You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
in goal last steer is re-included after each compaction #21291
What terminal emulator and version are you using (if applicable)?
No response
What issue are you seeing?
After each compaction event agent is re-reacting to last sent steer message that is no longer relevant.
What steps can reproduce the bug?
Start long running /goal
At some point sent steer like, refactor X now
Agent will address steer message as expected, and continue normally
Compaction happens
Agent re-recive last steer again and tries to address it again
This will repeat after every future compaction
What is the expected behavior?
Steer should not be re-included after compaction or, next goal cycle should displace user messages in history
Additional information
Here is codex analysis of the issue:
turn/steer becomes pending input, then gets recorded as a normal user message once consumed.
Compaction preserves recent non-summary user messages. It does not know that an old user message was
only a temporary steer.
/goal continuation prompts are injected as developer messages, not user messages, so they do not
displace that old steer as the latest “real user” message.
After each compaction, the replacement history can still contain that old steer as the most recent
real user message, plus a fresh summary. The model can then treat it as newly salient and react to it
again.
This is now fixed. Earlier implementations of the /goal feature injected the goal continuation prompt as a developer message. The new implementation uses a user message, which prevents this problem.
Doesn't really look fixed to me : in "goal" mode, the agent still seems to be wasting lots of tokens after each compaction re-evaluating the same previous steer message again and again and again.
This is now fixed. Earlier implementations of the /goal feature injected the goal continuation prompt as a developer message. The new implementation uses a user message, which prevents this problem.
Not fixed for me in Windows.
Feedback ID 019f7d4d-3161-7ce3-bb2e-2d0b8155f671
Version 26.715.31925 (latest available at time of writing).
One workaround I've come up to stop it re-handling old steering messages is to give a follow-up message with something like this:
"This steering command is an empty command to deal with a codex compacting bug that re-sends previous steering messages. Ignore this message."
@etraut-openai nearly two months later, this bug has not been fixed. These repeated steering commands can do serious damage in a task. Please re-open this issue and prioritise the bug as severe, as it's costing a lot of time and tokens. The sheer number of duplicate/similar issues in github should really be a giveaway that this is affecting a lot of people.
Activity
github-actions commentedon May 6, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
etraut-openai commentedon May 30, 2026
This is now fixed. Earlier implementations of the
/goalfeature injected the goal continuation prompt as a developer message. The new implementation uses a user message, which prevents this problem.nbros commentedon Jul 19, 2026
Doesn't really look fixed to me : in "goal" mode, the agent still seems to be wasting lots of tokens after each compaction re-evaluating the same previous steer message again and again and again.
andrew-adamson-proteros commentedon Jul 20, 2026
Not fixed for me in Windows.
Feedback ID 019f7d4d-3161-7ce3-bb2e-2d0b8155f671
Version 26.715.31925 (latest available at time of writing).
One workaround I've come up to stop it re-handling old steering messages is to give a follow-up message with something like this:
"This steering command is an empty command to deal with a codex compacting bug that re-sends previous steering messages. Ignore this message."
andrew-adamson-proteros commentedon Jul 28, 2026
@etraut-openai nearly two months later, this bug has not been fixed. These repeated steering commands can do serious damage in a task. Please re-open this issue and prioritise the bug as severe, as it's costing a lot of time and tokens. The sheer number of duplicate/similar issues in github should really be a giveaway that this is affecting a lot of people.