Merge remote-tracking branch 'origin/master' into worktree/custom-deepseek-models
# Conflicts: # apps/web/tests/snapshots/message-actions/ui.expected.md # apps/web/tests/snapshots/seeded-history/command-row.expected.md # apps/web/tests/snapshots/seeded-history/ui.expected.md # packages/client/ui-model/README.i18n.yaml # packages/client/ui-model/README.md # packages/client/ui-model/README.zh.md # packages/client/ui-model/tests/model-select.spec.tsx # packages/host/apiproxy/README.i18n.yaml
This commit is contained in:
Yichen Jiang
@@ -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
|
||||
@@ -42,7 +127,7 @@ describe('web e2e: seeded history renders through cold resume', () => {
|
||||
|
||||
beforeAll(async () => {
|
||||
scaffold = await launchWebScaffold({})
|
||||
// The workspace-aware flow runs sessions in <workspaceRoot>/workspace
|
||||
// The workspace-aware flow runs sessions in <workspaceCwd>/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.
|
||||
@@ -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')
|
||||
@@ -229,28 +318,65 @@ 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
|
||||
// model call, so the settled row renders keylessly over this cold history.
|
||||
// The row copy is the assertion: `permission · preset workspace-write`,
|
||||
// The row copy is the assertion: `permission · preset read-only`,
|
||||
// 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 })
|
||||
await page.getByRole('button', { name: 'Access mode, current: Workspace Write' }).click()
|
||||
await page.getByRole('menuitem', { name: 'Read Only' }).click()
|
||||
await page.getByRole('button', { name: 'Access mode, current: Read Only' }).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' })
|
||||
const row = page.locator('[data-variant="others"]').filter({ hasText: 'preset read-only' })
|
||||
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)
|
||||
expect(await row.getByText('/permission read-only', { 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')('fits short injected context without a scrollport', async () => {
|
||||
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: 'Short injected context.' }],
|
||||
source: { kind: 'plugin', plugin: 'fixture' },
|
||||
}))
|
||||
|
||||
const disclosures = page.getByRole('button', { name: 'Context injection' })
|
||||
await expect.poll(() => disclosures.count(), { timeout: 10_000 }).toBe(2)
|
||||
const disclosure = disclosures.nth(1)
|
||||
await disclosure.click()
|
||||
await expect.poll(() => disclosure.getAttribute('aria-expanded')).toBe('true')
|
||||
|
||||
const body = page.locator('[data-context-injection-body]')
|
||||
const bodyBox = await body.boundingBox()
|
||||
if (bodyBox === null) throw new Error('short context disclosure geometry is not measurable')
|
||||
expect(bodyBox.height).toBeLessThan(141)
|
||||
expect(await body.evaluate(element => element.scrollHeight > element.clientHeight)).toBe(false)
|
||||
})
|
||||
|
||||
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.
|
||||
|
||||
Reference in New Issue
Block a user