Tag: llm

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.

A context window is everything the model can see in one request: system prompt, tool definitions, history, tool results, thinking and the reply. Here is what counts, what happens at the limit on claude-opus-5-5 and friends, and the six techniques agents use to work past it: deferred tools, context editing, compaction, memory, subagents and output filtering.

Tool calling is a protocol, not magic: the model emits a structured request matching a JSON Schema you supplied, your code runs it, and the result goes back as a message. The schema and its descriptions are rendered into the model's prompt and, with strict mode, into a decoding grammar, so they shape behaviour more reliably than any system-prompt instruction. Here is how it works on claude-sonnet-5-5 and OpenAI strict mode, with schema patterns that make invalid calls impossible.

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.

An agent skill is a folder with a SKILL.md file that the agent loads on demand: only its name and description sit in the system prompt, the instructions arrive when a task matches, and bundled scripts run without ever entering context. Here is how that differs from a system prompt in cost, scope, invocation and trust, with the exact limits from the Agent Skills spec and Claude Code.

MCP is a JSON-RPC protocol that lets any AI host call tools, read resources and use prompts from any server, the way LSP did for language support. Here is how it works on the wire under revision 2026-07-28, captured from a real server, and why VS Code, Visual Studio, JetBrains, Xcode, Zed and Cursor all converged on it.

Every agent request pays for its system prompt, the provider's hidden tool-use preamble, and every tool schema before the user says anything. How to measure that fixed cost with differential count_tokens calls on the Anthropic API, the input_tokens endpoint on OpenAI, an MCP listTools probe, and /context in Claude Code, anchored to claude-opus-5-5, claude-sonnet-5, and @modelcontextprotocol/client 2.1.0.

BYOK lets you point GitHub Copilot at a local Ollama model in VS Code, the Copilot CLI, and the Copilot app. You keep chat and agent mode. You lose inline completions, semantic search, embeddings, /delegate, and roughly 20 points of SWE-bench. Here is the exact trade.

Since August 21, 2026 mentioning @GitHub in Slack starts a Copilot cloud agent session the whole channel can steer. Here is the setup, the Slack Code channel model, why the pull request comes from an app identity instead of you, what the thread context capture actually exposes, and how the two separate billing meters add up.