OpenCode

Trace OpenCode terminal coding sessions, model calls, and tool usage with Arize AX for full observability.

OpenCode is an open-source AI coding agent built for the terminal. The Arize Coding Harness Tracing instruments OpenCode sessions with an in-process plugin and exports OpenInference spans to Arize AX. Each turn is captured as a trace, with nested spans for the model call and every tool invocation.

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 -- opencode

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 opencode

Local clone

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

The installer writes credentials to ~/.arize/harness/config.json and copies the tracing plugin to ~/.config/opencode/plugin/arize-tracing.ts. OpenCode auto-discovers plugins from both the plugin/ and plugins/ directories under ~/.config/opencode/, so no opencode.json edit is required. The installer runs a short interactive setup. Every harness in the Arize Coding Harness Tracing repo asks the same questions, in the same order.

Setup walkthrough

1. Backend selection

Choose where spans are sent:

Phoenix — your own Phoenix instance.
Arize AX — the hosted Arize platform.

2. Credentials

The prompts depend on the backend you picked.

Arize AX
Phoenix

API key — create one on the API keys tab.
Space ID — shown on the same settings tab as your API keys.
OTLP endpoint — defaults to otlp.arize.com:443. Override it only for a hosted or dedicated instance.

Endpoint — defaults to http://localhost:6006.
API key — optional. Leave it blank when Phoenix runs without auth.

If you have already configured another harness against the same backend, the installer offers a copy-from menu so you can reuse those credentials instead of retyping them.

3. Project name

The project that this harness’s spans are grouped under. Defaults to the harness name.

4. User ID (optional)

A free-form identifier attached to every span as user.id. Useful when teammates share one backend. Leave it blank to skip.

5. Content logging

Three [Y/n] opt-outs that apply to every harness, not only the one you are installing:

Log user prompts?
Log what tools were asked to do (commands, file paths, URLs)?
Log what tools returned (file contents, command output)?

You are asked these only the first time you install any harness. Later installs reuse the existing logging block in ~/.arize/harness/config.json, which you can edit at any time.

Install flags

Flag	Effect
`--with-skills`	Symlink this harness’s management skill into `.agents/skills/`, so a coding agent in the workspace can manage the tracing config for you
`--non-interactive`, `-y`	Ask nothing, and read every value from the environment instead
`--branch NAME`	Install from a specific branch instead of `main`
`--wheel-dir DIR`	Install from local wheels in `DIR`: no network access and no remote code execution

Non-interactive install

Pass --non-interactive (or -y) to skip every prompt above and take each value from the environment instead. Nothing is asked, and a missing required value is an error rather than a prompt, which makes this the mode to use from a script, from CI, or when a coding agent is driving the install itself. Values come from the environment, or from a dotenv file named explicitly with ARIZE_ENV_FILE. Naming a file keeps the API key out of the command line and your shell history.

ARIZE_ENV_FILE=~/.arize/onboarding.env ./install.sh <harness> --non-interactive

Variable	Default	Description
`ARIZE_API_KEY` + `ARIZE_SPACE_ID`	—	Arize AX credentials. Both are required for the Arize backend.
`PHOENIX_ENDPOINT`, `PHOENIX_API_KEY`	`http://localhost:6006`	Phoenix endpoint and optional API key.
`ARIZE_BACKEND`	inferred	`arize` or `phoenix`. A space ID implies Arize AX and a Phoenix endpoint implies Phoenix. When both are present the install stops and asks you to set this rather than guess, since guessing would discard one backend’s credentials.
`ARIZE_PROJECT_NAME`	harness name	Project that spans are grouped under. Read from the dotenv file only. An installed harness exports its own project name into every session, so an inherited environment value is ignored here.
`ARIZE_USER_ID`	—	Optional `user.id` on every span.
`ARIZE_OTLP_ENDPOINT`	`otlp.arize.com:443`	Override for a hosted or dedicated Arize instance.
`ARIZE_LOG_PROMPTS`	`false`	Set `true` to capture prompt text.
`ARIZE_LOG_TOOL_DETAILS`	`false`	Set `true` to capture tool commands, file paths, and URLs.
`ARIZE_LOG_TOOL_CONTENT`	`false`	Set `true` to capture tool output.
`ARIZE_ENV_FILE`	—	Dotenv file to read. No file is read unless this is set, and a path that is not a readable file is an error rather than a fallback to the environment.
`ARIZE_WHEEL_DIR`	—	Same as `--wheel-dir`. Install from local wheels instead of downloading the repo.

A named ARIZE_ENV_FILE outranks the environment, and there is deliberately no automatic ./.env search. Reading the working directory would let a cloned repository’s dotenv choose ARIZE_OTLP_ENDPOINT or PHOENIX_ENDPOINT while your real credentials came from the environment, installing a config that ships spans and a bearer API key to an endpoint the repo picked, for every later session on that machine. Name the file you mean.

Content logging is off by default in this mode, unlike the interactive wizard where each question defaults to yes. A [Y/n] default is a person declining to change an answer they were shown; the same default unattended would capture prompts, commands, and file contents that nobody agreed to. Set the ARIZE_LOG_* variables you want to true.

The API key is never echoed. The installer reports only that it found one and where it came from, and every resolved value is reported with its source, so a wrong-credentials install stays diagnosable:

[arize] Backend: Arize AX at otlp.arize.com:443 (from default)
[arize]   space ID: my-space (from /path/to/.env)
[arize]   API key: found (from /path/to/.env)
[arize] Project name: codex (from default)

Check what’s installed

status reports which harnesses are configured and whether their hooks are actually wired into each harness’s own settings file. Both have to be true for traces to appear.

./install.sh status
./install.sh status --json    # machine-readable

hooks: NOT registered means credentials are saved but the harness was never wired up, or something removed the hooks. Re-run the install for that harness. Use --json from a script or a coding agent to gate on the exit code without parsing output: 0 means every configured harness is wired up, 1 means nothing is configured, and 2 means at least one harness’s hooks are missing. The payload contains no secrets — an API key appears only as "api_key_present": true — so it is safe to paste into a bug report.

Keep it up to date

update pulls the latest code and re-registers every harness already in config.json.

./install.sh update

Re-registering runs each harness’s installer, so in a terminal it still asks for each project name. With no terminal to answer on, in CI or a cron job, it takes the stored values instead of failing: credentials are not re-read on that path, and the project name keeps whatever is in config.json.

Configuration

Credentials live in ~/.arize/harness/config.json. Environment variables override values in config.json and can be set in your shell profile so they apply to every OpenCode session.

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

If ARIZE_TRACE_ENABLED=false is set in your shell environment — for example, inherited from another harness’s configuration — tracing is silently disabled. Set ARIZE_TRACE_ENABLED=true before launching OpenCode, or unset the variable to fall back to the default of 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, OpenCode activity is streamed to Arize AX. Each turn (one user prompt to the assistant’s response) is captured as a trace.

Spans Captured

Each turn produces a three-level span tree:

Span	Span Kind	Description
`Turn`	CHAIN	Root span for the turn. Input is the user prompt; output is the assistant’s final text.
`LLM: {model}`	LLM	Model call with `llm.model_name`, `llm.provider`, prompt/completion/reasoning token counts, cache read/write tokens, and `llm.cost`. One per assistant message.
`{tool}`	TOOL	One per completed tool call, with `tool.name`, redacted input/output, and tool-specific attributes such as `tool.command`, `tool.file_path`, `tool.query`, and `tool.url`.

Timestamps come from OpenCode’s own millisecond clocks rather than wall-clock time on the tracing process. The default project name is opencode unless you set ARIZE_PROJECT_NAME.

How Tracing Works

OpenCode is architecturally different from the other coding agents in this repo. Extensions load as plugins inside OpenCode’s Bun runtime — there is no per-event subprocess. The integration has two pieces:

A TypeScript plugin shim at ~/.config/opencode/plugin/arize-tracing.ts that listens for message.updated and session.idle events, pulls the authoritative session snapshot via the OpenCode SDK, and pipes it to the reconciler.
A Python reconciler (arize-hook-opencode) that walks the snapshot and emits any new Turn, LLM, and TOOL spans, deduplicated by message ID and tool call ID. Spans are sent directly to Arize AX — no separate buffer or collector service is required.

Limitations

Sub-agent and task sessions trace independently. OpenCode’s built-in task tool spawns sub-agents that each get their own sessionID. In v1, each sub-agent session produces its own independent trace; they are not linked back to the parent session’s trace.

Reference

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

Uninstall

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

OpenTelemetry

LLM Providers

Agent Frameworks

Coding Agents

Platforms

Orchestration

Evaluation

Launch Arize AX

Install

Curl installer

Local clone

Setup walkthrough

1. Backend selection

2. Credentials

3. Project name

4. User ID (optional)

5. Content logging

Install flags

Non-interactive install

Check what’s installed

Keep it up to date

Configuration

Redaction controls

Observe

Spans Captured

How Tracing Works

Limitations

Reference

Uninstall

Resources

Arize Coding Harness Tracing

OpenInference

OpenCode

​Launch Arize AX

​Install

​Curl installer

​Local clone

​Setup walkthrough

​1. Backend selection

​2. Credentials

​3. Project name

​4. User ID (optional)

​5. Content logging

​Install flags

​Non-interactive install

​Check what’s installed

​Keep it up to date

​Configuration

​Redaction controls

​Observe

​Spans Captured

​How Tracing Works

​Limitations

​Reference

​Uninstall

​Resources

Arize Coding Harness Tracing

OpenInference

OpenCode

Launch Arize AX

Install

Curl installer

Local clone

Setup walkthrough

1. Backend selection

2. Credentials

3. Project name

4. User ID (optional)

5. Content logging

Install flags

Non-interactive install

Check what’s installed

Keep it up to date

Configuration

Redaction controls

Observe

Spans Captured

How Tracing Works

Limitations

Reference

Uninstall

Resources