luulam/9router
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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>
This commit is contained in:
decolua
2026-07-10 18:01:20 +07:00
parent b61c50cbb7
commit a625ea9fd8
11 changed files with 176 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
open-sse/handlers/chatCore/nonStreamingHandler.js
View File

@@ -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)

28
open-sse/handlers/chatCore/requestDetail.js
View File

@@ -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.

10
open-sse/handlers/chatCore/sseToJsonHandler.js
View File

@@ -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({

13
open-sse/handlers/chatCore/streamingHandler.js
View File

@@ -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 };