feat: add FOREMAN_KEEP_ALIVE config for worker model residency

Allow configuring how long the worker model stays resident on the Ollama
target after a request via FOREMAN_KEEP_ALIVE env var. Accepts Ollama
duration strings ("-1" forever, "0" unload, "15m", "1h", etc). Defaults
to "-1" (pin forever). The embedder warm-up is unaffected and always
uses keep_alive=-1.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

cmd/foreman/main.go

@@ -79,6 +79,7 @@ func runServe(logger *slog.Logger) error {
 		"auth_enabled", cfg.Token != "",
 		"max_attempts", cfg.MaxAttempts,
 		"job_ttl", cfg.JobTTL,
+		"keep_alive", cfg.KeepAlive,
 	)
 
 	st, err := store.Open(cfg.DBPath)
@@ -107,7 +108,7 @@ func runServe(logger *slog.Logger) error {
 
 	// Create the notifier and worker.
 	notifier := worker.NewNotifier()
-	w := worker.New(st, client, inventory, notifier, dispatcher, logger)
+	w := worker.New(st, client, inventory, notifier, dispatcher, logger, cfg.KeepAlive)
 
 	// Start the worker loop in a goroutine.
 	go w.Run(ctx)