@codexapi/codexclaude 2.0.11 → 2.0.12

package/CUSTOMIZATIONS.md

@@ -5,8 +5,8 @@
 ## Upstream Runtime
 
 - Official package: `@openai/codex`
-- Pinned runtime version: `0.140.0`
-- Local launcher version: `2.0.11`
+- Pinned runtime version: `0.141.0`
+- Local launcher version: `2.0.12`
 
 ## Launcher Behavior
 
@@ -22,7 +22,7 @@
 
 The launcher writes a Codex model provider named `codexapi`:
 
-- `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.
+- `base_url = "https://codexapi.pro/v1"` for ChatGPT-5.5, Deepseek v4 Budget, and Google Gemini Flash 3.5, 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
@@ -30,16 +30,19 @@ 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-4-8`, 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`, `deepseek-v4-pro`, and `gemini-3.5-flash`.
 - Reasoning effort displayed in Codex: `xhigh`
 - Server-side upstream reasoning effort: `low`, enforced by CodexAPI.pro regardless of client display.
-- Local model catalog: `~/.codexclaude/model_catalog.json`; this keeps native Codex `/model` limited to the three supported CodexAPI.pro choices and prevents fallback metadata warnings for Opus 4.8 and Deepseek v4 Budget.
+- Local model catalog: `~/.codexclaude/model_catalog.json`; this keeps native Codex `/model` limited to the four supported CodexAPI.pro choices and prevents fallback metadata warnings for Opus 4.8, Deepseek v4 Budget, and Google Gemini Flash 3.5.
 - Service tier: omitted by default; `/fast` remains a user-controlled Codex setting and is billed server-side when active.
 - Approval policy: `never`
 - Sandbox mode: `danger-full-access`
 - TUI status line: `model-with-reasoning`, `fast-mode`, `current-dir`
 - 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.
+- Google Gemini Flash 3.5 Responses traffic keeps the user-visible Gemini model id while CodexAPI.pro routes it internally through Sonnet 4.6 with low server effort.
+
+Current backend state verified on 2026-06-18: CodexAPI.pro is routing ChatGPT-5.5 traffic through the signed-in Codex account path with `CODEXAPI_GPT55_ROUTE_MODE=codex`. Admin Manage Models can switch cross-model routing to GPT-5.5 via Opus 4.8 or Opus 4.8 via GPT-5.5. This is server-side operational routing and must not change the launcher-visible model ids, model catalog, or customer-facing labels.
 
 ## Wallet Display
 

package/README.md

@@ -1,8 +1,8 @@
 # codexclaude
 
-`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.
+`codexclaude` is the CodexAPI.pro launcher for customers who want one coding CLI that can use ChatGPT-5.5, Opus 4.8, Deepseek v4 Budget, or Google Gemini Flash 3.5 against the same CodexAPI.pro Token Wallet.
 
-Version `2.0.11` launches the official OpenAI Codex CLI `0.140.0` package and applies CodexAPI.pro account, wallet, model, and Full Access defaults before Codex starts.
+Version `2.0.12` launches the official OpenAI Codex CLI `0.141.0` package and applies CodexAPI.pro account, wallet, model, and Full Access defaults before Codex starts.
 
 ## Install
 
@@ -48,7 +48,7 @@ Switch model:
 codexclaude model
 ```
 
-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.
+Available model labels are `ChatGPT-5.5`, `Opus 4.8`, `Deepseek v4 Budget`, and `Google Gemini Flash 3.5`. All four use the CodexAPI.pro Responses-compatible endpoint and the same customer Token Wallet.
 
 Show current launcher changes:
 
@@ -73,14 +73,15 @@ codexclaude status
 ## Preserved CodexAPI.pro Customizations
 
 - Dashboard username or email plus password login.
-- ChatGPT-5.5, Opus 4.8, or Deepseek v4 Budget model selection.
+- ChatGPT-5.5, Opus 4.8, Deepseek v4 Budget, or Google Gemini Flash 3.5 model selection.
 - CodexAPI.pro Responses-compatible provider at `https://codexapi.pro/v1`.
 - Full Access defaults: approval policy `never` and sandbox mode `danger-full-access`.
 - xhigh visible reasoning in the local Codex UI while CodexAPI.pro keeps upstream runtime effort server-managed.
-- A local `~/.codexclaude/model_catalog.json` file so native Codex `/model` lists only ChatGPT-5.5, Opus 4.8, and Deepseek v4 Budget.
+- A local `~/.codexclaude/model_catalog.json` file so native Codex `/model` lists only ChatGPT-5.5, Opus 4.8, Deepseek v4 Budget, and Google Gemini Flash 3.5.
 - No default fast service tier. Fast mode is billed only when the user enables it inside Codex.
-- Official Codex `0.140.0` runtime with the current profile-compatible config enabled.
+- Official Codex `0.141.0` runtime with the current profile-compatible config enabled.
 - Token Wallet balance lookup before launch and in `codexclaude status`.
 - Opus 4.8 tool-call compatibility through the Chicago CodexAPI.pro Responses gateway.
+- Google Gemini Flash 3.5 is visible to users while CodexAPI.pro routes it server-side through the approved Sonnet 4.6 low-effort bridge.
 - 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

@@ -10,8 +10,8 @@ import { stdin as input, stdout as output } from "node:process";
 
 const require = createRequire(import.meta.url);
 
-const APP_VERSION = "2.0.11";
-const CODEX_VERSION = "0.140.0";
+const APP_VERSION = "2.0.12";
+const CODEX_VERSION = "0.141.0";
 const DISPLAY_REASONING_EFFORT = "xhigh";
 const SERVER_REASONING_EFFORT = "low";
 const API_ORIGIN = (process.env.CODEXCLAUDE_API_ORIGIN || "https://codexapi.pro").replace(/\/+$/, "");
@@ -58,6 +58,11 @@ const MODELS = {
     aliases: ["3", "deepseek", "deepseek-v4", "deepseek-v4-pro", "budget"],
     budget: true,
   },
+  "gemini-3.5-flash": {
+    id: "gemini-3.5-flash",
+    label: "Google Gemini Flash 3.5",
+    aliases: ["4", "gemini", "flash", "gemini-flash", "gemini-3.5-flash", "gemini-flash-3.5", "google-gemini-flash-3.5"],
+  },
 };
 
 async function main() {
@@ -117,7 +122,7 @@ codexclaude ${APP_VERSION}
 
 Commands:
   codexclaude login       Login with CodexAPI.pro username/email and password
-  codexclaude model       Select ChatGPT-5.5, Opus 4.8, or Deepseek v4 Budget
+  codexclaude model       Select ChatGPT-5.5, Opus 4.8, Deepseek v4 Budget, or Google Gemini Flash 3.5
   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
@@ -221,13 +226,14 @@ async function askModel(rl, current) {
   console.log("  1. ChatGPT-5.5");
   console.log("  2. Opus 4.8");
   console.log("  3. Deepseek v4 Budget");
+  console.log("  4. Google Gemini Flash 3.5");
   const answer = (await rl.question(`Model [${currentLabel}]: `)).trim().toLowerCase();
   if (!answer) {
     return MODELS[current] ? current : "gpt-5.5";
   }
   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 4.8, or 3 for Deepseek v4 Budget.");
+    throw new Error("Unknown model choice. Enter 1 for ChatGPT-5.5, 2 for Opus 4.8, 3 for Deepseek v4 Budget, or 4 for Google Gemini Flash 3.5.");
   }
   return match.id;
 }
@@ -503,6 +509,9 @@ function modelCatalogDescription(modelId) {
   if (modelId === "deepseek-v4-pro") {
     return "CodexAPI.pro Deepseek v4 Budget coding route with local Codex tools and wallet billing.";
   }
+  if (modelId === "gemini-3.5-flash") {
+    return "CodexAPI.pro Google Gemini Flash 3.5 coding route with local Codex tools and wallet billing.";
+  }
   return "CodexAPI.pro ChatGPT-5.5 coding route with local Codex tools and wallet billing.";
 }
 
@@ -693,6 +702,9 @@ function modelStatusName(model) {
   if (model === "deepseek-v4-pro") {
     return "deepseek-v4 budget";
   }
+  if (model === "gemini-3.5-flash") {
+    return "gemini flash 3.5";
+  }
   return "gpt-5.5";
 }
 
@@ -704,6 +716,9 @@ function normalizeConfig(config) {
   if (normalized.model === "claude-opus-4-7") {
     normalized.model = "claude-opus-4-8";
   }
+  if (["gemini-flash-3.5", "gemini-flash-3-5", "google-gemini-flash-3.5"].includes(normalized.model)) {
+    normalized.model = "gemini-3.5-flash";
+  }
   if (!MODELS[normalized.model]) {
     normalized.model = "gpt-5.5";
   }

package/codexclaude.md

@@ -9,8 +9,8 @@ there is no supported configuration or API boundary that can solve the issue.
 ## Current Release
 
 - Launcher package: `@codexapi/codexclaude`
-- Launcher version: `2.0.11`
-- Official Codex runtime dependency: `@openai/codex@0.140.0`
+- Launcher version: `2.0.12`
+- Official Codex runtime dependency: `@openai/codex@0.141.0`
 - Public install command: `npm install -g @codexapi/codexclaude@latest`
 - Default API origin: `https://codexapi.pro`
 - Normal Responses base URL: `https://codexapi.pro/v1`
@@ -19,16 +19,19 @@ there is no supported configuration or API boundary that can solve the issue.
 - Generated Codex config: `~/.codex/config.toml`
 - Generated Codex model catalog: `~/.codexclaude/model_catalog.json`
 
+State verified on 2026-06-18: the launcher pins official Codex CLI `0.141.0`. Backend routing currently sends ChatGPT-5.5 traffic through the signed-in Codex account path with `CODEXAPI_GPT55_ROUTE_MODE=codex`. Admin Manage Models can switch cross-model routing to GPT-5.5 via Opus 4.8 or Opus 4.8 via GPT-5.5; this is server routing state and must not collapse the launcher model list or rename customer-selected model ids.
+
 ## Required User-Facing Model Behavior
 
-`codexclaude` supports exactly three visible model choices:
+`codexclaude` supports exactly four visible model choices:
 
 - `gpt-5.5` displayed as `ChatGPT-5.5`
 - `claude-opus-4-8` displayed as `Opus 4.8`
 - `deepseek-v4-pro` displayed as `Deepseek v4 Budget`
+- `gemini-3.5-flash` displayed as `Google Gemini Flash 3.5`
 
-The launcher command `codexclaude model` must list only those three options.
-The native Codex `/model` picker must also list only those three options. This
+The launcher command `codexclaude model` must list only those four options.
+The native Codex `/model` picker must also list only those four options. This
 is enforced by writing `model_catalog_json` in `~/.codex/config.toml` and
 creating a complete Codex-compatible catalog at
 `~/.codexclaude/model_catalog.json`.
@@ -53,7 +56,7 @@ because the request body model is how CodexAPI.pro snapshots routing and
 billing before generation starts. The correct fix is to provide valid metadata
 for `claude-opus-4-8`.
 
-`bin/codexclaude.js` writes a local catalog with full metadata for all three
+`bin/codexclaude.js` writes a local catalog with full metadata for all four
 supported slugs. Each entry must include, at minimum:
 
 - `slug`
@@ -72,7 +75,7 @@ supported slugs. Each entry must include, at minimum:
 - `input_modalities`
 - `additional_speed_tiers`
 
-Keep `visibility = "list"` for the three supported entries. Do not include any
+Keep `visibility = "list"` for the four supported entries. Do not include any
 other list-visible models in this catalog.
 
 ## Reasoning Display Versus Server Runtime
@@ -138,7 +141,7 @@ terminal_title = ["project-name", "model-with-reasoning", "run-state"]
 ```
 
 The selected model must remain the user's chosen slug. Do not force the local
-config model to `gpt-5.5` when Opus or Deepseek is selected. The backend can
+config model to `gpt-5.5` when Opus, Deepseek, or Gemini is selected. The backend can
 route any selected model through GPT-5.5 or another upstream internally, but the
 client request must preserve the user-facing selected slug for display,
 snapshotting, and billing records.
@@ -155,6 +158,10 @@ region-aware unless operations explicitly changes the routing policy.
 this through the CodexAPI.pro-compatible path according to the active server
 policy.
 
+`gemini-3.5-flash` uses the configured API origin. The backend must keep
+`gemini-3.5-flash` visible to the user and usage records while routing the
+request internally through `claude-sonnet-4-6` at low server effort.
+
 The launcher must send these headers for every model:
 
 - `X-CodexAPI-Client: codexclaude`
@@ -205,7 +212,7 @@ When upgrading official `@openai/codex`:
 1. Update `CODEX_VERSION` in `bin/codexclaude.js`.
 2. Update `package.json` and `package-lock.json` to the same official Codex version.
 3. Keep the launcher package version higher than the last published version.
-4. Preserve the three-model `MODELS` map and aliases.
+4. Preserve the four-model `MODELS` map and aliases.
 5. Preserve `DISPLAY_REASONING_EFFORT = "xhigh"` and `SERVER_REASONING_EFFORT = "low"`.
 6. Preserve `writeModelCatalog()` and the `model_catalog_json` line in generated config.
 7. Preserve Full Access defaults: `approval_policy = "never"` and `sandbox_mode = "danger-full-access"`.
@@ -225,7 +232,7 @@ Run syntax validation:
 node --check bin/codexclaude.js
 ```
 
-Create a temporary home, write config, and verify Codex can parse the three
+Create a temporary home, write config, and verify Codex can parse the four
 model catalog entries without making a model call:
 
 ```bash
@@ -244,6 +251,7 @@ The JSON output must contain exactly:
 - `gpt-5.5`
 - `claude-opus-4-8`
 - `deepseek-v4-pro`
+- `gemini-3.5-flash`
 
 The Opus entry must have `default_reasoning_level = "xhigh"` and must not use
 fallback metadata.
@@ -262,6 +270,13 @@ python3 -m py_compile app/main.py app/openai_compat.py app/config.py app/postgre
 /root/codexapi/.venv/bin/pytest -q tests/test_openai_compat.py tests/test_main_helpers.py
 ```
 
+## Version 2.0.12 Changes
+
+- Updated the official OpenAI Codex runtime dependency to `@openai/codex@0.141.0`.
+- Added Google Gemini Flash 3.5 as a fourth visible launcher and native Codex `/model` choice.
+- Kept Gemini visible in client config, response metadata, and usage records while the backend routes it through Sonnet 4.6 low effort.
+- Preserved the CodexAPI.pro launcher layer, Full Access defaults, xhigh visible reasoning, server-managed low runtime effort, wallet auth, and Opus 4.8 Chicago routing.
+
 ## Version 2.0.11 Changes
 
 - Updated the official OpenAI Codex runtime dependency to `@openai/codex@0.140.0`.

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@codexapi/codexclaude",
-  "version": "2.0.11",
-  "description": "CodexAPI.pro coding CLI launcher for ChatGPT-5.5, Opus 4.8, and Deepseek v4 Budget, powered by official Codex CLI 0.140.0.",
+  "version": "2.0.12",
+  "description": "CodexAPI.pro coding CLI launcher for ChatGPT-5.5, Opus 4.8, Deepseek v4 Budget, and Google Gemini Flash 3.5, powered by official Codex CLI 0.141.0.",
   "license": "Apache-2.0",
   "type": "module",
   "bin": {
@@ -17,7 +17,7 @@
     "node": ">=20"
   },
   "dependencies": {
-    "@openai/codex": "0.140.0"
+    "@openai/codex": "0.141.0"
   },
   "publishConfig": {
     "access": "public"
@@ -27,6 +27,8 @@
     "claude",
     "opus",
     "deepseek",
+    "gemini",
+    "flash",
     "budget",
     "codexapi",
     "coding-cli"