fix: harden DynDNS recovery and publish v1.5.1

internal/hetzner/client.go

@@ -11,11 +11,15 @@ import (
 	"strconv"
 	"strings"
 	"time"
+
+	"github.com/root-kdw12/hetzner-api-dyndns-records-webinterface/internal/netresolve"
 )
 
 type Client struct {
-	baseURL string
-	http    *http.Client
+	baseURL            string
+	http               *http.Client
+	actionPollInterval time.Duration
+	actionTimeout      time.Duration
 }
 
 type Zone struct {
@@ -44,6 +48,8 @@ type APIError struct {
 	Message string
 }
 
+func (e *APIError) HTTPStatusCode() int { return e.Status }
+
 func (e *APIError) Error() string {
 	if e.Code != "" {
 		return fmt.Sprintf("Hetzner API %d (%s): %s", e.Status, e.Code, e.Message)
@@ -52,10 +58,16 @@ func (e *APIError) Error() string {
 }
 
 func New(baseURL string) *Client {
+	transport := http.DefaultTransport.(*http.Transport).Clone()
+	transport.DialContext = netresolve.New().DialContext
+	transport.IdleConnTimeout = 30 * time.Second
 	return &Client{
-		baseURL: strings.TrimRight(baseURL, "/"),
+		baseURL:            strings.TrimRight(baseURL, "/"),
+		actionPollInterval: 500 * time.Millisecond,
+		actionTimeout:      20 * time.Second,
 		http: &http.Client{
-			Timeout: 15 * time.Second,
+			Transport: transport,
+			Timeout:   15 * time.Second,
 			CheckRedirect: func(_ *http.Request, _ []*http.Request) error {
 				return http.ErrUseLastResponse
 			},
@@ -64,6 +76,8 @@ func New(baseURL string) *Client {
 }
 
 func (c *Client) ListZones(ctx context.Context, token string) ([]Zone, error) {
+	ctx, cancel := context.WithTimeout(ctx, 30*time.Second)
+	defer cancel()
 	var result []Zone
 	for page := 1; ; page++ {
 		var response struct {
@@ -87,12 +101,17 @@ func (c *Client) ListZones(ctx context.Context, token string) ([]Zone, error) {
 		if response.Meta.Pagination.NextPage == nil {
 			break
 		}
+		if *response.Meta.Pagination.NextPage <= page {
+			return nil, fmt.Errorf("Hetzner API pagination did not advance beyond page %d", page)
+		}
 		page = *response.Meta.Pagination.NextPage - 1
 	}
 	return result, nil
 }
 
 func (c *Client) ListRRSets(ctx context.Context, token, zoneID string) ([]RRSet, error) {
+	ctx, cancel := context.WithTimeout(ctx, 30*time.Second)
+	defer cancel()
 	var result []RRSet
 	for page := 1; ; page++ {
 		var response struct {
@@ -111,6 +130,9 @@ func (c *Client) ListRRSets(ctx context.Context, token, zoneID string) ([]RRSet,
 		if response.Meta.Pagination.NextPage == nil {
 			break
 		}
+		if *response.Meta.Pagination.NextPage <= page {
+			return nil, fmt.Errorf("Hetzner API pagination did not advance beyond page %d", page)
+		}
 		page = *response.Meta.Pagination.NextPage - 1
 	}
 	return result, nil
@@ -123,25 +145,25 @@ func (c *Client) CreateRRSet(ctx context.Context, token, zoneID, name, recordTyp
 		TTL     int      `json:"ttl"`
 		Records []Record `json:"records"`
 	}{Name: name, Type: recordType, TTL: ttl, Records: records}
-	return c.doJSON(ctx, token, http.MethodPost, "/zones/"+url.PathEscape(zoneID)+"/rrsets", body, nil)
+	return c.doAction(ctx, token, http.MethodPost, "/zones/"+url.PathEscape(zoneID)+"/rrsets", body)
 }
 
 func (c *Client) SetRRSetRecords(ctx context.Context, token, zoneID, name, recordType string, records []Record) error {
 	body := struct {
 		Records []Record `json:"records"`
 	}{Records: records}
-	return c.doJSON(ctx, token, http.MethodPost, rrsetPath(zoneID, name, recordType)+"/actions/set_records", body, nil)
+	return c.doAction(ctx, token, http.MethodPost, rrsetPath(zoneID, name, recordType)+"/actions/set_records", body)
 }
 
 func (c *Client) ChangeRRSetTTL(ctx context.Context, token, zoneID, name, recordType string, ttl int) error {
 	body := struct {
 		TTL int `json:"ttl"`
 	}{TTL: ttl}
-	return c.doJSON(ctx, token, http.MethodPost, rrsetPath(zoneID, name, recordType)+"/actions/change_ttl", body, nil)
+	return c.doAction(ctx, token, http.MethodPost, rrsetPath(zoneID, name, recordType)+"/actions/change_ttl", body)
 }
 
 func (c *Client) DeleteRRSet(ctx context.Context, token, zoneID, name, recordType string) error {
-	return c.doJSON(ctx, token, http.MethodDelete, rrsetPath(zoneID, name, recordType), nil, nil)
+	return c.doAction(ctx, token, http.MethodDelete, rrsetPath(zoneID, name, recordType), nil)
 }
 
 func (c *Client) UpdateRecordComments(ctx context.Context, token, zoneID, name, recordType string, records []Record) error {
@@ -160,7 +182,74 @@ func (c *Client) UpdateRecordComments(ctx context.Context, token, zoneID, name,
 			Comment string `json:"comment"`
 		}{Value: record.Value, Comment: record.Comment})
 	}
-	return c.doJSON(ctx, token, http.MethodPost, rrsetPath(zoneID, name, recordType)+"/actions/update_records", body, nil)
+	return c.doAction(ctx, token, http.MethodPost, rrsetPath(zoneID, name, recordType)+"/actions/update_records", body)
+}
+
+// ActionError reports a failed asynchronous operation even when its HTTP
+// request was accepted successfully.
+type ActionError struct {
+	ID      int64
+	Code    string
+	Message string
+}
+
+func (e *ActionError) ProviderActionID() int64 { return e.ID }
+
+func (e *ActionError) Error() string {
+	return fmt.Sprintf("Hetzner action %d failed (%s): %s", e.ID, e.Code, e.Message)
+}
+
+type actionResponse struct {
+	Action *struct {
+		ID     int64  `json:"id"`
+		Status string `json:"status"`
+		Error  *struct {
+			Code    string `json:"code"`
+			Message string `json:"message"`
+		} `json:"error"`
+	} `json:"action"`
+}
+
+func (c *Client) doAction(ctx context.Context, token, method, path string, body any) error {
+	ctx, cancel := context.WithTimeout(ctx, c.actionTimeout)
+	defer cancel()
+	var response actionResponse
+	if err := c.doJSON(ctx, token, method, path, body, &response); err != nil {
+		return err
+	}
+	var actionID int64
+	for {
+		action := response.Action
+		if action == nil || action.ID <= 0 || (actionID != 0 && action.ID != actionID) {
+			return fmt.Errorf("Hetzner API returned a missing or invalid action")
+		}
+		actionID = action.ID
+		switch action.Status {
+		case "success":
+			return nil
+		case "error":
+			failure := &ActionError{ID: action.ID, Code: "unknown", Message: "operation failed"}
+			if action.Error != nil {
+				failure.Code, failure.Message = action.Error.Code, action.Error.Message
+			}
+			return failure
+		case "running":
+		default:
+			return fmt.Errorf("Hetzner action %d returned an invalid status", actionID)
+		}
+		timer := time.NewTimer(c.actionPollInterval)
+		select {
+		case <-ctx.Done():
+			timer.Stop()
+			return fmt.Errorf("wait for Hetzner action %d: %w", actionID, ctx.Err())
+		case <-timer.C:
+		}
+		response = actionResponse{}
+		// Poll the accepted operation; never repeat a write whose outcome is unknown.
+		if err := c.doJSON(ctx, token, http.MethodGet, "/zones/actions/"+strconv.FormatInt(actionID, 10), nil, &response); err != nil {
+			return fmt.Errorf("check Hetzner action %d: %w", actionID, err)
+		}
+	}
 }
 
 func (c *Client) doJSON(ctx context.Context, token, method, path string, requestBody any, responseBody any) error {
@@ -186,14 +275,17 @@ func (c *Client) doJSON(ctx context.Context, token, method, path string, request
 		return fmt.Errorf("request Hetzner API: %w", err)
 	}
 	defer resp.Body.Close()
-	content, err := io.ReadAll(io.LimitReader(resp.Body, 1<<20))
+	content, err := io.ReadAll(io.LimitReader(resp.Body, (1<<20)+1))
 	if err != nil {
 		return fmt.Errorf("read Hetzner API response: %w", err)
 	}
+	if len(content) > 1<<20 {
+		return fmt.Errorf("Hetzner API response exceeds size limit")
+	}
 	if resp.StatusCode < http.StatusOK || resp.StatusCode >= http.StatusMultipleChoices {
 		return decodeAPIError(resp.StatusCode, content)
 	}
-	if responseBody != nil && len(content) > 0 {
+	if responseBody != nil {
 		if err := json.Unmarshal(content, responseBody); err != nil {
 			return fmt.Errorf("decode Hetzner API response: %w", err)
 		}

internal/hetzner/client_test.go

@@ -3,11 +3,107 @@ package hetzner
 import (
 	"context"
 	"encoding/json"
+	"errors"
 	"net/http"
 	"net/http/httptest"
 	"testing"
+	"time"
+
+	"github.com/root-kdw12/hetzner-api-dyndns-records-webinterface/internal/diagnostics"
 )
 
+func TestDNSWritesWaitForActionCompletion(t *testing.T) {
+	operations := map[string]func(*Client) error{
+		"create": func(c *Client) error {
+			return c.CreateRRSet(context.Background(), "token", "123", "home", "A", 60, nil)
+		},
+		"records": func(c *Client) error {
+			return c.SetRRSetRecords(context.Background(), "token", "123", "home", "A", nil)
+		},
+		"ttl": func(c *Client) error { return c.ChangeRRSetTTL(context.Background(), "token", "123", "home", "A", 60) },
+		"comments": func(c *Client) error {
+			return c.UpdateRecordComments(context.Background(), "token", "123", "home", "A", nil)
+		},
+		"delete": func(c *Client) error { return c.DeleteRRSet(context.Background(), "token", "123", "home", "A") },
+	}
+	for name, operation := range operations {
+		t.Run(name, func(t *testing.T) {
+			for _, status := range []string{"success", "error"} {
+				t.Run(status, func(t *testing.T) {
+					var writes, polls int
+					api := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+						if r.Method != http.MethodGet {
+							writes++
+							_, _ = w.Write([]byte(`{"action":{"id":42,"status":"running"}}`))
+							return
+						}
+						if r.URL.Path != "/zones/actions/42" || r.Header.Get("Authorization") != "Bearer token" {
+							t.Errorf("incorrect action polling request: %s", r.URL.Path)
+						}
+						polls++
+						if polls == 1 {
+							_, _ = w.Write([]byte(`{"action":{"id":42,"status":"running"}}`))
+						} else {
+							_, _ = w.Write([]byte(`{"action":{"id":42,"status":"` + status + `","error":{"code":"action_failed","message":"failed later"}}}`))
+						}
+					}))
+					defer api.Close()
+					client := New(api.URL)
+					client.actionPollInterval = time.Millisecond
+					err := operation(client)
+					if status == "success" && err != nil {
+						t.Fatal(err)
+					}
+					var actionErr *ActionError
+					if status == "error" && (!errors.As(err, &actionErr) || actionErr.Code != "action_failed") {
+						t.Fatalf("lost action failure: %v", err)
+					}
+					if status == "error" && (diagnostics.Failure(err) != "provider_action" || diagnostics.ActionID(err) != 42) {
+						t.Fatal("action failure missing from safe diagnostics")
+					}
+					if writes != 1 || polls != 2 {
+						t.Fatalf("returned too early or repeated write: writes=%d polls=%d", writes, polls)
+					}
+				})
+			}
+		})
+	}
+}
+
+func TestActionWaitIsBoundedAndRejectsMalformedResponses(t *testing.T) {
+	for _, body := range []string{"", `{}`, `{"action":{"id":42,"status":"unknown"}}`, `{"action":{"status":"running"}}`, `{"action":{"id":42,"status":"running"}}`} {
+		t.Run(body, func(t *testing.T) {
+			api := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { _, _ = w.Write([]byte(body)) }))
+			defer api.Close()
+			client := New(api.URL)
+			client.actionPollInterval = time.Millisecond
+			client.actionTimeout = 30 * time.Millisecond
+			if err := client.DeleteRRSet(context.Background(), "token", "123", "home", "A"); err == nil {
+				t.Fatal("unconfirmed operation reported success")
+			}
+			ctx, cancel := context.WithCancel(context.Background())
+			cancel()
+			if err := client.DeleteRRSet(ctx, "token", "123", "home", "A"); !errors.Is(err, context.Canceled) {
+				t.Fatalf("cancellation lost: %v", err)
+			}
+		})
+	}
+}
+
+func TestPaginationRejectsRepeatedPage(t *testing.T) {
+	api := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		_, _ = w.Write([]byte(`{"zones":[],"rrsets":[],"meta":{"pagination":{"next_page":1}}}`))
+	}))
+	defer api.Close()
+	client := New(api.URL)
+	if _, err := client.ListZones(context.Background(), "token"); err == nil {
+		t.Fatal("repeated zones page accepted")
+	}
+	if _, err := client.ListRRSets(context.Background(), "token", "123"); err == nil {
+		t.Fatal("repeated RRsets page accepted")
+	}
+}
+
 func TestSetRRSetRecordsUsesSetRecordsAction(t *testing.T) {
 	t.Parallel()
 	type capturedRequest struct {
@@ -33,7 +129,7 @@ func TestSetRRSetRecordsUsesSetRecordsAction(t *testing.T) {
 		}
 		w.Header().Set("Content-Type", "application/json")
 		w.WriteHeader(http.StatusCreated)
-		_, _ = w.Write([]byte(`{"action":{"status":"running"}}`))
+		_, _ = w.Write([]byte(`{"action":{"id":42,"status":"success"}}`))
 	}))
 	defer api.Close()
 
@@ -77,6 +173,7 @@ func TestUpdateRecordCommentsAlwaysSendsComment(t *testing.T) {
 		body["path"] = r.URL.Path
 		captured <- body
 		w.WriteHeader(http.StatusCreated)
+		_, _ = w.Write([]byte(`{"action":{"id":42,"status":"success"}}`))
 	}))
 	defer api.Close()
 
@@ -115,6 +212,7 @@ func TestChangeRRSetTTLUsesDedicatedAction(t *testing.T) {
 		body["path"] = r.URL.Path
 		captured <- body
 		w.WriteHeader(http.StatusCreated)
+		_, _ = w.Write([]byte(`{"action":{"id":42,"status":"success"}}`))
 	}))
 	defer api.Close()
 
@@ -133,7 +231,8 @@ func TestDeleteRRSetUsesRRSetEndpoint(t *testing.T) {
 	captured := make(chan *http.Request, 1)
 	api := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		captured <- r
-		w.WriteHeader(http.StatusNoContent)
+		w.WriteHeader(http.StatusOK)
+		_, _ = w.Write([]byte(`{"action":{"id":42,"status":"success"}}`))
 	}))
 	defer api.Close()