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

feat(headroom): add proxy lifecycle management + dashboard UI

Browse Source 
Build on the optional Headroom Token Saver from Carmelo Campos
(PR: feat: add optional Headroom token saver). Add managed start/stop
of the local headroom proxy from the dashboard, install detection,
status probing, and a simplified Token Saver UI.

- detect headroom CLI + python>=3.10, probe proxy /health
- spawn/stop proxy as a detached, pid-tracked process
- /api/headroom/{status,start,stop} routes, gated local-only in dashboardGuard
- one-click Start/Stop Headroom modal, no manual config needed
- claude<->openai shape conversion for /v1/compress via 9router translators

Thanks to Carmelo Campos (@carmelogunsroses) for the original Headroom integration.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
decolua
2026-06-20 10:09:50 +07:00
co-authored by Cursor
parent efd20be8d8
commit b55cf36d2e
33 changed files with 1019 additions and 130 deletions
Download Patch File Download Diff File Expand all files Collapse all files
open-sse/handlers/chatCore.js
+19 -3
View File
@@ -1,4 +1,4 @@
import { detectFormat, getTargetFormat } from "../services/provider.js";
import { detectFormat, getTargetFormat, resolveTransport } from "../services/provider.js";
import { translateRequest } from "../translator/index.js";
import { FORMATS } from "../translator/formats.js";
import { normalizeClaudePassthrough } from "../translator/formats/claude.js";
@@ -20,7 +20,9 @@ import { handleStreamingResponse, buildOnStreamComplete } from "./chatCore/strea
import { detectClientTool, isNativePassthrough } from "../utils/clientDetector.js";
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 { getCapabilitiesForModel } from "../providers/capabilities.js";
import { stripUnsupportedModalities } from "../translator/concerns/modality.js";
import { prefetchRemoteImages } from "../translator/concerns/prefetch.js";
@@ -32,7 +34,7 @@ import { prefetchRemoteImages } from "../translator/concerns/prefetch.js";
* @param {object} options.credentials - Provider credentials
* @param {string} options.sourceFormatOverride - Override detected source format (e.g. "openai-responses")
*/
export async function handleChatCore({ body, modelInfo, credentials, log, onCredentialsRefreshed, onRequestSuccess, onDisconnect, clientRawRequest, connectionId, userAgent, apiKey, ccFilterNaming, rtkEnabled, cavemanEnabled, cavemanLevel, sourceFormatOverride, providerThinking }) {
export async function handleChatCore({ body, modelInfo, credentials, log, onCredentialsRefreshed, onRequestSuccess, onDisconnect, clientRawRequest, connectionId, userAgent, apiKey, ccFilterNaming, rtkEnabled, headroomEnabled, headroomUrl, headroomCompressUserMessages, cavemanEnabled, cavemanLevel, ponytailEnabled, ponytailLevel, sourceFormatOverride, providerThinking }) {
const { provider, model } = modelInfo;
const requestStartTime = Date.now();
@@ -44,7 +46,10 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
const alias = PROVIDER_ID_TO_ALIAS[provider] || provider;
const modelTargetFormat = getModelTargetFormat(alias, model);
const targetFormat = modelTargetFormat || getTargetFormat(provider);
// Multi-endpoint providers: pick transport matching sourceFormat → zero translation
const runtimeTransport = resolveTransport(provider, sourceFormat);
const targetFormat = modelTargetFormat || runtimeTransport?.format || getTargetFormat(provider);
if (runtimeTransport && credentials) credentials.runtimeTransport = runtimeTransport;
const stripList = getModelStrip(alias, model);
const upstreamModel = getModelUpstreamId(alias, model);
@@ -149,12 +154,23 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
const rtkLine = formatRtkLog(rtkStats);
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 headroomLine = formatHeadroomLog(headroomStats);
if (headroomLine) log?.info?.("HEADROOM", headroomLine);
// Caveman: inject terse-style system prompt
if (cavemanEnabled && cavemanLevel) {
injectCaveman(translatedBody, finalFormat, cavemanLevel);
log?.debug?.("CAVEMAN", `${cavemanLevel} | ${finalFormat}`);
}
// Ponytail: inject lazy-senior-dev system prompt
if (ponytailEnabled && ponytailLevel) {
injectPonytail(translatedBody, finalFormat, ponytailLevel);
log?.debug?.("PONYTAIL", `${ponytailLevel} | ${finalFormat}`);
}
const executor = getExecutor(provider);
trackPendingRequest(model, provider, connectionId, true);
appendRequestLog({ model, provider, connectionId, status: "PENDING" }).catch(() => { });