claude-token-saver 2.16.0 → 2.18.0

package/src/advice.js

@@ -39,25 +39,33 @@ function toggleShortcut() {
  */
 export const ISSUE_MESSAGES = {
   LARGE_INPUT_PER_REQUEST: {
-    title: 'Per-request input tokens are unusually large (1M context suspected)',
-    titleKo: '요청당 입력 토큰이 비정상적으로 큼 (1M 컨텍스트 의심)',
+    title: 'Per-request input tokens are unusually large (context past 200k)',
+    titleKo: '요청당 입력 토큰이 비정상적으로 큼 (컨텍스트 200k 초과)',
+    // Since Opus 4.7 there is NO long-context price premium — 1M is standard
+    // rate and the default window on current models. The cost driver is the
+    // token volume itself: a 500k-token context re-reads ~500k tokens every
+    // turn (cache-read billed) and burns the subscription 5H/7D windows
+    // several times faster. That's what this warning is about.
     explain:
-      'Since Opus 4.7, 1M context is priced at the standard rate, and Max plans auto-promote ' +
-      'sessions to 1M. Once context goes past 200k, long-context pricing kicks in and cache reuse drops.',
+      'Current models default to a 1M window with no long-context premium — but the token ' +
+      'volume itself is the cost: every turn re-reads the whole context (billed as cache reads) ' +
+      'and drains the 5H/7D rate-limit windows several times faster. Cache reuse also drops.',
     explainKo:
-      'Opus 4.7부터 1M 컨텍스트가 표준 요금이 되었고, Max 플랜은 세션을 자동으로 1M으로 승격합니다. ' +
-      '200k를 넘는 순간 장기 컨텍스트 요금이 적용되며 캐시 재사용률도 떨어집니다.',
+      '현재 모델은 1M 윈도가 기본이고 장기 컨텍스트 프리미엄도 없습니다 — 하지만 토큰량 자체가 비용입니다. ' +
+      '매 턴 컨텍스트 전체를 다시 읽고(캐시 읽기 과금) 5H/7D 한도도 몇 배 빠르게 소모됩니다. ' +
+      '캐시 재사용률도 떨어집니다.',
     actions: () => [
       {
-        label: 'Disable 1M context (env var)',
-        labelKo: '1M 컨텍스트 끄기 (환경변수)',
-        commands: disable1mEnvSnippet(),
-      },
-      {
-        label: 'In-session toggle',
-        labelKo: '세션 내 즉시 토글',
-        commands: [`Press ${toggleShortcut()} to toggle on/off instantly`],
-        commandsKo: [`${toggleShortcut()} 누르면 즉시 on/off 토글`],
+        label: 'Compact or clear when context grows (first lever)',
+        labelKo: '컨텍스트가 커지면 /compact 또는 /clear (1순위)',
+        commands: [
+          '/compact  — summarize the session history in place',
+          '/clear    — drop history entirely at a clean task boundary',
+        ],
+        commandsKo: [
+          '/compact — 세션 히스토리를 그 자리에서 요약',
+          '/clear   — 작업 분기점에서 히스토리를 통째로 비우기',
+        ],
       },
       {
         label: 'Cap extended-thinking budget (⚠ check /effort first)',
@@ -90,16 +98,14 @@ export const ISSUE_MESSAGES = {
         ],
       },
       {
-        label: 'Compact or clear when context grows',
-        labelKo: '컨텍스트가 커지면 /compact 또는 /clear',
-        commands: [
-          '/compact  — summarize the session history in place',
-          '/clear    — drop history entirely at a clean task boundary',
-        ],
-        commandsKo: [
-          '/compact — 세션 히스토리를 그 자리에서 요약',
-          '/clear   — 작업 분기점에서 히스토리를 통째로 비우기',
-        ],
+        label: 'Cap the window at 200k if you never need more (optional)',
+        labelKo: '더 큰 윈도가 필요 없으면 200k로 제한 (선택)',
+        commands: disable1mEnvSnippet().concat([
+          `Or press ${toggleShortcut()} to toggle in-session`,
+        ]),
+        commandsKo: disable1mEnvSnippet().concat([
+          `또는 ${toggleShortcut()}로 세션 내 즉시 토글`,
+        ]),
       },
       {
         label: '⚠ Known bug #31640',
@@ -337,11 +343,13 @@ export const ISSUE_MESSAGES = {
     title: 'Context window is approaching the limit',
     titleKo: '컨텍스트 창이 한계에 근접',
     explain:
-      'As context grows toward 200k (or 1M), each turn becomes more expensive and cache ' +
-      'reuse efficiency drops. Past 200k, long-context pricing applies.',
+      'As context grows, each turn becomes more expensive (the whole context is re-read every ' +
+      'turn) and cache reuse efficiency drops. There is no price premium past 200k on current ' +
+      'models — the token volume itself is the cost, and it drains the 5H/7D caps faster.',
     explainKo:
-      '컨텍스트가 200k(또는 1M)에 가까워질수록 매 턴 비용이 높아지고 캐시 재사용 효율이 떨어집니다. ' +
-      '200k를 넘으면 장기 컨텍스트 요금이 적용됩니다.',
+      '컨텍스트가 커질수록 매 턴 비용이 높아지고(전체 컨텍스트를 매 턴 다시 읽음) 캐시 재사용 효율이 ' +
+      '떨어집니다. 현재 모델은 200k 초과 프리미엄이 없습니다 — 토큰량 자체가 비용이며 5H/7D 한도도 ' +
+      '더 빠르게 소모됩니다.',
     actions: () => [
       {
         label: '/compact at the next natural break',
@@ -435,8 +443,8 @@ export const ISSUE_MESSAGES = {
  */
 export const ISSUE_TIPS = {
   LARGE_INPUT_PER_REQUEST: {
-    en: 'Check `/effort` — `xhigh` is the #1 cap killer; switch to `/effort medium` (or `low`); disable 1M context; `/compact` when context grows',
-    ko: '`/effort` 확인 — `xhigh`가 캡 소진 1순위 원인, `medium`(또는 `low`)으로 복귀; 1M 컨텍스트 끄기; 컨텍스트 커지면 `/compact`',
+    en: '`/compact` or `/clear` — big contexts re-bill every turn and burn the 5H/7D caps; check `/effort` (`xhigh` is the #1 cap killer)',
+    ko: '`/compact` 또는 `/clear` — 큰 컨텍스트는 매 턴 재과금되고 5H/7D 한도를 태움; `/effort` 확인 (`xhigh`가 캡 소진 1순위)',
   },
   LOW_HIT_RATE: {
     en: 'Continue with `claude --continue`; keep CLAUDE.md trim — every line ships every turn',
@@ -463,8 +471,8 @@ export const ISSUE_TIPS = {
     ko: '지금 바로 아무 프롬프트나 보내 TTL 타이머 리셋; 또는 자리 비우기 전 `/compact` (Pro = 5분, Max = 1시간)',
   },
   CONTEXT_NEAR_LIMIT: {
-    en: '`/compact` before hitting the limit; `/clear` + re-attach only needed files; disable 1M: `export CLAUDE_MODEL_CONTEXT=200000`',
-    ko: '한계 도달 전 `/compact`; `/clear` 후 필요한 파일만 재첨부; 1M 끄기: `export CLAUDE_MODEL_CONTEXT=200000`',
+    en: '`/compact` before hitting the limit; `/clear` + re-attach only needed files',
+    ko: '한계 도달 전 `/compact`; `/clear` 후 필요한 파일만 재첨부',
   },
 };
 
@@ -474,6 +482,9 @@ export const ISSUE_TIPS = {
  * need a fallback so history.js can still surface the right tip.
  */
 export const CHIP_TO_CODES = {
+  '⚠ Ctx 200k+': ['LARGE_INPUT_PER_REQUEST'],
+  // Legacy chip name (pre-v2.18) — kept so `last`/`history` can still resolve
+  // codes from history files written by older versions.
   '⚠ 1M ON': ['LARGE_INPUT_PER_REQUEST'],
   '⚠ Cache miss': ['LOW_HIT_RATE'],
   '⚠ Input spike': ['LARGE_INPUT_PER_REQUEST'],
@@ -502,7 +513,11 @@ export const CAP_TIPS = {
  * shown to a global audience.
  */
 export function chipForIssues(issues, contextWindow) {
-  if (contextWindow?.size === '1M') return '⚠ 1M ON';
+  // Fires on *actual usage* (a real request carried >210k input tokens), not
+  // on the model merely supporting 1M — current models are all 1M by default
+  // with no price premium, so "1M ON" stopped being a meaningful alarm. The
+  // meaningful signal is "your context genuinely exceeded 200k".
+  if (contextWindow?.size === '1M') return '⚠ Ctx 200k+';
   const codes = issues.map((i) => i.code);
   if (codes.includes('LARGE_INPUT_PER_REQUEST')) return '⚠ Input spike';
   if (codes.includes('BUCKET_5M_DOMINANT')) return '⚠ 5m TTL';

package/src/cost.js

@@ -8,7 +8,17 @@
  */
 
 const PRICING = {
-  // Opus 4.5+ (new pricing tier — includes 4.5, 4.6, 4.7, and future)
+  // Fable 5 / Mythos 5 — premium tier above Opus ($10/$50). Cache write
+  // rates follow the standard multipliers (1.25x input for 5m, 2x for 1h),
+  // cache read is 0.1x input.
+  'claude-fable-5': {
+    input: 10.0,
+    cacheWrite5m: 12.5,
+    cacheWrite1h: 20.0,
+    cacheRead: 1.0,
+    output: 50.0,
+  },
+  // Opus 4.5+ (new pricing tier — includes 4.5, 4.6, 4.7, 4.8, and future)
   'claude-opus-new': {
     input: 5.0,
     cacheWrite5m: 6.25,
@@ -66,6 +76,11 @@ function detectPricingTier(model) {
   if (!model) return 'claude-sonnet';
   const m = model.toLowerCase();
 
+  // Fable 5 / Mythos 5 — must be checked before the generic fallback:
+  // without this, 'claude-fable-5' fell through to the Sonnet tier and
+  // under-estimated costs ~3x ($3/$15 vs the real $10/$50).
+  if (m.includes('fable') || m.includes('mythos')) return 'claude-fable-5';
+
   if (m.includes('opus')) {
     // Opus 4.5, 4.6, 4.7, and future 5+ use the new reduced pricing.
     if (/opus[-_.]?4[-_.]?[5-9]\b/.test(m)) return 'claude-opus-new';

package/src/demo.js

@@ -26,6 +26,7 @@ const SCENARIOS = [
       savings: 2123,
       elapsedSec: 30,
       contextSize: '200k',
+      ctxUsedPct: 34,
       spikeChip: null,
       caps: HEALTHY_CAPS,
     },
@@ -98,14 +99,15 @@ const SCENARIOS = [
   },
   {
     name: 'ctx-1m',
-    label: '⚠ 1M context auto-on',
+    label: '⚠ Context past 200k',
     data: {
       hitRate: 0.78,
       pct1h: 0.92,
       savings: 1340,
       elapsedSec: 30,
       contextSize: '1M',
-      spikeChip: '⚠ 1M ON',
+      ctxUsedPct: 28, // 28% of 1M ≈ 280k actually in context
+      spikeChip: '⚠ Ctx 200k+',
       caps: HEALTHY_CAPS,
     },
   },
@@ -271,7 +273,7 @@ export function buildTableDemoData(options = {}) {
     spikeReport: { spikes, baseline: { p95: 940_000 } },
     contextWindow: { size: '1M', maxContext: 280_000 },
     lastActivity: Date.now() - 60 * 1000,
-    spikeChip: '⚠ 1M ON',
+    spikeChip: '⚠ Ctx 200k+',
   };
 }
 
@@ -301,7 +303,7 @@ export function buildScenarioData(scenarioName, options) {
     if (!scenario) return null;
   }
 
-  const { hitRate, pct1h, pct5m, savings, elapsedSec, contextSize, spikeChip, caps } = scenario.data;
+  const { hitRate, pct1h, pct5m, savings, elapsedSec, contextSize, ctxUsedPct, spikeChip, caps } = scenario.data;
   return {
     summary: { hitRate },
     ttl: { pct1h, pct5m: pct5m ?? (1 - pct1h) },
@@ -314,6 +316,11 @@ export function buildScenarioData(scenarioName, options) {
     },
     lastActivity: Date.now() - elapsedSec * 1000,
     contextWindow: { size: contextSize },
+    // Live fill level (`📦 68%`) — scenarios that set ctxUsedPct exercise the
+    // stdin-driven segment; the rest fall back to the size-based chip.
+    ctxLive: ctxUsedPct != null
+      ? { usedPct: ctxUsedPct, size: contextSize === '1M' ? 1_000_000 : 200_000 }
+      : undefined,
     spikeChip,
     caps: buildCapsShape(caps),
     model: DEFAULT_MODEL,

package/src/formatters/statusline.js

@@ -214,7 +214,7 @@ export function formatNoSession({ caps = null, model = null, windowLabel = '' }
  * @param {string[]|null} [opts.segments] - whitelist of segments to render. Names: cap-warn, spike, harness, model, hit, ttl, saved, ctx, period, plus per-window keys (`five_hour`, `seven_day`, …). `5h`/`7d` are kept as aliases for back-compat. Null/undefined = all.
  */
 export function formatReport(data, { color = true, verbose = false, timer = true, mode = 'text', segments = null } = {}) {
-  const { summary, ttl, cost, options, lastActivity, contextWindow, spikeChip, caps, model } = data;
+  const { summary, ttl, cost, options, lastActivity, contextWindow, ctxLive, spikeChip, caps, model } = data;
   const { hitRate } = summary;
 
   // Hit rate → color signal
@@ -321,15 +321,36 @@ export function formatReport(data, { color = true, verbose = false, timer = true
     }
   }
 
-  // Context window chip (e.g. "📦 1M" or "📦 200k"). 1M gets a warning color
-  // because it's the expensive default on Max plans after Opus 4.7.
+  // Context chip. Two data sources, best first:
+  //
+  //  1. Live fill level from Claude Code's stdin (`context_window.used_percentage`)
+  //     — the current session's actual usage, refreshed every render. Rendered
+  //     as `📦 68%` and colored by fill (green <70, yellow 70–89, red 90+),
+  //     matching the cap-segment tone scale.
+  //  2. Fallback (table view / older Claude Code): transcript-inferred window
+  //     size. Note the semantics: `size === '1M'` means a real request already
+  //     carried >210k input tokens — actual heavy usage, not just the model
+  //     supporting 1M. Current models are all 1M by default with no price
+  //     premium, so this renders yellow ("your context is genuinely big"),
+  //     not red ("expensive mode on") like it used to.
   let ctxSeg = null;
-  if (contextWindow && contextWindow.size && contextWindow.size !== 'unknown') {
+  if (ctxLive && Number.isFinite(ctxLive.usedPct)) {
+    const pct = Math.max(0, Math.round(ctxLive.usedPct));
+    const tone = pct >= 90 ? RED : pct >= 70 ? YELLOW : GREEN;
+    const sizeLabel = ctxLive.size
+      ? (ctxLive.size >= 900_000 ? '1M' : `${Math.round(ctxLive.size / 1000)}k`)
+      : null;
+    const longLabel = sizeLabel ? `${pct}% of ${sizeLabel}` : `${pct}%`;
+    if (isIcon && verbose) {
+      ctxSeg = `${c(tone)}📦 Ctx ${longLabel}${c(RESET)}`;
+    } else if (isIcon) {
+      ctxSeg = `${c(tone)}📦 ${pct}%${c(RESET)}`;
+    } else {
+      ctxSeg = `${c(tone)}Ctx ${longLabel}${c(RESET)}`;
+    }
+  } else if (contextWindow && contextWindow.size && contextWindow.size !== 'unknown') {
     const label = contextWindow.size === '1M' ? '1M' : '200k';
-    const ctxColor = contextWindow.size === '1M' ? RED : GREEN;
-    // `Ctx` (not the full word `Context`) across every mode — the icon already
-    // tells the eye what the chip is, and the short form fits the same cadence
-    // as `Hit`/`Saved` peers when we eventually shorten those too.
+    const ctxColor = contextWindow.size === '1M' ? YELLOW : GREEN;
     if (isIcon && verbose) {
       ctxSeg = `${c(ctxColor)}📦 Ctx ${label}${c(RESET)}`;
     } else if (isIcon) {

package/src/formatters/table.js

@@ -86,7 +86,7 @@ function renderSpikeSection(spikes, contextWindow) {
   lines.push(r(`  ${'─'.repeat(50)}`));
   if (contextWindow && contextWindow.size === '1M') {
     lines.push(
-      r(`  Context mode: 1M  (max recent single-request input ${formatContextSize(contextWindow.maxContext)} tokens)`),
+      r(`  Context usage exceeded 200k  (max recent single-request input ${formatContextSize(contextWindow.maxContext)} tokens)`),
     );
     lines.push('');
   }
@@ -197,7 +197,7 @@ export function formatReport({ summary: sum, trend, ttl, anomalies, cost, option
   if (contextWindow && contextWindow.size !== 'unknown') {
     const note =
       contextWindow.size === '1M'
-        ? '⚠ 1M context active (Opus 4.7+ Max default). Disable with CLAUDE_CODE_DISABLE_1M_CONTEXT=1'
+        ? '⚠ Context exceeded 200k in recent requests — big contexts re-bill every turn and drain the 5H/7D caps. Use /compact or /clear.'
         : '✓ 200k context (standard)';
     lines.push(`  Context window: ${contextWindow.size}  ${note}`);
     lines.push(`  (max recent single-request input ${formatContextSize(contextWindow.maxContext)} tokens)`);

package/src/history.js

@@ -69,7 +69,8 @@ function saveState(state) {
 function chipKo(chip) {
   if (!chip) return chip;
   const map = {
-    '⚠ 1M ON': '⚠ 1M 컨텍스트 활성',
+    '⚠ Ctx 200k+': '⚠ 컨텍스트 200k 초과',
+    '⚠ 1M ON': '⚠ 1M 컨텍스트 활성', // legacy (pre-v2.18)
     '⚠ Cache miss': '⚠ 캐시 미스',
     '⚠ Rebuild churn': '⚠ 캐시 재빌드 빈발',
     '⚠ Input spike': '⚠ 입력 급증',
@@ -92,6 +93,9 @@ function chipKo(chip) {
  */
 function detailKo(detail) {
   if (!detail) return detail;
+  const m0 = detail.match(/^Single-request context exceeded 200k \(max (\d+)k tokens\)$/);
+  if (m0) return `단일 요청 컨텍스트 200k 초과 (최대 ${m0[1]}k 토큰)`;
+  // legacy detail shape (pre-v2.18)
   const m1 = detail.match(/^Context auto-promoted to 1M \(max single-request (\d+)k tokens\)$/);
   if (m1) return `1M 컨텍스트 자동 활성 (단일 요청 최대 ${m1[1]}k 토큰)`;
   const m2 = detail.match(/^session ([^:]+): (.+)$/);