lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ver Jan31stv7

Browse Source 
fixed an error in thunderbird evaluation
This commit is contained in:
David Chang
2024-02-01 00:17:41 +08:00
parent 4897211a46
commit a1e02c6d57
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
evaluation_examples/examples/thunderbird/030eeff7-b492-4218-b312-701ec99ee0cc.json
View File

@@ -68,7 +68,7 @@
"expected": {
"type": "rule",
"rules": {
"unexpect": {
"expect": {
"mail.identity.id1.auto_quote": {
"method": "eq",
"ref": false

2
main.py
View File

@@ -47,7 +47,7 @@ def human_agent():
Runs the Gym environment with human input.
"""
with open("evaluation_examples/examples/libreoffice_calc/4f07fbe9-70de-4927-a4d5-bb28bc12c52c.json", "r") as f:
with open("evaluation_examples/examples/thunderbird/030eeff7-b492-4218-b312-701ec99ee0cc.json", "r") as f:
example = json.load(f)
example["snapshot"] = "Snapshot 30"