Prerequisites
- OpenClaw installed:
- A Pioneer API key from the Pioneer dashboard.
jqinstalled for converting the live Pioneer model catalog into OpenClaw config.- Check to see if OpenClaw is available:
Setup steps
- Save Pioneer auth in OpenClaw
- Paste your Pioneer API key once. OpenClaw stores it in the local auth profile store and the gateway reuses it across terminal sessions.
Do not paste real API keys into docs, screenshots, shared shell history, or issue trackers. Rotate the key if it has been exposed.
- Paste your Pioneer API key once. OpenClaw stores it in the local auth profile store and the gateway reuses it across terminal sessions.
- Discover and register Pioneer models
- Pioneer’s supported inference models can change over time. Use the OpenAI-compatible
GET /v1/modelscatalog as the source of truth and convert it directly into OpenClaw model config. - This command reads the Pioneer key from the OpenClaw auth profile saved in step 1, uses it for the catalog fetch, and writes the discovered model catalog into
~/.openclaw/openclaw.json. - The command manually adds
pioneer/autofor Pioneer Auto, then reads the top-level.models[]catalog when present and falls back to the top-level.models[]catalog when present and falls back to.data[], deduplicates byid, filtersanthropic/*Claude Code discovery aliases so OpenClaw does not show duplicate models, and exposes every Pioneer model underagents.defaults.modelsfor the model picker andopenclaw models status. - OpenClaw uses
/thinkfor reasoning controls. Models that advertisesupported_reasoning_levels,reasoning,supports_reasoning, orthinkingmetadata are registered withreasoning: true; when Pioneer advertises exact reasoning levels, the command also writescompat.supportedReasoningEffortsso OpenClaw can include levels such asxhigh. - OpenClaw uses
/thinkfor reasoning controls. Models that advertisesupported_reasoning_levels,reasoning,supports_reasoning, orthinkingmetadata are registered withreasoning: true; when Pioneer advertises exact reasoning levels, the command also writescompat.supportedReasoningEffortsso OpenClaw can include levels such asxhigh. - To refresh the catalog later, re-run the same command. It replaces the Pioneer provider models and Pioneer agent allowlist while preserving non-Pioneer agent model entries.
- Pioneer’s supported inference models can change over time. Use the OpenAI-compatible
- Start the local gateway and open the Web UI
- The model-discovery command already sets
pioneer/autoas the default model. You do not need to runopenclaw models set pioneer/autoseparately. - Use the LaunchAgent service for normal local setup. Do not run
openclaw gateway rununless you are intentionally debugging in the foreground. - This avoids the noisy full
openclaw doctorflow during normal setup.openclaw gateway install --forcekeeps the macOS LaunchAgent service definition current, including the service environment.openclaw gateway restartthen applies the Pioneer model config and gateway token. openclaw dashboardmay print a clean URL such ashttp://127.0.0.1:18789/while copying a token-authenticated URL to your clipboard.- In the Web UI, choose a reasoning-capable Pioneer model and use the thinking selector to switch levels. From the CLI or chat input, send
/think low,/think medium,/think high, or/think off. Send/thinkwith no argument to see the current effective level. - In the Web UI, choose a reasoning-capable Pioneer model and use the thinking selector to switch levels. From the CLI or chat input, send
/think low,/think medium,/think high, or/think off. Send/thinkwith no argument to see the current effective level.
- The model-discovery command already sets
- Verify the setup (optional)
- These checks are useful when validating a fresh setup or debugging a user report:
- Expected result:
defaultModelispioneer/auto,allowed_countis greater than1, and the Pioneer auth probe succeeds. - OpenClaw may probe only the default/effective target even when the agent allowlist contains many Pioneer models. That is fine as long as the configured model count is greater than
1andpioneer/autoprobes successfully.
- These checks are useful when validating a fresh setup or debugging a user report:
- Run a first agent message from the CLI (optional)
- OpenClaw needs a target session for agent messages. A plain
--messageis not enough. - To continue the same local session:
- You can list sessions with:
- OpenClaw needs a target session for agent messages. A plain
Troubleshooting OpenClaw integration
Missing auth - pioneer
Missing auth - pioneer
OpenClaw does not have a Pioneer auth profile. Run:
Only pioneer/auto appears in OpenClaw
Only pioneer/auto appears in OpenClaw
The catalog fetch likely did not read the saved OpenClaw auth profile. Confirm the Pioneer profile exists, then rerun the discovery command.Confirm the saved auth profile exists:Confirm the catalog exposes the expected Pioneer router models before rerunning the discovery command:Expected output includes at least
pioneer/auto. Versioned router entries such as pioneer/auto_v1.1, pioneer/auto_v1.2, and pioneer/general appear when they are exposed by the production catalog for your key. If the catalog output is correct, rerun the discovery command and restart the gateway.Missing env var "PIONEER_API_KEY"
Missing env var "PIONEER_API_KEY"
This usually means the config points at an environment variable that is not visible to the OpenClaw process or gateway service. Prefer the auth-profile setup:If you intentionally use an env reference, confirm the variable is visible to the process that runs OpenClaw:For launchd,
launchctl setenv does not persist across reboots and may not be enough if OpenClaw uses a generated service environment wrapper.Gateway service not loaded
Gateway service not loaded
Reinstall and restart the LaunchAgent:
No target session selected
No target session selected
Pass a session target:
Gateway already running or port 18789 is in use
Gateway already running or port 18789 is in use
This usually means the LaunchAgent service is already bound to the gateway port. That is normal; do not start a second gateway with If For foreground debugging only, stop the service first, then run the gateway in the foreground:
openclaw gateway run.For normal use, restart the service and open the Web UI:gateway status says the service config is out of date, repair and restart:Dashboard auth required or gateway token mismatch
Dashboard auth required or gateway token mismatch
Use the configured shared gateway token. The Control UI expects the same token from Paste that value into the Web UI Do not manually extract tokens from OpenClaw’s SQLite state database.
gateway.auth.token or OPENCLAW_GATEWAY_TOKEN:Gateway Token field and click Connect.If the command is empty, create a token and restart the gateway:Gateway is running but probe fails
Gateway is running but probe fails
Check reachability and logs: