{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "pipetree pipeline",
  "description": "A pipetree pipeline config. Every top-level key except `defaults`, `systems` and `notifications` is a layer.",
  "type": "object",
  "properties": {
    "defaults": {
      "$ref": "#/$defs/Defaults"
    },
    "notifications": {
      "$ref": "#/$defs/Notifications"
    },
    "systems": {
      "type": "object",
      "description": "Systems by name. Tables reference them in `source.system`.",
      "additionalProperties": {
        "$ref": "#/$defs/System"
      }
    }
  },
  "additionalProperties": {
    "$ref": "#/$defs/Layer"
  },
  "$defs": {
    "Defaults": {
      "properties": {
        "system_columns": {
          "default": [
            "_inserted_at",
            "_updated_at",
            "_is_deleted",
            "_execution_id",
            "_source_system"
          ],
          "description": "Names of the audit columns. Read from the config but not used to select columns: pipetree stamps its fixed audit set on every table.",
          "items": {
            "type": "string"
          },
          "title": "System Columns",
          "type": "array"
        },
        "schema_policy": {
          "default": "evolve",
          "description": "Schema drift policy for every table that does not set its own.",
          "enum": [
            "evolve",
            "fail",
            "ignore"
          ],
          "title": "Schema Policy",
          "type": "string"
        }
      },
      "title": "Defaults",
      "type": "object"
    },
    "EmailNotification": {
      "additionalProperties": false,
      "properties": {
        "endpoint": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "$ref": "#/$defs/SecretRef"
            }
          ],
          "description": "Endpoint of the Azure Communication Services resource, `https://<resource>.communication.azure.com`. A literal or `{secret: name}`.",
          "title": "Endpoint"
        },
        "sender": {
          "description": "Sender address of a domain connected to the resource, for example `DoNotReply@<guid>.azurecomm.net`.",
          "title": "Sender",
          "type": "string"
        },
        "to": {
          "description": "Recipient addresses. At least one.",
          "items": {
            "type": "string"
          },
          "minItems": 1,
          "title": "To",
          "type": "array"
        },
        "on": {
          "const": "failure",
          "default": "failure",
          "description": "When to send. `failure` mails a run in which a table failed or was marked upstream_failed. No mail for a successful run.",
          "title": "On",
          "type": "string"
        }
      },
      "required": [
        "endpoint",
        "sender",
        "to"
      ],
      "title": "EmailNotification",
      "type": "object"
    },
    "Layer": {
      "title": "Layer",
      "description": "A layer: a namespace for tables, not an execution barrier.",
      "type": "object",
      "properties": {
        "tables": {
          "type": "object",
          "description": "Tables by name.",
          "additionalProperties": {
            "$ref": "#/$defs/Table"
          }
        }
      },
      "required": [
        "tables"
      ]
    },
    "Merge": {
      "additionalProperties": false,
      "properties": {
        "sequence_by": {
          "description": "Source columns that order the versions of a key. The highest value wins.",
          "items": {
            "type": "string"
          },
          "title": "Sequence By",
          "type": "array"
        },
        "delete_when": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Spark SQL expression, true for source rows that are deletes.",
          "title": "Delete When"
        },
        "delete_mode": {
          "default": "soft",
          "description": "What a delete row does: soft marks the row deleted, hard removes it (scd1 only), ignore drops delete rows from the batch.",
          "enum": [
            "soft",
            "hard",
            "ignore"
          ],
          "title": "Delete Mode",
          "type": "string"
        },
        "ignore_columns": {
          "description": "Columns whose changes alone are written in place: no new scd2 version and no audit column update.",
          "items": {
            "type": "string"
          },
          "title": "Ignore Columns",
          "type": "array"
        },
        "snapshot": {
          "default": false,
          "description": "The batch is the complete current state of the source (scd1 and scd2 only). An active key of the table that is not in the batch is handled like a delete row, following delete_mode.",
          "title": "Snapshot",
          "type": "boolean"
        },
        "snapshot_max_missing_ratio": {
          "default": 0.5,
          "description": "With snapshot: the table fails and nothing is written when more than this share of its active keys is missing from the batch.",
          "maximum": 1,
          "minimum": 0,
          "title": "Snapshot Max Missing Ratio",
          "type": "number"
        },
        "snapshot_allow_empty": {
          "default": false,
          "description": "With snapshot: an empty batch is an error unless this is true (then every active key counts as missing, subject to snapshot_max_missing_ratio).",
          "title": "Snapshot Allow Empty",
          "type": "boolean"
        }
      },
      "title": "Merge",
      "type": "object"
    },
    "Notifications": {
      "additionalProperties": false,
      "properties": {
        "email": {
          "anyOf": [
            {
              "$ref": "#/$defs/EmailNotification"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Email a failed run through Azure Communication Services, authenticated with a token credential (no connection string)."
        }
      },
      "title": "Notifications",
      "type": "object"
    },
    "SecretRef": {
      "description": "A `{secret: name}` reference, resolved later through the Platform seam.",
      "properties": {
        "secret": {
          "description": "Name of the secret, resolved by the platform at run time.",
          "title": "Secret",
          "type": "string"
        }
      },
      "required": [
        "secret"
      ],
      "title": "SecretRef",
      "type": "object"
    },
    "Source": {
      "additionalProperties": false,
      "properties": {
        "system": {
          "description": "Name of a system declared under `systems`.",
          "title": "System",
          "type": "string"
        },
        "object": {
          "description": "What to read from the system: a table, entity or file name the reader understands.",
          "title": "Object",
          "type": "string"
        }
      },
      "required": [
        "system",
        "object"
      ],
      "title": "Source",
      "type": "object"
    },
    "System": {
      "additionalProperties": true,
      "description": "A declared system. Connection properties beyond `type` vary per source\ntype (host, database, landing_path, ...), so they're captured as extras\nrather than hardcoded here - `pipetree.sources` owns interpreting them.",
      "properties": {
        "type": {
          "description": "Source type: csv, json, parquet, sqlserver, kusto, storage_stream, d365_export, synapse_link or custom. Other keys are passed to the source reader.",
          "title": "Type",
          "type": "string"
        }
      },
      "required": [
        "type"
      ],
      "title": "System",
      "type": "object"
    },
    "Table": {
      "additionalProperties": false,
      "properties": {
        "table_schema": {
          "description": "Schema the table is created in. Defaults to the layer name.",
          "title": "Table Schema",
          "type": "string"
        },
        "source": {
          "anyOf": [
            {
              "$ref": "#/$defs/Source"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Read from a declared system. Exactly one of `source` and `logic`."
        },
        "logic": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Path to a .sql or .py file, relative to the config. Exactly one of `source` and `logic`.",
          "title": "Logic"
        },
        "business_key": {
          "description": "Columns that identify a row. Required for scd1, scd2 and unknown_member.",
          "items": {
            "type": "string"
          },
          "title": "Business Key",
          "type": "array"
        },
        "strategy": {
          "description": "How the result is written to the table.",
          "enum": [
            "scd2",
            "scd1",
            "replace",
            "append"
          ],
          "title": "Strategy",
          "type": "string"
        },
        "merge": {
          "$ref": "#/$defs/Merge",
          "description": "Options for the scd1 and scd2 strategies."
        },
        "depends_on": {
          "anyOf": [
            {
              "const": "auto",
              "type": "string"
            },
            {
              "items": {
                "type": "string"
              },
              "type": "array"
            }
          ],
          "description": "`auto` reads the logic file; a list names parent tables (fqn or unambiguous bare name).",
          "title": "Depends On"
        },
        "unknown_member": {
          "default": false,
          "description": "Seed one row with a sentinel business key for facts to resolve a missing key to.",
          "title": "Unknown Member",
          "type": "boolean"
        },
        "schema_policy": {
          "description": "Schema drift policy for this table. Defaults to `defaults.schema_policy`.",
          "enum": [
            "evolve",
            "fail",
            "ignore"
          ],
          "title": "Schema Policy",
          "type": "string"
        },
        "surrogate_key": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "description": "Name of a generated integer key column (scd1 and scd2 only). The unknown member gets -1.",
          "title": "Surrogate Key"
        },
        "tags": {
          "description": "Labels for selecting tables with `pipetree run --tag`. Lowercase letters, digits, `-` and `_`, starting with a letter or digit, at most 40 characters, no duplicates within a table.",
          "items": {
            "type": "string"
          },
          "title": "Tags",
          "type": "array"
        }
      },
      "required": [
        "strategy"
      ],
      "title": "Table",
      "type": "object",
      "description": "One table. Exactly one of `source` and `logic`.",
      "oneOf": [
        {
          "required": [
            "source"
          ]
        },
        {
          "required": [
            "logic"
          ]
        }
      ]
    }
  }
}