fix(eval): replMode so successive evals can re-declare let/const; snapshot-first skill rule (#37, #38)

#38: `chrome-use eval` now runs with Runtime.evaluate replMode (like the DevTools
console) — top-level `let`/`const` no longer throw "already been declared" across
successive evals (independent `eval` steps in a `test` suite collided in the
page's shared lexical scope), and top-level await is allowed. Main-world and
completion-value semantics are unchanged.

#37: core skill gains a hard rule — snapshot-first, never screenshot+coordinates
to locate form fields/buttons; `snapshot -i` now pierces cross-origin iframes and
lists their elements by @ref; screenshots are for visual checks only, and a
full-page retina screenshot often exceeds an image reader's limits.

cli/Cargo.lock

@@ -290,7 +290,7 @@ checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
 
 [[package]]
 name = "chrome-use"
-version = "1.5.12"
+version = "1.5.13"
 dependencies = [
  "aes",
  "aes-gcm",

cli/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "chrome-use"
-version = "1.5.12"
+version = "1.5.13"
 edition = "2021"
 description = "Fast browser automation CLI for AI agents"
 license = "Apache-2.0"

cli/src/native/browser.rs

@@ -1202,15 +1202,23 @@ impl BrowserManager {
     pub async fn evaluate(&self, script: &str, _args: Option<Value>) -> Result<Value, String> {
         let session_id = self.active_session_id()?.to_string();
 
+        // `replMode: true` matches the DevTools console: top-level `let`/`const`
+        // can be re-declared across successive `eval`s instead of throwing
+        // "Identifier 'x' has already been declared" (issue #38 — independent
+        // `eval` steps in a test suite collided in the page's shared lexical
+        // scope), and top-level `await` is allowed. Completion-value and
+        // main-world semantics are unchanged. Built as raw params so the other
+        // ~28 EvaluateParams literals don't all need a new field.
         let result: EvaluateResult = self
             .client
             .send_command_typed(
                 "Runtime.evaluate",
-                &EvaluateParams {
-                    expression: script.to_string(),
-                    return_by_value: Some(true),
-                    await_promise: Some(true),
-                },
+                &json!({
+                    "expression": script,
+                    "returnByValue": true,
+                    "awaitPromise": true,
+                    "replMode": true,
+                }),
                 Some(&session_id),
             )
             .await?;

skill-data/core/SKILL.md

@@ -36,6 +36,17 @@ Refs (`@e1`, `@e2`, ...) are assigned fresh on every snapshot. They become
 submits, dynamic re-renders, dialog opens. Always re-snapshot before your
 next ref interaction.
 
+> **Hard rule: snapshot-first, never screenshot-to-locate.** For form fields and
+> buttons, ALWAYS `snapshot -i` and act on refs/selectors. Do **not** reach for
+> `screenshot` + coordinate clicks to find or hit an element — `snapshot -i` now
+> pierces **cross-origin iframes** (embedded Google Payments / Stripe / checkout /
+> KYC forms) and lists their elements by `@ref`, including input values. Use
+> coordinates only for canvas/WebGL, or when `snapshot` genuinely returns nothing
+> for your target. Screenshots are for *visual verification you report*, never the
+> agent's own input — and a full-page `screenshot` of a real retina browser is
+> often too large for an image reader anyway. (If you ever feel you *need* a
+> screenshot to read state or locate something, that's a bug — please file it.)
+
 > **Snapshot-first, always. Never default to `screenshot` + coordinate clicking
 > for form fields or buttons.** Run `snapshot -i` and act on `@refs`. Use
 > coordinates only for canvas/WebGL, or when `snapshot` genuinely returns nothing