feat: enhanced Code Context and Project Summary Features (#1191)

* fix: docker prod env variable fix

* lint and typecheck

* removed hardcoded tag

* better summary generation

* improved  summary generation for context optimization

* remove think tags from the generation

app/routes/api.llmcall.ts

@@ -7,6 +7,7 @@ import { MAX_TOKENS } from '~/lib/.server/llm/constants';
 import { LLMManager } from '~/lib/modules/llm/manager';
 import type { ModelInfo } from '~/lib/modules/llm/types';
 import { getApiKeysFromCookie, getProviderSettingsFromCookie } from '~/lib/api/cookies';
+import { createScopedLogger } from '~/utils/logger';
 
 export async function action(args: ActionFunctionArgs) {
   return llmCallAction(args);
@@ -21,6 +22,8 @@ async function getModelList(options: {
   return llmManager.updateModelList(options);
 }
 
+const logger = createScopedLogger('api.llmcall');
+
 async function llmCallAction({ context, request }: ActionFunctionArgs) {
   const { system, message, model, provider, streamOutput } = await request.json<{
     system: string;
@@ -106,6 +109,8 @@ async function llmCallAction({ context, request }: ActionFunctionArgs) {
         throw new Error('Provider not found');
       }
 
+      logger.info(`Generating response Provider: ${provider.name}, Model: ${modelDetails.name}`);
+
       const result = await generateText({
         system,
         messages: [
@@ -123,6 +128,7 @@ async function llmCallAction({ context, request }: ActionFunctionArgs) {
         maxTokens: dynamicMaxTokens,
         toolChoice: 'none',
       });
+      logger.info(`Generated response`);
 
       return new Response(JSON.stringify(result), {
         status: 200,