Fixing race condition in server and partial stream handling in frontend. (#2391)

* Fixing race condition in server.cpp and partial stream handling in completion.js

* Reverting assert edits.

* Adding newline to eof

examples/server/public/completion.js

@@ -43,6 +43,7 @@ export async function* llama(prompt, params = {}, config = {}) {
   const decoder = new TextDecoder();
 
   let content = "";
+  let leftover = ""; // Buffer for partially read lines
 
   try {
     let cont = true;
@@ -53,17 +54,31 @@ export async function* llama(prompt, params = {}, config = {}) {
         break;
       }
 
-      // sse answers in the form multiple lines of: value\n with data always present as a key. in our case we
+      // Add any leftover data to the current chunk of data
-      // mainly care about the data: key here, which we expect as json
+      const text = leftover + decoder.decode(result.value);
-      const text = decoder.decode(result.value);
 
-      // parse all sse events and add them to result
+      // Check if the last character is a line break
-      const regex = /^(\S+):\s(.*)$/gm;
+      const endsWithLineBreak = text.endsWith('\n');
-      for (const match of text.matchAll(regex)) {
+
-        result[match[1]] = match[2]
+      // Split the text into lines
+      let lines = text.split('\n');
+
+      // If the text doesn't end with a line break, then the last line is incomplete
+      // Store it in leftover to be added to the next chunk of data
+      if (!endsWithLineBreak) {
+        leftover = lines.pop();
+      } else {
+        leftover = ""; // Reset leftover if we have a line break at the end
       }
 
+      // Parse all sse events and add them to result
+      const regex = /^(\S+):\s(.*)$/gm;
+      for (const line of lines) {
+        const match = regex.exec(line);
+        if (match) {
+          result[match[1]] = match[2]
           // since we know this is llama.cpp, let's just decode the json in data
+          if (result.data) {
             result.data = JSON.parse(result.data);
             content += result.data.content;
 
@@ -75,9 +90,13 @@ export async function* llama(prompt, params = {}, config = {}) {
               if (result.data.generation_settings) {
                 generation_settings = result.data.generation_settings;
               }
+              cont = false;
               break;
             }
           }
+        }
+      }
+    }
   } catch (e) {
     if (e.name !== 'AbortError') {
       console.error("llama error: ", e);

examples/server/server.cpp

@@ -1274,7 +1274,11 @@ int main(int argc, char **argv)
                 sink.done();
                 return true;
             };
-            res.set_chunked_content_provider("text/event-stream", chunked_content_provider);
+            const auto on_complete = [&](bool) {
+                llama.mutex.unlock();
+            };
+            lock.release();
+            res.set_chunked_content_provider("text/event-stream", chunked_content_provider, on_complete);
         } });
 
     svr.Get("/model.json", [&llama](const Request &, Response &res)