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

fix(combo): keep nested combos as single units and stop 0-token detail rows

Browse Source 
Nested combos (comboA lists comboB, comboC, …) now stay one slot each:
the inner combo always runs as fallback to produce a single answer.
Failed hops are no longer written to Details/usage, and streaming no
longer inserts a 0-token placeholder row.

- chat.js: comboStack cycle detection; nested combos forced to fallback;
  persistUsage="success-only" for combo hops
- combo.js: discardResponse() cancels unused bodies (fusion timeout /
  fallback) so dropped streams fire onStreamComplete; getComboModelsFromData
  keeps nested names and honors enabled=false
- requestDetail.js: tokensForDetail() canonicalizes Claude/Gemini usage;
  shouldPersistRequestDetail() skips streaming-start and non-success hops
- streamingHandler.js: drop the 0-token streaming placeholder write
- RequestDetailsTab.js: read Gemini/Claude token names; show "streaming"
  status in amber
- tests: add combo-nested.test.js (13 cases)
- gitignore: ignore local .vitest/ artifacts

Co-authored-by: CommandCodeBot <noreply@commandcode.ai>
This commit is contained in:
luulam
2026-09-17 14:03:59 +07:00
parent a84ba559f3
commit 81a47f36c6
11 changed files with 332 additions and 144 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
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, formatDoneLine } from "./requestDetail.js";
import { buildRequestDetail, extractRequestConfig, extractUsageFromResponse, saveUsageStats, formatDoneLine, tokensForDetail, shouldPersistRequestDetail } from "./requestDetail.js";
import { saveRequestDetail } from "@/lib/usageDb.js";
import { matchStreamErrorPatterns } from "../../utils/streamErrorPatterns.js";
import { decloakToolNames } from "../../utils/claudeCloaking.js";
@@ -282,7 +282,7 @@ 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, customToolNames, trackDone, appendLog, pxpipe, reqTag, log, streamErrorPatterns }) {
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, streamErrorPatterns, persistUsage = "all" }) {
trackDone();
const contentType = providerResponse.headers.get("content-type") || "";
let responseBody;
@@ -387,23 +387,25 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
reqLogger.logConvertedResponse(translatedResponse);
const totalLatency = Date.now() - requestStartTime;
saveRequestDetail(buildRequestDetail({
provider, model, connectionId, apiKey,
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: translatedResponse?.choices?.[0]?.message?.content || translatedResponse?.content || null,
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);
});
if (shouldPersistRequestDetail(persistUsage, "success")) {
saveRequestDetail(buildRequestDetail({
provider, model, connectionId, apiKey,
latency: { ttft: totalLatency, total: totalLatency },
tokens: tokensForDetail(usage),
request: extractRequestConfig(body, stream),
providerRequest: finalBody || translatedBody || null,
providerResponse: responseBody || null,
response: {
content: translatedResponse?.choices?.[0]?.message?.content || translatedResponse?.content || null,
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);
});
}
return {
success: true,