Merge pull request 'Bug: make simulate routes with an empty seed set, so a green run proves less than it looks' (#124) from task/465-bug-make-simulate-routes-with-an-empty into master

cmd/mavend/simulator_test.go

@@ -1043,3 +1043,26 @@ func TestSimulatorRefusesBackwardsSteps(t *testing.T) {
 		t.Errorf("the clock moved to %s on a refused step, it must stay at 09:00", got)
 	}
 }
+
+// TestSimulatorRoutesWithTheDeployedSeeds — the scenarios must replay against
+// the classifier the deploy runs, not an empty one.
+//
+// They did not. The seed path was relative to the working directory, which is
+// cmd/mavend under `go test`, so every file failed to open and the whole
+// simulator scored three green scenarios with zero examples loaded (Vikunja
+// #465). The count is asserted rather than logged, because a silent zero is
+// exactly the failure that hid here for as long as it did.
+func TestSimulatorRoutesWithTheDeployedSeeds(t *testing.T) {
+	cls := router.NewClassifier(router.NewHashEmbedder(1024))
+	seedClassifier(cls)
+	total := 0
+	for _, intent := range cls.Intents() {
+		total += len(cls.Examples(intent))
+	}
+	if total == 0 {
+		t.Fatalf("no seed examples loaded from %s — the simulator would route on nothing", seedPath())
+	}
+	if len(cls.Intents()) != 7 {
+		t.Fatalf("seeded %d intents, want all 7", len(cls.Intents()))
+	}
+}

cmd/mavend/voicewire.go

@@ -398,11 +398,34 @@ func buildRouter(emb router.Embedder, acts router.ActMatcher, threshold float64,
 	})
 }
 
-// seedDir is the directory containing intent seed files. Each file is named
-// <intent>.txt and contains one training example per line (blank lines and
-// lines starting with # are ignored). Relative to the working directory.
+// seedDir is the directory containing intent seed files, relative to the repo
+// root. Each file is named <intent>.txt and holds one training example per
+// line (blank lines and lines starting with # are ignored).
 const seedDir = "models/seeds"
 
+// seedPath resolves seedDir against the working directory, walking up until it
+// finds it. The daemon runs from the repo root and the first candidate hits.
+//
+// A test does not: `go test ./cmd/mavend/` runs with the working directory at
+// cmd/mavend, so every open failed and the simulator scenarios replayed a whole
+// scripted day against a classifier holding zero examples (Vikunja #465). They
+// passed, which is the part that matters — a green simulator was not exercising
+// the routing the deploy runs, and a regression in the seed set could not have
+// shown up there.
+//
+// Bounded at five levels, so a daemon started somewhere without the seeds logs
+// the same failure it always did rather than walking to the filesystem root.
+func seedPath() string {
+	dir := seedDir
+	for i := 0; i < 5; i++ {
+		if st, err := os.Stat(dir); err == nil && st.IsDir() {
+			return dir
+		}
+		dir = filepath.Join("..", dir)
+	}
+	return seedDir
+}
+
 // seedClassifier floors the embedded examples so the cold-boot path
 // doesn't return ErrNoIntents. Loads examples from seedDir — one file per
 // intent (act.txt, reminder.txt, fact.txt, note.txt, query.txt). When the
@@ -427,11 +450,11 @@ func seedClassifier(c *router.Classifier) {
 		}
 		total += n
 	}
-	log.Printf("voice: loaded %d seed examples from %s", total, seedDir)
+	log.Printf("voice: loaded %d seed examples from %s", total, seedPath())
 }
 
 func loadSeedFile(c *router.Classifier, intent router.Intent) (int, error) {
-	path := filepath.Join(seedDir, string(intent)+".txt")
+	path := filepath.Join(seedPath(), string(intent)+".txt")
 	f, err := os.Open(path)
 	if err != nil {
 		return 0, fmt.Errorf("open %s: %w", path, err)