golangLAKEHOUSE/internal/shared/config.go

// Package shared also provides the TOML config loader. Per ADR
// equivalent of Rust ADR-006 (TOML config over env vars), every
// service reads `lakehouse.toml` with sane defaults and env
// overrides. Config is hot-reload-unaware in G0; reload-on-SIGHUP
// is a G1+ concern.
package shared

import (
	"errors"
	"fmt"
	"io/fs"
	"log/slog"
	"os"

	"github.com/pelletier/go-toml/v2"
)

// Config is the unified Lakehouse config. Each service reads only
// the section it cares about, but they all share the same file so
// operators have one place to look.
type Config struct {
	Gateway  GatewayConfig `toml:"gateway"`
	Storaged ServiceConfig `toml:"storaged"`
	Catalogd CatalogConfig `toml:"catalogd"`
	Ingestd  IngestConfig  `toml:"ingestd"`
	Queryd   QuerydConfig  `toml:"queryd"`
	S3       S3Config      `toml:"s3"`
	Log      LogConfig     `toml:"log"`
}

// IngestConfig adds ingestd-specific knobs. ingestd needs to PUT
// parquet to storaged AND register manifests with catalogd, so it
// holds two upstream URLs in addition to its own bind.
type IngestConfig struct {
	Bind        string `toml:"bind"`
	StoragedURL string `toml:"storaged_url"`
	CatalogdURL string `toml:"catalogd_url"`
}

// GatewayConfig adds the upstream URLs the reverse proxy fronts.
// Each route family (/v1/storage, /v1/catalog, /v1/ingest, /v1/sql)
// has its own upstream so we can scale services independently or
// move them to different boxes without touching gateway code.
type GatewayConfig struct {
	Bind        string `toml:"bind"`
	StoragedURL string `toml:"storaged_url"`
	CatalogdURL string `toml:"catalogd_url"`
	IngestdURL  string `toml:"ingestd_url"`
	QuerydURL   string `toml:"queryd_url"`
}

// QuerydConfig adds queryd-specific knobs. queryd talks DuckDB
// directly to MinIO via DuckDB's httpfs extension (so no storaged
// URL needed), and reads the catalog over HTTP for view registration.
// SecretsPath defaults to /etc/lakehouse/secrets-go.toml — the same
// file storaged uses, since both services need the S3 credentials.
type QuerydConfig struct {
	Bind         string `toml:"bind"`
	CatalogdURL  string `toml:"catalogd_url"`
	SecretsPath  string `toml:"secrets_path"`
	RefreshEvery string `toml:"refresh_every"` // duration string, e.g. "30s"
}

// CatalogConfig adds catalogd-specific knobs on top of the standard
// bind. StoragedURL points at the storaged service for manifest
// persistence; G0 defaults to the localhost bind.
type CatalogConfig struct {
	Bind        string `toml:"bind"`
	StoragedURL string `toml:"storaged_url"`
}

// ServiceConfig is the per-binary bind config. Default Bind ""
// means "use the service's hardcoded G0 default" — see DefaultConfig.
type ServiceConfig struct {
	Bind string `toml:"bind"`
}

// S3Config holds S3-compatible storage settings. Endpoint blank →
// AWS default. Bucket "" → "lakehouse-primary".
type S3Config struct {
	Endpoint        string `toml:"endpoint"`
	Region          string `toml:"region"`
	Bucket          string `toml:"bucket"`
	AccessKeyID     string `toml:"access_key_id"`
	SecretAccessKey string `toml:"secret_access_key"`
	UsePathStyle    bool   `toml:"use_path_style"`
}

// LogConfig — slog level for now; structured fields land G1+.
type LogConfig struct {
	Level string `toml:"level"`
}

// DefaultConfig returns the G0 dev defaults. Ports are shifted to
// 3110+ to coexist with the live Rust lakehouse on 3100/3201-3204
// during the migration. G5 cutover flips gateway back to 3100.
func DefaultConfig() Config {
	return Config{
		Gateway: GatewayConfig{
			Bind:        "127.0.0.1:3110",
			StoragedURL: "http://127.0.0.1:3211",
			CatalogdURL: "http://127.0.0.1:3212",
			IngestdURL:  "http://127.0.0.1:3213",
			QuerydURL:   "http://127.0.0.1:3214",
		},
		Storaged: ServiceConfig{Bind: "127.0.0.1:3211"},
		Catalogd: CatalogConfig{Bind: "127.0.0.1:3212", StoragedURL: "http://127.0.0.1:3211"},
		Ingestd: IngestConfig{
			Bind:        "127.0.0.1:3213",
			StoragedURL: "http://127.0.0.1:3211",
			CatalogdURL: "http://127.0.0.1:3212",
		},
		Queryd: QuerydConfig{
			Bind:         "127.0.0.1:3214",
			CatalogdURL:  "http://127.0.0.1:3212",
			SecretsPath:  "/etc/lakehouse/secrets-go.toml",
			RefreshEvery: "30s",
		},
		S3: S3Config{
			Endpoint:     "http://localhost:9000",
			Region:       "us-east-1",
			Bucket:       "lakehouse-primary",
			UsePathStyle: true,
		},
		Log: LogConfig{Level: "info"},
	}
}

// LoadConfig reads `lakehouse.toml` from path; if path is empty or
// the file doesn't exist, returns DefaultConfig. Any decode error is
// fatal (we don't want a misconfigured service silently falling back
// to defaults — that's the kind of bug you find at 2am).
//
// Per Opus + Qwen WARN #3: when path WAS given but the file is
// missing, log a warning so silent default-fallback doesn't hide
// misconfiguration. Empty path is fine (caller didn't ask for a
// file); non-empty + missing is suspicious.
func LoadConfig(path string) (Config, error) {
	cfg := DefaultConfig()
	if path == "" {
		return cfg, nil
	}
	b, err := os.ReadFile(path)
	if errors.Is(err, fs.ErrNotExist) {
		slog.Warn("config file not found, using defaults",
			"path", path,
			"hint", "create the file or pass -config /path/to/lakehouse.toml")
		return cfg, nil
	}
	if err != nil {
		return cfg, fmt.Errorf("read config: %w", err)
	}
	if err := toml.Unmarshal(b, &cfg); err != nil {
		return cfg, fmt.Errorf("parse config: %w", err)
	}
	return cfg, nil
}