Say max_retries is the total attempt count, not a retry count (closes #316)

The delivery core makes max_retries attempts in total: a fresh delivery
starts at attempt one and gives up once the attempt number reaches
max_retries, so 3 is three attempts, not four, and 0 is special-cased to
a single fire-and-forget attempt with no retries and no circuit breaker.
The create and edit target forms called it "Max retries" with no total,
and the README data-model row called it "maximum retry attempts", so an
operator wanting "try, then retry twice" would enter the wrong number.

Both forms and the README rows now state the number is the total number
of delivery attempts, with the 0 case spelled out. The delivery
arithmetic is unchanged. A UI copy test renders both forms and pins the
shared wording so it cannot drift back to a retry count.

Model: opus-4-8

README.md

@@ -1507,7 +1507,7 @@ events should be forwarded.
 | `type`           | TargetType | One of: `http`, `slack`, `database`, `log` |
 | `active`         | boolean    | Whether deliveries are enabled (default: true) |
 | `config`         | JSON text  | Type-specific configuration |
-| `max_retries`    | integer    | Maximum retry attempts for `http` and `slack` targets (0 = fire-and-forget, >0 = retries with backoff and a circuit breaker). Ignored by `database` and `log` targets |
+| `max_retries`    | integer    | Total delivery attempts for `http` and `slack` targets, not retries on top of the first: 0 is a single fire-and-forget attempt with no retries and no circuit breaker, and a value of N makes N attempts in all, with exponential backoff and a per-target circuit breaker. Ignored by `database` and `log` targets |
 | `max_queue_size` | integer    | Stored and shown on the target's detail view, but not enforced anywhere yet: nothing in the delivery engine consults it. Queue depth is set by the two fixed 10,000-entry channels |
 
 **Relations:** Belongs to Webhook. Has many Deliveries.
@@ -1515,12 +1515,12 @@ events should be forwarded.
 **Target types:**
 
 - **`http`** — Forward the event as an HTTP POST to a configured URL.
-  Behavior depends on `max_retries`: when `max_retries` is 0 (the
+  `max_retries` is the total number of delivery attempts, not retries on
-  default), the target operates in fire-and-forget mode — a single
+  top of the first: when `max_retries` is 0 (the default), the target
-  attempt with no retries and no circuit breaker. When `max_retries` is
+  operates in fire-and-forget mode, a single attempt with no retries and
-  greater than 0, failed deliveries are retried with exponential backoff
+  no circuit breaker; a value of N makes up to N attempts in all,
-  up to `max_retries` attempts, protected by a per-target circuit
+  retrying failed deliveries with exponential backoff and protecting them
-  breaker.
+  with a per-target circuit breaker.
 - **`slack`** — Post the event as a formatted message to a
   Slack-compatible incoming webhook URL (`webhookUrl` in `config`). It
   is built on the same HTTP core as `http` and honours `max_retries`

internal/database/database.go

@@ -17,12 +17,12 @@ import (
 	"gorm.io/gorm"
 	"sneak.berlin/go/webhooker/internal/banner"
 	"sneak.berlin/go/webhooker/internal/config"
-	"sneak.berlin/go/webhooker/internal/datadir"
 	"sneak.berlin/go/webhooker/internal/gormlog"
 	"sneak.berlin/go/webhooker/internal/logger"
 )
 
 const (
+	dataDirPerm       = 0750
 	randomPasswordLen = 16
 	sessionKeyLen     = 32
 )
@@ -185,9 +185,7 @@ func (d *Database) connect() error {
 // caller's decision.
 func (d *Database) connectTo(dataDir string) error {
 	// Ensure the data directory exists before opening the database.
-	// datadir.DirPerm is the single source of the directory mode; this
+	err := os.MkdirAll(dataDir, dataDirPerm)
-	// package creates the directory too, since either may run first.
-	err := os.MkdirAll(dataDir, datadir.DirPerm)
 	if err != nil {
 		return fmt.Errorf(
 			"creating data directory %s: %w",

internal/database/webhook_db_manager.go

@@ -13,7 +13,6 @@ import (
 	"gorm.io/driver/sqlite"
 	"gorm.io/gorm"
 	"sneak.berlin/go/webhooker/internal/config"
-	"sneak.berlin/go/webhooker/internal/datadir"
 	"sneak.berlin/go/webhooker/internal/gormlog"
 	"sneak.berlin/go/webhooker/internal/logger"
 )
@@ -54,9 +53,8 @@ func NewWebhookDBManager(
 		log:     params.Logger.Get(),
 	}
 
-	// Create data directory if it doesn't exist. datadir.DirPerm is the
+	// Create data directory if it doesn't exist
-	// single source of the directory mode; either package may run first.
+	err := os.MkdirAll(m.dataDir, dataDirPerm)
-	err := os.MkdirAll(m.dataDir, datadir.DirPerm)
 	if err != nil {
 		return nil, fmt.Errorf(
 			"creating data directory %s: %w",

internal/datadir/lock.go

@@ -29,11 +29,9 @@ import (
 // process that was killed with SIGKILL blocks nothing.
 const LockFileName = "webhooker.lock"
 
-// DirPerm is the mode DATA_DIR is created with. It is the single
+// dirPerm is the mode Acquire creates DATA_DIR with. It matches what
-// source of that mode: internal/database consumes it rather than
+// internal/database uses, since whichever runs first creates it.
-// keeping its own copy, so the two packages that both create the
+const dirPerm = 0o750
-// directory cannot drift into disagreeing about its permissions.
-const DirPerm = 0o750
 
 // ErrLocked reports that another live process holds the data
 // directory. Callers that need to know whether a deployment is running
@@ -66,7 +64,7 @@ func Acquire(dir string) (*Lock, error) {
 		return nil, ErrNoDir
 	}
 
-	err := os.MkdirAll(dir, DirPerm)
+	err := os.MkdirAll(dir, dirPerm)
 	if err != nil {
 		return nil, fmt.Errorf(
 			"creating data directory %s: %w", dir, err,

internal/handlers/ui_copy_test.go

@@ -300,3 +300,80 @@ func TestEntrypointCopyButtonIsProgressiveEnhancement(t *testing.T) {
 		"the page must render to completion, not abort partway",
 	)
 }
+
+// maxRetriesHelp is the wording both target forms must carry. The
+// delivery core makes max_retries attempts in total, not that many
+// retries on top of a first try (a fresh delivery starts at attempt 1
+// and target_http gives up once the attempt number reaches
+// max_retries), and 0 is special-cased to a single fire-and-forget
+// attempt with no circuit breaker.
+const maxRetriesHelp = "This is the total number of delivery attempts, " +
+	"not retries on top of the first: a value of 3 makes three attempts " +
+	"in all. 0 means a single attempt with no retries and no circuit " +
+	"breaker."
+
+// TestTargetFormMaxRetriesCopyMatchesBehaviour pins the max_retries
+// help text on both the create form (the add-target form on the webhook
+// detail page) and the edit form, so the copy cannot drift back to
+// calling the number a retry count.
+func TestTargetFormMaxRetriesCopyMatchesBehaviour(t *testing.T) {
+	t.Parallel()
+
+	var h *handlers.Handlers
+
+	var sess *session.Session
+
+	app := newTestApp(t, &h, &sess)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	webhook := &database.Webhook{Name: "wh", RetentionDays: 14}
+	webhook.ID = testWebhookID
+
+	entrypoint := database.Entrypoint{Path: "abc123"}
+	entrypoint.ID = "ep-1"
+
+	createBody := renderPage(
+		t, h, sess, "source_detail.html", map[string]any{
+			dataKeyWebhook: webhook,
+			"Entrypoints": handlers.NewEntrypointViews(
+				[]database.Entrypoint{entrypoint},
+			),
+			"Targets": delivery.NewTargetViews(nil),
+			"Events":  []database.Event{},
+			"BaseURL": "https://hooks.example.com",
+		},
+	)
+
+	assert.Contains(
+		t, createBody, maxRetriesHelp,
+		"the add-target form must explain max_retries as total attempts",
+	)
+
+	// A slack target exercises the same max_retries field while needing
+	// only Config.URL from the edit template, so the test data stays
+	// minimal. The Target key mirrors the field names the template reads
+	// off the handler's view value.
+	editBody := renderPage(
+		t, h, sess, "target_edit.html", map[string]any{
+			dataKeyWebhook: webhook,
+			"Target": map[string]any{
+				"ID":         "tg-1",
+				"Name":       "t",
+				"Type":       "slack",
+				"Active":     true,
+				"MaxRetries": 3,
+				"Config": map[string]any{
+					"URL": "https://hooks.slack.com/services/x",
+				},
+			},
+			dataKeyError: "",
+		},
+	)
+
+	assert.Contains(
+		t, editBody, maxRetriesHelp,
+		"the target edit form must explain max_retries as total attempts",
+	)
+}

templates/source_detail.html

@@ -120,10 +120,13 @@
                         <label class="text-sm text-gray-700">Timeout (seconds, blank = default):</label>
                         <input type="number" name="timeout" min="0" max="300" :disabled="targetType !== 'http'" class="input text-sm w-24">
                     </div>
-                    <div x-show="targetType === 'http'" class="flex gap-2 items-center">
+                    <div x-show="targetType === 'http'">
-                        <label class="text-sm text-gray-700">Max retries (0 = fire-and-forget):</label>
+                        <div class="flex gap-2 items-center">
+                            <label class="text-sm text-gray-700">Max retries:</label>
                             <input type="number" name="max_retries" value="0" min="0" max="20" class="input text-sm w-24">
                         </div>
+                        <p class="text-xs text-gray-500 mt-1">This is the total number of delivery attempts, not retries on top of the first: a value of 3 makes three attempts in all. 0 means a single attempt with no retries and no circuit breaker.</p>
+                    </div>
                     <div x-show="targetType === 'slack'">
                         <input type="url" name="url" placeholder="https://hooks.slack.com/services/..." :disabled="targetType !== 'slack'" class="input text-sm">
                         <p class="text-xs text-gray-500 mt-1">Slack or Mattermost incoming webhook URL. Payloads are pretty-printed in code blocks.</p>

templates/target_edit.html

@@ -69,7 +69,7 @@
             <div class="form-group">
                 <label for="max_retries" class="label">Max retries</label>
                 <input type="number" id="max_retries" name="max_retries" value="{{.Target.MaxRetries}}" min="0" max="20" class="input">
-                <p class="text-xs text-gray-500 mt-1">0 is fire-and-forget: one attempt, no circuit breaker.</p>
+                <p class="text-xs text-gray-500 mt-1">This is the total number of delivery attempts, not retries on top of the first: a value of 3 makes three attempts in all. 0 means a single attempt with no retries and no circuit breaker.</p>
             </div>
             {{end}}