fix(web): return every service a host row injects, and run the browser lane

The browser e2e lane had been failing wholesale since this stack moved the
agent plane into presets, and nothing caught it: 34 of 48 files. Two of the
causes are product defects, not test breakage.

`bashEnv` goes back to the host plane. `apps/cli/src/web.ts` injects it to
publish `DSH_WEB_URL`/`DSH_WEB_MODE`, so the earlier note that "nothing outside
the agent plane injects bashEnv" was simply wrong — behind a preset's `shell`
realm those variables reached no shell at all, and a `dsh web` agent could not
find the address of its own interface. This is the same criterion that returned
`subagents`: a host row that injects a service resolves before any session
exists and has no agent to key by, so the service is host-plane. `tool-bash`
consumes the host registry from inside the preset, which works because an
agent context chains to the host; only the reverse is invisible.

`tool-subagent-report` goes back with it. It is not a tool this agent calls: it
registers a continuable SETUP on the host `subagents` singleton, and that list
is not scope-aware. One copy per mounted preset meant every child was handed
`report` once per live session, so the second registration threw and a cold
subagent resume failed with `subagent-not-resumable` — a diagnostic three
layers removed from the cause.

The lane's own composition facts follow. Skill roots resolve inside a preset
now, a subtree include patches cannot reach, so the scaffold pins the roots'
documented environment fallback for its whole lifetime rather than for the boot
— presets mount per session. Without it the developer's real `~/.dsh/skills`
enters replay requests and goldens while CI sees none. The `apps/cli`
composition test pins `storage-json` for the same reason: unpinned it wrote,
and then read back, the developer's own `~/.dsh/storages/`.

Three tests now address through an agent what they used to read off the root
context, because that is where the thing lives: the tool catalog, the skill
registry, and the token meter. The seeded-history projection baseline asserts
the opposite of what it did — a detached session yields a preset-plane
projection only from a durable checkpoint written while it was live, and this
seed was written straight to persistence and never ran.

Goldens re-recorded for the hero's preset chip and the settings nav entry.

apps/web/tests/scaffold-hermetic.e2e.ts

@@ -3,6 +3,8 @@ import { tmpdir } from 'node:os'
 import { join } from 'node:path'
 import { expect, it } from 'vitest'
 import type {} from '@deepseek-ai/dsh-skill'
+import { SessionId } from '@deepseek-ai/dsh-session'
+import type {} from '@deepseek-ai/dsh-agent-presets'
 import { launchWebScaffold, type WebScaffold } from './scaffold.ts'
 
 async function writeSkill(root: string, name: string): Promise<void> {
@@ -37,10 +39,26 @@ it('isolates replay skill discovery from every ambient host root', async () => {
   let scaffold: WebScaffold | undefined
   try {
     scaffold = await launchWebScaffold()
-    const names = (await scaffold.ctx.skills.list({ cwd: scaffold.workspaceCwd })).map(skill => skill.name)
-    expect(names).not.toContain('ambient-dsh')
-    expect(names).not.toContain('ambient-agents')
-    expect(names).not.toContain('ambient-bundled')
+    const ctx = scaffold.ctx
+    // The skill registry belongs to one agent's preset, behind an `isolate`
+    // realm the host cannot resolve by name — so the roots under test are only
+    // reachable through a composed agent, which is also the only shape that
+    // ever asks. `serviceFor` is the same addressing the gateway's `skill.list`
+    // uses for a browser request about a session.
+    const handle = await ctx.agents.create({
+      sessionId: SessionId('hermetic-skills'),
+      setup: agentCtx => ctx.agentPresets.mount(agentCtx).then(() => undefined),
+    })
+    try {
+      const skills = ctx.agentPresets.serviceFor(handle.agent, 'skills')
+      if (skills === undefined) throw new Error('composed agent mounts no skill registry')
+      const names = (await skills.list({ cwd: scaffold.workspaceCwd })).map(skill => skill.name)
+      expect(names).not.toContain('ambient-dsh')
+      expect(names).not.toContain('ambient-agents')
+      expect(names).not.toContain('ambient-bundled')
+    } finally {
+      await handle.dispose()
+    }
   } finally {
     try {
       await scaffold?.close()

apps/web/tests/scaffold.ts

@@ -249,6 +249,31 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
   // paths at load, and an in-process boot must NEVER touch the developer's
   // real ~/.dsh document or credential file.
   const harnessHome = join(workspaceCwd, '.dsh-home')
+  // Skill discovery is model-visible input, and its roots now resolve inside a
+  // PRESET — a subtree this lane's include patches cannot reach, because the
+  // roster mounts it directly per session rather than as a row of the booted
+  // tree. The row's documented fallback is the environment, so pin that: the
+  // whole scaffold lifetime, not just the boot, since presets mount when a
+  // session is created. Without this a developer's real ~/.dsh/skills silently
+  // enters replay requests and goldens while CI sees none.
+  const skillRootEnvironment = {
+    DSH_HOME: join(workspaceCwd, '.dsh-home'),
+    DSH_AGENTS_HOME: join(workspaceCwd, '.agents-home'),
+    DSH_BUNDLED_SKILL_DIR: join(workspaceCwd, '.bundled-skills'),
+  }
+  const originalSkillRootEnvironment = Object.fromEntries(
+    Object.keys(skillRootEnvironment).map(key => [key, process.env[key]]),
+  )
+  let skillRootEnvironmentRestored = false
+  const restoreSkillRootEnvironment = (): void => {
+    if (skillRootEnvironmentRestored) return
+    skillRootEnvironmentRestored = true
+    for (const [key, value] of Object.entries(originalSkillRootEnvironment)) {
+      if (value === undefined) Reflect.deleteProperty(process.env, key)
+      else process.env[key] = value
+    }
+  }
+  Object.assign(process.env, skillRootEnvironment)
   let persistenceRoot: string
   try {
     persistenceRoot = await mkdtemp(join(tmpdir(), 'dsh-web-e2e-sessions-'))
@@ -418,6 +443,7 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
     if (process.cwd() !== originalCwd) process.chdir(originalCwd)
     const cleanupFailures = await cleanupScaffoldWorld(ctx, workspaceCwd, persistenceRoot)
     restoreCredentialEnvironment()
+    restoreSkillRootEnvironment()
     if (cleanupFailures.length > 0) {
       throw new AggregateError([error, ...cleanupFailures], 'web scaffold setup failed and cleanup was incomplete')
     }
@@ -465,6 +491,7 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
         failures.push(...await cleanupScaffoldWorld(ctx, workspaceCwd, persistenceRoot))
       } finally {
         restoreCredentialEnvironment()
+        restoreSkillRootEnvironment()
       }
       if (failures.length > 0) throw new AggregateError(failures, 'web scaffold teardown failed')
     },

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

@@ -18,6 +18,7 @@ import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
 import { createUserMessage } from '@deepseek-ai/dsh-llm'
 import type { ContentBlock, Message } from '@deepseek-ai/dsh-llm'
 import { deriveEventMessage, SessionId } from '@deepseek-ai/dsh-session'
+import type {} from '@deepseek-ai/dsh-agent-presets'
 import type { SessionEvent } from '@deepseek-ai/dsh-session'
 import type { TokenMeterService } from '@deepseek-ai/dsh-token-meter'
 import { join } from 'node:path'
@@ -170,10 +171,22 @@ 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])
-      const meter = scaffold.ctx.get('tokenMeter')
-      if (meter === undefined) throw new Error('seeded-history requires the composed token meter')
-      const realized = realizeSeedFixture(scaffold, raw, SEED_ID)
-      await seedSession(scaffold, withCompaction(realized, meter), SEED_ID)
+      // The meter belongs to an agent's preset, not to the process — token
+      // accounting is per session. It is used here as a pure pricing function
+      // over fixture content, so a throwaway composition is enough to reach one.
+      const priced = await scaffold.ctx.agents.create({
+        sessionId: SessionId('seeded-history-pricing'),
+        setup: agentCtx => scaffold.ctx.agentPresets.mount(agentCtx).then(() => undefined),
+      })
+      let realizedWithCompaction: string
+      try {
+        const meter = scaffold.ctx.agentPresets.serviceFor(priced.agent, 'tokenMeter')
+        if (meter === undefined) throw new Error('seeded-history requires the composed token meter')
+        realizedWithCompaction = withCompaction(realizeSeedFixture(scaffold, raw, SEED_ID), meter)
+      } finally {
+        await priced.dispose()
+      }
+      await seedSession(scaffold, realizedWithCompaction, SEED_ID)
     }
     browser = await chromium.launch()
     page = await newEnglishPage(browser)
@@ -220,11 +233,17 @@ describe('web e2e: seeded history renders through cold resume', () => {
     const projections = body.result.value?.projections
     expect(projections).toBeDefined()
     expect(projections?.asOfSeq).toBeGreaterThanOrEqual(0)
-    // The seed carries a session/title event: the title unit must serve it.
+    // The seed carries a session/title event: the title unit is host-plane, so
+    // it folds the detached log and serves the value with nothing composed.
     expect(typeof projections?.values.title).toBe('string')
-    // tool-todo is composed but the seed has no todo/write: whole-value null,
-    // key PRESENT (absence would mean the unit never registered).
-    expect(projections?.values).toHaveProperty('todos', null)
+    // `todos` is NOT here, and that is the contract rather than a gap. Its unit
+    // is registered by `tool-todo` inside an agent's preset, so a detached
+    // session yields it from exactly one place: a durable checkpoint written
+    // while the session was live. This seed was written straight to persistence
+    // and never ran, so it recorded none — and the answer no longer depends on
+    // whether some UNRELATED session happens to be composed right now, which is
+    // the whole reason the checkpoint row carries its own view.
+    expect(projections?.values).not.toHaveProperty('todos')
   })
 
   it.skipIf(MODE === 'record')('lists the seeded session cold and renders its history from the log', async () => {

apps/web/tests/shipped-composition.e2e.ts

@@ -11,6 +11,8 @@ import type {} from '@deepseek-ai/dsh-tools'
 import type {} from '@deepseek-ai/dsh-sandbox-policy'
 import type {} from '@deepseek-ai/dsh-user-approval'
 import type {} from '@deepseek-ai/dsh-permission'
+import { SessionId } from '@deepseek-ai/dsh-session'
+import type {} from '@deepseek-ai/dsh-agent-presets'
 import { launchWebScaffold, type WebScaffold } from './scaffold.ts'
 
 /**
@@ -63,11 +65,26 @@ afterEach(async () => {
 
 it('assembles the shipped Web catalog with the confined access default', async () => {
   scaffold = await launchWebScaffold()
-  const names = scaffold.ctx.tools.schemas().map(schema => schema.name).sort()
-  expect(names.filter(name => !RIPGREP_TOOLS.includes(name))).toEqual(EXPECTED_TOOLS)
-  // The packaged ripgrep binary ships with the dependency, so the pair is a
-  // fixed roster member on every host.
-  expect(names.filter(name => RIPGREP_TOOLS.includes(name))).toEqual(RIPGREP_TOOLS)
+  const ctx = scaffold.ctx
+  // The catalog belongs to an AGENT, not to the process: every model-facing row
+  // now lives in a preset mounted under one session's scope, so the global
+  // layer holds nothing and a caller must name the agent to see anything. This
+  // composes from the deployment default — what a session that names no preset
+  // gets — which is the shape this test has always been about.
+  expect(ctx.tools.schemas().map(schema => schema.name)).toEqual([])
+  const handle = await ctx.agents.create({
+    sessionId: SessionId('shipped-composition'),
+    setup: agentCtx => ctx.agentPresets.mount(agentCtx).then(() => undefined),
+  })
+  try {
+    const names = ctx.tools.schemas(handle.agent).map(schema => schema.name).sort()
+    expect(names.filter(name => !RIPGREP_TOOLS.includes(name))).toEqual(EXPECTED_TOOLS)
+    // The packaged ripgrep binary ships with the dependency, so the pair is a
+    // fixed roster member on every host.
+    expect(names.filter(name => RIPGREP_TOOLS.includes(name))).toEqual(RIPGREP_TOOLS)
+  } finally {
+    await handle.dispose()
+  }
   // `workspace-write` is not "the workspace and nothing else": the shared roots
   // helper always admits the temp directories too. Pinning it against an
   // explicit mode keeps the claim independent of this surface's default, and

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

@@ -25,6 +25,10 @@
   - img
   - text: workspace
   - img
+- button "标准模式":
+  - img
+  - text: 标准模式
+  - img
 - textbox "Describe what you want to build"
 - button "Commands":
   - img

apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md

@@ -25,6 +25,10 @@
   - img
   - text: workspace
   - img
+- button "标准模式":
+  - img
+  - text: 标准模式
+  - img
 - textbox "Describe what you want to build"
 - button "Commands":
   - img

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

@@ -1,6 +1,8 @@
 - banner:
   - navigation "Session hierarchy":
     - button "Reply with the single word" [disabled]
+  - img
+  - text: 标准模式
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"

apps/web/tests/snapshots/models-settings/configured.expected.md

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "Agent 预设":
+      - img
+      - text: Agent 预设
   - button "打开配置文件"
   - button "关闭":
     - img

apps/web/tests/snapshots/models-settings/empty.expected.md

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "Agent 预设":
+      - img
+      - text: Agent 预设
   - button "打开配置文件"
   - button "关闭":
     - img

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

@@ -7,6 +7,9 @@
     - button "模型":
       - img
       - text: 模型
+    - button "Agent 预设":
+      - img
+      - text: Agent 预设
   - button "打开配置文件"
   - button "关闭":
     - img

apps/web/tests/snapshots/settings-chrome/dialog.expected.md

@@ -7,10 +7,17 @@
     - button "模型":
       - img
       - text: 模型
+    - button "Agent 预设":
+      - img
+      - text: Agent 预设
   - button "打开配置文件"
   - button "关闭":
     - img
     - text: 关闭
+  - text: Agent 预设 对此后新建的会话生效。运行中的会话保持它开始时的 preset。
+  - button "standard":
+    - text: standard
+    - img
   - text: 权限 选择新会话的默认权限模式
   - button "Workspace Write":
     - text: Workspace Write