Files
paseo/packages/app/e2e/browser/agent-stream-smoothness.spec.ts
8d424e039e Reduce rendering cost in long chats (#7052)
* perf(app): stop re-walking the timeline on every streamed delta

Every coalesced delta rebuilds the stream render model with the same
tail. The model re-sliced the tail at the history-window start on every
call, so the rendered tail was a fresh array per delta and every WeakMap
keyed on it (ordering, history split, turn timing, the layout history
cache, row revision) missed each time. Cache the slice by tail identity
and window start.

Turn timing then still walked the whole rendered tail per delta and
allocated a new assistant-timing Map, which the layout memo depends on.
Split the walk: the tail is walked once per tail identity and the head is
walked from the carried open turn per delta. The Map keeps its identity
while the head adds no completed turn.

Adds identity-contract tests and a vitest bench for the per-delta
pipeline. 200 deltas over a 2,000-item timeline, mean per run:
default mounted window 5.68ms -> 2.82ms, history fully revealed
16.95ms -> 1.81ms.

Fixes #4816

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* perf(app): keep the stream view's per-delta work bounded by the head

The chat outline concatenated tail and head, reduced over the result in
the render body, and rebuilt jumpToPrompt on every delta even when the
outline was disabled, which is every native viewport. Memoize the tail's
contribution, scan only the head per delta, do nothing while disabled,
make jumpToPrompt a stable event so the rail's memo holds, and republish
the active prompt only when the index or reading position changes.

The view built a Set of every mounted id plus the live head per delta for
the outline's pending-jump check; key it on mounted history only and
treat live head rows as always mounted. Split plugin projection so a head
change does not re-project the tail, memoize the history-window boundary
lookup, and read the turn presentation's submission flag with some()
instead of allocating a filtered array.

Refs #4816

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* test(app): confirm full history before measuring streaming

---------

Co-authored-by: Ivan Malison <IvanMalison@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: paseo-bot[bot] <266920839+paseo-bot[bot]@users.noreply.github.com>
2026-10-16 01:15:40 +02:00

193 lines
7.4 KiB
TypeScript
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import { test, expect } from "../support/fixtures";
import { awaitAssistantMessage } from "../support/helpers/agent-stream";
import { startRunningMockAgent, submitMessage } from "../support/helpers/composer";
import {
seedLongMockAgentTimeline,
openAgentTimeline,
scrollTimelineUntilOlderHistoryIsReachable,
scrollTimelineToNewestLoadedEdge,
expectTimelinePromptVisible,
} from "../support/helpers/timeline-pagination";
import {
sampleStreamFrames,
summarizeStreamSmoothness,
} from "../support/helpers/stream-smoothness";
/**
* Streaming smoothness, measured on the path the user actually sees.
*
* The mock provider's "bursty-stream" model emits tokens in uneven runs separated
* by idle gaps, which is how real models arrive. Sampling and the statistics live
* in ../support/helpers/stream-smoothness.ts, which also documents what the two
* numbers mean.
*
* Budgets are deliberately loose. This spec exists to catch a regression in the
* shape of the stream, not to pin exact numbers on shared CI hardware. For
* reference, on a local dev daemon the paced reveal measures a CV around 1.3–1.5
* against 2.7 when painting deltas as they arrive.
*/
const SAMPLE_WINDOW_MS = 6_000;
const CHARS_PER_FRAME_CV_BUDGET = 2;
const UPDATE_GAP_P95_BUDGET_MS = 250;
const REACT_COMMIT_P95_BUDGET_MS = 12;
const REACT_COMMIT_COUNT_BUDGET = 600;
const RUN_AGENT_STREAM_PERF = process.env.PASEO_AGENT_STREAM_PERF_E2E === "1";
const agentStreamPerfDescribe = RUN_AGENT_STREAM_PERF ? test.describe : test.describe.skip;
interface ReactCommit {
id: string;
phase: "mount" | "update" | "nested-update";
actualDuration: number;
baseDuration: number;
startTime: number;
commitTime: number;
}
agentStreamPerfDescribe("Agent stream smoothness", () => {
test("reveals bursty model output at a steady rate", async ({ page }, testInfo) => {
test.setTimeout(120_000);
await page.addInitScript(() => {
Reflect.set(globalThis, "__PASEO_RENDER_PROFILE_ENABLED__", true);
});
const agent = await startRunningMockAgent(page, {
prefix: "stream-smoothness-",
model: "bursty-stream",
prompt: "Stream bursty output for smoothness measurement.",
});
try {
await awaitAssistantMessage(page);
await page.evaluate(() => {
const reset = Reflect.get(globalThis, "__PASEO_RESET_RENDER_PROFILE__");
if (typeof reset !== "function") {
throw new Error("Render profiler did not initialize");
}
reset();
});
const samples = await sampleStreamFrames(page, { sampleWindowMs: SAMPLE_WINDOW_MS });
const report = summarizeStreamSmoothness(samples, SAMPLE_WINDOW_MS);
const reactCommits = await readStreamReactCommits(page);
const reactReport = summarizeReactCommits(reactCommits);
await testInfo.attach("agent-stream-smoothness-report", {
body: JSON.stringify(report, null, 2),
contentType: "application/json",
});
await testInfo.attach("agent-stream-react-profile", {
body: JSON.stringify(reactReport, null, 2),
contentType: "application/json",
});
console.log(`[perf] Agent stream React: ${JSON.stringify(reactReport)}`);
console.log(`[perf] Agent stream smoothness: ${JSON.stringify(report)}`);
expect(
report.growthFrames,
"the stream must actually produce text during the sample window",
).toBeGreaterThan(20);
expect(
report.charsPerFrameCv,
`characters painted per frame should be steady (cv < ${CHARS_PER_FRAME_CV_BUDGET})`,
).toBeLessThan(CHARS_PER_FRAME_CV_BUDGET);
expect(
report.updateGapP95Ms,
`the text should not stall (p95 gap < ${UPDATE_GAP_P95_BUDGET_MS}ms)`,
).toBeLessThan(UPDATE_GAP_P95_BUDGET_MS);
expect(reactReport.count, "streaming should produce measured React commits").toBeGreaterThan(
20,
);
expect(
reactReport.count,
`the reveal should cap commits below ${REACT_COMMIT_COUNT_BUDGET} per sample window`,
).toBeLessThan(REACT_COMMIT_COUNT_BUDGET);
expect(
reactReport.actualDurationP95Ms,
`React commits should stay below ${REACT_COMMIT_P95_BUDGET_MS}ms at p95`,
).toBeLessThan(REACT_COMMIT_P95_BUDGET_MS);
} finally {
await agent.cleanup();
}
});
test("keeps streaming work bounded after revealing older history", async ({ page }, testInfo) => {
test.setTimeout(120_000);
await page.addInitScript(() => {
Reflect.set(globalThis, "__PASEO_RENDER_PROFILE_ENABLED__", true);
});
const agent = await seedLongMockAgentTimeline({ turns: 80, liveTurns: "thirty-minute-stream" });
try {
await openAgentTimeline(page, agent);
await expect(page.getByRole("textbox", { name: "Message agent..." }).first()).toBeVisible();
await scrollTimelineUntilOlderHistoryIsReachable(page, agent.oldestPrompt);
await expectTimelinePromptVisible(page, agent.oldestPrompt);
await scrollTimelineToNewestLoadedEdge(page);
await submitMessage(page, "Stream a long answer after reading older messages.");
await awaitAssistantMessage(page);
for (let sample = 0; sample < 3; sample += 1) {
await page.evaluate(() => globalThis.__PASEO_RESET_RENDER_PROFILE__?.());
const frames = await sampleStreamFrames(page, { sampleWindowMs: SAMPLE_WINDOW_MS });
const smoothness = summarizeStreamSmoothness(frames, SAMPLE_WINDOW_MS);
const react = summarizeReactCommits(await readStreamReactCommits(page));
await testInfo.attach(`revealed-history-stream-${sample}`, {
body: JSON.stringify({ smoothness, react }, null, 2),
contentType: "application/json",
});
console.log(`[perf] Revealed history stream: ${JSON.stringify({ smoothness, react })}`);
expect(smoothness.growthFrames).toBeGreaterThan(20);
expect(react.count).toBeGreaterThan(20);
expect(react.actualDurationP95Ms).toBeLessThan(REACT_COMMIT_P95_BUDGET_MS);
}
} finally {
await agent.cleanup();
}
});
});
async function readStreamReactCommits(
page: Parameters<typeof sampleStreamFrames>[0],
): Promise<ReactCommit[]> {
return await page.evaluate(() => {
const samples = Reflect.get(globalThis, "__PASEO_RENDER_PROFILE__");
if (!Array.isArray(samples)) {
return [];
}
return samples.filter(
(sample): sample is ReactCommit =>
typeof sample === "object" &&
sample !== null &&
typeof Reflect.get(sample, "id") === "string" &&
Reflect.get(sample, "id").startsWith("AgentStreamSection:"),
);
});
}
function summarizeReactCommits(commits: readonly ReactCommit[]) {
const durations = commits
.map((commit) => commit.actualDuration)
.sort((left, right) => left - right);
const total = durations.reduce((sum, duration) => sum + duration, 0);
return {
count: commits.length,
actualDurationTotalMs: round2(total),
actualDurationMeanMs: round2(commits.length > 0 ? total / commits.length : 0),
actualDurationP50Ms: percentile(durations, 50),
actualDurationP95Ms: percentile(durations, 95),
actualDurationMaxMs: durations.at(-1) ?? 0,
};
}
function round2(value: number): number {
return Math.round(value * 100) / 100;
}
function percentile(sorted: readonly number[], percentileValue: number): number {
if (sorted.length === 0) {
return 0;
}
return sorted[
Math.min(sorted.length - 1, Math.floor((sorted.length - 1) * (percentileValue / 100)))
];
}