internal/llm/client.go

@@ -129,6 +129,11 @@ type Req struct {
 	RepeatPenalty float64
 	// Stop — sequences that end generation early (e.g. newline for a one-liner).
 	Stop []string
+	// Temperature — 0 (the zero value) is greedy decoding, and greedy is what
+	// every caller here wanted before this field existed. It is set only by the
+	// phraser, whose own transport has always sampled at 0.7: routing a phrasing
+	// call through this client must not quietly change how it decodes.
+	Temperature float64
 }
 
 type msg struct {
@@ -176,7 +181,7 @@ func (c *Client) Complete(ctx context.Context, r Req) (string, error) {
 		Messages:      []msg{{Role: "system", Content: r.System}, {Role: "user", Content: r.User}},
 		MaxTokens:     r.MaxTokens,
 		Grammar:       r.Grammar,
-		Temp:          0,
+		Temp:          r.Temperature,
 		RepeatPenalty: r.RepeatPenalty,
 		Stop:          r.Stop,
 	})