refactor(log): unify request lifecycle logging with session-colored tags

Collapse scattered per-request console lines (request/routing/auth/pending/ usage/stream-usage/stream) into 3 correlated lines: request, transform, done. Add stable per-session color tag so concurrent request lines are easy to follow, surface thinking intent, always-on full error logging for debug, re-enable warn level, and uppercase keyword labels. Also fix usage overview cards wrapping (5 cards -> grid-cols-5). Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-10 18:01:20 +07:00
parent b61c50cbb7
commit a625ea9fd8
11 changed files with 176 additions and 69 deletions
--- a/open-sse/handlers/chatCore.js
+++ b/open-sse/handlers/chatCore.js
@@ -3,7 +3,6 @@ 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 { COLORS } from "../utils/stream.js";
 import { createStreamController } from "../utils/streamHandler.js";
 import { refreshWithRetry } from "../services/tokenRefresh.js";
 import { createRequestLogger } from "../utils/requestLogger.js";
@@ -22,12 +21,14 @@ import { detectClientTool, isNativePassthrough } from "../utils/clientDetector.j
 import { dedupeTools } from "../utils/toolDeduper.js";
 import { injectCaveman } from "../rtk/caveman.js";
 import { injectPonytail } from "../rtk/ponytail.js";
-import { compressMessages, formatRtkLog } from "../rtk/index.js";
-import { compressWithHeadroom, formatHeadroomLog, formatHeadroomSizeLog, isHeadroomPhantomSavings } from "../rtk/headroom.js";
-import { compressWithPxpipe, formatPxpipeLog } from "../rtk/pxpipe.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
@@ -39,6 +40,15 @@ import { prefetchRemoteImages } from "../translator/concerns/prefetch.js";
 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);

@@ -152,39 +162,68 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
  // 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);
-  const rtkLine = formatRtkLog(rtkStats);
-  if (rtkLine) console.log(rtkLine);
+  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 });
-  const headroomLine = formatHeadroomLog(headroomStats);
-  const headroomSizeLine = formatHeadroomSizeLog(headroomDiagnostics);
-  if (headroomLine) {
-    log?.info?.("HEADROOM", `${headroomLine}${headroomSizeLine ? ` | ${headroomSizeLine}` : ""}`);
+  if (headroomStats) {
+    const before = headroomStats.tokens_before || 0;
+    const delta = headroomStats.tokens_saved || 0;
+    const pct = before > 0 ? ((delta / before) * 100).toFixed(1) : "0";
+    xf.push(`HEADROOM −${delta}tok(${pct}%)`);
    if (isHeadroomPhantomSavings(headroomStats, headroomDiagnostics)) {
-      log?.warn?.("HEADROOM", `reported token delta, but outbound JSON shrank <5%; provider may bill near-original payload | ${headroomSizeLine}`);
+      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})` : ""}`);
+  } 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);
-    log?.debug?.("CAVEMAN", `${cavemanLevel} | ${finalFormat}`);
+    xf.push(`CAVEMAN:${cavemanLevel}`);
  }

  // Ponytail: inject lazy-senior-dev system prompt
  if (ponytailEnabled && ponytailLevel) {
    injectPonytail(translatedBody, finalFormat, ponytailLevel);
-    log?.debug?.("PONYTAIL", `${ponytailLevel} | ${finalFormat}`);
+    xf.push(`PONYTAIL:${ponytailLevel}`);
  }

  // PXPIPE: image bulky context (Claude-format bodies only), last saver before dispatch
@@ -196,12 +235,12 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
    });
    pxpipeSummary = pxpipeResult.summary;
    if (pxpipeResult.body) translatedBody = pxpipeResult.body;
-    const pxpipeLine = formatPxpipeLog(pxpipeSummary);
-    if (pxpipeLine) log?.info?.("PXPIPE", pxpipeLine);
-    else log?.debug?.("PXPIPE", `skipped: ${pxpipeSummary.reason}${pxpipeSummary.detail ? ` (${pxpipeSummary.detail})` : ""}`);
+    if (pxpipeSummary?.applied) xf.push(`PXPIPE:${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);
  appendRequestLog({ model, provider, connectionId, status: "PENDING" }).catch(() => { });
@@ -215,7 +254,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
      if (onDisconnect) onDisconnect(reason);
    },
    onError: () => trackPendingRequest(model, provider, connectionId, false),
-    log, provider, model
+    log, provider, model, reqTag
  });

  const proxyOptions = {
@@ -279,7 +318,9 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
      return createErrorResult(499, "Request aborted");
    }
    const errMsg = formatProviderError(error, provider, model, HTTP_STATUS.BAD_GATEWAY);
-    console.log(`${COLORS.red}[ERROR] ${errMsg}${COLORS.reset}`);
+    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);
  }

@@ -288,7 +329,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
    try {
      const newCredentials = await refreshWithRetry(() => executor.refreshCredentials(credentials, log), 3, log);
      if (newCredentials?.accessToken || newCredentials?.copilotToken) {
-        log?.info?.("TOKEN", `${provider.toUpperCase()} | refreshed`);
+        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}`); }
@@ -322,12 +363,15 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
    })).catch(() => { });

    const errMsg = formatProviderError(new Error(message), provider, model, statusCode);
-    console.log(`${COLORS.red}[ERROR] ${errMsg}${COLORS.reset}`);
+    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 };
+  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);

--- a/open-sse/handlers/chatCore/nonStreamingHandler.js
+++ b/open-sse/handlers/chatCore/nonStreamingHandler.js
@@ -6,7 +6,7 @@ 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";

@@ -198,7 +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, pxpipe }) {
+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;
@@ -235,7 +235,8 @@ 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)
--- a/open-sse/handlers/chatCore/requestDetail.js
+++ b/open-sse/handlers/chatCore/requestDetail.js
@@ -75,7 +75,25 @@ export function buildRequestDetail(base, 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;
@@ -83,9 +101,11 @@ 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}`);
+  }

  // Canonicalize to one storage convention (prompt_tokens cache-inclusive) so
  // cached/cache-creation tokens survive to cost calc + stats. See canonicalizeUsage.
--- a/open-sse/handlers/chatCore/sseToJsonHandler.js
+++ b/open-sse/handlers/chatCore/sseToJsonHandler.js
@@ -3,7 +3,7 @@ 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";

 // 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;
@@ -102,7 +102,7 @@ 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, 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 === "" && isResponsesProvider(provider));
  if (!isSSE) return null; // not handled here
@@ -124,7 +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;
@@ -200,7 +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({
--- a/open-sse/handlers/chatCore/streamingHandler.js
+++ b/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, saveUsageStats } 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";

@@ -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, pxpipe }) {
+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)
@@ -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: ${status}`));
    return {
      success: false,
@@ -109,7 +110,7 @@ export async function handleStreamingResponse({ providerResponse, provider, mode
 /**
 * Build onStreamComplete callback for streaming usage tracking.
 */
-export function buildOnStreamComplete({ provider, model, connectionId, apiKey, requestStartTime, body, stream, finalBody, translatedBody, clientRawRequest, pxpipe }) {
+export function buildOnStreamComplete({ provider, model, connectionId, apiKey, requestStartTime, body, stream, finalBody, translatedBody, clientRawRequest, pxpipe, reqTag, log }) {
  const streamDetailId = `${Date.now()}-${Math.random().toString(36).slice(2, 11)}`;

  const onStreamComplete = (contentObj, usage, ttftAt) => {
@@ -134,7 +135,9 @@ export function buildOnStreamComplete({ provider, model, connectionId, apiKey, r
      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 };
--- a/open-sse/utils/streamHandler.js
+++ b/open-sse/utils/streamHandler.js
@@ -15,16 +15,19 @@ function getTimeString() {
 * @param {string} options.provider - Provider name
 * @param {string} options.model - Model name
 */
-export function createStreamController({ onDisconnect, onError, log, provider, model } = {}) {
+export function createStreamController({ onDisconnect, onError, log, provider, model, reqTag = "" } = {}) {
  const abortController = new AbortController();
  const startTime = Date.now();
  let disconnected = false;
  let abortTimeout = null;

-  const logStream = (status) => {
+  // Only abnormal terminations are logged; normal completion is covered by "📊 done".
+  // isError uses errorLine (always shown, ignores LOG_LEVEL) so failures survive quiet levels.
+  const logStream = (symbol, status, isError = false) => {
    const duration = Date.now() - startTime;
-    const p = provider?.toUpperCase() || "UNKNOWN";
-    console.log(`[${getTimeString()}] 🌊 [STREAM] ${p} | ${model || "unknown"} | ${duration}ms | ${status}`);
+    const emit = isError ? log?.errorLine : log?.line;
+    if (emit) emit(reqTag, symbol, `${status} · ${provider}/${model} · ${duration}ms`);
+    else console.log(`[${getTimeString()}] ${symbol} ${provider}/${model} · ${status} · ${duration}ms`);
  };

  return {
@@ -38,7 +41,7 @@ export function createStreamController({ onDisconnect, onError, log, provider, m
      if (disconnected) return;
      disconnected = true;

-      logStream(`disconnect: ${reason}`);
+      logStream("⚡", `DISCONNECT: ${reason}`);
      dbg("CTRL", `${provider}/${model} | disconnect=${reason} | dur=${Date.now() - startTime}ms`);

      // Delay abort to allow cleanup
@@ -49,13 +52,11 @@ export function createStreamController({ onDisconnect, onError, log, provider, m
      onDisconnect?.({ reason, duration: Date.now() - startTime });
    },

-    // Call when stream completes normally
+    // Call when stream completes normally (no line here — "📊 done" is authoritative)
    handleComplete: () => {
      if (disconnected) return;
      disconnected = true;

-      logStream("complete");
-
      if (abortTimeout) {
        clearTimeout(abortTimeout);
        abortTimeout = null;
@@ -73,11 +74,11 @@ export function createStreamController({ onDisconnect, onError, log, provider, m
      }

      if (error.name === "AbortError") {
-        logStream("aborted");
+        logStream("⚡", "ABORTED");
        return;
      }

-      logStream(`error: ${error.message}`);
+      logStream("✗", `ERROR: ${error.message}${error.stack ? `\n    ${error.stack}` : ""}`, true);
      onError?.(error);
    },

--- a/open-sse/utils/usageTracking.js
+++ b/open-sse/utils/usageTracking.js
@@ -4,6 +4,9 @@

 import { FORMATS } from "../translator/formats.js";

+// Legacy per-chunk usage console line; off by default (superseded by "📊 done")
+const DEBUG_USAGE = process.env.LOG_USAGE_VERBOSE === "1";
+
 // ANSI color codes
 export const COLORS = {
  reset: "\x1b[0m",
@@ -401,6 +404,10 @@ export function estimateUsage(body, contentLength, targetFormat = FORMATS.OPENAI
 export function logUsage(provider, usage, model = null, connectionId = null, apiKey = null) {
  if (!usage || typeof usage !== "object") return;

+  // Console output moved to the unified "📊 done" line (streamingHandler). Kept as
+  // a no-op hook so callers stay unchanged; usage persistence happens via saveUsageStats.
+  if (!DEBUG_USAGE) return;
+
  const p = provider?.toUpperCase() || "UNKNOWN";

  // Support both formats:
--- a/src/app/(dashboard)/dashboard/usage/components/OverviewCards.js
+++ b/src/app/(dashboard)/dashboard/usage/components/OverviewCards.js
@@ -8,7 +8,7 @@ const fmtCost = (n) => `$${(n || 0).toFixed(2)}`;

 export default function OverviewCards({ stats }) {
  return (
-    <div className="grid min-w-0 grid-cols-1 gap-3 sm:grid-cols-2 md:grid-cols-2 lg:grid-cols-4 sm:gap-4">
+    <div className="grid min-w-0 grid-cols-1 gap-3 sm:grid-cols-2 md:grid-cols-3 lg:grid-cols-5 sm:gap-4">
      <Card className="flex min-w-0 flex-col gap-1 px-4 py-3">
        <span className="text-text-muted text-sm uppercase font-semibold">Total Requests</span>
        <span className="truncate text-2xl font-bold">{fmt(stats.totalRequests)}</span>
--- a/src/lib/db/repos/usageRepo.js
+++ b/src/lib/db/repos/usageRepo.js
@@ -189,8 +189,7 @@ export function trackPendingRequest(model, provider, connectionId, started, erro
    lastErrorProvider.ts = Date.now();
  }

-  const t = new Date().toLocaleTimeString("en-US", { hour12: false, hour: "2-digit", minute: "2-digit", second: "2-digit" });
-  console.log(`[${t}] [PENDING] ${started ? "START" : "END"}${error ? " (ERROR)" : ""} | provider=${provider} | model=${model}`);
+  // [PENDING] console line removed; lifecycle is visible via "▶" and "📊 done" lines
  scheduleStatsEvent("pending");
 }

--- a/src/sse/handlers/chat.js
+++ b/src/sse/handlers/chat.js
@@ -48,15 +48,9 @@ export async function handleChat(request, clientRawRequest = null) {
  }
  cacheClaudeHeaders(clientRawRequest.headers);

-  // Log request endpoint and model
-  const url = new URL(request.url);
  const modelStr = body.model;

-  // Count messages (support both messages[] and input[] formats)
-  const msgCount = body.messages?.length || body.input?.length || 0;
-  const toolCount = body.tools?.length || 0;
-  const effort = body.reasoning_effort || body.reasoning?.effort || null;
-  log.request("POST", `${url.pathname} | ${modelStr} | ${msgCount} msgs${toolCount ? ` | ${toolCount} tools` : ""}${effort ? ` | effort=${effort}` : ""}`);
+  // Request summary is emitted as the unified "▶" line in chatCore (has fmt/thinking/account)

  // Log API key (masked)
  const authHeader = request.headers.get("Authorization");
@@ -191,12 +185,7 @@ async function handleSingleModelChat(body, modelStr, clientRawRequest = null, re

  const { provider, model } = modelInfo;

-  // Log model routing (alias → actual model)
-  if (modelStr !== `${provider}/${model}`) {
-    log.info("ROUTING", `${modelStr} → ${provider}/${model}`);
-  } else {
-    log.info("ROUTING", `Provider: ${provider}, Model: ${model}`);
-  }
+  // Routing shown in the unified "▶" line (client model → provider/model)

  // Extract userAgent from request
  const userAgent = request?.headers?.get("user-agent") || "";
@@ -225,9 +214,7 @@ async function handleSingleModelChat(body, modelStr, clientRawRequest = null, re
      return errorResponse(lastStatus || HTTP_STATUS.SERVICE_UNAVAILABLE, lastError || "All accounts unavailable");
    }

-    // Log account selection
-    log.info("AUTH", `\x1b[32mUsing ${provider} account: ${credentials.connectionName}\x1b[0m`);
-
+    // Account selection shown in the unified "▶" line (acc:...)
    const refreshedCredentials = await checkAndRefreshToken(provider, credentials);

    // Ensure real project ID is available for providers that need it (P0 fix: cold miss)
@@ -288,7 +275,7 @@ async function handleSingleModelChat(body, modelStr, clientRawRequest = null, re
    const { shouldFallback } = await markAccountUnavailable(credentials.connectionId, result.status, result.error, provider, model, result.resetsAtMs);

    if (shouldFallback) {
-      log.warn("AUTH", `Account ${credentials.connectionName} unavailable (${result.status}), trying fallback`);
+      log.warn("FALLBACK", `⇄ ACC:${credentials.connectionName} UNAVAILABLE (${result.status}) → NEXT ACCOUNT`);
      excludeConnectionIds.add(credentials.connectionId);
      lastError = result.error;
      lastStatus = result.status;
--- a/src/sse/utils/logger.js
+++ b/src/sse/utils/logger.js
@@ -13,6 +13,49 @@ function formatTime() {
  return new Date().toLocaleTimeString("en-US", { hour12: false });
 }

+// Colored-dot tags to correlate request lines by session (same session → same color)
+const REQ_TAGS = ["🟢", "🔵", "🟣", "🟡", "🟠", "🔴", "⚪", "🟤"];
+let tagCursor = 0;
+
+// Allocate next rotating tag (fallback when no session seed available)
+export function nextTag() {
+  const tag = REQ_TAGS[tagCursor % REQ_TAGS.length];
+  tagCursor++;
+  return tag;
+}
+
+// Stable tag derived from a session/connection seed: same seed always maps to the same color
+export function tagForSession(seed) {
+  if (!seed) return nextTag();
+  let h = 0;
+  for (let i = 0; i < seed.length; i++) h = (h * 31 + seed.charCodeAt(i)) | 0;
+  return REQ_TAGS[Math.abs(h) % REQ_TAGS.length];
+}
+
+// Print one correlated line: [time] tag symbol message
+export function line(tag, symbol, message) {
+  if (LEVEL > LOG_LEVELS.INFO) return;
+  console.log(`[${formatTime()}] ${tag} ${symbol} ${message}`);
+}
+
+// Like line() but always printed regardless of LOG_LEVEL (errors must never be hidden)
+export function errorLine(tag, symbol, message) {
+  console.log(`[${formatTime()}] ${tag} ${symbol} ${message}`);
+}
+
+// Format thinking intent for the request line ("high(10k)" / "off" / "auto")
+export function fmtThink(intent) {
+  if (!intent || !intent.mode) return null;
+  if (intent.mode === "none") return "off";
+  if (intent.mode === "auto") return "auto";
+  if (intent.mode === "budget") {
+    const k = intent.budget >= 1000 ? `${Math.round(intent.budget / 1000)}k` : `${intent.budget}`;
+    return k;
+  }
+  if (intent.mode === "level") return intent.level;
+  return null;
+}
+
 function formatData(data) {
  if (!data) return "";
  if (typeof data === "string") return data;
@@ -40,7 +83,7 @@ export function info(tag, message, data) {
 export function warn(tag, message, data) {
  if (LEVEL <= LOG_LEVELS.WARN) {
    const dataStr = data ? ` ${formatData(data)}` : "";
-    // console.warn(`[${formatTime()}] ⚠️  [${tag}] ${message}${dataStr}`);
+    console.warn(`[${formatTime()}] ⚠️  [${tag}] ${message}${dataStr}`);
  }
 }