update

backend/train_lauf.py

@@ -0,0 +1,68 @@
+"""EIN Trainings-Trial: frischer Prozess (CREATOR_PARAMS wirkt beim Import), ein
+kompletter Mini-Lauf, deterministische Metriken als JSON — danach ist das Topic weg.
+
+CLI: python3 train_lauf.py <topic> <benchmark-location> <ausgabe.json>
+     (benchmark-location repo-relativ, z. B. "benchmarks/sortierverfahren")
+"""
+
+import asyncio
+import shutil
+import sys
+from datetime import datetime, timezone
+from pathlib import Path
+
+import agents
+import database
+import qa
+from blocks import generate_blocks
+from fsutil import atomic_write_json
+from paths import source_path, topic_dir
+
+
+async def trial(topic: str, location: str, out: str) -> None:
+    await database.init_db()
+    agents.on_event = database.add_event  # sonst keine Dauer-/Token-Events (main.py-lifespan-Pendant)
+    try:
+        await _aufraeumen(topic)  # Reste eines abgebrochenen Trials
+        await database.create_topic(topic)
+        qp = source_path(topic)
+        qp.parent.mkdir(parents=True, exist_ok=True)
+        atomic_write_json(qp, {"type": "uni", "location": location, "spec": ""})
+        start = datetime.now(timezone.utc)
+        # qa_force=True: das Gate misst, pausiert den Trial aber nie
+        await generate_blocks(topic, provider="minimax", research=True, qa_force=True)
+        dauer_min = round((datetime.now(timezone.utc) - start).total_seconds() / 60, 1)
+        report = await qa.qa_report(topic, llm=False) or {}
+        lauf = report.get("lauf") or {}
+        metrics = {
+            "topic": topic,
+            "note": report.get("note"),
+            "note_artefakte": report.get("note_artefakte"),
+            "quoten": report.get("quoten") or {},
+            "quoten_artefakte": report.get("quoten_artefakte") or {},
+            "bloecke": report.get("bloecke"),
+            "dauer_min": lauf.get("dauer_min") or dauer_min,
+            "tokens": (lauf.get("tokens") or {}),
+            "agents": (lauf.get("agents") or {}),
+        }
+        atomic_write_json(Path(out), metrics, indent=1)
+    finally:
+        await _aufraeumen(topic)
+        await database.close_db()
+
+
+async def _aufraeumen(topic: str) -> None:
+    """Topic restlos entfernen (DELETE-/topics-Sequenz aus routes.py)."""
+    await database.delete_topic(topic)
+    await database.delete_block_data(topic)
+    await database.delete_topic_pipeline(topic)
+    await database.delete_source(topic)
+    await database.delete_guide_content(topic)
+    shutil.rmtree(topic_dir(topic), ignore_errors=True)
+    shutil.rmtree(qa.QA_DIR / topic, ignore_errors=True)
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 4:
+        raise SystemExit("Nutzung: python3 train_lauf.py <topic> <benchmark-location> <ausgabe.json>")
+    asyncio.run(trial(sys.argv[1], sys.argv[2], sys.argv[3]))