--- title: OpenAI resets Codex and ChatGPT Work usage limits after... description: OpenAI reset usage limits for all paid Codex and ChatGPT Work users after fixing a series of bugs that were causing overconsumption of allowances. Root causes... canonical: https://daily.dev/posts/openai-resets-codex-and-chatgpt-work-usage-limits-after-fixing-multiple-overconsumption-bugs-ftkpeycch twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: OpenAI resets Codex and ChatGPT Work usage limits after fixing multiple overconsumption bugs | daily.dev og:description: OpenAI reset usage limits for all paid Codex and ChatGPT Work users after fixing a series of bugs that were causing overconsumption of allowances. Root causes... og:url: https://daily.dev/posts/openai-resets-codex-and-chatgpt-work-usage-limits-after-fixing-multiple-overconsumption-bugs-ftkpeycch og:image: https://api.daily.dev/og/posts/FtkpEyCCH.png og:image:alt: OpenAI resets Codex and ChatGPT Work usage limits after fixing multiple overconsumption bugs og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI resets Codex and ChatGPT Work usage limits after fixing multiple overconsumption bugs **[Collections](https://daily.dev/sources/collections)** · 2 min read · 1 upvotes · 1 comments ## Summary OpenAI reset usage limits for all paid Codex and ChatGPT Work users after fixing a series of bugs that were causing overconsumption of allowances. Root causes included compaction retaining old images, memory workers looping on stop hooks, goals continuing past their stop condition, automations running too frequently, subagents escalating unnecessarily, redundant computer history summarization, unneeded rolling task summaries, and MCP tool results being double-encoded. Depending on usage patterns, allowances should now stretch 10% to 50% further. OpenAI also added architectural safeguards and internal alerts to catch regressions, and is building in-app usage breakdowns. ## Content OpenAI has reset usage limits for all paid Codex and ChatGPT Work subscribers - twice in quick succession, with the second reset timed to 6pm PST. The company also announced it hit 25 million active users. More importantly, the team shipped a round of bug fixes that should make your existing allowance go further. Depending on how you use Codex, OpenAI says you should see between 10% and 50% more mileage out of your weekly limit than before. Separately, OpenAI quietly increased 5-hour rate limits by around 50% across all plans without a formal announcement. Here's what they found and fixed: - **Compaction** was keeping old images around, sometimes making context large enough to trigger compaction again. Users making heavy use of images should see about 10% less usage after the fix. - **Memory workers** running in the background could inherit Stop hooks and get stuck in a loop. One extreme case involved a thread checking whether it could stop 15,000 times. Affected fewer than 1% of users, but the worst cases were bad. - **Goals** could finish and then keep running past the intended stop condition, or the model would retry broken tools indefinitely. Some examples consumed between 15% and 70% of a weekly allowance in a single session. - **Automations** with custom schedules were sometimes running more frequently than configured. - **Subagents** - smaller models like Luna were occasionally pulling in more capable helpers without being asked. The orchestrating model could also request sub-agents to run in /fast mode even when it wasn't running that way itself. - **Computer History** was repeatedly summarizing overlapping activity. In some cases this consumed up to a fifth of the weekly allowance on its own. - **Rolling task summaries** were triggering extra background requests on ordinary turns, adding about 1% to token usage across the board. This has been disabled. - **MCP** had two separate issues: some tool results were being encoded twice, and tool instructions were getting cut off and re-fetched. OpenAI says it has made architectural changes to prevent these from regressing, with internal alerts if they do. The team is also working on in-app usage breakdowns so you can see where your allowance is actually going. ## Questions this post answers ### Why was my OpenAI Codex weekly usage allowance getting used up so fast? Several overconsumption bugs were draining Codex usage allowances faster than expected. Causes included compaction retaining stale images and re-triggering itself, memory workers stuck looping on Stop hooks (one thread checked 15,000 times), goals running past their intended stop condition or retrying broken tools (consuming 15-70% of a weekly allowance in one session), and Computer History repeatedly summarizing overlapping activity, sometimes using up to a fifth of the weekly allowance alone. _daily.dev surfaces fixes like these so heavy Codex users can stop losing quota to background bugs._ ### Did OpenAI increase Codex rate limits recently? Yes, OpenAI quietly raised 5-hour rate limits by around 50% across all Codex plans without a formal announcement, alongside a reset of weekly usage limits for paid Codex and ChatGPT Work subscribers. Separately, bug fixes to compaction, memory workers, goals, automations, subagents, and MCP handling should make existing weekly allowances last 10% to 50% longer depending on usage patterns. _track quiet limit changes like this on daily.dev before they affect your Codex workflow budget._ ### What MCP bugs was OpenAI Codex hitting that wasted usage quota? Two separate MCP issues were consuming extra usage: some tool results were being encoded twice, and tool instructions were getting cut off and then re-fetched, both adding unnecessary token overhead. These have been fixed as part of a broader round of changes that also disabled rolling task summaries, which were adding about 1% to token usage on ordinary turns. _developers debugging MCP overhead in agent tools can follow fixes like this on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 846 comments across x (as of 2026-09-13). **TL;DR:** Reaction is dominated by frustration that the reinstated 5-hour rolling limit on Plus plans makes the weekly usage reset largely meaningless, since users hit the short-window cap long before they can burn through their weekly allowance. **Sentiment:** 10% positive · 15% mixed · 75% skeptical **The case for** - A few users appreciate that the reset is a free bonus and see it as OpenAI subsidizing compute for cheap plans. - Some note Pro/higher-tier plans aren't affected by the 5-hour limit and work fine. **The pushback** - Many Plus users say the 5-hour limit stops them from meaningfully using the weekly reset, calling it a bait-and-switch. - Some argue banked/delayed resets would be fairer than a fixed-time reset that not everyone can use. - Complaints that cheaper plans are being squeezed while OpenAI pushes users toward pricier tiers. - A subthread devolves into arguing over whether $20/month users have any right to complain given subsidized pricing. **By community** - x (heated): Replies swing between people excitedly planning to burn usage and a larger, more vocal group angry that the 5-hour limit undermines the reset, with side arguments about fairness and pricing. **Hottest debate:** Whether the reintroduced 5-hour rolling cap makes the weekly reset pointless, and whether Plus-tier users have grounds to complain given the subsidized price. **Open questions** - Will OpenAI remove or adjust the 5-hour limit for Plus users? - Could resets be banked/delayed so users can choose when to use them? **Highlights** > @thsottiaux Yeah kinda hard to do when the 5H Limit Bullshit only allows it to work for 10 mins and spend 15% actual usage before I have to wait 5 hours each time. Then the project resuming consumes 15% of the 5H rate. Literally ruined codex. > — [jackatlas942 on x · 4 points, 3 comments](https://x.com/jackatlas942/status/2094168452818710843) > @thsottiaux Do you guys really hate plus subs this much? Most won't even hit %50 of their limit because of 5hr. Why not a banked reset? You guys are literally punishing people who can't afford to pay monthly 100 or 200$. Clade is evil for what they're doing but at least they're openly doing > — [dorukisb on x · 6 points, 2 comments](https://x.com/dorukisb/status/2094151777679720919) > @thsottiaux It’s been no more than 10 minutes. 5h went from 96% to 0% on Ultra only using 2 sub agents and the task failed. Codex is useless for hard problem with the way 5h limits just completely cuck you. Even xHigh will tank your usage so you have to wait or risk a task failure. > — [ilostmy\_fish on x · 2 points, 3 comments](https://x.com/ilostmy_fish/status/2094162640885154227) > @thsottiaux Wouldn't it be better to give delayed resets so that people could choose when to do the reset? But in any case, thanks, since this is not necessarily Openai in front of people, but simply a gift for users > — [pparik\_\_ on x · 4 points](https://x.com/pparik__/status/2094150936352469180) > @GraemeVIP @OhioValleyEV @thsottiaux The 5 hour limit does nothing to lower monthly usage by the way…it’s just there to stabilize peak hours. Which is what i’d say if they didn’t already prove that inference is flawless even with the 5 hour limit completely removed. > — [blex1\_ on x](https://x.com/blex1_/status/2094176439293669534) **Source threads** - [x](https://x.com/thsottiaux/status/2094144275957350900) · 0 points · 846 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#openai](https://daily.dev/tags/openai), [#chatgpt](https://daily.dev/tags/chatgpt), [#openai-codex](https://daily.dev/tags/openai-codex) [View this post on daily.dev](https://daily.dev/posts/openai-resets-codex-and-chatgpt-work-usage-limits-after-fixing-multiple-overconsumption-bugs-ftkpeycch) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"OpenAI resets Codex and ChatGPT Work usage limits after fixing multiple overconsumption bugs","url":"https://daily.dev/posts/openai-resets-codex-and-chatgpt-work-usage-limits-after-fixing-multiple-overconsumption-bugs-ftkpeycch","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/openai-resets-codex-and-chatgpt-work-usage-limits-after-fixing-multiple-overconsumption-bugs-ftkpeycch"},"datePublished":"2026-08-29T20:53:05.345Z","dateModified":"2026-09-13T19:53:09.936Z","description":"OpenAI reset usage limits for all paid Codex and ChatGPT Work users after fixing a series of bugs that were causing overconsumption of allowances. Root causes...","image":"https://pbs.twimg.com/media/HQ6vpUIWwAAYdLI.jpg","thumbnailUrl":"https://pbs.twimg.com/media/HQ6vpUIWwAAYdLI.jpg","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/openai-resets-codex-and-chatgpt-work-usage-limits-after-fixing-multiple-overconsumption-bugs-ftkpeycch","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"ai-agents,openai,chatgpt,openai-codex","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"OpenAI resets Codex and ChatGPT Work usage limits after fixing multiple overconsumption bugs"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/openai-resets-codex-and-chatgpt-work-usage-limits-after-fixing-multiple-overconsumption-bugs-ftkpeycch#faq","mainEntity":[{"@type":"Question","name":"Why was my OpenAI Codex weekly usage allowance getting used up so fast?","acceptedAnswer":{"@type":"Answer","text":"Several overconsumption bugs were draining Codex usage allowances faster than expected. Causes included compaction retaining stale images and re-triggering itself, memory workers stuck looping on Stop hooks (one thread checked 15,000 times), goals running past their intended stop condition or retrying broken tools (consuming 15-70% of a weekly allowance in one session), and Computer History repeatedly summarizing overlapping activity, sometimes using up to a fifth of the weekly allowance alone. daily.dev surfaces fixes like these so heavy Codex users can stop losing quota to background bugs."}},{"@type":"Question","name":"Did OpenAI increase Codex rate limits recently?","acceptedAnswer":{"@type":"Answer","text":"Yes, OpenAI quietly raised 5-hour rate limits by around 50% across all Codex plans without a formal announcement, alongside a reset of weekly usage limits for paid Codex and ChatGPT Work subscribers. Separately, bug fixes to compaction, memory workers, goals, automations, subagents, and MCP handling should make existing weekly allowances last 10% to 50% longer depending on usage patterns. track quiet limit changes like this on daily.dev before they affect your Codex workflow budget."}},{"@type":"Question","name":"What MCP bugs was OpenAI Codex hitting that wasted usage quota?","acceptedAnswer":{"@type":"Answer","text":"Two separate MCP issues were consuming extra usage: some tool results were being encoded twice, and tool instructions were getting cut off and then re-fetched, both adding unnecessary token overhead. These have been fixed as part of a broader round of changes that also disabled rolling task summaries, which were adding about 1% to token usage on ordinary turns. developers debugging MCP overhead in agent tools can follow fixes like this on daily.dev."}}]} ```