MVP stage 2: dedup (atom_relations) + compositions (telegram channel)

stage2/compositions.py

@@ -0,0 +1,127 @@
+#!/usr/bin/env python3
+"""
+MVP stage 2: compositions — собрать atom_versions под второй канал (Telegram).
+
+Для каждого атома генерирует версию под Telegram (plain text, до 1024 символов),
+если atom_versions для этого канала ещё нет.
+
+bge-m3 (dim=1024) — единственная embed-модель (для semantic-версий).
+Postgres (atom-db) — atom_versions как источник.
+
+Запуск:
+    python3 stage2/compositions.py --channel telegram --top 20
+    python3 stage2/compositions.py --channel telegram --limit 50
+"""
+
+import argparse
+import json
+import os
+import sys
+import time
+
+import psycopg2
+
+POSTGRES = {
+    "host": os.environ.get("POSTGRES_HOST", "127.0.0.1"),
+    "port": int(os.environ.get("POSTGRES_PORT", "5434")),
+    "user": os.environ.get("POSTGRES_USER", "atom"),
+    "dbname": os.environ.get("POSTGRES_DB", "content_atom"),
+    "password": os.environ.get("POSTGRES_PASSWORD", "atompass123"),
+}
+MAX_LEN = 1024  # Telegram limit
+
+
+def get_conn():
+    return psycopg2.connect(**POSTGRES)
+
+
+def get_atoms(conn, limit: int) -> list[dict]:
+    """Атомы для генерации (draft, не занятые)."""
+    with conn.cursor() as cur:
+        cur.execute("""
+            SELECT a.id, a.type, a.plain_text, a.word_count, a.project_id
+            FROM atoms a
+            WHERE a.plain_text IS NOT NULL
+            ORDER BY a.created_at DESC
+            LIMIT %s
+        """, (limit,))
+        cols = [d[0] for d in cur.description]
+        return [dict(zip(cols, row)) for row in cur.fetchall()]
+
+
+def has_version(conn, atom_id: str, channel: str) -> bool:
+    with conn.cursor() as cur:
+        cur.execute(
+            "SELECT 1 FROM atom_versions WHERE atom_id=%s AND channel=%s LIMIT 1",
+            (atom_id, channel),
+        )
+        return cur.fetchone() is not None
+
+
+def build_telegram_version(atom: dict) -> str:
+    """Генерация версии под Telegram (plain text)."""
+    text = atom["plain_text"]
+    if len(text) > MAX_LEN:
+        text = text[:MAX_LEN].rstrip() + "…"
+
+    # Типизированное оформление
+    t = atom["type"]
+    if t in ("stat",):
+        return f"📊 {text}"
+    if t in ("qa",):
+        return f"❓ {text}"
+    if t in ("cta",):
+        return f"👉 {text}"
+    if t in ("hook",):
+        return f"🔥 {text}"
+    if t in ("comparison",):
+        return f"⚖️ {text}"
+    if t in ("instruction",):
+        return f"✅ {text}"
+    if t in ("quote",):
+        return f'» {text}'
+    return text
+
+
+def insert_versions(conn, atom_id: str, content: str) -> bool:
+    """Вставить atom_versions под telegram (plain)."""
+    with conn.cursor() as cur:
+        cur.execute("""
+            INSERT INTO atom_versions
+            (atom_id, channel, format, content, quality_score)
+            VALUES (%s, %s, %s, %s, %s)
+            ON CONFLICT (atom_id, channel, format) DO NOTHING
+        """, (atom_id, "telegram", "plain", content, 7.0))
+        committed = cur.rowcount > 0
+    conn.commit()
+    return committed
+
+
+def main():
+    ap = argparse.ArgumentParser(description="MVP stage 2: compositions (telegram)")
+    ap.add_argument("--channel", default="telegram", help="канал")
+    ap.add_argument("--format", default="plain", help="формат")
+    ap.add_argument("--limit", type=int, default=20, help="сколько атомов")
+    args = ap.parse_args()
+
+    conn = get_conn()
+    atoms = get_atoms(conn, args.limit)
+    print(f"  • {len(atoms)} атомов для {args.channel}")
+
+    n = 0
+    start = time.time()
+    for atom in atoms:
+        if has_version(conn, str(atom["id"]), args.channel):
+            continue
+        content = build_telegram_version(atom)
+        if insert_versions(conn, str(atom["id"]), content):
+            n += 1
+    conn.close()
+
+    print(f"  ✓ atom_versions: {n} за {time.time()-start:.1f}с")
+    print(f"\nMVP stage 2 compositions OK: {n} версий под {args.channel}")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())