rpk ai run codex
Launch the OpenAI Codex CLI with its model traffic routed
through the Redpanda AI gateway for the current rpk ai environment.
rpk ai generates a throwaway Codex config in a temporary CODEX_HOME, points it at
the gateway’s OpenAI-compatible Responses endpoint for the chosen provider, and
wires Codex’s bearer to rpk ai auth token so it refreshes itself for the
life of the session. Your own ~/.codex config is never read or modified, and no
token is written to disk.
The launch directory is auto-trusted under a workspace-write sandbox
(approval_policy=on-request) so the fresh CODEX_HOME doesn’t prompt for trust on
every run; pass --no-auto-trust to keep Codex’s normal first-run trust prompt.
Only openai / openai_compatible providers are supported (Codex speaks the OpenAI Responses API). Pass Codex’s own flags after a literal --:
rpk ai run codex -L openai -m gpt-5.3-codex -e high -- --ask-for-approval never
Flags
| Value | Type | Description |
|---|---|---|
|
string |
persistent CODEX_HOME dir (default: a throwaway temp dir); its config.toml is regenerated each run and the dir is tightened to 0700; your real |
|
string |
model reasoning effort: minimal|low|medium|high (omit to let Codex use its default). |
|
string |
aigw LLM provider name to route through (must be openai/openai_compatible). |
|
string |
model id to use (must be in the provider’s allowlist); omit to let Codex pick its default. |
|
bool |
do not pre-trust the launch directory; let Codex show its normal first-run trust prompt instead (default: the launch dir is auto-trusted under a workspace-write sandbox). |
|
bool |
print the generated Codex config.toml and exit (no gateway call, no codex needed). |
Global flags
| Value | Type | Description |
|---|---|---|
|
string |
Redpanda or |
|
stringArray |
Override |
|
bool |
Ignore |
|
string |
|
|
bool |
Enable verbose logging. |