Add benchmark feature

admin.tsx

@@ -2,13 +2,21 @@ import React, { useEffect, useMemo, useState } from "react";
 import { createRoot } from "react-dom/client";
 import "./admin.css";
 
+type BenchSummary = {
+  id: string;
+  status: string;
+  totalRounds: number;
+  completedRounds: number;
+} | null;
+
 type AdminSnapshot = {
   isPaused: boolean;
   isRunningRound: boolean;
   done: boolean;
   completedInMemory: number;
   persistedRounds: number;
   viewerCount: number;
+  bench?: BenchSummary;
 };
 
 type AdminResponse = { ok: true } & AdminSnapshot;
@@ -61,6 +69,7 @@ function App() {
   const [pending, setPending] = useState<string | null>(null);
   const [isResetOpen, setIsResetOpen] = useState(false);
   const [resetText, setResetText] = useState("");
+  const [benchRoundsPerPairing, setBenchRoundsPerPairing] = useState(1);
 
   useEffect(() => {
     let mounted = true;
@@ -173,6 +182,53 @@ function App() {
     }
   }
 
+  async function onBenchStart() {
+    setError(null);
+    setPending("bench-start");
+    try {
+      const response = await fetch("/api/bench/start", {
+        method: "POST",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({ roundsPerPairing: benchRoundsPerPairing }),
+        cache: "no-store",
+      });
+      if (!response.ok) {
+        const text = await response.text();
+        throw new Error(text || `Request failed (${response.status})`);
+      }
+      try {
+        const statusData = await requestAdminJson("/api/admin/status");
+        setSnapshot(statusData);
+      } catch {}
+    } catch (err) {
+      setError(err instanceof Error ? err.message : "Failed to start benchmark");
+    } finally {
+      setPending(null);
+    }
+  }
+
+  async function onBenchCancel() {
+    setError(null);
+    setPending("bench-cancel");
+    try {
+      const response = await fetch("/api/bench/cancel", {
+        method: "POST",
+        cache: "no-store",
+      });
+      if (!response.ok) {
+        throw new Error(await readErrorMessage(response));
+      }
+      try {
+        const statusData = await requestAdminJson("/api/admin/status");
+        setSnapshot(statusData);
+      } catch {}
+    } catch (err) {
+      setError(err instanceof Error ? err.message : "Failed to cancel benchmark");
+    } finally {
+      setPending(null);
+    }
+  }
+
   async function onLogout() {
     setError(null);
     setPending("logout");
@@ -263,6 +319,7 @@ function App() {
         <nav className="quick-links">
           <a href="/">Live Game</a>
           <a href="/history">History</a>
+          <a href="/bench">Bench</a>
           <button className="link-button" onClick={onLogout} disabled={busy}>
             Logout
           </button>
@@ -327,6 +384,86 @@ function App() {
         </section>
       </main>
 
+      <section className="panel panel--main" style={{ marginTop: 24 }}>
+        <div className="panel-head">
+          <h2 style={{ fontFamily: "var(--serif)", fontSize: "clamp(24px, 4vw, 36px)", lineHeight: 1 }}>
+            Benchmark
+          </h2>
+          <p>
+            Run a round-robin benchmark where every model plays against every
+            other model.{" "}
+            <a href="/bench" style={{ color: "var(--accent)", textDecoration: "none" }}>
+              View results
+            </a>
+          </p>
+        </div>
+
+        {snapshot?.bench ? (
+          <div>
+            <div className="status-grid" style={{ marginBottom: 16 }}>
+              <StatusCard label="Status" value={snapshot.bench.status} />
+              <StatusCard
+                label="Progress"
+                value={`${snapshot.bench.completedRounds}/${snapshot.bench.totalRounds}`}
+              />
+            </div>
+            <div className="actions" style={{ gridTemplateColumns: "repeat(2, minmax(0, 1fr))" }}>
+              <button
+                type="button"
+                className="btn btn--danger"
+                disabled={busy}
+                onClick={onBenchCancel}
+              >
+                {pending === "bench-cancel" ? "Cancelling..." : "Cancel Benchmark"}
+              </button>
+              <a
+                href="/bench"
+                className="btn"
+                style={{ textAlign: "center", textDecoration: "none", display: "inline-flex", alignItems: "center", justifyContent: "center" }}
+              >
+                View Live Results
+              </a>
+            </div>
+          </div>
+        ) : (
+          <div className="actions" style={{ gridTemplateColumns: "auto 1fr auto" }}>
+            <select
+              value={benchRoundsPerPairing}
+              onChange={(e) => setBenchRoundsPerPairing(Number(e.target.value))}
+              style={{
+                background: "var(--bg)",
+                border: "1px solid var(--border)",
+                color: "var(--text)",
+                fontFamily: "var(--mono)",
+                fontSize: 12,
+                padding: "10px 12px",
+                outline: "none",
+              }}
+              disabled={busy}
+            >
+              <option value={1}>1 round/pairing</option>
+              <option value={3}>3 rounds/pairing</option>
+              <option value={5}>5 rounds/pairing</option>
+            </select>
+            <button
+              type="button"
+              className="btn btn--primary"
+              disabled={busy}
+              onClick={onBenchStart}
+            >
+              {pending === "bench-start" ? "Starting..." : "Start Benchmark"}
+            </button>
+            <a
+              href="/bench"
+              className="btn"
+              style={{ textAlign: "center", textDecoration: "none", display: "inline-flex", alignItems: "center", justifyContent: "center" }}
+            >
+              Past Results
+            </a>
+          </div>
+        )}
+      </section>
+
       {isResetOpen && (
         <div className="modal-backdrop" role="dialog" aria-modal="true">
           <div className="modal">

bench-db.ts

@@ -0,0 +1,144 @@
+import { db } from "./db.ts";
+
+db.exec(`
+  CREATE TABLE IF NOT EXISTS bench_runs (
+    id TEXT PRIMARY KEY,
+    status TEXT NOT NULL DEFAULT 'running',
+    config TEXT NOT NULL,
+    started_at INTEGER NOT NULL,
+    finished_at INTEGER,
+    total_rounds INTEGER NOT NULL,
+    completed_rounds INTEGER NOT NULL DEFAULT 0,
+    error TEXT
+  );
+`);
+
+db.exec(`
+  CREATE TABLE IF NOT EXISTS bench_rounds (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    run_id TEXT NOT NULL,
+    pairing_index INTEGER NOT NULL,
+    round_num INTEGER NOT NULL,
+    data TEXT NOT NULL,
+    FOREIGN KEY (run_id) REFERENCES bench_runs(id)
+  );
+`);
+
+export type BenchRunRow = {
+  id: string;
+  status: string;
+  config: string;
+  started_at: number;
+  finished_at: number | null;
+  total_rounds: number;
+  completed_rounds: number;
+  error: string | null;
+};
+
+export type BenchRoundRow = {
+  id: number;
+  run_id: string;
+  pairing_index: number;
+  round_num: number;
+  data: string;
+};
+
+export function saveBenchRun(run: {
+  id: string;
+  status: string;
+  config: object;
+  startedAt: number;
+  totalRounds: number;
+}) {
+  db.prepare(
+    `INSERT INTO bench_runs (id, status, config, started_at, total_rounds, completed_rounds)
+     VALUES ($id, $status, $config, $started_at, $total_rounds, 0)`,
+  ).run({
+    $id: run.id,
+    $status: run.status,
+    $config: JSON.stringify(run.config),
+    $started_at: run.startedAt,
+    $total_rounds: run.totalRounds,
+  });
+}
+
+export function updateBenchRunStatus(
+  id: string,
+  update: {
+    status?: string;
+    completedRounds?: number;
+    finishedAt?: number;
+    error?: string;
+  },
+) {
+  const sets: string[] = [];
+  const params: Record<string, unknown> = { $id: id };
+
+  if (update.status !== undefined) {
+    sets.push("status = $status");
+    params.$status = update.status;
+  }
+  if (update.completedRounds !== undefined) {
+    sets.push("completed_rounds = $completed_rounds");
+    params.$completed_rounds = update.completedRounds;
+  }
+  if (update.finishedAt !== undefined) {
+    sets.push("finished_at = $finished_at");
+    params.$finished_at = update.finishedAt;
+  }
+  if (update.error !== undefined) {
+    sets.push("error = $error");
+    params.$error = update.error;
+  }
+
+  if (sets.length === 0) return;
+  db.prepare(`UPDATE bench_runs SET ${sets.join(", ")} WHERE id = $id`).run(
+    params,
+  );
+}
+
+export function saveBenchRound(round: {
+  runId: string;
+  pairingIndex: number;
+  roundNum: number;
+  data: object;
+}) {
+  db.prepare(
+    `INSERT INTO bench_rounds (run_id, pairing_index, round_num, data)
+     VALUES ($run_id, $pairing_index, $round_num, $data)`,
+  ).run({
+    $run_id: round.runId,
+    $pairing_index: round.pairingIndex,
+    $round_num: round.roundNum,
+    $data: JSON.stringify(round.data),
+  });
+}
+
+export function getBenchRuns(): BenchRunRow[] {
+  return db
+    .query("SELECT * FROM bench_runs ORDER BY started_at DESC")
+    .all() as BenchRunRow[];
+}
+
+export function getBenchRun(id: string): BenchRunRow | null {
+  return (
+    (db
+      .query("SELECT * FROM bench_runs WHERE id = $id")
+      .get({ $id: id }) as BenchRunRow | null) ?? null
+  );
+}
+
+export function getBenchRounds(runId: string): BenchRoundRow[] {
+  return db
+    .query(
+      "SELECT * FROM bench_rounds WHERE run_id = $run_id ORDER BY pairing_index ASC, round_num ASC",
+    )
+    .all({ $run_id: runId }) as BenchRoundRow[];
+}
+
+export function markStaleBenchRunsAsError() {
+  db.prepare(
+    `UPDATE bench_runs SET status = 'error', error = 'Server restarted', finished_at = $now
+     WHERE status = 'running'`,
+  ).run({ $now: Date.now() });
+}