Generate an Apache Flink SQL streaming job from a natural-language request and a schema, then RUN it on real Flink against sample data and return the verified SQL plus its actual output (or the Flink error). Use whenever the user wants a Flink streaming job (windowed aggregates, top-N, dedup, interval/temporal joins, filters) — it produces jobs that provably run, unlike hand-written SQL. Supply representative sample rows.

Discover a Kafka topic's schema by sampling its messages, returning a schema + sample rows ready to pass to generate_flink_job. Use when the user references a real topic and you don't have its schema. Requires a reachable Kafka broker with the topic populated.

Produce a deployable topic->topic Flink job: INSERT INTO a Kafka sink topic SELECT ... The SELECT logic is verified on the sample data by running it on real Flink; the returned deployable_sql is the full pipeline (upsert-kafka sink for updating jobs). Use when the user wants to WRITE results to a Kafka topic, not just query them.