podium

GitHub Copilot

50 of 51 criteria have a sourced finding; 50 were also cross-checked by a second agent. Every comparison that includes GitHub Copilot links here for scope, limitations, atomic answers and sources.

Humans approve the rubric, templates and prototype; they do not review every finding. An agent source cross-check is not a hands-on product test. A missing sourced finding is not evidence that a capability is absent.

Rubric
0.3 · 51 criteria
Source checks
2026-11-07 to 2026-11-21
Agent cross-checked
50 criteria
Comparisons
1

Access and agent choice

ACC-01

Client access

Agent cross-checked partial

The Copilot desktop app supports macOS, Linux and Windows, including optional WSL2 execution on Windows. GitHub Mobile provides native Android and iOS clients with Copilot chat and issue delegation. Copilot in the cloud starts from GitHub.com; GitHub Mobile is also an entry point. The CLI supports Linux, macOS and Windows through PowerShell or WSL. Copilot Chat is documented in IDEs; per-editor feature parity remains unverified. The app starts and steers sessions, reviews changes and manages PRs. Copilot in the cloud is available in a mobile browser, including use of connected tools. GitHub Mobile live notifications cover cloud agent and remote CLI sessions with In progress, Waiting for user input, Idle and Finished states. Desktop app notifications are not documented in these sources. Cloud sandbox sessions continue on any client and every surface shows the same session list; a stopped sandbox resumes from a snapshot; app v1.2.0 adds a GitHub Mobile QR code to continue cloud sessions on a phone.

Scope
Surfaces: GitHub Copilot app, GitHub Copilot CLI, GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Mobile · Version: Public source baseline 2026-11-07; targeted mobile browser, VM, shared-human prompting and pricing corrections checked 2026-11-13; no installed-product test · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: local, managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Partial atomic answers name their limits: notifications. No configured product fixture was run.
9 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:nov07-cli, github-copilot:nov07-plans, github-copilot:gap07-desktop, github-copilot:gap07-mobile, github-copilot:facet38-mobile-browser, github-copilot:nov21-cloud-sandboxes, github-copilot:nov21-cloud-experience, github-copilot:nov21-app-v120, github-copilot:nov21-live-notifications

Agent cross-checked partial

GitHub supports public-preview Anthropic Claude using Claude Agent SDK and OpenAI Codex using Codex SDK alongside Copilot. Users assign a prompt or issue to a partner coding agent, receive a PR and request iteration through comments. Generally available models come from OpenAI, Anthropic, Google, Microsoft, Moonshot AI and xAI. User BYOK connects OpenAI-compatible endpoints, Azure OpenAI, Anthropic and local endpoints such as Ollama or vLLM. Adapters for other agent harnesses are not documented. The Agents tab starts sessions with Copilot, Anthropic Claude or OpenAI Codex (Claude and Codex in public preview). Each is a separate agent session; combining harnesses within one task is not documented.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Partial atomic answers name their limits: custom_adapters, mixed_harness_operation. No configured product fixture was run.
5 atomic answers
  • Harnesses [supported] GitHub supports public-preview Anthropic Claude using Claude Agent SDK and OpenAI Codex using Codex SDK alongside Copilot. Sources: github-copilot:gap07-partner-agents.
  • Model providers [supported] Generally available models come from OpenAI, Anthropic, Google, Microsoft, Moonshot AI and xAI. Sources: github-copilot:nov21-models.
  • Custom adapters [partial] User BYOK connects OpenAI-compatible endpoints, Azure OpenAI, Anthropic and local endpoints such as Ollama or vLLM. Adapters for other agent harnesses are not documented. Sources: github-copilot:nov21-cli, github-copilot:nov21-byok.
  • Session integration [supported] Users assign a prompt or issue to a partner coding agent, receive a PR and request iteration through comments. Sources: github-copilot:gap07-partner-agents.
  • Mixed harness operation [partial] The Agents tab starts sessions with Copilot, Anthropic Claude or OpenAI Codex (Claude and Codex in public preview). Each is a separate agent session; combining harnesses within one task is not documented. Sources: github-copilot:nov21-third-party-agents, github-copilot:nov21-agent-management.

Sources: github-copilot:gap07-partner-agents, github-copilot:nov21-cli, github-copilot:nov21-byok, github-copilot:nov21-third-party-agents, github-copilot:nov21-agent-management, github-copilot:nov21-models

Agent cross-checked partial

Partner Claude and Codex agents can use the existing Copilot subscription; this does not establish use of separate Claude or ChatGPT consumer subscriptions. Current plans allocate GitHub AI credits; organization usage can draw from a shared pool. Partner agents require a paid Copilot plan and separately enabled account/organization policies; integrations are public preview. User-configured BYOK works in VS Code, JetBrains, Xcode, Copilot CLI, the app and the SDK; requests go directly to the provider. GitHub.com is not a listed BYOK client. BYOK can use Ollama and other local or on-network endpoints, including in air-gapped environments when the endpoint is reachable. The app signs in to github.com or GHE.com and, since v1.2.0, can add GitHub Enterprise Server accounts in Settings > Accounts. Switching between several github.com Copilot accounts is not documented. BYOK works without a Copilot subscription, but the app still requires a GitHub account and sign-in.

Scope
Surfaces: GitHub Copilot app, GitHub Copilot CLI, GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Partial atomic answers name their limits: account_switching. No configured product fixture was run.
7 atomic answers
  • Agent subscriptions [supported] Partner Claude and Codex agents can use the existing Copilot subscription; this does not establish use of separate Claude or ChatGPT consumer subscriptions. Sources: github-copilot:gap07-partner-agents.
  • Api accounts [supported] User-configured BYOK works in VS Code, JetBrains, Xcode, Copilot CLI, the app and the SDK; requests go directly to the provider. GitHub.com is not a listed BYOK client. Sources: github-copilot:nov21-byok.
  • Vendor credits [supported] Current plans allocate GitHub AI credits; organization usage can draw from a shared pool. Sources: github-copilot:nov07-plans.
  • Local models [supported] BYOK can use Ollama and other local or on-network endpoints, including in air-gapped environments when the endpoint is reachable. Sources: github-copilot:nov21-cli, github-copilot:nov21-byok.
  • Account switching [partial] The app signs in to github.com or GHE.com and, since v1.2.0, can add GitHub Enterprise Server accounts in Settings > Accounts. Switching between several github.com Copilot accounts is not documented. Sources: github-copilot:nov21-app-start, github-copilot:nov21-app-v120.
  • Vendor account requirement [supported] BYOK works without a Copilot subscription, but the app still requires a GitHub account and sign-in. Sources: github-copilot:nov21-byok, github-copilot:nov21-app-start.
  • Provider restrictions [supported] Partner agents require a paid Copilot plan and separately enabled account/organization policies; integrations are public preview. Sources: github-copilot:gap07-partner-agents.

Sources: github-copilot:nov07-plans, github-copilot:gap07-partner-agents, github-copilot:nov21-app-start, github-copilot:nov21-app-v120, github-copilot:nov21-byok, github-copilot:nov21-cli

Agent cross-checked partial

Cloud work requires repositories hosted on GitHub; other Git hosting is explicitly excluded for this workflow. Cloud sandboxes and GitHub Actions-based environments have different setup and customization controls. Prepare a Linux host, authenticate/register its environment, and select it from a client signed into the same GitHub account. Documented app path: install, sign in to GitHub, choose a plan or model provider, connect a repository or folder, pick a session mode, prompt, review Changes, then Create PR. Remote control accepts CLI sessions in directories not associated with a repository, and the app can connect a local folder. The app lists Git as a prerequisite; full non-Git operation is not documented. Remote control supports non-GitHub repositories and the app clones repositories from other Git hosts by URL. Cloud agent sessions only work with GitHub-hosted repositories. App onboarding offers a Copilot plan or a BYOK model provider; without write access a cloud session is read-only. Error guidance for missing prerequisites is not documented.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Partial atomic answers name their limits: no_git, local_git_without_remote, prerequisite_guidance. No configured product fixture was run.
7 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:gap07-custom-environment, github-copilot:nov21-app-start, github-copilot:nov21-cloud-overview, github-copilot:nov21-remote-control

Agent cross-checked partial

copilot -p runs a single prompt and exits; tool approval flags scope execution. The agent tasks API creates, lists and gets cloud agent tasks; REST and GraphQL issue APIs assign issues to Copilot. Both are public preview; stop and steer endpoints are not documented. The Copilot SDK client library (MIT; moved to microsoft/copilot-sdk as Microsoft Copilot SDK) can start sessions, including cloud sandbox sessions. The MIT licence covers only the SDK client: SDK use needs a Copilot subscription unless BYOK keys are configured, and cloud sandbox sessions run on GitHub's hosted service under Copilot plan terms and billing. The API creates, lists and reads tasks; CLI and remote control can steer, stop and approve permission requests. The tasks API accepts only user-to-server tokens (PAT, OAuth app or GitHub App user token). GitHub App installation tokens are supported only for SDK server-to-server use, in public preview. The SDK is generally available and follows semantic versioning; the latest stable release is v2.0.1 (2026-11-18), and prereleases are also published (v2.0.2-preview.4 on 2026-11-21). The tasks API, the issue-assignment API and SDK server-to-server authentication are public preview.

Scope
Surfaces: GitHub Copilot CLI · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: local, managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Programmable access: first-party sources in this pass did not establish mcp_server, webhooks. Detailed client actions, provider-specific eligibility and first-run prerequisites need targeted access; no install timing or external-tool fixture was run.
8 atomic answers
  • Cli [supported] copilot -p runs a single prompt and exits; tool approval flags scope execution. Sources: github-copilot:nov07-cli.
  • Api [partial] The agent tasks API creates, lists and gets cloud agent tasks; REST and GraphQL issue APIs assign issues to Copilot. Both are public preview; stop and steer endpoints are not documented. Sources: github-copilot:nov21-tasks-api.
  • Sdk [supported] The Copilot SDK client library (MIT; moved to microsoft/copilot-sdk as Microsoft Copilot SDK) can start sessions, including cloud sandbox sessions. The MIT licence covers only the SDK client: SDK use needs a Copilot subscription unless BYOK keys are configured, and cloud sandbox sessions run on GitHub's hosted service under Copilot plan terms and billing. Sources: github-copilot:nov21-cloud-sandboxes, github-copilot:nov21-sdk-transition, github-copilot:nov21-sdk-repo.
  • Mcp server [unknown] Not established for mcp server in the named first-party source pass. Product access and scenario tests were not run.
  • Webhooks [unknown] Not established for webhooks in the named first-party source pass. Product access and scenario tests were not run.
  • Operations [partial] The API creates, lists and reads tasks; CLI and remote control can steer, stop and approve permission requests. Sources: github-copilot:nov21-tasks-api, github-copilot:nov21-remote-control.
  • Authentication [supported] The tasks API accepts only user-to-server tokens (PAT, OAuth app or GitHub App user token). GitHub App installation tokens are supported only for SDK server-to-server use, in public preview. Sources: github-copilot:nov21-tasks-api, github-copilot:nov21-s2s-auth.
  • Stability [partial] The SDK is generally available and follows semantic versioning; the latest stable release is v2.0.1 (2026-11-18), and prereleases are also published (v2.0.2-preview.4 on 2026-11-21). The tasks API, the issue-assignment API and SDK server-to-server authentication are public preview. Sources: github-copilot:nov21-tasks-api, github-copilot:nov21-sdk-repo, github-copilot:nov21-s2s-auth.

Sources: github-copilot:nov07-cli, github-copilot:nov21-tasks-api, github-copilot:nov21-s2s-auth, github-copilot:nov21-remote-control, github-copilot:nov21-cloud-sandboxes, github-copilot:nov21-sdk-transition, github-copilot:nov21-sdk-repo

Agent cross-checked partial

Cloud work supports MCP; personal MCP and connectors in cloud sandboxes differ from repository MCP on Actions. The app Customize area discovers and manages plugins, skills, MCP servers and canvases; the app can install MCP servers from Customize. Custom agent profiles can restrict available tools; hooks run commands during agent work. Personal, repository and organization custom instructions and agent skills apply; Copilot CLI imports prepared memories in bulk. GitHub handles authentication for connectors; personal MCP servers support only key-based auth via COPILOT_MCP_ secrets; repository and custom-agent MCP servers do not support remote OAuth servers. The default GitHub MCP token is read-only and scoped to the current repository; the tools field allowlists tools; delegated runs call configured MCP tools without approval. Copilot owns the integration layer: GitHub-managed connectors, administrator-configured repository MCP servers and user-configured personal MCP servers.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Partial atomic answers name their limits: authentication. No configured product fixture was run.
7 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:nov21-mcp, github-copilot:nov21-cloud-overview, github-copilot:nov21-custom-agents, github-copilot:nov21-cli, github-copilot:nov21-memory, github-copilot:nov21-cloud-experience, github-copilot:nov21-app-start

Agent cross-checked partial

Official docs state only that the app is built on GitHub Copilot CLI; the desktop UI framework is not documented.

Scope
Surfaces: GitHub Copilot app · Version: Public first-party sources checked 2026-11-21; no installed release tested · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-21 (1 day old)
Agent cross-check
2026-11-21
  • Unknown after the 2026-11-21 targeted first-party documentation, release and repository pass: desktop_implementation, mobile_implementation, hybrids. No configured product fixture was run; documentation does not establish successful hands-on behavior.
4 atomic answers
  • Desktop implementation [unknown] Not established for desktop implementation in the named first-party source pass. Product access and scenario tests were not run.
  • Mobile implementation [unknown] Not established for mobile implementation in the named first-party source pass. Product access and scenario tests were not run.
  • Hybrids [unknown] Not established for hybrids in the named first-party source pass. Product access and scenario tests were not run.
  • Implementation evidence [partial] Official docs state only that the app is built on GitHub Copilot CLI; the desktop UI framework is not documented. Sources: github-copilot:nov21-app.

Sources: github-copilot:nov21-app

Planning and context

Agent cross-checked partial

The GitHub.com chat/agent flow accepts repository-context prompts. Work can originate in GitHub issues; GitHub remains the issue system. Sessions start from prompts on web, app, CLI, IDE and Mobile; @GitHub in Slack and Teams creates issues. GitHub issues can be assigned to Copilot; Linear and Sentry connectors provide context only. @copilot on PRs, @GitHub in Slack and Teams (GA 2026-11-06) and automation triggers on issue and PR events start work. GitHub issue numbers and URLs; agent tasks carry task IDs. GitHub Issues is the native tracker, so agents read and assign issues on the same platform without a sync layer. Sync with external trackers such as Linear is not documented; connectors provide context. Automations can be granted tools to label, comment, mark PRs ready or draft and merge PRs.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Intake and external tracker relationship: first-party sources in this pass did not establish external_roundtrips. No shared requirement-to-implementation, backlog evolution or authoritative-record round-trip fixture was run. Instructions and per-task plans do not prove living specifications.
9 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:nov21-automations, github-copilot:nov21-risks, github-copilot:nov21-slack-teams, github-copilot:nov21-mobile, github-copilot:nov21-tasks-api, github-copilot:nov21-cloud-experience, github-copilot:nov21-dependencies, github-copilot:nov21-automation-tools

Agent cross-checked partial

CLI plan mode asks clarifying questions and builds an implementation plan before code changes. Project Overview relates sessions to their plan, code changes and PR. Humans can give a project follow-up work and direction. Issue-artifact Markdown is editable on github.com (public preview); app canvases let people and agents work on the same plan. Issue artifact edits keep version history (public preview). Stopped cloud sandbox sessions keep a snapshot and resume from any client.

Scope
Surfaces: GitHub Copilot CLI, GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: local, managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: acceptance_criteria. No configured product fixture was run; documentation does not establish successful hands-on behavior.
7 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:nov07-cli, github-copilot:gap07-projects, github-copilot:nov21-app-ga, github-copilot:nov21-issue-artifacts, github-copilot:nov21-cloud-sandboxes

Agent cross-checked partial

Parent issues hold sub-issues; projects group by parent issue. Up to eight nesting levels and 100 sub-issues per parent, including issues from other repositories. Blocked-by and blocking relationships are set in the issue UI and the gh CLI. An existing issue can become a parent by adding sub-issues; linkage to session history is not documented. An existing issue can gain sub-issues and keeps its number and discussion; carry-over of session outputs is not documented. No mandatory workflow: chats, single-repository sessions or projects.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Copilot app · Version: Public first-party sources checked 2026-11-21; no installed release tested · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-21 (1 day old)
Agent cross-check
2026-11-21
  • Unknown after the 2026-11-21 targeted first-party documentation, release and repository pass: readiness, enforcement, state_propagation. No configured product fixture was run; documentation does not establish successful hands-on behavior.
9 atomic answers
  • Epics [supported] Parent issues hold sub-issues; projects group by parent issue. Sources: github-copilot:nov21-sub-issues.
  • Hierarchy [supported] Up to eight nesting levels and 100 sub-issues per parent, including issues from other repositories. Sources: github-copilot:nov21-sub-issues.
  • Blockers [supported] Blocked-by and blocking relationships are set in the issue UI and the gh CLI. Sources: github-copilot:nov21-dependencies.
  • Readiness [unknown] Not established for readiness in the named first-party source pass. Product access and scenario tests were not run.
  • Enforcement [unknown] Not established for enforcement in the named first-party source pass. Product access and scenario tests were not run.
  • State propagation [unknown] Not established for state propagation in the named first-party source pass. Product access and scenario tests were not run.
  • Task to epic [partial] An existing issue can become a parent by adding sub-issues; linkage to session history is not documented. Sources: github-copilot:nov21-sub-issues.
  • Identity retention [partial] An existing issue can gain sub-issues and keeps its number and discussion; carry-over of session outputs is not documented. Sources: github-copilot:nov21-sub-issues.
  • Workflow constraints [supported] No mandatory workflow: chats, single-repository sessions or projects. Sources: github-copilot:nov21-app, github-copilot:nov21-app-universe.

Sources: github-copilot:nov21-dependencies, github-copilot:nov21-sub-issues, github-copilot:nov21-app, github-copilot:nov21-app-universe

Agent cross-checked partial

Custom instructions, skills and custom agents apply with environment-specific configuration. Agent skills work on github.com, Mobile, the app and CLI. App projects hold repositories, design mocks, Slack threads and notes (public preview). Copilot Memory stores repository facts and user preferences across sessions and surfaces. Repository facts are per repository (not pooled, not copied to forks); preferences are per user. Repository facts cite code; user preferences cite the user's words. Memories cannot be edited directly on GitHub.com; Copilot upvotes or downvotes them and users can delete them. Write-access users delete repository facts, users delete their preferences, and Business/Enterprise admins can delete preferences. Memories expire after 90 days by default (7-180 configurable for repository facts); citations are checked against the current branch. Repository facts are visible to read-access users and shared across surfaces; colleague takeover is not documented.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Partial atomic answers name their limits: project_docs, correction, takeover_continuity. No configured product fixture was run.
10 atomic answers
  • Instructions [supported] Custom instructions, skills and custom agents apply with environment-specific configuration. Sources: github-copilot:nov07-cloud.
  • Skills [supported] Agent skills work on github.com, Mobile, the app and CLI. Sources: github-copilot:nov21-app, github-copilot:nov21-cloud-experience.
  • Project docs [partial] App projects hold repositories, design mocks, Slack threads and notes (public preview). Sources: github-copilot:nov21-app-universe.
  • Memory [supported] Copilot Memory stores repository facts and user preferences across sessions and surfaces. Sources: github-copilot:nov21-memory.
  • Scope [supported] Repository facts are per repository (not pooled, not copied to forks); preferences are per user. Sources: github-copilot:nov21-memory.
  • Provenance [supported] Repository facts cite code; user preferences cite the user's words. Sources: github-copilot:nov21-memory.
  • Correction [partial] Memories cannot be edited directly on GitHub.com; Copilot upvotes or downvotes them and users can delete them. Sources: github-copilot:nov21-memory.
  • Deletion [supported] Write-access users delete repository facts, users delete their preferences, and Business/Enterprise admins can delete preferences. Sources: github-copilot:nov21-memory.
  • Freshness [supported] Memories expire after 90 days by default (7-180 configurable for repository facts); citations are checked against the current branch. Sources: github-copilot:nov21-memory.
  • Takeover continuity [partial] Repository facts are visible to read-access users and shared across surfaces; colleague takeover is not documented. Sources: github-copilot:nov21-memory.

Sources: github-copilot:nov07-cloud, github-copilot:nov21-memory, github-copilot:nov21-app-universe, github-copilot:nov21-app, github-copilot:nov21-cloud-experience

Agent cross-checked partial

GitHub chat documents semantic code search limited to default branches. Built-in connectors (Sentry, Linear, Cloudflare), MCP servers and Slack or Figma context. Voice and image input on Mobile; image generation in the app; Playwright screenshots in cloud agent. Memory citations are checked against the current branch. Chat is scoped to one organization or personal repositories by default; the GitHub MCP token is repository-scoped and read-only. Memory facts cite supporting code.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Architecture and API awareness: first-party sources in this pass did not establish indexing, api_retrieval, conflict_detection, review_enforcement. No shared requirement-to-implementation, backlog evolution or authoritative-record round-trip fixture was run. Instructions and per-task plans do not prove living specifications.
10 atomic answers
  • Indexing [unknown] Not established for indexing in the named first-party source pass. Product access and scenario tests were not run.
  • External knowledge [supported] Built-in connectors (Sentry, Linear, Cloudflare), MCP servers and Slack or Figma context. Sources: github-copilot:nov21-app-universe, github-copilot:nov21-cloud-experience.
  • Multimodal inputs [supported] Voice and image input on Mobile; image generation in the app; Playwright screenshots in cloud agent. Sources: github-copilot:nov21-mcp, github-copilot:nov21-app-universe, github-copilot:nov21-cloud-experience.
  • Freshness [partial] Memory citations are checked against the current branch. Sources: github-copilot:nov21-memory.
  • Access scope [supported] Chat is scoped to one organization or personal repositories by default; the GitHub MCP token is repository-scoped and read-only. Sources: github-copilot:nov21-mcp, github-copilot:nov21-cloud-experience.
  • Api retrieval [unknown] Not established for api retrieval in the named first-party source pass. Product access and scenario tests were not run.
  • Citations [partial] Memory facts cite supporting code. Sources: github-copilot:nov21-memory.
  • Conflict detection [unknown] Not established for conflict detection in the named first-party source pass. Product access and scenario tests were not run.
  • Review enforcement [unknown] Not established for review enforcement in the named first-party source pass. Product access and scenario tests were not run.

Sources: github-copilot:nov07-cloud, github-copilot:nov21-mcp, github-copilot:nov21-cloud-experience, github-copilot:nov21-memory, github-copilot:nov21-app-universe

Agent cross-checked partial

Copilot drafts GitHub repository issues for human submission. Copilot drafts updates to existing repository issues. Drafted issue fields include labels. Drafted issue fields include assignees. GitHub issues are repository records that can precede an implementation session. Generated issues use repository issue forms/templates and structured fields. Issue and PR comments; only write-access users' comments reach the agent. Project custom fields such as Size can filter issues in the app; a priority field was not checked. The app browses and searches issues. The app filters issues and PRs by custom fields; Mobile filters sessions. Issues close and reopen (both are automation triggers); archiving was not established. Issue reopened is an automation trigger. Projects group issues by parent issue. An issue exists without a running agent until it is assigned to Copilot or a session starts from it. Assign an issue to Copilot or start a session from it. Issues have open, closed and status changes; sessions have task states. No external tracker is needed; GitHub Issues is built in.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Partial atomic answers name their limits: prioritize, archive, durable_states. No configured product fixture was run.
17 atomic answers

Sources: github-copilot:gap07-issues, github-copilot:nov21-automation-tools, github-copilot:nov21-risks, github-copilot:nov21-tasks-api, github-copilot:nov21-app, github-copilot:nov21-mobile, github-copilot:nov21-app-v120, github-copilot:nov21-sub-issues

Agent cross-checked partial

Copilot can propose issue creation with human draft review. Copilot can propose updates to an existing issue. Issue drafts can include assignees. The user reviews and refines an issue draft before submitting. The same issue numbers and URLs are used through the gh CLI and the GitHub MCP server. The GitHub MCP server reads issues and PRs. Copilot appears as an issue assignee; agent self-claiming is not documented. Granted tools can mark PRs ready or draft and merge them; issue state writes depend on tool scope. The gh CLI edits blocked-by links; agent use of them is not documented. Results are PRs and issue artifacts (public preview); app sessions attach artifacts automatically. Commits are authored by Copilot with the requester as co-author; shared automations act as Copilot; Slack/Teams items carry an attribution line. Write access is required; automation tools can be limited to Only this issue.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: children, conflicts. No configured product fixture was run; documentation does not establish successful hands-on behavior.
14 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:gap07-issues, github-copilot:nov21-automations, github-copilot:nov21-risks, github-copilot:nov21-slack-teams, github-copilot:nov21-mobile, github-copilot:nov21-dependencies, github-copilot:nov21-cloud-overview, github-copilot:nov21-mcp, github-copilot:nov21-issue-artifacts, github-copilot:nov21-automation-tools

No sourced public finding not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

Coordination and automation

COORD-01

Parallel work

Agent cross-checked partial

The Copilot app runs multiple sessions simultaneously. Independent workstreams can run concurrently. The app sidebar groups agent sessions by repository.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
  • Unknown after the targeted first-party documentation, release and repository pass: quotas, observed_concurrency. No configured product fixture was run; documentation does not establish successful hands-on behavior.
5 atomic answers
  • Concurrent sessions [supported] The Copilot app runs multiple sessions simultaneously. Sources: github-copilot:gap07-desktop.
  • Concurrent tasks [supported] Independent workstreams can run concurrently. Sources: github-copilot:gap07-desktop.
  • Quotas [unknown] Not established for quotas in the named first-party source pass. Product access and scenario tests were not run.
  • Observed concurrency [unknown] Not established for observed concurrency in the named first-party source pass. Product access and scenario tests were not run.
  • Status visibility [supported] The app sidebar groups agent sessions by repository. Sources: github-copilot:gap07-desktop.

Sources: github-copilot:gap07-desktop

Agent cross-checked partial

The orchestrator assigns context and tools to subagent tasks. Work is assigned through GitHub issue Assignees, including assigning Copilot to an issue. Agent tasks report a queued state; queue management is not documented. Automations route repository events, schedules, API calls and other automation runs to agent runs; Copilot Fusion routes models, not work. Cloud agent can push only to its own copilot/ branch or to the PR branch it was asked to work on; this restricts the agent, not human ownership.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: claims, duplicate_prevention. No configured product fixture was run; documentation does not establish successful hands-on behavior.
7 atomic answers
  • Human assignment [supported] Work is assigned through GitHub issue Assignees, including assigning Copilot to an issue. Sources: github-copilot:nov21-mobile, github-copilot:nov21-sub-issues.
  • Agent assignment [supported] The orchestrator assigns context and tools to subagent tasks. Sources: github-copilot:gap07-fleet.
  • Claims [unknown] Not established for claims in the named first-party source pass. Product access and scenario tests were not run.
  • Queues [partial] Agent tasks report a queued state; queue management is not documented. Sources: github-copilot:nov21-tasks-api.
  • Routing [partial] Automations route repository events, schedules, API calls and other automation runs to agent runs; Copilot Fusion routes models, not work. Sources: github-copilot:nov21-automations, github-copilot:nov21-automation-tools, github-copilot:nov21-fusion.
  • Duplicate prevention [unknown] Not established for duplicate prevention in the named first-party source pass. Product access and scenario tests were not run.
  • Ownership enforcement [partial] Cloud agent can push only to its own copilot/ branch or to the PR branch it was asked to work on; this restricts the agent, not human ownership. Sources: github-copilot:nov21-risks.

Sources: github-copilot:gap07-fleet, github-copilot:nov21-mobile, github-copilot:nov21-sub-issues, github-copilot:nov21-risks, github-copilot:nov21-tasks-api, github-copilot:nov21-automations, github-copilot:nov21-automation-tools, github-copilot:nov21-fusion

Agent cross-checked partial

The main agent is the orchestrator and assigns subagent tasks. Custom agents or models can specialize suitable subtasks. The orchestrator reviews and combines child results. The product-owned Copilot main agent manages child workflow and dependencies. /fleet analyzes task decomposition and starts eligible subagents. /fleet is available in the app and CLI. Partner agents (Claude and Codex, public preview) run as separate sessions; a Copilot coordinator directing them is not documented. Partner agents (public preview) use the user's Copilot sign-in and subscription; enabling them installs a GitHub App per agent. Session logs show progress in real time; per-child progress for coordinated agents is not documented. Partner agent PRs (public preview) accept follow-up requests through PR comments.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: messages, retained_results. No configured product fixture was run; documentation does not establish successful hands-on behavior.
12 atomic answers
  • Roles [supported] The main agent is the orchestrator and assigns subagent tasks. Sources: github-copilot:gap07-fleet.
  • Model harness effort [supported] Custom agents or models can specialize suitable subtasks. Sources: github-copilot:gap07-fleet.
  • Messages [unknown] Not established for messages in the named first-party source pass. Product access and scenario tests were not run.
  • Results return [supported] The orchestrator reviews and combines child results. Sources: github-copilot:gap07-fleet.
  • Cross harness [partial] Partner agents (Claude and Codex, public preview) run as separate sessions; a Copilot coordinator directing them is not documented. Sources: github-copilot:nov21-third-party-agents.
  • Orchestration owner [supported] The product-owned Copilot main agent manages child workflow and dependencies. Sources: github-copilot:gap07-fleet.
  • Activation [supported] /fleet analyzes task decomposition and starts eligible subagents. Sources: github-copilot:gap07-fleet.
  • Authentication [supported] Partner agents (public preview) use the user's Copilot sign-in and subscription; enabling them installs a GitHub App per agent. Sources: github-copilot:nov21-third-party-agents.
  • Live progress [partial] Session logs show progress in real time; per-child progress for coordinated agents is not documented. Sources: github-copilot:nov21-agent-management.
  • Retained results [unknown] Not established for retained results in the named first-party source pass. Product access and scenario tests were not run.
  • Followup [partial] Partner agent PRs (public preview) accept follow-up requests through PR comments. Sources: github-copilot:nov21-third-party-agents.
  • Invocation [supported] /fleet is available in the app and CLI. Sources: github-copilot:gap07-fleet.

Sources: github-copilot:gap07-fleet, github-copilot:nov21-third-party-agents, github-copilot:nov21-agent-management

Agent cross-checked partial

Automations run on schedules. Repository events and API requests can trigger an automation. Saved automation definitions run repeatedly. Cloud automations run on GitHub infrastructure. A per-run AI credit limit (minimum 30) stops a run; task completion criteria are not documented. Automations run in the cloud and are managed from the Agents tab, the app, VS Code or the REST API.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: overlaps, retries. No configured product fixture was run; documentation does not establish successful hands-on behavior.
8 atomic answers
  • Schedules [supported] Automations run on schedules. Sources: github-copilot:gap07-automations.
  • Events [supported] Repository events and API requests can trigger an automation. Sources: github-copilot:gap07-automations.
  • Recurring tasks [supported] Saved automation definitions run repeatedly. Sources: github-copilot:gap07-automations.
  • Completion conditions [partial] A per-run AI credit limit (minimum 30) stops a run; task completion criteria are not documented. Sources: github-copilot:nov21-automations.
  • Scheduler location [supported] Cloud automations run on GitHub infrastructure. Sources: github-copilot:gap07-automations.
  • Overlaps [unknown] Not established for overlaps in the named first-party source pass. Product access and scenario tests were not run.
  • Retries [unknown] Not established for retries in the named first-party source pass. Product access and scenario tests were not run.
  • Client independence [supported] Automations run in the cloud and are managed from the Agents tab, the app, VS Code or the REST API. Sources: github-copilot:nov21-automations.

Sources: github-copilot:nov07-cloud, github-copilot:gap07-automations, github-copilot:nov21-automations

Agent cross-checked partial

Steer this session sends further direction from a project. Needs input groups decisions, reviews and permission requests. A stopped cloud sandbox session keeps a snapshot and resumes later; pausing a running task without stopping is not documented. Remote control can stop a session; agent tasks have a cancelled state. A stopped cloud sandbox session resumes with files and work intact from any client. Mobile live notifications include a Waiting for user input state. App projects run agents in the background and check in when they need the user. Tasks report failed and timed_out states; security validation results and actions appear in the session log. Remote control mirrors CLI permission approvals and questions to GitHub Mobile and github.com. Session data is retained 28 days for Actions-based sessions and for the life of the account for cloud sandbox sessions.

Scope
Surfaces: GitHub Copilot CLI · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: local, managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Partial atomic answers name their limits: pause, escalation, visible_errors, chat_terminal_parity. No configured product fixture was run.
10 atomic answers

Sources: github-copilot:nov07-cli, github-copilot:gap07-projects, github-copilot:nov21-remote-control, github-copilot:nov21-app-universe, github-copilot:nov21-live-notifications, github-copilot:nov21-cloud-sandboxes, github-copilot:nov21-cloud-overview, github-copilot:nov21-tasks-api, github-copilot:nov21-risks

Agent cross-checked partial

A project coordinates related sessions across repositories. Project Overview groups work needing input. Users reopen project sessions, conversations, changes and plans. Blocked issues show a Blocked icon on project boards and Issues pages.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: fleet_fixture, workload, navigation_errors, fixture_mode. No configured product fixture was run; documentation does not establish successful hands-on behavior.
8 atomic answers
  • Fleet fixture [unknown] Not established for fleet fixture in the named first-party source pass. Product access and scenario tests were not run.
  • Parent child [supported] A project coordinates related sessions across repositories. Sources: github-copilot:gap07-projects.
  • Dependencies [partial] Blocked issues show a Blocked icon on project boards and Issues pages. Sources: github-copilot:nov21-dependencies.
  • Attention [supported] Project Overview groups work needing input. Sources: github-copilot:gap07-projects.
  • History [supported] Users reopen project sessions, conversations, changes and plans. Sources: github-copilot:gap07-projects.
  • Workload [unknown] Not established for workload in the named first-party source pass. Product access and scenario tests were not run.
  • Navigation errors [unknown] Not established for navigation errors in the named first-party source pass. Product access and scenario tests were not run.
  • Fixture mode [unknown] Not established for fixture mode in the named first-party source pass. Product access and scenario tests were not run.

Sources: github-copilot:gap07-projects, github-copilot:nov21-dependencies

Agent cross-checked partial

Chats run without a branch or workspace, and a focused session can start directly in one repository. App projects span repositories and agents (public preview). The app offers Interactive, Plan and Autopilot modes; no preset is required. Automations can propose changes to their own tools, triggers and prompts for the user to apply or dismiss. Model and reasoning effort are set per session; custom agent profiles configure instructions and tools. Users steer cloud sessions mid-run; the app can change sandboxing for an active local session. Business and Enterprise need the app policy (CLI policy also for remote control); partner agents need enabling by policy.

Scope
Surfaces: GitHub Copilot app, GitHub Copilot cloud agent, GitHub Copilot CLI · Version: Public first-party sources checked 2026-11-21; no installed release tested · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-21 (1 day old)
Agent cross-check
2026-11-21
  • Unknown after the 2026-11-21 targeted first-party documentation, release and repository pass: live_roles, retained_relationships, discoverability. No configured product fixture was run; documentation does not establish successful hands-on behavior.
10 atomic answers

Sources: github-copilot:nov21-cli, github-copilot:nov21-custom-agents, github-copilot:nov21-app, github-copilot:nov21-third-party-agents, github-copilot:nov21-remote-control, github-copilot:nov21-app-universe, github-copilot:nov21-local-sandbox, github-copilot:nov21-agent-management, github-copilot:nov21-automations

Execution and reliability

Agent cross-checked partial

Default project tasks run against the local machine; --cloud selects GitHub-hosted compute instead. Copilot sessions can run on a registered user-managed Linux machine. Cloud sandboxes and Actions-based sessions execute remotely; Actions can use configured self-hosted runners. The user supplies and maintains a Linux execution host and registers it with Copilot. The user is responsible for custom host infrastructure and lifecycle. A cloud sandbox continues working without the client staying connected. Cloud sessions can be continued across supported Copilot clients. Actions-based sessions can run on ARC self-hosted runners; the Copilot service is GitHub-hosted and unavailable for GitHub Enterprise Server. App sessions run locally or in the cloud; cloud sessions can be opened in VS Code or CLI.

Scope
Surfaces: GitHub Copilot CLI, GitHub Copilot cloud agent, GitHub Mobile · Version: GitHub Copilot plans, billing docs and changelog retrieved 2026-11-12 (app v1.2.0, CLI v1.0.109) · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: local, managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: region. No configured product fixture was run; documentation does not establish successful hands-on behavior.
12 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:nov07-cli, github-copilot:gap07-custom-environment, github-copilot:gap07-sandboxes, github-copilot:nov12-cl-cloud-exp, github-copilot:nov12-sandbox-billing, github-copilot:nov21-agent-management, github-copilot:nov21-app, github-copilot:nov21-plans, github-copilot:nov21-actions-env

Agent cross-checked partial

Desktop sessions use Git worktrees and local OS sandbox restrictions. Actions-based cloud-agent sessions can use fresh hosted virtual machines. Current cloud-sandbox documentation does not establish its container or VM implementation. Repositories are cloned into each cloud sandbox. Cloud sandbox commands cannot touch local files; local sandboxing applies path rules. Local sandboxing contains spawned processes; built-in CLI file tools run in-process outside it. Cloud sessions follow the firewall allowlist; local sandboxing has per-host rules. The local proxy swaps credential placeholders for approved hosts; COPILOT_MCP_ secrets serve MCP servers. Local sandboxing is lightweight OS containment, not a VM; trusted-directory scoping is heuristic.

Scope
Surfaces: GitHub Copilot CLI, GitHub Copilot cloud agent, GitHub Mobile · Version: Public source baseline 2026-11-07; targeted mobile browser, VM, shared-human prompting and pricing corrections checked 2026-11-13; no installed-product test · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: local, managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • The scoped first-party source pass does not establish container. No hands-on scenario was run.
12 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:nov07-cli, github-copilot:gap07-desktop, github-copilot:facet38-actions-vm, github-copilot:nov21-cloud-sandboxes, github-copilot:nov21-local-sandbox, github-copilot:nov21-risks, github-copilot:nov21-mcp, github-copilot:nov21-cli

Agent cross-checked partial

The user does not need to stay connected while a cloud sandbox works. Returning to a stopped cloud session resumes files and in-progress work. Stopped cloud sandboxes retain a state snapshot. Session logs reopen from the session list. Remote control streams a live CLI session while the machine stays online. The CLI auto-compacts at about 95% of the token limit.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: GitHub Copilot plans, billing docs and changelog retrieved 2026-11-12 (app v1.2.0, CLI v1.0.109) · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: worker_crash, service_restart, duplicate_actions, manual_repair, multi_day_continuity. No configured product fixture was run; documentation does not establish successful hands-on behavior.
12 atomic answers
  • Client disconnect [supported] The user does not need to stay connected while a cloud sandbox works. Sources: github-copilot:gap07-sandboxes.
  • Worker crash [unknown] Not established for worker crash in the named first-party source pass. Product access and scenario tests were not run.
  • Service restart [unknown] Not established for service restart in the named first-party source pass. Product access and scenario tests were not run.
  • Expiry [partial] Cloud sandboxes have no one-hour cap; stopped sandboxes keep a billed snapshot until deleted. Sources: github-copilot:nov12-cl-cloud-exp, github-copilot:nov12-sandbox-billing.
  • Transcript reload [supported] Session logs reopen from the session list. Sources: github-copilot:nov21-cloud-overview, github-copilot:nov21-agent-management.
  • Process reconnect [partial] Remote control streams a live CLI session while the machine stays online. Sources: github-copilot:nov21-cloud-overview, github-copilot:nov21-remote-control.
  • Task resume [supported] Returning to a stopped cloud session resumes files and in-progress work. Sources: github-copilot:gap07-sandboxes.
  • State reconstruction [supported] Stopped cloud sandboxes retain a state snapshot. Sources: github-copilot:gap07-sandboxes.
  • Context loss [partial] The CLI auto-compacts at about 95% of the token limit. Sources: github-copilot:nov21-cli.
  • Duplicate actions [unknown] Not established for duplicate actions in the named first-party source pass. Product access and scenario tests were not run.
  • Manual repair [unknown] Not established for manual repair in the named first-party source pass. Product access and scenario tests were not run.
  • Multi day continuity [unknown] Not established for multi day continuity in the named first-party source pass. Product access and scenario tests were not run.

Sources: github-copilot:gap07-sandboxes, github-copilot:nov12-cl-cloud-exp, github-copilot:nov12-sandbox-billing, github-copilot:nov21-cli, github-copilot:nov21-cloud-overview, github-copilot:nov21-remote-control, github-copilot:nov21-agent-management

Agent cross-checked partial

Cloud sandbox state is snapshotted while a session is stopped. Cloud personalizations can use a dotfiles repository; no dotfile install scripts are run. copilot-setup-steps preinstalls tools for Actions sessions; sandboxes copy .copilot dotfiles without running install scripts. The setup steps example caches npm; no general cache feature is described. services is honoured only in Actions setup steps. Agent secrets and variables; COPILOT_MCP_ secrets for MCP servers.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: ports, duplicate_installs, collisions, automatic_repair. No configured product fixture was run; documentation does not establish successful hands-on behavior.
10 atomic answers
  • Dependencies [supported] copilot-setup-steps preinstalls tools for Actions sessions; sandboxes copy .copilot dotfiles without running install scripts. Sources: github-copilot:nov21-cloud-sandboxes, github-copilot:nov21-actions-env.
  • Caches [partial] The setup steps example caches npm; no general cache feature is described. Sources: github-copilot:nov21-actions-env.
  • Snapshots [supported] Cloud sandbox state is snapshotted while a session is stopped. Sources: github-copilot:gap07-sandboxes.
  • Services [partial] services is honoured only in Actions setup steps. Sources: github-copilot:nov21-actions-env.
  • Ports [unknown] Not established for ports in the named first-party source pass. Product access and scenario tests were not run.
  • Secrets [supported] Agent secrets and variables; COPILOT_MCP_ secrets for MCP servers. Sources: github-copilot:nov21-mcp, github-copilot:nov21-actions-env.
  • Duplicate installs [unknown] Not established for duplicate installs in the named first-party source pass. Product access and scenario tests were not run.
  • Collisions [unknown] Not established for collisions in the named first-party source pass. Product access and scenario tests were not run.
  • Remote setup [supported] Cloud personalizations can use a dotfiles repository; no dotfile install scripts are run. Sources: github-copilot:gap07-sandboxes.
  • Automatic repair [unknown] Not established for automatic repair in the named first-party source pass. Product access and scenario tests were not run.

Sources: github-copilot:gap07-sandboxes, github-copilot:nov21-actions-env, github-copilot:nov21-cloud-sandboxes, github-copilot:nov21-mcp

Agent cross-checked partial

Actions-based Copilot sessions stop after a maximum 59 minutes; the limit cannot be extended. Each automation can set AI Credit limits. Per-session AI credit cap in CLI and SDK (soft, public preview); auto-compaction. Tasks have a timed_out state; setup steps timeout is at most 59 minutes. Session limits are a soft cap; budgets can block usage; automation period limits do not stop running runs.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: turn_limits, retries, provider_failures. No configured product fixture was run; documentation does not establish successful hands-on behavior.
8 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:gap07-automations, github-copilot:nov21-sandbox-billing, github-copilot:nov21-automations, github-copilot:nov21-session-limits, github-copilot:nov21-actions-env, github-copilot:nov21-tasks-api, github-copilot:nov21-cli

Agent cross-checked partial

Session logs record work and tools used; GitHub says logs do not replace review and testing. OpenTelemetry from CLI, the app and VS Code Agent Host; content capture off by default. AI usage CSV reports and the usage metrics API. The usage metrics API reports distinct and top custom agents, skills and MCP servers per user and per organization; outcome statistics per agent are not documented. Tasks report failed and timed_out states. Tasks report a waiting_for_user state. The Fusion benchmark score is vendor-reported without fixture or attempt detail.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Truthful status and operational statistics: first-party sources in this pass did not establish failure_reasons, task_stats, project_stats, time_stats, reconnect_consistency, responsiveness. No client-disconnect, crash/restart, resource-pressure or invoice-reconciliation fixture was run. Documented persistence is distinct from measured recovery.
13 atomic answers
  • Logs [supported] Session logs record work and tools used; GitHub says logs do not replace review and testing. Sources: github-copilot:nov07-cloud.
  • Traces [partial] OpenTelemetry from CLI, the app and VS Code Agent Host; content capture off by default. Sources: github-copilot:nov21-telemetry-capture.
  • Failure reasons [unknown] Not established for failure reasons in the named first-party source pass. Product access and scenario tests were not run.
  • Usage export [supported] AI usage CSV reports and the usage metrics API. Sources: github-copilot:nov21-s2s-auth, github-copilot:nov21-usage-metrics.
  • Task stats [unknown] Not established for task stats in the named first-party source pass. Product access and scenario tests were not run.
  • Agent stats [partial] The usage metrics API reports distinct and top custom agents, skills and MCP servers per user and per organization; outcome statistics per agent are not documented. Sources: github-copilot:nov21-usage-metrics.
  • Project stats [unknown] Not established for project stats in the named first-party source pass. Product access and scenario tests were not run.
  • Time stats [unknown] Not established for time stats in the named first-party source pass. Product access and scenario tests were not run.
  • Failure status [supported] Tasks report failed and timed_out states. Sources: github-copilot:nov21-tasks-api.
  • Approval status [supported] Tasks report a waiting_for_user state. Sources: github-copilot:nov21-tasks-api.
  • Reconnect consistency [unknown] Not established for reconnect consistency in the named first-party source pass. Product access and scenario tests were not run.
  • Performance method [partial] The Fusion benchmark score is vendor-reported without fixture or attempt detail. Sources: github-copilot:nov21-fusion.
  • Responsiveness [unknown] Not established for responsiveness in the named first-party source pass. Product access and scenario tests were not run.

Sources: github-copilot:nov07-cloud, github-copilot:nov21-usage-metrics, github-copilot:nov21-tasks-api, github-copilot:nov21-fusion, github-copilot:nov21-telemetry-capture, github-copilot:nov21-s2s-auth

Agent cross-checked partial

Each subagent independently consumes model usage and can increase GitHub AI Credit consumption. CLI session limits (public preview) track credits per session with /limits; a per-task cost view on GitHub.com was not found. Session credit tracking with limits (public preview) in CLI and SDK. Billing is per token, but Copilot code review costs are published only as estimated typical ranges. /context shows token usage; billing is per token. AI usage CSV reports. The AI usage CSV includes app_client_id for app-attributed usage.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: GitHub Copilot plans, billing docs and changelog retrieved 2026-11-12 (app v1.2.0, CLI v1.0.109) · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: epic_cost, harness_aggregation, provider_reconciliation, refresh_delay. No configured product fixture was run; documentation does not establish successful hands-on behavior.
14 atomic answers
  • Task cost [partial] CLI session limits (public preview) track credits per session with /limits; a per-task cost view on GitHub.com was not found. Sources: github-copilot:nov21-session-limits.
  • Session cost [partial] Session credit tracking with limits (public preview) in CLI and SDK. Sources: github-copilot:nov21-session-limits.
  • Child cost [supported] Each subagent independently consumes model usage and can increase GitHub AI Credit consumption. Sources: github-copilot:gap07-fleet.
  • Epic cost [unknown] Not established for epic cost in the named first-party source pass. Product access and scenario tests were not run.
  • Harness aggregation [unknown] Not established for harness aggregation in the named first-party source pass. Product access and scenario tests were not run.
  • Billed vs estimated [partial] Billing is per token, but Copilot code review costs are published only as estimated typical ranges. Sources: github-copilot:nov21-model-pricing.
  • Tokens [supported] /context shows token usage; billing is per token. Sources: github-copilot:nov21-cli, github-copilot:nov21-model-pricing.
  • Subscription allowance [supported] Base plus flex credits reset monthly at 00:00 UTC on the 1st, with no carry-over. Sources: github-copilot:nov12-ubb-ind.
  • Provider reconciliation [unknown] Not established for provider reconciliation in the named first-party source pass. Product access and scenario tests were not run.
  • Compute cost [supported] Cloud sandbox compute, memory and snapshot storage are metered at published rates. Sources: github-copilot:nov12-sandbox-billing.
  • Refresh delay [unknown] Not established for refresh delay in the named first-party source pass. Product access and scenario tests were not run.
  • Alerts [supported] Budget alerts fire at 75%, 90% and 100%; product or SKU budgets can stop sandbox usage at 100%. Sources: github-copilot:nov12-plans, github-copilot:nov12-sandbox-billing.
  • Export [supported] AI usage CSV reports. Sources: github-copilot:nov21-s2s-auth.
  • Drilldown [partial] The AI usage CSV includes app_client_id for app-attributed usage. Sources: github-copilot:nov21-s2s-auth.

Sources: github-copilot:gap07-fleet, github-copilot:nov12-ubb-ind, github-copilot:nov12-sandbox-billing, github-copilot:nov12-plans, github-copilot:nov21-model-pricing, github-copilot:nov21-s2s-auth, github-copilot:nov21-session-limits, github-copilot:nov21-cli

Agent cross-checked partial

Agent tasks can be queued. Cloud sandbox memory is billed as allocated; sandbox sizes are not published and CPU or RAM limits for agent tools are not documented. Temporary rate limits tell users to wait and retry. Tasks have a cancelled state; remote control can stop sessions. Cloud sandboxes and GitHub-hosted runners draw from one included compute allowance.

Scope
Surfaces: GitHub Copilot cloud agent · Version: Public first-party sources checked 2026-11-21; no installed release tested · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-21 (1 day old)
Agent cross-check
2026-11-21
  • Unknown after the 2026-11-21 targeted first-party documentation, release and repository pass: concurrency, host_awareness, check_reuse, check_deduplication, bounded_tests, fairness, recovery. No configured product fixture was run; documentation does not establish successful hands-on behavior.
12 atomic answers
  • Concurrency [unknown] Not established for concurrency in the named first-party source pass. Product access and scenario tests were not run.
  • Queues [partial] Agent tasks can be queued. Sources: github-copilot:nov21-tasks-api.
  • Cpu ram [partial] Cloud sandbox memory is billed as allocated; sandbox sizes are not published and CPU or RAM limits for agent tools are not documented. Sources: github-copilot:nov21-sandbox-billing.
  • Backpressure [partial] Temporary rate limits tell users to wait and retry. Sources: github-copilot:nov21-usage-limits.
  • Host awareness [unknown] Not established for host awareness in the named first-party source pass. Product access and scenario tests were not run.
  • Check reuse [unknown] Not established for check reuse in the named first-party source pass. Product access and scenario tests were not run.
  • Check deduplication [unknown] Not established for check deduplication in the named first-party source pass. Product access and scenario tests were not run.
  • Bounded tests [unknown] Not established for bounded tests in the named first-party source pass. Product access and scenario tests were not run.
  • Cancellation [partial] Tasks have a cancelled state; remote control can stop sessions. Sources: github-copilot:nov21-tasks-api, github-copilot:nov21-remote-control.
  • Fairness [unknown] Not established for fairness in the named first-party source pass. Product access and scenario tests were not run.
  • Recovery [unknown] Not established for recovery in the named first-party source pass. Product access and scenario tests were not run.
  • Shared limits [partial] Cloud sandboxes and GitHub-hosted runners draw from one included compute allowance. Sources: github-copilot:nov21-sandbox-billing.

Sources: github-copilot:nov21-usage-limits, github-copilot:nov21-tasks-api, github-copilot:nov21-remote-control, github-copilot:nov21-sandbox-billing

Human collaboration and control

Agent cross-checked partial

Repository collaborators can follow shared work. Writers can each ask Copilot for changes on the same open PR using @copilot comments. Shared local-session links remain view-only; simultaneous input conflict handling is unestablished. Teams Canvas discussion around plans and changes. PR comments drive follow-up iterations. Slack/Teams attribution line and co-authored commits. Cloud sessions need a paid plan; Free keeps Copilot Chat. Cloud sessions continue without the owner connected; remote-control sessions need the owner's machine online.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public source baseline 2026-11-07; targeted mobile browser, VM, shared-human prompting and pricing corrections checked 2026-11-13; no installed-product test · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • The scoped first-party source pass does not establish presence, ordering, conflicts. No hands-on scenario was run.
11 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:facet38-shared-pr, github-copilot:nov21-risks, github-copilot:nov21-slack-teams, github-copilot:nov21-third-party-agents, github-copilot:nov21-cloud-overview, github-copilot:nov21-cloud-sandboxes, github-copilot:nov21-cloud-experience

Agent cross-checked partial

Enterprise owners set the Copilot in the cloud and third-party agent policies; organization owners block repositories, configure the cloud agent firewall and choose which enabled agents to allow. GitHub documents enterprise roles with permissions (enterprise owner, billing manager, app manager, security manager in public preview, custom roles); the current pages name no AI manager role. CLI OAuth includes authorization for organizations using SAML SSO. Without repository write access the cloud session is read-only; organization policies and SSO requirements apply. Repository read or write access sets session and automation rights. The requester cannot approve their own Copilot PR; personal vs shared automations differ in visibility, editing and identity. Seats are assigned; for card or PayPal customers seats are paid upfront and revoking a seat gives no prorated refund. Owners can suspend or uninstall apps and revoke seats. Content exclusion and organization policy management are only in Business and Enterprise.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07, organization_roles rechecked 2026-11-21; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: provisioning. No configured product fixture was run; documentation does not establish successful hands-on behavior.
9 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:gap07-offline, github-copilot:nov21-billing-changes, github-copilot:nov21-plans, github-copilot:nov21-automations, github-copilot:nov21-cloud-overview, github-copilot:nov21-s2s-auth, github-copilot:nov21-risks, github-copilot:nov21-enterprise-agent-policy, github-copilot:nov21-enterprise-roles

Agent cross-checked partial

Automation GitHub-tool writes can be scoped to all repository resources or the triggering issue. MCP tools keep separate credential scopes. Approval before tools that are not allowed; shell(COMMAND) allow and deny rules. Admin firewall allowlists; local per-host rules. The local proxy releases credentials only to approved HTTPS hosts. Workflows wait for Approve and run; humans review and merge draft PRs. Write-access users approve workflow runs; the requester cannot approve the PR. Allow once or for the session; allowlist changes apply to new sessions only. --allow-tool, --allow-all-tools and allow for the session. --deny-tool takes precedence; rejecting a request can include feedback. /sandbox disable and allowlist edits; revoking granted session approvals is not documented. The CLI asks by default; local sandboxing is off by default; the cloud firewall restricts internet access. Assisted permissions, plan mode and local sandboxing. Managed settings can require sandboxing and block when unavailable; enterprise agent-permission and MCP allowlists apply in the cloud.

Scope
Surfaces: GitHub Copilot CLI · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: local, managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: tunnels. No configured product fixture was run; documentation does not establish successful hands-on behavior.
14 atomic answers

Sources: github-copilot:nov07-cli, github-copilot:gap07-automations, github-copilot:nov21-cli, github-copilot:nov21-risks, github-copilot:nov21-local-sandbox, github-copilot:nov21-cloud-experience, github-copilot:nov21-cloud-sandboxes

Agent cross-checked partial

Shared automation definitions and runs are visible to repository readers; writers can edit them. Signed commits, session logs and audit log events. Admins see audit log events; approval records are not detailed. Issue artifacts (public preview) keep version history. Issue and PR comments. Memory and the session list persist across sessions. Admins export preferences; usage CSV; issue artifact download (public preview). 28 days for Actions sessions; account lifetime for cloud sandbox sessions. Commits are signed and Verified; the session-log integrity model is not documented.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: decisions, mutability. No configured product fixture was run; documentation does not establish successful hands-on behavior.
11 atomic answers

Sources: github-copilot:gap07-automations, github-copilot:nov21-risks, github-copilot:nov21-agent-management, github-copilot:nov21-memory, github-copilot:nov21-issue-artifacts, github-copilot:nov21-s2s-auth, github-copilot:nov21-cloud-overview

Agent cross-checked partial

The app lets users review proposed session changes and PRs in-product. The cloud flow accepts refinements before the user opens a PR. My Work and PR filters in the app. App canvases show plans, terminals, browser previews and diffs. Copilot code review comments on PRs. Agent Merge fixes CI and conflicts and can pair with auto-merge. Max review effort (public preview) runs several reviewer agents plus an aggregator.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: effort, missed_evidence, keyboard, narrow_screen, context_switching, retained_context. No configured product fixture was run; documentation does not establish successful hands-on behavior.
13 atomic answers
  • Pending reviews [partial] My Work and PR filters in the app. Sources: github-copilot:nov21-app-repo, github-copilot:nov21-app-v120.
  • Change understanding [supported] The app lets users review proposed session changes and PRs in-product. Sources: github-copilot:gap07-desktop.
  • Evidence navigation [partial] App canvases show plans, terminals, browser previews and diffs. Sources: github-copilot:nov21-app-repo.
  • Comments [supported] Copilot code review comments on PRs. Sources: github-copilot:nov21-cloud-overview.
  • Request changes [supported] The cloud flow accepts refinements before the user opens a PR. Sources: github-copilot:nov07-cloud.
  • Shipping guidance [partial] Agent Merge fixes CI and conflicts and can pair with auto-merge. Sources: github-copilot:nov21-agent-merge.
  • Effort [unknown] Not established for effort in the named first-party source pass. Product access and scenario tests were not run.
  • Missed evidence [unknown] Not established for missed evidence in the named first-party source pass. Product access and scenario tests were not run.
  • Keyboard [unknown] Not established for keyboard in the named first-party source pass. Product access and scenario tests were not run.
  • Narrow screen [unknown] Not established for narrow screen in the named first-party source pass. Product access and scenario tests were not run.
  • Context switching [unknown] Not established for context switching in the named first-party source pass. Product access and scenario tests were not run.
  • Roles [partial] Max review effort (public preview) runs several reviewer agents plus an aggregator. Sources: github-copilot:nov21-code-review-max.
  • Retained context [unknown] Not established for retained context in the named first-party source pass. Product access and scenario tests were not run.

Sources: github-copilot:nov07-cloud, github-copilot:gap07-desktop, github-copilot:nov21-cloud-overview, github-copilot:nov21-app-repo, github-copilot:nov21-app-v120, github-copilot:nov21-code-review-max, github-copilot:nov21-agent-merge

Agent cross-checked partial

Shared automations belong to the repository and keep working after the creator leaves; a colleague continuing the same interactive session is not documented. Read-access users can view automation session prompts, logs and changes. Issue artifacts (public preview) stay on the issue. Cloud sandbox sessions continue without the owner connected. Shared automation actions are attributed to Copilot.

Scope
Surfaces: GitHub Copilot cloud agent · Version: Public first-party sources checked 2026-11-21; no installed release tested · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-21 (1 day old)
Agent cross-check
2026-11-21
  • Unknown after the 2026-11-21 targeted first-party documentation, release and repository pass: ongoing_takeover, decisions, permissions, runtime_context, ownership, context_loss, harness_transfer. No configured product fixture was run; documentation does not establish successful hands-on behavior.
12 atomic answers
  • Ongoing takeover [unknown] Not established for ongoing takeover in the named first-party source pass. Product access and scenario tests were not run.
  • Same task [partial] Shared automations belong to the repository and keep working after the creator leaves; a colleague continuing the same interactive session is not documented. Sources: github-copilot:nov21-automations.
  • Session history [partial] Read-access users can view automation session prompts, logs and changes. Sources: github-copilot:nov21-automations.
  • Decisions [unknown] Not established for decisions in the named first-party source pass. Product access and scenario tests were not run.
  • Artifacts [supported] Issue artifacts (public preview) stay on the issue. Sources: github-copilot:nov21-issue-artifacts.
  • Permissions [unknown] Not established for permissions in the named first-party source pass. Product access and scenario tests were not run.
  • Runtime context [unknown] Not established for runtime context in the named first-party source pass. Product access and scenario tests were not run.
  • Owner disconnect [partial] Cloud sandbox sessions continue without the owner connected. Sources: github-copilot:nov21-cloud-sandboxes.
  • Ownership [unknown] Not established for ownership in the named first-party source pass. Product access and scenario tests were not run.
  • Attribution [partial] Shared automation actions are attributed to Copilot. Sources: github-copilot:nov21-automations.
  • Context loss [unknown] Not established for context loss in the named first-party source pass. Product access and scenario tests were not run.
  • Harness transfer [unknown] Not established for harness transfer in the named first-party source pass. Product access and scenario tests were not run.

Sources: github-copilot:nov21-issue-artifacts, github-copilot:nov21-automations, github-copilot:nov21-cloud-sandboxes

Verification and delivery

Agent cross-checked partial

Project Library retains reference material and generated artifacts. Library collects a project’s artifacts. Project sessions link to changes, plans and associated PRs. The app Changes view and pull requests show diffs. Playwright takes screenshots; images attach to issue artifacts (public preview). gh issue artifact (issue artifacts, public preview) supports video attachments and automations can upload video. App canvases and Teams Canvas show previews. Security validation results appear in the session log. Copilot code review leaves comments and an overview comment. Each agent commit message links to its session log. Session data retention is 28 days or account lifetime by environment.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: child_findings, prompt_leakage. No configured product fixture was run; documentation does not establish successful hands-on behavior.
13 atomic answers

Sources: github-copilot:gap07-projects, github-copilot:nov21-app-start, github-copilot:nov21-cloud-overview, github-copilot:nov21-slack-teams, github-copilot:nov21-app-repo, github-copilot:nov21-issue-artifacts, github-copilot:nov21-automation-tools, github-copilot:nov21-code-review-max, github-copilot:nov21-risks, github-copilot:nov21-mcp

Agent cross-checked partial

Cloud development sessions can run tests and linters; required delivery gates were not tested. Cloud agent runs tests and linters. Actions workflows run after approval; Agent Merge fixes failing workflows. Copilot code review gives a second opinion; Max effort (public preview) uses several providers. Branch protection and required checks apply to the agent. Rulesets and required checks block merge; the agent cannot merge its draft. Rulesets, Copilot approval settings and approvable paths. Copilot approval is dismissed on new commits; unattributed PRs need an extra approval.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Verification and spec gates: first-party sources in this pass did not establish types, spec_checks, requirement_conflicts. No draft PR, failed-gate, stale-approval, rollback or six-task batch-review fixture was run. Described actions do not prove delivery authority.
11 atomic answers

Sources: github-copilot:nov07-cloud, github-copilot:nov21-risks, github-copilot:nov21-agent-merge, github-copilot:nov21-code-review-max, github-copilot:nov21-cloud-overview

Agent cross-checked partial

CLI documentation gives commit and revert examples, separate from tested delivery behavior. Both Actions-based and cloud-sandbox sessions work on one branch and can open one PR per task. Further scoped facts are recorded in the atomic answers. Each task gets a copilot/ branch. Local app sessions run in their own worktrees. @copilot on a PR continues work on its branch. Agent Merge resolves merge conflicts. Sessions link to their PRs from the Agents tab.

Scope
Surfaces: GitHub Copilot CLI, GitHub Copilot cloud agent, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: local, managed-cloud · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Git and pull request workflow: first-party sources in this pass did not establish rebase. No draft PR, failed-gate, stale-approval, rollback or six-task batch-review fixture was run. Described actions do not prove delivery authority.
9 atomic answers
  • Branches [supported] Each task gets a copilot/ branch. Sources: github-copilot:nov21-risks.
  • Worktrees [supported] Local app sessions run in their own worktrees. Sources: github-copilot:nov21-app.
  • Commits [supported] CLI documentation gives commit and revert examples, separate from tested delivery behavior. Sources: github-copilot:nov07-cli.
  • Pull requests [supported] Both Actions-based and cloud-sandbox sessions work on one branch and can open one PR per task. Sources: github-copilot:nov07-cloud.
  • Comments [supported] @copilot on a PR continues work on its branch. Sources: github-copilot:nov21-risks.
  • Ci response [supported] Agent Merge can watch selected failed Actions checks or merge conflicts and work on blockers. Sources: github-copilot:nov07-cloud.
  • Rebase [unknown] Not established for rebase in the named first-party source pass. Product access and scenario tests were not run.
  • Conflicts [supported] Agent Merge resolves merge conflicts. Sources: github-copilot:nov21-agent-merge.
  • Product state [supported] Sessions link to their PRs from the Agents tab. Sources: github-copilot:nov21-agent-management.

Sources: github-copilot:nov07-cloud, github-copilot:nov07-cli, github-copilot:nov21-risks, github-copilot:nov21-agent-merge, github-copilot:nov21-agent-management, github-copilot:nov21-app

Agent cross-checked partial

The app can leave a PR review; exact revision binding and enforced authority were not established. The app offers PR merge after reviewing changes and CI status.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-07
  • Unknown after the targeted first-party documentation, release and repository pass: release, deploy, exact_revision, authority_enforcement. No configured product fixture was run; documentation does not establish successful hands-on behavior.
6 atomic answers
  • Approve [partial] The app can leave a PR review; exact revision binding and enforced authority were not established. Sources: github-copilot:gap07-desktop.
  • Merge [supported] The app offers PR merge after reviewing changes and CI status. Sources: github-copilot:gap07-desktop.
  • Release [unknown] Not established for release in the named first-party source pass. Product access and scenario tests were not run.
  • Deploy [unknown] Not established for deploy in the named first-party source pass. Product access and scenario tests were not run.
  • Exact revision [unknown] Not established for exact revision in the named first-party source pass. Product access and scenario tests were not run.
  • Authority enforcement [unknown] Not established for authority enforcement in the named first-party source pass. Product access and scenario tests were not run.

Sources: github-copilot:gap07-desktop

Agent cross-checked partial

Commit messages link to session logs. Sessions open PRs; Mobile can filter merged tasks. Mobile session filters include Open and Merged. Session logs and issue artifacts (public preview) are retained. New commits dismiss Copilot's approval.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Mobile · Version: Public first-party sources checked 2026-11-21; no installed release tested · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-21 (1 day old)
Agent cross-check
2026-11-21
  • Unknown after the 2026-11-21 targeted first-party documentation, release and repository pass: build_links, deployment_links, rollback, revert. No configured product fixture was run; documentation does not establish successful hands-on behavior.
9 atomic answers
  • Delivery status [partial] Mobile session filters include Open and Merged. Sources: github-copilot:nov21-mobile.
  • Retained evidence [partial] Session logs and issue artifacts (public preview) are retained. Sources: github-copilot:nov21-cloud-overview, github-copilot:nov21-issue-artifacts.
  • Rollback [unknown] Not established for rollback in the named first-party source pass. Product access and scenario tests were not run.
  • Revert [unknown] Not established for revert in the named first-party source pass. Product access and scenario tests were not run.
  • Stale approval invalidation [supported] New commits dismiss Copilot's approval. Sources: github-copilot:nov21-code-review-max.

Sources: github-copilot:nov21-risks, github-copilot:nov21-mobile, github-copilot:nov21-agent-management, github-copilot:nov21-cloud-overview, github-copilot:nov21-issue-artifacts, github-copilot:nov21-code-review-max

Agent cross-checked partial

My Work and PR filters in the app. PR summaries on paid plans (not Free); review overview comment. App sessions are grouped by repository. PRs can be filtered by custom fields such as Size. Review findings stay on the PR. Issue artifacts (public preview) attach to each issue. Partner agents (Claude and Codex, public preview) iterate on PR comments. Copilot approval is dismissed when new commits are pushed, so it applies to the reviewed commits. Agent Merge, combinable with auto-merge. New commits dismiss approval.

Scope
Surfaces: GitHub Copilot cloud agent, GitHub Copilot app · Version: Public first-party sources checked 2026-11-21; no installed release tested · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-21 (1 day old)
Agent cross-check
2026-11-21
  • Unknown after the 2026-11-21 targeted first-party documentation, release and repository pass: dependency_queues, check_deduplication. No configured product fixture was run; documentation does not establish successful hands-on behavior.
12 atomic answers

Sources: github-copilot:nov21-issue-artifacts, github-copilot:nov21-code-review-max, github-copilot:nov21-app, github-copilot:nov21-agent-merge, github-copilot:nov21-third-party-agents, github-copilot:nov21-app-repo, github-copilot:nov21-app-v120, github-copilot:nov21-plans

Ownership, privacy and economics

Agent cross-checked partial

Copilot application/service use is governed by custom GitHub or Microsoft terms according to purchaser and plan. Hosted Copilot service use is covered by the plan-specific service terms, not a public SDK license. The Copilot SDK (microsoft/copilot-sdk) and GitHub Agentic Workflows (github/gh-aw) are MIT licensed; the Copilot service, CLI and app are not open source. The github/app and github/copilot-cli repositories host releases, issues and licence files only, not source; the VS Code Copilot extension source is public (MIT) in microsoft/vscode/extensions/copilot. At this check: app v1.4.3 (2026-11-19; v1.2.0 released 2026-11-10), CLI v1.0.114 stable (2026-11-18) and v1.0.115-5 prerelease, SDK v2.0.1 stable (2026-11-18) and v2.0.2-preview.4 prerelease (microsoft/copilot-sdk), VS Code Copilot extension source in microsoft/vscode at bfbf12b.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: hosted_parity. No configured product fixture was run; documentation does not establish successful hands-on behavior.
6 atomic answers

Sources: github-copilot:gap07-terms, github-copilot:nov21-gh-aw, github-copilot:nov21-sdk-repo, github-copilot:nov21-app-repo, github-copilot:nov21-app-v120, github-copilot:nov21-cli-repo, github-copilot:nov21-vscode-copilot

Agent cross-checked partial

Copilot CLI can run on user infrastructure without a GitHub account in offline BYOK mode, using a local/in-network model. Hosted Copilot UI and integrations are separate. Offline mode makes no GitHub requests; a remote model endpoint still receives context if configured. BYOK CLI does not require GitHub login. Admins export user preference memories; issue artifacts (public preview) can be downloaded with gh issue artifact; AI usage is exported as CSV reports. Copilot CLI bulk-imports prepared memories. Issue artifacts (public preview) are Markdown or HTML files; creating and viewing HTML artifacts in the GitHub app is coming soon. Usage reports are CSV. Individual plan cancellation takes effect at the end of the billing cycle; usage incurred before cancelling is still owed.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public sources checked 2026-11-07; no installed release tested · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: history_portability. No configured product fixture was run; documentation does not establish successful hands-on behavior.
8 atomic answers

Sources: github-copilot:gap07-offline, github-copilot:nov21-usage-billing, github-copilot:nov21-memory, github-copilot:nov21-s2s-auth, github-copilot:nov21-issue-artifacts

Agent cross-checked partial

COPILOT_OFFLINE=true fully disables CLI telemetry and GitHub network requests; configured model-provider traffic remains. Offline BYOK can use local or in-network inference; an internet provider still receives prompts and code. Cloud sessions clone repositories into GitHub-hosted sandboxes. Chat and session data in cloud sandbox sessions is kept for the life of the account; Actions-based sessions keep data 28 days. Local sandboxing gives tools credential placeholders and a local proxy supplies real credentials only to approved hosts; personal MCP secrets are stored in Copilot settings. Session logs show the agent's work and tools; session logs and audit log events are available to administrators. Issue artifacts are stored on the issue (public preview). Session data: 28 days (Actions) or account lifetime (cloud sandbox); memories expire after 90 days by default. Memories can be deleted by users and administrators; session deletion was not established in these sources. The app signs in to GHE.com data-residency hosts; the cloud sandbox region is not stated. The OpenTelemetry identity attributes and five capture classes are documented. OpenTelemetry identity capture and all content capture classes are off by default; a separate pseudonymous user identifier exists.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: GitHub Copilot plans, billing docs and changelog retrieved 2026-11-12 (app v1.2.0, CLI v1.0.109) · Plan: First-party documentation; client, plan and execution restrictions are named per atomic answer. Unlisted parity is unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Unknown after the targeted first-party documentation, release and repository pass: subprocessors, consent_prompt. No configured product fixture was run; documentation does not establish successful hands-on behavior.
15 atomic answers
  • Code data [partial] Cloud sessions clone repositories into GitHub-hosted sandboxes. Sources: github-copilot:nov21-cloud-sandboxes.
  • Prompts [supported] Chat and session data in cloud sandbox sessions is kept for the life of the account; Actions-based sessions keep data 28 days. Sources: github-copilot:nov21-cloud-overview, github-copilot:nov21-billing-changes.
  • Credentials [partial] Local sandboxing gives tools credential placeholders and a local proxy supplies real credentials only to approved hosts; personal MCP secrets are stored in Copilot settings. Sources: github-copilot:nov21-local-sandbox, github-copilot:nov21-mcp.
  • Logs [supported] Session logs show the agent's work and tools; session logs and audit log events are available to administrators. Sources: github-copilot:nov21-cloud-overview, github-copilot:nov21-risks.
  • Artifacts [partial] Issue artifacts are stored on the issue (public preview). Sources: github-copilot:nov21-issue-artifacts.
  • Retention [supported] Session data: 28 days (Actions) or account lifetime (cloud sandbox); memories expire after 90 days by default. Sources: github-copilot:nov21-cloud-overview, github-copilot:nov21-memory.
  • Deletion [partial] Memories can be deleted by users and administrators; session deletion was not established in these sources. Sources: github-copilot:nov21-memory.
  • Training [supported] Since 2026-04-24 Free, Pro and Pro+ interaction data trains GitHub models unless the user opts out; Business, Enterprise, enterprise-owned repositories and private repository content at rest are excluded. Sources: github-copilot:nov12-training.
  • Residency [partial] The app signs in to GHE.com data-residency hosts; the cloud sandbox region is not stated. Sources: github-copilot:nov21-app-start.
  • Subprocessors [unknown] Not established for subprocessors in the named first-party source pass. Product access and scenario tests were not run.
  • Telemetry disclosure [supported] The OpenTelemetry identity attributes and five capture classes are documented. Sources: github-copilot:nov21-telemetry-capture.
  • Telemetry defaults [partial] OpenTelemetry identity capture and all content capture classes are off by default; a separate pseudonymous user identifier exists. Sources: github-copilot:nov21-telemetry-capture.
  • Telemetry controls [supported] COPILOT_OFFLINE=true fully disables CLI telemetry and GitHub network requests; configured model-provider traffic remains. Sources: github-copilot:gap07-offline.
  • Provider separation [supported] Offline BYOK can use local or in-network inference; an internet provider still receives prompts and code. Sources: github-copilot:gap07-offline.

Sources: github-copilot:gap07-offline, github-copilot:nov12-training, github-copilot:nov21-issue-artifacts, github-copilot:nov21-cloud-sandboxes, github-copilot:nov21-local-sandbox, github-copilot:nov21-mcp, github-copilot:nov21-memory, github-copilot:nov21-cloud-overview, github-copilot:nov21-risks, github-copilot:nov21-billing-changes, github-copilot:nov21-app-start, github-copilot:nov21-telemetry-capture

Agent cross-checked partial

At the 7 November check: Pro $10/month, Pro+ $39/month, Max $100/month, Business $19/granted seat/month and Enterprise $39/granted seat/month, in USD. Pro lists 1,000 base plus 500 flex credits; Pro+ 3,900 plus 3,100; Max 10,000 plus 10,000. Credit amounts are not task counts. Cloud-sandbox compute, memory and snapshot storage are billed by consumption after the shared allowance. The CLI can use a user-provided model provider API key, paid separately to that provider. Copilot Enterprise is described as designed for GitHub Enterprise Cloud enterprises, and Copilot access is $0 for GitHub Enterprise Cloud licensees; the cost of a required GitHub Enterprise Cloud plan is not stated on these pages. Usage beyond the included credits costs $0.01 per AI credit through an additional-usage budget.

Scope
Surfaces: GitHub Copilot app, GitHub Copilot CLI, GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Mobile · Version: GitHub Copilot plans, billing docs and changelog retrieved 2026-11-12 (app v1.2.0, CLI v1.0.109); targeted mobile browser, VM, shared-human prompting and pricing corrections checked 2026-11-13; no installed-product test · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Price and included usage: first-party sources did not establish seat_minimum, trial, taxes. No hands-on scenario, full license/hosted parity audit or fixed one/two/five-person workload costing was performed. Public pricing is dated; missing rates remain unknown.
12 atomic answers
  • Currency [supported] Prices are in US dollars. Sources: github-copilot:nov12-ind-plans.
  • Interval [supported] Monthly: Pro $10, Pro+ $39, Max $100; Business $19 and Enterprise $39 per granted seat. Pro and Pro+ annual plans that stayed on legacy billing after 2026-06-01 keep premium requests. Sources: github-copilot:nov12-ind-plans, github-copilot:nov12-legacy-requests.
  • Seats [supported] Individual plans are per user; Business and Enterprise are per granted seat; Copilot access is $0 for Enterprise Cloud license holders or $10 Standalone. Sources: github-copilot:nov12-ind-plans, github-copilot:nov12-cl-ent-copilot.
  • Seat minimum [unknown] Not established for seat minimum in the named first-party source pass. Product access and scenario tests were not run.
  • Workspace fees [partial] Copilot Enterprise is described as designed for GitHub Enterprise Cloud enterprises, and Copilot access is $0 for GitHub Enterprise Cloud licensees; the cost of a required GitHub Enterprise Cloud plan is not stated on these pages. Sources: github-copilot:nov21-plans.
  • Included usage [supported] Pro 1,500 credits (1,000 base + 500 flex), Pro+ 7,000, Max 20,000; Business 1,900 and Enterprise 3,900 per user; Copilot access has none. Completions stay unlimited on paid plans. Credit amounts are not task counts. Sources: github-copilot:nov12-ind-plans, github-copilot:nov12-ubb-ind.
  • Credits [supported] 1 AI credit = $0.01; usage is priced per model and token; base credits are fixed, the flex allotment may change, and nothing carries over. Sources: github-copilot:nov12-plans, github-copilot:nov12-ubb-ind.
  • Trial [unknown] Not established for trial in the named first-party source pass. Product access and scenario tests were not run.
  • Overages [supported] Usage beyond the included credits costs $0.01 per AI credit through an additional-usage budget. Sources: github-copilot:nov21-plans, github-copilot:nov21-usage-billing.
  • Taxes [unknown] Not established for taxes in the named first-party source pass. Product access and scenario tests were not run.
  • Model cost [supported] Per-token rates by model, converted to AI Credits; 10% discount for auto model selection and 30% for Fusion through 2026-11-30. The CLI can also use a user-provided model provider API key, paid separately to that provider. Sources: github-copilot:facet38-cli-byok, github-copilot:nov12-ubb-ind.
  • Compute cost [supported] Cloud sandboxes are billed by consumption after the shared allowance: $0.000024 per compute second, $0.000003 per allocated GiB-second and $0.005 per GiB-month of snapshots. Sources: github-copilot:facet38-compute-billing, github-copilot:nov12-sandbox-billing.

Sources: github-copilot:nov07-plans, github-copilot:facet38-compute-billing, github-copilot:facet38-cli-byok, github-copilot:nov12-ind-plans, github-copilot:nov12-legacy-requests, github-copilot:nov12-cl-ent-copilot, github-copilot:nov12-ubb-ind, github-copilot:nov12-plans, github-copilot:nov12-sandbox-billing, github-copilot:nov21-plans, github-copilot:nov21-usage-billing

Agent cross-checked partial

One person: Pro $10, Pro+ $39 or Max $100 per month, plus credits beyond the allowance at $0.01 and cloud sandbox compute. Billing for cloud sandbox usage begins 2026-11-23. Business for two: 2 x $19 = $38 per month with 3,800 pooled credits. Business for five: 5 x $19 = $95 per month with 5 x 1,900 = 9,500 pooled credits; overage $0.01 per credit. Token rates are published per 1M tokens per model, for example Claude Sonnet 5.5 $2 input and $10 output. Cloud sandbox compute is $0.000024 per vCPU second ($0.0864 per vCPU-hour) and memory $0.000003 per GiB second ($0.0108 per GiB-hour); sandbox sizes are not published. Billing for cloud sandbox usage begins 2026-11-23. Published seat prices: Pro $10, Pro+ $39, Max $100 per month; Business $19 and Enterprise $39 per granted seat per month. Variable costs are AI credits beyond the allowance and cloud sandbox compute, memory and storage. Billing for cloud sandbox usage begins 2026-11-23. Plans include AI credit allowances and cloud sandbox use draws from the included compute allowance. Billing for cloud sandbox usage begins 2026-11-23. Task token counts, sandbox vCPU and memory sizes and the Free credit amount are not published.

Scope
Surfaces: GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Copilot CLI, GitHub Copilot app, GitHub Mobile · Version: Public first-party sources checked 2026-11-21; no installed release tested · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-21 (1 day old)
Agent cross-check
2026-11-21
  • Unknown after the 2026-11-21 targeted first-party documentation, release and repository pass: task_assumptions, concurrency. No configured product fixture was run; documentation does not establish successful hands-on behavior.
  • Cloud sandbox meters take effect on 2026-11-23 per the 2026-10-28 cloud-experience changelog; recheck after that date.
11 atomic answers

Sources: github-copilot:nov21-sandbox-billing, github-copilot:nov21-plans, github-copilot:nov21-model-pricing, github-copilot:nov21-plans-page, github-copilot:nov21-usage-billing, github-copilot:nov21-cloud-experience

Agent cross-checked partial

Copilot is not available for GitHub Enterprise Server; model and feature availability depend on policies and spend controls. Paid plans and Copilot Business/Enterprise contact GitHub Support; GitHub Free uses Community discussions; preview features are out of support scope. GitHub Status lists Copilot and Copilot AI Model Providers components; incidents include critical 2026-10-28 and 2026-11-11 and major 2026-11-09. Models were retired on 2026-10-19 and 2026-11-16, with further deprecations announced for December; the SDK is moving to Microsoft as Microsoft Copilot SDK. Exports found: issue artifacts (public preview), administrator memory export and usage reports.

Scope
Surfaces: GitHub Copilot app, GitHub Copilot CLI, GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Mobile · Version: GitHub Copilot plans, billing docs and changelog retrieved 2026-11-12 (app v1.2.0, CLI v1.0.109) · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Availability and support: first-party sources in this pass did not establish response_commitments. No full license/hosted parity audit, assurance-report access or fixed one/two/five-person workload costing was performed. Public pricing is dated; missing rates remain unknown.
8 atomic answers

Sources: github-copilot:nov07-plans, github-copilot:nov12-cl-cloud-exp, github-copilot:nov12-app-release, github-copilot:nov12-cli-releases, github-copilot:nov21-models, github-copilot:nov21-sdk-transition, github-copilot:nov21-changelog, github-copilot:nov21-memory, github-copilot:nov21-issue-artifacts, github-copilot:nov21-status, github-copilot:nov21-support

Agent cross-checked partial

A SOC 2 Type 2 report is listed for enterprises and the 2024 post confirms Type II Copilot coverage; newer Copilot periods were not verified. Copilot Business and Enterprise were in scope of the 2024 SOC reports. 2024-04-01 to 2024-09-30 is the latest period stated in a public first-party post; later periods are not publicly stated. Enterprise owners download reports from the enterprise Compliance page; the 2024 post points to the GitHub Enterprise Trust Center. Public first-party statements checked 2026-11-21; reports themselves not inspected. Evidence is vendor statements; the gated reports were not inspected.

Scope
Surfaces: GitHub Copilot cloud agent · Version: Public first-party sources checked 2026-11-21; no installed release tested · Plan: Not specified · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
unknown
Checked
2026-11-21 (1 day old)
Agent cross-check
2026-11-21
  • Unknown after the 2026-11-21 targeted first-party documentation, release and repository pass: iso_scope, iso_issuer, iso_validity. No configured product fixture was run; documentation does not establish successful hands-on behavior.
9 atomic answers
  • Iso scope [unknown] Not established for iso scope in the named first-party source pass. Product access and scenario tests were not run.
  • Iso issuer [unknown] Not established for iso issuer in the named first-party source pass. Product access and scenario tests were not run.
  • Iso validity [unknown] Not established for iso validity in the named first-party source pass. Product access and scenario tests were not run.
  • Soc2 type [partial] A SOC 2 Type 2 report is listed for enterprises and the 2024 post confirms Type II Copilot coverage; newer Copilot periods were not verified. Sources: github-copilot:nov21-compliance, github-copilot:nov21-soc-2024.
  • Soc2 scope [partial] Copilot Business and Enterprise were in scope of the 2024 SOC reports. Sources: github-copilot:nov21-soc-2024.
  • Soc2 period [partial] 2024-04-01 to 2024-09-30 is the latest period stated in a public first-party post; later periods are not publicly stated. Sources: github-copilot:nov21-soc-2024.
  • Report access [supported] Enterprise owners download reports from the enterprise Compliance page; the 2024 post points to the GitHub Enterprise Trust Center. Sources: github-copilot:nov21-compliance, github-copilot:nov21-soc-2024.
  • Verification date [supported] Public first-party statements checked 2026-11-21; reports themselves not inspected. Sources: github-copilot:nov21-compliance.
  • Evidence status [supported] Evidence is vendor statements; the gated reports were not inspected. Sources: github-copilot:nov21-compliance, github-copilot:nov21-soc-2024.

Sources: github-copilot:nov21-compliance, github-copilot:nov21-soc-2024

Agent cross-checked partial

Free has limited features and an AI-credit allowance; the plans page says all plans include CLI and the Copilot app. Copilot in the cloud requires a paid plan; Free retains GitHub.com and GitHub Mobile chat. BYOK and local models work without a Copilot plan; provider costs apply. Projects, partner agents and the tasks API are public preview on eligible plans. Free covers the app and CLI (including with BYOK) but not Copilot in the cloud; automations require Pro or higher.

Scope
Surfaces: GitHub Copilot app, GitHub Copilot CLI, GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Mobile · Version: GitHub Copilot plans, billing docs and changelog retrieved 2026-11-12 (app v1.2.0, CLI v1.0.109) · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Useful free tier and evaluation access: first-party sources in this pass did not establish trial, credits_trial. No full license/hosted parity audit, assurance-report access or fixed one/two/five-person workload costing was performed. Public pricing is dated; missing rates remain unknown.
10 atomic answers

Sources: github-copilot:nov07-plans, github-copilot:nov12-plans, github-copilot:nov12-cl-cloud-exp, github-copilot:nov21-third-party-agents, github-copilot:nov21-tasks-api, github-copilot:nov21-app-universe, github-copilot:nov21-automations, github-copilot:nov21-plans, github-copilot:nov21-app-repo, github-copilot:nov21-byok

Agent cross-checked partial

Business/Enterprise include pooled credits with separately billed excess usage; Copilot access has no included usage allowance. Overage is $0.01 per AI credit. Partially specified: base credits, overage and model token rates are published, but the Free credit amount, flex allotment stability, sandbox sizes and code review model are not.

Scope
Surfaces: GitHub Copilot app, GitHub Copilot CLI, GitHub Copilot cloud agent, Copilot IDE agent mode, GitHub Mobile · Version: GitHub Copilot plans, billing docs and changelog retrieved 2026-11-12 (app v1.2.0, CLI v1.0.109) · Plan: Plan restrictions and client/mode boundaries are stated per atomic answer; unlisted parity remains unknown. · OS: Not specified · Execution modes: Not specified · Region: Not specified · Harness: Not specified
Availability
unknown
Delivery
native
Checked
2026-11-07 (15 days old)
Agent cross-check
2026-11-21
  • Pricing transparency: first-party sources in this pass did not establish compute_markup, model_markup, minimum_commitment. No full license/hosted parity audit, assurance-report access or fixed one/two/five-person workload costing was performed. Public pricing is dated; missing rates remain unknown.
9 atomic answers
  • Units [supported] Business/Enterprise include pooled credits with separately billed excess usage; Copilot access has no included usage allowance. Sources: github-copilot:nov07-plans.
  • Included limits [supported] Published monthly credit allowances per plan; Copilot access via Enterprise has no included credits. Sources: github-copilot:nov12-ind-plans, github-copilot:nov12-cl-ent-copilot.
  • Overages [supported] Overage is $0.01 per AI credit. Sources: github-copilot:nov21-usage-billing.
  • Compute markup [unknown] Not established for compute markup in the named first-party source pass. Product access and scenario tests were not run.
  • Model markup [unknown] Not established for model markup in the named first-party source pass. Product access and scenario tests were not run.
  • Minimum commitment [unknown] Not established for minimum commitment in the named first-party source pass. Product access and scenario tests were not run.
  • Cancellation [supported] Individual cancellation takes effect at the end of the billing cycle; usage already incurred is still owed. Sources: github-copilot:nov12-ubb-ind.
  • Sales only unknowns [partial] Copilot included with GitHub Enterprise goes through account teams; self-serve is not yet available. Sources: github-copilot:nov12-cl-ent-copilot.
  • Transparency classification [partial] Partially specified: base credits, overage and model token rates are published, but the Free credit amount, flex allotment stability, sandbox sizes and code review model are not. Sources: github-copilot:nov21-sandbox-billing, github-copilot:nov21-plans, github-copilot:nov21-usage-billing, github-copilot:nov21-model-pricing.

Sources: github-copilot:nov07-plans, github-copilot:nov12-ind-plans, github-copilot:nov12-cl-ent-copilot, github-copilot:nov12-ubb-ind, github-copilot:nov21-usage-billing, github-copilot:nov21-sandbox-billing, github-copilot:nov21-plans, github-copilot:nov21-model-pricing

Sources

github-copilot:nov07-cloud

Copilot in the cloud

GitHub distinguishes cloud sandboxes from Actions-based sessions, including repository scope, compute controls, shared logs and a 59-minute Actions limit.

Kind
documented
Locator
Environment comparison; ways to work; limitations
Source date
Not stated
Retrieved
2026-11-07
github-copilot:nov07-cli

GitHub Copilot CLI

The CLI runs interactively or by prompt, supports local/cloud sandbox modes and structured planning, and can act on GitHub issues and PRs.

Kind
documented
Locator
Supported OS; modes; sandboxing; GitHub tasks
Source date
Not stated
Retrieved
2026-11-07
github-copilot:nov07-plans

Plans for GitHub Copilot

The current plan table uses GitHub AI credits and separates free chat/client access from paid cloud work.

Kind
documented
Locator
Plan overview; individual plans; credit allowances
Source date
Not stated
Retrieved
2026-11-07
github-copilot:gap07-desktop

GitHub Copilot app

Copilot app supports macOS, Linux and Windows, separate worktrees/branches, parallel sessions and PR review/merge workflows. Organization policy governs access.

Kind
documented
Locator
Supported systems; Parallel workspaces; Workflow
Source date
Not stated
Retrieved
2026-11-07
github-copilot:gap07-mobile

GitHub Mobile

GitHub Mobile ships Android and iOS apps and supports Copilot chat and assigning issues to Copilot.

Kind
documented
Locator
Availability; Copilot features
Source date
Not stated
Retrieved
2026-11-07
github-copilot:facet38-mobile-browser

Copilot connectors

Copilot in the cloud can use connected tools from a mobile browser, as well as GitHub Mobile on iOS and Android.

Kind
documented
Locator
Where you can use connectors
Source date
Not stated
Retrieved
2026-11-13
github-copilot:nov21-cloud-sandboxes

About cloud sandboxes for GitHub Copilot

GitHub creates an isolated Linux sandbox per cloud session, clones each repository into it, and the user need not stay connected. Sessions can be picked up from any client; a stopped session keeps a snapshot and resumes with work intact. Sandbox commands cannot read or change local files. Network follows the cloud agent firewall allowlists; allowlist changes apply only to new sessions. Dotfiles .copilot are copied on create or resume without running install scripts; setup steps and self-hosted runners need Actions. Used by web, Mobile, Slack, Teams, the app, VS Code, JetBrains (preview), CLI --cloud and SDK cloud sessions.

Kind
documented
Locator
About; Continue sessions across clients; Session lifecycle; Isolation and network; Customizing; Access; Billing
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-live-notifications

GitHub Mobile: Live notifications for Copilot CLI sessions

GitHub Mobile live notifications cover cloud coding agent sessions and remote CLI sessions, with states In progress, Waiting for user input, Idle and Finished.

Kind
documented
Locator
Release note
Source date
2026-07-08
Retrieved
2026-11-21
github-copilot:nov21-cloud-experience

Work from anywhere with a new, connected Copilot cloud experience

One session continues across web, Mobile, app, VS Code and CLI with the same session list; sandboxes snapshot and resume. Mobile accepts voice and image input; Slack and Teams @GitHub create issues and sessions. Built-in connectors (Sentry, Linear, Cloudflare), key-auth MCP and skills apply. Chat sessions are scoped to one organization or personal repositories by default; enterprise agent permission and MCP allowlist settings apply. Paid plans only; Free keeps Copilot Chat.

Kind
documented
Locator
Release note (edited 2026-11-19)
Source date
2026-10-28
Retrieved
2026-11-21
github-copilot:nov21-app-v120

GitHub Copilot app v1.2.0

v1.2.0 adds an Open in menu with a GitHub Mobile QR code to continue cloud and Codespace sessions, GitHub Enterprise Server accounts in Settings > Accounts, and filtering issues and PRs by custom fields such as a Project Size.

Kind
documented
Locator
Release notes
Source date
2026-11-10
Retrieved
2026-11-21
github-copilot:gap07-partner-agents

Third-party coding agents

Paid Copilot plans support public-preview Claude Agent SDK and Codex SDK coding agents. These are named coding-agent integrations, not only models. GitHub policy must enable each partner separately.

Kind
documented
Locator
Supported agents; Costs; Availability
Source date
Not stated
Retrieved
2026-11-07
github-copilot:nov21-byok

Bring your own key for GitHub Copilot

User BYOK in VS Code, JetBrains, Xcode, Copilot CLI, the app and the SDK sends requests directly to the provider and works without a Copilot subscription; local or on-network endpoints work in air-gapped environments if reachable. Enterprise custom models (public preview) route through GitHub and need a Copilot license.

Kind
documented
Locator
BYOK configured by users; configured by an enterprise or organization; Choosing between the two
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-third-party-agents

Third-party coding agents

Anthropic Claude and OpenAI Codex coding agents are public preview, run alongside Copilot, are started from the Agents tab, issues, PR mentions, Mobile or VS Code, and must be enabled by user, organization or enterprise policy. Enabling them installs a GitHub App for each agent and they can be powered by the existing Copilot subscription. They open PRs, request review and iterate on PR comments; they are separate agent sessions.

Kind
documented
Locator
Introduction; Where you can use coding agents; Making coding agents available; Partner agents
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-models

Supported AI models in GitHub Copilot

Generally available models come from OpenAI, Anthropic, Google, Microsoft, Moonshot AI and xAI. The retirement table lists models retired on 2026-10-19 and 2026-11-16 with suggested alternatives.

Kind
documented
Locator
Supported AI models; Model retirement history
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-agent-management

Agent management

The Agents tab and Copilot home start sessions with Copilot, Anthropic Claude, OpenAI Codex or custom agents, show live session logs in real time, list active sessions, accept steering input mid-session, open a session in VS Code or Copilot CLI, and link to the resulting pull request for review and merge.

Kind
documented
Locator
About agents; Managing agents
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-cli

GitHub Copilot CLI

Interactive mode with plan mode; manual approval offers allow once, allow for the session (restored on resume) or reject with feedback. --allow-tool, --allow-all-tools and --deny-tool take shell(COMMAND), write and MCP tool specifications; deny takes precedence. /permissions assisted lets a model approve requests it judges safe. Trusted-directory scoping is heuristic. Auto-compaction runs at about 95% of the token limit; /context shows token usage. Custom instructions, custom agents, hooks, skills and Copilot Memory are supported; reasoning levels are configurable. BYOK connects OpenAI-compatible, Azure OpenAI or Anthropic endpoints, including local Ollama and vLLM.

Kind
documented
Locator
Modes of use; Steering; Automatic context management; Customizing; Trusted directories; Allowed tools; Model usage; Using your own model provider
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-app-start

Getting started with the GitHub Copilot app

Prerequisites are a GitHub account, a Copilot plan or own model provider credentials, and Git. Onboarding signs in to GitHub (GHE.com hostnames supported; GHES accounts added later), offers a plan or a model provider, then connects repositories or local folders, including clones from other Git hosts. A session is started with a mode and prompt; Changes shows the diff and Create PR opens a pull request. Customize discovers and manages plugins, skills, MCP servers and canvases.

Kind
documented
Locator
Prerequisites; Opening the app; Connecting a repository or folder; First code changes; Orienting yourself
Source date
Not stated
Retrieved
2026-11-21
github-copilot:gap07-custom-environment

Creating a custom environment

Users can register a Linux host or codespace as a custom execution environment. The user operates the host, workspace and dependencies. Closing a client does not stop the machine.

Kind
documented
Locator
Linux machine; Registration; Lifecycle
Source date
Not stated
Retrieved
2026-11-07
github-copilot:nov21-remote-control

Remote control for Copilot CLI sessions now generally available

Remote control streams a CLI session in real time to Mobile and github.com, supports non-GitHub repositories and directories without a repository, and lets users steer, review plans, stop the session, approve or deny permission requests and answer questions. Business and Enterprise need remote control and CLI policies enabled.

Kind
documented
Locator
Release note
Source date
2026-05-18
Retrieved
2026-11-21
github-copilot:nov21-cloud-overview

GitHub Copilot on GitHub.com and GitHub Mobile

Chat data is retained 28 days for Actions-based sessions and for the life of the account for cloud sandbox sessions. Without write access a session is read-only. Agentic work runs tests and linters; code review comments and suggests fixes. Hooks run commands during agent work; custom instructions (personal, repository, organization), custom agents and agent skills apply. Session logs show work and tools. Remote control keeps a CLI session on the local machine, which must stay online. Actions sessions support self-hosted runners and have a 59-minute limit. Copilot only works with GitHub-hosted repositories; new cloud experience requires a paid plan.

Kind
documented
Locator
Comparison of Actions-based sessions and cloud sandboxes; Access and availability; Ways to work; Session history; Customize; Limitations
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-tasks-api

Using Copilot cloud agent via the API

Agent tasks API (public preview) creates, lists and gets tasks by ID; states are queued, in_progress, completed, failed, idle, waiting_for_user, timed_out and cancelled. It accepts only user-to-server tokens (PAT, OAuth app, GitHub App user token); installation tokens are unsupported. REST and GraphQL issue APIs (public preview) assign GitHub issues to Copilot with target repo, base branch, instructions, custom agent and model.

Kind
documented
Locator
Agent tasks API; Authentication; Starting, listing, status; Issues API
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-s2s-auth

GitHub Copilot supports server-to-server authentication

In public preview, SDK services can use GitHub App installation tokens with the Copilot Requests organization permission; usage is billed to the organization, appears in AI usage CSV reports with app_client_id, and owners stop access by suspending or uninstalling the app.

Kind
documented
Locator
Release note
Source date
2026-10-27
Retrieved
2026-11-21
github-copilot:nov21-sdk-transition

GitHub Copilot SDK is becoming Microsoft Copilot SDK

GitHub Copilot SDK is moving in phases to the Microsoft organization as Microsoft Copilot SDK; support stays the same.

Kind
documented
Locator
Release note
Source date
2026-10-28
Retrieved
2026-11-21
github-copilot:nov21-sdk-repo

microsoft/copilot-sdk repository

github/copilot-sdk now redirects to microsoft/copilot-sdk (MIT). The README calls it Microsoft Copilot SDK for Python, TypeScript, Go, .NET, Java and Rust, exposing the Copilot CLI engine, and says it is generally available and follows semantic versioning. Its FAQ says a Copilot subscription is required unless BYOK keys are used, and SDK prompts are billed like Copilot CLI usage. Latest stable release v2.0.1 (2026-11-18, tag commit 3ce6145); the GitHub API marks v2.0.2-preview.4 (2026-11-21) as a prerelease.

Kind
documented
Locator
README: overview, FAQ (subscription, billing, BYOK), status line 154; Releases
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-memory

About GitHub Copilot Memory

Copilot Memory stores repository facts (shared with read-access collaborators, per repository, not pooled, not copied to forks) and user preferences, used across the app, CLI, code review, cloud agent, Mobile, Slack and Teams. Facts cite code and preferences cite the user's words; Copilot checks citations against the current branch and upvotes or downvotes memories. Memories cannot be created or edited directly on GitHub.com; CLI imports memories in bulk. Write-access users delete facts, users delete preferences, and Business/Enterprise admins can export or delete preferences. Default expiry is 90 days; owners can set 7-180 days for repository facts.

Kind
documented
Locator
Types of memories; Where available; Storage and ownership; How memories are created; Reinforced and retired; Retention and expiry
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-mcp

Model Context Protocol (MCP)

Cloud agent starts with the GitHub MCP server (read-only token scoped to the current repository by default) and Playwright (reads pages and takes screenshots on localhost). Connectors are GitHub-verified servers whose authentication GitHub handles. Personal MCP servers support key-based auth via COPILOT_MCP_ secrets and are only for the user. Repository administrators configure repository servers for everyone with write access; remote OAuth servers are unsupported there. The tools field allowlists tools; delegated work calls configured MCP tools without approval. The app discovers and installs MCP servers from Customize.

Kind
documented
Locator
Where you can use MCP; Default MCP servers; Personal MCP servers; Repository-level configuration; Best practices
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-custom-agents

Custom agents

Agent profiles are Markdown files with instructions that can restrict available tools and configure MCP servers; they are shared at repository, organization and enterprise level and used in the app, CLI, cloud agent and supported IDEs.

Kind
documented
Locator
About agent profiles; Where you can use custom agents
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-app

GitHub Copilot app

The desktop app is built on Copilot CLI, available on all plans (Business/Enterprise need the app policy), runs parallel sessions each in its own worktree and branch, locally or in a cloud sandbox, with Interactive, Plan and Autopilot modes, per-session model and reasoning effort, BYOK models, chats without a branch, projects spanning repositories, issue browsing and search, session start from an issue, and sessions grouped by repository.

Kind
documented
Locator
Introduction; Availability; Benefits; What can I do; Workflow
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-mobile

Using Copilot cloud agent on GitHub Mobile

On Mobile an issue is assigned to Copilot through its Assignees; sessions can be started from issues, PRs or repositories, and the session list can be searched and filtered, for example Open or Merged.

Kind
documented
Locator
Starting a session; Assigning an issue to Copilot; Tracking sessions
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-dependencies

Creating issue dependencies

Issues can be marked blocked by or blocking others; blocked issues show a Blocked icon on project boards and Issues pages; gh issue create/edit/view manage and read dependencies by issue number or URL.

Kind
documented
Locator
Marking blocked by or blocking; GitHub CLI
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-automations

Copilot automations

Automations run cloud agent on schedules, repository events or the API; they are managed from the Agents tab, the app, VS Code and the REST API. Write access is needed to create them. Shared automations act as Copilot, belong to the repository and keep working if the creator leaves; personal ones act as the creator, who cannot approve their PRs. Runs are visible to everyone with read access, including prompt, logs and changes. AI-credit limits: per run (minimum 30) stops a run; daily, weekly and monthly limits stop new runs but not running ones. Automations can propose changes to their own tools, triggers and prompts.

Kind
documented
Locator
Overview; Availability and permissions; Personal and shared automations; Triggers; Billing; Proposed improvements; Security and safety
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-automation-tools

New tools, triggers, and cost controls for Copilot Automations

Automations gain API triggers, issue triggers including closed, reopened and status changed, PR triggers, chaining, and tools to upload image or video attachments, merge PRs, mark PRs ready or draft and update comments; per-run, daily, weekly and monthly credit limits.

Kind
documented
Locator
Release note
Source date
2026-10-28
Retrieved
2026-11-21
github-copilot:nov21-slack-teams

@GitHub in Slack and Teams is generally available and more

@GitHub in Slack and Teams is GA; it creates issues, implements changes and opens PRs. Canvas in Teams shows plans, code changes and previews beside the discussion. Created issues and PRs say "Created from a Slack/Teams conversation with @username".

Kind
documented
Locator
Release note
Source date
2026-11-06
Retrieved
2026-11-21
github-copilot:nov21-risks

Risks and mitigations for GitHub Copilot cloud agent

Only write-access users trigger the agent and only their comments reach it. It pushes to one copilot/ branch or the PR branch it was asked on, subject to branch protection and required checks; it cannot mark PRs ready, approve or merge. Workflows wait for a write-access user to Approve and run. The requester cannot approve the PR; unattributed PRs need an extra approval. Internet access is firewalled. CodeQL, advisory and secret-scanning validation results and actions appear in the session log, and Copilot code review gives a second opinion. Commits are authored by Copilot with the requester as co-author, signed and Verified, and link to session logs; session logs and audit log events are available to administrators. Shared automations act as Copilot.

Kind
documented
Locator
Unvalidated code; Push changes; Sensitive information; Prompt injection; Auditability; Automations
Source date
Not stated
Retrieved
2026-11-21
github-copilot:gap07-projects

Copilot App projects

Projects retain ongoing goals, conversations, artifacts and recurring work. Overview groups Needs input, Open, Working and Done. Users inspect plans, changes and PRs and steer sessions.

Kind
documented
Locator
Tracking; Library; Recurring work
Source date
Not stated
Retrieved
2026-11-07
github-copilot:nov21-app-ga

GitHub Copilot app generally available

The app is GA on macOS, Windows and Linux; canvases are bidirectional surfaces where the user and agent operate on the same plan, pull request, terminal or browser session.

Kind
documented
Locator
Release note
Source date
2026-06-17
Retrieved
2026-11-21
github-copilot:nov21-issue-artifacts

Issue artifacts are now in public preview

Issue artifacts (public preview) attach Markdown, HTML and link artifacts to issues; app sessions attach artifacts automatically; gh issue artifact creates, edits, lists, views, downloads and deletes them, with image and video attachments; artifacts are edited on github.com with version history.

Kind
documented
Locator
Release note
Source date
2026-10-28
Retrieved
2026-11-21
github-copilot:nov21-sub-issues

Adding sub-issues

Issues take up to 100 sub-issues per parent and eight nesting levels; existing issues, including from other repositories, can be added; projects can group and filter by parent. gh issue create --parent and gh issue edit --add-sub-issue manage them.

Kind
documented
Locator
Overview; Creating; Adding existing issues; GitHub CLI
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-app-universe

GitHub Copilot app, Universe releases

App projects (public preview) hold repositories, design mocks, Slack threads and notes; Copilot coordinates agents in the background and checks in when it needs the user; focused single-repository sessions remain. Slack and Figma context and image generation are available.

Kind
documented
Locator
Release note
Source date
2026-10-28
Retrieved
2026-11-21
github-copilot:gap07-issues

Copilot issue creation and updates

In public preview, Copilot creates or updates GitHub issues from prompts/images, including title, body, labels and assignees. Humans review drafts before submission.

Kind
documented
Locator
Create; Update; Review drafts
Source date
Not stated
Retrieved
2026-11-07
github-copilot:gap07-fleet

Delegating and parallelizing

/fleet makes the main agent orchestrate subtasks and dependencies, run independent children concurrently and combine results. Each child uses its own context and additional model usage.

Kind
documented
Locator
Fleet workflow; Considerations
Source date
Not stated
Retrieved
2026-11-07
github-copilot:nov21-fusion

Route and orchestrate models with GitHub Copilot Fusion

Copilot Fusion routes and orchestrates models per prompt (single, cascade, critique). GitHub reports a Fusion Max score of 60 on the Artificial Analysis Coding Agent Index without fixture or attempt detail.

Kind
documented
Locator
Release note
Source date
2026-10-28
Retrieved
2026-11-21
github-copilot:gap07-automations

Copilot automations

Paid-plan automations trigger on schedules, repository events or API requests. Per-run credit controls and repository write scope are configurable; shared automation visibility/editing follows repository permissions.

Kind
documented
Locator
Create; Limits; Manage
Source date
Not stated
Retrieved
2026-11-07
github-copilot:nov21-local-sandbox

About local sandboxing for GitHub Copilot

Local sandboxing (CLI and app) is off by default and is lightweight OS process/filesystem containment via MXC, not a VM or container. It restricts filesystem paths, outbound and local network or per-host rules, and credentials: sandboxed tools get placeholders and a local proxy supplies real credentials only to approved HTTPS hosts. Built-in CLI file tools run in-process outside the OS sandbox and honour policy best-effort. The app can change sandboxing for an active local session. Managed settings can require sandboxing and fail closed when unavailable; /sandbox disable turns it off where policy permits bypass.

Kind
documented
Locator
Local sandboxing; How it works; Configuring; Cross-platform support; Enterprise policy enforcement
Source date
Not stated
Retrieved
2026-11-21
github-copilot:gap07-sandboxes

Cloud sandboxes

Cloud sandboxes run isolated Linux sessions without needing the client connected. Multiple sessions run in parallel; stopped sessions retain snapshots and resume files. GitHub Actions remains a separate environment option.

Kind
documented
Locator
Benefits; Lifecycle; Customization
Source date
Not stated
Retrieved
2026-11-07
github-copilot:nov12-sandbox-billing

Billing for cloud and local sandboxes

Cloud sandboxes bill $0.000024 per compute second, $0.000003 per allocated GiB-second and $0.005 per GiB-month of snapshot storage. Compute and memory draw from the plan’s included compute pool shared with GitHub-hosted runners; the repository owner (or selected/personal account) pays; product or SKU budgets can stop usage at 100%; AI-credit budgets do not apply. Local sandboxing is included in the seat.

Kind
documented
Locator
Rates; allowance; who pays; budgets
Source date
Not stated
Retrieved
2026-11-12
github-copilot:nov12-cl-cloud-exp

Work from anywhere with a new connected Copilot cloud experience

GA on paid plans from 2026-10-28: cloud tasks start from github.com, GitHub Mobile, CLI, app, VS Code, Slack or Teams; every session runs in a cloud sandbox by default with no one-hour limit on total running time; sandboxes snapshot on shutdown and resume from any surface; the included Actions entitlement becomes one dollar-based pool, with sandbox billing starting in November 2026; --environment-host registers your own machine. Free keeps Chat on github.com and Mobile only.

Kind
vendor-claimed
Locator
Full entry
Source date
2026-10-28
Retrieved
2026-11-12
github-copilot:nov21-plans

Plans for GitHub Copilot

Pro $10/month (1,000 base + 500 flex credits), Pro+ $39, Max $100; Business $19 and Enterprise $39 per granted seat per month with 1,900 and 3,900 credits per user contributed to a shared pool, overage $0.01 per credit; Copilot access $0 for GitHub Enterprise Cloud licensees or $10 standalone. Copilot Enterprise is designed for enterprises using GitHub Enterprise Cloud. Free and Student have an unspecified credit allowance. Copilot in the cloud is not in Free; PR summaries are not in Free; content exclusion and organization policy management only in Business and Enterprise. All plans include CLI and the app. Copilot is not available for GitHub Enterprise Server.

Kind
documented
Locator
Plans overview; Individual plans; Organization and enterprise plans
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-actions-env

Configure the development environment for agents on GitHub Actions

copilot-setup-steps.yml preinstalls tools for Actions-based sessions; the example caches npm dependencies; only settings such as steps, services and timeout-minutes (maximum 59) are honoured. Secrets and variables for cloud agent are configured separately. Actions sessions can run on ephemeral self-hosted runners via ARC with the integrated firewall disabled.

Kind
documented
Locator
Copilot setup steps; Preinstalling tools; Self-hosted runners
Source date
Not stated
Retrieved
2026-11-21
github-copilot:facet38-actions-vm

Building a secure cloud environment for agents

GitHub recommends hosted runners so each cloud-agent Actions job runs on a fresh virtual machine; self-hosted runners remain an alternative.

Kind
documented
Locator
Configure runners
Source date
Not stated
Retrieved
2026-11-13
github-copilot:nov21-sandbox-billing

Billing for cloud and local sandboxes for GitHub Copilot

Only cloud sandboxes are billed: compute $0.000024 per vCPU second, memory $0.000003 per allocated GiB second, snapshot storage $0.005 per GiB month. Memory is billed as allocated, not used. Sandbox compute and memory draw from the same included compute allowance as standard GitHub-hosted runners, with no priority between them. Budgets can stop usage at 100%; without a payment method usage is blocked after the quota. Sandbox vCPU and memory sizes are not published; the 2 vCPU/4 GiB case is an example.

Kind
documented
Locator
How sandbox usage is measured; Free and billed use; Pricing; Managing your budget
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-session-limits

Set AI credit session limits in Copilot CLI and SDK

CLI and SDK session limits (public preview) track AI credits across a session; /limits views or sets them and --max-ai-credits bounds a run. They are a soft cap that may be slightly exceeded and complement budgets.

Kind
documented
Locator
Release note
Source date
2026-07-01
Retrieved
2026-11-21
github-copilot:nov21-telemetry-capture

Client telemetry user attribution and configurable capture

In CLI, the app and VS Code Agent Host, OpenTelemetry identity capture (user.name, process.user.name, host.name) is off by default and separate from an existing pseudonymous identifier; prompt, response, tool argument, tool output and policy detail capture classes are each off by default and managed values take precedence.

Kind
documented
Locator
Release note
Source date
2026-10-12
Retrieved
2026-11-21
github-copilot:nov21-usage-metrics

Data available in Copilot usage metrics

Usage metrics API reports distinct and top custom agents, skills and MCP servers used per user and per enterprise or organization.

Kind
documented
Locator
User and enterprise report fields; Customization fields
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov12-plans

GitHub Copilot plans

Free $0 with no credit card, 2,000 completions a month and limited chat/agent use; Pro $10 ($15 of credits), Pro+ $39 ($70), Max $100 ($200); 1 AI credit = $0.01 USD; budget alerts at 75%, 90% and 100%; Free cannot buy extra credits.

Kind
vendor-claimed
Locator
Plan cards; comparison table
Source date
Not stated
Retrieved
2026-11-12
github-copilot:nov12-ubb-ind

Usage-based billing for individuals

Interactions are priced per model and token and converted to AI credits ($0.01 each). Base credits are fixed; the flex allotment may change. Allowance resets on the 1st at 00:00 UTC with no carry-over. Chat, CLI, cloud agent, Spaces, Spark and third-party agents consume credits; completions stay unlimited on paid plans. 10% discount for auto model selection; 30% Fusion discount through 2026-11-30. Cancellation takes effect at cycle end, with incurred usage still owed.

Kind
documented
Locator
Pricing; allotments; discounts; cancellation
Source date
Not stated
Retrieved
2026-11-12
github-copilot:nov21-model-pricing

Models and pricing for GitHub Copilot

Model prices are per 1M tokens, for example Claude Sonnet 5.5 $2.00 input and $10.00 output. Copilot code review uses an undisclosed model and publishes only estimated typical credit ranges per review effort level.

Kind
documented
Locator
Pricing tables; Copilot code review cost considerations
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-usage-limits

Usage limits for GitHub Copilot

GitHub applies temporary rate limits for capacity and fairness; users are told to wait and retry, check usage or upgrade.

Kind
documented
Locator
Rate limits; Additional usage limits; What to do if you hit a limit
Source date
Not stated
Retrieved
2026-11-21
github-copilot:facet38-shared-pr

Troubleshooting Copilot cloud agent

Copilot accepts @copilot comments on its assigned open PRs from people with repository write access; it uses those comments to continue work. This is shared PR prompting, distinct from view-only local-session sharing.

Kind
documented
Locator
Copilot will not respond to my pull request comments
Source date
Not stated
Retrieved
2026-11-13
github-copilot:gap07-offline

Copilot CLI Authentication

BYOK requires no GitHub account. COPILOT_OFFLINE=true avoids GitHub services and fully disables telemetry; only the configured provider remains. Complete airgap requires a local/in-network model. OAuth can authorize SAML organizations.

Kind
documented
Locator
Unauthenticated use; Offline mode; OAuth SSO
Source date
Not stated
Retrieved
2026-11-07
github-copilot:nov21-billing-changes

Upcoming changes to GitHub Copilot policies and billing

For card or PayPal customers, new Business and Enterprise seat assignments are paid upfront; revoking a seat gives no prorated refund. Unified Copilot on github.com retains chat data for the life of the account instead of 28 days.

Kind
documented
Locator
Release note
Source date
2026-08-28
Retrieved
2026-11-21
github-copilot:nov21-enterprise-agent-policy

Managing GitHub Copilot in the cloud for your enterprise or organization

Enterprise owners set the Copilot in the cloud policy for all or selected organizations and enable third-party agents; organization owners block the cloud agent in repositories, configure the agent firewall and choose which enabled agents to allow. The page no longer names an AI manager role.

Kind
documented
Locator
Managing the Copilot in the cloud policy; firewall; third-party agents
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-enterprise-roles

Abilities of roles in an enterprise

Predefined enterprise roles with stated permissions: enterprise owner (all settings, members and policies, including enforcing policy across organizations), billing manager, enterprise open-source license manager, app manager, security manager (public preview), user and guest collaborator, plus custom roles. No AI manager role is listed.

Kind
documented
Locator
About roles in an enterprise (table); Enterprise owners
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-agent-merge

Agent Merge watches and fixes pull requests in the cloud

Agent Merge watches a PR and fixes failing Actions workflows, merge conflicts or both in a cloud environment, and can be combined with auto-merge; paid plans.

Kind
documented
Locator
Release note
Source date
2026-10-28
Retrieved
2026-11-21
github-copilot:nov21-code-review-max

Copilot code review: Merge with confidence with Max and approvals

Max effort (public preview) runs several independent review agents across providers plus an aggregation agent. Reviews include an approval assessment in the overview comment; approvals (GA, off by default) count toward required approvals and are dismissed when new commits are pushed. Admins set default and maximum effort and which paths Copilot may approve.

Kind
documented
Locator
Release note
Source date
2026-10-28
Retrieved
2026-11-21
github-copilot:nov21-app-repo

github/app README

The public repo hosts releases, issues, discussions and changelog only (License: all rights reserved; contents .github, docs, flags, changelog, README). Any Copilot plan including Free works, or BYOK without a plan. Canvases show plans, terminals, browser previews, diffs and workflow state; My Work gathers sessions, issues and PRs.

Kind
documented
Locator
README at 6e4ad0f; repository contents; latest release v1.4.3 (2026-11-19)
Source date
Not stated
Retrieved
2026-11-21
github-copilot:gap07-terms

Additional Product Terms

Copilot use is governed by GitHub Generative AI Services Terms for direct Business/Enterprise purchases, Microsoft Product Terms for Microsoft purchases, or GitHub Terms AI section otherwise.

Kind
documented
Locator
GitHub Copilot
Source date
Not stated
Retrieved
2026-11-07
github-copilot:nov21-gh-aw

github/gh-aw repository

GitHub Agentic Workflows repository is MIT licensed per repository metadata; latest prerelease v1.3.1 published 2026-11-18.

Kind
documented
Locator
Repository metadata (license) and releases
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-cli-repo

github/copilot-cli repository

The repository contains README, changelog, install script, container files and a proprietary GitHub Copilot CLI License (run and redistribute unmodified copies), not CLI source. Latest stable release v1.0.114 (2026-11-18); prerelease v1.0.115-5 (2026-11-21).

Kind
documented
Locator
Contents and LICENSE.md at 020bbc0; releases
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-vscode-copilot

microsoft/vscode extensions/copilot

microsoft/vscode-copilot-chat (MIT) is archived and says the extension moved into microsoft/vscode; extensions/copilot at commit bfbf12b holds its source (src, package.json, LICENSE.txt).

Kind
documented
Locator
Directory listing at bfbf12b; archived microsoft/vscode-copilot-chat README
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-usage-billing

Usage-based billing for individuals

1 AI credit = $0.01; tokens are priced per model. Paid plans include fixed base credits plus a variable flex allotment that can change. After the allowance, users upgrade or set an additional-usage budget in dollars drawn down at $0.01 per credit, which may be capped. Cancellation takes effect at the end of the billing cycle; usage incurred before cancelling must still be paid and may be charged after cancellation.

Kind
documented
Locator
What are AI Credits; How AI credits work; What happens if I exceed; About changes to your plan
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov12-training

Updates to GitHub Copilot interaction data usage policy

From 2026-04-24, interaction data from Copilot Free, Pro and Pro+ is used to train models unless the user opts out under Privacy in Copilot settings; Business, Enterprise, enterprise-owned repositories and private repository content at rest are excluded. No later amendment on the page.

Kind
documented
Locator
Full post
Source date
2026-03-25
Retrieved
2026-11-12
github-copilot:facet38-compute-billing

Billing for cloud and local sandboxes

Cloud sandbox compute, memory and snapshot storage are metered. After the shared compute allowance, additional use is billed. Published rates are $0.000024 per compute second, $0.000003 per GiB-second and $0.005 per GiB-month.

Kind
documented
Locator
How sandbox usage is measured; Pricing
Source date
Not stated
Retrieved
2026-11-13
github-copilot:facet38-cli-byok

Authenticating GitHub Copilot CLI

Copilot CLI can connect to a user-provided model provider API key without GitHub authentication; GitHub-hosted features still require GitHub authentication.

Kind
documented
Locator
Unauthenticated use
Source date
Not stated
Retrieved
2026-11-13
github-copilot:nov12-ind-plans

GitHub Copilot plans (docs)

USD prices. Pro $10 with 1,000 base + 500 flex credits, Pro+ $39 with 3,900 + 3,100, Max $100 with 10,000 + 10,000. Business $19 per granted seat with 1,900 credits per user; Enterprise $39 with 3,900; Copilot access $0 for GitHub Enterprise Cloud license holders or $10 Standalone with no included credits. Copilot is not available for GHES.

Kind
documented
Locator
Individual plans; organization and enterprise plans
Source date
Not stated
Retrieved
2026-11-12
github-copilot:nov12-legacy-requests

Requests in GitHub Copilot

Premium-request billing (Pro 300, Pro+ 1,500 per month, $0.04 per extra request) now applies only to Pro and Pro+ subscribers on existing annual plans who stayed on legacy billing after 2026-06-01.

Kind
documented
Locator
Who is billed in premium requests
Source date
Not stated
Retrieved
2026-11-12
github-copilot:nov12-cl-ent-copilot

GitHub Enterprise now includes access to GitHub Copilot

Enterprises with a GitHub or Microsoft account team get Copilot for every licensed user, metered against the enterprise budget from the first request with no included credits; Copilot Standalone is $10 per user per month; completions keep working with no budget; self-serve is not yet available.

Kind
vendor-claimed
Locator
Full entry
Source date
2026-10-28
Retrieved
2026-11-12
github-copilot:nov21-plans-page

GitHub Copilot plans

Business and Enterprise list per-user monthly prices and pooled usage: included AI credits are shared organization-wide with admin spending controls.

Kind
documented
Locator
Plan cards; Business features
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov12-app-release

GitHub Copilot app v1.2.0

Published 10 Nov (2026): Open in menu with QR hand-off of cloud and Codespace sessions to GitHub Mobile, GHES accounts, custom-field filters for issues and PRs, minute-precise and cron automation schedules, multilingual dictation.

Kind
vendor-claimed
Locator
Release notes
Source date
2026-11-10
Retrieved
2026-11-12
github-copilot:nov12-cli-releases

github/copilot-cli releases

Latest release v1.0.109 on 2026-11-10; v1.0.110-0 to -3 are pre-releases.

Kind
vendor-claimed
Locator
Latest release
Source date
2026-11-10
Retrieved
2026-11-12
github-copilot:nov21-support

About GitHub Support

Paid plans, Copilot Business and Copilot Enterprise contact GitHub Support directly; GitHub Free users use Community discussions except for account, security and abuse. Preview features and Copilot output correctness are out of support scope.

Kind
documented
Locator
Plans; Scope of support
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-changelog

GitHub Changelog: Copilot label

Lists November 2026 Copilot entries, including models deprecated on 2026-11-16 and upcoming December model deprecations announced 2026-11-13 and 2026-11-17.

Kind
documented
Locator
November 2026 entries
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-status

GitHub Status incidents API

Status has Copilot and Copilot AI Model Providers components; recent incidents include critical 2026-10-28 and 2026-11-11 and major 2026-11-09 Copilot incidents.

Kind
documented
Locator
Incidents with Copilot components
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-compliance

Accessing compliance reports for your enterprise

Enterprise settings provide downloadable SOC 1 Type 2, SOC 2 Type 2, CSA CAIQ, ISO/IEC 27001:2022, CSA STAR and other reports from the Compliance page. The page does not state report periods or name Copilot scope.

Kind
documented
Locator
About compliance reports; Accessing reports
Source date
Not stated
Retrieved
2026-11-21
github-copilot:nov21-soc-2024

The latest GitHub and GitHub Copilot SOC reports are now available

SOC 1, 2 and 3 reports covering Copilot Business and Enterprise apply to 2024-04-01 to 2024-09-30 and are available on the GitHub Enterprise Trust Center; Copilot gained Type II coverage after earlier Type I reports.

Kind
documented
Locator
Release note
Source date
2024-12-06
Retrieved
2026-11-21

Comparisons with GitHub Copilot

Compare GitHub Copilot with any other product on adecomparison.com.