Merge branch 'perf/lag': dashboard lag fixes

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

# Conflicts:
#	client/src/components/Sagi/PetSprite.tsx
#	client/src/components/Sagi/useSagiBrain.ts

server/routes/lanes.js

@@ -211,7 +211,11 @@ function featurePayload(feature) {
 /** Push the current state of one lane to every connected client. */
 function broadcastLane(id) {
   const lane = lanesLib.getLane(id);
-  if (lane) broadcast("lane_update", { lane: payload(lane) });
+  if (!lane) return;
+  // The cached list-sessions (as GET / uses), not a synchronous has-session —
+  // through sudo for a member's pane — on every hook that moves a lane.
+  const live = lane.run_id ? tmux.liveSessions() : null;
+  broadcast("lane_update", { lane: payload(lane, live) });
 }
 
 router.get("/", (req, res) => {

server/routes/metrics.js

@@ -29,6 +29,22 @@ const { calculateCost, dailyTokenRows } = require("./pricing");
 
 const router = Router();
 
+// How long the event loop was held up — what an operator sees as a laggy
+// terminal: every keystroke's echo waits for it. Sampled every 20 ms and reset
+// each minute, so the gauges describe the last minute or so.
+const LOOP_WINDOW_MS = 60_000;
+const loopDelay = require("perf_hooks").monitorEventLoopDelay({ resolution: 20 });
+loopDelay.enable();
+let loopWindow = null; // the last full minute, reported until the next one ends
+setInterval(() => {
+  loopWindow = {
+    p50: loopDelay.percentile(50),
+    p99: loopDelay.percentile(99),
+    max: loopDelay.max,
+  };
+  loopDelay.reset();
+}, LOOP_WINDOW_MS).unref();
+
 // Resolved once at load — the dashboard version, surfaced as a build-info label
 // (the canonical Prometheus idiom for exposing a version string as a metric).
 const APP_VERSION = (() => {
@@ -100,6 +116,23 @@ router.get("/", (_req, res) => {
     [{ value: process.memoryUsage().rss }]
   );
 
+  const loop = loopWindow || {
+    p50: loopDelay.percentile(50),
+    p99: loopDelay.percentile(99),
+    max: loopDelay.max,
+  };
+  appendMetric(
+    out,
+    "agenthub_event_loop_delay_seconds",
+    "Event-loop delay over the last minute (p50, p99, max): how long requests, hooks and terminal echo waited.",
+    "gauge",
+    [
+      { labels: { quantile: "0.5" }, value: loop.p50 / 1e9 },
+      { labels: { quantile: "0.99" }, value: loop.p99 / 1e9 },
+      { labels: { quantile: "1" }, value: loop.max / 1e9 },
+    ]
+  );
+
   // Sessions by status.
   const sessionCounts = new Map(stmts.sessionStatusCounts.all().map((r) => [r.status, r.count]));
   appendMetric(

server/routes/sessions.js

@@ -475,11 +475,31 @@ function sessionOutline(sessionId) {
   };
 }
 
+// Each open chat polls its outline every few seconds, and building it parses
+// every tool event of the session: keep the last answer per session until its
+// events change (a new id, or fewer rows after a cleanup).
+const outlineStamp = db.prepare(
+  "SELECT MAX(id) AS max_id, COUNT(*) AS n FROM events WHERE session_id = ?"
+);
+const OUTLINE_CACHE_MAX = 100;
+const outlineCache = new Map();
+function cachedOutline(sessionId) {
+  const st = outlineStamp.get(sessionId);
+  const stamp = `${st.max_id}:${st.n}`;
+  const hit = outlineCache.get(sessionId);
+  if (hit && hit.stamp === stamp) return hit.body;
+  const body = sessionOutline(sessionId);
+  outlineCache.delete(sessionId);
+  outlineCache.set(sessionId, { stamp, body });
+  if (outlineCache.size > OUTLINE_CACHE_MAX) outlineCache.delete(outlineCache.keys().next().value);
+  return body;
+}
+
 router.get("/:id/outline", (req, res) => {
   if (!stmts.getSession.get(req.params.id)) {
     return res.status(404).json({ error: { code: "NOT_FOUND", message: "Session not found" } });
   }
-  res.json(sessionOutline(req.params.id));
+  res.json(cachedOutline(req.params.id));
 });
 
 // An image the session's own Read tool returned (`?path=`, exact), for the Chat
@@ -1187,10 +1207,13 @@ router.get("/:id/transcript", async (req, res) => {
     }
 
     if (afterLine !== null) {
-      // Incremental mode: skip lines until after afterLine, collect up to limit, then stop
-      let foundStart = false;
+      // Incremental mode: skip lines until after afterLine, collect up to limit, then stop.
+      // A line the client already has is skipped BEFORE it is parsed: every open
+      // chat tails its transcript every few seconds, and parsing the whole JSONL
+      // (MBs for a long session) each time was most of the server's steady CPU.
       for await (const line of rl) {
         lineNum++;
+        if (lineNum <= afterLine) continue;
         if (!line.trim()) continue;
         let entry;
         try {
@@ -1200,11 +1223,6 @@ router.get("/:id/transcript", async (req, res) => {
         }
         if (!renders(entry)) continue;
 
-        if (!foundStart) {
-          if (lineNum <= afterLine) continue;
-          foundStart = true;
-        }
-
         const message = isCodex ? codexMessage(entry, lineNum) : parseMessage(entry, lineNum);
         if (!message) continue;
         total++;

server/routes/settings.js

@@ -11,6 +11,7 @@ const v8 = require("v8");
 const { db, stmts, DB_PATH, DEFAULT_PRICING, applyIntroPricing } = require("../db");
 const { getConnectionCount } = require("../websocket");
 const { transcriptCache } = require("./hooks");
+const { forgetHourly } = require("../lib/hourly-usage");
 
 const router = Router();
 
@@ -179,6 +180,7 @@ router.post("/clear-data", (_req, res) => {
 function clearAll() {
   db.prepare("DELETE FROM token_usage").run();
   db.prepare("DELETE FROM token_usage_hourly").run();
+  forgetHourly();
   db.prepare("DELETE FROM events").run();
   db.prepare("DELETE FROM agents").run();
   db.prepare("DELETE FROM sessions").run();
@@ -782,6 +784,7 @@ router.post("/cleanup", (req, res) => {
         db.prepare(`DELETE FROM token_usage_hourly WHERE session_id IN (${placeholders})`).run(
           ...chunk
         );
+        forgetHourly(chunk);
         db.prepare(`DELETE FROM sessions WHERE id IN (${placeholders})`).run(...chunk);
       }
       result.purged_sessions = ids.length;