feat: route workflow image inputs natively

backend/services/workflow_router.py

@@ -9,6 +9,7 @@ from __future__ import annotations
 
 import json
 from collections.abc import Callable
+from copy import deepcopy
 from typing import Any
 
 from loguru import logger
@@ -24,6 +25,32 @@ STAY_ON_CURRENT_AGENT = STAY_ON_CURRENT_NODE
 MAX_ROUTING_HISTORY_ENTRIES = 20
 
 
+def _routing_user_message(
+    routing_input: str,
+    current_user_message: dict[str, Any] | None,
+) -> dict[str, Any]:
+    """Combine routing metadata with the current text or multimodal turn."""
+    if not current_user_message:
+        return {"role": "user", "content": routing_input}
+
+    content = current_user_message.get("content")
+    if not isinstance(content, list):
+        current_text = str(content or "").strip()
+        suffix = f"\n\n[当前用户输入]\n{current_text}" if current_text else ""
+        return {"role": "user", "content": f"{routing_input}{suffix}"}
+
+    return {
+        "role": "user",
+        "content": [
+            {
+                "type": "text",
+                "text": f"{routing_input}\n\n[当前用户输入如下]",
+            },
+            *deepcopy(content),
+        ],
+    }
+
+
 class WorkflowLLMRouter:
     """Select one LLM edge without allowing the router to speak."""
 
@@ -40,6 +67,7 @@ class WorkflowLLMRouter:
         variables: dict[str, Any],
         edge_name: Callable[[dict[str, Any]], str],
         edge_description: Callable[[dict[str, Any]], str],
+        current_user_message: dict[str, Any] | None = None,
     ) -> LLMRouteResult:
         """Return a typed match, no-match or technical error."""
         if not edges:
@@ -85,7 +113,13 @@ class WorkflowLLMRouter:
             f"当前节点任务：{node_prompt or '未配置'}\n"
             f"转移条件：\n{ordered_conditions}"
         )
-        recent_history = history[-MAX_ROUTING_HISTORY_ENTRIES:]
+        # WorkflowBrain records the current turn before routing. When the full
+        # current message is supplied separately, keep only earlier history so
+        # the text is not duplicated and the image remains attached to its turn.
+        routing_history = (
+            history[:-1] if current_user_message and history else history
+        )
+        recent_history = routing_history[-MAX_ROUTING_HISTORY_ENTRIES:]
         routing_input = json.dumps(
             {
                 "conversation": recent_history,
@@ -108,7 +142,7 @@ class WorkflowLLMRouter:
                 model=self._cfg.model,
                 messages=[
                     {"role": "system", "content": router_prompt},
-                    {"role": "user", "content": routing_input},
+                    _routing_user_message(routing_input, current_user_message),
                 ],
                 tools=tools,
                 tool_choice="required",