OpenAI Chat Completions (HTTP)
WednesdayAI’s Gateway can serve a small OpenAI-compatible Chat Completions endpoint. This endpoint is disabled by default. Enable it in config first.POST /v1/chat/completions- Same port as the Gateway (WS + HTTP multiplex):
http://<gateway-host>:<port>/v1/chat/completions
wednesdayai agent), so routing/permissions/config match your Gateway.
Authentication
Uses the Gateway auth configuration. Send a bearer token:Authorization: Bearer <token>
- When
gateway.auth.mode="token", usegateway.auth.token(orOPENCLAW_GATEWAY_TOKEN). - When
gateway.auth.mode="password", usegateway.auth.password(orOPENCLAW_GATEWAY_PASSWORD). - If
gateway.auth.rateLimitis configured and too many auth failures occur, the endpoint returns429withRetry-After.
Security boundary (important)
Treat this endpoint as a full operator-access surface for the gateway instance.- HTTP bearer auth here is not a narrow per-user scope model.
- A valid Gateway token/password for this endpoint should be treated like an owner/operator credential.
- Requests run through the same control-plane agent path as trusted operator actions.
- If the target agent policy allows sensitive tools, this endpoint can use them.
- Keep this endpoint on loopback/tailnet/private ingress only; do not expose it directly to the public internet.
Choosing an agent
No custom headers required: encode the agent id in the OpenAImodel field:
model: "openclaw:<agentId>"(example:"openclaw:main","openclaw:beta")model: "agent:<agentId>"(alias)
x-openclaw-agent-id: <agentId>(default:main)
x-openclaw-session-key: <sessionKey>to fully control session routing.
Enabling the endpoint
Setgateway.http.endpoints.chatCompletions.enabled to true:
Disabling the endpoint
Setgateway.http.endpoints.chatCompletions.enabled to false:
Session behavior
By default the endpoint is stateless per request (a new session key is generated each call). If the request includes an OpenAIuser string, the Gateway derives a stable session key from it, so repeated calls can share an agent session.
Workspace lane denial
If the target agent has workspace lanes enabled and the run cannot be attributed to a linked identity insession.identityLinks, the endpoint returns 403 with:
stream: true, the denial arrives as a final content chunk containing Error: <message> (finish reason stop) instead of a 403 status. HTTP requests carry no paired device, so calls into lane-enabled agents are currently denied; the error message states the reason. See Workspace Lanes.
Streaming (SSE)
Setstream: true to receive Server-Sent Events (SSE):
Content-Type: text/event-stream- Each event line is
data: <json> - Stream ends with
data: [DONE]