A local endpoint that publishes no limits — LM Studio's /models says nothing — left every model on the 8192/4096 defaults with no way to say "this one has a 131k window". Each discovered model now gets three optional pins in the endpoint editor: context window, max output tokens, thinking (auto/on/off). A pin always wins: user pin → what the endpoint published → compiled default. Blank means no opinion, so discovery keeps ruling wherever you don't pin. Pins live in customProvider.overrides keyed by model id, stored apart from the discovery snapshot: a reconnect refreshes the models and prunes the pins of models that vanished while keeping the rest. Pins are written by PATCH /api/custom-provider, which never probes — the whole point is configuring a server that isn't answering /models correctly. Connect still probes and still fails loudly when the endpoint is down. A pin under 2048 tokens is rejected on the write side and clamped up on the read path, matching the compaction-floor discipline.
109 lines
4.4 KiB
TypeScript
109 lines
4.4 KiB
TypeScript
/**
|
|
* The custom endpoint's connect surface (one provider in the Keys list).
|
|
* GET → non-secret config { baseUrl, models, overrides } + keyPresent (masked).
|
|
* POST → connect: validate + normalize the base URL, probe /models (fail
|
|
* fast), store the key, persist { baseUrl, models }, re-sync the
|
|
* provider into piModels(). Discovery lives here because connecting
|
|
* and discovering are one user action. Stored user pins survive a
|
|
* reconnect, pruned to the ids the endpoint still advertises.
|
|
* PATCH → store per-model pins only. No probe: pins must be editable with
|
|
* the local server switched off (the case they exist for).
|
|
* DELETE → disconnect: drop the stored config + the stored key and unregister
|
|
* the provider (the mirror image of POST; idempotent).
|
|
*/
|
|
import {
|
|
deleteKey,
|
|
discoverModels,
|
|
effectiveSettings,
|
|
keyValue,
|
|
parseCustomModelOverridesBody,
|
|
readSettingsRecord,
|
|
saveKey,
|
|
syncCustomProvider,
|
|
writeSettingsRecord,
|
|
} from "@/src/server";
|
|
import { CUSTOM_PROVIDER, normalizeBaseUrl, sanitizeCustomModelOverrides } from "@/src/core";
|
|
|
|
export const dynamic = "force-dynamic";
|
|
|
|
export async function GET() {
|
|
const cp = effectiveSettings().customProvider;
|
|
return Response.json({
|
|
baseUrl: cp.baseUrl,
|
|
models: cp.models,
|
|
overrides: cp.overrides,
|
|
keyPresent: keyValue(CUSTOM_PROVIDER.envVar) !== undefined,
|
|
});
|
|
}
|
|
|
|
export async function POST(request: Request) {
|
|
const body = (await request.json().catch(() => null)) as { baseUrl?: unknown; key?: unknown } | null;
|
|
const base = normalizeBaseUrl(typeof body?.baseUrl === "string" ? body.baseUrl : "");
|
|
if (!base) return Response.json({ error: "Base URL must be a valid http(s) URL" }, { status: 400 });
|
|
|
|
// Empty key string clears it, absent leaves it stored; only a real key rides the probe.
|
|
const keyProvided = typeof body?.key === "string";
|
|
const key = keyProvided ? (body!.key as string).trim() : undefined;
|
|
|
|
// Probe first: a URL that doesn't answer with a model list never persists.
|
|
const found = await discoverModels(base, key ? key : undefined);
|
|
if (!found.ok) return Response.json({ error: found.error }, { status: 502 });
|
|
|
|
if (keyProvided) {
|
|
if (key) {
|
|
const saved = saveKey(CUSTOM_PROVIDER.envVar, key);
|
|
if (!saved.ok) return Response.json({ error: saved.error }, { status: 400 });
|
|
} else {
|
|
deleteKey(CUSTOM_PROVIDER.envVar);
|
|
}
|
|
}
|
|
|
|
const record = readSettingsRecord() ?? { version: 1 };
|
|
// User pins are never rewritten by discovery — only pruned to what the
|
|
// endpoint still advertises (the single prune law, core/settings.ts).
|
|
const overrides = sanitizeCustomModelOverrides(
|
|
record.customProvider?.overrides,
|
|
found.models.map((m) => m.id),
|
|
);
|
|
const next = writeSettingsRecord({
|
|
...record,
|
|
customProvider: { baseUrl: base, models: found.models, overrides },
|
|
});
|
|
syncCustomProvider(next.customProvider);
|
|
return Response.json({ ok: true, models: next.customProvider?.models ?? [] });
|
|
}
|
|
|
|
/** Store the per-model pins (replace-whole). Pruned against the STORED model
|
|
* list, never a probe — an offline endpoint keeps its pins editable. */
|
|
export async function PATCH(request: Request) {
|
|
const parsed = parseCustomModelOverridesBody(await request.json().catch(() => null));
|
|
if (!parsed.ok) return Response.json({ error: parsed.error }, { status: 400 });
|
|
|
|
const cp = effectiveSettings().customProvider;
|
|
if (!cp.baseUrl) return Response.json({ error: "No custom endpoint configured" }, { status: 409 });
|
|
|
|
const overrides = sanitizeCustomModelOverrides(
|
|
parsed.settings,
|
|
cp.models.map((m) => m.id),
|
|
);
|
|
const record = readSettingsRecord() ?? { version: 1 };
|
|
const next = writeSettingsRecord({
|
|
...record,
|
|
customProvider: { baseUrl: cp.baseUrl, models: cp.models, overrides },
|
|
});
|
|
syncCustomProvider(next.customProvider);
|
|
return Response.json({ ok: true, overrides: next.customProvider?.overrides ?? {} });
|
|
}
|
|
|
|
/** Disconnect: forget the endpoint AND its key, then unregister the provider.
|
|
* Deleting the section (rather than blanking baseUrl) keeps settings.json the
|
|
* same shape as a never-connected install. Idempotent by construction. */
|
|
export async function DELETE() {
|
|
const record = readSettingsRecord() ?? { version: 1 };
|
|
const { customProvider: _dropped, ...rest } = record;
|
|
const next = writeSettingsRecord(rest);
|
|
deleteKey(CUSTOM_PROVIDER.envVar);
|
|
syncCustomProvider(next.customProvider);
|
|
return Response.json({ ok: true });
|
|
}
|