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.
212 lines
5.0 KiB
Go
212 lines
5.0 KiB
Go
package learning
|
|
|
|
import (
|
|
"math"
|
|
"testing"
|
|
|
|
"github.com/dtoro/oikos/internal/adapters/postgres/sqlcgen"
|
|
)
|
|
|
|
func TestWilsonLowerBound(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
success float64
|
|
total float64
|
|
z float64
|
|
want float64
|
|
// For approximate checks
|
|
approx bool
|
|
epsilon float64
|
|
}{
|
|
{"zero total", 5, 0, 1.96, 0, false, 0},
|
|
{"zero success", 0, 10, 1.96, 0, true, 1e-10},
|
|
{"all success small n", 3, 3, 1.96, 0, true, 0.5},
|
|
{"all success large n", 100, 100, 1.96, 0, true, 0.05},
|
|
{"half success large n", 50, 100, 1.96, 0.39, true, 0.02},
|
|
{"higher z gives lower bound", 8, 10, 3.0, 0, true, 0.5},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
got := wilsonLowerBound(tt.success, tt.total, tt.z)
|
|
if tt.approx {
|
|
if tt.want > 0 && math.Abs(got-tt.want) > tt.epsilon {
|
|
t.Errorf("wilsonLowerBound(%v, %v, %v) = %v, want ~%v (±%v)", tt.success, tt.total, tt.z, got, tt.want, tt.epsilon)
|
|
}
|
|
if got < 0 {
|
|
t.Errorf("wilsonLowerBound returned negative: %v", got)
|
|
}
|
|
if got > 1 {
|
|
t.Errorf("wilsonLowerBound returned >1: %v", got)
|
|
}
|
|
} else {
|
|
if got != tt.want {
|
|
t.Errorf("wilsonLowerBound(%v, %v, %v) = %v, want %v", tt.success, tt.total, tt.z, got, tt.want)
|
|
}
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestWilsonLowerBoundMonotonic(t *testing.T) {
|
|
prev := 0.0
|
|
for s := 0.0; s <= 20; s++ {
|
|
got := wilsonLowerBound(s, 20, 1.96)
|
|
if got < prev-1e-9 {
|
|
t.Errorf("not monotonically increasing: s=%v got=%v prev=%v", s, got, prev)
|
|
}
|
|
prev = got
|
|
}
|
|
}
|
|
|
|
func TestCountOutcomes(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
items []sqlcgen.GetFeedbackAfterWatermarkRow
|
|
wantSuccess int
|
|
wantFailure int
|
|
}{
|
|
{
|
|
"empty",
|
|
nil,
|
|
0, 0,
|
|
},
|
|
{
|
|
"all success",
|
|
[]sqlcgen.GetFeedbackAfterWatermarkRow{
|
|
{Outcome: "success"},
|
|
{Outcome: "success"},
|
|
},
|
|
2, 0,
|
|
},
|
|
{
|
|
"all failure",
|
|
[]sqlcgen.GetFeedbackAfterWatermarkRow{
|
|
{Outcome: "failure"},
|
|
{Outcome: "unexpected"},
|
|
},
|
|
0, 2,
|
|
},
|
|
{
|
|
"mixed including partial",
|
|
[]sqlcgen.GetFeedbackAfterWatermarkRow{
|
|
{Outcome: "success"},
|
|
{Outcome: "failure"},
|
|
{Outcome: "partial"},
|
|
{Outcome: "unexpected"},
|
|
},
|
|
2, 2,
|
|
},
|
|
{
|
|
"unknown outcome ignored",
|
|
[]sqlcgen.GetFeedbackAfterWatermarkRow{
|
|
{Outcome: "success"},
|
|
{Outcome: "bogus"},
|
|
},
|
|
1, 0,
|
|
},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
s, f := countOutcomes(tt.items)
|
|
if s != tt.wantSuccess || f != tt.wantFailure {
|
|
t.Errorf("countOutcomes() = (%d, %d), want (%d, %d)", s, f, tt.wantSuccess, tt.wantFailure)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestComputeConfidence(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
success int
|
|
failure int
|
|
wantMax float64
|
|
wantMin float64
|
|
}{
|
|
{"zero total", 0, 0, 0, 0},
|
|
{"one success no failures", 1, 0, 0.2, 0},
|
|
{"five success no failures", 5, 0, 1.0, 0.3},
|
|
{"ten success no failures", 10, 0, 1.0, 0.5},
|
|
{"half success", 5, 5, 0.5, 0.2},
|
|
{"all failures", 0, 10, 0.01, 0},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
got := computeConfidence(tt.success, tt.failure)
|
|
if got < 0 || got > 1 {
|
|
t.Errorf("confidence out of [0,1]: %v", got)
|
|
}
|
|
if got > tt.wantMax+0.01 {
|
|
t.Errorf("confidence too high: got %v, max ~%v", got, tt.wantMax)
|
|
}
|
|
if tt.wantMin > 0 && got < tt.wantMin-0.1 {
|
|
t.Errorf("confidence too low: got %v, min ~%v", got, tt.wantMin)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestComputeConfidenceSampleSizeCap(t *testing.T) {
|
|
got := computeConfidence(1, 0)
|
|
if got > 0.2+1e-9 {
|
|
t.Errorf("sample size cap not applied: 1 sample should cap at 1/5=0.2, got %v", got)
|
|
}
|
|
got = computeConfidence(4, 0)
|
|
if got > 0.8+1e-9 {
|
|
t.Errorf("sample size cap not applied: 4 samples should cap at 4/5=0.8, got %v", got)
|
|
}
|
|
}
|
|
|
|
func TestShouldValidate(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
evidenceCount int
|
|
confidence float64
|
|
quarantined bool
|
|
want bool
|
|
}{
|
|
{"enough evidence and confidence", 5, 0.7, false, true},
|
|
{"high evidence high confidence", 10, 0.9, false, true},
|
|
{"not enough evidence", 4, 0.9, false, false},
|
|
{"not enough confidence", 5, 0.69, false, false},
|
|
{"quarantined blocks validation", 10, 0.9, true, false},
|
|
{"exactly at threshold", 5, 0.7, false, true},
|
|
{"zero evidence", 0, 0.9, false, false},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
got := shouldValidate(tt.evidenceCount, tt.confidence, tt.quarantined)
|
|
if got != tt.want {
|
|
t.Errorf("shouldValidate(%d, %v, %v) = %v, want %v", tt.evidenceCount, tt.confidence, tt.quarantined, got, tt.want)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestShouldQuarantine(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
total int
|
|
want bool
|
|
}{
|
|
{"zero", 0, false},
|
|
{"small", 5, false},
|
|
{"at threshold", 10, false},
|
|
{"over threshold", 11, true},
|
|
{"large burst", 50, true},
|
|
}
|
|
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
got := shouldQuarantine(tt.total)
|
|
if got != tt.want {
|
|
t.Errorf("shouldQuarantine(%d) = %v, want %v", tt.total, got, tt.want)
|
|
}
|
|
})
|
|
}
|
|
}
|