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"`
	Vectord  VectordConfig `toml:"vectord"`
	Embedd   EmbeddConfig  `toml:"embedd"`
	Pathwayd  PathwaydConfig  `toml:"pathwayd"`
	Matrixd   MatrixdConfig   `toml:"matrixd"`
	Observerd ObserverdConfig `toml:"observerd"`
	Chatd     ChatdConfig     `toml:"chatd"`
	S3        S3Config        `toml:"s3"`
	Models    ModelsConfig    `toml:"models"`
	Log      LogConfig     `toml:"log"`
	Auth     AuthConfig    `toml:"auth"`
}

// 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.
//
// MaxIngestBytes caps the multipart body size. CSVs are typically
// 4-6× larger than the resulting Snappy-compressed Parquet, so 256
// MiB CSV → ~50 MiB Parquet — well under storaged's 256 MiB PUT
// cap. Real-scale validation (2026-04-29) showed 500K workers ×
// 18 cols = 344 MiB CSV → 71 MiB Parquet; bumping this knob to
// 512 MiB is the documented path for that workload.
type IngestConfig struct {
	Bind           string `toml:"bind"`
	StoragedURL    string `toml:"storaged_url"`
	CatalogdURL    string `toml:"catalogd_url"`
	MaxIngestBytes int64  `toml:"max_ingest_bytes"`
}

// GatewayConfig adds the upstream URLs the reverse proxy fronts.
// Each route family (/v1/storage, /v1/catalog, /v1/ingest, /v1/sql,
// /v1/vectors, /v1/embed, /v1/pathway, /v1/matrix, /v1/observer)
// 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"`
	VectordURL   string `toml:"vectord_url"`
	EmbeddURL    string `toml:"embedd_url"`
	PathwaydURL  string `toml:"pathwayd_url"`
	MatrixdURL   string `toml:"matrixd_url"`
	ObserverdURL string `toml:"observerd_url"`
	ChatdURL     string `toml:"chatd_url"`
}

// EmbeddConfig drives the embed service. ProviderURL points at the
// embedding backend (Ollama in G2, possibly OpenAI/Voyage in G3+).
// DefaultModel is what gets used when callers don't specify a
// model in their request body. CacheSize is the LRU cache cap on
// (model, sha256(text)) → vector lookups; 0 disables caching.
// Default 10000 entries ≈ 30 MiB at d=768.
type EmbeddConfig struct {
	Bind         string `toml:"bind"`
	ProviderURL  string `toml:"provider_url"`
	DefaultModel string `toml:"default_model"`
	CacheSize    int    `toml:"cache_size"`
}

// VectordConfig adds vectord-specific knobs. StoragedURL is
// optional — empty string disables persistence, useful for ephemeral
// dev or test runs. When set, indexes Save after every state change
// and Load on startup.
type VectordConfig struct {
	Bind        string `toml:"bind"`
	StoragedURL string `toml:"storaged_url"`
}

// PathwaydConfig drives the pathway-memory service (cmd/pathwayd).
// PersistPath: file path to the JSONL log; empty = in-memory only
// (test/dev). Production sets a stable path under /var/lib/lakehouse
// or similar so traces survive restart.
type PathwaydConfig struct {
	Bind        string `toml:"bind"`
	PersistPath string `toml:"persist_path"`
}

// MatrixdConfig drives the matrix-indexer service (cmd/matrixd).
// Per docs/SPEC.md §3.4: multi-corpus retrieve+merge over vectord
// with embed-via-embedd for query text. Both upstream URLs are
// required — matrixd has no in-process fallback.
type MatrixdConfig struct {
	Bind       string `toml:"bind"`
	EmbeddURL  string `toml:"embedd_url"`
	VectordURL string `toml:"vectord_url"`
}

// ChatdConfig drives the chat dispatcher service (cmd/chatd) — Phase 4.
// Routes /v1/chat to the right provider based on model-name prefix
// or :cloud suffix. Per-provider API keys come from env vars (or
// /etc/lakehouse/<provider>.env files); empty keys leave the provider
// unregistered so requests for that provider 404 cleanly.
//
// OllamaURL is the local Ollama upstream (no auth). Empty disables
// the local Ollama provider — useful in deployments that don't run
// Ollama on the box (cloud-only operation).
type ChatdConfig struct {
	Bind                string `toml:"bind"`
	OllamaURL           string `toml:"ollama_url"`
	// API-key env var names. Default to the conventional names.
	// Operators can rename these for environments using different env
	// var conventions, but the defaults match /etc/lakehouse/*.env
	// files that systemd already loads.
	OllamaCloudKeyEnv   string `toml:"ollama_cloud_key_env"`
	OpenRouterKeyEnv    string `toml:"openrouter_key_env"`
	OpenCodeKeyEnv      string `toml:"opencode_key_env"`
	KimiKeyEnv          string `toml:"kimi_key_env"`
	// Optional .env file paths — a fallback when the env var isn't set
	// in the process environment. Same keys, "KEY=value" lines.
	OllamaCloudKeyFile  string `toml:"ollama_cloud_key_file"`
	OpenRouterKeyFile   string `toml:"openrouter_key_file"`
	OpenCodeKeyFile     string `toml:"opencode_key_file"`
	KimiKeyFile         string `toml:"kimi_key_file"`
	// Per-call timeout in seconds. 0 = 180s default.
	TimeoutSecs int `toml:"timeout_secs"`
}

// ObserverdConfig drives the observer service (cmd/observerd).
// PersistPath: file path to the JSONL ops log; empty = in-memory
// only (test/dev). Production sets a stable path under
// /var/lib/lakehouse/observer/ops.jsonl so ops survive restart.
// Mirrors the PathwaydConfig pattern.
type ObserverdConfig struct {
	Bind        string `toml:"bind"`
	PersistPath string `toml:"persist_path"`
}

// 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"`
}

// ModelsConfig names the models used by each tier of the small-model
// pipeline (per project_small_model_pipeline_vision.md and the Rust
// `config/providers.toml` convention). Callers reference tier names,
// not literal model IDs — bumping a tier means editing this file, not
// hunting through code.
//
// Tier philosophy:
//   - local_*    : on-box Ollama. Cheap, fast, JSON-clean. Inner-loop
//                  hot path. Repeated calls per query.
//   - cloud_*    : Ollama Cloud (Pro plan). Larger context, called when
//                  local is uncertain. Auth via OLLAMA_CLOUD_KEY.
//   - frontier_* : OpenRouter / OpenCode. Rate-limited, billed per call.
//                  Reserved for blockers and full-scope reviews, not
//                  steady state.
//
// WeakModels is the codified "local-hot-path eligible" list that the
// matrix downgrade gate consults — replacing the previous hardcoded
// switch in internal/matrix/downgrade.go. A model in this list bypasses
// the corpus-downgrade rule: it's already weak, no need to downgrade
// further. Strong (paid / cloud / frontier) models trigger the gate.
type ModelsConfig struct {
	LocalFast      string `toml:"local_fast"`
	LocalEmbed     string `toml:"local_embed"`
	LocalJudge     string `toml:"local_judge"`
	LocalReview    string `toml:"local_review"`

	CloudJudge     string `toml:"cloud_judge"`
	CloudReview    string `toml:"cloud_review"`
	CloudStrong    string `toml:"cloud_strong"`

	FrontierReview string `toml:"frontier_review"`
	FrontierArch   string `toml:"frontier_arch"`
	FrontierStrong string `toml:"frontier_strong"`
	FrontierFree   string `toml:"frontier_free"`

	WeakModels []string `toml:"weak_models"`
}

// Resolve maps a tier name (e.g. "local_judge") to the configured
// model ID. Unknown tier returns "". Callers should fall back to a
// hardcoded default and log a warning when this returns empty — the
// alternative (panic) would make a missing tier crash the binary at
// startup, which is too aggressive for an additive config.
func (m ModelsConfig) Resolve(tier string) string {
	switch tier {
	case "local_fast":
		return m.LocalFast
	case "local_embed":
		return m.LocalEmbed
	case "local_judge":
		return m.LocalJudge
	case "local_review":
		return m.LocalReview
	case "cloud_judge":
		return m.CloudJudge
	case "cloud_review":
		return m.CloudReview
	case "cloud_strong":
		return m.CloudStrong
	case "frontier_review":
		return m.FrontierReview
	case "frontier_arch":
		return m.FrontierArch
	case "frontier_strong":
		return m.FrontierStrong
	case "frontier_free":
		return m.FrontierFree
	default:
		return ""
	}
}

// IsWeak reports whether `model` is in the configured WeakModels list.
// Used by matrix.downgrade to decide whether to bypass the strong-model
// downgrade gate (weak models stay on the full lakehouse path).
func (m ModelsConfig) IsWeak(model string) bool {
	for _, w := range m.WeakModels {
		if w == model {
			return true
		}
	}
	return false
}

// AuthConfig is the inter-service auth posture from ADR-003.
// Token is a Bearer token; empty means "no auth" (G0 dev mode).
// AllowedIPs is a list of CIDRs (or bare IPs treated as /32);
// empty means "any source IP."
//
// Both layers operate independently when set:
//   - Token + AllowedIPs both empty  → middleware is a no-op
//   - Token only                     → 401 unless Bearer matches
//   - AllowedIPs only                → 403 unless r.RemoteAddr in CIDR
//   - Both                           → both gates apply
//
// The startup gate in shared.Run refuses to start with non-loopback
// bind AND empty Token — that's the audit's R-001 + R-007 worst
// case (no auth, world-reachable). LH_<SVC>_ALLOW_NONLOOPBACK=1 still
// bypasses the bind gate for explicit dev cases; the auth gate is
// independent of that bypass and is the real production guard.
type AuthConfig struct {
	Token      string   `toml:"token"`
	AllowedIPs []string `toml:"allowed_ips"`
	// TokenEnv names an environment variable; LoadConfig populates
	// Token from os.Getenv(TokenEnv) when Token is empty. Per ADR-006
	// 6.2: production deploys put the secret in /etc/lakehouse/auth.env
	// (mode 0600) loaded by systemd EnvironmentFile=, NOT in the
	// committed TOML. TokenEnv defaults to "AUTH_TOKEN".
	TokenEnv string `toml:"token_env"`
	// SecondaryTokens lets operators stage a rotation: both primary
	// and any secondary token pass auth during the rotation window.
	// After every caller updates, operators promote secondary →
	// primary and clear secondary. Per ADR-006 Decision 6.5.
	SecondaryTokens []string `toml:"secondary_tokens"`
}

// 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",
			VectordURL:  "http://127.0.0.1:3215",
			EmbeddURL:   "http://127.0.0.1:3216",
			PathwaydURL: "http://127.0.0.1:3217",
			MatrixdURL:   "http://127.0.0.1:3218",
			ObserverdURL: "http://127.0.0.1:3219",
			ChatdURL:     "http://127.0.0.1:3220",
		},
		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",
			MaxIngestBytes: 256 << 20, // 256 MiB; bump per deployment via lakehouse.toml
		},
		Vectord: VectordConfig{
			Bind:        "127.0.0.1:3215",
			StoragedURL: "http://127.0.0.1:3211",
		},
		Embedd: EmbeddConfig{
			Bind:         "127.0.0.1:3216",
			ProviderURL:  "http://localhost:11434", // local Ollama
			DefaultModel: "nomic-embed-text",
			CacheSize:    10_000, // ~30 MiB at d=768; set to 0 to disable
		},
		Pathwayd: PathwaydConfig{
			Bind: "127.0.0.1:3217",
			// PersistPath empty by default = in-memory only. Production
			// sets to e.g. /var/lib/lakehouse/pathway/state.jsonl.
		},
		Matrixd: MatrixdConfig{
			Bind:       "127.0.0.1:3218",
			EmbeddURL:  "http://127.0.0.1:3216",
			VectordURL: "http://127.0.0.1:3215",
		},
		Observerd: ObserverdConfig{
			Bind: "127.0.0.1:3219",
			// PersistPath empty by default = in-memory only.
		},
		Chatd: ChatdConfig{
			Bind:               "127.0.0.1:3220",
			OllamaURL:          "http://localhost:11434",
			OllamaCloudKeyEnv:  "OLLAMA_CLOUD_KEY",
			OpenRouterKeyEnv:   "OPENROUTER_API_KEY",
			OpenCodeKeyEnv:     "OPENCODE_API_KEY",
			KimiKeyEnv:         "KIMI_API_KEY",
			OllamaCloudKeyFile: "/etc/lakehouse/ollama_cloud.env",
			OpenRouterKeyFile:  "/etc/lakehouse/openrouter.env",
			OpenCodeKeyFile:    "/etc/lakehouse/opencode.env",
			KimiKeyFile:        "/etc/lakehouse/kimi.env",
			TimeoutSecs:        180,
		},
		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,
		},
		Models: ModelsConfig{
			// Tier 1 — local hot path. JSON-clean, fast, deterministic.
			// qwen3.5:latest replaces qwen2.5 as the local default per
			// 2026-04-29 architectural review (stronger local model,
			// same JSON-clean property).
			LocalFast:      "qwen3.5:latest",
			LocalEmbed:     "nomic-embed-text",
			LocalJudge:     "qwen3.5:latest",
			LocalReview:    "qwen3.5:latest",

			// Tier 2 — Ollama Cloud (Pro plan). 2026-04-28 upgrade.
			// kimi-k2:1t is upstream-broken; deepseek/kimi-k2.6/qwen3-coder
			// are the working primaries.
			CloudJudge:  "kimi-k2.6:cloud",
			CloudReview: "qwen3-coder:480b",
			CloudStrong: "deepseek-v3.2",

			// Tier 3 — frontier. OpenRouter credits + OpenCode key.
			// Use sparingly: rate-limited, billed per call.
			FrontierReview: "openrouter/anthropic/claude-opus-4-7",
			FrontierArch:   "openrouter/moonshotai/kimi-k2-0905",
			FrontierStrong: "openrouter/openai/gpt-5",
			FrontierFree:   "opencode/claude-opus-4-7",

			// Local-hot-path eligible. matrix.downgrade reads this
			// list to decide whether to bypass the strong-model gate.
			WeakModels: []string{"qwen3.5:latest", "qwen3:latest"},
		},
		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)
	}
	resolveAuthFromEnv(&cfg.Auth)
	return cfg, nil
}

// resolveAuthFromEnv populates cfg.Auth.Token from os.Getenv(TokenEnv)
// when Token is empty. Per ADR-006 Decision 6.2: production deploys
// keep the secret in /etc/lakehouse/auth.env (mode 0600), loaded by
// systemd EnvironmentFile=, never in the committed TOML.
//
// TokenEnv defaults to "AUTH_TOKEN" so operators don't have to
// configure both — setting AUTH_TOKEN env is enough.
func resolveAuthFromEnv(auth *AuthConfig) {
	envName := auth.TokenEnv
	if envName == "" {
		envName = "AUTH_TOKEN"
	}
	if auth.Token == "" {
		if v := os.Getenv(envName); v != "" {
			auth.Token = v
		}
	}
}