Fix Python CI "update cassettes" step (#4591)

* Fix updated cassettes step

* Clarifications

* Use github.ref_name instead of github.ref

* Fix duplicate runs on `master`

---------

Co-authored-by: Reinier van der Leer <github@pwuts.nl>

.github/workflows/ci.yml

@@ -18,7 +18,7 @@ concurrency:
 jobs:
   lint:
     # eliminate duplicate runs on master
-    if: github.event_name == 'push' || github.ref_name != 'master' || (github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target'))
+    if: github.event_name == 'push' || github.base_ref != 'master' || (github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target'))
 
     runs-on: ubuntu-latest
     env:
@@ -37,14 +37,15 @@ jobs:
         with:
           python-version: ${{ env.min-python-version }}
 
-      - name: Set Date
-        run: echo "DATE=$(date +'%Y-%m-%d')" >> $GITHUB_ENV
+      - id: get_date
+        name: Get date
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
 
-      - name: Cache Python packages
+      - name: Set up Python dependency cache
         uses: actions/cache@v3
         with:
           path: ~/.cache/pip
-          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}-${{ env.DATE }}
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}-${{ steps.get_date.outputs.date }}
 
       - name: Install dependencies
         run: |
@@ -73,7 +74,7 @@ jobs:
 
   test:
     # eliminate duplicate runs on master
-    if: github.event_name == 'push' || github.ref_name != 'master' || (github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target'))
+    if: github.event_name == 'push' || github.base_ref != 'master' || (github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target'))
 
     permissions:
       # Gives the action the necessary permissions for publishing new
@@ -90,7 +91,7 @@ jobs:
         python-version: ["3.10"]
 
     steps:
-      - name: Check out repository
+      - name: Checkout repository
         uses: actions/checkout@v3
         with:
           fetch-depth: 0
@@ -98,8 +99,12 @@ jobs:
           repository: ${{ github.event.pull_request.head.repo.full_name }}
           submodules: true
 
-      - id: checkout_cassettes
-        name: Check out cassettes
+      - name: Configure git user Auto-GPT-Bot
+        run: |
+          git config --global user.name "Auto-GPT-Bot"
+          git config --global user.email "github-bot@agpt.co"
+
+      - name: Checkout cassettes
         if: ${{ startsWith(github.event_name, 'pull_request') }}
         run: |
           cassette_branch="${{ github.event.pull_request.user.login }}-${{ github.event.pull_request.head.ref }}"
@@ -111,21 +116,14 @@ jobs:
 
             git checkout $cassette_branch
 
-            if git merge --no-commit --no-ff ${{ github.event.pull_request.base.ref }}; then
-              echo "Using cassettes from mirror branch, synced to upstream branch '${{ github.event.pull_request.base.ref }}'"
-            else
-              echo "Could not merge upstream changes to cassettes. Using cassettes from ${{ github.event.pull_request.base.ref }}."
-              git merge --abort
-              git checkout ${{ github.event.pull_request.base.ref }}
-
-              # Delete branch to prevent conflict when re-creating it
-              git branch -D $cassette_branch
-            fi
-            echo "cassette_branch=$(git branch --show-current)" >> $GITHUB_OUTPUT
+            # Pick non-conflicting cassette updates from the base branch
+            git merge --no-commit --strategy-option=ours origin/${{ github.event.pull_request.base.ref }}
+            echo "Using cassettes from mirror branch '$cassette_branch'," \
+              "synced to upstream branch '${{ github.event.pull_request.base.ref }}'."
           else
-            echo "Branch '$cassette_branch' does not exist in cassette submodule."\
-              "Using cassettes from ${{ github.event.pull_request.base.ref }}."
-            echo "cassette_branch=${{ github.event.pull_request.base.ref }}" >> $GITHUB_OUTPUT
+            git checkout -b $cassette_branch
+            echo "Branch '$cassette_branch' does not exist in cassette submodule." \
+              "Using cassettes from '${{ github.event.pull_request.base.ref }}'."
           fi
 
       - name: Set up Python ${{ matrix.python-version }}
@@ -133,21 +131,22 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
 
-      - name: Set Date
-        run: echo "DATE=$(date +'%Y-%m-%d')" >> $GITHUB_ENV
+      - id: get_date
+        name: Get date
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
 
-      - name: Cache Python packages
+      - name: Set up Python dependency cache
         uses: actions/cache@v3
         with:
           path: ~/.cache/pip
-          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}-${{ env.DATE }}
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}-${{ steps.get_date.outputs.date }}
 
-      - name: Install dependencies
+      - name: Install Python dependencies
         run: |
           python -m pip install --upgrade pip
           pip install -r requirements.txt
 
-      - name: Run pytest tests with coverage
+      - name: Run pytest with coverage
         run: |
           pytest -n auto --cov=autogpt --cov-report term-missing --cov-branch --cov-report xml --cov-report term
           python tests/integration/challenges/utils/build_current_score.py
@@ -162,10 +161,9 @@ jobs:
 
       - id: setup_git_auth
         name: Set up git token authentication
+        # Cassettes may be pushed even when tests fail
+        if: success() || failure()
         run: |
-          git config --global user.name "Auto-GPT-Bot"
-          git config --global user.email "github-bot@agpt.co"
-
           config_key="http.${{ github.server_url }}/.extraheader"
           base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
 
@@ -186,58 +184,39 @@ jobs:
           if ! git diff --quiet $score_file; then
             git add $score_file
             git commit -m "Update challenge scores"
-            git push origin HEAD:${{ github.ref }}
+            git push origin HEAD:${{ github.ref_name }}
           else
             echo "The challenge scores didn't change."
           fi
 
       - id: push_cassettes
         name: Push updated cassettes
+        # For pull requests, push updated cassettes even when tests fail
+        if: github.event_name == 'push' || success() || failure()
         run: |
           if [ "${{ startsWith(github.event_name, 'pull_request') }}" = "true" ]; then
             is_pull_request=true
             cassette_branch="${{ github.event.pull_request.user.login }}-${{ github.event.pull_request.head.ref }}"
-            cassette_source_branch="${{ steps.checkout_cassettes.outputs.cassette_branch }}"
-            base_branch="${{ github.event.pull_request.base.ref }}"
           else
-            current_branch=$(echo ${{ github.ref }} | sed -e "s/refs\/heads\///g")
-            cassette_branch=$current_branch
+            cassette_branch="${{ github.ref_name }}"
           fi
 
           cd tests/Auto-GPT-test-cassettes
-          git fetch origin $cassette_source_branch:$cassette_source_branch
-
           # Commit & push changes to cassettes if any
-          if ! git diff --quiet $cassette_source_branch --; then
-            if [ "$cassette_branch" != "$cassette_source_branch" ]; then
-              git checkout -b $cassette_branch
-            fi
+          if ! git diff --quiet; then
             git add .
             git commit -m "Auto-update cassettes"
-
-            if [ $is_pull_request ]; then
-              git push --force origin HEAD:$cassette_branch
-            else
-              git push origin HEAD:$cassette_branch
-            fi
-
-            cd ../..
-            if [ $is_pull_request ]; then
-              git fetch origin $base_branch
-              cassette_diff=$(git diff origin/$base_branch)
-            else
+            git push origin HEAD:$cassette_branch
+            if [ ! $is_pull_request ]; then
+              cd ../..
               git add tests/Auto-GPT-test-cassettes
               git commit -m "Update cassette submodule"
-              git push origin HEAD:$current_branch
+              git push origin HEAD:$cassette_branch
             fi
-          else
-            echo "No cassette changes to commit"
-          fi
-
-          if [ -n "$cassette_diff" ]; then
             echo "updated=true" >> $GITHUB_OUTPUT
           else
             echo "updated=false" >> $GITHUB_OUTPUT
+            echo "No cassette changes to commit"
           fi
 
       - name: Post Set up git token auth
@@ -246,7 +225,7 @@ jobs:
           git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
           git submodule foreach git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
 
-      - name: Apply or remove behaviour change label and comment on PR
+      - name: Apply "behaviour change" label and comment on PR
         if: ${{ startsWith(github.event_name, 'pull_request') }}
         run: |
           PR_NUMBER=${{ github.event.pull_request.number }}
@@ -263,10 +242,4 @@ jobs:
 
             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."
-          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
           fi

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 @@ CYCLE_COUNT = 3
 @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/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 @@ from autogpt.agent import Agent
 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 @@ CYCLE_COUNT = 3
 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
@@ -19,6 +20,7 @@ CYCLE_COUNT = 3
 def test_kubernetes_template_challenge_a(
     kubernetes_agent: Agent,
     monkeypatch: pytest.MonkeyPatch,
+    patched_api_requestor: MockerFixture,
     config: Config,
     level_to_run: int,
 ) -> None:

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 @@ from tests.utils import requires_api_key
 @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 @@ NOISE = 1000
 @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 @@ NOISE = 1000
 @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,