+The enterprise and organization settings endpoints, including the organization runner endpoint, don't support GitHub Apps or fine-grained personal access tokens. The repository settings endpoints support both, with Administration: read permission to read settings and Administration: write permission to update them.
Xcode 开发者现在可以在 IDE 的内置编码助手中直接使用 Copilot（Xcode 27.3 beta+），补充现有的基于扩展的集成
证据
+You can now work with GitHub Copilot directly in Xcode's built-in coding assistant, bringing Copilot into your native Xcode workflow. The integration is now in public preview, available starting with Xcode 27.3 beta.
+The Copilot usage metrics API now shows bring your own key (BYOK) usage across GitHub Copilot, so you can separate it from Copilot-hosted model usage.
GitHub Copilot Fusion is now generally available with intelligent multi-model routing and orchestration.
Developers can now use Copilot Fusion to automatically route tasks to the best model without manual selection. Copilot Fusion offers three effort levels (Standard, High, Max) and uses three execution patterns (Single, Cascade, Critique) to optimize performance and cost.
证据
+GitHub Copilot Fusion is generally available. Instead of picking a model for each task, choose Copilot Fusion and let Copilot intelligently route and orchestrate which models it uses for you.
Users on paid Copilot plans receive 30% discount on model costs when using Copilot Fusion for a limited time.
Paid Copilot plan users get cost savings on Copilot Fusion usage during the promotion period. Standard billing applies after the promotional period ends.
证据
+When you use Copilot Fusion you're billed for each model it uses, at each model's standard rate. For a limited time, users on paid Copilot plans will receive a 30% discount on model costs when using Copilot Fusion.
企业客户现在可以使用 REST API 端点（在企业、团队、应用和组织级别）以编程方式管理整个组织中的 Copilot 模型可用性。
证据
+GET and PATCH endpoints are now generally available for model policies at four levels:
Enterprise: /enterprises/{enterprise}/copilot/model-policies
Enterprise teams: /enterprises/{enterprise}/teams/{team_slug}/copilot/model-policies
Enterprise apps: /enterprises/{enterprise}/copilot/apps/model-policies
Organization: /orgs/{org}/copilot/model-policies
用户必须从 Gemini 3.7 Flash、GPT-5.5、GPT-5.4、GPT-5.4 mini、GPT-5 mini 和 Grok 4.5 迁移到它们建议的替代方案。企业需要更新工作流并通过模型策略启用替代模型。
证据
+As of today, October 19, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions).
Model | Deprecation date | Suggested alternative
Gemini 3.7 Flash | 2026-10-19 | Gemini 3.8 Flash
GPT-5.5 | 2026-10-19 | GPT-6.1 Sol
GPT-5.4 | 2026-10-19 | GPT-6.1 Sol
GPT-5.4 mini | 2026-10-19 | GPT-6 Luna
GPT-5 mini | 2026-10-19 | GPT-6 Luna
Grok 4.5 | 2026-10-19 | Grok 4.7
+HydraFusion Max is built on the same architecture and uses the same workflow techniques as HydraFusion, but is tuned for frontier capability on more demanding tasks. It applies higher reasoning efforts where depth and thoroughness matter most, while still using orchestration to consider token efficiency.
GitHub Copilot 弃用四个 AI 模型：Gemini 3.5/3.6 Flash、Kimi K2.7 Code 和 Claude Opus 4.7
依赖这些模型的用户必须迁移到替代方案（Gemini 3.8 Flash、Kimi K3、Claude Opus 5.5）。企业管理员需要在策略中启用替代模型。工作流和集成需要更新。
证据
+As of today, October 2, 2026, we have deprecated the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). [Table showing: Gemini 3.5 Flash → Gemini 3.8 Flash, Gemini 3.6 Flash → Gemini 3.8 Flash, Kimi K2.7 Code → Kimi K3, Claude Opus 4.7 → Claude Opus 5.5]
+The enterprise and organization repository-level Copilot usage metrics reports now break down how long pull requests spend in each stage of review. A new pull_request_review_times array on each repos-1-day row reports a median and a 90th percentile for the time from ready for review to first review, first review to final review, and final review to merge.
所有 Copilot 用户（包括 Business 和 Enterprise）现在可以访问以前仅限于 Pro/Pro+/Max 计划的个人代码审查设置，并提供新的细粒度控制，可配置自动审查和审查工作量等级。
证据
+Previously, personal Copilot code review settings were available only with Copilot Pro, Pro+, and Max on the "Copilot features" page... Under your profile → Copilot settings, a dedicated "code review" page under Copilot is now available on every Copilot plan, including Copilot Business and Copilot Enterprise.
用户应注意 Claude Opus 5.5 输出带有水印，但这不影响质量、可读性或 token 成本。
证据
+Claude Opus 5.5 watermarks its text outputs. The watermark doesn't change the meaning, quality, or readability of outputs, nor does it add any tokens or cost.
+`copilot_feature_engagement`: Adds the dashboard's active-user total and feature engagement counts to enterprise and organization 28-day aggregate reports. `totals_by_feature`: Breaks engagement down by code completion, agent edit, passive Copilot code review, active Copilot code review, Copilot cloud agent, Copilot CLI, and Copilot app. `users_in_phase_28d`: Reports the full rolling 28-day population classified into each AI adoption phase as of that day.
Copilot budget increase requests workflow now generally available
组织和企业所有者现在可以在设置中直接审批、调整或拒绝成员预算请求。成员达到限额时可以请求更多 AI credits，而不是被阻止使用 Copilot 功能。
证据
+Previously, when a member used all the Copilot AI credits available to them, they were blocked from Copilot features that consume credits. This release adds a flow for them to request more budget the moment they hit the limit. You can approve, adjust, or deny that request without leaving your settings.
+Usage is charged based on the model auto selects, regardless of tier. Paid subscribers continue to receive a 10% discount on usage billed through auto.
+We have deprecated MAI-Code-1-Flash across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions) today, September 10, 2026.
+If you administer GitHub Copilot Business or GitHub Copilot Enterprise, you can now centrally control which agent operations are blocked, require human approval, or can proceed without a prompt. Managed permissions cover shell commands, file reads and edits, and network domains.
+We will deprecate the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions) on October 2nd, 2026:
Model | Deprecation date | Suggested alternative
Gemini 3.5 Flash | 2026-10-02 | Gemini 3.8 Flash
Gemini 3.6 Flash | 2026-10-02 | Gemini 3.8 Flash
Kimi K2.7 Code | 2026-10-02 | Kimi K3
Claude Opus 4.7 | 2026-10-02 | Claude Opus 5
+You can now set your preferred GitHub Copilot model as the default for new conversations through enterprise-managed settings. This lets you choose the default model that best fits your workflows.
+Free
For getting started with GitHub Copilot.
$0USD
Pro
For everyday coding with agents in GitHub Copilot.
$10USDper user / month
Pro+
For more complex development with premium models.
$39USDper user / month
Max
For sustained, high-volume agent workflows with GitHub Copilot.
$100USDper user / month
GitHub Copilot for JetBrains 现支持企业托管设置，用于插件治理、MCP servers、OpenTelemetry 和权限管理
企业管理员现在可以集中管理和控制 Copilot 插件治理、MCP server 访问、遥测收集和权限模式，覆盖整个组织的所有 JetBrains IDE 用户。
证据
+GitHub Copilot for JetBrains now supports enterprise managed settings for plugin governance, MCP server access, OpenTelemetry, and permission modes. Administrators can now apply consistent controls for everyone on your enterprise's Copilot plan.
+Copilot memory can now retain and recall useful information across agent chat sessions. This helps you maintain context between conversations instead of repeatedly providing the same project details or preferences.
企业和组织管理员现在可以通过 Copilot 使用指标 API 在企业、组织、企业用户和组织用户报告中跟踪各个代理应用 (如 Claude 和 Codex 代理) 的使用情况。
证据
+The Copilot usage metrics API now reports that activity, broken out by individual agent. The usage metrics API does this in the enterprise, organization, enterprise-user, and organization-user 1-day and 28-day reports.
+When you delegate a task to GitHub Copilot cloud agent, you can now set the reasoning level for models that support it. This allows you to control how much the model reasons before it responds.
+As of today, July 31, 2026, we have deprecated the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions).
Gemini 2.5 Pro 2026-07-31 Gemini 3.1 Pro (Preview)
Gemini 3 Flash 2026-07-31 Gemini 3.6 Flash
+The GitHub Copilot app now has its own policy, so you can control who has access to it at the enterprise and organization levels. Until now, access to the Copilot app depended on your GitHub Copilot CLI policy being enabled. From several conversations with customers, we understand that many of you want to manage each client independently. Now the Copilot app and the Copilot CLI each have their own policy, giving you the flexibility and control to enable the right clients for your teams.
企业和组织管理员现在可以通过两个新的 REST API 端点访问每个仓库的 Copilot 编码代理和代码审查拉取请求活动的细分数据。
证据
+Two new endpoints return a per-repository report for a single day:
<ul>
<li><code>GET /enterprises/{enterprise}/copilot/metrics/reports/repos-1-day?day=YYYY-MM-DD</code></li>
<li><code>GET /orgs/{org}/copilot/metrics/reports/repos-1-day?day=YYYY-MM-DD</code></li>
</ul>
Each response returns the following activity:
<ul>
<li>Pull requests created and merged by Copilot coding agent.</li>
<li>Pull requests reviewed by Copilot code review, with suggestion counts broken down by comment type.</li>
</ul>