Merge remote-tracking branch 'origin/master' into fix/web-sources-scroll
This commit is contained in:
@@ -1,7 +1,7 @@
|
||||
// Web e2e scenario: message IconActions + clocks. Cold-seeds the seeded-history
|
||||
// fixture (zero model calls) and pins the settled conversation aria after the
|
||||
// user/assistant footers are focus-revealed — the surface package jsdom tests
|
||||
// cannot substitute for (docs/testing.md snapshot rule).
|
||||
// Web e2e scenario: message IconActions + clocks. Cold-seeds a deterministic
|
||||
// completed-turn-tail fork case (zero model calls) and pins the settled
|
||||
// conversation aria after the footers are focus-revealed — the surface package
|
||||
// jsdom tests cannot substitute for (docs/testing.md snapshot rule).
|
||||
import { mkdir, readFile, writeFile } from 'node:fs/promises'
|
||||
import { join } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
@@ -25,6 +25,48 @@ const MODE = webSnapshotMode()
|
||||
const SEED_ID = 'message-actions-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.'
|
||||
const MID_TURN_TEXT = 'I will read both files before answering.'
|
||||
const SECOND_PROMPT = 'Now give the final answer.'
|
||||
|
||||
/**
|
||||
* Adapt the borrowed recording into response -> tools -> interrupted Think,
|
||||
* followed by one ordinary completed response. The first response keeps
|
||||
* copy/clock but is not a legal branch point; the second is the real turn tail.
|
||||
* @param raw - Recorded seeded-history JSONL.
|
||||
* @returns A contiguous, closed two-turn fixture.
|
||||
*/
|
||||
function completedTailFixture(raw: string): string {
|
||||
const kept: string[] = []
|
||||
for (const line of raw.trimEnd().split('\n')) {
|
||||
const row = JSON.parse(line) as {
|
||||
type: string
|
||||
seq?: number
|
||||
seq0?: number
|
||||
data?: { content?: unknown[] }
|
||||
}
|
||||
const firstSeq = row.seq ?? row.seq0
|
||||
if (firstSeq !== undefined && firstSeq >= 101) break
|
||||
if (row.type === 'assistant/message' && row.seq === 64) {
|
||||
const content = row.data?.content
|
||||
if (!Array.isArray(content)) throw new Error('borrowed step-one assistant message has no content')
|
||||
content.splice(1, 0, { type: 'text', text: MID_TURN_TEXT })
|
||||
kept.push(JSON.stringify(row))
|
||||
} else {
|
||||
kept.push(line)
|
||||
}
|
||||
}
|
||||
const tail = [
|
||||
{ type: 'step/end', seq: 101, time: 1784974102749, data: { turn: 1, step: 2 } },
|
||||
{ type: 'turn/end', seq: 102, time: 1784974102750, data: { turn: 1, reason: { kind: 'aborted' } } },
|
||||
{ type: 'turn/start', seq: 103, time: 1784974103000, data: { turn: 2, trigger: { kind: 'message', source: { kind: 'user', rpcId: '{{rpcId}}' } } } },
|
||||
{ type: 'user/message', seq: 104, time: 1784974103001, data: { content: [{ type: 'text', text: SECOND_PROMPT }], source: { kind: 'user', rpcId: '{{rpcId}}' } }, surfaceOp: 'append' },
|
||||
{ type: 'step/start', seq: 105, time: 1784974103002, data: { turn: 2, step: 1 } },
|
||||
{ type: 'assistant/message', seq: 106, time: 1784974103003, data: { turn: 2, step: 1, content: [{ type: 'text', text: 'DONE' }], provenance: { provider: 'deepseek-official', model: 'deepseek-v4-flash' } }, sourceEventSeqs: [], surfaceOp: 'append' },
|
||||
{ type: 'step/end', seq: 107, time: 1784974103004, data: { turn: 2, step: 1 } },
|
||||
{ type: 'turn/end', seq: 108, time: 1784974103005, data: { turn: 2, reason: { kind: 'completed' } } },
|
||||
]
|
||||
return `${[...kept, ...tail.map(row => JSON.stringify(row))].join('\n')}\n`
|
||||
}
|
||||
|
||||
describe('web e2e: message IconActions and clocks on settled history', () => {
|
||||
let scaffold: WebScaffold
|
||||
@@ -38,8 +80,8 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
|
||||
await mkdir(sessionCwd, { recursive: true })
|
||||
await writeFile(join(sessionCwd, 'a.txt'), 'alpha\n')
|
||||
await writeFile(join(sessionCwd, 'b.txt'), 'beta\n')
|
||||
const raw = await readFile(SEED, 'utf8')
|
||||
expect(fixtureUserPrompts(raw), 'borrowed seed must carry the drive prompt').toEqual([PROMPT])
|
||||
const raw = completedTailFixture(await readFile(SEED, 'utf8'))
|
||||
expect(fixtureUserPrompts(raw), 'adapted seed must carry both prompts').toEqual([PROMPT, SECOND_PROMPT])
|
||||
await seedSession(scaffold, raw, SEED_ID)
|
||||
browser = await chromium.launch()
|
||||
page = await newEnglishPage(browser)
|
||||
@@ -53,7 +95,7 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
|
||||
await scaffold?.close()
|
||||
})
|
||||
|
||||
it.skipIf(MODE === 'record')('lists the seeded session and reveals user/assistant IconActions', async () => {
|
||||
it.skipIf(MODE === 'record')('enables branch only on the completed transcript tail', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-message-actions'))
|
||||
const groupRow = page.locator('[role="treeitem"]').first()
|
||||
await groupRow.waitFor({ timeout: 15_000 })
|
||||
@@ -61,16 +103,24 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
|
||||
const sessionRow = page.locator('[role="treeitem"]').nth(1)
|
||||
await sessionRow.waitFor({ timeout: 10_000 })
|
||||
await sessionRow.click()
|
||||
await expect.poll(() => page.getByText(MID_TURN_TEXT, { exact: true }).count(), { timeout: 15_000 }).toBe(1)
|
||||
await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 15_000 }).toBe(1)
|
||||
|
||||
// Focus-reveal the footers (hover:hover keeps them opacity-hidden until
|
||||
// hover/focus-within). User and each turn's last content assistant both
|
||||
// have copy + branch.
|
||||
// hover/focus-within). Every durable message footer keeps branch visible,
|
||||
// but only the final assistant at a completed transcript tail enables it.
|
||||
const copyButtons = page.getByRole('button', { name: 'Copy' })
|
||||
await expect.poll(() => copyButtons.count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(2)
|
||||
await expect.poll(() => copyButtons.count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(4)
|
||||
await copyButtons.first().focus()
|
||||
await expect.poll(() => page.getByRole('button', { name: 'Branch into a new conversation' }).count(), { timeout: 5_000 })
|
||||
.toBeGreaterThanOrEqual(2)
|
||||
const branchButtons = page.getByRole('button', { name: 'Branch into a new conversation' })
|
||||
await expect.poll(() => branchButtons.count(), { timeout: 5_000 }).toBe(4)
|
||||
await expect.poll(
|
||||
() => branchButtons.evaluateAll(buttons => buttons.map(button => button.getAttribute('aria-disabled'))),
|
||||
{ timeout: 5_000 },
|
||||
).toEqual(['true', 'true', 'true', null])
|
||||
await branchButtons.first().focus()
|
||||
await expect.poll(() => page.getByRole('tooltip').textContent(), { timeout: 5_000 })
|
||||
.toBe('Available only on the last message of a completed turn')
|
||||
await expect.poll(() => page.getByRole('button', { name: 'Edit' }).count(), { timeout: 5_000 }).toBe(0)
|
||||
}, 60_000)
|
||||
|
||||
@@ -89,8 +139,7 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
|
||||
|
||||
it.skipIf(MODE === 'record')('forks through the settled-message and session-row actions', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-message-fork'))
|
||||
// Exercise the assistant action specifically; package coverage pins the
|
||||
// user action separately at its own event seq.
|
||||
// The last message action belongs to the completed second-turn assistant.
|
||||
await page.getByRole('button', { name: 'Branch into a new conversation' }).last().click()
|
||||
await expect.poll(
|
||||
() => scaffold.ctx.agents.list().find(agent => agent.session.header.parentSession === SessionId(SEED_ID)),
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: "Run two shell commands: wait for cancellation, then write skipped.txt. {{date}} {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: "Using ONE run_code program: run bash `echo CODE_ROUND_OK`, then read the file missing.txt catching its error in the program. Return an object with both outcomes. Then reply DONE and stop. {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: "Use only Cordis tools. First call cordis_inspect with what \"temporary\". Then call cordis_mount with this exact code: \"return { name: \\\"snapshot-noop\\\", apply(ctx) {} }\". Read its returned id and call cordis_unmount with that exact id. After all three calls succeed, reply exactly CORDIS_UI_DONE and stop. {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: "Use the bash tool to run exactly: echo WEB_E2E_OK. Then reply with the single word DONE and stop. {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Reply with the single word LIGHTHOUSE and stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -8,12 +8,19 @@
|
||||
- button "Copy":
|
||||
- img
|
||||
- tooltip "Copy"
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Think The user wants me to read a.txt and b.txt, then reply with \"DONE\". Let me do both reads in parallel.":
|
||||
- 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.
|
||||
- paragraph: I will read both files before answering.
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn 7/25 {{clock}}
|
||||
- button "Read a.txt":
|
||||
- img
|
||||
- img
|
||||
@@ -28,6 +35,12 @@
|
||||
- img
|
||||
- img
|
||||
- text: Think Both files have been read. a.txt contains "alpha" and b.txt contains "beta". I'll now reply with DONE as instructed.
|
||||
- text: Stopped Now give the final answer. 7/25 {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- paragraph: DONE
|
||||
- button "Copy":
|
||||
- img
|
||||
@@ -42,4 +55,4 @@
|
||||
- text: deepseek-v4-flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok
|
||||
- text: 2 turns · 3 steps Tool call {{duration}} Cache hit 98% Input 7.8K tok · Output 103 tok
|
||||
|
||||
@@ -8,8 +8,9 @@
|
||||
- text: "plan Plan mode on. Use /plan off to leave. Plan a small change: add a --greeting flag to a CLI. Do not read or write any files. Call exit_plan_mode with a short plan of at most five bullet points. Once the plan is approved, reply with the single word DONE and stop. {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: "Use the ask_user_question tool to ask me exactly one question with id \"color\", question \"Which color do you prefer?\", header \"Pick one\", and two options: label \"Blue\" with description \"A cool recessive hue that reads as calm and trustworthy in long reading sessions and dense dashboards.\", and label \"Green\" with description \"A restful mid-spectrum hue with the highest perceived brightness, easiest on the eye over long sessions.\" After I answer, reply with the single word DONE and stop. {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
@@ -22,8 +23,9 @@
|
||||
- text: {{clock}} Edited queue item {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- paragraph: partial
|
||||
- status: Deep diving...
|
||||
- list:
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Reply with a one-sentence description of event sourcing, then stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop. 7/25 {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Think The user wants me to read a.txt and b.txt, then reply with \"DONE\". Let me do both reads in parallel.":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: "Use the read tool twice in one assistant message: read a.txt and b.txt. Then reply with the single word DONE and stop. 7/25 {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Think The user wants me to read a.txt and b.txt, then reply with \"DONE\". Let me do both reads in parallel.":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Use the ask_user_question tool to ask me exactly one question with id "checkpoint", question "Ready to continue?", header "Checkpoint", and options labeled "Yes" and "No". After I answer, reply with one short sentence acknowledging my answer and stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Use the ask_user_question tool to ask me exactly one question with id "checkpoint", question "Ready to continue?", header "Checkpoint", and options labeled "Yes" and "No". After I answer, reply with one short sentence acknowledging my answer and stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
@@ -24,8 +25,9 @@
|
||||
- text: "Interjection: include the word BANANA in your final reply. {{clock}}"
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- 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
|
||||
|
||||
@@ -12,8 +12,9 @@
|
||||
- text: Explain event sourcing in one sentence. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
@@ -30,8 +31,9 @@
|
||||
- text: {{clock}} Now give the same explanation to a human reader. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Think The user is asking for a one-sentence description of event sourcing. This is a straightforward knowledge question that doesn't require any skill loading or tool calls.":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -7,8 +7,9 @@
|
||||
- text: Use web_search to search exactly "DeepSeek Harness snapshot search". Then reply exactly SEARCH_DONE and stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- button "Branch into a new conversation" [disabled]:
|
||||
- img
|
||||
- text: Available only on the last message of a completed turn
|
||||
- button "Context injection":
|
||||
- img
|
||||
- img
|
||||
|
||||
@@ -11,6 +11,7 @@ import { chromium } from 'playwright'
|
||||
import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
|
||||
import { credentialRef } from '@deepseek-ai/dsh-credentials'
|
||||
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import { WEB_SEARCH_MAX_RESULTS } from '@deepseek-ai/dsh-tool-web'
|
||||
import {
|
||||
assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
|
||||
launchWebScaffold, recordFixture, watchConsole, webSnapshotMode, type WebScaffold,
|
||||
|
||||
Reference in New Issue
Block a user