@alexeiled/claude-router 1.20.0 → 1.20.1
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.
- package/.claude-plugin/plugin.json +1 -1
- package/CHANGELOG.md +16 -0
- package/docs/configuration.md +1 -1
- package/docs/providers.md +4 -4
- package/docs/router-band.svg +1 -1
- package/docs/router-pane-usage-whatif.svg +2 -2
- package/docs/router-pane-usage.svg +2 -2
- package/docs/user-guide.md +5 -7
- package/lib/band.mjs +25 -16
- package/lib/display.mjs +26 -97
- package/lib/panel.mjs +46 -144
- package/lib/usage.mjs +1 -2
- package/package.json +1 -1
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "router",
|
|
3
3
|
"displayName": "Router",
|
|
4
|
-
"version": "1.20.
|
|
4
|
+
"version": "1.20.1",
|
|
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 +1,21 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 1.20.1 (2026-11-03)
|
|
4
|
+
|
|
5
|
+
### Changed
|
|
6
|
+
|
|
7
|
+
- One cost measure everywhere: every dollar is the reply's tokens at API list prices, on a Claude plan too. Profiles that mix plan and credits models, such as model-proxy with Opus and DeepSeek, get back one sum, its cheaper, stronger and cache-rebuild parts, the ledger, `vs yours`, What if and findings. This replaces the 1.20.0 per-billing split and its `observed credits … · plan … · your models mix plan and credits` line.
|
|
8
|
+
- The band's session row, `/router` and the comparison-unavailable line say what the replies cost: `routing −$1.84 (−22%) vs Opus 5.5 · xhigh = −$2.31 cheaper models +$0.47 cache rebuilds · $6.40 at API prices · 64 replies`. `observed $…` and `est. at list prices` are gone.
|
|
9
|
+
- The Usage footer and pane help say what an API price is and what it means on a plan.
|
|
10
|
+
|
|
11
|
+
### Fixed
|
|
12
|
+
|
|
13
|
+
- Name provider models in readouts: `DeepSeek Flash`, `GLM 5.3`, `MiniMax M3.1 Flash`, `MiMo V2.6 Pro`, `Kimi K3.1 Pro` instead of raw ids such as `Deepseek-flash[1m]`.
|
|
14
|
+
|
|
15
|
+
### Upgrade
|
|
16
|
+
|
|
17
|
+
Restart Claude Code after updating. No router-file or record changes are needed.
|
|
18
|
+
|
|
3
19
|
## 1.20.0 (2026-11-03)
|
|
4
20
|
|
|
5
21
|
### Changed
|
package/docs/configuration.md
CHANGED
|
@@ -58,7 +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
|
-
|
|
61
|
+
`billing` does not change a readout: Usage prices plan and credits models alike, at API prices; see [every dollar is an API price](user-guide.md#every-dollar-is-an-api-price).
|
|
62
62
|
A provider name or URL does not establish its billing product.
|
|
63
63
|
|
|
64
64
|
### Provider cache behavior
|
package/docs/providers.md
CHANGED
|
@@ -312,14 +312,14 @@ Launch on the model you would otherwise use:
|
|
|
312
312
|
|
|
313
313
|
| Launch model | Routing starts | Usage compares with |
|
|
314
314
|
| --- | --- | --- |
|
|
315
|
-
| `deepseek-flash[1m]` | at `low`, on DeepSeek | DeepSeek: Opus turns show as
|
|
316
|
-
| `claude-opus-5-5` | at `high`, on Opus, until the classifier supports a cheaper tier | Opus: DeepSeek turns show as
|
|
315
|
+
| `deepseek-flash[1m]` | at `low`, on DeepSeek | DeepSeek: Opus turns show as stronger models, at their API price |
|
|
316
|
+
| `claude-opus-5-5` | at `high`, on Opus, until the classifier supports a cheaper tier | Opus: DeepSeek turns show as cheaper models |
|
|
317
317
|
|
|
318
318
|
A launch model must be a model that some route runs. On any other model, a fresh session starts with routing off.
|
|
319
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
320
|
|
|
321
|
-
Opus is billed by the plan and DeepSeek in credits,
|
|
322
|
-
See [
|
|
321
|
+
Opus is billed by the plan and DeepSeek in credits, but Usage prices both at API prices, so one sum compares them: `routing −$41.20 (−10%) vs Opus 5.5 · high`.
|
|
322
|
+
See [every dollar is an API price](user-guide.md#every-dollar-is-an-api-price).
|
|
323
323
|
|
|
324
324
|
Open `/router` and check the selected file, classifier health and routing state before use.
|
|
325
325
|
The catalog must contain the bare native IDs; `[1m]` is client metadata, not a proxy alias.
|
package/docs/router-band.svg
CHANGED
|
@@ -50,7 +50,7 @@
|
|
|
50
50
|
<text x="94.2" y="140" fill="#6fcf97" font-weight="700" xml:space="preserve">routing −$1.84 (−22%)</text>
|
|
51
51
|
<text x="258.0" y="140" fill="#d0d0d0" xml:space="preserve"> vs Opus 5.5 · xhigh</text>
|
|
52
52
|
<text x="414.0" y="140" fill="#7c7c7c" xml:space="preserve"> = −$2.31 + $0.47</text>
|
|
53
|
-
<text x="562.2" y="140" fill="#7c7c7c" xml:space="preserve"> · 64 replies</text>
|
|
53
|
+
<text x="562.2" y="140" fill="#7c7c7c" xml:space="preserve"> · $6.40 at API prices · 64 replies</text>
|
|
54
54
|
<text x="24.0" y="159" fill="#7c7c7c" xml:space="preserve">pin next turn </text>
|
|
55
55
|
<rect x="133.2" y="145" width="70.2" height="18" rx="4" fill="#2e3340"/>
|
|
56
56
|
<text x="133.2" y="159" fill="#d0d0d0" xml:space="preserve">[ micro ]</text>
|
|
@@ -180,8 +180,8 @@
|
|
|
180
180
|
<text x="390.6" y="908" fill="#7c7c7c" xml:space="preserve"> its agent file sets it</text>
|
|
181
181
|
<text x="24.0" y="946" fill="#7c7c7c" xml:space="preserve"> ■ moved by the router · □ Claude Code’s pick · color: the model</text>
|
|
182
182
|
<text x="24.0" y="965" fill="#7c7c7c" xml:space="preserve"> vs CC: the same tokens on Claude Code’s pick, at list prices</text>
|
|
183
|
-
<text x="24.0" y="1003" fill="#7c7c7c" xml:space="preserve">
|
|
184
|
-
<text x="24.0" y="1022" fill="#7c7c7c" xml:space="preserve"> on a Claude plan it
|
|
183
|
+
<text x="24.0" y="1003" fill="#7c7c7c" xml:space="preserve"> every $ at API prices, plan and credits alike · not a bill;</text>
|
|
184
|
+
<text x="24.0" y="1022" fill="#7c7c7c" xml:space="preserve"> on a Claude plan it shows quota use · answer quality not measured</text>
|
|
185
185
|
<rect x="24.0" y="1046" width="140.4" height="18" rx="4" fill="#2e3340"/>
|
|
186
186
|
<text x="24.0" y="1060" fill="#7c7c7c" xml:space="preserve">[ Delete history ]</text>
|
|
187
187
|
<rect x="24.0" y="1065" width="70.2" height="18" rx="4" fill="#2e3340"/>
|
|
@@ -179,8 +179,8 @@
|
|
|
179
179
|
<text x="390.6" y="908" fill="#7c7c7c" xml:space="preserve"> its agent file sets it</text>
|
|
180
180
|
<text x="24.0" y="946" fill="#7c7c7c" xml:space="preserve"> ■ moved by the router · □ Claude Code’s pick · color: the model</text>
|
|
181
181
|
<text x="24.0" y="965" fill="#7c7c7c" xml:space="preserve"> vs CC: the same tokens on Claude Code’s pick, at list prices</text>
|
|
182
|
-
<text x="24.0" y="1003" fill="#7c7c7c" xml:space="preserve">
|
|
183
|
-
<text x="24.0" y="1022" fill="#7c7c7c" xml:space="preserve"> on a Claude plan it
|
|
182
|
+
<text x="24.0" y="1003" fill="#7c7c7c" xml:space="preserve"> every $ at API prices, plan and credits alike · not a bill;</text>
|
|
183
|
+
<text x="24.0" y="1022" fill="#7c7c7c" xml:space="preserve"> on a Claude plan it shows quota use · answer quality not measured</text>
|
|
184
184
|
<rect x="24.0" y="1046" width="140.4" height="18" rx="4" fill="#2e3340"/>
|
|
185
185
|
<text x="24.0" y="1060" fill="#7c7c7c" xml:space="preserve">[ Delete history ]</text>
|
|
186
186
|
<rect x="24.0" y="1065" width="70.2" height="18" rx="4" fill="#2e3340"/>
|
package/docs/user-guide.md
CHANGED
|
@@ -61,7 +61,7 @@ Read the first line of the picture from left to right:
|
|
|
61
61
|
| `✕ Routing unavailable` | Nothing routes: a missing/invalid provider file, an old Claude Code, or leftover v0.8 settings. **Fix** opens the pane. |
|
|
62
62
|
| `○ Router · ■ Haiku 5.5 · moved down by the router` | You are viewing a subagent's transcript. The model it runs on, and who picked it; see below. |
|
|
63
63
|
|
|
64
|
-
The band shows one routing control at a time. While routing is on, hover over the band for a second row: pin a tier for the next turn, **Turn off** routing, or show two rows. While routing is off, **Turn on** sits on the first line next to `Routing off` and stays at any width: a narrow band drops the explanation and the model first. On a narrow band the hover row drops `routing on`, then **2 rows**, then `pin next turn`, then the pins; it keeps **Turn off**, and **1 row** when the band shows two. The hover row needs a pointer: from the keyboard, run `/router off`, or open the pane and press `f`. The two-row band adds this session against your model,
|
|
64
|
+
The band shows one routing control at a time. While routing is on, hover over the band for a second row: pin a tier for the next turn, **Turn off** routing, or show two rows. While routing is off, **Turn on** sits on the first line next to `Routing off` and stays at any width: a narrow band drops the explanation and the model first. On a narrow band the hover row drops `routing on`, then **2 rows**, then `pin next turn`, then the pins; it keeps **Turn off**, and **1 row** when the band shows two. The hover row needs a pointer: from the keyboard, run `/router off`, or open the pane and press `f`. The two-row band adds this session against your model, the parts that add up to it, and what the replies cost: `session routing −$1.84 (−22%) vs Opus 5.5 · xhigh = −$2.31 cheaper models +$0.47 cache rebuilds · $6.40 at API prices · 64 replies`, or `session routing +$2.48 (×5.0) vs Haiku 5.5 · high = +$2.31 stronger models +$0.17 cache rebuilds · $3.10 at API prices · 41 replies` when routing cost more. Read it as: the routed replies cost $6.40 at API prices, $1.84 less than the same tokens on Opus 5.5 · xhigh would have cost; cheaper models saved $2.31 and the cache rebuilds after switches took back $0.47. Minus is less than your model, plus is more. **Cache rebuilds** is what the model switches cost: the next model must write the prompt cache again. The row is the first line of the pane's SESSION block, with the same words and the same number, and both count the replies of the turn still running. After a `/model` change the row names the models the replies ran against, as the Usage tab does. Before the tenth routed reply it leaves out the parts and adds `early sample`, as the pane does, because one switch can decide a short run: `session routing −$0.05 (−19%) vs Opus 5.5 · xhigh · $0.21 at API prices · 3 replies · early sample`. When the row is short, the parts lose their words (`= −$2.31 + $0.47`), then the parts drop, then the reply count, then the cost. Every dollar is an [API price](#every-dollar-is-an-api-price). Router remembers that choice across sessions. When Router changes the model between turns, a toast reads `Model changed: old → new · reason`. A pin does not raise one, and neither does a change of effort alone.
|
|
65
65
|
|
|
66
66
|
The band steps aside while a survey needs the space.
|
|
67
67
|
|
|
@@ -108,7 +108,7 @@ The Usage tab keeps observed routed spend and, when the cache history permits it
|
|
|
108
108
|
|
|
109
109
|
The top row picks the period: **Session**, **Today**, **7d** (today and the six days before), **30d**, **Month** (since the first of this month) and **All**. Press `p` for the next one. The pane remembers the choice across sessions. Session holds this session's replies, and the line under the row names your model, or every model when `/model` changed during the session. The other periods add up the replies of every session on those calendar days. Each session counts against its own model, and the line reads `all projects · Oct 7 – Oct 13 · each session vs its own model`.
|
|
110
110
|
|
|
111
|
-
When comparisons are unavailable, the band, Now tab and Usage tab say
|
|
111
|
+
When comparisons are unavailable, the band, Now tab and Usage tab say `$… at API prices · N replies · comparison unavailable`.
|
|
112
112
|
Counts, tokens, activity/model/tier breakdowns and cost trends still include these replies. A mixed period labels the
|
|
113
113
|
comparable subset separately; its savings cover only those replies. `vs yours` is `—` for a row with incomplete
|
|
114
114
|
comparison coverage, and **What if** stays unavailable rather than inventing a baseline. This is common with automatic
|
|
@@ -124,11 +124,9 @@ 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
|
-
####
|
|
127
|
+
#### Every dollar is an API price
|
|
128
128
|
|
|
129
|
-
|
|
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.
|
|
129
|
+
Every dollar in the band, `/router`, the Now tab and Usage is the same measure: the reply's tokens at the list prices in `router.json`, as if paid per token. It is not a bill. On a Claude plan it shows how much quota you use, in the same dollars as a model billed in credits. A profile that mixes the two, such as the [model-proxy profile](providers.md#mix-anthropic-and-deepseek-with-model-proxy) with Opus and DeepSeek, gets one sum and one comparison: `routing −$41.20 (−10%) vs Opus 5.5 · high` means the routed replies cost $41.20 less at API prices than the same tokens on Opus. `billing` in `router.json` sets only the credits cap on cold cache writes; it does not change a readout.
|
|
132
130
|
|
|
133
131
|
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.
|
|
134
132
|
|
|
@@ -238,7 +236,7 @@ These thresholds are starting values. They are not tuned on data yet.
|
|
|
238
236
|
|
|
239
237
|
On the **Classifier** tab, **ACROSS SESSIONS · since the last reset** shows the counts kept across sessions, once there are any: the turns labelled from their tools, **Agreement** over them, **Code/ops/explore**, the same agreement over the turns the classifier answered `code`, `ops` or `explore` (omitted when there are none), the two most frequent mismatches as `predicted → observed count` (`code → read 3`), **Activity moves**, the moves to another route inside a tier, taken and refused for any reason, **Escalations**, such as `after a cheaper activity move: 1 in 12 moves`, the tool-error escalations that followed a move to a cheaper route in `on` while the turns stayed on it in `on` (turning routing off, a turn with routing off, or a turn in `off` ends the watch, a pin in between does not, and an escalation the credits cap held counts). Each of these lines appears only when it has data. The active classifier's p95 wait across sessions shows on its **Deadline** line instead (not recorded with activity routing `off`). This agreement compares the classifier's raw answer, so it can differ from the session's. The pane reads these counts when the session starts and when it opens, and adds this session's turns as they finish; another session's new latency and escalation readings show the next time the pane opens. **Delete history** on the Usage tab deletes these counts with the usage and subagent records, for this session and across sessions.
|
|
240
238
|
|
|
241
|
-
`/router` without a UI surface adds an `Activity: ops (81%)` line, the resolved route, and `Agreement across sessions: 19 of 22 turns (86%) · code/ops/explore 9 of 10 (90%)`. It also prints the session in the band's words, such as `Session: routing −$1.84 (−22%) vs Opus 5.5 · xhigh = −$2.31 cheaper models +$0.47 cache rebuilds,
|
|
239
|
+
`/router` without a UI surface adds an `Activity: ops (81%)` line, the resolved route, and `Agreement across sessions: 19 of 22 turns (86%) · code/ops/explore 9 of 10 (90%)`. It also prints the session in the band's words, such as `Session: routing −$1.84 (−22%) vs Opus 5.5 · xhigh = −$2.31 cheaper models +$0.47 cache rebuilds, $6.40 at API prices, 64 replies`.
|
|
242
240
|
|
|
243
241
|
## Change routing
|
|
244
242
|
|
package/lib/band.mjs
CHANGED
|
@@ -1,8 +1,6 @@
|
|
|
1
1
|
import { activeClassifier, TIERS } from './config.mjs';
|
|
2
2
|
import {
|
|
3
3
|
activityVerb,
|
|
4
|
-
answerSegments,
|
|
5
|
-
billingSplit,
|
|
6
4
|
classifierLabel,
|
|
7
5
|
classifierStatus,
|
|
8
6
|
classifierWarns,
|
|
@@ -16,11 +14,12 @@ import {
|
|
|
16
14
|
percentPair,
|
|
17
15
|
reasonActivity,
|
|
18
16
|
routeLabel,
|
|
17
|
+
routingAnswer,
|
|
19
18
|
routingModeText,
|
|
20
19
|
savingsColor,
|
|
21
20
|
sessionUsage,
|
|
22
21
|
shortReason,
|
|
23
|
-
|
|
22
|
+
spentText,
|
|
24
23
|
TIER_COLOR,
|
|
25
24
|
unavailableReason,
|
|
26
25
|
usageMetrics,
|
|
@@ -216,28 +215,28 @@ export function bandSegments(config, view, usage, actions) {
|
|
|
216
215
|
}
|
|
217
216
|
|
|
218
217
|
// The second row of the detailed band: this session against your model, as the pane's SESSION block starts, and the
|
|
219
|
-
// parts that add up to it: "routing +$0.18 (+4%) vs Opus 5.5 · high = −$0.42 cheaper
|
|
220
|
-
// rebuilds · 34 replies". When the band is narrow the parts lose their
|
|
221
|
-
// parts.
|
|
218
|
+
// parts that add up to it, then what the replies cost: "routing +$0.18 (+4%) vs Opus 5.5 · high = −$0.42 cheaper
|
|
219
|
+
// models +$0.60 cache rebuilds · $4.62 at API prices · 34 replies". When the band is narrow the parts lose their
|
|
220
|
+
// words, then the parts go, then the reply count, then the cost.
|
|
222
221
|
export function sessionRow(config, view, columns, now = Date.now()) {
|
|
223
222
|
const label = part('session ', { dimColor: true });
|
|
224
223
|
const summary = sessionUsage(view, now);
|
|
225
224
|
const r = readout(summary);
|
|
226
|
-
const split = billingSplit(config, summary);
|
|
227
225
|
if (summary.observed.uncomparedReplies)
|
|
228
226
|
return fitSegments(
|
|
229
|
-
[segment(0, label, part(observedUsageText(summary.observed
|
|
227
|
+
[segment(0, label, part(observedUsageText(summary.observed), { dimColor: true }))],
|
|
230
228
|
columns,
|
|
231
229
|
).flatMap((s) => s.parts);
|
|
232
230
|
if (!modelSpec(config, view.nativeModel))
|
|
233
231
|
return [label, part(`${modelName(view.nativeModel)} has no list price`, { dimColor: true })];
|
|
234
232
|
if (!r.replies) return [part('no replies yet', { dimColor: true })];
|
|
235
233
|
const count = `${r.replies} repl${r.replies === 1 ? 'y' : 'ies'}`;
|
|
234
|
+
const spent = spentText(r.routedUsd);
|
|
236
235
|
const answer = [
|
|
237
236
|
label,
|
|
238
|
-
|
|
239
|
-
|
|
240
|
-
]
|
|
237
|
+
part(routingAnswer(r), { color: savingsColor(r.differenceUsd), bold: true }),
|
|
238
|
+
part(` vs ${comparedModel(config, view, summary)}`),
|
|
239
|
+
];
|
|
241
240
|
const width = (row) => row.reduce((n, p) => n + p.text.length, 0);
|
|
242
241
|
const fit = (rows) =>
|
|
243
242
|
fitSegments(
|
|
@@ -245,10 +244,14 @@ export function sessionRow(config, view, columns, now = Date.now()) {
|
|
|
245
244
|
columns,
|
|
246
245
|
).flatMap((s) => s.parts);
|
|
247
246
|
// Below EARLY_REPLIES one switch decides the sum, so the parts wait, as on the pane.
|
|
248
|
-
if (r.early)
|
|
249
|
-
|
|
250
|
-
|
|
251
|
-
|
|
247
|
+
if (r.early)
|
|
248
|
+
return fit([
|
|
249
|
+
[...answer, part(`${SEPARATOR}${spent} · ${count} · early sample`, { dimColor: true })],
|
|
250
|
+
[...answer, part(`${SEPARATOR}${spent}`, { dimColor: true })],
|
|
251
|
+
answer,
|
|
252
|
+
]);
|
|
253
|
+
const replies = part(`${SEPARATOR}${spent} · ${count}`, { dimColor: true });
|
|
254
|
+
const cost = part(`${SEPARATOR}${spent}`, { dimColor: true });
|
|
252
255
|
const parts = costParts(r);
|
|
253
256
|
const named = parts.flatMap(([amount, words, value], i) => [
|
|
254
257
|
part(i ? ' ' : ' = ', { dimColor: true }),
|
|
@@ -261,7 +264,13 @@ export function sessionRow(config, view, columns, now = Date.now()) {
|
|
|
261
264
|
}),
|
|
262
265
|
]
|
|
263
266
|
: [];
|
|
264
|
-
return fit([
|
|
267
|
+
return fit([
|
|
268
|
+
[...answer, ...named, replies],
|
|
269
|
+
[...answer, ...bare, replies],
|
|
270
|
+
[...answer, replies],
|
|
271
|
+
[...answer, cost],
|
|
272
|
+
answer,
|
|
273
|
+
]);
|
|
265
274
|
}
|
|
266
275
|
|
|
267
276
|
// The row revealed under the pointer: pins and the mode control while routing is on, and the one- or two-row choice.
|
package/lib/display.mjs
CHANGED
|
@@ -3,7 +3,6 @@ import { readMetrics, readStore, storeSummary, UNPRICED_CAUSES } from './activit
|
|
|
3
3
|
import {
|
|
4
4
|
activeClassifier,
|
|
5
5
|
CLASSIFIER_OPTIONS,
|
|
6
|
-
DEFAULTS,
|
|
7
6
|
endpointSettings,
|
|
8
7
|
resolveRoute,
|
|
9
8
|
routeSpec,
|
|
@@ -13,10 +12,9 @@ import {
|
|
|
13
12
|
import { ratesAt } from './cost.mjs';
|
|
14
13
|
import { applyMode, modeLabel, modeRoute } from './modes.mjs';
|
|
15
14
|
import { PROBE_RESULTS } from './probe-results.mjs';
|
|
16
|
-
import { PROVIDER_DEFAULTS } from './providers.mjs';
|
|
17
15
|
import { cellForModel } from './route.mjs';
|
|
18
16
|
import { modelSpec, readout } from './savings.mjs';
|
|
19
|
-
import { allTime,
|
|
17
|
+
import { allTime, periodRange, readUsage, summarize, withReplies } from './usage.mjs';
|
|
20
18
|
|
|
21
19
|
// Cost order, cheapest first, so the colors read as a scale. Hex values: every surface draws them.
|
|
22
20
|
export const TIER_COLOR = { micro: '#5fd7af', low: '#5f9fe0', medium: '#d7af5f', high: '#e0708a' };
|
|
@@ -72,11 +70,20 @@ export const NOT_A_TIER_REASON = 'not a routing tier';
|
|
|
72
70
|
|
|
73
71
|
export function modelName(id) {
|
|
74
72
|
if (!id) return 'no response yet';
|
|
73
|
+
if (id.startsWith('claude-'))
|
|
74
|
+
return id
|
|
75
|
+
.replace(/^claude-/, '')
|
|
76
|
+
.replace(/-([0-9])-([0-9])(-\d{8})?$/, ' $1.$2')
|
|
77
|
+
.replace(/^./, (c) => c.toUpperCase());
|
|
78
|
+
// A provider id, `deepseek-flash[1m]` → "DeepSeek Flash": the `[1m]` context suffix is client metadata, not a name.
|
|
75
79
|
return id
|
|
76
|
-
.replace(
|
|
77
|
-
.
|
|
78
|
-
.replace(/^./, (c) => c.toUpperCase())
|
|
80
|
+
.replace(/\[[^\]]*\]$/, '')
|
|
81
|
+
.split('-')
|
|
82
|
+
.map((word) => BRANDS[word.toLowerCase()] ?? word.replace(/^./, (c) => c.toUpperCase()))
|
|
83
|
+
.join(' ');
|
|
79
84
|
}
|
|
85
|
+
// Provider names whose casing a capital first letter gets wrong.
|
|
86
|
+
const BRANDS = { deepseek: 'DeepSeek', glm: 'GLM', minimax: 'MiniMax', mimo: 'MiMo' };
|
|
80
87
|
|
|
81
88
|
// "Opus 5.5 · high"; a model with no effort reading shows its name alone.
|
|
82
89
|
export const routeLabel = (model, effort) =>
|
|
@@ -347,87 +354,12 @@ export const liveUsage = (view, record) => withReplies(readUsage(record), view.u
|
|
|
347
354
|
// This session's routed replies, the running turns' included.
|
|
348
355
|
export const sessionUsage = (view, now) => summarize(liveUsage(view, view.usageSession), periodRange('session', now));
|
|
349
356
|
|
|
350
|
-
//
|
|
351
|
-
//
|
|
352
|
-
export const
|
|
353
|
-
|
|
354
|
-
|
|
355
|
-
|
|
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} ${signedUsd(value)}`, value }];
|
|
424
|
-
}),
|
|
425
|
-
];
|
|
426
|
-
}
|
|
427
|
-
export const answerText = (r, split) =>
|
|
428
|
-
answerSegments(r, split)
|
|
429
|
-
.map((segment) => segment.text)
|
|
430
|
-
.join('');
|
|
357
|
+
// Every dollar amount is a reply's tokens at the router.json list prices, as if paid per token: on a Claude plan it
|
|
358
|
+
// shows quota use in the same dollars as credits, so plan and credit models add up and compare.
|
|
359
|
+
export const spentText = (value) => `${usd(value)} at API prices`;
|
|
360
|
+
// What the replies cost is known even when a counterfactual cache history cannot be priced.
|
|
361
|
+
export const observedUsageText = (observed) =>
|
|
362
|
+
`${spentText(observed.routedUsd)} · ${replyCount(observed.replies)} · comparison unavailable`;
|
|
431
363
|
|
|
432
364
|
// The models a session's replies were priced against, when they are not the one `/model` selects now: after a
|
|
433
365
|
// `/model` change the record keeps each reply against the model selected when it ran. Null when they are.
|
|
@@ -462,26 +394,23 @@ export const switchesLost = (r) => r.switchUsd > 0 && r.switchUsd > -r.cheaperUs
|
|
|
462
394
|
export function savingsLine(config, view, now) {
|
|
463
395
|
const summary = sessionUsage(view, now);
|
|
464
396
|
const session = readout(summary);
|
|
465
|
-
const split = billingSplit(config, summary);
|
|
466
397
|
if (summary.observed.uncomparedReplies)
|
|
467
|
-
return `Session: ${observedUsageText(summary.observed
|
|
398
|
+
return `Session: ${observedUsageText(summary.observed)}${session.replies ? `; ${replyCount(session.replies)} comparable only: ${routingAnswer(session)}` : ''}`;
|
|
468
399
|
const label = `vs ${comparedModel(config, view, summary)}`;
|
|
469
400
|
if (!session.replies) {
|
|
470
401
|
const kept = allTime(view.usageStore, view.savingsStore);
|
|
471
402
|
const across = readout(kept.totals);
|
|
472
|
-
const keptBy = keptSplit(config, kept);
|
|
473
403
|
if (kept.observed.uncomparedReplies)
|
|
474
|
-
return `Session ${label}: no routed replies yet; across sessions ${observedUsageText(kept.observed
|
|
404
|
+
return `Session ${label}: no routed replies yet; across sessions ${observedUsageText(kept.observed)}`;
|
|
475
405
|
const saved = across.early
|
|
476
406
|
? ''
|
|
477
|
-
: `; ${
|
|
407
|
+
: `; ${routingAnswer(across)} since ${sinceDate(kept.since)}, each session against its own model`;
|
|
478
408
|
return `Session ${label}: no routed replies yet${saved}`;
|
|
479
409
|
}
|
|
480
|
-
|
|
481
|
-
|
|
482
|
-
|
|
483
|
-
|
|
484
|
-
return `Session: ${answer}${parts.length ? ` = ${parts.join(' ')}` : ''}, ${replyCount(session.replies)}, est. at list prices`;
|
|
410
|
+
if (session.early)
|
|
411
|
+
return `Session: ${routingAnswer(session)} ${label}, ${spentText(session.routedUsd)}, ${replyCount(session.replies)}, early sample`;
|
|
412
|
+
const parts = costParts(session).map(([amount, words]) => `${amount} ${words}`);
|
|
413
|
+
return `Session: ${routingAnswer(session)} ${label}${parts.length ? ` = ${parts.join(' ')}` : ''}, ${spentText(session.routedUsd)}, ${replyCount(session.replies)}`;
|
|
485
414
|
}
|
|
486
415
|
|
|
487
416
|
export const GATEWAY_SETTINGS = 'v0.8 gateway settings remain · see /router';
|
package/lib/panel.mjs
CHANGED
|
@@ -18,12 +18,6 @@ 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,
|
|
27
21
|
COST_PART,
|
|
28
22
|
classifierLabel,
|
|
29
23
|
classifierStatus,
|
|
@@ -31,7 +25,6 @@ import {
|
|
|
31
25
|
formatTokens,
|
|
32
26
|
GATEWAY_CLEANUP,
|
|
33
27
|
GATEWAY_SETTINGS,
|
|
34
|
-
keptSplit,
|
|
35
28
|
liveUsage,
|
|
36
29
|
missingCredentials,
|
|
37
30
|
missingText,
|
|
@@ -44,6 +37,7 @@ import {
|
|
|
44
37
|
recordedModels,
|
|
45
38
|
routeLabel,
|
|
46
39
|
routeName,
|
|
40
|
+
routingAnswer,
|
|
47
41
|
routingModeOf,
|
|
48
42
|
routingModeText,
|
|
49
43
|
savingsColor,
|
|
@@ -51,7 +45,6 @@ import {
|
|
|
51
45
|
shownConfig,
|
|
52
46
|
signedUsd,
|
|
53
47
|
sparkline,
|
|
54
|
-
splitCompared,
|
|
55
48
|
switchesLost,
|
|
56
49
|
TIER_COLOR,
|
|
57
50
|
unavailableReason,
|
|
@@ -359,10 +352,10 @@ function nowTab(ui, config, view, usage, actions, _modelOptions, columns, now) {
|
|
|
359
352
|
// Today repeats this session's part of it until another session adds to it.
|
|
360
353
|
const ownToday = summarize(liveUsage(view, view.usageSession), periodRange('today', now));
|
|
361
354
|
if (today.observed.replies > ownToday.observed.replies)
|
|
362
|
-
out.push(ui.text(' '), ...todayLines(ui,
|
|
355
|
+
out.push(ui.text(' '), ...todayLines(ui, today, actions, columns));
|
|
363
356
|
out.push(
|
|
364
357
|
...sessionAgentLines(ui, view, actions, columns),
|
|
365
|
-
...worthLines(ui,
|
|
358
|
+
...worthLines(ui, today, actions, columns),
|
|
366
359
|
ui.text(' '),
|
|
367
360
|
ui.gauge('Context ', metrics.contextBar, contextSuffix(metrics)),
|
|
368
361
|
ui.line(
|
|
@@ -507,12 +500,11 @@ function sessionLines(ui, config, view, summary, actions, columns, now) {
|
|
|
507
500
|
if (!strip && !summary.observed.replies) return [ui.line(ui.head('SESSION'), ui.dim(' · no replies yet'))];
|
|
508
501
|
const out = [ui.line(ui.head('SESSION'), head.length ? ui.dim(` · ${head.join(' · ')}`) : null)];
|
|
509
502
|
// The band's session row, then the parts that add up to it.
|
|
510
|
-
const split = billingSplit(config, summary);
|
|
511
503
|
if (summary.observed.uncomparedReplies) {
|
|
512
504
|
out.push(
|
|
513
505
|
ui.line(
|
|
514
506
|
' ',
|
|
515
|
-
ui.text(observedUsageText(summary.observed
|
|
507
|
+
ui.text(observedUsageText(summary.observed)),
|
|
516
508
|
' ',
|
|
517
509
|
ui.Button({ key: 'usage-session', label: 'Usage', onPress: () => actions.usageFor('session') }),
|
|
518
510
|
),
|
|
@@ -520,23 +512,11 @@ function sessionLines(ui, config, view, summary, actions, columns, now) {
|
|
|
520
512
|
} else if (summary.replies) {
|
|
521
513
|
const r = readout(summary);
|
|
522
514
|
out.push(
|
|
523
|
-
answerLine(
|
|
524
|
-
ui,
|
|
525
|
-
r,
|
|
526
|
-
split,
|
|
527
|
-
comparedModel(config, view, summary),
|
|
528
|
-
() => actions.usageFor('session'),
|
|
529
|
-
'session',
|
|
530
|
-
columns,
|
|
531
|
-
),
|
|
515
|
+
answerLine(ui, r, comparedModel(config, view, summary), () => actions.usageFor('session'), 'session', columns),
|
|
532
516
|
);
|
|
533
517
|
if (!r.early)
|
|
534
|
-
out.push(
|
|
535
|
-
|
|
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));
|
|
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));
|
|
540
520
|
}
|
|
541
521
|
if (strip) {
|
|
542
522
|
out.push(
|
|
@@ -599,12 +579,12 @@ function lastSwitchLine(ui, last, now) {
|
|
|
599
579
|
|
|
600
580
|
// Routing against your model in the band's words, "routing −$1.84 (−22%) vs Opus 5.5 · xhigh", with the Usage tab on
|
|
601
581
|
// the same period one press away; an early sample says so.
|
|
602
|
-
function answerLine(ui, r,
|
|
582
|
+
function answerLine(ui, r, against, open, period, columns) {
|
|
603
583
|
const early = ' · early sample';
|
|
604
|
-
const width = 2 +
|
|
584
|
+
const width = 2 + routingAnswer(r).length + ` vs ${against}`.length + early.length + USAGE_LINK;
|
|
605
585
|
return ui.line(
|
|
606
586
|
' ',
|
|
607
|
-
...answerParts(ui, r,
|
|
587
|
+
...answerParts(ui, r, against),
|
|
608
588
|
r.early && (!Number.isFinite(columns) || width <= columns) ? ui.dim(early) : null,
|
|
609
589
|
' ',
|
|
610
590
|
ui.Button({ key: `usage-${period}`, label: 'Usage', onPress: open }),
|
|
@@ -620,9 +600,8 @@ const lostLine = (ui, actions) =>
|
|
|
620
600
|
);
|
|
621
601
|
|
|
622
602
|
// Today across sessions, shown once another session added to it.
|
|
623
|
-
function todayLines(ui,
|
|
603
|
+
function todayLines(ui, summary, actions, columns) {
|
|
624
604
|
const switches = summary.switches.tier + summary.switches.activity;
|
|
625
|
-
const split = billingSplit(config, summary);
|
|
626
605
|
return [
|
|
627
606
|
ui.line(
|
|
628
607
|
ui.head('TODAY'),
|
|
@@ -632,32 +611,17 @@ function todayLines(ui, config, summary, actions, columns) {
|
|
|
632
611
|
),
|
|
633
612
|
summary.observed.uncomparedReplies
|
|
634
613
|
? ui.line(
|
|
635
|
-
ui.text(observedUsageText(summary.observed
|
|
614
|
+
ui.text(observedUsageText(summary.observed)),
|
|
636
615
|
' ',
|
|
637
616
|
ui.Button({ key: 'usage-today', label: 'Usage', onPress: () => actions.usageFor('today') }),
|
|
638
617
|
)
|
|
639
|
-
: answerLine(
|
|
640
|
-
ui,
|
|
641
|
-
readout(summary),
|
|
642
|
-
split,
|
|
643
|
-
'each session’s own model',
|
|
644
|
-
() => actions.usageFor('today'),
|
|
645
|
-
'today',
|
|
646
|
-
columns,
|
|
647
|
-
),
|
|
618
|
+
: answerLine(ui, readout(summary), 'each session’s own model', () => actions.usageFor('today'), 'today', columns),
|
|
648
619
|
];
|
|
649
620
|
}
|
|
650
621
|
|
|
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
|
-
|
|
655
622
|
// Today's first finding from Usage's WORTH A LOOK, with the tab that changes it; nothing when there is none.
|
|
656
|
-
function worthLines(ui,
|
|
657
|
-
const [first] =
|
|
658
|
-
!summary.observed.uncomparedReplies && summary.replies >= INSIGHT_REPLIES
|
|
659
|
-
? billingInsights(summary, billingSplit(config, summary))
|
|
660
|
-
: [];
|
|
623
|
+
function worthLines(ui, summary, actions, columns) {
|
|
624
|
+
const [first] = !summary.observed.uncomparedReplies && summary.replies >= INSIGHT_REPLIES ? insights(summary) : [];
|
|
661
625
|
if (!first) return [];
|
|
662
626
|
return [ui.text(' '), ui.line(ui.head('WORTH A LOOK'), ui.dim(' · today')), insightLine(ui, first, actions, columns)];
|
|
663
627
|
}
|
|
@@ -1326,10 +1290,9 @@ function storeUsage(ui, store, metrics) {
|
|
|
1326
1290
|
// The footer as [text, joiner] pieces, packed to the pane: two lines at full width, more in a narrow pane, never a
|
|
1327
1291
|
// line that ends in a joiner.
|
|
1328
1292
|
const SAVINGS_FOOTER = [
|
|
1329
|
-
['API
|
|
1330
|
-
['same tokens and output length', ' · '],
|
|
1293
|
+
['every $ at API prices, plan and credits alike', ' · '],
|
|
1331
1294
|
['not a bill;', ' '],
|
|
1332
|
-
['on a Claude plan it
|
|
1295
|
+
['on a Claude plan it shows quota use', ' · '],
|
|
1333
1296
|
['answer quality not measured', ''],
|
|
1334
1297
|
];
|
|
1335
1298
|
const FULL_WIDTH = 68;
|
|
@@ -1761,10 +1724,10 @@ function scopeLine(ui, config, view, period, summary, now) {
|
|
|
1761
1724
|
}
|
|
1762
1725
|
|
|
1763
1726
|
// The answer first, in the band's words: "routing −$1.84 (−22%) vs Opus 5.5 · xhigh", or why there is nothing to compare.
|
|
1764
|
-
function headline(ui, config, view, period, r, summary, observed
|
|
1727
|
+
function headline(ui, config, view, period, r, summary, observed = summary.observed) {
|
|
1765
1728
|
if (observed.uncomparedReplies)
|
|
1766
1729
|
return [
|
|
1767
|
-
ui.text(observedUsageText(observed
|
|
1730
|
+
ui.text(observedUsageText(observed), { bold: true }),
|
|
1768
1731
|
ui.dim(
|
|
1769
1732
|
`${observed.uncomparedReplies} of ${observed.replies} replies have no comparison; savings are not estimated for them.`,
|
|
1770
1733
|
),
|
|
@@ -1775,7 +1738,6 @@ function headline(ui, config, view, period, r, summary, observed, split) {
|
|
|
1775
1738
|
...answerParts(
|
|
1776
1739
|
ui,
|
|
1777
1740
|
r,
|
|
1778
|
-
split,
|
|
1779
1741
|
period === 'session' ? comparedModel(config, view, summary) : 'each session’s own model',
|
|
1780
1742
|
),
|
|
1781
1743
|
),
|
|
@@ -1798,7 +1760,7 @@ function headline(ui, config, view, period, r, summary, observed, split) {
|
|
|
1798
1760
|
const against = period === 'session' ? comparedModel(config, view, summary) : 'each session’s own model';
|
|
1799
1761
|
return [
|
|
1800
1762
|
ui.line(
|
|
1801
|
-
...answerParts(ui, r,
|
|
1763
|
+
...answerParts(ui, r, against),
|
|
1802
1764
|
r.early ? ui.text(` early sample · ${plural(r.replies, 'reply', 'replies')}`, { color: 'yellow' }) : null,
|
|
1803
1765
|
),
|
|
1804
1766
|
];
|
|
@@ -1806,39 +1768,10 @@ function headline(ui, config, view, period, r, summary, observed, split) {
|
|
|
1806
1768
|
|
|
1807
1769
|
const capital = (words) => words[0].toUpperCase() + words.slice(1);
|
|
1808
1770
|
|
|
1809
|
-
// "routing −$1.84 (−22%) vs Opus 5.5 · xhigh", the answer bold in the savings color, as the band says it
|
|
1810
|
-
|
|
1811
|
-
|
|
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
|
-
];
|
|
1771
|
+
// "routing −$1.84 (−22%) vs Opus 5.5 · xhigh", the answer bold in the savings color, as the band says it.
|
|
1772
|
+
function answerParts(ui, r, against) {
|
|
1773
|
+
return [ui.text(routingAnswer(r), { bold: true, color: savingsColor(r.differenceUsd) }), ` vs ${against}`];
|
|
1840
1774
|
}
|
|
1841
|
-
const BILLING_AMOUNT = 13;
|
|
1842
1775
|
|
|
1843
1776
|
// Your model − cheaper models + stronger models + switch cache writes = routed, in whole cents that add up (readout).
|
|
1844
1777
|
function ledger(ui, config, view, { period, r, summary, legacy, columns, compact = false }) {
|
|
@@ -1926,10 +1859,8 @@ const statsLine = (ui, s) =>
|
|
|
1926
1859
|
);
|
|
1927
1860
|
|
|
1928
1861
|
// The period's cost by activity, model or tier, most first; `g` presses the next grouping. A row opens to what it
|
|
1929
|
-
// holds and its cost parts. A narrow pane drops "mostly on" (or the share) before any number.
|
|
1930
|
-
|
|
1931
|
-
// difference would subtract quota from cash.
|
|
1932
|
-
function breakdownLines(ui, config, view, actions, summary, columns, split) {
|
|
1862
|
+
// holds and its cost parts. A narrow pane drops "mostly on" (or the share) before any number.
|
|
1863
|
+
function breakdownLines(ui, view, actions, summary, columns) {
|
|
1933
1864
|
const by = GROUPS.some(([id]) => id === view.usageGroup) ? view.usageGroup : 'activity';
|
|
1934
1865
|
const next = GROUPS[(GROUPS.findIndex(([id]) => id === by) + 1) % GROUPS.length][0];
|
|
1935
1866
|
const out = [
|
|
@@ -1959,24 +1890,14 @@ function breakdownLines(ui, config, view, actions, summary, columns, split) {
|
|
|
1959
1890
|
` ${''.padEnd(NAME)}${'replies'.padStart(8)}${'cost'.padStart(10)}${'vs yours'.padStart(11)}${tail ? ` ${tailHead}` : ''}`,
|
|
1960
1891
|
),
|
|
1961
1892
|
);
|
|
1962
|
-
const
|
|
1963
|
-
|
|
1964
|
-
|
|
1965
|
-
|
|
1966
|
-
return billings.size === 1 ? [...billings][0] : 'both';
|
|
1967
|
-
};
|
|
1968
|
-
const numbers = (sums, unavailable, rowCells) => {
|
|
1969
|
-
const other = unavailable ? null : otherBilling(rowCells);
|
|
1970
|
-
return [
|
|
1971
|
-
`${String(sums[0]).padStart(8)}${usd(sums[1]).padStart(10)}`,
|
|
1972
|
-
unavailable || other ? ui.dim((other ?? '—').padStart(11)) : differenceText(ui, sums[1] - sums[2], 11),
|
|
1973
|
-
];
|
|
1974
|
-
};
|
|
1893
|
+
const numbers = (sums, unavailable) => [
|
|
1894
|
+
`${String(sums[0]).padStart(8)}${usd(sums[1]).padStart(10)}`,
|
|
1895
|
+
unavailable ? ui.dim('—'.padStart(11)) : differenceText(ui, sums[1] - sums[2], 11),
|
|
1896
|
+
];
|
|
1975
1897
|
for (const group of groups) {
|
|
1976
1898
|
const id = `${by}:${group.name}`;
|
|
1977
1899
|
const open = view.usageOpen === id;
|
|
1978
|
-
const
|
|
1979
|
-
const route = by === 'model' ? null : mostlyOn(groupCells);
|
|
1900
|
+
const route = by === 'model' ? null : mostlyOn(cellsWhere(cells, by, group.name));
|
|
1980
1901
|
out.push(
|
|
1981
1902
|
ui.line(
|
|
1982
1903
|
' ',
|
|
@@ -1988,7 +1909,7 @@ function breakdownLines(ui, config, view, actions, summary, columns, split) {
|
|
|
1988
1909
|
}),
|
|
1989
1910
|
' ',
|
|
1990
1911
|
ui.cell(NAME, groupName(ui, by, group.name)),
|
|
1991
|
-
...numbers(group.sums, missing.has(group.name)
|
|
1912
|
+
...numbers(group.sums, missing.has(group.name)),
|
|
1992
1913
|
!tail
|
|
1993
1914
|
? null
|
|
1994
1915
|
: by === 'model'
|
|
@@ -2007,20 +1928,16 @@ function breakdownLines(ui, config, view, actions, summary, columns, split) {
|
|
|
2007
1928
|
...numbers(
|
|
2008
1929
|
child.sums,
|
|
2009
1930
|
missing.get(group.name)?.children.some((c) => c.name === child.name),
|
|
2010
|
-
cellsWhere(groupCells, CHILD_BY[by], child.name),
|
|
2011
1931
|
),
|
|
2012
1932
|
),
|
|
2013
1933
|
);
|
|
2014
1934
|
const [, , , cheaper, stronger, switched, input, , output] = group.sums;
|
|
2015
|
-
const tokens = `input ${formatTokens(input)} · output ${formatTokens(output)}`;
|
|
2016
1935
|
out.push(
|
|
2017
1936
|
...dimLines(
|
|
2018
1937
|
ui,
|
|
2019
1938
|
missing.has(group.name)
|
|
2020
|
-
? ` comparison unavailable · ${
|
|
2021
|
-
:
|
|
2022
|
-
? ` ${tokens}`
|
|
2023
|
-
: ` cheaper ${signedUsd(cents(cheaper))} · stronger ${signedUsd(cents(stronger))} · switch ${signedUsd(cents(switched))} · ${tokens}`,
|
|
1939
|
+
? ` comparison unavailable · input ${formatTokens(input)} · output ${formatTokens(output)}`
|
|
1940
|
+
: ` cheaper ${signedUsd(cents(cheaper))} · stronger ${signedUsd(cents(stronger))} · switch ${signedUsd(cents(switched))} · input ${formatTokens(input)} · output ${formatTokens(output)}`,
|
|
2024
1941
|
columns,
|
|
2025
1942
|
),
|
|
2026
1943
|
);
|
|
@@ -2029,9 +1946,8 @@ function breakdownLines(ui, config, view, actions, summary, columns, split) {
|
|
|
2029
1946
|
}
|
|
2030
1947
|
|
|
2031
1948
|
// What the period's tokens would cost on each model alone, as your model for every reply (compareModels), beside what
|
|
2032
|
-
// routing spent and your own models; a model some reply had no price on is left out.
|
|
2033
|
-
|
|
2034
|
-
function compareLines(ui, config, summary, split) {
|
|
1949
|
+
// routing spent and your own models; a model some reply had no price on is left out.
|
|
1950
|
+
function compareLines(ui, summary) {
|
|
2035
1951
|
if (summary.observed.uncomparedReplies)
|
|
2036
1952
|
return [ui.dim('What if unavailable: some replies have no comparable cache history.')];
|
|
2037
1953
|
const yours = Object.keys(summary.yours);
|
|
@@ -2043,7 +1959,6 @@ function compareLines(ui, config, summary, split) {
|
|
|
2043
1959
|
value,
|
|
2044
1960
|
routed: false,
|
|
2045
1961
|
yours: model === single,
|
|
2046
|
-
other: split && billingOf(config, model) !== split.yours ? billingOf(config, model) : null,
|
|
2047
1962
|
}));
|
|
2048
1963
|
if (!rows.some((row) => row.yours))
|
|
2049
1964
|
rows.push({
|
|
@@ -2051,9 +1966,8 @@ function compareLines(ui, config, summary, split) {
|
|
|
2051
1966
|
value: summary.yoursUsd,
|
|
2052
1967
|
routed: false,
|
|
2053
1968
|
yours: true,
|
|
2054
|
-
other: null,
|
|
2055
1969
|
});
|
|
2056
|
-
rows.push({ label: 'Routed', value: summary.routedUsd, routed: true, yours: false
|
|
1970
|
+
rows.push({ label: 'Routed', value: summary.routedUsd, routed: true, yours: false });
|
|
2057
1971
|
rows.sort((a, b) => a.value - b.value);
|
|
2058
1972
|
const max = Math.max(...rows.map((row) => row.value));
|
|
2059
1973
|
return [
|
|
@@ -2065,15 +1979,10 @@ function compareLines(ui, config, summary, split) {
|
|
|
2065
1979
|
ui.text('█'.repeat(filled), { color: row.routed ? 'cyan' : 'gray' }),
|
|
2066
1980
|
' '.repeat(BAR - filled),
|
|
2067
1981
|
usd(row.value).padStart(LEDGER_AMOUNT),
|
|
2068
|
-
row.routed
|
|
2069
|
-
? ''
|
|
2070
|
-
: row.yours || row.other
|
|
2071
|
-
? ui.dim((row.other ?? '—').padStart(11))
|
|
2072
|
-
: differenceText(ui, row.value - summary.yoursUsd, 11),
|
|
1982
|
+
row.routed ? '' : row.yours ? ui.dim('—'.padStart(11)) : differenceText(ui, row.value - summary.yoursUsd, 11),
|
|
2073
1983
|
);
|
|
2074
1984
|
}),
|
|
2075
1985
|
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')] : []),
|
|
2077
1986
|
];
|
|
2078
1987
|
}
|
|
2079
1988
|
|
|
@@ -2101,9 +2010,9 @@ function trendLines(ui, view, actions, summary, period, now) {
|
|
|
2101
2010
|
|
|
2102
2011
|
// The evidence worth a look, each with the tab that changes it: the cell that carried most of the cost, the switch
|
|
2103
2012
|
// writes against the saving, the cell that ran above your model. Never which model to use.
|
|
2104
|
-
function insightLines(ui, summary, actions, columns
|
|
2013
|
+
function insightLines(ui, summary, actions, columns) {
|
|
2105
2014
|
if (summary.observed.uncomparedReplies || summary.replies < INSIGHT_REPLIES) return [];
|
|
2106
|
-
const list =
|
|
2015
|
+
const list = insights(summary);
|
|
2107
2016
|
if (!list.length) return [];
|
|
2108
2017
|
return [
|
|
2109
2018
|
ui.text(' '),
|
|
@@ -2175,21 +2084,14 @@ function usageTab(ui, config, view, _usage, actions, _modelOptions, columns, now
|
|
|
2175
2084
|
const kept = period === 'all' ? allTime(record, view.savingsStore) : null;
|
|
2176
2085
|
const legacy = kept?.legacy ?? null;
|
|
2177
2086
|
const r = readout(kept?.totals ?? summary);
|
|
2178
|
-
const split = billingSplit(config, summary);
|
|
2179
|
-
const answerSplit = kept ? keptSplit(config, kept) : split;
|
|
2180
2087
|
const out = [periodRow(ui, period, actions), scopeLine(ui, config, view, period, summary, now), ui.text(' ')];
|
|
2181
|
-
out.push(...headline(ui, config, view, period, r, summary, kept?.observed ?? summary.observed
|
|
2088
|
+
out.push(...headline(ui, config, view, period, r, summary, kept?.observed ?? summary.observed));
|
|
2182
2089
|
if (r.replies) {
|
|
2183
|
-
out.push(
|
|
2184
|
-
ui.text(' '),
|
|
2185
|
-
...(answerSplit
|
|
2186
|
-
? billingLedger(ui, answerSplit, true)
|
|
2187
|
-
: ledger(ui, config, view, { period, r, summary, legacy, columns })),
|
|
2188
|
-
);
|
|
2090
|
+
out.push(ui.text(' '), ...ledger(ui, config, view, { period, r, summary, legacy, columns }));
|
|
2189
2091
|
}
|
|
2190
2092
|
if (summary.observed.replies) out.push(ui.text(' '), statsLine(ui, { ...summary.observed, turns: summary.turns }));
|
|
2191
2093
|
if (summary.observed.replies) {
|
|
2192
|
-
out.push(ui.text(' '), ...breakdownLines(ui,
|
|
2094
|
+
out.push(ui.text(' '), ...breakdownLines(ui, view, actions, summary, columns), ui.text(' '));
|
|
2193
2095
|
out.push(
|
|
2194
2096
|
...(view.usageCompare
|
|
2195
2097
|
? [
|
|
@@ -2198,10 +2100,10 @@ function usageTab(ui, config, view, _usage, actions, _modelOptions, columns, now
|
|
|
2198
2100
|
ui.dim(' · the same tokens on one model '),
|
|
2199
2101
|
ui.Button({ key: 'usage-compare', label: 'Trend', hotkey: 'c', onPress: actions.usageCompare }),
|
|
2200
2102
|
),
|
|
2201
|
-
...compareLines(ui,
|
|
2103
|
+
...compareLines(ui, summary),
|
|
2202
2104
|
]
|
|
2203
2105
|
: trendLines(ui, view, actions, summary, period, now)),
|
|
2204
|
-
...insightLines(ui, summary, actions, columns
|
|
2106
|
+
...insightLines(ui, summary, actions, columns),
|
|
2205
2107
|
);
|
|
2206
2108
|
}
|
|
2207
2109
|
out.push(
|
|
@@ -2218,8 +2120,8 @@ function helpLines(ui) {
|
|
|
2218
2120
|
return [
|
|
2219
2121
|
ui.text(' '),
|
|
2220
2122
|
ui.head('ABOUT THESE NUMBERS'),
|
|
2221
|
-
ui.dim('Cost, context and cache are Claude readings. $
|
|
2222
|
-
ui.dim('
|
|
2123
|
+
ui.dim('Cost, context and cache are Claude readings. Every $ is API prices:'),
|
|
2124
|
+
ui.dim('tokens × router.json list prices, as if paid per token, on a plan too.'),
|
|
2223
2125
|
ui.dim('Routing vs your model holds tokens and output length the same'),
|
|
2224
2126
|
ui.dim('and does not measure answer quality. Cache benefit is before writes.'),
|
|
2225
2127
|
ui.dim('The context bar uses the routed model’s window, 20% in reserve.'),
|
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).
|
|
359
359
|
export function allTime(usageStore, savingsStore) {
|
|
360
360
|
const record = readUsage(usageStore);
|
|
361
361
|
const summary = summarize(record, { from: null, to: null });
|
|
@@ -369,7 +369,6 @@ export function allTime(usageStore, savingsStore) {
|
|
|
369
369
|
routedUsd: summary.observed.routedUsd + legacy.routedUsd,
|
|
370
370
|
},
|
|
371
371
|
legacy,
|
|
372
|
-
summary,
|
|
373
372
|
};
|
|
374
373
|
}
|
|
375
374
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@alexeiled/claude-router",
|
|
3
|
-
"version": "1.20.
|
|
3
|
+
"version": "1.20.1",
|
|
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",
|