fix(html-extract): optimize the logic for extracting HTML content to …

…improve extraction accuracy (#62)

* chore: optimize extract logic

* chore: fix word type error

* chore: optimize build error

* chore: optimize generate test data

* chore: optimize generate test data

packages/midscene/src/ai-model/automation/planning.ts

@@ -32,7 +32,7 @@ export function systemPromptToTaskPlanning() {
   1. The actions you composed MUST be based on the page context information you get. Instead of making up actions that are not related to the page context.
   2. In most cases, you should Locate one element first, then do other actions on it. For example, alway Find one element, then hover on it. But if you think it's necessary to do other actions first (like global scroll, global key press), you can do that.
 
-  If the planned tasks are sequential and tasks may appear only after the execution of previous tasks, this is considered normal. If any errors occur during task planning (such as the page content being irrelevant to the task or the mentioned element not existing), please return the error message with an explanation in the errors field. Thoughts, prompts, and error messages should all be in the same language as the user query.
+  If the planned tasks are sequential and tasks may appear only after the execution of previous tasks, this is considered normal. Thoughts, prompts, and error messages should all be in the same language as the user query.
   
   Return in the following JSON format:
   {

packages/midscene/tests/ai/automation/__snapshots__/planning.test.ts.snap

@@ -1,29 +1,5 @@
 // Vitest Snapshot v1, https://vitest.dev/guide/snapshot.html
 
-exports[`automation - planning > basic run 1`] = `
-{
-  "timeMs": 3500,
-}
-`;
-
-exports[`automation - planning > basic run 2`] = `
-{
-  "value": "Enter",
-}
-`;
-
-exports[`automation - planning coze > basic run 1`] = `
-{
-  "timeMs": 3500,
-}
-`;
-
-exports[`automation - planning coze > basic run 2`] = `
-{
-  "value": "Enter",
-}
-`;
-
 exports[`automation - planning openAI > basic run 1`] = `
 {
   "timeMs": 3500,

packages/midscene/tests/ai/extract/__snapshots__/extract.test.ts.snap

@@ -1,38 +1,5 @@
 // Vitest Snapshot v1, https://vitest.dev/guide/snapshot.html
 
-exports[`assert coze > todo 1`] = `
-{
-  "data": [
-    "Learn Python",
-    "Learn Rust",
-    "Learn AI",
-  ],
-  "errors": [],
-  "language": "en",
-}
-`;
-
-exports[`assert coze > todo obj 1`] = `
-{
-  "data": [
-    {
-      "checked": false,
-      "text": "Learn Python",
-    },
-    {
-      "checked": false,
-      "text": "Learn Rust",
-    },
-    {
-      "checked": false,
-      "text": "Learn AI",
-    },
-  ],
-  "errors": [],
-  "language": "en",
-}
-`;
-
 exports[`assert openAI > online order 1`] = `
 {
   "data": [

packages/midscene/tests/ai/inspector/__snapshots__/online_order_inspector.test.ts.snap

@@ -12,7 +12,7 @@
   {
     "elements": [
       {
-        "id": "ba59909699",
+        "id": "e666c51ff8",
         "indexId": "2",
       },
     ],
@@ -46,11 +46,11 @@
   {
     "elements": [
       {
-        "id": "580cfae23c",
+        "id": "fadfa10182",
         "indexId": "23",
       },
       {
-        "id": "925c254744",
+        "id": "001617dbf8",
         "indexId": "29",
       },
     ],

packages/midscene/tests/ai/inspector/__snapshots__/todo_inspector.test.ts.snap

@@ -12,7 +12,7 @@
   {
     "elements": [
       {
-        "id": "b5bacc879a",
+        "id": "e477ad490a",
         "indexId": "8",
       },
     ],
@@ -42,7 +42,7 @@
   {
     "elements": [
       {
-        "id": "0f8f471e06",
+        "id": "284ba7f2b3",
         "indexId": "15",
       },
     ],