feat(db): idempotent schema + 'codex migrate' command (audit M-1, T-2)

M-1: schema.sql could not be re-applied (leading CREATE TABLE/INDEX lacked
IF NOT EXISTS), apply_schema was never called, and the live migration just
failed on a missing chunks.section column. Fixes:

- schema.sql: all CREATE TABLE/INDEX now use IF NOT EXISTS — the whole file is
  re-applyable as a no-op.
- codex migrate: new CLI command that applies schema.sql. Connects via
  MIGRATION_DATABASE_URL (falls back to DATABASE_URL) and catches
  InsufficientPrivilege with guidance — because the app role is DML-only and
  core tables are owned by 'postgres' (the privilege dimension found during the
  live migration incident).
- config: migration_database_url (optional privileged connection).
- db: apply_schema docstring corrected (idempotency now true) + privilege note.
- T-2: static test that schema.sql is fully idempotent; migrate privilege-error
  test.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

codex/cli.py

@@ -29,6 +29,37 @@ app.add_typer(graph_app, name="graph")
 app.add_typer(search_app, name="search")
 
 
+@app.command()
+def migrate() -> None:
+    """Apply infra/schema.sql to bring the database schema up to date (idempotent).
+
+    Must connect as a role that can run DDL (owns / can CREATE + ALTER the tables).
+    The application's DATABASE_URL is usually a least-privilege DML role and will
+    fail with InsufficientPrivilege; set MIGRATION_DATABASE_URL to a privileged
+    (owner/superuser) connection (audit M-1).
+    """
+    import psycopg
+    import psycopg.rows
+
+    from codex.config import get_settings
+    from codex.db import apply_schema
+
+    settings = get_settings()
+    url = settings.migration_database_url or settings.database_url
+    try:
+        with psycopg.connect(url, row_factory=psycopg.rows.dict_row) as conn:
+            apply_schema(conn)
+    except psycopg.errors.InsufficientPrivilege as exc:
+        typer.echo(
+            "ERROR: schema migration needs a role that owns the tables "
+            "(CREATE/ALTER). Set MIGRATION_DATABASE_URL to a privileged connection "
+            f"and retry. ({exc})",
+            err=True,
+        )
+        raise typer.Exit(1) from exc
+    typer.echo("Schema applied — database is up to date.")
+
+
 @app.command()
 def ingest(
     paper_id: str = typer.Argument(..., help="arXiv ID, DOI, or OpenAlex W-ID"),

codex/config.py

@@ -34,6 +34,17 @@ class Settings(BaseSettings):
         ),
     )
 
+    migration_database_url: str | None = Field(
+        default=None,
+        description=(
+            "Optional privileged connection string used by `codex migrate` to apply "
+            "schema DDL. The app's database_url is typically a least-privilege DML "
+            "role that cannot CREATE/ALTER owner-held tables (raises "
+            "InsufficientPrivilege); point this at an owner/superuser connection. "
+            "Falls back to database_url when unset."
+        ),
+    )
+
     # ------------------------------------------------------------------
     # External services
     # ------------------------------------------------------------------

codex/db.py

@@ -45,11 +45,16 @@ def get_conn() -> Generator[psycopg.Connection[psycopg.rows.DictRow], None, None
 def apply_schema(conn: psycopg.Connection[psycopg.rows.DictRow]) -> None:
     """Idempotently apply ``infra/schema.sql`` to the connected database.
 
-    Safe to call on every startup — all DDL statements use
-    ``CREATE … IF NOT EXISTS``.
+    Safe to call repeatedly — every statement is ``CREATE … IF NOT EXISTS`` or
+    ``ADD COLUMN IF NOT EXISTS``, so re-application is a no-op.
+
+    Requires a connection whose role can run DDL (owns / can CREATE + ALTER the
+    tables). The least-privilege application role is typically DML-only and will
+    raise ``InsufficientPrivilege``; use a privileged connection — see
+    ``codex migrate`` and ``MIGRATION_DATABASE_URL`` (audit M-1).
 
     Args:
-        conn: An open psycopg connection (obtained via :func:`get_conn`).
+        conn: An open psycopg connection with DDL privileges.
     """
     schema_path = Path(__file__).parent.parent / "infra" / "schema.sql"
     sql = schema_path.read_text(encoding="utf-8")