Evan Mattson
435201b71b
* fix(a2a): reject empty invocations explicitly Key decisions: - Keep A2A continuation authority explicit; durable session task state only enriches diagnostics. - Raise AgentInvalidRequestException with participant and available task context instead of inventing input. - Leave AgentExecutor and Group Chat production contracts unchanged. Files changed: - packages/a2a/agent_framework_a2a/_agent.py - packages/a2a/tests/test_a2a_agent.py - packages/a2a/tests/test_a2a_group_chat.py Notes for next iteration: - No blockers. INPUT_REQUIRED pause/resume remains a separate task. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix(a2a): pause group chat for remote input Key decisions: - Translate A2A INPUT_REQUIRED task content into the existing Content user-input-request contract. - Use the remote task ID as stable request correlation for streamed and finalized responses. - Reuse AgentExecutor request handling so caller input resumes the same task without a workflow-specific A2A path. Files changed: - packages/a2a/agent_framework_a2a/_agent.py - packages/a2a/tests/test_a2a_agent.py - packages/a2a/tests/test_a2a_group_chat.py Notes for next iteration: - Checkpoint restoration of pending A2A input is now unblocked. - The local issue file could not be moved because repository issue files are restricted by content exclusion policy. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * fix(a2a): restore pending input from checkpoints Key decisions: - Keep normalized INPUT_REQUIRED content durable by excluding transport-only protobuf raw representations. - Restore through the existing AgentExecutor checkpoint and request-response path without a new schema or continuation API. - Cover file-backed restoration in streaming and non-streaming Group Chat runs, including unrelated-response rejection and exact task resumption. Files changed: - packages/a2a/agent_framework_a2a/_agent.py - packages/a2a/tests/test_a2a_group_chat.py Notes for next iteration: - The local issue file could not be moved because repository issue files are restricted by content exclusion policy. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * test(handoff): lock textless target context Key decisions: - Exercise the built Handoff workflow in streaming and non-streaming modes instead of bypassing routing, sessions, or termination. - Keep the slice test-only because current production already carries the initial task to a textless handoff target without synthetic user input. - Revisit the source to verify its handoff function call retains a matching result and user-turn termination sees only caller messages. Files changed: - packages/orchestrations/tests/test_handoff.py Notes for next iteration: - No production defect was reproduced. - The local issue file could not be moved because repository issue files are restricted by content exclusion policy. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * test(handoff): use resolved IDs in event assertions * fix(workflows): preserve A2A input request semantics * fix(workflows): preserve input request correlation * fix(a2a): deduplicate message-less input requests * fix(workflows): preserve specialized input requests * test(openai): use current web search model --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Get Started with Microsoft Agent Framework A2A
Please install this package via pip:
pip install agent-framework-a2a --pre
A2A Agent Integration
The A2A agent integration enables communication with remote A2A-compliant agents using the standardized A2A protocol. This allows your Agent Framework applications to connect to agents running on different platforms, languages, or services.
A2AAgent (Client)
The A2AAgent class is a client that wraps an A2A Client to connect the Agent Framework with external A2A-compliant agents.
from agent_framework.a2a import A2AAgent
# Connect to a remote A2A agent
a2a_agent = A2AAgent(url="http://remote-agent/a2a")
response = await a2a_agent.run("Hello!")
A2AExecutor (Hosting)
The A2AExecutor class bridges local AI agents built with the agent_framework library to the A2A protocol, allowing them to be hosted and accessed by other A2A-compliant clients.
from agent_framework.a2a import A2AExecutor
from a2a.server.apps import A2AStarletteApplication
from a2a.server.request_handlers import DefaultRequestHandler
from a2a.server.tasks import InMemoryTaskStore
# Create an A2A executor for your agent
executor = A2AExecutor(agent=my_agent)
# Set up the request handler and server application
request_handler = DefaultRequestHandler(
agent_executor=executor,
task_store=InMemoryTaskStore(),
)
app = A2AStarletteApplication(
agent_card=my_agent_card,
http_handler=request_handler,
).build()
Basic Usage Example
See the A2A agent examples which demonstrate:
- Connecting to remote A2A agents
- Hosting local agents via A2A protocol
- Sending messages and receiving responses
- Handling different content types (text, files, data)
- Streaming responses and real-time interaction
Security considerations
The hosting example above focuses on protocol wiring and does not add authentication or authorization by itself. Production A2A hosts should protect their HTTP or JSON-RPC entry points with the deployment's normal auth layer and verify that each caller is allowed to access the requested agent, task, or session.
Task, thread, context, and session identifiers used by an A2A host are routing handles, not bearer credentials. Do not rely on client-supplied identifiers alone to select or mutate persisted state; bind them to authenticated user, tenant, or workspace context first.