luulam/9router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge origin/master (v0.5.69) into gitea/new_feature

Browse Source
This commit is contained in:
luulam
2026-09-07 14:10:11 +07:00
parent 86112cee6d eb712ca821
commit a835771c97
222 changed files with 12285 additions and 3371 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
open-sse/handlers/chatCore.js
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 { maybeRejectEarlyStreamError } from "../utils/streamErrorPeek.js";
@@ -58,7 +59,7 @@ 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, capsOverride, streamErrorPatterns }) {
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 }) {
const { provider, model } = modelInfo;
const requestStartTime = Date.now();
// Stable per-session color so all lines of one CLI conversation share a tag
@@ -91,7 +92,12 @@ 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);
@@ -238,6 +244,12 @@ 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";
@@ -248,7 +260,7 @@ 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) {
@@ -346,7 +358,17 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
// exception: it is decoded by the executor into OpenAI-compatible output.
let providerResponseFormat = targetFormat;
try {
const result = await executor.execute({ model, body: translatedBody, stream, credentials, signal: streamController.signal, log, proxyOptions });
const result = await executor.execute({
model,
body: translatedBody,
stream,
credentials,
providerSessionId: sessionSeed,
clientTool,
signal: streamController.signal,
log,
proxyOptions,
});
providerResponse = result.response;
providerUrl = result.url;
providerHeaders = result.headers;
@@ -399,7 +421,17 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
try { await onCredentialsRefreshed(newCredentials); } catch (e) { log?.warn?.("TOKEN", `onCredentialsRefreshed failed: ${e.message}`); }
}
try {
const retryResult = await executor.execute({ model, body: translatedBody, stream, credentials, signal: streamController.signal, log, proxyOptions });
const retryResult = await executor.execute({
model,
body: translatedBody,
stream,
credentials,
providerSessionId: sessionSeed,
clientTool,
signal: streamController.signal,
log,
proxyOptions,
});
if (retryResult.response.ok) {
providerResponse = retryResult.response;
providerUrl = retryResult.url;
@@ -481,7 +513,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
// Streaming response
const { onStreamComplete, streamDetailId } = buildOnStreamComplete({ ...sharedCtx });
return handleStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat: providerResponseFormat, userAgent, reqLogger, toolNameMap, customToolNames, streamController, onStreamComplete, streamDetailId });
return handleStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat: providerResponseFormat, userAgent, reqLogger, toolNameMap, customToolNames, streamController, onStreamComplete, streamDetailId, credentials });
}
export function isTokenExpiringSoon(expiresAt, bufferMs = 5 * 60 * 1000) {