chore: revert pty-smoke harness experiments (race-retry + CI debug step)

Diagnosis is conclusive and the experiments aren't the fix, so restore the
harness to its original state (net-zero diff vs main for both files).

What the CI debug step proved: `claude -p` returns READY — claude v2.1.187 fully
DISCOVERS /office-hours from the symlinked registry. Only the interactive PTY TUI
rejects it as "Unknown command" (and it received the full command text). So the
e2e-pty-plan-smoke failure is a claude 2.1.187 interactive-TUI regression (skills
discovered by `claude -p` aren't exposed as TUI slash commands), pre-existing in
the #2077 harness and failing identically on its own origin branch — unrelated to
this activation PR. The race-retry can't help (the TUI genuinely lacks the
command); the debug step also tripped actionlint (shellcheck SC2012). Both reverted.

.github/workflows/evals.yml

@@ -216,24 +216,6 @@ jobs:
             || { echo "ERROR: plan-ceo-review SKILL.md missing 'name: plan-ceo-review' frontmatter" >&2; exit 1; }
           echo "skill registry OK"
 
-      # TEMP DEBUG (remove after diagnosing pty-smoke discovery): the smoke fails
-      # with "Unknown command: /office-hours" even after retries (not a race).
-      # Capture what claude actually discovers in CI to fix the registry precisely.
-      - name: Debug skill discovery (pty smoke)
-        if: matrix.suite.name == 'e2e-pty-plan-smoke'
-        env:
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-        run: |
-          set +e
-          echo "=== claude version + binary ==="; command -v claude; claude --version 2>&1 | head -3
-          echo "=== HOME/CLAUDE/XDG env ==="; env | grep -iE '^(HOME|CLAUDE|XDG)=' || true
-          echo "=== ~/.claude/skills (top) ==="; ls -la "$HOME/.claude/skills" 2>&1 | head -30
-          echo "=== office-hours SKILL.md resolves? ==="; head -3 "$HOME/.claude/skills/office-hours/SKILL.md" 2>&1
-          echo "=== project .claude in cwd? ==="; ls -la "$GITHUB_WORKSPACE/.claude" 2>&1 | head
-          echo "=== claude -p probe (same discovery path) ==="
-          cd "$GITHUB_WORKSPACE"
-          timeout 90 claude -p "Reply with exactly the word READY and nothing else if the /office-hours slash command is available to you, otherwise reply MISSING." 2>&1 | tail -10
-
       - name: Run ${{ matrix.suite.name }}
         env:
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}

test/helpers/claude-pty-runner.ts

@@ -1605,7 +1605,7 @@ export async function runPlanSkillObservation(opts: {
       // command.
       await Bun.sleep(3000);
     }
-    let since = session.mark();
+    const since = session.mark();
     session.send(`/${opts.skillName}\r`);
 
     const budgetMs = opts.timeoutMs ?? 180_000;
@@ -1619,7 +1619,6 @@ export async function runPlanSkillObservation(opts: {
     // even if the current state is 'working'.
     let proseAUQEverObserved = false;
     let waitingEverObserved = false;
-    let unknownCmdRetries = 0;
     const JUDGE_AFTER_MS = 60_000;
     const JUDGE_INTERVAL_MS = 30_000;
     while (Date.now() - start < budgetMs) {
@@ -1635,24 +1634,9 @@ export async function runPlanSkillObservation(opts: {
         };
       }
       if (visible.includes('Unknown command:')) {
-        // Skill-discovery race: in a cold CI container the overlay-FS scan of
-        // the symlinked ~/.claude/skills registry can finish AFTER the boot
-        // grace, so the first `/skill` send reaches claude before the skill is
-        // indexed and is rejected as unknown. (Reproduces only in CI — passes
-        // locally where claude is warm and discovery is instant.) Re-send the
-        // command a few times, re-marking first so the stale "Unknown command:"
-        // line in scrollback can't immediately re-trip this check, before
-        // concluding the skill is genuinely unregistered.
-        if (unknownCmdRetries < 3) {
-          unknownCmdRetries++;
-          await Bun.sleep(6000);
-          since = session.mark();
-          session.send(`/${opts.skillName}\r`);
-          continue;
-        }
         return {
           outcome: 'exited',
-          summary: `claude rejected /${opts.skillName} as unknown command after ${unknownCmdRetries} retries (skill not registered in this cwd)`,
+          summary: `claude rejected /${opts.skillName} as unknown command (skill not registered in this cwd)`,
           evidence: visible.slice(-2000),
           elapsedMs: Date.now() - startedAt,
         };