feat: add sampling param CLI flags to populate_knowledge binary

Adds --temperature, --top-p, --top-k, --min-p flags so batch runs can
tune the same sampling params now supported by the API endpoints.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/bin/populate_knowledge.rs

@@ -39,6 +39,22 @@ struct Args {
     #[arg(long)]
     num_ctx: Option<i32>,
 
+    /// Sampling temperature (e.g. 0.8). Omit for model default
+    #[arg(long)]
+    temperature: Option<f32>,
+
+    /// Top-p (nucleus) sampling (e.g. 0.9). Omit for model default
+    #[arg(long)]
+    top_p: Option<f32>,
+
+    /// Top-k sampling (e.g. 40). Omit for model default
+    #[arg(long)]
+    top_k: Option<i32>,
+
+    /// Min-p sampling (e.g. 0.05). Omit for model default
+    #[arg(long)]
+    min_p: Option<f32>,
+
     /// Re-process files that already have an insight stored
     #[arg(long, default_value_t = false)]
     reprocess: bool,
@@ -78,6 +94,13 @@ async fn main() -> anyhow::Result<()> {
     if let Some(ctx) = args.num_ctx {
         ollama.set_num_ctx(Some(ctx));
     }
+    if args.temperature.is_some()
+        || args.top_p.is_some()
+        || args.top_k.is_some()
+        || args.min_p.is_some()
+    {
+        ollama.set_sampling_params(args.temperature, args.top_p, args.top_k, args.min_p);
+    }
 
     let sms_api_url =
         std::env::var("SMS_API_URL").unwrap_or_else(|_| "http://localhost:8000".to_string());
@@ -125,6 +148,18 @@ async fn main() -> anyhow::Result<()> {
     if let Some(ctx) = args.num_ctx {
         println!("Num ctx:        {}", ctx);
     }
+    if let Some(t) = args.temperature {
+        println!("Temperature:    {}", t);
+    }
+    if let Some(p) = args.top_p {
+        println!("Top P:          {}", p);
+    }
+    if let Some(k) = args.top_k {
+        println!("Top K:          {}", k);
+    }
+    if let Some(m) = args.min_p {
+        println!("Min P:          {}", m);
+    }
     println!(
         "Mode:           {}",
         if args.reprocess {
@@ -202,10 +237,10 @@ async fn main() -> anyhow::Result<()> {
                 args.model.clone(),
                 None,
                 args.num_ctx,
-                None,
-                None,
-                None,
-                None,
+                args.temperature,
+                args.top_p,
+                args.top_k,
+                args.min_p,
                 args.max_iterations,
             )
             .await