claude bcc2305cd0 llm: let a caller name its sampling temperature (V-490) ...

The phraser's own transport has always sampled at 0.7 and this client has
always been greedy. Routing a phrasing call through the client must not
change how it decodes, so Req carries the temperature and 0 — the zero
value, and what every existing caller wanted — is still greedy.

2026-08-03 12:27:04 +04:00

..

client_test.go

Swap the resident model without restarting mavend (#250)

2026-08-01 03:59:08 +04:00

client.go

llm: let a caller name its sampling temperature (V-490)

2026-08-03 12:27:04 +04:00

gate_test.go

llm: give voice turns priority on the single llama-server slot

2026-08-01 14:05:07 +04:00

gate.go

llm: give voice turns priority on the single llama-server slot

2026-08-01 14:05:07 +04:00

modelid_test.go

Label eval runs with the model the server actually loaded (#379)

2026-07-31 14:25:28 +04:00

modelid.go

Label eval runs with the model the server actually loaded (#379)

2026-07-31 14:25:28 +04:00

remote_test.go

llm: pin that a down workstation is invisible (V-485)

2026-08-02 17:19:53 +04:00

remote.go

llm: prefer the workstation model, floor on the resident one (V-485)

2026-08-02 17:19:53 +04:00