Python: Introduce the chat history reducer

[moonbox3]

Motivation and Context

The SK Python framework has been missing the ability to configure a chat history reducer of type ChatHistoryTruncationReducer and ChatHistorySummarizationReducer which have existed in the .Net SK Agent framework for some time.

The goal of this PR is to introduce the chat history reducers and allow them for use for not only the agent framework, but also anything else that uses a chat history (chat completion, for example). The ChatHistoryReducer extends the ChatHistory class, and so it's simple to include a reducer and logic to reduce messages as one manages the chat history either in an agent framework setting or in a chat completion setting.

Description

This PR:

• Introduces the chat history reducer functionality in Python -- both the ChatHistoryTruncationReducer and ChatHistorySummarizationReducer.
• Add unit tests for code coverage.
• Adds a sample Chat Completion History Reducer to show how to configure both reducers and what each parameter does.
• Add chat completion samples showing how to manage a chat history reducer, including how to specify that function call content and function result content should be part of the summarization payload.
• Updates the Agent SelectionStrategy, KernelFunctionSelectionStrategy and KernelFunctionTermination strategy to use the reducer.
  • Additionally updates the classes above to use a new select_agent abstract method so that one can define an initial agent to run in a particular scenario.
• Removes the deprecated FunctionCallBehavior class, and removes some nasty circular dependencies that we had lurking in the code base for some time. This FunctionCallBehavior has been marked with a deprecation warning for 6+ months now. All samples and docs have moved over to use FunctionChoiceBehavior - developers using FunctionCallBehavior should have had enough time to switch.
• Closes Python Agents: ChatHistoryReducer #7969
• Closes Python: ChatHistory Reduction #10102

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the SK Contribution Guidelines and the pre-submission formatting script raises no violations
• All unit tests pass, and I have added new tests where possible
• I didn't break anyone 😄

[markwallace-microsoft]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
semantic_kernel/agents
agent.py	45	11	76%	48–59, 72–73
semantic_kernel/agents/chat_completion
chat_completion_agent.py	87	1	99%	82
semantic_kernel/agents/strategies/selection
kernel_function_selection_strategy.py	57	4	93%	62–65
selection_strategy.py	20	2	90%	41, 57
semantic_kernel/agents/strategies/termination
kernel_function_termination_strategy.py	47	4	91%	54–57
semantic_kernel/connectors/ai
chat_completion_client_base.py	124	2	98%	393, 403
semantic_kernel/connectors/ai/anthropic/services
anthropic_chat_completion.py	162	8	95%	159, 165, 178, 184, 188, 245–247, 380
utils.py	45	3	93%	67, 100–103
semantic_kernel/connectors/ai/azure_ai_inference/services
azure_ai_inference_base.py	44	1	98%	99
azure_ai_inference_chat_completion.py	110	6	95%	120–123, 132, 154, 178
semantic_kernel/connectors/ai/bedrock/services
bedrock_chat_completion.py	135	14	90%	117, 139, 164, 168–171, 229, 247–266, 325
semantic_kernel/connectors/ai/bedrock/services/model_provider
utils.py	78	20	74%	70, 73, 104, 108–119, 136–154, 175–178
semantic_kernel/connectors/ai/google/google_ai/services
google_ai_chat_completion.py	118	4	97%	126, 153, 179, 181
semantic_kernel/connectors/ai/google/vertex_ai/services
vertex_ai_chat_completion.py	117	4	97%	123, 150, 176, 178
semantic_kernel/connectors/ai/mistral_ai/services
mistral_ai_chat_completion.py	120	38	68%	121–124, 134, 149–152, 167, 183–187, 202–210, 227–235, 248–261, 267, 276–280, 325–328
semantic_kernel/connectors/ai/ollama/services
ollama_chat_completion.py	137	34	75%	116, 141, 145–146, 156, 169, 186, 206–207, 211, 224–234, 245–247, 258–267, 279, 289–290, 312, 323–324, 350, 359–367
utils.py	47	28	40%	31, 46–54, 66–88, 100–104, 125–133
semantic_kernel/connectors/ai/open_ai/prompt_execution_settings
open_ai_prompt_execution_settings.py	84	2	98%	119, 133
semantic_kernel/connectors/ai/open_ai/services
open_ai_chat_completion_base.py	128	7	95%	71, 81, 102, 122, 143, 179, 320
semantic_kernel/contents
function_call_content.py	107	1	99%	196
semantic_kernel/contents/history_reducer
chat_history_reducer_utils.py	93	9	90%	164–165, 175–180, 193, 198–199
chat_history_summarization_reducer.py	90	9	90%	111, 113, 129–130, 155–156, 163, 171, 208
chat_history_truncation_reducer.py	34	3	91%	55–58, 74
TOTAL	16950	1824	89%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
3020	4 💤	0 ❌	0 🔥	1m 25s ⏱️

[eavanvalkenburg]

Couple of questions raised, most importantly why this isn't part of the whole thing instead of part of agents!

[eavanvalkenburg]

couple of small comments!

[eavanvalkenburg]

Only further improvement would be to test with the function call settings, but that can come later

[moonbox3]

Only further improvement would be to test with the function call settings, but that can come later

What do you mean?