fix hdc input issues（issues 270+288+312）

phone_agent/actions/handler.py

@@ -41,6 +41,8 @@ def __init__(
         self.device_id = device_id
         self.confirmation_callback = confirmation_callback or self._default_confirmation
         self.takeover_callback = takeover_callback or self._default_takeover
+        # Track last tap coordinates for passing to type_text (used by HDC)
+        self._last_tap_coords: tuple[int, int] | None = None
 
     def execute(
         self, action: dict[str, Any], screen_width: int, screen_height: int
@@ -135,6 +137,9 @@ def _handle_tap(self, action: dict, width: int, height: int) -> ActionResult:
 
         x, y = self._convert_relative_to_absolute(element, width, height)
 
+        # Store tap coordinates for potential use in subsequent Type action
+        self._last_tap_coords = (x, y)
+
         # Check for sensitive operation
         if "message" in action:
             if not self.confirmation_callback(action["message"]):
@@ -162,8 +167,12 @@ def _handle_type(self, action: dict, width: int, height: int) -> ActionResult:
         device_factory.clear_text(self.device_id)
         time.sleep(TIMING_CONFIG.action.text_clear_delay)
 
-        # Handle multiline text by splitting on newlines
-        device_factory.type_text(text, self.device_id)
+        # Type text with last tap coordinates if available (for HDC)
+        if self._last_tap_coords:
+            x, y = self._last_tap_coords
+            device_factory.type_text(text, self.device_id, x, y)
+        else:
+            device_factory.type_text(text, self.device_id)
         time.sleep(TIMING_CONFIG.action.text_input_delay)
 
         # Restore original keyboard
@@ -396,4 +405,4 @@ def do(**kwargs) -> dict[str, Any]:
 def finish(**kwargs) -> dict[str, Any]:
     """Helper function for creating 'finish' actions."""
     kwargs["_metadata"] = "finish"
-    return kwargs
+    return kwargs

phone_agent/device_factory.py

@@ -105,9 +105,15 @@ def launch_app(
         """Launch an app."""
         return self.module.launch_app(app_name, device_id, delay)
 
-    def type_text(self, text: str, device_id: str | None = None):
-        """Type text."""
-        return self.module.type_text(text, device_id)
+    def type_text(self, text: str, device_id: str | None = None, x: int | None = None, y: int | None = None):
+        """Type text with optional coordinates for HDC."""
+        import inspect
+        sig = inspect.signature(self.module.type_text)
+        # Check if the module supports x, y parameters (HDC does, ADB/iOS don't)
+        if 'x' in sig.parameters and 'y' in sig.parameters:
+            return self.module.type_text(text, device_id, x, y)
+        else:
+            return self.module.type_text(text, device_id)
 
     def clear_text(self, device_id: str | None = None):
         """Clear text."""
@@ -164,4 +170,4 @@ def get_device_factory() -> DeviceFactory:
     global _device_factory
     if _device_factory is None:
         _device_factory = DeviceFactory(DeviceType.ADB)  # Default to ADB
-    return _device_factory
+    return _device_factory

phone_agent/hdc/input.py

@@ -7,23 +7,29 @@
 from phone_agent.hdc.connection import _run_hdc_command
 
 
-def type_text(text: str, device_id: str | None = None) -> None:
+def type_text(text: str, device_id: str | None = None, x: int | None = None, y: int | None = None) -> None:
     """
     Type text into the currently focused input field.
 
     Args:
         text: The text to type. Supports multi-line text with newline characters.
         device_id: Optional HDC device ID for multi-device setups.
+        x: Optional X coordinate of the input field (recommended for HarmonyOS).
+        y: Optional Y coordinate of the input field (recommended for HarmonyOS).
 
     Note:
-        HarmonyOS uses: hdc shell uitest uiInput text "文本内容"
-        This command works without coordinates when input field is focused.
+        HarmonyOS command format:
+        - With coordinates: hdc shell uitest uiInput inputText X Y "文本内容"
+        - Without coordinates: hdc shell uitest uiInput text "文本内容" (may not work reliably)
         For multi-line text, the function splits by newlines and sends ENTER keyEvents.
         ENTER key code in HarmonyOS: 2054
-        Recommendation: Click on the input field first to focus it, then use this function.
+        Recommendation: Click on the input field first to focus it, then use this function with coordinates.
     """
     hdc_prefix = _get_hdc_prefix(device_id)
 
+    # Determine which command to use
+    use_input_text = x is not None and y is not None
+
     # Handle multi-line text by splitting on newlines
     if '\n' in text:
         lines = text.split('\n')
@@ -32,11 +38,18 @@ def type_text(text: str, device_id: str | None = None) -> None:
                 # Escape special characters for shell
                 escaped_line = line.replace('"', '\\"').replace("$", "\\$")
 
-                _run_hdc_command(
-                    hdc_prefix + ["shell", "uitest", "uiInput", "text", escaped_line],
-                    capture_output=True,
-                    text=True,
-                )
+                if use_input_text:
+                    _run_hdc_command(
+                        hdc_prefix + ["shell", "uitest", "uiInput", "inputText", str(x), str(y), escaped_line],
+                        capture_output=True,
+                        text=True,
+                    )
+                else:
+                    _run_hdc_command(
+                        hdc_prefix + ["shell", "uitest", "uiInput", "text", escaped_line],
+                        capture_output=True,
+                        text=True,
+                    )
 
             # Send ENTER key event after each line except the last one
             if i < len(lines) - 1:
@@ -49,18 +62,26 @@ def type_text(text: str, device_id: str | None = None) -> None:
                 except Exception as e:
                     print(f"[HDC] ENTER keyEvent failed: {e}")
     else:
-        # Single line text - original logic
+        # Single line text
         # Escape special characters for shell (keep quotes for proper text handling)
-        # The text will be wrapped in quotes in the command
         escaped_text = text.replace('"', '\\"').replace("$", "\\$")
 
-        # HarmonyOS uitest uiInput text command
-        # Format: hdc shell uitest uiInput text "文本内容"
-        _run_hdc_command(
-            hdc_prefix + ["shell", "uitest", "uiInput", "text", escaped_text],
-            capture_output=True,
-            text=True,
-        )
+        if use_input_text:
+            # HarmonyOS uitest uiInput inputText command with coordinates
+            # Format: hdc shell uitest uiInput inputText X Y "文本内容"
+            _run_hdc_command(
+                hdc_prefix + ["shell", "uitest", "uiInput", "inputText", str(x), str(y), escaped_text],
+                capture_output=True,
+                text=True,
+            )
+        else:
+            # HarmonyOS uitest uiInput text command (fallback)
+            # Format: hdc shell uitest uiInput text "文本内容"
+            _run_hdc_command(
+                hdc_prefix + ["shell", "uitest", "uiInput", "text", escaped_text],
+                capture_output=True,
+                text=True,
+            )
 
 
 def clear_text(device_id: str | None = None) -> None:
@@ -146,4 +167,4 @@ def _get_hdc_prefix(device_id: str | None) -> list:
     """Get HDC command prefix with optional device specifier."""
     if device_id:
         return ["hdc", "-t", device_id]
-    return ["hdc"]
+    return ["hdc"]