After a few exchanges of prompting and working, Codex stops showing its work / activity log, after a brief initial output ... so I dont know if its working or not #6274

What version of Codex is running?

codex-cli 0.55.0

What subscription do you have?

Plus

Which model were you using?

gpt-5-codex

What platform is your computer?

Windows WSL2

What issue are you seeing?

Codex just stops responding properly ...

› Are you doing anything ?

• Still with you—was digging through worker_pool.py and the timeout delivery path to see where the normal end-to-end latency gets printed (it doesn’t). Next move is to add the same latency
calculation you see in the regular dispatch path so TIMEOUT_DELIVERED includes the elapsed time. Let me know if you’d like me to add that now.

› whats is going on ?

/status

╭────────────────────────────────────────────────────────────────────────────╮
│ >_ OpenAI Codex (v0.55.0) │
│ │
│ Visit https://chatgpt.com/codex/settings/usage for up-to-date │
│ information on rate limits and credits │
│ │
│ Model: gpt-5-codex (reasoning none, summaries auto) │
│ Directory: XXXXXXXXXXXXXXXXXXXXXXXXXXX │
│ Approval: on-request │
│ Sandbox: workspace-write │
│ Agents.md: │
│ Account: dravXXXXXp@gmail.com (Plus) │
│ Session: 019a5534-151a-7703-88b9-fae7fbba04df │
│ │
│ Context window: 76% left (74.5K used / 272K) │
│ 5h limit: [███░░░░░░░░░░░░░░░░░] 15% used (resets 15:10) │
│ Weekly limit: [█░░░░░░░░░░░░░░░░░░░] 5% used (resets 17:27 on 10 Nov) │
╰────────────────────────────────────────────────────────────────────────────╯

› Are you checking or not ... answer me

› What is going on ?

• Sorry for the radio silence—I’ve been tracing the timeout delivery path to see where the latency data should come from. The end-to-end latency isn’t already captured for timeouts; we
need to measure it ourselves. Plan is:

• calculate timeout_latency_ms = (time.time() - segment.created_time) * 1000,
• log the same style message we use elsewhere.

If you’re good with that approach I’ll drop the code into worker_pool.py right after the timeout callback succeeds and show you the diff.

› ok sure

› i need some kind of output to see what you are doing .. otherwise i dont know what is going oon and whether to prompt you or not

› Find and fix a bug in @filename

75% context left · ? for shortcuts

What steps can reproduce the bug?

Chat for sometime and codex stops responding

What is the expected behavior?

No response

Additional information

No response