Spaces:
Sleeping
Sleeping
commit
Browse files- openenv.yaml +6 -77
openenv.yaml
CHANGED
|
@@ -1,77 +1,6 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
from easy syntax checks up to multi-vulnerability security audits.
|
| 8 |
-
|
| 9 |
-
author: Simran Shaikh
|
| 10 |
-
tags:
|
| 11 |
-
- openenv
|
| 12 |
-
- code-review
|
| 13 |
-
- security
|
| 14 |
-
- software-engineering
|
| 15 |
-
- real-world
|
| 16 |
-
|
| 17 |
-
language: python
|
| 18 |
-
|
| 19 |
-
tasks:
|
| 20 |
-
- id: easy_syntax
|
| 21 |
-
name: "Python Syntax Error Detection"
|
| 22 |
-
difficulty: easy
|
| 23 |
-
max_steps: 5
|
| 24 |
-
description: >
|
| 25 |
-
Identify and fix a syntax error hidden in a short Python function.
|
| 26 |
-
Graded on: correct issue_type, description accuracy, and fix validity.
|
| 27 |
-
|
| 28 |
-
- id: medium_logic
|
| 29 |
-
name: "Logic Bug: Off-by-One in Palindrome Check"
|
| 30 |
-
difficulty: medium
|
| 31 |
-
max_steps: 8
|
| 32 |
-
description: >
|
| 33 |
-
Find and fix a subtle off-by-one indexing bug in a palindrome checker.
|
| 34 |
-
Fix is verified by executing 5 deterministic test cases.
|
| 35 |
-
|
| 36 |
-
- id: hard_security
|
| 37 |
-
name: "Security Vulnerability: SQL Injection, Path Traversal & Weak Hashing"
|
| 38 |
-
difficulty: hard
|
| 39 |
-
max_steps: 10
|
| 40 |
-
description: >
|
| 41 |
-
Perform a full security audit of an authentication module containing
|
| 42 |
-
three distinct vulnerabilities. All must be identified and remediated.
|
| 43 |
-
|
| 44 |
-
api:
|
| 45 |
-
reset: POST /reset
|
| 46 |
-
step: POST /step
|
| 47 |
-
state: GET /state
|
| 48 |
-
tasks: GET /tasks
|
| 49 |
-
|
| 50 |
-
reward:
|
| 51 |
-
min: 0.0
|
| 52 |
-
max: 1.0
|
| 53 |
-
type: continuous
|
| 54 |
-
partial_credit: true
|
| 55 |
-
|
| 56 |
-
observation_space:
|
| 57 |
-
task_id: string
|
| 58 |
-
task_name: string
|
| 59 |
-
difficulty: string
|
| 60 |
-
language: string
|
| 61 |
-
code_snippet: string
|
| 62 |
-
context: string
|
| 63 |
-
step_number: integer
|
| 64 |
-
max_steps: integer
|
| 65 |
-
previous_feedback: string | null
|
| 66 |
-
|
| 67 |
-
action_space:
|
| 68 |
-
identified_issues:
|
| 69 |
-
type: array
|
| 70 |
-
items:
|
| 71 |
-
line_number: integer | null
|
| 72 |
-
issue_type: "syntax_error | logic_bug | security_vulnerability | performance | style"
|
| 73 |
-
description: string
|
| 74 |
-
severity: "low | medium | high | critical"
|
| 75 |
-
suggested_fix: string | null
|
| 76 |
-
explanation: string
|
| 77 |
-
done: boolean
|
|
|
|
| 1 |
+
spec_version: 1
|
| 2 |
+
name: code_review_env
|
| 3 |
+
type: space
|
| 4 |
+
runtime: fastapi
|
| 5 |
+
app: server.app:app
|
| 6 |
+
port: 7860
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|