docs: clarify that missing model causes polling to skip, not fail

This commit is contained in:
Troed Sångberg
2026-06-14 12:33:37 +02:00
parent 014e63845d
commit a0e580b44b
+1 -1
View File
@@ -20,7 +20,7 @@ The plugin discovers the llama-server URL by reading the OpenCode configuration
### Slot Polling
Every 500ms, the plugin polls `GET /slots?model=<model>` on each discovered server. The model parameter is required by the `/slots` endpoint. Model discovery is attempted from the current route's session, falling back to an empty model parameter.
Every 500ms, the plugin polls `GET /slots?model=<model>` on each discovered server. The model parameter is required by the `/slots` endpoint. If the model cannot be discovered from the current route's session, the plugin skips polling.
### State Classification