* Move intervention to root

* usage

* 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>

* moves AgentId into Agent
* Renames AgentRuntime to AgentMessenger (more accurate name)
* Remove IAgentRuntime Interface
* changes constructor of Agent to take IAgentWorker instead of IAgentRuntime

* refactor renaming agent base

* 1st draft

* 1st draft

* format

* rename the tsts

* move IagentWorker

* 1st draft

* format

* gen-proto

* run gen-proto-samples

* format

* merge problem format

* 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>

* Move model context out of components

* move models out of components

* rename docs file

* Update agent doc

* Remove outdated doc

* Update references

* Update readme

* Update readme

* 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>

* Flatten core base and components

* remove extra files

* dont export from deprecated locations

* format

* fmt

* adds a python xlang sample and aspire code to host it
* fixes message delivery on dotnet runtime

* Replatform closure agent on base agent

* Fix mypy

* update agentcaht

---------

* delete files and update dependencies

* add explicit config exports

* ignore mypy error on nb

---------

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

* add ui streaming to distributed group chat example

Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>

* fix pyright error after updating dependencies

Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>

---------

Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>

* first notebook for distributed rock, paper and scissors

* add distributed group chat notebook

* fix formatting

* fix pipeline issues

* fix formatting issue

* promote distributed group chat notebook into a multiple files

* fix docs

* fix docs

* fix pyright

* Apply suggestions from code review

Add PR review suggestions

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

* improving group chat manager from round robin to LLM based

Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>

* remove lfs file to fix

Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>

* add gut back using lfs

Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>

* re-add gif using lfs

Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>

* remove gitattributes

Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>

* redo git lfs add

---------

Signed-off-by: Mohammad Mazraeh <mazraeh.mohammad@gmail.com>
Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

Added contributors to recognize the other devs who helped build the example

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

* Create Semantic Router example

* ruff formatting

* linting fixes

* pyright fixes

---------

* Restructure extensions, update corresponding docs

* update tests, add deprecation messages

* fix tests

* update lockfile

---------

* move docker code exec to autogen-ext

* fix test

* rename docker subpackage

* add missing renamed package

---------

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

* Add moa cookbook for multi-layer mixture-of-agents

* Update moa

* Check for prints

* format

* add subscription deduplication

* format

---------

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

* Update pyright extends for core

* Fixes

* Add response for registering agent type and adding subscriptions in distributed runtime

* Update unit tests

* lint

* Initial impl of new register and subscriptions

* progress

* test fixes, main issue was unbound self in routed agent

* fix issues

* remove sender from send_message call

* Fix agent type

---------

Co-authored-by: Aaron Gaetje <aagaetje@microsoft.com>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>

* fix docker samples, improve error message

* mypy fixes

* format

* mypy ignore

Co-authored-by: Mohammad Mazraeh <mmazraeh@microsoft.com>

* host agent runtime API and docs

* graceful shutdown of worker

* HostAgentRuntime --> WorkerAgentRuntimeHost

* Add unit tests for worker runtime

* Fix bug in worker runtime adding sender filed to proto. Documentation.

* wip

* Fix unit tests; refactor API

* fix formatting

* Fix

* Update

* Make source field optional in Event proto

* Fixed AZURE_OPENAI_API_ENDPOINT name. Added needed packages.

* remove hatch comment from doc

---------

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

* create model context component, remove chat memory component, refactor samples #454

* Fix bugs in samples.

* Fix

* Update docs

* add unit tests

* Add slow human in loop

* Fix

* Fix

* Fix

* Fix input

* Don't persist to json

* Add comment

* Fix imports

* Feedback

* Use if instead of while

* Add stop_when

* Merge from UV

* Multiple handlers

* Allow multiple intervention handleres to be supplied

* intervention_handler -> intervention_handlers

* Fix up

* Merge

* Merge

* Fix termination

* Handle feedback

* fmt

* Fix

* Fix

* Add initial message in the assistant memory

* Documentation

* fmt

* Update comment

* Downgrade protobuf from v5 to v4

* Address feedback

* Update python/packages/autogen-core/samples/demos/slow_human_in_loop.py

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

* Update python/packages/autogen-core/samples/demos/slow_human_in_loop.py

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

* Update python/packages/autogen-core/samples/demos/slow_human_in_loop.py

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

* Address comment

* Fix

* Fix to use lambda

---------

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

* Support datacontenttype and lay groundwork for unknown payloads

* Update dotnet based on proto changes

* Allow multiple intervention handleres to be supplied

* intervention_handler -> intervention_handlers

* Run format

---------

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

* Move packages to packages directory

* remove screenshot

* update some paths