groove-dev 0.27.128 → 0.27.130

package/node_modules/@groove-dev/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@groove-dev/cli",
-  "version": "0.27.128",
+  "version": "0.27.130",
   "description": "GROOVE CLI — manage AI coding agents from your terminal",
   "license": "FSL-1.1-Apache-2.0",
   "type": "module",

package/node_modules/@groove-dev/daemon/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@groove-dev/daemon",
-  "version": "0.27.128",
+  "version": "0.27.130",
   "description": "GROOVE daemon — agent orchestration engine",
   "license": "FSL-1.1-Apache-2.0",
   "type": "module",

package/node_modules/@groove-dev/daemon/src/api.js

@@ -6669,6 +6669,27 @@ Keep responses concise. Help them think, don't lecture them about the system the
     }
   });
 
+  app.get('/api/lab/local-models', (req, res) => {
+    try {
+      res.json(daemon.modelLab.listLocalModels());
+    } catch (err) {
+      res.status(500).json({ error: err.message });
+    }
+  });
+
+  app.post('/api/lab/launch-local', async (req, res) => {
+    try {
+      const { modelId } = req.body;
+      if (!modelId || typeof modelId !== 'string') {
+        return res.status(400).json({ error: 'modelId is required' });
+      }
+      const result = await daemon.modelLab.launchLocalModel(modelId);
+      res.json(result);
+    } catch (err) {
+      res.status(400).json({ error: err.message });
+    }
+  });
+
   app.post('/api/lab/inference', async (req, res) => {
     try {
       const params = validateLabInferenceParams(req.body);

package/node_modules/@groove-dev/daemon/src/model-lab.js

@@ -442,6 +442,52 @@ export class ModelLab {
     this._saveSession(session);
   }
 
+  // ─── Launch Local GGUF ───────────────────────────────────────
+
+  async launchLocalModel(modelId) {
+    const mm = this.daemon.modelManager;
+    const ls = this.daemon.llamaServer;
+    if (!mm || !ls) throw new Error('Local model serving not available');
+
+    const model = mm.getModel(modelId);
+    if (!model) throw new Error('Model not found in local store');
+
+    const modelPath = mm.getModelPath(modelId);
+    if (!modelPath) throw new Error('Model file not found on disk');
+
+    const endpoint = await ls.ensureServer(modelPath);
+    if (!endpoint) throw new Error('Failed to start inference server');
+
+    const existing = [...this.runtimes.values()].find(
+      (r) => r._localModelId === modelId,
+    );
+    if (existing) {
+      existing.endpoint = endpoint;
+      existing.models = [{ id: model.filename, name: model.filename, size: model.sizeBytes }];
+      this._saveRuntimes();
+      this.daemon.broadcast({ type: 'lab:runtime:updated', data: existing });
+      return { runtime: existing, model: model.filename };
+    }
+
+    const label = model.filename.replace(/\.gguf$/i, '');
+    const runtime = await this.addRuntime({
+      name: `${label} (local)`,
+      type: 'llama-cpp',
+      endpoint,
+      models: [{ id: model.filename, name: model.filename, size: model.sizeBytes }],
+    });
+    runtime._localModelId = modelId;
+    this._saveRuntimes();
+
+    return { runtime, model: model.filename };
+  }
+
+  listLocalModels() {
+    const mm = this.daemon.modelManager;
+    if (!mm) return [];
+    return mm.getInstalled().filter((m) => m.exists);
+  }
+
   // ─── Auto-detect Ollama ─────────────────────────────────────
 
   async autoDetectOllama() {