feat : better form handling

sources/agents/code_agent.py

@@ -1,3 +1,4 @@
+import platform, os
 
 from sources.utility import pretty_print, animate_thinking
 from sources.agents.agent import Agent, executorResult
@@ -20,6 +21,7 @@ class CoderAgent(Agent):
             "go": GoInterpreter(),
             "file_finder": FileFinder()
         }
+        self.work_dir = self.tools["file_finder"].get_work_dir()
         self.role = {
             "en": "code",
             "fr": "codage",
@@ -27,10 +29,20 @@ class CoderAgent(Agent):
         }
         self.type = "code_agent"
 
+    
+    def add_sys_info_prompt(self, prompt):
+        """Add system information to the prompt."""
+        info = f"System Info:\n" \
+               f"OS: {platform.system()} {platform.release()}\n" \
+               f"Python Version: {platform.python_version()}\n" \
+               f"\nYou must work in directory: {self.work_dir}"
+        return f"{prompt}\n\n{info}"
+
     def process(self, prompt, speech_module) -> str:
         answer = ""
         attempt = 0
-        max_attempts = 3
+        max_attempts = 4
+        prompt = self.add_sys_info_prompt(prompt)
         self.memory.push('user', prompt)
         clarify_trigger = "REQUEST_CLARIFICATION"
 

sources/browser.py

@@ -268,7 +268,7 @@ class Browser:
         except Exception as e:
             raise e
 
-    def find_all_inputs(self, timeout=4):
+    def find_all_inputs(self, timeout=3):
         WebDriverWait(self.driver, timeout).until(
             EC.presence_of_element_located((By.TAG_NAME, "body"))
         )
@@ -291,14 +291,17 @@ class Browser:
                     continue
                 input_name = element["text"] or element["id"] or input_type
                 if input_type == "checkbox" or input_type == "radio":
+                    try:
                         checked_status = "checked" if element.is_selected() else "unchecked"
+                    except Exception as e:
+                        continue
                     form_strings.append(f"[{input_name}]({checked_status})")
                 else:
                     form_strings.append(f"[{input_name}]("")")
             return form_strings
 
         except Exception as e:
-            return [f"Error extracting form inputs."]
+            raise e
 
     def get_buttons_xpath(self) -> List[str]:
         """
@@ -312,13 +315,14 @@ class Browser:
                 continue
             text = (button.text or button.get_attribute("value") or "").lower().replace(' ', '')
             xpath = f"(//button | //input[@type='submit'])[{i + 1}]"
-            if "login" in text or "sign" in text or "register":
             result.append((text, xpath))
         result.sort(key=lambda x: len(x[0]))
         return result
 
     def find_and_click_submission(self, timeout: int = 10) -> bool:
-        possible_submissions = ["login", "submit", "register"]
+        possible_submissions = ["login", "submit", "register", "calculate", "login", "submit", "register", "calculate", "save", "send",
+                                "continue", "apply", "ok", "confirm", "next", "proceed", "accept", "agree", "yes", "no", "cancel",
+                                "close", "done", "finish", "start", "calculate"]
         for submission in possible_submissions:
             if self.find_and_click_btn(submission, timeout):
                 return True
@@ -392,6 +396,7 @@ class Browser:
                         element.click()
                         self.logger.info(f"Set {name} to {value}")
                 else:
+                    element.clear()
                     element.send_keys(value)
                     self.logger.info(f"Filled {name} with {value}")
             return True
@@ -443,13 +448,12 @@ if __name__ == "__main__":
     browser = Browser(driver, anticaptcha_manual_install=True)
     time.sleep(10)
     
-    print("AntiCaptcha Test")
+    print("AntiCaptcha / Form Test")
     browser.go_to("https://www.google.com/recaptcha/api2/demo")
+    #browser.go_to("https://practicetestautomation.com/practice-test-login/")
     time.sleep(10)
-    print("Form Test:")
-    browser.go_to("https://practicetestautomation.com/practice-test-login/")
     inputs = browser.get_form_inputs()
-    inputs = ['[username](student)', f'[password](Password123)', '[appOtp]()', '[backupOtp]()']
+    inputs = ['[input1](Martin)', f'[input2](Test)', '[input3](test@gmail.com)']
     browser.fill_form_inputs(inputs)
     browser.find_and_click_submission()
     time.sleep(30)