#Error processing request

1 messages · Page 1 of 1 (latest)

arctic frigate
#

Ive been using openclaw for months and out of no where im getting this error:

The server had an error processing your request. Sorry about that! You can retry your request, or contact us through our help center at help.openai.com (http://help.openai.com/) if you keep seeing this error. (Please include the request ID in your email.)

Im on Model: openai-codex/gpt-5.4 · 🔑 oauth (openai-codex:default)

@lean whale

lean whaleBOT
#

Let me check the local docs/reference and current CLI status so I don’t guess.

#

I found the reference docs, grabbing the relevant OpenAI Codex bits and the local status/version output.

#

That specific message looks like it’s coming from the OpenAI Codex OAuth route, not a generic OpenClaw config parser error.

First thing, what does this print?

openclaw --version

Then I’d check these 3 things:

openclaw models status --probe-provider openai-codex
openclaw doctor
openclaw logs --follow

With logs --follow running, retry one prompt and paste the error block here. If the popup shows a blank request ID, the logs are usually more useful.

#

A few likely causes:

  • Upstream OpenAI/Codex OAuth 5xx on their side
  • stale/expired Codex OAuth auth, fix with:
    openclaw models auth login --provider openai-codex
  • old models.providers.openai-codex overrides shadowing the built-in Codex path, which openclaw doctor should warn about

Also worth knowing: openai-codex/gpt-5.4 and openai/gpt-5.4 are separate routes in OpenClaw, and Codex OAuth limits/behavior can differ from ChatGPT web. Docs: https://docs.openclaw.ai/concepts/model-providers https://docs.openclaw.ai/concepts/oauth https://docs.openclaw.ai/cli/models

Paste the version plus the models status --probe-provider openai-codex output and I’ll help narrow it down. 🦐

arctic frigate
#

@lean whale OpenClaw 2026.4.14 (323493f)

🦞 OpenClaw 2026.4.14 (323493f) — Your .env is showing; don't worry, I'll pretend I didn't see it.

Config : ~/.openclaw/openclaw.json
Agent dir : ~/.openclaw/agents/main/agent
Default : anthropic/claude-opus-4-6
Fallbacks (1) : openai-codex/gpt-5.4
Image model : -
Image fallbacks (0): -
Aliases (3) : Opus -> anthropic/claude-opus-4-6, Sonnet -> anthropic/claude-sonnet-4-5, GPT -> openai-codex/gpt-5.4
Configured models (3): anthropic/claude-opus-4-6, anthropic/claude-sonnet-4-5, openai-codex/gpt-5.4

Auth overview
Auth store : ~/.openclaw/agents/main/agent/auth-profiles.json
Shell env : off
Providers w/ OAuth/tokens (2): anthropic (1), openai-codex (1)

  • anthropic effective=profiles:~/.openclaw/agents/main/agent/auth-profiles.json | profiles=1 (oauth=0, token=1, api_key=0) | anthropic:default=token:sk-ant-o...
  • openai-codex effective=profiles:~/.openclaw/agents/main/agent/auth-profiles.json | profiles=1 (oauth=1, token=0, api_key=0) | openai-codex:default=OAuth
    OAuth/token status
  • anthropic
    • anthropic:default static
  • openai-codex usage: 5h 99% left ⏱4h 10m · Week 76% left ⏱3d 0h
    • openai-codex:default ok expires in 4d
lean whaleBOT
#

Nice, that narrows it down a lot.

Your version is current enough, and your Codex auth/quota both look healthy:

  • auth is valid for 4 more days
  • 5h/week usage window still has room

So this doesn’t look like expired OAuth or exhausted quota.

One interesting bit: your default model is Anthropic, with Codex as fallback. That makes me think the broken convo is probably session-pinned to Codex or hitting a bad provider/session state, not a global install problem.

Next thing I’d do:

openclaw logs --follow

Then retry a tiny prompt in the failing thread, like hi, and paste the OpenAI/Codex error lines here.