mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-26 09:52:11 +03:00
72ee80649c
* feat(autoCombo): latency/speed-optimized routing mode + omniroute_pick_fastest_model MCP tool * test(translator): split responses chat request coverage * refactor(mcp): extract fastest-model tool modules * fix(i18n): cover provider icon and cors labels * test(mutation): register latency coverage files * test(ci): collect executor unit tests * refactor(ci): reduce latency path complexity * fix(mcp): include models catalog module * feat(autoCombo): latency/speed-optimized routing + omniroute_pick_fastest_model MCP tool Re-cut onto release tip: keep speed-routing + MCP tool + supporting catalog split; drop out-of-scope translator split, en.json/ci.yml/package.json orphans, and unrelated proxyFetch/responsesStreamHelpers/tokenLimitCounter refactors. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> --------- Co-authored-by: kooshapari <kooshapari@users.noreply.github.com> Co-authored-by: Diego Rodrigues de Sa e Souza <diegosouza.pw@outlook.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
111 lines
3.1 KiB
TypeScript
111 lines
3.1 KiB
TypeScript
import { z } from "zod";
|
|
import type { McpToolDefinition } from "./toolDefinition.ts";
|
|
|
|
export const pickFastestModelInput = z.object({
|
|
comboId: z
|
|
.string()
|
|
.optional()
|
|
.describe(
|
|
"Optional combo id or name to scope the ranking to. Omit to rank across all enabled combos."
|
|
),
|
|
includeUnhealthy: z
|
|
.boolean()
|
|
.optional()
|
|
.describe(
|
|
"When true, OPEN-circuit candidates are scored (sorted to the bottom) instead of filtered out."
|
|
),
|
|
weights: z
|
|
.object({
|
|
ttft: z.number().min(0).optional(),
|
|
tps: z.number().min(0).optional(),
|
|
e2e: z.number().min(0).optional(),
|
|
p95: z.number().min(0).optional(),
|
|
health: z.number().min(0).optional(),
|
|
reliability: z.number().min(0).optional(),
|
|
stability: z.number().min(0).optional(),
|
|
})
|
|
.partial()
|
|
.optional()
|
|
.describe("Optional speed-ranking weight overrides merged onto the defaults."),
|
|
applyToCombo: z
|
|
.boolean()
|
|
.optional()
|
|
.describe("When true + comboId present, switches the combo to auto/latency routing."),
|
|
limit: z.number().int().min(1).max(50).optional().describe("Ranked result limit."),
|
|
});
|
|
|
|
export const pickFastestModelOutput = z.object({
|
|
fastest: z
|
|
.object({
|
|
provider: z.string(),
|
|
model: z.string(),
|
|
score: z.number(),
|
|
reason: z.string(),
|
|
})
|
|
.nullable(),
|
|
ranked: z.array(
|
|
z.object({
|
|
provider: z.string(),
|
|
model: z.string(),
|
|
score: z.number(),
|
|
factors: z.object({
|
|
ttft: z.number(),
|
|
tps: z.number(),
|
|
e2e: z.number(),
|
|
p95: z.number(),
|
|
health: z.number(),
|
|
reliability: z.number(),
|
|
stability: z.number(),
|
|
}),
|
|
metrics: z.object({
|
|
avgTtftMs: z.number().nullable(),
|
|
avgTokensPerSecond: z.number().nullable(),
|
|
avgE2ELatencyMs: z.number().nullable(),
|
|
p95LatencyMs: z.number().nullable(),
|
|
latencyStdDev: z.number().nullable(),
|
|
failureRate: z.number(),
|
|
circuitBreakerState: z.enum(["CLOSED", "OPEN", "HALF_OPEN"]),
|
|
}),
|
|
reason: z.string(),
|
|
})
|
|
),
|
|
weights: z.object({
|
|
ttft: z.number(),
|
|
tps: z.number(),
|
|
e2e: z.number(),
|
|
p95: z.number(),
|
|
health: z.number(),
|
|
reliability: z.number(),
|
|
stability: z.number(),
|
|
}),
|
|
comboScope: z.object({ id: z.string(), name: z.string() }).nullable(),
|
|
appliedToCombo: z
|
|
.object({
|
|
id: z.string(),
|
|
name: z.string(),
|
|
strategy: z.string(),
|
|
autoRoutingStrategy: z.string(),
|
|
})
|
|
.nullable(),
|
|
});
|
|
|
|
export const pickFastestModelTool: McpToolDefinition<
|
|
typeof pickFastestModelInput,
|
|
typeof pickFastestModelOutput
|
|
> = {
|
|
name: "omniroute_pick_fastest_model",
|
|
description:
|
|
"Picks the fastest reliable provider-model pair from live telemetry and can apply latency routing to a combo.",
|
|
inputSchema: pickFastestModelInput,
|
|
outputSchema: pickFastestModelOutput,
|
|
scopes: ["read:combos", "read:health", "read:usage"],
|
|
auditLevel: "basic",
|
|
phase: 2,
|
|
sourceEndpoints: [
|
|
"/api/combos",
|
|
"/api/monitoring/health",
|
|
"/api/usage/quota",
|
|
"/api/usage/analytics",
|
|
],
|
|
};
|