Expand governed Dataflow editor and node library

src/govoplan_dataflow/backend/schemas.py

@@ -4,7 +4,7 @@ import math
 from datetime import datetime
 from typing import Any, Literal
 
-from pydantic import BaseModel, ConfigDict, Field, field_validator
+from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
 
 
 PipelineStatus = Literal["draft", "active", "archived"]
@@ -152,6 +152,8 @@ class PipelinePreviewResponse(BaseModel):
     truncated: bool
     diagnostics: list[DataflowDiagnostic]
     node_diagnostics: list[NodePreviewDiagnostic]
+    source_fingerprints: list[dict[str, Any]]
+    input_row_count: int
     definition_hash: str
     executor_version: str
 
@@ -159,3 +161,93 @@ class PipelinePreviewResponse(BaseModel):
 class PipelineDeleteResponse(BaseModel):
     deleted: bool
     pipeline_id: str
+
+
+class NodePortDefinitionResponse(BaseModel):
+    id: str
+    label: str
+    required: bool
+    multiple: bool
+    minimum_connections: int
+
+
+class NodeConfigFieldResponse(BaseModel):
+    id: str
+    label: str
+    kind: str
+    required: bool
+    description: str | None
+    options: list[tuple[str, str]]
+
+
+class NodeTypeDefinitionResponse(BaseModel):
+    type: str
+    category: str
+    category_label: str
+    label: str
+    description: str
+    icon: str
+    input_ports: list[NodePortDefinitionResponse]
+    output_ports: list[NodePortDefinitionResponse]
+    config_fields: list[NodeConfigFieldResponse]
+    default_config: dict[str, Any]
+    sql_support: str
+
+
+class NodeLibraryResponse(BaseModel):
+    nodes: list[NodeTypeDefinitionResponse]
+
+
+class TabularSourceColumnResponse(BaseModel):
+    name: str
+    data_type: str
+    nullable: bool
+
+
+class TabularSourceResponse(BaseModel):
+    ref: str
+    provider: str
+    source_name: str
+    name: str
+    description: str | None
+    columns: list[TabularSourceColumnResponse]
+    schema_version: str
+    fingerprint: str
+    row_count: int | None
+    byte_count: int | None
+    updated_at: datetime | None
+    capabilities: list[str]
+
+
+class TabularSourceListResponse(BaseModel):
+    available: bool
+    writable: bool
+    sources: list[TabularSourceResponse]
+
+
+class TabularSnapshotCreateRequest(BaseModel):
+    name: str = Field(min_length=1, max_length=300)
+    source_name: str = Field(
+        min_length=1,
+        max_length=120,
+        pattern=r"^[A-Za-z_][A-Za-z0-9_]*$",
+    )
+    description: str | None = Field(default=None, max_length=4000)
+    format: Literal["json", "csv"] = "json"
+    rows: list[dict[str, Any]] | None = Field(default=None, max_length=10_000)
+    csv_text: str | None = Field(default=None, max_length=5_000_000)
+    delimiter: str = Field(default=",", min_length=1, max_length=1)
+
+    @model_validator(mode="after")
+    def validate_format_payload(self) -> TabularSnapshotCreateRequest:
+        if self.format == "json":
+            if self.rows is None:
+                raise ValueError("JSON snapshots require rows.")
+            if self.csv_text is not None:
+                raise ValueError("JSON snapshots cannot include CSV text.")
+        else:
+            if not self.csv_text:
+                raise ValueError("CSV snapshots require CSV text.")
+            if self.rows is not None:
+                raise ValueError("CSV snapshots cannot include JSON rows.")
+        return self