feat: initial CodeBoard monorepo scaffold

Turborepo monorepo with npm workspaces:
- apps/web: Next.js 14 frontend with Tailwind v4, SSE progress, doc viewer
- apps/worker: BullMQ job processor (clone → parse → LLM generate)
- packages/shared: TypeScript types
- packages/parser: Babel-based AST parser (JS/TS) + regex (Python)
- packages/llm: OpenAI/Anthropic provider abstraction + prompt pipeline
- packages/diagrams: Mermaid architecture & dependency graph generators
- packages/database: Prisma schema (PostgreSQL)
- Docker multi-stage build (web + worker targets)

All packages compile successfully with tsc and next build.

apps/worker/src/index.ts

@@ -0,0 +1,42 @@
+import { Worker } from "bullmq";
+import IORedis from "ioredis";
+import { processGenerationJob } from "./processor.js";
+
+const redisUrl = process.env.REDIS_URL ?? "redis://localhost:6379";
+const connection = new IORedis(redisUrl, { maxRetriesPerRequest: null });
+
+const worker = new Worker(
+  "codeboard:generate",
+  async (job) => {
+    console.log(`[worker] Processing job ${job.id}: ${job.data.repoUrl}`);
+    return processGenerationJob(job);
+  },
+  {
+    connection,
+    concurrency: 2,
+    removeOnComplete: { count: 100 },
+    removeOnFail: { count: 50 },
+  }
+);
+
+worker.on("completed", (job) => {
+  console.log(`[worker] Job ${job.id} completed`);
+});
+
+worker.on("failed", (job, err) => {
+  console.error(`[worker] Job ${job?.id} failed:`, err.message);
+});
+
+worker.on("ready", () => {
+  console.log("[worker] Ready and waiting for jobs on codeboard:generate");
+});
+
+async function shutdown() {
+  console.log("[worker] Shutting down...");
+  await worker.close();
+  await connection.quit();
+  process.exit(0);
+}
+
+process.on("SIGTERM", shutdown);
+process.on("SIGINT", shutdown);

apps/worker/src/jobs/clone.ts

@@ -0,0 +1,87 @@
+import { simpleGit } from "simple-git";
+import { mkdtemp, readdir, stat } from "node:fs/promises";
+import { join } from "node:path";
+import { tmpdir } from "node:os";
+import type { CloneResult } from "@codeboard/shared";
+
+async function countFiles(dir: string): Promise<{ files: number; lines: number }> {
+  let files = 0;
+  let lines = 0;
+
+  const entries = await readdir(dir, { withFileTypes: true });
+  for (const entry of entries) {
+    if (entry.name === ".git" || entry.name === "node_modules") continue;
+    const fullPath = join(dir, entry.name);
+    if (entry.isDirectory()) {
+      const sub = await countFiles(fullPath);
+      files += sub.files;
+      lines += sub.lines;
+    } else {
+      files++;
+      const fileStat = await stat(fullPath);
+      lines += Math.ceil(fileStat.size / 40);
+    }
+  }
+
+  return { files, lines };
+}
+
+export async function cloneRepository(repoUrl: string): Promise<CloneResult> {
+  const tmpDir = await mkdtemp(join(tmpdir(), "codeboard-"));
+  const git = simpleGit();
+
+  await git.clone(repoUrl, tmpDir, ["--depth", "1", "--single-branch"]);
+
+  const localGit = simpleGit(tmpDir);
+  const log = await localGit.log({ maxCount: 1 });
+  const lastCommit = log.latest?.hash ?? "unknown";
+
+  const repoName = repoUrl
+    .replace(/\.git$/, "")
+    .split("/")
+    .slice(-1)[0] ?? "unknown";
+
+  const { files: totalFiles, lines: totalLines } = await countFiles(tmpDir);
+
+  const languageCounts: Record<string, number> = {};
+  const extMap: Record<string, string> = {
+    ".ts": "TypeScript", ".tsx": "TypeScript",
+    ".js": "JavaScript", ".jsx": "JavaScript",
+    ".py": "Python", ".go": "Go",
+    ".rs": "Rust", ".java": "Java",
+    ".rb": "Ruby", ".php": "PHP",
+  };
+
+  async function scanLanguages(dir: string) {
+    const entries = await readdir(dir, { withFileTypes: true });
+    for (const entry of entries) {
+      if (entry.name.startsWith(".") || entry.name === "node_modules") continue;
+      const fullPath = join(dir, entry.name);
+      if (entry.isDirectory()) {
+        await scanLanguages(fullPath);
+      } else {
+        const ext = entry.name.slice(entry.name.lastIndexOf("."));
+        const lang = extMap[ext];
+        if (lang) {
+          const fileStat = await stat(fullPath);
+          languageCounts[lang] = (languageCounts[lang] ?? 0) + fileStat.size;
+        }
+      }
+    }
+  }
+  await scanLanguages(tmpDir);
+
+  return {
+    localPath: tmpDir,
+    metadata: {
+      name: repoName,
+      description: "",
+      defaultBranch: "main",
+      languages: languageCounts,
+      stars: 0,
+      lastCommit,
+      totalFiles,
+      totalLines,
+    },
+  };
+}

apps/worker/src/jobs/generate.ts

@@ -0,0 +1,26 @@
+import type { CodeStructure, GeneratedDocs } from "@codeboard/shared";
+import { createProvider, generateDocumentation } from "@codeboard/llm";
+
+export async function generateDocs(
+  codeStructure: CodeStructure,
+  onProgress?: (stage: string, progress: number) => void
+): Promise<GeneratedDocs> {
+  const apiKey =
+    process.env.OPENAI_API_KEY ?? process.env.ANTHROPIC_API_KEY ?? "";
+
+  if (!apiKey) {
+    throw new Error(
+      "No LLM API key configured. Set OPENAI_API_KEY or ANTHROPIC_API_KEY."
+    );
+  }
+
+  const providerType = process.env.OPENAI_API_KEY ? "openai" : "anthropic";
+  const provider = createProvider({
+    provider: providerType,
+    apiKey,
+    model: process.env.LLM_MODEL,
+    baseUrl: process.env.LLM_BASE_URL,
+  });
+
+  return generateDocumentation(codeStructure, provider, onProgress);
+}

apps/worker/src/jobs/parse.ts

@@ -0,0 +1,8 @@
+import type { CodeStructure } from "@codeboard/shared";
+import { analyzeRepository } from "@codeboard/parser";
+
+export async function parseRepository(
+  localPath: string
+): Promise<CodeStructure> {
+  return analyzeRepository(localPath);
+}

apps/worker/src/processor.ts

@@ -0,0 +1,83 @@
+import type { Job } from "bullmq";
+import IORedis from "ioredis";
+import { cloneRepository } from "./jobs/clone.js";
+import { parseRepository } from "./jobs/parse.js";
+import { generateDocs } from "./jobs/generate.js";
+
+interface GenerateJobData {
+  repoUrl: string;
+  generationId: string;
+}
+
+const redis = new IORedis(process.env.REDIS_URL ?? "redis://localhost:6379");
+
+async function updateProgress(
+  generationId: string,
+  status: string,
+  progress: number,
+  message?: string
+) {
+  await redis.publish(
+    `codeboard:progress:${generationId}`,
+    JSON.stringify({ status, progress, message })
+  );
+  await redis.set(
+    `codeboard:status:${generationId}`,
+    JSON.stringify({ status, progress, message }),
+    "EX",
+    3600
+  );
+}
+
+export async function processGenerationJob(
+  job: Job<GenerateJobData>
+): Promise<unknown> {
+  const { repoUrl, generationId } = job.data;
+  const startTime = Date.now();
+
+  try {
+    await updateProgress(generationId, "CLONING", 10, "Cloning repository...");
+    const cloneResult = await cloneRepository(repoUrl);
+
+    await updateProgress(
+      generationId,
+      "PARSING",
+      30,
+      `Analyzing ${cloneResult.metadata.totalFiles} files...`
+    );
+    const codeStructure = await parseRepository(cloneResult.localPath);
+
+    await updateProgress(
+      generationId,
+      "GENERATING",
+      50,
+      `Generating docs for ${codeStructure.modules.length} modules...`
+    );
+
+    const docs = await generateDocs(codeStructure, (stage, progress) => {
+      const mappedProgress = 50 + Math.floor(progress * 0.4);
+      updateProgress(generationId, "GENERATING", mappedProgress, `${stage}...`);
+    });
+
+    docs.id = generationId;
+    docs.repoUrl = repoUrl;
+    docs.repoName = cloneResult.metadata.name;
+
+    const duration = Math.floor((Date.now() - startTime) / 1000);
+
+    await redis.set(
+      `codeboard:result:${generationId}`,
+      JSON.stringify(docs),
+      "EX",
+      86400
+    );
+
+    await updateProgress(generationId, "COMPLETED", 100, "Done!");
+
+    return { generationId, duration, repoName: cloneResult.metadata.name };
+  } catch (err) {
+    const message = err instanceof Error ? err.message : "Unknown error";
+    await updateProgress(generationId, "FAILED", 0, message);
+    throw err;
+  }
+}