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

50
open-sse/handlers/chatCore.js
View File

@@ -14,7 +14,7 @@ import { handleBypassRequest } from "../utils/bypassHandler.js";
import { trackPendingRequest, saveRequestDetail } from "@/lib/usageDb.js";
import { getExecutor } from "../executors/index.js";
import { supportsGrokCliReasoningEffort } from "../config/grokCli.js";
import { buildRequestDetail, extractRequestConfig } from "./chatCore/requestDetail.js";
import { buildRequestDetail, extractRequestConfig, shouldPersistRequestDetail } from "./chatCore/requestDetail.js";
import { handleForcedSSEToJson } from "./chatCore/sseToJsonHandler.js";
import { handleNonStreamingResponse } from "./chatCore/nonStreamingHandler.js";
import { handleStreamingResponse, buildOnStreamComplete } from "./chatCore/streamingHandler.js";
@@ -59,7 +59,7 @@ export function stripContinuityFields(body) {
return body;
}
export async function handleChatCore({ body, modelInfo, credentials, log, onCredentialsRefreshed, onRequestSuccess, onDisconnect, clientRawRequest, connectionId, userAgent, apiKey, ccFilterNaming, rtkEnabled, headroomEnabled, headroomUrl, headroomCompressUserMessages, headroomTimeoutMs, cavemanEnabled, cavemanLevel, ponytailEnabled, ponytailLevel, pxpipeEnabled, pxpipeMinChars, pxpipeTimeoutMs, pxpipeTransform, onPxpipeEvent, sourceFormatOverride, providerThinking, capsOverride = null, streamErrorPatterns = null }) {
export async function handleChatCore({ body, modelInfo, credentials, log, onCredentialsRefreshed, onRequestSuccess, onDisconnect, clientRawRequest, connectionId, userAgent, apiKey, ccFilterNaming, rtkEnabled, headroomEnabled, headroomUrl, headroomCompressUserMessages, headroomTimeoutMs, cavemanEnabled, cavemanLevel, ponytailEnabled, ponytailLevel, pxpipeEnabled, pxpipeMinChars, pxpipeTimeoutMs, pxpipeTransform, onPxpipeEvent, sourceFormatOverride, providerThinking, capsOverride = null, streamErrorPatterns = null, persistUsage = "all" }) {
const { provider, model } = modelInfo;
const requestStartTime = Date.now();
// Stable per-session color so all lines of one CLI conversation share a tag
@@ -377,16 +377,18 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
reqLogger.logTargetRequest(providerUrl, providerHeaders, finalBody);
} catch (error) {
trackPendingRequest(model, provider, connectionId, false, true);
saveRequestDetail(buildRequestDetail({
provider, model, connectionId,
latency: { ttft: 0, total: Date.now() - requestStartTime },
tokens: { prompt_tokens: 0, completion_tokens: 0 },
request: extractRequestConfig(body, stream),
providerRequest: translatedBody || null,
response: { error: error.message || String(error), status: error.name === "AbortError" ? 499 : 502, thinking: null },
pxpipe: pxpipeSummary,
status: "error"
})).catch(() => { });
if (shouldPersistRequestDetail(persistUsage, "error")) {
saveRequestDetail(buildRequestDetail({
provider, model, connectionId,
latency: { ttft: 0, total: Date.now() - requestStartTime },
tokens: { prompt_tokens: 0, completion_tokens: 0 },
request: extractRequestConfig(body, stream),
providerRequest: translatedBody || null,
response: { error: error.message || String(error), status: error.name === "AbortError" ? 499 : 502, thinking: null },
pxpipe: pxpipeSummary,
status: "error"
})).catch(() => { });
}
if (error.name === "AbortError") {
streamController.handleError(error);
@@ -451,16 +453,18 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
if (!providerResponse.ok) {
trackPendingRequest(model, provider, connectionId, false, true);
const { statusCode, message, resetsAtMs } = await parseUpstreamError(providerResponse, executor);
saveRequestDetail(buildRequestDetail({
provider, model, connectionId,
latency: { ttft: 0, total: Date.now() - requestStartTime },
tokens: { prompt_tokens: 0, completion_tokens: 0 },
request: extractRequestConfig(body, stream),
providerRequest: finalBody || translatedBody || null,
response: { error: message, status: statusCode, thinking: null },
pxpipe: pxpipeSummary,
status: "error"
})).catch(() => { });
if (shouldPersistRequestDetail(persistUsage, "error")) {
saveRequestDetail(buildRequestDetail({
provider, model, connectionId,
latency: { ttft: 0, total: Date.now() - requestStartTime },
tokens: { prompt_tokens: 0, completion_tokens: 0 },
request: extractRequestConfig(body, stream),
providerRequest: finalBody || translatedBody || null,
response: { error: message, status: statusCode, thinking: null },
pxpipe: pxpipeSummary,
status: "error"
})).catch(() => { });
}
const errMsg = formatProviderError(new Error(message), provider, model, statusCode);
if (log?.errorLine) {
@@ -472,7 +476,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
}
const appendLog = () => {}; // request log derived from usageHistory; kept as no-op seam for handlers
const sharedCtx = { provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, pxpipe: pxpipeSummary, reqTag, log, streamErrorPatterns };
const sharedCtx = { provider, model, body, stream, translatedBody, finalBody, requestStartTime, connectionId, apiKey, clientRawRequest, onRequestSuccess, pxpipe: pxpipeSummary, reqTag, log, streamErrorPatterns, persistUsage };
// Early-peek streaming responses for configured in-stream error patterns.
// Some upstreams fail INSIDE a 200 SSE stream; without this the failure is