"""MBPP latent-planning results: pass@1 vs loop depth, trained vs untrained."""
import json
from pathlib import Path

import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt

OUT = Path(__file__).resolve().parent.parent / "results-loop"
tr = json.load(open(OUT / "eval_code_trained.json"))
un = json.load(open(OUT / "eval_code_untrained.json"))
ks = sorted(int(k) for k in tr["ks"])
BLUE, GRAY = "#2b6cb0", "#8a8f98"

def curve(res, sel):
    return [res["ks"][str(k)]["acc"] if sel == "all"
            else res["ks"][str(k)]["by_label"].get(sel, 0.0) for k in ks]

fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(11, 4.2))
for ax in (ax1, ax2):
    ax.grid(True, color="#e5e5e5", lw=0.7)
    ax.set_axisbelow(True)
    for s in ("top", "right"):
        ax.spines[s].set_visible(False)
    ax.set_xticks(ks)
    ax.set_xlabel("loop depth k (prompt-only)")

ax1.plot(ks, curve(tr, "all"), "-o", color=BLUE, lw=2, ms=5, label="trained · all")
ax1.plot(ks, curve(un, "all"), "-o", color=GRAY, lw=2, ms=5, label="untrained · all")
ax1.axhline(curve(tr, "all")[0], color="#bbb", lw=1, ls=":")
ax1.set_ylabel("pass@1 (250 MBPP test items)")
ax1.set_title("Overall: trained k=2 beats no-loop baseline", fontsize=11)
ax1.legend(fontsize=8, frameon=False)

ax2.plot(ks, curve(tr, "hard"), "-s", color=BLUE, lw=2, ms=5,
         label="trained · hard (plan-only)")
ax2.plot(ks, curve(un, "hard"), "-s", color=GRAY, lw=2, ms=5,
         label="untrained · hard")
ax2.set_ylabel("pass@1, hard bucket (~56 items)")
ax2.set_title("Planning-dependent problems: 3.6% → 46.4%", fontsize=11)
ax2.legend(fontsize=8, frameon=False)
ax2.annotate("silent loops recover ~46%\nof explicit-planning gap",
             xy=(4, curve(tr, "hard")[-1]), xytext=(1.8, 0.30), fontsize=8,
             color=BLUE, arrowprops=dict(arrowstyle="-", color=BLUE, lw=0.8))

fig.suptitle("MBPP latent planning: loop the workspace over the prompt, "
             "then write code normally", fontsize=12, y=1.02)
fig.tight_layout()
fig.savefig(OUT / "loop_eval_code.png", dpi=140, bbox_inches="tight",
            facecolor="white")
print("wrote", OUT / "loop_eval_code.png")