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>

internal/server/server_test.go

@@ -38,7 +38,7 @@ func newTestServer(t *testing.T, cfg config.Config, client ollama.Client) (*Serv
 	inv := ollama.NewModelInventory(client, logger)
 	notifier := worker.NewNotifier()
 	dispatcher := webhook.NewDispatcher("", logger)
-	w := worker.New(st, client, inv, notifier, dispatcher, logger)
+	w := worker.New(st, client, inv, notifier, dispatcher, logger, "-1")
 	srv := New(cfg, st, client, inv, notifier, w, dispatcher, logger)
 	return srv, st
 }