@alexeiled/claude-router 1.19.2 → 1.20.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "router",
3
3
  "displayName": "Router",
4
- "version": "1.19.2",
4
+ "version": "1.20.0",
5
5
  "description": "Native model and effort routing within your provider. Anthropic, DeepSeek, z.ai, MiniMax, MiMo and Kimi defaults, custom provider profiles, classifier advice and one model per subagent.",
6
6
  "author": {
7
7
  "name": "Alexei Ledenev",
package/CHANGELOG.md CHANGED
@@ -1,5 +1,16 @@
1
1
  # Changelog
2
2
 
3
+ ## 1.20.0 (2026-11-03)
4
+
5
+ ### Changed
6
+
7
+ - Keep plan and credits apart when a profile mixes them, such as model-proxy with Opus and DeepSeek. The band, `/router`, the Now tab and Usage give each billing its own difference against your model, `routing credits +$4.10 · plan −$50.00 vs Opus 5.5 · medium`, instead of one sum that added plan quota to paid credits. The ledger becomes a per-billing table; cross-billing parts, `vs yours` cells and findings are left out. Single-billing profiles read as before.
8
+ - Document how the model-proxy launch model sets both the fallback and the comparison, and which tier each launch model starts at.
9
+
10
+ ### Upgrade
11
+
12
+ Restart Claude Code after updating. No router-file or record changes are needed: existing records split by the billing of the models they name.
13
+
3
14
  ## 1.19.2 (2026-11-01)
4
15
 
5
16
  ### Added
@@ -58,6 +58,7 @@ New provider sources: [MiniMax pricing](https://platform.minimax.io/docs/pricing
58
58
  [MiMo pricing](https://mimo.mi.com/docs/en-US/pricing), and [Kimi pricing](https://platform.kimi.ai/docs/pricing/chat).
59
59
  All non-Anthropic built-in presets use `billing: "credits"`.
60
60
  For an included-plan model, set `billing: "plan"` to disable the cold-input cash cap.
61
+ When a profile mixes plan and credits models, Usage gives each billing its own difference instead of one sum; see [plan and credits apart](user-guide.md#plan-and-credits-apart).
61
62
  A provider name or URL does not establish its billing product.
62
63
 
63
64
  ### Provider cache behavior
package/docs/providers.md CHANGED
@@ -214,7 +214,8 @@ Claude Code sends every request to one local `claude-proxy` endpoint. The proxy
214
214
 
215
215
  1. Install and configure [claude-proxy](https://github.com/alexei-led/claude-proxy/blob/main/docs/integration.md).
216
216
  2. Save the following complete profile as `model-proxy-router.json` in the selected Claude Code configuration directory.
217
- 3. Start the proxy manually, then use its `connect` command from v0.1.3 or newer.
217
+ 3. Start the proxy manually, then use its `connect` command from v0.1.4 or newer.
218
+ Older proxies forward Claude Code's built-in Artifact tool schema unchanged, and DeepSeek rejects its `pattern` regex with `400 Invalid schema for function 'Artifact'`.
218
219
 
219
220
  ```json
220
221
  {
@@ -287,14 +288,39 @@ The default classifier is Jev and needs its existing plugin credential. Select a
287
288
  claude-proxy --config /path/to/proxy.json
288
289
 
289
290
  # Terminal 2: preserve that account's existing CLAUDE_CONFIG_DIR
290
- claude-proxy connect --config /path/to/proxy.json -- claude --model 'deepseek-flash[1m]'
291
+ CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1 CLAUDE_CODE_ATTRIBUTION_HEADER=0 ENABLE_TOOL_SEARCH=false \
292
+ claude-proxy connect --config /path/to/proxy.json -- claude --model 'deepseek-flash[1m]'
291
293
  ```
292
294
 
295
+ Any turn may reach DeepSeek, so set the same Claude Code flags a direct DeepSeek session needs:
296
+
297
+ | Variable | Why |
298
+ | --- | --- |
299
+ | `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` | Drops beta request fields that third-party endpoints reject. Opus turns lose those betas too. |
300
+ | `CLAUDE_CODE_ATTRIBUTION_HEADER=0` | Omits the per-version attribution block, so the system prompt stays cacheable upstream. |
301
+ | `ENABLE_TOOL_SEARCH=false` | Tool search sends `tool_definition` blocks; DeepSeek answers `422 unknown variant`. |
302
+
293
303
  `connect` supplies `CLAUDE_ROUTER_PROVIDER=model-proxy`, the local URL and the separate local access header only to the child process.
294
304
  It does not change saved OAuth, configure provider keys, start the proxy, or install this Mod.
295
305
  Without the helper, the proxy guide documents equivalent process-local environment setup.
296
306
  Endpoint and credential fields do not belong in this router JSON.
297
307
 
308
+ ### Choose the launch model
309
+
310
+ The `--model` you launch with is your model, as in any profile. It serves the turns routing does not choose, and Usage compares the routed replies against it.
311
+ Launch on the model you would otherwise use:
312
+
313
+ | Launch model | Routing starts | Usage compares with |
314
+ | --- | --- | --- |
315
+ | `deepseek-flash[1m]` | at `low`, on DeepSeek | DeepSeek: Opus turns show as plan quota spent and credits saved |
316
+ | `claude-opus-5-5` | at `high`, on Opus, until the classifier supports a cheaper tier | Opus: DeepSeek turns show as credits spent and plan quota saved |
317
+
318
+ A launch model must be a model that some route runs. On any other model, a fresh session starts with routing off.
319
+ To start on another Claude model, such as Sonnet, add it to `models`, put it on a route, and map it in the proxy configuration.
320
+
321
+ Opus is billed by the plan and DeepSeek in credits, so Usage keeps the two apart: `routing credits +$4.10 · plan −$50.00 vs Opus 5.5 · medium`.
322
+ See [plan and credits apart](user-guide.md#plan-and-credits-apart).
323
+
298
324
  Open `/router` and check the selected file, classifier health and routing state before use.
299
325
  The catalog must contain the bare native IDs; `[1m]` is client metadata, not a proxy alias.
300
326
  Every selected provider receives the unchanged history. Approve each destination; do not mix company context into an unapproved provider.
@@ -124,6 +124,12 @@ When the whole period is comparable, the answer comes first, in the band's words
124
124
  | + Cache rebuilds | What rewriting the prompt cache after a model switch cost, and its share of the saving. |
125
125
  | = Routed | What the routed replies cost, with a bar against your model: `54% of your model`, or `×2.1`. |
126
126
 
127
+ #### Plan and credits apart
128
+
129
+ A profile can mix models billed by a Claude plan (`billing: "plan"`) with models billed in credits (`billing: "credits"`), such as the [model-proxy profile](providers.md#mix-anthropic-and-deepseek-with-model-proxy). Plan dollars stand for quota; credits are paid. When the replies ran on, or are compared with, models of both billings, every readout gives each billing its own difference instead of one sum: `routing credits +$4.10 · plan −$50.00 vs Opus 5.5 · medium`. Here routing spent $4.10 of credits on DeepSeek and saved $50.00 of Opus quota at list prices. The ledger becomes a table of routed cost, your model's cost and the difference per billing. The cheaper, stronger and cache-rebuild parts are left out, because each would subtract quota from cash. In **BY**, a row whose models are not billed as your model is names its billing (`credits`, `plan` or `both`) in place of `vs yours`. **What if** names it the same way, and **WORTH A LOOK** keeps only the share of the cost.
130
+
131
+ A model's billing comes from the selected profile, or from a built-in profile when the selected file does not list that model. If your models themselves span both billings in the period, for example after `/model` moved between Opus and DeepSeek, there is no single model to compare with. The readout then shows what each billing cost: `observed credits $4.10 · plan $20.00 · your models mix plan and credits`. A model that no profile prices, and **All** with totals from before dated records, keep the single sum.
132
+
127
133
  A line of counts follows: replies, turns, input tokens, the share of the input read from the cache, and output tokens. With routing off or unavailable and no routed reply this session, the tab says the replies use your model and are not counted.
128
134
 
129
135
  **BY** splits the period's cost by **Activity**, **Model** or **Tier**. Press `g` for the next grouping. Each row gives the replies, the routed cost and `vs yours`, the difference against your model. The last column is the route most of the row's replies used, or, by model, the row's share of the cost. Select **▸** to open a row. An activity lists its routes, and a model or a tier lists its activities. A line under them gives the row's cheaper, stronger and switch parts and its tokens. A narrow pane drops the last column first.
package/lib/band.mjs CHANGED
@@ -1,6 +1,8 @@
1
1
  import { activeClassifier, TIERS } from './config.mjs';
2
2
  import {
3
3
  activityVerb,
4
+ answerSegments,
5
+ billingSplit,
4
6
  classifierLabel,
5
7
  classifierStatus,
6
8
  classifierWarns,
@@ -14,11 +16,11 @@ import {
14
16
  percentPair,
15
17
  reasonActivity,
16
18
  routeLabel,
17
- routingAnswer,
18
19
  routingModeText,
19
20
  savingsColor,
20
21
  sessionUsage,
21
22
  shortReason,
23
+ splitCompared,
22
24
  TIER_COLOR,
23
25
  unavailableReason,
24
26
  usageMetrics,
@@ -221,9 +223,10 @@ export function sessionRow(config, view, columns, now = Date.now()) {
221
223
  const label = part('session ', { dimColor: true });
222
224
  const summary = sessionUsage(view, now);
223
225
  const r = readout(summary);
226
+ const split = billingSplit(config, summary);
224
227
  if (summary.observed.uncomparedReplies)
225
228
  return fitSegments(
226
- [segment(0, label, part(observedUsageText(summary.observed), { dimColor: true }))],
229
+ [segment(0, label, part(observedUsageText(summary.observed, split), { dimColor: true }))],
227
230
  columns,
228
231
  ).flatMap((s) => s.parts);
229
232
  if (!modelSpec(config, view.nativeModel))
@@ -232,9 +235,9 @@ export function sessionRow(config, view, columns, now = Date.now()) {
232
235
  const count = `${r.replies} repl${r.replies === 1 ? 'y' : 'ies'}`;
233
236
  const answer = [
234
237
  label,
235
- part(routingAnswer(r), { color: savingsColor(r.differenceUsd), bold: true }),
236
- part(` vs ${comparedModel(config, view, summary)}`),
237
- ];
238
+ ...answerSegments(r, split).map(({ text, value }) => part(text, { color: savingsColor(value), bold: true })),
239
+ split && !splitCompared(split) ? null : part(` vs ${comparedModel(config, view, summary)}`),
240
+ ].filter(Boolean);
238
241
  const width = (row) => row.reduce((n, p) => n + p.text.length, 0);
239
242
  const fit = (rows) =>
240
243
  fitSegments(
@@ -244,6 +247,8 @@ export function sessionRow(config, view, columns, now = Date.now()) {
244
247
  // Below EARLY_REPLIES one switch decides the sum, so the parts wait, as on the pane.
245
248
  if (r.early) return fit([[...answer, part(`${SEPARATOR}${count} · early sample`, { dimColor: true })], answer]);
246
249
  const replies = part(`${SEPARATOR}${count}`, { dimColor: true });
250
+ // Per billing the parts would subtract quota from cash: a split shows its two differences alone.
251
+ if (split) return fit([[...answer, replies], answer]);
247
252
  const parts = costParts(r);
248
253
  const named = parts.flatMap(([amount, words, value], i) => [
249
254
  part(i ? ' ' : ' = ', { dimColor: true }),
package/lib/display.mjs CHANGED
@@ -3,6 +3,7 @@ import { readMetrics, readStore, storeSummary, UNPRICED_CAUSES } from './activit
3
3
  import {
4
4
  activeClassifier,
5
5
  CLASSIFIER_OPTIONS,
6
+ DEFAULTS,
6
7
  endpointSettings,
7
8
  resolveRoute,
8
9
  routeSpec,
@@ -12,9 +13,10 @@ import {
12
13
  import { ratesAt } from './cost.mjs';
13
14
  import { applyMode, modeLabel, modeRoute } from './modes.mjs';
14
15
  import { PROBE_RESULTS } from './probe-results.mjs';
16
+ import { PROVIDER_DEFAULTS } from './providers.mjs';
15
17
  import { cellForModel } from './route.mjs';
16
18
  import { modelSpec, readout } from './savings.mjs';
17
- import { allTime, periodRange, readUsage, summarize, withReplies } from './usage.mjs';
19
+ import { allTime, breakdown, periodRange, readUsage, summarize, withReplies } from './usage.mjs';
18
20
 
19
21
  // Cost order, cheapest first, so the colors read as a scale. Hex values: every surface draws them.
20
22
  export const TIER_COLOR = { micro: '#5fd7af', low: '#5f9fe0', medium: '#d7af5f', high: '#e0708a' };
@@ -345,9 +347,87 @@ export const liveUsage = (view, record) => withReplies(readUsage(record), view.u
345
347
  // This session's routed replies, the running turns' included.
346
348
  export const sessionUsage = (view, now) => summarize(liveUsage(view, view.usageSession), periodRange('session', now));
347
349
 
348
- // Observed spend is valid even when a counterfactual cache history cannot be priced.
349
- export const observedUsageText = (observed) =>
350
- `observed ${usd(observed.routedUsd)} · ${observed.replies} repl${observed.replies === 1 ? 'y' : 'ies'} · comparison unavailable`;
350
+ // Observed spend is valid even when a counterfactual cache history cannot be priced. With a billing split, each
351
+ // billing's spend: plan and credits are not added.
352
+ export const observedUsageText = (observed, split = null) =>
353
+ `observed ${split ? billingCosts(split, 'observedUsd') : usd(observed.routedUsd)} · ${observed.replies} repl${observed.replies === 1 ? 'y' : 'ies'} · comparison unavailable`;
354
+
355
+ // Plan and credits are different money: on a Claude plan the list-price dollars stand for quota, credits are paid.
356
+ export const BILLINGS = ['credits', 'plan'];
357
+ // The billing of the model an API id runs on: the selected profile's entry, else a built-in profile's, so a period
358
+ // that holds another profile's sessions still reads. Null for a model no profile prices.
359
+ const BUILT_IN_PROFILES = [DEFAULTS, ...Object.values(PROVIDER_DEFAULTS)];
360
+ export function billingOf(config, id) {
361
+ for (const profile of [config, ...BUILT_IN_PROFILES]) {
362
+ const spec = modelSpec(profile, id);
363
+ if (spec) return spec.billing;
364
+ }
365
+ return null;
366
+ }
367
+ const wholeCents = (value) => Math.round(value * 100) / 100;
368
+
369
+ // A summary told per billing when its replies ran on, or are compared with, both plan and credits models: one sum
370
+ // would add quota to cash. `yours` is your model's billing; per billing, in whole cents: `observedUsd` what every
371
+ // reply cost, `routedUsd` what the compared replies cost, and `yoursUsd` your model's cost for them, all of it in your
372
+ // model's billing. `yours` and `yoursUsd` are null when your models themselves span both billings: a record keeps
373
+ // which model was yours, not each reply's cost on it. Null when one billing covers every model, or some model has no
374
+ // known billing: the one-sum readout stands then.
375
+ export function billingSplit(config, summary) {
376
+ const seen = new Set();
377
+ const costs = (cells) => {
378
+ const out = { credits: 0, plan: 0 };
379
+ for (const { name, sums } of breakdown(cells, 'model')) {
380
+ const billing = billingOf(config, name);
381
+ if (!billing) return null;
382
+ seen.add(billing);
383
+ out[billing] += sums[1];
384
+ }
385
+ return out;
386
+ };
387
+ const observed = costs(summary.observed.cells);
388
+ const routed = costs(summary.cells);
389
+ const yours = new Set(Object.keys(summary.yours).map((id) => billingOf(config, id)));
390
+ if (!observed || !routed || yours.has(null)) return null;
391
+ for (const billing of yours) seen.add(billing);
392
+ if (seen.size < 2) return null;
393
+ const mine = yours.size === 1 ? [...yours][0] : null;
394
+ const side = (billing) => ({
395
+ observedUsd: wholeCents(observed[billing]),
396
+ routedUsd: wholeCents(routed[billing]),
397
+ yoursUsd: mine === null ? null : billing === mine ? wholeCents(summary.yoursUsd) : 0,
398
+ });
399
+ return { yours: mine, credits: side('credits'), plan: side('plan') };
400
+ }
401
+ // The split of every reply kept across sessions (allTime). Limit: the undated totals from before the usage records
402
+ // name no models, so while they hold replies the one sum stands.
403
+ export const keptSplit = (config, kept) => (kept.legacy.replies ? null : billingSplit(config, kept.summary));
404
+
405
+ // "credits $4.10 · plan $20.00": each billing's `key` sum.
406
+ const billingCosts = (split, key) => BILLINGS.map((billing) => `${billing} ${usd(split[billing][key])}`).join(' · ');
407
+ // Routing against your model in one billing, in whole cents: minus is less than your model.
408
+ export const billingDifference = (side) => wholeCents(side.routedUsd - side.yoursUsd);
409
+ // Every compared reply of the split is priced against models of one billing.
410
+ export const splitCompared = (split) => split.yours !== null;
411
+
412
+ // The answer as text parts, each with the signed amount that colors it (null: plain): one sum, "routing −$1.84
413
+ // (−22%)"; per billing, "routing credits +$4.10 · plan −$61.20"; or, when your models span both billings, what each
414
+ // billing cost, "observed credits $4.10 · plan $20.00 · your models mix plan and credits".
415
+ export function answerSegments(r, split) {
416
+ if (!split) return [{ text: routingAnswer(r), value: r.differenceUsd }];
417
+ if (!splitCompared(split))
418
+ return [{ text: `observed ${billingCosts(split, 'routedUsd')} · your models mix plan and credits`, value: null }];
419
+ return [
420
+ { text: 'routing ', value: null },
421
+ ...BILLINGS.flatMap((billing, i) => {
422
+ const value = billingDifference(split[billing]);
423
+ return [...(i ? [{ text: ' · ', value: null }] : []), { text: `${billing} ${signedUsd(value)}`, value }];
424
+ }),
425
+ ];
426
+ }
427
+ export const answerText = (r, split) =>
428
+ answerSegments(r, split)
429
+ .map((segment) => segment.text)
430
+ .join('');
351
431
 
352
432
  // The models a session's replies were priced against, when they are not the one `/model` selects now: after a
353
433
  // `/model` change the record keeps each reply against the model selected when it ran. Null when they are.
@@ -382,23 +462,26 @@ export const switchesLost = (r) => r.switchUsd > 0 && r.switchUsd > -r.cheaperUs
382
462
  export function savingsLine(config, view, now) {
383
463
  const summary = sessionUsage(view, now);
384
464
  const session = readout(summary);
465
+ const split = billingSplit(config, summary);
385
466
  if (summary.observed.uncomparedReplies)
386
- return `Session: ${observedUsageText(summary.observed)}${session.replies ? `; ${replyCount(session.replies)} comparable only: ${routingAnswer(session)}` : ''}, est. at list prices`;
467
+ return `Session: ${observedUsageText(summary.observed, split)}${session.replies ? `; ${replyCount(session.replies)} comparable only: ${answerText(session, split)}` : ''}, est. at list prices`;
387
468
  const label = `vs ${comparedModel(config, view, summary)}`;
388
469
  if (!session.replies) {
389
470
  const kept = allTime(view.usageStore, view.savingsStore);
390
471
  const across = readout(kept.totals);
472
+ const keptBy = keptSplit(config, kept);
391
473
  if (kept.observed.uncomparedReplies)
392
- return `Session ${label}: no routed replies yet; across sessions ${observedUsageText(kept.observed)}, est. at list prices`;
474
+ return `Session ${label}: no routed replies yet; across sessions ${observedUsageText(kept.observed, keptBy)}, est. at list prices`;
393
475
  const saved = across.early
394
476
  ? ''
395
- : `; ${routingAnswer(across)} since ${sinceDate(kept.since)}, each session against its own model`;
477
+ : `; ${answerText(across, keptBy)} since ${sinceDate(kept.since)}, each session against its own model`;
396
478
  return `Session ${label}: no routed replies yet${saved}`;
397
479
  }
398
- if (session.early)
399
- return `Session: ${routingAnswer(session)} ${label}, ${replyCount(session.replies)}, early sample, est. at list prices`;
400
- const parts = costParts(session).map(([amount, words]) => `${amount} ${words}`);
401
- return `Session: ${routingAnswer(session)} ${label}${parts.length ? ` = ${parts.join(' ')}` : ''}, ${replyCount(session.replies)}, est. at list prices`;
480
+ // Per billing the parts would subtract quota from cash, so a split says its two differences alone.
481
+ const answer = split && !splitCompared(split) ? answerText(session, split) : `${answerText(session, split)} ${label}`;
482
+ if (session.early) return `Session: ${answer}, ${replyCount(session.replies)}, early sample, est. at list prices`;
483
+ const parts = split ? [] : costParts(session).map(([amount, words]) => `${amount} ${words}`);
484
+ return `Session: ${answer}${parts.length ? ` = ${parts.join(' ')}` : ''}, ${replyCount(session.replies)}, est. at list prices`;
402
485
  }
403
486
 
404
487
  export const GATEWAY_SETTINGS = 'v0.8 gateway settings remain · see /router';
package/lib/panel.mjs CHANGED
@@ -18,6 +18,12 @@ import { effortSharesCache, routeEffort } from './cost.mjs';
18
18
  import {
19
19
  activityReading,
20
20
  activityVerb,
21
+ answerSegments,
22
+ answerText,
23
+ BILLINGS,
24
+ billingDifference,
25
+ billingOf,
26
+ billingSplit,
21
27
  COST_PART,
22
28
  classifierLabel,
23
29
  classifierStatus,
@@ -25,6 +31,7 @@ import {
25
31
  formatTokens,
26
32
  GATEWAY_CLEANUP,
27
33
  GATEWAY_SETTINGS,
34
+ keptSplit,
28
35
  liveUsage,
29
36
  missingCredentials,
30
37
  missingText,
@@ -37,7 +44,6 @@ import {
37
44
  recordedModels,
38
45
  routeLabel,
39
46
  routeName,
40
- routingAnswer,
41
47
  routingModeOf,
42
48
  routingModeText,
43
49
  savingsColor,
@@ -45,6 +51,7 @@ import {
45
51
  shownConfig,
46
52
  signedUsd,
47
53
  sparkline,
54
+ splitCompared,
48
55
  switchesLost,
49
56
  TIER_COLOR,
50
57
  unavailableReason,
@@ -352,10 +359,10 @@ function nowTab(ui, config, view, usage, actions, _modelOptions, columns, now) {
352
359
  // Today repeats this session's part of it until another session adds to it.
353
360
  const ownToday = summarize(liveUsage(view, view.usageSession), periodRange('today', now));
354
361
  if (today.observed.replies > ownToday.observed.replies)
355
- out.push(ui.text(' '), ...todayLines(ui, today, actions, columns));
362
+ out.push(ui.text(' '), ...todayLines(ui, config, today, actions, columns));
356
363
  out.push(
357
364
  ...sessionAgentLines(ui, view, actions, columns),
358
- ...worthLines(ui, today, actions, columns),
365
+ ...worthLines(ui, config, today, actions, columns),
359
366
  ui.text(' '),
360
367
  ui.gauge('Context ', metrics.contextBar, contextSuffix(metrics)),
361
368
  ui.line(
@@ -500,11 +507,12 @@ function sessionLines(ui, config, view, summary, actions, columns, now) {
500
507
  if (!strip && !summary.observed.replies) return [ui.line(ui.head('SESSION'), ui.dim(' · no replies yet'))];
501
508
  const out = [ui.line(ui.head('SESSION'), head.length ? ui.dim(` · ${head.join(' · ')}`) : null)];
502
509
  // The band's session row, then the parts that add up to it.
510
+ const split = billingSplit(config, summary);
503
511
  if (summary.observed.uncomparedReplies) {
504
512
  out.push(
505
513
  ui.line(
506
514
  ' ',
507
- ui.text(observedUsageText(summary.observed)),
515
+ ui.text(observedUsageText(summary.observed, split)),
508
516
  ' ',
509
517
  ui.Button({ key: 'usage-session', label: 'Usage', onPress: () => actions.usageFor('session') }),
510
518
  ),
@@ -512,11 +520,23 @@ function sessionLines(ui, config, view, summary, actions, columns, now) {
512
520
  } else if (summary.replies) {
513
521
  const r = readout(summary);
514
522
  out.push(
515
- answerLine(ui, r, comparedModel(config, view, summary), () => actions.usageFor('session'), 'session', columns),
523
+ answerLine(
524
+ ui,
525
+ r,
526
+ split,
527
+ comparedModel(config, view, summary),
528
+ () => actions.usageFor('session'),
529
+ 'session',
530
+ columns,
531
+ ),
516
532
  );
517
533
  if (!r.early)
518
- out.push(...ledger(ui, config, view, { period: 'session', r, summary, legacy: null, columns, compact: true }));
519
- if (!r.early && switchesLost(r)) out.push(lostLine(ui, actions));
534
+ out.push(
535
+ ...(split
536
+ ? billingLedger(ui, split)
537
+ : ledger(ui, config, view, { period: 'session', r, summary, legacy: null, columns, compact: true })),
538
+ );
539
+ if (!r.early && !split && switchesLost(r)) out.push(lostLine(ui, actions));
520
540
  }
521
541
  if (strip) {
522
542
  out.push(
@@ -579,12 +599,12 @@ function lastSwitchLine(ui, last, now) {
579
599
 
580
600
  // Routing against your model in the band's words, "routing −$1.84 (−22%) vs Opus 5.5 · xhigh", with the Usage tab on
581
601
  // the same period one press away; an early sample says so.
582
- function answerLine(ui, r, against, open, period, columns) {
602
+ function answerLine(ui, r, split, against, open, period, columns) {
583
603
  const early = ' · early sample';
584
- const width = 2 + routingAnswer(r).length + ` vs ${against}`.length + early.length + USAGE_LINK;
604
+ const width = 2 + answerText(r, split).length + ` vs ${against}`.length + early.length + USAGE_LINK;
585
605
  return ui.line(
586
606
  ' ',
587
- ...answerParts(ui, r, against),
607
+ ...answerParts(ui, r, split, against),
588
608
  r.early && (!Number.isFinite(columns) || width <= columns) ? ui.dim(early) : null,
589
609
  ' ',
590
610
  ui.Button({ key: `usage-${period}`, label: 'Usage', onPress: open }),
@@ -600,8 +620,9 @@ const lostLine = (ui, actions) =>
600
620
  );
601
621
 
602
622
  // Today across sessions, shown once another session added to it.
603
- function todayLines(ui, summary, actions, columns) {
623
+ function todayLines(ui, config, summary, actions, columns) {
604
624
  const switches = summary.switches.tier + summary.switches.activity;
625
+ const split = billingSplit(config, summary);
605
626
  return [
606
627
  ui.line(
607
628
  ui.head('TODAY'),
@@ -611,17 +632,32 @@ function todayLines(ui, summary, actions, columns) {
611
632
  ),
612
633
  summary.observed.uncomparedReplies
613
634
  ? ui.line(
614
- ui.text(observedUsageText(summary.observed)),
635
+ ui.text(observedUsageText(summary.observed, split)),
615
636
  ' ',
616
637
  ui.Button({ key: 'usage-today', label: 'Usage', onPress: () => actions.usageFor('today') }),
617
638
  )
618
- : answerLine(ui, readout(summary), 'each session’s own model', () => actions.usageFor('today'), 'today', columns),
639
+ : answerLine(
640
+ ui,
641
+ readout(summary),
642
+ split,
643
+ 'each session’s own model',
644
+ () => actions.usageFor('today'),
645
+ 'today',
646
+ columns,
647
+ ),
619
648
  ];
620
649
  }
621
650
 
651
+ // The findings that hold within one billing: with plan and credits apart, a part against your model would subtract
652
+ // quota from cash, so only the share of the cost stays.
653
+ const billingInsights = (summary, split) => insights(summary).filter((insight) => !split || insight.kind === 'cost');
654
+
622
655
  // Today's first finding from Usage's WORTH A LOOK, with the tab that changes it; nothing when there is none.
623
- function worthLines(ui, summary, actions, columns) {
624
- const [first] = !summary.observed.uncomparedReplies && summary.replies >= INSIGHT_REPLIES ? insights(summary) : [];
656
+ function worthLines(ui, config, summary, actions, columns) {
657
+ const [first] =
658
+ !summary.observed.uncomparedReplies && summary.replies >= INSIGHT_REPLIES
659
+ ? billingInsights(summary, billingSplit(config, summary))
660
+ : [];
625
661
  if (!first) return [];
626
662
  return [ui.text(' '), ui.line(ui.head('WORTH A LOOK'), ui.dim(' · today')), insightLine(ui, first, actions, columns)];
627
663
  }
@@ -1725,10 +1761,10 @@ function scopeLine(ui, config, view, period, summary, now) {
1725
1761
  }
1726
1762
 
1727
1763
  // The answer first, in the band's words: "routing −$1.84 (−22%) vs Opus 5.5 · xhigh", or why there is nothing to compare.
1728
- function headline(ui, config, view, period, r, summary, observed = summary.observed) {
1764
+ function headline(ui, config, view, period, r, summary, observed, split) {
1729
1765
  if (observed.uncomparedReplies)
1730
1766
  return [
1731
- ui.text(observedUsageText(observed), { bold: true }),
1767
+ ui.text(observedUsageText(observed, split), { bold: true }),
1732
1768
  ui.dim(
1733
1769
  `${observed.uncomparedReplies} of ${observed.replies} replies have no comparison; savings are not estimated for them.`,
1734
1770
  ),
@@ -1739,6 +1775,7 @@ function headline(ui, config, view, period, r, summary, observed = summary.obser
1739
1775
  ...answerParts(
1740
1776
  ui,
1741
1777
  r,
1778
+ split,
1742
1779
  period === 'session' ? comparedModel(config, view, summary) : 'each session’s own model',
1743
1780
  ),
1744
1781
  ),
@@ -1761,7 +1798,7 @@ function headline(ui, config, view, period, r, summary, observed = summary.obser
1761
1798
  const against = period === 'session' ? comparedModel(config, view, summary) : 'each session’s own model';
1762
1799
  return [
1763
1800
  ui.line(
1764
- ...answerParts(ui, r, against),
1801
+ ...answerParts(ui, r, split, against),
1765
1802
  r.early ? ui.text(` early sample · ${plural(r.replies, 'reply', 'replies')}`, { color: 'yellow' }) : null,
1766
1803
  ),
1767
1804
  ];
@@ -1769,10 +1806,39 @@ function headline(ui, config, view, period, r, summary, observed = summary.obser
1769
1806
 
1770
1807
  const capital = (words) => words[0].toUpperCase() + words.slice(1);
1771
1808
 
1772
- // "routing −$1.84 (−22%) vs Opus 5.5 · xhigh", the answer bold in the savings color, as the band says it.
1773
- function answerParts(ui, r, against) {
1774
- return [ui.text(routingAnswer(r), { bold: true, color: savingsColor(r.differenceUsd) }), ` vs ${against}`];
1809
+ // "routing −$1.84 (−22%) vs Opus 5.5 · xhigh", the answer bold in the savings color, as the band says it; per billing
1810
+ // each difference in its own color. A split without one billing for your models compares with nothing.
1811
+ function answerParts(ui, r, split, against) {
1812
+ return [
1813
+ ...answerSegments(r, split).map(({ text, value }) =>
1814
+ ui.text(text, { bold: true, ...(savingsColor(value) ? { color: savingsColor(value) } : {}) }),
1815
+ ),
1816
+ split && !splitCompared(split) ? null : ` vs ${against}`,
1817
+ ].filter(Boolean);
1818
+ }
1819
+
1820
+ // Per billing, what the replies cost, what your model would have, and the difference: plan dollars stand for quota
1821
+ // and credits are paid, so neither is added to the other. `note` says so under the table.
1822
+ function billingLedger(ui, split, note = false) {
1823
+ const amount = (value) => (value === null ? '—' : usd(value)).padStart(BILLING_AMOUNT);
1824
+ return [
1825
+ ui.dim(
1826
+ ` ${''.padEnd(LEDGER_LABEL)}${'routed'.padStart(LEDGER_AMOUNT)}${'your model'.padStart(BILLING_AMOUNT)}${'difference'.padStart(BILLING_AMOUNT)}`,
1827
+ ),
1828
+ ...BILLINGS.map((billing) => {
1829
+ const side = split[billing];
1830
+ return ui.line(
1831
+ ' ',
1832
+ ui.cell(LEDGER_LABEL, ui.text(capital(billing))),
1833
+ usd(side.routedUsd).padStart(LEDGER_AMOUNT),
1834
+ amount(side.yoursUsd),
1835
+ side.yoursUsd === null ? amount(null) : differenceText(ui, billingDifference(side), BILLING_AMOUNT),
1836
+ );
1837
+ }),
1838
+ ...(note ? [ui.dim(' at list prices; plan dollars stand for quota, credits are paid')] : []),
1839
+ ];
1775
1840
  }
1841
+ const BILLING_AMOUNT = 13;
1776
1842
 
1777
1843
  // Your model − cheaper models + stronger models + switch cache writes = routed, in whole cents that add up (readout).
1778
1844
  function ledger(ui, config, view, { period, r, summary, legacy, columns, compact = false }) {
@@ -1860,8 +1926,10 @@ const statsLine = (ui, s) =>
1860
1926
  );
1861
1927
 
1862
1928
  // The period's cost by activity, model or tier, most first; `g` presses the next grouping. A row opens to what it
1863
- // holds and its cost parts. A narrow pane drops "mostly on" (or the share) before any number.
1864
- function breakdownLines(ui, view, actions, summary, columns) {
1929
+ // holds and its cost parts. A narrow pane drops "mostly on" (or the share) before any number. With a billing split, a
1930
+ // row whose models are not all billed as your model is names its billing in place of `vs yours` and its parts: that
1931
+ // difference would subtract quota from cash.
1932
+ function breakdownLines(ui, config, view, actions, summary, columns, split) {
1865
1933
  const by = GROUPS.some(([id]) => id === view.usageGroup) ? view.usageGroup : 'activity';
1866
1934
  const next = GROUPS[(GROUPS.findIndex(([id]) => id === by) + 1) % GROUPS.length][0];
1867
1935
  const out = [
@@ -1891,14 +1959,24 @@ function breakdownLines(ui, view, actions, summary, columns) {
1891
1959
  ` ${''.padEnd(NAME)}${'replies'.padStart(8)}${'cost'.padStart(10)}${'vs yours'.padStart(11)}${tail ? ` ${tailHead}` : ''}`,
1892
1960
  ),
1893
1961
  );
1894
- const numbers = (sums, unavailable) => [
1895
- `${String(sums[0]).padStart(8)}${usd(sums[1]).padStart(10)}`,
1896
- unavailable ? ui.dim('—'.padStart(11)) : differenceText(ui, sums[1] - sums[2], 11),
1897
- ];
1962
+ const otherBilling = (rowCells) => {
1963
+ if (!split) return null;
1964
+ const billings = new Set(breakdown(rowCells, 'model').map(({ name }) => billingOf(config, name)));
1965
+ if (billings.size === 1 && billings.has(split.yours)) return null;
1966
+ return billings.size === 1 ? [...billings][0] : 'both';
1967
+ };
1968
+ const numbers = (sums, unavailable, rowCells) => {
1969
+ const other = unavailable ? null : otherBilling(rowCells);
1970
+ return [
1971
+ `${String(sums[0]).padStart(8)}${usd(sums[1]).padStart(10)}`,
1972
+ unavailable || other ? ui.dim((other ?? '—').padStart(11)) : differenceText(ui, sums[1] - sums[2], 11),
1973
+ ];
1974
+ };
1898
1975
  for (const group of groups) {
1899
1976
  const id = `${by}:${group.name}`;
1900
1977
  const open = view.usageOpen === id;
1901
- const route = by === 'model' ? null : mostlyOn(cellsWhere(cells, by, group.name));
1978
+ const groupCells = cellsWhere(cells, by, group.name);
1979
+ const route = by === 'model' ? null : mostlyOn(groupCells);
1902
1980
  out.push(
1903
1981
  ui.line(
1904
1982
  ' ',
@@ -1910,7 +1988,7 @@ function breakdownLines(ui, view, actions, summary, columns) {
1910
1988
  }),
1911
1989
  ' ',
1912
1990
  ui.cell(NAME, groupName(ui, by, group.name)),
1913
- ...numbers(group.sums, missing.has(group.name)),
1991
+ ...numbers(group.sums, missing.has(group.name), groupCells),
1914
1992
  !tail
1915
1993
  ? null
1916
1994
  : by === 'model'
@@ -1929,16 +2007,20 @@ function breakdownLines(ui, view, actions, summary, columns) {
1929
2007
  ...numbers(
1930
2008
  child.sums,
1931
2009
  missing.get(group.name)?.children.some((c) => c.name === child.name),
2010
+ cellsWhere(groupCells, CHILD_BY[by], child.name),
1932
2011
  ),
1933
2012
  ),
1934
2013
  );
1935
2014
  const [, , , cheaper, stronger, switched, input, , output] = group.sums;
2015
+ const tokens = `input ${formatTokens(input)} · output ${formatTokens(output)}`;
1936
2016
  out.push(
1937
2017
  ...dimLines(
1938
2018
  ui,
1939
2019
  missing.has(group.name)
1940
- ? ` comparison unavailable · input ${formatTokens(input)} · output ${formatTokens(output)}`
1941
- : ` cheaper ${signedUsd(cents(cheaper))} · stronger ${signedUsd(cents(stronger))} · switch ${signedUsd(cents(switched))} · input ${formatTokens(input)} · output ${formatTokens(output)}`,
2020
+ ? ` comparison unavailable · ${tokens}`
2021
+ : otherBilling(groupCells)
2022
+ ? ` ${tokens}`
2023
+ : ` cheaper ${signedUsd(cents(cheaper))} · stronger ${signedUsd(cents(stronger))} · switch ${signedUsd(cents(switched))} · ${tokens}`,
1942
2024
  columns,
1943
2025
  ),
1944
2026
  );
@@ -1947,8 +2029,9 @@ function breakdownLines(ui, view, actions, summary, columns) {
1947
2029
  }
1948
2030
 
1949
2031
  // What the period's tokens would cost on each model alone, as your model for every reply (compareModels), beside what
1950
- // routing spent and your own models; a model some reply had no price on is left out.
1951
- function compareLines(ui, summary) {
2032
+ // routing spent and your own models; a model some reply had no price on is left out. With a billing split, a model
2033
+ // billed otherwise than your model names its billing in place of the difference.
2034
+ function compareLines(ui, config, summary, split) {
1952
2035
  if (summary.observed.uncomparedReplies)
1953
2036
  return [ui.dim('What if unavailable: some replies have no comparable cache history.')];
1954
2037
  const yours = Object.keys(summary.yours);
@@ -1960,6 +2043,7 @@ function compareLines(ui, summary) {
1960
2043
  value,
1961
2044
  routed: false,
1962
2045
  yours: model === single,
2046
+ other: split && billingOf(config, model) !== split.yours ? billingOf(config, model) : null,
1963
2047
  }));
1964
2048
  if (!rows.some((row) => row.yours))
1965
2049
  rows.push({
@@ -1967,8 +2051,9 @@ function compareLines(ui, summary) {
1967
2051
  value: summary.yoursUsd,
1968
2052
  routed: false,
1969
2053
  yours: true,
2054
+ other: null,
1970
2055
  });
1971
- rows.push({ label: 'Routed', value: summary.routedUsd, routed: true, yours: false });
2056
+ rows.push({ label: 'Routed', value: summary.routedUsd, routed: true, yours: false, other: null });
1972
2057
  rows.sort((a, b) => a.value - b.value);
1973
2058
  const max = Math.max(...rows.map((row) => row.value));
1974
2059
  return [
@@ -1980,10 +2065,15 @@ function compareLines(ui, summary) {
1980
2065
  ui.text('█'.repeat(filled), { color: row.routed ? 'cyan' : 'gray' }),
1981
2066
  ' '.repeat(BAR - filled),
1982
2067
  usd(row.value).padStart(LEDGER_AMOUNT),
1983
- row.routed ? '' : row.yours ? ui.dim('—'.padStart(11)) : differenceText(ui, row.value - summary.yoursUsd, 11),
2068
+ row.routed
2069
+ ? ''
2070
+ : row.yours || row.other
2071
+ ? ui.dim((row.other ?? '—').padStart(11))
2072
+ : differenceText(ui, row.value - summary.yoursUsd, 11),
1984
2073
  );
1985
2074
  }),
1986
2075
  ui.dim(' same tokens and output on each model alone · answer quality not measured'),
2076
+ ...(split ? [ui.dim(' Routed adds plan and credits at list prices; plan dollars stand for quota')] : []),
1987
2077
  ];
1988
2078
  }
1989
2079
 
@@ -2011,9 +2101,9 @@ function trendLines(ui, view, actions, summary, period, now) {
2011
2101
 
2012
2102
  // The evidence worth a look, each with the tab that changes it: the cell that carried most of the cost, the switch
2013
2103
  // writes against the saving, the cell that ran above your model. Never which model to use.
2014
- function insightLines(ui, summary, actions, columns) {
2104
+ function insightLines(ui, summary, actions, columns, split) {
2015
2105
  if (summary.observed.uncomparedReplies || summary.replies < INSIGHT_REPLIES) return [];
2016
- const list = insights(summary);
2106
+ const list = billingInsights(summary, split);
2017
2107
  if (!list.length) return [];
2018
2108
  return [
2019
2109
  ui.text(' '),
@@ -2085,14 +2175,21 @@ function usageTab(ui, config, view, _usage, actions, _modelOptions, columns, now
2085
2175
  const kept = period === 'all' ? allTime(record, view.savingsStore) : null;
2086
2176
  const legacy = kept?.legacy ?? null;
2087
2177
  const r = readout(kept?.totals ?? summary);
2178
+ const split = billingSplit(config, summary);
2179
+ const answerSplit = kept ? keptSplit(config, kept) : split;
2088
2180
  const out = [periodRow(ui, period, actions), scopeLine(ui, config, view, period, summary, now), ui.text(' ')];
2089
- out.push(...headline(ui, config, view, period, r, summary, kept?.observed ?? summary.observed));
2181
+ out.push(...headline(ui, config, view, period, r, summary, kept?.observed ?? summary.observed, answerSplit));
2090
2182
  if (r.replies) {
2091
- out.push(ui.text(' '), ...ledger(ui, config, view, { period, r, summary, legacy, columns }));
2183
+ out.push(
2184
+ ui.text(' '),
2185
+ ...(answerSplit
2186
+ ? billingLedger(ui, answerSplit, true)
2187
+ : ledger(ui, config, view, { period, r, summary, legacy, columns })),
2188
+ );
2092
2189
  }
2093
2190
  if (summary.observed.replies) out.push(ui.text(' '), statsLine(ui, { ...summary.observed, turns: summary.turns }));
2094
2191
  if (summary.observed.replies) {
2095
- out.push(ui.text(' '), ...breakdownLines(ui, view, actions, summary, columns), ui.text(' '));
2192
+ out.push(ui.text(' '), ...breakdownLines(ui, config, view, actions, summary, columns, split), ui.text(' '));
2096
2193
  out.push(
2097
2194
  ...(view.usageCompare
2098
2195
  ? [
@@ -2101,10 +2198,10 @@ function usageTab(ui, config, view, _usage, actions, _modelOptions, columns, now
2101
2198
  ui.dim(' · the same tokens on one model '),
2102
2199
  ui.Button({ key: 'usage-compare', label: 'Trend', hotkey: 'c', onPress: actions.usageCompare }),
2103
2200
  ),
2104
- ...compareLines(ui, summary),
2201
+ ...compareLines(ui, config, summary, split),
2105
2202
  ]
2106
2203
  : trendLines(ui, view, actions, summary, period, now)),
2107
- ...insightLines(ui, summary, actions, columns),
2204
+ ...insightLines(ui, summary, actions, columns, split),
2108
2205
  );
2109
2206
  }
2110
2207
  out.push(
package/lib/usage.mjs CHANGED
@@ -355,7 +355,7 @@ export function summarize(record, { from, to }) {
355
355
  const READOUT_SUMS = ['replies', 'routedUsd', 'yoursUsd', 'cheaperUsd', 'strongerUsd', 'switchUsd'];
356
356
 
357
357
  // Every routed reply kept: the usage records' days and the undated savings totals from before them, as `readout`
358
- // takes them, and since when (ms; null without any).
358
+ // takes them, and since when (ms; null without any); `summary` is the dated days alone.
359
359
  export function allTime(usageStore, savingsStore) {
360
360
  const record = readUsage(usageStore);
361
361
  const summary = summarize(record, { from: null, to: null });
@@ -369,6 +369,7 @@ export function allTime(usageStore, savingsStore) {
369
369
  routedUsd: summary.observed.routedUsd + legacy.routedUsd,
370
370
  },
371
371
  legacy,
372
+ summary,
372
373
  };
373
374
  }
374
375
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@alexeiled/claude-router",
3
- "version": "1.19.2",
3
+ "version": "1.20.0",
4
4
  "description": "Native Claude Code model and effort routing with Anthropic, DeepSeek, z.ai, MiniMax, MiMo and Kimi defaults, custom provider profiles, and classifier advice.",
5
5
  "license": "MIT",
6
6
  "author": "Alexei Ledenev",