Tabela de funcionalidades do Microsoft Azure AI Foundry

See the following table for an overview of the capabilities offered by the connector when executing agents in agentic processes.

Feature Area	Recurso	Foundry AI Agent in Maestro
Autenticação	Single token, Bearer token (e.g. Personal Access Token).	Não
Autenticação	Service Principal-based authentication (e.g., service key, OAuth 2.0).	Sim
Autenticação	User-delegated, token-based authentication (e.g., On-Behalf-Of, OpenID).	Sim
Project Discovery	Discover available projects based on authentication.	No (provided by the user)
Agent Discovery	Discover available agents.	Yes (lists all agents in a project)
Invocation	Supports synchronous (request-response) invocation.	Não
Invocation	Supports streaming invocation (Server-Sent Events).	Não
Invocation	Supports asynchronous invocation with polling or webhook/callback.	Sim
Invocation	Ability to specify the agent's tools/skills within the API request.	Yes (in Prompt)
Session Management	Maintains conversational context via session IDs and allows for the retrieval of event history from an ongoing session.	Yes (use of thread_id within Manage Properties in Maestro)
Output Controls	Enforces structured, schema-adherent JSON output from agents.	Não
Content Handling	Supports multi-modal content exchange (e.g., binary files, images, audio).	Partial (possible if the developer encodes the output and sends it in the prompt)
Observability	Provides comprehensive observability through togglable verbose tracing, OTEL-formatted traces, and cross-platform correlation IDs.	Yes (in Azure Foundry Portal)
Consumption & Attribution	Tracks and attributes AI consumption (tokens/units) per response for cost analysis.	Yes (in Portal)
Controle de versão	Enables agent versioning for CI/CD workflows, targeted invocations by version number (e.g., GA, preview), and rollbacks.	Não
Tratamento de Erro	Delivers structured, detailed error messages (reason, domain, metadata) for advanced debugging and conditional logic.	Sim