Codex Desktop ambient_suggestions consumes ~70k tokens in the background

Resolved 💬 3 comments Opened Jun 28, 2026 by yjh765113785-droid Closed Aug 4, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

Codex version

Codex Desktop for Windows 26.623.5546.0

Environment

  • Windows 11 Pro
  • Codex Desktop signed in with ChatGPT
  • Date observed: 2026-06-28
  • No app-server reconnects were recorded during the affected period

Problem

Codex Desktop generated home-page ambient suggestions in background/ephemeral turns and consumed a very large amount of included usage despite no corresponding user-requested response.

The desktop log recorded two successful ephemeral_generation_token_usage events for feature=ambient_suggestions:

| Time (UTC) | Model | Input | Cached input | Output | Reasoning output | Total |
|---|---:|---:|---:|---:|---:|---:|
| 2026-06-28 00:28:15 | gpt-5.4 | 34,478 | 34,176 | 157 | 140 | 34,635 |
| 2026-06-28 00:28:24 | gpt-5.4 | 35,776 | 34,688 | 15 | 0 | 35,791 |
| Total | | 70,254 | 68,864 | 172 | 140 | 70,426 |

The app also logged the generated turns as unknown conversations:

Received turn/started for unknown conversation
ephemeral_generation_token_usage feature=ambient_suggestions ...
Received turn/completed for unknown conversation

The installed app bundle indicates that ambient-suggestions-enabled defaults to true.

Steps to reproduce

  1. Open Codex Desktop with existing long conversations/projects.
  2. Visit or remain on the home page.
  3. Wait for ambient suggestions to appear.
  4. Inspect the desktop log for ephemeral_generation_token_usage feature=ambient_suggestions.

Expected behavior

Background home-page suggestions should not silently consume a large amount of the user's included Codex quota. At minimum, the feature should clearly disclose its usage impact and expose an obvious opt-out before generation.

Actual behavior

Two unsolicited background generations consumed 70,426 total tokens in roughly nine seconds. The visible generated output was only 172 tokens.

Additional notes

  • This was not caused by network reconnect retries: the desktop log showed zero non-zero reconnect attempts during the affected app session.
  • Please confirm whether ambient_suggestions usage is intended to count against user limits.
  • Please consider disabling the feature by default, limiting context size, or making the opt-out prominent.
  • Please advise whether quota consumed by these background generations can be restored.

Sensitive account information and conversation text have intentionally been omitted.

View original on GitHub ↗

3 Comments

github-actions[bot] contributor · 2 months ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #30310
  • #28908

Powered by Codex Action

CudoMudo · 2 months ago

Issue is presented wrong. There is no issue. Agent was causing artificial ram leak with using wsl2.

CudoMudo · 2 months ago

Update: I believe this issue was misdiagnosed.

The high RAM usage was not a Codex Desktop memory leak by itself. In my workflow, Codex triggered bash, which started WSL2 (VmmemWSL). WSL then retained several GB of RAM until I manually ran wsl --shutdown.

After shutting down WSL, system memory dropped back to normal.

So the real issue is not the one described here. This can be closed from my side, or treated only as feedback that Codex/Windows workflows can unintentionally start WSL and leave users thinking Codex is leaking memory.