test(design): plan-mode names its read list and caps its additions and summary

At 6fcb0981 plan-design-review-plan-mode timed out at 300 s (9 turns): 22 cat/sed
chunk reads (~50 s), then a 28 KB plan Write (~150 s), before the read-back
finished. The 9a7a7e54 pass took 240 s with a 24.6 KB Write. Read SKILL.md,
review-sections.md and plan.md natively in one response, keep additions under
14,000 characters and the summary within ten lines. Budgets unchanged.
This commit is contained in:
garrytan committed 2026-09-30 23:23:18 +00:00
1 parent 6a4d54fc55
commit 878092dd0d
2 files changed
+8 -4

No files matched your search

+5 -1
View File
@@ -89,7 +89,7 @@ async function exercise(mode: 'success' | 'max-turns' | 'first-timeout' | 'secon
expect(opts.signal.aborted).toBe(false);
// Bind the complete actual compact-delivery prompt, not selected snippets.
expect(new Bun.CryptoHasher('sha256').update(opts.prompt).digest('hex'))
.toBe('2fa957ab9d56850a1629a845d6fe0ee5a1cb7c0843ab6555b621971d270604cb');
.toBe('56468e8f520719957c612ced2da1f5f2f3698bc4551075a429bee4816e157cdb');
expect(opts.testName).toBe(id); expect(opts.maxTurns).toBe(15); expect(opts.timeout).toBe(CAPTURE_MS);
for (const key of ['model', 'tools', 'allowedTools', 'appendSystemPrompt', 'env']) expect(opts).not.toHaveProperty(key);
expect(opts.prompt).toContain('Review the plan in ./plan.md');
@@ -101,6 +101,10 @@ async function exercise(mode: 'success' | 'max-turns' | 'first-timeout' | 'secon
expect(opts.prompt).toContain('Write before publishing a completed walkthrough');
expect(opts.prompt).toContain('Read plan.md back to verify the saved changes');
expect(opts.prompt).toContain('Then return a brief, concrete summary');
expect(opts.prompt).toContain('natively Read plan-design-review/SKILL.md');
expect(opts.prompt).toContain('plan-design-review/sections/review-sections.md (the one lazy section this review requires)');
expect(opts.prompt).toContain('including the report, under 14,000 characters');
expect(opts.prompt).toContain('in at most ten lines');
expect(opts.prompt).toContain('execute every required pass and lazy-section Read');
expect(opts.prompt).toContain('Retain all required report fields, design decisions, diagrams, ratings, and explanations');
expect(opts.prompt).toContain('use the canonical tables and decision IDs');