Error handling in getting LLM-based summary

[qingyun-wu]

Why are these changes needed?

The llm-based summary method (introduced in #1402) is not robust. Handling errors so that the code fails gracefully.

A quick fix to some of the known failure cases is added at #1564. But it is not necessarily sufficient and it may take some time to sort out a good one.

Related issue number

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://microsoft.github.io/autogen/docs/Contribute#documentation to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[codecov-commenter]

Codecov Report

Attention: 4 lines in your changes are missing coverage. Please review.

Comparison is base (3e33a2c) 35.28% compared to head (8c79294) 42.33%.
Report is 1 commits behind head on main.

Files	Patch %	Lines
autogen/agentchat/conversable_agent.py	20.00%	4 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1567      +/-   ##
==========================================
+ Coverage   35.28%   42.33%   +7.04%     
==========================================
  Files          44       44              
  Lines        5311     5315       +4     
  Branches     1231     1300      +69     
==========================================
+ Hits         1874     2250     +376     
+ Misses       3283     2863     -420     
- Partials      154      202      +48     

Flag	Coverage Δ
unittests	42.31% <20.00%> (+7.02%)	⬆️

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.

[afourney]

GroupChat has/had the same problem and resolved it this way:

autogen/autogen/agentchat/groupchat.py

Lines 346 to 354 in 3e33a2c

	selected_agent = None
	select_speaker_messages = self.messages.copy()
	# If last message is a tool call or function call, blank the call so the api doesn't throw
	if select_speaker_messages[-1].get("function_call", False):
	select_speaker_messages[-1] = dict(select_speaker_messages[-1], function_call=None)
	if select_speaker_messages[-1].get("tool_calls", False):
	select_speaker_messages[-1] = dict(select_speaker_messages[-1], tool_calls=None)
	select_speaker_messages = select_speaker_messages + [
	{"role": "system", "content": self.select_speaker_prompt(graph_eligible_agents)}