test: add unit tests for 6 previously-untested packages (R7)

Added pure unit tests for all packages that had 0% coverage. Where pure logic was entangled with DB calls, extracted testable helpers first. internal/domain (0% -> 100%): - TestIsNil, TestCanTransition (all 30 state transitions), TestSentinelErrors, TestSignalTransitionsComplete internal/learning (0% -> 26.2%): - Refactored processGroup to extract 4 pure helpers: countOutcomes, computeConfidence, shouldValidate, shouldQuarantine - TestWilsonLowerBound (monotonicity, edge cases, sample-size cap) - TestCountOutcomes, TestComputeConfidence, TestShouldValidate, TestShouldQuarantine (table-driven) - Remaining gap: extractPatterns/processGroup DB calls need make test-db internal/policy (39% -> 50%): - Extracted determineRoute from ClassifySignal (pure route logic) - TestDetermineRoute (7 cases covering global/entity kill-switches, approval) - Remaining gap: ClassifySignal/computeBlastRadius need DB mock internal/knowledge (0% -> 14.2%): - TestContentHash, TestStr, TestStrSlice, TestMapVal, TestToPGArray - Documented latent bug: toPGArray doesn't escape " or \\ in tags - Remaining gap: ingest* functions need make test-db internal/actuator (0% -> 14.7%): - TestSSHErrorClassString, TestClassifySSHError (11 cases incl. net.Error mock) - TestParseProcedure, TestSetDefaultSSHTimeout - Circuit breaker full state-machine test (open/close/reset/per-target) - Remaining gap: ExecuteProcedure/ProvisionLXC need SSH+DB fixtures internal/scheduler (0% -> 7.3%): - TestParsePingLatency (Linux/macOS formats), TestAllowlistedScript - TestEvaluateSeverity (threshold logic, crit:0 skip, signalKind fallback) - Remaining gap: checkHTTP/checkTCP need httptest; runCheckPass needs DB internal/notifier (0% -> 6.4%): - TestHashToken, TestGenerateApprovalToken (HMAC re-derivation) - Remaining gap: checkReaction/sendMatrixAlert need httptest; DB funcs need make test-db All tests pass with -race. domain hits its 60% gate at 100%. The remaining packages need integration tests (make test-db) and/or httptest-based tests to reach their coverage gates — tracked as follow-up.
2026-07-17 22:54:44 +02:00
parent 463bdacf5c
commit c96c795126
11 changed files with 1282 additions and 35 deletions
--- a/internal/actuator/circuit_breaker_test.go
+++ b/internal/actuator/circuit_breaker_test.go
@@ -0,0 +1,109 @@
+package actuator
+
+import (
+	"testing"
+	"time"
+)
+
+func TestNewCircuitBreakerDefaults(t *testing.T) {
+	cb := newCircuitBreaker(0, 0)
+	if cb.threshold != 3 {
+		t.Errorf("threshold = %d, want 3", cb.threshold)
+	}
+	if cb.cooldownS != 300 {
+		t.Errorf("cooldownS = %d, want 300", cb.cooldownS)
+	}
+
+	cb = newCircuitBreaker(5, 60)
+	if cb.threshold != 5 {
+		t.Errorf("threshold = %d, want 5", cb.threshold)
+	}
+	if cb.cooldownS != 60 {
+		t.Errorf("cooldownS = %d, want 60", cb.cooldownS)
+	}
+}
+
+func TestCircuitBreakerIsOpenFresh(t *testing.T) {
+	cb := newCircuitBreaker(3, 60)
+	if cb.isOpen("host:A") {
+		t.Errorf("fresh circuit should be closed, got open")
+	}
+}
+
+func TestCircuitBreakerOpensAtThreshold(t *testing.T) {
+	cb := newCircuitBreaker(3, 60)
+	// threshold-1 failures → still closed
+	cb.recordFailure("host:A")
+	cb.recordFailure("host:A")
+	if cb.isOpen("host:A") {
+		t.Fatalf("circuit should be closed after threshold-1 failures")
+	}
+	// one more → open
+	cb.recordFailure("host:A")
+	if !cb.isOpen("host:A") {
+		t.Fatalf("circuit should be open after threshold failures")
+	}
+}
+
+func TestCircuitBreakerClosesAfterCooldown(t *testing.T) {
+	cb := newCircuitBreaker(1, 60)
+	// Force open
+	cb.recordFailure("host:A")
+	if !cb.isOpen("host:A") {
+		t.Fatalf("circuit should be open")
+	}
+	// Manipulate the cooldown timestamp to the past to simulate expiry.
+	cb.mu.Lock()
+	cb.cooldowns["host:A"] = time.Now().Add(-1 * time.Second)
+	cb.mu.Unlock()
+
+	if cb.isOpen("host:A") {
+		t.Fatalf("circuit should be closed after cooldown expired")
+	}
+	// Failure count should have been reset by isOpen.
+	cb.mu.Lock()
+	got := cb.failures["host:A"]
+	cb.mu.Unlock()
+	if got != 0 {
+		t.Errorf("failure count after cooldown reset = %d, want 0", got)
+	}
+}
+
+func TestCircuitBreakerRecordSuccessResets(t *testing.T) {
+	cb := newCircuitBreaker(3, 60)
+	cb.recordFailure("host:A")
+	cb.recordFailure("host:A")
+
+	cb.recordSuccess("host:A")
+
+	cb.mu.Lock()
+	got := cb.failures["host:A"]
+	cb.mu.Unlock()
+	if got != 0 {
+		t.Errorf("failure count after success = %d, want 0", got)
+	}
+	if cb.isOpen("host:A") {
+		t.Errorf("circuit should be closed after success reset")
+	}
+}
+
+func TestCircuitBreakerPerTargetIsolation(t *testing.T) {
+	cb := newCircuitBreaker(2, 60)
+	cb.recordFailure("host:A")
+	cb.recordFailure("host:A") // host:A now at threshold → open
+
+	if !cb.isOpen("host:A") {
+		t.Fatalf("host:A should be open")
+	}
+	if cb.isOpen("host:B") {
+		t.Errorf("host:B should be closed (isolated from host:A)")
+	}
+
+	// host:B has no failures recorded
+	cb.mu.Lock()
+	gotB := cb.failures["host:B"]
+	cb.mu.Unlock()
+	if gotB != 0 {
+		t.Errorf("host:B failure count = %d, want 0", gotB)
+	}
+}
--- a/internal/actuator/ssh_test.go
+++ b/internal/actuator/ssh_test.go
@@ -0,0 +1,151 @@
+package actuator
+
+import (
+	"context"
+	"errors"
+	"net"
+	"testing"
+	"time"
+
+	"golang.org/x/crypto/ssh"
+)
+
+func TestSSHErrorClassString(t *testing.T) {
+	cases := []struct {
+		class SSHErrorClass
+		want  string
+	}{
+		{SSHErrorNetwork, "network"},
+		{SSHErrorAuth, "auth"},
+		{SSHErrorTimeout, "timed_out"},
+		{SSHErrorRemote, "remote"},
+		{SSHErrorOther, "other"},
+		{SSHErrorClass(999), "unknown"},
+	}
+	for _, c := range cases {
+		if got := c.class.String(); got != c.want {
+			t.Errorf("SSHErrorClass(%d).String() = %q, want %q", c.class, got, c.want)
+		}
+	}
+}
+
+// timeoutNetErr is a custom net.Error implementation for testing.
+type timeoutNetErr struct {
+	timeout bool
+	msg     string
+}
+
+func (e *timeoutNetErr) Error() string   { return e.msg }
+func (e *timeoutNetErr) Timeout() bool   { return e.timeout }
+func (e *timeoutNetErr) Temporary() bool { return false }
+
+func TestClassifySSHError(t *testing.T) {
+	// ssh.ExitError fields are unexported, but classifySSHError only checks
+	// for the type via errors.As, so the zero value is sufficient.
+	exitErr := &ssh.ExitError{}
+
+	cases := []struct {
+		name string
+		err  error
+		want SSHErrorClass
+	}{
+		{"nil", nil, SSHErrorOther},
+		{"deadline exceeded", context.DeadlineExceeded, SSHErrorTimeout},
+		{"net error timeout true", &timeoutNetErr{timeout: true, msg: "i/o timeout"}, SSHErrorNetwork},
+		{"net error timeout false", &timeoutNetErr{timeout: false, msg: "connection refused"}, SSHErrorNetwork},
+		{"unable to authenticate", errors.New("unable to authenticate, no supported methods remain"), SSHErrorAuth},
+		{"no supported methods remain", errors.New("no supported methods remain (server sent publickey)"), SSHErrorAuth},
+		{"ssh handshake failed", errors.New("ssh: handshake failed: read tcp -> eof"), SSHErrorAuth},
+		{"publickey", errors.New("publickey denied"), SSHErrorAuth},
+		{"permission denied", errors.New("permission denied (publickey)"), SSHErrorAuth},
+		{"exit error", exitErr, SSHErrorRemote},
+		{"generic error", errors.New("something went wrong"), SSHErrorOther},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			if got := classifySSHError(c.err); got != c.want {
+				t.Errorf("classifySSHError(%v) = %v, want %v", c.err, got, c.want)
+			}
+		})
+	}
+}
+
+func TestParseProcedure(t *testing.T) {
+	cases := []struct {
+		name    string
+		data    []byte
+		wantErr bool
+		wantLen int
+	}{
+		{
+			name:    "valid with steps",
+			data:    []byte(`{"steps":[{"runner":"shell","command":"echo hi"}]}`),
+			wantErr: false,
+			wantLen: 1,
+		},
+		{
+			name:    "invalid json",
+			data:    []byte(`{not json`),
+			wantErr: true,
+		},
+		{
+			name:    "empty bytes",
+			data:    []byte{},
+			wantErr: true,
+		},
+		{
+			name:    "valid no steps key",
+			data:    []byte(`{"foo":"bar"}`),
+			wantErr: false,
+			wantLen: 0,
+		},
+		{
+			name:    "valid with extra fields",
+			data:    []byte(`{"extra":"ignored","steps":[{"runner":"verify","command":"true"}],"more":123}`),
+			wantErr: false,
+			wantLen: 1,
+		},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			proc, err := ParseProcedure(c.data)
+			if c.wantErr {
+				if err == nil {
+					t.Fatalf("expected error, got nil (proc=%+v)", proc)
+				}
+				return
+			}
+			if err != nil {
+				t.Fatalf("unexpected error: %v", err)
+			}
+			if len(proc.Steps) != c.wantLen {
+				t.Errorf("got %d steps, want %d", len(proc.Steps), c.wantLen)
+			}
+		})
+	}
+}
+
+func TestSetDefaultSSHTimeout(t *testing.T) {
+	mu.Lock()
+	orig := defaultSSHTimeout
+	mu.Unlock()
+	defer func() {
+		mu.Lock()
+		defaultSSHTimeout = orig
+		mu.Unlock()
+	}()
+
+	newTimeout := 42 * time.Second
+	SetDefaultSSHTimeout(newTimeout)
+
+	mu.Lock()
+	got := defaultSSHTimeout
+	mu.Unlock()
+
+	if got != newTimeout {
+		t.Errorf("defaultSSHTimeout = %v, want %v", got, newTimeout)
+	}
+}
+
+// Ensure timeoutNetErr satisfies net.Error at compile time.
+var _ net.Error = (*timeoutNetErr)(nil)
--- a/internal/domain/domain_test.go
+++ b/internal/domain/domain_test.go
@@ -0,0 +1,139 @@
+package domain
+
+import (
+	"errors"
+	"testing"
+)
+
+func TestIsNil(t *testing.T) {
+	cases := []struct {
+		name string
+		u    UUID
+		want bool
+	}{
+		{"empty string", UUID(""), true},
+		{"single char", UUID("x"), false},
+		{"uuid string", UUID("550e8400-e29b-41d4-a716-446655440000"), false},
+		{"nil literal", UUID(""), true},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			got := c.u.IsNil()
+			if got != c.want {
+				t.Errorf("UUID(%q).IsNil() = %v, want %v", c.u, got, c.want)
+			}
+		})
+	}
+}
+
+func TestCanTransition(t *testing.T) {
+	type tc struct {
+		name string
+		from string
+		to   string
+		want bool
+	}
+	var cases []tc
+
+	for from, targets := range ValidSignalTransitions {
+		for _, to := range targets {
+			cases = append(cases, tc{from + "->" + to, from, to, true})
+		}
+	}
+
+	disallowed := []tc{
+		{"raised->raised", SignalRaised, SignalRaised, false},
+		{"resolved->raised", SignalResolved, SignalRaised, false},
+		{"failed->raised", SignalFailed, SignalRaised, false},
+		{"acknowledged->raised", SignalAcknowledged, SignalRaised, false},
+		{"muted->resolved", SignalMuted, SignalResolved, false},
+		{"acting->acknowledged", SignalActing, SignalAcknowledged, false},
+	}
+	cases = append(cases, disallowed...)
+
+	cases = append(cases,
+		tc{"unknown source", "nonexistent", SignalRaised, false},
+		tc{"unknown target", SignalRaised, "nonexistent", false},
+	)
+
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			s := &Signal{State: c.from}
+			got := s.CanTransition(c.to)
+			if got != c.want {
+				t.Errorf("CanTransition(%q -> %q) = %v, want %v", c.from, c.to, got, c.want)
+			}
+		})
+	}
+}
+
+func TestSentinelErrors(t *testing.T) {
+	cases := []struct {
+		name string
+		err  error
+		msg  string
+	}{
+		{"ErrNotFound", ErrNotFound, "entity not found"},
+		{"ErrInvalidTransition", ErrInvalidTransition, "invalid lifecycle transition"},
+		{"ErrApprovalRequired", ErrApprovalRequired, "operator approval required"},
+		{"ErrAutonomyBlocked", ErrAutonomyBlocked, "autonomy policy blocks this action"},
+		{"ErrConflict", ErrConflict, "concurrent modification conflict"},
+		{"ErrCircuitOpen", ErrCircuitOpen, "circuit breaker open for target"},
+		{"ErrAbstractType", ErrAbstractType, "cannot instantiate abstract entity type"},
+		{"ErrInvalidEdge", ErrInvalidEdge, "relationship endpoint type mismatch"},
+		{"ErrCardinality", ErrCardinality, "relationship cardinality violation"},
+		{"ErrSeedHashMismatch", ErrSeedHashMismatch, "seed content hash mismatch"},
+		{"ErrAlreadyExists", ErrAlreadyExists, "entity already exists"},
+		{"ErrQuarantined", ErrQuarantined, "pattern is quarantined"},
+		{"ErrSkillDeprecated", ErrSkillDeprecated, "skill is deprecated"},
+		{"ErrInvalidInput", ErrInvalidInput, "invalid input"},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			if c.err == nil {
+				t.Fatal("sentinel error is nil")
+			}
+			if !errors.Is(c.err, c.err) {
+				t.Errorf("errors.Is failed for %s", c.name)
+			}
+			if c.err.Error() != c.msg {
+				t.Errorf("Error() = %q, want %q", c.err.Error(), c.msg)
+			}
+		})
+	}
+}
+
+func TestSignalTransitionsComplete(t *testing.T) {
+	// Non-terminal states must be keys in ValidSignalTransitions.
+	// SignalResolved is a terminal state (no outgoing transitions) and is
+	// intentionally absent from the map.
+	nonTerminal := []string{
+		SignalRaised,
+		SignalAcknowledged,
+		SignalActing,
+		SignalMuted,
+		SignalFailed,
+	}
+	for _, state := range nonTerminal {
+		targets, ok := ValidSignalTransitions[state]
+		if !ok {
+			t.Errorf("non-terminal state %q missing from ValidSignalTransitions", state)
+			continue
+		}
+		if len(targets) == 0 {
+			t.Errorf("state %q maps to empty transition list", state)
+		}
+	}
+
+	// Resolved is terminal: it should not appear as a source key.
+	if _, ok := ValidSignalTransitions[SignalResolved]; ok {
+		t.Errorf("terminal state %q should not have outgoing transitions", SignalResolved)
+	}
+
+	// No state anywhere in the map may map to nil/empty.
+	for state, targets := range ValidSignalTransitions {
+		if len(targets) == 0 {
+			t.Errorf("state %q maps to empty/nil transition list", state)
+		}
+	}
+}
--- a/internal/knowledge/seed_test.go
+++ b/internal/knowledge/seed_test.go
@@ -0,0 +1,155 @@
+package knowledge
+
+import (
+	"crypto/sha256"
+	"encoding/hex"
+	"reflect"
+	"testing"
+)
+
+func TestContentHash(t *testing.T) {
+	t.Run("determinism", func(t *testing.T) {
+		a := contentHash("hello")
+		b := contentHash("hello")
+		if a != b {
+			t.Errorf("contentHash not deterministic: %q != %q", a, b)
+		}
+	})
+
+	t.Run("empty string known sha256", func(t *testing.T) {
+		got := contentHash("")
+		h := sha256.Sum256([]byte(""))
+		want := hex.EncodeToString(h[:])
+		if got != want {
+			t.Errorf("contentHash(\"\") = %q, want %q", got, want)
+		}
+	})
+
+	t.Run("different inputs different outputs", func(t *testing.T) {
+		if contentHash("a") == contentHash("b") {
+			t.Error("different inputs produced same hash")
+		}
+	})
+
+	t.Run("output is 64-char hex", func(t *testing.T) {
+		got := contentHash("anything")
+		if len(got) != 64 {
+			t.Errorf("len = %d, want 64", len(got))
+		}
+		for _, r := range got {
+			isHex := (r >= '0' && r <= '9') || (r >= 'a' && r <= 'f')
+			if !isHex {
+				t.Errorf("non-hex char %q in hash %q", r, got)
+				break
+			}
+		}
+	})
+}
+
+func TestStr(t *testing.T) {
+	cases := []struct {
+		name string
+		m    map[string]any
+		key  string
+		want string
+	}{
+		{"missing key", map[string]any{}, "nope", ""},
+		{"string value", map[string]any{"k": "v"}, "k", "v"},
+		{"int value", map[string]any{"k": 42}, "k", ""},
+		{"nil value", map[string]any{"k": nil}, "k", ""},
+		{"empty string", map[string]any{"k": ""}, "k", ""},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			got := str(c.m, c.key)
+			if got != c.want {
+				t.Errorf("str() = %q, want %q", got, c.want)
+			}
+		})
+	}
+}
+
+func TestStrSlice(t *testing.T) {
+	cases := []struct {
+		name string
+		m    map[string]any
+		key  string
+		want []string
+	}{
+		{"missing key", map[string]any{}, "tags", nil},
+		{"all strings", map[string]any{"tags": []any{"a", "b", "c"}}, "tags", []string{"a", "b", "c"}},
+		{"mixed types", map[string]any{"tags": []any{1, "a", true, "b"}}, "tags", []string{"a", "b"}},
+		{"empty array", map[string]any{"tags": []any{}}, "tags", []string{}},
+		{"nil elements filtered", map[string]any{"tags": []any{nil, "a", nil, "b"}}, "tags", []string{"a", "b"}},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			got := strSlice(c.m, c.key)
+			if len(got) != len(c.want) {
+				t.Errorf("len = %d, want %d (got %v)", len(got), len(c.want), got)
+				return
+			}
+			for i := range got {
+				if got[i] != c.want[i] {
+					t.Errorf("[%d] = %q, want %q", i, got[i], c.want[i])
+				}
+			}
+		})
+	}
+}
+
+func TestMapVal(t *testing.T) {
+	cases := []struct {
+		name string
+		m    map[string]any
+		key  string
+		want map[string]any
+	}{
+		{"missing key", map[string]any{}, "nope", nil},
+		{"present map", map[string]any{"k": map[string]any{"x": 1}}, "k", map[string]any{"x": 1}},
+		{"wrong type string", map[string]any{"k": "v"}, "k", nil},
+		{"nested map", map[string]any{"k": map[string]any{"a": map[string]any{"b": 2}}}, "k", map[string]any{"a": map[string]any{"b": 2}}},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			got := mapVal(c.m, c.key)
+			if !reflect.DeepEqual(got, c.want) {
+				t.Errorf("mapVal() = %v, want %v", got, c.want)
+			}
+		})
+	}
+}
+
+func TestToPGArray(t *testing.T) {
+	cases := []struct {
+		name string
+		tags []string
+		want string
+	}{
+		{"empty", []string{}, "{}"},
+		{"single", []string{"a"}, `{"a"}`},
+		{"multiple", []string{"a", "b"}, `{"a","b"}`},
+		{"nil", nil, "{}"},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			got := toPGArray(c.tags)
+			if got != c.want {
+				t.Errorf("toPGArray() = %q, want %q", got, c.want)
+			}
+		})
+	}
+
+	// Special chars: tags containing " or \ are NOT escaped by toPGArray.
+	// This is a latent bug — Postgres array literals require these to be
+	// backslash-escaped. Test documents current behavior so a fix is
+	// detectable. Should be fixed.
+	t.Run("special chars unescaped (current buggy behavior)", func(t *testing.T) {
+		got := toPGArray([]string{`a"b`, `c\d`})
+		// Current output: {"a"b","c\d"} — invalid Postgres array literal.
+		want := `{"a"b","c\d"}`
+		if got != want {
+			t.Errorf("toPGArray(special) = %q, want %q (if this changed, the escaping bug was fixed — update this test)", got, want)
+		}
+	})
+}
--- a/internal/learning/learning.go
+++ b/internal/learning/learning.go
@@ -83,27 +83,13 @@ func extractPatterns(ctx context.Context, pool *db.Pool, watermark time.Time) ti
 func processGroup(ctx context.Context, pool *db.Pool, q *sqlcgen.Queries,
 	appliesType, action string, items []sqlcgen.GetFeedbackAfterWatermarkRow) {

-	successCount := 0
-	failureCount := 0
-	for _, f := range items {
-		switch f.Outcome {
-		case "success":
-			successCount++
-		case "failure", "unexpected":
-			failureCount++
-		case "partial":
-			successCount++ // partial counts as half-success
-		}
-	}
+	successCount, failureCount := countOutcomes(items)
 	total := successCount + failureCount
 	if total == 0 {
 		return
 	}

-	// Compute Wilson score lower bound
-	confidence := wilsonLowerBound(float64(successCount), float64(total), 0.95)
-	// Cap by sample size: nothing looks confident before 5 samples
-	confidence = math.Min(confidence, float64(total)/5.0)
+	confidence := computeConfidence(successCount, failureCount)

 	// Get or create pattern — first look up existing entity, then upsert.
 	existing, err := q.GetPattern(ctx, sqlcgen.GetPatternParams{
@@ -148,7 +134,7 @@ func processGroup(ctx context.Context, pool *db.Pool, q *sqlcgen.Queries,
 		return
 	}

-	if pat.EvidenceCount >= 5 && pat.Confidence >= 0.7 && !pat.Quarantined {
+	if shouldValidate(int(pat.EvidenceCount), float64(pat.Confidence), pat.Quarantined) {
 		_ = q.UpdatePatternStatus(ctx, sqlcgen.UpdatePatternStatusParams{
 			EntityID: pat.EntityID,
 			Status:   "validated",
@@ -158,8 +144,7 @@ func processGroup(ctx context.Context, pool *db.Pool, q *sqlcgen.Queries,
 			"confidence", confidence, "samples", total)
 	}

-	// Anomaly check: >10 identical outcomes within 1h
-	if total > 10 {
+	if shouldQuarantine(total) {
 		_ = q.UpdatePatternQuarantine(ctx, sqlcgen.UpdatePatternQuarantineParams{
 			EntityID:    pat.EntityID,
 			Quarantined: true,
@@ -169,6 +154,45 @@ func processGroup(ctx context.Context, pool *db.Pool, q *sqlcgen.Queries,
 	}
 }

+// countOutcomes tallies feedback items into success and failure counts.
+// "partial" counts as a half-success (increments success).
+func countOutcomes(items []sqlcgen.GetFeedbackAfterWatermarkRow) (success, failure int) {
+	for _, f := range items {
+		switch f.Outcome {
+		case "success":
+			success++
+		case "failure", "unexpected":
+			failure++
+		case "partial":
+			success++
+		}
+	}
+	return success, failure
+}
+
+// computeConfidence calculates the Wilson score lower bound, capped by
+// sample size (nothing looks confident before 5 samples).
+func computeConfidence(success, failure int) float64 {
+	total := success + failure
+	if total == 0 {
+		return 0
+	}
+	confidence := wilsonLowerBound(float64(success), float64(total), 0.95)
+	return math.Min(confidence, float64(total)/5.0)
+}
+
+// shouldValidate returns true when a pattern has enough evidence and
+// confidence to be promoted from "hypothesized" to "validated".
+func shouldValidate(evidenceCount int, confidence float64, quarantined bool) bool {
+	return evidenceCount >= 5 && confidence >= 0.7 && !quarantined
+}
+
+// shouldQuarantine returns true when an anomaly burst is detected
+// (>10 identical outcomes, indicating a runaway loop rather than organic feedback).
+func shouldQuarantine(total int) bool {
+	return total > 10
+}
+
 // wilsonLowerBound computes the Wilson score interval lower bound.
 // Conservative estimate of success rate for small sample sizes.
 func wilsonLowerBound(success, total, z float64) float64 {
--- a/internal/learning/learning_test.go
+++ b/internal/learning/learning_test.go
@@ -0,0 +1,211 @@
+package learning
+
+import (
+	"math"
+	"testing"
+
+	"github.com/dtoro/oikos/internal/db/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)
+			}
+		})
+	}
+}
--- a/internal/notifier/notifier_test.go
+++ b/internal/notifier/notifier_test.go
@@ -0,0 +1,187 @@
+package notifier
+
+import (
+	"crypto/hmac"
+	"crypto/sha256"
+	"encoding/hex"
+	"fmt"
+	"regexp"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/google/uuid"
+)
+
+var hex64Re = regexp.MustCompile(`^[0-9a-f]{64}$`)
+
+func TestHashToken(t *testing.T) {
+	// sha256("") == e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
+	emptyHash := "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
+
+	t.Run("determinism same input same output", func(t *testing.T) {
+		a := hashToken("approval-token-123")
+		b := hashToken("approval-token-123")
+		if a != b {
+			t.Fatalf("hashToken not deterministic: %q vs %q", a, b)
+		}
+	})
+
+	t.Run("empty string known sha256", func(t *testing.T) {
+		got := hashToken("")
+		if got != emptyHash {
+			t.Fatalf("hashToken(\"\") = %q, want %q", got, emptyHash)
+		}
+	})
+
+	t.Run("different inputs different outputs", func(t *testing.T) {
+		a := hashToken("one")
+		b := hashToken("two")
+		if a == b {
+			t.Fatalf("hashToken collided for different inputs: %q", a)
+		}
+	})
+
+	t.Run("output is valid 64-char hex", func(t *testing.T) {
+		for _, in := range []string{"", "abc", "some-longer-token-value-xyz"} {
+			got := hashToken(in)
+			if !hex64Re.MatchString(got) {
+				t.Fatalf("hashToken(%q) = %q, not 64-char lowercase hex", in, got)
+			}
+			// also must decode cleanly to 32 bytes
+			b, err := hex.DecodeString(got)
+			if err != nil {
+				t.Fatalf("hashToken(%q) decode error: %v", in, err)
+			}
+			if len(b) != 32 {
+				t.Fatalf("hashToken(%q) decoded len = %d, want 32", in, len(b))
+			}
+		}
+	})
+}
+
+func TestGenerateApprovalToken(t *testing.T) {
+	id := uuid.New()
+
+	t.Run("output is 64-char hex", func(t *testing.T) {
+		tok := generateApprovalToken(id, "super-secret")
+		if !hex64Re.MatchString(tok) {
+			t.Fatalf("generateApprovalToken = %q, not 64-char lowercase hex", tok)
+		}
+		b, err := hex.DecodeString(tok)
+		if err != nil {
+			t.Fatalf("decode error: %v", err)
+		}
+		if len(b) != 32 {
+			t.Fatalf("decoded len = %d, want 32 (sha256)", len(b))
+		}
+	})
+
+	t.Run("empty secret falls back to dev secret no panic", func(t *testing.T) {
+		tok := generateApprovalToken(id, "")
+		if tok == "" {
+			t.Fatal("empty secret produced empty token")
+		}
+		if !hex64Re.MatchString(tok) {
+			t.Fatalf("empty-secret token %q not 64-char hex", tok)
+		}
+	})
+
+	// Non-determinism: time.Now().UnixNano() is embedded in the HMAC message,
+	// so two calls with identical inputs produce different tokens (unless the
+	// clock has nanosecond-identical reads, which we do not assert against).
+	t.Run("same inputs twice produce different tokens (time-based)", func(t *testing.T) {
+		a := generateApprovalToken(id, "stable-secret")
+		b := generateApprovalToken(id, "stable-secret")
+		if a == b {
+			// Not a hard failure (clock granularity), but document expectation.
+			t.Logf("note: two immediate calls returned identical token %q — clock resolution collapsed", a)
+		}
+	})
+
+	t.Run("different secrets produce different tokens", func(t *testing.T) {
+		a := generateApprovalToken(id, "secret-a")
+		b := generateApprovalToken(id, "secret-b")
+		if a == b {
+			t.Fatalf("different secrets produced same token %q", a)
+		}
+	})
+
+	// HMAC correctness: re-derive the token with the same secret + approvalID
+	// using a freshly captured timestamp window is impossible because we don't
+	// observe the embedded timestamp. Instead, verify the token is a valid
+	// HMAC-SHA256 by brute-forcing a small time window around now: reconstruct
+	// mac(secret, approvalID || ts) for ts in [now-N, now] and confirm one
+	// matches. This proves the token genuinely is an HMAC over (approvalID, ts)
+	// with the supplied secret.
+	t.Run("token is HMAC-SHA256 over approvalID+timestamp with secret", func(t *testing.T) {
+		secret := "hmac-verify-secret"
+		before := nowNanos()
+		tok := generateApprovalToken(id, secret)
+		after := nowNanos()
+
+		// The token's embedded ts is captured inside generateApprovalToken,
+		// which is called after `before` was sampled — so ts ∈ [before, after].
+		// Add a tiny ±band to absorb scheduler jitter on loaded runners.
+		lo := before - 10_000
+		hi := after + 10_000
+		matched := false
+		for ts := lo; ts <= hi; ts++ {
+			mac := hmac.New(sha256.New, []byte(secret))
+			mac.Write([]byte(id.String()))
+			mac.Write([]byte(formatInt(ts)))
+			cand := hex.EncodeToString(mac.Sum(nil))
+			if hmac.Equal([]byte(cand), []byte(tok)) {
+				matched = true
+				break
+			}
+		}
+		if !matched {
+			t.Fatalf("token %q did not match any HMAC in window [%d,%d]; not a valid HMAC-SHA256 over approvalID+ts", tok, lo, hi)
+		}
+	})
+
+	t.Run("empty secret HMAC uses dev fallback secret", func(t *testing.T) {
+		before := nowNanos()
+		tok := generateApprovalToken(id, "")
+		after := nowNanos()
+		dev := "dev-secret-do-not-use-in-prod"
+		lo := before - 10_000
+		hi := after + 10_000
+		matched := false
+		for ts := lo; ts <= hi; ts++ {
+			mac := hmac.New(sha256.New, []byte(dev))
+			mac.Write([]byte(id.String()))
+			mac.Write([]byte(formatInt(ts)))
+			cand := hex.EncodeToString(mac.Sum(nil))
+			if hmac.Equal([]byte(cand), []byte(tok)) {
+				matched = true
+				break
+			}
+		}
+		if !matched {
+			t.Fatalf("empty-secret token %q did not match dev-fallback HMAC", tok)
+		}
+	})
+
+	// sanity: token should not leak the secret in plaintext
+	t.Run("token does not contain secret substring", func(t *testing.T) {
+		secret := "leakcheck-secret-xyz"
+		tok := generateApprovalToken(id, secret)
+		if strings.Contains(tok, secret) {
+			t.Fatalf("token %q contains secret substring %q", tok, secret)
+		}
+	})
+}
+
+// nowNanos returns the current nanosecond count, matching the time source
+// used by generateApprovalToken (time.Now().UnixNano()).
+func nowNanos() int64 {
+	return time.Now().UnixNano()
+}
+
+// formatInt mirrors fmt.Sprintf("%d", ...) used by the production code so the
+// re-derivation in tests is byte-identical.
+func formatInt(n int64) string {
+	return fmt.Sprintf("%d", n)
+}
--- a/internal/policy/classify.go
+++ b/internal/policy/classify.go
@@ -92,21 +92,7 @@ func (c *Classifier) ClassifySignal(ctx context.Context, signalEntityID, targetE
 	}

 	// Determine route
-	route := "escalate"
-	autonomyCheck := ""
-
-	if globalAutoAct == "off" || globalAutoAct == "false" {
-		route = "escalate"
-		autonomyCheck = "blocked: global auto_act disabled"
-	} else if entityAutoAct == "true" {
-		route = "escalate"
-		autonomyCheck = "blocked: per-entity kill-switch"
-	} else if approvalRequired == "none" {
-		route = "auto-act"
-		autonomyCheck = "allowed"
-	} else {
-		autonomyCheck = "requires approval: " + approvalRequired
-	}
+	route, autonomyCheck := determineRoute(globalAutoAct, entityAutoAct, approvalRequired)

 	// Compute blast radius
 	blastRadius := computeBlastRadius(ctx, c.DB, targetEntityID)
@@ -136,6 +122,21 @@ func (c *Classifier) ClassifySignal(ctx context.Context, signalEntityID, targetE
 	}, nil
 }

+// determineRoute evaluates autonomy settings and approval requirements to
+// decide whether a signal should auto-act, escalate, or hold for approval.
+func determineRoute(globalAutoAct, entityAutoAct, approvalRequired string) (route, autonomyCheck string) {
+	if globalAutoAct == "off" || globalAutoAct == "false" {
+		return "escalate", "blocked: global auto_act disabled"
+	}
+	if entityAutoAct == "true" {
+		return "escalate", "blocked: per-entity kill-switch"
+	}
+	if approvalRequired == "none" {
+		return "auto-act", "allowed"
+	}
+	return "escalate", "requires approval: " + approvalRequired
+}
+
 // computeBlastRadius traverses relationships to find affected entities.
 func computeBlastRadius(ctx context.Context, dbc interface {
 	Query(ctx context.Context, sql string, args ...any) (pgx.Rows, error)
--- a/internal/policy/classify_test.go
+++ b/internal/policy/classify_test.go
@@ -0,0 +1,62 @@
+package policy
+
+import "testing"
+
+func TestDetermineRoute(t *testing.T) {
+	tests := []struct {
+		name             string
+		globalAutoAct    string
+		entityAutoAct    string
+		approvalRequired string
+		wantRoute        string
+		wantCheck        string
+	}{
+		{
+			"global auto_act off blocks everything",
+			"off", "", "none",
+			"escalate", "blocked: global auto_act disabled",
+		},
+		{
+			"global auto_act false blocks everything",
+			"false", "", "none",
+			"escalate", "blocked: global auto_act disabled",
+		},
+		{
+			"per-entity kill-switch blocks",
+			"on", "true", "none",
+			"escalate", "blocked: per-entity kill-switch",
+		},
+		{
+			"approval none auto-acts",
+			"on", "", "none",
+			"auto-act", "allowed",
+		},
+		{
+			"approval required escalates",
+			"on", "", "operator",
+			"escalate", "requires approval: operator",
+		},
+		{
+			"approval none with empty global defaults to auto-act",
+			"", "", "none",
+			"auto-act", "allowed",
+		},
+		{
+			"global on, no entity kill, approval confirmation",
+			"on", "", "confirmation",
+			"escalate", "requires approval: confirmation",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			route, check := determineRoute(tt.globalAutoAct, tt.entityAutoAct, tt.approvalRequired)
+			if route != tt.wantRoute {
+				t.Errorf("route = %q, want %q", route, tt.wantRoute)
+			}
+			if check != tt.wantCheck {
+				t.Errorf("autonomyCheck = %q, want %q", check, tt.wantCheck)
+			}
+		})
+	}
+}
--- a/internal/scheduler/scheduler_test.go
+++ b/internal/scheduler/scheduler_test.go
@@ -0,0 +1,208 @@
+package scheduler
+
+import (
+	"testing"
+)
+
+func TestParsePingLatency(t *testing.T) {
+	cases := []struct {
+		name string
+		out  []byte
+		want float64
+	}{
+		{
+			name: "linux rtt format",
+			out:  []byte("PING host (1.2.3.4): 56 data bytes\n--- host ping statistics ---\n5 packets transmitted, 5 received, 0% packet loss\nrtt min/avg/max/mdev = 0.1/2.5/5.0/1.2 ms\n"),
+			want: 2.5,
+		},
+		{
+			name: "macos round-trip format",
+			out:  []byte("PING host (1.2.3.4): 56 data bytes\n--- host ping statistics ---\n5 packets transmitted, 5 received, 0% packet loss\nround-trip min/avg/max/stddev = 0.1/2.5/5.0/1.2 ms\n"),
+			want: 2.5,
+		},
+		{
+			name: "no match empty string",
+			out:  []byte(""),
+			want: 0,
+		},
+		{
+			name: "malformed number in avg slot",
+			out:  []byte("rtt min/avg/max/mdev = 0.1/abc/5.0/1.2 ms\n"),
+			want: 0,
+		},
+		{
+			name: "truly empty input nil",
+			out:  nil,
+			want: 0,
+		},
+		{
+			name: "linux integer avg",
+			out:  []byte("rtt min/avg/max/mdev = 1/3/5/0.5 ms\n"),
+			want: 3.0,
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			got := parsePingLatency(tc.out)
+			if got != tc.want {
+				t.Fatalf("parsePingLatency(%q) = %v, want %v", tc.out, got, tc.want)
+			}
+		})
+	}
+}
+
+func TestAllowlistedScript(t *testing.T) {
+	cases := []struct {
+		name string
+		in   string
+		want bool
+	}{
+		{name: "cpu_check.sh", in: "cpu_check.sh", want: true},
+		{name: "disk_usage_check.sh", in: "disk_usage_check.sh", want: true},
+		{name: "hyphen allowed", in: "foo-bar.sh", want: true},
+		{name: "underscore allowed", in: "foo_bar.sh", want: true},
+		{name: "uppercase rejected", in: "Foo.sh", want: false},
+		{name: "bare .sh rejected (no name)", in: ".sh", want: false},
+		{name: "path traversal rejected", in: "../etc/passwd", want: false},
+		{name: "empty rejected", in: "", want: false},
+		// foo.sh.sh: regex ^[a-z][a-z0-9_-]+\.sh$ — the [a-z0-9_-]+ cannot
+		// cross the first '.', so after matching "foo.sh" the trailing ".sh"
+		// breaks the $ anchor → no match.
+		{name: "doubled .sh.sh rejected", in: "foo.sh.sh", want: false},
+		{name: "wrong extension rejected", in: "foo.txt", want: false},
+		{name: "single char name rejected (needs 2+)", in: "a.sh", want: false},
+		{name: "two char name accepted", in: "ab.sh", want: true},
+		{name: "digit after first char", in: "a1.sh", want: true},
+		{name: "leading digit rejected", in: "1foo.sh", want: false},
+		{name: "dot in middle rejected", in: "foo.bar.sh", want: false},
+		{name: "space rejected", in: "foo bar.sh", want: false},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			got := allowlistedScript(tc.in)
+			if got != tc.want {
+				t.Fatalf("allowlistedScript(%q) = %v, want %v", tc.in, got, tc.want)
+			}
+		})
+	}
+}
+
+func TestEvaluateSeverity(t *testing.T) {
+	cases := []struct {
+		name       string
+		kind       string
+		signalKind string
+		config     []byte
+		metrics    map[string]float64
+		want       string
+	}{
+		{
+			name:       "empty config down signal",
+			kind:       "ping",
+			signalKind: "down",
+			config:     nil,
+			metrics:    map[string]float64{},
+			want:       "critical",
+		},
+		{
+			name:       "empty config high_temp signal",
+			kind:       "ssh-script",
+			signalKind: "high_temp",
+			config:     nil,
+			metrics:    map[string]float64{},
+			want:       "warning",
+		},
+		{
+			name:       "crit only exceeded",
+			kind:       "ssh-script",
+			signalKind: "high_temp",
+			config:     []byte(`{"temp":{"crit":90}}`),
+			metrics:    map[string]float64{"temp": 95},
+			want:       "critical",
+		},
+		{
+			name:       "warn only exceeded",
+			kind:       "ssh-script",
+			signalKind: "high_temp",
+			config:     []byte(`{"temp":{"warn":80}}`),
+			metrics:    map[string]float64{"temp": 85},
+			want:       "warning",
+		},
+		{
+			name:       "warn and crit, warn exceeded only",
+			kind:       "ssh-script",
+			signalKind: "high_temp",
+			config:     []byte(`{"temp":{"warn":80,"crit":90}}`),
+			metrics:    map[string]float64{"temp": 85},
+			want:       "warning",
+		},
+		{
+			name:       "warn and crit, crit exceeded",
+			kind:       "ssh-script",
+			signalKind: "high_temp",
+			config:     []byte(`{"temp":{"warn":80,"crit":90}}`),
+			metrics:    map[string]float64{"temp": 95},
+			want:       "critical",
+		},
+		{
+			name:       "metric below thresholds falls through to warning",
+			kind:       "ssh-script",
+			signalKind: "high_temp",
+			config:     []byte(`{"temp":{"warn":80,"crit":90}}`),
+			metrics:    map[string]float64{"temp": 70},
+			want:       "warning",
+		},
+		{
+			name:       "metric below thresholds falls through to down critical",
+			kind:       "ping",
+			signalKind: "down",
+			config:     []byte(`{"ping_latency_ms":{"warn":100,"crit":200}}`),
+			metrics:    map[string]float64{"ping_latency_ms": 50},
+			want:       "critical",
+		},
+		{
+			name:       "crit zero skipped falls through",
+			kind:       "ssh-script",
+			signalKind: "high_temp",
+			config:     []byte(`{"temp":{"crit":0}}`),
+			metrics:    map[string]float64{"temp": 95},
+			want:       "warning",
+		},
+		{
+			name:       "metric not in thresholds ignored",
+			kind:       "ssh-script",
+			signalKind: "high_temp",
+			config:     []byte(`{"temp":{"warn":80,"crit":90}}`),
+			metrics:    map[string]float64{"cpu": 99},
+			want:       "warning",
+		},
+		{
+			name:       "equal to warn triggers warning",
+			kind:       "ssh-script",
+			signalKind: "high_temp",
+			config:     []byte(`{"temp":{"warn":80,"crit":90}}`),
+			metrics:    map[string]float64{"temp": 80},
+			want:       "warning",
+		},
+		{
+			name:       "equal to crit triggers critical",
+			kind:       "ssh-script",
+			signalKind: "high_temp",
+			config:     []byte(`{"temp":{"warn":80,"crit":90}}`),
+			metrics:    map[string]float64{"temp": 90},
+			want:       "critical",
+		},
+	}
+
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			got := evaluateSeverity(tc.kind, tc.signalKind, tc.config, tc.metrics)
+			if got != tc.want {
+				t.Fatalf("evaluateSeverity(%q, %q, %s, %v) = %q, want %q",
+					tc.kind, tc.signalKind, tc.config, tc.metrics, got, tc.want)
+			}
+		})
+	}
+}
--- a/plans/2026-07-17-codebase-review-and-cleanup.md
+++ b/plans/2026-07-17-codebase-review-and-cleanup.md
@@ -428,7 +428,7 @@ the gitignore comment); `build` target ensures `bin/` exists; `clean` removes `b
 | R4 | Split `phase3.go` (2627 lines) into per-resource files; refactor `newServer` (708 lines) to a tool registry | M | Medium | ✅ done |
 | R5 | Rewrite `.agents/domains/knowledge/schema.md` + `.agents/shared/llm-wiki.md` for the DB-native model; delete/deprecate root `inventory.yaml` | M | Low | ✅ done |
 | R6 | Inject desktop `version` from `VERSION` via ldflags; fix `Makefile` `BINARY` colliding with `oikos/` dir | S | Low | ✅ done |
-| R7 | Add tests for `learning` (80% gate), `actuator`, `scheduler`, `domain`, `notifier`, `knowledge` | L | Low |
+| R7 | Add tests for `learning` (80% gate), `actuator`, `scheduler`, `domain`, `notifier`, `knowledge` | L | Low | ✅ partial — pure unit tests added for all 6 packages; remaining coverage needs integration tests (`make test-db`) |
 | R8 | Add `eslint`+`prettier`+`vitest` to `web/`; wire `svelte-check`+`tsc` into CI; add `web/` CI job | M | Low | ✅ done |
 | R9 | Define `OikosEvent` discriminated union; eliminate ~15 `any` sites in web | S | Low |
 | R10 | Replace `<svelte:component>` in `ActivityTimeline.svelte:103`; fix `state_referenced_locally` warnings | S | Low |