Codex Spark unable to compact conversations #11641

Activity

1. dionny

   added

   bugSomething isn't workingSomething isn't working

   on Feb 12, 2026
2. dionny

   changed the title [-]Codex Spark seems to fail to compact[/-] [+]Codex Spark unable to compact conversations[/+] on Feb 12, 2026
3. aibrahim-oai commented on Feb 12, 2026

   

   aibrahim-oai

   on Feb 12, 2026

   Contributor

   More actions

   Can you do /feedback?
4. dionny commented on Feb 12, 2026

   

   dionny

   on Feb 12, 2026

   Author

   More actions

   ■ 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.
5. dionny commented on Feb 12, 2026

   

   dionny

   on Feb 12, 2026

   Author

   More actions

   Done! Thread ID = 019c53f7-344a-7fe3-a92b-631660a8567f
6. skypher commented on Feb 14, 2026

   

   skypher

   on Feb 14, 2026

   More actions

   Here's mine: 019c5b45-9eeb-7ea0-9623- f917e08494fe
7. bahmanpour1980-lab

   added a commit that references this issue on Feb 21, 2026

   Update models.json

   f748b1a
8. etraut-openai

   added

   contextIssues related to context management (including compaction)Issues related to context management (including compaction)

   on Mar 23, 2026
9. yassirusa commented on Apr 6, 2026

   

   yassirusa

   on Apr 6, 2026

   More actions

   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"
10. ioma8 commented on Apr 9, 2026

    

    ioma8

    on Apr 9, 2026

    More actions

    This needs to be fixed! Disrupts flow!
11. JohnnyVicious commented on Apr 9, 2026

    

    JohnnyVicious

    on Apr 9, 2026

    More actions

    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.
12. etraut-openai commented on Jun 29, 2026

    

    etraut-openai

    on Jun 29, 2026

    Contributor

    More actions

    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.
13. etraut-openai

    closed this as completedon Jun 29, 2026