Plumb ctx through classifier and Ollama HTTP path

OllamaClient.Generate/GenerateText/call now take ctx and build the HTTP
request via NewRequestWithContext, so an in-flight LLM call is aborted
when the parent context is cancelled (Ctrl-C). Classifier.Classify and
its tier helpers take ctx too. ProcessFunc gets a ctx parameter so the
poller can forward its cancellable context down to classification.

Explainer.summarize manages its own 60s context since reaction-driven
flow has no parent ctx to inherit.

main.go

@@ -95,8 +95,8 @@ func main() {
 	slog.Info("post queue started")
 
 	// Build the pipeline callback: classify → enqueue
-	processItem := func(item *ingestion.FeedItem) {
-		result, err := cls.Classify(item)
+	processItem := func(ctx context.Context, item *ingestion.FeedItem) {
+		result, err := cls.Classify(ctx, item)
 		if err != nil {
 			slog.Error("classification failed, will retry next cycle",
 				"guid", item.GUID,