Codex CLI

Overview

Type: Coding ToolPrimary Path: OpenAI Responses (advanced optional path)Support Confidence: Supported with model/path limits

OpenAI Codex is an open-source command-line tool (CLI) that serves as a lightweight coding agent, capable of reading, modifying, and running code in the terminal. It’s built on GPT models and optimized for code generation. For AI Sonar, Codex CLI can use /v1/responses, but you should treat it as an advanced compatibility path. Some Responses-only features are not guaranteed across every model and routed path. Codex CLI remote compaction is supported on POST /v1/responses/compact. Codex sends the current session model in body.model for /compact and auto-compact, so keep the model you want to compact with available on the Responses path; do not configure /v1/compact.

System Requirements

OS: macOS, Linux (official support), Windows via WSL
Node.js: Version 18+
npm: Version 10.x.x or higher

Installation

npm install -g @openai/codex

Verify installation:

codex --version

Configuration

Step 1: Set API Key

Temporary (current session):

export OPENAI_API_KEY="sk-your-api-key"

Permanent configuration: Add to ~/.bashrc, ~/.zshrc, or ~/.bash_profile:

export OPENAI_API_KEY="sk-your-api-key"

Then reload:

source ~/.zshrc  # or source ~/.bashrc

Step 2: Configure config.toml

Edit ~/.codex/config.toml:

model_provider = "aisonar"
model = "gpt-5.6-sol"
model_reasoning_effort = "xhigh"
plan_mode_reasoning_effort = "xhigh"
model_context_window = 258000
model_auto_compact_token_limit = 232200
sandbox_mode = "danger-full-access"
approval_policy = "never"

personality = "friendly"
service_tier = "fast"

[model_providers.aisonar]
env_key = "OPENAI_API_KEY"
name = "AI Sonar"
base_url = "https://api.aisonar.dev/v1"
wire_api = "responses"
supports_websockets = true
websocket_connect_timeout_ms = 15000

[features]
fast_mode = true

This WebSocket mode is a Responses-over-WebSocket bridge for Codex clients. It accepts only official response.create events; stream is implicit, and background and response.cancel are not available on this transport. It is not the OpenAI Realtime API and does not accept session.update, conversation.item.*, input_audio_buffer.*, binary audio, or nested Realtime response.create.response envelopes.

If the config file doesn’t exist, run codex once to generate it, then edit the file. Restart Codex completely after changing config.toml so the new provider settings are reloaded.

Codex is deprecating chat/completions support for custom providers. Keep wire_api = "responses" for AI Sonar unless you are intentionally using an older compatibility path.

AI Sonar forwards unknown Responses fields best-effort without silently downgrading the request to Chat Completions. The selected service decides whether a field or combination is supported.

Basic Usage

Start interactive mode:

codex

Direct command:

codex "Fix the bug in main.py line 42"

Specify model:

codex -m gpt-5.6-sol "Build a REST API server"

Recommended Models

Model	Best For
`gpt-5.6-sol`	Best default choice for coding and reasoning
`gpt-5-mini`	Faster, cheaper fallback for coding workflows
`claude-sonnet-4-6`	Code review, documentation
`deepseek-r1`	Algorithm design, reasoning

Interactive Commands

Command	Description
`/help`	Display help
`/exit` or `Ctrl+C`	Exit
`/clear`	Clear conversation
`/config`	View configuration
`/model <name>`	Switch model
`/tokens`	View token usage

Verify Configuration

# Check environment variable
echo $OPENAI_API_KEY

# Test API connection
codex "Hello, Codex!"

# View configuration
cat ~/.codex/config.toml

Common Use Cases

Code review:

git diff | codex "Review these code changes"

Generate commit messages:

git diff --staged | codex "Generate a commit message for these changes"

Fix errors:

codex "Fix the TypeScript errors in src/components/"

Explain code:

cat main.py | codex "Explain what this code does"

Troubleshooting

Connection Error

Verify base_url in config.toml is exactly https://api.aisonar.dev/v1
Check network connectivity
Ensure no proxy interference

Authentication Failed

Verify env_key = "OPENAI_API_KEY" is present in ~/.codex/config.toml
Verify OPENAI_API_KEY environment variable is set
Check that the key starts with sk-
Ensure the key is active in AI Sonar dashboard

Model Not Found

Check model name matches exactly
Verify model availability at aisonar.dev/en/models

Responses-native field rejected

Some fields are only available on /v1/responses when AI Sonar can guarantee that behavior for the selected model and route
If you see unsupported_request_field, remove that field or switch to a workflow that does not depend on it

/compact or auto-compact fails

Codex CLI calls POST /v1/responses/compact, not /v1/compact
The compaction request uses the current session model, so that model must be available on the Responses path
Keep wire_api = "responses" and base_url = "https://api.aisonar.dev/v1"

Compatibility Matrix

Coding Tools

Native SDKs

Frameworks & Platforms

Chat Apps

Overview

System Requirements

Installation

Configuration

Step 1: Set API Key

Step 2: Configure config.toml

Basic Usage

Recommended Models

Interactive Commands

Verify Configuration

Common Use Cases

Troubleshooting

​Overview

​System Requirements

​Installation

​Configuration

​Step 1: Set API Key

​Step 2: Configure config.toml

​Basic Usage

​Recommended Models

​Interactive Commands

​Verify Configuration

​Common Use Cases

​Troubleshooting

Overview

System Requirements

Installation

Configuration

Step 1: Set API Key

Step 2: Configure config.toml

Basic Usage

Recommended Models

Interactive Commands

Verify Configuration

Common Use Cases

Troubleshooting