@fudrouter/fsrouter 0.6.72 → 0.6.74

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

@@ -1,19 +1,74 @@
 import { FORMATS } from "../../translator/formats.js";
 import { needsTranslation } from "../../translator/index.js";
+import { fromOpenAIFinish } from "../../translator/concerns/finishReason.js";
 import { ollamaBodyToOpenAI } from "../../translator/response/ollama-to-openai.js";
 import { addBufferToUsage, filterUsageForFormat } from "../../utils/usageTracking.js";
 import { createErrorResult } from "../../utils/error.js";
 import { HTTP_STATUS } from "../../config/runtimeConfig.js";
 import { parseSSEToOpenAIResponse } from "./sseToJsonHandler.js";
-import { buildRequestDetail, extractRequestConfig, extractUsageFromResponse, saveUsageStats } from "./requestDetail.js";
-import { appendRequestLog, saveRequestDetail } from '../../../dist/lib/usageDb.js';
+import { buildRequestDetail, extractRequestConfig, extractUsageFromResponse, saveUsageStats, formatDoneLine } from "./requestDetail.js";
+import { appendRequestLog, saveRequestDetail } from '../../dist/lib/usageDb.js';
 import { decloakToolNames } from "../../utils/claudeCloaking.js";
 
+function parseToolArguments(value) {
+  if (!value) return {};
+  if (typeof value === "object") return value;
+  try {
+    return JSON.parse(value);
+  } catch {
+    return {};
+  }
+}
+
+function openAICompletionToClaudeMessage(responseBody) {
+  if (!responseBody?.choices?.[0]) return responseBody;
+  const choice = responseBody.choices[0];
+  const message = choice.message || {};
+  const content = [];
+
+  const reasoning = message.reasoning_content || message.provider_specific_fields?.reasoning_content || "";
+  if (reasoning) {
+    content.push({ type: "thinking", thinking: reasoning });
+  }
+  if (typeof message.content === "string" && message.content.length > 0) {
+    content.push({ type: "text", text: message.content });
+  }
+  for (const toolCall of message.tool_calls || []) {
+    const fn = toolCall.function || {};
+    content.push({
+      type: "tool_use",
+      id: toolCall.id || `toolu_${Date.now()}_${content.length}`,
+      name: fn.name || toolCall.name || "",
+      input: parseToolArguments(fn.arguments || toolCall.arguments),
+    });
+  }
+  if (content.length === 0) content.push({ type: "text", text: "" });
+
+  const usage = responseBody.usage || {};
+  return {
+    id: String(responseBody.id || `msg_${Date.now()}`).replace(/^chatcmpl-/, ""),
+    type: "message",
+    role: "assistant",
+    model: responseBody.model || "unknown",
+    content,
+    stop_reason: fromOpenAIFinish(choice.finish_reason, FORMATS.CLAUDE),
+    stop_sequence: null,
+    usage: {
+      input_tokens: usage.prompt_tokens || usage.input_tokens || 0,
+      output_tokens: usage.completion_tokens || usage.output_tokens || 0,
+    },
+  };
+}
+
 /**
  * Translate non-streaming response body from provider format → OpenAI format.
  */
 export function translateNonStreamingResponse(responseBody, targetFormat, sourceFormat) {
-  if (targetFormat === sourceFormat || targetFormat === FORMATS.OPENAI) return responseBody;
+  if (targetFormat === sourceFormat) return responseBody;
+  if (targetFormat === FORMATS.OPENAI && sourceFormat === FORMATS.CLAUDE) {
+    return openAICompletionToClaudeMessage(responseBody);
+  }
+  if (targetFormat === FORMATS.OPENAI) return responseBody;
 
   // Gemini / Antigravity
   if (targetFormat === FORMATS.GEMINI || targetFormat === FORMATS.ANTIGRAVITY || targetFormat === FORMATS.GEMINI_CLI || targetFormat === FORMATS.VERTEX) {
@@ -37,6 +92,12 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
             function: { name: part.functionCall.name, arguments: JSON.stringify(part.functionCall.args || {}) }
           });
         }
+        // Handle inline image data (from image generation models)
+        const inlineData = part.inlineData || part.inline_data;
+        if (inlineData?.data) {
+          const mimeType = inlineData.mimeType || inlineData.mime_type || "image/png";
+          textContent += `\n![image](data:${mimeType};base64,${inlineData.data})\n`;
+        }
       }
     }
 
@@ -76,7 +137,12 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
     // missing/null (e.g. M3 with max_tokens:1 spends the budget on thinking
     // and returns `content: null`). Returning the raw body would leave the
     // OpenAI client without a `choices` array and surface as a UI test error.
-    if (responseBody.content && !Array.isArray(responseBody.content)) return responseBody;
+    // Early return if the response is already in OpenAI format (has choices array)
+    // or if it has content as a non-array value (likely a different non-Claude format).
+    // Some providers (e.g. xiaomi-tokenplan) return OpenAI-format responses even when
+    // the request was translated to Claude format — the targetFormat is Claude but the
+    // actual response is OpenAI-native and needs no further translation.
+    if (responseBody.choices || (responseBody.content && !Array.isArray(responseBody.content))) return responseBody;
 
     let textContent = "", thinkingContent = "";
     const toolCalls = [];
@@ -132,7 +198,7 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
 /**
  * Handle non-streaming response from provider.
  */
-export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, trackDone, appendLog }) {
+export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, trackDone, appendLog, pxpipe, reqTag, log }) {
   trackDone();
   const contentType = providerResponse.headers.get("content-type") || "";
   let responseBody;
@@ -156,18 +222,26 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
   }
 
   reqLogger.logProviderResponse(providerResponse.status, providerResponse.statusText, providerResponse.headers, responseBody);
-  if (onRequestSuccess) await onRequestSuccess();
+  if (onRequestSuccess) {
+    Promise.resolve()
+      .then(onRequestSuccess)
+      .catch(err => {
+        console.error("[ChatCore] onRequestSuccess failed:", err?.message || err);
+      });
+  }
 
   // Decloak tool_use names once on raw Claude body, before any translation (INPUT side)
   responseBody = decloakToolNames(responseBody, toolNameMap);
 
   const usage = extractUsageFromResponse(responseBody);
   appendLog({ tokens: usage, status: "200 OK" });
-  saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint });
+  saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint, silent: true });
+  if (log?.line) log.line(reqTag, "📊", formatDoneLine({ usage, latency: { total: Date.now() - requestStartTime } }));
 
   const translatedResponse = needsTranslation(targetFormat, sourceFormat)
     ? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat)
     : responseBody;
+  const isClaudeMessageResponse = sourceFormat === FORMATS.CLAUDE && translatedResponse?.type === "message";
 
   // Fix finish_reason for tool_calls: some providers return non-standard values (e.g. "other")
   if (translatedResponse?.choices?.[0]) {
@@ -180,95 +254,32 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
   }
 
   // Ensure OpenAI-required fields
-  if (!translatedResponse.object) translatedResponse.object = "chat.completion";
-  if (!translatedResponse.created) translatedResponse.created = Math.floor(Date.now() / 1000);
+  if (!isClaudeMessageResponse) {
+    if (!translatedResponse.object) translatedResponse.object = "chat.completion";
+    if (!translatedResponse.created) translatedResponse.created = Math.floor(Date.now() / 1000);
+  }
 
   // Strip Azure-specific fields
-  delete translatedResponse.prompt_filter_results;
-  if (translatedResponse?.choices) {
-    for (const choice of translatedResponse.choices) delete choice.content_filter_results;
+  if (!isClaudeMessageResponse) {
+    delete translatedResponse.prompt_filter_results;
+    if (translatedResponse?.choices) {
+      for (const choice of translatedResponse.choices) delete choice.content_filter_results;
+    }
   }
 
   if (translatedResponse?.usage) {
     translatedResponse.usage = filterUsageForFormat(addBufferToUsage(translatedResponse.usage), sourceFormat);
   }
 
-  // Strip reasoning_content — some clients (e.g. Firecrawl AI SDK) have JSON parsers that
-  // break on this non-standard field, even though OpenAI allows it in extensions.
-  if (translatedResponse?.choices && sourceFormat !== FORMATS.CLAUDE) {
+  // Strip reasoning_content only when content is non-empty.
+  // When content is empty (e.g. thinking models that used all tokens for reasoning),
+  // reasoning_content is the only useful output and must be preserved.
+  if (!isClaudeMessageResponse && translatedResponse?.choices) {
     for (const choice of translatedResponse.choices) {
-      if (choice?.message) delete choice.message.reasoning_content;
-    }
-  }
-
-  // If client sent Anthropic Messages format (/v1/messages), convert response back to
-  // Anthropic format. 9router always works in OpenAI format internally; this step
-  // is the reverse-translation for Claude Code / Anthropic SDK clients.
-  if (sourceFormat === FORMATS.CLAUDE) {
-    const choice = translatedResponse?.choices?.[0];
-    const msg = choice?.message || {};
-    const contentBlocks = [];
-    if (msg.reasoning_content) contentBlocks.push({ type: "thinking", thinking: msg.reasoning_content });
-    if (msg.content) contentBlocks.push({ type: "text", text: msg.content });
-    if (Array.isArray(msg.tool_calls)) {
-      for (const tc of msg.tool_calls) {
-        let input = {};
-        try { input = JSON.parse(tc.function?.arguments || "{}"); } catch {}
-        contentBlocks.push({ type: "tool_use", id: tc.id, name: tc.function?.name, input });
+      if (choice?.message?.reasoning_content && choice.message.content) {
+        delete choice.message.reasoning_content;
       }
     }
-    // Claude Code requires at least one text or tool_use block — cannot be only thinking
-    const hasTextOrTool = contentBlocks.some(b => b.type === "text" || b.type === "tool_use");
-    if (!hasTextOrTool) contentBlocks.push({ type: "text", text: "" });
-
-    let stopReason = "end_turn";
-    const fr = choice?.finish_reason;
-    if (fr === "tool_calls") stopReason = "tool_use";
-    else if (fr === "length") stopReason = "max_tokens";
-
-    const anthropicResponse = {
-      id: translatedResponse.id || `msg_${Date.now()}`,
-      type: "message",
-      role: "assistant",
-      content: contentBlocks.length ? contentBlocks : [{ type: "text", text: "" }],
-      model: translatedResponse.model || model,
-      stop_reason: stopReason,
-      stop_sequence: null,
-    };
-    if (translatedResponse.usage) {
-      anthropicResponse.usage = {
-        input_tokens: translatedResponse.usage.prompt_tokens || 0,
-        output_tokens: translatedResponse.usage.completion_tokens || 0,
-      };
-    } else {
-      anthropicResponse.usage = { input_tokens: 0, output_tokens: 0 };
-    }
-
-    reqLogger.logConvertedResponse(anthropicResponse);
-    const totalLatency = Date.now() - requestStartTime;
-    saveRequestDetail(buildRequestDetail({
-      provider, model, connectionId,
-      latency: { ttft: totalLatency, total: totalLatency },
-      tokens: usage || { prompt_tokens: 0, completion_tokens: 0 },
-      request: extractRequestConfig(body, stream),
-      providerRequest: finalBody || translatedBody || null,
-      providerResponse: responseBody || null,
-      response: {
-        content: msg.content || null,
-        thinking: msg.reasoning_content || null,
-        finish_reason: choice?.finish_reason || "unknown"
-      },
-      status: "success"
-    }, { endpoint: clientRawRequest?.endpoint || null })).catch(err => {
-      console.error("[RequestDetail] Failed to save:", err.message);
-    });
-
-    return {
-      success: true,
-      response: new Response(JSON.stringify(anthropicResponse), {
-        headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" }
-      })
-    };
   }
 
   reqLogger.logConvertedResponse(translatedResponse);
@@ -286,6 +297,7 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
       thinking: translatedResponse?.choices?.[0]?.message?.reasoning_content || translatedResponse?.reasoning_content || null,
       finish_reason: translatedResponse?.choices?.[0]?.finish_reason || "unknown"
     },
+    pxpipe,
     status: "success"
   }, { endpoint: clientRawRequest?.endpoint || null })).catch(err => {
     console.error("[RequestDetail] Failed to save:", err.message);

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

@@ -1,5 +1,6 @@
-import { saveRequestUsage, appendRequestLog, saveRequestDetail } from '../../../dist/lib/usageDb.js';
+import { saveRequestUsage, appendRequestLog, saveRequestDetail } from '../../dist/lib/usageDb.js';
 import { COLORS } from "../../utils/stream.js";
+import { canonicalizeUsage } from "../../utils/usageTracking.js";
 
 const OPTIONAL_PARAMS = [
   "temperature", "top_p", "top_k",
@@ -48,7 +49,8 @@ export function extractUsageFromResponse(responseBody) {
     return {
       prompt_tokens: responseBody.usageMetadata.promptTokenCount || 0,
       completion_tokens: responseBody.usageMetadata.candidatesTokenCount || 0,
-      reasoning_tokens: responseBody.usageMetadata.thoughtsTokenCount
+      cached_tokens: responseBody.usageMetadata.cachedContentTokenCount || 0,
+      reasoning_tokens: responseBody.usageMetadata.thoughtsTokenCount || 0
     };
   }
 
@@ -67,12 +69,31 @@ export function buildRequestDetail(base, overrides = {}) {
     providerRequest: base.providerRequest || null,
     providerResponse: base.providerResponse || null,
     response: base.response || {},
+    pxpipe: base.pxpipe || undefined,
     status: base.status || "success",
     ...overrides
   };
 }
 
-export function saveUsageStats({ provider, model, tokens, connectionId, apiKey, endpoint, label = "USAGE" }) {
+// Build the "done" summary: duration, ttft, in/out tokens with cache breakdown
+export function formatDoneLine({ usage, latency }) {
+  const u = usage || {};
+  const inTok = u.prompt_tokens ?? u.input_tokens ?? 0;
+  const outTok = u.completion_tokens ?? u.output_tokens ?? 0;
+  const cacheRead = u.cache_read_input_tokens ?? u.cached_tokens ?? u.prompt_tokens_details?.cached_tokens ?? 0;
+  const cacheCreate = u.cache_creation_input_tokens ?? 0;
+  let inStr = `IN ${inTok}`;
+  if (cacheRead || cacheCreate) {
+    const parts = [];
+    if (cacheRead) parts.push(`↻${cacheRead}`);
+    if (cacheCreate) parts.push(`+${cacheCreate}`);
+    inStr += ` (CACHE ${parts.join(" ")})`;
+  }
+  const ttftStr = latency?.ttft ? ` · TTFT ${latency.ttft}ms` : "";
+  return `DONE ${latency?.total ?? 0}ms${ttftStr} · ${inStr} · OUT ${outTok}`;
+}
+
+export function saveUsageStats({ provider, model, tokens, connectionId, apiKey, endpoint, label = "USAGE", silent = false }) {
   if (!tokens || typeof tokens !== "object") return;
 
   const inTokens = tokens.input_tokens ?? tokens.prompt_tokens ?? 0;
@@ -80,12 +101,15 @@ export function saveUsageStats({ provider, model, tokens, connectionId, apiKey,
 
   if (inTokens === 0 && outTokens === 0) return;
 
-  const time = new Date().toLocaleTimeString("en-US", { hour12: false, hour: "2-digit", minute: "2-digit", second: "2-digit" });
-  const accountSuffix = connectionId ? ` | account=${connectionId.slice(0, 8)}...` : "";
-  console.log(`${COLORS.green}[${time}] 📊 [${label}] ${provider.toUpperCase()} | in=${inTokens} | out=${outTokens}${accountSuffix}${COLORS.reset}`);
+  if (!silent) {
+    const time = new Date().toLocaleTimeString("en-US", { hour12: false, hour: "2-digit", minute: "2-digit", second: "2-digit" });
+    const accountSuffix = connectionId ? ` | account=${connectionId.slice(0, 8)}...` : "";
+    console.log(`${COLORS.green}[${time}] 📊 [${label}] ${provider.toUpperCase()} | in=${inTokens} | out=${outTokens}${accountSuffix}${COLORS.reset}`);
+  }
 
-  // Normalize to OpenAI token shape for storage
-  const normalized = {
+  // Canonicalize to one storage convention (prompt_tokens cache-inclusive) so
+  // cached/cache-creation tokens survive to cost calc + stats. See canonicalizeUsage.
+  const normalized = canonicalizeUsage(tokens) || {
     prompt_tokens: tokens.prompt_tokens ?? tokens.input_tokens ?? 0,
     completion_tokens: tokens.completion_tokens ?? tokens.output_tokens ?? 0
   };

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

@@ -2,8 +2,12 @@ import { convertResponsesStreamToJson } from "../../transformer/streamToJsonConv
 import { createErrorResult } from "../../utils/error.js";
 import { HTTP_STATUS } from "../../config/runtimeConfig.js";
 import { FORMATS } from "../../translator/formats.js";
-import { buildRequestDetail, extractRequestConfig, saveUsageStats } from "./requestDetail.js";
-import { saveRequestDetail, appendRequestLog } from '../../../dist/lib/usageDb.js';
+import { PROVIDERS } from "../../config/providers.js";
+import { buildRequestDetail, extractRequestConfig, saveUsageStats, formatDoneLine } from "./requestDetail.js";
+
+// Responses-API providers (e.g. codex) may emit SSE without content-type + use Responses output shape
+const isResponsesProvider = (p) => PROVIDERS[p]?.format === FORMATS.OPENAI_RESPONSES;
+import { saveRequestDetail, appendRequestLog } from '../../dist/lib/usageDb.js';
 
 function textFromResponsesMessageItem(item) {
   if (!item?.content || !Array.isArray(item.content)) return "";
@@ -98,9 +102,9 @@ export function parseSSEToOpenAIResponse(rawSSE, fallbackModel) {
  * Handle case: provider forced streaming but client wants JSON.
  * Supports both Codex/Responses API SSE and standard Chat Completions SSE.
  */
-export async function handleForcedSSEToJson({ providerResponse, sourceFormat, provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, trackDone, appendLog }) {
+export async function handleForcedSSEToJson({ providerResponse, sourceFormat, provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, trackDone, appendLog, reqTag, log }) {
   const contentType = providerResponse.headers.get("content-type") || "";
-  const isSSE = contentType.includes("text/event-stream") || (contentType === "" && provider === "codex");
+  const isSSE = contentType.includes("text/event-stream") || (contentType === "" && isResponsesProvider(provider));
   if (!isSSE) return null; // not handled here
 
   trackDone();
@@ -112,7 +116,7 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, pr
   };
 
   // Codex/Responses API SSE path
-  const isCodexResponsesApi = provider === "codex" || sourceFormat === FORMATS.OPENAI_RESPONSES;
+  const isCodexResponsesApi = isResponsesProvider(provider) || sourceFormat === FORMATS.OPENAI_RESPONSES;
   if (isCodexResponsesApi) {
     try {
       const jsonResponse = await convertResponsesStreamToJson(providerResponse.body);
@@ -120,7 +124,8 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, pr
 
       const usage = jsonResponse.usage || {};
       appendLog({ tokens: usage, status: "200 OK" });
-      saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint });
+      saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint, silent: true });
+      if (log?.line) log.line(reqTag, "📊", formatDoneLine({ usage, latency: { total: Date.now() - requestStartTime } }));
 
       const { msgItem, textContent } = pickAssistantMessageForChatCompletion(jsonResponse.output);
       const totalLatency = Date.now() - requestStartTime;
@@ -196,7 +201,8 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, pr
 
     const usage = parsed.usage || {};
     appendLog({ tokens: usage, status: "200 OK" });
-    saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint });
+    saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint, silent: true });
+    if (log?.line) log.line(reqTag, "📊", formatDoneLine({ usage, latency: { total: Date.now() - requestStartTime } }));
 
     const totalLatency = Date.now() - requestStartTime;
     saveRequestDetail(buildRequestDetail({

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

@@ -2,15 +2,21 @@ 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 { PROVIDERS } from "../../config/providers.js";
+import { STREAM_STALL_TIMEOUT_MS } from "../../config/runtimeConfig.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": "*"
+import { buildRequestDetail, extractRequestConfig, saveUsageStats, formatDoneLine } from "./requestDetail.js";
+import { saveRequestDetail } from '../../dist/lib/usageDb.js';
+import { SSE_HEADERS_CORS as SSE_HEADERS } from "../../utils/sseConstants.js";
+
+// Codex returns Responses API SSE → which client format to translate INTO, by request sourceFormat.
+// Gemini-family all map to ANTIGRAVITY decoder; unknown sources fall back to OPENAI.
+const CODEX_SOURCE_TO_TARGET = {
+  [FORMATS.OPENAI_RESPONSES]: FORMATS.OPENAI_RESPONSES,
+  [FORMATS.CLAUDE]: FORMATS.CLAUDE,
+  [FORMATS.ANTIGRAVITY]: FORMATS.ANTIGRAVITY,
+  [FORMATS.GEMINI]: FORMATS.ANTIGRAVITY,
+  [FORMATS.GEMINI_CLI]: FORMATS.ANTIGRAVITY,
 };
 
 /**
@@ -18,15 +24,12 @@ const SSE_HEADERS = {
  */
 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;
+  // Responses-API providers (e.g. codex) emit Responses SSE → translate into client format
+  const isResponsesProvider = PROVIDERS[provider]?.format === FORMATS.OPENAI_RESPONSES;
+  const needsCodexTranslation = isResponsesProvider && 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;
+    const codexTarget = CODEX_SOURCE_TO_TARGET[sourceFormat] || FORMATS.OPENAI;
     return createSSETransformStreamWithLogger(FORMATS.OPENAI_RESPONSES, codexTarget, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey);
   }
 
@@ -40,19 +43,63 @@ function buildTransformStream({ provider, sourceFormat, targetFormat, userAgent,
 /**
  * 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();
+export async function handleStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, userAgent, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, streamController, onStreamComplete, streamDetailId, pxpipe, reqTag, log }) {
+  if (onRequestSuccess) {
+    Promise.resolve()
+      .then(onRequestSuccess)
+      .catch(err => {
+        console.error("[ChatCore] onRequestSuccess failed:", err?.message || err);
+      });
+  }
+
+  // When upstream returns HTML/text instead of SSE (e.g. Cloudflare 5xx error
+  // page), piping it through the SSE transform stream causes Next.js
+  // "failed to pipe response" and crashes the chat router. Read the body,
+  // pull a short human-readable message from the <title>, sanitize it, and
+  // return a clean JSON error instead. The message is stripped of HTML tags
+  // and clamped so untrusted upstream text never reaches the client verbatim
+  // (the UI may render error.message as HTML).
+  const upstreamContentType = (providerResponse.headers.get('content-type') || '').toLowerCase();
+  if (upstreamContentType && !upstreamContentType.includes('text/event-stream') && !upstreamContentType.includes('application/json')) {
+    const bodyText = await providerResponse.text().catch(() => '');
+    const titleMatch = bodyText.match(/<title>([^<]+)<\/title>/i);
+    const sanitizedTitle = (titleMatch?.[1] || '').replace(/<[^>]*>/g, '').replace(/[\r\n]+/g, ' ').trim().slice(0, 160);
+    const shortMsg = sanitizedTitle
+      || (bodyText.length < 200 ? bodyText.replace(/<[^>]*>/g, '').trim().slice(0, 160) : `Upstream returned non-SSE response (${upstreamContentType})`);
+    const status = providerResponse.status || 502;
+    if (log?.errorLine) log.errorLine(reqTag, "✗", `BLOCKED ${status} · ${provider}/${model} · non-SSE (${upstreamContentType})\n    ${shortMsg}`);
+    else console.warn(`[STREAM] ${provider} | ${model} | blocked pipe: ${shortMsg} [${status}]`);
+    streamController?.handleError?.(new Error(`upstream non-SSE: ${status}`));
+    return {
+      success: false,
+      response: new Response(JSON.stringify({ error: { message: `[${status}]: ${shortMsg}` } }), {
+        status,
+        headers: { 'Content-Type': 'application/json', 'Access-Control-Allow-Origin': '*' },
+      }),
+    };
+  }
 
   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).
+  const stallTimeoutMs = PROVIDERS[provider]?.stallTimeoutMs || STREAM_STALL_TIMEOUT_MS;
+  const transformedBody = pipeWithDisconnect(providerResponse, transformStream, streamController, onAbortTerminal, stallTimeoutMs);
+
+  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,
+    providerResponse: "[Streaming - raw response not captured]",
+    response: { content: "[Streaming in progress...]", thinking: null, type: "streaming" },
+    pxpipe,
+    status: "success"
+  }, { id: streamDetailId })).catch(err => {
+    console.error("[RequestDetail] Failed to save streaming request:", err.message);
+  });
 
   return {
     success: true,
@@ -63,7 +110,7 @@ export function handleStreamingResponse({ providerResponse, provider, model, sou
 /**
  * Build onStreamComplete callback for streaming usage tracking.
  */
-export function buildOnStreamComplete({ provider, model, connectionId, apiKey, requestStartTime, body, stream, finalBody, translatedBody, clientRawRequest }) {
+export function buildOnStreamComplete({ provider, model, connectionId, apiKey, requestStartTime, body, stream, finalBody, translatedBody, clientRawRequest, pxpipe, reqTag, log }) {
   const streamDetailId = `${Date.now()}-${Math.random().toString(36).slice(2, 11)}`;
 
   const onStreamComplete = (contentObj, usage, ttftAt) => {
@@ -82,14 +129,16 @@ export function buildOnStreamComplete({ provider, model, connectionId, apiKey, r
       providerRequest: finalBody || translatedBody || null,
       providerResponse: safeContent,
       response: { content: safeContent, thinking: safeThinking, type: "streaming" },
+      pxpipe,
       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" });
+    // Persist stream usage to DB (no console line; the "📊 done" line below is authoritative)
+    saveUsageStats({ provider, model, tokens: usage, connectionId, apiKey, endpoint: clientRawRequest?.endpoint, label: "STREAM USAGE", silent: true });
+    if (log?.line) log.line(reqTag, "📊", formatDoneLine({ usage, latency }));
   };
 
   return { onStreamComplete, streamDetailId };
 }
-