fix(#3229): shared model catalog source of truth for agent profiles + runtime tier defaults (#3230)

* docs(adr): add ADR-0003 model catalog module

* fix(#3229): add shared model catalog as source of truth for agent profiles and runtime tier defaults

Research / design (ADR-0003):
- Existing drift came from 4 independent model truths:
  1. CJS model-profiles.cjs
  2. SDK config-query.ts stale copy (18 agents)
  3. settings-advanced.md runtime tier table
  4. session-runner Claude-only profile map
- New design: one machine-readable Model Catalog Module in sdk/shared/
  that both packages ship and consume.

Implementation:
- sdk/shared/model-catalog.json — canonical source of truth for:
  - full 33-agent registry
  - per-agent golden (quality) alias + balanced/budget aliases
  - adaptive derivation from routingTier
  - agent→phaseType map
  - agent→dynamic-routing default tier map
  - runtime tier defaults for all supported runtimes
- get-shit-done/bin/lib/model-catalog.cjs — CJS adapter over the catalog
- sdk/src/model-catalog.ts — SDK adapter over the same catalog
- CJS model-profiles.cjs now re-exports derived data from model-catalog.cjs
- SDK config-query.ts now re-exports MODEL_PROFILES/VALID_PROFILES from
  model-catalog.ts instead of maintaining its own list
- sdk/src/query/helpers.ts runtime list now comes from the catalog (fixes hermes drift)
- sdk/src/session-runner.ts Claude profile→model-id mapping now resolves via catalog
- docs/CONFIGURATION.md + settings-advanced.md runtime tables updated to match catalog

Behavior changes:
- resolve-model now covers every shipped agent file on disk (33 agents)
- unknown-agent fallback is profile-semantic, not hardcoded sonnet:
  quality→opus, budget→haiku, balanced/adaptive→sonnet, inherit→inherit
- Group B runtimes remain known runtimes but do not get built-in tier defaults

Tests (RED→GREEN):
- root tests: shipped agent files must equal MODEL_PROFILES keys
- sdk tests: shipped agent files must equal MODEL_PROFILES keys
- direct fix assertion: gsd-code-reviewer resolves to opus under quality with no unknown_agent
- runtime defaults parity test: settings-advanced.md + CONFIGURATION.md tables must match catalog
- helper tests: hermes included in SUPPORTED_RUNTIMES and getRuntimeConfigDir()

Closes #3229

* chore(changeset): update #3229 changeset pr field to 3230

* fix(ci): update inherit fallback expectations and inventory parity for model catalog
This commit is contained in:
Tom Boucher
2026-05-08 21:25:37 -04:00
committed by GitHub
parent deeb6deb67
commit 96806003c5
23 changed files with 557 additions and 368 deletions

View File

@@ -3,8 +3,8 @@
*/
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
import { mkdtemp, writeFile, mkdir, rm } from 'node:fs/promises';
import { join } from 'node:path';
import { mkdtemp, writeFile, mkdir, rm, readdir } from 'node:fs/promises';
import { join, resolve } from 'node:path';
import { tmpdir } from 'node:os';
import { GSDError, ErrorClassification, exitCodeFor } from '../errors.js';
@@ -121,16 +121,36 @@ describe('resolveModel', () => {
expect(data).not.toHaveProperty('unknown_agent');
});
it('returns unknown_agent flag for unknown agent', async () => {
it('resolves shipped-but-previously-missing agents without unknown_agent (#3229)', async () => {
const { resolveModel } = await import('./config-query.js');
await writeFile(
join(tmpDir, '.planning', 'config.json'),
JSON.stringify({ model_profile: 'balanced' }),
JSON.stringify({ model_profile: 'quality' }),
);
const result = await resolveModel(['unknown-agent'], tmpDir);
const result = await resolveModel(['gsd-code-reviewer'], tmpDir);
const data = result.data as Record<string, unknown>;
expect(data).toHaveProperty('model', 'sonnet');
expect(data).toHaveProperty('unknown_agent', true);
expect(data).toHaveProperty('model', 'opus');
expect(data).toHaveProperty('profile', 'quality');
expect(data).not.toHaveProperty('unknown_agent');
});
it('returns profile-semantic fallback for truly unknown agents (#3229)', async () => {
const { resolveModel } = await import('./config-query.js');
await writeFile(
join(tmpDir, '.planning', 'config.json'),
JSON.stringify({ model_profile: 'quality' }),
);
const quality = (await resolveModel(['unknown-agent'], tmpDir)).data as Record<string, unknown>;
expect(quality).toHaveProperty('model', 'opus');
expect(quality).toHaveProperty('unknown_agent', true);
await writeFile(
join(tmpDir, '.planning', 'config.json'),
JSON.stringify({ model_profile: 'budget' }),
);
const budget = (await resolveModel(['unknown-agent'], tmpDir)).data as Record<string, unknown>;
expect(budget).toHaveProperty('model', 'haiku');
expect(budget).toHaveProperty('unknown_agent', true);
});
it('throws GSDError when no agent type provided', async () => {
@@ -195,12 +215,17 @@ describe('resolveModel', () => {
// ─── MODEL_PROFILES ─────────────────────────────────────────────────────────
describe('MODEL_PROFILES', () => {
it('contains all 18 agent entries (sync with model-profiles.cjs)', async () => {
it('contains every shipped gsd agent file on disk (#3229)', async () => {
const { MODEL_PROFILES } = await import('./config-query.js');
expect(Object.keys(MODEL_PROFILES)).toHaveLength(18);
const repoRoot = resolve(process.cwd(), '..');
const agentFiles = (await readdir(join(repoRoot, 'agents')))
.filter((f) => /^gsd-.*\.md$/.test(f))
.map((f) => f.replace(/\.md$/, ''))
.sort();
expect(Object.keys(MODEL_PROFILES).sort()).toEqual(agentFiles);
});
it('has quality/balanced/budget/adaptive for each agent', async () => {
it('has quality/balanced/budget/adaptive for each shipped agent', async () => {
const { MODEL_PROFILES } = await import('./config-query.js');
for (const agent of Object.keys(MODEL_PROFILES)) {
expect(MODEL_PROFILES[agent]).toHaveProperty('quality');
@@ -214,9 +239,9 @@ describe('MODEL_PROFILES', () => {
// ─── VALID_PROFILES ─────────────────────────────────────────────────────────
describe('VALID_PROFILES', () => {
it('contains the four profile names', async () => {
it('contains quality, balanced, budget, adaptive, and inherit', async () => {
const { VALID_PROFILES } = await import('./config-query.js');
expect(VALID_PROFILES).toEqual(['quality', 'balanced', 'budget', 'adaptive']);
expect(VALID_PROFILES.sort()).toEqual(['adaptive', 'balanced', 'budget', 'inherit', 'quality']);
});
});