claude-code-proxy/proxy/internal/model/models.go

package model

import (
	"encoding/json"
	"time"
)

type ContextKey string

const BodyBytesKey ContextKey = "bodyBytes"

// ProxySettings holds dynamic proxy configuration (persisted in DB)
type ProxySettings struct {
	RequestHeaderRules  []HeaderRule `json:"requestHeaderRules"`
	ResponseHeaderRules []HeaderRule `json:"responseHeaderRules"`
}

// HeaderRule defines an action to take on a specific header.
// Actions: "block" (remove), "set" (override value), "replace" (find & replace in value)
type HeaderRule struct {
	Header  string `json:"header"`            // Header name (case-insensitive match)
	Action  string `json:"action"`            // "block", "set", "replace"
	Value   string `json:"value,omitempty"`   // For "set": the new value. For "replace": the replacement string.
	Find    string `json:"find,omitempty"`    // For "replace": the string to find in the header value
	Enabled bool   `json:"enabled"`           // Toggle without deleting
}

type PromptGrade struct {
	Score            int                      `json:"score"`
	MaxScore         int                      `json:"maxScore"`
	Feedback         string                   `json:"feedback"`
	ImprovedPrompt   string                   `json:"improvedPrompt"`
	Criteria         map[string]CriteriaScore `json:"criteria"`
	GradingTimestamp string                   `json:"gradingTimestamp"`
	IsProcessing     bool                     `json:"isProcessing"`
}

type CriteriaScore struct {
	Score    int    `json:"score"`
	Feedback string `json:"feedback"`
}

type RequestLog struct {
	RequestID        string              `json:"requestId"`
	Timestamp        string              `json:"timestamp"`
	Method           string              `json:"method"`
	Endpoint         string              `json:"endpoint"`
	Headers          map[string][]string `json:"headers"`
	Body             interface{}         `json:"body"`
	Model            string              `json:"model,omitempty"`
	OriginalModel    string              `json:"originalModel,omitempty"`
	RoutedModel      string              `json:"routedModel,omitempty"`
	UserAgent        string              `json:"userAgent"`
	ContentType      string              `json:"contentType"`
	PromptGrade      *PromptGrade        `json:"promptGrade,omitempty"`
	Response         *ResponseLog        `json:"response,omitempty"`
	ConversationHash string              `json:"conversationHash,omitempty"`
	MessageCount     int                 `json:"messageCount,omitempty"`
	OrganizationID   string              `json:"organizationId,omitempty"`
}

type ResponseLog struct {
	StatusCode      int                 `json:"statusCode"`
	Headers         map[string][]string `json:"headers"`
	Body            json.RawMessage     `json:"body,omitempty"`
	BodyText        string              `json:"bodyText,omitempty"`
	StreamError     string              `json:"streamError,omitempty"`
	ResponseTime    int64               `json:"responseTime"`
	StreamingChunks []string            `json:"streamingChunks,omitempty"`
	ChunkTimings    []ChunkTiming       `json:"chunkTimings,omitempty"`
	IsStreaming     bool                `json:"isStreaming"`
	CompletedAt     string              `json:"completedAt"`
	RateLimit       *RateLimitInfo      `json:"rateLimit,omitempty"`
}

// ChunkTiming records when each SSE chunk arrived during streaming
type ChunkTiming struct {
	Index     int    `json:"index"`
	Timestamp string `json:"timestamp"`
	ByteSize  int    `json:"byteSize"`
	ElapsedMs int64  `json:"elapsedMs"`
}

// RateLimitInfo captures rate limit / quota data from upstream response headers
type RateLimitInfo struct {
	// Organization
	OrganizationID string `json:"organizationId,omitempty"`

	// Legacy per-resource rate limits
	RequestsLimit     int    `json:"requestsLimit,omitempty"`
	RequestsRemaining int    `json:"requestsRemaining,omitempty"`
	RequestsReset     string `json:"requestsReset,omitempty"`
	TokensLimit       int    `json:"tokensLimit,omitempty"`
	TokensRemaining   int    `json:"tokensRemaining,omitempty"`
	TokensReset       string `json:"tokensReset,omitempty"`

	// Unified quota system (Anthropic's current model)
	UnifiedStatus             string  `json:"unifiedStatus,omitempty"`
	UnifiedUtilization5h      float64 `json:"unifiedUtilization5h,omitempty"`
	UnifiedReset5h            string  `json:"unifiedReset5h,omitempty"`
	UnifiedUtilization7d      float64 `json:"unifiedUtilization7d,omitempty"`
	UnifiedReset7d            string  `json:"unifiedReset7d,omitempty"`
	UnifiedFallbackPercentage float64 `json:"unifiedFallbackPercentage,omitempty"`
	UnifiedOverageStatus      string  `json:"unifiedOverageStatus,omitempty"`
	UnifiedRepresentativeClaim string `json:"unifiedRepresentativeClaim,omitempty"`
}

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

type ChatCompletionRequest struct {
	Model    string        `json:"model"`
	Messages []ChatMessage `json:"messages"`
	Stream   bool          `json:"stream,omitempty"`
}

type AnthropicUsage struct {
	InputTokens              int    `json:"input_tokens"`
	OutputTokens             int    `json:"output_tokens"`
	CacheCreationInputTokens int    `json:"cache_creation_input_tokens,omitempty"`
	CacheReadInputTokens     int    `json:"cache_read_input_tokens,omitempty"`
	ServiceTier              string `json:"service_tier,omitempty"`
}

type AnthropicResponse struct {
	Content      []AnthropicContentBlock `json:"content"`
	ID           string                  `json:"id"`
	Model        string                  `json:"model"`
	Role         string                  `json:"role"`
	StopReason   string                  `json:"stop_reason"`
	StopSequence *string                 `json:"stop_sequence"`
	Type         string                  `json:"type"`
	Usage        AnthropicUsage          `json:"usage"`
}

type AnthropicContentBlock struct {
	Type string `json:"type"`
	Text string `json:"text"`
}

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

func (m *AnthropicMessage) GetContentBlocks() []AnthropicContentBlock {
	switch v := m.Content.(type) {
	case string:
		return []AnthropicContentBlock{{Type: "text", Text: v}}
	case []interface{}:
		var blocks []AnthropicContentBlock
		for _, item := range v {
			if block, ok := item.(map[string]interface{}); ok {
				if typ, hasType := block["type"].(string); hasType {
					if text, hasText := block["text"].(string); hasText {
						blocks = append(blocks, AnthropicContentBlock{Type: typ, Text: text})
					}
				}
			}
		}
		return blocks
	case []AnthropicContentBlock:
		return v
	default:
		return []AnthropicContentBlock{}
	}
}

type AnthropicSystemMessage struct {
	Text         string        `json:"text"`
	Type         string        `json:"type"`
	CacheControl *CacheControl `json:"cache_control,omitempty"`
}

type CacheControl struct {
	Type string `json:"type"`
}

type Tool struct {
	Name        string      `json:"name"`
	Description string      `json:"description"`
	InputSchema InputSchema `json:"input_schema"`
}

type InputSchema struct {
	Type       interface{}            `json:"type"`
	Properties map[string]interface{} `json:"properties"`
	Required   []string               `json:"required,omitempty"`
}

type AnthropicRequest struct {
	Model       string                   `json:"model"`
	Messages    []AnthropicMessage       `json:"messages"`
	MaxTokens   int                      `json:"max_tokens"`
	Temperature *float64                 `json:"temperature,omitempty"`
	System      []AnthropicSystemMessage `json:"system,omitempty"`
	Stream      bool                     `json:"stream,omitempty"`
	Tools       []Tool                   `json:"tools,omitempty"`
	ToolChoice  interface{}              `json:"tool_choice,omitempty"`
}

type ModelsResponse struct {
	Object string      `json:"object"`
	Data   []ModelInfo `json:"data"`
}

type ModelInfo struct {
	ID      string `json:"id"`
	Object  string `json:"object"`
	Created int64  `json:"created"`
	OwnedBy string `json:"owned_by"`
}

type GradeRequest struct {
	Messages       []AnthropicMessage       `json:"messages"`
	SystemMessages []AnthropicSystemMessage `json:"systemMessages"`
	RequestID      string                   `json:"requestId,omitempty"`
}

type HealthResponse struct {
	Status    string    `json:"status"`
	Timestamp time.Time `json:"timestamp"`
}

type ErrorResponse struct {
	Error   string `json:"error"`
	Details string `json:"details,omitempty"`
}

// UsageStats represents aggregated token usage statistics
type UsageStats struct {
	TotalRequests     int                     `json:"total_requests"`
	TotalInputTokens  int64                   `json:"total_input_tokens"`
	TotalOutputTokens int64                   `json:"total_output_tokens"`
	TotalCacheTokens  int64                   `json:"total_cache_tokens"`
	RequestsByModel   map[string]ModelStats   `json:"requests_by_model"`
	StartDate         string                  `json:"start_date,omitempty"`
	EndDate           string                  `json:"end_date,omitempty"`
}

// ModelStats represents per-model usage statistics
type ModelStats struct {
	RequestCount  int   `json:"request_count"`
	InputTokens   int64 `json:"input_tokens"`
	OutputTokens  int64 `json:"output_tokens"`
	CacheTokens   int64 `json:"cache_tokens"`
}

// RequestSummary is a lightweight version of RequestLog for fast list views
type RequestSummary struct {
	RequestID        string          `json:"requestId"`
	Timestamp        string          `json:"timestamp"`
	Method           string          `json:"method"`
	Endpoint         string          `json:"endpoint"`
	Model            string          `json:"model,omitempty"`
	OriginalModel    string          `json:"originalModel,omitempty"`
	RoutedModel      string          `json:"routedModel,omitempty"`
	StatusCode       int             `json:"statusCode,omitempty"`
	ResponseTime     int64           `json:"responseTime,omitempty"`
	Usage            *AnthropicUsage `json:"usage,omitempty"`
	ConversationHash string          `json:"conversationHash,omitempty"`
	MessageCount     int             `json:"messageCount,omitempty"`
	StopReason       string          `json:"stopReason,omitempty"`
}

// Dashboard stats structures
type DashboardStats struct {
	DailyStats []DailyTokens `json:"dailyStats"`
}

type HourlyStatsResponse struct {
	HourlyStats     []HourlyTokens `json:"hourlyStats"`
	TodayTokens     int64          `json:"todayTokens"`
	TodayRequests   int            `json:"todayRequests"`
	AvgResponseTime int64          `json:"avgResponseTime"`
}

type ModelStatsResponse struct {
	ModelStats []ModelTokens `json:"modelStats"`
}

type DailyTokens struct {
	Date     string                    `json:"date"`
	Tokens   int64                     `json:"tokens"`
	Requests int                       `json:"requests"`
	Models   map[string]DailyModelStat `json:"models,omitempty"`
}

type HourlyTokens struct {
	Hour     int                       `json:"hour"`
	Label    string                    `json:"label,omitempty"`
	Tokens   int64                     `json:"tokens"`
	Requests int                       `json:"requests"`
	Models   map[string]DailyModelStat `json:"models,omitempty"`
}

// DailyModelStat represents per-model stats for dashboard aggregation
type DailyModelStat struct {
	Tokens   int64 `json:"tokens"`
	Requests int   `json:"requests"`
}

type ModelTokens struct {
	Model    string `json:"model"`
	Tokens   int64  `json:"tokens"`
	Requests int    `json:"requests"`
}

type StreamingEvent struct {
	Type         string        `json:"type"`
	Index        *int          `json:"index,omitempty"`
	Delta        *Delta        `json:"delta,omitempty"`
	ContentBlock *ContentBlock `json:"content_block,omitempty"`
}

type Delta struct {
	Type  string          `json:"type,omitempty"`
	Text  string          `json:"text,omitempty"`
	Name  string          `json:"name,omitempty"`
	Input json.RawMessage `json:"input,omitempty"`
}

type ContentBlock struct {
	Type  string          `json:"type"`
	ID    string          `json:"id,omitempty"`
	Name  string          `json:"name,omitempty"`
	Input json.RawMessage `json:"input,omitempty"`
	Text  string          `json:"text,omitempty"`
}