How to tell which Claude Code, Codex, and OpenCode session is stuck (without checking 10 terminals)
A practical workflow to detect “waiting for approval” vs “offline” vs “actually running”, using lightweight checks first and a phone-friendly control loop when you have it.
- CLI
- 0.2.17
- Preview ref
- a2c45c8
A common awkward situation:
Multiple sessions are going (Claude Code, Codex, OpenCode). You put the laptop down for a bit. You come back and something feels off.
Not “it crashed” — more like:
- nothing is moving
- the output stopped mid-thought
- the session is “running” but it’s unclear whether it’s doing anything
The worst part is the overhead: if you have 5–10 sessions, you can burn 20 minutes just figuring out which one needs attention.
This guide is a workflow to answer one question quickly:
Which session is actually stuck, and what kind of stuck is it?
TL;DR
- Don’t guess. First classify the stuckness:
- Waiting for approval / needs input (the common case)
- Disconnected / offline (machine sleeps, Wi‑Fi dropped)
- Busy (still running, just slow)
- Broken (crashed / wedged)
- Start with the lowest-friction checks (session list + last activity + one log tail).
- If you want a phone-friendly “what needs attention right now?” loop, Happier is one of the options that helps because it has a global Inbox and notification routing for requests.
The problem (in plain language)
Most “stuck sessions” are not actually stuck.
They’re waiting.
- waiting for a permission prompt
- waiting for a question you didn’t answer
- waiting because your laptop slept and the client is disconnected
The reason this is hard is that terminals don’t tell you “this needs your attention.” They tell you “this process exists.”
And if you have multiple sessions, the cost isn’t the fix — it’s the diagnosis.
Common approaches and their trade-offs
- Just keep fewer sessions: realistic sometimes, but real work tends to get parallelized.
- One tmux window per repo with a naming scheme: helps, but it’s still a manual scan.
- Tail logs (Codex log_dir / OpenCode logs): useful, but you still have to open the right one.
- Claude Code’s built-in resume/naming and Agent Teams view: useful, but it doesn’t give you a cross-provider “attention list”.
If you want that “attention list” from your phone (or browser), Happier is an open-source app that lets you run and orchestrate Claude Code, Codex, OpenCode and other agents cross-device. It surfaces approvals and requests in one place.
If you’re new to Happier (what it is, and where to get it)
If you haven’t seen Happier before: it’s an open-source companion app (mobile/web/desktop) for coding sessions like Claude Code, Codex, and OpenCode.
The workflow is: sessions keep running on a machine you trust (laptop / server / dev box), and Happier is where you monitor, approve, and keep things moving from your phone.
Get set up:
- How to run Happier from your phone
- GitHub: https://github.com/happier-dev/happier
- Install/download: https://github.com/happier-dev/happier#how-it-works
- Discord: https://discord.gg/W6Pb8KuHfg
A diagnostic checklist that works
1) First: is it waiting for you?
If the session is “stuck”, ask: is it actually blocked on a human decision?
Common signs:
- the last output is a question ("Which option should I pick?")
- the session is waiting on tool permissions
- the session is in a provider-specific mode that requires a user action (e.g. exit plan)
If you’re using Happier, this is where the global Inbox helps: approval requests and permission/user-action requests surface there, and notification routing tries to land you in the exact session that needs attention.
2) Second: is the client disconnected because the machine slept or Wi‑Fi dropped?
If you closed a laptop lid, hopped networks, or your client went into background, the process might be fine but your view is stale.
Typical fixes depend on your tool:
- If you are SSH’ing, Mosh is the least painful “roaming + sleep” upgrade for this class of problem.
- If the tool is a client/server streaming UI, you may need to reconnect or reload the stream.
(There are real-world reports of “stale session state after sleep” issues in client/server tools; in those cases the fix is often “reconnect + upgrade”.)
3) Third: is it busy, just slow?
A session can look stuck when it’s:
- chewing through a big diff
- running tests
- waiting on a slow network call
In this case, what you want is progress signals:
- last tool call timestamp
- last file edit
- last token output
If you can’t get any progress signal, treat it as broken and move to the next step.
4) Last: treat it as wedged (and choose a safe intervention)
If you’re convinced it’s truly wedged:
- prefer a low-risk interrupt (“stop and summarize where you are”)
- then restart/resume
Avoid killing processes blindly if you care about preserving session identity. If you have a resumable model, use resume/attach paths rather than “start new and paste context”.
A phone-first “attention list” workflow (Happier)
If you’re running many sessions and you keep losing time to diagnosis, the best thing Happier gives you is not “more power.”
It’s less searching:
-
Inbox answers: “what needs my attention right now?”
-
Notifications deep-link to the right session (and the right server profile)
-
Needs attention groups the sessions that are blocked on you, so the rest can keep running without you checking each one
Park a session with a reminder
Some sessions aren't stuck. They're just not your problem for the next two hours. Since 0.2.13 you can set them aside on purpose:
- Open the session row's menu and choose Remind me.
- Pick a suggested time, Choose date and time…, or a saved preset.
Setting a reminder marks the session read and moves it out of Needs attention until the time comes. Then it returns there, even if nothing new happened. Since 0.2.16, opening the session clears a due reminder (turn off Settings → Session → Clear reminders on open if you prefer to clear them by hand). Reminders change Happier's in-app attention state. They don't send a push. Details are in the session read state docs.
Nudge a busy session without stopping it
If a session is busy but heading the wrong way, Steer now (0.2.16) delivers your queued message to the agent without interrupting the turn, where the agent supports steering. Send now still interrupts. See steering.
Keep your phone quiet while you're at the computer
Also new in 0.2.16: an optional notification setting mutes phone pushes while Happier is focused on a computer. If computer focus can't be established, pushes still reach the phone.
The honest trade-off: it depends on the machine still being reachable.
Troubleshooting
I can’t tell if it’s stuck or waiting
Force a decision:
- send a short message: “Are you waiting on my input or still running?”
- if the tool supports it, request a one-line status update
I keep losing track of sessions
Use one of these patterns:
- one worktree / one session per task
- consistent naming for sessions and repos
- one “attention list” surface (Inbox, Needs attention, notifications)
- a Remind me time for sessions you’ve read but want back later