Agents
GitHub at Ignite: Copilot Evals, “Adaptive” code review and Copilot in the browser; Foundry adds Baseten; TensorWave commits 457 MW to OpenAI
At Ignite, GitHub puts Copilot Evals in public preview to test your skills, agents and MCP tools, lets Copilot pick the effort for each code review and lets it drive Chrome. Microsoft Foundry adds Baseten and deploys models and agents onto your own AKS clusters. TensorWave will supply 457 MW of AMD capacity to OpenAI. Also: Claude Code 2.1.327, Codex CLI 0.170.0, OpenCode 2.3.2.
- Coding agents
- Cloud & infrastructure
- Models
- #GitHub Copilot
- #Microsoft Ignite
- #Microsoft Foundry
- #Baseten
- #TensorWave
- #OpenAI
- #AMD
- #Claude Code
- #Codex
- #OpenCode
- #MCP
Microsoft Ignite opened on November 17, 2026, and GitHub shipped about fifteen Copilot updates that day (GitHub changelog). Three matter directly to anyone who customizes their agents: repeatable evaluations, a code review that sizes its own effort, and browser use. On the infrastructure side, Microsoft Foundry opens up to Baseten and to your own Kubernetes clusters, and TensorWave signed a 457 MW contract with OpenAI.
Copilot Evals: test your skills, agents and MCP tools
GitHub Copilot Evals has been in public preview since November 17 for Copilot Individual, Business and Enterprise plans (GitHub). An “eval” is a repeatable test: you give an agent a realistic task, describe what a good result looks like, and check both the result and how the agent got there. With the /eval command or plain language you can:
- create an eval for a skill, a custom agent or an MCP tool in your project;
- run it and see which checks pass or fail (you approve each run before it starts);
- compare runs before and after a change to your setup.
The evaluation engine is Vally, an extensible local tool. Copilot Evals installs as a VS Code extension, as a Copilot CLI plugin, or from the Customize menu of the GitHub Copilot app.
Code review: Copilot picks the effort and looks for secrets
According to GitHub, Copilot code review gets four updates, open to the Pro, Pro+, Max, Business and Enterprise plans:
- Adaptive (public preview): Copilot weighs each pull request's complexity and risk and reviews it at Lite, Balanced or Max; each review shows the level it picked. Adaptive never goes above the maximum level set for the enterprise, organization or repository, and Balanced stays the default.
- Cross-repository context (preview, public repositories): the review can read related public repositories to find code that depends on the change.
- Secret detection (preview): more than 500 secret types found by pattern, built with more than 150 partners, plus LLMs and a GitHub model for credentials with no recognizable format.
- Azure Repos: Copilot code review for Azure DevOps is now generally available, billed in GitHub AI credits to the linked Azure subscription.
The same day, the “security review” specialist in Copilot CLI and the Copilot app gained the ability to run GitHub secret scanning on a developer's or an agent's changes before merge. It is off by default and consumes AI credits under the Secret Protection AI Credit SKU (GitHub).
Copilot drives the browser and signs in with Entra
- Browser use (public preview): with the GitHub Copilot extension for Chrome, Copilot CLI, the Copilot app, VS Code and JetBrains can control the browser to debug a web app or automate tests. In Copilot CLI you turn it on through
/plugin(GitHub). - Microsoft Entra sign-in in Copilot CLI (preview): silent authentication to a GitHub Enterprise Managed User account, or use of a Microsoft 365 Copilot license, on Windows and macOS; Linux will follow (GitHub).
Copilot Fusion and harness comparisons
GitHub says Copilot Fusion Max reaches a 71.2% resolution rate on Terminal-Bench 4.1, 5.4 points ahead of Opus 5.5 and Fable 5.2, at a cost 88% lower than Fable 5.2 and 57% lower than Opus 5.5 (GitHub). These are GitHub's figures. Fusion comes to github.com, Visual Studio and the GitHub Mobile beta apps, and adds Claude Sonnet 5.5 (Max level), GPT-6.1 Terra (High) and MAI-Code-2 (Standard). The Copilot benchmarks site adds a view comparing Copilot CLI with Claude Code and Codex CLI on the same model at the same (medium) reasoning effort, plus Terminal-Bench-Science 0.1 (GitHub).
Microsoft Foundry: Baseten, model router and AKS
- Foundry claims more than 11,000 models. Its model router now picks from 44 models (OpenAI, Anthropic, xAI, DeepSeek, Meta and others), and automatic model selection is on by default in supported projects (Microsoft).
- Baseten on Foundry (public preview) brings Baseten-optimized open models, including Kimi-K3, GLM 5.3, GLM-5.3-Flash and DeepSeek V4.1-Flash-1017, as serverless pay-as-you-go (global or US Data Zone), with provisioned throughput from December. Baseten joins Fireworks, already available.
- AKS AI Manager for Foundry deploys open-weight models and Foundry hosted agents onto AKS clusters you already run; each agent session runs in its own pod inside a lightweight VM through AKS pod sandboxing (Microsoft).
- AMD and Microsoft announce Instinct MI350P GPU support for Windows Server 2025 and the upcoming Windows Server 2028, with GPU partitioning, for on-premises inference (AMD).
Infrastructure: 457 MW for OpenAI at TensorWave
TensorWave, a GPU cloud backed by AMD Ventures, announced on November 16 a six-year agreement to provide OpenAI with 457 MW of IT capacity across several US sites, on AMD Instinct MI455X GPUs in Helios racks, as dedicated capacity for OpenAI (TensorWave, Business Wire). First capacity is due in the first half of 2027 and the full deployment by early 2028. Neither the value nor the sites were disclosed (The Next Web). TensorWave says it has secured more than 2 GW of long-term data center capacity. On November 17, Argentum AI and Kyndryl also signed a 20-year, $630 million agreement for 10 MW in Boulder, Colorado, where Argentum is deploying Nvidia B300 systems for inference (Kyndryl).
Claude Code 2.1.327
Released overnight from November 17 to 18, Paris time (release notes): claude mcp add-json <name> - reads the server's JSON from standard input, so tokens stay off the command line; /install-github-app asks for confirmation before changing a repository; /status lists broken agent, skill and command files, and hook matchers that never match. Several fixes protect data: stopping the Remote Control server in worktree mode no longer deletes git-ignored files such as .env, claude mcp add and remove no longer delete other keys in .mcp.json, and /export asks before overwriting a file. WebFetch now refuses URLs over 2,000 characters.
Codex CLI 0.170.0
Released on November 18 (release notes): WebRTC negotiation for realtime voice calls in the TUI, automatically refreshed authentication headers for OpenTelemetry HTTP exporters, and experimental support for identically named MCP servers across environments. Fixes cover MCP OAuth credential races, Windows sandbox and file replacement, and child threads losing sandbox restrictions.
OpenCode 2.3.1 and 2.3.2
Two releases on November 18. 2.3.1 moves a shell command that hits its timeout to the background instead of killing it, writes the compaction summary in the background (turn it off with compaction.background: false; an unused summary still costs tokens), reads CLAUDE.md again where there is no AGENTS.md, adds GPT 6.2 Sol and Astra for ChatGPT sign-in, and turns experimental schedules into “automations” (time, interval, cron or MCP event). 2.3.2 fixes system prompt caching for GPT-6.2 models: on gpt-6.2-sol through GitHub Copilot, uncached input per step drops from about 14,000 tokens to 3, according to OpenCode.
What we updated
- Claude Code page: latest version v2.1.327.
- Codex page: latest version 0.170.0 (Codex CLI).
- OpenCode page: latest version 2.3.2.
- GitHub Copilot page: Copilot Evals and Adaptive code review sources.
- New counter: 457 MW of AMD IT capacity committed to OpenAI by TensorWave.
Sources
- GitHub, GitHub Copilot Evals is now in public preview (Nov 17, 2026)
- GitHub, Copilot code review: Adaptive effort, secret detection, and more (Nov 17, 2026)
- GitHub, Secret scanning on demand for developers and agents (Nov 17, 2026)
- GitHub, Let GitHub Copilot interact with your browser (Nov 17, 2026)
- GitHub, GitHub Copilot CLI adds Microsoft Entra sign-in as a preview (Nov 17, 2026)
- GitHub, GitHub Copilot Fusion updates and harness comparisons (Nov 17, 2026)
- Microsoft, From model choice to your durable advantage (Nov 17, 2026)
- Microsoft, AKS at Microsoft Ignite 2026 (Nov 17, 2026)
- AMD, AMD Instinct MI350P Comes to Windows Server (Nov 17, 2026)
- TensorWave, press release on the OpenAI agreement (Nov 16, 2026); The Next Web, TensorWave will supply OpenAI with 457MW (Nov 16, 2026)
- Kyndryl, Argentum AI and Kyndryl sign $630M data center deal (Nov 17, 2026)
- Anthropic, Claude Code v2.1.327 release notes (Nov 18, 2026)
- OpenAI, Codex CLI 0.170.0 release notes (Nov 18, 2026)
- OpenCode, release notes for v2.3.1 and v2.3.2 (Nov 18, 2026)
Spotted an error in this article? Report it · Our corrections policy