fix: restrict tool-heavy/swe-bench tagging to software development or agent-related tasks

internal/server/server.go

@@ -574,6 +574,31 @@ func (s *Server) handleChatCompletions(c *gin.Context) {
 		return
 	}
 
+	// Prune message history to sliding window if configured
+	if s.cfg.Server.MaxHistoryMessages > 0 && len(req.Messages) > s.cfg.Server.MaxHistoryMessages {
+		var systemMsgs []models.ChatMessage
+		var otherMsgs []models.ChatMessage
+		for _, msg := range req.Messages {
+			if msg.Role == "system" {
+				systemMsgs = append(systemMsgs, msg)
+			} else {
+				otherMsgs = append(otherMsgs, msg)
+			}
+		}
+
+		keepCount := s.cfg.Server.MaxHistoryMessages - len(systemMsgs)
+		if keepCount < 1 {
+			keepCount = 1
+		}
+		if len(otherMsgs) > keepCount {
+			startIndex := len(otherMsgs) - keepCount
+			otherMsgs = otherMsgs[startIndex:]
+			log.Printf("[DEBUG] Pruned message history: kept %d system messages and last %d messages (total %d out of %d)", 
+				len(systemMsgs), len(otherMsgs), len(systemMsgs)+len(otherMsgs), len(req.Messages))
+			req.Messages = append(systemMsgs, otherMsgs...)
+		}
+	}
+
 	// Strip common prefixes and prepare model ID
 	modelID := req.Model
 	prefixes := []string{"gemini/", "google/", "openai/", "deepseek/", "moonshot/", "grok/", "ollama/", "xiaomi/"}
@@ -1119,7 +1144,15 @@ func (s *Server) getRouteCtxTags(routeCtx *router.RouteContext) []string {
 		}
 	}
 
-	if routeCtx.RequiresToolCalling {
+	hasHeavyLogic := false
+	for _, tag := range tags {
+		if tag == "heavy-logic" {
+			hasHeavyLogic = true
+			break
+		}
+	}
+
+	if routeCtx.RequiresToolCalling && (routeCtx.IsSoftwareDevelopment || hasHeavyLogic) {
 		tags = append(tags, "tool-heavy", "multi-step-agent", "swe-bench")
 	}