* Add support for model family specification

* spelling mistake

* lint, etc

* fixes

* Add missing model context attribute

* fix type

* Add test

* imports

---------

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* Refine types in agentchat

* importg

* fix mypy

* Decouple model_context from AssistantAgent

* add UnboundedBufferedChatCompletionContext to mimic pervious model_context behaviour on AssistantAgent

* moving unbounded buffered chat to a different file

* fix model_context assertions in test_group_chat

* Refactor model context, introduce states

* fixes

* update

---------

Co-authored-by: aditya.kurniawan <aditya.kurniawan@core42.ai>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Victor Dibia <victordibia@microsoft.com>

* Adding ToolCallResultSummaryMessage

* Support for ToolCallResultSummaryMessage

* Added ToolCallSummaryMessage

* ruff format

* Add ToolCallSummaryMessage to ChatMessage

* typing and tests for ToolCallSummaryMessage

* PR Feedback

---------

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Hussein Mozannar <hmozannar@microsoft.com>

* Define AgentEvent, rename tool call messages to events.

* update doc

* Use AgentEvent | ChatMessage to replace AgentMessage

* Update docs

* update deprecation notice

* remove unused

* fix doc

* format

* feat: add support for list of messages as team task input
* Update society of mind agent to use the list input task
---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* add models.openai namespace

* refactor tools namespace

* update lock file

* revert pyproject changes

* update docs and add cast

* update ext models doc ref

* increase underline

* add reply models namespace

* update imports

* fix test

* linting

* fix missing conflicts

* revert pydantic changes

* rename to replay

* replay

* fix reply

* Fix test

* formatting

* example

---------

Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com>
Co-authored-by: Jack Gerrits <jack@jackgerrits.com>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>

* 1 tool call iteration default

* handoff first

* return_only_response

* add and remove tools

* print out tool calls

* pass checks

* fix issues

* add test

* add unit tests

* remove extra print

* Update python/packages/autogen-agentchat/src/autogen_agentchat/agents/_assistant_agent.py

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* documentation and none max_tools_calls

* Always limit # tool call to 1

* Update notebooks for the changing behavior of assistant agent.

* Merge branch 'main' into assistant_Agent_tools

* add reflect_on_tool_use parameter to format the tool call result

* wip

* wip

* fix pyright

* Add unit tests

* Merge remote-tracking branch 'origin/main' into assistant_Agent_tools

* Update with custom formatting of tool call summary

* format

* Merge branch 'main' into assistant_Agent_tools

* Move model context out of components

* move models out of components

* rename docs file

* Move grpc runtimes to ext, flatten application

* rename to grpc

* fmt

1. convert dataclass types to pydantic basemodel 
2. add save_state and load_state for ChatAgent
3. state types for AgentChat
---------

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* Address issue_4543 and add tests.

* Fixed pyright errors.

* Flatten core base and components

* remove extra files

* dont export from deprecated locations

* format

* fmt

* Fix handoff bug in user proxy agent

* Update documentation

---------

* Propagate team cancellation token in agentchat

* Docs

---------

Co-authored-by: Ryan Sweet <rysweet@microsoft.com>

* Termination Conditions Tutorial (#4334)

* Fix format

* Update python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/termination.ipynb

* Update python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/termination.ipynb

* Update python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/termination.ipynb

* update docs

* update doc

---------

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* initial addition of a user proxy agent in agentchat, related to #3614

* fix typing/mypy errors

* format fixes

* format and pyright checks

* update, add support for returning handoff message, add tests

---------

Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
Co-authored-by: Hussein Mozannar <hmozannar@microsoft.com>

* Console to return last processed (#4277)

* Preserve input generator type

* Add tests

* format

---------

Co-authored-by: Jack Gerrits <jack@jackgerrits.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* initial assistant client draft

* expose assistants client

* initial openai assistant agentchat draft

* update file search

* add delete methods and fix typing

* add tool execution

* fix tool call and add docstring

* abstract tools and support thread management

* add tests

* removed unused typevars

* add unsaved test changes

* test typing fixes

---------

Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com>

* task can be ChatMessage; add group chat state validation step, and address swarm state valiation; change handling of start and reset to RPC to capture any error.

* Update tutorial note

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* fix select speaker for swarm

* Fix max-turn = 1 for swarm

* Max turn parameter for group chats

* Add note no usage

* Handoff termination and show how to use it for asking user input

* lint

* Initial implementation of SOM agent

* add tests

* edit prompt

* Update prompt

* lint

* Add task type that are messages to enable multi-modal tasks.

* fix test

* AgentChat pause and resume a task
Resolves #3859

* Add

* Update usage

* Update usage

* WIP to address stateful group chat

* Refactor group chat to add reset and flags for running

* documentation

* Agentchat refactor

* Move termination stop message to a separate field in task result

* Update quick start example

* Use string stop reason instead of stop message in task result for simpler API

* Use main function

* Termination condition as part of constructor

* Update doc

* Update notebooks

* Add token usage termination

* fix test

* Add token usage to messages

* small test edit

* AssistantAgent no longer sends out StopMessage. We use TextMentionTermination("TERMINATE") on the team instead for default setting.

* Fix test

* Custom selector function for SelectorGroupChat

* Update documentation

* Remove termination condition from team constructor

* fix usage