fix: dedup text content in snapshot (#909)

* fix: dedup text content in snapshot

* fix: format

---------

Co-authored-by: 羲洋 <lipengyang.lpy@alibaba-inc.com>

cli/src/native/e2e_tests.rs

@@ -2210,3 +2210,66 @@ async fn e2e_snapshot_cursor_many_elements() {
     let resp = execute_command(&json!({ "id": "99", "action": "close" }), &mut state).await;
     assert_success(&resp);
 }
+
+/// Test that InlineTextBox nodes are filtered from snapshot output while preserving
+/// the actual text content from parent elements.
+#[tokio::test]
+#[ignore]
+async fn e2e_snapshot_inline_text_box_filtered() {
+    let mut state = DaemonState::new();
+
+    let resp = execute_command(
+        &json!({ "id": "1", "action": "launch", "headless": true }),
+        &mut state,
+    )
+    .await;
+    assert_success(&resp);
+
+    // Simple HTML with text content that would generate InlineTextBox nodes
+    let html =
+        "data:text/html,<html><body><div><span>Hello</span> <span>World</span></div></body></html>";
+
+    let resp = execute_command(
+        &json!({ "id": "2", "action": "navigate", "url": html }),
+        &mut state,
+    )
+    .await;
+    assert_success(&resp);
+
+    // Take snapshot to capture full output and verify InlineTextBox filtering
+    let start = std::time::Instant::now();
+    let resp = execute_command(&json!({ "id": "3", "action": "snapshot" }), &mut state).await;
+    assert_success(&resp);
+    let elapsed = start.elapsed();
+
+    let snapshot_output = get_data(&resp)["snapshot"].as_str().unwrap();
+
+    // Verify that InlineTextBox does not appear in the output
+    assert!(
+        !snapshot_output.contains("InlineTextBox"),
+        "Snapshot output should not contain InlineTextBox: {}",
+        snapshot_output
+    );
+
+    // Verify that the actual text content is preserved
+    assert!(
+        snapshot_output.contains("Hello"),
+        "Snapshot should contain 'Hello': {}",
+        snapshot_output
+    );
+    assert!(
+        snapshot_output.contains("World"),
+        "Snapshot should contain 'World': {}",
+        snapshot_output
+    );
+
+    // Must complete quickly
+    assert!(
+        elapsed.as_secs() < 5,
+        "snapshot with InlineTextBox filtering took {:?}, expected < 5s",
+        elapsed,
+    );
+
+    let resp = execute_command(&json!({ "id": "99", "action": "close" }), &mut state).await;
+    assert_success(&resp);
+}

cli/src/native/snapshot.rs

@@ -712,7 +712,7 @@ fn build_tree(nodes: &[AXNode]) -> (Vec<TreeNode>, Vec<usize>) {
         let (level, checked, expanded, selected, disabled, required) =
             extract_properties(&node.properties);
 
-        if node.ignored.unwrap_or(false) && role != "RootWebArea" {
+        if (node.ignored.unwrap_or(false) && role != "RootWebArea") || role == "InlineTextBox" {
             tree_nodes.push(TreeNode {
                 role: String::new(),
                 name: String::new(),