feat: organize tools and enable qwen realtime calls

backend/services/node_specs.py

@@ -1,4 +1,4 @@
-"""Workflow v3 node catalog, v2 compatibility normalization, and validation."""
+"""Workflow v4 node catalog, normalization, and validation."""
 
 from __future__ import annotations
 
@@ -14,7 +14,7 @@ from services.message_policy import (
 )
 
 
-SPEC_VERSION = "3"
+SPEC_VERSION = "4"
 NODE_TYPES = {
     "start",
     "agent",
@@ -28,7 +28,6 @@ EDGE_MODES = {"llm", "expression", "always"}
 WORKFLOW_RUNTIME_MODES = {"pipeline", "realtime"}
 WORKFLOW_LLM_ROUTING_MODES = {"llm_router", "edge_tool"}
 AGENT_ENTRY_MODES = {"wait_user", "generate"}
-ACTION_RESULT_ASSIGNMENT_MODES = {"inherit", "override", "none"}
 ACTION_USER_INPUT_POLICIES = {"queue", "block"}
 AUTOMATIC_NODE_TYPES = {
     "start",
@@ -195,11 +194,8 @@ def _normalize_agent_data(data: dict[str, Any]) -> None:
     if data.get("entryMode") not in AGENT_ENTRY_MODES:
         data["entryMode"] = "wait_user"
     data.pop("entrySpeech", None)
-    data.pop("systemTools", None)
-    state_names = data.get("stateVariableNames")
-    data["stateVariableNames"] = list(
-        dict.fromkeys(str(name) for name in state_names or [] if str(name))
-    )
+    data.setdefault("toolBindings", [])
+    data.setdefault("builtInTools", {})
     legacy_prompt = str(data.pop("visionFocusPrompt", "") or "").strip()
     if "visionPrompt" not in data:
         data["visionPrompt"] = legacy_prompt
@@ -215,35 +211,30 @@ def _normalize_agent_data(data: dict[str, Any]) -> None:
                 data.get("visionModelResourceId"),
                 data.get("visionPrompt"),
                 data.get("knowledgeBaseId"),
-                data.get("toolIds"),
+                data.get("toolBindings"),
             )
         )
         data["inheritGlobalConfig"] = not has_node_overrides
 
 
 def _normalize_action_data(data: dict[str, Any]) -> None:
-    """Add Action defaults while preserving the behavior of saved graphs.
-
-    Older Action nodes always passed an empty mapping when no node-level
-    assignments were configured, so they did *not* inherit the reusable
-    tool's assignments.  Infer ``none`` for that shape and ``override`` for
-    an existing non-empty mapping.  Newly created nodes should persist their
-    intended mode explicitly.
-    """
-    if "resultAssignmentMode" not in data:
-        assignments = data.get("resultAssignments")
-        data["resultAssignmentMode"] = (
-            "override" if isinstance(assignments, dict) and assignments else "none"
-        )
-    data.setdefault("resultAssignments", {})
+    """Add deterministic Action defaults."""
+    data.setdefault(
+        "toolBinding",
+        {
+            "toolId": "",
+            "argumentBindings": {},
+            "templateBindings": {},
+            "resultAssignments": {},
+        },
+    )
     data.setdefault("userInputPolicy", "queue")
     data.pop("speech", None)
 
 
 def _normalize_update_state_data(data: dict[str, Any]) -> None:
-    """Keep deterministic state updates as one explicit assignment object."""
-    assignments = data.get("assignments")
-    data["assignments"] = dict(assignments) if isinstance(assignments, dict) else {}
+    """Keep deterministic state updates as typed expression rules."""
+    data.setdefault("updates", [])
 
 
 def _normalize_message_data(data: dict[str, Any]) -> None:
@@ -278,7 +269,8 @@ def _normalize_settings(settings: dict[str, Any], *, global_prompt: str = "") ->
     settings.setdefault("visionPrompt", legacy_prompt)
     if "visionPromptMode" not in settings:
         settings["visionPromptMode"] = "guided" if legacy_prompt else "runtime"
-    settings.setdefault("toolIds", [])
+    settings.setdefault("toolBindings", [])
+    settings.setdefault("builtInTools", {})
     settings.setdefault("knowledgeBaseId", "")
     settings.setdefault("knowledgeMode", "automatic")
     settings.setdefault("knowledgeTopN", 5)
@@ -288,7 +280,7 @@ def _normalize_settings(settings: dict[str, Any], *, global_prompt: str = "") ->
 
 
 def normalize_graph(graph: dict[str, Any] | None) -> dict[str, Any]:
-    """Return a deep-copied v3 graph; preserve v3 IDs and migrate v2 semantics."""
+    """Return a deep-copied v4 graph."""
     source = deepcopy(graph or {})
     if str(source.get("specVersion") or "") == SPEC_VERSION:
         settings = source.setdefault("settings", {})
@@ -402,7 +394,7 @@ def normalize_graph(graph: dict[str, Any] | None) -> dict[str, Any]:
     settings = deepcopy(source.get("settings") or {})
     _normalize_settings(settings, global_prompt=global_prompt)
     return {
-        "specVersion": 3,
+        "specVersion": 4,
         "settings": settings,
         "nodes": mapped_nodes,
         "edges": mapped_edges,
@@ -475,12 +467,11 @@ def validate_graph(graph: dict[str, Any]) -> list[str]:
             entry_mode = data.get("entryMode", "wait_user")
             if entry_mode not in AGENT_ENTRY_MODES:
                 errors.append(f"Agent 节点 {node_id} 的进入模式无效:{entry_mode}")
-            state_names = data.get("stateVariableNames", [])
-            if not isinstance(state_names, list) or any(
-                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
+            if not isinstance(source.get("toolBindings"), list):
+                errors.append(f"Agent 节点 {node_id} 的工具绑定必须是列表")
+            if not isinstance(source.get("builtInTools"), dict):
+                errors.append(f"Agent 节点 {node_id} 的内建工具配置必须是对象")
             vision_prompt_mode = str(source.get("visionPromptMode") or "runtime")
             if vision_prompt_mode not in VISION_PROMPT_MODES:
                 errors.append(
@@ -562,13 +553,9 @@ def validate_graph(graph: dict[str, Any]) -> list[str]:
                     )
         elif node_type == "action":
             data = node.get("data") or {}
-            assignment_mode = data.get("resultAssignmentMode")
-            if assignment_mode not in ACTION_RESULT_ASSIGNMENT_MODES:
-                errors.append(
-                    f"Action 节点 {node_id} 的结果变量模式无效:{assignment_mode}"
-                )
-            if not isinstance(data.get("resultAssignments"), dict):
-                errors.append(f"Action 节点 {node_id} 的结果变量映射必须是对象")
+            binding = data.get("toolBinding")
+            if not isinstance(binding, dict) or not binding.get("toolId"):
+                errors.append(f"Action 节点 {node_id} 必须配置工具绑定")
             input_policy = data.get("userInputPolicy")
             if input_policy not in ACTION_USER_INPUT_POLICIES:
                 errors.append(
@@ -580,10 +567,10 @@ def validate_graph(graph: dict[str, Any]) -> list[str]:
                 )
         elif node_type == "update_state":
             data = node.get("data") or {}
-            assignments = data.get("assignments")
-            if not isinstance(assignments, dict) or not assignments:
+            updates = data.get("updates")
+            if not isinstance(updates, list) or not updates:
                 errors.append(
-                    f"Update State 节点 {node_id} 必须配置至少一个变量赋值"
+                    f"Update State 节点 {node_id} 必须配置至少一条更新规则"
                 )
 
     if counts["start"] != 1:
@@ -729,7 +716,11 @@ def graph_references(graph: dict[str, Any]) -> dict[str, set[str]]:
         )
         if value
     }
-    tools: set[str] = {str(tool_id) for tool_id in settings.get("toolIds") or []}
+    tools: set[str] = {
+        str(binding.get("toolId") or "")
+        for binding in settings.get("toolBindings") or []
+        if isinstance(binding, dict) and binding.get("toolId")
+    }
     knowledge: set[str] = (
         {str(settings["knowledgeBaseId"])}
         if settings.get("knowledgeBaseId")
@@ -753,10 +744,12 @@ def graph_references(graph: dict[str, Any]) -> dict[str, set[str]]:
             ):
                 if resource_id:
                     resources.add(str(resource_id))
-            for tool_id in data.get("toolIds") or []:
-                tools.add(str(tool_id))
+            for binding in data.get("toolBindings") or []:
+                if isinstance(binding, dict) and binding.get("toolId"):
+                    tools.add(str(binding["toolId"]))
             if data.get("knowledgeBaseId"):
                 knowledge.add(str(data["knowledgeBaseId"]))
-        if data.get("toolId"):
-            tools.add(str(data["toolId"]))
+        binding = data.get("toolBinding")
+        if isinstance(binding, dict) and binding.get("toolId"):
+            tools.add(str(binding["toolId"]))
     return {"model_resources": resources, "tools": tools, "knowledge_bases": knowledge}