Codex CLI 0.149.0 Adds Agent Dashboard

@openai’s Codex changelog for Codex CLI 0.149.0 is an official release note for OpenAI Codex, OpenAI’s coding agent tooling, published August 20, 2026. It deals with a very practical problem: managing long-running local and remote Codex sessions without losing context, approvals, or working-directory state. The takeaway is that 0.149.0 moves the codex cli toward a session control surface, not just a prompt box. For codex cli github readers, the release also points back to the openai/codex repo for the implementation trail and issue discussion.

Open the agents dashboard before starting another thread

The Codex CLI is a terminal interface for running OpenAI Codex against a repository or a remote coding session. In 0.149.0, @openai added an interactive Codex agents dashboard for searching, starting, opening, renaming, and stopping tasks, with configurable shortcuts.

That matters because the hard part of agent work is often not asking the first question. It is remembering which task is still alive, which one has pending output, and which one should be stopped before it edits the same files as another session.

Picture a repo like billing-api with three threads: one investigating flaky Jest tests, one updating invoice copy, and one trying a database migration. A dashboard gives those sessions a visible place to live. The trap is treating visibility as cleanup. If task names are vague, a dashboard only makes the mess easier to see.

Send follow-ups with codex queue

The release adds codex queue, a command for sending messages to existing local or remote sessions. This is the small feature that feels boring until it saves you from opening a duplicate terminal and making the same agent rediscover the same repo state.

The changelog also says queued messages now wake idle sessions more reliably. Duplicate session names resolve more usefully, and pasted or deferred command semantics are preserved. In plain English: queueing is meant to behave like a continuation, not like a half-new chat wearing an old name.

Use it when the session already owns the task. For example, if a Codex agent is halfway through replacing a deprecated feature flag, queue the follow-up there: ask it to include the migration test, not to start a fresh investigation. Avoid queueing stateful instructions when you are unsure of the working directory or permission profile.

Check location and permissions before trusting a resume

Codex CLI 0.149.0 adds /cd, /pwd, and /cwd commands for managing the working directory in TUI sessions. That is a nice quality-of-life change, but it is also a safety feature. A coding agent that is in the wrong directory can produce very confident nonsense.

The release also fixes resumed and forked threads so they restore their active permission profile instead of silently falling back to current defaults. That is a sharp bug fix. If you paused a session under a restrictive profile, you do not want a later resume to inherit a looser default without making noise.

There are adjacent fixes for duplicate sub-agent activity, TUI routing for sub-agent notifications and approvals, and bounded replay buffers for inactive TUI threads. None of this is glamorous. It is the plumbing that makes a codex agent feel less spooky during real work.

Run codex doctor when the environment feels haunted

codex doctor now diagnoses endpoint protection, network and proxy failures, desktop app state, and update connectivity. That list reads like a week of actual support tickets compressed into one command.

This helps when Codex behaves inconsistently across laptops. One developer might be blocked by endpoint protection, another by a proxy, and another by update connectivity. A doctor command gives the first pass a shared shape before everyone starts guessing.

It does not replace debugging. It tells you where to look first. If a WebRTC sideband connection drops, 0.149.0 also includes a reconnect fix for unexpected transport loss without dropping pending output, but network policies and desktop state can still be outside Codex’s control.

Try 0.149.0 in one existing repo

Start with one repo where a failed experiment will be annoying, not catastrophic. If you are mapping this into your own Codex CLI workflows, keep the first pass narrow: one branch, one task, one verification loop.

Install the exact version from the changelog:

npm install -g @openai/[email protected]
codex doctor
codex

Inside the TUI, try the working-directory commands before asking Codex to edit anything:

/pwd
/cwd
/cd packages/api

Then add a tiny repo-local instruction so the agent has a boundary. A practical AGENTS.md for a Node service might look like this:

# AGENTS.md
- Before editing, confirm the working directory with /pwd in the Codex TUI.
- Reuse the existing Codex session for follow-up requests when it owns the task.
- After changes, run: npm test -- --runInBand
- If MCP access is needed, use read-only GitHub and Jira tools unless the task explicitly asks for writes.

That MCP note is intentionally plain. Codex MCP access is powerful because it can connect work to GitHub, Jira, docs, or private systems. The boundary should say what kind of access is expected before the agent discovers tools mid-task.

If you came from codex cli github, treat GitHub as the discussion trail and the official changelog as the behavior list. The two answer different questions: one shows how the project is maintained, the other says what shipped.

A related pattern shows up in cliclaw Runs Coding CLIs From Telegram: once coding sessions become controllable from somewhere else, naming, wakeups, and handoffs matter more than the chat transcript.

Checklist: what to try first in one repo

• Install the exact release with npm install -g @openai/[email protected].
• Run codex doctor before starting a real task.
• Open one known repo on a throwaway branch.
• Confirm the TUI working directory with /pwd or /cwd.
• Start one task, give it a boring name, and look for it in the agents dashboard.
• Use codex queue only for a follow-up that belongs to that same task.
• Resume or fork a session, then confirm the active permission profile before edits.
• Add or update AGENTS.md with the repo’s test command and MCP access boundary.
• Stop the task from the dashboard when you are done, so stale sessions do not keep pretending to be active work.

Common questions

• What changed in Codex CLI 0.149.0?

  Codex CLI 0.149.0 adds an interactive agents dashboard, working-directory TUI commands, codex queue, stronger Vim editing motions, and broader codex doctor checks. The changelog also lists reliability fixes for queued messages, resumed permission profiles, sub-agent routing, WebRTC reconnects, Windows Terminal scrollback, and replay-buffer memory use.

• Where does codex cli github fit with this release?

  The codex cli github path is best used for repository code, issues, and design discussion, not as a replacement for the official release note. The 0.149.0 changelog is the authoritative behavior summary, while the openai/codex repository is useful when you want implementation context or maintainer discussion.

• Should I use codex queue instead of starting a new session?

  Use codex queue when the follow-up clearly belongs to an existing local or remote Codex session. Start a new session when the task, directory, branch, or permission boundary has changed. The 0.149.0 fixes make queued wakeups more reliable, but they do not make ambiguous task ownership safe.

• Does codex doctor replace manual environment debugging?

  No, codex doctor is a first-pass diagnostic, not a full debugger. In 0.149.0 it checks endpoint protection, network and proxy failures, desktop app state, and update connectivity. That is enough to shorten many support loops, but local security software and network policy can still require manual investigation.

• What is the biggest limit in the changelog?

  The biggest limit is that session controls still depend on clear human naming and repo boundaries. The dashboard, queue, and working-directory commands make state easier to inspect, but they do not decide which task should own a file. A small AGENTS.md rule and a real test command still matter.

Best ways to use this research

• Best for: Codex users who already run CLI sessions and want to understand why 0.149.0 changes day-to-day session handling.
• Best first artifact: A repo-local AGENTS.md that names the test command, working-directory check, and MCP access boundary.
• Best comparison angle: Compare old prompt-per-terminal habits with the new dashboard-and-queue flow for one real maintenance task.
• Best verification loop: Run codex doctor, confirm /pwd, let Codex edit on a branch, then run the repo’s normal tests before merging anything.

Further reading

• @openai — source
• OpenAI Developers — Codex CLI
• GitHub — openai/codex

Try the boring path first

Install 0.149.0, run codex doctor, and test the dashboard with one low-risk repo. The release is most useful when you make session state visible before the work gets complicated.

One methodology lens

One useful way to read this through our methodology is the Design step: delegate option mapping and pattern exploration, review the interfaces and tradeoffs, and keep ownership of architecture and contracts. If that split is still fuzzy, the workflow usually is too.