minor clean up

packages/inference-service/src/index.js

@@ -4,7 +4,7 @@ const {getEnv, PORTS, OLLAMA, logger} = require('@nexusai/shared');
 const inferenceRouter = require('./routes/inference');
 
 const app = express();
-app.use(express.json());
+app.use(express.json({ limit: '8mb' }));  // prompts include full context window
 
 const PORT      = getEnv('PORT', PORTS.INFERENCE);
 const PROVIDER  = getEnv('INFERENCE_PROVIDER',   'ollama');

packages/inference-service/src/providers/ollama.js

@@ -57,7 +57,16 @@ async function* completeStream(prompt, options = {} ) {
     });
 
     for await (const chunk of stream) {
-        yield chunk;
+        if (chunk.done) {
+            yield {
+                response:   '',
+                done:       true,
+                model:      chunk.model,
+                tokenCount: (chunk.eval_count ?? 0) + (chunk.prompt_eval_count ?? 0),
+            };
+        } else {
+            yield chunk;
+        }
     }
 }
 

packages/inference-service/src/routes/inference.js

@@ -23,7 +23,7 @@ router.post('/complete', async (req, res) => {
 
 // Streaming completion endpoint - sends partial responses as they arrive
 router.post('/complete/stream', async (req, res) => {
-    const { prompt, model, temperature, topP, topK, repeatPenalty } = req.body;
+    const { prompt, model, temperature, maxTokens, topP, topK, repeatPenalty } = req.body;
 
     if (!prompt) return res.status(400).json({ error: 'prompt is required' });
 
@@ -35,7 +35,7 @@ router.post('/complete/stream', async (req, res) => {
         let lastModel = model;
         let tokenCount = 0;
 
-        for await (const chunk of completeStream(prompt, { model, temperature, topP, topK, repeatPenalty })) {
+        for await (const chunk of completeStream(prompt, { model, temperature, maxTokens,topP, topK, repeatPenalty })) {
             if (chunk.response) {
                 res.write(`data: ${JSON.stringify({ response: chunk.response })}\n\n`);
             }