Merge remote-tracking branch 'origin/master' into gitea/feature/end

Resolved conflicts taking origin/master (v0.5.55) as canonical, with local
features re-applied:
- runtime log level (LOG_LEVEL env + dashboard Settings → Logging, applied
  immediately and persisted across restarts)
- free/noAuth provider enable/disable toggle via providerStrategies.enabled
- parallel model testing (Test All Models / Test Selected Keys)

open-sse/handlers/chatCore/nonStreamingHandler.js

@@ -6,9 +6,10 @@ import { addBufferToUsage, filterUsageForFormat } from "../../utils/usageTrackin
 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 { buildRequestDetail, extractRequestConfig, extractUsageFromResponse, saveUsageStats, formatDoneLine } from "./requestDetail.js";
 import { appendRequestLog, saveRequestDetail } from "@/lib/usageDb.js";
 import { decloakToolNames } from "../../utils/claudeCloaking.js";
+import { ROLE, RESPONSES_ITEM } from "../../translator/schema/index.js";
 
 function parseToolArguments(value) {
   if (!value) return {};
@@ -60,11 +61,93 @@ function openAICompletionToClaudeMessage(responseBody) {
   };
 }
 
+/**
+ * Convert an OpenAI Chat Completions non-streaming response body into the
+ * OpenAI Responses API shape. Used when a Responses-format client (e.g. Codex)
+ * is routed to a Chat Completions upstream and `stream:false` — the streaming
+ * path already emits Responses events, but the JSON path returned a raw
+ * `chat.completion` body, so tool_calls were invisible to Responses clients.
+ */
+function extractCustomToolInput(argumentsValue) {
+  const argumentsText = typeof argumentsValue === "string" ? argumentsValue : JSON.stringify(argumentsValue || {});
+  try {
+    const parsed = JSON.parse(argumentsText);
+    if (parsed && typeof parsed === "object" && typeof parsed.input === "string") return parsed.input;
+  } catch { /* raw freeform input */ }
+  return argumentsText;
+}
+
+function openAICompletionToResponses(responseBody, customToolNames = null) {
+  const choice = responseBody?.choices?.[0];
+  if (!choice) return responseBody;
+
+  const message = choice.message || {};
+  const output = [];
+
+  // Reasoning → a reasoning item (summary text), mirroring the streaming path.
+  const reasoning = message.reasoning_content || message.reasoning;
+  if (typeof reasoning === "string" && reasoning.length > 0) {
+    output.push({
+      type: RESPONSES_ITEM.REASONING,
+      summary: [{ type: RESPONSES_ITEM.SUMMARY_TEXT, text: reasoning }],
+    });
+  }
+
+  // Assistant text → a message item with output_text content.
+  const text = typeof message.content === "string" ? message.content : "";
+  if (text.length > 0) {
+    output.push({
+      type: RESPONSES_ITEM.MESSAGE,
+      role: ROLE.ASSISTANT,
+      content: [{ type: RESPONSES_ITEM.OUTPUT_TEXT, text, annotations: [] }],
+    });
+  }
+
+  // tool_calls → function_call/custom_tool_call items (Responses-native tool shape).
+  for (const tc of message.tool_calls || []) {
+    const fn = tc.function || {};
+    const custom = customToolNames?.has(fn.name);
+    output.push({
+      type: custom ? RESPONSES_ITEM.CUSTOM_TOOL_CALL : RESPONSES_ITEM.FUNCTION_CALL,
+      id: `${custom ? "ctc" : "fc"}_${tc.id || ""}`,
+      call_id: tc.id || "",
+      name: fn.name || "",
+      ...(custom
+        ? { input: extractCustomToolInput(fn.arguments) }
+        : { arguments: typeof fn.arguments === "string" ? fn.arguments : JSON.stringify(fn.arguments || {}) }),
+    });
+  }
+
+  const usage = responseBody.usage || {};
+  const status = choice.finish_reason === "tool_calls" ? "completed" : (choice.finish_reason === "stop" ? "completed" : (choice.finish_reason || "completed"));
+
+  return {
+    id: `resp_${responseBody.id || ""}`.replace(/^resp_chatcmpl-/, "resp_"),
+    object: "response",
+    created_at: responseBody.created || Math.floor(Date.now() / 1000),
+    model: responseBody.model || "unknown",
+    status,
+    background: false,
+    error: null,
+    output,
+    usage: {
+      input_tokens: usage.prompt_tokens || usage.input_tokens || 0,
+      output_tokens: usage.completion_tokens || usage.output_tokens || 0,
+      total_tokens: usage.total_tokens || (usage.prompt_tokens || 0) + (usage.completion_tokens || 0),
+    },
+  };
+}
+
 /**
  * Translate non-streaming response body from provider format → OpenAI format.
  */
-export function translateNonStreamingResponse(responseBody, targetFormat, sourceFormat) {
+export function translateNonStreamingResponse(responseBody, targetFormat, sourceFormat, customToolNames = null) {
   if (targetFormat === sourceFormat) return responseBody;
+  // Provider responded in OpenAI Chat Completions shape but the client speaks
+  // Responses API — convert so tool_calls/text surface as Responses `output`.
+  if (targetFormat === FORMATS.OPENAI && sourceFormat === FORMATS.OPENAI_RESPONSES) {
+    return openAICompletionToResponses(responseBody, customToolNames);
+  }
   if (targetFormat === FORMATS.OPENAI && sourceFormat === FORMATS.CLAUDE) {
     return openAICompletionToClaudeMessage(responseBody);
   }
@@ -198,7 +281,7 @@ 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, customToolNames, trackDone, appendLog, pxpipe, reqTag, log }) {
   trackDone();
   const contentType = providerResponse.headers.get("content-type") || "";
   let responseBody;
@@ -235,12 +318,16 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
 
   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)
+    ? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat, customToolNames)
     : responseBody;
   const isClaudeMessageResponse = sourceFormat === FORMATS.CLAUDE && translatedResponse?.type === "message";
+  // Responses-format translation produces a `object:"response"` body with no
+  // `choices`; skip the Chat-Completions-specific post-processing below for it.
+  const isResponsesResponse = sourceFormat === FORMATS.OPENAI_RESPONSES && translatedResponse?.object === "response";
 
   // Fix finish_reason for tool_calls: some providers return non-standard values (e.g. "other")
   if (translatedResponse?.choices?.[0]) {
@@ -253,13 +340,13 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
   }
 
   // Ensure OpenAI-required fields
-  if (!isClaudeMessageResponse) {
+  if (!isClaudeMessageResponse && !isResponsesResponse) {
     if (!translatedResponse.object) translatedResponse.object = "chat.completion";
     if (!translatedResponse.created) translatedResponse.created = Math.floor(Date.now() / 1000);
   }
 
   // Strip Azure-specific fields
-  if (!isClaudeMessageResponse) {
+  if (!isClaudeMessageResponse && !isResponsesResponse) {
     delete translatedResponse.prompt_filter_results;
     if (translatedResponse?.choices) {
       for (const choice of translatedResponse.choices) delete choice.content_filter_results;
@@ -273,7 +360,7 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
   // 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) {
+  if (!isClaudeMessageResponse && !isResponsesResponse && translatedResponse?.choices) {
     for (const choice of translatedResponse.choices) {
       if (choice?.message?.reasoning_content && choice.message.content) {
         delete choice.message.reasoning_content;
@@ -296,6 +383,7 @@ 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);

open-sse/handlers/chatCore/requestDetail.js

@@ -44,13 +44,14 @@ export function extractUsageFromResponse(responseBody) {
     };
   }
 
-  // Gemini format
-  if (responseBody.usageMetadata) {
+  // Gemini format. Antigravity / gemini-cli wrap the payload in { response: {...} }.
+  const usageMetadata = responseBody.usageMetadata || responseBody.response?.usageMetadata;
+  if (usageMetadata) {
     return {
-      prompt_tokens: responseBody.usageMetadata.promptTokenCount || 0,
-      completion_tokens: responseBody.usageMetadata.candidatesTokenCount || 0,
-      cached_tokens: responseBody.usageMetadata.cachedContentTokenCount || 0,
-      reasoning_tokens: responseBody.usageMetadata.thoughtsTokenCount || 0
+      prompt_tokens: usageMetadata.promptTokenCount || 0,
+      completion_tokens: usageMetadata.candidatesTokenCount || 0,
+      cached_tokens: usageMetadata.cachedContentTokenCount || 0,
+      reasoning_tokens: usageMetadata.thoughtsTokenCount || 0
     };
   }
 
@@ -69,12 +70,31 @@ 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;
@@ -82,35 +102,17 @@ export function saveUsageStats({ provider, model, tokens, connectionId, apiKey,
 
   if (inTokens === 0 && outTokens === 0) return;
 
-  // Extract cache/reasoning tokens (unified from different formats)
-  const cacheRead = tokens.cache_read_input_tokens || tokens.cached_tokens || tokens.prompt_tokens_details?.cached_tokens || 0;
-  const cacheCreation = tokens.cache_creation_input_tokens || 0;
-  const reasoning = tokens.reasoning_tokens || 0;
+  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}`);
+  }
 
-  const time = new Date().toLocaleTimeString("en-US", { hour12: false, hour: "2-digit", minute: "2-digit", second: "2-digit" });
-  const accountSuffix = connectionId ? ` | account=${connectionId.slice(0, 8)}...` : "";
-  
-  let msg = `${COLORS.green}[${time}] 📊 [${label}] ${provider?.toUpperCase() || "UNKNOWN"} | in=${inTokens} | out=${outTokens}${accountSuffix}`;
-  if (tokens.estimated) msg += ` ${COLORS.yellow}(estimated)${COLORS.reset}`;
-  if (cacheRead) msg += ` | cache_read=${cacheRead}`;
-  if (cacheCreation) msg += ` | cache_create=${cacheCreation}`;
-  if (reasoning) msg += ` | reasoning=${reasoning}`;
-  msg += `${COLORS.reset}`;
-  console.log(msg);
-
-<<<<<<< HEAD
-  // Normalize to OpenAI token shape for storage (include all token types)
-  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) || {
->>>>>>> 7f436e2792be4fa5a4d1c4d6b8e9bc85eaaa6a3d
     prompt_tokens: tokens.prompt_tokens ?? tokens.input_tokens ?? 0,
-    completion_tokens: tokens.completion_tokens ?? tokens.output_tokens ?? 0,
-    cache_read_input_tokens: cacheRead,
-    cache_creation_input_tokens: cacheCreation,
-    reasoning_tokens: reasoning,
+    completion_tokens: tokens.completion_tokens ?? tokens.output_tokens ?? 0
   };
 
   saveRequestUsage({

open-sse/handlers/chatCore/sseToJsonHandler.js

@@ -3,7 +3,8 @@ import { createErrorResult } from "../../utils/error.js";
 import { HTTP_STATUS } from "../../config/runtimeConfig.js";
 import { FORMATS } from "../../translator/formats.js";
 import { PROVIDERS } from "../../config/providers.js";
-import { buildRequestDetail, extractRequestConfig, saveUsageStats } from "./requestDetail.js";
+import { buildRequestDetail, extractRequestConfig, saveUsageStats, formatDoneLine } from "./requestDetail.js";
+import { ROLE, RESPONSES_ITEM } from "../../translator/schema/index.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;
@@ -34,21 +35,97 @@ function pickAssistantMessageForChatCompletion(output) {
   return { msgItem: last, textContent: textFromResponsesMessageItem(last) };
 }
 
+/**
+ * Convert an OpenAI Chat Completions JSON body into the Responses API shape.
+ * Inlined here (not imported from nonStreamingHandler.js) to avoid a circular
+ * import. Mirrors openAICompletionToResponses in nonStreamingHandler.js.
+ */
+function extractCustomToolInput(argumentsValue) {
+  const argumentsText = typeof argumentsValue === "string" ? argumentsValue : JSON.stringify(argumentsValue || {});
+  try {
+    const parsed = JSON.parse(argumentsText);
+    if (parsed && typeof parsed === "object" && typeof parsed.input === "string") return parsed.input;
+  } catch { /* raw freeform input */ }
+  return argumentsText;
+}
+
+function chatCompletionToResponses(responseBody, customToolNames = null) {
+  const choice = responseBody?.choices?.[0];
+  if (!choice) return responseBody;
+
+  const message = choice.message || {};
+  const output = [];
+
+  const reasoning = message.reasoning_content || message.reasoning;
+  if (typeof reasoning === "string" && reasoning.length > 0) {
+    output.push({
+      type: RESPONSES_ITEM.REASONING,
+      summary: [{ type: RESPONSES_ITEM.SUMMARY_TEXT, text: reasoning }],
+    });
+  }
+
+  const text = typeof message.content === "string" ? message.content : "";
+  if (text.length > 0) {
+    output.push({
+      type: RESPONSES_ITEM.MESSAGE,
+      role: ROLE.ASSISTANT,
+      content: [{ type: RESPONSES_ITEM.OUTPUT_TEXT, text, annotations: [] }],
+    });
+  }
+
+  for (const tc of message.tool_calls || []) {
+    const fn = tc.function || {};
+    const custom = customToolNames?.has(fn.name);
+    output.push({
+      type: custom ? RESPONSES_ITEM.CUSTOM_TOOL_CALL : RESPONSES_ITEM.FUNCTION_CALL,
+      id: `${custom ? "ctc" : "fc"}_${tc.id || ""}`,
+      call_id: tc.id || "",
+      name: fn.name || "",
+      ...(custom
+        ? { input: extractCustomToolInput(fn.arguments) }
+        : { arguments: typeof fn.arguments === "string" ? fn.arguments : JSON.stringify(fn.arguments || {}) }),
+    });
+  }
+
+  const usage = responseBody.usage || {};
+  return {
+    id: `resp_${responseBody.id || ""}`.replace(/^resp_chatcmpl-/, "resp_"),
+    object: "response",
+    created_at: responseBody.created || Math.floor(Date.now() / 1000),
+    model: responseBody.model || "unknown",
+    status: "completed",
+    background: false,
+    error: null,
+    output,
+    usage: {
+      input_tokens: usage.prompt_tokens || usage.input_tokens || 0,
+      output_tokens: usage.completion_tokens || usage.output_tokens || 0,
+      total_tokens: usage.total_tokens || (usage.prompt_tokens || 0) + (usage.completion_tokens || 0),
+    },
+  };
+}
+
 /**
  * Parse OpenAI-style SSE text into a single chat completion JSON.
  * Used when provider forces streaming but client wants non-streaming.
  */
 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];
@@ -102,7 +179,7 @@ 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, targetFormat, provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, customToolNames, trackDone, appendLog, reqTag, log }) {
   const contentType = providerResponse.headers.get("content-type") || "";
   const isSSE = contentType.includes("text/event-stream") || (contentType === "" && isResponsesProvider(provider));
   if (!isSSE) return null; // not handled here
@@ -116,7 +193,10 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, pr
   };
 
   // Codex/Responses API SSE path
-  const isCodexResponsesApi = isResponsesProvider(provider) || sourceFormat === FORMATS.OPENAI_RESPONSES;
+  // Branch on the UPSTREAM format (targetFormat = format we spoke to the provider in),
+  // not the client format: a Responses-API client behind a chat-native forced-streaming
+  // provider still receives chat SSE chunks, which must go through the standard path.
+  const isCodexResponsesApi = isResponsesProvider(provider) || targetFormat === FORMATS.OPENAI_RESPONSES;
   if (isCodexResponsesApi) {
     try {
       const jsonResponse = await convertResponsesStreamToJson(providerResponse.body);
@@ -124,15 +204,21 @@ 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 } }));
 
+      // Same cache-inclusive total for the recorded detail, so the DB and the
+      // client-facing usage can never disagree.
+      const inTokensForLog = (usage.input_tokens || 0)
+        + (usage.cache_read_input_tokens || usage.cached_tokens || 0)
+        + (usage.cache_creation_input_tokens || 0);
       const { msgItem, textContent } = pickAssistantMessageForChatCompletion(jsonResponse.output);
       const totalLatency = Date.now() - requestStartTime;
 
       saveRequestDetail(buildRequestDetail({
         ...ctx,
         latency: { ttft: totalLatency, total: totalLatency },
-        tokens: { prompt_tokens: usage.input_tokens || 0, completion_tokens: usage.output_tokens || 0 },
+        tokens: { prompt_tokens: inTokensForLog, completion_tokens: usage.output_tokens || 0 },
         response: { content: textContent, thinking: null, finish_reason: jsonResponse.status || "unknown" },
         status: "success"
       }, { endpoint: clientRawRequest?.endpoint || null })).catch(() => {});
@@ -142,9 +228,21 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, pr
         return { success: true, response: new Response(JSON.stringify(jsonResponse), { headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" } }) };
       }
 
-      // Build client-format response
-      const inTokens = usage.input_tokens || 0;
+      // Build client-format response.
+      // input_tokens EXCLUDES cached tokens on cache-capable upstreams, so summing
+      // only input+output under-reports prompt_tokens — measured: 2012 reported
+      // where the real prompt was ~5344 with 5332 served from cache. Fold the cache
+      // counters in, and keep them visible in prompt_tokens_details so a client can
+      // tell a cache hit from a small prompt.
+      const cacheRead = usage.cache_read_input_tokens || usage.cached_tokens || 0;
+      const cacheCreate = usage.cache_creation_input_tokens || 0;
+      const inTokens = (usage.input_tokens || 0) + cacheRead + cacheCreate;
       const outTokens = usage.output_tokens || 0;
+      const cacheDetails = (cacheRead > 0 || cacheCreate > 0)
+        ? { prompt_tokens_details: {
+              ...(cacheRead > 0 ? { cached_tokens: cacheRead } : {}),
+              ...(cacheCreate > 0 ? { cache_creation_tokens: cacheCreate } : {}) } }
+        : {};
       let finalResp;
 
       // Extract tool calls from Responses API output (function_call items)
@@ -179,7 +277,7 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, pr
           created: jsonResponse.created_at || Math.floor(Date.now() / 1000),
           model: jsonResponse.model || model,
           choices: [{ index: 0, message, finish_reason: finishReason }],
-          usage: { prompt_tokens: inTokens, completion_tokens: outTokens, total_tokens: inTokens + outTokens }
+          usage: { prompt_tokens: inTokens, completion_tokens: outTokens, total_tokens: inTokens + outTokens, ...cacheDetails }
         };
       }
 
@@ -195,12 +293,19 @@ 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();
 
     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({
@@ -215,6 +320,15 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, pr
       status: "success"
     }, { endpoint: clientRawRequest?.endpoint || null })).catch(() => {});
 
+    // Re-attach usage explicitly. This handler already HAS the correct usage — it is
+    // the same object written to the usage DB, and for a cached Claude request that DB
+    // row reads cache_read_input_tokens: 11022 — yet the client was observed receiving
+    // no usage field at all (verified 2026-08-04 with a fingerprinted payload matched
+    // on both sides). Whatever drops it between assembly and serialisation, the client
+    // must not be left unable to account for its own token spend: a caller cannot tell
+    // a 90%-cached request from a cheap one without this.
+    if (usage && Object.keys(usage).length > 0) parsed.usage = usage;
+
     // 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.
@@ -227,7 +341,17 @@ export async function handleForcedSSEToJson({ providerResponse, sourceFormat, pr
       }
     }
 
-    return { success: true, response: new Response(JSON.stringify(parsed), { headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" } }) };
+    // A Responses-format client (e.g. Codex) forced this provider to stream,
+    // but wants JSON back. parseSSEToOpenAIResponse yields a Chat Completions
+    // body; convert it to the Responses `output` shape so tool_calls are not
+    // lost on the non-streaming return path. Inlined (not imported from
+    // nonStreamingHandler.js) to avoid a circular import: nonStreamingHandler
+    // already imports parseSSEToOpenAIResponse from this module.
+    const finalBody = sourceFormat === FORMATS.OPENAI_RESPONSES
+      ? chatCompletionToResponses(parsed, customToolNames)
+      : parsed;
+
+    return { success: true, response: new Response(JSON.stringify(finalBody), { headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" } }) };
   } catch (err) {
     console.error("[ChatCore] Chat Completions SSE→JSON failed:", err);
     return createErrorResult(HTTP_STATUS.BAD_GATEWAY, "Failed to convert streaming response to JSON");

open-sse/handlers/chatCore/streamingHandler.js

@@ -5,7 +5,7 @@ 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 } from "./requestDetail.js";
+import { buildRequestDetail, extractRequestConfig, saveUsageStats, formatDoneLine } from "./requestDetail.js";
 import { saveRequestDetail } from "@/lib/usageDb.js";
 import { SSE_HEADERS_CORS as SSE_HEADERS } from "../../utils/sseConstants.js";
 
@@ -22,7 +22,7 @@ const CODEX_SOURCE_TO_TARGET = {
 /**
  * Determine which SSE transform stream to use based on provider/format.
  */
-function buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey }) {
+function buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, customToolNames, model, connectionId, body, onStreamComplete, apiKey }) {
   const isDroidCLI = userAgent?.toLowerCase().includes("droid") || userAgent?.toLowerCase().includes("codex-cli");
   // Responses-API providers (e.g. codex) emit Responses SSE → translate into client format
   const isResponsesProvider = PROVIDERS[provider]?.format === FORMATS.OPENAI_RESPONSES;
@@ -30,11 +30,11 @@ function buildTransformStream({ provider, sourceFormat, targetFormat, userAgent,
 
   if (needsCodexTranslation) {
     const codexTarget = CODEX_SOURCE_TO_TARGET[sourceFormat] || FORMATS.OPENAI;
-    return createSSETransformStreamWithLogger(FORMATS.OPENAI_RESPONSES, codexTarget, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey);
+    return createSSETransformStreamWithLogger(FORMATS.OPENAI_RESPONSES, codexTarget, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey, customToolNames);
   }
 
   if (needsTranslation(targetFormat, sourceFormat)) {
-    return createSSETransformStreamWithLogger(targetFormat, sourceFormat, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey);
+    return createSSETransformStreamWithLogger(targetFormat, sourceFormat, provider, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey, customToolNames);
   }
 
   return createPassthroughStreamWithLogger(provider, reqLogger, model, connectionId, body, onStreamComplete, apiKey);
@@ -43,7 +43,7 @@ function buildTransformStream({ provider, sourceFormat, targetFormat, userAgent,
 /**
  * Handle streaming response — pipe provider SSE through transform stream to client.
  */
-export async function handleStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, userAgent, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, streamController, onStreamComplete, streamDetailId }) {
+export async function handleStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, userAgent, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, customToolNames, streamController, onStreamComplete, streamDetailId, pxpipe, reqTag, log }) {
   if (onRequestSuccess) {
     Promise.resolve()
       .then(onRequestSuccess)
@@ -67,7 +67,8 @@ export async function handleStreamingResponse({ providerResponse, provider, mode
     const shortMsg = sanitizedTitle
       || (bodyText.length < 200 ? bodyText.replace(/<[^>]*>/g, '').trim().slice(0, 160) : `Upstream returned non-SSE response (${upstreamContentType})`);
     const status = providerResponse.status || 502;
-    console.warn(`[STREAM] ${provider} | ${model} | blocked pipe: ${shortMsg} [${status}]`);
+    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,
@@ -78,7 +79,7 @@ export async function handleStreamingResponse({ providerResponse, provider, mode
     };
   }
 
-  const transformStream = buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, model, connectionId, body, onStreamComplete, apiKey });
+  const transformStream = buildTransformStream({ provider, sourceFormat, targetFormat, userAgent, reqLogger, toolNameMap, customToolNames, 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;
@@ -94,6 +95,7 @@ export async function handleStreamingResponse({ providerResponse, provider, mode
     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);
@@ -108,7 +110,7 @@ export async function handleStreamingResponse({ providerResponse, provider, mode
 /**
  * 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) => {
@@ -127,10 +129,15 @@ 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);
     });
+
+    // 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 };