chromeflow 0.1.35 → 0.1.37

package/CLAUDE.md

@@ -43,6 +43,7 @@ Do NOT ask "should I open the browser?" — just do it. The user expects seamles
         get_page_text() or wait_for_selector(".success") — ALWAYS confirm after click; click_element returns after 600ms regardless of outcome
         fill_form([{label, value}, ...])    — fill multiple fields in one call; prefer over repeated fill_input
         fill_input("Product name", "Pro")   — fill a single field (works on React, CodeMirror, and contenteditable)
+        set_file_input("Upload", "/abs/path/to/file.zip") — upload a file to a file input (even hidden inputs)
         clear_overlays()                    — call this immediately after fill_input/fill_form succeeds
         scroll_to_element("label text")     — jump directly to a known field; prefer this over scroll_page when the target is known
         scroll_page("down")                 — reveal off-screen content when target location is unknown
@@ -102,8 +103,8 @@ use `take_and_copy_screenshot()` — it saves a PNG to ~/Downloads and copies it
   `get_elements()` when you need pixel coordinates of visible elements; use `get_form_fields()`
   when you need to understand the full structure of a form including fields below the fold.
 - `get_form_fields()` includes `[type=file]` fields even when they are visually hidden behind
-  custom drag-and-drop zones. File fields are marked "manual only" — highlight them and ask
-  the user to select the file; they cannot be filled programmatically.
+  custom drag-and-drop zones. Use `set_file_input(hint, filePath)` to upload a file — provide
+  the label/hint text and the absolute path to the file on disk.
 - For forms with multiple fields, use `fill_form([{label, value}, ...])` to fill them all
   in a single call. It returns a per-field success/failure report so you can immediately see
   which fields weren't found. Use `fill_input` only for a single field.

package/README.md

@@ -1,13 +1,13 @@
 # Chromeflow
 
-Browser guidance for Claude Code. When Claude needs you to set up Stripe, grab API keys, configure a third-party service, or do anything in a browser — Chromeflow takes over. It highlights what to click, fills in fields it knows, clicks buttons automatically, and writes captured values straight to your `.env`.
+Browser guidance for Claude Code. When Claude needs you to set up Stripe, grab API keys, configure a third-party service, or do anything in a browser — Chromeflow takes over. It highlights what to click, fills in fields it knows, clicks buttons automatically, uploads files, and writes captured values straight to your `.env`.
 
 ## How it works
 
 Chromeflow is two things that work together:
 
-- **MCP server** — gives Claude Code a set of browser tools (`open_page`, `click_element`, `fill_input`, `read_element`, `write_to_env`, etc.)
-- **Chrome extension** — receives those commands and acts on the active tab (highlights, clicks, fills, captures screenshots)
+- **MCP server** — gives Claude Code a set of browser tools (`open_page`, `click_element`, `fill_form`, `set_file_input`, `read_element`, `write_to_env`, etc.)
+- **Chrome extension** — receives those commands and acts on the active tab (highlights, clicks, fills, uploads files, captures screenshots)
 
 Claude drives the flow. You only touch the browser for things that genuinely need you — login, passwords, payment details, personal choices.
 
@@ -49,6 +49,40 @@ Just ask Claude normally:
 
 Claude will navigate, highlight steps, click what it can, pause for anything sensitive, and write values to your `.env` automatically.
 
+## What Claude can do
+
+| Capability | Tools |
+|------------|-------|
+| Navigate pages, open new tabs | `open_page`, `list_tabs`, `switch_to_tab` |
+| Click buttons and links | `click_element` |
+| Fill single fields | `fill_input` |
+| Fill multiple fields in one call | `fill_form` |
+| Upload files (even hidden inputs) | `set_file_input` |
+| Read page content as text | `get_page_text` |
+| Inspect all form fields | `get_form_fields` |
+| Scroll to a known element | `scroll_to_element` |
+| Highlight elements for the user | `highlight_region`, `find_and_highlight` |
+| Wait for the user to click | `wait_for_click` |
+| Wait for async changes | `wait_for_selector` |
+| Run arbitrary JS | `execute_script` |
+| Capture credentials to `.env` | `read_element`, `write_to_env` |
+| Screenshot (element location only) | `take_screenshot` |
+| Screenshot + save + copy to clipboard | `take_and_copy_screenshot` |
+| Save/restore form state across tabs | `save_page_state`, `restore_page_state` |
+| Show a step-by-step guide panel | `show_guide_panel`, `mark_step_done` |
+
+### File uploads
+
+`set_file_input` uses Chrome DevTools Protocol to bypass the browser's file-input script restriction — the same mechanism used by Playwright and Puppeteer. It works even when the `<input type=file>` is hidden behind a custom drag-and-drop zone.
+
+```
+set_file_input("Upload", "/Users/you/Downloads/task.zip")
+```
+
+### Dedicated Claude window
+
+Click the Chromeflow extension icon and use **"Use this window for Claude"** to lock Claude's browser operations to a specific Chrome window. This lets you freely use other Chrome windows without Claude interfering.
+
 ## Adding to another project
 
 Run setup from the new project's directory — the MCP server is already registered globally, this just drops `CLAUDE.md` and tool permissions into the project:

package/dist/setup.js

@@ -167,7 +167,9 @@ const CHROMEFLOW_TOOLS = [
   // v0.1.25+
   "take_and_copy_screenshot",
   // v0.1.32+
-  "fill_form"
+  "fill_form",
+  // v0.1.36+
+  "set_file_input"
 ].map((t) => `mcp__chromeflow__${t}`);
 function patchSettingsLocalJson(cwd) {
   const claudeDir = join(cwd, ".claude");

package/dist/tools/browser.js

@@ -169,6 +169,25 @@ ${lines.join("\n")}${r.warning ?? ""}` }]
       };
     }
   );
+  server.tool(
+    "set_file_input",
+    `Upload a file to a file input field. Works even when the input is visually hidden behind a custom drag-and-drop zone.
+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.`,
+    {
+      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)")
+    },
+    async ({ hint, file_path }) => {
+      const response = await bridge.request({ type: "set_file_input", hint, filePath: file_path });
+      const r = response;
+      return {
+        content: [{ type: "text", text: r.message ?? (r.success ? "File set successfully" : "Failed to set file") }]
+      };
+    }
+  );
   server.tool(
     "execute_script",
     `Execute JavaScript in the current page's context and return the result as a string.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "chromeflow",
-  "version": "0.1.35",
+  "version": "0.1.37",
   "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": {