"""PR deduplication service.

Queries the agent_threads table to find which PRs from a given list have
not yet been processed.  This prevents the PR poller from re-triggering
graph runs for PRs that already have an existing thread.
"""

from release_agent.models.pr import PRInfo

_QUERY = """
    SELECT pr_id, repo_name
    FROM agent_threads
    WHERE (pr_id, repo_name) IN (
        SELECT unnest(%s::text[]), unnest(%s::text[])
    )
"""


async def find_unprocessed_prs(pool, prs: list[PRInfo]) -> list[PRInfo]:
    """Return the subset of prs that have no existing agent_threads record.

    A PR is considered already-processed if there exists a row in agent_threads
    with matching (pr_id, repo_name) pair. The SQL uses unnest to enforce
    pair-wise matching (not independent ANY on each column).

    Args:
        pool: Async psycopg connection pool.
        prs: List of PRInfo objects to check.

    Returns:
        A new list containing only PRs with no existing thread.
        Original list is not mutated.
    """
    if not prs:
        return []

    pr_ids = [p.pr_id for p in prs]
    repo_names = [p.repo_name for p in prs]

    async with pool.connection() as conn:
        async with conn.cursor() as cur:
            await cur.execute(_QUERY, (pr_ids, repo_names))
            rows = await cur.fetchall()

    processed = {(str(row[0]), str(row[1])) for row in rows}
    return [p for p in prs if (p.pr_id, p.repo_name) not in processed]