Copilot stopped being autocomplete and became a delivery system. the september 18 changelog adds a…
copilot stopped being autocomplete and became a delivery system. the september 18 changelog adds a sentry canvas that turns production crash reports into candidate fixes, auto model-selection tiers, and ga usage metrics for the agents window.
the agent now reports to a dashboard.
Context
GitHub's changelog of 18 September 2026, titled for the 14 September weekly release, says the Copilot app adds a Sentry canvas to review errors, stack traces and context, investigate the cause, validate a fix and prepare a pull request. Auto model selection gets efficiency, balance and intelligence tiers rolling out in VS Code, Copilot CLI and the Copilot app, and all three tiers select from the same available models. Usage metrics for the dedicated VS Code Agents window are generally available for Business and Enterprise. A 11 September changelog snippet first covered adding VS Code agents to usage metrics.
The Sentry canvas, tiers and GA metrics are first-party in the 18 September entry. Candidate fixes and autonomous delivery are the note's wording, since the changelog describes working with Copilot to investigate, validate and prepare a pull request. Became a delivery system is the author's framing. Which date is the GA date for the agents metrics is unresolved between the 11 and 18 September entries. The auto-selection tiers differ from HydraFusion, which routes between models as a research preview.
Related work
- Earlier note on the previous Copilot weekly release ↗The 7 September weekly release in the same changelog series.
Watch next
- GitHub docs on Sentry canvas availability and the rollout state of the tiers.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 21 September 2026 at 11:37 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →