Repository navigation
Error running remote compact task #9800
Description
What version of Codex is running?
v0.89.0
What subscription do you have?
Pro
Which model were you using?
gpt-5.2-codex reasoning xhigh
What platform is your computer?
Ubuntu 24.04
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?
Uploaded thread: 019becfa-bd48-7f63-882a-9a90d6052cb9
What is the expected behavior?
No response
Additional information
No response
Activity
swordfish444 commentedon Jan 26, 2026
@etraut-openai The uploaded thread ID here (019becfa-bd48-7f63-882a-9a90d6052cb9) should be really useful — thanks @nshkrdotcom.This feels like part of the broader “remote compaction can fail hard and strand the session” family (e.g. #9666 is a timeout waiting for the child process; there are a few other
remote compact taskreports too), just with a different failure mode (context_length_exceeded).Two thoughts:
context_length_exceeded, it likely means the compactor request is still too large (maybe including too much history/tool output). Server-side truncation/chunking of compactor input might help.If you want to reduce fragmentation, maybe track these under a single canonical “remote compaction failures” issue and link the various thread IDs.
nshkrdotcom commentedon Jan 26, 2026
Hasnt happened since, and I have since updated codex.
atomical commentedon Jan 31, 2026
Still experiencing this issue. It may have to do with too much tool output in my case.
Vathivis commentedon Feb 3, 2026
started happening to me as well
id: 019c1eda-5393-7d70-a40c-a93a64ae17d8
Numinex-Corp commentedon Feb 4, 2026
Same for me. Having PRO plans. So for my case it happened 2 times and maybe seems related to plan mode. Because i was close to full context length and when using Plan mode it made the plan and didnt replay to launch the plan.
kcosr commentedon Feb 5, 2026
This has been happening to me for a few days. Previously I was a few versions of Codex behind, but I just upgraded and the problem continues.
019c2b9e-9310-7e43-af8f-ba6a031258db
brianbader commentedon Feb 27, 2026
This has been happening to me as well. I'm running codex on windows using ubuntu wsl.
019c9c8c-8d5e-7d20-96d6-06ddcabcb1d1
edit: the specific error I am seeing is below
bitsydarel commentedon Apr 14, 2026
Error running remote compact task: {
"error": {
"message": "Unknown parameter: 'prompt_cache_retention'.",
"type": "invalid_request_error",
"param": "prompt_cache_retention",
"code": "unknown_parameter"
}
}
SebasGarcia08 commentedon Apr 14, 2026
This is happening to me very often now:
Error running remote compact task: {
"error": {
"message": "Unknown parameter: 'prompt_cache_retention'.",
"type": "invalid_request_error",
"param": "prompt_cache_retention",
"code": "unknown_parameter"
}
}
TheBatashev commentedon Apr 14, 2026
Error running remote compact task: { "error": { "message": "Unknown parameter: 'prompt_cache_retention'.", "type": "invalid_request_error", "param": "prompt_cache_retention", "code": "unknown_parameter" } }
HazelSX2 commentedon Apr 14, 2026
Latest version: very often at pro plan gpt-5.4 highx:
Error running remote compact task: {
"error": {
"message": "Unknown parameter: 'prompt_cache_retention'.",
"type": "invalid_request_error",
"param": "prompt_cache_retention",
"code": "unknown_parameter"
}
}
Running fine again after wait some minutes...
scottweiss commentedon Apr 14, 2026
gpt-5.4 xhigh
■ Error running remote compact task: {
"error": {
"message": "Unknown parameter: 'prompt_cache_retention'.",
"type": "invalid_request_error",
"param": "prompt_cache_retention",
"code": "unknown_parameter"
}
}
temktoznaet commentedon Apr 14, 2026
GPT 5.4
Error running remote compact task: { "error": { "message": "Unknown parameter: 'prompt_cache_retention'.", "type": "invalid_request_error", "param": "prompt_cache_retention", "code": "unknown_parameter" } }
YolozzZ66 commentedon Apr 14, 2026
I wait about 5 mins, and it return running normally.
etraut-openai commentedon Apr 14, 2026
For those who were seeing the "prompt_cache_retention" error, that should be fixed now.
challmy commentedon May 22, 2026
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" } }
I am a 5x Pro package. Can anyone solve this problem for me?
019e4df6-f2ad-7bd3-a8b3-c0b65c4c4565
etraut-openai commentedon Jun 29, 2026
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
/feedbackand open a new bug report.