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

Merge remote-tracking branch 'origin/master' into xtr/react-loop-simplification

Browse Source 
# Conflicts:
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/session.i18n.yaml
#	docs/persistence-catalog.md
#	packages/cordis/tool-cordis/src/api-catalog.ts
This commit is contained in:
_Kerman
2026-07-30 17:30:10 +08:00
parent 5a0d26a0e4 aaf8fd07e0
commit d1dc303bc6
135 changed files with 2293 additions and 844 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
apps/web/tests/code-mode-round.e2e.ts
View File

@@ -118,14 +118,14 @@ describe('web e2e: Code Mode round renders nested sub-calls', () => {
expect(await nest.locator('[data-state="error"]').count()).toBeGreaterThanOrEqual(1)
}, 60_000)
it.skipIf(MODE === 'record')('a bash sub-row click leaves the default details panel open', async () => {
it.skipIf(MODE === 'record')('a bash sub-row click leaves the default details panel closed', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-code-mode-details'))
const nest = page.locator('[data-subcalls]').first()
const frame = page.locator('[style*="grid-template-columns"]').first()
expect(await frame.getAttribute('data-details-collapsed')).toBeNull()
expect(await frame.getAttribute('data-details-collapsed')).toBe('true')
await nest.locator('[data-sample="bash-global"]').first().click()
// Tool rows do not drive layout geometry; the Session's default panel stays open.
await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBeNull()
// Tool rows do not drive layout geometry; the Session's default panel stays closed.
await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true')
})
it.skipIf(MODE === 'record')('matches the conversation aria golden with stable anchors', async () => {

28
apps/web/tests/details-session-lifecycle.e2e.ts
View File

@@ -1,12 +1,14 @@
// Keyless browser regression for the details column's Session ownership.
// The shipped composition retains geometry through unselected states and closes it only when a different Session takes ownership.
// Keyless browser regression for the details column's default visibility and Session ownership.
// The shipped composition starts closed after selection and reload, retains an explicitly opened width through
// unselected states, and closes it only when a different Session takes ownership.
import { readFile } 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 {
fixtureUserPrompts, launchWebScaffold, seedSession, watchConsole, webSnapshotMode, type WebScaffold,
acknowledgeReloadConnectionLoss, fixtureUserPrompts, launchWebScaffold, seedSession, watchConsole,
webSnapshotMode, type WebScaffold,
} from './scaffold.ts'
import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
@@ -52,7 +54,7 @@ describe.skipIf(MODE === 'record')('web e2e: details panel follows the current S
await scaffold?.close()
})
it('retains geometry through hero and closes it for a different Session', async () => {
it('starts and reloads closed, then stays closed across Session ownership changes', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-details-session-lifecycle'))
const settled = scaffold.whenTurnSettled()
const input = page.locator('textarea').first()
@@ -61,10 +63,18 @@ describe.skipIf(MODE === 'record')('web e2e: details panel follows the current S
await settled
await page.getByText('LIGHTHOUSE', { exact: true }).waitFor({ timeout: 15_000 })
await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(360)
expect(await page.getByText('详情', { exact: true }).count()).toBe(1)
await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0)
expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false)
await page.getByRole('button', { name: 'New session', exact: true }).last().click()
const warningStart = tripwire.warnings.length
await page.reload({ waitUntil: 'load' })
acknowledgeReloadConnectionLoss(tripwire, warningStart)
await appFrame(page).waitFor({ timeout: 30_000 })
await page.getByText('LIGHTHOUSE', { exact: true }).waitFor({ timeout: 15_000 })
await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0)
expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false)
await page.getByRole('button', { name: /^(?:New session|新.*会话)$/ }).last().click()
await page.getByText("Let's start building", { exact: false }).waitFor({ timeout: 15_000 })
await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0)
expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false)
@@ -72,8 +82,8 @@ describe.skipIf(MODE === 'record')('web e2e: details panel follows the current S
const original = page.locator('[role=treeitem]').filter({ hasText: 'Reply with the single word' }).first()
await original.click()
await page.getByText('LIGHTHOUSE', { exact: true }).waitFor({ timeout: 15_000 })
await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(360)
expect(await page.getByText('详情', { exact: true }).count()).toBe(1)
await expect.poll(() => detailsTrack(page), { timeout: 5_000 }).toBe(0)
expect(await page.getByText('详情', { exact: true }).isVisible()).toBe(false)
const ungrouped = page.getByText('Ungrouped', { exact: true })
const ungroupedRow = ungrouped.locator('..').locator('..')

3
apps/web/tests/live-interactions.e2e.ts
View File

@@ -167,6 +167,9 @@ describe('web e2e: live-turn interactions (cancel / error / retry)', () => {
// "no crash, composer recovers, turn logged as error".
await expect.poll(() => page.locator('textarea').first().isEnabled(), { timeout: 10_000 }).toBe(true)
expect(await page.locator('[data-streaming="true"]').count()).toBe(0)
// The blank workspace also has an enabled composer. Wait for the driven
// session's only visible message before capturing its no-error-copy state.
await expect.poll(() => page.getByText(PROMPT, { exact: true }).first().isVisible(), { timeout: 10_000 }).toBe(true)
// Golden of the same gap: the prompt bubble alone, no error copy in the
// tree — the diff that changes when web-error-surface lands.
const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold!.workspaceCwd)

10
apps/web/tests/navigation-panes.e2e.ts
View File

@@ -173,24 +173,24 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
await expect.poll(() => page.locator('tr[data-timeline-focus]').count(), { timeout: 10_000 }).toBe(0)
}, 60_000)
it.skipIf(MODE === 'record')('bash and file-path rows leave the default details column open', async () => {
it.skipIf(MODE === 'record')('bash and file-path rows leave the default details column closed', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-details'))
await page.getByRole('tab', { name: 'Chat' }).click()
const bashRow = page.locator('[data-sample="bash-global"]').first()
await bashRow.waitFor({ timeout: 15_000 })
const frame = page.locator('[style*="grid-template-columns"]').first()
expect(await frame.getAttribute('data-details-collapsed')).toBeNull()
expect(await frame.getAttribute('data-details-collapsed')).toBe('true')
await bashRow.click()
await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBeNull()
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()
await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBeNull()
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()
await fileLink.waitFor({ timeout: 10_000 })
await fileLink.click()
await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBeNull()
await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBe('true')
}, 60_000)
it.skipIf(MODE === 'record')('renders the bash row as a terminal card in the real browser', async () => {

4
apps/web/tests/seeded-history.e2e.ts
View File

@@ -140,9 +140,9 @@ describe('web e2e: seeded history renders through cold resume', () => {
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')).toBeNull()
expect(await frame.getAttribute('data-details-collapsed')).toBe('true')
await fileLink.click()
await expect.poll(() => frame.getAttribute('data-details-collapsed'), { timeout: 5_000 }).toBeNull()
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)
})

10
apps/web/tests/smoke-real.e2e.ts
View File

@@ -454,7 +454,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
await screen(page, '07-back-to-chat')
})
it('5 bash differential rendering: tool row click leaves the default details column open', async () => {
it('5 bash differential rendering: tool row click leaves the default details column closed', async () => {
onTestFailed(() => saveFailureShot(page, 'w5-tool-details'))
const input = page.locator('textarea').first()
await input.fill('请用 bash 工具运行命令 echo w5marker 然后告诉我结果')
@@ -466,11 +466,11 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
const toolRow = page.locator('[data-sample="bash-global"]')
await toolRow.waitFor({ timeout: 120_000 })
await screen(page, '08-bash-round')
expect(await detailsTrack(page)).toBe(360)
expect(await detailsTrack(page)).toBe(0)
await toolRow.click()
// Tool rows no longer drive layout.openDetails; the default column stays open.
expect(await detailsTrack(page)).toBe(360)
await screen(page, '09-details-open')
// Tool rows no longer drive layout.openDetails; the default column stays closed.
expect(await detailsTrack(page)).toBe(0)
await screen(page, '09-details-closed')
}, 150_000)
it('6 sidebar drag widens the column and resets across reload', async () => {

1
apps/web/tests/snapshots/code-mode-round/ui.expected.md
View File

@@ -36,6 +36,7 @@
- button "Add attachment":
- 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

1
apps/web/tests/snapshots/cordis-tool-round/ui.expected.md
View File

@@ -50,6 +50,7 @@
- button "Add attachment":
- 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

1
apps/web/tests/snapshots/fresh-round-trip/ui.expected.md
View File

@@ -33,6 +33,7 @@
- button "Add attachment":
- 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

1
apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md
View File

@@ -29,6 +29,7 @@
- button "Add attachment":
- 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

1
apps/web/tests/snapshots/lifecycle-chrome/reloaded.expected.md
View File

@@ -25,6 +25,7 @@
- button "Add attachment":
- 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

1
apps/web/tests/snapshots/live-interactions/cancel.expected.md
View File

@@ -22,6 +22,7 @@
- button "Add attachment":
- 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

1
apps/web/tests/snapshots/live-interactions/error-auth.expected.md
View File

@@ -15,6 +15,7 @@
- button "Add attachment":
- 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

1
apps/web/tests/snapshots/live-interactions/retry.expected.md
View File

@@ -25,6 +25,7 @@
- button "Add attachment":
- 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

1
apps/web/tests/snapshots/message-actions/ui.expected.md
View File

@@ -36,6 +36,7 @@
- button "Add attachment":
- 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/question-composer/answered.expected.md
View File

@@ -18,7 +18,7 @@
- button:
- img
- img
- text: "Tool call ask_user_question · {\"questions\": [{\"id\": \"color\", \"question\": \"Which color do you prefer?\", \"header\": \"Pick one\", \"options\": [{\"label\": \"Blue\", \"description\": \"A cool recessive hue that reads as calm and trustworthy in long reading sessions and dense dashboards.\"}, {\"label\": \"Green\", \"description\": \"A restful mid-spectrum hue with the highest perceived brightness, easiest on the eye over long sessions.\"}]}]}"
- 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
@@ -33,6 +33,7 @@
- button "Add attachment":
- 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

22
apps/web/tests/snapshots/question-composer/ui.expected.md
View File

@@ -1,23 +1,17 @@
- region "Which color do you prefer?":
- text: Pick one
- heading "Which color do you prefer?" [level=2]
- text: 1 / 1
- button "Previous question" [disabled]:
- img
- button "Next question" [disabled]:
- img
- button "Dismiss all questions":
- img
- radiogroup:
- radio "Blue":
- text: 1 Blue A cool recessive hue that reads as calm and trustworthy in long reading sessions and dense dashboards.
- img
- radio "Green":
- text: 2 Green A restful mid-spectrum hue with the highest perceived brightness, easiest on the eye over long sessions.
- img
- button "Other — enter a custom answer":
- img
- text: Other — enter a custom answer
- radio "Blue": 1 Blue A cool recessive hue that reads as calm and trustworthy in long reading sessions and dense dashboards.
- radio "Green": 2 Green A restful mid-spectrum hue with the highest perceived brightness, easiest on the eye over long sessions.
- textbox "Type your answer"
- button "Previous question" [disabled]:
- img
- text: 1 / 1
- button "Next question" [disabled]:
- img
- status
- button "Skip this question"
- button "Submit" [disabled]

1
apps/web/tests/snapshots/queue-actions/editing.expected.md
View File

@@ -29,6 +29,7 @@
- button "Add attachment":
- 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

1
apps/web/tests/snapshots/queue-actions/ui.expected.md
View File

@@ -23,6 +23,7 @@
- button "Add attachment":
- 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

1
apps/web/tests/snapshots/seeded-history/ui.expected.md
View File

@@ -35,6 +35,7 @@
- button "Add attachment":
- 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

24
apps/web/tests/snapshots/steering/mid-steer.expected.md
View File

@@ -18,27 +18,21 @@
- button:
- img
- img
- text: "Tool call ask_user_question · {\"questions\": [{\"id\": \"checkpoint\", \"question\": \"Ready to continue?\", \"header\": \"Checkpoint\", \"options\": [{\"label\": \"Yes\"}, {\"label\": \"No\"}]}]}"
- text: Ask question waiting
- region "Ready to continue?":
- text: Checkpoint
- heading "Ready to continue?" [level=2]
- text: 1 / 1
- button "Previous question" [disabled]:
- img
- button "Next question" [disabled]:
- img
- button "Dismiss all questions":
- img
- radiogroup:
- radio "Yes":
- text: 1 Yes
- img
- radio "No":
- text: 2 No
- img
- button "Other — enter a custom answer":
- img
- text: Other — enter a custom answer
- radio "Yes": 1 Yes
- radio "No": 2 No
- textbox "Type your answer"
- button "Previous question" [disabled]:
- img
- text: 1 / 1
- button "Next question" [disabled]:
- img
- status
- button "Skip this question"
- button "Submit" [disabled]

3
apps/web/tests/snapshots/steering/settled.expected.md
View File

@@ -18,7 +18,7 @@
- button:
- img
- img
- text: "Tool call ask_user_question · {\"questions\": [{\"id\": \"checkpoint\", \"question\": \"Ready to continue?\", \"header\": \"Checkpoint\", \"options\": [{\"label\": \"Yes\"}, {\"label\": \"No\"}]}]} 插话 Interjection: include the word BANANA in your final reply."
- text: "Ask question 1/1 answered 插话 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
@@ -33,6 +33,7 @@
- button "Add attachment":
- 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/workspace-management.e2e.ts
View File

@@ -180,7 +180,9 @@ describe('web e2e: workspace management (create / rename / flat view / hover car
// current selection while it moves into Ungrouped.
const groupRow = page.locator('[role="treeitem"]').filter({ hasText: workspace.title }).first()
await groupRow.waitFor({ timeout: 10_000 })
const groupSection = groupRow.locator('..')
// The header row is wrapped by its HoverCard anchor span, so the section
// is the nearest groupSection ancestor, not the immediate parent.
const groupSection = groupRow.locator('xpath=ancestor::*[contains(@class, "groupSection")][1]')
if (await groupSection.locator('[role="treeitem"]').count() < 2) await groupRow.click()
await expect.poll(
() => groupSection.locator('[role="treeitem"]').count(),