ERROR codex_core::compact_remote: remote compaction failed #13271

Activity

1. etraut-openai

   added

   bugSomething isn't workingSomething isn't working

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

   on Mar 2, 2026
2. garitar commented on Mar 19, 2026

   

   garitar

   on Mar 19, 2026

   More actions

   I hit what looks like the same failure on codex-cli 0.115.0 on Darwin 25.2.0 arm64, model gpt-5.3-codex-spark with xhigh reasoning.

   One extra data point that may help narrow root cause: on this machine, the live Codex model cache at ~/.codex/models_cache.json says Spark has:

   {
     "slug": "gpt-5.3-codex-spark",
     "context_window": 128000,
     "effective_context_window_percent": 95
   }

   So Codex's effective window becomes 121600, which exactly matches the failing runtime log:

   ERROR codex_core::compact_remote: remote compaction failed ...
   last_api_response_total_tokens=116010
   estimated_tokens_of_items_added_since_last_successful_api_response=11672
   model_context_window_tokens=Some(121600)
   ...
   "code": "context_length_exceeded"
   

   That suggests this may not just be a generic overflow. If the default auto-compaction threshold is still 90% of raw context, Spark only has 6400 tokens of slack between compact trigger (115200) and effective hard ceiling (121600). In this failure, the last successful response was already at 116010, and the next accumulated step added 11672, so a single search/tool-heavy step seems able to outrun the remaining headroom.

   Another bad outcome from the same run: after the compaction failure, Codex wrote an empty final artifact instead of a useful terminal failure result:

   Warning: no last agent message; wrote empty content ...
   

   So I think there may be two separate problems here:

   1. Spark's current effective window / compaction timing is too tight for long search-heavy sessions.
   2. When compact_remote overflows, Codex can degrade to an empty final output artifact.

   If useful, I can provide a tighter repro packet, but the failing shape here was a broad audit-style run with web search and bounded scratch enabled.
3. nos1609 commented on Apr 11, 2026

   

   nos1609

   on Apr 11, 2026

   More actions

   Got the same issue on gpt-5.4 with codex-cli 0.120.0

   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" }
4. korenmic commented on May 26, 2026

   

   korenmic

   on May 26, 2026

   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" } }
   

   Getting it in 5.5 in codex desktop too when trying to run /compact
5. 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.

   ❤️React with ❤️1Reacted by Daniil Sedov
6. etraut-openai

   closed this as completedon Jun 29, 2026