fix: review findings — NaN threshold guard, percent-escape rejection in upstream model ids

- Segment: reject NaN thresholds (NaN fails every comparison, so it
  passed the [0,1] range check and reached the shim as the literal
  string "NaN"); ±Inf were already caught by the range comparisons,
  now covered by tests too.
- upstreamPath: reject '%' in model ids — %2F/%2E%2E percent-escapes
  decode back into path structure server-side, bypassing the literal
  /?#/.. rejection. Ids never legitimately contain '%'.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01WWCQcYStWXBYUy5sZWnbLT

provider/llamaswap/segment_restore_test.go

@@ -3,6 +3,7 @@ package llamaswap
 import (
 	"context"
 	"errors"
+	"math"
 	"net/http"
 	"net/http/httptest"
 	"testing"
@@ -95,6 +96,16 @@ func TestSegmentRejectsBadArgs(t *testing.T) {
 		imagegen.SegmentationRequest{Image: imagegen.Image{Data: []byte{1}}, Prompt: "dog", Threshold: 1.5}); !errors.Is(err, llm.ErrUnsupported) {
 		t.Errorf("threshold 1.5: err = %v, want ErrUnsupported", err)
 	}
+	for name, bad := range map[string]float64{
+		"NaN":  math.NaN(),
+		"+Inf": math.Inf(1),
+		"-Inf": math.Inf(-1),
+	} {
+		if _, err := sg.Segment(context.Background(),
+			imagegen.SegmentationRequest{Image: imagegen.Image{Data: []byte{1}}, Prompt: "dog", Threshold: bad}); !errors.Is(err, llm.ErrUnsupported) {
+			t.Errorf("threshold %s: err = %v, want ErrUnsupported", name, err)
+		}
+	}
 }
 
 func TestSegmentRejectsNonImageResponse(t *testing.T) {