nezumi/9router
1
0
Fork 0
mirror of https://github.com/Nezumi-2711/9router.git synced 2026-09-22 13:38:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(headroom): clarify token diagnostics vs provider billing

Browse Source 
Distinguish Headroom-reported token deltas from outbound payload size,
scrub credentials in logs, and warn on phantom savings when compressed
JSON barely shrinks. Refs #1998

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Sutarto Jordan Chrisfivo
2026-06-26 11:12:07 +07:00
committed by decolua
co-authored by Cursor
parent c7933de79c
commit fb543a1f39
4 changed files with 401 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
open-sse/handlers/chatCore.js
+10 -3
View File
@@ -22,7 +22,7 @@ import { dedupeTools } from "../utils/toolDeduper.js";
import { injectCaveman } from "../rtk/caveman.js";
import { injectPonytail } from "../rtk/ponytail.js";
import { compressMessages, formatRtkLog } from "../rtk/index.js";
import { compressWithHeadroom, formatHeadroomLog } from "../rtk/headroom.js";
import { compressWithHeadroom, formatHeadroomLog, formatHeadroomSizeLog, isHeadroomPhantomSavings } from "../rtk/headroom.js";
import { getCapabilitiesForModel } from "../providers/capabilities.js";
import { stripUnsupportedModalities } from "../translator/concerns/modality.js";
import { prefetchRemoteImages } from "../translator/concerns/prefetch.js";
@@ -162,9 +162,16 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
if (rtkLine) console.log(rtkLine);
// Headroom: optional external proxy compression; fail open if proxy is absent.
const headroomStats = await compressWithHeadroom(translatedBody, { enabled: headroomEnabled, url: headroomUrl, model: upstreamModel, format: finalFormat, compressUserMessages: headroomCompressUserMessages });
const headroomDiagnostics = {};
const headroomStats = await compressWithHeadroom(translatedBody, { enabled: headroomEnabled, url: headroomUrl, model: upstreamModel, format: finalFormat, compressUserMessages: headroomCompressUserMessages, diagnostics: headroomDiagnostics });
const headroomLine = formatHeadroomLog(headroomStats);
if (headroomLine) log?.info?.("HEADROOM", headroomLine);
const headroomSizeLine = formatHeadroomSizeLog(headroomDiagnostics);
if (headroomLine) {
log?.info?.("HEADROOM", `${headroomLine}${headroomSizeLine ? ` | ${headroomSizeLine}` : ""}`);
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})` : ""}`);
// Caveman: inject terse-style system prompt
if (cavemanEnabled && cavemanLevel) {