mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
# Conflicts: # .agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md # .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md # .agents/notes/implemented/feature/2026-07-06-sandbox.i18n.yaml # .agents/notes/implemented/feature/2026-07-06-sandbox.md # .agents/notes/implemented/feature/2026-07-06-sandbox.zh.md # .agents/notes/implemented/feature/2026-07-27-tmux-location-context.i18n.yaml # .agents/notes/implemented/simplification/2026-06-20-public-agent-stop-surface.i18n.yaml # .agents/notes/implemented/simplification/2026-07-28-remove-synthetic-log-only-turns.i18n.yaml # .agents/notes/implemented/simplification/2026-07-30-private-agent-send.i18n.yaml # docs/architecture.i18n.yaml # docs/architecture.md # docs/architecture.zh.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/compaction.i18n.yaml # docs/core-data-structures/core.i18n.yaml # docs/core-data-structures/core.md # docs/core-data-structures/core.zh.md # docs/core-data-structures/llm-streaming.i18n.yaml # docs/core-data-structures/llm-streaming.md # docs/core-data-structures/llm-streaming.zh.md # docs/core-data-structures/session.i18n.yaml # docs/event-producer-consumer.md # docs/module-graph.md # docs/persistence-catalog.md # examples/acp-agent/tests/goal-snapshots/goal-session/session.expected.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl # examples/acp-agent/tests/snapshots/bash-spill/session.jsonl # examples/acp-agent/tests/snapshots/bash-tool-turn/session.jsonl # examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl # examples/acp-agent/tests/snapshots/cancel/session.jsonl # examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl # examples/acp-agent/tests/snapshots/code-mode-workspace-context/session.jsonl # examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl # examples/acp-agent/tests/snapshots/empty-response-retry/session.jsonl # examples/acp-agent/tests/snapshots/error-finish/session.jsonl # examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl # examples/acp-agent/tests/snapshots/fs-edit/session.jsonl # examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl # examples/acp-agent/tests/snapshots/fs-glob-sampling/session.jsonl # examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl # examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl # examples/acp-agent/tests/snapshots/fs-read/session.jsonl # examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl # examples/acp-agent/tests/snapshots/fs-write/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-invalid-matcher/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-invalid-matcher/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl # examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl # examples/acp-agent/tests/snapshots/lsp-definition/session.jsonl # examples/acp-agent/tests/snapshots/multi-turn/session.jsonl # examples/acp-agent/tests/snapshots/packed-chunks/session.jsonl # examples/acp-agent/tests/snapshots/parallel-tool-calls/session.jsonl # examples/acp-agent/tests/snapshots/pty-tools/session.jsonl # examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl # examples/acp-agent/tests/snapshots/session-query-spill/session.jsonl # examples/acp-agent/tests/snapshots/session-sandbox-root/session.jsonl # examples/acp-agent/tests/snapshots/session-title-after-turn/session.jsonl # examples/acp-agent/tests/snapshots/skill-load/session.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-depth-two-rejection/session.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl # examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl # examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl # examples/acp-agent/tests/snapshots/text-turn/session.jsonl # examples/acp-agent/tests/snapshots/todo-write/session.jsonl # examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl # examples/acp-agent/tests/snapshots/web-fetch/session.jsonl # examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl # examples/acp-agent/tests/snapshots/workflow-run/session.jsonl # examples/acp-agent/tests/snapshots/workspace-context/session.jsonl # examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl # examples/headless-agent/tests/semantic-checkpoint-snapshots/tool-outcome-unknown/session.expected.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/goal-tools/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/missing-credential/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/provider-retry/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/pty-tools/session.jsonl # examples/headless-agent/tests/snapshots/pty-tools/stream-json.expected.jsonl # examples/headless-agent/tests/snapshots/ralph-loop/stream-json.expected.jsonl # examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/child.expected.jsonl # examples/headless-agent/tests/subagent-inheritance-snapshots/parent-override/parent.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/bash-tool/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/bash-tool/session.jsonl # examples/jsonrpc-agent/tests/snapshots/persistent-tools/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/persistent-tools/session.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.1.jsonl # examples/jsonrpc-agent/tests/snapshots/subagent-spawn/session.jsonl # examples/jsonrpc-agent/tests/snapshots/text-turn/notifications.expected.jsonl # examples/jsonrpc-agent/tests/snapshots/text-turn/session.jsonl # packages/client/runtime/README.i18n.yaml # packages/client/runtime/src/client/sessions/request-inspection.ts # packages/compact/compact-basic/README.i18n.yaml # packages/compact/compact-basic/README.md # packages/compact/compact-basic/README.zh.md # packages/compact/compact-basic/src/index.ts # packages/context/time-context/tests/time-context.spec.ts # packages/context/tmux-context/README.i18n.yaml # packages/context/tmux-context/tests/tmux-context.spec.ts # packages/context/workspace-context/tests/workspace-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/core/agent-loop/README.i18n.yaml # packages/core/agent-loop/README.md # packages/core/agent-loop/README.zh.md # packages/core/agent-loop/src/agent.ts # packages/core/agent/README.i18n.yaml # packages/core/agent/README.md # packages/core/agent/README.zh.md # packages/core/agent/src/types.ts # packages/core/session/README.i18n.yaml # packages/core/session/README.md # packages/core/session/README.zh.md # packages/fs/tool-str-replace-editor/tests/tools.spec.ts # packages/goal/command-goal/tests/command-goal.spec.ts # packages/goal/goal/tests/goal.spec.ts # packages/host/apiproxy/README.i18n.yaml # packages/host/apiproxy/README.md # packages/host/apiproxy/README.zh.md # packages/host/apiproxy/src/api/index.ts # packages/host/apiproxy/tests/api-proxy-workspace.spec.ts # packages/llm/llm/README.i18n.yaml # packages/llm/llm/README.md # packages/llm/llm/README.zh.md # packages/llm/llm/src/index.ts # packages/pty/pty-local/tests/index.spec.ts # packages/pty/pty-local/tests/local.spec.ts # packages/pty/pty/tests/service.spec.ts # packages/pty/tool-bash-persistent/tests/loader-composition.spec.ts # packages/pty/tool-bash-persistent/tests/tools.spec.ts # packages/pty/tool-pty/tests/loader-composition.spec.ts # packages/pty/tool-pty/tests/tools.spec.ts # packages/session-persistence/session-checkpoint-policy/tests/crash-recovery.e2e.ts # packages/skill/tool-skill/tests/tool-skill.spec.ts # packages/tasks/tasks-local/tests/tasks.spec.ts # packages/ui/tui/README.i18n.yaml # packages/ui/tui/tests/tui.spec.ts # packages/ui/user-approval/src/index.ts # packages/ui/user-approval/tests/approval.spec.ts
130 lines
6.0 KiB
TypeScript
130 lines
6.0 KiB
TypeScript
// Web e2e scenario for the opt-in Cordis tools. Record mode drives a real
|
|
// model through inspect, mount, and unmount; replay pins the same shipped Web
|
|
// composition, durable calls, generic rows, highlighted Plugin source, and
|
|
// conversation accessibility tree.
|
|
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 type { SessionEvent } from '@deepseek-ai/dsh-session'
|
|
import {
|
|
captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
|
|
launchWebScaffold, recordFixture, watchConsole, webSnapshotMode, type WebScaffold,
|
|
} from './scaffold.ts'
|
|
import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
|
|
|
|
const FIXTURE = fileURLToPath(new URL('./snapshots/cordis-tool-round/session.jsonl', import.meta.url))
|
|
const UI_EXPECTED = fileURLToPath(new URL('./snapshots/cordis-tool-round/ui.expected.md', import.meta.url))
|
|
const MODE = webSnapshotMode()
|
|
const CORDIS_TOOLS = ['cordis_inspect', 'cordis_mount', 'cordis_unmount'] as const
|
|
const MOUNT_CODE = 'return { name: "snapshot-noop", apply(ctx) {} }'
|
|
const PROMPT = 'Use only Cordis tools. First call cordis_inspect with what "temporary". '
|
|
+ `Then call cordis_mount with this exact code: ${JSON.stringify(MOUNT_CODE)}. `
|
|
+ 'Read its returned id and call cordis_unmount with that exact id. '
|
|
+ 'After all three calls succeed, reply exactly CORDIS_UI_DONE and stop.'
|
|
|
|
function assertCompleteCordisLifecycle(events: readonly SessionEvent[]): void {
|
|
const turnEnd = events.findLast(
|
|
(event): event is Extract<SessionEvent, { type: 'turn/end' }> => event.type === 'turn/end',
|
|
)
|
|
const reason = turnEnd?.data.reason
|
|
const reasonSummary = { kind: reason?.kind }
|
|
expect(reasonSummary).toEqual({ kind: 'completed' })
|
|
|
|
const calls = events.filter(
|
|
(event): event is Extract<SessionEvent, { type: 'tool/call' }> => event.type === 'tool/call',
|
|
)
|
|
expect(calls.map(event => event.data.name)).toEqual(CORDIS_TOOLS)
|
|
|
|
const callIds = new Set(calls.map(event => String(event.data.callId)))
|
|
const results = events.filter(
|
|
(event): event is Extract<SessionEvent, { type: 'tool/result' }> =>
|
|
event.type === 'tool/result' && callIds.has(String(event.data.message.source.callId)),
|
|
)
|
|
expect(results).toHaveLength(CORDIS_TOOLS.length)
|
|
expect(results.every(event => !event.data.message.content[0].isError)).toBe(true)
|
|
}
|
|
|
|
describe('web e2e: Cordis tools use the generic row variants', () => {
|
|
let scaffold: WebScaffold
|
|
let browser: Browser
|
|
let page: Page
|
|
let tripwire: ReturnType<typeof watchConsole>
|
|
const sessionEvents: SessionEvent[] = []
|
|
|
|
beforeAll(async () => {
|
|
scaffold = await launchWebScaffold({
|
|
cordisTools: true,
|
|
...(MODE === 'record' ? {} : { replayFixture: FIXTURE, paceMs: 15 }),
|
|
})
|
|
scaffold.ctx.on('session/event', (_session, event: SessionEvent) => { sessionEvents.push(event) })
|
|
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 })
|
|
await connectFreshWorkspace(page, scaffold.workspaceCwd)
|
|
}, 120_000)
|
|
|
|
afterAll(async () => {
|
|
await browser?.close()
|
|
await scaffold?.close()
|
|
})
|
|
|
|
it('drives the recorded Cordis lifecycle to a settled turn (all modes)', async () => {
|
|
onTestFailed(() => saveFailureShot(page, 'web-e2e-cordis-drive'))
|
|
if (MODE !== 'record') {
|
|
expect(fixtureUserPrompts(await readFile(FIXTURE, 'utf8'))).toEqual([PROMPT])
|
|
}
|
|
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
|
|
if (MODE === 'record') {
|
|
assertCompleteCordisLifecycle(sessionEvents)
|
|
await expect.poll(() => page.getByText('CORDIS_UI_DONE', { exact: true }).count(), { timeout: 15_000 })
|
|
.toBeGreaterThanOrEqual(1)
|
|
await recordFixture(scaffold, sessionId, FIXTURE)
|
|
}
|
|
}, 200_000)
|
|
|
|
it.skipIf(MODE === 'record')('the durable log carries one complete Cordis lifecycle', () => {
|
|
assertCompleteCordisLifecycle(sessionEvents)
|
|
})
|
|
|
|
it.skipIf(MODE === 'record')('renders Cordis lifecycle titles over the generic row mechanics', async () => {
|
|
onTestFailed(() => saveFailureShot(page, 'web-e2e-cordis-rows'))
|
|
await expect.poll(() => page.getByText('CORDIS_UI_DONE', { exact: true }).count(), { timeout: 15_000 })
|
|
.toBeGreaterThanOrEqual(1)
|
|
|
|
const inspectRow = page.locator('[data-tool="cordis_inspect"]').filter({ hasText: 'Inspect' }).first()
|
|
await inspectRow.waitFor({ timeout: 10_000 })
|
|
|
|
const mountRow = page.locator('[data-tool="cordis_mount"]').filter({ hasText: 'Mount temporary Plugin' }).first()
|
|
await mountRow.waitFor({ timeout: 10_000 })
|
|
// 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)
|
|
|
|
const unmountRow = page.locator('[data-tool="cordis_unmount"]').filter({ hasText: 'Unmount temporary Plugin' }).first()
|
|
await unmountRow.waitFor({ timeout: 10_000 })
|
|
await expect.poll(() => unmountRow.textContent()).toContain('dyn-')
|
|
await expect(unmountRow.getAttribute('data-state')).resolves.toBe('ok')
|
|
})
|
|
|
|
it.skipIf(MODE === 'record')('matches the conversation aria golden', async () => {
|
|
onTestFailed(() => saveFailureShot(page, 'web-e2e-cordis-aria'))
|
|
const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
|
|
await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
|
|
})
|
|
|
|
it.skipIf(MODE === 'record')('stayed clean: no page errors or reconnect churn', () => {
|
|
expect(tripwire.pageErrors).toEqual([])
|
|
expect(tripwire.warnings).toEqual([])
|
|
})
|
|
})
|