@codexapi/codexclaude 2.0.44 → 2.0.46

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CUSTOMIZATIONS.md CHANGED
@@ -5,10 +5,10 @@
5
5
  ## Runtime
6
6
 
7
7
  - Customer-facing app name: `MagnetAPI.org Codex CLI`
8
- - Local launcher version: `2.0.44`
9
- - Bundled official runtime dependency: `@openai/codex@0.164.0`
8
+ - Local launcher version: `2.0.46`
9
+ - Bundled official runtime dependency: `@openai/codex@0.166.0`
10
10
  - Required install command: `npm install -g @codexapi/codexclaude@latest`
11
- - Hosted fallback archive: `https://codexapi.pro/downloads/codexapi-codexclaude-2.0.44.tgz`, with its SHA-256 sidecar. The updater installs a verified local copy, not an npm remote URL.
11
+ - Hosted fallback archive: `https://codexapi.pro/downloads/codexapi-codexclaude-2.0.46.tgz`, with its SHA-256 sidecar. The updater installs a verified local copy, not an npm remote URL.
12
12
  - Bundled runtime version is managed internally and must not be used for customer update prompts.
13
13
  - Launcher update checks may call the CodexAPI.pro version endpoint and `@codexapi/codexclaude` npm metadata only.
14
14
  - The launcher must never check `@openai/codex` npm metadata or OpenAI GitHub releases for update notices.
@@ -69,7 +69,7 @@ Before launching the runtime, the launcher calls `/api/v1/wallet/status`, then `
69
69
  Expected status line:
70
70
 
71
71
  ```text
72
- MagnetAPI.org Codex CLI v2.0.44 · ChatGPT 6.1 SOL Extra High · ~/project · Wallet balance $20.00
72
+ MagnetAPI.org Codex CLI v2.0.46 · ChatGPT 6.1 SOL Extra High · ~/project · Wallet balance $20.00
73
73
  ChatGPT 6.1 SOL and Google Argon 4 are selectable in codexclaude. SOL Extra High is the default. Actual model processing follows your service's routing. Save 15% on API coding usage with codexclaude.
74
74
  ```
75
75
 
@@ -97,3 +97,5 @@ When updating the bundled runtime:
97
97
  16. Update `README.md`, `CUSTOMIZATIONS.md`, and `codexclaude.md`.
98
98
  17. Run syntax checks, temporary-home setup, alias-preservation tests, `npm pack --dry-run`, and endpoint validation before publishing.
99
99
  18. Keep CLI top-up payment-method collection on Stripe's hosted surface and preserve checkout/confirm polling plus wallet refresh tests.
100
+
101
+ Google Carbon 4 (`gemini-4-carbon`) is a **managed preview**, first in the picker. Native Google Carbon is not yet available through this service. The selection uses the service-selected route and your existing Google model rate card. Your saved model remains selected; new installations still default to ChatGPT 6.1 SOL / Extra High.
package/README.md CHANGED
@@ -1,6 +1,6 @@
1
- # codexclaude 2.0.44
1
+ # codexclaude 2.0.46
2
2
 
3
- Bundles the exact official Codex runtime 0.164.0.
3
+ Bundles the exact official Codex runtime 0.166.0.
4
4
 
5
5
  ```sh
6
6
  npm install -g @codexapi/codexclaude@latest
@@ -15,6 +15,8 @@ The model selector refreshes your public Credit Wallet, subscriber five-hour usa
15
15
 
16
16
  Unlimited shows Claude only or All Models, minutes:seconds remaining and active, paused, ready-to-start or queued status. These GET-only checks cannot submit a coding pass or activate unused time. A failed lookup shows unavailable rather than a fabricated zero. Billing follows your account’s current routing and rates, including the existing 15% managed-client usage reduction.
17
17
 
18
- At interactive startup, the native Codex model picker receives a timestamped account snapshot in its model descriptions. Codex 0.164.0 has no model-switch hook or custom status-line command: descriptions are snapshots, not a live countdown. Run `codexclaude model` for a fresh check before a session. Headless protocol output stays clean.
18
+ At interactive startup, the native Codex model picker receives a timestamped account snapshot in its model descriptions. Codex 0.166.0 has no model-switch hook or custom status-line command: descriptions are snapshots, not a live countdown. Run `codexclaude model` for a fresh check before a session. Headless protocol output stays clean.
19
19
 
20
20
  Four-site authentication supports CodexAPI.pro, ChatPlus.chat, MagnetAPI.org and MyAPI.world. Native tools, MCP, skills, hooks, project files and session history remain local. The package owns only its own command and preserves unrelated native configuration. Mandatory managed updates verify the actual installed version, support a checksum-verified hosted fallback, and never require --force.
21
+
22
+ Google Carbon 4 (`gemini-4-carbon`) is a **managed preview**, first in the picker. Native Google Carbon is not yet available through this service. The selection uses the service-selected route and your existing Google model rate card. Your saved model remains selected; new installations still default to ChatGPT 6.1 SOL / Extra High.
@@ -16,8 +16,8 @@ import { installedPackage, npmInvocation, performUpdate, releaseTarget } from ".
16
16
 
17
17
  const require = createRequire(import.meta.url);
18
18
 
19
- const APP_VERSION = "2.0.44";
20
- const CODEX_VERSION = "0.164.0";
19
+ const APP_VERSION = "2.0.46";
20
+ const CODEX_VERSION = "0.166.0";
21
21
  const APP_DISPLAY_NAME = "MagnetAPI.org Codex CLI";
22
22
  const DEFAULT_MODEL_ID = "gpt-6.1-sol";
23
23
  const DEFAULT_DISPLAY_REASONING_EFFORT = "xhigh";
@@ -40,7 +40,7 @@ const CODEX_CONFIG_FILE = path.join(CODEX_DIR, "config.toml");
40
40
  const CODEX_UPDATE_CACHE_FILE = path.join(CODEX_DIR, "version.json");
41
41
  const PROVIDER_ID = "codexapi";
42
42
  const MODEL_CATALOG_CONTEXT_WINDOW = 272000;
43
- const FABLE_ANNOUNCEMENT = "Claude Opus 5.5 is first in the model picker. ChatGPT 6.1 SOL, Google Argon 4 and DeepSeek V4.1 Flash are selectable in codexclaude. SOL Extra High is the default. Actual model processing follows your service's routing. Save 15% on API coding usage with codexclaude.";
43
+ const FABLE_ANNOUNCEMENT = "Google Carbon 4 (Managed preview) is first in the model picker. Native Google Carbon is not yet available through this service; the preview follows the service-selected route and existing Google rate card. ChatGPT 6.1 SOL, Google Argon 4 and DeepSeek V4.1 Flash are selectable in codexclaude. SOL Extra High is the default. Actual model processing follows your service's routing. Save 15% on API coding usage with codexclaude.";
44
44
  const ANSI_GREEN = "\x1b[32m";
45
45
  const ANSI_RESET = "\x1b[0m";
46
46
  const SERVICE_CATALOG = [
@@ -99,6 +99,15 @@ const TOPUP_POLL_INTERVAL_MS = positiveInteger(process.env.CODEXCLAUDE_TOPUP_POL
99
99
  const TOPUP_TIMEOUT_MS = positiveInteger(process.env.CODEXCLAUDE_TOPUP_TIMEOUT_MS, 30 * 60 * 1000);
100
100
 
101
101
  const MODELS = {
102
+ "gemini-4-carbon": {
103
+ id: "gemini-4-carbon",
104
+ label: "Google Carbon 4 (Managed preview)",
105
+ aliases: ["gemini-4-carbon", "google-carbon-4", "gemini-carbon-4", "carbon", "carbon-4"],
106
+ reasoningEffort: "medium",
107
+ contextWindow: 1048576,
108
+ maxOutputTokens: 65536,
109
+ supportedReasoningLevels: SUPPORTED_REASONING_LEVELS.filter(({ effort }) => ["low", "medium", "high"].includes(effort)),
110
+ },
102
111
  "claude-opus-5-5": {
103
112
  id: "claude-opus-5-5",
104
113
  label: "Claude Opus 5.5",
@@ -1051,6 +1060,9 @@ function modelCatalogEntry(model, index) {
1051
1060
  }
1052
1061
 
1053
1062
  function modelCatalogDescription(modelId) {
1063
+ if (modelId === "gemini-4-carbon") {
1064
+ return "Managed preview with local coding tools and image input. Native Google Carbon is not yet available through this service. Execution follows your service routing and existing Google rate card.";
1065
+ }
1054
1066
  if (modelId === "gpt-6.1-sol") {
1055
1067
  return "ChatGPT 6.1 SOL: coding tools, image input, and Extra High reasoning by default.";
1056
1068
  }
@@ -1320,6 +1332,9 @@ function formatStatusLine(config, wallet, cwd) {
1320
1332
  }
1321
1333
 
1322
1334
  function modelStatusName(model) {
1335
+ if (model === "gemini-4-carbon") {
1336
+ return "Google Carbon 4 (Managed preview)";
1337
+ }
1323
1338
  if (model === "gpt-6.1-sol") {
1324
1339
  return "ChatGPT 6.1 SOL";
1325
1340
  }
@@ -1417,6 +1432,9 @@ function normalizeConfig(config) {
1417
1432
  if (["deepseek-v4.1-flash", "deepseek-v4.1-flash-1017", "deepseek/deepseek-v4.1-flash", "deepseek-4.1", "deepseek-flash-4.1"].includes(normalized.model)) {
1418
1433
  normalized.model = "deepseek-flash";
1419
1434
  }
1435
+ if (["google-carbon-4", "gemini-carbon-4", "carbon", "carbon-4"].includes(normalized.model)) {
1436
+ normalized.model = "gemini-4-carbon";
1437
+ }
1420
1438
  if (["google/gemini-4-argon", "google-argon-4", "argon", "argon-4"].includes(normalized.model)) {
1421
1439
  normalized.model = "gemini-4-argon";
1422
1440
  }
package/codexclaude.md CHANGED
@@ -1,6 +1,25 @@
1
- # Current release: 2.0.44 / runtime 0.164.0
1
+ # Current source: codexclaude 2.0.46 / native Codex 0.166.0
2
2
 
3
- October 24: Opus 5.5 first; GPT-5 and 4.6 removed from pickers; public balance, actual allowance percentages and scoped Unlimited time shown during model selection. Preserve routing, native tools and customer configuration. Publication and deployment evidence: /root/codexapi/output/launchers-20261024/REPORT.md. Older release claims below are historical.
3
+ Google Carbon 4 (`gemini-4-carbon`) is a managed preview placed first in the picker. It is not native Google Carbon execution. Initial routing is the operator-approved OpenInference destination; admins can change Carbon independently or follow global routing. Existing Google service rates apply. New defaults stay SOL 6.1 / XHigh; saved selections and headless output are preserved. Publication and mandatory-update status must be verified independently.
4
+
5
+ ## Previous source handoff
6
+
7
+ # Current source: 2.0.45 / runtime 0.166.0
8
+
9
+ 31 October: bundles exact official Codex0.166.0. Existing model order,
10
+ SOL6.1/XHigh defaults, saved choices, native tools/MCP/history, four-site login,
11
+ account snapshots and verified updater fallback remain. Google Carbon4 is not
12
+ advertised as available: Google announced restricted partner rollout, its public
13
+ API catalogue and live OpenRouter catalogue do not provide a verified route. Add
14
+ it only after approved real access, capabilities, pricing and useful tool probes.
15
+ This runtime upgrade changes no provider routing or pricing. Publication and
16
+ latest/minimum activation require actual receipts under
17
+ /root/codexapi/output/google-carbon4-20261031; source version alone proves neither.
18
+
19
+ ## Previous release: 2.0.44 / runtime 0.164.0
20
+
21
+ October24: Opus5.5 first, retired GPT5/4.6 picker cleanup and public account status.
22
+ Historical publication evidence: /root/codexapi/output/launchers-20261024/REPORT.md.
4
23
 
5
24
  # codexclaude Customization Ledger
6
25
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@codexapi/codexclaude",
3
- "version": "2.0.44",
3
+ "version": "2.0.46",
4
4
  "description": "MagnetAPI.org Codex CLI for ChatGPT 6.1 SOL, Google Argon 4, DeepSeek V4.1 Flash, Astra, Fable 5.1, Opus 5, Sonnet and Daybreak Blue.",
5
5
  "license": "Apache-2.0",
6
6
  "type": "module",
@@ -23,7 +23,7 @@
23
23
  },
24
24
  "dependencies": {
25
25
  "@iarna/toml": "2.2.5",
26
- "@openai/codex": "0.164.0"
26
+ "@openai/codex": "0.166.0"
27
27
  },
28
28
  "publishConfig": {
29
29
  "access": "public"