pangolin/server/internal/alert/notifier_test.go

package alert_test

import (
	"context"
	"encoding/json"
	"io"
	"net/http"
	"net/http/httptest"
	"strings"
	"sync/atomic"
	"testing"

	"github.com/alicebob/miniredis/v2"
	"github.com/redis/go-redis/v9"

	"github.com/wangjia/pangolin/server/internal/alert"
)

// ─────────────────────────────────────────────────────────────────────────────
// Test helpers
// ─────────────────────────────────────────────────────────────────────────────

func newTestRedis(t *testing.T) *redis.Client {
	t.Helper()
	mr := miniredis.RunT(t)
	return redis.NewClient(&redis.Options{Addr: mr.Addr()})
}

// tgServer is a tiny Telegram Bot API mock.
type tgServer struct {
	statusCode atomic.Int32 // HTTP status to return; default 200
	callCount  atomic.Int32 // total calls received
	lastBody   atomic.Value // last []byte body received
	srv        *httptest.Server
}

func newTGServer(t *testing.T) *tgServer {
	t.Helper()
	ts := &tgServer{}
	ts.statusCode.Store(http.StatusOK)
	ts.srv = httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		ts.callCount.Add(1)
		body, _ := io.ReadAll(r.Body)
		ts.lastBody.Store(body)
		w.WriteHeader(int(ts.statusCode.Load()))
		w.Write([]byte(`{"ok":true}`)) //nolint:errcheck
	}))
	t.Cleanup(ts.srv.Close)
	return ts
}

// parsedBody parses the last received request body as a map.
func (ts *tgServer) parsedBody(t *testing.T) map[string]string {
	t.Helper()
	raw, _ := ts.lastBody.Load().([]byte)
	if len(raw) == 0 {
		t.Fatal("tgServer: no body received yet")
	}
	var m map[string]string
	if err := json.Unmarshal(raw, &m); err != nil {
		t.Fatalf("tgServer: unmarshal body: %v", err)
	}
	return m
}

// newNotifier creates a TGNotifier pointing at the mock server.
func newNotifier(t *testing.T, ts *tgServer, rdb *redis.Client) *alert.TGNotifier {
	t.Helper()
	return alert.NewTGNotifier(alert.TGConfig{
		BotToken:       "test-token",
		ChatID:         "-1001234567",
		RunbookBaseURL: "https://example.internal/runbook",
		BaseURL:        ts.srv.URL,
	}, rdb, nil)
}

// ─────────────────────────────────────────────────────────────────────────────
// Test: all seven event types render correct templates with runbook anchors
// ─────────────────────────────────────────────────────────────────────────────

func TestAllEventTypesRendered(t *testing.T) {
	tests := []struct {
		eventType     alert.EventType
		wantAnchor    string
		wantTitlePart string // substring expected in the TG message text (HTML-encoded if needed)
	}{
		{alert.EventTypeBlockConfirmed, "#block-confirmed", "判封确认"},
		{alert.EventTypeReplenishFailed, "#replenish-failed", "补新连续失败≥3"},
		// "<" is HTML-escaped to "&lt;" in TG HTML mode — check escaped form.
		{alert.EventTypeWatermarkLow, "#watermark-low", "水位&lt;70%"},
		{alert.EventTypeBreakerTripped, "#breaker-tripped", "熔断触发"},
		{alert.EventTypeProbeAgentLost, "#probe-agent-lost", "探针失联"},
		// ">" is HTML-escaped to "&gt;" in TG HTML mode — check escaped form.
		{alert.EventTypeHeartbeatMissing, "#heartbeat-missing", "心跳缺失&gt;90s"},
		{alert.EventTypeFault, "#node-fault", "故障态"},
	}

	for _, tc := range tests {
		t.Run(string(tc.eventType), func(t *testing.T) {
			rdb := newTestRedis(t)
			ts := newTGServer(t)
			n := newNotifier(t, ts, rdb)

			e := alert.NewEvent(tc.eventType, "node-abc", map[string]string{
				"reason": "test reason",
			})

			ctx := context.Background()
			if err := n.Notify(ctx, e); err != nil {
				t.Fatalf("Notify() returned error: %v", err)
			}

			// Exactly one TG call must have been made.
			if got := ts.callCount.Load(); got != 1 {
				t.Fatalf("TG call count = %d; want 1", got)
			}

			body := ts.parsedBody(t)
			text := body["text"]

			// Message must contain the Chinese event title.
			if !strings.Contains(text, tc.wantTitlePart) {
				t.Errorf("message does not contain %q:\n%s", tc.wantTitlePart, text)
			}

			// Message must contain the runbook anchor.
			if !strings.Contains(text, tc.wantAnchor) {
				t.Errorf("message does not contain runbook anchor %q:\n%s", tc.wantAnchor, text)
			}

			// Message must contain the node ID (internal only — no domain).
			if !strings.Contains(text, "node-abc") {
				t.Errorf("message does not contain node ID:\n%s", text)
			}

			// parse_mode must be HTML.
			if body["parse_mode"] != "HTML" {
				t.Errorf("parse_mode = %q; want HTML", body["parse_mode"])
			}
		})
	}
}

// ─────────────────────────────────────────────────────────────────────────────
// Test: dedup — second message for same (Type, NodeID) within 10 min is suppressed
// ─────────────────────────────────────────────────────────────────────────────

func TestDedupSuppressesSecondMessage(t *testing.T) {
	rdb := newTestRedis(t)
	ts := newTGServer(t)
	n := newNotifier(t, ts, rdb)

	ctx := context.Background()
	// Use a Warning-severity event (WatermarkLow) so dedup applies.
	// Note: WatermarkLow has Warning severity → dedup applies.
	e := alert.NewEvent(alert.EventTypeBlockConfirmed, "node-dup", nil)

	// First call — must go through.
	if err := n.Notify(ctx, e); err != nil {
		t.Fatalf("first Notify() error: %v", err)
	}
	if got := ts.callCount.Load(); got != 1 {
		t.Fatalf("after first call: TG count = %d; want 1", got)
	}

	// Second call with same (Type, NodeID) — must be suppressed (no TG call).
	if err := n.Notify(ctx, e); err != nil {
		t.Fatalf("second Notify() error: %v", err)
	}
	if got := ts.callCount.Load(); got != 1 {
		t.Errorf("after second call: TG count = %d; want still 1 (dedup)", got)
	}

	// Third call with different NodeID — must go through (distinct dedup key).
	e2 := alert.NewEvent(alert.EventTypeBlockConfirmed, "node-other", nil)
	if err := n.Notify(ctx, e2); err != nil {
		t.Fatalf("third Notify() error: %v", err)
	}
	if got := ts.callCount.Load(); got != 2 {
		t.Errorf("after third call (different node): TG count = %d; want 2", got)
	}
}

// ─────────────────────────────────────────────────────────────────────────────
// Test: critical events are never deduplicated — each call goes through
// ─────────────────────────────────────────────────────────────────────────────

func TestCriticalEventsNotDeduped(t *testing.T) {
	rdb := newTestRedis(t)
	ts := newTGServer(t)
	n := newNotifier(t, ts, rdb)

	ctx := context.Background()
	// BreakerTripped is Critical severity — must bypass dedup.
	e := alert.NewEvent(alert.EventTypeBreakerTripped, "node-crit", nil)

	for i := 1; i <= 3; i++ {
		if err := n.Notify(ctx, e); err != nil {
			t.Fatalf("call %d: Notify() error: %v", i, err)
		}
		if got := ts.callCount.Load(); int(got) != i {
			t.Errorf("after call %d: TG count = %d; want %d (no dedup for critical)", i, got, i)
		}
	}
}

// ─────────────────────────────────────────────────────────────────────────────
// Test: TG 5xx triggers retries; after exhausting retries falls back to log;
//       Notify() never returns an error.
// ─────────────────────────────────────────────────────────────────────────────

func TestTG5xxRetriesThenFallsBack(t *testing.T) {
	rdb := newTestRedis(t)
	ts := newTGServer(t)

	// Capture fallback calls.
	var fallbackCalls atomic.Int32
	fallback := &capturingNotifier{
		fn: func(alert.Event) { fallbackCalls.Add(1) },
	}

	n := alert.NewTGNotifier(alert.TGConfig{
		BotToken: "test-token",
		ChatID:   "-1001234567",
		BaseURL:  ts.srv.URL,
	}, rdb, fallback)

	// Configure mock TG server to return 500.
	ts.statusCode.Store(http.StatusInternalServerError)

	ctx := context.Background()
	e := alert.NewEvent(alert.EventTypeFault, "node-fail", map[string]string{"reason": "both fail"})

	// Notify must return nil (not block the scheduler).
	if err := n.Notify(ctx, e); err != nil {
		t.Fatalf("Notify() must not return error; got %v", err)
	}

	// TG must have been called 3 times (1 initial + 2 retries = maxRetries+1).
	if got := ts.callCount.Load(); got != 3 {
		t.Errorf("TG call count = %d; want 3 (1 + 2 retries)", got)
	}

	// Fallback must have been called exactly once.
	if got := fallbackCalls.Load(); got != 1 {
		t.Errorf("fallback call count = %d; want 1", got)
	}
}

// ─────────────────────────────────────────────────────────────────────────────
// Test: LogNotifier always succeeds (used in offline/dev mode)
// ─────────────────────────────────────────────────────────────────────────────

func TestLogNotifier(t *testing.T) {
	n := alert.LogNotifier{}
	ctx := context.Background()

	for _, et := range []alert.EventType{
		alert.EventTypeBlockConfirmed,
		alert.EventTypeReplenishFailed,
		alert.EventTypeWatermarkLow,
		alert.EventTypeBreakerTripped,
		alert.EventTypeProbeAgentLost,
		alert.EventTypeHeartbeatMissing,
		alert.EventTypeFault,
	} {
		e := alert.NewEvent(et, "node-log", nil)
		if err := n.Notify(ctx, e); err != nil {
			t.Errorf("LogNotifier.Notify(%s) error: %v", et, err)
		}
	}
}

// ─────────────────────────────────────────────────────────────────────────────
// Test: RunbookAnchor override takes precedence over type default
// ─────────────────────────────────────────────────────────────────────────────

func TestRunbookAnchorOverride(t *testing.T) {
	rdb := newTestRedis(t)
	ts := newTGServer(t)
	n := newNotifier(t, ts, rdb)

	e := alert.NewEvent(alert.EventTypeFault, "node-anch", nil)
	e.RunbookAnchor = "#custom-anchor"

	if err := n.Notify(context.Background(), e); err != nil {
		t.Fatal(err)
	}

	body := ts.parsedBody(t)
	if !strings.Contains(body["text"], "#custom-anchor") {
		t.Errorf("expected #custom-anchor in message:\n%s", body["text"])
	}
}

// ─────────────────────────────────────────────────────────────────────────────
// Helpers
// ─────────────────────────────────────────────────────────────────────────────

// capturingNotifier is a Notifier that calls fn on each Notify.
type capturingNotifier struct {
	fn func(alert.Event)
}

func (c *capturingNotifier) Notify(_ context.Context, e alert.Event) error {
	c.fn(e)
	return nil
}