Tag: microsoft-agent-framework

Magentic orchestration is Agent Framework's port of AutoGen's Magentic-One: an LLM manager writes a fact sheet and plan (the task ledger), then grades every round with a JSON progress ledger to pick the next agent, detect stalls and replan. Here is how the loop works on Microsoft.Agents.AI.Workflows 1.24.0 and agent-framework-orchestrations 1.3.1, what it costs per round, and the limit defaults that let it run forever.

The Agent Harness is Microsoft Agent Framework's batteries-included runtime: one call (AsHarnessAgent in .NET, create_harness_agent in Python) wraps any chat client in a tool loop with todos, plan/execute modes, file memory, tool approval, compaction and OpenTelemetry. Here is what it actually sends to the model on Microsoft.Agents.AI.Harness 1.23.0, what it costs per call, and how to trim it.

In a workflow, your code decides the next step and the model fills in each step. In an agent, the model decides the next step and your code only executes it. That one question (who owns the control flow) determines cost, latency, testability and failure modes. Here is the distinction as Anthropic, Microsoft Agent Framework and LangGraph define it, with the same task built both ways in Python against claude-haiku-4-5 and claude-sonnet-5-5.

The agent-framework-hosting packages are conversion helpers, not a runtime. One Agent instance, one AgentState, and three thin adapters give you a Telegram bot, an A2A peer, and an MCP tool from the same process. Here is the wiring, the per-channel session-ID policy, and the four things each channel refuses to do.

Agent Framework ships an in-memory chat history provider and nothing else for .NET. Here is a Cosmos DB backed ChatHistoryProvider that survives process restarts, the container design that keeps a 200-turn session cheap, and the second provider you need if you want semantic recall across sessions.

Conversation history can live in your process, in your database, in the provider, or on the machine that ran the agent. Where you put it does not change your token bill, it decides your retention exposure, and it decides whether you can ever change providers. The numbers, the retention windows, and a storage shape that survives all three.

Defensive system prompts are heuristic. Information-flow control is not: label every piece of content with integrity and confidentiality, propagate most-restrictive-wins through every tool call, and check the label at the sink before it runs. An 80-line runnable harness, the Agent Framework FIDES implementation, and the false positives the pattern buys you.

Stop shipping SKILL.md folders inside every agent deployment. Serve them from an MCP server and pull them with UseMcpSkills on Microsoft.Agents.AI.Mcp 1.18. Includes the exact skill://index.json shape, a working C# server, the wire trace, and the SEP-2640 drift that will bite you.

Replace a hand-rolled classifier-plus-switch router with AgentWorkflowBuilder.CreateHandoffBuilderWith in Microsoft.Agents.AI.Workflows 1.17.0. What breaks, the six migration steps, and the gotchas around agent Ids, descriptions, and context broadcast.

Use declarative YAML when the graph is a sequential routing decision that non-developers change often. Use code-first WorkflowBuilder the moment you need parallelism, custom executors, or a non-Foundry agent. Here is the decision, the action catalog limits, and the code both ways.