Skip to content

Error running remote compact task: stream disconnected before completion: error sending request for url (https://chatgpt.com/backend-api/codex/responses/compact #15046

Open
Open
Error running remote compact task: stream disconnected before completion: error sending request for url (https://chatgpt.com/backend-api/codex/responses/compact#15046
Labels
bugSomething isn't workingcontextIssues related to context management (including compaction)

Description

@briantcl1992
briantcl1992
opened on Mar 18, 2026

What version of Codex CLI is running?

0.115

What subscription do you have?

chatgpt Pro

Which model were you using?

gpt-5.4

What platform is your computer?

linux

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

linux terminal

What issue are you seeing?

always running into Error running remote compact task: stream disconnected before completion: error sending request for url (https://chatgpt.com/backend-api/codex/responses/compact) when there is still context left.

What steps can reproduce the bug?

Uploaded thread: 019cdbad-25cb-7d00-a1bd-13cc5b058058

What is the expected behavior?

No response

Additional information

No response

Activity

  1. briantcl1992
    added
    bugSomething isn't working
    on Mar 18, 2026

  2. github-actions commented on Mar 18, 2026

    @github-actions
    github-actionsBot
    on Mar 18, 2026 – with GitHub Actions
    Contributor

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

    Powered by Codex Action

  3. etraut-openai
    added
    contextIssues related to context management (including compaction)
    on Mar 23, 2026
  4. etraut-openai
    marked Error running remote compact task: stream disconnected before completion: error sending request for url (https://chatgpt.com/backend-api/codex/responses/compact) #15727 as a duplicate of this issue on Mar 25, 2026

  5. maxiloEmmmm commented on Mar 25, 2026

    @maxiloEmmmm
    maxiloEmmmm
    on Mar 25, 2026

    +1

  6. etraut-openai
    marked ■ Error running remote compact task: stream disconnected before completion: error sending request for url (https://chatgpt.com/backend-api/codex/responses/compact) #16436 as a duplicate of this issue on Apr 2, 2026

  7. smyja commented on Apr 11, 2026

    @smyja
    smyja
    on Apr 11, 2026

    Turned off my wifi anf turned it on again. Also set model to low and fast and its olved the issue

  8. briantcl1992 commented on Apr 11, 2026

    @briantcl1992
    briantcl1992
    on Apr 11, 2026
    Author

    Thanks! Yeah there is this trick that can unblock this error but I want to run my sessions for really long (hours of long running task) with continued context and this error interrupts it and make it impossible...

  9. Alavi1412 commented on Apr 15, 2026

    @Alavi1412
    Alavi1412
    on Apr 15, 2026

    You can also run the /compact command manually and then, ask the agent to continue. But still, it interferes with long-running agents.

  10. chenzhiy2001 commented on Apr 19, 2026

    @chenzhiy2001
    chenzhiy2001
    on Apr 19, 2026

    i turned off and on VPN and the problem is solved

  11. KiteBA89 commented on Apr 26, 2026

    @KiteBA89
    KiteBA89
    on Apr 26, 2026

    i switch model from gpt5.4 to 5.3codex solved

  12. ibabencu commented on Apr 28, 2026

    @ibabencu
    ibabencu
    on Apr 28, 2026

    hey, this is a relatively new occurrence.
    I hope you fix it.
    thread ID 019dd23f-4f50-73d0-9f18-bb1101f6c3ae

  13. Akagilnc commented on May 2, 2026

    @Akagilnc
    Akagilnc
    on May 2, 2026

    Reproducing on Codex CLI v0.125.0, macOS (Apple Silicon), ChatGPT Pro subscription, model gpt-5.5.

    Symptom

    Error running remote compact task: stream disconnected before completion:
error sending request for url (https://chatgpt.com/backend-api/codex/responses/compact)

    Failure happens consistently at the 5-minute mark (300s), which exactly matches the documented default of stream_idle_timeout_ms = 300000 for SSE streams. The compact endpoint stays silent during server-side compute on long sessions, so the client-side idle timeout fires before any response bytes arrive.

    No working override path exists for ChatGPT subscription users

    1. [model_providers.openai] block is rejected — built-in provider IDs (openai, ollama, lmstudio) are reserved per the advanced config docs.
    2. Top-level stream_idle_timeout_ms is documented as accepted in older releases but ignored in current ones.
    3. Defining a custom provider (e.g. [model_providers.my-openai]) requires env_key = "OPENAI_API_KEY". ChatGPT subscription users only have auth.json from codex login — no API key, so this path is blocked.
    4. openai_base_url only changes the base URL, not the timeout.

    Net result: a config knob exists, the default is the exact value causing the bug, but the knob is unreachable for the largest segment of paying users. Existing workarounds in this thread (toggle VPN / switch model / pre-emptive /compact) are all narrow side-effects that don't address the root cause.

    Things tried that did NOT help (network-layer fixes — confirming the bug is HTTP-level, not network)

    • macOS net.inet.tcp.always_keepalive=1, keepidle=60s, keepintvl=30s (persisted via LaunchDaemon)
    • Proxy VPS (Linux): net.ipv4.tcp_keepalive_time=60, BBR + fq qdisc, tcp_rmem/wmem ceiling raised to 64 MB
    • All confirmed effective for SSH long-idle and other TCP-level idle scenarios; irrelevant to this bug as expected — TCP keepalive packets aren't visible to the HTTP-stream idle policy at the chatgpt.com edge.

    Asks (any one would unblock)

    1. Allow stream_idle_timeout_ms override for the built-in openai provider — either via a top-level key (openai_stream_idle_timeout_ms?) symmetric to openai_base_url, or by accepting non-conflicting fields like timeouts inside [model_providers.openai].
    2. Server-side SSE heartbeat from /backend-api/codex/responses/compact during compute, so the stream is never silent for >300s.
    3. Client-side: bump the default for the compact code path specifically. Compact computation reasonably takes minutes on long sessions; 5-minute default is too aggressive for this endpoint.

    Happy to provide upload thread IDs from any reproduction if useful.

  14. endoibiza commented on May 16, 2026

    @endoibiza
    endoibiza
    on May 16, 2026 – with ChatGPT Codex Connector

    I’m also seeing this in Codex.

    Error:
    Automatically compacting context
    Error running remote compact task: stream disconnected before completion: error sending request for url (https://chatgpt.com/backend-api/codex/responses/compact)

    Environment:

    • Codex CLI: 0.131.0-alpha.9
    • Platform: macOS 26.4.1, build 25E253
    • Kernel/arch: Darwin 25.4.0, arm64
    • Surface: Codex desktop app / local Codex session
    • Date observed: 2026-05-16
    • Timezone: Europe/Madrid
    • Privacy preference: minimal details, no thread IDs shared publicly

    Impact:
    Compaction fails when the conversation gets large, leaving the session hard or impossible to continue without starting a fresh thread.

    Expected:
    Automatic context compaction should complete successfully, or retry/fallback gracefully without breaking the session.

    Actual:
    The remote /backend-api/codex/responses/compact request disconnects before completion.

  15. briantcl1992 commented on May 16, 2026

    @briantcl1992
    briantcl1992
    on May 16, 2026
    Author

    I am still facing this error... have been building some tools to help me rescue this programatically but those tools are brittle... Any update on this team? it is really frustrating to deal with this compaction error....

  16. etraut-openai commented on Jun 29, 2026

    @etraut-openai
    etraut-openai
    on Jun 29, 2026
    Contributor

    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.

  17. etraut-openai
    closed this as completedon Jun 29, 2026
  18. etraut-openai
    reopened this on Jun 29, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't workingcontextIssues related to context management (including compaction)

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions