Day 28/ Banked 2/2
Reset credit activity
We shipped some good updates to dots today and the banked reset has been activated and should land in everyones accounts sometime soon! https://t.co/Y7Mnp6Cuu1
Check source post ↗QUOTA ORBIT
Public Codex reset announcements and completion updates, in one place.
Daily improvements and quota reset signals
RECENT RESET EVENTS
Sorted by public post time. Check each item against its source post.
We shipped some good updates to dots today and the banked reset has been activated and should land in everyones accounts sometime soon! https://t.co/Y7Mnp6Cuu1
Check source post ↗Thursday is feeling codexy to me. Perhaps also a good time for a banked reset.
Check source post ↗It’s been a while without resets. Maybe I should come back out of the basement
Check source post ↗Your dot will choose the best model for the task, drawing on different models for different parts of the work.
Check source post ↗Fellow resetters, heads up that we're working on expanding the family of frontier models that power dots, including GPT-6 Astra and GPT-6.1 Terra and some others in the future. Terra brings …
Check source post ↗WEB · MAC · CHROME · WECHAT
Read public updates on the web, check your quota on Mac, and get alerts through Chrome or WeChat.
No Codex login required. Enable page alerts or background push.
The Moonlit Archivist desktop pet reads on your desktop. Click to view quota and public updates.
To view personal quota, install Codex CLI and sign in first.
Apple silicon · macOS 13+ | Website trial
Download Mac betaChecks public updates while the browser runs. Does not read personal account usage.
Install Chrome extension ↗
Check announcements and estimated times; subscribe to the next alert.
After opening, subscribe inside the Mini Program.
This page loads a snapshot every 5 minutes while open. Source transcripts may lag. Failed checks retain older records and are not marked successful.
Public updates may lag or be missing. Historical announcements are not new opportunities; a source failure does not mean there are no new updates.
THE SIGNAL LOG
Recent public transcripts, ordered by post time. This is not a complete archive.
We shipped some good updates to dots today and the banked reset has been activated and should land in everyones accounts sometime soon!
Thursday is feeling codexy to me. Perhaps also a good time for a banked reset.
Day 26/ You can now easily switch between multiple accounts on mobile, and coming soon to desktop too. Next two days will be resets… banked… do with this what you may 👀.
And it's done. See you tomorrow for some good news.
A follow-up announced the reset complete at 2026-10-28 14:29 · Beijing time.
View completion announcement →Day 23/ Much requested iCloud Main & Calendar plugins. Just kidding, today is a reset. Still much requested though!
The operator confirmed the reset. This is our verification, not a confirmation post from Tibo. Operator verification time:2026-10-26 14:05 · Beijing time
View maintainer verification detailsDay 21/ Wonder what happens the remaining seven days. But today is a reset.
It is all propagated. Enjoy some mad codexing tomorrow. Fun week ahead too.
A follow-up announced the reset complete at 2026-10-25 14:06 · Beijing time.
View completion announcement →Day 20/ Rest and reset
The operator confirmed the reset. This is our verification, not a confirmation post from Tibo. Operator verification time:2026-10-24 07:53 · Beijing time
View maintainer verification detailsDay 18/ Decisions API is GA, OpenResponses joined the Linux Foundation, we shipped some performance improvements and Uber is going all-in on codex & work. But yes… that’s a reset!
Day 28/ Banked 2/2
Banked 1/2
It means a public post announced a completed reset, not that we checked your account. View your personal quota in Codex or the Mac app. Reset credit distributions and global resets are shown separately. Read the personal quota reset guide →
Receive public updates by email, browser alerts or the Chrome extension. Prefer WeChat? Choose “WeChat alerts”, scan to open Starshore Reset Helper, and subscribe to the next announcement or completion alert as needed. See the guide for setup and troubleshooting; alerts do not confirm that your personal quota has reset. Read the alert setup and troubleshooting guide →
The page refreshes every five minutes and public monitoring runs independently. Page alerts need an open tab. Once background push is connected, the page can close while the browser runs. Sleep, offline mode and system blocking affect delivery.
No. We show collected updates, not reset probabilities. Sources may lag or miss posts. Failed or stale records are not treated as current evidence.
Each click creates a random ID stored in this browser. The server stores the ID, receipt time and feature version to count and deduplicate wishes. No login or Codex account is needed. Device counts do not sync across devices. Clearing browser data removes local records and unsynced wishes. Keep the page open after reconnecting to finish syncing. Totals count clicks, not people or reset probabilities.
Daily improvements and quota reset signals
Observation: 2026-10-05 — 2026-11-01 · Pacific timeBased on the Day 1 post, using Pacific calendar dates; the 28-day range is calculated by this site.
Source last checked · 2026-11-21 19:01 · Beijing time
Third-party transcript. Check the source and scope; this does not represent your account status.
Public resets and personal quota guide
Day 28/ Banked 2/2
Banked 1/2
Day 26/ You can now easily switch between multiple accounts on mobile, and coming soon to desktop too. Next two days will be resets… banked… do with this what you may 👀.
https://t.co/iQxsqbuk0f
Day 25/
We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today.
We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage.
And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.
Day 24/ Text your dot just like anyone else. Makes it super easy to share/forward things, leave it voice notes or you can even go creative with "Hey Siri, text Iggy to <INSERT WILD REQUEST>" and sit back and relax. https://t.co/T4t4m1m6DV
The quoted ChatGPT announcement said the feature was rolling out as a preview for Pro users in the US at the time. ↗
And it's done. See you tomorrow for some good news. https://t.co/WhJle2cWRG
Day 23/ Much requested iCloud Main & Calendar plugins. Just kidding, today is a reset. Still much requested though! https://t.co/tHe09XkVXH
Later confirmed by an announcement · 2026-10-28 14:29 · Beijing time
Lands by midnight PST.
Expected deadline · 2026-10-28 16:00 · Beijing time
Check source post ↗Day 22/ Terra is back!
Our first model that is significantly better at writing, personality and nuanced understanding of requests.
Packs a punch across the board, very good at computer use, and gives 2X more usage than 6.1 Sol across API and subscriptions. https://t.co/1ilnCkAPuy
Operator confirmation: the quota reset is complete. This is a site verification, not a Tibo announcement. Verification time is not the actual reset time; check your own account quota.
Day 21/ Wonder what happens the remaining seven days. But today is a reset.
Later confirmed by the site · 2026-10-26 14:05 · Beijing time
It is all propagated. Enjoy some mad codexing tomorrow. Fun week ahead too. https://t.co/qOrzwSeIZZ https://t.co/xKaK95EAly
Day 20/ Rest and reset
Later confirmed by an announcement · 2026-10-25 14:06 · Beijing time
By midnight PST
Expected deadline · 2026-10-25 16:00 · Beijing time
Check source post ↗Operator confirmation: the quota reset is complete. This is a site verification, not a Tibo announcement. Verification time is not the actual reset time; check your own account quota.
On codex cli updates. We've added reusable prompt presets, inline model and permission settings, and enterprise MCP sign-in. We've also fixed failures when resuming long sessions and added Windows corporate-proxy authentication.
Surprisingly the CLI has grown 2X in usage since devday.
Day 19/ Small updates. Calls connect much faster for dots, changing reasoning in codex & work mid conversation does not invalidate cache anymore and a we've also updated the codex cli.
Day 18/ Decisions API is GA, OpenResponses joined the Linux Foundation, we shipped some performance improvements and Uber is going all-in on codex & work. But yes… that’s a reset!
This post also announces a shipped improvement
Later confirmed by the site · 2026-10-24 07:53 · Beijing time
Landing tomorrow before 10am PST together with a small ship.
Expected deadline · 2026-10-24 02:00 · Beijing time
Check source post ↗Operator confirmation: the quota reset is complete. This is a site verification, not a Tibo announcement. Verification time is not the actual reset time; check your own account quota.
Day 16/
You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache. https://t.co/0HYeB01KVh
There were reports of usage draining faster than anticipated for some users over the weekend. We've identified approximately 40,000 accounts that had an inconsistency on which usage limits where the actual usage that was applied did not correspond to their actual selected plan. We are reaching out individually to all these users and have corrected the issue. If this affected you, we'll add credits to your account. Sorry we got this wrong.
COOKED livestream: Codex capabilities and community creations
Day 14/
Small quality of life improvement. You can now edit previous messages within a thread in the desktop app. Long time requested, and took way too long to get that one out.
Also we just added slides support yesterday, try it out. Currently available in Pro, Business and Enterprise while we learn from your feedback.
We also significantly improved GPT-6 Pro for all pro users
https://t.co/XE28U4S359
Day 12/
We’ve made improvements to Codex & Work that increase the effective usage you get. We achieved this by reusing context across subagents, keeping context cached longer, and improved request routing that allows us to increase cache hits.
Day 11/
We've landed a series of changes and more compute to very significantly decrease the occurrence of the disruptive "Selected model is at capacity. Please try a different model". When it does happen, it should also eventually just continue by itself and not just block on it.
Let us know if you still see it out there in the wild and we'll take a look.
Day 9/
We've rolled out optimizations to how we store state on disk for the chatgpt & codex desktop app that should reduce the amount stored on disk by 60%. Small ship but we've heard enough feedback about power users running out of disk space.
Day 7/
We have increased default context length for GPT-6.1 Sol to 500k when used through Codex & Work, up from 272k or an ~ 80% increase.
We will go higher in the future, but it helps reduce occurrence of compactions and with tasks that require keeping a lot of context and nuance over periods of time. It was carefully tested and is the new sweet spot for most of our users. You can still override it if you want to be higher our lower, with maximum context length of GPT-6.1 Sol of 1M.
Your ChatGPT subscription is now also a Devin subscription https://t.co/kJE3sbq2wP
Dots got a pretty big upgrade https://t.co/j54EmJMwLu
Day 5 (dots edition)/
You can now create and text your dot entirely from the ChatGPT mobile app. Impressed so many created them via the desktop/web app previously. Time to scale! https://t.co/Im3fcNswPl
Day 5/
Composer predictions in the desktop app. Often leads to a double take with how on point they are. Included in the Pro plans without consuming usage. https://t.co/02dqoClrWn
Day 4/
We have improved steering to be instant, leading to the model now reacting much faster to adjustments you make, allowing you to course-correct direction in realtime and not have the model waste effort.
Also releasing GPT-6.1 Sol ultrafast. The two work very well together.
Day 3 (encore)/
We silently re-shipped codex cloud. It’s pretty good now https://t.co/Fau14sCke8
We're going beyond text and are releasing a new version of GPT-6 to all users in ChatGPT. Lots of model and infra improvements coming together here to scale it to 1.2B users! https://t.co/nDVVnTq3ti
Roundup of Day 2/
2.1/ Approve for me (auto-review) is now included and does not use usage. Can be between 2-10% of plan when used. Also better for you. 2.2/ Simplified API for builders. 2.3/ Meeting notes integrated. 2.4/ Decisions API live for builders. Will use in the app to improve the experience.
Day 2.4/
Decisions API is live. We will use this ourselves to improve the experience for everyone in many fun ways. Realtime general classifier does open some great possibilities. https://t.co/acVDfnvOvU
Day 2.3/
Never worry about remembering what you were saying with that colleague. Just talk your heart out and build up the context to load up into codex to get it all done. https://t.co/Nsyknop4O7
Day 2.2/
OK this one is smaller, but we removed some friction for when building on the API. Happy building. https://t.co/hfi2655wyW
Day 2.1/
We have made Auto-review free for all users signed in through a ChatGPT account. You can enable it in settings > permissions > auto-review. Auto-review improves upon the default sandbox setting that requires you to approve everything, which is prone to decision fatigue unless you spend a lot of time configuring specific rules.
It allows you to run long tasks while having a second agent review all actions taken by the primary agent. Its only goal is to prevent high-risk actions from being taken and to protect against unwanted actions that are not aligned with the original user intent. This Auto-review feature is now free and does not draw usage from your plan.
Day 1/
We have optimized the default speed to be ~50% faster across GPT-6 Astra and GPT-6.1 Sol through the subscription across all our products and partners using Sign in With ChatGPT (including OpenCode, Pi, Amp, Devin, ...).
No changes needed on your end and this should be felt within the next two hours.
Tap the book. Turn a little hope into starlight.
May your next session have all the quota it needs.
No constellations collected yet
Light a star every 10 wishes; complete a constellation at 30.
Connecting to wish records…
Just for fun. Wishes do not trigger or speed up actual resets.If this tool helps you, you can buy the creator a coffee. It is free to use, with or without your support.
Optional support · One-time payment · No auto-renewalTest mode: no real charges.