From 711ae5df73aebd7823c3b65b654ace4d64fb90d9 Mon Sep 17 00:00:00 2001
From: Bill <bill@bballou.com>
Date: Sat, 1 Nov 2025 23:10:01 -0400
Subject: [PATCH] feat(db): add downloading_data status and warnings column

Add support for:
- downloading_data job status for visibility during data prep
- warnings TEXT column for storing job-level warnings (JSON array)

Co-Authored-By: Claude <noreply@anthropic.com>
---
 api/database.py                    |  5 ++--
 tests/unit/test_database_schema.py | 47 ++++++++++++++++++++++++++++++
 2 files changed, 50 insertions(+), 2 deletions(-)
 create mode 100644 tests/unit/test_database_schema.py

diff --git a/api/database.py b/api/database.py
index d6932a7..5da0c6a 100644
--- a/api/database.py
+++ b/api/database.py
@@ -85,7 +85,7 @@ def initialize_database(db_path: str = "data/jobs.db") -> None:
         CREATE TABLE IF NOT EXISTS jobs (
             job_id TEXT PRIMARY KEY,
             config_path TEXT NOT NULL,
-            status TEXT NOT NULL CHECK(status IN ('pending', 'running', 'completed', 'partial', 'failed')),
+            status TEXT NOT NULL CHECK(status IN ('pending', 'downloading_data', 'running', 'completed', 'partial', 'failed')),
             date_range TEXT NOT NULL,
             models TEXT NOT NULL,
             created_at TEXT NOT NULL,
@@ -93,7 +93,8 @@ def initialize_database(db_path: str = "data/jobs.db") -> None:
             updated_at TEXT,
             completed_at TEXT,
             total_duration_seconds REAL,
-            error TEXT
+            error TEXT,
+            warnings TEXT
         )
     """)
 
diff --git a/tests/unit/test_database_schema.py b/tests/unit/test_database_schema.py
new file mode 100644
index 0000000..af11ab2
--- /dev/null
+++ b/tests/unit/test_database_schema.py
@@ -0,0 +1,47 @@
+import pytest
+import sqlite3
+from api.database import initialize_database, get_db_connection
+
+def test_jobs_table_allows_downloading_data_status(tmp_path):
+    """Test that jobs table accepts downloading_data status."""
+    db_path = str(tmp_path / "test.db")
+    initialize_database(db_path)
+
+    conn = get_db_connection(db_path)
+    cursor = conn.cursor()
+
+    # Should not raise constraint violation
+    cursor.execute("""
+        INSERT INTO jobs (job_id, config_path, status, date_range, models, created_at)
+        VALUES ('test-123', 'config.json', 'downloading_data', '[]', '[]', '2025-11-01T00:00:00Z')
+    """)
+    conn.commit()
+
+    # Verify it was inserted
+    cursor.execute("SELECT status FROM jobs WHERE job_id = 'test-123'")
+    result = cursor.fetchone()
+    assert result[0] == "downloading_data"
+
+    conn.close()
+
+def test_jobs_table_has_warnings_column(tmp_path):
+    """Test that jobs table has warnings TEXT column."""
+    db_path = str(tmp_path / "test.db")
+    initialize_database(db_path)
+
+    conn = get_db_connection(db_path)
+    cursor = conn.cursor()
+
+    # Insert job with warnings
+    cursor.execute("""
+        INSERT INTO jobs (job_id, config_path, status, date_range, models, created_at, warnings)
+        VALUES ('test-456', 'config.json', 'completed', '[]', '[]', '2025-11-01T00:00:00Z', '["Warning 1", "Warning 2"]')
+    """)
+    conn.commit()
+
+    # Verify warnings can be retrieved
+    cursor.execute("SELECT warnings FROM jobs WHERE job_id = 'test-456'")
+    result = cursor.fetchone()
+    assert result[0] == '["Warning 1", "Warning 2"]'
+
+    conn.close()