User: "What's our Q3 revenue?"
Model: "Based on the documents, Q3 revenue was $4.2M."
Reality: The documents never mention Q3 revenue. The model made it up.

Workspace A queries for "budget data"
Workspace B's documents somehow appear in results
Data leak detected post-incident

Recruiter lands on site → sees "Sign Up" → bounces
Client wants to try with their docs → blocked by auth flow → gives up

Engineer: "The system works pretty well."
CEO: "What does 'pretty well' mean?"
Engineer: *silence*

// lib/auth.ts

export function createGuestCookieValue(expiresAt: number): string {
  const secret = process.env.SESSION_SECRET!;

  if (secret.length < 32) {
    throw new Error('SESSION_SECRET must be >= 32 bytes');
  }

  // Format: guest:expiresAt:hmac-signature
  const payload = `guest:${expiresAt}`;

  const mac = createHmac('sha256', secret)
    .update(payload)
    .digest('base64url');

  return `${payload}:${mac}`;
}

export function parseGuestCookieValue(value: string): { 
  expiresAt: number; 
  isValid: boolean; 
} | null {
  const parts = value.split(':');
  if (parts.length !== 3) return null;

  const [prefix, expiresAtStr, providedMac] = parts;

  // 1. Validate prefix
  if (prefix !== 'guest') {
    return null;
  }

  // 2. Validate expiration (no parsing errors, not expired)
  const expiresAt = parseInt(expiresAtStr, 10);
  if (isNaN(expiresAt)) {
    return null;
  }

  if (expiresAt < Date.now()) {
    // Expired token - still valid format, but expired
    return { expiresAt, isValid: false };
  }

  // 3. Validate HMAC signature (timing-safe comparison)
  const secret = process.env.SESSION_SECRET!;
  const payload = `guest:${expiresAtStr}`;

  const expectedMac = createHmac('sha256', secret)
    .update(payload)
    .digest('base64url');

  // Use timing-safe comparison to prevent timing attacks
  // Even if signature is wrong, comparison takes same time
  const isValid = timingSafeEqual(
    Buffer.from(providedMac, 'utf-8'),
    Buffer.from(expectedMac, 'utf-8')
  );

  if (!isValid) {
    console.warn('[auth] Invalid guest cookie signature');
    return null;
  }

  return { expiresAt, isValid: true };
}

// app/api/auth/guest/route.ts

export async function POST(request: NextRequest) {
  try {
    // 1. CSRF check (same-origin only)
    const origin = request.headers.get('origin');
    const requestUrl = new URL(request.url);

    if (origin && origin !== requestUrl.origin) {
      return Response.json(
        { error: 'CSRF violation' },
        { status: 403 }
      );
    }

    // 2. Check for existing real session (don't override)
    const existingSession = await getSession(request);
    if (existingSession && !existingSession.isGuest) {
      // Already authenticated with real account
      return Response.json(
        { error: 'Already authenticated' },
        { status: 400 }
      );
    }

    // 3. Mint new guest cookie (1 hour from now)
    const expiresAt = Date.now() + 60 * 60 * 1000; // 3600 seconds
    const cookieValue = createGuestCookieValue(expiresAt);

    // 4. Return response with guest cookie
    // HttpOnly: Can't be accessed via JavaScript (XSS protection)
    // Secure: Only sent over HTTPS
    // SameSite=Strict: Only sent with same-site requests (CSRF protection)
    const response = new Response(null, {
      status: 303, // See Other - redirect after POST
      headers: {
        Location: '/search',
        'Set-Cookie': [
          `rag_guest=${cookieValue}; Path=/; HttpOnly; Secure; SameSite=Strict; Max-Age=3600`,
          // Also set a real session cookie to redirect logic
        ].join(', ')
      }
    });

    return response;
  } catch (error) {
    console.error('[auth/guest] POST failed:', error);
    return Response.json(
      { error: 'Guest mint failed' },
      { status: 500 }
    );
  }
}

export async function GET(request: NextRequest) {
  // GET endpoint for redirect-after-login flow
  // Allows ?next=/documents to redirect to a specific page

  const nextParam = new URL(request.url).searchParams.get('next');
  const allowedNextPaths = ['/search', '/documents', '/evaluations', '/architecture'];

  // Sanitize next parameter (prevent open redirects)
  const safeNextPath = nextParam && allowedNextPaths.includes(nextParam)
    ? nextParam
    : '/search';

  const expiresAt = Date.now() + 60 * 60 * 1000;
  const cookieValue = createGuestCookieValue(expiresAt);

  return new Response(null, {
    status: 303,
    headers: {
      Location: safeNextPath,
      'Set-Cookie': `rag_guest=${cookieValue}; Path=/; HttpOnly; Secure; SameSite=Strict; Max-Age=3600`
    }
  });
}

// lib/auth.ts

export async function getSession(
  request: NextRequest,
  options?: { guestToken?: string }
): Promise<SessionData | null> {
  try {
    // 1. Check for real authenticated session (from POST /auth/signin)
    const realSessionCookie = request.cookies.get('rag_session')?.value;

    if (realSessionCookie) {
      // Validate real session (hits database)
      const session = await validateRealSession(realSessionCookie);

      if (session) {
        return { ...session, isGuest: false };
      }
      // If invalid, fall through to guest check
    }

    // 2. Check for guest token
    const guestCookie = options?.guestToken || request.cookies.get('rag_guest')?.value;

    if (!guestCookie) {
      return null;
    }

    // 3. Parse and validate guest cookie (no database hit!)
    const guestParsed = parseGuestCookieValue(guestCookie);

    if (!guestParsed) {
      return null;
    }

    // 4. Fetch guest user + workspace from database
    // (We need to do ONE lookup to get user_id and workspace_id)
    const guestUser = await db.query(
      `SELECT u.id, u.email, wm.workspace_id, wm.role
       FROM users u
       JOIN workspace_members wm ON u.id = wm.user_id
       WHERE u.id = $1 AND wm.workspace_id = $2`,
      [GUEST_USER_ID, GUEST_WORKSPACE_ID]
    );

    if (!guestUser.rows.length) {
      console.warn('[auth] Guest principal or workspace not found');
      return null;
    }

    const { workspace_id, role } = guestUser.rows[0];

    return {
      userId: GUEST_USER_ID,
      email: 'guest@rag-system.local',
      workspaceId: workspace_id,
      role: role as 'guest' | 'viewer',
      isGuest: true,
      sessionId: `guest:${guestParsed.expiresAt}` // synthetic ID
    };
  } catch (error) {
    console.error('[auth] getSession error:', error);
    return null;
  }
}

export async function requireAuth(request: NextRequest): Promise<SessionData> {
  const session = await getSession(request);

  if (!session) {
    throw new Error('Not authenticated');
  }

  return session;
}

Request → [Layer 1: Retrieval] → [Layer 2: Session] → [Layer 3: Mutation] → Response
  ↓           ✓ workspace_id         ✓ role check        ✓ ownership check
  └─────────────────────────────────────────────────────────────────────────┘
             Layered defense: No single point of failure

// lib/retrieval/hybrid.ts

export async function retrieveChunksByHybrid(
  query: string,
  workspaceId: string,
  limit: number = 5
): Promise<DocumentChunk[]> {
  try {
    // 1. Vector search (pgvector)
    // Only return chunks from this workspace
    const vectorResults = await db.query(
      `SELECT 
         dc.id, dc.document_id, dc.text, dc.embedding,
         d.source, d.workspace_id,
         dc.embedding <-> $1 as distance
       FROM document_chunks dc
       JOIN documents d ON dc.document_id = d.id
       WHERE d.workspace_id = $2
       ORDER BY distance ASC
       LIMIT $3`,
      [embedding, workspaceId, limit]
    );

    // 2. Keyword search (PostgreSQL tsvector)
    // Only return chunks from this workspace
    const keywordResults = await db.query(
      `SELECT 
         dc.id, dc.document_id, dc.text,
         d.source, d.workspace_id,
         ts_rank(to_tsvector('english', dc.text), 
                 to_tsquery('english', $1)) as relevance
       FROM document_chunks dc
       JOIN documents d ON dc.document_id = d.id
       WHERE d.workspace_id = $2
       AND to_tsvector('english', dc.text) @@ to_tsquery('english', $3)
       ORDER BY relevance DESC
       LIMIT $4`,
      [query, workspaceId, query, limit]
    );

    // 3. Merge results using Reciprocal Rank Fusion (RRF)
    // RRF handles different scoring scales gracefully
    return mergeByRRF(vectorResults.rows, keywordResults.rows, limit);
  } catch (error) {
    console.error('[retrieval] hybrid search failed:', error);
    throw error;
  }
}

// RRF: score = sum(1 / (k + rank)) for each ranking
function mergeByRRF(
  vectorChunks: DocumentChunk[],
  keywordChunks: DocumentChunk[],
  limit: number
): DocumentChunk[] {
  const k = 60; // Reciprocal rank fusion parameter
  const scores = new Map<string, number>();

  // Score vector results
  vectorChunks.forEach((chunk, rank) => {
    const score = 1 / (k + rank + 1);
    scores.set(chunk.id, (scores.get(chunk.id) || 0) + score);
  });

  // Score keyword results
  keywordChunks.forEach((chunk, rank) => {
    const score = 1 / (k + rank + 1);
    scores.set(chunk.id, (scores.get(chunk.id) || 0) + score);
  });

  // Merge and sort by RRF score
  const merged = Array.from(scores.entries())
    .sort((a, b) => b[1] - a[1])
    .slice(0, limit)
    .map(([id]) => {
      return vectorChunks.find(c => c.id === id) ||
             keywordChunks.find(c => c.id === id);
    })
    .filter(Boolean) as DocumentChunk[];

  return merged;
}

// lib/require-page-auth.ts

export async function requirePageAuth(
  request: NextRequest,
  requiredWorkspaceId?: string
): Promise<SessionData> {
  const session = await getSession(request);

  if (!session) {
    // Redirect to guest mint
    const nextPath = new URL(request.url).pathname;
    return new Response(null, {
      status: 302,
      headers: {
        Location: `/api/auth/guest?next=${encodeURIComponent(nextPath)}`
      }
    });
  }

  // If a specific workspace is required, verify membership
  if (requiredWorkspaceId && session.workspaceId !== requiredWorkspaceId) {
    throw new Error('Unauthorized workspace access');
  }

  return session;
}

// app/api/search/route.ts

export async function POST(request: NextRequest) {
  try {
    const session = await requireAuth(request);
    const body = await request.json();
    const query = body.query as string;

    // 1. Verify guest can only access guest workspace
    if (session.isGuest) {
      const guestWorkspaceId = '00000000-0000-4000-8000-000000000a02';
      if (session.workspaceId !== guestWorkspaceId) {
        return Response.json(
          { error: 'Unauthorized' },
          { status: 403 }
        );
      }
    }

    // 2. Verify workspace membership exists
    const membership = await db.query(
      `SELECT role FROM workspace_members
       WHERE workspace_id = $1 AND user_id = $2`,
      [session.workspaceId, session.userId]
    );

    if (!membership.rows.length) {
      return Response.json(
        { error: 'Not a member of this workspace' },
        { status: 403 }
      );
    }

    // 3. Proceed with retrieval (which itself checks workspace_id)
    const chunks = await retrieveChunksByHybrid(
      query,
      session.workspaceId
    );

    // 4. Generate answer (only from retrieved chunks)
    const answer = await generateAnswer(chunks);

    return Response.json({ answer, chunks });
  } catch (error) {
    console.error('[search] POST failed:', error);
    return Response.json(
      { error: 'Search failed' },
      { status: 500 }
    );
  }
}

// lib/permissions.ts

export type Role = 'owner' | 'editor' | 'viewer' | 'guest';

export function assertWritable(session: SessionData): void {
  if (session.isGuest || session.role === 'viewer') {
    throw new Error('Read-only access');
  }

  if (session.role !== 'owner' && session.role !== 'editor') {
    throw new Error('Insufficient permissions');
  }
}

// app/api/documents/upload/route.ts

export async function POST(request: NextRequest) {
  try {
    const session = await requireAuth(request);

    // Permission check
    assertWritable(session);

    const formData = await request.formData();
    const file = formData.get('file') as File;

    if (!file) {
      return Response.json(
        { error: 'No file provided' },
        { status: 400 }
      );
    }

    // 2. Upload to workspace
    const document = await createDocument({
      workspaceId: session.workspaceId,
      name: file.name,
      content: await file.text()
    });

    // 3. Chunk and embed
    await ingestDocument(document.id, session.workspaceId);

    return Response.json({ document });
  } catch (error) {
    if (error instanceof Error) {
      if (error.message === 'Read-only access') {
        return Response.json(
          { error: 'Read-only access' },
          { status: 403 }
        );
      }
    }

    console.error('[documents/upload] POST failed:', error);
    return Response.json(
      { error: 'Upload failed' },
      { status: 500 }
    );
  }
}

// app/api/documents/[id]/route.ts

export async function DELETE(
  request: NextRequest,
  context: { params: { id: string } }
) {
  try {
    const session = await requireAuth(request);

    // Permission check
    assertWritable(session);

    const documentId = context.params.id;

    // 1. Verify document belongs to workspace
    const doc = await db.query(
      `SELECT workspace_id FROM documents WHERE id = $1`,
      [documentId]
    );

    if (!doc.rows.length) {
      return Response.json(
        { error: 'Document not found' },
        { status: 404 }
      );
    }

    if (doc.rows[0].workspace_id !== session.workspaceId) {
      return Response.json(
        { error: 'Unauthorized' },
        { status: 403 }
      );
    }

    // 2. Delete document and associated chunks
    await db.query('DELETE FROM document_chunks WHERE document_id = $1', [documentId]);
    await db.query('DELETE FROM documents WHERE id = $1', [documentId]);

    return Response.json({ success: true });
  } catch (error) {
    if (error instanceof Error && error.message === 'Read-only access') {
      return Response.json({ error: 'Read-only access' }, { status: 403 });
    }

    console.error('[documents/delete] DELETE failed:', error);
    return Response.json({ error: 'Delete failed' }, { status: 500 });
  }
}

// lib/__tests__/workspace-isolation.test.ts

describe('Workspace Isolation', () => {
  it('should reject cross-workspace data access via SQL injection', async () => {
    const guestSession = await mintGuestSession();
    const maliciousQuery = "'; OR '1'='1"; // Attempt to bypass workspace check

    // Even if query goes through, Layer 1 filters by workspace_id
    const results = await retrieveChunksByHybrid(
      maliciousQuery,
      guestSession.workspaceId
    );

    // Should only return guest workspace chunks
    const hasLeakedChunks = results.some(
      chunk => chunk.workspaceId !== guestSession.workspaceId
    );

    expect(hasLeakedChunks).toBe(false);
  });

  it('should reject guest mutations at application layer', async () => {
    const guestSession = await mintGuestSession();

    const response = await fetch('/api/documents/upload', {
      method: 'POST',
      headers: {
        Cookie: `rag_guest=${guestSession.cookieValue}`
      },
      body: formData
    });

    expect(response.status).toBe(403);
    expect(await response.json()).toEqual({
      error: 'Read-only access'
    });
  });

  it('should reject guest mutations at database layer', async () => {
    // Even if application layer somehow allows mutation,
    // database role checks prevent it
    const result = await db.query(
      `INSERT INTO documents (workspace_id, name)
       VALUES ($1, $2)
       RETURNING id`,
      ['other-workspace-id', 'malicious-doc']
    );

    // If guest somehow has DB connection (shouldn't happen),
    // database user permissions still block it
    expect(result.rows).toHaveLength(0);
  });
});

// lib/retrieval/hybrid.ts

interface RetrievalResult {
  chunks: DocumentChunk[];
  retrievalLatency: number;
  vectorCount: number;
  keywordCount: number;
}

export async function retrieveChunksByHybrid(
  query: string,
  workspaceId: string,
  limit: number = 5,
  alpha: number = 0.5 // Weighting between vector and keyword
): Promise<RetrievalResult> {
  const startTime = performance.now();

  try {
    // 1. Vector search
    const embedding = await getQueryEmbedding(query); // nomic-embed-text

    const vectorPromise = db.query(
      `SELECT 
         dc.id,
         dc.document_id,
         dc.text,
         d.source,
         d.workspace_id,
         1 - (dc.embedding <-> $1) as similarity_score
       FROM document_chunks dc
       JOIN documents d ON dc.document_id = d.id
       WHERE d.workspace_id = $2
       AND d.status = 'completed'
       ORDER BY dc.embedding <-> $1 ASC
       LIMIT $3`,
      [embedding, workspaceId, limit * 2] // Over-fetch for merging
    );

    // 2. Keyword search (PostgreSQL full-text search)
    const queryTerms = parseQueryTerms(query); // tokenize, stem
    const tsquery = buildTsquery(queryTerms); // build PostgreSQL tsquery

    const keywordPromise = db.query(
      `SELECT 
         dc.id,
         dc.document_id,
         dc.text,
         d.source,
         d.workspace_id,
         ts_rank(
           to_tsvector('english', dc.text),
           to_tsquery('english', $1)
         ) as keyword_score
       FROM document_chunks dc
       JOIN documents d ON dc.document_id = d.id
       WHERE d.workspace_id = $2
       AND d.status = 'completed'
       AND to_tsvector('english', dc.text) @@ to_tsquery('english', $3)
       ORDER BY keyword_score DESC
       LIMIT $4`,
      [tsquery, workspaceId, tsquery, limit * 2]
    );

    // 3. Execute in parallel
    const [vectorResults, keywordResults] = await Promise.all([
      vectorPromise,
      keywordPromise
    ]);

    // 4. Merge using RRF
    const merged = mergeByRRF(
      vectorResults.rows,
      keywordResults.rows,
      limit,
      alpha
    );

    const endTime = performance.now();

    return {
      chunks: merged,
      retrievalLatency: endTime - startTime,
      vectorCount: vectorResults.rows.length,
      keywordCount: keywordResults.rows.length
    };
  } catch (error) {
    console.error('[retrieval] hybrid search failed:', error);
    throw error;
  }
}

// RRF: Combines rankings without normalizing scores
function mergeByRRF(
  vectorChunks: DocumentChunk[],
  keywordChunks: DocumentChunk[],
  limit: number,
  alpha: number = 0.5
): DocumentChunk[] {
  const k = 60; // RRF constant (typical: 60)
  const scores = new Map<string, { score: number; chunk: DocumentChunk }>();

  // Score vector results
  // RRF prevents one modality from dominating
  vectorChunks.forEach((chunk, rank) => {
    const rrf_score = 1 / (k + rank + 1); // rank is 0-indexed
    const existing = scores.get(chunk.id);

    scores.set(chunk.id, {
      score: (existing?.score || 0) + (alpha * rrf_score),
      chunk
    });
  });

  // Score keyword results
  keywordChunks.forEach((chunk, rank) => {
    const rrf_score = 1 / (k + rank + 1);
    const existing = scores.get(chunk.id);

    scores.set(chunk.id, {
      score: (existing?.score || 0) + ((1 - alpha) * rrf_score),
      chunk
    });
  });

  // Sort by combined RRF score and return top-k
  const merged = Array.from(scores.values())
    .sort((a, b) => b.score - a.score)
    .slice(0, limit)
    .map(({ chunk }) => chunk);

  return merged;
}

function parseQueryTerms(query: string): string[] {
  // Tokenize, lowercase, remove stopwords
  return query
    .toLowerCase()
    .split(/\s+/)
    .filter(term => !STOPWORDS.has(term))
    .map(term => stem(term)); // Porter stemming
}

function buildTsquery(terms: string[]): string {
  // Build PostgreSQL tsquery: term1 & term2 & term3
  return terms.join(' & ');
}

Chunk A: vector rank #2, keyword rank #5
  → RRF score = 1/(60+2) + 1/(60+5) = 0.0154 + 0.0141 = 0.0295

Chunk B: vector rank #1, keyword rank #15
  → RRF score = 1/(60+1) + 1/(60+15) = 0.0164 + 0.0132 = 0.0296

Final ranking: Chunk B (slightly higher despite lower keyword rank)

Benchmark on 10K chunks / 3 documents:

Vector search:  ~45ms (pgvector index scan)
Keyword search: ~18ms (tsvector GiST index)
Total:          ~65ms (parallel execution)
Memory:         ~2MB (cached embeddings via pgvector)

Scaling to 100K chunks:
Vector search:  ~65ms (index still efficient)
Keyword search: ~22ms (full-text index holds up)
Total:          ~90ms

Q: How many vacation days do employees get?
A: "Employees accrue 2.5 vacation days per month [1], 
    which amounts to 30 days annually [2]."

Sources:
[1] "Vacation benefits..." (from handbook)
[2] "Employees get 40 days annually..." (model hallucinated this—not in corpus)

// lib/citation-validation.ts

interface Citation {
  index: number;
  chunkId: string;
  text: string;
  source: string;
  confidence: number; // 0-1
}

export async function validateCitationsStrict(
  answer: string,
  sourceChunks: DocumentChunk[]
): Promise<{ answer: string; citations: Citation[]; removedCount: number }> {
  const extractedCitations = extractCitationMarkers(answer);
  const validatedCitations: Citation[] = [];
  let removedCount = 0;

  // For each [N] marker in the answer
  for (const marker of extractedCitations) {
    const chunkIndex = parseInt(marker.index, 10) - 1; // 1-indexed → 0-indexed

    // 1. Bounds check: Does the chunk exist?
    if (chunkIndex < 0 || chunkIndex >= sourceChunks.length) {
      console.warn(`[citation] Out-of-bounds citation: [${marker.index}]`);
      removeMarkerFromAnswer(answer, marker);
      removedCount++;
      continue;
    }

    const chunk = sourceChunks[chunkIndex];
    const citationText = extractCitationContent(answer, marker.index);

    // 2. Substring check: Does the citation text appear in the chunk?
    const normalizedChunkText = normalizeText(chunk.text);
    const normalizedCitationText = normalizeText(citationText);

    if (!normalizedChunkText.includes(normalizedCitationText)) {
      console.warn(`[citation] Citation not found in chunk: "${citationText}"`);
      removeMarkerFromAnswer(answer, marker);
      removedCount++;
      continue;
    }

    // 3. Semantic check: Does the citation *meaning* align with the chunk?
    // Use embedding similarity to verify semantic relevance
    const citationEmbedding = await getEmbedding(citationText);
    const chunkEmbedding = chunk.embedding;

    const similarity = cosineSimilarity(citationEmbedding, chunkEmbedding);
    const confidenceThreshold = 0.65; // Adjust based on evaluation data

    if (similarity < confidenceThreshold) {
      console.warn(
        `[citation] Low semantic relevance: similarity=${similarity.toFixed(3)}`
      );
      removeMarkerFromAnswer(answer, marker);
      removedCount++;
      continue;
    }

    // Citation passed all checks
    validatedCitations.push({
      index: marker.index,
      chunkId: chunk.id,
      text: citationText,
      source: chunk.source,
      confidence: similarity
    });
  }

  return { answer, citations: validatedCitations, removedCount };
}

function extractCitationMarkers(answer: string): Array<{ index: string; position: number }> {
  const regex = /\[(\d+)\]/g;
  const matches: Array<{ index: string; position: number }> = [];

  let match;
  while ((match = regex.exec(answer)) !== null) {
    matches.push({ index: match[1], position: match.index });
  }

  return matches;
}

function extractCitationContent(answer: string, markerIndex: string): string {
  // Extract text between citation markers
  // E.g., "...content[1]...content[2]..." → extract content between [1] and [2]

  const marker = `[${markerIndex}]`;
  const nextMarker = `[${parseInt(markerIndex, 10) + 1}]`;

  const startPos = answer.indexOf(marker);
  const endPos = answer.indexOf(nextMarker, startPos);

  if (startPos === -1) return '';
  if (endPos === -1) return answer.substring(startPos + marker.length).trim();

  return answer.substring(startPos + marker.length, endPos).trim();
}

function normalizeText(text: string): string {
  return text
    .toLowerCase()
    .replace(/\s+/g, ' ')
    .replace(/[.,!?;:—–-]/g, '')
    .trim();
}

function cosineSimilarity(a: number[], b: number[]): number {
  const dotProduct = a.reduce((sum, val, i) => sum + val * b[i], 0);
  const magnitudeA = Math.sqrt(a.reduce((sum, val) => sum + val * val, 0));
  const magnitudeB = Math.sqrt(b.reduce((sum, val) => sum + val * val, 0));

  return magnitudeA === 0 || magnitudeB === 0 ? 0 : dotProduct / (magnitudeA * magnitudeB);
}

// lib/generation.ts

export async function generateAnswerWithCitations(
  query: string,
  chunks: DocumentChunk[]
): Promise<{
  answer: string;
  citations: Citation[];
  latency: number;
  model: string;
}> {
  const startTime = performance.now();

  // 1. Build context from chunks
  const context = buildContext(chunks);

  const prompt = `Answer the question based only on the provided context.
If the answer is not in the context, say "I don't know."
Include citations [1], [2], etc. for each source.

Context:
${context}

Question: ${query}

Answer:`;

  // 2. Call LLM
  const rawAnswer = await callOllama('mistral:latest', prompt, {
    temperature: 0.1, // Low temperature for more consistent citations
    stop: ['\n\nQuestion:', '\n\nContext:']
  });

  // 3. Validate citations
  const { answer, citations, removedCount } = await validateCitationsStrict(
    rawAnswer,
    chunks
  );

  if (removedCount > 0) {
    console.info(`[generation] Removed ${removedCount} hallucinated citations`);
  }

  const endTime = performance.now();

  return {
    answer,
    citations,
    latency: endTime - startTime,
    model: 'mistral:latest'
  };
}

function buildContext(chunks: DocumentChunk[]): string {
  return chunks
    .map((chunk, idx) => {
      const marker = `[${idx + 1}]`;
      const sourceNote = `(Source: ${chunk.source})`;
      return `${marker} ${chunk.text} ${sourceNote}`;
    })
    .join('\n\n');
}

Before validation:
  - Citations per answer: 2.3 (avg)
  - Hallucinated citations: 0.8 per answer
  - Precision: 65.3%

After validation:
  - Citations per answer: 1.8 (avg)
  - Hallucinated citations: 0.2 per answer (92% reduction)
  - Precision: 74.6% ✓

Engineer A: "The system works pretty well."
Engineer B: "Is it better than last month?"
Engineer A: *silence*

July:   Recall: 62%, Precision: 68%, Correctness: 75%
August: Recall: 66.7%, Precision: 74.6%, Correctness: 80%
Status: All metrics improved

// lib/evaluation.ts

interface EvaluationCase {
  id: string;
  query: string;
  expectedDocuments: string[]; // Which documents should be retrieved
  shouldHaveAnswer: boolean; // Can this be answered?
  expectedAnswerKeywords: string[]; // Key terms in correct answer
}

const evaluationCases: EvaluationCase[] = [
  {
    id: 'vacation-days',
    query: 'How many vacation days do employees accrue?',
    expectedDocuments: ['handbook'],
    shouldHaveAnswer: true,
    expectedAnswerKeywords: ['2.5', 'per month', '30 days']
  },
  {
    id: 'ceo-favorite-color',
    query: "What's the CEO's favorite color?",
    expectedDocuments: [],
    shouldHaveAnswer: false // Not in handbook
  },
  // ... 13 more cases
];

export async function runEvaluation(): Promise<EvaluationMetrics> {
  const results = {
    retrievalRecall: 0,
    retrievalPrecision: 0,
    citationPrecision: 0,
    citationRecall: 0,
    answerCorrectness: 0,
    noAnswerAccuracy: 0,
    avgLatency: 0
  };

  for (const testCase of evaluationCases) {
    console.log(`[eval] Running case: ${testCase.id}`);

    // 1. Retrieve
    const startTime = performance.now();
    const retrieved = await retrieveChunksByHybrid(
      testCase.query,
      GUEST_WORKSPACE_ID,
      5
    );
    const latency = performance.now() - startTime;
    results.avgLatency += latency;

    // 2. Score retrieval
    const retrievedDocs = new Set(
      retrieved.chunks.map(c => c.source)
    );

    const correctRetrievals = testCase.expectedDocuments.filter(doc =>
      retrievedDocs.has(doc)
    ).length;

    const recall = correctRetrievals / testCase.expectedDocuments.length;
    const precision = testCase.expectedDocuments.length > 0
      ? correctRetrievals / Math.max(1, retrievedDocs.size)
      : 1;

    results.retrievalRecall += recall;
    results.retrievalPrecision += precision;

    // 3. Generate answer
    const { answer, citations } = await generateAnswerWithCitations(
      testCase.query,
      retrieved.chunks
    );

    // 4. Score answer
    if (testCase.shouldHaveAnswer) {
      const hasAnswer = !answer.includes("don't know");

      if (hasAnswer) {
        // Check if key terms appear in answer
        const keywordsFound = testCase.expectedAnswerKeywords.filter(
          keyword => answer.toLowerCase().includes(keyword.toLowerCase())
        ).length;

        const correctness = keywordsFound / testCase.expectedAnswerKeywords.length;
        results.answerCorrectness += correctness;
      } else {
        results.answerCorrectness += 0; // Wrong: should have answered
      }
    } else {
      // Case shouldn't have an answer
      const correctlyDeclined = answer.includes("don't know");
      results.noAnswerAccuracy += correctlyDeclined ? 1 : 0;
    }

    // 5. Score citations
    const validCitations = citations.filter(c =>
      testCase.expectedDocuments.includes(c.source)
    ).length;

    const citationPrecision = citations.length > 0
      ? validCitations / citations.length
      : 1;

    results.citationPrecision += citationPrecision;
  }

  // Average
  return {
    ...results,
    retrievalRecall: results.retrievalRecall / evaluationCases.length,
    retrievalPrecision: results.retrievalPrecision / evaluationCases.length,
    citationPrecision: results.citationPrecision / evaluationCases.length,
    answerCorrectness: results.answerCorrectness / evaluationCases.length,
    noAnswerAccuracy: results.noAnswerAccuracy / evaluationCases.length,
    avgLatency: results.avgLatency / evaluationCases.length
  };
}

Metric                  | Value  | Target
─────────────────────────────────────────
Retrieval Recall        | 66.7%  | >60%  ✓
Retrieval Precision     | 61.8%  | >50%  ✓
Citation Precision      | 74.6%  | >70%  ✓
Answer Correctness      | 80%    | >75%  ✓
No-Answer Accuracy      | 100%   | >95%  ✓
Avg Latency            | 3.3s   | <5s   ✓

# 1. Start Ollama locally
ollama serve

# 2. Expose via Tailscale Funnel (secure tunnel)
tailscale funnel --bg 11434

# Output:
# Available on the internet:
# https://your-machine.ts.net/
# |-- proxy http://127.0.0.1:11434

export OLLAMA_API_URL="https://your-machine.ts.net/"

CREATE TABLE workspaces (
  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
  name VARCHAR(255) NOT NULL,
  owner_id UUID NOT NULL REFERENCES users(id),
  created_at TIMESTAMPTZ DEFAULT now()
);

CREATE TABLE documents (
  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
  workspace_id UUID NOT NULL REFERENCES workspaces(id) ON DELETE CASCADE,
  name VARCHAR(255) NOT NULL,
  content TEXT NOT NULL,
  status VARCHAR(50) DEFAULT 'pending', -- pending, processing, completed
  created_at TIMESTAMPTZ DEFAULT now()
);

CREATE TABLE document_chunks (
  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
  document_id UUID NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
  workspace_id UUID NOT NULL REFERENCES workspaces(id) ON DELETE CASCADE,
  text TEXT NOT NULL,
  embedding vector(768), -- nomic-embed-text dimension
  created_at TIMESTAMPTZ DEFAULT now(),

  -- Indexes for performance
  CONSTRAINT fk_workspace CHECK (workspace_id IN (
    SELECT workspace_id FROM documents WHERE id = document_id
  ))
);

CREATE INDEX idx_document_chunks_workspace ON document_chunks(workspace_id);
CREATE INDEX idx_document_chunks_embedding ON document_chunks USING ivfflat (embedding vector_cosine_ops);
CREATE INDEX idx_document_chunks_text_tsvector ON document_chunks USING gist (to_tsvector('english', text));

// lib/__tests__/integration.test.ts

describe('End-to-End RAG Flow', () => {
  it('should retrieve and generate answer with valid citations', async () => {
    // 1. Setup guest session
    const guest = await mintGuestSession();

    // 2. Search for question
    const searchResponse = await fetch('/api/search', {
      method: 'POST',
      headers: {
        'Cookie': `rag_guest=${guest.cookieValue}`,
        'Content-Type': 'application/json'
      },
      body: JSON.stringify({ query: 'How many vacation days?' })
    });

    expect(searchResponse.status).toBe(200);

    const { answer, citations } = await searchResponse.json();

    // 3. Verify answer has citations
    expect(citations.length).toBeGreaterThan(0);
    expect(citations.length).toBeLessThan(5);

    // 4. Verify each citation is valid
    for (const citation of citations) {
      expect(citation.text).toBeTruthy();
      expect(citation.source).toBe('handbook');
      expect(citation.confidence).toBeGreaterThan(0.6);
    }

    // 5. Verify answer doesn't have uncited text
    const citedMarkers = new Set(citations.map(c => `[${c.index}]`));
    const allMarkers = answer.match(/\[\d+\]/g) || [];

    for (const marker of allMarkers) {
      expect(citedMarkers.has(marker)).toBe(true);
    }
  });
});