fix(models): default local custom providers to completions

This commit is contained in:
Peter Steinberger
2026-04-27 13:09:54 +01:00
parent b6c8e51dcb
commit 63eaf8ea51
10 changed files with 124 additions and 9 deletions

View File

@@ -189,7 +189,7 @@ Use the LM Studio host's reachable address, keep `/v1`, and make sure LM Studio
}
```
Unlike generic OpenAI-compatible providers, `lmstudio` automatically trusts its configured local/private endpoint for guarded model requests. If you use a custom provider id instead of `lmstudio`, set `models.providers.<id>.request.allowPrivateNetwork: true` explicitly.
Unlike generic OpenAI-compatible providers, `lmstudio` automatically trusts its configured local/private endpoint for guarded model requests. Custom loopback provider IDs such as `localhost` or `127.0.0.1` are also trusted automatically; for LAN, tailnet, or private DNS custom provider IDs, set `models.providers.<id>.request.allowPrivateNetwork: true` explicitly.
## Related