Codex Spark unable to compact conversations

Resolved 💬 8 comments Opened Feb 12, 2026 by dionny Closed Jun 29, 2026

💡 Likely answer: A maintainer (aibrahim-oai, contributor) responded on this thread — see the highlighted reply below.

What version of Codex CLI is running?

0.100.0

What subscription do you have?

Pro

Which model were you using?

gpt-5.3-codex-spark-xhigh

What platform is your computer?

_No response_

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

_No response_

What issue are you seeing?

■ Error running remote compact task: {
"error": {
"message": "Your input exceeds the context window of this model. Please adjust
your input and try again.",
"type": "invalid_request_error",
"param": "input",
"code": "context_length_exceeded"
}
}

What steps can reproduce the bug?

I can reliably reproduce the problem. Compaction doesn't seem to be working with Codex Spark.

What is the expected behavior?

Compaction should work.

Additional information

_No response_

View original on GitHub ↗

8 Comments

aibrahim-oai contributor · 5 months ago

Can you do /feedback?

dionny · 5 months ago

■ Error running remote compact task: {
  "error": {
    "message": "Your input exceeds the context window of this model. Please adjust
your input and try again.",
    "type": "invalid_request_error",
    "param": "input",
    "code": "context_length_exceeded"
  }
}

────────────────────────────────────────────────────────────────────────────────────

• Model changed to gpt-5.3-codex xhigh

• Context compacted

This suggests Codex Spark has a smaller context window than Codex.

dionny · 5 months ago

Done! Thread ID = 019c53f7-344a-7fe3-a92b-631660a8567f

skypher · 5 months ago

Here's mine: 019c5b45-9eeb-7ea0-9623- f917e08494fe

yassirusa · 3 months ago

When will this be worked on. Codex-5.3 and codex-5.3-spark are completely useless and they keep churning tokens without editing any code until they "run out of room"

ioma8 · 3 months ago

This needs to be fixed! Disrupts flow!

JohnnyVicious · 3 months ago

I stopped using codex-spark all together coz of this, the only workaround is switching model to GPT-5.4 with a restart/resume and then run compact. But after a bit you run into the same error again after you switched to spark.

etraut-openai contributor · 21 days ago

Thanks for reporting this problem. Until recently, Codex used a separate endpoint and server-side logic for compaction. We recently switched to a more robust approach where the compaction logic is moved locally using the same endpoint as normal turns. This eliminates "remote compaction" errors and increases the stability and reliability of compaction operations. If you see further problems with compaction, please use /feedback and open a new bug report.