Prompting changes to better support smaller models.

[afourney]

A series of changes to the python/packages/autogen-ext/src/autogen_ext/agents/web_surfer/_multimodal_web_surfer.py file have been made to better support smaller models.

This includes changes to the prompts, state descriptions, and ordering of messages.

Regression tasks with OpenAI models shows no change in GAIA scores, while scores for Llama are significantly improved.

[codecov]

Codecov Report

Attention: Patch coverage is 75.75758% with 8 lines in your changes missing coverage. Please review.

Project coverage is 78.08%. Comparing base (3b2bf82) to head (6dd3e7b).
Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
...en_ext/agents/web_surfer/_multimodal_web_surfer.py	75.75%	8 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #5386      +/-   ##
==========================================
+ Coverage   77.93%   78.08%   +0.14%     
==========================================
  Files         158      158              
  Lines        9578     9576       -2     
==========================================
+ Hits         7465     7477      +12     
+ Misses       2113     2099      -14     

Flag	Coverage Δ
unittests	78.08% <75.75%> (+0.14%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

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