llmmeta/helper.go

@@ -34,6 +34,7 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"log/slog"
 	"strings"
 	"time"
 
@@ -574,7 +575,9 @@ func (h *Helper) recordLedger(ctx context.Context, call MetaCall) {
 	if h.storage == nil {
 		return
 	}
-	_ = h.storage.RecordMetaCall(ctx, call)
+	if err := h.storage.RecordMetaCall(ctx, call); err != nil {
+		slog.Warn("llmmeta: failed to record ledger row", "err", err)
+	}
 }
 
 // tryParseJSON attempts to decode text as JSON. Returns the parsed

model/call.go

@@ -237,7 +237,7 @@ func recordUsage(ctx context.Context, resp *llm.Response) {
 		return
 	}
 	u := resp.Usage
-	if u.InputTokens == 0 && u.OutputTokens == 0 {
+	if u.InputTokens == 0 && u.OutputTokens == 0 && u.CacheReadTokens == 0 && u.CacheWriteTokens == 0 {
 		return
 	}
 	model := resolvedModelName(ctx, resp)

model/cloud_sync.go

@@ -314,7 +314,7 @@ func (c *CloudOllamaLimitCache) fetchTags(ctx context.Context) ([]string, error)
 		return nil, err
 	}
 	defer resp.Body.Close()
-	body, err := io.ReadAll(resp.Body)
+	body, err := io.ReadAll(io.LimitReader(resp.Body, maxLimitCacheResponseBytes))
 	if err != nil {
 		return nil, err
 	}
@@ -367,7 +367,7 @@ func (c *CloudOllamaLimitCache) fetchContextLength(ctx context.Context, modelNam
 		return 0, err
 	}
 	defer resp.Body.Close()
-	respBody, err := io.ReadAll(resp.Body)
+	respBody, err := io.ReadAll(io.LimitReader(resp.Body, maxLimitCacheResponseBytes))
 	if err != nil {
 		return 0, err
 	}
@@ -451,3 +451,8 @@ func truncate(b []byte, n int) string {
 	}
 	return string(b[:n]) + "...(truncated)"
 }
+
+// maxLimitCacheResponseBytes bounds the ollama.com limit-cache HTTP responses
+// (/api/tags, /api/show) so a misbehaving endpoint can't stream an unbounded
+// body before the 15s timeout fires. 1 MiB is far above any real response.
+const maxLimitCacheResponseBytes = 1 << 20