@gotcos/glasses-server 6.30.0 → 6.31.0

package/CHANGELOG.md

@@ -2219,6 +2219,53 @@ unsaved capture, and makes batch status stop lying about finished work.
 
 # Changelog
 
+## [6.31.0] - 2026-08-16
+
+### "Running" meant an open window, not a working agent
+
+- `GET /api/agent-sessions` adds **`running_active`**: the thread's transcript was
+  written in the last 30 seconds, so an agent is generating in it right now.
+- This exists because `running` could not answer that question and was being read
+  as though it could. It comes from a process registry, and a Claude Code record
+  describes an open WINDOW (`kind: interactive`, `entrypoint: claude-desktop`) —
+  so a session that finished an hour ago, with the window still up, stayed
+  `running: true` forever. A finished session reported itself active on the
+  glasses and never cleared.
+- The transcript is the only part of a session with a clock in it. While a
+  session generates, its jsonl mtime tracks the wall clock to within a second;
+  when it stops, the mtime goes stale while the registry record does not. That
+  divergence is the whole signal.
+- The window is 30 seconds, deliberately much wider than the observed write
+  cadence, so a long tool call between writes does not flap a working session to
+  idle and back.
+- **Costs one stat per HELD thread, not per listed thread.** Freshness is layered
+  on after the occupancy scan and only over what it found, so a list with nothing
+  running does no extra filesystem work at all.
+- Anything unmeasurable — no transcript, unreadable file, a timestamp from the
+  future — reads as NOT active. The row then falls back to "open", which is still
+  true of a thread with a live owner. The stronger claim has to be earned by an
+  actual observation.
+- **Still a display hint and still never a write gate.** `attachability` and
+  `attach` keep probing at the moment of the write, unchanged.
+
+### The session detail describes its own liveness
+
+- `GET /api/agent-sessions/:provider/:sessionId` now carries the same three
+  `running_*` fields plus `running_stamped: true` and `runningDegraded`.
+- Until now only the LIST stamped occupancy, so the detail page had to borrow the
+  flags from whichever row the user tapped. Those flags froze at the moment of the
+  tap, which is the other half of why a finished session never cleared: the page
+  had no way to ask again. A polling client needs a payload that carries its own
+  liveness.
+- `running_stamped` exists so a client can tell an old server's silence from a new
+  server's `false`. They demand opposite behaviour: keep the borrowed hint, or drop
+  it as stale.
+- Nearly free: the handler already resolves and stats the transcript, so only the
+  single-thread occupancy scan is new, and that is the same scan `attachability`
+  runs on every menu open.
+
+**Required by the COS Glasses build that ships the honest activity line.**
+
 ## [6.30.0] - 2026-08-16
 
 ### Sessions know which threads are live

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gotcos/glasses-server",
-  "version": "6.30.0",
+  "version": "6.31.0",
   "description": "COS Glasses \u2014 self-hosted AI heads-up-display server for Even G2 smart glasses, powered by Claude Code, Codex, or Cursor Agent CLI",
   "type": "module",
   "bin": {

package/server/lib/occupied-threads.ts

@@ -41,10 +41,15 @@ import { isValidNativeThreadId } from './native-thread-id.js'
 export interface OccupiedThread {
   threadId: string
   /**
-   * Every process working in this thread, COS's own children included.
+   * Every process holding this thread open, COS's own children included.
    *
-   * This is the DISPLAY question — "is an agent working in here right now" — and
-   * a turn COS queued is just as much a running agent as a desktop window is.
+   * WHAT THIS ACTUALLY MEASURES, stated plainly because the first version of the
+   * feature got it wrong in user-facing copy: a registry record means A PROCESS
+   * HOLDS THIS THREAD OPEN. It does NOT mean an agent is generating. A Claude
+   * Code record reads `kind: interactive, entrypoint: claude-desktop` for an open
+   * WINDOW, so a session that finished ten minutes ago with the window still up
+   * has an owner forever. The lens said "ACTIVE NOW" off this number and was
+   * lying; it now says the thread is OPEN, which is all this count can support.
    */
   owners: number
   /**
@@ -55,6 +60,16 @@ export interface OccupiedThread {
    * window does.
    */
   foreignOwners: number
+  /**
+   * The transcript was WRITTEN inside the freshness window: an agent is
+   * generating here, not merely holding the file open.
+   *
+   * This is the signal `owners` cannot give. Set only from a positive
+   * observation of a recent write — see `withActiveRecently`, which is where it
+   * is filled in. `occupiedThreads` itself has no path to a transcript and
+   * always leaves it false.
+   */
+  activeRecently: boolean
 }
 
 export interface OccupiedScan {
@@ -178,7 +193,11 @@ export function occupiedThreads(
     // hide COS's own queued turn from the very screen the user opens to watch it.
     const foreign = owners.filter(o => !o.selfOwned).length
     if (owners.length > 0) {
-      occupied.set(threadId, { threadId, owners: owners.length, foreignOwners: foreign })
+      // `activeRecently` is FALSE here and can only be raised by
+      // `withActiveRecently`. This function reads a process registry; a registry
+      // record cannot tell generating from idling, and inferring one from the
+      // other is the exact defect this field exists to fix.
+      occupied.set(threadId, { threadId, owners: owners.length, foreignOwners: foreign, activeRecently: false })
     }
   }
 
@@ -189,3 +208,78 @@ export function occupiedThreads(
 export function noOccupancyKnown(): OccupiedScan {
   return { occupied: new Map(EMPTY.occupied), degraded: true }
 }
+
+/**
+ * How recently the transcript must have been written for a held thread to read
+ * as WORKING rather than merely OPEN.
+ *
+ * WHY A SECOND SIGNAL EXISTS AT ALL. `owners` answers "a process holds this
+ * thread", which is not the question the user is asking when he looks at the
+ * lens. He watched a session finish on his Mac while the glasses still showed it
+ * active, because the window was still open and the registry record therefore
+ * still existed. Occupancy has no clock in it; the transcript does.
+ *
+ * MEASURED, not assumed: while a session generates, its jsonl mtime tracks the
+ * wall clock to within a second, and when generation stops the mtime goes stale
+ * while the registry record stays exactly where it was. That divergence is the
+ * whole signal.
+ *
+ * 30 seconds is deliberately far wider than the observed sub-second write
+ * cadence. The gap this has to survive is a long tool call or a slow first token
+ * between writes, and a window sized to the cadence would flap a working session
+ * to OPEN and back every time the model paused to think. The cost of the wide
+ * window is bounded and known: a session that stops is reported working for up
+ * to 30 more seconds, which is a late correction rather than a permanent lie.
+ */
+export const ACTIVE_RECENTLY_WINDOW_MS = 30_000
+
+/**
+ * Was this transcript written inside the window?
+ *
+ * NULL IS NOT "RECENT". An unresolvable path, an unreadable file, a stat that
+ * threw — every one of them arrives here as null and answers false, so the row
+ * falls back to OPEN. That is not a fail-open: OPEN is still a true statement
+ * about a thread with a live owner. It is the STRONGER claim, "an agent is
+ * working in here", that has to be earned by an actual observation.
+ *
+ * A timestamp far in the FUTURE is refused for the same reason rather than
+ * treated as maximally fresh. Skew of a few seconds is normal and lands inside
+ * the window; a file dated next week is a clock this server cannot reason about,
+ * and letting it manufacture a permanent "working" badge would rebuild the bug
+ * from the other direction.
+ */
+export function isActiveRecently(mtimeMs: number | null | undefined, nowMs: number): boolean {
+  if (typeof mtimeMs !== 'number' || !Number.isFinite(mtimeMs)) return false
+  if (!Number.isFinite(nowMs)) return false
+  return Math.abs(nowMs - mtimeMs) <= ACTIVE_RECENTLY_WINDOW_MS
+}
+
+/**
+ * Fill in `activeRecently` for a scan, from transcript write times.
+ *
+ * PURE, and separate from `occupiedThreads` on purpose. Resolving a thread id to
+ * a transcript path is the session STORE's job (it owns the projects/rollouts
+ * layout), and this module owns process occupancy; wiring the store in here
+ * would make an occupancy scan depend on a filesystem it does not otherwise know
+ * about. The caller stats — for HELD THREADS ONLY, which is what keeps this
+ * cheap, since it is one stat per already-occupied row and never one per listed
+ * row — and hands the readings in.
+ *
+ * A thread with no entry in the map is not an error and not "recent": it reads
+ * exactly like an unreadable one, because from here the two are the same
+ * absence of evidence.
+ */
+export function withActiveRecently(
+  scan: OccupiedScan,
+  transcriptMtimes: ReadonlyMap<string, number | null>,
+  nowMs: number,
+): OccupiedScan {
+  const occupied = new Map<string, OccupiedThread>()
+  for (const [threadId, record] of scan.occupied) {
+    occupied.set(threadId, {
+      ...record,
+      activeRecently: isActiveRecently(transcriptMtimes.get(threadId), nowMs),
+    })
+  }
+  return { occupied, degraded: scan.degraded }
+}

package/server/routes/agent-sessions.ts

@@ -32,7 +32,13 @@ import {
 import { searchAgentSessions, type AgentSessionSearchHit } from '../lib/agent-session-search.js'
 import { claudeSessionNamesVisible, claudeSessionsDir, claudeSessionsEnabled, readClaudePeers } from './claude-sessions.js'
 import { workspaceFromCwd } from '../lib/claude-session-registry.js'
-import { occupiedThreads, noOccupancyKnown, type OccupiedScan, type OccupiedThread } from '../lib/occupied-threads.js'
+import {
+  occupiedThreads,
+  noOccupancyKnown,
+  withActiveRecently,
+  type OccupiedScan,
+  type OccupiedThread,
+} from '../lib/occupied-threads.js'
 import { realOccupancyDirs, realOccupancyProbes } from '../lib/occupancy-probes.js'
 import { cosSpawnedPids } from '../lib/agent-session-ownership-store.js'
 
@@ -105,16 +111,115 @@ function runningThreads(rows: readonly AgentSessionRow[]): OccupiedScan {
   }
 }
 
-/** Stamp the running hint onto a projected row. */
-function withRunning<T extends { session_id: string }>(entry: T, scan: OccupiedScan) {
+/**
+ * When each HELD thread's transcript was last written.
+ *
+ * ONLY the threads the scan already found occupied. That is the entire cost
+ * argument: the occupied set is typically one or two rows out of sixty, so this
+ * is one or two path resolutions and stats per request, not sixty. An empty scan
+ * does no filesystem work at all.
+ *
+ * WHY NOT REUSE `row.modified`, WHICH IS ALREADY AN MTIME. Because for the rows
+ * that matter it is not one. A live Claude row comes from `liveClaudeRows`,
+ * whose `modified` is the registry's `lastActiveAt` (or, absent that, literally
+ * `new Date()`), and `enrichLiveClaude` does not replace it with the file's
+ * mtime. Reading freshness off that field would report an open window as a fresh
+ * write on every single request, which is precisely the bug being fixed.
+ *
+ * Every failure lands on null, and null is doubt rather than "recent" — see
+ * `isActiveRecently`. A row that cannot be measured reads OPEN, which is still
+ * true of a thread with a live owner.
+ */
+async function transcriptMtimes(
+  scan: OccupiedScan,
+  rows: readonly AgentSessionRow[],
+): Promise<Map<string, number | null>> {
+  const mtimes = new Map<string, number | null>()
+  if (scan.occupied.size === 0) return mtimes
+
+  const providerById = new Map<string, AgentProvider>()
+  for (const row of rows) providerById.set(row.session_id, row.provider)
+  const roots = agentSessionRoots()
+
+  await Promise.all([...scan.occupied.keys()].map(async threadId => {
+    try {
+      const provider = providerById.get(threadId)
+      // An occupied id with no row cannot happen today (the scan is built FROM
+      // the rows), but guessing a provider to go looking for a file is how a
+      // caller-supplied id reaches the filesystem. Unknown stays unmeasured.
+      if (!provider) {
+        mtimes.set(threadId, null)
+        return
+      }
+      const file = await findAgentSessionFile(provider, threadId, roots)
+      mtimes.set(threadId, file ? (await stat(file)).mtimeMs : null)
+    } catch {
+      mtimes.set(threadId, null)
+    }
+  }))
+  return mtimes
+}
+
+/**
+ * Stamp the running hint onto a projected row.
+ *
+ * EXPORTED so the WIRE KEYS are covered by a behaviour test rather than by
+ * reading this file. The client reads `running_active` by exact name
+ * (`session-running.ts` accepts only a literal `true` on a known key), so a
+ * rename here is silent on this side and renders every session as merely open on
+ * the lens. Pure: it takes the scan, it does no I/O.
+ */
+export function withRunning<T extends { session_id: string }>(entry: T, scan: OccupiedScan) {
   const occ = scan.occupied.get(entry.session_id)
   return {
     ...entry,
-    // An agent is working in this thread right now, whoever started it.
+    // A process HOLDS this thread open, whoever started it. Not "is generating":
+    // a Claude record for an open window outlives the work by however long the
+    // window stays up, which is why `running_active` exists below.
     running: occ !== undefined,
     // Held by something that is not COS, so a Continue would be refused. The
     // badge reads `running`; the Continue affordance reads this.
     running_foreign: (occ?.foreignOwners ?? 0) > 0,
+    // The transcript was WRITTEN in the last few seconds: an agent is generating
+    // here, not just holding the file. This is the only one of the three that
+    // clears on its own when the work stops. Still a display hint, never a gate.
+    running_active: occ?.activeRecently === true,
+  }
+}
+
+/**
+ * Occupancy plus freshness for ONE thread, for the detail route.
+ *
+ * WHY THE DETAIL ROUTE STAMPS THIS AT ALL. It did not, and the lens had to borrow
+ * the hint from whichever list row the user tapped. That worked exactly once: the
+ * detail page was a single fetch, so the borrowed flags were frozen at the moment
+ * it opened and could never clear, which is half of why a finished session stayed
+ * "active" on the glasses until Miles navigated away. A page that polls needs a
+ * payload that carries its own liveness.
+ *
+ * NEARLY FREE HERE. The handler has already resolved the transcript path and
+ * stat'ed it, so freshness costs nothing extra and only the single-thread
+ * occupancy scan is new — the same scan `attachability` already runs on every
+ * menu open. Contrast the list, where the same work would be sixty scans.
+ *
+ * STILL A DISPLAY HINT. Nothing about being on the detail payload makes it a
+ * gate; `attach` re-probes at the write, unchanged.
+ */
+function runningForThread(provider: AgentProvider, threadId: string, mtimeMs: number): OccupiedScan {
+  if (provider !== 'claude' && provider !== 'codex') return { occupied: new Map(), degraded: false }
+  try {
+    const scan = occupiedThreads(
+      provider,
+      [threadId],
+      realOccupancyProbes(cosSpawnedPids),
+      realOccupancyDirs(),
+    )
+    return withActiveRecently(scan, new Map([[threadId, mtimeMs]]), Date.now())
+  } catch (error) {
+    // The transcript is the point; occupancy is decoration. A probe failure must
+    // never cost the user their session.
+    console.error(`[agent-sessions] detail occupancy failed: ${error instanceof Error ? error.message : error}`)
+    return noOccupancyKnown()
   }
 }
 
@@ -164,7 +269,11 @@ agentSessionsRouter.get('/agent-sessions', async (req, res) => {
     const sort = asSort(req.query.sort)
     const live = await liveClaudeRows()
     const sessions = await listAgentSessions(agentSessionRoots(), new Date(), live, limit, sort)
-    const running = runningThreads(sessions)
+    const scan = runningThreads(sessions)
+    // Freshness is layered on AFTER occupancy, and only over what occupancy
+    // found. `Date.now()` is read once so every row in a payload is judged
+    // against the same instant.
+    const running = withActiveRecently(scan, await transcriptMtimes(scan, sessions), Date.now())
     res.json({
       sessions: sessions.map(row => withRunning(toEntry(row), running)),
       total: sessions.length,
@@ -234,8 +343,19 @@ agentSessionsRouter.get('/agent-sessions/:provider/:sessionId', async (req, res)
       if (named) parsed.display_label = named
     }
     const modified = st.mtime.toISOString()
+    const running = runningForThread(provider, parsed.session_id, st.mtimeMs)
     res.json({
-      session_id: parsed.session_id,
+      ...withRunning({ session_id: parsed.session_id }, running),
+      // The client must be able to tell "this server stamped nothing" from "this
+      // server stamped false", because the two demand opposite behaviour: an old
+      // server's silence means keep using the hint borrowed from the list row, and
+      // a new server's `false` means the thread genuinely went quiet and the
+      // borrowed hint is the stale thing. Without this marker the poll could never
+      // clear the flag it exists to clear.
+      running_stamped: true,
+      // Same meaning as on the list: a probe could not see clearly, so render
+      // unknown rather than treating a quiet scan as "nothing is running".
+      runningDegraded: running.degraded,
       provider: parsed.provider,
       slug: parsed.session_id,
       custom_title: parsed.display_label,