# v0.5.70 (2026-09-08)

## Features
- **Providers**: creating a compatible / custom-embedding node now registers the endpoint only — the API key is added afterwards from the node's page, like the built-in providers. The create dialogs drop the API Key / Model ID / Check fields, and `POST /api/provider-nodes` no longer accepts credentials at all, so a node can never be half-created
- **Providers**: compatible nodes now use the same model rows as built-in providers — capability badges, copy, per-model test, alias handling and the Add/Edit Model modal with vision + reasoning toggles, replacing the weaker read-only list
- **Providers**: compatible nodes get the built-in bulk toolbars: Test All / Disable / Active / Select All over connections, and Test All Models / Disable All / Active All over models, with per-row disable and a restore strip for disabled models
- **Providers**: wire the dead "Fetch Models" button on compatible nodes to the live upstream catalog, de-duplicating against already-added models

## Fixes
- **Models**: persist per-model capability assertions for custom and compatible providers and honor them everywhere — unsupported media is stripped on the chat path, `/v1/models` and `/api/models` report what the user asserted, and thinking translation follows it (asserting `reasoning:false` now actually strips thinking fields, `reasoning:true` emits them)
- **Models**: partial capability edits merge instead of overwriting, so toggling vision off no longer erases a stored reasoning assertion
- **Capabilities**: keep server-injected readers (synced catalog, user-asserted capabilities) in process-wide state — Next.js compiles startup and each API route into separate bundles with their own module instances, so a boot-time install was invisible to every request handler and the models.dev catalog contributed nothing to upstream requests since 0532f00d
- **Dashboard**: thinking-level picker and model-row suffix reflect user-asserted reasoning on compatible nodes
- **Providers**: `Default Model` is optional when adding an API key to a compatible node — the node's own model list (and the picker in the test modals) already determine what gets probed, and the built-in fallback still covers connection checks
- **Providers**: restore the `useCopyToClipboard` import dropped from the provider detail page, which crashed the route with `ReferenceError` for every provider
- **DB**: restore `getModelAliases` / `setModelAlias` / `deleteModelAlias` re-exports dropped from the `localDb` shim by 86112cee, which broke `GET /api/models` and `GET /v1/models` at import time
- **Providers**: remove dead `PassthroughModelsSection` (never passed props, superseded by the shared model rows)
- **Media Providers**: creating a custom embedding node reports that a key still has to be added, instead of claiming a key was saved; the edit dialog keeps its API Key + Check affordance since a stored key already exists there
- **Build**: self-host Inter instead of fetching it through `next/font/google` at build time — a Docker / mirrored builder with no route to `fonts.googleapis.com` failed the entire image build on `Failed to fetch 'Inter' from Google Fonts`. The seven `@font-face` rules and their `unicode-range`s copy what `next/font` emitted (a `latin`-only file would have dropped Vietnamese diacritics) and the latin subset is preloaded as before, so rendered metrics are unchanged

tests/unit/capability-source-instance.test.js

@@ -0,0 +1,76 @@
+import { afterEach, describe, expect, it, vi } from "vitest";
+
+/**
+ * Next.js compiles `instrumentation.js` and every API route into SEPARATE server
+ * bundles, so one source file gets a distinct module instance per bundle. A
+ * reader installed into a plain module-local variable therefore lands in the
+ * startup copy while the chat route reads its own still-empty copy: the setter
+ * appears to succeed and the feature is silently dead.
+ *
+ * Distinct `?bundle=` suffixes give this file two instances of the same module in
+ * one process — it models "two bundles" without a real build.
+ */
+const boot = await import("../../open-sse/providers/capabilities.js?bundle=boot");
+const route = await import("../../open-sse/providers/capabilities.js?bundle=route");
+
+afterEach(() => {
+  boot.setUserCapsSource(null);
+  boot.setCatalogSource(null);
+});
+
+describe("capability sources across server bundles", () => {
+  it("keeps distinct module instances per bundle", () => {
+    // If these ever collapse into one instance the tests below prove nothing.
+    expect(route).not.toBe(boot);
+  });
+
+  it("honours a user-asserted caps source installed at startup", () => {
+    boot.setUserCapsSource(() => ({ vision: false }));
+    // qwen3-vl-plus is vision by name heuristic; the assertion must win in the
+    // bundle that actually serves the request.
+    expect(route.getCapabilitiesForModel("custom-node", "qwen3-vl-plus").vision).toBe(false);
+
+    boot.setUserCapsSource(() => ({ reasoning: true }));
+    expect(route.getCapabilitiesForModel("custom-node", "my-private-chatml-9").reasoning).toBe(true);
+  });
+
+  it("honours a catalog source installed at startup", () => {
+    boot.setCatalogSource({
+      getModalities: (model) => (model === "hand-rolled-7b" ? { vision: true } : null),
+      getLimits: (provider, model) => (model === "hand-rolled-7b" ? { contextWindow: 400000 } : null),
+    });
+    const caps = route.getCapabilitiesForModel("custom-node", "hand-rolled-7b");
+    expect(caps.vision).toBe(true);
+    expect(caps.contextWindow).toBe(400000);
+  });
+
+  it("detaches the catalog everywhere when one bundle detaches it", () => {
+    // modelCatalog/sync.js nulls the reader while computing a delta against the
+    // hand-written tables, then reinstalls it; both bundles must agree.
+    boot.setCatalogSource({ getModalities: () => ({ vision: true }), getLimits: () => null });
+    expect(route.getCapabilitiesForModel("custom-node", "hand-rolled-7b").vision).toBe(true);
+
+    boot.setCatalogSource(null);
+    expect(route.getCapabilitiesForModel("custom-node", "hand-rolled-7b").vision).toBe(false);
+  });
+});
+
+describe("user-caps snapshot across server bundles", () => {
+  const rows = [{ providerAlias: "node-abc", id: "chat-9", type: "llm", caps: { reasoning: true } }];
+
+  it("makes a rebuild started by the write route visible to the request route", async () => {
+    vi.doMock("@/lib/db/index.js", () => ({ getCustomModels: async () => rows }));
+    try {
+      const write = await import("../../src/lib/modelCaps/userCaps.js?bundle=write");
+      const request = await import("../../src/lib/modelCaps/userCaps.js?bundle=request");
+
+      write.invalidateUserCaps();
+      await vi.waitFor(() => {
+        expect(request.getUserCapsFor("node-abc", "chat-9")).toEqual({ reasoning: true });
+      });
+    } finally {
+      vi.doUnmock("@/lib/db/index.js");
+      vi.resetModules();
+    }
+  });
+});