chromeflow 0.1.37 → 0.1.38

package/CLAUDE.md

@@ -140,6 +140,9 @@ screenshot to check what happened.
 2. `get_elements()` to get exact coords → `highlight_region(x,y,w,h,msg)`
 3. `take_screenshot()` only if you still can't identify the element from DOM queries
 
+**Multiple elements with the same label** (e.g. many "Remove" buttons):
+`click_element("Remove", nth=3)` — use `nth` (1-based) to target the specific one by order top-to-bottom. Check `get_form_fields` or `get_page_text` first to determine which index corresponds to the right section.
+
 **`fill_input` not found:**
 1. `click_element(hint)` to focus the field, then retry `fill_input`
 2. `find_and_highlight(hint, "Click here — I'll fill it in")` (no `valueToType`) then
@@ -173,6 +176,13 @@ for (var i = 0; i < allEls.length; i++) {
 controls[N].textContent.trim(); // should show selected value
 ```
 
+**Page text with large embedded content** (e.g. uploaded log files previewed inline): full-page `get_page_text()` pagination becomes unwieldy. Scope to a specific section instead:
+```
+get_page_text(selector=".section-3")   — scope to a CSS selector
+get_page_text(selector="#upload-form") — scope to an id
+```
+Use `execute_script("document.querySelectorAll('section').length")` to find structural selectors first.
+
 **Page content rendered as images** (e.g. qualification "Examples" tabs that show PNG screenshots
 instead of DOM text): `get_page_text()` returns nothing useful. Zoom out and screenshot instead:
 

package/dist/tools/browser.js

@@ -122,7 +122,8 @@ save_to controls where the PNG is saved: "downloads" (default) saves to ~/Downlo
     `Get the exact pixel positions of all visible interactive elements on the page (inputs, buttons, links, selects).
 Use this INSTEAD OF take_screenshot when you need coordinates for highlight_region \u2014 the coordinates are exact DOM values, not estimates.
 Returns a numbered list with element type, label, and precise x/y/width/height in CSS pixels.
-After calling this, use those exact coordinates in highlight_region \u2014 do NOT adjust them.`,
+IMPORTANT: x/y are VIEWPORT-relative (0,0 = top-left of the visible area). Use these exact values directly in highlight_region \u2014 do not add window.scrollY.
+Use get_form_fields instead if you need document y positions or fields below the fold.`,
     {},
     async () => {
       const response = await bridge.request({ type: "get_elements" });
@@ -175,7 +176,7 @@ ${lines.join("\n")}${r.warning ?? ""}` }]
 Uses Chrome DevTools Protocol to set the file \u2014 the only way to bypass the browser's file-input script restriction.
 hint: label text or name of the file input (or empty string to target the first file input on the page).
 file_path: absolute path to the file on the local filesystem (e.g. /Users/you/Downloads/task.zip).
-After calling this, call get_page_text to confirm the file was accepted.`,
+After calling this, verify the upload was accepted: use execute_script to check that the input's files.length > 0, or use get_page_text to look for a success indicator (e.g. a Remove button appearing). If not accepted, call set_file_input again \u2014 occasional React timing issues may require a retry.`,
     {
       hint: z.string().describe("Label text, name, or surrounding text of the file input. Use empty string to target the first file input on the page."),
       file_path: z.string().describe("Absolute path to the file to upload (e.g. /Users/you/Downloads/task.zip)")

package/dist/tools/flow.js

@@ -17,14 +17,16 @@ function registerFlowTools(server, bridge) {
     `Click a button, link, or interactive element on the page by its visible text or aria-label.
 Use this whenever Claude can press a button without needing user input \u2014 e.g. "Save", "Continue", "Create product", "Add pricing", "Confirm", "Next".
 After clicking, use get_page_text to check the result \u2014 only use take_screenshot if you need pixel positions.
-Do NOT use for: elements that require the user to make a personal choice, consent to terms, or enter sensitive data.`,
+Do NOT use for: elements that require the user to make a personal choice, consent to terms, or enter sensitive data.
+When multiple elements share the same label (e.g. many "Remove" buttons), use nth to target a specific one (1 = first/topmost, 2 = second, etc.).`,
     {
       textHint: z.string().describe(
         "The visible label of the button or link (e.g. 'Save product', 'Continue', 'Add a product', 'Create')"
-      )
+      ),
+      nth: z.number().int().min(1).optional().describe("Which match to click when multiple elements share the same label (1 = first/topmost, default 1)")
     },
-    async ({ textHint }) => {
-      const response = await bridge.request({ type: "click_element", textHint });
+    async ({ textHint, nth }) => {
+      const response = await bridge.request({ type: "click_element", textHint, nth });
       const r = response;
       if (!r.success) {
         return {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "chromeflow",
-  "version": "0.1.37",
+  "version": "0.1.38",
   "description": "Browser guidance MCP server for Claude Code — highlights, clicks, fills, and captures from the web so you don't have to.",
   "type": "module",
   "bin": {