teleo-codex/ops/pipeline-v2/backfill-descriptions.py

#!/usr/bin/env python3
"""One-time backfill: populate prs.description with claim titles from merged files.

For PRs that have description=NULL or empty, reads the claim files on main
(for merged PRs) or on the branch (for open PRs) and extracts H1 titles.

Usage: python3 backfill-descriptions.py [--dry-run]

Requires: run from the teleo-codex git worktree (main branch).
"""

import re
import sqlite3
import subprocess
import sys
from pathlib import Path

DB_PATH = Path("/opt/teleo-eval/pipeline/pipeline.db")
MAIN_WORKTREE = Path("/opt/teleo-eval/teleo-codex")
CLAIM_DIRS = ("domains/", "core/", "foundations/")

dry_run = "--dry-run" in sys.argv


def get_pr_claim_titles(pr_number: int, branch: str, status: str) -> list[str]:
    """Extract H1 claim titles from a PR's changed files."""
    titles = []

    # For merged PRs: diff the merge commit on main
    # For open PRs: diff against main
    try:
        if status == "merged":
            # Get the diff from the branch name — files are on main now
            # Use git log to find the merge and diff its changes
            result = subprocess.run(
                ["git", "diff", "--name-only", f"origin/main...origin/{branch}"],
                capture_output=True, text=True, timeout=10,
                cwd=str(MAIN_WORKTREE),
            )
            if result.returncode != 0:
                # Branch may be deleted — try reading files from main directly
                # We can't reconstruct the diff, but we can search by PR number in audit_log
                return titles
        else:
            result = subprocess.run(
                ["git", "diff", "--name-only", f"origin/main...origin/{branch}"],
                capture_output=True, text=True, timeout=10,
                cwd=str(MAIN_WORKTREE),
            )
            if result.returncode != 0:
                return titles

        changed_files = [
            f.strip() for f in result.stdout.strip().split("\n")
            if f.strip() and any(f.strip().startswith(d) for d in CLAIM_DIRS) and f.strip().endswith(".md")
        ]

        for fpath in changed_files:
            # Read from main for merged, from branch for open
            ref = "origin/main" if status == "merged" else f"origin/{branch}"
            show = subprocess.run(
                ["git", "show", f"{ref}:{fpath}"],
                capture_output=True, text=True, timeout=5,
                cwd=str(MAIN_WORKTREE),
            )
            if show.returncode == 0:
                for line in show.stdout.split("\n"):
                    if line.startswith("# ") and len(line) > 3:
                        titles.append(line[2:].strip())
                        break

    except (subprocess.TimeoutExpired, Exception) as e:
        print(f"  PR #{pr_number}: error — {e}")

    return titles


def main():
    conn = sqlite3.connect(str(DB_PATH))
    conn.row_factory = sqlite3.Row

    # Find PRs with empty description
    rows = conn.execute(
        "SELECT number, branch, status FROM prs WHERE description IS NULL OR description = '' ORDER BY number DESC"
    ).fetchall()

    print(f"Found {len(rows)} PRs with empty description")

    updated = 0
    skipped = 0

    for row in rows:
        pr_num = row["number"]
        branch = row["branch"]
        status = row["status"]

        if not branch:
            skipped += 1
            continue

        titles = get_pr_claim_titles(pr_num, branch, status)

        if titles:
            desc = " | ".join(titles)
            if dry_run:
                print(f"  PR #{pr_num} ({status}): would set → {desc[:100]}...")
            else:
                conn.execute(
                    "UPDATE prs SET description = ? WHERE number = ?",
                    (desc, pr_num),
                )
                updated += 1
                if updated % 50 == 0:
                    conn.commit()
                    print(f"  ...{updated} updated so far")
        else:
            skipped += 1

    if not dry_run:
        conn.commit()

    conn.close()
    print(f"\nDone. Updated: {updated}, Skipped: {skipped}, Total: {len(rows)}")
    if dry_run:
        print("(dry run — no changes written)")


if __name__ == "__main__":
    main()