feat: split worker into separate binary (cmd/worker)

Kafka consumers and WorkerPool are moved out of the server process into
a dedicated worker binary. Server now handles HTTP + SSE only; worker
handles Kafka consumption and AI processing.

- cmd/worker/main.go + init.go: new binary with minimal config
  (DATABASE_URL, OPENAI_API_KEY, KAFKA_BROKERS)
- cmd/server: remove WorkerPool, paidConsumer, freeConsumer
- Dockerfile: builds both server and worker binaries
- docker-compose.yml: add worker service
- Makefile: add run-worker and docker-logs-worker targets
- README.md: document worker startup and env vars

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

backend/cmd/server/providers.go

@@ -197,14 +197,6 @@ func newKafkaProducer(appConfig *config.Config) (*kafka.Producer, error) {
 	return kafka.NewProducer(appConfig.KafkaBrokers)
 }
 
-func newPaidKafkaConsumer(appConfig *config.Config) (*kafka.Consumer, error) {
-	return kafka.NewConsumer(appConfig.KafkaBrokers, "dish-recognition-workers", recognition.TopicPaid)
-}
-
-func newFreeKafkaConsumer(appConfig *config.Config) (*kafka.Consumer, error) {
-	return kafka.NewConsumer(appConfig.KafkaBrokers, "dish-recognition-workers", recognition.TopicFree)
-}
-
 // ---------------------------------------------------------------------------
 // Interface assertions (compile-time checks)
 // ---------------------------------------------------------------------------