Initialize governed Dataflow module

src/govoplan_dataflow/backend/schemas.py

@@ -0,0 +1,161 @@
+from __future__ import annotations
+
+import math
+from datetime import datetime
+from typing import Any, Literal
+
+from pydantic import BaseModel, ConfigDict, Field, field_validator
+
+
+PipelineStatus = Literal["draft", "active", "archived"]
+EditorMode = Literal["graph", "sql"]
+DiagnosticSeverity = Literal["info", "warning", "error"]
+
+
+class GraphPosition(BaseModel):
+    x: float
+    y: float
+
+    @field_validator("x", "y")
+    @classmethod
+    def finite_coordinate(cls, value: float) -> float:
+        if not math.isfinite(value):
+            raise ValueError("Graph coordinates must be finite")
+        return value
+
+
+class GraphNode(BaseModel):
+    id: str = Field(min_length=1, max_length=100, pattern=r"^[A-Za-z0-9_.:-]+$")
+    type: str = Field(min_length=1, max_length=80)
+    label: str = Field(min_length=1, max_length=200)
+    position: GraphPosition
+    config: dict[str, Any] = Field(default_factory=dict)
+
+
+class GraphEdge(BaseModel):
+    id: str = Field(min_length=1, max_length=120, pattern=r"^[A-Za-z0-9_.:-]+$")
+    source: str = Field(min_length=1, max_length=100)
+    target: str = Field(min_length=1, max_length=100)
+    source_port: str = Field(default="output", min_length=1, max_length=80)
+    target_port: str = Field(default="input", min_length=1, max_length=80)
+
+
+class PipelineGraph(BaseModel):
+    schema_version: Literal[1] = 1
+    nodes: list[GraphNode] = Field(default_factory=list, max_length=100)
+    edges: list[GraphEdge] = Field(default_factory=list, max_length=200)
+
+
+class DataflowDiagnostic(BaseModel):
+    severity: DiagnosticSeverity
+    code: str
+    message: str
+    node_id: str | None = None
+    field: str | None = None
+
+
+class PipelineRevisionResponse(BaseModel):
+    model_config = ConfigDict(from_attributes=True)
+
+    id: str
+    revision: int
+    schema_version: int
+    graph: PipelineGraph
+    sql_text: str | None
+    editor_mode: EditorMode
+    content_hash: str
+    created_by: str | None
+    created_at: datetime
+
+
+class PipelineResponse(BaseModel):
+    id: str
+    tenant_id: str
+    name: str
+    description: str | None
+    status: PipelineStatus
+    current_revision: int
+    created_by: str | None
+    updated_by: str | None
+    created_at: datetime
+    updated_at: datetime
+    revision: PipelineRevisionResponse
+
+
+class PipelineListResponse(BaseModel):
+    pipelines: list[PipelineResponse]
+
+
+class PipelineCreateRequest(BaseModel):
+    name: str = Field(min_length=1, max_length=300)
+    description: str | None = Field(default=None, max_length=4000)
+    status: PipelineStatus = "draft"
+    graph: PipelineGraph
+    sql_text: str | None = Field(default=None, max_length=100_000)
+    editor_mode: EditorMode = "graph"
+
+
+class PipelineUpdateRequest(PipelineCreateRequest):
+    expected_revision: int = Field(ge=1)
+
+
+class PipelineDraftRequest(BaseModel):
+    graph: PipelineGraph | None = None
+    sql_text: str | None = Field(default=None, max_length=100_000)
+    source_nodes: list[GraphNode] = Field(default_factory=list, max_length=20)
+
+
+class PipelineValidationResponse(BaseModel):
+    valid: bool
+    graph: PipelineGraph | None
+    sql_text: str | None
+    diagnostics: list[DataflowDiagnostic]
+
+
+class PipelineSqlResponse(PipelineValidationResponse):
+    pass
+
+
+class PipelinePreviewRequest(BaseModel):
+    pipeline_id: str | None = None
+    revision: int | None = Field(default=None, ge=1)
+    graph: PipelineGraph | None = None
+    sql_text: str | None = Field(default=None, max_length=100_000)
+    source_nodes: list[GraphNode] = Field(default_factory=list, max_length=20)
+    row_limit: int = Field(default=100, ge=1, le=500)
+
+
+class PreviewColumn(BaseModel):
+    name: str
+    type: str
+    nullable: bool = True
+
+
+class NodePreviewDiagnostic(BaseModel):
+    node_id: str
+    status: Literal["succeeded", "failed", "skipped"]
+    input_rows: int = 0
+    output_rows: int = 0
+    duration_ms: float = 0
+    columns: list[PreviewColumn] = Field(default_factory=list)
+    messages: list[str] = Field(default_factory=list)
+
+
+class PipelinePreviewResponse(BaseModel):
+    run_id: str | None
+    pipeline_id: str | None
+    revision: int | None
+    status: Literal["succeeded", "failed"]
+    columns: list[PreviewColumn]
+    rows: list[dict[str, Any]]
+    total_rows: int
+    truncated: bool
+    diagnostics: list[DataflowDiagnostic]
+    node_diagnostics: list[NodePreviewDiagnostic]
+    definition_hash: str
+    executor_version: str
+
+
+class PipelineDeleteResponse(BaseModel):
+    deleted: bool
+    pipeline_id: str