mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-08-07 21:38:53 +00:00
* feat(browser): add agentic browser control
* fix(frontend): format browser view changes
* fix(browser): keep browser optional and isolate sidecar layout
* fix(browser): address PR review security and IME findings
- Nginx: add a browser-stream WebSocket location before the generic
/api/threads regex so Live upgrades instead of downgrading to HTTP
(both nginx.conf and nginx.local.conf).
- Ownership: require an existing owned thread for the WS stream and REST
navigate, and tear down the browser session on thread deletion so a
later caller cannot reuse a retained page/cookies by guessing the id.
- SSRF: enforce the URL policy at the browser request boundary via a
context-level route guard covering redirects, popups, iframes, and
subresources (skipped for CDP-attached Chrome).
- IME: skip key forwarding while a composition is active so confirming a
CJK candidate with Enter no longer submits the remote page form.
Adds regression tests for the request guard, session teardown on delete,
and the composing-Enter key decision.
* fix(frontend): smooth streaming in long tool threads
* Revert "fix(frontend): smooth streaming in long tool threads"
This reverts commit f0462516eabe77f138d4027ea1c714fb226683cf.
* fix(browser): address review security and lifecycle findings
- Reject cross-origin WebSocket upgrades on the live browser stream
(Origin allow-list reuse of CORS/same-origin helpers) to close a
WS-CSRF hole, and fail closed when the ownership store is absent.
- Warn when a CDP-attached session runs with the SSRF request guard
off, and drop the unreachable CDP screencast teardown dead code.
- Read browser session launch config from a single canonical source
(browser_navigate) so it is deterministic regardless of call order.
- Bound per-thread Chromium accumulation with idle-timeout eviction
and an LRU max-sessions cap.
- Reset the Live reconnect counter on a successful open so the stream
can't permanently stall after the cumulative attempt cap.
* fix(frontend): reduce long tool thread render stalls
Reuse stable historical message groups during streaming, defer heavy Markdown and browser previews, and lazy-decode message images.
* fix(browser): keep live control responsive during continuous input
Why: Manual browser control felt laggy — a physical click ran the remote
Playwright click three times and each non-move input synchronously awaited a
JPEG screenshot, so events queued behind capture (queue wait up to ~237ms).
The first async attempt used a trailing-edge debounce, which froze the visible
page until a wheel/keyboard gesture stopped ("scroll finishes, then it jumps").
What:
- Frontend forwards one `click` per physical click instead of also emitting
`down`/`up`, so the remote page is not clicked twice per gesture.
- Backend detaches live-frame capture from input dispatch: non-move actions
start a rate-limited background refresh loop (leading frame + bounded cadence)
that keeps emitting frames while input continues and never blocks dispatch.
- Add regression tests: input dispatch no longer awaits the screenshot, rapid
inputs coalesce, and continuous input keeps refreshing before it stops.
Scenarios: Verified in the live Browser panel — a single click completes in
~57ms (was blocked behind a 171ms capture), and a 1.14s sustained wheel gesture
renders ~7 frames throughout the scroll instead of one frame after it ends.
* fix(browser): harden worker and session lifecycle
* fix(browser): address latest review feedback
* fix(frontend): preserve optimistic new-chat message
* test(e2e): preserve mocked message run ids
* fix(browser): address capability review feedback
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
108 lines
3.6 KiB
TypeScript
108 lines
3.6 KiB
TypeScript
import { describe, expect, it } from "@rstest/core";
|
||
import { createElement, type ImgHTMLAttributes } from "react";
|
||
import { renderToStaticMarkup } from "react-dom/server";
|
||
|
||
import { MarkdownContent } from "@/components/workspace/messages/markdown-content";
|
||
|
||
function renderMarkdown(
|
||
content: string,
|
||
isLoading: boolean,
|
||
components?: Parameters<typeof MarkdownContent>[0]["components"],
|
||
) {
|
||
return renderToStaticMarkup(
|
||
createElement(MarkdownContent, { content, isLoading, components }),
|
||
);
|
||
}
|
||
|
||
describe("MarkdownContent streaming code blocks", () => {
|
||
it("renders fenced code without Streamdown highlighting while streaming", () => {
|
||
const html = renderMarkdown(
|
||
["```html", '<main class="report">Hello</main>', "```"].join("\n"),
|
||
true,
|
||
);
|
||
|
||
expect(html).toContain("data-streaming-code-block");
|
||
expect(html).toContain('data-language="html"');
|
||
expect(html).toContain(
|
||
"<main class="report">Hello</main>",
|
||
);
|
||
expect(html).not.toContain('data-streamdown="code-block"');
|
||
});
|
||
|
||
it("keeps inline code inline while streaming", () => {
|
||
const html = renderMarkdown("Use `const answer = 42` here.", true);
|
||
|
||
expect(html).toContain('data-streaming-inline-code="true"');
|
||
expect(html).not.toContain("data-streaming-code-block");
|
||
});
|
||
|
||
it("keeps an unlabeled single-line fence as a block while streaming", () => {
|
||
const html = renderMarkdown(["```", "x", "```"].join("\n"), true);
|
||
|
||
expect(html).toContain("data-streaming-code-block");
|
||
expect(html).not.toContain('data-streaming-inline-code="true"');
|
||
});
|
||
|
||
it("restores Streamdown highlighting after streaming finishes", () => {
|
||
const html = renderMarkdown(
|
||
["```html", '<main class="report">Hello</main>', "```"].join("\n"),
|
||
false,
|
||
);
|
||
|
||
expect(html).toContain('data-streamdown="code-block"');
|
||
expect(html).not.toContain("data-streaming-code-block");
|
||
});
|
||
|
||
it("preserves custom non-code renderers while streaming", () => {
|
||
const html = renderMarkdown(
|
||
"[Docs](https://example.com)\n\n",
|
||
true,
|
||
{
|
||
a: ({ children, href }) =>
|
||
createElement("a", { "data-custom-link": true, href }, children),
|
||
img: (props: ImgHTMLAttributes<HTMLImageElement>) =>
|
||
createElement("img", { ...props, "data-custom-image": true }),
|
||
},
|
||
);
|
||
|
||
expect(html).toContain('data-custom-link="true"');
|
||
expect(html).toContain('data-custom-image="true"');
|
||
});
|
||
|
||
it("preserves a caller-provided code renderer while streaming", () => {
|
||
const html = renderMarkdown(
|
||
["```html", "<main />", "```"].join("\n"),
|
||
true,
|
||
{
|
||
code: ({ children }) =>
|
||
createElement("code", { "data-custom-code": true }, children),
|
||
},
|
||
);
|
||
|
||
expect(html).toContain('data-custom-code="true"');
|
||
expect(html).toContain("data-streaming-code-block");
|
||
});
|
||
|
||
it("does not paint an initial large streaming chunk all at once", () => {
|
||
const content = "x".repeat(120);
|
||
|
||
expect(renderMarkdown(content, true)).not.toContain(content);
|
||
expect(renderMarkdown(content, false)).toContain(content);
|
||
});
|
||
});
|
||
|
||
describe("MarkdownContent strikethrough", () => {
|
||
it("preserves single tildes in temperature ranges", () => {
|
||
const html = renderMarkdown("周六23~30℃;周日22~30℃", false);
|
||
|
||
expect(html).toContain("周六23~30℃;周日22~30℃");
|
||
expect(html).not.toContain("<del>");
|
||
});
|
||
|
||
it("continues to render double-tilde strikethrough", () => {
|
||
const html = renderMarkdown("状态:~~已取消~~", false);
|
||
|
||
expect(html).toContain("<del>已取消</del>");
|
||
});
|
||
});
|