You're asking some completely different questions here from sources talking about completely different aspects of antibody-mediated immunity.
The first statement, from WHO, is talking about people who have antibodies now and whether they will have immunity in the future.
Antibodies are produced by particular immune system cells. Someone can recover from the virus today but if those immune cells that produce the specific antibodies against the virus aren't present in 1 year, then that person may have no protection.
WE CANNOT KNOW YET about this. This is a brand new virus, it's only been around for maybe 6 months. There is absolutely no way science can know what level of immunity people will have in 12 months from a virus that has only been around for 6, no matter how hard you ask the question. All we can do is speculate based on what is known about other coronaviruses.
The second point is completely separate: this is about convalescent plasma, taking plasma from people recently recovered and giving it to people currently sick. This isn't intended to "make them immune", it's to give a boost of antibodies to temporarily do the job of combating the virus by binding active virus and making it inactive, buying time to mount an immune response in the infected patient.
For this to work, you need to be able to collect and administer enough antibody-rich plasma and then the antibodies need to get to where the virus is causing infection. If there aren't enough antibodies in the plasma, it won't work. If the antibodies don't get to where the virus is (e.g., the lungs rather than the blood), it won't work (except perhaps in patients with viremia). If the antibodies get there but there aren't enough relative to the concentration of virus, it won't work.
We won't know whether it works until we try it in a lot of patients. Unlike drug therapies which can be fairly standardized, convalescent plasma is really complicated: it depends not just on the principle of the therapy but also on the specific patients the plasma comes from and the specific patients the plasma goes to. There are some promising initial studies (both with the new virus and in the past) that encourage people to keep trying, but so far that's all we have:
Shen, C., Wang, Z., Zhao, F., Yang, Y., Li, J., Yuan, J., ... & Wei, J. (2020). Treatment of 5 critically ill patients with COVID-19 with convalescent plasma. Jama.
Chen, L., Xiong, J., Bao, L., & Shi, Y. (2020). Convalescent plasma as a potential therapy for COVID-19. The Lancet Infectious Diseases, 20(4), 398-400.
Casadevall, A., & Pirofski, L. A. (2020). The convalescent sera option for containing COVID-19. The Journal of clinical investigation, 130(4), 1545-1548.