OpenCode Go cuts off usage in VSCode with one days notice

OpenCode Go will begin rejecting inference API requests that lack an `x-opencode-session` header starting 09/05, a change that affects 1685 user organizations calling the service through GitHub Copilot Chat (UA `GitHubCopilotChat/0.63.0`). OpenCode Go said it needs a stable per-conversation ID for routing and optimization, and that Copilot Chat does not send the header in any version it has seen, asking the client to add `x-opencode-session: <stable-id-per-conversation>` to all outbound inference HTTP requests.

Hi — we operate the OpenCode Go managed-inference API, and 1685 of your users' orgs call it through GitHub Copilot Chat UA GitHubCopilotChat/0.63.0 . Starting 09/05, requests without an x-opencode-session header will error on our side — we need a stable per-conversation ID for routing/optimization. Copilot Chat doesn't send it in any version we've seen. Ask: include x-opencode-session: <stable-id-per-conversation on all outbound inference HTTP requests. Any stable UUID per conversation works. Happy to confirm from our telemetry once a build ships it. Thanks