feat(rtk): add X-9Router-Token-Saver header to bypass token savers per request

This commit is contained in:
joachimBrindeau
2026-07-16 11:27:42 +07:00
parent 88a8c72d2d
commit c9926897ba
4 changed files with 57 additions and 6 deletions
+2
View File
@@ -56,6 +56,8 @@ export const GEMINI_NATIVE_TTS_FETCH_TIMEOUT_MS = envMs("GEMINI_NATIVE_TTS_FETCH
export const DEFAULT_MAX_TOKENS = 64000;
export const DEFAULT_MIN_TOKENS = 32000;
export const TOKEN_SAVER_HEADER = "x-9router-token-saver";
// Retry config for 429 responses (legacy - kept for backward compatibility)
export const RETRY_CONFIG = {
maxAttempts: 2,
+9 -6
View File
@@ -9,7 +9,7 @@ import { createRequestLogger } from "../utils/requestLogger.js";
import { getModelTargetFormat, getModelStrip, getModelUpstreamId, getModelType, PROVIDER_ID_TO_ALIAS } from "../config/providerModels.js";
import { PROVIDERS } from "../config/providers.js";
import { createErrorResult, parseUpstreamError, formatProviderError } from "../utils/error.js";
import { HTTP_STATUS } from "../config/runtimeConfig.js";
import { HTTP_STATUS, TOKEN_SAVER_HEADER } from "../config/runtimeConfig.js";
import { handleBypassRequest } from "../utils/bypassHandler.js";
import { trackPendingRequest, appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
import { getExecutor } from "../executors/index.js";
@@ -156,14 +156,17 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
delete translatedBody.tools;
}
// Per-request opt-out: client can bypass all token savers via header
const tokenSaverEnabled = clientRawRequest?.headers?.[TOKEN_SAVER_HEADER]?.toLowerCase() !== "off";
// RTK: compress tool_result content
const rtkStats = compressMessages(translatedBody, rtkEnabled);
const rtkStats = compressMessages(translatedBody, tokenSaverEnabled && rtkEnabled);
const rtkLine = formatRtkLog(rtkStats);
if (rtkLine) console.log(rtkLine);
// Headroom: optional external proxy compression; fail open if proxy is absent.
const headroomDiagnostics = {};
const headroomStats = await compressWithHeadroom(translatedBody, { enabled: headroomEnabled, url: headroomUrl, model: upstreamModel, format: finalFormat, compressUserMessages: headroomCompressUserMessages, diagnostics: headroomDiagnostics });
const headroomStats = await compressWithHeadroom(translatedBody, { enabled: tokenSaverEnabled && headroomEnabled, url: headroomUrl, model: upstreamModel, format: finalFormat, compressUserMessages: headroomCompressUserMessages, diagnostics: headroomDiagnostics });
const headroomLine = formatHeadroomLog(headroomStats);
const headroomSizeLine = formatHeadroomSizeLog(headroomDiagnostics);
if (headroomLine) {
@@ -171,16 +174,16 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
if (isHeadroomPhantomSavings(headroomStats, headroomDiagnostics)) {
log?.warn?.("HEADROOM", `reported token delta, but outbound JSON shrank <5%; provider may bill near-original payload | ${headroomSizeLine}`);
}
} else if (headroomEnabled) log?.warn?.("HEADROOM", `skipped: ${headroomDiagnostics.reason || "compression unavailable"}${headroomDiagnostics.endpoint ? ` (${headroomDiagnostics.endpoint})` : ""}`);
} else if (tokenSaverEnabled && headroomEnabled) log?.warn?.("HEADROOM", `skipped: ${headroomDiagnostics.reason || "compression unavailable"}${headroomDiagnostics.endpoint ? ` (${headroomDiagnostics.endpoint})` : ""}`);
// Caveman: inject terse-style system prompt
if (cavemanEnabled && cavemanLevel) {
if (tokenSaverEnabled && cavemanEnabled && cavemanLevel) {
injectCaveman(translatedBody, finalFormat, cavemanLevel);
log?.debug?.("CAVEMAN", `${cavemanLevel} | ${finalFormat}`);
}
// Ponytail: inject lazy-senior-dev system prompt
if (ponytailEnabled && ponytailLevel) {
if (tokenSaverEnabled && ponytailEnabled && ponytailLevel) {
injectPonytail(translatedBody, finalFormat, ponytailLevel);
log?.debug?.("PONYTAIL", `${ponytailLevel} | ${finalFormat}`);
}