Merge remote-tracking branch 'upstream/master'

# Conflicts:
#	open-sse/handlers/chatCore.js
#	open-sse/providers/registry/index.js
#	open-sse/services/usage.js
This commit is contained in:
MUH. IQRAM BAHRING
2026-08-30 23:23:48 +08:00
114 changed files with 5586 additions and 2183 deletions
+15 -3
View File
@@ -28,6 +28,7 @@ import { compressWithPxpipe } from "../rtk/pxpipe.js";
import { getCapabilitiesForModel } from "../providers/capabilities.js";
import { stripUnsupportedModalities } from "../translator/concerns/modality.js";
import { prefetchRemoteImages } from "../translator/concerns/prefetch.js";
import { defaultClaudeToolType } from "../translator/concerns/toolCall.js";
import { resolveSessionId } from "../utils/sessionManager.js";
import { markPoolUnfit, clearPoolUnfit } from "../services/proxyPoolFitness.js";
@@ -63,7 +64,7 @@ export function stripContinuityFields(body) {
return body;
}
export async function handleChatCore({ body, modelInfo, credentials, log, onCredentialsRefreshed, onRequestSuccess, onDisconnect, clientRawRequest, connectionId, userAgent, apiKey, ccFilterNaming, rtkEnabled, headroomEnabled, headroomUrl, headroomCompressUserMessages, cavemanEnabled, cavemanLevel, ponytailEnabled, ponytailLevel, pxpipeEnabled, pxpipeMinChars, pxpipeTimeoutMs, pxpipeTransform, onPxpipeEvent, sourceFormatOverride, providerThinking, resolveProxyConfig }) {
export async function handleChatCore({ body, modelInfo, credentials, log, onCredentialsRefreshed, onRequestSuccess, onDisconnect, clientRawRequest, connectionId, userAgent, apiKey, ccFilterNaming, rtkEnabled, headroomEnabled, headroomUrl, headroomCompressUserMessages, headroomTimeoutMs, cavemanEnabled, cavemanLevel, ponytailEnabled, ponytailLevel, pxpipeEnabled, pxpipeMinChars, pxpipeTimeoutMs, pxpipeTransform, onPxpipeEvent, sourceFormatOverride, providerThinking, resolveProxyConfig }) {
const { provider, model } = modelInfo;
const requestStartTime = Date.now();
// Stable per-session color so all lines of one CLI conversation share a tag
@@ -96,7 +97,12 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
// differ — kimi/glm only do /chat/completions). Undeclared models keep the
// upstream default (use the transport), preserving behavior for glm/deepseek/...
const useTransport = (!modelSupportedFormats || modelSupportedFormats.includes(sourceFormat)) ? runtimeTransport : null;
const targetFormat = modelTargetFormat || useTransport?.format || getTargetFormat(provider, credentials);
// A source-format-matched endpoint keeps the request lossless. Prefer it
// over a model-level targetFormat, which is only the fallback for clients
// whose wire format has no supported transport (for example MiniMax-M3:
// OpenAI clients should stay on /chat/completions; other clients can fall
// back to its declared Claude target).
const targetFormat = useTransport?.format || modelTargetFormat || getTargetFormat(provider, credentials);
if (useTransport && credentials) credentials.runtimeTransport = useTransport;
const stripList = getModelStrip(alias, model);
const upstreamModel = getModelUpstreamId(alias, model);
@@ -241,6 +247,12 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
delete translatedBody.tools;
}
// Claude tool schema requires `type` to be explicitly set; strict gateways (e.g., MiniMax)
// reject legacy payloads that omit it with HTTP 400. Default to "custom" when missing.
if (finalFormat === FORMATS.CLAUDE && Array.isArray(translatedBody.tools)) {
translatedBody.tools = defaultClaudeToolType(translatedBody.tools);
}
// Per-request opt-out: client can bypass all token savers via header
const tokenSaverEnabled = clientRawRequest?.headers?.[TOKEN_SAVER_HEADER]?.toLowerCase() !== "off";
@@ -251,7 +263,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
// Headroom: optional external proxy compression; fail open if proxy is absent.
const headroomDiagnostics = {};
const headroomStats = await compressWithHeadroom(translatedBody, { enabled: tokenSaverEnabled && 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, timeoutMs: headroomTimeoutMs, diagnostics: headroomDiagnostics });
const headroomLine = formatHeadroomLog(headroomStats);
const headroomSizeLine = formatHeadroomSizeLog(headroomDiagnostics);
if (headroomLine) {