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>

client/client_test.go

@@ -48,7 +48,7 @@ func newTestForeman(t *testing.T, ollamaClient ollama.Client, webhookSecret stri
 
 	notifier := worker.NewNotifier()
 	dispatcher := webhook.NewDispatcher(webhookSecret, logger)
-	w := worker.New(st, ollamaClient, inv, notifier, dispatcher, logger)
+	w := worker.New(st, ollamaClient, inv, notifier, dispatcher, logger, "-1")
 
 	cfg := config.Config{
 		OllamaURL:     "http://localhost:11434",
@@ -260,7 +260,7 @@ func TestSubmit_AuthToken(t *testing.T) {
 
 	notifier := worker.NewNotifier()
 	dispatcher := webhook.NewDispatcher("", logger)
-	w := worker.New(st, ollamaStub, inv, notifier, dispatcher, logger)
+	w := worker.New(st, ollamaStub, inv, notifier, dispatcher, logger, "-1")
 
 	cfg := config.Config{
 		OllamaURL:   "http://localhost:11434",