Step 222: workflow evaluation tasks
This commit is contained in:
20
eval/workflows/workflow_01.json
Normal file
20
eval/workflows/workflow_01.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_01",
|
||||
"description": "Annotate all functions in module",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_02.json
Normal file
20
eval/workflows/workflow_02.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_02",
|
||||
"description": "Annotate all functions in module",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_03.json
Normal file
20
eval/workflows/workflow_03.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_03",
|
||||
"description": "Annotate all functions in module",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
18
eval/workflows/workflow_04.json
Normal file
18
eval/workflows/workflow_04.json
Normal file
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"id": "workflow_04",
|
||||
"description": "Cross-language projection with fixes",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_project",
|
||||
"whetstone_run_pipeline"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_project",
|
||||
"whetstone_run_pipeline"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
18
eval/workflows/workflow_05.json
Normal file
18
eval/workflows/workflow_05.json
Normal file
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"id": "workflow_05",
|
||||
"description": "Cross-language projection with fixes",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_project",
|
||||
"whetstone_run_pipeline"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_project",
|
||||
"whetstone_run_pipeline"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
18
eval/workflows/workflow_06.json
Normal file
18
eval/workflows/workflow_06.json
Normal file
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"id": "workflow_06",
|
||||
"description": "Cross-language projection with fixes",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_project",
|
||||
"whetstone_run_pipeline"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_project",
|
||||
"whetstone_run_pipeline"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
18
eval/workflows/workflow_07.json
Normal file
18
eval/workflows/workflow_07.json
Normal file
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"id": "workflow_07",
|
||||
"description": "Cross-language projection with fixes",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_project",
|
||||
"whetstone_run_pipeline"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_project",
|
||||
"whetstone_run_pipeline"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
18
eval/workflows/workflow_08.json
Normal file
18
eval/workflows/workflow_08.json
Normal file
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"id": "workflow_08",
|
||||
"description": "Cross-language projection with fixes",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_project",
|
||||
"whetstone_run_pipeline"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_project",
|
||||
"whetstone_run_pipeline"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_09.json
Normal file
20
eval/workflows/workflow_09.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_09",
|
||||
"description": "Refactor pattern with batch mutate",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_mutate",
|
||||
"whetstone_run_pipeline"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_mutate",
|
||||
"whetstone_run_pipeline"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_10.json
Normal file
20
eval/workflows/workflow_10.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_10",
|
||||
"description": "Refactor pattern with batch mutate",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_mutate",
|
||||
"whetstone_run_pipeline"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_mutate",
|
||||
"whetstone_run_pipeline"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_11.json
Normal file
20
eval/workflows/workflow_11.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_11",
|
||||
"description": "Refactor pattern with batch mutate",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_mutate",
|
||||
"whetstone_run_pipeline"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_mutate",
|
||||
"whetstone_run_pipeline"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_12.json
Normal file
20
eval/workflows/workflow_12.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_12",
|
||||
"description": "Refactor pattern with batch mutate",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_mutate",
|
||||
"whetstone_run_pipeline"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_mutate",
|
||||
"whetstone_run_pipeline"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_13.json
Normal file
20
eval/workflows/workflow_13.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_13",
|
||||
"description": "Refactor pattern with batch mutate",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_mutate",
|
||||
"whetstone_run_pipeline"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_get_ast",
|
||||
"whetstone_mutate",
|
||||
"whetstone_run_pipeline"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_14.json
Normal file
20
eval/workflows/workflow_14.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_14",
|
||||
"description": "Debug annotation errors and revalidate",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_run_pipeline",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_run_pipeline",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_15.json
Normal file
20
eval/workflows/workflow_15.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_15",
|
||||
"description": "Debug annotation errors and revalidate",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_run_pipeline",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_run_pipeline",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_16.json
Normal file
20
eval/workflows/workflow_16.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_16",
|
||||
"description": "Debug annotation errors and revalidate",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_run_pipeline",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_run_pipeline",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_17.json
Normal file
20
eval/workflows/workflow_17.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_17",
|
||||
"description": "Debug annotation errors and revalidate",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_run_pipeline",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_run_pipeline",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
20
eval/workflows/workflow_18.json
Normal file
20
eval/workflows/workflow_18.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"id": "workflow_18",
|
||||
"description": "Debug annotation errors and revalidate",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
"whetstone_run_pipeline",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
"whetstone_run_pipeline",
|
||||
"whetstone_suggest_annotations",
|
||||
"whetstone_apply_annotation"
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
16
eval/workflows/workflow_19.json
Normal file
16
eval/workflows/workflow_19.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"id": "workflow_19",
|
||||
"description": "",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
16
eval/workflows/workflow_20.json
Normal file
16
eval/workflows/workflow_20.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"id": "workflow_20",
|
||||
"description": "",
|
||||
"language": "python",
|
||||
"setupAst": "def f(x):\\n return x + 1\\n\\ndef g(y):\\n return y * 2\\n",
|
||||
"expectedOutcome": {
|
||||
"toolCalls": [
|
||||
|
||||
]
|
||||
},
|
||||
"tools": [
|
||||
|
||||
],
|
||||
"maxSteps": 12,
|
||||
"allowPartial": true
|
||||
}
|
||||
Reference in New Issue
Block a user