add wordllama

[ahuang11]

This requires pre-fetching the model which can be tedious to set up in firewalled envs. Otherwise, it's really quick and works a lot better than the original implementation.

[codecov]

Codecov Report

Attention: Patch coverage is 12.50000% with 7 lines in your changes missing coverage. Please review.

Project coverage is 53.81%. Comparing base (73fda79) to head (4daceec).
Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
lumen/ai/agents.py	12.50%	7 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #733      +/-   ##
==========================================
- Coverage   60.82%   53.81%   -7.01%     
==========================================
  Files         100      100              
  Lines       12402    12393       -9     
==========================================
- Hits         7543     6669     -874     
- Misses       4859     5724     +865     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.