fix: pull default Ollama model when leader uses inherit

When the leader's SubAgentModel is "inherit", the deploy skipped the
Ollama model pull but OPENCODE_MODEL was set to the default model
(e.g. qwen3:4b). This caused "model not found" errors at runtime.
Now falls back to defaultOpenCodeModel() for the pull step.

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

Author: barckcode

VERSION

@@ -1 +1 @@
-0.4.8
+0.4.9

internal/api/handlers_teams.go

@@ -372,15 +372,19 @@ func (s *Server) deployTeamAsync(team models.Team) {
 				return
 			}
 
-			// Determine model to pull from leader's SubAgentModel (strip "ollama/" prefix).
+			// Determine model to pull: use leader's explicit model, or fall back
+			// to the default model for the Ollama provider.
 			ollamaModel := ""
 			for _, a := range team.Agents {
 				if a.Role == models.AgentRoleLeader {
 					ollamaModel = a.SubAgentModel
 					break
 				}
 			}
-			if ollamaModel != "" && ollamaModel != "inherit" {
+			if ollamaModel == "" || ollamaModel == "inherit" {
+				ollamaModel = defaultOpenCodeModel(team.ModelProvider)
+			}
+			if ollamaModel != "" {
 				ollamaModel = strings.TrimPrefix(ollamaModel, "ollama/")
 				s.db.Model(&team).Update("status_message", "Pulling Ollama model: "+ollamaModel+"...")