feat(insights): Phase B schema + service skeletons

PR1 of Phase B per docs/superpowers/specs/2026-04-28-phase-b-insights-alerts-design.md.
Lays the foundation that PRs 2-10 will fill in with behaviour.

Schema (migration 0014):
- alerts table with rule-engine fields (rule_id, severity, link,
  entity_type/id, fingerprint, fired/dismissed/acknowledged/resolved
  timestamps, jsonb metadata). Partial-unique fingerprint index keeps
  one open row per (port, rule, entity); separate indexes power
  severity-filtered and time-ordered queries.
- analytics_snapshots (port_id, metric_id) -> jsonb cache + computedAt
  for the 15-min recurring refresh.
- expenses: duplicate_of self-FK, dedup_scanned_at, ocr_status/raw/
  confidence; partial index on (port, vendor, amount, date) where
  duplicate_of IS NULL drives the dedup heuristic.
- audit_logs.search_text: GENERATED ALWAYS tsvector over
  action+entity_type+entity_id+user_id, GIN-indexed (drizzle can't
  model GENERATED ALWAYS in TS yet, so the migration appends manual
  ALTER + the GIN index).

Service skeletons in src/lib/services/:
- alerts.service.ts: fingerprintFor, reconcileAlertsForPort (upsert +
  auto-resolve), dismiss, acknowledge, listAlertsForPort.
- alert-rules.ts: RULE_REGISTRY of 10 rule evaluators (currently no-op);
  PR2 fills in the bodies.
- analytics.service.ts: readSnapshot/writeSnapshot with 15-min TTL +
  no-op compute* stubs for the four chart series; PR3 fills behavior.
- expense-dedup.service.ts: scanForDuplicates + markBestDuplicate
  using the partial dedup index. PR8 wires the BullMQ trigger.
- expense-ocr.service.ts: OcrResult/OcrLineItem types + ocrReceipt
  stub. PR9 wires Claude Vision (Haiku 4.5 + ephemeral system-prompt
  cache).
- audit-search.service.ts: tsvector @@ plainto_tsquery + cursor
  pagination on (createdAt, id). PR10 wires the admin UI.

tsc clean, lint clean, vitest 675/675 (one unrelated AES random-output
flake passes solo).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Matt Ciaccio
2026-04-28 14:43:01 +02:00
parent f1ed2a5f87
commit e77d55ac50
13 changed files with 10451 additions and 10 deletions

View File

@@ -0,0 +1,56 @@
CREATE TABLE "alerts" (
"id" text PRIMARY KEY NOT NULL,
"port_id" text NOT NULL,
"rule_id" text NOT NULL,
"severity" text NOT NULL,
"title" text NOT NULL,
"body" text,
"link" text NOT NULL,
"entity_type" text,
"entity_id" text,
"fingerprint" text NOT NULL,
"fired_at" timestamp with time zone DEFAULT now() NOT NULL,
"dismissed_at" timestamp with time zone,
"dismissed_by" text,
"acknowledged_at" timestamp with time zone,
"acknowledged_by" text,
"resolved_at" timestamp with time zone,
"metadata" jsonb DEFAULT '{}'::jsonb
);
--> statement-breakpoint
CREATE TABLE "analytics_snapshots" (
"port_id" text NOT NULL,
"metric_id" text NOT NULL,
"computed_at" timestamp with time zone DEFAULT now() NOT NULL,
"data" jsonb NOT NULL
);
--> statement-breakpoint
ALTER TABLE "expenses" ADD COLUMN "duplicate_of" text;--> statement-breakpoint
ALTER TABLE "expenses" ADD COLUMN "dedup_scanned_at" timestamp with time zone;--> statement-breakpoint
ALTER TABLE "expenses" ADD COLUMN "ocr_status" text DEFAULT 'pending';--> statement-breakpoint
ALTER TABLE "expenses" ADD COLUMN "ocr_raw" jsonb;--> statement-breakpoint
ALTER TABLE "expenses" ADD COLUMN "ocr_confidence" numeric;--> statement-breakpoint
ALTER TABLE "audit_logs" ADD COLUMN "search_text" "tsvector";--> statement-breakpoint
ALTER TABLE "alerts" ADD CONSTRAINT "alerts_port_id_ports_id_fk" FOREIGN KEY ("port_id") REFERENCES "public"."ports"("id") ON DELETE cascade ON UPDATE no action;--> statement-breakpoint
ALTER TABLE "alerts" ADD CONSTRAINT "alerts_dismissed_by_user_id_fk" FOREIGN KEY ("dismissed_by") REFERENCES "public"."user"("id") ON DELETE no action ON UPDATE no action;--> statement-breakpoint
ALTER TABLE "alerts" ADD CONSTRAINT "alerts_acknowledged_by_user_id_fk" FOREIGN KEY ("acknowledged_by") REFERENCES "public"."user"("id") ON DELETE no action ON UPDATE no action;--> statement-breakpoint
ALTER TABLE "analytics_snapshots" ADD CONSTRAINT "analytics_snapshots_port_id_ports_id_fk" FOREIGN KEY ("port_id") REFERENCES "public"."ports"("id") ON DELETE cascade ON UPDATE no action;--> statement-breakpoint
CREATE UNIQUE INDEX "idx_alerts_fingerprint_open" ON "alerts" USING btree ("port_id","fingerprint") WHERE resolved_at IS NULL;--> statement-breakpoint
CREATE INDEX "idx_alerts_port_fired" ON "alerts" USING btree ("port_id","fired_at");--> statement-breakpoint
CREATE INDEX "idx_alerts_port_severity_open" ON "alerts" USING btree ("port_id","severity") WHERE resolved_at IS NULL AND dismissed_at IS NULL;--> statement-breakpoint
CREATE UNIQUE INDEX "idx_analytics_pk" ON "analytics_snapshots" USING btree ("port_id","metric_id");--> statement-breakpoint
ALTER TABLE "expenses" ADD CONSTRAINT "expenses_duplicate_of_expenses_id_fk" FOREIGN KEY ("duplicate_of") REFERENCES "public"."expenses"("id") ON DELETE set null ON UPDATE no action;--> statement-breakpoint
CREATE INDEX "idx_expenses_dedup" ON "expenses" USING btree ("port_id","establishment_name","amount","expense_date") WHERE duplicate_of IS NULL;--> statement-breakpoint
-- audit_logs.search_text needs to be GENERATED ALWAYS (drizzle can't model that
-- in TS yet); drop the empty column and re-add it as the generated form.
ALTER TABLE "audit_logs" DROP COLUMN "search_text";--> statement-breakpoint
ALTER TABLE "audit_logs" ADD COLUMN "search_text" tsvector
GENERATED ALWAYS AS (
to_tsvector('simple',
coalesce("action", '') || ' ' ||
coalesce("entity_type", '') || ' ' ||
coalesce("entity_id", '') || ' ' ||
coalesce("user_id", '')
)
) STORED;--> statement-breakpoint
CREATE INDEX "idx_audit_search" ON "audit_logs" USING gin("search_text");