fix(httpclient): replace DefaultClient with timed clients and retry

Пакет httpclient: timeout 45s, idle pool, DoWithRetry. Scheduler и nodecli
используют retry; pipeline/asnresolve/jobs — httpclient.New вместо DefaultClient.

Co-authored-by: Cursor <[email protected]>

internal/asnresolve/ripestat.go

@@ -13,6 +13,8 @@ import (
 	"strconv"
 	"strings"
 	"time"
+
+	"evobgp/internal/httpclient"
 )
 
 // DefaultRIPEStatURL is the RIPEstat announced-prefixes data call (no API key).
@@ -24,7 +26,7 @@ const DefaultASOverviewURL = "https://stat.ripe.net/data/as-overview/data.json"
 // AnnouncedPrefixes returns currently announced IPv4/IPv6 prefixes for the ASN (best-effort via RIPEstat).
 func AnnouncedPrefixes(ctx context.Context, hc *http.Client, asn int64) ([]netip.Prefix, error) {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	base := strings.TrimSpace(os.Getenv("EVOBGP_RIPESTAT_ANNOUNCED_PREFIXES_URL"))
 	if base == "" {
@@ -86,7 +88,7 @@ func AnnouncedPrefixes(ctx context.Context, hc *http.Client, asn int64) ([]netip
 // ASHolderName returns the holder / organization label for the ASN from RIPEstat as-overview (best-effort).
 func ASHolderName(ctx context.Context, hc *http.Client, asn int64) (string, error) {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	base := strings.TrimSpace(os.Getenv("EVOBGP_RIPESTAT_AS_OVERVIEW_URL"))
 	if base == "" {

internal/httpapi/bootstrap.go

@@ -7,6 +7,7 @@ import (
 	"time"
 
 	"evobgp/internal/db"
+	"evobgp/internal/httpclient"
 	"evobgp/internal/jobs"
 	"evobgp/internal/observability"
 	"evobgp/internal/repository"
@@ -17,7 +18,7 @@ import (
 
 // NewCDNHTTPClient returns the shared HTTP client for CDN and preview fetches (PERF-02 / ERR-03).
 func NewCDNHTTPClient() *http.Client {
-	return &http.Client{Timeout: 45 * time.Second}
+	return httpclient.New(httpclient.DefaultTimeout)
 }
 
 // BootstrapWorkers opens the same store.Backend and jobs.Registry as New (without HTTP or bundle keys).

internal/httpclient/httpclient.go

@@ -0,0 +1,68 @@
+// Package httpclient provides shared HTTP clients and retry helpers for outbound calls.
+package httpclient
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"net/http"
+	"time"
+)
+
+const DefaultTimeout = 45 * time.Second
+
+// New returns an HTTP client with timeout and tuned idle connection pooling.
+func New(timeout time.Duration) *http.Client {
+	if timeout <= 0 {
+		timeout = DefaultTimeout
+	}
+	tr := http.DefaultTransport.(*http.Transport).Clone()
+	tr.MaxIdleConns = 100
+	tr.MaxIdleConnsPerHost = 10
+	return &http.Client{Timeout: timeout, Transport: tr}
+}
+
+// DoWithRetry executes hc.Do(req) up to maxAttempts times with linear backoff.
+func DoWithRetry(ctx context.Context, hc *http.Client, req *http.Request, maxAttempts int) (*http.Response, error) {
+	if hc == nil {
+		hc = New(0)
+	}
+	if maxAttempts <= 0 {
+		maxAttempts = 3
+	}
+	var lastErr error
+	for attempt := 0; attempt < maxAttempts; attempt++ {
+		if attempt > 0 {
+			wait := time.Duration(attempt) * 2 * time.Second
+			select {
+			case <-ctx.Done():
+				return nil, ctx.Err()
+			case <-time.After(wait):
+			}
+			if req.GetBody != nil {
+				body, err := req.GetBody()
+				if err != nil {
+					return nil, err
+				}
+				req.Body = body
+			}
+		}
+		reqClone := req.Clone(ctx)
+		resp, err := hc.Do(reqClone)
+		if err != nil {
+			lastErr = err
+			continue
+		}
+		if resp.StatusCode >= 500 {
+			_, _ = io.Copy(io.Discard, resp.Body)
+			_ = resp.Body.Close()
+			lastErr = fmt.Errorf("httpclient: upstream %s", resp.Status)
+			continue
+		}
+		return resp, nil
+	}
+	if lastErr != nil {
+		return nil, lastErr
+	}
+	return nil, fmt.Errorf("httpclient: request failed after %d attempts", maxAttempts)
+}

internal/httpclient/httpclient_test.go

@@ -0,0 +1,39 @@
+package httpclient
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+)
+
+func TestDoWithRetry_retriesOn500(t *testing.T) {
+	var calls int
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		calls++
+		if calls < 3 {
+			http.Error(w, "fail", http.StatusBadGateway)
+			return
+		}
+		w.WriteHeader(http.StatusOK)
+		_, _ = w.Write([]byte("ok"))
+	}))
+	defer srv.Close()
+
+	req, err := http.NewRequest(http.MethodGet, srv.URL, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	resp, err := DoWithRetry(context.Background(), New(5*time.Second), req, 3)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer func() { _ = resp.Body.Close() }()
+	if resp.StatusCode != http.StatusOK {
+		t.Fatalf("status %d", resp.StatusCode)
+	}
+	if calls != 3 {
+		t.Fatalf("want 3 calls, got %d", calls)
+	}
+}

internal/jobs/worker.go

@@ -13,6 +13,7 @@ import (
 
 	"evobgp/internal/birddeploy"
 	"evobgp/internal/birdfmt"
+	"evobgp/internal/httpclient"
 	"evobgp/internal/nodedispatch"
 	"evobgp/internal/observability"
 	"evobgp/internal/pipeline"
@@ -70,7 +71,7 @@ type revisionLogEntry struct {
 	Message        string   `json:"message"`
 }
 
-var defaultWorkerHTTP = &http.Client{Timeout: 45 * time.Second}
+var defaultWorkerHTTP = httpclient.New(httpclient.DefaultTimeout)
 
 func (w *Worker) httpClient() *http.Client {
 	if w != nil && w.HTTPClient != nil {

internal/nodecli/commands.go

@@ -16,6 +16,7 @@ import (
 
 	"evobgp/internal/birdfmt"
 	"evobgp/internal/bundle"
+	"evobgp/internal/httpclient"
 	"evobgp/internal/signing"
 )
 
@@ -55,6 +56,10 @@ func CmdPullBundle(args []string) int {
 	return 0
 }
 
+func nodeHTTPClient() *http.Client {
+	return httpclient.New(60 * time.Second)
+}
+
 func fetchLatestRevision(base, token, speaker string) (string, error) {
 	u := strings.TrimRight(base, "/") + "/v1/speakers/" + speaker + "/revisions/latest"
 	req, err := http.NewRequest(http.MethodGet, u, nil)
@@ -62,7 +67,9 @@ func fetchLatestRevision(base, token, speaker string) (string, error) {
 		return "", err
 	}
 	req.Header.Set("Authorization", "Bearer "+token)
-	resp, err := http.DefaultClient.Do(req)
+	ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
+	defer cancel()
+	resp, err := httpclient.DoWithRetry(ctx, nodeHTTPClient(), req, 3)
 	if err != nil {
 		return "", err
 	}
@@ -90,7 +97,9 @@ func fetchBundle(base, token, speaker, revision string) ([]byte, error) {
 		return nil, err
 	}
 	req.Header.Set("Authorization", "Bearer "+token)
-	resp, err := http.DefaultClient.Do(req)
+	ctx, cancel := context.WithTimeout(context.Background(), 120*time.Second)
+	defer cancel()
+	resp, err := httpclient.DoWithRetry(ctx, nodeHTTPClient(), req, 3)
 	if err != nil {
 		return nil, err
 	}

internal/pipeline/prefetch.go

@@ -7,13 +7,14 @@ import (
 	"strings"
 	"time"
 
+	"evobgp/internal/httpclient"
 	"evobgp/internal/store"
 )
 
 // PrefetchCDNSourceETags performs conditional GETs for CDN sources; on 200 parses CIDRs into module_prefix_snapshot.
 func PrefetchCDNSourceETags(ctx context.Context, st store.Backend, hc *http.Client) error {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	tenants, err := st.ListTenantIDs()
 	if err != nil {

internal/pipeline/refresh.go

@@ -19,6 +19,7 @@ import (
 	"time"
 
 	"evobgp/internal/birdfmt"
+	"evobgp/internal/httpclient"
 	"evobgp/internal/observability"
 	"evobgp/internal/store"
 
@@ -50,7 +51,7 @@ func MaterializedASPrefixKey(asn int64) string {
 // It does not create a new config revision.
 func RefreshModuleIngest(ctx context.Context, st store.Backend, hc *http.Client, tenantID, moduleID string) error {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	start := time.Now()
 	mod, err := st.GetModule(tenantID, moduleID)
@@ -84,7 +85,7 @@ func RefreshModuleIngest(ctx context.Context, st store.Backend, hc *http.Client,
 // If materialized prefixes are unchanged, returns latest revision id without creating a duplicate.
 func RenderTenantRevision(ctx context.Context, st store.Backend, hc *http.Client, tenantID, triggerModuleID string) (revisionID string, err error) {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	agg, err := aggregateTenantPrefixRowsAll(ctx, st, hc, tenantID)
 	if err != nil {
@@ -117,7 +118,7 @@ func RenderTenantRevision(ctx context.Context, st store.Backend, hc *http.Client
 func RenderTenantRevisionFromPrefixes(ctx context.Context, st store.Backend, hc *http.Client, tenantID, triggerModuleID string, rows []store.PrefixRow) (revisionID string, err error) {
 	_ = ctx
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	agg := append([]store.PrefixRow(nil), rows...)
 	rawCount := len(agg)

internal/pipeline/tenant_refresh.go

@@ -7,13 +7,14 @@ import (
 	"strings"
 	"sync"
 
+	"evobgp/internal/httpclient"
 	"evobgp/internal/store"
 )
 
 // RefreshTenantModules ingests all listed modules in parallel and updates per-module snapshots.
 func RefreshTenantModules(ctx context.Context, st store.Backend, hc *http.Client, tenantID string, moduleIDs []string) error {
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
 	var ids []string
 	seen := make(map[string]struct{})

internal/scheduler/run.go

@@ -14,6 +14,7 @@ import (
 
 	"evobgp/internal/broker"
 	"evobgp/internal/config"
+	"evobgp/internal/httpclient"
 	"evobgp/internal/jobs"
 	"evobgp/internal/pipeline"
 	"evobgp/internal/store"
@@ -108,6 +109,9 @@ func postTenantRefresh(ctx context.Context, deps *Deps, moduleIDs []string, idem
 	if err != nil {
 		return err
 	}
+	req.GetBody = func() (io.ReadCloser, error) {
+		return io.NopCloser(bytes.NewReader(body)), nil
+	}
 	req.Header.Set("Authorization", "Bearer "+strings.TrimSpace(deps.APIToken))
 	req.Header.Set("Content-Type", "application/json")
 	if idempotencyKey != "" {
@@ -115,9 +119,9 @@ func postTenantRefresh(ctx context.Context, deps *Deps, moduleIDs []string, idem
 	}
 	hc := deps.HTTP
 	if hc == nil {
-		hc = http.DefaultClient
+		hc = httpclient.New(httpclient.DefaultTimeout)
 	}
-	resp, err := hc.Do(req)
+	resp, err := httpclient.DoWithRetry(ctx, hc, req, 3)
 	if err != nil {
 		return err
 	}