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
Key takeaways
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.
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.
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 tutorials
[[zh]][[/zh]][[en]]Review a public website[[/en]]
SearchScope SEO/GEO
[[zh]][[/zh]][[en]]Access and usage guide[[/en]]
AI Prompt Management System | 418 Bilingual Prompts for Writing, SEO and AI Creation
High-Frequency AI Prompts for Work, Learning, and Teaching guide
High-Frequency AI Prompts for Work, Learning, and Teaching
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.
Bayer Shares Production Lessons From 22 Specialist Agents: HTTP Success Is Not Task Success
AWS published Bayer Crop Science’s Agentic Decision Engine case study on October 23, 2026. The production system runs 22 specialist agents over governed analytics workflows, models, logs, and visualization tools. This article turns the architecture into five reusable acceptance checks for enterprise agent teams: persist the state needed to resume work, define identity and authorization at every boundary, scope each agent’s tool catalog, distinguish transport success from task success, and release to a gated group before broader access. It also explains why Bayer’s adoption and resolution figures are evidence about one implementation, not promises for another organization. The focus is operational proof, least privilege, rollback, and observable outcomes rather than prompt polish.
IskayPet Connects SharePoint to a Managed Knowledge Base: Validate Permissions Before Answers
AWS published IskayPet’s corporate knowledge assistant case study on October 22, 2026. The system connects Amazon Bedrock Managed Knowledge Bases to existing SharePoint repositories and answers cited questions across retail operations, veterinary care, onboarding, and procurement in four languages and three countries. This article turns the case into a practical acceptance plan for knowledge owners. It checks source scope, inherited permissions, hybrid retrieval, duplicate and fragment removal, citation quality, feedback, and token cost before expansion. It also separates the customer’s reported production results from what another organization should expect. A managed retrieval stack reduces infrastructure work, but it does not remove content ownership, access reviews, evaluation datasets, or human verification of important answers.
Copilot in Visual Studio Adds PR Exploration, a BYOM Migration, and NuGet Fixes
GitHub summarized three September updates for Copilot in Visual Studio 2026 on October 22, 2026. The Git agent can explore an attached pull request and link back to comments and files. Bring Your Own Model remains in preview but now requires the new Agent experience, and previously configured Ollama models must be added again. NuGet Audit warnings can open Copilot Chat with the NuGet MCP server to propose dependency fixes. This article gives .NET developers a cautious upgrade checklist: preserve current settings, validate each feature independently, review package and lock-file changes, run targeted tests and vulnerability scans, and keep a rollback path. Summaries and suggested fixes remain review inputs, not verified outcomes.