fix(permissions): update wildcard handling for command patterns

- Add PlatformBlocksComponent to Agent as a default component
- Component automatically enables when PLATFORM_API_KEY env var is set
- Config now uses UserConfigurable for env var support:
  - PLATFORM_API_KEY (required to enable)
  - PLATFORM_URL (default: https://platform.agpt.co)
  - PLATFORM_BLOCKS_ENABLED (default: true)
  - PLATFORM_TIMEOUT (default: 60)
- API key stored as SecretStr for security

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

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

@@ -6,11 +6,15 @@ 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) }}
@@ -19,47 +23,22 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: classic/original_autogpt
+    working-directory: classic
 
 jobs:
   test:
     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' }}
+    runs-on: ubuntu-latest
 
     steps:
-      # 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'
+      - name: Start MinIO service
         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:
@@ -71,41 +50,23 @@ jobs:
           git config --global user.name "Auto-GPT-Bot"
           git config --global user.email "github-bot@agpt.co"
 
-      - name: Set up Python ${{ matrix.python-version }}
+      - name: Set up Python 3.12
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: "3.12"
 
       - 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: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/original_autogpt/poetry.lock') }}
+          path: ~/.cache/pypoetry
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
 
-      - name: Install Poetry (Unix)
-        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 Poetry
+        run: curl -sSL https://install.python-poetry.org | python3 -
 
       - name: Install Python dependencies
         run: poetry install
@@ -116,12 +77,12 @@ jobs:
             --cov=autogpt --cov-branch --cov-report term-missing --cov-report xml \
             --numprocesses=logical --durations=10 \
             --junitxml=junit.xml -o junit_family=legacy \
-            tests/unit tests/integration
+            original_autogpt/tests/unit original_autogpt/tests/integration
         env:
           CI: true
           PLAIN_OUTPUT: True
           OPENAI_API_KEY: ${{ secrets.OPENAI_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
 
@@ -135,11 +96,11 @@ jobs:
         uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
-          flags: autogpt-agent,${{ runner.os }}
+          flags: autogpt-agent
 
       - name: Upload logs to artifact
         if: always()
         uses: actions/upload-artifact@v4
         with:
           name: test-logs
-          path: classic/original_autogpt/logs/
+          path: classic/logs/

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

@@ -11,9 +11,6 @@ on:
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
       - 'classic/benchmark/**'
-      - 'classic/run'
-      - 'classic/cli.py'
-      - 'classic/setup.py'
       - '!**/*.md'
   pull_request:
     branches: [ master, dev, release-* ]
@@ -22,9 +19,6 @@ on:
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
       - 'classic/benchmark/**'
-      - 'classic/run'
-      - 'classic/cli.py'
-      - 'classic/setup.py'
       - '!**/*.md'
 
 defaults:
@@ -35,13 +29,9 @@ 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: '3.10'
+      min-python-version: '3.12'
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -55,22 +45,22 @@ 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: Run regression tests
+      - name: Install dependencies
+        run: poetry install
+
+      - name: Run smoke tests with direct-benchmark
         run: |
-          ./run agent start ${{ matrix.agent-name }}
-          cd ${{ matrix.agent-name }}
-          poetry run agbenchmark --mock --test=BasicRetrieval --test=Battleship --test=WebArenaTask_0
-          poetry run agbenchmark --test=WriteFile
+          poetry run direct-benchmark run \
+            --strategies one_shot \
+            --models claude \
+            --tests ReadFile,WriteFile \
+            --json
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          AGENT_NAME: ${{ matrix.agent-name }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           REQUESTS_CA_BUNDLE: /etc/ssl/certs/ca-certificates.crt
-          HELICONE_CACHE_ENABLED: false
-          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' }}
+          NONINTERACTIVE_MODE: "true"
+          CI: true

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

@@ -1,17 +1,21 @@
-name: Classic - AGBenchmark CI
+name: Classic - Direct Benchmark CI
 
 on:
   push:
     branches: [ master, dev, ci-test* ]
     paths:
-      - 'classic/benchmark/**'
-      - '!classic/benchmark/reports/**'
+      - 'classic/direct_benchmark/**'
+      - 'classic/benchmark/agbenchmark/challenges/**'
+      - 'classic/original_autogpt/**'
+      - 'classic/forge/**'
       - .github/workflows/classic-benchmark-ci.yml
   pull_request:
     branches: [ master, dev, release-* ]
     paths:
-      - 'classic/benchmark/**'
-      - '!classic/benchmark/reports/**'
+      - 'classic/direct_benchmark/**'
+      - 'classic/benchmark/agbenchmark/challenges/**'
+      - 'classic/original_autogpt/**'
+      - 'classic/forge/**'
       - .github/workflows/classic-benchmark-ci.yml
 
 concurrency:
@@ -23,23 +27,16 @@ defaults:
     shell: bash
 
 env:
-  min-python-version: '3.10'
+  min-python-version: '3.12'
 
 jobs:
-  test:
-    permissions:
-      contents: read
+  benchmark-tests:
+    runs-on: ubuntu-latest
     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/benchmark
+        working-directory: classic
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -47,71 +44,84 @@ jobs:
           fetch-depth: 0
           submodules: true
 
-      - name: Set up Python ${{ matrix.python-version }}
+      - name: Set up Python ${{ env.min-python-version }}
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ env.min-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: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/benchmark/poetry.lock') }}
+          path: ~/.cache/pypoetry
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
 
-      - name: Install Poetry (Unix)
-        if: runner.os != 'Windows'
+      - name: Install Poetry
         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
+      - name: Install dependencies
         run: poetry install
 
-      - name: Run pytest with coverage
+      - name: Run basic benchmark tests
         run: |
-          poetry run pytest -vv \
-            --cov=agbenchmark --cov-branch --cov-report term-missing --cov-report xml \
-            --durations=10 \
-            --junitxml=junit.xml -o junit_family=legacy \
-            tests
+          echo "Testing ReadFile challenge with one_shot strategy..."
+          poetry run direct-benchmark run \
+            --strategies one_shot \
+            --models claude \
+            --tests ReadFile \
+            --json
+
+          echo "Testing WriteFile challenge..."
+          poetry run direct-benchmark run \
+            --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: Upload test results to Codecov
-        if: ${{ !cancelled() }}  # Run even if tests fail
-        uses: codecov/test-results-action@v1
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
+      - name: Test category filtering
+        run: |
+          echo "Testing coding category..."
+          poetry run direct-benchmark run \
+            --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: Upload coverage reports to Codecov
-        uses: codecov/codecov-action@v5
-        with:
-          token: ${{ secrets.CODECOV_TOKEN }}
-          flags: agbenchmark,${{ runner.os }}
+      - name: Test multiple strategies
+        run: |
+          echo "Testing multiple strategies..."
+          poetry run direct-benchmark run \
+            --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"
 
-  self-test-with-agent:
+  # Run regression tests on maintain challenges
+  regression-tests:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        agent-name: [forge]
-      fail-fast: false
-    timeout-minutes: 20
+    timeout-minutes: 45
+    if: github.ref == 'refs/heads/master' || github.ref == 'refs/heads/dev'
+    defaults:
+      run:
+        shell: bash
+        working-directory: classic
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -126,51 +136,22 @@ jobs:
 
       - name: Install Poetry
         run: |
-          curl -sSL https://install.python-poetry.org | python -
+          curl -sSL https://install.python-poetry.org | python3 -
+
+      - name: Install dependencies
+        run: poetry install
 
       - name: Run regression tests
-        working-directory: classic
         run: |
-          ./run agent start ${{ matrix.agent-name }}
-          cd ${{ matrix.agent-name }}
-
-          set +e # Ignore non-zero exit codes and continue execution
-          echo "Running the following command: poetry run agbenchmark --maintain --mock"
-          poetry run agbenchmark --maintain --mock
-          EXIT_CODE=$?
-          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
+          echo "Running regression tests (previously beaten challenges)..."
+          poetry run direct-benchmark run \
+            --strategies one_shot \
+            --models claude \
+            --maintain \
+            --parallel 4 \
+            --json
         env:
+          CI: true
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          TELEMETRY_ENVIRONMENT: autogpt-benchmark-ci
-          TELEMETRY_OPT_IN: ${{ github.ref_name == 'master' }}
+          NONINTERACTIVE_MODE: "true"

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

@@ -6,13 +6,11 @@ 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) }}
@@ -21,115 +19,38 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: classic/forge
+    working-directory: classic
 
 jobs:
   test:
     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' }}
+    runs-on: ubuntu-latest
 
     steps:
-      # 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'
+      - name: Start MinIO service
         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: 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 }}
+      - name: Set up Python 3.12
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: "3.12"
 
       - 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: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/forge/poetry.lock') }}
+          path: ~/.cache/pypoetry
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
 
-      - name: Install Poetry (Unix)
-        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 Poetry
+        run: curl -sSL https://install.python-poetry.org | python3 -
 
       - name: Install Python dependencies
         run: poetry install
@@ -140,12 +61,15 @@ jobs:
             --cov=forge --cov-branch --cov-report term-missing --cov-report xml \
             --durations=10 \
             --junitxml=junit.xml -o junit_family=legacy \
-            forge
+            forge/forge forge/tests
         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 }}
-          S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          S3_ENDPOINT_URL: http://127.0.0.1:9000
           AWS_ACCESS_KEY_ID: minioadmin
           AWS_SECRET_ACCESS_KEY: minioadmin
 
@@ -159,85 +83,11 @@ jobs:
         uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
-          flags: forge,${{ 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
+          flags: forge
 
       - name: Upload logs to artifact
         if: always()
         uses: actions/upload-artifact@v4
         with:
           name: test-logs
-          path: classic/forge/logs/
+          path: classic/logs/

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

@@ -1,60 +0,0 @@
-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@v7
-        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

@@ -7,7 +7,9 @@ on:
       - '.github/workflows/classic-python-checks-ci.yml'
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
-      - 'classic/benchmark/**'
+      - 'classic/direct_benchmark/**'
+      - 'classic/pyproject.toml'
+      - 'classic/poetry.lock'
       - '**.py'
       - '!classic/forge/tests/vcr_cassettes'
   pull_request:
@@ -16,7 +18,9 @@ on:
       - '.github/workflows/classic-python-checks-ci.yml'
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
-      - 'classic/benchmark/**'
+      - 'classic/direct_benchmark/**'
+      - 'classic/pyproject.toml'
+      - 'classic/poetry.lock'
       - '**.py'
       - '!classic/forge/tests/vcr_cassettes'
 
@@ -27,44 +31,13 @@ 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: "3.10"
-
-    strategy:
-      matrix:
-        sub-package: ${{ fromJson(needs.get-changed-parts.outputs.changed-parts) }}
-      fail-fast: false
+      min-python-version: "3.12"
 
     steps:
       - name: Checkout repository
@@ -81,42 +54,31 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/.cache/pypoetry
-          key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}
+          key: ${{ runner.os }}-poetry-${{ hashFiles('classic/poetry.lock') }}
 
       - name: Install Poetry
         run: curl -sSL https://install.python-poetry.org | python3 -
 
-      # Install dependencies
-
       - name: Install Python dependencies
-        run: poetry -C classic/${{ matrix.sub-package }} install
+        run: poetry 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: "3.10"
-
-    strategy:
-      matrix:
-        sub-package: ${{ fromJson(needs.get-changed-parts.outputs.changed-parts) }}
-      fail-fast: false
+      min-python-version: "3.12"
 
     steps:
       - name: Checkout repository
@@ -133,19 +95,16 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/.cache/pypoetry
-          key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}
+          key: ${{ runner.os }}-poetry-${{ hashFiles('classic/poetry.lock') }}
 
       - name: Install Poetry
         run: curl -sSL https://install.python-poetry.org | python3 -
 
-      # Install dependencies
-
       - name: Install Python dependencies
-        run: poetry -C classic/${{ matrix.sub-package }} install
+        run: poetry install
 
       # Typecheck
 
       - name: Typecheck
         if: success() || failure()
         run: poetry run pyright
-        working-directory: classic/${{ matrix.sub-package }}

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

@@ -128,7 +128,7 @@ jobs:
           token: ${{ secrets.GITHUB_TOKEN }}
           exitOnceUploaded: true
 
-  e2e_test:
+  test:
     runs-on: big-boi
     needs: setup
     strategy:
@@ -258,39 +258,3 @@ jobs:
       - name: Print Final Docker Compose logs
         if: always()
         run: docker compose -f ../docker-compose.yml logs
-
-  integration_test:
-    runs-on: ubuntu-latest
-    needs: setup
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          submodules: recursive
-
-      - name: Set up Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: "22.18.0"
-
-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Restore dependencies cache
-        uses: actions/cache@v4
-        with:
-          path: ~/.pnpm-store
-          key: ${{ needs.setup.outputs.cache-key }}
-          restore-keys: |
-            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
-            ${{ runner.os }}-pnpm-
-
-      - name: Install dependencies
-        run: pnpm install --frozen-lockfile
-
-      - name: Generate API client
-        run: pnpm generate:api
-
-      - name: Run Integration Tests
-        run: pnpm test:unit

.gitignore

@@ -3,6 +3,7 @@
 classic/original_autogpt/keys.py
 classic/original_autogpt/*.json
 auto_gpt_workspace/*
+.autogpt/
 *.mpeg
 .env
 # Root .env files
@@ -159,6 +160,10 @@ 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
@@ -177,5 +182,8 @@ autogpt_platform/backend/settings.py
 
 *.ign.*
 .test-contents
-.claude/settings.local.json
+**/.claude/settings.local.json
 /autogpt_platform/backend/logs
+
+# Test database
+test.db

.gitmodules

@@ -1,3 +0,0 @@
-[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

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

AGENTS.md

@@ -16,34 +16,6 @@ See `docs/content/platform/getting-started.md` for setup instructions.
 - Format Python code with `poetry run format`.
 - Format frontend code using `pnpm format`.
 
-## Frontend guidelines:
-
-See `/frontend/CONTRIBUTING.md` for complete patterns. Quick reference:
-
-1. **Pages**: Create in `src/app/(platform)/feature-name/page.tsx`
-   - Add `usePageName.ts` hook for logic
-   - Put sub-components in local `components/` folder
-2. **Components**: Structure as `ComponentName/ComponentName.tsx` + `useComponentName.ts` + `helpers.ts`
-   - Use design system components from `src/components/` (atoms, molecules, organisms)
-   - Never use `src/components/__legacy__/*`
-3. **Data fetching**: Use generated API hooks from `@/app/api/__generated__/endpoints/`
-   - Regenerate with `pnpm generate:api`
-   - Pattern: `use{Method}{Version}{OperationName}`
-4. **Styling**: Tailwind CSS only, use design tokens, Phosphor Icons only
-5. **Testing**: Add Storybook stories for new components, Playwright for E2E
-6. **Code conventions**: Function declarations (not arrow functions) for components/handlers
-
-- Component props should be `interface Props { ... }` (not exported) unless the interface needs to be used outside the component
-- Separate render logic from business logic (component.tsx + useComponent.ts + helpers.ts)
-- Colocate state when possible and avoid creating large components, use sub-components ( local `/components` folder next to the parent component ) when sensible
-- Avoid large hooks, abstract logic into `helpers.ts` files when sensible
-- Use function declarations for components, arrow functions only for callbacks
-- No barrel files or `index.ts` re-exports
-- Avoid comments at all times unless the code is very complex
-- Do not use `useCallback` or `useMemo` unless asked to optimise a given function
-- Do not type hook returns, let Typescript infer as much as possible
-- Never type with `any`, if not types available use `unknown`
-
 ## Testing
 
 - Backend: `poetry run test` (runs pytest with a docker based postgres + prisma).
@@ -51,8 +23,22 @@ See `/frontend/CONTRIBUTING.md` for complete patterns. Quick reference:
 
 Always run the relevant linters and tests before committing.
 Use conventional commit messages for all commits (e.g. `feat(backend): add API`).
-Types: - feat - fix - refactor - ci - dx (developer experience)
-Scopes: - platform - platform/library - platform/marketplace - backend - backend/executor - frontend - frontend/library - frontend/marketplace - blocks
+  Types:
+    - feat
+    - fix
+    - refactor
+    - ci
+    - dx (developer experience)
+  Scopes:
+    - platform
+      - platform/library
+      - platform/marketplace
+      - backend
+        - backend/executor
+      - frontend
+        - frontend/library
+        - frontend/marketplace
+      - blocks
 
 ## Pull requests
 

autogpt_platform/CLAUDE.md

@@ -85,6 +85,17 @@ pnpm format
 pnpm types
 ```
 
+**📖 Complete Guide**: See `/frontend/CONTRIBUTING.md` and `/frontend/.cursorrules` for comprehensive frontend patterns.
+
+**Key Frontend Conventions:**
+
+- Separate render logic from data/behavior in components
+- Use generated API hooks from `@/app/api/__generated__/endpoints/`
+- Use function declarations (not arrow functions) for components/handlers
+- Use design system components from `src/components/` (atoms, molecules, organisms)
+- Only use Phosphor Icons
+- Never use `src/components/__legacy__/*` or deprecated `BackendAPI`
+
 ## Architecture Overview
 
 ### Backend Architecture
@@ -183,50 +194,6 @@ ex: do the inputs and outputs tie well together?
 
 If you get any pushback or hit complex block conditions check the new_blocks guide in the docs.
 
-**Handling files in blocks with `store_media_file()`:**
-
-When blocks need to work with files (images, videos, documents), use `store_media_file()` from `backend.util.file`. The `return_format` parameter determines what you get back:
-
-| Format | Use When | Returns |
-|--------|----------|---------|
-| `"for_local_processing"` | Processing with local tools (ffmpeg, MoviePy, PIL) | Local file path (e.g., `"image.png"`) |
-| `"for_external_api"` | Sending content to external APIs (Replicate, OpenAI) | Data URI (e.g., `"data:image/png;base64,..."`) |
-| `"for_block_output"` | Returning output from your block | Smart: `workspace://` in CoPilot, data URI in graphs |
-
-**Examples:**
-```python
-# INPUT: Need to process file locally with ffmpeg
-local_path = await store_media_file(
-    file=input_data.video,
-    execution_context=execution_context,
-    return_format="for_local_processing",
-)
-# local_path = "video.mp4" - use with Path/ffmpeg/etc
-
-# INPUT: Need to send to external API like Replicate
-image_b64 = await store_media_file(
-    file=input_data.image,
-    execution_context=execution_context,
-    return_format="for_external_api",
-)
-# image_b64 = "data:image/png;base64,iVBORw0..." - send to API
-
-# OUTPUT: Returning result from block
-result_url = await store_media_file(
-    file=generated_image_url,
-    execution_context=execution_context,
-    return_format="for_block_output",
-)
-yield "image_url", result_url
-# In CoPilot: result_url = "workspace://abc123"
-# In graphs:  result_url = "data:image/png;base64,..."
-```
-
-**Key points:**
-- `for_block_output` is the ONLY format that auto-adapts to execution context
-- Always use `for_block_output` for block outputs unless you have a specific reason not to
-- Never hardcode workspace checks - let `for_block_output` handle it
-
 **Modifying the API:**
 
 1. Update route in `/backend/backend/server/routers/`
@@ -234,7 +201,7 @@ yield "image_url", result_url
 3. Write tests alongside the route file
 4. Run `poetry run test` to verify
 
-### Frontend guidelines:
+**Frontend feature development:**
 
 See `/frontend/CONTRIBUTING.md` for complete patterns. Quick reference:
 
@@ -251,17 +218,6 @@ See `/frontend/CONTRIBUTING.md` for complete patterns. Quick reference:
 5. **Testing**: Add Storybook stories for new components, Playwright for E2E
 6. **Code conventions**: Function declarations (not arrow functions) for components/handlers
 
-- Component props should be `interface Props { ... }` (not exported) unless the interface needs to be used outside the component
-- Separate render logic from business logic (component.tsx + useComponent.ts + helpers.ts)
-- Colocate state when possible and avoid creating large components, use sub-components ( local `/components` folder next to the parent component ) when sensible
-- Avoid large hooks, abstract logic into `helpers.ts` files when sensible
-- Use function declarations for components, arrow functions only for callbacks
-- No barrel files or `index.ts` re-exports
-- Do not use `useCallback` or `useMemo` unless asked to optimise a given function
-- Avoid comments at all times unless the code is very complex
-- Do not type hook returns, let Typescript infer as much as possible
-- Never type with `any`, if not types available use `unknown`
-
 ### Security Implementation
 
 **Cache Protection Middleware:**

autogpt_platform/backend/.env.default

@@ -178,10 +178,5 @@ AYRSHARE_JWT_KEY=
 SMARTLEAD_API_KEY=
 ZEROBOUNCE_API_KEY=
 
-# PostHog Analytics
-# Get API key from https://posthog.com - Project Settings > Project API Key
-POSTHOG_API_KEY=
-POSTHOG_HOST=https://eu.i.posthog.com
-
 # Other Services
 AUTOMOD_API_KEY=

autogpt_platform/backend/backend/api/external/v1/routes.py

@@ -86,8 +86,6 @@ async def execute_graph_block(
     obj = backend.data.block.get_block(block_id)
     if not obj:
         raise HTTPException(status_code=404, detail=f"Block #{block_id} not found.")
-    if obj.disabled:
-        raise HTTPException(status_code=403, detail=f"Block #{block_id} is disabled.")
 
     output = defaultdict(list)
     async for name, data in obj.execute(data):

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

@@ -1,308 +0,0 @@
-"""RabbitMQ consumer for operation completion messages.
-
-This module provides a consumer that listens for completion notifications
-from external services (like Agent Generator) and triggers the appropriate
-stream registry and chat service updates.
-"""
-
-import asyncio
-import logging
-
-import orjson
-from pydantic import BaseModel
-
-from backend.data.rabbitmq import (
-    AsyncRabbitMQ,
-    Exchange,
-    ExchangeType,
-    Queue,
-    RabbitMQConfig,
-)
-
-from . import service as chat_service
-from . import stream_registry
-from .response_model import StreamError, StreamToolOutputAvailable
-from .tools.models import ErrorResponse
-
-logger = logging.getLogger(__name__)
-
-# Queue and exchange configuration
-OPERATION_COMPLETE_EXCHANGE = Exchange(
-    name="chat_operations",
-    type=ExchangeType.DIRECT,
-    durable=True,
-)
-
-OPERATION_COMPLETE_QUEUE = Queue(
-    name="chat_operation_complete",
-    durable=True,
-    exchange=OPERATION_COMPLETE_EXCHANGE,
-    routing_key="operation.complete",
-)
-
-RABBITMQ_CONFIG = RabbitMQConfig(
-    exchanges=[OPERATION_COMPLETE_EXCHANGE],
-    queues=[OPERATION_COMPLETE_QUEUE],
-)
-
-
-class OperationCompleteMessage(BaseModel):
-    """Message format for operation completion notifications."""
-
-    operation_id: str
-    task_id: str
-    success: bool
-    result: dict | str | None = None
-    error: str | None = None
-
-
-class ChatCompletionConsumer:
-    """Consumer for chat operation completion messages from RabbitMQ."""
-
-    def __init__(self):
-        self._rabbitmq: AsyncRabbitMQ | None = None
-        self._consumer_task: asyncio.Task | None = None
-        self._running = False
-
-    async def start(self) -> None:
-        """Start the completion consumer."""
-        if self._running:
-            logger.warning("Completion consumer already running")
-            return
-
-        self._rabbitmq = AsyncRabbitMQ(RABBITMQ_CONFIG)
-        await self._rabbitmq.connect()
-
-        self._running = True
-        self._consumer_task = asyncio.create_task(self._consume_messages())
-        logger.info("Chat completion consumer started")
-
-    async def stop(self) -> None:
-        """Stop the completion consumer."""
-        self._running = False
-
-        if self._consumer_task:
-            self._consumer_task.cancel()
-            try:
-                await self._consumer_task
-            except asyncio.CancelledError:
-                pass
-            self._consumer_task = None
-
-        if self._rabbitmq:
-            await self._rabbitmq.disconnect()
-            self._rabbitmq = None
-
-        logger.info("Chat completion consumer stopped")
-
-    async def _consume_messages(self) -> None:
-        """Main message consumption loop."""
-        if not self._rabbitmq:
-            logger.error("RabbitMQ not initialized")
-            return
-
-        try:
-            channel = await self._rabbitmq.get_channel()
-            queue = await channel.get_queue(OPERATION_COMPLETE_QUEUE.name)
-
-            async with queue.iterator() as queue_iter:
-                async for message in queue_iter:
-                    if not self._running:
-                        break
-
-                    try:
-                        async with message.process():
-                            await self._handle_message(message.body)
-                    except Exception as e:
-                        logger.error(
-                            f"Error processing completion message: {e}",
-                            exc_info=True,
-                        )
-                        # Message will be requeued due to exception
-
-        except asyncio.CancelledError:
-            logger.info("Consumer cancelled")
-        except Exception as e:
-            logger.error(f"Consumer error: {e}", exc_info=True)
-            # Attempt to reconnect after a delay
-            if self._running:
-                await asyncio.sleep(5)
-                await self._consume_messages()
-
-    async def _handle_message(self, body: bytes) -> None:
-        """Handle a single completion message."""
-        try:
-            data = orjson.loads(body)
-            message = OperationCompleteMessage(**data)
-        except Exception as e:
-            logger.error(f"Failed to parse completion message: {e}")
-            return
-
-        logger.info(
-            f"Received completion for operation {message.operation_id} "
-            f"(task_id={message.task_id}, success={message.success})"
-        )
-
-        # Find task in registry
-        task = await stream_registry.find_task_by_operation_id(message.operation_id)
-        if task is None:
-            # Try to look up by task_id directly
-            task = await stream_registry.get_task(message.task_id)
-
-        if task is None:
-            logger.warning(
-                f"Task not found for operation {message.operation_id} "
-                f"(task_id={message.task_id})"
-            )
-            return
-
-        if message.success:
-            await self._handle_success(task, message)
-        else:
-            await self._handle_failure(task, message)
-
-    async def _handle_success(
-        self,
-        task: stream_registry.ActiveTask,
-        message: OperationCompleteMessage,
-    ) -> None:
-        """Handle successful operation completion."""
-        # Publish result to stream registry
-        result_output = message.result if message.result else {"status": "completed"}
-        await stream_registry.publish_chunk(
-            task.task_id,
-            StreamToolOutputAvailable(
-                toolCallId=task.tool_call_id,
-                toolName=task.tool_name,
-                output=(
-                    result_output
-                    if isinstance(result_output, str)
-                    else orjson.dumps(result_output).decode("utf-8")
-                ),
-                success=True,
-            ),
-        )
-
-        # Update pending operation in database
-        result_str = (
-            message.result
-            if isinstance(message.result, str)
-            else (
-                orjson.dumps(message.result).decode("utf-8")
-                if message.result
-                else '{"status": "completed"}'
-            )
-        )
-        await chat_service._update_pending_operation(
-            session_id=task.session_id,
-            tool_call_id=task.tool_call_id,
-            result=result_str,
-        )
-
-        # Generate LLM continuation with streaming
-        await chat_service._generate_llm_continuation_with_streaming(
-            session_id=task.session_id,
-            user_id=task.user_id,
-            task_id=task.task_id,
-        )
-
-        # Mark task as completed
-        await stream_registry.mark_task_completed(task.task_id, status="completed")
-
-        logger.info(
-            f"Successfully processed completion for task {task.task_id} "
-            f"(operation {message.operation_id})"
-        )
-
-    async def _handle_failure(
-        self,
-        task: stream_registry.ActiveTask,
-        message: OperationCompleteMessage,
-    ) -> None:
-        """Handle failed operation completion."""
-        error_msg = message.error or "Operation failed"
-
-        # Publish error to stream registry
-        await stream_registry.publish_chunk(
-            task.task_id,
-            StreamError(errorText=error_msg),
-        )
-
-        # Update pending operation with error
-        error_response = ErrorResponse(
-            message=error_msg,
-            error=message.error,
-        )
-        await chat_service._update_pending_operation(
-            session_id=task.session_id,
-            tool_call_id=task.tool_call_id,
-            result=error_response.model_dump_json(),
-        )
-
-        # Mark task as failed
-        await stream_registry.mark_task_completed(task.task_id, status="failed")
-
-        logger.info(
-            f"Processed failure for task {task.task_id} "
-            f"(operation {message.operation_id}): {error_msg}"
-        )
-
-
-# Module-level consumer instance
-_consumer: ChatCompletionConsumer | None = None
-
-
-async def start_completion_consumer() -> None:
-    """Start the global completion consumer."""
-    global _consumer
-    if _consumer is None:
-        _consumer = ChatCompletionConsumer()
-    await _consumer.start()
-
-
-async def stop_completion_consumer() -> None:
-    """Stop the global completion consumer."""
-    global _consumer
-    if _consumer:
-        await _consumer.stop()
-        _consumer = None
-
-
-async def publish_operation_complete(
-    operation_id: str,
-    task_id: str,
-    success: bool,
-    result: dict | str | None = None,
-    error: str | None = None,
-) -> None:
-    """Publish an operation completion message.
-
-    This is a helper function for testing or for services that want to
-    publish completion messages directly.
-
-    Args:
-        operation_id: The operation ID that completed.
-        task_id: The task ID associated with the operation.
-        success: Whether the operation succeeded.
-        result: The result data (for success).
-        error: The error message (for failure).
-    """
-    message = OperationCompleteMessage(
-        operation_id=operation_id,
-        task_id=task_id,
-        success=success,
-        result=result,
-        error=error,
-    )
-
-    rabbitmq = AsyncRabbitMQ(RABBITMQ_CONFIG)
-    try:
-        await rabbitmq.connect()
-        await rabbitmq.publish_message(
-            routing_key="operation.complete",
-            message=message.model_dump_json(),
-            exchange=OPERATION_COMPLETE_EXCHANGE,
-        )
-        logger.info(f"Published completion for operation {operation_id}")
-    finally:
-        await rabbitmq.disconnect()

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

@@ -33,29 +33,9 @@ class ChatConfig(BaseSettings):
 
     stream_timeout: int = Field(default=300, description="Stream timeout in seconds")
     max_retries: int = Field(default=3, description="Maximum number of retries")
-    max_agent_runs: int = Field(default=30, description="Maximum number of agent runs")
+    max_agent_runs: int = Field(default=3, description="Maximum number of agent runs")
     max_agent_schedules: int = Field(
-        default=30, description="Maximum number of agent schedules"
-    )
-
-    # Long-running operation configuration
-    long_running_operation_ttl: int = Field(
-        default=600,
-        description="TTL in seconds for long-running operation tracking in Redis (safety net if pod dies)",
-    )
-
-    # Stream registry configuration for SSE reconnection
-    stream_ttl: int = Field(
-        default=3600,
-        description="TTL in seconds for stream data in Redis (1 hour)",
-    )
-    stream_max_length: int = Field(
-        default=1000,
-        description="Maximum number of messages to store per stream",
-    )
-    internal_api_key: str | None = Field(
-        default=None,
-        description="API key for internal webhook callbacks (env: CHAT_INTERNAL_API_KEY)",
+        default=3, description="Maximum number of agent schedules"
     )
 
     # Langfuse Prompt Management Configuration

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

@@ -247,45 +247,3 @@ async def get_chat_session_message_count(session_id: str) -> int:
     """Get the number of messages in a chat session."""
     count = await PrismaChatMessage.prisma().count(where={"sessionId": session_id})
     return count
-
-
-async def update_tool_message_content(
-    session_id: str,
-    tool_call_id: str,
-    new_content: str,
-) -> bool:
-    """Update the content of a tool message in chat history.
-
-    Used by background tasks to update pending operation messages with final results.
-
-    Args:
-        session_id: The chat session ID.
-        tool_call_id: The tool call ID to find the message.
-        new_content: The new content to set.
-
-    Returns:
-        True if a message was updated, False otherwise.
-    """
-    try:
-        result = await PrismaChatMessage.prisma().update_many(
-            where={
-                "sessionId": session_id,
-                "toolCallId": tool_call_id,
-            },
-            data={
-                "content": new_content,
-            },
-        )
-        if result == 0:
-            logger.warning(
-                f"No message found to update for session {session_id}, "
-                f"tool_call_id {tool_call_id}"
-            )
-            return False
-        return True
-    except Exception as e:
-        logger.error(
-            f"Failed to update tool message for session {session_id}, "
-            f"tool_call_id {tool_call_id}: {e}"
-        )
-        return False

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

@@ -290,26 +290,6 @@ async def _cache_session(session: ChatSession) -> None:
     await async_redis.setex(redis_key, config.session_ttl, session.model_dump_json())
 
 
-async def cache_chat_session(session: ChatSession) -> None:
-    """Cache a chat session without persisting to the database."""
-    await _cache_session(session)
-
-
-async def invalidate_session_cache(session_id: str) -> None:
-    """Invalidate a chat session from Redis cache.
-
-    Used by background tasks to ensure fresh data is loaded on next access.
-    This is best-effort - Redis failures are logged but don't fail the operation.
-    """
-    try:
-        redis_key = _get_session_cache_key(session_id)
-        async_redis = await get_redis_async()
-        await async_redis.delete(redis_key)
-    except Exception as e:
-        # Best-effort: log but don't fail - cache will expire naturally
-        logger.warning(f"Failed to invalidate session cache for {session_id}: {e}")
-
-
 async def _get_session_from_db(session_id: str) -> ChatSession | None:
     """Get a chat session from the database."""
     prisma_session = await chat_db.get_chat_session(session_id)

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

@@ -31,7 +31,6 @@ class ResponseType(str, Enum):
     # Other
     ERROR = "error"
     USAGE = "usage"
-    HEARTBEAT = "heartbeat"
 
 
 class StreamBaseResponse(BaseModel):
@@ -143,20 +142,3 @@ class StreamError(StreamBaseResponse):
     details: dict[str, Any] | None = Field(
         default=None, description="Additional error details"
     )
-
-
-class StreamHeartbeat(StreamBaseResponse):
-    """Heartbeat to keep SSE connection alive during long-running operations.
-
-    Uses SSE comment format (: comment) which is ignored by clients but keeps
-    the connection alive through proxies and load balancers.
-    """
-
-    type: ResponseType = ResponseType.HEARTBEAT
-    toolCallId: str | None = Field(
-        default=None, description="Tool call ID if heartbeat is for a specific tool"
-    )
-
-    def to_sse(self) -> str:
-        """Convert to SSE comment format to keep connection alive."""
-        return ": heartbeat\n\n"

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

@@ -5,17 +5,15 @@ from collections.abc import AsyncGenerator
 from typing import Annotated
 
 from autogpt_libs import auth
-from fastapi import APIRouter, Depends, Header, HTTPException, Query, Security
+from fastapi import APIRouter, Depends, Query, Security
 from fastapi.responses import StreamingResponse
 from pydantic import BaseModel
 
 from backend.util.exceptions import NotFoundError
 
 from . import service as chat_service
-from . import stream_registry
 from .config import ChatConfig
 from .model import ChatSession, create_chat_session, get_chat_session, get_user_sessions
-from .response_model import StreamFinish
 
 config = ChatConfig()
 
@@ -83,14 +81,6 @@ class ListSessionsResponse(BaseModel):
     total: int
 
 
-class OperationCompleteRequest(BaseModel):
-    """Request model for external completion webhook."""
-
-    success: bool
-    result: dict | str | None = None
-    error: str | None = None
-
-
 # ========== Routes ==========
 
 
@@ -182,12 +172,12 @@ async def get_session(
         user_id: The optional authenticated user ID, or None for anonymous access.
 
     Returns:
-        SessionDetailResponse: Details for the requested session, or None if not found.
+        SessionDetailResponse: Details for the requested session; raises NotFoundError if not found.
 
     """
     session = await get_chat_session(session_id, user_id)
     if not session:
-        raise NotFoundError(f"Session {session_id} not found.")
+        raise NotFoundError(f"Session {session_id} not found")
 
     messages = [message.model_dump() for message in session.messages]
     logger.info(
@@ -232,8 +222,6 @@ async def stream_chat_post(
     session = await _validate_and_get_session(session_id, user_id)
 
     async def event_generator() -> AsyncGenerator[str, None]:
-        chunk_count = 0
-        first_chunk_type: str | None = None
         async for chunk in chat_service.stream_chat_completion(
             session_id,
             request.message,
@@ -242,26 +230,7 @@ async def stream_chat_post(
             session=session,  # Pass pre-fetched session to avoid double-fetch
             context=request.context,
         ):
-            if chunk_count < 3:
-                logger.info(
-                    "Chat stream chunk",
-                    extra={
-                        "session_id": session_id,
-                        "chunk_type": str(chunk.type),
-                    },
-                )
-            if not first_chunk_type:
-                first_chunk_type = str(chunk.type)
-            chunk_count += 1
             yield chunk.to_sse()
-        logger.info(
-            "Chat stream completed",
-            extra={
-                "session_id": session_id,
-                "chunk_count": chunk_count,
-                "first_chunk_type": first_chunk_type,
-            },
-        )
         # AI SDK protocol termination
         yield "data: [DONE]\n\n"
 
@@ -306,8 +275,6 @@ async def stream_chat_get(
     session = await _validate_and_get_session(session_id, user_id)
 
     async def event_generator() -> AsyncGenerator[str, None]:
-        chunk_count = 0
-        first_chunk_type: str | None = None
         async for chunk in chat_service.stream_chat_completion(
             session_id,
             message,
@@ -315,26 +282,7 @@ async def stream_chat_get(
             user_id=user_id,
             session=session,  # Pass pre-fetched session to avoid double-fetch
         ):
-            if chunk_count < 3:
-                logger.info(
-                    "Chat stream chunk",
-                    extra={
-                        "session_id": session_id,
-                        "chunk_type": str(chunk.type),
-                    },
-                )
-            if not first_chunk_type:
-                first_chunk_type = str(chunk.type)
-            chunk_count += 1
             yield chunk.to_sse()
-        logger.info(
-            "Chat stream completed",
-            extra={
-                "session_id": session_id,
-                "chunk_count": chunk_count,
-                "first_chunk_type": first_chunk_type,
-            },
-        )
         # AI SDK protocol termination
         yield "data: [DONE]\n\n"
 
@@ -376,243 +324,6 @@ async def session_assign_user(
     return {"status": "ok"}
 
 
-# ========== Task Streaming (SSE Reconnection) ==========
-
-
-@router.get(
-    "/tasks/{task_id}/stream",
-)
-async def stream_task(
-    task_id: str,
-    user_id: str | None = Depends(auth.get_user_id),
-    last_idx: int = Query(default=0, ge=0, description="Last message index received"),
-):
-    """
-    Reconnect to a long-running task's SSE stream.
-
-    When a long-running operation (like agent generation) starts, the client
-    receives a task_id. If the connection drops, the client can reconnect
-    using this endpoint to resume receiving updates.
-
-    Args:
-        task_id: The task ID from the operation_started response.
-        user_id: Authenticated user ID for ownership validation.
-        last_idx: Last message index received (0 for full replay).
-
-    Returns:
-        StreamingResponse: SSE-formatted response chunks starting from last_idx.
-
-    Raises:
-        NotFoundError: If task_id is not found or user doesn't have access.
-    """
-    # Get subscriber queue from stream registry
-    subscriber_queue = await stream_registry.subscribe_to_task(
-        task_id=task_id,
-        user_id=user_id,
-        last_idx=last_idx,
-    )
-
-    if subscriber_queue is None:
-        raise NotFoundError(f"Task {task_id} not found or access denied.")
-
-    async def event_generator() -> AsyncGenerator[str, None]:
-        chunk_count = 0
-        try:
-            while True:
-                # Wait for next chunk from the queue
-                chunk = await subscriber_queue.get()
-                chunk_count += 1
-                yield chunk.to_sse()
-
-                # Check for finish signal
-                if isinstance(chunk, StreamFinish):
-                    logger.info(
-                        f"Task stream completed for task {task_id}, "
-                        f"chunk_count={chunk_count}"
-                    )
-                    break
-        except Exception as e:
-            logger.error(f"Error in task stream {task_id}: {e}", exc_info=True)
-
-        # AI SDK protocol termination
-        yield "data: [DONE]\n\n"
-
-    return StreamingResponse(
-        event_generator(),
-        media_type="text/event-stream",
-        headers={
-            "Cache-Control": "no-cache",
-            "Connection": "keep-alive",
-            "X-Accel-Buffering": "no",
-            "x-vercel-ai-ui-message-stream": "v1",
-        },
-    )
-
-
-@router.get(
-    "/tasks/{task_id}",
-)
-async def get_task_status(
-    task_id: str,
-    user_id: str | None = Depends(auth.get_user_id),
-) -> dict:
-    """
-    Get the status of a long-running task.
-
-    Args:
-        task_id: The task ID to check.
-        user_id: Authenticated user ID for ownership validation.
-
-    Returns:
-        dict: Task status including task_id, status, tool_name, and operation_id.
-
-    Raises:
-        NotFoundError: If task_id is not found or user doesn't have access.
-    """
-    task = await stream_registry.get_task(task_id)
-
-    if task is None:
-        raise NotFoundError(f"Task {task_id} not found.")
-
-    # Validate ownership
-    if user_id and task.user_id and task.user_id != user_id:
-        raise NotFoundError(f"Task {task_id} not found.")
-
-    return {
-        "task_id": task.task_id,
-        "session_id": task.session_id,
-        "status": task.status,
-        "tool_name": task.tool_name,
-        "operation_id": task.operation_id,
-        "created_at": task.created_at.isoformat(),
-    }
-
-
-# ========== External Completion Webhook ==========
-
-
-@router.post(
-    "/operations/{operation_id}/complete",
-    status_code=200,
-)
-async def complete_operation(
-    operation_id: str,
-    request: OperationCompleteRequest,
-    x_api_key: str | None = Header(default=None),
-) -> dict:
-    """
-    External completion webhook for long-running operations.
-
-    Called by Agent Generator (or other services) when an operation completes.
-    This triggers the stream registry to publish completion and continue LLM generation.
-
-    Args:
-        operation_id: The operation ID to complete.
-        request: Completion payload with success status and result/error.
-        x_api_key: Internal API key for authentication.
-
-    Returns:
-        dict: Status of the completion.
-
-    Raises:
-        HTTPException: If API key is invalid or operation not found.
-    """
-    # Validate internal API key
-    if config.internal_api_key:
-        if x_api_key != config.internal_api_key:
-            raise HTTPException(status_code=401, detail="Invalid API key")
-    else:
-        # If no internal API key is configured, log a warning
-        logger.warning(
-            "Operation complete webhook called without API key validation "
-            "(CHAT_INTERNAL_API_KEY not configured)"
-        )
-
-    # Find task by operation_id
-    task = await stream_registry.find_task_by_operation_id(operation_id)
-    if task is None:
-        raise HTTPException(
-            status_code=404,
-            detail=f"Operation {operation_id} not found",
-        )
-
-    logger.info(
-        f"Received completion webhook for operation {operation_id} "
-        f"(task_id={task.task_id}, success={request.success})"
-    )
-
-    if request.success:
-        # Publish result to stream registry
-        from .response_model import StreamToolOutputAvailable
-
-        result_output = request.result if request.result else {"status": "completed"}
-        await stream_registry.publish_chunk(
-            task.task_id,
-            StreamToolOutputAvailable(
-                toolCallId=task.tool_call_id,
-                toolName=task.tool_name,
-                output=(
-                    result_output
-                    if isinstance(result_output, str)
-                    else str(result_output)
-                ),
-                success=True,
-            ),
-        )
-
-        # Update pending operation in database
-        from . import service as svc
-
-        result_str = (
-            request.result
-            if isinstance(request.result, str)
-            else str(request.result) if request.result else '{"status": "completed"}'
-        )
-        await svc._update_pending_operation(
-            session_id=task.session_id,
-            tool_call_id=task.tool_call_id,
-            result=result_str,
-        )
-
-        # Generate LLM continuation with streaming
-        await svc._generate_llm_continuation_with_streaming(
-            session_id=task.session_id,
-            user_id=task.user_id,
-            task_id=task.task_id,
-        )
-
-        # Mark task as completed
-        await stream_registry.mark_task_completed(task.task_id, status="completed")
-    else:
-        # Publish error to stream registry
-        from .response_model import StreamError
-
-        error_msg = request.error or "Operation failed"
-        await stream_registry.publish_chunk(
-            task.task_id,
-            StreamError(errorText=error_msg),
-        )
-
-        # Update pending operation with error
-        from . import service as svc
-        from .tools.models import ErrorResponse
-
-        error_response = ErrorResponse(
-            message=error_msg,
-            error=request.error,
-        )
-        await svc._update_pending_operation(
-            session_id=task.session_id,
-            tool_call_id=task.tool_call_id,
-            result=error_response.model_dump_json(),
-        )
-
-        # Mark task as failed
-        await stream_registry.mark_task_completed(task.task_id, status="failed")
-
-    return {"status": "ok", "task_id": task.task_id}
-
-
 # ========== Health Check ==========
 
 

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

@@ -1,470 +0,0 @@
-"""Stream registry for managing reconnectable SSE streams.
-
-This module provides a registry for tracking active streaming tasks and their
-messages. It supports:
-- Creating tasks with unique IDs for long-running operations
-- Publishing stream messages to both Redis Streams and in-memory queues
-- Subscribing to tasks with replay of missed messages
-- Looking up tasks by operation_id for webhook callbacks
-"""
-
-import asyncio
-import logging
-from dataclasses import dataclass, field
-from datetime import datetime, timezone
-from typing import Any, Literal
-
-import orjson
-
-from backend.data.redis_client import get_redis_async
-
-from .config import ChatConfig
-from .response_model import StreamBaseResponse, StreamFinish
-
-logger = logging.getLogger(__name__)
-config = ChatConfig()
-
-
-@dataclass
-class ActiveTask:
-    """Represents an active streaming task."""
-
-    task_id: str
-    session_id: str
-    user_id: str | None
-    tool_call_id: str
-    tool_name: str
-    operation_id: str
-    status: Literal["running", "completed", "failed"] = "running"
-    created_at: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
-    queue: asyncio.Queue[StreamBaseResponse] = field(default_factory=asyncio.Queue)
-    asyncio_task: asyncio.Task | None = None
-
-
-# Module-level registry for active tasks
-_active_tasks: dict[str, ActiveTask] = {}
-
-# Redis key patterns
-TASK_META_PREFIX = "chat:task:meta:"  # Hash for task metadata
-TASK_STREAM_PREFIX = "chat:stream:"  # Redis Stream for messages
-TASK_OP_PREFIX = "chat:task:op:"  # Operation ID -> task_id mapping
-
-
-def _get_task_meta_key(task_id: str) -> str:
-    """Get Redis key for task metadata."""
-    return f"{TASK_META_PREFIX}{task_id}"
-
-
-def _get_task_stream_key(task_id: str) -> str:
-    """Get Redis key for task message stream."""
-    return f"{TASK_STREAM_PREFIX}{task_id}"
-
-
-def _get_operation_mapping_key(operation_id: str) -> str:
-    """Get Redis key for operation_id to task_id mapping."""
-    return f"{TASK_OP_PREFIX}{operation_id}"
-
-
-async def create_task(
-    task_id: str,
-    session_id: str,
-    user_id: str | None,
-    tool_call_id: str,
-    tool_name: str,
-    operation_id: str,
-) -> ActiveTask:
-    """Create a new streaming task in memory and Redis.
-
-    Args:
-        task_id: Unique identifier for the task
-        session_id: Chat session ID
-        user_id: User ID (may be None for anonymous)
-        tool_call_id: Tool call ID from the LLM
-        tool_name: Name of the tool being executed
-        operation_id: Operation ID for webhook callbacks
-
-    Returns:
-        The created ActiveTask instance
-    """
-    task = ActiveTask(
-        task_id=task_id,
-        session_id=session_id,
-        user_id=user_id,
-        tool_call_id=tool_call_id,
-        tool_name=tool_name,
-        operation_id=operation_id,
-    )
-
-    # Store in memory registry
-    _active_tasks[task_id] = task
-
-    # Store metadata in Redis for durability
-    redis = await get_redis_async()
-    meta_key = _get_task_meta_key(task_id)
-    op_key = _get_operation_mapping_key(operation_id)
-
-    await redis.hset(  # type: ignore[misc]
-        meta_key,
-        mapping={
-            "task_id": task_id,
-            "session_id": session_id,
-            "user_id": user_id or "",
-            "tool_call_id": tool_call_id,
-            "tool_name": tool_name,
-            "operation_id": operation_id,
-            "status": task.status,
-            "created_at": task.created_at.isoformat(),
-        },
-    )
-    await redis.expire(meta_key, config.stream_ttl)
-
-    # Create operation_id -> task_id mapping for webhook lookups
-    await redis.set(op_key, task_id, ex=config.stream_ttl)
-
-    logger.info(
-        f"Created streaming task {task_id} for operation {operation_id} "
-        f"in session {session_id}"
-    )
-
-    return task
-
-
-async def publish_chunk(
-    task_id: str,
-    chunk: StreamBaseResponse,
-) -> int:
-    """Publish a chunk to the task's stream.
-
-    Writes to both Redis Stream (for replay) and in-memory queue (for live subscribers).
-
-    Args:
-        task_id: Task ID to publish to
-        chunk: The stream response chunk to publish
-
-    Returns:
-        The message index in the Redis Stream
-    """
-    redis = await get_redis_async()
-    stream_key = _get_task_stream_key(task_id)
-
-    # Serialize chunk to JSON
-    chunk_json = chunk.model_dump_json()
-
-    # Add to Redis Stream with auto-generated ID
-    # The ID format is "timestamp-sequence" which gives us ordering
-    message_id = await redis.xadd(
-        stream_key,
-        {"data": chunk_json},
-        maxlen=config.stream_max_length,
-    )
-
-    # Publish to in-memory queue if task exists
-    task = _active_tasks.get(task_id)
-    if task:
-        try:
-            task.queue.put_nowait(chunk)
-        except asyncio.QueueFull:
-            logger.warning(f"Queue full for task {task_id}, dropping chunk")
-
-    logger.debug(f"Published chunk to task {task_id}, message_id={message_id}")
-
-    # Parse the message_id to extract the index
-    # Redis Stream IDs are "timestamp-sequence", we return the raw ID
-    return int(message_id.split("-")[1]) if "-" in message_id else 0
-
-
-async def subscribe_to_task(
-    task_id: str,
-    user_id: str | None,
-    last_idx: int = 0,
-) -> asyncio.Queue[StreamBaseResponse] | None:
-    """Subscribe to a task's stream with replay of missed messages.
-
-    Args:
-        task_id: Task ID to subscribe to
-        user_id: User ID for ownership validation
-        last_idx: Last message index received (0 for full replay)
-
-    Returns:
-        An asyncio Queue that will receive stream chunks, or None if task not found
-        or user doesn't have access
-    """
-    # Check in-memory first
-    task = _active_tasks.get(task_id)
-
-    if task:
-        # Validate ownership
-        if user_id and task.user_id and task.user_id != user_id:
-            logger.warning(
-                f"User {user_id} attempted to subscribe to task {task_id} "
-                f"owned by {task.user_id}"
-            )
-            return None
-
-        # Create a new queue for this subscriber
-        subscriber_queue: asyncio.Queue[StreamBaseResponse] = asyncio.Queue()
-
-        # Replay from Redis Stream
-        redis = await get_redis_async()
-        stream_key = _get_task_stream_key(task_id)
-
-        # Read all messages from stream
-        # Use "0-0" to get all messages or construct ID from last_idx
-        start_id = "0-0" if last_idx == 0 else f"0-{last_idx}"
-        messages = await redis.xread({stream_key: start_id}, block=0, count=1000)
-
-        if messages:
-            # messages format: [[stream_name, [(id, {data: json}), ...]]]
-            for _stream_name, stream_messages in messages:
-                for _msg_id, msg_data in stream_messages:
-                    if b"data" in msg_data:
-                        try:
-                            chunk_data = orjson.loads(msg_data[b"data"])
-                            # Reconstruct the appropriate response type
-                            chunk = _reconstruct_chunk(chunk_data)
-                            if chunk:
-                                await subscriber_queue.put(chunk)
-                        except Exception as e:
-                            logger.warning(f"Failed to replay message: {e}")
-
-        # If task is still running, set up live subscription
-        if task.status == "running":
-            # Forward messages from task queue to subscriber queue
-            async def _forward_messages():
-                try:
-                    while True:
-                        chunk = await task.queue.get()
-                        await subscriber_queue.put(chunk)
-                        if isinstance(chunk, StreamFinish):
-                            break
-                except asyncio.CancelledError:
-                    pass
-
-            asyncio.create_task(_forward_messages())
-        else:
-            # Task is done, add finish marker
-            await subscriber_queue.put(StreamFinish())
-
-        return subscriber_queue
-
-    # Try to load from Redis if not in memory
-    redis = await get_redis_async()
-    meta_key = _get_task_meta_key(task_id)
-    meta: dict[Any, Any] = await redis.hgetall(meta_key)  # type: ignore[misc]
-
-    if not meta:
-        logger.warning(f"Task {task_id} not found in memory or Redis")
-        return None
-
-    # Validate ownership
-    task_user_id = meta.get(b"user_id", b"").decode() or None
-    if user_id and task_user_id and task_user_id != user_id:
-        logger.warning(
-            f"User {user_id} attempted to subscribe to task {task_id} "
-            f"owned by {task_user_id}"
-        )
-        return None
-
-    # Replay from Redis Stream only (task is not in memory, so it's completed/crashed)
-    subscriber_queue = asyncio.Queue()
-    stream_key = _get_task_stream_key(task_id)
-
-    start_id = "0-0" if last_idx == 0 else f"0-{last_idx}"
-    messages = await redis.xread({stream_key: start_id}, block=0, count=1000)
-
-    if messages:
-        for _stream_name, stream_messages in messages:
-            for _msg_id, msg_data in stream_messages:
-                if b"data" in msg_data:
-                    try:
-                        chunk_data = orjson.loads(msg_data[b"data"])
-                        chunk = _reconstruct_chunk(chunk_data)
-                        if chunk:
-                            await subscriber_queue.put(chunk)
-                    except Exception as e:
-                        logger.warning(f"Failed to replay message: {e}")
-
-    # Add finish marker since task is not active
-    await subscriber_queue.put(StreamFinish())
-
-    return subscriber_queue
-
-
-async def mark_task_completed(
-    task_id: str,
-    status: Literal["completed", "failed"] = "completed",
-) -> None:
-    """Mark a task as completed and publish final event.
-
-    Args:
-        task_id: Task ID to mark as completed
-        status: Final status ("completed" or "failed")
-    """
-    task = _active_tasks.get(task_id)
-
-    if task:
-        task.status = status
-        # Publish finish event to all subscribers
-        await publish_chunk(task_id, StreamFinish())
-
-        # Remove from active tasks after a short delay to allow subscribers to finish
-        async def _cleanup():
-            await asyncio.sleep(5)
-            _active_tasks.pop(task_id, None)
-            logger.info(f"Cleaned up task {task_id} from memory")
-
-        asyncio.create_task(_cleanup())
-
-    # Update Redis metadata
-    redis = await get_redis_async()
-    meta_key = _get_task_meta_key(task_id)
-    await redis.hset(meta_key, "status", status)  # type: ignore[misc]
-
-    logger.info(f"Marked task {task_id} as {status}")
-
-
-async def find_task_by_operation_id(operation_id: str) -> ActiveTask | None:
-    """Find a task by its operation ID.
-
-    Used by webhook callbacks to locate the task to update.
-
-    Args:
-        operation_id: Operation ID to search for
-
-    Returns:
-        ActiveTask if found, None otherwise
-    """
-    # Check in-memory first
-    for task in _active_tasks.values():
-        if task.operation_id == operation_id:
-            return task
-
-    # Try Redis lookup
-    redis = await get_redis_async()
-    op_key = _get_operation_mapping_key(operation_id)
-    task_id = await redis.get(op_key)
-
-    if task_id:
-        task_id_str = task_id.decode() if isinstance(task_id, bytes) else task_id
-        # Check if task is in memory
-        if task_id_str in _active_tasks:
-            return _active_tasks[task_id_str]
-
-        # Load metadata from Redis
-        meta_key = _get_task_meta_key(task_id_str)
-        meta: dict[Any, Any] = await redis.hgetall(meta_key)  # type: ignore[misc]
-
-        if meta:
-            # Reconstruct task object (not fully active, but has metadata)
-            return ActiveTask(
-                task_id=meta.get(b"task_id", b"").decode(),
-                session_id=meta.get(b"session_id", b"").decode(),
-                user_id=meta.get(b"user_id", b"").decode() or None,
-                tool_call_id=meta.get(b"tool_call_id", b"").decode(),
-                tool_name=meta.get(b"tool_name", b"").decode(),
-                operation_id=operation_id,
-                status=meta.get(b"status", b"running").decode(),  # type: ignore
-            )
-
-    return None
-
-
-async def get_task(task_id: str) -> ActiveTask | None:
-    """Get a task by its ID.
-
-    Args:
-        task_id: Task ID to look up
-
-    Returns:
-        ActiveTask if found, None otherwise
-    """
-    # Check in-memory first
-    if task_id in _active_tasks:
-        return _active_tasks[task_id]
-
-    # Try Redis lookup
-    redis = await get_redis_async()
-    meta_key = _get_task_meta_key(task_id)
-    meta: dict[Any, Any] = await redis.hgetall(meta_key)  # type: ignore[misc]
-
-    if meta:
-        return ActiveTask(
-            task_id=meta.get(b"task_id", b"").decode(),
-            session_id=meta.get(b"session_id", b"").decode(),
-            user_id=meta.get(b"user_id", b"").decode() or None,
-            tool_call_id=meta.get(b"tool_call_id", b"").decode(),
-            tool_name=meta.get(b"tool_name", b"").decode(),
-            operation_id=meta.get(b"operation_id", b"").decode(),
-            status=meta.get(b"status", b"running").decode(),  # type: ignore[arg-type]
-        )
-
-    return None
-
-
-def _reconstruct_chunk(chunk_data: dict) -> StreamBaseResponse | None:
-    """Reconstruct a StreamBaseResponse from JSON data.
-
-    Args:
-        chunk_data: Parsed JSON data from Redis
-
-    Returns:
-        Reconstructed response object, or None if unknown type
-    """
-    from .response_model import (
-        ResponseType,
-        StreamError,
-        StreamFinish,
-        StreamHeartbeat,
-        StreamStart,
-        StreamTextDelta,
-        StreamTextEnd,
-        StreamTextStart,
-        StreamToolInputAvailable,
-        StreamToolInputStart,
-        StreamToolOutputAvailable,
-        StreamUsage,
-    )
-
-    chunk_type = chunk_data.get("type")
-
-    try:
-        if chunk_type == ResponseType.START.value:
-            return StreamStart(**chunk_data)
-        elif chunk_type == ResponseType.FINISH.value:
-            return StreamFinish(**chunk_data)
-        elif chunk_type == ResponseType.TEXT_START.value:
-            return StreamTextStart(**chunk_data)
-        elif chunk_type == ResponseType.TEXT_DELTA.value:
-            return StreamTextDelta(**chunk_data)
-        elif chunk_type == ResponseType.TEXT_END.value:
-            return StreamTextEnd(**chunk_data)
-        elif chunk_type == ResponseType.TOOL_INPUT_START.value:
-            return StreamToolInputStart(**chunk_data)
-        elif chunk_type == ResponseType.TOOL_INPUT_AVAILABLE.value:
-            return StreamToolInputAvailable(**chunk_data)
-        elif chunk_type == ResponseType.TOOL_OUTPUT_AVAILABLE.value:
-            return StreamToolOutputAvailable(**chunk_data)
-        elif chunk_type == ResponseType.ERROR.value:
-            return StreamError(**chunk_data)
-        elif chunk_type == ResponseType.USAGE.value:
-            return StreamUsage(**chunk_data)
-        elif chunk_type == ResponseType.HEARTBEAT.value:
-            return StreamHeartbeat(**chunk_data)
-        else:
-            logger.warning(f"Unknown chunk type: {chunk_type}")
-            return None
-    except Exception as e:
-        logger.warning(f"Failed to reconstruct chunk of type {chunk_type}: {e}")
-        return None
-
-
-async def set_task_asyncio_task(task_id: str, asyncio_task: asyncio.Task) -> None:
-    """Associate an asyncio.Task with an ActiveTask.
-
-    Args:
-        task_id: Task ID
-        asyncio_task: The asyncio Task to associate
-    """
-    task = _active_tasks.get(task_id)
-    if task:
-        task.asyncio_task = asyncio_task

autogpt_platform/backend/backend/api/features/chat/tools/IDEAS.md

@@ -1,79 +0,0 @@
-# CoPilot Tools - Future Ideas
-
-## Multimodal Image Support for CoPilot
-
-**Problem:** CoPilot uses a vision-capable model but can't "see" workspace images. When a block generates an image and returns `workspace://abc123`, CoPilot can't evaluate it (e.g., checking blog thumbnail quality).
-
-**Backend Solution:**
-When preparing messages for the LLM, detect `workspace://` image references and convert them to proper image content blocks:
-
-```python
-# Before sending to LLM, scan for workspace image references
-# and inject them as image content parts
-
-# Example message transformation:
-# FROM: {"role": "assistant", "content": "Generated image: workspace://abc123"}
-# TO:   {"role": "assistant", "content": [
-#         {"type": "text", "text": "Generated image: workspace://abc123"},
-#         {"type": "image_url", "image_url": {"url": "data:image/png;base64,..."}}
-#       ]}
-```
-
-**Where to implement:**
-- In the chat stream handler before calling the LLM
-- Or in a message preprocessing step
-- Need to fetch image from workspace, convert to base64, add as image content
-
-**Considerations:**
-- Only do this for image MIME types (image/png, image/jpeg, etc.)
-- May want a size limit (don't pass 10MB images)
-- Track which images were "shown" to the AI for frontend indicator
-- Cost implications - vision API calls are more expensive
-
-**Frontend Solution:**
-Show visual indicator on workspace files in chat:
-- If AI saw the image: normal display
-- If AI didn't see it: overlay icon saying "AI can't see this image"
-
-Requires response metadata indicating which `workspace://` refs were passed to the model.
-
----
-
-## Output Post-Processing Layer for run_block
-
-**Problem:** Many blocks produce large outputs that:
-- Consume massive context (100KB base64 image = ~133KB tokens)
-- Can't fit in conversation
-- Break things and cause high LLM costs
-
-**Proposed Solution:** Instead of modifying individual blocks or `store_media_file()`, implement a centralized output processor in `run_block.py` that handles outputs before they're returned to CoPilot.
-
-**Benefits:**
-1. **Centralized** - one place to handle all output processing
-2. **Future-proof** - new blocks automatically get output processing
-3. **Keeps blocks pure** - they don't need to know about context constraints
-4. **Handles all large outputs** - not just images
-
-**Processing Rules:**
-- Detect base64 data URIs → save to workspace, return `workspace://` reference
-- Truncate very long strings (>N chars) with truncation note
-- Summarize large arrays/lists (e.g., "Array with 1000 items, first 5: [...]")
-- Handle nested large outputs in dicts recursively
-- Cap total output size
-
-**Implementation Location:** `run_block.py` after block execution, before returning `BlockOutputResponse`
-
-**Example:**
-```python
-def _process_outputs_for_context(
-    outputs: dict[str, list[Any]],
-    workspace_manager: WorkspaceManager,
-    max_string_length: int = 10000,
-    max_array_preview: int = 5,
-) -> dict[str, list[Any]]:
-    """Process block outputs to prevent context bloat."""
-    processed = {}
-    for name, values in outputs.items():
-        processed[name] = [_process_value(v, workspace_manager) for v in values]
-    return processed
-```

autogpt_platform/backend/backend/api/features/chat/tools/__init__.py

@@ -1,10 +1,8 @@
-import logging
 from typing import TYPE_CHECKING, Any
 
 from openai.types.chat import ChatCompletionToolParam
 
 from backend.api.features.chat.model import ChatSession
-from backend.api.features.chat.tracking import track_tool_called
 
 from .add_understanding import AddUnderstandingTool
 from .agent_output import AgentOutputTool
@@ -18,18 +16,10 @@ from .get_doc_page import GetDocPageTool
 from .run_agent import RunAgentTool
 from .run_block import RunBlockTool
 from .search_docs import SearchDocsTool
-from .workspace_files import (
-    DeleteWorkspaceFileTool,
-    ListWorkspaceFilesTool,
-    ReadWorkspaceFileTool,
-    WriteWorkspaceFileTool,
-)
 
 if TYPE_CHECKING:
     from backend.api.features.chat.response_model import StreamToolOutputAvailable
 
-logger = logging.getLogger(__name__)
-
 # Single source of truth for all tools
 TOOL_REGISTRY: dict[str, BaseTool] = {
     "add_understanding": AddUnderstandingTool(),
@@ -43,11 +33,6 @@ TOOL_REGISTRY: dict[str, BaseTool] = {
     "view_agent_output": AgentOutputTool(),
     "search_docs": SearchDocsTool(),
     "get_doc_page": GetDocPageTool(),
-    # Workspace tools for CoPilot file operations
-    "list_workspace_files": ListWorkspaceFilesTool(),
-    "read_workspace_file": ReadWorkspaceFileTool(),
-    "write_workspace_file": WriteWorkspaceFileTool(),
-    "delete_workspace_file": DeleteWorkspaceFileTool(),
 }
 
 # Export individual tool instances for backwards compatibility
@@ -60,11 +45,6 @@ tools: list[ChatCompletionToolParam] = [
 ]
 
 
-def get_tool(tool_name: str) -> BaseTool | None:
-    """Get a tool instance by name."""
-    return TOOL_REGISTRY.get(tool_name)
-
-
 async def execute_tool(
     tool_name: str,
     parameters: dict[str, Any],
@@ -73,20 +53,7 @@ async def execute_tool(
     tool_call_id: str,
 ) -> "StreamToolOutputAvailable":
     """Execute a tool by name."""
-    tool = get_tool(tool_name)
+    tool = TOOL_REGISTRY.get(tool_name)
     if not tool:
         raise ValueError(f"Tool {tool_name} not found")
-
-    # Track tool call in PostHog
-    logger.info(
-        f"Tracking tool call: tool={tool_name}, user={user_id}, "
-        f"session={session.session_id}, call_id={tool_call_id}"
-    )
-    track_tool_called(
-        user_id=user_id,
-        session_id=session.session_id,
-        tool_name=tool_name,
-        tool_call_id=tool_call_id,
-    )
-
     return await tool.execute(user_id, session, tool_call_id, **parameters)

autogpt_platform/backend/backend/api/features/chat/tools/add_understanding.py

@@ -3,6 +3,8 @@
 import logging
 from typing import Any
 
+from langfuse import observe
+
 from backend.api.features.chat.model import ChatSession
 from backend.data.understanding import (
     BusinessUnderstandingInput,
@@ -59,6 +61,7 @@ and automations for the user's specific needs."""
         """Requires authentication to store user-specific data."""
         return True
 
+    @observe(as_type="tool", name="add_understanding")
     async def _execute(
         self,
         user_id: str | None,

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/__init__.py

@@ -1,28 +1,29 @@
 """Agent generator package - Creates agents from natural language."""
 
 from .core import (
-    AgentGeneratorNotConfiguredError,
+    apply_agent_patch,
     decompose_goal,
     generate_agent,
     generate_agent_patch,
     get_agent_as_json,
-    json_to_graph,
     save_agent_to_library,
 )
-from .service import health_check as check_external_service_health
-from .service import is_external_service_configured
+from .fixer import apply_all_fixes
+from .utils import get_blocks_info
+from .validator import validate_agent
 
 __all__ = [
     # Core functions
     "decompose_goal",
     "generate_agent",
     "generate_agent_patch",
+    "apply_agent_patch",
     "save_agent_to_library",
     "get_agent_as_json",
-    "json_to_graph",
-    # Exceptions
-    "AgentGeneratorNotConfiguredError",
-    # Service
-    "is_external_service_configured",
-    "check_external_service_health",
+    # Fixer
+    "apply_all_fixes",
+    # Validator
+    "validate_agent",
+    # Utils
+    "get_blocks_info",
 ]

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/client.py

@@ -0,0 +1,25 @@
+"""OpenRouter client configuration for agent generation."""
+
+import os
+
+from openai import AsyncOpenAI
+
+# Configuration - use OPEN_ROUTER_API_KEY for consistency with chat/config.py
+OPENROUTER_API_KEY = os.getenv("OPEN_ROUTER_API_KEY")
+AGENT_GENERATOR_MODEL = os.getenv("AGENT_GENERATOR_MODEL", "anthropic/claude-opus-4.5")
+
+# OpenRouter client (OpenAI-compatible API)
+_client: AsyncOpenAI | None = None
+
+
+def get_client() -> AsyncOpenAI:
+    """Get or create the OpenRouter client."""
+    global _client
+    if _client is None:
+        if not OPENROUTER_API_KEY:
+            raise ValueError("OPENROUTER_API_KEY environment variable is required")
+        _client = AsyncOpenAI(
+            base_url="https://openrouter.ai/api/v1",
+            api_key=OPENROUTER_API_KEY,
+        )
+    return _client

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/core.py

@@ -1,5 +1,7 @@
 """Core agent generation functions."""
 
+import copy
+import json
 import logging
 import uuid
 from typing import Any
@@ -7,35 +9,13 @@ from typing import Any
 from backend.api.features.library import db as library_db
 from backend.data.graph import Graph, Link, Node, create_graph
 
-from .service import (
-    decompose_goal_external,
-    generate_agent_external,
-    generate_agent_patch_external,
-    is_external_service_configured,
-)
+from .client import AGENT_GENERATOR_MODEL, get_client
+from .prompts import DECOMPOSITION_PROMPT, GENERATION_PROMPT, PATCH_PROMPT
+from .utils import get_block_summaries, parse_json_from_llm
 
 logger = logging.getLogger(__name__)
 
 
-class AgentGeneratorNotConfiguredError(Exception):
-    """Raised when the external Agent Generator service is not configured."""
-
-    pass
-
-
-def _check_service_configured() -> None:
-    """Check if the external Agent Generator service is configured.
-
-    Raises:
-        AgentGeneratorNotConfiguredError: If the service is not configured.
-    """
-    if not is_external_service_configured():
-        raise AgentGeneratorNotConfiguredError(
-            "Agent Generator service is not configured. "
-            "Set AGENTGENERATOR_HOST environment variable to enable agent generation."
-        )
-
-
 async def decompose_goal(description: str, context: str = "") -> dict[str, Any] | None:
     """Break down a goal into steps or return clarifying questions.
 
@@ -48,13 +28,40 @@ async def decompose_goal(description: str, context: str = "") -> dict[str, Any]
         - {"type": "clarifying_questions", "questions": [...]}
         - {"type": "instructions", "steps": [...]}
         Or None on error
-
-    Raises:
-        AgentGeneratorNotConfiguredError: If the external service is not configured.
     """
-    _check_service_configured()
-    logger.info("Calling external Agent Generator service for decompose_goal")
-    return await decompose_goal_external(description, context)
+    client = get_client()
+    prompt = DECOMPOSITION_PROMPT.format(block_summaries=get_block_summaries())
+
+    full_description = description
+    if context:
+        full_description = f"{description}\n\nAdditional context:\n{context}"
+
+    try:
+        response = await client.chat.completions.create(
+            model=AGENT_GENERATOR_MODEL,
+            messages=[
+                {"role": "system", "content": prompt},
+                {"role": "user", "content": full_description},
+            ],
+            temperature=0,
+        )
+
+        content = response.choices[0].message.content
+        if content is None:
+            logger.error("LLM returned empty content for decomposition")
+            return None
+
+        result = parse_json_from_llm(content)
+
+        if result is None:
+            logger.error(f"Failed to parse decomposition response: {content[:200]}")
+            return None
+
+        return result
+
+    except Exception as e:
+        logger.error(f"Error decomposing goal: {e}")
+        return None
 
 
 async def generate_agent(instructions: dict[str, Any]) -> dict[str, Any] | None:
@@ -65,14 +72,31 @@ async def generate_agent(instructions: dict[str, Any]) -> dict[str, Any] | None:
 
     Returns:
         Agent JSON dict or None on error
-
-    Raises:
-        AgentGeneratorNotConfiguredError: If the external service is not configured.
     """
-    _check_service_configured()
-    logger.info("Calling external Agent Generator service for generate_agent")
-    result = await generate_agent_external(instructions)
-    if result:
+    client = get_client()
+    prompt = GENERATION_PROMPT.format(block_summaries=get_block_summaries())
+
+    try:
+        response = await client.chat.completions.create(
+            model=AGENT_GENERATOR_MODEL,
+            messages=[
+                {"role": "system", "content": prompt},
+                {"role": "user", "content": json.dumps(instructions, indent=2)},
+            ],
+            temperature=0,
+        )
+
+        content = response.choices[0].message.content
+        if content is None:
+            logger.error("LLM returned empty content for agent generation")
+            return None
+
+        result = parse_json_from_llm(content)
+
+        if result is None:
+            logger.error(f"Failed to parse agent JSON: {content[:200]}")
+            return None
+
         # Ensure required fields
         if "id" not in result:
             result["id"] = str(uuid.uuid4())
@@ -80,7 +104,12 @@ async def generate_agent(instructions: dict[str, Any]) -> dict[str, Any] | None:
             result["version"] = 1
         if "is_active" not in result:
             result["is_active"] = True
-    return result
+
+        return result
+
+    except Exception as e:
+        logger.error(f"Error generating agent: {e}")
+        return None
 
 
 def json_to_graph(agent_json: dict[str, Any]) -> Graph:
@@ -189,7 +218,6 @@ async def save_agent_to_library(
     library_agents = await library_db.create_library_agent(
         graph=created_graph,
         user_id=user_id,
-        sensitive_action_safe_mode=True,
         create_library_agents_for_sub_graphs=False,
     )
 
@@ -255,23 +283,108 @@ async def get_agent_as_json(
 async def generate_agent_patch(
     update_request: str, current_agent: dict[str, Any]
 ) -> dict[str, Any] | None:
-    """Update an existing agent using natural language.
-
-    The external Agent Generator service handles:
-    - Generating the patch
-    - Applying the patch
-    - Fixing and validating the result
+    """Generate a patch to update an existing agent.
 
     Args:
         update_request: Natural language description of changes
         current_agent: Current agent JSON
 
     Returns:
-        Updated agent JSON, clarifying questions dict, or None on error
-
-    Raises:
-        AgentGeneratorNotConfiguredError: If the external service is not configured.
+        Patch dict or clarifying questions, or None on error
     """
-    _check_service_configured()
-    logger.info("Calling external Agent Generator service for generate_agent_patch")
-    return await generate_agent_patch_external(update_request, current_agent)
+    client = get_client()
+    prompt = PATCH_PROMPT.format(
+        current_agent=json.dumps(current_agent, indent=2),
+        block_summaries=get_block_summaries(),
+    )
+
+    try:
+        response = await client.chat.completions.create(
+            model=AGENT_GENERATOR_MODEL,
+            messages=[
+                {"role": "system", "content": prompt},
+                {"role": "user", "content": update_request},
+            ],
+            temperature=0,
+        )
+
+        content = response.choices[0].message.content
+        if content is None:
+            logger.error("LLM returned empty content for patch generation")
+            return None
+
+        return parse_json_from_llm(content)
+
+    except Exception as e:
+        logger.error(f"Error generating patch: {e}")
+        return None
+
+
+def apply_agent_patch(
+    current_agent: dict[str, Any], patch: dict[str, Any]
+) -> dict[str, Any]:
+    """Apply a patch to an existing agent.
+
+    Args:
+        current_agent: Current agent JSON
+        patch: Patch dict with operations
+
+    Returns:
+        Updated agent JSON
+    """
+    agent = copy.deepcopy(current_agent)
+    patches = patch.get("patches", [])
+
+    for p in patches:
+        patch_type = p.get("type")
+
+        if patch_type == "modify":
+            node_id = p.get("node_id")
+            changes = p.get("changes", {})
+
+            for node in agent.get("nodes", []):
+                if node["id"] == node_id:
+                    _deep_update(node, changes)
+                    logger.debug(f"Modified node {node_id}")
+                    break
+
+        elif patch_type == "add":
+            new_nodes = p.get("new_nodes", [])
+            new_links = p.get("new_links", [])
+
+            agent["nodes"] = agent.get("nodes", []) + new_nodes
+            agent["links"] = agent.get("links", []) + new_links
+            logger.debug(f"Added {len(new_nodes)} nodes, {len(new_links)} links")
+
+        elif patch_type == "remove":
+            node_ids_to_remove = set(p.get("node_ids", []))
+            link_ids_to_remove = set(p.get("link_ids", []))
+
+            # Remove nodes
+            agent["nodes"] = [
+                n for n in agent.get("nodes", []) if n["id"] not in node_ids_to_remove
+            ]
+
+            # Remove links (both explicit and those referencing removed nodes)
+            agent["links"] = [
+                link
+                for link in agent.get("links", [])
+                if link["id"] not in link_ids_to_remove
+                and link["source_id"] not in node_ids_to_remove
+                and link["sink_id"] not in node_ids_to_remove
+            ]
+
+            logger.debug(
+                f"Removed {len(node_ids_to_remove)} nodes, {len(link_ids_to_remove)} links"
+            )
+
+    return agent
+
+
+def _deep_update(target: dict, source: dict) -> None:
+    """Recursively update a dict with another dict."""
+    for key, value in source.items():
+        if key in target and isinstance(target[key], dict) and isinstance(value, dict):
+            _deep_update(target[key], value)
+        else:
+            target[key] = value

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/fixer.py

@@ -0,0 +1,606 @@
+"""Agent fixer - Fixes common LLM generation errors."""
+
+import logging
+import re
+import uuid
+from typing import Any
+
+from .utils import (
+    ADDTODICTIONARY_BLOCK_ID,
+    ADDTOLIST_BLOCK_ID,
+    CODE_EXECUTION_BLOCK_ID,
+    CONDITION_BLOCK_ID,
+    CREATEDICT_BLOCK_ID,
+    CREATELIST_BLOCK_ID,
+    DATA_SAMPLING_BLOCK_ID,
+    DOUBLE_CURLY_BRACES_BLOCK_IDS,
+    GET_CURRENT_DATE_BLOCK_ID,
+    STORE_VALUE_BLOCK_ID,
+    UNIVERSAL_TYPE_CONVERTER_BLOCK_ID,
+    get_blocks_info,
+    is_valid_uuid,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def fix_agent_ids(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix invalid UUIDs in agent and link IDs."""
+    # Fix agent ID
+    if not is_valid_uuid(agent.get("id", "")):
+        agent["id"] = str(uuid.uuid4())
+        logger.debug(f"Fixed agent ID: {agent['id']}")
+
+    # Fix node IDs
+    id_mapping = {}  # Old ID -> New ID
+    for node in agent.get("nodes", []):
+        if not is_valid_uuid(node.get("id", "")):
+            old_id = node.get("id", "")
+            new_id = str(uuid.uuid4())
+            id_mapping[old_id] = new_id
+            node["id"] = new_id
+            logger.debug(f"Fixed node ID: {old_id} -> {new_id}")
+
+    # Fix link IDs and update references
+    for link in agent.get("links", []):
+        if not is_valid_uuid(link.get("id", "")):
+            link["id"] = str(uuid.uuid4())
+            logger.debug(f"Fixed link ID: {link['id']}")
+
+        # Update source/sink IDs if they were remapped
+        if link.get("source_id") in id_mapping:
+            link["source_id"] = id_mapping[link["source_id"]]
+        if link.get("sink_id") in id_mapping:
+            link["sink_id"] = id_mapping[link["sink_id"]]
+
+    return agent
+
+
+def fix_double_curly_braces(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix single curly braces to double in template blocks."""
+    for node in agent.get("nodes", []):
+        if node.get("block_id") not in DOUBLE_CURLY_BRACES_BLOCK_IDS:
+            continue
+
+        input_data = node.get("input_default", {})
+        for key in ("prompt", "format"):
+            if key in input_data and isinstance(input_data[key], str):
+                original = input_data[key]
+                # Fix simple variable references: {var} -> {{var}}
+                fixed = re.sub(
+                    r"(?<!\{)\{([a-zA-Z_][a-zA-Z0-9_]*)\}(?!\})",
+                    r"{{\1}}",
+                    original,
+                )
+                if fixed != original:
+                    input_data[key] = fixed
+                    logger.debug(f"Fixed curly braces in {key}")
+
+    return agent
+
+
+def fix_storevalue_before_condition(agent: dict[str, Any]) -> dict[str, Any]:
+    """Add StoreValueBlock before ConditionBlock if needed for value2."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+
+    # Find all ConditionBlock nodes
+    condition_node_ids = {
+        node["id"] for node in nodes if node.get("block_id") == CONDITION_BLOCK_ID
+    }
+
+    if not condition_node_ids:
+        return agent
+
+    new_nodes = []
+    new_links = []
+    processed_conditions = set()
+
+    for link in links:
+        sink_id = link.get("sink_id")
+        sink_name = link.get("sink_name")
+
+        # Check if this link goes to a ConditionBlock's value2
+        if sink_id in condition_node_ids and sink_name == "value2":
+            source_node = next(
+                (n for n in nodes if n["id"] == link.get("source_id")), None
+            )
+
+            # Skip if source is already a StoreValueBlock
+            if source_node and source_node.get("block_id") == STORE_VALUE_BLOCK_ID:
+                continue
+
+            # Skip if we already processed this condition
+            if sink_id in processed_conditions:
+                continue
+
+            processed_conditions.add(sink_id)
+
+            # Create StoreValueBlock
+            store_node_id = str(uuid.uuid4())
+            store_node = {
+                "id": store_node_id,
+                "block_id": STORE_VALUE_BLOCK_ID,
+                "input_default": {"data": None},
+                "metadata": {"position": {"x": 0, "y": -100}},
+            }
+            new_nodes.append(store_node)
+
+            # Create link: original source -> StoreValueBlock
+            new_links.append(
+                {
+                    "id": str(uuid.uuid4()),
+                    "source_id": link["source_id"],
+                    "source_name": link["source_name"],
+                    "sink_id": store_node_id,
+                    "sink_name": "input",
+                    "is_static": False,
+                }
+            )
+
+            # Update original link: StoreValueBlock -> ConditionBlock
+            link["source_id"] = store_node_id
+            link["source_name"] = "output"
+
+            logger.debug(f"Added StoreValueBlock before ConditionBlock {sink_id}")
+
+    if new_nodes:
+        agent["nodes"] = nodes + new_nodes
+
+    return agent
+
+
+def fix_addtolist_blocks(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix AddToList blocks by adding prerequisite empty AddToList block.
+
+    When an AddToList block is found:
+    1. Checks if there's a CreateListBlock before it
+    2. Removes CreateListBlock if linked directly to AddToList
+    3. Adds an empty AddToList block before the original
+    4. Ensures the original has a self-referencing link
+    """
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+    new_nodes = []
+    original_addtolist_ids = set()
+    nodes_to_remove = set()
+    links_to_remove = []
+
+    # First pass: identify CreateListBlock nodes to remove
+    for link in links:
+        source_node = next(
+            (n for n in nodes if n.get("id") == link.get("source_id")), None
+        )
+        sink_node = next((n for n in nodes if n.get("id") == link.get("sink_id")), None)
+
+        if (
+            source_node
+            and sink_node
+            and source_node.get("block_id") == CREATELIST_BLOCK_ID
+            and sink_node.get("block_id") == ADDTOLIST_BLOCK_ID
+        ):
+            nodes_to_remove.add(source_node.get("id"))
+            links_to_remove.append(link)
+            logger.debug(f"Removing CreateListBlock {source_node.get('id')}")
+
+    # Second pass: process AddToList blocks
+    filtered_nodes = []
+    for node in nodes:
+        if node.get("id") in nodes_to_remove:
+            continue
+
+        if node.get("block_id") == ADDTOLIST_BLOCK_ID:
+            original_addtolist_ids.add(node.get("id"))
+            node_id = node.get("id")
+            pos = node.get("metadata", {}).get("position", {"x": 0, "y": 0})
+
+            # Check if already has prerequisite
+            has_prereq = any(
+                link.get("sink_id") == node_id
+                and link.get("sink_name") == "list"
+                and link.get("source_name") == "updated_list"
+                for link in links
+            )
+
+            if not has_prereq:
+                # Remove links to "list" input (except self-reference)
+                for link in links:
+                    if (
+                        link.get("sink_id") == node_id
+                        and link.get("sink_name") == "list"
+                        and link.get("source_id") != node_id
+                        and link not in links_to_remove
+                    ):
+                        links_to_remove.append(link)
+
+                # Create prerequisite AddToList block
+                prereq_id = str(uuid.uuid4())
+                prereq_node = {
+                    "id": prereq_id,
+                    "block_id": ADDTOLIST_BLOCK_ID,
+                    "input_default": {"list": [], "entry": None, "entries": []},
+                    "metadata": {
+                        "position": {"x": pos.get("x", 0) - 800, "y": pos.get("y", 0)}
+                    },
+                }
+                new_nodes.append(prereq_node)
+
+                # Link prerequisite to original
+                links.append(
+                    {
+                        "id": str(uuid.uuid4()),
+                        "source_id": prereq_id,
+                        "source_name": "updated_list",
+                        "sink_id": node_id,
+                        "sink_name": "list",
+                        "is_static": False,
+                    }
+                )
+                logger.debug(f"Added prerequisite AddToList block for {node_id}")
+
+        filtered_nodes.append(node)
+
+    # Remove marked links
+    filtered_links = [link for link in links if link not in links_to_remove]
+
+    # Add self-referencing links for original AddToList blocks
+    for node in filtered_nodes + new_nodes:
+        if (
+            node.get("block_id") == ADDTOLIST_BLOCK_ID
+            and node.get("id") in original_addtolist_ids
+        ):
+            node_id = node.get("id")
+            has_self_ref = any(
+                link["source_id"] == node_id
+                and link["sink_id"] == node_id
+                and link["source_name"] == "updated_list"
+                and link["sink_name"] == "list"
+                for link in filtered_links
+            )
+            if not has_self_ref:
+                filtered_links.append(
+                    {
+                        "id": str(uuid.uuid4()),
+                        "source_id": node_id,
+                        "source_name": "updated_list",
+                        "sink_id": node_id,
+                        "sink_name": "list",
+                        "is_static": False,
+                    }
+                )
+                logger.debug(f"Added self-reference for AddToList {node_id}")
+
+    agent["nodes"] = filtered_nodes + new_nodes
+    agent["links"] = filtered_links
+    return agent
+
+
+def fix_addtodictionary_blocks(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix AddToDictionary blocks by removing empty CreateDictionary nodes."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+    nodes_to_remove = set()
+    links_to_remove = []
+
+    for link in links:
+        source_node = next(
+            (n for n in nodes if n.get("id") == link.get("source_id")), None
+        )
+        sink_node = next((n for n in nodes if n.get("id") == link.get("sink_id")), None)
+
+        if (
+            source_node
+            and sink_node
+            and source_node.get("block_id") == CREATEDICT_BLOCK_ID
+            and sink_node.get("block_id") == ADDTODICTIONARY_BLOCK_ID
+        ):
+            nodes_to_remove.add(source_node.get("id"))
+            links_to_remove.append(link)
+            logger.debug(f"Removing CreateDictionary {source_node.get('id')}")
+
+    agent["nodes"] = [n for n in nodes if n.get("id") not in nodes_to_remove]
+    agent["links"] = [link for link in links if link not in links_to_remove]
+    return agent
+
+
+def fix_code_execution_output(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix CodeExecutionBlock output: change 'response' to 'stdout_logs'."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+
+    for link in links:
+        source_node = next(
+            (n for n in nodes if n.get("id") == link.get("source_id")), None
+        )
+        if (
+            source_node
+            and source_node.get("block_id") == CODE_EXECUTION_BLOCK_ID
+            and link.get("source_name") == "response"
+        ):
+            link["source_name"] = "stdout_logs"
+            logger.debug("Fixed CodeExecutionBlock output: response -> stdout_logs")
+
+    return agent
+
+
+def fix_data_sampling_sample_size(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix DataSamplingBlock by setting sample_size to 1 as default."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+    links_to_remove = []
+
+    for node in nodes:
+        if node.get("block_id") == DATA_SAMPLING_BLOCK_ID:
+            node_id = node.get("id")
+            input_default = node.get("input_default", {})
+
+            # Remove links to sample_size
+            for link in links:
+                if (
+                    link.get("sink_id") == node_id
+                    and link.get("sink_name") == "sample_size"
+                ):
+                    links_to_remove.append(link)
+
+            # Set default
+            input_default["sample_size"] = 1
+            node["input_default"] = input_default
+            logger.debug(f"Fixed DataSamplingBlock {node_id} sample_size to 1")
+
+    if links_to_remove:
+        agent["links"] = [link for link in links if link not in links_to_remove]
+
+    return agent
+
+
+def fix_node_x_coordinates(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix node x-coordinates to ensure 800+ unit spacing between linked nodes."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+    node_lookup = {n.get("id"): n for n in nodes}
+
+    for link in links:
+        source_id = link.get("source_id")
+        sink_id = link.get("sink_id")
+
+        source_node = node_lookup.get(source_id)
+        sink_node = node_lookup.get(sink_id)
+
+        if not source_node or not sink_node:
+            continue
+
+        source_pos = source_node.get("metadata", {}).get("position", {})
+        sink_pos = sink_node.get("metadata", {}).get("position", {})
+
+        source_x = source_pos.get("x", 0)
+        sink_x = sink_pos.get("x", 0)
+
+        if abs(sink_x - source_x) < 800:
+            new_x = source_x + 800
+            if "metadata" not in sink_node:
+                sink_node["metadata"] = {}
+            if "position" not in sink_node["metadata"]:
+                sink_node["metadata"]["position"] = {}
+            sink_node["metadata"]["position"]["x"] = new_x
+            logger.debug(f"Fixed node {sink_id} x: {sink_x} -> {new_x}")
+
+    return agent
+
+
+def fix_getcurrentdate_offset(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix GetCurrentDateBlock offset to ensure it's positive."""
+    for node in agent.get("nodes", []):
+        if node.get("block_id") == GET_CURRENT_DATE_BLOCK_ID:
+            input_default = node.get("input_default", {})
+            if "offset" in input_default:
+                offset = input_default["offset"]
+                if isinstance(offset, (int, float)) and offset < 0:
+                    input_default["offset"] = abs(offset)
+                    logger.debug(f"Fixed offset: {offset} -> {abs(offset)}")
+
+    return agent
+
+
+def fix_ai_model_parameter(
+    agent: dict[str, Any],
+    blocks_info: list[dict[str, Any]],
+    default_model: str = "gpt-4o",
+) -> dict[str, Any]:
+    """Add default model parameter to AI blocks if missing."""
+    block_map = {b.get("id"): b for b in blocks_info}
+
+    for node in agent.get("nodes", []):
+        block_id = node.get("block_id")
+        block = block_map.get(block_id)
+
+        if not block:
+            continue
+
+        # Check if block has AI category
+        categories = block.get("categories", [])
+        is_ai_block = any(
+            cat.get("category") == "AI" for cat in categories if isinstance(cat, dict)
+        )
+
+        if is_ai_block:
+            input_default = node.get("input_default", {})
+            if "model" not in input_default:
+                input_default["model"] = default_model
+                node["input_default"] = input_default
+                logger.debug(
+                    f"Added model '{default_model}' to AI block {node.get('id')}"
+                )
+
+    return agent
+
+
+def fix_link_static_properties(
+    agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+) -> dict[str, Any]:
+    """Fix is_static property based on source block's staticOutput."""
+    block_map = {b.get("id"): b for b in blocks_info}
+    node_lookup = {n.get("id"): n for n in agent.get("nodes", [])}
+
+    for link in agent.get("links", []):
+        source_node = node_lookup.get(link.get("source_id"))
+        if not source_node:
+            continue
+
+        source_block = block_map.get(source_node.get("block_id"))
+        if not source_block:
+            continue
+
+        static_output = source_block.get("staticOutput", False)
+        if link.get("is_static") != static_output:
+            link["is_static"] = static_output
+            logger.debug(f"Fixed link {link.get('id')} is_static to {static_output}")
+
+    return agent
+
+
+def fix_data_type_mismatch(
+    agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+) -> dict[str, Any]:
+    """Fix data type mismatches by inserting UniversalTypeConverterBlock."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+    block_map = {b.get("id"): b for b in blocks_info}
+    node_lookup = {n.get("id"): n for n in nodes}
+
+    def get_property_type(schema: dict, name: str) -> str | None:
+        if "_#_" in name:
+            parent, child = name.split("_#_", 1)
+            parent_schema = schema.get(parent, {})
+            if "properties" in parent_schema:
+                return parent_schema["properties"].get(child, {}).get("type")
+            return None
+        return schema.get(name, {}).get("type")
+
+    def are_types_compatible(src: str, sink: str) -> bool:
+        if {src, sink} <= {"integer", "number"}:
+            return True
+        return src == sink
+
+    type_mapping = {
+        "string": "string",
+        "text": "string",
+        "integer": "number",
+        "number": "number",
+        "float": "number",
+        "boolean": "boolean",
+        "bool": "boolean",
+        "array": "list",
+        "list": "list",
+        "object": "dictionary",
+        "dict": "dictionary",
+        "dictionary": "dictionary",
+    }
+
+    new_links = []
+    nodes_to_add = []
+
+    for link in links:
+        source_node = node_lookup.get(link.get("source_id"))
+        sink_node = node_lookup.get(link.get("sink_id"))
+
+        if not source_node or not sink_node:
+            new_links.append(link)
+            continue
+
+        source_block = block_map.get(source_node.get("block_id"))
+        sink_block = block_map.get(sink_node.get("block_id"))
+
+        if not source_block or not sink_block:
+            new_links.append(link)
+            continue
+
+        source_outputs = source_block.get("outputSchema", {}).get("properties", {})
+        sink_inputs = sink_block.get("inputSchema", {}).get("properties", {})
+
+        source_type = get_property_type(source_outputs, link.get("source_name", ""))
+        sink_type = get_property_type(sink_inputs, link.get("sink_name", ""))
+
+        if (
+            source_type
+            and sink_type
+            and not are_types_compatible(source_type, sink_type)
+        ):
+            # Insert type converter
+            converter_id = str(uuid.uuid4())
+            target_type = type_mapping.get(sink_type, sink_type)
+
+            converter_node = {
+                "id": converter_id,
+                "block_id": UNIVERSAL_TYPE_CONVERTER_BLOCK_ID,
+                "input_default": {"type": target_type},
+                "metadata": {"position": {"x": 0, "y": 100}},
+            }
+            nodes_to_add.append(converter_node)
+
+            # source -> converter
+            new_links.append(
+                {
+                    "id": str(uuid.uuid4()),
+                    "source_id": link["source_id"],
+                    "source_name": link["source_name"],
+                    "sink_id": converter_id,
+                    "sink_name": "value",
+                    "is_static": False,
+                }
+            )
+
+            # converter -> sink
+            new_links.append(
+                {
+                    "id": str(uuid.uuid4()),
+                    "source_id": converter_id,
+                    "source_name": "value",
+                    "sink_id": link["sink_id"],
+                    "sink_name": link["sink_name"],
+                    "is_static": False,
+                }
+            )
+
+            logger.debug(f"Inserted type converter: {source_type} -> {target_type}")
+        else:
+            new_links.append(link)
+
+    if nodes_to_add:
+        agent["nodes"] = nodes + nodes_to_add
+        agent["links"] = new_links
+
+    return agent
+
+
+def apply_all_fixes(
+    agent: dict[str, Any], blocks_info: list[dict[str, Any]] | None = None
+) -> dict[str, Any]:
+    """Apply all fixes to an agent JSON.
+
+    Args:
+        agent: Agent JSON dict
+        blocks_info: Optional list of block info dicts for advanced fixes
+
+    Returns:
+        Fixed agent JSON
+    """
+    # Basic fixes (no block info needed)
+    agent = fix_agent_ids(agent)
+    agent = fix_double_curly_braces(agent)
+    agent = fix_storevalue_before_condition(agent)
+    agent = fix_addtolist_blocks(agent)
+    agent = fix_addtodictionary_blocks(agent)
+    agent = fix_code_execution_output(agent)
+    agent = fix_data_sampling_sample_size(agent)
+    agent = fix_node_x_coordinates(agent)
+    agent = fix_getcurrentdate_offset(agent)
+
+    # Advanced fixes (require block info)
+    if blocks_info is None:
+        blocks_info = get_blocks_info()
+
+    agent = fix_ai_model_parameter(agent, blocks_info)
+    agent = fix_link_static_properties(agent, blocks_info)
+    agent = fix_data_type_mismatch(agent, blocks_info)
+
+    return agent

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/prompts.py

@@ -0,0 +1,225 @@
+"""Prompt templates for agent generation."""
+
+DECOMPOSITION_PROMPT = """
+You are an expert AutoGPT Workflow Decomposer. Your task is to analyze a user's high-level goal and break it down into a clear, step-by-step plan using the available blocks.
+
+Each step should represent a distinct, automatable action suitable for execution by an AI automation system.
+
+---
+
+FIRST: Analyze the user's goal and determine:
+1) Design-time configuration (fixed settings that won't change per run)
+2) Runtime inputs (values the agent's end-user will provide each time it runs)
+
+For anything that can vary per run (email addresses, names, dates, search terms, etc.):
+- DO NOT ask for the actual value
+- Instead, define it as an Agent Input with a clear name, type, and description
+
+Only ask clarifying questions about design-time config that affects how you build the workflow:
+- Which external service to use (e.g., "Gmail vs Outlook", "Notion vs Google Docs")
+- Required formats or structures (e.g., "CSV, JSON, or PDF output?")
+- Business rules that must be hard-coded
+
+IMPORTANT CLARIFICATIONS POLICY:
+- Ask no more than five essential questions
+- Do not ask for concrete values that can be provided at runtime as Agent Inputs
+- Do not ask for API keys or credentials; the platform handles those directly
+- If there is enough information to infer reasonable defaults, prefer to propose defaults
+
+---
+
+GUIDELINES:
+1. List each step as a numbered item
+2. Describe the action clearly and specify inputs/outputs
+3. Ensure steps are in logical, sequential order
+4. Mention block names naturally (e.g., "Use GetWeatherByLocationBlock to...")
+5. Help the user reach their goal efficiently
+
+---
+
+RULES:
+1. OUTPUT FORMAT: Only output either clarifying questions OR step-by-step instructions, not both
+2. USE ONLY THE BLOCKS PROVIDED
+3. ALL required_input fields must be provided
+4. Data types of linked properties must match
+5. Write expert-level prompts for AI-related blocks
+
+---
+
+CRITICAL BLOCK RESTRICTIONS:
+1. AddToListBlock: Outputs updated list EVERY addition, not after all additions
+2. SendEmailBlock: Draft the email for user review; set SMTP config based on email type
+3. ConditionBlock: value2 is reference, value1 is contrast
+4. CodeExecutionBlock: DO NOT USE - use AI blocks instead
+5. ReadCsvBlock: Only use the 'rows' output, not 'row'
+
+---
+
+OUTPUT FORMAT:
+
+If more information is needed:
+```json
+{{
+  "type": "clarifying_questions",
+  "questions": [
+    {{
+      "question": "Which email provider should be used? (Gmail, Outlook, custom SMTP)",
+      "keyword": "email_provider",
+      "example": "Gmail"
+    }}
+  ]
+}}
+```
+
+If ready to proceed:
+```json
+{{
+  "type": "instructions",
+  "steps": [
+    {{
+      "step_number": 1,
+      "block_name": "AgentShortTextInputBlock",
+      "description": "Get the URL of the content to analyze.",
+      "inputs": [{{"name": "name", "value": "URL"}}],
+      "outputs": [{{"name": "result", "description": "The URL entered by user"}}]
+    }}
+  ]
+}}
+```
+
+---
+
+AVAILABLE BLOCKS:
+{block_summaries}
+"""
+
+GENERATION_PROMPT = """
+You are an expert AI workflow builder. Generate a valid agent JSON from the given instructions.
+
+---
+
+NODES:
+Each node must include:
+- `id`: Unique UUID v4 (e.g. `a8f5b1e2-c3d4-4e5f-8a9b-0c1d2e3f4a5b`)
+- `block_id`: The block identifier (must match an Allowed Block)
+- `input_default`: Dict of inputs (can be empty if no static inputs needed)
+- `metadata`: Must contain:
+  - `position`: {{"x": number, "y": number}} - adjacent nodes should differ by 800+ in X
+  - `customized_name`: Clear name describing this block's purpose in the workflow
+
+---
+
+LINKS:
+Each link connects a source node's output to a sink node's input:
+- `id`: MUST be UUID v4 (NOT "link-1", "link-2", etc.)
+- `source_id`: ID of the source node
+- `source_name`: Output field name from the source block
+- `sink_id`: ID of the sink node
+- `sink_name`: Input field name on the sink block
+- `is_static`: true only if source block has static_output: true
+
+CRITICAL: All IDs must be valid UUID v4 format!
+
+---
+
+AGENT (GRAPH):
+Wrap nodes and links in:
+- `id`: UUID of the agent
+- `name`: Short, generic name (avoid specific company names, URLs)
+- `description`: Short, generic description
+- `nodes`: List of all nodes
+- `links`: List of all links
+- `version`: 1
+- `is_active`: true
+
+---
+
+TIPS:
+- All required_input fields must be provided via input_default or a valid link
+- Ensure consistent source_id and sink_id references
+- Avoid dangling links
+- Input/output pins must match block schemas
+- Do not invent unknown block_ids
+
+---
+
+ALLOWED BLOCKS:
+{block_summaries}
+
+---
+
+Generate the complete agent JSON. Output ONLY valid JSON, no explanation.
+"""
+
+PATCH_PROMPT = """
+You are an expert at modifying AutoGPT agent workflows. Given the current agent and a modification request, generate a JSON patch to update the agent.
+
+CURRENT AGENT:
+{current_agent}
+
+AVAILABLE BLOCKS:
+{block_summaries}
+
+---
+
+PATCH FORMAT:
+Return a JSON object with the following structure:
+
+```json
+{{
+  "type": "patch",
+  "intent": "Brief description of what the patch does",
+  "patches": [
+    {{
+      "type": "modify",
+      "node_id": "uuid-of-node-to-modify",
+      "changes": {{
+        "input_default": {{"field": "new_value"}},
+        "metadata": {{"customized_name": "New Name"}}
+      }}
+    }},
+    {{
+      "type": "add",
+      "new_nodes": [
+        {{
+          "id": "new-uuid",
+          "block_id": "block-uuid",
+          "input_default": {{}},
+          "metadata": {{"position": {{"x": 0, "y": 0}}, "customized_name": "Name"}}
+        }}
+      ],
+      "new_links": [
+        {{
+          "id": "link-uuid",
+          "source_id": "source-node-id",
+          "source_name": "output_field",
+          "sink_id": "sink-node-id",
+          "sink_name": "input_field"
+        }}
+      ]
+    }},
+    {{
+      "type": "remove",
+      "node_ids": ["uuid-of-node-to-remove"],
+      "link_ids": ["uuid-of-link-to-remove"]
+    }}
+  ]
+}}
+```
+
+If you need more information, return:
+```json
+{{
+  "type": "clarifying_questions",
+  "questions": [
+    {{
+      "question": "What specific change do you want?",
+      "keyword": "change_type",
+      "example": "Add error handling"
+    }}
+  ]
+}}
+```
+
+Generate the minimal patch needed. Output ONLY valid JSON.
+"""

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

@@ -1,269 +0,0 @@
-"""External Agent Generator service client.
-
-This module provides a client for communicating with the external Agent Generator
-microservice. When AGENTGENERATOR_HOST is configured, the agent generation functions
-will delegate to the external service instead of using the built-in LLM-based implementation.
-"""
-
-import logging
-from typing import Any
-
-import httpx
-
-from backend.util.settings import Settings
-
-logger = logging.getLogger(__name__)
-
-_client: httpx.AsyncClient | None = None
-_settings: Settings | None = None
-
-
-def _get_settings() -> Settings:
-    """Get or create settings singleton."""
-    global _settings
-    if _settings is None:
-        _settings = Settings()
-    return _settings
-
-
-def is_external_service_configured() -> bool:
-    """Check if external Agent Generator service is configured."""
-    settings = _get_settings()
-    return bool(settings.config.agentgenerator_host)
-
-
-def _get_base_url() -> str:
-    """Get the base URL for the external service."""
-    settings = _get_settings()
-    host = settings.config.agentgenerator_host
-    port = settings.config.agentgenerator_port
-    return f"http://{host}:{port}"
-
-
-def _get_client() -> httpx.AsyncClient:
-    """Get or create the HTTP client for the external service."""
-    global _client
-    if _client is None:
-        settings = _get_settings()
-        _client = httpx.AsyncClient(
-            base_url=_get_base_url(),
-            timeout=httpx.Timeout(settings.config.agentgenerator_timeout),
-        )
-    return _client
-
-
-async def decompose_goal_external(
-    description: str, context: str = ""
-) -> dict[str, Any] | None:
-    """Call the external service to decompose a goal.
-
-    Args:
-        description: Natural language goal description
-        context: Additional context (e.g., answers to previous questions)
-
-    Returns:
-        Dict with either:
-        - {"type": "clarifying_questions", "questions": [...]}
-        - {"type": "instructions", "steps": [...]}
-        - {"type": "unachievable_goal", ...}
-        - {"type": "vague_goal", ...}
-        Or None on error
-    """
-    client = _get_client()
-
-    # Build the request payload
-    payload: dict[str, Any] = {"description": description}
-    if context:
-        # The external service uses user_instruction for additional context
-        payload["user_instruction"] = context
-
-    try:
-        response = await client.post("/api/decompose-description", json=payload)
-        response.raise_for_status()
-        data = response.json()
-
-        if not data.get("success"):
-            logger.error(f"External service returned error: {data.get('error')}")
-            return None
-
-        # Map the response to the expected format
-        response_type = data.get("type")
-        if response_type == "instructions":
-            return {"type": "instructions", "steps": data.get("steps", [])}
-        elif response_type == "clarifying_questions":
-            return {
-                "type": "clarifying_questions",
-                "questions": data.get("questions", []),
-            }
-        elif response_type == "unachievable_goal":
-            return {
-                "type": "unachievable_goal",
-                "reason": data.get("reason"),
-                "suggested_goal": data.get("suggested_goal"),
-            }
-        elif response_type == "vague_goal":
-            return {
-                "type": "vague_goal",
-                "suggested_goal": data.get("suggested_goal"),
-            }
-        else:
-            logger.error(
-                f"Unknown response type from external service: {response_type}"
-            )
-            return None
-
-    except httpx.HTTPStatusError as e:
-        logger.error(f"HTTP error calling external agent generator: {e}")
-        return None
-    except httpx.RequestError as e:
-        logger.error(f"Request error calling external agent generator: {e}")
-        return None
-    except Exception as e:
-        logger.error(f"Unexpected error calling external agent generator: {e}")
-        return None
-
-
-async def generate_agent_external(
-    instructions: dict[str, Any]
-) -> dict[str, Any] | None:
-    """Call the external service to generate an agent from instructions.
-
-    Args:
-        instructions: Structured instructions from decompose_goal
-
-    Returns:
-        Agent JSON dict or None on error
-    """
-    client = _get_client()
-
-    try:
-        response = await client.post(
-            "/api/generate-agent", json={"instructions": instructions}
-        )
-        response.raise_for_status()
-        data = response.json()
-
-        if not data.get("success"):
-            logger.error(f"External service returned error: {data.get('error')}")
-            return None
-
-        return data.get("agent_json")
-
-    except httpx.HTTPStatusError as e:
-        logger.error(f"HTTP error calling external agent generator: {e}")
-        return None
-    except httpx.RequestError as e:
-        logger.error(f"Request error calling external agent generator: {e}")
-        return None
-    except Exception as e:
-        logger.error(f"Unexpected error calling external agent generator: {e}")
-        return None
-
-
-async def generate_agent_patch_external(
-    update_request: str, current_agent: dict[str, Any]
-) -> dict[str, Any] | None:
-    """Call the external service to generate a patch for an existing agent.
-
-    Args:
-        update_request: Natural language description of changes
-        current_agent: Current agent JSON
-
-    Returns:
-        Updated agent JSON, clarifying questions dict, or None on error
-    """
-    client = _get_client()
-
-    try:
-        response = await client.post(
-            "/api/update-agent",
-            json={
-                "update_request": update_request,
-                "current_agent_json": current_agent,
-            },
-        )
-        response.raise_for_status()
-        data = response.json()
-
-        if not data.get("success"):
-            logger.error(f"External service returned error: {data.get('error')}")
-            return None
-
-        # Check if it's clarifying questions
-        if data.get("type") == "clarifying_questions":
-            return {
-                "type": "clarifying_questions",
-                "questions": data.get("questions", []),
-            }
-
-        # Otherwise return the updated agent JSON
-        return data.get("agent_json")
-
-    except httpx.HTTPStatusError as e:
-        logger.error(f"HTTP error calling external agent generator: {e}")
-        return None
-    except httpx.RequestError as e:
-        logger.error(f"Request error calling external agent generator: {e}")
-        return None
-    except Exception as e:
-        logger.error(f"Unexpected error calling external agent generator: {e}")
-        return None
-
-
-async def get_blocks_external() -> list[dict[str, Any]] | None:
-    """Get available blocks from the external service.
-
-    Returns:
-        List of block info dicts or None on error
-    """
-    client = _get_client()
-
-    try:
-        response = await client.get("/api/blocks")
-        response.raise_for_status()
-        data = response.json()
-
-        if not data.get("success"):
-            logger.error("External service returned error getting blocks")
-            return None
-
-        return data.get("blocks", [])
-
-    except httpx.HTTPStatusError as e:
-        logger.error(f"HTTP error getting blocks from external service: {e}")
-        return None
-    except httpx.RequestError as e:
-        logger.error(f"Request error getting blocks from external service: {e}")
-        return None
-    except Exception as e:
-        logger.error(f"Unexpected error getting blocks from external service: {e}")
-        return None
-
-
-async def health_check() -> bool:
-    """Check if the external service is healthy.
-
-    Returns:
-        True if healthy, False otherwise
-    """
-    if not is_external_service_configured():
-        return False
-
-    client = _get_client()
-
-    try:
-        response = await client.get("/health")
-        response.raise_for_status()
-        data = response.json()
-        return data.get("status") == "healthy" and data.get("blocks_loaded", False)
-    except Exception as e:
-        logger.warning(f"External agent generator health check failed: {e}")
-        return False
-
-
-async def close_client() -> None:
-    """Close the HTTP client."""
-    global _client
-    if _client is not None:
-        await _client.aclose()
-        _client = None

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/utils.py

@@ -0,0 +1,213 @@
+"""Utilities for agent generation."""
+
+import json
+import re
+from typing import Any
+
+from backend.data.block import get_blocks
+
+# UUID validation regex
+UUID_REGEX = re.compile(
+    r"^[a-f0-9]{8}-[a-f0-9]{4}-4[a-f0-9]{3}-[89ab][a-f0-9]{3}-[a-f0-9]{12}$"
+)
+
+# Block IDs for various fixes
+STORE_VALUE_BLOCK_ID = "1ff065e9-88e8-4358-9d82-8dc91f622ba9"
+CONDITION_BLOCK_ID = "715696a0-e1da-45c8-b209-c2fa9c3b0be6"
+ADDTOLIST_BLOCK_ID = "aeb08fc1-2fc1-4141-bc8e-f758f183a822"
+ADDTODICTIONARY_BLOCK_ID = "31d1064e-7446-4693-a7d4-65e5ca1180d1"
+CREATELIST_BLOCK_ID = "a912d5c7-6e00-4542-b2a9-8034136930e4"
+CREATEDICT_BLOCK_ID = "b924ddf4-de4f-4b56-9a85-358930dcbc91"
+CODE_EXECUTION_BLOCK_ID = "0b02b072-abe7-11ef-8372-fb5d162dd712"
+DATA_SAMPLING_BLOCK_ID = "4a448883-71fa-49cf-91cf-70d793bd7d87"
+UNIVERSAL_TYPE_CONVERTER_BLOCK_ID = "95d1b990-ce13-4d88-9737-ba5c2070c97b"
+GET_CURRENT_DATE_BLOCK_ID = "b29c1b50-5d0e-4d9f-8f9d-1b0e6fcbf0b1"
+
+DOUBLE_CURLY_BRACES_BLOCK_IDS = [
+    "44f6c8ad-d75c-4ae1-8209-aad1c0326928",  # FillTextTemplateBlock
+    "6ab085e2-20b3-4055-bc3e-08036e01eca6",
+    "90f8c45e-e983-4644-aa0b-b4ebe2f531bc",
+    "363ae599-353e-4804-937e-b2ee3cef3da4",  # AgentOutputBlock
+    "3b191d9f-356f-482d-8238-ba04b6d18381",
+    "db7d8f02-2f44-4c55-ab7a-eae0941f0c30",
+    "3a7c4b8d-6e2f-4a5d-b9c1-f8d23c5a9b0e",
+    "ed1ae7a0-b770-4089-b520-1f0005fad19a",
+    "a892b8d9-3e4e-4e9c-9c1e-75f8efcf1bfa",
+    "b29c1b50-5d0e-4d9f-8f9d-1b0e6fcbf0b1",
+    "716a67b3-6760-42e7-86dc-18645c6e00fc",
+    "530cf046-2ce0-4854-ae2c-659db17c7a46",
+    "ed55ac19-356e-4243-a6cb-bc599e9b716f",
+    "1f292d4a-41a4-4977-9684-7c8d560b9f91",  # LLM blocks
+    "32a87eab-381e-4dd4-bdb8-4c47151be35a",
+]
+
+
+def is_valid_uuid(value: str) -> bool:
+    """Check if a string is a valid UUID v4."""
+    return isinstance(value, str) and UUID_REGEX.match(value) is not None
+
+
+def _compact_schema(schema: dict) -> dict[str, str]:
+    """Extract compact type info from a JSON schema properties dict.
+
+    Returns a dict of {field_name: type_string} for essential info only.
+    """
+    props = schema.get("properties", {})
+    result = {}
+
+    for name, prop in props.items():
+        # Skip internal/complex fields
+        if name.startswith("_"):
+            continue
+
+        # Get type string
+        type_str = prop.get("type", "any")
+
+        # Handle anyOf/oneOf (optional types)
+        if "anyOf" in prop:
+            types = [t.get("type", "?") for t in prop["anyOf"] if t.get("type")]
+            type_str = "|".join(types) if types else "any"
+        elif "allOf" in prop:
+            type_str = "object"
+
+        # Add array item type if present
+        if type_str == "array" and "items" in prop:
+            items = prop["items"]
+            if isinstance(items, dict):
+                item_type = items.get("type", "any")
+                type_str = f"array[{item_type}]"
+
+        result[name] = type_str
+
+    return result
+
+
+def get_block_summaries(include_schemas: bool = True) -> str:
+    """Generate compact block summaries for prompts.
+
+    Args:
+        include_schemas: Whether to include input/output type info
+
+    Returns:
+        Formatted string of block summaries (compact format)
+    """
+    blocks = get_blocks()
+    summaries = []
+
+    for block_id, block_cls in blocks.items():
+        block = block_cls()
+        name = block.name
+        desc = getattr(block, "description", "") or ""
+
+        # Truncate description
+        if len(desc) > 150:
+            desc = desc[:147] + "..."
+
+        if not include_schemas:
+            summaries.append(f"- {name} (id: {block_id}): {desc}")
+        else:
+            # Compact format with type info only
+            inputs = {}
+            outputs = {}
+            required = []
+
+            if hasattr(block, "input_schema"):
+                try:
+                    schema = block.input_schema.jsonschema()
+                    inputs = _compact_schema(schema)
+                    required = schema.get("required", [])
+                except Exception:
+                    pass
+
+            if hasattr(block, "output_schema"):
+                try:
+                    schema = block.output_schema.jsonschema()
+                    outputs = _compact_schema(schema)
+                except Exception:
+                    pass
+
+            # Build compact line format
+            # Format: NAME (id): desc | in: {field:type, ...} [required] | out: {field:type}
+            in_str = ", ".join(f"{k}:{v}" for k, v in inputs.items())
+            out_str = ", ".join(f"{k}:{v}" for k, v in outputs.items())
+            req_str = f" req=[{','.join(required)}]" if required else ""
+
+            static = " [static]" if getattr(block, "static_output", False) else ""
+
+            line = f"- {name} (id: {block_id}): {desc}"
+            if in_str:
+                line += f"\n  in: {{{in_str}}}{req_str}"
+            if out_str:
+                line += f"\n  out: {{{out_str}}}{static}"
+
+            summaries.append(line)
+
+    return "\n".join(summaries)
+
+
+def get_blocks_info() -> list[dict[str, Any]]:
+    """Get block information with schemas for validation and fixing."""
+    blocks = get_blocks()
+    blocks_info = []
+    for block_id, block_cls in blocks.items():
+        block = block_cls()
+        blocks_info.append(
+            {
+                "id": block_id,
+                "name": block.name,
+                "description": getattr(block, "description", ""),
+                "categories": getattr(block, "categories", []),
+                "staticOutput": getattr(block, "static_output", False),
+                "inputSchema": (
+                    block.input_schema.jsonschema()
+                    if hasattr(block, "input_schema")
+                    else {}
+                ),
+                "outputSchema": (
+                    block.output_schema.jsonschema()
+                    if hasattr(block, "output_schema")
+                    else {}
+                ),
+            }
+        )
+    return blocks_info
+
+
+def parse_json_from_llm(text: str) -> dict[str, Any] | None:
+    """Extract JSON from LLM response (handles markdown code blocks)."""
+    if not text:
+        return None
+
+    # Try fenced code block
+    match = re.search(r"```(?:json)?\s*([\s\S]*?)```", text, re.IGNORECASE)
+    if match:
+        try:
+            return json.loads(match.group(1).strip())
+        except json.JSONDecodeError:
+            pass
+
+    # Try raw text
+    try:
+        return json.loads(text.strip())
+    except json.JSONDecodeError:
+        pass
+
+    # Try finding {...} span
+    start = text.find("{")
+    end = text.rfind("}")
+    if start != -1 and end > start:
+        try:
+            return json.loads(text[start : end + 1])
+        except json.JSONDecodeError:
+            pass
+
+    # Try finding [...] span
+    start = text.find("[")
+    end = text.rfind("]")
+    if start != -1 and end > start:
+        try:
+            return json.loads(text[start : end + 1])
+        except json.JSONDecodeError:
+            pass
+
+    return None

autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/validator.py

@@ -0,0 +1,279 @@
+"""Agent validator - Validates agent structure and connections."""
+
+import logging
+import re
+from typing import Any
+
+from .utils import get_blocks_info
+
+logger = logging.getLogger(__name__)
+
+
+class AgentValidator:
+    """Validator for AutoGPT agents with detailed error reporting."""
+
+    def __init__(self):
+        self.errors: list[str] = []
+
+    def add_error(self, error: str) -> None:
+        """Add an error message."""
+        self.errors.append(error)
+
+    def validate_block_existence(
+        self, agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+    ) -> bool:
+        """Validate all block IDs exist in the blocks library."""
+        valid = True
+        valid_block_ids = {b.get("id") for b in blocks_info if b.get("id")}
+
+        for node in agent.get("nodes", []):
+            block_id = node.get("block_id")
+            node_id = node.get("id")
+
+            if not block_id:
+                self.add_error(f"Node '{node_id}' is missing 'block_id' field.")
+                valid = False
+                continue
+
+            if block_id not in valid_block_ids:
+                self.add_error(
+                    f"Node '{node_id}' references block_id '{block_id}' which does not exist."
+                )
+                valid = False
+
+        return valid
+
+    def validate_link_node_references(self, agent: dict[str, Any]) -> bool:
+        """Validate all node IDs referenced in links exist."""
+        valid = True
+        valid_node_ids = {n.get("id") for n in agent.get("nodes", []) if n.get("id")}
+
+        for link in agent.get("links", []):
+            link_id = link.get("id", "Unknown")
+            source_id = link.get("source_id")
+            sink_id = link.get("sink_id")
+
+            if not source_id:
+                self.add_error(f"Link '{link_id}' is missing 'source_id'.")
+                valid = False
+            elif source_id not in valid_node_ids:
+                self.add_error(
+                    f"Link '{link_id}' references non-existent source_id '{source_id}'."
+                )
+                valid = False
+
+            if not sink_id:
+                self.add_error(f"Link '{link_id}' is missing 'sink_id'.")
+                valid = False
+            elif sink_id not in valid_node_ids:
+                self.add_error(
+                    f"Link '{link_id}' references non-existent sink_id '{sink_id}'."
+                )
+                valid = False
+
+        return valid
+
+    def validate_required_inputs(
+        self, agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+    ) -> bool:
+        """Validate required inputs are provided."""
+        valid = True
+        block_map = {b.get("id"): b for b in blocks_info}
+
+        for node in agent.get("nodes", []):
+            block_id = node.get("block_id")
+            block = block_map.get(block_id)
+
+            if not block:
+                continue
+
+            required_inputs = block.get("inputSchema", {}).get("required", [])
+            input_defaults = node.get("input_default", {})
+            node_id = node.get("id")
+
+            # Get linked inputs
+            linked_inputs = {
+                link["sink_name"]
+                for link in agent.get("links", [])
+                if link.get("sink_id") == node_id
+            }
+
+            for req_input in required_inputs:
+                if (
+                    req_input not in input_defaults
+                    and req_input not in linked_inputs
+                    and req_input != "credentials"
+                ):
+                    block_name = block.get("name", "Unknown Block")
+                    self.add_error(
+                        f"Node '{node_id}' ({block_name}) is missing required input '{req_input}'."
+                    )
+                    valid = False
+
+        return valid
+
+    def validate_data_type_compatibility(
+        self, agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+    ) -> bool:
+        """Validate linked data types are compatible."""
+        valid = True
+        block_map = {b.get("id"): b for b in blocks_info}
+        node_lookup = {n.get("id"): n for n in agent.get("nodes", [])}
+
+        def get_type(schema: dict, name: str) -> str | None:
+            if "_#_" in name:
+                parent, child = name.split("_#_", 1)
+                parent_schema = schema.get(parent, {})
+                if "properties" in parent_schema:
+                    return parent_schema["properties"].get(child, {}).get("type")
+                return None
+            return schema.get(name, {}).get("type")
+
+        def are_compatible(src: str, sink: str) -> bool:
+            if {src, sink} <= {"integer", "number"}:
+                return True
+            return src == sink
+
+        for link in agent.get("links", []):
+            source_node = node_lookup.get(link.get("source_id"))
+            sink_node = node_lookup.get(link.get("sink_id"))
+
+            if not source_node or not sink_node:
+                continue
+
+            source_block = block_map.get(source_node.get("block_id"))
+            sink_block = block_map.get(sink_node.get("block_id"))
+
+            if not source_block or not sink_block:
+                continue
+
+            source_outputs = source_block.get("outputSchema", {}).get("properties", {})
+            sink_inputs = sink_block.get("inputSchema", {}).get("properties", {})
+
+            source_type = get_type(source_outputs, link.get("source_name", ""))
+            sink_type = get_type(sink_inputs, link.get("sink_name", ""))
+
+            if source_type and sink_type and not are_compatible(source_type, sink_type):
+                self.add_error(
+                    f"Type mismatch: {source_block.get('name')} output '{link['source_name']}' "
+                    f"({source_type}) -> {sink_block.get('name')} input '{link['sink_name']}' ({sink_type})."
+                )
+                valid = False
+
+        return valid
+
+    def validate_nested_sink_links(
+        self, agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+    ) -> bool:
+        """Validate nested sink links (with _#_ notation)."""
+        valid = True
+        block_map = {b.get("id"): b for b in blocks_info}
+        node_lookup = {n.get("id"): n for n in agent.get("nodes", [])}
+
+        for link in agent.get("links", []):
+            sink_name = link.get("sink_name", "")
+
+            if "_#_" in sink_name:
+                parent, child = sink_name.split("_#_", 1)
+
+                sink_node = node_lookup.get(link.get("sink_id"))
+                if not sink_node:
+                    continue
+
+                block = block_map.get(sink_node.get("block_id"))
+                if not block:
+                    continue
+
+                input_props = block.get("inputSchema", {}).get("properties", {})
+                parent_schema = input_props.get(parent)
+
+                if not parent_schema:
+                    self.add_error(
+                        f"Invalid nested link '{sink_name}': parent '{parent}' not found."
+                    )
+                    valid = False
+                    continue
+
+                if not parent_schema.get("additionalProperties"):
+                    if not (
+                        isinstance(parent_schema, dict)
+                        and "properties" in parent_schema
+                        and child in parent_schema.get("properties", {})
+                    ):
+                        self.add_error(
+                            f"Invalid nested link '{sink_name}': child '{child}' not found in '{parent}'."
+                        )
+                        valid = False
+
+        return valid
+
+    def validate_prompt_spaces(self, agent: dict[str, Any]) -> bool:
+        """Validate prompts don't have spaces in template variables."""
+        valid = True
+
+        for node in agent.get("nodes", []):
+            input_default = node.get("input_default", {})
+            prompt = input_default.get("prompt", "")
+
+            if not isinstance(prompt, str):
+                continue
+
+            # Find {{...}} with spaces
+            matches = re.finditer(r"\{\{([^}]+)\}\}", prompt)
+            for match in matches:
+                content = match.group(1)
+                if " " in content:
+                    self.add_error(
+                        f"Node '{node.get('id')}' has spaces in template variable: "
+                        f"'{{{{{content}}}}}' should be '{{{{{content.replace(' ', '_')}}}}}'."
+                    )
+                    valid = False
+
+        return valid
+
+    def validate(
+        self, agent: dict[str, Any], blocks_info: list[dict[str, Any]] | None = None
+    ) -> tuple[bool, str | None]:
+        """Run all validations.
+
+        Returns:
+            Tuple of (is_valid, error_message)
+        """
+        self.errors = []
+
+        if blocks_info is None:
+            blocks_info = get_blocks_info()
+
+        checks = [
+            self.validate_block_existence(agent, blocks_info),
+            self.validate_link_node_references(agent),
+            self.validate_required_inputs(agent, blocks_info),
+            self.validate_data_type_compatibility(agent, blocks_info),
+            self.validate_nested_sink_links(agent, blocks_info),
+            self.validate_prompt_spaces(agent),
+        ]
+
+        all_passed = all(checks)
+
+        if all_passed:
+            logger.info("Agent validation successful")
+            return True, None
+
+        error_message = "Agent validation failed:\n"
+        for i, error in enumerate(self.errors, 1):
+            error_message += f"{i}. {error}\n"
+
+        logger.warning(f"Agent validation failed with {len(self.errors)} errors")
+        return False, error_message
+
+
+def validate_agent(
+    agent: dict[str, Any], blocks_info: list[dict[str, Any]] | None = None
+) -> tuple[bool, str | None]:
+    """Convenience function to validate an agent.
+
+    Returns:
+        Tuple of (is_valid, error_message)
+    """
+    validator = AgentValidator()
+    return validator.validate(agent, blocks_info)

autogpt_platform/backend/backend/api/features/chat/tools/agent_output.py

@@ -5,6 +5,7 @@ import re
 from datetime import datetime, timedelta, timezone
 from typing import Any
 
+from langfuse import observe
 from pydantic import BaseModel, field_validator
 
 from backend.api.features.chat.model import ChatSession
@@ -328,6 +329,7 @@ class AgentOutputTool(BaseTool):
             total_executions=len(available_executions) if available_executions else 1,
         )
 
+    @observe(as_type="tool", name="view_agent_output")
     async def _execute(
         self,
         user_id: str | None,

autogpt_platform/backend/backend/api/features/chat/tools/base.py

@@ -36,16 +36,6 @@ class BaseTool:
         """Whether this tool requires authentication."""
         return False
 
-    @property
-    def is_long_running(self) -> bool:
-        """Whether this tool is long-running and should execute in background.
-
-        Long-running tools (like agent generation) are executed via background
-        tasks to survive SSE disconnections. The result is persisted to chat
-        history and visible when the user refreshes.
-        """
-        return False
-
     def as_openai_tool(self) -> ChatCompletionToolParam:
         """Convert to OpenAI tool format."""
         return ChatCompletionToolParam(

autogpt_platform/backend/backend/api/features/chat/tools/create_agent.py

@@ -3,13 +3,17 @@
 import logging
 from typing import Any
 
+from langfuse import observe
+
 from backend.api.features.chat.model import ChatSession
 
 from .agent_generator import (
-    AgentGeneratorNotConfiguredError,
+    apply_all_fixes,
     decompose_goal,
     generate_agent,
+    get_blocks_info,
     save_agent_to_library,
+    validate_agent,
 )
 from .base import BaseTool
 from .models import (
@@ -23,6 +27,9 @@ from .models import (
 
 logger = logging.getLogger(__name__)
 
+# Maximum retries for agent generation with validation feedback
+MAX_GENERATION_RETRIES = 2
+
 
 class CreateAgentTool(BaseTool):
     """Tool for creating agents from natural language descriptions."""
@@ -42,10 +49,6 @@ class CreateAgentTool(BaseTool):
     def requires_auth(self) -> bool:
         return True
 
-    @property
-    def is_long_running(self) -> bool:
-        return True
-
     @property
     def parameters(self) -> dict[str, Any]:
         return {
@@ -77,6 +80,7 @@ class CreateAgentTool(BaseTool):
             "required": ["description"],
         }
 
+    @observe(as_type="tool", name="create_agent")
     async def _execute(
         self,
         user_id: str | None,
@@ -87,8 +91,9 @@ class CreateAgentTool(BaseTool):
 
         Flow:
         1. Decompose the description into steps (may return clarifying questions)
-        2. Generate agent JSON (external service handles fixing and validation)
-        3. Preview or save based on the save parameter
+        2. Generate agent JSON from the steps
+        3. Apply fixes to correct common LLM errors
+        4. Preview or save based on the save parameter
         """
         description = kwargs.get("description", "").strip()
         context = kwargs.get("context", "")
@@ -105,23 +110,18 @@ class CreateAgentTool(BaseTool):
         # Step 1: Decompose goal into steps
         try:
             decomposition_result = await decompose_goal(description, context)
-        except AgentGeneratorNotConfiguredError:
+        except ValueError as e:
+            # Handle missing API key or configuration errors
             return ErrorResponse(
-                message=(
-                    "Agent generation is not available. "
-                    "The Agent Generator service is not configured."
-                ),
-                error="service_not_configured",
+                message=f"Agent generation is not configured: {str(e)}",
+                error="configuration_error",
                 session_id=session_id,
             )
 
         if decomposition_result is None:
             return ErrorResponse(
-                message="Failed to analyze the goal. The agent generation service may be unavailable or timed out. Please try again.",
-                error="decomposition_failed",
-                details={
-                    "description": description[:100]
-                },  # Include context for debugging
+                message="Failed to analyze the goal. Please try rephrasing.",
+                error="Decomposition failed",
                 session_id=session_id,
             )
 
@@ -171,35 +171,72 @@ class CreateAgentTool(BaseTool):
                 session_id=session_id,
             )
 
-        # Step 2: Generate agent JSON (external service handles fixing and validation)
-        try:
-            agent_json = await generate_agent(decomposition_result)
-        except AgentGeneratorNotConfiguredError:
-            return ErrorResponse(
-                message=(
-                    "Agent generation is not available. "
-                    "The Agent Generator service is not configured."
-                ),
-                error="service_not_configured",
-                session_id=session_id,
+        # Step 2: Generate agent JSON with retry on validation failure
+        blocks_info = get_blocks_info()
+        agent_json = None
+        validation_errors = None
+
+        for attempt in range(MAX_GENERATION_RETRIES + 1):
+            # Generate agent (include validation errors from previous attempt)
+            if attempt == 0:
+                agent_json = await generate_agent(decomposition_result)
+            else:
+                # Retry with validation error feedback
+                logger.info(
+                    f"Retry {attempt}/{MAX_GENERATION_RETRIES} with validation feedback"
+                )
+                retry_instructions = {
+                    **decomposition_result,
+                    "previous_errors": validation_errors,
+                    "retry_instructions": (
+                        "The previous generation had validation errors. "
+                        "Please fix these issues in the new generation:\n"
+                        f"{validation_errors}"
+                    ),
+                }
+                agent_json = await generate_agent(retry_instructions)
+
+            if agent_json is None:
+                if attempt == MAX_GENERATION_RETRIES:
+                    return ErrorResponse(
+                        message="Failed to generate the agent. Please try again.",
+                        error="Generation failed",
+                        session_id=session_id,
+                    )
+                continue
+
+            # Step 3: Apply fixes to correct common errors
+            agent_json = apply_all_fixes(agent_json, blocks_info)
+
+            # Step 4: Validate the agent
+            is_valid, validation_errors = validate_agent(agent_json, blocks_info)
+
+            if is_valid:
+                logger.info(f"Agent generated successfully on attempt {attempt + 1}")
+                break
+
+            logger.warning(
+                f"Validation failed on attempt {attempt + 1}: {validation_errors}"
             )
 
-        if agent_json is None:
-            return ErrorResponse(
-                message="Failed to generate the agent. The agent generation service may be unavailable or timed out. Please try again.",
-                error="generation_failed",
-                details={
-                    "description": description[:100]
-                },  # Include context for debugging
-                session_id=session_id,
-            )
+            if attempt == MAX_GENERATION_RETRIES:
+                # Return error with validation details
+                return ErrorResponse(
+                    message=(
+                        f"Generated agent has validation errors after {MAX_GENERATION_RETRIES + 1} attempts. "
+                        f"Please try rephrasing your request or simplify the workflow."
+                    ),
+                    error="validation_failed",
+                    details={"validation_errors": validation_errors},
+                    session_id=session_id,
+                )
 
         agent_name = agent_json.get("name", "Generated Agent")
         agent_description = agent_json.get("description", "")
         node_count = len(agent_json.get("nodes", []))
         link_count = len(agent_json.get("links", []))
 
-        # Step 3: Preview or save
+        # Step 4: Preview or save
         if not save:
             return AgentPreviewResponse(
                 message=(

autogpt_platform/backend/backend/api/features/chat/tools/edit_agent.py

@@ -3,13 +3,18 @@
 import logging
 from typing import Any
 
+from langfuse import observe
+
 from backend.api.features.chat.model import ChatSession
 
 from .agent_generator import (
-    AgentGeneratorNotConfiguredError,
+    apply_agent_patch,
+    apply_all_fixes,
     generate_agent_patch,
     get_agent_as_json,
+    get_blocks_info,
     save_agent_to_library,
+    validate_agent,
 )
 from .base import BaseTool
 from .models import (
@@ -23,6 +28,9 @@ from .models import (
 
 logger = logging.getLogger(__name__)
 
+# Maximum retries for patch generation with validation feedback
+MAX_GENERATION_RETRIES = 2
+
 
 class EditAgentTool(BaseTool):
     """Tool for editing existing agents using natural language."""
@@ -35,17 +43,13 @@ class EditAgentTool(BaseTool):
     def description(self) -> str:
         return (
             "Edit an existing agent from the user's library using natural language. "
-            "Generates updates to the agent while preserving unchanged parts."
+            "Generates a patch to update the agent while preserving unchanged parts."
         )
 
     @property
     def requires_auth(self) -> bool:
         return True
 
-    @property
-    def is_long_running(self) -> bool:
-        return True
-
     @property
     def parameters(self) -> dict[str, Any]:
         return {
@@ -83,6 +87,7 @@ class EditAgentTool(BaseTool):
             "required": ["agent_id", "changes"],
         }
 
+    @observe(as_type="tool", name="edit_agent")
     async def _execute(
         self,
         user_id: str | None,
@@ -93,8 +98,9 @@ class EditAgentTool(BaseTool):
 
         Flow:
         1. Fetch the current agent
-        2. Generate updated agent (external service handles fixing and validation)
-        3. Preview or save based on the save parameter
+        2. Generate a patch based on the requested changes
+        3. Apply the patch to create an updated agent
+        4. Preview or save based on the save parameter
         """
         agent_id = kwargs.get("agent_id", "").strip()
         changes = kwargs.get("changes", "").strip()
@@ -131,59 +137,121 @@ class EditAgentTool(BaseTool):
         if context:
             update_request = f"{changes}\n\nAdditional context:\n{context}"
 
-        # Step 2: Generate updated agent (external service handles fixing and validation)
-        try:
-            result = await generate_agent_patch(update_request, current_agent)
-        except AgentGeneratorNotConfiguredError:
-            return ErrorResponse(
-                message=(
-                    "Agent editing is not available. "
-                    "The Agent Generator service is not configured."
-                ),
-                error="service_not_configured",
-                session_id=session_id,
-            )
+        # Step 2: Generate patch with retry on validation failure
+        blocks_info = get_blocks_info()
+        updated_agent = None
+        validation_errors = None
+        intent = "Applied requested changes"
 
-        if result is None:
-            return ErrorResponse(
-                message="Failed to generate changes. The agent generation service may be unavailable or timed out. Please try again.",
-                error="update_generation_failed",
-                details={"agent_id": agent_id, "changes": changes[:100]},
-                session_id=session_id,
-            )
-
-        # Check if LLM returned clarifying questions
-        if result.get("type") == "clarifying_questions":
-            questions = result.get("questions", [])
-            return ClarificationNeededResponse(
-                message=(
-                    "I need some more information about the changes. "
-                    "Please answer the following questions:"
-                ),
-                questions=[
-                    ClarifyingQuestion(
-                        question=q.get("question", ""),
-                        keyword=q.get("keyword", ""),
-                        example=q.get("example"),
+        for attempt in range(MAX_GENERATION_RETRIES + 1):
+            # Generate patch (include validation errors from previous attempt)
+            try:
+                if attempt == 0:
+                    patch_result = await generate_agent_patch(
+                        update_request, current_agent
                     )
-                    for q in questions
-                ],
-                session_id=session_id,
+                else:
+                    # Retry with validation error feedback
+                    logger.info(
+                        f"Retry {attempt}/{MAX_GENERATION_RETRIES} with validation feedback"
+                    )
+                    retry_request = (
+                        f"{update_request}\n\n"
+                        f"IMPORTANT: The previous edit had validation errors. "
+                        f"Please fix these issues:\n{validation_errors}"
+                    )
+                    patch_result = await generate_agent_patch(
+                        retry_request, current_agent
+                    )
+            except ValueError as e:
+                # Handle missing API key or configuration errors
+                return ErrorResponse(
+                    message=f"Agent generation is not configured: {str(e)}",
+                    error="configuration_error",
+                    session_id=session_id,
+                )
+
+            if patch_result is None:
+                if attempt == MAX_GENERATION_RETRIES:
+                    return ErrorResponse(
+                        message="Failed to generate changes. Please try rephrasing.",
+                        error="Patch generation failed",
+                        session_id=session_id,
+                    )
+                continue
+
+            # Check if LLM returned clarifying questions
+            if patch_result.get("type") == "clarifying_questions":
+                questions = patch_result.get("questions", [])
+                return ClarificationNeededResponse(
+                    message=(
+                        "I need some more information about the changes. "
+                        "Please answer the following questions:"
+                    ),
+                    questions=[
+                        ClarifyingQuestion(
+                            question=q.get("question", ""),
+                            keyword=q.get("keyword", ""),
+                            example=q.get("example"),
+                        )
+                        for q in questions
+                    ],
+                    session_id=session_id,
+                )
+
+            # Step 3: Apply patch and fixes
+            try:
+                updated_agent = apply_agent_patch(current_agent, patch_result)
+                updated_agent = apply_all_fixes(updated_agent, blocks_info)
+            except Exception as e:
+                if attempt == MAX_GENERATION_RETRIES:
+                    return ErrorResponse(
+                        message=f"Failed to apply changes: {str(e)}",
+                        error="patch_apply_failed",
+                        details={"exception": str(e)},
+                        session_id=session_id,
+                    )
+                validation_errors = str(e)
+                continue
+
+            # Step 4: Validate the updated agent
+            is_valid, validation_errors = validate_agent(updated_agent, blocks_info)
+
+            if is_valid:
+                logger.info(f"Agent edited successfully on attempt {attempt + 1}")
+                intent = patch_result.get("intent", "Applied requested changes")
+                break
+
+            logger.warning(
+                f"Validation failed on attempt {attempt + 1}: {validation_errors}"
             )
 
-        # Result is the updated agent JSON
-        updated_agent = result
+            if attempt == MAX_GENERATION_RETRIES:
+                # Return error with validation details
+                return ErrorResponse(
+                    message=(
+                        f"Updated agent has validation errors after "
+                        f"{MAX_GENERATION_RETRIES + 1} attempts. "
+                        f"Please try rephrasing your request or simplify the changes."
+                    ),
+                    error="validation_failed",
+                    details={"validation_errors": validation_errors},
+                    session_id=session_id,
+                )
+
+        # At this point, updated_agent is guaranteed to be set (we return on all failure paths)
+        assert updated_agent is not None
 
         agent_name = updated_agent.get("name", "Updated Agent")
         agent_description = updated_agent.get("description", "")
         node_count = len(updated_agent.get("nodes", []))
         link_count = len(updated_agent.get("links", []))
 
-        # Step 3: Preview or save
+        # Step 5: Preview or save
         if not save:
             return AgentPreviewResponse(
                 message=(
-                    f"I've updated the agent. "
+                    f"I've updated the agent. Changes: {intent}. "
                     f"The agent now has {node_count} blocks. "
                     f"Review it and call edit_agent with save=true to save the changes."
                 ),
@@ -209,7 +277,10 @@ class EditAgentTool(BaseTool):
             )
 
             return AgentSavedResponse(
-                message=f"Updated agent '{created_graph.name}' has been saved to your library!",
+                message=(
+                    f"Updated agent '{created_graph.name}' has been saved to your library! "
+                    f"Changes: {intent}"
+                ),
                 agent_id=created_graph.id,
                 agent_name=created_graph.name,
                 library_agent_id=library_agent.id,

autogpt_platform/backend/backend/api/features/chat/tools/find_agent.py

@@ -2,6 +2,8 @@
 
 from typing import Any
 
+from langfuse import observe
+
 from backend.api.features.chat.model import ChatSession
 
 from .agent_search import search_agents
@@ -35,6 +37,7 @@ class FindAgentTool(BaseTool):
             "required": ["query"],
         }
 
+    @observe(as_type="tool", name="find_agent")
     async def _execute(
         self, user_id: str | None, session: ChatSession, **kwargs
     ) -> ToolResponseBase:

autogpt_platform/backend/backend/api/features/chat/tools/find_block.py

@@ -1,6 +1,7 @@
 import logging
 from typing import Any
 
+from langfuse import observe
 from prisma.enums import ContentType
 
 from backend.api.features.chat.model import ChatSession
@@ -55,6 +56,7 @@ class FindBlockTool(BaseTool):
     def requires_auth(self) -> bool:
         return True
 
+    @observe(as_type="tool", name="find_block")
     async def _execute(
         self,
         user_id: str | None,
@@ -107,8 +109,7 @@ class FindBlockTool(BaseTool):
                 block_id = result["content_id"]
                 block = get_block(block_id)
 
-                # Skip disabled blocks
-                if block and not block.disabled:
+                if block:
                     # Get input/output schemas
                     input_schema = {}
                     output_schema = {}

autogpt_platform/backend/backend/api/features/chat/tools/find_library_agent.py

@@ -2,6 +2,8 @@
 
 from typing import Any
 
+from langfuse import observe
+
 from backend.api.features.chat.model import ChatSession
 
 from .agent_search import search_agents
@@ -41,6 +43,7 @@ class FindLibraryAgentTool(BaseTool):
     def requires_auth(self) -> bool:
         return True
 
+    @observe(as_type="tool", name="find_library_agent")
     async def _execute(
         self, user_id: str | None, session: ChatSession, **kwargs
     ) -> ToolResponseBase:

autogpt_platform/backend/backend/api/features/chat/tools/get_doc_page.py

@@ -4,6 +4,8 @@ import logging
 from pathlib import Path
 from typing import Any
 
+from langfuse import observe
+
 from backend.api.features.chat.model import ChatSession
 from backend.api.features.chat.tools.base import BaseTool
 from backend.api.features.chat.tools.models import (
@@ -71,6 +73,7 @@ class GetDocPageTool(BaseTool):
         url_path = path.rsplit(".", 1)[0] if "." in path else path
         return f"{DOCS_BASE_URL}/{url_path}"
 
+    @observe(as_type="tool", name="get_doc_page")
     async def _execute(
         self,
         user_id: str | None,

autogpt_platform/backend/backend/api/features/chat/tools/models.py

@@ -28,16 +28,6 @@ class ResponseType(str, Enum):
     BLOCK_OUTPUT = "block_output"
     DOC_SEARCH_RESULTS = "doc_search_results"
     DOC_PAGE = "doc_page"
-    # Workspace response types
-    WORKSPACE_FILE_LIST = "workspace_file_list"
-    WORKSPACE_FILE_CONTENT = "workspace_file_content"
-    WORKSPACE_FILE_METADATA = "workspace_file_metadata"
-    WORKSPACE_FILE_WRITTEN = "workspace_file_written"
-    WORKSPACE_FILE_DELETED = "workspace_file_deleted"
-    # Long-running operation types
-    OPERATION_STARTED = "operation_started"
-    OPERATION_PENDING = "operation_pending"
-    OPERATION_IN_PROGRESS = "operation_in_progress"
 
 
 # Base response model
@@ -344,43 +334,3 @@ class BlockOutputResponse(ToolResponseBase):
     block_name: str
     outputs: dict[str, list[Any]]
     success: bool = True
-
-
-# Long-running operation models
-class OperationStartedResponse(ToolResponseBase):
-    """Response when a long-running operation has been started in the background.
-
-    This is returned immediately to the client while the operation continues
-    to execute. The user can close the tab and check back later.
-
-    The task_id can be used to reconnect to the SSE stream via
-    GET /chat/tasks/{task_id}/stream?last_idx=0
-    """
-
-    type: ResponseType = ResponseType.OPERATION_STARTED
-    operation_id: str
-    tool_name: str
-    task_id: str | None = None  # For SSE reconnection
-
-
-class OperationPendingResponse(ToolResponseBase):
-    """Response stored in chat history while a long-running operation is executing.
-
-    This is persisted to the database so users see a pending state when they
-    refresh before the operation completes.
-    """
-
-    type: ResponseType = ResponseType.OPERATION_PENDING
-    operation_id: str
-    tool_name: str
-
-
-class OperationInProgressResponse(ToolResponseBase):
-    """Response when an operation is already in progress.
-
-    Returned for idempotency when the same tool_call_id is requested again
-    while the background task is still running.
-    """
-
-    type: ResponseType = ResponseType.OPERATION_IN_PROGRESS
-    tool_call_id: str

autogpt_platform/backend/backend/api/features/chat/tools/run_agent.py

@@ -3,14 +3,11 @@
 import logging
 from typing import Any
 
+from langfuse import observe
 from pydantic import BaseModel, Field, field_validator
 
 from backend.api.features.chat.config import ChatConfig
 from backend.api.features.chat.model import ChatSession
-from backend.api.features.chat.tracking import (
-    track_agent_run_success,
-    track_agent_scheduled,
-)
 from backend.api.features.library import db as library_db
 from backend.data.graph import GraphModel
 from backend.data.model import CredentialsMetaInput
@@ -36,7 +33,7 @@ from .models import (
     UserReadiness,
 )
 from .utils import (
-    build_missing_credentials_from_graph,
+    check_user_has_required_credentials,
     extract_credentials_from_schema,
     fetch_graph_from_store_slug,
     get_or_create_library_agent,
@@ -158,6 +155,7 @@ class RunAgentTool(BaseTool):
         """All operations require authentication."""
         return True
 
+    @observe(as_type="tool", name="run_agent")
     async def _execute(
         self,
         user_id: str | None,
@@ -239,13 +237,15 @@ class RunAgentTool(BaseTool):
                 # Return credentials needed response with input data info
                 # The UI handles credential setup automatically, so the message
                 # focuses on asking about input data
-                requirements_creds_dict = build_missing_credentials_from_graph(
-                    graph, None
+                credentials = extract_credentials_from_schema(
+                    graph.credentials_input_schema
                 )
-                missing_credentials_dict = build_missing_credentials_from_graph(
-                    graph, graph_credentials
+                missing_creds_check = await check_user_has_required_credentials(
+                    user_id, credentials
                 )
-                requirements_creds_list = list(requirements_creds_dict.values())
+                missing_credentials_dict = {
+                    c.id: c.model_dump() for c in missing_creds_check
+                }
 
                 return SetupRequirementsResponse(
                     message=self._build_inputs_message(graph, MSG_WHAT_VALUES_TO_USE),
@@ -259,7 +259,7 @@ class RunAgentTool(BaseTool):
                             ready_to_run=False,
                         ),
                         requirements={
-                            "credentials": requirements_creds_list,
+                            "credentials": [c.model_dump() for c in credentials],
                             "inputs": self._get_inputs_list(graph.input_schema),
                             "execution_modes": self._get_execution_modes(graph),
                         },
@@ -455,16 +455,6 @@ class RunAgentTool(BaseTool):
             session.successful_agent_runs.get(library_agent.graph_id, 0) + 1
         )
 
-        # Track in PostHog
-        track_agent_run_success(
-            user_id=user_id,
-            session_id=session_id,
-            graph_id=library_agent.graph_id,
-            graph_name=library_agent.name,
-            execution_id=execution.id,
-            library_agent_id=library_agent.id,
-        )
-
         library_agent_link = f"/library/agents/{library_agent.id}"
         return ExecutionStartedResponse(
             message=(
@@ -546,18 +536,6 @@ class RunAgentTool(BaseTool):
             session.successful_agent_schedules.get(library_agent.graph_id, 0) + 1
         )
 
-        # Track in PostHog
-        track_agent_scheduled(
-            user_id=user_id,
-            session_id=session_id,
-            graph_id=library_agent.graph_id,
-            graph_name=library_agent.name,
-            schedule_id=result.id,
-            schedule_name=schedule_name,
-            cron=cron,
-            library_agent_id=library_agent.id,
-        )
-
         library_agent_link = f"/library/agents/{library_agent.id}"
         return ExecutionStartedResponse(
             message=(

autogpt_platform/backend/backend/api/features/chat/tools/run_agent_test.py

@@ -29,7 +29,7 @@ def mock_embedding_functions():
         yield
 
 
-@pytest.mark.asyncio(loop_scope="session")
+@pytest.mark.asyncio(scope="session")
 async def test_run_agent(setup_test_data):
     """Test that the run_agent tool successfully executes an approved agent"""
     # Use test data from fixture
@@ -70,7 +70,7 @@ async def test_run_agent(setup_test_data):
     assert result_data["graph_name"] == "Test Agent"
 
 
-@pytest.mark.asyncio(loop_scope="session")
+@pytest.mark.asyncio(scope="session")
 async def test_run_agent_missing_inputs(setup_test_data):
     """Test that the run_agent tool returns error when inputs are missing"""
     # Use test data from fixture
@@ -106,7 +106,7 @@ async def test_run_agent_missing_inputs(setup_test_data):
     assert "message" in result_data
 
 
-@pytest.mark.asyncio(loop_scope="session")
+@pytest.mark.asyncio(scope="session")
 async def test_run_agent_invalid_agent_id(setup_test_data):
     """Test that the run_agent tool returns error for invalid agent ID"""
     # Use test data from fixture
@@ -141,7 +141,7 @@ async def test_run_agent_invalid_agent_id(setup_test_data):
     )
 
 
-@pytest.mark.asyncio(loop_scope="session")
+@pytest.mark.asyncio(scope="session")
 async def test_run_agent_with_llm_credentials(setup_llm_test_data):
     """Test that run_agent works with an agent requiring LLM credentials"""
     # Use test data from fixture
@@ -185,7 +185,7 @@ async def test_run_agent_with_llm_credentials(setup_llm_test_data):
     assert result_data["graph_name"] == "LLM Test Agent"
 
 
-@pytest.mark.asyncio(loop_scope="session")
+@pytest.mark.asyncio(scope="session")
 async def test_run_agent_shows_available_inputs_when_none_provided(setup_test_data):
     """Test that run_agent returns available inputs when called without inputs or use_defaults."""
     user = setup_test_data["user"]
@@ -219,7 +219,7 @@ async def test_run_agent_shows_available_inputs_when_none_provided(setup_test_da
     assert "inputs" in result_data["message"].lower()
 
 
-@pytest.mark.asyncio(loop_scope="session")
+@pytest.mark.asyncio(scope="session")
 async def test_run_agent_with_use_defaults(setup_test_data):
     """Test that run_agent executes successfully with use_defaults=True."""
     user = setup_test_data["user"]
@@ -251,7 +251,7 @@ async def test_run_agent_with_use_defaults(setup_test_data):
     assert result_data["graph_id"] == graph.id
 
 
-@pytest.mark.asyncio(loop_scope="session")
+@pytest.mark.asyncio(scope="session")
 async def test_run_agent_missing_credentials(setup_firecrawl_test_data):
     """Test that run_agent returns setup_requirements when credentials are missing."""
     user = setup_firecrawl_test_data["user"]
@@ -285,7 +285,7 @@ async def test_run_agent_missing_credentials(setup_firecrawl_test_data):
     assert len(setup_info["user_readiness"]["missing_credentials"]) > 0
 
 
-@pytest.mark.asyncio(loop_scope="session")
+@pytest.mark.asyncio(scope="session")
 async def test_run_agent_invalid_slug_format(setup_test_data):
     """Test that run_agent returns error for invalid slug format (no slash)."""
     user = setup_test_data["user"]
@@ -313,7 +313,7 @@ async def test_run_agent_invalid_slug_format(setup_test_data):
     assert "username/agent-name" in result_data["message"]
 
 
-@pytest.mark.asyncio(loop_scope="session")
+@pytest.mark.asyncio(scope="session")
 async def test_run_agent_unauthenticated():
     """Test that run_agent returns need_login for unauthenticated users."""
     tool = RunAgentTool()
@@ -340,7 +340,7 @@ async def test_run_agent_unauthenticated():
     assert "sign in" in result_data["message"].lower()
 
 
-@pytest.mark.asyncio(loop_scope="session")
+@pytest.mark.asyncio(scope="session")
 async def test_run_agent_schedule_without_cron(setup_test_data):
     """Test that run_agent returns error when scheduling without cron expression."""
     user = setup_test_data["user"]
@@ -372,7 +372,7 @@ async def test_run_agent_schedule_without_cron(setup_test_data):
     assert "cron" in result_data["message"].lower()
 
 
-@pytest.mark.asyncio(loop_scope="session")
+@pytest.mark.asyncio(scope="session")
 async def test_run_agent_schedule_without_name(setup_test_data):
     """Test that run_agent returns error when scheduling without schedule_name."""
     user = setup_test_data["user"]

autogpt_platform/backend/backend/api/features/chat/tools/run_block.py

@@ -1,15 +1,15 @@
 """Tool for executing blocks directly."""
 
 import logging
-import uuid
 from collections import defaultdict
 from typing import Any
 
+from langfuse import observe
+
 from backend.api.features.chat.model import ChatSession
 from backend.data.block import get_block
 from backend.data.execution import ExecutionContext
 from backend.data.model import CredentialsMetaInput
-from backend.data.workspace import get_or_create_workspace
 from backend.integrations.creds_manager import IntegrationCredentialsManager
 from backend.util.exceptions import BlockError
 
@@ -22,7 +22,6 @@ from .models import (
     ToolResponseBase,
     UserReadiness,
 )
-from .utils import build_missing_credentials_from_field_info
 
 logger = logging.getLogger(__name__)
 
@@ -130,6 +129,7 @@ class RunBlockTool(BaseTool):
 
         return matched_credentials, missing_credentials
 
+    @observe(as_type="tool", name="run_block")
     async def _execute(
         self,
         user_id: str | None,
@@ -178,11 +178,6 @@ class RunBlockTool(BaseTool):
                 message=f"Block '{block_id}' not found",
                 session_id=session_id,
             )
-        if block.disabled:
-            return ErrorResponse(
-                message=f"Block '{block_id}' is disabled",
-                session_id=session_id,
-            )
 
         logger.info(f"Executing block {block.name} ({block_id}) for user {user_id}")
 
@@ -194,11 +189,7 @@ class RunBlockTool(BaseTool):
 
         if missing_credentials:
             # Return setup requirements response with missing credentials
-            credentials_fields_info = block.input_schema.get_credentials_fields_info()
-            missing_creds_dict = build_missing_credentials_from_field_info(
-                credentials_fields_info, set(matched_credentials.keys())
-            )
-            missing_creds_list = list(missing_creds_dict.values())
+            missing_creds_dict = {c.id: c.model_dump() for c in missing_credentials}
 
             return SetupRequirementsResponse(
                 message=(
@@ -215,7 +206,7 @@ class RunBlockTool(BaseTool):
                         ready_to_run=False,
                     ),
                     requirements={
-                        "credentials": missing_creds_list,
+                        "credentials": [c.model_dump() for c in missing_credentials],
                         "inputs": self._get_inputs_list(block),
                         "execution_modes": ["immediate"],
                     },
@@ -225,48 +216,11 @@ class RunBlockTool(BaseTool):
             )
 
         try:
-            # Get or create user's workspace for CoPilot file operations
-            workspace = await get_or_create_workspace(user_id)
-
-            # Generate synthetic IDs for CoPilot context
-            # Each chat session is treated as its own agent with one continuous run
-            # This means:
-            # - graph_id (agent) = session (memories scoped to session when limit_to_agent=True)
-            # - graph_exec_id (run) = session (memories scoped to session when limit_to_run=True)
-            # - node_exec_id = unique per block execution
-            synthetic_graph_id = f"copilot-session-{session.session_id}"
-            synthetic_graph_exec_id = f"copilot-session-{session.session_id}"
-            synthetic_node_id = f"copilot-node-{block_id}"
-            synthetic_node_exec_id = (
-                f"copilot-{session.session_id}-{uuid.uuid4().hex[:8]}"
-            )
-
-            # Create unified execution context with all required fields
-            execution_context = ExecutionContext(
-                # Execution identity
-                user_id=user_id,
-                graph_id=synthetic_graph_id,
-                graph_exec_id=synthetic_graph_exec_id,
-                graph_version=1,  # Versions are 1-indexed
-                node_id=synthetic_node_id,
-                node_exec_id=synthetic_node_exec_id,
-                # Workspace with session scoping
-                workspace_id=workspace.id,
-                session_id=session.session_id,
-            )
-
-            # Prepare kwargs for block execution
-            # Keep individual kwargs for backwards compatibility with existing blocks
+            # Fetch actual credentials and prepare kwargs for block execution
+            # Create execution context with defaults (blocks may require it)
             exec_kwargs: dict[str, Any] = {
                 "user_id": user_id,
-                "execution_context": execution_context,
-                # Legacy: individual kwargs for blocks not yet using execution_context
-                "workspace_id": workspace.id,
-                "graph_exec_id": synthetic_graph_exec_id,
-                "node_exec_id": synthetic_node_exec_id,
-                "node_id": synthetic_node_id,
-                "graph_version": 1,  # Versions are 1-indexed
-                "graph_id": synthetic_graph_id,
+                "execution_context": ExecutionContext(),
             }
 
             for field_name, cred_meta in matched_credentials.items():

autogpt_platform/backend/backend/api/features/chat/tools/search_docs.py

@@ -3,6 +3,7 @@
 import logging
 from typing import Any
 
+from langfuse import observe
 from prisma.enums import ContentType
 
 from backend.api.features.chat.model import ChatSession
@@ -87,6 +88,7 @@ class SearchDocsTool(BaseTool):
         url_path = path.rsplit(".", 1)[0] if "." in path else path
         return f"{DOCS_BASE_URL}/{url_path}"
 
+    @observe(as_type="tool", name="search_docs")
     async def _execute(
         self,
         user_id: str | None,

autogpt_platform/backend/backend/api/features/chat/tools/utils.py

@@ -8,7 +8,7 @@ from backend.api.features.library import model as library_model
 from backend.api.features.store import db as store_db
 from backend.data import graph as graph_db
 from backend.data.graph import GraphModel
-from backend.data.model import CredentialsFieldInfo, CredentialsMetaInput
+from backend.data.model import CredentialsMetaInput
 from backend.integrations.creds_manager import IntegrationCredentialsManager
 from backend.util.exceptions import NotFoundError
 
@@ -89,59 +89,6 @@ def extract_credentials_from_schema(
     return credentials
 
 
-def _serialize_missing_credential(
-    field_key: str, field_info: CredentialsFieldInfo
-) -> dict[str, Any]:
-    """
-    Convert credential field info into a serializable dict that preserves all supported
-    credential types (e.g., api_key + oauth2) so the UI can offer multiple options.
-    """
-    supported_types = sorted(field_info.supported_types)
-    provider = next(iter(field_info.provider), "unknown")
-    scopes = sorted(field_info.required_scopes or [])
-
-    return {
-        "id": field_key,
-        "title": field_key.replace("_", " ").title(),
-        "provider": provider,
-        "provider_name": provider.replace("_", " ").title(),
-        "type": supported_types[0] if supported_types else "api_key",
-        "types": supported_types,
-        "scopes": scopes,
-    }
-
-
-def build_missing_credentials_from_graph(
-    graph: GraphModel, matched_credentials: dict[str, CredentialsMetaInput] | None
-) -> dict[str, Any]:
-    """
-    Build a missing_credentials mapping from a graph's aggregated credentials inputs,
-    preserving all supported credential types for each field.
-    """
-    matched_keys = set(matched_credentials.keys()) if matched_credentials else set()
-    aggregated_fields = graph.aggregate_credentials_inputs()
-
-    return {
-        field_key: _serialize_missing_credential(field_key, field_info)
-        for field_key, (field_info, _node_fields) in aggregated_fields.items()
-        if field_key not in matched_keys
-    }
-
-
-def build_missing_credentials_from_field_info(
-    credential_fields: dict[str, CredentialsFieldInfo],
-    matched_keys: set[str],
-) -> dict[str, Any]:
-    """
-    Build missing_credentials mapping from a simple credentials field info dictionary.
-    """
-    return {
-        field_key: _serialize_missing_credential(field_key, field_info)
-        for field_key, field_info in credential_fields.items()
-        if field_key not in matched_keys
-    }
-
-
 def extract_credentials_as_dict(
     credentials_input_schema: dict[str, Any] | None,
 ) -> dict[str, CredentialsMetaInput]:

autogpt_platform/backend/backend/api/features/chat/tools/workspace_files.py

@@ -1,620 +0,0 @@
-"""CoPilot tools for workspace file operations."""
-
-import base64
-import logging
-from typing import Any, Optional
-
-from pydantic import BaseModel
-
-from backend.api.features.chat.model import ChatSession
-from backend.data.workspace import get_or_create_workspace
-from backend.util.settings import Config
-from backend.util.virus_scanner import scan_content_safe
-from backend.util.workspace import WorkspaceManager
-
-from .base import BaseTool
-from .models import ErrorResponse, ResponseType, ToolResponseBase
-
-logger = logging.getLogger(__name__)
-
-
-class WorkspaceFileInfoData(BaseModel):
-    """Data model for workspace file information (not a response itself)."""
-
-    file_id: str
-    name: str
-    path: str
-    mime_type: str
-    size_bytes: int
-
-
-class WorkspaceFileListResponse(ToolResponseBase):
-    """Response containing list of workspace files."""
-
-    type: ResponseType = ResponseType.WORKSPACE_FILE_LIST
-    files: list[WorkspaceFileInfoData]
-    total_count: int
-
-
-class WorkspaceFileContentResponse(ToolResponseBase):
-    """Response containing workspace file content (legacy, for small text files)."""
-
-    type: ResponseType = ResponseType.WORKSPACE_FILE_CONTENT
-    file_id: str
-    name: str
-    path: str
-    mime_type: str
-    content_base64: str
-
-
-class WorkspaceFileMetadataResponse(ToolResponseBase):
-    """Response containing workspace file metadata and download URL (prevents context bloat)."""
-
-    type: ResponseType = ResponseType.WORKSPACE_FILE_METADATA
-    file_id: str
-    name: str
-    path: str
-    mime_type: str
-    size_bytes: int
-    download_url: str
-    preview: str | None = None  # First 500 chars for text files
-
-
-class WorkspaceWriteResponse(ToolResponseBase):
-    """Response after writing a file to workspace."""
-
-    type: ResponseType = ResponseType.WORKSPACE_FILE_WRITTEN
-    file_id: str
-    name: str
-    path: str
-    size_bytes: int
-
-
-class WorkspaceDeleteResponse(ToolResponseBase):
-    """Response after deleting a file from workspace."""
-
-    type: ResponseType = ResponseType.WORKSPACE_FILE_DELETED
-    file_id: str
-    success: bool
-
-
-class ListWorkspaceFilesTool(BaseTool):
-    """Tool for listing files in user's workspace."""
-
-    @property
-    def name(self) -> str:
-        return "list_workspace_files"
-
-    @property
-    def description(self) -> str:
-        return (
-            "List files in the user's workspace. "
-            "Returns file names, paths, sizes, and metadata. "
-            "Optionally filter by path prefix."
-        )
-
-    @property
-    def parameters(self) -> dict[str, Any]:
-        return {
-            "type": "object",
-            "properties": {
-                "path_prefix": {
-                    "type": "string",
-                    "description": (
-                        "Optional path prefix to filter files "
-                        "(e.g., '/documents/' to list only files in documents folder). "
-                        "By default, only files from the current session are listed."
-                    ),
-                },
-                "limit": {
-                    "type": "integer",
-                    "description": "Maximum number of files to return (default 50, max 100)",
-                    "minimum": 1,
-                    "maximum": 100,
-                },
-                "include_all_sessions": {
-                    "type": "boolean",
-                    "description": (
-                        "If true, list files from all sessions. "
-                        "Default is false (only current session's files)."
-                    ),
-                },
-            },
-            "required": [],
-        }
-
-    @property
-    def requires_auth(self) -> bool:
-        return True
-
-    async def _execute(
-        self,
-        user_id: str | None,
-        session: ChatSession,
-        **kwargs,
-    ) -> ToolResponseBase:
-        session_id = session.session_id
-
-        if not user_id:
-            return ErrorResponse(
-                message="Authentication required",
-                session_id=session_id,
-            )
-
-        path_prefix: Optional[str] = kwargs.get("path_prefix")
-        limit = min(kwargs.get("limit", 50), 100)
-        include_all_sessions: bool = kwargs.get("include_all_sessions", False)
-
-        try:
-            workspace = await get_or_create_workspace(user_id)
-            # Pass session_id for session-scoped file access
-            manager = WorkspaceManager(user_id, workspace.id, session_id)
-
-            files = await manager.list_files(
-                path=path_prefix,
-                limit=limit,
-                include_all_sessions=include_all_sessions,
-            )
-            total = await manager.get_file_count(
-                path=path_prefix,
-                include_all_sessions=include_all_sessions,
-            )
-
-            file_infos = [
-                WorkspaceFileInfoData(
-                    file_id=f.id,
-                    name=f.name,
-                    path=f.path,
-                    mime_type=f.mimeType,
-                    size_bytes=f.sizeBytes,
-                )
-                for f in files
-            ]
-
-            scope_msg = "all sessions" if include_all_sessions else "current session"
-            return WorkspaceFileListResponse(
-                files=file_infos,
-                total_count=total,
-                message=f"Found {len(files)} files in workspace ({scope_msg})",
-                session_id=session_id,
-            )
-
-        except Exception as e:
-            logger.error(f"Error listing workspace files: {e}", exc_info=True)
-            return ErrorResponse(
-                message=f"Failed to list workspace files: {str(e)}",
-                error=str(e),
-                session_id=session_id,
-            )
-
-
-class ReadWorkspaceFileTool(BaseTool):
-    """Tool for reading file content from workspace."""
-
-    # Size threshold for returning full content vs metadata+URL
-    # Files larger than this return metadata with download URL to prevent context bloat
-    MAX_INLINE_SIZE_BYTES = 32 * 1024  # 32KB
-    # Preview size for text files
-    PREVIEW_SIZE = 500
-
-    @property
-    def name(self) -> str:
-        return "read_workspace_file"
-
-    @property
-    def description(self) -> str:
-        return (
-            "Read a file from the user's workspace. "
-            "Specify either file_id or path to identify the file. "
-            "For small text files, returns content directly. "
-            "For large or binary files, returns metadata and a download URL. "
-            "Paths are scoped to the current session by default. "
-            "Use /sessions/<session_id>/... for cross-session access."
-        )
-
-    @property
-    def parameters(self) -> dict[str, Any]:
-        return {
-            "type": "object",
-            "properties": {
-                "file_id": {
-                    "type": "string",
-                    "description": "The file's unique ID (from list_workspace_files)",
-                },
-                "path": {
-                    "type": "string",
-                    "description": (
-                        "The virtual file path (e.g., '/documents/report.pdf'). "
-                        "Scoped to current session by default."
-                    ),
-                },
-                "force_download_url": {
-                    "type": "boolean",
-                    "description": (
-                        "If true, always return metadata+URL instead of inline content. "
-                        "Default is false (auto-selects based on file size/type)."
-                    ),
-                },
-            },
-            "required": [],  # At least one must be provided
-        }
-
-    @property
-    def requires_auth(self) -> bool:
-        return True
-
-    def _is_text_mime_type(self, mime_type: str) -> bool:
-        """Check if the MIME type is a text-based type."""
-        text_types = [
-            "text/",
-            "application/json",
-            "application/xml",
-            "application/javascript",
-            "application/x-python",
-            "application/x-sh",
-        ]
-        return any(mime_type.startswith(t) for t in text_types)
-
-    async def _execute(
-        self,
-        user_id: str | None,
-        session: ChatSession,
-        **kwargs,
-    ) -> ToolResponseBase:
-        session_id = session.session_id
-
-        if not user_id:
-            return ErrorResponse(
-                message="Authentication required",
-                session_id=session_id,
-            )
-
-        file_id: Optional[str] = kwargs.get("file_id")
-        path: Optional[str] = kwargs.get("path")
-        force_download_url: bool = kwargs.get("force_download_url", False)
-
-        if not file_id and not path:
-            return ErrorResponse(
-                message="Please provide either file_id or path",
-                session_id=session_id,
-            )
-
-        try:
-            workspace = await get_or_create_workspace(user_id)
-            # Pass session_id for session-scoped file access
-            manager = WorkspaceManager(user_id, workspace.id, session_id)
-
-            # Get file info
-            if file_id:
-                file_info = await manager.get_file_info(file_id)
-                if file_info is None:
-                    return ErrorResponse(
-                        message=f"File not found: {file_id}",
-                        session_id=session_id,
-                    )
-                target_file_id = file_id
-            else:
-                # path is guaranteed to be non-None here due to the check above
-                assert path is not None
-                file_info = await manager.get_file_info_by_path(path)
-                if file_info is None:
-                    return ErrorResponse(
-                        message=f"File not found at path: {path}",
-                        session_id=session_id,
-                    )
-                target_file_id = file_info.id
-
-            # Decide whether to return inline content or metadata+URL
-            is_small_file = file_info.sizeBytes <= self.MAX_INLINE_SIZE_BYTES
-            is_text_file = self._is_text_mime_type(file_info.mimeType)
-
-            # Return inline content for small text files (unless force_download_url)
-            if is_small_file and is_text_file and not force_download_url:
-                content = await manager.read_file_by_id(target_file_id)
-                content_b64 = base64.b64encode(content).decode("utf-8")
-
-                return WorkspaceFileContentResponse(
-                    file_id=file_info.id,
-                    name=file_info.name,
-                    path=file_info.path,
-                    mime_type=file_info.mimeType,
-                    content_base64=content_b64,
-                    message=f"Successfully read file: {file_info.name}",
-                    session_id=session_id,
-                )
-
-            # Return metadata + workspace:// reference for large or binary files
-            # This prevents context bloat (100KB file = ~133KB as base64)
-            # Use workspace:// format so frontend urlTransform can add proxy prefix
-            download_url = f"workspace://{target_file_id}"
-
-            # Generate preview for text files
-            preview: str | None = None
-            if is_text_file:
-                try:
-                    content = await manager.read_file_by_id(target_file_id)
-                    preview_text = content[: self.PREVIEW_SIZE].decode(
-                        "utf-8", errors="replace"
-                    )
-                    if len(content) > self.PREVIEW_SIZE:
-                        preview_text += "..."
-                    preview = preview_text
-                except Exception:
-                    pass  # Preview is optional
-
-            return WorkspaceFileMetadataResponse(
-                file_id=file_info.id,
-                name=file_info.name,
-                path=file_info.path,
-                mime_type=file_info.mimeType,
-                size_bytes=file_info.sizeBytes,
-                download_url=download_url,
-                preview=preview,
-                message=f"File: {file_info.name} ({file_info.sizeBytes} bytes). Use download_url to retrieve content.",
-                session_id=session_id,
-            )
-
-        except FileNotFoundError as e:
-            return ErrorResponse(
-                message=str(e),
-                session_id=session_id,
-            )
-        except Exception as e:
-            logger.error(f"Error reading workspace file: {e}", exc_info=True)
-            return ErrorResponse(
-                message=f"Failed to read workspace file: {str(e)}",
-                error=str(e),
-                session_id=session_id,
-            )
-
-
-class WriteWorkspaceFileTool(BaseTool):
-    """Tool for writing files to workspace."""
-
-    @property
-    def name(self) -> str:
-        return "write_workspace_file"
-
-    @property
-    def description(self) -> str:
-        return (
-            "Write or create a file in the user's workspace. "
-            "Provide the content as a base64-encoded string. "
-            f"Maximum file size is {Config().max_file_size_mb}MB. "
-            "Files are saved to the current session's folder by default. "
-            "Use /sessions/<session_id>/... for cross-session access."
-        )
-
-    @property
-    def parameters(self) -> dict[str, Any]:
-        return {
-            "type": "object",
-            "properties": {
-                "filename": {
-                    "type": "string",
-                    "description": "Name for the file (e.g., 'report.pdf')",
-                },
-                "content_base64": {
-                    "type": "string",
-                    "description": "Base64-encoded file content",
-                },
-                "path": {
-                    "type": "string",
-                    "description": (
-                        "Optional virtual path where to save the file "
-                        "(e.g., '/documents/report.pdf'). "
-                        "Defaults to '/{filename}'. Scoped to current session."
-                    ),
-                },
-                "mime_type": {
-                    "type": "string",
-                    "description": (
-                        "Optional MIME type of the file. "
-                        "Auto-detected from filename if not provided."
-                    ),
-                },
-                "overwrite": {
-                    "type": "boolean",
-                    "description": "Whether to overwrite if file exists at path (default: false)",
-                },
-            },
-            "required": ["filename", "content_base64"],
-        }
-
-    @property
-    def requires_auth(self) -> bool:
-        return True
-
-    async def _execute(
-        self,
-        user_id: str | None,
-        session: ChatSession,
-        **kwargs,
-    ) -> ToolResponseBase:
-        session_id = session.session_id
-
-        if not user_id:
-            return ErrorResponse(
-                message="Authentication required",
-                session_id=session_id,
-            )
-
-        filename: str = kwargs.get("filename", "")
-        content_b64: str = kwargs.get("content_base64", "")
-        path: Optional[str] = kwargs.get("path")
-        mime_type: Optional[str] = kwargs.get("mime_type")
-        overwrite: bool = kwargs.get("overwrite", False)
-
-        if not filename:
-            return ErrorResponse(
-                message="Please provide a filename",
-                session_id=session_id,
-            )
-
-        if not content_b64:
-            return ErrorResponse(
-                message="Please provide content_base64",
-                session_id=session_id,
-            )
-
-        # Decode content
-        try:
-            content = base64.b64decode(content_b64)
-        except Exception:
-            return ErrorResponse(
-                message="Invalid base64-encoded content",
-                session_id=session_id,
-            )
-
-        # Check size
-        max_file_size = Config().max_file_size_mb * 1024 * 1024
-        if len(content) > max_file_size:
-            return ErrorResponse(
-                message=f"File too large. Maximum size is {Config().max_file_size_mb}MB",
-                session_id=session_id,
-            )
-
-        try:
-            # Virus scan
-            await scan_content_safe(content, filename=filename)
-
-            workspace = await get_or_create_workspace(user_id)
-            # Pass session_id for session-scoped file access
-            manager = WorkspaceManager(user_id, workspace.id, session_id)
-
-            file_record = await manager.write_file(
-                content=content,
-                filename=filename,
-                path=path,
-                mime_type=mime_type,
-                overwrite=overwrite,
-            )
-
-            return WorkspaceWriteResponse(
-                file_id=file_record.id,
-                name=file_record.name,
-                path=file_record.path,
-                size_bytes=file_record.sizeBytes,
-                message=f"Successfully wrote file: {file_record.name}",
-                session_id=session_id,
-            )
-
-        except ValueError as e:
-            return ErrorResponse(
-                message=str(e),
-                session_id=session_id,
-            )
-        except Exception as e:
-            logger.error(f"Error writing workspace file: {e}", exc_info=True)
-            return ErrorResponse(
-                message=f"Failed to write workspace file: {str(e)}",
-                error=str(e),
-                session_id=session_id,
-            )
-
-
-class DeleteWorkspaceFileTool(BaseTool):
-    """Tool for deleting files from workspace."""
-
-    @property
-    def name(self) -> str:
-        return "delete_workspace_file"
-
-    @property
-    def description(self) -> str:
-        return (
-            "Delete a file from the user's workspace. "
-            "Specify either file_id or path to identify the file. "
-            "Paths are scoped to the current session by default. "
-            "Use /sessions/<session_id>/... for cross-session access."
-        )
-
-    @property
-    def parameters(self) -> dict[str, Any]:
-        return {
-            "type": "object",
-            "properties": {
-                "file_id": {
-                    "type": "string",
-                    "description": "The file's unique ID (from list_workspace_files)",
-                },
-                "path": {
-                    "type": "string",
-                    "description": (
-                        "The virtual file path (e.g., '/documents/report.pdf'). "
-                        "Scoped to current session by default."
-                    ),
-                },
-            },
-            "required": [],  # At least one must be provided
-        }
-
-    @property
-    def requires_auth(self) -> bool:
-        return True
-
-    async def _execute(
-        self,
-        user_id: str | None,
-        session: ChatSession,
-        **kwargs,
-    ) -> ToolResponseBase:
-        session_id = session.session_id
-
-        if not user_id:
-            return ErrorResponse(
-                message="Authentication required",
-                session_id=session_id,
-            )
-
-        file_id: Optional[str] = kwargs.get("file_id")
-        path: Optional[str] = kwargs.get("path")
-
-        if not file_id and not path:
-            return ErrorResponse(
-                message="Please provide either file_id or path",
-                session_id=session_id,
-            )
-
-        try:
-            workspace = await get_or_create_workspace(user_id)
-            # Pass session_id for session-scoped file access
-            manager = WorkspaceManager(user_id, workspace.id, session_id)
-
-            # Determine the file_id to delete
-            target_file_id: str
-            if file_id:
-                target_file_id = file_id
-            else:
-                # path is guaranteed to be non-None here due to the check above
-                assert path is not None
-                file_info = await manager.get_file_info_by_path(path)
-                if file_info is None:
-                    return ErrorResponse(
-                        message=f"File not found at path: {path}",
-                        session_id=session_id,
-                    )
-                target_file_id = file_info.id
-
-            success = await manager.delete_file(target_file_id)
-
-            if not success:
-                return ErrorResponse(
-                    message=f"File not found: {target_file_id}",
-                    session_id=session_id,
-                )
-
-            return WorkspaceDeleteResponse(
-                file_id=target_file_id,
-                success=True,
-                message="File deleted successfully",
-                session_id=session_id,
-            )
-
-        except Exception as e:
-            logger.error(f"Error deleting workspace file: {e}", exc_info=True)
-            return ErrorResponse(
-                message=f"Failed to delete workspace file: {str(e)}",
-                error=str(e),
-                session_id=session_id,
-            )

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

@@ -1,250 +0,0 @@
-"""PostHog analytics tracking for the chat system."""
-
-import atexit
-import logging
-from typing import Any
-
-from posthog import Posthog
-
-from backend.util.settings import Settings
-
-logger = logging.getLogger(__name__)
-settings = Settings()
-
-# PostHog client instance (lazily initialized)
-_posthog_client: Posthog | None = None
-
-
-def _shutdown_posthog() -> None:
-    """Flush and shutdown PostHog client on process exit."""
-    if _posthog_client is not None:
-        _posthog_client.flush()
-        _posthog_client.shutdown()
-
-
-atexit.register(_shutdown_posthog)
-
-
-def _get_posthog_client() -> Posthog | None:
-    """Get or create the PostHog client instance."""
-    global _posthog_client
-    if _posthog_client is not None:
-        return _posthog_client
-
-    if not settings.secrets.posthog_api_key:
-        logger.debug("PostHog API key not configured, analytics disabled")
-        return None
-
-    _posthog_client = Posthog(
-        settings.secrets.posthog_api_key,
-        host=settings.secrets.posthog_host,
-    )
-    logger.info(
-        f"PostHog client initialized with host: {settings.secrets.posthog_host}"
-    )
-    return _posthog_client
-
-
-def _get_base_properties() -> dict[str, Any]:
-    """Get base properties included in all events."""
-    return {
-        "environment": settings.config.app_env.value,
-        "source": "chat_copilot",
-    }
-
-
-def track_user_message(
-    user_id: str | None,
-    session_id: str,
-    message_length: int,
-) -> None:
-    """Track when a user sends a message in chat.
-
-    Args:
-        user_id: The user's ID (or None for anonymous)
-        session_id: The chat session ID
-        message_length: Length of the user's message
-    """
-    client = _get_posthog_client()
-    if not client:
-        return
-
-    try:
-        properties = {
-            **_get_base_properties(),
-            "session_id": session_id,
-            "message_length": message_length,
-        }
-        client.capture(
-            distinct_id=user_id or f"anonymous_{session_id}",
-            event="copilot_message_sent",
-            properties=properties,
-        )
-    except Exception as e:
-        logger.warning(f"Failed to track user message: {e}")
-
-
-def track_tool_called(
-    user_id: str | None,
-    session_id: str,
-    tool_name: str,
-    tool_call_id: str,
-) -> None:
-    """Track when a tool is called in chat.
-
-    Args:
-        user_id: The user's ID (or None for anonymous)
-        session_id: The chat session ID
-        tool_name: Name of the tool being called
-        tool_call_id: Unique ID of the tool call
-    """
-    client = _get_posthog_client()
-    if not client:
-        logger.info("PostHog client not available for tool tracking")
-        return
-
-    try:
-        properties = {
-            **_get_base_properties(),
-            "session_id": session_id,
-            "tool_name": tool_name,
-            "tool_call_id": tool_call_id,
-        }
-        distinct_id = user_id or f"anonymous_{session_id}"
-        logger.info(
-            f"Sending copilot_tool_called event to PostHog: distinct_id={distinct_id}, "
-            f"tool_name={tool_name}"
-        )
-        client.capture(
-            distinct_id=distinct_id,
-            event="copilot_tool_called",
-            properties=properties,
-        )
-    except Exception as e:
-        logger.warning(f"Failed to track tool call: {e}")
-
-
-def track_agent_run_success(
-    user_id: str,
-    session_id: str,
-    graph_id: str,
-    graph_name: str,
-    execution_id: str,
-    library_agent_id: str,
-) -> None:
-    """Track when an agent is successfully run.
-
-    Args:
-        user_id: The user's ID
-        session_id: The chat session ID
-        graph_id: ID of the agent graph
-        graph_name: Name of the agent
-        execution_id: ID of the execution
-        library_agent_id: ID of the library agent
-    """
-    client = _get_posthog_client()
-    if not client:
-        return
-
-    try:
-        properties = {
-            **_get_base_properties(),
-            "session_id": session_id,
-            "graph_id": graph_id,
-            "graph_name": graph_name,
-            "execution_id": execution_id,
-            "library_agent_id": library_agent_id,
-        }
-        client.capture(
-            distinct_id=user_id,
-            event="copilot_agent_run_success",
-            properties=properties,
-        )
-    except Exception as e:
-        logger.warning(f"Failed to track agent run: {e}")
-
-
-def track_agent_scheduled(
-    user_id: str,
-    session_id: str,
-    graph_id: str,
-    graph_name: str,
-    schedule_id: str,
-    schedule_name: str,
-    cron: str,
-    library_agent_id: str,
-) -> None:
-    """Track when an agent is successfully scheduled.
-
-    Args:
-        user_id: The user's ID
-        session_id: The chat session ID
-        graph_id: ID of the agent graph
-        graph_name: Name of the agent
-        schedule_id: ID of the schedule
-        schedule_name: Name of the schedule
-        cron: Cron expression for the schedule
-        library_agent_id: ID of the library agent
-    """
-    client = _get_posthog_client()
-    if not client:
-        return
-
-    try:
-        properties = {
-            **_get_base_properties(),
-            "session_id": session_id,
-            "graph_id": graph_id,
-            "graph_name": graph_name,
-            "schedule_id": schedule_id,
-            "schedule_name": schedule_name,
-            "cron": cron,
-            "library_agent_id": library_agent_id,
-        }
-        client.capture(
-            distinct_id=user_id,
-            event="copilot_agent_scheduled",
-            properties=properties,
-        )
-    except Exception as e:
-        logger.warning(f"Failed to track agent schedule: {e}")
-
-
-def track_trigger_setup(
-    user_id: str,
-    session_id: str,
-    graph_id: str,
-    graph_name: str,
-    trigger_type: str,
-    library_agent_id: str,
-) -> None:
-    """Track when a trigger is set up for an agent.
-
-    Args:
-        user_id: The user's ID
-        session_id: The chat session ID
-        graph_id: ID of the agent graph
-        graph_name: Name of the agent
-        trigger_type: Type of trigger (e.g., 'webhook')
-        library_agent_id: ID of the library agent
-    """
-    client = _get_posthog_client()
-    if not client:
-        return
-
-    try:
-        properties = {
-            **_get_base_properties(),
-            "session_id": session_id,
-            "graph_id": graph_id,
-            "graph_name": graph_name,
-            "trigger_type": trigger_type,
-            "library_agent_id": library_agent_id,
-        }
-        client.capture(
-            distinct_id=user_id,
-            event="copilot_trigger_setup",
-            properties=properties,
-        )
-    except Exception as e:
-        logger.warning(f"Failed to track trigger setup: {e}")

autogpt_platform/backend/backend/api/features/executions/review/model.py

@@ -23,7 +23,6 @@ class PendingHumanReviewModel(BaseModel):
         id: Unique identifier for the review record
         user_id: ID of the user who must perform the review
         node_exec_id: ID of the node execution that created this review
-        node_id: ID of the node definition (for grouping reviews from same node)
         graph_exec_id: ID of the graph execution containing the node
         graph_id: ID of the graph template being executed
         graph_version: Version number of the graph template
@@ -38,10 +37,6 @@ class PendingHumanReviewModel(BaseModel):
     """
 
     node_exec_id: str = Field(description="Node execution ID (primary key)")
-    node_id: str = Field(
-        description="Node definition ID (for grouping)",
-        default="",  # Temporary default for test compatibility
-    )
     user_id: str = Field(description="User ID associated with the review")
     graph_exec_id: str = Field(description="Graph execution ID")
     graph_id: str = Field(description="Graph ID")
@@ -71,9 +66,7 @@ class PendingHumanReviewModel(BaseModel):
     )
 
     @classmethod
-    def from_db(
-        cls, review: "PendingHumanReview", node_id: str
-    ) -> "PendingHumanReviewModel":
+    def from_db(cls, review: "PendingHumanReview") -> "PendingHumanReviewModel":
         """
         Convert a database model to a response model.
 
@@ -81,14 +74,9 @@ class PendingHumanReviewModel(BaseModel):
         payload, instructions, and editable flag.
 
         Handles invalid data gracefully by using safe defaults.
-
-        Args:
-            review: Database review object
-            node_id: Node definition ID (fetched from NodeExecution)
         """
         return cls(
             node_exec_id=review.nodeExecId,
-            node_id=node_id,
             user_id=review.userId,
             graph_exec_id=review.graphExecId,
             graph_id=review.graphId,
@@ -119,13 +107,6 @@ class ReviewItem(BaseModel):
     reviewed_data: SafeJsonData | None = Field(
         None, description="Optional edited data (ignored if approved=False)"
     )
-    auto_approve_future: bool = Field(
-        default=False,
-        description=(
-            "If true and this review is approved, future executions of this same "
-            "block (node) will be automatically approved. This only affects approved reviews."
-        ),
-    )
 
     @field_validator("reviewed_data")
     @classmethod
@@ -193,9 +174,6 @@ class ReviewRequest(BaseModel):
     This request must include ALL pending reviews for a graph execution.
     Each review will be either approved (with optional data modifications)
     or rejected (data ignored). The execution will resume only after ALL reviews are processed.
-
-    Each review item can individually specify whether to auto-approve future executions
-    of the same block via the `auto_approve_future` field on ReviewItem.
     """
 
     reviews: List[ReviewItem] = Field(

autogpt_platform/backend/backend/api/features/executions/review/routes.py

@@ -1,27 +1,17 @@
-import asyncio
 import logging
-from typing import Any, List
+from typing import List
 
 import autogpt_libs.auth as autogpt_auth_lib
 from fastapi import APIRouter, HTTPException, Query, Security, status
 from prisma.enums import ReviewStatus
 
-from backend.data.execution import (
-    ExecutionContext,
-    ExecutionStatus,
-    get_graph_execution_meta,
-)
-from backend.data.graph import get_graph_settings
+from backend.data.execution import get_graph_execution_meta
 from backend.data.human_review import (
-    create_auto_approval_record,
     get_pending_reviews_for_execution,
     get_pending_reviews_for_user,
-    get_reviews_by_node_exec_ids,
     has_pending_reviews_for_graph_exec,
     process_all_reviews_for_execution,
 )
-from backend.data.model import USER_TIMEZONE_NOT_SET
-from backend.data.user import get_user_by_id
 from backend.executor.utils import add_graph_execution
 
 from .model import PendingHumanReviewModel, ReviewRequest, ReviewResponse
@@ -137,70 +127,17 @@ async def process_review_action(
             detail="At least one review must be provided",
         )
 
-    # Batch fetch all requested reviews (regardless of status for idempotent handling)
-    reviews_map = await get_reviews_by_node_exec_ids(
-        list(all_request_node_ids), user_id
-    )
-
-    # Validate all reviews were found (must exist, any status is OK for now)
-    missing_ids = all_request_node_ids - set(reviews_map.keys())
-    if missing_ids:
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail=f"Review(s) not found: {', '.join(missing_ids)}",
-        )
-
-    # Validate all reviews belong to the same execution
-    graph_exec_ids = {review.graph_exec_id for review in reviews_map.values()}
-    if len(graph_exec_ids) > 1:
-        raise HTTPException(
-            status_code=status.HTTP_409_CONFLICT,
-            detail="All reviews in a single request must belong to the same execution.",
-        )
-
-    graph_exec_id = next(iter(graph_exec_ids))
-
-    # Validate execution status before processing reviews
-    graph_exec_meta = await get_graph_execution_meta(
-        user_id=user_id, execution_id=graph_exec_id
-    )
-
-    if not graph_exec_meta:
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail=f"Graph execution #{graph_exec_id} not found",
-        )
-
-    # Only allow processing reviews if execution is paused for review
-    # or incomplete (partial execution with some reviews already processed)
-    if graph_exec_meta.status not in (
-        ExecutionStatus.REVIEW,
-        ExecutionStatus.INCOMPLETE,
-    ):
-        raise HTTPException(
-            status_code=status.HTTP_409_CONFLICT,
-            detail=f"Cannot process reviews while execution status is {graph_exec_meta.status}. "
-            f"Reviews can only be processed when execution is paused (REVIEW status). "
-            f"Current status: {graph_exec_meta.status}",
-        )
-
-    # Build review decisions map and track which reviews requested auto-approval
-    # Auto-approved reviews use original data (no modifications allowed)
+    # Build review decisions map
     review_decisions = {}
-    auto_approve_requests = {}  # Map node_exec_id -> auto_approve_future flag
-
     for review in request.reviews:
         review_status = (
             ReviewStatus.APPROVED if review.approved else ReviewStatus.REJECTED
         )
-        # If this review requested auto-approval, don't allow data modifications
-        reviewed_data = None if review.auto_approve_future else review.reviewed_data
         review_decisions[review.node_exec_id] = (
             review_status,
-            reviewed_data,
+            review.reviewed_data,
             review.message,
         )
-        auto_approve_requests[review.node_exec_id] = review.auto_approve_future
 
     # Process all reviews
     updated_reviews = await process_all_reviews_for_execution(
@@ -208,87 +145,6 @@ async def process_review_action(
         review_decisions=review_decisions,
     )
 
-    # Create auto-approval records for approved reviews that requested it
-    # Deduplicate by node_id to avoid race conditions when multiple reviews
-    # for the same node are processed in parallel
-    async def create_auto_approval_for_node(
-        node_id: str, review_result
-    ) -> tuple[str, bool]:
-        """
-        Create auto-approval record for a node.
-        Returns (node_id, success) tuple for tracking failures.
-        """
-        try:
-            await create_auto_approval_record(
-                user_id=user_id,
-                graph_exec_id=review_result.graph_exec_id,
-                graph_id=review_result.graph_id,
-                graph_version=review_result.graph_version,
-                node_id=node_id,
-                payload=review_result.payload,
-            )
-            return (node_id, True)
-        except Exception as e:
-            logger.error(
-                f"Failed to create auto-approval record for node {node_id}",
-                exc_info=e,
-            )
-            return (node_id, False)
-
-    # Collect node_exec_ids that need auto-approval
-    node_exec_ids_needing_auto_approval = [
-        node_exec_id
-        for node_exec_id, review_result in updated_reviews.items()
-        if review_result.status == ReviewStatus.APPROVED
-        and auto_approve_requests.get(node_exec_id, False)
-    ]
-
-    # Batch-fetch node executions to get node_ids
-    nodes_needing_auto_approval: dict[str, Any] = {}
-    if node_exec_ids_needing_auto_approval:
-        from backend.data.execution import get_node_executions
-
-        node_execs = await get_node_executions(
-            graph_exec_id=graph_exec_id, include_exec_data=False
-        )
-        node_exec_map = {node_exec.node_exec_id: node_exec for node_exec in node_execs}
-
-        for node_exec_id in node_exec_ids_needing_auto_approval:
-            node_exec = node_exec_map.get(node_exec_id)
-            if node_exec:
-                review_result = updated_reviews[node_exec_id]
-                # Use the first approved review for this node (deduplicate by node_id)
-                if node_exec.node_id not in nodes_needing_auto_approval:
-                    nodes_needing_auto_approval[node_exec.node_id] = review_result
-            else:
-                logger.error(
-                    f"Failed to create auto-approval record for {node_exec_id}: "
-                    f"Node execution not found. This may indicate a race condition "
-                    f"or data inconsistency."
-                )
-
-    # Execute all auto-approval creations in parallel (deduplicated by node_id)
-    auto_approval_results = await asyncio.gather(
-        *[
-            create_auto_approval_for_node(node_id, review_result)
-            for node_id, review_result in nodes_needing_auto_approval.items()
-        ],
-        return_exceptions=True,
-    )
-
-    # Count auto-approval failures
-    auto_approval_failed_count = 0
-    for result in auto_approval_results:
-        if isinstance(result, Exception):
-            # Unexpected exception during auto-approval creation
-            auto_approval_failed_count += 1
-            logger.error(
-                f"Unexpected exception during auto-approval creation: {result}"
-            )
-        elif isinstance(result, tuple) and len(result) == 2 and not result[1]:
-            # Auto-approval creation failed (returned False)
-            auto_approval_failed_count += 1
-
     # Count results
     approved_count = sum(
         1
@@ -301,53 +157,30 @@ async def process_review_action(
         if review.status == ReviewStatus.REJECTED
     )
 
-    # Resume execution only if ALL pending reviews for this execution have been processed
+    # Resume execution if we processed some reviews
     if updated_reviews:
+        # Get graph execution ID from any processed review
+        first_review = next(iter(updated_reviews.values()))
+        graph_exec_id = first_review.graph_exec_id
+
+        # Check if any pending reviews remain for this execution
         still_has_pending = await has_pending_reviews_for_graph_exec(graph_exec_id)
 
         if not still_has_pending:
-            # Get the graph_id from any processed review
-            first_review = next(iter(updated_reviews.values()))
-
+            # Resume execution
             try:
-                # Fetch user and settings to build complete execution context
-                user = await get_user_by_id(user_id)
-                settings = await get_graph_settings(
-                    user_id=user_id, graph_id=first_review.graph_id
-                )
-
-                # Preserve user's timezone preference when resuming execution
-                user_timezone = (
-                    user.timezone if user.timezone != USER_TIMEZONE_NOT_SET else "UTC"
-                )
-
-                execution_context = ExecutionContext(
-                    human_in_the_loop_safe_mode=settings.human_in_the_loop_safe_mode,
-                    sensitive_action_safe_mode=settings.sensitive_action_safe_mode,
-                    user_timezone=user_timezone,
-                )
-
                 await add_graph_execution(
                     graph_id=first_review.graph_id,
                     user_id=user_id,
                     graph_exec_id=graph_exec_id,
-                    execution_context=execution_context,
                 )
                 logger.info(f"Resumed execution {graph_exec_id}")
             except Exception as e:
                 logger.error(f"Failed to resume execution {graph_exec_id}: {str(e)}")
 
-    # Build error message if auto-approvals failed
-    error_message = None
-    if auto_approval_failed_count > 0:
-        error_message = (
-            f"{auto_approval_failed_count} auto-approval setting(s) could not be saved. "
-            f"You may need to manually approve these reviews in future executions."
-        )
-
     return ReviewResponse(
         approved_count=approved_count,
         rejected_count=rejected_count,
-        failed_count=auto_approval_failed_count,
-        error=error_message,
+        failed_count=0,
+        error=None,
     )

autogpt_platform/backend/backend/api/features/library/db.py

@@ -21,7 +21,7 @@ from backend.data.model import CredentialsMetaInput
 from backend.integrations.creds_manager import IntegrationCredentialsManager
 from backend.integrations.webhooks.graph_lifecycle_hooks import on_graph_activate
 from backend.util.clients import get_scheduler_client
-from backend.util.exceptions import DatabaseError, InvalidInputError, NotFoundError
+from backend.util.exceptions import DatabaseError, NotFoundError
 from backend.util.json import SafeJson
 from backend.util.models import Pagination
 from backend.util.settings import Config
@@ -64,11 +64,11 @@ async def list_library_agents(
 
     if page < 1 or page_size < 1:
         logger.warning(f"Invalid pagination: page={page}, page_size={page_size}")
-        raise InvalidInputError("Invalid pagination input")
+        raise DatabaseError("Invalid pagination input")
 
     if search_term and len(search_term.strip()) > 100:
         logger.warning(f"Search term too long: {repr(search_term)}")
-        raise InvalidInputError("Search term is too long")
+        raise DatabaseError("Search term is too long")
 
     where_clause: prisma.types.LibraryAgentWhereInput = {
         "userId": user_id,
@@ -175,7 +175,7 @@ async def list_favorite_library_agents(
 
     if page < 1 or page_size < 1:
         logger.warning(f"Invalid pagination: page={page}, page_size={page_size}")
-        raise InvalidInputError("Invalid pagination input")
+        raise DatabaseError("Invalid pagination input")
 
     where_clause: prisma.types.LibraryAgentWhereInput = {
         "userId": user_id,
@@ -401,11 +401,27 @@ async def add_generated_agent_image(
     )
 
 
+def _initialize_graph_settings(graph: graph_db.GraphModel) -> GraphSettings:
+    """
+    Initialize GraphSettings based on graph content.
+
+    Args:
+        graph: The graph to analyze
+
+    Returns:
+        GraphSettings with appropriate human_in_the_loop_safe_mode value
+    """
+    if graph.has_human_in_the_loop:
+        # Graph has HITL blocks - set safe mode to True by default
+        return GraphSettings(human_in_the_loop_safe_mode=True)
+    else:
+        # Graph has no HITL blocks - keep None
+        return GraphSettings(human_in_the_loop_safe_mode=None)
+
+
 async def create_library_agent(
     graph: graph_db.GraphModel,
     user_id: str,
-    hitl_safe_mode: bool = True,
-    sensitive_action_safe_mode: bool = False,
     create_library_agents_for_sub_graphs: bool = True,
 ) -> list[library_model.LibraryAgent]:
     """
@@ -414,8 +430,6 @@ async def create_library_agent(
     Args:
         agent: The agent/Graph to add to the library.
         user_id: The user to whom the agent will be added.
-        hitl_safe_mode: Whether HITL blocks require manual review (default True).
-        sensitive_action_safe_mode: Whether sensitive action blocks require review.
         create_library_agents_for_sub_graphs: If True, creates LibraryAgent records for sub-graphs as well.
 
     Returns:
@@ -451,11 +465,7 @@ async def create_library_agent(
                             }
                         },
                         settings=SafeJson(
-                            GraphSettings.from_graph(
-                                graph_entry,
-                                hitl_safe_mode=hitl_safe_mode,
-                                sensitive_action_safe_mode=sensitive_action_safe_mode,
-                            ).model_dump()
+                            _initialize_graph_settings(graph_entry).model_dump()
                         ),
                     ),
                     include=library_agent_include(
@@ -583,13 +593,7 @@ async def update_library_agent(
             )
         update_fields["isDeleted"] = is_deleted
     if settings is not None:
-        existing_agent = await get_library_agent(id=library_agent_id, user_id=user_id)
-        current_settings_dict = (
-            existing_agent.settings.model_dump() if existing_agent.settings else {}
-        )
-        new_settings = settings.model_dump(exclude_unset=True)
-        merged_settings = {**current_settings_dict, **new_settings}
-        update_fields["settings"] = SafeJson(merged_settings)
+        update_fields["settings"] = SafeJson(settings.model_dump())
 
     try:
         # If graph_version is provided, update to that specific version
@@ -623,6 +627,33 @@ async def update_library_agent(
         raise DatabaseError("Failed to update library agent") from e
 
 
+async def update_library_agent_settings(
+    user_id: str,
+    agent_id: str,
+    settings: GraphSettings,
+) -> library_model.LibraryAgent:
+    """
+    Updates the settings for a specific LibraryAgent.
+
+    Args:
+        user_id: The owner of the LibraryAgent.
+        agent_id: The ID of the LibraryAgent to update.
+        settings: New GraphSettings to apply.
+
+    Returns:
+        The updated LibraryAgent.
+
+    Raises:
+        NotFoundError: If the specified LibraryAgent does not exist.
+        DatabaseError: If there's an error in the update operation.
+    """
+    return await update_library_agent(
+        library_agent_id=agent_id,
+        user_id=user_id,
+        settings=settings,
+    )
+
+
 async def delete_library_agent(
     library_agent_id: str, user_id: str, soft_delete: bool = True
 ) -> None:
@@ -807,7 +838,7 @@ async def add_store_agent_to_library(
                 "isCreatedByUser": False,
                 "useGraphIsActiveVersion": False,
                 "settings": SafeJson(
-                    GraphSettings.from_graph(graph_model).model_dump()
+                    _initialize_graph_settings(graph_model).model_dump()
                 ),
             },
             include=library_agent_include(
@@ -1197,15 +1228,8 @@ async def fork_library_agent(
         )
         new_graph = await on_graph_activate(new_graph, user_id=user_id)
 
-        # Create a library agent for the new graph, preserving safe mode settings
-        return (
-            await create_library_agent(
-                new_graph,
-                user_id,
-                hitl_safe_mode=original_agent.settings.human_in_the_loop_safe_mode,
-                sensitive_action_safe_mode=original_agent.settings.sensitive_action_safe_mode,
-            )
-        )[0]
+        # Create a library agent for the new graph
+        return (await create_library_agent(new_graph, user_id))[0]
     except prisma.errors.PrismaError as e:
         logger.error(f"Database error cloning library agent: {e}")
         raise DatabaseError("Failed to fork library agent") from e

autogpt_platform/backend/backend/api/features/library/model.py

@@ -73,12 +73,6 @@ class LibraryAgent(pydantic.BaseModel):
     has_external_trigger: bool = pydantic.Field(
         description="Whether the agent has an external trigger (e.g. webhook) node"
     )
-    has_human_in_the_loop: bool = pydantic.Field(
-        description="Whether the agent has human-in-the-loop blocks"
-    )
-    has_sensitive_action: bool = pydantic.Field(
-        description="Whether the agent has sensitive action blocks"
-    )
     trigger_setup_info: Optional[GraphTriggerInfo] = None
 
     # Indicates whether there's a new output (based on recent runs)
@@ -186,8 +180,6 @@ class LibraryAgent(pydantic.BaseModel):
                 graph.credentials_input_schema if sub_graphs is not None else None
             ),
             has_external_trigger=graph.has_external_trigger,
-            has_human_in_the_loop=graph.has_human_in_the_loop,
-            has_sensitive_action=graph.has_sensitive_action,
             trigger_setup_info=graph.trigger_setup_info,
             new_output=new_output,
             can_access_graph=can_access_graph,

autogpt_platform/backend/backend/api/features/library/routes/agents.py

@@ -1,3 +1,4 @@
+import logging
 from typing import Literal, Optional
 
 import autogpt_libs.auth as autogpt_auth_lib
@@ -5,11 +6,15 @@ from fastapi import APIRouter, Body, HTTPException, Query, Security, status
 from fastapi.responses import Response
 from prisma.enums import OnboardingStep
 
+import backend.api.features.store.exceptions as store_exceptions
 from backend.data.onboarding import complete_onboarding_step
+from backend.util.exceptions import DatabaseError, NotFoundError
 
 from .. import db as library_db
 from .. import model as library_model
 
+logger = logging.getLogger(__name__)
+
 router = APIRouter(
     prefix="/agents",
     tags=["library", "private"],
@@ -21,6 +26,10 @@ router = APIRouter(
     "",
     summary="List Library Agents",
     response_model=library_model.LibraryAgentResponse,
+    responses={
+        200: {"description": "List of library agents"},
+        500: {"description": "Server error", "content": {"application/json": {}}},
+    },
 )
 async def list_library_agents(
     user_id: str = Security(autogpt_auth_lib.get_user_id),
@@ -44,19 +53,43 @@ async def list_library_agents(
 ) -> library_model.LibraryAgentResponse:
     """
     Get all agents in the user's library (both created and saved).
+
+    Args:
+        user_id: ID of the authenticated user.
+        search_term: Optional search term to filter agents by name/description.
+        filter_by: List of filters to apply (favorites, created by user).
+        sort_by: List of sorting criteria (created date, updated date).
+        page: Page number to retrieve.
+        page_size: Number of agents per page.
+
+    Returns:
+        A LibraryAgentResponse containing agents and pagination metadata.
+
+    Raises:
+        HTTPException: If a server/database error occurs.
     """
-    return await library_db.list_library_agents(
-        user_id=user_id,
-        search_term=search_term,
-        sort_by=sort_by,
-        page=page,
-        page_size=page_size,
-    )
+    try:
+        return await library_db.list_library_agents(
+            user_id=user_id,
+            search_term=search_term,
+            sort_by=sort_by,
+            page=page,
+            page_size=page_size,
+        )
+    except Exception as e:
+        logger.error(f"Could not list library agents for user #{user_id}: {e}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=str(e),
+        ) from e
 
 
 @router.get(
     "/favorites",
     summary="List Favorite Library Agents",
+    responses={
+        500: {"description": "Server error", "content": {"application/json": {}}},
+    },
 )
 async def list_favorite_library_agents(
     user_id: str = Security(autogpt_auth_lib.get_user_id),
@@ -73,12 +106,30 @@ async def list_favorite_library_agents(
 ) -> library_model.LibraryAgentResponse:
     """
     Get all favorite agents in the user's library.
+
+    Args:
+        user_id: ID of the authenticated user.
+        page: Page number to retrieve.
+        page_size: Number of agents per page.
+
+    Returns:
+        A LibraryAgentResponse containing favorite agents and pagination metadata.
+
+    Raises:
+        HTTPException: If a server/database error occurs.
     """
-    return await library_db.list_favorite_library_agents(
-        user_id=user_id,
-        page=page,
-        page_size=page_size,
-    )
+    try:
+        return await library_db.list_favorite_library_agents(
+            user_id=user_id,
+            page=page,
+            page_size=page_size,
+        )
+    except Exception as e:
+        logger.error(f"Could not list favorite library agents for user #{user_id}: {e}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=str(e),
+        ) from e
 
 
 @router.get("/{library_agent_id}", summary="Get Library Agent")
@@ -111,6 +162,10 @@ async def get_library_agent_by_graph_id(
     summary="Get Agent By Store ID",
     tags=["store", "library"],
     response_model=library_model.LibraryAgent | None,
+    responses={
+        200: {"description": "Library agent found"},
+        404: {"description": "Agent not found"},
+    },
 )
 async def get_library_agent_by_store_listing_version_id(
     store_listing_version_id: str,
@@ -119,15 +174,32 @@ async def get_library_agent_by_store_listing_version_id(
     """
     Get Library Agent from Store Listing Version ID.
     """
-    return await library_db.get_library_agent_by_store_version_id(
-        store_listing_version_id, user_id
-    )
+    try:
+        return await library_db.get_library_agent_by_store_version_id(
+            store_listing_version_id, user_id
+        )
+    except NotFoundError as e:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=str(e),
+        )
+    except Exception as e:
+        logger.error(f"Could not fetch library agent from store version ID: {e}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=str(e),
+        ) from e
 
 
 @router.post(
     "",
     summary="Add Marketplace Agent",
     status_code=status.HTTP_201_CREATED,
+    responses={
+        201: {"description": "Agent added successfully"},
+        404: {"description": "Store listing version not found"},
+        500: {"description": "Server error"},
+    },
 )
 async def add_marketplace_agent_to_library(
     store_listing_version_id: str = Body(embed=True),
@@ -138,19 +210,59 @@ async def add_marketplace_agent_to_library(
 ) -> library_model.LibraryAgent:
     """
     Add an agent from the marketplace to the user's library.
+
+    Args:
+        store_listing_version_id: ID of the store listing version to add.
+        user_id: ID of the authenticated user.
+
+    Returns:
+        library_model.LibraryAgent: Agent added to the library
+
+    Raises:
+        HTTPException(404): If the listing version is not found.
+        HTTPException(500): If a server/database error occurs.
     """
-    agent = await library_db.add_store_agent_to_library(
-        store_listing_version_id=store_listing_version_id,
-        user_id=user_id,
-    )
-    if source != "onboarding":
-        await complete_onboarding_step(user_id, OnboardingStep.MARKETPLACE_ADD_AGENT)
-    return agent
+    try:
+        agent = await library_db.add_store_agent_to_library(
+            store_listing_version_id=store_listing_version_id,
+            user_id=user_id,
+        )
+        if source != "onboarding":
+            await complete_onboarding_step(
+                user_id, OnboardingStep.MARKETPLACE_ADD_AGENT
+            )
+        return agent
+
+    except store_exceptions.AgentNotFoundError as e:
+        logger.warning(
+            f"Could not find store listing version {store_listing_version_id} "
+            "to add to library"
+        )
+        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=str(e))
+    except DatabaseError as e:
+        logger.error(f"Database error while adding agent to library: {e}", e)
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail={"message": str(e), "hint": "Inspect DB logs for details."},
+        ) from e
+    except Exception as e:
+        logger.error(f"Unexpected error while adding agent to library: {e}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail={
+                "message": str(e),
+                "hint": "Check server logs for more information.",
+            },
+        ) from e
 
 
 @router.patch(
     "/{library_agent_id}",
     summary="Update Library Agent",
+    responses={
+        200: {"description": "Agent updated successfully"},
+        500: {"description": "Server error"},
+    },
 )
 async def update_library_agent(
     library_agent_id: str,
@@ -159,21 +271,52 @@ async def update_library_agent(
 ) -> library_model.LibraryAgent:
     """
     Update the library agent with the given fields.
+
+    Args:
+        library_agent_id: ID of the library agent to update.
+        payload: Fields to update (auto_update_version, is_favorite, etc.).
+        user_id: ID of the authenticated user.
+
+    Raises:
+        HTTPException(500): If a server/database error occurs.
     """
-    return await library_db.update_library_agent(
-        library_agent_id=library_agent_id,
-        user_id=user_id,
-        auto_update_version=payload.auto_update_version,
-        graph_version=payload.graph_version,
-        is_favorite=payload.is_favorite,
-        is_archived=payload.is_archived,
-        settings=payload.settings,
-    )
+    try:
+        return await library_db.update_library_agent(
+            library_agent_id=library_agent_id,
+            user_id=user_id,
+            auto_update_version=payload.auto_update_version,
+            graph_version=payload.graph_version,
+            is_favorite=payload.is_favorite,
+            is_archived=payload.is_archived,
+            settings=payload.settings,
+        )
+    except NotFoundError as e:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=str(e),
+        ) from e
+    except DatabaseError as e:
+        logger.error(f"Database error while updating library agent: {e}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail={"message": str(e), "hint": "Verify DB connection."},
+        ) from e
+    except Exception as e:
+        logger.error(f"Unexpected error while updating library agent: {e}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail={"message": str(e), "hint": "Check server logs."},
+        ) from e
 
 
 @router.delete(
     "/{library_agent_id}",
     summary="Delete Library Agent",
+    responses={
+        204: {"description": "Agent deleted successfully"},
+        404: {"description": "Agent not found"},
+        500: {"description": "Server error"},
+    },
 )
 async def delete_library_agent(
     library_agent_id: str,
@@ -181,11 +324,28 @@ async def delete_library_agent(
 ) -> Response:
     """
     Soft-delete the specified library agent.
+
+    Args:
+        library_agent_id: ID of the library agent to delete.
+        user_id: ID of the authenticated user.
+
+    Returns:
+        204 No Content if successful.
+
+    Raises:
+        HTTPException(404): If the agent does not exist.
+        HTTPException(500): If a server/database error occurs.
     """
-    await library_db.delete_library_agent(
-        library_agent_id=library_agent_id, user_id=user_id
-    )
-    return Response(status_code=status.HTTP_204_NO_CONTENT)
+    try:
+        await library_db.delete_library_agent(
+            library_agent_id=library_agent_id, user_id=user_id
+        )
+        return Response(status_code=status.HTTP_204_NO_CONTENT)
+    except NotFoundError as e:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=str(e),
+        ) from e
 
 
 @router.post("/{library_agent_id}/fork", summary="Fork Library Agent")

autogpt_platform/backend/backend/api/features/library/routes_test.py

@@ -52,8 +52,6 @@ async def test_get_library_agents_success(
                 output_schema={"type": "object", "properties": {}},
                 credentials_input_schema={"type": "object", "properties": {}},
                 has_external_trigger=False,
-                has_human_in_the_loop=False,
-                has_sensitive_action=False,
                 status=library_model.LibraryAgentStatus.COMPLETED,
                 recommended_schedule_cron=None,
                 new_output=False,
@@ -77,8 +75,6 @@ async def test_get_library_agents_success(
                 output_schema={"type": "object", "properties": {}},
                 credentials_input_schema={"type": "object", "properties": {}},
                 has_external_trigger=False,
-                has_human_in_the_loop=False,
-                has_sensitive_action=False,
                 status=library_model.LibraryAgentStatus.COMPLETED,
                 recommended_schedule_cron=None,
                 new_output=False,
@@ -118,6 +114,21 @@ async def test_get_library_agents_success(
     )
 
 
+def test_get_library_agents_error(mocker: pytest_mock.MockFixture, test_user_id: str):
+    mock_db_call = mocker.patch("backend.api.features.library.db.list_library_agents")
+    mock_db_call.side_effect = Exception("Test error")
+
+    response = client.get("/agents?search_term=test")
+    assert response.status_code == 500
+    mock_db_call.assert_called_once_with(
+        user_id=test_user_id,
+        search_term="test",
+        sort_by=library_model.LibraryAgentSort.UPDATED_AT,
+        page=1,
+        page_size=15,
+    )
+
+
 @pytest.mark.asyncio
 async def test_get_favorite_library_agents_success(
     mocker: pytest_mock.MockFixture,
@@ -139,8 +150,6 @@ async def test_get_favorite_library_agents_success(
                 output_schema={"type": "object", "properties": {}},
                 credentials_input_schema={"type": "object", "properties": {}},
                 has_external_trigger=False,
-                has_human_in_the_loop=False,
-                has_sensitive_action=False,
                 status=library_model.LibraryAgentStatus.COMPLETED,
                 recommended_schedule_cron=None,
                 new_output=False,
@@ -175,6 +184,23 @@ async def test_get_favorite_library_agents_success(
     )
 
 
+def test_get_favorite_library_agents_error(
+    mocker: pytest_mock.MockFixture, test_user_id: str
+):
+    mock_db_call = mocker.patch(
+        "backend.api.features.library.db.list_favorite_library_agents"
+    )
+    mock_db_call.side_effect = Exception("Test error")
+
+    response = client.get("/agents/favorites")
+    assert response.status_code == 500
+    mock_db_call.assert_called_once_with(
+        user_id=test_user_id,
+        page=1,
+        page_size=15,
+    )
+
+
 def test_add_agent_to_library_success(
     mocker: pytest_mock.MockFixture, test_user_id: str
 ):
@@ -192,8 +218,6 @@ def test_add_agent_to_library_success(
         output_schema={"type": "object", "properties": {}},
         credentials_input_schema={"type": "object", "properties": {}},
         has_external_trigger=False,
-        has_human_in_the_loop=False,
-        has_sensitive_action=False,
         status=library_model.LibraryAgentStatus.COMPLETED,
         new_output=False,
         can_access_graph=True,
@@ -226,3 +250,19 @@ def test_add_agent_to_library_success(
         store_listing_version_id="test-version-id", user_id=test_user_id
     )
     mock_complete_onboarding.assert_awaited_once()
+
+
+def test_add_agent_to_library_error(mocker: pytest_mock.MockFixture, test_user_id: str):
+    mock_db_call = mocker.patch(
+        "backend.api.features.library.db.add_store_agent_to_library"
+    )
+    mock_db_call.side_effect = Exception("Test error")
+
+    response = client.post(
+        "/agents", json={"store_listing_version_id": "test-version-id"}
+    )
+    assert response.status_code == 500
+    assert "detail" in response.json()  # Verify error response structure
+    mock_db_call.assert_called_once_with(
+        store_listing_version_id="test-version-id", user_id=test_user_id
+    )

autogpt_platform/backend/backend/api/features/oauth_test.py

@@ -20,7 +20,6 @@ from typing import AsyncGenerator
 
 import httpx
 import pytest
-import pytest_asyncio
 from autogpt_libs.api_key.keysmith import APIKeySmith
 from prisma.enums import APIKeyPermission
 from prisma.models import OAuthAccessToken as PrismaOAuthAccessToken
@@ -39,13 +38,13 @@ keysmith = APIKeySmith()
 # ============================================================================
 
 
-@pytest.fixture(scope="session")
+@pytest.fixture
 def test_user_id() -> str:
     """Test user ID for OAuth tests."""
     return str(uuid.uuid4())
 
 
-@pytest_asyncio.fixture(scope="session", loop_scope="session")
+@pytest.fixture
 async def test_user(server, test_user_id: str):
     """Create a test user in the database."""
     await PrismaUser.prisma().create(
@@ -68,7 +67,7 @@ async def test_user(server, test_user_id: str):
     await PrismaUser.prisma().delete(where={"id": test_user_id})
 
 
-@pytest_asyncio.fixture
+@pytest.fixture
 async def test_oauth_app(test_user: str):
     """Create a test OAuth application in the database."""
     app_id = str(uuid.uuid4())
@@ -123,7 +122,7 @@ def pkce_credentials() -> tuple[str, str]:
     return generate_pkce()
 
 
-@pytest_asyncio.fixture
+@pytest.fixture
 async def client(server, test_user: str) -> AsyncGenerator[httpx.AsyncClient, None]:
     """
     Create an async HTTP client that talks directly to the FastAPI app.
@@ -288,7 +287,7 @@ async def test_authorize_invalid_client_returns_error(
     assert query_params["error"][0] == "invalid_client"
 
 
-@pytest_asyncio.fixture
+@pytest.fixture
 async def inactive_oauth_app(test_user: str):
     """Create an inactive test OAuth application in the database."""
     app_id = str(uuid.uuid4())
@@ -1005,7 +1004,7 @@ async def test_token_refresh_revoked(
     assert "revoked" in response.json()["detail"].lower()
 
 
-@pytest_asyncio.fixture
+@pytest.fixture
 async def other_oauth_app(test_user: str):
     """Create a second OAuth application for cross-app tests."""
     app_id = str(uuid.uuid4())

autogpt_platform/backend/backend/api/features/store/content_handlers.py

@@ -188,10 +188,6 @@ class BlockHandler(ContentHandler):
             try:
                 block_instance = block_cls()
 
-                # Skip disabled blocks - they shouldn't be indexed
-                if block_instance.disabled:
-                    continue
-
                 # Build searchable text from block metadata
                 parts = []
                 if hasattr(block_instance, "name") and block_instance.name:
@@ -252,19 +248,12 @@ class BlockHandler(ContentHandler):
         from backend.data.block import get_blocks
 
         all_blocks = get_blocks()
-
-        # Filter out disabled blocks - they're not indexed
-        enabled_block_ids = [
-            block_id
-            for block_id, block_cls in all_blocks.items()
-            if not block_cls().disabled
-        ]
-        total_blocks = len(enabled_block_ids)
+        total_blocks = len(all_blocks)
 
         if total_blocks == 0:
             return {"total": 0, "with_embeddings": 0, "without_embeddings": 0}
 
-        block_ids = enabled_block_ids
+        block_ids = list(all_blocks.keys())
         placeholders = ",".join([f"${i+1}" for i in range(len(block_ids))])
 
         embedded_result = await query_raw_with_schema(

autogpt_platform/backend/backend/api/features/store/content_handlers_test.py

@@ -81,7 +81,6 @@ async def test_block_handler_get_missing_items(mocker):
     mock_block_instance.name = "Calculator Block"
     mock_block_instance.description = "Performs calculations"
     mock_block_instance.categories = [MagicMock(value="MATH")]
-    mock_block_instance.disabled = False
     mock_block_instance.input_schema.model_json_schema.return_value = {
         "properties": {"expression": {"description": "Math expression to evaluate"}}
     }
@@ -117,18 +116,11 @@ async def test_block_handler_get_stats(mocker):
     """Test BlockHandler returns correct stats."""
     handler = BlockHandler()
 
-    # Mock get_blocks - each block class returns an instance with disabled=False
-    def make_mock_block_class():
-        mock_class = MagicMock()
-        mock_instance = MagicMock()
-        mock_instance.disabled = False
-        mock_class.return_value = mock_instance
-        return mock_class
-
+    # Mock get_blocks
     mock_blocks = {
-        "block-1": make_mock_block_class(),
-        "block-2": make_mock_block_class(),
-        "block-3": make_mock_block_class(),
+        "block-1": MagicMock(),
+        "block-2": MagicMock(),
+        "block-3": MagicMock(),
     }
 
     # Mock embedded count query (2 blocks have embeddings)
@@ -317,7 +309,6 @@ async def test_block_handler_handles_missing_attributes():
     mock_block_class = MagicMock()
     mock_block_instance = MagicMock()
     mock_block_instance.name = "Minimal Block"
-    mock_block_instance.disabled = False
     # No description, categories, or schema
     del mock_block_instance.description
     del mock_block_instance.categories
@@ -351,7 +342,6 @@ async def test_block_handler_skips_failed_blocks():
     good_instance.name = "Good Block"
     good_instance.description = "Works fine"
     good_instance.categories = []
-    good_instance.disabled = False
     good_block.return_value = good_instance
 
     bad_block = MagicMock()

autogpt_platform/backend/backend/api/features/store/db.py

@@ -1552,7 +1552,7 @@ async def review_store_submission(
 
                 # Generate embedding for approved listing (blocking - admin operation)
                 # Inside transaction: if embedding fails, entire transaction rolls back
-                await ensure_embedding(
+                embedding_success = await ensure_embedding(
                     version_id=store_listing_version_id,
                     name=store_listing_version.name,
                     description=store_listing_version.description,
@@ -1560,6 +1560,12 @@ async def review_store_submission(
                     categories=store_listing_version.categories or [],
                     tx=tx,
                 )
+                if not embedding_success:
+                    raise ValueError(
+                        f"Failed to generate embedding for listing {store_listing_version_id}. "
+                        "This is likely due to OpenAI API being unavailable. "
+                        "Please try again later or contact support if the issue persists."
+                    )
 
                 await prisma.models.StoreListing.prisma(tx).update(
                     where={"id": store_listing_version.StoreListing.id},

autogpt_platform/backend/backend/api/features/store/embeddings.py

@@ -21,6 +21,7 @@ from backend.util.json import dumps
 
 logger = logging.getLogger(__name__)
 
+
 # OpenAI embedding model configuration
 EMBEDDING_MODEL = "text-embedding-3-small"
 # Embedding dimension for the model above
@@ -62,42 +63,49 @@ def build_searchable_text(
     return " ".join(parts)
 
 
-async def generate_embedding(text: str) -> list[float]:
+async def generate_embedding(text: str) -> list[float] | None:
     """
     Generate embedding for text using OpenAI API.
 
-    Raises exceptions on failure - caller should handle.
+    Returns None if embedding generation fails.
+    Fail-fast: no retries to maintain consistency with approval flow.
     """
-    client = get_openai_client()
-    if not client:
-        raise RuntimeError("openai_internal_api_key not set, cannot generate embedding")
+    try:
+        client = get_openai_client()
+        if not client:
+            logger.error("openai_internal_api_key not set, cannot generate embedding")
+            return None
 
-    # Truncate text to token limit using tiktoken
-    # Character-based truncation is insufficient because token ratios vary by content type
-    enc = encoding_for_model(EMBEDDING_MODEL)
-    tokens = enc.encode(text)
-    if len(tokens) > EMBEDDING_MAX_TOKENS:
-        tokens = tokens[:EMBEDDING_MAX_TOKENS]
-        truncated_text = enc.decode(tokens)
-        logger.info(
-            f"Truncated text from {len(enc.encode(text))} to {len(tokens)} tokens"
+        # Truncate text to token limit using tiktoken
+        # Character-based truncation is insufficient because token ratios vary by content type
+        enc = encoding_for_model(EMBEDDING_MODEL)
+        tokens = enc.encode(text)
+        if len(tokens) > EMBEDDING_MAX_TOKENS:
+            tokens = tokens[:EMBEDDING_MAX_TOKENS]
+            truncated_text = enc.decode(tokens)
+            logger.info(
+                f"Truncated text from {len(enc.encode(text))} to {len(tokens)} tokens"
+            )
+        else:
+            truncated_text = text
+
+        start_time = time.time()
+        response = await client.embeddings.create(
+            model=EMBEDDING_MODEL,
+            input=truncated_text,
         )
-    else:
-        truncated_text = text
+        latency_ms = (time.time() - start_time) * 1000
 
-    start_time = time.time()
-    response = await client.embeddings.create(
-        model=EMBEDDING_MODEL,
-        input=truncated_text,
-    )
-    latency_ms = (time.time() - start_time) * 1000
+        embedding = response.data[0].embedding
+        logger.info(
+            f"Generated embedding: {len(embedding)} dims, "
+            f"{len(tokens)} tokens, {latency_ms:.0f}ms"
+        )
+        return embedding
 
-    embedding = response.data[0].embedding
-    logger.info(
-        f"Generated embedding: {len(embedding)} dims, "
-        f"{len(tokens)} tokens, {latency_ms:.0f}ms"
-    )
-    return embedding
+    except Exception as e:
+        logger.error(f"Failed to generate embedding: {e}")
+        return None
 
 
 async def store_embedding(
@@ -136,45 +144,48 @@ async def store_content_embedding(
 
     New function for unified content embedding storage.
     Uses raw SQL since Prisma doesn't natively support pgvector.
-
-    Raises exceptions on failure - caller should handle.
     """
-    client = tx if tx else prisma.get_client()
+    try:
+        client = tx if tx else prisma.get_client()
 
-    # Convert embedding to PostgreSQL vector format
-    embedding_str = embedding_to_vector_string(embedding)
-    metadata_json = dumps(metadata or {})
+        # Convert embedding to PostgreSQL vector format
+        embedding_str = embedding_to_vector_string(embedding)
+        metadata_json = dumps(metadata or {})
 
-    # Upsert the embedding
-    # WHERE clause in DO UPDATE prevents PostgreSQL 15 bug with NULLS NOT DISTINCT
-    # Use unqualified ::vector - pgvector is in search_path on all environments
-    await execute_raw_with_schema(
-        """
-        INSERT INTO {schema_prefix}"UnifiedContentEmbedding" (
-            "id", "contentType", "contentId", "userId", "embedding", "searchableText", "metadata", "createdAt", "updatedAt"
+        # Upsert the embedding
+        # WHERE clause in DO UPDATE prevents PostgreSQL 15 bug with NULLS NOT DISTINCT
+        await execute_raw_with_schema(
+            """
+            INSERT INTO {schema_prefix}"UnifiedContentEmbedding" (
+                "id", "contentType", "contentId", "userId", "embedding", "searchableText", "metadata", "createdAt", "updatedAt"
+            )
+            VALUES (gen_random_uuid()::text, $1::{schema_prefix}"ContentType", $2, $3, $4::vector, $5, $6::jsonb, NOW(), NOW())
+            ON CONFLICT ("contentType", "contentId", "userId")
+            DO UPDATE SET
+                "embedding" = $4::vector,
+                "searchableText" = $5,
+                "metadata" = $6::jsonb,
+                "updatedAt" = NOW()
+            WHERE {schema_prefix}"UnifiedContentEmbedding"."contentType" = $1::{schema_prefix}"ContentType"
+                AND {schema_prefix}"UnifiedContentEmbedding"."contentId" = $2
+                AND ({schema_prefix}"UnifiedContentEmbedding"."userId" = $3 OR ($3 IS NULL AND {schema_prefix}"UnifiedContentEmbedding"."userId" IS NULL))
+            """,
+            content_type,
+            content_id,
+            user_id,
+            embedding_str,
+            searchable_text,
+            metadata_json,
+            client=client,
+            set_public_search_path=True,
         )
-        VALUES (gen_random_uuid()::text, $1::{schema_prefix}"ContentType", $2, $3, $4::vector, $5, $6::jsonb, NOW(), NOW())
-        ON CONFLICT ("contentType", "contentId", "userId")
-        DO UPDATE SET
-            "embedding" = $4::vector,
-            "searchableText" = $5,
-            "metadata" = $6::jsonb,
-            "updatedAt" = NOW()
-        WHERE {schema_prefix}"UnifiedContentEmbedding"."contentType" = $1::{schema_prefix}"ContentType"
-            AND {schema_prefix}"UnifiedContentEmbedding"."contentId" = $2
-            AND ({schema_prefix}"UnifiedContentEmbedding"."userId" = $3 OR ($3 IS NULL AND {schema_prefix}"UnifiedContentEmbedding"."userId" IS NULL))
-        """,
-        content_type,
-        content_id,
-        user_id,
-        embedding_str,
-        searchable_text,
-        metadata_json,
-        client=client,
-    )
 
-    logger.info(f"Stored embedding for {content_type}:{content_id}")
-    return True
+        logger.info(f"Stored embedding for {content_type}:{content_id}")
+        return True
+
+    except Exception as e:
+        logger.error(f"Failed to store embedding for {content_type}:{content_id}: {e}")
+        return False
 
 
 async def get_embedding(version_id: str) -> dict[str, Any] | None:
@@ -206,31 +217,35 @@ async def get_content_embedding(
 
     New function for unified content embedding retrieval.
     Returns dict with contentType, contentId, embedding, timestamps or None if not found.
-
-    Raises exceptions on failure - caller should handle.
     """
-    result = await query_raw_with_schema(
-        """
-        SELECT
-            "contentType",
-            "contentId",
-            "userId",
-            "embedding"::text as "embedding",
-            "searchableText",
-            "metadata",
-            "createdAt",
-            "updatedAt"
-        FROM {schema_prefix}"UnifiedContentEmbedding"
-        WHERE "contentType" = $1::{schema_prefix}"ContentType" AND "contentId" = $2 AND ("userId" = $3 OR ($3 IS NULL AND "userId" IS NULL))
-        """,
-        content_type,
-        content_id,
-        user_id,
-    )
+    try:
+        result = await query_raw_with_schema(
+            """
+            SELECT
+                "contentType",
+                "contentId",
+                "userId",
+                "embedding"::text as "embedding",
+                "searchableText",
+                "metadata",
+                "createdAt",
+                "updatedAt"
+            FROM {schema_prefix}"UnifiedContentEmbedding"
+            WHERE "contentType" = $1::{schema_prefix}"ContentType" AND "contentId" = $2 AND ("userId" = $3 OR ($3 IS NULL AND "userId" IS NULL))
+            """,
+            content_type,
+            content_id,
+            user_id,
+            set_public_search_path=True,
+        )
 
-    if result and len(result) > 0:
-        return result[0]
-    return None
+        if result and len(result) > 0:
+            return result[0]
+        return None
+
+    except Exception as e:
+        logger.error(f"Failed to get embedding for {content_type}:{content_id}: {e}")
+        return None
 
 
 async def ensure_embedding(
@@ -258,38 +273,46 @@ async def ensure_embedding(
         tx: Optional transaction client
 
     Returns:
-        True if embedding exists/was created
-
-    Raises exceptions on failure - caller should handle.
+        True if embedding exists/was created, False on failure
     """
-    # Check if embedding already exists
-    if not force:
-        existing = await get_embedding(version_id)
-        if existing and existing.get("embedding"):
-            logger.debug(f"Embedding for version {version_id} already exists")
-            return True
+    try:
+        # Check if embedding already exists
+        if not force:
+            existing = await get_embedding(version_id)
+            if existing and existing.get("embedding"):
+                logger.debug(f"Embedding for version {version_id} already exists")
+                return True
 
-    # Build searchable text for embedding
-    searchable_text = build_searchable_text(name, description, sub_heading, categories)
+        # Build searchable text for embedding
+        searchable_text = build_searchable_text(
+            name, description, sub_heading, categories
+        )
 
-    # Generate new embedding
-    embedding = await generate_embedding(searchable_text)
+        # Generate new embedding
+        embedding = await generate_embedding(searchable_text)
+        if embedding is None:
+            logger.warning(f"Could not generate embedding for version {version_id}")
+            return False
 
-    # Store the embedding with metadata using new function
-    metadata = {
-        "name": name,
-        "subHeading": sub_heading,
-        "categories": categories,
-    }
-    return await store_content_embedding(
-        content_type=ContentType.STORE_AGENT,
-        content_id=version_id,
-        embedding=embedding,
-        searchable_text=searchable_text,
-        metadata=metadata,
-        user_id=None,  # Store agents are public
-        tx=tx,
-    )
+        # Store the embedding with metadata using new function
+        metadata = {
+            "name": name,
+            "subHeading": sub_heading,
+            "categories": categories,
+        }
+        return await store_content_embedding(
+            content_type=ContentType.STORE_AGENT,
+            content_id=version_id,
+            embedding=embedding,
+            searchable_text=searchable_text,
+            metadata=metadata,
+            user_id=None,  # Store agents are public
+            tx=tx,
+        )
+
+    except Exception as e:
+        logger.error(f"Failed to ensure embedding for version {version_id}: {e}")
+        return False
 
 
 async def delete_embedding(version_id: str) -> bool:
@@ -454,7 +477,6 @@ async def backfill_all_content_types(batch_size: int = 10) -> dict[str, Any]:
     total_processed = 0
     total_success = 0
     total_failed = 0
-    all_errors: dict[str, int] = {}  # Aggregate errors across all content types
 
     # Process content types in explicit order
     processing_order = [
@@ -500,13 +522,6 @@ async def backfill_all_content_types(batch_size: int = 10) -> dict[str, Any]:
             success = sum(1 for result in results if result is True)
             failed = len(results) - success
 
-            # Aggregate errors across all content types
-            if failed > 0:
-                for result in results:
-                    if isinstance(result, Exception):
-                        error_key = f"{type(result).__name__}: {str(result)}"
-                        all_errors[error_key] = all_errors.get(error_key, 0) + 1
-
             results_by_type[content_type.value] = {
                 "processed": len(missing_items),
                 "success": success,
@@ -532,13 +547,6 @@ async def backfill_all_content_types(batch_size: int = 10) -> dict[str, Any]:
                 "error": str(e),
             }
 
-    # Log aggregated errors once at the end
-    if all_errors:
-        error_details = ", ".join(
-            f"{error} ({count}x)" for error, count in all_errors.items()
-        )
-        logger.error(f"Embedding backfill errors: {error_details}")
-
     return {
         "by_type": results_by_type,
         "totals": {
@@ -550,12 +558,11 @@ async def backfill_all_content_types(batch_size: int = 10) -> dict[str, Any]:
     }
 
 
-async def embed_query(query: str) -> list[float]:
+async def embed_query(query: str) -> list[float] | None:
     """
     Generate embedding for a search query.
 
     Same as generate_embedding but with clearer intent.
-    Raises exceptions on failure - caller should handle.
     """
     return await generate_embedding(query)
 
@@ -588,30 +595,40 @@ async def ensure_content_embedding(
         tx: Optional transaction client
 
     Returns:
-        True if embedding exists/was created
-
-    Raises exceptions on failure - caller should handle.
+        True if embedding exists/was created, False on failure
     """
-    # Check if embedding already exists
-    if not force:
-        existing = await get_content_embedding(content_type, content_id, user_id)
-        if existing and existing.get("embedding"):
-            logger.debug(f"Embedding for {content_type}:{content_id} already exists")
-            return True
+    try:
+        # Check if embedding already exists
+        if not force:
+            existing = await get_content_embedding(content_type, content_id, user_id)
+            if existing and existing.get("embedding"):
+                logger.debug(
+                    f"Embedding for {content_type}:{content_id} already exists"
+                )
+                return True
 
-    # Generate new embedding
-    embedding = await generate_embedding(searchable_text)
+        # Generate new embedding
+        embedding = await generate_embedding(searchable_text)
+        if embedding is None:
+            logger.warning(
+                f"Could not generate embedding for {content_type}:{content_id}"
+            )
+            return False
 
-    # Store the embedding
-    return await store_content_embedding(
-        content_type=content_type,
-        content_id=content_id,
-        embedding=embedding,
-        searchable_text=searchable_text,
-        metadata=metadata or {},
-        user_id=user_id,
-        tx=tx,
-    )
+        # Store the embedding
+        return await store_content_embedding(
+            content_type=content_type,
+            content_id=content_id,
+            embedding=embedding,
+            searchable_text=searchable_text,
+            metadata=metadata or {},
+            user_id=user_id,
+            tx=tx,
+        )
+
+    except Exception as e:
+        logger.error(f"Failed to ensure embedding for {content_type}:{content_id}: {e}")
+        return False
 
 
 async def cleanup_orphaned_embeddings() -> dict[str, Any]:
@@ -838,8 +855,9 @@ async def semantic_search(
         limit = 100
 
     # Generate query embedding
-    try:
-        query_embedding = await embed_query(query)
+    query_embedding = await embed_query(query)
+
+    if query_embedding is not None:
         # Semantic search with embeddings
         embedding_str = embedding_to_vector_string(query_embedding)
 
@@ -853,58 +871,47 @@ async def semantic_search(
         # Add content type parameters and build placeholders dynamically
         content_type_start_idx = len(params) + 1
         content_type_placeholders = ", ".join(
-            "$" + str(content_type_start_idx + i) + '::{schema_prefix}"ContentType"'
+            f'${content_type_start_idx + i}::{{{{schema_prefix}}}}"ContentType"'
             for i in range(len(content_types))
         )
         params.extend([ct.value for ct in content_types])
 
-        # Build min_similarity param index before appending
-        min_similarity_idx = len(params) + 1
-        params.append(min_similarity)
-
-        # Use unqualified ::vector and <=> operator - pgvector is in search_path on all environments
-        sql = (
-            """
+        sql = f"""
             SELECT
                 "contentId" as content_id,
                 "contentType" as content_type,
                 "searchableText" as searchable_text,
                 metadata,
-                1 - (embedding <=> '"""
-            + embedding_str
-            + """'::vector) as similarity
-            FROM {schema_prefix}"UnifiedContentEmbedding"
-            WHERE "contentType" IN ("""
-            + content_type_placeholders
-            + """)
-            """
-            + user_filter
-            + """
-            AND 1 - (embedding <=> '"""
-            + embedding_str
-            + """'::vector) >= $"""
-            + str(min_similarity_idx)
-            + """
+                1 - (embedding <=> '{embedding_str}'::vector) as similarity
+            FROM {{{{schema_prefix}}}}"UnifiedContentEmbedding"
+            WHERE "contentType" IN ({content_type_placeholders})
+            {user_filter}
+            AND 1 - (embedding <=> '{embedding_str}'::vector) >= ${len(params) + 1}
             ORDER BY similarity DESC
             LIMIT $1
         """
-        )
+        params.append(min_similarity)
 
-        results = await query_raw_with_schema(sql, *params)
-        return [
-            {
-                "content_id": row["content_id"],
-                "content_type": row["content_type"],
-                "searchable_text": row["searchable_text"],
-                "metadata": row["metadata"],
-                "similarity": float(row["similarity"]),
-            }
-            for row in results
-        ]
-    except Exception as e:
-        logger.warning(f"Semantic search failed, falling back to lexical search: {e}")
+        try:
+            results = await query_raw_with_schema(
+                sql, *params, set_public_search_path=True
+            )
+            return [
+                {
+                    "content_id": row["content_id"],
+                    "content_type": row["content_type"],
+                    "searchable_text": row["searchable_text"],
+                    "metadata": row["metadata"],
+                    "similarity": float(row["similarity"]),
+                }
+                for row in results
+            ]
+        except Exception as e:
+            logger.error(f"Semantic search failed: {e}")
+            # Fall through to lexical search below
 
     # Fallback to lexical search if embeddings unavailable
+    logger.warning("Falling back to lexical search (embeddings unavailable)")
 
     params_lexical: list[Any] = [limit]
     user_filter = ""
@@ -915,41 +922,31 @@ async def semantic_search(
     # Add content type parameters and build placeholders dynamically
     content_type_start_idx = len(params_lexical) + 1
     content_type_placeholders_lexical = ", ".join(
-        "$" + str(content_type_start_idx + i) + '::{schema_prefix}"ContentType"'
+        f'${content_type_start_idx + i}::{{{{schema_prefix}}}}"ContentType"'
         for i in range(len(content_types))
     )
     params_lexical.extend([ct.value for ct in content_types])
 
-    # Build query param index before appending
-    query_param_idx = len(params_lexical) + 1
-    params_lexical.append(f"%{query}%")
-
-    # Use regular string (not f-string) for template to preserve {schema_prefix} placeholders
-    sql_lexical = (
-        """
+    sql_lexical = f"""
         SELECT
             "contentId" as content_id,
             "contentType" as content_type,
             "searchableText" as searchable_text,
             metadata,
             0.0 as similarity
-        FROM {schema_prefix}"UnifiedContentEmbedding"
-        WHERE "contentType" IN ("""
-        + content_type_placeholders_lexical
-        + """)
-        """
-        + user_filter
-        + """
-        AND "searchableText" ILIKE $"""
-        + str(query_param_idx)
-        + """
+        FROM {{{{schema_prefix}}}}"UnifiedContentEmbedding"
+        WHERE "contentType" IN ({content_type_placeholders_lexical})
+        {user_filter}
+        AND "searchableText" ILIKE ${len(params_lexical) + 1}
         ORDER BY "updatedAt" DESC
         LIMIT $1
     """
-    )
+    params_lexical.append(f"%{query}%")
 
     try:
-        results = await query_raw_with_schema(sql_lexical, *params_lexical)
+        results = await query_raw_with_schema(
+            sql_lexical, *params_lexical, set_public_search_path=True
+        )
         return [
             {
                 "content_id": row["content_id"],

autogpt_platform/backend/backend/api/features/store/embeddings_schema_test.py

@@ -298,16 +298,17 @@ async def test_schema_handling_error_cases():
             mock_client.execute_raw.side_effect = Exception("Database error")
             mock_get_client.return_value = mock_client
 
-            # Should raise exception on error
-            with pytest.raises(Exception, match="Database error"):
-                await embeddings.store_content_embedding(
-                    content_type=ContentType.STORE_AGENT,
-                    content_id="test-id",
-                    embedding=[0.1] * EMBEDDING_DIM,
-                    searchable_text="test",
-                    metadata=None,
-                    user_id=None,
-                )
+            result = await embeddings.store_content_embedding(
+                content_type=ContentType.STORE_AGENT,
+                content_id="test-id",
+                embedding=[0.1] * EMBEDDING_DIM,
+                searchable_text="test",
+                metadata=None,
+                user_id=None,
+            )
+
+            # Should return False on error, not raise
+            assert result is False
 
 
 if __name__ == "__main__":

autogpt_platform/backend/backend/api/features/store/embeddings_test.py

@@ -80,8 +80,9 @@ async def test_generate_embedding_no_api_key():
     ) as mock_get_client:
         mock_get_client.return_value = None
 
-        with pytest.raises(RuntimeError, match="openai_internal_api_key not set"):
-            await embeddings.generate_embedding("test text")
+        result = await embeddings.generate_embedding("test text")
+
+        assert result is None
 
 
 @pytest.mark.asyncio(loop_scope="session")
@@ -96,8 +97,9 @@ async def test_generate_embedding_api_error():
     ) as mock_get_client:
         mock_get_client.return_value = mock_client
 
-        with pytest.raises(Exception, match="API Error"):
-            await embeddings.generate_embedding("test text")
+        result = await embeddings.generate_embedding("test text")
+
+        assert result is None
 
 
 @pytest.mark.asyncio(loop_scope="session")
@@ -153,14 +155,18 @@ async def test_store_embedding_success(mocker):
     )
 
     assert result is True
-    # execute_raw is called once for INSERT (no separate SET search_path needed)
-    assert mock_client.execute_raw.call_count == 1
+    # execute_raw is called twice: once for SET search_path, once for INSERT
+    assert mock_client.execute_raw.call_count == 2
 
-    # Verify the INSERT query with the actual data
-    call_args = mock_client.execute_raw.call_args_list[0][0]
-    assert "test-version-id" in call_args
-    assert "[0.1,0.2,0.3]" in call_args
-    assert None in call_args  # userId should be None for store agents
+    # First call: SET search_path
+    first_call_args = mock_client.execute_raw.call_args_list[0][0]
+    assert "SET search_path" in first_call_args[0]
+
+    # Second call: INSERT query with the actual data
+    second_call_args = mock_client.execute_raw.call_args_list[1][0]
+    assert "test-version-id" in second_call_args
+    assert "[0.1,0.2,0.3]" in second_call_args
+    assert None in second_call_args  # userId should be None for store agents
 
 
 @pytest.mark.asyncio(loop_scope="session")
@@ -171,10 +177,11 @@ async def test_store_embedding_database_error(mocker):
 
     embedding = [0.1, 0.2, 0.3]
 
-    with pytest.raises(Exception, match="Database error"):
-        await embeddings.store_embedding(
-            version_id="test-version-id", embedding=embedding, tx=mock_client
-        )
+    result = await embeddings.store_embedding(
+        version_id="test-version-id", embedding=embedding, tx=mock_client
+    )
+
+    assert result is False
 
 
 @pytest.mark.asyncio(loop_scope="session")
@@ -274,16 +281,17 @@ async def test_ensure_embedding_create_new(mock_get, mock_store, mock_generate):
 async def test_ensure_embedding_generation_fails(mock_get, mock_generate):
     """Test ensure_embedding when generation fails."""
     mock_get.return_value = None
-    mock_generate.side_effect = Exception("Generation failed")
+    mock_generate.return_value = None
 
-    with pytest.raises(Exception, match="Generation failed"):
-        await embeddings.ensure_embedding(
-            version_id="test-id",
-            name="Test",
-            description="Test description",
-            sub_heading="Test heading",
-            categories=["test"],
-        )
+    result = await embeddings.ensure_embedding(
+        version_id="test-id",
+        name="Test",
+        description="Test description",
+        sub_heading="Test heading",
+        categories=["test"],
+    )
+
+    assert result is False
 
 
 @pytest.mark.asyncio(loop_scope="session")

autogpt_platform/backend/backend/api/features/store/hybrid_search.py

@@ -12,7 +12,7 @@ from dataclasses import dataclass
 from typing import Any, Literal
 
 from prisma.enums import ContentType
-from rank_bm25 import BM25Okapi  # type: ignore[import-untyped]
+from rank_bm25 import BM25Okapi
 
 from backend.api.features.store.embeddings import (
     EMBEDDING_DIM,
@@ -186,12 +186,13 @@ async def unified_hybrid_search(
 
     offset = (page - 1) * page_size
 
-    # Generate query embedding with graceful degradation
-    try:
-        query_embedding = await embed_query(query)
-    except Exception as e:
+    # Generate query embedding
+    query_embedding = await embed_query(query)
+
+    # Graceful degradation if embedding unavailable
+    if query_embedding is None or not query_embedding:
         logger.warning(
-            f"Failed to generate query embedding - falling back to lexical-only search: {e}. "
+            "Failed to generate query embedding - falling back to lexical-only search. "
             "Check that openai_internal_api_key is configured and OpenAI API is accessible."
         )
         query_embedding = [0.0] * EMBEDDING_DIM
@@ -362,7 +363,9 @@ async def unified_hybrid_search(
         LIMIT {limit_param} OFFSET {offset_param}
     """
 
-    results = await query_raw_with_schema(sql_query, *params)
+    results = await query_raw_with_schema(
+        sql_query, *params, set_public_search_path=True
+    )
 
     total = results[0]["total_count"] if results else 0
     # Apply BM25 reranking
@@ -463,12 +466,13 @@ async def hybrid_search(
 
     offset = (page - 1) * page_size
 
-    # Generate query embedding with graceful degradation
-    try:
-        query_embedding = await embed_query(query)
-    except Exception as e:
+    # Generate query embedding
+    query_embedding = await embed_query(query)
+
+    # Graceful degradation
+    if query_embedding is None or not query_embedding:
         logger.warning(
-            f"Failed to generate query embedding - falling back to lexical-only search: {e}"
+            "Failed to generate query embedding - falling back to lexical-only search."
         )
         query_embedding = [0.0] * EMBEDDING_DIM
         total_non_semantic = (
@@ -684,7 +688,9 @@ async def hybrid_search(
         LIMIT {limit_param} OFFSET {offset_param}
     """
 
-    results = await query_raw_with_schema(sql_query, *params)
+    results = await query_raw_with_schema(
+        sql_query, *params, set_public_search_path=True
+    )
 
     total = results[0]["total_count"] if results else 0
 

autogpt_platform/backend/backend/api/features/store/hybrid_search_test.py

@@ -172,8 +172,8 @@ async def test_hybrid_search_without_embeddings():
         with patch(
             "backend.api.features.store.hybrid_search.query_raw_with_schema"
         ) as mock_query:
-            # Simulate embedding failure by raising exception
-            mock_embed.side_effect = Exception("Embedding generation failed")
+            # Simulate embedding failure
+            mock_embed.return_value = None
             mock_query.return_value = mock_results
 
             # Should NOT raise - graceful degradation
@@ -613,9 +613,7 @@ async def test_unified_hybrid_search_graceful_degradation():
             "backend.api.features.store.hybrid_search.embed_query"
         ) as mock_embed:
             mock_query.return_value = mock_results
-            mock_embed.side_effect = Exception(
-                "Embedding generation failed"
-            )  # Embedding failure
+            mock_embed.return_value = None  # Embedding failure
 
             # Should NOT raise - graceful degradation
             results, total = await unified_hybrid_search(

autogpt_platform/backend/backend/api/features/v1.py

@@ -261,36 +261,14 @@ async def get_onboarding_agents(
     return await get_recommended_agents(user_id)
 
 
-class OnboardingStatusResponse(pydantic.BaseModel):
-    """Response for onboarding status check."""
-
-    is_onboarding_enabled: bool
-    is_chat_enabled: bool
-
-
 @v1_router.get(
     "/onboarding/enabled",
     summary="Is onboarding enabled",
     tags=["onboarding", "public"],
-    response_model=OnboardingStatusResponse,
+    dependencies=[Security(requires_user)],
 )
-async def is_onboarding_enabled(
-    user_id: Annotated[str, Security(get_user_id)],
-) -> OnboardingStatusResponse:
-    # Check if chat is enabled for user
-    is_chat_enabled = await is_feature_enabled(Flag.CHAT, user_id, False)
-
-    # If chat is enabled, skip legacy onboarding
-    if is_chat_enabled:
-        return OnboardingStatusResponse(
-            is_onboarding_enabled=False,
-            is_chat_enabled=True,
-        )
-
-    return OnboardingStatusResponse(
-        is_onboarding_enabled=await onboarding_enabled(),
-        is_chat_enabled=False,
-    )
+async def is_onboarding_enabled() -> bool:
+    return await onboarding_enabled()
 
 
 @v1_router.post(
@@ -386,8 +364,6 @@ async def execute_graph_block(
     obj = get_block(block_id)
     if not obj:
         raise HTTPException(status_code=404, detail=f"Block #{block_id} not found.")
-    if obj.disabled:
-        raise HTTPException(status_code=403, detail=f"Block #{block_id} is disabled.")
 
     user = await get_user_by_id(user_id)
     if not user:
@@ -785,8 +761,10 @@ async def create_new_graph(
     graph.reassign_ids(user_id=user_id, reassign_graph_id=True)
     graph.validate_graph(for_run=False)
 
+    # The return value of the create graph & library function is intentionally not used here,
+    # as the graph already valid and no sub-graphs are returned back.
     await graph_db.create_graph(graph, user_id=user_id)
-    await library_db.create_library_agent(graph, user_id)
+    await library_db.create_library_agent(graph, user_id=user_id)
     activated_graph = await on_graph_activate(graph, user_id=user_id)
 
     if create_graph.source == "builder":
@@ -910,19 +888,21 @@ async def set_graph_active_version(
 async def _update_library_agent_version_and_settings(
     user_id: str, agent_graph: graph_db.GraphModel
 ) -> library_model.LibraryAgent:
+    # Keep the library agent up to date with the new active version
     library = await library_db.update_agent_version_in_library(
         user_id, agent_graph.id, agent_graph.version
     )
-    updated_settings = GraphSettings.from_graph(
-        graph=agent_graph,
-        hitl_safe_mode=library.settings.human_in_the_loop_safe_mode,
-        sensitive_action_safe_mode=library.settings.sensitive_action_safe_mode,
-    )
-    if updated_settings != library.settings:
-        library = await library_db.update_library_agent(
-            library_agent_id=library.id,
+    # If the graph has HITL node, initialize the setting if it's not already set.
+    if (
+        agent_graph.has_human_in_the_loop
+        and library.settings.human_in_the_loop_safe_mode is None
+    ):
+        await library_db.update_library_agent_settings(
             user_id=user_id,
-            settings=updated_settings,
+            agent_id=library.id,
+            settings=library.settings.model_copy(
+                update={"human_in_the_loop_safe_mode": True}
+            ),
         )
     return library
 
@@ -939,18 +919,21 @@ async def update_graph_settings(
     user_id: Annotated[str, Security(get_user_id)],
 ) -> GraphSettings:
     """Update graph settings for the user's library agent."""
+    # Get the library agent for this graph
     library_agent = await library_db.get_library_agent_by_graph_id(
         graph_id=graph_id, user_id=user_id
     )
     if not library_agent:
         raise HTTPException(404, f"Graph #{graph_id} not found in user's library")
 
-    updated_agent = await library_db.update_library_agent(
-        library_agent_id=library_agent.id,
+    # Update the library agent settings
+    updated_agent = await library_db.update_library_agent_settings(
         user_id=user_id,
+        agent_id=library_agent.id,
         settings=settings,
     )
 
+    # Return the updated settings
     return GraphSettings.model_validate(updated_agent.settings)
 
 

autogpt_platform/backend/backend/api/features/v1_test.py

@@ -138,7 +138,6 @@ def test_execute_graph_block(
     """Test execute block endpoint"""
     # Mock block
     mock_block = Mock()
-    mock_block.disabled = False
 
     async def mock_execute(*args, **kwargs):
         yield "output1", {"data": "result1"}

autogpt_platform/backend/backend/api/features/workspace/__init__.py

@@ -1 +0,0 @@
-# Workspace API feature module

autogpt_platform/backend/backend/api/features/workspace/routes.py

@@ -1,122 +0,0 @@
-"""
-Workspace API routes for managing user file storage.
-"""
-
-import logging
-import re
-from typing import Annotated
-from urllib.parse import quote
-
-import fastapi
-from autogpt_libs.auth.dependencies import get_user_id, requires_user
-from fastapi.responses import Response
-
-from backend.data.workspace import get_workspace, get_workspace_file
-from backend.util.workspace_storage import get_workspace_storage
-
-
-def _sanitize_filename_for_header(filename: str) -> str:
-    """
-    Sanitize filename for Content-Disposition header to prevent header injection.
-
-    Removes/replaces characters that could break the header or inject new headers.
-    Uses RFC5987 encoding for non-ASCII characters.
-    """
-    # Remove CR, LF, and null bytes (header injection prevention)
-    sanitized = re.sub(r"[\r\n\x00]", "", filename)
-    # Escape quotes
-    sanitized = sanitized.replace('"', '\\"')
-    # For non-ASCII, use RFC5987 filename* parameter
-    # Check if filename has non-ASCII characters
-    try:
-        sanitized.encode("ascii")
-        return f'attachment; filename="{sanitized}"'
-    except UnicodeEncodeError:
-        # Use RFC5987 encoding for UTF-8 filenames
-        encoded = quote(sanitized, safe="")
-        return f"attachment; filename*=UTF-8''{encoded}"
-
-
-logger = logging.getLogger(__name__)
-
-router = fastapi.APIRouter(
-    dependencies=[fastapi.Security(requires_user)],
-)
-
-
-def _create_streaming_response(content: bytes, file) -> Response:
-    """Create a streaming response for file content."""
-    return Response(
-        content=content,
-        media_type=file.mimeType,
-        headers={
-            "Content-Disposition": _sanitize_filename_for_header(file.name),
-            "Content-Length": str(len(content)),
-        },
-    )
-
-
-async def _create_file_download_response(file) -> Response:
-    """
-    Create a download response for a workspace file.
-
-    Handles both local storage (direct streaming) and GCS (signed URL redirect
-    with fallback to streaming).
-    """
-    storage = await get_workspace_storage()
-
-    # For local storage, stream the file directly
-    if file.storagePath.startswith("local://"):
-        content = await storage.retrieve(file.storagePath)
-        return _create_streaming_response(content, file)
-
-    # For GCS, try to redirect to signed URL, fall back to streaming
-    try:
-        url = await storage.get_download_url(file.storagePath, expires_in=300)
-        # If we got back an API path (fallback), stream directly instead
-        if url.startswith("/api/"):
-            content = await storage.retrieve(file.storagePath)
-            return _create_streaming_response(content, file)
-        return fastapi.responses.RedirectResponse(url=url, status_code=302)
-    except Exception as e:
-        # Log the signed URL failure with context
-        logger.error(
-            f"Failed to get signed URL for file {file.id} "
-            f"(storagePath={file.storagePath}): {e}",
-            exc_info=True,
-        )
-        # Fall back to streaming directly from GCS
-        try:
-            content = await storage.retrieve(file.storagePath)
-            return _create_streaming_response(content, file)
-        except Exception as fallback_error:
-            logger.error(
-                f"Fallback streaming also failed for file {file.id} "
-                f"(storagePath={file.storagePath}): {fallback_error}",
-                exc_info=True,
-            )
-            raise
-
-
-@router.get(
-    "/files/{file_id}/download",
-    summary="Download file by ID",
-)
-async def download_file(
-    user_id: Annotated[str, fastapi.Security(get_user_id)],
-    file_id: str,
-) -> Response:
-    """
-    Download a file by its ID.
-
-    Returns the file content directly or redirects to a signed URL for GCS.
-    """
-    workspace = await get_workspace(user_id)
-    if workspace is None:
-        raise fastapi.HTTPException(status_code=404, detail="Workspace not found")
-
-    file = await get_workspace_file(file_id, workspace.id)
-    if file is None:
-        raise fastapi.HTTPException(status_code=404, detail="File not found")
-
-    return await _create_file_download_response(file)

autogpt_platform/backend/backend/api/rest_api.py

@@ -32,7 +32,6 @@ import backend.api.features.postmark.postmark
 import backend.api.features.store.model
 import backend.api.features.store.routes
 import backend.api.features.v1
-import backend.api.features.workspace.routes as workspace_routes
 import backend.data.block
 import backend.data.db
 import backend.data.graph
@@ -53,7 +52,6 @@ from backend.util.exceptions import (
 )
 from backend.util.feature_flag import initialize_launchdarkly, shutdown_launchdarkly
 from backend.util.service import UnhealthyServiceError
-from backend.util.workspace_storage import shutdown_workspace_storage
 
 from .external.fastapi_app import external_api
 from .features.analytics import router as analytics_router
@@ -126,11 +124,6 @@ async def lifespan_context(app: fastapi.FastAPI):
     except Exception as e:
         logger.warning(f"Error shutting down cloud storage handler: {e}")
 
-    try:
-        await shutdown_workspace_storage()
-    except Exception as e:
-        logger.warning(f"Error shutting down workspace storage: {e}")
-
     await backend.data.db.disconnect()
 
 
@@ -322,11 +315,6 @@ app.include_router(
     tags=["v2", "chat"],
     prefix="/api/chat",
 )
-app.include_router(
-    workspace_routes.router,
-    tags=["workspace"],
-    prefix="/api/workspace",
-)
 app.include_router(
     backend.api.features.oauth.router,
     tags=["oauth"],

autogpt_platform/backend/backend/blocks/ai_image_customizer.py

@@ -13,7 +13,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import (
     APIKeyCredentials,
     CredentialsField,
@@ -118,13 +117,11 @@ class AIImageCustomizerBlock(Block):
                 "credentials": TEST_CREDENTIALS_INPUT,
             },
             test_output=[
-                # Output will be a workspace ref or data URI depending on context
-                ("image_url", lambda x: x.startswith(("workspace://", "data:"))),
+                ("image_url", "https://replicate.delivery/generated-image.jpg"),
             ],
             test_mock={
-                # Use data URI to avoid HTTP requests during tests
                 "run_model": lambda *args, **kwargs: MediaFileType(
-                    "data:image/jpeg;base64,/9j/4AAQSkZJRgABAgAAAQABAAD/2wBDAAgGBgcGBQgHBwcJCQgKDBQNDAsLDBkSEw8UHRofHh0aHBwgJC4nICIsIxwcKDcpLDAxNDQ0Hyc5PTgyPC4zNDL/2wBDAQkJCQwLDBgNDRgyIRwhMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjL/wAARCAABAAEDASIAAhEBAxEB/8QAHwAAAQUBAQEBAQEAAAAAAAAAAAECAwQFBgcICQoL/8QAtRAAAgEDAwIEAwUFBAQAAAF9AQIDAAQRBRIhMUEGE1FhByJxFDKBkaEII0KxwRVS0fAkM2JyggkKFhcYGRolJicoKSo0NTY3ODk6Q0RFRkdISUpTVFVWV1hZWmNkZWZnaGlqc3R1dnd4eXqDhIWGh4iJipKTlJWWl5iZmqKjpKWmp6ipqrKztLW2t7i5usLDxMXGx8jJytLT1NXW19jZ2uHi4+Tl5ufo6erx8vP09fb3+Pn6/8QAHwEAAwEBAQEBAQEBAQAAAAAAAAECAwQFBgcICQoL/8QAtREAAgECBAQDBAcFBAQAAQJ3AAECAxEEBSExBhJBUQdhcRMiMoEIFEKRobHBCSMzUvAVYnLRChYkNOEl8RcYGRomJygpKjU2Nzg5OkNERUZHSElKU1RVVldYWVpjZGVmZ2hpanN0dXZ3eHl6goOEhYaHiImKkpOUlZaXmJmaoqOkpaanqKmqsrO0tba3uLm6wsPExcbHyMnK0tPU1dbX2Nna4uPk5ebn6Onq8vP09fb3+Pn6/9oADAMBAAIRAxEAPwD3+iiigD//2Q=="
+                    "https://replicate.delivery/generated-image.jpg"
                 ),
             },
             test_credentials=TEST_CREDENTIALS,
@@ -135,7 +132,8 @@ class AIImageCustomizerBlock(Block):
         input_data: Input,
         *,
         credentials: APIKeyCredentials,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         try:
@@ -143,9 +141,10 @@ class AIImageCustomizerBlock(Block):
             processed_images = await asyncio.gather(
                 *(
                     store_media_file(
+                        graph_exec_id=graph_exec_id,
                         file=img,
-                        execution_context=execution_context,
-                        return_format="for_external_api",  # Get content for Replicate API
+                        user_id=user_id,
+                        return_content=True,
                     )
                     for img in input_data.images
                 )
@@ -159,14 +158,7 @@ class AIImageCustomizerBlock(Block):
                 aspect_ratio=input_data.aspect_ratio.value,
                 output_format=input_data.output_format.value,
             )
-
-            # Store the generated image to the user's workspace for persistence
-            stored_url = await store_media_file(
-                file=result,
-                execution_context=execution_context,
-                return_format="for_block_output",
-            )
-            yield "image_url", stored_url
+            yield "image_url", result
         except Exception as e:
             yield "error", str(e)
 

autogpt_platform/backend/backend/blocks/ai_image_generator_block.py

@@ -6,7 +6,6 @@ from replicate.client import Client as ReplicateClient
 from replicate.helpers import FileOutput
 
 from backend.data.block import Block, BlockCategory, BlockSchemaInput, BlockSchemaOutput
-from backend.data.execution import ExecutionContext
 from backend.data.model import (
     APIKeyCredentials,
     CredentialsField,
@@ -14,8 +13,6 @@ from backend.data.model import (
     SchemaField,
 )
 from backend.integrations.providers import ProviderName
-from backend.util.file import store_media_file
-from backend.util.type import MediaFileType
 
 
 class ImageSize(str, Enum):
@@ -168,13 +165,11 @@ class AIImageGeneratorBlock(Block):
             test_output=[
                 (
                     "image_url",
-                    # Test output is a data URI since we now store images
-                    lambda x: x.startswith("data:image/"),
+                    "https://replicate.delivery/generated-image.webp",
                 ),
             ],
             test_mock={
-                # Return a data URI directly so store_media_file doesn't need to download
-                "_run_client": lambda *args, **kwargs: "data:image/webp;base64,UklGRiQAAABXRUJQVlA4IBgAAAAwAQCdASoBAAEAAQAcJYgCdAEO"
+                "_run_client": lambda *args, **kwargs: "https://replicate.delivery/generated-image.webp"
             },
         )
 
@@ -323,24 +318,11 @@ class AIImageGeneratorBlock(Block):
         style_text = style_map.get(style, "")
         return f"{style_text} of" if style_text else ""
 
-    async def run(
-        self,
-        input_data: Input,
-        *,
-        credentials: APIKeyCredentials,
-        execution_context: ExecutionContext,
-        **kwargs,
-    ):
+    async def run(self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs):
         try:
             url = await self.generate_image(input_data, credentials)
             if url:
-                # Store the generated image to the user's workspace/execution folder
-                stored_url = await store_media_file(
-                    file=MediaFileType(url),
-                    execution_context=execution_context,
-                    return_format="for_block_output",
-                )
-                yield "image_url", stored_url
+                yield "image_url", url
             else:
                 yield "error", "Image generation returned an empty result."
         except Exception as e:

autogpt_platform/backend/backend/blocks/ai_shortform_video_block.py

@@ -13,7 +13,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import (
     APIKeyCredentials,
     CredentialsField,
@@ -22,9 +21,7 @@ from backend.data.model import (
 )
 from backend.integrations.providers import ProviderName
 from backend.util.exceptions import BlockExecutionError
-from backend.util.file import store_media_file
 from backend.util.request import Requests
-from backend.util.type import MediaFileType
 
 TEST_CREDENTIALS = APIKeyCredentials(
     id="01234567-89ab-cdef-0123-456789abcdef",
@@ -274,10 +271,7 @@ class AIShortformVideoCreatorBlock(Block):
                 "voice": Voice.LILY,
                 "video_style": VisualMediaType.STOCK_VIDEOS,
             },
-            test_output=(
-                "video_url",
-                lambda x: x.startswith(("workspace://", "data:")),
-            ),
+            test_output=("video_url", "https://example.com/video.mp4"),
             test_mock={
                 "create_webhook": lambda *args, **kwargs: (
                     "test_uuid",
@@ -286,21 +280,15 @@ class AIShortformVideoCreatorBlock(Block):
                 "create_video": lambda *args, **kwargs: {"pid": "test_pid"},
                 "check_video_status": lambda *args, **kwargs: {
                     "status": "ready",
-                    "videoUrl": "data:video/mp4;base64,AAAA",
+                    "videoUrl": "https://example.com/video.mp4",
                 },
-                # Use data URI to avoid HTTP requests during tests
-                "wait_for_video": lambda *args, **kwargs: "data:video/mp4;base64,AAAA",
+                "wait_for_video": lambda *args, **kwargs: "https://example.com/video.mp4",
             },
             test_credentials=TEST_CREDENTIALS,
         )
 
     async def run(
-        self,
-        input_data: Input,
-        *,
-        credentials: APIKeyCredentials,
-        execution_context: ExecutionContext,
-        **kwargs,
+        self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs
     ) -> BlockOutput:
         # Create a new Webhook.site URL
         webhook_token, webhook_url = await self.create_webhook()
@@ -352,13 +340,7 @@ class AIShortformVideoCreatorBlock(Block):
             )
             video_url = await self.wait_for_video(credentials.api_key, pid)
             logger.debug(f"Video ready: {video_url}")
-            # Store the generated video to the user's workspace for persistence
-            stored_url = await store_media_file(
-                file=MediaFileType(video_url),
-                execution_context=execution_context,
-                return_format="for_block_output",
-            )
-            yield "video_url", stored_url
+            yield "video_url", video_url
 
 
 class AIAdMakerVideoCreatorBlock(Block):
@@ -465,10 +447,7 @@ class AIAdMakerVideoCreatorBlock(Block):
                     "https://cdn.revid.ai/uploads/1747076315114-image.png",
                 ],
             },
-            test_output=(
-                "video_url",
-                lambda x: x.startswith(("workspace://", "data:")),
-            ),
+            test_output=("video_url", "https://example.com/ad.mp4"),
             test_mock={
                 "create_webhook": lambda *args, **kwargs: (
                     "test_uuid",
@@ -477,21 +456,14 @@ class AIAdMakerVideoCreatorBlock(Block):
                 "create_video": lambda *args, **kwargs: {"pid": "test_pid"},
                 "check_video_status": lambda *args, **kwargs: {
                     "status": "ready",
-                    "videoUrl": "data:video/mp4;base64,AAAA",
+                    "videoUrl": "https://example.com/ad.mp4",
                 },
-                "wait_for_video": lambda *args, **kwargs: "data:video/mp4;base64,AAAA",
+                "wait_for_video": lambda *args, **kwargs: "https://example.com/ad.mp4",
             },
             test_credentials=TEST_CREDENTIALS,
         )
 
-    async def run(
-        self,
-        input_data: Input,
-        *,
-        credentials: APIKeyCredentials,
-        execution_context: ExecutionContext,
-        **kwargs,
-    ):
+    async def run(self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs):
         webhook_token, webhook_url = await self.create_webhook()
 
         payload = {
@@ -559,13 +531,7 @@ class AIAdMakerVideoCreatorBlock(Block):
             raise RuntimeError("Failed to create video: No project ID returned")
 
         video_url = await self.wait_for_video(credentials.api_key, pid)
-        # Store the generated video to the user's workspace for persistence
-        stored_url = await store_media_file(
-            file=MediaFileType(video_url),
-            execution_context=execution_context,
-            return_format="for_block_output",
-        )
-        yield "video_url", stored_url
+        yield "video_url", video_url
 
 
 class AIScreenshotToVideoAdBlock(Block):
@@ -660,10 +626,7 @@ class AIScreenshotToVideoAdBlock(Block):
                 "script": "Amazing numbers!",
                 "screenshot_url": "https://cdn.revid.ai/uploads/1747080376028-image.png",
             },
-            test_output=(
-                "video_url",
-                lambda x: x.startswith(("workspace://", "data:")),
-            ),
+            test_output=("video_url", "https://example.com/screenshot.mp4"),
             test_mock={
                 "create_webhook": lambda *args, **kwargs: (
                     "test_uuid",
@@ -672,21 +635,14 @@ class AIScreenshotToVideoAdBlock(Block):
                 "create_video": lambda *args, **kwargs: {"pid": "test_pid"},
                 "check_video_status": lambda *args, **kwargs: {
                     "status": "ready",
-                    "videoUrl": "data:video/mp4;base64,AAAA",
+                    "videoUrl": "https://example.com/screenshot.mp4",
                 },
-                "wait_for_video": lambda *args, **kwargs: "data:video/mp4;base64,AAAA",
+                "wait_for_video": lambda *args, **kwargs: "https://example.com/screenshot.mp4",
             },
             test_credentials=TEST_CREDENTIALS,
         )
 
-    async def run(
-        self,
-        input_data: Input,
-        *,
-        credentials: APIKeyCredentials,
-        execution_context: ExecutionContext,
-        **kwargs,
-    ):
+    async def run(self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs):
         webhook_token, webhook_url = await self.create_webhook()
 
         payload = {
@@ -754,10 +710,4 @@ class AIScreenshotToVideoAdBlock(Block):
             raise RuntimeError("Failed to create video: No project ID returned")
 
         video_url = await self.wait_for_video(credentials.api_key, pid)
-        # Store the generated video to the user's workspace for persistence
-        stored_url = await store_media_file(
-            file=MediaFileType(video_url),
-            execution_context=execution_context,
-            return_format="for_block_output",
-        )
-        yield "video_url", stored_url
+        yield "video_url", video_url

autogpt_platform/backend/backend/blocks/bannerbear/text_overlay.py

@@ -6,7 +6,6 @@ if TYPE_CHECKING:
 
 from pydantic import SecretStr
 
-from backend.data.execution import ExecutionContext
 from backend.sdk import (
     APIKeyCredentials,
     Block,
@@ -18,8 +17,6 @@ from backend.sdk import (
     Requests,
     SchemaField,
 )
-from backend.util.file import store_media_file
-from backend.util.type import MediaFileType
 
 from ._config import bannerbear
 
@@ -138,17 +135,15 @@ class BannerbearTextOverlayBlock(Block):
             },
             test_output=[
                 ("success", True),
-                # Output will be a workspace ref or data URI depending on context
-                ("image_url", lambda x: x.startswith(("workspace://", "data:"))),
+                ("image_url", "https://cdn.bannerbear.com/test-image.jpg"),
                 ("uid", "test-uid-123"),
                 ("status", "completed"),
             ],
             test_mock={
-                # Use data URI to avoid HTTP requests during tests
                 "_make_api_request": lambda *args, **kwargs: {
                     "uid": "test-uid-123",
                     "status": "completed",
-                    "image_url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAgGBgcGBQgHBwcJCQgKDBQNDAsLDBkSEw8UHRofHh0aHBwgJC4nICIsIxwcKDcpLDAxNDQ0Hyc5PTgyPC4zNDL/wAALCAABAAEBAREA/8QAHwAAAQUBAQEBAQEAAAAAAAAAAAECAwQFBgcICQoL/8QAtRAAAgEDAwIEAwUFBAQAAAF9AQIDAAQRBRIhMUEGE1FhByJxFDKBkaEII0KxwRVS0fAkM2JyggkKFhcYGRolJicoKSo0NTY3ODk6Q0RFRkdISUpTVFVWV1hZWmNkZWZnaGlqc3R1dnd4eXqDhIWGh4iJipKTlJWWl5iZmqKjpKWmp6ipqrKztLW2t7i5usLDxMXGx8jJytLT1NXW19jZ2uHi4+Tl5ufo6erx8vP09fb3+Pn6/9oACAEBAAA/APn+v//Z",
+                    "image_url": "https://cdn.bannerbear.com/test-image.jpg",
                 }
             },
             test_credentials=TEST_CREDENTIALS,
@@ -182,12 +177,7 @@ class BannerbearTextOverlayBlock(Block):
             raise Exception(error_msg)
 
     async def run(
-        self,
-        input_data: Input,
-        *,
-        credentials: APIKeyCredentials,
-        execution_context: ExecutionContext,
-        **kwargs,
+        self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs
     ) -> BlockOutput:
         # Build the modifications array
         modifications = []
@@ -244,18 +234,6 @@ class BannerbearTextOverlayBlock(Block):
 
         # Synchronous request - image should be ready
         yield "success", True
-
-        # Store the generated image to workspace for persistence
-        image_url = data.get("image_url", "")
-        if image_url:
-            stored_url = await store_media_file(
-                file=MediaFileType(image_url),
-                execution_context=execution_context,
-                return_format="for_block_output",
-            )
-            yield "image_url", stored_url
-        else:
-            yield "image_url", ""
-
+        yield "image_url", data.get("image_url", "")
         yield "uid", data.get("uid", "")
         yield "status", data.get("status", "completed")

autogpt_platform/backend/backend/blocks/basic.py

@@ -9,7 +9,6 @@ from backend.data.block import (
     BlockSchemaOutput,
     BlockType,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import SchemaField
 from backend.util.file import store_media_file
 from backend.util.type import MediaFileType, convert
@@ -18,10 +17,10 @@ from backend.util.type import MediaFileType, convert
 class FileStoreBlock(Block):
     class Input(BlockSchemaInput):
         file_in: MediaFileType = SchemaField(
-            description="The file to download and store. Can be a URL (https://...), data URI, or local path."
+            description="The file to store in the temporary directory, it can be a URL, data URI, or local path."
         )
         base_64: bool = SchemaField(
-            description="Whether to produce output in base64 format (not recommended, you can pass the file reference across blocks).",
+            description="Whether produce an output in base64 format (not recommended, you can pass the string path just fine accross blocks).",
             default=False,
             advanced=True,
             title="Produce Base64 Output",
@@ -29,18 +28,13 @@ class FileStoreBlock(Block):
 
     class Output(BlockSchemaOutput):
         file_out: MediaFileType = SchemaField(
-            description="Reference to the stored file. In CoPilot: workspace:// URI (visible in list_workspace_files). In graphs: data URI for passing to other blocks."
+            description="The relative path to the stored file in the temporary directory."
         )
 
     def __init__(self):
         super().__init__(
             id="cbb50872-625b-42f0-8203-a2ae78242d8a",
-            description=(
-                "Downloads and stores a file from a URL, data URI, or local path. "
-                "Use this to fetch images, documents, or other files for processing. "
-                "In CoPilot: saves to workspace (use list_workspace_files to see it). "
-                "In graphs: outputs a data URI to pass to other blocks."
-            ),
+            description="Stores the input file in the temporary directory.",
             categories={BlockCategory.BASIC, BlockCategory.MULTIMEDIA},
             input_schema=FileStoreBlock.Input,
             output_schema=FileStoreBlock.Output,
@@ -51,18 +45,15 @@ class FileStoreBlock(Block):
         self,
         input_data: Input,
         *,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
-        # Determine return format based on user preference
-        # for_external_api: always returns data URI (base64) - honors "Produce Base64 Output"
-        # for_block_output: smart format - workspace:// in CoPilot, data URI in graphs
-        return_format = "for_external_api" if input_data.base_64 else "for_block_output"
-
         yield "file_out", await store_media_file(
+            graph_exec_id=graph_exec_id,
             file=input_data.file_in,
-            execution_context=execution_context,
-            return_format=return_format,
+            user_id=user_id,
+            return_content=input_data.base_64,
         )
 
 
@@ -125,7 +116,6 @@ class PrintToConsoleBlock(Block):
             input_schema=PrintToConsoleBlock.Input,
             output_schema=PrintToConsoleBlock.Output,
             test_input={"text": "Hello, World!"},
-            is_sensitive_action=True,
             test_output=[
                 ("output", "Hello, World!"),
                 ("status", "printed"),

autogpt_platform/backend/backend/blocks/claude_code.py

@@ -1,659 +0,0 @@
-import json
-import shlex
-import uuid
-from typing import Literal, Optional
-
-from e2b import AsyncSandbox as BaseAsyncSandbox
-from pydantic import BaseModel, SecretStr
-
-from backend.data.block import (
-    Block,
-    BlockCategory,
-    BlockOutput,
-    BlockSchemaInput,
-    BlockSchemaOutput,
-)
-from backend.data.model import (
-    APIKeyCredentials,
-    CredentialsField,
-    CredentialsMetaInput,
-    SchemaField,
-)
-from backend.integrations.providers import ProviderName
-
-
-class ClaudeCodeExecutionError(Exception):
-    """Exception raised when Claude Code execution fails.
-
-    Carries the sandbox_id so it can be returned to the user for cleanup
-    when dispose_sandbox=False.
-    """
-
-    def __init__(self, message: str, sandbox_id: str = ""):
-        super().__init__(message)
-        self.sandbox_id = sandbox_id
-
-
-# Test credentials for E2B
-TEST_E2B_CREDENTIALS = APIKeyCredentials(
-    id="01234567-89ab-cdef-0123-456789abcdef",
-    provider="e2b",
-    api_key=SecretStr("mock-e2b-api-key"),
-    title="Mock E2B API key",
-    expires_at=None,
-)
-TEST_E2B_CREDENTIALS_INPUT = {
-    "provider": TEST_E2B_CREDENTIALS.provider,
-    "id": TEST_E2B_CREDENTIALS.id,
-    "type": TEST_E2B_CREDENTIALS.type,
-    "title": TEST_E2B_CREDENTIALS.title,
-}
-
-# Test credentials for Anthropic
-TEST_ANTHROPIC_CREDENTIALS = APIKeyCredentials(
-    id="2e568a2b-b2ea-475a-8564-9a676bf31c56",
-    provider="anthropic",
-    api_key=SecretStr("mock-anthropic-api-key"),
-    title="Mock Anthropic API key",
-    expires_at=None,
-)
-TEST_ANTHROPIC_CREDENTIALS_INPUT = {
-    "provider": TEST_ANTHROPIC_CREDENTIALS.provider,
-    "id": TEST_ANTHROPIC_CREDENTIALS.id,
-    "type": TEST_ANTHROPIC_CREDENTIALS.type,
-    "title": TEST_ANTHROPIC_CREDENTIALS.title,
-}
-
-
-class ClaudeCodeBlock(Block):
-    """
-    Execute tasks using Claude Code (Anthropic's AI coding assistant) in an E2B sandbox.
-
-    Claude Code can create files, install tools, run commands, and perform complex
-    coding tasks autonomously within a secure sandbox environment.
-    """
-
-    # Use base template - we'll install Claude Code ourselves for latest version
-    DEFAULT_TEMPLATE = "base"
-
-    class Input(BlockSchemaInput):
-        e2b_credentials: CredentialsMetaInput[
-            Literal[ProviderName.E2B], Literal["api_key"]
-        ] = CredentialsField(
-            description=(
-                "API key for the E2B platform to create the sandbox. "
-                "Get one on the [e2b website](https://e2b.dev/docs)"
-            ),
-        )
-
-        anthropic_credentials: CredentialsMetaInput[
-            Literal[ProviderName.ANTHROPIC], Literal["api_key"]
-        ] = CredentialsField(
-            description=(
-                "API key for Anthropic to power Claude Code. "
-                "Get one at [Anthropic's website](https://console.anthropic.com)"
-            ),
-        )
-
-        prompt: str = SchemaField(
-            description=(
-                "The task or instruction for Claude Code to execute. "
-                "Claude Code can create files, install packages, run commands, "
-                "and perform complex coding tasks."
-            ),
-            placeholder="Create a hello world index.html file",
-            default="",
-            advanced=False,
-        )
-
-        timeout: int = SchemaField(
-            description=(
-                "Sandbox timeout in seconds. Claude Code tasks can take "
-                "a while, so set this appropriately for your task complexity. "
-                "Note: This only applies when creating a new sandbox. "
-                "When reconnecting to an existing sandbox via sandbox_id, "
-                "the original timeout is retained."
-            ),
-            default=300,  # 5 minutes default
-            advanced=True,
-        )
-
-        setup_commands: list[str] = SchemaField(
-            description=(
-                "Optional shell commands to run before executing Claude Code. "
-                "Useful for installing dependencies or setting up the environment."
-            ),
-            default_factory=list,
-            advanced=True,
-        )
-
-        working_directory: str = SchemaField(
-            description="Working directory for Claude Code to operate in.",
-            default="/home/user",
-            advanced=True,
-        )
-
-        # Session/continuation support
-        session_id: str = SchemaField(
-            description=(
-                "Session ID to resume a previous conversation. "
-                "Leave empty for a new conversation. "
-                "Use the session_id from a previous run to continue that conversation."
-            ),
-            default="",
-            advanced=True,
-        )
-
-        sandbox_id: str = SchemaField(
-            description=(
-                "Sandbox ID to reconnect to an existing sandbox. "
-                "Required when resuming a session (along with session_id). "
-                "Use the sandbox_id from a previous run where dispose_sandbox was False."
-            ),
-            default="",
-            advanced=True,
-        )
-
-        conversation_history: str = SchemaField(
-            description=(
-                "Previous conversation history to continue from. "
-                "Use this to restore context on a fresh sandbox if the previous one timed out. "
-                "Pass the conversation_history output from a previous run."
-            ),
-            default="",
-            advanced=True,
-        )
-
-        dispose_sandbox: bool = SchemaField(
-            description=(
-                "Whether to dispose of the sandbox immediately after execution. "
-                "Set to False if you want to continue the conversation later "
-                "(you'll need both sandbox_id and session_id from the output)."
-            ),
-            default=True,
-            advanced=True,
-        )
-
-    class FileOutput(BaseModel):
-        """A file extracted from the sandbox."""
-
-        path: str
-        relative_path: str  # Path relative to working directory (for GitHub, etc.)
-        name: str
-        content: str
-
-    class Output(BlockSchemaOutput):
-        response: str = SchemaField(
-            description="The output/response from Claude Code execution"
-        )
-        files: list["ClaudeCodeBlock.FileOutput"] = SchemaField(
-            description=(
-                "List of text files created/modified by Claude Code during this execution. "
-                "Each file has 'path', 'relative_path', 'name', and 'content' fields."
-            )
-        )
-        conversation_history: str = SchemaField(
-            description=(
-                "Full conversation history including this turn. "
-                "Pass this to conversation_history input to continue on a fresh sandbox "
-                "if the previous sandbox timed out."
-            )
-        )
-        session_id: str = SchemaField(
-            description=(
-                "Session ID for this conversation. "
-                "Pass this back along with sandbox_id to continue the conversation."
-            )
-        )
-        sandbox_id: Optional[str] = SchemaField(
-            description=(
-                "ID of the sandbox instance. "
-                "Pass this back along with session_id to continue the conversation. "
-                "This is None if dispose_sandbox was True (sandbox was disposed)."
-            ),
-            default=None,
-        )
-        error: str = SchemaField(description="Error message if execution failed")
-
-    def __init__(self):
-        super().__init__(
-            id="4e34f4a5-9b89-4326-ba77-2dd6750b7194",
-            description=(
-                "Execute tasks using Claude Code in an E2B sandbox. "
-                "Claude Code can create files, install tools, run commands, "
-                "and perform complex coding tasks autonomously."
-            ),
-            categories={BlockCategory.DEVELOPER_TOOLS, BlockCategory.AI},
-            input_schema=ClaudeCodeBlock.Input,
-            output_schema=ClaudeCodeBlock.Output,
-            test_credentials={
-                "e2b_credentials": TEST_E2B_CREDENTIALS,
-                "anthropic_credentials": TEST_ANTHROPIC_CREDENTIALS,
-            },
-            test_input={
-                "e2b_credentials": TEST_E2B_CREDENTIALS_INPUT,
-                "anthropic_credentials": TEST_ANTHROPIC_CREDENTIALS_INPUT,
-                "prompt": "Create a hello world HTML file",
-                "timeout": 300,
-                "setup_commands": [],
-                "working_directory": "/home/user",
-                "session_id": "",
-                "sandbox_id": "",
-                "conversation_history": "",
-                "dispose_sandbox": True,
-            },
-            test_output=[
-                ("response", "Created index.html with hello world content"),
-                (
-                    "files",
-                    [
-                        {
-                            "path": "/home/user/index.html",
-                            "relative_path": "index.html",
-                            "name": "index.html",
-                            "content": "<html>Hello World</html>",
-                        }
-                    ],
-                ),
-                (
-                    "conversation_history",
-                    "User: Create a hello world HTML file\n"
-                    "Claude: Created index.html with hello world content",
-                ),
-                ("session_id", str),
-                ("sandbox_id", None),  # None because dispose_sandbox=True in test_input
-            ],
-            test_mock={
-                "execute_claude_code": lambda *args, **kwargs: (
-                    "Created index.html with hello world content",  # response
-                    [
-                        ClaudeCodeBlock.FileOutput(
-                            path="/home/user/index.html",
-                            relative_path="index.html",
-                            name="index.html",
-                            content="<html>Hello World</html>",
-                        )
-                    ],  # files
-                    "User: Create a hello world HTML file\n"
-                    "Claude: Created index.html with hello world content",  # conversation_history
-                    "test-session-id",  # session_id
-                    "sandbox_id",  # sandbox_id
-                ),
-            },
-        )
-
-    async def execute_claude_code(
-        self,
-        e2b_api_key: str,
-        anthropic_api_key: str,
-        prompt: str,
-        timeout: int,
-        setup_commands: list[str],
-        working_directory: str,
-        session_id: str,
-        existing_sandbox_id: str,
-        conversation_history: str,
-        dispose_sandbox: bool,
-    ) -> tuple[str, list["ClaudeCodeBlock.FileOutput"], str, str, str]:
-        """
-        Execute Claude Code in an E2B sandbox.
-
-        Returns:
-            Tuple of (response, files, conversation_history, session_id, sandbox_id)
-        """
-
-        # Validate that sandbox_id is provided when resuming a session
-        if session_id and not existing_sandbox_id:
-            raise ValueError(
-                "sandbox_id is required when resuming a session with session_id. "
-                "The session state is stored in the original sandbox. "
-                "If the sandbox has timed out, use conversation_history instead "
-                "to restore context on a fresh sandbox."
-            )
-
-        sandbox = None
-        sandbox_id = ""
-
-        try:
-            # Either reconnect to existing sandbox or create a new one
-            if existing_sandbox_id:
-                # Reconnect to existing sandbox for conversation continuation
-                sandbox = await BaseAsyncSandbox.connect(
-                    sandbox_id=existing_sandbox_id,
-                    api_key=e2b_api_key,
-                )
-            else:
-                # Create new sandbox
-                sandbox = await BaseAsyncSandbox.create(
-                    template=self.DEFAULT_TEMPLATE,
-                    api_key=e2b_api_key,
-                    timeout=timeout,
-                    envs={"ANTHROPIC_API_KEY": anthropic_api_key},
-                )
-
-                # Install Claude Code from npm (ensures we get the latest version)
-                install_result = await sandbox.commands.run(
-                    "npm install -g @anthropic-ai/claude-code@latest",
-                    timeout=120,  # 2 min timeout for install
-                )
-                if install_result.exit_code != 0:
-                    raise Exception(
-                        f"Failed to install Claude Code: {install_result.stderr}"
-                    )
-
-                # Run any user-provided setup commands
-                for cmd in setup_commands:
-                    setup_result = await sandbox.commands.run(cmd)
-                    if setup_result.exit_code != 0:
-                        raise Exception(
-                            f"Setup command failed: {cmd}\n"
-                            f"Exit code: {setup_result.exit_code}\n"
-                            f"Stdout: {setup_result.stdout}\n"
-                            f"Stderr: {setup_result.stderr}"
-                        )
-
-            # Capture sandbox_id immediately after creation/connection
-            # so it's available for error recovery if dispose_sandbox=False
-            sandbox_id = sandbox.sandbox_id
-
-            # Generate or use provided session ID
-            current_session_id = session_id if session_id else str(uuid.uuid4())
-
-            # Build base Claude flags
-            base_flags = "-p --dangerously-skip-permissions --output-format json"
-
-            # Add conversation history context if provided (for fresh sandbox continuation)
-            history_flag = ""
-            if conversation_history and not session_id:
-                # Inject previous conversation as context via system prompt
-                # Use consistent escaping via _escape_prompt helper
-                escaped_history = self._escape_prompt(
-                    f"Previous conversation context: {conversation_history}"
-                )
-                history_flag = f" --append-system-prompt {escaped_history}"
-
-            # Build Claude command based on whether we're resuming or starting new
-            # Use shlex.quote for working_directory and session IDs to prevent injection
-            safe_working_dir = shlex.quote(working_directory)
-            if session_id:
-                # Resuming existing session (sandbox still alive)
-                safe_session_id = shlex.quote(session_id)
-                claude_command = (
-                    f"cd {safe_working_dir} && "
-                    f"echo {self._escape_prompt(prompt)} | "
-                    f"claude --resume {safe_session_id} {base_flags}"
-                )
-            else:
-                # New session with specific ID
-                safe_current_session_id = shlex.quote(current_session_id)
-                claude_command = (
-                    f"cd {safe_working_dir} && "
-                    f"echo {self._escape_prompt(prompt)} | "
-                    f"claude --session-id {safe_current_session_id} {base_flags}{history_flag}"
-                )
-
-            # Capture timestamp before running Claude Code to filter files later
-            # Capture timestamp 1 second in the past to avoid race condition with file creation
-            timestamp_result = await sandbox.commands.run(
-                "date -u -d '1 second ago' +%Y-%m-%dT%H:%M:%S"
-            )
-            if timestamp_result.exit_code != 0:
-                raise RuntimeError(
-                    f"Failed to capture timestamp: {timestamp_result.stderr}"
-                )
-            start_timestamp = (
-                timestamp_result.stdout.strip() if timestamp_result.stdout else None
-            )
-
-            result = await sandbox.commands.run(
-                claude_command,
-                timeout=0,  # No command timeout - let sandbox timeout handle it
-            )
-
-            # Check for command failure
-            if result.exit_code != 0:
-                error_msg = result.stderr or result.stdout or "Unknown error"
-                raise Exception(
-                    f"Claude Code command failed with exit code {result.exit_code}:\n"
-                    f"{error_msg}"
-                )
-
-            raw_output = result.stdout or ""
-
-            # Parse JSON output to extract response and build conversation history
-            response = ""
-            new_conversation_history = conversation_history or ""
-
-            try:
-                # The JSON output contains the result
-                output_data = json.loads(raw_output)
-                response = output_data.get("result", raw_output)
-
-                # Build conversation history entry
-                turn_entry = f"User: {prompt}\nClaude: {response}"
-                if new_conversation_history:
-                    new_conversation_history = (
-                        f"{new_conversation_history}\n\n{turn_entry}"
-                    )
-                else:
-                    new_conversation_history = turn_entry
-
-            except json.JSONDecodeError:
-                # If not valid JSON, use raw output
-                response = raw_output
-                turn_entry = f"User: {prompt}\nClaude: {response}"
-                if new_conversation_history:
-                    new_conversation_history = (
-                        f"{new_conversation_history}\n\n{turn_entry}"
-                    )
-                else:
-                    new_conversation_history = turn_entry
-
-            # Extract files created/modified during this run
-            files = await self._extract_files(
-                sandbox, working_directory, start_timestamp
-            )
-
-            return (
-                response,
-                files,
-                new_conversation_history,
-                current_session_id,
-                sandbox_id,
-            )
-
-        except Exception as e:
-            # Wrap exception with sandbox_id so caller can access/cleanup
-            # the preserved sandbox when dispose_sandbox=False
-            raise ClaudeCodeExecutionError(str(e), sandbox_id) from e
-
-        finally:
-            if dispose_sandbox and sandbox:
-                await sandbox.kill()
-
-    async def _extract_files(
-        self,
-        sandbox: BaseAsyncSandbox,
-        working_directory: str,
-        since_timestamp: str | None = None,
-    ) -> list["ClaudeCodeBlock.FileOutput"]:
-        """
-        Extract text files created/modified during this Claude Code execution.
-
-        Args:
-            sandbox: The E2B sandbox instance
-            working_directory: Directory to search for files
-            since_timestamp: ISO timestamp - only return files modified after this time
-
-        Returns:
-            List of FileOutput objects with path, relative_path, name, and content
-        """
-        files: list[ClaudeCodeBlock.FileOutput] = []
-
-        # Text file extensions we can safely read as text
-        text_extensions = {
-            ".txt",
-            ".md",
-            ".html",
-            ".htm",
-            ".css",
-            ".js",
-            ".ts",
-            ".jsx",
-            ".tsx",
-            ".json",
-            ".xml",
-            ".yaml",
-            ".yml",
-            ".toml",
-            ".ini",
-            ".cfg",
-            ".conf",
-            ".py",
-            ".rb",
-            ".php",
-            ".java",
-            ".c",
-            ".cpp",
-            ".h",
-            ".hpp",
-            ".cs",
-            ".go",
-            ".rs",
-            ".swift",
-            ".kt",
-            ".scala",
-            ".sh",
-            ".bash",
-            ".zsh",
-            ".sql",
-            ".graphql",
-            ".env",
-            ".gitignore",
-            ".dockerfile",
-            "Dockerfile",
-            ".vue",
-            ".svelte",
-            ".astro",
-            ".mdx",
-            ".rst",
-            ".tex",
-            ".csv",
-            ".log",
-        }
-
-        try:
-            # List files recursively using find command
-            # Exclude node_modules and .git directories, but allow hidden files
-            # like .env and .gitignore (they're filtered by text_extensions later)
-            # Filter by timestamp to only get files created/modified during this run
-            safe_working_dir = shlex.quote(working_directory)
-            timestamp_filter = ""
-            if since_timestamp:
-                timestamp_filter = f"-newermt {shlex.quote(since_timestamp)} "
-            find_result = await sandbox.commands.run(
-                f"find {safe_working_dir} -type f "
-                f"{timestamp_filter}"
-                f"-not -path '*/node_modules/*' "
-                f"-not -path '*/.git/*' "
-                f"2>/dev/null"
-            )
-
-            if find_result.stdout:
-                for file_path in find_result.stdout.strip().split("\n"):
-                    if not file_path:
-                        continue
-
-                    # Check if it's a text file we can read
-                    is_text = any(
-                        file_path.endswith(ext) for ext in text_extensions
-                    ) or file_path.endswith("Dockerfile")
-
-                    if is_text:
-                        try:
-                            content = await sandbox.files.read(file_path)
-                            # Handle bytes or string
-                            if isinstance(content, bytes):
-                                content = content.decode("utf-8", errors="replace")
-
-                            # Extract filename from path
-                            file_name = file_path.split("/")[-1]
-
-                            # Calculate relative path by stripping working directory
-                            relative_path = file_path
-                            if file_path.startswith(working_directory):
-                                relative_path = file_path[len(working_directory) :]
-                                # Remove leading slash if present
-                                if relative_path.startswith("/"):
-                                    relative_path = relative_path[1:]
-
-                            files.append(
-                                ClaudeCodeBlock.FileOutput(
-                                    path=file_path,
-                                    relative_path=relative_path,
-                                    name=file_name,
-                                    content=content,
-                                )
-                            )
-                        except Exception:
-                            # Skip files that can't be read
-                            pass
-
-        except Exception:
-            # If file extraction fails, return empty results
-            pass
-
-        return files
-
-    def _escape_prompt(self, prompt: str) -> str:
-        """Escape the prompt for safe shell execution."""
-        # Use single quotes and escape any single quotes in the prompt
-        escaped = prompt.replace("'", "'\"'\"'")
-        return f"'{escaped}'"
-
-    async def run(
-        self,
-        input_data: Input,
-        *,
-        e2b_credentials: APIKeyCredentials,
-        anthropic_credentials: APIKeyCredentials,
-        **kwargs,
-    ) -> BlockOutput:
-        try:
-            (
-                response,
-                files,
-                conversation_history,
-                session_id,
-                sandbox_id,
-            ) = await self.execute_claude_code(
-                e2b_api_key=e2b_credentials.api_key.get_secret_value(),
-                anthropic_api_key=anthropic_credentials.api_key.get_secret_value(),
-                prompt=input_data.prompt,
-                timeout=input_data.timeout,
-                setup_commands=input_data.setup_commands,
-                working_directory=input_data.working_directory,
-                session_id=input_data.session_id,
-                existing_sandbox_id=input_data.sandbox_id,
-                conversation_history=input_data.conversation_history,
-                dispose_sandbox=input_data.dispose_sandbox,
-            )
-
-            yield "response", response
-            # Always yield files (empty list if none) to match Output schema
-            yield "files", [f.model_dump() for f in files]
-            # Always yield conversation_history so user can restore context on fresh sandbox
-            yield "conversation_history", conversation_history
-            # Always yield session_id so user can continue conversation
-            yield "session_id", session_id
-            # Always yield sandbox_id (None if disposed) to match Output schema
-            yield "sandbox_id", sandbox_id if not input_data.dispose_sandbox else None
-
-        except ClaudeCodeExecutionError as e:
-            yield "error", str(e)
-            # If sandbox was preserved (dispose_sandbox=False), yield sandbox_id
-            # so user can reconnect to or clean up the orphaned sandbox
-            if not input_data.dispose_sandbox and e.sandbox_id:
-                yield "sandbox_id", e.sandbox_id
-        except Exception as e:
-            yield "error", str(e)

autogpt_platform/backend/backend/blocks/data_manipulation.py

@@ -680,58 +680,3 @@ class ListIsEmptyBlock(Block):
 
     async def run(self, input_data: Input, **kwargs) -> BlockOutput:
         yield "is_empty", len(input_data.list) == 0
-
-
-class ConcatenateListsBlock(Block):
-    class Input(BlockSchemaInput):
-        lists: List[List[Any]] = SchemaField(
-            description="A list of lists to concatenate together. All lists will be combined in order into a single list.",
-            placeholder="e.g., [[1, 2], [3, 4], [5, 6]]",
-        )
-
-    class Output(BlockSchemaOutput):
-        concatenated_list: List[Any] = SchemaField(
-            description="The concatenated list containing all elements from all input lists in order."
-        )
-        error: str = SchemaField(
-            description="Error message if concatenation failed due to invalid input types."
-        )
-
-    def __init__(self):
-        super().__init__(
-            id="3cf9298b-5817-4141-9d80-7c2cc5199c8e",
-            description="Concatenates multiple lists into a single list. All elements from all input lists are combined in order.",
-            categories={BlockCategory.BASIC},
-            input_schema=ConcatenateListsBlock.Input,
-            output_schema=ConcatenateListsBlock.Output,
-            test_input=[
-                {"lists": [[1, 2, 3], [4, 5, 6]]},
-                {"lists": [["a", "b"], ["c"], ["d", "e", "f"]]},
-                {"lists": [[1, 2], []]},
-                {"lists": []},
-            ],
-            test_output=[
-                ("concatenated_list", [1, 2, 3, 4, 5, 6]),
-                ("concatenated_list", ["a", "b", "c", "d", "e", "f"]),
-                ("concatenated_list", [1, 2]),
-                ("concatenated_list", []),
-            ],
-        )
-
-    async def run(self, input_data: Input, **kwargs) -> BlockOutput:
-        concatenated = []
-        for idx, lst in enumerate(input_data.lists):
-            if lst is None:
-                # Skip None values to avoid errors
-                continue
-            if not isinstance(lst, list):
-                # Type validation: each item must be a list
-                # Strings are iterable and would cause extend() to iterate character-by-character
-                # Non-iterable types would raise TypeError
-                yield "error", (
-                    f"Invalid input at index {idx}: expected a list, got {type(lst).__name__}. "
-                    f"All items in 'lists' must be lists (e.g., [[1, 2], [3, 4]])."
-                )
-                return
-            concatenated.extend(lst)
-        yield "concatenated_list", concatenated

autogpt_platform/backend/backend/blocks/discord/bot_blocks.py

@@ -15,7 +15,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import APIKeyCredentials, SchemaField
 from backend.util.file import store_media_file
 from backend.util.request import Requests
@@ -667,7 +666,8 @@ class SendDiscordFileBlock(Block):
         file: MediaFileType,
         filename: str,
         message_content: str,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
     ) -> dict:
         intents = discord.Intents.default()
         intents.guilds = True
@@ -731,9 +731,10 @@ class SendDiscordFileBlock(Block):
                     # Local file path - read from stored media file
                     # This would be a path from a previous block's output
                     stored_file = await store_media_file(
+                        graph_exec_id=graph_exec_id,
                         file=file,
-                        execution_context=execution_context,
-                        return_format="for_external_api",  # Get content to send to Discord
+                        user_id=user_id,
+                        return_content=True,  # Get as data URI
                     )
                     # Now process as data URI
                     header, encoded = stored_file.split(",", 1)
@@ -780,7 +781,8 @@ class SendDiscordFileBlock(Block):
         input_data: Input,
         *,
         credentials: APIKeyCredentials,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         try:
@@ -791,7 +793,8 @@ class SendDiscordFileBlock(Block):
                 file=input_data.file,
                 filename=input_data.filename,
                 message_content=input_data.message_content,
-                execution_context=execution_context,
+                graph_exec_id=graph_exec_id,
+                user_id=user_id,
             )
 
             yield "status", result.get("status", "Unknown error")

autogpt_platform/backend/backend/blocks/fal/ai_video_generator.py

@@ -17,11 +17,8 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import SchemaField
-from backend.util.file import store_media_file
 from backend.util.request import ClientResponseError, Requests
-from backend.util.type import MediaFileType
 
 logger = logging.getLogger(__name__)
 
@@ -67,13 +64,9 @@ class AIVideoGeneratorBlock(Block):
                 "credentials": TEST_CREDENTIALS_INPUT,
             },
             test_credentials=TEST_CREDENTIALS,
-            test_output=[
-                # Output will be a workspace ref or data URI depending on context
-                ("video_url", lambda x: x.startswith(("workspace://", "data:"))),
-            ],
+            test_output=[("video_url", "https://fal.media/files/example/video.mp4")],
             test_mock={
-                # Use data URI to avoid HTTP requests during tests
-                "generate_video": lambda *args, **kwargs: "data:video/mp4;base64,AAAA"
+                "generate_video": lambda *args, **kwargs: "https://fal.media/files/example/video.mp4"
             },
         )
 
@@ -215,22 +208,11 @@ class AIVideoGeneratorBlock(Block):
             raise RuntimeError(f"API request failed: {str(e)}")
 
     async def run(
-        self,
-        input_data: Input,
-        *,
-        credentials: FalCredentials,
-        execution_context: ExecutionContext,
-        **kwargs,
+        self, input_data: Input, *, credentials: FalCredentials, **kwargs
     ) -> BlockOutput:
         try:
             video_url = await self.generate_video(input_data, credentials)
-            # Store the generated video to the user's workspace for persistence
-            stored_url = await store_media_file(
-                file=MediaFileType(video_url),
-                execution_context=execution_context,
-                return_format="for_block_output",
-            )
-            yield "video_url", stored_url
+            yield "video_url", video_url
         except Exception as e:
             error_message = str(e)
             yield "error", error_message

autogpt_platform/backend/backend/blocks/flux_kontext.py

@@ -12,7 +12,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import (
     APIKeyCredentials,
     CredentialsField,
@@ -122,12 +121,10 @@ class AIImageEditorBlock(Block):
                 "credentials": TEST_CREDENTIALS_INPUT,
             },
             test_output=[
-                # Output will be a workspace ref or data URI depending on context
-                ("output_image", lambda x: x.startswith(("workspace://", "data:"))),
+                ("output_image", "https://replicate.com/output/edited-image.png"),
             ],
             test_mock={
-                # Use data URI to avoid HTTP requests during tests
-                "run_model": lambda *args, **kwargs: "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==",
+                "run_model": lambda *args, **kwargs: "https://replicate.com/output/edited-image.png",
             },
             test_credentials=TEST_CREDENTIALS,
         )
@@ -137,7 +134,8 @@ class AIImageEditorBlock(Block):
         input_data: Input,
         *,
         credentials: APIKeyCredentials,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         result = await self.run_model(
@@ -146,25 +144,20 @@ class AIImageEditorBlock(Block):
             prompt=input_data.prompt,
             input_image_b64=(
                 await store_media_file(
+                    graph_exec_id=graph_exec_id,
                     file=input_data.input_image,
-                    execution_context=execution_context,
-                    return_format="for_external_api",  # Get content for Replicate API
+                    user_id=user_id,
+                    return_content=True,
                 )
                 if input_data.input_image
                 else None
             ),
             aspect_ratio=input_data.aspect_ratio.value,
             seed=input_data.seed,
-            user_id=execution_context.user_id or "",
-            graph_exec_id=execution_context.graph_exec_id or "",
+            user_id=user_id,
+            graph_exec_id=graph_exec_id,
         )
-        # Store the generated image to the user's workspace for persistence
-        stored_url = await store_media_file(
-            file=result,
-            execution_context=execution_context,
-            return_format="for_block_output",
-        )
-        yield "output_image", stored_url
+        yield "output_image", result
 
     async def run_model(
         self,

autogpt_platform/backend/backend/blocks/google/gmail.py

@@ -21,7 +21,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import SchemaField
 from backend.util.file import MediaFileType, get_exec_file_path, store_media_file
 from backend.util.settings import Settings
@@ -96,7 +95,8 @@ def _make_mime_text(
 
 async def create_mime_message(
     input_data,
-    execution_context: ExecutionContext,
+    graph_exec_id: str,
+    user_id: str,
 ) -> str:
     """Create a MIME message with attachments and return base64-encoded raw message."""
 
@@ -117,12 +117,12 @@ async def create_mime_message(
     if input_data.attachments:
         for attach in input_data.attachments:
             local_path = await store_media_file(
+                user_id=user_id,
+                graph_exec_id=graph_exec_id,
                 file=attach,
-                execution_context=execution_context,
-                return_format="for_local_processing",
+                return_content=False,
             )
-            assert execution_context.graph_exec_id  # Validated by store_media_file
-            abs_path = get_exec_file_path(execution_context.graph_exec_id, local_path)
+            abs_path = get_exec_file_path(graph_exec_id, local_path)
             part = MIMEBase("application", "octet-stream")
             with open(abs_path, "rb") as f:
                 part.set_payload(f.read())
@@ -582,25 +582,27 @@ class GmailSendBlock(GmailBase):
         input_data: Input,
         *,
         credentials: GoogleCredentials,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         service = self._build_service(credentials, **kwargs)
         result = await self._send_email(
             service,
             input_data,
-            execution_context,
+            graph_exec_id,
+            user_id,
         )
         yield "result", result
 
     async def _send_email(
-        self, service, input_data: Input, execution_context: ExecutionContext
+        self, service, input_data: Input, graph_exec_id: str, user_id: str
     ) -> dict:
         if not input_data.to or not input_data.subject or not input_data.body:
             raise ValueError(
                 "At least one recipient, subject, and body are required for sending an email"
             )
-        raw_message = await create_mime_message(input_data, execution_context)
+        raw_message = await create_mime_message(input_data, graph_exec_id, user_id)
         sent_message = await asyncio.to_thread(
             lambda: service.users()
             .messages()
@@ -690,28 +692,30 @@ class GmailCreateDraftBlock(GmailBase):
         input_data: Input,
         *,
         credentials: GoogleCredentials,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         service = self._build_service(credentials, **kwargs)
         result = await self._create_draft(
             service,
             input_data,
-            execution_context,
+            graph_exec_id,
+            user_id,
         )
         yield "result", GmailDraftResult(
             id=result["id"], message_id=result["message"]["id"], status="draft_created"
         )
 
     async def _create_draft(
-        self, service, input_data: Input, execution_context: ExecutionContext
+        self, service, input_data: Input, graph_exec_id: str, user_id: str
     ) -> dict:
         if not input_data.to or not input_data.subject:
             raise ValueError(
                 "At least one recipient and subject are required for creating a draft"
             )
 
-        raw_message = await create_mime_message(input_data, execution_context)
+        raw_message = await create_mime_message(input_data, graph_exec_id, user_id)
         draft = await asyncio.to_thread(
             lambda: service.users()
             .drafts()
@@ -1096,7 +1100,7 @@ class GmailGetThreadBlock(GmailBase):
 
 
 async def _build_reply_message(
-    service, input_data, execution_context: ExecutionContext
+    service, input_data, graph_exec_id: str, user_id: str
 ) -> tuple[str, str]:
     """
     Builds a reply MIME message for Gmail threads.
@@ -1186,12 +1190,12 @@ async def _build_reply_message(
     # Handle attachments
     for attach in input_data.attachments:
         local_path = await store_media_file(
+            user_id=user_id,
+            graph_exec_id=graph_exec_id,
             file=attach,
-            execution_context=execution_context,
-            return_format="for_local_processing",
+            return_content=False,
         )
-        assert execution_context.graph_exec_id  # Validated by store_media_file
-        abs_path = get_exec_file_path(execution_context.graph_exec_id, local_path)
+        abs_path = get_exec_file_path(graph_exec_id, local_path)
         part = MIMEBase("application", "octet-stream")
         with open(abs_path, "rb") as f:
             part.set_payload(f.read())
@@ -1307,14 +1311,16 @@ class GmailReplyBlock(GmailBase):
         input_data: Input,
         *,
         credentials: GoogleCredentials,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         service = self._build_service(credentials, **kwargs)
         message = await self._reply(
             service,
             input_data,
-            execution_context,
+            graph_exec_id,
+            user_id,
         )
         yield "messageId", message["id"]
         yield "threadId", message.get("threadId", input_data.threadId)
@@ -1337,11 +1343,11 @@ class GmailReplyBlock(GmailBase):
         yield "email", email
 
     async def _reply(
-        self, service, input_data: Input, execution_context: ExecutionContext
+        self, service, input_data: Input, graph_exec_id: str, user_id: str
     ) -> dict:
         # Build the reply message using the shared helper
         raw, thread_id = await _build_reply_message(
-            service, input_data, execution_context
+            service, input_data, graph_exec_id, user_id
         )
 
         # Send the message
@@ -1435,14 +1441,16 @@ class GmailDraftReplyBlock(GmailBase):
         input_data: Input,
         *,
         credentials: GoogleCredentials,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         service = self._build_service(credentials, **kwargs)
         draft = await self._create_draft_reply(
             service,
             input_data,
-            execution_context,
+            graph_exec_id,
+            user_id,
         )
         yield "draftId", draft["id"]
         yield "messageId", draft["message"]["id"]
@@ -1450,11 +1458,11 @@ class GmailDraftReplyBlock(GmailBase):
         yield "status", "draft_created"
 
     async def _create_draft_reply(
-        self, service, input_data: Input, execution_context: ExecutionContext
+        self, service, input_data: Input, graph_exec_id: str, user_id: str
     ) -> dict:
         # Build the reply message using the shared helper
         raw, thread_id = await _build_reply_message(
-            service, input_data, execution_context
+            service, input_data, graph_exec_id, user_id
         )
 
         # Create draft with proper thread association
@@ -1621,21 +1629,23 @@ class GmailForwardBlock(GmailBase):
         input_data: Input,
         *,
         credentials: GoogleCredentials,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         service = self._build_service(credentials, **kwargs)
         result = await self._forward_message(
             service,
             input_data,
-            execution_context,
+            graph_exec_id,
+            user_id,
         )
         yield "messageId", result["id"]
         yield "threadId", result.get("threadId", "")
         yield "status", "forwarded"
 
     async def _forward_message(
-        self, service, input_data: Input, execution_context: ExecutionContext
+        self, service, input_data: Input, graph_exec_id: str, user_id: str
     ) -> dict:
         if not input_data.to:
             raise ValueError("At least one recipient is required for forwarding")
@@ -1717,12 +1727,12 @@ To: {original_to}
         # Add any additional attachments
         for attach in input_data.additionalAttachments:
             local_path = await store_media_file(
+                user_id=user_id,
+                graph_exec_id=graph_exec_id,
                 file=attach,
-                execution_context=execution_context,
-                return_format="for_local_processing",
+                return_content=False,
             )
-            assert execution_context.graph_exec_id  # Validated by store_media_file
-            abs_path = get_exec_file_path(execution_context.graph_exec_id, local_path)
+            abs_path = get_exec_file_path(graph_exec_id, local_path)
             part = MIMEBase("application", "octet-stream")
             with open(abs_path, "rb") as f:
                 part.set_payload(f.read())

autogpt_platform/backend/backend/blocks/helpers/review.py

@@ -9,7 +9,7 @@ from typing import Any, Optional
 from prisma.enums import ReviewStatus
 from pydantic import BaseModel
 
-from backend.data.execution import ExecutionStatus
+from backend.data.execution import ExecutionContext, ExecutionStatus
 from backend.data.human_review import ReviewResult
 from backend.executor.manager import async_update_node_execution_status
 from backend.util.clients import get_database_manager_async_client
@@ -28,11 +28,6 @@ class ReviewDecision(BaseModel):
 class HITLReviewHelper:
     """Helper class for Human-In-The-Loop review operations."""
 
-    @staticmethod
-    async def check_approval(**kwargs) -> Optional[ReviewResult]:
-        """Check if there's an existing approval for this node execution."""
-        return await get_database_manager_async_client().check_approval(**kwargs)
-
     @staticmethod
     async def get_or_create_human_review(**kwargs) -> Optional[ReviewResult]:
         """Create or retrieve a human review from the database."""
@@ -60,11 +55,11 @@ class HITLReviewHelper:
     async def _handle_review_request(
         input_data: Any,
         user_id: str,
-        node_id: str,
         node_exec_id: str,
         graph_exec_id: str,
         graph_id: str,
         graph_version: int,
+        execution_context: ExecutionContext,
         block_name: str = "Block",
         editable: bool = False,
     ) -> Optional[ReviewResult]:
@@ -74,11 +69,11 @@ class HITLReviewHelper:
         Args:
             input_data: The input data to be reviewed
             user_id: ID of the user requesting the review
-            node_id: ID of the node in the graph definition
             node_exec_id: ID of the node execution
             graph_exec_id: ID of the graph execution
             graph_id: ID of the graph
             graph_version: Version of the graph
+            execution_context: Current execution context
             block_name: Name of the block requesting review
             editable: Whether the reviewer can edit the data
 
@@ -88,41 +83,15 @@ class HITLReviewHelper:
         Raises:
             Exception: If review creation or status update fails
         """
-        # Note: Safe mode checks (human_in_the_loop_safe_mode, sensitive_action_safe_mode)
-        # are handled by the caller:
-        # - HITL blocks check human_in_the_loop_safe_mode in their run() method
-        # - Sensitive action blocks check sensitive_action_safe_mode in is_block_exec_need_review()
-        # This function only handles checking for existing approvals.
-
-        # Check if this node has already been approved (normal or auto-approval)
-        if approval_result := await HITLReviewHelper.check_approval(
-            node_exec_id=node_exec_id,
-            graph_exec_id=graph_exec_id,
-            node_id=node_id,
-            user_id=user_id,
-            input_data=input_data,
-        ):
+        # Skip review if safe mode is disabled - return auto-approved result
+        if not execution_context.safe_mode:
             logger.info(
-                f"Block {block_name} skipping review for node {node_exec_id} - "
-                f"found existing approval"
-            )
-            # Return a new ReviewResult with the current node_exec_id but approved status
-            # For auto-approvals, always use current input_data
-            # For normal approvals, use approval_result.data unless it's None
-            is_auto_approval = approval_result.node_exec_id != node_exec_id
-            approved_data = (
-                input_data
-                if is_auto_approval
-                else (
-                    approval_result.data
-                    if approval_result.data is not None
-                    else input_data
-                )
+                f"Block {block_name} skipping review for node {node_exec_id} - safe mode disabled"
             )
             return ReviewResult(
-                data=approved_data,
+                data=input_data,
                 status=ReviewStatus.APPROVED,
-                message=approval_result.message,
+                message="Auto-approved (safe mode disabled)",
                 processed=True,
                 node_exec_id=node_exec_id,
             )
@@ -134,7 +103,7 @@ class HITLReviewHelper:
             graph_id=graph_id,
             graph_version=graph_version,
             input_data=input_data,
-            message=block_name,  # Use block_name directly as the message
+            message=f"Review required for {block_name} execution",
             editable=editable,
         )
 
@@ -160,11 +129,11 @@ class HITLReviewHelper:
     async def handle_review_decision(
         input_data: Any,
         user_id: str,
-        node_id: str,
         node_exec_id: str,
         graph_exec_id: str,
         graph_id: str,
         graph_version: int,
+        execution_context: ExecutionContext,
         block_name: str = "Block",
         editable: bool = False,
     ) -> Optional[ReviewDecision]:
@@ -174,11 +143,11 @@ class HITLReviewHelper:
         Args:
             input_data: The input data to be reviewed
             user_id: ID of the user requesting the review
-            node_id: ID of the node in the graph definition
             node_exec_id: ID of the node execution
             graph_exec_id: ID of the graph execution
             graph_id: ID of the graph
             graph_version: Version of the graph
+            execution_context: Current execution context
             block_name: Name of the block requesting review
             editable: Whether the reviewer can edit the data
 
@@ -189,11 +158,11 @@ class HITLReviewHelper:
         review_result = await HITLReviewHelper._handle_review_request(
             input_data=input_data,
             user_id=user_id,
-            node_id=node_id,
             node_exec_id=node_exec_id,
             graph_exec_id=graph_exec_id,
             graph_id=graph_id,
             graph_version=graph_version,
+            execution_context=execution_context,
             block_name=block_name,
             editable=editable,
         )

autogpt_platform/backend/backend/blocks/http.py

@@ -15,7 +15,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import (
     CredentialsField,
     CredentialsMetaInput,
@@ -117,9 +116,10 @@ class SendWebRequestBlock(Block):
 
     @staticmethod
     async def _prepare_files(
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
         files_name: str,
         files: list[MediaFileType],
+        user_id: str,
     ) -> list[tuple[str, tuple[str, BytesIO, str]]]:
         """
         Prepare files for the request by storing them and reading their content.
@@ -127,16 +127,11 @@ class SendWebRequestBlock(Block):
         (files_name, (filename, BytesIO, mime_type))
         """
         files_payload: list[tuple[str, tuple[str, BytesIO, str]]] = []
-        graph_exec_id = execution_context.graph_exec_id
-        if graph_exec_id is None:
-            raise ValueError("graph_exec_id is required for file operations")
 
         for media in files:
             # Normalise to a list so we can repeat the same key
             rel_path = await store_media_file(
-                file=media,
-                execution_context=execution_context,
-                return_format="for_local_processing",
+                graph_exec_id, media, user_id, return_content=False
             )
             abs_path = get_exec_file_path(graph_exec_id, rel_path)
             async with aiofiles.open(abs_path, "rb") as f:
@@ -148,7 +143,7 @@ class SendWebRequestBlock(Block):
         return files_payload
 
     async def run(
-        self, input_data: Input, *, execution_context: ExecutionContext, **kwargs
+        self, input_data: Input, *, graph_exec_id: str, user_id: str, **kwargs
     ) -> BlockOutput:
         # ─── Parse/normalise body ────────────────────────────────────
         body = input_data.body
@@ -179,7 +174,7 @@ class SendWebRequestBlock(Block):
         files_payload: list[tuple[str, tuple[str, BytesIO, str]]] = []
         if use_files:
             files_payload = await self._prepare_files(
-                execution_context, input_data.files_name, input_data.files
+                graph_exec_id, input_data.files_name, input_data.files, user_id
             )
 
         # Enforce body format rules
@@ -243,8 +238,9 @@ class SendAuthenticatedWebRequestBlock(SendWebRequestBlock):
         self,
         input_data: Input,
         *,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
         credentials: HostScopedCredentials,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         # Create SendWebRequestBlock.Input from our input (removing credentials field)
@@ -275,6 +271,6 @@ class SendAuthenticatedWebRequestBlock(SendWebRequestBlock):
 
         # Use parent class run method
         async for output_name, output_data in super().run(
-            base_input, execution_context=execution_context, **kwargs
+            base_input, graph_exec_id=graph_exec_id, user_id=user_id, **kwargs
         ):
             yield output_name, output_data

autogpt_platform/backend/backend/blocks/human_in_the_loop.py

@@ -97,7 +97,6 @@ class HumanInTheLoopBlock(Block):
         input_data: Input,
         *,
         user_id: str,
-        node_id: str,
         node_exec_id: str,
         graph_exec_id: str,
         graph_id: str,
@@ -105,7 +104,7 @@ class HumanInTheLoopBlock(Block):
         execution_context: ExecutionContext,
         **_kwargs,
     ) -> BlockOutput:
-        if not execution_context.human_in_the_loop_safe_mode:
+        if not execution_context.safe_mode:
             logger.info(
                 f"HITL block skipping review for node {node_exec_id} - safe mode disabled"
             )
@@ -116,12 +115,12 @@ class HumanInTheLoopBlock(Block):
         decision = await self.handle_review_decision(
             input_data=input_data.data,
             user_id=user_id,
-            node_id=node_id,
             node_exec_id=node_exec_id,
             graph_exec_id=graph_exec_id,
             graph_id=graph_id,
             graph_version=graph_version,
-            block_name=input_data.name,  # Use user-provided name instead of block type
+            execution_context=execution_context,
+            block_name=self.name,
             editable=input_data.editable,
         )
 

autogpt_platform/backend/backend/blocks/io.py

@@ -12,7 +12,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockType,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import SchemaField
 from backend.util.file import store_media_file
 from backend.util.mock import MockObject
@@ -463,21 +462,18 @@ class AgentFileInputBlock(AgentInputBlock):
         self,
         input_data: Input,
         *,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         if not input_data.value:
             return
 
-        # Determine return format based on user preference
-        # for_external_api: always returns data URI (base64) - honors "Produce Base64 Output"
-        # for_block_output: smart format - workspace:// in CoPilot, data URI in graphs
-        return_format = "for_external_api" if input_data.base_64 else "for_block_output"
-
         yield "result", await store_media_file(
+            graph_exec_id=graph_exec_id,
             file=input_data.value,
-            execution_context=execution_context,
-            return_format=return_format,
+            user_id=user_id,
+            return_content=input_data.base_64,
         )
 
 

autogpt_platform/backend/backend/blocks/llm.py

@@ -79,10 +79,6 @@ class ModelMetadata(NamedTuple):
     provider: str
     context_window: int
     max_output_tokens: int | None
-    display_name: str
-    provider_name: str
-    creator_name: str
-    price_tier: Literal[1, 2, 3]
 
 
 class LlmModelMeta(EnumMeta):
@@ -175,26 +171,6 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
     V0_1_5_LG = "v0-1.5-lg"
     V0_1_0_MD = "v0-1.0-md"
 
-    @classmethod
-    def __get_pydantic_json_schema__(cls, schema, handler):
-        json_schema = handler(schema)
-        llm_model_metadata = {}
-        for model in cls:
-            model_name = model.value
-            metadata = model.metadata
-            llm_model_metadata[model_name] = {
-                "creator": metadata.creator_name,
-                "creator_name": metadata.creator_name,
-                "title": metadata.display_name,
-                "provider": metadata.provider,
-                "provider_name": metadata.provider_name,
-                "name": model_name,
-                "price_tier": metadata.price_tier,
-            }
-        json_schema["llm_model"] = True
-        json_schema["llm_model_metadata"] = llm_model_metadata
-        return json_schema
-
     @property
     def metadata(self) -> ModelMetadata:
         return MODEL_METADATA[self]
@@ -214,291 +190,119 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
 
 MODEL_METADATA = {
     # https://platform.openai.com/docs/models
-    LlmModel.O3: ModelMetadata("openai", 200000, 100000, "O3", "OpenAI", "OpenAI", 2),
-    LlmModel.O3_MINI: ModelMetadata(
-        "openai", 200000, 100000, "O3 Mini", "OpenAI", "OpenAI", 1
-    ),  # o3-mini-2025-01-31
-    LlmModel.O1: ModelMetadata(
-        "openai", 200000, 100000, "O1", "OpenAI", "OpenAI", 3
-    ),  # o1-2024-12-17
-    LlmModel.O1_MINI: ModelMetadata(
-        "openai", 128000, 65536, "O1 Mini", "OpenAI", "OpenAI", 2
-    ),  # o1-mini-2024-09-12
+    LlmModel.O3: ModelMetadata("openai", 200000, 100000),
+    LlmModel.O3_MINI: ModelMetadata("openai", 200000, 100000),  # o3-mini-2025-01-31
+    LlmModel.O1: ModelMetadata("openai", 200000, 100000),  # o1-2024-12-17
+    LlmModel.O1_MINI: ModelMetadata("openai", 128000, 65536),  # o1-mini-2024-09-12
     # GPT-5 models
-    LlmModel.GPT5_2: ModelMetadata(
-        "openai", 400000, 128000, "GPT-5.2", "OpenAI", "OpenAI", 3
-    ),
-    LlmModel.GPT5_1: ModelMetadata(
-        "openai", 400000, 128000, "GPT-5.1", "OpenAI", "OpenAI", 2
-    ),
-    LlmModel.GPT5: ModelMetadata(
-        "openai", 400000, 128000, "GPT-5", "OpenAI", "OpenAI", 1
-    ),
-    LlmModel.GPT5_MINI: ModelMetadata(
-        "openai", 400000, 128000, "GPT-5 Mini", "OpenAI", "OpenAI", 1
-    ),
-    LlmModel.GPT5_NANO: ModelMetadata(
-        "openai", 400000, 128000, "GPT-5 Nano", "OpenAI", "OpenAI", 1
-    ),
-    LlmModel.GPT5_CHAT: ModelMetadata(
-        "openai", 400000, 16384, "GPT-5 Chat Latest", "OpenAI", "OpenAI", 2
-    ),
-    LlmModel.GPT41: ModelMetadata(
-        "openai", 1047576, 32768, "GPT-4.1", "OpenAI", "OpenAI", 1
-    ),
-    LlmModel.GPT41_MINI: ModelMetadata(
-        "openai", 1047576, 32768, "GPT-4.1 Mini", "OpenAI", "OpenAI", 1
-    ),
+    LlmModel.GPT5_2: ModelMetadata("openai", 400000, 128000),
+    LlmModel.GPT5_1: ModelMetadata("openai", 400000, 128000),
+    LlmModel.GPT5: ModelMetadata("openai", 400000, 128000),
+    LlmModel.GPT5_MINI: ModelMetadata("openai", 400000, 128000),
+    LlmModel.GPT5_NANO: ModelMetadata("openai", 400000, 128000),
+    LlmModel.GPT5_CHAT: ModelMetadata("openai", 400000, 16384),
+    LlmModel.GPT41: ModelMetadata("openai", 1047576, 32768),
+    LlmModel.GPT41_MINI: ModelMetadata("openai", 1047576, 32768),
     LlmModel.GPT4O_MINI: ModelMetadata(
-        "openai", 128000, 16384, "GPT-4o Mini", "OpenAI", "OpenAI", 1
+        "openai", 128000, 16384
     ),  # gpt-4o-mini-2024-07-18
-    LlmModel.GPT4O: ModelMetadata(
-        "openai", 128000, 16384, "GPT-4o", "OpenAI", "OpenAI", 2
-    ),  # gpt-4o-2024-08-06
+    LlmModel.GPT4O: ModelMetadata("openai", 128000, 16384),  # gpt-4o-2024-08-06
     LlmModel.GPT4_TURBO: ModelMetadata(
-        "openai", 128000, 4096, "GPT-4 Turbo", "OpenAI", "OpenAI", 3
+        "openai", 128000, 4096
     ),  # gpt-4-turbo-2024-04-09
-    LlmModel.GPT3_5_TURBO: ModelMetadata(
-        "openai", 16385, 4096, "GPT-3.5 Turbo", "OpenAI", "OpenAI", 1
-    ),  # gpt-3.5-turbo-0125
+    LlmModel.GPT3_5_TURBO: ModelMetadata("openai", 16385, 4096),  # gpt-3.5-turbo-0125
     # https://docs.anthropic.com/en/docs/about-claude/models
     LlmModel.CLAUDE_4_1_OPUS: ModelMetadata(
-        "anthropic", 200000, 32000, "Claude Opus 4.1", "Anthropic", "Anthropic", 3
+        "anthropic", 200000, 32000
     ),  # claude-opus-4-1-20250805
     LlmModel.CLAUDE_4_OPUS: ModelMetadata(
-        "anthropic", 200000, 32000, "Claude Opus 4", "Anthropic", "Anthropic", 3
+        "anthropic", 200000, 32000
     ),  # claude-4-opus-20250514
     LlmModel.CLAUDE_4_SONNET: ModelMetadata(
-        "anthropic", 200000, 64000, "Claude Sonnet 4", "Anthropic", "Anthropic", 2
+        "anthropic", 200000, 64000
     ),  # claude-4-sonnet-20250514
     LlmModel.CLAUDE_4_5_OPUS: ModelMetadata(
-        "anthropic", 200000, 64000, "Claude Opus 4.5", "Anthropic", "Anthropic", 3
+        "anthropic", 200000, 64000
     ),  # claude-opus-4-5-20251101
     LlmModel.CLAUDE_4_5_SONNET: ModelMetadata(
-        "anthropic", 200000, 64000, "Claude Sonnet 4.5", "Anthropic", "Anthropic", 3
+        "anthropic", 200000, 64000
     ),  # claude-sonnet-4-5-20250929
     LlmModel.CLAUDE_4_5_HAIKU: ModelMetadata(
-        "anthropic", 200000, 64000, "Claude Haiku 4.5", "Anthropic", "Anthropic", 2
+        "anthropic", 200000, 64000
     ),  # claude-haiku-4-5-20251001
     LlmModel.CLAUDE_3_7_SONNET: ModelMetadata(
-        "anthropic", 200000, 64000, "Claude 3.7 Sonnet", "Anthropic", "Anthropic", 2
+        "anthropic", 200000, 64000
     ),  # claude-3-7-sonnet-20250219
     LlmModel.CLAUDE_3_HAIKU: ModelMetadata(
-        "anthropic", 200000, 4096, "Claude 3 Haiku", "Anthropic", "Anthropic", 1
+        "anthropic", 200000, 4096
     ),  # claude-3-haiku-20240307
     # https://docs.aimlapi.com/api-overview/model-database/text-models
-    LlmModel.AIML_API_QWEN2_5_72B: ModelMetadata(
-        "aiml_api", 32000, 8000, "Qwen 2.5 72B Instruct Turbo", "AI/ML", "Qwen", 1
-    ),
-    LlmModel.AIML_API_LLAMA3_1_70B: ModelMetadata(
-        "aiml_api",
-        128000,
-        40000,
-        "Llama 3.1 Nemotron 70B Instruct",
-        "AI/ML",
-        "Nvidia",
-        1,
-    ),
-    LlmModel.AIML_API_LLAMA3_3_70B: ModelMetadata(
-        "aiml_api", 128000, None, "Llama 3.3 70B Instruct Turbo", "AI/ML", "Meta", 1
-    ),
-    LlmModel.AIML_API_META_LLAMA_3_1_70B: ModelMetadata(
-        "aiml_api", 131000, 2000, "Llama 3.1 70B Instruct Turbo", "AI/ML", "Meta", 1
-    ),
-    LlmModel.AIML_API_LLAMA_3_2_3B: ModelMetadata(
-        "aiml_api", 128000, None, "Llama 3.2 3B Instruct Turbo", "AI/ML", "Meta", 1
-    ),
+    LlmModel.AIML_API_QWEN2_5_72B: ModelMetadata("aiml_api", 32000, 8000),
+    LlmModel.AIML_API_LLAMA3_1_70B: ModelMetadata("aiml_api", 128000, 40000),
+    LlmModel.AIML_API_LLAMA3_3_70B: ModelMetadata("aiml_api", 128000, None),
+    LlmModel.AIML_API_META_LLAMA_3_1_70B: ModelMetadata("aiml_api", 131000, 2000),
+    LlmModel.AIML_API_LLAMA_3_2_3B: ModelMetadata("aiml_api", 128000, None),
     # https://console.groq.com/docs/models
-    LlmModel.LLAMA3_3_70B: ModelMetadata(
-        "groq", 128000, 32768, "Llama 3.3 70B Versatile", "Groq", "Meta", 1
-    ),
-    LlmModel.LLAMA3_1_8B: ModelMetadata(
-        "groq", 128000, 8192, "Llama 3.1 8B Instant", "Groq", "Meta", 1
-    ),
+    LlmModel.LLAMA3_3_70B: ModelMetadata("groq", 128000, 32768),
+    LlmModel.LLAMA3_1_8B: ModelMetadata("groq", 128000, 8192),
     # https://ollama.com/library
-    LlmModel.OLLAMA_LLAMA3_3: ModelMetadata(
-        "ollama", 8192, None, "Llama 3.3", "Ollama", "Meta", 1
-    ),
-    LlmModel.OLLAMA_LLAMA3_2: ModelMetadata(
-        "ollama", 8192, None, "Llama 3.2", "Ollama", "Meta", 1
-    ),
-    LlmModel.OLLAMA_LLAMA3_8B: ModelMetadata(
-        "ollama", 8192, None, "Llama 3", "Ollama", "Meta", 1
-    ),
-    LlmModel.OLLAMA_LLAMA3_405B: ModelMetadata(
-        "ollama", 8192, None, "Llama 3.1 405B", "Ollama", "Meta", 1
-    ),
-    LlmModel.OLLAMA_DOLPHIN: ModelMetadata(
-        "ollama", 32768, None, "Dolphin Mistral Latest", "Ollama", "Mistral AI", 1
-    ),
+    LlmModel.OLLAMA_LLAMA3_3: ModelMetadata("ollama", 8192, None),
+    LlmModel.OLLAMA_LLAMA3_2: ModelMetadata("ollama", 8192, None),
+    LlmModel.OLLAMA_LLAMA3_8B: ModelMetadata("ollama", 8192, None),
+    LlmModel.OLLAMA_LLAMA3_405B: ModelMetadata("ollama", 8192, None),
+    LlmModel.OLLAMA_DOLPHIN: ModelMetadata("ollama", 32768, None),
     # https://openrouter.ai/models
-    LlmModel.GEMINI_2_5_PRO: ModelMetadata(
-        "open_router",
-        1050000,
-        8192,
-        "Gemini 2.5 Pro Preview 03.25",
-        "OpenRouter",
-        "Google",
-        2,
-    ),
-    LlmModel.GEMINI_3_PRO_PREVIEW: ModelMetadata(
-        "open_router", 1048576, 65535, "Gemini 3 Pro Preview", "OpenRouter", "Google", 2
-    ),
-    LlmModel.GEMINI_2_5_FLASH: ModelMetadata(
-        "open_router", 1048576, 65535, "Gemini 2.5 Flash", "OpenRouter", "Google", 1
-    ),
-    LlmModel.GEMINI_2_0_FLASH: ModelMetadata(
-        "open_router", 1048576, 8192, "Gemini 2.0 Flash 001", "OpenRouter", "Google", 1
-    ),
+    LlmModel.GEMINI_2_5_PRO: ModelMetadata("open_router", 1050000, 8192),
+    LlmModel.GEMINI_3_PRO_PREVIEW: ModelMetadata("open_router", 1048576, 65535),
+    LlmModel.GEMINI_2_5_FLASH: ModelMetadata("open_router", 1048576, 65535),
+    LlmModel.GEMINI_2_0_FLASH: ModelMetadata("open_router", 1048576, 8192),
     LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: ModelMetadata(
-        "open_router",
-        1048576,
-        65535,
-        "Gemini 2.5 Flash Lite Preview 06.17",
-        "OpenRouter",
-        "Google",
-        1,
-    ),
-    LlmModel.GEMINI_2_0_FLASH_LITE: ModelMetadata(
-        "open_router",
-        1048576,
-        8192,
-        "Gemini 2.0 Flash Lite 001",
-        "OpenRouter",
-        "Google",
-        1,
-    ),
-    LlmModel.MISTRAL_NEMO: ModelMetadata(
-        "open_router", 128000, 4096, "Mistral Nemo", "OpenRouter", "Mistral AI", 1
-    ),
-    LlmModel.COHERE_COMMAND_R_08_2024: ModelMetadata(
-        "open_router", 128000, 4096, "Command R 08.2024", "OpenRouter", "Cohere", 1
-    ),
-    LlmModel.COHERE_COMMAND_R_PLUS_08_2024: ModelMetadata(
-        "open_router", 128000, 4096, "Command R Plus 08.2024", "OpenRouter", "Cohere", 2
-    ),
-    LlmModel.DEEPSEEK_CHAT: ModelMetadata(
-        "open_router", 64000, 2048, "DeepSeek Chat", "OpenRouter", "DeepSeek", 1
-    ),
-    LlmModel.DEEPSEEK_R1_0528: ModelMetadata(
-        "open_router", 163840, 163840, "DeepSeek R1 0528", "OpenRouter", "DeepSeek", 1
-    ),
-    LlmModel.PERPLEXITY_SONAR: ModelMetadata(
-        "open_router", 127000, 8000, "Sonar", "OpenRouter", "Perplexity", 1
-    ),
-    LlmModel.PERPLEXITY_SONAR_PRO: ModelMetadata(
-        "open_router", 200000, 8000, "Sonar Pro", "OpenRouter", "Perplexity", 2
+        "open_router", 1048576, 65535
     ),
+    LlmModel.GEMINI_2_0_FLASH_LITE: ModelMetadata("open_router", 1048576, 8192),
+    LlmModel.MISTRAL_NEMO: ModelMetadata("open_router", 128000, 4096),
+    LlmModel.COHERE_COMMAND_R_08_2024: ModelMetadata("open_router", 128000, 4096),
+    LlmModel.COHERE_COMMAND_R_PLUS_08_2024: ModelMetadata("open_router", 128000, 4096),
+    LlmModel.DEEPSEEK_CHAT: ModelMetadata("open_router", 64000, 2048),
+    LlmModel.DEEPSEEK_R1_0528: ModelMetadata("open_router", 163840, 163840),
+    LlmModel.PERPLEXITY_SONAR: ModelMetadata("open_router", 127000, 8000),
+    LlmModel.PERPLEXITY_SONAR_PRO: ModelMetadata("open_router", 200000, 8000),
     LlmModel.PERPLEXITY_SONAR_DEEP_RESEARCH: ModelMetadata(
         "open_router",
         128000,
         16000,
-        "Sonar Deep Research",
-        "OpenRouter",
-        "Perplexity",
-        3,
     ),
     LlmModel.NOUSRESEARCH_HERMES_3_LLAMA_3_1_405B: ModelMetadata(
-        "open_router",
-        131000,
-        4096,
-        "Hermes 3 Llama 3.1 405B",
-        "OpenRouter",
-        "Nous Research",
-        1,
+        "open_router", 131000, 4096
     ),
     LlmModel.NOUSRESEARCH_HERMES_3_LLAMA_3_1_70B: ModelMetadata(
-        "open_router",
-        12288,
-        12288,
-        "Hermes 3 Llama 3.1 70B",
-        "OpenRouter",
-        "Nous Research",
-        1,
-    ),
-    LlmModel.OPENAI_GPT_OSS_120B: ModelMetadata(
-        "open_router", 131072, 131072, "GPT-OSS 120B", "OpenRouter", "OpenAI", 1
-    ),
-    LlmModel.OPENAI_GPT_OSS_20B: ModelMetadata(
-        "open_router", 131072, 32768, "GPT-OSS 20B", "OpenRouter", "OpenAI", 1
-    ),
-    LlmModel.AMAZON_NOVA_LITE_V1: ModelMetadata(
-        "open_router", 300000, 5120, "Nova Lite V1", "OpenRouter", "Amazon", 1
-    ),
-    LlmModel.AMAZON_NOVA_MICRO_V1: ModelMetadata(
-        "open_router", 128000, 5120, "Nova Micro V1", "OpenRouter", "Amazon", 1
-    ),
-    LlmModel.AMAZON_NOVA_PRO_V1: ModelMetadata(
-        "open_router", 300000, 5120, "Nova Pro V1", "OpenRouter", "Amazon", 1
-    ),
-    LlmModel.MICROSOFT_WIZARDLM_2_8X22B: ModelMetadata(
-        "open_router", 65536, 4096, "WizardLM 2 8x22B", "OpenRouter", "Microsoft", 1
-    ),
-    LlmModel.GRYPHE_MYTHOMAX_L2_13B: ModelMetadata(
-        "open_router", 4096, 4096, "MythoMax L2 13B", "OpenRouter", "Gryphe", 1
-    ),
-    LlmModel.META_LLAMA_4_SCOUT: ModelMetadata(
-        "open_router", 131072, 131072, "Llama 4 Scout", "OpenRouter", "Meta", 1
-    ),
-    LlmModel.META_LLAMA_4_MAVERICK: ModelMetadata(
-        "open_router", 1048576, 1000000, "Llama 4 Maverick", "OpenRouter", "Meta", 1
-    ),
-    LlmModel.GROK_4: ModelMetadata(
-        "open_router", 256000, 256000, "Grok 4", "OpenRouter", "xAI", 3
-    ),
-    LlmModel.GROK_4_FAST: ModelMetadata(
-        "open_router", 2000000, 30000, "Grok 4 Fast", "OpenRouter", "xAI", 1
-    ),
-    LlmModel.GROK_4_1_FAST: ModelMetadata(
-        "open_router", 2000000, 30000, "Grok 4.1 Fast", "OpenRouter", "xAI", 1
-    ),
-    LlmModel.GROK_CODE_FAST_1: ModelMetadata(
-        "open_router", 256000, 10000, "Grok Code Fast 1", "OpenRouter", "xAI", 1
-    ),
-    LlmModel.KIMI_K2: ModelMetadata(
-        "open_router", 131000, 131000, "Kimi K2", "OpenRouter", "Moonshot AI", 1
-    ),
-    LlmModel.QWEN3_235B_A22B_THINKING: ModelMetadata(
-        "open_router",
-        262144,
-        262144,
-        "Qwen 3 235B A22B Thinking 2507",
-        "OpenRouter",
-        "Qwen",
-        1,
-    ),
-    LlmModel.QWEN3_CODER: ModelMetadata(
-        "open_router", 262144, 262144, "Qwen 3 Coder", "OpenRouter", "Qwen", 3
+        "open_router", 12288, 12288
     ),
+    LlmModel.OPENAI_GPT_OSS_120B: ModelMetadata("open_router", 131072, 131072),
+    LlmModel.OPENAI_GPT_OSS_20B: ModelMetadata("open_router", 131072, 32768),
+    LlmModel.AMAZON_NOVA_LITE_V1: ModelMetadata("open_router", 300000, 5120),
+    LlmModel.AMAZON_NOVA_MICRO_V1: ModelMetadata("open_router", 128000, 5120),
+    LlmModel.AMAZON_NOVA_PRO_V1: ModelMetadata("open_router", 300000, 5120),
+    LlmModel.MICROSOFT_WIZARDLM_2_8X22B: ModelMetadata("open_router", 65536, 4096),
+    LlmModel.GRYPHE_MYTHOMAX_L2_13B: ModelMetadata("open_router", 4096, 4096),
+    LlmModel.META_LLAMA_4_SCOUT: ModelMetadata("open_router", 131072, 131072),
+    LlmModel.META_LLAMA_4_MAVERICK: ModelMetadata("open_router", 1048576, 1000000),
+    LlmModel.GROK_4: ModelMetadata("open_router", 256000, 256000),
+    LlmModel.GROK_4_FAST: ModelMetadata("open_router", 2000000, 30000),
+    LlmModel.GROK_4_1_FAST: ModelMetadata("open_router", 2000000, 30000),
+    LlmModel.GROK_CODE_FAST_1: ModelMetadata("open_router", 256000, 10000),
+    LlmModel.KIMI_K2: ModelMetadata("open_router", 131000, 131000),
+    LlmModel.QWEN3_235B_A22B_THINKING: ModelMetadata("open_router", 262144, 262144),
+    LlmModel.QWEN3_CODER: ModelMetadata("open_router", 262144, 262144),
     # Llama API models
-    LlmModel.LLAMA_API_LLAMA_4_SCOUT: ModelMetadata(
-        "llama_api",
-        128000,
-        4028,
-        "Llama 4 Scout 17B 16E Instruct FP8",
-        "Llama API",
-        "Meta",
-        1,
-    ),
-    LlmModel.LLAMA_API_LLAMA4_MAVERICK: ModelMetadata(
-        "llama_api",
-        128000,
-        4028,
-        "Llama 4 Maverick 17B 128E Instruct FP8",
-        "Llama API",
-        "Meta",
-        1,
-    ),
-    LlmModel.LLAMA_API_LLAMA3_3_8B: ModelMetadata(
-        "llama_api", 128000, 4028, "Llama 3.3 8B Instruct", "Llama API", "Meta", 1
-    ),
-    LlmModel.LLAMA_API_LLAMA3_3_70B: ModelMetadata(
-        "llama_api", 128000, 4028, "Llama 3.3 70B Instruct", "Llama API", "Meta", 1
-    ),
+    LlmModel.LLAMA_API_LLAMA_4_SCOUT: ModelMetadata("llama_api", 128000, 4028),
+    LlmModel.LLAMA_API_LLAMA4_MAVERICK: ModelMetadata("llama_api", 128000, 4028),
+    LlmModel.LLAMA_API_LLAMA3_3_8B: ModelMetadata("llama_api", 128000, 4028),
+    LlmModel.LLAMA_API_LLAMA3_3_70B: ModelMetadata("llama_api", 128000, 4028),
     # v0 by Vercel models
-    LlmModel.V0_1_5_MD: ModelMetadata("v0", 128000, 64000, "v0 1.5 MD", "V0", "V0", 1),
-    LlmModel.V0_1_5_LG: ModelMetadata("v0", 512000, 64000, "v0 1.5 LG", "V0", "V0", 1),
-    LlmModel.V0_1_0_MD: ModelMetadata("v0", 128000, 64000, "v0 1.0 MD", "V0", "V0", 1),
+    LlmModel.V0_1_5_MD: ModelMetadata("v0", 128000, 64000),
+    LlmModel.V0_1_5_LG: ModelMetadata("v0", 512000, 64000),
+    LlmModel.V0_1_0_MD: ModelMetadata("v0", 128000, 64000),
 }
 
 DEFAULT_LLM_MODEL = LlmModel.GPT5_2

autogpt_platform/backend/backend/blocks/media.py

@@ -1,6 +1,6 @@
 import os
 import tempfile
-from typing import Optional
+from typing import Literal, Optional
 
 from moviepy.audio.io.AudioFileClip import AudioFileClip
 from moviepy.video.fx.Loop import Loop
@@ -13,7 +13,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import SchemaField
 from backend.util.file import MediaFileType, get_exec_file_path, store_media_file
 
@@ -47,19 +46,18 @@ class MediaDurationBlock(Block):
         self,
         input_data: Input,
         *,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         # 1) Store the input media locally
         local_media_path = await store_media_file(
+            graph_exec_id=graph_exec_id,
             file=input_data.media_in,
-            execution_context=execution_context,
-            return_format="for_local_processing",
-        )
-        assert execution_context.graph_exec_id is not None
-        media_abspath = get_exec_file_path(
-            execution_context.graph_exec_id, local_media_path
+            user_id=user_id,
+            return_content=False,
         )
+        media_abspath = get_exec_file_path(graph_exec_id, local_media_path)
 
         # 2) Load the clip
         if input_data.is_video:
@@ -90,6 +88,10 @@ class LoopVideoBlock(Block):
             default=None,
             ge=1,
         )
+        output_return_type: Literal["file_path", "data_uri"] = SchemaField(
+            description="How to return the output video. Either a relative path or base64 data URI.",
+            default="file_path",
+        )
 
     class Output(BlockSchemaOutput):
         video_out: str = SchemaField(
@@ -109,19 +111,17 @@ class LoopVideoBlock(Block):
         self,
         input_data: Input,
         *,
-        execution_context: ExecutionContext,
+        node_exec_id: str,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
-        assert execution_context.graph_exec_id is not None
-        assert execution_context.node_exec_id is not None
-        graph_exec_id = execution_context.graph_exec_id
-        node_exec_id = execution_context.node_exec_id
-
         # 1) Store the input video locally
         local_video_path = await store_media_file(
+            graph_exec_id=graph_exec_id,
             file=input_data.video_in,
-            execution_context=execution_context,
-            return_format="for_local_processing",
+            user_id=user_id,
+            return_content=False,
         )
         input_abspath = get_exec_file_path(graph_exec_id, local_video_path)
 
@@ -149,11 +149,12 @@ class LoopVideoBlock(Block):
         looped_clip = looped_clip.with_audio(clip.audio)
         looped_clip.write_videofile(output_abspath, codec="libx264", audio_codec="aac")
 
-        # Return output - for_block_output returns workspace:// if available, else data URI
+        # Return as data URI
         video_out = await store_media_file(
+            graph_exec_id=graph_exec_id,
             file=output_filename,
-            execution_context=execution_context,
-            return_format="for_block_output",
+            user_id=user_id,
+            return_content=input_data.output_return_type == "data_uri",
         )
 
         yield "video_out", video_out
@@ -176,6 +177,10 @@ class AddAudioToVideoBlock(Block):
             description="Volume scale for the newly attached audio track (1.0 = original).",
             default=1.0,
         )
+        output_return_type: Literal["file_path", "data_uri"] = SchemaField(
+            description="Return the final output as a relative path or base64 data URI.",
+            default="file_path",
+        )
 
     class Output(BlockSchemaOutput):
         video_out: MediaFileType = SchemaField(
@@ -195,24 +200,23 @@ class AddAudioToVideoBlock(Block):
         self,
         input_data: Input,
         *,
-        execution_context: ExecutionContext,
+        node_exec_id: str,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
-        assert execution_context.graph_exec_id is not None
-        assert execution_context.node_exec_id is not None
-        graph_exec_id = execution_context.graph_exec_id
-        node_exec_id = execution_context.node_exec_id
-
         # 1) Store the inputs locally
         local_video_path = await store_media_file(
+            graph_exec_id=graph_exec_id,
             file=input_data.video_in,
-            execution_context=execution_context,
-            return_format="for_local_processing",
+            user_id=user_id,
+            return_content=False,
         )
         local_audio_path = await store_media_file(
+            graph_exec_id=graph_exec_id,
             file=input_data.audio_in,
-            execution_context=execution_context,
-            return_format="for_local_processing",
+            user_id=user_id,
+            return_content=False,
         )
 
         abs_temp_dir = os.path.join(tempfile.gettempdir(), "exec_file", graph_exec_id)
@@ -236,11 +240,12 @@ class AddAudioToVideoBlock(Block):
         output_abspath = os.path.join(abs_temp_dir, output_filename)
         final_clip.write_videofile(output_abspath, codec="libx264", audio_codec="aac")
 
-        # 5) Return output - for_block_output returns workspace:// if available, else data URI
+        # 5) Return either path or data URI
         video_out = await store_media_file(
+            graph_exec_id=graph_exec_id,
             file=output_filename,
-            execution_context=execution_context,
-            return_format="for_block_output",
+            user_id=user_id,
+            return_content=input_data.output_return_type == "data_uri",
         )
 
         yield "video_out", video_out

autogpt_platform/backend/backend/blocks/screenshotone.py

@@ -11,7 +11,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import (
     APIKeyCredentials,
     CredentialsField,
@@ -113,7 +112,8 @@ class ScreenshotWebPageBlock(Block):
     @staticmethod
     async def take_screenshot(
         credentials: APIKeyCredentials,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         url: str,
         viewport_width: int,
         viewport_height: int,
@@ -155,11 +155,12 @@ class ScreenshotWebPageBlock(Block):
 
         return {
             "image": await store_media_file(
+                graph_exec_id=graph_exec_id,
                 file=MediaFileType(
                     f"data:image/{format.value};base64,{b64encode(content).decode('utf-8')}"
                 ),
-                execution_context=execution_context,
-                return_format="for_block_output",
+                user_id=user_id,
+                return_content=True,
             )
         }
 
@@ -168,13 +169,15 @@ class ScreenshotWebPageBlock(Block):
         input_data: Input,
         *,
         credentials: APIKeyCredentials,
-        execution_context: ExecutionContext,
+        graph_exec_id: str,
+        user_id: str,
         **kwargs,
     ) -> BlockOutput:
         try:
             screenshot_data = await self.take_screenshot(
                 credentials=credentials,
-                execution_context=execution_context,
+                graph_exec_id=graph_exec_id,
+                user_id=user_id,
                 url=input_data.url,
                 viewport_width=input_data.viewport_width,
                 viewport_height=input_data.viewport_height,

autogpt_platform/backend/backend/blocks/spreadsheet.py

@@ -7,7 +7,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import ContributorDetails, SchemaField
 from backend.util.file import get_exec_file_path, store_media_file
 from backend.util.type import MediaFileType
@@ -99,7 +98,7 @@ class ReadSpreadsheetBlock(Block):
         )
 
     async def run(
-        self, input_data: Input, *, execution_context: ExecutionContext, **_kwargs
+        self, input_data: Input, *, graph_exec_id: str, user_id: str, **_kwargs
     ) -> BlockOutput:
         import csv
         from io import StringIO
@@ -107,16 +106,14 @@ class ReadSpreadsheetBlock(Block):
         # Determine data source - prefer file_input if provided, otherwise use contents
         if input_data.file_input:
             stored_file_path = await store_media_file(
+                user_id=user_id,
+                graph_exec_id=graph_exec_id,
                 file=input_data.file_input,
-                execution_context=execution_context,
-                return_format="for_local_processing",
+                return_content=False,
             )
 
             # Get full file path
-            assert execution_context.graph_exec_id  # Validated by store_media_file
-            file_path = get_exec_file_path(
-                execution_context.graph_exec_id, stored_file_path
-            )
+            file_path = get_exec_file_path(graph_exec_id, stored_file_path)
             if not Path(file_path).exists():
                 raise ValueError(f"File does not exist: {file_path}")
 

autogpt_platform/backend/backend/blocks/talking_head.py

@@ -10,7 +10,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import (
     APIKeyCredentials,
     CredentialsField,
@@ -18,9 +17,7 @@ from backend.data.model import (
     SchemaField,
 )
 from backend.integrations.providers import ProviderName
-from backend.util.file import store_media_file
 from backend.util.request import Requests
-from backend.util.type import MediaFileType
 
 TEST_CREDENTIALS = APIKeyCredentials(
     id="01234567-89ab-cdef-0123-456789abcdef",
@@ -105,7 +102,7 @@ class CreateTalkingAvatarVideoBlock(Block):
             test_output=[
                 (
                     "video_url",
-                    lambda x: x.startswith(("workspace://", "data:")),
+                    "https://d-id.com/api/clips/abcd1234-5678-efgh-ijkl-mnopqrstuvwx/video",
                 ),
             ],
             test_mock={
@@ -113,10 +110,9 @@ class CreateTalkingAvatarVideoBlock(Block):
                     "id": "abcd1234-5678-efgh-ijkl-mnopqrstuvwx",
                     "status": "created",
                 },
-                # Use data URI to avoid HTTP requests during tests
                 "get_clip_status": lambda *args, **kwargs: {
                     "status": "done",
-                    "result_url": "data:video/mp4;base64,AAAA",
+                    "result_url": "https://d-id.com/api/clips/abcd1234-5678-efgh-ijkl-mnopqrstuvwx/video",
                 },
             },
             test_credentials=TEST_CREDENTIALS,
@@ -142,12 +138,7 @@ class CreateTalkingAvatarVideoBlock(Block):
         return response.json()
 
     async def run(
-        self,
-        input_data: Input,
-        *,
-        credentials: APIKeyCredentials,
-        execution_context: ExecutionContext,
-        **kwargs,
+        self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs
     ) -> BlockOutput:
         # Create the clip
         payload = {
@@ -174,14 +165,7 @@ class CreateTalkingAvatarVideoBlock(Block):
         for _ in range(input_data.max_polling_attempts):
             status_response = await self.get_clip_status(credentials.api_key, clip_id)
             if status_response["status"] == "done":
-                # Store the generated video to the user's workspace for persistence
-                video_url = status_response["result_url"]
-                stored_url = await store_media_file(
-                    file=MediaFileType(video_url),
-                    execution_context=execution_context,
-                    return_format="for_block_output",
-                )
-                yield "video_url", stored_url
+                yield "video_url", status_response["result_url"]
                 return
             elif status_response["status"] == "error":
                 raise RuntimeError(

autogpt_platform/backend/backend/blocks/test/test_blocks_dos_vulnerability.py

@@ -12,7 +12,6 @@ from backend.blocks.iteration import StepThroughItemsBlock
 from backend.blocks.llm import AITextSummarizerBlock
 from backend.blocks.text import ExtractTextInformationBlock
 from backend.blocks.xml_parser import XMLParserBlock
-from backend.data.execution import ExecutionContext
 from backend.util.file import store_media_file
 from backend.util.type import MediaFileType
 
@@ -234,12 +233,9 @@ class TestStoreMediaFileSecurity:
 
         with pytest.raises(ValueError, match="File too large"):
             await store_media_file(
+                graph_exec_id="test",
                 file=MediaFileType(large_data_uri),
-                execution_context=ExecutionContext(
-                    user_id="test_user",
-                    graph_exec_id="test",
-                ),
-                return_format="for_local_processing",
+                user_id="test_user",
             )
 
     @patch("backend.util.file.Path")
@@ -274,12 +270,9 @@ class TestStoreMediaFileSecurity:
         # Should raise an error when directory size exceeds limit
         with pytest.raises(ValueError, match="Disk usage limit exceeded"):
             await store_media_file(
+                graph_exec_id="test",
                 file=MediaFileType(
                     "data:text/plain;base64,dGVzdA=="
                 ),  # Small test file
-                execution_context=ExecutionContext(
-                    user_id="test_user",
-                    graph_exec_id="test",
-                ),
-                return_format="for_local_processing",
+                user_id="test_user",
             )

autogpt_platform/backend/backend/blocks/test/test_http.py

@@ -11,22 +11,10 @@ from backend.blocks.http import (
     HttpMethod,
     SendAuthenticatedWebRequestBlock,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import HostScopedCredentials
 from backend.util.request import Response
 
 
-def make_test_context(
-    graph_exec_id: str = "test-exec-id",
-    user_id: str = "test-user-id",
-) -> ExecutionContext:
-    """Helper to create test ExecutionContext."""
-    return ExecutionContext(
-        user_id=user_id,
-        graph_exec_id=graph_exec_id,
-    )
-
-
 class TestHttpBlockWithHostScopedCredentials:
     """Test suite for HTTP block integration with HostScopedCredentials."""
 
@@ -117,7 +105,8 @@ class TestHttpBlockWithHostScopedCredentials:
         async for output_name, output_data in http_block.run(
             input_data,
             credentials=exact_match_credentials,
-            execution_context=make_test_context(),
+            graph_exec_id="test-exec-id",
+            user_id="test-user-id",
         ):
             result.append((output_name, output_data))
 
@@ -172,7 +161,8 @@ class TestHttpBlockWithHostScopedCredentials:
         async for output_name, output_data in http_block.run(
             input_data,
             credentials=wildcard_credentials,
-            execution_context=make_test_context(),
+            graph_exec_id="test-exec-id",
+            user_id="test-user-id",
         ):
             result.append((output_name, output_data))
 
@@ -218,7 +208,8 @@ class TestHttpBlockWithHostScopedCredentials:
         async for output_name, output_data in http_block.run(
             input_data,
             credentials=non_matching_credentials,
-            execution_context=make_test_context(),
+            graph_exec_id="test-exec-id",
+            user_id="test-user-id",
         ):
             result.append((output_name, output_data))
 
@@ -267,7 +258,8 @@ class TestHttpBlockWithHostScopedCredentials:
         async for output_name, output_data in http_block.run(
             input_data,
             credentials=exact_match_credentials,
-            execution_context=make_test_context(),
+            graph_exec_id="test-exec-id",
+            user_id="test-user-id",
         ):
             result.append((output_name, output_data))
 
@@ -326,7 +318,8 @@ class TestHttpBlockWithHostScopedCredentials:
         async for output_name, output_data in http_block.run(
             input_data,
             credentials=auto_discovered_creds,  # Execution manager found these
-            execution_context=make_test_context(),
+            graph_exec_id="test-exec-id",
+            user_id="test-user-id",
         ):
             result.append((output_name, output_data))
 
@@ -389,7 +382,8 @@ class TestHttpBlockWithHostScopedCredentials:
         async for output_name, output_data in http_block.run(
             input_data,
             credentials=multi_header_creds,
-            execution_context=make_test_context(),
+            graph_exec_id="test-exec-id",
+            user_id="test-user-id",
         ):
             result.append((output_name, output_data))
 
@@ -477,7 +471,8 @@ class TestHttpBlockWithHostScopedCredentials:
             async for output_name, output_data in http_block.run(
                 input_data,
                 credentials=test_creds,
-                execution_context=make_test_context(),
+                graph_exec_id="test-exec-id",
+                user_id="test-user-id",
             ):
                 result.append((output_name, output_data))
 

autogpt_platform/backend/backend/blocks/test/test_smart_decision_maker.py

@@ -242,7 +242,7 @@ async def test_smart_decision_maker_tracks_llm_stats():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
+        mock_execution_context = ExecutionContext(safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -343,7 +343,7 @@ async def test_smart_decision_maker_parameter_validation():
 
         # Create execution context
 
-        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
+        mock_execution_context = ExecutionContext(safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -409,7 +409,7 @@ async def test_smart_decision_maker_parameter_validation():
 
         # Create execution context
 
-        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
+        mock_execution_context = ExecutionContext(safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -471,7 +471,7 @@ async def test_smart_decision_maker_parameter_validation():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
+        mock_execution_context = ExecutionContext(safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -535,7 +535,7 @@ async def test_smart_decision_maker_parameter_validation():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
+        mock_execution_context = ExecutionContext(safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -658,7 +658,7 @@ async def test_smart_decision_maker_raw_response_conversion():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
+        mock_execution_context = ExecutionContext(safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -730,7 +730,7 @@ async def test_smart_decision_maker_raw_response_conversion():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
+        mock_execution_context = ExecutionContext(safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -786,7 +786,7 @@ async def test_smart_decision_maker_raw_response_conversion():
         outputs = {}
         # Create execution context
 
-        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
+        mock_execution_context = ExecutionContext(safe_mode=False)
 
         # Create a mock execution processor for tests
 
@@ -905,7 +905,7 @@ async def test_smart_decision_maker_agent_mode():
         # Create a mock execution context
 
         mock_execution_context = ExecutionContext(
-            human_in_the_loop_safe_mode=False,
+            safe_mode=False,
         )
 
         # Create a mock execution processor for agent mode tests
@@ -1027,7 +1027,7 @@ async def test_smart_decision_maker_traditional_mode_default():
 
         # Create execution context
 
-        mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
+        mock_execution_context = ExecutionContext(safe_mode=False)
 
         # Create a mock execution processor for tests
 

autogpt_platform/backend/backend/blocks/test/test_smart_decision_maker_dynamic_fields.py

@@ -386,7 +386,7 @@ async def test_output_yielding_with_dynamic_fields():
             outputs = {}
             from backend.data.execution import ExecutionContext
 
-            mock_execution_context = ExecutionContext(human_in_the_loop_safe_mode=False)
+            mock_execution_context = ExecutionContext(safe_mode=False)
             mock_execution_processor = MagicMock()
 
             async for output_name, output_value in block.run(
@@ -609,9 +609,7 @@ async def test_validation_errors_dont_pollute_conversation():
                 outputs = {}
                 from backend.data.execution import ExecutionContext
 
-                mock_execution_context = ExecutionContext(
-                    human_in_the_loop_safe_mode=False
-                )
+                mock_execution_context = ExecutionContext(safe_mode=False)
 
                 # Create a proper mock execution processor for agent mode
                 from collections import defaultdict

autogpt_platform/backend/backend/blocks/text.py

@@ -11,7 +11,6 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockSchemaOutput,
 )
-from backend.data.execution import ExecutionContext
 from backend.data.model import SchemaField
 from backend.util import json, text
 from backend.util.file import get_exec_file_path, store_media_file
@@ -445,21 +444,18 @@ class FileReadBlock(Block):
         )
 
     async def run(
-        self, input_data: Input, *, execution_context: ExecutionContext, **_kwargs
+        self, input_data: Input, *, graph_exec_id: str, user_id: str, **_kwargs
     ) -> BlockOutput:
         # Store the media file properly (handles URLs, data URIs, etc.)
         stored_file_path = await store_media_file(
+            user_id=user_id,
+            graph_exec_id=graph_exec_id,
             file=input_data.file_input,
-            execution_context=execution_context,
-            return_format="for_local_processing",
+            return_content=False,
         )
 
-        # Get full file path (graph_exec_id validated by store_media_file above)
-        if not execution_context.graph_exec_id:
-            raise ValueError("execution_context.graph_exec_id is required")
-        file_path = get_exec_file_path(
-            execution_context.graph_exec_id, stored_file_path
-        )
+        # Get full file path
+        file_path = get_exec_file_path(graph_exec_id, stored_file_path)
 
         if not Path(file_path).exists():
             raise ValueError(f"File does not exist: {file_path}")

autogpt_platform/backend/backend/conftest.py

@@ -1,7 +1,7 @@
 import logging
 import os
 
-import pytest_asyncio
+import pytest
 from dotenv import load_dotenv
 
 from backend.util.logging import configure_logging
@@ -19,7 +19,7 @@ if not os.getenv("PRISMA_DEBUG"):
     prisma_logger.setLevel(logging.INFO)
 
 
-@pytest_asyncio.fixture(scope="session", loop_scope="session")
+@pytest.fixture(scope="session")
 async def server():
     from backend.util.test import SpinTestServer
 
@@ -27,7 +27,7 @@ async def server():
         yield server
 
 
-@pytest_asyncio.fixture(scope="session", loop_scope="session", autouse=True)
+@pytest.fixture(scope="session", autouse=True)
 async def graph_cleanup(server):
     created_graph_ids = []
     original_create_graph = server.agent_server.test_create_graph

autogpt_platform/backend/backend/data/block.py

@@ -441,7 +441,6 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
         static_output: bool = False,
         block_type: BlockType = BlockType.STANDARD,
         webhook_config: Optional[BlockWebhookConfig | BlockManualWebhookConfig] = None,
-        is_sensitive_action: bool = False,
     ):
         """
         Initialize the block with the given schema.
@@ -474,8 +473,8 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
         self.static_output = static_output
         self.block_type = block_type
         self.webhook_config = webhook_config
-        self.is_sensitive_action = is_sensitive_action
         self.execution_stats: NodeExecutionStats = NodeExecutionStats()
+        self.requires_human_review: bool = False
 
         if self.webhook_config:
             if isinstance(self.webhook_config, BlockWebhookConfig):
@@ -623,7 +622,6 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
         input_data: BlockInput,
         *,
         user_id: str,
-        node_id: str,
         node_exec_id: str,
         graph_exec_id: str,
         graph_id: str,
@@ -639,9 +637,8 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
             - should_pause: True if execution should be paused for review
             - input_data_to_use: The input data to use (may be modified by reviewer)
         """
-        if not (
-            self.is_sensitive_action and execution_context.sensitive_action_safe_mode
-        ):
+        # Skip review if not required or safe mode is disabled
+        if not self.requires_human_review or not execution_context.safe_mode:
             return False, input_data
 
         from backend.blocks.helpers.review import HITLReviewHelper
@@ -650,11 +647,11 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
         decision = await HITLReviewHelper.handle_review_decision(
             input_data=input_data,
             user_id=user_id,
-            node_id=node_id,
             node_exec_id=node_exec_id,
             graph_exec_id=graph_exec_id,
             graph_id=graph_id,
             graph_version=graph_version,
+            execution_context=execution_context,
             block_name=self.name,
             editable=True,
         )

autogpt_platform/backend/backend/data/block_cost_config.py

@@ -99,15 +99,10 @@ MODEL_COST: dict[LlmModel, int] = {
     LlmModel.OPENAI_GPT_OSS_20B: 1,
     LlmModel.GEMINI_2_5_PRO: 4,
     LlmModel.GEMINI_3_PRO_PREVIEW: 5,
-    LlmModel.GEMINI_2_5_FLASH: 1,
-    LlmModel.GEMINI_2_0_FLASH: 1,
-    LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: 1,
-    LlmModel.GEMINI_2_0_FLASH_LITE: 1,
     LlmModel.MISTRAL_NEMO: 1,
     LlmModel.COHERE_COMMAND_R_08_2024: 1,
     LlmModel.COHERE_COMMAND_R_PLUS_08_2024: 3,
     LlmModel.DEEPSEEK_CHAT: 2,
-    LlmModel.DEEPSEEK_R1_0528: 1,
     LlmModel.PERPLEXITY_SONAR: 1,
     LlmModel.PERPLEXITY_SONAR_PRO: 5,
     LlmModel.PERPLEXITY_SONAR_DEEP_RESEARCH: 10,
@@ -131,6 +126,11 @@ MODEL_COST: dict[LlmModel, int] = {
     LlmModel.KIMI_K2: 1,
     LlmModel.QWEN3_235B_A22B_THINKING: 1,
     LlmModel.QWEN3_CODER: 9,
+    LlmModel.GEMINI_2_5_FLASH: 1,
+    LlmModel.GEMINI_2_0_FLASH: 1,
+    LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: 1,
+    LlmModel.GEMINI_2_0_FLASH_LITE: 1,
+    LlmModel.DEEPSEEK_R1_0528: 1,
     # v0 by Vercel models
     LlmModel.V0_1_5_MD: 1,
     LlmModel.V0_1_5_LG: 2,

autogpt_platform/backend/backend/data/db.py

@@ -38,6 +38,20 @@ POOL_TIMEOUT = os.getenv("DB_POOL_TIMEOUT")
 if POOL_TIMEOUT:
     DATABASE_URL = add_param(DATABASE_URL, "pool_timeout", POOL_TIMEOUT)
 
+# Add public schema to search_path for pgvector type access
+# The vector extension is in public schema, but search_path is determined by schema parameter
+# Extract the schema from DATABASE_URL or default to 'public' (matching get_database_schema())
+parsed_url = urlparse(DATABASE_URL)
+url_params = dict(parse_qsl(parsed_url.query))
+db_schema = url_params.get("schema", "public")
+# Build search_path, avoiding duplicates if db_schema is already 'public'
+search_path_schemas = list(
+    dict.fromkeys([db_schema, "public"])
+)  # Preserves order, removes duplicates
+search_path = ",".join(search_path_schemas)
+# This allows using ::vector without schema qualification
+DATABASE_URL = add_param(DATABASE_URL, "options", f"-c search_path={search_path}")
+
 HTTP_TIMEOUT = int(POOL_TIMEOUT) if POOL_TIMEOUT else None
 
 prisma = Prisma(
@@ -113,48 +127,38 @@ async def _raw_with_schema(
     *args,
     execute: bool = False,
     client: Prisma | None = None,
+    set_public_search_path: bool = False,
 ) -> list[dict] | int:
     """Internal: Execute raw SQL with proper schema handling.
 
     Use query_raw_with_schema() or execute_raw_with_schema() instead.
 
-    Supports placeholders:
-        - {schema_prefix}: Table/type prefix (e.g., "platform".)
-        - {schema}: Raw schema name for application tables (e.g., platform)
-
-    Note on pgvector types:
-        Use unqualified ::vector and <=> operator in queries. PostgreSQL resolves
-        these via search_path, which includes the schema where pgvector is installed
-        on all environments (local, CI, dev).
-
     Args:
-        query_template: SQL query with {schema_prefix} and/or {schema} placeholders
+        query_template: SQL query with {schema_prefix} placeholder
         *args: Query parameters
         execute: If False, executes SELECT query. If True, executes INSERT/UPDATE/DELETE.
         client: Optional Prisma client for transactions (only used when execute=True).
+        set_public_search_path: If True, sets search_path to include public schema.
+                                Needed for pgvector types and other public schema objects.
 
     Returns:
         - list[dict] if execute=False (query results)
         - int if execute=True (number of affected rows)
-
-    Example with vector type:
-        await execute_raw_with_schema(
-            'INSERT INTO {schema_prefix}"Embedding" (vec) VALUES ($1::vector)',
-            embedding_data
-        )
     """
     schema = get_database_schema()
     schema_prefix = f'"{schema}".' if schema != "public" else ""
-
-    formatted_query = query_template.format(
-        schema_prefix=schema_prefix,
-        schema=schema,
-    )
+    formatted_query = query_template.format(schema_prefix=schema_prefix)
 
     import prisma as prisma_module
 
     db_client = client if client else prisma_module.get_client()
 
+    # Set search_path to include public schema if requested
+    # Prisma doesn't support the 'options' connection parameter, so we set it per-session
+    # This is idempotent and safe to call multiple times
+    if set_public_search_path:
+        await db_client.execute_raw(f"SET search_path = {schema}, public")  # type: ignore
+
     if execute:
         result = await db_client.execute_raw(formatted_query, *args)  # type: ignore
     else:
@@ -163,12 +167,16 @@ async def _raw_with_schema(
     return result
 
 
-async def query_raw_with_schema(query_template: str, *args) -> list[dict]:
+async def query_raw_with_schema(
+    query_template: str, *args, set_public_search_path: bool = False
+) -> list[dict]:
     """Execute raw SQL SELECT query with proper schema handling.
 
     Args:
-        query_template: SQL query with {schema_prefix} and/or {schema} placeholders
+        query_template: SQL query with {schema_prefix} placeholder
         *args: Query parameters
+        set_public_search_path: If True, sets search_path to include public schema.
+                                Needed for pgvector types and other public schema objects.
 
     Returns:
         List of result rows as dictionaries
@@ -179,20 +187,23 @@ async def query_raw_with_schema(query_template: str, *args) -> list[dict]:
             user_id
         )
     """
-    return await _raw_with_schema(query_template, *args, execute=False)  # type: ignore
+    return await _raw_with_schema(query_template, *args, execute=False, set_public_search_path=set_public_search_path)  # type: ignore
 
 
 async def execute_raw_with_schema(
     query_template: str,
     *args,
     client: Prisma | None = None,
+    set_public_search_path: bool = False,
 ) -> int:
     """Execute raw SQL command (INSERT/UPDATE/DELETE) with proper schema handling.
 
     Args:
-        query_template: SQL query with {schema_prefix} and/or {schema} placeholders
+        query_template: SQL query with {schema_prefix} placeholder
         *args: Query parameters
         client: Optional Prisma client for transactions
+        set_public_search_path: If True, sets search_path to include public schema.
+                                Needed for pgvector types and other public schema objects.
 
     Returns:
         Number of affected rows
@@ -204,7 +215,7 @@ async def execute_raw_with_schema(
             client=tx  # Optional transaction client
         )
     """
-    return await _raw_with_schema(query_template, *args, execute=True, client=client)  # type: ignore
+    return await _raw_with_schema(query_template, *args, execute=True, client=client, set_public_search_path=set_public_search_path)  # type: ignore
 
 
 class BaseDbModel(BaseModel):

autogpt_platform/backend/backend/data/event_bus.py

@@ -103,18 +103,8 @@ class RedisEventBus(BaseRedisEventBus[M], ABC):
         return redis.get_redis()
 
     def publish_event(self, event: M, channel_key: str):
-        """
-        Publish an event to Redis. Gracefully handles connection failures
-        by logging the error instead of raising exceptions.
-        """
-        try:
-            message, full_channel_name = self._serialize_message(event, channel_key)
-            self.connection.publish(full_channel_name, message)
-        except Exception:
-            logger.exception(
-                f"Failed to publish event to Redis channel {channel_key}. "
-                "Event bus operation will continue without Redis connectivity."
-            )
+        message, full_channel_name = self._serialize_message(event, channel_key)
+        self.connection.publish(full_channel_name, message)
 
     def listen_events(self, channel_key: str) -> Generator[M, None, None]:
         pubsub, full_channel_name = self._get_pubsub_channel(
@@ -138,19 +128,9 @@ class AsyncRedisEventBus(BaseRedisEventBus[M], ABC):
         return await redis.get_redis_async()
 
     async def publish_event(self, event: M, channel_key: str):
-        """
-        Publish an event to Redis. Gracefully handles connection failures
-        by logging the error instead of raising exceptions.
-        """
-        try:
-            message, full_channel_name = self._serialize_message(event, channel_key)
-            connection = await self.connection
-            await connection.publish(full_channel_name, message)
-        except Exception:
-            logger.exception(
-                f"Failed to publish event to Redis channel {channel_key}. "
-                "Event bus operation will continue without Redis connectivity."
-            )
+        message, full_channel_name = self._serialize_message(event, channel_key)
+        connection = await self.connection
+        await connection.publish(full_channel_name, message)
 
     async def listen_events(self, channel_key: str) -> AsyncGenerator[M, None]:
         pubsub, full_channel_name = self._get_pubsub_channel(