codex

OpenAI's agent, pinned to a known-good release (@latest broke three times in one week). Runs codex exec --json with approvals and its own sandbox turned off, since the Jetty sandbox already isolates the run.

Providers	`openai`, `openrouter`, `vllm`
Model ids	Bare on OpenAI (`gpt-5.5`); vendor-namespaced on OpenRouter (`openai/gpt-5.5`); verbatim on a custom endpoint.
MCP	No. Declared servers are logged as a warning and ignored.
Usage	Yes.
agent_env	`OPENAI_REASONING_EFFORT` (`minimal` to `xhigh`, model-dependent). `OPENAI_WIRE_API` only matters on older pins.

Two things trip people up. The Rust CLI ignores OPENAI_BASE_URL, so routing is written to config.toml and codex is left out of the OpenRouter auto-default: to run it on OpenRouter, say so. And codex 0.146 and later speak only the Responses API, so a chat-completions-only endpoint (plain vLLM) can't be driven by codex; use pi, opencode or hermes for those.

agent: codex
model: gpt-5.5
model_provider: openai

The same runbook on OpenRouter, with more thinking, from the run endpoint:

{
  "init_params": {
    "model": "openai/gpt-5.5",
    "model_provider": "openrouter",
    "agent_env": { "OPENAI_REASONING_EFFORT": "high" }
  }
}

Back: Runtime Configuration — the full comparison table, frontmatter defaults, and per-run overrides.