feat: Reginald follows the model you load (auto-detect) + shows it in the header

Instead of a hardcoded model name (which forces LM Studio to JIT-swap your loaded
model out — and fails when a big model already fills memory), resolve the model
at request time: an explicit env override wins, else ask the server which model
is *loaded* (LM Studio's native /api/v0/models), else the first non-embedding
model, else a default. Reginald now uses whatever you load, no config churn.

- main/model.ts: resolveLoadedModel() drives both model:status and model:chat;
  COMMITEA_MODEL_SMALL still overrides.
- useChat exposes the resolved model id; the panel header shows it
  (google/gemma-4-26b-a4b-qat → "gemma-4-26b-a4b · local").
- live-reginald e2e: header assertion relaxed to the loaded model; timeouts
  raised for a slow big local model (~2 calls/turn + a reconcile).

Verified: 14 fixture e2e green; live e2e drives the app against the loaded
gemma-4-26b — "What now?" → "You should work on #2 … on the critical path,
unblocks #33 and #4" (the real scheduler pick), header shows the live model.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

apps/desktop/src/main/model.ts

@@ -28,23 +28,57 @@ function resolveModelRouter(): ModelRouter | null {
   const baseUrl = process.env.COMMITEA_MODEL_URL ?? 'http://localhost:1234/v1'
   if (!baseUrl) return null
   return {
-    small: { baseUrl, model: process.env.COMMITEA_MODEL_SMALL ?? 'google/gemma-4-e4b' },
-    big: { baseUrl, model: process.env.COMMITEA_MODEL_BIG ?? 'qwen/qwen3.6-35b-a3b' },
+    small: { baseUrl, model: process.env.COMMITEA_MODEL_SMALL ?? '' },
+    big: { baseUrl, model: process.env.COMMITEA_MODEL_BIG ?? '' },
   }
 }
 
+/**
+ * Resolve which model to actually ask for. An explicit env override wins;
+ * otherwise ask the server which model is *loaded* (LM Studio's native
+ * `/api/v0/models`) so Reginald follows whatever you load — no config churn on a
+ * model switch. Falls back to the first non-embedding model, then a sane default.
+ */
+async function resolveLoadedModel(baseUrl: string, override: string): Promise<string> {
+  if (override) return override
+  const root = baseUrl.replace(/\/v1\/?$/, '')
+  try {
+    const res = await fetch(`${root}/api/v0/models`)
+    if (res.ok) {
+      const data = (await res.json()) as { data?: { id: string; state?: string; type?: string }[] }
+      const loaded = (data.data ?? []).find((m) => m.state === 'loaded' && m.type !== 'embeddings')
+      if (loaded) return loaded.id
+    }
+  } catch {
+    // native API unavailable — fall through to the OpenAI listing
+  }
+  try {
+    const res = await fetch(`${baseUrl.replace(/\/+$/, '')}/models`)
+    if (res.ok) {
+      const data = (await res.json()) as { data?: { id: string }[] }
+      const first = (data.data ?? []).find((m) => !/embed/i.test(m.id))
+      if (first) return first.id
+    }
+  } catch {
+    // ignore — use the default
+  }
+  return 'google/gemma-4-e4b'
+}
+
 export function registerModelIpc(): void {
   const router = resolveModelRouter()
 
-  ipcMain.handle('model:status', () => ({
-    configured: !!router,
-    model: router?.small.model ?? null,
-  }))
+  ipcMain.handle('model:status', async () => {
+    if (!router) return { configured: false, model: null }
+    const model = await resolveLoadedModel(router.small.baseUrl, router.small.model)
+    return { configured: true, model }
+  })
 
   ipcMain.handle('model:chat', async (_event, messages: ChatMessage[]) => {
     if (!router) return { ok: false as const, reason: 'unconfigured' as const }
     const client = getGiteaClient()
-    const chat = createChatClient(router.small, fetch)
+    const model = await resolveLoadedModel(router.small.baseUrl, router.small.model)
+    const chat = createChatClient({ ...router.small, model }, fetch)
 
     const execute = async (name: string, args: unknown) => {
       if (name !== 'query_project') return { error: `unknown tool: ${name}` }