Compare commits

...
Author SHA1 Message Date
leeguooooo 11eab471f1 chore(release): bump version to 0.14.0-fork.4 2026-02-25 10:10:26 +09:00
leeguooooo aa256e30c7 Merge remote-tracking branch 'upstream/main'
# Conflicts:
#	README.md
#	cli/src/connection.rs
#	cli/src/flags.rs
#	cli/src/main.rs
#	src/browser.ts
#	src/protocol.ts
2026-02-25 10:06:20 +09:00
Chris Tate c0e2b80f8c add dogfood skill for agent-driven exploratory qa (#538)
* dogfood skill

* evals

* haiku

* fixes

* caching

* fixes

* don't use npx
2026-02-24 11:35:50 -06:00
Chris Tate f319195974 add --selector flag to scroll command (#537)
* add --selector flag to scroll command

The `scroll` command uses `window.scrollBy()`, which has no effect on apps
that use custom scrollable containers (e.g. a nested div with overflow-y: auto).

The backend `handleScroll` already supports a `selector` parameter, but the CLI
never exposed it. This adds `-s` / `--selector` to the `scroll` command so users
can target a specific scrollable element:

    agent-browser scroll down 500 --selector "div.scroll-container"

Also fixes the backend to apply `direction`/`amount` when a selector is present
(previously those fields were only used in the no-selector branch).

Closes #501

* fixes
2026-02-24 07:40:46 -06:00
Chris Tate 77f2caa1bc feat: add --download-path option (#536)
* feat: add --download-path option

Adds a `--download-path` flag (and `AGENT_BROWSER_DOWNLOAD_PATH` env / `downloadPath` config key) to set a default download directory for browser downloads.

Without this, Playwright stores downloads in a temp directory that is deleted when the browser closes. The new option passes through to Playwright's `downloadsPath` on `launch()` and `launchPersistentContext()`.

Fixes #507

* improvements

* fixes

* fixes
2026-02-24 07:22:55 -06:00
leeguooooo 6f1dd39121 chore(clawhub): 改为本地 pre-push 自动同步 skill 2026-02-24 18:10:05 +09:00
leeguooooo 85d18799a4 feat(skill): 新增 agent-browser-stealth 的 OpenClaw skill 与 ClawHub 自动同步 2026-02-24 18:05:29 +09:00
leeguooooo 43e781a8d3 docs(readme): 精简文档并聚焦反爬能力 2026-02-24 18:00:19 +09:00
leeguooooo 25e8719e51 docs(readme): 补充 --delay 文本转义与 stealth 行为说明 2026-02-24 17:58:13 +09:00
leeguooooo ec011f46ff fix(stealth): 修复 launch 选项与测试基线不一致问题
在 stealth 默认策略下保留自定义 user-agent,不再被 CDP 覆盖。

同步更新 protocol/browser/launch/file-access 相关测试预期,并放宽 browser.test 的 hook 超时以消除偶发超时。
2026-02-24 17:42:12 +09:00
leeguooooo aef8fcc038 ci(release): 修复 OIDC 发布认证链路
移除 setup-node 的 registry-url 注入,避免发布步骤继承无效 NODE_AUTH_TOKEN。

发布前升级 npm 到 v11,使用独立 npmrc 并启用 provenance,以匹配 npm trusted publishing。
2026-02-24 17:24:20 +09:00
leeguooooo 96582b79fd ci(release): 调整 trusted publishing 发布流程
将 changesets/action 改为仅处理 version/PR,不再由其执行 publish。

新增发布前版本检查与独立 pnpm ci:publish 步骤,避免 OIDC 发布在 action 内失败。
2026-02-24 17:20:17 +09:00
34 changed files with 1816 additions and 1239 deletions
+42 -4
View File
@@ -142,8 +142,8 @@ jobs:
needs: build-binaries
runs-on: ubuntu-latest
outputs:
published: ${{ steps.changesets.outputs.published }}
publishedPackages: ${{ steps.changesets.outputs.publishedPackages }}
published: ${{ steps.publish_metadata.outputs.published }}
publishedPackages: ${{ steps.publish_metadata.outputs.publishedPackages }}
steps:
- name: Checkout Repo
uses: actions/checkout@v4
@@ -160,7 +160,6 @@ jobs:
with:
node-version: '22'
cache: pnpm
registry-url: 'https://registry.npmjs.org'
- name: Install Dependencies
run: pnpm install --frozen-lockfile
@@ -215,12 +214,51 @@ jobs:
uses: changesets/action@v1
with:
version: pnpm ci:version
publish: pnpm ci:publish
title: 'chore: version packages'
commit: 'chore: version packages'
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Check if publish is needed
id: publish_check
if: steps.changesets.outputs.hasChangesets == 'false'
run: |
LOCAL_VERSION=$(node -p "require('./package.json').version")
REMOTE_VERSION=$(npm view agent-browser-stealth version 2>/dev/null || echo "")
echo "local_version=$LOCAL_VERSION" >> "$GITHUB_OUTPUT"
echo "remote_version=$REMOTE_VERSION" >> "$GITHUB_OUTPUT"
if [ "$LOCAL_VERSION" != "$REMOTE_VERSION" ]; then
echo "needs_publish=true" >> "$GITHUB_OUTPUT"
else
echo "needs_publish=false" >> "$GITHUB_OUTPUT"
fi
echo "Local: $LOCAL_VERSION"
echo "Remote: ${REMOTE_VERSION:-<none>}"
- name: Publish to npm (trusted publishing)
id: publish_npm
if: steps.changesets.outputs.hasChangesets == 'false' && steps.publish_check.outputs.needs_publish == 'true'
env:
NODE_AUTH_TOKEN: ""
NPM_CONFIG_USERCONFIG: /home/runner/work/_temp/trusted-npmrc
NPM_CONFIG_PROVENANCE: "true"
run: |
npm install -g npm@^11
npm --version
printf "registry=https://registry.npmjs.org/\n" > "$NPM_CONFIG_USERCONFIG"
pnpm ci:publish
- name: Set release outputs
id: publish_metadata
run: |
if [ "${{ steps.publish_npm.outcome }}" = "success" ]; then
echo "published=true" >> "$GITHUB_OUTPUT"
echo "publishedPackages=[{\"name\":\"agent-browser-stealth\",\"version\":\"${{ steps.publish_check.outputs.local_version }}\"}]" >> "$GITHUB_OUTPUT"
else
echo "published=false" >> "$GITHUB_OUTPUT"
echo "publishedPackages=[]" >> "$GITHUB_OUTPUT"
fi
# Create GitHub release with binaries after npm publish
github-release:
name: Create GitHub Release
+5
View File
@@ -27,10 +27,15 @@ npm-debug.log*
.DS_Store
Thumbs.db
# Python
__pycache__/
# Test artifacts
*.png
*.jpeg
*.jpg
*.webm
test/e2e/.dogfood-output/
# Package manager
package-lock.json
+8
View File
@@ -0,0 +1,8 @@
if [ "${SKIP_CLAWHUB_SYNC:-0}" = "1" ]; then
echo "Skipping ClawHub sync (SKIP_CLAWHUB_SYNC=1)"
exit 0
fi
pnpm run clawhub:sync || {
echo "ClawHub sync failed. Push continues. Run 'pnpm run clawhub:sync' manually after fixing login/network."
}
+93 -1143
View File
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -4,7 +4,7 @@ version = 4
[[package]]
name = "agent-browser-stealth"
version = "0.14.0-fork.3"
version = "0.14.0-fork.4"
dependencies = [
"base64",
"dirs",
+1 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "agent-browser-stealth"
version = "0.14.0-fork.3"
version = "0.14.0-fork.4"
edition = "2021"
description = "Stealth browser automation CLI for AI agents with anti-bot evasions"
license = "Apache-2.0"
+125 -6
View File
@@ -369,12 +369,48 @@ pub fn parse_command(args: &[String], flags: &Flags) -> Result<Value, ParseError
// === Scroll ===
"scroll" => {
let dir = rest.first().unwrap_or(&"down");
let amount = rest
.get(1)
.and_then(|s| s.parse::<i32>().ok())
.unwrap_or(300);
Ok(json!({ "id": id, "action": "scroll", "direction": dir, "amount": amount }))
let mut cmd = json!({ "id": id, "action": "scroll" });
let obj = cmd.as_object_mut().unwrap();
let mut positional_index = 0;
let mut i = 0;
while i < rest.len() {
match rest[i] {
"-s" | "--selector" => {
if let Some(s) = rest.get(i + 1) {
obj.insert("selector".to_string(), json!(s));
i += 1;
} else {
return Err(ParseError::MissingArguments {
context: "scroll --selector".to_string(),
usage: "scroll [direction] [amount] [--selector <sel>]",
});
}
}
arg if arg.starts_with('-') => {}
_ => {
match positional_index {
0 => {
obj.insert("direction".to_string(), json!(rest[i]));
}
1 => {
if let Ok(n) = rest[i].parse::<i32>() {
obj.insert("amount".to_string(), json!(n));
}
}
_ => {}
}
positional_index += 1;
}
}
i += 1;
}
if !obj.contains_key("direction") {
obj.insert("direction".to_string(), json!("down"));
}
if !obj.contains_key("amount") {
obj.insert("amount".to_string(), json!(300));
}
Ok(cmd)
}
"scrollintoview" | "scrollinto" => {
let sel = rest.first().ok_or_else(|| ParseError::MissingArguments {
@@ -1988,8 +2024,10 @@ mod tests {
cli_proxy_bypass: false,
cli_allow_file_access: false,
cli_annotate: false,
cli_download_path: false,
annotate: false,
color_scheme: None,
download_path: None,
}
}
@@ -3565,4 +3603,85 @@ mod tests {
ParseError::MissingArguments { .. }
));
}
// === Scroll Tests ===
#[test]
fn test_scroll_defaults() {
let cmd = parse_command(&args("scroll"), &default_flags()).unwrap();
assert_eq!(cmd["action"], "scroll");
assert_eq!(cmd["direction"], "down");
assert_eq!(cmd["amount"], 300);
assert!(cmd.get("selector").is_none());
}
#[test]
fn test_scroll_direction_and_amount() {
let cmd = parse_command(&args("scroll up 200"), &default_flags()).unwrap();
assert_eq!(cmd["action"], "scroll");
assert_eq!(cmd["direction"], "up");
assert_eq!(cmd["amount"], 200);
}
#[test]
fn test_scroll_with_selector() {
let cmd = parse_command(
&args("scroll down 500 --selector div.scroll-container"),
&default_flags(),
)
.unwrap();
assert_eq!(cmd["action"], "scroll");
assert_eq!(cmd["direction"], "down");
assert_eq!(cmd["amount"], 500);
assert_eq!(cmd["selector"], "div.scroll-container");
}
#[test]
fn test_scroll_with_selector_short_flag() {
let cmd = parse_command(
&args("scroll left 100 -s .sidebar"),
&default_flags(),
)
.unwrap();
assert_eq!(cmd["action"], "scroll");
assert_eq!(cmd["direction"], "left");
assert_eq!(cmd["amount"], 100);
assert_eq!(cmd["selector"], ".sidebar");
}
#[test]
fn test_scroll_selector_before_positional() {
let cmd = parse_command(
&args("scroll --selector .panel down 400"),
&default_flags(),
)
.unwrap();
assert_eq!(cmd["action"], "scroll");
assert_eq!(cmd["direction"], "down");
assert_eq!(cmd["amount"], 400);
assert_eq!(cmd["selector"], ".panel");
}
#[test]
fn test_scroll_selector_only() {
let cmd = parse_command(
&args("scroll --selector .content"),
&default_flags(),
)
.unwrap();
assert_eq!(cmd["action"], "scroll");
assert_eq!(cmd["direction"], "down");
assert_eq!(cmd["amount"], 300);
assert_eq!(cmd["selector"], ".content");
}
#[test]
fn test_scroll_selector_missing_value() {
let result = parse_command(&args("scroll down 500 --selector"), &default_flags());
assert!(result.is_err());
assert!(matches!(
result.unwrap_err(),
ParseError::MissingArguments { .. }
));
}
}
+7
View File
@@ -220,6 +220,7 @@ pub fn ensure_daemon(
device: Option<&str>,
session_name: Option<&str>,
debug: bool,
download_path: Option<&str>,
) -> Result<DaemonResult, String> {
// Check if daemon is running AND responsive
if is_daemon_running(session) && daemon_ready(session) {
@@ -364,6 +365,9 @@ pub fn ensure_daemon(
if debug {
cmd.env("AGENT_BROWSER_DEBUG", "1");
}
if let Some(dp) = download_path {
cmd.env("AGENT_BROWSER_DOWNLOAD_PATH", dp);
}
// Create new process group and session to fully detach
unsafe {
@@ -448,6 +452,9 @@ pub fn ensure_daemon(
if debug {
cmd.env("AGENT_BROWSER_DEBUG", "1");
}
if let Some(dp) = download_path {
cmd.env("AGENT_BROWSER_DOWNLOAD_PATH", dp);
}
// CREATE_NEW_PROCESS_GROUP | DETACHED_PROCESS
const CREATE_NEW_PROCESS_GROUP: u32 = 0x00000200;
+29
View File
@@ -33,6 +33,7 @@ pub struct Config {
pub headers: Option<String>,
pub annotate: Option<bool>,
pub color_scheme: Option<String>,
pub download_path: Option<String>,
}
impl Config {
@@ -66,6 +67,7 @@ impl Config {
headers: other.headers.or(self.headers),
annotate: other.annotate.or(self.annotate),
color_scheme: other.color_scheme.or(self.color_scheme),
download_path: other.download_path.or(self.download_path),
}
}
}
@@ -131,6 +133,7 @@ fn extract_config_path(args: &[String]) -> Option<Option<String>> {
"--session-name",
"--color-scheme",
"--channel",
"--download-path",
];
let mut i = 0;
while i < args.len() {
@@ -200,6 +203,7 @@ pub struct Flags {
pub session_name: Option<String>,
pub annotate: bool,
pub color_scheme: Option<String>,
pub download_path: Option<String>,
// Track which launch-time options were explicitly passed via CLI
// (as opposed to being set only via environment variables)
@@ -212,6 +216,7 @@ pub struct Flags {
pub cli_proxy_bypass: bool,
pub cli_allow_file_access: bool,
pub cli_annotate: bool,
pub cli_download_path: bool,
}
pub fn parse_flags(args: &[String]) -> Flags {
@@ -278,6 +283,8 @@ pub fn parse_flags(args: &[String]) -> Flags {
color_scheme: env::var("AGENT_BROWSER_COLOR_SCHEME")
.ok()
.or(config.color_scheme),
download_path: env::var("AGENT_BROWSER_DOWNLOAD_PATH").ok()
.or(config.download_path),
cli_executable_path: false,
cli_extensions: false,
cli_state: false,
@@ -287,6 +294,7 @@ pub fn parse_flags(args: &[String]) -> Flags {
cli_proxy_bypass: false,
cli_allow_file_access: false,
cli_annotate: false,
cli_download_path: false,
};
let mut i = 0;
@@ -441,6 +449,13 @@ pub fn parse_flags(args: &[String]) -> Flags {
i += 1;
}
}
"--download-path" => {
if let Some(s) = args.get(i + 1) {
flags.download_path = Some(s.clone());
flags.cli_download_path = true;
i += 1;
}
}
"--config" => {
// Already handled by load_config(); skip the value
i += 1;
@@ -484,6 +499,7 @@ pub fn clean_args(args: &[String]) -> Vec<String> {
"--device",
"--session-name",
"--color-scheme",
"--download-path",
"--config",
];
@@ -668,6 +684,19 @@ mod tests {
assert!(!flags.cli_annotate);
}
#[test]
fn test_cli_download_path_tracking() {
let flags = parse_flags(&args("--download-path /tmp/dl snapshot"));
assert!(flags.cli_download_path);
assert_eq!(flags.download_path, Some("/tmp/dl".to_string()));
}
#[test]
fn test_cli_download_path_not_set_without_flag() {
let flags = parse_flags(&args("snapshot"));
assert!(!flags.cli_download_path);
}
#[test]
fn test_cli_multiple_flags_tracking() {
let flags = parse_flags(&args(
+31 -23
View File
@@ -267,6 +267,7 @@ fn main() {
flags.device.as_deref(),
flags.session_name.as_deref(),
flags.debug,
flags.download_path.as_deref(),
) {
Ok(result) => result,
Err(e) => {
@@ -317,6 +318,7 @@ fn main() {
},
flags.ignore_https_errors.then_some("--ignore-https-errors"),
flags.cli_allow_file_access.then_some("--allow-file-access"),
flags.cli_download_path.then_some("--download-path"),
]
.into_iter()
.flatten()
@@ -398,6 +400,10 @@ fn main() {
launch_cmd["colorScheme"] = json!(cs);
}
if let Some(ref dp) = flags.download_path {
launch_cmd["downloadPath"] = json!(dp);
}
let err = match send_command(launch_cmd, &flags.session) {
Ok(resp) if resp.success => None,
Ok(resp) => Some(
@@ -484,29 +490,26 @@ fn main() {
launch_cmd["colorScheme"] = json!(cs);
}
match send_command(launch_cmd, &flags.session) {
Ok(resp) => {
if !resp.success {
let msg = resp
.error
.unwrap_or_else(|| "CDP connection failed".to_string());
if flags.json {
println!(r#"{{"success":false,"error":"{}"}}"#, msg);
} else {
eprintln!("{} {}", color::error_indicator(), msg);
}
exit(1);
}
}
Err(e) => {
if flags.json {
println!(r#"{{"success":false,"error":"{}"}}"#, e);
} else {
eprintln!("{} {}", color::error_indicator(), e);
}
exit(1);
if let Some(ref dp) = flags.download_path {
launch_cmd["downloadPath"] = json!(dp);
}
let err = match send_command(launch_cmd, &flags.session) {
Ok(resp) if resp.success => None,
Ok(resp) => Some(
resp.error
.unwrap_or_else(|| "CDP connection failed".to_string()),
),
Err(e) => Some(e.to_string()),
};
if let Some(msg) = err {
if flags.json {
println!(r#"{{"success":false,"error":"{}"}}"#, msg);
} else {
eprintln!("{} {}", color::error_indicator(), msg);
}
exit(1);
}
}
@@ -599,7 +602,8 @@ fn main() {
|| flags.ignore_https_errors
|| flags.allow_file_access
|| flags.debug
|| flags.color_scheme.is_some())
|| flags.color_scheme.is_some()
|| flags.download_path.is_some())
&& flags.cdp.is_none()
&& flags.provider.is_none()
&& !launched_via_default_cdp
@@ -661,6 +665,10 @@ fn main() {
launch_cmd["colorScheme"] = json!(cs);
}
if let Some(ref dp) = flags.download_path {
launch_cmd["downloadPath"] = json!(dp);
}
match send_command(launch_cmd, &flags.session) {
Ok(resp) => {
if !resp.success {
+8 -2
View File
@@ -995,14 +995,17 @@ Use Cases:
r##"
agent-browser scroll - Scroll the page
Usage: agent-browser scroll [direction] [amount]
Usage: agent-browser scroll [direction] [amount] [options]
Scrolls the page in the specified direction.
Scrolls the page or a specific element in the specified direction.
Arguments:
direction up, down, left, right (default: down)
amount Pixels to scroll (default: 300)
Options:
-s, --selector <sel> CSS selector for a scrollable container
Global Options:
--json Output as JSON
--session <name> Use specific session
@@ -1012,6 +1015,7 @@ Examples:
agent-browser scroll down 500
agent-browser scroll up 200
agent-browser scroll left 100
agent-browser scroll down 500 --selector "div.scroll-container"
"##
}
"scrollintoview" | "scrollinto" => {
@@ -2130,6 +2134,7 @@ Options:
--auto-connect Auto-discover and connect to running Chrome
Project default: require existing browser at localhost:9333 (no auto local fallback)
--color-scheme <scheme> Color scheme: dark, light, no-preference (or AGENT_BROWSER_COLOR_SCHEME)
--download-path <path> Default download directory (or AGENT_BROWSER_DOWNLOAD_PATH)
--session-name <name> Auto-save/restore session state (cookies, localStorage)
--config <path> Use a custom config file (or AGENT_BROWSER_CONFIG env)
--debug Debug output
@@ -2180,6 +2185,7 @@ Environment:
AGENT_BROWSER_LOCALE Override auto-detected locale (e.g., zh-TW, ja-JP)
AGENT_BROWSER_TIMEZONE Override auto-detected timezone (e.g., Asia/Taipei)
AGENT_BROWSER_COLOR_SCHEME Color scheme preference (dark, light, no-preference)
AGENT_BROWSER_DOWNLOAD_PATH Default download directory for browser downloads
AGENT_BROWSER_DEFAULT_TIMEOUT Default Playwright timeout in ms (default: 25000)
AGENT_BROWSER_SESSION_NAME Auto-save/load state persistence name
AGENT_BROWSER_STATE_EXPIRE_DAYS Auto-delete saved states older than N days (default: 30)
+3 -1
View File
@@ -22,7 +22,7 @@ agent-browser focus <sel> # Focus element
agent-browser select <sel> <val> # Select dropdown option
agent-browser check <sel> # Check checkbox
agent-browser uncheck <sel> # Uncheck checkbox
agent-browser scroll <dir> [px] # Scroll (up/down/left/right)
agent-browser scroll <dir> [px] # Scroll (up/down/left/right, --selector <sel>)
agent-browser scrollintoview <sel> # Scroll element into view
agent-browser drag <src> <dst> # Drag and drop
agent-browser upload <sel> <files> # Upload files
@@ -117,6 +117,8 @@ agent-browser download <sel> <path> # Click element to trigger download
agent-browser wait --download [path] # Wait for any download to complete
```
Use `--download-path <dir>` (or `AGENT_BROWSER_DOWNLOAD_PATH` env) to set a default download directory. Without it, downloads go to a temporary directory that is deleted when the browser closes.
## Mouse
```bash
+2
View File
@@ -73,6 +73,7 @@ Every CLI flag can be set in the config file using its camelCase equivalent:
<tr><td><code>cdp</code></td><td><code>--cdp</code></td><td>string</td></tr>
<tr><td><code>autoConnect</code></td><td><code>--auto-connect</code></td><td>boolean</td></tr>
<tr><td><code>colorScheme</code></td><td><code>--color-scheme</code></td><td>string (<code>dark</code>, <code>light</code>, <code>no-preference</code>)</td></tr>
<tr><td><code>downloadPath</code></td><td><code>--download-path</code></td><td>string</td></tr>
<tr><td><code>headers</code></td><td><code>--headers</code></td><td>string (JSON)</td></tr>
</tbody>
</table>
@@ -151,6 +152,7 @@ These environment variables configure additional daemon and runtime behavior:
<tr><td><code>AGENT_BROWSER_AUTO_CONNECT</code></td><td>Auto-discover and connect to a running Chrome instance.</td><td>(disabled)</td></tr>
<tr><td><code>AGENT_BROWSER_ALLOW_FILE_ACCESS</code></td><td>Allow <code>file://</code> URLs to access local files.</td><td>(disabled)</td></tr>
<tr><td><code>AGENT_BROWSER_COLOR_SCHEME</code></td><td>Color scheme preference (<code>dark</code>, <code>light</code>, <code>no-preference</code>).</td><td>(none)</td></tr>
<tr><td><code>AGENT_BROWSER_DOWNLOAD_PATH</code></td><td>Default directory for browser downloads.</td><td>(temp directory)</td></tr>
<tr><td><code>AGENT_BROWSER_DEFAULT_TIMEOUT</code></td><td>Default Playwright timeout in ms. Keep below 30000 to avoid IPC timeouts.</td><td><code>25000</code></td></tr>
<tr><td><code>AGENT_BROWSER_SESSION_NAME</code></td><td>Auto-save/load state persistence name.</td><td>(none)</td></tr>
<tr><td><code>AGENT_BROWSER_STATE_EXPIRE_DAYS</code></td><td>Auto-delete saved session states older than N days.</td><td><code>30</code></td></tr>
+4 -1
View File
@@ -1,6 +1,6 @@
{
"name": "agent-browser-stealth",
"version": "0.14.0-fork.3",
"version": "0.14.0-fork.4",
"description": "Stealth browser automation CLI for AI agents with anti-bot evasions",
"type": "module",
"main": "dist/daemon.js",
@@ -33,7 +33,9 @@
"format:check": "prettier --check 'src/**/*.ts'",
"test": "vitest run",
"test:watch": "vitest",
"test:e2e:dogfood": "vitest run test/e2e/dogfood.eval.ts",
"postinstall": "node scripts/postinstall.js",
"clawhub:sync": "bash scripts/clawhub-sync.sh",
"sync:upstream": "bash scripts/sync-upstream.sh",
"sync:upstream:push": "bash scripts/sync-upstream.sh --push",
"changeset": "changeset",
@@ -68,6 +70,7 @@
"zod": "^3.22.4"
},
"devDependencies": {
"@anthropic-ai/claude-agent-sdk": "^0.2.52",
"@changesets/cli": "^2.29.8",
"@types/node": "^20.10.0",
"@types/ws": "^8.18.1",
+174
View File
@@ -24,6 +24,9 @@ importers:
specifier: ^3.22.4
version: 3.25.76
devDependencies:
'@anthropic-ai/claude-agent-sdk':
specifier: ^0.2.52
version: 0.2.52(zod@3.25.76)
'@changesets/cli':
specifier: ^2.29.8
version: 2.29.8(@types/node@20.19.28)
@@ -57,6 +60,12 @@ importers:
packages:
'@anthropic-ai/claude-agent-sdk@0.2.52':
resolution: {integrity: sha512-rdTQUu/HjKlDNNxJuhtXY6LJDOLvzVBU7sXFuFIG6CEC/nFfcvYq035EyjVw4nzu7lLZim/m+g2yZ8uNIcbaFw==}
engines: {node: '>=18.0.0'}
peerDependencies:
zod: ^4.0.0
'@appium/logger@1.7.1':
resolution: {integrity: sha512-9C2o9X/lBEDBUnKfAi3mRo9oG7Z03nmISLwsGkWxIWjMAvBdJD0RRSJMekWVKzfXN3byrI1WlCXTITzN4LAoLw==}
engines: {node: ^14.17.0 || ^16.13.0 || >=18.0.0, npm: '>=8'}
@@ -276,6 +285,95 @@ packages:
cpu: [x64]
os: [win32]
'@img/sharp-darwin-arm64@0.34.5':
resolution: {integrity: sha512-imtQ3WMJXbMY4fxb/Ndp6HBTNVtWCUI0WdobyheGf5+ad6xX8VIDO8u2xE4qc/fr08CKG/7dDseFtn6M6g/r3w==}
engines: {node: ^18.17.0 || ^20.3.0 || >=21.0.0}
cpu: [arm64]
os: [darwin]
'@img/sharp-darwin-x64@0.34.5':
resolution: {integrity: sha512-YNEFAF/4KQ/PeW0N+r+aVVsoIY0/qxxikF2SWdp+NRkmMB7y9LBZAVqQ4yhGCm/H3H270OSykqmQMKLBhBJDEw==}
engines: {node: ^18.17.0 || ^20.3.0 || >=21.0.0}
cpu: [x64]
os: [darwin]
'@img/sharp-libvips-darwin-arm64@1.2.4':
resolution: {integrity: sha512-zqjjo7RatFfFoP0MkQ51jfuFZBnVE2pRiaydKJ1G/rHZvnsrHAOcQALIi9sA5co5xenQdTugCvtb1cuf78Vf4g==}
cpu: [arm64]
os: [darwin]
'@img/sharp-libvips-darwin-x64@1.2.4':
resolution: {integrity: sha512-1IOd5xfVhlGwX+zXv2N93k0yMONvUlANylbJw1eTah8K/Jtpi15KC+WSiaX/nBmbm2HxRM1gZ0nSdjSsrZbGKg==}
cpu: [x64]
os: [darwin]
'@img/sharp-libvips-linux-arm64@1.2.4':
resolution: {integrity: sha512-excjX8DfsIcJ10x1Kzr4RcWe1edC9PquDRRPx3YVCvQv+U5p7Yin2s32ftzikXojb1PIFc/9Mt28/y+iRklkrw==}
cpu: [arm64]
os: [linux]
'@img/sharp-libvips-linux-arm@1.2.4':
resolution: {integrity: sha512-bFI7xcKFELdiNCVov8e44Ia4u2byA+l3XtsAj+Q8tfCwO6BQ8iDojYdvoPMqsKDkuoOo+X6HZA0s0q11ANMQ8A==}
cpu: [arm]
os: [linux]
'@img/sharp-libvips-linux-x64@1.2.4':
resolution: {integrity: sha512-tJxiiLsmHc9Ax1bz3oaOYBURTXGIRDODBqhveVHonrHJ9/+k89qbLl0bcJns+e4t4rvaNBxaEZsFtSfAdquPrw==}
cpu: [x64]
os: [linux]
'@img/sharp-libvips-linuxmusl-arm64@1.2.4':
resolution: {integrity: sha512-FVQHuwx1IIuNow9QAbYUzJ+En8KcVm9Lk5+uGUQJHaZmMECZmOlix9HnH7n1TRkXMS0pGxIJokIVB9SuqZGGXw==}
cpu: [arm64]
os: [linux]
'@img/sharp-libvips-linuxmusl-x64@1.2.4':
resolution: {integrity: sha512-+LpyBk7L44ZIXwz/VYfglaX/okxezESc6UxDSoyo2Ks6Jxc4Y7sGjpgU9s4PMgqgjj1gZCylTieNamqA1MF7Dg==}
cpu: [x64]
os: [linux]
'@img/sharp-linux-arm64@0.34.5':
resolution: {integrity: sha512-bKQzaJRY/bkPOXyKx5EVup7qkaojECG6NLYswgktOZjaXecSAeCWiZwwiFf3/Y+O1HrauiE3FVsGxFg8c24rZg==}
engines: {node: ^18.17.0 || ^20.3.0 || >=21.0.0}
cpu: [arm64]
os: [linux]
'@img/sharp-linux-arm@0.34.5':
resolution: {integrity: sha512-9dLqsvwtg1uuXBGZKsxem9595+ujv0sJ6Vi8wcTANSFpwV/GONat5eCkzQo/1O6zRIkh0m/8+5BjrRr7jDUSZw==}
engines: {node: ^18.17.0 || ^20.3.0 || >=21.0.0}
cpu: [arm]
os: [linux]
'@img/sharp-linux-x64@0.34.5':
resolution: {integrity: sha512-MEzd8HPKxVxVenwAa+JRPwEC7QFjoPWuS5NZnBt6B3pu7EG2Ge0id1oLHZpPJdn3OQK+BQDiw9zStiHBTJQQQQ==}
engines: {node: ^18.17.0 || ^20.3.0 || >=21.0.0}
cpu: [x64]
os: [linux]
'@img/sharp-linuxmusl-arm64@0.34.5':
resolution: {integrity: sha512-fprJR6GtRsMt6Kyfq44IsChVZeGN97gTD331weR1ex1c1rypDEABN6Tm2xa1wE6lYb5DdEnk03NZPqA7Id21yg==}
engines: {node: ^18.17.0 || ^20.3.0 || >=21.0.0}
cpu: [arm64]
os: [linux]
'@img/sharp-linuxmusl-x64@0.34.5':
resolution: {integrity: sha512-Jg8wNT1MUzIvhBFxViqrEhWDGzqymo3sV7z7ZsaWbZNDLXRJZoRGrjulp60YYtV4wfY8VIKcWidjojlLcWrd8Q==}
engines: {node: ^18.17.0 || ^20.3.0 || >=21.0.0}
cpu: [x64]
os: [linux]
'@img/sharp-win32-arm64@0.34.5':
resolution: {integrity: sha512-WQ3AgWCWYSb2yt+IG8mnC6Jdk9Whs7O0gxphblsLvdhSpSTtmu69ZG1Gkb6NuvxsNACwiPV6cNSZNzt0KPsw7g==}
engines: {node: ^18.17.0 || ^20.3.0 || >=21.0.0}
cpu: [arm64]
os: [win32]
'@img/sharp-win32-x64@0.34.5':
resolution: {integrity: sha512-+29YMsqY2/9eFEiW93eqWnuLcWcufowXewwSNIT6UwZdUUCrM3oFjMWH/Z6/TMmb4hlFenmfAVbpWeup2jryCw==}
engines: {node: ^18.17.0 || ^20.3.0 || >=21.0.0}
cpu: [x64]
os: [win32]
'@inquirer/external-editor@1.0.3':
resolution: {integrity: sha512-RWbSrDiYmO4LbejWY7ttpxczuwQyZLBUyygsA9Nsv95hpzUWwnNTVQmAq3xuh7vNwCp07UTmE5i11XAEExx4RA==}
engines: {node: '>=18'}
@@ -1950,6 +2048,20 @@ packages:
snapshots:
'@anthropic-ai/claude-agent-sdk@0.2.52(zod@3.25.76)':
dependencies:
zod: 3.25.76
optionalDependencies:
'@img/sharp-darwin-arm64': 0.34.5
'@img/sharp-darwin-x64': 0.34.5
'@img/sharp-linux-arm': 0.34.5
'@img/sharp-linux-arm64': 0.34.5
'@img/sharp-linux-x64': 0.34.5
'@img/sharp-linuxmusl-arm64': 0.34.5
'@img/sharp-linuxmusl-x64': 0.34.5
'@img/sharp-win32-arm64': 0.34.5
'@img/sharp-win32-x64': 0.34.5
'@appium/logger@1.7.1':
dependencies:
console-control-strings: 1.1.0
@@ -2181,6 +2293,68 @@ snapshots:
'@esbuild/win32-x64@0.27.2':
optional: true
'@img/sharp-darwin-arm64@0.34.5':
optionalDependencies:
'@img/sharp-libvips-darwin-arm64': 1.2.4
optional: true
'@img/sharp-darwin-x64@0.34.5':
optionalDependencies:
'@img/sharp-libvips-darwin-x64': 1.2.4
optional: true
'@img/sharp-libvips-darwin-arm64@1.2.4':
optional: true
'@img/sharp-libvips-darwin-x64@1.2.4':
optional: true
'@img/sharp-libvips-linux-arm64@1.2.4':
optional: true
'@img/sharp-libvips-linux-arm@1.2.4':
optional: true
'@img/sharp-libvips-linux-x64@1.2.4':
optional: true
'@img/sharp-libvips-linuxmusl-arm64@1.2.4':
optional: true
'@img/sharp-libvips-linuxmusl-x64@1.2.4':
optional: true
'@img/sharp-linux-arm64@0.34.5':
optionalDependencies:
'@img/sharp-libvips-linux-arm64': 1.2.4
optional: true
'@img/sharp-linux-arm@0.34.5':
optionalDependencies:
'@img/sharp-libvips-linux-arm': 1.2.4
optional: true
'@img/sharp-linux-x64@0.34.5':
optionalDependencies:
'@img/sharp-libvips-linux-x64': 1.2.4
optional: true
'@img/sharp-linuxmusl-arm64@0.34.5':
optionalDependencies:
'@img/sharp-libvips-linuxmusl-arm64': 1.2.4
optional: true
'@img/sharp-linuxmusl-x64@0.34.5':
optionalDependencies:
'@img/sharp-libvips-linuxmusl-x64': 1.2.4
optional: true
'@img/sharp-win32-arm64@0.34.5':
optional: true
'@img/sharp-win32-x64@0.34.5':
optional: true
'@inquirer/external-editor@1.0.3(@types/node@20.19.28)':
dependencies:
chardet: 2.1.1
+27
View File
@@ -0,0 +1,27 @@
#!/usr/bin/env bash
set -euo pipefail
ROOT_DIR="$(cd "$(dirname "$0")/.." && pwd)"
cd "$ROOT_DIR"
SKILL_NAME="agent-browser-stealth"
if ! command -v pnpm >/dev/null 2>&1; then
echo "pnpm is required for ClawHub sync"
exit 1
fi
if [ ! -f "skills/${SKILL_NAME}/SKILL.md" ]; then
echo "Missing skill file: skills/${SKILL_NAME}/SKILL.md"
exit 1
fi
# Sync only this fork-owned skill to avoid permission errors on other skills.
TMP_DIR="$(mktemp -d)"
trap 'rm -rf "$TMP_DIR"' EXIT
mkdir -p "$TMP_DIR/skills"
cp -R "skills/${SKILL_NAME}" "$TMP_DIR/skills/${SKILL_NAME}"
echo "Syncing local skill '${SKILL_NAME}' to ClawHub..."
cd "$TMP_DIR"
pnpm dlx clawhub@latest sync --all --root ./skills
echo "ClawHub sync completed."
+127
View File
@@ -0,0 +1,127 @@
---
name: agent-browser-stealth
description: Stealth-first browser automation for OpenClaw using agent-browser-stealth. Use when tasks involve bot-protected websites, anti-fingerprint evasion, captcha-prone flows, login persistence, region-sensitive targets (e.g., Shopee/TikTok/e-commerce), or any request to automate web actions with lower detection risk.
homepage: https://github.com/leeguooooo/agent-browser
---
# agent-browser-stealth for OpenClaw
Use this skill when the task needs web automation and anti-bot stability.
## What this skill prioritizes
- Use `agent-browser` CLI from `agent-browser-stealth` package
- Prefer stealth-safe interaction patterns over brittle one-shot scripts
- Keep command flow deterministic: `open -> snapshot -> act -> re-snapshot`
- Minimize bot signals with humanized pacing and stable session reuse
## Install and baseline
```bash
npm install -g agent-browser-stealth
agent-browser install
agent-browser --version
```
If default CDP mode is used in your environment, ensure a browser is available at `localhost:9333`, or pass `--cdp` / `--auto-connect` explicitly.
## Standard execution workflow
```bash
agent-browser open <url>
agent-browser wait --load networkidle
agent-browser snapshot -i
# choose refs (@e1, @e2, ...)
agent-browser click @eN
agent-browser fill @eM "..."
agent-browser snapshot -i
```
Use refs (`@e1`) from snapshot output whenever possible.
## Anti-bot operating rules
1. Prefer headed mode for sensitive targets:
```bash
agent-browser --headed --session-name shop open https://example.com
```
2. Reuse session state to avoid repeated cold-start fingerprints:
```bash
agent-browser --session-name shop open https://example.com
```
3. Keep interactions human-like:
```bash
agent-browser type @e2 "query" --delay 120
agent-browser wait 1200-2600
```
4. For contenteditable editors, use keyboard mode:
```bash
agent-browser click "[contenteditable='true']"
agent-browser keyboard type "Hello world" --delay 90
```
5. If text must literally include `--delay`, stop arg parsing with `--`:
```bash
agent-browser type @e2 -- "--delay 120"
agent-browser keyboard type -- "--delay 120"
```
## Region-sensitive websites
For region-bound sites, open target domain directly and let locale/timezone alignment apply.
```bash
agent-browser open https://shopee.tw
```
Only override locale/timezone when explicitly required by the task.
## Recovery patterns
If blocked or unstable:
1. Retry with `--headed`.
2. Reuse `--session-name`.
3. Slow down action cadence (`wait`, `type --delay`).
4. Re-open page and regenerate refs with `snapshot -i`.
## Minimal recipes
Login flow:
```bash
agent-browser --session-name account open https://example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "$USERNAME"
agent-browser fill @e2 "$PASSWORD"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
```
Search and capture:
```bash
agent-browser open https://example.com
agent-browser snapshot -i
agent-browser type @e2 "iphone" --delay 120
agent-browser press Enter
agent-browser wait --load networkidle
agent-browser screenshot result.png
```
## Output expectations for OpenClaw
When using this skill, return:
- Exact commands executed
- Key page state changes (URL/title/important element text)
- Any anti-bot signal encountered and mitigation used
- Next safe action
+6
View File
@@ -70,6 +70,7 @@ agent-browser press Enter # Press key
agent-browser keyboard type "text" --delay 90 # Type at current focus (no selector)
agent-browser keyboard inserttext "text" # Insert without key events
agent-browser scroll down 500 # Scroll page
agent-browser scroll down 500 --selector "div.content" # Scroll within a specific container
# Get information
agent-browser get text @e1 # Get element text
@@ -83,6 +84,11 @@ agent-browser wait --url "**/page" # Wait for URL pattern
agent-browser wait 2000 # Wait milliseconds
agent-browser wait 2000-5000 # Random wait between 2-5 seconds
# Downloads
agent-browser download @e1 ./file.pdf # Click element to trigger download
agent-browser wait --download ./output.zip # Wait for any download to complete
agent-browser --download-path ./downloads open <url> # Set default download directory
# Capture
agent-browser screenshot # Screenshot to temp dir
agent-browser screenshot --full # Full page screenshot
+216
View File
@@ -0,0 +1,216 @@
---
name: dogfood
description: Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
allowed-tools: Bash(agent-browser:*), Bash(npx agent-browser:*)
---
# Dogfood
Systematically explore a web application, find issues, and produce a report with full reproduction evidence for every finding.
## Setup
Only the **Target URL** is required. Everything else has sensible defaults -- use them unless the user explicitly provides an override.
| Parameter | Default | Example override |
|-----------|---------|-----------------|
| **Target URL** | _(required)_ | `vercel.com`, `http://localhost:3000` |
| **Session name** | Slugified domain (e.g., `vercel.com` -> `vercel-com`) | `--session my-session` |
| **Output directory** | `./dogfood-output/` | `Output directory: /tmp/qa` |
| **Scope** | Full app | `Focus on the billing page` |
| **Authentication** | None | `Sign in to user@example.com` |
If the user says something like "dogfood vercel.com", start immediately with defaults. Do not ask clarifying questions unless authentication is mentioned but credentials are missing.
Always use `agent-browser` directly -- never `npx agent-browser`. The direct binary uses the fast Rust client. `npx` routes through Node.js and is significantly slower.
## Workflow
```
1. Initialize Set up session, output dirs, report file
2. Authenticate Sign in if needed, save state
3. Orient Navigate to starting point, take initial snapshot
4. Explore Systematically visit pages and test features
5. Document Screenshot + record each issue as found
6. Wrap up Update summary counts, close session
```
### 1. Initialize
```bash
mkdir -p {OUTPUT_DIR}/screenshots {OUTPUT_DIR}/videos
```
Copy the report template into the output directory and fill in the header fields:
```bash
cp {SKILL_DIR}/templates/dogfood-report-template.md {OUTPUT_DIR}/report.md
```
Start a named session:
```bash
agent-browser --session {SESSION} open {TARGET_URL}
agent-browser --session {SESSION} wait --load networkidle
```
### 2. Authenticate
If the app requires login:
```bash
agent-browser --session {SESSION} snapshot -i
# Identify login form refs, fill credentials
agent-browser --session {SESSION} fill @e1 "{EMAIL}"
agent-browser --session {SESSION} fill @e2 "{PASSWORD}"
agent-browser --session {SESSION} click @e3
agent-browser --session {SESSION} wait --load networkidle
```
For OTP/email codes: ask the user, wait for their response, then enter the code.
After successful login, save state for potential reuse:
```bash
agent-browser --session {SESSION} state save {OUTPUT_DIR}/auth-state.json
```
### 3. Orient
Take an initial annotated screenshot and snapshot to understand the app structure:
```bash
agent-browser --session {SESSION} screenshot --annotate {OUTPUT_DIR}/screenshots/initial.png
agent-browser --session {SESSION} snapshot -i
```
Identify the main navigation elements and map out the sections to visit.
### 4. Explore
Read [references/issue-taxonomy.md](references/issue-taxonomy.md) for the full list of what to look for and the exploration checklist.
**Strategy -- work through the app systematically:**
- Start from the main navigation. Visit each top-level section.
- Within each section, test interactive elements: click buttons, fill forms, open dropdowns/modals.
- Check edge cases: empty states, error handling, boundary inputs.
- Try realistic end-to-end workflows (create, edit, delete flows).
- Check the browser console for errors periodically.
**At each page:**
```bash
agent-browser --session {SESSION} snapshot -i
agent-browser --session {SESSION} screenshot --annotate {OUTPUT_DIR}/screenshots/{page-name}.png
agent-browser --session {SESSION} errors
agent-browser --session {SESSION} console
```
Use your judgment on how deep to go. Spend more time on core features and less on peripheral pages. If you find a cluster of issues in one area, investigate deeper.
### 5. Document Issues (Repro-First)
Steps 4 and 5 happen together -- explore and document in a single pass. When you find an issue, stop exploring and document it immediately before moving on. Do not explore the whole app first and document later.
Every issue must be reproducible. When you find something wrong, do not just note it -- prove it with evidence. The goal is that someone reading the report can see exactly what happened and replay it.
**Choose the right level of evidence for the issue:**
#### Interactive / behavioral issues (functional, ux, console errors on action)
These require user interaction to reproduce -- use full repro with video and step-by-step screenshots:
1. **Start a repro video** _before_ reproducing:
```bash
agent-browser --session {SESSION} record start {OUTPUT_DIR}/videos/issue-{NNN}-repro.webm
```
2. **Walk through the steps at human pace.** Pause 1-2 seconds between actions so the video is watchable. Take a screenshot at each step:
```bash
agent-browser --session {SESSION} screenshot {OUTPUT_DIR}/screenshots/issue-{NNN}-step-1.png
sleep 1
# Perform action (click, fill, etc.)
sleep 1
agent-browser --session {SESSION} screenshot {OUTPUT_DIR}/screenshots/issue-{NNN}-step-2.png
sleep 1
# ...continue until the issue manifests
```
3. **Capture the broken state.** Pause so the viewer can see it, then take an annotated screenshot:
```bash
sleep 2
agent-browser --session {SESSION} screenshot --annotate {OUTPUT_DIR}/screenshots/issue-{NNN}-result.png
```
4. **Stop the video:**
```bash
agent-browser --session {SESSION} record stop
```
5. Write numbered repro steps in the report, each referencing its screenshot.
#### Static / visible-on-load issues (typos, placeholder text, clipped text, misalignment, console errors on load)
These are visible without interaction -- a single annotated screenshot is sufficient. No video, no multi-step repro:
```bash
agent-browser --session {SESSION} screenshot --annotate {OUTPUT_DIR}/screenshots/issue-{NNN}.png
```
Write a brief description and reference the screenshot in the report. Set **Repro Video** to `N/A`.
---
**For all issues:**
1. **Append to the report immediately.** Do not batch issues for later. Write each one as you find it so nothing is lost if the session is interrupted.
2. **Increment the issue counter** (ISSUE-001, ISSUE-002, ...).
### 6. Wrap Up
Aim to find **5-10 well-documented issues**, then wrap up. Depth of evidence matters more than total count -- 5 issues with full repro beats 20 with vague descriptions.
After exploring:
1. Re-read the report and update the summary severity counts so they match the actual issues. Every `### ISSUE-` block must be reflected in the totals.
2. Close the session:
```bash
agent-browser --session {SESSION} close
```
3. Tell the user the report is ready and summarize findings: total issues, breakdown by severity, and the most critical items.
## Guidance
- **Repro is everything.** Every issue needs proof -- but match the evidence to the issue. Interactive bugs need video and step-by-step screenshots. Static bugs (typos, placeholder text, visual glitches visible on load) only need a single annotated screenshot.
- **Don't record video for static issues.** A typo or clipped text doesn't benefit from a video. Save video for issues that involve user interaction, timing, or state changes.
- **For interactive issues, screenshot each step.** Capture the before, the action, and the after -- so someone can see the full sequence.
- **Write repro steps that map to screenshots.** Each numbered step in the report should reference its corresponding screenshot. A reader should be able to follow the steps visually without touching a browser.
- **Be thorough but use judgment.** You are not following a test script -- you are exploring like a real user would. If something feels off, investigate.
- **Write findings incrementally.** Append each issue to the report as you discover it. If the session is interrupted, findings are preserved. Never batch all issues for the end.
- **Never delete output files.** Do not `rm` screenshots, videos, or the report mid-session. Do not close the session and restart. Work forward, not backward.
- **Never read the target app's source code.** You are testing as a user, not auditing code. Do not read HTML, JS, or config files of the app under test. All findings must come from what you observe in the browser.
- **Check the console.** Many issues are invisible in the UI but show up as JS errors or failed requests.
- **Test like a user, not a robot.** Try common workflows end-to-end. Click things a real user would click. Enter realistic data.
- **Type like a human.** When filling form fields during video recording, use `type` instead of `fill` -- it types character-by-character. Use `fill` only outside of video recording when speed matters.
- **Pace repro videos for humans.** Add `sleep 1` between actions and `sleep 2` before the final result screenshot. Videos should be watchable at 1x speed -- a human reviewing the report needs to see what happened, not a blur of instant state changes.
- **Be efficient with commands.** Batch multiple `agent-browser` commands in a single shell call when they are independent (e.g., `agent-browser ... screenshot ... && agent-browser ... console`). Use `agent-browser --session {SESSION} scroll down 300` for scrolling -- do not use `key` or `evaluate` to scroll.
## References
| Reference | When to Read |
|-----------|--------------|
| [references/issue-taxonomy.md](references/issue-taxonomy.md) | Start of session -- calibrate what to look for, severity levels, exploration checklist |
## Templates
| Template | Purpose |
|----------|---------|
| [templates/dogfood-report-template.md](templates/dogfood-report-template.md) | Copy into output directory as the report file |
+109
View File
@@ -0,0 +1,109 @@
# Issue Taxonomy
Reference for categorizing issues found during dogfooding. Read this at the start of a dogfood session to calibrate what to look for.
## Contents
- [Severity Levels](#severity-levels)
- [Categories](#categories)
- [Exploration Checklist](#exploration-checklist)
## Severity Levels
| Severity | Definition |
|----------|------------|
| **critical** | Blocks a core workflow, causes data loss, or crashes the app |
| **high** | Major feature broken or unusable, no workaround |
| **medium** | Feature works but with noticeable problems, workaround exists |
| **low** | Minor cosmetic or polish issue |
## Categories
### Visual / UI
- Layout broken or misaligned elements
- Overlapping or clipped text
- Inconsistent spacing, padding, or margins
- Missing or broken icons/images
- Dark mode / light mode rendering issues
- Responsive layout problems (viewport sizes)
- Z-index stacking issues (elements hidden behind others)
- Font rendering issues (wrong font, size, weight)
- Color contrast problems
- Animation glitches or jank
### Functional
- Broken links (404, wrong destination)
- Buttons or controls that do nothing on click
- Form validation that rejects valid input or accepts invalid input
- Incorrect redirects
- Features that fail silently
- State not persisted when expected (lost on refresh, navigation)
- Race conditions (double-submit, stale data)
- Broken search or filtering
- Pagination issues
- File upload/download failures
### UX
- Confusing or unclear navigation
- Missing loading indicators or feedback after actions
- Slow or unresponsive interactions (>300ms perceived delay)
- Unclear error messages
- Missing confirmation for destructive actions
- Dead ends (no way to go back or proceed)
- Inconsistent patterns across similar features
- Missing keyboard shortcuts or focus management
- Unintuitive defaults
- Missing empty states or unhelpful empty states
### Content
- Typos or grammatical errors
- Outdated or incorrect text
- Placeholder or lorem ipsum content left in
- Truncated text without tooltip or expansion
- Missing or wrong labels
- Inconsistent terminology
### Performance
- Slow page loads (>3s)
- Janky scrolling or animations
- Large layout shifts (content jumping)
- Excessive network requests (check via console/network)
- Memory leaks (page slows over time)
- Unoptimized images (large file sizes)
### Console / Errors
- JavaScript exceptions in console
- Failed network requests (4xx, 5xx)
- Deprecation warnings
- CORS errors
- Mixed content warnings
- Unhandled promise rejections
### Accessibility
- Missing alt text on images
- Unlabeled form inputs
- Poor keyboard navigation (can't tab to elements)
- Focus traps
- Insufficient color contrast
- Missing ARIA attributes on dynamic content
- Screen reader incompatible patterns
## Exploration Checklist
Use this as a guide for what to test on each page/feature:
1. **Visual scan** -- Take an annotated screenshot. Look for layout, alignment, and rendering issues.
2. **Interactive elements** -- Click every button, link, and control. Do they work? Is there feedback?
3. **Forms** -- Fill and submit. Test empty submission, invalid input, and edge cases.
4. **Navigation** -- Follow all navigation paths. Check breadcrumbs, back button, deep links.
5. **States** -- Check empty states, loading states, error states, and full/overflow states.
6. **Console** -- Check for JS errors, failed requests, and warnings.
7. **Responsiveness** -- If relevant, test at different viewport sizes.
8. **Auth boundaries** -- Test what happens when not logged in, with different roles if applicable.
@@ -0,0 +1,53 @@
# Dogfood Report: {APP_NAME}
| Field | Value |
|-------|-------|
| **Date** | {DATE} |
| **App URL** | {URL} |
| **Session** | {SESSION_NAME} |
| **Scope** | {SCOPE} |
## Summary
| Severity | Count |
|----------|-------|
| Critical | 0 |
| High | 0 |
| Medium | 0 |
| Low | 0 |
| **Total** | **0** |
## Issues
<!-- Copy this block for each issue found. Interactive issues need video + step-by-step screenshots. Static issues (typos, visual glitches) only need a single screenshot -- set Repro Video to N/A. -->
### ISSUE-001: {Short title}
| Field | Value |
|-------|-------|
| **Severity** | critical / high / medium / low |
| **Category** | visual / functional / ux / content / performance / console / accessibility |
| **URL** | {page URL where issue was found} |
| **Repro Video** | {path to video, or N/A for static issues} |
**Description**
{What is wrong, what was expected, and what actually happened.}
**Repro Steps**
<!-- Each step has a screenshot. A reader should be able to follow along visually. -->
1. Navigate to {URL}
![Step 1](screenshots/issue-001-step-1.png)
2. {Action -- e.g., click "Settings" in the sidebar}
![Step 2](screenshots/issue-001-step-2.png)
3. {Action -- e.g., type "test" in the search field and press Enter}
![Step 3](screenshots/issue-001-step-3.png)
4. **Observe:** {what goes wrong -- e.g., the page shows a blank white screen instead of search results}
![Result](screenshots/issue-001-result.png)
---
+25 -25
View File
@@ -998,41 +998,41 @@ async function handleWait(command: WaitCommand, browser: BrowserManager): Promis
async function handleScroll(command: ScrollCommand, browser: BrowserManager): Promise<Response> {
const page = browser.getPage();
let deltaX = command.x ?? 0;
let deltaY = command.y ?? 0;
const hasExplicitDelta = command.x !== undefined || command.y !== undefined;
if (command.direction) {
const amount = command.amount ?? 100;
switch (command.direction) {
case 'up':
deltaY = -amount;
break;
case 'down':
deltaY = amount;
break;
case 'left':
deltaX = -amount;
break;
case 'right':
deltaX = amount;
break;
}
}
if (command.selector) {
const element = browser.getLocator(command.selector);
await element.scrollIntoViewIfNeeded();
if (command.x !== undefined || command.y !== undefined) {
if (hasExplicitDelta || deltaX !== 0 || deltaY !== 0) {
await element.evaluate(
(el, { x, y }) => {
el.scrollBy(x ?? 0, y ?? 0);
el.scrollBy(x, y);
},
{ x: command.x, y: command.y }
{ x: deltaX, y: deltaY }
);
}
} else {
// Scroll the page
let deltaX = command.x ?? 0;
let deltaY = command.y ?? 0;
if (command.direction) {
const amount = command.amount ?? 100;
switch (command.direction) {
case 'up':
deltaY = -amount;
break;
case 'down':
deltaY = amount;
break;
case 'left':
deltaX = -amount;
break;
case 'right':
deltaX = amount;
break;
}
}
await page.evaluate(`window.scrollBy(${deltaX}, ${deltaY})`);
}
+9 -8
View File
@@ -9,11 +9,11 @@ describe('BrowserManager', () => {
beforeAll(async () => {
browser = new BrowserManager();
await browser.launch({ headless: true });
});
}, 30000);
afterAll(async () => {
await browser.close();
});
}, 30000);
describe('launch and close', () => {
it('should report as launched', () => {
@@ -56,7 +56,7 @@ describe('BrowserManager', () => {
it('should report local stealth policy capabilities', async () => {
const testBrowser = new BrowserManager();
await testBrowser.launch({ headless: true, stealth: true });
await testBrowser.launch({ headless: true });
const status = testBrowser.getStealthStatus('chromium');
expect(status.enabled).toBe(true);
@@ -84,7 +84,7 @@ describe('BrowserManager', () => {
const spy = vi.spyOn(chromium, 'connectOverCDP').mockResolvedValue(mockBrowser as any);
const cdpBrowser = new BrowserManager();
await cdpBrowser.launch({ cdpPort: 9222, stealth: true });
await cdpBrowser.launch({ cdpPort: 9222 });
expect(addInitScript).toHaveBeenCalledTimes(1);
const status = cdpBrowser.getStealthStatus();
@@ -97,7 +97,7 @@ describe('BrowserManager', () => {
spy.mockRestore();
});
it('should disable stealth capabilities when launch stealth is false in CDP mode', async () => {
it('should ignore legacy stealth=false and keep CDP stealth capabilities enabled', async () => {
const addInitScript = vi.fn().mockResolvedValue(undefined);
const mockPage = { url: () => 'http://example.com', on: vi.fn(), isClosed: () => false };
const mockContext = {
@@ -116,11 +116,12 @@ describe('BrowserManager', () => {
const cdpBrowser = new BrowserManager();
await cdpBrowser.launch({ cdpPort: 9222, stealth: false });
expect(addInitScript).not.toHaveBeenCalled();
expect(addInitScript).toHaveBeenCalledTimes(1);
const status = cdpBrowser.getStealthStatus();
expect(status.enabled).toBe(false);
expect(status.enabled).toBe(true);
expect(status.connectionKind).toBe('cdp');
expect(status.capabilities).toEqual([]);
expect(status.capabilities).toContain('context-init-scripts');
expect(status.capabilities).not.toContain('chromium-launch-args');
await cdpBrowser.close();
spy.mockRestore();
+46 -3
View File
@@ -16,7 +16,7 @@ import {
} from 'playwright-core';
import path from 'node:path';
import os from 'node:os';
import { existsSync, mkdirSync, rmSync, readFileSync } from 'node:fs';
import { existsSync, mkdirSync, rmSync, readFileSync, statSync } from 'node:fs';
import { writeFile, mkdir } from 'node:fs/promises';
import type { LaunchCommand, TraceEvent } from './types.js';
import { type RefMap, type EnhancedSnapshot, getEnhancedSnapshot, parseRef } from './snapshot.js';
@@ -160,6 +160,7 @@ export class BrowserManager {
private contextTimezoneId: string | undefined = undefined;
private contextHeaders: Record<string, string> | undefined = undefined;
private contextUserAgent: string | undefined = undefined;
private downloadPath: string | null = null;
/**
* Set the persistent color scheme preference.
@@ -445,7 +446,10 @@ export class BrowserManager {
): Promise<void> {
const policy = this.getStealthPolicy();
if (!policy.applyInitScripts) return;
await applyStealthScripts(context, options);
await applyStealthScripts(context, {
...options,
userAgent: this.contextUserAgent,
});
this.logStealthPolicy('init-script applied');
}
@@ -1564,6 +1568,17 @@ export class BrowserManager {
}
this.logStealthPolicy('launch policy', options.browser ?? 'chromium');
if (options.downloadPath) {
this.downloadPath = options.downloadPath;
}
if (this.downloadPath && (cdpEndpoint || options.autoConnect)) {
const warning =
"--download-path is ignored when connecting via CDP or auto-connect (downloads use the remote browser's configuration)";
this.launchWarnings.push(warning);
console.error(`[WARN] ${warning}`);
}
if (cdpEndpoint) {
await this.connectViaCDP(cdpEndpoint);
return;
@@ -1575,6 +1590,13 @@ export class BrowserManager {
}
// Cloud browser providers require explicit opt-in via -p flag or AGENT_BROWSER_PROVIDER env var
// -p flag takes precedence over AGENT_BROWSER_PROVIDER.
if (this.downloadPath && provider) {
const warning =
"--download-path is ignored when using a cloud provider (downloads use the remote browser's configuration)";
this.launchWarnings.push(warning);
console.error(`[WARN] ${warning}`);
}
if (provider === 'browserbase') {
await this.connectToBrowserbase();
return;
@@ -1590,6 +1612,23 @@ export class BrowserManager {
return;
}
if (this.downloadPath) {
const resolved = path.resolve(this.downloadPath);
const stat = statSync(resolved, { throwIfNoEntry: false });
if (stat && !stat.isDirectory()) {
throw new Error(`Download path is not a directory: ${resolved}`);
}
if (!stat) {
try {
mkdirSync(resolved, { recursive: true });
} catch (e: unknown) {
const msg = e instanceof Error ? e.message : String(e);
throw new Error(`Cannot create download directory '${resolved}': ${msg}`);
}
}
this.downloadPath = resolved;
}
const browserType = options.browser ?? 'chromium';
if (hasExtensions && browserType !== 'chromium') {
throw new Error('Extensions are only supported in Chromium');
@@ -1679,6 +1718,7 @@ export class BrowserManager {
...(options.proxy && { proxy: options.proxy }),
ignoreHTTPSErrors: options.ignoreHTTPSErrors ?? false,
...(this.colorScheme && { colorScheme: this.colorScheme }),
...(this.downloadPath && { downloadsPath: this.downloadPath }),
}
);
this.isPersistentContext = true;
@@ -1689,11 +1729,14 @@ export class BrowserManager {
executablePath: options.executablePath,
...(chromeChannel && { channel: chromeChannel }),
args: baseArgs,
...(this.downloadPath && { downloadsPath: this.downloadPath }),
});
this.cdpEndpoint = null;
if (stealthPolicy.enabled && browserType === 'chromium') {
await applyBrowserLevelStealth(this.browser);
await applyBrowserLevelStealth(this.browser, {
userAgent: contextUserAgent,
});
}
if (!options.userAgent && stealthPolicy.enabled && browserType === 'chromium') {
+2 -2
View File
@@ -6,14 +6,14 @@ const cmd = (obj: object) => JSON.stringify(obj);
describe('parseCommand', () => {
describe('launch', () => {
it('should parse launch command with stealth flag', () => {
it('should parse launch command and ignore legacy stealth flag', () => {
const result = parseCommand(
cmd({ id: '1', action: 'launch', headless: false, stealth: true })
);
expect(result.success).toBe(true);
if (result.success) {
expect(result.command.action).toBe('launch');
expect(result.command.stealth).toBe(true);
expect((result.command as any).stealth).toBeUndefined();
}
});
});
+1
View File
@@ -50,6 +50,7 @@ const launchSchema = baseCommandSchema.extend({
ignoreHTTPSErrors: z.boolean().optional(),
allowFileAccess: z.boolean().optional(),
colorScheme: z.enum(['light', 'dark', 'no-preference']).optional(),
downloadPath: z.string().optional(),
storageState: z.string().optional(),
});
+21 -9
View File
@@ -10,6 +10,8 @@ import type { Browser, BrowserContext, Page } from 'playwright-core';
export interface StealthScriptOptions {
locale?: string;
userAgent?: string;
acceptLanguage?: string;
}
/**
@@ -35,25 +37,30 @@ export async function applyStealthScripts(
// Apply CDP-level User-Agent override so Workers also get the patched UA.
// This must be done per-page since CDP sessions are page-scoped.
for (const page of context.pages()) {
await applyCDPStealthToPage(page);
await applyCDPStealthToPage(page, options);
}
context.on('page', (page: Page) => applyCDPStealthToPage(page));
context.on('page', (page: Page) => applyCDPStealthToPage(page, options));
}
/**
* Apply browser-level CDP overrides that affect all targets (including Workers).
* Call this right after browser.launch() and before creating pages.
*/
export async function applyBrowserLevelStealth(browser: Browser): Promise<void> {
export async function applyBrowserLevelStealth(
browser: Browser,
options: StealthScriptOptions = {}
): Promise<void> {
try {
const cdp = await (browser as any).newBrowserCDPSession();
const version = await cdp.send('Browser.getVersion');
const rawUA = version?.userAgent ?? '';
if (!rawUA.includes('HeadlessChrome')) {
const explicitUA = options.userAgent?.trim();
if (!explicitUA && !rawUA.includes('HeadlessChrome')) {
await cdp.detach();
return;
}
const patchedUA = rawUA.replace(/HeadlessChrome/g, 'Chrome');
const patchedUA = explicitUA || rawUA.replace(/HeadlessChrome/g, 'Chrome');
const acceptLanguage = options.acceptLanguage ?? 'en-US,en;q=0.9';
const metadata = buildUserAgentMetadata(patchedUA);
// Override on all existing targets
@@ -66,7 +73,7 @@ export async function applyBrowserLevelStealth(browser: Browser): Promise<void>
});
await cdp.send('Emulation.setUserAgentOverride', {
userAgent: patchedUA,
acceptLanguage: 'en-US,en;q=0.9',
acceptLanguage,
platform: getPlatformString(),
userAgentMetadata: metadata,
});
@@ -81,17 +88,22 @@ export async function applyBrowserLevelStealth(browser: Browser): Promise<void>
}
}
async function applyCDPStealthToPage(page: Page): Promise<void> {
async function applyCDPStealthToPage(
page: Page,
options: StealthScriptOptions = {}
): Promise<void> {
try {
const cdp = await page.context().newCDPSession(page);
const ua = await cdp.send('Browser.getVersion').catch(() => null);
const rawUA = ua?.userAgent ?? '';
const patchedUA = rawUA.replace(/HeadlessChrome/g, 'Chrome');
const explicitUA = options.userAgent?.trim();
const patchedUA = explicitUA || rawUA.replace(/HeadlessChrome/g, 'Chrome');
const acceptLanguage = options.acceptLanguage ?? 'en-US,en;q=0.9';
const metadata = buildUserAgentMetadata(patchedUA);
await cdp.send('Emulation.setUserAgentOverride', {
userAgent: patchedUA,
acceptLanguage: 'en-US,en;q=0.9',
acceptLanguage,
platform: getPlatformString(),
userAgentMetadata: metadata,
});
+1
View File
@@ -31,6 +31,7 @@ export interface LaunchCommand extends BaseCommand {
ignoreHTTPSErrors?: boolean;
allowFileAccess?: boolean; // Enable file:// URL access and cross-origin file requests
colorScheme?: 'light' | 'dark' | 'no-preference'; // Persistent color scheme override
downloadPath?: string; // Directory for browser downloads (Playwright's downloadsPath)
// Auto-load state file for session persistence
autoStateFilePath?: string;
}
+261
View File
@@ -0,0 +1,261 @@
import { describe, it, expect, beforeAll } from 'vitest';
import { query } from '@anthropic-ai/claude-agent-sdk';
import type { SDKMessage, SDKResultMessage } from '@anthropic-ai/claude-agent-sdk';
import { mkdirSync, readFileSync, writeFileSync, appendFileSync, existsSync, readdirSync, rmSync } from 'node:fs';
import path from 'node:path';
const AI_GATEWAY_URL =
process.env.ANTHROPIC_BASE_URL || 'https://ai-gateway.vercel.sh';
const API_KEY = process.env.AI_GATEWAY_API_KEY;
const MODEL = process.env.DOGFOOD_MODEL || 'anthropic/claude-haiku-4.5';
const CUSTOM_URL = process.env.DOGFOOD_URL;
const FIXTURE_PATH = path.resolve('test/e2e/fixtures/buggy-app.html');
const SKILL_PATH = path.resolve('skills/dogfood/SKILL.md');
const TARGET_URL = CUSTOM_URL || `file://${FIXTURE_PATH}`;
const IS_FIXTURE = !CUSTOM_URL;
const OUTPUT_DIR = path.resolve('test/e2e/.dogfood-output');
const EVAL_TIMEOUT = 10 * 60 * 1000;
async function runDogfood(outputDir: string): Promise<{
result: SDKResultMessage | null;
messages: SDKMessage[];
toolsUsed: Set<string>;
}> {
const instruction = [
`Read the dogfood skill at ${SKILL_PATH} and follow its workflow.`,
`Dogfood ${TARGET_URL}`,
`Output directory: ${outputDir}`,
].join(' ');
const messages: SDKMessage[] = [];
const toolsUsed = new Set<string>();
let result: SDKResultMessage | null = null;
const conversation = query({
prompt: instruction,
options: {
model: MODEL,
cwd: process.cwd(),
allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Glob', 'Grep'],
permissionMode: 'bypassPermissions',
allowDangerouslySkipPermissions: true,
maxTurns: 80,
maxBudgetUsd: 2,
settingSources: ['project'],
persistSession: false,
env: {
...process.env,
ANTHROPIC_BASE_URL: AI_GATEWAY_URL,
ANTHROPIC_API_KEY: API_KEY,
},
},
});
const verbose = process.env.DOGFOOD_VERBOSE !== '0';
const log = verbose ? (msg: string) => process.stderr.write(` [dogfood] ${msg}\n`) : () => {};
const chatLogPath = path.join(outputDir, 'chat-log.jsonl');
writeFileSync(chatLogPath, '');
function appendToLog(entry: Record<string, unknown>) {
appendFileSync(chatLogPath, JSON.stringify(entry) + '\n');
}
for await (const message of conversation) {
messages.push(message);
if (message.type === 'system' && message.subtype === 'init') {
log(`session started (model: ${message.model})`);
appendToLog({ type: 'system', subtype: 'init', model: message.model });
}
if (message.type === 'assistant' && message.message?.content) {
const logParts: Record<string, unknown>[] = [];
for (const block of message.message.content) {
if ('type' in block && block.type === 'tool_use') {
toolsUsed.add(block.name);
const input = block.input as Record<string, unknown>;
let preview: string;
if (block.name === 'Bash') {
const cmd = String(input.command ?? '');
const firstLine = cmd.split('\n').find(l => l.trim() && !l.trim().startsWith('#')) ?? cmd.split('\n')[0];
preview = firstLine.trim().slice(0, 200);
} else if (block.name === 'Write') {
preview = String(input.file_path ?? input.path ?? '');
} else if (block.name === 'Read') {
preview = String(input.file_path ?? input.path ?? '');
} else if (block.name === 'Edit') {
preview = String(input.file_path ?? input.path ?? '');
} else {
preview = JSON.stringify(input).slice(0, 120);
}
log(`${block.name}: ${preview}`);
logParts.push({ tool: block.name, input: block.input });
}
if ('type' in block && block.type === 'text' && block.text) {
const line = block.text.split('\n')[0].slice(0, 120);
if (line.trim()) log(line);
logParts.push({ text: block.text });
}
}
appendToLog({ type: 'assistant', content: logParts });
}
if (message.type === 'result') {
result = message;
const cost = `$${message.total_cost_usd.toFixed(4)}`;
const usage = message.usage;
const cacheRead = usage.cache_read_input_tokens ?? 0;
const cacheCreate = usage.cache_creation_input_tokens ?? 0;
const inputTokens = usage.input_tokens ?? 0;
const cacheInfo = cacheRead > 0
? ` | cache: ${cacheRead} read, ${cacheCreate} created, ${inputTokens} uncached`
: '';
if (message.subtype === 'success') {
log(`done (${message.num_turns} turns, ${cost}${cacheInfo})`);
} else {
log(`stopped: ${message.subtype} (${message.num_turns} turns, ${cost}${cacheInfo})`);
}
appendToLog({ type: 'result', subtype: message.subtype, num_turns: message.num_turns, cost: message.total_cost_usd });
}
}
log(`chat log: ${chatLogPath}`);
return { result, messages, toolsUsed };
}
function findFiles(dir: string, ext: string): string[] {
if (!existsSync(dir)) return [];
return readdirSync(dir, { recursive: true })
.map(String)
.filter((f) => f.endsWith(ext));
}
describe.skipIf(!API_KEY)('Dogfood e2e eval (Agent SDK)', () => {
const outputDir = OUTPUT_DIR;
let evalResult: Awaited<ReturnType<typeof runDogfood>>;
beforeAll(async () => {
if (existsSync(outputDir)) {
rmSync(outputDir, { recursive: true, force: true });
}
mkdirSync(outputDir, { recursive: true });
evalResult = await runDogfood(outputDir);
}, EVAL_TIMEOUT);
it('completes without hard failure', () => {
expect(evalResult.result, 'No result message received').toBeTruthy();
const acceptable = ['success', 'error_max_turns', 'error_max_budget_usd'];
expect(
acceptable,
`Agent failed unexpectedly: ${evalResult.result!.subtype}`
).toContain(evalResult.result!.subtype);
});
it('used agent-browser via Bash tool', () => {
expect(
evalResult.toolsUsed.has('Bash'),
'Agent never used Bash (needed for agent-browser commands)'
).toBe(true);
});
it('produced a report file', () => {
const reportPath = path.join(outputDir, 'report.md');
expect(existsSync(reportPath), 'report.md not found in output dir').toBe(
true
);
});
it('found a minimum number of issues', () => {
const reportPath = path.join(outputDir, 'report.md');
if (!existsSync(reportPath)) return;
const report = readFileSync(reportPath, 'utf-8');
const issueBlocks = report.match(/###\s+ISSUE-\d+/g) || [];
if (IS_FIXTURE) {
expect(
issueBlocks.length,
`Expected >=2 issues from fixture, found ${issueBlocks.length}`
).toBeGreaterThanOrEqual(2);
} else {
expect(issueBlocks.length).toBeGreaterThanOrEqual(1);
}
});
it('each issue has required fields and repro evidence', () => {
const reportPath = path.join(outputDir, 'report.md');
if (!existsSync(reportPath)) return;
const report = readFileSync(reportPath, 'utf-8');
const issueSections = report.split(/(?=###\s+ISSUE-\d+)/).slice(1);
for (const section of issueSections) {
const issueId = section.match(/ISSUE-\d+/)?.[0] ?? 'unknown';
expect(section, `${issueId}: missing Severity`).toMatch(
/\*\*Severity\*\*/i
);
const sevMatch = section.match(
/\*\*Severity\*\*\s*\|?\s*(critical|high|medium|low)/i
);
expect(sevMatch, `${issueId}: invalid severity value`).toBeTruthy();
expect(section, `${issueId}: missing Category`).toMatch(
/\*\*Category\*\*/i
);
expect(section, `${issueId}: missing URL`).toMatch(/\*\*URL\*\*/i);
expect(section, `${issueId}: missing Repro Video field`).toMatch(
/\*\*Repro Video\*\*/i
);
const hasScreenshot = /!\[.*?\]\(.*?\)/.test(section);
const hasReproSteps = /\*\*Repro Steps\*\*/i.test(section);
expect(
hasScreenshot || hasReproSteps,
`${issueId}: needs either screenshot refs or repro steps`
).toBe(true);
}
});
it('has a summary table with non-zero total', () => {
const reportPath = path.join(outputDir, 'report.md');
if (!existsSync(reportPath)) return;
const report = readFileSync(reportPath, 'utf-8');
expect(report, 'Missing Summary section').toContain('## Summary');
const totalMatch = report.match(/\*\*Total\*\*\s*\|?\s*\*\*(\d+)\*\*/);
expect(totalMatch, 'Summary Total not found').toBeTruthy();
if (totalMatch) {
const total = parseInt(totalMatch[1], 10);
expect(total, 'Summary Total should be > 0').toBeGreaterThan(0);
}
});
it('produced screenshot files', () => {
const screenshotsDir = path.join(outputDir, 'screenshots');
const screenshots = findFiles(screenshotsDir, '.png');
expect(
screenshots.length,
'No screenshot files found in output'
).toBeGreaterThan(0);
});
it('produced video files for interactive issues', () => {
const reportPath = path.join(outputDir, 'report.md');
if (!existsSync(reportPath)) return;
const report = readFileSync(reportPath, 'utf-8');
const hasVideoRefs = /videos\/issue-\d+/.test(report);
if (!hasVideoRefs) return;
const videosDir = path.join(outputDir, 'videos');
const videos = findFiles(videosDir, '.webm');
expect(
videos.length,
'Report references videos but none were found'
).toBeGreaterThan(0);
});
});
+210
View File
@@ -0,0 +1,210 @@
import { describe, it, expect } from 'vitest';
import { readFileSync, existsSync } from 'node:fs';
import path from 'node:path';
const SKILL_DIR = path.resolve('skills/dogfood');
const SKILL_MD = path.join(SKILL_DIR, 'SKILL.md');
const TAXONOMY_MD = path.join(SKILL_DIR, 'references', 'issue-taxonomy.md');
const TEMPLATE_MD = path.join(SKILL_DIR, 'templates', 'dogfood-report-template.md');
function readSkillFile(filePath: string): string {
return readFileSync(filePath, 'utf-8');
}
function parseFrontmatter(content: string): Record<string, string> {
const match = content.match(/^---\n([\s\S]*?)\n---/);
if (!match) return {};
const fields: Record<string, string> = {};
for (const line of match[1].split('\n')) {
const colonIdx = line.indexOf(':');
if (colonIdx > 0) {
fields[line.slice(0, colonIdx).trim()] = line.slice(colonIdx + 1).trim();
}
}
return fields;
}
describe('Dogfood skill: file structure', () => {
it('SKILL.md exists', () => {
expect(existsSync(SKILL_MD)).toBe(true);
});
it('references/issue-taxonomy.md exists', () => {
expect(existsSync(TAXONOMY_MD)).toBe(true);
});
it('templates/dogfood-report-template.md exists', () => {
expect(existsSync(TEMPLATE_MD)).toBe(true);
});
});
describe('Dogfood skill: SKILL.md frontmatter', () => {
const content = readSkillFile(SKILL_MD);
const frontmatter = parseFrontmatter(content);
it('has name field', () => {
expect(frontmatter.name).toBe('dogfood');
});
it('has description field', () => {
expect(frontmatter.description).toBeTruthy();
expect(frontmatter.description!.length).toBeGreaterThan(50);
});
it('has allowed-tools field', () => {
expect(frontmatter['allowed-tools']).toBeTruthy();
expect(frontmatter['allowed-tools']).toContain('agent-browser');
});
});
describe('Dogfood skill: SKILL.md body references', () => {
const content = readSkillFile(SKILL_MD);
it('references issue-taxonomy.md', () => {
expect(content).toContain('references/issue-taxonomy.md');
});
it('references dogfood-report-template.md', () => {
expect(content).toContain('templates/dogfood-report-template.md');
});
it('referenced files exist on disk', () => {
const refPattern = /\[.*?\]\((references\/.*?\.md|templates\/.*?\.md)\)/g;
const refs = [...content.matchAll(refPattern)].map((m) => m[1]);
expect(refs.length).toBeGreaterThan(0);
for (const ref of refs) {
const fullPath = path.join(SKILL_DIR, ref);
expect(existsSync(fullPath), `Missing: ${ref}`).toBe(true);
}
});
});
describe('Dogfood skill: report template', () => {
const template = readSkillFile(TEMPLATE_MD);
it('has ISSUE- prefix in issue blocks', () => {
expect(template).toContain('ISSUE-');
});
it('has Severity field', () => {
expect(template).toContain('**Severity**');
});
it('has Category field', () => {
expect(template).toContain('**Category**');
});
it('has URL field', () => {
expect(template).toContain('**URL**');
});
it('has Repro Video field', () => {
expect(template).toContain('**Repro Video**');
});
it('has Repro Steps section', () => {
expect(template).toContain('**Repro Steps**');
});
it('has screenshot image references in repro steps', () => {
expect(template).toMatch(/!\[.*?\]\(screenshots\//);
});
it('lists all valid severity values', () => {
expect(template).toMatch(/critical\s*\/\s*high\s*\/\s*medium\s*\/\s*low/);
});
it('lists all valid category values', () => {
const categoryLine = template
.split('\n')
.find((l) => l.includes('**Category**'));
expect(categoryLine).toBeTruthy();
for (const cat of [
'visual',
'functional',
'ux',
'content',
'performance',
'console',
'accessibility',
]) {
expect(categoryLine!.toLowerCase()).toContain(cat);
}
});
it('has Summary table with severity counts', () => {
expect(template).toContain('## Summary');
for (const sev of ['Critical', 'High', 'Medium', 'Low', 'Total']) {
expect(template).toContain(sev);
}
});
});
describe('Dogfood skill: issue taxonomy', () => {
const taxonomy = readSkillFile(TAXONOMY_MD);
it('has severity level definitions', () => {
expect(taxonomy).toContain('## Severity Levels');
for (const sev of ['critical', 'high', 'medium', 'low']) {
expect(taxonomy.toLowerCase()).toContain(`**${sev}**`);
}
});
it('has all 7 category sections', () => {
const expectedCategories = [
'Visual',
'Functional',
'UX',
'Content',
'Performance',
'Console',
'Accessibility',
];
for (const cat of expectedCategories) {
expect(taxonomy).toMatch(new RegExp(`###\\s+.*${cat}`, 'i'));
}
});
it('has exploration checklist', () => {
expect(taxonomy).toContain('## Exploration Checklist');
});
it('checklist has numbered items', () => {
const checklistSection = taxonomy.split('## Exploration Checklist')[1];
expect(checklistSection).toBeTruthy();
const numberedItems = checklistSection!.match(/^\d+\./gm);
expect(numberedItems!.length).toBeGreaterThanOrEqual(5);
});
});
describe('Dogfood skill: cross-consistency', () => {
const template = readSkillFile(TEMPLATE_MD);
const taxonomy = readSkillFile(TAXONOMY_MD);
it('every category in template exists in taxonomy', () => {
const categoryLine = template
.split('\n')
.find((l) => l.includes('**Category**'));
expect(categoryLine).toBeTruthy();
const categories = categoryLine!
.split('|')
.pop()!
.split('/')
.map((c) => c.trim().toLowerCase())
.filter(Boolean);
for (const cat of categories) {
expect(
taxonomy.toLowerCase(),
`Category "${cat}" from template not found in taxonomy`
).toMatch(new RegExp(`###\\s+.*${cat}`));
}
});
it('every severity in template exists in taxonomy', () => {
for (const sev of ['critical', 'high', 'medium', 'low']) {
expect(taxonomy.toLowerCase()).toContain(`**${sev}**`);
}
});
});
+159
View File
@@ -0,0 +1,159 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Buggy App - Dogfood Test Fixture</title>
<style>
* { margin: 0; padding: 0; box-sizing: border-box; }
body { font-family: system-ui, sans-serif; color: #333; background: #f9f9f9; }
header { background: #1a1a2e; color: #fff; padding: 16px 24px; display: flex; justify-content: space-between; align-items: center; }
header h1 { font-size: 20px; }
nav { display: flex; gap: 16px; }
nav a { color: #ccc; text-decoration: none; }
nav a:hover { color: #fff; }
main { max-width: 960px; margin: 0 auto; padding: 32px 24px; }
.card { background: #fff; border: 1px solid #e0e0e0; border-radius: 8px; padding: 24px; margin-bottom: 24px; }
.card h2 { margin-bottom: 12px; }
.btn { padding: 8px 16px; border: none; border-radius: 4px; cursor: pointer; font-size: 14px; }
.btn-primary { background: #3b82f6; color: #fff; }
.btn-danger { background: #ef4444; color: #fff; }
input, textarea { padding: 8px 12px; border: 1px solid #d0d0d0; border-radius: 4px; font-size: 14px; width: 100%; margin-bottom: 12px; }
label { display: block; margin-bottom: 4px; font-weight: 500; }
footer { text-align: center; padding: 24px; color: #999; font-size: 12px; }
/* BUG: Visual - clipped text via overflow: hidden on a short container */
.clipped-container {
overflow: hidden;
height: 20px;
border: 1px solid #e0e0e0;
padding: 4px 8px;
margin-top: 8px;
}
/* BUG: Visual - misaligned element */
.misaligned {
display: flex;
align-items: flex-start; /* should be center */
gap: 12px;
padding: 12px;
background: #f0f4ff;
border-radius: 8px;
margin-top: 12px;
}
.misaligned .icon {
width: 40px;
height: 40px;
background: #3b82f6;
border-radius: 50%;
flex-shrink: 0;
margin-top: 14px; /* intentionally off */
}
.misaligned .label {
font-size: 16px;
line-height: 40px;
}
</style>
</head>
<body>
<header>
<h1>Buggy App</h1>
<nav>
<a href="#dashboard">Dashboard</a>
<a href="#settings">Settings</a>
<!-- BUG: Functional - broken link to nonexistent page -->
<a href="#/this-page-does-not-exist">Reports</a>
<a href="#help">Help</a>
</nav>
</header>
<main>
<!-- BUG: Content - typo "Welocme" -->
<h2 style="margin-bottom: 24px;">Welocme to the Dashboard</h2>
<!-- Card 1: Functional bug - button throws JS error -->
<div class="card">
<h2>Quick Actions</h2>
<p>Perform common tasks from here.</p>
<div style="margin-top: 12px; display: flex; gap: 8px;">
<!-- BUG: Functional - button throws JS error on click -->
<button class="btn btn-primary" onclick="processAction()">Run Analysis</button>
<button class="btn btn-danger" onclick="deleteAllData()">Delete All Data</button>
</div>
</div>
<!-- Card 2: Visual bugs - clipped text and misaligned element -->
<div class="card">
<h2>System Status</h2>
<!-- BUG: Visual - text is clipped because container is too short -->
<div class="clipped-container">
The system is currently operating normally. All services are online and responding within expected latency thresholds. Last health check completed at 14:32 UTC.
</div>
<!-- BUG: Visual - icon and label are misaligned -->
<div class="misaligned">
<div class="icon"></div>
<span class="label">All systems operational</span>
</div>
</div>
<!-- Card 3: Content bug - placeholder text -->
<div class="card">
<h2>Recent Activity</h2>
<!-- BUG: Content - lorem ipsum placeholder left in -->
<p>Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris.</p>
</div>
<!-- Card 4: UX bug - form with no feedback on submit -->
<div class="card">
<h2>Contact Support</h2>
<form id="support-form">
<label for="subject">Subject</label>
<input type="text" id="subject" placeholder="Enter subject">
<label for="message">Message</label>
<textarea id="message" rows="3" placeholder="Describe your issue"></textarea>
<!-- BUG: UX - submit does nothing, no feedback -->
<button type="submit" class="btn btn-primary">Send Message</button>
</form>
</div>
<!-- Card 5: UX bug - empty state with no message -->
<div class="card">
<h2>Notifications</h2>
<!-- BUG: UX - empty container with no empty state message -->
<div id="notifications-list" style="min-height: 60px;">
</div>
</div>
</main>
<footer>
&copy; 2025 Buggy App Inc. All rights reserved.
</footer>
<script>
// BUG: Console - error on page load
console.error("Failed to initialize analytics: endpoint not configured");
// BUG: Console - failed fetch on page load
fetch("https://api.nonexistent-endpoint.invalid/v1/health")
.catch(function() {});
// BUG: Functional - function referenced by button is broken
function processAction() {
// Throws because undefinedService is not defined
undefinedService.runAnalysis();
}
// No confirmation for destructive action
function deleteAllData() {
alert("All data deleted!");
}
// Form submit does nothing
document.getElementById("support-form").addEventListener("submit", function(e) {
e.preventDefault();
});
</script>
</body>
</html>
+2 -2
View File
@@ -146,9 +146,9 @@ describe('File Access (Issue #345)', () => {
const content = await page.locator('h1').textContent();
expect(content).toBe('Test File Access');
// Verify webdriver is hidden (from custom arg)
// Verify webdriver is hidden under stealth defaults
const webdriver = await page.evaluate(() => navigator.webdriver);
expect(webdriver).toBe(false);
expect(webdriver).toBeUndefined();
});
});
});
+7 -7
View File
@@ -11,7 +11,7 @@ describe('Launch Options', () => {
});
describe('browser args', () => {
it('should launch with custom args to disable webdriver detection', async () => {
it('should keep webdriver undefined with custom args under stealth defaults', async () => {
browser = new BrowserManager();
await browser.launch({
headless: true,
@@ -21,9 +21,9 @@ describe('Launch Options', () => {
const page = browser.getPage();
await page.goto('about:blank');
// Check that navigator.webdriver is false
// Under stealth defaults, webdriver is hidden (undefined)
const webdriver = await page.evaluate(() => navigator.webdriver);
expect(webdriver).toBe(false);
expect(webdriver).toBeUndefined();
});
it('should launch with multiple args', async () => {
@@ -39,7 +39,7 @@ describe('Launch Options', () => {
expect(browser.isLaunched()).toBe(true);
});
it('should launch without args (default behavior)', async () => {
it('should launch without args and keep webdriver hidden by default', async () => {
browser = new BrowserManager();
await browser.launch({
headless: true,
@@ -48,9 +48,9 @@ describe('Launch Options', () => {
const page = browser.getPage();
await page.goto('about:blank');
// Default Playwright behavior - webdriver is true
// Stealth default behavior - webdriver is hidden
const webdriver = await page.evaluate(() => navigator.webdriver);
expect(webdriver).toBe(true);
expect(webdriver).toBeUndefined();
});
});
@@ -152,7 +152,7 @@ describe('Launch Options', () => {
// Verify webdriver is hidden
const webdriver = await page.evaluate(() => navigator.webdriver);
expect(webdriver).toBe(false);
expect(webdriver).toBeUndefined();
});
});
});
+1 -1
View File
@@ -3,7 +3,7 @@ import { defineConfig } from 'vitest/config';
export default defineConfig({
test: {
globals: true,
include: ['src/**/*.test.ts', 'test/**/*.test.ts'],
include: ['src/**/*.test.ts', 'test/**/*.test.ts', 'test/**/*.eval.ts'],
testTimeout: 30000,
},
});