{"version":"pulse-v1","generatedAt":"2026-09-25T00:47:35.581Z","source":{"repo":"openai/codex","label":"rate-limits","description":"Public GitHub issues in openai/codex: everything labeled \"rate-limits\", plus issues whose titles clearly mention usage, quota, limits or resets."},"windows":{"h24":{"start":"2026-09-24T00:47:35.581Z","end":"2026-09-25T00:47:35.581Z"},"d7":{"start":"2026-09-18T00:47:35.581Z","end":"2026-09-25T00:47:35.581Z"},"prev7":{"start":"2026-09-11T00:47:35.581Z","end":"2026-09-18T00:47:35.581Z"}},"totals":{"fetched":327,"relevant":305,"rejected":22,"unclassified":54,"h24":17,"d7":131,"prev7":174},"complete":true,"clusters":[{"id":"capacity","name":"“Model at capacity” errors","kind":"known","links":[{"href":"/rate-limits","label":"Rate limit and capacity errors"}],"counts":{"h24":2,"d7":38,"prev7":50},"delta":-12,"trend":"stable","change":"38 reports in the last 7 days, 50 the week before. Roughly steady.","evidence":"community-reported","samples":[{"number":47794,"title":"[Bug][macOS][Work] Deterministic reasoning regression across high-end models + repeated capacity errors; Chat mode remains correct","url":"https://github.com/openai/codex/issues/47794","createdAt":"2026-09-24T08:56:48.000Z","state":"open","clusterId":"capacity","provenance":"label","models":["Reasoning effort"]},{"number":47790,"title":"Selected model is at capacity. Please try a different model.","url":"https://github.com/openai/codex/issues/47790","createdAt":"2026-09-24T08:40:47.000Z","state":"open","clusterId":"capacity","provenance":"label","models":[]},{"number":47304,"title":"Repeated \"Selected model is at capacity\" / server_overloaded across models despite available Pro usage","url":"https://github.com/openai/codex/issues/47304","createdAt":"2026-09-22T15:06:42.000Z","state":"open","clusterId":"capacity","provenance":"keyword","models":[]},{"number":47238,"title":"[Bug] Pro $200 account always shows \"Selected model is at capacity\" despite 69% weekly limit remaining","url":"https://github.com/openai/codex/issues/47238","createdAt":"2026-09-22T09:47:49.000Z","state":"open","clusterId":"capacity","provenance":"label","models":[]}],"models":[{"name":"Astra","count":4},{"name":"Reasoning effort","count":3},{"name":"Sol","count":3},{"name":"Luna","count":3}],"distinctDays":10},{"id":"depletion","name":"Unexpected usage depletion","kind":"known","links":[{"href":"/usage-draining-fast","label":"Why Codex usage drains fast"}],"counts":{"h24":3,"d7":27,"prev7":32},"delta":-5,"trend":"stable","change":"27 reports in the last 7 days, 32 the week before. Roughly steady.","evidence":"community-reported","samples":[{"number":47880,"title":"Request for an investigation into Codex GPT-6 task quality and high usage, and for quota compensation","url":"https://github.com/openai/codex/issues/47880","createdAt":"2026-09-24T16:40:57.000Z","state":"open","clusterId":"depletion","provenance":"label","models":[]},{"number":47878,"title":"[CLI][Astra] Research loop consumes excessive quota and incorrectly re-applies an old pause instruction","url":"https://github.com/openai/codex/issues/47878","createdAt":"2026-09-24T16:36:20.000Z","state":"open","clusterId":"depletion","provenance":"label","models":["Astra"]},{"number":47823,"title":"many users commenting on excessive usage","url":"https://github.com/openai/codex/issues/47823","createdAt":"2026-09-24T11:52:45.000Z","state":"open","clusterId":"depletion","provenance":"label","models":[]},{"number":47637,"title":"98% of fresh 5-hour Codex usage consumed within minutes — possible metering issue","url":"https://github.com/openai/codex/issues/47637","createdAt":"2026-09-23T19:33:56.000Z","state":"open","clusterId":"depletion","provenance":"label","models":[]}],"models":[{"name":"Astra","count":11},{"name":"Sol","count":5},{"name":"Reasoning effort","count":4},{"name":"Luna","count":4}],"distinctDays":14},{"id":"usage-display","name":"Usage display & /status","kind":"known","links":[{"href":"/dashboard","label":"Where to check Codex usage"}],"counts":{"h24":6,"d7":16,"prev7":24},"delta":-8,"trend":"stable","change":"16 reports in the last 7 days, 24 the week before. Roughly steady.","evidence":"community-reported","samples":[{"number":47816,"title":"Codex App MacOS /status says Rate limit: Unavailable while Settings shows usage","url":"https://github.com/openai/codex/issues/47816","createdAt":"2026-09-24T11:09:59.000Z","state":"open","clusterId":"usage-display","provenance":"label","models":[]},{"number":47788,"title":"Codex / Work analytics shows incorrect 5-hour reset time based on local OS time","url":"https://github.com/openai/codex/issues/47788","createdAt":"2026-09-24T08:27:57.000Z","state":"open","clusterId":"usage-display","provenance":"label","models":[]},{"number":47781,"title":"Usage limits unavailable in VS Code Insiders extension while CLI works","url":"https://github.com/openai/codex/issues/47781","createdAt":"2026-09-24T08:03:03.000Z","state":"closed","clusterId":"usage-display","provenance":"label","models":[]},{"number":47768,"title":"Quota limit not visible","url":"https://github.com/openai/codex/issues/47768","createdAt":"2026-09-24T06:49:11.000Z","state":"open","clusterId":"usage-display","provenance":"label","models":[]}],"models":[{"name":"Spark","count":8}],"distinctDays":12},{"id":"plan-allowance","name":"Plan changes & allowance","kind":"known","links":[{"href":"/limits","label":"Codex limits by plan"},{"href":"/credits","label":"Codex credits"}],"counts":{"h24":2,"d7":9,"prev7":5},"delta":4,"trend":"rising","change":"9 reports in the last 7 days, up from 5 the week before (+80%).","evidence":"community-reported","samples":[{"number":47893,"title":"Upgraded to Pro hit limit after running one command!!!","url":"https://github.com/openai/codex/issues/47893","createdAt":"2026-09-24T17:33:50.000Z","state":"open","clusterId":"plan-allowance","provenance":"label","models":[]},{"number":47869,"title":"VS Code: Work locally selector does not open; subscription endpoints return 403","url":"https://github.com/openai/codex/issues/47869","createdAt":"2026-09-24T16:06:07.000Z","state":"open","clusterId":"plan-allowance","provenance":"label","models":[]},{"number":47586,"title":"[Bug] Free weekly quota carries over after upgrading to Plus, leaving paid Codex capacity at 0%","url":"https://github.com/openai/codex/issues/47586","createdAt":"2026-09-23T16:26:25.000Z","state":"open","clusterId":"plan-allowance","provenance":"label","models":[]},{"number":47516,"title":"Codex: silent downgrade to gpt-4o - selected model never actually served (3 models tested, 8/8 valid answers)","url":"https://github.com/openai/codex/issues/47516","createdAt":"2026-09-23T09:17:20.000Z","state":"open","clusterId":"plan-allowance","provenance":"label","models":[]}],"models":[],"distinctDays":10},{"id":"limit-policy","name":"Requests to change limits","kind":"known","links":[{"href":"/limits/5-hour","label":"The 5-hour limit"},{"href":"/limits/weekly","label":"The weekly limit"}],"counts":{"h24":2,"d7":7,"prev7":7},"delta":0,"trend":"stable","change":"7 reports in the last 7 days, 7 the week before. Roughly steady.","evidence":"community-reported","samples":[{"number":47928,"title":"Feature request: remove the 5-hour usage limit","url":"https://github.com/openai/codex/issues/47928","createdAt":"2026-09-24T19:54:42.000Z","state":"closed","clusterId":"limit-policy","provenance":"label","models":[]},{"number":47740,"title":"Add a setting to disable CLI usage-limit warnings","url":"https://github.com/openai/codex/issues/47740","createdAt":"2026-09-24T04:09:36.000Z","state":"open","clusterId":"limit-policy","provenance":"label","models":[]},{"number":47500,"title":"The \"5h limit\" should be canceled during the last 5 hours of the \"Weekly limit\" for Plus subscribers.","url":"https://github.com/openai/codex/issues/47500","createdAt":"2026-09-23T08:24:41.000Z","state":"open","clusterId":"limit-policy","provenance":"label","models":[]},{"number":47261,"title":"Allow continued Codex usage after the 5-hour limit by consuming weekly quota at an increased rate","url":"https://github.com/openai/codex/issues/47261","createdAt":"2026-09-22T11:23:20.000Z","state":"open","clusterId":"limit-policy","provenance":"label","models":[]}],"models":[{"name":"Sol","count":1}],"distinctDays":9},{"id":"limit-reached","name":"Hitting the limit","kind":"known","links":[{"href":"/rate-limits","label":"What happens when you hit the limit"},{"href":"/limits","label":"Codex limits by plan"}],"counts":{"h24":1,"d7":5,"prev7":8},"delta":-3,"trend":"stable","change":"5 reports in the last 7 days, 8 the week before. Roughly steady.","evidence":"community-reported","samples":[{"number":47728,"title":"app-server: turn ends with `error` then `turn/completed` when the account usage limit is reached, so drivers relaunch in a tight loop","url":"https://github.com/openai/codex/issues/47728","createdAt":"2026-09-24T02:56:18.000Z","state":"open","clusterId":"limit-reached","provenance":"label","models":[]},{"number":47503,"title":"Chat Bar (macOS) incorrectly blocked by “Codex/Work usage limit” while regular Chat works (Go plan)","url":"https://github.com/openai/codex/issues/47503","createdAt":"2026-09-23T08:31:51.000Z","state":"open","clusterId":"limit-reached","provenance":"label","models":[]},{"number":47356,"title":"Rate limit error on Pro","url":"https://github.com/openai/codex/issues/47356","createdAt":"2026-09-22T20:12:02.000Z","state":"open","clusterId":"limit-reached","provenance":"label","models":[]},{"number":47309,"title":"MultiAgentV2 usage hints can exceed the 10K model-visible item limit","url":"https://github.com/openai/codex/issues/47309","createdAt":"2026-09-22T15:29:45.000Z","state":"open","clusterId":"limit-reached","provenance":"keyword","models":[]}],"models":[{"name":"Luna","count":1}],"distinctDays":8},{"id":"token-accounting","name":"Token accounting & compaction","kind":"known","links":[{"href":"/what-counts-toward-codex-usage","label":"What counts toward Codex usage"}],"counts":{"h24":1,"d7":5,"prev7":0},"delta":5,"trend":"rising","change":"5 reports in the last 7 days, up from 0 the week before.","evidence":"community-reported","samples":[{"number":47825,"title":"Hosted search usage causes premature auto-compaction","url":"https://github.com/openai/codex/issues/47825","createdAt":"2026-09-24T12:16:31.000Z","state":"open","clusterId":"token-accounting","provenance":"label","models":[]},{"number":47003,"title":"Auto-compaction request usage is never added to total_token_usage in rollouts (not recorded at all in 0.147)","url":"https://github.com/openai/codex/issues/47003","createdAt":"2026-09-21T11:18:48.000Z","state":"open","clusterId":"token-accounting","provenance":"label","models":[]},{"number":46975,"title":"WebSocket startup prewarm reports ~9k uncached input tokens omitted from turn usage","url":"https://github.com/openai/codex/issues/46975","createdAt":"2026-09-21T08:55:44.000Z","state":"open","clusterId":"token-accounting","provenance":"label","models":[]},{"number":46948,"title":"[macOS Desktop 26.915.31945] Automatic thread_description used 267,264 input tokens, then failed with invalid_encrypted_content","url":"https://github.com/openai/codex/issues/46948","createdAt":"2026-09-21T06:13:34.000Z","state":"open","clusterId":"token-accounting","provenance":"label","models":[]}],"models":[],"distinctDays":3},{"id":"banked-resets","name":"Banked & instant resets","kind":"known","links":[{"href":"/banked-resets","label":"Banked resets explained"},{"href":"/instant-reset","label":"Instant resets"}],"counts":{"h24":0,"d7":5,"prev7":1},"delta":4,"trend":"rising","change":"5 reports in the last 7 days, up from 1 the week before.","evidence":"community-reported","samples":[{"number":47566,"title":"[Pro 20x][macOS][GPT-6 Astra Ultra] One ~8-hour task exhausted two usage-reset credits","url":"https://github.com/openai/codex/issues/47566","createdAt":"2026-09-23T15:04:58.000Z","state":"open","clusterId":"banked-resets","provenance":"label","models":["Astra","Reasoning effort"]},{"number":47251,"title":"You have a new rate limit reset available - only I don't","url":"https://github.com/openai/codex/issues/47251","createdAt":"2026-09-22T10:57:57.000Z","state":"open","clusterId":"banked-resets","provenance":"label","models":[]},{"number":47000,"title":"Problem with Spark and reset credits","url":"https://github.com/openai/codex/issues/47000","createdAt":"2026-09-21T11:03:31.000Z","state":"open","clusterId":"banked-resets","provenance":"label","models":["Spark"]},{"number":46907,"title":"Subject: Banked Codex reset UI Failure — request to verify ledger and expiry-time visibility","url":"https://github.com/openai/codex/issues/46907","createdAt":"2026-09-20T23:35:28.000Z","state":"open","clusterId":"banked-resets","provenance":"label","models":[]}],"models":[{"name":"Astra","count":2},{"name":"Reasoning effort","count":1},{"name":"Spark","count":1}],"distinctDays":5},{"id":"reset-timing","name":"Reset timing & windows","kind":"known","links":[{"href":"/reset","label":"When Codex limits reset"}],"counts":{"h24":0,"d7":3,"prev7":5},"delta":-2,"trend":"stable","change":"3 reports in the last 7 days, 5 the week before. Roughly steady.","evidence":"community-reported","samples":[{"number":47297,"title":"Show the calendar reset date alongside the relative countdown in Usage","url":"https://github.com/openai/codex/issues/47297","createdAt":"2026-09-22T14:04:12.000Z","state":"open","clusterId":"reset-timing","provenance":"label","models":[]},{"number":47156,"title":"Request to Reset Tokens Upon Subscription Renewal","url":"https://github.com/openai/codex/issues/47156","createdAt":"2026-09-22T02:15:42.000Z","state":"open","clusterId":"reset-timing","provenance":"label","models":[]},{"number":47061,"title":"5-Hour Usage Limit Exceeding Immediately After Reset","url":"https://github.com/openai/codex/issues/47061","createdAt":"2026-09-21T16:07:36.000Z","state":"open","clusterId":"reset-timing","provenance":"label","models":[]},{"number":45826,"title":"Codex weekly reset date incorrectly shifted from Sep 15 to Sep 19 after Pro upgrade","url":"https://github.com/openai/codex/issues/45826","createdAt":"2026-09-16T01:23:49.000Z","state":"closed","clusterId":"reset-timing","provenance":"label","models":[]}],"models":[],"distinctDays":5},{"id":"luna-reserve","name":"Luna Reserve","kind":"known","links":[{"href":"/luna-reserve","label":"How Luna Reserve works"}],"counts":{"h24":0,"d7":1,"prev7":3},"delta":-2,"trend":"low","change":"1 report this week, 3 the week before. Too few to call a trend.","evidence":"community-reported","samples":[{"number":46421,"title":"Unable to switch out of the exhausted Luna Reserve mode in an old resumed session","url":"https://github.com/openai/codex/issues/46421","createdAt":"2026-09-18T12:08:54.000Z","state":"open","clusterId":"luna-reserve","provenance":"label","models":["Luna"]},{"number":46227,"title":"Luna Reserve rollout is missing from What's New / changelog, so eligible Pro users discover it only after quota exhaustion","url":"https://github.com/openai/codex/issues/46227","createdAt":"2026-09-17T14:26:34.000Z","state":"open","clusterId":"luna-reserve","provenance":"label","models":["Luna"]},{"number":46181,"title":"Luna reserve not working in CLI or desktop app","url":"https://github.com/openai/codex/issues/46181","createdAt":"2026-09-17T10:09:54.000Z","state":"open","clusterId":"luna-reserve","provenance":"label","models":["Luna"]},{"number":45132,"title":"app-server clients cannot use Luna Reserve: supportsLunaReserve exists but has no accept/redeem action","url":"https://github.com/openai/codex/issues/45132","createdAt":"2026-09-12T23:30:39.000Z","state":"open","clusterId":"luna-reserve","provenance":"label","models":["Luna"]}],"models":[{"name":"Luna","count":4}],"distinctDays":3}],"emerging":[],"questions":[{"number":47928,"title":"Feature request: remove the 5-hour usage limit","url":"https://github.com/openai/codex/issues/47928","createdAt":"2026-09-24T19:54:42.000Z","state":"closed","clusterId":"limit-policy","provenance":"label","models":[]},{"number":47893,"title":"Upgraded to Pro hit limit after running one command!!!","url":"https://github.com/openai/codex/issues/47893","createdAt":"2026-09-24T17:33:50.000Z","state":"open","clusterId":"plan-allowance","provenance":"label","models":[]},{"number":47880,"title":"Request for an investigation into Codex GPT-6 task quality and high usage, and for quota compensation","url":"https://github.com/openai/codex/issues/47880","createdAt":"2026-09-24T16:40:57.000Z","state":"open","clusterId":"depletion","provenance":"label","models":[]},{"number":47878,"title":"[CLI][Astra] Research loop consumes excessive quota and incorrectly re-applies an old pause instruction","url":"https://github.com/openai/codex/issues/47878","createdAt":"2026-09-24T16:36:20.000Z","state":"open","clusterId":"depletion","provenance":"label","models":["Astra"]},{"number":47869,"title":"VS Code: Work locally selector does not open; subscription endpoints return 403","url":"https://github.com/openai/codex/issues/47869","createdAt":"2026-09-24T16:06:07.000Z","state":"open","clusterId":"plan-allowance","provenance":"label","models":[]},{"number":47825,"title":"Hosted search usage causes premature auto-compaction","url":"https://github.com/openai/codex/issues/47825","createdAt":"2026-09-24T12:16:31.000Z","state":"open","clusterId":"token-accounting","provenance":"label","models":[]},{"number":47823,"title":"many users commenting on excessive usage","url":"https://github.com/openai/codex/issues/47823","createdAt":"2026-09-24T11:52:45.000Z","state":"open","clusterId":"depletion","provenance":"label","models":[]},{"number":47816,"title":"Codex App MacOS /status says Rate limit: Unavailable while Settings shows usage","url":"https://github.com/openai/codex/issues/47816","createdAt":"2026-09-24T11:09:59.000Z","state":"open","clusterId":"usage-display","provenance":"label","models":[]},{"number":47794,"title":"[Bug][macOS][Work] Deterministic reasoning regression across high-end models + repeated capacity errors; Chat mode remains correct","url":"https://github.com/openai/codex/issues/47794","createdAt":"2026-09-24T08:56:48.000Z","state":"open","clusterId":"capacity","provenance":"label","models":["Reasoning effort"]},{"number":47790,"title":"Selected model is at capacity. Please try a different model.","url":"https://github.com/openai/codex/issues/47790","createdAt":"2026-09-24T08:40:47.000Z","state":"open","clusterId":"capacity","provenance":"label","models":[]},{"number":47788,"title":"Codex / Work analytics shows incorrect 5-hour reset time based on local OS time","url":"https://github.com/openai/codex/issues/47788","createdAt":"2026-09-24T08:27:57.000Z","state":"open","clusterId":"usage-display","provenance":"label","models":[]},{"number":47781,"title":"Usage limits unavailable in VS Code Insiders extension while CLI works","url":"https://github.com/openai/codex/issues/47781","createdAt":"2026-09-24T08:03:03.000Z","state":"closed","clusterId":"usage-display","provenance":"label","models":[]},{"number":47768,"title":"Quota limit not visible","url":"https://github.com/openai/codex/issues/47768","createdAt":"2026-09-24T06:49:11.000Z","state":"open","clusterId":"usage-display","provenance":"label","models":[]},{"number":47740,"title":"Add a setting to disable CLI usage-limit warnings","url":"https://github.com/openai/codex/issues/47740","createdAt":"2026-09-24T04:09:36.000Z","state":"open","clusterId":"limit-policy","provenance":"label","models":[]},{"number":47738,"title":"Windows app shows Codex reset timestamp +1 hour compared with web Usage","url":"https://github.com/openai/codex/issues/47738","createdAt":"2026-09-24T03:28:20.000Z","state":"open","clusterId":"usage-display","provenance":"label","models":[]},{"number":47734,"title":"VS Code Codex extension 26.917.62051: 5-hour and weekly usage indicators missing after update","url":"https://github.com/openai/codex/issues/47734","createdAt":"2026-09-24T03:17:21.000Z","state":"closed","clusterId":"usage-display","provenance":"label","models":[]},{"number":47728,"title":"app-server: turn ends with `error` then `turn/completed` when the account usage limit is reached, so drivers relaunch in a tight loop","url":"https://github.com/openai/codex/issues/47728","createdAt":"2026-09-24T02:56:18.000Z","state":"open","clusterId":"limit-reached","provenance":"label","models":[]},{"number":47667,"title":"Quota Limit Bars in VS Code Extension not visible since extension version 26.5917","url":"https://github.com/openai/codex/issues/47667","createdAt":"2026-09-23T21:22:49.000Z","state":"open","clusterId":"usage-display","provenance":"label","models":[]},{"number":47637,"title":"98% of fresh 5-hour Codex usage consumed within minutes — possible metering issue","url":"https://github.com/openai/codex/issues/47637","createdAt":"2026-09-23T19:33:56.000Z","state":"open","clusterId":"depletion","provenance":"label","models":[]},{"number":47615,"title":"Codex VS Code extension: `/status` shows `Rate limit: Unavailable` while CLI shows limits","url":"https://github.com/openai/codex/issues/47615","createdAt":"2026-09-23T18:35:14.000Z","state":"open","clusterId":"usage-display","provenance":"label","models":[]},{"number":47586,"title":"[Bug] Free weekly quota carries over after upgrading to Plus, leaving paid Codex capacity at 0%","url":"https://github.com/openai/codex/issues/47586","createdAt":"2026-09-23T16:26:25.000Z","state":"open","clusterId":"plan-allowance","provenance":"label","models":[]},{"number":47578,"title":"[IDE extension] Restore Usage remaining in Work locally menu and show remaining limits persistently","url":"https://github.com/openai/codex/issues/47578","createdAt":"2026-09-23T15:44:21.000Z","state":"closed","clusterId":"usage-display","provenance":"label","models":[]},{"number":47566,"title":"[Pro 20x][macOS][GPT-6 Astra Ultra] One ~8-hour task exhausted two usage-reset credits","url":"https://github.com/openai/codex/issues/47566","createdAt":"2026-09-23T15:04:58.000Z","state":"open","clusterId":"banked-resets","provenance":"label","models":["Astra","Reasoning effort"]},{"number":47516,"title":"Codex: silent downgrade to gpt-4o - selected model never actually served (3 models tested, 8/8 valid answers)","url":"https://github.com/openai/codex/issues/47516","createdAt":"2026-09-23T09:17:20.000Z","state":"open","clusterId":"plan-allowance","provenance":"label","models":[]},{"number":47514,"title":"Excessive Codex usage caused by repeated redundant execution/rework in long Unity session using GPT-6-Astra ultra","url":"https://github.com/openai/codex/issues/47514","createdAt":"2026-09-23T09:10:25.000Z","state":"closed","clusterId":"depletion","provenance":"label","models":["Astra","Reasoning effort"]},{"number":47503,"title":"Chat Bar (macOS) incorrectly blocked by “Codex/Work usage limit” while regular Chat works (Go plan)","url":"https://github.com/openai/codex/issues/47503","createdAt":"2026-09-23T08:31:51.000Z","state":"open","clusterId":"limit-reached","provenance":"label","models":[]},{"number":47500,"title":"The \"5h limit\" should be canceled during the last 5 hours of the \"Weekly limit\" for Plus subscribers.","url":"https://github.com/openai/codex/issues/47500","createdAt":"2026-09-23T08:24:41.000Z","state":"open","clusterId":"limit-policy","provenance":"label","models":[]},{"number":47486,"title":"[VS Code] Usage settings missing for ChatGPT Business workspace while available on Desktop","url":"https://github.com/openai/codex/issues/47486","createdAt":"2026-09-23T07:24:39.000Z","state":"open","clusterId":"usage-display","provenance":"label","models":[]},{"number":47442,"title":"Codex usage being used insanely fast on 20x pro plan","url":"https://github.com/openai/codex/issues/47442","createdAt":"2026-09-23T03:57:41.000Z","state":"open","clusterId":"depletion","provenance":"label","models":[]},{"number":47426,"title":"Idle-time tasks: queue deferrable work that runs when server capacity is spare, at no (or discounted) usage cost","url":"https://github.com/openai/codex/issues/47426","createdAt":"2026-09-23T01:48:06.000Z","state":"open","clusterId":"depletion","provenance":"label","models":[]},{"number":47356,"title":"Rate limit error on Pro","url":"https://github.com/openai/codex/issues/47356","createdAt":"2026-09-22T20:12:02.000Z","state":"open","clusterId":"limit-reached","provenance":"label","models":[]},{"number":47324,"title":"[Windows][ChatGPT Pro] Astra Low consumed ~90% of weekly Codex allowance in ~50 minutes","url":"https://github.com/openai/codex/issues/47324","createdAt":"2026-09-22T17:04:33.000Z","state":"open","clusterId":"depletion","provenance":"label","models":["Astra"]},{"number":47309,"title":"MultiAgentV2 usage hints can exceed the 10K model-visible item limit","url":"https://github.com/openai/codex/issues/47309","createdAt":"2026-09-22T15:29:45.000Z","state":"open","clusterId":"limit-reached","provenance":"keyword","models":[]},{"number":47305,"title":"You've reached your usage limit. Upgrade your plan or add credits to continue","url":"https://github.com/openai/codex/issues/47305","createdAt":"2026-09-22T15:15:13.000Z","state":"open","clusterId":"plan-allowance","provenance":"label","models":[]},{"number":47304,"title":"Repeated \"Selected model is at capacity\" / server_overloaded across models despite available Pro usage","url":"https://github.com/openai/codex/issues/47304","createdAt":"2026-09-22T15:06:42.000Z","state":"open","clusterId":"capacity","provenance":"keyword","models":[]},{"number":47298,"title":"Show Codex usage limits in credits/units, not only percentages","url":"https://github.com/openai/codex/issues/47298","createdAt":"2026-09-22T14:14:27.000Z","state":"open","clusterId":"usage-display","provenance":"label","models":[]},{"number":47297,"title":"Show the calendar reset date alongside the relative countdown in Usage","url":"https://github.com/openai/codex/issues/47297","createdAt":"2026-09-22T14:04:12.000Z","state":"open","clusterId":"reset-timing","provenance":"label","models":[]},{"number":47262,"title":"Bad Response - Re Account Credit Allowances","url":"https://github.com/openai/codex/issues/47262","createdAt":"2026-09-22T11:30:01.000Z","state":"open","clusterId":"plan-allowance","provenance":"label","models":[]},{"number":47261,"title":"Allow continued Codex usage after the 5-hour limit by consuming weekly quota at an increased rate","url":"https://github.com/openai/codex/issues/47261","createdAt":"2026-09-22T11:23:20.000Z","state":"open","clusterId":"limit-policy","provenance":"label","models":[]},{"number":47251,"title":"You have a new rate limit reset available - only I don't","url":"https://github.com/openai/codex/issues/47251","createdAt":"2026-09-22T10:57:57.000Z","state":"open","clusterId":"banked-resets","provenance":"label","models":[]}]}