Remove smoke test

tools/smoke_test.py

@@ -1,140 +0,0 @@
-#!/usr/bin/env python3
-"""CPU smoke test for the Space.
-
-Builds a one-repo data directory (real GRU contexts and prompts, placeholder
-cached predictions), then drives every app handler and serves the UI once.
-
-    C2L_DATA_DIR=/tmp/c2l_smoke python tools/smoke_test.py --repo MiniMax-AI/Mini-Agent
-"""
-
-from __future__ import annotations
-
-import argparse
-import gzip
-import json
-import os
-import sys
-import time
-import urllib.request
-from collections import defaultdict
-from pathlib import Path
-
-import numpy as np
-import pyarrow.parquet as pq
-import torch
-
-HERE = Path(__file__).resolve().parents[1]
-sys.path.insert(0, str(HERE))
-
-from c2l.core import CommitGRU  # noqa: E402
-
-COMMITS = "/scratch/lhotsko/REPO_DATASET/commit_parquet_hf_v2/commits/cr_test.parquet"
-QNAS = "/scratch/lhotsko/REPO_DATASET/code2lora_snapshots_hf/qna/cr_test.parquet"
-
-
-def build(repo: str, out: Path) -> None:
-    from huggingface_hub import hf_hub_download
-    from transformers import AutoTokenizer
-
-    out.mkdir(parents=True, exist_ok=True)
-    safe = repo.replace("/", "__")
-    ct = pq.read_table(COMMITS, filters=[("repo_id", "=", repo)]).to_pylist()
-    ct.sort(key=lambda r: r["commit_index"])
-    qt = pq.read_table(QNAS, columns=["repo_id", "commit_sha", "test_file", "lineno", "test_function",
-                                      "prefix", "target"], filters=[("repo_id", "=", repo)]).to_pylist()
-    by_sha = defaultdict(list)
-    for q in qt:
-        by_sha[q["commit_sha"]].append(q)
-
-    state = torch.load(hf_hub_download("code2lora/code2lora-gru", "code2lora_gru.pt"),
-                       map_location="cpu", weights_only=False, mmap=True)
-    gc = state.get("gru_config") or {}
-    gru = CommitGRU(int(gc.get("diff_input_dim", 2048)), int(gc.get("repo_state_dim", 2048)),
-                    int(gc.get("hidden_dim", 2048)))
-    gru.load_state_dict(state["gru_state"])
-    gru.eval()
-    with torch.no_grad():
-        h = gru.init_hidden(torch.tensor(ct[0]["repo_state_embedding"]).unsqueeze(0))
-        ctx = []
-        for r in ct:
-            h = gru.step(torch.tensor(r["diff_embedding"]).unsqueeze(0), h)
-            ctx.append(gru.context(h).float())
-    np.save(out / f"{safe}.ctx.npy", torch.cat(ctx).numpy().astype(np.float32))
-
-    tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-1.5B")
-    bos = tok.bos_token_id if tok.bos_token_id is not None else tok.eos_token_id
-    commits, qnas = [], []
-    for k, r in enumerate(ct):
-        group = []
-        for j, q in enumerate(by_sha[r["commit_sha"]][:8]):
-            ids = ([bos] + tok.encode(q["prefix"], add_special_tokens=False))[-4096:]
-            had_bos = ids[0] == bos
-            group.append({"k": k, "test_file": q["test_file"], "lineno": int(q["lineno"] or 0),
-                          "test_function": q["test_function"] or "",
-                          "prompt": tok.decode(ids[1:] if had_bos else ids), "had_bos": had_bos,
-                          "n_prompt_tokens": len(ids), "target": q["target"],
-                          "base_pred": "placeholder", "base_em": 0.0, "base_es": 0.0,
-                          "c2l_pred": q["target"], "c2l_em": 1.0, "c2l_es": 1.0,
-                          **({"prev_pred": "placeholder", "prev_em": 0.0, "prev_es": 0.0} if j == 0 and k else {})})
-        qnas.append(group)
-        commits.append({"sha": r["commit_sha"], "commit_index": r["commit_index"],
-                        "timestamp": r["commit_timestamp"], "n_new_assertions": r["n_new_assertions"],
-                        "diff_preview": (r["production_code_diff"] or "")[:6000],
-                        "n_qnas": len(group), "base_em": 0.0 if group else None,
-                        "c2l_em": 1.0 if group else None, "time_travel": bool(group and k)})
-    with gzip.open(out / f"{safe}.json.gz", "wt", encoding="utf-8") as f:
-        json.dump({"repo_id": repo, "commits": commits, "qnas": qnas,
-                   "max_input_tokens": 4096, "max_new_tokens": 64}, f)
-    (out / "index.json").write_text(json.dumps([{
-        "repo_id": repo, "safe": safe, "n_commits": len(commits), "n_qnas": sum(map(len, qnas)),
-        "base_em": 0.0, "c2l_em": 1.0, "n_time_travel": sum(c["time_travel"] for c in commits),
-        "first_date": commits[0]["timestamp"], "last_date": commits[-1]["timestamp"],
-        "description": "smoke test", "stars": 1234}]))
-    print(f"[build] {repo}: {len(commits)} commits, {sum(map(len, qnas))} qnas", flush=True)
-
-
-def drive() -> None:
-    t0 = time.time()
-    import app
-    print(f"[app] import + engine {time.time() - t0:.0f}s", flush=True)
-    safe = app.INDEX[0]["safe"]
-    r = app.on_repo(safe)
-    k1 = r[1].value if hasattr(r[1], "value") else r[1]["value"]
-    print("[on_repo] ok, start commit", k1, flush=True)
-    r = app.on_commit(safe, k1, None)
-    i = r[3].value if hasattr(r[3], "value") else r[3]["value"]
-    print("[on_commit] ok, pick", i, flush=True)
-    t = time.time()
-    status, st, *_ = app.on_adapt(safe, k1, i)
-    print(f"[on_adapt] {time.time() - t:.2f}s  state={st}", flush=True)
-    print(status[:400])
-    _, preds, _ = app.on_pick(safe, k1, i, st)
-    assert "Code2LoRA @ commit" in preds, preds
-    t = time.time()
-    live = app.on_live(safe, k1, i, st, progress=lambda *a, **k: None)
-    print(f"[on_live] {time.time() - t:.1f}s\n{live}", flush=True)
-    t = time.time()
-    prompt = app.on_prefill(safe, k1, i)
-    custom = app.on_custom(safe, k1, prompt, 32, st, progress=lambda *a, **k: None)
-    print(f"[on_custom] {time.time() - t:.1f}s\n{custom[:1500]}", flush=True)
-    for k in range(1, len(app.load_repo(safe)["commits"]) + 1):
-        app.on_commit(safe, k, st)
-        app.on_adapt(safe, k, 0)
-    print("[all commits] ok", flush=True)
-
-    app.demo.queue(max_size=32).launch(server_port=7861, prevent_thread_lock=True)
-    body = urllib.request.urlopen("http://127.0.0.1:7861/", timeout=30).read()
-    print(f"[serve] GET / -> {len(body)} bytes", flush=True)
-    app.demo.close()
-
-
-if __name__ == "__main__":
-    ap = argparse.ArgumentParser()
-    ap.add_argument("--repo", default="MiniMax-AI/Mini-Agent")
-    ap.add_argument("--build-only", action="store_true")
-    args = ap.parse_args()
-    data = Path(os.environ["C2L_DATA_DIR"])
-    if not (data / "index.json").exists():
-        build(args.repo, data)
-    if not args.build_only:
-        drive()

tools/smoke_test.sbatch

@@ -1,20 +0,0 @@
-#!/bin/bash
-# CPU smoke test mirroring the free Space tier (2 vCPU).
-#   sbatch hf_space_demo/tools/smoke_test.sbatch
-#SBATCH --job-name=c2l_space_smoke
-#SBATCH --output=slurm_logs/c2l_space_smoke_%j.out
-#SBATCH --time=01:00:00
-#SBATCH --cpus-per-task=2
-#SBATCH --mem=24G
-#SBATCH --account=def-yuntian
-
-set -euo pipefail
-module purge 2>/dev/null || true
-module load StdEnv/2023 python/3.12 arrow
-P=/home/lhotsko/projects/def-yuntian/lhotsko/c2l_space
-source $P/venv/bin/activate
-cd /home/lhotsko/RepoPeftData/hf_space_demo
-
-export PYTHONUNBUFFERED=1 HF_HOME=$P/hf HF_HUB_OFFLINE=1 C2L_DATA_DIR=$P/smoke_data
-export OMP_NUM_THREADS=2 GRADIO_ANALYTICS_ENABLED=False
-python tools/smoke_test.py