DeepSWE v1.1 평가 실행하기

git clone https://github.com/coreweave/cwsandbox-recipes.git
cd cwsandbox-recipes/recipes/deepswe
uv sync --locked

git clone https://github.com/datacurve-ai/deep-swe.git
git -C deep-swe checkout 0b9fabbb63b9104d678fe965e1632f2dd9eaa2ea

export CWSANDBOX_API_KEY="[API-ACCESS-TOKEN]"
export FORGE_API_KEY="[FORGE-API-KEY]"
export MSWEA_MODEL_RETRY_STOP_AFTER_ATTEMPT=3
export MSWEA_SILENT_STARTUP=1

for key in ["CWSANDBOX_API_KEY"] + (
    ["FORGE_API_KEY"] if args.agent == "mini" else []
):
    if not os.environ.get(key):
        parser.error(f"Set {key} in the environment")

os.environ["OPENAI_API_KEY"] = os.environ["FORGE_API_KEY"]

uv run --locked python - <<'PY'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.inference.wandb.ai/v1",
    api_key=os.environ["FORGE_API_KEY"],
    timeout=60,
)
response = client.chat.completions.create(
    model="moonshotai/Kimi-K2.7-Code",
    messages=[{"role": "user", "content": "Respond with exactly OK."}],
    max_tokens=64,
)
print(response.choices[0].message.content)
PY

uv run --locked python run.py \
  --tasks deep-swe/tasks \
  --task tomlkit-toml-table-converters \
  --steps 160 --agent-timeout 1800 \
  --job-name kimi-smoke

uv run --locked python run.py \
  --tasks deep-swe/tasks \
  --task abs-stepped-slices \
  --task tomlkit-toml-table-converters \
  --steps 160 --agent-timeout 1800 \
  --job-name kimi-sample

uv run --locked python -m json.tool jobs/kimi-sample/result.json

uv run --locked python - <<'PY'
from cwsandbox import AuthStrategy, Sandbox

sandbox = Sandbox.from_id(
    "[SANDBOX-ID]", auth=AuthStrategy.COREWEAVE_API_KEY
).result()
sandbox.stop(missing_ok=True).result()
PY