feat: implement automatic repository discovery and sync

Author: TarunyaProgrammer

backend/src/modules/sync/discovery.service.ts

@@ -0,0 +1,92 @@
+import { Injectable, Logger, OnApplicationBootstrap } from '@nestjs/common';
+import { GitHubService } from '../github';
+import { PrismaService } from '../../prisma';
+import { SyncService } from './sync.service';
+import { ConfigService } from '@nestjs/config';
+
+@Injectable()
+export class DiscoveryService implements OnApplicationBootstrap {
+  private readonly logger = new Logger(DiscoveryService.name);
+  private readonly org: string;
+
+  constructor(
+    private readonly github: GitHubService,
+    private readonly prisma: PrismaService,
+    private readonly sync: SyncService,
+    private readonly config: ConfigService,
+  ) {
+    this.org = this.config.get<string>('GITHUB_ORG', 'c2siorg');
+  }
+
+  onApplicationBootstrap() {
+    this.logger.log(
+      'Application started — triggering initial repository discovery...',
+    );
+    // Run discovery in background so it doesn't block startup
+    void this.discoverAndEnqueue();
+  }
+
+  /**
+   * Fetch all repositories from the org and ensure they exist in the database.
+   * Then enqueue sync jobs for them.
+   */
+  async discoverAndEnqueue(): Promise<void> {
+    try {
+      this.logger.log(`Starting repository discovery for org: "${this.org}"`);
+      
+      const remoteRepos = await this.github.listOrgRepos();
+      this.logger.log(
+        `Found ${remoteRepos.length} public repositories in "${this.org}"`,
+      );
+
+      let newCount = 0;
+      let updatedCount = 0;
+
+      for (const repo of remoteRepos) {
+        // We use the GitHub database ID as our primary key (BigInt)
+        const dbRepo = await this.prisma.repository.upsert({
+          where: { id: BigInt(repo.id) },
+          create: {
+            id: BigInt(repo.id),
+            name: repo.name,
+            fullName: repo.full_name,
+            htmlUrl: `https://github.com/${repo.full_name}`,
+            starsCount: 0, // Will be updated by full sync
+            forksCount: 0,
+            openIssuesCount: 0,
+            isActive: true,
+            syncedAt: new Date(0), // Mark as never fully synced
+            githubCreatedAt: new Date(), // Placeholder, updated by full sync
+            defaultBranch: 'main',
+          },
+          update: {
+            isActive: true, // Ensure it stays active if it exists
+          },
+        });
+
+        // If it's never been synced or was synced very long ago, enqueue it
+        const neverSynced = dbRepo.syncedAt.getTime() === 0;
+        
+        if (neverSynced) {
+          await this.sync.enqueueRepoSync(
+            repo.full_name,
+            'discovery-initial',
+            5,
+          );
+          newCount++;
+        } else {
+          updatedCount++;
+        }
+      }
+
+      this.logger.log(
+        `Discovery complete: ${newCount} new repos enqueued, ${updatedCount} existing repos verified.`,
+      );
+    } catch (err) {
+      this.logger.error(
+        `Repository discovery failed: ${(err as Error).message}`,
+        (err as Error).stack,
+      );
+    }
+  }
+}

backend/src/modules/sync/sync.module.ts

@@ -7,6 +7,7 @@ import { SyncService, SYNC_QUEUE_NAME } from './sync.service';
 import { SyncProcessor } from './sync.processor';
 import { ProcessingService } from './processing.service';
 import { SyncScheduler } from './sync.scheduler';
+import { DiscoveryService } from './discovery.service';
 
 @Module({
   imports: [
@@ -21,7 +22,13 @@ import { SyncScheduler } from './sync.scheduler';
     GitHubModule,
     AnalyzerModule,
   ],
-  providers: [SyncService, SyncProcessor, ProcessingService, SyncScheduler],
-  exports: [SyncService],
+  providers: [
+    SyncService,
+    SyncProcessor,
+    ProcessingService,
+    SyncScheduler,
+    DiscoveryService,
+  ],
+  exports: [SyncService, DiscoveryService],
 })
 export class SyncModule {}

backend/src/modules/sync/sync.scheduler.ts

@@ -2,6 +2,7 @@ import { Injectable, Logger } from '@nestjs/common';
 import { Cron } from '@nestjs/schedule';
 import { SyncService } from './sync.service';
 import { GitHubService } from '../github';
+import { DiscoveryService } from './discovery.service';
 
 @Injectable()
 export class SyncScheduler {
@@ -10,8 +11,18 @@ export class SyncScheduler {
   constructor(
     private readonly syncService: SyncService,
     private readonly githubService: GitHubService,
+    private readonly discoveryService: DiscoveryService,
   ) {}
 
+  /**
+   * Every 12 hours: Discover new repositories in the organization.
+   */
+  @Cron('0 */12 * * *')
+  async discoverRepos(): Promise<void> {
+    this.logger.log('Starting scheduled repository discovery');
+    await this.discoveryService.discoverAndEnqueue();
+  }
+
   /**
    * Every 6 hours: sync repos whose syncedAt is older than 6 hours.
    */