Compare commits

...
Author SHA1 Message Date
Chris Tate 18ec83914e 0.4.2 2026-01-12 00:57:29 -06:00
Chris Tate 5e95c6cbff fix skill name 2026-01-12 00:56:26 -06:00
Chris Tate bc0b99c374 0.4.1 (#17)
* sync version

* 0.4.1

* add release script
2026-01-12 00:43:52 -06:00
Chris Tate a0802b1863 fix locator issues (#14)
* fix locator issues

* address feedback
2026-01-12 00:29:53 -06:00
Chris Tate 403a7e5d56 usage with agents (#15) 2026-01-12 00:29:45 -06:00
Chris Tate 277febad63 fix session cmd (#13)
* fix session cmd

* address feedback
2026-01-12 00:06:34 -06:00
11 changed files with 611 additions and 34 deletions
+44
View File
@@ -403,6 +403,50 @@ The daemon starts automatically on first command and persists between commands f
| Linux x64 | ✅ Native Rust | Node.js |
| Windows | - | Node.js |
## Usage with AI Agents
### Just ask the agent
The simplest approach - just tell your agent to use it:
```
Use agent-browser to test the login flow. Run agent-browser --help to see available commands.
```
The `--help` output is comprehensive and most agents can figure it out from there.
### AGENTS.md / CLAUDE.md
For more consistent results, add to your project or global instructions file:
```markdown
## Browser Automation
Use `agent-browser` for web automation. Run `agent-browser --help` for all commands.
Core workflow:
1. `agent-browser open <url>` - Navigate to page
2. `agent-browser snapshot -i` - Get interactive elements with refs (@e1, @e2)
3. `agent-browser click @e1` / `fill @e2 "text"` - Interact using refs
4. Re-snapshot after page changes
```
### Claude Code Skill
For Claude Code, a [skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices) provides richer context:
```bash
cp -r node_modules/agent-browser/skills/agent-browser .claude/skills/
```
Or download:
```bash
mkdir -p .claude/skills/agent-browser
curl -o .claude/skills/agent-browser/SKILL.md \
https://raw.githubusercontent.com/vercel-labs/agent-browser/main/skills/agent-browser/SKILL.md
```
## License
Apache-2.0
+75 -1
View File
@@ -4,11 +4,12 @@ version = 4
[[package]]
name = "agent-browser"
version = "0.4.0"
version = "0.4.2"
dependencies = [
"libc",
"serde",
"serde_json",
"windows-sys",
]
[[package]]
@@ -107,6 +108,79 @@ version = "1.0.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
[[package]]
name = "windows-sys"
version = "0.52.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
dependencies = [
"windows-targets",
]
[[package]]
name = "windows-targets"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
dependencies = [
"windows_aarch64_gnullvm",
"windows_aarch64_msvc",
"windows_i686_gnu",
"windows_i686_gnullvm",
"windows_i686_msvc",
"windows_x86_64_gnu",
"windows_x86_64_gnullvm",
"windows_x86_64_msvc",
]
[[package]]
name = "windows_aarch64_gnullvm"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
[[package]]
name = "windows_aarch64_msvc"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
[[package]]
name = "windows_i686_gnu"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
[[package]]
name = "windows_i686_gnullvm"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
[[package]]
name = "windows_i686_msvc"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
[[package]]
name = "windows_x86_64_gnu"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
[[package]]
name = "windows_x86_64_msvc"
version = "0.52.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
[[package]]
name = "zmij"
version = "1.0.12"
+4 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "agent-browser"
version = "0.4.0"
version = "0.4.2"
edition = "2021"
description = "Fast browser automation CLI for AI agents"
license = "Apache-2.0"
@@ -12,6 +12,9 @@ serde_json = "1.0"
[target.'cfg(unix)'.dependencies]
libc = "0.2"
[target.'cfg(windows)'.dependencies]
windows-sys = { version = "0.52", features = ["Win32_System_Threading", "Win32_Foundation"] }
[profile.release]
opt-level = 3
lto = true
+85
View File
@@ -6,14 +6,93 @@ mod output;
use serde_json::json;
use std::env;
use std::fs;
use std::process::exit;
#[cfg(unix)]
use libc;
#[cfg(windows)]
use windows_sys::Win32::Foundation::CloseHandle;
#[cfg(windows)]
use windows_sys::Win32::System::Threading::{OpenProcess, PROCESS_QUERY_LIMITED_INFORMATION};
use commands::{gen_id, parse_command, ParseError};
use connection::{ensure_daemon, send_command};
use flags::{clean_args, parse_flags};
use install::run_install;
use output::{print_help, print_response};
fn run_session(args: &[String], session: &str, json_mode: bool) {
let subcommand = args.get(1).map(|s| s.as_str());
match subcommand {
Some("list") => {
let tmp = env::temp_dir();
let mut sessions: Vec<String> = Vec::new();
if let Ok(entries) = fs::read_dir(&tmp) {
for entry in entries.flatten() {
let name = entry.file_name().to_string_lossy().to_string();
// Look for socket files (Unix) or pid files
if name.starts_with("agent-browser-") && name.ends_with(".pid") {
let session_name = name
.strip_prefix("agent-browser-")
.and_then(|s| s.strip_suffix(".pid"))
.unwrap_or("");
if !session_name.is_empty() {
// Check if session is actually running
let pid_path = tmp.join(&name);
if let Ok(pid_str) = fs::read_to_string(&pid_path) {
if let Ok(pid) = pid_str.trim().parse::<u32>() {
#[cfg(unix)]
let running = unsafe { libc::kill(pid as i32, 0) == 0 };
#[cfg(windows)]
let running = unsafe {
let handle = OpenProcess(PROCESS_QUERY_LIMITED_INFORMATION, 0, pid);
if handle != 0 {
CloseHandle(handle);
true
} else {
false
}
};
if running {
sessions.push(session_name.to_string());
}
}
}
}
}
}
}
if json_mode {
println!(
r#"{{"success":true,"data":{{"sessions":{}}}}}"#,
serde_json::to_string(&sessions).unwrap_or_default()
);
} else if sessions.is_empty() {
println!("No active sessions");
} else {
println!("Active sessions:");
for s in &sessions {
let marker = if s == session { "" } else { " " };
println!("{} {}", marker, s);
}
}
}
None | Some(_) => {
// Just show current session
if json_mode {
println!(r#"{{"success":true,"data":{{"session":"{}"}}}}"#, session);
} else {
println!("{}", session);
}
}
}
}
fn main() {
let args: Vec<String> = env::args().skip(1).collect();
let flags = parse_flags(&args);
@@ -31,6 +110,12 @@ fn main() {
return;
}
// Handle session separately (doesn't need daemon)
if clean.get(0).map(|s| s.as_str()) == Some("session") {
run_session(&clean, &flags.session, flags.json);
return;
}
let cmd = match parse_command(&clean, &flags) {
Ok(c) => c,
Err(e) => {
+4
View File
@@ -215,6 +215,10 @@ Debug:
errors [--clear] View page errors
highlight <sel> Highlight element
Sessions:
session Show current session name
session list List active sessions
Setup:
install Install browser binaries
install --with-deps Also install system dependencies (Linux)
+11 -7
View File
@@ -1,26 +1,30 @@
{
"name": "agent-browser",
"version": "0.4.0",
"version": "0.4.2",
"description": "Headless browser automation CLI for AI agents",
"type": "module",
"main": "dist/daemon.js",
"files": [
"dist",
"bin",
"scripts"
"scripts",
"skills"
],
"bin": {
"agent-browser": "./bin/agent-browser"
},
"scripts": {
"prepare": "husky",
"version:sync": "node scripts/sync-version.js",
"version": "npm run version:sync && git add cli/Cargo.toml",
"build": "tsc",
"build:native": "cargo build --release --manifest-path cli/Cargo.toml && node scripts/copy-native.js",
"build:linux": "docker compose -f docker/docker-compose.yml run --rm build-linux",
"build:macos": "(cargo build --release --manifest-path cli/Cargo.toml --target aarch64-apple-darwin & cargo build --release --manifest-path cli/Cargo.toml --target x86_64-apple-darwin & wait) && cp cli/target/aarch64-apple-darwin/release/agent-browser bin/agent-browser-darwin-arm64 && cp cli/target/x86_64-apple-darwin/release/agent-browser bin/agent-browser-darwin-x64",
"build:windows": "docker compose -f docker/docker-compose.yml run --rm build-windows",
"build:all-platforms": "(npm run build:linux & npm run build:windows & wait) && npm run build:macos",
"build:native": "npm run version:sync && cargo build --release --manifest-path cli/Cargo.toml && node scripts/copy-native.js",
"build:linux": "npm run version:sync && docker compose -f docker/docker-compose.yml run --rm build-linux",
"build:macos": "npm run version:sync && (cargo build --release --manifest-path cli/Cargo.toml --target aarch64-apple-darwin & cargo build --release --manifest-path cli/Cargo.toml --target x86_64-apple-darwin & wait) && cp cli/target/aarch64-apple-darwin/release/agent-browser bin/agent-browser-darwin-arm64 && cp cli/target/x86_64-apple-darwin/release/agent-browser bin/agent-browser-darwin-x64",
"build:windows": "npm run version:sync && docker compose -f docker/docker-compose.yml run --rm build-windows",
"build:all-platforms": "npm run version:sync && (npm run build:linux & npm run build:windows & wait) && npm run build:macos",
"build:docker": "docker build -t agent-browser-builder -f docker/Dockerfile.build .",
"release": "npm run version:sync && npm run build && npm run build:all-platforms && npm publish",
"start": "node dist/daemon.js",
"dev": "tsx src/daemon.ts",
"typecheck": "tsc --noEmit",
+43
View File
@@ -0,0 +1,43 @@
#!/usr/bin/env node
/**
* Syncs the version from package.json to all other config files.
* Run this script before building or releasing.
*/
import { readFileSync, writeFileSync } from "fs";
import { dirname, join } from "path";
import { fileURLToPath } from "url";
const __dirname = dirname(fileURLToPath(import.meta.url));
const rootDir = join(__dirname, "..");
// Read version from package.json (single source of truth)
const packageJson = JSON.parse(
readFileSync(join(rootDir, "package.json"), "utf-8")
);
const version = packageJson.version;
console.log(`Syncing version ${version} to all config files...`);
// Update Cargo.toml
const cargoTomlPath = join(rootDir, "cli/Cargo.toml");
let cargoToml = readFileSync(cargoTomlPath, "utf-8");
const cargoVersionRegex = /^version\s*=\s*"[^"]*"/m;
const newCargoVersion = `version = "${version}"`;
if (cargoVersionRegex.test(cargoToml)) {
const oldMatch = cargoToml.match(cargoVersionRegex)?.[0];
if (oldMatch !== newCargoVersion) {
cargoToml = cargoToml.replace(cargoVersionRegex, newCargoVersion);
writeFileSync(cargoTomlPath, cargoToml);
console.log(` Updated cli/Cargo.toml: ${oldMatch} -> ${newCargoVersion}`);
} else {
console.log(` cli/Cargo.toml already up to date`);
}
} else {
console.error(" Could not find version field in cli/Cargo.toml");
process.exit(1);
}
console.log("Version sync complete.");
+143
View File
@@ -0,0 +1,143 @@
---
name: agent-browser
description: Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
---
# Browser Automation with agent-browser
## Quick start
```bash
agent-browser open <url> # Navigate to page
agent-browser snapshot -i # Get interactive elements with refs
agent-browser click @e1 # Click element by ref
agent-browser fill @e2 "text" # Fill input by ref
agent-browser close # Close browser
```
## Core workflow
1. Navigate: `agent-browser open <url>`
2. Snapshot: `agent-browser snapshot -i` (returns elements with refs like `@e1`, `@e2`)
3. Interact using refs from the snapshot
4. Re-snapshot after navigation or significant DOM changes
## Commands
### Navigation
```bash
agent-browser open <url> # Navigate to URL
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
agent-browser close # Close browser
```
### Snapshot (page analysis)
```bash
agent-browser snapshot # Full accessibility tree
agent-browser snapshot -i # Interactive elements only (recommended)
agent-browser snapshot -c # Compact output
agent-browser snapshot -d 3 # Limit depth to 3
```
### Interactions (use @refs from snapshot)
```bash
agent-browser click @e1 # Click
agent-browser dblclick @e1 # Double-click
agent-browser fill @e2 "text" # Clear and type
agent-browser type @e2 "text" # Type without clearing
agent-browser press Enter # Press key
agent-browser press Control+a # Key combination
agent-browser hover @e1 # Hover
agent-browser check @e1 # Check checkbox
agent-browser uncheck @e1 # Uncheck checkbox
agent-browser select @e1 "value" # Select dropdown
agent-browser scroll down 500 # Scroll page
agent-browser scrollintoview @e1 # Scroll element into view
```
### Get information
```bash
agent-browser get text @e1 # Get element text
agent-browser get value @e1 # Get input value
agent-browser get title # Get page title
agent-browser get url # Get current URL
```
### Screenshots
```bash
agent-browser screenshot # Screenshot to stdout
agent-browser screenshot path.png # Save to file
agent-browser screenshot --full # Full page
```
### Wait
```bash
agent-browser wait @e1 # Wait for element
agent-browser wait 2000 # Wait milliseconds
agent-browser wait --text "Success" # Wait for text
agent-browser wait --load networkidle # Wait for network idle
```
### Semantic locators (alternative to refs)
```bash
agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
```
## Example: Form submission
```bash
agent-browser open https://example.com/form
agent-browser snapshot -i
# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]
agent-browser fill @e1 "user@example.com"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i # Check result
```
## Example: Authentication with saved state
```bash
# Login once
agent-browser open https://app.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"
agent-browser state save auth.json
# Later sessions: load saved state
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard
```
## Sessions (parallel browsers)
```bash
agent-browser --session test1 open site-a.com
agent-browser --session test2 open site-b.com
agent-browser session list
```
## JSON output (for parsing)
Add `--json` for machine-readable output:
```bash
agent-browser snapshot -i --json
agent-browser get text @e1 --json
```
## Debugging
```bash
agent-browser open example.com --headed # Show browser window
agent-browser console # View console messages
agent-browser errors # View page errors
```
+100 -19
View File
@@ -111,6 +111,47 @@ interface SnapshotData {
refs?: Record<string, { role: string; name?: string }>;
}
/**
* Convert Playwright errors to AI-friendly messages
*/
function toAIFriendlyError(error: unknown, selector: string): Error {
const message = error instanceof Error ? error.message : String(error);
// Handle strict mode violation (multiple elements match)
if (message.includes('strict mode violation')) {
// Extract count if available
const countMatch = message.match(/resolved to (\d+) elements/);
const count = countMatch ? countMatch[1] : 'multiple';
return new Error(
`Selector "${selector}" matched ${count} elements. ` +
`Run 'snapshot' to get updated refs, or use a more specific CSS selector.`
);
}
// Handle element not found
if (
message.includes('waiting for') &&
(message.includes('to be visible') || message.includes('Timeout'))
) {
return new Error(
`Element "${selector}" not found or not visible. ` +
`Run 'snapshot' to see current page elements.`
);
}
// Handle element not interactable
if (message.includes('intercepts pointer events') || message.includes('not visible')) {
return new Error(
`Element "${selector}" is not interactable (may be hidden or covered). ` +
`Try scrolling it into view or check if a modal/overlay is blocking it.`
);
}
// Return original error for unknown cases
return error instanceof Error ? error : new Error(message);
}
/**
* Execute a command and return a response
*/
@@ -384,11 +425,15 @@ async function handleClick(command: ClickCommand, browser: BrowserManager): Prom
// Support both refs (@e1) and regular selectors
const locator = browser.getLocator(command.selector);
await locator.click({
button: command.button,
clickCount: command.clickCount,
delay: command.delay,
});
try {
await locator.click({
button: command.button,
clickCount: command.clickCount,
delay: command.delay,
});
} catch (error) {
throw toAIFriendlyError(error, command.selector);
}
return successResponse(command.id, { clicked: true });
}
@@ -396,13 +441,17 @@ async function handleClick(command: ClickCommand, browser: BrowserManager): Prom
async function handleType(command: TypeCommand, browser: BrowserManager): Promise<Response> {
const locator = browser.getLocator(command.selector);
if (command.clear) {
await locator.fill('');
}
try {
if (command.clear) {
await locator.fill('');
}
await locator.pressSequentially(command.text, {
delay: command.delay,
});
await locator.pressSequentially(command.text, {
delay: command.delay,
});
} catch (error) {
throw toAIFriendlyError(error, command.selector);
}
return successResponse(command.id, { typed: true });
}
@@ -556,14 +605,22 @@ async function handleSelect(command: SelectCommand, browser: BrowserManager): Pr
const locator = browser.getLocator(command.selector);
const values = Array.isArray(command.values) ? command.values : [command.values];
await locator.selectOption(values);
try {
await locator.selectOption(values);
} catch (error) {
throw toAIFriendlyError(error, command.selector);
}
return successResponse(command.id, { selected: values });
}
async function handleHover(command: HoverCommand, browser: BrowserManager): Promise<Response> {
const locator = browser.getLocator(command.selector);
await locator.hover();
try {
await locator.hover();
} catch (error) {
throw toAIFriendlyError(error, command.selector);
}
return successResponse(command.id, { hovered: true });
}
@@ -643,26 +700,42 @@ async function handleWindowNew(
async function handleFill(command: FillCommand, browser: BrowserManager): Promise<Response> {
const locator = browser.getLocator(command.selector);
await locator.fill(command.value);
try {
await locator.fill(command.value);
} catch (error) {
throw toAIFriendlyError(error, command.selector);
}
return successResponse(command.id, { filled: true });
}
async function handleCheck(command: CheckCommand, browser: BrowserManager): Promise<Response> {
const locator = browser.getLocator(command.selector);
await locator.check();
try {
await locator.check();
} catch (error) {
throw toAIFriendlyError(error, command.selector);
}
return successResponse(command.id, { checked: true });
}
async function handleUncheck(command: UncheckCommand, browser: BrowserManager): Promise<Response> {
const locator = browser.getLocator(command.selector);
await locator.uncheck();
try {
await locator.uncheck();
} catch (error) {
throw toAIFriendlyError(error, command.selector);
}
return successResponse(command.id, { unchecked: true });
}
async function handleUpload(command: UploadCommand, browser: BrowserManager): Promise<Response> {
const locator = browser.getLocator(command.selector);
const files = Array.isArray(command.files) ? command.files : [command.files];
await locator.setInputFiles(files);
try {
await locator.setInputFiles(files);
} catch (error) {
throw toAIFriendlyError(error, command.selector);
}
return successResponse(command.id, { uploaded: files });
}
@@ -671,13 +744,21 @@ async function handleDoubleClick(
browser: BrowserManager
): Promise<Response> {
const locator = browser.getLocator(command.selector);
await locator.dblclick();
try {
await locator.dblclick();
} catch (error) {
throw toAIFriendlyError(error, command.selector);
}
return successResponse(command.id, { clicked: true });
}
async function handleFocus(command: FocusCommand, browser: BrowserManager): Promise<Response> {
const locator = browser.getLocator(command.selector);
await locator.focus();
try {
await locator.focus();
} catch (error) {
throw toAIFriendlyError(error, command.selector);
}
return successResponse(command.id, { focused: true });
}
+11 -3
View File
@@ -95,12 +95,20 @@ export class BrowserManager {
const page = this.getPage();
// Parse the selector and create locator
// Build locator with exact: true to avoid substring matches
let locator: Locator;
if (refData.name) {
return page.getByRole(refData.role as any, { name: refData.name });
locator = page.getByRole(refData.role as any, { name: refData.name, exact: true });
} else {
return page.getByRole(refData.role as any);
locator = page.getByRole(refData.role as any);
}
// If an nth index is stored (for disambiguation), use it
if (refData.nth !== undefined) {
locator = locator.nth(refData.nth);
}
return locator;
}
/**
+91 -3
View File
@@ -24,6 +24,8 @@ export interface RefMap {
selector: string;
role: string;
name?: string;
/** Index for disambiguation when multiple elements have same role+name */
nth?: number;
};
}
@@ -129,7 +131,7 @@ const STRUCTURAL_ROLES = new Set([
function buildSelector(role: string, name?: string): string {
if (name) {
const escapedName = name.replace(/"/g, '\\"');
return `getByRole('${role}', { name: "${escapedName}" })`;
return `getByRole('${role}', { name: "${escapedName}", exact: true })`;
}
return `getByRole('${role}')`;
}
@@ -161,12 +163,60 @@ export async function getEnhancedSnapshot(
return { tree: enhancedTree, refs };
}
/**
* Track role+name combinations to detect duplicates
*/
interface RoleNameTracker {
counts: Map<string, number>;
/** Maps role+name key to array of ref IDs that use it */
refsByKey: Map<string, string[]>;
getKey(role: string, name?: string): string;
getNextIndex(role: string, name?: string): number;
trackRef(role: string, name: string | undefined, ref: string): void;
/** Get all role+name keys that have duplicates */
getDuplicateKeys(): Set<string>;
}
function createRoleNameTracker(): RoleNameTracker {
const counts = new Map<string, number>();
const refsByKey = new Map<string, string[]>();
return {
counts,
refsByKey,
getKey(role: string, name?: string): string {
return `${role}:${name ?? ''}`;
},
getNextIndex(role: string, name?: string): number {
const key = this.getKey(role, name);
const current = counts.get(key) ?? 0;
counts.set(key, current + 1);
return current;
},
trackRef(role: string, name: string | undefined, ref: string): void {
const key = this.getKey(role, name);
const refs = refsByKey.get(key) ?? [];
refs.push(ref);
refsByKey.set(key, refs);
},
getDuplicateKeys(): Set<string> {
const duplicates = new Set<string>();
for (const [key, refs] of refsByKey) {
if (refs.length > 1) {
duplicates.add(key);
}
}
return duplicates;
},
};
}
/**
* Process ARIA snapshot: add refs and apply filters
*/
function processAriaTree(ariaTree: string, refs: RefMap, options: SnapshotOptions): string {
const lines = ariaTree.split('\n');
const result: string[] = [];
const tracker = createRoleNameTracker();
// For interactive-only mode, we collect just interactive elements
if (options.interactive) {
@@ -179,31 +229,43 @@ function processAriaTree(ariaTree: string, refs: RefMap, options: SnapshotOption
if (INTERACTIVE_ROLES.has(roleLower)) {
const ref = nextRef();
const nth = tracker.getNextIndex(roleLower, name);
tracker.trackRef(roleLower, name, ref);
refs[ref] = {
selector: buildSelector(roleLower, name),
role: roleLower,
name,
nth, // Always store nth, we'll use it for duplicates
};
let enhanced = `- ${role}`;
if (name) enhanced += ` "${name}"`;
enhanced += ` [ref=${ref}]`;
// Only show nth in output if it's > 0 (for readability)
if (nth > 0) enhanced += ` [nth=${nth}]`;
if (suffix && suffix.includes('[')) enhanced += suffix;
result.push(enhanced);
}
}
// Post-process: remove nth from refs that don't have duplicates
removeNthFromNonDuplicates(refs, tracker);
return result.join('\n') || '(no interactive elements)';
}
// Normal processing with depth/compact filters
for (const line of lines) {
const processed = processLine(line, refs, options);
const processed = processLine(line, refs, options, tracker);
if (processed !== null) {
result.push(processed);
}
}
// Post-process: remove nth from refs that don't have duplicates
removeNthFromNonDuplicates(refs, tracker);
// If compact mode, remove empty structural elements
if (options.compact) {
return compactTree(result.join('\n'));
@@ -212,6 +274,22 @@ function processAriaTree(ariaTree: string, refs: RefMap, options: SnapshotOption
return result.join('\n');
}
/**
* Remove nth from refs that ended up not having duplicates
* This keeps single-element locators simple (no unnecessary .nth(0))
*/
function removeNthFromNonDuplicates(refs: RefMap, tracker: RoleNameTracker): void {
const duplicateKeys = tracker.getDuplicateKeys();
for (const [ref, data] of Object.entries(refs)) {
const key = tracker.getKey(data.role, data.name);
if (!duplicateKeys.has(key)) {
// Not a duplicate, remove nth to keep locator simple
delete refs[ref].nth;
}
}
}
/**
* Get indentation level (number of spaces / 2)
*/
@@ -223,7 +301,12 @@ function getIndentLevel(line: string): number {
/**
* Process a single line: add ref if needed, filter if requested
*/
function processLine(line: string, refs: RefMap, options: SnapshotOptions): string | null {
function processLine(
line: string,
refs: RefMap,
options: SnapshotOptions,
tracker: RoleNameTracker
): string | null {
const depth = getIndentLevel(line);
// Check max depth
@@ -273,17 +356,22 @@ function processLine(line: string, refs: RefMap, options: SnapshotOptions): stri
if (shouldHaveRef) {
const ref = nextRef();
const nth = tracker.getNextIndex(roleLower, name);
tracker.trackRef(roleLower, name, ref);
refs[ref] = {
selector: buildSelector(roleLower, name),
role: roleLower,
name,
nth, // Always store nth, we'll clean up non-duplicates later
};
// Build enhanced line with ref
let enhanced = `${prefix}${role}`;
if (name) enhanced += ` "${name}"`;
enhanced += ` [ref=${ref}]`;
// Only show nth in output if it's > 0 (for readability)
if (nth > 0) enhanced += ` [nth=${nth}]`;
if (suffix) enhanced += suffix;
return enhanced;