JetBrains Custom Model Clients with Keeptrusts
Use this pattern only for a plugin that explicitly supports a custom model endpoint. The Keeptrusts gateway is not a forward proxy and must not be placed in the IDE's global HTTP proxy settings.
Configuration contract
Set the plugin's values to:
| Plugin setting | Value |
|---|---|
| API base URL | http://127.0.0.1:41002/v1 |
| API key | A Keeptrusts client API token |
| Model | An ID returned by /v1/models |
Some plugins require a complete endpoint such as
http://127.0.0.1:41002/v1/chat/completions; follow the plugin's current
documentation. Keep provider credentials in the gateway configuration.
Scope the claim
A plugin may use separate services for chat, completion, embeddings, reranking, or telemetry. Confirm each feature independently. A matching Keeptrusts event positively verifies this model path; lack of an event is a diagnostic lead, not proof of bypass.
For JetBrains AI Assistant itself, use its supported provider settings in JetBrains AI Assistant with Keeptrusts.
Verify
Run kt events tail --since 10m --follow, select the custom model in the plugin,
and send a small request. If the event tail stays empty, check gateway event
delivery, the CLI organization and region, the event window and filters, and
then the plugin's active model and endpoint.