Merge branch 'master' into gitea/new_feature

open-sse/handlers/chatCore.js

@@ -291,12 +291,16 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 
   // Execute request
   let providerResponse, providerUrl, providerHeaders, finalBody;
+  // Most executors return their registry format. Cursor AgentService is an
+  // 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 });
     providerResponse = result.response;
     providerUrl = result.url;
     providerHeaders = result.headers;
     finalBody = result.transformedBody;
+    providerResponseFormat = result.responseFormat || targetFormat;
     reqLogger.logTargetRequest(providerUrl, providerHeaders, finalBody);
   } catch (error) {
     trackPendingRequest(model, provider, connectionId, false, true);
@@ -326,7 +330,18 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
   // 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);
+      // Mutate credentials after each successful refresh: rotating refresh_token
+      // providers (xAI/grok-cli) issue a new RT on every refresh; without this,
+      // refreshWithRetry's 2nd/3rd attempt reuses the already-consumed RT →
+      // invalid_grant → auth_failed retryable=false.
+      const newCredentials = await refreshWithRetry(async () => {
+        const result = await executor.refreshCredentials(credentials, log);
+        if (result?.refreshToken && result.refreshToken !== credentials.refreshToken) {
+          if (result.accessToken) credentials.accessToken = result.accessToken;
+          credentials.refreshToken = result.refreshToken;
+        }
+        return result;
+      }, 3, log);
       if (newCredentials?.accessToken || newCredentials?.copilotToken) {
         if (log?.line) log.line(reqTag, "🔑", `TOKEN REFRESHED · ${provider}/${model}`);
         Object.assign(credentials, newCredentials);
@@ -335,7 +350,11 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
         }
         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; }
+          if (retryResult.response.ok) {
+            providerResponse = retryResult.response;
+            providerUrl = retryResult.url;
+            providerResponseFormat = retryResult.responseFormat || targetFormat;
+          }
         } catch { log?.warn?.("TOKEN", `${provider.toUpperCase()} | retry after refresh failed`); }
       } else {
         log?.warn?.("TOKEN", `${provider.toUpperCase()} | refresh failed`);
@@ -382,14 +401,14 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
 
   // True non-streaming response
   if (!stream) {
-    const result = await handleNonStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat, reqLogger, toolNameMap, trackDone, appendLog });
+    const result = await handleNonStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat: providerResponseFormat, 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 });
+  return handleStreamingResponse({ ...sharedCtx, providerResponse, sourceFormat, targetFormat: providerResponseFormat, userAgent, reqLogger, toolNameMap, streamController, onStreamComplete, streamDetailId });
 }
 
 export function isTokenExpiringSoon(expiresAt, bufferMs = 5 * 60 * 1000) {

open-sse/handlers/chatCore/sseToJsonHandler.js

@@ -40,15 +40,21 @@ function pickAssistantMessageForChatCompletion(output) {
  */
 export function parseSSEToOpenAIResponse(rawSSE, fallbackModel) {
   const chunks = [];
+  let streamError = null;
 
   for (const line of String(rawSSE || "").split("\n")) {
     const trimmed = line.trim();
     if (!trimmed.startsWith("data:")) continue;
     const payload = trimmed.slice(5).trim();
     if (!payload || payload === "[DONE]") continue;
-    try { chunks.push(JSON.parse(payload)); } catch { /* ignore malformed lines */ }
+    try {
+      const chunk = JSON.parse(payload);
+      if (chunk?.error) streamError = chunk.error;
+      else chunks.push(chunk);
+    } catch { /* ignore malformed lines */ }
   }
 
+  if (streamError) return { error: streamError };
   if (chunks.length === 0) return null;
 
   const first = chunks[0];
@@ -196,6 +202,12 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, pr
     const sseText = await providerResponse.text();
     const parsed = parseSSEToOpenAIResponse(sseText, model);
     if (!parsed) return createErrorResult(HTTP_STATUS.BAD_GATEWAY, "Invalid SSE response for non-streaming request");
+    if (parsed.error) {
+      return createErrorResult(
+        HTTP_STATUS.BAD_GATEWAY,
+        parsed.error.message || "Upstream SSE stream failed"
+      );
+    }
 
     if (onRequestSuccess) await onRequestSuccess();
 

open-sse/handlers/embeddingsCore.js

@@ -116,6 +116,7 @@ export async function handleEmbeddingsCore({
 
   return {
     success: true,
+    usage: normalized.usage || null,
     response: new Response(JSON.stringify(normalized), {
       headers: {
         "Content-Type": "application/json",

open-sse/handlers/fetch/index.js

@@ -49,7 +49,10 @@ function truncate(text, max) {
 }
 
 function parseJinaTitle(text) {
-  const m = String(text || "").match(/^\s*#\s+(.+)$/m);
+  const source = String(text || "");
+  const metadataTitle = source.match(/^\s*Title:\s*(.+)$/mi);
+  if (metadataTitle) return metadataTitle[1].trim();
+  const m = source.match(/^\s*#\s+(.+)$/m);
   return m ? m[1].trim() : null;
 }
 
@@ -151,11 +154,14 @@ async function runFirecrawl({ url, fmt, timeoutMs, apiKey, maxCharacters, costPe
 }
 
 async function runJina({ url, fmt, timeoutMs, apiKey, maxCharacters, costPerQuery, startedAt }) {
-  const target = `https://r.jina.ai/${encodeURIComponent(url)}`;
   const upstreamStart = Date.now();
-  const r = await tryFetch(target, {
-    method: "GET",
-    headers: apiKey ? { authorization: `Bearer ${apiKey}` } : {}
+  const r = await tryFetch("https://r.jina.ai/", {
+    method: "POST",
+    headers: {
+      "content-type": "application/json",
+      ...(apiKey ? { authorization: `Bearer ${apiKey}` } : {})
+    },
+    body: JSON.stringify({ url })
   }, timeoutMs);
 
   if (!r.ok) {

open-sse/handlers/search/callers.js

@@ -1,7 +1,6 @@
 /**
  * Search Provider Request Builders
  *
- * Ported from OmniRoute open-sse/handlers/search.ts (lines 223-610).
  * Builds HTTP request `{ url, init }` for 10 search providers.
  *
  * @typedef {Object} SearchProviderConfig

open-sse/handlers/search/normalizers.js

@@ -1,7 +1,6 @@
 /**
  * Search Response Normalizers
  *
- * Ported from OmniRoute open-sse/handlers/search.ts.
  * Each normalizer maps a provider-specific response into the unified SearchResult shape.
  */