Gateway: disable OpenAI HTTP chat completions by default (#686)

* feat(gateway): disable OpenAI chat completions HTTP by default

* test(gateway): deflake mock OpenAI tool-calling

* docs(changelog): note OpenAI HTTP endpoint default-off
This commit is contained in:
Peter Steinberger
2026-01-10 21:55:54 +00:00
committed by GitHub
parent 06052640e8
commit 1c257f170a
8 changed files with 52 additions and 9 deletions
+1
View File
@@ -14,6 +14,7 @@
### Fixes
- CLI: avoid success message when daemon restart is skipped. (#685) — thanks @carlulsoe.
- Gateway: disable the OpenAI-compatible `/v1/chat/completions` endpoint by default; enable via `gateway.http.endpoints.chatCompletions.enabled=true`.
- macOS: stabilize bridge tunnels, guard invoke senders on disconnect, and drain stdout/stderr to avoid deadlocks. (#676) — thanks @ngutman.
- Agents/System: clarify sandboxed runtime in system prompt and surface elevated availability when sandboxed.
- Auto-reply: prefer `RawBody` for command/directive parsing (WhatsApp + Discord) and prevent fallback runs from clobbering concurrent session updates. (#643) — thanks @mcinteerj.