Spaces:
Running
Running
File size: 9,706 Bytes
ff9fcbd | 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 | """
FastAPI application for the Code Review Environment.
Endpoints:
POST /reset — start new episode
POST /step — take an action
GET /state — get episode state
GET /health — health check
GET /tasks — list all tasks + action schema
POST /grader — grade a set of findings (stateless)
POST /baseline — run keyword-heuristic baseline on all tasks
WS /ws — persistent WebSocket session
GET /docs — Swagger UI (auto-generated)
"""
from __future__ import annotations
import sys
import os
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import json
import asyncio
import dataclasses
from typing import Optional, List, Dict, Any
from fastapi import FastAPI, WebSocket, WebSocketDisconnect, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
from models import ReviewAction, Issue
from server.environment import CodeReviewEnvironment
from server.graders import grade_episode, run_keyword_baseline
from tasks.data import ALL_TASKS, TASK_IDS
def _serialize(obj) -> dict:
if dataclasses.is_dataclass(obj) and not isinstance(obj, type):
d = dataclasses.asdict(obj)
# asdict handles nested dataclasses and lists recursively
return d
if isinstance(obj, dict):
return obj
raise TypeError(f"Cannot serialize {type(obj)}")
_env_instance = CodeReviewEnvironment()
def _make_app() -> FastAPI:
try:
from openenv.core.env_server import create_fastapi_app
base = create_fastapi_app(CodeReviewEnvironment)
return base
except Exception:
pass
_app = FastAPI(
title="Code Review Environment",
description=(
"An OpenEnv environment for training AI agents to perform "
"code review and security audits."
),
version="1.0.0",
)
_app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_methods=["*"],
allow_headers=["*"],
)
@_app.get("/health")
async def health():
return {"status": "healthy"}
@_app.post("/reset")
async def reset(body: dict = None):
body = body or {}
task_id = body.get("task_id")
seed = body.get("seed")
episode_id = body.get("episode_id")
obs = _env_instance.reset(task_id=task_id, seed=seed, episode_id=episode_id)
return _serialize(obs)
@_app.post("/step")
async def step(body: dict):
action = ReviewAction.from_dict(body)
obs = _env_instance.step(action)
return _serialize(obs)
@_app.get("/state")
async def state():
return _serialize(_env_instance.state)
@_app.websocket("/ws")
async def websocket_endpoint(websocket: WebSocket):
await websocket.accept()
ws_env = CodeReviewEnvironment()
try:
while True:
raw = await websocket.receive_text()
msg = json.loads(raw)
msg_type = msg.get("type", "")
if msg_type == "reset":
data = msg.get("data", {})
obs = ws_env.reset(
task_id=data.get("task_id"),
seed=data.get("seed"),
episode_id=data.get("episode_id"),
)
await websocket.send_text(json.dumps({
"type": "observation",
"data": _serialize(obs),
}))
elif msg_type == "step":
action = ReviewAction.from_dict(msg.get("data", {}))
obs = ws_env.step(action)
await websocket.send_text(json.dumps({
"type": "observation",
"data": _serialize(obs),
}))
elif msg_type == "state":
await websocket.send_text(json.dumps({
"type": "state",
"data": _serialize(ws_env.state),
}))
elif msg_type == "close":
break
else:
await websocket.send_text(json.dumps({
"type": "error",
"data": f"Unknown message type: {msg_type}",
}))
except WebSocketDisconnect:
pass
except Exception as e:
try:
await websocket.send_text(json.dumps({"type": "error", "data": str(e)}))
except Exception:
pass
return _app
app = _make_app()
@app.get("/tasks")
async def list_tasks():
tasks_list = []
for task in ALL_TASKS.values():
tasks_list.append({
"task_id": task["task_id"],
"difficulty": task["difficulty"],
"description": task["description"],
"language": task.get("language", "python"),
"max_steps": task["max_steps"],
"num_issues": len(task["ground_truth_issues"]),
"files": list(task["code_files"].keys()),
})
action_schema = {
"type": "object",
"description": "ReviewAction — one action per /step call",
"required": ["action_type"],
"properties": {
"action_type": {
"type": "string",
"enum": ["flag_issue", "clear_flag", "request_hint", "submit_review"],
"description": (
"flag_issue: mark a line as problematic. "
"clear_flag: remove a previous flag. "
"request_hint: get a hint (-0.01 reward). "
"submit_review: end episode and receive final grade."
),
},
"line_number": {
"type": "integer",
"description": "Line number of the issue (required for flag_issue / clear_flag)",
},
"filename": {
"type": "string",
"description": "File where the issue is (required for flag_issue / clear_flag)",
},
"issue_type": {
"type": "string",
"enum": ["bug", "security", "performance", "logic"],
"description": "Category of issue (required for flag_issue)",
},
"severity": {
"type": "string",
"enum": ["low", "medium", "high", "critical"],
"description": "Severity level (required for flag_issue)",
},
"description": {
"type": "string",
"description": "Human-readable description of the issue",
},
"fix_suggestion": {
"type": "string",
"description": "Optional suggested fix",
},
},
"examples": [
{
"action_type": "flag_issue",
"line_number": 6,
"filename": "utils.py",
"issue_type": "bug",
"severity": "high",
"description": "Off-by-one error in range()",
"fix_suggestion": "Change range(len(numbers) + 1) to range(len(numbers))",
},
{"action_type": "submit_review"},
],
}
return {
"tasks": tasks_list,
"action_schema": action_schema,
"total_tasks": len(tasks_list),
}
class GraderRequest(BaseModel):
task_id: str
flagged_issues: List[Dict[str, Any]]
@app.post("/grader")
async def run_grader(request: GraderRequest):
task = ALL_TASKS.get(request.task_id)
if not task:
raise HTTPException(
status_code=404,
detail=f"Unknown task_id '{request.task_id}'. Valid: {TASK_IDS}",
)
flagged = [Issue.from_dict(i) for i in request.flagged_issues]
ground_truth = [Issue.from_dict(gt) for gt in task["ground_truth_issues"]]
score = grade_episode(flagged, ground_truth)
tp = sum(
1 for f in flagged
if any(
True for gt in ground_truth
if abs(f.line_number - gt.line_number) <= 2
and f.filename == gt.filename
)
)
return {
"task_id": request.task_id,
"difficulty": task["difficulty"],
"score": score,
"max_score": 1.0,
"details": {
"total_flagged": len(flagged),
"true_positives": tp,
"false_positives": len(flagged) - tp,
"total_ground_truth": len(ground_truth),
},
}
@app.post("/baseline")
async def run_baseline():
results = {}
for task_id, task in ALL_TASKS.items():
findings = run_keyword_baseline(task)
ground_truth = [Issue.from_dict(gt) for gt in task["ground_truth_issues"]]
score = grade_episode(findings, ground_truth)
results[task_id] = {
"difficulty": task["difficulty"],
"score": score,
"findings_count": len(findings),
"ground_truth_count": len(ground_truth),
}
overall = sum(r["score"] for r in results.values()) / len(results)
return {
"baseline_scores": results,
"overall_average": round(overall, 4),
"method": "keyword_heuristic",
"note": (
"Run 'python baseline.py' with OPENAI_API_KEY for the LLM-based baseline. "
"This endpoint uses a deterministic regex heuristic."
),
}
def main():
import uvicorn
port = int(os.environ.get("PORT", 7860))
uvicorn.run("server.app:app", host="0.0.0.0", port=port)
if __name__ == "__main__":
main()
|