Behavision: face recognition for retail, edge to head office

Five components that ship as one product:

- behavision/  the recognition engine. RTSP ingest, YuNet detection, IoU
               tracking, ArcFace embeddings, a FAISS/SQLite gallery, and a
               FastAPI dashboard. Identity is decided once per TRACK from an
               average of at least three embeddings, never per frame.
- agent/       the Go edge agent: supervises the engine, holds a durable
               spool, and drains it to MQTT. Nothing is acked before the
               broker confirms.
- desktop/     the shop PC application (Wails + React + tray).
- server/      the cloud API, MQTT consumer, reports and assistant.
- web/         platform.loyaly.ai, the head-office app, embedded in the
               server binary.

The gallery stores 512-float embeddings and timestamps - no images unless
`app.store_faces` is switched on. Those embeddings are biometric personal
data under GDPR and India's DPDP: template inversion reconstructs a
recognisable face from an ArcFace vector, so data/behavision.db is treated
as a biometric database and DELETE /api/visitors/{id} is a real erasure.

CLAUDE.md carries the reasoning behind every non-obvious decision here,
including the ones that were measured and the ones that were wrong first.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HViLj9gYNRtSr7YVZmW5sn

agent/pkg/bridge/engine_client.go

@@ -0,0 +1,56 @@
+package bridge
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+	"time"
+)
+
+// EngineEmbeddings reads templates from the local engine's API.
+type EngineEmbeddings struct {
+	Base     string
+	User     string
+	Password string
+	Client   *http.Client
+}
+
+func NewEngineEmbeddings(base, user, password string) *EngineEmbeddings {
+	return &EngineEmbeddings{
+		Base: strings.TrimRight(base, "/"), User: user, Password: password,
+		Client: &http.Client{Timeout: 10 * time.Second},
+	}
+}
+
+func (e *EngineEmbeddings) Embedding(ctx context.Context, id int64) ([]float32, string, error) {
+	url := fmt.Sprintf("%s/api/identities/%d/embedding", e.Base, id)
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
+	if err != nil {
+		return nil, "", err
+	}
+	if e.User != "" {
+		req.SetBasicAuth(e.User, e.Password)
+	}
+	resp, err := e.Client.Do(req)
+	if err != nil {
+		return nil, "", err
+	}
+	defer resp.Body.Close()
+	if resp.StatusCode != http.StatusOK {
+		return nil, "", fmt.Errorf("engine returned %s", resp.Status)
+	}
+	var body struct {
+		Model     string    `json:"model"`
+		Embedding []float32 `json:"embedding"`
+	}
+	if err := json.NewDecoder(io.LimitReader(resp.Body, 1<<20)).Decode(&body); err != nil {
+		return nil, "", err
+	}
+	if len(body.Embedding) == 0 {
+		return nil, "", fmt.Errorf("engine returned an empty embedding")
+	}
+	return body.Embedding, body.Model, nil
+}