@fudrouter/fsrouter 0.6.64 → 0.6.65

package/open-sse/handlers/chatCore/streamingHandler.js

@@ -0,0 +1,95 @@
+import { FORMATS } from "../../translator/formats.js";
+import { needsTranslation } from "../../translator/index.js";
+import { createSSETransformStreamWithLogger, createPassthroughStreamWithLogger } from "../../utils/stream.js";
+import { pipeWithDisconnect } from "../../utils/streamHandler.js";
+import { buildAbortedResponsesTerminalBytes } from "../../utils/responsesStreamHelpers.js";
+import { buildRequestDetail, extractRequestConfig, saveUsageStats } from "./requestDetail.js";
+import { saveRequestDetail } from '../../../dist/lib/usageDb.js';
+
+const SSE_HEADERS = {
+  "Content-Type": "text/event-stream",
+  "Cache-Control": "no-cache",
+  "Connection": "keep-alive",
+  "Access-Control-Allow-Origin": "*"
+};
+
+/**
+ * Determine which SSE transform stream to use based on provider/format.
+ */
+function buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey }) {
+  const isDroidCLI = userAgent?.toLowerCase().includes("droid") || userAgent?.toLowerCase().includes("codex-cli");
+  const needsCodexTranslation = provider === "codex" && targetFormat === FORMATS.OPENAI_RESPONSES && !isDroidCLI;
+
+  if (needsCodexTranslation) {
+    // Codex returns Responses API SSE → translate to client format
+    let codexTarget;
+    if (sourceFormat === FORMATS.OPENAI_RESPONSES) codexTarget = FORMATS.OPENAI_RESPONSES;
+    else if (sourceFormat === FORMATS.CLAUDE) codexTarget = FORMATS.CLAUDE;
+    else if (sourceFormat === FORMATS.ANTIGRAVITY || sourceFormat === FORMATS.GEMINI || sourceFormat === FORMATS.GEMINI_CLI) codexTarget = FORMATS.ANTIGRAVITY;
+    else codexTarget = FORMATS.OPENAI;
+    return createSSETransformStreamWithLogger(FORMATS.OPENAI_RESPONSES, codexTarget, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey);
+  }
+
+  if (needsTranslation(targetFormat, sourceFormat)) {
+    return createSSETransformStreamWithLogger(targetFormat, sourceFormat, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey);
+  }
+
+  return createPassthroughStreamWithLogger(provider, reqLogger, model, connectionId, body, onStreamComplete, apiKey);
+}
+
+/**
+ * Handle streaming response — pipe provider SSE through transform stream to client.
+ */
+export function handleStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, userAgent, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, streamController, onStreamComplete }) {
+  if (onRequestSuccess) onRequestSuccess();
+
+  const transformStream = buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey });
+
+  // Responses passthrough: synthesize response.failed + [DONE] if the stream aborts/stalls before a terminal event
+  const isResponsesPassthrough = sourceFormat === FORMATS.OPENAI_RESPONSES && targetFormat === FORMATS.OPENAI_RESPONSES;
+  const onAbortTerminal = isResponsesPassthrough ? buildAbortedResponsesTerminalBytes : null;
+  const transformedBody = pipeWithDisconnect(providerResponse, transformStream, streamController, onAbortTerminal);
+
+  // NOTE: we intentionally do NOT save a placeholder "streaming in progress" record here.
+  // The final record is saved by onStreamComplete (built by buildOnStreamComplete) when the
+  // stream finishes. This avoids creating two DB rows per request (the phantom ttft=0 duplicate).
+
+  return {
+    success: true,
+    response: new Response(transformedBody, { headers: SSE_HEADERS })
+  };
+}
+
+/**
+ * Build onStreamComplete callback for streaming usage tracking.
+ */
+export function buildOnStreamComplete({ provider, model, connectionId, apiKey, requestStartTime, body, stream, finalBody, translatedBody, clientRawRequest }) {
+  const streamDetailId = `${Date.now()}-${Math.random().toString(36).slice(2, 11)}`;
+
+  const onStreamComplete = (contentObj, usage, ttftAt) => {
+    const latency = {
+      ttft: ttftAt ? ttftAt - requestStartTime : Date.now() - requestStartTime,
+      total: Date.now() - requestStartTime
+    };
+    const safeContent = contentObj?.content || "[Empty streaming response]";
+    const safeThinking = contentObj?.thinking || null;
+
+    saveRequestDetail(buildRequestDetail({
+      provider, model, connectionId,
+      latency,
+      tokens: usage || { prompt_tokens: 0, completion_tokens: 0 },
+      request: extractRequestConfig(body, stream),
+      providerRequest: finalBody || translatedBody || null,
+      providerResponse: safeContent,
+      response: { content: safeContent, thinking: safeThinking, type: "streaming" },
+      status: "success"
+    }, { id: streamDetailId })).catch(err => {
+      console.error("[RequestDetail] Failed to update streaming content:", err.message);
+    });
+
+    saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint, label: "STREAM USAGE" });
+  };
+
+  return { onStreamComplete, streamDetailId };
+}
+

package/open-sse/handlers/chatCore.js

@@ -0,0 +1,404 @@
+import { detectFormat, getTargetFormat, resolveTransport } from "../services/provider.js";
+import { translateRequest } from "../translator/index.js";
+import { stripThinkingSuffix } from "../translator/concerns/thinkingUnified.js";
+import { FORMATS } from "../translator/formats.js";
+import { normalizeClaudePassthrough } from "../translator/formats/claude.js";
+import { createStreamController } from "../utils/streamHandler.js";
+import { refreshWithRetry } from "../services/tokenRefresh.js";
+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 { handleBypassRequest } from "../utils/bypassHandler.js";
+import { trackPendingRequest, appendRequestLog, saveRequestDetail } from '../../../dist/lib/usageDb.js';
+import { getExecutor } from "../executors/index.js";
+import { buildRequestDetail, extractRequestConfig } from "./chatCore/requestDetail.js";
+import { handleForcedSSEToJson } from "./chatCore/sseToJsonHandler.js";
+import { handleNonStreamingResponse } from "./chatCore/nonStreamingHandler.js";
+import { handleStreamingResponse, buildOnStreamComplete } from "./chatCore/streamingHandler.js";
+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 } from "../rtk/index.js";
+import { compressWithHeadroom, formatHeadroomSizeLog, isHeadroomPhantomSavings } from "../rtk/headroom.js";
+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 { extractThinking } from "../translator/concerns/thinkingUnified.js";
+import { resolveSessionId } from "../utils/sessionManager.js";
+
+/**
+ * Core chat handler - shared between SSE and Worker
+ * @param {object} options.body - Request body
+ * @param {object} options.modelInfo - { provider, model }
+ * @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, headroomEnabled, headroomUrl, headroomCompressUserMessages, 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
+  const sessionSeed = (() => {
+    try {
+      return resolveSessionId({ headers: clientRawRequest?.headers, body, connectionId, scope: provider });
+    } catch {
+      return connectionId || "";
+    }
+  })();
+  const reqTag = log?.tagForSession ? log.tagForSession(sessionSeed) : (log?.nextTag ? log.nextTag() : "");
+
+  const sourceFormat = sourceFormatOverride || detectFormat(body);
+
+  // Check for bypass patterns (warmup, skip, cc naming)
+  const bypassResponse = handleBypassRequest(body, model, userAgent, ccFilterNaming);
+  if (bypassResponse) return bypassResponse;
+
+  const alias = PROVIDER_ID_TO_ALIAS[provider] || provider;
+  const modelTargetFormat = getModelTargetFormat(alias, model);
+  // 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);
+
+  // Inject provider-level thinking config override (only if client hasn't set)
+  // on/off → extended type (body.thinking), none/low/medium/high → effort type (body.reasoning_effort)
+  if (providerThinking?.mode && providerThinking.mode !== "auto") {
+    const mode = providerThinking.mode;
+    if (mode === "on" && !body.thinking) {
+      console.log("Injecting provider-level thinking config override: on");
+      body = { ...body, thinking: { type: "enabled", budget_tokens: 10000 } };
+    } else if (mode === "off" && !body.thinking) {
+      body = { ...body, thinking: { type: "disabled" } };
+    } else if (!body.reasoning_effort) {
+      body = { ...body, reasoning_effort: mode };
+    }
+  }
+
+  const clientRequestedStreaming = body.stream === true || sourceFormat === FORMATS.ANTIGRAVITY || sourceFormat === FORMATS.GEMINI || sourceFormat === FORMATS.GEMINI_CLI;
+  const providerRequiresStreaming = PROVIDERS[provider]?.forceStream === true;
+  let stream = providerRequiresStreaming ? true : (body.stream !== false);
+
+  // Image generation models require non-streaming (Google v1internal:generateContent)
+  const modelType = getModelType(alias, model);
+  const isImageGenModel = modelType === "imageGen" || /image|imagen|image-generation/i.test(model);
+  if (isImageGenModel && (provider === "antigravity" || provider === "gemini-cli")) {
+    stream = false;
+  }
+
+  // DeepSeek-TUI: interactive TUI panel sends stream:true and needs SSE.
+  // Non-interactive mode (-p flag) sends without stream and can't parse SSE.
+  // Only force non-streaming when client didn't explicitly request it.
+  const detectedTool = detectClientTool(clientRawRequest?.headers || {}, body);
+  if (detectedTool === "deepseek-tui" && body.stream !== true) stream = false;
+
+  // Check client Accept header preference for non-streaming requests
+  // This fixes AI SDK compatibility where clients send Accept: application/json
+  const acceptHeader = clientRawRequest?.headers?.accept || "";
+  const clientPrefersJson = acceptHeader.includes("application/json");
+  const clientPrefersSSE = acceptHeader.includes("text/event-stream");
+  if (clientPrefersJson && !clientPrefersSSE && body.stream !== true && !providerRequiresStreaming) {
+    stream = false;
+  }
+
+  const reqLogger = await createRequestLogger(sourceFormat, targetFormat, model);
+  if (clientRawRequest) reqLogger.logClientRawRequest(clientRawRequest.endpoint, clientRawRequest.body, clientRawRequest.headers);
+  reqLogger.logRawRequest(body);
+  log?.debug?.("FORMAT", `${sourceFormat} → ${targetFormat} | stream=${stream}`);
+
+  // Native passthrough: CLI tool and provider are the same ecosystem
+  // Skip all translation/normalization — only model and Bearer are swapped
+  const clientTool = detectClientTool(clientRawRequest?.headers || {}, body);
+  const passthrough = isNativePassthrough(clientTool, provider);
+
+  // Expose raw client headers to translators/executors for session-id resolution
+  if (credentials) credentials.rawHeaders = clientRawRequest?.headers || {};
+
+  // Auto-strip media blocks the model can't read (vision/audio/pdf) before translation.
+  if (!passthrough) {
+    const caps = getCapabilitiesForModel(provider, model);
+    if (stripUnsupportedModalities(body, sourceFormat, caps)) {
+      log?.debug?.("MODALITY", `stripped unsupported media for ${provider}/${model}`);
+    }
+    // Convert remote image URLs to base64 for targets that can't fetch URLs.
+    try {
+      const n = await prefetchRemoteImages(body, sourceFormat, targetFormat, { signal: undefined });
+      if (n > 0) log?.debug?.("MODALITY", `prefetched ${n} remote image(s) for ${targetFormat}`);
+    } catch (e) { log?.warn?.("MODALITY", `image prefetch failed: ${e.message}`); }
+  }
+
+  let translatedBody;
+  let toolNameMap;
+  if (passthrough) {
+    log?.debug?.("PASSTHROUGH", `${clientTool} → ${provider} | native lossless`);
+    translatedBody = { ...body, model: stripThinkingSuffix(upstreamModel) };
+    // Normalize newer Cowork/CC beta shapes (adaptive thinking, mid-conversation system) the API rejects
+    if (clientTool === "claude") normalizeClaudePassthrough(translatedBody, translatedBody.model);
+  } else {
+    translatedBody = translateRequest(sourceFormat, targetFormat, upstreamModel, body, stream, credentials, provider, reqLogger, stripList, connectionId, clientTool);
+    if (!translatedBody) {
+      trackPendingRequest(model, provider, connectionId, false, true);
+      return createErrorResult(HTTP_STATUS.BAD_REQUEST, `Failed to translate request for ${sourceFormat} → ${targetFormat}`);
+    }
+    toolNameMap = translatedBody._toolNameMap;
+    delete translatedBody._toolNameMap;
+    translatedBody.model = stripThinkingSuffix(upstreamModel);
+  }
+
+  // Dedupe duplicate built-in tools when equivalent MCP tools are present (Claude clients only).
+  if (clientTool === "claude" && Array.isArray(translatedBody.tools)) {
+    const { tools: deduped, stripped } = dedupeTools(translatedBody.tools);
+    if (stripped.length > 0) {
+      translatedBody.tools = deduped;
+      log?.debug?.("TOOLDEDUP", `stripped ${stripped.length}: ${stripped.slice(0, 3).join(", ")}${stripped.length > 3 ? "..." : ""}`);
+    }
+  }
+
+  // Token savers: applied at the final body just before dispatch
+  // Covers both passthrough (source shape) and translated (target shape) flows
+  const finalFormat = passthrough ? sourceFormat : targetFormat;
+
+  // Request line: one correlated summary (fmt + thinking + counts + account)
+  if (log?.line) {
+    const clientModel = clientRawRequest?.body?.model || `${provider}/${model}`;
+    const msgN = translatedBody.messages?.length || translatedBody.input?.length || translatedBody.contents?.length || body.messages?.length || body.input?.length || 0;
+    const toolN = translatedBody.tools?.length || body.tools?.length || 0;
+    const fmtStr = passthrough ? `FMT: ${sourceFormat} (passthrough)` : `FMT: ${sourceFormat}→${targetFormat}`;
+    const think = log.fmtThink?.(extractThinking(translatedBody));
+    const acc = credentials?.connectionName || credentials?.connectionId?.slice(0, 8) || "-";
+    const parts = [
+      `POST ${clientModel} → ${provider}/${model}`,
+      fmtStr,
+      stream ? "STREAM" : "JSON",
+      `${msgN} MSG`,
+    ];
+    if (toolN) parts.push(`${toolN} TOOL`);
+    if (think) parts.push(`THINK:${think}`);
+    parts.push(`ACC:${acc}`);
+    log.line(reqTag, "▶", parts.join(" · "));
+  }
+
+  // TTS models don't support tool messages/function calling
+  if (getModelType(alias, model) === "tts" && translatedBody.messages) {
+    translatedBody.messages = translatedBody.messages.filter(msg => msg.role !== "tool");
+    delete translatedBody.tools;
+  }
+
+  // Token-saver summary parts, printed as one "⚙" line at the end (only active ones)
+  const xf = [];
+
+  // RTK: compress tool_result content
+  const rtkStats = compressMessages(translatedBody, rtkEnabled);
+  if (rtkStats?.hits?.length) {
+    const saved = rtkStats.bytesBefore - rtkStats.bytesAfter;
+    const pct = rtkStats.bytesBefore > 0 ? ((saved / rtkStats.bytesBefore) * 100).toFixed(0) : "0";
+    xf.push(`RTK −${saved}B(${pct}%)`);
+  }
+
+  // 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 });
+  if (headroomStats) {
+    const before = headroomStats.tokens_before || 0;
+    const delta = headroomStats.tokens_saved || 0;
+    const pct = before > 0 ? ((delta / before) * 100).toFixed(1) : "0";
+    xf.push(`HEADROOM −${delta}tok(${pct}%)`);
+    if (isHeadroomPhantomSavings(headroomStats, headroomDiagnostics)) {
+      log?.warn?.("HEADROOM", `reported token delta, but outbound JSON shrank <5%; provider may bill near-original payload | ${formatHeadroomSizeLog(headroomDiagnostics)}`);
+    }
+  } else if (headroomEnabled) {
+    log?.warn?.("HEADROOM", `skipped: ${headroomDiagnostics.reason || "compression unavailable"}${headroomDiagnostics.endpoint ? ` (${headroomDiagnostics.endpoint})` : ""}`);
+  }
+
+  // Caveman: inject terse-style system prompt
+  if (cavemanEnabled && cavemanLevel) {
+    injectCaveman(translatedBody, finalFormat, cavemanLevel);
+    xf.push(`CAVEMAN:${cavemanLevel}`);
+  }
+
+  // Ponytail: inject lazy-senior-dev system prompt
+  if (ponytailEnabled && ponytailLevel) {
+    injectPonytail(translatedBody, finalFormat, ponytailLevel);
+    xf.push(`PONYTAIL:${ponytailLevel}`);
+  }
+
+  // PXPIPE: image bulky context (Claude-format bodies only), last saver before dispatch
+  let pxpipeSummary = null;
+  if (pxpipeEnabled) {
+    const pxpipeResult = await compressWithPxpipe(translatedBody, {
+      enabled: true, format: finalFormat, model: upstreamModel,
+      minChars: pxpipeMinChars, timeoutMs: pxpipeTimeoutMs, transform: pxpipeTransform,
+    });
+    pxpipeSummary = pxpipeResult.summary;
+    if (pxpipeResult.body) translatedBody = pxpipeResult.body;
+    if (pxpipeSummary?.applied) xf.push(`PXPIPE:${pxpipeSummary.imageCount}img`);
+    try { onPxpipeEvent?.({ provider, model, ...pxpipeSummary }); } catch { /* stats must not break requests */ }
+  }
+
+  if (xf.length && log?.line) log.line(reqTag, "⚙", xf.join(" · "));
+
+  const executor = getExecutor(provider);
+  trackPendingRequest(model, provider, connectionId, true);
+  try {
+    appendRequestLog({ model, provider, connectionId, status: "PENDING" }).catch(() => { });
+
+    const msgCount = translatedBody.messages?.length || translatedBody.input?.length || translatedBody.contents?.length || translatedBody.request?.contents?.length || 0;
+    log?.debug?.("REQUEST", `${provider.toUpperCase()} | ${model} | ${msgCount} msgs`);
+
+    const streamController = createStreamController({
+      onDisconnect: (reason) => {
+        trackPendingRequest(model, provider, connectionId, false);
+        if (onDisconnect) onDisconnect(reason);
+      },
+      onError: () => trackPendingRequest(model, provider, connectionId, false),
+      log, provider, model, reqTag
+    });
+
+  const proxyOptions = {
+    connectionProxyEnabled: credentials?.providerSpecificData?.connectionProxyEnabled === true,
+    connectionProxyUrl: credentials?.providerSpecificData?.connectionProxyUrl || "",
+    connectionNoProxy: credentials?.providerSpecificData?.connectionNoProxy || "",
+    vercelRelayUrl: credentials?.providerSpecificData?.vercelRelayUrl || "",
+  };
+
+  if (proxyOptions.vercelRelayUrl) {
+    const connectionName = credentials?.connectionName || credentials?.connectionId || "unknown";
+    const poolId = credentials?.providerSpecificData?.connectionProxyPoolId || "none";
+    log?.info?.("PROXY", `${provider.toUpperCase()} | ${model} | conn=${connectionName} | pool=${poolId} | vercel-relay=${proxyOptions.vercelRelayUrl}`);
+  } else if (proxyOptions.connectionProxyEnabled && proxyOptions.connectionProxyUrl) {
+    let maskedProxyUrl = proxyOptions.connectionProxyUrl;
+    try {
+      const parsed = new URL(proxyOptions.connectionProxyUrl);
+      const host = parsed.hostname || "";
+      const port = parsed.port ? `:${parsed.port}` : "";
+      const protocol = parsed.protocol || "http:";
+      maskedProxyUrl = `${protocol}//${host}${port}`;
+    } catch {
+      // Keep raw if URL parsing fails
+    }
+
+    const poolId = credentials?.providerSpecificData?.connectionProxyPoolId || "none";
+    const connectionName = credentials?.connectionName || credentials?.connectionId || "unknown";
+    log?.info?.("PROXY", `${provider.toUpperCase()} | ${model} | conn=${connectionName} | pool=${poolId} | url=${maskedProxyUrl}`);
+  }
+
+  if (proxyOptions.connectionProxyEnabled && proxyOptions.connectionNoProxy) {
+    const connectionName = credentials?.connectionName || credentials?.connectionId || "unknown";
+    log?.debug?.("PROXY", `${provider.toUpperCase()} | ${model} | conn=${connectionName} | no_proxy=${proxyOptions.connectionNoProxy}`);
+  }
+
+  // Execute request
+  let providerResponse, providerUrl, providerHeaders, finalBody;
+  try {
+    const result = await executor.execute({ model, body: translatedBody, stream, credentials, signal: streamController.signal, log, proxyOptions });
+    providerResponse = result.response;
+    providerUrl = result.url;
+    providerHeaders = result.headers;
+    finalBody = result.transformedBody;
+    reqLogger.logTargetRequest(providerUrl, providerHeaders, finalBody);
+  } catch (error) {
+    trackPendingRequest(model, provider, connectionId, false, true);
+    appendRequestLog({ model, provider, connectionId, status: `FAILED ${error.name === "AbortError" ? 499 : HTTP_STATUS.BAD_GATEWAY}` }).catch(() => { });
+    saveRequestDetail(buildRequestDetail({
+      provider, model, connectionId,
+      latency: { ttft: 0, total: Date.now() - requestStartTime },
+      tokens: { prompt_tokens: 0, completion_tokens: 0 },
+      request: extractRequestConfig(body, stream),
+      providerRequest: translatedBody || null,
+      response: { error: error.message || String(error), status: error.name === "AbortError" ? 499 : 502, thinking: null },
+      pxpipe: pxpipeSummary,
+      status: "error"
+    })).catch(() => { });
+
+    if (error.name === "AbortError") {
+      streamController.handleError(error);
+      return createErrorResult(499, "Request aborted");
+    }
+    const errMsg = formatProviderError(error, provider, model, HTTP_STATUS.BAD_GATEWAY);
+    if (log?.errorLine) {
+      log.errorLine(reqTag, "✗", `ERROR 502 · ${provider}/${model} · ${Date.now() - requestStartTime}ms\n    ${errMsg}${error.stack ? `\n    ${error.stack}` : ""}`);
+    }
+    return createErrorResult(HTTP_STATUS.BAD_GATEWAY, errMsg);
+  }
+
+  // Handle 401/403 - try token refresh (skip for noAuth providers)
+  if (!executor.noAuth && (providerResponse.status === HTTP_STATUS.UNAUTHORIZED || providerResponse.status === HTTP_STATUS.FORBIDDEN)) {
+    try {
+      const newCredentials = await refreshWithRetry(() => executor.refreshCredentials(credentials, log), 3, log);
+      if (newCredentials?.accessToken || newCredentials?.copilotToken) {
+        if (log?.line) log.line(reqTag, "🔑", `TOKEN REFRESHED · ${provider}/${model}`);
+        Object.assign(credentials, newCredentials);
+        if (onCredentialsRefreshed) {
+          try { await onCredentialsRefreshed(newCredentials); } catch (e) { log?.warn?.("TOKEN", `onCredentialsRefreshed failed: ${e.message}`); }
+        }
+        try {
+          const retryResult = await executor.execute({ model, body: translatedBody, stream, credentials, signal: streamController.signal, log, proxyOptions });
+          if (retryResult.response.ok) { providerResponse = retryResult.response; providerUrl = retryResult.url; }
+        } catch { log?.warn?.("TOKEN", `${provider.toUpperCase()} | retry after refresh failed`); }
+      } else {
+        log?.warn?.("TOKEN", `${provider.toUpperCase()} | refresh failed`);
+      }
+    } catch (e) {
+      log?.warn?.("TOKEN", `${provider.toUpperCase()} | refresh threw: ${e.message}`);
+    }
+  }
+
+  // Provider returned error
+  if (!providerResponse.ok) {
+    trackPendingRequest(model, provider, connectionId, false, true);
+    const { statusCode, message, resetsAtMs } = await parseUpstreamError(providerResponse, executor);
+    appendRequestLog({ model, provider, connectionId, status: `FAILED ${statusCode}` }).catch(() => { });
+    saveRequestDetail(buildRequestDetail({
+      provider, model, connectionId,
+      latency: { ttft: 0, total: Date.now() - requestStartTime },
+      tokens: { prompt_tokens: 0, completion_tokens: 0 },
+      request: extractRequestConfig(body, stream),
+      providerRequest: finalBody || translatedBody || null,
+      response: { error: message, status: statusCode, thinking: null },
+      pxpipe: pxpipeSummary,
+      status: "error"
+    })).catch(() => { });
+
+    const errMsg = formatProviderError(new Error(message), provider, model, statusCode);
+    if (log?.errorLine) {
+      const urlStr = providerUrl ? `\n    URL: ${providerUrl}` : "";
+      log.errorLine(reqTag, "✗", `ERROR ${statusCode} · ${provider}/${model} · ${Date.now() - requestStartTime}ms${urlStr}\n    ${errMsg}`);
+    }
+    reqLogger.logError(new Error(message), finalBody || translatedBody);
+    return createErrorResult(statusCode, errMsg, resetsAtMs);
+  }
+
+  const sharedCtx = { provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, pxpipe: pxpipeSummary, reqTag, log };
+  const appendLog = (extra) => appendRequestLog({ model, provider, connectionId, ...extra }).catch(() => { });
+  const trackDone = () => trackPendingRequest(model, provider, connectionId, false);
+
+  // Provider forced streaming but client wants JSON
+  if (!clientRequestedStreaming && providerRequiresStreaming) {
+    const result = await handleForcedSSEToJson({ ...sharedCtx, providerResponse, sourceFormat, trackDone, appendLog });
+    if (result) { streamController.handleComplete(); return result; }
+  }
+
+  // True non-streaming response
+  if (!stream) {
+    const result = await handleNonStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat, reqLogger, toolNameMap, trackDone, appendLog });
+    streamController.handleComplete();
+    return result;
+  }
+
+  // Streaming response
+  const { onStreamComplete, streamDetailId } = buildOnStreamComplete({ ...sharedCtx });
+  return handleStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, streamController, onStreamComplete, streamDetailId });
+  } catch (error) {
+    trackPendingRequest(model, provider, connectionId, false);
+    throw error;
+  }
+}
+
+export function isTokenExpiringSoon(expiresAt, bufferMs = 5 * 60 * 1000) {
+  if (!expiresAt) return false;
+  return new Date(expiresAt).getTime() - Date.now() < bufferMs;
+}

package/open-sse/handlers/embeddingProviders/_base.js

@@ -0,0 +1,4 @@
+// Shared embedding helpers
+export function bearerAuth(creds) {
+  return { "Authorization": `Bearer ${creds.apiKey || creds.accessToken}` };
+}

package/open-sse/handlers/embeddingProviders/gemini.js

@@ -0,0 +1,54 @@
+// Google Gemini embeddings — embedContent / batchEmbedContents
+const BASE = "https://generativelanguage.googleapis.com/v1beta";
+
+function modelPath(model) {
+  return model.startsWith("models/") ? model : `models/${model}`;
+}
+
+export default {
+  buildUrl: (model, creds, { input } = {}) => {
+    const apiKey = creds.apiKey || creds.accessToken;
+    const path = modelPath(model);
+    const op = Array.isArray(input) ? "batchEmbedContents" : "embedContent";
+    return `${BASE}/${path}:${op}?key=${encodeURIComponent(apiKey)}`;
+  },
+  buildHeaders: () => ({ "Content-Type": "application/json" }),
+  buildBody: (model, { input, dimensions }) => {
+    const m = modelPath(model);
+    const outputDimensionality = Number(dimensions);
+    const hasOutputDimensionality = Number.isFinite(outputDimensionality) && outputDimensionality > 0;
+    if (Array.isArray(input)) {
+      return {
+        requests: input.map((text) => ({
+          model: m,
+          content: { parts: [{ text: String(text) }] },
+          ...(hasOutputDimensionality ? { outputDimensionality } : {}),
+        })),
+      };
+    }
+    return {
+      model: m,
+      content: { parts: [{ text: String(input) }] },
+      ...(hasOutputDimensionality ? { outputDimensionality } : {}),
+    };
+  },
+  normalize: (responseBody, model) => {
+    if (responseBody.object === "list" && Array.isArray(responseBody.data)) return responseBody;
+    let items = [];
+    if (Array.isArray(responseBody.embeddings)) {
+      items = responseBody.embeddings.map((emb, idx) => ({
+        object: "embedding",
+        index: idx,
+        embedding: emb.values || [],
+      }));
+    } else if (responseBody.embedding?.values) {
+      items = [{ object: "embedding", index: 0, embedding: responseBody.embedding.values }];
+    }
+    return {
+      object: "list",
+      data: items,
+      model,
+      usage: { prompt_tokens: 0, total_tokens: 0 },
+    };
+  },
+};

package/open-sse/handlers/embeddingProviders/index.js

@@ -0,0 +1,23 @@
+// Embeddings provider adapter registry
+import createOpenAIEmbeddingAdapter from "./openai.js";
+import gemini from "./gemini.js";
+import openaiCompatNode from "./openaiCompatNode.js";
+
+const OPENAI_COMPAT_PROVIDERS = [
+  "openai", "openrouter", "mistral", "voyage-ai", "fireworks",
+  "together", "nebius", "github", "nvidia", "jina-ai",
+];
+
+const ADAPTERS = {
+  ...Object.fromEntries(OPENAI_COMPAT_PROVIDERS.map((id) => [id, createOpenAIEmbeddingAdapter(id)])),
+  gemini,
+  google_ai_studio: gemini,
+};
+
+export function getEmbeddingAdapter(provider) {
+  if (ADAPTERS[provider]) return ADAPTERS[provider];
+  if (provider?.startsWith?.("openai-compatible-") || provider?.startsWith?.("custom-embedding-")) {
+    return openaiCompatNode;
+  }
+  return null;
+}

package/open-sse/handlers/embeddingProviders/openai.js

@@ -0,0 +1,39 @@
+// OpenAI-compatible embeddings adapter (most providers)
+import { bearerAuth } from "./_base.js";
+
+const ENDPOINTS = {
+  openai: "https://api.openai.com/v1/embeddings",
+  openrouter: "https://openrouter.ai/api/v1/embeddings",
+  mistral: "https://api.mistral.ai/v1/embeddings",
+  "voyage-ai": "https://api.voyageai.com/v1/embeddings",
+  fireworks: "https://api.fireworks.ai/inference/v1/embeddings",
+  together: "https://api.together.xyz/v1/embeddings",
+  nebius: "https://api.tokenfactory.nebius.com/v1/embeddings",
+  github: "https://models.github.ai/inference/embeddings",
+  nvidia: "https://integrate.api.nvidia.com/v1/embeddings",
+  "jina-ai": "https://api.jina.ai/v1/embeddings",
+};
+
+export default function createOpenAIEmbeddingAdapter(providerId) {
+  return {
+    buildUrl: () => ENDPOINTS[providerId],
+    buildHeaders: (creds) => {
+      const headers = { "Content-Type": "application/json", ...bearerAuth(creds) };
+      if (providerId === "openrouter") {
+        headers["HTTP-Referer"] = "https://endpoint-proxy.local";
+        headers["X-Title"] = "Endpoint Proxy";
+      }
+      return headers;
+    },
+    buildBody: (model, { input, encoding_format, dimensions }) => {
+      const body = { model, input };
+      if (encoding_format) body.encoding_format = encoding_format;
+      if (dimensions != null && dimensions !== "") {
+        const dim = Number(dimensions);
+        if (Number.isFinite(dim) && dim > 0) body.dimensions = dim;
+      }
+      return body;
+    },
+    normalize: (responseBody) => responseBody,
+  };
+}

package/open-sse/handlers/embeddingProviders/openaiCompatNode.js

@@ -0,0 +1,13 @@
+// Custom node providers (openai-compatible-* / custom-embedding-*) — baseUrl from credentials
+import createOpenAIEmbeddingAdapter from "./openai.js";
+
+const baseAdapter = createOpenAIEmbeddingAdapter("openai");
+
+export default {
+  ...baseAdapter,
+  buildUrl: (_model, creds) => {
+    const rawBaseUrl = creds?.providerSpecificData?.baseUrl || "https://api.openai.com/v1";
+    const baseUrl = rawBaseUrl.replace(/\/$/, "").replace(/\/embeddings$/, "");
+    return `${baseUrl}/embeddings`;
+  },
+};