Report what the GenXEvo agent currently is: whether it is configured, which workspace roots it may read, what its security policy is, which Node runtime is hosting the server, whether test execution is permitted, and exactly which capabilities this build provides versus which are planned for a later phase. Call this FIRST in any session, and again whenever a capability behaves unexpectedly. Note that the Node runtime reported here runs GenXEvo itself and is usually NOT the runtime the automation project's tests run on — use genxevo_discover_project for that. Returns the GenXEvo ToolResult envelope: branch on the 'status' field, never on the prose in 'summary'. Read-only, takes no arguments, and always safe to repeat.

Scan the configured workspace and report the JavaScript automation project that is actually there: every package.json with its name, type, engines, packageManager field, scripts and declared dependencies; which lockfiles exist and therefore which package manager the project really uses; the test runner the project itself states it uses (mocha, jest, vitest, node:test or WebdriverIO, or 'unknown' — never assumed); the test roots, established from the runner's own configuration or from files matching a test-file shape rather than from any folder being called 'test'; the module system; the pinned Node version and where the pin came from; the browser automation library in use, distinguishing selenium-webdriver from WebdriverIO and from Playwright; candidate page-object directories, identified because their modules import a browser library and are not test files; and what is actually INSTALLED, read from node_modules/.package-lock.json, which is often not what the project declares. Every conclusion carries the signals that produced it and an explicit confidence level, so you can tell a fact from a guess. GenXEvo NEVER imports, evaluates, installs or runs anything in the project — wdio.conf.js, jest.config.js and their kind are executable JavaScript and are read as text only, and node_modules is never walked. Call this before reasoning about any test, locator or run. Read-only, takes no arguments, and always safe to repeat. If 'status' is 'partialSuccess' the scan hit a limit or could not read something, and 'not found' may mean 'not looked at'.