Repository navigation
OpenAI provider headers timeout after 10000ms on 1.15.11; increasing headerTimeout fixes it #29548
Description
Description
After upgrading OpenCode via Homebrew from 1.14.28 to 1.15.11, requests using the OpenAI provider began failing with:
Provider response headers timed out after 10000ms
Increasing the OpenAI provider headerTimeout resolved the issue locally.
This looks like a regression or a default timeout that may be too aggressive for some OpenAI/ChatGPT-provider requests or network environments.
Plugins
No custom plugins involved in the repro.
OpenCode version
1.15.11
Installed via Homebrew.
Steps to reproduce
- Upgrade OpenCode from
1.14.28to1.15.11via Homebrew. - Use the OpenAI provider with
gpt-5.5-fast/ GPT-5.5 Fast. - Run a normal request.
- Observe the request fail with:
Provider response headers timed out after 10000ms
- Add the following provider options to the global config:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"openai": {
"options": {
"headerTimeout": 60000,
"timeout": 600000,
"chunkTimeout": 60000
}
}
}
}- Verify with
opencode debug configthat the options are loaded. - Run the same request again.
- Observe that it succeeds after increasing
headerTimeout.
Screenshot and/or share link
N/A. Relevant terminal error is included above.
Operating System
macOS, arm64
Terminal
zsh
Question
Is the 10000ms default intended for OpenAI/ChatGPT-provider requests in 1.15.11? It may be too low for some responses or network/proxy environments.
Reacted by Ekaterina Markelova, Yashank, Clemens Damke, Sasha Koss, wbdb, Tomasz Boguszewski, Md. Abu Taher, 朱凌峰, Gerardo, Juan Fraire and 1 more
Reacted by Taiyi, Gurvan, Emmanuel Keifala, JHIH-SIOU LI, sbeygi, manumaso-nttd, ZenDevMaster, kostanovalexey, Aboghali, Yashank and 3 more
Metadata
Metadata
Assignees
Labels
No labels
Activity
github-actions commentedon May 27, 2026
This issue might be a duplicate of existing issues. Please check:
Headers Timeout Errorwith default timeout being too low for some provider requests; same workaround of increasingheaderTimeout/timeoutin config.opencode.jsonprovider options.rayborg commentedon May 27, 2026
Clarifying the duplicate suggestions:
Headers Timeout Error) while waiting on slow local providers such as Ollama.1.2.25and longer-running prompt/stream timeouts.This issue is specifically a shorter
10000msheader timeout observed after upgrading to1.15.11with the OpenAI provider / ChatGPT-provider path usinggpt-5.5-fast.The practical difference is the failing threshold and provider path:
Provider response headers timed out after 10000ms, fixed by settingprovider.openai.options.headerTimeoutto60000.So this may share the broader timeout-config surface, but it seems worth tracking separately unless maintainers consider the
1.15.11OpenAI10000msdefault intentionally covered by those issues.rekram1-node commentedon May 27, 2026
This is intentional, many people are getting no response from openai for extended periods of time almost every other request it seems for certain folks, so we have this header timeout to account for that, as seen in the release notes for the release.
We may bump it but it's entirely configurable and u can even disable it by setting
headerTimeout: falseC485 commentedon May 27, 2026
i guess we need something that will disable all timeouts in config file, for now
"timeout": 3000000, "chunkTimeout": 3000000, "headerTimeout": falsedoes nothing at all, for local providers we're still getting
TypeError: terminated at Fetch.onAborted (node:internal/deps/undici/undici:13602:53)I would be great to have it as soon as possible
rekram1-node commentedon May 27, 2026
@C485 this seems like something else entirely none of those timeouts are enabled by default besides header timeout but its only enabled for openai provider and thats it (by default)
Dayclone commentedon Jun 3, 2026
I get "Provider response headers timed out after 10000ms" now as well when it never used to happen
rekram1-node commentedon Jun 3, 2026
@Dayclone u can bump it
Dayclone commentedon Jun 3, 2026
@rekram1-node I did
"provider": { "openai": { "options": { "timeout": 20000 } },But probably did that wrong?
rekram1-node commentedon Jun 3, 2026
Yes u did, read above msgs, it is
headerTimeoutDayclone commentedon Jun 3, 2026
Yep that was it thank you! Seems to be working now.
Abdo-Eid commentedon Jun 8, 2026
From what I noticed, the problem appears after GPT models read/analyze images and disappears when I compact the conversation or talk in a new chat
i disabled the headerTimeout as @rekram1-node suggested, it took some time but it eventually responded without compaction
@rayborg
kossnocorp commentedon Jul 11, 2026
Tried the fix when using GPT-5.6 Sol and it worked! I had to fall back to Codex few times in the past because of this problem, and losing the session history of WIP was very annoying. I hope it gets fixed so OpenCode users don't churn, but the config change works for me for now 👌 Thank you @rayborg