feat(provider): expose Atomic Chat in /provider picker with autodetect (#810)

Adds Atomic Chat as a first-class preset inside the in-session /provider
slash command, mirroring the Ollama auto-detect flow. Picking it probes
127.0.0.1:1337/v1/models, lists loaded models for direct selection, and
falls back to "Enter manually" / "Back" when the server is unreachable
or no models are loaded. README updated to reflect the new setup path.

Made-with: Cursor

src/utils/providerDiscovery.test.ts

@@ -298,4 +298,66 @@ test('ollama generation readiness reports ready when chat probe succeeds', async
     state: 'ready',
     probeModel: 'llama3.1:8b',
   })
+})
+
+test('atomic chat readiness reports unreachable when /v1/models is down', async () => {
+  const { probeAtomicChatReadiness } = await loadProviderDiscoveryModule()
+
+  const calledUrls: string[] = []
+  globalThis.fetch = mock(input => {
+    const url = typeof input === 'string' ? input : input.url
+    calledUrls.push(url)
+    return Promise.resolve(new Response('unavailable', { status: 503 }))
+  }) as typeof globalThis.fetch
+
+  await expect(
+    probeAtomicChatReadiness({ baseUrl: 'http://127.0.0.1:1337' }),
+  ).resolves.toEqual({ state: 'unreachable' })
+
+  expect(calledUrls[0]).toBe('http://127.0.0.1:1337/v1/models')
+})
+
+test('atomic chat readiness reports no_models when server is reachable but empty', async () => {
+  const { probeAtomicChatReadiness } = await loadProviderDiscoveryModule()
+
+  globalThis.fetch = mock(() =>
+    Promise.resolve(
+      new Response(JSON.stringify({ data: [] }), {
+        status: 200,
+        headers: { 'Content-Type': 'application/json' },
+      }),
+    ),
+  ) as typeof globalThis.fetch
+
+  await expect(
+    probeAtomicChatReadiness({ baseUrl: 'http://127.0.0.1:1337' }),
+  ).resolves.toEqual({ state: 'no_models' })
+})
+
+test('atomic chat readiness returns loaded model ids when ready', async () => {
+  const { probeAtomicChatReadiness } = await loadProviderDiscoveryModule()
+
+  globalThis.fetch = mock(() =>
+    Promise.resolve(
+      new Response(
+        JSON.stringify({
+          data: [
+            { id: 'Qwen3_5-4B_Q4_K_M' },
+            { id: 'llama-3.1-8b-instruct' },
+          ],
+        }),
+        {
+          status: 200,
+          headers: { 'Content-Type': 'application/json' },
+        },
+      ),
+    ),
+  ) as typeof globalThis.fetch
+
+  await expect(
+    probeAtomicChatReadiness({ baseUrl: 'http://127.0.0.1:1337' }),
+  ).resolves.toEqual({
+    state: 'ready',
+    models: ['Qwen3_5-4B_Q4_K_M', 'llama-3.1-8b-instruct'],
+  })
 })

src/utils/providerDiscovery.ts

@@ -302,6 +302,24 @@ export async function listAtomicChatModels(
   }
 }
 
+export type AtomicChatReadiness =
+  | { state: 'unreachable' }
+  | { state: 'no_models' }
+  | { state: 'ready'; models: string[] }
+
+export async function probeAtomicChatReadiness(options?: {
+  baseUrl?: string
+}): Promise<AtomicChatReadiness> {
+  if (!(await hasLocalAtomicChat(options?.baseUrl))) {
+    return { state: 'unreachable' }
+  }
+  const models = await listAtomicChatModels(options?.baseUrl)
+  if (models.length === 0) {
+    return { state: 'no_models' }
+  }
+  return { state: 'ready', models }
+}
+
 export async function benchmarkOllamaModel(
   modelName: string,
   baseUrl?: string,

src/utils/providerProfiles.test.ts

@@ -527,6 +527,18 @@ describe('getProviderPresetDefaults', () => {
     expect(defaults.baseUrl).toBe('http://localhost:11434/v1')
     expect(defaults.model).toBe('llama3.1:8b')
   })
+
+  test('atomic-chat preset defaults to a local Atomic Chat endpoint', async () => {
+    const { getProviderPresetDefaults } = await importFreshProviderProfileModules()
+    delete process.env.OPENAI_MODEL
+
+    const defaults = getProviderPresetDefaults('atomic-chat')
+
+    expect(defaults.provider).toBe('openai')
+    expect(defaults.name).toBe('Atomic Chat')
+    expect(defaults.baseUrl).toBe('http://127.0.0.1:1337/v1')
+    expect(defaults.requiresApiKey).toBe(false)
+  })
 })
 
 describe('setActiveProviderProfile', () => {

src/utils/providerProfiles.ts

@@ -33,6 +33,7 @@ export type ProviderPreset =
   | 'custom'
   | 'nvidia-nim'
   | 'minimax'
+  | 'atomic-chat'
 
 export type ProviderProfileInput = {
   provider?: ProviderProfile['provider']
@@ -285,6 +286,15 @@ export function getProviderPresetDefaults(
         apiKey: process.env.MINIMAX_API_KEY ?? '',
         requiresApiKey: true,
       }
+    case 'atomic-chat':
+      return {
+        provider: 'openai',
+        name: 'Atomic Chat',
+        baseUrl: 'http://127.0.0.1:1337/v1',
+        model: process.env.OPENAI_MODEL ?? 'local-model',
+        apiKey: '',
+        requiresApiKey: false,
+      }
     case 'ollama':
     default:
       return {