2.3A Complete ReAct Test Using the CLI

Here is how an agent thinks through a login test using the ReAct loop:

TEST OBJECTIVE: Verify that submitting the login form with empty fields
shows appropriate validation errors.

STEP 1 — OBSERVE:
  $ playwright-cli open "https://app.example.com/login"
  $ playwright-cli snapshot
  → reads snapshot: textbox "Email" [ref=e8], textbox "Password" [ref=e9],
    button "Sign In" [ref=e11]

STEP 2 — THINK:
  "I see a login form with email and password fields and a Sign In button.
   My objective is to test empty field submission. I should click Sign In
   without filling in any fields."

STEP 3 — ACT:
  $ playwright-cli click e11

STEP 4 — OBSERVE:
  $ playwright-cli snapshot
  → reads snapshot: alert "Email is required" [ref=e15],
    alert "Password is required" [ref=e16], textbox "Email" [ref=e8] ...

STEP 5 — THINK:
  "Two validation errors appeared: one for email and one for password.
   Both say the field is required. This matches expected behavior.
   Let me also verify we stayed on the login page (no navigation)."

STEP 6 — OBSERVE:
  $ playwright-cli eval "location.href"
  → "https://app.example.com/login"

STEP 7 — THINK:
  "URL has not changed. We are still on the login page. Both required
   field errors are shown. Test objective is met."

STEP 8 — EVALUATE:
  DONE pass "Empty form submission correctly shows validation errors
  for both email ('Email is required') and password ('Password is required').
  Page did not navigate away from /login."