review-bot/llm/client.go

// Package llm provides clients for LLM chat completion APIs.
//
// Supports OpenAI-compatible (default), Anthropic Messages API, and SAP AI Core providers.
package llm

import (
	"bytes"
	"context"
	"encoding/json"
	"fmt"
	"io"
	"net/http"
	"strings"
	"time"
)

// Provider identifies which API format to use.
type Provider string

const (
	// ProviderOpenAI uses the OpenAI-compatible chat/completions endpoint.
	ProviderOpenAI Provider = "openai"
	// ProviderAnthropic uses the Anthropic Messages API endpoint.
	ProviderAnthropic Provider = "anthropic"
	// ProviderAICore uses SAP AI Core with OAuth authentication.
	ProviderAICore Provider = "aicore"
)

// Client calls an LLM chat completion API.
// A Client is safe for concurrent use by multiple goroutines after construction.
// WithTimeout, WithTemperature, and WithProvider must be called during setup,
// before concurrent use.
type Client struct {
	baseURL     string
	apiKey      string
	model       string
	temperature float64
	provider    Provider
	http        *http.Client
	aicore      *AICoreClient // Only set when provider is aicore
}

// NewClient creates a new LLM client. Default provider is OpenAI-compatible.
func NewClient(baseURL, apiKey, model string) *Client {
	return &Client{
		baseURL:  strings.TrimRight(baseURL, "/"),
		apiKey:   apiKey,
		model:    model,
		provider: ProviderOpenAI,
		http:     &http.Client{Timeout: 5 * time.Minute},
	}
}

// WithTimeout sets the HTTP request timeout for LLM calls (default 5 minutes).
// When using AI Core, this also sets the timeout on the AI Core client.
func (c *Client) WithTimeout(d time.Duration) *Client {
	c.http.Timeout = d
	if c.aicore != nil {
		c.aicore.WithTimeout(d)
	}
	return c
}

// WithTemperature sets the temperature for LLM requests (0 = omit, uses server default).
func (c *Client) WithTemperature(t float64) *Client {
	c.temperature = t
	return c
}

// WithProvider sets the API provider format (openai, anthropic, or aicore).
func (c *Client) WithProvider(p Provider) *Client {
	c.provider = p
	return c
}

// WithAICore configures the client to use SAP AI Core for authentication.
// This sets the provider to aicore automatically.
// The AI Core client inherits the current HTTP timeout from this client.
func (c *Client) WithAICore(cfg AICoreConfig) *Client {
	c.provider = ProviderAICore
	c.aicore = NewAICoreClient(cfg).WithTimeout(c.http.Timeout)
	return c
}

// Message represents a chat message.
type Message struct {
	Role    string `json:"role"`
	Content string `json:"content"`
}

// Complete sends a chat completion request and returns the assistant's response content.
// The first message with role "system" is treated as the system prompt.
func (c *Client) Complete(ctx context.Context, messages []Message) (string, error) {
	var result string
	var err error

	for attempt := 0; attempt < 2; attempt++ {
		switch c.provider {
		case ProviderAnthropic:
			result, err = c.completeAnthropic(ctx, messages)
		case ProviderAICore:
			result, err = c.completeAICore(ctx, messages)
		default:
			result, err = c.completeOpenAI(ctx, messages)
		}

		if err == nil {
			return result, nil
		}

		// Only retry on response body read errors (transient network issues).
		// Do not retry on context cancellation, status errors, or parse errors
		// that indicate a structural API problem.
		if !isRetryableError(err) {
			return "", err
		}

		if attempt == 0 && ctx.Err() == nil {
			// Brief pause before retry to allow transient issues to resolve.
			time.Sleep(500 * time.Millisecond)
		}
	}

	return "", err
}

// completeAICore routes to AI Core using the appropriate endpoint based on model type.
func (c *Client) completeAICore(ctx context.Context, messages []Message) (string, error) {
	if c.aicore == nil {
		return "", fmt.Errorf("AI Core client not configured")
	}

	if IsAnthropicModel(c.model) {
		return c.aicore.CompleteAnthropic(ctx, c.model, messages, 8192, c.temperature)
	}
	return c.aicore.CompleteOpenAI(ctx, c.model, messages, c.temperature)
}

// isRetryableError returns true for transient errors worth retrying.
func isRetryableError(err error) bool {
	if err == nil {
		return false
	}
	s := err.Error()
	// Body read failures (connection reset, truncation)
	if strings.Contains(s, "read response") {
		return true
	}
	// Unexpected body length (our content-length validation)
	if strings.Contains(s, "body length mismatch") {
		return true
	}
	return false
}

// --- OpenAI-compatible implementation ---

// ChatRequest is the OpenAI request payload.
type ChatRequest struct {
	Model       string    `json:"model"`
	Messages    []Message `json:"messages"`
	Temperature float64   `json:"temperature,omitempty"`
}

// ChatResponse is the OpenAI response.
type ChatResponse struct {
	Choices []struct {
		Message struct {
			Content string `json:"content"`
		} `json:"message"`
	} `json:"choices"`
}

func (c *Client) completeOpenAI(ctx context.Context, messages []Message) (string, error) {
	reqBody := ChatRequest{
		Model:       c.model,
		Temperature: c.temperature,
		Messages:    messages,
	}

	data, err := json.Marshal(reqBody)
	if err != nil {
		return "", fmt.Errorf("marshal request: %w", err)
	}

	url := c.baseURL + "/chat/completions"
	req, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(data))
	if err != nil {
		return "", fmt.Errorf("create request: %w", err)
	}
	req.Header.Set("Authorization", "Bearer "+c.apiKey)
	req.Header.Set("Content-Type", "application/json")

	return c.doRequest(req, func(body []byte) (string, error) {
		var resp ChatResponse
		if err := json.Unmarshal(body, &resp); err != nil {
			return "", fmt.Errorf("parse response: %w", err)
		}
		if len(resp.Choices) == 0 {
			return "", fmt.Errorf("no choices in LLM response")
		}
		return resp.Choices[0].Message.Content, nil
	})
}

// --- Anthropic Messages API implementation ---

type anthropicRequest struct {
	AnthropicVersion string         `json:"anthropic_version,omitempty"`
	Model       string         `json:"model,omitempty"`
	MaxTokens   int            `json:"max_tokens"`
	System      string         `json:"system,omitempty"`
	Messages    []anthropicMsg `json:"messages"`
	Temperature float64        `json:"temperature,omitempty"`
}

type anthropicMsg struct {
	Role    string `json:"role"`
	Content string `json:"content"`
}

type anthropicResponse struct {
	Content []struct {
		Type string `json:"type"`
		Text string `json:"text"`
	} `json:"content"`
}

func (c *Client) completeAnthropic(ctx context.Context, messages []Message) (string, error) {
	// Extract system message (first message with role "system")
	var system string
	var userMessages []anthropicMsg
	for _, m := range messages {
		if m.Role == "system" {
			system = m.Content
		} else {
			userMessages = append(userMessages, anthropicMsg{
				Role:    m.Role,
				Content: m.Content,
			})
		}
	}

	reqBody := anthropicRequest{
		Model:     c.model,
		MaxTokens: 8192,
		System:    system,
		Messages:  userMessages,
	}
	if c.temperature > 0 {
		reqBody.Temperature = c.temperature
	}

	data, err := json.Marshal(reqBody)
	if err != nil {
		return "", fmt.Errorf("marshal request: %w", err)
	}

	url := c.baseURL + "/messages"
	req, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(data))
	if err != nil {
		return "", fmt.Errorf("create request: %w", err)
	}
	req.Header.Set("x-api-key", c.apiKey)
	req.Header.Set("anthropic-version", "2023-06-01")
	req.Header.Set("Content-Type", "application/json")

	return c.doRequest(req, func(body []byte) (string, error) {
		var resp anthropicResponse
		if err := json.Unmarshal(body, &resp); err != nil {
			return "", fmt.Errorf("parse response: %w", err)
		}
		if len(resp.Content) == 0 {
			return "", fmt.Errorf("no content in Anthropic response")
		}
		// Concatenate all text blocks
		var sb strings.Builder
		for _, block := range resp.Content {
			if block.Type == "text" {
				sb.WriteString(block.Text)
			}
		}
		result := sb.String()
		if result == "" {
			return "", fmt.Errorf("no text content in Anthropic response")
		}
		return result, nil
	})
}

// --- Shared HTTP execution ---

func (c *Client) doRequest(req *http.Request, parse func([]byte) (string, error)) (string, error) {
	resp, err := c.http.Do(req)
	if err != nil {
		return "", fmt.Errorf("LLM request: %w", err)
	}
	defer resp.Body.Close()

	body, err := io.ReadAll(resp.Body)
	if err != nil {
		return "", fmt.Errorf("read response: %w", err)
	}

	// Validate body length against Content-Length header when present.
	// A mismatch indicates the response was truncated in transit.
	if cl := resp.ContentLength; cl > 0 && int64(len(body)) < cl {
		return "", fmt.Errorf("body length mismatch: Content-Length=%d, received=%d", cl, len(body))
	}

	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
		return "", fmt.Errorf("LLM API error (status %d): %s", resp.StatusCode, string(body))
	}

	return parse(body)
}