Constant "Bad Request" happening to me

Resolved 💬 8 comments Opened Feb 1, 2026 by Monkopedia Closed Feb 4, 2026
💡 Likely answer: A maintainer (etraut-openai, contributor) responded on this thread — see the highlighted reply below.

What version of Codex is running?

0.93.0

What subscription do you have?

Pro

Which model were you using?

tried with all models

What platform is your computer?

_No response_

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

_No response_

What issue are you seeing?

Constant "Bad Request" happening

What steps can reproduce the bug?

Uploaded thread: 019c1983-b1af-72a1-99ae-ebf08ac45e36

What is the expected behavior?

_No response_

Additional information

_No response_

View original on GitHub ↗

8 Comments

etraut-openai contributor · 5 months ago

Based on the logs, I'm guessing that you've enabled a feature that is still under development and is not yet supported. Please review your config.toml.

atomical · 5 months ago

Would background terminal be one of those?

etraut-openai contributor · 5 months ago

Try renaming your config.toml file temporarily, then relaunch Codex and log in. Do you still see the "Bad Request" in that case?

atomical · 5 months ago

Yes. 019c200d-be63-7152-aa8b-2b084f20432a

Monkopedia · 5 months ago

Sorry, I haven't been doing dev on the machine that was giving me these problems, will try again when I get a chance.

Monkopedia · 5 months ago

This is no longer reproducing for me, sorry.

pardeike · 5 months ago

I am currently having this all the time. Every second request gets me a red {"detail":"Bad Request"} even requests that are rather short and do not require lots of tokens (as it looks to me at least). I cannot let codex run unattended for more than a few minutes just to come back at it stopped mid-flight.

I am exclusively using codex 5.3 with xhigh thinking with my Pro account. I also told it to avoid parsing/sending large results but it happens at random times.

here is my config

model = "gpt-5.3-codex"
model_reasoning_effort = "xhigh"

approval_policy = "never"
sandbox_mode = "danger-full-access"
sandbox_workspace_write.network_access = true
web_search = "live"
features.shell_snapshot = true
features.unified_exec = true
features.steer = true
features.collab = true
model_verbosity = "high"
history.persistence = "save-all"
suppress_unstable_features_warning = true
personality = "pragmatic"

# [mcp_servers.gabs]
# command = "gabs"
# args = ["server"]

[projects."/Users/ap"]
trust_level = "trusted"

[notice]
hide_gpt5_1_migration_prompt = true
"hide_gpt-5.1-codex-max_migration_prompt" = true

[notice.model_migrations]
"gpt-5.2" = "gpt-5.2-codex"
etraut-openai contributor · 5 months ago

@pardeike, when you see this happen, please use the /feedback command to upload your logs and session details, then post the thread ID here.

Edit: Sorry, I just saw your post in #10571. Thanks for uploading your details.