phase 1: Go foundation — module, migrations, domain, seed ingest

Core deliverables: - Go module github.com/dtoro/oikos (Go 1.26.3) - cmd/oikos: single binary with role subcommands (migrate, seed, export) - 6 SQL migrations: ontology meta-schema, entity instances (UUID+slug, blast_radius recursive function), operations (signals/checks/approvals), cognition (classifications/executions/feedback/patterns/skills), policy, observability (TimescaleDB hypertables + CAGGs + retention) - Domain layer: entity, signal, execution, classification, pattern, skill, approval, check types + 11 sentinel errors + lifecycle state machines - DB layer: pgx pool, SQL splitter (handles 94436 and -- comments), migration runner, seed ingest (ontology+inventory+policy) with content-hash dedup - Config: env-based with defaults, secrets redaction - Observability: slog JSON logger with debug mode - Infrastructure: Makefile, docker-compose.yml, multi-stage Dockerfile (distroless, CGO_ENABLED=0) Verified end-to-end against timescale/timescaledb:2.17.2-pg16: - 6 migrations applied (65 SQL statements) - Seeds ingested: 6 lifecycles, 59 entity types, 46 relationship types, 111 entities, 144 relationships, 4 risk classes, 27 approval rules, 9 autonomy settings - Idempotent: second seed run is a no-op (content hash matches) Bugs fixed during implementation: - TimescaleDB CAGGs can't run in a transaction -> splitSQL() executes statements individually - Semicolons in -- comments treated as separators -> comment handling - YAML keys source/target didn't match code's source_type/target_type - yaml.Marshal produced YAML for JSONB columns -> json.Marshal
2026-07-07 01:07:26 +02:00
parent 55710bd254
commit aa2ca0ae6f
23 changed files with 1964 additions and 0 deletions
--- a/internal/db/pool.go
+++ b/internal/db/pool.go
@@ -0,0 +1,234 @@
+package db
+
+import (
+	"context"
+	"crypto/sha256"
+	"encoding/hex"
+	"fmt"
+	"io/fs"
+	"log/slog"
+	"sort"
+	"strings"
+
+	"github.com/dtoro/oikos/migrations"
+	"github.com/jackc/pgx/v5"
+	"github.com/jackc/pgx/v5/pgxpool"
+	"gopkg.in/yaml.v3"
+)
+
+// Pool wraps a pgx connection pool.
+type Pool struct {
+	*pgxpool.Pool
+}
+
+// New creates a new connection pool.
+func New(ctx context.Context, databaseURL string) (*Pool, error) {
+	cfg, err := pgxpool.ParseConfig(databaseURL)
+	if err != nil {
+		return nil, fmt.Errorf("parse database url: %w", err)
+	}
+	cfg.MaxConns = 15
+
+	pool, err := pgxpool.NewWithConfig(ctx, cfg)
+	if err != nil {
+		return nil, fmt.Errorf("create pool: %w", err)
+	}
+	if err := pool.Ping(ctx); err != nil {
+		return nil, fmt.Errorf("ping db: %w", err)
+	}
+	return &Pool{pool}, nil
+}
+
+// Migrate runs all embedded forward migrations in order.
+// Uses a schema_migrations table to track applied versions.
+func (p *Pool) Migrate(ctx context.Context) error {
+	// Create tracking table if not exists
+	_, err := p.Exec(ctx, `
+		CREATE TABLE IF NOT EXISTS schema_migrations (
+			version INT PRIMARY KEY,
+			applied_at TIMESTAMPTZ NOT NULL DEFAULT now()
+		)
+	`)
+	if err != nil {
+		return fmt.Errorf("create schema_migrations: %w", err)
+	}
+
+	// List migration files
+	entries, err := fs.ReadDir(migrations.FS, ".")
+	if err != nil {
+		return fmt.Errorf("read migration fs: %w", err)
+	}
+
+	var files []string
+	for _, e := range entries {
+		if !e.IsDir() && hasSuffix(e.Name(), ".up.sql") {
+			files = append(files, e.Name())
+		}
+	}
+	sort.Strings(files)
+
+	for _, fname := range files {
+		// Extract version number (001, 002, etc.)
+		var version int
+		if _, err := fmt.Sscanf(fname, "%03d", &version); err != nil {
+			continue
+		}
+
+		// Check if already applied
+		var applied int
+		err := p.QueryRow(ctx,
+			"SELECT COUNT(*) FROM schema_migrations WHERE version = $1", version).Scan(&applied)
+		if err != nil {
+			return fmt.Errorf("check migration %d: %w", version, err)
+		}
+		if applied > 0 {
+			continue
+		}
+
+		// Read and execute migration — split into individual statements
+		// because TimescaleDB CAGGs and some DDL can't run inside a transaction,
+		// and pgx's multi-statement Exec wraps them implicitly.
+		content, err := migrations.FS.ReadFile(fname)
+		if err != nil {
+			return fmt.Errorf("read %s: %w", fname, err)
+		}
+
+		stmts := splitSQL(string(content))
+		for i, stmt := range stmts {
+			stmt = strings.TrimSpace(stmt)
+			if stmt == "" {
+				continue
+			}
+			_, err := p.Exec(ctx, stmt)
+			if err != nil {
+				return fmt.Errorf("exec migration %s stmt %d: %w", fname, i+1, err)
+			}
+		}
+		_, err = p.Exec(ctx, "INSERT INTO schema_migrations (version) VALUES ($1)", version)
+		if err != nil {
+			return fmt.Errorf("record migration %d: %w", version, err)
+		}
+		slog.Info("migration applied", "file", fname, "version", version, "statements", len(stmts))
+	}
+
+	return nil
+}
+
+// SeedIngest ingests a YAML seed file into the database.
+// Idempotent: if the file's content hash matches seed_versions, it's a no-op (A4).
+func (p *Pool) SeedIngest(ctx context.Context, filename string, content []byte,
+	ingestFn func(ctx context.Context, tx pgx.Tx, data map[string]any) error) error {
+
+	hash := contentHash(content)
+
+	// Check if already applied with same hash
+	var existing string
+	err := p.QueryRow(ctx,
+		"SELECT content_hash FROM seed_versions WHERE file = $1", filename).Scan(&existing)
+	if err == nil && existing == hash {
+		return nil // no-op, same content
+	}
+
+	// Parse YAML
+	var data map[string]any
+	if err := yaml.Unmarshal(content, &data); err != nil {
+		return fmt.Errorf("parse %s: %w", filename, err)
+	}
+
+	// Apply in a single transaction
+	tx, err := p.Begin(ctx)
+	if err != nil {
+		return fmt.Errorf("begin tx: %w", err)
+	}
+	defer tx.Rollback(ctx)
+
+	if err := ingestFn(ctx, tx, data); err != nil {
+		return fmt.Errorf("ingest %s: %w", filename, err)
+	}
+
+	// Record the seed version
+	_, err = tx.Exec(ctx,
+		`INSERT INTO seed_versions (file, content_hash) VALUES ($1, $2)
+		 ON CONFLICT (file) DO UPDATE SET content_hash = $2, applied_at = now()`,
+		filename, hash)
+	if err != nil {
+		return fmt.Errorf("record seed version: %w", err)
+	}
+
+	if err := tx.Commit(ctx); err != nil {
+		return fmt.Errorf("commit seed: %w", err)
+	}
+
+	return nil
+}
+
+// contentHash returns a SHA-256 hex digest of the content.
+func contentHash(content []byte) string {
+	h := sha256.Sum256(content)
+	return hex.EncodeToString(h[:])
+}
+
+// hasSuffix reports whether the string ends with the given suffix.
+func hasSuffix(s, suffix string) bool {
+	return strings.HasSuffix(s, suffix)
+}
+
+// splitSQL splits a SQL string into individual statements.
+// Handles $$ ... $$ dollar-quoted blocks and -- line comments.
+func splitSQL(sql string) []string {
+	var statements []string
+	var current strings.Builder
+	inDollarQuote := false
+	dollarTag := ""
+
+	i := 0
+	for i < len(sql) {
+		// Handle line comments (-- to end of line)
+		if !inDollarQuote && i+1 < len(sql) && sql[i] == '-' && sql[i+1] == '-' {
+			// Skip to end of line
+			for i < len(sql) && sql[i] != '\n' {
+				current.WriteByte(sql[i])
+				i++
+			}
+			continue
+		}
+
+		// Check for dollar-quote start/end
+		if !inDollarQuote && sql[i] == '$' {
+			j := i + 1
+			for j < len(sql) && (sql[j] == '_' || (sql[j] >= 'a' && sql[j] <= 'z') || (sql[j] >= 'A' && sql[j] <= 'Z') || (sql[j] >= '0' && sql[j] <= '9')) {
+				j++
+			}
+			if j < len(sql) && sql[j] == '$' {
+				dollarTag = sql[i : j+1]
+				current.WriteString(dollarTag)
+				inDollarQuote = true
+				i = j + 1
+				continue
+			}
+		}
+		if inDollarQuote && strings.HasPrefix(sql[i:], dollarTag) {
+			current.WriteString(dollarTag)
+			i += len(dollarTag)
+			inDollarQuote = false
+			dollarTag = ""
+			continue
+		}
+
+		if !inDollarQuote && sql[i] == ';' {
+			statements = append(statements, current.String())
+			current.Reset()
+			i++
+			continue
+		}
+
+		current.WriteByte(sql[i])
+		i++
+	}
+
+	if strings.TrimSpace(current.String()) != "" {
+		statements = append(statements, current.String())
+	}
+
+	return statements
+}