fix(#1516): expose adaptive model_profile in /gsd-new-project AI Models prompt (#1654)

* fix(#1516): expose adaptive model_profile in /gsd-new-project AI Models prompt

Both onboarding paths (Step 2a auto-mode + Step 5 interactive) enumerated only
4 profiles (Balanced/Quality/Budget/Inherit), omitting 'adaptive' even though the
model catalog (model-catalog.json profiles) and docs/CONFIGURATION.md register 5.
Mirrors the proven /gsd:settings two-question split (#3784): Q1 routes between
Adaptive/Standard-tier/Inherit; Q2 (conditional on Q1=Standard) picks
Quality/Balanced/Budget — keeping every AskUserQuestion within the 4-option cap.
Both config-new-project example payloads now list adaptive. Regression cases
folded into the owning tests/new-project-mvp-prompt.test.cjs (per the
lint-regression-test-names ban on new top-level bug-NNNN files): each AI Models
prompt makes adaptive reachable, all 5 profiles reachable, 4-option cap honored,
both example enums include adaptive, brace balance. Workflow size baseline bumped
(new-project.md 62324 -> 66138 bytes; still well under the XL hard cap).

* chore(#1516): backfill changeset pr ref to 1654

tests/workflow-size-baseline.json

@@ -45,7 +45,7 @@
   "milestone-summary.md": 11774,
   "mvp-phase.md": 13582,
   "new-milestone.md": 32422,
-  "new-project.md": 62324,
+  "new-project.md": 66138,
   "new-workspace.md": 11254,
   "next.md": 20094,
   "node-repair.md": 4173,