chore(libs/deps-dev): bump pytest in /autogpt_platform/autogpt_libs

Bumps [pytest](https://github.com/pytest-dev/pytest) from 8.4.1 to 9.0.2. - [Release notes](https://github.com/pytest-dev/pytest/releases) - [Changelog](https://github.com/pytest-dev/pytest/blob/main/CHANGELOG.rst) - [Commits](https://github.com/pytest-dev/pytest/compare/8.4.1...9.0.2) --- updated-dependencies: - dependency-name: pytest dependency-version: 9.0.2 dependency-type: direct:development update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com>
2026-02-18 10:41:49 -05:00 · 2026-02-13 09:27:36 +00:00
231 changed files with 4477 additions and 20578 deletions
--- a/.dockerignore
+++ b/.dockerignore
@@ -5,13 +5,42 @@
 !docs/

 # Platform - Libs
-!autogpt_platform/autogpt_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

 # Platform - Backend
-!autogpt_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

 # Platform - Frontend
-!autogpt_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

 # Classic - AutoGPT
 !classic/original_autogpt/autogpt/
@@ -35,38 +64,6 @@
 # Classic - Frontend
 !classic/frontend/build/web/

-# 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
+# Explicitly re-ignore some folders
+.*
+**/__pycache__
--- a/.github/scripts/detect_overlaps.py
+++ b/.github/scripts/detect_overlaps.py
--- a/.github/workflows/claude-ci-failure-auto-fix.yml
+++ b/.github/workflows/claude-ci-failure-auto-fix.yml
@@ -40,48 +40,6 @@ 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
--- a/.github/workflows/claude-dependabot.yml
+++ b/.github/workflows/claude-dependabot.yml
@@ -77,15 +77,27 @@ 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"
-          cache: "pnpm"
-          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
+
+      - 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-

      - name: Install JavaScript dependencies
        working-directory: autogpt_platform/frontend
--- a/.github/workflows/claude.yml
+++ b/.github/workflows/claude.yml
@@ -93,15 +93,27 @@ 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"
-          cache: "pnpm"
-          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
+
+      - 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-

      - name: Install JavaScript dependencies
        working-directory: autogpt_platform/frontend
--- a/.github/workflows/codeql.yml
+++ b/.github/workflows/codeql.yml
@@ -62,7 +62,7 @@ jobs:

    # Initializes the CodeQL tools for scanning.
    - name: Initialize CodeQL
-      uses: github/codeql-action/init@v4
+      uses: github/codeql-action/init@v3
      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@v4
+      uses: github/codeql-action/analyze@v3
      with:
        category: "/language:${{matrix.language}}"
--- a/.github/workflows/docs-claude-review.yml
+++ b/.github/workflows/docs-claude-review.yml
@@ -7,10 +7,6 @@ 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
@@ -95,35 +91,5 @@ 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
--- a/.github/workflows/platform-backend-ci.yml
+++ b/.github/workflows/platform-backend-ci.yml
@@ -41,18 +41,13 @@ jobs:
        ports:
          - 6379:6379
      rabbitmq:
-        image: rabbitmq:4.1.4
+        image: rabbitmq:3.12-management
        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:
--- a/.github/workflows/platform-frontend-ci.yml
+++ b/.github/workflows/platform-frontend-ci.yml
@@ -6,16 +6,10 @@ 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:

@@ -32,6 +26,7 @@ jobs:
  setup:
    runs-on: ubuntu-latest
    outputs:
+      cache-key: ${{ steps.cache-key.outputs.key }}
      components-changed: ${{ steps.filter.outputs.components }}

    steps:
@@ -46,17 +41,28 @@ jobs:
            components:
              - 'autogpt_platform/frontend/src/components/**'

-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Set up Node
+      - name: Set up Node.js
        uses: actions/setup-node@v6
        with:
          node-version: "22.18.0"
-          cache: "pnpm"
-          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml

-      - name: Install dependencies to populate cache
+      - 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
+        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-
+
+      - name: Install dependencies
        run: pnpm install --frozen-lockfile

  lint:
@@ -67,15 +73,22 @@ jobs:
      - name: Checkout repository
        uses: actions/checkout@v6

-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Set up Node
+      - name: Set up Node.js
        uses: actions/setup-node@v6
        with:
          node-version: "22.18.0"
-          cache: "pnpm"
-          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
+
+      - name: Enable corepack
+        run: corepack enable
+
+      - name: Restore dependencies cache
+        uses: actions/cache@v5
+        with:
+          path: ~/.pnpm-store
+          key: ${{ needs.setup.outputs.cache-key }}
+          restore-keys: |
+            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
+            ${{ runner.os }}-pnpm-

      - name: Install dependencies
        run: pnpm install --frozen-lockfile
@@ -98,15 +111,22 @@ jobs:
        with:
          fetch-depth: 0

-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Set up Node
+      - name: Set up Node.js
        uses: actions/setup-node@v6
        with:
          node-version: "22.18.0"
-          cache: "pnpm"
-          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
+
+      - name: Enable corepack
+        run: corepack enable
+
+      - name: Restore dependencies cache
+        uses: actions/cache@v5
+        with:
+          path: ~/.pnpm-store
+          key: ${{ needs.setup.outputs.cache-key }}
+          restore-keys: |
+            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
+            ${{ runner.os }}-pnpm-

      - name: Install dependencies
        run: pnpm install --frozen-lockfile
@@ -121,8 +141,10 @@ jobs:
          exitOnceUploaded: true

  e2e_test:
-    name: end-to-end tests
    runs-on: big-boi
+    needs: setup
+    strategy:
+      fail-fast: false

    steps:
      - name: Checkout repository
@@ -130,11 +152,19 @@ jobs:
        with:
          submodules: recursive

-      - name: Set up Platform - Copy default supabase .env
+      - 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
        run: |
          cp ../.env.default ../.env

-      - name: Set up Platform - Copy backend .env and set OpenAI API key
+      - name: 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
@@ -142,125 +172,77 @@ jobs:
          # Used by E2E test data script to generate embeddings for approved store agents
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

-      - name: Set up Platform - Set up Docker Buildx
+      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v3
-        with:
-          driver: docker-container
-          driver-opts: network=host

-      - 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 "${{ github.ref }}"
-
-          # Build with bake using the resolved compose file (now includes cache config)
-          docker buildx bake --allow=fs.read=.. -f docker-compose.resolved.yml --load
-        env:
-          NEXT_PUBLIC_PW_TEST: true
-
-      - name: Set up tests - Cache E2E test data
-        id: e2e-data-cache
+      - name: Cache Docker layers
        uses: actions/cache@v5
        with:
-          path: /tmp/e2e_test_data.sql
-          key: e2e-test-data-${{ hashFiles('autogpt_platform/backend/test/e2e_test_data.py', 'autogpt_platform/backend/migrations/**', '.github/workflows/platform-frontend-ci.yml') }}
+          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-

-      - name: Set up Platform - Start Supabase DB + Auth
+      - name: Run docker compose
        run: |
-          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"
+          NEXT_PUBLIC_PW_TEST=true docker compose -f ../docker-compose.yml up -d
        env:
-          NEXT_PUBLIC_PW_TEST: true
+          DOCKER_BUILDKIT: 1
+          BUILDX_CACHE_FROM: type=local,src=/tmp/.buildx-cache
+          BUILDX_CACHE_TO: type=local,dest=/tmp/.buildx-cache-new,mode=max

-      - name: Set up tests - Load cached E2E test data
-        if: steps.e2e-data-cache.outputs.cache-hit == 'true'
+      - name: Move cache
        run: |
-          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
+          rm -rf /tmp/.buildx-cache
+          if [ -d "/tmp/.buildx-cache-new" ]; then
+            mv /tmp/.buildx-cache-new /tmp/.buildx-cache
+          fi

-          echo "✅ E2E test data restored from cache"
-
-      - name: Set up Platform - Start (all other services)
+      - name: Wait for services to be ready
        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..."
-        env:
-          NEXT_PUBLIC_PW_TEST: true
+          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..."

-      - name: Set up tests - Create E2E test data
-        if: steps.e2e-data-cache.outputs.cache-hit != 'true'
+      - name: Create E2E test data
        run: |
          echo "Creating E2E test data..."
-          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
-          }
+          # 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

-          # 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
+      - name: Restore dependencies cache
+        uses: actions/cache@v5
        with:
-          node-version: "22.18.0"
-          cache: "pnpm"
-          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
+          path: ~/.pnpm-store
+          key: ${{ needs.setup.outputs.cache-key }}
+          restore-keys: |
+            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
+            ${{ runner.os }}-pnpm-

-      - name: Set up tests - Install dependencies
+      - name: Install dependencies
        run: pnpm install --frozen-lockfile

-      - name: Set up tests - Install browser 'chromium'
+      - name: Install Browser 'chromium'
        run: pnpm playwright install --with-deps chromium

      - name: Run Playwright tests
@@ -287,7 +269,7 @@ jobs:

      - name: Print Final Docker Compose logs
        if: always()
-        run: docker compose -f ../docker-compose.resolved.yml logs
+        run: docker compose -f ../docker-compose.yml logs

  integration_test:
    runs-on: ubuntu-latest
@@ -299,15 +281,22 @@ jobs:
        with:
          submodules: recursive

-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Set up Node
+      - name: Set up Node.js
        uses: actions/setup-node@v6
        with:
          node-version: "22.18.0"
-          cache: "pnpm"
-          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
+
+      - name: Enable corepack
+        run: corepack enable
+
+      - name: Restore dependencies cache
+        uses: actions/cache@v5
+        with:
+          path: ~/.pnpm-store
+          key: ${{ needs.setup.outputs.cache-key }}
+          restore-keys: |
+            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
+            ${{ runner.os }}-pnpm-

      - name: Install dependencies
        run: pnpm install --frozen-lockfile
--- a/.github/workflows/pr-overlap-check.yml
+++ b/.github/workflows/pr-overlap-check.yml
@@ -1,39 +0,0 @@
-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 }}
--- a/.github/workflows/scripts/docker-ci-fix-compose-build-cache.py
+++ b/.github/workflows/scripts/docker-ci-fix-compose-build-cache.py
@@ -1,195 +0,0 @@
-#!/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()
--- a/autogpt_platform/CLAUDE.md
+++ b/autogpt_platform/CLAUDE.md
@@ -45,11 +45,6 @@ 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.
--- a/autogpt_platform/autogpt_libs/poetry.lock
+++ b/autogpt_platform/autogpt_libs/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand.

 [[package]]
 name = "annotated-doc"
@@ -67,7 +67,7 @@ description = "Backport of asyncio.Runner, a context manager that controls event
 optional = false
 python-versions = "<3.11,>=3.8"
 groups = ["dev"]
-markers = "python_version < \"3.11\""
+markers = "python_version == \"3.10\""
 files = [
    {file = "backports_asyncio_runner-1.2.0-py3-none-any.whl", hash = "sha256:0da0a936a8aeb554eccb426dc55af3ba63bcdc69fa1a600b5bb305413a4477b5"},
    {file = "backports_asyncio_runner-1.2.0.tar.gz", hash = "sha256:a5aa7b2b7d8f8bfcaa2b57313f70792df84e32a2a746f585213373f900b42162"},
@@ -541,7 +541,7 @@ description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
 groups = ["main", "dev"]
-markers = "python_version < \"3.11\""
+markers = "python_version == \"3.10\""
 files = [
    {file = "exceptiongroup-1.3.0-py3-none-any.whl", hash = "sha256:4d111e6e0c13d0644cad6ddaa7ed0261a0b36971f6d23e7ec9b4b9097da78a10"},
    {file = "exceptiongroup-1.3.0.tar.gz", hash = "sha256:b241f5885f560bc56a59ee63ca4c6a8bfa46ae4ad651af316d4e81817bb9fd88"},
@@ -2136,21 +2136,21 @@ files = [

 [[package]]
 name = "pytest"
-version = "8.4.1"
+version = "9.0.2"
 description = "pytest: simple powerful testing with Python"
 optional = false
-python-versions = ">=3.9"
+python-versions = ">=3.10"
 groups = ["dev"]
 files = [
-    {file = "pytest-8.4.1-py3-none-any.whl", hash = "sha256:539c70ba6fcead8e78eebbf1115e8b589e7565830d7d006a8723f19ac8a0afb7"},
-    {file = "pytest-8.4.1.tar.gz", hash = "sha256:7c67fd69174877359ed9371ec3af8a3d2b04741818c51e5e99cc1742251fa93c"},
+    {file = "pytest-9.0.2-py3-none-any.whl", hash = "sha256:711ffd45bf766d5264d487b917733b453d917afd2b0ad65223959f59089f875b"},
+    {file = "pytest-9.0.2.tar.gz", hash = "sha256:75186651a92bd89611d1d9fc20f0b4345fd827c41ccd5c299a868a05d70edf11"},
 ]

 [package.dependencies]
 colorama = {version = ">=0.4", markers = "sys_platform == \"win32\""}
 exceptiongroup = {version = ">=1", markers = "python_version < \"3.11\""}
-iniconfig = ">=1"
-packaging = ">=20"
+iniconfig = ">=1.0.1"
+packaging = ">=22"
 pluggy = ">=1.5,<2"
 pygments = ">=2.7.2"
 tomli = {version = ">=1", markers = "python_version < \"3.11\""}
@@ -2564,7 +2564,7 @@ description = "A lil' TOML parser"
 optional = false
 python-versions = ">=3.8"
 groups = ["dev"]
-markers = "python_version < \"3.11\""
+markers = "python_version == \"3.10\""
 files = [
    {file = "tomli-2.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:678e4fa69e4575eb77d103de3df8a895e1591b48e740211bd1067378c69e8249"},
    {file = "tomli-2.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:023aa114dd824ade0100497eb2318602af309e5a55595f76b626d6d9f3b7b0a6"},
@@ -2912,4 +2912,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<4.0"
-content-hash = "9619cae908ad38fa2c48016a58bcf4241f6f5793aa0e6cc140276e91c433cbbb"
+content-hash = "eee4c8907bfb10c44241b2f555de2860809286d1a90251918544bb0b4852de8c"
--- a/autogpt_platform/autogpt_libs/pyproject.toml
+++ b/autogpt_platform/autogpt_libs/pyproject.toml
@@ -23,7 +23,7 @@ uvicorn = "^0.40.0"

 [tool.poetry.group.dev.dependencies]
 pyright = "^1.1.408"
-pytest = "^8.4.1"
+pytest = "^9.0.2"
 pytest-asyncio = "^1.3.0"
 pytest-mock = "^3.15.1"
 pytest-cov = "^7.0.0"
--- a/autogpt_platform/backend/.env.default
+++ b/autogpt_platform/backend/.env.default
@@ -104,12 +104,6 @@ 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=

--- a/autogpt_platform/backend/Dockerfile
+++ b/autogpt_platform/backend/Dockerfile
@@ -1,5 +1,3 @@
-# ============================ DEPENDENCY BUILDER ============================ #
-
 FROM debian:13-slim AS builder

 # Set environment variables
@@ -53,62 +51,27 @@ 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

-# =============================== 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
+FROM debian:13-slim AS server_dependencies

 WORKDIR /app

-ENV DEBIAN_FRONTEND=noninteractive
+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

-# 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 \
+# Install Python, FFmpeg, and ImageMagick (required for video processing blocks)
+RUN apt-get update && apt-get install -y \
    python3.13 \
    python3-pip \
    ffmpeg \
    imagemagick \
-    jq \
-    ripgrep \
-    tree \
-    bubblewrap \
    && rm -rf /var/lib/apt/lists/*

-# Copy poetry (build-time only, for `poetry install --only-root` to create entry points)
+# Copy only necessary files from builder
+COPY --from=builder /app /app
 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
@@ -118,25 +81,30 @@ 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

-WORKDIR /app/autogpt_platform/backend
-
-# 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"

-# 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 ./
+RUN mkdir -p /app/autogpt_platform/autogpt_libs
+RUN mkdir -p /app/autogpt_platform/backend

-# Copy backend code + docs (for Copilot docs search)
-COPY 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
+
+# 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
+
+FROM server_dependencies AS server
+
+COPY autogpt_platform/backend /app/autogpt_platform/backend
 COPY docs /app/docs
-# 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
+RUN poetry install --no-ansi --only-root

 ENV PORT=8000

-CMD ["rest"]
+CMD ["poetry", "run", "rest"]
--- a/autogpt_platform/backend/backend/api/conftest.py
+++ b/autogpt_platform/backend/backend/api/conftest.py
@@ -1,9 +1,4 @@
-"""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.
-"""
+"""Common test fixtures for server tests."""

 import pytest
 from pytest_snapshot.plugin import Snapshot
@@ -16,6 +11,54 @@ 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."""
--- a/autogpt_platform/backend/backend/api/external/v1/tools.py
+++ b/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.copilot.model import ChatSession
-from backend.copilot.tools import find_agent_tool, run_agent_tool
-from backend.copilot.tools.models import ToolResponseBase
+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.data.auth.base import APIAuthorizationInfo

 logger = logging.getLogger(__name__)
--- a/autogpt_platform/backend/backend/api/features/chat/completion_consumer.py
+++ b/autogpt_platform/backend/backend/api/features/chat/completion_consumer.py
@@ -37,10 +37,12 @@ stale pending messages from dead consumers.

 import asyncio
 import logging
+import os
 import uuid
 from typing import Any

 import orjson
+from prisma import Prisma
 from pydantic import BaseModel
 from redis.exceptions import ResponseError

@@ -67,8 +69,8 @@ class OperationCompleteMessage(BaseModel):
 class ChatCompletionConsumer:
    """Consumer for chat operation completion messages from Redis Streams.

-    Database operations are handled through the chat_db() accessor, which
-    routes through DatabaseManager RPC when Prisma is not directly connected.
+    This consumer initializes its own Prisma client in start() to ensure
+    database operations work correctly within this async context.

    Uses Redis consumer groups to allow multiple platform pods to consume
    messages reliably with automatic redelivery on failure.
@@ -77,6 +79,7 @@ class ChatCompletionConsumer:
    def __init__(self):
        self._consumer_task: asyncio.Task | None = None
        self._running = False
+        self._prisma: Prisma | None = None
        self._consumer_name = f"consumer-{uuid.uuid4().hex[:8]}"

    async def start(self) -> None:
@@ -112,6 +115,15 @@ class ChatCompletionConsumer:
            f"Chat completion consumer started (consumer: {self._consumer_name})"
        )

+    async def _ensure_prisma(self) -> Prisma:
+        """Lazily initialize Prisma client on first use."""
+        if self._prisma is None:
+            database_url = os.getenv("DATABASE_URL", "postgresql://localhost:5432")
+            self._prisma = Prisma(datasource={"url": database_url})
+            await self._prisma.connect()
+            logger.info("[COMPLETION] Consumer Prisma client connected (lazy init)")
+        return self._prisma
+
    async def stop(self) -> None:
        """Stop the completion consumer."""
        self._running = False
@@ -124,6 +136,11 @@ class ChatCompletionConsumer:
                pass
            self._consumer_task = None

+        if self._prisma:
+            await self._prisma.disconnect()
+            self._prisma = None
+            logger.info("[COMPLETION] Consumer Prisma client disconnected")
+
        logger.info("Chat completion consumer stopped")

    async def _consume_messages(self) -> None:
@@ -235,7 +252,7 @@ class ChatCompletionConsumer:
            # XAUTOCLAIM after min_idle_time expires

    async def _handle_message(self, body: bytes) -> None:
-        """Handle a completion message."""
+        """Handle a completion message using our own Prisma client."""
        try:
            data = orjson.loads(body)
            message = OperationCompleteMessage(**data)
@@ -285,7 +302,8 @@ class ChatCompletionConsumer:
        message: OperationCompleteMessage,
    ) -> None:
        """Handle successful operation completion."""
-        await process_operation_success(task, message.result)
+        prisma = await self._ensure_prisma()
+        await process_operation_success(task, message.result, prisma)

    async def _handle_failure(
        self,
@@ -293,7 +311,8 @@ class ChatCompletionConsumer:
        message: OperationCompleteMessage,
    ) -> None:
        """Handle failed operation completion."""
-        await process_operation_failure(task, message.error)
+        prisma = await self._ensure_prisma()
+        await process_operation_failure(task, message.error, prisma)


 # Module-level consumer instance
--- a/autogpt_platform/backend/backend/api/features/chat/completion_handler.py
+++ b/autogpt_platform/backend/backend/api/features/chat/completion_handler.py
@@ -9,8 +9,7 @@ import logging
 from typing import Any

 import orjson
-
-from backend.data.db_accessors import chat_db
+from prisma import Prisma

 from . import service as chat_service
 from . import stream_registry
@@ -73,40 +72,48 @@ async def _update_tool_message(
    session_id: str,
    tool_call_id: str,
    content: str,
+    prisma_client: Prisma | None,
 ) -> None:
-    """Update tool message in database using the chat_db accessor.
-
-    Routes through DatabaseManager RPC when Prisma is not directly
-    connected (e.g. in the CoPilot Executor microservice).
+    """Update tool message in database.

    Args:
        session_id: The session ID
        tool_call_id: The tool call ID to update
        content: The new content for the message
+        prisma_client: Optional Prisma client. If None, uses chat_service.

    Raises:
-        ToolMessageUpdateError: If the database update fails.
+        ToolMessageUpdateError: If the database update fails. The caller should
+            handle this to avoid marking the task as completed with inconsistent state.
    """
    try:
-        updated = await chat_db().update_tool_message_content(
-            session_id=session_id,
-            tool_call_id=tool_call_id,
-            new_content=content,
-        )
-        if not updated:
-            raise ToolMessageUpdateError(
-                f"No message found with tool_call_id="
-                f"{tool_call_id} in session {session_id}"
+        if prisma_client:
+            # Use provided Prisma client (for consumer with its own connection)
+            updated_count = await prisma_client.chatmessage.update_many(
+                where={
+                    "sessionId": session_id,
+                    "toolCallId": tool_call_id,
+                },
+                data={"content": content},
+            )
+            # Check if any rows were updated - 0 means message not found
+            if updated_count == 0:
+                raise ToolMessageUpdateError(
+                    f"No message found with tool_call_id={tool_call_id} in session {session_id}"
+                )
+        else:
+            # Use service function (for webhook endpoint)
+            await chat_service._update_pending_operation(
+                session_id=session_id,
+                tool_call_id=tool_call_id,
+                result=content,
            )
    except ToolMessageUpdateError:
        raise
    except Exception as e:
-        logger.error(
-            f"[COMPLETION] Failed to update tool message: {e}",
-            exc_info=True,
-        )
+        logger.error(f"[COMPLETION] Failed to update tool message: {e}", exc_info=True)
        raise ToolMessageUpdateError(
-            f"Failed to update tool message for tool call #{tool_call_id}: {e}"
+            f"Failed to update tool message for tool_call_id={tool_call_id}: {e}"
        ) from e


@@ -195,6 +202,7 @@ async def _save_agent_from_result(
 async def process_operation_success(
    task: stream_registry.ActiveTask,
    result: dict | str | None,
+    prisma_client: Prisma | None = None,
 ) -> None:
    """Handle successful operation completion.

@@ -204,10 +212,12 @@ async def process_operation_success(
    Args:
        task: The active task that completed
        result: The result data from the operation
+        prisma_client: Optional Prisma client for database operations.
+            If None, uses chat_service._update_pending_operation instead.

    Raises:
-        ToolMessageUpdateError: If the database update fails. The task
-            will be marked as failed instead of completed.
+        ToolMessageUpdateError: If the database update fails. The task will be
+            marked as failed instead of completed to avoid inconsistent state.
    """
    # For agent generation tools, save the agent to library
    if task.tool_name in AGENT_GENERATION_TOOLS and isinstance(result, dict):
@@ -240,6 +250,7 @@ async def process_operation_success(
            session_id=task.session_id,
            tool_call_id=task.tool_call_id,
            content=result_str,
+            prisma_client=prisma_client,
        )
    except ToolMessageUpdateError:
        # DB update failed - mark task as failed to avoid inconsistent state
@@ -282,15 +293,18 @@ async def process_operation_success(
 async def process_operation_failure(
    task: stream_registry.ActiveTask,
    error: str | None,
+    prisma_client: Prisma | None = None,
 ) -> None:
    """Handle failed operation completion.

-    Publishes the error to the stream registry, updates the database
-    with the error response, and marks the task as failed.
+    Publishes the error to the stream registry, updates the database with
+    the error response, and marks the task as failed.

    Args:
        task: The active task that failed
        error: The error message from the operation
+        prisma_client: Optional Prisma client for database operations.
+            If None, uses chat_service._update_pending_operation instead.
    """
    error_msg = error or "Operation failed"

@@ -311,6 +325,7 @@ async def process_operation_failure(
            session_id=task.session_id,
            tool_call_id=task.tool_call_id,
            content=error_response.model_dump_json(),
+            prisma_client=prisma_client,
        )
    except ToolMessageUpdateError:
        # DB update failed - log but continue with cleanup
--- a/autogpt_platform/backend/backend/api/features/chat/config.py
+++ b/autogpt_platform/backend/backend/api/features/chat/config.py
@@ -27,11 +27,12 @@ class ChatConfig(BaseSettings):
    session_ttl: int = Field(default=43200, description="Session TTL in seconds")

    # Streaming Configuration
-    stream_timeout: int = Field(default=300, description="Stream timeout in seconds")
-    max_retries: int = Field(
-        default=3,
-        description="Max retries for fallback path (SDK handles retries internally)",
+    max_context_messages: int = Field(
+        default=50, ge=1, le=200, description="Maximum context messages"
    )
+
+    stream_timeout: int = Field(default=300, description="Stream timeout in seconds")
+    max_retries: int = Field(default=3, description="Maximum number of retries")
    max_agent_runs: int = Field(default=30, description="Maximum number of agent runs")
    max_agent_schedules: int = Field(
        default=30, description="Maximum number of agent schedules"
@@ -92,31 +93,6 @@ class ChatConfig(BaseSettings):
        description="Name of the prompt in Langfuse to fetch",
    )

-    # Claude Agent SDK Configuration
-    use_claude_agent_sdk: bool = Field(
-        default=True,
-        description="Use Claude Agent SDK for chat completions",
-    )
-    claude_agent_model: str | None = Field(
-        default=None,
-        description="Model for the Claude Agent SDK path. If None, derives from "
-        "the `model` field by stripping the OpenRouter provider prefix.",
-    )
-    claude_agent_max_buffer_size: int = Field(
-        default=10 * 1024 * 1024,  # 10MB (default SDK is 1MB)
-        description="Max buffer size in bytes for Claude Agent SDK JSON message parsing. "
-        "Increase if tool outputs exceed the limit.",
-    )
-    claude_agent_max_subtasks: int = Field(
-        default=10,
-        description="Max number of sub-agent Tasks the SDK can spawn per session.",
-    )
-    claude_agent_use_resume: bool = Field(
-        default=True,
-        description="Use --resume for multi-turn conversations instead of "
-        "history compression. Falls back to compression when unavailable.",
-    )
-
    # Extended thinking configuration for Claude models
    thinking_enabled: bool = Field(
        default=True,
@@ -162,17 +138,6 @@ class ChatConfig(BaseSettings):
            v = os.getenv("CHAT_INTERNAL_API_KEY")
        return v

-    @field_validator("use_claude_agent_sdk", mode="before")
-    @classmethod
-    def get_use_claude_agent_sdk(cls, v):
-        """Get use_claude_agent_sdk from environment if not provided."""
-        # Check environment variable - default to True if not set
-        env_val = os.getenv("CHAT_USE_CLAUDE_AGENT_SDK", "").lower()
-        if env_val:
-            return env_val in ("true", "1", "yes", "on")
-        # Default to True (SDK enabled by default)
-        return True if v is None else v
-
    # Prompt paths for different contexts
    PROMPT_PATHS: dict[str, str] = {
        "default": "prompts/chat_system.md",
--- a/autogpt_platform/backend/backend/api/features/chat/db.py
+++ b/autogpt_platform/backend/backend/api/features/chat/db.py
@@ -14,27 +14,29 @@ from prisma.types import (
    ChatSessionWhereInput,
 )

-from backend.data import db
+from backend.data.db import transaction
 from backend.util.json import SafeJson

-from .model import ChatMessage, ChatSession, ChatSessionInfo
-
 logger = logging.getLogger(__name__)


-async def get_chat_session(session_id: str) -> ChatSession | None:
+async def get_chat_session(session_id: str) -> PrismaChatSession | None:
    """Get a chat session by ID from the database."""
    session = await PrismaChatSession.prisma().find_unique(
        where={"id": session_id},
-        include={"Messages": {"order_by": {"sequence": "asc"}}},
+        include={"Messages": True},
    )
-    return ChatSession.from_db(session) if session else None
+    if session and session.Messages:
+        # Sort messages by sequence in Python - Prisma Python client doesn't support
+        # order_by in include clauses (unlike Prisma JS), so we sort after fetching
+        session.Messages.sort(key=lambda m: m.sequence)
+    return session


 async def create_chat_session(
    session_id: str,
    user_id: str,
-) -> ChatSessionInfo:
+) -> PrismaChatSession:
    """Create a new chat session in the database."""
    data = ChatSessionCreateInput(
        id=session_id,
@@ -43,8 +45,7 @@ async def create_chat_session(
        successfulAgentRuns=SafeJson({}),
        successfulAgentSchedules=SafeJson({}),
    )
-    prisma_session = await PrismaChatSession.prisma().create(data=data)
-    return ChatSessionInfo.from_db(prisma_session)
+    return await PrismaChatSession.prisma().create(data=data)


 async def update_chat_session(
@@ -55,7 +56,7 @@ async def update_chat_session(
    total_prompt_tokens: int | None = None,
    total_completion_tokens: int | None = None,
    title: str | None = None,
-) -> ChatSession | None:
+) -> PrismaChatSession | None:
    """Update a chat session's metadata."""
    data: ChatSessionUpdateInput = {"updatedAt": datetime.now(UTC)}

@@ -75,9 +76,12 @@ async def update_chat_session(
    session = await PrismaChatSession.prisma().update(
        where={"id": session_id},
        data=data,
-        include={"Messages": {"order_by": {"sequence": "asc"}}},
+        include={"Messages": True},
    )
-    return ChatSession.from_db(session) if session else None
+    if session and session.Messages:
+        # Sort in Python - Prisma Python doesn't support order_by in include clauses
+        session.Messages.sort(key=lambda m: m.sequence)
+    return session


 async def add_chat_message(
@@ -90,7 +94,7 @@ async def add_chat_message(
    refusal: str | None = None,
    tool_calls: list[dict[str, Any]] | None = None,
    function_call: dict[str, Any] | None = None,
-) -> ChatMessage:
+) -> PrismaChatMessage:
    """Add a message to a chat session."""
    # Build input dict dynamically rather than using ChatMessageCreateInput directly
    # because Prisma's TypedDict validation rejects optional fields set to None.
@@ -125,14 +129,14 @@ async def add_chat_message(
        ),
        PrismaChatMessage.prisma().create(data=cast(ChatMessageCreateInput, data)),
    )
-    return ChatMessage.from_db(message)
+    return message


 async def add_chat_messages_batch(
    session_id: str,
    messages: list[dict[str, Any]],
    start_sequence: int,
-) -> list[ChatMessage]:
+) -> list[PrismaChatMessage]:
    """Add multiple messages to a chat session in a batch.

    Uses a transaction for atomicity - if any message creation fails,
@@ -143,7 +147,7 @@ async def add_chat_messages_batch(

    created_messages = []

-    async with db.transaction() as tx:
+    async with transaction() as tx:
        for i, msg in enumerate(messages):
            # Build input dict dynamically rather than using ChatMessageCreateInput
            # directly because Prisma's TypedDict validation rejects optional fields
@@ -183,22 +187,21 @@ async def add_chat_messages_batch(
            data={"updatedAt": datetime.now(UTC)},
        )

-    return [ChatMessage.from_db(m) for m in created_messages]
+    return created_messages


 async def get_user_chat_sessions(
    user_id: str,
    limit: int = 50,
    offset: int = 0,
-) -> list[ChatSessionInfo]:
+) -> list[PrismaChatSession]:
    """Get chat sessions for a user, ordered by most recent."""
-    prisma_sessions = await PrismaChatSession.prisma().find_many(
+    return await PrismaChatSession.prisma().find_many(
        where={"userId": user_id},
        order={"updatedAt": "desc"},
        take=limit,
        skip=offset,
    )
-    return [ChatSessionInfo.from_db(s) for s in prisma_sessions]


 async def get_user_session_count(user_id: str) -> int:
--- a/autogpt_platform/backend/backend/api/features/chat/model.py
+++ b/autogpt_platform/backend/backend/api/features/chat/model.py
@@ -2,7 +2,7 @@ import asyncio
 import logging
 import uuid
 from datetime import UTC, datetime
-from typing import Any, Self, cast
+from typing import Any, cast
 from weakref import WeakValueDictionary

 from openai.types.chat import (
@@ -23,17 +23,26 @@ from prisma.models import ChatMessage as PrismaChatMessage
 from prisma.models import ChatSession as PrismaChatSession
 from pydantic import BaseModel

-from backend.data.db_accessors import chat_db
 from backend.data.redis_client import get_redis_async
 from backend.util import json
 from backend.util.exceptions import DatabaseError, RedisError

+from . import db as chat_db
 from .config import ChatConfig

 logger = logging.getLogger(__name__)
 config = ChatConfig()


+def _parse_json_field(value: str | dict | list | None, default: Any = None) -> Any:
+    """Parse a JSON field that may be stored as string or already parsed."""
+    if value is None:
+        return default
+    if isinstance(value, str):
+        return json.loads(value)
+    return value
+
+
 # Redis cache key prefix for chat sessions
 CHAT_SESSION_CACHE_PREFIX = "chat:session:"

@@ -43,7 +52,28 @@ def _get_session_cache_key(session_id: str) -> str:
    return f"{CHAT_SESSION_CACHE_PREFIX}{session_id}"


-# ===================== Chat data models ===================== #
+# Session-level locks to prevent race conditions during concurrent upserts.
+# Uses WeakValueDictionary to automatically garbage collect locks when no longer referenced,
+# preventing unbounded memory growth while maintaining lock semantics for active sessions.
+# Invalidation: Locks are auto-removed by GC when no coroutine holds a reference (after
+# async with lock: completes). Explicit cleanup also occurs in delete_chat_session().
+_session_locks: WeakValueDictionary[str, asyncio.Lock] = WeakValueDictionary()
+_session_locks_mutex = asyncio.Lock()
+
+
+async def _get_session_lock(session_id: str) -> asyncio.Lock:
+    """Get or create a lock for a specific session to prevent concurrent upserts.
+
+    Uses WeakValueDictionary for automatic cleanup: locks are garbage collected
+    when no coroutine holds a reference to them, preventing memory leaks from
+    unbounded growth of session locks.
+    """
+    async with _session_locks_mutex:
+        lock = _session_locks.get(session_id)
+        if lock is None:
+            lock = asyncio.Lock()
+            _session_locks[session_id] = lock
+        return lock


 class ChatMessage(BaseModel):
@@ -55,19 +85,6 @@ class ChatMessage(BaseModel):
    tool_calls: list[dict] | None = None
    function_call: dict | None = None

-    @staticmethod
-    def from_db(prisma_message: PrismaChatMessage) -> "ChatMessage":
-        """Convert a Prisma ChatMessage to a Pydantic ChatMessage."""
-        return ChatMessage(
-            role=prisma_message.role,
-            content=prisma_message.content,
-            name=prisma_message.name,
-            tool_call_id=prisma_message.toolCallId,
-            refusal=prisma_message.refusal,
-            tool_calls=_parse_json_field(prisma_message.toolCalls),
-            function_call=_parse_json_field(prisma_message.functionCall),
-        )
-

 class Usage(BaseModel):
    prompt_tokens: int
@@ -75,10 +92,11 @@ class Usage(BaseModel):
    total_tokens: int


-class ChatSessionInfo(BaseModel):
+class ChatSession(BaseModel):
    session_id: str
    user_id: str
    title: str | None = None
+    messages: list[ChatMessage]
    usage: list[Usage]
    credentials: dict[str, dict] = {}  # Map of provider -> credential metadata
    started_at: datetime
@@ -86,9 +104,60 @@ class ChatSessionInfo(BaseModel):
    successful_agent_runs: dict[str, int] = {}
    successful_agent_schedules: dict[str, int] = {}

-    @classmethod
-    def from_db(cls, prisma_session: PrismaChatSession) -> Self:
-        """Convert Prisma ChatSession to Pydantic ChatSession."""
+    def add_tool_call_to_current_turn(self, tool_call: dict) -> None:
+        """Attach a tool_call to the current turn's assistant message.
+
+        Searches backwards for the most recent assistant message (stopping at
+        any user message boundary). If found, appends the tool_call to it.
+        Otherwise creates a new assistant message with the tool_call.
+        """
+        for msg in reversed(self.messages):
+            if msg.role == "user":
+                break
+            if msg.role == "assistant":
+                if not msg.tool_calls:
+                    msg.tool_calls = []
+                msg.tool_calls.append(tool_call)
+                return
+
+        self.messages.append(
+            ChatMessage(role="assistant", content="", tool_calls=[tool_call])
+        )
+
+    @staticmethod
+    def new(user_id: str) -> "ChatSession":
+        return ChatSession(
+            session_id=str(uuid.uuid4()),
+            user_id=user_id,
+            title=None,
+            messages=[],
+            usage=[],
+            credentials={},
+            started_at=datetime.now(UTC),
+            updated_at=datetime.now(UTC),
+        )
+
+    @staticmethod
+    def from_db(
+        prisma_session: PrismaChatSession,
+        prisma_messages: list[PrismaChatMessage] | None = None,
+    ) -> "ChatSession":
+        """Convert Prisma models to Pydantic ChatSession."""
+        messages = []
+        if prisma_messages:
+            for msg in prisma_messages:
+                messages.append(
+                    ChatMessage(
+                        role=msg.role,
+                        content=msg.content,
+                        name=msg.name,
+                        tool_call_id=msg.toolCallId,
+                        refusal=msg.refusal,
+                        tool_calls=_parse_json_field(msg.toolCalls),
+                        function_call=_parse_json_field(msg.functionCall),
+                    )
+                )
+
        # Parse JSON fields from Prisma
        credentials = _parse_json_field(prisma_session.credentials, default={})
        successful_agent_runs = _parse_json_field(
@@ -110,10 +179,11 @@ class ChatSessionInfo(BaseModel):
                )
            )

-        return cls(
+        return ChatSession(
            session_id=prisma_session.id,
            user_id=prisma_session.userId,
            title=prisma_session.title,
+            messages=messages,
            usage=usage,
            credentials=credentials,
            started_at=prisma_session.createdAt,
@@ -122,55 +192,46 @@ class ChatSessionInfo(BaseModel):
            successful_agent_schedules=successful_agent_schedules,
        )

+    @staticmethod
+    def _merge_consecutive_assistant_messages(
+        messages: list[ChatCompletionMessageParam],
+    ) -> list[ChatCompletionMessageParam]:
+        """Merge consecutive assistant messages into single messages.

-class ChatSession(ChatSessionInfo):
-    messages: list[ChatMessage]
-
-    @classmethod
-    def new(cls, user_id: str) -> Self:
-        return cls(
-            session_id=str(uuid.uuid4()),
-            user_id=user_id,
-            title=None,
-            messages=[],
-            usage=[],
-            credentials={},
-            started_at=datetime.now(UTC),
-            updated_at=datetime.now(UTC),
-        )
-
-    @classmethod
-    def from_db(cls, prisma_session: PrismaChatSession) -> Self:
-        """Convert Prisma ChatSession to Pydantic ChatSession."""
-        if prisma_session.Messages is None:
-            raise ValueError(
-                f"Prisma session {prisma_session.id} is missing Messages relation"
-            )
-
-        return cls(
-            **ChatSessionInfo.from_db(prisma_session).model_dump(),
-            messages=[ChatMessage.from_db(m) for m in prisma_session.Messages],
-        )
-
-    def add_tool_call_to_current_turn(self, tool_call: dict) -> None:
-        """Attach a tool_call to the current turn's assistant message.
-
-        Searches backwards for the most recent assistant message (stopping at
-        any user message boundary). If found, appends the tool_call to it.
-        Otherwise creates a new assistant message with the tool_call.
+        Long-running tool flows can create split assistant messages: one with
+        text content and another with tool_calls. Anthropic's API requires
+        tool_result blocks to reference a tool_use in the immediately preceding
+        assistant message, so these splits cause 400 errors via OpenRouter.
        """
-        for msg in reversed(self.messages):
-            if msg.role == "user":
-                break
-            if msg.role == "assistant":
-                if not msg.tool_calls:
-                    msg.tool_calls = []
-                msg.tool_calls.append(tool_call)
-                return
+        if len(messages) < 2:
+            return messages

-        self.messages.append(
-            ChatMessage(role="assistant", content="", tool_calls=[tool_call])
-        )
+        result: list[ChatCompletionMessageParam] = [messages[0]]
+        for msg in messages[1:]:
+            prev = result[-1]
+            if prev.get("role") != "assistant" or msg.get("role") != "assistant":
+                result.append(msg)
+                continue
+
+            prev = cast(ChatCompletionAssistantMessageParam, prev)
+            curr = cast(ChatCompletionAssistantMessageParam, msg)
+
+            curr_content = curr.get("content") or ""
+            if curr_content:
+                prev_content = prev.get("content") or ""
+                prev["content"] = (
+                    f"{prev_content}\n{curr_content}" if prev_content else curr_content
+                )
+
+            curr_tool_calls = curr.get("tool_calls")
+            if curr_tool_calls:
+                prev_tool_calls = prev.get("tool_calls")
+                prev["tool_calls"] = (
+                    list(prev_tool_calls) + list(curr_tool_calls)
+                    if prev_tool_calls
+                    else list(curr_tool_calls)
+                )
+        return result

    def to_openai_messages(self) -> list[ChatCompletionMessageParam]:
        messages = []
@@ -260,70 +321,41 @@ class ChatSession(ChatSessionInfo):
                )
        return self._merge_consecutive_assistant_messages(messages)

-    @staticmethod
-    def _merge_consecutive_assistant_messages(
-        messages: list[ChatCompletionMessageParam],
-    ) -> list[ChatCompletionMessageParam]:
-        """Merge consecutive assistant messages into single messages.

-        Long-running tool flows can create split assistant messages: one with
-        text content and another with tool_calls. Anthropic's API requires
-        tool_result blocks to reference a tool_use in the immediately preceding
-        assistant message, so these splits cause 400 errors via OpenRouter.
-        """
-        if len(messages) < 2:
-            return messages
+async def _get_session_from_cache(session_id: str) -> ChatSession | None:
+    """Get a chat session from Redis cache."""
+    redis_key = _get_session_cache_key(session_id)
+    async_redis = await get_redis_async()
+    raw_session: bytes | None = await async_redis.get(redis_key)

-        result: list[ChatCompletionMessageParam] = [messages[0]]
-        for msg in messages[1:]:
-            prev = result[-1]
-            if prev.get("role") != "assistant" or msg.get("role") != "assistant":
-                result.append(msg)
-                continue
+    if raw_session is None:
+        return None

-            prev = cast(ChatCompletionAssistantMessageParam, prev)
-            curr = cast(ChatCompletionAssistantMessageParam, msg)
-
-            curr_content = curr.get("content") or ""
-            if curr_content:
-                prev_content = prev.get("content") or ""
-                prev["content"] = (
-                    f"{prev_content}\n{curr_content}" if prev_content else curr_content
-                )
-
-            curr_tool_calls = curr.get("tool_calls")
-            if curr_tool_calls:
-                prev_tool_calls = prev.get("tool_calls")
-                prev["tool_calls"] = (
-                    list(prev_tool_calls) + list(curr_tool_calls)
-                    if prev_tool_calls
-                    else list(curr_tool_calls)
-                )
-        return result
+    try:
+        session = ChatSession.model_validate_json(raw_session)
+        logger.info(
+            f"Loading session {session_id} from cache: "
+            f"message_count={len(session.messages)}, "
+            f"roles={[m.role for m in session.messages]}"
+        )
+        return session
+    except Exception as e:
+        logger.error(f"Failed to deserialize session {session_id}: {e}", exc_info=True)
+        raise RedisError(f"Corrupted session data for {session_id}") from e


-def _parse_json_field(value: str | dict | list | None, default: Any = None) -> Any:
-    """Parse a JSON field that may be stored as string or already parsed."""
-    if value is None:
-        return default
-    if isinstance(value, str):
-        return json.loads(value)
-    return value
-
-
-# ================ Chat cache + DB operations ================ #
-
-# NOTE: Database calls are automatically routed through DatabaseManager if Prisma is not
-#       connected directly.
-
-
-async def cache_chat_session(session: ChatSession) -> None:
-    """Cache a chat session in Redis (without persisting to the database)."""
+async def _cache_session(session: ChatSession) -> None:
+    """Cache a chat session in Redis."""
    redis_key = _get_session_cache_key(session.session_id)
    async_redis = await get_redis_async()
    await async_redis.setex(redis_key, config.session_ttl, session.model_dump_json())


+async def cache_chat_session(session: ChatSession) -> None:
+    """Cache a chat session without persisting to the database."""
+    await _cache_session(session)
+
+
 async def invalidate_session_cache(session_id: str) -> None:
    """Invalidate a chat session from Redis cache.

@@ -339,6 +371,80 @@ async def invalidate_session_cache(session_id: str) -> None:
        logger.warning(f"Failed to invalidate session cache for {session_id}: {e}")


+async def _get_session_from_db(session_id: str) -> ChatSession | None:
+    """Get a chat session from the database."""
+    prisma_session = await chat_db.get_chat_session(session_id)
+    if not prisma_session:
+        return None
+
+    messages = prisma_session.Messages
+    logger.info(
+        f"Loading session {session_id} from DB: "
+        f"has_messages={messages is not None}, "
+        f"message_count={len(messages) if messages else 0}, "
+        f"roles={[m.role for m in messages] if messages else []}"
+    )
+
+    return ChatSession.from_db(prisma_session, messages)
+
+
+async def _save_session_to_db(
+    session: ChatSession, existing_message_count: int
+) -> None:
+    """Save or update a chat session in the database."""
+    # Check if session exists in DB
+    existing = await chat_db.get_chat_session(session.session_id)
+
+    if not existing:
+        # Create new session
+        await chat_db.create_chat_session(
+            session_id=session.session_id,
+            user_id=session.user_id,
+        )
+        existing_message_count = 0
+
+    # Calculate total tokens from usage
+    total_prompt = sum(u.prompt_tokens for u in session.usage)
+    total_completion = sum(u.completion_tokens for u in session.usage)
+
+    # Update session metadata
+    await chat_db.update_chat_session(
+        session_id=session.session_id,
+        credentials=session.credentials,
+        successful_agent_runs=session.successful_agent_runs,
+        successful_agent_schedules=session.successful_agent_schedules,
+        total_prompt_tokens=total_prompt,
+        total_completion_tokens=total_completion,
+    )
+
+    # Add new messages (only those after existing count)
+    new_messages = session.messages[existing_message_count:]
+    if new_messages:
+        messages_data = []
+        for msg in new_messages:
+            messages_data.append(
+                {
+                    "role": msg.role,
+                    "content": msg.content,
+                    "name": msg.name,
+                    "tool_call_id": msg.tool_call_id,
+                    "refusal": msg.refusal,
+                    "tool_calls": msg.tool_calls,
+                    "function_call": msg.function_call,
+                }
+            )
+        logger.info(
+            f"Saving {len(new_messages)} new messages to DB for session {session.session_id}: "
+            f"roles={[m['role'] for m in messages_data]}, "
+            f"start_sequence={existing_message_count}"
+        )
+        await chat_db.add_chat_messages_batch(
+            session_id=session.session_id,
+            messages=messages_data,
+            start_sequence=existing_message_count,
+        )
+
+
 async def get_chat_session(
    session_id: str,
    user_id: str | None = None,
@@ -370,7 +476,7 @@ async def get_chat_session(
        logger.warning(f"Unexpected cache error for session {session_id}: {e}")

    # Fall back to database
-    logger.debug(f"Session {session_id} not in cache, checking database")
+    logger.info(f"Session {session_id} not in cache, checking database")
    session = await _get_session_from_db(session_id)

    if session is None:
@@ -386,7 +492,7 @@ async def get_chat_session(

    # Cache the session from DB
    try:
-        await cache_chat_session(session)
+        await _cache_session(session)
        logger.info(f"Cached session {session_id} from database")
    except Exception as e:
        logger.warning(f"Failed to cache session {session_id}: {e}")
@@ -394,45 +500,9 @@ async def get_chat_session(
    return session


-async def _get_session_from_cache(session_id: str) -> ChatSession | None:
-    """Get a chat session from Redis cache."""
-    redis_key = _get_session_cache_key(session_id)
-    async_redis = await get_redis_async()
-    raw_session: bytes | None = await async_redis.get(redis_key)
-
-    if raw_session is None:
-        return None
-
-    try:
-        session = ChatSession.model_validate_json(raw_session)
-        logger.info(
-            f"Loading session {session_id} from cache: "
-            f"message_count={len(session.messages)}, "
-            f"roles={[m.role for m in session.messages]}"
-        )
-        return session
-    except Exception as e:
-        logger.error(f"Failed to deserialize session {session_id}: {e}", exc_info=True)
-        raise RedisError(f"Corrupted session data for {session_id}") from e
-
-
-async def _get_session_from_db(session_id: str) -> ChatSession | None:
-    """Get a chat session from the database."""
-    session = await chat_db().get_chat_session(session_id)
-    if not session:
-        return None
-
-    logger.info(
-        f"Loaded session {session_id} from DB: "
-        f"has_messages={bool(session.messages)}, "
-        f"message_count={len(session.messages)}, "
-        f"roles={[m.role for m in session.messages]}"
-    )
-
-    return session
-
-
-async def upsert_chat_session(session: ChatSession) -> ChatSession:
+async def upsert_chat_session(
+    session: ChatSession,
+) -> ChatSession:
    """Update a chat session in both cache and database.

    Uses session-level locking to prevent race conditions when concurrent
@@ -450,7 +520,7 @@ async def upsert_chat_session(session: ChatSession) -> ChatSession:

    async with lock:
        # Get existing message count from DB for incremental saves
-        existing_message_count = await chat_db().get_chat_session_message_count(
+        existing_message_count = await chat_db.get_chat_session_message_count(
            session.session_id
        )

@@ -467,7 +537,7 @@ async def upsert_chat_session(session: ChatSession) -> ChatSession:

        # Save to cache (best-effort, even if DB failed)
        try:
-            await cache_chat_session(session)
+            await _cache_session(session)
        except Exception as e:
            # If DB succeeded but cache failed, raise cache error
            if db_error is None:
@@ -488,99 +558,6 @@ async def upsert_chat_session(session: ChatSession) -> ChatSession:
        return session


-async def _save_session_to_db(
-    session: ChatSession, existing_message_count: int
-) -> None:
-    """Save or update a chat session in the database."""
-    db = chat_db()
-
-    # Check if session exists in DB
-    existing = await db.get_chat_session(session.session_id)
-
-    if not existing:
-        # Create new session
-        await db.create_chat_session(
-            session_id=session.session_id,
-            user_id=session.user_id,
-        )
-        existing_message_count = 0
-
-    # Calculate total tokens from usage
-    total_prompt = sum(u.prompt_tokens for u in session.usage)
-    total_completion = sum(u.completion_tokens for u in session.usage)
-
-    # Update session metadata
-    await db.update_chat_session(
-        session_id=session.session_id,
-        credentials=session.credentials,
-        successful_agent_runs=session.successful_agent_runs,
-        successful_agent_schedules=session.successful_agent_schedules,
-        total_prompt_tokens=total_prompt,
-        total_completion_tokens=total_completion,
-    )
-
-    # Add new messages (only those after existing count)
-    new_messages = session.messages[existing_message_count:]
-    if new_messages:
-        messages_data = []
-        for msg in new_messages:
-            messages_data.append(
-                {
-                    "role": msg.role,
-                    "content": msg.content,
-                    "name": msg.name,
-                    "tool_call_id": msg.tool_call_id,
-                    "refusal": msg.refusal,
-                    "tool_calls": msg.tool_calls,
-                    "function_call": msg.function_call,
-                }
-            )
-        logger.info(
-            f"Saving {len(new_messages)} new messages to DB for session {session.session_id}: "
-            f"roles={[m['role'] for m in messages_data]}, "
-            f"start_sequence={existing_message_count}"
-        )
-        await db.add_chat_messages_batch(
-            session_id=session.session_id,
-            messages=messages_data,
-            start_sequence=existing_message_count,
-        )
-
-
-async def append_and_save_message(session_id: str, message: ChatMessage) -> ChatSession:
-    """Atomically append a message to a session and persist it.
-
-    Acquires the session lock, re-fetches the latest session state,
-    appends the message, and saves — preventing message loss when
-    concurrent requests modify the same session.
-    """
-    lock = await _get_session_lock(session_id)
-
-    async with lock:
-        session = await get_chat_session(session_id)
-        if session is None:
-            raise ValueError(f"Session {session_id} not found")
-
-        session.messages.append(message)
-        existing_message_count = await chat_db().get_chat_session_message_count(
-            session_id
-        )
-
-        try:
-            await _save_session_to_db(session, existing_message_count)
-        except Exception as e:
-            raise DatabaseError(
-                f"Failed to persist message to session {session_id}"
-            ) from e
-
-        try:
-            await cache_chat_session(session)
-        except Exception as e:
-            logger.warning(f"Cache write failed for session {session_id}: {e}")
-
-        return session
-
-
 async def create_chat_session(user_id: str) -> ChatSession:
    """Create a new chat session and persist it.

@@ -593,7 +570,7 @@ async def create_chat_session(user_id: str) -> ChatSession:

    # Create in database first - fail fast if this fails
    try:
-        await chat_db().create_chat_session(
+        await chat_db.create_chat_session(
            session_id=session.session_id,
            user_id=user_id,
        )
@@ -605,7 +582,7 @@ async def create_chat_session(user_id: str) -> ChatSession:

    # Cache the session (best-effort optimization, DB is source of truth)
    try:
-        await cache_chat_session(session)
+        await _cache_session(session)
    except Exception as e:
        logger.warning(f"Failed to cache new session {session.session_id}: {e}")

@@ -616,16 +593,20 @@ async def get_user_sessions(
    user_id: str,
    limit: int = 50,
    offset: int = 0,
-) -> tuple[list[ChatSessionInfo], int]:
+) -> tuple[list[ChatSession], int]:
    """Get chat sessions for a user from the database with total count.

    Returns:
        A tuple of (sessions, total_count) where total_count is the overall
        number of sessions for the user (not just the current page).
    """
-    db = chat_db()
-    sessions = await db.get_user_chat_sessions(user_id, limit, offset)
-    total_count = await db.get_user_session_count(user_id)
+    prisma_sessions = await chat_db.get_user_chat_sessions(user_id, limit, offset)
+    total_count = await chat_db.get_user_session_count(user_id)
+
+    sessions = []
+    for prisma_session in prisma_sessions:
+        # Convert without messages for listing (lighter weight)
+        sessions.append(ChatSession.from_db(prisma_session, None))

    return sessions, total_count

@@ -643,7 +624,7 @@ async def delete_chat_session(session_id: str, user_id: str | None = None) -> bo
    """
    # Delete from database first (with optional user_id validation)
    # This confirms ownership before invalidating cache
-    deleted = await chat_db().delete_chat_session(session_id, user_id)
+    deleted = await chat_db.delete_chat_session(session_id, user_id)

    if not deleted:
        return False
@@ -678,52 +659,20 @@ async def update_session_title(session_id: str, title: str) -> bool:
        True if updated successfully, False otherwise.
    """
    try:
-        result = await chat_db().update_chat_session(session_id=session_id, title=title)
+        result = await chat_db.update_chat_session(session_id=session_id, title=title)
        if result is None:
            logger.warning(f"Session {session_id} not found for title update")
            return False

-        # Update title in cache if it exists (instead of invalidating).
-        # This prevents race conditions where cache invalidation causes
-        # the frontend to see stale DB data while streaming is still in progress.
+        # Invalidate cache so next fetch gets updated title
        try:
-            cached = await _get_session_from_cache(session_id)
-            if cached:
-                cached.title = title
-                await cache_chat_session(cached)
+            redis_key = _get_session_cache_key(session_id)
+            async_redis = await get_redis_async()
+            await async_redis.delete(redis_key)
        except Exception as e:
-            # Not critical - title will be correct on next full cache refresh
-            logger.warning(
-                f"Failed to update title in cache for session {session_id}: {e}"
-            )
+            logger.warning(f"Failed to invalidate cache for session {session_id}: {e}")

        return True
    except Exception as e:
        logger.error(f"Failed to update title for session {session_id}: {e}")
        return False
-
-
-# ==================== Chat session locks ==================== #
-
-_session_locks: WeakValueDictionary[str, asyncio.Lock] = WeakValueDictionary()
-_session_locks_mutex = asyncio.Lock()
-
-
-async def _get_session_lock(session_id: str) -> asyncio.Lock:
-    """Get or create a lock for a specific session to prevent concurrent upserts.
-
-    This was originally added to solve the specific problem of race conditions between
-    the session title thread and the conversation thread, which always occurs on the
-    same instance as we prevent rapid request sends on the frontend.
-
-    Uses WeakValueDictionary for automatic cleanup: locks are garbage collected
-    when no coroutine holds a reference to them, preventing memory leaks from
-    unbounded growth of session locks. Explicit cleanup also occurs
-    in `delete_chat_session()`.
-    """
-    async with _session_locks_mutex:
-        lock = _session_locks.get(session_id)
-        if lock is None:
-            lock = asyncio.Lock()
-            _session_locks[session_id] = lock
-        return lock
--- a/autogpt_platform/backend/backend/api/features/chat/model_test.py
+++ b/autogpt_platform/backend/backend/api/features/chat/model_test.py
--- a/autogpt_platform/backend/backend/api/features/chat/response_model.py
+++ b/autogpt_platform/backend/backend/api/features/chat/response_model.py
--- a/autogpt_platform/backend/backend/api/features/chat/routes.py
+++ b/autogpt_platform/backend/backend/api/features/chat/routes.py
@@ -1,6 +1,5 @@
 """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
@@ -11,31 +10,20 @@ from fastapi import APIRouter, Depends, Header, HTTPException, Query, Response,
 from fastapi.responses import StreamingResponse
 from pydantic import BaseModel

-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 (
+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 (
    AgentDetailsResponse,
    AgentOutputResponse,
    AgentPreviewResponse,
    AgentSavedResponse,
    AgentsFoundResponse,
-    BlockDetailsResponse,
    BlockListResponse,
    BlockOutputResponse,
    ClarificationNeededResponse,
@@ -52,8 +40,6 @@ from backend.copilot.tools.models import (
    SetupRequirementsResponse,
    UnderstandingUpdatedResponse,
 )
-from backend.copilot.tracking import track_user_message
-from backend.util.exceptions import NotFoundError

 config = ChatConfig()

@@ -213,43 +199,6 @@ 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}",
 )
@@ -282,10 +231,6 @@ 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
@@ -355,9 +300,10 @@ async def stream_chat_post(
        f"user={user_id}, message_len={len(request.message)}",
        extra={"json_fields": log_meta},
    )
-    await _validate_and_get_session(session_id, user_id)
+
+    session = 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,
@@ -366,25 +312,6 @@ 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())
@@ -400,7 +327,7 @@ 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,
@@ -409,19 +336,82 @@ async def stream_chat_post(
        },
    )

-    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,
-    )
+    # Background task that runs the AI generation independently of SSE connection
+    async def run_ai_generation():
+        import time as time_module

+        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] Task enqueued to RabbitMQ, setup={setup_time:.1f}ms",
+        f"[TIMING] Background task started, setup={setup_time:.1f}ms",
        extra={"json_fields": {**log_meta, "setup_time_ms": setup_time}},
    )

@@ -516,14 +506,8 @@ 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
+            # Unsubscribe when client disconnects or stream ends to prevent resource leak
            if subscriber_queue is not None:
                try:
                    await stream_registry.unsubscribe_from_task(
@@ -767,6 +751,8 @@ 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:
@@ -985,7 +971,6 @@ ToolResponseUnion = (
    | AgentSavedResponse
    | ClarificationNeededResponse
    | BlockListResponse
-    | BlockDetailsResponse
    | BlockOutputResponse
    | DocSearchResultsResponse
    | DocPageResponse
--- a/autogpt_platform/backend/backend/api/features/chat/service.py
+++ b/autogpt_platform/backend/backend/api/features/chat/service.py
@@ -27,18 +27,20 @@ from openai.types.chat import (
    ChatCompletionToolParam,
 )

-from backend.data.db_accessors import chat_db, understanding_db
 from backend.data.redis_client import get_redis_async
-from backend.data.understanding import format_understanding_for_prompt
+from backend.data.understanding import (
+    format_understanding_for_prompt,
+    get_business_understanding,
+)
 from backend.util.exceptions import NotFoundError
 from backend.util.settings import AppEnvironment, Settings

+from . import db as chat_db
 from . import stream_registry
 from .config import ChatConfig
 from .model import (
    ChatMessage,
    ChatSession,
-    ChatSessionInfo,
    Usage,
    cache_chat_session,
    get_chat_session,
@@ -243,16 +245,12 @@ async def _get_system_prompt_template(context: str) -> str:
    return DEFAULT_SYSTEM_PROMPT.format(users_information=context)


-async def _build_system_prompt(
-    user_id: str | None, has_conversation_history: bool = False
-) -> tuple[str, Any]:
+async def _build_system_prompt(user_id: str | None) -> tuple[str, Any]:
    """Build the full system prompt including business understanding if available.

    Args:
-        user_id: The user ID for fetching business understanding.
-        has_conversation_history: Whether there's existing conversation history.
-            If True, we don't tell the model to greet/introduce (since they're
-            already in a conversation).
+        user_id: The user ID for fetching business understanding
+                     If "default" and this is the user's first session, will use "onboarding" instead.

    Returns:
        Tuple of (compiled prompt string, business understanding object)
@@ -261,15 +259,13 @@ async def _build_system_prompt(
    understanding = None
    if user_id:
        try:
-            understanding = await understanding_db().get_business_understanding(user_id)
+            understanding = await get_business_understanding(user_id)
        except Exception as e:
            logger.warning(f"Failed to fetch business understanding: {e}")
            understanding = None

    if understanding:
        context = format_understanding_for_prompt(understanding)
-    elif has_conversation_history:
-        context = "No prior understanding saved yet. Continue the existing conversation naturally."
    else:
        context = "This is the first time you are meeting the user. Greet them and introduce them to the platform"

@@ -337,7 +333,7 @@ async def _generate_session_title(
 async def assign_user_to_session(
    session_id: str,
    user_id: str,
-) -> ChatSessionInfo:
+) -> ChatSession:
    """
    Assign a user to a chat session.
    """
@@ -378,6 +374,7 @@ async def stream_chat_completion(

    Raises:
        NotFoundError: If session_id is invalid
+        ValueError: If max_context_messages is exceeded

    """
    completion_start = time.monotonic()
@@ -426,16 +423,12 @@ async def stream_chat_completion(
            f"Session {session_id} not found. Please create a new session first."
        )

-    # Append the new message to the session if it's not already there
-    new_message_role = "user" if is_user_message else "assistant"
-    if message and (
-        len(session.messages) == 0
-        or not (
-            session.messages[-1].role == new_message_role
-            and session.messages[-1].content == message
+    if message:
+        session.messages.append(
+            ChatMessage(
+                role="user" if is_user_message else "assistant", content=message
+            )
        )
-    ):
-        session.messages.append(ChatMessage(role=new_message_role, content=message))
        logger.info(
            f"Appended message (role={'user' if is_user_message else 'assistant'}), "
            f"new message_count={len(session.messages)}"
@@ -466,9 +459,8 @@ async def stream_chat_completion(

    # Generate title for new sessions on first user message (non-blocking)
    # Check: is_user_message, no title yet, and this is the first user message
-    user_messages = [m for m in session.messages if m.role == "user"]
-    first_user_msg = message or (user_messages[0].content if user_messages else None)
-    if is_user_message and first_user_msg and not session.title:
+    if is_user_message and message and not session.title:
+        user_messages = [m for m in session.messages if m.role == "user"]
        if len(user_messages) == 1:
            # First user message - generate title in background
            import asyncio
@@ -476,7 +468,7 @@ async def stream_chat_completion(
            # Capture only the values we need (not the session object) to avoid
            # stale data issues when the main flow modifies the session
            captured_session_id = session_id
-            captured_message = first_user_msg
+            captured_message = message
            captured_user_id = user_id

            async def _update_title():
@@ -1245,7 +1237,7 @@ async def _stream_chat_chunks(

                total_time = (time_module.perf_counter() - stream_chunks_start) * 1000
                logger.info(
-                    f"[TIMING] _stream_chat_chunks COMPLETED in {total_time / 1000:.1f}s; "
+                    f"[TIMING] _stream_chat_chunks COMPLETED in {total_time/1000:.1f}s; "
                    f"session={session.session_id}, user={session.user_id}",
                    extra={"json_fields": {**log_meta, "total_time_ms": total_time}},
                )
@@ -1253,7 +1245,6 @@ async def _stream_chat_chunks(
                return
            except Exception as e:
                last_error = e
-
                if _is_retryable_error(e) and retry_count < MAX_RETRIES:
                    retry_count += 1
                    # Calculate delay with exponential backoff
@@ -1269,27 +1260,12 @@ async def _stream_chat_chunks(
                    continue  # Retry the stream
                else:
                    # Non-retryable error or max retries exceeded
-                    _log_api_error(
-                        error=e,
-                        context="stream (not retrying)",
-                        session_id=session.session_id if session else None,
-                        message_count=len(messages) if messages else None,
-                        model=model,
-                        retry_count=retry_count,
+                    logger.error(
+                        f"Error in stream (not retrying): {e!s}",
+                        exc_info=True,
                    )
                    error_code = None
                    error_text = str(e)
-
-                    error_details = _extract_api_error_details(e)
-                    if error_details.get("response_body"):
-                        body = error_details["response_body"]
-                        if isinstance(body, dict):
-                            err = body.get("error")
-                            if isinstance(err, dict) and err.get("message"):
-                                error_text = err["message"]
-                            elif body.get("message"):
-                                error_text = body["message"]
-
                    if _is_region_blocked_error(e):
                        error_code = "MODEL_NOT_AVAILABLE_REGION"
                        error_text = (
@@ -1306,13 +1282,9 @@ async def _stream_chat_chunks(

        # If we exit the retry loop without returning, it means we exhausted retries
        if last_error:
-            _log_api_error(
-                error=last_error,
-                context=f"stream (max retries {MAX_RETRIES} exceeded)",
-                session_id=session.session_id if session else None,
-                message_count=len(messages) if messages else None,
-                model=model,
-                retry_count=MAX_RETRIES,
+            logger.error(
+                f"Max retries ({MAX_RETRIES}) exceeded. Last error: {last_error!s}",
+                exc_info=True,
            )
            yield StreamError(errorText=f"Max retries exceeded: {last_error!s}")
            yield StreamFinish()
@@ -1772,7 +1744,7 @@ async def _update_pending_operation(
    This is called by background tasks when long-running operations complete.
    """
    # Update the message in database
-    updated = await chat_db().update_tool_message_content(
+    updated = await chat_db.update_tool_message_content(
        session_id=session_id,
        tool_call_id=tool_call_id,
        new_content=result,
@@ -1885,7 +1857,6 @@ async def _generate_llm_continuation(
                break  # Success, exit retry loop
            except Exception as e:
                last_error = e
-
                if _is_retryable_error(e) and retry_count < MAX_RETRIES:
                    retry_count += 1
                    delay = min(
@@ -1899,25 +1870,17 @@ async def _generate_llm_continuation(
                    await asyncio.sleep(delay)
                    continue
                else:
-                    # Non-retryable error - log details and exit gracefully
-                    _log_api_error(
-                        error=e,
-                        context="LLM continuation (not retrying)",
-                        session_id=session_id,
-                        message_count=len(messages) if messages else None,
-                        model=config.model,
-                        retry_count=retry_count,
+                    # Non-retryable error - log and exit gracefully
+                    logger.error(
+                        f"Non-retryable error in LLM continuation: {e!s}",
+                        exc_info=True,
                    )
                    return

        if last_error:
-            _log_api_error(
-                error=last_error,
-                context=f"LLM continuation (max retries {MAX_RETRIES} exceeded)",
-                session_id=session_id,
-                message_count=len(messages) if messages else None,
-                model=config.model,
-                retry_count=MAX_RETRIES,
+            logger.error(
+                f"Max retries ({MAX_RETRIES}) exceeded for LLM continuation. "
+                f"Last error: {last_error!s}"
            )
            return

@@ -1957,91 +1920,6 @@ async def _generate_llm_continuation(
        logger.error(f"Failed to generate LLM continuation: {e}", exc_info=True)


-def _log_api_error(
-    error: Exception,
-    context: str,
-    session_id: str | None = None,
-    message_count: int | None = None,
-    model: str | None = None,
-    retry_count: int = 0,
-) -> None:
-    """Log detailed API error information for debugging."""
-    details = _extract_api_error_details(error)
-    details["context"] = context
-    details["session_id"] = session_id
-    details["message_count"] = message_count
-    details["model"] = model
-    details["retry_count"] = retry_count
-
-    if isinstance(error, RateLimitError):
-        logger.warning(f"Rate limit error in {context}: {details}", exc_info=error)
-    elif isinstance(error, APIConnectionError):
-        logger.warning(f"API connection error in {context}: {details}", exc_info=error)
-    elif isinstance(error, APIStatusError) and error.status_code >= 500:
-        logger.error(f"API server error (5xx) in {context}: {details}", exc_info=error)
-    else:
-        logger.error(f"API error in {context}: {details}", exc_info=error)
-
-
-def _extract_api_error_details(error: Exception) -> dict[str, Any]:
-    """Extract detailed information from OpenAI/OpenRouter API errors."""
-    error_msg = str(error)
-    details: dict[str, Any] = {
-        "error_type": type(error).__name__,
-        "error_message": error_msg[:500] + "..." if len(error_msg) > 500 else error_msg,
-    }
-
-    if hasattr(error, "code"):
-        details["code"] = getattr(error, "code", None)
-    if hasattr(error, "param"):
-        details["param"] = getattr(error, "param", None)
-
-    if isinstance(error, APIStatusError):
-        details["status_code"] = error.status_code
-        details["request_id"] = getattr(error, "request_id", None)
-
-        if hasattr(error, "body") and error.body:
-            details["response_body"] = _sanitize_error_body(error.body)
-
-        if hasattr(error, "response") and error.response:
-            headers = error.response.headers
-            details["openrouter_provider"] = headers.get("x-openrouter-provider")
-            details["openrouter_model"] = headers.get("x-openrouter-model")
-            details["retry_after"] = headers.get("retry-after")
-            details["rate_limit_remaining"] = headers.get("x-ratelimit-remaining")
-
-    return details
-
-
-def _sanitize_error_body(
-    body: Any, max_length: int = 2000
-) -> dict[str, Any] | str | None:
-    """Extract only safe fields from error response body to avoid logging sensitive data."""
-    if not isinstance(body, dict):
-        # Non-dict bodies (e.g., HTML error pages) - return truncated string
-        if body is not None:
-            body_str = str(body)
-            if len(body_str) > max_length:
-                return body_str[:max_length] + "...[truncated]"
-            return body_str
-        return None
-
-    safe_fields = ("message", "type", "code", "param", "error")
-    sanitized: dict[str, Any] = {}
-
-    for field in safe_fields:
-        if field in body:
-            value = body[field]
-            if field == "error" and isinstance(value, dict):
-                sanitized[field] = _sanitize_error_body(value, max_length)
-            elif isinstance(value, str) and len(value) > max_length:
-                sanitized[field] = value[:max_length] + "...[truncated]"
-            else:
-                sanitized[field] = value
-
-    return sanitized if sanitized else None
-
-
 async def _generate_llm_continuation_with_streaming(
    session_id: str,
    user_id: str | None,
--- a/autogpt_platform/backend/backend/api/features/chat/service_test.py
+++ b/autogpt_platform/backend/backend/api/features/chat/service_test.py
@@ -0,0 +1,82 @@
+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"
--- a/autogpt_platform/backend/backend/api/features/chat/stream_registry.py
+++ b/autogpt_platform/backend/backend/api/features/chat/stream_registry.py
@@ -814,28 +814,6 @@ async def get_active_task_for_session(
                if task_user_id and user_id != task_user_id:
                    continue

-                # Auto-expire stale tasks that exceeded stream_timeout
-                created_at_str = meta.get("created_at", "")
-                if created_at_str:
-                    try:
-                        created_at = datetime.fromisoformat(created_at_str)
-                        age_seconds = (
-                            datetime.now(timezone.utc) - created_at
-                        ).total_seconds()
-                        if age_seconds > config.stream_timeout:
-                            logger.warning(
-                                f"[TASK_LOOKUP] Auto-expiring stale task {task_id[:8]}... "
-                                f"(age={age_seconds:.0f}s > timeout={config.stream_timeout}s)"
-                            )
-                            await mark_task_completed(task_id, "failed")
-                            continue
-                    except (ValueError, TypeError):
-                        pass
-
-                logger.info(
-                    f"[TASK_LOOKUP] Found running task {task_id[:8]}... for session {session_id[:8]}..."
-                )
-
                # Get the last message ID from Redis Stream
                stream_key = _get_task_stream_key(task_id)
                last_id = "0-0"
--- a/autogpt_platform/backend/backend/api/features/chat/tools/IDEAS.md
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/IDEAS.md
--- a/autogpt_platform/backend/backend/api/features/chat/tools/init.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/init.py
@@ -3,18 +3,15 @@ from typing import TYPE_CHECKING, Any

 from openai.types.chat import ChatCompletionToolParam

-from backend.copilot.model import ChatSession
-from backend.copilot.tracking import track_tool_called
+from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.tracking import track_tool_called

 from .add_understanding import AddUnderstandingTool
 from .agent_output import AgentOutputTool
 from .base import BaseTool
-from .bash_exec import BashExecTool
-from .check_operation_status import CheckOperationStatusTool
 from .create_agent import CreateAgentTool
 from .customize_agent import CustomizeAgentTool
 from .edit_agent import EditAgentTool
-from .feature_requests import CreateFeatureRequestTool, SearchFeatureRequestsTool
 from .find_agent import FindAgentTool
 from .find_block import FindBlockTool
 from .find_library_agent import FindLibraryAgentTool
@@ -22,7 +19,6 @@ from .get_doc_page import GetDocPageTool
 from .run_agent import RunAgentTool
 from .run_block import RunBlockTool
 from .search_docs import SearchDocsTool
-from .web_fetch import WebFetchTool
 from .workspace_files import (
    DeleteWorkspaceFileTool,
    ListWorkspaceFilesTool,
@@ -31,7 +27,7 @@ from .workspace_files import (
 )

 if TYPE_CHECKING:
-    from backend.copilot.response_model import StreamToolOutputAvailable
+    from backend.api.features.chat.response_model import StreamToolOutputAvailable

 logger = logging.getLogger(__name__)

@@ -47,17 +43,8 @@ TOOL_REGISTRY: dict[str, BaseTool] = {
    "run_agent": RunAgentTool(),
    "run_block": RunBlockTool(),
    "view_agent_output": AgentOutputTool(),
-    "check_operation_status": CheckOperationStatusTool(),
    "search_docs": SearchDocsTool(),
    "get_doc_page": GetDocPageTool(),
-    # Web fetch for safe URL retrieval
-    "web_fetch": WebFetchTool(),
-    # Sandboxed code execution (bubblewrap)
-    "bash_exec": BashExecTool(),
-    # Persistent workspace tools (cloud storage, survives across sessions)
-    # Feature request tools
-    "search_feature_requests": SearchFeatureRequestsTool(),
-    "create_feature_request": CreateFeatureRequestTool(),
    # Workspace tools for CoPilot file operations
    "list_workspace_files": ListWorkspaceFilesTool(),
    "read_workspace_file": ReadWorkspaceFileTool(),
--- a/autogpt_platform/backend/backend/api/features/chat/tools/_test_data.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/_test_data.py
@@ -6,11 +6,11 @@ import pytest
 from prisma.types import ProfileCreateInput
 from pydantic import SecretStr

+from backend.api.features.chat.model import ChatSession
 from backend.api.features.store import db as store_db
 from backend.blocks.firecrawl.scrape import FirecrawlScrapeBlock
 from backend.blocks.io import AgentInputBlock, AgentOutputBlock
 from backend.blocks.llm import AITextGeneratorBlock
-from backend.copilot.model import ChatSession
 from backend.data.db import prisma
 from backend.data.graph import Graph, Link, Node, create_graph
 from backend.data.model import APIKeyCredentials
--- a/autogpt_platform/backend/backend/api/features/chat/tools/add_understanding.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/add_understanding.py
@@ -3,9 +3,11 @@
 import logging
 from typing import Any

-from backend.copilot.model import ChatSession
-from backend.data.db_accessors import understanding_db
-from backend.data.understanding import BusinessUnderstandingInput
+from backend.api.features.chat.model import ChatSession
+from backend.data.understanding import (
+    BusinessUnderstandingInput,
+    upsert_business_understanding,
+)

 from .base import BaseTool
 from .models import ErrorResponse, ToolResponseBase, UnderstandingUpdatedResponse
@@ -97,9 +99,7 @@ and automations for the user's specific needs."""
        ]

        # Upsert with merge
-        understanding = await understanding_db().upsert_business_understanding(
-            user_id, input_data
-        )
+        understanding = await upsert_business_understanding(user_id, input_data)

        # Build current understanding summary (filter out empty values)
        current_understanding = {
--- a/autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/init.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/init.py
--- a/autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/core.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/core.py
@@ -5,8 +5,9 @@ import re
 import uuid
 from typing import Any, NotRequired, TypedDict

-from backend.data.db_accessors import graph_db, library_db, store_db
-from backend.data.graph import Graph, Link, Node
+from backend.api.features.library import db as library_db
+from backend.api.features.store import db as store_db
+from backend.data.graph import Graph, Link, Node, get_graph, get_store_listed_graphs
 from backend.util.exceptions import DatabaseError, NotFoundError

 from .service import (
@@ -144,9 +145,8 @@ async def get_library_agent_by_id(
    Returns:
        LibraryAgentSummary if found, None otherwise
    """
-    db = library_db()
    try:
-        agent = await db.get_library_agent_by_graph_id(user_id, agent_id)
+        agent = await library_db.get_library_agent_by_graph_id(user_id, agent_id)
        if agent:
            logger.debug(f"Found library agent by graph_id: {agent.name}")
            return LibraryAgentSummary(
@@ -163,7 +163,7 @@ async def get_library_agent_by_id(
        logger.debug(f"Could not fetch library agent by graph_id {agent_id}: {e}")

    try:
-        agent = await db.get_library_agent(agent_id, user_id)
+        agent = await library_db.get_library_agent(agent_id, user_id)
        if agent:
            logger.debug(f"Found library agent by library_id: {agent.name}")
            return LibraryAgentSummary(
@@ -215,7 +215,7 @@ async def get_library_agents_for_generation(
        List of LibraryAgentSummary with schemas and recent executions for sub-agent composition
    """
    try:
-        response = await library_db().list_library_agents(
+        response = await library_db.list_library_agents(
            user_id=user_id,
            search_term=search_query,
            page=1,
@@ -272,7 +272,7 @@ async def search_marketplace_agents_for_generation(
        List of LibraryAgentSummary with full input/output schemas
    """
    try:
-        response = await store_db().get_store_agents(
+        response = await store_db.get_store_agents(
            search_query=search_query,
            page=1,
            page_size=max_results,
@@ -286,7 +286,7 @@ async def search_marketplace_agents_for_generation(
            return []

        graph_ids = [agent.agent_graph_id for agent in agents_with_graphs]
-        graphs = await graph_db().get_store_listed_graphs(graph_ids)
+        graphs = await get_store_listed_graphs(*graph_ids)

        results: list[LibraryAgentSummary] = []
        for agent in agents_with_graphs:
@@ -673,10 +673,9 @@ async def save_agent_to_library(
        Tuple of (created Graph, LibraryAgent)
    """
    graph = json_to_graph(agent_json)
-    db = library_db()
    if is_update:
-        return await db.update_graph_in_library(graph, user_id)
-    return await db.create_graph_in_library(graph, user_id)
+        return await library_db.update_graph_in_library(graph, user_id)
+    return await library_db.create_graph_in_library(graph, user_id)


 def graph_to_json(graph: Graph) -> dict[str, Any]:
@@ -736,14 +735,12 @@ async def get_agent_as_json(
    Returns:
        Agent as JSON dict or None if not found
    """
-    db = graph_db()
-
-    graph = await db.get_graph(agent_id, version=None, user_id=user_id)
+    graph = await get_graph(agent_id, version=None, user_id=user_id)

    if not graph and user_id:
        try:
-            library_agent = await library_db().get_library_agent(agent_id, user_id)
-            graph = await db.get_graph(
+            library_agent = await library_db.get_library_agent(agent_id, user_id)
+            graph = await get_graph(
                library_agent.graph_id, version=None, user_id=user_id
            )
        except NotFoundError:
--- a/autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/dummy.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/dummy.py
--- a/autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/errors.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/errors.py
--- a/autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/service.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/agent_generator/service.py
--- a/autogpt_platform/backend/backend/api/features/chat/tools/agent_output.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/agent_output.py
@@ -7,9 +7,10 @@ from typing import Any

 from pydantic import BaseModel, field_validator

+from backend.api.features.chat.model import ChatSession
+from backend.api.features.library import db as library_db
 from backend.api.features.library.model import LibraryAgent
-from backend.copilot.model import ChatSession
-from backend.data.db_accessors import execution_db, library_db
+from backend.data import execution as execution_db
 from backend.data.execution import ExecutionStatus, GraphExecution, GraphExecutionMeta

 from .base import BaseTool
@@ -164,12 +165,10 @@ class AgentOutputTool(BaseTool):
        Resolve agent from provided identifiers.
        Returns (library_agent, error_message).
        """
-        lib_db = library_db()
-
        # Priority 1: Exact library agent ID
        if library_agent_id:
            try:
-                agent = await lib_db.get_library_agent(library_agent_id, user_id)
+                agent = await library_db.get_library_agent(library_agent_id, user_id)
                return agent, None
            except Exception as e:
                logger.warning(f"Failed to get library agent by ID: {e}")
@@ -183,7 +182,7 @@ class AgentOutputTool(BaseTool):
                return None, f"Agent '{store_slug}' not found in marketplace"

            # Find in user's library by graph_id
-            agent = await lib_db.get_library_agent_by_graph_id(user_id, graph.id)
+            agent = await library_db.get_library_agent_by_graph_id(user_id, graph.id)
            if not agent:
                return (
                    None,
@@ -195,7 +194,7 @@ class AgentOutputTool(BaseTool):
        # Priority 3: Fuzzy name search in library
        if agent_name:
            try:
-                response = await lib_db.list_library_agents(
+                response = await library_db.list_library_agents(
                    user_id=user_id,
                    search_term=agent_name,
                    page_size=5,
@@ -229,11 +228,9 @@ class AgentOutputTool(BaseTool):
        Fetch execution(s) based on filters.
        Returns (single_execution, available_executions_meta, error_message).
        """
-        exec_db = execution_db()
-
        # If specific execution_id provided, fetch it directly
        if execution_id:
-            execution = await exec_db.get_graph_execution(
+            execution = await execution_db.get_graph_execution(
                user_id=user_id,
                execution_id=execution_id,
                include_node_executions=False,
@@ -243,7 +240,7 @@ class AgentOutputTool(BaseTool):
            return execution, [], None

        # Get completed executions with time filters
-        executions = await exec_db.get_graph_executions(
+        executions = await execution_db.get_graph_executions(
            graph_id=graph_id,
            user_id=user_id,
            statuses=[ExecutionStatus.COMPLETED],
@@ -257,7 +254,7 @@ class AgentOutputTool(BaseTool):

        # If only one execution, fetch full details
        if len(executions) == 1:
-            full_execution = await exec_db.get_graph_execution(
+            full_execution = await execution_db.get_graph_execution(
                user_id=user_id,
                execution_id=executions[0].id,
                include_node_executions=False,
@@ -265,7 +262,7 @@ class AgentOutputTool(BaseTool):
            return full_execution, [], None

        # Multiple executions - return latest with full details, plus list of available
-        full_execution = await exec_db.get_graph_execution(
+        full_execution = await execution_db.get_graph_execution(
            user_id=user_id,
            execution_id=executions[0].id,
            include_node_executions=False,
@@ -383,7 +380,7 @@ class AgentOutputTool(BaseTool):
            and not input_data.store_slug
        ):
            # Fetch execution directly to get graph_id
-            execution = await execution_db().get_graph_execution(
+            execution = await execution_db.get_graph_execution(
                user_id=user_id,
                execution_id=input_data.execution_id,
                include_node_executions=False,
@@ -395,7 +392,7 @@ class AgentOutputTool(BaseTool):
                )

            # Find library agent by graph_id
-            agent = await library_db().get_library_agent_by_graph_id(
+            agent = await library_db.get_library_agent_by_graph_id(
                user_id, execution.graph_id
            )
            if not agent:
--- a/autogpt_platform/backend/backend/api/features/chat/tools/agent_search.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/agent_search.py
@@ -4,7 +4,8 @@ import logging
 import re
 from typing import Literal

-from backend.data.db_accessors import library_db, store_db
+from backend.api.features.library import db as library_db
+from backend.api.features.store import db as store_db
 from backend.util.exceptions import DatabaseError, NotFoundError

 from .models import (
@@ -44,10 +45,8 @@ async def _get_library_agent_by_id(user_id: str, agent_id: str) -> AgentInfo | N
    Returns:
        AgentInfo if found, None otherwise
    """
-    lib_db = library_db()
-
    try:
-        agent = await lib_db.get_library_agent_by_graph_id(user_id, agent_id)
+        agent = await library_db.get_library_agent_by_graph_id(user_id, agent_id)
        if agent:
            logger.debug(f"Found library agent by graph_id: {agent.name}")
            return AgentInfo(
@@ -72,7 +71,7 @@ async def _get_library_agent_by_id(user_id: str, agent_id: str) -> AgentInfo | N
        )

    try:
-        agent = await lib_db.get_library_agent(agent_id, user_id)
+        agent = await library_db.get_library_agent(agent_id, user_id)
        if agent:
            logger.debug(f"Found library agent by library_id: {agent.name}")
            return AgentInfo(
@@ -134,7 +133,7 @@ async def search_agents(
    try:
        if source == "marketplace":
            logger.info(f"Searching marketplace for: {query}")
-            results = await store_db().get_store_agents(search_query=query, page_size=5)
+            results = await store_db.get_store_agents(search_query=query, page_size=5)
            for agent in results.agents:
                agents.append(
                    AgentInfo(
@@ -160,7 +159,7 @@ async def search_agents(

            if not agents:
                logger.info(f"Searching user library for: {query}")
-                results = await library_db().list_library_agents(
+                results = await library_db.list_library_agents(
                    user_id=user_id,  # type: ignore[arg-type]
                    search_term=query,
                    page_size=10,
--- a/autogpt_platform/backend/backend/api/features/chat/tools/base.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/base.py
@@ -5,8 +5,8 @@ from typing import Any

 from openai.types.chat import ChatCompletionToolParam

-from backend.copilot.model import ChatSession
-from backend.copilot.response_model import StreamToolOutputAvailable
+from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.response_model import StreamToolOutputAvailable

 from .models import ErrorResponse, NeedLoginResponse, ToolResponseBase

--- a/autogpt_platform/backend/backend/api/features/chat/tools/create_agent.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/create_agent.py
@@ -3,7 +3,7 @@
 import logging
 from typing import Any

-from backend.copilot.model import ChatSession
+from backend.api.features.chat.model import ChatSession

 from .agent_generator import (
    AgentGeneratorNotConfiguredError,
--- a/autogpt_platform/backend/backend/api/features/chat/tools/customize_agent.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/customize_agent.py
@@ -3,9 +3,9 @@
 import logging
 from typing import Any

+from backend.api.features.chat.model import ChatSession
+from backend.api.features.store import db as store_db
 from backend.api.features.store.exceptions import AgentNotFoundError
-from backend.copilot.model import ChatSession
-from backend.data.db_accessors import store_db as get_store_db

 from .agent_generator import (
    AgentGeneratorNotConfiguredError,
@@ -137,8 +137,6 @@ class CustomizeAgentTool(BaseTool):

        creator_username, agent_slug = parts

-        store_db = get_store_db()
-
        # Fetch the marketplace agent details
        try:
            agent_details = await store_db.get_store_agent_details(
--- a/autogpt_platform/backend/backend/api/features/chat/tools/edit_agent.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/edit_agent.py
@@ -3,7 +3,7 @@
 import logging
 from typing import Any

-from backend.copilot.model import ChatSession
+from backend.api.features.chat.model import ChatSession

 from .agent_generator import (
    AgentGeneratorNotConfiguredError,
--- a/autogpt_platform/backend/backend/api/features/chat/tools/find_agent.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/find_agent.py
@@ -2,7 +2,7 @@

 from typing import Any

-from backend.copilot.model import ChatSession
+from backend.api.features.chat.model import ChatSession

 from .agent_search import search_agents
 from .base import BaseTool
--- a/autogpt_platform/backend/backend/api/features/chat/tools/find_block.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/find_block.py
@@ -3,18 +3,18 @@ from typing import Any

 from prisma.enums import ContentType

-from backend.blocks import get_block
-from backend.blocks._base import BlockType
-from backend.copilot.model import ChatSession
-from backend.data.db_accessors import search
-
-from .base import BaseTool, ToolResponseBase
-from .models import (
+from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.tools.base import BaseTool, ToolResponseBase
+from backend.api.features.chat.tools.models import (
    BlockInfoSummary,
+    BlockInputFieldInfo,
    BlockListResponse,
    ErrorResponse,
    NoResultsResponse,
 )
+from backend.api.features.store.hybrid_search import unified_hybrid_search
+from backend.blocks import get_block
+from backend.blocks._base import BlockType

 logger = logging.getLogger(__name__)

@@ -55,8 +55,7 @@ class FindBlockTool(BaseTool):
            "Blocks are reusable components that perform specific tasks like "
            "sending emails, making API calls, processing text, etc. "
            "IMPORTANT: Use this tool FIRST to get the block's 'id' before calling run_block. "
-            "The response includes each block's id, name, and description. "
-            "Call run_block with the block's id **with no inputs** to see detailed inputs/outputs and execute it."
+            "The response includes each block's id, required_inputs, and input_schema."
        )

    @property
@@ -108,7 +107,7 @@ class FindBlockTool(BaseTool):

        try:
            # Search for blocks using hybrid search
-            results, total = await search().unified_hybrid_search(
+            results, total = await unified_hybrid_search(
                query=query,
                content_types=[ContentType.BLOCK],
                page=1,
@@ -125,7 +124,7 @@ class FindBlockTool(BaseTool):
                    session_id=session_id,
                )

-            # Enrich results with block information
+            # Enrich results with full block information
            blocks: list[BlockInfoSummary] = []
            for result in results:
                block_id = result["content_id"]
@@ -142,12 +141,65 @@ class FindBlockTool(BaseTool):
                ):
                    continue

+                # Get input/output schemas
+                input_schema = {}
+                output_schema = {}
+                try:
+                    input_schema = block.input_schema.jsonschema()
+                except Exception as e:
+                    logger.debug(
+                        "Failed to generate input schema for block %s: %s",
+                        block_id,
+                        e,
+                    )
+                try:
+                    output_schema = block.output_schema.jsonschema()
+                except Exception as e:
+                    logger.debug(
+                        "Failed to generate output schema for block %s: %s",
+                        block_id,
+                        e,
+                    )
+
+                # Get categories from block instance
+                categories = []
+                if hasattr(block, "categories") and block.categories:
+                    categories = [cat.value for cat in block.categories]
+
+                # Extract required inputs for easier use
+                required_inputs: list[BlockInputFieldInfo] = []
+                if input_schema:
+                    properties = input_schema.get("properties", {})
+                    required_fields = set(input_schema.get("required", []))
+                    # Get credential field names to exclude from required inputs
+                    credentials_fields = set(
+                        block.input_schema.get_credentials_fields().keys()
+                    )
+
+                    for field_name, field_schema in properties.items():
+                        # Skip credential fields - they're handled separately
+                        if field_name in credentials_fields:
+                            continue
+
+                        required_inputs.append(
+                            BlockInputFieldInfo(
+                                name=field_name,
+                                type=field_schema.get("type", "string"),
+                                description=field_schema.get("description", ""),
+                                required=field_name in required_fields,
+                                default=field_schema.get("default"),
+                            )
+                        )
+
                blocks.append(
                    BlockInfoSummary(
                        id=block_id,
                        name=block.name,
                        description=block.description or "",
-                        categories=[c.value for c in block.categories],
+                        categories=categories,
+                        input_schema=input_schema,
+                        output_schema=output_schema,
+                        required_inputs=required_inputs,
                    )
                )

@@ -176,7 +228,8 @@ class FindBlockTool(BaseTool):
            return BlockListResponse(
                message=(
                    f"Found {len(blocks)} block(s) matching '{query}'. "
-                    "To see a block's inputs/outputs and execute it, use run_block with the block's 'id' - providing no inputs."
+                    "To execute a block, use run_block with the block's 'id' field "
+                    "and provide 'input_data' matching the block's input_schema."
                ),
                blocks=blocks,
                count=len(blocks),
--- a/autogpt_platform/backend/backend/api/features/chat/tools/find_block_test.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/find_block_test.py
@@ -0,0 +1,139 @@
+"""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.blocks._base 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"
--- a/autogpt_platform/backend/backend/api/features/chat/tools/find_library_agent.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/find_library_agent.py
@@ -2,7 +2,7 @@

 from typing import Any

-from backend.copilot.model import ChatSession
+from backend.api.features.chat.model import ChatSession

 from .agent_search import search_agents
 from .base import BaseTool
--- a/autogpt_platform/backend/backend/api/features/chat/tools/get_doc_page.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/get_doc_page.py
@@ -4,10 +4,13 @@ import logging
 from pathlib import Path
 from typing import Any

-from backend.copilot.model import ChatSession
-
-from .base import BaseTool
-from .models import DocPageResponse, ErrorResponse, ToolResponseBase
+from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.tools.base import BaseTool
+from backend.api.features.chat.tools.models import (
+    DocPageResponse,
+    ErrorResponse,
+    ToolResponseBase,
+)

 logger = logging.getLogger(__name__)

--- a/autogpt_platform/backend/backend/api/features/chat/tools/helpers.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/helpers.py
--- a/autogpt_platform/backend/backend/api/features/chat/tools/models.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/models.py
@@ -25,7 +25,6 @@ class ResponseType(str, Enum):
    AGENT_SAVED = "agent_saved"
    CLARIFICATION_NEEDED = "clarification_needed"
    BLOCK_LIST = "block_list"
-    BLOCK_DETAILS = "block_details"
    BLOCK_OUTPUT = "block_output"
    DOC_SEARCH_RESULTS = "doc_search_results"
    DOC_PAGE = "doc_page"
@@ -41,15 +40,6 @@ class ResponseType(str, Enum):
    OPERATION_IN_PROGRESS = "operation_in_progress"
    # Input validation
    INPUT_VALIDATION_ERROR = "input_validation_error"
-    # Web fetch
-    WEB_FETCH = "web_fetch"
-    # Code execution
-    BASH_EXEC = "bash_exec"
-    # Operation status check
-    OPERATION_STATUS = "operation_status"
-    # Feature request types
-    FEATURE_REQUEST_SEARCH = "feature_request_search"
-    FEATURE_REQUEST_CREATED = "feature_request_created"


 # Base response model
@@ -345,17 +335,11 @@ class BlockInfoSummary(BaseModel):
    name: str
    description: str
    categories: list[str]
-    input_schema: dict[str, Any] = Field(
-        default_factory=dict,
-        description="Full JSON schema for block inputs",
-    )
-    output_schema: dict[str, Any] = Field(
-        default_factory=dict,
-        description="Full JSON schema for block outputs",
-    )
+    input_schema: dict[str, Any]
+    output_schema: dict[str, Any]
    required_inputs: list[BlockInputFieldInfo] = Field(
        default_factory=list,
-        description="List of input fields for this block",
+        description="List of required input fields for this block",
    )


@@ -368,29 +352,10 @@ class BlockListResponse(ToolResponseBase):
    query: str
    usage_hint: str = Field(
        default="To execute a block, call run_block with block_id set to the block's "
-        "'id' field and input_data containing the fields listed in required_inputs."
+        "'id' field and input_data containing the required fields from input_schema."
    )


-class BlockDetails(BaseModel):
-    """Detailed block information."""
-
-    id: str
-    name: str
-    description: str
-    inputs: dict[str, Any] = {}
-    outputs: dict[str, Any] = {}
-    credentials: list[CredentialsMetaInput] = []
-
-
-class BlockDetailsResponse(ToolResponseBase):
-    """Response for block details (first run_block attempt)."""
-
-    type: ResponseType = ResponseType.BLOCK_DETAILS
-    block: BlockDetails
-    user_authenticated: bool = False
-
-
 class BlockOutputResponse(ToolResponseBase):
    """Response for run_block tool."""

@@ -456,54 +421,3 @@ class AsyncProcessingResponse(ToolResponseBase):
    status: str = "accepted"  # Must be "accepted" for detection
    operation_id: str | None = None
    task_id: str | None = None
-
-
-class WebFetchResponse(ToolResponseBase):
-    """Response for web_fetch tool."""
-
-    type: ResponseType = ResponseType.WEB_FETCH
-    url: str
-    status_code: int
-    content_type: str
-    content: str
-    truncated: bool = False
-
-
-class BashExecResponse(ToolResponseBase):
-    """Response for bash_exec tool."""
-
-    type: ResponseType = ResponseType.BASH_EXEC
-    stdout: str
-    stderr: str
-    exit_code: int
-    timed_out: bool = False
-
-
-# Feature request models
-class FeatureRequestInfo(BaseModel):
-    """Information about a feature request issue."""
-
-    id: str
-    identifier: str
-    title: str
-
-
-class FeatureRequestSearchResponse(ToolResponseBase):
-    """Response for search_feature_requests tool."""
-
-    type: ResponseType = ResponseType.FEATURE_REQUEST_SEARCH
-    results: list[FeatureRequestInfo]
-    count: int
-    query: str
-
-
-class FeatureRequestCreatedResponse(ToolResponseBase):
-    """Response for create_feature_request tool."""
-
-    type: ResponseType = ResponseType.FEATURE_REQUEST_CREATED
-    issue_id: str
-    issue_identifier: str
-    issue_title: str
-    issue_url: str
-    is_new_issue: bool  # False if added to existing
-    customer_name: str
--- a/autogpt_platform/backend/backend/api/features/chat/tools/run_agent.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/run_agent.py
@@ -5,12 +5,16 @@ from typing import Any

 from pydantic import BaseModel, Field, field_validator

-from backend.copilot.config import ChatConfig
-from backend.copilot.model import ChatSession
-from backend.copilot.tracking import track_agent_run_success, track_agent_scheduled
-from backend.data.db_accessors import graph_db, library_db, user_db
+from backend.api.features.chat.config import ChatConfig
+from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.tracking import (
+    track_agent_run_success,
+    track_agent_scheduled,
+)
+from backend.api.features.library import db as library_db
 from backend.data.graph import GraphModel
 from backend.data.model import CredentialsMetaInput
+from backend.data.user import get_user_by_id
 from backend.executor import utils as execution_utils
 from backend.util.clients import get_scheduler_client
 from backend.util.exceptions import DatabaseError, NotFoundError
@@ -196,7 +200,7 @@ class RunAgentTool(BaseTool):

            # Priority: library_agent_id if provided
            if has_library_id:
-                library_agent = await library_db().get_library_agent(
+                library_agent = await library_db.get_library_agent(
                    params.library_agent_id, user_id
                )
                if not library_agent:
@@ -205,7 +209,9 @@ class RunAgentTool(BaseTool):
                        session_id=session_id,
                    )
                # Get the graph from the library agent
-                graph = await graph_db().get_graph(
+                from backend.data.graph import get_graph
+
+                graph = await get_graph(
                    library_agent.graph_id,
                    library_agent.graph_version,
                    user_id=user_id,
@@ -516,7 +522,7 @@ class RunAgentTool(BaseTool):
        library_agent = await get_or_create_library_agent(graph, user_id)

        # Get user timezone
-        user = await user_db().get_user_by_id(user_id)
+        user = await get_user_by_id(user_id)
        user_timezone = get_user_timezone_or_utc(user.timezone if user else timezone)

        # Create schedule
--- a/autogpt_platform/backend/backend/api/features/chat/tools/run_agent_test.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/run_agent_test.py
--- a/autogpt_platform/backend/backend/api/features/chat/tools/run_block.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/run_block.py
@@ -7,24 +7,24 @@ from typing import Any

 from pydantic_core import PydanticUndefined

+from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.tools.find_block import (
+    COPILOT_EXCLUDED_BLOCK_IDS,
+    COPILOT_EXCLUDED_BLOCK_TYPES,
+)
 from backend.blocks import get_block
 from backend.blocks._base import AnyBlockSchema
-from backend.copilot.model import ChatSession
-from backend.data.db_accessors import workspace_db
 from backend.data.execution import ExecutionContext
 from backend.data.model import CredentialsFieldInfo, CredentialsMetaInput
+from backend.data.workspace import get_or_create_workspace
 from backend.integrations.creds_manager import IntegrationCredentialsManager
 from backend.util.exceptions import BlockError

 from .base import BaseTool
-from .find_block import COPILOT_EXCLUDED_BLOCK_IDS, COPILOT_EXCLUDED_BLOCK_TYPES
 from .helpers import get_inputs_from_schema
 from .models import (
-    BlockDetails,
-    BlockDetailsResponse,
    BlockOutputResponse,
    ErrorResponse,
-    InputValidationErrorResponse,
    SetupInfo,
    SetupRequirementsResponse,
    ToolResponseBase,
@@ -51,8 +51,8 @@ class RunBlockTool(BaseTool):
            "Execute a specific block with the provided input data. "
            "IMPORTANT: You MUST call find_block first to get the block's 'id' - "
            "do NOT guess or make up block IDs. "
-            "On first attempt (without input_data), returns detailed schema showing "
-            "required inputs and outputs. Then call again with proper input_data to execute."
+            "Use the 'id' from find_block results and provide input_data "
+            "matching the block's required_inputs."
        )

    @property
@@ -67,19 +67,11 @@ class RunBlockTool(BaseTool):
                        "NEVER guess this - always get it from find_block first."
                    ),
                },
-                "block_name": {
-                    "type": "string",
-                    "description": (
-                        "The block's human-readable name from find_block results. "
-                        "Used for display purposes in the UI."
-                    ),
-                },
                "input_data": {
                    "type": "object",
                    "description": (
-                        "Input values for the block. "
-                        "First call with empty {} to see the block's schema, "
-                        "then call again with proper values to execute."
+                        "Input values for the block. Use the 'required_inputs' field "
+                        "from find_block to see what fields are needed."
                    ),
                },
            },
@@ -164,34 +156,6 @@ class RunBlockTool(BaseTool):
            await self._resolve_block_credentials(user_id, block, input_data)
        )

-        # Get block schemas for details/validation
-        try:
-            input_schema: dict[str, Any] = block.input_schema.jsonschema()
-        except Exception as e:
-            logger.warning(
-                "Failed to generate input schema for block %s: %s",
-                block_id,
-                e,
-            )
-            return ErrorResponse(
-                message=f"Block '{block.name}' has an invalid input schema",
-                error=str(e),
-                session_id=session_id,
-            )
-        try:
-            output_schema: dict[str, Any] = block.output_schema.jsonschema()
-        except Exception as e:
-            logger.warning(
-                "Failed to generate output schema for block %s: %s",
-                block_id,
-                e,
-            )
-            return ErrorResponse(
-                message=f"Block '{block.name}' has an invalid output schema",
-                error=str(e),
-                session_id=session_id,
-            )
-
        if missing_credentials:
            # Return setup requirements response with missing credentials
            credentials_fields_info = block.input_schema.get_credentials_fields_info()
@@ -224,56 +188,9 @@ class RunBlockTool(BaseTool):
                graph_version=None,
            )

-        # Check if this is a first attempt (required inputs missing)
-        # Return block details so user can see what inputs are needed
-        credentials_fields = set(block.input_schema.get_credentials_fields().keys())
-        required_keys = set(input_schema.get("required", []))
-        required_non_credential_keys = required_keys - credentials_fields
-        provided_input_keys = set(input_data.keys()) - credentials_fields
-
-        # Check for unknown input fields
-        valid_fields = (
-            set(input_schema.get("properties", {}).keys()) - credentials_fields
-        )
-        unrecognized_fields = provided_input_keys - valid_fields
-        if unrecognized_fields:
-            return InputValidationErrorResponse(
-                message=(
-                    f"Unknown input field(s) provided: {', '.join(sorted(unrecognized_fields))}. "
-                    f"Block was not executed. Please use the correct field names from the schema."
-                ),
-                session_id=session_id,
-                unrecognized_fields=sorted(unrecognized_fields),
-                inputs=input_schema,
-            )
-
-        # Show details when not all required non-credential inputs are provided
-        if not (required_non_credential_keys <= provided_input_keys):
-            # Get credentials info for the response
-            credentials_meta = []
-            for field_name, cred_meta in matched_credentials.items():
-                credentials_meta.append(cred_meta)
-
-            return BlockDetailsResponse(
-                message=(
-                    f"Block '{block.name}' details. "
-                    "Provide input_data matching the inputs schema to execute the block."
-                ),
-                session_id=session_id,
-                block=BlockDetails(
-                    id=block_id,
-                    name=block.name,
-                    description=block.description or "",
-                    inputs=input_schema,
-                    outputs=output_schema,
-                    credentials=credentials_meta,
-                ),
-                user_authenticated=True,
-            )
-
        try:
            # Get or create user's workspace for CoPilot file operations
-            workspace = await workspace_db().get_or_create_workspace(user_id)
+            workspace = await get_or_create_workspace(user_id)

            # Generate synthetic IDs for CoPilot context
            # Each chat session is treated as its own agent with one continuous run
--- a/autogpt_platform/backend/backend/api/features/chat/tools/run_block_test.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/run_block_test.py
@@ -0,0 +1,106 @@
+"""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.blocks._base 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
--- a/autogpt_platform/backend/backend/api/features/chat/tools/search_docs.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/search_docs.py
@@ -5,17 +5,16 @@ from typing import Any

 from prisma.enums import ContentType

-from backend.copilot.model import ChatSession
-from backend.data.db_accessors import search
-
-from .base import BaseTool
-from .models import (
+from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.tools.base import BaseTool
+from backend.api.features.chat.tools.models import (
    DocSearchResult,
    DocSearchResultsResponse,
    ErrorResponse,
    NoResultsResponse,
    ToolResponseBase,
 )
+from backend.api.features.store.hybrid_search import unified_hybrid_search

 logger = logging.getLogger(__name__)

@@ -118,7 +117,7 @@ class SearchDocsTool(BaseTool):

        try:
            # Search using hybrid search for DOCUMENTATION content type only
-            results, total = await search().unified_hybrid_search(
+            results, total = await unified_hybrid_search(
                query=query,
                content_types=[ContentType.DOCUMENTATION],
                page=1,
--- a/autogpt_platform/backend/backend/api/features/chat/tools/utils.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/utils.py
@@ -3,8 +3,9 @@
 import logging
 from typing import Any

+from backend.api.features.library import db as library_db
 from backend.api.features.library import model as library_model
-from backend.data.db_accessors import library_db, store_db
+from backend.api.features.store import db as store_db
 from backend.data.graph import GraphModel
 from backend.data.model import (
    Credentials,
@@ -14,7 +15,6 @@ from backend.data.model import (
    OAuth2Credentials,
 )
 from backend.integrations.creds_manager import IntegrationCredentialsManager
-from backend.integrations.providers import ProviderName
 from backend.util.exceptions import NotFoundError

 logger = logging.getLogger(__name__)
@@ -38,14 +38,13 @@ async def fetch_graph_from_store_slug(
    Raises:
        DatabaseError: If there's a database error during lookup.
    """
-    sdb = store_db()
    try:
-        store_agent = await sdb.get_store_agent_details(username, agent_name)
+        store_agent = await store_db.get_store_agent_details(username, agent_name)
    except NotFoundError:
        return None, None

    # Get the graph from store listing version
-    graph = await sdb.get_available_graph(
+    graph = await store_db.get_available_graph(
        store_agent.store_listing_version_id, hide_nodes=False
    )
    return graph, store_agent
@@ -210,13 +209,13 @@ async def get_or_create_library_agent(
    Returns:
        LibraryAgent instance
    """
-    existing = await library_db().get_library_agent_by_graph_id(
+    existing = await library_db.get_library_agent_by_graph_id(
        graph_id=graph.id, user_id=user_id
    )
    if existing:
        return existing

-    library_agents = await library_db().create_library_agent(
+    library_agents = await library_db.create_library_agent(
        graph=graph,
        user_id=user_id,
        create_library_agents_for_sub_graphs=False,
@@ -360,7 +359,7 @@ async def match_user_credentials_to_graph(
        _,
        _,
    ) in aggregated_creds.items():
-        # Find first matching credential by provider, type, scopes, and host/URL
+        # Find first matching credential by provider, type, and scopes
        matching_cred = next(
            (
                cred
@@ -375,10 +374,6 @@ async def match_user_credentials_to_graph(
                    cred.type != "host_scoped"
                    or _credential_is_for_host(cred, credential_requirements)
                )
-                and (
-                    cred.provider != ProviderName.MCP
-                    or _credential_is_for_mcp_server(cred, credential_requirements)
-                )
            ),
            None,
        )
@@ -449,22 +444,6 @@ def _credential_is_for_host(
    return credential.matches_url(list(requirements.discriminator_values)[0])


-def _credential_is_for_mcp_server(
-    credential: Credentials,
-    requirements: CredentialsFieldInfo,
-) -> bool:
-    """Check if an MCP OAuth credential matches the required server URL."""
-    if not requirements.discriminator_values:
-        return True
-
-    server_url = (
-        credential.metadata.get("mcp_server_url")
-        if isinstance(credential, OAuth2Credentials)
-        else None
-    )
-    return server_url in requirements.discriminator_values if server_url else False
-
-
 async def check_user_has_required_credentials(
    user_id: str,
    required_credentials: list[CredentialsMetaInput],
--- a/autogpt_platform/backend/backend/api/features/chat/tools/workspace_files.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tools/workspace_files.py
@@ -6,8 +6,8 @@ from typing import Any, Optional

 from pydantic import BaseModel

-from backend.copilot.model import ChatSession
-from backend.data.db_accessors import workspace_db
+from backend.api.features.chat.model import ChatSession
+from backend.data.workspace import get_or_create_workspace
 from backend.util.settings import Config
 from backend.util.virus_scanner import scan_content_safe
 from backend.util.workspace import WorkspaceManager
@@ -88,9 +88,7 @@ class ListWorkspaceFilesTool(BaseTool):
    @property
    def description(self) -> str:
        return (
-            "List files in the user's persistent workspace (cloud storage). "
-            "These files survive across sessions. "
-            "For ephemeral session files, use the SDK Read/Glob tools instead. "
+            "List files in the user's workspace. "
            "Returns file names, paths, sizes, and metadata. "
            "Optionally filter by path prefix."
        )
@@ -148,7 +146,7 @@ class ListWorkspaceFilesTool(BaseTool):
        include_all_sessions: bool = kwargs.get("include_all_sessions", False)

        try:
-            workspace = await workspace_db().get_or_create_workspace(user_id)
+            workspace = await get_or_create_workspace(user_id)
            # Pass session_id for session-scoped file access
            manager = WorkspaceManager(user_id, workspace.id, session_id)

@@ -167,8 +165,8 @@ class ListWorkspaceFilesTool(BaseTool):
                    file_id=f.id,
                    name=f.name,
                    path=f.path,
-                    mime_type=f.mime_type,
-                    size_bytes=f.size_bytes,
+                    mime_type=f.mimeType,
+                    size_bytes=f.sizeBytes,
                )
                for f in files
            ]
@@ -206,9 +204,7 @@ class ReadWorkspaceFileTool(BaseTool):
    @property
    def description(self) -> str:
        return (
-            "Read a file from the user's persistent workspace (cloud storage). "
-            "These files survive across sessions. "
-            "For ephemeral session files, use the SDK Read tool instead. "
+            "Read a file from the user's workspace. "
            "Specify either file_id or path to identify the file. "
            "For small text files, returns content directly. "
            "For large or binary files, returns metadata and a download URL. "
@@ -284,7 +280,7 @@ class ReadWorkspaceFileTool(BaseTool):
            )

        try:
-            workspace = await workspace_db().get_or_create_workspace(user_id)
+            workspace = await get_or_create_workspace(user_id)
            # Pass session_id for session-scoped file access
            manager = WorkspaceManager(user_id, workspace.id, session_id)

@@ -309,8 +305,8 @@ class ReadWorkspaceFileTool(BaseTool):
                target_file_id = file_info.id

            # Decide whether to return inline content or metadata+URL
-            is_small_file = file_info.size_bytes <= self.MAX_INLINE_SIZE_BYTES
-            is_text_file = self._is_text_mime_type(file_info.mime_type)
+            is_small_file = file_info.sizeBytes <= self.MAX_INLINE_SIZE_BYTES
+            is_text_file = self._is_text_mime_type(file_info.mimeType)

            # Return inline content for small text files (unless force_download_url)
            if is_small_file and is_text_file and not force_download_url:
@@ -321,7 +317,7 @@ class ReadWorkspaceFileTool(BaseTool):
                    file_id=file_info.id,
                    name=file_info.name,
                    path=file_info.path,
-                    mime_type=file_info.mime_type,
+                    mime_type=file_info.mimeType,
                    content_base64=content_b64,
                    message=f"Successfully read file: {file_info.name}",
                    session_id=session_id,
@@ -350,11 +346,11 @@ class ReadWorkspaceFileTool(BaseTool):
                file_id=file_info.id,
                name=file_info.name,
                path=file_info.path,
-                mime_type=file_info.mime_type,
-                size_bytes=file_info.size_bytes,
+                mime_type=file_info.mimeType,
+                size_bytes=file_info.sizeBytes,
                download_url=download_url,
                preview=preview,
-                message=f"File: {file_info.name} ({file_info.size_bytes} bytes). Use download_url to retrieve content.",
+                message=f"File: {file_info.name} ({file_info.sizeBytes} bytes). Use download_url to retrieve content.",
                session_id=session_id,
            )

@@ -382,9 +378,7 @@ class WriteWorkspaceFileTool(BaseTool):
    @property
    def description(self) -> str:
        return (
-            "Write or create a file in the user's persistent workspace (cloud storage). "
-            "These files survive across sessions. "
-            "For ephemeral session files, use the SDK Write tool instead. "
+            "Write or create a file in the user's workspace. "
            "Provide the content as a base64-encoded string. "
            f"Maximum file size is {Config().max_file_size_mb}MB. "
            "Files are saved to the current session's folder by default. "
@@ -484,7 +478,7 @@ class WriteWorkspaceFileTool(BaseTool):
            # Virus scan
            await scan_content_safe(content, filename=filename)

-            workspace = await workspace_db().get_or_create_workspace(user_id)
+            workspace = await get_or_create_workspace(user_id)
            # Pass session_id for session-scoped file access
            manager = WorkspaceManager(user_id, workspace.id, session_id)

@@ -500,7 +494,7 @@ class WriteWorkspaceFileTool(BaseTool):
                file_id=file_record.id,
                name=file_record.name,
                path=file_record.path,
-                size_bytes=file_record.size_bytes,
+                size_bytes=file_record.sizeBytes,
                message=f"Successfully wrote file: {file_record.name}",
                session_id=session_id,
            )
@@ -529,7 +523,7 @@ class DeleteWorkspaceFileTool(BaseTool):
    @property
    def description(self) -> str:
        return (
-            "Delete a file from the user's persistent workspace (cloud storage). "
+            "Delete a file from the user's workspace. "
            "Specify either file_id or path to identify the file. "
            "Paths are scoped to the current session by default. "
            "Use /sessions/<session_id>/... for cross-session access."
@@ -583,7 +577,7 @@ class DeleteWorkspaceFileTool(BaseTool):
            )

        try:
-            workspace = await workspace_db().get_or_create_workspace(user_id)
+            workspace = await get_or_create_workspace(user_id)
            # Pass session_id for session-scoped file access
            manager = WorkspaceManager(user_id, workspace.id, session_id)

--- a/autogpt_platform/backend/backend/api/features/chat/tracking.py
+++ b/autogpt_platform/backend/backend/api/features/chat/tracking.py
--- a/autogpt_platform/backend/backend/api/features/integrations/router.py
+++ b/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, Any, List, Literal
+from typing import TYPE_CHECKING, Annotated, 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, model_validator
+from pydantic import BaseModel, Field, SecretStr
 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
@@ -39,11 +39,7 @@ 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.credentials_store import provider_matches
-from backend.integrations.creds_manager import (
-    IntegrationCredentialsManager,
-    create_mcp_oauth_handler,
-)
+from backend.integrations.creds_manager import IntegrationCredentialsManager
 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
@@ -106,37 +102,9 @@ class CredentialsMetaResponse(BaseModel):
    scopes: list[str] | None
    username: str | None
    host: str | None = Field(
-        default=None,
-        description="Host pattern for host-scoped or MCP server URL for MCP credentials",
+        default=None, description="Host pattern for host-scoped 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(
@@ -211,7 +179,9 @@ async def callback(
        title=credentials.title,
        scopes=credentials.scopes,
        username=credentials.username,
-        host=(CredentialsMetaResponse.get_host(credentials)),
+        host=(
+            credentials.host if isinstance(credentials, HostScopedCredentials) else None
+        ),
    )


@@ -229,7 +199,7 @@ 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=CredentialsMetaResponse.get_host(cred),
+            host=cred.host if isinstance(cred, HostScopedCredentials) else None,
        )
        for cred in credentials
    ]
@@ -252,7 +222,7 @@ 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=CredentialsMetaResponse.get_host(cred),
+            host=cred.host if isinstance(cred, HostScopedCredentials) else None,
        )
        for cred in credentials
    ]
@@ -352,11 +322,7 @@ async def delete_credentials(

    tokens_revoked = None
    if isinstance(creds, OAuth2Credentials):
-        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)
+        handler = _get_provider_oauth_handler(request, provider)
        tokens_revoked = await handler.revoke_tokens(creds)

    return CredentialsDeletionResponse(revoked=tokens_revoked)
--- a/autogpt_platform/backend/backend/api/features/mcp/init.py
+++ b/autogpt_platform/backend/backend/api/features/mcp/init.py
--- a/autogpt_platform/backend/backend/api/features/mcp/routes.py
+++ b/autogpt_platform/backend/backend/api/features/mcp/routes.py
@@ -1,404 +0,0 @@
-"""
-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
--- a/autogpt_platform/backend/backend/api/features/mcp/test_routes.py
+++ b/autogpt_platform/backend/backend/api/features/mcp/test_routes.py
@@ -1,436 +0,0 @@
-"""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()
--- a/autogpt_platform/backend/backend/api/features/workspace/routes.py
+++ b/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 WorkspaceFile, get_workspace, get_workspace_file
+from backend.data.workspace import 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: WorkspaceFile) -> Response:
+def _create_streaming_response(content: bytes, file) -> Response:
    """Create a streaming response for file content."""
    return Response(
        content=content,
-        media_type=file.mime_type,
+        media_type=file.mimeType,
        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: WorkspaceFile) -> Response:
    )


-async def _create_file_download_response(file: WorkspaceFile) -> Response:
+async def _create_file_download_response(file) -> Response:
    """
    Create a download response for a workspace file.

@@ -66,33 +66,33 @@ async def _create_file_download_response(file: WorkspaceFile) -> Response:
    storage = await get_workspace_storage()

    # For local storage, stream the file directly
-    if file.storage_path.startswith("local://"):
-        content = await storage.retrieve(file.storage_path)
+    if file.storagePath.startswith("local://"):
+        content = await storage.retrieve(file.storagePath)
        return _create_streaming_response(content, file)

    # For GCS, try to redirect to signed URL, fall back to streaming
    try:
-        url = await storage.get_download_url(file.storage_path, expires_in=300)
+        url = await storage.get_download_url(file.storagePath, expires_in=300)
        # If we got back an API path (fallback), stream directly instead
        if url.startswith("/api/"):
-            content = await storage.retrieve(file.storage_path)
+            content = await storage.retrieve(file.storagePath)
            return _create_streaming_response(content, file)
        return fastapi.responses.RedirectResponse(url=url, status_code=302)
    except Exception as e:
        # Log the signed URL failure with context
        logger.error(
            f"Failed to get signed URL for file {file.id} "
-            f"(storagePath={file.storage_path}): {e}",
+            f"(storagePath={file.storagePath}): {e}",
            exc_info=True,
        )
        # Fall back to streaming directly from GCS
        try:
-            content = await storage.retrieve(file.storage_path)
+            content = await storage.retrieve(file.storagePath)
            return _create_streaming_response(content, file)
        except Exception as fallback_error:
            logger.error(
                f"Fallback streaming also failed for file {file.id} "
-                f"(storagePath={file.storage_path}): {fallback_error}",
+                f"(storagePath={file.storagePath}): {fallback_error}",
                exc_info=True,
            )
            raise
--- a/autogpt_platform/backend/backend/api/rest_api.py
+++ b/autogpt_platform/backend/backend/api/rest_api.py
@@ -26,7 +26,6 @@ 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
@@ -41,11 +40,11 @@ import backend.data.user
 import backend.integrations.webhooks.utils
 import backend.util.service
 import backend.util.settings
-from backend.blocks.llm import DEFAULT_LLM_MODEL
-from backend.copilot.completion_consumer import (
+from backend.api.features.chat.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
@@ -344,11 +343,6 @@ 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"],
--- a/autogpt_platform/backend/backend/app.py
+++ b/autogpt_platform/backend/backend/app.py
@@ -38,9 +38,7 @@ def main(**kwargs):

    from backend.api.rest_api import AgentServer
    from backend.api.ws_api import WebsocketServer
-    from backend.copilot.executor.manager import CoPilotExecutor
-    from backend.data.db_manager import DatabaseManager
-    from backend.executor import ExecutionManager, Scheduler
+    from backend.executor import DatabaseManager, ExecutionManager, Scheduler
    from backend.notifications import NotificationManager

    run_processes(
@@ -50,7 +48,6 @@ def main(**kwargs):
        WebsocketServer(),
        AgentServer(),
        ExecutionManager(),
-        CoPilotExecutor(),
        **kwargs,
    )

--- a/autogpt_platform/backend/backend/blocks/_base.py
+++ b/autogpt_platform/backend/backend/blocks/_base.py
@@ -64,7 +64,6 @@ class BlockType(Enum):
    AI = "AI"
    AYRSHARE = "Ayrshare"
    HUMAN_IN_THE_LOOP = "Human In The Loop"
-    MCP_TOOL = "MCP Tool"


 class BlockCategory(Enum):
--- a/autogpt_platform/backend/backend/blocks/basic.py
+++ b/autogpt_platform/backend/backend/blocks/basic.py
@@ -126,7 +126,6 @@ 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"),
--- a/autogpt_platform/backend/backend/blocks/data_manipulation.py
+++ b/autogpt_platform/backend/backend/blocks/data_manipulation.py
@@ -682,219 +682,17 @@ 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."
        )
@@ -902,7 +700,7 @@ 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. Supports optional deduplication and None removal.",
+            description="Concatenates multiple lists into a single list. All elements from all input lists are combined in order.",
            categories={BlockCategory.BASIC},
            input_schema=ConcatenateListsBlock.Input,
            output_schema=ConcatenateListsBlock.Output,
@@ -911,497 +709,29 @@ 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:
-        # 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)
+        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
--- a/autogpt_platform/backend/backend/blocks/jina/search.py
+++ b/autogpt_platform/backend/backend/blocks/jina/search.py
@@ -17,7 +17,6 @@ from backend.blocks.jina._auth import (
 from backend.blocks.search import GetRequest
 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):
@@ -111,12 +110,7 @@ class ExtractWebsiteContentBlock(Block, GetRequest):
        self, input_data: Input, *, credentials: JinaCredentials, **kwargs
    ) -> BlockOutput:
        if input_data.raw_content:
-            try:
-                parsed_url, _, _ = await validate_url(input_data.url, [])
-                url = parsed_url.geturl()
-            except ValueError as e:
-                yield "error", f"Invalid URL: {e}"
-                return
+            url = input_data.url
            headers = {}
        else:
            url = f"https://r.jina.ai/{input_data.url}"
@@ -125,20 +119,5 @@ class ExtractWebsiteContentBlock(Block, GetRequest):
                "Authorization": f"Bearer {credentials.api_key.get_secret_value()}",
            }

-        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
-
+        content = await self.get_request(url, json=False, headers=headers)
        yield "content", content
--- a/autogpt_platform/backend/backend/blocks/mcp/init.py
+++ b/autogpt_platform/backend/backend/blocks/mcp/init.py
--- a/autogpt_platform/backend/backend/blocks/mcp/block.py
+++ b/autogpt_platform/backend/backend/blocks/mcp/block.py
@@ -1,300 +0,0 @@
-"""
-MCP (Model Context Protocol) Tool Block.
-
-A single dynamic block that can connect to any MCP server, discover available tools,
-and execute them. Works like AgentExecutorBlock — the user selects a tool from a
-dropdown and the input/output schema adapts dynamically.
-"""
-
-import json
-import logging
-from typing import Any, Literal
-
-from pydantic import SecretStr
-
-from backend.blocks._base import (
-    Block,
-    BlockCategory,
-    BlockSchemaInput,
-    BlockSchemaOutput,
-    BlockType,
-)
-from backend.blocks.mcp.client import MCPClient, MCPClientError
-from backend.data.block import BlockInput, BlockOutput
-from backend.data.model import (
-    CredentialsField,
-    CredentialsMetaInput,
-    OAuth2Credentials,
-    SchemaField,
-)
-from backend.integrations.providers import ProviderName
-from backend.util.json import validate_with_jsonschema
-
-logger = logging.getLogger(__name__)
-
-TEST_CREDENTIALS = OAuth2Credentials(
-    id="test-mcp-cred",
-    provider="mcp",
-    access_token=SecretStr("mock-mcp-token"),
-    refresh_token=SecretStr("mock-refresh"),
-    scopes=[],
-    title="Mock MCP credential",
-)
-TEST_CREDENTIALS_INPUT = {
-    "provider": TEST_CREDENTIALS.provider,
-    "id": TEST_CREDENTIALS.id,
-    "type": TEST_CREDENTIALS.type,
-    "title": TEST_CREDENTIALS.title,
-}
-
-
-MCPCredentials = CredentialsMetaInput[Literal[ProviderName.MCP], Literal["oauth2"]]
-
-
-class MCPToolBlock(Block):
-    """
-    A block that connects to an MCP server, lets the user pick a tool,
-    and executes it with dynamic input/output schema.
-
-    The flow:
-    1. User provides an MCP server URL (and optional credentials)
-    2. Frontend calls the backend to get tool list from that URL
-    3. User selects a tool from a dropdown (available_tools)
-    4. The block's input schema updates to reflect the selected tool's parameters
-    5. On execution, the block calls the MCP server to run the tool
-    """
-
-    class Input(BlockSchemaInput):
-        server_url: str = SchemaField(
-            description="URL of the MCP server (Streamable HTTP endpoint)",
-            placeholder="https://mcp.example.com/mcp",
-        )
-        credentials: MCPCredentials = CredentialsField(
-            discriminator="server_url",
-            description="MCP server OAuth credentials",
-            default={},
-        )
-        selected_tool: str = SchemaField(
-            description="The MCP tool to execute",
-            placeholder="Select a tool",
-            default="",
-        )
-        tool_input_schema: dict[str, Any] = SchemaField(
-            description="JSON Schema for the selected tool's input parameters. "
-            "Populated automatically when a tool is selected.",
-            default={},
-            hidden=True,
-        )
-
-        tool_arguments: dict[str, Any] = SchemaField(
-            description="Arguments to pass to the selected MCP tool. "
-            "The fields here are defined by the tool's input schema.",
-            default={},
-        )
-
-        @classmethod
-        def get_input_schema(cls, data: BlockInput) -> dict[str, Any]:
-            """Return the tool's input schema so the builder UI renders dynamic fields."""
-            return data.get("tool_input_schema", {})
-
-        @classmethod
-        def get_input_defaults(cls, data: BlockInput) -> BlockInput:
-            """Return the current tool_arguments as defaults for the dynamic fields."""
-            return data.get("tool_arguments", {})
-
-        @classmethod
-        def get_missing_input(cls, data: BlockInput) -> set[str]:
-            """Check which required tool arguments are missing."""
-            required_fields = cls.get_input_schema(data).get("required", [])
-            tool_arguments = data.get("tool_arguments", {})
-            return set(required_fields) - set(tool_arguments)
-
-        @classmethod
-        def get_mismatch_error(cls, data: BlockInput) -> str | None:
-            """Validate tool_arguments against the tool's input schema."""
-            tool_schema = cls.get_input_schema(data)
-            if not tool_schema:
-                return None
-            tool_arguments = data.get("tool_arguments", {})
-            return validate_with_jsonschema(tool_schema, tool_arguments)
-
-    class Output(BlockSchemaOutput):
-        result: Any = SchemaField(description="The result returned by the MCP tool")
-        error: str = SchemaField(description="Error message if the tool call failed")
-
-    def __init__(self):
-        super().__init__(
-            id="a0a4b1c2-d3e4-4f56-a7b8-c9d0e1f2a3b4",
-            description="Connect to any MCP server and execute its tools. "
-            "Provide a server URL, select a tool, and pass arguments dynamically.",
-            categories={BlockCategory.DEVELOPER_TOOLS},
-            input_schema=MCPToolBlock.Input,
-            output_schema=MCPToolBlock.Output,
-            block_type=BlockType.MCP_TOOL,
-            test_credentials=TEST_CREDENTIALS,
-            test_input={
-                "server_url": "https://mcp.example.com/mcp",
-                "credentials": TEST_CREDENTIALS_INPUT,
-                "selected_tool": "get_weather",
-                "tool_input_schema": {
-                    "type": "object",
-                    "properties": {"city": {"type": "string"}},
-                    "required": ["city"],
-                },
-                "tool_arguments": {"city": "London"},
-            },
-            test_output=[
-                (
-                    "result",
-                    {"weather": "sunny", "temperature": 20},
-                ),
-            ],
-            test_mock={
-                "_call_mcp_tool": lambda *a, **kw: {
-                    "weather": "sunny",
-                    "temperature": 20,
-                },
-            },
-        )
-
-    async def _call_mcp_tool(
-        self,
-        server_url: str,
-        tool_name: str,
-        arguments: dict[str, Any],
-        auth_token: str | None = None,
-    ) -> Any:
-        """Call a tool on the MCP server. Extracted for easy mocking in tests."""
-        client = MCPClient(server_url, auth_token=auth_token)
-        await client.initialize()
-        result = await client.call_tool(tool_name, arguments)
-
-        if result.is_error:
-            error_text = ""
-            for item in result.content:
-                if item.get("type") == "text":
-                    error_text += item.get("text", "")
-            raise MCPClientError(
-                f"MCP tool '{tool_name}' returned an error: "
-                f"{error_text or 'Unknown error'}"
-            )
-
-        # Extract text content from the result
-        output_parts = []
-        for item in result.content:
-            if item.get("type") == "text":
-                text = item.get("text", "")
-                # Try to parse as JSON for structured output
-                try:
-                    output_parts.append(json.loads(text))
-                except (json.JSONDecodeError, ValueError):
-                    output_parts.append(text)
-            elif item.get("type") == "image":
-                output_parts.append(
-                    {
-                        "type": "image",
-                        "data": item.get("data"),
-                        "mimeType": item.get("mimeType"),
-                    }
-                )
-            elif item.get("type") == "resource":
-                output_parts.append(item.get("resource", {}))
-
-        # If single result, unwrap
-        if len(output_parts) == 1:
-            return output_parts[0]
-        return output_parts if output_parts else None
-
-    @staticmethod
-    async def _auto_lookup_credential(
-        user_id: str, server_url: str
-    ) -> "OAuth2Credentials | None":
-        """Auto-lookup stored MCP credential for a server URL.
-
-        This is a fallback for nodes that don't have ``credentials`` explicitly
-        set (e.g. nodes created before the credential field was wired up).
-        """
-        from backend.integrations.creds_manager import IntegrationCredentialsManager
-        from backend.integrations.providers import ProviderName
-
-        try:
-            mgr = IntegrationCredentialsManager()
-            mcp_creds = await mgr.store.get_creds_by_provider(
-                user_id, ProviderName.MCP.value
-            )
-            best: OAuth2Credentials | None = None
-            for cred in mcp_creds:
-                if (
-                    isinstance(cred, OAuth2Credentials)
-                    and (cred.metadata or {}).get("mcp_server_url") == server_url
-                ):
-                    if best is None or (
-                        (cred.access_token_expires_at or 0)
-                        > (best.access_token_expires_at or 0)
-                    ):
-                        best = cred
-            if best:
-                best = await mgr.refresh_if_needed(user_id, best)
-                logger.info(
-                    "Auto-resolved MCP credential %s for %s", best.id, server_url
-                )
-            return best
-        except Exception:
-            logger.warning("Auto-lookup MCP credential failed", exc_info=True)
-            return None
-
-    async def run(
-        self,
-        input_data: Input,
-        *,
-        user_id: str,
-        credentials: OAuth2Credentials | None = None,
-        **kwargs,
-    ) -> BlockOutput:
-        if not input_data.server_url:
-            yield "error", "MCP server URL is required"
-            return
-
-        if not input_data.selected_tool:
-            yield "error", "No tool selected. Please select a tool from the dropdown."
-            return
-
-        # Validate required tool arguments before calling the server.
-        # The executor-level validation is bypassed for MCP blocks because
-        # get_input_defaults() flattens tool_arguments, stripping tool_input_schema
-        # from the validation context.
-        required = set(input_data.tool_input_schema.get("required", []))
-        if required:
-            missing = required - set(input_data.tool_arguments.keys())
-            if missing:
-                yield "error", (
-                    f"Missing required argument(s): {', '.join(sorted(missing))}. "
-                    f"Please fill in all required fields marked with * in the block form."
-                )
-                return
-
-        # If no credentials were injected by the executor (e.g. legacy nodes
-        # that don't have the credentials field set), try to auto-lookup
-        # the stored MCP credential for this server URL.
-        if credentials is None:
-            credentials = await self._auto_lookup_credential(
-                user_id, input_data.server_url
-            )
-
-        auth_token = (
-            credentials.access_token.get_secret_value() if credentials else None
-        )
-
-        try:
-            result = await self._call_mcp_tool(
-                server_url=input_data.server_url,
-                tool_name=input_data.selected_tool,
-                arguments=input_data.tool_arguments,
-                auth_token=auth_token,
-            )
-            yield "result", result
-        except MCPClientError as e:
-            yield "error", str(e)
-        except Exception as e:
-            logger.exception(f"MCP tool call failed: {e}")
-            yield "error", f"MCP tool call failed: {str(e)}"
--- a/autogpt_platform/backend/backend/blocks/mcp/client.py
+++ b/autogpt_platform/backend/backend/blocks/mcp/client.py
@@ -1,323 +0,0 @@
-"""
-MCP (Model Context Protocol) HTTP client.
-
-Implements the MCP Streamable HTTP transport for listing tools and calling tools
-on remote MCP servers. Uses JSON-RPC 2.0 over HTTP POST.
-
-Handles both JSON and SSE (text/event-stream) response formats per the MCP spec.
-
-Reference: https://modelcontextprotocol.io/specification/2025-03-26/basic/transports
-"""
-
-import json
-import logging
-from dataclasses import dataclass, field
-from typing import Any
-
-from backend.util.request import Requests
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class MCPTool:
-    """Represents an MCP tool discovered from a server."""
-
-    name: str
-    description: str
-    input_schema: dict[str, Any]
-
-
-@dataclass
-class MCPCallResult:
-    """Result from calling an MCP tool."""
-
-    content: list[dict[str, Any]] = field(default_factory=list)
-    is_error: bool = False
-
-
-class MCPClientError(Exception):
-    """Raised when an MCP protocol error occurs."""
-
-    pass
-
-
-class MCPClient:
-    """
-    Async HTTP client for the MCP Streamable HTTP transport.
-
-    Communicates with MCP servers using JSON-RPC 2.0 over HTTP POST.
-    Supports optional Bearer token authentication.
-    """
-
-    def __init__(
-        self,
-        server_url: str,
-        auth_token: str | None = None,
-    ):
-        self.server_url = server_url.rstrip("/")
-        self.auth_token = auth_token
-        self._request_id = 0
-        self._session_id: str | None = None
-
-    def _next_id(self) -> int:
-        self._request_id += 1
-        return self._request_id
-
-    def _build_headers(self) -> dict[str, str]:
-        headers = {
-            "Content-Type": "application/json",
-            "Accept": "application/json, text/event-stream",
-        }
-        if self.auth_token:
-            headers["Authorization"] = f"Bearer {self.auth_token}"
-        if self._session_id:
-            headers["Mcp-Session-Id"] = self._session_id
-        return headers
-
-    def _build_jsonrpc_request(
-        self, method: str, params: dict[str, Any] | None = None
-    ) -> dict[str, Any]:
-        req: dict[str, Any] = {
-            "jsonrpc": "2.0",
-            "method": method,
-            "id": self._next_id(),
-        }
-        if params is not None:
-            req["params"] = params
-        return req
-
-    @staticmethod
-    def _parse_sse_response(text: str) -> dict[str, Any]:
-        """Parse an SSE (text/event-stream) response body into JSON-RPC data.
-
-        MCP servers may return responses as SSE with format:
-            event: message
-            data: {"jsonrpc":"2.0","result":{...},"id":1}
-
-        We extract the last `data:` line that contains a JSON-RPC response
-        (i.e. has an "id" field), which is the reply to our request.
-        """
-        last_data: dict[str, Any] | None = None
-        for line in text.splitlines():
-            stripped = line.strip()
-            if stripped.startswith("data:"):
-                payload = stripped[len("data:") :].strip()
-                if not payload:
-                    continue
-                try:
-                    parsed = json.loads(payload)
-                    # Only keep JSON-RPC responses (have "id"), skip notifications
-                    if isinstance(parsed, dict) and "id" in parsed:
-                        last_data = parsed
-                except (json.JSONDecodeError, ValueError):
-                    continue
-        if last_data is None:
-            raise MCPClientError("No JSON-RPC response found in SSE stream")
-        return last_data
-
-    async def _send_request(
-        self, method: str, params: dict[str, Any] | None = None
-    ) -> Any:
-        """Send a JSON-RPC request to the MCP server and return the result.
-
-        Handles both ``application/json`` and ``text/event-stream`` responses
-        as required by the MCP Streamable HTTP transport specification.
-        """
-        payload = self._build_jsonrpc_request(method, params)
-        headers = self._build_headers()
-
-        requests = Requests(
-            raise_for_status=True,
-            extra_headers=headers,
-        )
-        response = await requests.post(self.server_url, json=payload)
-
-        # Capture session ID from response (MCP Streamable HTTP transport)
-        session_id = response.headers.get("Mcp-Session-Id")
-        if session_id:
-            self._session_id = session_id
-
-        content_type = response.headers.get("content-type", "")
-        if "text/event-stream" in content_type:
-            body = self._parse_sse_response(response.text())
-        else:
-            try:
-                body = response.json()
-            except Exception as e:
-                raise MCPClientError(
-                    f"MCP server returned non-JSON response: {e}"
-                ) from e
-
-        if not isinstance(body, dict):
-            raise MCPClientError(
-                f"MCP server returned unexpected JSON type: {type(body).__name__}"
-            )
-
-        # Handle JSON-RPC error
-        if "error" in body:
-            error = body["error"]
-            if isinstance(error, dict):
-                raise MCPClientError(
-                    f"MCP server error [{error.get('code', '?')}]: "
-                    f"{error.get('message', 'Unknown error')}"
-                )
-            raise MCPClientError(f"MCP server error: {error}")
-
-        return body.get("result")
-
-    async def _send_notification(self, method: str) -> None:
-        """Send a JSON-RPC notification (no id, no response expected)."""
-        headers = self._build_headers()
-        notification = {"jsonrpc": "2.0", "method": method}
-        requests = Requests(
-            raise_for_status=False,
-            extra_headers=headers,
-        )
-        await requests.post(self.server_url, json=notification)
-
-    async def discover_auth(self) -> dict[str, Any] | None:
-        """Probe the MCP server's OAuth metadata (RFC 9728 / MCP spec).
-
-        Returns ``None`` if the server doesn't require auth, otherwise returns
-        a dict with:
-          - ``authorization_servers``: list of authorization server URLs
-          - ``resource``: the resource indicator URL (usually the MCP endpoint)
-          - ``scopes_supported``: optional list of supported scopes
-
-        The caller can then fetch the authorization server metadata to get
-        ``authorization_endpoint``, ``token_endpoint``, etc.
-        """
-        from urllib.parse import urlparse
-
-        parsed = urlparse(self.server_url)
-        base = f"{parsed.scheme}://{parsed.netloc}"
-
-        # Build candidates for protected-resource metadata (per RFC 9728)
-        path = parsed.path.rstrip("/")
-        candidates = []
-        if path and path != "/":
-            candidates.append(f"{base}/.well-known/oauth-protected-resource{path}")
-        candidates.append(f"{base}/.well-known/oauth-protected-resource")
-
-        requests = Requests(
-            raise_for_status=False,
-        )
-        for url in candidates:
-            try:
-                resp = await requests.get(url)
-                if resp.status == 200:
-                    data = resp.json()
-                    if isinstance(data, dict) and "authorization_servers" in data:
-                        return data
-            except Exception:
-                continue
-
-        return None
-
-    async def discover_auth_server_metadata(
-        self, auth_server_url: str
-    ) -> dict[str, Any] | None:
-        """Fetch the OAuth Authorization Server Metadata (RFC 8414).
-
-        Given an authorization server URL, returns a dict with:
-          - ``authorization_endpoint``
-          - ``token_endpoint``
-          - ``registration_endpoint`` (for dynamic client registration)
-          - ``scopes_supported``
-          - ``code_challenge_methods_supported``
-          - etc.
-        """
-        from urllib.parse import urlparse
-
-        parsed = urlparse(auth_server_url)
-        base = f"{parsed.scheme}://{parsed.netloc}"
-        path = parsed.path.rstrip("/")
-
-        # Try standard metadata endpoints (RFC 8414 and OpenID Connect)
-        candidates = []
-        if path and path != "/":
-            candidates.append(f"{base}/.well-known/oauth-authorization-server{path}")
-        candidates.append(f"{base}/.well-known/oauth-authorization-server")
-        candidates.append(f"{base}/.well-known/openid-configuration")
-
-        requests = Requests(
-            raise_for_status=False,
-        )
-        for url in candidates:
-            try:
-                resp = await requests.get(url)
-                if resp.status == 200:
-                    data = resp.json()
-                    if isinstance(data, dict) and "authorization_endpoint" in data:
-                        return data
-            except Exception:
-                continue
-
-        return None
-
-    async def initialize(self) -> dict[str, Any]:
-        """
-        Send the MCP initialize request.
-
-        This is required by the MCP protocol before any other requests.
-        Returns the server's capabilities.
-        """
-        result = await self._send_request(
-            "initialize",
-            {
-                "protocolVersion": "2025-03-26",
-                "capabilities": {},
-                "clientInfo": {"name": "AutoGPT-Platform", "version": "1.0.0"},
-            },
-        )
-        # Send initialized notification (no response expected)
-        await self._send_notification("notifications/initialized")
-
-        return result or {}
-
-    async def list_tools(self) -> list[MCPTool]:
-        """
-        Discover available tools from the MCP server.
-
-        Returns a list of MCPTool objects with name, description, and input schema.
-        """
-        result = await self._send_request("tools/list")
-        if not result or "tools" not in result:
-            return []
-
-        tools = []
-        for tool_data in result["tools"]:
-            tools.append(
-                MCPTool(
-                    name=tool_data.get("name", ""),
-                    description=tool_data.get("description", ""),
-                    input_schema=tool_data.get("inputSchema", {}),
-                )
-            )
-        return tools
-
-    async def call_tool(
-        self, tool_name: str, arguments: dict[str, Any]
-    ) -> MCPCallResult:
-        """
-        Call a tool on the MCP server.
-
-        Args:
-            tool_name: The name of the tool to call.
-            arguments: The arguments to pass to the tool.
-
-        Returns:
-            MCPCallResult with the tool's response content.
-        """
-        result = await self._send_request(
-            "tools/call",
-            {"name": tool_name, "arguments": arguments},
-        )
-        if not result:
-            return MCPCallResult(is_error=True)
-
-        return MCPCallResult(
-            content=result.get("content", []),
-            is_error=result.get("isError", False),
-        )
--- a/autogpt_platform/backend/backend/blocks/mcp/oauth.py
+++ b/autogpt_platform/backend/backend/blocks/mcp/oauth.py
@@ -1,204 +0,0 @@
-"""
-MCP OAuth handler for MCP servers that use OAuth 2.1 authorization.
-
-Unlike other OAuth handlers (GitHub, Google, etc.) where endpoints are fixed,
-MCP servers have dynamic endpoints discovered via RFC 9728 / RFC 8414 metadata.
-This handler accepts those endpoints at construction time.
-"""
-
-import logging
-import time
-import urllib.parse
-from typing import ClassVar, Optional
-
-from pydantic import SecretStr
-
-from backend.data.model import OAuth2Credentials
-from backend.integrations.oauth.base import BaseOAuthHandler
-from backend.integrations.providers import ProviderName
-from backend.util.request import Requests
-
-logger = logging.getLogger(__name__)
-
-
-class MCPOAuthHandler(BaseOAuthHandler):
-    """
-    OAuth handler for MCP servers with dynamically-discovered endpoints.
-
-    Construction requires the authorization and token endpoint URLs,
-    which are obtained via MCP OAuth metadata discovery
-    (``MCPClient.discover_auth`` + ``discover_auth_server_metadata``).
-    """
-
-    PROVIDER_NAME: ClassVar[ProviderName | str] = ProviderName.MCP
-    DEFAULT_SCOPES: ClassVar[list[str]] = []
-
-    def __init__(
-        self,
-        client_id: str,
-        client_secret: str,
-        redirect_uri: str,
-        *,
-        authorize_url: str,
-        token_url: str,
-        revoke_url: str | None = None,
-        resource_url: str | None = None,
-    ):
-        self.client_id = client_id
-        self.client_secret = client_secret
-        self.redirect_uri = redirect_uri
-        self.authorize_url = authorize_url
-        self.token_url = token_url
-        self.revoke_url = revoke_url
-        self.resource_url = resource_url
-
-    def get_login_url(
-        self,
-        scopes: list[str],
-        state: str,
-        code_challenge: Optional[str],
-    ) -> str:
-        scopes = self.handle_default_scopes(scopes)
-
-        params: dict[str, str] = {
-            "response_type": "code",
-            "client_id": self.client_id,
-            "redirect_uri": self.redirect_uri,
-            "state": state,
-        }
-        if scopes:
-            params["scope"] = " ".join(scopes)
-        # PKCE (S256) — included when the caller provides a code_challenge
-        if code_challenge:
-            params["code_challenge"] = code_challenge
-            params["code_challenge_method"] = "S256"
-        # MCP spec requires resource indicator (RFC 8707)
-        if self.resource_url:
-            params["resource"] = self.resource_url
-
-        return f"{self.authorize_url}?{urllib.parse.urlencode(params)}"
-
-    async def exchange_code_for_tokens(
-        self,
-        code: str,
-        scopes: list[str],
-        code_verifier: Optional[str],
-    ) -> OAuth2Credentials:
-        data: dict[str, str] = {
-            "grant_type": "authorization_code",
-            "code": code,
-            "redirect_uri": self.redirect_uri,
-            "client_id": self.client_id,
-        }
-        if self.client_secret:
-            data["client_secret"] = self.client_secret
-        if code_verifier:
-            data["code_verifier"] = code_verifier
-        if self.resource_url:
-            data["resource"] = self.resource_url
-
-        response = await Requests(raise_for_status=True).post(
-            self.token_url,
-            data=data,
-            headers={"Content-Type": "application/x-www-form-urlencoded"},
-        )
-        tokens = response.json()
-
-        if "error" in tokens:
-            raise RuntimeError(
-                f"Token exchange failed: {tokens.get('error_description', tokens['error'])}"
-            )
-
-        if "access_token" not in tokens:
-            raise RuntimeError("OAuth token response missing 'access_token' field")
-
-        now = int(time.time())
-        expires_in = tokens.get("expires_in")
-
-        return OAuth2Credentials(
-            provider=self.PROVIDER_NAME,
-            title=None,
-            access_token=SecretStr(tokens["access_token"]),
-            refresh_token=(
-                SecretStr(tokens["refresh_token"])
-                if tokens.get("refresh_token")
-                else None
-            ),
-            access_token_expires_at=now + expires_in if expires_in else None,
-            refresh_token_expires_at=None,
-            scopes=scopes,
-            metadata={
-                "mcp_token_url": self.token_url,
-                "mcp_resource_url": self.resource_url,
-            },
-        )
-
-    async def _refresh_tokens(
-        self, credentials: OAuth2Credentials
-    ) -> OAuth2Credentials:
-        if not credentials.refresh_token:
-            raise ValueError("No refresh token available for MCP OAuth credentials")
-
-        data: dict[str, str] = {
-            "grant_type": "refresh_token",
-            "refresh_token": credentials.refresh_token.get_secret_value(),
-            "client_id": self.client_id,
-        }
-        if self.client_secret:
-            data["client_secret"] = self.client_secret
-        if self.resource_url:
-            data["resource"] = self.resource_url
-
-        response = await Requests(raise_for_status=True).post(
-            self.token_url,
-            data=data,
-            headers={"Content-Type": "application/x-www-form-urlencoded"},
-        )
-        tokens = response.json()
-
-        if "error" in tokens:
-            raise RuntimeError(
-                f"Token refresh failed: {tokens.get('error_description', tokens['error'])}"
-            )
-
-        if "access_token" not in tokens:
-            raise RuntimeError("OAuth refresh response missing 'access_token' field")
-
-        now = int(time.time())
-        expires_in = tokens.get("expires_in")
-
-        return OAuth2Credentials(
-            id=credentials.id,
-            provider=self.PROVIDER_NAME,
-            title=credentials.title,
-            access_token=SecretStr(tokens["access_token"]),
-            refresh_token=(
-                SecretStr(tokens["refresh_token"])
-                if tokens.get("refresh_token")
-                else credentials.refresh_token
-            ),
-            access_token_expires_at=now + expires_in if expires_in else None,
-            refresh_token_expires_at=credentials.refresh_token_expires_at,
-            scopes=credentials.scopes,
-            metadata=credentials.metadata,
-        )
-
-    async def revoke_tokens(self, credentials: OAuth2Credentials) -> bool:
-        if not self.revoke_url:
-            return False
-
-        try:
-            data = {
-                "token": credentials.access_token.get_secret_value(),
-                "token_type_hint": "access_token",
-                "client_id": self.client_id,
-            }
-            await Requests().post(
-                self.revoke_url,
-                data=data,
-                headers={"Content-Type": "application/x-www-form-urlencoded"},
-            )
-            return True
-        except Exception:
-            logger.warning("Failed to revoke MCP OAuth tokens", exc_info=True)
-            return False
--- a/autogpt_platform/backend/backend/blocks/mcp/test_e2e.py
+++ b/autogpt_platform/backend/backend/blocks/mcp/test_e2e.py
@@ -1,109 +0,0 @@
-"""
-End-to-end tests against a real public MCP server.
-
-These tests hit the OpenAI docs MCP server (https://developers.openai.com/mcp)
-which is publicly accessible without authentication and returns SSE responses.
-
-Mark: These are tagged with ``@pytest.mark.e2e`` so they can be run/skipped
-independently of the rest of the test suite (they require network access).
-"""
-
-import json
-import os
-
-import pytest
-
-from backend.blocks.mcp.client import MCPClient
-
-# Public MCP server that requires no authentication
-OPENAI_DOCS_MCP_URL = "https://developers.openai.com/mcp"
-
-# Skip all tests in this module unless RUN_E2E env var is set
-pytestmark = pytest.mark.skipif(
-    not os.environ.get("RUN_E2E"), reason="set RUN_E2E=1 to run e2e tests"
-)
-
-
-class TestRealMCPServer:
-    """Tests against the live OpenAI docs MCP server."""
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_initialize(self):
-        """Verify we can complete the MCP handshake with a real server."""
-        client = MCPClient(OPENAI_DOCS_MCP_URL)
-        result = await client.initialize()
-
-        assert result["protocolVersion"] == "2025-03-26"
-        assert "serverInfo" in result
-        assert result["serverInfo"]["name"] == "openai-docs-mcp"
-        assert "tools" in result.get("capabilities", {})
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_list_tools(self):
-        """Verify we can discover tools from a real MCP server."""
-        client = MCPClient(OPENAI_DOCS_MCP_URL)
-        await client.initialize()
-        tools = await client.list_tools()
-
-        assert len(tools) >= 3  # server has at least 5 tools as of writing
-
-        tool_names = {t.name for t in tools}
-        # These tools are documented and should be stable
-        assert "search_openai_docs" in tool_names
-        assert "list_openai_docs" in tool_names
-        assert "fetch_openai_doc" in tool_names
-
-        # Verify schema structure
-        search_tool = next(t for t in tools if t.name == "search_openai_docs")
-        assert "query" in search_tool.input_schema.get("properties", {})
-        assert "query" in search_tool.input_schema.get("required", [])
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_tool_list_api_endpoints(self):
-        """Call the list_api_endpoints tool and verify we get real data."""
-        client = MCPClient(OPENAI_DOCS_MCP_URL)
-        await client.initialize()
-        result = await client.call_tool("list_api_endpoints", {})
-
-        assert not result.is_error
-        assert len(result.content) >= 1
-        assert result.content[0]["type"] == "text"
-
-        data = json.loads(result.content[0]["text"])
-        assert "paths" in data or "urls" in data
-        # The OpenAI API should have many endpoints
-        total = data.get("total", len(data.get("paths", [])))
-        assert total > 50
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_tool_search(self):
-        """Search for docs and verify we get results."""
-        client = MCPClient(OPENAI_DOCS_MCP_URL)
-        await client.initialize()
-        result = await client.call_tool(
-            "search_openai_docs", {"query": "chat completions", "limit": 3}
-        )
-
-        assert not result.is_error
-        assert len(result.content) >= 1
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_sse_response_handling(self):
-        """Verify the client correctly handles SSE responses from a real server.
-
-        This is the key test — our local test server returns JSON,
-        but real MCP servers typically return SSE. This proves the
-        SSE parsing works end-to-end.
-        """
-        client = MCPClient(OPENAI_DOCS_MCP_URL)
-        # initialize() internally calls _send_request which must parse SSE
-        result = await client.initialize()
-
-        # If we got here without error, SSE parsing works
-        assert isinstance(result, dict)
-        assert "protocolVersion" in result
-
-        # Also verify list_tools works (another SSE response)
-        tools = await client.list_tools()
-        assert len(tools) > 0
-        assert all(hasattr(t, "name") for t in tools)
--- a/autogpt_platform/backend/backend/blocks/mcp/test_integration.py
+++ b/autogpt_platform/backend/backend/blocks/mcp/test_integration.py
@@ -1,389 +0,0 @@
-"""
-Integration tests for MCP client and MCPToolBlock against a real HTTP server.
-
-These tests spin up a local MCP test server and run the full client/block flow
-against it — no mocking, real HTTP requests.
-"""
-
-import asyncio
-import json
-import threading
-from unittest.mock import patch
-
-import pytest
-from aiohttp import web
-from pydantic import SecretStr
-
-from backend.blocks.mcp.block import MCPToolBlock
-from backend.blocks.mcp.client import MCPClient
-from backend.blocks.mcp.test_server import create_test_mcp_app
-from backend.data.model import OAuth2Credentials
-
-MOCK_USER_ID = "test-user-integration"
-
-
-class _MCPTestServer:
-    """
-    Run an MCP test server in a background thread with its own event loop.
-    This avoids event loop conflicts with pytest-asyncio.
-    """
-
-    def __init__(self, auth_token: str | None = None):
-        self.auth_token = auth_token
-        self.url: str = ""
-        self._runner: web.AppRunner | None = None
-        self._loop: asyncio.AbstractEventLoop | None = None
-        self._thread: threading.Thread | None = None
-        self._started = threading.Event()
-
-    def _run(self):
-        self._loop = asyncio.new_event_loop()
-        asyncio.set_event_loop(self._loop)
-        self._loop.run_until_complete(self._start())
-        self._started.set()
-        self._loop.run_forever()
-
-    async def _start(self):
-        app = create_test_mcp_app(auth_token=self.auth_token)
-        self._runner = web.AppRunner(app)
-        await self._runner.setup()
-        site = web.TCPSite(self._runner, "127.0.0.1", 0)
-        await site.start()
-        port = site._server.sockets[0].getsockname()[1]  # type: ignore[union-attr]
-        self.url = f"http://127.0.0.1:{port}/mcp"
-
-    def start(self):
-        self._thread = threading.Thread(target=self._run, daemon=True)
-        self._thread.start()
-        if not self._started.wait(timeout=5):
-            raise RuntimeError("MCP test server failed to start within 5 seconds")
-        return self
-
-    def stop(self):
-        if self._loop and self._runner:
-            asyncio.run_coroutine_threadsafe(self._runner.cleanup(), self._loop).result(
-                timeout=5
-            )
-            self._loop.call_soon_threadsafe(self._loop.stop)
-        if self._thread:
-            self._thread.join(timeout=5)
-
-
-@pytest.fixture(scope="module")
-def mcp_server():
-    """Start a local MCP test server in a background thread."""
-    server = _MCPTestServer()
-    server.start()
-    yield server.url
-    server.stop()
-
-
-@pytest.fixture(scope="module")
-def mcp_server_with_auth():
-    """Start a local MCP test server with auth in a background thread."""
-    server = _MCPTestServer(auth_token="test-secret-token")
-    server.start()
-    yield server.url, "test-secret-token"
-    server.stop()
-
-
-@pytest.fixture(autouse=True)
-def _allow_localhost():
-    """
-    Allow 127.0.0.1 through SSRF protection for integration tests.
-
-    The Requests class blocks private IPs by default. We patch the Requests
-    constructor to always include 127.0.0.1 as a trusted origin so the local
-    test server is reachable.
-    """
-    from backend.util.request import Requests
-
-    original_init = Requests.__init__
-
-    def patched_init(self, *args, **kwargs):
-        trusted = list(kwargs.get("trusted_origins") or [])
-        trusted.append("http://127.0.0.1")
-        kwargs["trusted_origins"] = trusted
-        original_init(self, *args, **kwargs)
-
-    with patch.object(Requests, "__init__", patched_init):
-        yield
-
-
-def _make_client(url: str, auth_token: str | None = None) -> MCPClient:
-    """Create an MCPClient for integration tests."""
-    return MCPClient(url, auth_token=auth_token)
-
-
-# ── MCPClient integration tests ──────────────────────────────────────
-
-
-class TestMCPClientIntegration:
-    """Test MCPClient against a real local MCP server."""
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_initialize(self, mcp_server):
-        client = _make_client(mcp_server)
-        result = await client.initialize()
-
-        assert result["protocolVersion"] == "2025-03-26"
-        assert result["serverInfo"]["name"] == "test-mcp-server"
-        assert "tools" in result["capabilities"]
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_list_tools(self, mcp_server):
-        client = _make_client(mcp_server)
-        await client.initialize()
-        tools = await client.list_tools()
-
-        assert len(tools) == 3
-
-        tool_names = {t.name for t in tools}
-        assert tool_names == {"get_weather", "add_numbers", "echo"}
-
-        # Check get_weather schema
-        weather = next(t for t in tools if t.name == "get_weather")
-        assert weather.description == "Get current weather for a city"
-        assert "city" in weather.input_schema["properties"]
-        assert weather.input_schema["required"] == ["city"]
-
-        # Check add_numbers schema
-        add = next(t for t in tools if t.name == "add_numbers")
-        assert "a" in add.input_schema["properties"]
-        assert "b" in add.input_schema["properties"]
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_tool_get_weather(self, mcp_server):
-        client = _make_client(mcp_server)
-        await client.initialize()
-        result = await client.call_tool("get_weather", {"city": "London"})
-
-        assert not result.is_error
-        assert len(result.content) == 1
-        assert result.content[0]["type"] == "text"
-
-        data = json.loads(result.content[0]["text"])
-        assert data["city"] == "London"
-        assert data["temperature"] == 22
-        assert data["condition"] == "sunny"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_tool_add_numbers(self, mcp_server):
-        client = _make_client(mcp_server)
-        await client.initialize()
-        result = await client.call_tool("add_numbers", {"a": 3, "b": 7})
-
-        assert not result.is_error
-        data = json.loads(result.content[0]["text"])
-        assert data["result"] == 10
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_tool_echo(self, mcp_server):
-        client = _make_client(mcp_server)
-        await client.initialize()
-        result = await client.call_tool("echo", {"message": "Hello MCP!"})
-
-        assert not result.is_error
-        assert result.content[0]["text"] == "Hello MCP!"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_unknown_tool(self, mcp_server):
-        client = _make_client(mcp_server)
-        await client.initialize()
-        result = await client.call_tool("nonexistent_tool", {})
-
-        assert result.is_error
-        assert "Unknown tool" in result.content[0]["text"]
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_auth_success(self, mcp_server_with_auth):
-        url, token = mcp_server_with_auth
-        client = _make_client(url, auth_token=token)
-        result = await client.initialize()
-
-        assert result["protocolVersion"] == "2025-03-26"
-
-        tools = await client.list_tools()
-        assert len(tools) == 3
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_auth_failure(self, mcp_server_with_auth):
-        url, _ = mcp_server_with_auth
-        client = _make_client(url, auth_token="wrong-token")
-
-        with pytest.raises(Exception):
-            await client.initialize()
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_auth_missing(self, mcp_server_with_auth):
-        url, _ = mcp_server_with_auth
-        client = _make_client(url)
-
-        with pytest.raises(Exception):
-            await client.initialize()
-
-
-# ── MCPToolBlock integration tests ───────────────────────────────────
-
-
-class TestMCPToolBlockIntegration:
-    """Test MCPToolBlock end-to-end against a real local MCP server."""
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_full_flow_get_weather(self, mcp_server):
-        """Full flow: discover tools, select one, execute it."""
-        # Step 1: Discover tools (simulating what the frontend/API would do)
-        client = _make_client(mcp_server)
-        await client.initialize()
-        tools = await client.list_tools()
-        assert len(tools) == 3
-
-        # Step 2: User selects "get_weather" and we get its schema
-        weather_tool = next(t for t in tools if t.name == "get_weather")
-
-        # Step 3: Execute the block — no credentials (public server)
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url=mcp_server,
-            selected_tool="get_weather",
-            tool_input_schema=weather_tool.input_schema,
-            tool_arguments={"city": "Paris"},
-        )
-
-        outputs = []
-        async for name, data in block.run(input_data, user_id=MOCK_USER_ID):
-            outputs.append((name, data))
-
-        assert len(outputs) == 1
-        assert outputs[0][0] == "result"
-        result = outputs[0][1]
-        assert result["city"] == "Paris"
-        assert result["temperature"] == 22
-        assert result["condition"] == "sunny"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_full_flow_add_numbers(self, mcp_server):
-        """Full flow for add_numbers tool."""
-        client = _make_client(mcp_server)
-        await client.initialize()
-        tools = await client.list_tools()
-        add_tool = next(t for t in tools if t.name == "add_numbers")
-
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url=mcp_server,
-            selected_tool="add_numbers",
-            tool_input_schema=add_tool.input_schema,
-            tool_arguments={"a": 42, "b": 58},
-        )
-
-        outputs = []
-        async for name, data in block.run(input_data, user_id=MOCK_USER_ID):
-            outputs.append((name, data))
-
-        assert len(outputs) == 1
-        assert outputs[0][0] == "result"
-        assert outputs[0][1]["result"] == 100
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_full_flow_echo_plain_text(self, mcp_server):
-        """Verify plain text (non-JSON) responses work."""
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url=mcp_server,
-            selected_tool="echo",
-            tool_input_schema={
-                "type": "object",
-                "properties": {"message": {"type": "string"}},
-                "required": ["message"],
-            },
-            tool_arguments={"message": "Hello from AutoGPT!"},
-        )
-
-        outputs = []
-        async for name, data in block.run(input_data, user_id=MOCK_USER_ID):
-            outputs.append((name, data))
-
-        assert len(outputs) == 1
-        assert outputs[0][0] == "result"
-        assert outputs[0][1] == "Hello from AutoGPT!"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_full_flow_unknown_tool_yields_error(self, mcp_server):
-        """Calling an unknown tool should yield an error output."""
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url=mcp_server,
-            selected_tool="nonexistent_tool",
-            tool_arguments={},
-        )
-
-        outputs = []
-        async for name, data in block.run(input_data, user_id=MOCK_USER_ID):
-            outputs.append((name, data))
-
-        assert len(outputs) == 1
-        assert outputs[0][0] == "error"
-        assert "returned an error" in outputs[0][1]
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_full_flow_with_auth(self, mcp_server_with_auth):
-        """Full flow with authentication via credentials kwarg."""
-        url, token = mcp_server_with_auth
-
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url=url,
-            selected_tool="echo",
-            tool_input_schema={
-                "type": "object",
-                "properties": {"message": {"type": "string"}},
-                "required": ["message"],
-            },
-            tool_arguments={"message": "Authenticated!"},
-        )
-
-        # Pass credentials via the standard kwarg (as the executor would)
-        test_creds = OAuth2Credentials(
-            id="test-cred",
-            provider="mcp",
-            access_token=SecretStr(token),
-            refresh_token=SecretStr(""),
-            scopes=[],
-            title="Test MCP credential",
-        )
-
-        outputs = []
-        async for name, data in block.run(
-            input_data, user_id=MOCK_USER_ID, credentials=test_creds
-        ):
-            outputs.append((name, data))
-
-        assert len(outputs) == 1
-        assert outputs[0][0] == "result"
-        assert outputs[0][1] == "Authenticated!"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_no_credentials_runs_without_auth(self, mcp_server):
-        """Block runs without auth when no credentials are provided."""
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url=mcp_server,
-            selected_tool="echo",
-            tool_input_schema={
-                "type": "object",
-                "properties": {"message": {"type": "string"}},
-                "required": ["message"],
-            },
-            tool_arguments={"message": "No auth needed"},
-        )
-
-        outputs = []
-        async for name, data in block.run(
-            input_data, user_id=MOCK_USER_ID, credentials=None
-        ):
-            outputs.append((name, data))
-
-        assert len(outputs) == 1
-        assert outputs[0][0] == "result"
-        assert outputs[0][1] == "No auth needed"
--- a/autogpt_platform/backend/backend/blocks/mcp/test_mcp.py
+++ b/autogpt_platform/backend/backend/blocks/mcp/test_mcp.py
@@ -1,619 +0,0 @@
-"""
-Tests for MCP client and MCPToolBlock.
-"""
-
-import json
-from unittest.mock import AsyncMock, patch
-
-import pytest
-
-from backend.blocks.mcp.block import MCPToolBlock
-from backend.blocks.mcp.client import MCPCallResult, MCPClient, MCPClientError
-from backend.util.test import execute_block_test
-
-# ── SSE parsing unit tests ───────────────────────────────────────────
-
-
-class TestSSEParsing:
-    """Tests for SSE (text/event-stream) response parsing."""
-
-    def test_parse_sse_simple(self):
-        sse = (
-            "event: message\n"
-            'data: {"jsonrpc":"2.0","result":{"tools":[]},"id":1}\n'
-            "\n"
-        )
-        body = MCPClient._parse_sse_response(sse)
-        assert body["result"] == {"tools": []}
-        assert body["id"] == 1
-
-    def test_parse_sse_with_notifications(self):
-        """SSE streams can contain notifications (no id) before the response."""
-        sse = (
-            "event: message\n"
-            'data: {"jsonrpc":"2.0","method":"some/notification"}\n'
-            "\n"
-            "event: message\n"
-            'data: {"jsonrpc":"2.0","result":{"ok":true},"id":2}\n'
-            "\n"
-        )
-        body = MCPClient._parse_sse_response(sse)
-        assert body["result"] == {"ok": True}
-        assert body["id"] == 2
-
-    def test_parse_sse_error_response(self):
-        sse = (
-            "event: message\n"
-            'data: {"jsonrpc":"2.0","error":{"code":-32600,"message":"Bad Request"},"id":1}\n'
-        )
-        body = MCPClient._parse_sse_response(sse)
-        assert "error" in body
-        assert body["error"]["code"] == -32600
-
-    def test_parse_sse_no_data_raises(self):
-        with pytest.raises(MCPClientError, match="No JSON-RPC response found"):
-            MCPClient._parse_sse_response("event: message\n\n")
-
-    def test_parse_sse_empty_raises(self):
-        with pytest.raises(MCPClientError, match="No JSON-RPC response found"):
-            MCPClient._parse_sse_response("")
-
-    def test_parse_sse_ignores_non_data_lines(self):
-        sse = (
-            ": comment line\n"
-            "event: message\n"
-            "id: 123\n"
-            'data: {"jsonrpc":"2.0","result":"ok","id":1}\n'
-            "\n"
-        )
-        body = MCPClient._parse_sse_response(sse)
-        assert body["result"] == "ok"
-
-    def test_parse_sse_uses_last_response(self):
-        """If multiple responses exist, use the last one."""
-        sse = (
-            'data: {"jsonrpc":"2.0","result":"first","id":1}\n'
-            "\n"
-            'data: {"jsonrpc":"2.0","result":"second","id":2}\n'
-            "\n"
-        )
-        body = MCPClient._parse_sse_response(sse)
-        assert body["result"] == "second"
-
-
-# ── MCPClient unit tests ─────────────────────────────────────────────
-
-
-class TestMCPClient:
-    """Tests for the MCP HTTP client."""
-
-    def test_build_headers_without_auth(self):
-        client = MCPClient("https://mcp.example.com")
-        headers = client._build_headers()
-        assert "Authorization" not in headers
-        assert headers["Content-Type"] == "application/json"
-
-    def test_build_headers_with_auth(self):
-        client = MCPClient("https://mcp.example.com", auth_token="my-token")
-        headers = client._build_headers()
-        assert headers["Authorization"] == "Bearer my-token"
-
-    def test_build_jsonrpc_request(self):
-        client = MCPClient("https://mcp.example.com")
-        req = client._build_jsonrpc_request("tools/list")
-        assert req["jsonrpc"] == "2.0"
-        assert req["method"] == "tools/list"
-        assert "id" in req
-        assert "params" not in req
-
-    def test_build_jsonrpc_request_with_params(self):
-        client = MCPClient("https://mcp.example.com")
-        req = client._build_jsonrpc_request(
-            "tools/call", {"name": "test", "arguments": {"x": 1}}
-        )
-        assert req["params"] == {"name": "test", "arguments": {"x": 1}}
-
-    def test_request_id_increments(self):
-        client = MCPClient("https://mcp.example.com")
-        req1 = client._build_jsonrpc_request("tools/list")
-        req2 = client._build_jsonrpc_request("tools/list")
-        assert req2["id"] > req1["id"]
-
-    def test_server_url_trailing_slash_stripped(self):
-        client = MCPClient("https://mcp.example.com/mcp/")
-        assert client.server_url == "https://mcp.example.com/mcp"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_send_request_success(self):
-        client = MCPClient("https://mcp.example.com")
-
-        mock_response = AsyncMock()
-        mock_response.json.return_value = {
-            "jsonrpc": "2.0",
-            "result": {"tools": []},
-            "id": 1,
-        }
-
-        with patch.object(client, "_send_request", return_value={"tools": []}):
-            result = await client._send_request("tools/list")
-            assert result == {"tools": []}
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_send_request_error(self):
-        client = MCPClient("https://mcp.example.com")
-
-        async def mock_send(*args, **kwargs):
-            raise MCPClientError("MCP server error [-32600]: Invalid Request")
-
-        with patch.object(client, "_send_request", side_effect=mock_send):
-            with pytest.raises(MCPClientError, match="Invalid Request"):
-                await client._send_request("tools/list")
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_list_tools(self):
-        client = MCPClient("https://mcp.example.com")
-
-        mock_result = {
-            "tools": [
-                {
-                    "name": "get_weather",
-                    "description": "Get current weather for a city",
-                    "inputSchema": {
-                        "type": "object",
-                        "properties": {"city": {"type": "string"}},
-                        "required": ["city"],
-                    },
-                },
-                {
-                    "name": "search",
-                    "description": "Search the web",
-                    "inputSchema": {
-                        "type": "object",
-                        "properties": {"query": {"type": "string"}},
-                        "required": ["query"],
-                    },
-                },
-            ]
-        }
-
-        with patch.object(client, "_send_request", return_value=mock_result):
-            tools = await client.list_tools()
-
-        assert len(tools) == 2
-        assert tools[0].name == "get_weather"
-        assert tools[0].description == "Get current weather for a city"
-        assert tools[0].input_schema["properties"]["city"]["type"] == "string"
-        assert tools[1].name == "search"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_list_tools_empty(self):
-        client = MCPClient("https://mcp.example.com")
-
-        with patch.object(client, "_send_request", return_value={"tools": []}):
-            tools = await client.list_tools()
-
-        assert tools == []
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_list_tools_none_result(self):
-        client = MCPClient("https://mcp.example.com")
-
-        with patch.object(client, "_send_request", return_value=None):
-            tools = await client.list_tools()
-
-        assert tools == []
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_tool_success(self):
-        client = MCPClient("https://mcp.example.com")
-
-        mock_result = {
-            "content": [
-                {"type": "text", "text": json.dumps({"temp": 20, "city": "London"})}
-            ],
-            "isError": False,
-        }
-
-        with patch.object(client, "_send_request", return_value=mock_result):
-            result = await client.call_tool("get_weather", {"city": "London"})
-
-        assert not result.is_error
-        assert len(result.content) == 1
-        assert result.content[0]["type"] == "text"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_tool_error(self):
-        client = MCPClient("https://mcp.example.com")
-
-        mock_result = {
-            "content": [{"type": "text", "text": "City not found"}],
-            "isError": True,
-        }
-
-        with patch.object(client, "_send_request", return_value=mock_result):
-            result = await client.call_tool("get_weather", {"city": "???"})
-
-        assert result.is_error
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_tool_none_result(self):
-        client = MCPClient("https://mcp.example.com")
-
-        with patch.object(client, "_send_request", return_value=None):
-            result = await client.call_tool("get_weather", {"city": "London"})
-
-        assert result.is_error
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_initialize(self):
-        client = MCPClient("https://mcp.example.com")
-
-        mock_result = {
-            "protocolVersion": "2025-03-26",
-            "capabilities": {"tools": {}},
-            "serverInfo": {"name": "test-server", "version": "1.0.0"},
-        }
-
-        with (
-            patch.object(client, "_send_request", return_value=mock_result) as mock_req,
-            patch.object(client, "_send_notification") as mock_notif,
-        ):
-            result = await client.initialize()
-
-        mock_req.assert_called_once()
-        mock_notif.assert_called_once_with("notifications/initialized")
-        assert result["protocolVersion"] == "2025-03-26"
-
-
-# ── MCPToolBlock unit tests ──────────────────────────────────────────
-
-MOCK_USER_ID = "test-user-123"
-
-
-class TestMCPToolBlock:
-    """Tests for the MCPToolBlock."""
-
-    def test_block_instantiation(self):
-        block = MCPToolBlock()
-        assert block.id == "a0a4b1c2-d3e4-4f56-a7b8-c9d0e1f2a3b4"
-        assert block.name == "MCPToolBlock"
-
-    def test_input_schema_has_required_fields(self):
-        block = MCPToolBlock()
-        schema = block.input_schema.jsonschema()
-        props = schema.get("properties", {})
-        assert "server_url" in props
-        assert "selected_tool" in props
-        assert "tool_arguments" in props
-        assert "credentials" in props
-
-    def test_output_schema(self):
-        block = MCPToolBlock()
-        schema = block.output_schema.jsonschema()
-        props = schema.get("properties", {})
-        assert "result" in props
-        assert "error" in props
-
-    def test_get_input_schema_with_tool_schema(self):
-        tool_schema = {
-            "type": "object",
-            "properties": {"query": {"type": "string"}},
-            "required": ["query"],
-        }
-        data = {"tool_input_schema": tool_schema}
-        result = MCPToolBlock.Input.get_input_schema(data)
-        assert result == tool_schema
-
-    def test_get_input_schema_without_tool_schema(self):
-        result = MCPToolBlock.Input.get_input_schema({})
-        assert result == {}
-
-    def test_get_input_defaults(self):
-        data = {"tool_arguments": {"city": "London"}}
-        result = MCPToolBlock.Input.get_input_defaults(data)
-        assert result == {"city": "London"}
-
-    def test_get_missing_input(self):
-        data = {
-            "tool_input_schema": {
-                "type": "object",
-                "properties": {
-                    "city": {"type": "string"},
-                    "units": {"type": "string"},
-                },
-                "required": ["city", "units"],
-            },
-            "tool_arguments": {"city": "London"},
-        }
-        missing = MCPToolBlock.Input.get_missing_input(data)
-        assert missing == {"units"}
-
-    def test_get_missing_input_all_present(self):
-        data = {
-            "tool_input_schema": {
-                "type": "object",
-                "properties": {"city": {"type": "string"}},
-                "required": ["city"],
-            },
-            "tool_arguments": {"city": "London"},
-        }
-        missing = MCPToolBlock.Input.get_missing_input(data)
-        assert missing == set()
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_run_with_mock(self):
-        """Test the block using the built-in test infrastructure."""
-        block = MCPToolBlock()
-        await execute_block_test(block)
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_run_missing_server_url(self):
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url="",
-            selected_tool="test",
-        )
-        outputs = []
-        async for name, data in block.run(input_data, user_id=MOCK_USER_ID):
-            outputs.append((name, data))
-        assert outputs == [("error", "MCP server URL is required")]
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_run_missing_tool(self):
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url="https://mcp.example.com/mcp",
-            selected_tool="",
-        )
-        outputs = []
-        async for name, data in block.run(input_data, user_id=MOCK_USER_ID):
-            outputs.append((name, data))
-        assert outputs == [
-            ("error", "No tool selected. Please select a tool from the dropdown.")
-        ]
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_run_success(self):
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url="https://mcp.example.com/mcp",
-            selected_tool="get_weather",
-            tool_input_schema={
-                "type": "object",
-                "properties": {"city": {"type": "string"}},
-            },
-            tool_arguments={"city": "London"},
-        )
-
-        async def mock_call(*args, **kwargs):
-            return {"temp": 20, "city": "London"}
-
-        block._call_mcp_tool = mock_call  # type: ignore
-
-        outputs = []
-        async for name, data in block.run(input_data, user_id=MOCK_USER_ID):
-            outputs.append((name, data))
-
-        assert len(outputs) == 1
-        assert outputs[0][0] == "result"
-        assert outputs[0][1] == {"temp": 20, "city": "London"}
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_run_mcp_error(self):
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url="https://mcp.example.com/mcp",
-            selected_tool="bad_tool",
-        )
-
-        async def mock_call(*args, **kwargs):
-            raise MCPClientError("Tool not found")
-
-        block._call_mcp_tool = mock_call  # type: ignore
-
-        outputs = []
-        async for name, data in block.run(input_data, user_id=MOCK_USER_ID):
-            outputs.append((name, data))
-
-        assert outputs[0][0] == "error"
-        assert "Tool not found" in outputs[0][1]
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_mcp_tool_parses_json_text(self):
-        block = MCPToolBlock()
-
-        mock_result = MCPCallResult(
-            content=[
-                {"type": "text", "text": '{"temp": 20}'},
-            ],
-            is_error=False,
-        )
-
-        async def mock_init(self):
-            return {}
-
-        async def mock_call(self, name, args):
-            return mock_result
-
-        with (
-            patch.object(MCPClient, "initialize", mock_init),
-            patch.object(MCPClient, "call_tool", mock_call),
-        ):
-            result = await block._call_mcp_tool(
-                "https://mcp.example.com", "test_tool", {}
-            )
-
-        assert result == {"temp": 20}
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_mcp_tool_plain_text(self):
-        block = MCPToolBlock()
-
-        mock_result = MCPCallResult(
-            content=[
-                {"type": "text", "text": "Hello, world!"},
-            ],
-            is_error=False,
-        )
-
-        async def mock_init(self):
-            return {}
-
-        async def mock_call(self, name, args):
-            return mock_result
-
-        with (
-            patch.object(MCPClient, "initialize", mock_init),
-            patch.object(MCPClient, "call_tool", mock_call),
-        ):
-            result = await block._call_mcp_tool(
-                "https://mcp.example.com", "test_tool", {}
-            )
-
-        assert result == "Hello, world!"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_mcp_tool_multiple_content(self):
-        block = MCPToolBlock()
-
-        mock_result = MCPCallResult(
-            content=[
-                {"type": "text", "text": "Part 1"},
-                {"type": "text", "text": '{"part": 2}'},
-            ],
-            is_error=False,
-        )
-
-        async def mock_init(self):
-            return {}
-
-        async def mock_call(self, name, args):
-            return mock_result
-
-        with (
-            patch.object(MCPClient, "initialize", mock_init),
-            patch.object(MCPClient, "call_tool", mock_call),
-        ):
-            result = await block._call_mcp_tool(
-                "https://mcp.example.com", "test_tool", {}
-            )
-
-        assert result == ["Part 1", {"part": 2}]
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_mcp_tool_error_result(self):
-        block = MCPToolBlock()
-
-        mock_result = MCPCallResult(
-            content=[{"type": "text", "text": "Something went wrong"}],
-            is_error=True,
-        )
-
-        async def mock_init(self):
-            return {}
-
-        async def mock_call(self, name, args):
-            return mock_result
-
-        with (
-            patch.object(MCPClient, "initialize", mock_init),
-            patch.object(MCPClient, "call_tool", mock_call),
-        ):
-            with pytest.raises(MCPClientError, match="returned an error"):
-                await block._call_mcp_tool("https://mcp.example.com", "test_tool", {})
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_call_mcp_tool_image_content(self):
-        block = MCPToolBlock()
-
-        mock_result = MCPCallResult(
-            content=[
-                {
-                    "type": "image",
-                    "data": "base64data==",
-                    "mimeType": "image/png",
-                }
-            ],
-            is_error=False,
-        )
-
-        async def mock_init(self):
-            return {}
-
-        async def mock_call(self, name, args):
-            return mock_result
-
-        with (
-            patch.object(MCPClient, "initialize", mock_init),
-            patch.object(MCPClient, "call_tool", mock_call),
-        ):
-            result = await block._call_mcp_tool(
-                "https://mcp.example.com", "test_tool", {}
-            )
-
-        assert result == {
-            "type": "image",
-            "data": "base64data==",
-            "mimeType": "image/png",
-        }
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_run_with_credentials(self):
-        """Verify the block uses OAuth2Credentials and passes auth token."""
-        from pydantic import SecretStr
-
-        from backend.data.model import OAuth2Credentials
-
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url="https://mcp.example.com/mcp",
-            selected_tool="test_tool",
-        )
-
-        captured_tokens: list[str | None] = []
-
-        async def mock_call(server_url, tool_name, arguments, auth_token=None):
-            captured_tokens.append(auth_token)
-            return "ok"
-
-        block._call_mcp_tool = mock_call  # type: ignore
-
-        test_creds = OAuth2Credentials(
-            id="cred-123",
-            provider="mcp",
-            access_token=SecretStr("resolved-token"),
-            refresh_token=SecretStr(""),
-            scopes=[],
-            title="Test MCP credential",
-        )
-
-        async for _ in block.run(
-            input_data, user_id=MOCK_USER_ID, credentials=test_creds
-        ):
-            pass
-
-        assert captured_tokens == ["resolved-token"]
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_run_without_credentials(self):
-        """Verify the block works without credentials (public server)."""
-        block = MCPToolBlock()
-        input_data = MCPToolBlock.Input(
-            server_url="https://mcp.example.com/mcp",
-            selected_tool="test_tool",
-        )
-
-        captured_tokens: list[str | None] = []
-
-        async def mock_call(server_url, tool_name, arguments, auth_token=None):
-            captured_tokens.append(auth_token)
-            return "ok"
-
-        block._call_mcp_tool = mock_call  # type: ignore
-
-        outputs = []
-        async for name, data in block.run(input_data, user_id=MOCK_USER_ID):
-            outputs.append((name, data))
-
-        assert captured_tokens == [None]
-        assert outputs == [("result", "ok")]
--- a/autogpt_platform/backend/backend/blocks/mcp/test_oauth.py
+++ b/autogpt_platform/backend/backend/blocks/mcp/test_oauth.py
@@ -1,242 +0,0 @@
-"""
-Tests for MCP OAuth handler.
-"""
-
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-from pydantic import SecretStr
-
-from backend.blocks.mcp.client import MCPClient
-from backend.blocks.mcp.oauth import MCPOAuthHandler
-from backend.data.model import OAuth2Credentials
-
-
-def _mock_response(json_data: dict, status: int = 200) -> MagicMock:
-    """Create a mock Response with synchronous json() (matching Requests.Response)."""
-    resp = MagicMock()
-    resp.status = status
-    resp.ok = 200 <= status < 300
-    resp.json.return_value = json_data
-    return resp
-
-
-class TestMCPOAuthHandler:
-    """Tests for the MCPOAuthHandler."""
-
-    def _make_handler(self, **overrides) -> MCPOAuthHandler:
-        defaults = {
-            "client_id": "test-client-id",
-            "client_secret": "test-client-secret",
-            "redirect_uri": "https://app.example.com/callback",
-            "authorize_url": "https://auth.example.com/authorize",
-            "token_url": "https://auth.example.com/token",
-        }
-        defaults.update(overrides)
-        return MCPOAuthHandler(**defaults)
-
-    def test_get_login_url_basic(self):
-        handler = self._make_handler()
-        url = handler.get_login_url(
-            scopes=["read", "write"],
-            state="random-state-token",
-            code_challenge="S256-challenge-value",
-        )
-
-        assert "https://auth.example.com/authorize?" in url
-        assert "response_type=code" in url
-        assert "client_id=test-client-id" in url
-        assert "state=random-state-token" in url
-        assert "code_challenge=S256-challenge-value" in url
-        assert "code_challenge_method=S256" in url
-        assert "scope=read+write" in url
-
-    def test_get_login_url_with_resource(self):
-        handler = self._make_handler(resource_url="https://mcp.example.com/mcp")
-        url = handler.get_login_url(
-            scopes=[], state="state", code_challenge="challenge"
-        )
-
-        assert "resource=https" in url
-
-    def test_get_login_url_without_pkce(self):
-        handler = self._make_handler()
-        url = handler.get_login_url(scopes=["read"], state="state", code_challenge=None)
-
-        assert "code_challenge" not in url
-        assert "code_challenge_method" not in url
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_exchange_code_for_tokens(self):
-        handler = self._make_handler()
-
-        resp = _mock_response(
-            {
-                "access_token": "new-access-token",
-                "refresh_token": "new-refresh-token",
-                "expires_in": 3600,
-                "token_type": "Bearer",
-            }
-        )
-
-        with patch("backend.blocks.mcp.oauth.Requests") as MockRequests:
-            instance = MockRequests.return_value
-            instance.post = AsyncMock(return_value=resp)
-
-            creds = await handler.exchange_code_for_tokens(
-                code="auth-code",
-                scopes=["read"],
-                code_verifier="pkce-verifier",
-            )
-
-        assert isinstance(creds, OAuth2Credentials)
-        assert creds.access_token.get_secret_value() == "new-access-token"
-        assert creds.refresh_token is not None
-        assert creds.refresh_token.get_secret_value() == "new-refresh-token"
-        assert creds.scopes == ["read"]
-        assert creds.access_token_expires_at is not None
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_refresh_tokens(self):
-        handler = self._make_handler()
-
-        existing_creds = OAuth2Credentials(
-            id="existing-id",
-            provider="mcp",
-            access_token=SecretStr("old-token"),
-            refresh_token=SecretStr("old-refresh"),
-            scopes=["read"],
-            title="test",
-        )
-
-        resp = _mock_response(
-            {
-                "access_token": "refreshed-token",
-                "refresh_token": "new-refresh",
-                "expires_in": 3600,
-            }
-        )
-
-        with patch("backend.blocks.mcp.oauth.Requests") as MockRequests:
-            instance = MockRequests.return_value
-            instance.post = AsyncMock(return_value=resp)
-
-            refreshed = await handler._refresh_tokens(existing_creds)
-
-        assert refreshed.id == "existing-id"
-        assert refreshed.access_token.get_secret_value() == "refreshed-token"
-        assert refreshed.refresh_token is not None
-        assert refreshed.refresh_token.get_secret_value() == "new-refresh"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_refresh_tokens_no_refresh_token(self):
-        handler = self._make_handler()
-
-        creds = OAuth2Credentials(
-            provider="mcp",
-            access_token=SecretStr("token"),
-            scopes=["read"],
-            title="test",
-        )
-
-        with pytest.raises(ValueError, match="No refresh token"):
-            await handler._refresh_tokens(creds)
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_revoke_tokens_no_url(self):
-        handler = self._make_handler(revoke_url=None)
-
-        creds = OAuth2Credentials(
-            provider="mcp",
-            access_token=SecretStr("token"),
-            scopes=[],
-            title="test",
-        )
-
-        result = await handler.revoke_tokens(creds)
-        assert result is False
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_revoke_tokens_with_url(self):
-        handler = self._make_handler(revoke_url="https://auth.example.com/revoke")
-
-        creds = OAuth2Credentials(
-            provider="mcp",
-            access_token=SecretStr("token"),
-            scopes=[],
-            title="test",
-        )
-
-        resp = _mock_response({}, status=200)
-
-        with patch("backend.blocks.mcp.oauth.Requests") as MockRequests:
-            instance = MockRequests.return_value
-            instance.post = AsyncMock(return_value=resp)
-
-            result = await handler.revoke_tokens(creds)
-
-        assert result is True
-
-
-class TestMCPClientDiscovery:
-    """Tests for MCPClient OAuth metadata discovery."""
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_discover_auth_found(self):
-        client = MCPClient("https://mcp.example.com/mcp")
-
-        metadata = {
-            "authorization_servers": ["https://auth.example.com"],
-            "resource": "https://mcp.example.com/mcp",
-        }
-
-        resp = _mock_response(metadata, status=200)
-
-        with patch("backend.blocks.mcp.client.Requests") as MockRequests:
-            instance = MockRequests.return_value
-            instance.get = AsyncMock(return_value=resp)
-
-            result = await client.discover_auth()
-
-        assert result is not None
-        assert result["authorization_servers"] == ["https://auth.example.com"]
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_discover_auth_not_found(self):
-        client = MCPClient("https://mcp.example.com/mcp")
-
-        resp = _mock_response({}, status=404)
-
-        with patch("backend.blocks.mcp.client.Requests") as MockRequests:
-            instance = MockRequests.return_value
-            instance.get = AsyncMock(return_value=resp)
-
-            result = await client.discover_auth()
-
-        assert result is None
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_discover_auth_server_metadata(self):
-        client = MCPClient("https://mcp.example.com/mcp")
-
-        server_metadata = {
-            "issuer": "https://auth.example.com",
-            "authorization_endpoint": "https://auth.example.com/authorize",
-            "token_endpoint": "https://auth.example.com/token",
-            "registration_endpoint": "https://auth.example.com/register",
-            "code_challenge_methods_supported": ["S256"],
-        }
-
-        resp = _mock_response(server_metadata, status=200)
-
-        with patch("backend.blocks.mcp.client.Requests") as MockRequests:
-            instance = MockRequests.return_value
-            instance.get = AsyncMock(return_value=resp)
-
-            result = await client.discover_auth_server_metadata(
-                "https://auth.example.com"
-            )
-
-        assert result is not None
-        assert result["authorization_endpoint"] == "https://auth.example.com/authorize"
-        assert result["token_endpoint"] == "https://auth.example.com/token"
--- a/autogpt_platform/backend/backend/blocks/mcp/test_server.py
+++ b/autogpt_platform/backend/backend/blocks/mcp/test_server.py
@@ -1,162 +0,0 @@
-"""
-Minimal MCP server for integration testing.
-
-Implements the MCP Streamable HTTP transport (JSON-RPC 2.0 over HTTP POST)
-with a few sample tools. Runs on localhost with a random available port.
-"""
-
-import json
-import logging
-
-from aiohttp import web
-
-logger = logging.getLogger(__name__)
-
-# Sample tools this test server exposes
-TEST_TOOLS = [
-    {
-        "name": "get_weather",
-        "description": "Get current weather for a city",
-        "inputSchema": {
-            "type": "object",
-            "properties": {
-                "city": {
-                    "type": "string",
-                    "description": "City name",
-                },
-            },
-            "required": ["city"],
-        },
-    },
-    {
-        "name": "add_numbers",
-        "description": "Add two numbers together",
-        "inputSchema": {
-            "type": "object",
-            "properties": {
-                "a": {"type": "number", "description": "First number"},
-                "b": {"type": "number", "description": "Second number"},
-            },
-            "required": ["a", "b"],
-        },
-    },
-    {
-        "name": "echo",
-        "description": "Echo back the input message",
-        "inputSchema": {
-            "type": "object",
-            "properties": {
-                "message": {"type": "string", "description": "Message to echo"},
-            },
-            "required": ["message"],
-        },
-    },
-]
-
-
-def _handle_initialize(params: dict) -> dict:
-    return {
-        "protocolVersion": "2025-03-26",
-        "capabilities": {"tools": {"listChanged": False}},
-        "serverInfo": {"name": "test-mcp-server", "version": "1.0.0"},
-    }
-
-
-def _handle_tools_list(params: dict) -> dict:
-    return {"tools": TEST_TOOLS}
-
-
-def _handle_tools_call(params: dict) -> dict:
-    tool_name = params.get("name", "")
-    arguments = params.get("arguments", {})
-
-    if tool_name == "get_weather":
-        city = arguments.get("city", "Unknown")
-        return {
-            "content": [
-                {
-                    "type": "text",
-                    "text": json.dumps(
-                        {"city": city, "temperature": 22, "condition": "sunny"}
-                    ),
-                }
-            ],
-        }
-
-    elif tool_name == "add_numbers":
-        a = arguments.get("a", 0)
-        b = arguments.get("b", 0)
-        return {
-            "content": [{"type": "text", "text": json.dumps({"result": a + b})}],
-        }
-
-    elif tool_name == "echo":
-        message = arguments.get("message", "")
-        return {
-            "content": [{"type": "text", "text": message}],
-        }
-
-    else:
-        return {
-            "content": [{"type": "text", "text": f"Unknown tool: {tool_name}"}],
-            "isError": True,
-        }
-
-
-HANDLERS = {
-    "initialize": _handle_initialize,
-    "tools/list": _handle_tools_list,
-    "tools/call": _handle_tools_call,
-}
-
-
-async def handle_mcp_request(request: web.Request) -> web.Response:
-    """Handle incoming MCP JSON-RPC 2.0 requests."""
-    # Check auth if configured
-    expected_token = request.app.get("auth_token")
-    if expected_token:
-        auth_header = request.headers.get("Authorization", "")
-        if auth_header != f"Bearer {expected_token}":
-            return web.json_response(
-                {
-                    "jsonrpc": "2.0",
-                    "error": {"code": -32001, "message": "Unauthorized"},
-                    "id": None,
-                },
-                status=401,
-            )
-
-    body = await request.json()
-
-    # Handle notifications (no id field) — just acknowledge
-    if "id" not in body:
-        return web.Response(status=202)
-
-    method = body.get("method", "")
-    params = body.get("params", {})
-    request_id = body.get("id")
-
-    handler = HANDLERS.get(method)
-    if not handler:
-        return web.json_response(
-            {
-                "jsonrpc": "2.0",
-                "error": {
-                    "code": -32601,
-                    "message": f"Method not found: {method}",
-                },
-                "id": request_id,
-            }
-        )
-
-    result = handler(params)
-    return web.json_response({"jsonrpc": "2.0", "result": result, "id": request_id})
-
-
-def create_test_mcp_app(auth_token: str | None = None) -> web.Application:
-    """Create an aiohttp app that acts as an MCP server."""
-    app = web.Application()
-    app.router.add_post("/mcp", handle_mcp_request)
-    if auth_token:
-        app["auth_token"] = auth_token
-    return app
--- a/autogpt_platform/backend/backend/conftest.py
+++ b/autogpt_platform/backend/backend/conftest.py
@@ -1,7 +1,6 @@
 import logging
 import os

-import pytest
 import pytest_asyncio
 from dotenv import load_dotenv

@@ -28,54 +27,6 @@ async def server():
        yield server


-@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_asyncio.fixture(scope="session", loop_scope="session", autouse=True)
 async def graph_cleanup(server):
    created_graph_ids = []
--- a/autogpt_platform/backend/backend/copilot/init.py
+++ b/autogpt_platform/backend/backend/copilot/init.py
@@ -1 +0,0 @@
-
--- a/autogpt_platform/backend/backend/copilot/executor/init.py
+++ b/autogpt_platform/backend/backend/copilot/executor/init.py
--- a/autogpt_platform/backend/backend/copilot/executor/main.py
+++ b/autogpt_platform/backend/backend/copilot/executor/main.py
@@ -1,18 +0,0 @@
-"""Entry point for running the CoPilot Executor service.
-
-Usage:
-    python -m backend.copilot.executor
-"""
-
-from backend.app import run_processes
-
-from .manager import CoPilotExecutor
-
-
-def main():
-    """Run the CoPilot Executor service."""
-    run_processes(CoPilotExecutor())
-
-
-if __name__ == "__main__":
-    main()
--- a/autogpt_platform/backend/backend/copilot/executor/manager.py
+++ b/autogpt_platform/backend/backend/copilot/executor/manager.py
@@ -1,521 +0,0 @@
-"""CoPilot Executor Manager - main service for CoPilot task execution.
-
-This module contains the CoPilotExecutor class that consumes chat tasks from
-RabbitMQ and processes them using a thread pool, following the graph executor pattern.
-"""
-
-import asyncio
-import logging
-import os
-import threading
-import time
-import uuid
-from concurrent.futures import Future, ThreadPoolExecutor
-
-from pika.adapters.blocking_connection import BlockingChannel
-from pika.exceptions import AMQPChannelError, AMQPConnectionError
-from pika.spec import Basic, BasicProperties
-from prometheus_client import Gauge, start_http_server
-
-from backend.data import redis_client as redis
-from backend.data.rabbitmq import SyncRabbitMQ
-from backend.executor.cluster_lock import ClusterLock
-from backend.util.decorator import error_logged
-from backend.util.logging import TruncatedLogger
-from backend.util.process import AppProcess
-from backend.util.retry import continuous_retry
-from backend.util.settings import Settings
-
-from .processor import execute_copilot_task, init_worker
-from .utils import (
-    COPILOT_CANCEL_QUEUE_NAME,
-    COPILOT_EXECUTION_QUEUE_NAME,
-    GRACEFUL_SHUTDOWN_TIMEOUT_SECONDS,
-    CancelCoPilotEvent,
-    CoPilotExecutionEntry,
-    create_copilot_queue_config,
-)
-
-logger = TruncatedLogger(logging.getLogger(__name__), prefix="[CoPilotExecutor]")
-settings = Settings()
-
-# Prometheus metrics
-active_tasks_gauge = Gauge(
-    "copilot_executor_active_tasks",
-    "Number of active CoPilot tasks",
-)
-pool_size_gauge = Gauge(
-    "copilot_executor_pool_size",
-    "Maximum number of CoPilot executor workers",
-)
-utilization_gauge = Gauge(
-    "copilot_executor_utilization_ratio",
-    "Ratio of active tasks to pool size",
-)
-
-
-class CoPilotExecutor(AppProcess):
-    """CoPilot Executor service for processing chat generation tasks.
-
-    This service consumes tasks from RabbitMQ, processes them using a thread pool,
-    and publishes results to Redis Streams. It follows the graph executor pattern
-    for reliable message handling and graceful shutdown.
-
-    Key features:
-    - RabbitMQ-based task distribution with manual acknowledgment
-    - Thread pool executor for concurrent task processing
-    - Cluster lock for duplicate prevention across pods
-    - Graceful shutdown with timeout for in-flight tasks
-    - FANOUT exchange for cancellation broadcast
-    """
-
-    def __init__(self):
-        super().__init__()
-        self.pool_size = settings.config.num_copilot_workers
-        self.active_tasks: dict[str, tuple[Future, threading.Event]] = {}
-        self.executor_id = str(uuid.uuid4())
-
-        self._executor = None
-        self._stop_consuming = None
-
-        self._cancel_thread = None
-        self._cancel_client = None
-        self._run_thread = None
-        self._run_client = None
-
-        self._task_locks: dict[str, ClusterLock] = {}
-        self._active_tasks_lock = threading.Lock()
-
-    # ============ Main Entry Points (AppProcess interface) ============ #
-
-    def run(self):
-        """Main service loop - consume from RabbitMQ."""
-        logger.info(f"Pod assigned executor_id: {self.executor_id}")
-        logger.info(f"Spawn max-{self.pool_size} workers...")
-
-        pool_size_gauge.set(self.pool_size)
-        self._update_metrics()
-        start_http_server(settings.config.copilot_executor_port)
-
-        self.cancel_thread.start()
-        self.run_thread.start()
-
-        while True:
-            time.sleep(1e5)
-
-    def cleanup(self):
-        """Graceful shutdown with active execution waiting."""
-        pid = os.getpid()
-        logger.info(f"[cleanup {pid}] Starting graceful shutdown...")
-
-        # Signal the consumer thread to stop
-        try:
-            self.stop_consuming.set()
-            run_channel = self.run_client.get_channel()
-            run_channel.connection.add_callback_threadsafe(
-                lambda: run_channel.stop_consuming()
-            )
-            logger.info(f"[cleanup {pid}] Consumer has been signaled to stop")
-        except Exception as e:
-            logger.error(f"[cleanup {pid}] Error stopping consumer: {e}")
-
-        # Wait for active executions to complete
-        if self.active_tasks:
-            logger.info(
-                f"[cleanup {pid}] Waiting for {len(self.active_tasks)} active tasks to complete (timeout: {GRACEFUL_SHUTDOWN_TIMEOUT_SECONDS}s)..."
-            )
-
-            start_time = time.monotonic()
-            last_refresh = start_time
-            lock_refresh_interval = settings.config.cluster_lock_timeout / 10
-
-            while (
-                self.active_tasks
-                and (time.monotonic() - start_time) < GRACEFUL_SHUTDOWN_TIMEOUT_SECONDS
-            ):
-                self._cleanup_completed_tasks()
-                if not self.active_tasks:
-                    break
-
-                # Refresh cluster locks periodically
-                current_time = time.monotonic()
-                if current_time - last_refresh >= lock_refresh_interval:
-                    for lock in list(self._task_locks.values()):
-                        try:
-                            lock.refresh()
-                        except Exception as e:
-                            logger.warning(
-                                f"[cleanup {pid}] Failed to refresh lock: {e}"
-                            )
-                    last_refresh = current_time
-
-                logger.info(
-                    f"[cleanup {pid}] {len(self.active_tasks)} tasks still active, waiting..."
-                )
-                time.sleep(10.0)
-
-        # Stop message consumers
-        if self._run_thread:
-            self._stop_message_consumers(
-                self._run_thread, self.run_client, "[cleanup][run]"
-            )
-        if self._cancel_thread:
-            self._stop_message_consumers(
-                self._cancel_thread, self.cancel_client, "[cleanup][cancel]"
-            )
-
-        # Clean up worker threads (closes per-loop workspace storage sessions)
-        if self._executor:
-            from .processor import cleanup_worker
-
-            logger.info(f"[cleanup {pid}] Cleaning up workers...")
-            futures = []
-            for _ in range(self._executor._max_workers):
-                futures.append(self._executor.submit(cleanup_worker))
-            for f in futures:
-                try:
-                    f.result(timeout=10)
-                except Exception as e:
-                    logger.warning(f"[cleanup {pid}] Worker cleanup error: {e}")
-
-            logger.info(f"[cleanup {pid}] Shutting down executor...")
-            self._executor.shutdown(wait=False)
-
-        # Release any remaining locks
-        for task_id, lock in list(self._task_locks.items()):
-            try:
-                lock.release()
-                logger.info(f"[cleanup {pid}] Released lock for {task_id}")
-            except Exception as e:
-                logger.error(
-                    f"[cleanup {pid}] Failed to release lock for {task_id}: {e}"
-                )
-
-        logger.info(f"[cleanup {pid}] Graceful shutdown completed")
-
-    # ============ RabbitMQ Consumer Methods ============ #
-
-    @continuous_retry()
-    def _consume_cancel(self):
-        """Consume cancellation messages from FANOUT exchange."""
-        if self.stop_consuming.is_set() and not self.active_tasks:
-            logger.info("Stop reconnecting cancel consumer - service cleaned up")
-            return
-
-        if not self.cancel_client.is_ready:
-            self.cancel_client.disconnect()
-        self.cancel_client.connect()
-
-        # Check again after connect - shutdown may have been requested
-        if self.stop_consuming.is_set() and not self.active_tasks:
-            logger.info("Stop consuming requested during reconnect - disconnecting")
-            self.cancel_client.disconnect()
-            return
-
-        cancel_channel = self.cancel_client.get_channel()
-        cancel_channel.basic_consume(
-            queue=COPILOT_CANCEL_QUEUE_NAME,
-            on_message_callback=self._handle_cancel_message,
-            auto_ack=True,
-        )
-        logger.info("Starting to consume cancel messages...")
-        cancel_channel.start_consuming()
-        if not self.stop_consuming.is_set() or self.active_tasks:
-            raise RuntimeError("Cancel message consumer stopped unexpectedly")
-        logger.info("Cancel message consumer stopped gracefully")
-
-    @continuous_retry()
-    def _consume_run(self):
-        """Consume run messages from DIRECT exchange."""
-        if self.stop_consuming.is_set():
-            logger.info("Stop reconnecting run consumer - service cleaned up")
-            return
-
-        if not self.run_client.is_ready:
-            self.run_client.disconnect()
-        self.run_client.connect()
-
-        # Check again after connect - shutdown may have been requested
-        if self.stop_consuming.is_set():
-            logger.info("Stop consuming requested during reconnect - disconnecting")
-            self.run_client.disconnect()
-            return
-
-        run_channel = self.run_client.get_channel()
-        run_channel.basic_qos(prefetch_count=self.pool_size)
-
-        run_channel.basic_consume(
-            queue=COPILOT_EXECUTION_QUEUE_NAME,
-            on_message_callback=self._handle_run_message,
-            auto_ack=False,
-            consumer_tag="copilot_execution_consumer",
-        )
-        logger.info("Starting to consume run messages...")
-        run_channel.start_consuming()
-        if not self.stop_consuming.is_set():
-            raise RuntimeError("Run message consumer stopped unexpectedly")
-        logger.info("Run message consumer stopped gracefully")
-
-    # ============ Message Handlers ============ #
-
-    @error_logged(swallow=True)
-    def _handle_cancel_message(
-        self,
-        _channel: BlockingChannel,
-        _method: Basic.Deliver,
-        _properties: BasicProperties,
-        body: bytes,
-    ):
-        """Handle cancel message from FANOUT exchange."""
-        request = CancelCoPilotEvent.model_validate_json(body)
-        task_id = request.task_id
-        if not task_id:
-            logger.warning("Cancel message missing 'task_id'")
-            return
-        if task_id not in self.active_tasks:
-            logger.debug(f"Cancel received for {task_id} but not active")
-            return
-
-        _, cancel_event = self.active_tasks[task_id]
-        logger.info(f"Received cancel for {task_id}")
-        if not cancel_event.is_set():
-            cancel_event.set()
-        else:
-            logger.debug(f"Cancel already set for {task_id}")
-
-    def _handle_run_message(
-        self,
-        _channel: BlockingChannel,
-        method: Basic.Deliver,
-        _properties: BasicProperties,
-        body: bytes,
-    ):
-        """Handle run message from DIRECT exchange."""
-        delivery_tag = method.delivery_tag
-        # Capture the channel used at message delivery time to ensure we ack
-        # on the correct channel. Delivery tags are channel-scoped and become
-        # invalid if the channel is recreated after reconnection.
-        delivery_channel = _channel
-
-        def ack_message(reject: bool, requeue: bool):
-            """Acknowledge or reject the message.
-
-            Uses the channel from the original message delivery. If the channel
-            is no longer open (e.g., after reconnection), logs a warning and
-            skips the ack - RabbitMQ will redeliver the message automatically.
-            """
-            try:
-                if not delivery_channel.is_open:
-                    logger.warning(
-                        f"Channel closed, cannot ack delivery_tag={delivery_tag}. "
-                        "Message will be redelivered by RabbitMQ."
-                    )
-                    return
-
-                if reject:
-                    delivery_channel.connection.add_callback_threadsafe(
-                        lambda: delivery_channel.basic_nack(
-                            delivery_tag, requeue=requeue
-                        )
-                    )
-                else:
-                    delivery_channel.connection.add_callback_threadsafe(
-                        lambda: delivery_channel.basic_ack(delivery_tag)
-                    )
-            except (AMQPChannelError, AMQPConnectionError) as e:
-                # Channel/connection errors indicate stale delivery tag - don't retry
-                logger.warning(
-                    f"Cannot ack delivery_tag={delivery_tag} due to channel/connection "
-                    f"error: {e}. Message will be redelivered by RabbitMQ."
-                )
-            except Exception as e:
-                # Other errors might be transient, but log and skip to avoid blocking
-                logger.error(
-                    f"Unexpected error acking delivery_tag={delivery_tag}: {e}"
-                )
-
-        # Check if we're shutting down
-        if self.stop_consuming.is_set():
-            logger.info("Rejecting new task during shutdown")
-            ack_message(reject=True, requeue=True)
-            return
-
-        # Check if we can accept more tasks
-        self._cleanup_completed_tasks()
-        if len(self.active_tasks) >= self.pool_size:
-            ack_message(reject=True, requeue=True)
-            return
-
-        try:
-            entry = CoPilotExecutionEntry.model_validate_json(body)
-        except Exception as e:
-            logger.error(f"Could not parse run message: {e}, body={body}")
-            ack_message(reject=True, requeue=False)
-            return
-
-        task_id = entry.task_id
-
-        # Check for local duplicate - task is already running on this executor
-        if task_id in self.active_tasks:
-            logger.warning(
-                f"Task {task_id} already running locally, rejecting duplicate"
-            )
-            ack_message(reject=True, requeue=False)
-            return
-
-        # Try to acquire cluster-wide lock
-        cluster_lock = ClusterLock(
-            redis=redis.get_redis(),
-            key=f"copilot:task:{task_id}:lock",
-            owner_id=self.executor_id,
-            timeout=settings.config.cluster_lock_timeout,
-        )
-        current_owner = cluster_lock.try_acquire()
-        if current_owner != self.executor_id:
-            if current_owner is not None:
-                logger.warning(f"Task {task_id} already running on pod {current_owner}")
-                ack_message(reject=True, requeue=False)
-            else:
-                logger.warning(
-                    f"Could not acquire lock for {task_id} - Redis unavailable"
-                )
-                ack_message(reject=True, requeue=True)
-            return
-
-        # Execute the task
-        try:
-            self._task_locks[task_id] = cluster_lock
-
-            logger.info(
-                f"Acquired cluster lock for {task_id}, executor_id={self.executor_id}"
-            )
-
-            cancel_event = threading.Event()
-            future = self.executor.submit(
-                execute_copilot_task, entry, cancel_event, cluster_lock
-            )
-            self.active_tasks[task_id] = (future, cancel_event)
-        except Exception as e:
-            logger.warning(f"Failed to setup execution for {task_id}: {e}")
-            cluster_lock.release()
-            if task_id in self._task_locks:
-                del self._task_locks[task_id]
-            ack_message(reject=True, requeue=True)
-            return
-
-        self._update_metrics()
-
-        def on_run_done(f: Future):
-            logger.info(f"Run completed for {task_id}")
-            try:
-                if exec_error := f.exception():
-                    logger.error(f"Execution for {task_id} failed: {exec_error}")
-                    # Don't requeue failed tasks - they've been marked as failed
-                    # in the stream registry. Requeuing would cause infinite retries
-                    # for deterministic failures.
-                    ack_message(reject=True, requeue=False)
-                else:
-                    ack_message(reject=False, requeue=False)
-            except BaseException as e:
-                logger.exception(f"Error in run completion callback: {e}")
-            finally:
-                # Release the cluster lock
-                if task_id in self._task_locks:
-                    logger.info(f"Releasing cluster lock for {task_id}")
-                    self._task_locks[task_id].release()
-                    del self._task_locks[task_id]
-                self._cleanup_completed_tasks()
-
-        future.add_done_callback(on_run_done)
-
-    # ============ Helper Methods ============ #
-
-    def _cleanup_completed_tasks(self) -> list[str]:
-        """Remove completed futures from active_tasks and update metrics."""
-        completed_tasks = []
-        with self._active_tasks_lock:
-            for task_id, (future, _) in list(self.active_tasks.items()):
-                if future.done():
-                    completed_tasks.append(task_id)
-                    self.active_tasks.pop(task_id, None)
-                    logger.info(f"Cleaned up completed task {task_id}")
-
-        self._update_metrics()
-        return completed_tasks
-
-    def _update_metrics(self):
-        """Update Prometheus metrics."""
-        active_count = len(self.active_tasks)
-        active_tasks_gauge.set(active_count)
-        if self.stop_consuming.is_set():
-            utilization_gauge.set(1.0)
-        else:
-            utilization_gauge.set(
-                active_count / self.pool_size if self.pool_size > 0 else 0
-            )
-
-    def _stop_message_consumers(
-        self, thread: threading.Thread, client: SyncRabbitMQ, prefix: str
-    ):
-        """Stop a message consumer thread."""
-        try:
-            channel = client.get_channel()
-            channel.connection.add_callback_threadsafe(lambda: channel.stop_consuming())
-
-            thread.join(timeout=300)
-            if thread.is_alive():
-                logger.error(
-                    f"{prefix} Thread did not finish in time, forcing disconnect"
-                )
-
-            client.disconnect()
-            logger.info(f"{prefix} Client disconnected")
-        except Exception as e:
-            logger.error(f"{prefix} Error disconnecting client: {e}")
-
-    # ============ Lazy-initialized Properties ============ #
-
-    @property
-    def cancel_thread(self) -> threading.Thread:
-        if self._cancel_thread is None:
-            self._cancel_thread = threading.Thread(
-                target=lambda: self._consume_cancel(),
-                daemon=True,
-            )
-        return self._cancel_thread
-
-    @property
-    def run_thread(self) -> threading.Thread:
-        if self._run_thread is None:
-            self._run_thread = threading.Thread(
-                target=lambda: self._consume_run(),
-                daemon=True,
-            )
-        return self._run_thread
-
-    @property
-    def stop_consuming(self) -> threading.Event:
-        if self._stop_consuming is None:
-            self._stop_consuming = threading.Event()
-        return self._stop_consuming
-
-    @property
-    def executor(self) -> ThreadPoolExecutor:
-        if self._executor is None:
-            self._executor = ThreadPoolExecutor(
-                max_workers=self.pool_size,
-                initializer=init_worker,
-            )
-        return self._executor
-
-    @property
-    def cancel_client(self) -> SyncRabbitMQ:
-        if self._cancel_client is None:
-            self._cancel_client = SyncRabbitMQ(create_copilot_queue_config())
-        return self._cancel_client
-
-    @property
-    def run_client(self) -> SyncRabbitMQ:
-        if self._run_client is None:
-            self._run_client = SyncRabbitMQ(create_copilot_queue_config())
-        return self._run_client
--- a/autogpt_platform/backend/backend/copilot/executor/processor.py
+++ b/autogpt_platform/backend/backend/copilot/executor/processor.py
@@ -1,287 +0,0 @@
-"""CoPilot execution processor - per-worker execution logic.
-
-This module contains the processor class that handles CoPilot task execution
-in a thread-local context, following the graph executor pattern.
-"""
-
-import asyncio
-import logging
-import threading
-import time
-
-from backend.copilot import service as copilot_service
-from backend.copilot import stream_registry
-from backend.copilot.config import ChatConfig
-from backend.copilot.response_model import StreamError, StreamFinish, StreamFinishStep
-from backend.copilot.sdk import service as sdk_service
-from backend.executor.cluster_lock import ClusterLock
-from backend.util.decorator import error_logged
-from backend.util.feature_flag import Flag, is_feature_enabled
-from backend.util.logging import TruncatedLogger, configure_logging
-from backend.util.process import set_service_name
-from backend.util.retry import func_retry
-
-from .utils import CoPilotExecutionEntry, CoPilotLogMetadata
-
-logger = TruncatedLogger(logging.getLogger(__name__), prefix="[CoPilotExecutor]")
-
-
-# ============ Module Entry Points ============ #
-
-# Thread-local storage for processor instances
-_tls = threading.local()
-
-
-def execute_copilot_task(
-    entry: CoPilotExecutionEntry,
-    cancel: threading.Event,
-    cluster_lock: ClusterLock,
-):
-    """Execute a CoPilot task using the thread-local processor.
-
-    This function is the entry point called by the thread pool executor.
-
-    Args:
-        entry: The task payload
-        cancel: Threading event to signal cancellation
-        cluster_lock: Distributed lock for this execution
-    """
-    processor: CoPilotProcessor = _tls.processor
-    return processor.execute(entry, cancel, cluster_lock)
-
-
-def init_worker():
-    """Initialize the processor for the current worker thread.
-
-    This function is called by the thread pool executor when a new worker
-    thread is created. It ensures each worker has its own processor instance.
-    """
-    _tls.processor = CoPilotProcessor()
-    _tls.processor.on_executor_start()
-
-
-def cleanup_worker():
-    """Clean up the processor for the current worker thread.
-
-    Should be called before the worker thread's event loop is destroyed so
-    that event-loop-bound resources (e.g. ``aiohttp.ClientSession``) are
-    closed on the correct loop.
-    """
-    processor: CoPilotProcessor | None = getattr(_tls, "processor", None)
-    if processor is not None:
-        processor.cleanup()
-
-
-# ============ Processor Class ============ #
-
-
-class CoPilotProcessor:
-    """Per-worker execution logic for CoPilot tasks.
-
-    This class is instantiated once per worker thread and handles the execution
-    of CoPilot chat generation tasks. It maintains an async event loop for
-    running the async service code.
-
-    The execution flow:
-        1. CoPilot task is picked from RabbitMQ queue
-        2. Manager submits task to thread pool
-        3. Processor executes the task in its event loop
-        4. Results are published to Redis Streams
-    """
-
-    @func_retry
-    def on_executor_start(self):
-        """Initialize the processor when the worker thread starts.
-
-        This method is called once per worker thread to set up the async event
-        loop and initialize any required resources.
-
-        Database is accessed only through DatabaseManager, so we don't need to connect
-        to Prisma directly.
-        """
-        configure_logging()
-        set_service_name("CoPilotExecutor")
-        self.tid = threading.get_ident()
-        self.execution_loop = asyncio.new_event_loop()
-        self.execution_thread = threading.Thread(
-            target=self.execution_loop.run_forever, daemon=True
-        )
-        self.execution_thread.start()
-
-        logger.info(f"[CoPilotExecutor] Worker {self.tid} started")
-
-    def cleanup(self):
-        """Clean up event-loop-bound resources before the loop is destroyed.
-
-        Shuts down the workspace storage instance that belongs to this
-        worker's event loop, ensuring ``aiohttp.ClientSession.close()``
-        runs on the same loop that created the session.
-        """
-        from backend.util.workspace_storage import shutdown_workspace_storage
-
-        try:
-            future = asyncio.run_coroutine_threadsafe(
-                shutdown_workspace_storage(), self.execution_loop
-            )
-            future.result(timeout=5)
-        except Exception as e:
-            logger.warning(f"[CoPilotExecutor] Worker {self.tid} cleanup error: {e}")
-
-        # Stop the event loop
-        self.execution_loop.call_soon_threadsafe(self.execution_loop.stop)
-        self.execution_thread.join(timeout=5)
-        logger.info(f"[CoPilotExecutor] Worker {self.tid} cleaned up")
-
-    @error_logged(swallow=False)
-    def execute(
-        self,
-        entry: CoPilotExecutionEntry,
-        cancel: threading.Event,
-        cluster_lock: ClusterLock,
-    ):
-        """Execute a CoPilot task.
-
-        This is the main entry point for task execution. It runs the async
-        execution logic in the worker's event loop and handles errors.
-
-        Args:
-            entry: The task payload containing session and message info
-            cancel: Threading event to signal cancellation
-            cluster_lock: Distributed lock to prevent duplicate execution
-        """
-        log = CoPilotLogMetadata(
-            logging.getLogger(__name__),
-            task_id=entry.task_id,
-            session_id=entry.session_id,
-            user_id=entry.user_id,
-        )
-        log.info("Starting execution")
-
-        start_time = time.monotonic()
-
-        try:
-            # Run the async execution in our event loop
-            future = asyncio.run_coroutine_threadsafe(
-                self._execute_async(entry, cancel, cluster_lock, log),
-                self.execution_loop,
-            )
-
-            # Wait for completion, checking cancel periodically
-            while not future.done():
-                try:
-                    future.result(timeout=1.0)
-                except asyncio.TimeoutError:
-                    if cancel.is_set():
-                        log.info("Cancellation requested")
-                        future.cancel()
-                        break
-                    # Refresh cluster lock to maintain ownership
-                    cluster_lock.refresh()
-
-            if not future.cancelled():
-                # Get result to propagate any exceptions
-                future.result()
-
-            elapsed = time.monotonic() - start_time
-            log.info(f"Execution completed in {elapsed:.2f}s")
-
-        except Exception as e:
-            elapsed = time.monotonic() - start_time
-            log.error(f"Execution failed after {elapsed:.2f}s: {e}")
-            # Note: _execute_async already marks the task as failed before re-raising,
-            # so we don't call _mark_task_failed here to avoid duplicate error events.
-            raise
-
-    async def _execute_async(
-        self,
-        entry: CoPilotExecutionEntry,
-        cancel: threading.Event,
-        cluster_lock: ClusterLock,
-        log: CoPilotLogMetadata,
-    ):
-        """Async execution logic for CoPilot task.
-
-        This method calls the existing stream_chat_completion service function
-        and publishes results to the stream registry.
-
-        Args:
-            entry: The task payload
-            cancel: Threading event to signal cancellation
-            cluster_lock: Distributed lock for refresh
-            log: Structured logger for this task
-        """
-        last_refresh = time.monotonic()
-        refresh_interval = 30.0  # Refresh lock every 30 seconds
-
-        try:
-            # Choose service based on LaunchDarkly flag
-            config = ChatConfig()
-            use_sdk = await is_feature_enabled(
-                Flag.COPILOT_SDK,
-                entry.user_id or "anonymous",
-                default=config.use_claude_agent_sdk,
-            )
-            stream_fn = (
-                sdk_service.stream_chat_completion_sdk
-                if use_sdk
-                else copilot_service.stream_chat_completion
-            )
-            log.info(f"Using {'SDK' if use_sdk else 'standard'} service")
-
-            # Stream chat completion and publish chunks to Redis
-            async for chunk in stream_fn(
-                session_id=entry.session_id,
-                message=entry.message if entry.message else None,
-                is_user_message=entry.is_user_message,
-                user_id=entry.user_id,
-                context=entry.context,
-            ):
-                # Check for cancellation
-                if cancel.is_set():
-                    log.info("Cancelled during streaming")
-                    await stream_registry.publish_chunk(
-                        entry.task_id, StreamError(errorText="Operation cancelled")
-                    )
-                    await stream_registry.publish_chunk(
-                        entry.task_id, StreamFinishStep()
-                    )
-                    await stream_registry.publish_chunk(entry.task_id, StreamFinish())
-                    await stream_registry.mark_task_completed(
-                        entry.task_id, status="failed"
-                    )
-                    return
-
-                # Refresh cluster lock periodically
-                current_time = time.monotonic()
-                if current_time - last_refresh >= refresh_interval:
-                    cluster_lock.refresh()
-                    last_refresh = current_time
-
-                # Publish chunk to stream registry
-                await stream_registry.publish_chunk(entry.task_id, chunk)
-
-            # Mark task as completed
-            await stream_registry.mark_task_completed(entry.task_id, status="completed")
-            log.info("Task completed successfully")
-
-        except asyncio.CancelledError:
-            log.info("Task cancelled")
-            await stream_registry.mark_task_completed(entry.task_id, status="failed")
-            raise
-
-        except Exception as e:
-            log.error(f"Task failed: {e}")
-            await self._mark_task_failed(entry.task_id, str(e))
-            raise
-
-    async def _mark_task_failed(self, task_id: str, error_message: str):
-        """Mark a task as failed and publish error to stream registry."""
-        try:
-            await stream_registry.publish_chunk(
-                task_id, StreamError(errorText=error_message)
-            )
-            await stream_registry.publish_chunk(task_id, StreamFinishStep())
-            await stream_registry.publish_chunk(task_id, StreamFinish())
-            await stream_registry.mark_task_completed(task_id, status="failed")
-        except Exception as e:
-            logger.error(f"Failed to mark task {task_id} as failed: {e}")
--- a/autogpt_platform/backend/backend/copilot/executor/utils.py
+++ b/autogpt_platform/backend/backend/copilot/executor/utils.py
@@ -1,207 +0,0 @@
-"""RabbitMQ queue configuration for CoPilot executor.
-
-Defines two exchanges and queues following the graph executor pattern:
- 'copilot_execution' (DIRECT) for chat generation tasks
- 'copilot_cancel' (FANOUT) for cancellation requests
-"""
-
-import logging
-
-from pydantic import BaseModel
-
-from backend.data.rabbitmq import Exchange, ExchangeType, Queue, RabbitMQConfig
-from backend.util.logging import TruncatedLogger, is_structured_logging_enabled
-
-logger = logging.getLogger(__name__)
-
-
-# ============ Logging Helper ============ #
-
-
-class CoPilotLogMetadata(TruncatedLogger):
-    """Structured logging helper for CoPilot executor.
-
-    In cloud environments (structured logging enabled), uses a simple prefix
-    and passes metadata via json_fields. In local environments, uses a detailed
-    prefix with all metadata key-value pairs for easier debugging.
-
-    Args:
-        logger: The underlying logger instance
-        max_length: Maximum log message length before truncation
-        **kwargs: Metadata key-value pairs (e.g., task_id="abc", session_id="xyz")
-            These are added to json_fields in cloud mode, or to the prefix in local mode.
-    """
-
-    def __init__(
-        self,
-        logger: logging.Logger,
-        max_length: int = 1000,
-        **kwargs: str | None,
-    ):
-        # Filter out None values
-        metadata = {k: v for k, v in kwargs.items() if v is not None}
-        metadata["component"] = "CoPilotExecutor"
-
-        if is_structured_logging_enabled():
-            prefix = "[CoPilotExecutor]"
-        else:
-            # Build prefix from metadata key-value pairs
-            meta_parts = "|".join(
-                f"{k}:{v}" for k, v in metadata.items() if k != "component"
-            )
-            prefix = (
-                f"[CoPilotExecutor|{meta_parts}]" if meta_parts else "[CoPilotExecutor]"
-            )
-
-        super().__init__(
-            logger,
-            max_length=max_length,
-            prefix=prefix,
-            metadata=metadata,
-        )
-
-
-# ============ Exchange and Queue Configuration ============ #
-
-COPILOT_EXECUTION_EXCHANGE = Exchange(
-    name="copilot_execution",
-    type=ExchangeType.DIRECT,
-    durable=True,
-    auto_delete=False,
-)
-COPILOT_EXECUTION_QUEUE_NAME = "copilot_execution_queue"
-COPILOT_EXECUTION_ROUTING_KEY = "copilot.run"
-
-COPILOT_CANCEL_EXCHANGE = Exchange(
-    name="copilot_cancel",
-    type=ExchangeType.FANOUT,
-    durable=True,
-    auto_delete=False,
-)
-COPILOT_CANCEL_QUEUE_NAME = "copilot_cancel_queue"
-
-# CoPilot operations can include extended thinking and agent generation
-# which may take 30+ minutes to complete
-COPILOT_CONSUMER_TIMEOUT_SECONDS = 60 * 60  # 1 hour
-
-# Graceful shutdown timeout - allow in-flight operations to complete
-GRACEFUL_SHUTDOWN_TIMEOUT_SECONDS = 30 * 60  # 30 minutes
-
-
-def create_copilot_queue_config() -> RabbitMQConfig:
-    """Create RabbitMQ configuration for CoPilot executor.
-
-    Defines two exchanges and queues:
-    - 'copilot_execution' (DIRECT) for chat generation tasks
-    - 'copilot_cancel' (FANOUT) for cancellation requests
-
-    Returns:
-        RabbitMQConfig with exchanges and queues defined
-    """
-    run_queue = Queue(
-        name=COPILOT_EXECUTION_QUEUE_NAME,
-        exchange=COPILOT_EXECUTION_EXCHANGE,
-        routing_key=COPILOT_EXECUTION_ROUTING_KEY,
-        durable=True,
-        auto_delete=False,
-        arguments={
-            # Extended consumer timeout for long-running LLM operations
-            # Default 30-minute timeout is insufficient for extended thinking
-            # and agent generation which can take 30+ minutes
-            "x-consumer-timeout": COPILOT_CONSUMER_TIMEOUT_SECONDS
-            * 1000,
-        },
-    )
-    cancel_queue = Queue(
-        name=COPILOT_CANCEL_QUEUE_NAME,
-        exchange=COPILOT_CANCEL_EXCHANGE,
-        routing_key="",  # not used for FANOUT
-        durable=True,
-        auto_delete=False,
-    )
-    return RabbitMQConfig(
-        vhost="/",
-        exchanges=[COPILOT_EXECUTION_EXCHANGE, COPILOT_CANCEL_EXCHANGE],
-        queues=[run_queue, cancel_queue],
-    )
-
-
-# ============ Message Models ============ #
-
-
-class CoPilotExecutionEntry(BaseModel):
-    """Task payload for CoPilot AI generation.
-
-    This model represents a chat generation task to be processed by the executor.
-    """
-
-    task_id: str
-    """Unique identifier for this task (used for stream registry)"""
-
-    session_id: str
-    """Chat session ID"""
-
-    user_id: str | None
-    """User ID (may be None for anonymous users)"""
-
-    operation_id: str
-    """Operation ID for webhook callbacks and completion tracking"""
-
-    message: str
-    """User's message to process"""
-
-    is_user_message: bool = True
-    """Whether the message is from the user (vs system/assistant)"""
-
-    context: dict[str, str] | None = None
-    """Optional context for the message (e.g., {url: str, content: str})"""
-
-
-class CancelCoPilotEvent(BaseModel):
-    """Event to cancel a CoPilot operation."""
-
-    task_id: str
-    """Task ID to cancel"""
-
-
-# ============ Queue Publishing Helpers ============ #
-
-
-async def enqueue_copilot_task(
-    task_id: str,
-    session_id: str,
-    user_id: str | None,
-    operation_id: str,
-    message: str,
-    is_user_message: bool = True,
-    context: dict[str, str] | None = None,
-) -> None:
-    """Enqueue a CoPilot task for processing by the executor service.
-
-    Args:
-        task_id: Unique identifier for this task (used for stream registry)
-        session_id: Chat session ID
-        user_id: User ID (may be None for anonymous users)
-        operation_id: Operation ID for webhook callbacks and completion tracking
-        message: User's message to process
-        is_user_message: Whether the message is from the user (vs system/assistant)
-        context: Optional context for the message (e.g., {url: str, content: str})
-    """
-    from backend.util.clients import get_async_copilot_queue
-
-    entry = CoPilotExecutionEntry(
-        task_id=task_id,
-        session_id=session_id,
-        user_id=user_id,
-        operation_id=operation_id,
-        message=message,
-        is_user_message=is_user_message,
-        context=context,
-    )
-
-    queue_client = await get_async_copilot_queue()
-    await queue_client.publish_message(
-        routing_key=COPILOT_EXECUTION_ROUTING_KEY,
-        message=entry.model_dump_json(),
-        exchange=COPILOT_EXECUTION_EXCHANGE,
-    )
--- a/autogpt_platform/backend/backend/copilot/sdk/init.py
+++ b/autogpt_platform/backend/backend/copilot/sdk/init.py
@@ -1,14 +0,0 @@
-"""Claude Agent SDK integration for CoPilot.
-
-This module provides the integration layer between the Claude Agent SDK
-and the existing CoPilot tool system, enabling drop-in replacement of
-the current LLM orchestration with the battle-tested Claude Agent SDK.
-"""
-
-from .service import stream_chat_completion_sdk
-from .tool_adapter import create_copilot_mcp_server
-
-__all__ = [
-    "stream_chat_completion_sdk",
-    "create_copilot_mcp_server",
-]
--- a/autogpt_platform/backend/backend/copilot/sdk/response_adapter.py
+++ b/autogpt_platform/backend/backend/copilot/sdk/response_adapter.py
@@ -1,201 +0,0 @@
-"""Response adapter for converting Claude Agent SDK messages to Vercel AI SDK format.
-
-This module provides the adapter layer that converts streaming messages from
-the Claude Agent SDK into the Vercel AI SDK UI Stream Protocol format that
-the frontend expects.
-"""
-
-import json
-import logging
-import uuid
-
-from claude_agent_sdk import (
-    AssistantMessage,
-    Message,
-    ResultMessage,
-    SystemMessage,
-    TextBlock,
-    ToolResultBlock,
-    ToolUseBlock,
-    UserMessage,
-)
-
-from backend.copilot.response_model import (
-    StreamBaseResponse,
-    StreamError,
-    StreamFinish,
-    StreamFinishStep,
-    StreamStart,
-    StreamStartStep,
-    StreamTextDelta,
-    StreamTextEnd,
-    StreamTextStart,
-    StreamToolInputAvailable,
-    StreamToolInputStart,
-    StreamToolOutputAvailable,
-)
-
-from .tool_adapter import MCP_TOOL_PREFIX, pop_pending_tool_output
-
-logger = logging.getLogger(__name__)
-
-
-class SDKResponseAdapter:
-    """Adapter for converting Claude Agent SDK messages to Vercel AI SDK format.
-
-    This class maintains state during a streaming session to properly track
-    text blocks, tool calls, and message lifecycle.
-    """
-
-    def __init__(self, message_id: str | None = None):
-        self.message_id = message_id or str(uuid.uuid4())
-        self.text_block_id = str(uuid.uuid4())
-        self.has_started_text = False
-        self.has_ended_text = False
-        self.current_tool_calls: dict[str, dict[str, str]] = {}
-        self.task_id: str | None = None
-        self.step_open = False
-
-    def set_task_id(self, task_id: str) -> None:
-        """Set the task ID for reconnection support."""
-        self.task_id = task_id
-
-    def convert_message(self, sdk_message: Message) -> list[StreamBaseResponse]:
-        """Convert a single SDK message to Vercel AI SDK format."""
-        responses: list[StreamBaseResponse] = []
-
-        if isinstance(sdk_message, SystemMessage):
-            if sdk_message.subtype == "init":
-                responses.append(
-                    StreamStart(messageId=self.message_id, taskId=self.task_id)
-                )
-                # Open the first step (matches non-SDK: StreamStart then StreamStartStep)
-                responses.append(StreamStartStep())
-                self.step_open = True
-
-        elif isinstance(sdk_message, AssistantMessage):
-            # After tool results, the SDK sends a new AssistantMessage for the
-            # next LLM turn. Open a new step if the previous one was closed.
-            if not self.step_open:
-                responses.append(StreamStartStep())
-                self.step_open = True
-
-            for block in sdk_message.content:
-                if isinstance(block, TextBlock):
-                    if block.text:
-                        self._ensure_text_started(responses)
-                        responses.append(
-                            StreamTextDelta(id=self.text_block_id, delta=block.text)
-                        )
-
-                elif isinstance(block, ToolUseBlock):
-                    self._end_text_if_open(responses)
-
-                    # Strip MCP prefix so frontend sees "find_block"
-                    # instead of "mcp__copilot__find_block".
-                    tool_name = block.name.removeprefix(MCP_TOOL_PREFIX)
-
-                    responses.append(
-                        StreamToolInputStart(toolCallId=block.id, toolName=tool_name)
-                    )
-                    responses.append(
-                        StreamToolInputAvailable(
-                            toolCallId=block.id,
-                            toolName=tool_name,
-                            input=block.input,
-                        )
-                    )
-                    self.current_tool_calls[block.id] = {"name": tool_name}
-
-        elif isinstance(sdk_message, UserMessage):
-            # UserMessage carries tool results back from tool execution.
-            content = sdk_message.content
-            blocks = content if isinstance(content, list) else []
-            for block in blocks:
-                if isinstance(block, ToolResultBlock) and block.tool_use_id:
-                    tool_info = self.current_tool_calls.get(block.tool_use_id, {})
-                    tool_name = tool_info.get("name", "unknown")
-
-                    # Prefer the stashed full output over the SDK's
-                    # (potentially truncated) ToolResultBlock content.
-                    # The SDK truncates large results, writing them to disk,
-                    # which breaks frontend widget parsing.
-                    output = pop_pending_tool_output(tool_name) or (
-                        _extract_tool_output(block.content)
-                    )
-
-                    responses.append(
-                        StreamToolOutputAvailable(
-                            toolCallId=block.tool_use_id,
-                            toolName=tool_name,
-                            output=output,
-                            success=not (block.is_error or False),
-                        )
-                    )
-
-            # Close the current step after tool results — the next
-            # AssistantMessage will open a new step for the continuation.
-            if self.step_open:
-                responses.append(StreamFinishStep())
-                self.step_open = False
-
-        elif isinstance(sdk_message, ResultMessage):
-            self._end_text_if_open(responses)
-            # Close the step before finishing.
-            if self.step_open:
-                responses.append(StreamFinishStep())
-                self.step_open = False
-
-            if sdk_message.subtype == "success":
-                responses.append(StreamFinish())
-            elif sdk_message.subtype in ("error", "error_during_execution"):
-                error_msg = getattr(sdk_message, "result", None) or "Unknown error"
-                responses.append(
-                    StreamError(errorText=str(error_msg), code="sdk_error")
-                )
-                responses.append(StreamFinish())
-            else:
-                logger.warning(
-                    f"Unexpected ResultMessage subtype: {sdk_message.subtype}"
-                )
-                responses.append(StreamFinish())
-
-        else:
-            logger.debug(f"Unhandled SDK message type: {type(sdk_message).__name__}")
-
-        return responses
-
-    def _ensure_text_started(self, responses: list[StreamBaseResponse]) -> None:
-        """Start (or restart) a text block if needed."""
-        if not self.has_started_text or self.has_ended_text:
-            if self.has_ended_text:
-                self.text_block_id = str(uuid.uuid4())
-                self.has_ended_text = False
-            responses.append(StreamTextStart(id=self.text_block_id))
-            self.has_started_text = True
-
-    def _end_text_if_open(self, responses: list[StreamBaseResponse]) -> None:
-        """End the current text block if one is open."""
-        if self.has_started_text and not self.has_ended_text:
-            responses.append(StreamTextEnd(id=self.text_block_id))
-            self.has_ended_text = True
-
-
-def _extract_tool_output(content: str | list[dict[str, str]] | None) -> str:
-    """Extract a string output from a ToolResultBlock's content field."""
-    if isinstance(content, str):
-        return content
-    if isinstance(content, list):
-        parts = [item.get("text", "") for item in content if item.get("type") == "text"]
-        if parts:
-            return "".join(parts)
-        try:
-            return json.dumps(content)
-        except (TypeError, ValueError):
-            return str(content)
-    if content is None:
-        return ""
-    try:
-        return json.dumps(content)
-    except (TypeError, ValueError):
-        return str(content)
--- a/autogpt_platform/backend/backend/copilot/sdk/response_adapter_test.py
+++ b/autogpt_platform/backend/backend/copilot/sdk/response_adapter_test.py
@@ -1,366 +0,0 @@
-"""Unit tests for the SDK response adapter."""
-
-from claude_agent_sdk import (
-    AssistantMessage,
-    ResultMessage,
-    SystemMessage,
-    TextBlock,
-    ToolResultBlock,
-    ToolUseBlock,
-    UserMessage,
-)
-
-from backend.copilot.response_model import (
-    StreamBaseResponse,
-    StreamError,
-    StreamFinish,
-    StreamFinishStep,
-    StreamStart,
-    StreamStartStep,
-    StreamTextDelta,
-    StreamTextEnd,
-    StreamTextStart,
-    StreamToolInputAvailable,
-    StreamToolInputStart,
-    StreamToolOutputAvailable,
-)
-
-from .response_adapter import SDKResponseAdapter
-from .tool_adapter import MCP_TOOL_PREFIX
-
-
-def _adapter() -> SDKResponseAdapter:
-    a = SDKResponseAdapter(message_id="msg-1")
-    a.set_task_id("task-1")
-    return a
-
-
-# -- SystemMessage -----------------------------------------------------------
-
-
-def test_system_init_emits_start_and_step():
-    adapter = _adapter()
-    results = adapter.convert_message(SystemMessage(subtype="init", data={}))
-    assert len(results) == 2
-    assert isinstance(results[0], StreamStart)
-    assert results[0].messageId == "msg-1"
-    assert results[0].taskId == "task-1"
-    assert isinstance(results[1], StreamStartStep)
-
-
-def test_system_non_init_emits_nothing():
-    adapter = _adapter()
-    results = adapter.convert_message(SystemMessage(subtype="other", data={}))
-    assert results == []
-
-
-# -- AssistantMessage with TextBlock -----------------------------------------
-
-
-def test_text_block_emits_step_start_and_delta():
-    adapter = _adapter()
-    msg = AssistantMessage(content=[TextBlock(text="hello")], model="test")
-    results = adapter.convert_message(msg)
-    assert len(results) == 3
-    assert isinstance(results[0], StreamStartStep)
-    assert isinstance(results[1], StreamTextStart)
-    assert isinstance(results[2], StreamTextDelta)
-    assert results[2].delta == "hello"
-
-
-def test_empty_text_block_emits_only_step():
-    adapter = _adapter()
-    msg = AssistantMessage(content=[TextBlock(text="")], model="test")
-    results = adapter.convert_message(msg)
-    # Empty text skipped, but step still opens
-    assert len(results) == 1
-    assert isinstance(results[0], StreamStartStep)
-
-
-def test_multiple_text_deltas_reuse_block_id():
-    adapter = _adapter()
-    msg1 = AssistantMessage(content=[TextBlock(text="a")], model="test")
-    msg2 = AssistantMessage(content=[TextBlock(text="b")], model="test")
-    r1 = adapter.convert_message(msg1)
-    r2 = adapter.convert_message(msg2)
-    # First gets step+start+delta, second only delta (block & step already started)
-    assert len(r1) == 3
-    assert isinstance(r1[0], StreamStartStep)
-    assert isinstance(r1[1], StreamTextStart)
-    assert len(r2) == 1
-    assert isinstance(r2[0], StreamTextDelta)
-    assert r1[1].id == r2[0].id  # same block ID
-
-
-# -- AssistantMessage with ToolUseBlock --------------------------------------
-
-
-def test_tool_use_emits_input_start_and_available():
-    """Tool names arrive with MCP prefix and should be stripped for the frontend."""
-    adapter = _adapter()
-    msg = AssistantMessage(
-        content=[
-            ToolUseBlock(
-                id="tool-1",
-                name=f"{MCP_TOOL_PREFIX}find_agent",
-                input={"q": "x"},
-            )
-        ],
-        model="test",
-    )
-    results = adapter.convert_message(msg)
-    assert len(results) == 3
-    assert isinstance(results[0], StreamStartStep)
-    assert isinstance(results[1], StreamToolInputStart)
-    assert results[1].toolCallId == "tool-1"
-    assert results[1].toolName == "find_agent"  # prefix stripped
-    assert isinstance(results[2], StreamToolInputAvailable)
-    assert results[2].toolName == "find_agent"  # prefix stripped
-    assert results[2].input == {"q": "x"}
-
-
-def test_text_then_tool_ends_text_block():
-    adapter = _adapter()
-    text_msg = AssistantMessage(content=[TextBlock(text="thinking...")], model="test")
-    tool_msg = AssistantMessage(
-        content=[ToolUseBlock(id="t1", name=f"{MCP_TOOL_PREFIX}tool", input={})],
-        model="test",
-    )
-    adapter.convert_message(text_msg)  # opens step + text
-    results = adapter.convert_message(tool_msg)
-    # Step already open, so: TextEnd, ToolInputStart, ToolInputAvailable
-    assert len(results) == 3
-    assert isinstance(results[0], StreamTextEnd)
-    assert isinstance(results[1], StreamToolInputStart)
-
-
-# -- UserMessage with ToolResultBlock ----------------------------------------
-
-
-def test_tool_result_emits_output_and_finish_step():
-    adapter = _adapter()
-    # First register the tool call (opens step) — SDK sends prefixed name
-    tool_msg = AssistantMessage(
-        content=[ToolUseBlock(id="t1", name=f"{MCP_TOOL_PREFIX}find_agent", input={})],
-        model="test",
-    )
-    adapter.convert_message(tool_msg)
-
-    # Now send tool result
-    result_msg = UserMessage(
-        content=[ToolResultBlock(tool_use_id="t1", content="found 3 agents")]
-    )
-    results = adapter.convert_message(result_msg)
-    assert len(results) == 2
-    assert isinstance(results[0], StreamToolOutputAvailable)
-    assert results[0].toolCallId == "t1"
-    assert results[0].toolName == "find_agent"  # prefix stripped
-    assert results[0].output == "found 3 agents"
-    assert results[0].success is True
-    assert isinstance(results[1], StreamFinishStep)
-
-
-def test_tool_result_error():
-    adapter = _adapter()
-    adapter.convert_message(
-        AssistantMessage(
-            content=[
-                ToolUseBlock(id="t1", name=f"{MCP_TOOL_PREFIX}run_agent", input={})
-            ],
-            model="test",
-        )
-    )
-    result_msg = UserMessage(
-        content=[ToolResultBlock(tool_use_id="t1", content="timeout", is_error=True)]
-    )
-    results = adapter.convert_message(result_msg)
-    assert isinstance(results[0], StreamToolOutputAvailable)
-    assert results[0].success is False
-    assert isinstance(results[1], StreamFinishStep)
-
-
-def test_tool_result_list_content():
-    adapter = _adapter()
-    adapter.convert_message(
-        AssistantMessage(
-            content=[ToolUseBlock(id="t1", name=f"{MCP_TOOL_PREFIX}tool", input={})],
-            model="test",
-        )
-    )
-    result_msg = UserMessage(
-        content=[
-            ToolResultBlock(
-                tool_use_id="t1",
-                content=[
-                    {"type": "text", "text": "line1"},
-                    {"type": "text", "text": "line2"},
-                ],
-            )
-        ]
-    )
-    results = adapter.convert_message(result_msg)
-    assert isinstance(results[0], StreamToolOutputAvailable)
-    assert results[0].output == "line1line2"
-    assert isinstance(results[1], StreamFinishStep)
-
-
-def test_string_user_message_ignored():
-    """A plain string UserMessage (not tool results) produces no output."""
-    adapter = _adapter()
-    results = adapter.convert_message(UserMessage(content="hello"))
-    assert results == []
-
-
-# -- ResultMessage -----------------------------------------------------------
-
-
-def test_result_success_emits_finish_step_and_finish():
-    adapter = _adapter()
-    # Start some text first (opens step)
-    adapter.convert_message(
-        AssistantMessage(content=[TextBlock(text="done")], model="test")
-    )
-    msg = ResultMessage(
-        subtype="success",
-        duration_ms=100,
-        duration_api_ms=50,
-        is_error=False,
-        num_turns=1,
-        session_id="s1",
-    )
-    results = adapter.convert_message(msg)
-    # TextEnd + FinishStep + StreamFinish
-    assert len(results) == 3
-    assert isinstance(results[0], StreamTextEnd)
-    assert isinstance(results[1], StreamFinishStep)
-    assert isinstance(results[2], StreamFinish)
-
-
-def test_result_error_emits_error_and_finish():
-    adapter = _adapter()
-    msg = ResultMessage(
-        subtype="error",
-        duration_ms=100,
-        duration_api_ms=50,
-        is_error=True,
-        num_turns=0,
-        session_id="s1",
-        result="API rate limited",
-    )
-    results = adapter.convert_message(msg)
-    # No step was open, so no FinishStep — just Error + Finish
-    assert len(results) == 2
-    assert isinstance(results[0], StreamError)
-    assert "API rate limited" in results[0].errorText
-    assert isinstance(results[1], StreamFinish)
-
-
-# -- Text after tools (new block ID) ----------------------------------------
-
-
-def test_text_after_tool_gets_new_block_id():
-    adapter = _adapter()
-    # Text -> Tool -> ToolResult -> Text should get a new text block ID and step
-    adapter.convert_message(
-        AssistantMessage(content=[TextBlock(text="before")], model="test")
-    )
-    adapter.convert_message(
-        AssistantMessage(
-            content=[ToolUseBlock(id="t1", name=f"{MCP_TOOL_PREFIX}tool", input={})],
-            model="test",
-        )
-    )
-    # Send tool result (closes step)
-    adapter.convert_message(
-        UserMessage(content=[ToolResultBlock(tool_use_id="t1", content="ok")])
-    )
-    results = adapter.convert_message(
-        AssistantMessage(content=[TextBlock(text="after")], model="test")
-    )
-    # Should get StreamStartStep (new step) + StreamTextStart (new block) + StreamTextDelta
-    assert len(results) == 3
-    assert isinstance(results[0], StreamStartStep)
-    assert isinstance(results[1], StreamTextStart)
-    assert isinstance(results[2], StreamTextDelta)
-    assert results[2].delta == "after"
-
-
-# -- Full conversation flow --------------------------------------------------
-
-
-def test_full_conversation_flow():
-    """Simulate a complete conversation: init -> text -> tool -> result -> text -> finish."""
-    adapter = _adapter()
-    all_responses: list[StreamBaseResponse] = []
-
-    # 1. Init
-    all_responses.extend(
-        adapter.convert_message(SystemMessage(subtype="init", data={}))
-    )
-    # 2. Assistant text
-    all_responses.extend(
-        adapter.convert_message(
-            AssistantMessage(content=[TextBlock(text="Let me search")], model="test")
-        )
-    )
-    # 3. Tool use
-    all_responses.extend(
-        adapter.convert_message(
-            AssistantMessage(
-                content=[
-                    ToolUseBlock(
-                        id="t1",
-                        name=f"{MCP_TOOL_PREFIX}find_agent",
-                        input={"query": "email"},
-                    )
-                ],
-                model="test",
-            )
-        )
-    )
-    # 4. Tool result
-    all_responses.extend(
-        adapter.convert_message(
-            UserMessage(
-                content=[ToolResultBlock(tool_use_id="t1", content="Found 2 agents")]
-            )
-        )
-    )
-    # 5. More text
-    all_responses.extend(
-        adapter.convert_message(
-            AssistantMessage(content=[TextBlock(text="I found 2")], model="test")
-        )
-    )
-    # 6. Result
-    all_responses.extend(
-        adapter.convert_message(
-            ResultMessage(
-                subtype="success",
-                duration_ms=500,
-                duration_api_ms=400,
-                is_error=False,
-                num_turns=2,
-                session_id="s1",
-            )
-        )
-    )
-
-    types = [type(r).__name__ for r in all_responses]
-    assert types == [
-        "StreamStart",
-        "StreamStartStep",  # step 1: text + tool call
-        "StreamTextStart",
-        "StreamTextDelta",  # "Let me search"
-        "StreamTextEnd",  # closed before tool
-        "StreamToolInputStart",
-        "StreamToolInputAvailable",
-        "StreamToolOutputAvailable",  # tool result
-        "StreamFinishStep",  # step 1 closed after tool result
-        "StreamStartStep",  # step 2: continuation text
-        "StreamTextStart",  # new block after tool
-        "StreamTextDelta",  # "I found 2"
-        "StreamTextEnd",  # closed by result
-        "StreamFinishStep",  # step 2 closed
-        "StreamFinish",
-    ]
--- a/autogpt_platform/backend/backend/copilot/sdk/security_hooks.py
+++ b/autogpt_platform/backend/backend/copilot/sdk/security_hooks.py
@@ -1,305 +0,0 @@
-"""Security hooks for Claude Agent SDK integration.
-
-This module provides security hooks that validate tool calls before execution,
-ensuring multi-user isolation and preventing unauthorized operations.
-"""
-
-import json
-import logging
-import os
-import re
-from collections.abc import Callable
-from typing import Any, cast
-
-from .tool_adapter import (
-    BLOCKED_TOOLS,
-    DANGEROUS_PATTERNS,
-    MCP_TOOL_PREFIX,
-    WORKSPACE_SCOPED_TOOLS,
-)
-
-logger = logging.getLogger(__name__)
-
-
-def _deny(reason: str) -> dict[str, Any]:
-    """Return a hook denial response."""
-    return {
-        "hookSpecificOutput": {
-            "hookEventName": "PreToolUse",
-            "permissionDecision": "deny",
-            "permissionDecisionReason": reason,
-        }
-    }
-
-
-def _validate_workspace_path(
-    tool_name: str, tool_input: dict[str, Any], sdk_cwd: str | None
-) -> dict[str, Any]:
-    """Validate that a workspace-scoped tool only accesses allowed paths.
-
-    Allowed directories:
-    - The SDK working directory (``/tmp/copilot-<session>/``)
-    - The SDK tool-results directory (``~/.claude/projects/…/tool-results/``)
-    """
-    path = tool_input.get("file_path") or tool_input.get("path") or ""
-    if not path:
-        # Glob/Grep without a path default to cwd which is already sandboxed
-        return {}
-
-    # Resolve relative paths against sdk_cwd (the SDK sets cwd so the LLM
-    # naturally uses relative paths like "test.txt" instead of absolute ones).
-    # Tilde paths (~/) are home-dir references, not relative — expand first.
-    if path.startswith("~"):
-        resolved = os.path.realpath(os.path.expanduser(path))
-    elif not os.path.isabs(path) and sdk_cwd:
-        resolved = os.path.realpath(os.path.join(sdk_cwd, path))
-    else:
-        resolved = os.path.realpath(path)
-
-    # Allow access within the SDK working directory
-    if sdk_cwd:
-        norm_cwd = os.path.realpath(sdk_cwd)
-        if resolved.startswith(norm_cwd + os.sep) or resolved == norm_cwd:
-            return {}
-
-    # Allow access to ~/.claude/projects/*/tool-results/ (big tool results)
-    claude_dir = os.path.realpath(os.path.expanduser("~/.claude/projects"))
-    tool_results_seg = os.sep + "tool-results" + os.sep
-    if resolved.startswith(claude_dir + os.sep) and tool_results_seg in resolved:
-        return {}
-
-    logger.warning(
-        f"Blocked {tool_name} outside workspace: {path} (resolved={resolved})"
-    )
-    workspace_hint = f" Allowed workspace: {sdk_cwd}" if sdk_cwd else ""
-    return _deny(
-        f"[SECURITY] Tool '{tool_name}' can only access files within the workspace "
-        f"directory.{workspace_hint} "
-        "This is enforced by the platform and cannot be bypassed."
-    )
-
-
-def _validate_tool_access(
-    tool_name: str, tool_input: dict[str, Any], sdk_cwd: str | None = None
-) -> dict[str, Any]:
-    """Validate that a tool call is allowed.
-
-    Returns:
-        Empty dict to allow, or dict with hookSpecificOutput to deny
-    """
-    # Block forbidden tools
-    if tool_name in BLOCKED_TOOLS:
-        logger.warning(f"Blocked tool access attempt: {tool_name}")
-        return _deny(
-            f"[SECURITY] Tool '{tool_name}' is blocked for security. "
-            "This is enforced by the platform and cannot be bypassed. "
-            "Use the CoPilot-specific MCP tools instead."
-        )
-
-    # Workspace-scoped tools: allowed only within the SDK workspace directory
-    if tool_name in WORKSPACE_SCOPED_TOOLS:
-        return _validate_workspace_path(tool_name, tool_input, sdk_cwd)
-
-    # Check for dangerous patterns in tool input
-    # Use json.dumps for predictable format (str() produces Python repr)
-    input_str = json.dumps(tool_input) if tool_input else ""
-
-    for pattern in DANGEROUS_PATTERNS:
-        if re.search(pattern, input_str, re.IGNORECASE):
-            logger.warning(
-                f"Blocked dangerous pattern in tool input: {pattern} in {tool_name}"
-            )
-            return _deny(
-                "[SECURITY] Input contains a blocked pattern. "
-                "This is enforced by the platform and cannot be bypassed."
-            )
-
-    return {}
-
-
-def _validate_user_isolation(
-    tool_name: str, tool_input: dict[str, Any], user_id: str | None
-) -> dict[str, Any]:
-    """Validate that tool calls respect user isolation."""
-    # For workspace file tools, ensure path doesn't escape
-    if "workspace" in tool_name.lower():
-        path = tool_input.get("path", "") or tool_input.get("file_path", "")
-        if path:
-            # Check for path traversal
-            if ".." in path or path.startswith("/"):
-                logger.warning(
-                    f"Blocked path traversal attempt: {path} by user {user_id}"
-                )
-                return {
-                    "hookSpecificOutput": {
-                        "hookEventName": "PreToolUse",
-                        "permissionDecision": "deny",
-                        "permissionDecisionReason": "Path traversal not allowed",
-                    }
-                }
-
-    return {}
-
-
-def create_security_hooks(
-    user_id: str | None,
-    sdk_cwd: str | None = None,
-    max_subtasks: int = 3,
-    on_stop: Callable[[str, str], None] | None = None,
-) -> dict[str, Any]:
-    """Create the security hooks configuration for Claude Agent SDK.
-
-    Includes security validation and observability hooks:
-    - PreToolUse: Security validation before tool execution
-    - PostToolUse: Log successful tool executions
-    - PostToolUseFailure: Log and handle failed tool executions
-    - PreCompact: Log context compaction events (SDK handles compaction automatically)
-    - Stop: Capture transcript path for stateless resume (when *on_stop* is provided)
-
-    Args:
-        user_id: Current user ID for isolation validation
-        sdk_cwd: SDK working directory for workspace-scoped tool validation
-        max_subtasks: Maximum Task (sub-agent) spawns allowed per session
-        on_stop: Callback ``(transcript_path, sdk_session_id)`` invoked when
-            the SDK finishes processing — used to read the JSONL transcript
-            before the CLI process exits.
-
-    Returns:
-        Hooks configuration dict for ClaudeAgentOptions
-    """
-    try:
-        from claude_agent_sdk import HookMatcher
-        from claude_agent_sdk.types import HookContext, HookInput, SyncHookJSONOutput
-
-        # Per-session counter for Task sub-agent spawns
-        task_spawn_count = 0
-
-        async def pre_tool_use_hook(
-            input_data: HookInput,
-            tool_use_id: str | None,
-            context: HookContext,
-        ) -> SyncHookJSONOutput:
-            """Combined pre-tool-use validation hook."""
-            nonlocal task_spawn_count
-            _ = context  # unused but required by signature
-            tool_name = cast(str, input_data.get("tool_name", ""))
-            tool_input = cast(dict[str, Any], input_data.get("tool_input", {}))
-
-            # Rate-limit Task (sub-agent) spawns per session
-            if tool_name == "Task":
-                task_spawn_count += 1
-                if task_spawn_count > max_subtasks:
-                    logger.warning(
-                        f"[SDK] Task limit reached ({max_subtasks}), user={user_id}"
-                    )
-                    return cast(
-                        SyncHookJSONOutput,
-                        _deny(
-                            f"Maximum {max_subtasks} sub-tasks per session. "
-                            "Please continue in the main conversation."
-                        ),
-                    )
-
-            # Strip MCP prefix for consistent validation
-            is_copilot_tool = tool_name.startswith(MCP_TOOL_PREFIX)
-            clean_name = tool_name.removeprefix(MCP_TOOL_PREFIX)
-
-            # Only block non-CoPilot tools; our MCP-registered tools
-            # (including Read for oversized results) are already sandboxed.
-            if not is_copilot_tool:
-                result = _validate_tool_access(clean_name, tool_input, sdk_cwd)
-                if result:
-                    return cast(SyncHookJSONOutput, result)
-
-            # Validate user isolation
-            result = _validate_user_isolation(clean_name, tool_input, user_id)
-            if result:
-                return cast(SyncHookJSONOutput, result)
-
-            logger.debug(f"[SDK] Tool start: {tool_name}, user={user_id}")
-            return cast(SyncHookJSONOutput, {})
-
-        async def post_tool_use_hook(
-            input_data: HookInput,
-            tool_use_id: str | None,
-            context: HookContext,
-        ) -> SyncHookJSONOutput:
-            """Log successful tool executions for observability."""
-            _ = context
-            tool_name = cast(str, input_data.get("tool_name", ""))
-            logger.debug(f"[SDK] Tool success: {tool_name}, tool_use_id={tool_use_id}")
-            return cast(SyncHookJSONOutput, {})
-
-        async def post_tool_failure_hook(
-            input_data: HookInput,
-            tool_use_id: str | None,
-            context: HookContext,
-        ) -> SyncHookJSONOutput:
-            """Log failed tool executions for debugging."""
-            _ = context
-            tool_name = cast(str, input_data.get("tool_name", ""))
-            error = input_data.get("error", "Unknown error")
-            logger.warning(
-                f"[SDK] Tool failed: {tool_name}, error={error}, "
-                f"user={user_id}, tool_use_id={tool_use_id}"
-            )
-            return cast(SyncHookJSONOutput, {})
-
-        async def pre_compact_hook(
-            input_data: HookInput,
-            tool_use_id: str | None,
-            context: HookContext,
-        ) -> SyncHookJSONOutput:
-            """Log when SDK triggers context compaction.
-
-            The SDK automatically compacts conversation history when it grows too large.
-            This hook provides visibility into when compaction happens.
-            """
-            _ = context, tool_use_id
-            trigger = input_data.get("trigger", "auto")
-            logger.info(
-                f"[SDK] Context compaction triggered: {trigger}, user={user_id}"
-            )
-            return cast(SyncHookJSONOutput, {})
-
-        # --- Stop hook: capture transcript path for stateless resume ---
-        async def stop_hook(
-            input_data: HookInput,
-            tool_use_id: str | None,
-            context: HookContext,
-        ) -> SyncHookJSONOutput:
-            """Capture transcript path when SDK finishes processing.
-
-            The Stop hook fires while the CLI process is still alive, giving us
-            a reliable window to read the JSONL transcript before SIGTERM.
-            """
-            _ = context, tool_use_id
-            transcript_path = cast(str, input_data.get("transcript_path", ""))
-            sdk_session_id = cast(str, input_data.get("session_id", ""))
-
-            if transcript_path and on_stop:
-                logger.info(
-                    f"[SDK] Stop hook: transcript_path={transcript_path}, "
-                    f"sdk_session_id={sdk_session_id[:12]}..."
-                )
-                on_stop(transcript_path, sdk_session_id)
-
-            return cast(SyncHookJSONOutput, {})
-
-        hooks: dict[str, Any] = {
-            "PreToolUse": [HookMatcher(matcher="*", hooks=[pre_tool_use_hook])],
-            "PostToolUse": [HookMatcher(matcher="*", hooks=[post_tool_use_hook])],
-            "PostToolUseFailure": [
-                HookMatcher(matcher="*", hooks=[post_tool_failure_hook])
-            ],
-            "PreCompact": [HookMatcher(matcher="*", hooks=[pre_compact_hook])],
-        }
-
-        if on_stop is not None:
-            hooks["Stop"] = [HookMatcher(matcher=None, hooks=[stop_hook])]
-
-        return hooks
-    except ImportError:
-        # Fallback for when SDK isn't available - return empty hooks
-        logger.warning("claude-agent-sdk not available, security hooks disabled")
-        return {}
--- a/autogpt_platform/backend/backend/copilot/sdk/security_hooks_test.py
+++ b/autogpt_platform/backend/backend/copilot/sdk/security_hooks_test.py
@@ -1,190 +0,0 @@
-"""Tests for SDK security hooks — workspace paths, tool access, and deny messages.
-
-These are pure unit tests with no external dependencies (no SDK, no DB, no server).
-They validate that the security hooks correctly block unauthorized paths,
-tool access, and dangerous input patterns.
-"""
-
-import os
-
-from .security_hooks import _validate_tool_access, _validate_user_isolation
-
-SDK_CWD = "/tmp/copilot-abc123"
-
-
-def _is_denied(result: dict) -> bool:
-    hook = result.get("hookSpecificOutput", {})
-    return hook.get("permissionDecision") == "deny"
-
-
-def _reason(result: dict) -> str:
-    return result.get("hookSpecificOutput", {}).get("permissionDecisionReason", "")
-
-
-# -- Blocked tools -----------------------------------------------------------
-
-
-def test_blocked_tools_denied():
-    for tool in ("bash", "shell", "exec", "terminal", "command"):
-        result = _validate_tool_access(tool, {})
-        assert _is_denied(result), f"{tool} should be blocked"
-
-
-def test_unknown_tool_allowed():
-    result = _validate_tool_access("SomeCustomTool", {})
-    assert result == {}
-
-
-# -- Workspace-scoped tools --------------------------------------------------
-
-
-def test_read_within_workspace_allowed():
-    result = _validate_tool_access(
-        "Read", {"file_path": f"{SDK_CWD}/file.txt"}, sdk_cwd=SDK_CWD
-    )
-    assert result == {}
-
-
-def test_write_within_workspace_allowed():
-    result = _validate_tool_access(
-        "Write", {"file_path": f"{SDK_CWD}/output.json"}, sdk_cwd=SDK_CWD
-    )
-    assert result == {}
-
-
-def test_edit_within_workspace_allowed():
-    result = _validate_tool_access(
-        "Edit", {"file_path": f"{SDK_CWD}/src/main.py"}, sdk_cwd=SDK_CWD
-    )
-    assert result == {}
-
-
-def test_glob_within_workspace_allowed():
-    result = _validate_tool_access("Glob", {"path": f"{SDK_CWD}/src"}, sdk_cwd=SDK_CWD)
-    assert result == {}
-
-
-def test_grep_within_workspace_allowed():
-    result = _validate_tool_access("Grep", {"path": f"{SDK_CWD}/src"}, sdk_cwd=SDK_CWD)
-    assert result == {}
-
-
-def test_read_outside_workspace_denied():
-    result = _validate_tool_access(
-        "Read", {"file_path": "/etc/passwd"}, sdk_cwd=SDK_CWD
-    )
-    assert _is_denied(result)
-
-
-def test_write_outside_workspace_denied():
-    result = _validate_tool_access(
-        "Write", {"file_path": "/home/user/secrets.txt"}, sdk_cwd=SDK_CWD
-    )
-    assert _is_denied(result)
-
-
-def test_traversal_attack_denied():
-    result = _validate_tool_access(
-        "Read",
-        {"file_path": f"{SDK_CWD}/../../etc/passwd"},
-        sdk_cwd=SDK_CWD,
-    )
-    assert _is_denied(result)
-
-
-def test_no_path_allowed():
-    """Glob/Grep without a path argument defaults to cwd — should pass."""
-    result = _validate_tool_access("Glob", {}, sdk_cwd=SDK_CWD)
-    assert result == {}
-
-
-def test_read_no_cwd_denies_absolute():
-    """If no sdk_cwd is set, absolute paths are denied."""
-    result = _validate_tool_access("Read", {"file_path": "/tmp/anything"})
-    assert _is_denied(result)
-
-
-# -- Tool-results directory --------------------------------------------------
-
-
-def test_read_tool_results_allowed():
-    home = os.path.expanduser("~")
-    path = f"{home}/.claude/projects/-tmp-copilot-abc123/tool-results/12345.txt"
-    result = _validate_tool_access("Read", {"file_path": path}, sdk_cwd=SDK_CWD)
-    assert result == {}
-
-
-def test_read_claude_projects_without_tool_results_denied():
-    home = os.path.expanduser("~")
-    path = f"{home}/.claude/projects/-tmp-copilot-abc123/settings.json"
-    result = _validate_tool_access("Read", {"file_path": path}, sdk_cwd=SDK_CWD)
-    assert _is_denied(result)
-
-
-# -- Built-in Bash is blocked (use bash_exec MCP tool instead) ---------------
-
-
-def test_bash_builtin_always_blocked():
-    """SDK built-in Bash is blocked — bash_exec MCP tool with bubblewrap is used instead."""
-    result = _validate_tool_access("Bash", {"command": "echo hello"}, sdk_cwd=SDK_CWD)
-    assert _is_denied(result)
-
-
-# -- Dangerous patterns ------------------------------------------------------
-
-
-def test_dangerous_pattern_blocked():
-    result = _validate_tool_access("SomeTool", {"cmd": "sudo rm -rf /"})
-    assert _is_denied(result)
-
-
-def test_subprocess_pattern_blocked():
-    result = _validate_tool_access("SomeTool", {"code": "subprocess.run(...)"})
-    assert _is_denied(result)
-
-
-# -- User isolation ----------------------------------------------------------
-
-
-def test_workspace_path_traversal_blocked():
-    result = _validate_user_isolation(
-        "workspace_read", {"path": "../../../etc/shadow"}, user_id="user-1"
-    )
-    assert _is_denied(result)
-
-
-def test_workspace_absolute_path_blocked():
-    result = _validate_user_isolation(
-        "workspace_read", {"path": "/etc/passwd"}, user_id="user-1"
-    )
-    assert _is_denied(result)
-
-
-def test_workspace_normal_path_allowed():
-    result = _validate_user_isolation(
-        "workspace_read", {"path": "src/main.py"}, user_id="user-1"
-    )
-    assert result == {}
-
-
-def test_non_workspace_tool_passes_isolation():
-    result = _validate_user_isolation(
-        "find_agent", {"query": "email"}, user_id="user-1"
-    )
-    assert result == {}
-
-
-# -- Deny message quality ----------------------------------------------------
-
-
-def test_blocked_tool_message_clarity():
-    """Deny messages must include [SECURITY] and 'cannot be bypassed'."""
-    reason = _reason(_validate_tool_access("bash", {}))
-    assert "[SECURITY]" in reason
-    assert "cannot be bypassed" in reason
-
-
-def test_bash_builtin_blocked_message_clarity():
-    reason = _reason(_validate_tool_access("Bash", {"command": "echo hello"}))
-    assert "[SECURITY]" in reason
-    assert "cannot be bypassed" in reason
--- a/autogpt_platform/backend/backend/copilot/sdk/service.py
+++ b/autogpt_platform/backend/backend/copilot/sdk/service.py
@@ -1,760 +0,0 @@
-"""Claude Agent SDK service layer for CoPilot chat completions."""
-
-import asyncio
-import json
-import logging
-import os
-import uuid
-from collections.abc import AsyncGenerator
-from dataclasses import dataclass
-from typing import Any
-
-from backend.util.exceptions import NotFoundError
-
-from .. import stream_registry
-from ..config import ChatConfig
-from ..model import (
-    ChatMessage,
-    ChatSession,
-    get_chat_session,
-    update_session_title,
-    upsert_chat_session,
-)
-from ..response_model import (
-    StreamBaseResponse,
-    StreamError,
-    StreamFinish,
-    StreamStart,
-    StreamTextDelta,
-    StreamToolInputAvailable,
-    StreamToolOutputAvailable,
-)
-from ..service import (
-    _build_system_prompt,
-    _execute_long_running_tool_with_streaming,
-    _generate_session_title,
-)
-from ..tools.models import OperationPendingResponse, OperationStartedResponse
-from ..tools.sandbox import WORKSPACE_PREFIX, make_session_path
-from ..tracking import track_user_message
-from .response_adapter import SDKResponseAdapter
-from .security_hooks import create_security_hooks
-from .tool_adapter import (
-    COPILOT_TOOL_NAMES,
-    SDK_DISALLOWED_TOOLS,
-    LongRunningCallback,
-    create_copilot_mcp_server,
-    set_execution_context,
-)
-from .transcript import (
-    download_transcript,
-    read_transcript_file,
-    upload_transcript,
-    validate_transcript,
-    write_transcript_to_tempfile,
-)
-
-logger = logging.getLogger(__name__)
-config = ChatConfig()
-
-# Set to hold background tasks to prevent garbage collection
-_background_tasks: set[asyncio.Task[Any]] = set()
-
-
-@dataclass
-class CapturedTranscript:
-    """Info captured by the SDK Stop hook for stateless --resume."""
-
-    path: str = ""
-    sdk_session_id: str = ""
-
-    @property
-    def available(self) -> bool:
-        return bool(self.path)
-
-
-_SDK_CWD_PREFIX = WORKSPACE_PREFIX
-
-# Appended to the system prompt to inform the agent about available tools.
-# The SDK built-in Bash is NOT available — use mcp__copilot__bash_exec instead,
-# which has kernel-level network isolation (unshare --net).
-_SDK_TOOL_SUPPLEMENT = """
-
-## Tool notes
-
- The SDK built-in Bash tool is NOT available.  Use the `bash_exec` MCP tool
-  for shell commands — it runs in a network-isolated sandbox.
- **Shared workspace**: The SDK Read/Write tools and `bash_exec` share the
-  same working directory. Files created by one are readable by the other.
-  These files are **ephemeral** — they exist only for the current session.
- **Persistent storage**: Use `write_workspace_file` / `read_workspace_file`
-  for files that should persist across sessions (stored in cloud storage).
- Long-running tools (create_agent, edit_agent, etc.) are handled
-  asynchronously.  You will receive an immediate response; the actual result
-  is delivered to the user via a background stream.
-"""
-
-
-def _build_long_running_callback(user_id: str | None) -> LongRunningCallback:
-    """Build a callback that delegates long-running tools to the non-SDK infrastructure.
-
-    Long-running tools (create_agent, edit_agent, etc.) are delegated to the
-    existing background infrastructure: stream_registry (Redis Streams),
-    database persistence, and SSE reconnection.  This means results survive
-    page refreshes / pod restarts, and the frontend shows the proper loading
-    widget with progress updates.
-
-    The returned callback matches the ``LongRunningCallback`` signature:
-    ``(tool_name, args, session) -> MCP response dict``.
-    """
-
-    async def _callback(
-        tool_name: str, args: dict[str, Any], session: ChatSession
-    ) -> dict[str, Any]:
-        operation_id = str(uuid.uuid4())
-        task_id = str(uuid.uuid4())
-        tool_call_id = f"sdk-{uuid.uuid4().hex[:12]}"
-        session_id = session.session_id
-
-        # --- Build user-friendly messages (matches non-SDK service) ---
-        if tool_name == "create_agent":
-            desc = args.get("description", "")
-            desc_preview = (desc[:100] + "...") if len(desc) > 100 else desc
-            pending_msg = (
-                f"Creating your agent: {desc_preview}"
-                if desc_preview
-                else "Creating agent... This may take a few minutes."
-            )
-            started_msg = (
-                "Agent creation started. You can close this tab - "
-                "check your library in a few minutes."
-            )
-        elif tool_name == "edit_agent":
-            changes = args.get("changes", "")
-            changes_preview = (changes[:100] + "...") if len(changes) > 100 else changes
-            pending_msg = (
-                f"Editing agent: {changes_preview}"
-                if changes_preview
-                else "Editing agent... This may take a few minutes."
-            )
-            started_msg = (
-                "Agent edit started. You can close this tab - "
-                "check your library in a few minutes."
-            )
-        else:
-            pending_msg = f"Running {tool_name}... This may take a few minutes."
-            started_msg = (
-                f"{tool_name} started. You can close this tab - "
-                "check back in a few minutes."
-            )
-
-        # --- Register task in Redis for SSE reconnection ---
-        await stream_registry.create_task(
-            task_id=task_id,
-            session_id=session_id,
-            user_id=user_id,
-            tool_call_id=tool_call_id,
-            tool_name=tool_name,
-            operation_id=operation_id,
-        )
-
-        # --- Save OperationPendingResponse to chat history ---
-        pending_message = ChatMessage(
-            role="tool",
-            content=OperationPendingResponse(
-                message=pending_msg,
-                operation_id=operation_id,
-                tool_name=tool_name,
-            ).model_dump_json(),
-            tool_call_id=tool_call_id,
-        )
-        session.messages.append(pending_message)
-        await upsert_chat_session(session)
-
-        # --- Spawn background task (reuses non-SDK infrastructure) ---
-        bg_task = asyncio.create_task(
-            _execute_long_running_tool_with_streaming(
-                tool_name=tool_name,
-                parameters=args,
-                tool_call_id=tool_call_id,
-                operation_id=operation_id,
-                task_id=task_id,
-                session_id=session_id,
-                user_id=user_id,
-            )
-        )
-        _background_tasks.add(bg_task)
-        bg_task.add_done_callback(_background_tasks.discard)
-        await stream_registry.set_task_asyncio_task(task_id, bg_task)
-
-        logger.info(
-            f"[SDK] Long-running tool {tool_name} delegated to background "
-            f"(operation_id={operation_id}, task_id={task_id})"
-        )
-
-        # --- Return OperationStartedResponse as MCP tool result ---
-        # This flows through SDK → response adapter → frontend, triggering
-        # the loading widget with SSE reconnection support.
-        started_json = OperationStartedResponse(
-            message=started_msg,
-            operation_id=operation_id,
-            tool_name=tool_name,
-            task_id=task_id,
-        ).model_dump_json()
-
-        return {
-            "content": [{"type": "text", "text": started_json}],
-            "isError": False,
-        }
-
-    return _callback
-
-
-def _resolve_sdk_model() -> str | None:
-    """Resolve the model name for the Claude Agent SDK CLI.
-
-    Uses ``config.claude_agent_model`` if set, otherwise derives from
-    ``config.model`` by stripping the OpenRouter provider prefix (e.g.,
-    ``"anthropic/claude-opus-4.6"`` → ``"claude-opus-4.6"``).
-    """
-    if config.claude_agent_model:
-        return config.claude_agent_model
-    model = config.model
-    if "/" in model:
-        return model.split("/", 1)[1]
-    return model
-
-
-def _build_sdk_env() -> dict[str, str]:
-    """Build env vars for the SDK CLI process.
-
-    Routes API calls through OpenRouter (or a custom base_url) using
-    the same ``config.api_key`` / ``config.base_url`` as the non-SDK path.
-    This gives per-call token and cost tracking on the OpenRouter dashboard.
-
-    Only overrides ``ANTHROPIC_API_KEY`` when a valid proxy URL and auth
-    token are both present — otherwise returns an empty dict so the SDK
-    falls back to its default credentials.
-    """
-    env: dict[str, str] = {}
-    if config.api_key and config.base_url:
-        # Strip /v1 suffix — SDK expects the base URL without a version path
-        base = config.base_url.rstrip("/")
-        if base.endswith("/v1"):
-            base = base[:-3]
-        if not base or not base.startswith("http"):
-            # Invalid base_url — don't override SDK defaults
-            return env
-        env["ANTHROPIC_BASE_URL"] = base
-        env["ANTHROPIC_AUTH_TOKEN"] = config.api_key
-        # Must be explicitly empty so the CLI uses AUTH_TOKEN instead
-        env["ANTHROPIC_API_KEY"] = ""
-    return env
-
-
-def _make_sdk_cwd(session_id: str) -> str:
-    """Create a safe, session-specific working directory path.
-
-    Delegates to :func:`~backend.copilot.tools.sandbox.make_session_path`
-    (single source of truth for path sanitization) and adds a defence-in-depth
-    assertion.
-    """
-    cwd = make_session_path(session_id)
-    # Defence-in-depth: normpath + startswith is a CodeQL-recognised sanitizer
-    cwd = os.path.normpath(cwd)
-    if not cwd.startswith(_SDK_CWD_PREFIX):
-        raise ValueError(f"SDK cwd escaped prefix: {cwd}")
-    return cwd
-
-
-def _cleanup_sdk_tool_results(cwd: str) -> None:
-    """Remove SDK tool-result files for a specific session working directory.
-
-    The SDK creates tool-result files under ~/.claude/projects/<encoded-cwd>/tool-results/.
-    We clean only the specific cwd's results to avoid race conditions between
-    concurrent sessions.
-
-    Security: cwd MUST be created by _make_sdk_cwd() which sanitizes session_id.
-    """
-    import shutil
-
-    # Validate cwd is under the expected prefix
-    normalized = os.path.normpath(cwd)
-    if not normalized.startswith(_SDK_CWD_PREFIX):
-        logger.warning(f"[SDK] Rejecting cleanup for path outside workspace: {cwd}")
-        return
-
-    # SDK encodes the cwd path by replacing '/' with '-'
-    encoded_cwd = normalized.replace("/", "-")
-
-    # Construct the project directory path (known-safe home expansion)
-    claude_projects = os.path.expanduser("~/.claude/projects")
-    project_dir = os.path.join(claude_projects, encoded_cwd)
-
-    # Security check 3: Validate project_dir is under ~/.claude/projects
-    project_dir = os.path.normpath(project_dir)
-    if not project_dir.startswith(claude_projects):
-        logger.warning(
-            f"[SDK] Rejecting cleanup for escaped project path: {project_dir}"
-        )
-        return
-
-    results_dir = os.path.join(project_dir, "tool-results")
-    if os.path.isdir(results_dir):
-        for filename in os.listdir(results_dir):
-            file_path = os.path.join(results_dir, filename)
-            try:
-                if os.path.isfile(file_path):
-                    os.remove(file_path)
-            except OSError:
-                pass
-
-    # Also clean up the temp cwd directory itself
-    try:
-        shutil.rmtree(normalized, ignore_errors=True)
-    except OSError:
-        pass
-
-
-async def _compress_conversation_history(
-    session: ChatSession,
-) -> list[ChatMessage]:
-    """Compress prior conversation messages if they exceed the token threshold.
-
-    Uses the shared compress_context() from prompt.py which supports:
-    - LLM summarization of old messages (keeps recent ones intact)
-    - Progressive content truncation as fallback
-    - Middle-out deletion as last resort
-
-    Returns the compressed prior messages (everything except the current message).
-    """
-    prior = session.messages[:-1]
-    if len(prior) < 2:
-        return prior
-
-    from backend.util.prompt import compress_context
-
-    # Convert ChatMessages to dicts for compress_context
-    messages_dict = []
-    for msg in prior:
-        msg_dict: dict[str, Any] = {"role": msg.role}
-        if msg.content:
-            msg_dict["content"] = msg.content
-        if msg.tool_calls:
-            msg_dict["tool_calls"] = msg.tool_calls
-        if msg.tool_call_id:
-            msg_dict["tool_call_id"] = msg.tool_call_id
-        messages_dict.append(msg_dict)
-
-    try:
-        import openai
-
-        async with openai.AsyncOpenAI(
-            api_key=config.api_key, base_url=config.base_url, timeout=30.0
-        ) as client:
-            result = await compress_context(
-                messages=messages_dict,
-                model=config.model,
-                client=client,
-            )
-    except Exception as e:
-        logger.warning(f"[SDK] Context compression with LLM failed: {e}")
-        # Fall back to truncation-only (no LLM summarization)
-        result = await compress_context(
-            messages=messages_dict,
-            model=config.model,
-            client=None,
-        )
-
-    if result.was_compacted:
-        logger.info(
-            f"[SDK] Context compacted: {result.original_token_count} -> "
-            f"{result.token_count} tokens "
-            f"({result.messages_summarized} summarized, "
-            f"{result.messages_dropped} dropped)"
-        )
-        # Convert compressed dicts back to ChatMessages
-        return [
-            ChatMessage(
-                role=m["role"],
-                content=m.get("content"),
-                tool_calls=m.get("tool_calls"),
-                tool_call_id=m.get("tool_call_id"),
-            )
-            for m in result.messages
-        ]
-
-    return prior
-
-
-def _format_conversation_context(messages: list[ChatMessage]) -> str | None:
-    """Format conversation messages into a context prefix for the user message.
-
-    Returns a string like:
-        <conversation_history>
-        User: hello
-        You responded: Hi! How can I help?
-        </conversation_history>
-
-    Returns None if there are no messages to format.
-    """
-    if not messages:
-        return None
-
-    lines: list[str] = []
-    for msg in messages:
-        if not msg.content:
-            continue
-        if msg.role == "user":
-            lines.append(f"User: {msg.content}")
-        elif msg.role == "assistant":
-            lines.append(f"You responded: {msg.content}")
-        # Skip tool messages — they're internal details
-
-    if not lines:
-        return None
-
-    return "<conversation_history>\n" + "\n".join(lines) + "\n</conversation_history>"
-
-
-async def stream_chat_completion_sdk(
-    session_id: str,
-    message: str | None = None,
-    tool_call_response: str | None = None,  # noqa: ARG001
-    is_user_message: bool = True,
-    user_id: str | None = None,
-    retry_count: int = 0,  # noqa: ARG001
-    session: ChatSession | None = None,
-    context: dict[str, str] | None = None,  # noqa: ARG001
-) -> AsyncGenerator[StreamBaseResponse, None]:
-    """Stream chat completion using Claude Agent SDK.
-
-    Drop-in replacement for stream_chat_completion with improved reliability.
-    """
-
-    if session is None:
-        session = await get_chat_session(session_id, user_id)
-
-    if not session:
-        raise NotFoundError(
-            f"Session {session_id} not found. Please create a new session first."
-        )
-
-    # Append the new message to the session if it's not already there
-    new_message_role = "user" if is_user_message else "assistant"
-    if message and (
-        len(session.messages) == 0
-        or not (
-            session.messages[-1].role == new_message_role
-            and session.messages[-1].content == message
-        )
-    ):
-        session.messages.append(ChatMessage(role=new_message_role, content=message))
-        if is_user_message:
-            track_user_message(
-                user_id=user_id, session_id=session_id, message_length=len(message)
-            )
-
-    session = await upsert_chat_session(session)
-
-    # Generate title for new sessions (first user message)
-    if is_user_message and not session.title:
-        user_messages = [m for m in session.messages if m.role == "user"]
-        if len(user_messages) == 1:
-            first_message = user_messages[0].content or message or ""
-            if first_message:
-                task = asyncio.create_task(
-                    _update_title_async(session_id, first_message, user_id)
-                )
-                _background_tasks.add(task)
-                task.add_done_callback(_background_tasks.discard)
-
-    # Build system prompt (reuses non-SDK path with Langfuse support)
-    has_history = len(session.messages) > 1
-    system_prompt, _ = await _build_system_prompt(
-        user_id, has_conversation_history=has_history
-    )
-    system_prompt += _SDK_TOOL_SUPPLEMENT
-    message_id = str(uuid.uuid4())
-    task_id = str(uuid.uuid4())
-
-    yield StreamStart(messageId=message_id, taskId=task_id)
-
-    stream_completed = False
-    # Initialise sdk_cwd before the try so the finally can reference it
-    # even if _make_sdk_cwd raises (in that case it stays as "").
-    sdk_cwd = ""
-    use_resume = False
-
-    try:
-        # Use a session-specific temp dir to avoid cleanup race conditions
-        # between concurrent sessions.
-        sdk_cwd = _make_sdk_cwd(session_id)
-        os.makedirs(sdk_cwd, exist_ok=True)
-
-        set_execution_context(
-            user_id,
-            session,
-            long_running_callback=_build_long_running_callback(user_id),
-        )
-        try:
-            from claude_agent_sdk import ClaudeAgentOptions, ClaudeSDKClient
-
-            # Fail fast when no API credentials are available at all
-            sdk_env = _build_sdk_env()
-            if not sdk_env and not os.environ.get("ANTHROPIC_API_KEY"):
-                raise RuntimeError(
-                    "No API key configured. Set OPEN_ROUTER_API_KEY "
-                    "(or CHAT_API_KEY) for OpenRouter routing, "
-                    "or ANTHROPIC_API_KEY for direct Anthropic access."
-                )
-
-            mcp_server = create_copilot_mcp_server()
-
-            sdk_model = _resolve_sdk_model()
-
-            # --- Transcript capture via Stop hook ---
-            captured_transcript = CapturedTranscript()
-
-            def _on_stop(transcript_path: str, sdk_session_id: str) -> None:
-                captured_transcript.path = transcript_path
-                captured_transcript.sdk_session_id = sdk_session_id
-
-            security_hooks = create_security_hooks(
-                user_id,
-                sdk_cwd=sdk_cwd,
-                max_subtasks=config.claude_agent_max_subtasks,
-                on_stop=_on_stop if config.claude_agent_use_resume else None,
-            )
-
-            # --- Resume strategy: download transcript from bucket ---
-            resume_file: str | None = None
-            use_resume = False
-
-            if config.claude_agent_use_resume and user_id and len(session.messages) > 1:
-                transcript_content = await download_transcript(user_id, session_id)
-                if transcript_content and validate_transcript(transcript_content):
-                    resume_file = write_transcript_to_tempfile(
-                        transcript_content, session_id, sdk_cwd
-                    )
-                    if resume_file:
-                        use_resume = True
-                        logger.info(
-                            f"[SDK] Using --resume with transcript "
-                            f"({len(transcript_content)} bytes)"
-                        )
-
-            sdk_options_kwargs: dict[str, Any] = {
-                "system_prompt": system_prompt,
-                "mcp_servers": {"copilot": mcp_server},
-                "allowed_tools": COPILOT_TOOL_NAMES,
-                "disallowed_tools": SDK_DISALLOWED_TOOLS,
-                "hooks": security_hooks,
-                "cwd": sdk_cwd,
-                "max_buffer_size": config.claude_agent_max_buffer_size,
-            }
-            if sdk_env:
-                sdk_options_kwargs["model"] = sdk_model
-                sdk_options_kwargs["env"] = sdk_env
-            if use_resume and resume_file:
-                sdk_options_kwargs["resume"] = resume_file
-
-            options = ClaudeAgentOptions(**sdk_options_kwargs)  # type: ignore[arg-type]
-
-            adapter = SDKResponseAdapter(message_id=message_id)
-            adapter.set_task_id(task_id)
-
-            async with ClaudeSDKClient(options=options) as client:
-                current_message = message or ""
-                if not current_message and session.messages:
-                    last_user = [m for m in session.messages if m.role == "user"]
-                    if last_user:
-                        current_message = last_user[-1].content or ""
-
-                if not current_message.strip():
-                    yield StreamError(
-                        errorText="Message cannot be empty.",
-                        code="empty_prompt",
-                    )
-                    yield StreamFinish()
-                    return
-
-                # Build query: with --resume the CLI already has full
-                # context, so we only send the new message.  Without
-                # resume, compress history into a context prefix.
-                query_message = current_message
-                if not use_resume and len(session.messages) > 1:
-                    logger.warning(
-                        f"[SDK] Using compression fallback for session "
-                        f"{session_id} ({len(session.messages)} messages) — "
-                        f"no transcript available for --resume"
-                    )
-                    compressed = await _compress_conversation_history(session)
-                    history_context = _format_conversation_context(compressed)
-                    if history_context:
-                        query_message = (
-                            f"{history_context}\n\n"
-                            f"Now, the user says:\n{current_message}"
-                        )
-
-                logger.info(
-                    f"[SDK] Sending query ({len(session.messages)} msgs in session)"
-                )
-                logger.debug(f"[SDK] Query preview: {current_message[:80]!r}")
-                await client.query(query_message, session_id=session_id)
-
-                assistant_response = ChatMessage(role="assistant", content="")
-                accumulated_tool_calls: list[dict[str, Any]] = []
-                has_appended_assistant = False
-                has_tool_results = False
-
-                async for sdk_msg in client.receive_messages():
-                    logger.debug(
-                        f"[SDK] Received: {type(sdk_msg).__name__} "
-                        f"{getattr(sdk_msg, 'subtype', '')}"
-                    )
-                    for response in adapter.convert_message(sdk_msg):
-                        if isinstance(response, StreamStart):
-                            continue
-
-                        yield response
-
-                        if isinstance(response, StreamTextDelta):
-                            delta = response.delta or ""
-                            # After tool results, start a new assistant
-                            # message for the post-tool text.
-                            if has_tool_results and has_appended_assistant:
-                                assistant_response = ChatMessage(
-                                    role="assistant", content=delta
-                                )
-                                accumulated_tool_calls = []
-                                has_appended_assistant = False
-                                has_tool_results = False
-                                session.messages.append(assistant_response)
-                                has_appended_assistant = True
-                            else:
-                                assistant_response.content = (
-                                    assistant_response.content or ""
-                                ) + delta
-                                if not has_appended_assistant:
-                                    session.messages.append(assistant_response)
-                                    has_appended_assistant = True
-
-                        elif isinstance(response, StreamToolInputAvailable):
-                            accumulated_tool_calls.append(
-                                {
-                                    "id": response.toolCallId,
-                                    "type": "function",
-                                    "function": {
-                                        "name": response.toolName,
-                                        "arguments": json.dumps(response.input or {}),
-                                    },
-                                }
-                            )
-                            assistant_response.tool_calls = accumulated_tool_calls
-                            if not has_appended_assistant:
-                                session.messages.append(assistant_response)
-                                has_appended_assistant = True
-
-                        elif isinstance(response, StreamToolOutputAvailable):
-                            session.messages.append(
-                                ChatMessage(
-                                    role="tool",
-                                    content=(
-                                        response.output
-                                        if isinstance(response.output, str)
-                                        else str(response.output)
-                                    ),
-                                    tool_call_id=response.toolCallId,
-                                )
-                            )
-                            has_tool_results = True
-
-                        elif isinstance(response, StreamFinish):
-                            stream_completed = True
-
-                    if stream_completed:
-                        break
-
-                if (
-                    assistant_response.content or assistant_response.tool_calls
-                ) and not has_appended_assistant:
-                    session.messages.append(assistant_response)
-
-                # --- Capture transcript while CLI is still alive ---
-                # Must happen INSIDE async with: close() sends SIGTERM
-                # which kills the CLI before it can flush the JSONL.
-                if (
-                    config.claude_agent_use_resume
-                    and user_id
-                    and captured_transcript.available
-                ):
-                    # Give CLI time to flush JSONL writes before we read
-                    await asyncio.sleep(0.5)
-                    raw_transcript = read_transcript_file(captured_transcript.path)
-                    if raw_transcript:
-                        try:
-                            async with asyncio.timeout(30):
-                                await _upload_transcript_bg(
-                                    user_id, session_id, raw_transcript
-                                )
-                        except asyncio.TimeoutError:
-                            logger.warning(
-                                f"[SDK] Transcript upload timed out for {session_id}"
-                            )
-                    else:
-                        logger.debug("[SDK] Stop hook fired but transcript not usable")
-
-        except ImportError:
-            raise RuntimeError(
-                "claude-agent-sdk is not installed. "
-                "Disable SDK mode (CHAT_USE_CLAUDE_AGENT_SDK=false) "
-                "to use the OpenAI-compatible fallback."
-            )
-
-        await upsert_chat_session(session)
-        logger.debug(
-            f"[SDK] Session {session_id} saved with {len(session.messages)} messages"
-        )
-        if not stream_completed:
-            yield StreamFinish()
-
-    except Exception as e:
-        logger.error(f"[SDK] Error: {e}", exc_info=True)
-        try:
-            await upsert_chat_session(session)
-        except Exception as save_err:
-            logger.error(f"[SDK] Failed to save session on error: {save_err}")
-        yield StreamError(
-            errorText="An error occurred. Please try again.",
-            code="sdk_error",
-        )
-        yield StreamFinish()
-    finally:
-        if sdk_cwd:
-            _cleanup_sdk_tool_results(sdk_cwd)
-
-
-async def _upload_transcript_bg(
-    user_id: str, session_id: str, raw_content: str
-) -> None:
-    """Background task to strip progress entries and upload transcript."""
-    try:
-        await upload_transcript(user_id, session_id, raw_content)
-    except Exception as e:
-        logger.error(f"[SDK] Failed to upload transcript for {session_id}: {e}")
-
-
-async def _update_title_async(
-    session_id: str, message: str, user_id: str | None = None
-) -> None:
-    """Background task to update session title."""
-    try:
-        title = await _generate_session_title(
-            message, user_id=user_id, session_id=session_id
-        )
-        if title:
-            await update_session_title(session_id, title)
-            logger.debug(f"[SDK] Generated title for {session_id}: {title}")
-    except Exception as e:
-        logger.warning(f"[SDK] Failed to update session title: {e}")
--- a/autogpt_platform/backend/backend/copilot/sdk/tool_adapter.py
+++ b/autogpt_platform/backend/backend/copilot/sdk/tool_adapter.py
@@ -1,363 +0,0 @@
-"""Tool adapter for wrapping existing CoPilot tools as Claude Agent SDK MCP tools.
-
-This module provides the adapter layer that converts existing BaseTool implementations
-into in-process MCP tools that can be used with the Claude Agent SDK.
-
-Long-running tools (``is_long_running=True``) are delegated to the non-SDK
-background infrastructure (stream_registry, Redis persistence, SSE reconnection)
-via a callback provided by the service layer.  This avoids wasteful SDK polling
-and makes results survive page refreshes.
-"""
-
-import itertools
-import json
-import logging
-import os
-import uuid
-from collections.abc import Awaitable, Callable
-from contextvars import ContextVar
-from typing import Any
-
-from backend.copilot.model import ChatSession
-from backend.copilot.tools import TOOL_REGISTRY
-from backend.copilot.tools.base import BaseTool
-
-logger = logging.getLogger(__name__)
-
-# Allowed base directory for the Read tool (SDK saves oversized tool results here).
-# Restricted to ~/.claude/projects/ and further validated to require "tool-results"
-# in the path — prevents reading settings, credentials, or other sensitive files.
-_SDK_PROJECTS_DIR = os.path.expanduser("~/.claude/projects/")
-
-# MCP server naming - the SDK prefixes tool names as "mcp__{server_name}__{tool}"
-MCP_SERVER_NAME = "copilot"
-MCP_TOOL_PREFIX = f"mcp__{MCP_SERVER_NAME}__"
-
-# Context variables to pass user/session info to tool execution
-_current_user_id: ContextVar[str | None] = ContextVar("current_user_id", default=None)
-_current_session: ContextVar[ChatSession | None] = ContextVar(
-    "current_session", default=None
-)
-# Stash for MCP tool outputs before the SDK potentially truncates them.
-# Keyed by tool_name → full output string. Consumed (popped) by the
-# response adapter when it builds StreamToolOutputAvailable.
-_pending_tool_outputs: ContextVar[dict[str, str]] = ContextVar(
-    "pending_tool_outputs", default=None  # type: ignore[arg-type]
-)
-
-# Callback type for delegating long-running tools to the non-SDK infrastructure.
-# Args: (tool_name, arguments, session) → MCP-formatted response dict.
-LongRunningCallback = Callable[
-    [str, dict[str, Any], ChatSession], Awaitable[dict[str, Any]]
-]
-
-# ContextVar so the service layer can inject the callback per-request.
-_long_running_callback: ContextVar[LongRunningCallback | None] = ContextVar(
-    "long_running_callback", default=None
-)
-
-
-def set_execution_context(
-    user_id: str | None,
-    session: ChatSession,
-    long_running_callback: LongRunningCallback | None = None,
-) -> None:
-    """Set the execution context for tool calls.
-
-    This must be called before streaming begins to ensure tools have access
-    to user_id and session information.
-
-    Args:
-        user_id: Current user's ID.
-        session: Current chat session.
-        long_running_callback: Optional callback to delegate long-running tools
-            to the non-SDK background infrastructure (stream_registry + Redis).
-    """
-    _current_user_id.set(user_id)
-    _current_session.set(session)
-    _pending_tool_outputs.set({})
-    _long_running_callback.set(long_running_callback)
-
-
-def get_execution_context() -> tuple[str | None, ChatSession | None]:
-    """Get the current execution context."""
-    return (
-        _current_user_id.get(),
-        _current_session.get(),
-    )
-
-
-def pop_pending_tool_output(tool_name: str) -> str | None:
-    """Pop and return the stashed full output for *tool_name*.
-
-    The SDK CLI may truncate large tool results (writing them to disk and
-    replacing the content with a file reference). This stash keeps the
-    original MCP output so the response adapter can forward it to the
-    frontend for proper widget rendering.
-
-    Returns ``None`` if nothing was stashed for *tool_name*.
-    """
-    pending = _pending_tool_outputs.get(None)
-    if pending is None:
-        return None
-    return pending.pop(tool_name, None)
-
-
-async def _execute_tool_sync(
-    base_tool: BaseTool,
-    user_id: str | None,
-    session: ChatSession,
-    args: dict[str, Any],
-) -> dict[str, Any]:
-    """Execute a tool synchronously and return MCP-formatted response."""
-    effective_id = f"sdk-{uuid.uuid4().hex[:12]}"
-    result = await base_tool.execute(
-        user_id=user_id,
-        session=session,
-        tool_call_id=effective_id,
-        **args,
-    )
-
-    text = (
-        result.output if isinstance(result.output, str) else json.dumps(result.output)
-    )
-
-    # Stash the full output before the SDK potentially truncates it.
-    pending = _pending_tool_outputs.get(None)
-    if pending is not None:
-        pending[base_tool.name] = text
-
-    return {
-        "content": [{"type": "text", "text": text}],
-        "isError": not result.success,
-    }
-
-
-def _mcp_error(message: str) -> dict[str, Any]:
-    return {
-        "content": [
-            {"type": "text", "text": json.dumps({"error": message, "type": "error"})}
-        ],
-        "isError": True,
-    }
-
-
-def create_tool_handler(base_tool: BaseTool):
-    """Create an async handler function for a BaseTool.
-
-    This wraps the existing BaseTool._execute method to be compatible
-    with the Claude Agent SDK MCP tool format.
-
-    Long-running tools (``is_long_running=True``) are delegated to the
-    non-SDK background infrastructure via a callback set in the execution
-    context.  The callback persists the operation in Redis (stream_registry)
-    so results survive page refreshes and pod restarts.
-    """
-
-    async def tool_handler(args: dict[str, Any]) -> dict[str, Any]:
-        """Execute the wrapped tool and return MCP-formatted response."""
-        user_id, session = get_execution_context()
-
-        if session is None:
-            return _mcp_error("No session context available")
-
-        # --- Long-running: delegate to non-SDK background infrastructure ---
-        if base_tool.is_long_running:
-            callback = _long_running_callback.get(None)
-            if callback:
-                try:
-                    return await callback(base_tool.name, args, session)
-                except Exception as e:
-                    logger.error(
-                        f"Long-running callback failed for {base_tool.name}: {e}",
-                        exc_info=True,
-                    )
-                    return _mcp_error(f"Failed to start {base_tool.name}: {e}")
-            # No callback — fall through to synchronous execution
-            logger.warning(
-                f"[SDK] No long-running callback for {base_tool.name}, "
-                f"executing synchronously (may block)"
-            )
-
-        # --- Normal (fast) tool: execute synchronously ---
-        try:
-            return await _execute_tool_sync(base_tool, user_id, session, args)
-        except Exception as e:
-            logger.error(f"Error executing tool {base_tool.name}: {e}", exc_info=True)
-            return _mcp_error(f"Failed to execute {base_tool.name}: {e}")
-
-    return tool_handler
-
-
-def _build_input_schema(base_tool: BaseTool) -> dict[str, Any]:
-    """Build a JSON Schema input schema for a tool."""
-    return {
-        "type": "object",
-        "properties": base_tool.parameters.get("properties", {}),
-        "required": base_tool.parameters.get("required", []),
-    }
-
-
-async def _read_file_handler(args: dict[str, Any]) -> dict[str, Any]:
-    """Read a file with optional offset/limit. Restricted to SDK working directory.
-
-    After reading, the file is deleted to prevent accumulation in long-running pods.
-    """
-    file_path = args.get("file_path", "")
-    offset = args.get("offset", 0)
-    limit = args.get("limit", 2000)
-
-    # Security: only allow reads under ~/.claude/projects/**/tool-results/
-    real_path = os.path.realpath(file_path)
-    if not real_path.startswith(_SDK_PROJECTS_DIR) or "tool-results" not in real_path:
-        return {
-            "content": [{"type": "text", "text": f"Access denied: {file_path}"}],
-            "isError": True,
-        }
-
-    try:
-        with open(real_path) as f:
-            selected = list(itertools.islice(f, offset, offset + limit))
-        content = "".join(selected)
-        # Cleanup happens in _cleanup_sdk_tool_results after session ends;
-        # don't delete here — the SDK may read in multiple chunks.
-        return {"content": [{"type": "text", "text": content}], "isError": False}
-    except FileNotFoundError:
-        return {
-            "content": [{"type": "text", "text": f"File not found: {file_path}"}],
-            "isError": True,
-        }
-    except Exception as e:
-        return {
-            "content": [{"type": "text", "text": f"Error reading file: {e}"}],
-            "isError": True,
-        }
-
-
-_READ_TOOL_NAME = "Read"
-_READ_TOOL_DESCRIPTION = (
-    "Read a file from the local filesystem. "
-    "Use offset and limit to read specific line ranges for large files."
-)
-_READ_TOOL_SCHEMA = {
-    "type": "object",
-    "properties": {
-        "file_path": {
-            "type": "string",
-            "description": "The absolute path to the file to read",
-        },
-        "offset": {
-            "type": "integer",
-            "description": "Line number to start reading from (0-indexed). Default: 0",
-        },
-        "limit": {
-            "type": "integer",
-            "description": "Number of lines to read. Default: 2000",
-        },
-    },
-    "required": ["file_path"],
-}
-
-
-# Create the MCP server configuration
-def create_copilot_mcp_server():
-    """Create an in-process MCP server configuration for CoPilot tools.
-
-    This can be passed to ClaudeAgentOptions.mcp_servers.
-
-    Note: The actual SDK MCP server creation depends on the claude-agent-sdk
-    package being available. This function returns the configuration that
-    can be used with the SDK.
-    """
-    try:
-        from claude_agent_sdk import create_sdk_mcp_server, tool
-
-        # Create decorated tool functions
-        sdk_tools = []
-
-        for tool_name, base_tool in TOOL_REGISTRY.items():
-            handler = create_tool_handler(base_tool)
-            decorated = tool(
-                tool_name,
-                base_tool.description,
-                _build_input_schema(base_tool),
-            )(handler)
-            sdk_tools.append(decorated)
-
-        # Add the Read tool so the SDK can read back oversized tool results
-        read_tool = tool(
-            _READ_TOOL_NAME,
-            _READ_TOOL_DESCRIPTION,
-            _READ_TOOL_SCHEMA,
-        )(_read_file_handler)
-        sdk_tools.append(read_tool)
-
-        server = create_sdk_mcp_server(
-            name=MCP_SERVER_NAME,
-            version="1.0.0",
-            tools=sdk_tools,
-        )
-
-        return server
-
-    except ImportError:
-        # Let ImportError propagate so service.py handles the fallback
-        raise
-
-
-# SDK built-in tools allowed within the workspace directory.
-# Security hooks validate that file paths stay within sdk_cwd.
-# Bash is NOT included — use the sandboxed MCP bash_exec tool instead,
-# which provides kernel-level network isolation via unshare --net.
-# Task allows spawning sub-agents (rate-limited by security hooks).
-# WebSearch uses Brave Search via Anthropic's API — safe, no SSRF risk.
-_SDK_BUILTIN_TOOLS = ["Read", "Write", "Edit", "Glob", "Grep", "Task", "WebSearch"]
-
-# SDK built-in tools that must be explicitly blocked.
-# Bash: dangerous — agent uses mcp__copilot__bash_exec with kernel-level
-#   network isolation (unshare --net) instead.
-# WebFetch: SSRF risk — can reach internal network (localhost, 10.x, etc.).
-#   Agent uses the SSRF-protected mcp__copilot__web_fetch tool instead.
-SDK_DISALLOWED_TOOLS = ["Bash", "WebFetch"]
-
-# Tools that are blocked entirely in security hooks (defence-in-depth).
-# Includes SDK_DISALLOWED_TOOLS plus common aliases/synonyms.
-BLOCKED_TOOLS = {
-    *SDK_DISALLOWED_TOOLS,
-    "bash",
-    "shell",
-    "exec",
-    "terminal",
-    "command",
-}
-
-# Tools allowed only when their path argument stays within the SDK workspace.
-# The SDK uses these to handle oversized tool results (writes to tool-results/
-# files, then reads them back) and for workspace file operations.
-WORKSPACE_SCOPED_TOOLS = {"Read", "Write", "Edit", "Glob", "Grep"}
-
-# Dangerous patterns in tool inputs
-DANGEROUS_PATTERNS = [
-    r"sudo",
-    r"rm\s+-rf",
-    r"dd\s+if=",
-    r"/etc/passwd",
-    r"/etc/shadow",
-    r"chmod\s+777",
-    r"curl\s+.*\|.*sh",
-    r"wget\s+.*\|.*sh",
-    r"eval\s*\(",
-    r"exec\s*\(",
-    r"__import__",
-    r"os\.system",
-    r"subprocess",
-]
-
-# List of tool names for allowed_tools configuration
-# Include MCP tools, the MCP Read tool for oversized results,
-# and SDK built-in file tools for workspace operations.
-COPILOT_TOOL_NAMES = [
-    *[f"{MCP_TOOL_PREFIX}{name}" for name in TOOL_REGISTRY.keys()],
-    f"{MCP_TOOL_PREFIX}{_READ_TOOL_NAME}",
-    *_SDK_BUILTIN_TOOLS,
-]
--- a/autogpt_platform/backend/backend/copilot/sdk/transcript.py
+++ b/autogpt_platform/backend/backend/copilot/sdk/transcript.py
@@ -1,356 +0,0 @@
-"""JSONL transcript management for stateless multi-turn resume.
-
-The Claude Code CLI persists conversations as JSONL files (one JSON object per
-line).  When the SDK's ``Stop`` hook fires we read this file, strip bloat
-(progress entries, metadata), and upload the result to bucket storage.  On the
-next turn we download the transcript, write it to a temp file, and pass
-``--resume`` so the CLI can reconstruct the full conversation.
-
-Storage is handled via ``WorkspaceStorageBackend`` (GCS in prod, local
-filesystem for self-hosted) — no DB column needed.
-"""
-
-import json
-import logging
-import os
-import re
-
-logger = logging.getLogger(__name__)
-
-# UUIDs are hex + hyphens; strip everything else to prevent path injection.
-_SAFE_ID_RE = re.compile(r"[^0-9a-fA-F-]")
-
-# Entry types that can be safely removed from the transcript without breaking
-# the parentUuid conversation tree that ``--resume`` relies on.
-# - progress: UI progress ticks, no message content (avg 97KB for agent_progress)
-# - file-history-snapshot: undo tracking metadata
-# - queue-operation: internal queue bookkeeping
-# - summary: session summaries
-# - pr-link: PR link metadata
-STRIPPABLE_TYPES = frozenset(
-    {"progress", "file-history-snapshot", "queue-operation", "summary", "pr-link"}
-)
-
-# Workspace storage constants — deterministic path from session_id.
-TRANSCRIPT_STORAGE_PREFIX = "chat-transcripts"
-
-
-# ---------------------------------------------------------------------------
-# Progress stripping
-# ---------------------------------------------------------------------------
-
-
-def strip_progress_entries(content: str) -> str:
-    """Remove progress/metadata entries from a JSONL transcript.
-
-    Removes entries whose ``type`` is in ``STRIPPABLE_TYPES`` and reparents
-    any remaining child entries so the ``parentUuid`` chain stays intact.
-    Typically reduces transcript size by ~30%.
-    """
-    lines = content.strip().split("\n")
-
-    entries: list[dict] = []
-    for line in lines:
-        try:
-            entries.append(json.loads(line))
-        except json.JSONDecodeError:
-            # Keep unparseable lines as-is (safety)
-            entries.append({"_raw": line})
-
-    stripped_uuids: set[str] = set()
-    uuid_to_parent: dict[str, str] = {}
-    kept: list[dict] = []
-
-    for entry in entries:
-        if "_raw" in entry:
-            kept.append(entry)
-            continue
-        uid = entry.get("uuid", "")
-        parent = entry.get("parentUuid", "")
-        entry_type = entry.get("type", "")
-
-        if uid:
-            uuid_to_parent[uid] = parent
-
-        if entry_type in STRIPPABLE_TYPES:
-            if uid:
-                stripped_uuids.add(uid)
-        else:
-            kept.append(entry)
-
-    # Reparent: walk up chain through stripped entries to find surviving ancestor
-    for entry in kept:
-        if "_raw" in entry:
-            continue
-        parent = entry.get("parentUuid", "")
-        original_parent = parent
-        while parent in stripped_uuids:
-            parent = uuid_to_parent.get(parent, "")
-        if parent != original_parent:
-            entry["parentUuid"] = parent
-
-    result_lines: list[str] = []
-    for entry in kept:
-        if "_raw" in entry:
-            result_lines.append(entry["_raw"])
-        else:
-            result_lines.append(json.dumps(entry, separators=(",", ":")))
-
-    return "\n".join(result_lines) + "\n"
-
-
-# ---------------------------------------------------------------------------
-# Local file I/O (read from CLI's JSONL, write temp file for --resume)
-# ---------------------------------------------------------------------------
-
-
-def read_transcript_file(transcript_path: str) -> str | None:
-    """Read a JSONL transcript file from disk.
-
-    Returns the raw JSONL content, or ``None`` if the file is missing, empty,
-    or only contains metadata (≤2 lines with no conversation messages).
-    """
-    if not transcript_path or not os.path.isfile(transcript_path):
-        logger.debug(f"[Transcript] File not found: {transcript_path}")
-        return None
-
-    try:
-        with open(transcript_path) as f:
-            content = f.read()
-
-        if not content.strip():
-            logger.debug(f"[Transcript] Empty file: {transcript_path}")
-            return None
-
-        lines = content.strip().split("\n")
-        if len(lines) < 3:
-            # Raw files with ≤2 lines are metadata-only
-            # (queue-operation + file-history-snapshot, no conversation).
-            logger.debug(
-                f"[Transcript] Too few lines ({len(lines)}): {transcript_path}"
-            )
-            return None
-
-        # Quick structural validation — parse first and last lines.
-        json.loads(lines[0])
-        json.loads(lines[-1])
-
-        logger.info(
-            f"[Transcript] Read {len(lines)} lines, "
-            f"{len(content)} bytes from {transcript_path}"
-        )
-        return content
-
-    except (json.JSONDecodeError, OSError) as e:
-        logger.warning(f"[Transcript] Failed to read {transcript_path}: {e}")
-        return None
-
-
-def _sanitize_id(raw_id: str, max_len: int = 36) -> str:
-    """Sanitize an ID for safe use in file paths.
-
-    Session/user IDs are expected to be UUIDs (hex + hyphens).  Strip
-    everything else and truncate to *max_len* so the result cannot introduce
-    path separators or other special characters.
-    """
-    cleaned = _SAFE_ID_RE.sub("", raw_id or "")[:max_len]
-    return cleaned or "unknown"
-
-
-_SAFE_CWD_PREFIX = os.path.realpath("/tmp/copilot-")
-
-
-def write_transcript_to_tempfile(
-    transcript_content: str,
-    session_id: str,
-    cwd: str,
-) -> str | None:
-    """Write JSONL transcript to a temp file inside *cwd* for ``--resume``.
-
-    The file lives in the session working directory so it is cleaned up
-    automatically when the session ends.
-
-    Returns the absolute path to the file, or ``None`` on failure.
-    """
-    # Validate cwd is under the expected sandbox prefix (CodeQL sanitizer).
-    real_cwd = os.path.realpath(cwd)
-    if not real_cwd.startswith(_SAFE_CWD_PREFIX):
-        logger.warning(f"[Transcript] cwd outside sandbox: {cwd}")
-        return None
-
-    try:
-        os.makedirs(real_cwd, exist_ok=True)
-        safe_id = _sanitize_id(session_id, max_len=8)
-        jsonl_path = os.path.realpath(
-            os.path.join(real_cwd, f"transcript-{safe_id}.jsonl")
-        )
-        if not jsonl_path.startswith(real_cwd):
-            logger.warning(f"[Transcript] Path escaped cwd: {jsonl_path}")
-            return None
-
-        with open(jsonl_path, "w") as f:
-            f.write(transcript_content)
-
-        logger.info(f"[Transcript] Wrote resume file: {jsonl_path}")
-        return jsonl_path
-
-    except OSError as e:
-        logger.warning(f"[Transcript] Failed to write resume file: {e}")
-        return None
-
-
-def validate_transcript(content: str | None) -> bool:
-    """Check that a transcript has actual conversation messages.
-
-    A valid transcript for resume needs at least one user message and one
-    assistant message (not just queue-operation / file-history-snapshot
-    metadata).
-    """
-    if not content or not content.strip():
-        return False
-
-    lines = content.strip().split("\n")
-    if len(lines) < 2:
-        return False
-
-    has_user = False
-    has_assistant = False
-
-    for line in lines:
-        try:
-            entry = json.loads(line)
-            msg_type = entry.get("type")
-            if msg_type == "user":
-                has_user = True
-            elif msg_type == "assistant":
-                has_assistant = True
-        except json.JSONDecodeError:
-            return False
-
-    return has_user and has_assistant
-
-
-# ---------------------------------------------------------------------------
-# Bucket storage (GCS / local via WorkspaceStorageBackend)
-# ---------------------------------------------------------------------------
-
-
-def _storage_path_parts(user_id: str, session_id: str) -> tuple[str, str, str]:
-    """Return (workspace_id, file_id, filename) for a session's transcript.
-
-    Path structure: ``chat-transcripts/{user_id}/{session_id}.jsonl``
-    IDs are sanitized to hex+hyphen to prevent path traversal.
-    """
-    return (
-        TRANSCRIPT_STORAGE_PREFIX,
-        _sanitize_id(user_id),
-        f"{_sanitize_id(session_id)}.jsonl",
-    )
-
-
-def _build_storage_path(user_id: str, session_id: str, backend: object) -> str:
-    """Build the full storage path string that ``retrieve()`` expects.
-
-    ``store()`` returns a path like ``gcs://bucket/workspaces/...`` or
-    ``local://workspace_id/file_id/filename``.  Since we use deterministic
-    arguments we can reconstruct the same path for download/delete without
-    having stored the return value.
-    """
-    from backend.util.workspace_storage import GCSWorkspaceStorage
-
-    wid, fid, fname = _storage_path_parts(user_id, session_id)
-
-    if isinstance(backend, GCSWorkspaceStorage):
-        blob = f"workspaces/{wid}/{fid}/{fname}"
-        return f"gcs://{backend.bucket_name}/{blob}"
-    else:
-        # LocalWorkspaceStorage returns local://{relative_path}
-        return f"local://{wid}/{fid}/{fname}"
-
-
-async def upload_transcript(user_id: str, session_id: str, content: str) -> None:
-    """Strip progress entries and upload transcript to bucket storage.
-
-    Safety: only overwrites when the new (stripped) transcript is larger than
-    what is already stored.  Since JSONL is append-only, the latest transcript
-    is always the longest.  This prevents a slow/stale background task from
-    clobbering a newer upload from a concurrent turn.
-    """
-    from backend.util.workspace_storage import get_workspace_storage
-
-    stripped = strip_progress_entries(content)
-    if not validate_transcript(stripped):
-        logger.warning(
-            f"[Transcript] Skipping upload — stripped content is not a valid "
-            f"transcript for session {session_id}"
-        )
-        return
-
-    storage = await get_workspace_storage()
-    wid, fid, fname = _storage_path_parts(user_id, session_id)
-    encoded = stripped.encode("utf-8")
-    new_size = len(encoded)
-
-    # Check existing transcript size to avoid overwriting newer with older
-    path = _build_storage_path(user_id, session_id, storage)
-    try:
-        existing = await storage.retrieve(path)
-        if len(existing) >= new_size:
-            logger.info(
-                f"[Transcript] Skipping upload — existing transcript "
-                f"({len(existing)}B) >= new ({new_size}B) for session "
-                f"{session_id}"
-            )
-            return
-    except (FileNotFoundError, Exception):
-        pass  # No existing transcript or retrieval error — proceed with upload
-
-    await storage.store(
-        workspace_id=wid,
-        file_id=fid,
-        filename=fname,
-        content=encoded,
-    )
-    logger.info(
-        f"[Transcript] Uploaded {new_size} bytes "
-        f"(stripped from {len(content)}) for session {session_id}"
-    )
-
-
-async def download_transcript(user_id: str, session_id: str) -> str | None:
-    """Download transcript from bucket storage.
-
-    Returns the JSONL content string, or ``None`` if not found.
-    """
-    from backend.util.workspace_storage import get_workspace_storage
-
-    storage = await get_workspace_storage()
-    path = _build_storage_path(user_id, session_id, storage)
-
-    try:
-        data = await storage.retrieve(path)
-        content = data.decode("utf-8")
-        logger.info(
-            f"[Transcript] Downloaded {len(content)} bytes for session {session_id}"
-        )
-        return content
-    except FileNotFoundError:
-        logger.debug(f"[Transcript] No transcript in storage for {session_id}")
-        return None
-    except Exception as e:
-        logger.warning(f"[Transcript] Failed to download transcript: {e}")
-        return None
-
-
-async def delete_transcript(user_id: str, session_id: str) -> None:
-    """Delete transcript from bucket storage (e.g. after resume failure)."""
-    from backend.util.workspace_storage import get_workspace_storage
-
-    storage = await get_workspace_storage()
-    path = _build_storage_path(user_id, session_id, storage)
-
-    try:
-        await storage.delete(path)
-        logger.info(f"[Transcript] Deleted transcript for session {session_id}")
-    except Exception as e:
-        logger.warning(f"[Transcript] Failed to delete transcript: {e}")
--- a/autogpt_platform/backend/backend/copilot/sdk/transcript_test.py
+++ b/autogpt_platform/backend/backend/copilot/sdk/transcript_test.py
@@ -1,255 +0,0 @@
-"""Unit tests for JSONL transcript management utilities."""
-
-import json
-import os
-
-from .transcript import (
-    STRIPPABLE_TYPES,
-    read_transcript_file,
-    strip_progress_entries,
-    validate_transcript,
-    write_transcript_to_tempfile,
-)
-
-
-def _make_jsonl(*entries: dict) -> str:
-    return "\n".join(json.dumps(e) for e in entries) + "\n"
-
-
-# --- Fixtures ---
-
-
-METADATA_LINE = {"type": "queue-operation", "subtype": "create"}
-FILE_HISTORY = {"type": "file-history-snapshot", "files": []}
-USER_MSG = {"type": "user", "uuid": "u1", "message": {"role": "user", "content": "hi"}}
-ASST_MSG = {
-    "type": "assistant",
-    "uuid": "a1",
-    "parentUuid": "u1",
-    "message": {"role": "assistant", "content": "hello"},
-}
-PROGRESS_ENTRY = {
-    "type": "progress",
-    "uuid": "p1",
-    "parentUuid": "u1",
-    "data": {"type": "bash_progress", "stdout": "running..."},
-}
-
-VALID_TRANSCRIPT = _make_jsonl(METADATA_LINE, FILE_HISTORY, USER_MSG, ASST_MSG)
-
-
-# --- read_transcript_file ---
-
-
-class TestReadTranscriptFile:
-    def test_returns_content_for_valid_file(self, tmp_path):
-        path = tmp_path / "session.jsonl"
-        path.write_text(VALID_TRANSCRIPT)
-        result = read_transcript_file(str(path))
-        assert result is not None
-        assert "user" in result
-
-    def test_returns_none_for_missing_file(self):
-        assert read_transcript_file("/nonexistent/path.jsonl") is None
-
-    def test_returns_none_for_empty_path(self):
-        assert read_transcript_file("") is None
-
-    def test_returns_none_for_empty_file(self, tmp_path):
-        path = tmp_path / "empty.jsonl"
-        path.write_text("")
-        assert read_transcript_file(str(path)) is None
-
-    def test_returns_none_for_metadata_only(self, tmp_path):
-        content = _make_jsonl(METADATA_LINE, FILE_HISTORY)
-        path = tmp_path / "meta.jsonl"
-        path.write_text(content)
-        assert read_transcript_file(str(path)) is None
-
-    def test_returns_none_for_invalid_json(self, tmp_path):
-        path = tmp_path / "bad.jsonl"
-        path.write_text("not json\n{}\n{}\n")
-        assert read_transcript_file(str(path)) is None
-
-    def test_no_size_limit(self, tmp_path):
-        """Large files are accepted — bucket storage has no size limit."""
-        big_content = {"type": "user", "uuid": "u9", "data": "x" * 1_000_000}
-        content = _make_jsonl(METADATA_LINE, FILE_HISTORY, big_content, ASST_MSG)
-        path = tmp_path / "big.jsonl"
-        path.write_text(content)
-        result = read_transcript_file(str(path))
-        assert result is not None
-
-
-# --- write_transcript_to_tempfile ---
-
-
-class TestWriteTranscriptToTempfile:
-    """Tests use /tmp/copilot-* paths to satisfy the sandbox prefix check."""
-
-    def test_writes_file_and_returns_path(self):
-        cwd = "/tmp/copilot-test-write"
-        try:
-            result = write_transcript_to_tempfile(
-                VALID_TRANSCRIPT, "sess-1234-abcd", cwd
-            )
-            assert result is not None
-            assert os.path.isfile(result)
-            assert result.endswith(".jsonl")
-            with open(result) as f:
-                assert f.read() == VALID_TRANSCRIPT
-        finally:
-            import shutil
-
-            shutil.rmtree(cwd, ignore_errors=True)
-
-    def test_creates_parent_directory(self):
-        cwd = "/tmp/copilot-test-mkdir"
-        try:
-            result = write_transcript_to_tempfile(VALID_TRANSCRIPT, "sess-1234", cwd)
-            assert result is not None
-            assert os.path.isdir(cwd)
-        finally:
-            import shutil
-
-            shutil.rmtree(cwd, ignore_errors=True)
-
-    def test_uses_session_id_prefix(self):
-        cwd = "/tmp/copilot-test-prefix"
-        try:
-            result = write_transcript_to_tempfile(
-                VALID_TRANSCRIPT, "abcdef12-rest", cwd
-            )
-            assert result is not None
-            assert "abcdef12" in os.path.basename(result)
-        finally:
-            import shutil
-
-            shutil.rmtree(cwd, ignore_errors=True)
-
-    def test_rejects_cwd_outside_sandbox(self, tmp_path):
-        cwd = str(tmp_path / "not-copilot")
-        result = write_transcript_to_tempfile(VALID_TRANSCRIPT, "sess-1234", cwd)
-        assert result is None
-
-
-# --- validate_transcript ---
-
-
-class TestValidateTranscript:
-    def test_valid_transcript(self):
-        assert validate_transcript(VALID_TRANSCRIPT) is True
-
-    def test_none_content(self):
-        assert validate_transcript(None) is False
-
-    def test_empty_content(self):
-        assert validate_transcript("") is False
-
-    def test_metadata_only(self):
-        content = _make_jsonl(METADATA_LINE, FILE_HISTORY)
-        assert validate_transcript(content) is False
-
-    def test_user_only_no_assistant(self):
-        content = _make_jsonl(METADATA_LINE, FILE_HISTORY, USER_MSG)
-        assert validate_transcript(content) is False
-
-    def test_assistant_only_no_user(self):
-        content = _make_jsonl(METADATA_LINE, FILE_HISTORY, ASST_MSG)
-        assert validate_transcript(content) is False
-
-    def test_invalid_json_returns_false(self):
-        assert validate_transcript("not json\n{}\n{}\n") is False
-
-
-# --- strip_progress_entries ---
-
-
-class TestStripProgressEntries:
-    def test_strips_all_strippable_types(self):
-        """All STRIPPABLE_TYPES are removed from the output."""
-        entries = [
-            USER_MSG,
-            {"type": "progress", "uuid": "p1", "parentUuid": "u1"},
-            {"type": "file-history-snapshot", "files": []},
-            {"type": "queue-operation", "subtype": "create"},
-            {"type": "summary", "text": "..."},
-            {"type": "pr-link", "url": "..."},
-            ASST_MSG,
-        ]
-        result = strip_progress_entries(_make_jsonl(*entries))
-        result_types = {json.loads(line)["type"] for line in result.strip().split("\n")}
-        assert result_types == {"user", "assistant"}
-        for stype in STRIPPABLE_TYPES:
-            assert stype not in result_types
-
-    def test_reparents_children_of_stripped_entries(self):
-        """An assistant message whose parent is a progress entry gets reparented."""
-        progress = {
-            "type": "progress",
-            "uuid": "p1",
-            "parentUuid": "u1",
-            "data": {"type": "bash_progress"},
-        }
-        asst = {
-            "type": "assistant",
-            "uuid": "a1",
-            "parentUuid": "p1",  # Points to progress
-            "message": {"role": "assistant", "content": "done"},
-        }
-        content = _make_jsonl(USER_MSG, progress, asst)
-        result = strip_progress_entries(content)
-        lines = [json.loads(line) for line in result.strip().split("\n")]
-
-        asst_entry = next(e for e in lines if e["type"] == "assistant")
-        # Should be reparented to u1 (the user message)
-        assert asst_entry["parentUuid"] == "u1"
-
-    def test_reparents_through_chain(self):
-        """Reparenting walks through multiple stripped entries."""
-        p1 = {"type": "progress", "uuid": "p1", "parentUuid": "u1"}
-        p2 = {"type": "progress", "uuid": "p2", "parentUuid": "p1"}
-        p3 = {"type": "progress", "uuid": "p3", "parentUuid": "p2"}
-        asst = {
-            "type": "assistant",
-            "uuid": "a1",
-            "parentUuid": "p3",  # 3 levels deep
-            "message": {"role": "assistant", "content": "done"},
-        }
-        content = _make_jsonl(USER_MSG, p1, p2, p3, asst)
-        result = strip_progress_entries(content)
-        lines = [json.loads(line) for line in result.strip().split("\n")]
-
-        asst_entry = next(e for e in lines if e["type"] == "assistant")
-        assert asst_entry["parentUuid"] == "u1"
-
-    def test_preserves_non_strippable_entries(self):
-        """User, assistant, and system entries are preserved."""
-        system = {"type": "system", "uuid": "s1", "message": "prompt"}
-        content = _make_jsonl(system, USER_MSG, ASST_MSG)
-        result = strip_progress_entries(content)
-        result_types = [json.loads(line)["type"] for line in result.strip().split("\n")]
-        assert result_types == ["system", "user", "assistant"]
-
-    def test_empty_input(self):
-        result = strip_progress_entries("")
-        # Should return just a newline (empty content stripped)
-        assert result.strip() == ""
-
-    def test_no_strippable_entries(self):
-        """When there's nothing to strip, output matches input structure."""
-        content = _make_jsonl(USER_MSG, ASST_MSG)
-        result = strip_progress_entries(content)
-        result_lines = result.strip().split("\n")
-        assert len(result_lines) == 2
-
-    def test_handles_entries_without_uuid(self):
-        """Entries without uuid field are handled gracefully."""
-        no_uuid = {"type": "queue-operation", "subtype": "create"}
-        content = _make_jsonl(no_uuid, USER_MSG, ASST_MSG)
-        result = strip_progress_entries(content)
-        result_types = [json.loads(line)["type"] for line in result.strip().split("\n")]
-        # queue-operation is strippable
-        assert "queue-operation" not in result_types
-        assert "user" in result_types
-        assert "assistant" in result_types
--- a/autogpt_platform/backend/backend/copilot/service_test.py
+++ b/autogpt_platform/backend/backend/copilot/service_test.py
@@ -1,178 +0,0 @@
-import asyncio
-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,
-)
-from .sdk import service as sdk_service
-from .sdk.transcript import download_transcript
-
-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"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_sdk_resume_multi_turn(setup_test_user, test_user_id):
-    """Test that the SDK --resume path captures and uses transcripts across turns.
-
-    Turn 1: Send a message containing a unique keyword.
-    Turn 2: Ask the model to recall that keyword — proving the transcript was
-    persisted and restored via --resume.
-    """
-    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")
-
-    from .config import ChatConfig
-
-    cfg = ChatConfig()
-    if not cfg.claude_agent_use_resume:
-        return pytest.skip("CLAUDE_AGENT_USE_RESUME is not enabled, skipping test")
-
-    session = await create_chat_session(test_user_id)
-    session = await upsert_chat_session(session)
-
-    # --- Turn 1: send a message with a unique keyword ---
-    keyword = "ZEPHYR42"
-    turn1_msg = (
-        f"Please remember this special keyword: {keyword}. "
-        "Just confirm you've noted it, keep your response brief."
-    )
-    turn1_text = ""
-    turn1_errors: list[str] = []
-    turn1_ended = False
-
-    async for chunk in sdk_service.stream_chat_completion_sdk(
-        session.session_id,
-        turn1_msg,
-        user_id=test_user_id,
-    ):
-        if isinstance(chunk, StreamTextDelta):
-            turn1_text += chunk.delta
-        elif isinstance(chunk, StreamError):
-            turn1_errors.append(chunk.errorText)
-        elif isinstance(chunk, StreamFinish):
-            turn1_ended = True
-
-    assert turn1_ended, "Turn 1 did not finish"
-    assert not turn1_errors, f"Turn 1 errors: {turn1_errors}"
-    assert turn1_text, "Turn 1 produced no text"
-
-    # Wait for background upload task to complete (retry up to 5s)
-    transcript = None
-    for _ in range(10):
-        await asyncio.sleep(0.5)
-        transcript = await download_transcript(test_user_id, session.session_id)
-        if transcript:
-            break
-    assert transcript, (
-        "Transcript was not uploaded to bucket after turn 1 — "
-        "Stop hook may not have fired or transcript was too small"
-    )
-    logger.info(f"Turn 1 transcript uploaded: {len(transcript)} bytes")
-
-    # Reload session for turn 2
-    session = await get_chat_session(session.session_id, test_user_id)
-    assert session, "Session not found after turn 1"
-
-    # --- Turn 2: ask model to recall the keyword ---
-    turn2_msg = "What was the special keyword I asked you to remember?"
-    turn2_text = ""
-    turn2_errors: list[str] = []
-    turn2_ended = False
-
-    async for chunk in sdk_service.stream_chat_completion_sdk(
-        session.session_id,
-        turn2_msg,
-        user_id=test_user_id,
-        session=session,
-    ):
-        if isinstance(chunk, StreamTextDelta):
-            turn2_text += chunk.delta
-        elif isinstance(chunk, StreamError):
-            turn2_errors.append(chunk.errorText)
-        elif isinstance(chunk, StreamFinish):
-            turn2_ended = True
-
-    assert turn2_ended, "Turn 2 did not finish"
-    assert not turn2_errors, f"Turn 2 errors: {turn2_errors}"
-    assert turn2_text, "Turn 2 produced no text"
-    assert keyword in turn2_text, (
-        f"Model did not recall keyword '{keyword}' in turn 2. "
-        f"Response: {turn2_text[:200]}"
-    )
-    logger.info(f"Turn 2 recalled keyword successfully: {turn2_text[:100]}")
--- a/autogpt_platform/backend/backend/copilot/tools/bash_exec.py
+++ b/autogpt_platform/backend/backend/copilot/tools/bash_exec.py
@@ -1,124 +0,0 @@
-"""Bash execution tool — run shell commands in a bubblewrap sandbox.
-
-Full Bash scripting is allowed (loops, conditionals, pipes, functions, etc.).
-Safety comes from OS-level isolation (bubblewrap): only system dirs visible
-read-only, writable workspace only, clean env, no network.
-
-Requires bubblewrap (``bwrap``) — the tool is disabled when bwrap is not
-available (e.g. macOS development).
-"""
-
-import logging
-from typing import Any
-
-from backend.copilot.model import ChatSession
-
-from .base import BaseTool
-from .models import BashExecResponse, ErrorResponse, ToolResponseBase
-from .sandbox import get_workspace_dir, has_full_sandbox, run_sandboxed
-
-logger = logging.getLogger(__name__)
-
-
-class BashExecTool(BaseTool):
-    """Execute Bash commands in a bubblewrap sandbox."""
-
-    @property
-    def name(self) -> str:
-        return "bash_exec"
-
-    @property
-    def description(self) -> str:
-        if not has_full_sandbox():
-            return (
-                "Bash execution is DISABLED — bubblewrap sandbox is not "
-                "available on this platform. Do not call this tool."
-            )
-        return (
-            "Execute a Bash command or script in a bubblewrap sandbox. "
-            "Full Bash scripting is supported (loops, conditionals, pipes, "
-            "functions, etc.). "
-            "The sandbox shares the same working directory as the SDK Read/Write "
-            "tools — files created by either are accessible to both. "
-            "SECURITY: Only system directories (/usr, /bin, /lib, /etc) are "
-            "visible read-only, the per-session workspace is the only writable "
-            "path, environment variables are wiped (no secrets), all network "
-            "access is blocked at the kernel level, and resource limits are "
-            "enforced (max 64 processes, 512MB memory, 50MB file size). "
-            "Application code, configs, and other directories are NOT accessible. "
-            "To fetch web content, use the web_fetch tool instead. "
-            "Execution is killed after the timeout (default 30s, max 120s). "
-            "Returns stdout and stderr. "
-            "Useful for file manipulation, data processing with Unix tools "
-            "(grep, awk, sed, jq, etc.), and running shell scripts."
-        )
-
-    @property
-    def parameters(self) -> dict[str, Any]:
-        return {
-            "type": "object",
-            "properties": {
-                "command": {
-                    "type": "string",
-                    "description": "Bash command or script to execute.",
-                },
-                "timeout": {
-                    "type": "integer",
-                    "description": (
-                        "Max execution time in seconds (default 30, max 120)."
-                    ),
-                    "default": 30,
-                },
-            },
-            "required": ["command"],
-        }
-
-    @property
-    def requires_auth(self) -> bool:
-        return False
-
-    async def _execute(
-        self,
-        user_id: str | None,
-        session: ChatSession,
-        **kwargs: Any,
-    ) -> ToolResponseBase:
-        session_id = session.session_id if session else None
-
-        if not has_full_sandbox():
-            return ErrorResponse(
-                message="bash_exec requires bubblewrap sandbox (Linux only).",
-                error="sandbox_unavailable",
-                session_id=session_id,
-            )
-
-        command: str = (kwargs.get("command") or "").strip()
-        timeout: int = kwargs.get("timeout", 30)
-
-        if not command:
-            return ErrorResponse(
-                message="No command provided.",
-                error="empty_command",
-                session_id=session_id,
-            )
-
-        workspace = get_workspace_dir(session_id or "default")
-
-        stdout, stderr, exit_code, timed_out = await run_sandboxed(
-            command=["bash", "-c", command],
-            cwd=workspace,
-            timeout=timeout,
-        )
-
-        return BashExecResponse(
-            message=(
-                "Execution timed out"
-                if timed_out
-                else f"Command executed (exit {exit_code})"
-            ),
-            stdout=stdout,
-            stderr=stderr,
-            exit_code=exit_code,
-            timed_out=timed_out,
-            session_id=session_id,
-        )
--- a/autogpt_platform/backend/backend/copilot/tools/check_operation_status.py
+++ b/autogpt_platform/backend/backend/copilot/tools/check_operation_status.py
@@ -1,124 +0,0 @@
-"""CheckOperationStatusTool — query the status of a long-running operation."""
-
-import logging
-from typing import Any
-
-from backend.copilot.model import ChatSession
-
-from .base import BaseTool
-from .models import ErrorResponse, ResponseType, ToolResponseBase
-
-logger = logging.getLogger(__name__)
-
-
-class OperationStatusResponse(ToolResponseBase):
-    """Response for check_operation_status tool."""
-
-    type: ResponseType = ResponseType.OPERATION_STATUS
-    task_id: str
-    operation_id: str
-    status: str  # "running", "completed", "failed"
-    tool_name: str | None = None
-    message: str = ""
-
-
-class CheckOperationStatusTool(BaseTool):
-    """Check the status of a long-running operation (create_agent, edit_agent, etc.).
-
-    The CoPilot uses this tool to report back to the user whether an
-    operation that was started earlier has completed, failed, or is still
-    running.
-    """
-
-    @property
-    def name(self) -> str:
-        return "check_operation_status"
-
-    @property
-    def description(self) -> str:
-        return (
-            "Check the current status of a long-running operation such as "
-            "create_agent or edit_agent. Accepts either an operation_id or "
-            "task_id from a previous operation_started response. "
-            "Returns the current status: running, completed, or failed."
-        )
-
-    @property
-    def parameters(self) -> dict[str, Any]:
-        return {
-            "type": "object",
-            "properties": {
-                "operation_id": {
-                    "type": "string",
-                    "description": (
-                        "The operation_id from an operation_started response."
-                    ),
-                },
-                "task_id": {
-                    "type": "string",
-                    "description": (
-                        "The task_id from an operation_started response. "
-                        "Used as fallback if operation_id is not provided."
-                    ),
-                },
-            },
-            "required": [],
-        }
-
-    @property
-    def requires_auth(self) -> bool:
-        return False
-
-    async def _execute(
-        self,
-        user_id: str | None,
-        session: ChatSession,
-        **kwargs,
-    ) -> ToolResponseBase:
-        from backend.copilot import stream_registry
-
-        operation_id = (kwargs.get("operation_id") or "").strip()
-        task_id = (kwargs.get("task_id") or "").strip()
-
-        if not operation_id and not task_id:
-            return ErrorResponse(
-                message="Please provide an operation_id or task_id.",
-                error="missing_parameter",
-            )
-
-        task = None
-        if operation_id:
-            task = await stream_registry.find_task_by_operation_id(operation_id)
-        if task is None and task_id:
-            task = await stream_registry.get_task(task_id)
-
-        if task is None:
-            # Task not in Redis — it may have already expired (TTL).
-            # Check conversation history for the result instead.
-            return ErrorResponse(
-                message=(
-                    "Operation not found — it may have already completed and "
-                    "expired from the status tracker. Check the conversation "
-                    "history for the result."
-                ),
-                error="not_found",
-            )
-
-        status_messages = {
-            "running": (
-                f"The {task.tool_name or 'operation'} is still running. "
-                "Please wait for it to complete."
-            ),
-            "completed": (
-                f"The {task.tool_name or 'operation'} has completed successfully."
-            ),
-            "failed": f"The {task.tool_name or 'operation'} has failed.",
-        }
-
-        return OperationStatusResponse(
-            task_id=task.task_id,
-            operation_id=task.operation_id,
-            status=task.status,
-            tool_name=task.tool_name,
-            message=status_messages.get(task.status, f"Status: {task.status}"),
-        )
--- a/autogpt_platform/backend/backend/copilot/tools/feature_requests.py
+++ b/autogpt_platform/backend/backend/copilot/tools/feature_requests.py
@@ -1,462 +0,0 @@
-"""Feature request tools - search and create feature requests via Linear."""
-
-import logging
-from typing import Any
-
-from pydantic import SecretStr
-
-from backend.blocks.linear._api import LinearClient
-from backend.copilot.model import ChatSession
-from backend.data.db_accessors import user_db
-from backend.data.model import APIKeyCredentials
-from backend.util.settings import Settings
-
-from .base import BaseTool
-from .models import (
-    ErrorResponse,
-    FeatureRequestCreatedResponse,
-    FeatureRequestInfo,
-    FeatureRequestSearchResponse,
-    NoResultsResponse,
-    ToolResponseBase,
-)
-
-logger = logging.getLogger(__name__)
-
-MAX_SEARCH_RESULTS = 10
-
-# GraphQL queries/mutations
-SEARCH_ISSUES_QUERY = """
-query SearchFeatureRequests($term: String!, $filter: IssueFilter, $first: Int) {
-  searchIssues(term: $term, filter: $filter, first: $first) {
-    nodes {
-      id
-      identifier
-      title
-    }
-  }
-}
-"""
-
-CUSTOMER_UPSERT_MUTATION = """
-mutation CustomerUpsert($input: CustomerUpsertInput!) {
-  customerUpsert(input: $input) {
-    success
-    customer {
-      id
-      name
-      externalIds
-    }
-  }
-}
-"""
-
-ISSUE_CREATE_MUTATION = """
-mutation IssueCreate($input: IssueCreateInput!) {
-  issueCreate(input: $input) {
-    success
-    issue {
-      id
-      identifier
-      title
-      url
-    }
-  }
-}
-"""
-
-CUSTOMER_NEED_CREATE_MUTATION = """
-mutation CustomerNeedCreate($input: CustomerNeedCreateInput!) {
-  customerNeedCreate(input: $input) {
-    success
-    need {
-      id
-      body
-      customer {
-        id
-        name
-      }
-      issue {
-        id
-        identifier
-        title
-        url
-      }
-    }
-  }
-}
-"""
-
-
-_settings: Settings | None = None
-
-
-def _get_settings() -> Settings:
-    global _settings
-    if _settings is None:
-        _settings = Settings()
-    return _settings
-
-
-def _get_linear_config() -> tuple[LinearClient, str, str]:
-    """Return a configured Linear client, project ID, and team ID.
-
-    Raises RuntimeError if any required setting is missing.
-    """
-    secrets = _get_settings().secrets
-    if not secrets.copilot_linear_api_key:
-        raise RuntimeError("COPILOT_LINEAR_API_KEY is not configured")
-    if not secrets.linear_feature_request_project_id:
-        raise RuntimeError("LINEAR_FEATURE_REQUEST_PROJECT_ID is not configured")
-    if not secrets.linear_feature_request_team_id:
-        raise RuntimeError("LINEAR_FEATURE_REQUEST_TEAM_ID is not configured")
-
-    credentials = APIKeyCredentials(
-        id="system-linear",
-        provider="linear",
-        api_key=SecretStr(secrets.copilot_linear_api_key),
-        title="System Linear API Key",
-    )
-    client = LinearClient(credentials=credentials)
-    return (
-        client,
-        secrets.linear_feature_request_project_id,
-        secrets.linear_feature_request_team_id,
-    )
-
-
-class SearchFeatureRequestsTool(BaseTool):
-    """Tool for searching existing feature requests in Linear."""
-
-    @property
-    def name(self) -> str:
-        return "search_feature_requests"
-
-    @property
-    def description(self) -> str:
-        return (
-            "Search existing feature requests to check if a similar request "
-            "already exists before creating a new one. Returns matching feature "
-            "requests with their ID, title, and description."
-        )
-
-    @property
-    def parameters(self) -> dict[str, Any]:
-        return {
-            "type": "object",
-            "properties": {
-                "query": {
-                    "type": "string",
-                    "description": "Search term to find matching feature requests.",
-                },
-            },
-            "required": ["query"],
-        }
-
-    @property
-    def requires_auth(self) -> bool:
-        return True
-
-    async def _execute(
-        self,
-        user_id: str | None,
-        session: ChatSession,
-        **kwargs,
-    ) -> ToolResponseBase:
-        query = kwargs.get("query", "").strip()
-        session_id = session.session_id if session else None
-
-        if not query:
-            return ErrorResponse(
-                message="Please provide a search query.",
-                error="Missing query parameter",
-                session_id=session_id,
-            )
-
-        try:
-            client, project_id, _team_id = _get_linear_config()
-            data = await client.query(
-                SEARCH_ISSUES_QUERY,
-                {
-                    "term": query,
-                    "filter": {
-                        "project": {"id": {"eq": project_id}},
-                    },
-                    "first": MAX_SEARCH_RESULTS,
-                },
-            )
-
-            nodes = data.get("searchIssues", {}).get("nodes", [])
-
-            if not nodes:
-                return NoResultsResponse(
-                    message=f"No feature requests found matching '{query}'.",
-                    suggestions=[
-                        "Try different keywords",
-                        "Use broader search terms",
-                        "You can create a new feature request if none exists",
-                    ],
-                    session_id=session_id,
-                )
-
-            results = [
-                FeatureRequestInfo(
-                    id=node["id"],
-                    identifier=node["identifier"],
-                    title=node["title"],
-                )
-                for node in nodes
-            ]
-
-            return FeatureRequestSearchResponse(
-                message=f"Found {len(results)} feature request(s) matching '{query}'.",
-                results=results,
-                count=len(results),
-                query=query,
-                session_id=session_id,
-            )
-        except Exception as e:
-            logger.exception("Failed to search feature requests")
-            return ErrorResponse(
-                message="Failed to search feature requests.",
-                error=str(e),
-                session_id=session_id,
-            )
-
-
-class CreateFeatureRequestTool(BaseTool):
-    """Tool for creating feature requests (or adding needs to existing ones)."""
-
-    @property
-    def name(self) -> str:
-        return "create_feature_request"
-
-    @property
-    def description(self) -> str:
-        return (
-            "Create a new feature request or add a customer need to an existing one. "
-            "Always search first with search_feature_requests to avoid duplicates. "
-            "If a matching request exists, pass its ID as existing_issue_id to add "
-            "the user's need to it instead of creating a duplicate. "
-            "IMPORTANT: Never include personally identifiable information (PII) in "
-            "the title or description — no names, emails, phone numbers, company "
-            "names, or other identifying details. Write titles and descriptions in "
-            "generic, feature-focused language."
-        )
-
-    @property
-    def parameters(self) -> dict[str, Any]:
-        return {
-            "type": "object",
-            "properties": {
-                "title": {
-                    "type": "string",
-                    "description": (
-                        "Title for the feature request. Must be generic and "
-                        "feature-focused — do not include any user names, emails, "
-                        "company names, or other PII."
-                    ),
-                },
-                "description": {
-                    "type": "string",
-                    "description": (
-                        "Detailed description of what the user wants and why. "
-                        "Must not contain any personally identifiable information "
-                        "(PII) — describe the feature need generically without "
-                        "referencing specific users, companies, or contact details."
-                    ),
-                },
-                "existing_issue_id": {
-                    "type": "string",
-                    "description": (
-                        "If adding a need to an existing feature request, "
-                        "provide its Linear issue ID (from search results). "
-                        "Omit to create a new feature request."
-                    ),
-                },
-            },
-            "required": ["title", "description"],
-        }
-
-    @property
-    def requires_auth(self) -> bool:
-        return True
-
-    async def _find_or_create_customer(
-        self, client: LinearClient, user_id: str, name: str
-    ) -> dict:
-        """Find existing customer by user_id or create a new one via upsert.
-
-        Args:
-            client: Linear API client.
-            user_id: Stable external ID used to deduplicate customers.
-            name: Human-readable display name (e.g. the user's email).
-        """
-        data = await client.mutate(
-            CUSTOMER_UPSERT_MUTATION,
-            {
-                "input": {
-                    "name": name,
-                    "externalId": user_id,
-                },
-            },
-        )
-        result = data.get("customerUpsert", {})
-        if not result.get("success"):
-            raise RuntimeError(f"Failed to upsert customer: {data}")
-        return result["customer"]
-
-    async def _execute(
-        self,
-        user_id: str | None,
-        session: ChatSession,
-        **kwargs,
-    ) -> ToolResponseBase:
-        title = kwargs.get("title", "").strip()
-        description = kwargs.get("description", "").strip()
-        existing_issue_id = kwargs.get("existing_issue_id")
-        session_id = session.session_id if session else None
-
-        if not title or not description:
-            return ErrorResponse(
-                message="Both title and description are required.",
-                error="Missing required parameters",
-                session_id=session_id,
-            )
-
-        if not user_id:
-            return ErrorResponse(
-                message="Authentication required to create feature requests.",
-                error="Missing user_id",
-                session_id=session_id,
-            )
-
-        try:
-            client, project_id, team_id = _get_linear_config()
-        except Exception as e:
-            logger.exception("Failed to initialize Linear client")
-            return ErrorResponse(
-                message="Failed to create feature request.",
-                error=str(e),
-                session_id=session_id,
-            )
-
-        # Resolve a human-readable name (email) for the Linear customer record.
-        # Fall back to user_id if the lookup fails or returns None.
-        try:
-            customer_display_name = (
-                await user_db().get_user_email_by_id(user_id) or user_id
-            )
-        except Exception:
-            customer_display_name = user_id
-
-        # Step 1: Find or create customer for this user
-        try:
-            customer = await self._find_or_create_customer(
-                client, user_id, customer_display_name
-            )
-            customer_id = customer["id"]
-            customer_name = customer["name"]
-        except Exception as e:
-            logger.exception("Failed to upsert customer in Linear")
-            return ErrorResponse(
-                message="Failed to create feature request.",
-                error=str(e),
-                session_id=session_id,
-            )
-
-        # Step 2: Create or reuse issue
-        issue_id: str | None = None
-        issue_identifier: str | None = None
-        if existing_issue_id:
-            # Add need to existing issue - we still need the issue details for response
-            is_new_issue = False
-            issue_id = existing_issue_id
-        else:
-            # Create new issue in the feature requests project
-            try:
-                data = await client.mutate(
-                    ISSUE_CREATE_MUTATION,
-                    {
-                        "input": {
-                            "title": title,
-                            "description": description,
-                            "teamId": team_id,
-                            "projectId": project_id,
-                        },
-                    },
-                )
-                result = data.get("issueCreate", {})
-                if not result.get("success"):
-                    return ErrorResponse(
-                        message="Failed to create feature request issue.",
-                        error=str(data),
-                        session_id=session_id,
-                    )
-                issue = result["issue"]
-                issue_id = issue["id"]
-                issue_identifier = issue.get("identifier")
-            except Exception as e:
-                logger.exception("Failed to create feature request issue")
-                return ErrorResponse(
-                    message="Failed to create feature request.",
-                    error=str(e),
-                    session_id=session_id,
-                )
-            is_new_issue = True
-
-        # Step 3: Create customer need on the issue
-        try:
-            data = await client.mutate(
-                CUSTOMER_NEED_CREATE_MUTATION,
-                {
-                    "input": {
-                        "customerId": customer_id,
-                        "issueId": issue_id,
-                        "body": description,
-                        "priority": 0,
-                    },
-                },
-            )
-            need_result = data.get("customerNeedCreate", {})
-            if not need_result.get("success"):
-                orphaned = (
-                    {"issue_id": issue_id, "issue_identifier": issue_identifier}
-                    if is_new_issue
-                    else None
-                )
-                return ErrorResponse(
-                    message="Failed to attach customer need to the feature request.",
-                    error=str(data),
-                    details=orphaned,
-                    session_id=session_id,
-                )
-            need = need_result["need"]
-            issue_info = need["issue"]
-        except Exception as e:
-            logger.exception("Failed to create customer need")
-            orphaned = (
-                {"issue_id": issue_id, "issue_identifier": issue_identifier}
-                if is_new_issue
-                else None
-            )
-            return ErrorResponse(
-                message="Failed to attach customer need to the feature request.",
-                error=str(e),
-                details=orphaned,
-                session_id=session_id,
-            )
-
-        return FeatureRequestCreatedResponse(
-            message=(
-                f"{'Created new feature request' if is_new_issue else 'Added your request to existing feature request'}: "
-                f"{issue_info['title']}."
-            ),
-            issue_id=issue_info["id"],
-            issue_identifier=issue_info["identifier"],
-            issue_title=issue_info["title"],
-            issue_url=issue_info.get("url", ""),
-            is_new_issue=is_new_issue,
-            customer_name=customer_name,
-            session_id=session_id,
-        )
--- a/autogpt_platform/backend/backend/copilot/tools/feature_requests_test.py
+++ b/autogpt_platform/backend/backend/copilot/tools/feature_requests_test.py
@@ -1,610 +0,0 @@
-"""Tests for SearchFeatureRequestsTool and CreateFeatureRequestTool."""
-
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-from ._test_data import make_session
-from .feature_requests import CreateFeatureRequestTool, SearchFeatureRequestsTool
-from .models import (
-    ErrorResponse,
-    FeatureRequestCreatedResponse,
-    FeatureRequestSearchResponse,
-    NoResultsResponse,
-)
-
-_TEST_USER_ID = "test-user-feature-requests"
-_TEST_USER_EMAIL = "testuser@example.com"
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-
-_FAKE_PROJECT_ID = "test-project-id"
-_FAKE_TEAM_ID = "test-team-id"
-
-
-def _mock_linear_config(*, query_return=None, mutate_return=None):
-    """Return a patched _get_linear_config that yields a mock LinearClient."""
-    client = AsyncMock()
-    if query_return is not None:
-        client.query.return_value = query_return
-    if mutate_return is not None:
-        client.mutate.return_value = mutate_return
-    return (
-        patch(
-            "backend.copilot.tools.feature_requests._get_linear_config",
-            return_value=(client, _FAKE_PROJECT_ID, _FAKE_TEAM_ID),
-        ),
-        client,
-    )
-
-
-def _search_response(nodes: list[dict]) -> dict:
-    return {"searchIssues": {"nodes": nodes}}
-
-
-def _customer_upsert_response(
-    customer_id: str = "cust-1", name: str = _TEST_USER_EMAIL, success: bool = True
-) -> dict:
-    return {
-        "customerUpsert": {
-            "success": success,
-            "customer": {"id": customer_id, "name": name, "externalIds": [name]},
-        }
-    }
-
-
-def _issue_create_response(
-    issue_id: str = "issue-1",
-    identifier: str = "FR-1",
-    title: str = "New Feature",
-    success: bool = True,
-) -> dict:
-    return {
-        "issueCreate": {
-            "success": success,
-            "issue": {
-                "id": issue_id,
-                "identifier": identifier,
-                "title": title,
-                "url": f"https://linear.app/issue/{identifier}",
-            },
-        }
-    }
-
-
-def _need_create_response(
-    need_id: str = "need-1",
-    issue_id: str = "issue-1",
-    identifier: str = "FR-1",
-    title: str = "New Feature",
-    success: bool = True,
-) -> dict:
-    return {
-        "customerNeedCreate": {
-            "success": success,
-            "need": {
-                "id": need_id,
-                "body": "description",
-                "customer": {"id": "cust-1", "name": _TEST_USER_EMAIL},
-                "issue": {
-                    "id": issue_id,
-                    "identifier": identifier,
-                    "title": title,
-                    "url": f"https://linear.app/issue/{identifier}",
-                },
-            },
-        }
-    }
-
-
-# ===========================================================================
-# SearchFeatureRequestsTool
-# ===========================================================================
-
-
-class TestSearchFeatureRequestsTool:
-    """Tests for SearchFeatureRequestsTool._execute."""
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_successful_search(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        nodes = [
-            {
-                "id": "id-1",
-                "identifier": "FR-1",
-                "title": "Dark mode",
-            },
-            {
-                "id": "id-2",
-                "identifier": "FR-2",
-                "title": "Dark theme",
-            },
-        ]
-        patcher, _ = _mock_linear_config(query_return=_search_response(nodes))
-        with patcher:
-            tool = SearchFeatureRequestsTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID, session=session, query="dark mode"
-            )
-
-        assert isinstance(resp, FeatureRequestSearchResponse)
-        assert resp.count == 2
-        assert resp.results[0].id == "id-1"
-        assert resp.results[1].identifier == "FR-2"
-        assert resp.query == "dark mode"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_no_results(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, _ = _mock_linear_config(query_return=_search_response([]))
-        with patcher:
-            tool = SearchFeatureRequestsTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID, session=session, query="nonexistent"
-            )
-
-        assert isinstance(resp, NoResultsResponse)
-        assert "nonexistent" in resp.message
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_empty_query_returns_error(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        tool = SearchFeatureRequestsTool()
-        resp = await tool._execute(user_id=_TEST_USER_ID, session=session, query="   ")
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.error is not None
-        assert "query" in resp.error.lower()
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_missing_query_returns_error(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        tool = SearchFeatureRequestsTool()
-        resp = await tool._execute(user_id=_TEST_USER_ID, session=session)
-
-        assert isinstance(resp, ErrorResponse)
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_api_failure(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        client.query.side_effect = RuntimeError("Linear API down")
-        with patcher:
-            tool = SearchFeatureRequestsTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID, session=session, query="test"
-            )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.error is not None
-        assert "Linear API down" in resp.error
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_malformed_node_returns_error(self):
-        """A node missing required keys should be caught by the try/except."""
-        session = make_session(user_id=_TEST_USER_ID)
-        # Node missing 'identifier' key
-        bad_nodes = [{"id": "id-1", "title": "Missing identifier"}]
-        patcher, _ = _mock_linear_config(query_return=_search_response(bad_nodes))
-        with patcher:
-            tool = SearchFeatureRequestsTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID, session=session, query="test"
-            )
-
-        assert isinstance(resp, ErrorResponse)
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_linear_client_init_failure(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        with patch(
-            "backend.copilot.tools.feature_requests._get_linear_config",
-            side_effect=RuntimeError("No API key"),
-        ):
-            tool = SearchFeatureRequestsTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID, session=session, query="test"
-            )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.error is not None
-        assert "No API key" in resp.error
-
-
-# ===========================================================================
-# CreateFeatureRequestTool
-# ===========================================================================
-
-
-class TestCreateFeatureRequestTool:
-    """Tests for CreateFeatureRequestTool._execute."""
-
-    @pytest.fixture(autouse=True)
-    def _patch_email_lookup(self):
-        mock_user_db = MagicMock()
-        mock_user_db.get_user_email_by_id = AsyncMock(return_value=_TEST_USER_EMAIL)
-        with patch(
-            "backend.copilot.tools.feature_requests.user_db",
-            return_value=mock_user_db,
-        ):
-            yield
-
-    # ---- Happy paths -------------------------------------------------------
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_create_new_issue(self):
-        """Full happy path: upsert customer -> create issue -> attach need."""
-        session = make_session(user_id=_TEST_USER_ID)
-
-        patcher, client = _mock_linear_config()
-        client.mutate.side_effect = [
-            _customer_upsert_response(),
-            _issue_create_response(),
-            _need_create_response(),
-        ]
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="New Feature",
-                description="Please add this",
-            )
-
-        assert isinstance(resp, FeatureRequestCreatedResponse)
-        assert resp.is_new_issue is True
-        assert resp.issue_identifier == "FR-1"
-        assert resp.customer_name == _TEST_USER_EMAIL
-        assert client.mutate.call_count == 3
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_add_need_to_existing_issue(self):
-        """When existing_issue_id is provided, skip issue creation."""
-        session = make_session(user_id=_TEST_USER_ID)
-
-        patcher, client = _mock_linear_config()
-        client.mutate.side_effect = [
-            _customer_upsert_response(),
-            _need_create_response(issue_id="existing-1", identifier="FR-99"),
-        ]
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Existing Feature",
-                description="Me too",
-                existing_issue_id="existing-1",
-            )
-
-        assert isinstance(resp, FeatureRequestCreatedResponse)
-        assert resp.is_new_issue is False
-        assert resp.issue_id == "existing-1"
-        # Only 2 mutations: customer upsert + need create (no issue create)
-        assert client.mutate.call_count == 2
-
-    # ---- Validation errors -------------------------------------------------
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_missing_title(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        tool = CreateFeatureRequestTool()
-        resp = await tool._execute(
-            user_id=_TEST_USER_ID,
-            session=session,
-            title="",
-            description="some desc",
-        )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.error is not None
-        assert "required" in resp.error.lower()
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_missing_description(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        tool = CreateFeatureRequestTool()
-        resp = await tool._execute(
-            user_id=_TEST_USER_ID,
-            session=session,
-            title="Some title",
-            description="",
-        )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.error is not None
-        assert "required" in resp.error.lower()
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_missing_user_id(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        tool = CreateFeatureRequestTool()
-        resp = await tool._execute(
-            user_id=None,
-            session=session,
-            title="Some title",
-            description="Some desc",
-        )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.error is not None
-        assert "user_id" in resp.error.lower()
-
-    # ---- Linear client init failure ----------------------------------------
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_linear_client_init_failure(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        with patch(
-            "backend.copilot.tools.feature_requests._get_linear_config",
-            side_effect=RuntimeError("No API key"),
-        ):
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.error is not None
-        assert "No API key" in resp.error
-
-    # ---- Customer upsert failures ------------------------------------------
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_customer_upsert_api_error(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        client.mutate.side_effect = RuntimeError("Customer API error")
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.error is not None
-        assert "Customer API error" in resp.error
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_customer_upsert_not_success(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        client.mutate.return_value = _customer_upsert_response(success=False)
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_customer_malformed_response(self):
-        """Customer dict missing 'id' key should be caught."""
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        # success=True but customer has no 'id'
-        client.mutate.return_value = {
-            "customerUpsert": {
-                "success": True,
-                "customer": {"name": _TEST_USER_ID},
-            }
-        }
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-
-    # ---- Issue creation failures -------------------------------------------
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_issue_create_api_error(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        client.mutate.side_effect = [
-            _customer_upsert_response(),
-            RuntimeError("Issue create failed"),
-        ]
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.error is not None
-        assert "Issue create failed" in resp.error
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_issue_create_not_success(self):
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        client.mutate.side_effect = [
-            _customer_upsert_response(),
-            _issue_create_response(success=False),
-        ]
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-        assert "Failed to create feature request issue" in resp.message
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_issue_create_malformed_response(self):
-        """issueCreate success=True but missing 'issue' key."""
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        client.mutate.side_effect = [
-            _customer_upsert_response(),
-            {"issueCreate": {"success": True}},  # no 'issue' key
-        ]
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-
-    # ---- Customer need attachment failures ---------------------------------
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_need_create_api_error_new_issue(self):
-        """Need creation fails after new issue was created -> orphaned issue info."""
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        client.mutate.side_effect = [
-            _customer_upsert_response(),
-            _issue_create_response(issue_id="orphan-1", identifier="FR-10"),
-            RuntimeError("Need attach failed"),
-        ]
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.error is not None
-        assert "Need attach failed" in resp.error
-        assert resp.details is not None
-        assert resp.details["issue_id"] == "orphan-1"
-        assert resp.details["issue_identifier"] == "FR-10"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_need_create_api_error_existing_issue(self):
-        """Need creation fails on existing issue -> no orphaned info."""
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        client.mutate.side_effect = [
-            _customer_upsert_response(),
-            RuntimeError("Need attach failed"),
-        ]
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-                existing_issue_id="existing-1",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.details is None
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_need_create_not_success_includes_orphaned_info(self):
-        """customerNeedCreate returns success=False -> includes orphaned issue."""
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        client.mutate.side_effect = [
-            _customer_upsert_response(),
-            _issue_create_response(issue_id="orphan-2", identifier="FR-20"),
-            _need_create_response(success=False),
-        ]
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.details is not None
-        assert resp.details["issue_id"] == "orphan-2"
-        assert resp.details["issue_identifier"] == "FR-20"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_need_create_not_success_existing_issue_no_details(self):
-        """customerNeedCreate fails on existing issue -> no orphaned info."""
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        client.mutate.side_effect = [
-            _customer_upsert_response(),
-            _need_create_response(success=False),
-        ]
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-                existing_issue_id="existing-1",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.details is None
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_need_create_malformed_response(self):
-        """need_result missing 'need' key after success=True."""
-        session = make_session(user_id=_TEST_USER_ID)
-        patcher, client = _mock_linear_config()
-        client.mutate.side_effect = [
-            _customer_upsert_response(),
-            _issue_create_response(),
-            {"customerNeedCreate": {"success": True}},  # no 'need' key
-        ]
-
-        with patcher:
-            tool = CreateFeatureRequestTool()
-            resp = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                title="Title",
-                description="Desc",
-            )
-
-        assert isinstance(resp, ErrorResponse)
-        assert resp.details is not None
-        assert resp.details["issue_id"] == "issue-1"
--- a/Show More
+++ b/Show More