@alexeiled/claude-router 1.12.0 → 1.14.0

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": "1.12.0",
4
+ "version": "1.14.0",
5
5
  "description": "Model and effort routing for the main conversation by task difficulty and activity, advised by a prompt classifier (Jev, Clef, Clef Flash, OpenAI or local Ollama). Subagents get one model at spawn: every agent that does not pin one.",
6
6
  "author": {
7
7
  "name": "Alexei Ledenev",
package/CHANGELOG.md CHANGED
@@ -1,5 +1,36 @@
1
1
  # Changelog
2
2
 
3
+ ## 1.14.0 (2026-10-14)
4
+
5
+ Subagents now show which model each agent ran on, who picked it, and for which period. See [Understand usage and estimates](docs/user-guide.md#understand-usage-and-estimates).
6
+
7
+ ### Changed
8
+
9
+ - **SUBAGENTS** on the Usage tab follows the period row instead of summing every session since the last reset, and says its scope: `this session`, or `all projects` and the dates. Each agent is a square colored by the model it ran on, filled when the router moved it off Claude Code's pick. The routed types and the pass-throughs are one row each with agents, cost and the difference against Claude Code's pick, so a row no longer wraps; a row opens to its models. Each pass-through says why Claude Code picked the model.
10
+ - The band in a subagent's transcript names the agent's model and who picked it: `■ Haiku 5.5 · moved down by the router · Claude Code: Opus 5.5`, or `□ Opus 5.5 · Claude Code’s pick: the workflow sets it`.
11
+ - The Usage tab's scope line says `all projects` instead of `all sessions`: the records cover every project that uses this router install.
12
+ - Subagent records are kept by day and by model, version 2 under the same `subagents:v1:<session id>` keys. Records from before this version have no date or model: Session and All add them as one line.
13
+
14
+ ### Added
15
+
16
+ - **SUBAGENTS** on the Now tab, once this session started a subagent: how many run now, the squares, and what routing saved on them.
17
+
18
+ ## 1.13.0 (2026-10-13)
19
+
20
+ The Now tab shows this session and today instead of the last 30 replies, a window that matched no session, hour or day. See [Open the router pane](docs/user-guide.md#open-the-router-pane).
21
+
22
+ ### Changed
23
+
24
+ - **SESSION** replaces **LAST 30 REPLIES**. Its strip colors every reply of the session by tier; past 48 cells, or on a narrow pane, pairs of cells merge and the strip says how many replies a cell holds. After a restart of Claude Code the strip starts again and says since when. Its heading gives since when, the routed replies and the route switches. The switches are the ones the Usage tab counts, so a pin is not one. The replies per tier and per activity follow.
25
+ - **Pin next** replaces the TIERS ladder: one button per tier with the classifier's support, `▶` on the tier that runs now. The tab is four rows shorter.
26
+
27
+ ### Added
28
+
29
+ - **last switch** on the Now tab: when the route last changed, between which tiers, or between which routes inside a tier, and the activity. It includes the moves inside a turn that raise the `Model changed` toast.
30
+ - What routing saved or cost against your model this session, with the switch cache writes in it, and a **Usage** link that opens the Usage tab on Session.
31
+ - **TODAY**, once another session added to today: the same line for every session today, with a **Usage** link on Today.
32
+ - **WORTH A LOOK · today**: the Usage tab's first finding for today, from 20 replies, with its link to Routes or Policy.
33
+
3
34
  ## 1.12.0 (2026-10-13)
4
35
 
5
36
  The Usage tab now shows any period, not only this session and the time since the last reset. See [Compare routing with your model](docs/user-guide.md#compare-routing-with-your-model).
@@ -112,7 +112,7 @@ When a turn completes, the Mod labels it from the tool calls the assistant made
112
112
 
113
113
  Two stores hold counts:
114
114
 
115
- - **Session**: `activityStats` in the view, reset when the session ends. It has turns, requests, tokens, the list price of priced replies with their count, and routed replies by `model@effort` per activity, switches by tier and by activity, lateral moves taken and refused, and tool agreement. The label counted per activity is the applied activity in `on`. Tool agreement compares the answer that cleared `activityMass`, so it measures the classifier in both modes. The view also keeps an `activities` array aligned with the last 30 replies.
115
+ - **Session**: `activityStats` in the view, reset when the session ends. It has turns, requests, tokens, the list price of priced replies with their count, and routed replies by `model@effort` per activity, switches by tier and by activity, lateral moves taken and refused, and tool agreement. The label counted per activity is the applied activity in `on`. Tool agreement compares the answer that cleared `activityMass`, so it measures the classifier in both modes. The view also keeps `strip`, every reply since Claude Code started the session by tier in at most 48 cells that merge in pairs, with when its first reply arrived, and `lastSwitch`, the last route change with its tiers, routes and activity.
116
116
  - **Across sessions**: two `$.store` records per session. Each session's `activity:stats:v1:<session id>` holds a confusion matrix of the classifier's raw answer (including `uncertain` and `none`) against the observed bucket, run lengths per activity in five buckets, lateral switches taken and refused (from the decision's `lateral` field, so a hold or the cash gate counts), and `since`, its first count. A value with an unknown key or shape reads as empty; the `shadow` key that versions before 1.10.1 wrote is dropped on read and the rest is kept. Before 1.10.3 every session shared one `activity:stats:v1` key, read-modified-written each turn, so two sessions finishing turns together could lose a count and a stale write could undo a reset; that key now counts as one more record in the sum until **Delete history** deletes it, and 1.10.2 and earlier read only it. Each session's `activity:metrics:v1:<session id>` holds a classifier latency histogram per classifier id (22 buckets, at most 8 ids), the cheaper activity moves taken in `on` with the escalations that followed one, and `since`, its first reading; each part reads as empty on its own when its shape is wrong, as after a change of buckets. Both follow the usage records below: one writer per key, so sessions that finish turns at the same moment do not overwrite each other; this session's record held in memory and written after each turn that adds a count; the readout the sum of all records, latency kept to the first 8 classifier ids; and the same reset marker. Each record is bounded, and the records grow by one per session that recorded a count until **Delete history**. The view keeps the last sums read or written as `activityStore` and `activityMetrics`: read at session start and when the pane opens, replaced after each turn's write and after a reset. The open run is written when the session ends. **Delete history** clears the session counts, every stats and metrics record, and the usage records below.
117
117
 
118
118
  Nothing is recorded with `activityRouting: off`. Stats run inside a guard: a failed transcript read or store access loses that turn's counts and never fails the turn. Readings already in the session's metrics record stay in memory after a failed write and go out with the next turn that adds a reading. A turn from a session that has since changed is dropped.
@@ -131,7 +131,7 @@ A subagent's model is chosen once, in the `agent.spawn` hook, before its cache e
131
131
 
132
132
  `spawnAgent` in `hooks/native-router.mjs` passes the spawn through unchanged for a fork, a workflow agent (before the explicit check, since a workflow `agent({ model })` has `e.model` set), an explicit `e.model`, or a teammate (`passReason` in `lib/subagents.mjs`). Then `typeRoute` decides. A `subagents.types` entry wins; a key without a colon matches only the engine's built-in of that name. An unlisted built-in passes (`unlisted`), since its definition is not on disk. Any other agent is routed by its definition. `agentDefinition` finds the file once per provider and type in a session; a read that fails is tried again at the next spawn of the type. A plugin agent's `provider.plugin` is `plugin@marketplace`, the key of `<profile>/plugins/installed_plugins.json`, whose `installPath` entries hold `agents/*.md`. Other agents are looked up under the session's `.claude/agents`, then `<profile>/agents`. `agentFrontmatter` reads `name`, `model` and `modelRouting` from YAML or a one-line JSON object. No model, `inherit`, or `modelRouting: auto` is routed; any other model passes (`pinned`); a file not found, unreadable, or matches that disagree pass (`unknown`). A routed agent's type uses its models key, or for `classify` the active classifier is asked with the description and prompt alone, clipped to `context.maxTextChars`, with no history and no tool results. The answer maps to `subagents.heavy` when `P(high) ≥ heavyMass`, to `light` for an `explore` activity above `activityMass` or tier `micro`, else to `standard`. The spawn path has its own classifier client per classifier: its own failure count and pause, and no in-flight slot, so parallel spawns each get an answer and spawn failures never pause main-turn routing. Its deadline is the classifier's, capped at 3 seconds. That bounds how long a subagent waits to start. No advice, a missing key, a model `availableModels` blocks, or settings that cannot be read keep core's model. The router sends the configured full id, never an alias, because a family alias resolves to the parent's exact model when the families match. A `.catch` runs `next(e)`, so a failing hook spawns the agent as Claude Code would. Routing off (`/router off`, `/model`) or unavailable passes every spawn through and records nothing.
133
133
 
134
- Every spawn in `on` gets a record keyed by `agentId`, from `next(e)`'s answer. Its replies are priced in `turn.step` (`addAgentReply`), on the model they ran on and on core's model as `coreModelOf` estimates it (the definition's own model, else `CLAUDE_CODE_SUBAGENT_MODEL` except for Explore and Plan without `CLAUDE_CODE_SUBAGENT_MODEL_FORCE`, else `parentModel`). Cache writes are priced at the subagent lifetime (`subagentCacheTtl`). The record's counts go to this session's `$.store` key `subagents:v1:<session id>` at each of the agent's `turn.complete`s, and at session end for agents still running. They are counted per type and per pass-through reason, with respawns: a spawn of the type its parent loop finished one of in the last 10 minutes. The records follow the usage records: one writer per key, the readout `subagentStore` in the view is the sum, and the same reset marker applies. **Delete history** clears them too.
134
+ Every spawn in `on` gets a record keyed by `agentId`, from `next(e)`'s answer. Its replies are priced in `turn.step` (`addAgentReply`), on the model they ran on and on core's model as `coreModelOf` estimates it (the definition's own model, else `CLAUDE_CODE_SUBAGENT_MODEL` except for Explore and Plan without `CLAUDE_CODE_SUBAGENT_MODEL_FORCE`, else `parentModel`). Cache writes are priced at the subagent lifetime (`subagentCacheTtl`). The spawn record also keeps `move` (`moveOf`): `up` or `down` when the routed model's output price is above or below core's, `moved` when either has no price, null for the same model. The record's counts go to this session's `$.store` key `subagents:v1:<session id>` at each of the agent's `turn.complete`s, and at session end for agents still running. Since 1.14.0 the value is version 2, by local calendar day like the usage records, and days past 400 leave it when it is written: per day, per type and per pass-through reason, the agents, requests, priced requests, respawns (a spawn of the type its parent loop finished one of in the last 10 minutes) and classifier failures, and per model id the agents ran on, the agents, the agents moved, up and down, the routed cost and core's. An agent counts on the day of its first flush; its later requests and cost on the day of each flush. A version 1 value has no days or models: it reads as `undated` agents and cost, which only the Session and All periods add. The records follow the usage records: one writer per key, the view's `subagentStore` is every session's sum and `subagentSession` this session's, and the same reset marker applies. **Delete history** clears them too. The view's `subagentsRunning` counts the agents with a record between a spawn or a step and their turn's end; it is in memory, so a reload starts it over. The band in a subagent's transcript reads the agent's record from memory too.
135
135
 
136
136
  ## Classifier deadline and failure handling
137
137
 
@@ -136,27 +136,28 @@ Limits:
136
136
 
137
137
  ## Subagent routing
138
138
 
139
- Subagent routing has no measured result over time yet. It is `on` by default since 1.9. The Usage tab's **SUBAGENTS** section shows the counts kept across sessions since the last reset:
139
+ Subagent routing has no measured result over time yet. It is `on` by default since 1.9. The Usage tab's **SUBAGENTS** section shows the counts for the chosen period:
140
140
 
141
- - Per routed type: agents; **moved**, the agents whose decided model differs from the one they ran on; requests per agent; respawns; the choices by model; classifier failures; and `core → routed`, the list price of the agents' tokens on core's model against the decided one.
142
- - **Not routed**, the spawns that passed through, by reason (`fork`, `workflow`, `explicit`, `teammate`, `unlisted`, `pinned`, `unknown`), priced on the model they ran on. This is the share of subagent spend that routing cannot reach.
141
+ - Every agent by the model it ran on, filled when the router moved it off core's model, and what routing saved or cost on the routed agents.
142
+ - **ROUTED**, per type: agents, routed cost, and **vs CC**, the same tokens on core's model. Open, per model: the agents the router kept, moved up or moved down by output price, and their cost; requests per agent, respawns and classifier failures.
143
+ - **NOT ROUTED**, the spawns that passed through, by reason (`fork`, `workflow agent`, `explicit model`, `teammate`, `type not routed`, `pinned model`, `no definition`), priced on the model they ran on. This is the share of subagent spend that routing cannot reach.
143
144
 
144
145
  Method:
145
146
 
146
- - `routed` is the reply on the routed model and `core` the same tokens on core's model as the router estimates it: `CLAUDE_CODE_SUBAGENT_MODEL`, except for Explore and Plan without `CLAUDE_CODE_SUBAGENT_MODEL_FORCE`, else the parent's model. A subagent starts with a cold cache on one model and keeps it, so its own token counts on another model are a fair counterfactual. `ratesAt` applies Haiku 5.5's 5x rate above 100,000 prompt tokens. Explore agents often pass that, so Haiku can cost more than its base price suggests.
147
+ - The routed cost is the reply on the routed model and **vs CC** the same tokens on core's model as the router estimates it: `CLAUDE_CODE_SUBAGENT_MODEL`, except for Explore and Plan without `CLAUDE_CODE_SUBAGENT_MODEL_FORCE`, else the parent's model. A subagent starts with a cold cache on one model and keeps it, so its own token counts on another model are a fair counterfactual. `ratesAt` applies Haiku 5.5's 5x rate above 100,000 prompt tokens. Explore agents often pass that, so Haiku can cost more than its base price suggests.
147
148
  - Cache writes are priced at the subagent lifetime: five minutes unless `FORCE_PROMPT_CACHING_5M`, `CLAUDE_CODE_SUBAGENT_PROMPT_CACHE_TTL`, `subagentPromptCacheTtl` or `ENABLE_PROMPT_CACHING_1H` say otherwise, on a subscription too.
148
149
  - The counts cannot see quality. Two proxies stand in for it: requests per agent, and **respawns**, a spawn of the same type by the same parent within 10 minutes after one finished.
149
150
 
150
151
  Checks:
151
152
 
152
- - `test/subagents.test.mjs` covers each pass reason, the pin rule, the classify mapping, core's model estimate, the subagent lifetime, Haiku's long-context price, and the store's merge, reset and bad values. `test/hook-subagents.test.mjs` covers `on` (the routed model), a fork, an explicit model, a teammate, a workflow agent and a pinned project agent (each passes), a classifier failure (core's model), parallel spawns, a spawn-path pause that leaves main routing alone, respawns, session end, Delete history and the Usage tab.
153
+ - `test/subagents.test.mjs` covers each pass reason, the pin rule, the classify mapping, core's model estimate, the router's move, the subagent lifetime, Haiku's long-context price, and the store's days, merge, reset, bad values and records from before 1.14.0. `test/hook-subagents.test.mjs` covers `on` (the routed model), a fork, an explicit model, a teammate, a workflow agent and a pinned project agent (each passes), a classifier failure (core's model), parallel spawns, a spawn-path pause that leaves main routing alone, respawns, session end, Delete history, and the Usage and Now tabs. `test/usage-view.test.mjs` covers the block by period, an open row, a narrow pane and undated records; `test/hook-band.test.mjs` the band in a subagent's transcript.
153
154
  - `experiments/mod-router/results/agent-spawn-probe.json` records what Claude Code 2.1.296 does with a spawn's model, frontmatter and workflow agents.
154
155
  - `experiments/mod-router/results/subagent-routing-live.json` is a live `on` run on 2026-10-10 with Sonnet as the parent. Explore was sent Haiku and ran on it. general-purpose was classified `standard`. A pinned project agent and an explicit `opus` call passed through. The store counted each one.
155
156
 
156
157
  When to turn it `on`:
157
158
 
158
- - `routed` is below `core` for the routed types, by enough to matter;
159
- - the choices look right for the tasks: `light` for searches and reads, `heavy` rarely;
159
+ - **vs CC** is below zero for the routed types, by enough to matter;
160
+ - the models look right for the tasks: Haiku for searches and reads, Opus rarely;
160
161
  - **Not routed** leaves enough routable spend to bother.
161
162
 
162
163
  Keep it if requests per agent and respawns per type stay no higher than before you turned it on. Otherwise change `types` or `heavyMass`, exclude a type with `null`, or set `subagentRouting` to `off`.
@@ -29,14 +29,14 @@ Mode belongs to a Claude Code session. Clear starts a new session with routing o
29
29
 
30
30
  ## Router pane
31
31
 
32
- The status band is one line above the prompt: a tier meter, the activity, the route, a short reason, classifier support, and context and cache use. Segments drop by priority when the band is narrow: classifier support first, then context and cache, then the activity, then the reason. Hovering reveals pins, **Turn off**, and a two-row view; while routing is off, **Turn on** sits on the band itself, so the band carries one routing control at a time. A fresh session that starts with routing off because of its model shows `<model> is not a routing tier` on the band until the mode changes. The band yields to surveys. In a subagent's transcript it reads `subagent model chosen at spawn`, or `subagents keep their own model` with subagent routing off. A model change between turns raises a toast. A pin, or a step that changes only the effort, such as `medium` to `high` on the defaults, raises none. While the classifier runs, the turn's spinner says `Choosing model`. In Manual mode or when routing is unavailable, the prompt footer carries `routing off` or `routing unavailable`. The **Router** button opens the pane. The pane has five tabs, Now, Routes, Policy, Classifier, and Usage, under one line with the routing on/off pair and the classifier state. The [user guide](user-guide.md#open-the-router-pane) describes each tab.
32
+ The status band is one line above the prompt: a tier meter, the activity, the route, a short reason, classifier support, and context and cache use. Segments drop by priority when the band is narrow: classifier support first, then context and cache, then the activity, then the reason. Hovering reveals pins, **Turn off**, and a two-row view; while routing is off, **Turn on** sits on the band itself, so the band carries one routing control at a time. A fresh session that starts with routing off because of its model shows `<model> is not a routing tier` on the band until the mode changes. The band yields to surveys. In a subagent's transcript it names the agent's model and who picked it, such as `■ Haiku 5.5 · moved down by the router · Claude Code: Opus 5.5`; without a record of the agent it reads `subagent model chosen at spawn`, or `subagents keep their own model` with subagent routing off. A model change between turns raises a toast. A pin, or a step that changes only the effort, such as `medium` to `high` on the defaults, raises none. While the classifier runs, the turn's spinner says `Choosing model`. In Manual mode or when routing is unavailable, the prompt footer carries `routing off` or `routing unavailable`. The **Router** button opens the pane. The pane has five tabs, Now, Routes, Policy, Classifier, and Usage, under one line with the routing on/off pair and the classifier state. The [user guide](user-guide.md#open-the-router-pane) describes each tab.
33
33
 
34
34
  | Reading | Meaning and limits |
35
35
  | ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
36
36
  | Next turn / Served | The requested model and effort, with the tier's own model beside an activity override. **Served** appears only when the engine answered with another model. Actual effort is not reported. |
37
37
  | Classifier support | Per-tier probabilities from the last classification; under **Why**, the support for the switch against the bar the policy required, and the switch cost. Pins and skipped calls leave it empty. |
38
38
  | Activity | The classifier's activity choice as a verb with its share, the two next-best answers, and the threshold at which an activity applies; `uncertain` shown dim. Empty with routing off, a pin, or no answer. |
39
- | Last replies | The tier that served each of the last 30 main-conversation replies, a dot where the router did not choose, the model switches between them, and the replies per tier and per activity. |
39
+ | Session and today (Now) | Every main-conversation reply since Claude Code started the session as a strip colored by tier, pairs of cells merging past 48 cells or on a narrow pane; a dot where the router did not serve, and `since HH:MM` once a restart started the strip again. The replies per tier and per activity, the route switches and the last one, and routing against your model for the session and, once another session added to it, for today; today's first finding worth a look. |
40
40
  | Routing vs your model (Usage) | For a period (this session, today, 7 or 30 days, this month, or all), routed replies at configured list prices against the same tokens on your model, the model `/model` selected at the session effort when each reply ran: a ledger from your model through cheaper models, stronger models and switch cache writes to routed; tokens and cache hit. `early sample` below 10 replies. Output length is held the same; answer quality is not measured. |
41
41
  | Breakdown (Usage) | The period's replies, cost and difference against your model by activity, model or tier, each row opening to its routes or activities; the cost per hour, day or week, or **What if**, the same tokens on each model alone; from 20 replies, the cells worth a look, linked to Routes or Policy. |
42
42
  | Across sessions (Classifier) | The counts kept since the last reset: labelled turns, tool agreement on the classifier's raw answer, overall and for `code`, `ops` and `explore`, the two largest mismatches, activity moves inside a tier taken and refused, and escalations after a cheaper activity move. The active classifier's p95 latency shows on its **Deadline** line. `/router` text shows the agreement. |
@@ -1,12 +1,12 @@
1
- <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 657 458" role="img" aria-labelledby="title desc">
1
+ <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 665 610" role="img" aria-labelledby="title desc">
2
2
  <title id="title">Router pane, Now tab</title>
3
- <desc id="desc">What runs next turn: tier, model and activity, with the reason and the classifier support it weighed; classifier support per tier with pin buttons; the last 20 replies colored by tier with the switch count and the replies per tier and per activity; and context, cache and cost.</desc>
3
+ <desc id="desc">What runs next turn: tier, model and activity, with the reason and the classifier support it weighed; one pin button per tier with its support; this session since its first reply, as a strip of every reply colored by tier, with the replies per tier and per activity, the last route switch and what routing saved against your model; today across sessions; this session’s subagents as squares by model, one running, with what routing saved on them; today’s first finding worth a look with a link to Routes; and context, cache and cost.</desc>
4
4
  <style>
5
5
  text { font-family: ui-monospace, SFMono-Regular, Menlo, Consolas, 'Liberation Mono', monospace; font-size: 13px; }
6
6
  .cap { font-family: system-ui, -apple-system, 'Segoe UI', sans-serif; font-size: 12px; fill: #9a988f; }
7
7
  </style>
8
- <rect width="657" height="458" rx="8" fill="#1c1c1c"/>
9
- <rect x="10" y="10" width="637" height="438" rx="6" fill="none" stroke="#3f5f8f"/>
8
+ <rect width="665" height="610" rx="8" fill="#1c1c1c"/>
9
+ <rect x="10" y="10" width="645" height="590" rx="6" fill="none" stroke="#3f5f8f"/>
10
10
  <text x="24.0" y="34" fill="#5fafd7" font-weight="700" xml:space="preserve">ROUTING</text>
11
11
  <rect x="94.2" y="20" width="62.4" height="18" rx="4" fill="#87afff"/>
12
12
  <text x="94.2" y="34" fill="#0d1016" font-weight="700" xml:space="preserve">[ ◉ on ]</text>
@@ -36,77 +36,132 @@
36
36
  <text x="24.0" y="129" fill="#d0d0d0" xml:space="preserve">Why </text>
37
37
  <text x="109.8" y="129" fill="#d0d0d0" xml:space="preserve">clear need for a stronger model</text>
38
38
  <text x="24.0" y="148" fill="#7c7c7c" xml:space="preserve"> Jev gave stronger tiers 88% (needs 82%) · switch ≈ $0.48</text>
39
- <text x="24.0" y="186" fill="#5fafd7" font-weight="700" xml:space="preserve">TIERS</text>
40
- <text x="63.0" y="186" fill="#7c7c7c" xml:space="preserve"> · Jev support on the last turn · pin = next turn only</text>
41
- <text x="24.0" y="205" fill="#e0708a" font-weight="700" xml:space="preserve">▶ </text>
42
- <text x="39.6" y="205" fill="#e0708a" font-weight="700" xml:space="preserve">high </text>
43
- <text x="102.0" y="205" fill="#d0d0d0" xml:space="preserve">Opus 5.5 · xhigh </text>
44
- <text x="273.6" y="205" fill="#e0708a" xml:space="preserve">█████████░</text>
45
- <text x="351.6" y="205" fill="#d0d0d0" xml:space="preserve"> 88% </text>
46
- <rect x="406.2" y="191" width="54.6" height="18" rx="4" fill="#2e3340"/>
47
- <text x="406.2" y="205" fill="#d0d0d0" xml:space="preserve">[ pin ]</text>
48
- <text x="39.6" y="224" fill="#d7af5f" font-weight="700" xml:space="preserve">medium </text>
49
- <text x="102.0" y="224" fill="#d0d0d0" xml:space="preserve">Opus 5.5 · medium </text>
50
- <text x="273.6" y="224" fill="#d7af5f" xml:space="preserve">█░░░░░░░░░</text>
51
- <text x="351.6" y="224" fill="#d0d0d0" xml:space="preserve"> 7% </text>
52
- <rect x="406.2" y="210" width="54.6" height="18" rx="4" fill="#2e3340"/>
53
- <text x="406.2" y="224" fill="#d0d0d0" xml:space="preserve">[ pin ]</text>
54
- <text x="39.6" y="243" fill="#5f9fe0" font-weight="700" xml:space="preserve">low </text>
55
- <text x="102.0" y="243" fill="#d0d0d0" xml:space="preserve">Haiku 5.5 · high </text>
56
- <text x="273.6" y="243" fill="#5f9fe0" xml:space="preserve">░░░░░░░░░░</text>
57
- <text x="351.6" y="243" fill="#d0d0d0" xml:space="preserve"> 3% </text>
58
- <rect x="406.2" y="229" width="54.6" height="18" rx="4" fill="#2e3340"/>
59
- <text x="406.2" y="243" fill="#d0d0d0" xml:space="preserve">[ pin ]</text>
60
- <text x="39.6" y="262" fill="#5fd7af" font-weight="700" xml:space="preserve">micro </text>
61
- <text x="102.0" y="262" fill="#d0d0d0" xml:space="preserve">Haiku 5.5 · medium </text>
62
- <text x="273.6" y="262" fill="#5fd7af" xml:space="preserve">░░░░░░░░░░</text>
63
- <text x="351.6" y="262" fill="#d0d0d0" xml:space="preserve"> 2% </text>
64
- <rect x="406.2" y="248" width="54.6" height="18" rx="4" fill="#2e3340"/>
65
- <text x="406.2" y="262" fill="#d0d0d0" xml:space="preserve">[ pin ]</text>
66
- <text x="24.0" y="300" fill="#5fafd7" font-weight="700" xml:space="preserve">LAST 20 REPLIES</text>
67
- <text x="141.0" y="300" fill="#7c7c7c" xml:space="preserve"> · 7 model switches</text>
68
- <text x="39.6" y="319" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
69
- <text x="47.4" y="319" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
70
- <text x="55.2" y="319" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
71
- <text x="63.0" y="319" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
72
- <text x="70.8" y="319" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
73
- <text x="78.6" y="319" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
74
- <text x="86.4" y="319" fill="#d7af5f" font-weight="700" xml:space="preserve">█</text>
75
- <text x="94.2" y="319" fill="#d7af5f" font-weight="700" xml:space="preserve">█</text>
76
- <text x="102.0" y="319" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
77
- <text x="109.8" y="319" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
78
- <text x="117.6" y="319" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
79
- <text x="125.4" y="319" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
80
- <text x="133.2" y="319" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
81
- <text x="141.0" y="319" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
82
- <text x="148.8" y="319" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
83
- <text x="156.6" y="319" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
84
- <text x="164.4" y="319" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
85
- <text x="172.2" y="319" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
86
- <text x="180.0" y="319" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
87
- <text x="187.8" y="319" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
88
- <text x="39.6" y="338" fill="#5f9fe0" font-weight="700" xml:space="preserve">■ </text>
89
- <text x="55.2" y="338" fill="#d0d0d0" xml:space="preserve">low 10 </text>
90
- <text x="117.6" y="338" fill="#d7af5f" font-weight="700" xml:space="preserve">■ </text>
91
- <text x="133.2" y="338" fill="#d0d0d0" xml:space="preserve">medium 2 </text>
92
- <text x="211.2" y="338" fill="#e0708a" font-weight="700" xml:space="preserve">■ </text>
93
- <text x="226.8" y="338" fill="#d0d0d0" xml:space="preserve">high 8 </text>
94
- <text x="39.6" y="357" fill="#d7875f" font-style="italic" xml:space="preserve">coding</text>
95
- <text x="86.4" y="357" fill="#7c7c7c" xml:space="preserve"> 12 · </text>
96
- <text x="133.2" y="357" fill="#d7875f" font-style="italic" xml:space="preserve">exploring</text>
97
- <text x="203.4" y="357" fill="#7c7c7c" xml:space="preserve"> 4 · </text>
98
- <text x="242.4" y="357" fill="#d7875f" font-style="italic" xml:space="preserve">planning</text>
99
- <text x="304.8" y="357" fill="#7c7c7c" xml:space="preserve"> 2 · </text>
100
- <text x="343.8" y="357" fill="#d7875f" font-style="italic" xml:space="preserve">running</text>
101
- <text x="398.4" y="357" fill="#7c7c7c" xml:space="preserve"> 2</text>
102
- <text x="24.0" y="395" fill="#87d787" xml:space="preserve">Context ██████░░░░░░░░░░ 40% ~402.9K / 1.00M</text>
103
- <text x="24.0" y="414" fill="#87d787" xml:space="preserve">Cache </text>
104
- <text x="94.2" y="414" fill="#87d787" xml:space="preserve">100% reused on the last reply</text>
105
- <text x="320.4" y="414" fill="#7c7c7c" xml:space="preserve"> · </text>
106
- <text x="359.4" y="414" fill="#d0d0d0" xml:space="preserve">cost $18.003 </text>
107
- <text x="460.8" y="414" fill="#7c7c7c" xml:space="preserve">by Claude </text>
108
- <rect x="546.6" y="400" width="85.8" height="18" rx="4" fill="#2e3340"/>
109
- <text x="546.6" y="414" fill="#d0d0d0" xml:space="preserve">[ details ]</text>
110
- <rect x="24.0" y="419" width="70.2" height="18" rx="4" fill="#2e3340"/>
111
- <text x="24.0" y="433" fill="#d0d0d0" xml:space="preserve">[ Close ]</text>
39
+ <text x="24.0" y="167" fill="#d0d0d0" xml:space="preserve">Pin next </text>
40
+ <rect x="109.8" y="153" width="109.2" height="18" rx="4" fill="#2e3340"/>
41
+ <text x="109.8" y="167" fill="#d0d0d0" xml:space="preserve">[ ▶ high 88% ]</text>
42
+ <rect x="226.8" y="153" width="101.4" height="18" rx="4" fill="#2e3340"/>
43
+ <text x="226.8" y="167" fill="#d0d0d0" xml:space="preserve">[ medium 7% ]</text>
44
+ <rect x="336.0" y="153" width="78.0" height="18" rx="4" fill="#2e3340"/>
45
+ <text x="336.0" y="167" fill="#d0d0d0" xml:space="preserve">[ low 3% ]</text>
46
+ <rect x="421.8" y="153" width="93.6" height="18" rx="4" fill="#2e3340"/>
47
+ <text x="421.8" y="167" fill="#d0d0d0" xml:space="preserve">[ micro 2% ]</text>
48
+ <text x="523.2" y="167" fill="#7c7c7c" xml:space="preserve"> next turn only</text>
49
+ <text x="24.0" y="205" fill="#5fafd7" font-weight="700" xml:space="preserve">SESSION</text>
50
+ <text x="78.6" y="205" fill="#7c7c7c" xml:space="preserve"> · since 14:18 · 86 routed replies · 9 route switches</text>
51
+ <text x="39.6" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
52
+ <text x="47.4" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
53
+ <text x="55.2" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
54
+ <text x="63.0" y="224" fill="#d7af5f" font-weight="700" xml:space="preserve">█</text>
55
+ <text x="70.8" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
56
+ <text x="78.6" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
57
+ <text x="86.4" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
58
+ <text x="94.2" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
59
+ <text x="102.0" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
60
+ <text x="109.8" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
61
+ <text x="117.6" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
62
+ <text x="125.4" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
63
+ <text x="133.2" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
64
+ <text x="141.0" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
65
+ <text x="148.8" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
66
+ <text x="156.6" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
67
+ <text x="164.4" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
68
+ <text x="172.2" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
69
+ <text x="180.0" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
70
+ <text x="187.8" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
71
+ <text x="195.6" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
72
+ <text x="203.4" y="224" fill="#d7af5f" font-weight="700" xml:space="preserve">█</text>
73
+ <text x="211.2" y="224" fill="#d7af5f" font-weight="700" xml:space="preserve">█</text>
74
+ <text x="219.0" y="224" fill="#d7af5f" font-weight="700" xml:space="preserve">█</text>
75
+ <text x="226.8" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
76
+ <text x="234.6" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
77
+ <text x="242.4" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
78
+ <text x="250.2" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
79
+ <text x="258.0" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
80
+ <text x="265.8" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
81
+ <text x="273.6" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
82
+ <text x="281.4" y="224" fill="#5f9fe0" font-weight="700" xml:space="preserve">█</text>
83
+ <text x="289.2" y="224" fill="#d7af5f" font-weight="700" xml:space="preserve">█</text>
84
+ <text x="297.0" y="224" fill="#d7af5f" font-weight="700" xml:space="preserve">█</text>
85
+ <text x="304.8" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
86
+ <text x="312.6" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
87
+ <text x="320.4" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
88
+ <text x="328.2" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
89
+ <text x="336.0" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
90
+ <text x="343.8" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
91
+ <text x="351.6" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
92
+ <text x="359.4" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
93
+ <text x="367.2" y="224" fill="#e0708a" font-weight="700" xml:space="preserve">█</text>
94
+ <text x="375.0" y="224" fill="#7c7c7c" xml:space="preserve"> 2 replies per cell</text>
95
+ <text x="39.6" y="243" fill="#5f9fe0" font-weight="700" xml:space="preserve">■ </text>
96
+ <text x="55.2" y="243" fill="#d0d0d0" xml:space="preserve">low 41 </text>
97
+ <text x="117.6" y="243" fill="#d7af5f" font-weight="700" xml:space="preserve">■ </text>
98
+ <text x="133.2" y="243" fill="#d0d0d0" xml:space="preserve">medium 12 </text>
99
+ <text x="219.0" y="243" fill="#e0708a" font-weight="700" xml:space="preserve">■ </text>
100
+ <text x="234.6" y="243" fill="#d0d0d0" xml:space="preserve">high 33 </text>
101
+ <text x="39.6" y="262" fill="#d7875f" font-style="italic" xml:space="preserve">coding</text>
102
+ <text x="86.4" y="262" fill="#7c7c7c" xml:space="preserve"> 45 · </text>
103
+ <text x="133.2" y="262" fill="#d7875f" font-style="italic" xml:space="preserve">running</text>
104
+ <text x="187.8" y="262" fill="#7c7c7c" xml:space="preserve"> 26 · </text>
105
+ <text x="234.6" y="262" fill="#d7875f" font-style="italic" xml:space="preserve">exploring</text>
106
+ <text x="304.8" y="262" fill="#7c7c7c" xml:space="preserve"> 15</text>
107
+ <text x="39.6" y="281" fill="#7c7c7c" xml:space="preserve">last switch 15:38 </text>
108
+ <text x="187.8" y="281" fill="#d7af5f" font-weight="700" xml:space="preserve">medium</text>
109
+ <text x="234.6" y="281" fill="#7c7c7c" xml:space="preserve"> → </text>
110
+ <text x="258.0" y="281" fill="#e0708a" font-weight="700" xml:space="preserve">high</text>
111
+ <text x="289.2" y="281" fill="#7c7c7c" xml:space="preserve"> · </text>
112
+ <text x="312.6" y="281" fill="#d7875f" font-style="italic" xml:space="preserve">coding</text>
113
+ <text x="39.6" y="300" fill="#d0d0d0" xml:space="preserve">Routing saved </text>
114
+ <text x="148.8" y="300" fill="#6fcf97" font-weight="700" xml:space="preserve">$4.17 (39%)</text>
115
+ <text x="234.6" y="300" fill="#d0d0d0" xml:space="preserve"> vs your model</text>
116
+ <text x="343.8" y="300" fill="#7c7c7c" xml:space="preserve"> · switch writes $0.19</text>
117
+ <rect x="531.0" y="286" width="70.2" height="18" rx="4" fill="#2e3340"/>
118
+ <text x="531.0" y="300" fill="#d0d0d0" xml:space="preserve">[ Usage ]</text>
119
+ <text x="24.0" y="338" fill="#5fafd7" font-weight="700" xml:space="preserve">TODAY</text>
120
+ <text x="63.0" y="338" fill="#7c7c7c" xml:space="preserve"> · 104 routed replies · 12 route switches</text>
121
+ <text x="39.6" y="357" fill="#d0d0d0" xml:space="preserve">Routing saved </text>
122
+ <text x="148.8" y="357" fill="#6fcf97" font-weight="700" xml:space="preserve">$5.16 (40%)</text>
123
+ <text x="234.6" y="357" fill="#d0d0d0" xml:space="preserve"> vs your model</text>
124
+ <text x="343.8" y="357" fill="#7c7c7c" xml:space="preserve"> · switch writes $0.23</text>
125
+ <rect x="531.0" y="343" width="70.2" height="18" rx="4" fill="#2e3340"/>
126
+ <text x="531.0" y="357" fill="#d0d0d0" xml:space="preserve">[ Usage ]</text>
127
+ <text x="24.0" y="395" fill="#5fafd7" font-weight="700" xml:space="preserve">SUBAGENTS</text>
128
+ <text x="94.2" y="395" fill="#7c7c7c" xml:space="preserve"> · this session</text>
129
+ <text x="211.2" y="395" fill="#d7af5f" xml:space="preserve"> · ● 1 running</text>
130
+ <rect x="336.0" y="381" width="70.2" height="18" rx="4" fill="#2e3340"/>
131
+ <text x="336.0" y="395" fill="#d0d0d0" xml:space="preserve">[ Usage ]</text>
132
+ <text x="39.6" y="414" fill="#c3e88d" xml:space="preserve">■■</text>
133
+ <text x="55.2" y="414" fill="#c792ea" xml:space="preserve">■</text>
134
+ <text x="63.0" y="414" fill="#c792ea" xml:space="preserve">□□□</text>
135
+ <text x="102.0" y="414" fill="#c3e88d" xml:space="preserve">Haiku 5.5 2</text>
136
+ <text x="187.8" y="414" fill="#7c7c7c" xml:space="preserve"> · </text>
137
+ <text x="211.2" y="414" fill="#c792ea" xml:space="preserve">Opus 5.5 4</text>
138
+ <text x="24.0" y="433" fill="#d0d0d0" xml:space="preserve"> 6 agents</text>
139
+ <text x="102.0" y="433" fill="#7c7c7c" xml:space="preserve"> · </text>
140
+ <text x="125.4" y="433" fill="#d0d0d0" xml:space="preserve">■ 3 moved by the router</text>
141
+ <text x="304.8" y="433" fill="#7c7c7c" xml:space="preserve"> · </text>
142
+ <text x="328.2" y="433" fill="#d0d0d0" xml:space="preserve">□ 3 on Claude Code’s pick</text>
143
+ <text x="24.0" y="452" fill="#d0d0d0" xml:space="preserve"> Routing cost </text>
144
+ <text x="141.0" y="452" fill="#f0b429" xml:space="preserve">$0.08</text>
145
+ <text x="180.0" y="452" fill="#d0d0d0" xml:space="preserve"> more</text>
146
+ <text x="219.0" y="452" fill="#d0d0d0" xml:space="preserve"> (7%)</text>
147
+ <text x="258.0" y="452" fill="#7c7c7c" xml:space="preserve"> on 3 routed agents</text>
148
+ <text x="24.0" y="490" fill="#5fafd7" font-weight="700" xml:space="preserve">WORTH A LOOK</text>
149
+ <text x="117.6" y="490" fill="#7c7c7c" xml:space="preserve"> · today</text>
150
+ <text x="39.6" y="509" fill="#d7875f" font-style="italic" xml:space="preserve">coding</text>
151
+ <text x="86.4" y="509" fill="#7c7c7c" xml:space="preserve"> · </text>
152
+ <text x="109.8" y="509" fill="#e0708a" font-weight="700" xml:space="preserve">high</text>
153
+ <text x="141.0" y="509" fill="#d0d0d0" xml:space="preserve"> carried 61% of the cost</text>
154
+ <text x="328.2" y="509" fill="#7c7c7c" xml:space="preserve"> · mostly Opus 5.5 · xhigh</text>
155
+ <rect x="546.6" y="495" width="78.0" height="18" rx="4" fill="#2e3340"/>
156
+ <text x="546.6" y="509" fill="#d0d0d0" xml:space="preserve">[ Routes ]</text>
157
+ <text x="24.0" y="547" fill="#87d787" xml:space="preserve">Context ██████░░░░░░░░░░ 40% ~402.9K / 1.00M</text>
158
+ <text x="24.0" y="566" fill="#87d787" xml:space="preserve">Cache </text>
159
+ <text x="94.2" y="566" fill="#87d787" xml:space="preserve">100% reused on the last reply</text>
160
+ <text x="320.4" y="566" fill="#7c7c7c" xml:space="preserve"> · </text>
161
+ <text x="359.4" y="566" fill="#d0d0d0" xml:space="preserve">cost $18.003 </text>
162
+ <text x="460.8" y="566" fill="#7c7c7c" xml:space="preserve">by Claude </text>
163
+ <rect x="546.6" y="552" width="85.8" height="18" rx="4" fill="#2e3340"/>
164
+ <text x="546.6" y="566" fill="#d0d0d0" xml:space="preserve">[ details ]</text>
165
+ <rect x="24.0" y="571" width="70.2" height="18" rx="4" fill="#2e3340"/>
166
+ <text x="24.0" y="585" fill="#d0d0d0" xml:space="preserve">[ Close ]</text>
112
167
  </svg>