Include token count in api.Chunk

And calculate the tokens/chunk for gemini responses, fixing the tok/s
meter for gemini models.

Further, only consider the first candidate of streamed gemini responses.

pkg/tui/views/chat/update.go

@@ -111,7 +111,7 @@ func (m Model) Update(msg tea.Msg) (Model, tea.Cmd) {
 		m.replyCursor.Blink = false
 		cmds = append(cmds, m.replyCursor.BlinkCmd())
 
-		m.tokenCount++
+		m.tokenCount += msg.TokenCount
 		m.elapsed = time.Now().Sub(m.startTime)
 	case msgResponse:
 		cmds = append(cmds, m.waitForResponse()) // wait for the next response