feat(sse): restore GPT-6 Astra effort aliases and Codex 0.153.4 pin (#13026)

Three related things that genuinely belong together: the registry and suffix splitter not knowing Astra while the live catalog serves it, the Codex client pin Astra requires, and dropping `next/font/google` so a production image build does not reach fonts.googleapis.com. --- Validated in one consolidated worktree cut from `release/v3.8.51`, boarded with the other 19 PRs of this batch. Two in-batch conflicts, both additive and resolved by keeping each side: the `ENVIRONMENT.md` table (#13035 + #13011) and the `chatHelpers.ts` import block (#12975 on the tip + #13017). - `typecheck:core` clean; `check:dashboard-typecheck` OK (206 pre-existing, within baseline); `check:changelog-integrity` OK; `check:docs-counts` migrations ✓ - complexity 2816 / baseline 3218 and cognitive-complexity 1271 / baseline 1437 — both under baseline - 531 of 532 focused assertions green across the batch's 46 test files - `check-file-size` rebaselined for the batch's real growth (annotation `_rebaseline_2026_09_11_mergebatch_v3851_houminxi`, landed on #13038), attributed per PR The single red is **not this batch**: `tests/unit/combo/quota-weighted-strategy.test.ts` → "A/B isolation: 7 hard-empty + 2 at 0.5% + 1 at 40%, floor=1" asserts an order between two connections of identical weight and flakes on the pure tip too — 2 failures in 4 runs at `origin/release/v3.8.51` with nothing from this batch applied. ⚠️ base-red inherited: #12732 — `Docs Gates`, `Merge integrity`, `No new ESLint warnings`, `Unit Tests fast-path` and `Fast Quality Gates` reproduce on the pure tip (provider count 356 vs the 358 the modules define, SKILL.md drift, and `open-sse/utils/stream.ts` at 3115 > frozen 3098, untouched here). Thanks @HouMinXi — the live evidence on these (X500 logs, `storage.sqlite` state, real `/v1/models` probes, the 36-minute outage write-up) is what let a 20-PR batch be reviewed as a unit.
2026-09-14 10:52:17 +03:00 · 2026-09-11 18:28:25 -04:00
parent f4fd9190b3
commit d92bc8ef7a
25 changed files with 333 additions and 51 deletions
--- a/src/app/layout.tsx
+++ b/src/app/layout.tsx
@@ -1,4 +1,3 @@
-import { Inter } from "next/font/google";
 import "./globals.css";
 import { ThemeProvider } from "@/shared/components/ThemeProvider";
 import { NextIntlClientProvider } from "next-intl";
@@ -11,11 +10,6 @@ import { PwaRegister } from "@/shared/components/PwaRegister";
 import { LocaleAutoDetect } from "@/shared/components/LocaleAutoDetect";
 import { BasePathNetworkProvider } from "@/shared/components/BasePathNetworkProvider";

-const inter = Inter({
-  subsets: ["latin"],
-  variable: "--font-inter",
-});
-
 export const viewport: Viewport = {
  themeColor: "#0b0f1a",
  viewportFit: "cover",
@@ -135,7 +129,7 @@ export default async function RootLayout({ children }) {
          }}
        />
      </head>
-      <body className={`${inter.variable} font-sans antialiased`} suppressHydrationWarning>
+      <body className="font-sans antialiased" suppressHydrationWarning>
        <a
          href="#main-content"
          className="sr-only focus:not-sr-only focus:absolute focus:top-2 focus:left-2 focus:z-50 focus:px-4 focus:py-2 focus:bg-[#6366f1] focus:text-white focus:rounded-lg focus:text-sm focus:font-semibold focus:shadow-lg"
--- a/src/lib/usage/costCalculator.ts
+++ b/src/lib/usage/costCalculator.ts
@@ -101,6 +101,8 @@ export function getCodexFastCostMultiplier(

  const modelKey = stripCodexEffortSuffix(normalizeModelName(String(model || "")).toLowerCase());
  const compactModelKey = modelKey.replace(/-/g, "");
+  // Codex Astra Fast is 2.5x Standard (https://developers.openai.com/codex/pricing).
+  if (modelKey === "gpt-6-astra" || compactModelKey === "gpt6astra") return 2.5;
  if (
    /^gpt-5\.6-(?:sol|terra|luna)$/.test(modelKey) ||
    /^gpt5\.6(?:sol|terra|luna)$/.test(compactModelKey)
--- a/src/shared/constants/codexClient.ts
+++ b/src/shared/constants/codexClient.ts
@@ -3,7 +3,7 @@
 // refresh this so the fingerprint OpenAI sees from the OAuth/Responses face
 // matches the real client version. Overridable per-deployment via
 // CODEX_CLIENT_VERSION.
-export const DEFAULT_CODEX_CLIENT_VERSION = "0.153.2";
+export const DEFAULT_CODEX_CLIENT_VERSION = "0.153.4";
 export const CODEX_CLI_RS_ORIGINATOR = "codex_cli_rs";

 export function getCodexCliRsHeaders(
--- a/src/shared/constants/modelSpecs.ts
+++ b/src/shared/constants/modelSpecs.ts
@@ -118,6 +118,12 @@ const GEMINI_36_FLASH_MODEL_SPEC = {
 } satisfies ModelSpec;

 export const MODEL_SPECS: Record<string, ModelSpec> = {
+  // Public model limits; the Codex registry supplies its smaller OAuth window.
+  // https://developers.openai.com/api/docs/models/gpt-6-astra
+  "gpt-6-astra": {
+    ...GPT_5_6_MODEL_SPEC,
+    aliases: ["openai/gpt-6-astra"],
+  },
  "gpt-5.6": {
    ...GPT_5_6_MODEL_SPEC,
    aliases: ["openai/gpt-5.6"],
--- a/src/shared/constants/pricing/frontier-labs.ts
+++ b/src/shared/constants/pricing/frontier-labs.ts
@@ -3,6 +3,7 @@
 * Pure data; merged by default-pricing.ts via spread (god-file decomposition; semantic split).
 */
 import {
+  GPT_6_ASTRA_PRICING,
  GEMINI_3_7_FLASH_PROMO_PRICING,
  GPT_5_5_PRICING,
  GPT_5_6_LUNA_PRICING,
@@ -20,6 +21,7 @@ import {

 export const DEFAULT_PRICING_FRONTIER = {
  openai: {
+    "gpt-6-astra": GPT_6_ASTRA_PRICING,
    "gpt-5.6": GPT_5_6_SOL_PRICING,
    "gpt-5.6-sol": GPT_5_6_SOL_PRICING,
    "gpt-5.6-terra": GPT_5_6_TERRA_PRICING,
--- a/src/shared/constants/pricing/oauth-subscriptions.ts
+++ b/src/shared/constants/pricing/oauth-subscriptions.ts
@@ -3,6 +3,7 @@
 * Pure data; merged by default-pricing.ts via spread (god-file decomposition; semantic split).
 */
 import {
+  GPT_6_ASTRA_PRICING,
  CLAUDE_FABLE_5_1_PRICING,
  CLAUDE_OPUS_5_PRICING,
  GEMINI_3_7_FLASH_PROMO_PRICING,
@@ -19,6 +20,10 @@ const ANTIGRAVITY_GEMINI_3_7_PRICING = {
  "gemini-3.7-flash-high": GEMINI_3_7_FLASH_PROMO_PRICING,
 };

+// Codex Standard: 250 / 25 / 1250 credits per MTok, at 25 credits per USD.
+// https://developers.openai.com/codex/pricing
+const GPT_6_ASTRA_CODEX_PRICING = GPT_6_ASTRA_PRICING;
+
 export const DEFAULT_PRICING_OAUTH = {
  cc: {
    "claude-fable-5-1": CLAUDE_FABLE_5_1_PRICING,
@@ -88,6 +93,13 @@ export const DEFAULT_PRICING_OAUTH = {
    },
  },
  cx: {
+    "gpt-6-astra": GPT_6_ASTRA_CODEX_PRICING,
+    "gpt-6-astra-ultra": GPT_6_ASTRA_CODEX_PRICING,
+    "gpt-6-astra-max": GPT_6_ASTRA_CODEX_PRICING,
+    "gpt-6-astra-xhigh": GPT_6_ASTRA_CODEX_PRICING,
+    "gpt-6-astra-high": GPT_6_ASTRA_CODEX_PRICING,
+    "gpt-6-astra-medium": GPT_6_ASTRA_CODEX_PRICING,
+    "gpt-6-astra-low": GPT_6_ASTRA_CODEX_PRICING,
    "codex-auto-review": GPT_5_5_PRICING,
    // Codex uses credits per 1M tokens. OmniRoute stores the dollar-equivalent
    // values below at the documented conversion of 25 credits per USD.
--- a/src/shared/constants/pricing/shared-tiers.ts
+++ b/src/shared/constants/pricing/shared-tiers.ts
@@ -1,6 +1,16 @@
 /**
 * Pricing data — shared per-MTok tier constants (god-file decomposition). Pure data; merged by the barrel.
 */
+// OpenAI API Standard; Codex Standard has the same dollar-equivalent rates.
+// https://openai.com/index/gpt-6-astra/
+export const GPT_6_ASTRA_PRICING = {
+  input: 10.0,
+  output: 50.0,
+  cached: 1.0,
+  reasoning: 50.0,
+  cache_creation: 12.5,
+};
+
 export const GPT_5_3_CODEX_PRICING = {
  input: 5.0,
  output: 20.0,