Codex will not enter Plan Mode

What version of Codex CLI is running?

codex-cli 0.145.0

What subscription do you have?

Max ($100/mo plan)

Which model were you using?

gpt-5.6-Sol (Max)

What platform is your computer?

Linux 6.18.33.2-microsoft-standard-WSL2 x86_64 x86_64

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

tmux inside Windows Terminal (WSL)

Codex doctor report

{
  "schemaVersion": 1,
  "generatedAt": "1784921895s since unix epoch",
  "overallStatus": "warning",
  "codexVersion": "0.145.0",
  "checks": {
    "app_server.status": {
      "id": "app_server.status",
      "category": "app-server",
      "status": "warning",
      "summary": "background server socket is stale or unreachable",
      "details": {
        "app-server version": "unavailable (failed to connect to control socket)",
        "control socket": "/home/tyler/.codex/app-server-control/app-server-control.sock",
        "daemon state dir": "/home/tyler/.codex/app-server-daemon",
        "mode": "persistent",
        "pid file": "/home/tyler/.codex/app-server-daemon/app-server.pid (missing)",
        "settings": "/home/tyler/.codex/app-server-daemon/settings.json (file)",
        "status": "stale or unreachable",
        "update-loop pid file": "/home/tyler/.codex/app-server-daemon/app-server-updater.pid (file)"
      },
      "remediation": "Run codex app-server daemon version for more details.",
      "durationMs": 1
    },
    "auth.credentials": {
      "id": "auth.credentials",
      "category": "auth",
      "status": "ok",
      "summary": "auth is configured",
      "details": {
        "auth file": "/home/tyler/.codex/auth.json",
        "auth storage mode": "File",
        "stored API key": "false",
        "stored ChatGPT tokens": "true",
        "stored agent identity": "false",
        "stored auth mode": "chatgpt"
      },
      "remediation": null,
      "durationMs": 0
    },
    "config.load": {
      "id": "config.load",
      "category": "config",
      "status": "ok",
      "summary": "config loaded",
      "details": {
        "CODEX_HOME": "/home/tyler/.codex",
        "config.toml": "/home/tyler/.codex/config.toml",
        "config.toml parse": "ok",
        "cwd": "/home/tyler/build-pipeline",
        "enabled feature flags": "shell_tool, unified_exec, shell_snapshot, code_mode_host, terminal_resize_reflow, sqlite, hooks, enable_request_compression, multi_agent, apps, tool_search_always_defer_mcp_tools, tool_suggest, plugins, in_app_browser, browser_use, browser_use_full_cdp_access, browser_use_external, computer_use, remote_plugin, plugin_sharing, image_generation, resize_all_images, skill_mcp_dependency_install, skill_search, mentions_v2, steer, guardian_approval, goals, collaboration_modes, tool_call_mcp_elicitation, auth_elicitation, personality, fast_mode, tui_app_server, remote_compaction_v2, workspace_dependencies",
        "feature flag overrides": "none",
        "feature flags enabled": "36",
        "log dir": "/home/tyler/.codex/log",
        "mcp servers": "1",
        "model": "gpt-5.6-sol",
        "model provider": "openai",
        "sqlite home": "/home/tyler/.codex"
      },
      "remediation": null,
      "durationMs": 0
    },
    "git.environment": {
      "id": "git.environment",
      "category": "git",
      "status": "ok",
      "summary": "git version 2.43.0",
      "details": {
        ".git entry": "directory",
        "PATH git #1": "/usr/bin/git",
        "PATH git entries": "1",
        "git branch": "master",
        "git build options": "git version 2.43.0; cpu: x86_64; no commit associated with this build; sizeof-long: 8; sizeof-size_t: 8; shell-path: /bin/sh",
        "git exec path": "/usr/lib/git-core",
        "git version": "git version 2.43.0",
        "repo detected": "true",
        "repo root": "/home/tyler/build-pipeline",
        "selected git": "/usr/bin/git"
      },
      "remediation": null,
      "durationMs": 22
    },
    "installation": {
      "id": "installation",
      "category": "install",
      "status": "ok",
      "summary": "installation looks consistent",
      "details": {
        "PATH codex #1": "/home/tyler/.local/bin/codex",
        "PATH codex #2": "/home/tyler/.local/bin/codex",
        "PATH codex #3": "/home/tyler/.local/bin/codex",
        "PATH codex #4": "/home/tyler/.local/bin/codex",
        "PATH codex entries": "4",
        "current executable": "/home/tyler/.codex/packages/standalone/releases/0.145.0-x86_64-unknown-linux-musl/bin/codex",
        "install context": "standalone (unix, package /home/tyler/.codex/packages/standalone/releases/0.145.0-x86_64-unknown-linux-musl, bin /home/tyler/.codex/packages/standalone/releases/0.145.0-x86_64-unknown-linux-musl/bin, resources /home/tyler/.codex/packages/standalone/releases/0.145.0-x86_64-unknown-linux-musl/codex-resources, path /home/tyler/.codex/packages/standalone/releases/0.145.0-x86_64-unknown-linux-musl/codex-path)",
        "managed by bun": "false",
        "managed by npm": "false",
        "managed by pnpm": "false",
        "managed package root": "not set"
      },
      "remediation": null,
      "durationMs": 6
    },
    "mcp.config": {
      "id": "mcp.config",
      "category": "mcp",
      "status": "ok",
      "summary": "MCP configuration is locally consistent",
      "details": {
        "configured servers": "1",
        "disabled servers": "0",
        "stdio servers": "1"
      },
      "remediation": null,
      "durationMs": 0
    },
    "network.env": {
      "id": "network.env",
      "category": "network",
      "status": "ok",
      "summary": "network-related environment looks readable",
      "details": {
        "proxy env vars": "none"
      },
      "remediation": null,
      "durationMs": 0
    },
    "network.provider_reachability": {
      "id": "network.provider_reachability",
      "category": "reachability",
      "status": "ok",
      "summary": "active provider endpoints are reachable over HTTP",
      "details": {
        "ChatGPT base URL": "https://chatgpt.com/backend-api/ reachable (HTTP 403)",
        "reachability mode": "ChatGPT auth"
      },
      "remediation": null,
      "durationMs": 44
    },
    "network.websocket_reachability": {
      "id": "network.websocket_reachability",
      "category": "websocket",
      "status": "ok",
      "summary": "Responses WebSocket handshake succeeded",
      "details": {
        "DNS": "2 IPv4, 2 IPv6, first IPv4",
        "auth mode": "chatgpt",
        "connect timeout": "15000 ms",
        "endpoint": "wss://chatgpt.com/backend-api/<redacted>",
        "handshake result": "HTTP 101 Switching Protocols",
        "model provider": "openai",
        "models etag present": "true",
        "provider name": "OpenAI",
        "proxy env vars": "none",
        "reasoning header": "false",
        "server model present": "false",
        "supports websockets": "true",
        "wire API": "responses"
      },
      "remediation": null,
      "durationMs": 444
    },
    "runtime.provenance": {
      "id": "runtime.provenance",
      "category": "runtime",
      "status": "ok",
      "summary": "running standalone on linux-x86_64",
      "details": {
        "commit": "unknown",
        "current executable": "/home/tyler/.codex/packages/standalone/releases/0.145.0-x86_64-unknown-linux-musl/bin/codex",
        "install method": "standalone (unix, package /home/tyler/.codex/packages/standalone/releases/0.145.0-x86_64-unknown-linux-musl, bin /home/tyler/.codex/packages/standalone/releases/0.145.0-x86_64-unknown-linux-musl/bin, resources /home/tyler/.codex/packages/standalone/releases/0.145.0-x86_64-unknown-linux-musl/codex-resources, path /home/tyler/.codex/packages/standalone/releases/0.145.0-x86_64-unknown-linux-musl/codex-path)",
        "platform": "linux-x86_64",
        "version": "0.145.0"
      },
      "remediation": null,
      "durationMs": 0
    },
    "runtime.search": {
      "id": "runtime.search",
      "category": "search",
      "status": "ok",
      "summary": "search is OK (bundled)",
      "details": {
        "search command": "/home/tyler/.codex/packages/standalone/releases/0.145.0-x86_64-unknown-linux-musl/codex-path/rg",
        "search command readiness": "file exists",
        "search provider": "bundled"
      },
      "remediation": null,
      "durationMs": 0
    },
    "sandbox.helpers": {
      "id": "sandbox.helpers",
      "category": "sandbox",
      "status": "ok",
      "summary": "sandbox configuration is readable",
      "details": {
        "approval policy": "OnRequest",
        "codex-linux-sandbox helper": "/home/tyler/.codex/tmp/arg0/codex-arg0CCpsF9/codex-linux-sandbox",
        "execve wrapper helper": "/home/tyler/.codex/tmp/arg0/codex-arg0CCpsF9/codex-execve-wrapper",
        "filesystem sandbox": "restricted",
        "network sandbox": "restricted"
      },
      "remediation": null,
      "durationMs": 0
    },
    "state.paths": {
      "id": "state.paths",
      "category": "state",
      "status": "ok",
      "summary": "state paths and databases are inspectable",
      "details": {
        "CODEX_HOME": "/home/tyler/.codex (dir)",
        "active rollout files": "268 files, 273461298 total bytes, 1020377 average bytes",
        "archived rollout files": "0 files, 0 total bytes, 0 average bytes",
        "goals DB": "/home/tyler/.codex/goals_1.sqlite (file)",
        "goals DB integrity": "ok",
        "log DB": "/home/tyler/.codex/logs_2.sqlite (file)",
        "log DB integrity": "ok",
        "log dir": "/home/tyler/.codex/log (dir)",
        "memories DB": "/home/tyler/.codex/memories_1.sqlite (file)",
        "memories DB integrity": "ok",
        "sqlite home": "/home/tyler/.codex (dir)",
        "standalone release cache": "1 entries in /home/tyler/.codex/packages/standalone/releases",
        "state DB": "/home/tyler/.codex/state_5.sqlite (file)",
        "state DB integrity": "ok",
        "thread history DB": "/home/tyler/.codex/thread_history_1.sqlite (missing)",
        "thread history DB integrity": "skipped (missing)"
      },
      "remediation": null,
      "durationMs": 2281
    },
    "state.rollout_db_parity": {
      "id": "state.rollout_db_parity",
      "category": "threads",
      "status": "ok",
      "summary": "rollout files and state DB thread inventory agree",
      "details": {
        "default model provider": "openai",
        "rollout DB active files": "268",
        "rollout DB active rows": "268",
        "rollout DB archive mismatches": "0",
        "rollout DB archived files": "0",
        "rollout DB archived rows": "0",
        "rollout DB duplicate DB paths": "0",
        "rollout DB duplicate rollout thread ids": "0",
        "rollout DB malformed file names": "0",
        "rollout DB missing active rows": "0",
        "rollout DB missing archived rows": "0",
        "rollout DB model providers": "openai=267, openai_http=1",
        "rollout DB rows": "268",
        "rollout DB scan cap reached": "false",
        "rollout DB scan errors": "0",
        "rollout DB sources": "subagent:other=118, cli=117, subagent:thread_spawn=20, vscode=13",
        "rollout DB stale rows": "0"
      },
      "remediation": null,
      "durationMs": 94
    },
    "system.environment": {
      "id": "system.environment",
      "category": "system",
      "status": "ok",
      "summary": "OS language C",
      "details": {
        "EDITOR": "not set",
        "LANG": "C.UTF-8",
        "VISUAL": "not set",
        "os": "Ubuntu 24.4.0 (noble) [64-bit]",
        "os language": "C",
        "os type": "Ubuntu",
        "os version": "24.4.0"
      },
      "remediation": null,
      "durationMs": 4
    },
    "terminal.env": {
      "id": "terminal.env",
      "category": "terminal",
      "status": "ok",
      "summary": "terminal metadata was detected",
      "details": {
        "TERM": "xterm-256color",
        "color output": "enabled",
        "effective locale": "C.UTF-8",
        "multiplexer": "tmux 3.4",
        "stderr is terminal": "true",
        "stdin is terminal": "true",
        "stdout is terminal": "true",
        "terminal": "unknown",
        "terminal size": "139x30",
        "tmux allow-passthrough": "off",
        "tmux client termname": "xterm-256color",
        "tmux extended-keys": "off",
        "tmux focus-events": "off",
        "tmux set-clipboard": "external",
        "tmux xterm-keys": "on"
      },
      "remediation": null,
      "durationMs": 12
    },
    "terminal.title": {
      "id": "terminal.title",
      "category": "title",
      "status": "ok",
      "summary": "terminal title default",
      "details": {
        "terminal title activity": "true",
        "terminal title items": "activity, project-name",
        "terminal title project source": "git repo root",
        "terminal title project value": "build-pipeline",
        "terminal title source": "default"
      },
      "remediation": null,
      "durationMs": 1
    },
    "updates.status": {
      "id": "updates.status",
      "category": "updates",
      "status": "ok",
      "summary": "update configuration is locally consistent",
      "details": {
        "cached latest version": "0.145.0",
        "check for update on startup": "true",
        "dismissed version": "0.129.0",
        "last checked at": "2026-07-24T18:46:01.551510619Z",
        "latest version": "0.145.0",
        "latest version status": "current version is not older",
        "update action": "standalone installer",
        "version cache": "/home/tyler/.codex/version.json"
      },
      "remediation": null,
      "durationMs": 265
    }
  }
}

What issue are you seeing?

Codex CLI does not properly enter Plan mode. This has occurred two times in the past day and a half. I've discovered that this is the case after Codex proceeds to begin non-planning work (editing files, implementing changes etc., and not asking questions or producing a plan) despite being set to plan mode. Entering Plan Mode via Shift+Tab shortcut or /plan causes the purple "Plan mode" text to appear at the bottom right of the terminal session, and the agent's tools are correctly set, but the agent is told it is still in Default mode.

> Is plan mode not working for you? You typicaly ask clarifying questions and build an actual plan. Diagnose what went wrong here and then we'll continue • Yes—there was a mode mismatch, and I handled it poorly. The runtime instructions told me I was in Default mode. A request containing “make a plan” does not itself activate Plan mode. I attempted to use the planning checklist anyway, and the tool rejected it with the contradictory message that it was “not allowed in Plan mode.” That suggests Plan-mode state was not propagated consistently. I should have surfaced that mismatch immediately. Instead, I continued in Default mode, performed the audit, made several assumptions, and presented a provisional architecture as though it were an agreed plan. I also skipped important clarification questions, particularly: - Whether every teammate runs both controller and worker, or a shared controller targets personal workers. - Whether controller and worker may be the same machine. - Which operating systems must be supported. - Whether workers must reproduce Altair’s exact toolchain or may use compatible variants. - Whether dashboards remain local or are exposed to the team network. So the audit evidence remains useful, but the “implementation plan” should be treated as a draft proposal—not the proper Plan-mode result. When we continue, I’ll first confirm Plan mode is actually active, ask the consequential questions, and then produce a concrete implementation plan with scope, file-level changes, migration compatibility, verification, and explicit non-goals.

> Hmm. Do the instructions still inform you that you're in Default mode? • Yes. The active runtime instructions still identify the collaboration mode as Default, and I have not received a subsequent developer instruction switching it to Plan mode. Your UI may therefore be out of sync with the mode delivered to me.

> Can you verify whether the tools and abilities you have access to match with plan mode or default mode? I'm gathering some info • I’ll run a non-destructive planning-tool capability probe. This distinguishes the instruction label I can see from the mode the tool backend is actually enforcing. • The tooling currently behaves as Plan mode, despite the visible instructions still saying Default mode. Evidence: - request_user_input, described as Plan-mode-only, is exposed. - I just invoked update_plan; the backend rejected it specifically because “TODO/checklist tool is not allowed in Plan mode.” - Execution/editing tools are available in both modes, so they are not diagnostic. Therefore there is a split state: - Injected collaboration-mode instructions: Default - Tool/backend mode enforcement: Plan My earlier answers reflected only the instruction layer. The backend probe shows your mode change did take effect somewhere, but the collaboration-mode instruction was not refreshed accordingly.

What steps can reproduce the bug?

1) Enter plan mode with Shift+Tab or /plan
2) Tell agent to audit something and make a plan to fix
3) Watch the agent not do plan-mode things, not make a plan, not ask questions

What is the expected behavior?

Actually engage in plan mode

Additional information

I had started this Codex conversion with the node.js-installed CLI application, and then continued it (and encountered this bug) after reinstalling Codex CLI via the bash script method.