Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge latest master into Web transcript

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-31 11:39:49 +08:00
parent cc0d13872f 9525cc9db2
commit ef722cc14a
213 changed files with 5435 additions and 912 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
apps/web/tests/cordis-tool-round.e2e.ts
View File

@@ -107,7 +107,8 @@ describe('web e2e: Cordis tools use the generic row variants', () => {
const mountRow = page.locator('[data-tool="cordis_mount"]').filter({ hasText: 'Mount temporary Plugin' }).first()
await mountRow.waitFor({ timeout: 10_000 })
await mountRow.locator('button[aria-expanded]').click()
// The whole summary row is the expand toggle (unified tool-row interaction).
await mountRow.locator('[aria-expanded]').first().click()
await expect.poll(() => mountRow.locator('pre.shiki').textContent(), { timeout: 10_000 })
.toContain(MOUNT_CODE)

88
apps/web/tests/lifecycle-chrome.e2e.ts
View File

@@ -25,6 +25,8 @@ import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './suppor
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/lifecycle-chrome', import.meta.url))
const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
const HERO_EXPECTED = join(SNAPSHOT_DIR, 'hero.expected.md')
const COMMAND_MENU_EXPECTED = join(SNAPSHOT_DIR, 'command-menu.expected.md')
const PLAN_ACTIVE_EXPECTED = join(SNAPSHOT_DIR, 'plan-active.expected.md')
// Post-reload golden: the same settled conversation rebuilt purely from
// persistence + history — byte-equal rendering is exactly the recovery claim.
const RELOADED_EXPECTED = join(SNAPSHOT_DIR, 'reloaded.expected.md')
@@ -56,6 +58,88 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()
await scaffold?.close()
})
it.skipIf(MODE === 'record')('opens the shared slash menu from plus with only Command candidates', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-command-menu-launcher'))
const launcher = page.getByRole('button', { name: 'Commands' })
await launcher.click()
const menu = page.getByRole('listbox', { name: 'Trigger suggestions' })
await menu.waitFor({ timeout: 10_000 })
const snapshot = await captureStableAria(page, '[role="listbox"]', scaffold.workspaceCwd)
await compareOrRefreshGolden(COMMAND_MENU_EXPECTED, snapshot, MODE)
expect(snapshot).toContain('text: Commands')
expect(snapshot).not.toContain('text: Skills')
expect(snapshot).not.toContain('text: Subagents')
const launchedBox = await menu.boundingBox()
await page.locator('textarea').first().press('Escape')
await expect.poll(() => menu.count()).toBe(0)
const input = page.locator('textarea').first()
await input.fill('/')
await menu.waitFor({ timeout: 10_000 })
const typedBox = await menu.boundingBox()
expect(launchedBox).not.toBeNull()
expect(typedBox).not.toBeNull()
expect(Math.abs(launchedBox!.x - typedBox!.x)).toBeLessThan(1)
expect(Math.abs(
launchedBox!.y + launchedBox!.height - typedBox!.y - typedBox!.height,
)).toBeLessThan(1)
await input.fill('')
await expect.poll(() => menu.count()).toBe(0)
})
it.skipIf(MODE === 'record')('shows active Plan as the warn-state status action', async () => {
const activeScaffold = await launchWebScaffold()
const activePage = await newEnglishPage(browser)
const activeTripwire = watchConsole(activePage)
try {
await activePage.goto(activeScaffold.baseUrl, { waitUntil: 'load' })
await activePage.waitForSelector('[class*="frame"]', { timeout: 30_000 })
await connectFreshWorkspace(activePage)
const input = activePage.locator('textarea').first()
await activePage.getByRole('button', { name: 'Commands' }).click()
const menu = activePage.getByRole('listbox', { name: 'Trigger suggestions' })
await menu.waitFor({ timeout: 10_000 })
await menu.getByRole('option', { name: 'plan Enter or leave plan mode' }).click()
await expect.poll(() => input.inputValue()).toBe('/plan ')
await input.press('Enter')
const planButton = activePage.getByRole('button', { name: 'Plan mode on, press to turn off' })
await planButton.waitFor({ timeout: 10_000 })
const planSnapshot = await captureStableAria(activePage, '[class*="frame"]', activeScaffold.workspaceCwd)
await compareOrRefreshGolden(PLAN_ACTIVE_EXPECTED, planSnapshot, MODE)
const planStyle = await planButton.evaluate((element) => {
const probe = document.createElement('span')
probe.style.color = 'var(--dsw-alias-state-warn-label)'
probe.style.backgroundColor = 'var(--dsw-alias-state-warn-tertiary)'
document.body.append(probe)
const actual = getComputedStyle(element)
const reference = getComputedStyle(probe)
const result = {
color: actual.color,
backgroundColor: actual.backgroundColor,
borderRadius: actual.borderRadius,
fontSize: actual.fontSize,
referenceColor: reference.color,
referenceBackgroundColor: reference.backgroundColor,
}
probe.remove()
return result
})
expect(planStyle.color).toBe(planStyle.referenceColor)
expect(planStyle.backgroundColor).toBe(planStyle.referenceBackgroundColor)
expect(planStyle.borderRadius).toBe('999px')
expect(planStyle.fontSize).toBe('13px')
await planButton.click()
await expect.poll(() => planButton.count()).toBe(0)
expect(activeTripwire.pageErrors).toEqual([])
expect(activeTripwire.warnings).toEqual([])
} catch (error) {
await saveFailureShot(activePage, 'web-e2e-plan-active').catch(() => undefined)
throw error
} finally {
await activePage.close()
await activeScaffold.close()
}
})
it('sends the first prompt from the empty-state hero (all modes)', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-lifecycle-send'))
if (MODE !== 'record') {
@@ -152,6 +236,8 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()
it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
expect(tripwire.warnings).toEqual([])
await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'hero.expected.md', 'reloaded.expected.md'])
await assertFixtureInventory(SNAPSHOT_DIR, [
'session.jsonl', 'command-menu.expected.md', 'hero.expected.md', 'plan-active.expected.md', 'reloaded.expected.md',
])
})
})

78
apps/web/tests/navigation-panes.e2e.ts
View File

@@ -23,6 +23,7 @@ import { newEnglishPage, saveFailureShot } from './support.ts'
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/navigation-panes', import.meta.url))
const SEED = join(SNAPSHOT_DIR, 'seed.jsonl')
const TRAJECTORY_EXPECTED = join(SNAPSHOT_DIR, 'trajectory.expected.md')
const SEARCH_EXPECTED = join(SNAPSHOT_DIR, 'search-results.expected.md')
const TERMINAL_EXPECTED = join(SNAPSHOT_DIR, 'terminal-card.expected.md')
const MODE = webSnapshotMode()
const SEED_ID = 'navigation-panes-web-e2e'
@@ -95,39 +96,39 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
expect(calls.map(e => e.data.name).sort()).toEqual(['bash', 'read', 'read'])
}, 400_000)
it.skipIf(MODE === 'record')('opens the seeded session and renders both turns from the log', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-open'))
// Expand the collapsed group row, then open 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()
it.skipIf(MODE === 'record')('finds an unopened seeded session by message content and opens it', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-search'))
const search = page.getByPlaceholder('Search name, keywords', { exact: false })
// The cold row has not been opened, so only the persisted log can satisfy
// this query. First search lazily reconciles the SQLite content index.
await search.fill('zzzqx-no-such-session')
await page.getByText('No matching sessions').waitFor({ timeout: 30_000 })
await expect.poll(
() => page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem').count(),
{ timeout: 10_000 },
).toBe(0)
await search.fill('WATERFALL')
const resultTree = page.getByRole('tree', { name: 'Search results' })
const result = resultTree.getByRole('treeitem')
await expect.poll(() => result.count(), { timeout: 30_000 }).toBe(1)
await expect.poll(() => result.getByText('WATERFALL', { exact: false }).count(), {
timeout: 10_000,
}).toBeGreaterThanOrEqual(1)
const snapshot = (await captureStableAria(page, '[class*="listArea"]', scaffold.workspaceCwd))
.split(SEED_ID).join('{{seededId}}')
await compareOrRefreshGolden(SEARCH_EXPECTED, snapshot, MODE)
await result.click()
// Search navigation addresses the session, not a specific event, and the
// query remains until the user explicitly clears it.
await expect.poll(() => search.inputValue(), { timeout: 5_000 }).toBe('WATERFALL')
await expect.poll(() => page.getByText('FIRST_DONE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
await expect.poll(() => page.getByRole('heading', { name: 'Navigation Summary' }).count(), { timeout: 15_000 }).toBe(1)
}, 90_000)
it.skipIf(MODE === 'record')('filters the sidebar tree by title through the search box', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-search'))
// Runs after the session is open: a cold summary carries no title (the
// sidebar shows the cwd basename), and the durable title lands with the
// attach subscription's baseline — which is itself worth pinning: search
// matches the title the user sees, not a hidden cold field.
const search = page.getByPlaceholder('Search name, keywords', { exact: false })
await expect.poll(() => page.getByText('NavScenario', { exact: false }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
// Negative: a garbage query empties the tree (group rows hide too).
await search.fill('zzzqx-no-such-session')
await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBe(0)
// Positive: a title word narrows to the matched session + its group,
// force-expanded by search mode (case-insensitive client-side filter).
await search.fill('navscenario')
await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(2)
// Clear restores the unfiltered tree.
await page.getByRole('button', { name: 'Clear search' }).click()
await expect.poll(() => search.inputValue(), { timeout: 5_000 }).toBe('')
await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1)
}, 60_000)
}, 90_000)
it.skipIf(MODE === 'record')('renders the trajectory ledger and opens its local record inspector', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-trajectory'))
@@ -180,11 +181,13 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
await bashRow.waitFor({ timeout: 15_000 })
const frame = page.locator('[style*="grid-template-columns"]').first()
expect(await frame.getAttribute('data-details-collapsed')).toBe('true')
// The row click is the card's expand toggle (unified tool-row
// interaction); it must not drive layout geometry either way.
await bashRow.click()
await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true')
// The card's own controls are outside the summary row and must not open
// details either — the terminal card is read in place.
await page.locator('[data-sample="bash-global"] ~ [data-terminal] [class*="_copyButton_"]').first().click()
// details either — the expanded terminal card is read in place.
await page.locator('[data-sample="bash-global"] ~ div [data-terminal] [class*="_copyButton_"]').first().click()
await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true')
// Read summaries are host-open file links; they also must not open details.
const fileLink = page.locator('[data-variant="read"] button').first()
@@ -196,10 +199,14 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
it.skipIf(MODE === 'record')('renders the bash row as a terminal card in the real browser', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-terminal'))
await page.getByRole('tab', { name: 'Chat' }).click()
// The card is resident in the keyed bash row (no expand gesture): the
// recorded command's own output sits in the message flow, derived from the
// logged call/result presentations alone.
const card = page.locator('[data-sample="bash-global"] ~ [data-terminal], [data-sample="bash-global"] [data-terminal]').first()
// The card is expand-gated behind the whole-row toggle (the unified
// tool-row interaction): open it if a previous case left it collapsed.
// Expanded, the recorded command's own output sits in the message flow,
// derived from the logged call/result presentations alone.
const bashRow = page.locator('[data-sample="bash-global"]').first()
await bashRow.waitFor({ timeout: 15_000 })
if (await bashRow.getAttribute('aria-expanded') !== 'true') await bashRow.click()
const card = page.locator('[data-sample="bash-global"] ~ div [data-terminal]').first()
await card.waitFor({ timeout: 15_000 })
// Real layout, not jsdom's stub (which computes no geometry at all):
// squeeze the output pane below its content width and the line must keep
@@ -279,7 +286,8 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
expect(slotErrors).toEqual([])
expect(tripwire.warnings).toEqual([])
await assertFixtureInventory(SNAPSHOT_DIR, [
'seed.jsonl', 'trajectory.expected.md', 'terminal-card.expected.md',
'seed.jsonl', 'search-results.expected.md', 'trajectory.expected.md',
'terminal-card.expected.md',
])
})
})

1
apps/web/tests/scaffold.ts
View File

@@ -200,6 +200,7 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
const patches: PatchOptions[] = [
...surfacePatches,
{ id: 'session-persistence-jsonl', config: { root: persistenceRoot } },
{ id: 'session-query-sqlite', config: { path: ':memory:', openAt: 'first-search' } },
// storage-json's './.storages' yml default is cwd-relative and resolves
// per write; the scaffold restores the original cwd after boot, so the
// row gets an absolute temp root (removed with the workspace at close).

13
apps/web/tests/snapshots/code-mode-round/ui.expected.md
View File

@@ -15,13 +15,15 @@
- img
- img
- text: "Think The user wants me to write a single `run_code` program that:"
- button:
- button "Code Run bash echo and catch missing file read":
- img
- img
- text: Code Run bash echo and catch missing file read
- text: Code Run bash echo and catch missing file read
- img
- text: Bash Echo CODE_ROUND_OK Read
- button "missing.txt"
- text: Bash Echo CODE_ROUND_OK
- 'button "Read Error: cannot read \"{{cwd}}/workspace/missing.txt\": not found"':
- img
- text: "Read Error: cannot read \"{{cwd}}/workspace/missing.txt\": not found"
- button "Think The program ran successfully. Let me now reply DONE as instructed.":
- img
- img
@@ -33,10 +35,9 @@
- img
- text: {{clock}}
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

18
apps/web/tests/snapshots/cordis-tool-round/ui.expected.md
View File

@@ -15,27 +15,30 @@
- img
- img
- text: "Think The user wants me to:"
- button:
- button "Inspect temporary":
- img
- img
- text: Inspect temporary
- text: Inspect temporary
- 'button "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."':
- img
- img
- text: "Think Good, no temporary plugins running. Now step 2: call cordis_mount with the exact code."
- button [expanded]:
- 'button "Mount temporary Plugin return { name: \"snapshot-noop\", apply(ctx) {} }" [expanded]':
- img
- text: Mount temporary Plugin typescript
- text: "Mount temporary Plugin return { name: \"snapshot-noop\", apply(ctx) {} }"
- text: typescript
- button "Copy"
- code: "return { name: \"snapshot-noop\", apply(ctx) {} }"
- text: OUT Temporary Plugin dyn-1 is running (plugin "snapshot-noop"; available until unmounted or DSH restarts).
- button "Inspect"
- 'button "Think The id is \"dyn-1\". Now step 3: call cordis_unmount with that id."':
- img
- img
- text: "Think The id is \"dyn-1\". Now step 3: call cordis_unmount with that id."
- button:
- button "Unmount temporary Plugin dyn-1":
- img
- img
- text: Unmount temporary Plugin dyn-1
- text: Unmount temporary Plugin dyn-1
- button "Think All three calls succeeded. I should now reply exactly \"CORDIS_UI_DONE\" and stop.":
- img
- img
@@ -47,10 +50,9 @@
- img
- text: {{clock}}
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

11
apps/web/tests/snapshots/fresh-round-trip/ui.expected.md
View File

@@ -15,10 +15,10 @@
- img
- img
- text: Think The user wants me to run a simple bash command and reply with "DONE".
- img
- text: Bash Echo the test string Done workspace echo WEB_E2E_OK
- button "Copy"
- text: WEB_E2E_OK
- button "Bash Echo the test string":
- img
- img
- text: Bash Echo the test string
- button "Think The command executed successfully and output \"WEB_E2E_OK\". I just need to reply with \"DONE\".":
- img
- img
@@ -30,10 +30,9 @@
- img
- text: {{clock}}
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

6
apps/web/tests/snapshots/lifecycle-chrome/command-menu.expected.md Normal file
View File

@@ -0,0 +1,6 @@
- listbox "Trigger suggestions":
- text: Commands
- option "goal set or view the goal for a long-running task" [selected]
- option "permission Switch the permission preset (sandbox mode + approval policy)"
- option "plan Enter or leave plan mode"
- option "model Select the model for this conversation"

3
apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md
View File

@@ -26,10 +26,9 @@
- text: workspace
- img
- textbox "Describe what you want to build"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

39
apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md Normal file
View File

@@ -0,0 +1,39 @@
- button "New session"
- button "Collapse sidebar":
- img
- button "New session":
- img
- text: New Session
- text: Workspaces
- button "Group by":
- img
- button "Create workspace":
- img
- button "Search sessions":
- img
- textbox "Search name, keywords..."
- tree "Sessions":
- treeitem "workspace 1 session" [expanded]:
- img
- text: workspace 1 session
- treeitem "New Session now" [selected]
- button "Settings":
- img
- text: Settings
- text: Let's start building
- button "Choose workspace":
- img
- text: workspace
- img
- textbox "Describe what you want to build"
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode on, press to turn off": Plan
- button "Select model, current deepseek-v4-flash":
- text: deepseek-v4-flash
- img
- button "Send message" [disabled]
- text: Details
- button "Close details"
- text: Click a tool row in the message flow to view its details

3
apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md
View File

@@ -22,10 +22,9 @@
- img
- text: {{clock}}
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

3
apps/web/tests/snapshots/live-interactions/cancel.expected.md
View File

@@ -19,10 +19,9 @@
- img
- text: {{clock}}
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

3
apps/web/tests/snapshots/live-interactions/error-auth.expected.md
View File

@@ -12,10 +12,9 @@
- button "Edit":
- img
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

3
apps/web/tests/snapshots/live-interactions/retry.expected.md
View File

@@ -22,10 +22,9 @@
- img
- text: {{clock}}
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

19
apps/web/tests/snapshots/message-actions/ui.expected.md
View File

@@ -16,12 +16,16 @@
- img
- img
- text: Think The user wants me to read a.txt and b.txt, then reply with "DONE". Let me do both reads in parallel.
- img
- text: Read
- button "a.txt"
- img
- text: Read
- button "b.txt"
- button "Read a.txt":
- img
- img
- text: Read
- button "a.txt"
- button "Read b.txt":
- img
- img
- text: Read
- button "b.txt"
- button "Think Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed.":
- img
- img
@@ -33,10 +37,9 @@
- img
- text: 7/25 {{clock}}
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current deepseek-v4-flash":
- text: deepseek-v4-flash
- img

2
apps/web/tests/snapshots/navigation-panes/search-results.expected.md Normal file
View File

@@ -0,0 +1,2 @@
- tree "Search results":
- 'treeitem "{{workspace}} {{workspace}} ## Navigation Summary - alpha nav - beta nav ``` echo WATERFALL ```"'

7
apps/web/tests/snapshots/plan-review/approved.expected.md
View File

@@ -20,10 +20,10 @@
- text: Since the user has explicitly asked me not to read or write any files and to go straight to planning, I'll proceed with
- code: exit_plan_mode
- text: .
- button:
- 'button "Tool call exit_plan_mode · # Add `--greeting` flag to CLI"':
- img
- img
- text: "Tool call exit_plan_mode · # Add `--greeting` flag to CLI"
- text: "Tool call exit_plan_mode · # Add `--greeting` flag to CLI"
- 'button "Think The plan was approved. The user''s last instruction says: \"Once the plan is approved, reply with the single word DONE and stop.\" So I should just reply with DONE and stop."':
- img
- img
@@ -35,10 +35,9 @@
- img
- text: {{clock}}
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

7
apps/web/tests/snapshots/question-composer/answered.expected.md
View File

@@ -15,10 +15,10 @@
- img
- img
- text: Think The user wants me to use the ask_user_question tool with specific parameters. Let me do exactly that.
- button:
- button "Ask question 1/1 answered":
- img
- img
- text: Ask question 1/1 answered
- text: Ask question 1/1 answered
- button "Think The user answered \"Blue\". I should now reply with the single word DONE and stop.":
- img
- img
@@ -30,10 +30,9 @@
- img
- text: {{clock}}
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

3
apps/web/tests/snapshots/queue-actions/collapsed.expected.md
View File

@@ -14,10 +14,9 @@
- paragraph: partial
- button "2 queued messages"
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

3
apps/web/tests/snapshots/queue-actions/editing.expected.md
View File

@@ -27,10 +27,9 @@
- button "Cancel editing":
- img
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

3
apps/web/tests/snapshots/queue-actions/ui.expected.md
View File

@@ -20,10 +20,9 @@
- button "Remove queued message":
- img
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img

19
apps/web/tests/snapshots/seeded-history/command-row.expected.md
View File

@@ -15,12 +15,16 @@
- img
- img
- text: Think The user wants me to read a.txt and b.txt, then reply with "DONE". Let me do both reads in parallel.
- img
- text: Read
- button "a.txt"
- img
- text: Read
- button "b.txt"
- button "Read a.txt":
- img
- img
- text: Read
- button "a.txt"
- button "Read b.txt":
- img
- img
- text: Read
- button "b.txt"
- button "Think Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed.":
- img
- img
@@ -41,10 +45,9 @@
- img
- text: permission preset workspace-write
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Workspace Write"': Workspace Write
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current deepseek-v4-flash":
- text: deepseek-v4-flash
- img

19
apps/web/tests/snapshots/seeded-history/ui.expected.md
View File

@@ -15,12 +15,16 @@
- img
- img
- text: Think The user wants me to read a.txt and b.txt, then reply with "DONE". Let me do both reads in parallel.
- img
- text: Read
- button "a.txt"
- img
- text: Read
- button "b.txt"
- button "Read a.txt":
- img
- img
- text: Read
- button "a.txt"
- button "Read b.txt":
- img
- img
- text: Read
- button "b.txt"
- button "Think Both files have been read. a.txt contains \"alpha\" and b.txt contains \"beta\". I'll now reply with DONE as instructed.":
- img
- img
@@ -39,10 +43,9 @@
- img
- text: Context injection
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current deepseek-v4-flash":
- text: deepseek-v4-flash
- img

4
apps/web/tests/snapshots/steering/mid-steer.expected.md
View File

@@ -15,10 +15,10 @@
- img
- img
- text: Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that.
- button:
- button "Ask question waiting":
- img
- img
- text: Ask question waiting
- text: Ask question waiting
- region "Ready to continue?":
- text: Checkpoint
- heading "Ready to continue?" [level=2]

8
apps/web/tests/snapshots/steering/settled.expected.md
View File

@@ -15,10 +15,11 @@
- img
- img
- text: Think The user wants me to use the ask_user_question tool to ask them a specific question with the given parameters. Let me do exactly that.
- button:
- button "Ask question 1/1 answered":
- img
- img
- text: "Ask question 1/1 answered Interjection Interjection: include the word BANANA in your final reply."
- text: Ask question 1/1 answered
- text: "Interjection Interjection: include the word BANANA in your final reply."
- button "Think The user selected \"Yes\" and wants me to include the word \"BANANA\" in my final reply. Let me acknowledge their answer.":
- img
- img
@@ -30,10 +31,9 @@
- img
- text: {{clock}}
- textbox "Message the agent"
- button "Add attachment":
- button "Commands":
- img
- 'button "Access mode, current: Danger Full Access"': Danger Full Access
- button "Plan mode off, press to turn on": Plan off
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash
- img