Resolves #5919

1. Add `on_pause` and `on_resume` API to `ChatAgent` to support pausing
behavior when running `on_message` concurrently.
2. Add `GroupChatPause` and `GroupChatResume` RPC events and handle them
in `ChatAgentContainer`.
3. Add `pause` and `resume` API to `BaseGroupChat` to allow for this
behavior accessible from the public API.
4. Improve `SequentialRoutedAgent` class to customize which message
types are sequentially handled, making it possible to have concurrent
handling for some messages (e.g., `GroupChatPause`).
5. Added unit tests. 

See `test_group_chat_pause_resume.py` for how to use this feature. 

What is the difference between pause/resume vs. termination and restart?
- Pause and resume issue direct RPC calls to the participanting agents
of a team while they are running, allowing putting the on-going
generation or actions on hold. This is useful when an agent's turn takes
a long time and multiple steps to complete, and user/application wants
to re-evaluate whether it is worth continue the step or cancel. This
also allows user/application to pause individual agents and resuming
them independently from the team API.
- Termination and restart requires the whole team to comes to a
full-stop, and termination conditions are checked in between agents'
turns. So termination can only happen when no agent is working on its
turn. It is possible that a termination condition has reached well
before the team is terminated, if the agent is taking a long time to
generate a response.

Resolves: #5881

Modify `BaseGroupChat.save_state` to not require the team to be stopped
first. The `save_state` method is read-only. While it may retrieve an
inconsistent state when the team is running, we made a notice to it's
API doc.

Resolves: #5880

Resolves #4075

1. Introduce custom runtime parameter for all AgentChat teams
(RoundRobinGroupChat, SelectorGroupChat, etc.). This is done by making
sure each team's topics are isolated from other teams, and decoupling
state from agent identities. Also, I removed the closure agent from the
BaseGroupChat and use the group chat manager agent to relay messages to
the output message queue.
2. Added unit tests to test scenarios with custom runtimes by using
pytest fixture
3. Refactored existing unit tests to use ReplayChatCompletionClient with
a few improvements to the client.
4. Fix a one-liner bug in AssistantAgent that caused deserialized agent
to have handoffs.

How to use it? 

```python
import asyncio
from autogen_core import SingleThreadedAgentRuntime
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_agentchat.conditions import TextMentionTermination
from autogen_ext.models.replay import ReplayChatCompletionClient

async def main() -> None:
    # Create a runtime
    runtime = SingleThreadedAgentRuntime()
    runtime.start()

    # Create a model client.
    model_client = ReplayChatCompletionClient(
        ["1", "2", "3", "4", "5", "6", "7", "8", "9", "10"],
    )

    # Create agents
    agent1 = AssistantAgent("assistant1", model_client=model_client, system_message="You are a helpful assistant.")
    agent2 = AssistantAgent("assistant2", model_client=model_client, system_message="You are a helpful assistant.")

    # Create a termination condition
    termination_condition = TextMentionTermination("10", sources=["assistant1", "assistant2"])

    # Create a team
    team = RoundRobinGroupChat([agent1, agent2], runtime=runtime, termination_condition=termination_condition)

    # Run the team
    stream = team.run_stream(task="Count to 10.")
    async for message in stream:
        print(message)
    
    # Save the state.
    state = await team.save_state()

    # Load the state to an existing team.
    await team.load_state(state)

    # Run the team again
    model_client.reset()
    stream = team.run_stream(task="Count to 10.")
    async for message in stream:
        print(message)

    # Create a new team, with the same agent names.
    agent3 = AssistantAgent("assistant1", model_client=model_client, system_message="You are a helpful assistant.")
    agent4 = AssistantAgent("assistant2", model_client=model_client, system_message="You are a helpful assistant.")
    new_team = RoundRobinGroupChat([agent3, agent4], runtime=runtime, termination_condition=termination_condition)

    # Load the state to the new team.
    await new_team.load_state(state)

    # Run the new team
    model_client.reset()
    new_stream = new_team.run_stream(task="Count to 10.")
    async for message in new_stream:
        print(message)
    
    # Stop the runtime
    await runtime.stop()

asyncio.run(main())
```

TODOs as future PRs:
1. Documentation.
2. How to handle errors in custom runtime when the agent has exception?

---------

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

Resolves #5731

Resolves #5782

---------

Co-authored-by: Victor Dibia <victordibia@microsoft.com>

Resolves #5777

Add function call termination condition.

Useful as an alternative to TextMentionTermination for models with tool
call capability.

Closes #5732 
---------

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

<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->

<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->

## Why are these changes needed?

<!-- Please give a short summary of the change and the problem this
solves. -->

The PR introduces two changes.

The first change is adding a name attribute to
`FunctionExecutionResult`. The motivation is that semantic kernel
requires it for their function result interface and it seemed like a
easy modification as `FunctionExecutionResult` is always created in the
context of a `FunctionCall` which will contain the name. I'm unsure if
there was a motivation to keep it out but this change makes it easier to
trace which tool the result refers to and also increases api
compatibility with SK.

The second change is an update to how messages are mapped from autogen
to semantic kernel, which includes an update/fix in the processing of
function results.

## Related issue number

<!-- For example: "Closes #1234" -->

Related to #5675 but wont fix the underlying issue of anthropic
requiring tools during AssistantAgent reflection.

## Checks

- [ ] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> 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.

---------

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

## Why are these changes needed?

The CodeExecutorAgent documentation needs to be updated to explicitly
mention that it only processes code properly formatted in markdown code
blocks with triple backticks. This change adds a clear note with
examples to help users understand the required format for code
execution.

## Related issue number

Closes #5771


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

<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->

<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->

## Why are these changes needed?

Make FileSurfer and CodeExecAgent Declarative.
These agent presents are used as part of magentic one and having them
declarative is a precursor to their use in AGS.

<!-- Please give a short summary of the change and the problem this
solves. -->

## Related issue number

<!-- For example: "Closes #1234" -->
Closes #5607

## Checks

- [ ] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> 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.

Closes #4904 

Does not change default behavior in core.

In agentchat, this change will mean that exceptions that used to be
ignored and result in bugs like the group chat stopping are now reported
out to the user application.

---------

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

<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->

<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->

## Why are these changes needed?

<!-- Please give a short summary of the change and the problem this
solves. -->

I'm unsure if everyone will agree, but I started to look into adding new
logic and found that refactoring into smaller functions would make it
more maintainable.

There is no change in functionality, only a breakdown into smaller
methods to make it more modular and improve readability. There is a lot
of logic in the method and this refactor breaks it down into context
management, llm call and result processing.

## Related issue number

<!-- For example: "Closes #1234" -->

## Checks

- [ ] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> 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.

---------

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

## Why are these changes needed?

For the sake of subsequent people reading the metacode and following
programming specifications, variable names are updated in combination
with usage scenarios. Mainly contains the variable "_self_text" in
TextMentionTermination

Add metadata field to BaseMessage.

Why?
- additional metadata field can track 1) timestamp if needed, 2) flags
about the message. For instance, a use case is a metadata field
{"internal":"yes"} that would hide messages from being displayed in an
application or studio.

As long as an extra field is added to basemessage that is not consumed
by existing agents, I am happy.



Notes:
- We can also only add it to BaseChatMessage, that would be fine
- I don't care what the extra field is called as long as there is an
extra field somewhere
- I don't have preference for the type, a str could work, but a dict
would be more useful.

---------

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

Resolves #5610

And address various questions regarding to how to use user proxy agent
and human-in-the-loop.

Resolves #5562

## Why are these changes needed?
See issue for a bug description.
The problem was that a lot of openrouter models return `""` as
`tool_call.arguments`, which caused `json.loads` to fail
## Related issue number
https://github.com/microsoft/autogen/issues/5666
---------

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

Resolves #5192

Test

```python
import asyncio
import os
from random import randint
from typing import List
from autogen_core.tools import BaseTool, FunctionTool
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.ui import Console

async def get_current_time(city: str) -> str:
    return f"The current time in {city} is {randint(0, 23)}:{randint(0, 59)}."

tools: List[BaseTool] = [
    FunctionTool(
        get_current_time,
        name="get_current_time",
        description="Get current time for a city.",
    ),
]

model_client = OpenAIChatCompletionClient(
    model="anthropic/claude-3.5-haiku-20241022",
    base_url="https://openrouter.ai/api/v1",
    api_key=os.environ["OPENROUTER_API_KEY"],
    model_info={
        "family": "claude-3.5-haiku",
        "function_calling": True,
        "vision": False,
        "json_output": False,
    }
)

agent = AssistantAgent(
    name="Agent",
    model_client=model_client,
    tools=tools,
    system_message= "You are an assistant with some tools that can be used to answer some questions",
)

async def main() -> None:
    await Console(agent.run_stream(task="What is current time of Paris and Toronto?"))

asyncio.run(main())
```

```
---------- user ----------
What is current time of Paris and Toronto?
---------- Agent ----------
I'll help you find the current time for Paris and Toronto by using the get_current_time function for each city.
---------- Agent ----------
[FunctionCall(id='toolu_01NwP3fNAwcYKn1x656Dq9xW', arguments='{"city": "Paris"}', name='get_current_time'), FunctionCall(id='toolu_018d4cWSy3TxXhjgmLYFrfRt', arguments='{"city": "Toronto"}', name='get_current_time')]
---------- Agent ----------
[FunctionExecutionResult(content='The current time in Paris is 1:10.', call_id='toolu_01NwP3fNAwcYKn1x656Dq9xW', is_error=False), FunctionExecutionResult(content='The current time in Toronto is 7:28.', call_id='toolu_018d4cWSy3TxXhjgmLYFrfRt', is_error=False)]
---------- Agent ----------
The current time in Paris is 1:10.
The current time in Toronto is 7:28.
```

---------

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

Fixes #5366 

Solution: Instead of raising an error called `_init()`

---------

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

Resolves #5508

Resolves #4447

For `openai` client's structured output support is through its beta
client, which requires the function JSON schema to be strict when in
structured output mode.

Reference:
https://platform.openai.com/docs/guides/function-calling#strict-mode

Some LLMs recieve an explicit signal about tool use failures. 

Closes #5273

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

Don't throw an exception when model makes a mistake. Use retries, and if
not succeeding after a fixed attempts, fall back to the previous sepaker
if available, or the first participant.

Resolves #5453

Resolves #5425

Get's SelectorGroupChat working for llama by:

1. Using a UserMessage rather than a SystemMessage
2. Normalizing how roles are presented (one agent per line)
3. Normalizing how the transcript is constructed (a blank line between
every message)

Some agent descriptions were split over multiple lines in the M1
orchestrator. This PR ensures that each description appears on one, and
only one, line. This makes it easier for smaller models to understand.

<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->

<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->

## Why are these changes needed?

Currently the way to accomplish RAG behavior with agent chat,
specifically assistant agents is with the memory interface, however
there is no way to configure it via the declarative API.

<!-- Please give a short summary of the change and the problem this
solves. -->

## Related issue number

<!-- For example: "Closes #1234" -->

## 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.

---------

Co-authored-by: Victor Dibia <chuvidi2003@gmail.com>

Modify M1 agents to support text-only settings.
This allows M1 to be used with models like o3-mini and Llama3.1+

Allow AssistantAgent to drop images when not equipped with a multi-modal model.

Adds a corresponding utility function, which can be used in autogen-ext and teams, to accomplish the same.

This PR does the following: 

- Fix warning messages in AGS on launch.
- Improve Cli message to include app URL on startup from command line
- Minor improvements default gallery generator. (add more default tools)
- Improve new session behaviour.



## Related issue number

Closes #5097

## Checks

Resolves #5322

This PR adds a `sources` optional parameter to CodeExecutorAgent
(similar to the termination conditions), that allows finer-grained
control on which agents can provide code for execution.

It also moves the `_extract_markdown_code_blocks` subroutine to a member
method, so that it can be overridden by subclasses. I've found this to
be very important to support benchmarks like HumanEval, where we need to
add a test harness around the implementation.

Resolves #3983

* introduce `model_client_stream` parameter in `AssistantAgent` to
enable token-level streaming output.
* introduce `ModelClientStreamingChunkEvent` as a type of `AgentEvent`
to pass the streaming chunks to the application via `run_stream` and
`on_messages_stream`. Although this will not affect the inner messages
list in the final `Response` or `TaskResult`.
* handle this new message type in `Console`.

<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->

<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->

## Why are these changes needed?

Make AssistantAgent and Handoff use BaseTool.  
This ensures that they can be made declarative/serialized

<!-- Please give a short summary of the change and the problem this
solves. -->

## Related issue number

<!-- For example: "Closes #1234" -->

## 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.

* initial pass on making group chats declarative

* update group chat tests

* update impl to include participant serialization for all teams

* v1 making soc declarative

* update memory test

* update chatagent and team base classes

* update serialization doc notebook

* fomating updates

Update _magentic_one_orchestrator.py

In a Magentic Group Settting, if one of the Assitant Agents uses a tool it gives the following error, note this is under a FALSE reflect_on_tool variable.

Making it true, wont happen, though more tokens will be consumed and it will have a worst output and the philosophy of a tool as an answer is not followed...

* make memory and team an ABC

* update memory test

* update tests

* docs: update AssistantAgent documentation with attention and warning notes

* update

---------

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

* Pass context between AssistantAgent for handoffs

* Add parallel tool call test

---------

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

* v1, make assistant agent declarative

* make head tail context declarative

* update and formatting

* update assistant, format updates

* make websurfer declarative

* update formatting

* move declarative docs to advanced section

* remove tools until implemented

* minor updates to termination conditions

* update docs

Retry multiple times when M1 selects an invalid agent. Make agent selection deterministic when the team is a singleton (corner case).