* Move the AsAIAgent extension methods to the correct class
* Fix format issue
* Disable unit test, see issue #1109
---------
Co-authored-by: Mark Wallace <markwallace@microsoft.com>
* Re-enable ImplicitUsings in samples and clean up NoWarns
* Fix dotnet format
* More dotnet format
* More dotnet format
---------
Co-authored-by: Chris <66376200+crickman@users.noreply.github.com>
We shouldn't be shipping any more dependencies on this package, as it's becoming legacy, replaced by System.Linq.AsyncEnumerable.
We'll eventually want to replace it with System.Linq.AsyncEnumerable in all tests/samples, too, but that's hard to do until SK updates to use S.L.AsyncEnumerable once its 10.0.0 version is released. I did remove the package reference from tests/samples where it's not needed.
* Use copilot to improve XML docs for M.Agents.AI{.Abstractions}
Asked copilot to help improve some of the docs, then I reviewed them.
I also cleaned up a few things along the way, like a couple of extension method types that should be combined.
* Update dotnet/src/Microsoft.Agents.AI.Abstractions/InMemoryChatMessageStore.cs
---------
Co-authored-by: Mark Wallace <127216156+markwallace-microsoft@users.noreply.github.com>
* Update M.A.AI.OpenAI implementations
- There was only a ChatClient-based agent. Add a Responses one, too.
- Fix the public extension methods to create OpenAI types even when not backed by the right OpenAI client.
- Add reusable AgentRunResponse{Update} to ChatResponse{Update} conversion routines that are then used by the OpenAI agents and elsewhere
* Address feedback
* Adding more test for workflow vizualization.
* Improving README for sample.
* More cleanup.
* Removing rendering of workflow visualization and adding basic support for mermaid format.
* Adding basic mermaid tests.
* Improving sample. Switching to another branch.
* About to merge from main.
* Formatting.
* More fromatting.
* Removng uneeded call to ToUpper.
* Adding README.
* Moving samples under workflow to workflows.
* Removing uneeded README for map-reduce sample.
* Update OpenTelemetryAgent to latest spec
It was stale. Rather than try to keep it up-to-date manually, I've changed it to piggy back on OpenTelemetryChatClient, so that it inherits everything OpenTelemetryChatClient does and then augments it just with agent-specific tags.
* Address feedback / merge
* Make serialize methods sync and rename one to match others.
* Remove unnecessary async postfixes.
* Remove nullability of ChatMessageStore.Serialize return type, since the default JsonElement already represents an undefined json element.
* Fix unit test
* Disallow execution of multiple workflows at once
* Define notion of executor Reset() to allow reuse of workflows with shared executor instances
* Switch to delivering all messages to a single executor sequentially, with executors running in parallel
* Rename AI Agent packages to use Microsoft.Agents.AI
* Fix for build
* Fix formatting
* Fix formatting
* Ignore in VSTHRD200 in migration samples
* Ignore in VSTHRD200 in migration samples
* Add some missing projects and run format
* Fix build errors
* Address code review feedback
* Fix merge issues
---------
Co-authored-by: Mark Wallace <markwallace@microsoft.com>
* feat: Make Executor id field mandatory
When checkpointing is involved, it is critical to keep executor ids consistent between runs, even when recreating a new object tree for the workflow.
The default id-setting mechanism generated a guid for part of the id, making it not work when restoring from a checkpoint.
This change prevents this situation from arising.
* feat: Enable running untyped Workflows
With the change to enable delay-instantiation of executors and support for async Executor factory methods, we must instantiate the starting executor to know what are the valid input types for the workflow.
To avoid forcing instantiation every time, and to better support workflows with multiple input types, we enable support for build and interacting with the base Workflow type without type annotations, and remove the requirement to know a valid input type when initiating a run.
* feat: Support Output from any executor and multiple outputs.