geo/server/internal/shared/config/config.go

package config

import (
	"fmt"
	"os"
	"strings"
	"time"

	"github.com/spf13/viper"
)

type Config struct {
	Server        ServerConfig        `mapstructure:"server"`
	Database      DatabaseConfig      `mapstructure:"database"`
	Redis         RedisConfig         `mapstructure:"redis"`
	Qdrant        QdrantConfig        `mapstructure:"qdrant"`
	ObjectStorage ObjectStorageConfig `mapstructure:"object_storage"`
	Cache         CacheConfig         `mapstructure:"cache"`
	JWT           JWTConfig           `mapstructure:"jwt"`
	Log           LogConfig           `mapstructure:"log"`
	LLM           LLMConfig           `mapstructure:"llm"`
	Retrieval     RetrievalConfig     `mapstructure:"retrieval"`
	Generation    GenerationConfig    `mapstructure:"generation"`
}

type ServerConfig struct {
	Port int    `mapstructure:"port"`
	Mode string `mapstructure:"mode"`
}

type DatabaseConfig struct {
	Host         string `mapstructure:"host"`
	Port         int    `mapstructure:"port"`
	User         string `mapstructure:"user"`
	Password     string `mapstructure:"password"`
	DBName       string `mapstructure:"dbname"`
	SSLMode      string `mapstructure:"sslmode"`
	MaxOpenConns int    `mapstructure:"max_open_conns"`
	MaxIdleConns int    `mapstructure:"max_idle_conns"`
}

func (d DatabaseConfig) DSN() string {
	return fmt.Sprintf("postgres://%s:%s@%s:%d/%s?sslmode=%s",
		d.User, d.Password, d.Host, d.Port, d.DBName, d.SSLMode)
}

type RedisConfig struct {
	Addr string `mapstructure:"addr"`
	DB   int    `mapstructure:"db"`
}

type QdrantConfig struct {
	URL        string        `mapstructure:"url"`
	APIKey     string        `mapstructure:"api_key"`
	Collection string        `mapstructure:"collection"`
	Timeout    time.Duration `mapstructure:"timeout"`
}

type ObjectStorageConfig struct {
	Provider      string `mapstructure:"provider"`
	Endpoint      string `mapstructure:"endpoint"`
	AccessKey     string `mapstructure:"access_key"`
	SecretKey     string `mapstructure:"secret_key"`
	Bucket        string `mapstructure:"bucket"`
	UseSSL        bool   `mapstructure:"use_ssl"`
	PublicBaseURL string `mapstructure:"public_base_url"`
	Region        string `mapstructure:"region"`
}

type JWTConfig struct {
	Secret     string        `mapstructure:"secret"`
	AccessTTL  time.Duration `mapstructure:"access_ttl"`
	RefreshTTL time.Duration `mapstructure:"refresh_ttl"`
}

type LogConfig struct {
	Level  string `mapstructure:"level"`
	Format string `mapstructure:"format"`
}

type LLMConfig struct {
	Provider          string        `mapstructure:"provider"`
	APIKey            string        `mapstructure:"api_key"`
	BaseURL           string        `mapstructure:"base_url"`
	Model             string        `mapstructure:"model"`
	KnowledgeURLModel string        `mapstructure:"knowledge_url_model"`
	Timeout           time.Duration `mapstructure:"timeout"`
	MaxOutputTokens   int64         `mapstructure:"max_output_tokens"`
	Temperature       float64       `mapstructure:"temperature"`
	TopP              float64       `mapstructure:"top_p"`
	ReasoningEffort   string        `mapstructure:"reasoning_effort"`
	WebSearchLimit    int32         `mapstructure:"web_search_limit"`
}

type RetrievalConfig struct {
	Provider           string        `mapstructure:"provider"`
	BaseURL            string        `mapstructure:"base_url"`
	APIKey             string        `mapstructure:"api_key"`
	EmbeddingModel     string        `mapstructure:"embedding_model"`
	RerankerModel      string        `mapstructure:"reranker_model"`
	Timeout            time.Duration `mapstructure:"timeout"`
	ChunkSize          int           `mapstructure:"chunk_size"`
	ChunkOverlap       int           `mapstructure:"chunk_overlap"`
	EmbeddingBatchSize int           `mapstructure:"embedding_batch_size"`
	RecallLimit        int           `mapstructure:"recall_limit"`
	RerankTopN         int           `mapstructure:"rerank_top_n"`
	MaxChunksPerDoc    int           `mapstructure:"max_chunks_per_doc"`
	OverlapTokens      int           `mapstructure:"overlap_tokens"`
}

type CacheConfig struct {
	Driver string `mapstructure:"driver"` // "redis" or "memory"
}

type GenerationConfig struct {
	QueueSize         int           `mapstructure:"queue_size"`
	WorkerConcurrency int           `mapstructure:"worker_concurrency"`
	StreamEnabled     bool          `mapstructure:"stream_enabled"`
	ArticleTimeout    time.Duration `mapstructure:"article_timeout"`
}

func Load(configPath string) (*Config, error) {
	v := viper.New()
	v.SetConfigFile(configPath)
	v.AutomaticEnv()
	v.SetEnvKeyReplacer(strings.NewReplacer(".", "_"))

	if err := v.ReadInConfig(); err != nil {
		return nil, fmt.Errorf("read config: %w", err)
	}

	// Allow local overrides
	v.SetConfigFile(strings.Replace(configPath, ".yaml", ".local.yaml", 1))
	_ = v.MergeInConfig()

	var cfg Config
	if err := v.Unmarshal(&cfg); err != nil {
		return nil, fmt.Errorf("unmarshal config: %w", err)
	}

	applyEnvOverrides(&cfg)

	return &cfg, nil
}

func applyEnvOverrides(cfg *Config) {
	if cfg == nil {
		return
	}

	if apiKey, ok := lookupNonEmptyEnv("LLM_API_KEY"); ok {
		cfg.LLM.APIKey = apiKey
	}
	if model, ok := lookupNonEmptyEnv("LLM_KNOWLEDGE_URL_MODEL"); ok {
		cfg.LLM.KnowledgeURLModel = model
	}
	if apiKey, ok := lookupNonEmptyEnv("QDRANT_API_KEY"); ok {
		cfg.Qdrant.APIKey = apiKey
	}
	if url, ok := lookupNonEmptyEnv("QDRANT_URL"); ok {
		cfg.Qdrant.URL = url
	}
	if collection, ok := lookupNonEmptyEnv("QDRANT_COLLECTION"); ok {
		cfg.Qdrant.Collection = collection
	}
	if endpoint, ok := lookupNonEmptyEnv("OBJECT_STORAGE_ENDPOINT"); ok {
		cfg.ObjectStorage.Endpoint = endpoint
	}
	if accessKey, ok := lookupNonEmptyEnv("OBJECT_STORAGE_ACCESS_KEY"); ok {
		cfg.ObjectStorage.AccessKey = accessKey
	}
	if secretKey, ok := lookupNonEmptyEnv("OBJECT_STORAGE_SECRET_KEY"); ok {
		cfg.ObjectStorage.SecretKey = secretKey
	}
	if bucket, ok := lookupNonEmptyEnv("OBJECT_STORAGE_BUCKET"); ok {
		cfg.ObjectStorage.Bucket = bucket
	}
	if provider, ok := lookupNonEmptyEnv("OBJECT_STORAGE_PROVIDER"); ok {
		cfg.ObjectStorage.Provider = provider
	}
	if publicBaseURL, ok := lookupNonEmptyEnv("OBJECT_STORAGE_PUBLIC_BASE_URL"); ok {
		cfg.ObjectStorage.PublicBaseURL = publicBaseURL
	}
	if region, ok := lookupNonEmptyEnv("OBJECT_STORAGE_REGION"); ok {
		cfg.ObjectStorage.Region = region
	}
	if useSSL, ok := lookupBoolEnv("OBJECT_STORAGE_USE_SSL"); ok {
		cfg.ObjectStorage.UseSSL = useSSL
	}
	if apiKey, ok := lookupFirstNonEmptyEnv("SILICONFLOW_API_KEY", "RETRIEVAL_API_KEY", "EMBEDDING_API_KEY", "RERANKER_API_KEY"); ok {
		cfg.Retrieval.APIKey = apiKey
	}
	if baseURL, ok := lookupFirstNonEmptyEnv("SILICONFLOW_BASE_URL", "RETRIEVAL_BASE_URL"); ok {
		cfg.Retrieval.BaseURL = baseURL
	}
	if model, ok := lookupFirstNonEmptyEnv("SILICONFLOW_EMBEDDING_MODEL", "RETRIEVAL_EMBEDDING_MODEL"); ok {
		cfg.Retrieval.EmbeddingModel = model
	}
	if model, ok := lookupFirstNonEmptyEnv("SILICONFLOW_RERANKER_MODEL", "RETRIEVAL_RERANKER_MODEL"); ok {
		cfg.Retrieval.RerankerModel = model
	}
}

func lookupFirstNonEmptyEnv(keys ...string) (string, bool) {
	for _, key := range keys {
		if value, ok := lookupNonEmptyEnv(key); ok {
			return value, true
		}
	}
	return "", false
}

func lookupNonEmptyEnv(key string) (string, bool) {
	value, ok := os.LookupEnv(key)
	if !ok {
		return "", false
	}

	value = strings.TrimSpace(value)
	if value == "" {
		return "", false
	}

	return value, true
}

func lookupBoolEnv(key string) (bool, bool) {
	value, ok := os.LookupEnv(key)
	if !ok {
		return false, false
	}

	switch strings.ToLower(strings.TrimSpace(value)) {
	case "1", "true", "yes", "on":
		return true, true
	case "0", "false", "no", "off":
		return false, true
	default:
		return false, false
	}
}