Codex Ultra mode is just wasting usage
Nobody has claimed this yet.
Assessment
- Difficulty
- 5/5
- Estimated time
- Over a week
- Newbie friendliness
- 25/100
- Issue type
- Bug
- Clarity
- Needs clarification
- Activity status
- Quiet
- Tech stack
- rust
- Domain
- ai-infra-agents, cli
Research direction
Start at the Ultra mode entry point and reproduce the reported behavior using a project with a focused folder, an existing plan, and explicit testing steps. Compare Ultra with Extra high while reviewing the task progress and agent activity for repeated reviews, drift, and lag; the issue does not name files or tests, and completion criteria are not specified.
Written by the indexing model from the issue text.
Description
What issue are you seeing?
Hello, i dont know if this is a bug or not. I noticed that switching to ULTRA mode, is just wasting usage without doing any actual job. I tested on 2 projects and i was wondering where the weekly usage was going to. It spent the whole weekly on a single project in 2.5 hours, working in a specific folder with exact directions and the files inside it are optimized already and small in size (250-300 lines each) but they are plenty and hightly related to each one thats why i turned on ultra. Extra high mode finished the same task in 40 minutes and Ultra mode was fighting the whole night. And the strange thing is that it already had an optimized Plan to follow with exact tasks and specific testing steps.
I went through all the chat to figure out what it was doing, i even opened a side chat to complain about the thread because it was lagging as hell too. It was saying task 2/5 and side chat told me that the agents was fighting each other and were running reviews over and over again for simple lines and they were stucked into infinite review loop. Also they went outside of the folder to unrelated project features that had nothing to do with the task(drift). 2 weeks now it was just wasting my weekly (im in 200$ plan steady client). Without any actual results at the end. I dont know if the same is happening to CLI. I always use latest app versions. The problem is not about if Ultra was the right mode for my tasks. The problem is the drifting, lagging, and the fight between the spawned agents. If i had left it still open they would fight with my computer too.
What steps can reproduce the bug?
Executing tasks in Ultra mode.
What is the expected behavior?
No response
Additional information
No response
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.5k
- Avg merge
- 1m
- Merged PRs (30d)
- 1k
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from openai/codex
-
enhancement remote
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
bug CLI windows-os
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
-
macOS sandbox blocks hw.optional.arm64 sysctl, causing Flutter to misdetect Apple Silicon as x64 Openbug CLI sandbox
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
bug CLI TUI
Difficulty 2/5 1-3 hours Newbie friendliness 90/100
-
CLI config enhancement skills
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 86/100
kwakseongjae/auto-hwp#319 ·
-
area:cli bug filter-quality good first issue priority:medium
Difficulty 2/5 1-3 hours Newbie friendliness 84/100
-
Difficulty 1/5 Under an hour Newbie friendliness 72/100
bevyengine/bevy#25861 ·
-
comp-datalake
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
ClickHouse/ClickHouse#121222 ·
-
A-linter
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
oxc-project/oxc#26863 ·