Maven/cmd/mavend/decisiontrace_test.go

package main

import (
	"context"
	"strings"
	"testing"
	"time"

	"github.com/kami/maven/internal/decision"
	"github.com/kami/maven/internal/ipc"
	"github.com/kami/maven/internal/memory"
	"github.com/kami/maven/internal/router"
	"github.com/kami/maven/internal/tool"
	"github.com/kami/maven/internal/voice"
)

// traceHandler — a handler with the decision ring wired, the same shape the
// daemon builds in wireVoice.
func traceHandler(t *testing.T, ring *decision.Ring) *reactiveHandler {
	t.Helper()
	st := newTestStore(t)
	api := ipc.NewStoreAPI(st)
	now := time.Now()
	emb := router.NewHashEmbedder(1024)
	return &reactiveHandler{
		api:       api,
		recall:    recallWiring{embedder: emb, memStore: memory.NewInMemoryStore()},
		router:    buildRouter(emb, tool.NewMatcher(api), 0.55, nil),
		replier:   voice.NewStubReplier(),
		now:       func() time.Time { return now },
		dataStore: st,
		decisions: ring,
	}
}

// findClaim — the first claim for a claimant, or nil.
func findClaim(rec *decision.Record, claimant string) *decision.Claim {
	for i := range rec.Claims {
		if rec.Claims[i].Claimant == claimant {
			return &rec.Claims[i]
		}
	}
	return nil
}

// TestTurnRecordNamesWinnerAndLosers — the point of V-564. A turn a stage-0
// grammar claims must leave a record naming that grammar as the winner, naming
// a pre-route resolver that declined, and naming the routing engines that were
// never reached at all. The last of those is the fact the hardcoded ordering
// hides: "classifier" absent from the record and "classifier" never asked read
// the same to a human, and only one of them is the truth.
func TestTurnRecordNamesWinnerAndLosers(t *testing.T) {
	ring := decision.NewRing()
	h := traceHandler(t, ring)

	reply := h.handleText(context.Background(), "web", "сколько сейчас времени")
	if reply == "" {
		t.Fatal("turn produced no reply")
	}

	recs := ring.Recent(5)
	if len(recs) != 1 {
		t.Fatalf("want 1 record, got %d", len(recs))
	}
	rec := recs[0]
	if rec.Utterance != "сколько сейчас времени" {
		t.Errorf("utterance = %q", rec.Utterance)
	}
	if !strings.HasPrefix(rec.Winner, "stage0:") {
		t.Errorf("want a stage-0 grammar as the winner, got %q", rec.Winner)
	}

	// A loser that examined the turn: the confirm resolver ran first and had
	// nothing pending.
	confirm := findClaim(rec, "confirm")
	if confirm == nil || confirm.Outcome != decision.Declined {
		t.Errorf("confirm claim = %+v, want a decline", confirm)
	}

	// A loser that never looked: stage 0 answered, so neither routing engine
	// was reached.
	for _, name := range []string{"llm-router", "classifier"} {
		c := findClaim(rec, name)
		if c != nil && c.Outcome == decision.Won {
			t.Errorf("%s cannot have won a stage-0 turn: %+v", name, c)
		}
	}

	// And every rung of the ladder below the winner is named, not omitted.
	for _, name := range preRouteLadder {
		if findClaim(rec, name) == nil {
			t.Errorf("ladder rung %q is missing from the record", name)
		}
	}
}

// TestRecordingDoesNotChangeTheReply — instrumentation, so a turn with the ring
// wired and the same turn without it must answer identically. If this ever
// fails, a claim site is doing more than noting.
func TestRecordingDoesNotChangeTheReply(t *testing.T) {
	for _, utt := range []string{
		"сколько сейчас времени",
		"запиши что я пил воду",
		"что у меня сегодня",
	} {
		withRing := traceHandler(t, decision.NewRing()).handleText(context.Background(), "web", utt)
		without := traceHandler(t, nil).handleText(context.Background(), "web", utt)
		if withRing != without {
			t.Errorf("%q: recorded reply %q != unrecorded %q", utt, withRing, without)
		}
	}
}

// TestQueryChainRecordsWhoWasNeverAsked — a query source below the claimant is
// never consulted, and the record must say so rather than leave it out. This is
// the arm that would have explained the Rome misroute in one read.
func TestQueryChainRecordsWhoWasNeverAsked(t *testing.T) {
	ring := decision.NewRing()
	h := traceHandler(t, ring)
	h.handleText(context.Background(), "web", "что у меня сегодня")

	rec := ring.Recent(1)[0]
	var asked, never int
	for _, c := range rec.Claims {
		if c.Stage != decision.StageQuery {
			continue
		}
		if c.Outcome == decision.NeverAsked {
			never++
		} else {
			asked++
		}
	}
	if asked == 0 {
		t.Fatal("no query source reported at all")
	}
	if never == 0 {
		t.Fatal("no query source was recorded as never asked; the chain cannot have run to the end")
	}
	if got := len(querySourceNames()); asked+never != got {
		t.Errorf("record covers %d of %d query sources", asked+never, got)
	}
}

// TestTurnDecisionsFnConvertsTheRing — the IPC read path. Nil when voice was
// never wired, because a box with no turns is an empty page and not an error.
func TestTurnDecisionsFnConvertsTheRing(t *testing.T) {
	if fn := turnDecisionsFn(nil); fn != nil {
		t.Error("no wiring should mean no reader")
	}
	ring := decision.NewRing()
	h := traceHandler(t, ring)
	h.handleText(context.Background(), "web", "сколько сейчас времени")

	fn := turnDecisionsFn(&voiceWiring{handler: h})
	if fn == nil {
		t.Fatal("wired handler produced no reader")
	}
	out := fn(10)
	if len(out) != 1 || out[0].Winner == "" || len(out[0].Claims) == 0 {
		t.Fatalf("conversion lost the record: %+v", out)
	}
}