Anthropic Chat

// Cache system message content (tools cached implicitly)
ChatResponse response = chatModel.call(
    new Prompt(
        List.of(
            new SystemMessage("You are a helpful AI assistant with extensive knowledge..."),
            new UserMessage("What is machine learning?")
        ),
        AnthropicChatOptions.builder()
            .model("claude-sonnet-4")
            .cacheOptions(AnthropicCacheOptions.builder()
                .strategy(AnthropicCacheStrategy.SYSTEM_ONLY)
                .build())
            .maxTokens(500)
            .build()
    )
);

// Cache tool definitions, system prompt processed fresh each time
ChatResponse response = chatModel.call(
    new Prompt(
        List.of(
            new SystemMessage("You are a " + persona + " assistant..."), // Dynamic per-tenant
            new UserMessage("What's the weather like in San Francisco?")
        ),
        AnthropicChatOptions.builder()
            .model("claude-sonnet-4")
            .cacheOptions(AnthropicCacheOptions.builder()
                .strategy(AnthropicCacheStrategy.TOOLS_ONLY)
                .build())
            .toolCallbacks(weatherToolCallback) // Large tool set cached
            .maxTokens(500)
            .build()
    )
);

// Cache both tool definitions and system message with independent breakpoints
// Changing system won't invalidate tool cache (but changing tools invalidates both)
ChatResponse response = chatModel.call(
    new Prompt(
        List.of(
            new SystemMessage("You are a weather analysis assistant..."),
            new UserMessage("What's the weather like in San Francisco?")
        ),
        AnthropicChatOptions.builder()
            .model("claude-sonnet-4")
            .cacheOptions(AnthropicCacheOptions.builder()
                .strategy(AnthropicCacheStrategy.SYSTEM_AND_TOOLS)
                .build())
            .toolCallbacks(weatherToolCallback) // 20+ tools
            .maxTokens(500)
            .build()
    )
);

// Cache conversation history with ChatClient and memory (cache breakpoint on last user message)
ChatClient chatClient = ChatClient.builder(chatModel)
    .defaultSystem("You are a personalized career counselor...")
    .defaultAdvisors(MessageChatMemoryAdvisor.builder(chatMemory)
        .conversationId(conversationId)
        .build())
    .build();

String response = chatClient.prompt()
    .user("What career advice would you give me?")
    .options(AnthropicChatOptions.builder()
        .model("claude-sonnet-4")
        .cacheOptions(AnthropicCacheOptions.builder()
            .strategy(AnthropicCacheStrategy.CONVERSATION_HISTORY)
            .build())
        .maxTokens(500)
        .build())
    .call()
    .content();

String response = ChatClient.create(chatModel)
    .prompt()
    .system("You are an expert document analyst...")
    .user("Analyze this large document: " + document)
    .options(AnthropicChatOptions.builder()
        .model("claude-sonnet-4")
        .cacheOptions(AnthropicCacheOptions.builder()
            .strategy(AnthropicCacheStrategy.SYSTEM_ONLY)
            .build())
        .build())
    .call()
    .content();

ChatResponse response = chatModel.call(
    new Prompt(
        List.of(new SystemMessage(largeSystemPrompt)),
        AnthropicChatOptions.builder()
            .model("claude-sonnet-4")
            .cacheOptions(AnthropicCacheOptions.builder()
                .strategy(AnthropicCacheStrategy.SYSTEM_ONLY)
                .messageTypeTtl(MessageType.SYSTEM, AnthropicCacheTtl.ONE_HOUR)
                .build())
            .maxTokens(500)
            .build()
    )
);

AnthropicCacheOptions cache = AnthropicCacheOptions.builder()
    .strategy(AnthropicCacheStrategy.CONVERSATION_HISTORY)
    .messageTypeMinContentLength(MessageType.SYSTEM, 1024)
    .messageTypeMinContentLength(MessageType.USER, 1024)
    .messageTypeMinContentLength(MessageType.ASSISTANT, 1024)
    .contentLengthFunction(text -> MyTokenCounter.count(text))
    .build();

ChatResponse response = chatModel.call(
    new Prompt(
        List.of(/* messages */),
        AnthropicChatOptions.builder()
            .model("claude-sonnet-4")
            .cacheOptions(cache)
            .build()
    )
);

// Load a legal contract (PDF or text)
String legalContract = loadDocument("merger-agreement.pdf"); // ~3000 tokens

// System prompt with legal expertise
String legalSystemPrompt = "You are an expert legal analyst specializing in corporate law. " +
    "Analyze the following contract and provide precise answers about terms, obligations, and risks: " +
    legalContract;

// First analysis - creates cache
ChatResponse riskAnalysis = chatModel.call(
    new Prompt(
        List.of(
            new SystemMessage(legalSystemPrompt),
            new UserMessage("What are the key termination clauses and associated penalties?")
        ),
        AnthropicChatOptions.builder()
            .model("claude-sonnet-4")
            .cacheOptions(AnthropicCacheOptions.builder()
                .strategy(AnthropicCacheStrategy.SYSTEM_ONLY)
                .build())
            .maxTokens(1000)
            .build()
    )
);

// Subsequent questions reuse cached document - 90% cost savings
ChatResponse obligationAnalysis = chatModel.call(
    new Prompt(
        List.of(
            new SystemMessage(legalSystemPrompt), // Same content - cache hit
            new UserMessage("List all financial obligations and payment schedules.")
        ),
        AnthropicChatOptions.builder()
            .model("claude-sonnet-4")
            .cacheOptions(AnthropicCacheOptions.builder()
                .strategy(AnthropicCacheStrategy.SYSTEM_ONLY)
                .build())
            .maxTokens(1000)
            .build()
    )
);

// Define comprehensive code review guidelines
String reviewGuidelines = """
    You are a senior software engineer conducting code reviews. Apply these criteria:
    - Security vulnerabilities and best practices
    - Performance optimizations and memory usage
    - Code maintainability and readability
    - Testing coverage and edge cases
    - Design patterns and architecture compliance
    """;

List<String> codeFiles = Arrays.asList(
    "UserService.java", "PaymentController.java", "SecurityConfig.java"
);

List<String> reviews = new ArrayList<>();

for (String filename : codeFiles) {
    String sourceCode = loadSourceFile(filename);

    ChatResponse review = chatModel.call(
        new Prompt(
            List.of(
                new SystemMessage(reviewGuidelines), // Cached across all reviews
                new UserMessage("Review this " + filename + " code:\n\n" + sourceCode)
            ),
            AnthropicChatOptions.builder()
                .model("claude-sonnet-4")
                .cacheOptions(AnthropicCacheOptions.builder()
                    .strategy(AnthropicCacheStrategy.SYSTEM_ONLY)
                    .build())
                .maxTokens(800)
                .build()
        )
    );

    reviews.add(review.getResult().getOutput().getText());
}

// Guidelines cached after first request, subsequent reviews are faster and cheaper

// Define large shared tool set (used by all tenants)
List<FunctionCallback> sharedTools = Arrays.asList(
    weatherToolCallback,    // ~500 tokens
    calendarToolCallback,   // ~800 tokens
    emailToolCallback,      // ~700 tokens
    analyticsToolCallback,  // ~600 tokens
    reportingToolCallback,  // ~900 tokens
    // ... 20+ more tools, totaling 5000+ tokens
);

@Service
public class MultiTenantAIService {

    public String handleTenantRequest(String tenantId, String userQuery) {
        // Get tenant-specific configuration
        TenantConfig config = tenantRepository.findById(tenantId);

        // Dynamic system prompt per tenant
        String tenantSystemPrompt = String.format("""
            You are %s's AI assistant. Company values: %s.
            Brand voice: %s. Compliance requirements: %s.
            """, config.companyName(), config.values(),
                 config.brandVoice(), config.compliance());

        ChatResponse response = chatModel.call(
            new Prompt(
                List.of(
                    new SystemMessage(tenantSystemPrompt), // Different per tenant, NOT cached
                    new UserMessage(userQuery)
                ),
                AnthropicChatOptions.builder()
                    .model("claude-sonnet-4")
                    .cacheOptions(AnthropicCacheOptions.builder()
                        .strategy(AnthropicCacheStrategy.TOOLS_ONLY) // Cache tools only
                        .build())
                    .toolCallbacks(sharedTools) // Cached once, shared across all tenants
                    .maxTokens(800)
                    .build()
            )
        );

        return response.getResult().getOutput().getText();
    }
}

// Tools cached once (5000 tokens @ 10% = 500 token cost for cache hits)
// Each tenant's unique system prompt processed fresh (200-500 tokens @ 100%)
// Total per request: ~700-1000 tokens vs 5500+ without TOOLS_ONLY

// Load comprehensive product knowledge
String knowledgeBase = """
    PRODUCT DOCUMENTATION:
    - API endpoints and authentication methods
    - Common troubleshooting procedures
    - Billing and subscription details
    - Integration guides and examples
    - Known issues and workarounds
    """ + loadProductDocs(); // ~2500 tokens

@Service
public class CustomerSupportService {

    public String handleCustomerQuery(String customerQuery, String customerId) {
        ChatResponse response = chatModel.call(
            new Prompt(
                List.of(
                    new SystemMessage("You are a helpful customer support agent. " +
                        "Use this knowledge base to provide accurate solutions: " + knowledgeBase),
                    new UserMessage("Customer " + customerId + " asks: " + customerQuery)
                ),
                AnthropicChatOptions.builder()
                    .model("claude-sonnet-4")
                    .cacheOptions(AnthropicCacheOptions.builder()
                        .strategy(AnthropicCacheStrategy.SYSTEM_ONLY)
                        .build())
                    .maxTokens(600)
                    .build()
            )
        );

        return response.getResult().getOutput().getText();
    }
}

// Knowledge base is cached across all customer queries
// Multiple support agents can benefit from the same cached content

String response = ChatClient.create(chatModel)
    .prompt()
    .user("What's the weather in San Francisco?")
    .options(AnthropicChatOptions.builder()
        .toolChoice(new AnthropicApi.ToolChoiceTool("get_weather"))
        .build())
    .call()
    .content();

CitationDocument document = CitationDocument.builder()
    .plainText("The Eiffel Tower was completed in 1889 in Paris, France. " +
               "It stands 330 meters tall and was designed by Gustave Eiffel.")
    .title("Eiffel Tower Facts")
    .citationsEnabled(true)
    .build();

// From file path
CitationDocument document = CitationDocument.builder()
    .pdfFile("path/to/document.pdf")
    .title("Technical Specification")
    .citationsEnabled(true)
    .build();

// From byte array
byte[] pdfBytes = loadPdfBytes();
CitationDocument document = CitationDocument.builder()
    .pdf(pdfBytes)
    .title("Product Manual")
    .citationsEnabled(true)
    .build();

CitationDocument document = CitationDocument.builder()
    .customContent(
        "The Great Wall of China is approximately 21,196 kilometers long.",
        "It was built over many centuries, starting in the 7th century BC.",
        "The wall was constructed to protect Chinese states from invasions."
    )
    .title("Great Wall Facts")
    .citationsEnabled(true)
    .build();

CitationDocument parisDoc = CitationDocument.builder()
    .plainText("Paris is the capital city of France with a population of 2.1 million.")
    .title("Paris Information")
    .citationsEnabled(true)
    .build();

CitationDocument eiffelDoc = CitationDocument.builder()
    .plainText("The Eiffel Tower was designed by Gustave Eiffel for the 1889 World's Fair.")
    .title("Eiffel Tower History")
    .citationsEnabled(true)
    .build();

ChatResponse response = chatModel.call(
    new Prompt(
        "What is the capital of France and who designed the Eiffel Tower?",
        AnthropicChatOptions.builder()
            .model("claude-3-7-sonnet-latest")
            .citationDocuments(parisDoc, eiffelDoc)
            .build()
    )
);

Citation citation = citations.get(0);
if (citation.getType() == Citation.LocationType.CHAR_LOCATION) {
    int start = citation.getStartCharIndex();
    int end = citation.getEndCharIndex();
    String text = citation.getCitedText();
    System.out.println("Characters " + start + "-" + end + ": " + text);
}

Citation citation = citations.get(0);
if (citation.getType() == Citation.LocationType.PAGE_LOCATION) {
    int startPage = citation.getStartPageNumber();
    int endPage = citation.getEndPageNumber();
    System.out.println("Pages " + startPage + "-" + endPage);
}

Citation citation = citations.get(0);
if (citation.getType() == Citation.LocationType.CONTENT_BLOCK_LOCATION) {
    int startBlock = citation.getStartBlockIndex();
    int endBlock = citation.getEndBlockIndex();
    System.out.println("Content blocks " + startBlock + "-" + endBlock);
}

CitationDocument contract = CitationDocument.builder()
    .pdfFile("merger-agreement.pdf")
    .title("Merger Agreement 2024")
    .citationsEnabled(true)
    .build();

ChatResponse response = chatModel.call(
    new Prompt(
        "What are the key termination clauses in this contract?",
        AnthropicChatOptions.builder()
            .model("claude-sonnet-4")
            .maxTokens(2000)
            .citationDocuments(contract)
            .build()
    )
);

// Citations will reference specific pages in the PDF

CitationDocument kbArticle1 = CitationDocument.builder()
    .plainText(loadKnowledgeBaseArticle("authentication"))
    .title("Authentication Guide")
    .citationsEnabled(true)
    .build();

CitationDocument kbArticle2 = CitationDocument.builder()
    .plainText(loadKnowledgeBaseArticle("billing"))
    .title("Billing FAQ")
    .citationsEnabled(true)
    .build();

ChatResponse response = chatModel.call(
    new Prompt(
        "How do I reset my password and update my billing information?",
        AnthropicChatOptions.builder()
            .model("claude-3-7-sonnet-latest")
            .citationDocuments(kbArticle1, kbArticle2)
            .build()
    )
);

// Citations show which KB articles were referenced

CitationDocument clinicalStudy = CitationDocument.builder()
    .pdfFile("clinical-trial-results.pdf")
    .title("Clinical Trial Phase III Results")
    .citationsEnabled(true)
    .build();

CitationDocument regulatoryGuidance = CitationDocument.builder()
    .plainText(loadRegulatoryDocument())
    .title("FDA Guidance Document")
    .citationsEnabled(true)
    .build();

ChatResponse response = chatModel.call(
    new Prompt(
        "Summarize the efficacy findings and regulatory implications.",
        AnthropicChatOptions.builder()
            .model("claude-sonnet-4")
            .maxTokens(3000)
            .citationDocuments(clinicalStudy, regulatoryGuidance)
            .build()
    )
);

// Citations provide audit trail for compliance

CitationDocument document = CitationDocument.builder()
    .plainText("...")
    .title("Legal Contract")
    .context("This is a merger agreement dated January 2024 between Company A and Company B")
    .build();

CitationDocument document = CitationDocument.builder()
    .plainText("The Eiffel Tower was completed in 1889...")
    .title("Historical Facts")
    .citationsEnabled(true)  // Explicitly enable citations for this document
    .build();

CitationDocument backgroundDoc = CitationDocument.builder()
    .plainText("Background information about the industry...")
    .title("Context Document")
    // citationsEnabled defaults to false - Claude will use this but not cite it
    .build();