feat: add prompt startup actions and shared vision config

frontend/src/components/workflow/panels/AgentNodePanel.tsx

@@ -1,7 +1,6 @@
 "use client";
 
 import {
-  Camera,
   Bot,
   Brain,
   Database,
@@ -12,12 +11,9 @@ import {
   Wrench,
 } from "lucide-react";
 
-import {
-  ResourceSelectField,
-  ToggleRow,
-} from "@/components/assistant-editor/editor-controls";
 import { KnowledgeRetrievalConfigDialog } from "@/components/editor/knowledge-retrieval-config-dialog";
 import { SectionCard } from "@/components/editor/section-card";
+import { VisionConfigSection } from "@/components/editor/vision-config-section";
 import { TurnConfigEditor } from "@/components/turn-config-editor";
 import { Input } from "@/components/ui/input";
 import { Switch } from "@/components/ui/switch";
@@ -235,48 +231,23 @@ export function AgentNodePanel({
             />
           </SectionCard>
 
-          <SectionCard
-            icon={<Camera size={15} />}
-            title="视觉理解"
+          <VisionConfigSection
             description="配置当前 Agent 是否可以按需理解用户摄像头画面"
-          >
-            <ToggleRow
-              title="允许理解当前画面"
-              hint="开启后，该 Agent 会获得读取当前视频画面的工具。选择「模型自己」时，当前大语言模型必须支持图片输入。"
-              checked={Boolean(draft.visionEnabled)}
-              onChange={(visionEnabled) =>
-                setPatch({
-                  visionEnabled,
-                  ...(!visionEnabled
-                    ? { visionModelResourceId: "" }
-                    : {}),
-                })
-              }
-            />
-            {draft.visionEnabled && (
-              <>
-                <ResourceSelectField
-                  label="视觉模型"
-                  value={draft.visionModelResourceId ?? ""}
-                  onChange={(visionModelResourceId) =>
-                    set("visionModelResourceId", visionModelResourceId)
-                  }
-                  options={visionOptions.filter(
-                    (option) => option.value !== draft.llmResourceId,
-                  )}
-                  noneLabel="模型自己"
-                />
-                {!draft.visionModelResourceId &&
-                  !visionOptions.some(
-                    (option) => option.value === draft.llmResourceId,
-                  ) && (
-                    <p className="text-xs text-destructive">
-                      当前大语言模型未标记支持图片输入，请选择独立视觉模型。
-                    </p>
-                  )}
-              </>
-            )}
-          </SectionCard>
+            hint="开启后，该 Agent 会获得读取当前视频画面的工具。选择「模型自己」时，当前大语言模型必须支持图片输入。"
+            enabled={Boolean(draft.visionEnabled)}
+            modelResourceId={draft.visionModelResourceId ?? ""}
+            mainModelResourceId={(draft.llmResourceId as string) || ""}
+            modelOptions={visionOptions}
+            onEnabledChange={(visionEnabled) =>
+              setPatch({
+                visionEnabled,
+                ...(!visionEnabled ? { visionModelResourceId: "" } : {}),
+              })
+            }
+            onModelResourceIdChange={(visionModelResourceId) =>
+              set("visionModelResourceId", visionModelResourceId)
+            }
+          />
 
           <SectionCard
             icon={<Database size={15} />}

frontend/src/components/workflow/panels/GlobalSettingsPanel.tsx

@@ -1,7 +1,6 @@
 "use client";
 
 import {
-  AudioLines,
   Brain,
   Database,
   MessageSquareText,
@@ -9,12 +8,9 @@ import {
   Wrench,
 } from "lucide-react";
 
-import {
-  ResourceSelectField,
-  ToggleRow,
-} from "@/components/assistant-editor/editor-controls";
 import { KnowledgeRetrievalConfigDialog } from "@/components/editor/knowledge-retrieval-config-dialog";
 import { SectionCard } from "@/components/editor/section-card";
+import { VisionConfigSection } from "@/components/editor/vision-config-section";
 import { TurnConfigEditor } from "@/components/turn-config-editor";
 import { Textarea } from "@/components/ui/textarea";
 
@@ -60,8 +56,8 @@ export function GlobalSettingsPanel({
 
       <SectionCard
         icon={<Brain size={15} />}
-        title="模型配置"
-        description="工作流中所有 Agent 共用的大语言模型"
+        title="模型与语音"
+        description="继承全局配置的 Agent 共用的推理、语音识别和语音合成资源"
       >
         <ModelSelect
           label="大语言模型"
@@ -77,62 +73,39 @@ export function GlobalSettingsPanel({
             })
           }
         />
-        <ToggleRow
-          title="视觉理解"
-          hint="开启后，继承全局配置的 Agent 可以按需理解当前视频画面。选择「模型自己」时，全局大语言模型必须支持图片输入。"
-          checked={settings.visionEnabled}
-          onChange={(visionEnabled) =>
-            onSettingsChange({
-              ...settings,
-              visionEnabled,
-              ...(!visionEnabled ? { visionModelResourceId: "" } : {}),
-            })
-          }
-        />
-        {settings.visionEnabled && (
-          <>
-            <ResourceSelectField
-              label="视觉模型"
-              value={settings.visionModelResourceId}
-              onChange={(visionModelResourceId) =>
-                onSettingsChange({ ...settings, visionModelResourceId })
-              }
-              options={modelOptions.vision.filter(
-                (option) => option.value !== settings.llm,
-              )}
-              noneLabel="模型自己"
-            />
-            {!settings.visionModelResourceId &&
-              !modelOptions.vision.some(
-                (option) => option.value === settings.llm,
-              ) && (
-                <p className="text-xs text-destructive">
-                  当前大语言模型未标记支持图片输入，请选择独立视觉模型。
-                </p>
-              )}
-          </>
-        )}
-      </SectionCard>
-
-      <SectionCard
-        icon={<AudioLines size={15} />}
-        title="语音配置"
-        description="Agent 节点未单独选择资源时继承这里的默认值"
-      >
         <ModelSelect
           label="语音识别"
           value={settings.asr}
           options={modelOptions.asr}
-          onChange={(v) => onSettingsChange({ ...settings, asr: v })}
+          onChange={(asr) => onSettingsChange({ ...settings, asr })}
         />
         <ModelSelect
           label="语音合成"
           value={settings.tts}
           options={modelOptions.tts}
-          onChange={(v) => onSettingsChange({ ...settings, tts: v })}
+          onChange={(tts) => onSettingsChange({ ...settings, tts })}
         />
       </SectionCard>
 
+      <VisionConfigSection
+        description="配置继承全局设置的 Agent 是否可以按需理解用户摄像头画面"
+        hint="开启后，继承全局配置的 Agent 会获得读取当前视频画面的工具。选择「模型自己」时，全局大语言模型必须支持图片输入。"
+        enabled={settings.visionEnabled}
+        modelResourceId={settings.visionModelResourceId}
+        mainModelResourceId={settings.llm ?? ""}
+        modelOptions={modelOptions.vision}
+        onEnabledChange={(visionEnabled) =>
+          onSettingsChange({
+            ...settings,
+            visionEnabled,
+            ...(!visionEnabled ? { visionModelResourceId: "" } : {}),
+          })
+        }
+        onModelResourceIdChange={(visionModelResourceId) =>
+          onSettingsChange({ ...settings, visionModelResourceId })
+        }
+      />
+
       <SectionCard
         icon={<Database size={15} />}
         title="知识库配置"