openai / openai/codex

The command-execution service became saturated and returned: `code-mode host has too many active cells`

Open
#42,106 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug CLI tool-calls
Dominant language
Rust
Stars
125k
Forks
19.5k
PR merge metrics
PR metrics pending

Description

What version of Codex CLI is running?

codex-cli 0.151.0

What subscription do you have?

Pro 20x

Which model were you using?

gpt-5.6-sol

What platform is your computer?

Darwin 24.4.0 arm64 arm

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

iTerm 2

Codex doctor report
Codex Doctor v0.151.0 · macos-aarch64

Notes
   ↑ updates      0.152.0 available (current 0.151.0)
   ⚠ rollouts     257 active files · 16.38 GB on disk
   ⚠ sandbox      filesystem restricted · network enabled
   ⚠ threads      state DB rows point at missing or unusable rollout files
   ⚠ app-server   background server socket is stale or unreachable - Run codex app-server daemon version for more details.
   ⚠ desktop      recent macos security enforcement history was unavailable - check access to macos unified security logs and rerun codex doctor
─────────────────────────────────────────────────────────────

Environment
  ✓ system       en-MX
      os                       Mac OS 15.4.0 [64-bit]
      OS language              en-MX
      LANG                     en_AU.UTF-8
      VISUAL                   vim
      EDITOR                   vim
      PAGER                    less
      LESS                     -F -g -i -M -R -S -w -X -z-4
  ✓ disk         sufficient free disk space (78.5 GiB)
      warning threshold        5.0 GiB
      failure threshold        1.0 GiB
      CODEX_HOME available     78.5 GiB
      worktree available       78.5 GiB
  ✓ security     no supported endpoint protection detected
      endpoint products        none detected
  ✓ runtime      bun (package /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin, bin /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin, resources /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-resources, path /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path)
      version                  0.151.0
      install method           bun (package /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin, bin /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin, resources /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-resources, path /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path)
      commit                   unknown
      executable               ~/.bun/install/global/no…-apple-darwin/bin/codex
  ✓ install      consistent
      context                  bun (package /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin, bin /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin, resources /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-resources, path /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path)
      managed by               npm: no · bun: yes · pnpm: no · package root /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex
      PATH entries (2)         ~/.bun/bin/codex
                               ~/.bun/bin/codex
  ✓ search       file exists (bundled, /Users/fullofcaffeine/.bun/install/global/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path/rg)
      search command           ~/.bun/install/global/no…le-darwin/codex-path/rg
      search provider          bundled
      search command readiness file exists
  ✓ git          git version 2.40.1
      selected git             /opt/homebrew/bin/git
      version                  git version 2.40.1
      exec path                /opt/homebrew/Cellar/git/2.40.1/libexec/git-core
      repo detected            false
      PATH entries (2)         /opt/homebrew/bin/git
                               /usr/bin/git
  ✓ terminal     iTerm2 3.6.6
      terminal                 iTerm2
      TERM_PROGRAM             iTerm.app
      terminal version         3.6.6
      stdin is terminal        true
      stdout is terminal       true
      stderr is terminal       true
      terminal size            214x48
      color output             enabled
      COLORTERM                truecolor
      COLORFGBG                7;0
      TERMINFO_DIRS entry      /Applications/iTerm.app/…ents/Resources/terminfo (dir)
      TERMINFO_DIRS entry      /usr/share/terminfo (dir)
      effective locale         en_AU.UTF-8
  ✓ title        default · project fullofcaffeine
      title source             default
      title items              activity, project-name
      activity item            true
      project source           cwd
      project value            fullofcaffeine
  ✓ state        databases healthy
      CODEX_HOME               ~/.codex (dir)
      log dir                  ~/.codex/log (dir)
      sqlite home              ~/.codex (dir)
      state DB                 ~/.codex/state_5.sqlite (file) · integrity ok
      log DB                   ~/.codex/logs_2.sqlite (file) · integrity ok
      goals DB                 ~/.codex/goals_1.sqlite (file) · integrity ok
      memories DB              ~/.codex/memories_1.sqlite (file) · integrity ok
      active rollouts          257 files · 16.38 GB (avg 65.25 MB)
      archived rollouts        0 files · 0 B (avg 0 B)
      queue DB                 ~/.codex/queue_1.sqlite (file)
      queue DB integrity       ok
      thread history DB        ~/.codex/thread_history_1.sqlite (file)
      thread history DB integrity ok
  ⚠ threads      state DB rows point at missing or unusable rollout files
      default model provider   openai
      rollout DB active files  257
      rollout DB archived files 0
      rollout DB scan errors   0
      rollout DB malformed file names 0
      rollout DB scan cap reached false
      rollout DB rows          338
      rollout DB active rows   338
      rollout DB archived rows 0
      rollout DB missing active rows 0
      rollout DB missing archived rows 0
      rollout DB stale rows    79
      rollout DB archive mismatches 0
      rollout DB duplicate rollout thread ids 0
      rollout DB duplicate DB paths 0
      rollout DB model providers openai=338
      rollout DB sources       subagent:thread_spawn=196, cli=107, vscode=23, exec=12
      rollout DB stale row sample ~/.codex/sessions/2025/1…b290-dc1f8a84d07e.jsonl
      rollout DB stale row sample ~/.codex/sessions/2025/1…ab3e-3d9e2c7e7828.jsonl
      rollout DB stale row sample ~/.codex/sessions/2025/1…bda6-1a676ad716bc.jsonl
      rollout DB stale row sample ~/.codex/sessions/2025/1…9e69-52e306a99d6c.jsonl
      rollout DB stale row sample ~/.codex/sessions/2025/1…8f6d-f2de99116d88.jsonl

Configuration
  ✓ config       loaded
      model                    gpt-5.6-sol · openai
      cwd                      ~
      config.toml              ~/.codex/config.toml
      config.toml parse        ok
      MCP servers              4
      feature flags            47 enabled · 1 overridden (full list with --all)
      overrides                web_search_request
      legacy alias             web_search -> web_search_request
  ✓ auth         auth is configured
      auth storage mode        File
      auth file                ~/.codex/auth.json
      stored auth mode         chatgpt
      stored API key           false
      stored ChatGPT tokens    true
      stored agent identity    false
  ✓ mcp          4 server (4 stdio) · 1 disabled
      configured servers       4
      disabled servers         1
      stdio servers            4
  ✓ sandbox      restricted fs + enabled network · approval OnRequest
      approval policy          OnRequest
      filesystem sandbox       restricted
      network sandbox          enabled
      linux helper             none
      execve wrapper helper    ~/.codex/tmp/arg0/codex-…If/codex-execve-wrapper

Desktop App
  ✓ desktop      the desktop application is installed
      version                  26.810.50856
      running                  false
      log directory            $HOME/Library/Logs/com.openai.codex
  ✓ desktop      the desktop application is not running
  ⚠ desktop      recent macos security enforcement history was unavailable — check access to macos unified security logs and rerun codex doctor

Updates
  ✓ updates      update configuration is locally consistent
      startup update check     true
      update action            bun install -g @openai/codex
      version cache            ~/.codex/version.json
      cached latest version    0.149.0
      last checked at          2026-08-23 18:12 UTC
      latest version           0.152.0
      latest version status    newer version is available

Connectivity
  ✓ network      no proxy env vars
      proxy env vars           none
      system proxy             direct
      respect system proxy     disabled
      managed proxy            not configured
  ✓ websocket    connected (HTTP 101 Switching Protocols) · 15s timeout
      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                      2 IPv4, 0 IPv6, first IPv4
      handshake result         HTTP 101 Switching Protocols
      reasoning header         false
      server model present     false
  ✓ reachability active provider endpoints are reachable over HTTP
      reachability mode        ChatGPT auth
      ChatGPT inference URL    https://chatgpt.com/backend-api/<redacted> reachable (HTTP 405)
      desktop assets CDN       https://chatgpt.com/backend-api/<redacted> reachable (HTTP 200)

Background Server
  ⚠ app-server   background server socket is stale or unreachable — Run codex app-server daemon version for more details.
      daemon state dir         ~/.codex/app-server-daemon
      settings                 ~/.codex/app-server-daemon/settings.json (missing)
      pid file                 ~/.codex/app-server-daemon/app-server.pid (missing)
      update-loop pid file     ~/.codex/app-server-daem…/app-server-updater.pid (missing)
      control socket           ~/.codex/app-server-cont…app-server-control.sock
      status                   stale or unreachable
      app-server version       unavailable (failed to connect to control socket)
      mode                     ephemeral
What issue are you seeing?

As part of a long-running goal, Codex started complaining code-mode host has too many active cells in loop, wasting tokens and blocking the work. It then stopped.

Image

I tried to continue manually, but got the same issue:

Image
What steps can reproduce the bug?

Not sure, it happened all of the sudden, maybe related to a long session with a goal? More details in the thread I sent.

What is the expected behavior?

Long goals should work without falling into a spiral of doom, blocking my work and wasting tokens :/

Additional information

Thread ID: 019ff7c0-6461-7a32-85cc-49bdf4a7b32b.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No source file, test, or reliable reproduction sequence is named. Start by reviewing the supplied thread, the long-running goal context, and codex doctor output, then investigate the command-execution service behavior around repeated active cells. Done means the reported saturation can be reproduced or explained and the long-running work no longer loops or stops with this error.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
backend, cli
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.