gstack/scripts/resolvers
Garry Tan 028627fbcd
fix(preamble): harden AskUserQuestion Format + Codex ELI10 carve-out
Follow-up to v1.6.2.0. Codex (GPT-5.4) under the gpt.md overlay
treated "No preamble / Prefer doing over listing" as license to skip
the Simplify paragraph and the RECOMMENDATION line on AskUserQuestion
calls. Users had to manually re-prompt "ELI10 and don't forget to
recommend" almost every time.

Two layers:

1. model-overlays/gpt.md — adds an explicit "AskUserQuestion is NOT
   preamble" carve-out. The "No preamble" rule applies to direct
   answers; AskUserQuestion content must emit the full format
   (Re-ground, Simplify/ELI10, Recommend, Options). Tells the model:
   if you find yourself about to skip any of these, back up and emit
   them — the user will ask anyway, so do it the first time.

2. scripts/resolvers/preamble/generate-ask-user-format.ts — step 2
   renamed to "Simplify (ELI10, ALWAYS)" with explicit "not optional
   verbosity, not preamble" framing. Step 3 "Recommend (ALWAYS)"
   hardened: "Never omit, never collapse into the options list."

All T2 skills regenerated across all hosts. Golden fixtures refreshed
(claude-ship, codex-ship, factory-ship). Updated the ELI10 assertion
in test/gen-skill-docs.test.ts to match the new wording.

Codex compliance to be verified empirically via test/codex-e2e-plan-format.test.ts.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-04-22 21:34:31 -07:00
..
preamble fix(preamble): harden AskUserQuestion Format + Codex ELI10 carve-out 2026-04-22 21:34:31 -07:00
browse.ts fix: avoid tilde-in-assignment to silence Claude Code permission prompts (#993) 2026-04-16 14:49:56 -07:00
codex-helpers.ts feat: Factory Droid compatibility — works across Claude Code, Codex, and Factory (v0.13.5.0) (#621) 2026-03-29 08:57:34 -07:00
composition.ts feat: composable skills — INVOKE_SKILL resolver + factoring infrastructure (v0.13.7.0) (#644) 2026-03-29 23:35:17 -06:00
confidence.ts feat: GStack Learns — per-project self-learning infrastructure (v0.13.4.0) (#622) 2026-03-29 17:02:01 -06:00
constants.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
design.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
dx.ts feat: /plan-devex-review + /devex-review — DX review skills (v0.15.3.0) (#784) 2026-04-03 16:22:57 -07:00
gbrain.ts feat: Confusion Protocol, Hermes + GBrain hosts, brain-first resolver (v0.18.0.0) (#1005) 2026-04-16 10:41:38 -07:00
index.ts feat(v1.4.0.0): /make-pdf — markdown to publication-quality PDFs (#1086) 2026-04-20 13:20:30 +08:00
learnings.ts feat: recursive self-improvement — operational learning + full skill wiring (v0.13.8.0) (#647) 2026-03-31 23:08:22 -06:00
make-pdf.ts feat(v1.4.0.0): /make-pdf — markdown to publication-quality PDFs (#1086) 2026-04-20 13:20:30 +08:00
model-overlay.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
preamble.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
question-tuning.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
review-army.ts feat: context rot defense for /ship — subagent isolation + clean step numbering (v0.18.1.0) (#1030) 2026-04-16 23:14:03 -07:00
review.ts codex + Apple Silicon hardening wave (v0.18.4.0) (#1056) 2026-04-18 12:30:54 +08:00
testing.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
types.ts feat(v1.4.0.0): /make-pdf — markdown to publication-quality PDFs (#1086) 2026-04-20 13:20:30 +08:00
utility.ts feat(v1.5.2.0): Opus 4.7 migration — model overlay, voice, routing (#1117) 2026-04-22 01:06:22 -07:00