@gotcos/glasses-server 6.29.0 → 6.30.0

package/CHANGELOG.md

@@ -2219,6 +2219,28 @@ unsaved capture, and makes batch status stop lying about finished work.
 
 # Changelog
 
+## [6.30.0] - 2026-08-16
+
+### Sessions know which threads are live
+
+- `GET /api/agent-sessions` now stamps each row with `running` (an agent is
+  working in this thread right now) and `running_foreign` (it is held by
+  something that is not COS, so a Continue would be refused), plus a
+  `runningDegraded` flag on the payload when a probe could not see clearly.
+- `running` counts COS's own queued turn too. Two different questions: whether an
+  agent is working (the badge) and whether a write would be refused (the
+  affordance). Counting only foreign owners would hide your own turn from the
+  screen you open to watch it.
+- **This is a display hint and never a write gate.** Attach and turn keep probing
+  at the moment of the write, unchanged, so a desktop session opened between the
+  list render and the tap is still caught.
+- Fails the opposite way to the gate: doubt reports `degraded` rather than
+  painting every session busy.
+- One scan for the whole page, measured at 7ms for 45 real sessions (was 792ms
+  before a scan-scoped memo and skipping lsof when no Codex writer lock exists).
+
+**Required by COS Glasses 6.8.364.**
+
 ## [6.29.0] - 2026-08-16
 
 ### Continue is queued instead of holding the phone

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gotcos/glasses-server",
-  "version": "6.29.0",
+  "version": "6.30.0",
   "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

@@ -0,0 +1,191 @@
+// Which threads currently have a live desktop process, in ONE pass.
+//
+// WHY THIS EXISTS SEPARATELY FROM `threadOccupancy`.
+//
+// `claudeOwners(threadId, ...)` re-reads the whole session registry and shells
+// out to `ps` per entry, for ONE thread. That is correct and cheap when a user is
+// deciding whether to write into a single thread. Calling it once per row to
+// decorate a 53-row session list would mean tens of directory scans and hundreds
+// of process spawns on every list request.
+//
+// So this does the opposite shape: scan once, return the set of occupied ids, and
+// let the caller join in memory.
+//
+// THE LOAD-BEARING RULE, AND THE REASON THIS IS SAFE:
+//
+//   WHAT THIS PRODUCES IS A DISPLAY HINT. IT MUST NEVER GATE A WRITE.
+//
+// The attach and turn paths keep calling `threadOccupancy` at the moment of the
+// write, unchanged. That is deliberate: a list is rendered seconds or minutes
+// before the user acts, and a desktop session opened in that gap is exactly the
+// race the per-write probe exists to catch. This hint answers "should the UI show
+// this session as busy", never "is it safe to write".
+//
+// Being a hint is also why its failure mode is the opposite of the gate's. The
+// gate fails CLOSED — doubt means refuse. A hint that failed closed would paint
+// every session as running the moment a probe hiccuped, so doubt here means "I do
+// not know", rendered as not-running, and the real gate still refuses at the
+// write. Getting a hint wrong costs a misleading badge; getting the gate wrong
+// costs someone's conversation.
+
+import {
+  claudeOwners,
+  codexLockPath,
+  codexOwners,
+  type OccupancyDirs,
+  type OccupancyProbes,
+  type ThreadOwner,
+} from './thread-occupancy.js'
+import { isValidNativeThreadId } from './native-thread-id.js'
+
+export interface OccupiedThread {
+  threadId: string
+  /**
+   * Every process working in this thread, 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.
+   */
+  owners: number
+  /**
+   * Owners that are NOT COS's own children.
+   *
+   * The separate count matters because it answers a different question: whether a
+   * Continue would be refused. Self-owned work does not block a write; a desktop
+   * window does.
+   */
+  foreignOwners: number
+}
+
+export interface OccupiedScan {
+  /** threadId -> occupancy, for every thread with at least one owner. */
+  occupied: Map<string, OccupiedThread>
+  /**
+   * True when the scan could not see clearly (unreadable registry, missing
+   * detector). The caller should render "unknown", never "everything is running".
+   */
+  degraded: boolean
+}
+
+const EMPTY: OccupiedScan = { occupied: new Map(), degraded: true }
+
+/**
+ * Probes that answer each identical question once per scan.
+ *
+ * MEASURED, not assumed. `claudeOwners` re-reads the whole registry directory and
+ * re-runs `ps` for every entry, for ONE thread — so scanning 45 real sessions on
+ * this machine cost 771ms of repeated identical I/O. With this wrapper the same
+ * scan is one directory read, one read per entry, and one `ps` per pid.
+ *
+ * Correctness comes from reusing `claudeOwners` / `codexOwners` UNCHANGED, so the
+ * self-ownership rule and the PID-reuse guard stay in exactly one place. This only
+ * removes duplicate work; it makes no decisions.
+ *
+ * Scoped to a single scan on purpose. A longer-lived cache would answer "is a
+ * desktop process holding this thread" from stale data, and liveness has a
+ * lifetime of about now.
+ */
+function memoize(probes: OccupancyProbes): OccupancyProbes {
+  const dirs = new Map<string, string[]>()
+  const files = new Map<string, string | null>()
+  const starts = new Map<number, number | null>()
+  const alive = new Map<number, boolean>()
+  const exists = new Map<string, boolean>()
+  const dirsExist = new Map<string, boolean>()
+  let ledger: ReturnType<OccupancyProbes['cosSpawnedPids']> | undefined
+
+  const once = <K, V>(cache: Map<K, V>, key: K, compute: () => V): V => {
+    if (cache.has(key)) return cache.get(key)!
+    const value = compute()
+    cache.set(key, value)
+    return value
+  }
+
+  return {
+    ...probes,
+    readDir: (path: string) => once(dirs, path, () => probes.readDir(path)),
+    readFile: (path: string) => once(files, path, () => probes.readFile(path)),
+    processStartMs: (pid: number) => once(starts, pid, () => probes.processStartMs(pid)),
+    isAlive: (pid: number) => once(alive, pid, () => probes.isAlive(pid)),
+    fileExists: (path: string) => once(exists, path, () => probes.fileExists(path)),
+    dirExists: (path: string) => once(dirsExist, path, () => probes.dirExists(path)),
+    cosSpawnedPids: () => (ledger ??= probes.cosSpawnedPids()),
+  }
+}
+
+/**
+ * Scan one provider's registry once and return the threads a desktop process
+ * holds.
+ *
+ * Reuses `claudeOwners` / `codexOwners` rather than reimplementing the parsing,
+ * so the self-ownership rule (COS's own spawned children must not read as foreign
+ * owners) and the PID-reuse guard stay in exactly one place. Reuse alone would
+ * repeat the whole registry read per thread — `memoize` is what removes that, so
+ * the saving is real I/O rather than a claim in a comment.
+ */
+export function occupiedThreads(
+  provider: string,
+  threadIds: readonly string[],
+  probes: OccupancyProbes,
+  dirs: OccupancyDirs,
+): OccupiedScan {
+  if (provider !== 'claude' && provider !== 'codex') return { occupied: new Map(), degraded: false }
+
+  // Deduplicated and validated up front. An invalid id cannot match a record, and
+  // it also reaches a filesystem path in `codexLockPath`.
+  const ids = [...new Set(threadIds)].filter(isValidNativeThreadId)
+  if (ids.length === 0) return { occupied: new Map(), degraded: false }
+
+  // Every identical read answered once for the whole scan. See `memoize`.
+  const probe = memoize(probes)
+  const occupied = new Map<string, OccupiedThread>()
+  let degraded = false
+
+  for (const threadId of ids) {
+    // MEASURED: `codexOwners` reaches `lsof` even when no writer lock exists, and
+    // lsof costs ~45ms a call — 761ms across 17 codex threads on this machine,
+    // against zero locks on disk. A missing lock means no writer, which is the
+    // same conclusion lsof reaches the expensive way, so skip it.
+    //
+    // Only an explicit `false` skips. `fileExists` collapses absent with
+    // unreadable, and an unreadable lock must still go through the real check
+    // rather than being read as free.
+    if (provider === 'codex') {
+      let lockPresent = true
+      try {
+        lockPresent = probe.fileExists(codexLockPath(threadId, dirs.codexLocksDir))
+      } catch {
+        lockPresent = true
+      }
+      if (!lockPresent) continue
+    }
+
+    let owners: readonly ThreadOwner[]
+    let doubt: string | null
+    try {
+      const result = provider === 'claude'
+        ? claudeOwners(threadId, probe, dirs.claudeSessionsDir)
+        : codexOwners(threadId, probe, dirs.codexLocksDir)
+      owners = result.owners
+      doubt = result.doubt
+    } catch {
+      // One thread's probe throwing does not invalidate the others.
+      degraded = true
+      continue
+    }
+    if (doubt !== null) degraded = true
+    // ANY owner means an agent is working here. Counting only foreign ones would
+    // 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 })
+    }
+  }
+
+  return { occupied, degraded }
+}
+
+/** The safe answer when the caller cannot scan at all. */
+export function noOccupancyKnown(): OccupiedScan {
+  return { occupied: new Map(EMPTY.occupied), degraded: true }
+}

package/server/routes/agent-sessions.ts

@@ -32,6 +32,9 @@ 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 { realOccupancyDirs, realOccupancyProbes } from '../lib/occupancy-probes.js'
+import { cosSpawnedPids } from '../lib/agent-session-ownership-store.js'
 
 export const agentSessionsRouter = Router()
 
@@ -61,6 +64,60 @@ function toSearchHit(row: AgentSessionSearchHit) {
   }
 }
 
+/**
+ * Which of these sessions a desktop process is holding right now.
+ *
+ * ONE scan for the whole page. Calling `threadOccupancy` per row would re-read the
+ * registry and shell out to `ps` per entry, which at 53 sessions is hundreds of
+ * process spawns on a single list request.
+ *
+ * THIS IS A DISPLAY HINT AND MUST NEVER GATE A WRITE. The attach and turn routes
+ * keep probing at the moment of the write, unchanged, because a list is rendered
+ * seconds or minutes before the user acts and a desktop session opened in that gap
+ * is exactly the race the per-write probe exists to catch.
+ */
+function runningThreads(rows: readonly AgentSessionRow[]): OccupiedScan {
+  try {
+    const dirs = realOccupancyDirs()
+    // The spawn ledger is what lets a turn COS itself queued read as ours rather
+    // than as a foreign desktop window holding the thread.
+    const probes = realOccupancyProbes(cosSpawnedPids)
+    const byProvider = new Map<string, string[]>()
+    for (const row of rows) {
+      if (row.provider !== 'claude' && row.provider !== 'codex') continue
+      const list = byProvider.get(row.provider) ?? []
+      list.push(row.session_id)
+      byProvider.set(row.provider, list)
+    }
+    const merged = new Map<string, OccupiedThread>()
+    let degraded = false
+    for (const [provider, ids] of byProvider) {
+      const scan = occupiedThreads(provider, ids, probes, dirs)
+      for (const [id, occ] of scan.occupied) merged.set(id, occ)
+      if (scan.degraded) degraded = true
+    }
+    return { occupied: merged, degraded }
+  } catch (error) {
+    // The list is the point; occupancy is decoration. A probe failure must never
+    // cost the user their sessions.
+    console.error(`[agent-sessions] occupancy scan failed: ${error instanceof Error ? error.message : error}`)
+    return noOccupancyKnown()
+  }
+}
+
+/** Stamp the running hint onto a projected row. */
+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.
+    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,
+  }
+}
+
 function toEntry(row: AgentSessionRow) {
   return {
     session_id: row.session_id,
@@ -107,12 +164,16 @@ 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)
     res.json({
-      sessions: sessions.map(toEntry),
+      sessions: sessions.map(row => withRunning(toEntry(row), running)),
       total: sessions.length,
       windowHours: AGENT_SESSION_WINDOW_HOURS,
       sort,
       enabled: true,
+      // True when a probe could not see clearly. The client must render "unknown"
+      // rather than treating a quiet scan as "nothing is running".
+      runningDegraded: running.degraded,
     })
   } catch (error) {
     console.error(`[agent-sessions] list failed: ${error instanceof Error ? error.message : error}`)