Files
gstack/scripts/resolvers/index.ts
T
Garry Tan 6c8cf6774f feat: model overlays with explicit --model flag (no auto-detect)
Adds a per-model behavioral patch layer orthogonal to the host axis.
Different LLMs have different tendencies (GPT won't stop, Gemini
over-explains, o-series wants structured output). Overlays nudge each
model toward better defaults for gstack workflows.

Codex review caught three landmines the prior reviews missed:
1. Host != model — Claude Code can run any Claude model, Codex runs
   GPT/o-series, Cursor fronts multiple providers. Auto-detecting from
   host would lie. Dropped auto-detect. --model is explicit (default
   claude). Missing overlay file → empty string (graceful).
2. Import cycle — putting Model in resolvers/types.ts would cycle
   through hosts/index. Created neutral scripts/models.ts instead.
3. "Final say" is dangerous — overlay at the end of preamble could
   override STOP points, AskUserQuestion gates, /ship review gates.
   Placed overlay after spawned-session-check but before voice + tier
   sections. Wrapper heading adds explicit subordination language on
   every overlay: "subordinate to skill workflow, STOP points,
   AskUserQuestion gates, plan-mode safety, and /ship review gates."

Changes:
- scripts/models.ts: new neutral module. ALL_MODEL_NAMES, Model type,
  resolveModel() for family heuristics (gpt-5.4-mini → gpt-5.4, o3 →
  o-series, claude-opus-4-7 → claude), validateModel() helper.
- scripts/resolvers/types.ts: import Model, add ctx.model field.
- scripts/resolvers/model-overlay.ts: new resolver. Reads
  model-overlays/{model}.md. Supports {{INHERIT:base}} directive at
  top of file for concat (gpt-5.4 inherits gpt). Cycle guard.
- scripts/resolvers/index.ts: register MODEL_OVERLAY resolver.
- scripts/resolvers/preamble.ts: wire generateModelOverlay into
  composition before voice. Print MODEL_OVERLAY: {model} in preamble
  bash so users can see which overlay is active. Filter empty sections.
- scripts/gen-skill-docs.ts: parse --model CLI flag. Default claude.
  Unknown model → throw with list of valid options.
- model-overlays/{claude,gpt,gpt-5.4,gemini,o-series}.md: behavioral
  patches per model family. gpt-5.4.md uses {{INHERIT:gpt}} to extend
  gpt.md without duplication.
- test/gen-skill-docs.test.ts: fix qa-only guardrail regex scope.
  Was matching Edit/Glob/Grep anywhere after `allowed-tools:` in the
  whole file. Now scoped to frontmatter only. Body prose (Claude
  overlay references Edit as a tool) correctly no longer breaks it.

Verification:
- bun run gen:skill-docs --host all --dry-run → all fresh
- bun run gen:skill-docs --model gpt-5.4 → concat works, gpt.md +
  gpt-5.4.md content appears in order
- bun run gen:skill-docs --model unknown → errors with valid list
- All generated skills contain MODEL_OVERLAY: claude in preamble
- Golden ship fixtures regenerated

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-17 06:01:27 +08:00

68 lines
3.6 KiB
TypeScript

/**
* RESOLVERS record — maps {{PLACEHOLDER}} names to generator functions.
* Each resolver takes a TemplateContext and returns the replacement string.
*/
import type { TemplateContext, ResolverFn } from './types';
// Domain modules
import { generatePreamble } from './preamble';
import { generateTestFailureTriage } from './preamble';
import { generateCommandReference, generateSnapshotFlags, generateBrowseSetup } from './browse';
import { generateDesignMethodology, generateDesignHardRules, generateDesignOutsideVoices, generateDesignReviewLite, generateDesignSketch, generateDesignSetup, generateDesignMockup, generateDesignShotgunLoop } from './design';
import { generateTestBootstrap, generateTestCoverageAuditPlan, generateTestCoverageAuditShip, generateTestCoverageAuditReview } from './testing';
import { generateReviewDashboard, generatePlanFileReviewReport, generateSpecReviewLoop, generateBenefitsFrom, generateCodexSecondOpinion, generateAdversarialStep, generateCodexPlanReview, generatePlanCompletionAuditShip, generatePlanCompletionAuditReview, generatePlanVerificationExec, generateScopeDrift, generateCrossReviewDedup } from './review';
import { generateSlugEval, generateSlugSetup, generateBaseBranchDetect, generateDeployBootstrap, generateQAMethodology, generateCoAuthorTrailer, generateChangelogWorkflow } from './utility';
import { generateLearningsSearch, generateLearningsLog } from './learnings';
import { generateConfidenceCalibration } from './confidence';
import { generateInvokeSkill } from './composition';
import { generateReviewArmy } from './review-army';
import { generateDxFramework } from './dx';
import { generateModelOverlay } from './model-overlay';
export const RESOLVERS: Record<string, ResolverFn> = {
SLUG_EVAL: generateSlugEval,
SLUG_SETUP: generateSlugSetup,
COMMAND_REFERENCE: generateCommandReference,
SNAPSHOT_FLAGS: generateSnapshotFlags,
PREAMBLE: generatePreamble,
BROWSE_SETUP: generateBrowseSetup,
BASE_BRANCH_DETECT: generateBaseBranchDetect,
QA_METHODOLOGY: generateQAMethodology,
DESIGN_METHODOLOGY: generateDesignMethodology,
DESIGN_HARD_RULES: generateDesignHardRules,
DESIGN_OUTSIDE_VOICES: generateDesignOutsideVoices,
DESIGN_REVIEW_LITE: generateDesignReviewLite,
REVIEW_DASHBOARD: generateReviewDashboard,
PLAN_FILE_REVIEW_REPORT: generatePlanFileReviewReport,
TEST_BOOTSTRAP: generateTestBootstrap,
TEST_COVERAGE_AUDIT_PLAN: generateTestCoverageAuditPlan,
TEST_COVERAGE_AUDIT_SHIP: generateTestCoverageAuditShip,
TEST_COVERAGE_AUDIT_REVIEW: generateTestCoverageAuditReview,
TEST_FAILURE_TRIAGE: generateTestFailureTriage,
SPEC_REVIEW_LOOP: generateSpecReviewLoop,
DESIGN_SKETCH: generateDesignSketch,
DESIGN_SETUP: generateDesignSetup,
DESIGN_MOCKUP: generateDesignMockup,
DESIGN_SHOTGUN_LOOP: generateDesignShotgunLoop,
BENEFITS_FROM: generateBenefitsFrom,
CODEX_SECOND_OPINION: generateCodexSecondOpinion,
ADVERSARIAL_STEP: generateAdversarialStep,
SCOPE_DRIFT: generateScopeDrift,
DEPLOY_BOOTSTRAP: generateDeployBootstrap,
CODEX_PLAN_REVIEW: generateCodexPlanReview,
PLAN_COMPLETION_AUDIT_SHIP: generatePlanCompletionAuditShip,
PLAN_COMPLETION_AUDIT_REVIEW: generatePlanCompletionAuditReview,
PLAN_VERIFICATION_EXEC: generatePlanVerificationExec,
CO_AUTHOR_TRAILER: generateCoAuthorTrailer,
LEARNINGS_SEARCH: generateLearningsSearch,
LEARNINGS_LOG: generateLearningsLog,
CONFIDENCE_CALIBRATION: generateConfidenceCalibration,
INVOKE_SKILL: generateInvokeSkill,
CHANGELOG_WORKFLOW: generateChangelogWorkflow,
REVIEW_ARMY: generateReviewArmy,
CROSS_REVIEW_DEDUP: generateCrossReviewDedup,
DX_FRAMEWORK: generateDxFramework,
MODEL_OVERLAY: generateModelOverlay,
};