The issue occurred while using Codex. Recently, I often see the prompt "Selected model is at capacity. Please try a different model."
Open
Nobody has claimed this yet.
bug
CLI
connectivity
rate-limits
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.4k
- PR merge metrics
- PR metrics pending
Description
What version of Codex CLI is running?
0.154.0
What subscription do you have?
plus
Which model were you using?
gpt-6 astra
What platform is your computer?
masoc
What terminal emulator and version are you using (if applicable)?
iTerm2
Codex doctor report
Codex Doctor v0.154.0 · macos-aarch64
Notes
⚠ rollouts 146 active files · 1.17 GB on disk
⚠ threads 2 issues - rollout files are missing from the state DB; duplicate thread inventory entries found
─────────────────────────────────────────────────────────────
Environment
✓ system zh-Hans-CN
os Mac OS 26.6.2 [64-bit]
OS language zh-Hans-CN
LANG zh_CN.UTF-8
VISUAL not set
EDITOR not set
PAGER less
LESS -R
✓ disk sufficient free disk space (774.8 GiB)
warning threshold 5.0 GiB
failure threshold 1.0 GiB
CODEX_HOME available 774.8 GiB
worktree available 774.8 GiB
✓ security no supported endpoint protection detected
endpoint products none detected
✓ runtime npm (package /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin, bin /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin, resources /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-resources, path /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path)
version 0.154.0
install method npm (package /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin, bin /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin, resources /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-resources, path /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path)
commit unknown
executable ~/.nvm/versions/node/v22…-apple-darwin/bin/codex
✓ install consistent
context npm (package /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin, bin /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/bin, resources /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-resources, path /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path)
managed by npm: yes · bun: no · pnpm: no · Vite+: no · package root /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex
PATH entries (1) ~/.nvm/versions/node/v22.23.1/bin/codex
npm update target not inspected (PATH helpers are not executed)
✓ search file exists (bundled, /Users/royou/.nvm/versions/node/v22.23.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-darwin-arm64/vendor/aarch64-apple-darwin/codex-path/rg)
search command ~/.nvm/versions/node/v22…le-darwin/codex-path/rg
search provider bundled
search command readiness file exists
✓ git git executable found; execution not verified
selected git /usr/bin/git
repo detected false
PATH entries (1) /usr/bin/git
git execution not inspected (PATH helpers are not executed)
✓ terminal iTerm2 3.6.11
terminal iTerm2
TERM_PROGRAM iTerm.app
terminal version 3.6.11
stdin is terminal true
stdout is terminal true
stderr is terminal true
terminal size 272x63
color output enabled
COLORTERM truecolor
COLORFGBG 0;15
TERMINFO_DIRS entry /Applications/iTerm.app/…ents/Resources/terminfo (dir)
TERMINFO_DIRS entry /usr/share/terminfo (dir)
effective locale zh_CN.UTF-8
✓ title default · project royou
title source default
title items activity, project-name
activity item true
project source cwd
project value royou
✓ state databases healthy
CODEX_HOME ~/.codex (dir)
log dir ~/.codex/log (missing)
sqlite home ~/.codex (dir)
state DB ~/.codex/state_5.sqlite (file) · integrity ok
log DB ~/.codex/logs_2.sqlite (file) · integrity ok
goals DB ~/.codex/goals_1.sqlite (file) · integrity ok
memories DB ~/.codex/memories_1.sqlite (file) · integrity ok
active rollouts 146 files · 1.17 GB (avg 8.20 MB)
archived rollouts 12 files · 37.48 MB (avg 3.12 MB)
queue DB ~/.codex/queue_1.sqlite (file)
queue DB integrity ok
thread history DB ~/.codex/thread_history_1.sqlite (file)
thread history DB integrity ok
⚠ threads 2 issues - rollout files are missing from the state DB; duplicate thread inventory entries found
default model provider openai
rollout DB active files 146
rollout DB archived files 12
rollout DB scan errors 0
rollout DB malformed file names 0
rollout DB scan cap reached false
rollout DB rows 136
rollout DB active rows 124
rollout DB archived rows 12
rollout DB missing active rows 22
rollout DB missing archived rows 0
rollout DB stale rows 0
rollout DB archive mismatches 0
rollout DB duplicate rollout thread ids 7
rollout DB duplicate DB paths 0
rollout DB model providers openai=136
rollout DB sources subagent:other=61, vscode=61, subagent:thread_spawn=12, cli=2
rollout DB missing active sample ~/.codex/sessions/2026/0…a2f2-8f8891e4c539.jsonl
rollout DB missing active sample ~/.codex/sessions/2026/0…8493-50c4da11b47d.jsonl
rollout DB missing active sample ~/.codex/sessions/2026/0…90bd-e9f89e9b3a46.jsonl
rollout DB missing active sample ~/.codex/sessions/2026/0…a125-e01a8f8580cf.jsonl
rollout DB missing active sample ~/.codex/sessions/2026/0…8da0-118c65827755.jsonl
rollout DB duplicate rollout thread id sample 01a047a8-fb7e-7d23-a2f2-8f8891e4c539
rollout DB duplicate rollout thread id sample 01a05bb1-5fb6-7640-a671-0428afa5094e
rollout DB duplicate rollout thread id sample 01a06007-5863-7353-80f1-8480dd22ec51
rollout DB duplicate rollout thread id sample 01a07ade-f92c-7943-b137-26c7c9396af6
rollout DB duplicate rollout thread id sample 01a0a4f1-74a2-77e3-a125-e01a8f8580cf
→ Attach the doctor report to a bug report so support can inspect samples.
Configuration
✓ config loaded
model gpt-5.6-terra · openai
cwd ~
config.toml ~/.codex/config.toml
config.toml parse ok
MCP servers 2
feature flags 48 enabled · 0 overridden (full list with --all)
configuration scope invocation config, including cloud-managed policy
active thread overrides not inspected
configuration load ms 4
✓ auth auth is configured
auth storage mode File
auth file ~/.codex/auth.json
stored auth mode chatgpt
stored API key false
stored ChatGPT tokens true
stored agent identity false
✓ mcp 2 server (2 stdio) · 1 disabled
configured servers 2
disabled servers 1
stdio servers 2
✓ sandbox restricted fs + restricted network · approval OnRequest
approval policy OnRequest
filesystem sandbox restricted
denied-read rules 0
denied-read glob rules 0
glob scan max depth unbounded
managed filesystem source none
network sandbox restricted
linux helper none
execve wrapper helper ~/.codex/tmp/arg0/codex-…TX/codex-execve-wrapper
Desktop App
✓ desktop the desktop application is installed
version 26.911.61220
running true
log directory $HOME/Library/Logs/com.openai.codex
✓ desktop the desktop app-server initialized successfully
✓ desktop the desktop application passed available macos security assessments
gatekeeper accepted
Updates
✓ updates update configuration is locally consistent
startup update check true
update action npm install -g @openai/codex
version cache ~/.codex/version.json
cached latest version 0.154.0
last checked at 2026-09-17 07:29 UTC
npm update target not inspected (PATH helpers are not executed)
latest version 0.154.0
latest version status current version is not older
Connectivity
✓ network no proxy env vars
proxy env vars none
system proxy manual
respect system proxy disabled
managed proxy not configured
✓ websocket connected (HTTP 101 Switching Protocols) · 15s timeout
model provider openai
provider name OpenAI
wire API responses
supports websockets true
proxy env vars none
connect timeout 15000 ms
auth mode chatgpt
endpoint wss://chatgpt.com/backend-api/<redacted>
DNS 1 IPv4, 0 IPv6, first IPv4
handshake result HTTP 101 Switching Protocols
reasoning header false
server model present false
✓ reachability active provider endpoints are reachable over HTTP
reachability mode ChatGPT auth
ChatGPT inference URL https://chatgpt.com/backend-api/<redacted> reachable (HTTP 405)
desktop assets CDN https://chatgpt.com/backend-api/<redacted> reachable (HTTP 200)
Background Server
○ app-server not running (ephemeral mode)
daemon state dir ~/.codex/app-server-daemon
settings ~/.codex/app-server-daemon/settings.json (missing)
pid file ~/.codex/app-server-daemon/app-server.pid (missing)
update-loop pid file ~/.codex/app-server-daem…/app-server-updater.pid (missing)
control socket ~/.codex/app-server-cont…app-server-control.sock
status not running
mode ephemeral
─────────────────────────────────────────────────────────────
21 ok · 1 idle · 2 notes · 1 warn · 0 fail degraded
--summary compact output --all expand truncated lists
--json redacted report
What issue are you seeing?
Falling back from WebSockets to HTTPS transport. stream disconnected before completion: An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the
request ID 55190452-bb84-447c-9511-28c1c664bd99 in your message.
What steps can reproduce the bug?
Uploaded thread: 01a0ae4c-68f0-7033-bb96-02bccfe7269c
What is the expected behavior?
The issue occurred while using Codex. Recently, I often see the prompt "Selected model is at capacity. Please try a different model."
Additional information
The issue occurred while using Codex. Recently, I often see the prompt "Selected model is at capacity. Please try a different model."
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.
Research direction
Start by reproducing the report with Codex CLI 0.154.0, the gpt-6 astra model, and the supplied WebSocket-to-HTTPS fallback message. Inspect the transport and stream-disconnect handling, using the Codex doctor report to compare connectivity and configuration. Done means the capacity or disconnect behavior is explained and corrected, with a regression test for the observed failure.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- cli, networking
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100