Files
cortiq-gateway/web/js/views/routing.js
T
infosave2007 95e560dc72 feat: per-key spend accounting and per-task complexity pinning
API keys page: the table now answers "which department spends what" — per-key
requests, tokens in/out and cost for a selectable window (24h/7d/30d) plus a
cumulative all-time cost column, joined from stats by the key's account.

The stats log stays bounded while the accounting survives: once stats.jsonl
exceeds max_file_mb (default 16, 0 disables), records older than the
retention window fold into cumulative per-account totals in a small sidecar
file (tmp+rename on both) and leave the log. alltime = folded + in-file, a
record is never counted twice, verified end-to-end on synthetic data
(1.2 MB → 301 KB, totals identical before/after compaction and restarts).

Routing: a task rule can now PIN the complexity tier —
`[routing.tasks.legal] models=[...] tier="high"` (old plain-array rules parse
unchanged). The pinned tier replaces the router's verdict before the
escalation check and reports itself as route_source "router+task-rule@high".
The Routing page grows a per-task «Complexity» selector (Auto/low/medium/
high); verified live: a code prompt with a pinned high went
router+task-rule@high → the expensive model.

13 new strings in all 7 languages; docs/ROUTING(.ru) updated.
2026-08-08 08:42:11 +03:00

276 lines
9.7 KiB
JavaScript
Vendored
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
// Routing — tier editor (ordered model chips), default model, and policy.
import { h, mount, toast } from "../ui.js";
import { t } from "../i18n.js";
import { api } from "../api.js";
import { appState } from "../app.js";
// Known labels of the hosted taxonomy — used for localized names/descriptions
// and as the offline fallback; the live list comes from /routing/labels.
const TASK_META = {
chitchat: { icon: "💬" },
code: { icon: "⌨" },
"creative-writing": { icon: "✍" },
extraction: { icon: "📑" },
math: { icon: "∑" },
qa: { icon: "❓" },
summarization: { icon: "📋" },
translation: { icon: "🌍" },
};
export async function renderRouting() {
const meta = appState.meta || (await api.meta());
const [routing, modelsData] = await Promise.all([api.getRouting(), api.listModels()]);
const ids = (modelsData.models || []).map((m) => m.id);
// Task labels: live from the router when reachable, built-in set otherwise;
// labels that already have a rule are always shown (custom taxonomies).
let taskLabels = Object.keys(TASK_META);
let labelsSource = "builtin";
try {
const r = await api.routingLabels();
if (r.labels && r.labels.length) {
taskLabels = r.labels;
labelsSource = "router";
}
} catch {
/* offline — builtin list */
}
for (const k of Object.keys(routing.tasks || {})) {
if (!taskLabels.includes(k)) taskLabels.push(k);
}
// Share of recent traffic per task — shows which rules actually matter.
let taskShare = {};
try {
const stat = await api.stats("7d", "label");
const total = (stat.breakdown || []).reduce((a, b) => a + (b.requests || 0), 0);
if (total > 0) {
for (const b of stat.breakdown || []) taskShare[b.key] = (b.requests || 0) / total;
}
} catch {
/* no stats yet */
}
// local editable state — ensure standard tiers exist for a friendly editor
const tiers = Object.assign({ low: [], medium: [], high: [] }, routing.tiers || {});
const tasks = {};
const taskTiers = {};
for (const l of taskLabels) {
const v = (routing.tasks || {})[l];
// GET returns the full form {models, tier}; older configs may be arrays
tasks[l] = Array.isArray(v) ? v : (v && v.models) || [];
taskTiers[l] = (v && !Array.isArray(v) && v.tier) || "";
}
const st = {
tiers,
tasks,
taskTiers,
default: routing.default || ids[0] || "",
policy: routing.policy || { mode: "fixed_table", min_class: {} },
};
const root = h("div");
function moveChip(map, key, i, dir) {
const arr = map[key];
const ni = i + dir;
if (ni < 0 || ni >= arr.length) return;
[arr[i], arr[ni]] = [arr[ni], arr[i]];
render();
}
function removeChip(map, key, i) {
map[key].splice(i, 1);
render();
}
function addChip(map, key, id) {
if (id && !map[key].includes(id)) map[key].push(id);
render();
}
function chipEditor(map, key, emptyLabel) {
const arr = map[key];
const avail = ids.filter((id) => !arr.includes(id));
const addSel = h(
"select",
{ style: "width:auto", onChange: (e) => addChip(map, key, e.target.value) },
h("option", { value: "" }, t("routing.addModel")),
...avail.map((id) => h("option", { value: id }, id))
);
return h(
"div",
{ class: "chips" },
arr.length === 0 && emptyLabel ? h("span", { class: "muted small chips-empty" }, emptyLabel) : null,
...arr.map((id, i) =>
h(
"div",
{ class: "chip" },
h("span", { class: "ord" }, i + 1),
id,
h("span", { class: "arrow", title: "←", onClick: () => moveChip(map, key, i, -1) }, "◄"),
h("span", { class: "arrow", title: "→", onClick: () => moveChip(map, key, i, 1) }, "►"),
h("span", { class: "x", onClick: () => removeChip(map, key, i) }, "×")
)
),
avail.length ? addSel : null
);
}
function tierRow(tier) {
return h(
"div",
{ class: "tierrow" },
h("div", { class: "tname" }, h("span", { class: "badge tier-" + tier }, tier)),
chipEditor(st.tiers, tier)
);
}
function taskRow(label) {
const known = TASK_META[label];
const name = known ? t("task." + label) : label;
const share = taskShare[label];
return h(
"div",
{ class: "tierrow taskrow" },
h(
"div",
{ class: "tname taskname" },
h("div", {}, (known ? known.icon + " " : "") + name),
h("div", { class: "muted small mono" }, label),
share != null ? h("div", { class: "muted small" }, t("routing.tasks.share", { p: Math.round(share * 100) })) : null
),
chipEditor(st.tasks, label, t("routing.tasks.inherit")),
tierSelect(label)
);
}
// Per-task complexity pin: "авто" follows the router's verdict; a fixed
// tier forces it for this task (legal is always high, chitchat always low)
function tierSelect(label) {
const sel = h(
"select",
{ class: "task-tier", title: t("routing.tasks.tierHint") },
h("option", { value: "" }, t("routing.tasks.tierAuto")),
...Object.keys(st.tiers).map((tr) =>
h("option", { value: tr, selected: st.taskTiers[label] === tr ? "" : null }, tr))
);
sel.value = st.taskTiers[label] || "";
sel.addEventListener("change", () => {
st.taskTiers[label] = sel.value;
});
return h("div", { class: "task-tier-wrap" },
h("div", { class: "muted small" }, t("routing.tasks.tier")), sel);
}
function tasksCard() {
const addIn = h("input", { placeholder: t("routing.tasks.addPlaceholder"), style: "max-width:220px" });
const addBtn = h("button", { class: "btn ghost sm" }, "+ " + t("routing.tasks.addCustom"));
addBtn.addEventListener("click", () => {
const v = addIn.value.trim().toLowerCase();
if (!v || st.tasks[v]) return;
st.tasks[v] = [];
render();
});
return h(
"div",
{ class: "card" },
h("div", { class: "card-head" },
h("h3", {}, "🎯 " + t("routing.tasks.title")),
h("span", { class: "card-head sub" },
labelsSource === "router" ? t("routing.tasks.fromRouter") : t("routing.tasks.builtin"))),
h("div", { class: "muted small", style: "margin-bottom:10px" }, t("routing.tasks.hint")),
...Object.keys(st.tasks).map(taskRow),
h("div", { class: "flex", style: "gap:8px; margin-top:10px" }, addIn, addBtn)
);
}
function policyCard() {
const modeSel = h(
"select",
{ onChange: (e) => { st.policy.mode = e.target.value; render(); } },
h("option", { value: "fixed_table", selected: st.policy.mode === "fixed_table" }, t("routing.policy.fixed")),
h("option", { value: "cost_aware", selected: st.policy.mode === "cost_aware" }, t("routing.policy.costAware"))
);
const children = [
h("label", { class: "field" }, h("span", {}, t("routing.policy.mode")), modeSel),
];
if (st.policy.mode === "cost_aware") {
const maxIn = h("input", {
type: "number",
step: "0.01",
value: st.policy.max_cost_usd_per_request ?? "",
placeholder: "0.50",
onChange: (e) => { st.policy.max_cost_usd_per_request = e.target.value === "" ? null : parseFloat(e.target.value); },
});
children.push(h("label", { class: "field" }, h("span", {}, t("routing.policy.maxCost")), maxIn));
st.policy.min_class = st.policy.min_class || {};
const rows = Object.keys(st.tiers).map((tier) => {
const sel = h(
"select",
{ onChange: (e) => { st.policy.min_class[tier] = e.target.value; } },
h("option", { value: "" }, "—"),
...(meta.cost_tiers || []).map((c) => h("option", { value: c, selected: st.policy.min_class[tier] === c }, c))
);
return h("label", { class: "field" }, h("span", {}, t("routing.policy.minClass") + " · " + tier), sel);
});
children.push(h("div", { class: "row" }, ...rows));
}
return h("div", { class: "card" }, h("div", { class: "card-head" }, h("h3", {}, t("routing.policy"))), ...children);
}
function render() {
const defSel = h(
"select",
{ onChange: (e) => { st.default = e.target.value; } },
...ids.map((id) => h("option", { value: id, selected: id === st.default }, id))
);
const saveBtn = h("button", { class: "btn primary" }, t("common.save"));
saveBtn.addEventListener("click", async () => {
saveBtn.disabled = true;
try {
const tasks = {};
for (const [k, v] of Object.entries(st.tasks)) {
const tier = (st.taskTiers || {})[k] || "";
if (tier) tasks[k] = { models: v, tier };
else if (v.length) tasks[k] = v;
}
await api.putRouting({ tiers: st.tiers, tasks, default: st.default, policy: st.policy });
toast(t("toast.saved"), "good");
} catch (e) {
toast(String(e.message || e), "bad");
}
saveBtn.disabled = false;
});
mount(
root,
h(
"div",
{ class: "page-head" },
h(
"div",
{ class: "flex" },
h("div", { class: "grow" }, h("h2", {}, t("routing.title")), h("p", {}, t("routing.subtitle"))),
saveBtn
)
),
ids.length === 0 ? h("div", { class: "callout" }, t("routing.empty")) : null,
h(
"div",
{ class: "card" },
h("div", { class: "card-head" }, h("h3", {}, t("routing.tiers")), h("span", { class: "card-head sub" }, t("routing.tierHint"))),
...Object.keys(st.tiers).map(tierRow)
),
tasksCard(),
h(
"div",
{ class: "card" },
h("div", { class: "card-head" }, h("h3", {}, t("routing.default"))),
h("label", { class: "field" }, h("span", {}, t("routing.defaultHint")), defSel)
),
policyCard()
);
}
render();
return root;
}