AIContextProvider Class
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
Provides an abstract base class for components that enhance AI context during agent invocations.
public abstract class AIContextProvidertype AIContextProvider = classPublic MustInherit Class AIContextProvider- Inheritance
-
AIContextProvider
- Derived
Remarks
An AI context provider is a component that participates in the agent invocation lifecycle by:
- Listening to changes in conversations
- Providing additional context to agents during invocation
- Supplying additional function tools for enhanced capabilities
- Processing invocation results for state management or learning
Context providers operate through a two-phase lifecycle: they are called at the start of invocation via InvokingAsync(AIContextProvider+InvokingContext, CancellationToken) to provide context, and optionally called at the end of invocation via InvokedAsync(AIContextProvider+InvokedContext, CancellationToken) to process results.
Security considerations: Context providers may inject messages with any role, including system, which has the highest trust level and directly shapes LLM behavior. Developers must ensure that all providers attached to an agent are trusted. Agent Framework does not validate or filter the data returned by providers — it is accepted as-is and merged into the request context. If a provider retrieves data from an external source (e.g., a vector database or memory service), be aware that a compromised data source could introduce adversarial content designed to manipulate LLM behavior via indirect prompt injection. Implementers should validate and sanitize data retrieved from external sources before returning it.
Constructors
| Name | Description |
|---|---|
| AIContextProvider(Func<IEnumerable<ChatMessage>,IEnumerable<ChatMessage>>, Func<IEnumerable<ChatMessage>,IEnumerable<ChatMessage>>, Func<IEnumerable<ChatMessage>, IEnumerable<ChatMessage>>) |
Initializes a new instance of the AIContextProvider class. |
Properties
| Name | Description |
|---|---|
| ProvideInputMessageFilter |
Gets the filter function to apply to input messages before providing context via ProvideAIContextAsync(AIContextProvider+InvokingContext, CancellationToken). |
| StateKeys |
Gets the set of keys used to store the provider state in the StateBag. |
| StoreInputRequestMessageFilter |
Gets the filter function to apply to request messages before storing context via StoreAIContextAsync(AIContextProvider+InvokedContext, CancellationToken). |
| StoreInputResponseMessageFilter |
Gets the filter function to apply to response messages before storing context via StoreAIContextAsync(AIContextProvider+InvokedContext, CancellationToken). |
Methods
| Name | Description |
|---|---|
| GetService(Type, Object) |
Asks the AIContextProvider for an object of the specified type |
| GetService<TService>(Object) |
Asks the AIContextProvider for an object of type |
| InvokedAsync(AIContextProvider+InvokedContext, CancellationToken) |
Called at the end of the agent invocation to process the invocation results. |
| InvokedCoreAsync(AIContextProvider+InvokedContext, CancellationToken) |
Called at the end of the agent invocation to process the invocation results. |
| InvokingAsync(AIContextProvider+InvokingContext, CancellationToken) |
Called at the start of agent invocation to provide additional context. |
| InvokingCoreAsync(AIContextProvider+InvokingContext, CancellationToken) |
Called at the start of agent invocation to provide additional context. |
| ProvideAIContextAsync(AIContextProvider+InvokingContext, CancellationToken) |
When overridden in a derived class, provides additional AI context to be merged with the input context for the current invocation. |
| StoreAIContextAsync(AIContextProvider+InvokedContext, CancellationToken) |
When overridden in a derived class, processes invocation results at the end of the agent invocation. |