"""loop.py — Karpathy-style autoresearch loop for jepa-fx-risk.

Agent (on iguana/berget — NOT koala, whose GPU is reserved for train.py) reads
program.md + train.py + STATUS.md, proposes ONE change to train.py, we run it,
keep if val_vol_r2 improved else git-revert. Appends per-iter record to STATUS.md.

    LITELLM_KEY=xxx python loop.py [--iters N] [--model MODEL]

Env:
  LITELLM_KEY      — LiteLLM master key (required)
  LITELLM_BASE     — default http://localhost:30401/v1
  LOOP_MODEL       — default berget/gemma4-31b (non-thinking; iguana/berget only)
  LOOP_ITERS       — default 3
  TRAIN_TIMEOUT    — seconds per train.py run, default 120
"""
import argparse
import json
import os
import subprocess
import sys
import time
import textwrap
from pathlib import Path

import urllib.request

LITELLM_BASE = os.environ.get("LITELLM_BASE", "http://localhost:30401/v1")
LITELLM_KEY  = os.environ.get("LITELLM_KEY", "")
LOOP_MODEL   = os.environ.get("LOOP_MODEL", "berget/gemma4-31b")
LOOP_ITERS   = int(os.environ.get("LOOP_ITERS", "3"))
TRAIN_TIMEOUT = int(os.environ.get("TRAIN_TIMEOUT", "120"))
STATUS_MD    = Path("STATUS.md")
METRICS_JSON = Path("metrics.json")
TRAIN_PY     = Path("train.py")

AGENT_SYSTEM = textwrap.dedent("""\
    You are the autoresearch agent for jepa-fx-risk. Your job: propose ONE small,
    targeted change to train.py to improve val_vol_r2 (OOS R² predicting 1-day
    realized vol from frozen embeddings). Higher is better.

    Rules:
    - Return ONLY the full new content of train.py — nothing else, no explanation,
      no markdown fence. Raw Python only.
    - Change ONE thing at a time (one knob, one structural idea).
    - Do NOT touch prepare_data.py, loop.py, or the data pipeline — only train.py.
    - Do NOT add new data sources or new files.
    - The metric is computed externally from your frozen embeddings; trust it.
""")


def read_file(p: Path) -> str:
    return p.read_text() if p.exists() else ""


def gpu_snapshot() -> str:
    try:
        out = subprocess.check_output(
            ["nvidia-smi", "--query-gpu=utilization.gpu,memory.used,memory.total,temperature.gpu",
             "--format=csv,noheader,nounits"], timeout=5, text=True
        ).strip()
        util, mem_used, mem_total, temp = [x.strip() for x in out.split(",")]
        return "gpu=%s%% vram=%s/%sMiB temp=%s°C" % (util, mem_used, mem_total, temp)
    except Exception:
        return "gpu=N/A"


def read_metric() -> float | None:
    if not METRICS_JSON.exists():
        return None
    try:
        return float(json.loads(METRICS_JSON.read_text())["val_vol_r2"])
    except Exception:
        return None


def run_train() -> tuple[float | None, float, str]:
    """Run train.py. Returns (val_vol_r2 or None, wall_secs, stderr_tail)."""
    t0 = time.time()
    gpu_before = gpu_snapshot()
    try:
        r = subprocess.run(
            [sys.executable, "train.py"],
            capture_output=True, text=True, timeout=TRAIN_TIMEOUT,
        )
        elapsed = time.time() - t0
        if r.returncode != 0:
            return None, elapsed, (r.stderr or r.stdout)[-300:]
        metric = read_metric()
        return metric, elapsed, ""
    except subprocess.TimeoutExpired:
        return None, TRAIN_TIMEOUT, "TIMEOUT"


def call_agent(iteration: int, best_so_far: float | None) -> str:
    """Ask the LLM agent to edit train.py. Returns new train.py content."""
    context = "\n\n".join([
        "# program.md\n" + read_file(Path("program.md")),
        "# train.py (current)\n" + read_file(TRAIN_PY),
        "# STATUS.md (history)\n" + read_file(STATUS_MD)[-2000:],
        "# metrics.json (last run)\n" + read_file(METRICS_JSON),
        "Iteration %d. Best val_vol_r2 so far: %s. Improve it." % (
            iteration, "%.4f" % best_so_far if best_so_far is not None else "none yet"
        ),
    ])
    payload = json.dumps({
        "model": LOOP_MODEL,
        "messages": [
            {"role": "system", "content": AGENT_SYSTEM},
            {"role": "user",   "content": context},
        ],
        "temperature": 0.7,
        "max_tokens": 4096,
    }).encode()
    req = urllib.request.Request(
        LITELLM_BASE + "/chat/completions",
        data=payload,
        headers={"Authorization": "Bearer " + LITELLM_KEY,
                 "Content-Type": "application/json"},
        method="POST",
    )
    resp = urllib.request.urlopen(req, timeout=60)
    data = json.load(resp)
    return data["choices"][0]["message"]["content"]


def revert_train(original_content: str):
    TRAIN_PY.write_text(original_content)


def append_status(line: str):
    with open(STATUS_MD, "a") as f:
        f.write(line + "\n")


def main():
    if not LITELLM_KEY:
        print("ERROR: set LITELLM_KEY"); sys.exit(1)

    if not STATUS_MD.exists():
        STATUS_MD.write_text("# Autoresearch STATUS\n\n| iter | val_vol_r2 | delta | action | secs | gpu | change |\n|------|-----------|-------|--------|------|-----|--------|\n")

    # establish baseline
    baseline = read_metric()
    if baseline is None:
        print("No metrics.json — running train.py for baseline...")
        m, secs, err = run_train()
        if m is None:
            print("Baseline run failed:", err); sys.exit(1)
        baseline = m
        print("Baseline: val_vol_r2 = %.4f (%.1fs)" % (baseline, secs))

    best = baseline
    print("Starting loop | model=%s | iters=%d | baseline=%.4f" % (LOOP_MODEL, LOOP_ITERS, best))

    for i in range(1, LOOP_ITERS + 1):
        print("\n--- iter %d/%d ---" % (i, LOOP_ITERS))
        original = TRAIN_PY.read_text()

        print("  calling agent (%s)..." % LOOP_MODEL)
        t_agent = time.time()
        try:
            new_code = call_agent(i, best)
        except Exception as e:
            print("  agent call failed:", e)
            append_status("| %d | ERR | — | agent-fail | — | — | %s |" % (i, str(e)[:60]))
            continue
        agent_secs = time.time() - t_agent
        print("  agent replied in %.1fs" % agent_secs)

        # strip accidental markdown fences
        if new_code.strip().startswith("```"):
            lines = new_code.strip().splitlines()
            new_code = "\n".join(lines[1:-1] if lines[-1].strip() == "```" else lines[1:])

        TRAIN_PY.write_text(new_code)

        gpu = gpu_snapshot()
        print("  running train.py [%s]..." % gpu)
        metric, secs, err = run_train()

        if metric is None:
            print("  train.py FAILED — reverting. err:", err[:100])
            revert_train(original)
            append_status("| %d | FAIL | — | revert | %.0fs | %s | run error |" % (i, secs, gpu))
            continue

        delta = metric - best
        if metric > best:
            best = metric
            action = "KEEP"
        else:
            revert_train(original)
            action = "revert"

        summary = "| %d | %.4f | %+.4f | %s | %.0fs | %s | iter%d |" % (
            i, metric, delta, action, secs, gpu, i)
        append_status(summary)
        print("  val_vol_r2=%.4f  delta=%+.4f  action=%s  [%.0fs]" % (metric, delta, action, secs))

    print("\nDone. Best val_vol_r2 = %.4f (baseline was %.4f, delta %+.4f)" % (best, baseline, best - baseline))
    print("STATUS.md updated.")


if __name__ == "__main__":
    main()