@codexapi/codexclaude 2.0.18 → 2.0.20

package/CUSTOMIZATIONS.md

@@ -5,9 +5,9 @@
 ## Runtime
 
 - Customer-facing app name: `Magnetapi Client`
-- Local launcher version: `2.0.18`
+- Local launcher version: `2.0.20`
 - Bundled official runtime dependency: `@openai/codex@0.144.1`
-- Required install command: `npm install -g https://codexapi.pro/downloads/codexapi-codexclaude-2.0.18.tgz`
+- Required install command: `npm install -g https://codexapi.pro/downloads/codexapi-codexclaude-2.0.20.tgz`
 - Bundled runtime version is managed internally and must not be used for customer update prompts.
 - Launcher update checks may call the CodexAPI.pro version endpoint and `@codexapi/codexclaude` npm metadata only.
 - The launcher must never check `@openai/codex` npm metadata or OpenAI GitHub releases for update notices.
@@ -19,11 +19,12 @@
 - Rewrites `~/.codex/config.toml` before every launch.
 - Deletes stale `~/.codex/version.json` before writing managed config.
 - Launches the bundled platform-native runtime binary directly rather than the upstream npm wrapper.
+- Keeps launcher-owned output branded as `Magnetapi Client`; hardcoded native binary strings require a forked native runtime build if operations wants them removed across all platforms.
 - Starts with `--search` by default.
 - Passes unknown commands directly to the bundled runtime after config is applied.
 - Provides `codexclaude changelog` using the managed version endpoint.
 - Does not expose separate `codexclaude status` or `codexclaude usage` commands; wallet information remains a compact pre-launch line.
-- Version `2.0.18` is forced by the backend minimum version and older clients must show an update-required message.
+- Version `2.0.20` is forced by the backend minimum version and older clients must show an update-required message.
 
 ## Provider Config
 
@@ -40,14 +41,14 @@ The launcher writes a model provider named `codexapi`:
 
 ## Runtime Defaults
 
-- Default model: `claude-opus-4-8` displayed as `Opus 4.8`
-- Supported launcher choices: `gpt-5.5`, `claude-opus-4-8`, `claude-sonnet-5`, and `claude-fable-5`
+- Default model: `gpt-5.6-sol` displayed as `GPT-5.6 SOL`
+- Supported launcher choices: `gpt-5.6-sol`, `gpt-5.5`, `claude-opus-4-8`, `claude-sonnet-5`, and `claude-fable-5`
 - Reasoning effort displayed locally: `xhigh`
 - Reasoning hint sent in launcher env: `xhigh`
 - Approval policy: `never`
 - Sandbox mode: `danger-full-access`
 - Display wording for permissions: `Full Access` in launcher-owned copy
-- Local model catalog: `~/.codexclaude/model_catalog.json`; this keeps the native `/model` picker limited to the four supported choices and prevents fallback metadata warnings for Opus 4.8, Sonnet 5, and Fable 5.
+- Local model catalog: `~/.codexclaude/model_catalog.json`; this keeps the native `/model` picker limited to the five supported choices and prevents fallback metadata warnings for GPT-5.6 SOL, Opus 4.8, Sonnet 5, and Fable 5.
 - Service tier: omitted by default; `/fast` remains user-controlled and billed server-side when active.
 - TUI status line: `model-with-reasoning`, `fast-mode`, `current-dir`
 - Fable 5 stays visible to the user while the backend applies its custom routed premium path and billing multiplier.
@@ -59,7 +60,7 @@ Before launching the runtime, the launcher calls `/api/v1/wallet/status`, then `
 Expected status line:
 
 ```text
-Magnetapi Client v2.0.18 · opus-4.8 xhigh · ~/project · Wallet $20.00
+Magnetapi Client v2.0.20 · gpt-5.6-sol xhigh · ~/project · Wallet $20.00
 ```
 
 ## Upgrade Checklist
@@ -70,7 +71,7 @@ When updating the bundled runtime:
 2. Update `@openai/codex` in `package.json` and `package-lock.json`.
 3. Bump the launcher package version.
 4. Keep `APP_DISPLAY_NAME = "Magnetapi Client"`.
-5. Keep `DEFAULT_MODEL_ID = "claude-opus-4-8"`.
+5. Keep `DEFAULT_MODEL_ID = "gpt-5.6-sol"`.
 6. Keep `DISPLAY_REASONING_EFFORT = "xhigh"`.
 7. Keep Full Access defaults: `approval_policy = "never"` and `sandbox_mode = "danger-full-access"`.
 8. Keep `check_for_update_on_startup = false`.

package/README.md

@@ -1,13 +1,13 @@
 # codexclaude
 
-`codexclaude` installs the Magnetapi Client 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.
+`codexclaude` installs the Magnetapi Client for customers who want one coding CLI that can use GPT-5.6 SOL, ChatGPT-5.5, Opus 4.8, Sonnet 5, or Fable 5 against the same Token Wallet.
 
-Version `2.0.18` is a required major sync release. It bundles official Codex runtime dependency `@openai/codex@0.144.1`, launches the platform-native runtime binary directly, disables upstream OpenAI update prompts, and applies account, wallet, model, Full Access, Opus 4.8 default, and xhigh visible reasoning before each coding session starts.
+Version `2.0.20` is a required major sync release. It bundles official Codex runtime dependency `@openai/codex@0.144.1`, launches the platform-native runtime binary directly, disables upstream OpenAI update prompts, and applies account, wallet, model, Full Access, GPT-5.6 SOL default, and xhigh visible reasoning before each coding session starts.
 
 ## Install Or Update
 
 ```bash
-npm install -g https://codexapi.pro/downloads/codexapi-codexclaude-2.0.18.tgz
+npm install -g https://codexapi.pro/downloads/codexapi-codexclaude-2.0.20.tgz
 ```
 
 This does not delete local session history. The update replaces the `codexclaude` launcher package, refreshes the bundled runtime dependency, and rewrites the managed provider config the next time `codexclaude setup`, `codexclaude login`, or `codexclaude start` runs.
@@ -16,7 +16,7 @@ This does not delete local session history. The update replaces the `codexclaude
 
 The launcher checks CodexAPI.pro's managed version endpoint and the `@codexapi/codexclaude` npm package metadata only. It must never check `@openai/codex` npm metadata or OpenAI GitHub releases for customer update prompts.
 
-Version `2.0.18` is currently enforced as the minimum supported version, so older launchers show a required update message with the exact hosted tarball command above.
+Version `2.0.20` is currently enforced as the minimum supported version, so older launchers show a required update message with the exact hosted tarball command above.
 
 ## First Login
 
@@ -24,7 +24,7 @@ Version `2.0.18` is currently enforced as the minimum supported version, so olde
 codexclaude login
 ```
 
-Enter the Dashboard Username or Email Address and password. The launcher can log in to CodexAPI.pro, ChatPlus.chat, MyAPI.world, or MagnetAPI.org, then saves the correct System Token locally, writes `~/.codex/config.toml`, sets Full Access defaults, and lets the customer choose the coding model. If the customer presses Enter at the model prompt, Opus 4.8 is selected by default.
+Enter the Dashboard Username or Email Address and password. The launcher can log in to CodexAPI.pro, ChatPlus.chat, MyAPI.world, or MagnetAPI.org, then saves the correct System Token locally, writes `~/.codex/config.toml`, sets Full Access defaults, and lets the customer choose the coding model. If the customer presses Enter at the model prompt, GPT-5.6 SOL is selected by default.
 
 ## Start Coding
 
@@ -44,7 +44,7 @@ Switch model:
 codexclaude model
 ```
 
-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.
+Available model labels are `GPT-5.6 SOL`, `ChatGPT-5.5`, `Opus 4.8`, `Sonnet 5`, and `Fable 5`. All five use a Responses-compatible endpoint and the same customer Token Wallet.
 
 Show current launcher changes:
 
@@ -57,17 +57,17 @@ codexclaude changelog
 Before launching the coding runtime, the app prints a compact status line like:
 
 ```text
-Magnetapi Client v2.0.18 · opus-4.8 xhigh · ~/project · Wallet $20.00
+Magnetapi Client v2.0.20 · gpt-5.6-sol xhigh · ~/project · Wallet $20.00
 ```
 
 ## Preserved Customizations
 
 - Dashboard Username or Email Address plus password login for CodexAPI.pro, ChatPlus.chat, MyAPI.world, and MagnetAPI.org.
-- ChatGPT-5.5, Opus 4.8, Sonnet 5, or Fable 5 model selection, with Opus 4.8 as the default.
+- GPT-5.6 SOL, ChatGPT-5.5, Opus 4.8, Sonnet 5, or Fable 5 model selection, with GPT-5.6 SOL as the default.
 - Service-specific Responses-compatible provider for the dashboard account that logged in.
 - Full Access defaults: approval policy `never` and sandbox mode `danger-full-access`.
 - xhigh visible reasoning in the local UI while the API server keeps upstream runtime effort server-managed.
-- A local `~/.codexclaude/model_catalog.json` file so the native `/model` picker lists only ChatGPT-5.5, Opus 4.8, Sonnet 5, and Fable 5.
+- A local `~/.codexclaude/model_catalog.json` file so the native `/model` picker lists only GPT-5.6 SOL, 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 the client.
 - Token Wallet balance lookup before launch without exposing separate `status` or `usage` launcher commands.
 - Backend-identifying request headers so the API can enforce account and plan rules server-side.

package/bin/codexclaude.js

@@ -10,10 +10,10 @@ import { stdin as input, stdout as output } from "node:process";
 
 const require = createRequire(import.meta.url);
 
-const APP_VERSION = "2.0.18";
+const APP_VERSION = "2.0.20";
 const CODEX_VERSION = "0.144.1";
 const APP_DISPLAY_NAME = "Magnetapi Client";
-const DEFAULT_MODEL_ID = "claude-opus-4-8";
+const DEFAULT_MODEL_ID = "gpt-5.6-sol";
 const DISPLAY_REASONING_EFFORT = "xhigh";
 const SERVER_REASONING_EFFORT = "xhigh";
 const API_ORIGIN = (process.env.CODEXCLAUDE_API_ORIGIN || "https://codexapi.pro").replace(/\/+$/, "");
@@ -68,29 +68,34 @@ const SUPPORTED_REASONING_LEVELS = [
   { effort: "low", description: "Fast responses with lighter reasoning" },
   { effort: "medium", description: "Balances speed and reasoning depth for everyday coding" },
   { effort: "high", description: "Greater reasoning depth for complex work" },
-  { effort: "xhigh", description: "Extra high visible reasoning setting for CodexAPI.pro sessions" },
+  { effort: "xhigh", description: "Extra high visible reasoning setting for managed sessions" },
 ];
 
 const MODELS = {
+  "gpt-5.6-sol": {
+    id: "gpt-5.6-sol",
+    label: "GPT-5.6 SOL",
+    aliases: ["1", "gpt-5.6-sol", "gpt-5.6", "gpt56", "sol"],
+  },
   "gpt-5.5": {
     id: "gpt-5.5",
     label: "ChatGPT-5.5",
-    aliases: ["1", "gpt", "gpt-5.5", "chatgpt", "chatgpt-5.5"],
+    aliases: ["2", "gpt", "gpt-5.5", "chatgpt", "chatgpt-5.5"],
   },
   "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"],
+    aliases: ["3", "opus", "opus-4.8", "opus-4.7", "claude", "claude-opus-4-8", "claude-opus-4-7"],
   },
   "claude-sonnet-5": {
     id: "claude-sonnet-5",
     label: "Sonnet 5",
-    aliases: ["3", "sonnet", "sonnet-5", "sonnet-4.6", "sonnet-4-6", "claude-sonnet-5", "claude-sonnet-4-6", "claude-sonnet-4.6"],
+    aliases: ["4", "sonnet", "sonnet-5", "sonnet-4.6", "sonnet-4-6", "claude-sonnet-5", "claude-sonnet-4-6", "claude-sonnet-4.6"],
   },
   "claude-fable-5": {
     id: "claude-fable-5",
     label: "Fable 5",
-    aliases: ["4", "fable", "fable-5", "fabel", "fabel-5", "claude-fable-5", "claude-fabel-5"],
+    aliases: ["5", "fable", "fable-5", "fabel", "fabel-5", "claude-fable-5", "claude-fabel-5"],
     premium: true,
   },
 };
@@ -151,7 +156,7 @@ Commands:
   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 start       Start Magnetapi Client with --search
   codexclaude resume      Resume the latest coding session with --search
   codexclaude logout      Remove saved codexclaude account state
 
@@ -505,7 +510,7 @@ function updateRequiredMessage(metadata) {
     `Update required: ${APP_DISPLAY_NAME} has updated to codexclaude ${latest}. This major release is required for all users so your local client stays synced with the managed model catalog, Full Access defaults, and provider config.`,
     `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.",
+    "Your local session history will not be deleted. The update only replaces the codexclaude launcher and rewrites provider config backups.",
   ].join("\n");
 }
 
@@ -675,16 +680,19 @@ function modelCatalogEntry(model, index) {
 }
 
 function modelCatalogDescription(modelId) {
+  if (modelId === "gpt-5.6-sol") {
+    return "GPT-5.6 SOL managed coding route with local coding tools and wallet billing.";
+  }
   if (modelId === "claude-opus-4-8") {
-    return "Opus 4.8 coding route with local Codex tools and wallet billing.";
+    return "Opus 4.8 coding route with local coding tools and wallet billing.";
   }
   if (modelId === "claude-sonnet-5") {
-    return "Sonnet 5 coding route with local Codex tools and wallet billing.";
+    return "Sonnet 5 coding route with local coding tools and wallet billing.";
   }
   if (modelId === "claude-fable-5") {
-    return "Fable 5 premium coding route with local Codex tools and wallet billing.";
+    return "Fable 5 premium coding route with local coding tools and wallet billing.";
   }
-  return "ChatGPT-5.5 coding route with local Codex tools and wallet billing.";
+  return "ChatGPT-5.5 coding route with local coding tools and wallet billing.";
 }
 
 function readConfig() {
@@ -710,7 +718,7 @@ function saveConfig(config) {
 
 function logout() {
   saveConfig({ version: APP_VERSION, loggedOutAt: new Date().toISOString() });
-  console.log("codexclaude login state removed. Codex config was left untouched.");
+  console.log("codexclaude login state removed. Managed coding config was left untouched.");
 }
 
 async function runCodex(args) {
@@ -890,6 +898,9 @@ function formatStatusLine(config, wallet, cwd) {
 }
 
 function modelStatusName(model) {
+  if (model === "gpt-5.6-sol") {
+    return "gpt-5.6-sol";
+  }
   if (model === "claude-opus-4-8") {
     return "opus-4.8";
   }

package/codexclaude.md

@@ -5,13 +5,13 @@ This file is the durable handoff for the `@codexapi/codexclaude` package in `/ro
 ## Current Release
 
 - Package name: `@codexapi/codexclaude`
-- Launcher version: `2.0.18`
+- Launcher version: `2.0.20`
 - Customer-facing app name: `Magnetapi Client`
 - Bundled runtime dependency: `@openai/codex@0.144.1`
-- Required install command: `npm install -g https://codexapi.pro/downloads/codexapi-codexclaude-2.0.18.tgz`
-- Backend minimum version: `2.0.18`
-- Default visible model: `Opus 4.8`
-- Default model slug: `claude-opus-4-8`
+- Required install command: `npm install -g https://codexapi.pro/downloads/codexapi-codexclaude-2.0.20.tgz`
+- Backend minimum version: `2.0.20`
+- Default visible model: `GPT-5.6 SOL`
+- Default model slug: `gpt-5.6-sol`
 - Visible reasoning effort: `xhigh`
 - Local permissions: Full Access, implemented as `approval_policy = "never"` and `sandbox_mode = "danger-full-access"`
 - Local launcher state: `~/.codexclaude/config.json`
@@ -24,25 +24,26 @@ This file is the durable handoff for the `@codexapi/codexclaude` package in `/ro
 The launcher must present itself as:
 
 ```text
-Magnetapi Client v2.0.18
+Magnetapi Client v2.0.20
 ```
 
 Normal pre-launch status should look like:
 
 ```text
-Magnetapi Client v2.0.18 · opus-4.8 xhigh · ~/project · Wallet $20.00
+Magnetapi Client v2.0.20 · gpt-5.6-sol xhigh · ~/project · Wallet $20.00
 ```
 
 Do not show OpenAI update notices, OpenAI npm install commands, OpenAI release links, or the upstream runtime version in launcher-owned output. The package still depends on the official runtime internally, but the customer update surface is ours.
 
-The launcher command `codexclaude model` must list exactly four customer-visible models:
+The launcher command `codexclaude model` must list exactly five customer-visible models:
 
+- `gpt-5.6-sol` displayed as `GPT-5.6 SOL`
 - `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`
 
-Opus 4.8 must be the default when a new config is created or a legacy config contains an unsupported Gemini/Deepseek value. The selected model slug must stay in `~/.codex/config.toml`; do not rewrite Opus, Sonnet, or Fable to GPT locally just because the backend may route internally.
+GPT-5.6 SOL must be the default when a new config is created or a legacy config contains an unsupported Gemini/Deepseek value. `gpt-5.6-sol` is a managed public alias routed through the compatible signed-in GPT runtime until OpenAI publishes an official upstream API slug. The selected model slug must stay in `~/.codex/config.toml`; do not rewrite customer-facing model selections locally just because the backend may route internally.
 
 ## Update Policy
 
@@ -51,16 +52,18 @@ Opus 4.8 must be the default when a new config is created or a legacy config con
 - `https://codexapi.pro/api/v1/codexclaude/version`
 - `https://registry.npmjs.org/@codexapi%2Fcodexclaude/latest`
 
-It must not check `@openai/codex` npm metadata, OpenAI GitHub releases, or any upstream OpenAI update endpoint. Version `2.0.18` is a forced release: the backend `minimumVersion` equals `2.0.18`, and older clients must show an update-required message with the hosted tarball command.
+It must not check `@openai/codex` npm metadata, OpenAI GitHub releases, or any upstream OpenAI update endpoint. Version `2.0.20` is a forced release: the backend `minimumVersion` equals `2.0.20`, and older clients must show an update-required message with the hosted tarball command.
 
 The launcher writes `check_for_update_on_startup = false` and removes `~/.codex/version.json` so the bundled runtime does not display stale upstream update prompts. The launcher also resolves the platform-native runtime binary directly from the optional package (`@openai/codex-linux-x64`, `@openai/codex-darwin-arm64`, and so on). Do not fall back to the upstream npm wrapper, because that wrapper can re-enable upstream managed update behavior.
 
+The optional platform-native runtime packages can still contain upstream README files and hardcoded native strings inside the binary. Launcher-owned output must say `Magnetapi Client`; replacing native binary text itself requires a maintained forked native runtime build for every supported platform. Until such a fork exists, do not re-enable the upstream npm wrapper and do not present upstream update notices to customers.
+
 ## Generated Config Contract
 
 `bin/codexclaude.js` must rewrite `~/.codex/config.toml` before every coding session. Preserve this top-level shape:
 
 ```toml
-model = "claude-opus-4-8"
+model = "gpt-5.6-sol"
 model_catalog_json = "<absolute path to ~/.codexclaude/model_catalog.json>"
 preferred_auth_method = "apikey"
 model_provider = "codexapi"
@@ -77,7 +80,7 @@ base_url = "<service Responses URL>"
 experimental_bearer_token = "<customer System Token/API username>"
 wire_api = "responses"
 supports_websockets = false
-http_headers = { "X-CodexAPI-Client" = "codexclaude", "X-CodexAPI-Client-Version" = "2.0.18", "X-CodexAPI-Selected-Model" = "<selected model>" }
+http_headers = { "X-CodexAPI-Client" = "codexclaude", "X-CodexAPI-Client-Version" = "2.0.20", "X-CodexAPI-Selected-Model" = "<selected model>" }
 
 [tui]
 status_line = ["model-with-reasoning", "fast-mode", "current-dir"]
@@ -85,7 +88,7 @@ status_line_use_colors = true
 terminal_title = ["project-name", "model-with-reasoning", "run-state"]
 ```
 
-The generated model catalog must contain full metadata for the four supported slugs. This prevents fallback metadata warnings such as:
+The generated model catalog must contain full metadata for the five supported slugs. This prevents fallback metadata warnings such as:
 
 ```text
 Model metadata for `claude-opus-4-8` not found. Defaulting to fallback metadata; this can degrade performance and cause issues.
@@ -120,7 +123,7 @@ When updating the bundled runtime dependency:
 3. Bump `package.json` and `package-lock.json` to a new `@codexapi/codexclaude` version.
 4. Update `APP_VERSION` and `CODEX_VERSION` in `bin/codexclaude.js`.
 5. Preserve `APP_DISPLAY_NAME = "Magnetapi Client"`.
-6. Preserve `DEFAULT_MODEL_ID = "claude-opus-4-8"`.
+6. Preserve `DEFAULT_MODEL_ID = "gpt-5.6-sol"`.
 7. Preserve `DISPLAY_REASONING_EFFORT = "xhigh"` and `SERVER_REASONING_EFFORT = "xhigh"` unless operations explicitly changes the launcher-visible contract.
 8. Preserve Full Access defaults and the local model catalog.
 9. Preserve direct platform-native binary launch.
@@ -147,7 +150,7 @@ tmp_home="$(mktemp -d)"
 mkdir -p "$tmp_home/.codexclaude"
 cat > "$tmp_home/.codexclaude/config.json" <<'JSON'
 {
-  "version": "2.0.18",
+  "version": "2.0.20",
   "serviceId": "codexapi",
   "serviceLabel": "CodexAPI.pro",
   "apiOrigin": "https://codexapi.pro",
@@ -162,7 +165,7 @@ HOME="$tmp_home" CODEXCLAUDE_DISABLE_UPDATE_CHECK=1 CODEXCLAUDE_QUIET_STATUS=1 n
 
 Verify the generated config contains:
 
-- `model = "claude-opus-4-8"`
+- `model = "gpt-5.6-sol"`
 - `model_reasoning_effort = "xhigh"`
 - `check_for_update_on_startup = false`
 - `approval_policy = "never"`
@@ -180,20 +183,20 @@ After packaging, copy the tarball to the public downloads directories, restart t
 
 ```bash
 curl -fsS "https://codexapi.pro/api/v1/codexclaude/version?current=2.0.17"
-curl -fsSI "https://codexapi.pro/downloads/codexapi-codexclaude-2.0.18.tgz"
+curl -fsSI "https://codexapi.pro/downloads/codexapi-codexclaude-2.0.20.tgz"
 ```
 
-The version endpoint must report `latestVersion = 2.0.18`, `minimumVersion = 2.0.18`, and `updateRequired = true` for old clients.
+The version endpoint must report `latestVersion = 2.0.20`, `minimumVersion = 2.0.20`, and `updateRequired = true` for old clients.
 
-## Version 2.0.18 Changes
+## Version 2.0.20 Changes
 
 - Updated bundled runtime dependency to `@openai/codex@0.144.1`.
-- Forced all older codexclaude clients to update by setting backend minimum version to `2.0.18`.
+- Forced all older codexclaude clients to update by setting backend minimum version to `2.0.20`.
 - Changed launcher-owned identity to `Magnetapi Client`.
-- Changed the default selected model to Opus 4.8.
+- Added GPT-5.6 SOL as a managed model choice and made it the default selection.
 - Kept visible reasoning at xhigh.
 - Preserved Full Access defaults.
 - Disabled bundled runtime update checks through generated config and stale update-cache removal.
 - Removed launcher fallback to the upstream npm wrapper so OpenAI update prompts are not emitted by codexclaude.
 - Kept update monitoring limited to CodexAPI.pro version metadata and the `@codexapi/codexclaude` npm package.
-- Updated setup scripts to install the exact hosted `2.0.18` tarball.
+- Updated setup scripts to install the exact hosted `2.0.20` tarball.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@codexapi/codexclaude",
-  "version": "2.0.18",
+  "version": "2.0.20",
   "description": "Magnetapi Client launcher for ChatGPT-5.5, Opus 4.8, Sonnet 5, and Fable 5.",
   "license": "Apache-2.0",
   "type": "module",