AI_SETUP_LANES.md is stale: GPT-5.6 family (Sol/Terra/Luna) shipped, superseding GPT-5.5/5.4/5.3

[BaseInfinity]

Verified: AI_SETUP_LANES.md is stale — GPT-5.6 family shipped

Fact-checked directly against OpenAI's own docs (not inferred): the flagship model has moved
from GPT-5.5 to a new GPT-5.6 family with three tiers.

Model	Positioning	Price (in/out per 1M)
gpt-5.6-sol	Flagship — "strongest capability for complex coding, computer use, research, and cybersecurity"	$5 / $30
gpt-5.6-terra	Balanced — "competitive with GPT-5.5 at a lower cost"	$2.50 / $15
gpt-5.6-luna	High-volume/cheap — "fast and affordable... lowest cost in the family"	$1 / $6

Sources: https://developers.openai.com/api/docs/guides/latest-model.md,
https://learn.chatgpt.com/docs/models, https://developers.openai.com/api/docs/pricing.
Reasoning-effort levels (none/low/medium/high/xhigh/max) are unchanged; OpenAI's own
guidance is to preserve the prior GPT-5.5 effort setting as baseline, test one level lower, and
reserve max for the hardest quality-first work. Codex's own default (confirmed live, this
session) is now gpt-5.6-sol at medium reasoning.

Why this repo specifically

AI_SETUP_LANES.md here is entirely GPT-5.5/5.4/5.3-based:

• Setup A (Premium): GPT-5.5 xhigh for all 3 roles
• Setup B (Saver): GPT-5.5 xhigh planner/reviewer, GPT-5.3 Codex Spark primary driver /
  GPT-5.4 mini xhigh fallback (separate billing buckets)
• Setup C (Lite): GPT-5.4 mini standard driver, GPT-5.4 standard fallback, no reviewer

All three tiers are candidates for remapping onto the new family (Sol for Premium/reviewer
roles, Terra for the Saver driver tier, Luna for Lite) — but the actual billing-bucket
structure, availability, and whether Terra/Luna genuinely replace the old Spark/mini tiers
functionally (not just by rough price analogy) needs verification, not just a name swap.

Proposal

Same recipe already proven twice in this sweep (claude-sdlc-wizard's own "AI Setup Lanes v3"
ROADMAP #434/#436, and the cross-repo playbook already shared to this ecosystem): a scoped
Fable pass specifically on AI_SETUP_LANES.md (plus anywhere else in this repo that hardcodes
GPT-5.5/5.4/5.3 — README.md, skill files, any hook/script comments) to remap onto the GPT-5.6
family, verified against current docs/pricing rather than assumed from the old lane shape, then
a Codex cross-model review of the change itself before merging model-selection guidance that
every consumer of this wizard inherits.

---

Submitted as part of a cross-repo self-enforcement/currency review pass
(see claude-sdlc-wizard#236 -> PR #440, codex-sdlc-wizard#58).