.ts:35`](../packages/subagent/subagent-codex/src/index.ts)
+Source: [`packages/subagent/subagent-codex/src/index.ts:36`](../packages/subagent/subagent-codex/src/index.ts)
 
 <a id="deepseek-aidsh-subagent-dsh-sdk"></a>
 

docs/config-catalog.zh.md

@@ -872,6 +872,8 @@ export interface Config {
   models?: DeepSeekCatalogModel[]
   /** Maximum provider idle time while one stream read is outstanding (default five minutes). */
   streamIdleTimeoutMs?: number
+  /** Maximum accumulated base64 image payload per request (default 20 MiB). */
+  maxRequestImageBytes?: number
   /** Provider-owned model-request retry policy; omission uses normal mode with five retries. */
   retryPolicy?: RetryPolicyConfig
 }
@@ -888,12 +890,14 @@ export interface DeepSeekCatalogModel {
   contextWindow?: number
   /** Per-request output cap for this model; omission falls back to the profile's {@link DeepSeekConnectionOptions.maxTokens}. */
   maxTokens?: number
+  /** Accepted request modalities; omission is text-only. */
+  inputModalities?: ModelModality[]
 }
 ```
 
-依赖：[`RetryPolicyConfig`](../packages/llm/llm/src/index.ts)
+依赖：[`ModelModality`](../packages/llm/llm/src/index.ts) · [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts)
 
-来源：[`packages/llm/llm-deepseek/src/index.ts:62`](../packages/llm/llm-deepseek/src/index.ts)
+来源：[`packages/llm/llm-deepseek/src/index.ts:66`](../packages/llm/llm-deepseek/src/index.ts)
 
 <a id="deepseek-aidsh-llm-pi-ai"></a>
 
@@ -942,10 +946,11 @@ export interface PiAiProviderProfile {
    */
   modelOverrides?: Record<string, PiAiModelOverride>
   /**
-   * Reasoning-dispatch switches for every `openai-completions` model on this
-   * route; each model's own `compat` overrides per field. What neither sets
-   * keeps the installed catalog entry's value, then pi-ai's baseURL-derived
-   * detection.
+   * pi-ai wire-compatibility switches defaulting every model on this route
+   * whose protocol declares them; each model's own `compat` overrides per
+   * field. What neither sets keeps the installed catalog entry's value, then
+   * pi-ai's own detection. A switch no model on the route could read is
+   * refused rather than left looking applied.
    */
   compat?: PiAiCompatProfile
   /**
@@ -1033,7 +1038,7 @@ export interface PiAiModelProfile {
    * declares the offered levels and their wire spellings.
    */
   reasoningEfforts?: false | PiAiReasoningEfforts
-  /** Reasoning-dispatch switches for this model, winning over the route's. */
+  /** pi-ai wire-compatibility switches for this model, winning over the route's per field; one its protocol does not declare is refused. */
   compat?: PiAiCompatProfile
 }
 
@@ -1047,19 +1052,80 @@ export interface PiAiModelProfile {
 export type PiAiModelOverride = Omit<PiAiModelProfile, 'id'>
 
 /**
- * Reasoning-dispatch compatibility switches, set on the route (its models'
- * default) or per model (winning over the route). Only the switches pi-ai's
- * reasoning dispatch reads are offered; the rest of pi-ai's compat surface
- * keeps its baseURL-derived auto-detection. pi-ai types both fields only on
- * `OpenAICompletionsCompat` — the other wire protocols define their reasoning
- * fields in the protocol itself — so resolution rejects a model-level switch
- * anywhere else, while a route-level default skips past models it cannot fit.
+ * pi-ai wire-compatibility switches, set on the route (its models' default) or
+ * per model (winning over the route, field by field).
+ *
+ * pi-ai decides each of these from the provider id and baseURL when no layer
+ * sets it, and a private gateway's URL says nothing: for an endpoint it does
+ * not recognize the detection answers as though it were OpenAI itself, which
+ * is wrong for most OpenAI-compatible gateways. So every field here is one a
+ * deployment must be able to state because nothing can infer it, while the
+ * fields pi-ai's catalog sets for a named vendor stay withheld.
+ *
+ * A field belongs to the protocols whose upstream compat type declares it: a
+ * model-level switch its protocol does not take fails resolution, and a
+ * route-level one skips past models it cannot fit. "The three Responses
+ * protocols" below means `openai-responses`, `azure-openai-responses`, and
+ * `openai-codex-responses`, which pi-ai gives one shared compat type, so a
+ * switch settable on one is settable on all three.
  */
 export interface PiAiCompatProfile {
-  /** Reasoning parameter format the endpoint expects; absent keeps the catalog entry's, then pi-ai's baseURL-derived guess. */
-  thinkingFormat?: PiAiThinkingFormat
-  /** Whether the endpoint accepts `reasoning_effort`; absent keeps the catalog entry's, then pi-ai's baseURL-derived guess. */
+  /** Whether the endpoint accepts `store`; `openai-completions`. */
+  supportsStore?: boolean
+  /**
+   * Whether the endpoint accepts the `developer` role for the system prompt,
+   * which pi-ai sends only to a reasoning model; `false` keeps `system`.
+   * `openai-completions` and the three Responses protocols.
+   */
+  supportsDeveloperRole?: boolean
+  /** Whether the endpoint accepts `reasoning_effort`; `openai-completions`. */
   supportsReasoningEffort?: boolean
+  /** Whether the endpoint accepts `stream_options: {include_usage: true}`; `openai-completions`. */
+  supportsUsageInStreaming?: boolean
+  /** Which output-cap field the endpoint reads; `openai-completions`. */
+  maxTokensField?: NonNullable<OpenAICompletionsCompat['maxTokensField']>
+  /** Whether tool results must carry `name`; `openai-completions`. */
+  requiresToolResultName?: boolean
+  /** Whether a user message after tool results needs an assistant message between; `openai-completions`. */
+  requiresAssistantAfterToolResult?: boolean
+  /** Whether thinking blocks must travel as text in `<thinking>` delimiters; `openai-completions`. */
+  requiresThinkingAsText?: boolean
+  /** Whether replayed assistant messages need an empty `reasoning_content` while reasoning is on; `openai-completions`. */
+  requiresReasoningContentOnAssistantMessages?: boolean
+  /** Reasoning parameter format the endpoint expects; `openai-completions`. */
+  thinkingFormat?: PiAiThinkingFormat
+  /**
+   * Kwargs sent as `chat_template_kwargs`, which pi-ai reads only under the
+   * two `chat-template` thinking formats; `openai-completions`. Nothing checks
+   * that pairing: the format in force may come from the installed catalog
+   * entry or from pi-ai's own baseURL detection, neither of which resolution
+   * can read, so kwargs set beside another format are sent nowhere.
+   */
+  chatTemplateKwargs?: NonNullable<OpenAICompletionsCompat['chatTemplateKwargs']>
+  /**
+   * Whether the endpoint accepts `strict` in tool definitions;
+   * `openai-completions`, the three Responses protocols, `bedrock-converse-stream`.
+   */
+  supportsStrictMode?: boolean
+  /** Prompt-cache marker convention; `openai-completions`. */
+  cacheControlFormat?: NonNullable<OpenAICompletionsCompat['cacheControlFormat']>
+  /**
+   * Whether the endpoint accepts long prompt-cache retention;
+   * `openai-completions`, the three Responses protocols, `anthropic-messages`.
+   */
+  supportsLongCacheRetention?: boolean
+  /** Whether the endpoint accepts per-tool `eager_input_streaming`; `anthropic-messages`. */
+  supportsEagerToolInputStreaming?: boolean
+  /** Whether the endpoint accepts `cache_control` on tool definitions; `anthropic-messages`. */
+  supportsCacheControlOnTools?: boolean
+  /** Whether the endpoint accepts the `temperature` request field; `anthropic-messages`. */
+  supportsTemperature?: boolean
+  /** Whether to force adaptive thinking regardless of model id; `anthropic-messages`. */
+  forceAdaptiveThinking?: boolean
+  /** Whether to replay an empty thinking signature instead of converting thinking to text; `anthropic-messages`. */
+  allowEmptySignature?: boolean
+  /** Whether the endpoint accepts Anthropic strict tool schemas; `anthropic-messages`. */
+  supportsStrictTools?: boolean
 }
 
 /** One request modality a pi-ai model may accept. */
@@ -1076,21 +1142,12 @@ export type PiAiModality = Model<Api>['input'][number]
 export type PiAiReasoningEfforts = Partial<Record<ModelThinkingLevel, string | null>>
 
 /** One reasoning-dispatch wire format a profile may name. */
-export type PiAiThinkingFormat = Exclude<PiThinkingFormat, WithheldThinkingFormat>
-
-/** The `compat.thinkingFormat` spellings pi-ai accepts on an `openai-completions` model. */
-type PiThinkingFormat = NonNullable<OpenAICompletionsCompat['thinkingFormat']>
-
-/**
- * pi-ai thinking formats a profile cannot name: both drive the request through
- * `chatTemplateKwargs`, which this configuration does not expose.
- */
-type WithheldThinkingFormat = 'chat-template' | 'qwen-chat-template'
+export type PiAiThinkingFormat = NonNullable<OpenAICompletionsCompat['thinkingFormat']>
 ```
 
-依赖：`Api`（`@earendil-works/pi-ai`）· `CacheRetention`（`@earendil-works/pi-ai`）· `Model`（`@earendil-works/pi-ai`）· `ModelThinkingLevel`（`@earendil-works/pi-ai`）· `OpenAICompletionsCompat`（`@earendil-works/pi-ai`）· [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts) · `ThinkingBudgets`（`@earendil-works/pi-ai`）· `Transport`（`@earendil-works/pi-ai`）
+依赖：`Api`（`@earendil-works/pi-ai`）· `CacheRetention`（`@earendil-works/pi-ai`）· `Model`（`@earendil-works/pi-ai`）· `ModelThinkingLevel`（`@earendil-works/pi-ai`）· `OpenAICompletionsCompat`（`@earendil-works/pi-ai`）· [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts) · `ThinkingBudgets`（`@earendil-works/pi-ai`）· `Transport`（`@earendil-works/pi-ai`)
 
-来源：[`packages/llm/llm-pi-ai/src/config.ts:192`](../packages/llm/llm-pi-ai/src/config.ts)
+来源：[`packages/llm/llm-pi-ai/src/config.ts:201`](../packages/llm/llm-pi-ai/src/config.ts)
 
 <a id="deepseek-aidsh-llm-replay"></a>
 
@@ -1381,7 +1438,7 @@ export interface PlanModeConfig {
 }
 ```
 
-来源：[`packages/plan/plan-mode/src/index.ts:70`](../packages/plan/plan-mode/src/index.ts)
+来源：[`packages/plan/plan-mode/src/index.ts:71`](../packages/plan/plan-mode/src/index.ts)
 
 <a id="deepseek-aidsh-pwsh-local"></a>
 
@@ -2116,7 +2173,7 @@ export interface Config {
 export type ClaudeCodePermissionMode = typeof CLAUDE_CODE_PERMISSION_MODES[number]
 ```
 
-来源：[`packages/subagent/subagent-claude-code/src/index.ts:37`](../packages/subagent/subagent-claude-code/src/index.ts)
+来源：[`packages/subagent/subagent-claude-code/src/index.ts:38`](../packages/subagent/subagent-claude-code/src/index.ts)
 
 <a id="deepseek-aidsh-subagent-codex"></a>
 
@@ -2147,7 +2204,7 @@ export type CodexPermissionMode =
   | 'dangerously-bypass-approvals-and-sandbox'
 ```
 
-来源：[`packages/subagent/subagent-codex/src/index.ts:35`](../packages/subagent/subagent-codex/src/index.ts)
+来源：[`packages/subagent/subagent-codex/src/index.ts:36`](../packages/subagent/subagent-codex/src/index.ts)
 
 <a id="deepseek-aidsh-subagent-dsh-sdk"></a>
 

docs/event-producer-consumer.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 docs/event-producer-consumer.md
-event-producer-consumer.md: c7b474a15c701781a70019f0703c0d60da87bcae
-event-producer-consumer.zh.md: 2e0667288ea44f83b7030e686db194f04d550a9b
+event-producer-consumer.md: c906ee6329fac66e7391c266213dd150dd5b8e09
+event-producer-consumer.zh.md: 77bf401b7215bd263c0d84f04e0eabe6b28b7915

docs/event-producer-consumer.md

@@ -22,7 +22,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac
 | `agent/status` | `emit` | [`packages/core/agent/src/runtime-types.ts:178`](../packages/core/agent/src/runtime-types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`agent`](../packages/core/agent), `apiproxy`, [`compaction-basic`](../packages/compaction/compaction-basic), [`goal-round-driver`](../packages/goal/goal-round-driver), [`schedule`](../packages/schedule/schedule), `server`, [`team`](../packages/experimental/team) |
 | `agent/turn-stopping` | `serial` | [`packages/core/agent/src/runtime-types.ts:278`](../packages/core/agent/src/runtime-types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`hooks-claude-code`](../packages/hooks/hooks-claude-code), [`hooks-codex`](../packages/hooks/hooks-codex) |
 | `approval/request` | `waterfall` | [`packages/interaction/user-approval/src/index.ts:30`](../packages/interaction/user-approval/src/index.ts) | [`user-approval`](../packages/interaction/user-approval) (`waterfall`) | [`acp`](../packages/acp/acp), `apiproxy` |
-| `commands/change` | `emit` | [`packages/interaction/commands/src/types.ts:72`](../packages/interaction/commands/src/types.ts) | [`commands`](../packages/interaction/commands) (`events.dispatch`) | `apiproxy` |
+| `commands/change` | `emit` | [`packages/interaction/commands/src/types.ts:80`](../packages/interaction/commands/src/types.ts) | [`commands`](../packages/interaction/commands) (`events.dispatch`) | `apiproxy` |
 | `cordis/dynamic-package` | `emit` | [`packages/extensions/cordis-host-runner/src/types.ts:379`](../packages/extensions/cordis-host-runner/src/types.ts) | [`cordis-host-runner`](../packages/extensions/cordis-host-runner) (`emit`) | `apiproxy` |
 | `cordis/dynamic-retract` | `emit` | [`packages/extensions/cordis-host-runner/src/types.ts:385`](../packages/extensions/cordis-host-runner/src/types.ts) | [`cordis-host-runner`](../packages/extensions/cordis-host-runner) (`emit`) | `apiproxy` |
 | `cordis/inspect-query` | `emit` | [`packages/extensions/cordis-host-runner/src/types.ts:391`](../packages/extensions/cordis-host-runner/src/types.ts) | [`cordis-host-runner`](../packages/extensions/cordis-host-runner) (`emit`) | `apiproxy` |

docs/event-producer-consumer.zh.md

@@ -24,7 +24,7 @@
 | `agent/status` | `emit` | [`packages/core/agent/src/runtime-types.ts:178`](../packages/core/agent/src/runtime-types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`agent`](../packages/core/agent), `apiproxy`, [`compaction-basic`](../packages/compaction/compaction-basic), [`goal-round-driver`](../packages/goal/goal-round-driver), [`schedule`](../packages/schedule/schedule), `server`, [`team`](../packages/experimental/team) |
 | `agent/turn-stopping` | `serial` | [`packages/core/agent/src/runtime-types.ts:278`](../packages/core/agent/src/runtime-types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`hooks-claude-code`](../packages/hooks/hooks-claude-code), [`hooks-codex`](../packages/hooks/hooks-codex) |
 | `approval/request` | `waterfall` | [`packages/interaction/user-approval/src/index.ts:30`](../packages/interaction/user-approval/src/index.ts) | [`user-approval`](../packages/interaction/user-approval) (`waterfall`) | [`acp`](../packages/acp/acp), `apiproxy` |
-| `commands/change` | `emit` | [`packages/interaction/commands/src/types.ts:72`](../packages/interaction/commands/src/types.ts) | [`commands`](../packages/interaction/commands) (`events.dispatch`) | `apiproxy` |
+| `commands/change` | `emit` | [`packages/interaction/commands/src/types.ts:80`](../packages/interaction/commands/src/types.ts) | [`commands`](../packages/interaction/commands) (`events.dispatch`) | `apiproxy` |
 | `cordis/dynamic-package` | `emit` | [`packages/extensions/cordis-host-runner/src/types.ts:379`](../packages/extensions/cordis-host-runner/src/types.ts) | [`cordis-host-runner`](../packages/extensions/cordis-host-runner) (`emit`) | `apiproxy` |
 | `cordis/dynamic-retract` | `emit` | [`packages/extensions/cordis-host-runner/src/types.ts:385`](../packages/extensions/cordis-host-runner/src/types.ts) | [`cordis-host-runner`](../packages/extensions/cordis-host-runner) (`emit`) | `apiproxy` |
 | `cordis/inspect-query` | `emit` | [`packages/extensions/cordis-host-runner/src/types.ts:391`](../packages/extensions/cordis-host-runner/src/types.ts) | [`cordis-host-runner`](../packages/extensions/cordis-host-runner) (`emit`) | `apiproxy` |

docs/module-graph.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 docs/module-graph.md
-module-graph.md: 54aa13217a01ed44b44925365526438d4c867928
-module-graph.zh.md: 33c2f53afeb94c6d844f8406c1043d780436f588
+module-graph.md: 38d3acc73175d504dadf22e4a5317e5f84ff5be8
+module-graph.zh.md: 76880c34aef07f877147a90f62dacd2b6877de41

docs/module-graph.md

@@ -407,6 +407,7 @@ flowchart TD
   pkg_settings_file --> pkg_invariants
   pkg_settings_file --> pkg_settings
   pkg_llm_deepseek --> pkg_anonymous_user_id
+  pkg_llm_deepseek --> pkg_attachment
   pkg_llm_deepseek --> pkg_credentials
   pkg_llm_deepseek --> pkg_invariants
   pkg_llm_deepseek --> pkg_launch_environment
@@ -520,8 +521,10 @@ flowchart TD
   pkg_message_feedback --> pkg_storage_domain
   pkg_message_feedback --> pkg_typert_protocol
   pkg_commands --> pkg_agent
+  pkg_commands --> pkg_attachment
   pkg_commands --> pkg_brand
   pkg_commands --> pkg_invariants
+  pkg_commands --> pkg_llm
   pkg_commands --> pkg_scope
   pkg_commands --> pkg_session
   pkg_commands --> pkg_typert_protocol
@@ -612,6 +615,7 @@ flowchart TD
   pkg_command_goal --> pkg_commands
   pkg_command_goal --> pkg_goal
   pkg_command_goal --> pkg_invariants
+  pkg_command_goal --> pkg_llm
   pkg_goal_round_driver --> pkg_agent
   pkg_goal_round_driver --> pkg_goal
   pkg_goal_round_driver --> pkg_invariants
@@ -1329,6 +1333,7 @@ flowchart TD
   pkg_client_ui_subagent --> pkg_subagent
   pkg_client_ui_subagent --> pkg_token_meter
   pkg_client_ui_tool --> pkg_api_remotes
+  pkg_client_ui_tool --> pkg_client_connection
   pkg_client_ui_tool --> pkg_client_locale
   pkg_client_ui_tool --> pkg_client_runtime
   pkg_client_ui_tool --> pkg_client_ui_conversation
@@ -1352,6 +1357,7 @@ flowchart TD
   pkg_client_ui_workflow_run --> pkg_session
   pkg_client_ui_workflow_run --> pkg_tool_workflow
   pkg_client_ui_workflow_run --> pkg_workflow
+  pkg_client_ui_workspace --> pkg_client_connection
   pkg_client_ui_workspace --> pkg_client_locale
   pkg_client_ui_workspace --> pkg_client_runtime
   pkg_client_ui_workspace --> pkg_client_ui_conversation
@@ -1460,7 +1466,7 @@ flowchart TD
 | [`client-hmr`](../packages/client/hmr) | `client` | [`client-modules`](../packages/client/modules), [`host-webserver`](../packages/host/webserver), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`credentials-local`](../packages/credentials/credentials-local) | `credentials` | [`atomic-write`](../packages/util/atomic-write), [`credentials`](../packages/credentials/credentials), [`home-paths`](../packages/util/home-paths), [`invariants`](../packages/runtime-diagnostics/invariants), [`launch-environment`](../packages/util/launch-environment) |
 | [`settings-file`](../packages/settings/settings-file) | `settings` | [`atomic-write`](../packages/util/atomic-write), [`home-paths`](../packages/util/home-paths), [`invariants`](../packages/runtime-diagnostics/invariants), [`settings`](../packages/settings/settings) |
-| [`llm-deepseek`](../packages/llm/llm-deepseek) | `llm` | [`anonymous-user-id`](../packages/identity/anonymous-user-id), [`credentials`](../packages/credentials/credentials), [`invariants`](../packages/runtime-diagnostics/invariants), [`launch-environment`](../packages/util/launch-environment), [`llm`](../packages/llm/llm), [`settings`](../packages/settings/settings), [`timeout`](../packages/util/timeout) |
+| [`llm-deepseek`](../packages/llm/llm-deepseek) | `llm` | [`anonymous-user-id`](../packages/identity/anonymous-user-id), [`attachment`](../packages/attachment/attachment), [`credentials`](../packages/credentials/credentials), [`invariants`](../packages/runtime-diagnostics/invariants), [`launch-environment`](../packages/util/launch-environment), [`llm`](../packages/llm/llm), [`settings`](../packages/settings/settings), [`timeout`](../packages/util/timeout) |
 | [`llm-pi-ai`](../packages/llm/llm-pi-ai) | `llm` | [`attachment`](../packages/attachment/attachment), [`credentials`](../packages/credentials/credentials), [`invariants`](../packages/runtime-diagnostics/invariants), [`launch-environment`](../packages/util/launch-environment), [`llm`](../packages/llm/llm), [`settings`](../packages/settings/settings), [`timeout`](../packages/util/timeout) |
 | [`session`](../packages/core/session) | `core` | [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`typert-protocol`](../packages/typert/protocol) |
 | [`system-prompt`](../packages/core/system-prompt) | `core` | [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope) |
@@ -1488,7 +1494,7 @@ flowchart TD
 | [`spill-local`](../packages/spill/spill-local) | `spill` | [`invariants`](../packages/runtime-diagnostics/invariants), [`spill`](../packages/spill/spill) |
 | [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent), [`invariants`](../packages/runtime-diagnostics/invariants), [`session`](../packages/core/session) |
 | [`message-feedback`](../packages/feedback/message-feedback) | `feedback` | [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session/session-persistence), [`storage-domain`](../packages/storage/storage-domain), [`typert-protocol`](../packages/typert/protocol) |
-| [`commands`](../packages/interaction/commands) | `interaction` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`typert-protocol`](../packages/typert/protocol) |
+| [`commands`](../packages/interaction/commands) | `interaction` | [`agent`](../packages/core/agent), [`attachment`](../packages/attachment/attachment), [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`typert-protocol`](../packages/typert/protocol) |
 | [`user-approval`](../packages/interaction/user-approval) | `interaction` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
 | [`user-questions`](../packages/interaction/user-questions) | `interaction` | [`agent`](../packages/core/agent), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm) |
 | [`jobs`](../packages/jobs/jobs) | `jobs` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`session`](../packages/core/session) |
@@ -1507,7 +1513,7 @@ flowchart TD
 | [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
 | [`workspace`](../packages/workspace/workspace) | `workspace` | [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`session`](../packages/core/session), [`session-persistence`](../packages/session/session-persistence), [`storage`](../packages/storage/storage), [`storage-domain`](../packages/storage/storage-domain) |
 | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/interaction/user-approval) |
-| [`command-goal`](../packages/goal/command-goal) | `goal` | [`commands`](../packages/interaction/commands), [`goal`](../packages/goal/goal), [`invariants`](../packages/runtime-diagnostics/invariants) |
+| [`command-goal`](../packages/goal/command-goal) | `goal` | [`commands`](../packages/interaction/commands), [`goal`](../packages/goal/goal), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm) |
 | [`goal-round-driver`](../packages/goal/goal-round-driver) | `goal` | [`agent`](../packages/core/agent), [`goal`](../packages/goal/goal), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
 | [`fs-local`](../packages/fs/fs-local) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`fs-observation-policy`](../packages/fs/fs-observation-policy) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/runtime-diagnostics/invariants) |
@@ -1621,11 +1627,11 @@ flowchart TD
 | [`client-ui-plan`](../packages/client/ui-plan) | `client` | [`api-remotes`](../packages/api/remotes), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`invariants`](../packages/runtime-diagnostics/invariants), [`plan-mode`](../packages/plan/plan-mode) |
 | [`client-ui-settings-general`](../packages/client/ui-settings-general) | `client` | [`api-remotes`](../packages/api/remotes), [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-settings`](../packages/client/ui-settings), [`client-ui-sidebar`](../packages/client/ui-sidebar), [`invariants`](../packages/runtime-diagnostics/invariants), [`settings`](../packages/settings/settings) |
 | [`client-ui-subagent`](../packages/client/ui-subagent) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-input-trigger`](../packages/client/ui-input-trigger), [`invariants`](../packages/runtime-diagnostics/invariants), [`subagent`](../packages/subagent/subagent), [`token-meter`](../packages/llm/token-meter) |
-| [`client-ui-tool`](../packages/client/ui-tool) | `client` | [`api-remotes`](../packages/api/remotes), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`invariants`](../packages/runtime-diagnostics/invariants) |
+| [`client-ui-tool`](../packages/client/ui-tool) | `client` | [`api-remotes`](../packages/api/remotes), [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`client-ui-trajectory`](../packages/client/ui-trajectory) | `client` | [`agent`](../packages/core/agent), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`compaction`](../packages/compaction/compaction), [`invariants`](../packages/runtime-diagnostics/invariants), [`tools`](../packages/core/tools) |
 | [`client-ui-user-questions`](../packages/client/ui-user-questions) | `client` | [`api-remotes`](../packages/api/remotes), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`client-ui-workflow-run`](../packages/client/ui-workflow-run) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`invariants`](../packages/runtime-diagnostics/invariants), [`session`](../packages/core/session), [`tool-workflow`](../packages/workflow/tool-workflow), [`workflow`](../packages/workflow/workflow) |
-| [`client-ui-workspace`](../packages/client/ui-workspace) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-sidebar`](../packages/client/ui-sidebar), [`invariants`](../packages/runtime-diagnostics/invariants) |
+| [`client-ui-workspace`](../packages/client/ui-workspace) | `client` | [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-sidebar`](../packages/client/ui-sidebar), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`session-log-export`](../packages/session-query/session-log-export) | `session-query` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-commands`](../packages/client/ui-commands), [`client-ui-conversation`](../packages/client/ui-conversation), [`commands`](../packages/interaction/commands), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`client-ui-directory-picker-browse`](../packages/client/ui-directory-picker-browse) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-workspace`](../packages/client/ui-workspace), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`client-ui-directory-picker-native`](../packages/client/ui-directory-picker-native) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-workspace`](../packages/client/ui-workspace), [`invariants`](../packages/runtime-diagnostics/invariants) |

docs/module-graph.zh.md

@@ -409,6 +409,7 @@ flowchart TD
   pkg_settings_file --> pkg_invariants
   pkg_settings_file --> pkg_settings
   pkg_llm_deepseek --> pkg_anonymous_user_id
+  pkg_llm_deepseek --> pkg_attachment
   pkg_llm_deepseek --> pkg_credentials
   pkg_llm_deepseek --> pkg_invariants
   pkg_llm_deepseek --> pkg_launch_environment
@@ -522,8 +523,10 @@ flowchart TD
   pkg_message_feedback --> pkg_storage_domain
   pkg_message_feedback --> pkg_typert_protocol
   pkg_commands --> pkg_agent
+  pkg_commands --> pkg_attachment
   pkg_commands --> pkg_brand
   pkg_commands --> pkg_invariants
+  pkg_commands --> pkg_llm
   pkg_commands --> pkg_scope
   pkg_commands --> pkg_session
   pkg_commands --> pkg_typert_protocol
@@ -614,6 +617,7 @@ flowchart TD
   pkg_command_goal --> pkg_commands
   pkg_command_goal --> pkg_goal
   pkg_command_goal --> pkg_invariants
+  pkg_command_goal --> pkg_llm
   pkg_goal_round_driver --> pkg_agent
   pkg_goal_round_driver --> pkg_goal
   pkg_goal_round_driver --> pkg_invariants
@@ -1331,6 +1335,7 @@ flowchart TD
   pkg_client_ui_subagent --> pkg_subagent
   pkg_client_ui_subagent --> pkg_token_meter
   pkg_client_ui_tool --> pkg_api_remotes
+  pkg_client_ui_tool --> pkg_client_connection
   pkg_client_ui_tool --> pkg_client_locale
   pkg_client_ui_tool --> pkg_client_runtime
   pkg_client_ui_tool --> pkg_client_ui_conversation
@@ -1354,6 +1359,7 @@ flowchart TD
   pkg_client_ui_workflow_run --> pkg_session
   pkg_client_ui_workflow_run --> pkg_tool_workflow
   pkg_client_ui_workflow_run --> pkg_workflow
+  pkg_client_ui_workspace --> pkg_client_connection
   pkg_client_ui_workspace --> pkg_client_locale
   pkg_client_ui_workspace --> pkg_client_runtime
   pkg_client_ui_workspace --> pkg_client_ui_conversation
@@ -1462,7 +1468,7 @@ flowchart TD
 | [`client-hmr`](../packages/client/hmr) | `client` | [`client-modules`](../packages/client/modules), [`host-webserver`](../packages/host/webserver), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`credentials-local`](../packages/credentials/credentials-local) | `credentials` | [`atomic-write`](../packages/util/atomic-write), [`credentials`](../packages/credentials/credentials), [`home-paths`](../packages/util/home-paths), [`invariants`](../packages/runtime-diagnostics/invariants), [`launch-environment`](../packages/util/launch-environment) |
 | [`settings-file`](../packages/settings/settings-file) | `settings` | [`atomic-write`](../packages/util/atomic-write), [`home-paths`](../packages/util/home-paths), [`invariants`](../packages/runtime-diagnostics/invariants), [`settings`](../packages/settings/settings) |
-| [`llm-deepseek`](../packages/llm/llm-deepseek) | `llm` | [`anonymous-user-id`](../packages/identity/anonymous-user-id), [`credentials`](../packages/credentials/credentials), [`invariants`](../packages/runtime-diagnostics/invariants), [`launch-environment`](../packages/util/launch-environment), [`llm`](../packages/llm/llm), [`settings`](../packages/settings/settings), [`timeout`](../packages/util/timeout) |
+| [`llm-deepseek`](../packages/llm/llm-deepseek) | `llm` | [`anonymous-user-id`](../packages/identity/anonymous-user-id), [`attachment`](../packages/attachment/attachment), [`credentials`](../packages/credentials/credentials), [`invariants`](../packages/runtime-diagnostics/invariants), [`launch-environment`](../packages/util/launch-environment), [`llm`](../packages/llm/llm), [`settings`](../packages/settings/settings), [`timeout`](../packages/util/timeout) |
 | [`llm-pi-ai`](../packages/llm/llm-pi-ai) | `llm` | [`attachment`](../packages/attachment/attachment), [`credentials`](../packages/credentials/credentials), [`invariants`](../packages/runtime-diagnostics/invariants), [`launch-environment`](../packages/util/launch-environment), [`llm`](../packages/llm/llm), [`settings`](../packages/settings/settings), [`timeout`](../packages/util/timeout) |
 | [`session`](../packages/core/session) | `core` | [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`typert-protocol`](../packages/typert/protocol) |
 | [`system-prompt`](../packages/core/system-prompt) | `core` | [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope) |
@@ -1490,7 +1496,7 @@ flowchart TD
 | [`spill-local`](../packages/spill/spill-local) | `spill` | [`invariants`](../packages/runtime-diagnostics/invariants), [`spill`](../packages/spill/spill) |
 | [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent), [`invariants`](../packages/runtime-diagnostics/invariants), [`session`](../packages/core/session) |
 | [`message-feedback`](../packages/feedback/message-feedback) | `feedback` | [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session/session-persistence), [`storage-domain`](../packages/storage/storage-domain), [`typert-protocol`](../packages/typert/protocol) |
-| [`commands`](../packages/interaction/commands) | `interaction` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`typert-protocol`](../packages/typert/protocol) |
+| [`commands`](../packages/interaction/commands) | `interaction` | [`agent`](../packages/core/agent), [`attachment`](../packages/attachment/attachment), [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`typert-protocol`](../packages/typert/protocol) |
 | [`user-approval`](../packages/interaction/user-approval) | `interaction` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) |
 | [`user-questions`](../packages/interaction/user-questions) | `interaction` | [`agent`](../packages/core/agent), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm) |
 | [`jobs`](../packages/jobs/jobs) | `jobs` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`session`](../packages/core/session) |
@@ -1509,7 +1515,7 @@ flowchart TD
 | [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
 | [`workspace`](../packages/workspace/workspace) | `workspace` | [`brand`](../packages/util/brand), [`invariants`](../packages/runtime-diagnostics/invariants), [`session`](../packages/core/session), [`session-persistence`](../packages/session/session-persistence), [`storage`](../packages/storage/storage), [`storage-domain`](../packages/storage/storage-domain) |
 | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/interaction/user-approval) |
-| [`command-goal`](../packages/goal/command-goal) | `goal` | [`commands`](../packages/interaction/commands), [`goal`](../packages/goal/goal), [`invariants`](../packages/runtime-diagnostics/invariants) |
+| [`command-goal`](../packages/goal/command-goal) | `goal` | [`commands`](../packages/interaction/commands), [`goal`](../packages/goal/goal), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm) |
 | [`goal-round-driver`](../packages/goal/goal-round-driver) | `goal` | [`agent`](../packages/core/agent), [`goal`](../packages/goal/goal), [`invariants`](../packages/runtime-diagnostics/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) |
 | [`fs-local`](../packages/fs/fs-local) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`fs-observation-policy`](../packages/fs/fs-observation-policy) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/runtime-diagnostics/invariants) |
@@ -1623,11 +1629,11 @@ flowchart TD
 | [`client-ui-plan`](../packages/client/ui-plan) | `client` | [`api-remotes`](../packages/api/remotes), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`invariants`](../packages/runtime-diagnostics/invariants), [`plan-mode`](../packages/plan/plan-mode) |
 | [`client-ui-settings-general`](../packages/client/ui-settings-general) | `client` | [`api-remotes`](../packages/api/remotes), [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-settings`](../packages/client/ui-settings), [`client-ui-sidebar`](../packages/client/ui-sidebar), [`invariants`](../packages/runtime-diagnostics/invariants), [`settings`](../packages/settings/settings) |
 | [`client-ui-subagent`](../packages/client/ui-subagent) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-input-trigger`](../packages/client/ui-input-trigger), [`invariants`](../packages/runtime-diagnostics/invariants), [`subagent`](../packages/subagent/subagent), [`token-meter`](../packages/llm/token-meter) |
-| [`client-ui-tool`](../packages/client/ui-tool) | `client` | [`api-remotes`](../packages/api/remotes), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`invariants`](../packages/runtime-diagnostics/invariants) |
+| [`client-ui-tool`](../packages/client/ui-tool) | `client` | [`api-remotes`](../packages/api/remotes), [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`client-ui-trajectory`](../packages/client/ui-trajectory) | `client` | [`agent`](../packages/core/agent), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`compaction`](../packages/compaction/compaction), [`invariants`](../packages/runtime-diagnostics/invariants), [`tools`](../packages/core/tools) |
 | [`client-ui-user-questions`](../packages/client/ui-user-questions) | `client` | [`api-remotes`](../packages/api/remotes), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`client-ui-workflow-run`](../packages/client/ui-workflow-run) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`invariants`](../packages/runtime-diagnostics/invariants), [`session`](../packages/core/session), [`tool-workflow`](../packages/workflow/tool-workflow), [`workflow`](../packages/workflow/workflow) |
-| [`client-ui-workspace`](../packages/client/ui-workspace) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-sidebar`](../packages/client/ui-sidebar), [`invariants`](../packages/runtime-diagnostics/invariants) |
+| [`client-ui-workspace`](../packages/client/ui-workspace) | `client` | [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-sidebar`](../packages/client/ui-sidebar), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`session-log-export`](../packages/session-query/session-log-export) | `session-query` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-commands`](../packages/client/ui-commands), [`client-ui-conversation`](../packages/client/ui-conversation), [`commands`](../packages/interaction/commands), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`client-ui-directory-picker-browse`](../packages/client/ui-directory-picker-browse) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-workspace`](../packages/client/ui-workspace), [`invariants`](../packages/runtime-diagnostics/invariants) |
 | [`client-ui-directory-picker-native`](../packages/client/ui-directory-picker-native) | `client` | [`client-runtime`](../packages/client/runtime), [`client-ui-workspace`](../packages/client/ui-workspace), [`invariants`](../packages/runtime-diagnostics/invariants) |

docs/persistence-catalog.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 docs/persistence-catalog.md
-persistence-catalog.md: 24d50cdb4830202e6cac106edf7e93613e17c05e
-persistence-catalog.zh.md: ce09d703d0e5284920e5fc0427b25ca060ed7ef1
+persistence-catalog.md: cbe9cec195ad899ba27dd08743d64090ae7277f2
+persistence-catalog.zh.md: 8057a0910e505b95872c341283d1acdbf033faaf

docs/persistence-catalog.md

@@ -260,7 +260,7 @@ Source: [`packages/core/session/src/types.ts:277`](../packages/core/session/src/
 }
 ```
 
-Source: [`packages/interaction/commands/src/types.ts:95`](../packages/interaction/commands/src/types.ts)
+Source: [`packages/interaction/commands/src/types.ts:103`](../packages/interaction/commands/src/types.ts)
 
 <a id="commandrun--log-only"></a>
 
@@ -280,7 +280,7 @@ Source: [`packages/interaction/commands/src/types.ts:95`](../packages/interactio
 'command/run': { commandId: CommandId; name: string; args?: string; source: CommandSource }
 ```
 
-Source: [`packages/interaction/commands/src/types.ts:88`](../packages/interaction/commands/src/types.ts)
+Source: [`packages/interaction/commands/src/types.ts:96`](../packages/interaction/commands/src/types.ts)
 
 ### `compaction/*`
 
@@ -531,7 +531,7 @@ Source: [`packages/interaction/permission-presets/src/index.ts:50`](../packages/
 'plan/mode': { active: boolean }
 ```
 
-Source: [`packages/plan/plan-mode/src/index.ts:53`](../packages/plan/plan-mode/src/index.ts)
+Source: [`packages/plan/plan-mode/src/index.ts:54`](../packages/plan/plan-mode/src/index.ts)
 
 ### `request/*`
 

docs/persistence-catalog.zh.md

@@ -262,7 +262,7 @@ export type SessionEvent<T extends SessionEventType = SessionEventType> = {
 }
 ```
 
-来源：[`packages/interaction/commands/src/types.ts:95`](../packages/interaction/commands/src/types.ts)
+来源：[`packages/interaction/commands/src/types.ts:103`](../packages/interaction/commands/src/types.ts)
 
 <a id="commandrun--log-only"></a>
 
@@ -282,7 +282,7 @@ export type SessionEvent<T extends SessionEventType = SessionEventType> = {
 'command/run': { commandId: CommandId; name: string; args?: string; source: CommandSource }
 ```
 
-来源：[`packages/interaction/commands/src/types.ts:88`](../packages/interaction/commands/src/types.ts)
+来源：[`packages/interaction/commands/src/types.ts:96`](../packages/interaction/commands/src/types.ts)
 
 ### `compaction/*`
 
@@ -533,7 +533,7 @@ export type SessionEvent<T extends SessionEventType = SessionEventType> = {
 'plan/mode': { active: boolean }
 ```
 
-来源：[`packages/plan/plan-mode/src/index.ts:53`](../packages/plan/plan-mode/src/index.ts)
+来源：[`packages/plan/plan-mode/src/index.ts:54`](../packages/plan/plan-mode/src/index.ts)
 
 ### `request/*`
 

docs/subsystems/attachment.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 docs/subsystems/attachment.md
-attachment.md: 21e60dbc40504f22229ef98a2dd112eda82fffdd
-attachment.zh.md: 886e569b6db9f2a5b1dca39125785d8286e22c7a
+attachment.md: 748d3feb47ff6bdf2ab6849f2509a3c495fcd87a
+attachment.zh.md: eed28affb2c40726a088ddf2f0e17077d5a22df6

docs/subsystems/attachment.md

@@ -52,6 +52,18 @@ The reference records intrinsic dimensions and encoded length so clients can lay
 
 ## Commit and verified-read payloads
 
+```ts type-equiv
+/** Base64-encoded image upload accompanying one wire request. */
+interface EncodedImageAttachment {
+  /** Declared media type, verified against the decoded bytes during admission. */
+  mediaType: ImageMediaType
+  /** Canonical base64 encoding of the image bytes. */
+  data: string
+  /** Optional display name; it is never interpreted as a path. */
+  name?: string
+}
+```
+
 ```ts type-equiv
 /** Request to validate and durably commit one image. */
 interface SaveImageAttachment {
@@ -71,7 +83,7 @@ interface StoredImageAttachment {
 }
 ```
 
-`saveImage()` validates bytes and atomically commits one object before returning its reference. `validateImage()` runs the same admission checks without persisting anything; batch callers validate every member through it before saving any member, so validation rejection leaves no partial objects behind. `readImage()` accepts a reference from an authorized session path and returns bytes only after integrity verification. The service is deliberately retention-neutral: resumed and forked sessions may share objects, so reference-aware garbage collection is deferred rather than tied to any one session's deletion.
+`saveImage()` validates bytes and atomically commits one object before returning its reference. `validateImage()` runs the same admission checks without persisting anything; batch callers validate every member through it before saving any member, so validation rejection leaves no partial objects behind. `admitEncodedImages()` is the wire entry for base64 uploads: it enforces canonical base64, then delegates batch admission to `saveImages()`, which owns the count and aggregate-byte limits and the validate-all-before-save order. `readImage()` accepts a reference from an authorized session path and returns bytes only after integrity verification. The service is deliberately retention-neutral: resumed and forked sessions may share objects, so reference-aware garbage collection is deferred rather than tied to any one session's deletion.
 
 <!-- BEGIN GENERATED cordis-surface (gen-cordis-catalog.ts) — do not edit between markers -->
 
@@ -123,5 +135,5 @@ abstract saveImage(input: SaveImageAttachment): Promise<ImageAttachmentRef>
 abstract readImage(ref: ImageAttachmentRef, signal?: AbortSignal): Promise<StoredImageAttachment>
 ```
 
-Source: [`packages/attachment/attachment/src/index.ts:31`](../../packages/attachment/attachment/src/index.ts)
+Source: [`packages/attachment/attachment/src/index.ts:33`](../../packages/attachment/attachment/src/index.ts)
 <!-- END GENERATED cordis-surface -->

docs/subsystems/attachment.zh.md

@@ -52,6 +52,18 @@ interface ImageAttachmentLimits {
 
 ## 提交与经校验读取的数据
 
+```ts type-equiv
+/** Base64-encoded image upload accompanying one wire request. */
+interface EncodedImageAttachment {
+  /** Declared media type, verified against the decoded bytes during admission. */
+  mediaType: ImageMediaType
+  /** Canonical base64 encoding of the image bytes. */
+  data: string
+  /** Optional display name; it is never interpreted as a path. */
+  name?: string
+}
+```
+
 ```ts type-equiv
 /** Request to validate and durably commit one image. */
 interface SaveImageAttachment {
@@ -71,7 +83,7 @@ interface StoredImageAttachment {
 }
 ```
 
-`saveImage()` 校验字节并以原子方式提交一个对象，之后才返回其引用。`validateImage()` 执行相同的准入检查，但不持久化任何内容；批量调用方会在保存任何成员前通过它校验所有成员，因此校验拒绝不会留下部分对象。`readImage()` 接受来自已授权会话路径的引用，只在完整性校验通过后返回字节。该服务刻意不规定保留策略：恢复和 fork 后的会话可能共享对象，因此基于引用的垃圾回收会延期实现，而不是与任何一个会话的删除绑定。
+`saveImage()` 校验字节并以原子方式提交一个对象，之后才返回其引用。`validateImage()` 执行相同的准入检查，但不持久化任何内容；批量调用方会在保存任何成员前通过它校验所有成员，因此校验拒绝不会留下部分对象。`admitEncodedImages()` 是面向 base64 上传的 wire 入口：强制执行规范 base64，随后把批量准入委托给 `saveImages()`，由后者负责张数与聚合字节上限以及先全量校验再保存的顺序。`readImage()` 接受来自已授权会话路径的引用，只在完整性校验通过后返回字节。该服务刻意不规定保留策略：恢复和 fork 后的会话可能共享对象，因此基于引用的垃圾回收会延期实现，而不是与任何一个会话的删除绑定。
 
 <!-- BEGIN GENERATED cordis-surface (gen-cordis-catalog.ts) — do not edit between markers -->
 
@@ -123,5 +135,5 @@ abstract saveImage(input: SaveImageAttachment): Promise<ImageAttachmentRef>
 abstract readImage(ref: ImageAttachmentRef, signal?: AbortSignal): Promise<StoredImageAttachment>
 ```
 
-Source: [`packages/attachment/attachment/src/index.ts:31`](../../packages/attachment/attachment/src/index.ts)
+Source: [`packages/attachment/attachment/src/index.ts:33`](../../packages/attachment/attachment/src/index.ts)
 <!-- END GENERATED cordis-surface -->

docs/subsystems/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 docs/subsystems/commands.md
-commands.md: a4589d875fafdda7404e8c2d54fb739a4e945990
-commands.zh.md: 460784442257cc081fb73646c51885a432efadb5
+commands.md: a9752915d4eae22d448b5480f2d50746fd02ec5f
+commands.zh.md: 2fe3d71bafaf6653251a8ab53832dd4701152194

docs/subsystems/commands.md

@@ -8,13 +8,21 @@ Source: [`packages/interaction/commands/src/index.ts`](../../packages/interactio
 
 ## Input metadata
 
-The service exposes one optional unstructured-input hint. Command availability follows plugin composition: every adapter consuming the registry sees every effective definition.
+The service exposes one optional unstructured-input descriptor: a hint plus an image-acceptance flag. Command availability follows plugin composition: every adapter consuming the registry sees every effective definition.
 
 ```ts type-equiv
 /** Immutable metadata for a command's optional unstructured input. */
 interface CommandInputDescriptor {
   /** Placeholder shown before the user supplies free-form input. */
   readonly hint: string
+  /**
+   * Whether composer image attachments may accompany an invocation. Absent or
+   * false = the executor rejects an invocation carrying images and capable
+   * composers refuse the submission before dispatch. A declaring command's
+   * handler receives the admitted durable blocks and owns every further
+   * grammar decision, including rejecting sub-commands that cannot use them.
+   */
+  readonly images?: boolean
 }
 ```
 
@@ -55,6 +63,14 @@ interface CommandInvocation {
   readonly agent: Agent
   /** Exact text following the registered command name, including separator whitespace. */
   readonly rawInput: string
+  /**
+   * Durably admitted image blocks accompanying this invocation, in submission
+   * order; empty unless the definition declares `input.images`. The handler
+   * owns their model-visible use — the registry never schedules them itself —
+   * and a handler whose grammar cannot use them in this invocation returns an
+   * error so the dispatching composer retains the originals.
+   */
+  readonly attachments: readonly ImageBlock[]
   /** Cancellation signal owned by the dispatching UI request. */
   readonly signal: AbortSignal
 }
@@ -150,18 +166,25 @@ find(agent: Agent, name: string): CommandDefinition | undefined
  * handler-failure path is contained so the handler's own error stays the
  * reported failure.
  *
+ * Image admission is enforced here, not in the composer: images sent to a
+ * command that does not declare `input.images`, an absent attachment store,
+ * and an exceeded attachment limit each settle as an error result before
+ * the handler runs, and a rejected batch publishes no durable object.
+ *
  * @param agent - exact receiving agent.
  * @param line - complete slash-command line.
+ * @param images - base64-encoded composer images accompanying the line, in
+ *   submission order; empty for a plain invocation.
  * @param signal - cancellation signal owned by the UI request.
  * @returns the settled execution (result + lifecycle pairing id), or
  *   `undefined` when syntax or name does not resolve.
  */
-@Remote async execute( agent: Agent, line: string, signal: AbortSignal, ): Promise<CommandExecution | undefined>
+@Remote async execute( agent: Agent, line: string, images: readonly EncodedImageAttachment[], signal: AbortSignal, ): Promise<CommandExecution | undefined>
 ```
 
-Types: [Agent](core.md)
+Types: [Agent](core.md) · [EncodedImageAttachment](attachment.md)
 
-Source: [`packages/interaction/commands/src/index.ts:225`](../../packages/interaction/commands/src/index.ts)
+Source: [`packages/interaction/commands/src/index.ts:250`](../../packages/interaction/commands/src/index.ts)
 
 <a id="commands-events"></a>
 
@@ -183,5 +206,5 @@ A command was registered or unregistered. This is an unfiltered registry notific
 'commands/change'(): void
 ```
 
-Source: [`packages/interaction/commands/src/types.ts:72`](../../packages/interaction/commands/src/types.ts)
+Source: [`packages/interaction/commands/src/types.ts:80`](../../packages/interaction/commands/src/types.ts)
 <!-- END GENERATED cordis-surface -->

docs/subsystems/commands.zh.md

@@ -8,13 +8,21 @@
 
 ## 输入元数据
 
-该服务公开一个可选的非结构化输入提示。命令的可用性由插件组合决定：每个消费注册表的适配器都会看到全部生效定义。
+该服务公开一个可选的非结构化输入描述符：提示文本加图片接受标志。命令的可用性由插件组合决定：每个消费注册表的适配器都会看到全部生效定义。
 
 ```ts type-equiv
 /** Immutable metadata for a command's optional unstructured input. */
 interface CommandInputDescriptor {
   /** Placeholder shown before the user supplies free-form input. */
   readonly hint: string
+  /**
+   * Whether composer image attachments may accompany an invocation. Absent or
+   * false = the executor rejects an invocation carrying images and capable
+   * composers refuse the submission before dispatch. A declaring command's
+   * handler receives the admitted durable blocks and owns every further
+   * grammar decision, including rejecting sub-commands that cannot use them.
+   */
+  readonly images?: boolean
 }
 ```
 
@@ -55,6 +63,14 @@ interface CommandInvocation {
   readonly agent: Agent
   /** Exact text following the registered command name, including separator whitespace. */
   readonly rawInput: string
+  /**
+   * Durably admitted image blocks accompanying this invocation, in submission
+   * order; empty unless the definition declares `input.images`. The handler
+   * owns their model-visible use — the registry never schedules them itself —
+   * and a handler whose grammar cannot use them in this invocation returns an
+   * error so the dispatching composer retains the originals.
+   */
+  readonly attachments: readonly ImageBlock[]
   /** Cancellation signal owned by the dispatching UI request. */
   readonly signal: AbortSignal
 }
@@ -150,18 +166,25 @@ find(agent: Agent, name: string): CommandDefinition | undefined
  * handler-failure path is contained so the handler's own error stays the
  * reported failure.
  *
+ * Image admission is enforced here, not in the composer: images sent to a
+ * command that does not declare `input.images`, an absent attachment store,
+ * and an exceeded attachment limit each settle as an error result before
+ * the handler runs, and a rejected batch publishes no durable object.
+ *
  * @param agent - exact receiving agent.
  * @param line - complete slash-command line.
+ * @param images - base64-encoded composer images accompanying the line, in
+ *   submission order; empty for a plain invocation.
  * @param signal - cancellation signal owned by the UI request.
  * @returns the settled execution (result + lifecycle pairing id), or
  *   `undefined` when syntax or name does not resolve.
  */
-@Remote async execute( agent: Agent, line: string, signal: AbortSignal, ): Promise<CommandExecution | undefined>
+@Remote async execute( agent: Agent, line: string, images: readonly EncodedImageAttachment[], signal: AbortSignal, ): Promise<CommandExecution | undefined>
 ```
 
-Types: [Agent](core.md)
+Types: [Agent](core.md) · [EncodedImageAttachment](attachment.md)
 
-Source: [`packages/interaction/commands/src/index.ts:225`](../../packages/interaction/commands/src/index.ts)
+Source: [`packages/interaction/commands/src/index.ts:250`](../../packages/interaction/commands/src/index.ts)
 
 <a id="commands-events"></a>
 
@@ -183,5 +206,5 @@ A command was registered or unregistered. This is an unfiltered registry notific
 'commands/change'(): void
 ```
 
-Source: [`packages/interaction/commands/src/types.ts:72`](../../packages/interaction/commands/src/types.ts)
+Source: [`packages/interaction/commands/src/types.ts:80`](../../packages/interaction/commands/src/types.ts)
 <!-- END GENERATED cordis-surface -->

docs/subsystems/plan.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 docs/subsystems/plan.md
-plan.md: 4e6eb98e7c7cce295feeed0150984934f1a853e5
-plan.zh.md: f8236e6cbeca841bdab630aa831e844cc68179a0
+plan.md: 1f6863a24aa56773430be904e5a27c27384c9bff
+plan.zh.md: 056bce946b608876ac958f2d33d871e9622c7187

docs/subsystems/plan.md

@@ -83,5 +83,5 @@ set(agent: Agent, active: boolean): 'committed' | 'queued' | 'cancelled' | 'noop
 
 Types: [Agent](core.md)
 
-Source: [`packages/plan/plan-mode/src/index.ts:184`](../../packages/plan/plan-mode/src/index.ts)
+Source: [`packages/plan/plan-mode/src/index.ts:188`](../../packages/plan/plan-mode/src/index.ts)
 <!-- END GENERATED cordis-surface -->

docs/subsystems/plan.zh.md

@@ -83,5 +83,5 @@ set(agent: Agent, active: boolean): 'committed' | 'queued' | 'cancelled' | 'noop
 
 Types: [Agent](core.md)
 
-Source: [`packages/plan/plan-mode/src/index.ts:184`](../../packages/plan/plan-mode/src/index.ts)
+Source: [`packages/plan/plan-mode/src/index.ts:188`](../../packages/plan/plan-mode/src/index.ts)
 <!-- END GENERATED cordis-surface -->

docs/user/guide/providers.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 docs/user/guide/providers.md
-providers.md: 099f434ec4602aa402239e83c708d81fcadd7732
-providers.zh.md: 367c90b525ad628b3cd86b2d22045c25064e88a1
+providers.md: 59682d38c71893c16118639cb2b24f63497a3c13
+providers.zh.md: a9deac5c8ba46950af75b02e631aa83c56a4b72f

docs/user/guide/providers.md

@@ -79,6 +79,42 @@ Every list must name at least one modality except a model's own, where an empty
 
 Both fields state a claim about your endpoint rather than checking it. A model that declares images its endpoint does not serve is not caught here; the provider rejects the request instead.
 
+### Request compatibility
+
+A gateway can hold a working key at a reachable address and still refuse every request. pi-ai decides the shape of a request — which role carries the system prompt, which field caps the output, how a thinking level travels — from the endpoint's URL, and an address it does not recognize is addressed as though it were OpenAI itself. Most OpenAI-compatible gateways refuse at least one thing OpenAI accepts.
+
+Two account for most of it. A model that declares reasoning has its system prompt sent as `role: "developer"`, which many gateways reject outright, and the output cap is sent as `max_completion_tokens`, which a server that only knows `max_tokens` refuses. The form has no field for either; correct them on the route in `$DSH_HOME/settings.yaml`:
+
+```yaml
+llm-pi-ai:
+  providers:
+    my-gateway:
+      apiKeyEnv: GATEWAY_API_KEY
+      api: openai-completions
+      baseURL: https://gateway.example/v1
+      compat:
+        supportsDeveloperRole: false
+        maxTokensField: max_tokens
+      models:
+        - id: my-model
+```
+
+A route's `compat` is the default for its models, and a model's own wins field by field, so one model can be corrected without restating the route:
+
+```yaml
+      models:
+        - id: my-model
+        - id: my-reasoner
+          compat:
+            thinkingFormat: deepseek
+```
+
+What neither sets keeps the installed catalog's value for that model, and what the catalog does not describe falls to pi-ai's detection. Give every switch you name a value: a key left empty (`supportsDeveloperRole:`) is refused rather than ignored, because an empty value would erase what the catalog knows while saying nothing in its place. A name no protocol accepts is refused too, and the message lists the ones that are available.
+
+Each switch belongs to the protocols that declare it, so a switch valid on one `api` may be refused on another — the message names what that protocol does offer. Like `input` above, a switch states a claim about your endpoint rather than checking it: setting one your gateway does not actually need simply sends a different request.
+
+Every switch, its accepted values, and the protocols that take it are listed under `PiAiCompatProfile` in the [generated `dsh-llm-pi-ai` configuration reference](../../config-catalog.md#deepseek-aidsh-llm-pi-ai) — which is derived from the source, so it cannot fall behind what the adapter accepts.
+
 ## Select a model
 
 Configured providers appear in the model picker. Selecting a model also makes it the default for new sessions. A session that has already sent a request retains the model recorded in its own log.
@@ -90,9 +126,12 @@ If a saved default names a provider that was deleted, the composer displays **Se
 - **`MISSING_CREDENTIAL`** — Store the provider key through the Models page or supply the referenced environment variable.
 - **`UNKNOWN_MODEL`** — Select a configured model or add the missing model to the custom provider.
 - **Fetching available models returns 401** — Check the key. Model discovery calls the OpenAI-compatible `GET /models` endpoint; enter models manually for endpoints that do not provide it.
+- **The gateway refuses every request although the key and URL are right** — Its request shape differs from OpenAI's. Start with `compat.supportsDeveloperRole: false` and `compat.maxTokensField: max_tokens` on the route.
+- **Only reasoning models fail** — pi-ai sends their system prompt as the `developer` role, which the gateway rejects. Set `compat.supportsDeveloperRole: false`.
+- **A compat switch is refused as having no value** — A key written with nothing after the colon. Give it a value, or remove the key to keep the installed catalog's.
 - **An image is refused before sending** — The model declares no image modality. Give a custom provider's model `input: [text, image]`; DeepSeek's own chat-completions route is text-only and cannot be configured otherwise.
 - **The provider rejects a request carrying an image** — The model declares images its endpoint does not actually serve. Remove `image` from whichever list granted it — the model's `input`, or the route's `defaultInput` — then start a new session: the attached image stays in the session log, so the same request repeats until the session moves off it.
 
 ## Advanced configuration
 
-The generated [plugin configuration catalog](../../config-catalog.md) lists every supported field and default. The [`dsh-llm-pi-ai`](../../../packages/llm/llm-pi-ai/README.md) and [`dsh-llm-deepseek`](../../../packages/llm/llm-deepseek/README.md) references own direct `settings.yaml` configuration, catalog resolution, reasoning controls, credentials, and adapter errors.
+The generated [plugin configuration catalog](../../config-catalog.md) lists every supported field and default for every plugin; [`dsh-llm-pi-ai`](../../config-catalog.md#deepseek-aidsh-llm-pi-ai) is the provider section this page configures. The [`dsh-llm-pi-ai`](../../../packages/llm/llm-pi-ai/README.md) and [`dsh-llm-deepseek`](../../../packages/llm/llm-deepseek/README.md) references own direct `settings.yaml` configuration, catalog resolution, reasoning controls, credentials, and adapter errors.

docs/user/guide/providers.zh.md

@@ -79,6 +79,42 @@ llm-pi-ai:
 
 这两个字段都是对你端点的断言，而不是对它的检查。声明了端点并不提供的图片能力的模型不会在这里被拦下，改由提供方拒绝该请求。
 
+### 请求兼容性
+
+网关可能持有可用的密钥、地址也通得到，却仍然拒绝每一个请求。pi-ai 依据端点的 URL 决定请求的形状——系统提示词由哪个角色承载、输出上限写在哪个字段、思考级别如何传输——而对于它无法识别的地址，会当作 OpenAI 本身来对待。多数 OpenAI 兼容网关至少会拒绝 OpenAI 所接受的某一样东西。
+
+其中两样占了绝大多数。声明了推理能力的模型，其系统提示词会以 `role: "developer"` 发出，很多网关直接拒绝；输出上限则写作 `max_completion_tokens`，只认 `max_tokens` 的服务端会拒绝。表单里没有这两个字段；请在 `$DSH_HOME/settings.yaml` 的路由上更正：
+
+```yaml
+llm-pi-ai:
+  providers:
+    my-gateway:
+      apiKeyEnv: GATEWAY_API_KEY
+      api: openai-completions
+      baseURL: https://gateway.example/v1
+      compat:
+        supportsDeveloperRole: false
+        maxTokensField: max_tokens
+      models:
+        - id: my-model
+```
+
+路由的 `compat` 是其模型的默认值，模型自身的则逐字段胜出，因此更正某一个模型无需重述整条路由：
+
+```yaml
+      models:
+        - id: my-model
+        - id: my-reasoner
+          compat:
+            thinkingFormat: deepseek
+```
+
+两者都未设置的字段，沿用已安装 catalog 为该模型记录的值；catalog 也未描述的，落到 pi-ai 的检测。凡是写下的开关都要给值：冒号后留空的键（`supportsDeveloperRole:`）会被拒绝而不是被忽略，因为空值会抹掉 catalog 已知的信息，却又没有给出任何替代。任何协议都不接受的名字同样会被拒绝，报错会列出可用的那些。
+
+每个开关归属于声明了它的那些协议，因此在某个 `api` 上合法的开关，在另一个上可能被拒绝——报错会点名该协议实际提供哪些。与上面的 `input` 一样，开关陈述的是关于你的端点的一个断言，而不是对它的检查：设置一个网关其实并不需要的开关，只是发出一个不同的请求而已。
+
+全部开关、各自接受的取值，以及接受它们的协议，都列在[生成的 `dsh-llm-pi-ai` 配置参考](../../config-catalog.md#deepseek-aidsh-llm-pi-ai)的 `PiAiCompatProfile` 之下——该参考派生自源码，因此不会落后于适配器实际接受的内容。
+
 ## 选择模型
 
 已配置的提供方会出现在模型选择器中。选择模型也会将其设为新会话的默认值。已发送过请求的会话会保留自身日志中记录的模型。
@@ -90,9 +126,12 @@ llm-pi-ai:
 - **`MISSING_CREDENTIAL`**：通过模型页存储提供方密钥，或提供被引用的环境变量。
 - **`UNKNOWN_MODEL`**：选择已配置的模型，或向自定义提供方添加缺失的模型。
 - **获取可用模型返回 401**：检查密钥。模型发现会调用 OpenAI 兼容的 `GET /models` 端点；对于不提供该端点的服务，请手动输入模型。
+- **密钥与地址都正确，网关却拒绝每一个请求**：它的请求形状与 OpenAI 不同。先在路由上设 `compat.supportsDeveloperRole: false` 与 `compat.maxTokensField: max_tokens`。
+- **只有推理模型失败**：pi-ai 把它们的系统提示词以 `developer` 角色发出，而网关拒绝该角色。设 `compat.supportsDeveloperRole: false`。
+- **某个 compat 开关因没有值而被拒绝**：冒号后什么都没写。给它一个值，或删掉该键以沿用已安装 catalog 的值。
 - **图片在发送前被拒绝**：该模型未声明图片模态。请给自定义提供方的模型加上 `input: [text, image]`；DeepSeek 自身的 chat-completions 路由是纯文本的，且无法通过配置改变。
 - **提供方拒绝了带图片的请求**：该模型声明了其端点实际并不提供的图片能力。请从授予它图片能力的那个列表中移除 `image`——可能是模型的 `input`，也可能是路由的 `defaultInput`——然后开启新会话：附加的图片会留在会话日志里，因此在会话离开它之前，同一个请求会不断重复。
 
 ## 进阶配置
 
-自动生成的[插件配置目录](../../config-catalog.md)列出所有受支持的字段与默认值。[`dsh-llm-pi-ai`](../../../packages/llm/llm-pi-ai/README.md) 和 [`dsh-llm-deepseek`](../../../packages/llm/llm-deepseek/README.md) 参考文档负责直接 `settings.yaml` 配置、目录解析、推理控制、凭据与适配器错误。
+自动生成的[插件配置目录](../../config-catalog.md)列出每个插件的所有受支持字段与默认值；[`dsh-llm-pi-ai`](../../config-catalog.md#deepseek-aidsh-llm-pi-ai) 就是本页所配置的那个提供方段落。[`dsh-llm-pi-ai`](../../../packages/llm/llm-pi-ai/README.md) 和 [`dsh-llm-deepseek`](../../../packages/llm/llm-deepseek/README.md) 参考文档负责直接 `settings.yaml` 配置、目录解析、推理控制、凭据与适配器错误。

examples/acp-agent/code-mode-image.cordis.snapshot.yml

@@ -13,7 +13,7 @@
         name: '@deepseek-ai/dsh-acp-demo'
         config:
           provider: deepseek-official
-          model: deepseek-v4-flash
+          model: deepseek-v4-flash-vision-exp
           persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
           persistenceCompression: none
           workspaceContext:
@@ -37,6 +37,8 @@
                   name: DeepSeek
                   models:
                     - id: deepseek-v4-flash
-                      inputModalities: [text, image]
+                      inputModalities: [text]
                     - id: deepseek-v4-pro
                       inputModalities: [text]
+                    - id: deepseek-v4-flash-vision-exp
+                      inputModalities: [text, image]

examples/acp-agent/image.cordis.snapshot.yml

@@ -1,9 +1,9 @@
 # Keyless replay for the read-image success scenario. Include patches cannot
 # target entries behind a nested include, so this restates the replay overlay
 # directly over the base cordis.yml (the fs.cordis.snapshot.yml pattern) and
-# re-pins the recorded flash model. The replay catalog declares image input on
-# flash, so the strict read_image gate accepts the route and the tool result
-# carries the durable image block; the live DeepSeek route cannot record this.
+# re-pins the recorded vision model. The replay catalog declares image input,
+# so the strict read_image gate accepts the route and the tool result carries
+# the durable image block.
 - id: base
   name: '@deepseek-ai/cordis-plugin-include'
   config:
@@ -16,7 +16,7 @@
         name: '@deepseek-ai/dsh-acp-demo'
         config:
           provider: deepseek-official
-          model: deepseek-v4-flash
+          model: deepseek-v4-flash-vision-exp
           persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
           persistenceCompression: none
           workspaceContext:
@@ -36,6 +36,8 @@
                   name: DeepSeek
                   models:
                     - id: deepseek-v4-flash
-                      inputModalities: [text, image]
+                      inputModalities: [text]
                     - id: deepseek-v4-pro
                       inputModalities: [text]
+                    - id: deepseek-v4-flash-vision-exp
+                      inputModalities: [text, image]

examples/acp-agent/image.cordis.yml

@@ -3,7 +3,8 @@
 # snapshot harness scopes per run, so the overlay itself carries no paths. The
 # app config is restated to re-pin `deepseek-v4-flash` (base ships pro; the
 # authored fixture and the pinned header class are flash), because a config
-# patch replaces the whole app config.
+# patch replaces the whole app config. Keyless replay supplies its own exact
+# image-capable catalog while the production endpoint remains unavailable.
 - id: base
   name: '@deepseek-ai/cordis-plugin-include'
   config:

examples/acp-agent/tests/acp.snapshot.ts

@@ -16,6 +16,7 @@ import {
 } from '@deepseek-ai/dsh-acp-snapshot'
 import { resolvePwshPath } from '@deepseek-ai/dsh-pwsh-local'
 import { decodeStorageRecord } from '@deepseek-ai/dsh-session'
+import { OFFLOADED_IMAGE_TEXT } from '@deepseek-ai/dsh-llm'
 
 /**
  * The acp-agent example's snapshot suite: the scenario table for
@@ -222,27 +223,26 @@ const SCENARIOS: Scenario[] = [
     posixOnly: true,
   },
   // Authored keyless replays through the assembled app: the replay catalog
-  // declares flash image-capable (success) or text-only (refusal), and the
+  // declares the vision model image-capable and Flash text-only, and the
   // real read_image tool executes against the workspace fixture and the real
-  // attachment store. Both boot the same composed header (the tool registers
-  // with the attachment store, independent of route), so they share one class.
+  // attachment store. The success route selects the vision model while the
+  // refusal route retains text-only Flash, so each pins its exact header.
   {
     name: 'read-image',
     hasModelTurn: true,
     recorded: false,
     pinsHeader: true,
     headerClass: 'image',
-    // The overlay adds no prompt section (read_image carries no guidance), so
-    // the composed system prompt is byte-identical to the default class; only
-    // the tool-schema sidecar is class-specific.
-    systemPromptSource: 'text-turn',
     configPath: IMAGE_CONFIG,
   },
   {
     name: 'read-image-text-route',
     hasModelTurn: true,
     recorded: false,
-    headerClass: 'image',
+    pinsHeader: true,
+    headerClass: 'image-text-route',
+    systemPromptSource: 'text-turn',
+    toolSchemasSource: 'read-image',
     configPath: IMAGE_TEXT_ROUTE_CONFIG,
   },
   // Authored keyless replay of the oversized-image refusal: admission rejects
@@ -688,7 +688,7 @@ defineAcpSnapshotSuite({
   hasPwsh,
 })
 
-it('pins pi-ai image offload in the request sent by the assembled app', async () => {
+it('pins native DeepSeek image offload in the request sent by the assembled app', async () => {
   const requests: Record<string, unknown>[] = []
   const server = createServer((request: IncomingMessage, response: ServerResponse) => {
     let body = ''
@@ -697,13 +697,21 @@ it('pins pi-ai image offload in the request sent by the assembled app', async ()
     request.on('end', () => {
       requests.push(JSON.parse(body) as Record<string, unknown>)
       response.writeHead(200, { 'content-type': 'text/event-stream' })
-      response.end([
-        'data: {"choices":[{"delta":{"role":"assistant","content":""},"index":0,"finish_reason":null}]}',
-        'data: {"choices":[{"delta":{"content":"DONE"},"index":0,"finish_reason":null}]}',
-        'data: {"choices":[{"delta":{},"index":0,"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}',
-        'data: [DONE]',
-        '',
-      ].join('\n\n'))
+      const events = requests.length === 1
+        ? [
+          'data: {"choices":[{"delta":{"tool_calls":[{"index":0,"id":"native-read-image","type":"function","function":{"name":"read_image","arguments":"{\\"file_path\\":\\"red.png\\"}"}}]},"index":0,"finish_reason":null}]}',
+          'data: {"choices":[{"delta":{},"index":0,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}',
+          'data: [DONE]',
+          '',
+        ]
+        : [
+          'data: {"choices":[{"delta":{"role":"assistant","content":""},"index":0,"finish_reason":null}]}',
+          'data: {"choices":[{"delta":{"content":"DONE"},"index":0,"finish_reason":null}]}',
+          'data: {"choices":[{"delta":{},"index":0,"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}',
+          'data: [DONE]',
+          '',
+        ]
+      response.end(events.join('\n\n'))
     })
   })
   await new Promise<void>(resolve => server.listen(0, '127.0.0.1', resolve))
@@ -722,7 +730,7 @@ it('pins pi-ai image offload in the request sent by the assembled app', async ()
           { type: 'image', data: image, mimeType: 'image/png' },
           { type: 'text', text: ' with the newer image ' },
           { type: 'image', data: image, mimeType: 'image/png' },
-          { type: 'text', text: ', then reply with DONE.' },
+          { type: 'text', text: ', then use read_image on red.png and reply with DONE.' },
         ],
       },
     ],
@@ -734,13 +742,14 @@ it('pins pi-ai image offload in the request sent by the assembled app', async ()
       mode: 'record',
       configPath: IMAGE_OFFLOAD_CONFIG,
       fixtureFile: join(SNAPSHOTS_DIR, 'image-offload-request', 'session.jsonl'),
+      workspaceDir: join(SNAPSHOTS_DIR, 'read-image', 'workspace'),
       env: {
         DSH_SNAPSHOT_API_KEY: 'snapshot-key',
-        DSH_SNAPSHOT_BASE_URL: `http://127.0.0.1:${address.port}/v1`,
+        DSH_SNAPSHOT_BASE_URL: `http://127.0.0.1:${address.port}`,
       },
     })
     expect(result.stderr).toBe('')
-    expect(requests).toHaveLength(1)
+    expect(requests).toHaveLength(2)
     const messages = requests[0]?.messages as { content?: unknown }[] | undefined
     const offloaded = messages?.find(message => JSON.stringify(message.content).includes('[image omitted'))
     expect(offloaded?.content).toMatchInlineSnapshot(`
@@ -764,11 +773,62 @@ it('pins pi-ai image offload in the request sent by the assembled app', async ()
           "type": "image_url",
         },
         {
-          "text": ", then reply with DONE.",
+          "text": ", then use read_image on red.png and reply with DONE.",
           "type": "text",
         },
       ]
     `)
+
+    const followup = structuredClone((requests[1]?.messages as unknown[]).slice(1)) as Array<{
+      role?: unknown
+      content?: unknown
+    }>
+    const toolMessage = followup.find(message => message.role === 'tool')
+    if (toolMessage === undefined || typeof toolMessage.content !== 'string') {
+      throw new Error('native read_image request has no tool content')
+    }
+    const cwdSpellings = [...new Set([result.cwd, ...result.cwdAliases].flatMap(cwd => (
+      cwd.startsWith('/private/') ? [cwd, cwd.slice('/private'.length)] : [cwd, `/private${cwd}`]
+    )))]
+    let toolContent = toolMessage.content
+    for (const cwd of cwdSpellings) toolContent = toolContent.replaceAll(cwd, '{{cwd}}')
+    toolMessage.content = toolContent
+    expect(followup).toEqual([
+      {
+        role: 'user',
+        content: `Compare the older image ${OFFLOADED_IMAGE_TEXT} with the newer image ${OFFLOADED_IMAGE_TEXT}, then use read_image on red.png and reply with DONE.`,
+      },
+      {
+        role: 'user',
+        content: 'Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\n'
+          + 'Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\n'
+          + 'Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`).',
+      },
+      {
+        role: 'assistant',
+        content: '',
+        tool_calls: [{
+          id: 'native-read-image',
+          type: 'function',
+          function: { name: 'read_image', arguments: '{"file_path":"red.png"}' },
+        }],
+      },
+      {
+        role: 'tool',
+        tool_call_id: 'native-read-image',
+        content: '<path>{{cwd}}/red.png</path>\n<type>image</type>\n<content>\nimage/png image, 1x1 px, 69 bytes\n</content>',
+      },
+      {
+        role: 'user',
+        content: [
+          { type: 'text', text: 'Attached image(s) from tool result:' },
+          {
+            type: 'image_url',
+            image_url: { url: `data:image/png;base64,${image}` },
+          },
+        ],
+      },
+    ])
   } finally {
     await new Promise<void>(resolve => server.close(() => { resolve() }))
   }

examples/acp-agent/tests/fixtures/image-offload.cordis.yml

@@ -1,5 +1,5 @@
-# Keyless assembled-request snapshot for pi-ai image offload. The local
-# provider endpoint is supplied by the snapshot test; the real attachment
+# Keyless assembled-request snapshot for native DeepSeek image offload. The
+# local provider endpoint is supplied by the snapshot test; the real attachment
 # store and ACP bridge carry two uploaded images into one model request.
 - id: base
   name: '@deepseek-ai/cordis-plugin-include'
@@ -8,12 +8,21 @@
     patches:
       - id: llm-deepseek
         name: '@deepseek-ai/dsh-llm-deepseek'
-        disabled: true
+        config:
+          apiKeyEnv: DSH_SNAPSHOT_API_KEY
+          baseURL: !!js process.env.DSH_SNAPSHOT_BASE_URL
+          thinking: disabled
+          maxRequestImageBytes: 92
+          models:
+            - id: deepseek-v4-flash-vision-exp
+              contextWindow: 32768
+              maxTokens: 1024
+              inputModalities: [text, image]
       - id: acp-agent
         name: '@deepseek-ai/dsh-acp-demo'
         config:
-          provider: snapshot
-          model: vision
+          provider: deepseek-official
+          model: deepseek-v4-flash-vision-exp
           persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions'
           persistenceCompression: none
           workspaceContext:
@@ -25,17 +34,3 @@
       - insert:
           - id: attachment-local
             name: '@deepseek-ai/dsh-attachment-local'
-          - id: llm-pi-ai
-            name: '@deepseek-ai/dsh-llm-pi-ai'
-            config:
-              providers:
-                snapshot:
-                  apiKeyEnv: DSH_SNAPSHOT_API_KEY
-                  api: openai-completions
-                  baseURL: !!js process.env.DSH_SNAPSHOT_BASE_URL
-                  maxRequestImageBytes: 92
-                  models:
-                    - id: vision
-                      contextWindow: 32768
-                      maxTokens: 1024
-                      input: [text, image]

examples/acp-agent/tests/fixtures/subagent-result-diagnostic.ts

@@ -11,7 +11,28 @@ import { SessionId } from '@deepseek-ai/dsh-session'
 export const name = 'subagent-result-diagnostic'
 export const inject = ['subagents']
 
-const DIAGNOSTIC = 'Claude Code unattended decision (mode: dontAsk; request: tool permission; decision: denied): Claude Code denied the request before an interactive prompt'
+const RESULTS = [
+  {
+    id: '00000000-0000-4000-8000-0000000000d1',
+    diagnostic: 'Product subagent failure (product: Claude Code; stage: query-run; category: error_max_budget_usd)',
+    output: [{ type: 'text' as const, text: 'partial assistant text' }],
+  },
+  {
+    id: '00000000-0000-4000-8000-0000000000d2',
+    diagnostic: 'Product subagent failure (product: Claude Code; stage: query-run; category: error_max_budget_usd)',
+    output: [],
+  },
+  {
+    id: '00000000-0000-4000-8000-0000000000d3',
+    diagnostic: 'Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)',
+    output: [{ type: 'text' as const, text: 'partial assistant text' }],
+  },
+  {
+    id: '00000000-0000-4000-8000-0000000000d4',
+    diagnostic: 'Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)',
+    output: [],
+  },
+] as const
 
 class DiagnosticProvider implements SubagentProvider {
   readonly name = 'snapshot-diagnostic'
@@ -24,19 +45,16 @@ class DiagnosticProvider implements SubagentProvider {
       throw new Error('snapshot diagnostic provider start aborted')
     }
     const index = this.starts++
-    if (index > 1) {
-      throw new Error('snapshot diagnostic provider expected exactly two starts')
+    const fixture = RESULTS[index]
+    if (fixture === undefined) {
+      throw new Error('snapshot diagnostic provider expected exactly four starts')
     }
     return {
-      id: SessionId(index === 0
-        ? '00000000-0000-4000-8000-0000000000d1'
-        : '00000000-0000-4000-8000-0000000000d2'),
+      id: SessionId(fixture.id),
       localAgent: undefined,
       result: Promise.resolve({
-        output: index === 0
-          ? [{ type: 'text' as const, text: 'partial assistant text' }]
-          : [],
-        diagnostic: DIAGNOSTIC,
+        output: [...fixture.output],
+        diagnostic: fixture.diagnostic,
         stopReason: 'error' as const,
       }),
       dispose: async () => {},

examples/acp-agent/tests/snapshots/code-mode-read-image/session.jsonl

@@ -6,13 +6,13 @@
 {"type":"user/message","seq":4,"time":1786431644558,"data":{"content":[{"type":"text","text":"Using ONE run_code program, create a one-pixel PNG with Node.js, call read_image on it, then reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"08e67dbb-9432-4fe4-b7da-4483998c0a31"},"surfaceOp":"append"}
 {"type":"user/message","seq":5,"time":1786431644558,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"99b9db8d-e4ec-4ea9-b5e2-1e4c0ff6354b"},"surfaceOp":"append"}
 {"type":"session/title","seq":6,"time":1786431644558,"data":{"title":"Using ONE run_code program, create","messageSeqs":[4],"source":{"kind":"fallback"}}}
-{"type":"request/header","seq":7,"time":1786431644559,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
-{"type":"request/context","seq":8,"time":1786431644560,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
+{"type":"request/header","seq":7,"time":1786431644559,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"request/context","seq":8,"time":1786431644560,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"}}
 {"type":"assistant/chunk","seq":9,"time":1783952000009,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
 {"type":"assistant/chunk","seq":10,"time":1786431644571,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"code-image-call","name":"run_code","arguments":"{\"code\":\"const bytes = [137,80,78,71,13,10,26,10,0,0,0,13,73,72,68,82,0,0,0,1,0,0,0,1,8,2,0,0,0,144,119,83,222,0,0,0,12,73,68,65,84,120,156,99,248,207,192,0,0,3,1,1,0,201,254,146,239,0,0,0,0,73,69,78,68,174,66,96,130];\\nawait tools.bash({ command: \\\"node -e \\\\\\\"require('node:fs').writeFileSync('red.png',Buffer.from([137,80,78,71,13,10,26,10,0,0,0,13,73,72,68,82,0,0,0,1,0,0,0,1,8,2,0,0,0,144,119,83,222,0,0,0,12,73,68,65,84,120,156,99,248,207,192,0,0,3,1,1,0,201,254,146,239,0,0,0,0,73,69,78,68,174,66,96,130]));\\\\\\\"\\\", description: \\\"Create a one pixel PNG\\\" });\\nconst image = await tools.read_image({ file_path: \\\"red.png\\\" });\\nreturn image.path;\",\"description\":\"Create and inspect one image\"}"}}}}
 {"type":"assistant/chunk","seq":11,"time":1786431644572,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
 {"type":"assistant/chunk","seq":12,"time":1786431644572,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
-{"type":"assistant/message","seq":13,"time":1786431644572,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"code-image-call","name":"run_code","arguments":"{\"code\":\"const bytes = [137,80,78,71,13,10,26,10,0,0,0,13,73,72,68,82,0,0,0,1,0,0,0,1,8,2,0,0,0,144,119,83,222,0,0,0,12,73,68,65,84,120,156,99,248,207,192,0,0,3,1,1,0,201,254,146,239,0,0,0,0,73,69,78,68,174,66,96,130];\\nawait tools.bash({ command: \\\"node -e \\\\\\\"require('node:fs').writeFileSync('red.png',Buffer.from([137,80,78,71,13,10,26,10,0,0,0,13,73,72,68,82,0,0,0,1,0,0,0,1,8,2,0,0,0,144,119,83,222,0,0,0,12,73,68,65,84,120,156,99,248,207,192,0,0,3,1,1,0,201,254,146,239,0,0,0,0,73,69,78,68,174,66,96,130]));\\\\\\\"\\\", description: \\\"Create a one pixel PNG\\\" });\\nconst image = await tools.read_image({ file_path: \\\"red.png\\\" });\\nreturn image.path;\",\"description\":\"Create and inspect one image\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"644382c5-5a05-4bda-b8dc-b9195d6a7d8b"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12],"surfaceOp":"append"}
+{"type":"assistant/message","seq":13,"time":1786431644572,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"code-image-call","name":"run_code","arguments":"{\"code\":\"const bytes = [137,80,78,71,13,10,26,10,0,0,0,13,73,72,68,82,0,0,0,1,0,0,0,1,8,2,0,0,0,144,119,83,222,0,0,0,12,73,68,65,84,120,156,99,248,207,192,0,0,3,1,1,0,201,254,146,239,0,0,0,0,73,69,78,68,174,66,96,130];\\nawait tools.bash({ command: \\\"node -e \\\\\\\"require('node:fs').writeFileSync('red.png',Buffer.from([137,80,78,71,13,10,26,10,0,0,0,13,73,72,68,82,0,0,0,1,0,0,0,1,8,2,0,0,0,144,119,83,222,0,0,0,12,73,68,65,84,120,156,99,248,207,192,0,0,3,1,1,0,201,254,146,239,0,0,0,0,73,69,78,68,174,66,96,130]));\\\\\\\"\\\", description: \\\"Create a one pixel PNG\\\" });\\nconst image = await tools.read_image({ file_path: \\\"red.png\\\" });\\nreturn image.path;\",\"description\":\"Create and inspect one image\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"id":"ef352c42-b661-4b71-8c6a-7dbbd0a9f591"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12],"surfaceOp":"append"}
 {"type":"tool/call","seq":14,"time":1786431644573,"data":{"turn":1,"step":1,"callId":"code-image-call","name":"run_code","arguments":"{\"code\":\"const bytes = [137,80,78,71,13,10,26,10,0,0,0,13,73,72,68,82,0,0,0,1,0,0,0,1,8,2,0,0,0,144,119,83,222,0,0,0,12,73,68,65,84,120,156,99,248,207,192,0,0,3,1,1,0,201,254,146,239,0,0,0,0,73,69,78,68,174,66,96,130];\\nawait tools.bash({ command: \\\"node -e \\\\\\\"require('node:fs').writeFileSync('red.png',Buffer.from([137,80,78,71,13,10,26,10,0,0,0,13,73,72,68,82,0,0,0,1,0,0,0,1,8,2,0,0,0,144,119,83,222,0,0,0,12,73,68,65,84,120,156,99,248,207,192,0,0,3,1,1,0,201,254,146,239,0,0,0,0,73,69,78,68,174,66,96,130]));\\\\\\\"\\\", description: \\\"Create a one pixel PNG\\\" });\\nconst image = await tools.read_image({ file_path: \\\"red.png\\\" });\\nreturn image.path;\",\"description\":\"Create and inspect one image\"}"}}
 {"type":"tool/code-dispatch-start","seq":15,"time":1786431644697,"data":{"rootCallId":"code-image-call","parentCallId":"code-image-call","subCallId":"code-image-call:code:1","name":"bash","arguments":{"command":"node -e \"require('node:fs').writeFileSync('red.png',Buffer.from([137,80,78,71,13,10,26,10,0,0,0,13,73,72,68,82,0,0,0,1,0,0,0,1,8,2,0,0,0,144,119,83,222,0,0,0,12,73,68,65,84,120,156,99,248,207,192,0,0,3,1,1,0,201,254,146,239,0,0,0,0,73,69,78,68,174,66,96,130]));\"","description":"Create a one pixel PNG"}}}
 {"type":"tool/code-dispatch","seq":16,"time":1786431644828,"data":{"rootCallId":"code-image-call","parentCallId":"code-image-call","subCallId":"code-image-call:code:1","name":"bash","arguments":{"command":"node -e \"require('node:fs').writeFileSync('red.png',Buffer.from([137,80,78,71,13,10,26,10,0,0,0,13,73,72,68,82,0,0,0,1,0,0,0,1,8,2,0,0,0,144,119,83,222,0,0,0,12,73,68,65,84,120,156,99,248,207,192,0,0,3,1,1,0,201,254,146,239,0,0,0,0,73,69,78,68,174,66,96,130]));\"","description":"Create a one pixel PNG"},"isError":false,"content":[{"type":"text","text":"(no output)"}]}}
@@ -28,6 +28,6 @@
 {"type":"assistant/chunk","seq":26,"time":1786431644889,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
 {"type":"assistant/chunk","seq":27,"time":1786431644890,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
 {"type":"assistant/chunk","seq":28,"time":1786431644890,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
-{"type":"assistant/message","seq":29,"time":1786431644890,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"a6da60ea-d420-432b-ba00-9b99af045110"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28],"surfaceOp":"append"}
+{"type":"assistant/message","seq":29,"time":1786431644890,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"id":"a721cef2-2c49-4336-8d07-5f6cc15f4b67"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28],"surfaceOp":"append"}
 {"type":"step/end","seq":30,"time":1786431644890,"data":{"turn":1,"step":2}}
 {"type":"turn/end","seq":31,"time":1786431644890,"data":{"turn":1,"reason":{"kind":"completed"}}}

examples/acp-agent/tests/snapshots/code-mode-read-image/system-prompt.expected.md

@@ -1,6 +1,6 @@
 You are an AI agent powered by DeepSeek Harness.
 
-You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
+You are a coding assistant powered by the deepseek-v4-flash-vision-exp model. Your working directory is {{cwd}}.
 
 Verify your work by running the code or tests. Keep answers brief and factual.
 

examples/acp-agent/tests/snapshots/inline-image-prompt/session.jsonl

@@ -6,12 +6,12 @@
 {"type":"user/message","seq":4,"time":1783952000003,"data":{"content":[{"type":"text","text":"Inspect this image, then reply with exactly "},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","width":1,"height":1,"bytes":69}},{"type":"text","text":"the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"0c0c0c0c-0000-4000-8000-000000000001"},"surfaceOp":"append"}
 {"type":"user/message","seq":5,"time":1783952000004,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"0c0c0c0c-0000-4000-8000-000000000002"},"surfaceOp":"append"}
 {"type":"session/title","seq":6,"time":1783952000004,"data":{"title":"Inspect this image, then reply","messageSeqs":[4],"source":{"kind":"fallback"}}}
-{"type":"request/header","seq":7,"time":1783952000005,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
-{"type":"request/context","seq":8,"time":1783952000005,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
+{"type":"request/header","seq":7,"time":1783952000005,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"request/context","seq":8,"time":1783952000005,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"}}
 {"type":"assistant/chunk","seq":9,"time":1783952000006,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
 {"type":"assistant/chunk","seq":10,"time":1783952000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
 {"type":"assistant/chunk","seq":11,"time":1783952000008,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
 {"type":"assistant/chunk","seq":12,"time":1783952000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
-{"type":"assistant/message","seq":13,"time":1783952000009,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"0c0c0c0c-0000-4000-8000-000000000003"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12],"surfaceOp":"append"}
+{"type":"assistant/message","seq":13,"time":1783952000009,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"id":"e58e49ab-9c34-4ba0-9276-9429b32c5ea0"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12],"surfaceOp":"append"}
 {"type":"step/end","seq":14,"time":1783952000010,"data":{"turn":1,"step":1}}
 {"type":"turn/end","seq":15,"time":1783952000010,"data":{"turn":1,"reason":{"kind":"completed"}}}

examples/acp-agent/tests/snapshots/product-subagent-result-diagnostic/input.json

@@ -2,6 +2,6 @@
   "steps": [
     { "op": "initialize" },
     { "op": "newSession" },
-    { "op": "prompt", "text": "Use subagent_codex in the foreground exactly once; its result will fail with a diagnostic and partial output. Then use subagent_codex in the background exactly once and collect subagent-1 with job_output using wait true. After observing both failures, reply with exactly PARENT_OBSERVED_DIAGNOSTICS. Do not call any other tools." }
+    { "op": "prompt", "text": "Observe four diagnostic failures with subagent_codex. First call it in the foreground for the Claude Code diagnostic, then in the background for the same Claude Code diagnostic and collect subagent-1 with job_output using wait true. Next call it in the foreground for the Codex diagnostic, then in the background for the same Codex diagnostic and collect subagent-2 with job_output using wait true. After all four failures, reply with exactly PARENT_OBSERVED_DIAGNOSTICS. Do not call any other tools." }
   ]
 }

examples/acp-agent/tests/snapshots/product-subagent-result-diagnostic/replay.override.json

@@ -3,8 +3,8 @@
     "kind": "chunks",
     "chunks": [
       { "type": "block-start", "index": 0, "blockType": "tool-call" },
-      { "type": "tool-call-delta", "index": 0, "id": "call_diagnostic_foreground", "name": "subagent_codex", "argumentsDelta": "{\"description\":\"Observe foreground diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":false}" },
-      { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_diagnostic_foreground", "name": "subagent_codex", "arguments": "{\"description\":\"Observe foreground diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":false}" } },
+      { "type": "tool-call-delta", "index": 0, "id": "call_claude_foreground", "name": "subagent_codex", "argumentsDelta": "{\"description\":\"Observe Claude foreground diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":false}" },
+      { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_claude_foreground", "name": "subagent_codex", "arguments": "{\"description\":\"Observe Claude foreground diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":false}" } },
       { "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
       { "type": "finish", "reason": { "kind": "tool-calls" } }
     ]
@@ -13,8 +13,8 @@
     "kind": "chunks",
     "chunks": [
       { "type": "block-start", "index": 0, "blockType": "tool-call" },
-      { "type": "tool-call-delta", "index": 0, "id": "call_diagnostic_background", "name": "subagent_codex", "argumentsDelta": "{\"description\":\"Observe background diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":true}" },
-      { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_diagnostic_background", "name": "subagent_codex", "arguments": "{\"description\":\"Observe background diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":true}" } },
+      { "type": "tool-call-delta", "index": 0, "id": "call_claude_background", "name": "subagent_codex", "argumentsDelta": "{\"description\":\"Observe Claude background diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":true}" },
+      { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_claude_background", "name": "subagent_codex", "arguments": "{\"description\":\"Observe Claude background diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":true}" } },
       { "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
       { "type": "finish", "reason": { "kind": "tool-calls" } }
     ]
@@ -23,8 +23,38 @@
     "kind": "chunks",
     "chunks": [
       { "type": "block-start", "index": 0, "blockType": "tool-call" },
-      { "type": "tool-call-delta", "index": 0, "id": "call_diagnostic_output", "name": "job_output", "argumentsDelta": "{\"job_id\":\"subagent-1\",\"wait\":true}" },
-      { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_diagnostic_output", "name": "job_output", "arguments": "{\"job_id\":\"subagent-1\",\"wait\":true}" } },
+      { "type": "tool-call-delta", "index": 0, "id": "call_claude_output", "name": "job_output", "argumentsDelta": "{\"job_id\":\"subagent-1\",\"wait\":true}" },
+      { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_claude_output", "name": "job_output", "arguments": "{\"job_id\":\"subagent-1\",\"wait\":true}" } },
+      { "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
+      { "type": "finish", "reason": { "kind": "tool-calls" } }
+    ]
+  },
+  {
+    "kind": "chunks",
+    "chunks": [
+      { "type": "block-start", "index": 0, "blockType": "tool-call" },
+      { "type": "tool-call-delta", "index": 0, "id": "call_codex_foreground", "name": "subagent_codex", "argumentsDelta": "{\"description\":\"Observe Codex foreground diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":false}" },
+      { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_codex_foreground", "name": "subagent_codex", "arguments": "{\"description\":\"Observe Codex foreground diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":false}" } },
+      { "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
+      { "type": "finish", "reason": { "kind": "tool-calls" } }
+    ]
+  },
+  {
+    "kind": "chunks",
+    "chunks": [
+      { "type": "block-start", "index": 0, "blockType": "tool-call" },
+      { "type": "tool-call-delta", "index": 0, "id": "call_codex_background", "name": "subagent_codex", "argumentsDelta": "{\"description\":\"Observe Codex background diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":true}" },
+      { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_codex_background", "name": "subagent_codex", "arguments": "{\"description\":\"Observe Codex background diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":true}" } },
+      { "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
+      { "type": "finish", "reason": { "kind": "tool-calls" } }
+    ]
+  },
+  {
+    "kind": "chunks",
+    "chunks": [
+      { "type": "block-start", "index": 0, "blockType": "tool-call" },
+      { "type": "tool-call-delta", "index": 0, "id": "call_codex_output", "name": "job_output", "argumentsDelta": "{\"job_id\":\"subagent-2\",\"wait\":true}" },
+      { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_codex_output", "name": "job_output", "arguments": "{\"job_id\":\"subagent-2\",\"wait\":true}" } },
       { "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 5 } },
       { "type": "finish", "reason": { "kind": "tool-calls" } }
     ]

examples/acp-agent/tests/snapshots/product-subagent-result-diagnostic/session.jsonl

@@ -1,51 +1,84 @@
 {"type":"session","version":0,"id":"539aa64c-7f37-40ff-abd8-ed45b717be1b","createdAt":1783600629539,"cwd":"{{cwd}}","delegationDepth":0}
-{"type":"agent/inbox/spliced","seq":0,"time":1785498761270,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Use subagent_codex in the foreground exactly once; its result will fail with a diagnostic and partial output. Then use subagent_codex in the background exactly once and collect subagent-1 with job_output using wait true. After observing both failures, reply with exactly PARENT_OBSERVED_DIAGNOSTICS. Do not call any other tools."}],"source":{"kind":"user"},"role":"user","id":"b8004c02-9892-40a7-b7a4-28f04879082c"}]}}
+{"type":"agent/inbox/spliced","seq":0,"time":1785498761270,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Observe four diagnostic failures with subagent_codex. First call it in the foreground for the Claude Code diagnostic, then in the background for the same Claude Code diagnostic and collect subagent-1 with job_output using wait true. Next call it in the foreground for the Codex diagnostic, then in the background for the same Codex diagnostic and collect subagent-2 with job_output using wait true. After all four failures, reply with exactly PARENT_OBSERVED_DIAGNOSTICS. Do not call any other tools."}],"source":{"kind":"user"},"role":"user","id":"eb9f20a0-9eac-480c-9904-71a1ffbb742a"}]}}
 {"type":"turn/start","seq":1,"time":1785821359466,"data":{"turn":1}}
 {"type":"agent/inbox/spliced","seq":2,"time":1785821359466,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}}
 {"type":"step/start","seq":3,"time":1783600629542,"data":{"turn":1,"step":1}}
-{"type":"user/message","seq":4,"time":1785498761313,"data":{"content":[{"type":"text","text":"Use subagent_codex in the foreground exactly once; its result will fail with a diagnostic and partial output. Then use subagent_codex in the background exactly once and collect subagent-1 with job_output using wait true. After observing both failures, reply with exactly PARENT_OBSERVED_DIAGNOSTICS. Do not call any other tools."}],"source":{"kind":"user"},"role":"user","id":"b8004c02-9892-40a7-b7a4-28f04879082c"},"surfaceOp":"append"}
+{"type":"user/message","seq":4,"time":1785498761313,"data":{"content":[{"type":"text","text":"Observe four diagnostic failures with subagent_codex. First call it in the foreground for the Claude Code diagnostic, then in the background for the same Claude Code diagnostic and collect subagent-1 with job_output using wait true. Next call it in the foreground for the Codex diagnostic, then in the background for the same Codex diagnostic and collect subagent-2 with job_output using wait true. After all four failures, reply with exactly PARENT_OBSERVED_DIAGNOSTICS. Do not call any other tools."}],"source":{"kind":"user"},"role":"user","id":"eb9f20a0-9eac-480c-9904-71a1ffbb742a"},"surfaceOp":"append"}
 {"type":"user/message","seq":5,"time":1785730415287,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"4b8d9730-0b7b-4e14-8a30-3d852f808f0e"},"surfaceOp":"append"}
-{"type":"session/title","seq":6,"time":1785730415287,"data":{"title":"Use subagent_codex in the foreground","messageSeqs":[4],"source":{"kind":"fallback"}}}
+{"type":"session/title","seq":6,"time":1785730415287,"data":{"title":"Observe four diagnostic failures with","messageSeqs":[4],"source":{"kind":"fallback"}}}
 {"type":"request/header","seq":7,"time":1785498761318,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-pro"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/context","seq":8,"time":1785730415288,"data":{"provider":"deepseek-official","model":"deepseek-v4-pro"}}
 {"type":"assistant/chunk","seq":9,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
-{"type":"assistant/chunk","seq":10,"time":1783600630852,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_diagnostic_foreground","name":"subagent_codex","argumentsDelta":"{\"description\":\"Observe foreground diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":false}"}}}
-{"type":"assistant/chunk","seq":11,"time":1783600630852,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_diagnostic_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe foreground diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":false}"}}}}
+{"type":"assistant/chunk","seq":10,"time":1783600630852,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_claude_foreground","name":"subagent_codex","argumentsDelta":"{\"description\":\"Observe Claude foreground diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":false}"}}}
+{"type":"assistant/chunk","seq":11,"time":1783600630852,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_claude_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe Claude foreground diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":false}"}}}}
 {"type":"assistant/chunk","seq":12,"time":1783600630852,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
 {"type":"assistant/chunk","seq":13,"time":1783600630852,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
-{"type":"assistant/message","seq":14,"time":1786781990608,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_diagnostic_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe foreground diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":false}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"92e33995-2f02-4ad5-aec1-9df82cf4d583"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[9,10,11,12,13],"surfaceOp":"append"}
-{"type":"tool/call","seq":15,"time":1786781990608,"data":{"turn":1,"step":1,"callId":"call_diagnostic_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe foreground diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":false}"}}
-{"type":"tool/result","seq":16,"time":1786781990613,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_diagnostic_foreground"},"content":[{"type":"tool-result","toolCallId":"call_diagnostic_foreground","content":[{"type":"text","text":"Error: subagent run failed\nDiagnostic: Claude Code unattended decision (mode: dontAsk; request: tool permission; decision: denied): Claude Code denied the request before an interactive prompt\nPartial output before the run ended:\npartial assistant text"}],"isError":true}],"role":"user","id":"4e84e7b3-40c1-488e-b119-45e8bd7ce448"}},"sourceEventSeqs":[15],"surfaceOp":"append"}
+{"type":"assistant/message","seq":14,"time":1786781990608,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_claude_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe Claude foreground diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":false}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"3cc2d0b5-97a5-4685-af60-ed7f7db8f69a"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[9,10,11,12,13],"surfaceOp":"append"}
+{"type":"tool/call","seq":15,"time":1786781990608,"data":{"turn":1,"step":1,"callId":"call_claude_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe Claude foreground diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":false}"}}
+{"type":"tool/result","seq":16,"time":1786781990613,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"call_claude_foreground"},"content":[{"type":"tool-result","toolCallId":"call_claude_foreground","content":[{"type":"text","text":"Error: subagent run failed\nDiagnostic: Product subagent failure (product: Claude Code; stage: query-run; category: error_max_budget_usd)\nPartial output before the run ended:\npartial assistant text"}],"isError":true}],"role":"user","id":"8743817e-158e-45cb-88d9-a695b2653eca"}},"sourceEventSeqs":[15],"surfaceOp":"append"}
 {"type":"step/end","seq":17,"time":1786781990613,"data":{"turn":1,"step":1}}
 {"type":"step/start","seq":18,"time":1786781990618,"data":{"turn":1,"step":2}}
 {"type":"assistant/chunk","seq":19,"time":1783600630926,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
-{"type":"assistant/chunk","seq":20,"time":1783600630926,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_diagnostic_background","name":"subagent_codex","argumentsDelta":"{\"description\":\"Observe background diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":true}"}}}
-{"type":"assistant/chunk","seq":21,"time":1783600630926,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_diagnostic_background","name":"subagent_codex","arguments":"{\"description\":\"Observe background diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":true}"}}}}
+{"type":"assistant/chunk","seq":20,"time":1783600630926,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"call_claude_background","name":"subagent_codex","argumentsDelta":"{\"description\":\"Observe Claude background diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":true}"}}}
+{"type":"assistant/chunk","seq":21,"time":1783600630926,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_claude_background","name":"subagent_codex","arguments":"{\"description\":\"Observe Claude background diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":true}"}}}}
 {"type":"assistant/chunk","seq":22,"time":1783600630944,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
 {"type":"assistant/chunk","seq":23,"time":1783600630944,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
-{"type":"assistant/message","seq":24,"time":1786781990622,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_diagnostic_background","name":"subagent_codex","arguments":"{\"description\":\"Observe background diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"2fb444e2-7a52-4963-988e-b1ecbc3744d5"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[19,20,21,22,23],"surfaceOp":"append"}
-{"type":"tool/call","seq":25,"time":1786781990623,"data":{"turn":1,"step":2,"callId":"call_diagnostic_background","name":"subagent_codex","arguments":"{\"description\":\"Observe background diagnostic\",\"prompt\":\"Return the diagnostic failure.\",\"run_in_background\":true}"}}
-{"type":"agent/inbox/spliced","seq":26,"time":1786781990627,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"background job subagent-1 (subagent: Observe background diagnostic) finished [status: failed, error; diagnostic: Claude Code unattended decision (mode: dontAsk; request: tool permission; decision: denied): Claude Code denied the request before an interactive prompt]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe background diagnostic [status: failed, error; diagnostic: Claude Code unattended decision (mode: dontA…"},"role":"user","id":"de606545-e637-4d9a-ba17-4c722a7331fd"}]}}
-{"type":"tool/result","seq":27,"time":1786781990627,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"call_diagnostic_background"},"content":[{"type":"tool-result","toolCallId":"call_diagnostic_background","content":[{"type":"text","text":"started background subagent job subagent-1"}],"isError":false}],"role":"user","id":"3377f724-b4a7-4ce1-bed7-774f174917d6"}},"sourceEventSeqs":[25],"surfaceOp":"append"}
+{"type":"assistant/message","seq":24,"time":1786781990622,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_claude_background","name":"subagent_codex","arguments":"{\"description\":\"Observe Claude background diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"b504312a-1dc5-46ce-87a5-12a5817511b9"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[19,20,21,22,23],"surfaceOp":"append"}
+{"type":"tool/call","seq":25,"time":1786781990623,"data":{"turn":1,"step":2,"callId":"call_claude_background","name":"subagent_codex","arguments":"{\"description\":\"Observe Claude background diagnostic\",\"prompt\":\"Return the Claude diagnostic failure.\",\"run_in_background\":true}"}}
+{"type":"agent/inbox/spliced","seq":26,"time":1786781990627,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"background job subagent-1 (subagent: Observe Claude background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Claude Code; stage: query-run; category: error_max_budget_usd)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Claude background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cl…"},"role":"user","id":"0fdb9ddf-1657-4455-9941-e6a9daa8ae4a"}]}}
+{"type":"tool/result","seq":27,"time":1786781990627,"data":{"turn":1,"step":2,"message":{"source":{"kind":"tool","callId":"call_claude_background"},"content":[{"type":"tool-result","toolCallId":"call_claude_background","content":[{"type":"text","text":"started background subagent job subagent-1"}],"isError":false}],"role":"user","id":"fe60646b-0551-4703-aa03-c8cb5460d356"}},"sourceEventSeqs":[25],"surfaceOp":"append"}
 {"type":"step/end","seq":28,"time":1786781990627,"data":{"turn":1,"step":2}}
 {"type":"agent/inbox/spliced","seq":29,"time":1786781990627,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}}
 {"type":"step/start","seq":30,"time":1786781990632,"data":{"turn":1,"step":3}}
-{"type":"user/message","seq":31,"time":1786781990632,"data":{"content":[{"type":"text","text":"background job subagent-1 (subagent: Observe background diagnostic) finished [status: failed, error; diagnostic: Claude Code unattended decision (mode: dontAsk; request: tool permission; decision: denied): Claude Code denied the request before an interactive prompt]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe background diagnostic [status: failed, error; diagnostic: Claude Code unattended decision (mode: dontA…"},"role":"user","id":"de606545-e637-4d9a-ba17-4c722a7331fd"},"surfaceOp":"append"}
+{"type":"user/message","seq":31,"time":1786781990632,"data":{"content":[{"type":"text","text":"background job subagent-1 (subagent: Observe Claude background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Claude Code; stage: query-run; category: error_max_budget_usd)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Claude background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cl…"},"role":"user","id":"0fdb9ddf-1657-4455-9941-e6a9daa8ae4a"},"surfaceOp":"append"}
 {"type":"assistant/chunk","seq":32,"time":1783600631009,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
-{"type":"assistant/chunk","seq":33,"time":1783600631009,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"call_diagnostic_output","name":"job_output","argumentsDelta":"{\"job_id\":\"subagent-1\",\"wait\":true}"}}}
-{"type":"assistant/chunk","seq":34,"time":1783600631009,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_diagnostic_output","name":"job_output","arguments":"{\"job_id\":\"subagent-1\",\"wait\":true}"}}}}
+{"type":"assistant/chunk","seq":33,"time":1783600631009,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"call_claude_output","name":"job_output","argumentsDelta":"{\"job_id\":\"subagent-1\",\"wait\":true}"}}}
+{"type":"assistant/chunk","seq":34,"time":1783600631009,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_claude_output","name":"job_output","arguments":"{\"job_id\":\"subagent-1\",\"wait\":true}"}}}}
 {"type":"assistant/chunk","seq":35,"time":1785498761338,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
 {"type":"assistant/chunk","seq":36,"time":1785730415297,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
-{"type":"assistant/message","seq":37,"time":1785730415298,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_diagnostic_output","name":"job_output","arguments":"{\"job_id\":\"subagent-1\",\"wait\":true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"f43f988b-bc08-4811-8671-8edc0613f0d0"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[32,33,34,35,36],"surfaceOp":"append"}
-{"type":"tool/call","seq":38,"time":1786781990636,"data":{"turn":1,"step":3,"callId":"call_diagnostic_output","name":"job_output","arguments":"{\"job_id\":\"subagent-1\",\"wait\":true}"}}
-{"type":"tool/result","seq":39,"time":1786781990640,"data":{"turn":1,"step":3,"message":{"source":{"kind":"tool","callId":"call_diagnostic_output"},"content":[{"type":"tool-result","toolCallId":"call_diagnostic_output","content":[{"type":"text","text":"(no new output)\n[status: failed, error; diagnostic: Claude Code unattended decision (mode: dontAsk; request: tool permission; decision: denied): Claude Code denied the request before an interactive prompt]"}],"isError":false}],"role":"user","id":"6785120f-ae46-48d0-9f3f-d6cd1e6fc5d7"}},"sourceEventSeqs":[38],"surfaceOp":"append"}
+{"type":"assistant/message","seq":37,"time":1785730415298,"data":{"turn":1,"step":3,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_claude_output","name":"job_output","arguments":"{\"job_id\":\"subagent-1\",\"wait\":true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"c48a520a-74ed-42ee-9d93-ee59899975b0"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[32,33,34,35,36],"surfaceOp":"append"}
+{"type":"tool/call","seq":38,"time":1786781990636,"data":{"turn":1,"step":3,"callId":"call_claude_output","name":"job_output","arguments":"{\"job_id\":\"subagent-1\",\"wait\":true}"}}
+{"type":"tool/result","seq":39,"time":1786781990640,"data":{"turn":1,"step":3,"message":{"source":{"kind":"tool","callId":"call_claude_output"},"content":[{"type":"tool-result","toolCallId":"call_claude_output","content":[{"type":"text","text":"(no new output)\n[status: failed, error; diagnostic: Product subagent failure (product: Claude Code; stage: query-run; category: error_max_budget_usd)]"}],"isError":false}],"role":"user","id":"45bc0705-7243-4173-a119-4c0655af8dc1"}},"sourceEventSeqs":[38],"surfaceOp":"append"}
 {"type":"step/end","seq":40,"time":1786781990640,"data":{"turn":1,"step":3}}
 {"type":"step/start","seq":41,"time":1786781990645,"data":{"turn":1,"step":4}}
-{"type":"assistant/chunk","seq":42,"time":1786781990649,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
-{"type":"assistant/chunk","seq":43,"time":1786781990649,"data":{"turn":1,"step":4,"chunk":{"type":"text-delta","index":0,"text":"PARENT_OBSERVED_DIAGNOSTICS"}}}
-{"type":"assistant/chunk","seq":44,"time":1786781990649,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"PARENT_OBSERVED_DIAGNOSTICS"}}}}
-{"type":"assistant/chunk","seq":45,"time":1786781990649,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
-{"type":"assistant/chunk","seq":46,"time":1786781990649,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
-{"type":"assistant/message","seq":47,"time":1786781990649,"data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"text","text":"PARENT_OBSERVED_DIAGNOSTICS"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"49b868e8-2608-47e0-aaf8-b308ffe8194d"},"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[42,43,44,45,46],"surfaceOp":"append"}
-{"type":"step/end","seq":48,"time":1786781990650,"data":{"turn":1,"step":4}}
-{"type":"turn/end","seq":49,"time":1786781990650,"data":{"turn":1,"reason":{"kind":"completed"}}}
+{"type":"assistant/chunk","seq":42,"time":1786781990649,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":43,"time":1786781990649,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"call_codex_foreground","name":"subagent_codex","argumentsDelta":"{\"description\":\"Observe Codex foreground diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":false}"}}}
+{"type":"assistant/chunk","seq":44,"time":1786781990649,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_codex_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex foreground diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":false}"}}}}
+{"type":"assistant/chunk","seq":45,"time":1786781990649,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
+{"type":"assistant/chunk","seq":46,"time":1786781990649,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":47,"time":1786781990649,"data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_codex_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex foreground diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":false}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"89ab3728-fc3f-4825-97e5-383d46568d8c"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[42,43,44,45,46],"surfaceOp":"append"}
+{"type":"tool/call","seq":48,"time":1786994591759,"data":{"turn":1,"step":4,"callId":"call_codex_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex foreground diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":false}"}}
+{"type":"tool/result","seq":49,"time":1786994591762,"data":{"turn":1,"step":4,"message":{"source":{"kind":"tool","callId":"call_codex_foreground"},"content":[{"type":"tool-result","toolCallId":"call_codex_foreground","content":[{"type":"text","text":"Error: subagent run failed\nDiagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)\nPartial output before the run ended:\npartial assistant text"}],"isError":true}],"role":"user","id":"0a8fd87c-eacb-457b-a5ad-29dd88f599aa"}},"sourceEventSeqs":[48],"surfaceOp":"append"}
+{"type":"step/end","seq":50,"time":1786994591762,"data":{"turn":1,"step":4}}
+{"type":"step/start","seq":51,"time":1786994591767,"data":{"turn":1,"step":5}}
+{"type":"assistant/chunk","seq":52,"time":1786994591771,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":53,"time":1786994591771,"data":{"turn":1,"step":5,"chunk":{"type":"tool-call-delta","index":0,"id":"call_codex_background","name":"subagent_codex","argumentsDelta":"{\"description\":\"Observe Codex background diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":true}"}}}
+{"type":"assistant/chunk","seq":54,"time":1786994591771,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_codex_background","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex background diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":true}"}}}}
+{"type":"assistant/chunk","seq":55,"time":1786994591771,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
+{"type":"assistant/chunk","seq":56,"time":1786994591771,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":57,"time":1786994591771,"data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_codex_background","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex background diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"996da601-acb8-49c9-8dd7-e60a88a8f1a2"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[52,53,54,55,56],"surfaceOp":"append"}
+{"type":"tool/call","seq":58,"time":1786994591772,"data":{"turn":1,"step":5,"callId":"call_codex_background","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex background diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":true}"}}
+{"type":"agent/inbox/spliced","seq":59,"time":1786994591775,"data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"background job subagent-2 (subagent: Observe Codex background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Codex background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cod…"},"role":"user","id":"5f1d4517-50d4-48ef-8acc-8f9361ecb185"}]}}
+{"type":"tool/result","seq":60,"time":1786994591775,"data":{"turn":1,"step":5,"message":{"source":{"kind":"tool","callId":"call_codex_background"},"content":[{"type":"tool-result","toolCallId":"call_codex_background","content":[{"type":"text","text":"started background subagent job subagent-2"}],"isError":false}],"role":"user","id":"a8ba8362-275b-4bca-8b88-d1ef84d325a3"}},"sourceEventSeqs":[58],"surfaceOp":"append"}
+{"type":"step/end","seq":61,"time":1786994591776,"data":{"turn":1,"step":5}}
+{"type":"agent/inbox/spliced","seq":62,"time":1786994591776,"data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}}
+{"type":"step/start","seq":63,"time":1786994591781,"data":{"turn":1,"step":6}}
+{"type":"user/message","seq":64,"time":1786994591781,"data":{"content":[{"type":"text","text":"background job subagent-2 (subagent: Observe Codex background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Codex background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cod…"},"role":"user","id":"5f1d4517-50d4-48ef-8acc-8f9361ecb185"},"surfaceOp":"append"}
+{"type":"assistant/chunk","seq":65,"time":1786994591788,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":66,"time":1786994591788,"data":{"turn":1,"step":6,"chunk":{"type":"tool-call-delta","index":0,"id":"call_codex_output","name":"job_output","argumentsDelta":"{\"job_id\":\"subagent-2\",\"wait\":true}"}}}
+{"type":"assistant/chunk","seq":67,"time":1786994591788,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_codex_output","name":"job_output","arguments":"{\"job_id\":\"subagent-2\",\"wait\":true}"}}}}
+{"type":"assistant/chunk","seq":68,"time":1786994591789,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
+{"type":"assistant/chunk","seq":69,"time":1786994591789,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":70,"time":1786994591789,"data":{"turn":1,"step":6,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_codex_output","name":"job_output","arguments":"{\"job_id\":\"subagent-2\",\"wait\":true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"cfc1726c-5d9e-486a-aa0f-057219e16dfd"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[65,66,67,68,69],"surfaceOp":"append"}
+{"type":"tool/call","seq":71,"time":1786994591789,"data":{"turn":1,"step":6,"callId":"call_codex_output","name":"job_output","arguments":"{\"job_id\":\"subagent-2\",\"wait\":true}"}}
+{"type":"tool/result","seq":72,"time":1786994591797,"data":{"turn":1,"step":6,"message":{"source":{"kind":"tool","callId":"call_codex_output"},"content":[{"type":"tool-result","toolCallId":"call_codex_output","content":[{"type":"text","text":"(no new output)\n[status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)]"}],"isError":false}],"role":"user","id":"9671e5ee-f443-4548-8fd2-b0b76f00b629"}},"sourceEventSeqs":[71],"surfaceOp":"append"}
+{"type":"step/end","seq":73,"time":1786994591797,"data":{"turn":1,"step":6}}
+{"type":"step/start","seq":74,"time":1786994591802,"data":{"turn":1,"step":7}}
+{"type":"assistant/chunk","seq":75,"time":1786994591806,"data":{"turn":1,"step":7,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
+{"type":"assistant/chunk","seq":76,"time":1786994591806,"data":{"turn":1,"step":7,"chunk":{"type":"text-delta","index":0,"text":"PARENT_OBSERVED_DIAGNOSTICS"}}}
+{"type":"assistant/chunk","seq":77,"time":1786994591806,"data":{"turn":1,"step":7,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"PARENT_OBSERVED_DIAGNOSTICS"}}}}
+{"type":"assistant/chunk","seq":78,"time":1786994591806,"data":{"turn":1,"step":7,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":2}}}}
+{"type":"assistant/chunk","seq":79,"time":1786994591806,"data":{"turn":1,"step":7,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
+{"type":"assistant/message","seq":80,"time":1786994591806,"data":{"turn":1,"step":7,"message":{"role":"assistant","content":[{"type":"text","text":"PARENT_OBSERVED_DIAGNOSTICS"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"49b868e8-2608-47e0-aaf8-b308ffe8194d"},"usage":{"inputTokens":10,"outputTokens":2}},"sourceEventSeqs":[75,76,77,78,79],"surfaceOp":"append"}
+{"type":"step/end","seq":81,"time":1786994591806,"data":{"turn":1,"step":7}}
+{"type":"turn/end","seq":82,"time":1786994591807,"data":{"turn":1,"reason":{"kind":"completed"}}}

examples/acp-agent/tests/snapshots/read-image-dimension/session.jsonl

@@ -6,13 +6,13 @@
 {"type":"user/message","seq":4,"time":1783951000003,"data":{"content":[{"type":"text","text":"Use read_image on wide.png in the current directory. If the tool refuses because the image is too large, reply with exactly the single word TOOLARGE."}],"source":{"kind":"user"},"role":"user","id":"0a0a0a0a-0000-4000-8000-000000000001"},"surfaceOp":"append"}
 {"type":"user/message","seq":5,"time":1783951000004,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"11a08f07-014a-408b-bfc5-634770ce7179"},"surfaceOp":"append"}
 {"type":"session/title","seq":6,"time":1783951000004,"data":{"title":"Use read_image on wide.png in","messageSeqs":[4],"source":{"kind":"fallback"}}}
-{"type":"request/header","seq":7,"time":1783951000004,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
-{"type":"request/context","seq":8,"time":1783951000005,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
+{"type":"request/header","seq":7,"time":1783951000004,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"request/context","seq":8,"time":1783951000005,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"}}
 {"type":"assistant/chunk","seq":9,"time":1783951000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
 {"type":"assistant/chunk","seq":10,"time":1783951000008,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"read-image-dimension","name":"read_image","arguments":"{\"file_path\":\"wide.png\"}"}}}}
 {"type":"assistant/chunk","seq":11,"time":1783951000008,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
 {"type":"assistant/chunk","seq":12,"time":1783951000008,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
-{"type":"assistant/message","seq":13,"time":1783951000009,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"read-image-dimension","name":"read_image","arguments":"{\"file_path\":\"wide.png\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"9676ac40-f7a8-4a7b-9326-a45fef18f11e"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12],"surfaceOp":"append"}
+{"type":"assistant/message","seq":13,"time":1783951000009,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"read-image-dimension","name":"read_image","arguments":"{\"file_path\":\"wide.png\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"id":"a25d70ac-2bd6-4e44-9121-ed74975ee229"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12],"surfaceOp":"append"}
 {"type":"tool/call","seq":14,"time":1783951000009,"data":{"turn":1,"step":1,"callId":"read-image-dimension","name":"read_image","arguments":"{\"file_path\":\"wide.png\"}"}}
 {"type":"tool/result","seq":15,"time":1783951000014,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"read-image-dimension"},"content":[{"type":"tool-result","toolCallId":"read-image-dimension","content":[{"type":"text","text":"Error: cannot read \"{{cwd}}/wide.png\": at least one image side exceeds the 2000px limit; downscale the image and read the smaller copy"}],"isError":true}],"role":"user","id":"ee31751e-df5a-458e-8497-8113cf6107ef"}},"sourceEventSeqs":[14],"surfaceOp":"append"}
 {"type":"step/end","seq":16,"time":1783951000014,"data":{"turn":1,"step":1}}
@@ -21,6 +21,6 @@
 {"type":"assistant/chunk","seq":19,"time":1783951000017,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"TOOLARGE"}}}}
 {"type":"assistant/chunk","seq":20,"time":1783951000017,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
 {"type":"assistant/chunk","seq":21,"time":1783951000017,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
-{"type":"assistant/message","seq":22,"time":1783951000018,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"TOOLARGE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"1c15b391-a95a-4113-9d47-2a1dfc991cf9"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[18,19,20,21],"surfaceOp":"append"}
+{"type":"assistant/message","seq":22,"time":1783951000018,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"TOOLARGE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"id":"3a95dd83-34f7-4bc0-afb6-7ba3c9b483be"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[18,19,20,21],"surfaceOp":"append"}
 {"type":"step/end","seq":23,"time":1783951000018,"data":{"turn":1,"step":2}}
 {"type":"turn/end","seq":24,"time":1783951000018,"data":{"turn":1,"reason":{"kind":"completed"}}}

examples/acp-agent/tests/snapshots/read-image/session.jsonl

@@ -6,13 +6,13 @@
 {"type":"user/message","seq":4,"time":1783951000003,"data":{"content":[{"type":"text","text":"Use read_image to look at red.png in the current directory, then reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"0a0a0a0a-0000-4000-8000-000000000001"},"surfaceOp":"append"}
 {"type":"user/message","seq":5,"time":1786344283033,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"eecd1df6-153c-4a34-b198-42bfc9f9701e"},"surfaceOp":"append"}
 {"type":"session/title","seq":6,"time":1786344283033,"data":{"title":"Use read_image to look at","messageSeqs":[4],"source":{"kind":"fallback"}}}
-{"type":"request/header","seq":7,"time":1786344283034,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
-{"type":"request/context","seq":8,"time":1786344283034,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}}
+{"type":"request/header","seq":7,"time":1786344283034,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
+{"type":"request/context","seq":8,"time":1786344283034,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"}}
 {"type":"assistant/chunk","seq":9,"time":1783951000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
 {"type":"assistant/chunk","seq":10,"time":1786344283039,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"read-image-call","name":"read_image","arguments":"{\"file_path\":\"red.png\"}"}}}}
 {"type":"assistant/chunk","seq":11,"time":1786344283039,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
 {"type":"assistant/chunk","seq":12,"time":1786344283039,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
-{"type":"assistant/message","seq":13,"time":1786344283039,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"read-image-call","name":"read_image","arguments":"{\"file_path\":\"red.png\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"41e9fb55-6edb-419d-b76c-554daa5a1c5d"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12],"surfaceOp":"append"}
+{"type":"assistant/message","seq":13,"time":1786344283039,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"read-image-call","name":"read_image","arguments":"{\"file_path\":\"red.png\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"id":"2b71c837-237d-4d92-a857-8b8ad1a3f237"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12],"surfaceOp":"append"}
 {"type":"tool/call","seq":14,"time":1786344283039,"data":{"turn":1,"step":1,"callId":"read-image-call","name":"read_image","arguments":"{\"file_path\":\"red.png\"}"}}
 {"type":"tool/result","seq":15,"time":1786344283069,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"read-image-call"},"content":[{"type":"tool-result","toolCallId":"read-image-call","content":[{"type":"text","text":"<path>{{cwd}}/red.png</path>\n<type>image</type>\n<content>\nimage/png image, 1x1 px, 69 bytes\n</content>"},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","bytes":69,"width":1,"height":1,"name":"red.png"}}],"isError":false}],"role":"user","id":"0b5779fc-523e-4275-9a32-8eb5e39f521e"}},"sourceEventSeqs":[14],"surfaceOp":"append"}
 {"type":"step/end","seq":16,"time":1786344283069,"data":{"turn":1,"step":1}}
@@ -21,6 +21,6 @@
 {"type":"assistant/chunk","seq":19,"time":1786344283078,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}}
 {"type":"assistant/chunk","seq":20,"time":1786344283079,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}
 {"type":"assistant/chunk","seq":21,"time":1786344283079,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
-{"type":"assistant/message","seq":22,"time":1786344283079,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"73a87a50-8e0b-42af-8c54-d9b6fbe375f1"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[18,19,20,21],"surfaceOp":"append"}
+{"type":"assistant/message","seq":22,"time":1786344283079,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash-vision-exp"},"id":"5a45946c-b9f4-4f2c-a7c3-2569e541ec1d"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[18,19,20,21],"surfaceOp":"append"}
 {"type":"step/end","seq":23,"time":1786344283079,"data":{"turn":1,"step":2}}
 {"type":"turn/end","seq":24,"time":1786344283079,"data":{"turn":1,"reason":{"kind":"completed"}}}