let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(gateway): rename OpenAI HTTP endpoint doc

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-10 22:35:38 +01:00
parent 1110d96769
commit 56b11ad5a8
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/gateway/index.md
View File

@@ -28,7 +28,7 @@ pnpm gateway:watch
- Disable with `gateway.reload.mode="off"`. - Disable with `gateway.reload.mode="off"`.
- Binds WebSocket control plane to `127.0.0.1:<port>` (default 18789). - Binds WebSocket control plane to `127.0.0.1:<port>` (default 18789).
- The same port also serves HTTP (control UI, hooks, A2UI). Single-port multiplex. - The same port also serves HTTP (control UI, hooks, A2UI). Single-port multiplex.
- OpenAI-compatible HTTP API: [`/v1/chat/completions`](/gateway/openai-http-api). - OpenAI Chat Completions (HTTP): [`/v1/chat/completions`](/gateway/openai-http-api).
- Starts a Canvas file server by default on `canvasHost.port` (default `18793`), serving `http://<gateway-host>:18793/__clawdbot__/canvas/` from `~/clawd/canvas`. Disable with `canvasHost.enabled=false` or `CLAWDBOT_SKIP_CANVAS_HOST=1`. - Starts a Canvas file server by default on `canvasHost.port` (default `18793`), serving `http://<gateway-host>:18793/__clawdbot__/canvas/` from `~/clawd/canvas`. Disable with `canvasHost.enabled=false` or `CLAWDBOT_SKIP_CANVAS_HOST=1`.
- Logs to stdout; use launchd/systemd to keep it alive and rotate logs. - Logs to stdout; use launchd/systemd to keep it alive and rotate logs.
- Pass `--verbose` to mirror debug logging (handshakes, req/res, events) from the log file into stdio when troubleshooting. - Pass `--verbose` to mirror debug logging (handshakes, req/res, events) from the log file into stdio when troubleshooting.

4
docs/gateway/openai-http-api.md
View File

@@ -3,9 +3,9 @@ summary: "Expose an OpenAI-compatible /v1/chat/completions HTTP endpoint from th
read_when: read_when:
- Integrating tools that expect OpenAI Chat Completions - Integrating tools that expect OpenAI Chat Completions
--- ---
# OpenAI-compatible HTTP API # OpenAI Chat Completions (HTTP)
Clawdbot’s Gateway can serve a small OpenAI-compatible endpoint: Clawdbot’s Gateway can serve a small OpenAI-compatible Chat Completions endpoint:
- `POST /v1/chat/completions` - `POST /v1/chat/completions`
- Same port as the Gateway (WS + HTTP multiplex): `http://<gateway-host>:<port>/v1/chat/completions` - Same port as the Gateway (WS + HTTP multiplex): `http://<gateway-host>:<port>/v1/chat/completions`