agent: add sampling parameters (temperature, top_p, top_k)

Move temperature from a per-call parameter to an Agent field,
add top_p and top_k. All three are sent to the API via a new
SamplingParams struct, displayed on the F5 thalamus screen.

Defaults: temperature=0.6, top_p=0.95, top_k=20 (Qwen3.5 defaults).

Also adds top_p and top_k to ChatRequest so they're sent in the
API payload. Previously only temperature was sent.

UI controls for adjusting these at runtime are not yet implemented.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
This commit is contained in:
ProofOfConcept 2026-04-04 13:48:24 -04:00 committed by Kent Overstreet
parent 22f955ad9f
commit dd009742ef
7 changed files with 53 additions and 8 deletions

View file

@ -76,12 +76,17 @@ pub async fn call_api_with_tools(
let mut msg_opt = None;
let mut usage_opt = None;
for attempt in 0..5 {
let sampling = crate::agent::api::SamplingParams {
temperature: temperature.unwrap_or(0.6),
top_p: 0.95,
top_k: 20,
};
match client.chat_completion_stream_temp(
&messages,
Some(&tool_defs),
&ui_tx,
&reasoning,
temperature,
sampling,
Some(priority),
).await {
Ok((msg, usage)) => {