Merge remote-tracking branch 'origin/master' into worktree-session-hover-menu-fix

apps/web/tests/scaffold.ts

@@ -11,13 +11,14 @@
 // masking its credential, without making a model call.
 //
 // Composition divergences from `dsh web`, all deliberate, all via include
-// patches after the shipped surface overlay: temp persistenceRoot; local skill
-// roots confined to the temp workspace; workspace-context disabled (recorded
-// fixtures must not embed this repo's AGENTS.md); session-title-llm disabled
-// (its fire-and-forget title call would race the loop for the session's replay
-// cursor); webserver pinned to port 0 with the built dist; ordinary keyless
-// modes disable llm-deepseek and fill the open llm seam post-boot with
-// installLlmReplay on the settled root ctx
+// patches after the shipped surface overlay, over the SAME tree (never a
+// second yml): temp persistenceRoot; host-level skill roots confined to the
+// temp workspace while project skill discovery remains real; workspace-context
+// disabled (recorded fixtures must not embed this repo's AGENTS.md);
+// session-title-llm disabled (its fire-and-forget title call would race the
+// loop for the session's replay cursor); webserver pinned to port 0 with the
+// built dist; ordinary keyless modes disable llm-deepseek and fill the open
+// llm seam post-boot with installLlmReplay on the settled root ctx
 // (the plugin-row path discards the ReplayHandle; the direct install keeps
 // assertConsumed for the teardown fixture-consumption check).
 import { existsSync } from 'node:fs'

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

@@ -1,11 +1,12 @@
 // Web e2e scenario: seeded history. A recorded session seeded cold through
 // the REAL persistence API renders purely from the log — the surface nothing
 // else covers: sidebar cold listing, the implicit resume/attach inside the
-// history RPC, history-page tool views, and the client fold of historical
+// history RPC, history-page tool views, and the client's log-ordered transcript
 // events — with ZERO model calls in replay (no replay fixture; a stray stream
 // fails loud on the open llm seam). The cold session also carries the one
 // keyless command-row surface: an Access-chip pick runs `/permission` on the
-// host, so the settled row's copy has a golden here. The seed is a recorded fixture under the
+// host, so the settled row's copy has a golden here. The seed is a recorded
+// fixture under the
 // same record discipline as every other: DSH_SNAPSHOT=record drives the turn
 // live through the composer (real read tool against seeded workspace files)
 // and harvests seed.jsonl; replay/refresh seed it cold and only render.
@@ -34,6 +35,90 @@ const SEED_ID = 'seeded-history-web-e2e'
 
 const PROMPT = 'Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop.'
 
+/**
+ * Append a complete, valid compaction transaction over the recorded turn's own
+ * surface. The recording stays model-authentic and reusable; replay adds this
+ * deterministic condition before seeding it cold, so the scenario pins the bug
+ * this change fixes — a landed compaction must not erase history the reader
+ * already saw — through the real host and the real browser.
+ * @param raw - the committed seed fixture text.
+ * @returns the fixture with a compacted turn appended.
+ */
+function withCompaction(raw: string): string {
+  const lines = raw.trimEnd().split('\n')
+  const events = lines.slice(1).map(line => JSON.parse(line) as {
+    type: string
+    seq: number
+    time: number
+    surfaceOp?: unknown
+    data?: { turn?: unknown }
+  })
+  const surfaceSeqs = events
+    .filter(event => event.surfaceOp === 'append'
+      && (event.type === 'user/message'
+        || event.type === 'assistant/message'
+        || event.type === 'tool/result'
+        || event.type === 'steering/message'))
+    .map(event => event.seq)
+  const first = surfaceSeqs[0]
+  const last = surfaceSeqs.at(-1)
+  const tail = events.at(-1)
+  if (first === undefined || last === undefined || tail === undefined) {
+    throw new Error('seeded-history compaction requires a non-empty closed surface')
+  }
+  // The transaction opens the turn after the recording's last closed one; read
+  // it from the fixture so a re-recording with a different turn count stays
+  // valid instead of appending a duplicate turn number.
+  const lastTurn = events.filter(event => event.type === 'turn/end').at(-1)?.data?.turn
+  if (typeof lastTurn !== 'number') {
+    throw new Error('seeded-history compaction requires a recording ending on a closed turn')
+  }
+  const turn = lastTurn + 1
+  let seq = tail.seq + 1
+  let time = tail.time + 1
+  /**
+   * Append one event at the next seq/time.
+   * @param event - the event body, without seq/time.
+   * @returns the seq it took, so provenance cites the push instead of arithmetic over the push order below.
+   */
+  const at = (event: Record<string, unknown>): number => {
+    const taken = seq++
+    lines.push(JSON.stringify({ ...event, seq: taken, time: time++ }))
+    return taken
+  }
+  at({ type: 'turn/start', data: { turn, trigger: { kind: 'injection', source: { kind: 'plugin', plugin: 'compact' } } } })
+  const startSeq = at({ type: 'compact/start', data: { turn } })
+  const summarySeq = at({
+    type: 'compact/summary',
+    data: {
+      summary: [{
+        type: 'text',
+        text: '## Cold resume compact summary\n\n- The exact summary remains available.',
+      }],
+      shadowedRange: { start: first, end: last },
+      shadowedSeqs: surfaceSeqs,
+      shadowedTokenCount: 10_000,
+      provider: 'snapshot',
+      model: 'snapshot-compactor',
+    },
+  })
+  at({
+    type: 'user/message',
+    data: {
+      content: [{
+        type: 'text',
+        text: '<context_checkpoint>Model-only compact checkpoint.</context_checkpoint>',
+      }],
+      source: { kind: 'plugin', plugin: 'compact' },
+    },
+    surfaceOp: { op: 'replace', start: first, end: last },
+    sourceEventSeqs: [startSeq, summarySeq, ...surfaceSeqs],
+  })
+  at({ type: 'compact/end', data: { turn } })
+  at({ type: 'turn/end', data: { turn, reason: { kind: 'completed' } } })
+  return `${lines.join('\n')}\n`
+}
+
 describe('web e2e: seeded history renders through cold resume', () => {
   let scaffold: WebScaffold
   let browser: Browser
@@ -53,7 +138,7 @@ describe('web e2e: seeded history renders through cold resume', () => {
     if (MODE !== 'record') {
       const raw = await readFile(SEED, 'utf8')
       expect(fixtureUserPrompts(raw), 'seed fixture must carry exactly the drive prompt').toEqual([PROMPT])
-      await seedSession(scaffold, raw, SEED_ID)
+      await seedSession(scaffold, withCompaction(raw), SEED_ID)
     }
     browser = await chromium.launch()
     page = await newEnglishPage(browser)
@@ -119,11 +204,15 @@ describe('web e2e: seeded history renders through cold resume', () => {
     await sessionRow.click()
     // Settled barrier for history: the recorded final assistant text renders.
     await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 15_000 }).toBe(1)
+    await expect.poll(() => page.getByText('Context compacted', { exact: true }).count(), { timeout: 10_000 }).toBe(1)
     // Tool cards render from logged tool/call + tool/result alone (views are
     // host-recomputed per page; the generic card is the documented default).
     const toolRows = page.locator('[data-variant], [data-sample]')
     await expect.poll(() => toolRows.count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(2)
     expect(await page.getByText('a.txt', { exact: false }).count()).toBeGreaterThan(0)
+    // The bug this fixes: the compaction shadowed the whole recorded surface on
+    // the model side, and the prompt and full tool output are still on screen.
+    expect(await page.getByText(PROMPT, { exact: true }).count()).toBe(1)
 
     const agent = scaffold.ctx.agents.get(SessionId(SEED_ID))
     if (agent === undefined) throw new Error('seeded session did not attach an agent')
@@ -230,6 +319,22 @@ describe('web e2e: seeded history renders through cold resume', () => {
     await expect.poll(() => page.getByText('a.txt', { exact: false }).count(), { timeout: 5_000 }).toBeGreaterThan(0)
   })
 
+  it.skipIf(MODE === 'record')('expands the cold-resumed compact summary', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-compaction'))
+    const marker = page.getByRole('button', { name: /Context compacted/ })
+    await marker.waitFor({ timeout: 10_000 })
+    expect(await marker.getAttribute('aria-expanded')).toBe('false')
+    await marker.click()
+    await expect.poll(() => marker.getAttribute('aria-expanded'), { timeout: 5_000 }).toBe('true')
+    await expect.poll(() => page.getByRole('heading', { name: 'Cold resume compact summary' }).count(), {
+      timeout: 5_000,
+    }).toBe(1)
+    expect(await page.getByText('The exact summary remains available.', { exact: false }).count()).toBeGreaterThan(0)
+    // Restore the shared page state for any later case.
+    await marker.click()
+    await expect.poll(() => marker.getAttribute('aria-expanded'), { timeout: 5_000 }).toBe('false')
+  })
+
   it.skipIf(MODE === 'record')('an Access-chip switch lands one command row: bare name, non-repeating settlement text', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-command-row'))
     // The Access chip submits `/permission <preset>` — a host command with no

apps/web/tests/smoke-real.e2e.ts

@@ -163,6 +163,8 @@ describe('dsh web keyless CLI smoke', () => {
         env: {
           ...process.env,
           DEEPSEEK_API_KEY: 'keyless-web-no-call',
+          DSH_HOME: join(sessionsDir, '.dsh'),
+          DSH_AGENTS_HOME: join(sessionsDir, '.agents'),
           TSX_TSCONFIG_PATH: join(REPO_ROOT, 'tsconfig.json'),
         },
         stdio: ['ignore', 'pipe', 'pipe'],
@@ -226,6 +228,7 @@ describe('dsh web keyless CLI smoke', () => {
           DEEPSEEK_API_KEY: 'keyless-web-workspace',
           DEEPSEEK_BASE_URL: `http://127.0.0.1:${address.port}`,
           DSH_HOME: join(workspace, '.dsh'),
+          DSH_AGENTS_HOME: join(workspace, '.agents'),
           TSX_TSCONFIG_PATH: join(REPO_ROOT, 'tsconfig.json'),
         },
         stdio: ['ignore', 'pipe', 'pipe'],
@@ -245,6 +248,8 @@ describe('dsh web keyless CLI smoke', () => {
           setTimeout(() => { reject(new Error('provider request not received in 10s')) }, 10_000).unref()
         }),
       ])
+      expect(captured.messages?.some(message =>
+        message.role === 'user' && message.content?.includes('<available_skills>'))).toBe(false)
       const workspaceMessage = captured.messages?.find(message =>
         message.role === 'user' && message.content?.includes('web-workspace-context-probe'))
       expect(workspaceMessage).toMatchInlineSnapshot(`
@@ -413,6 +418,7 @@ describe('dsh web keyless CLI smoke', () => {
           DEEPSEEK_BASE_URL: `http://127.0.0.1:${address.port}`,
           DSH_TOOLS_MODE: 'code',
           DSH_HOME: join(workspace, '.dsh'),
+          DSH_AGENTS_HOME: join(workspace, '.agents'),
           TSX_TSCONFIG_PATH: join(REPO_ROOT, 'tsconfig.json'),
         },
         stdio: ['ignore', 'pipe', 'pipe'],
@@ -461,8 +467,8 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
     sessionsDir = mkdtempSync(join(tmpdir(), 'dsh-web-w5-'))
     const port = await probeFreePort()
     // tsx boot mirrors demo:web — lib/ may be unbuilt in this worktree. Isolate
-    // the global Harness home inside the temp world; tsx also needs the repo's
-    // loader and tsconfig paths pointed at explicitly.
+    // the host-level Harness and shared-agent homes inside the temp world; tsx
+    // also needs the repo's loader and tsconfig paths pointed at explicitly.
     const tsxLoader = pathToFileURL(createRequire(join(REPO_ROOT, 'package.json')).resolve('tsx')).href
     child = spawn(
       process.execPath,
@@ -472,6 +478,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
         env: {
           ...process.env,
           DSH_HOME: join(sessionsDir, '.dsh'),
+          DSH_AGENTS_HOME: join(sessionsDir, '.agents'),
           TSX_TSCONFIG_PATH: join(REPO_ROOT, 'tsconfig.json'),
         },
         stdio: ['ignore', 'pipe', 'pipe'],

apps/web/tests/snapshots/code-mode-round/ui.expected.md

@@ -42,4 +42,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 52% Input 17.2K tok · Output 252 tok
+- text: 1 turns · 2 steps Tool call {{duration}} Context 7% of 128K Cache hit 52% Input 17.2K tok · Output 252 tok

apps/web/tests/snapshots/cordis-tool-round/ui.expected.md

@@ -59,4 +59,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 4 steps Tool call {{duration}} Cache hit 77% Input 66.5K tok · Output 312 tok
+- text: 1 turns · 4 steps Tool call {{duration}} Context 13% of 128K Cache hit 77% Input 66.5K tok · Output 312 tok

apps/web/tests/snapshots/fresh-round-trip/ui.expected.md

@@ -39,4 +39,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 99% Input 15.7K tok · Output 111 tok
+- text: 1 turns · 2 steps Tool call {{duration}} Context 6% of 128K Cache hit 99% Input 15.7K tok · Output 111 tok

apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md

@@ -31,4 +31,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 1 steps Cache hit 99% Input 7.8K tok · Output 21 tok
+- text: 1 turns · 1 steps Context 6% of 128K Cache hit 99% Input 7.8K tok · Output 21 tok

apps/web/tests/snapshots/live-interactions/retry.expected.md

@@ -33,4 +33,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 1 steps Cache hit 99% Input 7.8K tok · Output 79 tok
+- text: 1 turns · 1 steps Context 6% of 128K Cache hit 99% Input 7.8K tok · Output 79 tok

apps/web/tests/snapshots/onboarding-deepseek-config/welcome.expected.md

@@ -1,10 +1,9 @@
 - region "内测声明":
   - heading "内测声明" [level=2]
-  - paragraph: 感谢您愿意拨冗试用 DeepSeek Harness。
-  - paragraph: 目前的版本仍处于内部测试阶段，功能仍待完善，体验难免有些粗糙。
+  - paragraph: 感谢您愿意拨冗试用 DeepSeek Harness。当前版本仍处于内部测试阶段，功能仍待完善，体验难免有些粗糙。
   - blockquote: “如切如磋，如琢如磨。” 产品的成长，离不开一次次真实的碰撞与坦诚的反馈。您在真实使用中发现的问题，也可能促使我们重新审视，甚至推翻已有的设计。
   - paragraph:
-    - text: 我们尤其希望听见那些失败、困惑与不顺手的时刻——
+    - text: 为了帮助我们更准确地还原您真实使用中的问题，内测版本默认会上传所有 Session Log；如需关闭，可以设置环境变量 DSH_TELEMETRY_DISABLED=1。另外，
     - strong: 如果您有任何反馈与建议，请在企业微信群中留言告诉我们
     - text: 。每一条反馈，都会帮助我们把它打磨得更好。
   - button "继续"

apps/web/tests/snapshots/plan-review/approved.expected.md

@@ -44,4 +44,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 51% Input 10.2K tok · Output 346 tok
+- text: 1 turns · 2 steps Tool call {{duration}} Context 4% of 128K Cache hit 51% Input 10.2K tok · Output 346 tok

apps/web/tests/snapshots/question-composer/answered.expected.md

@@ -39,4 +39,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 95% Input 8.6K tok · Output 180 tok
+- text: 1 turns · 2 steps Tool call {{duration}} Context 3% of 128K Cache hit 95% Input 8.6K tok · Output 180 tok

apps/web/tests/snapshots/seeded-history/command-row.expected.md

@@ -29,6 +29,9 @@
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}}
+- button "Context compacted View compaction summary":
+  - img
+  - text: Context compacted View compaction summary
 - button "Context injection":
   - img
   - img

apps/web/tests/snapshots/seeded-history/ui.expected.md

@@ -29,6 +29,9 @@
 - button "Branch into a new conversation":
   - img
 - text: 7/25 {{clock}}
+- button "Context compacted View compaction summary":
+  - img
+  - text: Context compacted View compaction summary
 - button "Context injection":
   - img
   - img

apps/web/tests/snapshots/steering/settled.expected.md

@@ -40,4 +40,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 156 tok
+- text: 1 turns · 2 steps Tool call {{duration}} Context 6% of 128K Cache hit 98% Input 15.8K tok · Output 156 tok

apps/web/tests/snapshots/web-search-round/ui.expected.md

@@ -34,4 +34,4 @@
   - text: DeepSeek-V4-Flash
   - img
 - button "Send message" [disabled]
-- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 0% Input 22 tok · Output 7 tok
+- text: 1 turns · 2 steps Tool call {{duration}} Context 0% of 128K Cache hit 0% Input 22 tok · Output 7 tok