Skip to main content
AI News

GitHub Copilot Metrics Add OpenCode and Other Clients: Requests Are Not Prompts

totals_by_client closes an off-IDE reporting gap, but client identity remains best effort

ENHE AI5 min4 views

GitHub added totals_by_client to the Copilot usage metrics API on October 23, 2026. Enterprise and organization reports can now show model traffic from OpenCode, Claude Code, Codex, Zed, Copilot CLI, GitHub apps, cloud agents, code review, VS Code, JetBrains, and other clients. This article helps administrators build reliable one-day and 28-day reports without confusing model calls with user prompts. It explains request, session, token, model, and selection-mode fields; separates client traffic from agent-app jobs; and adds checks for unknown identifiers, empty arrays, permissions, and coverage. The result is a governance trend report, not an exact invoice or individual productivity score.

More topic tags (8)
AI NewsAuto PublishingCodex研究SEOClaude CodeOpenCodeGitHub Copilot用量APItotals_by_client
GitHub Copilot Metrics Add OpenCode and Other Clients: Requests Are Not Prompts

Key takeaways

totals_by_client covers Copilot model traffic outside traditional IDE reporting.
request_count measures model calls, not user prompts.
client is a best-effort label, not a verified audit identity.

By ENHE AI · 2026-10-25 · AI-assisted drafting and editorial checks.

Direct answer: This is a client traffic view

The Copilot usage metrics API now includes totals_by_client for model traffic from tools such as OpenCode. It closes a reporting gap outside IDE telemetry, but it does not prove how much work an individual completed.

Fields and report scope

Entries include client, request_count, session_count, token_usage, and totals_by_model. They appear in enterprise, organization, and user-level one-day and 28-day reports, with model selection modes such as user_selected, auto, and product_selected.

A work context related to this task, not a product interface or test result. Image: Unsplash.
A work context related to this task, not a product interface or test result. Image: Unsplash.

Build an explainable report

Start with a known OpenCode or Codex pilot and record the date, client, and model. Compare that record with the one-day response, then inspect each day_totals entry in the 28-day report. Preserve other, unknown, and empty arrays instead of deleting awkward data.

Impact and interpretation risks

request_count counts successful model calls, and one prompt can trigger several calls. The client value comes from an integration identifier and is only best-effort; code review can report the model as unknown, so the figures are not prompt counts, invoices, or performance scores.

Frequently asked questions

Why was OpenCode missing before?

Tools outside the IDE often lack editor telemetry, so server-side request accounting closes the gap.

Does an empty array prove nobody used the tool?

No. It can mean no traffic or missing identification, so compare it with a known pilot.

Why administrators should care

Teams can see which surfaces generate model traffic and plan support, access, and training. The value is trend and coverage analysis, not individual scoring.

Related tools and reading

These pages support the same task, workflow, or risk boundary.

Conclusion

Validate client names, requests, and tokens against a known pilot before using one-day and 28-day trends for support or governance; do not treat the report as billing or employee evaluation.

What this means for everyday users

request_count counts successful model calls, and one prompt can trigger several calls. The client value comes from an integration identifier and is only best-effort; code review can report the model as unknown, so the figures are not prompt counts, invoices, or performance scores.

Related reading

GitHub Copilot Usage Metrics Adds Agent-App Activity

GitHub announced on August 7, 2026 that the Copilot Usage Metrics API now reports activity from third-party agent apps. Enterprise, organization, enterprise-user, and organization-user reports can expose the activity in one-day and 28-day windows. The new totals_by_3rd_party_agent data includes a stable agent_id and a display name that may change; the identifier should be the join key. This gives administrators a finer view of cost, permissions, and workflow adoption, but it does not automatically explain business value. Start with a read-only sample, reconcile time zones, pagination, and overlapping windows, then associate agent activity with AI credits, members, repositories, and permission changes before changing budgets or access.

GitHub Fixes Missing Copilot Agent Metrics and Lists Required IDE Updates

GitHub said on October 6, 2026 that some IDE versions moved Copilot agent sessions to the Copilot SDK without identifying the originating IDE. As a result, agent activity and agent lines-of-code metrics were omitted from reports, while some activity was attributed to Copilot CLI. VS Code 1.139.0 and later contain the fix; Visual Studio, JetBrains IDEs, Eclipse, and Xcode were scheduled to receive fixed releases between October and November. Historical activity on affected versions cannot be recovered after updating, and billing was not affected. This guide shows administrators how to inventory IDE versions, mark the reporting gap, update clients, compare post-update dashboard and API data, and avoid treating an instrumentation decline as proof that developers stopped using Copilot.

GitHub Copilot Usage API Names Custom Skills, Agents, and MCP Servers: How to Read the Report

GitHub updated the Copilot usage metrics API on October 22, 2026, so customer-defined skills, agents, MCP servers, slash commands, and plugins can appear by configured name instead of being grouped entirely under other or custom. Each totals_by_* list now includes as many as 25 entries per record, up from five. This article helps administrators turn the change into a reliable adoption report. It covers required Copilot CLI and SDK versions, a naming review before reports are shared, one-day and 28-day comparisons, and a reconciliation check against known pilots. It also explains why historical days, path-like names, outdated clients, and blocked telemetry can still undercount activity. The metrics are useful for trends and enablement, not exact billing.

GitHub Copilot Enters Xcode’s Built-In Assistant Preview: Should You Switch From the Extension?

GitHub announced on 2026-11-04 that Copilot is available in Xcode’s built-in coding assistant as a public preview starting with Xcode 27.3 beta. The setup requires a Mac running macOS Tahoe 26.6 or later, and GitHub says all Copilot plans are supported. The existing GitHub Copilot for Xcode extension remains a separate option, so this is a workflow choice rather than a forced migration. This guide provides a bounded comparison: verify the beta environment, run the same small coding task in the current extension and built-in assistant, compare context, edits, permission prompts, tests, and recovery, then keep the route that produces the clearest reviewable evidence.

Google Guided Learning Expands to Classroom and Search: Which Controls Schools Should Check First

Google announced on 2026-11-03 that Guided Learning is globally available in Google Classroom and that a Search pilot will begin in selected US schools. The company also says access to Gemini, Gemini Notebook, Gemini in Classroom, and Google Search AI products will remain entirely off for K-12 student accounts until school administrators explicitly enable them. This article separates teacher workflow from administrative authority and provides a practical readiness checklist: choose one learning objective, review the prompts students will see, confirm account and product controls, explain the activity to families and students, observe whether questions support reasoning, and keep a clear disable-and-return path if the tool distracts from learning.

Gemini Omni 1.2 Flash Adds 15-Second Video: What Creators Should Validate First

Google launched Gemini Omni 1.2 Flash on 2026-11-05 with native clips from three to fifteen seconds, multi-turn conversational editing, stronger reference following, and a listed API price of $0.07 per second for 720p video after a 30 percent reduction. A separate Google Vids announcement says Google Account and Workspace users can generate up to three fifteen-second videos per month at no cost. This guide turns those facts into one bounded creator test: prepare a simple reference pack, generate a single shot, inspect identity and product details at several points, make one controlled edit, record the real cost or allowance used, and keep a shorter fallback if the longer clip drifts.