test: extract MODE_RE + optionsSignature into PTY runner exports

Refactor prep for the upcoming per-finding AskUserQuestion count test
across plan-{ceo,eng,design,devex}-review. Both new tests and the existing
mode-routing test need the same mode regex and the same option-list
fingerprint dedupe — pulling them into one source of truth in
test/helpers/claude-pty-runner.ts so a fifth mode (or a tweak to the
fingerprint shape) updates everywhere instead of drifting per-test.

Mechanical: no behavior change in the mode-routing test.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-04-28 09:05:11 -07:00
parent 8bbe74faff
commit e6ce1dca70
2 changed files with 33 additions and 4 deletions
+29
View File
@@ -284,6 +284,35 @@ export function parseNumberedOptions(
return found;
}
/**
* The four /plan-ceo-review modes. Used by `skill-e2e-plan-ceo-mode-routing`
* to detect Step 0F mode-selection AskUserQuestions, and by the upcoming
* finding-count tests as a Step-0 boundary signal: an AUQ whose options
* match this regex IS the mode pick (the last Step-0 question for plan-ceo).
*
* Lifted out of the mode-routing test so multiple PTY tests can share one
* source of truth — when /plan-ceo-review adds a fifth mode, one regex updates
* everywhere instead of drifting per-test.
*/
export const MODE_RE = /HOLD SCOPE|SCOPE EXPANSION|SELECTIVE EXPANSION|SCOPE REDUCTION/i;
/**
* Stable signature for a parsed numbered-option list — used by tests to detect
* "is this AUQ the same as the last poll, or has the agent advanced to a new
* one?" Joins each option as `${index}:${label}` after sorting by index.
*
* Defensive sort means the signature is order-independent at the input level,
* even though `parseNumberedOptions` already returns indices in ascending order.
*/
export function optionsSignature(
opts: Array<{ index: number; label: string }>,
): string {
return [...opts]
.sort((a, b) => a.index - b.index)
.map((o) => `${o.index}:${o.label}`)
.join('|');
}
/**
* Pure classifier for the visible TTY buffer. Decides which outcome the
* polling loop should return on this tick, or `null` to keep polling.
+4 -4
View File
@@ -37,6 +37,8 @@ import {
isPermissionDialogVisible,
parseNumberedOptions,
isPlanReadyVisible,
MODE_RE,
optionsSignature,
TAIL_SCAN_BYTES,
type ClaudePtySession,
} from './helpers/claude-pty-runner';
@@ -44,8 +46,6 @@ import {
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'periodic';
const describeE2E = shouldRun ? describe : describe.skip;
const MODE_RE = /HOLD SCOPE|SCOPE EXPANSION|SELECTIVE EXPANSION|SCOPE REDUCTION/i;
interface ModeCase {
mode: 'HOLD SCOPE' | 'SCOPE EXPANSION';
/** Regex applied to visible-since-mode-pick text. At least one must match. */
@@ -96,8 +96,8 @@ async function navigateToModeAskUserQuestion(
// Has the rendered list changed since last poll? If not, we're seeing
// the same prompt and shouldn't double-press.
const sig = opts.map(o => `${o.index}:${o.label}`).join('|');
const lastSig = lastSeenList.map(o => `${o.index}:${o.label}`).join('|');
const sig = optionsSignature(opts);
const lastSig = optionsSignature(lastSeenList);
if (sig === lastSig) continue;
lastSeenList = opts;