@codexapi/codexclaude 2.0.4 → 2.0.6

package/CUSTOMIZATIONS.md

@@ -5,8 +5,8 @@
 ## Upstream Runtime
 
 - Official package: `@openai/codex`
-- Pinned runtime version: `0.134.0`
-- Local launcher version: `2.0.4`
+- Pinned runtime version: `0.135.0`
+- Local launcher version: `2.0.6`
 
 ## Launcher Behavior
 
@@ -22,7 +22,7 @@
 
 The launcher writes a Codex model provider named `codexapi`:
 
-- `base_url = "https://codexapi.pro/v1"`
+- `base_url = "https://codexapi.pro/v1"` for ChatGPT-5.5 and Deepseek v4 Budget, or `https://api-chicago.codexapi.pro/v1` for Opus 4.8.
 - `wire_api = "responses"`
 - `supports_websockets = false`
 - `experimental_bearer_token` set to the customer API username
@@ -30,13 +30,13 @@ The launcher writes a Codex model provider named `codexapi`:
 
 ## Runtime Defaults
 
-- Model: selected by the user, defaulting to `gpt-5.5`; supported launcher choices are `gpt-5.5`, `claude-opus-4-7`, and `deepseek-v4-pro`.
+- Model: selected by the user, defaulting to `gpt-5.5`; supported launcher choices are `gpt-5.5`, `claude-opus-4-8`, and `deepseek-v4-pro`.
 - Reasoning effort: `high`
 - Service tier: `fast`
 - Approval policy: `never`
 - Sandbox mode: `danger-full-access`
 - TUI status line: `model-with-reasoning`, `fast-mode`, `current-dir`
-- Opus 4.7 Responses traffic is routed through CodexAPI.pro's working Claude tool-call bridge.
+- Opus 4.8 Responses traffic is always routed through the Chicago CodexAPI.pro Claude tool-call bridge, regardless of the selected account/dashboard region.
 - Deepseek v4 Budget Responses traffic is routed through CodexAPI.pro's Deepseek-compatible gateway.
 
 ## Wallet Display

package/README.md

@@ -1,13 +1,13 @@
 # codexclaude
 
-`codexclaude` is the CodexAPI.pro launcher for customers who want one coding CLI that can use ChatGPT-5.5, Opus 4.7, or Deepseek v4 Budget against the same CodexAPI.pro Token Wallet.
+`codexclaude` is the CodexAPI.pro launcher for customers who want one coding CLI that can use ChatGPT-5.5, Opus 4.8, or Deepseek v4 Budget against the same CodexAPI.pro Token Wallet.
 
-Version `2.0.4` launches the official OpenAI Codex CLI `0.134.0` package and applies CodexAPI.pro account, wallet, model, and Full Access defaults before Codex starts.
+Version `2.0.6` launches the official OpenAI Codex CLI `0.135.0` package and applies CodexAPI.pro account, wallet, model, and Full Access defaults before Codex starts.
 
 ## Install
 
 ```bash
-npm install -g https://codexapi.pro/downloads/codexapi-codexclaude-2.0.4.tgz
+npm install -g @codexapi/codexclaude@latest
 ```
 
 This installs the current `codexclaude` launcher from npm.
@@ -17,7 +17,7 @@ This installs the current `codexclaude` launcher from npm.
 CodexAPI.pro checks the CodexAPI.pro API and npm at startup. If a newer required launcher is available, the app stops before coding starts and shows the exact **Update Now** command:
 
 ```bash
-npm install -g https://codexapi.pro/downloads/codexapi-codexclaude-2.0.4.tgz
+npm install -g @codexapi/codexclaude@latest
 ```
 
 This does not delete your local Codex session history. The update only replaces the `codexclaude` launcher and refreshes the CodexAPI.pro provider config.
@@ -48,7 +48,7 @@ Switch model:
 codexclaude model
 ```
 
-Available model labels are `ChatGPT-5.5`, `Opus 4.7`, and `Deepseek v4 Budget`. All three use the CodexAPI.pro Responses-compatible endpoint and the same customer Token Wallet.
+Available model labels are `ChatGPT-5.5`, `Opus 4.8`, and `Deepseek v4 Budget`. All three use the CodexAPI.pro Responses-compatible endpoint and the same customer Token Wallet.
 
 Show current launcher changes:
 
@@ -73,12 +73,12 @@ codexclaude status
 ## Preserved CodexAPI.pro Customizations
 
 - Dashboard username or email plus password login.
-- ChatGPT-5.5, Opus 4.7, or Deepseek v4 Budget model selection.
+- ChatGPT-5.5, Opus 4.8, or Deepseek v4 Budget model selection.
 - CodexAPI.pro Responses-compatible provider at `https://codexapi.pro/v1`.
 - Full Access defaults: approval policy `never` and sandbox mode `danger-full-access`.
 - High reasoning and fast service tier defaults.
-- Official Codex `0.134.0` runtime with the current profile-compatible config enabled.
+- Official Codex `0.135.0` runtime with the current profile-compatible config enabled.
 - Token Wallet balance lookup before launch and in `codexclaude status`.
-- Opus 4.7 tool-call compatibility through the CodexAPI.pro Responses gateway.
+- Opus 4.8 tool-call compatibility through the Chicago CodexAPI.pro Responses gateway.
 - Backend-identifying request headers so CodexAPI.pro can enforce subscription plan rules server-side.
 - npm latest-version checks before coding starts, with an explicit update command when a newer required launcher exists.

package/bin/codexclaude.js

@@ -10,12 +10,14 @@ import { stdin as input, stdout as output } from "node:process";
 
 const require = createRequire(import.meta.url);
 
-const APP_VERSION = "2.0.4";
-const CODEX_VERSION = "0.134.0";
+const APP_VERSION = "2.0.6";
+const CODEX_VERSION = "0.135.0";
 const CODEX_REASONING_EFFORT = "high";
 const CODEX_SERVICE_TIER = "fast";
 const API_ORIGIN = (process.env.CODEXCLAUDE_API_ORIGIN || "https://codexapi.pro").replace(/\/+$/, "");
 const API_BASE_URL = `${API_ORIGIN}/v1`;
+const CHICAGO_API_ORIGIN = "https://api-chicago.codexapi.pro";
+const CHICAGO_API_BASE_URL = `${CHICAGO_API_ORIGIN}/v1`;
 const VERSION_CHECK_PATH = "/api/v1/codexclaude/version";
 const NPM_PACKAGE_NAME = "@codexapi/codexclaude";
 const NPM_LATEST_URL = "https://registry.npmjs.org/@codexapi%2Fcodexclaude/latest";
@@ -32,10 +34,10 @@ const MODELS = {
     label: "ChatGPT-5.5",
     aliases: ["1", "gpt", "gpt-5.5", "chatgpt", "chatgpt-5.5"],
   },
-  "claude-opus-4-7": {
-    id: "claude-opus-4-7",
-    label: "Opus 4.7",
-    aliases: ["2", "opus", "opus-4.7", "claude", "claude-opus-4-7"],
+  "claude-opus-4-8": {
+    id: "claude-opus-4-8",
+    label: "Opus 4.8",
+    aliases: ["2", "opus", "opus-4.8", "opus-4.7", "claude", "claude-opus-4-8", "claude-opus-4-7"],
   },
   "deepseek-v4-pro": {
     id: "deepseek-v4-pro",
@@ -102,7 +104,7 @@ codexclaude ${APP_VERSION}
 
 Commands:
   codexclaude login       Login with CodexAPI.pro username/email and password
-  codexclaude model       Select ChatGPT-5.5, Opus 4.7, or Deepseek v4 Budget
+  codexclaude model       Select ChatGPT-5.5, Opus 4.8, or Deepseek v4 Budget
   codexclaude changelog   Show the latest CodexAPI.pro launcher changes
   codexclaude setup       Rewrite ~/.codex/config.toml with Full Access defaults
   codexclaude start       Start Codex with --search
@@ -150,7 +152,8 @@ async function loginFlow() {
       throw new Error("Login succeeded but no API username was returned.");
     }
     const existing = readConfig();
-    const selectedModel = await askModel(rl, existing?.model || "gpt-5.5");
+    const normalizedExisting = normalizeConfig(existing);
+    const selectedModel = await askModel(rl, normalizedExisting?.model || "gpt-5.5");
     const config = {
       version: APP_VERSION,
       apiOrigin: API_ORIGIN,
@@ -173,6 +176,7 @@ async function modelFlow() {
   const rl = readline.createInterface({ input, output });
   try {
     config.model = await askModel(rl, config.model || "gpt-5.5");
+    config.version = APP_VERSION;
     saveConfig(config);
     writeCodexConfig(config);
     console.log(`Model set to ${MODELS[config.model].label}.`);
@@ -193,6 +197,8 @@ async function ensureReady() {
     await loginFlow();
     config = requireConfig();
   }
+  config = normalizeConfig(config);
+  saveConfig(config);
   writeCodexConfig(config);
 }
 
@@ -200,7 +206,7 @@ async function askModel(rl, current) {
   const currentLabel = MODELS[current]?.label || MODELS["gpt-5.5"].label;
   console.log("\nChoose your coding model:");
   console.log("  1. ChatGPT-5.5");
-  console.log("  2. Opus 4.7");
+  console.log("  2. Opus 4.8");
   console.log("  3. Deepseek v4 Budget");
   const answer = (await rl.question(`Model [${currentLabel}]: `)).trim().toLowerCase();
   if (!answer) {
@@ -208,7 +214,7 @@ async function askModel(rl, current) {
   }
   const match = Object.values(MODELS).find((model) => model.aliases.includes(answer));
   if (!match) {
-    throw new Error("Unknown model choice. Enter 1 for ChatGPT-5.5, 2 for Opus 4.7, or 3 for Deepseek v4 Budget.");
+    throw new Error("Unknown model choice. Enter 1 for ChatGPT-5.5, 2 for Opus 4.8, or 3 for Deepseek v4 Budget.");
   }
   return match.id;
 }
@@ -400,7 +406,9 @@ function writeCodexConfig(config) {
     const backup = `${CODEX_CONFIG_FILE}.backup.${timestamp()}`;
     copyFileSync(CODEX_CONFIG_FILE, backup);
   }
-  const model = MODELS[config.model] ? config.model : "gpt-5.5";
+  const normalized = normalizeConfig(config);
+  const model = MODELS[normalized.model] ? normalized.model : "gpt-5.5";
+  const providerBaseUrl = providerBaseUrlForConfig(normalized);
   const toml = [
     `model = ${tomlString(model)}`,
     'preferred_auth_method = "apikey"',
@@ -412,8 +420,8 @@ function writeCodexConfig(config) {
     "",
     `[model_providers.${PROVIDER_ID}]`,
     'name = "CodexAPI.pro"',
-    `base_url = ${tomlString(API_BASE_URL)}`,
-    `experimental_bearer_token = ${tomlString(config.username)}`,
+    `base_url = ${tomlString(providerBaseUrl)}`,
+    `experimental_bearer_token = ${tomlString(normalized.username)}`,
     'wire_api = "responses"',
     "supports_websockets = false",
     `http_headers = { "X-CodexAPI-Client" = "codexclaude", "X-CodexAPI-Client-Version" = ${tomlString(APP_VERSION)}, "X-CodexAPI-Selected-Model" = ${tomlString(model)} }`,
@@ -429,7 +437,7 @@ function writeCodexConfig(config) {
 
 function readConfig() {
   try {
-    return JSON.parse(readFileSync(CONFIG_FILE, "utf8"));
+    return normalizeConfig(JSON.parse(readFileSync(CONFIG_FILE, "utf8")));
   } catch {
     return null;
   }
@@ -445,7 +453,7 @@ function requireConfig() {
 
 function saveConfig(config) {
   mkdirSync(CONFIG_DIR, { recursive: true });
-  writeFileSync(CONFIG_FILE, `${JSON.stringify(config, null, 2)}\n`, { encoding: "utf8", mode: 0o600 });
+  writeFileSync(CONFIG_FILE, `${JSON.stringify(normalizeConfig(config), null, 2)}\n`, { encoding: "utf8", mode: 0o600 });
 }
 
 function logout() {
@@ -465,6 +473,7 @@ async function status() {
   console.log(`Reasoning: ${CODEX_REASONING_EFFORT}`);
   console.log(`Service tier: ${CODEX_SERVICE_TIER}`);
   console.log(`API: ${config.apiOrigin || API_ORIGIN}`);
+  console.log(`Model API route: ${providerOriginLabel(config)}`);
   console.log(`Codex config: ${CODEX_CONFIG_FILE}`);
   try {
     const wallet = await walletSnapshot(config);
@@ -493,6 +502,7 @@ async function runCodex(args) {
     CODEXCLAUDE_CODEX_VERSION: CODEX_VERSION,
     CODEXCLAUDE_MODEL_ID: config.model,
     CODEXCLAUDE_MODEL_LABEL: MODELS[config.model]?.label || config.model,
+    CODEXCLAUDE_MODEL_API_BASE_URL: providerBaseUrlForConfig(config),
     CODEXCLAUDE_VERSION: APP_VERSION,
   };
   if (wallet) {
@@ -604,8 +614,8 @@ function formatStatusLine(config, wallet, cwd) {
 }
 
 function modelStatusName(model) {
-  if (model === "claude-opus-4-7") {
-    return "opus-4.7";
+  if (model === "claude-opus-4-8") {
+    return "opus-4.8";
   }
   if (model === "deepseek-v4-pro") {
     return "deepseek-v4 budget";
@@ -613,6 +623,38 @@ function modelStatusName(model) {
   return "gpt-5.5";
 }
 
+function normalizeConfig(config) {
+  if (!config || typeof config !== "object") {
+    return config;
+  }
+  const normalized = { ...config };
+  if (normalized.model === "claude-opus-4-7") {
+    normalized.model = "claude-opus-4-8";
+  }
+  if (!MODELS[normalized.model]) {
+    normalized.model = "gpt-5.5";
+  }
+  normalized.version = APP_VERSION;
+  normalized.apiOrigin = String(normalized.apiOrigin || API_ORIGIN).replace(/\/+$/, "");
+  return normalized;
+}
+
+function providerBaseUrlForConfig(config) {
+  const normalized = normalizeConfig(config);
+  if (normalized.model === "claude-opus-4-8") {
+    return CHICAGO_API_BASE_URL;
+  }
+  return `${normalized.apiOrigin || API_ORIGIN}/v1`;
+}
+
+function providerOriginLabel(config) {
+  const normalized = normalizeConfig(config);
+  if (normalized.model === "claude-opus-4-8") {
+    return `${CHICAGO_API_ORIGIN} (Chicago forced for Opus 4.8)`;
+  }
+  return normalized.apiOrigin || API_ORIGIN;
+}
+
 function formatUsd(value) {
   return `$${Number(value || 0).toLocaleString("en-US", {
     minimumFractionDigits: 2,

package/codexclaude.md

@@ -5,11 +5,11 @@ This file tracks the CodexAPI.pro-specific layer that must be re-applied after p
 ## Current Release
 
 - Launcher package: `@codexapi/codexclaude`
-- Launcher version: `2.0.4`
-- Official Codex runtime dependency: `@openai/codex@0.134.0`
-- Public install command: `npm install -g https://codexapi.pro/downloads/codexapi-codexclaude-2.0.4.tgz`
+- Launcher version: `2.0.6`
+- Official Codex runtime dependency: `@openai/codex@0.135.0`
+- Public install command: `npm install -g @codexapi/codexclaude@latest`
 - Default API origin: `https://codexapi.pro`
-- Responses base URL: `https://codexapi.pro/v1`
+- Responses base URL: `https://codexapi.pro/v1` for ChatGPT-5.5 and Deepseek v4 Budget; `https://api-chicago.codexapi.pro/v1` for Opus 4.8.
 
 ## Reapply Checklist After Upstream Codex Updates
 
@@ -33,7 +33,7 @@ This file tracks the CodexAPI.pro-specific layer that must be re-applied after p
 ## Model Choices
 
 - `gpt-5.5`: default ChatGPT-5.5 coding route.
-- `claude-opus-4-7`: Opus 4.7 coding route through CodexAPI.pro Responses compatibility.
+- `claude-opus-4-8`: Opus 4.8 coding route through Chicago CodexAPI.pro Responses compatibility.
 - `deepseek-v4-pro`: Deepseek v4 Budget coding route through CodexAPI.pro Responses compatibility.
 
 The selected model must be written into `~/.codex/config.toml` before the Codex process starts. The backend snapshots the route at request start; the launcher must not change the model mid-generation.
@@ -47,6 +47,18 @@ The selected model must be written into `~/.codex/config.toml` before the Codex
 - Updated the forced update message so users see the exact npm command.
 - Added this customization ledger for future upstream Codex merges.
 
+## Version 2.0.5 Changes
+
+- Published the launcher under the official npm org package `@codexapi/codexclaude`.
+- Updated install and update instructions to use `npm install -g @codexapi/codexclaude@latest`.
+
+## Version 2.0.6 Changes
+
+- Updated the official Codex runtime dependency to `@openai/codex@0.135.0`.
+- Migrated the Claude/Opus launcher choice from Opus 4.7 to Opus 4.8 while accepting old Opus 4.7 aliases for existing users.
+- Forced Opus 4.8 `codexclaude` Responses traffic to `https://api-chicago.codexapi.pro/v1` regardless of the account/dashboard region selected by the user.
+- Kept ChatGPT-5.5 and Deepseek v4 Budget region-aware.
+
 ## Validation Commands
 
 ```bash

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@codexapi/codexclaude",
-  "version": "2.0.4",
-  "description": "CodexAPI.pro coding CLI launcher for ChatGPT-5.5, Opus 4.7, and Deepseek v4 Budget, powered by official Codex CLI 0.134.0.",
+  "version": "2.0.6",
+  "description": "CodexAPI.pro coding CLI launcher for ChatGPT-5.5, Opus 4.8, and Deepseek v4 Budget, powered by official Codex CLI 0.135.0.",
   "license": "Apache-2.0",
   "type": "module",
   "bin": {
@@ -17,7 +17,7 @@
     "node": ">=20"
   },
   "dependencies": {
-    "@openai/codex": "0.134.0"
+    "@openai/codex": "0.135.0"
   },
   "publishConfig": {
     "access": "public"