feat(codex): advance Codex/OpenAI model defaults to GPT-5.6 (Sol/Terra/Luna)

Update runtimeTierDefaults.codex and providerPresets.openai in
model-catalog.json to the GPT-5.6 family (gpt-5.6-sol/terra/luna),
advancing from the superseded GPT-5.4/5.5 generation.

Model IDs verified against OpenAI developer API docs:
- gpt-5.6-sol: flagship, /, reasoning xhigh
- gpt-5.6-terra: balanced, .50/, reasoning medium
- gpt-5.6-luna: fast/cheap, /, reasoning medium

Tier mapping is 1:1 (Sol↔flagship, Terra↔balanced, Luna↔fast),
so profile semantics are unchanged — only the underlying IDs advance.

Updates: catalog JSON, test assertions (catalog defaults), docs
(CONFIGURATION.md + zh-CN/pt-BR translations, workflow settings),
and changeset.

Closes #2122
This commit is contained in:
Tom Boucher
2026-07-10 10:03:05 -04:00
parent a890dee7b0
commit 185abe2d66
29 changed files with 128 additions and 124 deletions

View File

@@ -8,7 +8,7 @@
* When `runtime` is set to a non-Claude value, profile tiers resolve to runtime-
* native model IDs.
*
* Codex: opus -> gpt-5.5 (xhigh), sonnet -> gpt-5.4 (medium), haiku -> gpt-5.4-mini (medium)
* Codex: opus -> gpt-5.6-sol (xhigh), sonnet -> gpt-5.6-terra (medium), haiku -> gpt-5.6-luna (medium)
*
* `runtime: "claude"` is the implicit default and is treated as a no-op for
* resolution — it does not override `resolve_model_ids: "omit"` or any other
@@ -170,10 +170,10 @@ describe('issue #2517: runtime "codex" — Codex tier resolution', () => {
beforeEach(() => { isolateHome(); tmpDir = createTempProject(); resetRuntimeWarningCaches(); });
afterEach(() => { cleanup(tmpDir); restoreHome(); });
test('opus tier -> gpt-5.5 model; heavy-tier agent -> xhigh effort on codex', () => {
test('opus tier -> gpt-5.6-sol model; heavy-tier agent -> xhigh effort on codex', () => {
writeConfig(tmpDir, { runtime: 'codex', model_profile: 'quality' });
// gsd-planner quality -> opus -> gpt-5.5 (model unchanged)
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.5');
// gsd-planner quality -> opus -> gpt-5.6-sol (model unchanged)
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.6-sol');
// gsd-planner is heavy routing tier → effort 'xhigh' → rendered model_reasoning_effort
const eff = resolveEffortInternal(tmpDir, 'gsd-planner');
const rendered = renderEffortForRuntime('codex', eff);
@@ -181,9 +181,9 @@ describe('issue #2517: runtime "codex" — Codex tier resolution', () => {
assert.strictEqual(rendered.value, 'xhigh');
});
test('sonnet tier -> gpt-5.4 model; heavy-tier agent -> xhigh effort on codex', () => {
test('sonnet tier -> gpt-5.6-terra model; heavy-tier agent -> xhigh effort on codex', () => {
writeConfig(tmpDir, { runtime: 'codex', model_profile: 'balanced' });
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-roadmapper'), 'gpt-5.4');
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-roadmapper'), 'gpt-5.6-terra');
// gsd-roadmapper is heavy routing tier → effort 'xhigh' (not catalog medium)
const eff = resolveEffortInternal(tmpDir, 'gsd-roadmapper');
const rendered = renderEffortForRuntime('codex', eff);
@@ -191,9 +191,9 @@ describe('issue #2517: runtime "codex" — Codex tier resolution', () => {
assert.strictEqual(rendered.value, 'xhigh');
});
test('haiku tier -> gpt-5.4-mini model; light-tier agent -> low effort on codex', () => {
test('haiku tier -> gpt-5.6-luna model; light-tier agent -> low effort on codex', () => {
writeConfig(tmpDir, { runtime: 'codex', model_profile: 'budget' });
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-codebase-mapper'), 'gpt-5.4-mini');
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-codebase-mapper'), 'gpt-5.6-luna');
// gsd-codebase-mapper is light routing tier → effort 'low' (not catalog medium)
const eff = resolveEffortInternal(tmpDir, 'gsd-codebase-mapper');
const rendered = renderEffortForRuntime('codex', eff);
@@ -203,10 +203,10 @@ describe('issue #2517: runtime "codex" — Codex tier resolution', () => {
test('adaptive profile resolves on Codex (no #1713/#1806 regression)', () => {
writeConfig(tmpDir, { runtime: 'codex', model_profile: 'adaptive' });
// gsd-planner adaptive -> opus -> gpt-5.5
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.5');
// gsd-codebase-mapper adaptive -> haiku -> gpt-5.4-mini
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-codebase-mapper'), 'gpt-5.4-mini');
// gsd-planner adaptive -> opus -> gpt-5.6-sol
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.6-sol');
// gsd-codebase-mapper adaptive -> haiku -> gpt-5.6-luna
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-codebase-mapper'), 'gpt-5.6-luna');
});
test('inherit profile still returns "inherit" on Codex; effort still resolves universally', () => {
@@ -226,7 +226,7 @@ describe('issue #2517: runtime "codex" — Codex tier resolution', () => {
model_profile: 'quality',
resolve_model_ids: 'omit',
});
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.5');
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.6-sol');
});
});
@@ -240,9 +240,9 @@ describe('issue #2517: precedence chain', () => {
writeConfig(tmpDir, {
runtime: 'codex',
model_profile: 'quality',
model_overrides: { 'gsd-planner': 'gpt-5.4-mini' },
model_overrides: { 'gsd-planner': 'gpt-5.6-luna' },
});
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.4-mini');
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.6-luna');
});
test('model_profile_overrides[runtime][tier] beats built-in defaults', () => {
@@ -255,9 +255,8 @@ describe('issue #2517: precedence chain', () => {
});
// gsd-planner quality -> opus -> overridden to gpt-5-pro
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5-pro');
// haiku not overridden — fall back to spec defaults
// gsd-codebase-mapper quality -> sonnet -> gpt-5.4
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-codebase-mapper'), 'gpt-5.4');
// gsd-codebase-mapper quality -> sonnet -> gpt-5.6-terra
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-codebase-mapper'), 'gpt-5.6-terra');
});
test('partial profile_overrides — only opus overridden, sonnet uses default', () => {
@@ -271,7 +270,7 @@ describe('issue #2517: precedence chain', () => {
// gsd-planner balanced -> opus -> overridden to gpt-5-pro
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5-pro');
// gsd-roadmapper balanced -> sonnet -> spec default
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-roadmapper'), 'gpt-5.4');
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-roadmapper'), 'gpt-5.6-terra');
});
test('per-agent override beats profile override beats default', () => {
@@ -316,7 +315,7 @@ describe('issue #2517: field-merge of overrides with built-in defaults (finding
model_profile: 'quality',
model_profile_overrides: { codex: { opus: { reasoning_effort: 'low' } } },
});
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.5');
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.6-sol');
const eff = resolveEffortInternal(tmpDir, 'gsd-planner');
const rendered = renderEffortForRuntime('codex', eff);
assert.strictEqual(rendered.param, 'model_reasoning_effort');
@@ -355,7 +354,7 @@ describe('issue #2517: field-merge of overrides with built-in defaults (finding
tier: 'opus',
overrides: { codex: { opus: { reasoning_effort: 'low' } } },
});
assert.deepStrictEqual(entry, { model: 'gpt-5.5', reasoning_effort: 'low' });
assert.deepStrictEqual(entry, { model: 'gpt-5.6-sol', reasoning_effort: 'low' });
});
test('resolveTierEntry helper: unknown runtime + no overrides -> null', () => {
@@ -396,7 +395,7 @@ describe('issue #2517: unknown runtime render param is null (effort does not lea
writeConfig(tmpDir, {
runtime: 'codx',
model_profile: 'quality',
model_profile_overrides: { codx: { opus: { model: 'gpt-5.4', reasoning_effort: 'xhigh' } } },
model_profile_overrides: { codx: { opus: { model: 'gpt-5.6-terra', reasoning_effort: 'xhigh' } } },
});
const eff = resolveEffortInternal(tmpDir, 'gsd-planner');
const rendered = renderEffortForRuntime('codx', eff);
@@ -412,9 +411,9 @@ describe('issue #2517: unknown runtime + safe fallback', () => {
test('unknown runtime falls back to Claude-alias safe default (no Codex IDs leaked)', () => {
writeConfig(tmpDir, { runtime: 'mystery-runtime', model_profile: 'quality' });
// Should NOT emit gpt-5.4 — should fall back to Claude alias
// Should NOT emit gpt-5.6-sol — should fall back to Claude alias
const resolved = resolveModelInternal(tmpDir, 'gsd-planner');
assert.notStrictEqual(resolved, 'gpt-5.4');
assert.notStrictEqual(resolved, 'gpt-5.6-sol');
assert.strictEqual(resolved, 'opus');
});
@@ -432,7 +431,7 @@ describe('issue #2517: unknown runtime + safe fallback', () => {
test('runtime:"codex" but missing model_profile_overrides[codex] uses spec defaults', () => {
writeConfig(tmpDir, { runtime: 'codex', model_profile: 'quality' });
// No model_profile_overrides at all — built-in Codex defaults take over
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.5');
assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-planner'), 'gpt-5.6-sol');
});
});
@@ -556,7 +555,7 @@ describe('issue #2517: install end-to-end — per-project config reaches Codex T
assert.ok(resolver, 'expected a resolver from per-project config');
assert.strictEqual(resolver.runtime, 'codex');
const entry = resolver.resolve('gsd-planner');
assert.deepStrictEqual(entry, { model: 'gpt-5.5', reasoning_effort: 'xhigh' });
assert.deepStrictEqual(entry, { model: 'gpt-5.6-sol', reasoning_effort: 'xhigh' });
});
test('per-project config wins over global ~/.gsd/defaults.json', () => {
@@ -569,7 +568,7 @@ describe('issue #2517: install end-to-end — per-project config reaches Codex T
const resolver = readGsdRuntimeProfileResolver(tmpDir);
assert.strictEqual(resolver.runtime, 'codex');
const entry = resolver.resolve('gsd-planner');
assert.strictEqual(entry.model, 'gpt-5.5');
assert.strictEqual(entry.model, 'gpt-5.6-sol');
});
test('generated Codex TOML embeds model = and model_reasoning_effort = lines', () => {
@@ -581,7 +580,7 @@ describe('issue #2517: install end-to-end — per-project config reaches Codex T
null,
resolver
);
assert.match(toml, /^model = "gpt-5\.5"$/m);
assert.match(toml, /^model = "gpt-5\.6-sol"$/m);
assert.match(toml, /^model_reasoning_effort = "xhigh"$/m);
});
@@ -636,7 +635,7 @@ describe('issue #2517: RUNTIME_PROFILE_MAP single source of truth (finding #16)'
// entries through `resolveTierEntry`, so any future drift between the two
// files would surface as a test failure here rather than a silent bug.
const codexOpus = RUNTIME_PROFILE_MAP.codex?.opus;
assert.deepStrictEqual(codexOpus, { model: 'gpt-5.5', reasoning_effort: 'xhigh' });
assert.deepStrictEqual(codexOpus, { model: 'gpt-5.6-sol', reasoning_effort: 'xhigh' });
const claudeOpus = RUNTIME_PROFILE_MAP.claude?.opus;
assert.deepStrictEqual(claudeOpus, { model: 'claude-opus-4-8' });
});