Codex

Trace Codex CLI agent turns, tool calls, and API requests in Arize AX for full observability.

Codex is OpenAI’s open-source CLI coding agent. The Arize Coding Harness Tracing instruments Codex notify hook events and exports OpenInference spans to Arize AX. Each agent turn is captured as an LLM span with tool calls, token usage, and API request details.

Launch Arize AX

To get started, sign up for a free Arize AX account and get your Space ID and API Key:

Log in at app.arize.com
Click Settings and copy the Space ID
Open the API Keys tab and create or copy an API key

Install

Curl installer

macOS / Linux:

curl -sSL https://raw.githubusercontent.com/Arize-ai/coding-harness-tracing/main/install.sh | bash -s -- codex

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Arize-ai/coding-harness-tracing/main/install.bat -OutFile $env:TEMP\install.bat
& $env:TEMP\install.bat codex

Local clone

git clone https://github.com/Arize-ai/coding-harness-tracing.git
cd coding-harness-tracing
./install.sh codex         # macOS / Linux
install.bat codex          # Windows

Open a new shell after install so the update takes effect.

Configuration

Credentials live in ~/.arize/harness/config.json. To override per category, set environment variables in ~/.codex/arize-env.sh — the notify hook sources this file automatically. Env values take precedence over config.json.

export ARIZE_API_KEY="<your-api-key>"
export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_PROJECT_NAME="codex"
export ARIZE_TRACE_ENABLED="true"

Redaction controls

Each ARIZE_LOG_* flag accepts "true" or "false" and defaults to "true". Set to "false" to opt out per category:

export ARIZE_LOG_PROMPTS="false"
export ARIZE_LOG_TOOL_DETAILS="false"
export ARIZE_LOG_TOOL_CONTENT="false"

Flag	Redacts
`ARIZE_LOG_PROMPTS`	User prompt and assistant response text
`ARIZE_LOG_TOOL_DETAILS`	Tool names and arguments
`ARIZE_LOG_TOOL_CONTENT`	Tool call output content

Observe

Once tracing is enabled, Codex activity is streamed to Arize AX. You’ll see:

Turn traces — each agent turn (user prompt to assistant response) as a parent LLM span
Tool call spans — one per tool decision and result pair
API request spans — one per API or WebSocket request
Session grouping — all turns from the same session grouped by session.id
Token usage — prompt, completion, and total token counts on every turn span

Hooks Captured

Codex emits a single notify event with subtypes for each lifecycle stage. The Arize AX hook fans them out into the spans listed above.

Notify subtype	Span Kind	Description
`agent-turn-start`	LLM	Parent turn span starts; records the user prompt
`agent-tool-call`	TOOL	Tool invocation, records name + input + result
`agent-api-request`	LLM	One span per API / WebSocket request to the model
`agent-turn-complete`	LLM	Turn span ends; records output and token counts
`agent-session-complete`	CHAIN	Session teardown, state file cleanup

Reference

For the full list of environment variables, default file paths, and troubleshooting steps, see the Codex tracing README.

Uninstall

curl -sSL https://raw.githubusercontent.com/Arize-ai/coding-harness-tracing/main/install.sh | bash -s -- uninstall codex

OpenTelemetry

LLM Providers

Agent Frameworks

Coding Agents

Platforms

Orchestration

Evaluation

Launch Arize AX

Install

Curl installer

Local clone

Configuration

Redaction controls

Observe

Hooks Captured

Reference

Uninstall

Resources

Arize Coding Harness Tracing

OpenInference

Codex CLI

​Launch Arize AX

​Install

​Curl installer

​Local clone

​Configuration

​Redaction controls

​Observe

​Hooks Captured

​Reference

​Uninstall

​Resources

Arize Coding Harness Tracing

OpenInference

Codex CLI

Launch Arize AX

Install

Curl installer

Local clone

Configuration

Redaction controls

Observe

Hooks Captured

Reference

Uninstall

Resources