-- Behavision server schema, migration 001.
--
-- Two rules run through all of it:
--
-- 1. `client_id` is on every table, even where a join could derive it. That is
--    what makes row-level security possible later, and it means a cross-tenant
--    leak requires a deliberately wrong WHERE clause rather than a forgotten
--    join condition.
--
-- 2. Face embeddings are biometric personal data under GDPR and India's DPDP.
--    Template inversion is an established attack — published results
--    reconstruct a recognisable face from an ArcFace embedding — so the
--    "it's just numbers" defence does not hold. They live in their own table,
--    are hard-deleted rather than soft-deleted, and every read of them is
--    expected to be tenant-scoped.

BEGIN;

CREATE EXTENSION IF NOT EXISTS vector;
CREATE EXTENSION IF NOT EXISTS pgcrypto;

-- ============================================================ tenancy ======

CREATE TABLE clients (
    id          uuid PRIMARY KEY DEFAULT gen_random_uuid(),
    slug        text NOT NULL UNIQUE,          -- used in MQTT topics
    name        text NOT NULL,
    active      boolean NOT NULL DEFAULT true,
    created_at  timestamptz NOT NULL DEFAULT now(),
    CONSTRAINT clients_slug_format CHECK (slug ~ '^[a-z0-9][a-z0-9-]{1,30}[a-z0-9]$')
);
COMMENT ON COLUMN clients.slug IS
    'Appears in MQTT topics as bv/<client.slug>.<site.slug>/... and is enforced '
    'by the broker ACL, so it must stay stable and URL/topic safe.';

CREATE TABLE sites (
    id          uuid PRIMARY KEY DEFAULT gen_random_uuid(),
    client_id   uuid NOT NULL REFERENCES clients(id) ON DELETE CASCADE,
    slug        text NOT NULL,
    name        text NOT NULL,
    timezone    text NOT NULL DEFAULT 'UTC',   -- footfall is reported in local time
    address     text NOT NULL DEFAULT '',
    active      boolean NOT NULL DEFAULT true,
    created_at  timestamptz NOT NULL DEFAULT now(),
    UNIQUE (client_id, slug),
    CONSTRAINT sites_slug_format CHECK (slug ~ '^[a-z0-9][a-z0-9-]{1,30}[a-z0-9]$')
);

-- One row per store PC. Exists so that "this site reported nothing" can be
-- distinguished from "this site is switched off" — without it, an agent that
-- has been unplugged for a week looks identical to a shop with no customers,
-- which is a silent hole in the customer's own report.
CREATE TABLE agents (
    id               uuid PRIMARY KEY DEFAULT gen_random_uuid(),
    client_id        uuid NOT NULL REFERENCES clients(id) ON DELETE CASCADE,
    site_id          uuid NOT NULL REFERENCES sites(id) ON DELETE CASCADE,
    mqtt_username    text NOT NULL UNIQUE,     -- '<client.slug>.<site.slug>'
    agent_version    text NOT NULL DEFAULT '',
    engine_version   text NOT NULL DEFAULT '',
    -- Which encoder actually loaded. Embeddings from different models are
    -- numerically incompatible, so this decides whether a site's vectors can
    -- be compared with anything else at all.
    recognition_model text NOT NULL DEFAULT '',
    last_heartbeat_at timestamptz,
    last_event_at     timestamptz,
    created_at        timestamptz NOT NULL DEFAULT now(),
    UNIQUE (site_id)
);
CREATE INDEX agents_heartbeat_idx ON agents (last_heartbeat_at);

-- ============================================================ people =======

-- A person, scoped to ONE client.
--
-- Deliberately not global. Linking the same face across unrelated clients
-- would build a cross-company biometric tracking network: legally
-- indefensible in every jurisdiction that matters, and commercially dead on
-- arrival — no retailer accepts their customer data enriching a competitor's.
-- Within one client, sites DO share, which is the feature: a customer
-- recognised at the Chennai store is the same record at the Bangalore store.
CREATE TABLE visitors (
    id            uuid PRIMARY KEY DEFAULT gen_random_uuid(),
    client_id     uuid NOT NULL REFERENCES clients(id) ON DELETE CASCADE,
    label         text NOT NULL DEFAULT '',    -- 'Visitor 12' until staff name them
    first_seen_at timestamptz NOT NULL DEFAULT now(),
    last_seen_at  timestamptz,
    visit_count   integer NOT NULL DEFAULT 0,
    -- Erasure request received. The embeddings are removed outright (see
    -- below); this row is kept only long enough to stop the same face being
    -- re-enrolled, and is purged by retention.
    deleted_at    timestamptz,
    created_at    timestamptz NOT NULL DEFAULT now()
);
CREATE INDEX visitors_client_idx    ON visitors (client_id) WHERE deleted_at IS NULL;
CREATE INDEX visitors_last_seen_idx ON visitors (client_id, last_seen_at DESC);

-- Biometric templates. The most sensitive table in the system.
--
-- ON DELETE CASCADE from visitors is doing real work: a GDPR/DPDP erasure
-- request must actually destroy the template, not flag it. There is no
-- soft-delete column here on purpose.
CREATE TABLE visitor_embeddings (
    id             uuid PRIMARY KEY DEFAULT gen_random_uuid(),
    visitor_id     uuid NOT NULL REFERENCES visitors(id) ON DELETE CASCADE,
    client_id      uuid NOT NULL REFERENCES clients(id) ON DELETE CASCADE,
    -- Same rule as the edge: vectors from different encoders occupy different
    -- spaces and must never be compared. Every query filters on this.
    model          text NOT NULL,
    embedding      vector(512) NOT NULL,
    quality        real NOT NULL DEFAULT 0,
    source_site_id uuid REFERENCES sites(id) ON DELETE SET NULL,
    created_at     timestamptz NOT NULL DEFAULT now()
);
CREATE INDEX visitor_embeddings_lookup_idx
    ON visitor_embeddings (client_id, model);
CREATE INDEX visitor_embeddings_visitor_idx
    ON visitor_embeddings (visitor_id);
-- No ANN (HNSW/IVFFlat) index yet, deliberately. Every search here MUST be
-- filtered by client_id, and pgvector's ANN indexes under-return when combined
-- with a selective filter — it walks the graph globally and then discards
-- other tenants' neighbours, so a client with few vectors can silently get
-- zero results. Exact search is microseconds at this scale (measured on the
-- edge: 100k vectors, 21.9 ms). Add an index when measurement says to, not
-- before.

-- What staff collect on the mobile form. Separate from `visitors` because it
-- is ordinary PII with a different lifecycle and a different access rule:
-- plenty of people should read a customer's name who should never touch a
-- biometric template.
CREATE TABLE visitor_profiles (
    id            uuid PRIMARY KEY DEFAULT gen_random_uuid(),
    visitor_id    uuid NOT NULL REFERENCES visitors(id) ON DELETE CASCADE,
    client_id     uuid NOT NULL REFERENCES clients(id) ON DELETE CASCADE,
    full_name     text NOT NULL DEFAULT '',
    phone         text NOT NULL DEFAULT '',
    email         text NOT NULL DEFAULT '',
    gender        text NOT NULL DEFAULT '',
    date_of_birth date,
    notes         text NOT NULL DEFAULT '',
    collected_by  uuid,                        -- app_users.id, set by the API
    collected_at  timestamptz NOT NULL DEFAULT now(),
    updated_at    timestamptz NOT NULL DEFAULT now(),
    UNIQUE (visitor_id)
);
CREATE INDEX visitor_profiles_phone_idx ON visitor_profiles (client_id, phone)
    WHERE phone <> '';

-- Consent is a record, not a flag: "when, how, and for what" is what an
-- auditor asks for, and a boolean cannot answer it. Revocation is a second
-- timestamp rather than a delete, so the withdrawal itself stays provable.
CREATE TABLE consents (
    id          uuid PRIMARY KEY DEFAULT gen_random_uuid(),
    visitor_id  uuid NOT NULL REFERENCES visitors(id) ON DELETE CASCADE,
    client_id   uuid NOT NULL REFERENCES clients(id) ON DELETE CASCADE,
    scope       text NOT NULL,                 -- 'biometric' | 'marketing' | ...
    method      text NOT NULL,                 -- 'in_store_form' | 'signage' | ...
    granted_at  timestamptz NOT NULL DEFAULT now(),
    revoked_at  timestamptz,
    collected_by uuid,
    evidence    jsonb NOT NULL DEFAULT '{}'::jsonb
);
CREATE INDEX consents_visitor_idx ON consents (visitor_id, scope);

-- ============================================================ activity =====

CREATE TABLE visits (
    id             uuid PRIMARY KEY DEFAULT gen_random_uuid(),
    client_id      uuid NOT NULL REFERENCES clients(id) ON DELETE CASCADE,
    site_id        uuid NOT NULL REFERENCES sites(id) ON DELETE CASCADE,
    visitor_id     uuid REFERENCES visitors(id) ON DELETE CASCADE,
    -- The agent's own event id. MQTT delivery is at-least-once by design, so
    -- the consumer MUST be idempotent: a redelivered event after a reconnect
    -- would otherwise double a store's footfall, which is the one number the
    -- customer is paying for.
    source_event_id text NOT NULL,
    occurred_at    timestamptz NOT NULL,
    received_at    timestamptz NOT NULL DEFAULT now(),
    camera_id      text NOT NULL DEFAULT '',
    is_new_visitor boolean NOT NULL DEFAULT false,
    similarity     real,
    quality        real,
    -- gender/age/emotion. jsonb because the estimators change and their
    -- outputs differ (integer age vs bucketed range).
    attributes     jsonb NOT NULL DEFAULT '{}'::jsonb,
    -- The object key, NOT a URL. A stored public URL is permanent and
    -- unrevocable; a key is presigned on read, expires, and can be deleted.
    image_key      text NOT NULL DEFAULT '',
    UNIQUE (client_id, source_event_id)
);
CREATE INDEX visits_site_time_idx    ON visits (site_id, occurred_at DESC);
CREATE INDEX visits_client_time_idx  ON visits (client_id, occurred_at DESC);
CREATE INDEX visits_visitor_idx      ON visits (visitor_id, occurred_at DESC);

-- Purchases are decoupled from how they were entered. Manual entry on the
-- mobile form today, a POS integration later, same table — `source` is the
-- only thing that differs, so adding POS is not a migration.
CREATE TABLE purchases (
    id          uuid PRIMARY KEY DEFAULT gen_random_uuid(),
    client_id   uuid NOT NULL REFERENCES clients(id) ON DELETE CASCADE,
    site_id     uuid NOT NULL REFERENCES sites(id) ON DELETE CASCADE,
    visitor_id  uuid REFERENCES visitors(id) ON DELETE SET NULL,
    visit_id    uuid REFERENCES visits(id) ON DELETE SET NULL,
    -- numeric, never float: money in a float loses cents, and this feeds the
    -- conversion report the customer judges the product by.
    amount      numeric(14,2) NOT NULL DEFAULT 0,
    currency    char(3) NOT NULL DEFAULT 'INR',
    items       jsonb NOT NULL DEFAULT '[]'::jsonb,
    source      text NOT NULL DEFAULT 'manual',  -- 'manual' | 'pos' | 'import'
    external_ref text NOT NULL DEFAULT '',
    recorded_by uuid,
    occurred_at timestamptz NOT NULL DEFAULT now(),
    created_at  timestamptz NOT NULL DEFAULT now()
);
CREATE INDEX purchases_site_time_idx ON purchases (site_id, occurred_at DESC);
CREATE INDEX purchases_visitor_idx   ON purchases (visitor_id);

-- ============================================================ access =======

CREATE TABLE app_users (
    id            uuid PRIMARY KEY DEFAULT gen_random_uuid(),
    client_id     uuid REFERENCES clients(id) ON DELETE CASCADE,  -- NULL = platform admin
    email         text NOT NULL,
    password_hash text NOT NULL,
    full_name     text NOT NULL DEFAULT '',
    role          text NOT NULL DEFAULT 'staff',  -- 'owner'|'manager'|'staff'|'admin'
    active        boolean NOT NULL DEFAULT true,
    last_login_at timestamptz,
    created_at    timestamptz NOT NULL DEFAULT now(),
    CONSTRAINT app_users_role_known
        CHECK (role IN ('owner', 'manager', 'staff', 'admin'))
);
-- Case-insensitive uniqueness, per client. Two clients may each have a
-- user with the same address; one client may not have two. coalesce() is
-- needed because a NULL client_id (platform admin) does not compare equal
-- to itself in a unique index, which would let duplicates through.
CREATE UNIQUE INDEX app_users_email_idx
    ON app_users (coalesce(client_id, '00000000-0000-0000-0000-000000000000'::uuid),
                  lower(email));

-- Every read of a biometric template and every export is worth a row here.
-- If a client ever asks "who looked at my customers", an audit trail is the
-- only answer that is not a guess.
CREATE TABLE audit_log (
    id         bigserial PRIMARY KEY,
    client_id  uuid REFERENCES clients(id) ON DELETE SET NULL,
    actor_id   uuid,
    actor_kind text NOT NULL DEFAULT 'user',   -- 'user' | 'agent' | 'system'
    action     text NOT NULL,
    entity     text NOT NULL DEFAULT '',
    entity_id  text NOT NULL DEFAULT '',
    detail     jsonb NOT NULL DEFAULT '{}'::jsonb,
    at         timestamptz NOT NULL DEFAULT now()
);
CREATE INDEX audit_log_client_time_idx ON audit_log (client_id, at DESC);

COMMIT;