Offer rebuild retry for failed creation commands

src/routes/api/provisioning/[id]/retry-rebuild/+server.ts

@@ -0,0 +1,10 @@
+import { json } from '@sveltejs/kit';
+import { requestRetryWithRebuild } from '$lib/server/provisioning/index.js';
+import { kickProvisioning } from '$lib/server/pipeline/worker.js';
+
+export function POST({ params }: { params: { id: string } }) {
+    const result = requestRetryWithRebuild(params.id);
+    if (!result.ok) return json({ error: result.error }, { status: result.status });
+    void kickProvisioning().catch(err => console.error('[provisioning] rebuild retry kick failed:', err));
+    return json(result, { status: 202 });
+}

src/routes/provisioning/[id]/+page.svelte

@@ -59,6 +59,17 @@
     });
     onMount(() => pollVisible(() => { now = Date.now(); return controller.refresh(); }, 5000, false));
     onDestroy(() => controller.dispose());
+    async function retryWithRebuild() {
+        if (!deployment || !detail?.canRetryWithRebuild || view.busy) return;
+        const id = deployment.id;
+        const confirmed = await confirmAction({
+            title: 'Retry creation with a rebuild?',
+            message: `Rebuild ${serverTitle(deployment.server)} (${deployment.server}) using the latest promoted setup. This keeps the same lobby and port, deletes its container and all instance files, and starts a new provisioning operation.\n\nPlayer safety, capacity limits, and protected work checks still apply. The original failure remains in this operation’s history.`,
+            confirmLabel: 'Retry with rebuild', danger: true
+        });
+        if (confirmed && view.id === id && detail?.canRetryWithRebuild) await controller.act('retry-rebuild',
+            'Rebuild retry requested. Follow the linked recovery operation below for progress.');
+    }
     async function overrideSafety() {
         if (!deployment || !canOverride || view.busy || detail?.safetyOverrideUnavailableReason) return;
         const id = deployment.id;
@@ -107,10 +118,11 @@
             {#if detail.warningMessages.length}<div class="warnings"><h3>Recorded warnings</h3><ul>{#each detail.warningMessages as warning}<li>{warning}</li>{/each}</ul></div>{/if}
 
             {#if detail.safetyOverride}<div class="warnings"><h3>Admin override enabled</h3><p>Player safety checks bypassed for this operation. Confirmed by {detail.safetyOverride.actorName} · <RelativeTime value={detail.safetyOverride.confirmedAt} />.</p></div>{/if}
-            {#if detail.canResumeVerification || detail.canResumeCleanup || detail.canResumeRebuild || detail.canCancel || detail.canCancelCreation || canOverride}
+            {#if detail.canResumeVerification || detail.canResumeCleanup || detail.canResumeRebuild || detail.canRetryWithRebuild || detail.canCancel || detail.canCancelCreation || canOverride}
                 <div class="recovery-actions">
                     {#if canOverride}<div><Button variant="danger" disabled={!!view.busy || !!detail.safetyOverrideUnavailableReason} loading={view.busy === 'override'} onclick={overrideSafety}>Admin override…</Button><p class="action-help">{detail.safetyOverrideUnavailableReason ?? 'Confirm to bypass player safety checks for this operation.'}</p></div>{/if}
-                    {#if detail.canResumeVerification}<Button variant="primary" loading={view.busy === 'resume'} disabled={!!view.busy} onclick={() => controller.act('resume', 'Health verification requested. The existing instance will be observed without another creation or restart.')}>Resume health verification</Button>{/if}
+                    {#if detail.canResumeVerification}<Button variant="primary" loading={view.busy === 'resume'} disabled={!!view.busy} onclick={() => controller.act('resume', 'Health verification requested. An unhealthy container may continue through this operation’s remaining recovery steps.')}>Resume health verification</Button>{/if}
+                    {#if detail.canRetryWithRebuild}<div><Button variant="primary" loading={view.busy === 'retry-rebuild'} disabled={!!view.busy} onclick={retryWithRebuild}>Retry with rebuild</Button><p class="action-help">Starts a new rebuild for the same lobby and port. Deletes instance files and uses the latest promoted setup.</p></div>{/if}
                     {#if detail.canResumeRebuild}<Button variant="primary" loading={view.busy === 'resume'} disabled={!!view.busy} onclick={() => controller.act('resume', 'Rebuild cleanup requested. Fresh creation waits for local cleanup to finish.')}>Resume rebuild cleanup</Button>{/if}
                     {#if detail.canResumeCleanup}<Button variant="primary" loading={view.busy === 'resume'} disabled={!!view.busy} onclick={() => controller.act('resume', 'Local cleanup requested. Remote container deletion will not be repeated.')}>Resume cleanup</Button>{/if}
                     {#if detail.canCancel}<div><Button disabled={!!view.busy} loading={view.busy === 'cancel'} onclick={() => controller.act('cancel', 'Operation cancelled. Already-submitted commands may finish; no further steps will be started.')}>Cancel operation</Button><p class="action-help">Stops remaining work and health checks. Changes already made are not undone.</p></div>{/if}