# .github/workflows/data-quality.yml
name: Data Quality

on: [push, pull_request]

jobs:
  data-quality:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Validate data quality
        uses: aegis-dq/aegis-dq@v0.7.0
        with:
          rules-file: rules.yaml
          db: data/warehouse.duckdb
          anthropic-api-key: ${{ secrets.ANTHROPIC_API_KEY }}

      - name: Validate data quality (offline)
        uses: aegis-dq/aegis-dq@v0.7.0
        with:
          rules-file: rules.yaml
          db: data/warehouse.duckdb
          no-llm: 'true'

      - name: Validate data quality
        id: dq
        uses: aegis-dq/aegis-dq@v0.7.0
        with:
          rules-file: rules.yaml

      - name: Post summary
        run: echo "Pass rate: ${{ steps.dq.outputs.pass-rate }}%"

╭──────────────────────────────────────────────────────╮
│ Aegis DQ  —  RetailCo E-commerce Demo                │
│ LLM: amazon.nova-pro-v1:0 via AWS Bedrock            │
╰──────────────────────────────────────────────────────╯

✓ Pipeline complete in 7.1s · 12 rules · $0.0056 LLM cost

╭──────────────── Validation Summary ─────────────────╮
│  Rules checked  │  12                               │
│  Passed         │  1   │  Failed  │  11             │
│  Pass rate      │  8%  │  Cost    │  $0.005576      │
╰─────────────────────────────────────────────────────╯

LLM Diagnoses
  orders_customer_fk  →  Order placed with customer_id=99 that does not exist.
                         Likely cause: customer deleted or test record not cleaned up.

  products_sku_unique →  Duplicate SKU-001 — two products share the same identifier.
                         Likely cause: duplicate import from supplier feed.

Remediation SQL (LLM-generated)
  orders_status_valid          UPDATE orders SET status = 'SHIPPED' WHERE status = 'DISPATCHED';
  products_price_positive      UPDATE products SET price = ABS(price) WHERE price < 0;
  products_stock_non_negative  UPDATE products SET stock_quantity = 0 WHERE stock_quantity < 0;

You (Hermes chat)
     │
     ▼
Hermes — memory, scheduling, multi-channel delivery
     │  MCP
     ▼
Aegis DQ — rules engine, LLM diagnosis, audit trail
     │
     ▼
Your warehouse + Your LLM

pip install aegis-dq

mcp_servers:
  aegis:
    command: aegis
    args: [mcp]
    env:
      ANTHROPIC_API_KEY: "${ANTHROPIC_API_KEY}"

# pipeline.yaml
name: orders-dq
rules: ./rules.yaml
database: ./warehouse.duckdb
kb:
  - ./policy.md     # business rules, SLAs, compliance docs
  - ./schema.md
goal: |
  Run all rules. For every failure explain the business impact,
  likely root cause, and a concrete remediation step.

Load the pipeline at pipeline.yaml and run it.

pip install aegis-dq

pip install aegis-dq

import duckdb

con = duckdb.connect("demo.db")
con.execute("""
    CREATE TABLE orders AS
    SELECT i AS order_id, 'placed' AS status, i * 9.99 AS revenue
    FROM range(1, 10001) t(i)
""")
# introduce some bad data
con.execute("UPDATE orders SET order_id = NULL WHERE order_id % 200 = 0")
con.execute("UPDATE orders SET revenue = -5.00 WHERE order_id % 500 = 0")
con.close()

export ANTHROPIC_API_KEY=sk-ant-...

# Generate rules from table schema alone
aegis generate orders --db demo.db --output rules.yaml

# Or point it at a policy doc and get business validation rules too
aegis generate orders --db demo.db --kb docs/orders_policy.md --output rules.yaml

aegis run rules.yaml --db demo.db

aegis run rules.yaml --db demo.db --no-llm

rules (Python / YAML)
    │
    ▼
  plan ──► parallel_table ──► reconcile ──► remediate ──► report
                 │
         ┌──────────────────┐
         │  per table:      │
         │  execute         │
         │  classify        │
         │  diagnose        │  ← concurrent across all tables
         │  rca             │
         └──────────────────┘

rules:
  - apiVersion: aegis.dev/v1
    kind: DataQualityRule
    metadata:
      id: orders_revenue_non_negative
      severity: critical
      owner: revenue-team
      tags: [revenue, validity]
    scope:
      warehouse: duckdb
      table: orders
    logic:
      type: sql_expression
      expression: "revenue >= 0"

# Schema-aware structural rules (not_null, between, unique, accepted_values...)
aegis generate orders --db warehouse.duckdb --output orders_rules.yaml

aegis generate orders \
  --db warehouse.duckdb \
  --kb docs/orders_policy.md \
  --output orders_rules.yaml

# orders_policy.md
- status must be one of: placed, confirmed, shipped, delivered, cancelled
- amount must be greater than 0; refunds are handled in a separate table
- customer_id must reference a valid customer (no test accounts: id > 1000)
- order_date must not be in the future
- discount_pct must be between 0 and 0.5 (max 50% discount)

aegis run rules.yaml --llm openai --llm-model gpt-4o
aegis run rules.yaml --llm ollama --llm-model llama3.2
aegis run rules.yaml --llm bedrock --llm-model amazon.nova-pro-v1:0