mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
0490f8bb06
A model entry's reasoningEfforts dict declares its selectable thinking levels — key = offered level, value = the wire spelling dispatch sends; only off may leave the value empty (supported, send nothing). false strips reasoning from a catalog model; every level is materialized explicitly into pi-ai's thinkingLevelMap so nobody has to know pi-ai's asymmetric absent-key defaulting. compat.thinkingFormat and compat.supportsReasoningEffort become configurable on the route and per model (model > route > catalog entry > pi-ai's URL-derived guess), openai-completions only, so a private gateway speaking the DeepSeek reasoning dialect no longer depends on its URL being recognizable. Record-typed drift gates pin both enums to pi-ai's, and an unserviceable declaration is refused at the write that produced it, naming route, model, and level.
96 lines
4.5 KiB
TypeScript
96 lines
4.5 KiB
TypeScript
// Web e2e scenario: a hand-declared model's `reasoningEfforts` reaches the
|
||
// composer's effort pane — the levels a settings profile declares are exactly
|
||
// what the picker offers, and picking one records it with the default route.
|
||
// Zero model calls: declaring, describing, and switching are settings/llm
|
||
// traffic only, so there is no fixture and a stray stream would fail loud.
|
||
import { readFile } from 'node:fs/promises'
|
||
import { fileURLToPath } from 'node:url'
|
||
import { join } from 'node:path'
|
||
import type { Browser, Page } from 'playwright'
|
||
import { chromium } from 'playwright'
|
||
import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
|
||
import { settingsNamespace } from '@deepseek-ai/dsh-settings'
|
||
import {
|
||
assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
|
||
launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
|
||
} from './scaffold.ts'
|
||
import { ZH_BROWSER_LOCALE, connectFreshWorkspaceZh, saveFailureShot } from './support.ts'
|
||
|
||
/** Starts the shipped default on this scenario's declared reasoning model. */
|
||
const OVERLAY = fileURLToPath(new URL('./declared-reasoning.overlay.yml', import.meta.url))
|
||
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/declared-reasoning', import.meta.url))
|
||
const UI_EXPECTED = fileURLToPath(new URL('./snapshots/declared-reasoning/ui.expected.md', import.meta.url))
|
||
const MODE = webSnapshotMode()
|
||
|
||
describe.skipIf(MODE === 'record')('web e2e: declared reasoning efforts reach the composer', () => {
|
||
let scaffold: WebScaffold
|
||
let browser: Browser
|
||
let page: Page
|
||
let tripwire: ReturnType<typeof watchConsole>
|
||
|
||
beforeAll(async () => {
|
||
scaffold = await launchWebScaffold({ extraOverlayPath: OVERLAY })
|
||
// The whole reasoning offer is the profile: key = selectable level, value
|
||
// = the wire spelling dispatch would send (`max: ultra` renames; the
|
||
// valueless `off` means "supported, send nothing"). The route sets no
|
||
// deployment default, so the pane leads with the provider-default entry.
|
||
await scaffold.ctx.settings.update(settingsNamespace('llm-pi-ai'), {
|
||
providers: {
|
||
'acme-gateway': {
|
||
displayName: 'Acme Gateway',
|
||
api: 'openai-completions',
|
||
baseURL: 'https://gateway.acme.example/v1',
|
||
models: [{
|
||
id: 'acme-think',
|
||
name: 'Acme Think',
|
||
reasoningEfforts: { off: null, high: 'high', max: 'ultra' },
|
||
}],
|
||
},
|
||
},
|
||
})
|
||
browser = await chromium.launch()
|
||
page = await browser.newPage({ viewport: { width: 1680, height: 1000 }, locale: ZH_BROWSER_LOCALE })
|
||
tripwire = watchConsole(page)
|
||
await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
|
||
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
|
||
await connectFreshWorkspaceZh(page, scaffold.workspaceCwd)
|
||
}, 120_000)
|
||
|
||
afterAll(async () => {
|
||
await browser?.close()
|
||
await scaffold?.close()
|
||
})
|
||
|
||
it('offers exactly the declared levels and records the picked one', async () => {
|
||
onTestFailed(() => saveFailureShot(page, 'web-e2e-declared-reasoning'))
|
||
const trigger = page.getByRole('button', { name: /^选择模型/ })
|
||
await trigger.waitFor({ timeout: 15_000 })
|
||
await trigger.click()
|
||
await page.getByRole('menuitem', { name: /推理等级/ }).click()
|
||
|
||
// Declared levels, nothing else: the provider-default entry (the route
|
||
// configures no `reasoning`), then Off/High/Max — minimal, low, medium,
|
||
// and xhigh were not declared and must not be offered.
|
||
const levels = page.getByRole('menuitemradio')
|
||
await expect.poll(async () => levels.allTextContents(), { timeout: 10_000 })
|
||
.toEqual(['Default', 'Off', 'High', 'Max'])
|
||
const snapshot = await captureStableAria(page, '[role="menu"]', scaffold.workspaceCwd)
|
||
await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
|
||
|
||
// Picking a level is the same gesture that saves the default target, so
|
||
// the effort lands in the gateway's settings section beside the route.
|
||
await page.getByRole('menuitemradio', { name: 'High' }).click()
|
||
await expect.poll(
|
||
async () => readFile(join(scaffold.harnessHome, 'settings.yaml'), 'utf8'),
|
||
{ timeout: 10_000 },
|
||
).toContain('reasoningEffort: high')
|
||
await expect.poll(() => trigger.getAttribute('aria-label'), { timeout: 10_000 })
|
||
.toBe('选择模型，当前 Acme Think，推理等级 High')
|
||
expect(tripwire.pageErrors).toEqual([])
|
||
}, 60_000)
|
||
|
||
it('keeps its snapshot inventory closed', async () => {
|
||
await assertFixtureInventory(SNAPSHOT_DIR, ['ui.expected.md'])
|
||
})
|
||
})
|