{"slug": "microsoft-copilot-sdk-2-0-rust-runtime-and-what-changes", "title": "Microsoft Copilot SDK 2.0: Rust Runtime and What Changes", "summary": "Microsoft released Copilot SDK 2.0 at Ignite, rewriting the runtime in Rust and cutting session-start overhead from 5.25 seconds in the 1.x TypeScript CLI to 55.3 milliseconds, the basis for Microsoft's \"95x faster\" claim. The release adds a `mode: \"empty\"` session isolation model that starts each session with zero capabilities and requires explicit tool opt-in, plus durable sessions that survive process restarts via `resume_session()`. Microsoft set February 2027 as the migration cutoff for GitHub Copilot SDK 1.x, and shipped Agent Controls, a managed Azure service built on the open Agent Control Specification that evaluates policies at four points in every agent turn.", "body_md": "Microsoft shipped Copilot SDK 2.0 at Ignite last week, alongside a name change, a full runtime rewrite in Rust, and a session model that finally makes multi-tenant agent apps practical to build and ship. If you are still on the GitHub Copilot SDK 1.x, you are on a maintenance branch with a deadline: VS Code deprecated the old local agent harness in its November update, and **February 2027** is the migration cutoff.\n\n## The Rust Runtime — What 95x Actually Means\n\nMicrosoft is leading with a “95x faster” headline, and the number is real — but it needs context before you repeat it in a planning meeting.\n\nThe 1.x SDK ran each session in its own container or process. Spinning that up was expensive: creating a client, starting a session, and completing one turn took 5.25 seconds in the TypeScript CLI. The 2.0 Rust core does the same workload in 55.3 milliseconds — that is where the 95x ratio comes from.\n\nWhat this does not measure: model inference. Your GPT-6.2 or Claude Fable calls are not getting 95x faster. The improvement is in the agent scaffolding overhead — the tax you pay every time a session starts. For a single developer building a personal assistant, that is barely noticeable. For a SaaS platform spinning up thousands of short-lived agent sessions per hour, it is a compounding cost and latency win that actually shows up in bills and p99 numbers.\n\n## Mode “empty” Makes Multi-Tenant Agent Apps Safe to Ship\n\nThe more important change — especially if you are building a product that runs agent sessions on behalf of multiple users — is the new session isolation model.\n\nIn 1.x, sessions inherited the ambient capabilities of the host: its shell, its filesystem, its default tools. For single-user tools, that is fine. For multi-tenant apps, it is a liability. One user’s session could see tools registered by another, and you were responsible for patching that gap yourself.\n\nSDK 2.0 introduces `mode: \"empty\"`. It starts every session with zero capabilities — no shell, no filesystem, no tools — and requires you to explicitly opt in:\n\n``` js\nimport { CopilotClient } from \"@microsoft/copilot-sdk\";\n\nconst client = new CopilotClient({ mode: \"empty\" });\nconst session = await client.createSession({\n  availableTools: [\"custom:lookup_order\"]\n});\n```\n\nEach session gets exactly the tools it is supposed to have. Cross-tenant contamination is now a configuration failure, not an architecture hazard waiting to happen.\n\n## Durable Sessions: Agents Survive Process Restarts\n\nSessions in 2.0 are first-class durable objects. They outlive any process or client connected to them. When you restart your server or deploy an update, existing agent sessions do not evaporate — you reconnect with `resume_session()`, and the agent picks up with its model config, tool registrations, and conversation history intact.\n\nIn 1.x, session durability was something you built yourself: serialize state, store it, reload it on reconnect. 2.0 handles that at the runtime layer — a real quality-of-life improvement for anyone shipping agent features in a production web app.\n\n## Agent Controls: Microsoft’s Answer to Agent Governance\n\nShipping alongside 2.0 is [Agent Controls](https://commandline.microsoft.com/introducing-agent-controls-an-enterprise-control-plane-for-agent-behavior/), a managed Azure service built on the open Agent Control Specification (ACS). It evaluates policies at four points in every agent turn: before the agent reads input, before it calls a tool, after a tool returns, and before the final response goes out. The ACS SDK integrates with LangChain, the OpenAI Agents SDK, the Anthropic SDK, AutoGen, Semantic Kernel, and MCP tools — not locked to the Microsoft stack.\n\nThe honest note: Agent Controls is a managed Azure service. Your policy layer gains a vendor dependency. For teams already running on Azure who need enterprise-grade agent governance, that trade-off probably makes sense. For everyone else, watch how the open ACS specification matures before committing.\n\n## Migration: Package Names, Breaking Changes, Deadline\n\nThe rename is straightforward — update your package references:\n\n- Node.js: `npm install @microsoft/copilot-sdk`\n- Python: `pip install microsoft-copilot-sdk`\n- Go: `go get github.com/microsoft/copilot-sdk/go/v2`\n- .NET: `dotnet add package Microsoft.Copilot.SDK`\n\nThe breaking changes are real: client and session options have been regrouped, RPC signatures changed, and the SDK now requires protocol version 4. The [v2.0.0 release notes](https://github.com/microsoft/copilot-sdk/releases/tag/v2.0.0) have the full list. The 1.x line still gets bug patches — its PyPI page now links directly to the v2 breaking-changes guide — but no new features are coming to it.\n\nThe deadline to care about: [VS Code 1.146](https://windowsforum.com/news/vs-code-1-146-deprecates-local-agent-harness-copilot-migration-due-february-2027.451860/) deprecated the local agent harness in November. Migration to the new harness — which requires Copilot SDK 2.0 — is due by February 2027. If you use VS Code’s agent features in your workflow, that is a hard deadline, not a suggestion.\n\nThe [official announcement](https://commandline.microsoft.com/microsoft-copilot-sdk-2-0-github/) includes a full getting-started guide. If you are building multi-tenant, multi-user agent apps and have not yet looked at `mode: \"empty\"`, that is the first thing worth reading.", "url": "https://wpnews.pro/news/microsoft-copilot-sdk-2-0-rust-runtime-and-what-changes", "canonical_source": "https://byteiota.com/microsoft-copilot-sdk-2-rust-runtime-faster-sessions/", "published_at": "2026-11-19 16:09:08+00:00", "updated_at": "2026-11-19 16:15:36.145573+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-tools", "ai-products"], "entities": ["Microsoft", "Copilot SDK 2.0", "GitHub Copilot SDK 1.x", "Agent Controls", "Agent Control Specification", "Azure", "VS Code", "LangChain"], "also_reported_by": [], "takeaway": "Copilot SDK 2.0's Rust core cuts session-start overhead from 5.25 seconds to 55.3 milliseconds (not model inference), and `mode: \"empty\"` starts each session with zero tools so multi-tenant apps must explicitly opt in per session.", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/microsoft-copilot-sdk-2-0-rust-runtime-and-what-changes", "markdown": "https://wpnews.pro/news/microsoft-copilot-sdk-2-0-rust-runtime-and-what-changes.md", "text": "https://wpnews.pro/news/microsoft-copilot-sdk-2-0-rust-runtime-and-what-changes.txt", "jsonld": "https://wpnews.pro/news/microsoft-copilot-sdk-2-0-rust-runtime-and-what-changes.jsonld"}}