internal/adapters/llm/client.go

@@ -25,12 +25,16 @@ import (
 // docs/homelab-integration.md.
 const defaultMaxTokens = 8192
 
+// defaultTemperature is what every caller got before WithTemperature existed.
+const defaultTemperature = 0.2
+
 // Client calls an OpenAI-compatible chat completions endpoint.
 type Client struct {
 	baseURL    string
 	apiKey     string
 	model      string
 	maxTokens  int
+	temp       float64
 	httpClient *http.Client
 	usageHook  func(model string, prompt, completion int)
 }
@@ -51,6 +55,12 @@ func WithMaxTokens(n int) Option {
 	}
 }
 
+// WithTemperature overrides the sampling temperature. Zero IS a valid value and is sent
+// as zero: the reconciler's accuracy was measured at temperature 0 and must run there.
+func WithTemperature(t float64) Option {
+	return func(c *Client) { c.temp = t }
+}
+
 // WithUsageHook registers a callback fired after a successful completion with the
 // model and the prompt/completion token counts from the response usage block. It
 // keeps this copied, stdlib-only package (ADR-004) decoupled from metrics: the
@@ -66,6 +76,7 @@ func New(baseURL, apiKey, model string, timeout time.Duration, opts ...Option) *
 		apiKey:     apiKey,
 		model:      model,
 		maxTokens:  defaultMaxTokens,
+		temp:       defaultTemperature,
 		httpClient: &http.Client{Timeout: timeout},
 	}
 	for _, opt := range opts {
@@ -105,7 +116,7 @@ func (c *Client) Complete(ctx context.Context, system, user string) (string, err
 			{Role: "system", Content: system},
 			{Role: "user", Content: user},
 		},
-		Temperature: 0.2,
+		Temperature: c.temp,
 		MaxTokens:   c.maxTokens,
 	}
 	b, err := json.Marshal(body)