- Add a section on how to use model client with tools
- Replace the obsecure pattern of using ToolAgent with a simpler
implementation of calling tool within the agent itself.
sometimes a client will subscribe but the message it was hoping for is
already published and delivered to one of its peers but it missed it.
this adds a five second (default) buffer and will deliver buffered
messages to new subscribers. messages are removed from the buffer after
5 seconds
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Right now if a remote agent sends a message that local agents do not
listen to (and thus will never configure a deserializer for), or if the
first agent in the iteration is one such, the runtime will throw an
unnecessary exception an come down, even though the deserialized message
will never actually be needed before a deserializer is registered.
The fix will downgrade that to a warning.
* Also updates the HelloAgent sample to be more amenable to being used
with gRPC directly, without configuring environment variables.
* integration tests used to use the samples - now they are separate
* patch dictionary problem in serializer
* add Message Registry with dead letter queue that gets checked on new
subs.
This pull request includes a small change to the
`python/packages/magentic-one-cli/src/magentic_one_cli/_m1.py` file. The
change modifies the help message for the `--config` argument to remove
the part about leaving it empty to print a sample configuration. This is
already handled by `--sample-config`.
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
[PythonCodeExecutionTool](https://github.com/microsoft/autogen/blob/main/python/packages/autogen-ext/src/autogen_ext/tools/code_execution/_code_execution.py)
declarative so it can be used in tools like AGS
Summary of changes
- Make CodeExecutor declarative (convert from Protocol to ABC, inherit
from ComponentBase)
- Make LocalCommandLineCodeExecutor, JupyterCodeExecutor and
DockerCommandLineCodeExecutor declarative , best effort. Not all fields
are serialized, warnings are shown where appropriate.
- Make PythonCodeExecutionTool declarative.
<!-- Please give a short summary of the change and the problem this
solves. -->
## Related issue number
Closes#5526
<!-- 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.
Pulls the .NET Docs a bit more into the documentation website proper:
* Add a link from the 0.4-series Python docs to
* Adds a transient redirect from /dotnet/ to /dotnet/dev/ to forward to
the dev docs until we do a non "-dev" release
the uv sync logging in the test build was really noisy - no longer
needed
## Why are these changes needed?
## 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.
This finishes the fix for the race condition between opening a
GrpcWorkerConnection and registering agent types on that worker. Now,
instead of failing to register, we return from the call (with the
expectation that we will finish registration as we set up the
connection)
Part 1: #5494
Part 2: #5514
---------
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. -->
## 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.
* There was an inconsistentcy between the package names that prevented
xlang from working even though the actual types were 1:1 compatible
* Also moves the HelloAgent aspire project into the Hello solution
folder
Fixed a wrong class name style in the document and removed trailing whitespace.
Co-authored-by: Wei Jen Lu <weijenlu@microsoft.com>
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. -->
Adds the following blurb to the model clients docs
## API Keys From Environment Variables
In the examples above, we show that you can provide the API key through
the `api_key` argument. Importantly, the OpenAI and Azure OpenAI clients
use the [openai
package](3f8d8205ae/src/openai/__init__.py (L260)),
which will automatically read an api key from the environment variable
if one is not provided.
- For OpenAI, you can set the `OPENAI_API_KEY` environment variable.
- For Azure OpenAI, you can set the `AZURE_OPENAI_API_KEY` environment
variable.
This is a good practice to explore, as it avoids including sensitive api
keys in your code.
## Why are these changes needed?
<!-- 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.
Right now we rely on opening the channel to associate a ClientId with an
entry on the gateway side. This causes a race when the channel is being
opened in the background while an RPC (e.g. MyAgent.register()) is
invoked.
If the RPC is processed first, the gateway rejects it due to "invalid"
clientId.
This fix makes this condition less likely to trigger, but there is still
a piece of the puzzle that needs to be solved on the Gateway side.
<!-- 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?
It is useful to rapidly validate any changes to a team structure as
teams are built either via drag and drop or by modifying the underlying
spec
You can now “validate” your team. The key ideas are as follows
- Each team is based on some Component Config specification which is a
pedantic model underneath.
- Validation is 3 pronged based on a ValidatorService class
- Data model validation (validate component schema)
- Instantiation validation (validate component can be instantiated)
- Provider validation, component_type validation (validate that provider
exists and can be imported)
- UX: each time a component is **loaded or saved**, it is automatically
validated and any errors shown (via a server endpoint). This way, the
developer immediately knows if updates to the configuration is wrong or
has errors.
> Note: this is different from actually running the component against a
task. Currently you can run the entire team. In a separate PR we will
implement ability to run/test other components.
<img width="1360" alt="image"
src="https://github.com/user-attachments/assets/d61095b7-0b07-463a-b4b2-5c50ded750f6"
/>
<img width="1368" alt="image"
src="https://github.com/user-attachments/assets/09a1677e-76e8-44a4-9749-15c27457efbb"
/>
<!-- Please give a short summary of the change and the problem this
solves. -->
## Related issue number
Closes#4616
<!-- 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.
We were registering the serializers when we already had a concrete type
on the way into Publish or Send on the .NET side. However, in a xLang
scenario, messages could originate from e.g. Python before being
sent/published from .NET, resulting in no serializer being found.
This change adds a second-change registration and lookup when the agent
is instantiated based on the IHandle<T> implementations.
We don't provide links to the dev releases on the site anymore, so let's
save some CI time and clutter
---------
Co-authored-by: Victor Dibia <victordibia@microsoft.com>
Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Closes#5297
---------
Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
Co-authored-by: Jacob Alber <jaalber@microsoft.com>
Co-authored-by: Jacob Alber <jacob.alber@microsoft.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Unlike with the InProcessRuntime, there is a two-phase initialization,
first when AgentsApp is built (when initial agents are registered) and
when it StartAsync()s and connects to the Gateway. Unfortunately, it is
possible to attempt to send direct RPC calls to the Gateway before the
message channel is opened; in this case, the Gateway has no connected
client corresponding to the RPC's clientId, and falls over.
The fix is to defer registering agents and subscriptions with the
gateway until after the connection is established after .StartAsync() is
called.
Add the following additional configuration options to
DockerCommandLineCodeExectutor:
- **extra_volumes** (Optional[Dict[str, Dict[str, str]]], optional): A
dictionary of extra volumes (beyond the work_dir) to mount to the
container. Defaults to None.
- **extra_hosts** (Optional[Dict[str, str]], optional): A dictionary of
host mappings to add to the container. (See Docker docs on extra_hosts)
Defaults to None.
- **init_command** (Optional[str], optional): A shell command to run
before each shell operation execution. Defaults to None.
## Why are these changes needed?
See linked issue below.
In summary: Enable the agents to:
- work with a richer set of sys admin tools on top of code execution
- add support for a 'project' directory the agents can interact on
that's accessible by bash tools and custom scripts
## Related issue number
Closes#5363
## Checks
- [x] 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.
- [x] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [x] I've made sure all auto checks have passed.
This PR improves documentation on custom agents
- Shows example on how to create a custom agent that directly uses a
model client. In this case an example of a GeminiAssistantAgent that
directly uses the Gemini SDK model client.
- Shows that that CustomAgent can be easily added to any agentchat team
- Shows how the same CustomAgent can be made declarative by inheriting
the Component interface and implementing the required methods.
Closes#5450
<!-- 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. -->
## Related issue number
<!-- For example: "Closes #1234" -->
Fix#4731
## 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.
## Why are these changes needed?
These changes are needed because currently there's no generic way to add
`tools` to autogen studio workflows using the existing DSL and schema
other than inline python.
This API will be quite verbose, and lacks a discovery mechanism, but it
unlocks a lot of programmatic use-cases.
## Related issue number
https://github.com/microsoft/autogen/issues/5170
Co-authored-by: Victor Dibia <victordibia@microsoft.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Have seen discussion on Discord regarding confusion about multi-modal
support in v0.4. This change adds a small note on how to use multi-modal
messages with agents.
<!-- 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 current implementation tries to recreate the metadata but it does it
in an incomplete way. This PR uses SK built-in kernel from function
decorator to infer the callable from the `run_json` and makes better use
of the pydantic schemas for the input and output to infer the schema of
the kernel function.
## Related issue number
<!-- For example: "Closes #1234" -->
Closes#5458
## 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: Leonardo Pinheiro <lpinheiro@microsoft.com>
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. -->
Add clear notes on how to specify api key and modifying specifications
in AGS.
Add diagrams explaining how to switch between visual builder and JSON
mode
## Why are these changes needed?
<!-- Please give a short summary of the change and the problem this
solves. -->
## Related issue number
<!-- For example: "Closes #1234" -->
@nour-bouzid
## 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.
<!-- 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. -->
It is often helpful to inspect the raw request and response to/from an
LLM as agents act.
This PR, does the following:
- Updates TeamManager to yield LLMCallEvents from core library
- Run in an async background task to listen for LLMCallEvent JIT style
when a team is run
- Add events to an async queue and
- yield those events in addition to whatever actual agentchat
team.run_stream yields.
- Update the AGS UI to show those LLMCallEvents in the messages section
as a team runs
- Add settings panel to show/hide llm call events in messages.
- Minor updates to default team
<img width="1539" alt="image"
src="https://github.com/user-attachments/assets/bfbb19fe-3560-4faa-b600-7dd244e0e974"
/>
<img width="1554" alt="image"
src="https://github.com/user-attachments/assets/775624f5-ba83-46e8-81ff-512bfeed6bab"
/>
<img width="1538" alt="image"
src="https://github.com/user-attachments/assets/3becbf85-b75a-4506-adb7-e5575ebbaec4"
/>
## Why are these changes needed?
<!-- Please give a short summary of the change and the problem this
solves. -->
## Related issue number
<!-- For example: "Closes #1234" -->
Closes#5440
## 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.
<!-- 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 current stream processing of SK model adapter returns on the first
function call chunk but this behavior is incorrect end ends up returning
with an incomplete function call. The observed behavior is that the
function name and arguments are split into different chunks and this
update correctly processes the chunks in this way.
## Related issue number
<!-- For example: "Closes #1234" -->
Fixes the reply in #5420
## 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: Leonardo Pinheiro <lpinheiro@microsoft.com>
