GitHub Copilot Fusion Routes Each Prompt Across Multiple Models
GitHub used Universe on October 28 to launch Copilot Fusion, a model-picker option that replaces choosing a single model with choosing an effort level (Standard, High or Max). For each prompt, Fusion picks a workflow: Single (one model handles it), Cascade (a cheaper model attempts first, a quality check accepts the result or escalates to a stronger model that starts fresh) or Critique (one model drafts, a second reviews, the first revises). It combines the HydraFusion research preview with Copilot's existing auto model selection.
GitHub reports that Fusion Max scored 60 on the Artificial Analysis Coding Agent Index, within two points of Claude Code with Opus 5.5 Max, at roughly half the average API cost, half the tokens and about 40% less time per task. Billing is per underlying model at standard rates, with a temporary 30% discount for paid plans. A companion change lets Fusion select local models.
Fusion is available on all Copilot plans in VS Code, the GitHub Copilot app, Copilot CLI and JetBrains IDEs. Admins only expose models already allowed by enterprise policy, can disable specific models for Fusion alone, and can make Fusion the default through managed settings. Research-preview users of HydraFusion are migrated automatically.
Read more — GitHub Changelog
Copilot Comes Bundled with GitHub Enterprise, and the Copilot SDK Moves to Microsoft
Also at Universe, GitHub changed how enterprises buy Copilot. Customers working with a GitHub or Microsoft account team can now get Copilot included for every licensed GitHub Enterprise user instead of buying separate seats. Users without an Enterprise license can get Copilot Standalone at $10 per user per month. Both have the same features and models as Copilot Enterprise but no per-seat monthly AI credits: usage is metered from the first request against the enterprise budget.
When that budget runs out, code completion and next-edit suggestions keep working, while Copilot Chat, code review and cloud features stop until budget is available. Self-serve subscriptions are not yet eligible, with dates to come "in the coming weeks"; Copilot Business and Enterprise remain on sale. For platform teams, the thing to manage shifts from seat counts to the AI usage budget and its alerts.
Separately, the GitHub Copilot SDK is being renamed the Microsoft Copilot SDK and will serve a shared "Microsoft Copilot harness" used across Microsoft and GitHub products. The repository will move to the Microsoft organization in phases. GitHub says no immediate changes are required, but package names and namespaces may change later, so teams building on the SDK should watch the repository for migration notes.
Read more — GitHub Changelog
Agent Merge and Shared Copilot Automations Push Copilot Further into the Cloud
Agent Merge, previously available in the Copilot app and VS Code, is now built into pull requests on github.com. A "Watch and fix" button in the merge box tells Copilot to monitor the PR and fix selected blockers (failing Actions workflows, merge conflicts or both) by spinning up a cloud development environment. Combined with auto-merge, it keeps the PR mergeable until GitHub merges it. It can be enabled by default for all your PRs and requires a paid Copilot plan.
Copilot Automations, which combine prompts, triggers and allowed tools into workflows that Copilot runs autonomously, gained a shared mode. Shared automations belong to a repository rather than a person: anyone with read access can see them, anyone with write access can edit them, credits bill to the repository owner, actions are attributed to Copilot, and they keep running if the author leaves. Examples include reproducing a bug when an issue is opened or capturing screenshots when a PR is marked ready for review.
Shared automations are rolling out to Pro, Pro+, Max, Business and Enterprise plans. In organization-owned repositories an admin must enable the policy that allows the Copilot cloud agent to bill to the organization. Universe also brought GA of GitHub Agentic Workflows, covered in this week's AI Dev Patterns digest.
Read more — GitHub Changelog
GPT-6.1 Terra Arrives in Copilot and Codex, Codex CLI Adds a Vertex AI Provider
OpenAI released GPT-6.1 Terra on October 26, positioned below GPT-6.1 Sol in cost and focused on image understanding and computer use across browsers, desktop and apps. In ChatGPT Work and the desktop app it is available on Plus, Pro, Business, Enterprise and Edu plans. GitHub made it generally available in Copilot the same day across VS Code, Visual Studio, Copilot CLI, the cloud agent, JetBrains, Xcode and Eclipse, reporting that it solved noticeably more terminal and C# tasks than GPT-5.6 Terra and works best on well-scoped tasks.
Codex CLI 0.165.0 (October 27) adds a built-in Google Cloud Vertex AI provider, selected with model_provider = "gcp", plus a repository filter in the session picker, directory grouping in the agent command center and experimental attached thread forks in the app-server API. Changing reasoning effort mid-conversation is now on by default, and Memory v2 is the default for fresh profiles. Codex CLI 0.166.0 (October 29) adds keyboard-driven transcript selection with search, codex queue --resume, codex doctor --network-only, and clearer explanations when a safety block triggers, with suggested safer follow-up prompts.
GPT-6.1 Terra is now in the bundled, Vertex AI and Amazon Bedrock catalogs, so the same model can be used through all three providers from Codex CLI.
Read more — OpenAI
Claude Code 2.1.311–2.1.316: Write Boundaries, Subagent Effort and Gateway Budgets
Claude Code shipped several releases over the past week. Version 2.1.314 adds permissions.blockWritesOutsideWorkingDirectories, which makes the Write, Edit and NotebookEdit tools refuse paths outside the working directories in every permission mode, a useful hard boundary for teams running agents in auto-accept modes. Version 2.1.316 adds CLAUDE_CODE_SUBAGENT_EFFORT to set the default effort level for subagents and CLAUDE_CODE_DISABLE_ULTRATHINK to turn off the ultrathink keyword.
Most of the remaining changes target organizations running Claude through the Claude apps gateway:
- 2.1.312:
oidc.user_id_claimidentifies users by a claim other thansub, such as Entra ID'soid. - 2.1.314: gateway upstreams accept a
groupslist, so only members of listed IdP groups are routed to them. - 2.1.316: pooled group budgets let a group's members draw from a shared monthly budget via
pooled_budget, andmanaged.policy_mode: layeredapplies every matching managed policy instead of only the first.
Smaller additions include syntax coloring for code blocks in VS Code, a Skills view in Claude Tag analytics showing how often each attached skill is used, effort-level selection for cloud routines, and self-hosted runner flags that keep idle sessions alive while background processes they started are still running.
Read more — Anthropic
Mistral Large 4 Released as a 1T-Parameter Open-Weight MoE
Mistral released Mistral Large 4 (nicknamed "Le Chonk") on Hugging Face on October 29. It is a multimodal Mixture-of-Experts model with about 1T total parameters and roughly 49B active per token (5 of 128 experts, one shared), a 1M-token context window, Multi-head Latent Attention with a sparse-attention indexer, and a 1.6B Pixtral vision encoder. It takes text and images and produces text.
Mistral emphasizes security and agentic coding results: 93% on Cybench, 82% on vulnerability reproduce-and-patch tasks in the Artificial Analysis Cyber Index, 93.3% attack resistance on Lakera B3, 61.7% on DeepSWE v1.1 and 28.3% on Terminal-Bench 4. It ranked as the fifth-best open-weight model on the Artificial Analysis Intelligence Index at launch.
Official FP8 and NVFP4 checkpoints are available, along with community GGUF quantizations. It runs with Transformers across 8 GPUs, with vLLM on Blackwell for NVFP4, or via llama.cpp, where a Q2_K quant fits on a single 512 GB Apple Silicon machine; TRL supports LoRA fine-tuning. The license is the Mistral Ecosystem Open-Weight License, an MIT derivative that restricts offering the model as a service, so check it before hosting the model for third parties.
Read more — Hugging Face
Microsoft 365 Copilot Adds Admin-Built MCP Connectors and Usage-Billed Work IQ APIs
Microsoft's October 27 release notes for Microsoft 365 Copilot include two developer-relevant changes. Admins can now build custom connectors based on the Model Context Protocol in the Microsoft 365 admin center and deploy them across Microsoft 365, so organizational data from internal systems can surface in Copilot without building a full Graph connector.
The Work IQ APIs gained usage-based billing, letting developers invoke agents and models without pre-assigned Copilot licenses, and a new endpoint provides programmatic access to both first-party and tenant-defined declarative agents. That makes it practical to call Copilot agents from internal applications where only a subset of users is licensed.
The same release adds a Learning Agent, web links as sources in Copilot Notebooks, new Copilot usage metrics in Viva Insights, and PowerPoint generation that reuses an attached deck's theme.
Read more — Microsoft Learn
Anthropic Files Public S-1 for a Nasdaq IPO Under the Ticker ANT
Anthropic, PBC announced on October 26 that it has filed a registration statement on Form S-1 with the SEC for a proposed initial public offering of Class A common stock. It intends to list on the Nasdaq Global Select Market under the ticker ANT, with Goldman Sachs and Morgan Stanley named as contacts for the preliminary prospectus. The number of shares and price range have not been determined, and the registration statement is not yet effective.
The public filing follows the confidential S-1 Anthropic submitted in June. For developers the immediate impact is limited, but a public prospectus will disclose far more detail about Anthropic's revenue mix, compute commitments and risk factors than has been available, which is relevant context for teams making long-term bets on the Claude platform.
Read more — Anthropic
Links & Sources
- Route and orchestrate models with GitHub Copilot Fusion
- GitHub Enterprise now includes access to GitHub Copilot
- GitHub Copilot SDK is becoming Microsoft Copilot SDK
- Agent Merge watches and fixes pull requests in the cloud
- Build shared workflows for your team with Copilot Automations
- GPT-6.1 Terra in GitHub Copilot
- OpenAI Codex changelog
- Claude Code changelog
- Welcome Le Chonk: Mistral Large 4 on Hugging Face
- Microsoft 365 Copilot release notes
- Anthropic files S-1 with the SEC for proposed initial public offering
You May Also Enjoy
