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

// 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
// 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
// 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.
import { readFile, writeFile, mkdir } from 'node:fs/promises'
import { fileURLToPath } from 'node:url'
import type { Browser, Page } from 'playwright'
import { chromium } from 'playwright'
import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
import { createUserMessage } from '@deepseek-ai/dsh-llm'
import { SessionId } from '@deepseek-ai/dsh-session'
import { join } from 'node:path'
import {
  assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
  launchWebScaffold, recordFixture, seedSession, watchConsole, webSnapshotMode, type WebScaffold,
} from './scaffold.ts'
import { newEnglishPage, saveFailureShot } from './support.ts'

const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/seeded-history', import.meta.url))
const SEED = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', import.meta.url))
const UI_EXPECTED = fileURLToPath(new URL('./snapshots/seeded-history/ui.expected.md', import.meta.url))
// The command-row golden: the same conversation after one /permission switch,
// which is the only surface that shows a settled command row's copy.
const COMMAND_ROW_EXPECTED = fileURLToPath(new URL('./snapshots/seeded-history/command-row.expected.md', import.meta.url))
const MODE = webSnapshotMode()
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.'

describe('web e2e: seeded history renders through cold resume', () => {
  let scaffold: WebScaffold
  let browser: Browser
  let page: Page
  let tripwire: ReturnType<typeof watchConsole>

  beforeAll(async () => {
    scaffold = await launchWebScaffold({})
    // The workspace-aware flow runs sessions in <workspaceRoot>/workspace
    // (the composer's default draft name); the read-tool targets must live in
    // that session cwd. Pre-creating the directory is safe: create-by-name
    // adopts an existing directory.
    const sessionCwd = join(scaffold.workspaceCwd, 'workspace')
    await mkdir(sessionCwd, { recursive: true })
    await writeFile(join(sessionCwd, 'a.txt'), 'alpha\n')
    await writeFile(join(sessionCwd, 'b.txt'), 'beta\n')
    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)
    }
    browser = await chromium.launch()
    page = await newEnglishPage(browser)
    tripwire = watchConsole(page)
    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
  }, 120_000)

  afterAll(async () => {
    await browser?.close()
    await scaffold?.close()
  })

  it.skipIf(MODE !== 'record')('records the seed turn live through the composer', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-record'))
    const input = page.locator('textarea').first()
    await input.waitFor({ timeout: 10_000 })
    const settled = scaffold.whenTurnSettled()
    await input.fill(PROMPT)
    await input.press('Enter')
    const sessionId = await settled
    await recordFixture(scaffold, sessionId, SEED)
  }, 200_000)

  it.skipIf(MODE === 'record')('serves the projections baseline on the real composition tail page', async () => {
    // Composition regression tripwire: the projection registry must be a row
    // in the SHIPPED cordis.yml — with it absent every domain unit's optional
    // injection stays silent and this block disappears (no titles/todos on
    // the web), while fixture-level suites stay green. Assert through the
    // real HTTP wire against the booted real host.
    const response = await fetch(`${scaffold.baseUrl}/api/session.history`, {
      method: 'POST',
      headers: { 'content-type': 'application/json' },
      body: JSON.stringify({
        type: 'client-request', rpcId: 'seeded-projections', method: 'session.history',
        payload: { sessionId: SEED_ID },
      }),
    })
    expect(response.ok).toBe(true)
    const body = await response.json() as {
      result: { ok: boolean; value?: { projections?: { asOfSeq: number; values: Record<string, unknown> } } }
    }
    expect(body.result.ok).toBe(true)
    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.
    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)
  })

  it.skipIf(MODE === 'record')('lists the seeded session cold and renders its history from the log', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-history'))
    // The sidebar tree collapses workspace groups by default: click the group
    // row (treeitem 0) to expand, then the revealed session row.
    const groupRow = page.locator('[role="treeitem"]').first()
    await groupRow.waitFor({ timeout: 15_000 })
    await groupRow.click()
    const sessionRow = page.locator('[role="treeitem"]').nth(1)
    await sessionRow.waitFor({ timeout: 10_000 })
    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)
    // 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)

    const agent = scaffold.ctx.agents.get(SessionId(SEED_ID))
    if (agent === undefined) throw new Error('seeded session did not attach an agent')
    agent.inject(createUserMessage({
      content: [{
        type: 'text',
        text: '<system-reminder>\n'
          + 'The following workspace instructions may be relevant to your work. '
          + 'Use them as guidance when applicable.\n\n'
          + Array.from({ length: 24 }, (_, index) => `Instruction ${index + 1}: preserve the logged context contract.`).join('\n')
          + '\n</system-reminder>',
      }],
      source: {
        kind: 'workspace-instructions',
        baseline: true,
        changes: [{
          action: 'set',
          scope: '.\u0000AGENTS.md',
          path: 'AGENTS.md',
          digest: 'context-injection-browser-snapshot',
        }],
      },
    }))
    await page.getByRole('button', { name: 'Context injection' }).waitFor({ timeout: 10_000 })
  }, 60_000)

  it.skipIf(MODE === 'record')('matches the historical conversation aria golden', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-aria'))
    // This scenario deliberately leaves the LLM seam open to prove zero
    // model calls. History still restores the routed id, but without an
    // advertised catalog row the selector prompts for a listed replacement.
    await page.getByRole('button', { name: 'Select model', exact: true })
      .waitFor({ timeout: 10_000 })
    const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd))
      .split(SEED_ID).join('{{seededId}}')
    await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
  })

  it.skipIf(MODE === 'record')('matches the Figma context disclosure geometry', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-context-injection'))
    const disclosure = page.getByRole('button', { name: 'Context injection' })
    expect(await disclosure.getAttribute('aria-expanded')).toBe('false')
    const collapsedIcon = disclosure.locator('svg').first()
    const collapsedIconBox = await collapsedIcon.boundingBox()
    expect(collapsedIconBox?.width).toBe(14)
    expect(collapsedIconBox?.height).toBe(14)

    await disclosure.click()
    await expect.poll(() => disclosure.getAttribute('aria-expanded')).toBe('true')
    const body = page.locator('[data-context-injection-body]')
    await body.waitFor({ timeout: 5_000 })
    const headerBox = await disclosure.boundingBox()
    const bodyBox = await body.boundingBox()
    if (headerBox === null || bodyBox === null) throw new Error('context disclosure geometry is not measurable')
    expect(headerBox.height).toBe(24)
    expect(bodyBox.x - headerBox.x).toBe(22)
    expect(bodyBox.y - headerBox.y - headerBox.height).toBe(4)
    expect(bodyBox.height).toBe(141)

    const style = await body.evaluate((element) => {
      const computed = getComputedStyle(element)
      return {
        backgroundColor: computed.backgroundColor,
        borderRadius: computed.borderRadius,
        color: computed.color,
        fontSize: computed.fontSize,
        lineHeight: computed.lineHeight,
        padding: [
          computed.paddingTop,
          computed.paddingRight,
          computed.paddingBottom,
          computed.paddingLeft,
        ],
        scrolls: element.scrollHeight > element.clientHeight,
      }
    })
    expect(style).toEqual({
      backgroundColor: 'rgb(249, 250, 251)',
      borderRadius: '8px',
      color: 'rgb(129, 133, 140)',
      fontSize: '11px',
      lineHeight: '16px',
      padding: ['10px', '16px', '12px', '12px'],
      scrolls: true,
    })

    await disclosure.click()
    await expect.poll(() => disclosure.getAttribute('aria-expanded')).toBe('false')
  })

  it.skipIf(MODE === 'record')('file-path tool rows rebuilt from the cold log stay details-inert', async () => {
    onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-toolrow'))
    // Interaction over cold-resumed history: read summaries are host-open
    // file links (not expand-in-place / not details). Runs after the golden
    // capture; still zero model calls.
    const fileLink = page.locator('[data-variant="read"] button').first()
    await fileLink.waitFor({ timeout: 10_000 })
    const frame = page.locator('[style*="grid-template-columns"]').first()
    expect(await frame.getAttribute('data-details-collapsed')).toBe('true')
    await fileLink.click()
    await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true')
    // Path label survives from the recorded args (a.txt).
    await expect.poll(() => page.getByText('a.txt', { exact: false }).count(), { timeout: 5_000 }).toBeGreaterThan(0)
  })

  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
    // model call, so the settled row renders keylessly over this cold history.
    // The row copy is the assertion: `permission · preset workspace-write`,
    // where neither half repeats the other (the dispatched `/` and its
    // argument stay out of the title, and the settlement text never restates
    // the command's own name).
    await page.getByRole('button', { name: 'Access mode, current: Full access' }).click()
    await page.getByRole('menuitem', { name: 'Workspace Write' }).click()
    await page.getByRole('button', { name: 'Access mode, current: Workspace Write' }).waitFor({ timeout: 10_000 })
    // Scoped to the row itself, so unrelated page text that happens to read
    // `permission` (a future resident slash menu) cannot satisfy or break it.
    const row = page.locator('[data-variant="others"]').filter({ hasText: 'preset workspace-write' })
    await expect.poll(() => row.count(), { timeout: 10_000 }).toBe(1)
    expect(await row.getByText('permission', { exact: true }).count()).toBe(1)
    expect(await row.getByText('/permission workspace-write', { exact: true }).count()).toBe(0)
    const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd))
      .split(SEED_ID).join('{{seededId}}')
    await compareOrRefreshGolden(COMMAND_ROW_EXPECTED, snapshot, MODE)
  }, 60_000)

  it.skipIf(MODE === 'record')('issued zero model calls and stayed clean', async () => {
    // No replay fixture was installed and the llm seam is open — any stray
    // stream would have failed the turn loudly. Cleanliness pins the wire.
    expect(tripwire.pageErrors).toEqual([])
    expect(tripwire.warnings).toEqual([])
    await assertFixtureInventory(SNAPSHOT_DIR, ['command-row.expected.md', 'seed.jsonl', 'ui.expected.md'])
  })
})