test: supply the split-overflow fixture's HOLD SCOPE mode as a prerequisite

The split actor always answered 0E's mode question with HOLD SCOPE. The
skill skips that question on an explicit choice, so the fixture now states
it and the attempt starts at the five candidate decisions (about 1.5 min
earlier in run 36385945043). Candidates, actor policy, floor and semantic
evaluation are unchanged; the fixture test pins the supplied choice.
This commit is contained in:
garrytan committed 2026-09-29 15:31:34 +00:00
1 parent 4973f96d98
commit 6f998e4299
3 files changed
+9 -2

No files matched your search

+3
View File
@@ -363,6 +363,9 @@ describe('CEO finding fixture establishes scope before launch', () => {
expect(committed).toBe(input);
expect(committed).toContain(target);
expect(committed).toContain('Proceed directly to the requested CEO review; skip the optional /office-hours prerequisite.');
// Supplied prerequisite: the split actor always chose HOLD SCOPE; an explicit
// choice skips 0E's mode question so the attempt starts at the candidates.
expect(committed).toContain('Use HOLD SCOPE mode for this review.');
expect(committed.match(/^## E[1-5]\)/gm)).toHaveLength(5);
expect(fs.readFileSync(path.join(root, 'CLAUDE.md'), 'utf8')).not.toContain('Payment processing');
} finally { fs.rmSync(root, { recursive: true, force: true }); }
+1
View File
@@ -146,6 +146,7 @@ export const FORCING_BATCHING_ENG = [
export const FORCING_SPLIT_OVERFLOW_CEO = [
'Please review this plan and help me decide scope. Write your plan-mode plan to /tmp/gstack-test-plan-ceo-split-overflow.md (use Edit/Write to that exact path).',
'Proceed directly to the requested CEO review; skip the optional /office-hours prerequisite.',
'Use HOLD SCOPE mode for this review.',
'',
'# Plan: Pick which chat-platform integrations to ship this quarter',
'',
@@ -29,8 +29,11 @@
* which is exactly the shape that hits Conductor's 4-option cap and
* triggers the new split-vs-drop guidance.
*
* Tier: periodic (~25 min, ~$0.30-$5.00/run depending on agent path).
* Sequential by default.
* The fixture supplies the HOLD SCOPE mode the actor always chose, so 0E skips
* its mode question. Run 36385945043 acknowledged all five candidates 8m55s
* after launch (mode question included); collection stops there.
*
* Tier: periodic (25 min budget; ~8-9 min expected). Sequential by default.
*/
import { test } from 'bun:test';