feat(setup): Claude-assisted error recovery with resume-at-step retry

When a setup step fails — whether hard via fail() or soft via the
"What's left" / "Skipping the first chat" notes — offer to ask Claude
to diagnose. On consent, spawn `claude -p --output-format stream-json`
with a scrolling 3-line action window ("Reading x", "Running y") so
the 1–4 minute investigations feel active rather than hung. No hard
timeout: debugging can take time, Ctrl-C is the escape hatch.

The prompt is minimal: one-paragraph framing, failed step name + msg +
hint, and a list of file references (not contents). Claude's Read/Grep
tools fetch what they need. A per-step map in claude-assist.ts gives
the most relevant files per step; the rest is README + auto.ts +
logs/setup.log + the per-step raw log.

Claude responds with REASON + COMMAND lines. We show the reason in a
clack note, prefill the command via setup/run-suggested.sh (bash 4+
readline, 3.x fallback to Enter-to-run), and eval on the user's
confirm.

When the user runs a fix, fail() now offers to retry the failing step
rather than aborting. setup/logs.ts tracks successfully-completed step
names in-memory; fail() threads those as NANOCLAW_SKIP on a spawnSync
retry, so the child picks up exactly where the parent left off — no
rebuilding containers or reinstalling OneCLI.

Other polish in this change:
- fitToWidth + dimWrap in lib/theme.ts to prevent long spinner labels
  from soft-wrapping (each terminal row stacks a stale copy otherwise).
- Shorter container step label ("Preparing your assistant's sandbox…")
  so it fits on narrow terminals.
- Wordmark anchored in the clack intro line on every run.
- All 25 existing fail() call sites updated to await fail(...) since
  fail is now async.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

setup/logs.ts

@@ -30,6 +30,16 @@ const PROGRESS_LOG = path.join(LOGS_DIR, 'setup.log');
 export const progressLogPath = PROGRESS_LOG;
 export const stepsDir = STEPS_DIR;
 
+// Track steps that finished cleanly in this run. Used by fail() to build
+// a NANOCLAW_SKIP list when re-executing after a Claude-assisted fix, so
+// the retry picks up at the failing step instead of redoing every step
+// before it.
+const completedInRun = new Set<string>();
+
+export function completedStepNames(): string[] {
+  return [...completedInRun];
+}
+
 /** Wipe prior logs and write a header. Called once per fresh run (by nanoclaw.sh or as a fallback by auto.ts if invoked standalone). */
 export function reset(meta: Record<string, string>): void {
   if (fs.existsSync(STEPS_DIR)) {
@@ -71,6 +81,10 @@ export function step(
   if (rawRel) lines.push(`  raw: ${rawRel}`);
   lines.push('');
   fs.appendFileSync(PROGRESS_LOG, lines.join('\n') + '\n');
+
+  if (status === 'success' || status === 'skipped') {
+    completedInRun.add(name);
+  }
 }
 
 /** A user answered a prompt. Logs as its own entry because the setup path depends on it. */