Merge branch 'master' of https://github.com/deepseek-harness/deepseek-harness into xtr/react-loop-simplification

# Conflicts: # .agents/notes/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml # docs/architecture.i18n.yaml # docs/cookbook/extension-cookbook.i18n.yaml # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/core.md # docs/core-data-structures/core.zh.md # docs/core-data-structures/llm-streaming.i18n.yaml # docs/core-data-structures/llm-streaming.md # docs/core-data-structures/llm-streaming.zh.md # docs/core-data-structures/session.i18n.yaml # docs/event-producer-consumer.md # docs/persistence-catalog.md # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/README.i18n.yaml # packages/core/agent-loop/src/agent.ts # packages/core/agent/README.i18n.yaml # packages/core/session/README.i18n.yaml # packages/core/session/src/types.ts # packages/llm/llm/README.i18n.yaml # packages/llm/llm/README.md # packages/llm/llm/README.zh.md # packages/llm/llm/src/index.ts # packages/llm/llm/tests/service.spec.ts # packages/sdk/sdk-client/README.i18n.yaml # packages/sdk/sdk-protocol/README.i18n.yaml # packages/sdk/sdk-protocol/README.md # packages/sdk/sdk-protocol/README.zh.md # packages/subagent/subagent-dsh-sdk/README.i18n.yaml # packages/ui/jsonrpc/README.i18n.yaml # packages/ui/jsonrpc/README.md # packages/ui/jsonrpc/README.zh.md # packages/ui/tui/src/index.ts # python/sdk/README.i18n.yaml # scripts/gen-cordis-catalog.ts
2026-07-31 10:16:14 +08:00
parent 060c0f78f0 1351565681
commit 7a463dbe44
1106 changed files with 33236 additions and 7168 deletions
--- a/packages/ui/tui/README.i18n.yaml
+++ b/packages/ui/tui/README.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 packages/ui/tui/README.md
-README.md: 99d76d21828bc6b1eb0220e11362885652b3cefd
-README.zh.md: 71b3b0546fed70a89f34a2ca4eee423be5909afd
+README.md: 63c888b1d51c02fa85a8f0cc1617874debd87c4e
+README.zh.md: ca5efc9ae26a9833d271991f73a21c607d8fb09d
--- a/packages/ui/tui/README.md
+++ b/packages/ui/tui/README.md
@@ -12,7 +12,7 @@ This package owns interactive terminal presentation and input only. It injects `

 After terminal startup succeeds, the package provides the terminal-local `ctx.tui` extension service. A plugin that injects it can call `openOverlay()` with a component factory and constrained layout options; the host exposes the viewport, semantic theme, display-text escaping, redraw, close, and a lifetime signal, but not the pi-tui tree, terminal, focus controller, or overlay handle. Plugin overlays, the model selector, and user questions share one FIFO modal queue. Each request is an effect of the calling plugin fiber, so unload removes queued work or closes visible work before cleanup settles; terminal shutdown unloads dependents before stopping pi-tui. Overlay state is not logged or replayed. Component code is trusted and may render ANSI styling, but must pass untrusted text through `host.display()`. The [interactive-extension Agent Note](../../../.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md) owns the boundary and rejected alternatives.

-The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the standing `todo/write` plan above the editor (cleared on the next `turn/start`), and presents `ctx.userInteraction` questions in a wide bottom-left keyboard panel with progress, numbered options, and aligned descriptions. The latest logged session title becomes the header subtitle, with `welcome` before a title exists, and the terminal window title becomes `<session title> — <configured title>`. A durable `llm/retry` event retracts the failed step's live chunks and renders the scheduled retry count, delay, and failure in the transcript; success, exhaustion, and cancellation then settle through ordinary session events. The footer totals each logged model step's usage once, including failed attempts, while treating committed-message usage as a fallback for logs without a usage chunk. Its idle view compares token-meter pressure with `ctx.llm.resolveModelInfo()` context for the current route, displays `context unknown` when the adapter has no capacity metadata, and also shows tool-card mode plus the current model and any explicitly selected reasoning effort; while the agent runs, an elapsed working indicator and `esc interrupt` replace that summary. Surface replacement events rebuild the transcript so compacted history does not reappear.
+The TUI rebuilds resumed history from the append-origin session events, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the standing `todo/write` plan above the editor (cleared on the next `turn/start`), and presents `ctx.userInteraction` questions in a wide bottom-left keyboard panel with progress, numbered options, and aligned descriptions. The latest logged session title becomes the header subtitle, with `welcome` before a title exists, and the terminal window title becomes `<session title> — <configured title>`. A durable `llm/retry` event retracts the failed step's live chunks and renders the scheduled retry count, delay, and failure in the transcript; success, exhaustion, and cancellation then settle through ordinary session events. The footer totals each logged model step's usage once, including failed attempts, while treating committed-message usage as a fallback for logs without a usage chunk. Its idle view compares token-meter pressure with `ctx.llm.resolveModelInfo()` context for the current route, displays `context unknown` when the adapter has no capacity metadata, and also shows tool-card mode plus the current model and any explicitly selected reasoning effort; while the agent runs, an elapsed working indicator and `esc interrupt` replace that summary. A surface replacement never rewrites the rendered transcript: the conversation it shadows stays readable, and a landed compaction checkpoint adds one dim `… earlier context was compacted …` marker at its log position, so the terminal reports where the model stopped seeing that history instead of erasing it. Model-only replacement copies — a pruned tool result, a regenerated assistant message — render nothing.

 An embedding may provide `TuiRuntime.formatCwd` when its logical workspace label differs from the session's host directory. The override changes only the footer label; tools continue to use the session `cwd`.

@@ -75,7 +75,7 @@ A launcher can seed a fresh session's first turn by providing `INITIAL_SKILL_KEY
    fileSearchExcludedDirectories: ['.git', 'node_modules', 'dist']
 ```

-Startup fails before mounting when either process stream is not a TTY. The composing app must mount the TUI before its config-created agent so the front door can observe `agent-loop/config-start-failed`; a matching exact-session failure is written before fullscreen mode starts and exits with status 1 instead of leaving a blank terminal. Disposal stops extension admission, unloads the `ctx.tui` provider and its dependent plugins, aborts running commands, removes the TUI definitions, stops loaders, rejects pending questions, drains terminal input, restores terminal state, unregisters event listeners and the user-interaction provider, and never exits a replacement process during HMR.
+Startup fails before mounting when either process stream is not a TTY. The composing app must mount the TUI before its config-created agent so the front door can observe `agent-loop/config-start-failed`; a matching exact-session failure is written before fullscreen mode starts and exits with status 1 instead of leaving a blank terminal. Disposal stops extension admission, unloads the `ctx.tui` provider and its dependent plugins, aborts running commands, removes the TUI definitions, stops loaders, rejects pending questions, drains terminal input, restores terminal state, unregisters event listeners and the user-interaction provider, and never exits a replacement process during HMR. A user exit disposes the application root so sibling resources close, then exits; a five-second fallback prevents one stuck disposer from trapping the process.

 ## Color

--- a/packages/ui/tui/README.zh.md
+++ b/packages/ui/tui/README.zh.md
@@ -12,7 +12,7 @@ DeepSeek Harness agent（智能体）的交互式终端入口，基于 [`@earend

 终端成功启动后，本包会提供终端本地的 `ctx.tui` 扩展服务。注入该服务的插件可以使用组件工厂和受限布局选项调用 `openOverlay()`；宿主会公开 viewport、语义化主题、显示文本转义、重绘、关闭和生命周期信号，但不公开 pi-tui 树、终端、焦点控制器或 overlay 句柄。插件 overlay、模型选择器和用户问题共用一个 FIFO 模态队列。每个请求都是调用方插件 fiber 的 effect，因此卸载会移除排队工作，或在清理结算前关闭可见工作；终端关闭会先卸载依赖项，再停止 pi-tui。Overlay 状态不会记录或回放。组件代码受信任，可以渲染 ANSI 样式，但必须通过 `host.display()` 处理不受信任文本。[交互式扩展 Agent Note](../../../.agents/notes/implemented/architecture/2026-07-22-tui-interactive-extension-service.md)持有该边界和未采用的替代方案。

-TUI 从活跃会话表层重建已恢复历史，渲染 Markdown 响应与 reasoning，将每个工具的 `presentCall` / `presentResult` 意图应用到终端、diff 或通用卡片，把站立的 `todo/write` 计划保留在编辑器上方（下一个 `turn/start` 时清空），并在左下方宽键盘面板中展示 `ctx.userInteraction` 问题，包含进度、编号选项和对齐说明。最新记录的会话标题成为 header 副标题；标题不存在时使用 `welcome`，终端窗口标题则变为 `<session title> — <configured title>`。持久 `llm/retry` 事件会撤回失败步骤的实时 chunk，并在 transcript（文本记录）中渲染计划重试次数、延迟和失败；成功、耗尽与取消随后通过普通会话事件结算。Footer 会对每个已记录模型步骤的用量只计一次，包括失败尝试；对于没有用量 chunk 的日志，以已提交消息的用量回退。其空闲视图会将 token-meter 压力与 `ctx.llm.resolveModelInfo()` 为当前路由返回的上下文容量进行比较；适配器没有容量元数据时显示 `context unknown`，并显示工具卡片模式、当前模型，以及任何显式选择的推理强度。Agent 运行时，这些摘要会替换为已经过工作时间指示器和 `esc interrupt`。表层替换事件会重建 transcript，使经过压缩（compaction）的历史不会再次出现。
+TUI 从追加来源的会话事件重建已恢复历史，渲染 Markdown 响应与 reasoning，将每个工具的 `presentCall` / `presentResult` 意图应用到终端、diff 或通用卡片，把站立的 `todo/write` 计划保留在编辑器上方（下一个 `turn/start` 时清空），并在左下方宽键盘面板中展示 `ctx.userInteraction` 问题，包含进度、编号选项和对齐说明。最新记录的会话标题成为 header 副标题；标题不存在时使用 `welcome`，终端窗口标题则变为 `<session title> — <configured title>`。持久 `llm/retry` 事件会撤回失败步骤的实时 chunk，并在 transcript（文本记录）中渲染计划重试次数、延迟和失败；成功、耗尽与取消随后通过普通会话事件结算。Footer 会对每个已记录模型步骤的用量只计一次，包括失败尝试；对于没有用量 chunk 的日志，以已提交消息的用量回退。其空闲视图会将 token-meter 压力与 `ctx.llm.resolveModelInfo()` 为当前路由返回的上下文容量进行比较；适配器没有容量元数据时显示 `context unknown`，并显示工具卡片模式、当前模型，以及任何显式选择的推理强度。Agent 运行时，这些摘要会替换为已经过工作时间指示器和 `esc interrupt`。表层替换从不重写已渲染的 transcript：被它遮蔽的对话仍可阅读，而已落地的压缩（compaction）检查点会在其日志位置添加一行暗色 `… earlier context was compacted …` 标记，因此终端报告的是模型从何处起不再看到那段历史，而不是把它抹掉。仅供模型使用的替换副本——被裁剪的工具结果、重新生成的 assistant 消息——不渲染任何内容。

 如果逻辑工作区标签与会话宿主目录不同，嵌入方可以提供 `TuiRuntime.formatCwd`。该覆盖只改变 footer 标签；工具仍使用会话 `cwd`。

@@ -75,7 +75,7 @@ Footer 将会话报告的用量汇总为 `↑<uncached input> ↓<output>`；任
    fileSearchExcludedDirectories: ['.git', 'node_modules', 'dist']
 ```

-任一进程流不是 TTY 时，启动会在挂载前失败。组合 app 必须先挂载 TUI，再挂载由配置创建的 agent，使入口能够观察 `agent-loop/config-start-failed`；完全匹配会话的失败会在全屏模式启动前写出并以状态 1 退出，而不是留下空白终端。dispose（资源释放）会停止接收扩展请求，卸载 `ctx.tui` 提供方及其依赖插件，中止运行中的命令，移除 TUI 定义，停止 loader，拒绝待处理问题，排空终端输入，恢复终端状态，注销事件 listener 和用户交互提供方，并且绝不会在 HMR 期间退出替换进程。
+任一进程流不是 TTY 时，启动会在挂载前失败。组合 app 必须先挂载 TUI，再挂载由配置创建的 agent，使入口能够观察 `agent-loop/config-start-failed`；完全匹配会话的失败会在全屏模式启动前写出并以状态 1 退出，而不是留下空白终端。dispose（资源释放）会停止接收扩展请求，卸载 `ctx.tui` 提供方及其依赖插件，中止运行中的命令，移除 TUI 定义，停止 loader，拒绝待处理问题，排空终端输入，恢复终端状态，注销事件 listener 和用户交互提供方，并且绝不会在 HMR 期间退出替换进程。用户退出会先 dispose 应用根上下文以关闭同级资源，再退出进程；五秒兜底可避免某个卡住的 disposer 困住进程。

 ## 颜色

--- a/packages/ui/tui/package.json
+++ b/packages/ui/tui/package.json
@@ -35,6 +35,7 @@
    "@deepseek-ai/dsh-agent": "^0.0.1",
    "@deepseek-ai/dsh-agent-loop": "^0.0.1",
    "@deepseek-ai/dsh-commands": "^0.0.1",
+    "@deepseek-ai/dsh-compact": "^0.0.1",
    "@deepseek-ai/dsh-invariants": "^0.0.1",
    "@deepseek-ai/dsh-llm": "^0.0.1",
    "@deepseek-ai/dsh-llm-retry": "^0.0.1",
@@ -74,6 +75,7 @@
    "@deepseek-ai/dsh-agent-loop": "workspace:^",
    "@deepseek-ai/dsh-goal": "workspace:^",
    "@deepseek-ai/dsh-commands": "workspace:^",
+    "@deepseek-ai/dsh-compact": "workspace:^",
    "@deepseek-ai/dsh-invariants": "workspace:^",
    "@deepseek-ai/dsh-llm": "workspace:^",
    "@deepseek-ai/dsh-llm-retry": "workspace:^",
--- a/packages/ui/tui/src/chat/helpers.ts
+++ b/packages/ui/tui/src/chat/helpers.ts
@@ -1,6 +1,6 @@
 /**
 * Zero-state helpers for the interactive chat channel: prompt-directory and
- * Git-branch formatting, surface/tool-call derivations over the session log,
+ * Git-branch formatting, transcript/tool-call derivations over the session log,
 * session-reference context cards, the placeholder editor, and banner-reveal
 * timing constants. None of these close over channel state.
 * @module @deepseek-ai/dsh-tui/chat/helpers
@@ -15,7 +15,9 @@ import {
  truncateToWidth,
  visibleWidth,
 } from '@earendil-works/pi-tui'
-import type { Session } from '@deepseek-ai/dsh-session'
+import { isCompactCheckpointSource } from '@deepseek-ai/dsh-compact'
+import { isAppendSurfaceEvent, isReplacementSurfaceEvent } from '@deepseek-ai/dsh-session'
+import type { Session, SessionEvent } from '@deepseek-ai/dsh-session'
 import { scrubbedParentEnv } from '@deepseek-ai/dsh-subprocess'

 /** Editor that shows a placeholder without making it editable content. */
@@ -81,24 +83,16 @@ export function gitBranch(cwd: string): string | undefined {
 }

 /**
- * Sequence numbers currently visible on the session surface.
- * @param session - session whose surface nodes to read.
- * @returns the set of visible event sequence numbers.
- */
-export function activeSurfaceSeqs(session: Session): Set<number> {
-  return new Set(session.surface.nodes)
-}
-
-/**
- * Tool-call ids whose owning assistant message is on the active surface.
+ * Tool-call ids whose owning assistant message is append-origin, so its tool
+ * cards stay paired in the transcript after a replacement shadowed the message
+ * on the model surface.
 * @param session - session whose events to scan.
- * @param active - sequence numbers currently on the surface.
- * @returns the set of active tool-call ids.
+ * @returns the set of transcript tool-call ids.
 */
-export function activeToolCallIds(session: Session, active: ReadonlySet<number>): Set<string> {
+export function transcriptToolCallIds(session: Session): Set<string> {
  const ids = new Set<string>()
  for (const event of session.events) {
-    if (event.type !== 'assistant/message' || !active.has(event.seq)) continue
+    if (event.type !== 'assistant/message' || !isAppendSurfaceEvent(event)) continue
    for (const block of event.data.message.content) {
      if (block.type === 'tool-call') ids.add(block.id)
    }
@@ -106,6 +100,26 @@ export function activeToolCallIds(session: Session, active: ReadonlySet<number>)
  return ids
 }

+/**
+ * Whether an event is a landed compaction checkpoint. Recognition goes through
+ * {@link isCompactCheckpointSource} — the compaction seam's backend-independent
+ * contract for the source every backend stamps on its replacement user message —
+ * rather than the shape of the replacement. Other replacements (a pruned
+ * `tool/result`, a regenerated `assistant/message`) rewrite one node for the
+ * model and mark no boundary in the conversation.
+ *
+ * Both current call sites already test the replacement themselves. The check
+ * keeps the exported predicate true to its name for a third caller, rather than
+ * making that caller repeat it.
+ * @param event - event to test.
+ * @returns true when the event compacted a surface range.
+ */
+export function isCompactCheckpoint(event: SessionEvent): boolean {
+  return event.type === 'user/message'
+    && isCompactCheckpointSource(event.data.source)
+    && isReplacementSurfaceEvent(event)
+}
+
 /**
 * Read a session-reference context card's display labels from an event source.
 * @param source - event source to inspect.
--- a/packages/ui/tui/src/chat/resume.ts
+++ b/packages/ui/tui/src/chat/resume.ts
@@ -29,7 +29,13 @@ import type { ChannelNotice, ChatChannelDeps } from './channel.ts'
 export interface ResumeControllerDeps extends ChatChannelDeps, ChannelNotice {
  readonly agent: Agent
  readonly runtime: TuiRuntime
-  readonly sessionQuery: SessionQueryService | undefined
+  /**
+   * The optional session-query service, re-read at each use. `sessionQuery` is
+   * mounted by an independent plugin, and a flat config tree gives no ordering
+   * guarantee between it and this front door, so a value captured once at
+   * construction can be `undefined` even though the service arrives moments later.
+   */
+  readonly sessionQuery: (this: void) => SessionQueryService | undefined
  readonly ui: TUI
  readonly editor: HintEditor
  /** Current agent status, re-read at each resume precondition point. */
@@ -74,9 +80,11 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro
          events: live.events.map(event => structuredClone(event)),
        }
      } else {
-        /* v8 ignore next -- caller checks the optional service before mapping records */
-        if (sessionQuery === undefined) throw new Error('session query is unavailable')
-        snapshot = await sessionQuery.readSession(record.header.id)
+        const readQuery = sessionQuery()
+        /* v8 ignore start -- caller proves the optional service before mapping records */
+        if (readQuery === undefined) throw new Error('session query is unavailable')
+        /* v8 ignore stop */
+        snapshot = await readQuery.readSession(record.header.id)
      }
      return summarizeResumeCandidate(
        record,
@@ -104,11 +112,13 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro
   * resolve the exact identity and workspace the host will re-exec into.
   */
  const preflightResume = async (sessionId: SessionId): Promise<{ id: SessionId; cwd: string }> => {
-    /* v8 ignore next -- only showResume can call this closure, after proving the optional service exists */
-    if (sessionQuery === undefined) throw new Error('Resume is unavailable: session query is not mounted.')
+    const query = sessionQuery()
+    /* v8 ignore start -- showResume alone calls this after proving the optional service exists */
+    if (query === undefined) throw new Error('Resume is unavailable: session query is not mounted.')
+    /* v8 ignore stop */
    const initialStatus = deps.agentStatus()
    if (initialStatus !== 'idle') throw new Error(`Resume requires an idle agent (status: ${initialStatus}).`)
-    const record = (await sessionQuery.listSessions()).find(candidate => candidate.header.id === sessionId)
+    const record = (await query.listSessions()).find(candidate => candidate.header.id === sessionId)
    if (record === undefined) throw new Error(`Session "${sessionId}" is no longer available.`)
    const candidate = await readResumeCandidate(
      record,
@@ -177,13 +187,14 @@ export function createResumeController(deps: ResumeControllerDeps): ResumeContro
        deps.appendNotice('Resume requires the current turn to finish or be cancelled first.', 'warning')
        return
      }
-      if (sessionQuery === undefined) {
+      const listQuery = sessionQuery()
+      if (listQuery === undefined) {
        deps.appendNotice('Resume is not available: session query is not mounted.', 'warning')
        return
      }
      const scan = ++resumeScan
      void resumeOverlay?.close()
-      void sessionQuery.listSessions().then(async (records) => {
+      void listQuery.listSessions().then(async (records) => {
        if (deps.isDisposed() || scan !== resumeScan) return
        // Every workspace in the store is summarized; the picker owns the
        // current-workspace/all-workspaces scope split over the whole set.
--- a/packages/ui/tui/src/components/transcript.ts
+++ b/packages/ui/tui/src/components/transcript.ts
@@ -389,10 +389,23 @@ export class ToolCardComponent implements Component {
    const glyph = this.result === undefined ? '○' : '●'
    const rawBody = this.renderBody()
    const view = this.resultView ?? this.callView
-    const genericContent = view.card === 'generic' ? view.content ?? this.result?.content : undefined
-    const unknownXml = this.definition === undefined && genericContent !== undefined
+    // A generic card's own content, or a web card's fallback to the raw result
+    // content (the `web` view carries no `content` copy), both render as one dim
+    // Markdown block below, so links/lists/headings keep the unified dim styling
+    // rather than reading as bare text. Terminal and diff cards own their body
+    // styling, so they are excluded (mirrors renderBody's post-terminal/diff fallback).
+    const markdownContent = view.card === 'generic'
+      ? view.content ?? this.result?.content
+      : view.card === 'web'
+        // A web resultView is only assigned alongside this.result (the result
+        // handler sets both) and the pending callView is never a web card, so
+        // the optional-chain undefined side is unreachable here.
+        /* v8 ignore next */
+        ? this.result?.content
+        : undefined
+    const unknownXml = this.definition === undefined && markdownContent !== undefined
      ? renderUnknownXml(
-        displayText(contentText(genericContent)),
+        displayText(contentText(markdownContent)),
        this.maxOutputLines,
        this.visibility === 'expanded',
        displayText,
@@ -405,7 +418,7 @@ export class ToolCardComponent implements Component {
    // A generic card renders title and result as one Markdown document, so the
    // document's own block spacing is preserved, then dims every row — the whole
    // card body reads as one dim block under the status-colored header.
-    const body = unknownXml ?? (genericContent !== undefined && rawBody.lines.length > 0
+    const body = unknownXml ?? (markdownContent !== undefined && rawBody.lines.length > 0
      ? this.dimBody(rawBody, width)
      : [...rawBody.prelude, ...rawBody.lines])
    const visibleBody = unknownXml !== undefined || this.visibility === 'expanded'
@@ -502,7 +515,11 @@ export class ToolCardComponent implements Component {
      // rather than under the dim result-output color.
      return { prelude: [...hunks, footer], lines: [] }
    }
-    const content = view.content ?? this.result?.content
+    // The web card carries no `content` copy, so a `web` result view falls back
+    // to the raw result content here (`view.card === 'generic'` narrows the
+    // generic union arm; a `web` card takes the same fallback, mirroring the
+    // `markdownContent` selection in render()).
+    const content = (view.card === 'generic' ? view.content : undefined) ?? this.result?.content
    const prelude: string[] = []
    const lines: string[] = []
    // The presenter title headlines the body now that the header is a fixed
--- a/packages/ui/tui/src/index.ts
+++ b/packages/ui/tui/src/index.ts
@@ -5,8 +5,21 @@
 * @module @deepseek-ai/dsh-tui
 */

-import { CombinedAutocompleteProvider, Container, Key, Spacer, Text, TUI, ProcessTerminal, matchesKey, visibleWidth, type EditorTheme, type SlashCommand, type TerminalColorScheme } from '@earendil-works/pi-tui'
-import { Service, type Context, type Fiber } from 'cordis'
+import {
+  CombinedAutocompleteProvider,
+  Container,
+  Key,
+  Spacer,
+  Text,
+  TUI,
+  ProcessTerminal,
+  matchesKey,
+  visibleWidth,
+  type EditorTheme,
+  type SlashCommand,
+  type TerminalColorScheme,
+} from '@earendil-works/pi-tui'
+import { Service, type Context, type Fiber, type FiberState } from 'cordis'
 import {
  assembleContextFor,
  installAgentLlmTarget,
@@ -22,6 +35,7 @@ import type { ContentBlock, MessageId } from '@deepseek-ai/dsh-llm'
 import type {} from '@deepseek-ai/dsh-llm-retry'
 import { renderPrompt } from '@deepseek-ai/dsh-system-prompt'
 import {
+  isReplacementSurfaceEvent,
  lastActivityTime,
  SessionId,
  type SessionEvent,
@@ -43,6 +57,7 @@ import {
  TuiExtensionServiceImpl,
  TuiOverlayManager,
 } from './extension/overlay-manager.ts'
+
 import {
  parseTuiPromptTemplate,
  renderTuiPromptTemplate,
@@ -106,14 +121,14 @@ import {
 } from './chat/skill-invocation.ts'
 import { ReferenceAutocompleteProvider } from './chat/autocomplete.ts'
 import {
-  activeSurfaceSeqs,
-  activeToolCallIds,
  BANNER_REVEAL_INTERVAL_MS,
  BANNER_REVEAL_STEPS,
  formatCwd,
  gitBranch,
  HintEditor,
+  isCompactCheckpoint,
  sessionReferenceCard,
+  transcriptToolCallIds,
 } from './chat/helpers.ts'
 import {
  createModelController,
@@ -158,6 +173,9 @@ export type {
  TuiViewport,
 } from './extension/types.ts'

+/** First terminal Cordis state: FAILED, DISPOSED, and UNLOADING are unusable. */
+const FIBER_FAILED = 3 as FiberState.FAILED
+
 declare module 'cordis' {
  interface Context {
    /** Terminal-only interaction service, available only while a TUI is mounted. */
@@ -170,8 +188,6 @@ declare module 'cordis' {
    tuiGoodbyeMessage: string | undefined
    /** Skill the launcher wants auto-invoked as the fresh session's first turn; absent leaves it to the user. */
    tuiInitialSkill: string | undefined
-    /** Launcher-owned session-store root the app bundle defaults to; absent keeps the bundle's project-local default. */
-    launcherSessionsRoot: string | undefined
  }
 }

@@ -216,16 +232,6 @@ export const TUI_GOODBYE_MESSAGE_KEY = 'tuiGoodbyeMessage'
 */
 export const INITIAL_SKILL_KEY = 'tuiInitialSkill'

-/**
- * Context key a launcher sets before any Loader entry mounts
- * (`ctx.provide(SESSIONS_ROOT_KEY, root)`) to supply its session-store root as
- * the app bundle's default persistence root. Shared-store policy (one store
- * across every cwd) belongs to the launcher — the dsh CLI resolves it under the
- * Harness home — never to a plugin; a bundle without this slot keeps its own
- * project-local default, and an explicit `persistenceRoot` config still wins.
- */
-export const SESSIONS_ROOT_KEY = 'launcherSessionsRoot'
-
 /**
 * Optional terminal-local interaction service provided by one mounted TUI.
 *
@@ -256,6 +262,13 @@ export const inject = ['agents', 'sessions', 'commands', 'userInteraction', 'too
 /** Model guidance for path-only file references selected through the TUI. */
 export const FILE_REFERENCE_PROMPT = 'Paths prefixed with @ are files explicitly referenced by the user. Use the read tool when their contents are needed; do not claim to have inspected a file before reading it.'

+/**
+ * Transcript row standing in for one compacted range. The conversation the
+ * compaction replaced stays rendered above it: the marker reports where the
+ * model stopped seeing that history, not that the history is gone.
+ */
+const COMPACTION_MARKER = '… earlier context was compacted …'
+
 interface RunningStatus {
  turn: number | undefined
  timer: ReturnType<typeof setInterval>
@@ -294,7 +307,6 @@ export function createTuiChat(
  const sessionId = SessionId(config.sessionId ?? 'main')
  const agent = ctx.agents.get(sessionId)
  if (agent === undefined) throw new Error(`ui-tui: session "${sessionId}" is not running`)
-  const sessionQuery = ctx.get('sessionQuery')
  const resolved = resolveTuiConfig(config)
  const palette = createPalette(resolved.theme.color)
  const mdTheme = markdownTheme(palette)
@@ -808,6 +820,23 @@ export function createTuiChat(
    }
  }

+  const renderCompactionMarker = (): void => {
+    chat.addChild(new Spacer(1))
+    chat.addChild(new Text(palette.dim(COMPACTION_MARKER), 0, 0))
+  }
+
+  /**
+   * Replay the human transcript from the append-only log. The model-visible
+   * surface shadows compacted ranges, so it is not the source here: every
+   * append-origin message stays rendered, and a replacement contributes at most
+   * the compaction marker at its own log position.
+   *
+   * The `tool/call` pairing check has no live counterpart, because only replay
+   * can meet an orphan: `tool/call` carries no `surfaceOp` of its own, so it
+   * inherits transcript membership from the `assistant/message` that advertised
+   * it, which the live listener has necessarily just rendered. A loaded log is a
+   * replay boundary, so the pairing is re-derived here instead of assumed.
+   */
  const rebuildTranscript = (populateHistory: boolean): void => {
    chat.clear()
    toolCards.clear()
@@ -815,15 +844,13 @@ export function createTuiChat(
    contextCards.clear()
    streaming = undefined
    todo.update([])
-    const active = activeSurfaceSeqs(agent.session)
-    const activeCalls = activeToolCallIds(agent.session, active)
+    const transcriptCalls = transcriptToolCallIds(agent.session)
    for (const event of agent.session.events) {
-      const isSurface = event.type === 'user/message'
-        || event.type === 'assistant/message'
-        || event.type === 'tool/result'
-        || event.type === 'steering/message'
-      if (isSurface && !active.has(event.seq)) continue
-      if (event.type === 'tool/call' && !activeCalls.has(event.data.callId)) continue
+      if (isReplacementSurfaceEvent(event)) {
+        if (isCompactCheckpoint(event)) renderCompactionMarker()
+        continue
+      }
+      if (event.type === 'tool/call' && !transcriptCalls.has(event.data.callId)) continue
      renderEvent(event, { addHistory: populateHistory, renderChunks: false })
    }
    requestRender()
@@ -845,7 +872,14 @@ export function createTuiChat(
    resolved,
    palette,
    overlayManager,
-    sessionQuery,
+    // Optional and independently mounted. Cordis transiently leaves this sibling
+    // non-ACTIVE during command callbacks, so the non-strict read is intentional;
+    // terminal fiber states still exclude failed, closing, and closed providers.
+    sessionQuery: () => {
+      const implementation = ctx.reflect._getImpl('sessionQuery', false)
+      if (implementation === undefined || implementation.fiber.state >= FIBER_FAILED) return undefined
+      return ctx.get('sessionQuery', false)
+    },
    ui,
    editor,
    appendNotice,
@@ -1482,8 +1516,11 @@ export function createTuiChat(
    recordEventUsage(tokens, event)
    if (event.type === 'turn/start' && runningStatus !== undefined) runningStatus.turn = event.data.turn
    if (event.type === 'assistant/message' && streaming?.isSettled()) streaming = undefined
-    if ('surfaceOp' in event && typeof event.surfaceOp === 'object') {
-      rebuildTranscript(false)
+    // A replacement mutates only the model surface, so the rendered transcript
+    // keeps what it already showed; a landed summary checkpoint adds its marker.
+    if (isReplacementSurfaceEvent(event)) {
+      if (isCompactCheckpoint(event)) renderCompactionMarker()
+      requestRender()
      return
    }
    renderEvent(event, { addHistory: false, renderChunks: true })
@@ -1658,9 +1695,35 @@ export function mountTui(ctx: Context, config: Config, runtime: TuiRuntime): voi
  if (existing !== undefined) start(existing)
 }

+const ROOT_DISPOSE_TIMEOUT_MS = 5_000
+
+/**
+ * Dispose the whole application before process exit, with a bounded fallback.
+ * @param ctx - The TUI plugin context whose root owns sibling resources.
+ * @param code - Process status to report.
+ * @param exit - Exit boundary, replaceable by tests.
+ */
+export function disposeRootAndExit(
+  ctx: Context,
+  code: number,
+  exit: (status: number) => void = (status) => { process.exit(status) },
+): void {
+  let exited = false
+  const exitOnce = (): void => {
+    if (exited) return
+    exited = true
+    exit(code)
+  }
+  const timeout = setTimeout(exitOnce, ROOT_DISPOSE_TIMEOUT_MS)
+  void ctx.root.fiber.dispose().then(
+    () => { clearTimeout(timeout); exitOnce() },
+    () => { clearTimeout(timeout); exitOnce() },
+  )
+}
+
 /** Cordis entry point using the process terminal; explicit TUI composition requires a TTY pair. */
 /* v8 ignore start -- production process wiring; fake-terminal tests cover mountTui/createTuiChat,
-   and the tui-agent PTY smoke covers the real entry */
+   and apps/cli PTY smokes cover the real entry */
 export function apply(ctx: Context, config: Config): void {
  if (!process.stdin.isTTY || !process.stdout.isTTY) {
    throw new Error('ui-tui: both stdin and stdout must be TTYs; use the one-shot @deepseek-ai/dsh-cli-demo app for pipes')
@@ -1680,7 +1743,7 @@ export function apply(ctx: Context, config: Config): void {
    initialSkill === undefined ? {} : { initialSkill },
  ), {
    terminal: new ProcessTerminal(),
-    exit: code => process.exit(code),
+    exit: (code) => { disposeRootAndExit(ctx, code) },
    ...resumeHost === undefined ? {} : { handoffResume: (sessionId, cwd) => resumeHost.handoff(sessionId, cwd) },
    ...goodbyeMessage === undefined ? {} : { goodbyeMessage },
  })
--- a/packages/ui/tui/tests/harness.ts
+++ b/packages/ui/tui/tests/harness.ts
@@ -102,10 +102,10 @@ export async function createTuiTestHarness<TerminalType extends Terminal, Exit e
  await ctx.plugin(UserInteractionService)
  await ctx.plugin(TuiPromptService)
  const catalog = options.catalog ?? {
-    providers: [{ id: 'deepseek', name: 'DeepSeek' }],
+    providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
    models: [
-      { provider: 'deepseek', id: 'deepseek-v4-flash', name: 'DeepSeek V4 Flash' },
-      { provider: 'deepseek', id: 'deepseek-v4-pro', name: 'DeepSeek V4 Pro' },
+      { provider: 'deepseek-official', id: 'deepseek-v4-flash', name: 'DeepSeek V4 Flash' },
+      { provider: 'deepseek-official', id: 'deepseek-v4-pro', name: 'DeepSeek V4 Pro' },
    ],
  }
  ctx.provide('tokenMeter', {
@@ -189,7 +189,7 @@ export async function createTuiTestHarness<TerminalType extends Terminal, Exit e
  const cancelled: AgentCancelCause[] = []
  const agent: FakeAgent = {
    id: sessionId,
-    options: options.agentOptions ?? { provider: 'deepseek', model: 'deepseek-v4-flash' },
+    options: options.agentOptions ?? { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
    session,
    inbox: new Inbox(session),
    status: options.status ?? 'idle',
--- a/packages/ui/tui/tests/prompt.spec.ts
+++ b/packages/ui/tui/tests/prompt.spec.ts
@@ -152,8 +152,8 @@ describe('TUI prompt values', () => {
 describe('TUI prompt templates', () => {
  it('interpolates values and removes separators around unavailable values', () => {
    const tokens = parseTuiPromptTemplate('${cwd} ${git/worktree} :: ${missing} ${model}')
-    const values = new Map([['cwd', '/work'], ['model', 'deepseek']])
-    expect(renderTuiPromptTemplate(tokens, name => values.get(name))).toBe('/work :: deepseek')
+    const values = new Map([['cwd', '/work'], ['model', 'deepseek-official']])
+    expect(renderTuiPromptTemplate(tokens, name => values.get(name))).toBe('/work :: deepseek-official')
  })

  it('keeps a trailing literal after the last value', () => {
--- a/packages/ui/tui/tests/snapshots/model-selector-filtered.expected.txt
+++ b/packages/ui/tui/tests/snapshots/model-selector-filtered.expected.txt
@@ -36,9 +36,9 @@ buffer
 14| "        │                                                                          │        "
  style 8-8 fg=bright-magenta
  style 83-83 fg=bright-magenta
-15| "        │ → deepseek/deepseek-v4-pro        DeepSeek V4 Pro                        │        "
+15| "        │ → deepseek-official/deepseek-v4-  DeepSeek V4 Pro                        │        "
  style 8-8 fg=bright-magenta
-  style 10-58 fg=bright-magenta inverse
+  style 10-41 fg=bright-magenta inverse
  style 83-83 fg=bright-magenta
 16| "        │                                                                          │        "
  style 8-8 fg=bright-magenta
--- a/packages/ui/tui/tests/snapshots/model-selector.expected.txt
+++ b/packages/ui/tui/tests/snapshots/model-selector.expected.txt
@@ -36,13 +36,13 @@ buffer
 14| "        │                                                                          │        "
  style 8-8 fg=bright-magenta
  style 83-83 fg=bright-magenta
-15| "        │ → deepseek/deepseek-v4-flash      DeepSeek V4 Flash — current            │        "
+15| "        │ → deepseek-official/deepseek-v4-  DeepSeek V4 Flash — current            │        "
  style 8-8 fg=bright-magenta
-  style 10-70 fg=bright-magenta inverse
+  style 10-41 fg=bright-magenta inverse
  style 83-83 fg=bright-magenta
-16| "        │   deepseek/deepseek-v4-pro        DeepSeek V4 Pro                        │        "
+16| "        │   deepseek-official/deepseek-v4-  DeepSeek V4 Pro                        │        "
  style 8-8 fg=bright-magenta
-  style 36-58 dim
+  style 42-58 dim
  style 83-83 fg=bright-magenta
 17| "        │                                                                          │        "
  style 8-8 fg=bright-magenta
--- a/packages/ui/tui/tests/snapshots/model-switching.expected.txt
+++ b/packages/ui/tui/tests/snapshots/model-switching.expected.txt
@@ -16,8 +16,8 @@ buffer
 5| "Model wait 0.0s                                                                             "
  style 0-14 dim
 6| <blank>
-7| "Model selected: deepseek/deepseek-v4-pro. New steps will use it.                            "
-  style 0-63 dim
+7| "Model selected: deepseek-official/deepseek-v4-pro. New steps will use it.                   "
+  style 0-72 dim
 8| <blank>
 9| "/workspace/project (tui-staging)  deepseek-v4-pro  ↑0 ↓0  0% context"
  style 0-17 fg=bright-magenta bold
--- a/packages/ui/tui/tests/snapshots/resume-sessions-all-workspaces.expected.txt
+++ b/packages/ui/tui/tests/snapshots/resume-sessions-all-workspaces.expected.txt
@@ -31,15 +31,15 @@ buffer
 13| "    unavailable: current session                                                            "
  style 2-31 fg=yellow
 14| "    Other workspace work                                                                    "
-15| "    2024-02-02T00:00:08.000Z · turn 1: completed · deepseek/deepseek-v4-pro                 "
-  style 2-74 dim
+15| "    2024-02-02T00:00:08.000Z · turn 1: completed · deepseek-official/deepseek-v4-pro        "
+  style 2-83 dim
 16| "    persisted · elsewhere-session                                                           "
  style 2-32 dim
 17| "    workspace /workspace/other                                                              "
  style 2-29 dim
 18| "    Resume selector design                                                                  "
-19| "    2024-01-01T00:00:08.000Z · turn 1: completed · deepseek/deepseek-v4-pro                 "
-  style 2-74 dim
+19| "    2024-01-01T00:00:08.000Z · turn 1: completed · deepseek-official/deepseek-v4-pro        "
+  style 2-83 dim
 20| "    persisted · earlier-session                                                             "
  style 2-30 dim
 21| "    workspace /workspace/project                                                            "
--- a/packages/ui/tui/tests/snapshots/resume-sessions.expected.txt
+++ b/packages/ui/tui/tests/snapshots/resume-sessions.expected.txt
@@ -29,8 +29,8 @@ buffer
 12| "    unavailable: current session                                                            "
  style 2-31 fg=yellow
 13| "    Resume selector design                                                                  "
-14| "    2024-01-01T00:00:08.000Z · turn 1: completed · deepseek/deepseek-v4-pro                 "
-  style 2-74 dim
+14| "    2024-01-01T00:00:08.000Z · turn 1: completed · deepseek-official/deepseek-v4-pro        "
+  style 2-83 dim
 15| "    persisted · earlier-session                                                             "
  style 2-30 dim
 16| "                                                                                            "
--- a/packages/ui/tui/tests/snapshots/status-diagnostics-narrow.expected.txt
+++ b/packages/ui/tui/tests/snapshots/status-diagnostics-narrow.expected.txt
@@ -1,7 +1,7 @@
-terminal 56x36 buffer=normal length=44 base=8 viewport=8
+terminal 56x36 buffer=normal length=45 base=9 viewport=9
 lifecycle started=1 stopped=0 progress=inactive
 title "Inspect session diagnostics — DSH snapshot"
-cursor hidden column=7 viewportRow=35 bufferRow=43
+cursor hidden column=7 viewportRow=35 bufferRow=44
 buffer
 0| " DEEPSEEK HARNESS"
  style 1-8 fg=bright-magenta bold
@@ -37,84 +37,87 @@ buffer
  style 0-0 dim
  style 3-12 dim
  style 55-55 dim
-15| "│  Model:      deepseek/deepseek-v4-pro (effort        │"
-  style 0-0 dim
-  style 3-12 dim
-  style 40-55 dim
-16| "│              default; reasoning blocks shown)        │"
-  style 0-0 dim
-  style 15-46 dim
-  style 55-55 dim
-17| "│                                                      │"
-  style 0-0 dim
-  style 55-55 dim
-18| "│  Agent:      idle · 8 events · 1 turn · 1 step · 1   │"
+15| "│  Model:      deepseek-official/deepseek-v4-pro       │"
  style 0-0 dim
  style 3-12 dim
  style 55-55 dim
-19| "│              tool call                               │"
+16| "│              (effort default; reasoning blocks       │"
+  style 0-0 dim
+  style 15-55 dim
+17| "│              shown)                                  │"
+  style 0-0 dim
+  style 15-20 dim
+  style 55-55 dim
+18| "│                                                      │"
  style 0-0 dim
  style 55-55 dim
-20| "│                                                      │"
-  style 0-0 dim
-  style 55-55 dim
-21| "│  Tokens:     1,250 input + 340 output                │"
+19| "│  Agent:      idle · 8 events · 1 turn · 1 step · 1   │"
  style 0-0 dim
  style 3-12 dim
  style 55-55 dim
-22| "│  KV cache:   [███████████░░░░░] 67% hit (3,000 read  │"
+20| "│              tool call                               │"
+  style 0-0 dim
+  style 55-55 dim
+21| "│                                                      │"
+  style 0-0 dim
+  style 55-55 dim
+22| "│  Tokens:     1,250 input + 340 output                │"
+  style 0-0 dim
+  style 3-12 dim
+  style 55-55 dim
+23| "│  KV cache:   [███████████░░░░░] 67% hit (3,000 read  │"
  style 0-0 dim
  style 3-12 dim
  style 15-15 dim
  style 16-26 fg=bright-magenta
  style 27-32 dim
  style 55-55 dim
-23| "│              + 250 write)                            │"
+24| "│              + 250 write)                            │"
  style 0-0 dim
  style 55-55 dim
-24| "│  Context:    [█████░░░░░░░░░░░] 33% used (42,000 /   │"
+25| "│  Context:    [█████░░░░░░░░░░░] 33% used (42,000 /   │"
  style 0-0 dim
  style 3-12 dim
  style 15-15 dim
  style 16-20 fg=bright-magenta
  style 21-32 dim
  style 55-55 dim
-25| "│              128,000)                                │"
+26| "│              128,000)                                │"
  style 0-0 dim
  style 55-55 dim
-26| "│                                                      │"
+27| "│                                                      │"
  style 0-0 dim
  style 55-55 dim
-27| "│  Created:    2026-07-22 09:10:11 UTC                 │"
+28| "│  Created:    2026-07-22 09:10:11 UTC                 │"
  style 0-0 dim
  style 3-12 dim
  style 55-55 dim
-28| "│  Active:     2026-07-22 09:10:11 UTC                 │"
+29| "│  Active:     2026-07-22 09:10:11 UTC                 │"
  style 0-0 dim
  style 3-12 dim
  style 55-55 dim
-29| "╰──────────────────────────────────────────────────────╯"
+30| "╰──────────────────────────────────────────────────────╯"
  style 0-55 dim
-30| <blank>
-31| "System prompt                                           "
+31| <blank>
+32| "System prompt                                           "
  style 0-12 fg=bright-magenta bold
-32| "You are an AI agent powered by the DeepSeek Harness SDK."
-33| "                                                        "
-34| "Paths prefixed with @ are files explicitly referenced by"
-35| "the user. Use the read tool when their contents are     "
-36| "needed; do not claim to have inspected a file before    "
-37| "reading it.                                             "
-38| <blank>
-39| "Registered tools                                        "
+33| "You are an AI agent powered by the DeepSeek Harness SDK."
+34| "                                                        "
+35| "Paths prefixed with @ are files explicitly referenced by"
+36| "the user. Use the read tool when their contents are     "
+37| "needed; do not claim to have inspected a file before    "
+38| "reading it.                                             "
+39| <blank>
+40| "Registered tools                                        "
  style 0-15 fg=bright-magenta bold
-40| "read, write                                             "
-41| <blank>
-42| "/workspace/project (tui-staging)  deepseek-v4-pro  ↑1.3k"
+41| "read, write                                             "
+42| <blank>
+43| "/workspace/project (tui-staging)  deepseek-v4-pro  ↑1.3k"
  style 0-17 fg=bright-magenta bold
  style 18-31 dim
  style 34-48 dim
  style 51-55 dim
-43| " dsh >                                                  "
+44| " dsh >                                                  "
  style 1-3 fg=bright-magenta bold
  style 5-6 dim
  style 7-7 inverse
--- a/packages/ui/tui/tests/snapshots/status-diagnostics.expected.txt
+++ b/packages/ui/tui/tests/snapshots/status-diagnostics.expected.txt
@@ -21,68 +21,68 @@ buffer
  style 0-2 fg=bright-magenta bold underline
 9| "inspect this session                                                                        "
 10| <blank>
-11| "╭─ Session status ───────────────────────────────────────────────────────────────╮"
+11| "╭─ Session status ────────────────────────────────────────────────────────────────────────╮"
  style 0-2 dim
  style 3-16 fg=bright-magenta bold
-  style 17-81 dim
-12| "│  Session:    main-session                                                      │"
+  style 17-90 dim
+12| "│  Session:    main-session                                                               │"
  style 0-0 dim
  style 3-12 dim
-  style 81-81 dim
-13| "│  Title:      Inspect session diagnostics                                       │"
+  style 90-90 dim
+13| "│  Title:      Inspect session diagnostics                                                │"
  style 0-0 dim
  style 3-12 dim
-  style 81-81 dim
-14| "│  Directory:  /workspace/project                                                │"
+  style 90-90 dim
+14| "│  Directory:  /workspace/project                                                         │"
  style 0-0 dim
  style 3-12 dim
-  style 81-81 dim
-15| "│  Model:      deepseek/deepseek-v4-pro (effort default; reasoning blocks shown) │"
+  style 90-90 dim
+15| "│  Model:      deepseek-official/deepseek-v4-pro (effort default; reasoning blocks shown) │"
  style 0-0 dim
  style 3-12 dim
-  style 40-79 dim
-  style 81-81 dim
-16| "│                                                                                │"
+  style 49-88 dim
+  style 90-90 dim
+16| "│                                                                                         │"
  style 0-0 dim
-  style 81-81 dim
-17| "│  Agent:      idle · 8 events · 1 turn · 1 step · 1 tool call                   │"
+  style 90-90 dim
+17| "│  Agent:      idle · 8 events · 1 turn · 1 step · 1 tool call                            │"
  style 0-0 dim
  style 3-12 dim
-  style 81-81 dim
-18| "│                                                                                │"
+  style 90-90 dim
+18| "│                                                                                         │"
  style 0-0 dim
-  style 81-81 dim
-19| "│  Tokens:     1,250 input + 340 output                                          │"
+  style 90-90 dim
+19| "│  Tokens:     1,250 input + 340 output                                                   │"
  style 0-0 dim
  style 3-12 dim
-  style 81-81 dim
-20| "│  KV cache:   [███████████░░░░░] 67% hit (3,000 read + 250 write)               │"
+  style 90-90 dim
+20| "│  KV cache:   [███████████░░░░░] 67% hit (3,000 read + 250 write)                        │"
  style 0-0 dim
  style 3-12 dim
  style 15-15 dim
  style 16-26 fg=bright-magenta
  style 27-32 dim
-  style 81-81 dim
-21| "│  Context:    [█████░░░░░░░░░░░] 33% used (42,000 / 128,000)                    │"
+  style 90-90 dim
+21| "│  Context:    [█████░░░░░░░░░░░] 33% used (42,000 / 128,000)                             │"
  style 0-0 dim
  style 3-12 dim
  style 15-15 dim
  style 16-20 fg=bright-magenta
  style 21-32 dim
-  style 81-81 dim
-22| "│                                                                                │"
+  style 90-90 dim
+22| "│                                                                                         │"
  style 0-0 dim
-  style 81-81 dim
-23| "│  Created:    2026-07-22 09:10:11 UTC                                           │"
+  style 90-90 dim
+23| "│  Created:    2026-07-22 09:10:11 UTC                                                    │"
  style 0-0 dim
  style 3-12 dim
-  style 81-81 dim
-24| "│  Active:     2026-07-22 09:10:11 UTC                                           │"
+  style 90-90 dim
+24| "│  Active:     2026-07-22 09:10:11 UTC                                                    │"
  style 0-0 dim
  style 3-12 dim
-  style 81-81 dim
-25| "╰────────────────────────────────────────────────────────────────────────────────╯"
-  style 0-81 dim
+  style 90-90 dim
+25| "╰─────────────────────────────────────────────────────────────────────────────────────────╯"
+  style 0-90 dim
 26| <blank>
 27| "System prompt                                                                               "
  style 0-12 fg=bright-magenta bold
--- a/packages/ui/tui/tests/snapshots/surface-after-compaction-narrow.expected.txt
+++ b/packages/ui/tui/tests/snapshots/surface-after-compaction-narrow.expected.txt
@@ -1,7 +1,7 @@
-terminal 44x18 buffer=normal length=18 base=0 viewport=0
+terminal 44x18 buffer=normal length=24 base=6 viewport=6
 lifecycle started=1 stopped=0 progress=inactive
 title "DSH snapshot"
-cursor hidden column=7 viewportRow=14 bufferRow=14
+cursor hidden column=7 viewportRow=17 bufferRow=23
 buffer
 0| " DEEPSEEK HARNESS"
  style 1-8 fg=bright-magenta bold
@@ -13,25 +13,39 @@ buffer
 3| <blank>
 4| "Assistant                                   "
  style 0-8 fg=bright-magenta bold underline
-5| "Model wait 0.0s                             "
+5| <blank>
+6| "You                                         "
+  style 0-2 fg=bright-magenta bold underline
+7| "Old prompt with a long line that exercises  "
+8| "wrapping and stays visible after compaction."
+9| <blank>
+10| "● Tool / bash / Run the coverage gate"
+  style 0-36 fg=green
+11| "$ pnpm run test:coverage                    "
+  style 0-23 dim
+12| "/workspace/project                          "
+  style 0-17 dim
+13| "packages/ui/tui 100%                        "
+  style 0-19 dim
+14| "… +1 lines (Ctrl+O to expand)               "
+  style 0-28 dim
+15| "1 test skipped                              "
+  style 0-13 dim
+16| "coverage complete                           "
+  style 0-16 dim
+17| "[exit 0]                                    "
+  style 0-7 dim
+18| "Model wait 0.0s                             "
  style 0-14 dim
-6| <blank>
-7| "Context · workspace-context"
-  style 0-26 dim
-8| "Additional instructions from:               "
-  style 0-43 dim
-9| "nested/AGENTS.md                            "
-  style 0-15 dim
-10| "                                            "
-11| "Render workspace context XML clearly.       "
-  style 0-36 dim
-12| <blank>
-13| "/workspace/project (tui-staging)  deepseek-v"
+19| <blank>
+20| "… earlier context was compacted …           "
+  style 0-32 dim
+21| <blank>
+22| "/workspace/project (tui-staging)  deepseek-v"
  style 0-17 fg=bright-magenta bold
  style 18-31 dim
  style 34-43 dim
-14| " dsh >                                      "
+23| " dsh >                                      "
  style 1-3 fg=bright-magenta bold
  style 5-6 dim
  style 7-7 inverse
-15-17| <blank>
--- a/packages/ui/tui/tests/snapshots/surface-after-compaction-wide.expected.txt
+++ b/packages/ui/tui/tests/snapshots/surface-after-compaction-wide.expected.txt
@@ -1,7 +1,7 @@
 terminal 104x30 buffer=normal length=30 base=0 viewport=0
 lifecycle started=1 stopped=0 progress=inactive
 title "DSH snapshot"
-cursor hidden column=7 viewportRow=13 bufferRow=13
+cursor hidden column=7 viewportRow=22 bufferRow=22
 buffer
 0| " DEEPSEEK HARNESS"
  style 1-8 fg=bright-magenta bold
@@ -13,25 +13,41 @@ buffer
 3| <blank>
 4| "Assistant                                                                                               "
  style 0-8 fg=bright-magenta bold underline
-5| "Model wait 0.0s                                                                                         "
+5| <blank>
+6| "You                                                                                                     "
+  style 0-2 fg=bright-magenta bold underline
+7| "Old prompt with a long line that exercises wrapping and stays visible after compaction.                 "
+8| <blank>
+9| "● Tool / bash / Run the coverage gate"
+  style 0-36 fg=green
+10| "$ pnpm run test:coverage                                                                                "
+  style 0-23 dim
+11| "/workspace/project                                                                                      "
+  style 0-17 dim
+12| "packages/ui/tui 100%                                                                                    "
+  style 0-19 dim
+13| "… +1 lines (Ctrl+O to expand)                                                                           "
+  style 0-28 dim
+14| "1 test skipped                                                                                          "
+  style 0-13 dim
+15| "coverage complete                                                                                       "
+  style 0-16 dim
+16| "[exit 0]                                                                                                "
+  style 0-7 dim
+17| "Model wait 0.0s                                                                                         "
  style 0-14 dim
-6| <blank>
-7| "Context · workspace-context"
-  style 0-26 dim
-8| "Additional instructions from: nested/AGENTS.md                                                          "
-  style 0-45 dim
-9| "                                                                                                        "
-10| "Render workspace context XML clearly.                                                                   "
-  style 0-36 dim
-11| <blank>
-12| "/workspace/project (tui-staging)  deepseek-v4-flash  ↑0 ↓0  0% context"
+18| <blank>
+19| "… earlier context was compacted …                                                                       "
+  style 0-32 dim
+20| <blank>
+21| "/workspace/project (tui-staging)  deepseek-v4-flash  ↑0 ↓0  0% context"
  style 0-17 fg=bright-magenta bold
  style 18-31 dim
  style 34-50 dim
  style 53-57 dim
  style 60-69 dim
-13| " dsh >                                                                                                  "
+22| " dsh >                                                                                                  "
  style 1-3 fg=bright-magenta bold
  style 5-6 dim
  style 7-7 inverse
-14-29| <blank>
+23-29| <blank>
--- a/packages/ui/tui/tests/snapshots/surface-before-compaction.expected.txt
+++ b/packages/ui/tui/tests/snapshots/surface-before-compaction.expected.txt
@@ -1,7 +1,7 @@
 terminal 80x24 buffer=normal length=24 base=0 viewport=0
 lifecycle started=1 stopped=0 progress=inactive
 title "DSH snapshot"
-cursor hidden column=7 viewportRow=20 bufferRow=20
+cursor hidden column=7 viewportRow=21 bufferRow=21
 buffer
 0| " DEEPSEEK HARNESS"
  style 1-8 fg=bright-magenta bold
@@ -16,35 +16,36 @@ buffer
 5| <blank>
 6| "You                                                                             "
  style 0-2 fg=bright-magenta bold underline
-7| "Old prompt with a long line that exercises wrapping before compaction.          "
-8| <blank>
-9| "● Tool / bash / Run the coverage gate"
+7| "Old prompt with a long line that exercises wrapping and stays visible after     "
+8| "compaction.                                                                     "
+9| <blank>
+10| "● Tool / bash / Run the coverage gate"
  style 0-36 fg=green
-10| "$ pnpm run test:coverage                                                        "
+11| "$ pnpm run test:coverage                                                        "
  style 0-23 dim
-11| "/workspace/project                                                              "
+12| "/workspace/project                                                              "
  style 0-17 dim
-12| "packages/ui/tui 100%                                                            "
+13| "packages/ui/tui 100%                                                            "
  style 0-19 dim
-13| "… +1 lines (Ctrl+O to expand)                                                   "
+14| "… +1 lines (Ctrl+O to expand)                                                   "
  style 0-28 dim
-14| "1 test skipped                                                                  "
+15| "1 test skipped                                                                  "
  style 0-13 dim
-15| "coverage complete                                                               "
+16| "coverage complete                                                               "
  style 0-16 dim
-16| "[exit 0]                                                                        "
+17| "[exit 0]                                                                        "
  style 0-7 dim
-17| "Model wait 0.0s                                                                 "
+18| "Model wait 0.0s                                                                 "
  style 0-14 dim
-18| <blank>
-19| "/workspace/project (tui-staging)  deepseek-v4-flash  ↑0 ↓0  0% context"
+19| <blank>
+20| "/workspace/project (tui-staging)  deepseek-v4-flash  ↑0 ↓0  0% context"
  style 0-17 fg=bright-magenta bold
  style 18-31 dim
  style 34-50 dim
  style 53-57 dim
  style 60-69 dim
-20| " dsh >                                                                          "
+21| " dsh >                                                                          "
  style 1-3 fg=bright-magenta bold
  style 5-6 dim
  style 7-7 inverse
-21-23| <blank>
+22-23| <blank>
--- a/packages/ui/tui/tests/snapshots/surface-replayed-compaction.expected.txt
+++ b/packages/ui/tui/tests/snapshots/surface-replayed-compaction.expected.txt
@@ -0,0 +1,53 @@
+terminal 104x30 buffer=normal length=30 base=0 viewport=0
+lifecycle started=1 stopped=0 progress=inactive
+title "DSH snapshot"
+cursor hidden column=7 viewportRow=22 bufferRow=22
+buffer
+0| " DEEPSEEK HARNESS"
+  style 1-8 fg=bright-magenta bold
+  style 10-16 bold
+1| " Snapshot agent ready."
+  style 1-21 dim
+2| " main-session"
+  style 1-12 dim
+3| <blank>
+4| "Assistant                                                                                               "
+  style 0-8 fg=bright-magenta bold underline
+5| <blank>
+6| "You                                                                                                     "
+  style 0-2 fg=bright-magenta bold underline
+7| "Old prompt with a long line that exercises wrapping and stays visible after compaction.                 "
+8| <blank>
+9| "● Tool / bash / Run the coverage gate"
+  style 0-36 fg=green
+10| "$ pnpm run test:coverage                                                                                "
+  style 0-23 dim
+11| "/workspace/project                                                                                      "
+  style 0-17 dim
+12| "packages/ui/tui 100%                                                                                    "
+  style 0-19 dim
+13| "… +1 lines (Ctrl+O to expand)                                                                           "
+  style 0-28 dim
+14| "1 test skipped                                                                                          "
+  style 0-13 dim
+15| "coverage complete                                                                                       "
+  style 0-16 dim
+16| "[exit 0]                                                                                                "
+  style 0-7 dim
+17| "Model wait 0.0s                                                                                         "
+  style 0-14 dim
+18| <blank>
+19| "… earlier context was compacted …                                                                       "
+  style 0-32 dim
+20| <blank>
+21| "/workspace/project (tui-staging)  deepseek-v4-flash  ↑0 ↓0  0% context"
+  style 0-17 fg=bright-magenta bold
+  style 18-31 dim
+  style 34-50 dim
+  style 53-57 dim
+  style 60-69 dim
+22| " dsh >                                                                                                  "
+  style 1-3 fg=bright-magenta bold
+  style 5-6 dim
+  style 7-7 inverse
+23-29| <blank>
--- a/packages/ui/tui/tests/tui.snapshot.ts
+++ b/packages/ui/tui/tests/tui.snapshot.ts
@@ -5,6 +5,7 @@ import { fileURLToPath } from 'node:url'
 import { afterAll, describe, expect, it, vi } from 'vitest'
 import type { Context } from 'cordis'
 import { agentEvents } from '@deepseek-ai/dsh-agent'
+import { COMPACT_CHECKPOINT_SOURCE } from '@deepseek-ai/dsh-compact'
 import { createUserMessage, CallId, type ContentBlock , createMessage, createToolResultMessage } from '@deepseek-ai/dsh-llm'
 import type {} from '@deepseek-ai/dsh-llm-retry'
 import { SessionId, type JsonValue, type Session, type SessionEvent } from '@deepseek-ai/dsh-session'
@@ -50,6 +51,7 @@ const CHECKPOINTS = [
  'surface-before-compaction',
  'surface-after-compaction-narrow',
  'surface-after-compaction-wide',
+  'surface-replayed-compaction',
  'model-selector',
  'model-selector-filtered',
  'model-switching',
@@ -181,6 +183,67 @@ function appendToolResult(
  }, { surfaceOp: 'append' })
 }

+/** Frozen clock for the compaction fixtures; see the live scenario for why. */
+const COMPACTION_FIXTURE_TIME = new Date(2026, 6, 21, 14, 40, 0).getTime()
+
+/** The surface range a compaction checkpoint replaces, with its provenance. */
+interface CompactionRange {
+  start: number
+  end: number
+  sources: number[]
+}
+
+/**
+ * Append one prompt / tool-call / tool-result step, the history a compaction
+ * shadows on the model surface and the transcript must keep showing. The prompt
+ * text is rendered verbatim; the tool card's body comes from `bash`'s static
+ * presenter, so the fixtures pin that the shadowed step's card survives rather
+ * than the result content below.
+ */
+function appendPreCompactionLog(session: Session): CompactionRange {
+  const user = session.append('user/message', createUserMessage({
+    content: [{ type: 'text', text: 'Old prompt with a long line that exercises wrapping and stays visible after compaction.' }],
+    source: { kind: 'user' },
+  }), { surfaceOp: 'append' })
+  const assistant = session.append('assistant/message', {
+    turn: 1,
+    step: 1,
+    message: createMessage({
+      role: 'assistant',
+      content: [{ type: 'tool-call', id: CallId('old-tool'), name: 'bash', arguments: '{}' }],
+      source: {
+        kind: 'model',
+        ...{ provider: 'mock', model: 'deepseek-v4-flash' },
+      },
+    }),
+  }, { surfaceOp: 'append' })
+  session.append('tool/call', { turn: 1, step: 1, callId: CallId('old-tool'), name: 'bash', arguments: '{}' })
+  const result = session.append('tool/result', {
+    turn: 1,
+    step: 1,
+    message: createToolResultMessage({
+      callId: CallId('old-tool'),
+      content: [{ type: 'text', text: 'shadowed step tool output' }],
+      isError: false,
+    }),
+  }, { surfaceOp: 'append' })
+  return { start: user.seq, end: result.seq, sources: [user.seq, assistant.seq, result.seq] }
+}
+
+/** Land a compaction: replace the range with the framed model-only checkpoint. */
+function appendCompactionCheckpoint(session: Session, range: CompactionRange): void {
+  session.append('user/message', createUserMessage({
+    content: [{
+      type: 'text',
+      text: '<context_checkpoint>\nModel-only summary payload that must never reach the transcript.\n</context_checkpoint>',
+    }],
+    source: COMPACT_CHECKPOINT_SOURCE,
+  }), {
+    surfaceOp: { op: 'replace', start: range.start, end: range.end },
+    sourceEventSeqs: range.sources,
+  })
+}
+
 function visualTool(
  name: string,
  call: NonNullable<ToolDefinition['presentCall']>,
@@ -489,7 +552,7 @@ describe('TUI terminal-state snapshots', () => {
          description: 'Audit terminal states from independent angles',
          phases: [
            { title: 'Inspect', detail: 'Map renderer branches' },
-            { title: 'Verify', detail: 'Challenge missing states', provider: 'deepseek', model: 'deepseek-v4-flash' },
+            { title: 'Verify', detail: 'Challenge missing states', provider: 'deepseek-official', model: 'deepseek-v4-flash' },
          ],
        },
        args: { packages: ['ui/tui', 'workflow/tool-workflow'] },
@@ -682,61 +745,22 @@ describe('TUI terminal-state snapshots', () => {
    await disposeSnapshot(harness)
  })

-  it('pins compaction surface replacement and narrow-to-wide reflow', async () => {
+  it('pins preserved history, the compaction marker, and narrow-to-wide reflow', async () => {
    // Freeze the clock: the timing header hides zero-duration buckets, so a
    // real-clock millisecond tick between the fixture appends and the render
    // would flip `Tools 0.0s` in and out of the pinned header.
-    const nowSpy = vi.spyOn(Date, 'now').mockReturnValue(new Date(2026, 6, 21, 14, 40, 0).getTime())
-    let replacementStart = 0
-    let replacementEnd = 0
-    let replacementSources: number[] = []
+    const nowSpy = vi.spyOn(Date, 'now').mockReturnValue(COMPACTION_FIXTURE_TIME)
+    // The awaited setup always invokes beforeMount, so the range the checkpoint
+    // replaces is assigned by the time the appends below need it.
+    let compacted!: CompactionRange
    const harness = await setupSnapshot({
      tools: ADVANCED_CARD_TOOLS,
-      beforeMount(session) {
-        const user = session.append('user/message', createUserMessage({
-          content: [{ type: 'text', text: 'Old prompt with a long line that exercises wrapping before compaction.' }],
-          source: { kind: 'user' },
-        }), { surfaceOp: 'append' })
-        const assistant = session.append('assistant/message', {
-          turn: 1,
-          step: 1,
-          message: createMessage({
-            role: 'assistant',
-            content: [{ type: 'tool-call', id: CallId('old-tool'), name: 'bash', arguments: '{}' }],
-            source: {
-              kind: 'model',
-              ...{ provider: 'mock', model: 'deepseek-v4-flash' },
-            },
-          }),
-        }, { surfaceOp: 'append' })
-        session.append('tool/call', { turn: 1, step: 1, callId: CallId('old-tool'), name: 'bash', arguments: '{}' })
-        const result = session.append('tool/result', {
-          turn: 1,
-          step: 1,
-          message: createToolResultMessage({
-            callId: CallId('old-tool'),
-            content: [{ type: 'text', text: 'obsolete output that must disappear' }],
-            isError: false,
-          }),
-        }, { surfaceOp: 'append' })
-        replacementStart = user.seq
-        replacementEnd = result.seq
-        replacementSources = [user.seq, assistant.seq, result.seq]
-      },
+      beforeMount(session) { compacted = appendPreCompactionLog(session) },
    }, { columns: 80, rows: 24 })
    await checkpoint('surface-before-compaction', harness.terminal, { includeScrollback: true })

    await renderAfter(harness, () => {
-      harness.session.append('user/message', createUserMessage({
-        content: [{
-          type: 'text',
-          text: '<system-reminder>\nAdditional instructions from: nested/AGENTS.md\n\nRender workspace context XML clearly.\n</system-reminder>',
-        }],
-        source: { kind: 'plugin', plugin: 'workspace-context' },
-      }), {
-        surfaceOp: { op: 'replace', start: replacementStart, end: replacementEnd },
-        sourceEventSeqs: replacementSources,
-      })
+      appendCompactionCheckpoint(harness.session, compacted)
      harness.terminal.resize(44, 18)
    })
    await checkpoint('surface-after-compaction-narrow', harness.terminal, { includeScrollback: true })
@@ -747,6 +771,23 @@ describe('TUI terminal-state snapshots', () => {
    nowSpy.mockRestore()
  })

+  // The resume path, which is what regressed for real users: the replacement is
+  // already stored when the terminal mounts, so the transcript comes from replay
+  // rather than from live appends. Pinned against the same log the live scenario
+  // ends on, at its wide size, so the two fixtures are directly comparable.
+  it('pins a stored compaction replayed at mount', async () => {
+    const nowSpy = vi.spyOn(Date, 'now').mockReturnValue(COMPACTION_FIXTURE_TIME)
+    const harness = await setupSnapshot({
+      tools: ADVANCED_CARD_TOOLS,
+      beforeMount(session) {
+        appendCompactionCheckpoint(session, appendPreCompactionLog(session))
+      },
+    }, { columns: 104, rows: 30 })
+    await checkpoint('surface-replayed-compaction', harness.terminal, { includeScrollback: true })
+    await disposeSnapshot(harness)
+    nowSpy.mockRestore()
+  })
+
  it('pins wrapped and explicit multiline shell-prompt input', async () => {
    const harness = await setupSnapshot({}, { columns: 44, rows: 18 })
    await renderAfter(harness, () => {
@@ -826,13 +867,13 @@ describe('TUI terminal-state snapshots', () => {
        { type: 'turn/start', seq: 0, time: Date.parse(`${day}T00:00:01Z`), data: { turn: 1 } },
        { type: 'user/message', seq: 1, time: Date.parse(`${day}T00:00:02Z`), data: createUserMessage({ content: [{ type: 'text', text: 'restore the selector' }], source: { kind: 'user' } }), surfaceOp: 'append' },
        { type: 'step/start', seq: 2, time: Date.parse(`${day}T00:00:03Z`), data: { turn: 1, step: 1 } },
-        { type: 'request/header', seq: 3, time: Date.parse(`${day}T00:00:04Z`), data: { header: { config: { provider: 'deepseek', model: 'deepseek-v4-pro' } }, reason: 'initial' } },
+        { type: 'request/header', seq: 3, time: Date.parse(`${day}T00:00:04Z`), data: { header: { config: { provider: 'deepseek-official', model: 'deepseek-v4-pro' } }, reason: 'initial' } },
        { type: 'assistant/message', seq: 4, time: Date.parse(`${day}T00:00:05Z`), data: {
          turn: 1, step: 1,
          message: createMessage({
            role: 'assistant',
            content: [{ type: 'text', text: 'ready' }],
-            source: { kind: 'model', provider: 'deepseek', model: 'deepseek-v4-pro' },
+            source: { kind: 'model', provider: 'deepseek-official', model: 'deepseek-v4-pro' },
          }),
        }, surfaceOp: 'append' },
        { type: 'step/end', seq: 5, time: Date.parse(`${day}T00:00:06Z`), data: { turn: 1, step: 1 } },
@@ -873,7 +914,7 @@ describe('TUI terminal-state snapshots', () => {
    const harness = await setupSnapshot({
      contextWindow: 128_000,
      contextTokens: 42_000,
-      agentOptions: { provider: 'deepseek', model: 'deepseek-v4-pro' },
+      agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-pro' },
      tools: {
        read: {
          name: 'read',
--- a/packages/ui/tui/tests/tui.spec.ts
+++ b/packages/ui/tui/tests/tui.spec.ts
@@ -9,6 +9,7 @@ import AgentRegistry, {
 } from '@deepseek-ai/dsh-agent'
 import { createUserMessage,
  createToolResultMessage,
+  freezeMessage,
  ReasoningEffortId,
  type LlmCallConfig,
  type LlmModelReasoningInfo,
@@ -16,6 +17,7 @@ import { createUserMessage,
 } from '@deepseek-ai/dsh-llm'
 import { GOAL_CHANGE_VERSION, GoalId, renderGoalChange, type GoalSnapshotChangeMeta } from '@deepseek-ai/dsh-goal'
 import CommandService, { type CommandInvocation } from '@deepseek-ai/dsh-commands'
+import { COMPACT_CHECKPOINT_SOURCE } from '@deepseek-ai/dsh-compact'
 import SessionStore, { SessionId, type JsonValue, type SessionEvent, type SessionHeader, type TurnEndReason } from '@deepseek-ai/dsh-session'
 import type { SessionRecord } from '@deepseek-ai/dsh-session-query'
 import SkillService, { type SkillCatalogSnapshot, type SkillDefinition, type SkillProvider, type SkillSummary } from '@deepseek-ai/dsh-skill'
@@ -26,6 +28,7 @@ import SessionReferenceService, { formatSessionReferenceMention } from '@deepsee
 import type {} from '@deepseek-ai/dsh-llm-retry'
 import {
  createTuiChat,
+  disposeRootAndExit,
  FILE_REFERENCE_PROMPT,
  mountTui,
  renderSkillInvocation,
@@ -235,7 +238,7 @@ describe('goodbye message and /resume', () => {
    ({ version: 0, id: SessionId(id), createdAt, cwd })
  const resumeEvents = (
    title: string,
-    provider = 'deepseek',
+    provider = 'deepseek-official',
    time = 100,
    reason: TurnEndReason = { kind: 'completed' },
  ): SessionEvent[] => [
@@ -307,8 +310,8 @@ describe('goodbye message and /resume', () => {
      sessionPersistence: {
        list: async () => [older, newer, header('foreign-session', 3000, '/elsewhere')],
        load: async id => id === newer.id
-          ? { meta: newer, events: resumeEvents('Newer product work', 'deepseek', 300) }
-          : { meta: older, events: resumeEvents('Older investigation', 'deepseek', 100) },
+          ? { meta: newer, events: resumeEvents('Newer product work', 'deepseek-official', 300) }
+          : { meta: older, events: resumeEvents('Older investigation', 'deepseek-official', 100) },
      },
    })
    result.terminal.send('/resume')
@@ -407,7 +410,7 @@ describe('goodbye message and /resume', () => {
        list: async () => targets,
        load: async id => ({
          meta: targets.find(target => target.id === id)!,
-          events: resumeEvents(`Paged ${id.slice('paged-'.length)}`, 'deepseek', 1000 - Number(id.slice('paged-'.length)) * 10),
+          events: resumeEvents(`Paged ${id.slice('paged-'.length)}`, 'deepseek-official', 1000 - Number(id.slice('paged-'.length)) * 10),
        }),
      },
    })
@@ -463,7 +466,7 @@ describe('goodbye message and /resume', () => {
      cwd: '/workspace',
      sessionPersistence: {
        list: async () => [target],
-        load: async () => ({ meta: target, events: resumeEvents(`Turn ${label}`, 'deepseek', 100, reason) }),
+        load: async () => ({ meta: target, events: resumeEvents(`Turn ${label}`, 'deepseek-official', 100, reason) }),
      },
    })
    result.terminal.send('/resume')
@@ -492,6 +495,41 @@ describe('goodbye message and /resume', () => {
    await dispose(result)
  })

+  it('allows a transient session-query state but rejects a terminal state', async () => {
+    let queryCtx: Context | undefined
+    let listCalls = 0
+    const result = await setup({
+      cwd: '/workspace',
+      async configureContext(ctx) {
+        await ctx.plugin({
+          apply(child: Context) {
+            queryCtx = child
+            child.provide('sessionQuery', {
+              listSessions: async () => { listCalls++; return [] },
+            } as never)
+          },
+        })
+      },
+    })
+    if (queryCtx === undefined) throw new Error('query provider did not mount')
+    const activeState = queryCtx.fiber.state
+    queryCtx.fiber.state = 0
+    result.terminal.send('/resume')
+    result.terminal.send('\r')
+    await tick(); await tick()
+    expect(listCalls).toBe(1)
+    result.terminal.send('\u001B')
+    await tick()
+    queryCtx.fiber.state = 5
+    result.terminal.send('/resume')
+    result.terminal.send('\r')
+    await tick()
+    expect(result.terminal.output).toContain('session query is not mounted')
+    expect(listCalls).toBe(1)
+    queryCtx.fiber.state = activeState
+    await dispose(result)
+  })
+
  it('keeps persisted query records readable without a persistence service', async () => {
    const target = header('query-only-persisted', 10, '/workspace')
    const result = await setup({
@@ -664,7 +702,7 @@ describe('goodbye message and /resume', () => {
  it('falls back to assistant provenance and header creation time for sparse logs', async () => {
    const assistantOnly = header('assistant-route', 20, '/workspace')
    const empty = header('empty-log', 10, '/workspace')
-    const events = resumeEvents('Assistant route', 'deepseek')
+    const events = resumeEvents('Assistant route', 'deepseek-official')
      .filter(event => event.type !== 'request/header')
      .map((event, seq) => ({ ...event, seq })) as SessionEvent[]
    const result = await setup({
@@ -679,7 +717,7 @@ describe('goodbye message and /resume', () => {
    result.terminal.send('/resume')
    result.terminal.send('\r')
    await tick(); await tick()
-    expect(result.terminal.output).toContain('deepseek/model-1')
+    expect(result.terminal.output).toContain('deepseek-official/model-1')
    expect(result.terminal.output).toContain(new Date(empty.createdAt).toISOString())
    await dispose(result)
  })
@@ -2316,7 +2354,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
      contextWindow: 128_000,
      contextTokens: 42_000,
      config: { showReasoning: false },
-      agentOptions: { provider: 'deepseek', model: 'deepseek-v4-pro' },
+      agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-pro' },
      tools: {
        read: {
          name: 'read', description: 'Read a file', parameters: {},
@@ -2364,7 +2402,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
    expect(result.terminal.output).toContain('main-session')
    expect(result.terminal.output).toContain('Inspect status \\x1b]2;unsafe\\x07')
    expect(result.terminal.output).toContain('/workspace/status')
-    expect(result.terminal.output).toContain('deepseek/deepseek-v4-pro (effort default; reasoning blocks')
+    expect(result.terminal.output).toContain('deepseek-official/deepseek-v4-pro (effort default; reasoning blocks')
    expect(result.terminal.output).toContain('hidden)')
    // 6 domain events + the /status invocation's own command/run (open turn: joined directly).
    expect(result.terminal.output).toContain('running · 7 events · 1 turn · 1 step · 2 tool calls')
@@ -3486,7 +3524,7 @@ describe('pi-tui chat lifecycle and transcript', () => {

    const failed = await setup({
      catalog: {
-        providers: [{ id: 'deepseek', name: 'DeepSeek' }],
+        providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
        models: [],
        listModels: () => Promise.reject(new Error('catalog offline')),
        resolveModelInfo: () => Promise.reject(new Error('capacity offline')),
@@ -3502,8 +3540,8 @@ describe('pi-tui chat lifecycle and transcript', () => {

    const reasoningFailed = await setup({
      catalog: {
-        providers: [{ id: 'deepseek', name: 'DeepSeek' }],
-        models: [{ provider: 'deepseek', id: 'model-1', name: 'Model One' }],
+        providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
+        models: [{ provider: 'deepseek-official', id: 'model-1', name: 'Model One' }],
        resolveModelInfo: () => Promise.reject(new Error('reasoning metadata offline')),
      },
    })
@@ -3519,7 +3557,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
    const deferred = Promise.withResolvers<never[]>()
    const result = await setup({
      catalog: {
-        providers: [{ id: 'deepseek', name: 'DeepSeek' }],
+        providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
        models: [],
        listModels: () => deferred.promise,
      },
@@ -3535,7 +3573,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
    const rejected = Promise.withResolvers<never[]>()
    const rejectedResult = await setup({
      catalog: {
-        providers: [{ id: 'deepseek', name: 'DeepSeek' }],
+        providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
        models: [],
        listModels: () => rejected.promise,
      },
@@ -3552,7 +3590,7 @@ describe('pi-tui chat lifecycle and transcript', () => {
    const contextResult = await setup({
      contextTokens: 99,
      catalog: {
-        providers: [{ id: 'deepseek', name: 'DeepSeek' }],
+        providers: [{ id: 'deepseek-official', name: 'DeepSeek' }],
        models: [],
        resolveModelInfo: () => context.promise.then(value => ({ context: value })),
      },
@@ -4269,6 +4307,14 @@ describe('tool cards and surface replay', () => {
      name: 'knownXml', description: '', parameters: {}, output: UNUSED_TOOL_OUTPUT, execute: async () => [],
      presentCall: () => ({ card: 'generic', title: 'Known XML' }),
    },
+    // A web card carries no `content` copy, so it falls back to the raw result
+    // content, which must still render through the dim Markdown path (bold
+    // markers stripped) rather than as bare text.
+    webCard: {
+      name: 'webCard', description: '', parameters: {}, output: UNUSED_TOOL_OUTPUT, execute: async () => [],
+      presentCall: () => ({ card: 'generic', title: 'Fetch page', kind: 'fetch' }),
+      presentResult: () => ({ card: 'web', kind: 'fetch', title: 'https://a.test', url: 'https://a.test', statusCode: 200, truncated: false }),
+    },
  }

  it('uses terminal, diff, generic, fallback, and collapsed tool presentations', async () => {
@@ -4289,6 +4335,7 @@ describe('tool cards and surface replay', () => {
      ['c11', 'terminalResult', '{}'],
      ['c12', 'symbolic', '{}'],
      ['c13', 'knownXml', '{}'],
+      ['c16', 'webCard', '{}'],
    ] as const
    appendAssistant(result.session, [
      { type: 'text', text: 'Calling tools' },
@@ -4382,6 +4429,14 @@ describe('tool cards and surface replay', () => {
        isError: false,
      }),
    }, { surfaceOp: 'append' })
+    result.session.append('tool/result', {
+      turn: 1, step: 1,
+      message: createToolResultMessage({
+        callId: 'c16' as never,
+        content: [{ type: 'text', text: 'Fetched **body** text' }],
+        isError: false,
+      }),
+    }, { surfaceOp: 'append' })
    result.session.append('tool/result', {
      turn: 1,
      step: 1,
@@ -4431,6 +4486,11 @@ describe('tool cards and surface replay', () => {
    expect(output).toContain('Empty card')
    expect(output).toContain('converted terminal')
    expect(output).toContain('<known><value>literal</value></known>')
+    // A web card carries no `content` copy, so it falls back to the raw result
+    // content, which still renders through the dim Markdown path: the bold
+    // markers are stripped rather than shown literally.
+    expect(output).toContain('Fetched body text')
+    expect(output).not.toContain('Fetched **body** text')
    expect(output).toContain('path: /tmp/a.txt')
    expect(output).toContain('line (number="1"): hello')
    expect(output).not.toContain('<result>')
@@ -4555,10 +4615,10 @@ describe('tool cards and surface replay', () => {
    await dispose(result)
  })

-  it('rebuilds after a surface replacement and hides shadowed tool calls', async () => {
+  it('keeps append-origin history and marks a landed compaction, live and on rebuild', async () => {
    const result = await setup({ tools })
    appendUser(result.session, 'old prompt')
-    const assistant = result.session.append('assistant/message', {
+    result.session.append('assistant/message', {
      turn: 1,
      step: 1,
      message: createMessage({
@@ -4581,21 +4641,116 @@ describe('tool cards and surface replay', () => {
        isError: false,
      }),
    }, { surfaceOp: 'append' })
-    const start = result.session.surface.nodes[0] as number
-    result.session.append('user/message', createUserMessage({
-      content: [{ type: 'text', text: 'summary replacement' }],
-      source: { kind: 'plugin', plugin: 'compact' },
-    }), {
-      surfaceOp: { op: 'replace', start, end: toolResult.seq },
-      sourceEventSeqs: [start, assistant.seq, toolResult.seq],
+    // Result pruning rewrites one node's content in place: model-only, and no
+    // boundary in the conversation, so the terminal keeps the full output.
+    const originalResult = toolResult.data.message.content[0]
+    result.session.append('tool/result', {
+      ...toolResult.data,
+      message: freezeMessage({
+        ...toolResult.data.message,
+        content: [{ ...originalResult, content: [{ type: 'text', text: 'pruned result copy' }] }] as [typeof originalResult],
+      }),
+    }, {
+      surfaceOp: { op: 'replace', start: toolResult.seq, end: toolResult.seq },
+      sourceEventSeqs: [toolResult.seq],
    })
+    const nodes = [...result.session.surface.nodes]
+    const checkpoint = result.session.append('user/message', createUserMessage({
+      content: [{ type: 'text', text: '<context_checkpoint>model-only summary payload</context_checkpoint>' }],
+      source: COMPACT_CHECKPOINT_SOURCE,
+    }), {
+      surfaceOp: { op: 'replace', start: nodes[0] as number, end: nodes.at(-1) as number },
+      sourceEventSeqs: nodes,
+    })
+    // A regenerated assistant message replaces one node without summarizing
+    // anything, so it marks no boundary either.
+    const generic = result.session.append('assistant/message', {
+      turn: 1,
+      step: 1,
+      message: createMessage({
+        role: 'assistant',
+        content: [{ type: 'text', text: 'generic replacement copy' }],
+        source: {
+          kind: 'model',
+          ...{ provider: 'mock', model: 'deepseek-v4-flash' },
+        },
+      }),
+    }, { surfaceOp: { op: 'replace', start: checkpoint.seq, end: checkpoint.seq }, sourceEventSeqs: [checkpoint.seq] })
+    // Only a checkpoint carrying the compaction seam's source marks a boundary:
+    // another plugin replacing a node is model-only.
+    result.session.append('user/message', createUserMessage({
+      content: [{ type: 'text', text: 'foreign plugin replacement copy' }],
+      source: { kind: 'plugin', plugin: 'other' },
+    }), { surfaceOp: { op: 'replace', start: generic.seq, end: generic.seq }, sourceEventSeqs: [generic.seq] })
    await tick()

    result.terminal.resize(89)
    await tick()
-    const lastFullRender = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
-    expect(lastFullRender).toContain('summary replacement')
-    expect(lastFullRender).not.toContain('old output')
+    const liveRender = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
+    expect(liveRender).toContain('old prompt')
+    // The shadowed step keeps its card: one call row, one full result, no
+    // second card from the pruned copy.
+    expect(liveRender.split('$ printf hello')).toHaveLength(2)
+    expect(liveRender).toContain('third')
+    expect(liveRender.split('[exit 0]')).toHaveLength(2)
+    expect(liveRender.split('… earlier context was compacted …')).toHaveLength(2)
+    expect(liveRender).not.toContain('model-only summary payload')
+    expect(liveRender).not.toContain('generic replacement copy')
+    expect(liveRender).not.toContain('foreign plugin replacement copy')
+
+    // Ctrl+R toggles reasoning, which rebuilds the transcript from the log; the
+    // replayed projection matches what the live appends produced, including the
+    // shadowed assistant message's tool card.
+    result.terminal.send('\x12')
+    await tick()
+    result.terminal.resize(90)
+    await tick()
+    const replayRender = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
+    expect(replayRender).toContain('old prompt')
+    expect(replayRender.split('$ printf hello')).toHaveLength(2)
+    expect(replayRender).toContain('third')
+    expect(replayRender.split('[exit 0]')).toHaveLength(2)
+    expect(replayRender.split('… earlier context was compacted …')).toHaveLength(2)
+    expect(replayRender).not.toContain('model-only summary payload')
+    expect(replayRender).not.toContain('generic replacement copy')
+    expect(replayRender).not.toContain('foreign plugin replacement copy')
+    await dispose(result)
+  })
+
+  it('replays a stored compaction as preserved history plus its marker', async () => {
+    const result = await setup({
+      beforeMount(session) {
+        appendUser(session, 'prompt before compaction')
+        session.append('assistant/message', {
+          turn: 1,
+          step: 1,
+          message: createMessage({
+            role: 'assistant',
+            content: [{ type: 'text', text: 'reply before compaction' }],
+            source: {
+              kind: 'model',
+              ...{ provider: 'mock', model: 'deepseek-v4-flash' },
+            },
+          }),
+        }, { surfaceOp: 'append' })
+        const nodes = [...session.surface.nodes]
+        session.append('user/message', createUserMessage({
+          content: [{ type: 'text', text: '<context_checkpoint>stored model-only payload</context_checkpoint>' }],
+          source: COMPACT_CHECKPOINT_SOURCE,
+        }), {
+          surfaceOp: { op: 'replace', start: nodes[0] as number, end: nodes.at(-1) as number },
+          sourceEventSeqs: nodes,
+        })
+      },
+    })
+    result.terminal.resize(89)
+    await tick()
+
+    const mounted = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J'))
+    expect(mounted).toContain('prompt before compaction')
+    expect(mounted).toContain('reply before compaction')
+    expect(mounted.split('… earlier context was compacted …')).toHaveLength(2)
+    expect(mounted).not.toContain('stored model-only payload')
    await dispose(result)
  })
 })
@@ -4892,6 +5047,59 @@ describe('TUI extension service', () => {
  })
 })

+describe('application exit', () => {
+  it('disposes the root fiber rather than only the TUI child before exiting', async () => {
+    const rootDispose = vi.fn(() => Promise.resolve())
+    const childDispose = vi.fn(() => Promise.resolve())
+    const ctx = {
+      root: { fiber: { dispose: rootDispose } },
+      fiber: { dispose: childDispose },
+    } as unknown as Context
+    const exit = vi.fn()
+    disposeRootAndExit(ctx, 7, exit)
+    await Promise.resolve()
+    expect(rootDispose).toHaveBeenCalledOnce()
+    expect(childDispose).not.toHaveBeenCalled()
+    expect(exit).toHaveBeenCalledOnce()
+    expect(exit).toHaveBeenCalledWith(7)
+  })
+
+  it('forces exit when root disposal does not settle', async () => {
+    vi.useFakeTimers()
+    try {
+      let settle!: () => void
+      const disposal = new Promise<void>((resolve) => { settle = resolve })
+      const ctx = {
+        root: { fiber: { dispose: () => disposal } },
+      } as unknown as Context
+      const exit = vi.fn()
+      disposeRootAndExit(ctx, 9, exit)
+      await vi.advanceTimersByTimeAsync(4_999)
+      expect(exit).not.toHaveBeenCalled()
+      await vi.advanceTimersByTimeAsync(1)
+      expect(exit).toHaveBeenCalledOnce()
+      expect(exit).toHaveBeenCalledWith(9)
+      settle()
+      await disposal
+      await Promise.resolve()
+      expect(exit).toHaveBeenCalledOnce()
+    } finally {
+      vi.useRealTimers()
+    }
+  })
+
+  it('exits after a rejected root disposal without an unhandled rejection', async () => {
+    const ctx = {
+      root: { fiber: { dispose: () => Promise.reject(new Error('cleanup failed')) } },
+    } as unknown as Context
+    const exit = vi.fn()
+    disposeRootAndExit(ctx, 5, exit)
+    await Promise.resolve()
+    await Promise.resolve()
+    expect(exit).toHaveBeenCalledWith(5)
+  })
+})
+
 describe('terminal mounting', () => {
  it('starts immediately when the configured agent already exists', async () => {
    const ctx = new Context()
--- a/packages/ui/tui/tsconfig.json
+++ b/packages/ui/tui/tsconfig.json
@@ -53,6 +53,9 @@
    {
      "path": "../commands"
    },
+    {
+      "path": "../../compact/compact"
+    },
    {
      "path": "../../skill/skill"
    },