evo/feedback_collector.py

"""
Agent Q3 [Evo] — Feedback Collector
Captures DPO / RLHF signal pairs from inference runs.
Writes to HF dataset madDegen/agent-q3-trainingevo.
"""
import json, os, datetime
from pathlib import Path

FEEDBACK_DIR = Path(os.getenv("FEEDBACK_DIR", "./feedback"))

def record(prompt: str, chosen: str, rejected: str, domain: str = "general"):
    """Record a DPO preference pair."""
    FEEDBACK_DIR.mkdir(exist_ok=True)
    entry = {
        "timestamp": datetime.datetime.utcnow().isoformat(),
        "domain":    domain,
        "prompt":    prompt,
        "chosen":    chosen,
        "rejected":  rejected,
    }
    date_str = datetime.date.today().isoformat()
    out_file = FEEDBACK_DIR / f"feedback_{date_str}.jsonl"
    with open(out_file, "a") as f:
        f.write(json.dumps(entry) + "\n")
    return entry

def push_to_hf(token: str = None):
    """Push accumulated feedback to madDegen/agent-q3-trainingevo."""
    from datasets import Dataset, load_dataset
    import glob
    token = token or os.getenv("HF_TOKEN")
    files = sorted(glob.glob(str(FEEDBACK_DIR / "*.jsonl")))
    rows  = []
    for fp in files:
        with open(fp) as f:
            rows.extend(json.loads(l) for l in f if l.strip())
    if not rows:
        print("No feedback to push.")
        return
    ds = Dataset.from_list(rows)
    ds.push_to_hub("madDegen/agent-q3-trainingevo", token=token, split="train")
    print(f"Pushed {len(rows)} feedback pairs to HF.")

if __name__ == "__main__":
    push_to_hf()