Fix challenges (#5561)

Fix challenges and CI

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

.github/workflows/autogpts-ci.yml

@@ -39,8 +39,7 @@ jobs:
 
       - name: Run regression tests
         run: |
-          ./run agent start ${{ matrix.agent-name }}
+          ./run agent start ${{ matrix.agent-name }} --setup
-          sleep 10
           cd autogpts/${{ matrix.agent-name }}
           poetry run agbenchmark --mock
           poetry run agbenchmark --test=WriteFile

.github/workflows/benchmark-ci.yml

@@ -98,7 +98,7 @@ jobs:
 
       - name: Run regression tests
         run: |
-          ./run agent start ${{ matrix.agent-name }}
+          ./run agent start ${{ matrix.agent-name }} --setup
           sleep 10
           cd autogpts/${{ matrix.agent-name }}
           set +e # Ignore non-zero exit codes and continue execution

benchmark/agbenchmark/challenges/verticals/data/2_label_csv/data.json

@@ -16,7 +16,7 @@
             "output.csv"
         ],
         "should_contain": [
-            "Item, Color\nBanana, Yellow\nLeaf, Green\nSky, Blue\nSunflower, Yellow\nGrass, Green\nJeans, Blue\nLemon, Yellow\nTree, Green\nOcean, Blue\nDaisy, Yellow\nFern, Green"
+            "Item,Color\nBanana,yellow\nLeaf,green\nSky,blue\nSunflower,yellow\nGrass,green\nJeans,blue\nLemon,yellow\nTree,green\nOcean,blue\nDaisy,yellow\nFern,green"
         ]
     },
     "info": {

frontend/assets/data_tree_structure.json

@@ -301,7 +301,7 @@
                         "output.csv"
                     ],
                     "should_contain": [
-                        "Item, Color\nBanana, Yellow\nLeaf, Green\nSky, Blue\nSunflower, Yellow\nGrass, Green\nJeans, Blue\nLemon, Yellow\nTree, Green\nOcean, Blue\nDaisy, Yellow\nFern, Green"
+                        "Item,Color\nBanana,yellow\nLeaf,green\nSky,blue\nSunflower,yellow\nGrass,green\nJeans,blue\nLemon,yellow\nTree,green\nOcean,blue\nDaisy,yellow\nFern,green"
                     ]
                 },
                 "info": {

frontend/assets/scrape_synthesize_tree_structure.json

@@ -289,7 +289,7 @@
                     ]
                 },
                 "name": "TestRevenueRetrieval2",
-                "task": "Write tesla's revenue every year since its creation into a .txt file. Use the US notation, with a precision rounded to the nearest million dollars (for instance, $31,578 billion)."
+                "task": "Write tesla's revenue every year since its creation into a .txt file. Use the US notation, with a precision rounded to the nearest million dollars (for instance, $31,578 million)."
             },
             "id": "agbenchmark/generate_test.py::TestRevenueRetrieval2::test_method[challenge_data0]",
             "label": "RevenueRetrieval2",
@@ -326,7 +326,7 @@
                     "side_effects": []
                 },
                 "name": "TestRevenueRetrieval",
-                "task": "Write tesla's exact revenue in 2022 into a .txt file. Use the US notation, with a precision rounded to the nearest million dollars (for instance, $31,578 billion)."
+                "task": "Write tesla's exact revenue in 2022 into a .txt file. Use the US notation, with a precision rounded to the nearest million dollars (for instance, $31,578 million)."
             },
             "id": "agbenchmark/generate_test.py::TestRevenueRetrieval::test_method[challenge_data0]",
             "label": "RevenueRetrieval",