llmgw/internal/cli/clustersettings_test.go

package cli

import (
	"context"
	"io"
	"log/slog"
	"os"
	"path/filepath"
	"strings"
	"testing"

	"gitea.mynodes.xyz/ilker/llmgw/internal/config"
	storepkg "gitea.mynodes.xyz/ilker/llmgw/internal/store"
)

func settingsFixture(t *testing.T, extra string) (path, store string) {
	t.Helper()
	dir := t.TempDir()
	store = filepath.Join(dir, "llmgw.db")
	path = filepath.Join(dir, "server.yaml")
	body := "listen: \":8080\"\nagent_insecure: true\nauth:\n  enabled: true\n  store: " + store +
		"\nrouter:\n  retries: 2\n" + extra
	if err := os.WriteFile(path, []byte(body), 0o600); err != nil {
		t.Fatal(err)
	}
	return path, store
}

var quiet = slog.New(slog.NewTextHandler(io.Discard, nil))

func TestTheFirstStartBringsTheFilesSettingsInWithGuardrails(t *testing.T) {
	path, store := settingsFixture(t, "")
	s, err := loadClusterSettings(t.Context(), path, quiet)
	if err != nil {
		t.Fatal(err)
	}
	if s.version != 1 || s.cfg.Router.Retries != 2 {
		t.Errorf("version %d retries %d", s.version, s.cfg.Router.Retries)
	}
	if len(s.cfg.Guard.Policies) == 0 || s.cfg.Guard.Policies["baseline"].Judge != nil {
		t.Errorf("a file without guard got %+v, want the baseline without a judge", s.cfg.Guard)
	}
	st, _ := storepkg.Open(t.Context(), store)
	defer st.Close()
	doc, _ := st.ClusterSettings(t.Context())
	if strings.Contains(doc.Body, "listen") || strings.Contains(doc.Body, store) || !strings.Contains(doc.Body, "retries: 2") {
		t.Errorf("the store holds a machine's keys, or lost the cluster's:\n%s", doc.Body)
	}

	// From then on the store's settings are the cluster's, whatever a
	// file says.
	_ = os.WriteFile(path, []byte(strings.Replace(mustRead(t, path), "retries: 2", "retries: 9", 1)), 0o600)
	again, err := loadClusterSettings(t.Context(), path, quiet)
	if err != nil || again.version != 1 || again.cfg.Router.Retries != 2 {
		t.Errorf("second start: version %d retries %d err %v", again.version, again.cfg.Router.Retries, err)
	}
}

func mustRead(t *testing.T, p string) string {
	b, err := os.ReadFile(p)
	if err != nil {
		t.Fatal(err)
	}
	return string(b)
}

func TestEveryChangeIsAppliedLiveOrByStartingAgain(t *testing.T) {
	path, store := settingsFixture(t, "")
	s, err := loadClusterSettings(t.Context(), path, quiet)
	if err != nil {
		t.Fatal(err)
	}
	st, _ := storepkg.Open(t.Context(), store)
	defer st.Close()
	var lived [][]string
	var restarts []string
	w := &settingsWatch{path: path, st: st, cur: s, log: quiet,
		live: func(_ config.Server, changed []string) bool {
			lived = append(lived, changed)
			return onlyLive(changed)
		},
		restart: func(why string) { restarts = append(restarts, why) },
	}
	ctx := context.Background()
	put := func(body string) {
		t.Helper()
		v, _ := st.ClusterSettingsVersion(ctx)
		if _, err := st.PutClusterSettings(ctx, v, body, "test", ""); err != nil {
			t.Fatal(err)
		}
	}
	cur, _ := st.ClusterSettings(ctx)

	w.check(ctx) // nothing changed
	if len(lived)+len(restarts) != 0 {
		t.Fatalf("acted on no change: %v %v", lived, restarts)
	}

	put(strings.Replace(cur.Body, "injection: flag", "injection: block", 1))
	w.check(ctx)
	if len(restarts) != 0 || len(lived) != 1 || lived[0][0] != "guard" {
		t.Fatalf("a guard change: lived %v restarts %v", lived, restarts)
	}

	cur, _ = st.ClusterSettings(ctx)
	put(strings.Replace(cur.Body, "retries: 2", "retries: 4", 1))
	w.check(ctx)
	if len(restarts) != 1 || !strings.Contains(restarts[0], "router") || w.cur.cfg.Router.Retries != 4 {
		t.Fatalf("a router change: restarts %v retries %d", restarts, w.cur.cfg.Router.Retries)
	}

	// A machine's own key, in its file.
	_ = os.WriteFile(path, []byte(strings.Replace(mustRead(t, path), `":8080"`, `":8090"`, 1)), 0o600)
	w.check(ctx)
	if len(restarts) != 2 || !strings.Contains(restarts[1], "listen") {
		t.Fatalf("a listener change: %v", restarts)
	}

	// Settings that do not load are not put in force.
	cur, _ = st.ClusterSettings(ctx)
	put(cur.Body + "control:\n  timezone: Mars/Olympus\n")
	w.check(ctx)
	if len(restarts) != 2 || w.cur.cfg.Control.Timezone != "" {
		t.Errorf("bad settings were applied: %v %q", restarts, w.cur.cfg.Control.Timezone)
	}
}

func TestAClusterDocumentCannotSetAMachinesKeys(t *testing.T) {
	path, _ := settingsFixture(t, "")
	if err := checkClusterSettings(path, []byte("listen: \":1\"\n")); err == nil {
		t.Error("listen was accepted")
	}
	if err := checkClusterSettings(path, []byte("control:\n  timezone: Mars/Olympus\n")); err == nil {
		t.Error("a timezone that is not one was accepted")
	}
	if err := checkClusterSettings(path, []byte("router:\n  retries: 3\n")); err != nil {
		t.Error(err)
	}
}