Release v0.4.1 (#4686)

Co-authored-by: Reinier van der Leer <github@pwuts.nl> Co-authored-by: Nicholas Tindle <nick@ntindle.com> Co-authored-by: Nicholas Tindle <nicktindle@outlook.com> Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com> Co-authored-by: merwanehamadi <merwanehamadi@gmail.com> Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com> Co-authored-by: Richard Beales <rich@richbeales.net> Co-authored-by: Luke K <2609441+lc0rp@users.noreply.github.com> Co-authored-by: Luke K (pr-0f3t) <2609441+lc0rp@users.noreply.github.com> Co-authored-by: Erik Peterson <e@eriklp.com> Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co> Co-authored-by: Benny van der Lans <49377421+bfalans@users.noreply.github.com> Co-authored-by: Jan <jan-github@phobia.de> Co-authored-by: Robin Richtsfeld <robin.richtsfeld@gmail.com> Co-authored-by: Marc Bornträger <marc.borntraeger@gmail.com> Co-authored-by: Stefan Ayala <stefanayala3266@gmail.com> Co-authored-by: javableu <45064273+javableu@users.noreply.github.com> Co-authored-by: DGdev91 <DGdev91@users.noreply.github.com> Co-authored-by: Kinance <kinance@gmail.com> Co-authored-by: digger yu <digger-yu@outlook.com> Co-authored-by: David <scenaristeur@gmail.com> Co-authored-by: gravelBridge <john.tian31@gmail.com> Fix Python CI "update cassettes" step (#4591) fix CI (#4596) Fix inverted logic for deny_command (#4563) fix current_score.json generation (#4601) Fix duckduckgo rate limiting (#4592) Fix debug code challenge (#4632) Fix issues with information retrieval challenge a (#4622) fix issues with env configuration and .env.template (#4630) Fix prompt issue causing 'No Command' issues and challenge to fail (#4623) Fix benchmark logs (#4653) Fix typo in docs/setup.md (#4613) Fix run.sh shebang (#4561) Fix autogpt docker image not working because missing prompt_settings (#4680) Fix execute_command coming from plugins (#4730)
2025-12-29 11:54:29 +01:00 · 2023-06-19 12:41:40 -04:00
parent 25a7957bb8
commit abb397e442
142 changed files with 3185 additions and 2562 deletions
--- a/.github/workflows/benchmarks.yml
+++ b/.github/workflows/benchmarks.yml
@@ -1,31 +1,73 @@
-name: Run Benchmarks
+name: Benchmarks

 on:
+  schedule:
+    - cron: '0 8 * * *'
  workflow_dispatch:

 jobs:
-  build:
+  Benchmark:
+    name: ${{ matrix.config.task-name }}
    runs-on: ubuntu-latest
-
-    env:
-      python-version: '3.10'
+    timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - python-version: "3.10"
+            task: "tests/challenges"
+            task-name: "Mandatory Tasks"
+          - python-version: "3.10"
+            task: "--beat-challenges -ra tests/challenges"
+            task-name: "Challenging Tasks"

    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v3
+      - name: Checkout repository
+        uses: actions/checkout@v3
+        with:
+          ref: master

-    - name: Set up Python ${{ env.python-version }}
-      uses: actions/setup-python@v4
-      with:
-        python-version: ${{ env.python-version }}
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.config.python-version }}

-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install -r requirements.txt
+      - id: get_date
+        name: Get date
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT

-    - name: benchmark
-      env:
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      run: |
-         python benchmark/benchmark_entrepreneur_gpt_with_undecisive_user.py
+      - name: Set up Python dependency cache
+        uses: actions/cache@v3
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}-${{ steps.get_date.outputs.date }}
+
+      - name: Install Python dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+
+      - name: Run pytest with coverage
+        run: |
+          rm -rf tests/Auto-GPT-test-cassettes
+          pytest -n auto --record-mode=all ${{ matrix.config.task }}
+        env:
+          CI: true
+          PROXY: ${{ secrets.PROXY }}
+          AGENT_MODE: ${{ secrets.AGENT_MODE }}
+          AGENT_TYPE: ${{ secrets.AGENT_TYPE }}
+          PLAIN_OUTPUT: True
+
+      - name: Upload logs as artifact
+        if: always()
+        uses: actions/upload-artifact@v3
+        with:
+          name: test-logs-${{ matrix.config.task-name }}
+          path: logs/
+
+      - name: Upload cassettes as artifact
+        if: always()
+        uses: actions/upload-artifact@v3
+        with:
+          name: cassettes-${{ matrix.config.task-name }}
+          path: tests/Auto-GPT-test-cassettes/
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -5,20 +5,20 @@ on:
    branches: [ master, ci-test* ]
    paths-ignore:
      - 'tests/Auto-GPT-test-cassettes'
-      - 'tests/integration/challenges/current_score.json'
+      - 'tests/challenges/current_score.json'
  pull_request:
-    branches: [ stable, master ]
+    branches: [ stable, master, release-* ]
  pull_request_target:
-    branches: [ master, ci-test* ]
+    branches: [ master, release-*, ci-test* ]

 concurrency:
-  group: ${{ format('ci-{0}', github.head_ref && format('pr-{0}', github.event.pull_request.number) || github.sha) }}
-  cancel-in-progress: ${{ startsWith(github.event_name, 'pull_request') && github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target') }}
+  group: ${{ format('ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
+  cancel-in-progress: ${{ startsWith(github.event_name, 'pull_request') }}

 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'))
+    # eliminate duplicate runs
+    if: github.event_name == 'push' || (github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target'))

    runs-on: ubuntu-latest
    env:
@@ -37,6 +37,16 @@ jobs:
        with:
          python-version: ${{ env.min-python-version }}

+      - id: get_date
+        name: Get date
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
+
+      - name: Set up Python dependency cache
+        uses: actions/cache@v3
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}-${{ steps.get_date.outputs.date }}
+
      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
@@ -59,12 +69,12 @@ jobs:

      - name: Check for unused imports and pass statements
        run: |
-          cmd="autoflake --remove-all-unused-imports --recursive --ignore-init-module-imports autogpt tests"
+          cmd="autoflake --remove-all-unused-imports --recursive --ignore-init-module-imports --ignore-pass-after-docstring autogpt tests"
          $cmd --check || (echo "You have unused imports or pass statements, please run '${cmd} --in-place'" && exit 1)

  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'))
+    # eliminate duplicate runs
+    if: github.event_name == 'push' || (github.event.pull_request.head.repo.fork == (github.event_name == 'pull_request_target'))

    permissions:
      # Gives the action the necessary permissions for publishing new
@@ -81,7 +91,7 @@ jobs:
        python-version: ["3.10"]

    steps:
-      - name: Check out repository
+      - name: Checkout repository
        uses: actions/checkout@v3
        with:
          fetch-depth: 0
@@ -89,8 +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 }}"
@@ -102,21 +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 }}
@@ -124,30 +131,41 @@ jobs:
        with:
          python-version: ${{ matrix.python-version }}

-      - name: Install dependencies
+      - id: get_date
+        name: Get date
+        run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
+
+      - name: Set up Python dependency cache
+        uses: actions/cache@v3
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}-${{ steps.get_date.outputs.date }}
+
+      - 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
+          pytest -n auto --cov=autogpt --cov-branch --cov-report term-missing --cov-report xml \
+            tests/unit tests/integration tests/challenges
+          python tests/challenges/utils/build_current_score.py
        env:
          CI: true
          PROXY: ${{ secrets.PROXY }}
-          AGENT_MODE: ${{ vars.AGENT_MODE }}
-          AGENT_TYPE: ${{ vars.AGENT_TYPE }}
+          AGENT_MODE: ${{ secrets.AGENT_MODE }}
+          AGENT_TYPE: ${{ secrets.AGENT_TYPE }}
+          PLAIN_OUTPUT: True

      - name: Upload coverage reports to Codecov
        uses: codecov/codecov-action@v3

      - 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)

@@ -163,63 +181,44 @@ jobs:
      - name: Push updated challenge scores
        if: github.event_name == 'push'
        run: |
-          score_file="tests/integration/challenges/current_score.json"
+          score_file="tests/challenges/current_score.json"

          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
@@ -228,7 +227,7 @@ 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 }}
@@ -245,10 +244,11 @@ 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
+
+      - name: Upload logs as artifact
+        if: always()
+        uses: actions/upload-artifact@v3
+        with:
+          name: test-logs
+          path: logs/
--- a/.github/workflows/docker-ci.yml
+++ b/.github/workflows/docker-ci.yml
@@ -5,9 +5,9 @@ on:
    branches: [ master ]
    paths-ignore:
      - 'tests/Auto-GPT-test-cassettes'
-      - 'tests/integration/challenges/current_score.json'
+      - 'tests/challenges/current_score.json'
  pull_request:
-    branches: [ master, stable ]
+    branches: [ master, release-*, stable ]

 concurrency:
  group: ${{ format('docker-ci-{0}', github.head_ref && format('pr-{0}', github.event.pull_request.number) || github.sha) }}
@@ -102,21 +102,25 @@ jobs:
      - id: test
        name: Run tests
        env:
+          PLAIN_OUTPUT: True
          CI: true
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
        run: |
          set +e
          test_output=$(
            docker run --env CI --env OPENAI_API_KEY --entrypoint python ${{ env.IMAGE_NAME }} -m \
-            pytest -n auto --cov=autogpt --cov-report term-missing --cov-branch --cov-report xml --cov-report term 2>&1
+            pytest -n auto --cov=autogpt --cov-branch --cov-report term-missing \
+              tests/unit tests/integration 2>&1
          )
          test_failure=$?
-  
+
          echo "$test_output"
-  
+
          cat << $EOF >> $GITHUB_STEP_SUMMARY
          # Tests $([ $test_failure = 0 ] && echo '✅' || echo '❌')
          \`\`\`
          $test_output
          \`\`\`
          $EOF
+
+          exit $test_failure
--- a/.github/workflows/pr-label.yml
+++ b/.github/workflows/pr-label.yml
@@ -3,10 +3,10 @@ name: "Pull Request auto-label"
 on:
  # So that PRs touching the same files as the push are updated
  push:
-    branches: [ master ]
+    branches: [ master, release-* ]
    paths-ignore:
      - 'tests/Auto-GPT-test-cassettes'
-      - 'tests/integration/challenges/current_score.json'
+      - 'tests/challenges/current_score.json'
  # So that the `dirtyLabel` is removed if conflicts are resolve
  # We recommend `pull_request_target` so that github secrets are available.
  # In `pull_request` we wouldn't be able to change labels of fork PRs
@@ -48,11 +48,10 @@ jobs:
          s_label: 'size/s'
          s_max_size: 10
          m_label: 'size/m'
-          m_max_size: 50
+          m_max_size: 100
          l_label: 'size/l'
-          l_max_size: 200
+          l_max_size: 500
          xl_label: 'size/xl'
          message_if_xl: >
-            This PR exceeds the recommended size of 200 lines.
+            This PR exceeds the recommended size of 500 lines.
            Please make sure you are NOT addressing multiple issues with one PR.
-            Note this PR might be rejected due to its size