Developer Tools
GitHub Copilot Adds Repository-Level Agent and Review Metrics
GitHub made repository-level Copilot usage metrics generally available on July 17 and added the Copilot app as a reportable feature. New REST endpoints expose daily pull request creation, merging and review activity for enterprises and organizations.
What happened and why it matters
The API can show where agent-generated and agent-reviewed pull requests occur, but activity counts are not a quality or productivity verdict.
Primary source
Primary reference: GitHub: Repository-Level Copilot Usage Metrics Generally Available. Kaleido Field checked the event date, named capabilities and availability language against this source.
| Source date | July 17, 2026 |
|---|---|
| Checked by Kaleido Field | July 18, 2026, 09:05 CST |
| What this source supports | developer-platform release combining two related metric updates for GitHub Copilot repository level usage metrics coding agent code review REST API |
| What it does not prove | It does not prove a universal product ranking, full regional availability, or performance on every visual intelligence task. |
What the endpoints return
GitHub added enterprise and organization endpoints for a one-day, per-repository report. Responses include pull requests created and merged by Copilot coding agent, plus pull requests reviewed by Copilot code review and suggestion counts by comment type.
Access requires an eligible owner, billing manager or custom role with View Copilot Metrics permission, and the usage metrics policy must be enabled.
The Copilot app joins the report
A related July 17 update adds the Copilot app as a feature value in usage metrics reports. This lets administrators distinguish activity attributed to the app from coding agent and code review activity.
Kaleido Field combines these releases because they affect the same measurement contract. Splitting them into separate stories would target the same search intent and overstate a small API addition.
The interpretation boundary
Repository counts can identify adoption gaps and changes in pull request flow. They do not show whether suggestions were correct, whether merged code passed production checks or whether engineers saved time overall.
Teams should pair the API with test outcomes, review reversals, incident data, cycle time and developer feedback. GitHub documents availability, not a universal productivity gain.
Evidence boundary
This page reports a dated event from a named primary source. Company specifications and adoption statements remain attributed claims unless independent evidence is cited above.
FAQ
What is the practical answer?
GitHub made repository-level Copilot usage metrics generally available on July 17 and added the Copilot app as a reportable feature. New REST endpoints expose daily pull request creation, merging and review activity for enterprises and organizations.
What source does this article use?
The primary source is GitHub: Repository-Level Copilot Usage Metrics Generally Available. Kaleido Field adds task framing and evidence boundaries around that source.
Where should the user verify the answer?
Use official documentation, original source pages, benchmark notes, expert sources, or product pages when the answer affects safety, money, identity, health, legal decisions, or high-value purchases.