RAHUL-13 commited on
Commit
29ff1ff
·
verified ·
1 Parent(s): 7ee7de1

Upload openenv.yaml with huggingface_hub

Browse files
Files changed (1) hide show
  1. openenv.yaml +99 -0
openenv.yaml ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ name: bug_report_structuring
2
+ description: >
3
+ An OpenEnv environment that challenges LLM agents to convert messy,
4
+ unstructured bug reports into well-organized structured formats.
5
+ Tests extraction, classification, and structuring capabilities.
6
+
7
+ version: "1.0.0"
8
+ author: SAI-RAHUL-ROKKAM
9
+
10
+ environment:
11
+ type: text
12
+ interface: http
13
+ endpoints:
14
+ reset: POST /reset
15
+ step: POST /step
16
+ state: GET /state
17
+ health: GET /health
18
+
19
+ tasks:
20
+ - id: easy
21
+ name: Simple Bug Report
22
+ description: >
23
+ Single clear bug with all information present but poorly formatted.
24
+ Login button freeze on Chrome.
25
+ difficulty: easy
26
+ max_steps: 3
27
+
28
+ - id: medium
29
+ name: Multi-Symptom Bug Report
30
+ description: >
31
+ Multiple symptoms with ambiguity and partial information.
32
+ Search results stale, filter broken, HTML rendering issue.
33
+ difficulty: medium
34
+ max_steps: 4
35
+
36
+ - id: hard
37
+ name: Compound Technical Report
38
+ description: >
39
+ Multiple distinct bugs with detailed technical information.
40
+ Analytics dashboard with 3 separate issues requiring decomposition.
41
+ difficulty: hard
42
+ max_steps: 5
43
+
44
+ scoring:
45
+ type: weighted_average
46
+ range: [0.0, 1.0]
47
+ dimensions:
48
+ - name: title
49
+ weight: 0.15
50
+ description: Clear, descriptive bug title
51
+ - name: steps_to_reproduce
52
+ weight: 0.25
53
+ description: Complete step-by-step reproduction instructions
54
+ - name: expected_behavior
55
+ weight: 0.15
56
+ description: Accurate expected behavior description
57
+ - name: actual_behavior
58
+ weight: 0.15
59
+ description: Accurate actual behavior description
60
+ - name: severity
61
+ weight: 0.15
62
+ description: Correct severity classification
63
+ - name: environment
64
+ weight: 0.10
65
+ description: Platform and version details
66
+ - name: format
67
+ weight: 0.05
68
+ description: Structural completeness
69
+
70
+ action_schema:
71
+ type: object
72
+ properties:
73
+ title:
74
+ type: string
75
+ description: Clear, concise bug title
76
+ steps_to_reproduce:
77
+ type: string
78
+ description: Numbered reproduction steps
79
+ expected_behavior:
80
+ type: string
81
+ description: What should happen
82
+ actual_behavior:
83
+ type: string
84
+ description: What actually happens
85
+ severity:
86
+ type: string
87
+ enum: [low, medium, high, critical]
88
+ environment:
89
+ type: string
90
+ description: OS, browser, version info
91
+ additional_notes:
92
+ type: string
93
+ description: Any other relevant details
94
+
95
+ deployment:
96
+ platform: huggingface_spaces
97
+ sdk: docker
98
+ port: 7860
99
+ hardware: cpu-basic