Request too large for gpt-5.6-luna in organization org

What version of Codex CLI is running?

codex-cli 0.146.1

What subscription do you have?

?

Which model were you using?

gpt 5.6 luna

What platform is your computer?

cachyos

What terminal emulator and version are you using (if applicable)?

Konsole

Codex doctor report

~/_newmodel> codex doctor
Codex Doctor v0.146.1 · linux-x86_64

Notes
↑ updates      0.147.0 available (current 0.146.1)
─────────────────────────────────────────────────────────────

Environment
✓ system       tr-TR
os                       CachyOS Linux Rolling Release [64-bit]
OS language              tr-TR
LANG                     tr_TR.UTF-8
VISUAL                   not set
EDITOR                   not set
✓ runtime      other
version                  0.146.1
install method           other
commit                   unknown
executable               /usr/bin/codex
✓ install      consistent
context                  other
managed by               npm: no · bun: no · pnpm: no · package root —
PATH entries (2)         /usr/bin/codex
/bin/codex
✓ search       ripgrep 15.2.0 (system, rg)
search command           rg
search provider          system
search command readiness ripgrep 15.2.0
✓ git          git version 2.55.0
selected git             /usr/bin/git
version                  git version 2.55.0
exec path                /usr/lib/git-core
repo detected            false
PATH entries (2)         /usr/bin/git
/bin/git
✓ terminal     Konsole 260403
terminal                 Konsole
terminal version         260403
stdin is terminal        true
stdout is terminal       true
stderr is terminal       true
terminal size            204x83
color output             enabled
COLORTERM                truecolor
COLORFGBG                15;0
effective locale         tr_TR.UTF-8
WAYLAND_DISPLAY          present
DISPLAY                  present
✓ title        default · project _newmodel
title source             default
title items              activity, project-name
activity item            true
project source           cwd
project value            _newmodel
✓ state        databases healthy
CODEX_HOME               ~/.codex (dir)
log dir                  ~/.codex/log (dir)
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          11 files · 2.67 MB (avg 248.91 KB)
archived rollouts        0 files · 0 B (avg 0 B)
thread history DB        ~/.codex/thread_history_1.sqlite (missing)
thread history DB integrity skipped (missing)
✓ threads      rollout files and state DB thread inventory agree
default model provider   openai
rollout DB active files  11
rollout DB archived files 0
rollout DB scan errors   0
rollout DB malformed file names 0
rollout DB scan cap reached false
rollout DB rows          11
rollout DB active rows   11
rollout DB archived rows 0
rollout DB missing active rows 0
rollout DB missing archived rows 0
rollout DB stale rows    0
rollout DB archive mismatches 0
rollout DB duplicate rollout thread ids 0
rollout DB duplicate DB paths 0
rollout DB model providers openai=11
rollout DB sources       cli=11

Configuration
✓ config       loaded
model                    gpt-5.6-luna · openai
cwd                      ~/_newmodel
config.toml              ~/.codex/config.toml
config.toml parse        ok
MCP servers              0
feature flags            38 enabled · 0 overridden (full list with --all)
✓ auth         auth is configured
auth storage mode        File
auth file                ~/.codex/auth.json
auth env vars present    OPENAI_API_KEY
stored auth mode         api_key
stored API key           true
stored ChatGPT tokens    false
stored agent identity    false
✓ mcp          no MCP servers configured
✓ sandbox      restricted fs + restricted network · approval OnRequest
approval policy          OnRequest
filesystem sandbox       restricted
network sandbox          restricted
linux helper             ~/.codex/tmp/arg0/codex-…ICR/codex-linux-sandbox
execve wrapper helper    ~/.codex/tmp/arg0/codex-…CR/codex-execve-wrapper

Updates
✓ updates      update configuration is locally consistent
startup update check     true
update action            manual or unknown
version cache            ~/.codex/version.json
cached latest version    0.147.0
last checked at          2026-08-12 19:15 UTC
latest version           0.147.0
latest version status    newer version is available

Connectivity
✓ network      no proxy env vars
proxy env vars           none
✓ 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                api_key
endpoint                 wss://api.openai.com/v1/<redacted>
DNS                      2 IPv4, 0 IPv6, first IPv4
handshake result         HTTP 101 Switching Protocols
reasoning header         false
models etag present      false
server model present     false
✓ reachability active provider endpoints are reachable over HTTP
reachability mode        API key auth
openai API base URL      https://api.openai.com/v1 reachable (HTTP 404)
openai API route probe   https://api.openai.com/v1/<redacted> route exists (HTTP 401)

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

─────────────────────────────────────────────────────────────
17 ok · 1 idle · 1 notes · 0 warn · 0 fail ok

--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: Request too large for gpt-5.6-luna in organization org-b4g4X7AHZEEhfU5LlCT6H4N4 on tokens per min (TPM): Limit 200000, Requested 208334. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.

■ stream disconnected before completion: Request too large for gpt-5.6-luna in organization org-b4g4X7AHZEEhfU5LlCT6H4N4 on tokens per min (TPM): Limit 200000, Requested 208334. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.

› İŞİ DURDURMADIYSAN NE YAPIYORDUN ? BEN DIŞARIYA ÇIKMIŞTIM. NE KADAR SÜREDİR İŞ YAPMADAN BEKLEDİN ?

› BEN SANA DURMA DEVAM ET DEMEDİMMİ ? NEDEN BENİ DİNLEMEDİN ?

■ stream disconnected before completion: Request too large for gpt-5.6-luna in organization org-b4g4X7AHZEEhfU5LlCT6H4N4 on tokens per min (TPM): Limit 200000, Requested 208385. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.

› STOP. DUR. NE İŞ YAPIYORSAN BEKLEMEYE AL

■ stream disconnected before completion: Request too large for gpt-5.6-luna in organization org-b4g4X7AHZEEhfU5LlCT6H4N4 on tokens per min (TPM): Limit 200000, Requested 208414. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.

■ stream disconnected before completion: Request too large for gpt-5.6-luna in organization org-b4g4X7AHZEEhfU5LlCT6H4N4 on tokens per min (TPM): Limit 200000, Requested 208436. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.

■ Error running remote compact task: stream disconnected before completion: Request too large for gpt-5.6-luna in organization org-b4g4X7AHZEEhfU5LlCT6H4N4 on tokens per min (TPM): Limit 200000, Requested 208454. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.

• Stopping all background terminals.

› model tıkandı

■ stream disconnected before completion: Request too large for gpt-5.6-luna in organization org-b4g4X7AHZEEhfU5LlCT6H4N4 on tokens per min (TPM): Limit 200000, Requested 208444. The input or output tokens must be reduced in order to run successfully. Visit https://platform.openai.com/account/rate-limits to learn more.

• Feedback uploaded. Please open an issue using the following URL:

https://github.com/openai/codex/issues/new?template=3-cli.yml&steps=Uploaded%20thread:%20019ffa99-b86e-7f02-98b5-a0717699ce9d

Or mention your thread ID 019ffa99-b86e-7f02-98b5-a0717699ce9d in an existing issue.

What steps can reproduce the bug?

Uploaded thread: 019ffa99-b86e-7f02-98b5-a0717699ce9d

What is the expected behavior?

No response

Additional information

No response

Start by reviewing uploaded thread 019ffa99-b86e-7f02-98b5-a0717699ce9d and the repeated request-too-large logs, including the WebSockets-to-HTTPS fallback and remote compact failure. No source file, reproduction steps beyond the uploaded thread, or expected behavior is provided, so the completion criteria need clarification before implementation.