Codex Desktop and CLI repeatedly show "Selected model is at capacity" across GPT-5.6 Sol and Luna

What version of Codex CLI is running?

Codex CLI version: 0.154.0

What subscription do you have?

plus

Which model were you using?

GPT-5.6 Sol - GPT-5.6 Luna

What platform is your computer?

Windows

What terminal emulator and version are you using (if applicable)?

VS Code

Codex doctor report

Notes
   ⚠ websocket    Responses WebSocket timed out; HTTPS fallback may still work - Check proxy, VPN, firewall, DNS, custom CA, and WebSocket policy support.
   ⚠ reachability desktop update and runtime CDN is unreachable
─────────────────────────────────────────────────────────────

Environment
  ✓ system       zh-CN
      os                       Windows 10.0.22631 (Windows 11 CoreCountrySpecific) [64-bit]
      OS language              zh-CN
      VISUAL                   not set
      EDITOR                   not set
  ✓ disk         sufficient free disk space (19.6 GiB)
      warning threshold        5.0 GiB
      failure threshold        1.0 GiB
      CODEX_HOME available     19.6 GiB
      worktree available       19.6 GiB
  ✓ security     no supported endpoint protection detected
      endpoint products        none detected
  ✓ runtime      npm (package C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc, bin C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\bin, resources C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\codex-resources, path C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\codex-path)
      version                  0.154.0
      install method           npm (package C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc, bin C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\bin, resources C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\codex-resources, path C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\codex-path)
      commit                   unknown
      executable               C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\bin\codex.exe
  ✓ install      consistent
      context                  npm (package C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc, bin C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\bin, resources C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\codex-resources, path C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\codex-path)
      managed by               npm: yes · bun: no · pnpm: no · Vite+: no · package root C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex
      PATH entries (1)         C:\Users\齐伟\AppData\Roaming\npm\codex.cmd
      npm update target        not inspected (PATH helpers are not executed)
  ✓ search       file exists (bundled, C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\codex-path\rg.exe)
      search command           C:\Users\齐伟\AppData\Roaming\npm\node_modules\@openai\codex\node_modules\@openai\codex-win32-x64\vendor\x86_64-pc-windows-msvc\codex-path\rg.exe
      search provider          bundled
      search command readiness file exists
  ✓ git          no Git worktree is active
  ✓ git          git executable found; execution not verified
      selected git             C:\Git\cmd\git.exe
      repo detected            false
      PATH entries (2)         C:\Git\cmd\git.exe
                               C:\Program Files\Git\cmd\git.exe
      git execution            not inspected (PATH helpers are not executed)
  ✓ terminal     unknown
      terminal                 unknown
      stdin is terminal        true
      stdout is terminal       true
      stderr is terminal       true
      terminal size            120x30
      color output             enabled
      console input code page  936
      console output code page 936
      stdout console mode      0x00000007 (VT processing: true)
      stderr console mode      0x00000007 (VT processing: true)
  ✓ title        default · project 齐伟
      title source             default
      title items              activity, project-name
      activity item            true
      project source           cwd
      project value            齐伟
  ✓ state        databases healthy
      CODEX_HOME               C:\Users\齐伟\.codex (dir)
      log dir                  C:\Users\齐伟\.codex\log (missing)
      sqlite home              C:\Users\齐伟\.codex (dir)
      state DB                 C:\Users\齐伟\.codex\state_5.sqlite (file) · integrity ok
      log DB                   C:\Users\齐伟\.codex\logs_2.sqlite (file) · integrity ok
      goals DB                 C:\Users\齐伟\.codex\goals_1.sqlite (file) · integrity ok
      memories DB              C:\Users\齐伟\.codex\memories_1.sqlite (file) · integrity ok
      active rollouts          34 files · 369.32 MB (avg 10.86 MB)
      archived rollouts        10 files · 20.63 MB (avg 2.06 MB)
      queue DB                 C:\Users\齐伟\.codex\queue_1.sqlite (file)
      queue DB integrity       ok
      thread history DB        C:\Users\齐伟\.codex\thread_history_1.sqlite (file)
      thread history DB integrity ok
  ✓ threads      rollout files and state DB thread inventory agree
      default model provider   openai
      rollout DB active files  34
      rollout DB archived files 10
      rollout DB scan errors   0
      rollout DB malformed file names 0
      rollout DB scan cap reached false
      rollout DB rows          44
      rollout DB active rows   34
      rollout DB archived rows 10
      rollout DB missing active rows 0
      rollout DB missing archived rows 0
      rollout DB stale rows    0
      rollout DB archive mismatches 0
      rollout DB duplicate rollout thread ids 0
      rollout DB duplicate DB paths 0
      rollout DB model providers openai=44
      rollout DB sources       vscode=28, subagent:other=14, cli=2

Configuration
  ✓ config       loaded
      model                    gpt-5.6-sol · openai
      cwd                      C:\Users\齐伟
      config.toml              C:\Users\齐伟\.codex\config.toml
      config.toml parse        ok
      MCP servers              1
      feature flags            50 enabled · 1 overridden (full list with --all)
      overrides                memories
      configuration scope      invocation config, including cloud-managed policy
      active thread overrides  not inspected
      configuration load ms    12
  ✓ auth         auth is configured
      auth storage mode        File
      auth file                C:\Users\齐伟\.codex\auth.json
      stored auth mode         chatgpt
      stored API key           false
      stored ChatGPT tokens    true
      stored agent identity    false
  ✓ mcp          1 server (1 stdio) · 0 disabled
      configured servers       1
      disabled servers         0
      stdio servers            1
  ✓ sandbox      restricted fs + restricted network · approval OnRequest
      approval policy          OnRequest
      filesystem sandbox       restricted
      denied-read rules        0
      denied-read glob rules   0
      glob scan max depth      unbounded
      managed filesystem source none
      network sandbox          restricted
      linux helper             none
      execve wrapper helper    none
      sandbox backend          elevated
      denied-read restrictions false
      sandbox provisioning     complete

Desktop App
  ✓ desktop      the desktop application is installed
      version                  26.908.4834.0
      running                  false
      log directory            $HOME\AppData\Local\Codex/Logs
  ✓ desktop      the desktop application is not running
  ✓ desktop      no locally visible recent Codex security enforcement was found

Updates
  ✓ updates      update configuration is locally consistent
      startup update check     true
      update action            npm install -g @openai/codex
      version cache            C:\Users\齐伟\.codex\version.json
      cached latest version    0.154.0
      last checked at          2026-09-17 07:14 UTC
      npm update target        not inspected (PATH helpers are not executed)
      latest version           0.154.0
      latest version status    current version is not older

Connectivity
  ✓ network      no proxy env vars
      proxy env vars           none
      respect system proxy     disabled
      managed proxy            not configured
  ⚠ websocket    Responses WebSocket timed out; HTTPS fallback may still work — Check proxy, VPN, firewall, DNS, custom CA, and WebSocket policy support.
      model provider           openai
      provider name            OpenAI
      wire API                 responses
      supports websockets      true
      proxy env vars           none
      connect timeout          15000 ms
      auth mode                chatgpt
      endpoint                 wss://chatgpt.com/backend-api/<redacted>
      DNS                      1 IPv4, 1 IPv6, first IPv4
    · handshake timed out
  ⚠ reachability desktop update and runtime CDN is unreachable
      reachability mode        ChatGPT auth
      ChatGPT inference URL    https://chatgpt.com/backend-api/<redacted> reachable (HTTP 405)
    ▸ desktop assets CDN       https://persistent.oaistatic.com/codex-app-prod/<redacted> request timed out (optional) (expected desktop update and runtime CDN reachable over HTTPS)
    → check proxy, firewall, DNS, and certificate access to persistent.oaistatic.com

Background Server
  ○ app-server   not running (ephemeral mode)
      daemon state dir         C:\Users\齐伟\.codex\app-server-daemon
      settings                 C:\Users\齐伟\.codex\app-server-daemon\settings.json (missing)
      pid file                 C:\Users\齐伟\.codex\app-server-daemon\app-server.pid (missing)
      update-loop pid file     C:\Users\齐伟\.codex\app-server-daemon\app-server-updater.pid (missing)
      control socket           C:\Users\齐伟\.codex\app-server-control\app-server-control.sock
      status                   not running
      mode                     ephemeral

─────────────────────────────────────────────────────────────
21 ok · 1 idle · 2 notes · 2 warn · 0 fail degraded

--summary compact output   --all expand truncated lists
--json redacted report
PS C:\Users\齐伟>

What issue are you seeing?

Summary

I am consistently getting the following error when using Codex on Windows:

Selected model is at capacity. Please try a different model.

The issue affects both Codex Desktop and Codex CLI.

Environment

• OS: Windows
• ChatGPT plan: Plus
• Codex CLI version: 0.154.0
• Models tested:
  • GPT-5.6 Sol
  • GPT-5.6 Luna

What I tested

• The issue occurs in both new and existing projects.
• The issue occurs in both Codex Desktop and Codex CLI.
• The issue occurs with both GPT-5.6 Sol and GPT-5.6 Luna.
• I tested with VPN enabled and disabled; the issue still occurs.
• Very short requests sometimes succeed, but the capacity error returns immediately afterward.
• My account still has remaining 5-hour and weekly usage limits, so the usage limits are not fully exhausted.

Other errors observed

I have also seen:

Falling back from WebSockets to HTTPS transport. request timed out

and:

stream disconnected before completion

Expected behavior

Codex should be able to run normally while there is still remaining usage quota, or provide a more specific error if this is an account-level routing or backend capacity issue.

Additional information

This does not appear to be limited to one project, one model, one client, or VPN/network configuration.

Please check whether my account is being routed to an overloaded or unhealthy Codex backend, or whether there is any account-level capacity issue.

Thread ID:
01a0ae4f-1225-7d12-b380-ac89ed9ebcbe

Request ID:
23d0fe4e-4bcf-4f4e-b71f-3023fa75063f

I can provide screenshots and additional logs if needed.

What steps can reproduce the bug?

Uploaded thread: 01a0ae4f-1225-7d12-b380-ac89ed9ebcbe

What is the expected behavior?

No response

Additional information

No response

Start by reproducing the issue with Codex CLI 0.154.0 and the Desktop app on Windows using GPT-5.6 Sol and Luna. Compare the repeated capacity error with the WebSocket timeout and HTTPS fallback reported by codex doctor. Done means determining whether the behavior is client-side and reproducible, or an external service or connectivity issue.