Merge master into fix/subprocess-password-scrub

This commit is contained in:
Tianyi Cui
2026-07-29 21:40:50 +08:00
116 changed files with 10873 additions and 940 deletions

View File

@@ -0,0 +1,6 @@
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
# side as of the last confirmed-consistent state. Both languages carry equal authority;
# after editing either side, bring the other along and re-record with:
# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-27-trajectory-inspection-ledger.md
2026-07-27-trajectory-inspection-ledger.md: 8c2a7c42b7898776de5d42459b09c0fb1737ec0b
2026-07-27-trajectory-inspection-ledger.zh.md: 6c5733046dc2cfd3fd2bd005f4cf5c2d2bd110af

View File

@@ -0,0 +1,43 @@
# Agent Note: Trajectory inspection ledger
Status: implemented
English | [中文](2026-07-27-trajectory-inspection-ledger.zh.md)
## Problem
Trajectory has to make prose, machine payloads, token usage, timing, and nested tool activity readable in the same viewport. The earlier stacked Turn and Step cards preserved hierarchy but spent too much vertical space on repeated chrome, while a completely flat table would erase the causal structure that makes a trajectory useful. Role colors also risked borrowing success and warning semantics, which made visual decoration indistinguishable from runtime state.
## Decision
**Render a compact, turn-aware event ledger with a local record inspector, using the existing DeepSeek design system.**
- The ledger keeps session events in sequence within rewind-delimited branches. Turn boundaries use a slightly heavier rule, the raw Turn id, and a continuous left rail; Request boundaries appear as small points integrated into that structure and use one chronological numbering space across ordinary and compaction requests.
- Event kind and content form the two stable columns. Role tags align toward the content, nested subtools receive a small indentation, and CSS truncation preserves the available preview width. Token usage and duration stay in the inspector.
- Product prose uses the existing sans stack. Turn ids, token counts, durations, tool calls, raw payloads, and other machine data use the existing code stack.
- Existing theme tokens own both light and dark rendering. Neutral borders and surfaces form the structure; distinct low-emphasis role hues support scanning without carrying success or failure meaning, while business blue identifies selection, links, and focus.
- The client runtime exposes a read-only history source independent from Session and SessionManager. Each activated source owns its raw entries, paging, live gap repair, and reconnect rebuild; the ordinary conversation snapshot remains the folded Chat projection. Trajectory subscribes to that source, exhausts its paging only while mounted, and lazily derives its event order, context lineage, schema index, and Requests instead of imposing those structures on every conversation consumer.
- Ordinary generation and compaction calls form one chronological Request projection, distinguished by purpose rather than separate collections. Effective prompt state and its change ride the Request that introduced them; compaction and prompt changes are not independent inspection entities. Complete history makes global Request numbering and cumulative usage session-wide rather than tail-window-relative.
- Call schemas come from the active recorded Request header. Keyless snapshot fixtures deliberately replace that catalog with the non-array `{{tools}}` token, which the durable inspection boundary treats as unavailable instead of attempting to project or fabricate schemas.
- Selecting a record or Request opens an inspector inside Trajectory. Tabs and Summary sections follow the selected entity: Markdown messages expose rendered, source, provenance, and hierarchy views; tools add JSON payload/result and schema views; Requests add options, usage, timing, and result navigation. Images render as media rather than serialized data.
- Turn folding removes all rows after its first record and replaces them with a compact step/tool-call count; Assistant folding applies the same interaction to its tool-call descendants. Global controls fold or expand both levels.
- The separate Waterfall tab is removed. A fixed Overview above the ledger projects every record with known `startedAt` onto three semantic timing lanes using its own duration. Dragging left or right commits an inclusive interval filter: any record whose active interval overlaps either boundary remains visible, records without known timing leave the focused ledger, and clearing the selection restores the full branch. The Overview keeps the full time domain while focused so the selection can be resized or cleared without losing orientation.
- This local inspector remains independent from the conversation-wide Chat details column. At narrow widths it overlays the ledger and remains dismissible by keyboard or pointer.
## Alternatives considered
**Copy Vite DevTools fonts, colors, glass surfaces, or component shapes.** Rejected: those choices express a different product identity. The implementation only adopts the transferable method: neutral structure, semantic accents, machine-data typography, dense scanning, and shadows reserved for floating layers.
**Keep one card per Turn and Step.** Rejected: repeated card chrome reduced the number of visible records and made cross-step comparison slower.
**Flatten every record without Turn or Request boundaries.** Rejected: a trajectory is not merely a log stream; those boundaries preserve the causal structure without consuming dedicated rows.
**Reuse the global Chat details column.** Rejected: it would couple local inspection to conversation navigation and make a row click unexpectedly change another view's state.
**Keep timing in a separate Waterfall tab.** Rejected: the placeholder summarized node counts rather than record timing and forced users to switch away from the rows they wanted to focus. A full-domain Overview keeps timing and filtered records in one visual context.
**Change global theme tokens to match the reference.** Rejected: the existing theme already provides paired light and dark semantic layers, and a local redesign does not justify changing unrelated surfaces.
## Consequences
Trajectory shows more useful records per viewport while retaining Turn and Request orientation. Context rewrites and compactions remain inline with their surrounding history, while a rewind begins a successor branch that inherits only the retained prefix. The main ledger omits token usage and duration so content receives the available width; the local inspector exposes those facts together with full payloads, provenance, schemas, and request timing. The Overview uses recorded start/duration facts without fabricating live elapsed time, and its inclusive focus behavior matches the interaction users already know from Chrome DevTools Network. Focused component tests pin projection, folding, record and interval selection, entity-specific tabs, and running/error semantics; the assembled Web snapshot pins the ledger, Overview, and inspector through the real client composition.

View File

@@ -0,0 +1,43 @@
# Agent Note轨迹检查记录表
Status: implemented
[English](2026-07-27-trajectory-inspection-ledger.md) | 中文
## 问题
轨迹视图需要在同一视口内清晰呈现正文、机器载荷、token 用量、计时数据和嵌套工具活动。此前堆叠式的轮次与步骤卡片虽然保留了层级,却在重复界面框架上耗费了太多垂直空间;完全扁平化的表格又会抹去因果结构,而这种结构正是轨迹视图的价值所在。角色配色还可能借用成功与警告语义,使视觉装饰与运行时状态无法区分。
## 决策
**使用现有 DeepSeek 设计系统,渲染保留轮次结构的紧凑事件记录表,并提供局部记录检查器。**
- 记录表在以 `rewind` 划分的分支内按会话事件顺序展示。轮次边界由稍粗的分割线、原始轮次 id 和连续的左侧竖线表示请求边界以融入该结构的小圆点表示普通请求与压缩compaction请求在整个时间序列中共用一套编号。
- 事件类型与内容构成两个稳定列。角色标签朝内容侧对齐,嵌套子工具略微缩进,内容预览使用 CSS 截断以适应可用宽度。token 用量和耗时留在检查器中。
- 产品正文使用现有无衬线字体栈。轮次 id、token 数、耗时、工具调用、原始载荷和其他机器数据使用现有代码字体栈。
- 现有主题 token 同时负责亮色和暗色渲染。中性边框与表面构成整体结构;区分度较低的角色色帮助扫读而不表达成功或失败语义,业务蓝色则标识选择状态、链接和焦点。
- 客户端 runtime 提供独立于 Session 和 SessionManager 的只读历史数据源。每个已激活的数据源自行拥有原始条目、分页、实时缺口修复和重连重建;普通会话快照仍然只是 Chat 所需的折叠投影。Trajectory 订阅该数据源仅在挂载期间补齐全部历史并按需派生事件顺序、上下文谱系、schema 索引和请求,避免让所有会话消费者承担这些结构。
- 普通生成调用与压缩调用形成一条按时间排序的请求投影,以 purpose 区分而不是放入不同集合。生效的提示词状态及其变化附着在引入它们的请求上;压缩和提示词变化都不是独立检查实体。完整历史使全局请求编号和累计用量以整个会话为范围,而不是相对于末尾窗口。
- 调用 schema 来自当前生效且已记录的请求头。无密钥快照 fixture测试前置数据有意将该目录替换为非数组 token `{{tools}}`,持久化检查边界会将其视为不可用,而不是尝试投影或虚构 schema。
- 选择记录或请求后轨迹视图内部会打开检查器其标签页和概览区域随实体类型变化Markdown 消息提供渲染、源码、来源和层级视图;工具提供 JSON 载荷/结果和 schema 视图;请求提供选项、用量、计时和结果跳转。图片以媒体形式渲染,而不是显示为序列化数据。
- 折叠轮次时保留其第一条记录,将后续行替换为紧凑的步骤和工具调用数量;折叠助手时对其工具调用后代应用相同交互。全局控件可以分别折叠或展开这两个层级。
- 移除独立的 waterfall瀑布式事件标签页。固定在记录表上方的 Overview 区域将所有 `startedAt` 已知的记录按各自耗时投影到三条语义计时轨道。向左或向右拖动会提交包含边界的区间筛选任何活动区间与所选区间相交的记录都会保留计时未知的记录会从聚焦后的记录表中移除清除选择则恢复完整分支。聚焦后Overview 区域仍保留完整时间范围,以便在不失去方位的情况下调整或清除选择。
- 此局部检查器与会话级 Chat 详情栏相互独立。在窄屏下,检查器会覆盖记录表,并且仍可通过键盘或指针关闭。
## 曾考虑的替代方案
**照搬 Vite DevTools 的字体、颜色、玻璃表面或组件形状。** 不予采纳:这些选择表达的是另一种产品身份。实现仅吸收可迁移的方法,即中性结构、语义强调色、机器数据排版、紧凑扫读,以及只为浮层保留阴影。
**每个轮次和步骤保留一张卡片。** 不予采纳:重复的卡片框架减少了可见记录数量,并降低了跨步骤比较的速度。
**不使用轮次或请求边界,将所有记录完全扁平化。** 不予采纳:轨迹并非普通日志流;这些边界无需占用独立行,也能保留因果结构。
**复用全局 Chat 详情栏。** 不予采纳:这会让局部检查与会话导航耦合,还会使行点击意外改变另一个视图的状态。
**将计时保留在独立的 waterfall 标签页中。** 不予采纳:占位实现汇总的是节点数而非记录计时,并迫使用户离开想要聚焦的记录。保留完整时间范围的 Overview 区域让计时和筛选后的记录处于同一视觉上下文中。
**修改全局主题 token 以匹配参考设计。** 不予采纳:现有主题已经提供配对的亮色与暗色语义层,局部重新设计不足以成为修改无关表面的理由。
## 后果
轨迹视图在保留轮次与请求定位的同时,每个视口可以显示更多有效记录。上下文 `rewrite` 与压缩保持在周边历史中的原始位置,`rewind` 则建立仅继承保留前缀的后继分支。主记录表省略 token 用量和耗时让内容获得可用宽度局部检查器展示这些数据以及完整载荷、来源、schema 和请求计时。Overview 区域使用记录的开始时间与耗时数据,而不虚构实时流逝时间,其包含边界的聚焦行为与用户熟悉的 Chrome DevTools Network 交互一致。针对性组件测试锁定投影、折叠、记录与区间选择、实体特定标签页和运行/错误语义;组装后的 Web 快照则通过真实客户端组合锁定记录表、Overview 区域与检查器。

View File

@@ -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/simplification/2026-07-28-local-json-tree-renderer.md
2026-07-28-local-json-tree-renderer.md: 5e8e6d6968319ada53e65a48e9e03b297dc0141c
2026-07-28-local-json-tree-renderer.zh.md: 221880391da05551d05ad9e3dadb909e2e74fa68

View File

@@ -0,0 +1,32 @@
# Agent Note: Local JSON tree renderer
Status: implemented
English | [中文](2026-07-28-local-json-tree-renderer.zh.md)
## Problem
The read-only JSON inspector used by the [trajectory ledger](../feature/2026-07-27-trajectory-inspection-ledger.md) needs compact object and array previews, explicit array paths for copy actions, fixed-open and collapsible root modes, and keyboard navigation. `react-json-view-lite` exposes neither custom node rendering nor row identity, so satisfying those requirements through that dependency requires a package-manager patch against compiled distribution files and DOM traversal that reconstructs data paths from visible labels. The patch behaves as an untyped fork while its source maps and upstream source remain unchanged.
## Decision
`JsonTree` owns its recursive presentation in `dsh-client-ui-primitives`.
- Each rendered row receives its value and property path directly. Object keys and array indexes extend that path during recursion, so copy actions never recover application data from rendered DOM text.
- Expandable rows render the compact preview locally and mount child rows only while expanded. `expandTopLevel` selects between a fixed-open bracket frame and a collapsible root node without changing the public component contract.
- The tree keeps one tabbable expander among visible nodes. Pointer activation claims that tab stop; Up and Down move it cyclically, while Left and Right collapse or expand the focused node.
- `react-json-view-lite` is not a package dependency and has no pnpm patch. Focused component tests pin previews, expansion, keyboard focus, and array copy paths.
## Alternatives considered
**Keep the distribution patch.** Rejected because the application-specific renderer and array identity contract would remain hidden in generated third-party files, and every dependency update would require reviewing a fork without matching source maps.
**Use the upstream renderer without previews.** Rejected because `{…}` and `[…]` discard the compact payload context that the trajectory inspector uses for scanning.
**Inject previews and row metadata after render.** Rejected because effects or mutation observers would depend on the same private DOM structure while splitting one row between React ownership and imperative mutation.
**Adopt a larger JSON viewer.** Rejected because editing, search, and theme systems are outside the current read-only contract; the added dependency surface would not remove the inspector-specific copy and layout code.
## Consequences
The JSON inspector has one source-level owner, explicit data flow, accurate array paths, and no patched dependency. The package now owns recursive rendering, expansion state, ARIA tree structure, and roving focus behavior, so changes to those semantics require focused component coverage. The implementation remains intentionally read-only and limited to the preview, navigation, and copy behavior used by current consumers.

View File

@@ -0,0 +1,32 @@
# Agent Note本地 JSON 树渲染器
Status: implemented
[English](2026-07-28-local-json-tree-renderer.md) | 中文
## 问题
[轨迹检查记录表](../feature/2026-07-27-trajectory-inspection-ledger.md)使用的只读 JSON 检查器需要提供紧凑的对象和数组预览、供复制操作使用的明确数组路径、固定展开与可折叠两种根节点模式,以及键盘导航。`react-json-view-lite` 既不提供自定义节点渲染,也不提供行标识;要通过该依赖满足这些要求,就必须使用包管理器为编译后的发布文件打补丁,并遍历 DOM从可见标签中还原数据路径。该补丁实际上相当于一个不受类型约束的 fork但其源码映射与上游源码均未同步修改。
## 决策
`dsh-client-ui-primitives` 中的 `JsonTree` 自行负责递归呈现。
- 每个渲染行都直接接收自身的值和属性路径。递归时,对象键和数组索引会附加到路径末尾,因此复制操作无需再从 DOM 渲染文本中反向还原应用数据。
- 可展开行在本地渲染紧凑预览,仅在展开时挂载子行。`expandTopLevel` 可选择固定展开的括号框架或可折叠根节点,而不改变组件的公开契约。
- 树中所有可见节点仅保留一个可通过 Tab 键聚焦的展开控件。使用指针激活控件后,该控件会成为 Tab 键焦点位置;上、下方向键循环移动焦点,左、右方向键折叠或展开当前焦点所在节点。
- `react-json-view-lite` 不在 `dsh-client-ui-primitives` 的依赖项中,也没有 pnpm 补丁。针对性组件测试锁定预览、展开、键盘焦点和数组复制路径。
## 曾考虑的替代方案
**保留发布文件补丁。** 不予采纳:应用专用的渲染逻辑和数组标识契约仍会隐藏在生成的第三方文件中;每次更新依赖,都必须评审一个没有配套源码映射的 fork。
**直接使用不提供预览的上游渲染器。** 不予采纳:`{…}``[…]` 会丢失轨迹检查器扫读时所需的紧凑载荷上下文。
**渲染后注入预览和行元数据。** 不予采纳Effect 或 MutationObserver 仍会依赖同一套私有 DOM 结构,同时使 React 和命令式变更机制分别负责同一行的不同部分。
**采用更大型的 JSON 查看器。** 不予采纳:编辑、搜索与主题系统不在当前只读契约范围内;扩大依赖范围也无法去除检查器专用的复制和布局代码。
## 后果
JSON 检查器在源码层由单一实现负责,具有显式数据流和准确的数组路径,且没有经过补丁修改的依赖。`dsh-client-ui-primitives` 负责递归渲染、展开状态、ARIA 树结构和焦点循环移动行为,因此修改这些语义时必须提供针对性组件测试。实现有意保持只读,仅包含当前消费方使用的预览、导航与复制行为。