mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-19 05:32:19 +03:00
* feat(api): add provider quota telemetry, adaptive routing, and status inventory Adds a read-only OmniRoute status/inventory surface plus supporting resilience and usage-tracking infrastructure: - src/lib/quota/providerQuotaTelemetry.ts, providerCapabilities.ts: provider quota state and capability signals, sourced from configured metadata rather than invented values; unknown stays unknown. - src/lib/resilience/adaptiveCircuit.ts, failureClassification.ts: circuit state with lazy recovery and explicit failure classification. - src/lib/usage/usageLedger.ts, budgetGuard.ts, modelPricingRegistry.ts: internal usage tracking and budget allow/warn/deny decisions, kept separate from upstream-reported quota (never conflated). - src/lib/routing/adaptiveRouting.ts: excludes exhausted-quota and open-circuit candidates from routing, penalizes approaching-limit. - src/lib/omnirouteStatus.ts + src/app/api/omniroute/status, route/preview: read-only status endpoint; never issues a live upstream model request (asserted via liveRequestExecuted: false). - src/lib/db/quotaPools.ts: adds ensurePool() for idempotent pool management by automation/CLI callers, following the existing group-demo default-group convention. - scripts/omniroute-verify.mjs (+ omniroute:verify script): local verification against the running gateway. 9 new unit tests, all passing. typecheck:core clean relative to base (release/v3.8.50) -- the 2 pre-existing gateways.ts errors are tracked separately in #9985 and untouched by this change. * test(cli): align cli-machine-token assertions with HMAC-SHA256 64-char format The quota-telemetry feature hardens cliToken to HMAC-SHA256(machineId, SALT) (64-char hex, pristine machine id). Update the regression test to the new format and mirror the production derivation in the different-machine-id check. Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com> --------- Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> Co-authored-by: desamours-hub <desamours-hub@users.noreply.github.com> Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
53 lines
1.5 KiB
TypeScript
53 lines
1.5 KiB
TypeScript
export interface ModelPricing {
|
|
providerId: string;
|
|
modelId: string;
|
|
inputPricePerMillionTokens?: number;
|
|
outputPricePerMillionTokens?: number;
|
|
source?: string;
|
|
effectiveAt?: string;
|
|
}
|
|
|
|
export class ModelPricingRegistry {
|
|
private readonly entries = new Map<string, ModelPricing>();
|
|
|
|
private key(providerId: string, modelId: string): string {
|
|
return `${providerId.trim().toLowerCase()}\0${modelId.trim().toLowerCase()}`;
|
|
}
|
|
|
|
set(pricing: ModelPricing): void {
|
|
this.entries.set(this.key(pricing.providerId, pricing.modelId), { ...pricing });
|
|
}
|
|
|
|
get(providerId: string, modelId: string): ModelPricing | undefined {
|
|
return this.entries.get(this.key(providerId, modelId));
|
|
}
|
|
|
|
estimate(
|
|
providerId: string,
|
|
modelId: string,
|
|
inputTokens = 0,
|
|
outputTokens = 0
|
|
): number | undefined {
|
|
const pricing = this.get(providerId, modelId);
|
|
if (!pricing) return undefined;
|
|
const input =
|
|
pricing.inputPricePerMillionTokens === undefined
|
|
? 0
|
|
: (inputTokens * pricing.inputPricePerMillionTokens) / 1_000_000;
|
|
const output =
|
|
pricing.outputPricePerMillionTokens === undefined
|
|
? 0
|
|
: (outputTokens * pricing.outputPricePerMillionTokens) / 1_000_000;
|
|
if (
|
|
pricing.inputPricePerMillionTokens === undefined &&
|
|
pricing.outputPricePerMillionTokens === undefined
|
|
)
|
|
return undefined;
|
|
return Number((input + output).toFixed(12));
|
|
}
|
|
|
|
list(): ModelPricing[] {
|
|
return [...this.entries.values()].map((entry) => ({ ...entry }));
|
|
}
|
|
}
|