fix: harden combo fallback and health checks (#704)

This commit is contained in:
Randi
2026-03-28 19:39:16 -04:00
committed by GitHub
parent f6b0811f78
commit dd9de2efa9
7 changed files with 250 additions and 18 deletions

View File

@@ -1122,18 +1122,27 @@ function TestResultsView({ results }) {
{results.results?.map((r, i) => (
<div
key={i}
title={r.error || undefined}
className="flex items-center gap-2 text-xs px-2 py-1.5 rounded bg-black/[0.02] dark:bg-white/[0.02]"
>
<span
className={`material-symbols-outlined text-[14px] ${
r.status === "ok"
? "text-emerald-500"
: r.status === "skipped"
? "text-text-muted"
: "text-red-500"
: r.status === "reachable"
? "text-amber-500"
: r.status === "skipped"
? "text-text-muted"
: "text-red-500"
}`}
>
{r.status === "ok" ? "check_circle" : r.status === "skipped" ? "skip_next" : "error"}
{r.status === "ok"
? "check_circle"
: r.status === "reachable"
? "network_check"
: r.status === "skipped"
? "skip_next"
: "error"}
</span>
<code className="font-mono flex-1">{r.model}</code>
{r.latencyMs !== undefined && <span className="text-text-muted">{r.latencyMs}ms</span>}
@@ -1141,9 +1150,11 @@ function TestResultsView({ results }) {
className={`text-[10px] uppercase font-medium ${
r.status === "ok"
? "text-emerald-500"
: r.status === "skipped"
? "text-text-muted"
: "text-red-500"
: r.status === "reachable"
? "text-amber-500"
: r.status === "skipped"
? "text-text-muted"
: "text-red-500"
}`}
>
{r.status}

View File

@@ -1,4 +1,9 @@
import { NextResponse } from "next/server";
import {
buildComboTestRequestBody,
probeComboModelReachability,
shouldProbeComboTestReachability,
} from "@/lib/combos/testHealth";
import { getComboByName } from "@/lib/localDb";
import { testComboSchema } from "@/shared/validation/schemas";
import { isValidationFailure, validateBody } from "@/shared/validation/helpers";
@@ -49,13 +54,9 @@ export async function POST(request) {
const startTime = Date.now();
try {
// Send a minimal chat request to the internal SSE handler
// Use OpenAI-compatible format — universally accepted by all providers via the translator
const testBody = {
model: modelStr,
messages: [{ role: "user", content: "Hi" }],
max_tokens: 5,
stream: false,
};
// Use a tiny but realistic request body so gateway-routed models do not
// get flagged as dead just because the probe payload is too synthetic.
const testBody = buildComboTestRequestBody(modelStr);
const internalUrl = `${getBaseUrl(request)}/v1/chat/completions`;
const controller = new AbortController();
@@ -88,6 +89,29 @@ export async function POST(request) {
} catch {
errorMsg = res.statusText;
}
let reachability = null;
if (shouldProbeComboTestReachability(res.status)) {
try {
reachability = await probeComboModelReachability(modelStr);
} catch {
reachability = null;
}
}
if (reachability?.reachable) {
results.push({
model: modelStr,
status: "reachable",
statusCode: res.status,
error: errorMsg,
latencyMs,
provider: reachability.provider,
probeMethod: reachability.method,
});
continue;
}
results.push({
model: modelStr,
status: "error",

View File

@@ -0,0 +1,74 @@
import { validateProviderApiKey } from "@/lib/providers/validation";
import { getProviderCredentials } from "@/sse/services/auth";
import { getModelInfo } from "@/sse/services/model";
const SOFT_REACHABILITY_STATUSES = new Set([400, 405, 406, 409, 422]);
export function buildComboTestRequestBody(modelStr: string) {
return {
model: modelStr,
messages: [{ role: "user", content: "Reply with OK only." }],
// Some gateway-routed models reject ultra-tiny budgets during smoke tests.
max_tokens: 16,
stream: false,
};
}
export function shouldProbeComboTestReachability(statusCode: number) {
return SOFT_REACHABILITY_STATUSES.has(Number(statusCode));
}
type ProbeDeps = {
getModelInfo?: typeof getModelInfo;
getProviderCredentials?: typeof getProviderCredentials;
validateProviderApiKey?: typeof validateProviderApiKey;
};
export async function probeComboModelReachability(modelStr: string, deps: ProbeDeps = {}) {
const resolveModel = deps.getModelInfo || getModelInfo;
const loadCredentials = deps.getProviderCredentials || getProviderCredentials;
const validateKey = deps.validateProviderApiKey || validateProviderApiKey;
const modelInfo = await resolveModel(modelStr);
if (!modelInfo?.provider) {
return { reachable: false, reason: "unresolved_model" };
}
const credentials = await loadCredentials(
modelInfo.provider,
null,
null,
modelInfo.model || modelStr
);
if (!credentials || credentials.allRateLimited) {
return { reachable: false, reason: "credentials_unavailable" };
}
const apiKey = credentials.apiKey || credentials.accessToken;
if (typeof apiKey !== "string" || apiKey.trim().length === 0) {
return { reachable: false, reason: "missing_auth_material" };
}
const providerSpecificData =
credentials.providerSpecificData && typeof credentials.providerSpecificData === "object"
? { ...credentials.providerSpecificData }
: {};
if (!providerSpecificData.validationModelId && modelInfo.model) {
providerSpecificData.validationModelId = modelInfo.model;
}
const validation = await validateKey({
provider: modelInfo.provider,
apiKey,
providerSpecificData,
});
return {
reachable: Boolean(validation?.valid),
provider: modelInfo.provider,
model: modelInfo.model || null,
method: validation?.method || null,
warning: validation?.warning || null,
};
}