Add AutoGLM-OS agent (#309)

* autoglm-os initialize * clean code * chore: use proxy for download setup * feat(autoglm-os): add parameter to toggle images * fix: use temporary directory for files pulled from the vm to prevent potential collision when running multiple instances of the same task in parallel * update * add client_password * update multienv * fix * fix prompt * fix prompt * fix prompt * fix sys prompt * feat: use proxy in file evaluator * fix client_password * fix note_prompt * fix autoglm agent cmd type * fix * revert: fix: use temporary directory for files pulled from the vm to prevent potential collision when running multiple instances of the same task in parallel reverts commit bab5473eea1de0e61b0e1d68b23ce324a5b0ee57 * feat(autoglm): setup tools * fix(autoglm): remove second time of get a11y tree * add osworld server restart * Revert "add osworld server restart" This reverts commit 7bd9d84122e246ce2a26de0e49c25494244c2b3d. * fix _launch_setup * fix autoglm agent tools & xml tree * fix desktop_env * fix bug for tool name capitalization * fix: always use proxy for setup download * add fail after exceeding max turns * fix(autoglm): avoid adding image to message when screenshot is empty * fix maximize_window * fix maximize_window * fix maximize_window * fix import browsertools module bug * fix task proxy config bug * restore setup * refactor desktop env * restore image in provider * restore file.py * refactor desktop_env * quick fix * refactor desktop_env.step * fix our env reset * add max truns constraint * clean run script * clean lib_run_single.py --------- Co-authored-by: hanyullai <hanyullai@outlook.com> Co-authored-by: JingBh <jingbohao@yeah.net>
2025-08-17 12:08:40 +08:00
parent c833d03a4b
commit aa05f6cc26
26 changed files with 8657 additions and 23 deletions
--- a/mm_agents/autoglm/tools/package/google_chrome.py
+++ b/mm_agents/autoglm/tools/package/google_chrome.py
@@ -0,0 +1,107 @@
+class BrowserTools:
+    ret = ""
+
+    @classmethod
+    def print_result(cls):
+        print(cls.ret)
+
+    @classmethod
+    def env_info(cls):
+        cls.ret = "None"
+
+    # @classmethod
+    # def show_all_tabs(cls):
+    #     cls.ret = "Browser not found"
+    #     for attempt in range(3):
+    #         with sync_playwright() as p:
+    #             try:
+    #                 browser = p.chromium.connect_over_cdp(cls.remote_debugging_url)
+    #                 if not browser:
+    #                     continue
+    #                 context = browser.contexts[0]
+    #                 # 获取所有窗口名称
+    #                 cls.ret = 'Browser Tabs: '
+    #                 for idx, page in enumerate(context.pages):
+    #                     cls.ret += f"{idx}. {page.title()} ({page.url})" + '\n'
+    #                 return cls.ret
+    #             except TimeoutError:
+    #                 cls.ret = 'Failed to get browser tabs'
+    #                 return None
+    #     return None
+
+    @classmethod
+    def open_profile_settings(cls):
+        """
+        Open the profile settings page in the browser.
+        """
+        return {"action_type": "OPEN_CHROME_TAB", "parameters": {"urls_to_open": ["chrome://settings/people"]}}
+
+    @classmethod
+    def open_password_settings(cls):
+        """
+        Open the password settings page in the browser.
+        """
+        return {"action_type": "OPEN_CHROME_TAB", "parameters": {"urls_to_open": ["chrome://settings/autofill"]}}
+
+    @classmethod
+    def open_privacy_settings(cls):
+        """
+        Open the privacy settings page in the browser.
+        """
+        return {"action_type": "OPEN_CHROME_TAB", "parameters": {"urls_to_open": ["chrome://settings/privacy"]}}
+
+    @classmethod
+    def open_appearance_settings(cls):
+        """
+        Open the appearance settings page in the browser.
+        """
+        return {"action_type": "OPEN_CHROME_TAB", "parameters": {"urls_to_open": ["chrome://settings/appearance"]}}
+
+    @classmethod
+    def open_search_engine_settings(cls):
+        """
+        Open the search engine settings page in the browser.
+        """
+        return {"action_type": "OPEN_CHROME_TAB", "parameters": {"urls_to_open": ["chrome://settings/search"]}}
+
+    @classmethod
+    def bring_back_last_tab(cls):
+        """
+        Bring back the last tab in the browser.
+        """
+        return f"import pyautogui; pyautogui.hotkey('ctrl', 'shift', 't'); print('Brought back last tab')"
+
+    @classmethod
+    def print(cls):
+        """
+        Open the print option in current page.
+        """
+        return f"import pyautogui; pyautogui.hotkey('ctrl', 'p'); print('Opened print option')"
+
+    @classmethod
+    def delete_browsing_data(cls):
+        """
+        Delete browsing data in the browser.
+        """
+        return f"import pyautogui; pyautogui.hotkey('ctrl', 'shift', 'del'); print('Deleted browsing data')"
+
+    @classmethod
+    def open_extensions(cls):
+        """
+        open the extensions page in the browser.
+        """
+        return {"action_type": "OPEN_CHROME_TAB", "parameters": {"urls_to_open": ["chrome://extensions"]}}
+
+    @classmethod
+    def bookmark_page(cls):
+        """
+        Bookmark the current page in the browser.
+        """
+        return f"import pyautogui; pyautogui.hotkey('ctrl', 'd'); print('Bookmarked page')"
+
+    @classmethod
+    def open_bookmarks(cls):
+        """
+        Open the bookmarks page in the browser.
+        """
+        return {"action_type": "OPEN_CHROME_TAB", "parameters": {"urls_to_open": ["chrome://bookmarks"]}}