reasoning_effort_override sends unsupported configuration_update to Luna, Terra, and Sol
Open
Nobody has claimed this yet.
bug
CLI
config
exec
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.4k
- PR merge metrics
- PR metrics pending
Description
What version of Codex CLI is running?
codex-cli 0.154.0, standalone Linux installation. Confirmed this is the latest stable release on both GitHub Releases and npm on 2026-09-11.
What subscription do you have?
ChatGPT Pro 20x. Authenticated through ChatGPT.
Which model were you using?
Affected: gpt-5.6-luna, gpt-5.6-terra, and gpt-5.6-sol, each at low reasoning effort. gpt-6-astra at low succeeds as a control.
What platform is your computer?
Manjaro Linux 26.1.0. uname -mprs:
Linux 6.1.182-1-MANJARO x86_64 unknown
What terminal emulator and version are you using (if applicable)?
Ghostty for the original interactive failure. Also reproduced with non-interactive codex exec using captured stdout/stderr, so the failure does not depend on the terminal emulator.
Codex doctor report
Collected after disabling the flag globally as a workaround; the reproduction below overrides the flag per invocation and ignores the user config. Home/project paths and unrelated rollout filenames are redacted.
Full reviewed codex doctor --json output
{
"schemaVersion": 1,
"generatedAt": "1789110028s 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": "<home>/.codex/app-server-control/app-server-control.sock",
"daemon state dir": "<home>/.codex/app-server-daemon",
"mode": "persistent",
"pid file": "<home>/.codex/app-server-daemon/app-server.pid (file)",
"settings": "<home>/.codex/app-server-daemon/settings.json (file)",
"status": "not running",
"update-loop pid file": "<home>/.codex/app-server-daemon/app-server-updater.pid (file)"
},
"remediation": null,
"durationMs": 1
},
"auth.credentials": {
"id": "auth.credentials",
"category": "auth",
"status": "ok",
"summary": "auth is configured",
"details": {
"auth file": "<home>/.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": "<home>/.codex",
"active thread overrides": "not inspected",
"config.toml": "<home>/.codex/config.toml",
"config.toml parse": "ok",
"configuration load ms": "23",
"configuration scope": "invocation config, including cloud-managed policy",
"cwd": "<project>",
"enabled feature flags": "shell_tool, view_image, sleep_tool, unified_exec, unified_exec_tty, unified_exec_zsh_fork, shell_snapshot, content_item_kinds, code_mode_host, terminal_resize_reflow, sqlite, hooks, enable_request_compression, unbounded_connection_retries, multi_agent, tool_search_always_defer_mcp_tools, tool_suggest, plugins, in_app_browser, in_app_chat, in_app_dictation, in_app_local_automation, in_app_updates, browser_use, browser_use_full_cdp_access, browser_use_external, computer_use, remote_plugin, plugin_sharing, external_migration, image_generation, resize_all_images, item_ids, skill_mcp_dependency_install, skill_search, mentions_v2, steer, default_mode_request_user_input, guardian_approval, goals, context_management, collaboration_modes, tool_call_mcp_elicitation, auth_elicitation, personality, fast_mode, tui_app_server, remote_compaction_v2, compaction_image_budget, workspace_dependencies",
"feature flag overrides": "apps=false, external_migration=true, default_mode_request_user_input=true, context_management=true",
"feature flags enabled": "50",
"log dir": "<home>/.codex/log",
"mcp servers": "1",
"model": "gpt-6-astra",
"model provider": "openai",
"sqlite home": "<home>/.codex"
},
"remediation": null,
"durationMs": 0
},
"git.environment": {
"id": "git.environment",
"category": "git",
"status": "ok",
"summary": "git executable found; execution not verified",
"details": {
".git entry": "file -> <git-worktree>",
"PATH git #1": "/usr/bin/git",
"PATH git entries": "1",
"git execution": "not inspected (PATH helpers are not executed)",
"repo detected": "true",
"repo root": "<project>",
"selected git": "/usr/bin/git"
},
"remediation": null,
"durationMs": 0
},
"installation": {
"id": "installation",
"category": "install",
"status": "ok",
"summary": "installation looks consistent",
"details": {
"PATH codex #1": "<home>/.local/bin/codex",
"PATH codex #2": "<home>/.local/share/npm/bin/codex",
"PATH codex entries": "2",
"current executable": "<home>/.codex/packages/standalone/releases/0.154.0-x86_64-unknown-linux-musl/bin/codex",
"install context": "standalone (unix, package <home>/.codex/packages/standalone/releases/0.154.0-x86_64-unknown-linux-musl, bin <home>/.codex/packages/standalone/releases/0.154.0-x86_64-unknown-linux-musl/bin, resources <home>/.codex/packages/standalone/releases/0.154.0-x86_64-unknown-linux-musl/codex-resources, path <home>/.codex/packages/standalone/releases/0.154.0-x86_64-unknown-linux-musl/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": 1
},
"mcp.config": {
"id": "mcp.config",
"category": "mcp",
"status": "ok",
"summary": "MCP configuration is locally consistent",
"details": {
"configured servers": "1",
"disabled servers": "0",
"streamable_http servers": "1"
},
"remediation": null,
"durationMs": 378
},
"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)",
"reachability mode": "ChatGPT auth"
},
"remediation": null,
"durationMs": 283
},
"network.websocket_reachability": {
"id": "network.websocket_reachability",
"category": "websocket",
"status": "ok",
"summary": "Responses WebSocket handshake succeeded",
"details": {
"DNS": "2 IPv4, 2 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": 923
},
"runtime.provenance": {
"id": "runtime.provenance",
"category": "runtime",
"status": "ok",
"summary": "running standalone on linux-x86_64",
"details": {
"commit": "unknown",
"current executable": "<home>/.codex/packages/standalone/releases/0.154.0-x86_64-unknown-linux-musl/bin/codex",
"install method": "standalone (unix, package <home>/.codex/packages/standalone/releases/0.154.0-x86_64-unknown-linux-musl, bin <home>/.codex/packages/standalone/releases/0.154.0-x86_64-unknown-linux-musl/bin, resources <home>/.codex/packages/standalone/releases/0.154.0-x86_64-unknown-linux-musl/codex-resources, path <home>/.codex/packages/standalone/releases/0.154.0-x86_64-unknown-linux-musl/codex-path)",
"platform": "linux-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": "<home>/.codex/packages/standalone/releases/0.154.0-x86_64-unknown-linux-musl/codex-path/rg",
"search command readiness": "file exists",
"search provider": "bundled"
},
"remediation": null,
"durationMs": 0
},
"sandbox.helpers": {
"id": "sandbox.helpers",
"category": "sandbox",
"status": "ok",
"summary": "sandbox configuration is readable",
"details": {
"approval policy": "Never",
"codex-linux-sandbox helper": "<home>/.codex/tmp/arg0/codex-arg0uFpvcb/codex-linux-sandbox",
"denied-read glob rules": "0",
"denied-read rules": "0",
"execve wrapper helper": "<home>/.codex/tmp/arg0/codex-arg0uFpvcb/codex-execve-wrapper",
"filesystem sandbox": "unrestricted",
"glob scan max depth": "unbounded",
"managed filesystem source": "none",
"network sandbox": "enabled"
},
"remediation": null,
"durationMs": 0
},
"security.endpoint": {
"id": "security.endpoint",
"category": "security",
"status": "ok",
"summary": "endpoint protection is not inspected on this platform",
"details": {
"endpoint products": "not inspected on this platform"
},
"remediation": null,
"durationMs": 0
},
"state.paths": {
"id": "state.paths",
"category": "state",
"status": "ok",
"summary": "state paths and databases are inspectable",
"details": {
"CODEX_HOME": "<home>/.codex (dir)",
"active rollout files": "2672 files, 3325627470 total bytes, 1244621 average bytes",
"archived rollout files": "0 files, 0 total bytes, 0 average bytes",
"goals DB": "<home>/.codex/goals_1.sqlite (file)",
"goals DB integrity": "ok",
"log DB": "<home>/.codex/logs_2.sqlite (file)",
"log DB integrity": "ok",
"log dir": "<home>/.codex/log (dir)",
"memories DB": "<home>/.codex/memories_1.sqlite (file)",
"memories DB integrity": "ok",
"queue DB": "<home>/.codex/queue_1.sqlite (file)",
"queue DB integrity": "ok",
"sqlite home": "<home>/.codex (dir)",
"standalone release cache": "15 entries in <home>/.codex/packages/standalone/releases",
"state DB": "<home>/.codex/state_5.sqlite (file)",
"state DB integrity": "ok",
"thread history DB": "<home>/.codex/thread_history_1.sqlite (file)",
"thread history DB integrity": "ok"
},
"remediation": null,
"durationMs": 4829
},
"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": "2672",
"rollout DB active rows": "2620",
"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": "52",
"rollout DB missing active sample": [
"<home>/.codex/sessions/2026/03/20/<unrelated-rollout>.jsonl",
"<home>/.codex/sessions/2026/03/20/<unrelated-rollout>.jsonl",
"<home>/.codex/sessions/2026/03/23/<unrelated-rollout>.jsonl",
"<home>/.codex/sessions/2026/03/24/<unrelated-rollout>.jsonl",
"<home>/.codex/sessions/2026/03/24/<unrelated-rollout>.jsonl"
],
"rollout DB missing archived rows": "0",
"rollout DB model providers": "openai=2620",
"rollout DB rows": "2620",
"rollout DB scan cap reached": "false",
"rollout DB scan errors": "0",
"rollout DB sources": "cli=1292, subagent:thread_spawn=588, vscode=387, subagent:review=314, subagent:other=20, exec=19",
"rollout DB stale rows": "0"
},
"issues": [
{
"severity": "warning",
"cause": "rollout files are missing from the state DB",
"measured": "52 active, 0 archived",
"expected": "every rollout file has a matching threads row",
"remedy": null,
"fields": []
}
],
"remediation": null,
"durationMs": 1103
},
"system.disk": {
"id": "system.disk",
"category": "disk",
"status": "ok",
"summary": "sufficient free disk space (153.3 GiB)",
"details": {
"CODEX_HOME available": "153.3 GiB",
"failure threshold": "1.0 GiB",
"warning threshold": "5.0 GiB",
"worktree available": "153.3 GiB"
},
"remediation": null,
"durationMs": 0
},
"system.environment": {
"id": "system.environment",
"category": "system",
"status": "ok",
"summary": "OS language C",
"details": {
"EDITOR": "set",
"GH_PAGER": "set",
"GIT_PAGER": "set",
"LANG": "en_US.UTF-8",
"LC_ALL": "C.UTF-8",
"LC_CTYPE": "C.UTF-8",
"PAGER": "set",
"VISUAL": "set",
"os": "Manjaro 26.1.0 (Bian-May) [64-bit]",
"os language": "C",
"os type": "Manjaro",
"os version": "26.1.0"
},
"remediation": null,
"durationMs": 8
},
"terminal.env": {
"id": "terminal.env",
"category": "terminal",
"status": "ok",
"summary": "terminal metadata was detected",
"details": {
"COLORTERM": "truecolor",
"DISPLAY": "present",
"NO_COLOR": "1",
"TERM": "foot-extra",
"WAYLAND_DISPLAY": "present",
"color output": "disabled (NO_COLOR)",
"effective locale": "C.UTF-8",
"stderr is terminal": "false",
"stdin is terminal": "false",
"stdout is terminal": "false",
"terminal": "unknown",
"terminal size": "80x24"
},
"remediation": null,
"durationMs": 1
},
"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": "git repo root",
"terminal title project value": "<project-name>",
"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",
"last checked at": "2026-09-11T06:50:39.474605051Z",
"latest version": "0.154.0",
"latest version status": "current version is not older",
"update action": "standalone installer",
"version cache": "<home>/.codex/version.json"
},
"remediation": null,
"durationMs": 1343
}
}
}
What issue are you seeing?
Enabling the experimental reasoning_effort_override feature makes the first request fail with HTTP 400 on GPT-5.6 Luna, Terra, and Sol. The backend rejects a configuration_update input item. Each model succeeds when the flag is disabled. Astra succeeds with the flag enabled.
The original failure happened after launching the TUI with Astra selected, switching to Luna with /model, and sending test. Further testing reproduces the same error in fresh sessions that start directly on each affected model. A model switch, resumed history, and a reasoning-effort change are not required.
Live results on 0.154.0, one fresh invocation per cell, all at low:
| Model | Flag disabled | Flag enabled |
|---|---|---|
gpt-5.6-luna |
OK, exit 0 |
HTTP 400, exit 1 |
gpt-5.6-terra |
OK, exit 0 |
HTTP 400, exit 1 |
gpt-5.6-sol |
OK, exit 0 |
HTTP 400, exit 1 |
gpt-6-astra |
Not tested | OK, exit 0 |
All tests used the prompt Reply with exactly OK. Do not use tools., an empty working directory, --ignore-user-config, and --ephemeral.
Full backend error from Luna:
{
"type": "error",
"error": {
"type": "invalid_request_error",
"code": "unsupported_value",
"message": "The 'configuration_update' item type is not supported with this model.",
"param": "input[5].type"
},
"status": 400
}
Terra and Sol return the same error, with param equal to input[7].type. No assistant answer is produced.
What steps can reproduce the bug?
With Codex 0.154.0 authenticated through ChatGPT:
repro_dir=$(mktemp -d)
codex exec \
--ignore-user-config \
--ephemeral \
--skip-git-repo-check \
-C "$repro_dir" \
--sandbox read-only \
-c 'approval_policy="never"' \
-m gpt-5.6-luna \
-c 'model_reasoning_effort="low"' \
--enable reasoning_effort_override \
--json \
'Reply with exactly OK. Do not use tools.'
- Observe
turn.failed, the HTTP 400 above, and process exit 1. - Replace
gpt-5.6-lunawithgpt-5.6-terraorgpt-5.6-sol. Both fail the same way. - Replace
--enable reasoning_effort_overridewith--disable reasoning_effort_overrideand start a fresh invocation. All three models replyOKand exit 0. - Keep the flag enabled but select
gpt-6-astra. It repliesOKand exits 0.
Original persisted Luna failure thread: 01a08f3b-8648-75e2-a650-13567194dce0. The isolated follow-up tests used ephemeral sessions.
What is the expected behavior?
When the flag is enabled, Codex should emit configuration_update only for models that support it. Unsupported models should keep using the ordinary request-level reasoning effort and complete successfully.
Model-switch handling should also account for any incompatible configuration-update items already in history, rather than replaying them to a model that rejects them. The fresh-session failures above establish that there is also a problem before any history migration is involved.
Additional information
The 0.154.0 client checks the feature flag, model_info.use_responses_lite, and whether the provider is OpenAI before recording the item. It does not check a separate capability for accepting configuration_update:
effort_for_configuration_update in rust-v0.154.0
Based on the source and the live results, use_responses_lite appears insufficient as the compatibility check for this item type.
Related context:
- #43110 introduced this flag and the item-emission path.
- #42996 concerns Astra cache preservation when reasoning effort changes. This report covers HTTP 400 failures on unsupported models, even on the first turn at an unchanged effort.
- #43795 adds request-effort pinning and model-switch handling. I have not tested an unreleased build containing that follow-up.
Workaround: set features.reasoning_effort_override = false and start a fresh session.
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 failure with non-interactive codex exec using reasoning_effort_override for the affected models, comparing it with the successful gpt-6-astra control. Trace where the configuration_update request is assembled and verify completion by confirming unsupported updates are no longer sent to Luna, Terra, or Sol and the regression is covered by a test.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- cli
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100