refactor: address review feedback

- Move helpers after search_agents function
- Simplify list_all logic by setting query='' early
- Update find_library_agent description to 'Search for or list'

.dockerignore

@@ -5,42 +5,13 @@
 !docs/
 
 # Platform - Libs
-!autogpt_platform/autogpt_libs/autogpt_libs/
-!autogpt_platform/autogpt_libs/pyproject.toml
-!autogpt_platform/autogpt_libs/poetry.lock
-!autogpt_platform/autogpt_libs/README.md
+!autogpt_platform/autogpt_libs/
 
 # Platform - Backend
-!autogpt_platform/backend/backend/
-!autogpt_platform/backend/test/e2e_test_data.py
-!autogpt_platform/backend/migrations/
-!autogpt_platform/backend/schema.prisma
-!autogpt_platform/backend/pyproject.toml
-!autogpt_platform/backend/poetry.lock
-!autogpt_platform/backend/README.md
-!autogpt_platform/backend/.env
-!autogpt_platform/backend/gen_prisma_types_stub.py
-
-# Platform - Market
-!autogpt_platform/market/market/
-!autogpt_platform/market/scripts.py
-!autogpt_platform/market/schema.prisma
-!autogpt_platform/market/pyproject.toml
-!autogpt_platform/market/poetry.lock
-!autogpt_platform/market/README.md
+!autogpt_platform/backend/
 
 # Platform - Frontend
-!autogpt_platform/frontend/src/
-!autogpt_platform/frontend/public/
-!autogpt_platform/frontend/scripts/
-!autogpt_platform/frontend/package.json
-!autogpt_platform/frontend/pnpm-lock.yaml
-!autogpt_platform/frontend/tsconfig.json
-!autogpt_platform/frontend/README.md
-## config
-!autogpt_platform/frontend/*.config.*
-!autogpt_platform/frontend/.env.*
-!autogpt_platform/frontend/.env
+!autogpt_platform/frontend/
 
 # Classic - AutoGPT
 !classic/original_autogpt/autogpt/
@@ -64,6 +35,38 @@
 # Classic - Frontend
 !classic/frontend/build/web/
 
-# Explicitly re-ignore some folders
-.*
-**/__pycache__
+# Explicitly re-ignore unwanted files from whitelisted directories
+# Note: These patterns MUST come after the whitelist rules to take effect
+
+# Hidden files and directories (but keep frontend .env files needed for build)
+**/.*
+!autogpt_platform/frontend/.env
+!autogpt_platform/frontend/.env.default
+!autogpt_platform/frontend/.env.production
+
+# Python artifacts
+**/__pycache__/
+**/*.pyc
+**/*.pyo
+**/.venv/
+**/.ruff_cache/
+**/.pytest_cache/
+**/.coverage
+**/htmlcov/
+
+# Node artifacts
+**/node_modules/
+**/.next/
+**/storybook-static/
+**/playwright-report/
+**/test-results/
+
+# Build artifacts
+**/dist/
+**/build/
+!autogpt_platform/frontend/src/**/build/
+**/target/
+
+# Logs and temp files
+**/*.log
+**/*.tmp

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

@@ -40,6 +40,48 @@ jobs:
           git checkout -b "$BRANCH_NAME"
           echo "branch_name=$BRANCH_NAME" >> $GITHUB_OUTPUT
 
+      # Backend Python/Poetry setup (so Claude can run linting/tests)
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Set up Python dependency cache
+        uses: actions/cache@v5
+        with:
+          path: ~/.cache/pypoetry
+          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
+
+      - name: Install Poetry
+        run: |
+          cd autogpt_platform/backend
+          HEAD_POETRY_VERSION=$(python3 ../../.github/workflows/scripts/get_package_version_from_lockfile.py poetry)
+          curl -sSL https://install.python-poetry.org | POETRY_VERSION=$HEAD_POETRY_VERSION python3 -
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Install Python dependencies
+        working-directory: autogpt_platform/backend
+        run: poetry install
+
+      - name: Generate Prisma Client
+        working-directory: autogpt_platform/backend
+        run: poetry run prisma generate && poetry run gen-prisma-stub
+
+      # Frontend Node.js/pnpm setup (so Claude can run linting/tests)
+      - name: Enable corepack
+        run: corepack enable
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v6
+        with:
+          node-version: "22"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
+
+      - name: Install JavaScript dependencies
+        working-directory: autogpt_platform/frontend
+        run: pnpm install --frozen-lockfile
+
       - name: Get CI failure details
         id: failure_details
         uses: actions/github-script@v8

.github/workflows/claude-dependabot.yml

@@ -77,27 +77,15 @@ jobs:
         run: poetry run prisma generate && poetry run gen-prisma-stub
 
       # Frontend Node.js/pnpm setup (mirrors platform-frontend-ci.yml)
+      - name: Enable corepack
+        run: corepack enable
+
       - name: Set up Node.js
         uses: actions/setup-node@v6
         with:
           node-version: "22"
-
-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Set pnpm store directory
-        run: |
-          pnpm config set store-dir ~/.pnpm-store
-          echo "PNPM_HOME=$HOME/.pnpm-store" >> $GITHUB_ENV
-
-      - name: Cache frontend dependencies
-        uses: actions/cache@v5
-        with:
-          path: ~/.pnpm-store
-          key: ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/package.json') }}
-          restore-keys: |
-            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
-            ${{ runner.os }}-pnpm-
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
       - name: Install JavaScript dependencies
         working-directory: autogpt_platform/frontend

.github/workflows/claude.yml

@@ -93,27 +93,15 @@ jobs:
         run: poetry run prisma generate && poetry run gen-prisma-stub
 
       # Frontend Node.js/pnpm setup (mirrors platform-frontend-ci.yml)
+      - name: Enable corepack
+        run: corepack enable
+
       - name: Set up Node.js
         uses: actions/setup-node@v6
         with:
           node-version: "22"
-
-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Set pnpm store directory
-        run: |
-          pnpm config set store-dir ~/.pnpm-store
-          echo "PNPM_HOME=$HOME/.pnpm-store" >> $GITHUB_ENV
-
-      - name: Cache frontend dependencies
-        uses: actions/cache@v5
-        with:
-          path: ~/.pnpm-store
-          key: ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/package.json') }}
-          restore-keys: |
-            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
-            ${{ runner.os }}-pnpm-
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
       - name: Install JavaScript dependencies
         working-directory: autogpt_platform/frontend

.github/workflows/codeql.yml

@@ -62,7 +62,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v3
+      uses: github/codeql-action/init@v4
       with:
         languages: ${{ matrix.language }}
         build-mode: ${{ matrix.build-mode }}
@@ -93,6 +93,6 @@ jobs:
         exit 1
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v3
+      uses: github/codeql-action/analyze@v4
       with:
         category: "/language:${{matrix.language}}"

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

@@ -7,6 +7,10 @@ on:
       - "docs/integrations/**"
       - "autogpt_platform/backend/backend/blocks/**"
 
+concurrency:
+  group: claude-docs-review-${{ github.event.pull_request.number }}
+  cancel-in-progress: true
+
 jobs:
   claude-review:
     # Only run for PRs from members/collaborators
@@ -91,5 +95,35 @@ jobs:
             3. Read corresponding documentation files to verify accuracy
             4. Provide your feedback as a PR comment
 
+            ## IMPORTANT: Comment Marker
+            Start your PR comment with exactly this HTML comment marker on its own line:
+            <!-- CLAUDE_DOCS_REVIEW -->
+
+            This marker is used to identify and replace your comment on subsequent runs.
+
             Be constructive and specific. If everything looks good, say so!
             If there are issues, explain what's wrong and suggest how to fix it.
+
+      - name: Delete old Claude review comments
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Get all comment IDs with our marker, sorted by creation date (oldest first)
+          COMMENT_IDS=$(gh api \
+            repos/${{ github.repository }}/issues/${{ github.event.pull_request.number }}/comments \
+            --jq '[.[] | select(.body | contains("<!-- CLAUDE_DOCS_REVIEW -->"))] | sort_by(.created_at) | .[].id')
+
+          # Count comments
+          COMMENT_COUNT=$(echo "$COMMENT_IDS" | grep -c . || true)
+
+          if [ "$COMMENT_COUNT" -gt 1 ]; then
+            # Delete all but the last (newest) comment
+            echo "$COMMENT_IDS" | head -n -1 | while read -r COMMENT_ID; do
+              if [ -n "$COMMENT_ID" ]; then
+                echo "Deleting old review comment: $COMMENT_ID"
+                gh api -X DELETE repos/${{ github.repository }}/issues/comments/$COMMENT_ID
+              fi
+            done
+          else
+            echo "No old review comments to clean up"
+          fi

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

@@ -41,13 +41,18 @@ jobs:
         ports:
           - 6379:6379
       rabbitmq:
-        image: rabbitmq:3.12-management
+        image: rabbitmq:4.1.4
         ports:
           - 5672:5672
-          - 15672:15672
         env:
           RABBITMQ_DEFAULT_USER: ${{ env.RABBITMQ_DEFAULT_USER }}
           RABBITMQ_DEFAULT_PASS: ${{ env.RABBITMQ_DEFAULT_PASS }}
+        options: >-
+          --health-cmd "rabbitmq-diagnostics -q ping"
+          --health-interval 30s
+          --health-timeout 10s
+          --health-retries 5
+          --health-start-period 10s
       clamav:
         image: clamav/clamav-debian:latest
         ports:

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

@@ -6,10 +6,16 @@ on:
     paths:
       - ".github/workflows/platform-frontend-ci.yml"
       - "autogpt_platform/frontend/**"
+      - "autogpt_platform/backend/Dockerfile"
+      - "autogpt_platform/docker-compose.yml"
+      - "autogpt_platform/docker-compose.platform.yml"
   pull_request:
     paths:
       - ".github/workflows/platform-frontend-ci.yml"
       - "autogpt_platform/frontend/**"
+      - "autogpt_platform/backend/Dockerfile"
+      - "autogpt_platform/docker-compose.yml"
+      - "autogpt_platform/docker-compose.platform.yml"
   merge_group:
   workflow_dispatch:
 
@@ -26,7 +32,6 @@ jobs:
   setup:
     runs-on: ubuntu-latest
     outputs:
-      cache-key: ${{ steps.cache-key.outputs.key }}
       components-changed: ${{ steps.filter.outputs.components }}
 
     steps:
@@ -41,28 +46,17 @@ jobs:
             components:
               - 'autogpt_platform/frontend/src/components/**'
 
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-
       - name: Enable corepack
         run: corepack enable
 
-      - name: Generate cache key
-        id: cache-key
-        run: echo "key=${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/package.json') }}" >> $GITHUB_OUTPUT
-
-      - name: Cache dependencies
-        uses: actions/cache@v5
+      - name: Set up Node
+        uses: actions/setup-node@v6
         with:
-          path: ~/.pnpm-store
-          key: ${{ steps.cache-key.outputs.key }}
-          restore-keys: |
-            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
-            ${{ runner.os }}-pnpm-
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
-      - name: Install dependencies
+      - name: Install dependencies to populate cache
         run: pnpm install --frozen-lockfile
 
   lint:
@@ -73,22 +67,15 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v6
 
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-
       - name: Enable corepack
         run: corepack enable
 
-      - name: Restore dependencies cache
-        uses: actions/cache@v5
+      - name: Set up Node
+        uses: actions/setup-node@v6
         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-
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
@@ -111,22 +98,15 @@ jobs:
         with:
           fetch-depth: 0
 
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-
       - name: Enable corepack
         run: corepack enable
 
-      - name: Restore dependencies cache
-        uses: actions/cache@v5
+      - name: Set up Node
+        uses: actions/setup-node@v6
         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-
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
@@ -141,10 +121,8 @@ jobs:
           exitOnceUploaded: true
 
   e2e_test:
+    name: end-to-end tests
     runs-on: big-boi
-    needs: setup
-    strategy:
-      fail-fast: false
 
     steps:
       - name: Checkout repository
@@ -152,19 +130,11 @@ jobs:
         with:
           submodules: recursive
 
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-
-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Copy default supabase .env
+      - name: Set up Platform - Copy default supabase .env
         run: |
           cp ../.env.default ../.env
 
-      - name: Copy backend .env and set OpenAI API key
+      - name: Set up Platform - Copy backend .env and set OpenAI API key
         run: |
           cp ../backend/.env.default ../backend/.env
           echo "OPENAI_INTERNAL_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> ../backend/.env
@@ -172,77 +142,125 @@ jobs:
           # Used by E2E test data script to generate embeddings for approved store agents
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
 
-      - name: Set up Docker Buildx
+      - name: Set up Platform - Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
+        with:
+          driver: docker-container
+          driver-opts: network=host
 
-      - name: Cache Docker layers
+      - name: Set up Platform - Expose GHA cache to docker buildx CLI
+        uses: crazy-max/ghaction-github-runtime@v3
+
+      - name: Set up Platform - Build Docker images (with cache)
+        working-directory: autogpt_platform
+        run: |
+          pip install pyyaml
+
+          # Resolve extends and generate a flat compose file that bake can understand
+          docker compose -f docker-compose.yml config > docker-compose.resolved.yml
+
+          # Add cache configuration to the resolved compose file
+          python ../.github/workflows/scripts/docker-ci-fix-compose-build-cache.py \
+            --source docker-compose.resolved.yml \
+            --cache-from "type=gha" \
+            --cache-to "type=gha,mode=max" \
+            --backend-hash "${{ hashFiles('autogpt_platform/backend/Dockerfile', 'autogpt_platform/backend/poetry.lock', 'autogpt_platform/backend/backend') }}" \
+            --frontend-hash "${{ hashFiles('autogpt_platform/frontend/Dockerfile', 'autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/src') }}" \
+            --git-ref "${{ github.ref }}"
+
+          # Build with bake using the resolved compose file (now includes cache config)
+          docker buildx bake --allow=fs.read=.. -f docker-compose.resolved.yml --load
+        env:
+          NEXT_PUBLIC_PW_TEST: true
+
+      - name: Set up tests - Cache E2E test data
+        id: e2e-data-cache
         uses: actions/cache@v5
         with:
-          path: /tmp/.buildx-cache
-          key: ${{ runner.os }}-buildx-frontend-test-${{ hashFiles('autogpt_platform/docker-compose.yml', 'autogpt_platform/backend/Dockerfile', 'autogpt_platform/backend/pyproject.toml', 'autogpt_platform/backend/poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-buildx-frontend-test-
+          path: /tmp/e2e_test_data.sql
+          key: e2e-test-data-${{ hashFiles('autogpt_platform/backend/test/e2e_test_data.py', 'autogpt_platform/backend/migrations/**', '.github/workflows/platform-frontend-ci.yml') }}
 
-      - name: Run docker compose
+      - name: Set up Platform - Start Supabase DB + Auth
         run: |
-          NEXT_PUBLIC_PW_TEST=true docker compose -f ../docker-compose.yml up -d
+          docker compose -f ../docker-compose.resolved.yml up -d db auth --no-build
+          echo "Waiting for database to be ready..."
+          timeout 60 sh -c 'until docker compose -f ../docker-compose.resolved.yml exec -T db pg_isready -U postgres 2>/dev/null; do sleep 2; done'
+          echo "Waiting for auth service to be ready..."
+          timeout 60 sh -c 'until docker compose -f ../docker-compose.resolved.yml exec -T db psql -U postgres -d postgres -c "SELECT 1 FROM auth.users LIMIT 1" 2>/dev/null; do sleep 2; done' || echo "Auth schema check timeout, continuing..."
+
+      - name: Set up Platform - Run migrations
+        run: |
+          echo "Running migrations..."
+          docker compose -f ../docker-compose.resolved.yml run --rm migrate
+          echo "✅ Migrations completed"
         env:
-          DOCKER_BUILDKIT: 1
-          BUILDX_CACHE_FROM: type=local,src=/tmp/.buildx-cache
-          BUILDX_CACHE_TO: type=local,dest=/tmp/.buildx-cache-new,mode=max
+          NEXT_PUBLIC_PW_TEST: true
 
-      - name: Move cache
+      - name: Set up tests - Load cached E2E test data
+        if: steps.e2e-data-cache.outputs.cache-hit == 'true'
         run: |
-          rm -rf /tmp/.buildx-cache
-          if [ -d "/tmp/.buildx-cache-new" ]; then
-            mv /tmp/.buildx-cache-new /tmp/.buildx-cache
-          fi
+          echo "✅ Found cached E2E test data, restoring..."
+          {
+            echo "SET session_replication_role = 'replica';"
+            cat /tmp/e2e_test_data.sql
+            echo "SET session_replication_role = 'origin';"
+          } | docker compose -f ../docker-compose.resolved.yml exec -T db psql -U postgres -d postgres -b
+          # Refresh materialized views after restore
+          docker compose -f ../docker-compose.resolved.yml exec -T db \
+            psql -U postgres -d postgres -b -c "SET search_path TO platform; SELECT refresh_store_materialized_views();" || true
 
-      - name: Wait for services to be ready
+          echo "✅ E2E test data restored from cache"
+
+      - name: Set up Platform - Start (all other services)
         run: |
+          docker compose -f ../docker-compose.resolved.yml up -d --no-build
           echo "Waiting for rest_server to be ready..."
           timeout 60 sh -c 'until curl -f http://localhost:8006/health 2>/dev/null; do sleep 2; done' || echo "Rest server health check timeout, continuing..."
-          echo "Waiting for database to be ready..."
-          timeout 60 sh -c 'until docker compose -f ../docker-compose.yml exec -T db pg_isready -U postgres 2>/dev/null; do sleep 2; done' || echo "Database ready check timeout, continuing..."
+        env:
+          NEXT_PUBLIC_PW_TEST: true
 
-      - name: Create E2E test data
+      - name: Set up tests - Create E2E test data
+        if: steps.e2e-data-cache.outputs.cache-hit != 'true'
         run: |
           echo "Creating E2E test data..."
-          # First try to run the script from inside the container
-          if docker compose -f ../docker-compose.yml exec -T rest_server test -f /app/autogpt_platform/backend/test/e2e_test_data.py; then
-            echo "✅ Found e2e_test_data.py in container, running it..."
-            docker compose -f ../docker-compose.yml exec -T rest_server sh -c "cd /app/autogpt_platform && python backend/test/e2e_test_data.py" || {
-              echo "❌ E2E test data creation failed!"
-              docker compose -f ../docker-compose.yml logs --tail=50 rest_server
-              exit 1
-            }
-          else
-            echo "⚠️ e2e_test_data.py not found in container, copying and running..."
-            # Copy the script into the container and run it
-            docker cp ../backend/test/e2e_test_data.py $(docker compose -f ../docker-compose.yml ps -q rest_server):/tmp/e2e_test_data.py || {
-              echo "❌ Failed to copy script to container"
-              exit 1
-            }
-            docker compose -f ../docker-compose.yml exec -T rest_server sh -c "cd /app/autogpt_platform && python /tmp/e2e_test_data.py" || {
-              echo "❌ E2E test data creation failed!"
-              docker compose -f ../docker-compose.yml logs --tail=50 rest_server
-              exit 1
-            }
-          fi
+          docker cp ../backend/test/e2e_test_data.py $(docker compose -f ../docker-compose.resolved.yml ps -q rest_server):/tmp/e2e_test_data.py
+          docker compose -f ../docker-compose.resolved.yml exec -T rest_server sh -c "cd /app/autogpt_platform && python /tmp/e2e_test_data.py" || {
+            echo "❌ E2E test data creation failed!"
+            docker compose -f ../docker-compose.resolved.yml logs --tail=50 rest_server
+            exit 1
+          }
 
-      - name: Restore dependencies cache
-        uses: actions/cache@v5
+          # Dump auth.users + platform schema for cache (two separate dumps)
+          echo "Dumping database for cache..."
+          {
+            docker compose -f ../docker-compose.resolved.yml exec -T db \
+              pg_dump -U postgres --data-only --column-inserts \
+              --table='auth.users' postgres
+            docker compose -f ../docker-compose.resolved.yml exec -T db \
+              pg_dump -U postgres --data-only --column-inserts \
+              --schema=platform \
+              --exclude-table='platform._prisma_migrations' \
+              --exclude-table='platform.apscheduler_jobs' \
+              --exclude-table='platform.apscheduler_jobs_batched_notifications' \
+              postgres
+          } > /tmp/e2e_test_data.sql
+
+          echo "✅ Database dump created for caching ($(wc -l < /tmp/e2e_test_data.sql) lines)"
+
+      - name: Set up tests - Enable corepack
+        run: corepack enable
+
+      - name: Set up tests - Set up Node
+        uses: actions/setup-node@v6
         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-
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
-      - name: Install dependencies
+      - name: Set up tests - Install dependencies
         run: pnpm install --frozen-lockfile
 
-      - name: Install Browser 'chromium'
+      - name: Set up tests - Install browser 'chromium'
         run: pnpm playwright install --with-deps chromium
 
       - name: Run Playwright tests
@@ -269,7 +287,7 @@ jobs:
 
       - name: Print Final Docker Compose logs
         if: always()
-        run: docker compose -f ../docker-compose.yml logs
+        run: docker compose -f ../docker-compose.resolved.yml logs
 
   integration_test:
     runs-on: ubuntu-latest
@@ -281,22 +299,15 @@ jobs:
         with:
           submodules: recursive
 
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-
       - name: Enable corepack
         run: corepack enable
 
-      - name: Restore dependencies cache
-        uses: actions/cache@v5
+      - name: Set up Node
+        uses: actions/setup-node@v6
         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-
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
       - name: Install dependencies
         run: pnpm install --frozen-lockfile

.github/workflows/pr-overlap-check.yml

@@ -0,0 +1,39 @@
+name: PR Overlap Detection
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+    branches:
+      - dev
+      - master
+
+permissions:
+  contents: read
+  pull-requests: write
+
+jobs:
+  check-overlaps:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0  # Need full history for merge testing
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Configure git
+        run: |
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git config user.name "github-actions[bot]"
+
+      - name: Run overlap detection
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        # Always succeed - this check informs contributors, it shouldn't block merging
+        continue-on-error: true
+        run: |
+          python .github/scripts/detect_overlaps.py ${{ github.event.pull_request.number }}

.github/workflows/scripts/docker-ci-fix-compose-build-cache.py

@@ -0,0 +1,195 @@
+#!/usr/bin/env python3
+"""
+Add cache configuration to a resolved docker-compose file for all services
+that have a build key, and ensure image names match what docker compose expects.
+"""
+
+import argparse
+
+import yaml
+
+
+DEFAULT_BRANCH = "dev"
+CACHE_BUILDS_FOR_COMPONENTS = ["backend", "frontend"]
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Add cache config to a resolved compose file"
+    )
+    parser.add_argument(
+        "--source",
+        required=True,
+        help="Source compose file to read (should be output of `docker compose config`)",
+    )
+    parser.add_argument(
+        "--cache-from",
+        default="type=gha",
+        help="Cache source configuration",
+    )
+    parser.add_argument(
+        "--cache-to",
+        default="type=gha,mode=max",
+        help="Cache destination configuration",
+    )
+    for component in CACHE_BUILDS_FOR_COMPONENTS:
+        parser.add_argument(
+            f"--{component}-hash",
+            default="",
+            help=f"Hash for {component} cache scope (e.g., from hashFiles())",
+        )
+    parser.add_argument(
+        "--git-ref",
+        default="",
+        help="Git ref for branch-based cache scope (e.g., refs/heads/master)",
+    )
+    args = parser.parse_args()
+
+    # Normalize git ref to a safe scope name (e.g., refs/heads/master -> master)
+    git_ref_scope = ""
+    if args.git_ref:
+        git_ref_scope = args.git_ref.replace("refs/heads/", "").replace("/", "-")
+
+    with open(args.source, "r") as f:
+        compose = yaml.safe_load(f)
+
+    # Get project name from compose file or default
+    project_name = compose.get("name", "autogpt_platform")
+
+    def get_image_name(dockerfile: str, target: str) -> str:
+        """Generate image name based on Dockerfile folder and build target."""
+        dockerfile_parts = dockerfile.replace("\\", "/").split("/")
+        if len(dockerfile_parts) >= 2:
+            folder_name = dockerfile_parts[-2]  # e.g., "backend" or "frontend"
+        else:
+            folder_name = "app"
+        return f"{project_name}-{folder_name}:{target}"
+
+    def get_build_key(dockerfile: str, target: str) -> str:
+        """Generate a unique key for a Dockerfile+target combination."""
+        return f"{dockerfile}:{target}"
+
+    def get_component(dockerfile: str) -> str | None:
+        """Get component name (frontend/backend) from dockerfile path."""
+        for component in CACHE_BUILDS_FOR_COMPONENTS:
+            if component in dockerfile:
+                return component
+        return None
+
+    # First pass: collect all services with build configs and identify duplicates
+    # Track which (dockerfile, target) combinations we've seen
+    build_key_to_first_service: dict[str, str] = {}
+    services_to_build: list[str] = []
+    services_to_dedupe: list[str] = []
+
+    for service_name, service_config in compose.get("services", {}).items():
+        if "build" not in service_config:
+            continue
+
+        build_config = service_config["build"]
+        dockerfile = build_config.get("dockerfile", "Dockerfile")
+        target = build_config.get("target", "default")
+        build_key = get_build_key(dockerfile, target)
+
+        if build_key not in build_key_to_first_service:
+            # First service with this build config - it will do the actual build
+            build_key_to_first_service[build_key] = service_name
+            services_to_build.append(service_name)
+        else:
+            # Duplicate - will just use the image from the first service
+            services_to_dedupe.append(service_name)
+
+    # Second pass: configure builds and deduplicate
+    modified_services = []
+    for service_name, service_config in compose.get("services", {}).items():
+        if "build" not in service_config:
+            continue
+
+        build_config = service_config["build"]
+        dockerfile = build_config.get("dockerfile", "Dockerfile")
+        target = build_config.get("target", "latest")
+        image_name = get_image_name(dockerfile, target)
+
+        # Set image name for all services (needed for both builders and deduped)
+        service_config["image"] = image_name
+
+        if service_name in services_to_dedupe:
+            # Remove build config - this service will use the pre-built image
+            del service_config["build"]
+            continue
+
+        # This service will do the actual build - add cache config
+        cache_from_list = []
+        cache_to_list = []
+
+        component = get_component(dockerfile)
+        if not component:
+            # Skip services that don't clearly match frontend/backend
+            continue
+
+        # Get the hash for this component
+        component_hash = getattr(args, f"{component}_hash")
+
+        # Scope format: platform-{component}-{target}-{hash|ref}
+        # Example: platform-backend-server-abc123
+
+        if "type=gha" in args.cache_from:
+            # 1. Primary: exact hash match (most specific)
+            if component_hash:
+                hash_scope = f"platform-{component}-{target}-{component_hash}"
+                cache_from_list.append(f"{args.cache_from},scope={hash_scope}")
+
+            # 2. Fallback: branch-based cache
+            if git_ref_scope:
+                ref_scope = f"platform-{component}-{target}-{git_ref_scope}"
+                cache_from_list.append(f"{args.cache_from},scope={ref_scope}")
+
+            # 3. Fallback: dev branch cache (for PRs/feature branches)
+            if git_ref_scope and git_ref_scope != DEFAULT_BRANCH:
+                master_scope = f"platform-{component}-{target}-{DEFAULT_BRANCH}"
+                cache_from_list.append(f"{args.cache_from},scope={master_scope}")
+
+        if "type=gha" in args.cache_to:
+            # Write to both hash-based and branch-based scopes
+            if component_hash:
+                hash_scope = f"platform-{component}-{target}-{component_hash}"
+                cache_to_list.append(f"{args.cache_to},scope={hash_scope}")
+
+            if git_ref_scope:
+                ref_scope = f"platform-{component}-{target}-{git_ref_scope}"
+                cache_to_list.append(f"{args.cache_to},scope={ref_scope}")
+
+        # Ensure we have at least one cache source/target
+        if not cache_from_list:
+            cache_from_list.append(args.cache_from)
+        if not cache_to_list:
+            cache_to_list.append(args.cache_to)
+
+        build_config["cache_from"] = cache_from_list
+        build_config["cache_to"] = cache_to_list
+        modified_services.append(service_name)
+
+    # Write back to the same file
+    with open(args.source, "w") as f:
+        yaml.dump(compose, f, default_flow_style=False, sort_keys=False)
+
+    print(f"Added cache config to {len(modified_services)} services in {args.source}:")
+    for svc in modified_services:
+        svc_config = compose["services"][svc]
+        build_cfg = svc_config.get("build", {})
+        cache_from_list = build_cfg.get("cache_from", ["none"])
+        cache_to_list = build_cfg.get("cache_to", ["none"])
+        print(f"  - {svc}")
+        print(f"      image: {svc_config.get('image', 'N/A')}")
+        print(f"      cache_from: {cache_from_list}")
+        print(f"      cache_to: {cache_to_list}")
+    if services_to_dedupe:
+        print(
+            f"Deduplicated {len(services_to_dedupe)} services (will use pre-built images):"
+        )
+        for svc in services_to_dedupe:
+            print(f"  - {svc} -> {compose['services'][svc].get('image', 'N/A')}")
+
+
+if __name__ == "__main__":
+    main()

autogpt_platform/CLAUDE.md

@@ -45,6 +45,11 @@ AutoGPT Platform is a monorepo containing:
 - Backend/Frontend services use YAML anchors for consistent configuration
 - Supabase services (`db/docker/docker-compose.yml`) follow the same pattern
 
+### Branching Strategy
+
+- **`dev`** is the main development branch. All PRs should target `dev`.
+- **`master`** is the production branch. Only used for production releases.
+
 ### Creating Pull Requests
 
 - Create the PR against the `dev` branch of the repository.

autogpt_platform/autogpt_libs/poetry.lock

@@ -448,61 +448,61 @@ toml = ["tomli ; python_full_version <= \"3.11.0a6\""]
 
 [[package]]
 name = "cryptography"
-version = "46.0.4"
+version = "46.0.5"
 description = "cryptography is a package which provides cryptographic recipes and primitives to Python developers."
 optional = false
 python-versions = "!=3.9.0,!=3.9.1,>=3.8"
 groups = ["main"]
 files = [
-    {file = "cryptography-46.0.4-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:281526e865ed4166009e235afadf3a4c4cba6056f99336a99efba65336fd5485"},
-    {file = "cryptography-46.0.4-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5f14fba5bf6f4390d7ff8f086c566454bff0411f6d8aa7af79c88b6f9267aecc"},
-    {file = "cryptography-46.0.4-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:47bcd19517e6389132f76e2d5303ded6cf3f78903da2158a671be8de024f4cd0"},
-    {file = "cryptography-46.0.4-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:01df4f50f314fbe7009f54046e908d1754f19d0c6d3070df1e6268c5a4af09fa"},
-    {file = "cryptography-46.0.4-cp311-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:5aa3e463596b0087b3da0dbe2b2487e9fc261d25da85754e30e3b40637d61f81"},
-    {file = "cryptography-46.0.4-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:0a9ad24359fee86f131836a9ac3bffc9329e956624a2d379b613f8f8abaf5255"},
-    {file = "cryptography-46.0.4-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:dc1272e25ef673efe72f2096e92ae39dea1a1a450dd44918b15351f72c5a168e"},
-    {file = "cryptography-46.0.4-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:de0f5f4ec8711ebc555f54735d4c673fc34b65c44283895f1a08c2b49d2fd99c"},
-    {file = "cryptography-46.0.4-cp311-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:eeeb2e33d8dbcccc34d64651f00a98cb41b2dc69cef866771a5717e6734dfa32"},
-    {file = "cryptography-46.0.4-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:3d425eacbc9aceafd2cb429e42f4e5d5633c6f873f5e567077043ef1b9bbf616"},
-    {file = "cryptography-46.0.4-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:91627ebf691d1ea3976a031b61fb7bac1ccd745afa03602275dda443e11c8de0"},
-    {file = "cryptography-46.0.4-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:2d08bc22efd73e8854b0b7caff402d735b354862f1145d7be3b9c0f740fef6a0"},
-    {file = "cryptography-46.0.4-cp311-abi3-win32.whl", hash = "sha256:82a62483daf20b8134f6e92898da70d04d0ef9a75829d732ea1018678185f4f5"},
-    {file = "cryptography-46.0.4-cp311-abi3-win_amd64.whl", hash = "sha256:6225d3ebe26a55dbc8ead5ad1265c0403552a63336499564675b29eb3184c09b"},
-    {file = "cryptography-46.0.4-cp314-cp314t-macosx_10_9_universal2.whl", hash = "sha256:485e2b65d25ec0d901bca7bcae0f53b00133bf3173916d8e421f6fddde103908"},
-    {file = "cryptography-46.0.4-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:078e5f06bd2fa5aea5a324f2a09f914b1484f1d0c2a4d6a8a28c74e72f65f2da"},
-    {file = "cryptography-46.0.4-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:dce1e4f068f03008da7fa51cc7abc6ddc5e5de3e3d1550334eaf8393982a5829"},
-    {file = "cryptography-46.0.4-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:2067461c80271f422ee7bdbe79b9b4be54a5162e90345f86a23445a0cf3fd8a2"},
-    {file = "cryptography-46.0.4-cp314-cp314t-manylinux_2_28_ppc64le.whl", hash = "sha256:c92010b58a51196a5f41c3795190203ac52edfd5dc3ff99149b4659eba9d2085"},
-    {file = "cryptography-46.0.4-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:829c2b12bbc5428ab02d6b7f7e9bbfd53e33efd6672d21341f2177470171ad8b"},
-    {file = "cryptography-46.0.4-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:62217ba44bf81b30abaeda1488686a04a702a261e26f87db51ff61d9d3510abd"},
-    {file = "cryptography-46.0.4-cp314-cp314t-manylinux_2_34_aarch64.whl", hash = "sha256:9c2da296c8d3415b93e6053f5a728649a87a48ce084a9aaf51d6e46c87c7f2d2"},
-    {file = "cryptography-46.0.4-cp314-cp314t-manylinux_2_34_ppc64le.whl", hash = "sha256:9b34d8ba84454641a6bf4d6762d15847ecbd85c1316c0a7984e6e4e9f748ec2e"},
-    {file = "cryptography-46.0.4-cp314-cp314t-manylinux_2_34_x86_64.whl", hash = "sha256:df4a817fa7138dd0c96c8c8c20f04b8aaa1fac3bbf610913dcad8ea82e1bfd3f"},
-    {file = "cryptography-46.0.4-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:b1de0ebf7587f28f9190b9cb526e901bf448c9e6a99655d2b07fff60e8212a82"},
-    {file = "cryptography-46.0.4-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:9b4d17bc7bd7cdd98e3af40b441feaea4c68225e2eb2341026c84511ad246c0c"},
-    {file = "cryptography-46.0.4-cp314-cp314t-win32.whl", hash = "sha256:c411f16275b0dea722d76544a61d6421e2cc829ad76eec79280dbdc9ddf50061"},
-    {file = "cryptography-46.0.4-cp314-cp314t-win_amd64.whl", hash = "sha256:728fedc529efc1439eb6107b677f7f7558adab4553ef8669f0d02d42d7b959a7"},
-    {file = "cryptography-46.0.4-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:a9556ba711f7c23f77b151d5798f3ac44a13455cc68db7697a1096e6d0563cab"},
-    {file = "cryptography-46.0.4-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8bf75b0259e87fa70bddc0b8b4078b76e7fd512fd9afae6c1193bcf440a4dbef"},
-    {file = "cryptography-46.0.4-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:3c268a3490df22270955966ba236d6bc4a8f9b6e4ffddb78aac535f1a5ea471d"},
-    {file = "cryptography-46.0.4-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:812815182f6a0c1d49a37893a303b44eaac827d7f0d582cecfc81b6427f22973"},
-    {file = "cryptography-46.0.4-cp38-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:a90e43e3ef65e6dcf969dfe3bb40cbf5aef0d523dff95bfa24256be172a845f4"},
-    {file = "cryptography-46.0.4-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:a05177ff6296644ef2876fce50518dffb5bcdf903c85250974fc8bc85d54c0af"},
-    {file = "cryptography-46.0.4-cp38-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:daa392191f626d50f1b136c9b4cf08af69ca8279d110ea24f5c2700054d2e263"},
-    {file = "cryptography-46.0.4-cp38-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:e07ea39c5b048e085f15923511d8121e4a9dc45cee4e3b970ca4f0d338f23095"},
-    {file = "cryptography-46.0.4-cp38-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:d5a45ddc256f492ce42a4e35879c5e5528c09cd9ad12420828c972951d8e016b"},
-    {file = "cryptography-46.0.4-cp38-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:6bb5157bf6a350e5b28aee23beb2d84ae6f5be390b2f8ee7ea179cda077e1019"},
-    {file = "cryptography-46.0.4-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:dd5aba870a2c40f87a3af043e0dee7d9eb02d4aff88a797b48f2b43eff8c3ab4"},
-    {file = "cryptography-46.0.4-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:93d8291da8d71024379ab2cb0b5c57915300155ad42e07f76bea6ad838d7e59b"},
-    {file = "cryptography-46.0.4-cp38-abi3-win32.whl", hash = "sha256:0563655cb3c6d05fb2afe693340bc050c30f9f34e15763361cf08e94749401fc"},
-    {file = "cryptography-46.0.4-cp38-abi3-win_amd64.whl", hash = "sha256:fa0900b9ef9c49728887d1576fd8d9e7e3ea872fa9b25ef9b64888adc434e976"},
-    {file = "cryptography-46.0.4-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:766330cce7416c92b5e90c3bb71b1b79521760cdcfc3a6a1a182d4c9fab23d2b"},
-    {file = "cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c236a44acfb610e70f6b3e1c3ca20ff24459659231ef2f8c48e879e2d32b73da"},
-    {file = "cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:8a15fb869670efa8f83cbffbc8753c1abf236883225aed74cd179b720ac9ec80"},
-    {file = "cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:fdc3daab53b212472f1524d070735b2f0c214239df131903bae1d598016fa822"},
-    {file = "cryptography-46.0.4-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:44cc0675b27cadb71bdbb96099cca1fa051cd11d2ade09e5cd3a2edb929ed947"},
-    {file = "cryptography-46.0.4-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:be8c01a7d5a55f9a47d1888162b76c8f49d62b234d88f0ff91a9fbebe32ffbc3"},
-    {file = "cryptography-46.0.4.tar.gz", hash = "sha256:bfd019f60f8abc2ed1b9be4ddc21cfef059c841d86d710bb69909a688cbb8f59"},
+    {file = "cryptography-46.0.5-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:351695ada9ea9618b3500b490ad54c739860883df6c1f555e088eaf25b1bbaad"},
+    {file = "cryptography-46.0.5-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:c18ff11e86df2e28854939acde2d003f7984f721eba450b56a200ad90eeb0e6b"},
+    {file = "cryptography-46.0.5-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:4d7e3d356b8cd4ea5aff04f129d5f66ebdc7b6f8eae802b93739ed520c47c79b"},
+    {file = "cryptography-46.0.5-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:50bfb6925eff619c9c023b967d5b77a54e04256c4281b0e21336a130cd7fc263"},
+    {file = "cryptography-46.0.5-cp311-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:803812e111e75d1aa73690d2facc295eaefd4439be1023fefc4995eaea2af90d"},
+    {file = "cryptography-46.0.5-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3ee190460e2fbe447175cda91b88b84ae8322a104fc27766ad09428754a618ed"},
+    {file = "cryptography-46.0.5-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:f145bba11b878005c496e93e257c1e88f154d278d2638e6450d17e0f31e558d2"},
+    {file = "cryptography-46.0.5-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:e9251e3be159d1020c4030bd2e5f84d6a43fe54b6c19c12f51cde9542a2817b2"},
+    {file = "cryptography-46.0.5-cp311-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:47fb8a66058b80e509c47118ef8a75d14c455e81ac369050f20ba0d23e77fee0"},
+    {file = "cryptography-46.0.5-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:4c3341037c136030cb46e4b1e17b7418ea4cbd9dd207e4a6f3b2b24e0d4ac731"},
+    {file = "cryptography-46.0.5-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:890bcb4abd5a2d3f852196437129eb3667d62630333aacc13dfd470fad3aaa82"},
+    {file = "cryptography-46.0.5-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:80a8d7bfdf38f87ca30a5391c0c9ce4ed2926918e017c29ddf643d0ed2778ea1"},
+    {file = "cryptography-46.0.5-cp311-abi3-win32.whl", hash = "sha256:60ee7e19e95104d4c03871d7d7dfb3d22ef8a9b9c6778c94e1c8fcc8365afd48"},
+    {file = "cryptography-46.0.5-cp311-abi3-win_amd64.whl", hash = "sha256:38946c54b16c885c72c4f59846be9743d699eee2b69b6988e0a00a01f46a61a4"},
+    {file = "cryptography-46.0.5-cp314-cp314t-macosx_10_9_universal2.whl", hash = "sha256:94a76daa32eb78d61339aff7952ea819b1734b46f73646a07decb40e5b3448e2"},
+    {file = "cryptography-46.0.5-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5be7bf2fb40769e05739dd0046e7b26f9d4670badc7b032d6ce4db64dddc0678"},
+    {file = "cryptography-46.0.5-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:fe346b143ff9685e40192a4960938545c699054ba11d4f9029f94751e3f71d87"},
+    {file = "cryptography-46.0.5-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:c69fd885df7d089548a42d5ec05be26050ebcd2283d89b3d30676eb32ff87dee"},
+    {file = "cryptography-46.0.5-cp314-cp314t-manylinux_2_28_ppc64le.whl", hash = "sha256:8293f3dea7fc929ef7240796ba231413afa7b68ce38fd21da2995549f5961981"},
+    {file = "cryptography-46.0.5-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:1abfdb89b41c3be0365328a410baa9df3ff8a9110fb75e7b52e66803ddabc9a9"},
+    {file = "cryptography-46.0.5-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:d66e421495fdb797610a08f43b05269e0a5ea7f5e652a89bfd5a7d3c1dee3648"},
+    {file = "cryptography-46.0.5-cp314-cp314t-manylinux_2_34_aarch64.whl", hash = "sha256:4e817a8920bfbcff8940ecfd60f23d01836408242b30f1a708d93198393a80b4"},
+    {file = "cryptography-46.0.5-cp314-cp314t-manylinux_2_34_ppc64le.whl", hash = "sha256:68f68d13f2e1cb95163fa3b4db4bf9a159a418f5f6e7242564fc75fcae667fd0"},
+    {file = "cryptography-46.0.5-cp314-cp314t-manylinux_2_34_x86_64.whl", hash = "sha256:a3d1fae9863299076f05cb8a778c467578262fae09f9dc0ee9b12eb4268ce663"},
+    {file = "cryptography-46.0.5-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:c4143987a42a2397f2fc3b4d7e3a7d313fbe684f67ff443999e803dd75a76826"},
+    {file = "cryptography-46.0.5-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:7d731d4b107030987fd61a7f8ab512b25b53cef8f233a97379ede116f30eb67d"},
+    {file = "cryptography-46.0.5-cp314-cp314t-win32.whl", hash = "sha256:c3bcce8521d785d510b2aad26ae2c966092b7daa8f45dd8f44734a104dc0bc1a"},
+    {file = "cryptography-46.0.5-cp314-cp314t-win_amd64.whl", hash = "sha256:4d8ae8659ab18c65ced284993c2265910f6c9e650189d4e3f68445ef82a810e4"},
+    {file = "cryptography-46.0.5-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:4108d4c09fbbf2789d0c926eb4152ae1760d5a2d97612b92d508d96c861e4d31"},
+    {file = "cryptography-46.0.5-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:7d1f30a86d2757199cb2d56e48cce14deddf1f9c95f1ef1b64ee91ea43fe2e18"},
+    {file = "cryptography-46.0.5-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:039917b0dc418bb9f6edce8a906572d69e74bd330b0b3fea4f79dab7f8ddd235"},
+    {file = "cryptography-46.0.5-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:ba2a27ff02f48193fc4daeadf8ad2590516fa3d0adeeb34336b96f7fa64c1e3a"},
+    {file = "cryptography-46.0.5-cp38-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:61aa400dce22cb001a98014f647dc21cda08f7915ceb95df0c9eaf84b4b6af76"},
+    {file = "cryptography-46.0.5-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3ce58ba46e1bc2aac4f7d9290223cead56743fa6ab94a5d53292ffaac6a91614"},
+    {file = "cryptography-46.0.5-cp38-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:420d0e909050490d04359e7fdb5ed7e667ca5c3c402b809ae2563d7e66a92229"},
+    {file = "cryptography-46.0.5-cp38-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:582f5fcd2afa31622f317f80426a027f30dc792e9c80ffee87b993200ea115f1"},
+    {file = "cryptography-46.0.5-cp38-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:bfd56bb4b37ed4f330b82402f6f435845a5f5648edf1ad497da51a8452d5d62d"},
+    {file = "cryptography-46.0.5-cp38-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:a3d507bb6a513ca96ba84443226af944b0f7f47dcc9a399d110cd6146481d24c"},
+    {file = "cryptography-46.0.5-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:9f16fbdf4da055efb21c22d81b89f155f02ba420558db21288b3d0035bafd5f4"},
+    {file = "cryptography-46.0.5-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:ced80795227d70549a411a4ab66e8ce307899fad2220ce5ab2f296e687eacde9"},
+    {file = "cryptography-46.0.5-cp38-abi3-win32.whl", hash = "sha256:02f547fce831f5096c9a567fd41bc12ca8f11df260959ecc7c3202555cc47a72"},
+    {file = "cryptography-46.0.5-cp38-abi3-win_amd64.whl", hash = "sha256:556e106ee01aa13484ce9b0239bca667be5004efb0aabbed28d353df86445595"},
+    {file = "cryptography-46.0.5-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:3b4995dc971c9fb83c25aa44cf45f02ba86f71ee600d81091c2f0cbae116b06c"},
+    {file = "cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:bc84e875994c3b445871ea7181d424588171efec3e185dced958dad9e001950a"},
+    {file = "cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:2ae6971afd6246710480e3f15824ed3029a60fc16991db250034efd0b9fb4356"},
+    {file = "cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:d861ee9e76ace6cf36a6a89b959ec08e7bc2493ee39d07ffe5acb23ef46d27da"},
+    {file = "cryptography-46.0.5-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:2b7a67c9cd56372f3249b39699f2ad479f6991e62ea15800973b956f4b73e257"},
+    {file = "cryptography-46.0.5-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:8456928655f856c6e1533ff59d5be76578a7157224dbd9ce6872f25055ab9ab7"},
+    {file = "cryptography-46.0.5.tar.gz", hash = "sha256:abace499247268e3757271b2f1e244b36b06f8515cf27c4d49468fc9eb16e93d"},
 ]
 
 [package.dependencies]
@@ -516,7 +516,7 @@ nox = ["nox[uv] (>=2024.4.15)"]
 pep8test = ["check-sdist", "click (>=8.0.1)", "mypy (>=1.14)", "ruff (>=0.11.11)"]
 sdist = ["build (>=1.0.0)"]
 ssh = ["bcrypt (>=3.1.5)"]
-test = ["certifi (>=2024)", "cryptography-vectors (==46.0.4)", "pretend (>=0.7)", "pytest (>=7.4.0)", "pytest-benchmark (>=4.0)", "pytest-cov (>=2.10.1)", "pytest-xdist (>=3.5.0)"]
+test = ["certifi (>=2024)", "cryptography-vectors (==46.0.5)", "pretend (>=0.7)", "pytest (>=7.4.0)", "pytest-benchmark (>=4.0)", "pytest-cov (>=2.10.1)", "pytest-xdist (>=3.5.0)"]
 test-randomorder = ["pytest-randomly"]
 
 [[package]]
@@ -570,24 +570,25 @@ tests = ["coverage", "coveralls", "dill", "mock", "nose"]
 
 [[package]]
 name = "fastapi"
-version = "0.128.0"
+version = "0.128.7"
 description = "FastAPI framework, high performance, easy to learn, fast to code, ready for production"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "fastapi-0.128.0-py3-none-any.whl", hash = "sha256:aebd93f9716ee3b4f4fcfe13ffb7cf308d99c9f3ab5622d8877441072561582d"},
-    {file = "fastapi-0.128.0.tar.gz", hash = "sha256:1cc179e1cef10a6be60ffe429f79b829dce99d8de32d7acb7e6c8dfdf7f2645a"},
+    {file = "fastapi-0.128.7-py3-none-any.whl", hash = "sha256:6bd9bd31cb7047465f2d3fa3ba3f33b0870b17d4eaf7cdb36d1576ab060ad662"},
+    {file = "fastapi-0.128.7.tar.gz", hash = "sha256:783c273416995486c155ad2c0e2b45905dedfaf20b9ef8d9f6a9124670639a24"},
 ]
 
 [package.dependencies]
 annotated-doc = ">=0.0.2"
 pydantic = ">=2.7.0"
-starlette = ">=0.40.0,<0.51.0"
+starlette = ">=0.40.0,<1.0.0"
 typing-extensions = ">=4.8.0"
+typing-inspection = ">=0.4.2"
 
 [package.extras]
-all = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.8)", "httpx (>=0.23.0,<1.0.0)", "itsdangerous (>=1.1.0)", "jinja2 (>=3.1.5)", "orjson (>=3.2.1)", "pydantic-extra-types (>=2.0.0)", "pydantic-settings (>=2.0.0)", "python-multipart (>=0.0.18)", "pyyaml (>=5.3.1)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0)", "uvicorn[standard] (>=0.12.0)"]
+all = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.8)", "httpx (>=0.23.0,<1.0.0)", "itsdangerous (>=1.1.0)", "jinja2 (>=3.1.5)", "orjson (>=3.9.3)", "pydantic-extra-types (>=2.0.0)", "pydantic-settings (>=2.0.0)", "python-multipart (>=0.0.18)", "pyyaml (>=5.3.1)", "ujson (>=5.8.0)", "uvicorn[standard] (>=0.12.0)"]
 standard = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.8)", "httpx (>=0.23.0,<1.0.0)", "jinja2 (>=3.1.5)", "pydantic-extra-types (>=2.0.0)", "pydantic-settings (>=2.0.0)", "python-multipart (>=0.0.18)", "uvicorn[standard] (>=0.12.0)"]
 standard-no-fastapi-cloud-cli = ["email-validator (>=2.0.0)", "fastapi-cli[standard-no-fastapi-cloud-cli] (>=0.0.8)", "httpx (>=0.23.0,<1.0.0)", "jinja2 (>=3.1.5)", "pydantic-extra-types (>=2.0.0)", "pydantic-settings (>=2.0.0)", "python-multipart (>=0.0.18)", "uvicorn[standard] (>=0.12.0)"]
 
@@ -1062,14 +1063,14 @@ urllib3 = ">=1.26.0,<3"
 
 [[package]]
 name = "launchdarkly-server-sdk"
-version = "9.14.1"
+version = "9.15.0"
 description = "LaunchDarkly SDK for Python"
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.10"
 groups = ["main"]
 files = [
-    {file = "launchdarkly_server_sdk-9.14.1-py3-none-any.whl", hash = "sha256:a9e2bd9ecdef845cd631ae0d4334a1115e5b44257c42eb2349492be4bac7815c"},
-    {file = "launchdarkly_server_sdk-9.14.1.tar.gz", hash = "sha256:1df44baf0a0efa74d8c1dad7a00592b98bce7d19edded7f770da8dbc49922213"},
+    {file = "launchdarkly_server_sdk-9.15.0-py3-none-any.whl", hash = "sha256:c267e29bfa3fb5e2a06a208448ada6ed5557a2924979b8d79c970b45d227c668"},
+    {file = "launchdarkly_server_sdk-9.15.0.tar.gz", hash = "sha256:f31441b74bc1a69c381db57c33116509e407a2612628ad6dff0a7dbb39d5020b"},
 ]
 
 [package.dependencies]
@@ -1478,14 +1479,14 @@ testing = ["coverage", "pytest", "pytest-benchmark"]
 
 [[package]]
 name = "postgrest"
-version = "2.27.2"
+version = "2.28.0"
 description = "PostgREST client for Python. This library provides an ORM interface to PostgREST."
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "postgrest-2.27.2-py3-none-any.whl", hash = "sha256:1666fef3de05ca097a314433dd5ae2f2d71c613cb7b233d0f468c4ffe37277da"},
-    {file = "postgrest-2.27.2.tar.gz", hash = "sha256:55407d530b5af3d64e883a71fec1f345d369958f723ce4a8ab0b7d169e313242"},
+    {file = "postgrest-2.28.0-py3-none-any.whl", hash = "sha256:7bca2f24dd1a1bf8a3d586c7482aba6cd41662da6733045fad585b63b7f7df75"},
+    {file = "postgrest-2.28.0.tar.gz", hash = "sha256:c36b38646d25ea4255321d3d924ce70f8d20ec7799cb42c1221d6a818d4f6515"},
 ]
 
 [package.dependencies]
@@ -2248,14 +2249,14 @@ cli = ["click (>=5.0)"]
 
 [[package]]
 name = "realtime"
-version = "2.27.2"
+version = "2.28.0"
 description = ""
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "realtime-2.27.2-py3-none-any.whl", hash = "sha256:34a9cbb26a274e707e8fc9e3ee0a66de944beac0fe604dc336d1e985db2c830f"},
-    {file = "realtime-2.27.2.tar.gz", hash = "sha256:b960a90294d2cea1b3f1275ecb89204304728e08fff1c393cc1b3150739556b3"},
+    {file = "realtime-2.28.0-py3-none-any.whl", hash = "sha256:db1bd59bab9b1fcc9f9d3b1a073bed35bf4994d720e6751f10031a58d57a3836"},
+    {file = "realtime-2.28.0.tar.gz", hash = "sha256:d18cedcebd6a8f22fcd509bc767f639761eb218b7b2b6f14fc4205b6259b50fc"},
 ]
 
 [package.dependencies]
@@ -2436,14 +2437,14 @@ full = ["httpx (>=0.27.0,<0.29.0)", "itsdangerous", "jinja2", "python-multipart
 
 [[package]]
 name = "storage3"
-version = "2.27.2"
+version = "2.28.0"
 description = "Supabase Storage client for Python."
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "storage3-2.27.2-py3-none-any.whl", hash = "sha256:e6f16e7a260729e7b1f46e9bf61746805a02e30f5e419ee1291007c432e3ec63"},
-    {file = "storage3-2.27.2.tar.gz", hash = "sha256:cb4807b7f86b4bb1272ac6fdd2f3cfd8ba577297046fa5f88557425200275af5"},
+    {file = "storage3-2.28.0-py3-none-any.whl", hash = "sha256:ecb50efd2ac71dabbdf97e99ad346eafa630c4c627a8e5a138ceb5fbbadae716"},
+    {file = "storage3-2.28.0.tar.gz", hash = "sha256:bc1d008aff67de7a0f2bd867baee7aadbcdb6f78f5a310b4f7a38e8c13c19865"},
 ]
 
 [package.dependencies]
@@ -2487,35 +2488,35 @@ python-dateutil = ">=2.6.0"
 
 [[package]]
 name = "supabase"
-version = "2.27.2"
+version = "2.28.0"
 description = "Supabase client for Python."
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "supabase-2.27.2-py3-none-any.whl", hash = "sha256:d4dce00b3a418ee578017ec577c0e5be47a9a636355009c76f20ed2faa15bc54"},
-    {file = "supabase-2.27.2.tar.gz", hash = "sha256:2aed40e4f3454438822442a1e94a47be6694c2c70392e7ae99b51a226d4293f7"},
+    {file = "supabase-2.28.0-py3-none-any.whl", hash = "sha256:42776971c7d0ccca16034df1ab96a31c50228eb1eb19da4249ad2f756fc20272"},
+    {file = "supabase-2.28.0.tar.gz", hash = "sha256:aea299aaab2a2eed3c57e0be7fc035c6807214194cce795a3575add20268ece1"},
 ]
 
 [package.dependencies]
 httpx = ">=0.26,<0.29"
-postgrest = "2.27.2"
-realtime = "2.27.2"
-storage3 = "2.27.2"
-supabase-auth = "2.27.2"
-supabase-functions = "2.27.2"
+postgrest = "2.28.0"
+realtime = "2.28.0"
+storage3 = "2.28.0"
+supabase-auth = "2.28.0"
+supabase-functions = "2.28.0"
 yarl = ">=1.22.0"
 
 [[package]]
 name = "supabase-auth"
-version = "2.27.2"
+version = "2.28.0"
 description = "Python Client Library for Supabase Auth"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "supabase_auth-2.27.2-py3-none-any.whl", hash = "sha256:78ec25b11314d0a9527a7205f3b1c72560dccdc11b38392f80297ef98664ee91"},
-    {file = "supabase_auth-2.27.2.tar.gz", hash = "sha256:0f5bcc79b3677cb42e9d321f3c559070cfa40d6a29a67672cc8382fb7dc2fe97"},
+    {file = "supabase_auth-2.28.0-py3-none-any.whl", hash = "sha256:2ac85026cc285054c7fa6d41924f3a333e9ec298c013e5b5e1754039ba7caec9"},
+    {file = "supabase_auth-2.28.0.tar.gz", hash = "sha256:2bb8f18ff39934e44b28f10918db965659f3735cd6fbfcc022fe0b82dbf8233e"},
 ]
 
 [package.dependencies]
@@ -2525,14 +2526,14 @@ pyjwt = {version = ">=2.10.1", extras = ["crypto"]}
 
 [[package]]
 name = "supabase-functions"
-version = "2.27.2"
+version = "2.28.0"
 description = "Library for Supabase Functions"
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
 files = [
-    {file = "supabase_functions-2.27.2-py3-none-any.whl", hash = "sha256:db480efc669d0bca07605b9b6f167312af43121adcc842a111f79bea416ef754"},
-    {file = "supabase_functions-2.27.2.tar.gz", hash = "sha256:d0c8266207a94371cb3fd35ad3c7f025b78a97cf026861e04ccd35ac1775f80b"},
+    {file = "supabase_functions-2.28.0-py3-none-any.whl", hash = "sha256:30bf2d586f8df285faf0621bb5d5bb3ec3157234fc820553ca156f009475e4ae"},
+    {file = "supabase_functions-2.28.0.tar.gz", hash = "sha256:db3dddfc37aca5858819eb461130968473bd8c75bd284581013958526dac718b"},
 ]
 
 [package.dependencies]
@@ -2911,4 +2912,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<4.0"
-content-hash = "40eae94995dc0a388fa832ed4af9b6137f28d5b5ced3aaea70d5f91d4d9a179d"
+content-hash = "9619cae908ad38fa2c48016a58bcf4241f6f5793aa0e6cc140276e91c433cbbb"

autogpt_platform/autogpt_libs/pyproject.toml

@@ -11,14 +11,14 @@ python = ">=3.10,<4.0"
 colorama = "^0.4.6"
 cryptography = "^46.0"
 expiringdict = "^1.2.2"
-fastapi = "^0.128.0"
+fastapi = "^0.128.7"
 google-cloud-logging = "^3.13.0"
-launchdarkly-server-sdk = "^9.14.1"
+launchdarkly-server-sdk = "^9.15.0"
 pydantic = "^2.12.5"
 pydantic-settings = "^2.12.0"
 pyjwt = { version = "^2.11.0", extras = ["crypto"] }
 redis = "^6.2.0"
-supabase = "^2.27.2"
+supabase = "^2.28.0"
 uvicorn = "^0.40.0"
 
 [tool.poetry.group.dev.dependencies]

autogpt_platform/backend/.env.default

@@ -104,6 +104,12 @@ TWITTER_CLIENT_SECRET=
 # Make a new workspace for your OAuth APP -- trust me
 # https://linear.app/settings/api/applications/new
 # Callback URL: http://localhost:3000/auth/integrations/oauth_callback
+LINEAR_API_KEY=
+# Linear project and team IDs for the feature request tracker.
+# Find these in your Linear workspace URL: linear.app/<workspace>/project/<project-id>
+# and in team settings. Used by the chat copilot to file and search feature requests.
+LINEAR_FEATURE_REQUEST_PROJECT_ID=
+LINEAR_FEATURE_REQUEST_TEAM_ID=
 LINEAR_CLIENT_ID=
 LINEAR_CLIENT_SECRET=
 

autogpt_platform/backend/Dockerfile

@@ -1,3 +1,5 @@
+# ============================ DEPENDENCY BUILDER ============================ #
+
 FROM debian:13-slim AS builder
 
 # Set environment variables
@@ -51,27 +53,62 @@ COPY autogpt_platform/backend/backend/data/partial_types.py ./backend/data/parti
 COPY autogpt_platform/backend/gen_prisma_types_stub.py ./
 RUN poetry run prisma generate && poetry run gen-prisma-stub
 
-FROM debian:13-slim AS server_dependencies
+# =============================== DB MIGRATOR =============================== #
+
+# Lightweight migrate stage - only needs Prisma CLI, not full Python environment
+FROM debian:13-slim AS migrate
+
+WORKDIR /app/autogpt_platform/backend
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install only what's needed for prisma migrate: Node.js and minimal Python for prisma-python
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    python3.13 \
+    python3-pip \
+    ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy Node.js from builder (needed for Prisma CLI)
+COPY --from=builder /usr/bin/node /usr/bin/node
+COPY --from=builder /usr/lib/node_modules /usr/lib/node_modules
+COPY --from=builder /usr/bin/npm /usr/bin/npm
+
+# Copy Prisma binaries
+COPY --from=builder /root/.cache/prisma-python/binaries /root/.cache/prisma-python/binaries
+
+# Install prisma-client-py directly (much smaller than copying full venv)
+RUN pip3 install prisma>=0.15.0 --break-system-packages
+
+COPY autogpt_platform/backend/schema.prisma ./
+COPY autogpt_platform/backend/backend/data/partial_types.py ./backend/data/partial_types.py
+COPY autogpt_platform/backend/gen_prisma_types_stub.py ./
+COPY autogpt_platform/backend/migrations ./migrations
+
+# ============================== BACKEND SERVER ============================== #
+
+FROM debian:13-slim AS server
 
 WORKDIR /app
 
-ENV POETRY_HOME=/opt/poetry \
-    POETRY_NO_INTERACTION=1 \
-    POETRY_VIRTUALENVS_CREATE=true \
-    POETRY_VIRTUALENVS_IN_PROJECT=true \
-    DEBIAN_FRONTEND=noninteractive
-ENV PATH=/opt/poetry/bin:$PATH
+ENV DEBIAN_FRONTEND=noninteractive
 
-# Install Python, FFmpeg, and ImageMagick (required for video processing blocks)
-RUN apt-get update && apt-get install -y \
+# Install Python, FFmpeg, ImageMagick, and CLI tools for agent use.
+# bubblewrap provides OS-level sandbox (whitelist-only FS + no network)
+# for the bash_exec MCP tool.
+# Using --no-install-recommends saves ~650MB by skipping unnecessary deps like llvm, mesa, etc.
+RUN apt-get update && apt-get install -y --no-install-recommends \
     python3.13 \
     python3-pip \
     ffmpeg \
     imagemagick \
+    jq \
+    ripgrep \
+    tree \
+    bubblewrap \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy only necessary files from builder
-COPY --from=builder /app /app
+# Copy poetry (build-time only, for `poetry install --only-root` to create entry points)
 COPY --from=builder /usr/local/lib/python3* /usr/local/lib/python3*
 COPY --from=builder /usr/local/bin/poetry /usr/local/bin/poetry
 # Copy Node.js installation for Prisma
@@ -81,30 +118,25 @@ COPY --from=builder /usr/bin/npm /usr/bin/npm
 COPY --from=builder /usr/bin/npx /usr/bin/npx
 COPY --from=builder /root/.cache/prisma-python/binaries /root/.cache/prisma-python/binaries
 
-ENV PATH="/app/autogpt_platform/backend/.venv/bin:$PATH"
-
-RUN mkdir -p /app/autogpt_platform/autogpt_libs
-RUN mkdir -p /app/autogpt_platform/backend
-
-COPY autogpt_platform/autogpt_libs /app/autogpt_platform/autogpt_libs
-
-COPY autogpt_platform/backend/poetry.lock autogpt_platform/backend/pyproject.toml /app/autogpt_platform/backend/
-
 WORKDIR /app/autogpt_platform/backend
 
-FROM server_dependencies AS migrate
+# Copy only the .venv from builder (not the entire /app directory)
+# The .venv includes the generated Prisma client
+COPY --from=builder /app/autogpt_platform/backend/.venv ./.venv
+ENV PATH="/app/autogpt_platform/backend/.venv/bin:$PATH"
 
-# Migration stage only needs schema and migrations - much lighter than full backend
-COPY autogpt_platform/backend/schema.prisma /app/autogpt_platform/backend/
-COPY autogpt_platform/backend/backend/data/partial_types.py /app/autogpt_platform/backend/backend/data/partial_types.py
-COPY autogpt_platform/backend/migrations /app/autogpt_platform/backend/migrations
+# Copy dependency files + autogpt_libs (path dependency)
+COPY autogpt_platform/autogpt_libs /app/autogpt_platform/autogpt_libs
+COPY autogpt_platform/backend/poetry.lock autogpt_platform/backend/pyproject.toml ./
 
-FROM server_dependencies AS server
-
-COPY autogpt_platform/backend /app/autogpt_platform/backend
+# Copy backend code + docs (for Copilot docs search)
+COPY autogpt_platform/backend ./
 COPY docs /app/docs
-RUN poetry install --no-ansi --only-root
+# Install the project package to create entry point scripts in .venv/bin/
+# (e.g., rest, executor, ws, db, scheduler, notification - see [tool.poetry.scripts])
+RUN POETRY_VIRTUALENVS_CREATE=true POETRY_VIRTUALENVS_IN_PROJECT=true \
+    poetry install --no-ansi --only-root
 
 ENV PORT=8000
 
-CMD ["poetry", "run", "rest"]
+CMD ["rest"]

autogpt_platform/backend/backend/api/conftest.py

@@ -1,4 +1,9 @@
-"""Common test fixtures for server tests."""
+"""Common test fixtures for server tests.
+
+Note: Common fixtures like test_user_id, admin_user_id, target_user_id,
+setup_test_user, and setup_admin_user are defined in the parent conftest.py
+(backend/conftest.py) and are available here automatically.
+"""
 
 import pytest
 from pytest_snapshot.plugin import Snapshot
@@ -11,54 +16,6 @@ def configured_snapshot(snapshot: Snapshot) -> Snapshot:
     return snapshot
 
 
-@pytest.fixture
-def test_user_id() -> str:
-    """Test user ID fixture."""
-    return "3e53486c-cf57-477e-ba2a-cb02dc828e1a"
-
-
-@pytest.fixture
-def admin_user_id() -> str:
-    """Admin user ID fixture."""
-    return "4e53486c-cf57-477e-ba2a-cb02dc828e1b"
-
-
-@pytest.fixture
-def target_user_id() -> str:
-    """Target user ID fixture."""
-    return "5e53486c-cf57-477e-ba2a-cb02dc828e1c"
-
-
-@pytest.fixture
-async def setup_test_user(test_user_id):
-    """Create test user in database before tests."""
-    from backend.data.user import get_or_create_user
-
-    # Create the test user in the database using JWT token format
-    user_data = {
-        "sub": test_user_id,
-        "email": "test@example.com",
-        "user_metadata": {"name": "Test User"},
-    }
-    await get_or_create_user(user_data)
-    return test_user_id
-
-
-@pytest.fixture
-async def setup_admin_user(admin_user_id):
-    """Create admin user in database before tests."""
-    from backend.data.user import get_or_create_user
-
-    # Create the admin user in the database using JWT token format
-    user_data = {
-        "sub": admin_user_id,
-        "email": "test-admin@example.com",
-        "user_metadata": {"name": "Test Admin"},
-    }
-    await get_or_create_user(user_data)
-    return admin_user_id
-
-
 @pytest.fixture
 def mock_jwt_user(test_user_id):
     """Provide mock JWT payload for regular user testing."""

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

@@ -10,7 +10,7 @@ from typing_extensions import TypedDict
 
 import backend.api.features.store.cache as store_cache
 import backend.api.features.store.model as store_model
-import backend.data.block
+import backend.blocks
 from backend.api.external.middleware import require_permission
 from backend.data import execution as execution_db
 from backend.data import graph as graph_db
@@ -67,7 +67,7 @@ async def get_user_info(
     dependencies=[Security(require_permission(APIKeyPermission.READ_BLOCK))],
 )
 async def get_graph_blocks() -> Sequence[dict[Any, Any]]:
-    blocks = [block() for block in backend.data.block.get_blocks().values()]
+    blocks = [block() for block in backend.blocks.get_blocks().values()]
     return [b.to_dict() for b in blocks if not b.disabled]
 
 
@@ -83,7 +83,7 @@ async def execute_graph_block(
         require_permission(APIKeyPermission.EXECUTE_BLOCK)
     ),
 ) -> CompletedBlockOutput:
-    obj = backend.data.block.get_block(block_id)
+    obj = backend.blocks.get_block(block_id)
     if not obj:
         raise HTTPException(status_code=404, detail=f"Block #{block_id} not found.")
     if obj.disabled:

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

@@ -15,9 +15,9 @@ from prisma.enums import APIKeyPermission
 from pydantic import BaseModel, Field
 
 from backend.api.external.middleware import require_permission
-from backend.api.features.chat.model import ChatSession
-from backend.api.features.chat.tools import find_agent_tool, run_agent_tool
-from backend.api.features.chat.tools.models import ToolResponseBase
+from backend.copilot.model import ChatSession
+from backend.copilot.tools import find_agent_tool, run_agent_tool
+from backend.copilot.tools.models import ToolResponseBase
 from backend.data.auth.base import APIAuthorizationInfo
 
 logger = logging.getLogger(__name__)

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

@@ -10,10 +10,15 @@ import backend.api.features.library.db as library_db
 import backend.api.features.library.model as library_model
 import backend.api.features.store.db as store_db
 import backend.api.features.store.model as store_model
-import backend.data.block
 from backend.blocks import load_all_blocks
+from backend.blocks._base import (
+    AnyBlockSchema,
+    BlockCategory,
+    BlockInfo,
+    BlockSchema,
+    BlockType,
+)
 from backend.blocks.llm import LlmModel
-from backend.data.block import AnyBlockSchema, BlockCategory, BlockInfo, BlockSchema
 from backend.data.db import query_raw_with_schema
 from backend.integrations.providers import ProviderName
 from backend.util.cache import cached
@@ -22,7 +27,7 @@ from backend.util.models import Pagination
 from .model import (
     BlockCategoryResponse,
     BlockResponse,
-    BlockType,
+    BlockTypeFilter,
     CountResponse,
     FilterType,
     Provider,
@@ -88,7 +93,7 @@ def get_block_categories(category_blocks: int = 3) -> list[BlockCategoryResponse
 def get_blocks(
     *,
     category: str | None = None,
-    type: BlockType | None = None,
+    type: BlockTypeFilter | None = None,
     provider: ProviderName | None = None,
     page: int = 1,
     page_size: int = 50,
@@ -669,9 +674,9 @@ async def get_suggested_blocks(count: int = 5) -> list[BlockInfo]:
     for block_type in load_all_blocks().values():
         block: AnyBlockSchema = block_type()
         if block.disabled or block.block_type in (
-            backend.data.block.BlockType.INPUT,
-            backend.data.block.BlockType.OUTPUT,
-            backend.data.block.BlockType.AGENT,
+            BlockType.INPUT,
+            BlockType.OUTPUT,
+            BlockType.AGENT,
         ):
             continue
         # Find the execution count for this block

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

@@ -4,7 +4,7 @@ from pydantic import BaseModel
 
 import backend.api.features.library.model as library_model
 import backend.api.features.store.model as store_model
-from backend.data.block import BlockInfo
+from backend.blocks._base import BlockInfo
 from backend.integrations.providers import ProviderName
 from backend.util.models import Pagination
 
@@ -15,7 +15,7 @@ FilterType = Literal[
     "my_agents",
 ]
 
-BlockType = Literal["all", "input", "action", "output"]
+BlockTypeFilter = Literal["all", "input", "action", "output"]
 
 
 class SearchEntry(BaseModel):

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

@@ -88,7 +88,7 @@ async def get_block_categories(
 )
 async def get_blocks(
     category: Annotated[str | None, fastapi.Query()] = None,
-    type: Annotated[builder_model.BlockType | None, fastapi.Query()] = None,
+    type: Annotated[builder_model.BlockTypeFilter | None, fastapi.Query()] = None,
     provider: Annotated[ProviderName | None, fastapi.Query()] = None,
     page: Annotated[int, fastapi.Query()] = 1,
     page_size: Annotated[int, fastapi.Query()] = 50,

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

@@ -1,119 +0,0 @@
-import pytest
-
-from .model import (
-    ChatMessage,
-    ChatSession,
-    Usage,
-    get_chat_session,
-    upsert_chat_session,
-)
-
-messages = [
-    ChatMessage(content="Hello, how are you?", role="user"),
-    ChatMessage(
-        content="I'm fine, thank you!",
-        role="assistant",
-        tool_calls=[
-            {
-                "id": "t123",
-                "type": "function",
-                "function": {
-                    "name": "get_weather",
-                    "arguments": '{"city": "New York"}',
-                },
-            }
-        ],
-    ),
-    ChatMessage(
-        content="I'm using the tool to get the weather",
-        role="tool",
-        tool_call_id="t123",
-    ),
-]
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_chatsession_serialization_deserialization():
-    s = ChatSession.new(user_id="abc123")
-    s.messages = messages
-    s.usage = [Usage(prompt_tokens=100, completion_tokens=200, total_tokens=300)]
-    serialized = s.model_dump_json()
-    s2 = ChatSession.model_validate_json(serialized)
-    assert s2.model_dump() == s.model_dump()
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_chatsession_redis_storage(setup_test_user, test_user_id):
-
-    s = ChatSession.new(user_id=test_user_id)
-    s.messages = messages
-
-    s = await upsert_chat_session(s)
-
-    s2 = await get_chat_session(
-        session_id=s.session_id,
-        user_id=s.user_id,
-    )
-
-    assert s2 == s
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_chatsession_redis_storage_user_id_mismatch(
-    setup_test_user, test_user_id
-):
-
-    s = ChatSession.new(user_id=test_user_id)
-    s.messages = messages
-    s = await upsert_chat_session(s)
-
-    s2 = await get_chat_session(s.session_id, "different_user_id")
-
-    assert s2 is None
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_chatsession_db_storage(setup_test_user, test_user_id):
-    """Test that messages are correctly saved to and loaded from DB (not cache)."""
-    from backend.data.redis_client import get_redis_async
-
-    # Create session with messages including assistant message
-    s = ChatSession.new(user_id=test_user_id)
-    s.messages = messages  # Contains user, assistant, and tool messages
-    assert s.session_id is not None, "Session id is not set"
-    # Upsert to save to both cache and DB
-    s = await upsert_chat_session(s)
-
-    # Clear the Redis cache to force DB load
-    redis_key = f"chat:session:{s.session_id}"
-    async_redis = await get_redis_async()
-    await async_redis.delete(redis_key)
-
-    # Load from DB (cache was cleared)
-    s2 = await get_chat_session(
-        session_id=s.session_id,
-        user_id=s.user_id,
-    )
-
-    assert s2 is not None, "Session not found after loading from DB"
-    assert len(s2.messages) == len(
-        s.messages
-    ), f"Message count mismatch: expected {len(s.messages)}, got {len(s2.messages)}"
-
-    # Verify all roles are present
-    roles = [m.role for m in s2.messages]
-    assert "user" in roles, f"User message missing. Roles found: {roles}"
-    assert "assistant" in roles, f"Assistant message missing. Roles found: {roles}"
-    assert "tool" in roles, f"Tool message missing. Roles found: {roles}"
-
-    # Verify message content
-    for orig, loaded in zip(s.messages, s2.messages):
-        assert orig.role == loaded.role, f"Role mismatch: {orig.role} != {loaded.role}"
-        assert (
-            orig.content == loaded.content
-        ), f"Content mismatch for {orig.role}: {orig.content} != {loaded.content}"
-        if orig.tool_calls:
-            assert (
-                loaded.tool_calls is not None
-            ), f"Tool calls missing for {orig.role} message"
-            assert len(orig.tool_calls) == len(loaded.tool_calls)

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

@@ -1,5 +1,6 @@
 """Chat API routes for chat session management and streaming via SSE."""
 
+import asyncio
 import logging
 import uuid as uuid_module
 from collections.abc import AsyncGenerator
@@ -10,20 +11,31 @@ from fastapi import APIRouter, Depends, Header, HTTPException, Query, Response,
 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 .completion_handler import process_operation_failure, process_operation_success
-from .config import ChatConfig
-from .model import ChatSession, create_chat_session, get_chat_session, get_user_sessions
-from .response_model import StreamFinish, StreamHeartbeat
-from .tools.models import (
+from backend.copilot import service as chat_service
+from backend.copilot import stream_registry
+from backend.copilot.completion_handler import (
+    process_operation_failure,
+    process_operation_success,
+)
+from backend.copilot.config import ChatConfig
+from backend.copilot.executor.utils import enqueue_copilot_task
+from backend.copilot.model import (
+    ChatMessage,
+    ChatSession,
+    append_and_save_message,
+    create_chat_session,
+    delete_chat_session,
+    get_chat_session,
+    get_user_sessions,
+)
+from backend.copilot.response_model import StreamError, StreamFinish, StreamHeartbeat
+from backend.copilot.tools.models import (
     AgentDetailsResponse,
     AgentOutputResponse,
     AgentPreviewResponse,
     AgentSavedResponse,
     AgentsFoundResponse,
+    BlockDetailsResponse,
     BlockListResponse,
     BlockOutputResponse,
     ClarificationNeededResponse,
@@ -40,6 +52,8 @@ from .tools.models import (
     SetupRequirementsResponse,
     UnderstandingUpdatedResponse,
 )
+from backend.copilot.tracking import track_user_message
+from backend.util.exceptions import NotFoundError
 
 config = ChatConfig()
 
@@ -199,6 +213,43 @@ async def create_session(
     )
 
 
+@router.delete(
+    "/sessions/{session_id}",
+    dependencies=[Security(auth.requires_user)],
+    status_code=204,
+    responses={404: {"description": "Session not found or access denied"}},
+)
+async def delete_session(
+    session_id: str,
+    user_id: Annotated[str, Security(auth.get_user_id)],
+) -> Response:
+    """
+    Delete a chat session.
+
+    Permanently removes a chat session and all its messages.
+    Only the owner can delete their sessions.
+
+    Args:
+        session_id: The session ID to delete.
+        user_id: The authenticated user's ID.
+
+    Returns:
+        204 No Content on success.
+
+    Raises:
+        HTTPException: 404 if session not found or not owned by user.
+    """
+    deleted = await delete_chat_session(session_id, user_id)
+
+    if not deleted:
+        raise HTTPException(
+            status_code=404,
+            detail=f"Session {session_id} not found or access denied",
+        )
+
+    return Response(status_code=204)
+
+
 @router.get(
     "/sessions/{session_id}",
 )
@@ -231,6 +282,10 @@ async def get_session(
     active_task, last_message_id = await stream_registry.get_active_task_for_session(
         session_id, user_id
     )
+    logger.info(
+        f"[GET_SESSION] session={session_id}, active_task={active_task is not None}, "
+        f"msg_count={len(messages)}, last_role={messages[-1].get('role') if messages else 'none'}"
+    )
     if active_task:
         # Filter out the in-progress assistant message from the session response.
         # The client will receive the complete assistant response through the SSE
@@ -300,10 +355,9 @@ async def stream_chat_post(
         f"user={user_id}, message_len={len(request.message)}",
         extra={"json_fields": log_meta},
     )
-
-    session = await _validate_and_get_session(session_id, user_id)
+    await _validate_and_get_session(session_id, user_id)
     logger.info(
-        f"[TIMING] session validated in {(time.perf_counter() - stream_start_time)*1000:.1f}ms",
+        f"[TIMING] session validated in {(time.perf_counter() - stream_start_time) * 1000:.1f}ms",
         extra={
             "json_fields": {
                 **log_meta,
@@ -312,6 +366,25 @@ async def stream_chat_post(
         },
     )
 
+    # Atomically append user message to session BEFORE creating task to avoid
+    # race condition where GET_SESSION sees task as "running" but message isn't
+    # saved yet.  append_and_save_message re-fetches inside a lock to prevent
+    # message loss from concurrent requests.
+    if request.message:
+        message = ChatMessage(
+            role="user" if request.is_user_message else "assistant",
+            content=request.message,
+        )
+        if request.is_user_message:
+            track_user_message(
+                user_id=user_id,
+                session_id=session_id,
+                message_length=len(request.message),
+            )
+        logger.info(f"[STREAM] Saving user message to session {session_id}")
+        await append_and_save_message(session_id, message)
+        logger.info(f"[STREAM] User message saved for session {session_id}")
+
     # Create a task in the stream registry for reconnection support
     task_id = str(uuid_module.uuid4())
     operation_id = str(uuid_module.uuid4())
@@ -327,7 +400,7 @@ async def stream_chat_post(
         operation_id=operation_id,
     )
     logger.info(
-        f"[TIMING] create_task completed in {(time.perf_counter() - task_create_start)*1000:.1f}ms",
+        f"[TIMING] create_task completed in {(time.perf_counter() - task_create_start) * 1000:.1f}ms",
         extra={
             "json_fields": {
                 **log_meta,
@@ -336,82 +409,19 @@ async def stream_chat_post(
         },
     )
 
-    # Background task that runs the AI generation independently of SSE connection
-    async def run_ai_generation():
-        import time as time_module
+    await enqueue_copilot_task(
+        task_id=task_id,
+        session_id=session_id,
+        user_id=user_id,
+        operation_id=operation_id,
+        message=request.message,
+        is_user_message=request.is_user_message,
+        context=request.context,
+    )
 
-        gen_start_time = time_module.perf_counter()
-        logger.info(
-            f"[TIMING] run_ai_generation STARTED, task={task_id}, session={session_id}, user={user_id}",
-            extra={"json_fields": log_meta},
-        )
-        first_chunk_time, ttfc = None, None
-        chunk_count = 0
-        try:
-            async for chunk in chat_service.stream_chat_completion(
-                session_id,
-                request.message,
-                is_user_message=request.is_user_message,
-                user_id=user_id,
-                session=session,  # Pass pre-fetched session to avoid double-fetch
-                context=request.context,
-                _task_id=task_id,  # Pass task_id so service emits start with taskId for reconnection
-            ):
-                chunk_count += 1
-                if first_chunk_time is None:
-                    first_chunk_time = time_module.perf_counter()
-                    ttfc = first_chunk_time - gen_start_time
-                    logger.info(
-                        f"[TIMING] FIRST AI CHUNK at {ttfc:.2f}s, type={type(chunk).__name__}",
-                        extra={
-                            "json_fields": {
-                                **log_meta,
-                                "chunk_type": type(chunk).__name__,
-                                "time_to_first_chunk_ms": ttfc * 1000,
-                            }
-                        },
-                    )
-                # Write to Redis (subscribers will receive via XREAD)
-                await stream_registry.publish_chunk(task_id, chunk)
-
-            gen_end_time = time_module.perf_counter()
-            total_time = (gen_end_time - gen_start_time) * 1000
-            logger.info(
-                f"[TIMING] run_ai_generation FINISHED in {total_time/1000:.1f}s; "
-                f"task={task_id}, session={session_id}, "
-                f"ttfc={ttfc or -1:.2f}s, n_chunks={chunk_count}",
-                extra={
-                    "json_fields": {
-                        **log_meta,
-                        "total_time_ms": total_time,
-                        "time_to_first_chunk_ms": (
-                            ttfc * 1000 if ttfc is not None else None
-                        ),
-                        "n_chunks": chunk_count,
-                    }
-                },
-            )
-            await stream_registry.mark_task_completed(task_id, "completed")
-        except Exception as e:
-            elapsed = time_module.perf_counter() - gen_start_time
-            logger.error(
-                f"[TIMING] run_ai_generation ERROR after {elapsed:.2f}s: {e}",
-                extra={
-                    "json_fields": {
-                        **log_meta,
-                        "elapsed_ms": elapsed * 1000,
-                        "error": str(e),
-                    }
-                },
-            )
-            await stream_registry.mark_task_completed(task_id, "failed")
-
-    # Start the AI generation in a background task
-    bg_task = asyncio.create_task(run_ai_generation())
-    await stream_registry.set_task_asyncio_task(task_id, bg_task)
     setup_time = (time.perf_counter() - stream_start_time) * 1000
     logger.info(
-        f"[TIMING] Background task started, setup={setup_time:.1f}ms",
+        f"[TIMING] Task enqueued to RabbitMQ, setup={setup_time:.1f}ms",
         extra={"json_fields": {**log_meta, "setup_time_ms": setup_time}},
     )
 
@@ -506,8 +516,14 @@ async def stream_chat_post(
                     "json_fields": {**log_meta, "elapsed_ms": elapsed, "error": str(e)}
                 },
             )
+            # Surface error to frontend so it doesn't appear stuck
+            yield StreamError(
+                errorText="An error occurred. Please try again.",
+                code="stream_error",
+            ).to_sse()
+            yield StreamFinish().to_sse()
         finally:
-            # Unsubscribe when client disconnects or stream ends to prevent resource leak
+            # Unsubscribe when client disconnects or stream ends
             if subscriber_queue is not None:
                 try:
                     await stream_registry.unsubscribe_from_task(
@@ -751,8 +767,6 @@ async def stream_task(
         )
 
     async def event_generator() -> AsyncGenerator[str, None]:
-        import asyncio
-
         heartbeat_interval = 15.0  # Send heartbeat every 15 seconds
         try:
             while True:
@@ -971,6 +985,7 @@ ToolResponseUnion = (
     | AgentSavedResponse
     | ClarificationNeededResponse
     | BlockListResponse
+    | BlockDetailsResponse
     | BlockOutputResponse
     | DocSearchResultsResponse
     | DocPageResponse

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

@@ -1,82 +0,0 @@
-import logging
-from os import getenv
-
-import pytest
-
-from . import service as chat_service
-from .model import create_chat_session, get_chat_session, upsert_chat_session
-from .response_model import (
-    StreamError,
-    StreamFinish,
-    StreamTextDelta,
-    StreamToolOutputAvailable,
-)
-
-logger = logging.getLogger(__name__)
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_stream_chat_completion(setup_test_user, test_user_id):
-    """
-    Test the stream_chat_completion function.
-    """
-    api_key: str | None = getenv("OPEN_ROUTER_API_KEY")
-    if not api_key:
-        return pytest.skip("OPEN_ROUTER_API_KEY is not set, skipping test")
-
-    session = await create_chat_session(test_user_id)
-
-    has_errors = False
-    has_ended = False
-    assistant_message = ""
-    async for chunk in chat_service.stream_chat_completion(
-        session.session_id, "Hello, how are you?", user_id=session.user_id
-    ):
-        logger.info(chunk)
-        if isinstance(chunk, StreamError):
-            has_errors = True
-        if isinstance(chunk, StreamTextDelta):
-            assistant_message += chunk.delta
-        if isinstance(chunk, StreamFinish):
-            has_ended = True
-
-    assert has_ended, "Chat completion did not end"
-    assert not has_errors, "Error occurred while streaming chat completion"
-    assert assistant_message, "Assistant message is empty"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_stream_chat_completion_with_tool_calls(setup_test_user, test_user_id):
-    """
-    Test the stream_chat_completion function.
-    """
-    api_key: str | None = getenv("OPEN_ROUTER_API_KEY")
-    if not api_key:
-        return pytest.skip("OPEN_ROUTER_API_KEY is not set, skipping test")
-
-    session = await create_chat_session(test_user_id)
-    session = await upsert_chat_session(session)
-
-    has_errors = False
-    has_ended = False
-    had_tool_calls = False
-    async for chunk in chat_service.stream_chat_completion(
-        session.session_id,
-        "Please find me an agent that can help me with my business. Use the query 'moneny printing agent'",
-        user_id=session.user_id,
-    ):
-        logger.info(chunk)
-        if isinstance(chunk, StreamError):
-            has_errors = True
-
-        if isinstance(chunk, StreamFinish):
-            has_ended = True
-        if isinstance(chunk, StreamToolOutputAvailable):
-            had_tool_calls = True
-
-    assert has_ended, "Chat completion did not end"
-    assert not has_errors, "Error occurred while streaming chat completion"
-    assert had_tool_calls, "Tool calls did not occur"
-    session = await get_chat_session(session.session_id)
-    assert session, "Session not found"
-    assert session.usage, "Usage is empty"

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

@@ -1,139 +0,0 @@
-"""Tests for block filtering in FindBlockTool."""
-
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-from backend.api.features.chat.tools.find_block import (
-    COPILOT_EXCLUDED_BLOCK_IDS,
-    COPILOT_EXCLUDED_BLOCK_TYPES,
-    FindBlockTool,
-)
-from backend.api.features.chat.tools.models import BlockListResponse
-from backend.data.block import BlockType
-
-from ._test_data import make_session
-
-_TEST_USER_ID = "test-user-find-block"
-
-
-def make_mock_block(
-    block_id: str, name: str, block_type: BlockType, disabled: bool = False
-):
-    """Create a mock block for testing."""
-    mock = MagicMock()
-    mock.id = block_id
-    mock.name = name
-    mock.description = f"{name} description"
-    mock.block_type = block_type
-    mock.disabled = disabled
-    mock.input_schema = MagicMock()
-    mock.input_schema.jsonschema.return_value = {"properties": {}, "required": []}
-    mock.input_schema.get_credentials_fields.return_value = {}
-    mock.output_schema = MagicMock()
-    mock.output_schema.jsonschema.return_value = {}
-    mock.categories = []
-    return mock
-
-
-class TestFindBlockFiltering:
-    """Tests for block filtering in FindBlockTool."""
-
-    def test_excluded_block_types_contains_expected_types(self):
-        """Verify COPILOT_EXCLUDED_BLOCK_TYPES contains all graph-only types."""
-        assert BlockType.INPUT in COPILOT_EXCLUDED_BLOCK_TYPES
-        assert BlockType.OUTPUT in COPILOT_EXCLUDED_BLOCK_TYPES
-        assert BlockType.WEBHOOK in COPILOT_EXCLUDED_BLOCK_TYPES
-        assert BlockType.WEBHOOK_MANUAL in COPILOT_EXCLUDED_BLOCK_TYPES
-        assert BlockType.NOTE in COPILOT_EXCLUDED_BLOCK_TYPES
-        assert BlockType.HUMAN_IN_THE_LOOP in COPILOT_EXCLUDED_BLOCK_TYPES
-        assert BlockType.AGENT in COPILOT_EXCLUDED_BLOCK_TYPES
-
-    def test_excluded_block_ids_contains_smart_decision_maker(self):
-        """Verify SmartDecisionMakerBlock is in COPILOT_EXCLUDED_BLOCK_IDS."""
-        assert "3b191d9f-356f-482d-8238-ba04b6d18381" in COPILOT_EXCLUDED_BLOCK_IDS
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_excluded_block_type_filtered_from_results(self):
-        """Verify blocks with excluded BlockTypes are filtered from search results."""
-        session = make_session(user_id=_TEST_USER_ID)
-
-        # Mock search returns an INPUT block (excluded) and a STANDARD block (included)
-        search_results = [
-            {"content_id": "input-block-id", "score": 0.9},
-            {"content_id": "standard-block-id", "score": 0.8},
-        ]
-
-        input_block = make_mock_block("input-block-id", "Input Block", BlockType.INPUT)
-        standard_block = make_mock_block(
-            "standard-block-id", "HTTP Request", BlockType.STANDARD
-        )
-
-        def mock_get_block(block_id):
-            return {
-                "input-block-id": input_block,
-                "standard-block-id": standard_block,
-            }.get(block_id)
-
-        with patch(
-            "backend.api.features.chat.tools.find_block.unified_hybrid_search",
-            new_callable=AsyncMock,
-            return_value=(search_results, 2),
-        ):
-            with patch(
-                "backend.api.features.chat.tools.find_block.get_block",
-                side_effect=mock_get_block,
-            ):
-                tool = FindBlockTool()
-                response = await tool._execute(
-                    user_id=_TEST_USER_ID, session=session, query="test"
-                )
-
-        # Should only return the standard block, not the INPUT block
-        assert isinstance(response, BlockListResponse)
-        assert len(response.blocks) == 1
-        assert response.blocks[0].id == "standard-block-id"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_excluded_block_id_filtered_from_results(self):
-        """Verify SmartDecisionMakerBlock is filtered from search results."""
-        session = make_session(user_id=_TEST_USER_ID)
-
-        smart_decision_id = "3b191d9f-356f-482d-8238-ba04b6d18381"
-        search_results = [
-            {"content_id": smart_decision_id, "score": 0.9},
-            {"content_id": "normal-block-id", "score": 0.8},
-        ]
-
-        # SmartDecisionMakerBlock has STANDARD type but is excluded by ID
-        smart_block = make_mock_block(
-            smart_decision_id, "Smart Decision Maker", BlockType.STANDARD
-        )
-        normal_block = make_mock_block(
-            "normal-block-id", "Normal Block", BlockType.STANDARD
-        )
-
-        def mock_get_block(block_id):
-            return {
-                smart_decision_id: smart_block,
-                "normal-block-id": normal_block,
-            }.get(block_id)
-
-        with patch(
-            "backend.api.features.chat.tools.find_block.unified_hybrid_search",
-            new_callable=AsyncMock,
-            return_value=(search_results, 2),
-        ):
-            with patch(
-                "backend.api.features.chat.tools.find_block.get_block",
-                side_effect=mock_get_block,
-            ):
-                tool = FindBlockTool()
-                response = await tool._execute(
-                    user_id=_TEST_USER_ID, session=session, query="decision"
-                )
-
-        # Should only return normal block, not SmartDecisionMakerBlock
-        assert isinstance(response, BlockListResponse)
-        assert len(response.blocks) == 1
-        assert response.blocks[0].id == "normal-block-id"

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

@@ -1,106 +0,0 @@
-"""Tests for block execution guards in RunBlockTool."""
-
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from backend.api.features.chat.tools.models import ErrorResponse
-from backend.api.features.chat.tools.run_block import RunBlockTool
-from backend.data.block import BlockType
-
-from ._test_data import make_session
-
-_TEST_USER_ID = "test-user-run-block"
-
-
-def make_mock_block(
-    block_id: str, name: str, block_type: BlockType, disabled: bool = False
-):
-    """Create a mock block for testing."""
-    mock = MagicMock()
-    mock.id = block_id
-    mock.name = name
-    mock.block_type = block_type
-    mock.disabled = disabled
-    mock.input_schema = MagicMock()
-    mock.input_schema.jsonschema.return_value = {"properties": {}, "required": []}
-    mock.input_schema.get_credentials_fields_info.return_value = []
-    return mock
-
-
-class TestRunBlockFiltering:
-    """Tests for block execution guards in RunBlockTool."""
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_excluded_block_type_returns_error(self):
-        """Attempting to execute a block with excluded BlockType returns error."""
-        session = make_session(user_id=_TEST_USER_ID)
-
-        input_block = make_mock_block("input-block-id", "Input Block", BlockType.INPUT)
-
-        with patch(
-            "backend.api.features.chat.tools.run_block.get_block",
-            return_value=input_block,
-        ):
-            tool = RunBlockTool()
-            response = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                block_id="input-block-id",
-                input_data={},
-            )
-
-        assert isinstance(response, ErrorResponse)
-        assert "cannot be run directly in CoPilot" in response.message
-        assert "designed for use within graphs only" in response.message
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_excluded_block_id_returns_error(self):
-        """Attempting to execute SmartDecisionMakerBlock returns error."""
-        session = make_session(user_id=_TEST_USER_ID)
-
-        smart_decision_id = "3b191d9f-356f-482d-8238-ba04b6d18381"
-        smart_block = make_mock_block(
-            smart_decision_id, "Smart Decision Maker", BlockType.STANDARD
-        )
-
-        with patch(
-            "backend.api.features.chat.tools.run_block.get_block",
-            return_value=smart_block,
-        ):
-            tool = RunBlockTool()
-            response = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                block_id=smart_decision_id,
-                input_data={},
-            )
-
-        assert isinstance(response, ErrorResponse)
-        assert "cannot be run directly in CoPilot" in response.message
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_non_excluded_block_passes_guard(self):
-        """Non-excluded blocks pass the filtering guard (may fail later for other reasons)."""
-        session = make_session(user_id=_TEST_USER_ID)
-
-        standard_block = make_mock_block(
-            "standard-id", "HTTP Request", BlockType.STANDARD
-        )
-
-        with patch(
-            "backend.api.features.chat.tools.run_block.get_block",
-            return_value=standard_block,
-        ):
-            tool = RunBlockTool()
-            response = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                block_id="standard-id",
-                input_data={},
-            )
-
-        # Should NOT be an ErrorResponse about CoPilot exclusion
-        # (may be other errors like missing credentials, but not the exclusion guard)
-        if isinstance(response, ErrorResponse):
-            assert "cannot be run directly in CoPilot" not in response.message

autogpt_platform/backend/backend/api/features/integrations/router.py

@@ -1,7 +1,7 @@
 import asyncio
 import logging
 from datetime import datetime, timedelta, timezone
-from typing import TYPE_CHECKING, Annotated, List, Literal
+from typing import TYPE_CHECKING, Annotated, Any, List, Literal
 
 from autogpt_libs.auth import get_user_id
 from fastapi import (
@@ -14,7 +14,7 @@ from fastapi import (
     Security,
     status,
 )
-from pydantic import BaseModel, Field, SecretStr
+from pydantic import BaseModel, Field, SecretStr, model_validator
 from starlette.status import HTTP_500_INTERNAL_SERVER_ERROR, HTTP_502_BAD_GATEWAY
 
 from backend.api.features.library.db import set_preset_webhook, update_preset
@@ -39,7 +39,11 @@ from backend.data.onboarding import OnboardingStep, complete_onboarding_step
 from backend.data.user import get_user_integrations
 from backend.executor.utils import add_graph_execution
 from backend.integrations.ayrshare import AyrshareClient, SocialPlatform
-from backend.integrations.creds_manager import IntegrationCredentialsManager
+from backend.integrations.credentials_store import provider_matches
+from backend.integrations.creds_manager import (
+    IntegrationCredentialsManager,
+    create_mcp_oauth_handler,
+)
 from backend.integrations.oauth import CREDENTIALS_BY_PROVIDER, HANDLERS_BY_NAME
 from backend.integrations.providers import ProviderName
 from backend.integrations.webhooks import get_webhook_manager
@@ -102,9 +106,37 @@ class CredentialsMetaResponse(BaseModel):
     scopes: list[str] | None
     username: str | None
     host: str | None = Field(
-        default=None, description="Host pattern for host-scoped credentials"
+        default=None,
+        description="Host pattern for host-scoped or MCP server URL for MCP credentials",
     )
 
+    @model_validator(mode="before")
+    @classmethod
+    def _normalize_provider(cls, data: Any) -> Any:
+        """Fix ``ProviderName.X`` format from Python 3.13 ``str(Enum)`` bug."""
+        if isinstance(data, dict):
+            prov = data.get("provider", "")
+            if isinstance(prov, str) and prov.startswith("ProviderName."):
+                member = prov.removeprefix("ProviderName.")
+                try:
+                    data = {**data, "provider": ProviderName[member].value}
+                except KeyError:
+                    pass
+        return data
+
+    @staticmethod
+    def get_host(cred: Credentials) -> str | None:
+        """Extract host from credential: HostScoped host or MCP server URL."""
+        if isinstance(cred, HostScopedCredentials):
+            return cred.host
+        if isinstance(cred, OAuth2Credentials) and cred.provider in (
+            ProviderName.MCP,
+            ProviderName.MCP.value,
+            "ProviderName.MCP",
+        ):
+            return (cred.metadata or {}).get("mcp_server_url")
+        return None
+
 
 @router.post("/{provider}/callback", summary="Exchange OAuth code for tokens")
 async def callback(
@@ -179,9 +211,7 @@ async def callback(
         title=credentials.title,
         scopes=credentials.scopes,
         username=credentials.username,
-        host=(
-            credentials.host if isinstance(credentials, HostScopedCredentials) else None
-        ),
+        host=(CredentialsMetaResponse.get_host(credentials)),
     )
 
 
@@ -199,7 +229,7 @@ async def list_credentials(
             title=cred.title,
             scopes=cred.scopes if isinstance(cred, OAuth2Credentials) else None,
             username=cred.username if isinstance(cred, OAuth2Credentials) else None,
-            host=cred.host if isinstance(cred, HostScopedCredentials) else None,
+            host=CredentialsMetaResponse.get_host(cred),
         )
         for cred in credentials
     ]
@@ -222,7 +252,7 @@ async def list_credentials_by_provider(
             title=cred.title,
             scopes=cred.scopes if isinstance(cred, OAuth2Credentials) else None,
             username=cred.username if isinstance(cred, OAuth2Credentials) else None,
-            host=cred.host if isinstance(cred, HostScopedCredentials) else None,
+            host=CredentialsMetaResponse.get_host(cred),
         )
         for cred in credentials
     ]
@@ -322,7 +352,11 @@ async def delete_credentials(
 
     tokens_revoked = None
     if isinstance(creds, OAuth2Credentials):
-        handler = _get_provider_oauth_handler(request, provider)
+        if provider_matches(provider.value, ProviderName.MCP.value):
+            # MCP uses dynamic per-server OAuth — create handler from metadata
+            handler = create_mcp_oauth_handler(creds)
+        else:
+            handler = _get_provider_oauth_handler(request, provider)
         tokens_revoked = await handler.revoke_tokens(creds)
 
     return CredentialsDeletionResponse(revoked=tokens_revoked)

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

@@ -12,12 +12,11 @@ import backend.api.features.store.image_gen as store_image_gen
 import backend.api.features.store.media as store_media
 import backend.data.graph as graph_db
 import backend.data.integrations as integrations_db
-from backend.data.block import BlockInput
 from backend.data.db import transaction
 from backend.data.execution import get_graph_execution
 from backend.data.graph import GraphSettings
 from backend.data.includes import AGENT_PRESET_INCLUDE, library_agent_include
-from backend.data.model import CredentialsMetaInput
+from backend.data.model import CredentialsMetaInput, GraphInput
 from backend.integrations.creds_manager import IntegrationCredentialsManager
 from backend.integrations.webhooks.graph_lifecycle_hooks import (
     on_graph_activate,
@@ -1130,7 +1129,7 @@ async def create_preset_from_graph_execution(
 async def update_preset(
     user_id: str,
     preset_id: str,
-    inputs: Optional[BlockInput] = None,
+    inputs: Optional[GraphInput] = None,
     credentials: Optional[dict[str, CredentialsMetaInput]] = None,
     name: Optional[str] = None,
     description: Optional[str] = None,

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

@@ -6,9 +6,12 @@ import prisma.enums
 import prisma.models
 import pydantic
 
-from backend.data.block import BlockInput
 from backend.data.graph import GraphModel, GraphSettings, GraphTriggerInfo
-from backend.data.model import CredentialsMetaInput, is_credentials_field_name
+from backend.data.model import (
+    CredentialsMetaInput,
+    GraphInput,
+    is_credentials_field_name,
+)
 from backend.util.json import loads as json_loads
 from backend.util.models import Pagination
 
@@ -323,7 +326,7 @@ class LibraryAgentPresetCreatable(pydantic.BaseModel):
     graph_id: str
     graph_version: int
 
-    inputs: BlockInput
+    inputs: GraphInput
     credentials: dict[str, CredentialsMetaInput]
 
     name: str
@@ -352,7 +355,7 @@ class LibraryAgentPresetUpdatable(pydantic.BaseModel):
     Request model used when updating a preset for a library agent.
     """
 
-    inputs: Optional[BlockInput] = None
+    inputs: Optional[GraphInput] = None
     credentials: Optional[dict[str, CredentialsMetaInput]] = None
 
     name: Optional[str] = None
@@ -395,7 +398,7 @@ class LibraryAgentPreset(LibraryAgentPresetCreatable):
                 "Webhook must be included in AgentPreset query when webhookId is set"
             )
 
-        input_data: BlockInput = {}
+        input_data: GraphInput = {}
         input_credentials: dict[str, CredentialsMetaInput] = {}
 
         for preset_input in preset.InputPresets:

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

@@ -0,0 +1,404 @@
+"""
+MCP (Model Context Protocol) API routes.
+
+Provides endpoints for MCP tool discovery and OAuth authentication so the
+frontend can list available tools on an MCP server before placing a block.
+"""
+
+import logging
+from typing import Annotated, Any
+from urllib.parse import urlparse
+
+import fastapi
+from autogpt_libs.auth import get_user_id
+from fastapi import Security
+from pydantic import BaseModel, Field
+
+from backend.api.features.integrations.router import CredentialsMetaResponse
+from backend.blocks.mcp.client import MCPClient, MCPClientError
+from backend.blocks.mcp.oauth import MCPOAuthHandler
+from backend.data.model import OAuth2Credentials
+from backend.integrations.creds_manager import IntegrationCredentialsManager
+from backend.integrations.providers import ProviderName
+from backend.util.request import HTTPClientError, Requests
+from backend.util.settings import Settings
+
+logger = logging.getLogger(__name__)
+
+settings = Settings()
+router = fastapi.APIRouter(tags=["mcp"])
+creds_manager = IntegrationCredentialsManager()
+
+
+# ====================== Tool Discovery ====================== #
+
+
+class DiscoverToolsRequest(BaseModel):
+    """Request to discover tools on an MCP server."""
+
+    server_url: str = Field(description="URL of the MCP server")
+    auth_token: str | None = Field(
+        default=None,
+        description="Optional Bearer token for authenticated MCP servers",
+    )
+
+
+class MCPToolResponse(BaseModel):
+    """A single MCP tool returned by discovery."""
+
+    name: str
+    description: str
+    input_schema: dict[str, Any]
+
+
+class DiscoverToolsResponse(BaseModel):
+    """Response containing the list of tools available on an MCP server."""
+
+    tools: list[MCPToolResponse]
+    server_name: str | None = None
+    protocol_version: str | None = None
+
+
+@router.post(
+    "/discover-tools",
+    summary="Discover available tools on an MCP server",
+    response_model=DiscoverToolsResponse,
+)
+async def discover_tools(
+    request: DiscoverToolsRequest,
+    user_id: Annotated[str, Security(get_user_id)],
+) -> DiscoverToolsResponse:
+    """
+    Connect to an MCP server and return its available tools.
+
+    If the user has a stored MCP credential for this server URL, it will be
+    used automatically — no need to pass an explicit auth token.
+    """
+    auth_token = request.auth_token
+
+    # Auto-use stored MCP credential when no explicit token is provided.
+    if not auth_token:
+        mcp_creds = await creds_manager.store.get_creds_by_provider(
+            user_id, ProviderName.MCP.value
+        )
+        # Find the freshest credential for this server URL
+        best_cred: OAuth2Credentials | None = None
+        for cred in mcp_creds:
+            if (
+                isinstance(cred, OAuth2Credentials)
+                and (cred.metadata or {}).get("mcp_server_url") == request.server_url
+            ):
+                if best_cred is None or (
+                    (cred.access_token_expires_at or 0)
+                    > (best_cred.access_token_expires_at or 0)
+                ):
+                    best_cred = cred
+        if best_cred:
+            # Refresh the token if expired before using it
+            best_cred = await creds_manager.refresh_if_needed(user_id, best_cred)
+            logger.info(
+                f"Using MCP credential {best_cred.id} for {request.server_url}, "
+                f"expires_at={best_cred.access_token_expires_at}"
+            )
+            auth_token = best_cred.access_token.get_secret_value()
+
+    client = MCPClient(request.server_url, auth_token=auth_token)
+
+    try:
+        init_result = await client.initialize()
+        tools = await client.list_tools()
+    except HTTPClientError as e:
+        if e.status_code in (401, 403):
+            raise fastapi.HTTPException(
+                status_code=401,
+                detail="This MCP server requires authentication. "
+                "Please provide a valid auth token.",
+            )
+        raise fastapi.HTTPException(status_code=502, detail=str(e))
+    except MCPClientError as e:
+        raise fastapi.HTTPException(status_code=502, detail=str(e))
+    except Exception as e:
+        raise fastapi.HTTPException(
+            status_code=502,
+            detail=f"Failed to connect to MCP server: {e}",
+        )
+
+    return DiscoverToolsResponse(
+        tools=[
+            MCPToolResponse(
+                name=t.name,
+                description=t.description,
+                input_schema=t.input_schema,
+            )
+            for t in tools
+        ],
+        server_name=(
+            init_result.get("serverInfo", {}).get("name")
+            or urlparse(request.server_url).hostname
+            or "MCP"
+        ),
+        protocol_version=init_result.get("protocolVersion"),
+    )
+
+
+# ======================== OAuth Flow ======================== #
+
+
+class MCPOAuthLoginRequest(BaseModel):
+    """Request to start an OAuth flow for an MCP server."""
+
+    server_url: str = Field(description="URL of the MCP server that requires OAuth")
+
+
+class MCPOAuthLoginResponse(BaseModel):
+    """Response with the OAuth login URL for the user to authenticate."""
+
+    login_url: str
+    state_token: str
+
+
+@router.post(
+    "/oauth/login",
+    summary="Initiate OAuth login for an MCP server",
+)
+async def mcp_oauth_login(
+    request: MCPOAuthLoginRequest,
+    user_id: Annotated[str, Security(get_user_id)],
+) -> MCPOAuthLoginResponse:
+    """
+    Discover OAuth metadata from the MCP server and return a login URL.
+
+    1. Discovers the protected-resource metadata (RFC 9728)
+    2. Fetches the authorization server metadata (RFC 8414)
+    3. Performs Dynamic Client Registration (RFC 7591) if available
+    4. Returns the authorization URL for the frontend to open in a popup
+    """
+    client = MCPClient(request.server_url)
+
+    # Step 1: Discover protected-resource metadata (RFC 9728)
+    protected_resource = await client.discover_auth()
+
+    metadata: dict[str, Any] | None = None
+
+    if protected_resource and protected_resource.get("authorization_servers"):
+        auth_server_url = protected_resource["authorization_servers"][0]
+        resource_url = protected_resource.get("resource", request.server_url)
+
+        # Step 2a: Discover auth-server metadata (RFC 8414)
+        metadata = await client.discover_auth_server_metadata(auth_server_url)
+    else:
+        # Fallback: Some MCP servers (e.g. Linear) are their own auth server
+        # and serve OAuth metadata directly without protected-resource metadata.
+        # Don't assume a resource_url — omitting it lets the auth server choose
+        # the correct audience for the token (RFC 8707 resource is optional).
+        resource_url = None
+        metadata = await client.discover_auth_server_metadata(request.server_url)
+
+    if (
+        not metadata
+        or "authorization_endpoint" not in metadata
+        or "token_endpoint" not in metadata
+    ):
+        raise fastapi.HTTPException(
+            status_code=400,
+            detail="This MCP server does not advertise OAuth support. "
+            "You may need to provide an auth token manually.",
+        )
+
+    authorize_url = metadata["authorization_endpoint"]
+    token_url = metadata["token_endpoint"]
+    registration_endpoint = metadata.get("registration_endpoint")
+    revoke_url = metadata.get("revocation_endpoint")
+
+    # Step 3: Dynamic Client Registration (RFC 7591) if available
+    frontend_base_url = settings.config.frontend_base_url
+    if not frontend_base_url:
+        raise fastapi.HTTPException(
+            status_code=500,
+            detail="Frontend base URL is not configured.",
+        )
+    redirect_uri = f"{frontend_base_url}/auth/integrations/mcp_callback"
+
+    client_id = ""
+    client_secret = ""
+    if registration_endpoint:
+        reg_result = await _register_mcp_client(
+            registration_endpoint, redirect_uri, request.server_url
+        )
+        if reg_result:
+            client_id = reg_result.get("client_id", "")
+            client_secret = reg_result.get("client_secret", "")
+
+    if not client_id:
+        client_id = "autogpt-platform"
+
+    # Step 4: Store state token with OAuth metadata for the callback
+    scopes = (protected_resource or {}).get("scopes_supported") or metadata.get(
+        "scopes_supported", []
+    )
+    state_token, code_challenge = await creds_manager.store.store_state_token(
+        user_id,
+        ProviderName.MCP.value,
+        scopes,
+        state_metadata={
+            "authorize_url": authorize_url,
+            "token_url": token_url,
+            "revoke_url": revoke_url,
+            "resource_url": resource_url,
+            "server_url": request.server_url,
+            "client_id": client_id,
+            "client_secret": client_secret,
+        },
+    )
+
+    # Step 5: Build and return the login URL
+    handler = MCPOAuthHandler(
+        client_id=client_id,
+        client_secret=client_secret,
+        redirect_uri=redirect_uri,
+        authorize_url=authorize_url,
+        token_url=token_url,
+        resource_url=resource_url,
+    )
+    login_url = handler.get_login_url(
+        scopes, state_token, code_challenge=code_challenge
+    )
+
+    return MCPOAuthLoginResponse(login_url=login_url, state_token=state_token)
+
+
+class MCPOAuthCallbackRequest(BaseModel):
+    """Request to exchange an OAuth code for tokens."""
+
+    code: str = Field(description="Authorization code from OAuth callback")
+    state_token: str = Field(description="State token for CSRF verification")
+
+
+class MCPOAuthCallbackResponse(BaseModel):
+    """Response after successfully storing OAuth credentials."""
+
+    credential_id: str
+
+
+@router.post(
+    "/oauth/callback",
+    summary="Exchange OAuth code for MCP tokens",
+)
+async def mcp_oauth_callback(
+    request: MCPOAuthCallbackRequest,
+    user_id: Annotated[str, Security(get_user_id)],
+) -> CredentialsMetaResponse:
+    """
+    Exchange the authorization code for tokens and store the credential.
+
+    The frontend calls this after receiving the OAuth code from the popup.
+    On success, subsequent ``/discover-tools`` calls for the same server URL
+    will automatically use the stored credential.
+    """
+    valid_state = await creds_manager.store.verify_state_token(
+        user_id, request.state_token, ProviderName.MCP.value
+    )
+    if not valid_state:
+        raise fastapi.HTTPException(
+            status_code=400,
+            detail="Invalid or expired state token.",
+        )
+
+    meta = valid_state.state_metadata
+    frontend_base_url = settings.config.frontend_base_url
+    if not frontend_base_url:
+        raise fastapi.HTTPException(
+            status_code=500,
+            detail="Frontend base URL is not configured.",
+        )
+    redirect_uri = f"{frontend_base_url}/auth/integrations/mcp_callback"
+
+    handler = MCPOAuthHandler(
+        client_id=meta["client_id"],
+        client_secret=meta.get("client_secret", ""),
+        redirect_uri=redirect_uri,
+        authorize_url=meta["authorize_url"],
+        token_url=meta["token_url"],
+        revoke_url=meta.get("revoke_url"),
+        resource_url=meta.get("resource_url"),
+    )
+
+    try:
+        credentials = await handler.exchange_code_for_tokens(
+            request.code, valid_state.scopes, valid_state.code_verifier
+        )
+    except Exception as e:
+        raise fastapi.HTTPException(
+            status_code=400,
+            detail=f"OAuth token exchange failed: {e}",
+        )
+
+    # Enrich credential metadata for future lookup and token refresh
+    if credentials.metadata is None:
+        credentials.metadata = {}
+    credentials.metadata["mcp_server_url"] = meta["server_url"]
+    credentials.metadata["mcp_client_id"] = meta["client_id"]
+    credentials.metadata["mcp_client_secret"] = meta.get("client_secret", "")
+    credentials.metadata["mcp_token_url"] = meta["token_url"]
+    credentials.metadata["mcp_resource_url"] = meta.get("resource_url", "")
+
+    hostname = urlparse(meta["server_url"]).hostname or meta["server_url"]
+    credentials.title = f"MCP: {hostname}"
+
+    # Remove old MCP credentials for the same server to prevent stale token buildup.
+    try:
+        old_creds = await creds_manager.store.get_creds_by_provider(
+            user_id, ProviderName.MCP.value
+        )
+        for old in old_creds:
+            if (
+                isinstance(old, OAuth2Credentials)
+                and (old.metadata or {}).get("mcp_server_url") == meta["server_url"]
+            ):
+                await creds_manager.store.delete_creds_by_id(user_id, old.id)
+                logger.info(
+                    f"Removed old MCP credential {old.id} for {meta['server_url']}"
+                )
+    except Exception:
+        logger.debug("Could not clean up old MCP credentials", exc_info=True)
+
+    await creds_manager.create(user_id, credentials)
+
+    return CredentialsMetaResponse(
+        id=credentials.id,
+        provider=credentials.provider,
+        type=credentials.type,
+        title=credentials.title,
+        scopes=credentials.scopes,
+        username=credentials.username,
+        host=credentials.metadata.get("mcp_server_url"),
+    )
+
+
+# ======================== Helpers ======================== #
+
+
+async def _register_mcp_client(
+    registration_endpoint: str,
+    redirect_uri: str,
+    server_url: str,
+) -> dict[str, Any] | None:
+    """Attempt Dynamic Client Registration (RFC 7591) with an MCP auth server."""
+    try:
+        response = await Requests(raise_for_status=True).post(
+            registration_endpoint,
+            json={
+                "client_name": "AutoGPT Platform",
+                "redirect_uris": [redirect_uri],
+                "grant_types": ["authorization_code"],
+                "response_types": ["code"],
+                "token_endpoint_auth_method": "client_secret_post",
+            },
+        )
+        data = response.json()
+        if isinstance(data, dict) and "client_id" in data:
+            return data
+        return None
+    except Exception as e:
+        logger.warning(f"Dynamic client registration failed for {server_url}: {e}")
+        return None

autogpt_platform/backend/backend/api/features/mcp/test_routes.py

@@ -0,0 +1,436 @@
+"""Tests for MCP API routes.
+
+Uses httpx.AsyncClient with ASGITransport instead of fastapi.testclient.TestClient
+to avoid creating blocking portals that can corrupt pytest-asyncio's session event loop.
+"""
+
+from unittest.mock import AsyncMock, patch
+
+import fastapi
+import httpx
+import pytest
+import pytest_asyncio
+from autogpt_libs.auth import get_user_id
+
+from backend.api.features.mcp.routes import router
+from backend.blocks.mcp.client import MCPClientError, MCPTool
+from backend.util.request import HTTPClientError
+
+app = fastapi.FastAPI()
+app.include_router(router)
+app.dependency_overrides[get_user_id] = lambda: "test-user-id"
+
+
+@pytest_asyncio.fixture(scope="module")
+async def client():
+    transport = httpx.ASGITransport(app=app)
+    async with httpx.AsyncClient(transport=transport, base_url="http://test") as c:
+        yield c
+
+
+class TestDiscoverTools:
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_discover_tools_success(self, client):
+        mock_tools = [
+            MCPTool(
+                name="get_weather",
+                description="Get weather for a city",
+                input_schema={
+                    "type": "object",
+                    "properties": {"city": {"type": "string"}},
+                    "required": ["city"],
+                },
+            ),
+            MCPTool(
+                name="add_numbers",
+                description="Add two numbers",
+                input_schema={
+                    "type": "object",
+                    "properties": {
+                        "a": {"type": "number"},
+                        "b": {"type": "number"},
+                    },
+                },
+            ),
+        ]
+
+        with (
+            patch("backend.api.features.mcp.routes.MCPClient") as MockClient,
+            patch("backend.api.features.mcp.routes.creds_manager") as mock_cm,
+        ):
+            mock_cm.store.get_creds_by_provider = AsyncMock(return_value=[])
+            instance = MockClient.return_value
+            instance.initialize = AsyncMock(
+                return_value={
+                    "protocolVersion": "2025-03-26",
+                    "serverInfo": {"name": "test-server"},
+                }
+            )
+            instance.list_tools = AsyncMock(return_value=mock_tools)
+
+            response = await client.post(
+                "/discover-tools",
+                json={"server_url": "https://mcp.example.com/mcp"},
+            )
+
+        assert response.status_code == 200
+        data = response.json()
+        assert len(data["tools"]) == 2
+        assert data["tools"][0]["name"] == "get_weather"
+        assert data["tools"][1]["name"] == "add_numbers"
+        assert data["server_name"] == "test-server"
+        assert data["protocol_version"] == "2025-03-26"
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_discover_tools_with_auth_token(self, client):
+        with patch("backend.api.features.mcp.routes.MCPClient") as MockClient:
+            instance = MockClient.return_value
+            instance.initialize = AsyncMock(
+                return_value={"serverInfo": {}, "protocolVersion": "2025-03-26"}
+            )
+            instance.list_tools = AsyncMock(return_value=[])
+
+            response = await client.post(
+                "/discover-tools",
+                json={
+                    "server_url": "https://mcp.example.com/mcp",
+                    "auth_token": "my-secret-token",
+                },
+            )
+
+        assert response.status_code == 200
+        MockClient.assert_called_once_with(
+            "https://mcp.example.com/mcp",
+            auth_token="my-secret-token",
+        )
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_discover_tools_auto_uses_stored_credential(self, client):
+        """When no explicit token is given, stored MCP credentials are used."""
+        from pydantic import SecretStr
+
+        from backend.data.model import OAuth2Credentials
+
+        stored_cred = OAuth2Credentials(
+            provider="mcp",
+            title="MCP: example.com",
+            access_token=SecretStr("stored-token-123"),
+            refresh_token=None,
+            access_token_expires_at=None,
+            refresh_token_expires_at=None,
+            scopes=[],
+            metadata={"mcp_server_url": "https://mcp.example.com/mcp"},
+        )
+
+        with (
+            patch("backend.api.features.mcp.routes.MCPClient") as MockClient,
+            patch("backend.api.features.mcp.routes.creds_manager") as mock_cm,
+        ):
+            mock_cm.store.get_creds_by_provider = AsyncMock(return_value=[stored_cred])
+            mock_cm.refresh_if_needed = AsyncMock(return_value=stored_cred)
+            instance = MockClient.return_value
+            instance.initialize = AsyncMock(
+                return_value={"serverInfo": {}, "protocolVersion": "2025-03-26"}
+            )
+            instance.list_tools = AsyncMock(return_value=[])
+
+            response = await client.post(
+                "/discover-tools",
+                json={"server_url": "https://mcp.example.com/mcp"},
+            )
+
+        assert response.status_code == 200
+        MockClient.assert_called_once_with(
+            "https://mcp.example.com/mcp",
+            auth_token="stored-token-123",
+        )
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_discover_tools_mcp_error(self, client):
+        with (
+            patch("backend.api.features.mcp.routes.MCPClient") as MockClient,
+            patch("backend.api.features.mcp.routes.creds_manager") as mock_cm,
+        ):
+            mock_cm.store.get_creds_by_provider = AsyncMock(return_value=[])
+            instance = MockClient.return_value
+            instance.initialize = AsyncMock(
+                side_effect=MCPClientError("Connection refused")
+            )
+
+            response = await client.post(
+                "/discover-tools",
+                json={"server_url": "https://bad-server.example.com/mcp"},
+            )
+
+        assert response.status_code == 502
+        assert "Connection refused" in response.json()["detail"]
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_discover_tools_generic_error(self, client):
+        with (
+            patch("backend.api.features.mcp.routes.MCPClient") as MockClient,
+            patch("backend.api.features.mcp.routes.creds_manager") as mock_cm,
+        ):
+            mock_cm.store.get_creds_by_provider = AsyncMock(return_value=[])
+            instance = MockClient.return_value
+            instance.initialize = AsyncMock(side_effect=Exception("Network timeout"))
+
+            response = await client.post(
+                "/discover-tools",
+                json={"server_url": "https://timeout.example.com/mcp"},
+            )
+
+        assert response.status_code == 502
+        assert "Failed to connect" in response.json()["detail"]
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_discover_tools_auth_required(self, client):
+        with (
+            patch("backend.api.features.mcp.routes.MCPClient") as MockClient,
+            patch("backend.api.features.mcp.routes.creds_manager") as mock_cm,
+        ):
+            mock_cm.store.get_creds_by_provider = AsyncMock(return_value=[])
+            instance = MockClient.return_value
+            instance.initialize = AsyncMock(
+                side_effect=HTTPClientError("HTTP 401 Error: Unauthorized", 401)
+            )
+
+            response = await client.post(
+                "/discover-tools",
+                json={"server_url": "https://auth-server.example.com/mcp"},
+            )
+
+        assert response.status_code == 401
+        assert "requires authentication" in response.json()["detail"]
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_discover_tools_forbidden(self, client):
+        with (
+            patch("backend.api.features.mcp.routes.MCPClient") as MockClient,
+            patch("backend.api.features.mcp.routes.creds_manager") as mock_cm,
+        ):
+            mock_cm.store.get_creds_by_provider = AsyncMock(return_value=[])
+            instance = MockClient.return_value
+            instance.initialize = AsyncMock(
+                side_effect=HTTPClientError("HTTP 403 Error: Forbidden", 403)
+            )
+
+            response = await client.post(
+                "/discover-tools",
+                json={"server_url": "https://auth-server.example.com/mcp"},
+            )
+
+        assert response.status_code == 401
+        assert "requires authentication" in response.json()["detail"]
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_discover_tools_missing_url(self, client):
+        response = await client.post("/discover-tools", json={})
+        assert response.status_code == 422
+
+
+class TestOAuthLogin:
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_oauth_login_success(self, client):
+        with (
+            patch("backend.api.features.mcp.routes.MCPClient") as MockClient,
+            patch("backend.api.features.mcp.routes.creds_manager") as mock_cm,
+            patch("backend.api.features.mcp.routes.settings") as mock_settings,
+            patch(
+                "backend.api.features.mcp.routes._register_mcp_client"
+            ) as mock_register,
+        ):
+            instance = MockClient.return_value
+            instance.discover_auth = AsyncMock(
+                return_value={
+                    "authorization_servers": ["https://auth.sentry.io"],
+                    "resource": "https://mcp.sentry.dev/mcp",
+                    "scopes_supported": ["openid"],
+                }
+            )
+            instance.discover_auth_server_metadata = AsyncMock(
+                return_value={
+                    "authorization_endpoint": "https://auth.sentry.io/authorize",
+                    "token_endpoint": "https://auth.sentry.io/token",
+                    "registration_endpoint": "https://auth.sentry.io/register",
+                }
+            )
+            mock_register.return_value = {
+                "client_id": "registered-client-id",
+                "client_secret": "registered-secret",
+            }
+            mock_cm.store.store_state_token = AsyncMock(
+                return_value=("state-token-123", "code-challenge-abc")
+            )
+            mock_settings.config.frontend_base_url = "http://localhost:3000"
+
+            response = await client.post(
+                "/oauth/login",
+                json={"server_url": "https://mcp.sentry.dev/mcp"},
+            )
+
+        assert response.status_code == 200
+        data = response.json()
+        assert "login_url" in data
+        assert data["state_token"] == "state-token-123"
+        assert "auth.sentry.io/authorize" in data["login_url"]
+        assert "registered-client-id" in data["login_url"]
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_oauth_login_no_oauth_support(self, client):
+        with patch("backend.api.features.mcp.routes.MCPClient") as MockClient:
+            instance = MockClient.return_value
+            instance.discover_auth = AsyncMock(return_value=None)
+            instance.discover_auth_server_metadata = AsyncMock(return_value=None)
+
+            response = await client.post(
+                "/oauth/login",
+                json={"server_url": "https://simple-server.example.com/mcp"},
+            )
+
+        assert response.status_code == 400
+        assert "does not advertise OAuth" in response.json()["detail"]
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_oauth_login_fallback_to_public_client(self, client):
+        """When DCR is unavailable, falls back to default public client ID."""
+        with (
+            patch("backend.api.features.mcp.routes.MCPClient") as MockClient,
+            patch("backend.api.features.mcp.routes.creds_manager") as mock_cm,
+            patch("backend.api.features.mcp.routes.settings") as mock_settings,
+        ):
+            instance = MockClient.return_value
+            instance.discover_auth = AsyncMock(
+                return_value={
+                    "authorization_servers": ["https://auth.example.com"],
+                    "resource": "https://mcp.example.com/mcp",
+                }
+            )
+            instance.discover_auth_server_metadata = AsyncMock(
+                return_value={
+                    "authorization_endpoint": "https://auth.example.com/authorize",
+                    "token_endpoint": "https://auth.example.com/token",
+                    # No registration_endpoint
+                }
+            )
+            mock_cm.store.store_state_token = AsyncMock(
+                return_value=("state-abc", "challenge-xyz")
+            )
+            mock_settings.config.frontend_base_url = "http://localhost:3000"
+
+            response = await client.post(
+                "/oauth/login",
+                json={"server_url": "https://mcp.example.com/mcp"},
+            )
+
+        assert response.status_code == 200
+        data = response.json()
+        assert "autogpt-platform" in data["login_url"]
+
+
+class TestOAuthCallback:
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_oauth_callback_success(self, client):
+        from pydantic import SecretStr
+
+        from backend.data.model import OAuth2Credentials
+
+        mock_creds = OAuth2Credentials(
+            provider="mcp",
+            title=None,
+            access_token=SecretStr("access-token-xyz"),
+            refresh_token=None,
+            access_token_expires_at=None,
+            refresh_token_expires_at=None,
+            scopes=[],
+            metadata={
+                "mcp_token_url": "https://auth.sentry.io/token",
+                "mcp_resource_url": "https://mcp.sentry.dev/mcp",
+            },
+        )
+
+        with (
+            patch("backend.api.features.mcp.routes.creds_manager") as mock_cm,
+            patch("backend.api.features.mcp.routes.settings") as mock_settings,
+            patch("backend.api.features.mcp.routes.MCPOAuthHandler") as MockHandler,
+        ):
+            mock_settings.config.frontend_base_url = "http://localhost:3000"
+
+            # Mock state verification
+            mock_state = AsyncMock()
+            mock_state.state_metadata = {
+                "authorize_url": "https://auth.sentry.io/authorize",
+                "token_url": "https://auth.sentry.io/token",
+                "client_id": "test-client-id",
+                "client_secret": "test-secret",
+                "server_url": "https://mcp.sentry.dev/mcp",
+            }
+            mock_state.scopes = ["openid"]
+            mock_state.code_verifier = "verifier-123"
+            mock_cm.store.verify_state_token = AsyncMock(return_value=mock_state)
+            mock_cm.create = AsyncMock()
+
+            handler_instance = MockHandler.return_value
+            handler_instance.exchange_code_for_tokens = AsyncMock(
+                return_value=mock_creds
+            )
+
+            # Mock old credential cleanup
+            mock_cm.store.get_creds_by_provider = AsyncMock(return_value=[])
+
+            response = await client.post(
+                "/oauth/callback",
+                json={"code": "auth-code-abc", "state_token": "state-token-123"},
+            )
+
+        assert response.status_code == 200
+        data = response.json()
+        assert "id" in data
+        assert data["provider"] == "mcp"
+        assert data["type"] == "oauth2"
+        mock_cm.create.assert_called_once()
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_oauth_callback_invalid_state(self, client):
+        with patch("backend.api.features.mcp.routes.creds_manager") as mock_cm:
+            mock_cm.store.verify_state_token = AsyncMock(return_value=None)
+
+            response = await client.post(
+                "/oauth/callback",
+                json={"code": "auth-code", "state_token": "bad-state"},
+            )
+
+        assert response.status_code == 400
+        assert "Invalid or expired" in response.json()["detail"]
+
+    @pytest.mark.asyncio(loop_scope="session")
+    async def test_oauth_callback_token_exchange_fails(self, client):
+        with (
+            patch("backend.api.features.mcp.routes.creds_manager") as mock_cm,
+            patch("backend.api.features.mcp.routes.settings") as mock_settings,
+            patch("backend.api.features.mcp.routes.MCPOAuthHandler") as MockHandler,
+        ):
+            mock_settings.config.frontend_base_url = "http://localhost:3000"
+            mock_state = AsyncMock()
+            mock_state.state_metadata = {
+                "authorize_url": "https://auth.example.com/authorize",
+                "token_url": "https://auth.example.com/token",
+                "client_id": "cid",
+                "server_url": "https://mcp.example.com/mcp",
+            }
+            mock_state.scopes = []
+            mock_state.code_verifier = "v"
+            mock_cm.store.verify_state_token = AsyncMock(return_value=mock_state)
+
+            handler_instance = MockHandler.return_value
+            handler_instance.exchange_code_for_tokens = AsyncMock(
+                side_effect=RuntimeError("Token exchange failed")
+            )
+
+            response = await client.post(
+                "/oauth/callback",
+                json={"code": "bad-code", "state_token": "state"},
+            )
+
+        assert response.status_code == 400
+        assert "token exchange failed" in response.json()["detail"].lower()

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

@@ -5,8 +5,8 @@ from typing import Optional
 import aiohttp
 from fastapi import HTTPException
 
+from backend.blocks import get_block
 from backend.data import graph as graph_db
-from backend.data.block import get_block
 from backend.util.settings import Settings
 
 from .models import ApiResponse, ChatRequest, GraphData

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

@@ -152,7 +152,7 @@ class BlockHandler(ContentHandler):
 
     async def get_missing_items(self, batch_size: int) -> list[ContentItem]:
         """Fetch blocks without embeddings."""
-        from backend.data.block import get_blocks
+        from backend.blocks import get_blocks
 
         # Get all available blocks
         all_blocks = get_blocks()
@@ -249,7 +249,7 @@ class BlockHandler(ContentHandler):
 
     async def get_stats(self) -> dict[str, int]:
         """Get statistics about block embedding coverage."""
-        from backend.data.block import get_blocks
+        from backend.blocks import get_blocks
 
         all_blocks = get_blocks()
 

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

@@ -93,7 +93,7 @@ async def test_block_handler_get_missing_items(mocker):
     mock_existing = []
 
     with patch(
-        "backend.data.block.get_blocks",
+        "backend.blocks.get_blocks",
         return_value=mock_blocks,
     ):
         with patch(
@@ -135,7 +135,7 @@ async def test_block_handler_get_stats(mocker):
     mock_embedded = [{"count": 2}]
 
     with patch(
-        "backend.data.block.get_blocks",
+        "backend.blocks.get_blocks",
         return_value=mock_blocks,
     ):
         with patch(
@@ -327,7 +327,7 @@ async def test_block_handler_handles_missing_attributes():
     mock_blocks = {"block-minimal": mock_block_class}
 
     with patch(
-        "backend.data.block.get_blocks",
+        "backend.blocks.get_blocks",
         return_value=mock_blocks,
     ):
         with patch(
@@ -360,7 +360,7 @@ async def test_block_handler_skips_failed_blocks():
     mock_blocks = {"good-block": good_block, "bad-block": bad_block}
 
     with patch(
-        "backend.data.block.get_blocks",
+        "backend.blocks.get_blocks",
         return_value=mock_blocks,
     ):
         with patch(

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

@@ -662,7 +662,7 @@ async def cleanup_orphaned_embeddings() -> dict[str, Any]:
                 )
                 current_ids = {row["id"] for row in valid_agents}
             elif content_type == ContentType.BLOCK:
-                from backend.data.block import get_blocks
+                from backend.blocks import get_blocks
 
                 current_ids = set(get_blocks().keys())
             elif content_type == ContentType.DOCUMENTATION:

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

@@ -7,15 +7,6 @@ from replicate.client import Client as ReplicateClient
 from replicate.exceptions import ReplicateError
 from replicate.helpers import FileOutput
 
-from backend.blocks.ideogram import (
-    AspectRatio,
-    ColorPalettePreset,
-    IdeogramModelBlock,
-    IdeogramModelName,
-    MagicPromptOption,
-    StyleType,
-    UpscaleOption,
-)
 from backend.data.graph import GraphBaseMeta
 from backend.data.model import CredentialsMetaInput, ProviderName
 from backend.integrations.credentials_store import ideogram_credentials
@@ -50,6 +41,16 @@ async def generate_agent_image_v2(graph: GraphBaseMeta | AgentGraph) -> io.Bytes
     if not ideogram_credentials.api_key:
         raise ValueError("Missing Ideogram API key")
 
+    from backend.blocks.ideogram import (
+        AspectRatio,
+        ColorPalettePreset,
+        IdeogramModelBlock,
+        IdeogramModelName,
+        MagicPromptOption,
+        StyleType,
+        UpscaleOption,
+    )
+
     name = graph.name
     description = f"{name} ({graph.description})" if graph.description else name
 

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

@@ -40,10 +40,11 @@ from backend.api.model import (
     UpdateTimezoneRequest,
     UploadFileResponse,
 )
+from backend.blocks import get_block, get_blocks
 from backend.data import execution as execution_db
 from backend.data import graph as graph_db
 from backend.data.auth import api_key as api_key_db
-from backend.data.block import BlockInput, CompletedBlockOutput, get_block, get_blocks
+from backend.data.block import BlockInput, CompletedBlockOutput
 from backend.data.credit import (
     AutoTopUpConfig,
     RefundRequest,

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

@@ -11,7 +11,7 @@ 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.data.workspace import WorkspaceFile, get_workspace, get_workspace_file
 from backend.util.workspace_storage import get_workspace_storage
 
 
@@ -44,11 +44,11 @@ router = fastapi.APIRouter(
 )
 
 
-def _create_streaming_response(content: bytes, file) -> Response:
+def _create_streaming_response(content: bytes, file: WorkspaceFile) -> Response:
     """Create a streaming response for file content."""
     return Response(
         content=content,
-        media_type=file.mimeType,
+        media_type=file.mime_type,
         headers={
             "Content-Disposition": _sanitize_filename_for_header(file.name),
             "Content-Length": str(len(content)),
@@ -56,7 +56,7 @@ def _create_streaming_response(content: bytes, file) -> Response:
     )
 
 
-async def _create_file_download_response(file) -> Response:
+async def _create_file_download_response(file: WorkspaceFile) -> Response:
     """
     Create a download response for a workspace file.
 
@@ -66,33 +66,33 @@ async def _create_file_download_response(file) -> Response:
     storage = await get_workspace_storage()
 
     # For local storage, stream the file directly
-    if file.storagePath.startswith("local://"):
-        content = await storage.retrieve(file.storagePath)
+    if file.storage_path.startswith("local://"):
+        content = await storage.retrieve(file.storage_path)
         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)
+        url = await storage.get_download_url(file.storage_path, expires_in=300)
         # If we got back an API path (fallback), stream directly instead
         if url.startswith("/api/"):
-            content = await storage.retrieve(file.storagePath)
+            content = await storage.retrieve(file.storage_path)
             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}",
+            f"(storagePath={file.storage_path}): {e}",
             exc_info=True,
         )
         # Fall back to streaming directly from GCS
         try:
-            content = await storage.retrieve(file.storagePath)
+            content = await storage.retrieve(file.storage_path)
             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}",
+                f"(storagePath={file.storage_path}): {fallback_error}",
                 exc_info=True,
             )
             raise

autogpt_platform/backend/backend/api/rest_api.py

@@ -26,6 +26,7 @@ import backend.api.features.executions.review.routes
 import backend.api.features.library.db
 import backend.api.features.library.model
 import backend.api.features.library.routes
+import backend.api.features.mcp.routes as mcp_routes
 import backend.api.features.oauth
 import backend.api.features.otto.routes
 import backend.api.features.postmark.postmark
@@ -40,11 +41,11 @@ import backend.data.user
 import backend.integrations.webhooks.utils
 import backend.util.service
 import backend.util.settings
-from backend.api.features.chat.completion_consumer import (
+from backend.blocks.llm import DEFAULT_LLM_MODEL
+from backend.copilot.completion_consumer import (
     start_completion_consumer,
     stop_completion_consumer,
 )
-from backend.blocks.llm import DEFAULT_LLM_MODEL
 from backend.data.model import Credentials
 from backend.integrations.providers import ProviderName
 from backend.monitoring.instrumentation import instrument_fastapi
@@ -343,6 +344,11 @@ app.include_router(
     tags=["workspace"],
     prefix="/api/workspace",
 )
+app.include_router(
+    mcp_routes.router,
+    tags=["v2", "mcp"],
+    prefix="/api/mcp",
+)
 app.include_router(
     backend.api.features.oauth.router,
     tags=["oauth"],

autogpt_platform/backend/backend/app.py

@@ -38,7 +38,9 @@ def main(**kwargs):
 
     from backend.api.rest_api import AgentServer
     from backend.api.ws_api import WebsocketServer
-    from backend.executor import DatabaseManager, ExecutionManager, Scheduler
+    from backend.copilot.executor.manager import CoPilotExecutor
+    from backend.data.db_manager import DatabaseManager
+    from backend.executor import ExecutionManager, Scheduler
     from backend.notifications import NotificationManager
 
     run_processes(
@@ -48,6 +50,7 @@ def main(**kwargs):
         WebsocketServer(),
         AgentServer(),
         ExecutionManager(),
+        CoPilotExecutor(),
         **kwargs,
     )
 

autogpt_platform/backend/backend/blocks/__init__.py

@@ -3,22 +3,19 @@ import logging
 import os
 import re
 from pathlib import Path
-from typing import TYPE_CHECKING, TypeVar
+from typing import Sequence, Type, TypeVar
 
+from backend.blocks._base import AnyBlockSchema, BlockType
 from backend.util.cache import cached
 
 logger = logging.getLogger(__name__)
 
-
-if TYPE_CHECKING:
-    from backend.data.block import Block
-
 T = TypeVar("T")
 
 
 @cached(ttl_seconds=3600)
-def load_all_blocks() -> dict[str, type["Block"]]:
-    from backend.data.block import Block
+def load_all_blocks() -> dict[str, type["AnyBlockSchema"]]:
+    from backend.blocks._base import Block
     from backend.util.settings import Config
 
     # Check if example blocks should be loaded from settings
@@ -50,8 +47,8 @@ def load_all_blocks() -> dict[str, type["Block"]]:
         importlib.import_module(f".{module}", package=__name__)
 
     # Load all Block instances from the available modules
-    available_blocks: dict[str, type["Block"]] = {}
-    for block_cls in all_subclasses(Block):
+    available_blocks: dict[str, type["AnyBlockSchema"]] = {}
+    for block_cls in _all_subclasses(Block):
         class_name = block_cls.__name__
 
         if class_name.endswith("Base"):
@@ -64,7 +61,7 @@ def load_all_blocks() -> dict[str, type["Block"]]:
                 "please name the class with 'Base' at the end"
             )
 
-        block = block_cls.create()
+        block = block_cls()  # pyright: ignore[reportAbstractUsage]
 
         if not isinstance(block.id, str) or len(block.id) != 36:
             raise ValueError(
@@ -105,7 +102,7 @@ def load_all_blocks() -> dict[str, type["Block"]]:
         available_blocks[block.id] = block_cls
 
     # Filter out blocks with incomplete auth configs, e.g. missing OAuth server secrets
-    from backend.data.block import is_block_auth_configured
+    from ._utils import is_block_auth_configured
 
     filtered_blocks = {}
     for block_id, block_cls in available_blocks.items():
@@ -115,11 +112,48 @@ def load_all_blocks() -> dict[str, type["Block"]]:
     return filtered_blocks
 
 
-__all__ = ["load_all_blocks"]
-
-
-def all_subclasses(cls: type[T]) -> list[type[T]]:
+def _all_subclasses(cls: type[T]) -> list[type[T]]:
     subclasses = cls.__subclasses__()
     for subclass in subclasses:
-        subclasses += all_subclasses(subclass)
+        subclasses += _all_subclasses(subclass)
     return subclasses
+
+
+# ============== Block access helper functions ============== #
+
+
+def get_blocks() -> dict[str, Type["AnyBlockSchema"]]:
+    return load_all_blocks()
+
+
+# Note on the return type annotation: https://github.com/microsoft/pyright/issues/10281
+def get_block(block_id: str) -> "AnyBlockSchema | None":
+    cls = get_blocks().get(block_id)
+    return cls() if cls else None
+
+
+@cached(ttl_seconds=3600)
+def get_webhook_block_ids() -> Sequence[str]:
+    return [
+        id
+        for id, B in get_blocks().items()
+        if B().block_type in (BlockType.WEBHOOK, BlockType.WEBHOOK_MANUAL)
+    ]
+
+
+@cached(ttl_seconds=3600)
+def get_io_block_ids() -> Sequence[str]:
+    return [
+        id
+        for id, B in get_blocks().items()
+        if B().block_type in (BlockType.INPUT, BlockType.OUTPUT)
+    ]
+
+
+@cached(ttl_seconds=3600)
+def get_human_in_the_loop_block_ids() -> Sequence[str]:
+    return [
+        id
+        for id, B in get_blocks().items()
+        if B().block_type == BlockType.HUMAN_IN_THE_LOOP
+    ]

autogpt_platform/backend/backend/blocks/_base.py

@@ -0,0 +1,740 @@
+import inspect
+import logging
+from abc import ABC, abstractmethod
+from enum import Enum
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Callable,
+    ClassVar,
+    Generic,
+    Optional,
+    Type,
+    TypeAlias,
+    TypeVar,
+    cast,
+    get_origin,
+)
+
+import jsonref
+import jsonschema
+from pydantic import BaseModel
+
+from backend.data.block import BlockInput, BlockOutput, BlockOutputEntry
+from backend.data.model import (
+    Credentials,
+    CredentialsFieldInfo,
+    CredentialsMetaInput,
+    SchemaField,
+    is_credentials_field_name,
+)
+from backend.integrations.providers import ProviderName
+from backend.util import json
+from backend.util.exceptions import (
+    BlockError,
+    BlockExecutionError,
+    BlockInputError,
+    BlockOutputError,
+    BlockUnknownError,
+)
+from backend.util.settings import Config
+
+logger = logging.getLogger(__name__)
+
+if TYPE_CHECKING:
+    from backend.data.execution import ExecutionContext
+    from backend.data.model import ContributorDetails, NodeExecutionStats
+
+    from ..data.graph import Link
+
+app_config = Config()
+
+
+BlockTestOutput = BlockOutputEntry | tuple[str, Callable[[Any], bool]]
+
+
+class BlockType(Enum):
+    STANDARD = "Standard"
+    INPUT = "Input"
+    OUTPUT = "Output"
+    NOTE = "Note"
+    WEBHOOK = "Webhook"
+    WEBHOOK_MANUAL = "Webhook (manual)"
+    AGENT = "Agent"
+    AI = "AI"
+    AYRSHARE = "Ayrshare"
+    HUMAN_IN_THE_LOOP = "Human In The Loop"
+    MCP_TOOL = "MCP Tool"
+
+
+class BlockCategory(Enum):
+    AI = "Block that leverages AI to perform a task."
+    SOCIAL = "Block that interacts with social media platforms."
+    TEXT = "Block that processes text data."
+    SEARCH = "Block that searches or extracts information from the internet."
+    BASIC = "Block that performs basic operations."
+    INPUT = "Block that interacts with input of the graph."
+    OUTPUT = "Block that interacts with output of the graph."
+    LOGIC = "Programming logic to control the flow of your agent"
+    COMMUNICATION = "Block that interacts with communication platforms."
+    DEVELOPER_TOOLS = "Developer tools such as GitHub blocks."
+    DATA = "Block that interacts with structured data."
+    HARDWARE = "Block that interacts with hardware."
+    AGENT = "Block that interacts with other agents."
+    CRM = "Block that interacts with CRM services."
+    SAFETY = (
+        "Block that provides AI safety mechanisms such as detecting harmful content"
+    )
+    PRODUCTIVITY = "Block that helps with productivity"
+    ISSUE_TRACKING = "Block that helps with issue tracking"
+    MULTIMEDIA = "Block that interacts with multimedia content"
+    MARKETING = "Block that helps with marketing"
+
+    def dict(self) -> dict[str, str]:
+        return {"category": self.name, "description": self.value}
+
+
+class BlockCostType(str, Enum):
+    RUN = "run"  # cost X credits per run
+    BYTE = "byte"  # cost X credits per byte
+    SECOND = "second"  # cost X credits per second
+
+
+class BlockCost(BaseModel):
+    cost_amount: int
+    cost_filter: BlockInput
+    cost_type: BlockCostType
+
+    def __init__(
+        self,
+        cost_amount: int,
+        cost_type: BlockCostType = BlockCostType.RUN,
+        cost_filter: Optional[BlockInput] = None,
+        **data: Any,
+    ) -> None:
+        super().__init__(
+            cost_amount=cost_amount,
+            cost_filter=cost_filter or {},
+            cost_type=cost_type,
+            **data,
+        )
+
+
+class BlockInfo(BaseModel):
+    id: str
+    name: str
+    inputSchema: dict[str, Any]
+    outputSchema: dict[str, Any]
+    costs: list[BlockCost]
+    description: str
+    categories: list[dict[str, str]]
+    contributors: list[dict[str, Any]]
+    staticOutput: bool
+    uiType: str
+
+
+class BlockSchema(BaseModel):
+    cached_jsonschema: ClassVar[dict[str, Any]]
+
+    @classmethod
+    def jsonschema(cls) -> dict[str, Any]:
+        if cls.cached_jsonschema:
+            return cls.cached_jsonschema
+
+        model = jsonref.replace_refs(cls.model_json_schema(), merge_props=True)
+
+        def ref_to_dict(obj):
+            if isinstance(obj, dict):
+                # OpenAPI <3.1 does not support sibling fields that has a $ref key
+                # So sometimes, the schema has an "allOf"/"anyOf"/"oneOf" with 1 item.
+                keys = {"allOf", "anyOf", "oneOf"}
+                one_key = next((k for k in keys if k in obj and len(obj[k]) == 1), None)
+                if one_key:
+                    obj.update(obj[one_key][0])
+
+                return {
+                    key: ref_to_dict(value)
+                    for key, value in obj.items()
+                    if not key.startswith("$") and key != one_key
+                }
+            elif isinstance(obj, list):
+                return [ref_to_dict(item) for item in obj]
+
+            return obj
+
+        cls.cached_jsonschema = cast(dict[str, Any], ref_to_dict(model))
+
+        return cls.cached_jsonschema
+
+    @classmethod
+    def validate_data(cls, data: BlockInput) -> str | None:
+        return json.validate_with_jsonschema(
+            schema=cls.jsonschema(),
+            data={k: v for k, v in data.items() if v is not None},
+        )
+
+    @classmethod
+    def get_mismatch_error(cls, data: BlockInput) -> str | None:
+        return cls.validate_data(data)
+
+    @classmethod
+    def get_field_schema(cls, field_name: str) -> dict[str, Any]:
+        model_schema = cls.jsonschema().get("properties", {})
+        if not model_schema:
+            raise ValueError(f"Invalid model schema {cls}")
+
+        property_schema = model_schema.get(field_name)
+        if not property_schema:
+            raise ValueError(f"Invalid property name {field_name}")
+
+        return property_schema
+
+    @classmethod
+    def validate_field(cls, field_name: str, data: BlockInput) -> str | None:
+        """
+        Validate the data against a specific property (one of the input/output name).
+        Returns the validation error message if the data does not match the schema.
+        """
+        try:
+            property_schema = cls.get_field_schema(field_name)
+            jsonschema.validate(json.to_dict(data), property_schema)
+            return None
+        except jsonschema.ValidationError as e:
+            return str(e)
+
+    @classmethod
+    def get_fields(cls) -> set[str]:
+        return set(cls.model_fields.keys())
+
+    @classmethod
+    def get_required_fields(cls) -> set[str]:
+        return {
+            field
+            for field, field_info in cls.model_fields.items()
+            if field_info.is_required()
+        }
+
+    @classmethod
+    def __pydantic_init_subclass__(cls, **kwargs):
+        """Validates the schema definition. Rules:
+        - Fields with annotation `CredentialsMetaInput` MUST be
+          named `credentials` or `*_credentials`
+        - Fields named `credentials` or `*_credentials` MUST be
+          of type `CredentialsMetaInput`
+        """
+        super().__pydantic_init_subclass__(**kwargs)
+
+        # Reset cached JSON schema to prevent inheriting it from parent class
+        cls.cached_jsonschema = {}
+
+        credentials_fields = cls.get_credentials_fields()
+
+        for field_name in cls.get_fields():
+            if is_credentials_field_name(field_name):
+                if field_name not in credentials_fields:
+                    raise TypeError(
+                        f"Credentials field '{field_name}' on {cls.__qualname__} "
+                        f"is not of type {CredentialsMetaInput.__name__}"
+                    )
+
+                CredentialsMetaInput.validate_credentials_field_schema(
+                    cls.get_field_schema(field_name), field_name
+                )
+
+            elif field_name in credentials_fields:
+                raise KeyError(
+                    f"Credentials field '{field_name}' on {cls.__qualname__} "
+                    "has invalid name: must be 'credentials' or *_credentials"
+                )
+
+    @classmethod
+    def get_credentials_fields(cls) -> dict[str, type[CredentialsMetaInput]]:
+        return {
+            field_name: info.annotation
+            for field_name, info in cls.model_fields.items()
+            if (
+                inspect.isclass(info.annotation)
+                and issubclass(
+                    get_origin(info.annotation) or info.annotation,
+                    CredentialsMetaInput,
+                )
+            )
+        }
+
+    @classmethod
+    def get_auto_credentials_fields(cls) -> dict[str, dict[str, Any]]:
+        """
+        Get fields that have auto_credentials metadata (e.g., GoogleDriveFileInput).
+
+        Returns a dict mapping kwarg_name -> {field_name, auto_credentials_config}
+
+        Raises:
+            ValueError: If multiple fields have the same kwarg_name, as this would
+                cause silent overwriting and only the last field would be processed.
+        """
+        result: dict[str, dict[str, Any]] = {}
+        schema = cls.jsonschema()
+        properties = schema.get("properties", {})
+
+        for field_name, field_schema in properties.items():
+            auto_creds = field_schema.get("auto_credentials")
+            if auto_creds:
+                kwarg_name = auto_creds.get("kwarg_name", "credentials")
+                if kwarg_name in result:
+                    raise ValueError(
+                        f"Duplicate auto_credentials kwarg_name '{kwarg_name}' "
+                        f"in fields '{result[kwarg_name]['field_name']}' and "
+                        f"'{field_name}' on {cls.__qualname__}"
+                    )
+                result[kwarg_name] = {
+                    "field_name": field_name,
+                    "config": auto_creds,
+                }
+        return result
+
+    @classmethod
+    def get_credentials_fields_info(cls) -> dict[str, CredentialsFieldInfo]:
+        result = {}
+
+        # Regular credentials fields
+        for field_name in cls.get_credentials_fields().keys():
+            result[field_name] = CredentialsFieldInfo.model_validate(
+                cls.get_field_schema(field_name), by_alias=True
+            )
+
+        # Auto-generated credentials fields (from GoogleDriveFileInput etc.)
+        for kwarg_name, info in cls.get_auto_credentials_fields().items():
+            config = info["config"]
+            # Build a schema-like dict that CredentialsFieldInfo can parse
+            auto_schema = {
+                "credentials_provider": [config.get("provider", "google")],
+                "credentials_types": [config.get("type", "oauth2")],
+                "credentials_scopes": config.get("scopes"),
+            }
+            result[kwarg_name] = CredentialsFieldInfo.model_validate(
+                auto_schema, by_alias=True
+            )
+
+        return result
+
+    @classmethod
+    def get_input_defaults(cls, data: BlockInput) -> BlockInput:
+        return data  # Return as is, by default.
+
+    @classmethod
+    def get_missing_links(cls, data: BlockInput, links: list["Link"]) -> set[str]:
+        input_fields_from_nodes = {link.sink_name for link in links}
+        return input_fields_from_nodes - set(data)
+
+    @classmethod
+    def get_missing_input(cls, data: BlockInput) -> set[str]:
+        return cls.get_required_fields() - set(data)
+
+
+class BlockSchemaInput(BlockSchema):
+    """
+    Base schema class for block inputs.
+    All block input schemas should extend this class for consistency.
+    """
+
+    pass
+
+
+class BlockSchemaOutput(BlockSchema):
+    """
+    Base schema class for block outputs that includes a standard error field.
+    All block output schemas should extend this class to ensure consistent error handling.
+    """
+
+    error: str = SchemaField(
+        description="Error message if the operation failed", default=""
+    )
+
+
+BlockSchemaInputType = TypeVar("BlockSchemaInputType", bound=BlockSchemaInput)
+BlockSchemaOutputType = TypeVar("BlockSchemaOutputType", bound=BlockSchemaOutput)
+
+
+class EmptyInputSchema(BlockSchemaInput):
+    pass
+
+
+class EmptyOutputSchema(BlockSchemaOutput):
+    pass
+
+
+# For backward compatibility - will be deprecated
+EmptySchema = EmptyOutputSchema
+
+
+# --8<-- [start:BlockWebhookConfig]
+class BlockManualWebhookConfig(BaseModel):
+    """
+    Configuration model for webhook-triggered blocks on which
+    the user has to manually set up the webhook at the provider.
+    """
+
+    provider: ProviderName
+    """The service provider that the webhook connects to"""
+
+    webhook_type: str
+    """
+    Identifier for the webhook type. E.g. GitHub has repo and organization level hooks.
+
+    Only for use in the corresponding `WebhooksManager`.
+    """
+
+    event_filter_input: str = ""
+    """
+    Name of the block's event filter input.
+    Leave empty if the corresponding webhook doesn't have distinct event/payload types.
+    """
+
+    event_format: str = "{event}"
+    """
+    Template string for the event(s) that a block instance subscribes to.
+    Applied individually to each event selected in the event filter input.
+
+    Example: `"pull_request.{event}"` -> `"pull_request.opened"`
+    """
+
+
+class BlockWebhookConfig(BlockManualWebhookConfig):
+    """
+    Configuration model for webhook-triggered blocks for which
+    the webhook can be automatically set up through the provider's API.
+    """
+
+    resource_format: str
+    """
+    Template string for the resource that a block instance subscribes to.
+    Fields will be filled from the block's inputs (except `payload`).
+
+    Example: `f"{repo}/pull_requests"` (note: not how it's actually implemented)
+
+    Only for use in the corresponding `WebhooksManager`.
+    """
+    # --8<-- [end:BlockWebhookConfig]
+
+
+class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
+    def __init__(
+        self,
+        id: str = "",
+        description: str = "",
+        contributors: list["ContributorDetails"] = [],
+        categories: set[BlockCategory] | None = None,
+        input_schema: Type[BlockSchemaInputType] = EmptyInputSchema,
+        output_schema: Type[BlockSchemaOutputType] = EmptyOutputSchema,
+        test_input: BlockInput | list[BlockInput] | None = None,
+        test_output: BlockTestOutput | list[BlockTestOutput] | None = None,
+        test_mock: dict[str, Any] | None = None,
+        test_credentials: Optional[Credentials | dict[str, Credentials]] = None,
+        disabled: bool = False,
+        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.
+
+        Args:
+            id: The unique identifier for the block, this value will be persisted in the
+                DB. So it should be a unique and constant across the application run.
+                Use the UUID format for the ID.
+            description: The description of the block, explaining what the block does.
+            contributors: The list of contributors who contributed to the block.
+            input_schema: The schema, defined as a Pydantic model, for the input data.
+            output_schema: The schema, defined as a Pydantic model, for the output data.
+            test_input: The list or single sample input data for the block, for testing.
+            test_output: The list or single expected output if the test_input is run.
+            test_mock: function names on the block implementation to mock on test run.
+            disabled: If the block is disabled, it will not be available for execution.
+            static_output: Whether the output links of the block are static by default.
+        """
+        from backend.data.model import NodeExecutionStats
+
+        self.id = id
+        self.input_schema = input_schema
+        self.output_schema = output_schema
+        self.test_input = test_input
+        self.test_output = test_output
+        self.test_mock = test_mock
+        self.test_credentials = test_credentials
+        self.description = description
+        self.categories = categories or set()
+        self.contributors = contributors or set()
+        self.disabled = disabled
+        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()
+
+        if self.webhook_config:
+            if isinstance(self.webhook_config, BlockWebhookConfig):
+                # Enforce presence of credentials field on auto-setup webhook blocks
+                if not (cred_fields := self.input_schema.get_credentials_fields()):
+                    raise TypeError(
+                        "credentials field is required on auto-setup webhook blocks"
+                    )
+                # Disallow multiple credentials inputs on webhook blocks
+                elif len(cred_fields) > 1:
+                    raise ValueError(
+                        "Multiple credentials inputs not supported on webhook blocks"
+                    )
+
+                self.block_type = BlockType.WEBHOOK
+            else:
+                self.block_type = BlockType.WEBHOOK_MANUAL
+
+            # Enforce shape of webhook event filter, if present
+            if self.webhook_config.event_filter_input:
+                event_filter_field = self.input_schema.model_fields[
+                    self.webhook_config.event_filter_input
+                ]
+                if not (
+                    isinstance(event_filter_field.annotation, type)
+                    and issubclass(event_filter_field.annotation, BaseModel)
+                    and all(
+                        field.annotation is bool
+                        for field in event_filter_field.annotation.model_fields.values()
+                    )
+                ):
+                    raise NotImplementedError(
+                        f"{self.name} has an invalid webhook event selector: "
+                        "field must be a BaseModel and all its fields must be boolean"
+                    )
+
+            # Enforce presence of 'payload' input
+            if "payload" not in self.input_schema.model_fields:
+                raise TypeError(
+                    f"{self.name} is webhook-triggered but has no 'payload' input"
+                )
+
+            # Disable webhook-triggered block if webhook functionality not available
+            if not app_config.platform_base_url:
+                self.disabled = True
+
+    @abstractmethod
+    async def run(self, input_data: BlockSchemaInputType, **kwargs) -> BlockOutput:
+        """
+        Run the block with the given input data.
+        Args:
+            input_data: The input data with the structure of input_schema.
+
+        Kwargs: Currently 14/02/2025 these include
+            graph_id: The ID of the graph.
+            node_id: The ID of the node.
+            graph_exec_id: The ID of the graph execution.
+            node_exec_id: The ID of the node execution.
+            user_id: The ID of the user.
+
+        Returns:
+            A Generator that yields (output_name, output_data).
+            output_name: One of the output name defined in Block's output_schema.
+            output_data: The data for the output_name, matching the defined schema.
+        """
+        # --- satisfy the type checker, never executed -------------
+        if False:  # noqa: SIM115
+            yield "name", "value"  # pyright: ignore[reportMissingYield]
+        raise NotImplementedError(f"{self.name} does not implement the run method.")
+
+    async def run_once(
+        self, input_data: BlockSchemaInputType, output: str, **kwargs
+    ) -> Any:
+        async for item in self.run(input_data, **kwargs):
+            name, data = item
+            if name == output:
+                return data
+        raise ValueError(f"{self.name} did not produce any output for {output}")
+
+    def merge_stats(self, stats: "NodeExecutionStats") -> "NodeExecutionStats":
+        self.execution_stats += stats
+        return self.execution_stats
+
+    @property
+    def name(self):
+        return self.__class__.__name__
+
+    def to_dict(self):
+        return {
+            "id": self.id,
+            "name": self.name,
+            "inputSchema": self.input_schema.jsonschema(),
+            "outputSchema": self.output_schema.jsonschema(),
+            "description": self.description,
+            "categories": [category.dict() for category in self.categories],
+            "contributors": [
+                contributor.model_dump() for contributor in self.contributors
+            ],
+            "staticOutput": self.static_output,
+            "uiType": self.block_type.value,
+        }
+
+    def get_info(self) -> BlockInfo:
+        from backend.data.credit import get_block_cost
+
+        return BlockInfo(
+            id=self.id,
+            name=self.name,
+            inputSchema=self.input_schema.jsonschema(),
+            outputSchema=self.output_schema.jsonschema(),
+            costs=get_block_cost(self),
+            description=self.description,
+            categories=[category.dict() for category in self.categories],
+            contributors=[
+                contributor.model_dump() for contributor in self.contributors
+            ],
+            staticOutput=self.static_output,
+            uiType=self.block_type.value,
+        )
+
+    async def execute(self, input_data: BlockInput, **kwargs) -> BlockOutput:
+        try:
+            async for output_name, output_data in self._execute(input_data, **kwargs):
+                yield output_name, output_data
+        except Exception as ex:
+            if isinstance(ex, BlockError):
+                raise ex
+            else:
+                raise (
+                    BlockExecutionError
+                    if isinstance(ex, ValueError)
+                    else BlockUnknownError
+                )(
+                    message=str(ex),
+                    block_name=self.name,
+                    block_id=self.id,
+                ) from ex
+
+    async def is_block_exec_need_review(
+        self,
+        input_data: BlockInput,
+        *,
+        user_id: str,
+        node_id: str,
+        node_exec_id: str,
+        graph_exec_id: str,
+        graph_id: str,
+        graph_version: int,
+        execution_context: "ExecutionContext",
+        **kwargs,
+    ) -> tuple[bool, BlockInput]:
+        """
+        Check if this block execution needs human review and handle the review process.
+
+        Returns:
+            Tuple of (should_pause, input_data_to_use)
+            - 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
+        ):
+            return False, input_data
+
+        from backend.blocks.helpers.review import HITLReviewHelper
+
+        # Handle the review request and get decision
+        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,
+            block_name=self.name,
+            editable=True,
+        )
+
+        if decision is None:
+            # We're awaiting review - pause execution
+            return True, input_data
+
+        if not decision.should_proceed:
+            # Review was rejected, raise an error to stop execution
+            raise BlockExecutionError(
+                message=f"Block execution rejected by reviewer: {decision.message}",
+                block_name=self.name,
+                block_id=self.id,
+            )
+
+        # Review was approved - use the potentially modified data
+        # ReviewResult.data must be a dict for block inputs
+        reviewed_data = decision.review_result.data
+        if not isinstance(reviewed_data, dict):
+            raise BlockExecutionError(
+                message=f"Review data must be a dict for block input, got {type(reviewed_data).__name__}",
+                block_name=self.name,
+                block_id=self.id,
+            )
+        return False, reviewed_data
+
+    async def _execute(self, input_data: BlockInput, **kwargs) -> BlockOutput:
+        # Check for review requirement only if running within a graph execution context
+        # Direct block execution (e.g., from chat) skips the review process
+        has_graph_context = all(
+            key in kwargs
+            for key in (
+                "node_exec_id",
+                "graph_exec_id",
+                "graph_id",
+                "execution_context",
+            )
+        )
+        if has_graph_context:
+            should_pause, input_data = await self.is_block_exec_need_review(
+                input_data, **kwargs
+            )
+            if should_pause:
+                return
+
+        # Validate the input data (original or reviewer-modified) once
+        if error := self.input_schema.validate_data(input_data):
+            raise BlockInputError(
+                message=f"Unable to execute block with invalid input data: {error}",
+                block_name=self.name,
+                block_id=self.id,
+            )
+
+        # Use the validated input data
+        async for output_name, output_data in self.run(
+            self.input_schema(**{k: v for k, v in input_data.items() if v is not None}),
+            **kwargs,
+        ):
+            if output_name == "error":
+                raise BlockExecutionError(
+                    message=output_data, block_name=self.name, block_id=self.id
+                )
+            if self.block_type == BlockType.STANDARD and (
+                error := self.output_schema.validate_field(output_name, output_data)
+            ):
+                raise BlockOutputError(
+                    message=f"Block produced an invalid output data: {error}",
+                    block_name=self.name,
+                    block_id=self.id,
+                )
+            yield output_name, output_data
+
+    def is_triggered_by_event_type(
+        self, trigger_config: dict[str, Any], event_type: str
+    ) -> bool:
+        if not self.webhook_config:
+            raise TypeError("This method can't be used on non-trigger blocks")
+        if not self.webhook_config.event_filter_input:
+            return True
+        event_filter = trigger_config.get(self.webhook_config.event_filter_input)
+        if not event_filter:
+            raise ValueError("Event filter is not configured on trigger")
+        return event_type in [
+            self.webhook_config.event_format.format(event=k)
+            for k in event_filter
+            if event_filter[k] is True
+        ]
+
+
+# Type alias for any block with standard input/output schemas
+AnyBlockSchema: TypeAlias = Block[BlockSchemaInput, BlockSchemaOutput]

autogpt_platform/backend/backend/blocks/_utils.py

@@ -0,0 +1,122 @@
+import logging
+import os
+
+from backend.integrations.providers import ProviderName
+
+from ._base import AnyBlockSchema
+
+logger = logging.getLogger(__name__)
+
+
+def is_block_auth_configured(
+    block_cls: type[AnyBlockSchema],
+) -> bool:
+    """
+    Check if a block has a valid authentication method configured at runtime.
+
+    For example if a block is an OAuth-only block and there env vars are not set,
+    do not show it in the UI.
+
+    """
+    from backend.sdk.registry import AutoRegistry
+
+    # Create an instance to access input_schema
+    try:
+        block = block_cls()
+    except Exception as e:
+        # If we can't create a block instance, assume it's not OAuth-only
+        logger.error(f"Error creating block instance for {block_cls.__name__}: {e}")
+        return True
+    logger.debug(
+        f"Checking if block {block_cls.__name__} has a valid provider configured"
+    )
+
+    # Get all credential inputs from input schema
+    credential_inputs = block.input_schema.get_credentials_fields_info()
+    required_inputs = block.input_schema.get_required_fields()
+    if not credential_inputs:
+        logger.debug(
+            f"Block {block_cls.__name__} has no credential inputs - Treating as valid"
+        )
+        return True
+
+    # Check credential inputs
+    if len(required_inputs.intersection(credential_inputs.keys())) == 0:
+        logger.debug(
+            f"Block {block_cls.__name__} has only optional credential inputs"
+            " - will work without credentials configured"
+        )
+
+    # Check if the credential inputs for this block are correctly configured
+    for field_name, field_info in credential_inputs.items():
+        provider_names = field_info.provider
+        if not provider_names:
+            logger.warning(
+                f"Block {block_cls.__name__} "
+                f"has credential input '{field_name}' with no provider options"
+                " - Disabling"
+            )
+            return False
+
+        # If a field has multiple possible providers, each one needs to be usable to
+        # prevent breaking the UX
+        for _provider_name in provider_names:
+            provider_name = _provider_name.value
+            if provider_name in ProviderName.__members__.values():
+                logger.debug(
+                    f"Block {block_cls.__name__} credential input '{field_name}' "
+                    f"provider '{provider_name}' is part of the legacy provider system"
+                    " - Treating as valid"
+                )
+                break
+
+            provider = AutoRegistry.get_provider(provider_name)
+            if not provider:
+                logger.warning(
+                    f"Block {block_cls.__name__} credential input '{field_name}' "
+                    f"refers to unknown provider '{provider_name}' - Disabling"
+                )
+                return False
+
+            # Check the provider's supported auth types
+            if field_info.supported_types != provider.supported_auth_types:
+                logger.warning(
+                    f"Block {block_cls.__name__} credential input '{field_name}' "
+                    f"has mismatched supported auth types (field <> Provider): "
+                    f"{field_info.supported_types} != {provider.supported_auth_types}"
+                )
+
+            if not (supported_auth_types := provider.supported_auth_types):
+                # No auth methods are been configured for this provider
+                logger.warning(
+                    f"Block {block_cls.__name__} credential input '{field_name}' "
+                    f"provider '{provider_name}' "
+                    "has no authentication methods configured - Disabling"
+                )
+                return False
+
+            # Check if provider supports OAuth
+            if "oauth2" in supported_auth_types:
+                # Check if OAuth environment variables are set
+                if (oauth_config := provider.oauth_config) and bool(
+                    os.getenv(oauth_config.client_id_env_var)
+                    and os.getenv(oauth_config.client_secret_env_var)
+                ):
+                    logger.debug(
+                        f"Block {block_cls.__name__} credential input '{field_name}' "
+                        f"provider '{provider_name}' is configured for OAuth"
+                    )
+                else:
+                    logger.error(
+                        f"Block {block_cls.__name__} credential input '{field_name}' "
+                        f"provider '{provider_name}' "
+                        "is missing OAuth client ID or secret - Disabling"
+                    )
+                    return False
+
+        logger.debug(
+            f"Block {block_cls.__name__} credential input '{field_name}' is valid; "
+            f"supported credential types: {', '.join(field_info.supported_types)}"
+        )
+
+    return True

autogpt_platform/backend/backend/blocks/agent.py

@@ -1,7 +1,7 @@
 import logging
-from typing import Any, Optional
+from typing import TYPE_CHECKING, Any, Optional
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockInput,
@@ -9,13 +9,15 @@ from backend.data.block import (
     BlockSchema,
     BlockSchemaInput,
     BlockType,
-    get_block,
 )
 from backend.data.execution import ExecutionContext, ExecutionStatus, NodesInputMasks
 from backend.data.model import NodeExecutionStats, SchemaField
 from backend.util.json import validate_with_jsonschema
 from backend.util.retry import func_retry
 
+if TYPE_CHECKING:
+    from backend.executor.utils import LogMetadata
+
 _logger = logging.getLogger(__name__)
 
 
@@ -124,9 +126,10 @@ class AgentExecutorBlock(Block):
         graph_version: int,
         graph_exec_id: str,
         user_id: str,
-        logger,
+        logger: "LogMetadata",
     ) -> BlockOutput:
 
+        from backend.blocks import get_block
         from backend.data.execution import ExecutionEventType
         from backend.executor import utils as execution_utils
 
@@ -198,7 +201,7 @@ class AgentExecutorBlock(Block):
         self,
         graph_exec_id: str,
         user_id: str,
-        logger,
+        logger: "LogMetadata",
     ) -> None:
         from backend.executor import utils as execution_utils
 

autogpt_platform/backend/backend/blocks/ai_condition.py

@@ -1,5 +1,11 @@
 from typing import Any
 
+from backend.blocks._base import (
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
 from backend.blocks.llm import (
     DEFAULT_LLM_MODEL,
     TEST_CREDENTIALS,
@@ -11,12 +17,6 @@ from backend.blocks.llm import (
     LLMResponse,
     llm_call,
 )
-from backend.data.block import (
-    BlockCategory,
-    BlockOutput,
-    BlockSchemaInput,
-    BlockSchemaOutput,
-)
 from backend.data.model import APIKeyCredentials, NodeExecutionStats, SchemaField
 
 

autogpt_platform/backend/backend/blocks/ai_image_customizer.py

@@ -6,7 +6,7 @@ from pydantic import SecretStr
 from replicate.client import Client as ReplicateClient
 from replicate.helpers import FileOutput
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/ai_image_generator_block.py

@@ -5,7 +5,12 @@ from pydantic import SecretStr
 from replicate.client import Client as ReplicateClient
 from replicate.helpers import FileOutput
 
-from backend.data.block import Block, BlockCategory, BlockSchemaInput, BlockSchemaOutput
+from backend.blocks._base import (
+    Block,
+    BlockCategory,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
 from backend.data.execution import ExecutionContext
 from backend.data.model import (
     APIKeyCredentials,

autogpt_platform/backend/backend/blocks/ai_music_generator.py

@@ -6,7 +6,7 @@ from typing import Literal
 from pydantic import SecretStr
 from replicate.client import Client as ReplicateClient
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/ai_shortform_video_block.py

@@ -6,7 +6,7 @@ from typing import Literal
 
 from pydantic import SecretStr
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/apollo/organization.py

@@ -1,3 +1,10 @@
+from backend.blocks._base import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
 from backend.blocks.apollo._api import ApolloClient
 from backend.blocks.apollo._auth import (
     TEST_CREDENTIALS,
@@ -10,13 +17,6 @@ from backend.blocks.apollo.models import (
     PrimaryPhone,
     SearchOrganizationsRequest,
 )
-from backend.data.block import (
-    Block,
-    BlockCategory,
-    BlockOutput,
-    BlockSchemaInput,
-    BlockSchemaOutput,
-)
 from backend.data.model import CredentialsField, SchemaField
 
 

autogpt_platform/backend/backend/blocks/apollo/people.py

@@ -1,5 +1,12 @@
 import asyncio
 
+from backend.blocks._base import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
 from backend.blocks.apollo._api import ApolloClient
 from backend.blocks.apollo._auth import (
     TEST_CREDENTIALS,
@@ -14,13 +21,6 @@ from backend.blocks.apollo.models import (
     SearchPeopleRequest,
     SenorityLevels,
 )
-from backend.data.block import (
-    Block,
-    BlockCategory,
-    BlockOutput,
-    BlockSchemaInput,
-    BlockSchemaOutput,
-)
 from backend.data.model import CredentialsField, SchemaField
 
 

autogpt_platform/backend/backend/blocks/apollo/person.py

@@ -1,3 +1,10 @@
+from backend.blocks._base import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
 from backend.blocks.apollo._api import ApolloClient
 from backend.blocks.apollo._auth import (
     TEST_CREDENTIALS,
@@ -6,13 +13,6 @@ from backend.blocks.apollo._auth import (
     ApolloCredentialsInput,
 )
 from backend.blocks.apollo.models import Contact, EnrichPersonRequest
-from backend.data.block import (
-    Block,
-    BlockCategory,
-    BlockOutput,
-    BlockSchemaInput,
-    BlockSchemaOutput,
-)
 from backend.data.model import CredentialsField, SchemaField
 
 

autogpt_platform/backend/backend/blocks/ayrshare/_util.py

@@ -3,7 +3,7 @@ from typing import Optional
 
 from pydantic import BaseModel, Field
 
-from backend.data.block import BlockSchemaInput
+from backend.blocks._base import BlockSchemaInput
 from backend.data.model import SchemaField, UserIntegrations
 from backend.integrations.ayrshare import AyrshareClient
 from backend.util.clients import get_database_manager_async_client

autogpt_platform/backend/backend/blocks/basic.py

@@ -1,7 +1,7 @@
 import enum
 from typing import Any
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
@@ -126,6 +126,7 @@ class PrintToConsoleBlock(Block):
             output_schema=PrintToConsoleBlock.Output,
             test_input={"text": "Hello, World!"},
             is_sensitive_action=True,
+            disabled=True,  # Disabled per Nick Tindle's request (OPEN-3000)
             test_output=[
                 ("output", "Hello, World!"),
                 ("status", "printed"),

autogpt_platform/backend/backend/blocks/block.py

@@ -2,7 +2,7 @@ import os
 import re
 from typing import Type
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/branching.py

@@ -1,7 +1,7 @@
 from enum import Enum
 from typing import Any
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/claude_code.py

@@ -1,12 +1,12 @@
 import json
 import shlex
 import uuid
-from typing import Literal, Optional
+from typing import TYPE_CHECKING, Literal, Optional
 
 from e2b import AsyncSandbox as BaseAsyncSandbox
-from pydantic import BaseModel, SecretStr
+from pydantic import SecretStr
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
@@ -20,6 +20,13 @@ from backend.data.model import (
     SchemaField,
 )
 from backend.integrations.providers import ProviderName
+from backend.util.sandbox_files import (
+    SandboxFileOutput,
+    extract_and_store_sandbox_files,
+)
+
+if TYPE_CHECKING:
+    from backend.executor.utils import ExecutionContext
 
 
 class ClaudeCodeExecutionError(Exception):
@@ -174,22 +181,15 @@ class ClaudeCodeBlock(Block):
             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(
+        files: list[SandboxFileOutput] = SchemaField(
             description=(
                 "List of text files created/modified by Claude Code during this execution. "
-                "Each file has 'path', 'relative_path', 'name', and 'content' fields."
+                "Each file has 'path', 'relative_path', 'name', 'content', and 'workspace_ref' fields. "
+                "workspace_ref contains a workspace:// URI if the file was stored to workspace."
             )
         )
         conversation_history: str = SchemaField(
@@ -252,6 +252,7 @@ class ClaudeCodeBlock(Block):
                             "relative_path": "index.html",
                             "name": "index.html",
                             "content": "<html>Hello World</html>",
+                            "workspace_ref": None,
                         }
                     ],
                 ),
@@ -267,11 +268,12 @@ class ClaudeCodeBlock(Block):
                 "execute_claude_code": lambda *args, **kwargs: (
                     "Created index.html with hello world content",  # response
                     [
-                        ClaudeCodeBlock.FileOutput(
+                        SandboxFileOutput(
                             path="/home/user/index.html",
                             relative_path="index.html",
                             name="index.html",
                             content="<html>Hello World</html>",
+                            workspace_ref=None,
                         )
                     ],  # files
                     "User: Create a hello world HTML file\n"
@@ -294,7 +296,8 @@ class ClaudeCodeBlock(Block):
         existing_sandbox_id: str,
         conversation_history: str,
         dispose_sandbox: bool,
-    ) -> tuple[str, list["ClaudeCodeBlock.FileOutput"], str, str, str]:
+        execution_context: "ExecutionContext",
+    ) -> tuple[str, list[SandboxFileOutput], str, str, str]:
         """
         Execute Claude Code in an E2B sandbox.
 
@@ -449,14 +452,18 @@ class ClaudeCodeBlock(Block):
                 else:
                     new_conversation_history = turn_entry
 
-            # Extract files created/modified during this run
-            files = await self._extract_files(
-                sandbox, working_directory, start_timestamp
+            # Extract files created/modified during this run and store to workspace
+            sandbox_files = await extract_and_store_sandbox_files(
+                sandbox=sandbox,
+                working_directory=working_directory,
+                execution_context=execution_context,
+                since_timestamp=start_timestamp,
+                text_only=True,
             )
 
             return (
                 response,
-                files,
+                sandbox_files,  # Already SandboxFileOutput objects
                 new_conversation_history,
                 current_session_id,
                 sandbox_id,
@@ -471,140 +478,6 @@ class ClaudeCodeBlock(Block):
             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
@@ -617,6 +490,7 @@ class ClaudeCodeBlock(Block):
         *,
         e2b_credentials: APIKeyCredentials,
         anthropic_credentials: APIKeyCredentials,
+        execution_context: "ExecutionContext",
         **kwargs,
     ) -> BlockOutput:
         try:
@@ -637,6 +511,7 @@ class ClaudeCodeBlock(Block):
                 existing_sandbox_id=input_data.sandbox_id,
                 conversation_history=input_data.conversation_history,
                 dispose_sandbox=input_data.dispose_sandbox,
+                execution_context=execution_context,
             )
 
             yield "response", response

autogpt_platform/backend/backend/blocks/code_executor.py

@@ -1,12 +1,12 @@
 from enum import Enum
-from typing import Any, Literal, Optional
+from typing import TYPE_CHECKING, Any, Literal, Optional
 
 from e2b_code_interpreter import AsyncSandbox
 from e2b_code_interpreter import Result as E2BExecutionResult
 from e2b_code_interpreter.charts import Chart as E2BExecutionResultChart
 from pydantic import BaseModel, Field, JsonValue, SecretStr
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
@@ -20,6 +20,13 @@ from backend.data.model import (
     SchemaField,
 )
 from backend.integrations.providers import ProviderName
+from backend.util.sandbox_files import (
+    SandboxFileOutput,
+    extract_and_store_sandbox_files,
+)
+
+if TYPE_CHECKING:
+    from backend.executor.utils import ExecutionContext
 
 TEST_CREDENTIALS = APIKeyCredentials(
     id="01234567-89ab-cdef-0123-456789abcdef",
@@ -85,6 +92,9 @@ class CodeExecutionResult(MainCodeExecutionResult):
 class BaseE2BExecutorMixin:
     """Shared implementation methods for E2B executor blocks."""
 
+    # Default working directory in E2B sandboxes
+    WORKING_DIR = "/home/user"
+
     async def execute_code(
         self,
         api_key: str,
@@ -95,14 +105,21 @@ class BaseE2BExecutorMixin:
         timeout: Optional[int] = None,
         sandbox_id: Optional[str] = None,
         dispose_sandbox: bool = False,
+        execution_context: Optional["ExecutionContext"] = None,
+        extract_files: bool = False,
     ):
         """
         Unified code execution method that handles all three use cases:
         1. Create new sandbox and execute (ExecuteCodeBlock)
         2. Create new sandbox, execute, and return sandbox_id (InstantiateCodeSandboxBlock)
         3. Connect to existing sandbox and execute (ExecuteCodeStepBlock)
+
+        Args:
+            extract_files: If True and execution_context provided, extract files
+                           created/modified during execution and store to workspace.
         """  # noqa
         sandbox = None
+        files: list[SandboxFileOutput] = []
         try:
             if sandbox_id:
                 # Connect to existing sandbox (ExecuteCodeStepBlock case)
@@ -118,6 +135,12 @@ class BaseE2BExecutorMixin:
                     for cmd in setup_commands:
                         await sandbox.commands.run(cmd)
 
+            # Capture timestamp before execution to scope file extraction
+            start_timestamp = None
+            if extract_files:
+                ts_result = await sandbox.commands.run("date -u +%Y-%m-%dT%H:%M:%S")
+                start_timestamp = ts_result.stdout.strip() if ts_result.stdout else None
+
             # Execute the code
             execution = await sandbox.run_code(
                 code,
@@ -133,7 +156,24 @@ class BaseE2BExecutorMixin:
             stdout_logs = "".join(execution.logs.stdout)
             stderr_logs = "".join(execution.logs.stderr)
 
-            return results, text_output, stdout_logs, stderr_logs, sandbox.sandbox_id
+            # Extract files created/modified during this execution
+            if extract_files and execution_context:
+                files = await extract_and_store_sandbox_files(
+                    sandbox=sandbox,
+                    working_directory=self.WORKING_DIR,
+                    execution_context=execution_context,
+                    since_timestamp=start_timestamp,
+                    text_only=False,  # Include binary files too
+                )
+
+            return (
+                results,
+                text_output,
+                stdout_logs,
+                stderr_logs,
+                sandbox.sandbox_id,
+                files,
+            )
         finally:
             # Dispose of sandbox if requested to reduce usage costs
             if dispose_sandbox and sandbox:
@@ -238,6 +278,12 @@ class ExecuteCodeBlock(Block, BaseE2BExecutorMixin):
             description="Standard output logs from execution"
         )
         stderr_logs: str = SchemaField(description="Standard error logs from execution")
+        files: list[SandboxFileOutput] = SchemaField(
+            description=(
+                "Files created or modified during execution. "
+                "Each file has path, name, content, and workspace_ref (if stored)."
+            ),
+        )
 
     def __init__(self):
         super().__init__(
@@ -259,23 +305,30 @@ class ExecuteCodeBlock(Block, BaseE2BExecutorMixin):
                 ("results", []),
                 ("response", "Hello World"),
                 ("stdout_logs", "Hello World\n"),
+                ("files", []),
             ],
             test_mock={
-                "execute_code": lambda api_key, code, language, template_id, setup_commands, timeout, dispose_sandbox: (  # noqa
+                "execute_code": lambda api_key, code, language, template_id, setup_commands, timeout, dispose_sandbox, execution_context, extract_files: (  # noqa
                     [],  # results
                     "Hello World",  # text_output
                     "Hello World\n",  # stdout_logs
                     "",  # stderr_logs
                     "sandbox_id",  # sandbox_id
+                    [],  # files
                 ),
             },
         )
 
     async def run(
-        self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs
+        self,
+        input_data: Input,
+        *,
+        credentials: APIKeyCredentials,
+        execution_context: "ExecutionContext",
+        **kwargs,
     ) -> BlockOutput:
         try:
-            results, text_output, stdout, stderr, _ = await self.execute_code(
+            results, text_output, stdout, stderr, _, files = await self.execute_code(
                 api_key=credentials.api_key.get_secret_value(),
                 code=input_data.code,
                 language=input_data.language,
@@ -283,6 +336,8 @@ class ExecuteCodeBlock(Block, BaseE2BExecutorMixin):
                 setup_commands=input_data.setup_commands,
                 timeout=input_data.timeout,
                 dispose_sandbox=input_data.dispose_sandbox,
+                execution_context=execution_context,
+                extract_files=True,
             )
 
             # Determine result object shape & filter out empty formats
@@ -296,6 +351,8 @@ class ExecuteCodeBlock(Block, BaseE2BExecutorMixin):
                 yield "stdout_logs", stdout
             if stderr:
                 yield "stderr_logs", stderr
+            # Always yield files (empty list if none)
+            yield "files", [f.model_dump() for f in files]
         except Exception as e:
             yield "error", str(e)
 
@@ -393,6 +450,7 @@ class InstantiateCodeSandboxBlock(Block, BaseE2BExecutorMixin):
                     "Hello World\n",  # stdout_logs
                     "",  # stderr_logs
                     "sandbox_id",  # sandbox_id
+                    [],  # files
                 ),
             },
         )
@@ -401,7 +459,7 @@ class InstantiateCodeSandboxBlock(Block, BaseE2BExecutorMixin):
         self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs
     ) -> BlockOutput:
         try:
-            _, text_output, stdout, stderr, sandbox_id = await self.execute_code(
+            _, text_output, stdout, stderr, sandbox_id, _ = await self.execute_code(
                 api_key=credentials.api_key.get_secret_value(),
                 code=input_data.setup_code,
                 language=input_data.language,
@@ -500,6 +558,7 @@ class ExecuteCodeStepBlock(Block, BaseE2BExecutorMixin):
                     "Hello World\n",  # stdout_logs
                     "",  # stderr_logs
                     sandbox_id,  # sandbox_id
+                    [],  # files
                 ),
             },
         )
@@ -508,7 +567,7 @@ class ExecuteCodeStepBlock(Block, BaseE2BExecutorMixin):
         self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs
     ) -> BlockOutput:
         try:
-            results, text_output, stdout, stderr, _ = await self.execute_code(
+            results, text_output, stdout, stderr, _, _ = await self.execute_code(
                 api_key=credentials.api_key.get_secret_value(),
                 code=input_data.step_code,
                 language=input_data.language,

autogpt_platform/backend/backend/blocks/code_extraction_block.py

@@ -1,6 +1,6 @@
 import re
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/codex.py

@@ -6,7 +6,7 @@ from openai import AsyncOpenAI
 from openai.types.responses import Response as OpenAIResponse
 from pydantic import SecretStr
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/compass/triggers.py

@@ -1,6 +1,6 @@
 from pydantic import BaseModel
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockManualWebhookConfig,

autogpt_platform/backend/backend/blocks/count_words_and_char_block.py

@@ -1,4 +1,4 @@
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/data_manipulation.py

@@ -1,6 +1,6 @@
 from typing import Any, List
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
@@ -682,17 +682,219 @@ class ListIsEmptyBlock(Block):
         yield "is_empty", len(input_data.list) == 0
 
 
+# =============================================================================
+# List Concatenation Helpers
+# =============================================================================
+
+
+def _validate_list_input(item: Any, index: int) -> str | None:
+    """Validate that an item is a list. Returns error message or None."""
+    if item is None:
+        return None  # None is acceptable, will be skipped
+    if not isinstance(item, list):
+        return (
+            f"Invalid input at index {index}: expected a list, "
+            f"got {type(item).__name__}. "
+            f"All items in 'lists' must be lists (e.g., [[1, 2], [3, 4]])."
+        )
+    return None
+
+
+def _validate_all_lists(lists: List[Any]) -> str | None:
+    """Validate that all items in a sequence are lists. Returns first error or None."""
+    for idx, item in enumerate(lists):
+        error = _validate_list_input(item, idx)
+        if error is not None and item is not None:
+            return error
+    return None
+
+
+def _concatenate_lists_simple(lists: List[List[Any]]) -> List[Any]:
+    """Concatenate a sequence of lists into a single list, skipping None values."""
+    result: List[Any] = []
+    for lst in lists:
+        if lst is None:
+            continue
+        result.extend(lst)
+    return result
+
+
+def _flatten_nested_list(nested: List[Any], max_depth: int = -1) -> List[Any]:
+    """
+    Recursively flatten a nested list structure.
+
+    Args:
+        nested: The list to flatten.
+        max_depth: Maximum recursion depth. -1 means unlimited.
+
+    Returns:
+        A flat list with all nested elements extracted.
+    """
+    result: List[Any] = []
+    _flatten_recursive(nested, result, current_depth=0, max_depth=max_depth)
+    return result
+
+
+_MAX_FLATTEN_DEPTH = 1000
+
+
+def _flatten_recursive(
+    items: List[Any],
+    result: List[Any],
+    current_depth: int,
+    max_depth: int,
+) -> None:
+    """Internal recursive helper for flattening nested lists."""
+    if current_depth > _MAX_FLATTEN_DEPTH:
+        raise RecursionError(
+            f"Flattening exceeded maximum depth of {_MAX_FLATTEN_DEPTH} levels. "
+            "Input may be too deeply nested."
+        )
+    for item in items:
+        if isinstance(item, list) and (max_depth == -1 or current_depth < max_depth):
+            _flatten_recursive(item, result, current_depth + 1, max_depth)
+        else:
+            result.append(item)
+
+
+def _deduplicate_list(items: List[Any]) -> List[Any]:
+    """
+    Remove duplicate elements from a list, preserving order of first occurrences.
+
+    Args:
+        items: The list to deduplicate.
+
+    Returns:
+        A list with duplicates removed, maintaining original order.
+    """
+    seen: set = set()
+    result: List[Any] = []
+    for item in items:
+        item_id = _make_hashable(item)
+        if item_id not in seen:
+            seen.add(item_id)
+            result.append(item)
+    return result
+
+
+def _make_hashable(item: Any):
+    """
+    Create a hashable representation of any item for deduplication.
+    Converts unhashable types (dicts, lists) into deterministic tuple structures.
+    """
+    if isinstance(item, dict):
+        return tuple(
+            sorted(
+                ((_make_hashable(k), _make_hashable(v)) for k, v in item.items()),
+                key=lambda x: (str(type(x[0])), str(x[0])),
+            )
+        )
+    if isinstance(item, (list, tuple)):
+        return tuple(_make_hashable(i) for i in item)
+    if isinstance(item, set):
+        return frozenset(_make_hashable(i) for i in item)
+    return item
+
+
+def _filter_none_values(items: List[Any]) -> List[Any]:
+    """Remove None values from a list."""
+    return [item for item in items if item is not None]
+
+
+def _compute_nesting_depth(
+    items: Any, current: int = 0, max_depth: int = _MAX_FLATTEN_DEPTH
+) -> int:
+    """
+    Compute the maximum nesting depth of a list structure using iteration to avoid RecursionError.
+
+    Uses a stack-based approach to handle deeply nested structures without hitting Python's
+    recursion limit (~1000 levels).
+    """
+    if not isinstance(items, list):
+        return current
+
+    # Stack contains tuples of (item, depth)
+    stack = [(items, current)]
+    max_observed_depth = current
+
+    while stack:
+        item, depth = stack.pop()
+
+        if depth > max_depth:
+            return depth
+
+        if not isinstance(item, list):
+            max_observed_depth = max(max_observed_depth, depth)
+            continue
+
+        if len(item) == 0:
+            max_observed_depth = max(max_observed_depth, depth + 1)
+            continue
+
+        # Add all children to stack with incremented depth
+        for child in item:
+            stack.append((child, depth + 1))
+
+    return max_observed_depth
+
+
+def _interleave_lists(lists: List[List[Any]]) -> List[Any]:
+    """
+    Interleave elements from multiple lists in round-robin fashion.
+    Example: [[1,2,3], [a,b], [x,y,z]] -> [1, a, x, 2, b, y, 3, z]
+    """
+    if not lists:
+        return []
+    filtered = [lst for lst in lists if lst is not None]
+    if not filtered:
+        return []
+    result: List[Any] = []
+    max_len = max(len(lst) for lst in filtered)
+    for i in range(max_len):
+        for lst in filtered:
+            if i < len(lst):
+                result.append(lst[i])
+    return result
+
+
+# =============================================================================
+# List Concatenation Blocks
+# =============================================================================
+
+
 class ConcatenateListsBlock(Block):
+    """
+    Concatenates two or more lists into a single list.
+
+    This block accepts a list of lists and combines all their elements
+    in order into one flat output list. It supports options for
+    deduplication and None-filtering to provide flexible list merging
+    capabilities for workflow pipelines.
+    """
+
     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]]",
         )
+        deduplicate: bool = SchemaField(
+            description="If True, remove duplicate elements from the concatenated result while preserving order.",
+            default=False,
+            advanced=True,
+        )
+        remove_none: bool = SchemaField(
+            description="If True, remove None values from the concatenated result.",
+            default=False,
+            advanced=True,
+        )
 
     class Output(BlockSchemaOutput):
         concatenated_list: List[Any] = SchemaField(
             description="The concatenated list containing all elements from all input lists in order."
         )
+        length: int = SchemaField(
+            description="The total number of elements in the concatenated list."
+        )
         error: str = SchemaField(
             description="Error message if concatenation failed due to invalid input types."
         )
@@ -700,7 +902,7 @@ class ConcatenateListsBlock(Block):
     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.",
+            description="Concatenates multiple lists into a single list. All elements from all input lists are combined in order. Supports optional deduplication and None removal.",
             categories={BlockCategory.BASIC},
             input_schema=ConcatenateListsBlock.Input,
             output_schema=ConcatenateListsBlock.Output,
@@ -709,29 +911,497 @@ class ConcatenateListsBlock(Block):
                 {"lists": [["a", "b"], ["c"], ["d", "e", "f"]]},
                 {"lists": [[1, 2], []]},
                 {"lists": []},
+                {"lists": [[1, 2, 2, 3], [3, 4]], "deduplicate": True},
+                {"lists": [[1, None, 2], [None, 3]], "remove_none": True},
             ],
             test_output=[
                 ("concatenated_list", [1, 2, 3, 4, 5, 6]),
+                ("length", 6),
                 ("concatenated_list", ["a", "b", "c", "d", "e", "f"]),
+                ("length", 6),
                 ("concatenated_list", [1, 2]),
+                ("length", 2),
                 ("concatenated_list", []),
+                ("length", 0),
+                ("concatenated_list", [1, 2, 3, 4]),
+                ("length", 4),
+                ("concatenated_list", [1, 2, 3]),
+                ("length", 3),
             ],
         )
 
+    def _validate_inputs(self, lists: List[Any]) -> str | None:
+        return _validate_all_lists(lists)
+
+    def _perform_concatenation(self, lists: List[List[Any]]) -> List[Any]:
+        return _concatenate_lists_simple(lists)
+
+    def _apply_deduplication(self, items: List[Any]) -> List[Any]:
+        return _deduplicate_list(items)
+
+    def _apply_none_removal(self, items: List[Any]) -> List[Any]:
+        return _filter_none_values(items)
+
+    def _post_process(
+        self, items: List[Any], deduplicate: bool, remove_none: bool
+    ) -> List[Any]:
+        """Apply all post-processing steps to the concatenated result."""
+        result = items
+        if remove_none:
+            result = self._apply_none_removal(result)
+        if deduplicate:
+            result = self._apply_deduplication(result)
+        return result
+
     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
+        # Validate all inputs are lists
+        validation_error = self._validate_inputs(input_data.lists)
+        if validation_error is not None:
+            yield "error", validation_error
+            return
+
+        # Perform concatenation
+        concatenated = self._perform_concatenation(input_data.lists)
+
+        # Apply post-processing
+        result = self._post_process(
+            concatenated, input_data.deduplicate, input_data.remove_none
+        )
+
+        yield "concatenated_list", result
+        yield "length", len(result)
+
+
+class FlattenListBlock(Block):
+    """
+    Flattens a nested list structure into a single flat list.
+
+    This block takes a list that may contain nested lists at any depth
+    and produces a single-level list with all leaf elements. Useful
+    for normalizing data structures from multiple sources that may
+    have varying levels of nesting.
+    """
+
+    class Input(BlockSchemaInput):
+        nested_list: List[Any] = SchemaField(
+            description="A potentially nested list to flatten into a single-level list.",
+            placeholder="e.g., [[1, [2, 3]], [4, [5, [6]]]]",
+        )
+        max_depth: int = SchemaField(
+            description="Maximum depth to flatten. -1 means flatten completely. 1 means flatten only one level.",
+            default=-1,
+            advanced=True,
+        )
+
+    class Output(BlockSchemaOutput):
+        flattened_list: List[Any] = SchemaField(
+            description="The flattened list with all nested elements extracted."
+        )
+        length: int = SchemaField(
+            description="The number of elements in the flattened list."
+        )
+        original_depth: int = SchemaField(
+            description="The maximum nesting depth of the original input list."
+        )
+        error: str = SchemaField(description="Error message if flattening failed.")
+
+    def __init__(self):
+        super().__init__(
+            id="cc45bb0f-d035-4756-96a7-fe3e36254b4d",
+            description="Flattens a nested list structure into a single flat list. Supports configurable maximum flattening depth.",
+            categories={BlockCategory.BASIC},
+            input_schema=FlattenListBlock.Input,
+            output_schema=FlattenListBlock.Output,
+            test_input=[
+                {"nested_list": [[1, 2], [3, [4, 5]]]},
+                {"nested_list": [1, [2, [3, [4]]]]},
+                {"nested_list": [1, [2, [3, [4]]], 5], "max_depth": 1},
+                {"nested_list": []},
+                {"nested_list": [1, 2, 3]},
+            ],
+            test_output=[
+                ("flattened_list", [1, 2, 3, 4, 5]),
+                ("length", 5),
+                ("original_depth", 3),
+                ("flattened_list", [1, 2, 3, 4]),
+                ("length", 4),
+                ("original_depth", 4),
+                ("flattened_list", [1, 2, [3, [4]], 5]),
+                ("length", 4),
+                ("original_depth", 4),
+                ("flattened_list", []),
+                ("length", 0),
+                ("original_depth", 1),
+                ("flattened_list", [1, 2, 3]),
+                ("length", 3),
+                ("original_depth", 1),
+            ],
+        )
+
+    def _compute_depth(self, items: List[Any]) -> int:
+        """Compute the nesting depth of the input list."""
+        return _compute_nesting_depth(items)
+
+    def _flatten(self, items: List[Any], max_depth: int) -> List[Any]:
+        """Flatten the list to the specified depth."""
+        return _flatten_nested_list(items, max_depth=max_depth)
+
+    def _validate_max_depth(self, max_depth: int) -> str | None:
+        """Validate the max_depth parameter."""
+        if max_depth < -1:
+            return f"max_depth must be -1 (unlimited) or a non-negative integer, got {max_depth}"
+        return None
+
+    async def run(self, input_data: Input, **kwargs) -> BlockOutput:
+        # Validate max_depth
+        depth_error = self._validate_max_depth(input_data.max_depth)
+        if depth_error is not None:
+            yield "error", depth_error
+            return
+
+        original_depth = self._compute_depth(input_data.nested_list)
+        flattened = self._flatten(input_data.nested_list, input_data.max_depth)
+
+        yield "flattened_list", flattened
+        yield "length", len(flattened)
+        yield "original_depth", original_depth
+
+
+class InterleaveListsBlock(Block):
+    """
+    Interleaves elements from multiple lists in round-robin fashion.
+
+    Given multiple input lists, this block takes one element from each
+    list in turn, producing an output where elements alternate between
+    sources. Lists of different lengths are handled gracefully - shorter
+    lists simply stop contributing once exhausted.
+    """
+
+    class Input(BlockSchemaInput):
+        lists: List[List[Any]] = SchemaField(
+            description="A list of lists to interleave. Elements will be taken in round-robin order.",
+            placeholder="e.g., [[1, 2, 3], ['a', 'b', 'c']]",
+        )
+
+    class Output(BlockSchemaOutput):
+        interleaved_list: List[Any] = SchemaField(
+            description="The interleaved list with elements alternating from each input list."
+        )
+        length: int = SchemaField(
+            description="The total number of elements in the interleaved list."
+        )
+        error: str = SchemaField(description="Error message if interleaving failed.")
+
+    def __init__(self):
+        super().__init__(
+            id="9f616084-1d9f-4f8e-bc00-5b9d2a75cd75",
+            description="Interleaves elements from multiple lists in round-robin fashion, alternating between sources.",
+            categories={BlockCategory.BASIC},
+            input_schema=InterleaveListsBlock.Input,
+            output_schema=InterleaveListsBlock.Output,
+            test_input=[
+                {"lists": [[1, 2, 3], ["a", "b", "c"]]},
+                {"lists": [[1, 2, 3], ["a", "b"], ["x", "y", "z"]]},
+                {"lists": [[1], [2], [3]]},
+                {"lists": []},
+            ],
+            test_output=[
+                ("interleaved_list", [1, "a", 2, "b", 3, "c"]),
+                ("length", 6),
+                ("interleaved_list", [1, "a", "x", 2, "b", "y", 3, "z"]),
+                ("length", 8),
+                ("interleaved_list", [1, 2, 3]),
+                ("length", 3),
+                ("interleaved_list", []),
+                ("length", 0),
+            ],
+        )
+
+    def _validate_inputs(self, lists: List[Any]) -> str | None:
+        return _validate_all_lists(lists)
+
+    def _interleave(self, lists: List[List[Any]]) -> List[Any]:
+        return _interleave_lists(lists)
+
+    async def run(self, input_data: Input, **kwargs) -> BlockOutput:
+        validation_error = self._validate_inputs(input_data.lists)
+        if validation_error is not None:
+            yield "error", validation_error
+            return
+
+        result = self._interleave(input_data.lists)
+        yield "interleaved_list", result
+        yield "length", len(result)
+
+
+class ZipListsBlock(Block):
+    """
+    Zips multiple lists together into a list of grouped tuples/lists.
+
+    Takes two or more input lists and combines corresponding elements
+    into sub-lists. For example, zipping [1,2,3] and ['a','b','c']
+    produces [[1,'a'], [2,'b'], [3,'c']]. Supports both truncating
+    to shortest list and padding to longest list with a fill value.
+    """
+
+    class Input(BlockSchemaInput):
+        lists: List[List[Any]] = SchemaField(
+            description="A list of lists to zip together. Corresponding elements will be grouped.",
+            placeholder="e.g., [[1, 2, 3], ['a', 'b', 'c']]",
+        )
+        pad_to_longest: bool = SchemaField(
+            description="If True, pad shorter lists with fill_value to match the longest list. If False, truncate to shortest.",
+            default=False,
+            advanced=True,
+        )
+        fill_value: Any = SchemaField(
+            description="Value to use for padding when pad_to_longest is True.",
+            default=None,
+            advanced=True,
+        )
+
+    class Output(BlockSchemaOutput):
+        zipped_list: List[List[Any]] = SchemaField(
+            description="The zipped list of grouped elements."
+        )
+        length: int = SchemaField(
+            description="The number of groups in the zipped result."
+        )
+        error: str = SchemaField(description="Error message if zipping failed.")
+
+    def __init__(self):
+        super().__init__(
+            id="0d0e684f-5cb9-4c4b-b8d1-47a0860e0c07",
+            description="Zips multiple lists together into a list of grouped elements. Supports padding to longest or truncating to shortest.",
+            categories={BlockCategory.BASIC},
+            input_schema=ZipListsBlock.Input,
+            output_schema=ZipListsBlock.Output,
+            test_input=[
+                {"lists": [[1, 2, 3], ["a", "b", "c"]]},
+                {"lists": [[1, 2, 3], ["a", "b"]]},
+                {
+                    "lists": [[1, 2], ["a", "b", "c"]],
+                    "pad_to_longest": True,
+                    "fill_value": 0,
+                },
+                {"lists": []},
+            ],
+            test_output=[
+                ("zipped_list", [[1, "a"], [2, "b"], [3, "c"]]),
+                ("length", 3),
+                ("zipped_list", [[1, "a"], [2, "b"]]),
+                ("length", 2),
+                ("zipped_list", [[1, "a"], [2, "b"], [0, "c"]]),
+                ("length", 3),
+                ("zipped_list", []),
+                ("length", 0),
+            ],
+        )
+
+    def _validate_inputs(self, lists: List[Any]) -> str | None:
+        return _validate_all_lists(lists)
+
+    def _zip_truncate(self, lists: List[List[Any]]) -> List[List[Any]]:
+        """Zip lists, truncating to shortest."""
+        filtered = [lst for lst in lists if lst is not None]
+        if not filtered:
+            return []
+        return [list(group) for group in zip(*filtered)]
+
+    def _zip_pad(self, lists: List[List[Any]], fill_value: Any) -> List[List[Any]]:
+        """Zip lists, padding shorter ones with fill_value."""
+        if not lists:
+            return []
+        lists = [lst for lst in lists if lst is not None]
+        if not lists:
+            return []
+        max_len = max(len(lst) for lst in lists)
+        result: List[List[Any]] = []
+        for i in range(max_len):
+            group: List[Any] = []
+            for lst in lists:
+                if i < len(lst):
+                    group.append(lst[i])
+                else:
+                    group.append(fill_value)
+            result.append(group)
+        return result
+
+    async def run(self, input_data: Input, **kwargs) -> BlockOutput:
+        validation_error = self._validate_inputs(input_data.lists)
+        if validation_error is not None:
+            yield "error", validation_error
+            return
+
+        if not input_data.lists:
+            yield "zipped_list", []
+            yield "length", 0
+            return
+
+        if input_data.pad_to_longest:
+            result = self._zip_pad(input_data.lists, input_data.fill_value)
+        else:
+            result = self._zip_truncate(input_data.lists)
+
+        yield "zipped_list", result
+        yield "length", len(result)
+
+
+class ListDifferenceBlock(Block):
+    """
+    Computes the difference between two lists (elements in the first
+    list that are not in the second list).
+
+    This is useful for finding items that exist in one dataset but
+    not in another, such as finding new items, missing items, or
+    items that need to be processed.
+    """
+
+    class Input(BlockSchemaInput):
+        list_a: List[Any] = SchemaField(
+            description="The primary list to check elements from.",
+            placeholder="e.g., [1, 2, 3, 4, 5]",
+        )
+        list_b: List[Any] = SchemaField(
+            description="The list to subtract. Elements found here will be removed from list_a.",
+            placeholder="e.g., [3, 4, 5, 6]",
+        )
+        symmetric: bool = SchemaField(
+            description="If True, compute symmetric difference (elements in either list but not both).",
+            default=False,
+            advanced=True,
+        )
+
+    class Output(BlockSchemaOutput):
+        difference: List[Any] = SchemaField(
+            description="Elements from list_a not found in list_b (or symmetric difference if enabled)."
+        )
+        length: int = SchemaField(
+            description="The number of elements in the difference result."
+        )
+        error: str = SchemaField(description="Error message if the operation failed.")
+
+    def __init__(self):
+        super().__init__(
+            id="05309873-9d61-447e-96b5-b804e2511829",
+            description="Computes the difference between two lists. Returns elements in the first list not found in the second, or symmetric difference.",
+            categories={BlockCategory.BASIC},
+            input_schema=ListDifferenceBlock.Input,
+            output_schema=ListDifferenceBlock.Output,
+            test_input=[
+                {"list_a": [1, 2, 3, 4, 5], "list_b": [3, 4, 5, 6, 7]},
+                {
+                    "list_a": [1, 2, 3, 4, 5],
+                    "list_b": [3, 4, 5, 6, 7],
+                    "symmetric": True,
+                },
+                {"list_a": ["a", "b", "c"], "list_b": ["b"]},
+                {"list_a": [], "list_b": [1, 2, 3]},
+            ],
+            test_output=[
+                ("difference", [1, 2]),
+                ("length", 2),
+                ("difference", [1, 2, 6, 7]),
+                ("length", 4),
+                ("difference", ["a", "c"]),
+                ("length", 2),
+                ("difference", []),
+                ("length", 0),
+            ],
+        )
+
+    def _compute_difference(self, list_a: List[Any], list_b: List[Any]) -> List[Any]:
+        """Compute elements in list_a not in list_b."""
+        b_hashes = {_make_hashable(item) for item in list_b}
+        return [item for item in list_a if _make_hashable(item) not in b_hashes]
+
+    def _compute_symmetric_difference(
+        self, list_a: List[Any], list_b: List[Any]
+    ) -> List[Any]:
+        """Compute elements in either list but not both."""
+        a_hashes = {_make_hashable(item) for item in list_a}
+        b_hashes = {_make_hashable(item) for item in list_b}
+        only_in_a = [item for item in list_a if _make_hashable(item) not in b_hashes]
+        only_in_b = [item for item in list_b if _make_hashable(item) not in a_hashes]
+        return only_in_a + only_in_b
+
+    async def run(self, input_data: Input, **kwargs) -> BlockOutput:
+        if input_data.symmetric:
+            result = self._compute_symmetric_difference(
+                input_data.list_a, input_data.list_b
+            )
+        else:
+            result = self._compute_difference(input_data.list_a, input_data.list_b)
+
+        yield "difference", result
+        yield "length", len(result)
+
+
+class ListIntersectionBlock(Block):
+    """
+    Computes the intersection of two lists (elements present in both lists).
+
+    This is useful for finding common items between two datasets,
+    such as shared tags, mutual connections, or overlapping categories.
+    """
+
+    class Input(BlockSchemaInput):
+        list_a: List[Any] = SchemaField(
+            description="The first list to intersect.",
+            placeholder="e.g., [1, 2, 3, 4, 5]",
+        )
+        list_b: List[Any] = SchemaField(
+            description="The second list to intersect.",
+            placeholder="e.g., [3, 4, 5, 6, 7]",
+        )
+
+    class Output(BlockSchemaOutput):
+        intersection: List[Any] = SchemaField(
+            description="Elements present in both list_a and list_b."
+        )
+        length: int = SchemaField(
+            description="The number of elements in the intersection."
+        )
+        error: str = SchemaField(description="Error message if the operation failed.")
+
+    def __init__(self):
+        super().__init__(
+            id="b6eb08b6-dbe3-411b-b9b4-2508cb311a1f",
+            description="Computes the intersection of two lists, returning only elements present in both.",
+            categories={BlockCategory.BASIC},
+            input_schema=ListIntersectionBlock.Input,
+            output_schema=ListIntersectionBlock.Output,
+            test_input=[
+                {"list_a": [1, 2, 3, 4, 5], "list_b": [3, 4, 5, 6, 7]},
+                {"list_a": ["a", "b", "c"], "list_b": ["c", "d", "e"]},
+                {"list_a": [1, 2], "list_b": [3, 4]},
+                {"list_a": [], "list_b": [1, 2, 3]},
+            ],
+            test_output=[
+                ("intersection", [3, 4, 5]),
+                ("length", 3),
+                ("intersection", ["c"]),
+                ("length", 1),
+                ("intersection", []),
+                ("length", 0),
+                ("intersection", []),
+                ("length", 0),
+            ],
+        )
+
+    def _compute_intersection(self, list_a: List[Any], list_b: List[Any]) -> List[Any]:
+        """Compute elements present in both lists, preserving order from list_a."""
+        b_hashes = {_make_hashable(item) for item in list_b}
+        seen: set = set()
+        result: List[Any] = []
+        for item in list_a:
+            h = _make_hashable(item)
+            if h in b_hashes and h not in seen:
+                result.append(item)
+                seen.add(h)
+        return result
+
+    async def run(self, input_data: Input, **kwargs) -> BlockOutput:
+        result = self._compute_intersection(input_data.list_a, input_data.list_b)
+        yield "intersection", result
+        yield "length", len(result)

autogpt_platform/backend/backend/blocks/decoder_block.py

@@ -1,6 +1,6 @@
 import codecs
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

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

@@ -8,7 +8,7 @@ from typing import Any, Literal, cast
 import discord
 from pydantic import SecretStr
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/discord/oauth_blocks.py

@@ -2,7 +2,7 @@
 Discord OAuth-based blocks.
 """
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/email_block.py

@@ -7,7 +7,7 @@ from typing import Literal
 
 from pydantic import BaseModel, ConfigDict, SecretStr
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/encoder_block.py

@@ -2,7 +2,7 @@
 
 import codecs
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/enrichlayer/linkedin.py

@@ -8,7 +8,7 @@ which provides access to LinkedIn profile data and related information.
 import logging
 from typing import Optional
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

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

@@ -3,6 +3,13 @@ import logging
 from enum import Enum
 from typing import Any
 
+from backend.blocks._base import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
 from backend.blocks.fal._auth import (
     TEST_CREDENTIALS,
     TEST_CREDENTIALS_INPUT,
@@ -10,13 +17,6 @@ from backend.blocks.fal._auth import (
     FalCredentialsField,
     FalCredentialsInput,
 )
-from backend.data.block import (
-    Block,
-    BlockCategory,
-    BlockOutput,
-    BlockSchemaInput,
-    BlockSchemaOutput,
-)
 from backend.data.execution import ExecutionContext
 from backend.data.model import SchemaField
 from backend.util.file import store_media_file

autogpt_platform/backend/backend/blocks/flux_kontext.py

@@ -5,7 +5,7 @@ from pydantic import SecretStr
 from replicate.client import Client as ReplicateClient
 from replicate.helpers import FileOutput
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/github/checks.py

@@ -3,7 +3,7 @@ from typing import Optional
 
 from pydantic import BaseModel
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/github/ci.py

@@ -5,7 +5,7 @@ from typing import Optional
 
 from typing_extensions import TypedDict
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/github/issues.py

@@ -3,7 +3,7 @@ from urllib.parse import urlparse
 
 from typing_extensions import TypedDict
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/github/pull_requests.py

@@ -2,7 +2,7 @@ import re
 
 from typing_extensions import TypedDict
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/github/repo.py

@@ -2,7 +2,7 @@ import base64
 
 from typing_extensions import TypedDict
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/github/reviews.py

@@ -4,7 +4,7 @@ from typing import Any, List, Optional
 
 from typing_extensions import TypedDict
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/github/statuses.py

@@ -3,7 +3,7 @@ from typing import Optional
 
 from pydantic import BaseModel
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/github/triggers.py

@@ -4,7 +4,7 @@ from pathlib import Path
 
 from pydantic import BaseModel
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/google/calendar.py

@@ -8,7 +8,7 @@ from google.oauth2.credentials import Credentials
 from googleapiclient.discovery import build
 from pydantic import BaseModel
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/google/docs.py

@@ -7,14 +7,14 @@ from google.oauth2.credentials import Credentials
 from googleapiclient.discovery import build
 from gravitas_md2gdocs import to_requests
 
-from backend.blocks.google._drive import GoogleDriveFile, GoogleDriveFileField
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
     BlockSchemaInput,
     BlockSchemaOutput,
 )
+from backend.blocks.google._drive import GoogleDriveFile, GoogleDriveFileField
 from backend.data.model import SchemaField
 from backend.util.settings import Settings
 

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

@@ -14,7 +14,7 @@ from google.oauth2.credentials import Credentials
 from googleapiclient.discovery import build
 from pydantic import BaseModel, Field
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/google/sheets.py

@@ -7,14 +7,14 @@ from enum import Enum
 from google.oauth2.credentials import Credentials
 from googleapiclient.discovery import build
 
-from backend.blocks.google._drive import GoogleDriveFile, GoogleDriveFileField
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
     BlockSchemaInput,
     BlockSchemaOutput,
 )
+from backend.blocks.google._drive import GoogleDriveFile, GoogleDriveFileField
 from backend.data.model import SchemaField
 from backend.util.settings import Settings
 

autogpt_platform/backend/backend/blocks/google_maps.py

@@ -3,7 +3,7 @@ from typing import Literal
 import googlemaps
 from pydantic import BaseModel, SecretStr
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

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

@@ -9,9 +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.human_review import ReviewResult
-from backend.executor.manager import async_update_node_execution_status
 from backend.util.clients import get_database_manager_async_client
 
 logger = logging.getLogger(__name__)
@@ -43,6 +41,8 @@ class HITLReviewHelper:
     @staticmethod
     async def update_node_execution_status(**kwargs) -> None:
         """Update the execution status of a node."""
+        from backend.executor.manager import async_update_node_execution_status
+
         await async_update_node_execution_status(
             db_client=get_database_manager_async_client(), **kwargs
         )
@@ -88,12 +88,13 @@ class HITLReviewHelper:
         Raises:
             Exception: If review creation or status update fails
         """
+        from backend.data.execution import ExecutionStatus
+
         # 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,

autogpt_platform/backend/backend/blocks/http.py

@@ -8,7 +8,7 @@ from typing import Literal
 import aiofiles
 from pydantic import SecretStr
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/hubspot/company.py

@@ -1,15 +1,15 @@
-from backend.blocks.hubspot._auth import (
-    HubSpotCredentials,
-    HubSpotCredentialsField,
-    HubSpotCredentialsInput,
-)
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
     BlockSchemaInput,
     BlockSchemaOutput,
 )
+from backend.blocks.hubspot._auth import (
+    HubSpotCredentials,
+    HubSpotCredentialsField,
+    HubSpotCredentialsInput,
+)
 from backend.data.model import SchemaField
 from backend.util.request import Requests
 

autogpt_platform/backend/backend/blocks/hubspot/contact.py

@@ -1,15 +1,15 @@
-from backend.blocks.hubspot._auth import (
-    HubSpotCredentials,
-    HubSpotCredentialsField,
-    HubSpotCredentialsInput,
-)
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
     BlockSchemaInput,
     BlockSchemaOutput,
 )
+from backend.blocks.hubspot._auth import (
+    HubSpotCredentials,
+    HubSpotCredentialsField,
+    HubSpotCredentialsInput,
+)
 from backend.data.model import SchemaField
 from backend.util.request import Requests
 

autogpt_platform/backend/backend/blocks/hubspot/engagement.py

@@ -1,17 +1,17 @@
 from datetime import datetime, timedelta
 
-from backend.blocks.hubspot._auth import (
-    HubSpotCredentials,
-    HubSpotCredentialsField,
-    HubSpotCredentialsInput,
-)
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
     BlockSchemaInput,
     BlockSchemaOutput,
 )
+from backend.blocks.hubspot._auth import (
+    HubSpotCredentials,
+    HubSpotCredentialsField,
+    HubSpotCredentialsInput,
+)
 from backend.data.model import SchemaField
 from backend.util.request import Requests
 

autogpt_platform/backend/backend/blocks/human_in_the_loop.py

@@ -3,8 +3,7 @@ from typing import Any
 
 from prisma.enums import ReviewStatus
 
-from backend.blocks.helpers.review import HITLReviewHelper
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
@@ -12,6 +11,7 @@ from backend.data.block import (
     BlockSchemaOutput,
     BlockType,
 )
+from backend.blocks.helpers.review import HITLReviewHelper
 from backend.data.execution import ExecutionContext
 from backend.data.human_review import ReviewResult
 from backend.data.model import SchemaField
@@ -21,43 +21,71 @@ logger = logging.getLogger(__name__)
 
 class HumanInTheLoopBlock(Block):
     """
-    This block pauses execution and waits for human approval or modification of the data.
+    Pauses execution and waits for human approval or rejection of the data.
 
-    When executed, it creates a pending review entry and sets the node execution status
-    to REVIEW. The execution will remain paused until a human user either:
-    - Approves the data (with or without modifications)
-    - Rejects the data
+    When executed, this block creates a pending review entry and sets the node execution
+    status to REVIEW. The execution remains paused until a human user either approves
+    or rejects the data.
 
-    This is useful for workflows that require human validation or intervention before
-    proceeding to the next steps.
+    **How it works:**
+    - The input data is presented to a human reviewer
+    - The reviewer can approve or reject (and optionally modify the data if editable)
+    - On approval: the data flows out through the `approved_data` output pin
+    - On rejection: the data flows out through the `rejected_data` output pin
+
+    **Important:** The output pins yield the actual data itself, NOT status strings.
+    The approval/rejection decision determines WHICH output pin fires, not the value.
+    You do NOT need to compare the output to "APPROVED" or "REJECTED" - simply connect
+    downstream blocks to the appropriate output pin for each case.
+
+    **Example usage:**
+    - Connect `approved_data` → next step in your workflow (data was approved)
+    - Connect `rejected_data` → error handling or notification (data was rejected)
     """
 
     class Input(BlockSchemaInput):
-        data: Any = SchemaField(description="The data to be reviewed by a human user")
+        data: Any = SchemaField(
+            description="The data to be reviewed by a human user. "
+            "This exact data will be passed through to either approved_data or "
+            "rejected_data output based on the reviewer's decision."
+        )
         name: str = SchemaField(
-            description="A descriptive name for what this data represents",
+            description="A descriptive name for what this data represents. "
+            "This helps the reviewer understand what they are reviewing.",
         )
         editable: bool = SchemaField(
-            description="Whether the human reviewer can edit the data",
+            description="Whether the human reviewer can edit the data before "
+            "approving or rejecting it",
             default=True,
             advanced=True,
         )
 
     class Output(BlockSchemaOutput):
         approved_data: Any = SchemaField(
-            description="The data when approved (may be modified by reviewer)"
+            description="Outputs the input data when the reviewer APPROVES it. "
+            "The value is the actual data itself (not a status string like 'APPROVED'). "
+            "If the reviewer edited the data, this contains the modified version. "
+            "Connect downstream blocks here for the 'approved' workflow path."
         )
         rejected_data: Any = SchemaField(
-            description="The data when rejected (may be modified by reviewer)"
+            description="Outputs the input data when the reviewer REJECTS it. "
+            "The value is the actual data itself (not a status string like 'REJECTED'). "
+            "If the reviewer edited the data, this contains the modified version. "
+            "Connect downstream blocks here for the 'rejected' workflow path."
         )
         review_message: str = SchemaField(
-            description="Any message provided by the reviewer", default=""
+            description="Optional message provided by the reviewer explaining their "
+            "decision. Only outputs when the reviewer provides a message; "
+            "this pin does not fire if no message was given.",
+            default="",
         )
 
     def __init__(self):
         super().__init__(
             id="8b2a7b3c-6e9d-4a5f-8c1b-2e3f4a5b6c7d",
-            description="Pause execution and wait for human approval or modification of data",
+            description="Pause execution for human review. Data flows through "
+            "approved_data or rejected_data output based on the reviewer's decision. "
+            "Outputs contain the actual data, not status strings.",
             categories={BlockCategory.BASIC},
             input_schema=HumanInTheLoopBlock.Input,
             output_schema=HumanInTheLoopBlock.Output,

autogpt_platform/backend/backend/blocks/ideogram.py

@@ -3,7 +3,7 @@ from typing import Any, Dict, Literal, Optional
 
 from pydantic import SecretStr
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/io.py

@@ -2,9 +2,7 @@ import copy
 from datetime import date, time
 from typing import Any, Optional
 
-# Import for Google Drive file input block
-from backend.blocks.google._drive import AttachmentView, GoogleDriveFile
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
@@ -12,6 +10,9 @@ from backend.data.block import (
     BlockSchemaInput,
     BlockType,
 )
+
+# Import for Google Drive file input block
+from backend.blocks.google._drive import AttachmentView, GoogleDriveFile
 from backend.data.execution import ExecutionContext
 from backend.data.model import SchemaField
 from backend.util.file import store_media_file

autogpt_platform/backend/backend/blocks/iteration.py

@@ -1,6 +1,6 @@
 from typing import Any
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,

autogpt_platform/backend/backend/blocks/jina/chunking.py

@@ -1,15 +1,15 @@
-from backend.blocks.jina._auth import (
-    JinaCredentials,
-    JinaCredentialsField,
-    JinaCredentialsInput,
-)
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
     BlockSchemaInput,
     BlockSchemaOutput,
 )
+from backend.blocks.jina._auth import (
+    JinaCredentials,
+    JinaCredentialsField,
+    JinaCredentialsInput,
+)
 from backend.data.model import SchemaField
 from backend.util.request import Requests
 

autogpt_platform/backend/backend/blocks/jina/embeddings.py

@@ -1,15 +1,15 @@
-from backend.blocks.jina._auth import (
-    JinaCredentials,
-    JinaCredentialsField,
-    JinaCredentialsInput,
-)
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
     BlockSchemaInput,
     BlockSchemaOutput,
 )
+from backend.blocks.jina._auth import (
+    JinaCredentials,
+    JinaCredentialsField,
+    JinaCredentialsInput,
+)
 from backend.data.model import SchemaField
 from backend.util.request import Requests
 

autogpt_platform/backend/backend/blocks/jina/fact_checker.py

@@ -3,18 +3,18 @@ from urllib.parse import quote
 
 from typing_extensions import TypedDict
 
-from backend.blocks.jina._auth import (
-    JinaCredentials,
-    JinaCredentialsField,
-    JinaCredentialsInput,
-)
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,
     BlockSchemaInput,
     BlockSchemaOutput,
 )
+from backend.blocks.jina._auth import (
+    JinaCredentials,
+    JinaCredentialsField,
+    JinaCredentialsInput,
+)
 from backend.data.model import SchemaField
 from backend.util.request import Requests
 

autogpt_platform/backend/backend/blocks/jina/search.py

@@ -1,5 +1,12 @@
 from urllib.parse import quote
 
+from backend.blocks._base import (
+    Block,
+    BlockCategory,
+    BlockOutput,
+    BlockSchemaInput,
+    BlockSchemaOutput,
+)
 from backend.blocks.jina._auth import (
     TEST_CREDENTIALS,
     TEST_CREDENTIALS_INPUT,
@@ -8,15 +15,9 @@ from backend.blocks.jina._auth import (
     JinaCredentialsInput,
 )
 from backend.blocks.search import GetRequest
-from backend.data.block import (
-    Block,
-    BlockCategory,
-    BlockOutput,
-    BlockSchemaInput,
-    BlockSchemaOutput,
-)
 from backend.data.model import SchemaField
 from backend.util.exceptions import BlockExecutionError
+from backend.util.request import HTTPClientError, HTTPServerError, validate_url
 
 
 class SearchTheWebBlock(Block, GetRequest):
@@ -110,7 +111,12 @@ class ExtractWebsiteContentBlock(Block, GetRequest):
         self, input_data: Input, *, credentials: JinaCredentials, **kwargs
     ) -> BlockOutput:
         if input_data.raw_content:
-            url = input_data.url
+            try:
+                parsed_url, _, _ = await validate_url(input_data.url, [])
+                url = parsed_url.geturl()
+            except ValueError as e:
+                yield "error", f"Invalid URL: {e}"
+                return
             headers = {}
         else:
             url = f"https://r.jina.ai/{input_data.url}"
@@ -119,5 +125,20 @@ class ExtractWebsiteContentBlock(Block, GetRequest):
                 "Authorization": f"Bearer {credentials.api_key.get_secret_value()}",
             }
 
-        content = await self.get_request(url, json=False, headers=headers)
+        try:
+            content = await self.get_request(url, json=False, headers=headers)
+        except HTTPClientError as e:
+            yield "error", f"Client error ({e.status_code}) fetching {input_data.url}: {e}"
+            return
+        except HTTPServerError as e:
+            yield "error", f"Server error ({e.status_code}) fetching {input_data.url}: {e}"
+            return
+        except Exception as e:
+            yield "error", f"Failed to fetch {input_data.url}: {e}"
+            return
+
+        if not content:
+            yield "error", f"No content returned for {input_data.url}"
+            return
+
         yield "content", content

autogpt_platform/backend/backend/blocks/llm.py

@@ -15,7 +15,7 @@ from anthropic.types import ToolParam
 from groq import AsyncGroq
 from pydantic import BaseModel, SecretStr
 
-from backend.data.block import (
+from backend.blocks._base import (
     Block,
     BlockCategory,
     BlockOutput,