fluid-core/conformance/suite/slice_test.go

package suite

import (
	"context"
	"strings"
	"testing"

	"github.com/tegwick/fluid-core/internal/contract"
	"github.com/tegwick/fluid-core/internal/fitness"
	"github.com/tegwick/fluid-core/internal/intent"
	"github.com/tegwick/fluid-core/internal/policy"
	"github.com/tegwick/fluid-core/internal/promotion"
)

// TestFirstVerticalSlice is the whole point of the conformance suite.
//
// ArchitectureBlueprint.md section 50 lists eleven things the first FLUID
// deployment must demonstrate, and says plainly what success means:
//
//	The first success criterion is not autonomous coding.
//	It is proving that the revision-experiment-fitness loop works cleanly
//	and safely.
//
// This test runs all eleven with no human steps.
func TestFirstVerticalSlice(t *testing.T) {
	h := New(t)
	loop := RunFullLoop(t, h)

	// 1. Two deterministic revisions.
	for _, id := range []contract.RevisionID{"R-1", "R-2"} {
		if _, err := h.Registry.Revision(id); err != nil {
			t.Fatalf("revision %s is not published: %v", id, err)
		}
	}

	// 2. Explicit revision routing.
	policy, err := h.Registry.Policy()
	if err != nil {
		t.Fatalf("no routing policy: %v", err)
	}
	if policy.DefaultRevision == "" {
		t.Error("the routing policy names no default revision")
	}

	// 3. Telemetry.
	telemetry := h.Telemetry()
	if len(telemetry) == 0 {
		t.Fatal("no telemetry recorded")
	}

	// 4. One consumer cohort dimension.
	var sawCohort bool
	for _, ev := range telemetry {
		if ev.Cohort != nil && *ev.Cohort != "" {
			sawCohort = true
			break
		}
	}
	if !sawCohort {
		t.Error("no telemetry carries a cohort assignment")
	}

	// 5. Pressure detection.
	if loop.Pressure == "" {
		t.Fatal("no pressure was detected")
	}

	// 6. A hypothesis, linked to that pressure.
	hyp, err := h.Hypotheses.Get(context.Background(), loop.Hypothesis)
	if err != nil {
		t.Fatal(err)
	}
	if hyp.Explanation.Claim == "" {
		t.Error("the hypothesis offers no explanation")
	}

	// 7. A candidate revision, claimed by that hypothesis.
	var claimsCandidate bool
	for _, r := range hyp.CandidateRevisionRefs {
		if r == loop.Candidate {
			claimsCandidate = true
		}
	}
	if !claimsCandidate {
		t.Errorf("the hypothesis does not claim %s", loop.Candidate)
	}

	// 8. A controlled 90/10 experiment.
	exp, err := h.Experiments.Get(context.Background(), loop.Experiment)
	if err != nil {
		t.Fatal(err)
	}
	if exp.Allocation["control"] != 0.9 || exp.Allocation["candidate"] != 0.1 {
		t.Errorf("allocation was %v, want a 90/10 split", exp.Allocation)
	}

	// 9. Fitness comparison.
	if loop.Evaluation.Verdict != fitness.VerdictSucceeded {
		t.Fatalf("verdict %s: %v", loop.Evaluation.Verdict, loop.Evaluation.Reasons)
	}
	primary := loop.Evaluation.PrimaryResults()
	if len(primary) != 1 {
		t.Fatalf("expected one primary metric, got %d", len(primary))
	}
	// The candidate should show the reduction the hypothesis predicted.
	if primary[0].Current >= primary[0].Baseline {
		t.Errorf("requests per task did not fall: %v -> %v",
			primary[0].Baseline, primary[0].Current)
	}
	t.Logf("requests per completed task: %.2f -> %.2f (target %.2f)",
		primary[0].Baseline, primary[0].Current, *primary[0].Target)

	// 10. Promotion.
	if loop.Decision.Outcome != promotion.Promote {
		t.Errorf("decision was %s, want PROMOTE", loop.Decision.Outcome)
	}
	if loop.Decision.Override {
		t.Error("the promotion was an override; the evidence should have carried it")
	}

	// 11. A complete audit trail.
	//
	// Every stage of the loop must have left a reconstructable record. This is
	// the assertion that would fail first if any part of the framework started
	// deciding things without saying so.
	events := h.Events(string(loop.Candidate))
	required := map[string]bool{
		"SIGN_PASSED":               false,
		"POLICY_CHECK_PASSED":       false,
		"INTENT_BOUND":              false,
		"REVISION_PUBLISHED":        false,
		"PROMOTION_DECIDED_PROMOTE": false,
	}
	for _, ev := range events {
		if _, tracked := required[ev.EventType]; tracked {
			required[ev.EventType] = true
		}
	}
	for name, seen := range required {
		if !seen {
			t.Errorf("the audit trail is missing %s", name)
		}
	}

	// The pressure, hypothesis and experiment each left their own trail.
	for _, entity := range []string{
		string(loop.Pressure), string(loop.Hypothesis), string(loop.Experiment),
	} {
		if len(h.Events(entity)) == 0 {
			t.Errorf("%s left no audit events", entity)
		}
	}

	t.Logf("slice complete: %s -> %s -> %s -> %s (%s)",
		loop.Pressure, loop.Hypothesis, loop.Experiment, loop.Candidate, loop.Decision.Outcome)
}

// TestSliceIsReproducible runs the loop twice over fresh state and requires the
// same conclusion both times.
//
// A loop whose verdict depended on run order would be measuring the harness
// rather than the interface.
func TestSliceIsReproducible(t *testing.T) {
	var verdicts []fitness.Verdict
	var ratios []float64

	for i := 0; i < 2; i++ {
		h := New(t)
		loop := RunFullLoop(t, h)
		verdicts = append(verdicts, loop.Evaluation.Verdict)
		ratios = append(ratios, loop.Evaluation.PrimaryResults()[0].Current)
	}

	if verdicts[0] != verdicts[1] {
		t.Errorf("verdict varied between runs: %s then %s", verdicts[0], verdicts[1])
	}
	if ratios[0] != ratios[1] {
		t.Errorf("measured ratio varied between runs: %v then %v", ratios[0], ratios[1])
	}
}

// TestSliceRefusesPromotionWithoutEvidence confirms the loop cannot be
// short-circuited: the same candidate, promoted without its experiment, is
// refused.
func TestSliceRefusesPromotionWithoutEvidence(t *testing.T) {
	h := New(t)

	descriptor, err := h.Registry.Revision("R-2")
	if err != nil {
		t.Fatal(err)
	}
	governing, err := h.Intents.GoverningIntent(context.Background(), "R-2")
	if err != nil {
		t.Fatal(err)
	}

	limits := policy.DefaultLimits()
	limits.AllowedAdaptationClasses = append(limits.AllowedAdaptationClasses,
		contract.AdaptationClassContract)
	limits.RequiredMode = intent.ModeExperimental

	_, err = promotion.NewController(h.Store, policy.NewGate(limits)).Decide(context.Background(), promotion.Request{
		Revision: "R-2",
		Outcome:  promotion.Promote,
		Reason:   "it looks better",
		Actor:    Operator,
		GateInput: &policy.Input{
			Descriptor:            descriptor,
			GoverningMode:         governing.Mode,
			AdaptationClasses:     []contract.AdaptationClass{contract.AdaptationClassContract},
			RequestedTrafficShare: 0.2,
			Approved:              true,
			ApprovedBy:            &Operator,
		},
	})
	if err == nil {
		t.Fatal("a candidate was promoted with no fitness evidence")
	}
	if !strings.Contains(err.Error(), "fitness") {
		t.Errorf("refusal does not cite missing evidence: %v", err)
	}
}