diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml
index 736a066889..1daf12d8e6 100644
--- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.i18n.yaml
+++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.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/2026-07-26-todo-parallel-in-progress.md
-2026-07-26-todo-parallel-in-progress.md: bf463eea602214755a6a828f1620e24df21d5784
-2026-07-26-todo-parallel-in-progress.zh.md: f0e33ef1b985f2834abdb1e103b3f6d4e803f91f
+2026-07-26-todo-parallel-in-progress.md: f1fdb9a96e8b689dba71c448924bbad6cb207420
+2026-07-26-todo-parallel-in-progress.zh.md: fe79952652c138c59dd5ab4da316bab97e880fe5
diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md
index bf463eea60..f1fdb9a96e 100644
--- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md
+++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.md
@@ -35,6 +35,8 @@ The row takes `planSummary` in `toolviews/plan-summary.ts`. It names the first a
 
 `planSummary` returns the name and the count as separate fields rather than one joined string, because the row truncates its summary with `overflow: hidden` / `text-overflow: ellipsis`. A count appended to the task name sits at the far end of the truncatable text, so exactly the narrow viewports and long task names that make the count informative are the ones that clip it away, leaving a parallel plan indistinguishable from a sequential one. The row therefore renders the count in its own `flex: none` span beside the ellipsized text; a pre-joined string could not express that split, and pushing the count in front of the name was rejected because the task name is what the reader is looking for first.
 
+Splitting the count into its own span puts it outside the `.summary` rule, so it also has to repeat that rule's `font-size` and `line-height`. The web shell leaves body text at the browser default rather than the row's 14px, so an unstyled span renders visibly larger than the text it sits beside on a 24px row. Inheriting from a shared parent was the alternative; repeating two declarations keeps the split spans independent, which is the property the ellipsis boundary needs.
+
 ## Consequences
 
 A todo list can now faithfully mirror parallel execution, and every UI renders several active markers at once: the TUI's per-status prefix needed no change, the plan strip's header counts the active items, and the row needed the derivation above. The tool no longer rejects a formerly-invalid snapshot shape, so the change is compatible with every previously valid call; only the error path was removed. The model-facing description changed, which re-recorded the tool-catalog page and every `pinsHeader` scenario's `tool-schemas.expected.json` (ten of them carry the todo schema). Each new pinning scenario master gains carries its own copy of that description, so a branch changing the tool description has to refresh the pins that landed after it branched — `pnpm run test:snapshot:refresh` does it keylessly. The web fixture's todo sample now runs two items `in_progress`, so the assembled web transcript replays a parallel plan and would fail again if either surface returned to single-active derivation.
diff --git a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md
index f0e33ef1b9..fe79952652 100644
--- a/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md
+++ b/.agents/notes/implemented/feature/2026-07-26-todo-parallel-in-progress.zh.md
@@ -35,6 +35,8 @@ Status: implemented
 
 `planSummary` 把任务名与计数作为两个独立字段返回，而不是一个拼好的字符串，因为工具行用 `overflow: hidden` / `text-overflow: ellipsis` 截断其摘要文本。计数接在任务名之后时位于可截断文本的末端，于是恰恰是让计数变得有意义的那些场景——窄视口、长任务名——会把它裁掉，让并行计划看起来与顺序计划无异。因此工具行把计数渲染在自己的 `flex: none` span 中，与被省略号截断的文本并列；一个预先拼好的字符串无法表达这个切分，而把计数放到任务名之前也被否决了：读者首先要找的是任务名。
 
+把计数拆进独立 span 也意味着它落在 `.summary` 规则之外，因此必须重复该规则的 `font-size` 与 `line-height`。Web 外壳把正文字号留在浏览器默认值而非该行的 14px，所以未加样式的 span 会明显大于同一 24px 行内与之并列的文本。另一个方案是从共同父元素继承；重复这两条声明让被拆开的两个 span 保持互不影响，而这正是省略号边界所需要的性质。
+
 ## 后果
 
 现在 todo 列表可以忠实反映并行执行，并且每个 UI 都能一次渲染多个活跃标记：TUI 按状态区分的前缀无需改动，计划横条的表头会计数活跃条目，工具行则需要上述推导。工具不再拒绝一种此前无效的快照形状，因此该改动兼容此前所有合法的调用；被移除的只是错误路径。面向模型的描述发生了变化，这重新记录了 tool-catalog 页面以及每个 `pinsHeader` 场景的 `tool-schemas.expected.json`（其中十个带有 todo schema）。master 每新增一个 pin 场景，就会自带一份该描述的副本，因此改动工具描述的分支必须刷新它分叉之后落地的那些 pin —— `pnpm run test:snapshot:refresh` 可以无 key 完成。web fixture 的 todo 样本现在有两个条目处于 `in_progress`，因此组装后的 web transcript 回放的是一个并行计划；若任一展示面退回单活跃项推导，它会再次失败。