diff --git a/src/langbot/libs/qq_official_api/api.py b/src/langbot/libs/qq_official_api/api.py
index 69ab414a8..0ba1917d9 100644
--- a/src/langbot/libs/qq_official_api/api.py
+++ b/src/langbot/libs/qq_official_api/api.py
@@ -693,7 +693,7 @@ class QQOfficialClient:
         target_type: str,
         target_id: str,
         markdown_content: str,
-        keyboard: dict,
+        keyboard: Optional[dict] = None,
         msg_id: Optional[str] = None,
         event_id: Optional[str] = None,
         msg_seq: int = 1,
@@ -734,9 +734,10 @@ class QQOfficialClient:
         body: dict[str, Any] = {
             'msg_type': 2,
             'markdown': {'content': markdown_content},
-            'keyboard': keyboard,
             'msg_seq': msg_seq,
         }
+        if keyboard and keyboard.get('content', {}).get('rows'):
+            body['keyboard'] = keyboard
         if msg_id:
             body['msg_id'] = msg_id
         if event_id:
diff --git a/src/langbot/libs/wecom_ai_bot_api/api.py b/src/langbot/libs/wecom_ai_bot_api/api.py
index 60a3f45ba..4bbe30222 100644
--- a/src/langbot/libs/wecom_ai_bot_api/api.py
+++ b/src/langbot/libs/wecom_ai_bot_api/api.py
@@ -1129,12 +1129,10 @@ def build_button_interaction_payload(
     input_hint_lines = _wecom_input_hint_lines(form_data)
     if input_hint_lines:
         sub_title_parts.append('Fill these fields in chat before choosing an action:\n' + '\n'.join(input_hint_lines))
-    elif should_show_actions and actions:
-        sub_title_parts.append('Choose an action to continue.')
     if overflow:
         extra_lines = [f'  - {a.get("title") or a.get("id") or ""} (回复 id: {a.get("id") or ""})' for a in overflow]
         sub_title_parts.append(f'另有 {len(overflow)} 个选项不在按钮列表中，可直接回复 id：\n' + '\n'.join(extra_lines))
-    sub_title_text = '\n\n'.join(sub_title_parts) or '请选择一个操作以继续。'
+    sub_title_text = '\n\n'.join(sub_title_parts)
 
     button_list = []
     for idx, action in enumerate(visible_actions):
@@ -1452,8 +1450,8 @@ def build_button_interaction_update_card(
         }
         if action_key == clean_action_id:
             button['style'] = _wecom_button_style(action, selected=True)
-            button['text'] = f'已选择：{button_title}'
-            button['replace_text'] = f'已选择：{button_title}'
+            button['text'] = f'✅ {button_title}'
+            button['replace_text'] = f'✅ {button_title}'
             matched = True
         button_list.append(button)
 
@@ -1463,7 +1461,7 @@ def build_button_interaction_update_card(
                 'text': action_title or clean_action_id,
                 'style': 1,
                 'key': clean_action_id,
-                'replace_text': f'已选择：{action_title or clean_action_id}',
+                'replace_text': f'✅ {action_title or clean_action_id}',
             }
         )
 
diff --git a/src/langbot/pkg/platform/sources/dingtalk.py b/src/langbot/pkg/platform/sources/dingtalk.py
index e412cf0ae..7e7a7e16a 100644
--- a/src/langbot/pkg/platform/sources/dingtalk.py
+++ b/src/langbot/pkg/platform/sources/dingtalk.py
@@ -296,14 +296,8 @@ def _dingtalk_completed_input_lines(form_data: dict) -> list[str]:
         value = inputs.get(field_name)
         if value in (None, '', []):
             continue
-        field_type = _dingtalk_field_type(field)
         display_value = _dingtalk_display_input_value(field, value)
-        if field_type == 'select':
-            lines.append(f'✅ 已选择 {field_name}：{display_value}')
-        elif field_type in {'file', 'file-list'}:
-            lines.append(f'✅ 已上传 {field_name}：{display_value}')
-        else:
-            lines.append(f'✅ 已填写 {field_name}：{display_value}')
+        lines.append(f'✅ {field_name}：{display_value}')
     return lines
 
 
@@ -960,9 +954,7 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         input_hint_lines = [] if native_field else _dingtalk_input_hint_lines(form_data)
         if input_hint_lines:
             parts.append('Fill these fields in chat before choosing an action:<br>' + '<br>'.join(input_hint_lines))
-        elif should_show_actions and actions:
-            parts.append('Choose an action to continue.')
-        display_content = '<br><br>'.join(parts) or '请选择一个操作以继续。'
+        display_content = '<br><br>'.join(parts)
 
         try:
             await self.bot.update_card_data(
@@ -1062,9 +1054,7 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         input_hint_lines = [] if native_field else _dingtalk_input_hint_lines(form_data)
         if input_hint_lines:
             parts.append('Fill these fields in chat before choosing an action:<br>' + '<br>'.join(input_hint_lines))
-        elif should_show_actions and actions:
-            parts.append('Choose an action to continue.')
-        display_content = '<br><br>'.join(parts) or '请选择一个操作以继续。'
+        display_content = '<br><br>'.join(parts)
 
         btns = self._build_btns(actions if should_show_actions else [], out_track_id)
 
@@ -1100,7 +1090,7 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         """Create a new card for resumed-workflow streaming output.
 
         Used after a button click triggers a synthetic event — the form
-        card stays put with the "已选择" notice, and a fresh card is
+        card stays put with the selection notice, and a fresh card is
         spawned here for the LLM reply to stream into.
         """
         form_template_id = (self.config.get('human_input_card_template_id') or '').strip()
@@ -1349,7 +1339,7 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                 return
 
         # Visual feedback on the form card itself: keep the prompt visible,
-        # add a "已选择" line, remove the buttons. The resumed-workflow
+        # add a selection line, remove the buttons. The resumed-workflow
         # output lives on a separate new card (lazy-created in
         # reply_message_chunk on the synthetic event), so the form card
         # stays put as a record of the user's selection.
@@ -1367,7 +1357,7 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         # Crucial: do NOT leave the form card's out_track_id in
         # active_turn_card — otherwise create_message_card for the
         # synthetic event would reuse it for the resume output, painting
-        # the LLM reply on top of the "已选择" notice. Clear it so the
+        # the LLM reply on top of the selection notice. Clear it so the
         # resume goes through the lazy-create path and spawns a fresh card.
         session_key = state.get('session_key', '')
         if session_key and self.active_turn_card.get(session_key) == out_track_id:
@@ -1487,7 +1477,7 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
     ) -> None:
         """Update the form card to acknowledge the user's selection.
 
-        Keeps the original prompt visible, adds a "已选择: X" notice, and
+        Keeps the original prompt visible, adds a selection notice, and
         clears the buttons. The card stays as a permanent record of the
         choice; the resumed workflow's output goes to a separate new card.
         """
@@ -1504,7 +1494,7 @@ class DingTalkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         )
         if completed_lines and not all(line in form_content for line in completed_lines):
             parts.append('<hr>' + '<br>'.join(completed_lines))
-        parts.append(f'<hr>✅ 已选择：**{action_title}**')
+        parts.append(f'<hr>✅ {action_title}')
         content = '<br><br>'.join(parts)
         if self.ap is not None:
             self.ap.logger.info(f'DingTalk _mark_card_resolved: out_track_id={out_track_id} action={action_title!r}')
diff --git a/src/langbot/pkg/platform/sources/discord.py b/src/langbot/pkg/platform/sources/discord.py
index 9613e9bcc..3cb13a251 100644
--- a/src/langbot/pkg/platform/sources/discord.py
+++ b/src/langbot/pkg/platform/sources/discord.py
@@ -1396,7 +1396,6 @@ class DiscordAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         body_parts: list[str] = []
         if form_content:
             body_parts.append(form_content)
-        body_parts.append('Please select an option below:')
         embed_body = '\n\n'.join(body_parts)
         # Discord embed.description has a 4096 char limit — defensive trim.
         if len(embed_body) > 4000:
@@ -1589,7 +1588,7 @@ class DiscordAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         stale: bool = False,
     ) -> None:
         """Disable all buttons on the form view and annotate the chosen
-        one — mirrors DingTalk/Lark's in-card 已选择 feedback."""
+        one — mirrors DingTalk/Lark's in-card selection feedback."""
         try:
             for child in view.children:
                 if not isinstance(child, discord_ui.Button):
diff --git a/src/langbot/pkg/platform/sources/lark.py b/src/langbot/pkg/platform/sources/lark.py
index e100bab9f..23dcfd90c 100644
--- a/src/langbot/pkg/platform/sources/lark.py
+++ b/src/langbot/pkg/platform/sources/lark.py
@@ -187,13 +187,7 @@ def _lark_completed_input_lines(form_data: dict) -> list[str]:
         if value in (None, '', []):
             continue
         display_value = _lark_display_input_value(field, value)
-        field_type = _dify_field_type(field)
-        if field_type == 'select':
-            lines.append(f'✅ 已选择 {field_name}：**{display_value}**')
-        elif field_type in {'file', 'file-list'}:
-            lines.append(f'✅ 已上传 {field_name}：**{display_value}**')
-        else:
-            lines.append(f'✅ 已填写 {field_name}：**{display_value}**')
+        lines.append(f'✅ {field_name}：{display_value}')
     return lines
 
 
@@ -2014,7 +2008,7 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
 
         Supports Dify form-action resume:  when the runner yields a chunk with
         ``_resume_from_form=True``, the card transitions from buttons to a
-        grey "已选择" notice and a new ``streaming_txt_resume`` element is added
+        grey selection notice and a new ``streaming_txt_resume`` element is added
         for subsequent resume chunks to stream into.
 
         When ``_open_new_card=True`` on the final chunk, the existing card is
@@ -2051,7 +2045,7 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             )
             if completed_lines and not all(line in stored_form_content for line in completed_lines):
                 notice_parts.append('---\n' + '\n'.join(completed_lines))
-            notice_parts.append(f'---\n✅ 已选择：**{action_title}**')
+            notice_parts.append(f'---\n✅ {action_title}')
             selected_notice = '\n\n'.join(notice_parts)
         else:
             selected_notice = ''
@@ -2379,7 +2373,7 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         """Update the entire card layout.
 
         • form_data → show interactive buttons (initial Dify pause)
-        • notice_text → replace buttons with a grey "已选择" notice (resume transition)
+        • notice_text → replace buttons with a grey selection notice (resume transition)
         • resume_placeholder_text → add a streaming_txt_resume markdown element
         """
         form_data = form_data or {}
diff --git a/src/langbot/pkg/platform/sources/qqofficial.py b/src/langbot/pkg/platform/sources/qqofficial.py
index f5923bf1c..3369391e8 100644
--- a/src/langbot/pkg/platform/sources/qqofficial.py
+++ b/src/langbot/pkg/platform/sources/qqofficial.py
@@ -842,51 +842,22 @@ class QQOfficialAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter
         form_content = form_data.get('form_content') or ''
         is_field_step = bool(form_data.get('_current_input_field')) and not form_data.get('_action_select_only')
         parts = [f'### {node_title}']
+        plain_parts = [node_title]
         if form_content.strip():
             parts.append(form_content.strip())
-        parts.append('请点击下方按钮选择：')
+            plain_parts.append(form_content.strip())
         markdown_content = '\n\n'.join(parts)
+        plain_content = '\n\n'.join(plain_parts)
 
         keyboard = build_keyboard_from_select_field(form_data) if is_field_step else None
-        if is_field_step and not keyboard.get('content', {}).get('rows'):
-            field_parts = parts[:-1] if len(parts) > 1 else parts
-            text_msg = platform_message.MessageChain([platform_message.Plain(text='\n\n'.join(field_parts))])
-            try:
-                await self.reply_message(message_source, text_msg)
-            except Exception:
-                await self.logger.error(f'QQ Official: field-step text send failed: {traceback.format_exc()}')
-                return
-
-            sender_id = ''
-            if source is not None:
-                sender_id = (
-                    getattr(source, 'user_openid', None)
-                    or getattr(source, 'member_openid', None)
-                    or getattr(source, 'd_author_id', None)
-                    or ''
-                )
-            if not sender_id and message_source.sender is not None:
-                sender_id = str(getattr(message_source.sender, 'id', '') or '')
-            self._pending_forms[session_key] = {
-                'form_data': form_data,
-                'msg_id': msg_id,
-                'sender_id': sender_id,
-                'target_type': target_type,
-                'target_id': target_id,
-                'source_event_t': source.t if source is not None else None,
-                'posted_at': time.time(),
-            }
-            await self.logger.info(
-                f'QQ Official: form field step posted session={session_key} '
-                f'field={form_data.get("_current_input_field")!r}'
-            )
-            return
-
-        if keyboard is None:
+        is_text_field_step = is_field_step and not keyboard.get('content', {}).get('rows')
+        if is_text_field_step:
+            keyboard = None
+        if keyboard is None and not is_text_field_step:
             keyboard = build_keyboard_from_form(form_data, buttons_per_row=2)
-        if not keyboard.get('content', {}).get('rows'):
+        if keyboard is not None and not keyboard.get('content', {}).get('rows') and not is_text_field_step:
             # No actions to render — fall back to plain text.
-            text_msg = platform_message.MessageChain([platform_message.Plain(text=markdown_content)])
+            text_msg = platform_message.MessageChain([platform_message.Plain(text=plain_content)])
             try:
                 await self.reply_message(message_source, text_msg)
             except Exception:
@@ -935,7 +906,7 @@ class QQOfficialAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter
             await self.logger.error(
                 f'QQ Official: send_markdown_keyboard failed, falling back to text: {traceback.format_exc()}'
             )
-            text_msg = platform_message.MessageChain([platform_message.Plain(text=markdown_content)])
+            text_msg = platform_message.MessageChain([platform_message.Plain(text=plain_content)])
             try:
                 await self.reply_message(message_source, text_msg)
             except Exception:
diff --git a/src/langbot/pkg/platform/sources/telegram.py b/src/langbot/pkg/platform/sources/telegram.py
index afb583674..62d5ee49c 100644
--- a/src/langbot/pkg/platform/sources/telegram.py
+++ b/src/langbot/pkg/platform/sources/telegram.py
@@ -304,7 +304,7 @@ class TelegramAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                     action_title = self._form_action_titles[query.data]
                     try:
                         original_text = query.message.text or ''
-                        selected_text = f'{original_text}\n\n✅ Selected: {action_title}'
+                        selected_text = f'{original_text}\n\n✅ {action_title}'
                         await query.edit_message_text(text=selected_text, reply_markup=None)
                     except Exception:
                         # If edit fails (e.g. message too long), just pass
@@ -687,15 +687,10 @@ class TelegramAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         effective_message = update.effective_message
         message_thread_id = getattr(effective_message, 'message_thread_id', None) if effective_message else None
 
-        if is_select_field:
-            prompt = f'Please select {select_field}:'
-        elif is_field_step:
-            prompt = f'Please reply with a value for {current_field}.'
-        else:
-            prompt = 'Please select an action:'
-        text_lines = [f'[{node_title}] {prompt}']
+        heading = f'[{node_title}]'
+        text_lines = [heading]
         if form_content:
-            text_lines.insert(0, form_content)
+            text_lines.append(form_content)
 
         if oversized:
             # callback_data exceeds Telegram's 64-byte limit — fall back to
@@ -722,7 +717,7 @@ class TelegramAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                 # prompts even when they cannot read ordinary group messages.
                 'reply_markup': ForceReply(
                     selective=False,
-                    input_field_placeholder=f'Enter {current_field}',
+                    input_field_placeholder=current_field,
                 ),
             }
         else:
diff --git a/tests/unit_tests/platform/test_dingtalk_adapter.py b/tests/unit_tests/platform/test_dingtalk_adapter.py
index 0850eab08..bf51cf55a 100644
--- a/tests/unit_tests/platform/test_dingtalk_adapter.py
+++ b/tests/unit_tests/platform/test_dingtalk_adapter.py
@@ -93,7 +93,7 @@ def test_dingtalk_completed_input_lines_include_text_and_select_values():
         }
     )
 
-    assert lines == ['✅ 已填写 comment：looks good', '✅ 已选择 choice：B']
+    assert lines == ['✅ comment：looks good', '✅ choice：B']
 
 
 def test_dingtalk_clean_form_content_uses_all_input_defs():
diff --git a/tests/unit_tests/platform/test_lark_adapter.py b/tests/unit_tests/platform/test_lark_adapter.py
index 933d27cf0..59b91ee60 100644
--- a/tests/unit_tests/platform/test_lark_adapter.py
+++ b/tests/unit_tests/platform/test_lark_adapter.py
@@ -109,9 +109,9 @@ def test_lark_completed_input_lines_include_text_select_and_files():
     )
 
     assert lines == [
-        '✅ 已填写 us_input：**你好**',
-        '✅ 已选择 xiala：**or**',
-        '✅ 已上传 files：**2 file(s)**',
+        '✅ us_input：你好',
+        '✅ xiala：or',
+        '✅ files：2 file(s)',
     ]
 
 
@@ -193,4 +193,4 @@ def test_lark_completed_input_lines_display_select_value_from_object():
         }
     )
 
-    assert lines == ['✅ 已选择 xiala：**B**']
+    assert lines == ['✅ xiala：B']
diff --git a/tests/unit_tests/platform/test_qqofficial_api.py b/tests/unit_tests/platform/test_qqofficial_api.py
index db86a2483..0f791f612 100644
--- a/tests/unit_tests/platform/test_qqofficial_api.py
+++ b/tests/unit_tests/platform/test_qqofficial_api.py
@@ -75,6 +75,7 @@ def _stream_test_adapter():
     adapter.logger = AsyncMock()
     adapter.bot = MagicMock()
     adapter.bot.send_stream_msg = AsyncMock(return_value={'id': 'stream-1'})
+    adapter.bot.send_markdown_keyboard = AsyncMock(return_value={'id': 'message-1'})
     adapter.ap = None
     adapter._stream_ctx = {}
     adapter._stream_ctx_ts = {}
@@ -142,6 +143,36 @@ async def test_qq_non_streaming_fallback_keeps_latest_snapshot_only():
     assert str(sent_chain) == 'Hello'
 
 
+@pytest.mark.asyncio
+async def test_qq_text_field_prompt_keeps_form_content():
+    from langbot.pkg.platform.sources.qqofficial import QQOfficialAdapter
+
+    adapter = _stream_test_adapter()
+    adapter._pending_forms = {}
+    adapter._session_event_ids = {}
+    adapter._anchor_msg_seq = {}
+    source = MagicMock()
+    source.d_id = 'source-1'
+    source.t = 'C2C_MESSAGE_CREATE'
+    event = MagicMock()
+    event.source_platform_object = source
+    event.sender.id = 'user-1'
+    form_data = {
+        '_current_input_field': 'us_input',
+        'node_title': 'Manual input',
+        'form_content': '1234\nEnter your question',
+        'input_defs': [{'output_variable_name': 'us_input', 'type': 'paragraph'}],
+        'actions': [{'id': 'yes', 'title': 'yes'}],
+    }
+
+    with patch.object(QQOfficialAdapter, '_resolve_target_from_event', return_value=('c2c', 'user-1')):
+        await adapter._handle_form_chunk(event, platform_message.MessageChain([]), form_data)
+
+    send_call = adapter.bot.send_markdown_keyboard.await_args.kwargs
+    assert send_call['markdown_content'] == '### Manual input\n\n1234\nEnter your question'
+    assert send_call['keyboard'] is None
+
+
 @pytest.mark.asyncio
 async def test_qq_select_click_enqueues_input_progress_query():
     import langbot.pkg.core.app  # noqa: F401
diff --git a/tests/unit_tests/platform/test_telegram_adapter.py b/tests/unit_tests/platform/test_telegram_adapter.py
index 247d51b16..f3308f16e 100644
--- a/tests/unit_tests/platform/test_telegram_adapter.py
+++ b/tests/unit_tests/platform/test_telegram_adapter.py
@@ -116,5 +116,8 @@ async def test_telegram_text_field_does_not_show_action_buttons():
     args = bot.send_message.await_args.kwargs
     assert isinstance(args['reply_markup'], ForceReply)
     assert args['reply_markup'].selective is False
-    assert 'Please reply with a value for us_input.' in args['text']
+    assert args['reply_markup'].input_field_placeholder == 'us_input'
+    assert 'Please reply' not in args['text']
+    assert args['text'].startswith('[人工介入]')
+    assert 'us_input (paragraph)' in args['text']
     assert adapter._form_action_titles == {}
diff --git a/tests/unit_tests/platform/test_wecombot_template_card.py b/tests/unit_tests/platform/test_wecombot_template_card.py
index 7bdb387ca..0fc650aa2 100644
--- a/tests/unit_tests/platform/test_wecombot_template_card.py
+++ b/tests/unit_tests/platform/test_wecombot_template_card.py
@@ -81,10 +81,10 @@ def test_build_button_interaction_update_card_marks_clicked_button():
     assert card['sub_title_text'] == 'Please choose one action.'
     assert card['button_list'][0] == {'text': 'Approve', 'style': 2, 'key': 'approve'}
     assert card['button_list'][1] == {
-        'text': '已选择：Reject',
+        'text': '✅ Reject',
         'style': 1,
         'key': 'reject',
-        'replace_text': '已选择：Reject',
+        'replace_text': '✅ Reject',
     }
     assert card['source'] == {'desc': 'LangBot'}