⬆️ chore(desktop): bump agent-browser to v0.24.0#13550
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## canary #13550 +/- ##
==========================================
- Coverage 66.66% 66.66% -0.01%
==========================================
Files 1999 1999
Lines 165815 165815
Branches 16096 16093 -3
==========================================
- Hits 110546 110542 -4
- Misses 55145 55149 +4
Partials 124 124
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
|
@arvinxx - This is a desktop platform change (bumping agent-browser version). Please take a look. |
Sync the local-testing skill's agent-browser section with the upstream SKILL.md from vercel-labs/agent-browser. Adds new commands: batch, auth vault, semantic locators, annotated screenshots, clipboard, dialog handling, diff, streaming, iOS simulator, dashboard, cloud providers, and engine selection. https://claude.ai/code/session_01XnRtpGn54turwVXf4MziLM
b6ff319 to
2a98b65
Compare
There was a problem hiding this comment.
Pull request overview
This PR updates the desktop app’s bundled agent-browser version and refreshes the internal local-testing skill documentation to reflect newer agent-browser workflows and capabilities.
Changes:
- Bump the downloaded/bundled
agent-browserbinary version tov0.24.0. - Expand and restructure the local testing guide with updated
agent-browsercommand patterns, examples, and troubleshooting notes.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| apps/desktop/scripts/download-agent-browser.mjs | Updates the agent-browser release version used for the desktop-bundled download. |
| .agents/skills/local-testing/SKILL.md | Major refresh of local testing documentation, adding detailed agent-browser usage patterns and gotchas. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| import { fileURLToPath } from 'node:url'; | ||
|
|
||
| const VERSION = '0.20.1'; | ||
| const VERSION = '0.24.0'; |
There was a problem hiding this comment.
VERSION was bumped here, but there are other in-repo strings that still hardcode the bundled agent-browser version as v0.20.1 (e.g., packages/builtin-skills/src/agent-browser/content.ts and packages/builtin-skills/src/agent-browser/index.ts). Please update those to keep the user-facing skill prompts/descriptions consistent with the binary actually shipped by the desktop app, or centralize the version so it can’t drift.
| ## Prerequisites | ||
|
|
||
| - `agent-browser` CLI installed globally (`agent-browser --version`) | ||
| Install via `npm i -g agent-browser`, `brew install agent-browser`, or `cargo install agent-browser`. Run `agent-browser install` to download Chrome. Run `agent-browser upgrade` to update. |
There was a problem hiding this comment.
This section now recommends installing agent-browser globally via npm/brew/cargo, but the repository also treats agent-browser as bundled with the desktop app (and even mentions a specific bundled version elsewhere). To avoid confusion for contributors, consider clarifying when global installation is needed vs using the bundled binary, and (if you mention versions) keep the version in sync with the desktop-bundled version bump in this PR.
| Install via `npm i -g agent-browser`, `brew install agent-browser`, or `cargo install agent-browser`. Run `agent-browser install` to download Chrome. Run `agent-browser upgrade` to update. | |
| If you are testing through the desktop app, prefer the `agent-browser` binary bundled with the app/repository workflow when available. Only install `agent-browser` globally (`npm i -g agent-browser`, `brew install agent-browser`, or `cargo install agent-browser`) when you specifically need the standalone CLI outside the bundled setup. For a standalone install, run `agent-browser install` to download Chrome. Run `agent-browser upgrade` only for that global/standalone CLI. |
* ⬆️ chore(desktop): bump agent-browser to v0.24.0 https://claude.ai/code/session_01XnRtpGn54turwVXf4MziLM * 📝 chore: update agent-browser skill to match upstream v0.24.0 Sync the local-testing skill's agent-browser section with the upstream SKILL.md from vercel-labs/agent-browser. Adds new commands: batch, auth vault, semantic locators, annotated screenshots, clipboard, dialog handling, diff, streaming, iOS simulator, dashboard, cloud providers, and engine selection. https://claude.ai/code/session_01XnRtpGn54turwVXf4MziLM --------- Co-authored-by: Claude <noreply@anthropic.com>
# 🚀 release: 20260407 This release includes **148 commits**. Key updates are below. - **Response API tool execution is more capable and reliable** — Added hosted builtin tools + client-side function tools and improved tool-call streaming/completion behavior. [#13406](#13406) [#13414](#13414) [#13506](#13506) [#13555](#13555) - **Input and composition UX upgraded** — Added AI input auto-completion and multiple chat-input stability fixes. [#13458](#13458) [#13551](#13551) [#13481](#13481) - **Model/provider compatibility improved** — Better Gemini/Google tool schema handling and additional model updates. [#13429](#13429) [#13465](#13465) [#13613](#13613) - **Desktop and CLI reliability improved** — Gateway WebSocket support and desktop runtime upgrades. [#13608](#13608) [#13550](#13550) [#13557](#13557) - **Security hardening continued** — Fixed auth and sanitization risks and upgraded vulnerable dependencies. [#13535](#13535) [#13529](#13529) [#13479](#13479) ### Models & Providers - Added/updated support for `glm-5v-turbo`, GLM-5.1 updates, and qwen3.5-omni series. [#13487](#13487) [#13405](#13405) [#13422](#13422) - Added additional ImageGen providers/models (Wanxiang 2.7 and Keling from Qwen). [#13478](#13478) - Improved Gemini/Google tool schema and compatibility handling across runtime paths. [#13429](#13429) [#13465](#13465) [#13613](#13613) ### Response API & Runtime - Added hosted builtin tools in Response API and client-side function tool execution support. [#13406](#13406) [#13414](#13414) - Improved stream tool-call argument handling and `response.completed` output correctness. [#13506](#13506) [#13555](#13555) - Improved runtime error/context handling for intervention and provider edge cases. [#13420](#13420) [#13607](#13607) ### Desktop App - Bumped desktop dependencies and runtime integrations (`agent-browser`, `electron`). [#13550](#13550) [#13557](#13557) - Simplified desktop release channel setup by removing nightly release flow. [#13480](#13480) ### CLI - Added OpenClaw migration command. [#13566](#13566) - Added local device binding support for `lh agent run`. [#13277](#13277) - Added WebSocket gateway support and reconnect reliability improvements. [#13608](#13608) [#13418](#13418) ### Security - Removed risky `apiKey` fallback behavior in webapi auth path to prevent bypass risk. [#13535](#13535) - Sanitized HTML artifact rendering and iframe sandboxing to reduce XSS-to-RCE risk. [#13529](#13529) - Upgraded nodemailer to v8 to address SMTP command injection advisory. [#13479](#13479) ### Bug Fixes - Fixed image generation model default switch issues. [#13587](#13587) - Fixed subtopic re-fork message scope behavior and agent panel reset edge cases. [#13606](#13606) [#13556](#13556) - Fixed chat-input freeze on paste and mention plugin behavior. [#13551](#13551) [#13415](#13415) - Fixed auth/social sign-in and settings UX edge cases. [#13368](#13368) [#13392](#13392) [#13338](#13338) ### Credits Huge thanks to these contributors: @chriszf @hardy-one @Innei @lijian @neko @OctopusNote @rdmclin2 @rivertwilight @RylanCai @suyua9 @sxjeru @Tsuki @wangyk @WindSpiritSR @yizhuo @YuTengjing @hezhijie0327 @arvinxx
https://claude.ai/code/session_01XnRtpGn54turwVXf4MziLM