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

feat: pre-request token validation, mid-stream error handling, and usage stats improvements

Browse Source 
- Qoder: handle mid-stream errors by returning proper error Response instead of embedding in stream
- Qoder: add refreshCredentials() to validate token via quota endpoint before requests
- chatCore: validate and refresh provider tokens before sending chat requests
- chatCore: bail early with 401 on unrecoverable token refresh errors
- Usage stats: track apiKey, comboName, fallbackHistory in request details
- Dashboard: improve Combos, Endpoint, Provider, Usage, and RequestDetails pages
- API keys route: upsert logic with provider_type support
- DB repos: usageRepo query improvements, requestDetailsRepo pagination, apiKeysRepo updates
This commit is contained in:
luulam
2026-06-29 10:08:07 +07:00
parent 1fe8115dad
commit 2305e26e25
27 changed files with 1433 additions and 459 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
open-sse/handlers/chatCore/nonStreamingHandler.js
View File

@@ -143,7 +143,7 @@ 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, midStreamError, onMidStreamError }) {
export async function handleNonStreamingResponse({ providerResponse, provider, model, sourceFormat, targetFormat, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, comboName, fallbackHistory, clientRawRequest, onRequestSuccess, reqLogger, toolNameMap, trackDone, appendLog, midStreamError, onMidStreamError }) {
trackDone();
const contentType = providerResponse.headers.get("content-type") || "";
let responseBody;
@@ -189,7 +189,7 @@ 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, comboName });
const translatedResponse = needsTranslation(targetFormat, sourceFormat)
? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat)
@@ -234,7 +234,7 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
const totalLatency = Date.now() - requestStartTime;
saveRequestDetail(buildRequestDetail({
provider, model, connectionId,
provider, model, connectionId, apiKey, comboName, fallbackHistory,
latency: { ttft: totalLatency, total: totalLatency },
tokens: usage || { prompt_tokens: 0, completion_tokens: 0 },
request: extractRequestConfig(body, stream),