Merge pull request #82 from SuanmoSuanyangTechnology/feat/memory-perceptual

Feat/memory perceptual

api/app/core/workflow/executor.py

@@ -338,7 +338,6 @@ class WorkflowExecutor:
                     chunk_count += 1
                     event_type = data.get("type", "node_chunk")  # "message" or "node_chunk"
                     logger.info(f"[CUSTOM] ✅ 收到 {event_type} #{chunk_count} from {data.get('node_id')}")
-
                     yield {
                         "event": event_type,  # "message" or "node_chunk"
                         "data": {
@@ -347,7 +346,8 @@ class WorkflowExecutor:
                             "full_content": data.get("full_content"),
                             "chunk_index": data.get("chunk_index"),
                             "is_prefix": data.get("is_prefix"),
-                            "is_suffix": data.get("is_suffix")
+                            "is_suffix": data.get("is_suffix"),
+                            "conversation_id": input_data.get("conversation_id"),
                         }
                     }
 

api/app/schemas/memory_perceptual_schema.py

@@ -44,6 +44,9 @@ class PerceptualMemoryItem(BaseModel):
     summary: Optional[str] = Field(None, description="summary")
     storage_type: FileStorageType = Field(..., description="Storage type for file")
     created_time: int = Field(..., description="create time")
+    topic: str = Field(..., description="topic")
+    domain: str = Field(..., description="domain")
+    keywords: list[str] = Field(..., description="keywords")
 
     class Config:
         from_attributes = True

api/app/services/memory_perceptual_service.py

@@ -136,6 +136,9 @@ class MemoryPerceptualService:
 
             memory_items = []
             for memory in memories:
+                meta_data = memory.meta_data or {}
+                content = meta_data.get("content")
+                content = Content(**content)
                 memory_item = PerceptualMemoryItem(
                     id=memory.id,
                     perceptual_type=PerceptualType(memory.perceptual_type),
@@ -143,6 +146,9 @@ class MemoryPerceptualService:
                     file_name=memory.file_name,
                     file_ext=memory.file_ext,
                     summary=memory.summary,
+                    topic=content.topic,
+                    domain=content.domain,
+                    keywords=content.keywords,
                     created_time=int(memory.created_time.timestamp()*1000),
                     storage_type=FileStorageType(memory.storage_service),
                 )

api/app/services/prompt/conversation_summary_system.jinja2

@@ -35,7 +35,8 @@ You are a professional dialogue content summarizer, specializing in extracting c
   1. `theme`: A concise phrase describing the conversation’s core topic (e.g., "inquiry about delivery time rules");
   2. `summary`: A single sentence including "user request + AI response + interaction logic" (≤150 words);
   3. `takeaways`: A list of brief bullet-point takeaways summarizing the key points from the conversation (e.g., ["User clarified delivery time differences between regular and remote areas"]).
-  4. `question`: A list of brief declarative statements summarizing the pitfalls the user encountered during the current conversation.Return an empty list if none are present.
+  4. `question`: The `question` field is a list of brief declarative statements describing objective pitfalls or problems the user actually encountered during the current conversation.
+Strict rules: Only include problems that clearly and directly affected task progress. Each item must be a short, factual, declarative statement. Only record issues that are explicitly observable from the conversation. Do NOT include assumptions, interpretations, or stylistic judgments.
   5. `info_score`: Numerical score (0–100) representing conversation information richness.
 - Language Style: Concise, objective, conversational (avoid overly formal terms).