Update Score In Pull Request Number 4499

.github/workflows/ci.yml

@@ -119,17 +119,14 @@ jobs:
 
       - name: Run pytest tests with coverage
         run: |
-          pytest -n auto --cov=autogpt --cov-report term-missing --cov-branch --cov-report xml --cov-report term
+          pytest tests/integration/challenges/basic_abilities/test_write_file.py
           python tests/integration/challenges/utils/build_current_score.py
         env:
           CI: true
           PROXY: ${{ secrets.PROXY }}
           AGENT_MODE: ${{ vars.AGENT_MODE }}
           AGENT_TYPE: ${{ vars.AGENT_TYPE }}
 
-      - name: Upload coverage reports to Codecov
-        uses: codecov/codecov-action@v3
-
       - name: Update cassette submodule to push target if push event
         if: ${{ github.event_name == 'push' }}
         run: |
@@ -177,7 +174,7 @@ jobs:
 
           # Check if there are any changes
           if ! git diff-index --quiet HEAD; then
-              git commit -m "Auto-update cassettes after merging PR #$pr_number"
+              git commit -m "Auto-update cassettes after merging PR #${{ github.event.pull_request.number }}"
               git push -f origin HEAD:refs/heads/$new_branch
 
           else
@@ -193,10 +190,67 @@ jobs:
             echo "DIFF_EXISTS=false" >> $GITHUB_ENV
           fi
 
+      - name: Beat Challenges
+        if: ${{ env.DIFF_EXISTS == 'true' }}
+        run: |
+          pytest -n auto tests/integration/challenges/memory/test_memory_challenge_c.py tests/integration/challenges/basic_abilities/test_write_file.py --beat-challenges --cov=autogpt --cov-report term-missing --cov-branch --cov-report xml --cov-report term
+          python tests/integration/challenges/utils/build_current_score.py
+        env:
+          CI: true
+          PROXY: ${{ secrets.PROXY }}
+          AGENT_MODE: ${{ vars.AGENT_MODE }}
+          AGENT_TYPE: ${{ vars.AGENT_TYPE }}
+
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v3
+
+      - name: Beat challenges - Update cassette submodule to submodule branch if PR event
+        if: ${{ env.DIFF_EXISTS == 'true' }}
+        run: |
+          new_branch="${{ github.event.pull_request.user.login }}-${{ github.event.pull_request.head.ref }}"
+
+          cd tests/Auto-GPT-test-cassettes
+          git config --global user.name "Auto-GPT-Bot"
+          git config --global user.email "github-bot@agpt.co"
+          git add .
+
+          # Check if there are any changes
+          if ! git diff-index --quiet HEAD; then
+              git commit -m "Auto-update cassettes after merging PR #${{ github.event.pull_request.number }} (Beat challenges)"
+              git push -f origin HEAD:refs/heads/$new_branch
+
+          else
+              echo "No changes to commit"
+              exit 0
+          fi
+
+      - name: Create Pull Request
+        if: ${{ env.DIFF_EXISTS == 'true' }}
+        run: |
+          current_date_time=$(date +'%Y%m%d%H%M%S')
+          new_branch="update-score-${{ github.event.pull_request.number }}-$current_date_time"
+
+          git config --global user.name "Auto-GPT-Bot"
+          git config --global user.email "github-bot@agpt.co"
+          git add tests/integration/challenges/current_score.json
+          if ! git diff-index --quiet HEAD; then
+            git commit -m "Update score"
+            git checkout -b $new_branch
+            git push origin $new_branch
+
+            echo ${{ secrets.PAT_REVIEW }} | gh auth login --with-token
+            gh pr create --title "Update Score In Pull Request Number ${{ github.event.pull_request.number }}" \
+            --head "$new_branch" \
+            --base "${{ github.event.pull_request.head.ref }}" \
+            --body "This pull request updates the current score of Auto-GPT. Please check the files changed and merge the pull request." \
+            --repo ${{ github.event.pull_request.head.repo.full_name }}
+          else
+            echo "The current score didn't change."
+          fi
+
       - name: Apply or remove behaviour change label and comment
         if: ${{ github.event_name == 'pull_request_target' }}
         run: |
-          PR_NUMBER=${{ github.event.pull_request.number }}
           TOKEN=${{ secrets.PAT_REVIEW }}
           REPO=${{ github.repository }}
 
@@ -205,15 +259,15 @@ jobs:
             curl -X POST \
             -H "Authorization: Bearer $TOKEN" \
             -H "Accept: application/vnd.github.v3+json" \
-            https://api.github.com/repos/$REPO/issues/$PR_NUMBER/labels \
+            https://api.github.com/repos/$REPO/issues/${{ github.event.pull_request.number }}/labels \
             -d '{"labels":["behaviour change"]}'
 
             echo $TOKEN | gh auth login --with-token
-            gh api repos/$REPO/issues/$PR_NUMBER/comments -X POST -F body="You changed AutoGPT's behaviour. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
+            gh api repos/$REPO/issues/${{ github.event.pull_request.number }}/comments -X POST -F body="You changed AutoGPT's behaviour. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
           else
             echo "Removing label..."
             curl -X DELETE \
             -H "Authorization: Bearer $TOKEN" \
             -H "Accept: application/vnd.github.v3+json" \
-            https://api.github.com/repos/$REPO/issues/$PR_NUMBER/labels/behaviour%20change
+            https://api.github.com/repos/$REPO/issues/${{ github.event.pull_request.number }}/labels/behaviour%20change
           fi

.gitmodules

@@ -1,4 +1,4 @@
 [submodule "tests/Auto-GPT-test-cassettes"]
     path = tests/Auto-GPT-test-cassettes
     url = https://github.com/Significant-Gravitas/Auto-GPT-test-cassettes
-    branch = master
+    branch = ci-test-1

autogpt/llm/utils/__init__.py

@@ -96,7 +96,9 @@ def _wrapped(*args, **kwargs):
                         user_warned = True
 
                 except APIError as e:
-                    if (e.http_status not in [502, 429]) or (attempt == num_attempts):
+                    if (e.http_status not in [502, 429]) or (
+                        attempt == num_attempts
+                    ):
                         raise
 
                 backoff = backoff_base ** (attempt + 2)

tests/integration/agent_factory.py

@@ -81,7 +81,7 @@ def writer_agent(agent_test_config, memory_none: NoMemory, workspace: Workspace)
         ai_role="an AI designed to use the write_to_file command to write 'Hello World' into a file named \"hello_world.txt\" and then use the task_complete command to complete the task.",
         ai_goals=[
             "Use the write_to_file command to write 'Hello World' into a file named \"hello_world.txt\".",
-            "Use the task_complete command to complete the task.",
+            "Use the task_complete command to complete the task!",
             "Do not use any other commands.",
         ],
     )
@@ -116,7 +116,7 @@ def memory_management_agent(agent_test_config, memory_json_file, workspace: Work
 
     ai_config = AIConfig(
         ai_name="Follow-Instructions-GPT",
-        ai_role="an AI designed to read the instructions_1.txt file using the read_file method and follow the instructions in the file.",
+        ai_role="an AI designed to read the instructions_1.txt file using the read_file method and follow the instructions in the file!",
         ai_goals=[
             "Use the command read_file to read the instructions_1.txt file",
             "Follow the instructions in the instructions_1.txt file",

tests/integration/challenges/basic_abilities/test_browse_website.py

@@ -1,4 +1,5 @@
 import pytest
+from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from tests.integration.challenges.challenge_decorator.challenge_decorator import (
@@ -15,7 +16,7 @@
 @challenge
 def test_browse_website(
     browser_agent: Agent,
-    patched_api_requestor: None,
+    patched_api_requestor: MockerFixture,
     monkeypatch: pytest.MonkeyPatch,
     level_to_run: int,
 ) -> None:

tests/integration/challenges/basic_abilities/test_write_file.py

@@ -1,4 +1,5 @@
 import pytest
+from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file
@@ -17,7 +18,7 @@
 @challenge
 def test_write_file(
     writer_agent: Agent,
-    patched_api_requestor: None,
+    patched_api_requestor: MockerFixture,
     monkeypatch: pytest.MonkeyPatch,
     config: Config,
     level_to_run: int,

tests/integration/challenges/current_score.json

@@ -1,47 +1,13 @@
 {
     "basic_abilities": {
-        "browse_website": {
-            "max_level": 1,
-            "max_level_beaten": 1
-        },
         "write_file": {
             "max_level": 1,
             "max_level_beaten": 1
         }
     },
-    "debug_code": {
-        "debug_code_challenge_a": {
-            "max_level": 1,
-            "max_level_beaten": 1
-        }
-    },
-    "information_retrieval": {
-        "information_retrieval_challenge_a": {
-            "max_level": 3,
-            "max_level_beaten": 1
-        },
-        "information_retrieval_challenge_b": {
-            "max_level": 1,
-            "max_level_beaten": 1
-        }
-    },
-    "kubernetes": {
-        "kubernetes_template_challenge_a": {
-            "max_level": 1,
-            "max_level_beaten": null
-        }
-    },
     "memory": {
-        "memory_challenge_a": {
-            "max_level": 3,
-            "max_level_beaten": 3
-        },
-        "memory_challenge_b": {
-            "max_level": 5,
-            "max_level_beaten": null
-        },
         "memory_challenge_c": {
-            "max_level": 5,
+            "max_level": 1,
             "max_level_beaten": 1
         }
     }

tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_a.py

@@ -1,4 +1,5 @@
 import pytest
+from pytest_mock import MockerFixture
 
 from autogpt.commands.file_operations import read_file
 from autogpt.config import Config
@@ -19,7 +20,7 @@
 def test_information_retrieval_challenge_a(
     information_retrieval_agents: Agent,
     monkeypatch: pytest.MonkeyPatch,
-    patched_api_requestor: None,
+    patched_api_requestor: MockerFixture,
     config: Config,
     level_to_run: int,
 ) -> None:

tests/integration/challenges/information_retrieval/test_information_retrieval_challenge_b.py

@@ -1,6 +1,7 @@
 import contextlib
 
 import pytest
+from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file
@@ -20,7 +21,7 @@
 def test_information_retrieval_challenge_b(
     get_nobel_prize_agent: Agent,
     monkeypatch: pytest.MonkeyPatch,
-    patched_api_requestor: None,
+    patched_api_requestor: MockerFixture,
     level_to_run: int,
     config: Config,
 ) -> None:

tests/integration/challenges/kubernetes/test_kubernetes_template_challenge_a.py

@@ -1,5 +1,6 @@
 import pytest
 import yaml
+from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file
@@ -21,6 +22,7 @@ def test_kubernetes_template_challenge_a(
     monkeypatch: pytest.MonkeyPatch,
     config: Config,
     level_to_run: int,
+    patched_api_requestor: MockerFixture,
 ) -> None:
     """
     Test the challenge_a function in a given agent by mocking user inputs

tests/integration/challenges/memory/test_memory_challenge_a.py

@@ -1,4 +1,5 @@
 import pytest
+from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
@@ -15,7 +16,7 @@
 @challenge
 def test_memory_challenge_a(
     memory_management_agent: Agent,
-    patched_api_requestor: None,
+    patched_api_requestor: MockerFixture,
     monkeypatch: pytest.MonkeyPatch,
     config: Config,
     level_to_run: int,

tests/integration/challenges/memory/test_memory_challenge_b.py

@@ -1,4 +1,5 @@
 import pytest
+from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
@@ -17,7 +18,7 @@
 @challenge
 def test_memory_challenge_b(
     memory_management_agent: Agent,
-    patched_api_requestor: None,
+    patched_api_requestor: MockerFixture,
     monkeypatch: pytest.MonkeyPatch,
     config: Config,
     level_to_run: int,

tests/integration/challenges/memory/test_memory_challenge_c.py

@@ -1,4 +1,5 @@
 import pytest
+from pytest_mock import MockerFixture
 
 from autogpt.agent import Agent
 from autogpt.commands.file_operations import read_file, write_to_file
@@ -18,7 +19,7 @@
 @challenge
 def test_memory_challenge_c(
     memory_management_agent: Agent,
-    patched_api_requestor: None,
+    patched_api_requestor: MockerFixture,
     monkeypatch: pytest.MonkeyPatch,
     config: Config,
     level_to_run: int,

tests/integration/memory/test_json_file_memory.py

@@ -80,7 +80,9 @@ def test_json_memory_get(config: Config, memory_item: MemoryItem, mock_get_embed
 
 @pytest.mark.vcr
 @requires_api_key("OPENAI_API_KEY")
-def test_json_memory_get_relevant(config: Config, patched_api_requestor: None) -> None:
+def test_json_memory_get_relevant(
+    config: Config, patched_api_requestor: MockerFixture
+) -> None:
     index = JSONFileMemory(config)
     mem1 = MemoryItem.from_text_file("Sample text", "sample.txt")
     mem2 = MemoryItem.from_text_file("Grocery list:\n- Pancake mix", "groceries.txt")