feat: add trace log level (#10650)

reduce prompt log to trace level

runner/ollamarunner/runner.go

@@ -12,7 +12,6 @@ import (
 	"net"
 	"net/http"
 	"os"
-	"path/filepath"
 	"regexp"
 	"runtime"
 	"strconv"
@@ -24,7 +23,9 @@ import (
 	"golang.org/x/sync/semaphore"
 
 	"github.com/ollama/ollama/api"
+	"github.com/ollama/ollama/envconfig"
 	"github.com/ollama/ollama/llm"
+	"github.com/ollama/ollama/logutil"
 	"github.com/ollama/ollama/ml"
 	"github.com/ollama/ollama/model"
 	"github.com/ollama/ollama/model/input"
@@ -816,7 +817,7 @@ func Execute(args []string) error {
 	kvCacheType := fs.String("kv-cache-type", "", "quantization type for KV cache (default: f16)")
 	port := fs.Int("port", 8080, "Port to expose the server on")
 	threads := fs.Int("threads", runtime.NumCPU(), "Number of threads to use during generation")
-	verbose := fs.Bool("verbose", false, "verbose output (default: disabled)")
+	_ = fs.Bool("verbose", false, "verbose output (default: disabled)")
 	_ = fs.Bool("no-mmap", false, "do not memory-map model (slower load but may reduce pageouts if not using mlock)")
 	tensorSplit := fs.String("tensor-split", "", "fraction of the model to offload to each GPU, comma-separated list of proportions")
 	multiUserCache := fs.Bool("multiuser-cache", false, "optimize input cache algorithm for multiple users")
@@ -831,22 +832,7 @@ func Execute(args []string) error {
 	if err := fs.Parse(args); err != nil {
 		return err
 	}
-	level := slog.LevelInfo
-	if *verbose {
-		level = slog.LevelDebug
-	}
-	handler := slog.NewTextHandler(os.Stderr, &slog.HandlerOptions{
-		Level:     level,
-		AddSource: true,
-		ReplaceAttr: func(_ []string, attr slog.Attr) slog.Attr {
-			if attr.Key == slog.SourceKey {
-				source := attr.Value.Any().(*slog.Source)
-				source.File = filepath.Base(source.File)
-			}
-			return attr
-		},
-	})
-	slog.SetDefault(slog.New(handler))
+	slog.SetDefault(logutil.NewLogger(os.Stderr, envconfig.LogLevel()))
 	slog.Info("starting ollama engine")
 
 	server := &Server{