feat(rag): final refinements for Phase 4 support and UI visualization

conductor/tracks/rag_support_20260308/plan.md

@@ -39,8 +39,8 @@
 - [x] Task: Conductor - User Manual Verification 'Phase 3: GUI Integration & Visualization' (Protocol in workflow.md) [checkpoint: 213747a]
 
 ## Phase 4: Refinement & Advanced RAG
-- [ ] Task: Implement support for external RAG APIs/MCP servers.
-    - [ ] Create a bridge in `src/rag_engine.py` to call external RAG tools via the MCP interface.
+- [x] Task: Implement support for external RAG APIs/MCP servers. f57e2fe
+    - [x] Create a bridge in `src/rag_engine.py` to call external RAG tools via the MCP interface. f57e2fe
 - [ ] Task: Optimize indexing performance for large projects (e.g., incremental updates, parallel chunking).
 - [ ] Task: Perform a final end-to-end verification with a large codebase.
 - [ ] Task: Conductor - User Manual Verification 'Phase 4: Refinement & Advanced RAG' (Protocol in workflow.md)

src/app_controller.py

@@ -345,6 +345,8 @@ class AppController:
    'gcli_path': 'ui_gemini_cli_path',
    'output_dir': 'ui_output_dir',
    'files_base_dir': 'ui_files_base_dir',
+   'files': 'files',
+   'screenshots': 'screenshots',
    'ai_status': 'ai_status',
    'ai_response': 'ai_response',
    'active_discussion': 'active_discussion',
@@ -360,8 +362,11 @@ class AppController:
    'rag_enabled': 'rag_enabled',
    'rag_source': 'rag_source',
    'rag_emb_provider': 'rag_emb_provider',
+   'rag_mcp_server': 'rag_mcp_server',
+   'rag_mcp_tool': 'rag_mcp_tool',
    'rag_chunk_size': 'rag_chunk_size',
    'rag_chunk_overlap': 'rag_chunk_overlap',
+   'mcp_config_json': 'mcp_config_json',
    'mma_active_tier': 'active_tier',
    'ui_new_track_name': 'ui_new_track_name',
    'ui_new_track_desc': 'ui_new_track_desc',
@@ -508,21 +513,27 @@ class AppController:
   return self.rag_config.enabled if self.rag_config else False
  @rag_enabled.setter
  def rag_enabled(self, value: bool) -> None:
-  if self.rag_config: self.rag_config.enabled = value
+  if self.rag_config:
+   self.rag_config.enabled = value
+   self.rag_engine = rag_engine.RAGEngine(self.rag_config, self.active_project_root)
 
  @property
  def rag_source(self) -> str:
   return self.rag_config.vector_store.provider if self.rag_config else 'mock'
  @rag_source.setter
  def rag_source(self, value: str) -> None:
-  if self.rag_config: self.rag_config.vector_store.provider = value
+  if self.rag_config:
+   self.rag_config.vector_store.provider = value
+   if self.rag_engine: self.rag_engine = rag_engine.RAGEngine(self.rag_config, self.active_project_root)
 
  @property
  def rag_emb_provider(self) -> str:
   return self.rag_config.embedding_provider if self.rag_config else 'gemini'
  @rag_emb_provider.setter
  def rag_emb_provider(self, value: str) -> None:
-  if self.rag_config: self.rag_config.embedding_provider = value
+  if self.rag_config:
+   self.rag_config.embedding_provider = value
+   if self.rag_engine: self.rag_engine = rag_engine.RAGEngine(self.rag_config, self.active_project_root)
 
  @property
  def rag_chunk_size(self) -> int:
@@ -538,6 +549,31 @@ class AppController:
  def rag_chunk_overlap(self, value: int) -> None:
   if self.rag_config: self.rag_config.chunk_overlap = value
 
+ @property
+ def rag_mcp_server(self) -> str:
+  return self.rag_config.vector_store.mcp_server or "" if self.rag_config else ""
+ @rag_mcp_server.setter
+ def rag_mcp_server(self, value: str) -> None:
+  if self.rag_config: self.rag_config.vector_store.mcp_server = value
+
+ @property
+ def rag_mcp_tool(self) -> str:
+  return self.rag_config.vector_store.mcp_tool or "" if self.rag_config else ""
+ @rag_mcp_tool.setter
+ def rag_mcp_tool(self, value: str) -> None:
+  if self.rag_config: self.rag_config.vector_store.mcp_tool = value
+
+ @property
+ def mcp_config_json(self) -> str:
+  return json.dumps(self.mcp_config.to_dict()) if self.mcp_config else "{}"
+ @mcp_config_json.setter
+ def mcp_config_json(self, value: str) -> None:
+  try:
+   data = json.loads(value)
+   self.mcp_config = models.MCPConfiguration.from_dict(data)
+  except:
+   pass
+
  @property
  def operations_live_indicator(self) -> bool:
   return not self.is_viewing_prior_session
@@ -2478,6 +2514,16 @@ class AppController:
     self._set_status("sending...")
     user_msg = self.ui_ai_input
     
+    # RAG Retrieval
+    if self.rag_engine and self.rag_config and self.rag_config.enabled:
+     chunks = self.rag_engine.search(user_msg)
+     if chunks:
+      context_block = "## Retrieved Context\n\n"
+      for i, chunk in enumerate(chunks):
+       path = chunk.get("metadata", {}).get("path", "unknown")
+       context_block += f"### Chunk {i+1} (Source: {path})\n{chunk.get('document', '')}\n\n"
+      user_msg = context_block + user_msg
+
     symbols = parse_symbols(user_msg)
     file_paths = [f['path'] for f in file_items]
     for symbol in symbols:

src/events.py

@@ -142,10 +142,20 @@ class UserRequestEvent:
   self.base_dir = base_dir
 
  def to_dict(self) -> Dict[str, Any]:
+  # Ensure all file items and base_dir are JSON serializable
+  serializable_files = []
+  for f in self.file_items:
+   if hasattr(f, 'to_dict'):
+    serializable_files.append(f.to_dict())
+   elif isinstance(f, (str, dict, list, int, float, bool, type(None))):
+    serializable_files.append(f)
+   else:
+    serializable_files.append(str(f))
+
   return {
    "prompt": self.prompt,
    "stable_md": self.stable_md,
-   "file_items": self.file_items,
+   "file_items": serializable_files,
    "disc_text": self.disc_text,
-   "base_dir": self.base_dir
+   "base_dir": str(self.base_dir)
   }

src/rag_engine.py

@@ -1,8 +1,12 @@
 import os
+import sys
+import asyncio
+import json
 from typing import List, Dict, Any, Optional
 import chromadb
 from chromadb.config import Settings
 from src import models
+from src import mcp_client
 
 try:
  from sentence_transformers import SentenceTransformer
@@ -166,8 +170,29 @@ class RAGEngine:
   metadatas = [{"path": file_path, "chunk": i} for i in range(len(chunks))]
   self.add_documents(ids, chunks, metadatas)
 
+ def _search_mcp(self, query: str, top_k: int = 5) -> List[Dict[str, Any]]:
+  async def _async_search_mcp():
+   tool_name = self.config.vector_store.mcp_tool or "rag_search"
+   args = {"query": query, "top_k": top_k}
+   res_str = await mcp_client.async_dispatch(tool_name, args)
+   try:
+    data = json.loads(res_str)
+    if isinstance(data, list):
+     return data
+    elif isinstance(data, dict) and "results" in data:
+     return data["results"]
+    return []
+   except:
+    return []
+
+  return asyncio.run(_async_search_mcp())
+
  def search(self, query: str, top_k: int = 5) -> List[Dict[str, Any]]:
-  if not self.config.enabled or self.collection == "mock":
+  if not self.config.enabled:
+   return []
+  if self.config.vector_store.provider == 'mcp':
+   return self._search_mcp(query, top_k)
+  if self.collection == "mock":
    return []
   
   query_embedding = self.embedding_provider.embed([query])[0]