fix: integrate Claude CLI provider state

packages/web/server/lib/small-model/index.js

@@ -120,6 +120,13 @@ export async function generateSmallModelText({ prompt, system, maxOutputTokens,
     );
   }
 
+  if (resolved.providerID === 'claude-code') {
+    throw Object.assign(
+      new Error('Claude Code cannot be used for background small-model actions. Choose another Small Model in Settings → Sessions.'),
+      { statusCode: 422, code: 'small-model-provider-unsupported' },
+    );
+  }
+
   // Callers with a session context can forbid silently switching providers:
   // an explicit user choice (settings override, opencode config, request
   // model) is always allowed, anything else must stay on the session's
@@ -183,6 +190,7 @@ export function listAuthenticatedProviders() {
     const ids = new Set(
       Object.keys(auth || {}).filter((providerID) => isUsableAuthEntry(auth[providerID])),
     );
+    ids.delete('claude-code');
     // The catalog id is github-copilot while legacy auth entries may sit
     // under the copilot alias.
     if (isUsableAuthEntry(getAuthEntryForProvider(auth, 'github-copilot'))) {

packages/web/server/lib/small-model/index.test.js

@@ -26,12 +26,42 @@ vi.mock('./call.js', () => ({
   }),
 }));
 
-const { generateSmallModelText, describeSmallModel } = await import('./index.js');
+const { generateSmallModelText, describeSmallModel, listAuthenticatedProviders } = await import('./index.js');
 const { readAuthFile } = await import('../opencode/auth.js');
 const { readConfigLayers } = await import('../opencode/shared.js');
 const { getModelCatalog } = await import('./catalog.js');
 const { callSmallModel } = await import('./call.js');
 
+describe('unsupported small-model providers', () => {
+  beforeEach(() => {
+    readAuthFile.mockReturnValue({
+      'claude-code': {
+        type: 'oauth',
+        access: 'claude-cli-managed',
+        refresh: 'claude-cli-managed',
+      },
+    });
+    readConfigLayers.mockReturnValue({ mergedConfig: {} });
+    getModelCatalog.mockResolvedValue({});
+    callSmallModel.mockReset();
+  });
+
+  it('rejects Claude Code with an actionable error before transport dispatch', async () => {
+    await expect(generateSmallModelText({
+      prompt: 'summarize this',
+      model: 'claude-code/haiku',
+    })).rejects.toMatchObject({
+      statusCode: 422,
+      code: 'small-model-provider-unsupported',
+    });
+    expect(callSmallModel).not.toHaveBeenCalled();
+  });
+
+  it('does not offer Claude Code in the Small Model picker', () => {
+    expect(listAuthenticatedProviders()).not.toContain('claude-code');
+  });
+});
+
 // 8k context leaves 4k input tokens after the output reserve → 16k chars.
 const CATALOG = {
   anthropic: {

packages/web/server/lib/small-model/routes.js

@@ -39,7 +39,9 @@ export function registerSmallModelRoutes(app, { getSmallModelService }) {
         console.error('Small model generation failed:', error);
       }
       res.status(statusCode).json({
-        error: error.message || 'Small model generation failed',
+        error: statusCode === 404
+          ? (error.message || 'No small model is available')
+          : 'The selected Small Model could not complete this action. Choose another model in Settings → Sessions → Small Model and try again.',
         ...(error?.code ? { code: error.code } : {}),
       });
     }