feat(providers): add GitHub Copilot subscription OAuth (device flow + copilot-token re-mint)

28th platform `github-copilot` (uses_oauth, ChatCompletions wire). Two-stage auth:
RFC-8628 GitHub device flow (client Iv1.b507a08c87ecfe98, scope read:user, errors
in a 200 body) mints the DURABLE github token; a GET api.github.com/copilot_internal/
v2/token exchange re-mints the SHORT-LIVED copilot token. Persisted as key=copilot
token, refresh_token=github token, expires_at=copilot expiry; the "refresh" is a
copilot-token re-mint (not a refresh_token grant), dispatched via
OAuthTokenBody::GithubCopilotExchange in the generic refresher.

VS Code editor-identity headers on /models + /chat/completions, gated on
SamplerConfig.github_copilot / PlatformId::sends_copilot_editor_headers() so every
other ChatCompletions provider stays byte-identical. Live /models filtered
(parse_github_copilot_listing) to the openai-completions-served models: keep iff
model_picker_enabled && policy.state!="disabled" && tool_calls!=false AND not a
claude-4.x/5.x (messages) or gpt-5/oswe/mai- (responses-only) id — those need
per-model wire routing (documented debt), excluded rather than mis-routed.

Inherits the leak-safe pooled routing (scope oauth/github-copilot); its bearer/
refresh/api_key never touch the Kimi token (regression test added). Fail-fast on
an out-of-range copilot expires_at (would otherwise silently 401 mid-session).
Adversarial security review: GO, no CRITICAL/HIGH. Known limitation: Pi's
per-model policy-enablement POST is not ported (documented in AGENTS.md).

crates/codegen/kigi-shell/src/auth/oauth_registry.rs

@@ -147,6 +147,43 @@ mod tests {
             .expect("claude-pro-max carries an OAuthConfig")
     }
 
+    fn copilot_oauth() -> &'static kigi_models::OAuthConfig {
+        kigi_models::PlatformId::GithubCopilot
+            .oauth()
+            .expect("github-copilot carries an OAuthConfig")
+    }
+
+    /// A `github-copilot/<model>` turn resolves to the process-global pooled
+    /// github-copilot manager (its OWN `oauth/github-copilot` scope), NEVER the
+    /// primary Kimi manager — the same leak-safe routing as xai-grok /
+    /// claude-pro-max, and a DISTINCT pool entry from either.
+    #[tokio::test]
+    async fn github_copilot_model_resolves_to_its_own_manager_not_kimi() {
+        let (_kd, kimi) = primary_with_token("kimi-tok");
+        let home = tempfile::tempdir().unwrap();
+        let resolved = manager_for_model(home.path(), "github-copilot/gpt-4.1", Some(&kimi))
+            .expect("github-copilot model resolves to its pooled manager");
+        assert!(
+            !Arc::ptr_eq(&resolved, &kimi),
+            "github-copilot must NOT resolve to the Kimi manager"
+        );
+        assert!(
+            Arc::ptr_eq(&resolved, &global_manager_for(home.path(), copilot_oauth())),
+            "github-copilot must resolve to its OWN process-global pooled manager"
+        );
+        assert!(
+            !Arc::ptr_eq(&resolved, &global_manager_for(home.path(), claude_oauth())),
+            "github-copilot and claude-pro-max must not share a pooled manager"
+        );
+        // Fail-fast: even with a Kimi primary, a copilot turn never yields the
+        // Kimi bearer — it draws from the copilot pool (its own token, or None).
+        assert_ne!(
+            session_key_for_model(home.path(), "github-copilot/gpt-4.1", Some(&kimi)),
+            Some("kimi-tok".to_string()),
+            "a github-copilot model must never receive the primary Kimi token"
+        );
+    }
+
     /// A `claude-pro-max/<model>` turn resolves to the process-global pooled
     /// claude-pro-max manager (its OWN `oauth/claude-pro-max` scope), NEVER the
     /// primary Kimi manager — the same leak-safe routing as xai-grok, and a