Merge branch 'main' into chore/update-claude-fallback-models

Co-authored-by: Simos Mikelatos <simosmik@gmail.com>

public/modelConstants.js

@@ -11,7 +11,8 @@ export const CLAUDE_MODELS = {
     {
       value: "default",
       label: "Default (recommended)",
-      description: "Use the default model (currently Opus 4.8 (1M context)) · $5/$25 per Mtok",
+      description:
+        "Use the default model (currently Opus 4.8 (1M context)) · $5/$25 per Mtok",
     },
     {
       value: "sonnet",
@@ -23,6 +24,12 @@ export const CLAUDE_MODELS = {
       label: "Sonnet (1M context)",
       description: "Sonnet 4.6 for long sessions · $3/$15 per Mtok",
     },
+    {
+      value: "opus[1m]",
+      label: "Opus 4.8 (1M context)",
+      description:
+        "Opus 4.8 with 1M context · Most capable for complex work · $5/$25 per Mtok",
+    },
     {
       value: "haiku",
       label: "Haiku",

server/modules/providers/list/claude/claude-models.provider.ts

@@ -18,18 +18,23 @@ export const CLAUDE_FALLBACK_MODELS: ProviderModelsDefinition = {
     {
       value: 'default',
       label: 'Default (recommended)',
-      description: 'Use the default model (currently Opus 4.7 (1M context)) · $5/$25 per Mtok',
+      description: 'Use the default model (currently Opus 4.8 (1M context)) · $5/$25 per Mtok',
     },
     {
-      value: 'sonnet',
-      label: 'Sonnet',
-      description: 'Sonnet 4.6 · Best for everyday tasks · $3/$15 per Mtok',
+      value: "sonnet",
+      label: "Sonnet",
+      description: "Sonnet 4.6 · Best for everyday tasks · $3/$15 per Mtok",
     },
     {
       value: 'sonnet[1m]',
       label: 'Sonnet (1M context)',
       description: 'Sonnet 4.6 for long sessions · $3/$15 per Mtok',
     },
+    {
+      value: 'opus[1m]',
+      label: 'Opus 4.8 (1M context)',
+      description: 'Opus 4.8 with 1M context · Most capable for complex work · $5/$25 per Mtok',
+    },
     {
       value: 'haiku',
       label: 'Haiku',

server/modules/providers/services/provider-models.service.ts

@@ -17,6 +17,7 @@ import { readProviderSessionActiveModelChange } from '@/shared/utils.js';
 
 export const PROVIDER_MODELS_CACHE_TTL_MS = 3 * 24 * 60 * 60 * 1000;
 const PROVIDER_MODELS_CACHE_VERSION = 1;
+const UNCACHED_PROVIDERS = new Set<LLMProvider>(['claude']);
 
 type ProviderModelsServiceDependencies = {
   resolveProvider?: (provider: LLMProvider) => Pick<IProvider, 'models'>;
@@ -232,10 +233,42 @@ export const createProviderModelsService = (dependencies: ProviderModelsServiceD
     return request;
   };
 
+  const loadDirectModels = (
+    provider: LLMProvider,
+  ): Promise<ProviderModelsResult> => {
+    const request = resolveProvider(provider).models.getSupportedModels()
+      .then((models) => {
+        const currentTime = now();
+        return {
+          models,
+          cache: {
+            updatedAt: new Date(currentTime).toISOString(),
+            expiresAt: new Date(currentTime).toISOString(),
+            source: 'fresh' as const,
+          },
+        };
+      })
+      .finally(() => {
+        pendingRequests.delete(provider);
+      });
+
+    pendingRequests.set(provider, request);
+    return request;
+  };
+
   const getProviderModels = async (
     provider: LLMProvider,
     options: ProviderModelsOptions = {},
   ): Promise<ProviderModelsResult> => {
+    if (UNCACHED_PROVIDERS.has(provider)) {
+      const pendingRequest = pendingRequests.get(provider);
+      if (pendingRequest) {
+        return pendingRequest;
+      }
+
+      return loadDirectModels(provider);
+    }
+
     if (options.bypassCache) {
       const pendingRequest = pendingRequests.get(provider);
       if (pendingRequest) {

server/modules/providers/tests/provider-models.service.test.ts

@@ -130,6 +130,37 @@ test('provider models are cached for the three-day ttl', async () => {
   }
 });
 
+test('claude provider models are always loaded directly from the provider', async () => {
+  const tempRoot = await mkdtemp(path.join(os.tmpdir(), 'provider-model-cache-claude-direct-'));
+  let loadCount = 0;
+
+  try {
+    const service = createProviderModelsService({
+      cachePath: path.join(tempRoot, 'models-cache.json'),
+      resolveProvider: (provider) => ({
+        models: {
+          getSupportedModels: async () => {
+            loadCount += 1;
+            return createModels(`${provider}-${loadCount}`);
+          },
+          getCurrentActiveModel: async () => createCurrentActiveModel(`${provider}-active`),
+          changeActiveModel: async (input) => createSessionActiveModelChange(provider, input),
+        },
+      }),
+    });
+
+    const first = await service.getProviderModels('claude');
+    const second = await service.getProviderModels('claude');
+
+    assert.equal(loadCount, 2);
+    assert.equal(first.models.DEFAULT, 'claude-1');
+    assert.equal(second.models.DEFAULT, 'claude-2');
+    assert.equal(second.cache.source, 'fresh');
+  } finally {
+    await rm(tempRoot, { recursive: true, force: true });
+  }
+});
+
 test('provider model cache is persisted across service instances', async () => {
   const tempRoot = await mkdtemp(path.join(os.tmpdir(), 'provider-model-cache-file-'));
   const cachePath = path.join(tempRoot, 'models-cache.json');