fix(copilot): Use correct OpenRouter reasoning API format

Addresses review comments from CodeRabbit and Sentry:

- Change reasoning format from {"enabled": True} (invalid) to
  {"max_tokens": config.thinking_budget_tokens} per OpenRouter docs
- Add missing thinking_budget_tokens config field (default: 10000)
- Extract duplicate code into _apply_thinking_config() helper function
- Update description from 'adaptive' to 'extended' thinking for clarity

References:
- OpenRouter reasoning docs: https://openrouter.ai/docs/reasoning-tokens

.github/workflows/classic-autogpt-ci.yml

@@ -6,15 +6,11 @@ on:
     paths:
       - '.github/workflows/classic-autogpt-ci.yml'
       - 'classic/original_autogpt/**'
-      - 'classic/direct_benchmark/**'
-      - 'classic/forge/**'
   pull_request:
     branches: [ master, dev, release-* ]
     paths:
       - '.github/workflows/classic-autogpt-ci.yml'
       - 'classic/original_autogpt/**'
-      - 'classic/direct_benchmark/**'
-      - 'classic/forge/**'
 
 concurrency:
   group: ${{ format('classic-autogpt-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -23,22 +19,47 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: classic
+    working-directory: classic/original_autogpt
 
 jobs:
   test:
     permissions:
       contents: read
     timeout-minutes: 30
-    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10"]
+        platform-os: [ubuntu, macos, macos-arm64, windows]
+    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
 
     steps:
-      - name: Start MinIO service
+      # Quite slow on macOS (2~4 minutes to set up Docker)
+      # - name: Set up Docker (macOS)
+      #   if: runner.os == 'macOS'
+      #   uses: crazy-max/ghaction-setup-docker@v3
+
+      - name: Start MinIO service (Linux)
+        if: runner.os == 'Linux'
         working-directory: '.'
         run: |
           docker pull minio/minio:edge-cicd
           docker run -d -p 9000:9000 minio/minio:edge-cicd
 
+      - name: Start MinIO service (macOS)
+        if: runner.os == 'macOS'
+        working-directory: ${{ runner.temp }}
+        run: |
+          brew install minio/stable/minio
+          mkdir data
+          minio server ./data &
+
+      # No MinIO on Windows:
+      # - Windows doesn't support running Linux Docker containers
+      # - It doesn't seem possible to start background processes on Windows. They are
+      #   killed after the step returns.
+      #   See: https://github.com/actions/runner/issues/598#issuecomment-2011890429
+
       - name: Checkout repository
         uses: actions/checkout@v4
         with:
@@ -50,23 +71,41 @@ jobs:
           git config --global user.name "Auto-GPT-Bot"
           git config --global user.email "github-bot@agpt.co"
 
-      - name: Set up Python 3.12
+      - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
-          python-version: "3.12"
+          python-version: ${{ matrix.python-version }}
 
       - id: get_date
         name: Get date
         run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
 
       - name: Set up Python dependency cache
+        # On Windows, unpacking cached dependencies takes longer than just installing them
+        if: runner.os != 'Windows'
         uses: actions/cache@v4
         with:
-          path: ~/.cache/pypoetry
+          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/original_autogpt/poetry.lock') }}
 
-      - name: Install Poetry
+      - name: Install Poetry (Unix)
-        run: curl -sSL https://install.python-poetry.org | python3 -
+        if: runner.os != 'Windows'
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+
+          if [ "${{ runner.os }}" = "macOS" ]; then
+            PATH="$HOME/.local/bin:$PATH"
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Install Poetry (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: |
+          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
+
+          $env:PATH += ";$env:APPDATA\Python\Scripts"
+          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
 
       - name: Install Python dependencies
         run: poetry install
@@ -77,12 +116,12 @@ jobs:
             --cov=autogpt --cov-branch --cov-report term-missing --cov-report xml \
             --numprocesses=logical --durations=10 \
             --junitxml=junit.xml -o junit_family=legacy \
-            original_autogpt/tests/unit original_autogpt/tests/integration
+            tests/unit tests/integration
         env:
           CI: true
           PLAIN_OUTPUT: True
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          S3_ENDPOINT_URL: http://127.0.0.1:9000
+          S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
           AWS_ACCESS_KEY_ID: minioadmin
           AWS_SECRET_ACCESS_KEY: minioadmin
 
@@ -96,11 +135,11 @@ jobs:
         uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
-          flags: autogpt-agent
+          flags: autogpt-agent,${{ runner.os }}
 
       - name: Upload logs to artifact
         if: always()
         uses: actions/upload-artifact@v4
         with:
           name: test-logs
-          path: classic/logs/
+          path: classic/original_autogpt/logs/

.github/workflows/classic-autogpts-ci.yml

@@ -11,6 +11,9 @@ on:
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
       - 'classic/benchmark/**'
+      - 'classic/run'
+      - 'classic/cli.py'
+      - 'classic/setup.py'
       - '!**/*.md'
   pull_request:
     branches: [ master, dev, release-* ]
@@ -19,6 +22,9 @@ on:
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
       - 'classic/benchmark/**'
+      - 'classic/run'
+      - 'classic/cli.py'
+      - 'classic/setup.py'
       - '!**/*.md'
 
 defaults:
@@ -29,9 +35,13 @@ defaults:
 jobs:
   serve-agent-protocol:
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        agent-name: [ original_autogpt ]
+      fail-fast: false
     timeout-minutes: 20
     env:
-      min-python-version: '3.12'
+      min-python-version: '3.10'
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -45,22 +55,22 @@ jobs:
           python-version: ${{ env.min-python-version }}
 
       - name: Install Poetry
+        working-directory: ./classic/${{ matrix.agent-name }}/
         run: |
           curl -sSL https://install.python-poetry.org | python -
 
-      - name: Install dependencies
+      - name: Run regression tests
-        run: poetry install
-
-      - name: Run smoke tests with direct-benchmark
         run: |
-          poetry run direct-benchmark run \
+          ./run agent start ${{ matrix.agent-name }}
-            --strategies one_shot \
+          cd ${{ matrix.agent-name }}
-            --models claude \
+          poetry run agbenchmark --mock --test=BasicRetrieval --test=Battleship --test=WebArenaTask_0
-            --tests ReadFile,WriteFile \
+          poetry run agbenchmark --test=WriteFile
-            --json
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          AGENT_NAME: ${{ matrix.agent-name }}
           REQUESTS_CA_BUNDLE: /etc/ssl/certs/ca-certificates.crt
-          NONINTERACTIVE_MODE: "true"
+          HELICONE_CACHE_ENABLED: false
-          CI: true
+          HELICONE_PROPERTY_AGENT: ${{ matrix.agent-name }}
+          REPORTS_FOLDER: ${{ format('../../reports/{0}', matrix.agent-name) }}
+          TELEMETRY_ENVIRONMENT: autogpt-ci
+          TELEMETRY_OPT_IN: ${{ github.ref_name == 'master' }}

.github/workflows/classic-benchmark-ci.yml

@@ -1,21 +1,17 @@
-name: Classic - Direct Benchmark CI
+name: Classic - AGBenchmark CI
 
 on:
   push:
     branches: [ master, dev, ci-test* ]
     paths:
-      - 'classic/direct_benchmark/**'
+      - 'classic/benchmark/**'
-      - 'classic/benchmark/agbenchmark/challenges/**'
+      - '!classic/benchmark/reports/**'
-      - 'classic/original_autogpt/**'
-      - 'classic/forge/**'
       - .github/workflows/classic-benchmark-ci.yml
   pull_request:
     branches: [ master, dev, release-* ]
     paths:
-      - 'classic/direct_benchmark/**'
+      - 'classic/benchmark/**'
-      - 'classic/benchmark/agbenchmark/challenges/**'
+      - '!classic/benchmark/reports/**'
-      - 'classic/original_autogpt/**'
-      - 'classic/forge/**'
       - .github/workflows/classic-benchmark-ci.yml
 
 concurrency:
@@ -27,16 +23,23 @@ defaults:
     shell: bash
 
 env:
-  min-python-version: '3.12'
+  min-python-version: '3.10'
 
 jobs:
-  benchmark-tests:
+  test:
-    runs-on: ubuntu-latest
+    permissions:
+      contents: read
     timeout-minutes: 30
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10"]
+        platform-os: [ubuntu, macos, macos-arm64, windows]
+    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
     defaults:
       run:
         shell: bash
-        working-directory: classic
+        working-directory: classic/benchmark
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -44,88 +47,71 @@ jobs:
           fetch-depth: 0
           submodules: true
 
-      - name: Set up Python ${{ env.min-python-version }}
+      - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ env.min-python-version }}
+          python-version: ${{ matrix.python-version }}
 
       - name: Set up Python dependency cache
+        # On Windows, unpacking cached dependencies takes longer than just installing them
+        if: runner.os != 'Windows'
         uses: actions/cache@v4
         with:
-          path: ~/.cache/pypoetry
+          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/benchmark/poetry.lock') }}
 
-      - name: Install Poetry
+      - name: Install Poetry (Unix)
+        if: runner.os != 'Windows'
         run: |
           curl -sSL https://install.python-poetry.org | python3 -
 
-      - name: Install dependencies
+          if [ "${{ runner.os }}" = "macOS" ]; then
+            PATH="$HOME/.local/bin:$PATH"
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Install Poetry (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: |
+          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
+
+          $env:PATH += ";$env:APPDATA\Python\Scripts"
+          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
+
+      - name: Install Python dependencies
         run: poetry install
 
-      - name: Run basic benchmark tests
+      - name: Run pytest with coverage
         run: |
-          echo "Testing ReadFile challenge with one_shot strategy..."
+          poetry run pytest -vv \
-          poetry run direct-benchmark run \
+            --cov=agbenchmark --cov-branch --cov-report term-missing --cov-report xml \
-            --fresh \
+            --durations=10 \
-            --strategies one_shot \
+            --junitxml=junit.xml -o junit_family=legacy \
-            --models claude \
+            tests
-            --tests ReadFile \
-            --json
-
-          echo "Testing WriteFile challenge..."
-          poetry run direct-benchmark run \
-            --fresh \
-            --strategies one_shot \
-            --models claude \
-            --tests WriteFile \
-            --json
         env:
           CI: true
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          NONINTERACTIVE_MODE: "true"
 
-      - name: Test category filtering
+      - name: Upload test results to Codecov
-        run: |
+        if: ${{ !cancelled() }}  # Run even if tests fail
-          echo "Testing coding category..."
+        uses: codecov/test-results-action@v1
-          poetry run direct-benchmark run \
+        with:
-            --fresh \
+          token: ${{ secrets.CODECOV_TOKEN }}
-            --strategies one_shot \
-            --models claude \
-            --categories coding \
-            --tests ReadFile,WriteFile \
-            --json
-        env:
-          CI: true
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          NONINTERACTIVE_MODE: "true"
 
-      - name: Test multiple strategies
+      - name: Upload coverage reports to Codecov
-        run: |
+        uses: codecov/codecov-action@v5
-          echo "Testing multiple strategies..."
+        with:
-          poetry run direct-benchmark run \
+          token: ${{ secrets.CODECOV_TOKEN }}
-            --fresh \
+          flags: agbenchmark,${{ runner.os }}
-            --strategies one_shot,plan_execute \
-            --models claude \
-            --tests ReadFile \
-            --parallel 2 \
-            --json
-        env:
-          CI: true
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          NONINTERACTIVE_MODE: "true"
 
-  # Run regression tests on maintain challenges
+  self-test-with-agent:
-  regression-tests:
     runs-on: ubuntu-latest
-    timeout-minutes: 45
+    strategy:
-    if: github.ref == 'refs/heads/master' || github.ref == 'refs/heads/dev'
+      matrix:
-    defaults:
+        agent-name: [forge]
-      run:
+      fail-fast: false
-        shell: bash
+    timeout-minutes: 20
-        working-directory: classic
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -140,23 +126,51 @@ jobs:
 
       - name: Install Poetry
         run: |
-          curl -sSL https://install.python-poetry.org | python3 -
+          curl -sSL https://install.python-poetry.org | python -
-
-      - name: Install dependencies
-        run: poetry install
 
       - name: Run regression tests
+        working-directory: classic
         run: |
-          echo "Running regression tests (previously beaten challenges)..."
+          ./run agent start ${{ matrix.agent-name }}
-          poetry run direct-benchmark run \
+          cd ${{ matrix.agent-name }}
-            --fresh \
+
-            --strategies one_shot \
+          set +e # Ignore non-zero exit codes and continue execution
-            --models claude \
+          echo "Running the following command: poetry run agbenchmark --maintain --mock"
-            --maintain \
+          poetry run agbenchmark --maintain --mock
-            --parallel 4 \
+          EXIT_CODE=$?
-            --json
+          set -e  # Stop ignoring non-zero exit codes
+          # Check if the exit code was 5, and if so, exit with 0 instead
+          if [ $EXIT_CODE -eq 5 ]; then
+            echo "regression_tests.json is empty."
+          fi
+
+          echo "Running the following command: poetry run agbenchmark --mock"
+          poetry run agbenchmark --mock
+
+          echo "Running the following command: poetry run agbenchmark --mock --category=data"
+          poetry run agbenchmark --mock --category=data
+
+          echo "Running the following command: poetry run agbenchmark --mock --category=coding"
+          poetry run agbenchmark --mock --category=coding
+
+          # echo "Running the following command: poetry run agbenchmark --test=WriteFile"
+          # poetry run agbenchmark --test=WriteFile
+          cd ../benchmark
+          poetry install
+          echo "Adding the BUILD_SKILL_TREE environment variable. This will attempt to add new elements in the skill tree. If new elements are added, the CI fails because they should have been pushed"
+          export BUILD_SKILL_TREE=true
+
+          # poetry run agbenchmark --mock
+
+          # CHANGED=$(git diff --name-only | grep -E '(agbenchmark/challenges)|(../classic/frontend/assets)') || echo "No diffs"
+          # if [ ! -z "$CHANGED" ]; then
+          #   echo "There are unstaged changes please run agbenchmark and commit those changes since they are needed."
+          #   echo "$CHANGED"
+          #   exit 1
+          # else
+          #   echo "No unstaged changes."
+          # fi
         env:
-          CI: true
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          NONINTERACTIVE_MODE: "true"
+          TELEMETRY_ENVIRONMENT: autogpt-benchmark-ci
+          TELEMETRY_OPT_IN: ${{ github.ref_name == 'master' }}

.github/workflows/classic-forge-ci.yml

@@ -6,11 +6,13 @@ on:
     paths:
       - '.github/workflows/classic-forge-ci.yml'
       - 'classic/forge/**'
+      - '!classic/forge/tests/vcr_cassettes'
   pull_request:
     branches: [ master, dev, release-* ]
     paths:
       - '.github/workflows/classic-forge-ci.yml'
       - 'classic/forge/**'
+      - '!classic/forge/tests/vcr_cassettes'
 
 concurrency:
   group: ${{ format('forge-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -19,38 +21,115 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: classic
+    working-directory: classic/forge
 
 jobs:
   test:
     permissions:
       contents: read
     timeout-minutes: 30
-    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10"]
+        platform-os: [ubuntu, macos, macos-arm64, windows]
+    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
 
     steps:
-      - name: Start MinIO service
+      # Quite slow on macOS (2~4 minutes to set up Docker)
+      # - name: Set up Docker (macOS)
+      #   if: runner.os == 'macOS'
+      #   uses: crazy-max/ghaction-setup-docker@v3
+
+      - name: Start MinIO service (Linux)
+        if: runner.os == 'Linux'
         working-directory: '.'
         run: |
           docker pull minio/minio:edge-cicd
           docker run -d -p 9000:9000 minio/minio:edge-cicd
 
+      - name: Start MinIO service (macOS)
+        if: runner.os == 'macOS'
+        working-directory: ${{ runner.temp }}
+        run: |
+          brew install minio/stable/minio
+          mkdir data
+          minio server ./data &
+
+      # No MinIO on Windows:
+      # - Windows doesn't support running Linux Docker containers
+      # - It doesn't seem possible to start background processes on Windows. They are
+      #   killed after the step returns.
+      #   See: https://github.com/actions/runner/issues/598#issuecomment-2011890429
+
       - name: Checkout repository
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          submodules: true
 
-      - name: Set up Python 3.12
+      - name: Checkout cassettes
+        if: ${{ startsWith(github.event_name, 'pull_request') }}
+        env:
+          PR_BASE: ${{ github.event.pull_request.base.ref }}
+          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
+          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
+        run: |
+          cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
+          cassette_base_branch="${PR_BASE}"
+          cd tests/vcr_cassettes
+
+          if ! git ls-remote --exit-code --heads origin $cassette_base_branch ; then
+            cassette_base_branch="master"
+          fi
+
+          if git ls-remote --exit-code --heads origin $cassette_branch ; then
+            git fetch origin $cassette_branch
+            git fetch origin $cassette_base_branch
+
+            git checkout $cassette_branch
+
+            # Pick non-conflicting cassette updates from the base branch
+            git merge --no-commit --strategy-option=ours origin/$cassette_base_branch
+            echo "Using cassettes from mirror branch '$cassette_branch'," \
+              "synced to upstream branch '$cassette_base_branch'."
+          else
+            git checkout -b $cassette_branch
+            echo "Branch '$cassette_branch' does not exist in cassette submodule." \
+              "Using cassettes from '$cassette_base_branch'."
+          fi
+
+      - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
-          python-version: "3.12"
+          python-version: ${{ matrix.python-version }}
 
       - name: Set up Python dependency cache
+        # On Windows, unpacking cached dependencies takes longer than just installing them
+        if: runner.os != 'Windows'
         uses: actions/cache@v4
         with:
-          path: ~/.cache/pypoetry
+          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/forge/poetry.lock') }}
 
-      - name: Install Poetry
+      - name: Install Poetry (Unix)
-        run: curl -sSL https://install.python-poetry.org | python3 -
+        if: runner.os != 'Windows'
+        run: |
+          curl -sSL https://install.python-poetry.org | python3 -
+
+          if [ "${{ runner.os }}" = "macOS" ]; then
+            PATH="$HOME/.local/bin:$PATH"
+            echo "$HOME/.local/bin" >> $GITHUB_PATH
+          fi
+
+      - name: Install Poetry (Windows)
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: |
+          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
+
+          $env:PATH += ";$env:APPDATA\Python\Scripts"
+          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
 
       - name: Install Python dependencies
         run: poetry install
@@ -61,15 +140,12 @@ jobs:
             --cov=forge --cov-branch --cov-report term-missing --cov-report xml \
             --durations=10 \
             --junitxml=junit.xml -o junit_family=legacy \
-            forge/forge forge/tests
+            forge
         env:
           CI: true
           PLAIN_OUTPUT: True
-          # API keys - tests that need these will skip if not available
-          # Secrets are not available to fork PRs (GitHub security feature)
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
-          S3_ENDPOINT_URL: http://127.0.0.1:9000
           AWS_ACCESS_KEY_ID: minioadmin
           AWS_SECRET_ACCESS_KEY: minioadmin
 
@@ -83,11 +159,85 @@ jobs:
         uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
-          flags: forge
+          flags: forge,${{ runner.os }}
+
+      - id: setup_git_auth
+        name: Set up git token authentication
+        # Cassettes may be pushed even when tests fail
+        if: success() || failure()
+        run: |
+          config_key="http.${{ github.server_url }}/.extraheader"
+          if [ "${{ runner.os }}" = 'macOS' ]; then
+            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64)
+          else
+            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
+          fi
+
+          git config "$config_key" \
+            "Authorization: Basic $base64_pat"
+
+          cd tests/vcr_cassettes
+          git config "$config_key" \
+            "Authorization: Basic $base64_pat"
+
+          echo "config_key=$config_key" >> $GITHUB_OUTPUT
+
+      - id: push_cassettes
+        name: Push updated cassettes
+        # For pull requests, push updated cassettes even when tests fail
+        if: github.event_name == 'push' || (! github.event.pull_request.head.repo.fork && (success() || failure()))
+        env:
+          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
+          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
+        run: |
+          if [ "${{ startsWith(github.event_name, 'pull_request') }}" = "true" ]; then
+            is_pull_request=true
+            cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
+          else
+            cassette_branch="${{ github.ref_name }}"
+          fi
+
+          cd tests/vcr_cassettes
+          # Commit & push changes to cassettes if any
+          if ! git diff --quiet; then
+            git add .
+            git commit -m "Auto-update cassettes"
+            git push origin HEAD:$cassette_branch
+            if [ ! $is_pull_request ]; then
+              cd ../..
+              git add tests/vcr_cassettes
+              git commit -m "Update cassette submodule"
+              git push origin HEAD:$cassette_branch
+            fi
+            echo "updated=true" >> $GITHUB_OUTPUT
+          else
+            echo "updated=false" >> $GITHUB_OUTPUT
+            echo "No cassette changes to commit"
+          fi
+
+      - name: Post Set up git token auth
+        if: steps.setup_git_auth.outcome == 'success'
+        run: |
+          git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
+          git submodule foreach git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
+
+      - name: Apply "behaviour change" label and comment on PR
+        if: ${{ startsWith(github.event_name, 'pull_request') }}
+        run: |
+          PR_NUMBER="${{ github.event.pull_request.number }}"
+          TOKEN="${{ secrets.PAT_REVIEW }}"
+          REPO="${{ github.repository }}"
+
+          if [[ "${{ steps.push_cassettes.outputs.updated }}" == "true" ]]; then
+            echo "Adding label and comment..."
+            echo $TOKEN | gh auth login --with-token
+            gh issue edit $PR_NUMBER --add-label "behaviour change"
+            gh issue comment $PR_NUMBER --body "You changed AutoGPT's behaviour on ${{ runner.os }}. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
+          fi
 
       - name: Upload logs to artifact
         if: always()
         uses: actions/upload-artifact@v4
         with:
           name: test-logs
-          path: classic/logs/
+          path: classic/forge/logs/

.github/workflows/classic-frontend-ci.yml

@@ -0,0 +1,60 @@
+name: Classic - Frontend CI/CD
+
+on:
+  push:
+    branches:
+      - master
+      - dev
+      - 'ci-test*' # This will match any branch that starts with "ci-test"
+    paths:
+      - 'classic/frontend/**'
+      - '.github/workflows/classic-frontend-ci.yml'
+  pull_request:
+    paths:
+      - 'classic/frontend/**'
+      - '.github/workflows/classic-frontend-ci.yml'
+
+jobs:
+  build:
+    permissions:
+      contents: write
+      pull-requests: write
+    runs-on: ubuntu-latest
+    env:
+      BUILD_BRANCH: ${{ format('classic-frontend-build/{0}', github.ref_name) }}
+
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+
+      - name: Setup Flutter
+        uses: subosito/flutter-action@v2
+        with:
+          flutter-version: '3.13.2'
+
+      - name: Build Flutter to Web
+        run: |
+          cd classic/frontend
+          flutter build web --base-href /app/
+
+      # - name: Commit and Push to ${{ env.BUILD_BRANCH }}
+      #   if: github.event_name == 'push'
+      #   run: |
+      #     git config --local user.email "action@github.com"
+      #     git config --local user.name "GitHub Action"
+      #     git add classic/frontend/build/web
+      #     git checkout -B ${{ env.BUILD_BRANCH }}
+      #     git commit -m "Update frontend build to ${GITHUB_SHA:0:7}" -a
+      #     git push -f origin ${{ env.BUILD_BRANCH }}
+
+      - name: Create PR ${{ env.BUILD_BRANCH }} -> ${{ github.ref_name }}
+        if: github.event_name == 'push'
+        uses: peter-evans/create-pull-request@v8
+        with:
+          add-paths: classic/frontend/build/web
+          base: ${{ github.ref_name }}
+          branch: ${{ env.BUILD_BRANCH }}
+          delete-branch: true
+          title: "Update frontend build in `${{ github.ref_name }}`"
+          body: "This PR updates the frontend build based on commit ${{ github.sha }}."
+          commit-message: "Update frontend build based on commit ${{ github.sha }}"

.github/workflows/classic-python-checks.yml

@@ -7,9 +7,7 @@ on:
       - '.github/workflows/classic-python-checks-ci.yml'
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
-      - 'classic/direct_benchmark/**'
+      - 'classic/benchmark/**'
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
       - '**.py'
       - '!classic/forge/tests/vcr_cassettes'
   pull_request:
@@ -18,9 +16,7 @@ on:
       - '.github/workflows/classic-python-checks-ci.yml'
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
-      - 'classic/direct_benchmark/**'
+      - 'classic/benchmark/**'
-      - 'classic/pyproject.toml'
-      - 'classic/poetry.lock'
       - '**.py'
       - '!classic/forge/tests/vcr_cassettes'
 
@@ -31,13 +27,44 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: classic
 
 jobs:
+  get-changed-parts:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - id: changes-in
+        name: Determine affected subprojects
+        uses: dorny/paths-filter@v3
+        with:
+          filters: |
+            original_autogpt:
+              - classic/original_autogpt/autogpt/**
+              - classic/original_autogpt/tests/**
+              - classic/original_autogpt/poetry.lock
+            forge:
+              - classic/forge/forge/**
+              - classic/forge/tests/**
+              - classic/forge/poetry.lock
+            benchmark:
+              - classic/benchmark/agbenchmark/**
+              - classic/benchmark/tests/**
+              - classic/benchmark/poetry.lock
+    outputs:
+      changed-parts: ${{ steps.changes-in.outputs.changes }}
+
   lint:
+    needs: get-changed-parts
     runs-on: ubuntu-latest
     env:
-      min-python-version: "3.12"
+      min-python-version: "3.10"
+
+    strategy:
+      matrix:
+        sub-package: ${{ fromJson(needs.get-changed-parts.outputs.changed-parts) }}
+      fail-fast: false
 
     steps:
       - name: Checkout repository
@@ -54,31 +81,42 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/.cache/pypoetry
-          key: ${{ runner.os }}-poetry-${{ hashFiles('classic/poetry.lock') }}
+          key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}
 
       - name: Install Poetry
         run: curl -sSL https://install.python-poetry.org | python3 -
 
+      # Install dependencies
+
       - name: Install Python dependencies
-        run: poetry install
+        run: poetry -C classic/${{ matrix.sub-package }} install
 
       # Lint
 
       - name: Lint (isort)
         run: poetry run isort --check .
+        working-directory: classic/${{ matrix.sub-package }}
 
       - name: Lint (Black)
         if: success() || failure()
         run: poetry run black --check .
+        working-directory: classic/${{ matrix.sub-package }}
 
       - name: Lint (Flake8)
         if: success() || failure()
         run: poetry run flake8 .
+        working-directory: classic/${{ matrix.sub-package }}
 
   types:
+    needs: get-changed-parts
     runs-on: ubuntu-latest
     env:
-      min-python-version: "3.12"
+      min-python-version: "3.10"
+
+    strategy:
+      matrix:
+        sub-package: ${{ fromJson(needs.get-changed-parts.outputs.changed-parts) }}
+      fail-fast: false
 
     steps:
       - name: Checkout repository
@@ -95,16 +133,19 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/.cache/pypoetry
-          key: ${{ runner.os }}-poetry-${{ hashFiles('classic/poetry.lock') }}
+          key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}
 
       - name: Install Poetry
         run: curl -sSL https://install.python-poetry.org | python3 -
 
+      # Install dependencies
+
       - name: Install Python dependencies
-        run: poetry install
+        run: poetry -C classic/${{ matrix.sub-package }} install
 
       # Typecheck
 
       - name: Typecheck
         if: success() || failure()
         run: poetry run pyright
+        working-directory: classic/${{ matrix.sub-package }}

.github/workflows/claude-ci-failure-auto-fix.yml

@@ -22,7 +22,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           ref: ${{ github.event.workflow_run.head_branch }}
           fetch-depth: 0

.github/workflows/claude-dependabot.yml

@@ -30,7 +30,7 @@ jobs:
       actions: read # Required for CI access
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 1
 

.github/workflows/claude.yml

@@ -40,7 +40,7 @@ jobs:
       actions: read # Required for CI access
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 1
 

.github/workflows/codeql.yml

@@ -58,7 +58,7 @@ jobs:
         # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v6
+      uses: actions/checkout@v4
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL

.github/workflows/copilot-setup-steps.yml

@@ -27,7 +27,7 @@ jobs:
     # If you do not check out your code, Copilot will do this for you.
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
           submodules: true

.github/workflows/docs-block-sync.yml

@@ -23,7 +23,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 1
 

.github/workflows/docs-claude-review.yml

@@ -23,7 +23,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
 

.github/workflows/docs-enhance.yml

@@ -28,7 +28,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 1
 

.github/workflows/platform-autogpt-deploy-dev.yaml

@@ -25,7 +25,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           ref: ${{ github.event.inputs.git_ref || github.ref_name }}
 
@@ -52,7 +52,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Trigger deploy workflow
-        uses: peter-evans/repository-dispatch@v4
+        uses: peter-evans/repository-dispatch@v3
         with:
           token: ${{ secrets.DEPLOY_TOKEN }}
           repository: Significant-Gravitas/AutoGPT_cloud_infrastructure

.github/workflows/platform-autogpt-deploy-prod.yml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           ref: ${{ github.ref_name || 'master' }}
 
@@ -45,7 +45,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Trigger deploy workflow
-        uses: peter-evans/repository-dispatch@v4
+        uses: peter-evans/repository-dispatch@v3
         with:
           token: ${{ secrets.DEPLOY_TOKEN }}
           repository: Significant-Gravitas/AutoGPT_cloud_infrastructure

.github/workflows/platform-backend-ci.yml

@@ -68,7 +68,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
           submodules: true

.github/workflows/platform-dev-deploy-event-dispatcher.yml

@@ -82,7 +82,7 @@ jobs:
           
       - name: Dispatch Deploy Event
         if: steps.check_status.outputs.should_deploy == 'true'
-        uses: peter-evans/repository-dispatch@v4
+        uses: peter-evans/repository-dispatch@v3
         with:
           token: ${{ secrets.DISPATCH_TOKEN }}
           repository: Significant-Gravitas/AutoGPT_cloud_infrastructure
@@ -110,7 +110,7 @@ jobs:
 
       - name: Dispatch Undeploy Event (from comment)
         if: steps.check_status.outputs.should_undeploy == 'true'
-        uses: peter-evans/repository-dispatch@v4
+        uses: peter-evans/repository-dispatch@v3
         with:
           token: ${{ secrets.DISPATCH_TOKEN }}
           repository: Significant-Gravitas/AutoGPT_cloud_infrastructure
@@ -168,7 +168,7 @@ jobs:
           github.event_name == 'pull_request' &&
           github.event.action == 'closed' &&
           steps.check_pr_close.outputs.should_undeploy == 'true'
-        uses: peter-evans/repository-dispatch@v4
+        uses: peter-evans/repository-dispatch@v3
         with:
           token: ${{ secrets.DISPATCH_TOKEN }}
           repository: Significant-Gravitas/AutoGPT_cloud_infrastructure

.github/workflows/platform-frontend-ci.yml

@@ -31,7 +31,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
 
       - name: Check for component changes
         uses: dorny/paths-filter@v3
@@ -71,7 +71,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
 
       - name: Set up Node.js
         uses: actions/setup-node@v6
@@ -107,7 +107,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0
 
@@ -148,7 +148,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           submodules: recursive
 
@@ -277,7 +277,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           submodules: recursive
 

.github/workflows/platform-fullstack-ci.yml

@@ -29,7 +29,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
 
       - name: Set up Node.js
         uses: actions/setup-node@v6
@@ -63,7 +63,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
         with:
           submodules: recursive
 

.github/workflows/repo-workflow-checker.yml

@@ -11,7 +11,7 @@ jobs:
     steps:
       # - name: Wait some time for all actions to start
       #   run: sleep 30
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         # with:
           # fetch-depth: 0
       - name: Set up Python

.gitignore

@@ -3,7 +3,6 @@
 classic/original_autogpt/keys.py
 classic/original_autogpt/*.json
 auto_gpt_workspace/*
-.autogpt/
 *.mpeg
 .env
 # Root .env files
@@ -160,10 +159,6 @@ CURRENT_BULLETIN.md
 
 # AgBenchmark
 classic/benchmark/agbenchmark/reports/
-classic/reports/
-classic/direct_benchmark/reports/
-classic/.benchmark_workspaces/
-classic/direct_benchmark/.benchmark_workspaces/
 
 # Nodejs
 package-lock.json
@@ -182,11 +177,7 @@ autogpt_platform/backend/settings.py
 
 *.ign.*
 .test-contents
-**/.claude/settings.local.json
 .claude/settings.local.json
 CLAUDE.local.md
 /autogpt_platform/backend/logs
-
-# Test database
-test.db
 .next

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "classic/forge/tests/vcr_cassettes"]
+	path = classic/forge/tests/vcr_cassettes
+	url = https://github.com/Significant-Gravitas/Auto-GPT-test-cassettes

.pre-commit-config.yaml

@@ -43,10 +43,29 @@ repos:
         pass_filenames: false
 
       - id: poetry-install
-        name: Check & Install dependencies - Classic
+        name: Check & Install dependencies - Classic - AutoGPT
-        alias: poetry-install-classic
+        alias: poetry-install-classic-autogpt
-        entry: poetry -C classic install
+        entry: poetry -C classic/original_autogpt install
-        files: ^classic/poetry\.lock$
+        # include forge source (since it's a path dependency)
+        files: ^classic/(original_autogpt|forge)/poetry\.lock$
+        types: [file]
+        language: system
+        pass_filenames: false
+
+      - id: poetry-install
+        name: Check & Install dependencies - Classic - Forge
+        alias: poetry-install-classic-forge
+        entry: poetry -C classic/forge install
+        files: ^classic/forge/poetry\.lock$
+        types: [file]
+        language: system
+        pass_filenames: false
+
+      - id: poetry-install
+        name: Check & Install dependencies - Classic - Benchmark
+        alias: poetry-install-classic-benchmark
+        entry: poetry -C classic/benchmark install
+        files: ^classic/benchmark/poetry\.lock$
         types: [file]
         language: system
         pass_filenames: false
@@ -97,10 +116,26 @@ repos:
         language: system
 
       - id: isort
-        name: Lint (isort) - Classic
+        name: Lint (isort) - Classic - AutoGPT
-        alias: isort-classic
+        alias: isort-classic-autogpt
-        entry: bash -c 'cd classic && poetry run isort $(echo "$@" | sed "s|classic/||g")' --
+        entry: poetry -P classic/original_autogpt run isort -p autogpt
-        files: ^classic/(original_autogpt|forge|direct_benchmark)/
+        files: ^classic/original_autogpt/
+        types: [file, python]
+        language: system
+
+      - id: isort
+        name: Lint (isort) - Classic - Forge
+        alias: isort-classic-forge
+        entry: poetry -P classic/forge run isort -p forge
+        files: ^classic/forge/
+        types: [file, python]
+        language: system
+
+      - id: isort
+        name: Lint (isort) - Classic - Benchmark
+        alias: isort-classic-benchmark
+        entry: poetry -P classic/benchmark run isort -p agbenchmark
+        files: ^classic/benchmark/
         types: [file, python]
         language: system
 
@@ -114,13 +149,26 @@ repos:
 
   - repo: https://github.com/PyCQA/flake8
     rev: 7.0.0
-    # Use consolidated flake8 config at classic/.flake8
+    # To have flake8 load the config of the individual subprojects, we have to call
+    # them separately.
     hooks:
       - id: flake8
-        name: Lint (Flake8) - Classic
+        name: Lint (Flake8) - Classic - AutoGPT
-        alias: flake8-classic
+        alias: flake8-classic-autogpt
-        files: ^classic/(original_autogpt|forge|direct_benchmark)/
+        files: ^classic/original_autogpt/(autogpt|scripts|tests)/
-        args: [--config=classic/.flake8]
+        args: [--config=classic/original_autogpt/.flake8]
+
+      - id: flake8
+        name: Lint (Flake8) - Classic - Forge
+        alias: flake8-classic-forge
+        files: ^classic/forge/(forge|tests)/
+        args: [--config=classic/forge/.flake8]
+
+      - id: flake8
+        name: Lint (Flake8) - Classic - Benchmark
+        alias: flake8-classic-benchmark
+        files: ^classic/benchmark/(agbenchmark|tests)/((?!reports).)*[/.]
+        args: [--config=classic/benchmark/.flake8]
 
   - repo: local
     hooks:
@@ -156,10 +204,29 @@ repos:
         pass_filenames: false
 
       - id: pyright
-        name: Typecheck - Classic
+        name: Typecheck - Classic - AutoGPT
-        alias: pyright-classic
+        alias: pyright-classic-autogpt
-        entry: poetry -C classic run pyright
+        entry: poetry -C classic/original_autogpt run pyright
-        files: ^classic/(original_autogpt|forge|direct_benchmark)/.*\.py$|^classic/poetry\.lock$
+        # include forge source (since it's a path dependency) but exclude *_test.py files:
+        files: ^(classic/original_autogpt/((autogpt|scripts|tests)/|poetry\.lock$)|classic/forge/(forge/.*(?<!_test)\.py|poetry\.lock)$)
+        types: [file]
+        language: system
+        pass_filenames: false
+
+      - id: pyright
+        name: Typecheck - Classic - Forge
+        alias: pyright-classic-forge
+        entry: poetry -C classic/forge run pyright
+        files: ^classic/forge/(forge/|poetry\.lock$)
+        types: [file]
+        language: system
+        pass_filenames: false
+
+      - id: pyright
+        name: Typecheck - Classic - Benchmark
+        alias: pyright-classic-benchmark
+        entry: poetry -C classic/benchmark run pyright
+        files: ^classic/benchmark/(agbenchmark/|tests/|poetry\.lock$)
         types: [file]
         language: system
         pass_filenames: false

autogpt_platform/backend/backend/api/features/chat/config.py

@@ -96,7 +96,13 @@ class ChatConfig(BaseSettings):
     # Extended thinking configuration for Claude models
     thinking_enabled: bool = Field(
         default=True,
-        description="Enable adaptive thinking for Claude models via OpenRouter",
+        description="Enable extended thinking for Claude models via OpenRouter",
+    )
+    thinking_budget_tokens: int = Field(
+        default=10000,
+        ge=1000,
+        le=100000,
+        description="Maximum tokens for extended thinking (budget_tokens for Claude)",
     )
 
     @field_validator("api_key", mode="before")

autogpt_platform/backend/backend/api/features/chat/response_model.py

@@ -10,8 +10,6 @@ from typing import Any
 
 from pydantic import BaseModel, Field
 
-from backend.util.json import dumps as json_dumps
-
 
 class ResponseType(str, Enum):
     """Types of streaming responses following AI SDK protocol."""
@@ -195,18 +193,6 @@ class StreamError(StreamBaseResponse):
         default=None, description="Additional error details"
     )
 
-    def to_sse(self) -> str:
-        """Convert to SSE format, only emitting fields required by AI SDK protocol.
-
-        The AI SDK uses z.strictObject({type, errorText}) which rejects
-        any extra fields like `code` or `details`.
-        """
-        data = {
-            "type": self.type.value,
-            "errorText": self.errorText,
-        }
-        return f"data: {json_dumps(data)}\n\n"
-
 
 class StreamHeartbeat(StreamBaseResponse):
     """Heartbeat to keep SSE connection alive during long-running operations.

autogpt_platform/backend/backend/api/features/chat/service.py

@@ -80,6 +80,19 @@ settings = Settings()
 client = openai.AsyncOpenAI(api_key=config.api_key, base_url=config.base_url)
 
 
+def _apply_thinking_config(extra_body: dict[str, Any], model: str) -> None:
+    """Apply extended thinking configuration for Anthropic models via OpenRouter.
+
+    OpenRouter's reasoning API expects either:
+    - {"max_tokens": N} for explicit token budget
+    - {"effort": "high"} for automatic budget
+
+    See: https://openrouter.ai/docs/reasoning-tokens
+    """
+    if config.thinking_enabled and "anthropic" in model.lower():
+        extra_body["reasoning"] = {"max_tokens": config.thinking_budget_tokens}
+
+
 langfuse = get_client()
 
 # Redis key prefix for tracking running long-running operations
@@ -1066,9 +1079,8 @@ async def _stream_chat_chunks(
                         :128
                     ]  # OpenRouter limit
 
-                # Enable adaptive thinking for Anthropic models via OpenRouter
+                # Enable extended thinking for Anthropic models via OpenRouter
-                if config.thinking_enabled and "anthropic" in model.lower():
+                _apply_thinking_config(extra_body, model)
-                    extra_body["reasoning"] = {"enabled": True}
 
                 api_call_start = time_module.perf_counter()
                 stream = await client.chat.completions.create(
@@ -1833,9 +1845,8 @@ async def _generate_llm_continuation(
         if session_id:
             extra_body["session_id"] = session_id[:128]
 
-        # Enable adaptive thinking for Anthropic models via OpenRouter
+        # Enable extended thinking for Anthropic models via OpenRouter
-        if config.thinking_enabled and "anthropic" in config.model.lower():
+        _apply_thinking_config(extra_body, config.model)
-            extra_body["reasoning"] = {"enabled": True}
 
         retry_count = 0
         last_error: Exception | None = None
@@ -1967,9 +1978,8 @@ async def _generate_llm_continuation_with_streaming(
         if session_id:
             extra_body["session_id"] = session_id[:128]
 
-        # Enable adaptive thinking for Anthropic models via OpenRouter
+        # Enable extended thinking for Anthropic models via OpenRouter
-        if config.thinking_enabled and "anthropic" in config.model.lower():
+        _apply_thinking_config(extra_body, config.model)
-            extra_body["reasoning"] = {"enabled": True}
 
         # Make streaming LLM call (no tools - just text response)
         from typing import cast

autogpt_platform/backend/backend/blocks/human_in_the_loop.py

@@ -21,71 +21,43 @@ logger = logging.getLogger(__name__)
 
 class HumanInTheLoopBlock(Block):
     """
-    Pauses execution and waits for human approval or rejection of the data.
+    This block pauses execution and waits for human approval or modification of the data.
 
-    When executed, this block creates a pending review entry and sets the node execution
+    When executed, it creates a pending review entry and sets the node execution status
-    status to REVIEW. The execution remains paused until a human user either approves
+    to REVIEW. The execution will remain paused until a human user either:
-    or rejects the data.
+    - Approves the data (with or without modifications)
+    - Rejects the data
 
-    **How it works:**
+    This is useful for workflows that require human validation or intervention before
-    - The input data is presented to a human reviewer
+    proceeding to the next steps.
-    - The reviewer can approve or reject (and optionally modify the data if editable)
-    - On approval: the data flows out through the `approved_data` output pin
-    - On rejection: the data flows out through the `rejected_data` output pin
-
-    **Important:** The output pins yield the actual data itself, NOT status strings.
-    The approval/rejection decision determines WHICH output pin fires, not the value.
-    You do NOT need to compare the output to "APPROVED" or "REJECTED" - simply connect
-    downstream blocks to the appropriate output pin for each case.
-
-    **Example usage:**
-    - Connect `approved_data` → next step in your workflow (data was approved)
-    - Connect `rejected_data` → error handling or notification (data was rejected)
     """
 
     class Input(BlockSchemaInput):
-        data: Any = SchemaField(
+        data: Any = SchemaField(description="The data to be reviewed by a human user")
-            description="The data to be reviewed by a human user. "
-            "This exact data will be passed through to either approved_data or "
-            "rejected_data output based on the reviewer's decision."
-        )
         name: str = SchemaField(
-            description="A descriptive name for what this data represents. "
+            description="A descriptive name for what this data represents",
-            "This helps the reviewer understand what they are reviewing.",
         )
         editable: bool = SchemaField(
-            description="Whether the human reviewer can edit the data before "
+            description="Whether the human reviewer can edit the data",
-            "approving or rejecting it",
             default=True,
             advanced=True,
         )
 
     class Output(BlockSchemaOutput):
         approved_data: Any = SchemaField(
-            description="Outputs the input data when the reviewer APPROVES it. "
+            description="The data when approved (may be modified by reviewer)"
-            "The value is the actual data itself (not a status string like 'APPROVED'). "
-            "If the reviewer edited the data, this contains the modified version. "
-            "Connect downstream blocks here for the 'approved' workflow path."
         )
         rejected_data: Any = SchemaField(
-            description="Outputs the input data when the reviewer REJECTS it. "
+            description="The data when rejected (may be modified by reviewer)"
-            "The value is the actual data itself (not a status string like 'REJECTED'). "
-            "If the reviewer edited the data, this contains the modified version. "
-            "Connect downstream blocks here for the 'rejected' workflow path."
         )
         review_message: str = SchemaField(
-            description="Optional message provided by the reviewer explaining their "
+            description="Any message provided by the reviewer", default=""
-            "decision. Only outputs when the reviewer provides a message; "
-            "this pin does not fire if no message was given.",
-            default="",
         )
 
     def __init__(self):
         super().__init__(
             id="8b2a7b3c-6e9d-4a5f-8c1b-2e3f4a5b6c7d",
-            description="Pause execution for human review. Data flows through "
+            description="Pause execution and wait for human approval or modification of data",
-            "approved_data or rejected_data output based on the reviewer's decision. "
-            "Outputs contain the actual data, not status strings.",
             categories={BlockCategory.BASIC},
             input_schema=HumanInTheLoopBlock.Input,
             output_schema=HumanInTheLoopBlock.Output,

autogpt_platform/backend/backend/data/graph.py

@@ -743,11 +743,6 @@ class GraphModel(Graph, GraphMeta):
                 # For invalid blocks, we still raise immediately as this is a structural issue
                 raise ValueError(f"Invalid block {node.block_id} for node #{node.id}")
 
-            if block.disabled:
-                raise ValueError(
-                    f"Block {node.block_id} is disabled and cannot be used in graphs"
-                )
-
             node_input_mask = (
                 nodes_input_masks.get(node.id, {}) if nodes_input_masks else {}
             )

autogpt_platform/backend/backend/executor/manager.py

@@ -213,9 +213,6 @@ async def execute_node(
         block_name=node_block.name,
     )
 
-    if node_block.disabled:
-        raise ValueError(f"Block {node_block.id} is disabled and cannot be executed")
-
     # Sanity check: validate the execution input.
     input_data, error = validate_exec(node, data.inputs, resolve_input=False)
     if input_data is None:

autogpt_platform/backend/backend/util/prompt.py

@@ -364,44 +364,6 @@ def _remove_orphan_tool_responses(
     return result
 
 
-def validate_and_remove_orphan_tool_responses(
-    messages: list[dict],
-    log_warning: bool = True,
-) -> list[dict]:
-    """
-    Validate tool_call/tool_response pairs and remove orphaned responses.
-
-    Scans messages in order, tracking all tool_call IDs. Any tool response
-    referencing an ID not seen in a preceding message is considered orphaned
-    and removed. This prevents API errors like Anthropic's "unexpected tool_use_id".
-
-    Args:
-        messages: List of messages to validate (OpenAI or Anthropic format)
-        log_warning: Whether to log a warning when orphans are found
-
-    Returns:
-        A new list with orphaned tool responses removed
-    """
-    available_ids: set[str] = set()
-    orphan_ids: set[str] = set()
-
-    for msg in messages:
-        available_ids |= _extract_tool_call_ids_from_message(msg)
-        for resp_id in _extract_tool_response_ids_from_message(msg):
-            if resp_id not in available_ids:
-                orphan_ids.add(resp_id)
-
-    if not orphan_ids:
-        return messages
-
-    if log_warning:
-        logger.warning(
-            f"Removing {len(orphan_ids)} orphan tool response(s): {orphan_ids}"
-        )
-
-    return _remove_orphan_tool_responses(messages, orphan_ids)
-
-
 def _ensure_tool_pairs_intact(
     recent_messages: list[dict],
     all_messages: list[dict],
@@ -761,13 +723,6 @@ async def compress_context(
 
     # Filter out any None values that may have been introduced
     final_msgs: list[dict] = [m for m in msgs if m is not None]
-
-    # ---- STEP 6: Final tool-pair validation ---------------------------------
-    # After all compression steps, verify that every tool response has a
-    # matching tool_call in a preceding assistant message. Remove orphans
-    # to prevent API errors (e.g., Anthropic's "unexpected tool_use_id").
-    final_msgs = validate_and_remove_orphan_tool_responses(final_msgs)
-
     final_count = sum(_msg_tokens(m, enc) for m in final_msgs)
     error = None
     if final_count + reserve > target_tokens:

autogpt_platform/backend/poetry.lock

@@ -46,14 +46,14 @@ pycares = ">=4.9.0,<5"
 
 [[package]]
 name = "aiofiles"
-version = "25.1.0"
+version = "24.1.0"
 description = "File support for asyncio."
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.8"
 groups = ["main"]
 files = [
-    {file = "aiofiles-25.1.0-py3-none-any.whl", hash = "sha256:abe311e527c862958650f9438e859c1fa7568a141b22abcd015e120e86a85695"},
+    {file = "aiofiles-24.1.0-py3-none-any.whl", hash = "sha256:b4ec55f4195e3eb5d7abd1bf7e061763e864dd4954231fb8539a0ef8bb8260e5"},
-    {file = "aiofiles-25.1.0.tar.gz", hash = "sha256:a8d728f0a29de45dc521f18f07297428d56992a742f0cd2701ba86e44d23d5b2"},
+    {file = "aiofiles-24.1.0.tar.gz", hash = "sha256:22a075c9e5a3810f0c2e48f3008c94d68c65d763b9b03857924c99e57355166c"},
 ]
 
 [[package]]
@@ -8440,4 +8440,4 @@ cffi = ["cffi (>=1.17,<2.0) ; platform_python_implementation != \"PyPy\" and pyt
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<3.14"
-content-hash = "c06e96ad49388ba7a46786e9ea55ea2c1a57408e15613237b4bee40a592a12af"
+content-hash = "fc135114e01de39c8adf70f6132045e7d44a19473c1279aee0978de65aad1655"

autogpt_platform/backend/pyproject.toml

@@ -76,7 +76,7 @@ yt-dlp = "2025.12.08"
 zerobouncesdk = "^1.1.2"
 # NOTE: please insert new dependencies in their alphabetical location
 pytest-snapshot = "^0.9.0"
-aiofiles = "^25.1.0"
+aiofiles = "^24.1.0"
 tiktoken = "^0.12.0"
 aioclamd = "^1.0.0"
 setuptools = "^80.9.0"

autogpt_platform/frontend/src/app/(platform)/copilot/CopilotPage.tsx

@@ -1,11 +1,11 @@
 "use client";
 
+import { LoadingSpinner } from "@/components/atoms/LoadingSpinner/LoadingSpinner";
 import { SidebarProvider } from "@/components/ui/sidebar";
 import { ChatContainer } from "./components/ChatContainer/ChatContainer";
 import { ChatSidebar } from "./components/ChatSidebar/ChatSidebar";
 import { MobileDrawer } from "./components/MobileDrawer/MobileDrawer";
 import { MobileHeader } from "./components/MobileHeader/MobileHeader";
-import { ScaleLoader } from "./components/ScaleLoader/ScaleLoader";
 import { useCopilotPage } from "./useCopilotPage";
 
 export function CopilotPage() {
@@ -34,11 +34,7 @@ export function CopilotPage() {
   } = useCopilotPage();
 
   if (isUserLoading || !isLoggedIn) {
-    return (
+    return <LoadingSpinner size="large" cover />;
-      <div className="fixed inset-0 z-50 flex items-center justify-center bg-[#f8f8f9]">
-        <ScaleLoader className="text-neutral-400" />
-      </div>
-    );
   }
 
   return (

autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatMessagesContainer/ChatMessagesContainer.tsx

@@ -10,9 +10,8 @@ import {
   MessageResponse,
 } from "@/components/ai-elements/message";
 import { LoadingSpinner } from "@/components/atoms/LoadingSpinner/LoadingSpinner";
-import { toast } from "@/components/molecules/Toast/use-toast";
 import { ToolUIPart, UIDataTypes, UIMessage, UITools } from "ai";
-import { useEffect, useRef, useState } from "react";
+import { useEffect, useState } from "react";
 import { CreateAgentTool } from "../../tools/CreateAgent/CreateAgent";
 import { EditAgentTool } from "../../tools/EditAgent/EditAgent";
 import { FindAgentsTool } from "../../tools/FindAgents/FindAgents";
@@ -122,7 +121,6 @@ export const ChatMessagesContainer = ({
   isLoading,
 }: ChatMessagesContainerProps) => {
   const [thinkingPhrase, setThinkingPhrase] = useState(getRandomPhrase);
-  const lastToastTimeRef = useRef(0);
 
   useEffect(() => {
     if (status === "submitted") {
@@ -130,20 +128,6 @@ export const ChatMessagesContainer = ({
     }
   }, [status]);
 
-  // Show a toast when a new error occurs, debounced to avoid spam
-  useEffect(() => {
-    if (!error) return;
-    const now = Date.now();
-    if (now - lastToastTimeRef.current < 3_000) return;
-    lastToastTimeRef.current = now;
-    toast({
-      variant: "destructive",
-      title: "Something went wrong",
-      description:
-        "The assistant encountered an error. Please try sending your message again.",
-    });
-  }, [error]);
-
   const lastMessage = messages[messages.length - 1];
   const lastAssistantHasVisibleContent =
     lastMessage?.role === "assistant" &&
@@ -159,10 +143,10 @@ export const ChatMessagesContainer = ({
 
   return (
     <Conversation className="min-h-0 flex-1">
-      <ConversationContent className="flex min-h-screen flex-1 flex-col gap-6 px-3 py-6">
+      <ConversationContent className="gap-6 px-3 py-6">
         {isLoading && messages.length === 0 && (
-          <div className="flex min-h-full flex-1 items-center justify-center">
+          <div className="flex flex-1 items-center justify-center">
-            <LoadingSpinner className="text-neutral-600" />
+            <LoadingSpinner size="large" className="text-neutral-400" />
           </div>
         )}
         {messages.map((message, messageIndex) => {
@@ -279,12 +263,8 @@ export const ChatMessagesContainer = ({
           </Message>
         )}
         {error && (
-          <div className="rounded-lg bg-red-50 p-4 text-sm text-red-700">
+          <div className="rounded-lg bg-red-50 p-3 text-red-600">
-            <p className="font-medium">Something went wrong</p>
+            Error: {error.message}
-            <p className="mt-1 text-red-600">
-              The assistant encountered an error. Please try sending your
-              message again.
-            </p>
           </div>
         )}
       </ConversationContent>

autogpt_platform/frontend/src/app/(platform)/copilot/components/ChatSidebar/ChatSidebar.tsx

@@ -121,8 +121,8 @@ export function ChatSidebar() {
             className="mt-4 flex flex-col gap-1"
           >
             {isLoadingSessions ? (
-              <div className="flex min-h-[30rem] items-center justify-center py-4">
+              <div className="flex items-center justify-center py-4">
-                <LoadingSpinner size="small" className="text-neutral-600" />
+                <LoadingSpinner size="small" className="text-neutral-400" />
               </div>
             ) : sessions.length === 0 ? (
               <p className="py-4 text-center text-sm text-neutral-500">

autogpt_platform/frontend/src/app/(platform)/copilot/components/ScaleLoader/ScaleLoader.module.css

@@ -1,35 +0,0 @@
-.loader {
-  width: 48px;
-  height: 48px;
-  display: inline-block;
-  position: relative;
-}
-
-.loader::after,
-.loader::before {
-  content: "";
-  box-sizing: border-box;
-  width: 100%;
-  height: 100%;
-  border-radius: 50%;
-  background: currentColor;
-  position: absolute;
-  left: 0;
-  top: 0;
-  animation: animloader 2s linear infinite;
-}
-
-.loader::after {
-  animation-delay: 1s;
-}
-
-@keyframes animloader {
-  0% {
-    transform: scale(0);
-    opacity: 1;
-  }
-  100% {
-    transform: scale(1);
-    opacity: 0;
-  }
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/ScaleLoader/ScaleLoader.tsx

@@ -1,16 +0,0 @@
-import { cn } from "@/lib/utils";
-import styles from "./ScaleLoader.module.css";
-
-interface Props {
-  size?: number;
-  className?: string;
-}
-
-export function ScaleLoader({ size = 48, className }: Props) {
-  return (
-    <div
-      className={cn(styles.loader, className)}
-      style={{ width: size, height: size }}
-    />
-  );
-}

autogpt_platform/frontend/src/app/(platform)/copilot/components/ToolAccordion/AccordionContent.tsx

@@ -30,7 +30,7 @@ export function ContentCard({
   return (
     <div
       className={cn(
-        "min-w-0 rounded-lg bg-gradient-to-r from-purple-500/30 to-blue-500/30 p-[1px]",
+        "rounded-lg bg-gradient-to-r from-purple-500/30 to-blue-500/30 p-[1px]",
         className,
       )}
     >

autogpt_platform/frontend/src/app/(platform)/copilot/tools/CreateAgent/CreateAgent.tsx

@@ -4,6 +4,7 @@ import { WarningDiamondIcon } from "@phosphor-icons/react";
 import type { ToolUIPart } from "ai";
 import { useCopilotChatActions } from "../../components/CopilotChatActionsProvider/useCopilotChatActions";
 import { MorphingTextAnimation } from "../../components/MorphingTextAnimation/MorphingTextAnimation";
+import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
 import { ProgressBar } from "../../components/ProgressBar/ProgressBar";
 import {
   ContentCardDescription,
@@ -48,7 +49,12 @@ interface Props {
   part: CreateAgentToolPart;
 }
 
-function getAccordionMeta(output: CreateAgentToolOutput) {
+function getAccordionMeta(output: CreateAgentToolOutput): {
+  icon: React.ReactNode;
+  title: React.ReactNode;
+  titleClassName?: string;
+  description?: string;
+} {
   const icon = <AccordionIcon />;
 
   if (isAgentSavedOutput(output)) {
@@ -67,7 +73,6 @@ function getAccordionMeta(output: CreateAgentToolOutput) {
       icon,
       title: "Needs clarification",
       description: `${questions.length} question${questions.length === 1 ? "" : "s"}`,
-      expanded: true,
     };
   }
   if (
@@ -76,7 +81,7 @@ function getAccordionMeta(output: CreateAgentToolOutput) {
     isOperationInProgressOutput(output)
   ) {
     return {
-      icon,
+      icon: <OrbitLoader size={32} />,
       title: "Creating agent, this may take a few minutes. Sit back and relax.",
     };
   }
@@ -92,23 +97,18 @@ function getAccordionMeta(output: CreateAgentToolOutput) {
 export function CreateAgentTool({ part }: Props) {
   const text = getAnimationText(part);
   const { onSend } = useCopilotChatActions();
-
   const isStreaming =
     part.state === "input-streaming" || part.state === "input-available";
 
   const output = getCreateAgentToolOutput(part);
-
   const isError =
     part.state === "output-error" || (!!output && isErrorOutput(output));
-
   const isOperating =
     !!output &&
     (isOperationStartedOutput(output) ||
       isOperationPendingOutput(output) ||
       isOperationInProgressOutput(output));
-
   const progress = useAsymptoticProgress(isOperating);
-
   const hasExpandableContent =
     part.state === "output-available" &&
     !!output &&
@@ -149,7 +149,10 @@ export function CreateAgentTool({ part }: Props) {
       </div>
 
       {hasExpandableContent && output && (
-        <ToolAccordion {...getAccordionMeta(output)}>
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={isOperating || isClarificationNeededOutput(output)}
+        >
           {isOperating && (
             <ContentGrid>
               <ProgressBar value={progress} className="max-w-[280px]" />

autogpt_platform/frontend/src/app/(platform)/copilot/tools/EditAgent/EditAgent.tsx

@@ -146,7 +146,10 @@ export function EditAgentTool({ part }: Props) {
       </div>
 
       {hasExpandableContent && output && (
-        <ToolAccordion {...getAccordionMeta(output)}>
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={isOperating || isClarificationNeededOutput(output)}
+        >
           {isOperating && (
             <ContentGrid>
               <ProgressBar value={progress} className="max-w-[280px]" />

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/RunAgent.tsx

@@ -61,7 +61,14 @@ export function RunAgentTool({ part }: Props) {
       </div>
 
       {hasExpandableContent && output && (
-        <ToolAccordion {...getAccordionMeta(output)}>
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={
+            isRunAgentExecutionStartedOutput(output) ||
+            isRunAgentSetupRequirementsOutput(output) ||
+            isRunAgentAgentDetailsOutput(output)
+          }
+        >
           {isRunAgentExecutionStartedOutput(output) && (
             <ExecutionStartedCard output={output} />
           )}

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunAgent/helpers.tsx

@@ -10,7 +10,7 @@ import {
   WarningDiamondIcon,
 } from "@phosphor-icons/react";
 import type { ToolUIPart } from "ai";
-import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+import { SpinnerLoader } from "../../components/SpinnerLoader/SpinnerLoader";
 
 export interface RunAgentInput {
   username_agent_slug?: string;
@@ -171,7 +171,7 @@ export function ToolIcon({
     );
   }
   if (isStreaming) {
-    return <OrbitLoader size={24} />;
+    return <SpinnerLoader size={40} className="text-neutral-700" />;
   }
   return <PlayIcon size={14} weight="regular" className="text-neutral-400" />;
 }
@@ -203,7 +203,7 @@ export function getAccordionMeta(output: RunAgentToolOutput): {
         ? output.status.trim()
         : "started";
     return {
-      icon,
+      icon: <SpinnerLoader size={28} className="text-neutral-700" />,
       title: output.graph_name,
       description: `Status: ${statusText}`,
     };

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunBlock/RunBlock.tsx

@@ -55,7 +55,13 @@ export function RunBlockTool({ part }: Props) {
       </div>
 
       {hasExpandableContent && output && (
-        <ToolAccordion {...getAccordionMeta(output)}>
+        <ToolAccordion
+          {...getAccordionMeta(output)}
+          defaultExpanded={
+            isRunBlockBlockOutput(output) ||
+            isRunBlockSetupRequirementsOutput(output)
+          }
+        >
           {isRunBlockBlockOutput(output) && <BlockOutputCard output={output} />}
 
           {isRunBlockSetupRequirementsOutput(output) && (

autogpt_platform/frontend/src/app/(platform)/copilot/tools/RunBlock/helpers.tsx

@@ -8,7 +8,7 @@ import {
   WarningDiamondIcon,
 } from "@phosphor-icons/react";
 import type { ToolUIPart } from "ai";
-import { OrbitLoader } from "../../components/OrbitLoader/OrbitLoader";
+import { SpinnerLoader } from "../../components/SpinnerLoader/SpinnerLoader";
 
 export interface RunBlockInput {
   block_id?: string;
@@ -120,7 +120,7 @@ export function ToolIcon({
     );
   }
   if (isStreaming) {
-    return <OrbitLoader size={24} />;
+    return <SpinnerLoader size={40} className="text-neutral-700" />;
   }
   return <PlayIcon size={14} weight="regular" className="text-neutral-400" />;
 }
@@ -149,7 +149,7 @@ export function getAccordionMeta(output: RunBlockToolOutput): {
   if (isRunBlockBlockOutput(output)) {
     const keys = Object.keys(output.outputs ?? {});
     return {
-      icon,
+      icon: <SpinnerLoader size={32} className="text-neutral-700" />,
       title: output.block_name,
       description:
         keys.length > 0

autogpt_platform/frontend/src/app/(platform)/copilot/useCopilotPage.ts

@@ -3,6 +3,7 @@ import { useBreakpoint } from "@/lib/hooks/useBreakpoint";
 import { useSupabase } from "@/lib/supabase/hooks/useSupabase";
 import { useChat } from "@ai-sdk/react";
 import { DefaultChatTransport } from "ai";
+import { useRouter } from "next/navigation";
 import { useEffect, useMemo, useState } from "react";
 import { useChatSession } from "./useChatSession";
 
@@ -10,6 +11,7 @@ export function useCopilotPage() {
   const { isUserLoading, isLoggedIn } = useSupabase();
   const [isDrawerOpen, setIsDrawerOpen] = useState(false);
   const [pendingMessage, setPendingMessage] = useState<string | null>(null);
+  const router = useRouter();
 
   const {
     sessionId,
@@ -52,6 +54,10 @@ export function useCopilotPage() {
     transport: transport ?? undefined,
   });
 
+  useEffect(() => {
+    if (!isUserLoading && !isLoggedIn) router.replace("/login");
+  }, [isUserLoading, isLoggedIn]);
+
   useEffect(() => {
     if (!hydratedMessages || hydratedMessages.length === 0) return;
     setMessages((prev) => {

autogpt_platform/frontend/src/app/api/chat/sessions/[sessionId]/stream/route.ts

@@ -1,8 +1,11 @@
 import { environment } from "@/services/environment";
 import { getServerAuthToken } from "@/lib/autogpt-server-api/helpers";
 import { NextRequest } from "next/server";
-import { normalizeSSEStream, SSE_HEADERS } from "../../../sse-helpers";
 
+/**
+ * SSE Proxy for chat streaming.
+ * Supports POST with context (page content + URL) in the request body.
+ */
 export async function POST(
   request: NextRequest,
   { params }: { params: Promise<{ sessionId: string }> },
@@ -20,14 +23,17 @@ export async function POST(
       );
     }
 
+    // Get auth token from server-side session
     const token = await getServerAuthToken();
 
+    // Build backend URL
     const backendUrl = environment.getAGPTServerBaseUrl();
     const streamUrl = new URL(
       `/api/chat/sessions/${sessionId}/stream`,
       backendUrl,
     );
 
+    // Forward request to backend with auth header
     const headers: Record<string, string> = {
       "Content-Type": "application/json",
       Accept: "text/event-stream",
@@ -57,15 +63,14 @@ export async function POST(
       });
     }
 
-    if (!response.body) {
+    // Return the SSE stream directly
-      return new Response(
+    return new Response(response.body, {
-        JSON.stringify({ error: "Empty response from chat service" }),
+      headers: {
-        { status: 502, headers: { "Content-Type": "application/json" } },
+        "Content-Type": "text/event-stream",
-      );
+        "Cache-Control": "no-cache, no-transform",
-    }
+        Connection: "keep-alive",
-
+        "X-Accel-Buffering": "no",
-    return new Response(normalizeSSEStream(response.body), {
+      },
-      headers: SSE_HEADERS,
     });
   } catch (error) {
     console.error("SSE proxy error:", error);
@@ -82,6 +87,13 @@ export async function POST(
   }
 }
 
+/**
+ * Resume an active stream for a session.
+ *
+ * Called by the AI SDK's `useChat(resume: true)` on page load.
+ * Proxies to the backend which checks for an active stream and either
+ * replays it (200 + SSE) or returns 204 No Content.
+ */
 export async function GET(
   _request: NextRequest,
   { params }: { params: Promise<{ sessionId: string }> },
@@ -112,6 +124,7 @@ export async function GET(
       headers,
     });
 
+    // 204 = no active stream to resume
     if (response.status === 204) {
       return new Response(null, { status: 204 });
     }
@@ -124,13 +137,12 @@ export async function GET(
       });
     }
 
-    if (!response.body) {
+    return new Response(response.body, {
-      return new Response(null, { status: 204 });
-    }
-
-    return new Response(normalizeSSEStream(response.body), {
       headers: {
-        ...SSE_HEADERS,
+        "Content-Type": "text/event-stream",
+        "Cache-Control": "no-cache, no-transform",
+        Connection: "keep-alive",
+        "X-Accel-Buffering": "no",
         "x-vercel-ai-ui-message-stream": "v1",
       },
     });

autogpt_platform/frontend/src/app/api/chat/sse-helpers.ts

@@ -1,72 +0,0 @@
-export const SSE_HEADERS = {
-  "Content-Type": "text/event-stream",
-  "Cache-Control": "no-cache, no-transform",
-  Connection: "keep-alive",
-  "X-Accel-Buffering": "no",
-} as const;
-
-export function normalizeSSEStream(
-  input: ReadableStream<Uint8Array>,
-): ReadableStream<Uint8Array> {
-  const decoder = new TextDecoder();
-  const encoder = new TextEncoder();
-  let buffer = "";
-
-  return input.pipeThrough(
-    new TransformStream<Uint8Array, Uint8Array>({
-      transform(chunk, controller) {
-        buffer += decoder.decode(chunk, { stream: true });
-
-        const parts = buffer.split("\n\n");
-        buffer = parts.pop() ?? "";
-
-        for (const part of parts) {
-          const normalized = normalizeSSEEvent(part);
-          controller.enqueue(encoder.encode(normalized + "\n\n"));
-        }
-      },
-      flush(controller) {
-        if (buffer.trim()) {
-          const normalized = normalizeSSEEvent(buffer);
-          controller.enqueue(encoder.encode(normalized + "\n\n"));
-        }
-      },
-    }),
-  );
-}
-
-function normalizeSSEEvent(event: string): string {
-  const lines = event.split("\n");
-  const dataLines: string[] = [];
-  const otherLines: string[] = [];
-
-  for (const line of lines) {
-    if (line.startsWith("data: ")) {
-      dataLines.push(line.slice(6));
-    } else {
-      otherLines.push(line);
-    }
-  }
-
-  if (dataLines.length === 0) return event;
-
-  const dataStr = dataLines.join("\n");
-  try {
-    const parsed = JSON.parse(dataStr) as Record<string, unknown>;
-    if (parsed.type === "error") {
-      const normalized = {
-        type: "error",
-        errorText:
-          typeof parsed.errorText === "string"
-            ? parsed.errorText
-            : "An unexpected error occurred",
-      };
-      const newData = `data: ${JSON.stringify(normalized)}`;
-      return [...otherLines.filter((l) => l.length > 0), newData].join("\n");
-    }
-  } catch {
-    // Not valid JSON — pass through as-is
-  }
-
-  return event;
-}

autogpt_platform/frontend/src/app/api/chat/tasks/[taskId]/stream/route.ts

@@ -1,8 +1,20 @@
 import { environment } from "@/services/environment";
 import { getServerAuthToken } from "@/lib/autogpt-server-api/helpers";
 import { NextRequest } from "next/server";
-import { normalizeSSEStream, SSE_HEADERS } from "../../../sse-helpers";
 
+/**
+ * SSE Proxy for task stream reconnection.
+ *
+ * This endpoint allows clients to reconnect to an ongoing or recently completed
+ * background task's stream. It replays missed messages from Redis Streams and
+ * subscribes to live updates if the task is still running.
+ *
+ * Client contract:
+ * 1. When receiving an operation_started event, store the task_id
+ * 2. To reconnect: GET /api/chat/tasks/{taskId}/stream?last_message_id={idx}
+ * 3. Messages are replayed from the last_message_id position
+ * 4. Stream ends when "finish" event is received
+ */
 export async function GET(
   request: NextRequest,
   { params }: { params: Promise<{ taskId: string }> },
@@ -12,12 +24,15 @@ export async function GET(
   const lastMessageId = searchParams.get("last_message_id") || "0-0";
 
   try {
+    // Get auth token from server-side session
     const token = await getServerAuthToken();
 
+    // Build backend URL
     const backendUrl = environment.getAGPTServerBaseUrl();
     const streamUrl = new URL(`/api/chat/tasks/${taskId}/stream`, backendUrl);
     streamUrl.searchParams.set("last_message_id", lastMessageId);
 
+    // Forward request to backend with auth header
     const headers: Record<string, string> = {
       Accept: "text/event-stream",
       "Cache-Control": "no-cache",
@@ -41,12 +56,14 @@ export async function GET(
       });
     }
 
-    if (!response.body) {
+    // Return the SSE stream directly
-      return new Response(null, { status: 204 });
+    return new Response(response.body, {
-    }
+      headers: {
-
+        "Content-Type": "text/event-stream",
-    return new Response(normalizeSSEStream(response.body), {
+        "Cache-Control": "no-cache, no-transform",
-      headers: SSE_HEADERS,
+        Connection: "keep-alive",
+        "X-Accel-Buffering": "no",
+      },
     });
   } catch (error) {
     console.error("Task stream proxy error:", error);

autogpt_platform/frontend/src/lib/supabase/helpers.ts

@@ -6,7 +6,6 @@ import { SupabaseClient } from "@supabase/supabase-js";
 export const PROTECTED_PAGES = [
   "/auth/authorize",
   "/auth/integrations",
-  "/copilot",
   "/monitor",
   "/build",
   "/onboarding",

classic/.flake8

@@ -1,15 +1,12 @@
 [flake8]
 max-line-length = 88
-extend-ignore = E203
 exclude =
     .tox,
     __pycache__,
     *.pyc,
-    .env,
+    .env
-    venv*,
+    venv*/*,
-    .venv,
+    .venv/*,
-    reports,
+    reports/*,
-    dist,
+    dist/*,
-    data,
+    data/*,
-    .benchmark_workspaces,
-    .autogpt,

classic/CLAUDE.md

@@ -1,291 +0,0 @@
-# CLAUDE.md
-
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
-
-## Project Overview
-
-AutoGPT Classic is an experimental, **unsupported** project demonstrating autonomous GPT-4 operation. Dependencies will not be updated, and the codebase contains known vulnerabilities. This is preserved for educational/historical purposes.
-
-## Repository Structure
-
-```
-classic/
-├── pyproject.toml          # Single consolidated Poetry project
-├── poetry.lock             # Single lock file
-├── forge/
-│   └── forge/              # Core agent framework package
-├── original_autogpt/
-│   └── autogpt/            # AutoGPT agent package
-├── direct_benchmark/
-│   └── direct_benchmark/   # Benchmark harness package
-└── benchmark/              # Challenge definitions (data, not code)
-```
-
-All packages are managed by a single `pyproject.toml` at the classic/ root.
-
-## Common Commands
-
-### Setup & Install
-```bash
-# Install everything from classic/ directory
-cd classic
-poetry install
-```
-
-### Running Agents
-```bash
-# Run forge agent
-poetry run python -m forge
-
-# Run original autogpt server
-poetry run serve --debug
-
-# Run autogpt CLI
-poetry run autogpt
-```
-
-Agents run on `http://localhost:8000` by default.
-
-### Benchmarking
-```bash
-# Run benchmarks
-poetry run direct-benchmark run
-
-# Run specific strategies and models
-poetry run direct-benchmark run \
-    --strategies one_shot,rewoo \
-    --models claude \
-    --parallel 4
-
-# Run a single test
-poetry run direct-benchmark run --tests ReadFile
-
-# List available commands
-poetry run direct-benchmark --help
-```
-
-### Testing
-```bash
-poetry run pytest                              # All tests
-poetry run pytest forge/tests/                 # Forge tests only
-poetry run pytest original_autogpt/tests/      # AutoGPT tests only
-poetry run pytest -k test_name                 # Single test by name
-poetry run pytest path/to/test.py              # Specific test file
-poetry run pytest --cov                        # With coverage
-```
-
-### Linting & Formatting
-
-Run from the classic/ directory:
-
-```bash
-# Format everything (recommended to run together)
-poetry run black . && poetry run isort .
-
-# Check formatting (CI-style, no changes)
-poetry run black --check . && poetry run isort --check-only .
-
-# Lint
-poetry run flake8        # Style linting
-
-# Type check
-poetry run pyright       # Type checking (some errors are expected in infrastructure code)
-```
-
-Note: Always run linters over the entire directory, not specific files, for best results.
-
-## Architecture
-
-### Forge (Core Framework)
-The `forge` package is the foundation that other components depend on:
-- `forge/agent/` - Agent implementation and protocols
-- `forge/llm/` - Multi-provider LLM integrations (OpenAI, Anthropic, Groq, LiteLLM)
-- `forge/components/` - Reusable agent components
-- `forge/file_storage/` - File system abstraction
-- `forge/config/` - Configuration management
-
-### Original AutoGPT
-- `original_autogpt/autogpt/app/` - CLI application entry points
-- `original_autogpt/autogpt/agents/` - Agent implementations
-- `original_autogpt/autogpt/agent_factory/` - Agent creation logic
-
-### Direct Benchmark
-Benchmark harness for testing agent performance:
-- `direct_benchmark/direct_benchmark/` - CLI and harness code
-- `benchmark/agbenchmark/challenges/` - Test cases organized by category (code, retrieval, data, etc.)
-- Reports generated in `direct_benchmark/reports/`
-
-### Package Structure
-All three packages are included in a single Poetry project. Imports are fully qualified:
-- `from forge.agent.base import BaseAgent`
-- `from autogpt.agents.agent import Agent`
-- `from direct_benchmark.harness import BenchmarkHarness`
-
-## Code Style
-
-- Python 3.12 target
-- Line length: 88 characters (Black default)
-- Black for formatting, isort for imports (profile="black")
-- Type hints with Pyright checking
-
-## Testing Patterns
-
-- Async support via pytest-asyncio
-- Fixtures defined in `conftest.py` files provide: `tmp_project_root`, `storage`, `config`, `llm_provider`, `agent`
-- Tests requiring API keys (OPENAI_API_KEY, ANTHROPIC_API_KEY) will skip if not set
-
-## Environment Setup
-
-Copy `.env.example` to `.env` in the relevant directory and add your API keys:
-```bash
-cp .env.example .env
-# Edit .env with your OPENAI_API_KEY, etc.
-```
-
-## Workspaces
-
-Agents operate within a **workspace** - a directory containing all agent data and files. The workspace root defaults to the current working directory.
-
-### Workspace Structure
-
-```
-{workspace}/
-├── .autogpt/
-│   ├── autogpt.yaml              # Workspace-level permissions
-│   ├── ap_server.db              # Agent Protocol database (server mode)
-│   └── agents/
-│       └── AutoGPT-{agent_id}/
-│           ├── state.json        # Agent profile, directives, action history
-│           ├── permissions.yaml  # Agent-specific permission overrides
-│           └── workspace/        # Agent's sandboxed working directory
-```
-
-### Key Concepts
-
-- **Multiple agents** can coexist in the same workspace (each gets its own subdirectory)
-- **File access** is sandboxed to the agent's `workspace/` directory by default
-- **State persistence** - agent state saves to `state.json` and survives across sessions
-- **Storage backends** - supports local filesystem, S3, and GCS (via `FILE_STORAGE_BACKEND` env var)
-
-### Specifying a Workspace
-
-```bash
-# Default: uses current directory
-cd /path/to/my/project && poetry run autogpt
-
-# Or specify explicitly via CLI (if supported)
-poetry run autogpt --workspace /path/to/workspace
-```
-
-## Settings Location
-
-Configuration uses a **layered system** with three levels (in order of precedence):
-
-### 1. Environment Variables (Global)
-
-Loaded from `.env` file in the working directory:
-
-```bash
-# Required
-OPENAI_API_KEY=sk-...
-
-# Optional LLM settings
-SMART_LLM=gpt-4o                    # Model for complex reasoning
-FAST_LLM=gpt-4o-mini                # Model for simple tasks
-EMBEDDING_MODEL=text-embedding-3-small
-
-# Optional search providers (for web search component)
-TAVILY_API_KEY=tvly-...
-SERPER_API_KEY=...
-GOOGLE_API_KEY=...
-GOOGLE_CUSTOM_SEARCH_ENGINE_ID=...
-
-# Optional infrastructure
-LOG_LEVEL=DEBUG                     # DEBUG, INFO, WARNING, ERROR
-DATABASE_STRING=sqlite:///agent.db  # Agent Protocol database
-PORT=8000                           # Server port
-FILE_STORAGE_BACKEND=local          # local, s3, or gcs
-```
-
-### 2. Workspace Settings (`{workspace}/.autogpt/autogpt.yaml`)
-
-Workspace-wide permissions that apply to **all agents** in this workspace:
-
-```yaml
-allow:
-  - read_file({workspace}/**)
-  - write_to_file({workspace}/**)
-  - list_folder({workspace}/**)
-  - web_search(*)
-
-deny:
-  - read_file(**.env)
-  - read_file(**.env.*)
-  - read_file(**.key)
-  - read_file(**.pem)
-  - execute_shell(rm -rf:*)
-  - execute_shell(sudo:*)
-```
-
-Auto-generated with sensible defaults if missing.
-
-### 3. Agent Settings (`{workspace}/.autogpt/agents/{id}/permissions.yaml`)
-
-Agent-specific permission overrides:
-
-```yaml
-allow:
-  - execute_python(*)
-  - web_search(*)
-
-deny:
-  - execute_shell(*)
-```
-
-## Permissions
-
-The permission system uses **pattern matching** with a **first-match-wins** evaluation order.
-
-### Permission Check Order
-
-1. Agent deny list → **Block**
-2. Workspace deny list → **Block**
-3. Agent allow list → **Allow**
-4. Workspace allow list → **Allow**
-5. Session denied list → **Block** (commands denied during this session)
-6. **Prompt user** → Interactive approval (if in interactive mode)
-
-### Pattern Syntax
-
-Format: `command_name(glob_pattern)`
-
-| Pattern | Description |
-|---------|-------------|
-| `read_file({workspace}/**)` | Read any file in workspace (recursive) |
-| `write_to_file({workspace}/*.txt)` | Write only .txt files in workspace root |
-| `execute_shell(python:**)` | Execute Python commands only |
-| `execute_shell(git:*)` | Execute any git command |
-| `web_search(*)` | Allow all web searches |
-
-Special tokens:
-- `{workspace}` - Replaced with actual workspace path
-- `**` - Matches any path including `/`
-- `*` - Matches any characters except `/`
-
-### Interactive Approval Scopes
-
-When prompted for permission, users can choose:
-
-| Scope | Effect |
-|-------|--------|
-| **Once** | Allow this one time only (not saved) |
-| **Agent** | Always allow for this agent (saves to agent `permissions.yaml`) |
-| **Workspace** | Always allow for all agents (saves to `autogpt.yaml`) |
-| **Deny** | Deny this command (saves to appropriate deny list) |
-
-### Default Security
-
-Out of the box, the following are **denied by default**:
-- Reading sensitive files (`.env`, `.key`, `.pem`)
-- Destructive shell commands (`rm -rf`, `sudo`)
-- Operations outside the workspace directory

classic/CLI-USAGE.md

@@ -0,0 +1,182 @@
+## CLI Documentation
+
+This document describes how to interact with the project's CLI (Command Line Interface). It includes the types of outputs you can expect from each command. Note that the `agents stop` command will terminate any process running on port 8000.
+
+### 1. Entry Point for the CLI
+
+Running the `./run` command without any parameters will display the help message, which provides a list of available commands and options. Additionally, you can append `--help` to any command to view help information specific to that command.
+
+```sh
+./run
+```
+
+**Output**:
+
+```
+Usage: cli.py [OPTIONS] COMMAND [ARGS]...
+
+Options:
+  --help  Show this message and exit.
+
+Commands:
+  agent     Commands to create, start and stop agents
+  benchmark  Commands to start the benchmark and list tests and categories
+  setup      Installs dependencies needed for your system.
+```
+
+If you need assistance with any command, simply add the `--help` parameter to the end of your command, like so:
+
+```sh
+./run COMMAND --help
+```
+
+This will display a detailed help message regarding that specific command, including a list of any additional options and arguments it accepts.
+
+### 2. Setup Command
+
+```sh
+./run setup
+```
+
+**Output**:
+
+```
+Setup initiated
+Installation has been completed.
+```
+
+This command initializes the setup of the project.
+
+### 3. Agents Commands
+
+**a. List All Agents**
+
+```sh
+./run agent list
+```
+
+**Output**:
+
+```
+Available agents: 🤖
+        🐙 forge
+        🐙 autogpt
+```
+
+Lists all the available agents.
+
+**b. Create a New Agent**
+
+```sh
+./run agent create my_agent
+```
+
+**Output**:
+
+```
+🎉 New agent 'my_agent' created and switched to the new directory in agents folder.
+```
+
+Creates a new agent named 'my_agent'.
+
+**c. Start an Agent**
+
+```sh
+./run agent start my_agent
+```
+
+**Output**:
+
+```
+... (ASCII Art representing the agent startup)
+[Date and Time] [forge.sdk.db] [DEBUG] 🐛  Initializing AgentDB with database_string: sqlite:///agent.db
+[Date and Time] [forge.sdk.agent] [INFO] 📝  Agent server starting on http://0.0.0.0:8000
+```
+
+Starts the 'my_agent' and displays startup ASCII art and logs.
+
+**d. Stop an Agent**
+
+```sh
+./run agent stop
+```
+
+**Output**:
+
+```
+Agent stopped
+```
+
+Stops the running agent.
+
+### 4. Benchmark Commands
+
+**a. List Benchmark Categories**
+
+```sh
+./run benchmark categories list
+```
+
+**Output**:
+
+```
+Available categories: 📚
+        📖 code
+        📖 safety
+        📖 memory
+        ... (and so on)
+```
+
+Lists all available benchmark categories.
+
+**b. List Benchmark Tests**
+
+```sh
+./run benchmark tests list
+```
+
+**Output**:
+
+```
+Available tests: 📚
+        📖 interface
+                🔬 Search - TestSearch
+                🔬 Write File - TestWriteFile
+        ... (and so on)
+```
+
+Lists all available benchmark tests.
+
+**c. Show Details of a Benchmark Test**
+
+```sh
+./run benchmark tests details TestWriteFile
+```
+
+**Output**:
+
+```
+TestWriteFile
+-------------
+
+        Category:  interface
+        Task:  Write the word 'Washington' to a .txt file
+        ... (and other details)
+```
+
+Displays the details of the 'TestWriteFile' benchmark test.
+
+**d. Start Benchmark for the Agent**
+
+```sh
+./run benchmark start my_agent
+```
+
+**Output**:
+
+```
+(more details about the testing process shown whilst the test are running)
+============= 13 failed, 1 passed in 0.97s ============...
+```
+
+Displays the results of the benchmark tests on 'my_agent'.

classic/Dockerfile.autogpt

@@ -2,7 +2,7 @@
 ARG BUILD_TYPE=dev
 
 # Use an official Python base image from the Docker Hub
-FROM python:3.12-slim AS autogpt-base
+FROM python:3.10-slim AS autogpt-base
 
 # Install browsers
 RUN apt-get update && apt-get install -y \
@@ -34,6 +34,9 @@ COPY original_autogpt/pyproject.toml original_autogpt/poetry.lock ./
 # Include forge so it can be used as a path dependency
 COPY forge/ ../forge
 
+# Include frontend
+COPY frontend/ ../frontend
+
 # Set the entrypoint
 ENTRYPOINT ["poetry", "run", "autogpt"]
 CMD []

classic/FORGE-QUICKSTART.md

@@ -0,0 +1,173 @@
+# Quickstart Guide
+
+> For the complete getting started [tutorial series](https://aiedge.medium.com/autogpt-forge-e3de53cc58ec) <- click here
+
+Welcome to the Quickstart Guide! This guide will walk you through setting up, building, and running your own AutoGPT agent. Whether you're a seasoned AI developer or just starting out, this guide will provide you with the steps to jumpstart your journey in AI development with AutoGPT.
+
+## System Requirements
+
+This project supports Linux (Debian-based), Mac, and Windows Subsystem for Linux (WSL). If you use a Windows system, you must install WSL. You can find the installation instructions for WSL [here](https://learn.microsoft.com/en-us/windows/wsl/).
+
+
+## Getting Setup
+1. **Fork the Repository**
+   To fork the repository, follow these steps:
+   - Navigate to the main page of the repository.
+
+   ![Repository](../docs/content/imgs/quickstart/001_repo.png)
+   - In the top-right corner of the page, click Fork.
+
+   ![Create Fork UI](../docs/content/imgs/quickstart/002_fork.png)
+   - On the next page, select your GitHub account to create the fork.
+   - Wait for the forking process to complete. You now have a copy of the repository in your GitHub account.
+
+2. **Clone the Repository**
+   To clone the repository, you need to have Git installed on your system. If you don't have Git installed, download it from [here](https://git-scm.com/downloads). Once you have Git installed, follow these steps:
+   - Open your terminal.
+   - Navigate to the directory where you want to clone the repository.
+   - Run the git clone command for the fork you just created
+
+   ![Clone the Repository](../docs/content/imgs/quickstart/003_clone.png)
+
+   - Then open your project in your ide
+
+   ![Open the Project in your IDE](../docs/content/imgs/quickstart/004_ide.png)
+
+4. **Setup the Project**
+    Next, we need to set up the required dependencies. We have a tool to help you perform all the tasks on the repo.
+    It can be accessed by running the `run` command by typing `./run` in the terminal.
+
+    The first command you need to use is `./run setup.` This will guide you through setting up your system.
+    Initially, you will get instructions for installing Flutter and Chrome and setting up your GitHub access token like the following image:
+    
+    ![Setup the Project](../docs/content/imgs/quickstart/005_setup.png)
+
+### For Windows Users
+
+If you're a Windows user and experience issues after installing WSL, follow the steps below to resolve them. 
+
+#### Update WSL 
+Run the following command in Powershell or Command Prompt:
+1. Enable the optional WSL and Virtual Machine Platform components.
+2. Download and install the latest Linux kernel.
+3. Set WSL 2 as the default.
+4. Download and install the Ubuntu Linux distribution (a reboot may be required).
+
+```shell
+wsl --install
+```
+
+For more detailed information and additional steps, refer to [Microsoft's WSL Setup Environment Documentation](https://learn.microsoft.com/en-us/windows/wsl/setup/environment).
+
+#### Resolve FileNotFoundError or "No such file or directory" Errors
+When you run `./run setup`, if you encounter errors like `No such file or directory` or `FileNotFoundError`, it might be because Windows-style line endings (CRLF - Carriage Return Line Feed) are not compatible with Unix/Linux style line endings (LF - Line Feed).
+
+To resolve this, you can use the `dos2unix` utility to convert the line endings in your script from CRLF to LF. Here’s how to install and run `dos2unix` on the script:
+
+```shell
+sudo apt update
+sudo apt install dos2unix
+dos2unix ./run
+```
+
+After executing the above commands, running `./run setup` should work successfully. 
+
+#### Store Project Files within the WSL File System
+If you continue to experience issues, consider storing your project files within the WSL file system instead of the Windows file system. This method avoids path translations and permissions issues and provides a more consistent development environment.
+
+You can keep running the command to get feedback on where you are up to with your setup. 
+When setup has been completed, the command will return an output like this:
+
+![Setup Complete](../docs/content/imgs/quickstart/006_setup_complete.png)
+
+## Creating Your Agent
+
+After completing the setup, the next step is to create your agent template.
+Execute the command `./run agent create YOUR_AGENT_NAME`, where `YOUR_AGENT_NAME` should be replaced with your chosen name.
+
+Tips for naming your agent:
+* Give it its own unique name, or name it after yourself
+* Include an important aspect of your agent in the name, such as its purpose
+
+Examples: `SwiftyosAssistant`, `PwutsPRAgent`, `MySuperAgent`
+
+![Create an Agent](../docs/content/imgs/quickstart/007_create_agent.png)
+
+## Running your Agent
+
+Your agent can be started using the command: `./run agent start YOUR_AGENT_NAME`
+
+This starts the agent on the URL: `http://localhost:8000/`
+
+![Start the Agent](../docs/content/imgs/quickstart/009_start_agent.png)
+
+The front end can be accessed from `http://localhost:8000/`; first, you must log in using either a Google account or your GitHub account.
+
+![Login](../docs/content/imgs/quickstart/010_login.png)
+
+Upon logging in, you will get a page that looks something like this: your task history down the left-hand side of the page, and the 'chat' window to send tasks to your agent.
+
+![Login](../docs/content/imgs/quickstart/011_home.png)
+
+When you have finished with your agent or just need to restart it, use Ctl-C to end the session. Then, you can re-run the start command.
+
+If you are having issues and want to ensure the agent has been stopped, there is a `./run agent stop` command, which will kill the process using port 8000, which should be the agent. 
+
+## Benchmarking your Agent
+
+The benchmarking system can also be accessed using the CLI too:
+
+```bash
+agpt % ./run benchmark
+Usage: cli.py benchmark [OPTIONS] COMMAND [ARGS]...
+
+  Commands to start the benchmark and list tests and categories
+
+Options:
+  --help  Show this message and exit.
+
+Commands:
+  categories  Benchmark categories group command
+  start       Starts the benchmark command
+  tests       Benchmark tests group command
+agpt % ./run benchmark categories     
+Usage: cli.py benchmark categories [OPTIONS] COMMAND [ARGS]...
+
+  Benchmark categories group command
+
+Options:
+  --help  Show this message and exit.
+
+Commands:
+  list  List benchmark categories command
+agpt % ./run benchmark tests      
+Usage: cli.py benchmark tests [OPTIONS] COMMAND [ARGS]...
+
+  Benchmark tests group command
+
+Options:
+  --help  Show this message and exit.
+
+Commands:
+  details  Benchmark test details command
+  list     List benchmark tests command
+```
+
+The benchmark has been split into different categories of skills you can test your agent on. You can see what categories are available with
+```bash
+./run benchmark categories list
+# And what tests are available with
+./run benchmark tests list
+```
+
+![Login](../docs/content/imgs/quickstart/012_tests.png)
+
+
+Finally, you can run the benchmark with
+
+```bash
+./run benchmark start YOUR_AGENT_NAME
+
+```
+
+>

classic/README.md

@@ -4,7 +4,7 @@ AutoGPT Classic was an experimental project to demonstrate autonomous GPT-4 oper
 
 ## Project Status
 
-**This project is unsupported, and dependencies will not be updated.** It was an experiment that has concluded its initial research phase. If you want to use AutoGPT, you should use the [AutoGPT Platform](/autogpt_platform).
+⚠️ **This project is unsupported, and dependencies will not be updated. It was an experiment that has concluded its initial research phase. If you want to use AutoGPT, you should use the [AutoGPT Platform](/autogpt_platform)**
 
 For those interested in autonomous AI agents, we recommend exploring more actively maintained alternatives or referring to this codebase for educational purposes only.
 
@@ -16,171 +16,37 @@ AutoGPT Classic was one of the first implementations of autonomous AI agents - A
 - Learn from the results and adjust its approach
 - Chain multiple actions together to achieve an objective
 
+## Key Features
+
+- 🔄 Autonomous task chaining
+- 🛠 Tool and API integration capabilities
+- 💾 Memory management for context retention
+- 🔍 Web browsing and information gathering
+- 📝 File operations and content creation
+- 🔄 Self-prompting and task breakdown
+
 ## Structure
 
-```
+The project is organized into several key components:
-classic/
+- `/benchmark` - Performance testing tools
-├── pyproject.toml          # Single consolidated Poetry project
+- `/forge` - Core autonomous agent framework
-├── poetry.lock             # Single lock file
+- `/frontend` - User interface components
-├── forge/                  # Core autonomous agent framework
+- `/original_autogpt` - Original implementation
-├── original_autogpt/       # Original implementation
-├── direct_benchmark/       # Benchmark harness
-└── benchmark/              # Challenge definitions (data)
-```
 
 ## Getting Started
 
-### Prerequisites
+While this project is no longer actively maintained, you can still explore the codebase:
-
-- Python 3.12+
-- [Poetry](https://python-poetry.org/docs/#installation)
-
-### Installation
 
+1. Clone the repository:
 ```bash
-# Clone the repository
 git clone https://github.com/Significant-Gravitas/AutoGPT.git
 cd classic
-
-# Install everything
-poetry install
 ```
 
-### Configuration
+2. Review the documentation:
-
+- For reference, see the [documentation](https://docs.agpt.co). You can browse at the same point in time as this commit so the docs don't change.
-Configuration uses a layered system:
+- Check `CLI-USAGE.md` for command-line interface details
-
+- Refer to `TROUBLESHOOTING.md` for common issues
-1. **Environment variables** (`.env` file)
-2. **Workspace settings** (`.autogpt/autogpt.yaml`)
-3. **Agent settings** (`.autogpt/agents/{id}/permissions.yaml`)
-
-Copy the example environment file and add your API keys:
-
-```bash
-cp .env.example .env
-```
-
-Key environment variables:
-```bash
-# Required
-OPENAI_API_KEY=sk-...
-
-# Optional LLM settings
-SMART_LLM=gpt-4o                    # Model for complex reasoning
-FAST_LLM=gpt-4o-mini                # Model for simple tasks
-
-# Optional search providers
-TAVILY_API_KEY=tvly-...
-SERPER_API_KEY=...
-
-# Optional infrastructure
-LOG_LEVEL=DEBUG
-PORT=8000
-FILE_STORAGE_BACKEND=local          # local, s3, or gcs
-```
-
-### Running
-
-All commands run from the `classic/` directory:
-
-```bash
-# Run forge agent
-poetry run python -m forge
-
-# Run original autogpt server
-poetry run serve --debug
-
-# Run autogpt CLI
-poetry run autogpt
-```
-
-Agents run on `http://localhost:8000` by default.
-
-### Benchmarking
-
-```bash
-poetry run direct-benchmark run
-```
-
-### Testing
-
-```bash
-poetry run pytest                        # All tests
-poetry run pytest forge/tests/           # Forge tests only
-poetry run pytest original_autogpt/tests/ # AutoGPT tests only
-```
-
-## Workspaces
-
-Agents operate within a **workspace** directory that contains all agent data and files:
-
-```
-{workspace}/
-├── .autogpt/
-│   ├── autogpt.yaml              # Workspace-level permissions
-│   ├── ap_server.db              # Agent Protocol database (server mode)
-│   └── agents/
-│       └── AutoGPT-{agent_id}/
-│           ├── state.json        # Agent profile, directives, history
-│           ├── permissions.yaml  # Agent-specific permissions
-│           └── workspace/        # Agent's sandboxed working directory
-```
-
-- The workspace defaults to the current working directory
-- Multiple agents can coexist in the same workspace
-- Agent file access is sandboxed to their `workspace/` subdirectory
-- State persists across sessions via `state.json`
-
-## Permissions
-
-AutoGPT uses a **layered permission system** with pattern matching:
-
-### Permission Files
-
-| File | Scope | Location |
-|------|-------|----------|
-| `autogpt.yaml` | All agents in workspace | `.autogpt/autogpt.yaml` |
-| `permissions.yaml` | Single agent | `.autogpt/agents/{id}/permissions.yaml` |
-
-### Permission Format
-
-```yaml
-allow:
-  - read_file({workspace}/**)     # Read any file in workspace
-  - write_to_file({workspace}/**) # Write any file in workspace
-  - web_search(*)                 # All web searches
-
-deny:
-  - read_file(**.env)             # Block .env files
-  - execute_shell(sudo:*)         # Block sudo commands
-```
-
-### Check Order (First Match Wins)
-
-1. Agent deny → Block
-2. Workspace deny → Block
-3. Agent allow → Allow
-4. Workspace allow → Allow
-5. Prompt user → Interactive approval
-
-### Interactive Approval
-
-When prompted, users can approve commands with different scopes:
-- **Once** - Allow this one time only
-- **Agent** - Always allow for this agent
-- **Workspace** - Always allow for all agents
-- **Deny** - Block this command
-
-### Default Security
-
-Denied by default:
-- Sensitive files (`.env`, `.key`, `.pem`)
-- Destructive commands (`rm -rf`, `sudo`)
-- Operations outside the workspace
-
-## Security Notice
-
-This codebase has **known vulnerabilities** and issues with its dependencies. It will not be updated to new dependencies. Use for educational purposes only.
 
 ## License
 
@@ -189,3 +55,27 @@ This project segment is licensed under the MIT License - see the [LICENSE](LICEN
 ## Documentation
 
 Please refer to the [documentation](https://docs.agpt.co) for more detailed information about the project's architecture and concepts.
+You can browse at the same point in time as this commit so the docs don't change.
+
+## Historical Impact
+
+AutoGPT Classic played a significant role in advancing the field of autonomous AI agents:
+- Demonstrated practical implementation of AI autonomy
+- Inspired numerous derivative projects and research
+- Contributed to the development of AI agent architectures
+- Helped identify key challenges in AI autonomy
+
+## Security Notice
+
+If you're studying this codebase, please understand this has KNOWN vulnerabilities and issues with its dependencies. It will not be updated to new dependencies.
+
+## Community & Support
+
+While active development has concluded:
+- The codebase remains available for study and reference
+- Historical discussions can be found in project issues
+- Related research and developments continue in the broader AI agent community
+
+## Acknowledgments
+
+Thanks to all contributors who participated in this experimental project and helped advance the field of autonomous AI agents.

classic/benchmark/.env.example

@@ -0,0 +1,4 @@
+AGENT_NAME=mini-agi
+REPORTS_FOLDER="reports/mini-agi"
+OPENAI_API_KEY="sk-" # for LLM eval
+BUILD_SKILL_TREE=false # set to true to build the skill tree.

classic/benchmark/.flake8

@@ -0,0 +1,12 @@
+[flake8]
+max-line-length = 88
+# Ignore rules that conflict with Black code style
+extend-ignore = E203, W503
+exclude =
+    __pycache__/,
+    *.pyc,
+    .pytest_cache/,
+    venv*/,
+    .venv/,
+    reports/,
+    agbenchmark/reports/,

classic/benchmark/.gitignore

@@ -0,0 +1,174 @@
+agbenchmark_config/workspace/
+backend/backend_stdout.txt
+reports/df*.pkl
+reports/raw*
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+.DS_Store
+```
+secrets.json
+agbenchmark_config/challenges_already_beaten.json
+agbenchmark_config/challenges/pri_*
+agbenchmark_config/updates.json
+agbenchmark_config/reports/*
+agbenchmark_config/reports/success_rate.json
+agbenchmark_config/reports/regression_tests.json

classic/benchmark/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 AutoGPT
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

classic/benchmark/README.md

@@ -0,0 +1,25 @@
+# Auto-GPT Benchmarks
+
+Built for the purpose of benchmarking the performance of agents regardless of how they work.
+
+Objectively know how well your agent is performing in categories like code, retrieval, memory, and safety.
+
+Save time and money while doing it through smart dependencies. The best part? It's all automated.
+
+## Scores:
+
+<img width="733" alt="Screenshot 2023-07-25 at 10 35 01 AM" src="https://github.com/Significant-Gravitas/Auto-GPT-Benchmarks/assets/9652976/98963e0b-18b9-4b17-9a6a-4d3e4418af70">
+
+## Ranking overall:
+
+- 1- [Beebot](https://github.com/AutoPackAI/beebot)
+- 2- [mini-agi](https://github.com/muellerberndt/mini-agi)
+- 3- [Auto-GPT](https://github.com/Significant-Gravitas/AutoGPT)
+
+## Detailed results:
+
+<img width="733" alt="Screenshot 2023-07-25 at 10 42 15 AM" src="https://github.com/Significant-Gravitas/Auto-GPT-Benchmarks/assets/9652976/39be464c-c842-4437-b28a-07d878542a83">
+
+[Click here to see the results and the raw data!](https://docs.google.com/spreadsheets/d/1WXm16P2AHNbKpkOI0LYBpcsGG0O7D8HYTG5Uj0PaJjA/edit#gid=203558751)!
+
+More agents coming soon !

classic/benchmark/agbenchmark/README.md

@@ -0,0 +1,69 @@
+## As a user
+
+1. `pip install auto-gpt-benchmarks`
+2. Add boilerplate code to run and kill agent
+3. `agbenchmark`
+   - `--category challenge_category` to run tests in a specific category
+   - `--mock` to only run mock tests if they exists for each test
+   - `--noreg` to skip any tests that have passed in the past. When you run without this flag and a previous challenge that passed fails, it will now not be regression tests
+4. We call boilerplate code for your agent
+5. Show pass rate of tests, logs, and any other metrics
+
+## Contributing
+
+##### Diagrams: https://whimsical.com/agbenchmark-5n4hXBq1ZGzBwRsK4TVY7x
+
+### To run the existing mocks
+
+1. clone the repo `auto-gpt-benchmarks`
+2. `pip install poetry`
+3. `poetry shell`
+4. `poetry install`
+5. `cp .env_example .env`
+6. `git submodule update --init --remote --recursive`
+7. `uvicorn server:app --reload`
+8. `agbenchmark --mock`
+   Keep config the same and watch the logs :)
+
+### To run with mini-agi
+
+1. Navigate to `auto-gpt-benchmarks/agent/mini-agi`
+2. `pip install -r requirements.txt`
+3. `cp .env_example .env`, set `PROMPT_USER=false` and add your `OPENAI_API_KEY=`. Sset `MODEL="gpt-3.5-turbo"` if you don't have access to `gpt-4` yet. Also make sure you have Python 3.10^ installed
+4. set `AGENT_NAME=mini-agi` in `.env` file and where you want your `REPORTS_FOLDER` to be
+5. Make sure to follow the commands above, and remove mock flag `agbenchmark`
+
+- To add requirements `poetry add requirement`.
+
+Feel free to create prs to merge with `main` at will (but also feel free to ask for review) - if you can't send msg in R&D chat for access.
+
+If you push at any point and break things - it'll happen to everyone - fix it asap. Step 1 is to revert `master` to last working commit
+
+Let people know what beautiful code you write does, document everything well
+
+Share your progress :)
+
+#### Dataset
+
+Manually created, existing challenges within Auto-Gpt, https://osu-nlp-group.github.io/Mind2Web/
+
+## How do I add new agents to agbenchmark ?
+
+Example with smol developer.
+
+1- Create a github branch with your agent following the same pattern as this example:
+
+https://github.com/smol-ai/developer/pull/114/files
+
+2- Create the submodule and the github workflow by following the same pattern as this example:
+
+https://github.com/Significant-Gravitas/Auto-GPT-Benchmarks/pull/48/files
+
+## How do I run agent in different environments?
+
+**To just use as the benchmark for your agent**. `pip install` the package and run `agbenchmark`
+
+**For internal Auto-GPT ci runs**, specify the `AGENT_NAME` you want you use and set the `HOME_ENV`.
+Ex. `AGENT_NAME=mini-agi`
+
+**To develop agent alongside benchmark**, you can specify the `AGENT_NAME` you want you use and add as a submodule to the repo

classic/benchmark/agbenchmark/__main__.py

@@ -0,0 +1,352 @@
+import logging
+import os
+import sys
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Optional
+
+import click
+from click_default_group import DefaultGroup
+from dotenv import load_dotenv
+
+from agbenchmark.config import AgentBenchmarkConfig
+from agbenchmark.utils.logging import configure_logging
+
+load_dotenv()
+
+# try:
+#     if os.getenv("HELICONE_API_KEY"):
+#         import helicone  # noqa
+
+#         helicone_enabled = True
+#     else:
+#         helicone_enabled = False
+# except ImportError:
+#     helicone_enabled = False
+
+
+class InvalidInvocationError(ValueError):
+    pass
+
+
+logger = logging.getLogger(__name__)
+
+BENCHMARK_START_TIME_DT = datetime.now(timezone.utc)
+BENCHMARK_START_TIME = BENCHMARK_START_TIME_DT.strftime("%Y-%m-%dT%H:%M:%S+00:00")
+
+
+# if helicone_enabled:
+#     from helicone.lock import HeliconeLockManager
+
+#     HeliconeLockManager.write_custom_property(
+#         "benchmark_start_time", BENCHMARK_START_TIME
+#     )
+
+
+@click.group(cls=DefaultGroup, default_if_no_args=True)
+@click.option("--debug", is_flag=True, help="Enable debug output")
+def cli(
+    debug: bool,
+) -> Any:
+    configure_logging(logging.DEBUG if debug else logging.INFO)
+
+
+@cli.command(hidden=True)
+def start():
+    raise DeprecationWarning(
+        "`agbenchmark start` is deprecated. Use `agbenchmark run` instead."
+    )
+
+
+@cli.command(default=True)
+@click.option(
+    "-N", "--attempts", default=1, help="Number of times to run each challenge."
+)
+@click.option(
+    "-c",
+    "--category",
+    multiple=True,
+    help="(+) Select a category to run.",
+)
+@click.option(
+    "-s",
+    "--skip-category",
+    multiple=True,
+    help="(+) Exclude a category from running.",
+)
+@click.option("--test", multiple=True, help="(+) Select a test to run.")
+@click.option("--maintain", is_flag=True, help="Run only regression tests.")
+@click.option("--improve", is_flag=True, help="Run only non-regression tests.")
+@click.option(
+    "--explore",
+    is_flag=True,
+    help="Run only challenges that have never been beaten.",
+)
+@click.option(
+    "--no-dep",
+    is_flag=True,
+    help="Run all (selected) challenges, regardless of dependency success/failure.",
+)
+@click.option("--cutoff", type=int, help="Override the challenge time limit (seconds).")
+@click.option("--nc", is_flag=True, help="Disable the challenge time limit.")
+@click.option("--mock", is_flag=True, help="Run with mock")
+@click.option("--keep-answers", is_flag=True, help="Keep answers")
+@click.option(
+    "--backend",
+    is_flag=True,
+    help="Write log output to a file instead of the terminal.",
+)
+# @click.argument(
+#     "agent_path",
+#     type=click.Path(exists=True, file_okay=False, path_type=Path),
+#     required=False,
+# )
+def run(
+    maintain: bool,
+    improve: bool,
+    explore: bool,
+    mock: bool,
+    no_dep: bool,
+    nc: bool,
+    keep_answers: bool,
+    test: tuple[str],
+    category: tuple[str],
+    skip_category: tuple[str],
+    attempts: int,
+    cutoff: Optional[int] = None,
+    backend: Optional[bool] = False,
+    # agent_path: Optional[Path] = None,
+) -> None:
+    """
+    Run the benchmark on the agent in the current directory.
+
+    Options marked with (+) can be specified multiple times, to select multiple items.
+    """
+    from agbenchmark.main import run_benchmark, validate_args
+
+    agbenchmark_config = AgentBenchmarkConfig.load()
+    logger.debug(f"agbenchmark_config: {agbenchmark_config.agbenchmark_config_dir}")
+    try:
+        validate_args(
+            maintain=maintain,
+            improve=improve,
+            explore=explore,
+            tests=test,
+            categories=category,
+            skip_categories=skip_category,
+            no_cutoff=nc,
+            cutoff=cutoff,
+        )
+    except InvalidInvocationError as e:
+        logger.error("Error: " + "\n".join(e.args))
+        sys.exit(1)
+
+    original_stdout = sys.stdout  # Save the original standard output
+    exit_code = None
+
+    if backend:
+        with open("backend/backend_stdout.txt", "w") as f:
+            sys.stdout = f
+            exit_code = run_benchmark(
+                config=agbenchmark_config,
+                maintain=maintain,
+                improve=improve,
+                explore=explore,
+                mock=mock,
+                no_dep=no_dep,
+                no_cutoff=nc,
+                keep_answers=keep_answers,
+                tests=test,
+                categories=category,
+                skip_categories=skip_category,
+                attempts_per_challenge=attempts,
+                cutoff=cutoff,
+            )
+
+        sys.stdout = original_stdout
+
+    else:
+        exit_code = run_benchmark(
+            config=agbenchmark_config,
+            maintain=maintain,
+            improve=improve,
+            explore=explore,
+            mock=mock,
+            no_dep=no_dep,
+            no_cutoff=nc,
+            keep_answers=keep_answers,
+            tests=test,
+            categories=category,
+            skip_categories=skip_category,
+            attempts_per_challenge=attempts,
+            cutoff=cutoff,
+        )
+
+        sys.exit(exit_code)
+
+
+@cli.command()
+@click.option("--port", type=int, help="Port to run the API on.")
+def serve(port: Optional[int] = None):
+    """Serve the benchmark frontend and API on port 8080."""
+    import uvicorn
+
+    from agbenchmark.app import setup_fastapi_app
+
+    config = AgentBenchmarkConfig.load()
+    app = setup_fastapi_app(config)
+
+    # Run the FastAPI application using uvicorn
+    port = port or int(os.getenv("PORT", 8080))
+    uvicorn.run(app, host="0.0.0.0", port=port)
+
+
+@cli.command()
+def config():
+    """Displays info regarding the present AGBenchmark config."""
+    from .utils.utils import pretty_print_model
+
+    try:
+        config = AgentBenchmarkConfig.load()
+    except FileNotFoundError as e:
+        click.echo(e, err=True)
+        return 1
+
+    pretty_print_model(config, include_header=False)
+
+
+@cli.group()
+def challenge():
+    logging.getLogger().setLevel(logging.WARNING)
+
+
+@challenge.command("list")
+@click.option(
+    "--all", "include_unavailable", is_flag=True, help="Include unavailable challenges."
+)
+@click.option(
+    "--names", "only_names", is_flag=True, help="List only the challenge names."
+)
+@click.option("--json", "output_json", is_flag=True)
+def list_challenges(include_unavailable: bool, only_names: bool, output_json: bool):
+    """Lists [available|all] challenges."""
+    import json
+
+    from tabulate import tabulate
+
+    from .challenges.builtin import load_builtin_challenges
+    from .challenges.webarena import load_webarena_challenges
+    from .utils.data_types import Category, DifficultyLevel
+    from .utils.utils import sorted_by_enum_index
+
+    DIFFICULTY_COLORS = {
+        difficulty: color
+        for difficulty, color in zip(
+            DifficultyLevel,
+            ["black", "blue", "cyan", "green", "yellow", "red", "magenta", "white"],
+        )
+    }
+    CATEGORY_COLORS = {
+        category: f"bright_{color}"
+        for category, color in zip(
+            Category,
+            ["blue", "cyan", "green", "yellow", "magenta", "red", "white", "black"],
+        )
+    }
+
+    # Load challenges
+    challenges = filter(
+        lambda c: c.info.available or include_unavailable,
+        [
+            *load_builtin_challenges(),
+            *load_webarena_challenges(skip_unavailable=False),
+        ],
+    )
+    challenges = sorted_by_enum_index(
+        challenges, DifficultyLevel, key=lambda c: c.info.difficulty
+    )
+
+    if only_names:
+        if output_json:
+            click.echo(json.dumps([c.info.name for c in challenges]))
+            return
+
+        for c in challenges:
+            click.echo(
+                click.style(c.info.name, fg=None if c.info.available else "black")
+            )
+        return
+
+    if output_json:
+        click.echo(
+            json.dumps([json.loads(c.info.model_dump_json()) for c in challenges])
+        )
+        return
+
+    headers = tuple(
+        click.style(h, bold=True) for h in ("Name", "Difficulty", "Categories")
+    )
+    table = [
+        tuple(
+            v if challenge.info.available else click.style(v, fg="black")
+            for v in (
+                challenge.info.name,
+                (
+                    click.style(
+                        challenge.info.difficulty.value,
+                        fg=DIFFICULTY_COLORS[challenge.info.difficulty],
+                    )
+                    if challenge.info.difficulty
+                    else click.style("-", fg="black")
+                ),
+                " ".join(
+                    click.style(cat.value, fg=CATEGORY_COLORS[cat])
+                    for cat in sorted_by_enum_index(challenge.info.category, Category)
+                ),
+            )
+        )
+        for challenge in challenges
+    ]
+    click.echo(tabulate(table, headers=headers))
+
+
+@challenge.command()
+@click.option("--json", is_flag=True)
+@click.argument("name")
+def info(name: str, json: bool):
+    from itertools import chain
+
+    from .challenges.builtin import load_builtin_challenges
+    from .challenges.webarena import load_webarena_challenges
+    from .utils.utils import pretty_print_model
+
+    for challenge in chain(
+        load_builtin_challenges(),
+        load_webarena_challenges(skip_unavailable=False),
+    ):
+        if challenge.info.name != name:
+            continue
+
+        if json:
+            click.echo(challenge.info.model_dump_json())
+            break
+
+        pretty_print_model(challenge.info)
+        break
+    else:
+        click.echo(click.style(f"Unknown challenge '{name}'", fg="red"), err=True)
+
+
+@cli.command()
+def version():
+    """Print version info for the AGBenchmark application."""
+    import toml
+
+    package_root = Path(__file__).resolve().parent.parent
+    pyproject = toml.load(package_root / "pyproject.toml")
+    version = pyproject["tool"]["poetry"]["version"]
+    click.echo(f"AGBenchmark version {version}")
+
+
+if __name__ == "__main__":
+    cli()

classic/benchmark/agbenchmark/agent_api_interface.py

@@ -0,0 +1,111 @@
+import logging
+import time
+from pathlib import Path
+from typing import AsyncIterator, Optional
+
+from agent_protocol_client import (
+    AgentApi,
+    ApiClient,
+    Configuration,
+    Step,
+    TaskRequestBody,
+)
+
+from agbenchmark.agent_interface import get_list_of_file_paths
+from agbenchmark.config import AgentBenchmarkConfig
+
+logger = logging.getLogger(__name__)
+
+
+async def run_api_agent(
+    task: str,
+    config: AgentBenchmarkConfig,
+    timeout: int,
+    artifacts_location: Optional[Path] = None,
+    *,
+    mock: bool = False,
+) -> AsyncIterator[Step]:
+    configuration = Configuration(host=config.host)
+    async with ApiClient(configuration) as api_client:
+        api_instance = AgentApi(api_client)
+        task_request_body = TaskRequestBody(input=task, additional_input=None)
+
+        start_time = time.time()
+        response = await api_instance.create_agent_task(
+            task_request_body=task_request_body
+        )
+        task_id = response.task_id
+
+        if artifacts_location:
+            logger.debug("Uploading task input artifacts to agent...")
+            await upload_artifacts(
+                api_instance, artifacts_location, task_id, "artifacts_in"
+            )
+
+        logger.debug("Running agent until finished or timeout...")
+        while True:
+            step = await api_instance.execute_agent_task_step(task_id=task_id)
+            yield step
+
+            if time.time() - start_time > timeout:
+                raise TimeoutError("Time limit exceeded")
+            if step and mock:
+                step.is_last = True
+            if not step or step.is_last:
+                break
+
+        if artifacts_location:
+            # In "mock" mode, we cheat by giving the correct artifacts to pass the test
+            if mock:
+                logger.debug("Uploading mock artifacts to agent...")
+                await upload_artifacts(
+                    api_instance, artifacts_location, task_id, "artifacts_out"
+                )
+
+            logger.debug("Downloading agent artifacts...")
+            await download_agent_artifacts_into_folder(
+                api_instance, task_id, config.temp_folder
+            )
+
+
+async def download_agent_artifacts_into_folder(
+    api_instance: AgentApi, task_id: str, folder: Path
+):
+    artifacts = await api_instance.list_agent_task_artifacts(task_id=task_id)
+
+    for artifact in artifacts.artifacts:
+        # current absolute path of the directory of the file
+        if artifact.relative_path:
+            path: str = (
+                artifact.relative_path
+                if not artifact.relative_path.startswith("/")
+                else artifact.relative_path[1:]
+            )
+            folder = (folder / path).parent
+
+        if not folder.exists():
+            folder.mkdir(parents=True)
+
+        file_path = folder / artifact.file_name
+        logger.debug(f"Downloading agent artifact {artifact.file_name} to {folder}")
+        with open(file_path, "wb") as f:
+            content = await api_instance.download_agent_task_artifact(
+                task_id=task_id, artifact_id=artifact.artifact_id
+            )
+
+            f.write(content)
+
+
+async def upload_artifacts(
+    api_instance: AgentApi, artifacts_location: Path, task_id: str, type: str
+) -> None:
+    for file_path in get_list_of_file_paths(artifacts_location, type):
+        relative_path: Optional[str] = "/".join(
+            str(file_path).split(f"{type}/", 1)[-1].split("/")[:-1]
+        )
+        if not relative_path:
+            relative_path = None
+
+        await api_instance.upload_agent_task_artifacts(
+            task_id=task_id, file=str(file_path), relative_path=relative_path
+        )

classic/benchmark/agbenchmark/agent_interface.py

@@ -0,0 +1,27 @@
+import os
+import shutil
+from pathlib import Path
+
+from dotenv import load_dotenv
+
+load_dotenv()
+
+HELICONE_GRAPHQL_LOGS = os.getenv("HELICONE_GRAPHQL_LOGS", "").lower() == "true"
+
+
+def get_list_of_file_paths(
+    challenge_dir_path: str | Path, artifact_folder_name: str
+) -> list[Path]:
+    source_dir = Path(challenge_dir_path) / artifact_folder_name
+    if not source_dir.exists():
+        return []
+    return list(source_dir.iterdir())
+
+
+def copy_challenge_artifacts_into_workspace(
+    challenge_dir_path: str | Path, artifact_folder_name: str, workspace: str | Path
+) -> None:
+    file_paths = get_list_of_file_paths(challenge_dir_path, artifact_folder_name)
+    for file_path in file_paths:
+        if file_path.is_file():
+            shutil.copy(file_path, workspace)

classic/benchmark/agbenchmark/app.py

@@ -0,0 +1,339 @@
+import datetime
+import glob
+import json
+import logging
+import sys
+import time
+import uuid
+from collections import deque
+from multiprocessing import Process
+from pathlib import Path
+from typing import Optional
+
+import httpx
+import psutil
+from agent_protocol_client import AgentApi, ApiClient, ApiException, Configuration
+from agent_protocol_client.models import Task, TaskRequestBody
+from fastapi import APIRouter, FastAPI, HTTPException, Request, Response
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel, ConfigDict, ValidationError
+
+from agbenchmark.challenges import ChallengeInfo
+from agbenchmark.config import AgentBenchmarkConfig
+from agbenchmark.reports.processing.report_types_v2 import (
+    BenchmarkRun,
+    Metrics,
+    RepositoryInfo,
+    RunDetails,
+    TaskInfo,
+)
+from agbenchmark.schema import TaskEvalRequestBody
+from agbenchmark.utils.utils import write_pretty_json
+
+sys.path.append(str(Path(__file__).parent.parent))
+
+logger = logging.getLogger(__name__)
+
+CHALLENGES: dict[str, ChallengeInfo] = {}
+challenges_path = Path(__file__).parent / "challenges"
+challenge_spec_files = deque(
+    glob.glob(
+        f"{challenges_path}/**/data.json",
+        recursive=True,
+    )
+)
+
+logger.debug("Loading challenges...")
+while challenge_spec_files:
+    challenge_spec_file = Path(challenge_spec_files.popleft())
+    challenge_relpath = challenge_spec_file.relative_to(challenges_path.parent)
+    if challenge_relpath.is_relative_to("challenges/deprecated"):
+        continue
+
+    logger.debug(f"Loading {challenge_relpath}...")
+    try:
+        challenge_info = ChallengeInfo.model_validate_json(
+            challenge_spec_file.read_text()
+        )
+    except ValidationError as e:
+        if logging.getLogger().level == logging.DEBUG:
+            logger.warning(f"Spec file {challenge_relpath} failed to load:\n{e}")
+        logger.debug(f"Invalid challenge spec: {challenge_spec_file.read_text()}")
+        continue
+
+    if not challenge_info.eval_id:
+        challenge_info.eval_id = str(uuid.uuid4())
+        # this will sort all the keys of the JSON systematically
+        # so that the order is always the same
+        write_pretty_json(challenge_info.model_dump(), challenge_spec_file)
+
+    CHALLENGES[challenge_info.eval_id] = challenge_info
+
+
+class BenchmarkTaskInfo(BaseModel):
+    task_id: str
+    start_time: datetime.datetime
+    challenge_info: ChallengeInfo
+
+
+task_informations: dict[str, BenchmarkTaskInfo] = {}
+
+
+def find_agbenchmark_without_uvicorn():
+    pids = []
+    for process in psutil.process_iter(
+        attrs=[
+            "pid",
+            "cmdline",
+            "name",
+            "username",
+            "status",
+            "cpu_percent",
+            "memory_info",
+            "create_time",
+            "cwd",
+            "connections",
+        ]
+    ):
+        try:
+            # Convert the process.info dictionary values to strings and concatenate them
+            full_info = " ".join([str(v) for k, v in process.as_dict().items()])
+
+            if "agbenchmark" in full_info and "uvicorn" not in full_info:
+                pids.append(process.pid)
+        except (psutil.NoSuchProcess, psutil.AccessDenied, psutil.ZombieProcess):
+            pass
+    return pids
+
+
+class CreateReportRequest(BaseModel):
+    test: str
+    test_run_id: str
+    # category: Optional[str] = []
+    mock: Optional[bool] = False
+
+    model_config = ConfigDict(extra="forbid")
+
+
+updates_list = []
+
+origins = [
+    "http://localhost:8000",
+    "http://localhost:8080",
+    "http://127.0.0.1:5000",
+    "http://localhost:5000",
+]
+
+
+def stream_output(pipe):
+    for line in pipe:
+        print(line, end="")
+
+
+def setup_fastapi_app(agbenchmark_config: AgentBenchmarkConfig) -> FastAPI:
+    from agbenchmark.agent_api_interface import upload_artifacts
+    from agbenchmark.challenges import get_challenge_from_source_uri
+    from agbenchmark.main import run_benchmark
+
+    configuration = Configuration(
+        host=agbenchmark_config.host or "http://localhost:8000"
+    )
+    app = FastAPI()
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=origins,
+        allow_credentials=True,
+        allow_methods=["*"],
+        allow_headers=["*"],
+    )
+    router = APIRouter()
+
+    @router.post("/reports")
+    def run_single_test(body: CreateReportRequest) -> dict:
+        pids = find_agbenchmark_without_uvicorn()
+        logger.info(f"pids already running with agbenchmark: {pids}")
+
+        logger.debug(f"Request to /reports: {body.model_dump()}")
+
+        # Start the benchmark in a separate thread
+        benchmark_process = Process(
+            target=lambda: run_benchmark(
+                config=agbenchmark_config,
+                tests=(body.test,),
+                mock=body.mock or False,
+            )
+        )
+        benchmark_process.start()
+
+        # Wait for the benchmark to finish, with a timeout of 200 seconds
+        timeout = 200
+        start_time = time.time()
+        while benchmark_process.is_alive():
+            if time.time() - start_time > timeout:
+                logger.warning(f"Benchmark run timed out after {timeout} seconds")
+                benchmark_process.terminate()
+                break
+            time.sleep(1)
+        else:
+            logger.debug(f"Benchmark finished running in {time.time() - start_time} s")
+
+        # List all folders in the current working directory
+        reports_folder = agbenchmark_config.reports_folder
+        folders = [folder for folder in reports_folder.iterdir() if folder.is_dir()]
+
+        # Sort the folders based on their names
+        sorted_folders = sorted(folders, key=lambda x: x.name)
+
+        # Get the last folder
+        latest_folder = sorted_folders[-1] if sorted_folders else None
+
+        # Read report.json from this folder
+        if latest_folder:
+            report_path = latest_folder / "report.json"
+            logger.debug(f"Getting latest report from {report_path}")
+            if report_path.exists():
+                with report_path.open() as file:
+                    data = json.load(file)
+                logger.debug(f"Report data: {data}")
+            else:
+                raise HTTPException(
+                    502,
+                    "Could not get result after running benchmark: "
+                    f"'report.json' does not exist in '{latest_folder}'",
+                )
+        else:
+            raise HTTPException(
+                504, "Could not get result after running benchmark: no reports found"
+            )
+
+        return data
+
+    @router.post("/agent/tasks", tags=["agent"])
+    async def create_agent_task(task_eval_request: TaskEvalRequestBody) -> Task:
+        """
+        Creates a new task using the provided TaskEvalRequestBody and returns a Task.
+
+        Args:
+            task_eval_request: `TaskRequestBody` including an eval_id.
+
+        Returns:
+            Task: A new task with task_id, input, additional_input,
+                and empty lists for artifacts and steps.
+
+        Example:
+            Request (TaskEvalRequestBody defined in schema.py):
+                {
+                    ...,
+                    "eval_id": "50da533e-3904-4401-8a07-c49adf88b5eb"
+                }
+
+            Response (Task defined in `agent_protocol_client.models`):
+                {
+                    "task_id": "50da533e-3904-4401-8a07-c49adf88b5eb",
+                    "input": "Write the word 'Washington' to a .txt file",
+                    "artifacts": []
+                }
+        """
+        try:
+            challenge_info = CHALLENGES[task_eval_request.eval_id]
+            async with ApiClient(configuration) as api_client:
+                api_instance = AgentApi(api_client)
+                task_input = challenge_info.task
+
+                task_request_body = TaskRequestBody(
+                    input=task_input, additional_input=None
+                )
+                task_response = await api_instance.create_agent_task(
+                    task_request_body=task_request_body
+                )
+                task_info = BenchmarkTaskInfo(
+                    task_id=task_response.task_id,
+                    start_time=datetime.datetime.now(datetime.timezone.utc),
+                    challenge_info=challenge_info,
+                )
+                task_informations[task_info.task_id] = task_info
+
+                if input_artifacts_dir := challenge_info.task_artifacts_dir:
+                    await upload_artifacts(
+                        api_instance,
+                        input_artifacts_dir,
+                        task_response.task_id,
+                        "artifacts_in",
+                    )
+                return task_response
+        except ApiException as e:
+            logger.error(f"Error whilst trying to create a task:\n{e}")
+            logger.error(
+                "The above error was caused while processing request: "
+                f"{task_eval_request}"
+            )
+            raise HTTPException(500)
+
+    @router.post("/agent/tasks/{task_id}/steps")
+    async def proxy(request: Request, task_id: str):
+        timeout = httpx.Timeout(300.0, read=300.0)  # 5 minutes
+        async with httpx.AsyncClient(timeout=timeout) as client:
+            # Construct the new URL
+            new_url = f"{configuration.host}/ap/v1/agent/tasks/{task_id}/steps"
+
+            # Forward the request
+            response = await client.post(
+                new_url,
+                content=await request.body(),
+                headers=dict(request.headers),
+            )
+
+            # Return the response from the forwarded request
+            return Response(content=response.content, status_code=response.status_code)
+
+    @router.post("/agent/tasks/{task_id}/evaluations")
+    async def create_evaluation(task_id: str) -> BenchmarkRun:
+        task_info = task_informations[task_id]
+        challenge = get_challenge_from_source_uri(task_info.challenge_info.source_uri)
+        try:
+            async with ApiClient(configuration) as api_client:
+                api_instance = AgentApi(api_client)
+                eval_results = await challenge.evaluate_task_state(
+                    api_instance, task_id
+                )
+
+            eval_info = BenchmarkRun(
+                repository_info=RepositoryInfo(),
+                run_details=RunDetails(
+                    command=f"agbenchmark --test={challenge.info.name}",
+                    benchmark_start_time=(
+                        task_info.start_time.strftime("%Y-%m-%dT%H:%M:%S+00:00")
+                    ),
+                    test_name=challenge.info.name,
+                ),
+                task_info=TaskInfo(
+                    data_path=challenge.info.source_uri,
+                    is_regression=None,
+                    category=[c.value for c in challenge.info.category],
+                    task=challenge.info.task,
+                    answer=challenge.info.reference_answer or "",
+                    description=challenge.info.description or "",
+                ),
+                metrics=Metrics(
+                    success=all(e.passed for e in eval_results),
+                    success_percentage=(
+                        100 * sum(e.score for e in eval_results) / len(eval_results)
+                        if eval_results  # avoid division by 0
+                        else 0
+                    ),
+                    attempted=True,
+                ),
+                config={},
+            )
+
+            logger.debug(
+                f"Returning evaluation data:\n{eval_info.model_dump_json(indent=4)}"
+            )
+            return eval_info
+        except ApiException as e:
+            logger.error(f"Error {e} whilst trying to evaluate task: {task_id}")
+            raise HTTPException(500)
+
+    app.include_router(router, prefix="/ap/v1")
+
+    return app

classic/benchmark/agbenchmark/challenges/base.py

@@ -1,98 +1,19 @@
 import logging
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Any, AsyncIterator, Awaitable, ClassVar, Optional
+from typing import AsyncIterator, Awaitable, ClassVar, Optional
 
 import pytest
-from agbenchmark.config import AgentBenchmarkConfig
-from agbenchmark.utils.data_types import Category, DifficultyLevel, EvalResult
 from agent_protocol_client import AgentApi, Step
 from colorama import Fore, Style
 from pydantic import BaseModel, Field
 
+from agbenchmark.config import AgentBenchmarkConfig
+from agbenchmark.utils.data_types import Category, DifficultyLevel, EvalResult
+
 logger = logging.getLogger(__name__)
 
 
-def format_step_output(step: Step, step_num: int, challenge_name: str) -> str:
-    """Format a step for concise, informative console output.
-
-    Format: [Challenge] step N: tool_name(args) → result [$cost]
-    """
-    parts = [f"[{challenge_name}]", f"step {step_num}:"]
-
-    # Get additional_output data
-    ao: dict[str, Any] = step.additional_output or {}
-
-    # Get the tool being used in this step
-    use_tool = ao.get("use_tool", {})
-    tool_name = use_tool.get("name", "")
-    tool_args = use_tool.get("arguments", {})
-
-    if tool_name:
-        # Format tool call with abbreviated arguments
-        args_str = _format_tool_args(tool_name, tool_args)
-        parts.append(f"{Fore.CYAN}{tool_name}{Fore.RESET}({args_str})")
-    else:
-        parts.append(f"{Fore.YELLOW}(no tool){Fore.RESET}")
-
-    # Get result from last action (this step's tool will be executed next iteration)
-    last_action = ao.get("last_action", {})
-    if last_action:
-        result = last_action.get("result", {})
-        if isinstance(result, dict):
-            if result.get("error"):
-                parts.append(f"→ {Fore.RED}error{Fore.RESET}")
-            elif result.get("status") == "success":
-                parts.append(f"→ {Fore.GREEN}✓{Fore.RESET}")
-
-    # Add cost if available
-    cost = ao.get("task_cumulative_cost", 0)
-    if cost > 0:
-        parts.append(f"{Fore.BLUE}${cost:.3f}{Fore.RESET}")
-
-    return " ".join(parts)
-
-
-def _format_tool_args(tool_name: str, args: dict) -> str:
-    """Format tool arguments for display, keeping it concise."""
-    if not args:
-        return ""
-
-    # For common tools, show the most relevant argument
-    key_args = {
-        "read_file": ["filename"],
-        "write_file": ["filename"],
-        "open_file": ["filename", "file_path"],
-        "execute_python": ["filename"],
-        "execute_shell": ["command_line"],
-        "web_search": ["query"],
-        "read_webpage": ["url"],
-        "finish": ["reason"],
-        "ask_user": ["question"],
-        "todo_write": [],  # Skip args for todo_write (too verbose)
-    }
-
-    if tool_name in key_args:
-        keys = key_args[tool_name]
-        if not keys:
-            return "..."
-        values = [str(args.get(k, ""))[:40] for k in keys if k in args]
-        if values:
-            return ", ".join(
-                f'"{v}"' if " " not in v else f'"{v[:20]}..."' for v in values
-            )
-
-    # Default: show first arg value, abbreviated
-    if args:
-        first_key = next(iter(args))
-        first_val = str(args[first_key])[:30]
-        return f'{first_key}="{first_val}"' + (
-            "..." if len(str(args[first_key])) > 30 else ""
-        )
-
-    return ""
-
-
 class ChallengeInfo(BaseModel):
     eval_id: str = ""
     name: str
@@ -174,7 +95,7 @@ class BaseChallenge(ABC):
             cls.info.task, config, timeout, cls.info.task_artifacts_dir, mock=mock
         ):
             i += 1
-            print(format_step_output(step, i, cls.info.name))
+            print(f"[{cls.info.name}] - step {step.name} ({i}. request)")
             yield step
         logger.debug(f"Finished {cls.info.name} challenge run")
 
@@ -182,4 +103,5 @@ class BaseChallenge(ABC):
     @abstractmethod
     async def evaluate_task_state(
         cls, agent: AgentApi, task_id: str
-    ) -> list[EvalResult]: ...
+    ) -> list[EvalResult]:
+        ...

classic/benchmark/agbenchmark/challenges/builtin.py

@@ -10,16 +10,6 @@ from pathlib import Path
 from typing import Annotated, Any, ClassVar, Iterator, Literal, Optional
 
 import pytest
-from agbenchmark.agent_api_interface import download_agent_artifacts_into_folder
-from agbenchmark.agent_interface import copy_challenge_artifacts_into_workspace
-from agbenchmark.config import AgentBenchmarkConfig
-from agbenchmark.utils.data_types import Category, DifficultyLevel, EvalResult
-from agbenchmark.utils.prompts import (
-    END_PROMPT,
-    FEW_SHOT_EXAMPLES,
-    PROMPT_MAP,
-    SCORING_MAP,
-)
 from agent_protocol_client import AgentApi, ApiClient
 from agent_protocol_client import Configuration as ClientConfig
 from agent_protocol_client import Step
@@ -33,6 +23,17 @@ from pydantic import (
     field_validator,
 )
 
+from agbenchmark.agent_api_interface import download_agent_artifacts_into_folder
+from agbenchmark.agent_interface import copy_challenge_artifacts_into_workspace
+from agbenchmark.config import AgentBenchmarkConfig
+from agbenchmark.utils.data_types import Category, DifficultyLevel, EvalResult
+from agbenchmark.utils.prompts import (
+    END_PROMPT,
+    FEW_SHOT_EXAMPLES,
+    PROMPT_MAP,
+    SCORING_MAP,
+)
+
 from .base import BaseChallenge, ChallengeInfo
 
 logger = logging.getLogger(__name__)
@@ -68,9 +69,9 @@ class BuiltinChallengeSpec(BaseModel):
         class Eval(BaseModel):
             type: str
             scoring: Optional[Literal["percentage", "scale", "binary"]] = None
-            template: Optional[Literal["rubric", "reference", "question", "custom"]] = (
+            template: Optional[
-                None
+                Literal["rubric", "reference", "question", "custom"]
-            )
+            ] = None
             examples: Optional[str] = None
 
             @field_validator("scoring", "template")
@@ -227,11 +228,9 @@ class BuiltinChallenge(BaseChallenge):
         request.node.user_properties.append(
             (
                 "answers",
-                (
+                [r.result for r in eval_results]
-                    [r.result for r in eval_results]
+                if request.config.getoption("--keep-answers")
-                    if request.config.getoption("--keep-answers")
+                else None,
-                    else None
-                ),
             )
         )
         request.node.user_properties.append(("scores", [r.score for r in eval_results]))