tokenmaxxing 0.5.0 → 0.6.1

package/DESIGN.md

@@ -78,7 +78,7 @@ Each terminal ran the supervisor, so each has its own child `claude`, its own `-
 ## 5. Rotation policy
 Trigger at `five_hour >= 95%` OR `seven_day >= 95%`, per org. "Exhausted" is a **timestamped state** (`resets_at`), not a flag - an account is a candidate again after it resets. Optional projected threshold (`95 − EMA(per-turn Δ%)`) so a single large turn can't blow past 100% before the next Stop hook.
 
-**Model-aware trigger.** Claude subscriptions also enforce a **per-model weekly cap** - the capable models (Fable, Opus) have a tighter weekly limit that binds *before* the aggregate (e.g. 80% week-Fable at only 50% week-all-models). This cap isn't in statusLine stdin, so when the active model is in `policy.switchModels` we read it from `claude -p '/usage'` (free, 0 tokens, TTL-cached) and add `week(<activeModel>) >= threshold` to the trigger. A Fable session switches on the Fable cap; a Sonnet session rides the aggregate.
+**Model-aware trigger.** Claude subscriptions also enforce **per-model weekly caps** - currently only for Sonnet and Fable (there is no Opus-only quota), and Fable's tighter limit binds *before* the aggregate (e.g. 80% week-Fable at only 50% week-all-models). This cap isn't in statusLine stdin, so when the active model is in `policy.switchModels` we read it from `claude -p '/usage'` (free, 0 tokens, TTL-cached) and add `week(<activeModel>) >= threshold` to the trigger. A Fable session switches on the Fable cap; a Sonnet session rides the aggregate.
 
 ---
 

package/README.md

@@ -48,10 +48,12 @@ claude                  # use claude as always
 Switching triggers at **95%** (configurable) on any of:
 
 - **Session** (5-hour) or **week (all models)** - the aggregate windows, fed free/push-based by the statusLine.
-- **Per-model weekly cap** - the capable models (Fable, Opus) have their own tighter weekly limit that binds *before* the aggregate. tokenmaxxing reads it from `claude -p '/usage'` (free, 0 tokens, TTL-cached) whenever the active model is one of `policy.switchModels`, so a Fable session switches on the Fable cap while a Sonnet session rides the aggregate.
+- **Per-model weekly cap** - the most capable model (Fable) has its own tighter weekly limit that binds *before* the aggregate (per-model caps currently exist only for Sonnet and Fable, and Sonnet's is generous). tokenmaxxing reads it from `claude -p '/usage'` (free, 0 tokens, TTL-cached) whenever the active model is one of `policy.switchModels`, so a Fable session switches on the Fable cap while a Sonnet session rides the aggregate.
 
 The 5% headroom is deliberate: it's the budget to reach a clean turn boundary and respawn before the wall.
 
+The **target** is chosen greedily off each account's cached windows: the usable account (session and week under threshold, or past their reset) whose weekly window **expires soonest** - unused weekly allowance is forfeited at the fixed per-account reset. Cached resets are absolute UTC epochs, so a stale snapshot still resolves correctly: a weekly reset that has passed extrapolates forward in 7-day steps, and a session window past its reset counts as empty. `tokenmaxxing switch` ranks the current account too and does nothing when it already wins, so it is idempotent - running it periodically converges on the right account.
+
 ## Configuration
 
 `~/.config/tokenmaxxing/config.json` (every field optional):
@@ -61,7 +63,7 @@ The 5% headroom is deliberate: it's the budget to reach a clean turn boundary an
   "threshold": 95,
   "policy": {
     "projectionMargin": 0,
-    "switchModels": ["fable", "opus"],
+    "switchModels": ["fable"],
     "usagePollTtlMs": 90000
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "tokenmaxxing",
-  "version": "0.5.0",
+  "version": "0.6.1",
   "description": "Automatic Claude Code account switching: pool multiple accounts and hot-swap when quota fills, resuming your session on the fresh account.",
   "type": "module",
   "license": "MIT",

package/src/cli/add.ts

@@ -118,6 +118,7 @@ export async function cmdAdd(): Promise<number> {
       needsReauth: false,
       lastUsage: sampled ? { fiveHour: sampled.session, sevenDay: sampled.weekAll } : existing?.lastUsage,
       lastPerModel: sampled && Object.keys(sampled.perModel).length > 0 ? sampled.perModel : existing?.lastPerModel,
+      lastUsageAt: sampled ? Date.now() : existing?.lastUsageAt,
     };
     if (existing) Object.assign(existing, fresh);
     else idx.accounts.push(fresh);

package/src/cli/render.ts

@@ -40,6 +40,19 @@ export function fmtReset(epochMs: number | null | undefined, now = Date.now()):
   return `resets in ${m}m`;
 }
 
+/** Age of a cached sample, largest unit only: "just now", "3m ago", "2h ago",
+ *  "5d ago". */
+export function fmtAgo(epochMs: number, now = Date.now()): string {
+  const dsec = Math.max(0, Math.round((now - epochMs) / 1000));
+  if (dsec < 60) return "just now";
+  const d = Math.floor(dsec / 86400);
+  const h = Math.floor((dsec % 86400) / 3600);
+  const m = Math.floor((dsec % 3600) / 60);
+  if (d > 0) return `${d}d ago`;
+  if (h > 0) return `${h}h ago`;
+  return `${m}m ago`;
+}
+
 /** Compact time-until-reset for the statusLine: the largest unit only ("6d",
  *  "2h", "45m"), floored to "1m" so a live window never reads as zero, and ""
  *  once the reset has passed (the window is simply empty again). Non-empty

package/src/cli/status.ts

@@ -10,8 +10,8 @@ import { readOAuthAccount } from "../lib/claudejson.ts";
 import { probeActiveUsage, probeParkedUsage, type SampleOutcome } from "../lib/sample.ts";
 import { withLock } from "../lib/lock.ts";
 import { paths } from "../lib/paths.ts";
-import { isExhausted } from "../lib/picker.ts";
-import { bar, c, fmtReset } from "./render.ts";
+import { isExhausted, nextWeeklyReset } from "../lib/picker.ts";
+import { bar, c, fmtAgo, fmtReset } from "./render.ts";
 import type { FullUsage } from "../lib/usage.ts";
 import type { UsageWindow } from "../lib/types.ts";
 
@@ -58,6 +58,9 @@ export async function cmdStatus(): Promise<number> {
         if (!outcome.ok) return;
         a.lastUsage = { fiveHour: outcome.usage.session, sevenDay: outcome.usage.weekAll };
         if (Object.keys(outcome.usage.perModel).length > 0) a.lastPerModel = outcome.usage.perModel;
+        // stamp when the figures were actually measured: the statusLine tee's
+        // own write time for the push-fed active account, else the probe time.
+        a.lastUsageAt = fromStatusLine && live ? live.ts : Date.now();
       }),
     );
     saveAccounts(idx);
@@ -66,8 +69,15 @@ export async function cmdStatus(): Promise<number> {
   console.log(c.dim(`threshold ${cfg.threshold}%  ·  ${idx.accounts.length} account(s)`));
   console.log();
 
-  const row = (name: string, w: UsageWindow) =>
-    console.log(`    ${name.padEnd(5)} ${bar(w.usedPercentage)}  ${c.dim(fmtReset(w.resetsAt, now))}`);
+  // A window whose cached reset has passed is empty again; weekly windows recur
+  // on a fixed per-account anchor, so a stale weekly reset extrapolates forward.
+  // Fresh samples pass through unchanged (their resets are in the future).
+  const row = (name: string, w: UsageWindow, weekly: boolean) => {
+    const passed = w.resetsAt != null && w.resetsAt <= now;
+    const pct = passed ? 0 : w.usedPercentage;
+    const resetsAt = weekly ? nextWeeklyReset(w.resetsAt, now) : passed ? null : w.resetsAt;
+    console.log(`    ${name.padEnd(5)} ${bar(pct)}  ${c.dim(fmtReset(resetsAt, now))}`);
+  };
 
   for (const a of idx.accounts) {
     const active = a.accountUuid === idx.activeAccountUuid;
@@ -82,18 +92,18 @@ export async function cmdStatus(): Promise<number> {
     const badges: string[] = [];
     if (active) badges.push(c.green("active"));
     if (a.needsReauth) badges.push(c.red("needs-reauth"));
-    if (isExhausted(a, { now, threshold: cfg.threshold, currentAccountUuid: idx.activeAccountUuid }))
+    if (isExhausted(a, { now, threshold: cfg.threshold, currentAccountUuid: idx.activeAccountUuid, switchFamilies: cfg.policy.switchModels }))
       badges.push(c.yellow("exhausted"));
 
     console.log(`${marker} ${c.bold(a.label || a.email)} ${badges.join(" ")}`);
     if (aggregate) {
-      row("5h", aggregate.fiveHour);
-      row("week", aggregate.sevenDay);
+      row("5h", aggregate.fiveHour, false);
+      row("week", aggregate.sevenDay, true);
     }
-    if (perModel) for (const [name, w] of Object.entries(perModel)) row(name, w);
+    if (perModel) for (const [name, w] of Object.entries(perModel)) row(name, w, true);
     if (failed && outcome && !outcome.ok) {
-      const note = aggregate || perModel ? "cached · live sample failed" : "live sample failed";
-      console.log(`    ${c.yellow(note)}: ${c.dim(outcome.reason)}`);
+      const cached = aggregate || perModel ? `cached${a.lastUsageAt != null ? ` ${fmtAgo(a.lastUsageAt, now)}` : ""} · ` : "";
+      console.log(`    ${c.yellow(`${cached}live sample failed`)}: ${c.dim(outcome.reason)}`);
     }
     console.log();
   }

package/src/cli/switch.ts

@@ -1,16 +1,28 @@
-// `tokenmaxxing switch [selector]` (also the bare `tokenmaxxing` / `xx`).
-// No selector → auto-pick the best available account. With a selector → switch to
-// that one. Manual/recovery tool: no threshold gate, runs under the flock. When
-// everything is depleted it still switches to the soonest-resetting account.
+// `tokenmaxxing switch [selector]`.
+// No selector → greedy: rank EVERY account (current included) by soonest weekly
+// expiry among those with session/week under threshold, off the cached windows.
+// When the current account already wins (or ties - swapping between equals buys
+// nothing), do nothing: the command is idempotent, so running it periodically
+// converges on the right account. With a selector → switch to that one. Runs
+// under the flock. When everything is depleted it stays on / switches to
+// whichever account recovers soonest.
+//
+// The active LABEL can drift from the live login (manual /login is the
+// surviving drift source). A no-op would freeze that drift forever, so when
+// ~/.claude.json names a different account than accounts.json we swap for real
+// instead of trusting the label - performSwap resolves the live credential's
+// true owner, harvesting the drifted login correctly.
 
 import { withLock } from "../lib/lock.ts";
 import { paths } from "../lib/paths.ts";
 import { loadAccounts, loadConfig } from "../lib/state.ts";
+import { readOAuthAccount } from "../lib/claudejson.ts";
 import { performSwap, chooseAndSwap } from "../lib/swap.ts";
-import { pickEarliestReset } from "../lib/picker.ts";
+import { isExhausted, pickBest, pickEarliestReset, swapPreference, weeklyExpiry, type PickCtx } from "../lib/picker.ts";
 import { InvalidGrantError } from "../lib/oauth.ts";
 import { findAccount } from "./rename.ts";
 import { c, fmtReset } from "./render.ts";
+import type { Account } from "../lib/types.ts";
 
 export async function cmdSwitch(selector?: string): Promise<number> {
   const idx0 = loadAccounts();
@@ -23,12 +35,10 @@ export async function cmdSwitch(selector?: string): Promise<number> {
 
   return withLock(paths.lockFile, async () => {
     const idx = loadAccounts();
+    const claimed = readOAuthAccount()?.accountUuid ?? null;
+    const drifted = claimed != null && claimed !== idx.activeAccountUuid;
 
-    if (selector) {
-      const target = findAccount(idx.accounts, selector);
-      if (!target) { console.error(c.red(`no account matches "${selector}"`)); return 1; }
-      if (target.accountUuid === idx.activeAccountUuid) { console.log(`already on ${c.bold(target.label)}`); return 0; }
-      if (target.needsReauth) { console.error(c.red(`${target.label} needs re-auth - \`tokenmaxxing add\``)); return 1; }
+    const swapTo = async (target: Account): Promise<number> => {
       try {
         await performSwap(target);
       } catch (e) {
@@ -37,25 +47,69 @@ export async function cmdSwitch(selector?: string): Promise<number> {
       }
       console.log(`${c.green("↻")} switched to ${c.bold(target.label)}`);
       return 0;
+    };
+
+    if (selector) {
+      const target = findAccount(idx.accounts, selector);
+      if (!target) { console.error(c.red(`no account matches "${selector}"`)); return 1; }
+      if (target.accountUuid === idx.activeAccountUuid && !drifted) { console.log(`already on ${c.bold(target.label)}`); return 0; }
+      if (target.needsReauth) { console.error(c.red(`${target.label} needs re-auth - \`tokenmaxxing add\``)); return 1; }
+      return swapTo(target);
     }
 
-    // auto: best account under threshold
-    const landed = await chooseAndSwap({ now, threshold: cfg.threshold });
-    if (landed) {
-      console.log(`${c.green("↻")} switched to ${c.bold(landed.label)}`);
+    // auto: greedy over everyone, current included - a no-op when current wins.
+    // No session context here, so every configured per-model family gates.
+    const everyone: PickCtx = { now, threshold: cfg.threshold, currentAccountUuid: null, switchFamilies: cfg.policy.switchModels };
+    const active = idx.accounts.find((a) => a.accountUuid === idx.activeAccountUuid) ?? null;
+    const best = pickBest(idx.accounts, everyone);
+    const currentWins =
+      best != null && active != null && !active.needsReauth && !isExhausted(active, everyone) &&
+      (best.accountUuid === active.accountUuid || swapPreference(now).every((k) => k(active) === k(best)));
+    if (currentWins) {
+      if (drifted) return swapTo(active);
+      const expiry = weeklyExpiry(active, now);
+      const why = Number.isFinite(expiry) ? ` (weekly ${fmtReset(expiry, now)})` : "";
+      console.log(`already on the best account: ${c.bold(active.label)}${why}`);
       return 0;
     }
+    if (best) {
+      const landed = await chooseAndSwap({ now, threshold: cfg.threshold, switchFamilies: cfg.policy.switchModels });
+      if (landed) {
+        console.log(`${c.green("↻")} switched to ${c.bold(landed.label)}`);
+        return 0;
+      }
+    }
 
-    // everything is depleted → switch to whichever recovers soonest
-    const earliest = pickEarliestReset(idx.accounts, { now, threshold: cfg.threshold, currentAccountUuid: idx.activeAccountUuid });
-    if (!earliest) { console.error(c.yellow("no switchable account (all need re-auth?)")); return 1; }
-    try {
-      await performSwap(earliest.account);
-    } catch (e) {
-      if (e instanceof InvalidGrantError) { console.error(c.red(`${earliest.account.label}'s refresh token is dead`)); return 1; }
-      throw e;
+    // No usable target swapped in: everything is depleted, or the remaining
+    // candidates' refresh tokens just died (chooseAndSwap marks needs-reauth,
+    // hence the reload). Stay on / switch to whichever recovers soonest.
+    const fresh = loadAccounts();
+    const earliest = pickEarliestReset(fresh.accounts, everyone);
+    if (!earliest) {
+      // Either every account needs re-auth, or every account is blocked with no
+      // recoverable bound (unparsed reset clocks AND no sample time - see log).
+      const reauth = fresh.accounts.filter((a) => a.needsReauth).map((a) => a.label);
+      if (reauth.length > 0) { console.error(c.yellow(`no switchable account - re-auth needed: ${reauth.join(", ")}`)); return 1; }
+      // never freeze a label drift behind a no-op (see header).
+      if (drifted && active) return swapTo(active);
+      console.log(c.yellow("all accounts at their limit with unknown reset times (unparsed reset clocks? see tokenmaxxing.log) - staying put"));
+      return 0;
+    }
+    const reauth = fresh.accounts.filter((a) => a.needsReauth).map((a) => a.label);
+    const reauthNote = reauth.length ? ` - re-auth needed: ${reauth.join(", ")}` : "";
+    if (earliest.account.accountUuid === fresh.activeAccountUuid && !drifted) {
+      // availableAt in the past means the current account is fine and the
+      // others are simply unusable - do not claim a limit that is not there.
+      const msg = earliest.availableAt <= now
+        ? `staying on ${c.bold(earliest.account.label)} - no usable switch target${reauthNote}`
+        : `all accounts at limit - staying on ${c.bold(earliest.account.label)} (${fmtReset(earliest.availableAt, now)})${reauthNote}`;
+      console.log(c.yellow(msg));
+      return 0;
+    }
+    const code = await swapTo(earliest.account);
+    if (code === 0 && earliest.availableAt > now) {
+      console.log(c.yellow(`all accounts at limit - ${c.bold(earliest.account.label)} recovers soonest (${fmtReset(earliest.availableAt, now)})${reauthNote}`));
     }
-    console.log(`${c.yellow("↻")} all accounts at limit - switched to ${c.bold(earliest.account.label)} (${fmtReset(earliest.availableAt, now)})`);
-    return 0;
+    return code;
   });
 }

package/src/entries/sessionstart.ts

@@ -1,8 +1,8 @@
 // SessionStart hook. A launch/resume backstop: if the active account is already
 // over threshold with FRESH usage (e.g. a prior session left it exhausted), swap
 // the credential before this session's first turn so it starts on a good account.
-// Right after a respawn, usage.json is stale for the new org, so the org guard in
-// evaluateAndMaybeSwap makes this correctly no-op.
+// Right after a respawn, the post-swap cooldown in evaluateAndMaybeSwap makes
+// this correctly no-op.
 
 import { z } from "zod";
 import { evaluateAndMaybeSwap } from "../lib/decide.ts";

package/src/entries/statusline.ts

@@ -17,7 +17,7 @@ import { sortBy } from "es-toolkit";
 import { z } from "zod";
 import { readOAuthAccount } from "../lib/claudejson.ts";
 import { loadAccounts, loadConfig, loadLastSwapAt, loadModelUsage, writeUsage } from "../lib/state.ts";
-import { familyTokens, matchedFamily, parseStatusLineStdin, parseStatusLineModel } from "../lib/usage.ts";
+import { familyTokens, gatedFamilies, matchedFamily, parseStatusLineStdin, parseStatusLineModel } from "../lib/usage.ts";
 import { isExhausted, swapPreference, weeklyExpiry } from "../lib/picker.ts";
 import { worktreeName } from "../lib/worktree.ts";
 import { fmtResetShort, makeColors } from "../cli/render.ts";
@@ -105,7 +105,12 @@ export function renderStatusline(stdinObj: unknown, ctx: RenderCtx): string {
         : "";
 
   // ---- parked accounts, in swap order: the first usable ◇ is the next target
-  const pickCtx = { now: ctx.now, threshold: ctx.threshold, currentAccountUuid: ctx.accounts.activeAccountUuid };
+  const pickCtx = {
+    now: ctx.now,
+    threshold: ctx.threshold,
+    currentAccountUuid: ctx.accounts.activeAccountUuid,
+    switchFamilies: gatedFamilies(parseStatusLineModel(stdinObj), ctx.switchModels),
+  };
   const parked = sortBy(
     ctx.accounts.accounts.filter((a) => a.accountUuid !== ctx.accounts.activeAccountUuid),
     [(a) => (a.needsReauth || isExhausted(a, pickCtx) ? 1 : 0), ...swapPreference(ctx.now)],

package/src/entries/stophook.ts

@@ -30,7 +30,10 @@ export async function runStopHook(): Promise<number> {
     (parsed.success ? parsed.data.session_id : undefined) ?? process.env.TOKENMAXXING_SESSION_ID;
 
   try {
-    const decision = await evaluateAndMaybeSwap();
+    // Anticipatory depleted swaps are only sane when the respawn marker below
+    // will actually pause the session until the reset.
+    const canPause = process.env.TOKENMAXXING_SUPERVISED === "1" && sessionId != null;
+    const decision = await evaluateAndMaybeSwap(Date.now(), canPause);
     // Respawn on a swap, or on a depleted-pool wait (relaunch after the reset).
     if (decision.account && (decision.swapped || decision.waitUntil !== undefined)) {
       log(decision.swapped ? "stop.swapped" : "stop.wait", { account: decision.account.accountUuid.slice(0, 8), waitUntil: decision.waitUntil });

package/src/lib/claudebin.ts

@@ -7,9 +7,14 @@ import { loadConfig } from "./state.ts";
 
 export function resolveRealClaude(): string {
   const cfg = loadConfig();
-  if (cfg.claudeBin && existsSync(cfg.claudeBin)) return cfg.claudeBin;
-  if (process.env.TOKENMAXXING_CLAUDE_BIN && existsSync(process.env.TOKENMAXXING_CLAUDE_BIN))
-    return process.env.TOKENMAXXING_CLAUDE_BIN;
+  if (cfg.claudeBin) {
+    if (existsSync(cfg.claudeBin)) return cfg.claudeBin;
+    // A configured-but-vanished binary must not silently degrade to the PATH
+    // scan: under a relocated TOKENMAXXING_HOME the scan's binDir guard misses
+    // the installed wrapper, which then recurses through the supervisor
+    // (observed 2026-07-12 as a forever-hung `/usage` probe).
+    throw new Error(`configured claudeBin does not exist: ${cfg.claudeBin} - fix config.json`);
+  }
   for (const d of (process.env.PATH ?? "").split(":")) {
     if (!d || d === paths.binDir) continue;
     const cand = join(d, "claude");

package/src/lib/decide.ts

@@ -1,11 +1,16 @@
-// Shared switch decision used by both the Stop hook and the SessionStart hook.
-// Cheap pre-check off the lock; the authoritative re-check + swap under the flock.
+// Shared switch decision used by the Stop/SessionStart hooks and the periodic
+// `check` timer. Cheap pre-check off the lock; the authoritative re-check + swap
+// under the flock.
 //
 // Two limit families are checked, both metered against the CURRENTLY-active org:
-//   1. AGGREGATE windows (session=five_hour, week-all=seven_day) from statusLine.
-//   2. PER-MODEL weekly cap (e.g. "week (Fable)") - only when the active model is
-//      capacity-constrained (config policy.switchModels). This isn't in statusLine,
-//      so we read it from `claude -p '/usage'`, TTL-cached (not every turn).
+//   1. AGGREGATE windows (session=five_hour, week-all=seven_day). A rendering
+//      statusLine tees them fresh every turn; when nothing renders (headless
+//      boxes, idle TUIs) they come from `claude -p '/usage'`, re-probed once the
+//      snapshot ages past the poll TTL so they can never freeze at a stale value.
+//   2. PER-MODEL weekly cap (e.g. "week (Fable)") - when the active model is
+//      capacity-constrained (config policy.switchModels), or for EVERY configured
+//      family when the model is unknown (nothing rendered within the TTL, so the
+//      session that stamped the last model may be gone).
 //
 // The org guard is load-bearing: right after a respawn, usage.json still reflects
 // the OLD account, so org != activeOrg → we correctly do nothing until fresh usage
@@ -15,14 +20,14 @@ import { maxBy } from "es-toolkit";
 import { z } from "zod";
 import { withLock } from "./lock.ts";
 import { paths } from "./paths.ts";
-import { loadAccounts, loadConfig, loadUsage, loadModelUsage, saveAccounts, saveModelUsage, writeUsage } from "./state.ts";
+import { loadAccounts, loadConfig, loadLastSwapAt, loadUsage, loadModelUsage, saveAccounts, saveModelUsage, usageTeeAt, writeUsage } from "./state.ts";
 import { readOAuthAccount } from "./claudejson.ts";
 import { chooseAndSwap, performSwap } from "./swap.ts";
 import { pickEarliestReset, usableAt } from "./picker.ts";
 import { InvalidGrantError } from "./oauth.ts";
-import { familyTokens, matchedFamily, probeUsage } from "./usage.ts";
+import { familyTokens, gatedFamilies, probeUsage } from "./usage.ts";
 import { log } from "./log.ts";
-import { AccountSchema, type Account, type Config, type ModelUsageState, type UsageState, type UsageWindow } from "./types.ts";
+import { AccountSchema, ModelUsageStateSchema, UsageStateSchema, type Account, type Config, type ModelUsageState, type UsageState, type UsageWindow } from "./types.ts";
 
 const SwapDecisionSchema = z.object({
   swapped: z.boolean(),
@@ -33,75 +38,130 @@ const SwapDecisionSchema = z.object({
 });
 export type SwapDecision = z.infer<typeof SwapDecisionSchema>;
 
-/** Cold-start aggregate fallback when statusLine hasn't written usage.json yet. */
-async function probeAggregate(org: string | null): Promise<UsageState | null> {
-  const full = await probeUsage();
-  if (!full) return null;
-  return { fiveHour: full.session, sevenDay: full.weekAll, org, ts: Date.now(), model: null };
-}
-
-/** Ensure a fresh-enough per-model cache for the active org; poll `/usage` if stale. */
-async function ensurePerModel(cfg: Config, org: string | null): Promise<ModelUsageState | null> {
-  const cached = loadModelUsage();
-  const fresh = cached && cached.org === org && Date.now() - cached.ts < cfg.policy.usagePollTtlMs;
-  if (fresh) return cached;
-  const full = await probeUsage();
-  if (!full) {
-    // Probing the live token fail-silently while it's busy is expected; stamp the
-    // cache so the next probe waits out the TTL instead of every turn re-paying
-    // the full backoff (the 2026-07-10 post-swap probe storm).
-    saveModelUsage({ perModel: cached?.org === org ? cached.perModel : {}, org, ts: Date.now() });
-    return cached;
-  }
-  const state: ModelUsageState = { perModel: full.perModel, org, ts: Date.now() };
-  saveModelUsage(state);
-  return state;
+/** A window's usable-against percentage NOW: one whose cached reset has passed
+ *  is empty again, never a switch reason. */
+function liveUsed(w: UsageWindow, now: number): number {
+  return w.resetsAt != null && w.resetsAt <= now ? 0 : w.usedPercentage;
 }
 
 /** The family's weekly cap among the `/usage` rows; when several rows match the
- *  family, the most-used one wins (switching early beats metering a depleted cap). */
-function capForFamily(mu: ModelUsageState, family: string): UsageWindow | undefined {
+ *  family, the most-used LIVE one wins (switching early beats metering a depleted
+ *  cap, but a row whose reset passed must not mask a still-burning sibling). */
+function capForFamily(mu: ModelUsageState, family: string, now: number): UsageWindow | undefined {
   const rows = Object.entries(mu.perModel)
     .filter(([k]) => familyTokens(k).includes(family))
     .map(([, w]) => w);
-  return maxBy(rows, (w) => w.usedPercentage);
+  return maxBy(rows, (w) => liveUsed(w, now));
 }
 
 /** True if the active account is over the floor on ANY applicable limit. */
-function isOver(u: UsageState | null, mu: ModelUsageState | null, org: string | null, cfg: Config, floor: number): boolean {
+function isOver(u: UsageState | null, mu: ModelUsageState | null, org: string | null, cfg: Config, floor: number, now: number): boolean {
   if (!u || !org || u.org !== org) return false;
-  if (u.fiveHour.usedPercentage >= floor || u.sevenDay.usedPercentage >= floor) return true;
-  const family = matchedFamily(u.model, cfg.policy.switchModels);
-  if (family && mu && mu.org === org) {
-    const cap = capForFamily(mu, family);
-    if (cap && cap.usedPercentage >= floor) return true;
+  if (liveUsed(u.fiveHour, now) >= floor || liveUsed(u.sevenDay, now) >= floor) return true;
+  if (mu && mu.org === org) {
+    for (const family of gatedFamilies(u.model, cfg.policy.switchModels)) {
+      const cap = capForFamily(mu, family, now);
+      if (cap && liveUsed(cap, now) >= floor) return true;
+    }
   }
   return false;
 }
 
-/** Does the active model warrant a per-model `/usage` poll? */
+/** Does a per-model cap gate the decision for this usage snapshot? */
 function needsPerModel(u: UsageState | null, cfg: Config): boolean {
-  return matchedFamily(u?.model ?? null, cfg.policy.switchModels) !== null;
+  return u != null && gatedFamilies(u.model, cfg.policy.switchModels).length > 0;
+}
+
+const SnapshotsSchema = z.object({
+  u: UsageStateSchema.nullable(),
+  mu: ModelUsageStateSchema.nullable(),
+});
+type Snapshots = z.infer<typeof SnapshotsSchema>;
+
+/** usage.json is trusted while the tee proved itself alive (mtime, NOT the
+ *  embedded ts - write-on-change lets ts age under an alive feed) within the
+ *  TTL for the live org. */
+function usageFresh(u: UsageState | null, org: string | null, ttl: number, now: number): boolean {
+  if (u == null || u.org !== org) return false;
+  const teeAt = usageTeeAt();
+  return teeAt != null && now - teeAt <= ttl;
+}
+
+/**
+ * Load the two usage snapshots, re-probing `/usage` (free, 0 tokens) when they
+ * are absent, org-drifted, or older than the poll TTL. ONE probe carries all
+ * three limit kinds, so a success refreshes BOTH files; anything less leaves a
+ * headless box (no rendering statusLine to tee) evaluating frozen or
+ * org-mismatched values forever - the 2026-07-12 stella blindness. The
+ * refreshed usage carries model: null (whatever session stamped the old model
+ * may be gone), which gates every configured family. model-usage.json's ts also
+ * stamps FAILED attempts, so a busy live token cannot cause a probe storm
+ * (2026-07-10): the next hook waits out the TTL instead of re-probing.
+ */
+async function loadFreshSnapshots(cfg: Config, org: string | null, now: number): Promise<Snapshots> {
+  let u = loadUsage();
+  let mu = loadModelUsage();
+  const ttl = cfg.policy.usagePollTtlMs;
+  const probeAttempted = mu != null && mu.org === org && now - mu.ts <= ttl;
+  if (org && !probeAttempted && (!usageFresh(u, org, ttl, now) || needsPerModel(u, cfg))) {
+    const full = await probeUsage();
+    const ts = Date.now();
+    // A swap can complete while the probe runs (no lock is held here). Its
+    // result would then be stamped under the pre-swap org over the files the
+    // swap just cleared - discard it; the locked re-check below rejects this
+    // evaluation anyway and the next one re-probes the new org.
+    if (readOAuthAccount()?.organizationUuid === org) {
+      if (full) {
+        // A probe takes seconds; a rendering session's tee may have landed
+        // while it ran. The tee is fresher AND model-aware, so it wins.
+        const teed = loadUsage();
+        if (usageFresh(teed, org, ttl, ts)) {
+          u = teed;
+        } else {
+          u = { fiveHour: full.session, sevenDay: full.weekAll, org, ts, model: null };
+          writeUsage(u);
+        }
+        mu = { perModel: full.perModel, org, ts };
+        saveModelUsage(mu);
+      } else {
+        mu = { perModel: mu?.org === org ? (mu?.perModel ?? {}) : {}, org, ts };
+        saveModelUsage(mu);
+      }
+    }
+  }
+  return { u, mu };
 }
 
-export async function evaluateAndMaybeSwap(now = Date.now()): Promise<SwapDecision> {
+/** How long after a swap the auto paths hold still. The statusLine tee is
+ *  suppressed this long (sessions adopt the swap in <=30s), so a decision made
+ *  sooner runs model-blind on data the swap itself invalidated - that is how a
+ *  model-aware swap got immediately undone into an A<->B respawn loop. Manual
+ *  `switch` is unaffected. */
+const POST_SWAP_COOLDOWN_MS = 45_000;
+
+/**
+ * `anticipatory` allows the depleted path to swap onto an account that is still
+ * blocked but recovers soonest. Only a caller that can PAUSE until the reset
+ * (the supervised Stop hook, which writes a respawn marker the supervisor
+ * honors with a countdown) should pass true: from the check timer or an
+ * unsupervised hook, pre-parking silently yanks a live session onto a
+ * known-over-limit account, and buys nothing - the normal pick path adopts the
+ * recovering account the moment its reset passes.
+ */
+export async function evaluateAndMaybeSwap(now = Date.now(), anticipatory = false): Promise<SwapDecision> {
+  const lastSwapAt = loadLastSwapAt();
+  if (lastSwapAt != null && now - lastSwapAt < POST_SWAP_COOLDOWN_MS) {
+    return { swapped: false, account: null, reason: "post-swap-cooldown" };
+  }
+
   const cfg = loadConfig();
   const floor = cfg.threshold - cfg.policy.projectionMargin;
   const activeOrg = readOAuthAccount()?.organizationUuid ?? null;
 
-  let usage = loadUsage();
-  if (!usage && activeOrg) {
-    usage = await probeAggregate(activeOrg);
-    // Persist: post-swap the snapshots are cleared and the statusLine tee is in
-    // its grace window, so without this every turn boundary would re-probe.
-    if (usage) writeUsage(usage);
-  }
-
-  // per-model poll (TTL-cached) only when on a capacity-constrained model
-  const mu = needsPerModel(usage, cfg) ? await ensurePerModel(cfg, activeOrg) : null;
+  const { u: usage, mu } = await loadFreshSnapshots(cfg, activeOrg, now);
 
   // cheap pre-check off the lock - the common case exits here.
-  if (!isOver(usage, mu, activeOrg, cfg, floor)) {
+  if (!isOver(usage, mu, activeOrg, cfg, floor, now)) {
     return { swapped: false, account: null, reason: "under-threshold-or-stale" };
   }
 
@@ -116,25 +176,31 @@ export async function evaluateAndMaybeSwap(now = Date.now()): Promise<SwapDecisi
       const active = idx.accounts.find((a) => a.accountUuid === idx.activeAccountUuid);
       if (active) {
         active.lastUsage = { fiveHour: u2.fiveHour, sevenDay: u2.sevenDay };
+        active.lastUsageAt = u2.ts;
         // Snapshot per-model caps too, so they still show after we switch away.
-        if (mu2 && mu2.org === org2) active.lastPerModel = mu2.perModel;
+        // An empty map is a failed probe's anti-storm stamp, not a measurement -
+        // it must not erase the burnt-cap snapshot the picker screens on.
+        if (mu2 && mu2.org === org2 && Object.keys(mu2.perModel).length > 0) active.lastPerModel = mu2.perModel;
         saveAccounts(idx);
       }
     }
 
-    if (!isOver(u2, mu2, org2, cfg, floor)) {
+    if (!isOver(u2, mu2, org2, cfg, floor, now)) {
       return { swapped: false, account: null, reason: "raced-already-swapped" };
     }
 
-    const landed = await chooseAndSwap({ now, threshold: cfg.threshold });
+    // Candidates are screened by the same families that drove this decision, so
+    // the pool cannot ping-pong onto an account the gate would immediately flag.
+    const switchFamilies = gatedFamilies(u2?.model ?? null, cfg.policy.switchModels);
+    const landed = await chooseAndSwap({ now, threshold: cfg.threshold, switchFamilies });
     if (landed) return { swapped: true, account: landed, reason: "swapped" };
 
     // Every account is depleted. Wait for whichever recovers soonest (including the
     // current one), if that reset is within the auto-wait window.
     const fresh = loadAccounts();
-    const ctx = { now, threshold: cfg.threshold, currentAccountUuid: fresh.activeAccountUuid };
+    const ctx = { now, threshold: cfg.threshold, currentAccountUuid: fresh.activeAccountUuid, switchFamilies };
     const current = fresh.accounts.find((a) => a.accountUuid === fresh.activeAccountUuid);
-    const currentAt = current ? usableAt(current, cfg.threshold, now) : Number.POSITIVE_INFINITY;
+    const currentAt = current ? usableAt(current, ctx) : Number.POSITIVE_INFINITY;
     const other = pickEarliestReset(fresh.accounts, ctx);
 
     let target: Account | null = null;
@@ -149,6 +215,10 @@ export async function evaluateAndMaybeSwap(now = Date.now()): Promise<SwapDecisi
     }
 
     const isCurrent = target.accountUuid === fresh.activeAccountUuid;
+    if (!isCurrent && !anticipatory) {
+      log("decide.depleted_no_park", { account: target.accountUuid.slice(0, 8), waitUntil });
+      return { swapped: false, account: null, reason: "all-depleted" };
+    }
     if (!isCurrent) {
       try {
         await performSwap(target);

package/src/lib/picker.ts

@@ -1,82 +1,113 @@
-// Choose the best account to switch TO when the active one crosses threshold.
-// Policy: exclude the current account and any that need reauth or are still
-// rate-limited (usage >= threshold and not yet past resets_at). Among the rest,
-// prefer the account whose weekly window expires soonest: weekly limits reset
-// at a fixed per-account time and unused allowance is forfeited at reset, so
-// quota nearest its reset is use-it-or-lose-it and should be drained first.
-// Tiebreak on lowest 7-day usage, then soonest 5h reset.
+// Choose the account to switch TO. Greedy policy: among usable accounts (no
+// reauth, no window >= threshold that hasn't reset yet), take the one whose
+// weekly window expires soonest - weekly limits reset at a fixed per-account
+// time and unused allowance is forfeited at reset, so quota nearest its reset
+// is use-it-or-lose-it and should be drained first. Runs entirely off each
+// account's cached windows (absolute UTC epochs, so a stale snapshot still
+// resolves to the correct upcoming reset), which makes the pick deterministic
+// and idempotent: re-running lands on the same account.
 
 import { minBy, sortBy } from "es-toolkit";
 import { z } from "zod";
-import { AccountSchema, type Account } from "./types.ts";
+import { familyTokens } from "./usage.ts";
+import { AccountSchema, type Account, type UsageWindow } from "./types.ts";
 
 const PickCtxSchema = z.object({
   now: z.number(),
   threshold: z.number(),
+  /** account to exclude (hooks switch AWAY from it); null ranks everyone. */
   currentAccountUuid: z.string().nullable(),
+  /** families whose per-model weekly cap counts toward exhaustion (from
+   *  gatedFamilies): a candidate with a burnt gated cap is no switch target -
+   *  landing on it would re-trigger the same gate and ping-pong the pool. */
+  switchFamilies: z.array(z.string()),
 });
 export type PickCtx = z.infer<typeof PickCtxSchema>;
 
+/** The account's cached per-model windows that belong to a gated family. */
+function gatedPerModelWindows(a: Account, families: string[]): UsageWindow[] {
+  return Object.entries(a.lastPerModel ?? {})
+    .filter(([model]) => families.some((f) => familyTokens(model).includes(f)))
+    .map(([, w]) => w);
+}
+
+const WEEK_MS = 7 * 24 * 60 * 60 * 1000;
+const FIVE_HOURS_MS = 5 * 60 * 60 * 1000;
+
+/** Epoch until which `w` blocks the account; anything <= now means it does not
+ *  block. A window with no known reset (unparsed clock) is still bounded by
+ *  its own duration past the sample time - a 5h window sampled 6h ago has
+ *  certainly reset - so a benched account always recovers by itself. With no
+ *  sample time either, it blocks indefinitely: guessing "usable now" would
+ *  swap onto it with waitUntil=now and churn kill/respawn. */
+function blockedUntil(w: UsageWindow, windowMs: number, sampledAt: number | undefined, ctx: PickCtx): number {
+  if (w.usedPercentage < ctx.threshold) return 0;
+  if (w.resetsAt != null) return w.resetsAt;
+  return sampledAt != null ? sampledAt + windowMs : Number.POSITIVE_INFINITY;
+}
+
+/** When each of the account's windows stops blocking: the two aggregates plus
+ *  the gated per-model caps. */
+function blockingUntil(a: Account, ctx: PickCtx): number[] {
+  const u = a.lastUsage;
+  return [
+    ...(u ? [blockedUntil(u.fiveHour, FIVE_HOURS_MS, a.lastUsageAt, ctx), blockedUntil(u.sevenDay, WEEK_MS, a.lastUsageAt, ctx)] : []),
+    ...gatedPerModelWindows(a, ctx.switchFamilies).map((w) => blockedUntil(w, WEEK_MS, a.lastUsageAt, ctx)),
+  ];
+}
+
 /** An account is "exhausted" if a window is >= threshold and hasn't reset yet. */
 export function isExhausted(a: Account, ctx: PickCtx): boolean {
-  const u = a.lastUsage;
-  if (!u) return false;
-  const blocked = (w: { usedPercentage: number; resetsAt: number | null }) =>
-    w.usedPercentage >= ctx.threshold && (w.resetsAt == null || w.resetsAt > ctx.now);
-  return blocked(u.fiveHour) || blocked(u.sevenDay);
+  return blockingUntil(a, ctx).some((t) => t > ctx.now);
 }
 
-const WEEK_MS = 7 * 24 * 60 * 60 * 1000;
+/** Next occurrence of a weekly reset. The weekly reset is a fixed per-account
+ *  anchor, so a cached (past) resetsAt extrapolates forward in 7-day steps -
+ *  an old snapshot still yields the correct upcoming reset. */
+export function nextWeeklyReset(resetsAt: number | null, now: number): number | null {
+  if (resetsAt == null || resetsAt > now) return resetsAt;
+  return resetsAt + (Math.floor((now - resetsAt) / WEEK_MS) + 1) * WEEK_MS;
+}
 
-/** Epoch ms when the account's weekly quota is next forfeited. The weekly reset
- *  is a fixed per-account anchor, so a stale (past) resetsAt extrapolates
- *  forward in 7-day steps; an account with no sampled reset sorts last. */
+/** Epoch ms when the account's weekly quota is next forfeited; an account with
+ *  no sampled reset sorts last. */
 export function weeklyExpiry(a: Account, now: number): number {
-  const r = a.lastUsage?.sevenDay.resetsAt;
-  if (r == null) return Number.POSITIVE_INFINITY;
-  if (r > now) return r;
-  return r + (Math.floor((now - r) / WEEK_MS) + 1) * WEEK_MS;
+  return nextWeeklyReset(a.lastUsage?.sevenDay.resetsAt ?? null, now) ?? Number.POSITIVE_INFINITY;
 }
 
-/** The switch preference: soonest weekly expiry first; tiebreak lowest 7-day
- *  usage, then soonest 5h reset. Shared with the statusLine pool ordering so
- *  the display order IS the swap order. */
+/** The switch preference: soonest weekly expiry first, tiebreak lowest 7-day
+ *  usage. Shared with the statusLine pool ordering so the display order IS the
+ *  swap order. */
 export const swapPreference = (now: number) => [
   (a: Account) => weeklyExpiry(a, now),
   (a: Account) => a.lastUsage?.sevenDay.usedPercentage ?? 0,
-  (a: Account) => a.lastUsage?.fiveHour.resetsAt ?? Number.POSITIVE_INFINITY,
 ];
 
 export function pickBest(accounts: Account[], ctx: PickCtx): Account | null {
-  const candidates = accounts.filter(
-    (a) =>
-      a.accountUuid !== ctx.currentAccountUuid &&
-      !a.needsReauth &&
-      !isExhausted(a, ctx),
+  const usable = accounts.filter(
+    (a) => a.accountUuid !== ctx.currentAccountUuid && !a.needsReauth && !isExhausted(a, ctx),
   );
-  if (candidates.length === 0) return null;
-  return sortBy(candidates, swapPreference(ctx.now))[0]!;
+  return sortBy(usable, swapPreference(ctx.now))[0] ?? null;
 }
 
-/** When an account becomes usable again: the latest reset among its over-threshold
- *  windows (all must reset), or `now` if nothing is over. */
-export function usableAt(a: Account, threshold: number, now: number): number {
-  const u = a.lastUsage;
-  if (!u) return now;
-  const blocking = [u.fiveHour, u.sevenDay]
-    .filter((w) => w.usedPercentage >= threshold && w.resetsAt != null)
-    .map((w) => w.resetsAt as number);
-  return blocking.length ? Math.max(...blocking) : now;
+/** When an account becomes usable again: the latest blocking bound among its
+ *  windows (all must clear), or `now` if nothing blocks. Consistent with
+ *  isExhausted by construction (same blockingUntil). */
+export function usableAt(a: Account, ctx: PickCtx): number {
+  const blocking = blockingUntil(a, ctx).filter((t) => t > ctx.now);
+  return blocking.length ? Math.max(...blocking) : ctx.now;
 }
 
 const EarliestResetSchema = z.object({ account: AccountSchema, availableAt: z.number() });
 export type EarliestReset = z.infer<typeof EarliestResetSchema>;
 
 /** For the all-depleted case: the account (not current, not reauth) that becomes
- *  usable soonest. */
+ *  usable soonest. Accounts blocked with no known reset are unknowable, never
+ *  a wait target. */
 export function pickEarliestReset(accounts: Account[], ctx: PickCtx): EarliestReset | null {
   const mapped = accounts
     .filter((a) => a.accountUuid !== ctx.currentAccountUuid && !a.needsReauth)
-    .map((a) => ({ account: a, availableAt: usableAt(a, ctx.threshold, ctx.now) }));
+    .map((a) => ({ account: a, availableAt: usableAt(a, ctx) }))
+    .filter((x) => Number.isFinite(x.availableAt));
   return minBy(mapped, (x) => x.availableAt) ?? null;
 }

package/src/lib/state.ts

@@ -1,6 +1,6 @@
 // Config + accounts index + usage snapshot persistence. All writes atomic.
 
-import { existsSync, readFileSync, rmSync } from "node:fs";
+import { existsSync, readFileSync, rmSync, statSync, utimesSync } from "node:fs";
 import { isEqual } from "es-toolkit";
 import { z } from "zod";
 import { paths, realClaudeBinFromEnv } from "./paths.ts";
@@ -22,7 +22,9 @@ import {
 const DEFAULT_CONFIG: Config = {
   threshold: 95,
   claudeBin: "",
-  policy: { projectionMargin: 0, switchModels: ["fable", "opus"], usagePollTtlMs: 90_000, maxWaitMs: 3_600_000 },
+  // per-model weekly caps exist only for Sonnet and Fable (no Opus-only quota,
+  // per the user 2026-07-12), and only Fable's is worth switching on.
+  policy: { projectionMargin: 0, switchModels: ["fable"], usagePollTtlMs: 90_000, maxWaitMs: 3_600_000 },
 };
 
 /** On-disk shape (all optional); validated via Zod, merged over defaults. */
@@ -124,14 +126,42 @@ export function saveLastSwapAt(ts: number): void {
   writeFileAtomic(paths.lastSwapJson, JSON.stringify(LastSwapSchema.parse({ ts })));
 }
 
-/** Write-on-change: skip the write (and its fsync) when only `ts` would differ. */
+/** An alive feed re-proving unchanged figures still refreshes `ts` this often,
+ *  so cache-age displays stay honest without a write+fsync per tick. */
+const USAGE_TS_REFRESH_MS = 10 * 60_000;
+
+/** Write-on-change: skip the write (and its fsync) when only `ts` would differ,
+ *  unless the stored `ts` has aged past the refresh window. A suppressed write
+ *  still bumps the file's mtime (metadata only, no fsync): mtime is the feed's
+ *  liveness heartbeat, and without the bump an alive tee re-proving unchanged
+ *  figures reads as a dead feed and the decision path goes model-blind. */
 export function writeUsage(next: UsageState): boolean {
   const prev = loadUsage();
-  if (prev && isEqual({ ...prev, ts: 0 }, { ...next, ts: 0 })) return false;
+  if (prev && isEqual({ ...prev, ts: 0 }, { ...next, ts: 0 }) && next.ts - prev.ts < USAGE_TS_REFRESH_MS) {
+    try {
+      utimesSync(paths.usageJson, new Date(next.ts), new Date(next.ts));
+    } catch (e) {
+      // The file vanished mid-race: a concurrent swap just invalidated these
+      // figures. Suppressing stays correct; a write would resurrect them.
+      if ((e as { code?: string }).code !== "ENOENT") throw e;
+    }
+    return false;
+  }
   writeFileAtomic(paths.usageJson, JSON.stringify(next));
   return true;
 }
 
+/** When the usage feed last proved itself alive (usage.json mtime), null if the
+ *  snapshot is absent. Fresher than the embedded `ts`, which write-on-change
+ *  deliberately lets age while figures hold still. */
+export function usageTeeAt(): number | null {
+  try {
+    return statSync(paths.usageJson).mtimeMs;
+  } catch {
+    return null;
+  }
+}
+
 // ---- model-usage.json (per-model caps from `/usage`, TTL-cached) ----------
 
 export function loadModelUsage(): ModelUsageState | null {

package/src/lib/types.ts

@@ -84,6 +84,10 @@ export const AccountSchema = z.object({
   addedAt: z.string(),
   lastUsage: UsageWindowsSchema.optional(),
   lastPerModel: z.record(z.string(), UsageWindowSchema).optional(),
+  /** epoch ms of the sample behind lastUsage/lastPerModel. Their resetsAt
+   *  values are absolute epochs (UTC-anchored), so even an old snapshot still
+   *  resolves to correct resets - display it as a dated cache, never discard. */
+  lastUsageAt: z.number().optional(),
   needsReauth: z.boolean().optional(),
   subscriptionType: z.string().optional(),
 });

package/src/lib/usage.ts

@@ -67,6 +67,19 @@ export function matchedFamily(model: ModelInfo | null, families: string[]): stri
   return families.find((f) => tokens.has(f)) ?? null;
 }
 
+/** Families whose per-model weekly cap gates a switch, given the active model:
+ *  the model's own family when it is capacity-constrained, none when it is a
+ *  known-unconstrained model, and EVERY configured family when the model is
+ *  unknown. The unknown case matters on headless boxes: a swap clears the
+ *  snapshots and only an actively-rendering statusLine restores the model, so
+ *  the periodic check ran model-blind for hours while the active account sat at
+ *  its Fable cap (the 2026-07-12 stella incident). */
+export function gatedFamilies(model: ModelInfo | null, families: string[]): string[] {
+  if (!model) return families;
+  const family = matchedFamily(model, families);
+  return family ? [family] : [];
+}
+
 export const FullUsageSchema = z.object({
   session: UsageWindowSchema,
   weekAll: UsageWindowSchema,
@@ -195,6 +208,11 @@ const CRED_ENV_OVERRIDES = [
 /** One `claude -p '/usage'` invocation → parsed usage, or null if it produced no
  *  limit lines (claude prints only a local-stats footer when its own usage fetch
  *  errors/throttles) or failed to run. */
+/** A probe child that wedges (auth prompt, dead endpoint) must never block the
+ *  Stop/SessionStart hooks or the status flock forever; a healthy `/usage`
+ *  answers in seconds. */
+const PROBE_KILL_MS = 60_000;
+
 async function probeUsageOnce(env: Record<string, string>, now: number): Promise<FullUsage | null> {
   let out: string;
   try {
@@ -203,12 +221,17 @@ async function probeUsageOnce(env: Record<string, string>, now: number): Promise
       stdout: "pipe",
       stderr: "pipe",
     });
-    out = await new Response(p.stdout).text();
-    const errText = await new Response(p.stderr).text();
-    await p.exited;
-    if (p.exitCode !== 0) {
-      log("usage.probe_failed", { exit: p.exitCode ?? "signal", stderr: errText.trim().slice(0, 200) });
-      return null;
+    const killer = setTimeout(() => p.kill(), PROBE_KILL_MS);
+    try {
+      out = await new Response(p.stdout).text();
+      const errText = await new Response(p.stderr).text();
+      await p.exited;
+      if (p.exitCode !== 0) {
+        log("usage.probe_failed", { exit: p.exitCode ?? "signal", stderr: errText.trim().slice(0, 200) });
+        return null;
+      }
+    } finally {
+      clearTimeout(killer);
     }
   } catch (e) {
     log("usage.probe_failed", { err: String((e as Error).message ?? e) });

package/src/main.ts

@@ -24,7 +24,7 @@ function printHelp(): void {
   console.log(`${c.bold("tokenmaxxing")} - automatic Claude Code account switching
 
   ${c.cyan("tokenmaxxing")}            show the pool with usage bars (alias of ${c.cyan("status")})
-  ${c.cyan("tokenmaxxing switch")} [sel]  switch now to the best (or a specific) account
+  ${c.cyan("tokenmaxxing switch")} [sel]  switch to the best (or a specific) account; no-op when already on it
   ${c.cyan("tokenmaxxing check")}      evaluate once, switch if over threshold (run by the periodic timer)
   ${c.cyan("tokenmaxxing init")}       import the current account + install supervisor & hooks
   ${c.cyan("tokenmaxxing add")}        register an additional account (isolated login)