Repository navigation
selected model is at capacity error is occurring only on specific accounts. #45600
Description
What version of Codex CLI is running?
0.154.0
What subscription do you have?
pro 20x
Which model were you using?
gpt-6-astra
What platform is your computer?
windows11
What terminal emulator and version are you using (if applicable)?
windows terminal(powershell)
Codex doctor report
{
"schemaVersion": 1,
"generatedAt": "1789445393s since unix epoch",
"overallStatus": "warning",
"codexVersion": "0.154.0",
"checks": {
"app_server.status": {
"id": "app_server.status",
"category": "app-server",
"status": "ok",
"summary": "background server is not running",
"details": {
"control socket": "C:\\Users\\js\\.codex\\app-server-control\\app-server-control.sock",
"daemon state dir": "C:\\Users\\js\\.codex\\app-server-daemon",
"mode": "ephemeral",
"pid file": "C:\\Users\\js\\.codex\\app-server-daemon\\app-server.pid (missing)",
"settings": "C:\\Users\\js\\.codex\\app-server-daemon\\settings.json (missing)",
"status": "not running",
"update-loop pid file": "C:\\Users\\js\\.codex\\app-server-daemon\\app-server-updater.pid (missing)"
},
"remediation": null,
"durationMs": 0
},
"auth.credentials": {
"id": "auth.credentials",
"category": "auth",
"status": "ok",
"summary": "auth is configured",
"details": {
"auth file": "C:\\Users\\js\\.codex\\auth.json",
"auth storage mode": "File",
"stored API key": "false",
"stored ChatGPT tokens": "true",
"stored agent identity": "false",
"stored auth mode": "chatgpt"
},
"remediation": null,
"durationMs": 0
},
"config.load": {
"id": "config.load",
"category": "config",
"status": "ok",
"summary": "config loaded",
"details": {
"CODEX_HOME": "C:\\Users\\js\\.codex",
"active thread overrides": "not inspected",
"config.toml": "C:\\Users\\js\\.codex\\config.toml",
"config.toml parse": "ok",
"configuration load ms": "4",
"configuration scope": "invocation config, including cloud-managed policy",
"cwd": "C:\\Users\\js",
"enabled feature flags": "<redacted>",
"feature flag overrides": "prevent_idle_sleep=true",
"feature flags enabled": "50",
"log dir": "C:\\Users\\js\\.codex\\log",
"mcp servers": "4",
"model": "gpt-6-astra",
"model provider": "openai",
"sqlite home": "C:\\Users\\js\\.codex"
},
"remediation": null,
"durationMs": 0
},
"desktop.app.version": {
"id": "desktop.app.version",
"category": "desktop",
"status": "ok",
"summary": "the desktop application is installed",
"details": {
"log directory": "$HOME\\AppData\\Local\\Codex/Logs",
"running": "false",
"version": "26.908.4834.0"
},
"remediation": null,
"durationMs": 0
},
"desktop.app_server.handshake": {
"id": "desktop.app_server.handshake",
"category": "desktop",
"status": "ok",
"summary": "the desktop application is not running",
"details": {},
"remediation": null,
"durationMs": 0
},
"desktop.security.enforcement": {
"id": "desktop.security.enforcement",
"category": "desktop",
"status": "ok",
"summary": "no locally visible recent Codex security enforcement was found",
"details": {},
"remediation": null,
"durationMs": 0
},
"git.environment": {
"id": "git.environment",
"category": "git",
"status": "ok",
"summary": "git executable found; execution not verified",
"details": {
"PATH git #1": "C:\\Program Files\\Git\\cmd\\git.exe",
"PATH git entries": "1",
"git execution": "not inspected (PATH helpers are not executed)",
"repo detected": "false",
"selected git": "C:\\Program Files\\Git\\cmd\\git.exe"
},
"remediation": null,
"durationMs": 13
},
"git.worktree.dev_drive": {
"id": "git.worktree.dev_drive",
"category": "git",
"status": "ok",
"summary": "no Git worktree is active",
"details": {},
"remediation": null,
"durationMs": 0
},
"installation": {
"id": "installation",
"category": "install",
"status": "ok",
"summary": "installation looks consistent",
"details": {
"PATH codex #1": "C:\\Users\\js\\AppData\\Local\\Programs\\OpenAI\\Codex\\bin\\codex.exe",
"current executable": "C:\\Users\\js\\AppData\\Local\\Programs\\OpenAI\\Codex\\bin\\codex.exe",
"install context": "standalone (windows, package C:\\Users\\js\\.codex\\packages\\standalone\\releases\\0.154.0-x86_64-pc-windows-msvc, bin C:\\Users\\js\\.codex\\packages\\standalone\\releases\\0.154.0-x86_64-pc-windows-msvc\\bin, resources C:\\Users\\js\\.codex\\packages\\standalone\\releases\\0.154.0-x86_64-pc-windows-msvc\\codex-resources, path C:\\Users\\js\\.codex\\packages\\standalone\\releases\\0.154.0-x86_64-pc-windows-msvc\\codex-path)",
"managed by Vite+": "false",
"managed by bun": "false",
"managed by npm": "false",
"managed by pnpm": "false",
"managed package root": "not set"
},
"remediation": null,
"durationMs": 10
},
"mcp.config": {
"id": "mcp.config",
"category": "mcp",
"status": "ok",
"summary": "MCP configuration is locally consistent",
"details": {
"configured servers": "4",
"disabled servers": "0",
"stdio servers": "3",
"streamable_http servers": "1"
},
"remediation": null,
"durationMs": 129
},
"network.env": {
"id": "network.env",
"category": "network",
"status": "ok",
"summary": "network-related environment looks readable",
"details": {
"managed proxy": "not configured",
"proxy env vars": "none",
"respect system proxy": "disabled"
},
"remediation": null,
"durationMs": 0
},
"network.provider_reachability": {
"id": "network.provider_reachability",
"category": "reachability",
"status": "ok",
"summary": "active provider endpoints are reachable over HTTP",
"details": {
"ChatGPT inference URL": "https://chatgpt.com/backend-api/<redacted> reachable (HTTP 405)",
"desktop assets CDN": "https://persistent.oaistatic.com/codex-app-prod/<redacted> reachable (HTTP 200)",
"reachability mode": "ChatGPT auth"
},
"remediation": null,
"durationMs": 407
},
"network.websocket_reachability": {
"id": "network.websocket_reachability",
"category": "websocket",
"status": "ok",
"summary": "Responses WebSocket handshake succeeded",
"details": {
"DNS": "2 IPv4, 0 IPv6, first IPv4",
"auth mode": "chatgpt",
"connect timeout": "15000 ms",
"endpoint": "wss://chatgpt.com/backend-api/<redacted>",
"handshake result": "HTTP 101 Switching Protocols",
"model provider": "openai",
"provider name": "OpenAI",
"proxy env vars": "none",
"reasoning header": "false",
"server model present": "false",
"supports websockets": "true",
"wire API": "responses"
},
"remediation": null,
"durationMs": 631
},
"runtime.provenance": {
"id": "runtime.provenance",
"category": "runtime",
"status": "ok",
"summary": "running standalone on windows-x86_64",
"details": {
"commit": "unknown",
"current executable": "C:\\Users\\js\\AppData\\Local\\Programs\\OpenAI\\Codex\\bin\\codex.exe",
"install method": "standalone (windows, package C:\\Users\\js\\.codex\\packages\\standalone\\releases\\0.154.0-x86_64-pc-windows-msvc, bin C:\\Users\\js\\.codex\\packages\\standalone\\releases\\0.154.0-x86_64-pc-windows-msvc\\bin, resources C:\\Users\\js\\.codex\\packages\\standalone\\releases\\0.154.0-x86_64-pc-windows-msvc\\codex-resources, path C:\\Users\\js\\.codex\\packages\\standalone\\releases\\0.154.0-x86_64-pc-windows-msvc\\codex-path)",
"platform": "windows-x86_64",
"version": "0.154.0"
},
"remediation": null,
"durationMs": 0
},
"runtime.search": {
"id": "runtime.search",
"category": "search",
"status": "ok",
"summary": "search command found (bundled); execution not verified",
"details": {
"search command": "C:\\Users\\js\\.codex\\packages\\standalone\\releases\\0.154.0-x86_64-pc-windows-msvc\\codex-path\\rg.exe",
"search command readiness": "file exists",
"search provider": "bundled"
},
"remediation": null,
"durationMs": 0
},
"sandbox.helpers": {
"id": "sandbox.helpers",
"category": "sandbox",
"status": "warning",
"summary": "elevated Windows sandbox provisioning is incomplete or outdated",
"details": {
"approval policy": "Never",
"codex-linux-sandbox helper": "none",
"denied-read glob rules": "0",
"denied-read restrictions": "false",
"denied-read rules": "0",
"execve wrapper helper": "none",
"filesystem sandbox": "unrestricted",
"glob scan max depth": "unbounded",
"managed filesystem source": "none",
"network sandbox": "enabled",
"sandbox backend": "elevated",
"sandbox provisioning": "incomplete"
},
"issues": [
{
"severity": "warning",
"cause": "elevated Windows sandbox provisioning is incomplete or outdated",
"measured": null,
"expected": null,
"remedy": "run codex sandbox setup --elevated --user <end-user> --codex-home <authoritative-home> from an elevated shell",
"fields": [
"sandbox provisioning"
]
}
],
"remediation": "run codex sandbox setup --elevated --user <end-user> --codex-home <authoritative-home> from an elevated shell",
"durationMs": 0
},
"security.endpoint": {
"id": "security.endpoint",
"category": "security",
"status": "warning",
"summary": "endpoint protection detected; Codex exclusions are unverified",
"details": {
"Codex exclusions": "not verified",
"endpoint products": "Microsoft Defender",
"exclusion targets": "signed Codex app; codex.exe; codex-windows-sandbox-setup.exe; codex-command-runner.exe; codex-code-mode-host.exe"
},
"issues": [
{
"severity": "warning",
"cause": "Microsoft Defender can interfere with Codex. Verify Codex exclusions.",
"measured": "not verified",
"expected": "Codex application and helper exclusions",
"remedy": "Microsoft Defender: Add a certificate or executable-path exclusion for Codex and its helpers. If Attack Surface Reduction blocks Codex, add a rule exclusion. If Controlled Folder Access blocks Codex, allow the app.",
"fields": [
"Codex exclusions"
]
}
],
"remediation": "ask your security administrator to verify Codex exclusions and required helper allowances",
"durationMs": 14
},
"state.paths": {
"id": "state.paths",
"category": "state",
"status": "ok",
"summary": "state paths and databases are inspectable",
"details": {
"CODEX_HOME": "C:\\Users\\js\\.codex (dir)",
"active rollout files": "5 files, 1062575 total bytes, 212515 average bytes",
"archived rollout files": "0 files, 0 total bytes, 0 average bytes",
"goals DB": "C:\\Users\\js\\.codex\\goals_1.sqlite (file)",
"goals DB integrity": "ok",
"log DB": "C:\\Users\\js\\.codex\\logs_2.sqlite (file)",
"log DB integrity": "ok",
"log dir": "C:\\Users\\js\\.codex\\log (missing)",
"memories DB": "C:\\Users\\js\\.codex\\memories_1.sqlite (file)",
"memories DB integrity": "ok",
"queue DB": "C:\\Users\\js\\.codex\\queue_1.sqlite (file)",
"queue DB integrity": "ok",
"sqlite home": "C:\\Users\\js\\.codex (dir)",
"standalone release cache": "1 entries in C:\\Users\\js\\.codex\\packages\\standalone\\releases",
"state DB": "C:\\Users\\js\\.codex\\state_5.sqlite (file)",
"state DB integrity": "ok",
"thread history DB": "C:\\Users\\js\\.codex\\thread_history_1.sqlite (file)",
"thread history DB integrity": "ok"
},
"remediation": null,
"durationMs": 731
},
"state.rollout_db_parity": {
"id": "state.rollout_db_parity",
"category": "threads",
"status": "warning",
"summary": "rollout files and state DB thread inventory differ",
"details": {
"default model provider": "openai",
"rollout DB active files": "5",
"rollout DB active rows": "169",
"rollout DB archive mismatches": "0",
"rollout DB archived files": "0",
"rollout DB archived rows": "0",
"rollout DB duplicate DB paths": "0",
"rollout DB duplicate rollout thread ids": "0",
"rollout DB malformed file names": "0",
"rollout DB missing active rows": "0",
"rollout DB missing archived rows": "0",
"rollout DB model providers": "openai=139, cliproxy=30",
"rollout DB rows": "169",
"rollout DB scan cap reached": "false",
"rollout DB scan errors": "0",
"rollout DB sources": "cli=127, exec=20, subagent:thread_spawn=18, vscode=4",
"rollout DB stale row sample": [
"C:\\Users\\js\\.codex\\sessions\\2026\\09\\10\\rollout-2026-09-10T17-25-34-01a08a6c-17a6-7470-a94e-1dedb600c434.jsonl",
"C:\\Users\\js\\.codex\\sessions\\2026\\09\\10\\rollout-2026-09-10T17-27-30-01a08a6d-da6b-79f3-8c46-2b05e791fa95.jsonl",
"C:\\Users\\js\\.codex\\sessions\\2026\\09\\10\\rollout-2026-09-10T17-30-48-01a08a70-e011-7e80-b374-666ca6673020.jsonl",
"C:\\Users\\js\\.codex\\sessions\\2026\\09\\10\\rollout-2026-09-10T17-35-30-01a08a75-3018-7ba3-9ade-368f1c3cc9bf.jsonl",
"C:\\Users\\js\\.codex\\sessions\\2026\\09\\10\\rollout-2026-09-10T17-36-20-01a08a75-f2d8-7f20-af96-340bc080c10e.jsonl"
],
"rollout DB stale rows": "164"
},
"issues": [
{
"severity": "warning",
"cause": "state DB rows point at missing or unusable rollout files",
"measured": "164 stale rows",
"expected": "every state DB rollout path is a file on disk",
"remedy": null,
"fields": []
}
],
"remediation": null,
"durationMs": 14
},
"system.disk": {
"id": "system.disk",
"category": "disk",
"status": "ok",
"summary": "sufficient free disk space (177.0 GiB)",
"details": {
"CODEX_HOME available": "177.0 GiB",
"failure threshold": "1.0 GiB",
"warning threshold": "5.0 GiB",
"worktree available": "177.0 GiB"
},
"remediation": null,
"durationMs": 0
},
"system.environment": {
"id": "system.environment",
"category": "system",
"status": "ok",
"summary": "OS language ko-KR",
"details": {
"EDITOR": "set",
"VISUAL": "set",
"os": "Windows 10.0.26200 (Windows 11 Professional) [64-bit]",
"os language": "ko-KR",
"os type": "Windows",
"os version": "10.0.26200"
},
"remediation": null,
"durationMs": 0
},
"terminal.env": {
"id": "terminal.env",
"category": "terminal",
"status": "ok",
"summary": "terminal metadata was detected",
"details": {
"WT_SESSION": "present",
"color output": "enabled",
"console input code page": "65001",
"console output code page": "65001",
"stderr console mode": "0x00000007 (VT processing: true)",
"stderr is terminal": "true",
"stdin is terminal": "true",
"stdout console mode": "0x00000007 (VT processing: true)",
"stdout is terminal": "true",
"terminal": "Windows Terminal",
"terminal size": "88x89"
},
"remediation": null,
"durationMs": 0
},
"terminal.title": {
"id": "terminal.title",
"category": "title",
"status": "ok",
"summary": "terminal title default",
"details": {
"terminal title activity": "true",
"terminal title items": "activity, project-name",
"terminal title project source": "cwd",
"terminal title project value": "js",
"terminal title source": "default"
},
"remediation": null,
"durationMs": 0
},
"updates.status": {
"id": "updates.status",
"category": "updates",
"status": "ok",
"summary": "update configuration is locally consistent",
"details": {
"cached latest version": "0.154.0",
"check for update on startup": "true",
"desktop application": "OpenAI.Codex",
"desktop latest build": "26.908.9136.0",
"desktop update status": "available",
"last checked at": "2026-09-15T02:11:36.202092200Z",
"latest version": "0.154.0",
"latest version status": "current version is not older",
"update action": "standalone installer",
"version cache": "C:\\Users\\js\\.codex\\version.json"
},
"remediation": null,
"durationMs": 139
}
}
}What issue are you seeing?
Selected model is at capacity error is keep occurring. It doesn't matter actual openai's server overloaded. It is related my account error I guess. My friend's account is operating very smoothly. never stop while work is in progress. but my account is always fail with that error. please check this bug and fix it. I can't use 20% weekly usage even last week even gpt-6-astra model is released. It's so frustrating. please help me
What steps can reproduce the bug?
Uploaded thread: 01a0a337-6c5e-7312-bd57-e4764f0eedb0
What is the expected behavior?
Don't stop while work is in progress.
Additional information
I feel like my account is shadow banned. I hope not but I can't use my weekly usage above 20% It's so frustrating.
Activity
github-actions commentedon Sep 15, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
laoyang75 commentedon Sep 16, 2026
Same account-specific capacity error, not quota.
Thread ID: 01a0a90d-57e9-79a0-8f77-51e6714b81b5
Started: 2026-09-11
CLI: 0.154.0
Plan: ChatGPT Pro
Model: gpt-5.6-sol (reasoning medium)
/status on 2026-09-16 15:12 +08: 5h 100% left, weekly 80% left
Desktop existing threads sometimes work; CLI / new sessions fail for 6 days.
Hacksco commentedon Sep 16, 2026
I can reproduce this as well, with an additional cross-device data point that may help distinguish a local/client problem from an account/backend-routing problem.
Environment
0.154.026.908.9136.0Minimal reproduction on 2026-09-16
I created a fresh Codex Desktop task and submitted only:
你好The task used:
gpt-5.6-lunalowIt failed after about 6.5 seconds with:
{ "message": "Selected model is at capacity. Please try a different model.", "codex_error_info": "server_overloaded" }There was no assistant output before failure (
last_agent_message: null). An immediate retry failed again after about 8 seconds with the sameserver_overloadedclassification.I have reproduced the same capacity failure across all models available to me (including GPT-5.5, GPT-5.6, and GPT-6) and across all available reasoning-effort levels I tested. I also reproduce the problem in browser-based ChatGPT Work. In Work, I see both
所选模型已达容量上限。请尝试其他模型。("The selected model is at capacity. Please try another model.") and消息流中的错误("Error in message stream"). This makes the issue appear broader than a single model, reasoning setting, device, or local Codex client.Usage / rate-limit state
At the time of the failures, the rollout log reported:
So the account still had weekly usage available and Codex did not report a rate limit being reached.
codex doctorresultsAfter moving to a stable network route,
codex doctor --jsonreports:The WebSocket diagnostic specifically reports:
and the security check reports:
This makes a persistent local network/WebSocket failure less likely for the latest reproductions.
Cross-device reproduction
The most important additional observation is that I tested the same ChatGPT account on another computer, and the same
Selected model is at capacitybehavior occurs there as well.So far, the failure follows the account across computers rather than staying with one Codex installation or one machine.
I am not claiming this proves an account restriction or account-specific routing issue, but it may be useful for distinguishing model-wide serving capacity, ChatGPT-auth admission control, account/provisioning state, regional/serving-pool routing, and client/network problems.
Backend correlation IDs
Recent minimal reproduction:
If the Codex team can correlate these IDs with backend serving/admission-control telemetry, that may help identify why multiple models are returning
server_overloadedwhile quota remains available.The issue currently makes Codex effectively unusable for me despite having remaining Pro usage. Thanks for investigating.
Hacksco commentedon Sep 16, 2026
Follow-up with two additional data points: a CLI rollback matrix and an Android/Work reproduction.
1. Side-by-side Codex CLI rollback test
I downloaded official Windows x86_64 binaries from the
openai/codexGitHub releases and ran them side-by-side without replacing my installed0.154.0. The tests used the same ChatGPT account, same network/proxy route,gpt-5.6-sol,--ephemeral,--ignore-user-config, and the same minimal request.Small-sample results from the same test window:
0.151.00.152.00.153.00.154.0The failed runs returned the same error:
One
0.153.0run first reported astream disconnected/ reconnect event and then completed successfully.Because older versions also reproduce the capacity failure, this does not look like a problem exclusive to
0.154.0. The sample is too small to claim any meaningful success-rate difference between versions; the mixed successes/failures are also consistent with an intermittent backend/admission issue.Note: I intentionally ran the older release executables side-by-side rather than installing them globally, so they emitted a missing
codex-code-mode-host.exewarning. The requests still reachedturn.startedand then either completed normally or failed with the capacity error, so I am not treating that warning as the cause of the capacity failures.2. Android ChatGPT app / Work mode also reproduces it
I also tested the same ChatGPT account on an Android phone using the official ChatGPT app in Work mode. With a minimal prompt (
你好), Work also fails.The Android app shows the same UI errors I see in browser-based Work:
English meaning:
So the current reproduction now spans:
0.151.0through0.154.0)This still does not prove an account-specific backend issue, but it makes a single-device, single-installation, single-CLI-version, or single-client explanation increasingly unlikely. I hope these additional data points help with backend correlation / admission-routing investigation.
laoyang75 commentedon Sep 16, 2026
Same account-specific capacity error, not quota.
Thread ID: 01a0a90d-57e9-79a0-8f77-51e6714b81b5
Started: 2026-09-11
CLI: 0.154.0
Plan: ChatGPT Pro
Model: gpt-5.6-sol (reasoning medium)
/status on 2026-09-16 15:12 +08: 5h 100% left, weekly 80% left
Desktop existing threads sometimes work; CLI / new sessions fail for 6 days.
Hacksco commentedon Sep 16, 2026
Follow-up after isolating and substantially improving the network path. This seems useful because the Codex failure still reproduces even after the transport diagnostics became clean.
Network path cleanup / A-B result
I changed only the upstream/front relay while keeping the same final Los Angeles SOCKS5 egress, and I also disabled the TUN/virtual-adapter mode so that only the local system/mixed proxy (
127.0.0.1:7892) remains in use.The new front relay is materially healthier than the previous one:
codex doctor --jsonnow reports:network.websocket_reachability: okResponses WebSocket handshake succeededHTTP 101 Switching Protocolsnetwork.provider_reachability: okpersistent.oaistatic.comreachable (HTTP 200)The previous relay had measurable packet loss and intermittent WebSocket/TLS failures, so changing it clearly improved the network layer.
Real Codex turn still fails
Despite the clean diagnostics above, a fresh minimal
gpt-5.6-solrequest still behaved as follows:stream disconnected before completionFinal request ID from this reproduction:
This is especially notable because the failure survives the WebSocket -> HTTPS fallback, while
codex doctorreports both WebSocket and provider reachability as healthy.Other models on the same cleaned-up network path
Immediately afterwards I ran the same minimal test against two other models:
and:
So after removing the previously measurable network instability, the account still reproduces either server-side capacity errors or stream-processing failures across models.
At this point the network path is much less likely to explain the core issue by itself. Combined with my earlier cross-device, browser Work, Android Work, and CLI-version reproductions, I hope this helps narrow the investigation toward backend admission / account provisioning / serving-route state rather than a single client or transport path.