GitHub Copilot September 2026: Model Deprecations, Gemini 3.8 and Signup Changes

October 3, 2026 update: For teams reviewing GitHub Copilot’s September 2026 model, access and policy changes, four models retired on October 2. GitHub’s suggested replacements are: Gemini 3.5 Flash and Gemini 3.6 Flash to Gemini 3.8 Flash, Kimi K2.7 Code to Kimi K3, and Claude Opus 4.7 to Claude Opus 5.5, as listed in the October 2 notice. GitHub says no manual removal is needed. Check model access and update explicit workflow pins before switching; the current supported-model guide says Kimi K3 is excluded from default enablement, so verify its policy separately.

September 23, 2026 update: GitHub’s September 18 notice schedules six more Copilot models across Chat, inline edits, ask and agent modes, and code completions on October 19. The later date remains separate from the completed October 2 wave; its mappings and Business/Enterprise default-enable rule are below.

September 11, 2026 source date: GitHub’s VS Code Agents usage update and code-review update were published on September 11. Availability depends on plan, policy, repository and product surface.

September 4, 2026 update: The Gemini 3.8 Flash and Business and Enterprise signup notices describe gradual rollout and seat or billing timing. Verify the current organization state before acting on either.

September 3, 2026 update: Two September 2 Changelog entries add governance controls: enterprise-managed default models and content exclusions in the Copilot app and CLI. These controls cover different surfaces and policy scopes.

What changed in the September 11 update

GitHub’s usage-metrics entry adds fields for VS Code Agents, including daily active users and totals by the dedicated VS Code agent surface. GitHub distinguishes that surface from editor Agent Mode and generic Copilot rollups. A blank or null value can therefore mean that the feature is unavailable or that the field does not apply; it should not be silently converted into zero usage.

A separate code-review entry describes addressed-comment auto-resolution, smart commit messages and analysis changes. GitHub also describes an agent ensemble in Lite and broader shell-tool work behind firewall controls. The percentages in the announcement are GitHub’s own experiment results. Keep them labelled as vendor evidence, not as an independent benchmark or a promise that a repository will see the same outcome.

A decision matrix for Copilot administrators

A safe admin checklist

1. Identify the surface. Record whether the question concerns VS Code Agents, editor Agent Mode, the Copilot app, CLI, JetBrains or code review. Do not compare unlike counters.
2. Record the policy boundary. Note organisation, enterprise, repository and user settings that can control access. A changelog entry is not a live entitlement read-back.
3. Choose a review-only pilot. Select a low-risk repository, keep branch protection and required human review in force, and record the commit SHA and feature setting.
4. Inspect the proposed change. An addressed comment, smart commit message or analysis result still needs a human owner to validate scope, tests, security and attribution.
5. Measure the right denominator. Keep dedicated VS Code Agent fields separate from other Copilot usage. Document null handling and the time window before comparing reports.
6. Write a rollback rule. Disable the experiment or revert the workflow if review quality, policy compliance or repository safety is not acceptable.

What the weekly release does not prove

The September 7 weekly release lists Jira integration in the Copilot app, experimental HydraFusion CLI routing, VS Code automations, voice and issue work, and a managed JetBrains sandbox. A weekly roundup is a discovery pointer; it does not prove a shared availability date, identical permissions or production readiness across surfaces. Verify the current documentation and account state before changing a workflow.

September 2 additions: default models and content exclusions

Default model policy

GitHub’s default-model changelog says enterprise-managed settings support any preferred default model for new conversations, with team overrides through the documented model and team-mapping controls. The relevant administrator task is to record the intended default, the teams allowed to override it and the review owner. “Available in the setting” does not mean every model is available to every plan, organisation, user or surface. Check the current default-availability guide and model-access guide before applying the setting.

Content-exclusion policy

GitHub also says content exclusions are generally available in the Copilot app and CLI and that the app/CLI respect enterprise, organisation and repository policies. The Changelog entry should be read with the content-exclusion documentation: an administrator configures paths or fnmatch-style patterns, propagation can take up to 30 minutes, and the setting must be tested. The current documentation notes a limitation for Agent mode in IDEs, so do not claim that one exclusion configuration blocks every Copilot surface.

Use GitHub’s enterprise-managed-settings reference as the schema authority and its configuration guide for the admin path. Test one repository with a known excluded path, one included path and the actual client surfaces your teams use. Save the observed policy state and timestamp; do not infer a successful exclusion from a setting that has not propagated. These controls have different scopes: model availability, excluded repository paths, budget expiry and code-review approvals each need a named owner and a current policy read-back.

Changelog posts and community discussions can help identify administrator questions, but they do not establish plan entitlement or enforcement. For adjacent implementation, use the Copilot VS Code release guide for feature changes, the agent/plugin guide for tool governance and the agent-harness guide for state and evaluation.

The two September 2 entries are documented product-policy updates. They do not prove that a particular organisation has the setting enabled, that a user can select every model or that an exclusion covers every client. Confirm account-level readback before changing production policy.

Short answer: GitHub Copilot retired four models on October 2 and has six more scheduled for October 19. Use the date-specific replacement map, check plan and model policy, then update any pinned workflows. Keep the September billing, budget, default-model, content-exclusion, usage and review controls in the same admin checklist.

Four GitHub Changelog entries from 31 August and 1 September 2026 change Copilot governance rather than adding one isolated feature. This checklist turns the model, access, budget and review-policy changes into explicit owner decisions.

The September admin checklist

GitHub’s 31 August and 1 September 2026 Changelog entries form one practical administrator update. The changes touch four controls: selected model deprecations, Team-plan model access when a user belongs to multiple organisations, individual-user budget expiry, and Copilot code-review approvals.

The safest response is an inventory, not a panic migration. Check which repositories and teams depend on a named model, identify the billing organisation for multi-seat users, record budget owners and expiry dates, and decide whether code-review approval belongs in branch protection. GitHub says no action is required to remove the deprecated models, but that does not remove the need to test the replacement workflow.

This guide covers model availability and administrator controls. Use the GitHub Copilot VS Code August release guide for editor features and the Fable versus Sonnet comparison for a broader model-selection discussion.

Model deprecations: map by family, then test

A date-aware model lifecycle register

GitHub’s August 31 notice, September 10 notice, October 2 notice and September 18 notice give the dates and suggested alternatives below. The list is scoped to models inside GitHub Copilot; it does not announce retirement of the providers’ separate APIs. “Suggested alternative” is a migration pointer, not a promise that behavior, access or cost is equivalent.

The table preserves the alternatives GitHub named at each date; some later changed status. Claude Opus 4.7 was retired in the October 2 notice, and Gemini 3.7 Flash is scheduled in the October 19 notice. For current selection, follow the later dated rows and GitHub’s current supported-model documentation.

September 1 and 10: GitHub noted that Claude Sonnet 4.6 remains available to individual Copilot subscribers on annual plans. Current supported-model documentation retains that exception; check the current plan and client before assuming the old model is unavailable to every user.

October 2, effective: The effective-date notice maps Claude Opus 4.7 to Opus 5.5. The September 3 advance notice had suggested Opus 5, while the current supported-model retirement history uses generic “latest Claude Opus” wording; use the October 2 notice for the version-specific mapping. GitHub says Enterprise administrators may need to enable alternatives. Its current supported-model guide excludes open-weight Kimi K3 from default enablement. Inspect Kimi K3’s explicit organization or enterprise model policy and confirm it appears in the user’s plan and client selector, using the model-access guide for the setup path. For Opus 5.5 access and billing details, see the Copilot Opus 5.5 access and billing guide.

October 19, scheduled: The October 19 notice says the suggested alternatives are automatically enabled for Copilot Business and Enterprise under default model enablement unless an administrator turned off the global default or explicitly disabled a model. This condition belongs to the six October 19 models in the table; do not apply it to October 2’s Kimi K3 row. The default-availability guide and model-access guide explain current policy and plan boundaries. GitHub says Copilot Free and Student use auto model selection only.

Before changing a default: record the lifecycle date, current model, suggested target, owner, client surface and policy setting. Search repository settings, scripts, integrations and shared guidance for explicit Copilot selections, then review each match before editing so provider API identifiers are not changed by mistake. Check whether the target appears in the affected user’s model selector. Run representative tasks in a low-risk repository only after access is confirmed, then save the model, date, repository and observed result. No replacement-model or account-policy test is reported in this guide.

• Update pinned workflows before their stated retirement date.
• Verify model policy and client access before switching users.
• Record cost or usage controls and the budget owner with the migration decision.
• Retain a human owner and fallback for critical workflows.

Team access now follows the billing organisation

GitHub’s Team-plan access update says that when a user has seats in multiple organisations, model access follows the organisation paying for that usage. The user can check the billing organisation under Usage billed to. A seat in another organisation does not grant access to models that the billing organisation has not enabled.

The operational check is straightforward: identify the seat, open the billing or usage relationship, find the organisation that is billed, and inspect its model policy. Do not ask a user to change seats or permissions until the billing path is confirmed. GitHub says enterprise-only access is unaffected by this specific change.

For an adjacent access-control mindset, use the agent plugins, Skills and MCP guide and the scheduled-workflow permissions guide; those pages are not GitHub documentation, but they reinforce explicit ownership and permission checks.

Individual budget expiry is a governance control

GitHub’s September 1 budget update lets Business and Enterprise administrators set an individual user budget to expire at the next billing cycle or on a chosen date, or leave it without an expiry. The Budgets REST API uses an expires_at field. When the budget expires, GitHub says the user falls back to the next applicable budget, such as a cost-center per-user budget or the universal budget.

Assign an owner and reason to each expiry. A temporary project may use a fixed date, while a recurring team budget may align to the next billing cycle. Record what happens at expiry, how the user requests renewal, and whether repository or organisation budgets remain unaffected. Do not assume a budget setting is a complete cost-control system.

Review spend and task value together. A lower cap can protect a budget while also interrupting a critical agent workflow. Set an escalation path before a user reaches the limit and make the renewal decision visible to the technical and business owner.

Copilot code-review approvals are off by default

GitHub’s September 1 code-review notice says every Copilot review includes an approval assessment, but that assessment alone does not count toward merge requirements. Actual approvals are off by default and can be configured at the enterprise, organisation or repository level. When enabled, an approval can satisfy a required-approvals rule; a new commit dismisses it. For setup steps, see the Copilot code-review configuration guide.

That makes this a branch-protection decision, not a simple quality badge. Before enabling it, define which repositories qualify, what human review remains required, how CODEOWNERS interacts with the setting, and what happens when a new commit arrives. Test the setting in a non-critical repository and keep an audit trail of policy changes.

For wider agent permission context, connect to the Claude Code Auto Mode guide; the product is different, but the governance principle is shared: make machine authority explicit and reviewable.

A practical admin runbook

Start with a change register dated 3 October 2026. For each team, record the retirement date and status, old and suggested model, affected client surface, policy owner, billing organisation, budget expiry and code-review setting. Add the source link and date of the last account read-back so the register can be updated when GitHub changes a product rule.

Then plan the smallest safe validation: one representative task for each replacement the team intends to use, one multi-seat billing-access check, one budget-expiry read-back and one review-policy check in a non-critical repository. These checks were not performed for this guide; they are steps for the administrator who owns the account and repository.

Finally, publish internal guidance that distinguishes what GitHub changed from what your organisation decided. That separation prevents a vendor default, an entitlement condition and an internal control from being reported as the same thing.

Recommended workflow

1. Create a dated inventory of affected models, organisations, budgets and repositories.
2. Map deprecated model families and test listed replacements on representative tasks.
3. Verify the billing organisation for any user with multiple Team-plan seats.
4. Set budget expiry with an owner, renewal path and escalation rule.
5. Pilot code-review approvals in a non-critical repository and re-check branch protection after new commits.

Related Digital Marketer guides

• GitHub Copilot in VS Code August 2026 — See this guide for VS Code editor features and their client availability.
• OpenAI agent plugins, Skills and MCP — Agent integration and control-plane context.
• ChatGPT Work scheduled tasks — Scheduled-workflow governance context.
• ChatGPT Site Tools and WebMCP — Browser and site-tool workflow context.
• Claude Code Auto Mode — Permission and classifier context for agentic work.
• Claude Tag for Marketing Teams — Slack-based Claude workflows, memory and spend controls.

Questions marketers are asking

Do I need to remove deprecated Copilot models?

GitHub says no manual removal is needed after a model is deprecated. The October 2 wave is already effective; update explicit pins and verify access to the chosen alternative. Prepare for the separate October 19 schedule before its date.

Does the Kimi K3 replacement enable itself automatically?

Do not assume so. GitHub’s current supported-model documentation says open-weight Kimi K3 is outside default model enablement. An administrator should inspect the applicable organization or enterprise model policy and confirm Kimi K3 appears for the affected plan and client.

Why can a multi-organisation Team user lose model access?

GitHub says access is determined by the billing organisation under Usage billed to for this case.

Can an individual Copilot budget expire?

Business and Enterprise admins can choose no expiry, the next billing cycle or a specific date, according to GitHub.

Can Copilot approve a pull request automatically?

GitHub says approval assessments are available, actual approvals are off by default and configurable. If enabled, they can count toward required approvals; new commits dismiss the approval.

AI disclosure: This article was prepared with assistance from OpenAI. Its product claims are linked to GitHub sources. No organisation’s account settings or replacement-model behaviour were tested for this guide.