gstack/scripts
Garry Tan da75ebaaa0
refactor(opus-4.7): split overlay, align routing, fix trailer fallback
Follow-up to wintermute's initial Opus 4.7 migration commit (addresses
ship-quality review findings before v1.6.1.0 release).

Overlay split (model-overlays/):
  - Move 4 Opus-4.7-specific nudges (Fan out, Effort-match, Batch your
    questions, Literal interpretation) from claude.md into new
    opus-4-7.md with {{INHERIT:claude}}
  - claude.md now holds only model-agnostic nudges (Todo discipline,
    Think before heavy, Dedicated tools over Bash)
  - Prevents Opus-4.7-specific guidance leaking onto Sonnet/Haiku
  - Uses existing {{INHERIT:claude}} mechanism at
    scripts/resolvers/model-overlay.ts:28-43

scripts/models.ts:
  - Add opus-4-7 to ALL_MODEL_NAMES
  - resolveModel: claude-opus-4-7-* variants route to opus-4-7,
    all other claude-* variants continue to route to claude

scripts/resolvers/utility.ts:
  - Update coAuthor trailer fallback: Opus 4.6 -> Opus 4.7
    (fallback was missed in the initial migration commit)

scripts/resolvers/preamble/generate-routing-injection.ts:
  - Align policy with new SKILL.md.tmpl: soft "when in doubt, invoke"
    instead of hard "ALWAYS invoke... Do NOT answer directly"
  - Replace stale /checkpoint reference with /context-save +
    /context-restore (skills were renamed in v1.0.1.0)
  - Expand route coverage to match full skill inventory:
    /plan-devex-review, /qa-only, /devex-review, /land-and-deploy,
    /setup-deploy, /canary, /open-gstack-browser,
    /setup-browser-cookies, /benchmark, /learn, /plan-tune, /health

scripts/resolvers/preamble/generate-voice-directive.ts:
  - Voice example closing: "Want me to ship it?" -> "Want me to fix it?"
  - Preserves directness while routing through review gates

SKILL.md.tmpl:
  - Add routing triggers for skills that were missing from the list:
    /plan-devex-review, /qa-only, /devex-review, /land-and-deploy,
    /setup-deploy, /canary, /open-gstack-browser,
    /setup-browser-cookies, /benchmark, /learn, /plan-tune, /health
  - Within Opus 4.7 overlay, added scope boundary to
    "Literal interpretation" nudge ("fix tests that this branch
    introduced or is responsible for")
  - Added pacing exception to "Batch your questions" nudge so skills
    that require one-question-at-a-time pacing still win

Follow-up commit will regenerate SKILL.md files + update goldens.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-21 23:39:42 -07:00
..
app feat: GStack Browser — double-click AI browser with anti-bot stealth (#695) 2026-04-04 10:17:05 -07:00
host-adapters feat: declarative multi-host platform + OpenCode, Slate, Cursor, OpenClaw (v0.15.5.0) (#793) 2026-04-04 15:32:20 -07:00
resolvers refactor(opus-4.7): split overlay, align routing, fix trailer fallback 2026-04-21 23:39:42 -07:00
analytics.ts feat: safety hook skills + skill usage telemetry (v0.7.1) (#189) 2026-03-18 23:57:59 -05:00
archetypes.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
build-app.sh feat: GStack Browser — double-click AI browser with anti-bot stealth (#695) 2026-04-04 10:17:05 -07:00
dev-skill.ts feat: Wave 3 — community bug fixes & platform support (v0.11.6.0) (#359) 2026-03-23 22:15:23 -07:00
discover-skills.ts fix: community PRs + security hardening + E2E stability (v0.12.7.0) (#552) 2026-03-26 23:21:27 -06:00
eval-compare.ts feat: worktree isolation for E2E tests + infrastructure elegance (v0.11.12.0) (#425) 2026-03-23 23:05:22 -07:00
eval-list.ts feat: worktree isolation for E2E tests + infrastructure elegance (v0.11.12.0) (#425) 2026-03-23 23:05:22 -07:00
eval-select.ts feat: diff-based test selection for E2E and LLM-judge evals (v0.6.1.0) (#139) 2026-03-17 18:45:41 -05:00
eval-summary.ts feat: worktree isolation for E2E tests + infrastructure elegance (v0.11.12.0) (#425) 2026-03-23 23:05:22 -07:00
eval-watch.ts feat: /land-and-deploy, /canary, /benchmark + perf review (v0.7.0) (#183) 2026-03-21 14:31:36 -07:00
garry-output-comparison.ts fix: remove hardcoded author emails from throughput script 2026-04-18 15:36:50 +08:00
gen-skill-docs.ts feat(v1.3.0.0): open agents learnings + cross-model benchmark skill (#1040) 2026-04-19 17:50:31 +08:00
host-config-export.ts feat: declarative multi-host platform + OpenCode, Slate, Cursor, OpenClaw (v0.15.5.0) (#793) 2026-04-04 15:32:20 -07:00
host-config.ts feat: OpenClaw integration v2 — prompt is the bridge (v0.15.9.0) (#816) 2026-04-05 02:23:59 -07:00
jargon-list.json feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
models.ts refactor(opus-4.7): split overlay, align routing, fix trailer fallback 2026-04-21 23:39:42 -07:00
one-way-doors.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
psychographic-signals.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
question-registry.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
setup-scc.sh feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00
skill-check.ts feat: declarative multi-host platform + OpenCode, Slate, Cursor, OpenClaw (v0.15.5.0) (#793) 2026-04-04 15:32:20 -07:00
slop-diff.ts security: tunnel dual-listener + SSRF + envelope + path wave (v1.6.0.0) (#1137) 2026-04-21 21:58:27 -07:00
update-readme-throughput.ts feat: gstack v1 — simpler prompts + real LOC receipts (v1.0.0.0) (#1039) 2026-04-18 15:05:42 +08:00