feat: add account management, email verification, AI fixes, and user guides

- Profile settings, account transfer, delete/leave account flows
- Email verification with JWT tokens and Resend integration
- AI assistant/copilot fixes: markdown rendering, shared RAG helpers,
  token tracking, input refocus, model_validate usage
- User guides hub + detail pages with 13 topic guides
- Sidebar and top bar navigation for guides

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

backend/app/services/assistant_chat_service.py

@@ -12,7 +12,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.core.ai_provider import get_ai_provider
 from app.models.assistant_chat import AssistantChat
-from app.services import rag_service
+from app.services.rag_service import search as rag_search, build_rag_context, extract_suggested_flows
 
 logger = logging.getLogger(__name__)
 
@@ -33,36 +33,6 @@ When answering:
 """
 
 
-def _build_rag_context(rag_results: list[dict[str, Any]]) -> str:
-    """Format RAG results into a system prompt section."""
-    if not rag_results:
-        return ""
-
-    parts = ["\n--- RELEVANT FLOWS FROM TEAM LIBRARY ---"]
-    for r in rag_results[:5]:
-        parts.append(f"- [{r['tree_type']}] {r['tree_name']}: {r['chunk_text'][:200]}")
-
-    return "\n".join(parts)
-
-
-def _extract_suggested_flows(rag_results: list[dict[str, Any]]) -> list[dict[str, Any]]:
-    """Extract unique suggested flows from RAG results."""
-    seen: set[str] = set()
-    suggestions = []
-    for r in rag_results:
-        tid = r["tree_id"]
-        if tid in seen or r["similarity"] < 0.3:
-            continue
-        seen.add(tid)
-        suggestions.append({
-            "tree_id": tid,
-            "tree_name": r["tree_name"],
-            "tree_type": r["tree_type"],
-            "relevance_snippet": r["chunk_text"][:150],
-        })
-    return suggestions[:3]
-
-
 def _auto_title(message: str) -> str:
     """Generate a short title from the first user message."""
     title = message.strip()[:100]
@@ -113,7 +83,7 @@ async def send_message(
         chat.title = _auto_title(message)
 
     # RAG search
-    rag_results = await rag_service.search(
+    rag_results = await rag_search(
         query=message,
         account_id=account_id,
         db=db,
@@ -121,7 +91,7 @@ async def send_message(
     )
 
     # Build system prompt
-    system_prompt = ASSISTANT_SYSTEM_PROMPT + _build_rag_context(rag_results)
+    system_prompt = ASSISTANT_SYSTEM_PROMPT + build_rag_context(rag_results)
 
     # Build messages for AI
     ai_messages = []
@@ -147,6 +117,6 @@ async def send_message(
     chat.total_input_tokens += input_tokens
     chat.total_output_tokens += output_tokens
 
-    suggested_flows = _extract_suggested_flows(rag_results)
+    suggested_flows = extract_suggested_flows(rag_results)
 
     return ai_content, suggested_flows, chat

backend/app/services/copilot_service.py

@@ -15,7 +15,7 @@ from sqlalchemy.orm import selectinload
 from app.core.ai_provider import get_ai_provider
 from app.models.tree import Tree
 from app.models.copilot_conversation import CopilotConversation
-from app.services import rag_service
+from app.services.rag_service import search as rag_search, build_rag_context, extract_suggested_flows
 
 logger = logging.getLogger(__name__)
 
@@ -83,45 +83,6 @@ def _find_node(structure: dict, node_id: str) -> Optional[dict]:
     return None
 
 
-def _build_rag_context(rag_results: list[dict[str, Any]]) -> str:
-    """Format RAG results into a system prompt section."""
-    if not rag_results:
-        return ""
-
-    parts = ["\n--- RELEVANT FLOWS FROM TEAM LIBRARY ---"]
-    for r in rag_results[:5]:  # Cap at 5 for prompt size
-        parts.append(f"- [{r['tree_type']}] {r['tree_name']}: {r['chunk_text'][:200]}")
-
-    return "\n".join(parts)
-
-
-def _extract_suggested_flows(
-    rag_results: list[dict[str, Any]],
-    exclude_tree_id: Optional[UUID] = None,
-) -> list[dict[str, Any]]:
-    """Extract unique suggested flows from RAG results."""
-    seen_tree_ids: set[str] = set()
-    suggestions = []
-
-    for r in rag_results:
-        tid = r["tree_id"]
-        if exclude_tree_id and tid == str(exclude_tree_id):
-            continue
-        if tid in seen_tree_ids:
-            continue
-        if r["similarity"] < 0.3:
-            continue
-        seen_tree_ids.add(tid)
-        suggestions.append({
-            "tree_id": tid,
-            "tree_name": r["tree_name"],
-            "tree_type": r["tree_type"],
-            "relevance_snippet": r["chunk_text"][:150],
-        })
-
-    return suggestions[:3]
-
-
 async def start_conversation(
     user_id: UUID,
     account_id: UUID,
@@ -168,10 +129,10 @@ async def send_message(
     message: str,
     current_node_id: Optional[str],
     db: AsyncSession,
-) -> tuple[str, list[dict[str, Any]]]:
+) -> tuple[str, list[dict[str, Any]], CopilotConversation]:
     """Send a user message and get AI response.
 
-    Returns (ai_content, suggested_flows).
+    Returns (ai_content, suggested_flows, conversation).
     """
     result = await db.execute(
         select(CopilotConversation).where(
@@ -199,7 +160,7 @@ async def send_message(
         conversation.current_node_id = current_node_id
 
     # RAG search
-    rag_results = await rag_service.search(
+    rag_results = await rag_search(
         query=message,
         account_id=conversation.account_id,
         db=db,
@@ -209,7 +170,7 @@ async def send_message(
     # Build system prompt
     system_prompt = COPILOT_SYSTEM_PROMPT
     system_prompt += _build_flow_context(tree, conversation.current_node_id)
-    system_prompt += _build_rag_context(rag_results)
+    system_prompt += build_rag_context(rag_results)
 
     # Build messages for AI
     ai_messages = []
@@ -236,6 +197,6 @@ async def send_message(
     conversation.total_output_tokens += output_tokens
 
     # Extract suggested flows
-    suggested_flows = _extract_suggested_flows(rag_results, exclude_tree_id=tree.id)
+    suggested_flows = extract_suggested_flows(rag_results, exclude_tree_id=tree.id)
 
-    return ai_content, suggested_flows
+    return ai_content, suggested_flows, conversation

backend/app/services/rag_service.py

@@ -168,3 +168,42 @@ async def search(
         }
         for row in rows
     ]
+
+
+def build_rag_context(rag_results: list[dict[str, Any]]) -> str:
+    """Format RAG results into a system prompt section."""
+    if not rag_results:
+        return ""
+
+    parts = ["\n--- RELEVANT FLOWS FROM TEAM LIBRARY ---"]
+    for r in rag_results[:5]:  # Cap at 5 for prompt size
+        parts.append(f"- [{r['tree_type']}] {r['tree_name']}: {r['chunk_text'][:200]}")
+
+    return "\n".join(parts)
+
+
+def extract_suggested_flows(
+    rag_results: list[dict[str, Any]],
+    exclude_tree_id: Optional[UUID] = None,
+) -> list[dict[str, Any]]:
+    """Extract unique suggested flows from RAG results."""
+    seen_tree_ids: set[str] = set()
+    suggestions = []
+
+    for r in rag_results:
+        tid = r["tree_id"]
+        if exclude_tree_id and tid == str(exclude_tree_id):
+            continue
+        if tid in seen_tree_ids:
+            continue
+        if r["similarity"] < 0.3:
+            continue
+        seen_tree_ids.add(tid)
+        suggestions.append({
+            "tree_id": tid,
+            "tree_name": r["tree_name"],
+            "tree_type": r["tree_type"],
+            "relevance_snippet": r["chunk_text"][:150],
+        })
+
+    return suggestions[:3]