opengstack 0.13.7 → 0.13.9

package/skills/browse/src/commands.ts

@@ -0,0 +1,128 @@
+/**
+ * Command registry — single source of truth for all browse commands.
+ *
+ * Dependency graph:
+ *   commands.ts ──▶ server.ts (runtime dispatch)
+ *                ──▶ gen-skill-docs.ts (doc generation)
+ *                ──▶ skill-parser.ts (validation)
+ *                ──▶ skill-check.ts (health reporting)
+ *
+ * Zero side effects. Safe to import from build scripts and tests.
+ */
+
+export const READ_COMMANDS = new Set([
+  'text', 'html', 'links', 'forms', 'accessibility',
+  'js', 'eval', 'css', 'attrs',
+  'console', 'network', 'cookies', 'storage', 'perf',
+  'dialog', 'is',
+]);
+
+export const WRITE_COMMANDS = new Set([
+  'goto', 'back', 'forward', 'reload',
+  'click', 'fill', 'select', 'hover', 'type', 'press', 'scroll', 'wait',
+  'viewport', 'cookie', 'cookie-import', 'cookie-import-browser', 'header', 'useragent',
+  'upload', 'dialog-accept', 'dialog-dismiss',
+]);
+
+export const META_COMMANDS = new Set([
+  'tabs', 'tab', 'newtab', 'closetab',
+  'status', 'stop', 'restart',
+  'screenshot', 'pdf', 'responsive',
+  'chain', 'diff',
+  'url', 'snapshot',
+  'handoff', 'resume',
+  'connect', 'disconnect', 'focus',
+  'inbox',
+  'watch',
+  'state',
+  'frame',
+]);
+
+export const ALL_COMMANDS = new Set([...READ_COMMANDS, ...WRITE_COMMANDS, ...META_COMMANDS]);
+
+export const COMMAND_DESCRIPTIONS: Record<string, { category: string; description: string; usage?: string }> = {
+  // Navigation
+  'goto':    { category: 'Navigation', description: 'Navigate to URL', usage: 'goto <url>' },
+  'back':    { category: 'Navigation', description: 'History back' },
+  'forward': { category: 'Navigation', description: 'History forward' },
+  'reload':  { category: 'Navigation', description: 'Reload page' },
+  'url':     { category: 'Navigation', description: 'Print current URL' },
+  // Reading
+  'text':    { category: 'Reading', description: 'Cleaned page text' },
+  'html':    { category: 'Reading', description: 'innerHTML of selector (throws if not found), or full page HTML if no selector given', usage: 'html [selector]' },
+  'links':   { category: 'Reading', description: 'All links as "text → href"' },
+  'forms':   { category: 'Reading', description: 'Form fields as JSON' },
+  'accessibility': { category: 'Reading', description: 'Full ARIA tree' },
+  // Inspection
+  'js':      { category: 'Inspection', description: 'Run JavaScript expression and return result as string', usage: 'js <expr>' },
+  'eval':    { category: 'Inspection', description: 'Run JavaScript from file and return result as string (path must be under /tmp or cwd)', usage: 'eval <file>' },
+  'css':     { category: 'Inspection', description: 'Computed CSS value', usage: 'css <sel> <prop>' },
+  'attrs':   { category: 'Inspection', description: 'Element attributes as JSON', usage: 'attrs <sel|@ref>' },
+  'is':      { category: 'Inspection', description: 'State check (visible/hidden/enabled/disabled/checked/editable/focused)', usage: 'is <prop> <sel>' },
+  'console': { category: 'Inspection', description: 'Console messages (--errors filters to error/warning)', usage: 'console [--clear|--errors]' },
+  'network': { category: 'Inspection', description: 'Network requests', usage: 'network [--clear]' },
+  'dialog':  { category: 'Inspection', description: 'Dialog messages', usage: 'dialog [--clear]' },
+  'cookies': { category: 'Inspection', description: 'All cookies as JSON' },
+  'storage': { category: 'Inspection', description: 'Read all localStorage + sessionStorage as JSON, or set <key> <value> to write localStorage', usage: 'storage [set k v]' },
+  'perf':    { category: 'Inspection', description: 'Page load timings' },
+  // Interaction
+  'click':   { category: 'Interaction', description: 'Click element', usage: 'click <sel>' },
+  'fill':    { category: 'Interaction', description: 'Fill input', usage: 'fill <sel> <val>' },
+  'select':  { category: 'Interaction', description: 'Select dropdown option by value, label, or visible text', usage: 'select <sel> <val>' },
+  'hover':   { category: 'Interaction', description: 'Hover element', usage: 'hover <sel>' },
+  'type':    { category: 'Interaction', description: 'Type into focused element', usage: 'type <text>' },
+  'press':   { category: 'Interaction', description: 'Press key — Enter, Tab, Escape, ArrowUp/Down/Left/Right, Backspace, Delete, Home, End, PageUp, PageDown, or modifiers like Shift+Enter', usage: 'press <key>' },
+  'scroll':  { category: 'Interaction', description: 'Scroll element into view, or scroll to page bottom if no selector', usage: 'scroll [sel]' },
+  'wait':    { category: 'Interaction', description: 'Wait for element, network idle, or page load (timeout: 15s)', usage: 'wait <sel|--networkidle|--load>' },
+  'upload':  { category: 'Interaction', description: 'Upload file(s)', usage: 'upload <sel> <file> [file2...]' },
+  'viewport':{ category: 'Interaction', description: 'Set viewport size', usage: 'viewport <WxH>' },
+  'cookie':  { category: 'Interaction', description: 'Set cookie on current page domain', usage: 'cookie <name>=<value>' },
+  'cookie-import': { category: 'Interaction', description: 'Import cookies from JSON file', usage: 'cookie-import <json>' },
+  'cookie-import-browser': { category: 'Interaction', description: 'Import cookies from installed Chromium browsers (opens picker, or use --domain for direct import)', usage: 'cookie-import-browser [browser] [--domain d]' },
+  'header':  { category: 'Interaction', description: 'Set custom request header (colon-separated, sensitive values auto-redacted)', usage: 'header <name>:<value>' },
+  'useragent': { category: 'Interaction', description: 'Set user agent', usage: 'useragent <string>' },
+  'dialog-accept': { category: 'Interaction', description: 'Auto-accept next alert/confirm/prompt. Optional text is sent as the prompt response', usage: 'dialog-accept [text]' },
+  'dialog-dismiss': { category: 'Interaction', description: 'Auto-dismiss next dialog' },
+  // Visual
+  'screenshot': { category: 'Visual', description: 'Save screenshot (supports element crop via CSS/@ref, --clip region, --viewport)', usage: 'screenshot [--viewport] [--clip x,y,w,h] [selector|@ref] [path]' },
+  'pdf':     { category: 'Visual', description: 'Save as PDF', usage: 'pdf [path]' },
+  'responsive': { category: 'Visual', description: 'Screenshots at mobile (375x812), tablet (768x1024), desktop (1280x720). Saves as {prefix}-mobile.png etc.', usage: 'responsive [prefix]' },
+  'diff':    { category: 'Visual', description: 'Text diff between pages', usage: 'diff <url1> <url2>' },
+  // Tabs
+  'tabs':    { category: 'Tabs', description: 'List open tabs' },
+  'tab':     { category: 'Tabs', description: 'Switch to tab', usage: 'tab <id>' },
+  'newtab':  { category: 'Tabs', description: 'Open new tab', usage: 'newtab [url]' },
+  'closetab':{ category: 'Tabs', description: 'Close tab', usage: 'closetab [id]' },
+  // Server
+  'status':  { category: 'Server', description: 'Health check' },
+  'stop':    { category: 'Server', description: 'Shutdown server' },
+  'restart': { category: 'Server', description: 'Restart server' },
+  // Meta
+  'snapshot':{ category: 'Snapshot', description: 'Accessibility tree with @e refs for element selection. Flags: -i interactive only, -c compact, -d N depth limit, -s sel scope, -D diff vs previous, -a annotated screenshot, -o path output, -C cursor-interactive @c refs', usage: 'snapshot [flags]' },
+  'chain':   { category: 'Meta', description: 'Run commands from JSON stdin. Format: [["cmd","arg1",...],...]' },
+  // Handoff
+  'handoff': { category: 'Server', description: 'Open visible Chrome at current page for user takeover', usage: 'handoff [message]' },
+  'resume':  { category: 'Server', description: 'Re-snapshot after user takeover, return control to AI', usage: 'resume' },
+  // Headed mode
+  'connect': { category: 'Server', description: 'Launch headed Chromium with Chrome extension', usage: 'connect' },
+  'disconnect': { category: 'Server', description: 'Disconnect headed browser, return to headless mode' },
+  'focus':   { category: 'Server', description: 'Bring headed browser window to foreground (macOS)', usage: 'focus [@ref]' },
+  // Inbox
+  'inbox':   { category: 'Meta', description: 'List messages from sidebar scout inbox', usage: 'inbox [--clear]' },
+  // Watch
+  'watch':   { category: 'Meta', description: 'Passive observation — periodic snapshots while user browses', usage: 'watch [stop]' },
+  // State
+  'state':   { category: 'Server', description: 'Save/load browser state (cookies + URLs)', usage: 'state save|load <name>' },
+  // Frame
+  'frame':   { category: 'Meta', description: 'Switch to iframe context (or main to return)', usage: 'frame <sel|@ref|--name n|--url pattern|main>' },
+};
+
+// Load-time validation: descriptions must cover exactly the command sets
+const allCmds = new Set([...READ_COMMANDS, ...WRITE_COMMANDS, ...META_COMMANDS]);
+const descKeys = new Set(Object.keys(COMMAND_DESCRIPTIONS));
+for (const cmd of allCmds) {
+  if (!descKeys.has(cmd)) throw new Error(`COMMAND_DESCRIPTIONS missing entry for: ${cmd}`);
+}
+for (const key of descKeys) {
+  if (!allCmds.has(key)) throw new Error(`COMMAND_DESCRIPTIONS has unknown command: ${key}`);
+}

package/skills/browse/src/config.ts

@@ -0,0 +1,150 @@
+/**
+ * Shared config for browse CLI + server.
+ *
+ * Resolution:
+ *   1. BROWSE_STATE_FILE env → derive stateDir from parent
+ *   2. git rev-parse --show-toplevel → projectDir/.gstack/
+ *   3. process.cwd() fallback (non-git environments)
+ *
+ * The CLI computes the config and passes BROWSE_STATE_FILE to the
+ * spawned server. The server derives all paths from that env var.
+ */
+
+import * as fs from 'fs';
+import * as path from 'path';
+
+export interface BrowseConfig {
+  projectDir: string;
+  stateDir: string;
+  stateFile: string;
+  consoleLog: string;
+  networkLog: string;
+  dialogLog: string;
+}
+
+/**
+ * Detect the git repository root, or null if not in a repo / git unavailable.
+ */
+export function getGitRoot(): string | null {
+  try {
+    const proc = Bun.spawnSync(['git', 'rev-parse', '--show-toplevel'], {
+      stdout: 'pipe',
+      stderr: 'pipe',
+      timeout: 2_000, // Don't hang if .git is broken
+    });
+    if (proc.exitCode !== 0) return null;
+    return proc.stdout.toString().trim() || null;
+  } catch {
+    return null;
+  }
+}
+
+/**
+ * Resolve all browse config paths.
+ *
+ * If BROWSE_STATE_FILE is set (e.g. by CLI when spawning server, or by
+ * tests for isolation), all paths are derived from it. Otherwise, the
+ * project root is detected via git or cwd.
+ */
+export function resolveConfig(
+  env: Record<string, string | undefined> = process.env,
+): BrowseConfig {
+  let stateFile: string;
+  let stateDir: string;
+  let projectDir: string;
+
+  if (env.BROWSE_STATE_FILE) {
+    stateFile = env.BROWSE_STATE_FILE;
+    stateDir = path.dirname(stateFile);
+    projectDir = path.dirname(stateDir); // parent of .gstack/
+  } else {
+    projectDir = getGitRoot() || process.cwd();
+    stateDir = path.join(projectDir, '.gstack');
+    stateFile = path.join(stateDir, 'browse.json');
+  }
+
+  return {
+    projectDir,
+    stateDir,
+    stateFile,
+    consoleLog: path.join(stateDir, 'browse-console.log'),
+    networkLog: path.join(stateDir, 'browse-network.log'),
+    dialogLog: path.join(stateDir, 'browse-dialog.log'),
+  };
+}
+
+/**
+ * Create the .gstack/ state directory if it doesn't exist.
+ * Throws with a clear message on permission errors.
+ */
+export function ensureStateDir(config: BrowseConfig): void {
+  try {
+    fs.mkdirSync(config.stateDir, { recursive: true });
+  } catch (err: any) {
+    if (err.code === 'EACCES') {
+      throw new Error(`Cannot create state directory ${config.stateDir}: permission denied`);
+    }
+    if (err.code === 'ENOTDIR') {
+      throw new Error(`Cannot create state directory ${config.stateDir}: a file exists at that path`);
+    }
+    throw err;
+  }
+
+  // Ensure .gstack/ is in the project's .gitignore
+  const gitignorePath = path.join(config.projectDir, '.gitignore');
+  try {
+    const content = fs.readFileSync(gitignorePath, 'utf-8');
+    if (!content.match(/^\.gstack\/?$/m)) {
+      const separator = content.endsWith('\n') ? '' : '\n';
+      fs.appendFileSync(gitignorePath, `${separator}.gstack/\n`);
+    }
+  } catch (err: any) {
+    if (err.code !== 'ENOENT') {
+      // Write warning to server log (visible even in daemon mode)
+      const logPath = path.join(config.stateDir, 'browse-server.log');
+      try {
+        fs.appendFileSync(logPath, `[${new Date().toISOString()}] Warning: could not update .gitignore at ${gitignorePath}: ${err.message}\n`);
+      } catch {
+        // stateDir write failed too — nothing more we can do
+      }
+    }
+    // ENOENT (no .gitignore) — skip silently
+  }
+}
+
+/**
+ * Derive a slug from the git remote origin URL (owner-repo format).
+ * Falls back to the directory basename if no remote is configured.
+ */
+export function getRemoteSlug(): string {
+  try {
+    const proc = Bun.spawnSync(['git', 'remote', 'get-url', 'origin'], {
+      stdout: 'pipe',
+      stderr: 'pipe',
+      timeout: 2_000,
+    });
+    if (proc.exitCode !== 0) throw new Error('no remote');
+    const url = proc.stdout.toString().trim();
+    // SSH:   git@github.com:owner/repo.git → owner-repo
+    // HTTPS: https://github.com/owner/repo.git → owner-repo
+    const match = url.match(/[:/]([^/]+)\/([^/]+?)(?:\.git)?$/);
+    if (match) return `${match[1]}-${match[2]}`;
+    throw new Error('unparseable');
+  } catch {
+    const root = getGitRoot();
+    return path.basename(root || process.cwd());
+  }
+}
+
+/**
+ * Read the binary version (git SHA) from browse/dist/.version.
+ * Returns null if the file doesn't exist or can't be read.
+ */
+export function readVersionHash(execPath: string = process.execPath): string | null {
+  try {
+    const versionFile = path.resolve(path.dirname(execPath), '.version');
+    return fs.readFileSync(versionFile, 'utf-8').trim() || null;
+  } catch {
+    return null;
+  }
+}