feat: Phase 2 — ports package, secrets port move, postgres adapter move

Problem: the hexagon's Phase 2 (plans/2026-08-15-hexagonal-architecture.md) must give the use-cases-to-be their contract surface: driven-port interfaces, test fakes, the secrets interface moved into core, and the postgres package inside the adapters tree — before the first vertical slice (Phase 3) can wire a composition root. Change: - internal/core/ports: full driven-port catalog per plan §3.3 — repositories as transaction-scoped aggregates whose inputs carry derived checks, audit, and events (§3.6), plus CommandExecutor, TargetResolver, Checker, Secrets, EventPublisher, Provisioner. Port-local payload types (Event, AuditEntry, CheckDef, KnowledgeEntry, ExecResult) keep signatures off infrastructure; TypeTree aliases internal/ontology (pure over domain) until checkdefaults is absorbed. ReadModels intentionally not declared yet — it materializes with the Phase 3 slice and grows as report handlers rewire. - secrets.Backend is now an alias of ports.Secrets; implementations (Infisical, SOPS, Manager) unchanged. mcp's local secretBackend subset is deleted; tool constructors take ports.Secrets. - internal/db → internal/adapters/postgres (mechanical import rewrite; package identifier stays db until the Phase 3 repository split). sqlc.yaml, Makefile, golangci exclusions, and docs follow the move; make generate-check verified. - internal/adapters/ssh: Executor implements ports.CommandExecutor over the actuator dial pool + RunStreaming (10-min default timeout carried over from the httpapi path). - internal/adapters/remote: Resolver implements ports.TargetResolver delegating to internal/remote (still pool-based; drops onto ports.EntityRepository when repositories land in Phase 3 — documented transitional import). - internal/core/ports/portstest: importable fakes — in-memory EntityRepo (with check-then-act SetState, side-effect recording), RecordingExecutor, FakeChecker, SpyPublisher; port-satisfaction guards; tests. Risk: ports are declared ahead of implementations — signatures firm up per phase as slices land (documented in the package doc); the remote→postgres transitional import is explicit and dissolves in Phase 3. Verification: go vet, make test (race, 19 packages), generate-check, golangci on core+adapters — 0 issues; full-repo baseline down 365→344.
2026-08-15 22:56:56 +02:00
parent d4d99a7473
commit 64f7d54011
93 changed files with 1102 additions and 103 deletions
--- a/internal/adapters/postgres/lifecycle.go
+++ b/internal/adapters/postgres/lifecycle.go
@@ -0,0 +1,182 @@
+package db
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+
+	"github.com/dtoro/oikos/internal/adapters/postgres/sqlcgen"
+	"github.com/google/uuid"
+	"github.com/jackc/pgx/v5"
+)
+
+// ErrTransitionInvalid is a sentinel returned by ValidateTransition when the
+// from→to pair is not a declared lifecycle transition or a precondition fails.
+// Callers test with errors.Is to distinguish semantic validation failures
+// (→ HTTP 409) from infrastructure errors (→ HTTP 500).
+var ErrTransitionInvalid = errors.New("invalid lifecycle transition")
+
+// ValidateTransition enforces an entity type's lifecycle: fromState → toState
+// must be a declared transition, and every precondition it lists must hold. A
+// type with no lifecycle defined allows any state. A no-op (fromState ==
+// toState) passes immediately.
+//
+// Shared by the HTTP PATCH path and the MCP set_entity_state tool so both
+// surfaces apply identical lifecycle rules — previously only the HTTP path
+// validated transitions, so an agent changing state via MCP could skip the
+// graph's retire/deprecate guardrails entirely.
+func ValidateTransition(ctx context.Context, tx pgx.Tx, entityID uuid.UUID, entityType, fromState, toState string) error {
+	if toState == fromState {
+		return nil
+	}
+	lc, err := sqlcgen.New(tx).GetLifecycleForType(ctx, entityType)
+	if err != nil {
+		if err == pgx.ErrNoRows {
+			return nil // no lifecycle defined → any state allowed
+		}
+		return err
+	}
+	var transitions map[string]map[string]json.RawMessage
+	if err := json.Unmarshal(lc.Transitions, &transitions); err != nil {
+		return fmt.Errorf("parse lifecycle transitions: %w", err)
+	}
+	tos, ok := transitions[fromState]
+	if !ok {
+		return fmt.Errorf("%w: no transitions defined from %q", ErrTransitionInvalid, fromState)
+	}
+	trans, ok := tos[toState]
+	if !ok {
+		return fmt.Errorf("%w: %s → %s is not a declared lifecycle transition", ErrTransitionInvalid, fromState, toState)
+	}
+	var gate struct {
+		Requires []string `json:"requires"`
+	}
+	if err := json.Unmarshal(trans, &gate); err == nil {
+		for _, check := range gate.Requires {
+			if err := checkPrecondition(ctx, tx, entityID, entityType, check); err != nil {
+				return fmt.Errorf("%w: precondition %q not met: %w", ErrTransitionInvalid, check, err)
+			}
+		}
+	}
+	return nil
+}
+
+// checkPrecondition evaluates one mechanical precondition named by a lifecycle
+// transition's `requires` list. Soft/operator-confirmed checks pass; unknown
+// checks are skipped (operator intent overrides). Moved here from httpapi so
+// both surfaces share one implementation.
+func checkPrecondition(ctx context.Context, tx pgx.Tx, entityID uuid.UUID, entityType, check string) error {
+	switch check {
+	case "no-inbound-edges":
+		var count int
+		if err := tx.QueryRow(ctx,
+			"SELECT count(*) FROM relationships WHERE target_id = $1 AND valid_to IS NULL", entityID).Scan(&count); err != nil {
+			return err
+		}
+		if count > 0 {
+			return fmt.Errorf("%d inbound relationship edges remaining", count)
+		}
+	case "backups-verified", "secrets-revoked", "ingress-dns-removed":
+		attrs, err := fetchAttrs(ctx, tx, entityID)
+		if err != nil {
+			return err
+		}
+		want := map[string]string{
+			"backups-verified":    "backups_verified",
+			"secrets-revoked":     "secrets_revoked",
+			"ingress-dns-removed": "ingress_dns_removed",
+		}[check]
+		if !attrTruthy(attrs, want) {
+			return fmt.Errorf("%s not recorded in entity attributes", want)
+		}
+	case "age-key-enrolled-if-needed":
+		if entityType == "workstation" {
+			attrs, err := fetchAttrs(ctx, tx, entityID)
+			if err != nil {
+				return err
+			}
+			if !attrTruthy(attrs, "age_pubkey") {
+				return fmt.Errorf("age key not enrolled (no age_pubkey in attributes)")
+			}
+		}
+	case "mesh-joined-if-needed":
+		if entityType == "workstation" {
+			attrs, err := fetchAttrs(ctx, tx, entityID)
+			if err != nil {
+				return err
+			}
+			if !attrTruthy(attrs, "mesh_ip") {
+				return fmt.Errorf("mesh not joined (no mesh_ip in attributes)")
+			}
+		}
+	case "health-check-answering":
+		st, err := sqlcgen.New(tx).GetEntityStatus(ctx, entityID)
+		if err != nil || st.Health == "unknown" || st.Health == "down" {
+			h := "unknown"
+			if err == nil {
+				h = st.Health
+			}
+			return fmt.Errorf("health check not answering (status: %s)", h)
+		}
+	case "doc-page-complete":
+		var count int
+		if err := tx.QueryRow(ctx, `
+			SELECT count(*) FROM relationships r
+			JOIN entities ke ON ke.id = r.source_id
+			WHERE r.target_id = $1 AND r.valid_to IS NULL
+			  AND r.type = 'documents' AND ke.type IN ('document','runbook','investigation')`,
+			entityID).Scan(&count); err != nil {
+			return err
+		}
+		if count == 0 {
+			return fmt.Errorf("no documentation linked to entity")
+		}
+	case "inventory-entry", "ip-reserved", "storage-pool-chosen", "cancelled-note",
+		"preflight-passed", "error-summary", "replacement-live-or-role-retired",
+		"replacement-failed", "post-verify-passed", "recovery-verified", "written-off",
+		"ingress-live-if-public", "doc-page-stub", "un-deprecate-note", "write-off-note":
+		// Soft checks — always pass. Operator-confirmed via the transition
+		// request itself, or not mechanically enforceable.
+	default:
+		// Unknown preconditions are skipped (operator intent overrides).
+	}
+	return nil
+}
+
+// fetchAttrs loads an entity's JSONB attributes column as a decoded map.
+// Missing attributes decode to an empty map (every key absent).
+func fetchAttrs(ctx context.Context, tx pgx.Tx, entityID uuid.UUID) (map[string]any, error) {
+	var raw string
+	if err := tx.QueryRow(ctx, "SELECT coalesce(attributes::text,'{}') FROM entities WHERE id = $1", entityID).Scan(&raw); err != nil {
+		return nil, err
+	}
+	var attrs map[string]any
+	if err := json.Unmarshal([]byte(raw), &attrs); err != nil {
+		return nil, fmt.Errorf("decode entity attributes: %w", err)
+	}
+	if attrs == nil {
+		attrs = map[string]any{}
+	}
+	return attrs, nil
+}
+
+// attrTruthy reports whether key is present in attrs with a meaningful value.
+// It replaces substring matching on raw JSONB text: a previous strings.Contains
+// check treated {"backups_verified": false} as satisfied (the key text was
+// present) and bypassed the attributes GIN index. Booleans must be true;
+// strings must be non-empty; nil/absent fail.
+func attrTruthy(attrs map[string]any, key string) bool {
+	v, ok := attrs[key]
+	if !ok || v == nil {
+		return false
+	}
+	switch t := v.(type) {
+	case bool:
+		return t
+	case string:
+		return t != ""
+	default:
+		return true // numbers, objects, arrays count as present
+	}
+}