fix: support vision prompt modes

backend/services/node_specs.py

@@ -6,6 +6,7 @@ from collections import defaultdict, deque
 from copy import deepcopy
 from typing import Any
 
+from models import VISION_PROMPT_MODES
 from services.message_policy import (
     MESSAGE_COMPLETION_POLICIES,
     MESSAGE_CONFIRMATION,
@@ -199,6 +200,11 @@ def _normalize_agent_data(data: dict[str, Any]) -> None:
     data["stateVariableNames"] = list(
         dict.fromkeys(str(name) for name in state_names or [] if str(name))
     )
+    legacy_prompt = str(data.pop("visionFocusPrompt", "") or "").strip()
+    if "visionPrompt" not in data:
+        data["visionPrompt"] = legacy_prompt
+    if "visionPromptMode" not in data:
+        data["visionPromptMode"] = "guided" if legacy_prompt else "runtime"
     if "inheritGlobalConfig" not in data:
         has_node_overrides = any(
             (
@@ -207,7 +213,7 @@ def _normalize_agent_data(data: dict[str, Any]) -> None:
                 data.get("ttsResourceId"),
                 data.get("visionEnabled"),
                 data.get("visionModelResourceId"),
-                data.get("visionFocusPrompt"),
+                data.get("visionPrompt"),
                 data.get("knowledgeBaseId"),
                 data.get("toolIds"),
             )
@@ -268,7 +274,10 @@ def _normalize_settings(settings: dict[str, Any], *, global_prompt: str = "") ->
     settings.setdefault("defaultTtsResourceId", "")
     settings.setdefault("visionEnabled", False)
     settings.setdefault("visionModelResourceId", "")
-    settings.setdefault("visionFocusPrompt", "")
+    legacy_prompt = str(settings.pop("visionFocusPrompt", "") or "").strip()
+    settings.setdefault("visionPrompt", legacy_prompt)
+    if "visionPromptMode" not in settings:
+        settings["visionPromptMode"] = "guided" if legacy_prompt else "runtime"
     settings.setdefault("toolIds", [])
     settings.setdefault("knowledgeBaseId", "")
     settings.setdefault("knowledgeMode", "automatic")
@@ -471,6 +480,20 @@ def validate_graph(graph: dict[str, Any]) -> list[str]:
                 not isinstance(name, str) for name in state_names
             ):
                 errors.append(f"Agent 节点 {node_id} 的状态变量授权必须是列表")
+            source = settings if data.get("inheritGlobalConfig", True) else data
+            vision_prompt_mode = str(source.get("visionPromptMode") or "runtime")
+            if vision_prompt_mode not in VISION_PROMPT_MODES:
+                errors.append(
+                    f"Agent 节点 {node_id} 的视觉提示词模式无效:{vision_prompt_mode}"
+                )
+            if (
+                source.get("visionEnabled")
+                and vision_prompt_mode in {"fixed", "guided"}
+                and not str(source.get("visionPrompt") or "").strip()
+            ):
+                errors.append(
+                    f"Agent 节点 {node_id} 的固定或引导模式必须填写视觉提示词"
+                )
             if runtime_mode == "realtime":
                 if data.get("contextPolicy", "inherit") != "inherit":
                     errors.append(
@@ -487,7 +510,6 @@ def validate_graph(graph: dict[str, Any]) -> list[str]:
                     errors.append(
                         f"Realtime Agent 节点 {node_id} 不支持节点级模型、语音或交互策略覆盖"
                     )
-                source = settings if data.get("inheritGlobalConfig", True) else data
                 if (
                     source.get("knowledgeBaseId")
                     and source.get("knowledgeMode") != "on_demand"