Files
gitmost/apps/client/src/features/ai-chat/components/reasoning-block.test.tsx
T
agent_coder 2d30ad1fa2 fix(ai-chat): parse reasoning markdown only while expanded to stop the thinking-stream hang (#302)
The reasoning block memoized its markdown render on [trimmed] alone, so as the
reasoning text streamed in it re-parsed the whole, ever-growing text (marked +
DOMPurify) on every throttled delta (~20Hz) — an O(n^2) CPU storm that pinned the
main thread and froze the chat during a long "thinking" phase. Worse, the block is
collapsed by default, so all that parsing was for a hidden body the user never sees
(html is only shown inside <Collapse in={open}>).

Gate the parse on `open`: collapsed shows the cheap raw-text fallback and does no
markdown parsing; expanding parses the current text once (an instant user click), and
further streaming while open is the normal per-delta append render, like the answer.

Test: assert renderChatMarkdown is not called while collapsed and is called once on
expand.

closes #302

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-03 05:01:37 +03:00

88 lines
3.8 KiB
TypeScript

import { describe, it, expect, vi } from "vitest";
import { render, screen, fireEvent } from "@testing-library/react";
import { MantineProvider } from "@mantine/core";
// Spy on the markdown renderer so we can assert it is NOT called while the block
// is collapsed (the #302 fix) and IS called once on expand. The count/fallback
// tests don't depend on real markdown, so a light stub is safe.
vi.mock("@/features/ai-chat/utils/markdown.ts", () => ({
renderChatMarkdown: vi.fn((md: string) => `<p>${md}</p>`),
}));
// Stub react-i18next so `t` returns the key with `{{count}}` interpolated. This
// keeps the assertions on the component's OWN count logic (authoritative vs
// estimate) rather than on translation, and mirrors the t-mock pattern used by
// other component tests in the repo.
vi.mock("react-i18next", () => ({
useTranslation: () => ({
t: (key: string, opts?: { count?: number }) =>
opts && typeof opts.count === "number"
? key.replace("{{count}}", String(opts.count))
: key,
}),
}));
import ReasoningBlock from "./reasoning-block";
import { estimateTokens } from "@/features/ai-chat/utils/count-stream-tokens.ts";
import { renderChatMarkdown } from "@/features/ai-chat/utils/markdown.ts";
// matchMedia (read by MantineProvider) is stubbed globally in vitest.setup.ts.
function renderBlock(props: { text: string; tokens?: number }) {
return render(
<MantineProvider>
<ReasoningBlock {...props} />
</MantineProvider>,
);
}
describe("ReasoningBlock", () => {
it("shows the authoritative count in the header when tokens > 0", () => {
// Text "thinking…" estimates to ceil(9/4) = 3, but the authoritative 42
// must win, so the header shows 42 (and NOT the 3-token estimate).
renderBlock({ text: "thinking…", tokens: 42 });
expect(screen.getByText("Thinking · 42 tokens")).toBeDefined();
expect(screen.queryByText("Thinking · 3 tokens")).toBeNull();
});
it("falls back to the text-length estimate when no authoritative tokens", () => {
const text = "some reasoning prose that streams in";
const estimate = estimateTokens(text);
renderBlock({ text });
expect(estimate).toBeGreaterThan(0);
expect(screen.getByText(new RegExp(`${estimate} tokens`))).toBeDefined();
});
it("header-only when text is empty but an authoritative count is present", () => {
renderBlock({ text: "", tokens: 17 });
expect(screen.getByText(/17 tokens/)).toBeDefined();
// No disclosure body to expand: the toggle button is disabled.
const button = screen.getByRole("button");
expect((button as HTMLButtonElement).disabled).toBe(true);
});
it("renders the reasoning body (markdown or raw-text fallback)", () => {
renderBlock({ text: "**bold** reasoning", tokens: 5 });
// The toggle is enabled because there IS body text to expand.
const button = screen.getByRole("button");
expect((button as HTMLButtonElement).disabled).toBe(false);
// The body prose renders (markdown -> sanitized html, or raw-text fallback);
// either way the text is present in the document.
expect(screen.getByText(/reasoning/)).toBeDefined();
});
it("does not parse the reasoning markdown while collapsed; parses on expand (#302)", () => {
const renderSpy = vi.mocked(renderChatMarkdown);
renderSpy.mockClear();
renderBlock({ text: "**bold** reasoning", tokens: 5 });
// Collapsed is the default. The expensive markdown parse (marked + DOMPurify)
// must NOT run for the hidden body — that O(n^2) re-parse on every streamed
// delta is exactly what froze the chat (#302). The collapsed body shows the
// cheap raw-text fallback instead.
expect(renderSpy).not.toHaveBeenCalled();
// Expanding parses the current text exactly once (a user-initiated click).
fireEvent.click(screen.getByRole("button"));
expect(renderSpy).toHaveBeenCalledTimes(1);
});
});