Spaces:
Build error
Build error
File size: 12,924 Bytes
c8e832f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 | """Static PR-review tasks and hidden grading rubrics."""
from __future__ import annotations
from dataclasses import dataclass, field
from typing import Dict, Iterable, List, Sequence
try:
from models import Category, Difficulty, Severity, TaskDescriptor, TaskSummary
except ModuleNotFoundError: # pragma: no cover
from ..models import Category, Difficulty, Severity, TaskDescriptor, TaskSummary
@dataclass(frozen=True)
class RubricIssue:
"""One hidden issue that can be matched by the deterministic grader."""
issue_id: str
file_path: str
line: int
category: Category
severity: Severity
keywords: Sequence[str]
min_keyword_hits: int
weight: float
@dataclass(frozen=True)
class TaskSpec:
"""Complete task definition, including hidden rubric metadata."""
task_id: str
difficulty: Difficulty
title: str
goal: str
repo_summary: str
visible_diff: str
file_contents: Dict[str, str]
changed_files: Sequence[str]
rubric_issues: Sequence[RubricIssue]
max_steps: int
@property
def available_files(self) -> List[str]:
return list(self.file_contents.keys())
def to_descriptor(self) -> TaskDescriptor:
return TaskDescriptor(
task_id=self.task_id,
difficulty=self.difficulty,
title=self.title,
goal=self.goal,
repo_summary=self.repo_summary,
changed_files=list(self.changed_files),
available_files=self.available_files,
max_steps=self.max_steps,
)
def to_summary(self) -> TaskSummary:
return TaskSummary(
task_id=self.task_id,
difficulty=self.difficulty,
title=self.title,
goal=self.goal,
)
TASKS: List[TaskSpec] = [
TaskSpec(
task_id="py-pr-review-easy",
difficulty="easy",
title="Retry Delay Regression",
goal=(
"Review the pull request and identify the real bug introduced in the retry "
"delay helper before it ships."
),
repo_summary=(
"This service computes retry delays for background notification delivery. "
"The change is intended to relax validation for legacy callers."
),
visible_diff="\n".join(
[
"diff --git a/src/notifications/retry.py b/src/notifications/retry.py",
"@@",
"- if base_delay <= 0:",
"+ if base_delay < 0:",
" return 0.0",
]
),
file_contents={
"src/notifications/retry.py": "\n".join(
[
"from __future__ import annotations",
"",
"def calculate_retry_delay(attempt: int, base_delay: float = 2.0) -> float:",
' """Return the retry delay in seconds."""',
" if attempt < 0:",
' raise ValueError(\"attempt must be >= 0\")',
" if base_delay < 0:",
" return 0.0",
" return attempt / base_delay",
]
)
},
changed_files=("src/notifications/retry.py",),
rubric_issues=(
RubricIssue(
issue_id="zero-base-delay-divides",
file_path="src/notifications/retry.py",
line=7,
category="bug",
severity="warning",
keywords=("zero", "division", "base_delay"),
min_keyword_hits=2,
weight=1.0,
),
),
max_steps=4,
),
TaskSpec(
task_id="py-pr-review-medium",
difficulty="medium",
title="Coupon Billing Rollout",
goal=(
"Review the billing change and identify both the production regression and "
"the missing coverage that would have caught it."
),
repo_summary=(
"The billing service is adding coupon support for one-off invoices. The PR "
"touches both the service code and its unit tests."
),
visible_diff="\n".join(
[
"diff --git a/app/billing/invoice_service.py b/app/billing/invoice_service.py",
"@@",
" def charge_invoice(order: dict, gateway: Gateway) -> str:",
"- return gateway.charge(order[\"customer_id\"], order[\"amount_cents\"])",
"+ total = order[\"amount_cents\"]",
"+ coupon = order.get(\"coupon_code\")",
"+ if coupon:",
"+ discount = gateway.lookup_discount(coupon)",
"+ total = max(total - discount, 0)",
"+ return gateway.charge(order[\"customer_id\"], order[\"amount_cents\"])",
"",
"diff --git a/tests/test_invoice_service.py b/tests/test_invoice_service.py",
"@@",
" class FakeGateway:",
"+ def lookup_discount(self, coupon: str) -> int:",
"+ return 250",
]
),
file_contents={
"app/billing/invoice_service.py": "\n".join(
[
"from gateway import Gateway",
"",
"def charge_invoice(order: dict, gateway: Gateway) -> str:",
' total = order["amount_cents"]',
' coupon = order.get("coupon_code")',
" if coupon:",
" discount = gateway.lookup_discount(coupon)",
" total = max(total - discount, 0)",
' return gateway.charge(order["customer_id"], order["amount_cents"])',
]
),
"tests/test_invoice_service.py": "\n".join(
[
"from app.billing.invoice_service import charge_invoice",
"",
"class FakeGateway:",
" def lookup_discount(self, coupon: str) -> int:",
" return 250",
"",
" def charge(self, customer_id: str, amount_cents: int) -> str:",
" self.last_charge = (customer_id, amount_cents)",
' return "charge_123"',
"",
"def test_charge_invoice_without_coupon():",
" gateway = FakeGateway()",
' charge_invoice({"customer_id": "cus_1", "amount_cents": 1000}, gateway)',
' assert gateway.last_charge == ("cus_1", 1000)',
]
),
},
changed_files=("app/billing/invoice_service.py", "tests/test_invoice_service.py"),
rubric_issues=(
RubricIssue(
issue_id="discount-total-unused",
file_path="app/billing/invoice_service.py",
line=8,
category="bug",
severity="warning",
keywords=("discount", "total", "charge", "amount"),
min_keyword_hits=2,
weight=0.6,
),
RubricIssue(
issue_id="missing-coupon-test",
file_path="tests/test_invoice_service.py",
line=11,
category="testing",
severity="warning",
keywords=("missing", "test", "coupon", "discount"),
min_keyword_hits=2,
weight=0.4,
),
),
max_steps=5,
),
TaskSpec(
task_id="py-pr-review-hard",
difficulty="hard",
title="Async Job Runner Deduplication",
goal=(
"Review the async job-runner PR and find the subtle concurrency issues "
"without inventing extra problems."
),
repo_summary=(
"A shared webhook backfill service is deduplicating in-flight work with an "
"async task cache and writing the latest result for operators to inspect."
),
visible_diff="\n".join(
[
"diff --git a/app/jobs/runner.py b/app/jobs/runner.py",
"@@",
" async def run_job(job_id: str, payload: dict, worker) -> str:",
" if job_id in ACTIVE_RUNS:",
" return await ACTIVE_RUNS[job_id]",
"+ lock = asyncio.Lock()",
"+ async with lock:",
"+ task = asyncio.create_task(worker.run(payload))",
"+ ACTIVE_RUNS[job_id] = task",
" try:",
" result = await task",
" finally:",
" ACTIVE_RUNS.pop(job_id, None)",
"+ Path(\"latest-result.json\").write_text(result)",
" return result",
]
),
file_contents={
"app/jobs/runner.py": "\n".join(
[
"import asyncio",
"from pathlib import Path",
"",
"ACTIVE_RUNS: dict[str, asyncio.Task[str]] = {}",
"",
"async def run_job(job_id: str, payload: dict, worker) -> str:",
" if job_id in ACTIVE_RUNS:",
" return await ACTIVE_RUNS[job_id]",
"",
" lock = asyncio.Lock()",
" async with lock:",
" task = asyncio.create_task(worker.run(payload))",
" ACTIVE_RUNS[job_id] = task",
" try:",
" result = await task",
" finally:",
" ACTIVE_RUNS.pop(job_id, None)",
"",
' Path("latest-result.json").write_text(result)',
" return result",
]
),
"tests/test_runner.py": "\n".join(
[
"import pytest",
"",
"from app.jobs.runner import run_job",
"",
"class FakeWorker:",
" async def run(self, payload: dict) -> str:",
' return payload["job_id"]',
"",
"@pytest.mark.asyncio",
"async def test_run_job_returns_worker_result():",
" worker = FakeWorker()",
' result = await run_job("job-1", {"job_id": "job-1"}, worker)',
' assert result == "job-1"',
]
),
},
changed_files=("app/jobs/runner.py", "tests/test_runner.py"),
rubric_issues=(
RubricIssue(
issue_id="per-call-lock-race",
file_path="app/jobs/runner.py",
line=9,
category="bug",
severity="warning",
keywords=("lock", "race", "concurrent", "duplicate"),
min_keyword_hits=2,
weight=0.55,
),
RubricIssue(
issue_id="shared-output-file-race",
file_path="app/jobs/runner.py",
line=18,
category="maintainability",
severity="warning",
keywords=("latest", "result", "file", "concurrent", "overwrite"),
min_keyword_hits=2,
weight=0.45,
),
),
max_steps=6,
),
]
TASKS_BY_ID: Dict[str, TaskSpec] = {task.task_id: task for task in TASKS}
def list_task_descriptors() -> List[TaskDescriptor]:
"""Return public descriptors for all tasks."""
return [task.to_descriptor() for task in TASKS]
def list_task_summaries() -> List[TaskSummary]:
"""Return task summaries for lightweight route responses."""
return [task.to_summary() for task in TASKS]
def get_task(task_id: str) -> TaskSpec:
"""Return a task by id."""
try:
return TASKS_BY_ID[task_id]
except KeyError as exc: # pragma: no cover
raise ValueError(f"Unknown task_id: {task_id}") from exc
def task_ids() -> Iterable[str]:
"""Return task ids in benchmark order."""
return [task.task_id for task in TASKS]
|