@codexapi/codexclaude 2.0.14 → 2.0.16

package/CUSTOMIZATIONS.md

@@ -1,12 +1,13 @@
 # CodexAPI.pro Customizations
 
-`codexclaude` intentionally tracks the official OpenAI Codex CLI while keeping a thin CodexAPI.pro launcher layer.
+`codexclaude` intentionally tracks the managed coding runtime while keeping a thin CodexAPI.pro launcher layer.
 
-## Upstream Runtime
+## Runtime
 
-- Official package: `@openai/codex`
-- Pinned runtime version: `0.142.5`
-- Local launcher version: `2.0.14`
+- Customer-facing app name: `Magnetapi.org Coding Agent`
+- Local launcher version: `2.0.16`
+- Bundled official Codex dependency: `@openai/codex@0.143.0`
+- Bundled coding runtime is managed internally and must not be advertised in customer-facing startup text.
 
 ## Launcher Behavior
 
@@ -14,16 +15,16 @@
 - Saves the returned API username in `~/.codexclaude/config.json`.
 - Rewrites `~/.codex/config.toml` before every launch.
 - Starts official Codex with `--search` by default.
-- Passes all unknown commands directly to the official Codex CLI.
-- Provides `codexclaude changelog` so users can see forced-update changes from the terminal.
+- Passes all unknown commands directly to the bundled coding runtime.
+- Provides `codexclaude changelog` so users can see recommended or required update changes from the terminal.
 - Does not expose separate `codexclaude status` or `codexclaude usage` commands; wallet information remains a compact pre-launch line.
-- Checks npm latest at startup and blocks coding with an Update Now command when a newer launcher is available.
+- Shows a non-blocking update notice at startup when a newer recommended launcher is available. Only versions below the backend minimum may be blocked.
 
 ## Provider Config
 
 The launcher writes a Codex model provider named `codexapi`:
 
-- `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.
+- `base_url = "https://codexapi.pro/v1"` for ChatGPT-5.5, or `https://api-chicago.codexapi.pro/v1` for Claude-family models.
 - `wire_api = "responses"`
 - `supports_websockets = false`
 - `experimental_bearer_token` set to the customer API username
@@ -31,20 +32,18 @@ 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`, `claude-sonnet-5`, `claude-fable-5`, `deepseek-v4-pro`, and `gemini-3.5-flash`.
+- Model: selected by the user, defaulting to `gpt-5.5`; supported launcher choices are `gpt-5.5`, `claude-opus-4-8`, `claude-sonnet-5`, and `claude-fable-5`.
 - Reasoning effort displayed in Codex: `xhigh`
 - Server-side upstream reasoning effort: `high`, enforced by CodexAPI.pro regardless of client display.
-- Local model catalog: `~/.codexclaude/model_catalog.json`; this keeps native Codex `/model` limited to the six supported CodexAPI.pro choices and prevents fallback metadata warnings for Opus 4.8, Sonnet 5, Fable 5, Deepseek v4 Budget, and Google Gemini Flash 3.5.
+- 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, Sonnet 5, and Fable 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`
 - Claude-family Responses traffic uses the Claude-compatible CodexAPI.pro endpoint for CodexAPI.pro and ChatPlus accounts, while MyAPI.world accounts keep the MyAPI endpoint.
 - Fable 5 stays visible to the user while the backend applies the custom routed premium path and 2x billing multiplier.
-- 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 5 with the configured server effort.
 
-Current backend state verified on 2026-06-25: Admin Manage Models controls runtime routing server-side. This operational routing must not change the launcher-visible model ids, model catalog, or customer-facing labels.
+Current backend state verified on 2026-07-08: Admin Manage Models controls runtime routing server-side. This operational routing 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, Sonnet 5, Fable 5, Deepseek v4 Budget, or Google Gemini Flash 3.5 against the same Token Wallet.
+`codexclaude` installs the Magnetapi.org Coding Agent for customers who want one coding CLI that can use ChatGPT-5.5, Opus 4.8, Sonnet 5, or Fable 5 against the same Token Wallet.
 
-Version `2.0.14` launches the official OpenAI Codex CLI `0.142.5` package and applies account, wallet, model, and Full Access defaults before Codex starts.
+Version `2.0.16` applies account, wallet, model, and Full Access defaults before the coding session starts. It bundles official Codex `0.143.0`.
 
 ## Install
 
@@ -12,12 +12,12 @@ npm install -g @codexapi/codexclaude@latest
 
 This installs the current `codexclaude` launcher from npm.
 
-## Required updates
+## Update Notices
 
-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:
+CodexAPI.pro checks the CodexAPI.pro API and npm at startup. If a newer recommended launcher is available, the app shows a clear update notice and the exact command, then lets you keep coding. Only versions below the backend minimum are blocked.
 
 ```bash
-npm install -g @codexapi/codexclaude@latest
+npm install -g @codexapi/codexclaude@2.0.16
 ```
 
 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 4.8`, `Sonnet 5`, `Fable 5`, `Deepseek v4 Budget`, and `Google Gemini Flash 3.5`. All six use a Responses-compatible endpoint and the same customer Token Wallet.
+Available model labels are `ChatGPT-5.5`, `Opus 4.8`, `Sonnet 5`, and `Fable 5`. All four use a Responses-compatible endpoint and the same customer Token Wallet.
 
 Show current launcher changes:
 
@@ -67,15 +67,14 @@ gpt-5.5 xhigh · ~/codexapi · Wallet $20.00
 ## Preserved CodexAPI.pro Customizations
 
 - Dashboard username or email plus password login.
-- ChatGPT-5.5, Opus 4.8, Sonnet 5, Fable 5, Deepseek v4 Budget, or Google Gemini Flash 3.5 model selection.
+- ChatGPT-5.5, Opus 4.8, Sonnet 5, or Fable 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, Sonnet 5, Fable 5, Deepseek v4 Budget, and Google Gemini Flash 3.5.
+- A local `~/.codexclaude/model_catalog.json` file so native Codex `/model` lists only ChatGPT-5.5, Opus 4.8, Sonnet 5, and Fable 5.
 - No default fast service tier. Fast mode is billed only when the user enables it inside Codex.
-- Official Codex `0.142.5` runtime with the current profile-compatible config enabled.
+- Magnetapi.org Coding Agent `2.0.16` with the current profile-compatible config enabled.
 - Token Wallet balance lookup before launch without exposing separate `status` or `usage` launcher commands.
 - 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 5 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.
+- Non-blocking update notices before coding starts, with an explicit update command when a newer recommended launcher exists.

package/bin/codexclaude.js

@@ -10,8 +10,9 @@ import { stdin as input, stdout as output } from "node:process";
 
 const require = createRequire(import.meta.url);
 
-const APP_VERSION = "2.0.14";
-const CODEX_VERSION = "0.142.5";
+const APP_VERSION = "2.0.16";
+const CODEX_VERSION = "0.143.0";
+const APP_DISPLAY_NAME = "Magnetapi.org Coding Agent";
 const DISPLAY_REASONING_EFFORT = "xhigh";
 const SERVER_REASONING_EFFORT = "high";
 const API_ORIGIN = (process.env.CODEXCLAUDE_API_ORIGIN || "https://codexapi.pro").replace(/\/+$/, "");
@@ -63,24 +64,13 @@ const MODELS = {
     aliases: ["4", "fable", "fable-5", "fabel", "fabel-5", "claude-fable-5", "claude-fabel-5"],
     premium: true,
   },
-  "deepseek-v4-pro": {
-    id: "deepseek-v4-pro",
-    label: "Deepseek v4 Budget",
-    aliases: ["5", "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: ["6", "gemini", "flash", "gemini-flash", "gemini-3.5-flash", "gemini-flash-3.5", "google-gemini-flash-3.5"],
-  },
 };
 
 async function main() {
   ensureExecutable();
   const [command = "start", ...args] = process.argv.slice(2);
   if (["-v", "--version", "version"].includes(command)) {
-    console.log(`codexclaude ${APP_VERSION}`);
+    console.log(`${APP_DISPLAY_NAME} ${APP_VERSION}`);
     return;
   }
   if (["-h", "--help", "help"].includes(command)) {
@@ -125,18 +115,18 @@ async function main() {
 
 function printHelp() {
   console.log(`
-codexclaude ${APP_VERSION}
+${APP_DISPLAY_NAME} ${APP_VERSION}
 
 Commands:
   codexclaude login       Login with CodexAPI.pro username/email and password
-  codexclaude model       Select ChatGPT-5.5, Opus 4.8, Sonnet 5, Fable 5, Deepseek v4 Budget, or Google Gemini Flash 3.5
+  codexclaude model       Select ChatGPT-5.5, Opus 4.8, Sonnet 5, or Fable 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
   codexclaude resume      Resume with codex resume --search
   codexclaude logout      Remove saved codexclaude account state
 
-Any other command is passed through to official Codex CLI ${CODEX_VERSION} after config is applied.
+Any other command is passed through to the bundled coding runtime after Magnetapi.org account and model config is applied.
 `);
 }
 
@@ -283,19 +273,9 @@ async function enforceLauncherVersion() {
   if (metadata?.updateRequired || isOlderVersion(APP_VERSION, metadata?.minimumVersion)) {
     throw new Error(updateRequiredMessage(metadata));
   }
-  const npmMetadata = await npmLatestMetadata();
-  if (npmMetadata?.version && isOlderVersion(APP_VERSION, npmMetadata.version)) {
-    throw new Error(
-      updateRequiredMessage({
-        latestVersion: npmMetadata.version,
-        minimumVersion: npmMetadata.version,
-        installCommand: UPDATE_COMMAND,
-        registryInstallCommand: UPDATE_COMMAND,
-        changes: [
-          `npm latest is ${npmMetadata.version}; update codexclaude before starting a coding session.`,
-        ],
-      }),
-    );
+  const updateMetadata = optionalUpdateMetadata(metadata, await npmLatestMetadata());
+  if (updateMetadata) {
+    printOptionalUpdateNotice(updateMetadata);
   }
 }
 
@@ -394,13 +374,49 @@ function updateRequiredMessage(metadata) {
   const latest = metadata?.latestVersion || "latest";
   const minimum = metadata?.minimumVersion || latest;
   return [
-    `Update Now: CodexAPI.pro has updated to codexclaude ${latest}. Update your agent now to continue.`,
+    `Update required: CodexAPI.pro has updated to codexclaude ${latest}. Update your agent now to continue.`,
     `Installed codexclaude: ${APP_VERSION}. Required: ${minimum}. Latest: ${latest}.`,
     `Run: ${installCommand}`,
     "Your Codex session history will not be deleted. The update only replaces the codexclaude launcher and rewrites provider config backups.",
   ].join("\n");
 }
 
+function optionalUpdateMetadata(serviceMetadata, npmMetadata) {
+  const candidates = [serviceMetadata, npmMetadata].filter(Boolean);
+  let selected = null;
+  for (const candidate of candidates) {
+    const candidateVersion = candidate.latestVersion || candidate.version;
+    if (!candidateVersion || !isOlderVersion(APP_VERSION, candidateVersion)) {
+      continue;
+    }
+    if (!selected || isOlderVersion(selected.latestVersion || selected.version, candidateVersion)) {
+      selected = {
+        ...candidate,
+        latestVersion: candidateVersion,
+      };
+    }
+  }
+  return selected;
+}
+
+function printOptionalUpdateNotice(metadata) {
+  const installCommand =
+    metadata?.installCommand ||
+    metadata?.registryInstallCommand ||
+    UPDATE_COMMAND;
+  const latest = metadata?.latestVersion || metadata?.version || "latest";
+  const changes = Array.isArray(metadata?.changes) ? metadata.changes.slice(0, 4) : [];
+  const border = "─".repeat(64);
+  const line = (text) => `│ ${String(text)}`.slice(0, 65).padEnd(65) + "│";
+  console.error(`\n┌${border}┐`);
+  console.error(line(`codexclaude ${latest} is available. You can keep coding on ${APP_VERSION}.`));
+  console.error(line(`Update when ready: ${installCommand}`));
+  for (const change of changes) {
+    console.error(line(`• ${change}`));
+  }
+  console.error(`└${border}┘\n`);
+}
+
 function isOlderVersion(current, required) {
   if (!required) {
     return false;
@@ -526,12 +542,6 @@ function modelCatalogDescription(modelId) {
   if (modelId === "claude-fable-5") {
     return "CodexAPI.pro Fable 5 premium coding route with local Codex tools and wallet billing.";
   }
-  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.";
 }
 
@@ -572,6 +582,7 @@ async function runCodex(args) {
   if (!isTruthy(process.env.CODEXCLAUDE_QUIET_STATUS)) {
     console.log(formatStatusLine(config, wallet, process.cwd()));
   }
+  process.stdout.write(`\x1b]0;${APP_DISPLAY_NAME} v${APP_VERSION}\x07`);
   const launch = resolveCodexLaunch();
   const env = {
     ...process.env,
@@ -687,7 +698,7 @@ function numericWalletValue(value) {
 function formatStatusLine(config, wallet, cwd) {
   const model = modelStatusName(config.model);
   const walletText = wallet ? `Wallet ${formatUsd(wallet.balance)}` : "Wallet unavailable";
-  return `${model} ${DISPLAY_REASONING_EFFORT} · ${formatCwd(cwd)} · ${walletText}`;
+  return `${APP_DISPLAY_NAME} v${APP_VERSION} · ${model} ${DISPLAY_REASONING_EFFORT} · ${formatCwd(cwd)} · ${walletText}`;
 }
 
 function modelStatusName(model) {
@@ -700,12 +711,6 @@ function modelStatusName(model) {
   if (model === "claude-fable-5") {
     return "fable-5";
   }
-  if (model === "deepseek-v4-pro") {
-    return "deepseek-v4 budget";
-  }
-  if (model === "gemini-3.5-flash") {
-    return "gemini flash 3.5";
-  }
   return "gpt-5.5";
 }
 
@@ -723,8 +728,19 @@ function normalizeConfig(config) {
   if (["claude-fabel-5", "fable-5", "fabel-5"].includes(normalized.model)) {
     normalized.model = "claude-fable-5";
   }
-  if (["gemini-flash-3.5", "gemini-flash-3-5", "google-gemini-flash-3.5"].includes(normalized.model)) {
-    normalized.model = "gemini-3.5-flash";
+  if (
+    [
+      "deepseek-v4-pro",
+      "deepseek-v4-budget",
+      "deepseek",
+      "budget",
+      "gemini-3.5-flash",
+      "gemini-flash-3.5",
+      "gemini-flash-3-5",
+      "google-gemini-flash-3.5",
+    ].includes(normalized.model)
+  ) {
+    normalized.model = "gpt-5.5";
   }
   if (!MODELS[normalized.model]) {
     normalized.model = "gpt-5.5";

package/codexclaude.md

@@ -1,7 +1,7 @@
 # codexclaude Customization Ledger
 
 This file records the CodexAPI.pro-specific behavior that must survive every
-upgrade of the official OpenAI Codex CLI dependency. Treat it as the handoff
+upgrade of the bundled coding runtime dependency. Treat it as the handoff
 document for future maintainers. The launcher should remain a thin wrapper
 around official `@openai/codex`; do not patch the native Codex binary unless
 there is no supported configuration or API boundary that can solve the issue.
@@ -9,9 +9,10 @@ there is no supported configuration or API boundary that can solve the issue.
 ## Current Release
 
 - Launcher package: `@codexapi/codexclaude`
-- Launcher version: `2.0.14`
-- Official Codex runtime dependency: `@openai/codex@0.142.5`
-- Public install command: `npm install -g @codexapi/codexclaude@latest`
+- Launcher version: `2.0.16`
+- Customer-facing app name: `Magnetapi.org Coding Agent`
+- Bundled runtime dependency: official `@openai/codex@0.143.0`; do not print the upstream runtime version in customer-facing startup text.
+- Public update command for this optional release: `npm install -g @codexapi/codexclaude@2.0.16`
 - Default API origin: `https://codexapi.pro`
 - Normal Responses base URL: `https://codexapi.pro/v1`
 - Opus 4.8 Responses base URL: `https://api-chicago.codexapi.pro/v1`
@@ -19,21 +20,19 @@ 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 2026-07-05: the launcher pins official Codex CLI `0.142.5`. Backend routing is server-controlled by Admin Manage Models and must not collapse the launcher model list or rename customer-selected model ids.
+State verified on 2026-07-08: the launcher presents itself as Magnetapi.org Coding Agent `2.0.16`. Backend routing is server-controlled by Admin Manage Models and must not collapse the launcher model list or rename customer-selected model ids.
 
 ## Required User-Facing Model Behavior
 
-`codexclaude` supports exactly six 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`
 - `claude-sonnet-5` displayed as `Sonnet 5`
 - `claude-fable-5` displayed as `Fable 5`
-- `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 six options.
-The native Codex `/model` picker must also list only those six 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`.
@@ -58,7 +57,7 @@ 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 six
+`bin/codexclaude.js` writes a local catalog with full metadata for all four
 supported slugs. Each entry must include, at minimum:
 
 - `slug`
@@ -77,7 +76,7 @@ supported slugs. Each entry must include, at minimum:
 - `input_modalities`
 - `additional_speed_tiers`
 
-Keep `visibility = "list"` for the six 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
@@ -141,7 +140,7 @@ 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, Sonnet, Fable, Deepseek, or Gemini is selected. The backend can
+config model to `gpt-5.5` when Opus, Sonnet, or Fable 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.
@@ -154,14 +153,6 @@ Claude-family codexclaude models use the CodexAPI.pro Claude-compatible Response
 
 `claude-fable-5` is a premium customer-visible model. The backend bills it at the configured 2x multiplier and routes it through the Admin-selected Fable 5 route while preserving `claude-fable-5` in client-visible status and usage records.
 
-`deepseek-v4-pro` uses the configured API origin. The backend currently routes
-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-5` at the configured server effort.
-
 The launcher must send these headers for every model:
 
 - `X-CodexAPI-Client: codexclaude`
@@ -211,8 +202,8 @@ 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 six-model `MODELS` map and aliases.
+3. Keep the launcher package version higher than the last published version and keep customer-facing startup text on the Magnetapi.org Coding Agent version.
+4. Preserve the four-model `MODELS` map and aliases.
 5. Preserve `DISPLAY_REASONING_EFFORT = "xhigh"` and keep `SERVER_REASONING_EFFORT` aligned with the server default.
 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"`.
@@ -220,7 +211,7 @@ When upgrading official `@openai/codex`:
 9. Preserve bearer username auth with the CodexAPI.pro API username.
 10. Preserve the `X-CodexAPI-*` headers.
 11. Preserve Claude-family endpoint routing unless operations changes it.
-12. Preserve update enforcement through `/api/v1/codexclaude/version` and npm latest metadata.
+12. Preserve update checks through `/api/v1/codexclaude/version` and npm metadata. Recommended releases must be non-blocking; only versions below the backend `minimumVersion` may be forced.
 13. Update this file with a new release section explaining what changed.
 14. Run the validation commands below before publishing.
 
@@ -250,8 +241,8 @@ The JSON output must contain exactly:
 
 - `gpt-5.5`
 - `claude-opus-4-8`
-- `deepseek-v4-pro`
-- `gemini-3.5-flash`
+- `claude-sonnet-5`
+- `claude-fable-5`
 
 The Opus entry must have `default_reasoning_level = "xhigh"` and must not use
 fallback metadata.
@@ -270,6 +261,21 @@ 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 2.0.16 Changes
+
+- Updated the bundled official Codex dependency to `@openai/codex@0.143.0`.
+- Kept the launcher model picker and native Codex `/model` catalog limited to ChatGPT-5.5, Opus 4.8, Sonnet 5, and Fable 5.
+- Kept the customer-facing startup identity as Magnetapi.org Coding Agent and continued hiding the upstream Codex runtime version in normal startup text.
+- Changed the update surface for this release to a recommended, non-blocking notice. Users should be shown the exact update command, but they must not be forced off `2.0.15` for this release.
+- Preserved Full Access defaults, xhigh visible reasoning, bearer username auth, Responses wire API, and the CodexAPI.pro identification headers.
+
+## Version 2.0.15 Changes
+
+- Renamed the launcher-controlled startup/status surface to Magnetapi.org Coding Agent and now prints the app version instead of the upstream runtime version.
+- Removed Gemini Flash and Deepseek from the launcher model picker and generated native Codex model catalog.
+- Kept ChatGPT-5.5, Opus 4.8, Sonnet 5, and Fable 5 as the only visible codexclaude model choices.
+- Preserved Full Access defaults, xhigh visible reasoning, wallet auth, local model catalog metadata, and CodexAPI.pro identifying headers.
+
 ## Version 2.0.14 Changes
 
 - Updated the official OpenAI Codex runtime dependency to `@openai/codex@0.142.5`, the latest version currently published on npm.

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@codexapi/codexclaude",
-  "version": "2.0.14",
-  "description": "CodexAPI.pro coding CLI launcher for ChatGPT-5.5, Opus 4.8, Sonnet 5, Fable 5, Deepseek v4 Budget, and Google Gemini Flash 3.5, powered by official Codex CLI 0.142.5.",
+  "version": "2.0.16",
+  "description": "Magnetapi.org Coding Agent launcher for ChatGPT-5.5, Opus 4.8, Sonnet 5, and Fable 5.",
   "license": "Apache-2.0",
   "type": "module",
   "bin": {
@@ -17,7 +17,7 @@
     "node": ">=20"
   },
   "dependencies": {
-    "@openai/codex": "^0.142.5"
+    "@openai/codex": "0.143.0"
   },
   "publishConfig": {
     "access": "public"
@@ -26,10 +26,6 @@
     "codex",
     "claude",
     "opus",
-    "deepseek",
-    "gemini",
-    "flash",
-    "budget",
     "codexapi",
     "coding-cli"
   ],