Agents
GPT-6.1 Sol lands across GitHub Copilot's coding-agent surfaces
GitHub adds GPT-6.1 Sol to Copilot across coding-agent and developer surfaces, with enterprise policy controls and usage-based billing.
GitHub Copilot
-
New Models
Anthropic launches Claude Sonnet 5.5 with faster, lower-cost everyday performance
Anthropic launches Claude Sonnet 5.5 with claimed speed and cost gains, while GitHub makes the model generally available in Copilot.
-
Agents
GitHub lets Copilot route models for cost or quality—but Efficiency is not a spending cap
Copilot Auto gains Efficiency, Balance and Intelligence tiers, but billing still follows the selected model, making Efficiency a preference rather than a spending cap.
-
Agents
GitHub turns Code Quality backlog fixes into a bulk Copilot agent job
GitHub Code Quality can assign up to 25 findings to Copilot at once, shifting remediation toward batch agent work while preserving pull-request review.
-
Agents
GitHub makes Copilot agent permissions enforceable above local settings
GitHub adds enterprise-managed deny, ask and allow rules for Copilot agent operations that local auto-approval and saved grants cannot weaken.
-
Agents
GitHub lets Copilot approvals count toward merge requirements
Copilot code review can now count as a required pull-request approval, with enterprise, repository and path controls around where AI approval applies.
-
Agents
GitHub extends Copilot content exclusions to app and CLI, but gaps remain
Copilot app and CLI now respect content exclusions, while GitHub still documents gaps in IDE agent modes, symlinks and remote filesystems.
