more optmizations

mcp/server.py

@@ -59,11 +59,10 @@ def embed(text, input_type):
     assert resp.embeddings.float_ is not None
     return resp.embeddings.float_[0]
 
-def search(query, roles: list[str], limit: int = 5) -> list[dict]:
+def search(query, roles: list[str], limit: int = 3, max_content_length: int = 1500) -> list[dict]:
     query_embedding = embed(query, 'search_query')
 
     if not roles:
-        # No roles = no results
         return []
 
     rows = conn.execute(
@@ -71,7 +70,13 @@ def search(query, roles: list[str], limit: int = 5) -> list[dict]:
         (roles, query_embedding, limit)
     ).fetchall()
 
-    return [{'key': row['key'], 'content': row['content']} for row in rows]
+    docs = []
+    for row in rows:
+        content = row['content'] or ''
+        if len(content) > max_content_length:
+            content = content[:max_content_length] + '...[truncated, use get_document_page for full text]'
+        docs.append({'key': row['key'], 'content': content})
+    return docs
 
 @mcp.tool
 def get_cave_location(cave: str, state: str, county: str) -> list[dict]:

web/agent/src/agent.py

@@ -23,9 +23,9 @@ logger.info("Initializing Cavepedia agent...")
 
 
 def limit_history(ctx: RunContext[None], messages: list[ModelMessage]) -> list[ModelMessage]:
-    """Limit conversation history to manage token usage and request size."""
+    """Limit conversation history to manage token usage."""
-    # Keep only the last few messages to avoid large requests hitting Cloudflare limits
+    # Keep last 8 messages for context, but not unlimited
-    return messages[-4:]
+    return messages[-8:]
 
 def check_mcp_available(url: str, timeout: float = 5.0) -> bool:
     """Check if MCP server is reachable via health endpoint."""
@@ -54,7 +54,7 @@ Rules:
 4. Can create ascii diagrams/maps.
 5. Be direct—no sycophantic phrases.
 6. Keep responses concise.
-7. Use tools sparingly—one search usually suffices. Answer from your knowledge when possible."""
+7. Search ONCE, then answer with what you found. Do not search repeatedly for the same topic."""
 
 
 def create_agent(user_roles: list[str] | None = None):