Merge branch 'dev' into ntindle/google-issues-fix

Resolved conflicts:
- executor/utils.py: kept auto-credentials validation + dev's comment update
- graph_test.py: kept both auto-credentials tests AND MCP deduplication tests

.claude/skills/pr-address/SKILL.md

@@ -1,79 +0,0 @@
----
-name: pr-address
-description: Address PR review comments and loop until CI green and all comments resolved. TRIGGER when user asks to address comments, fix PR feedback, respond to reviewers, or babysit/monitor a PR.
-user-invocable: true
-args: "[PR number or URL] — if omitted, finds PR for current branch."
-metadata:
-  author: autogpt-team
-  version: "1.0.0"
----
-
-# PR Address
-
-## Find the PR
-
-```bash
-gh pr list --head $(git branch --show-current) --repo Significant-Gravitas/AutoGPT
-gh pr view {N}
-```
-
-## Fetch comments (all sources)
-
-```bash
-gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/reviews       # top-level reviews
-gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/comments      # inline review comments
-gh api repos/Significant-Gravitas/AutoGPT/issues/{N}/comments     # PR conversation comments
-```
-
-**Bots to watch for:**
-- `autogpt-reviewer` — posts "Blockers", "Should Fix", "Nice to Have". Address ALL of them.
-- `sentry[bot]` — bug predictions. Fix real bugs, explain false positives.
-- `coderabbitai[bot]` — automated review. Address actionable items.
-
-## For each unaddressed comment
-
-Address comments **one at a time**: fix → commit → push → inline reply → next.
-
-1. Read the referenced code, make the fix (or reply explaining why it's not needed)
-2. Commit and push the fix
-3. Reply **inline** (not as a new top-level comment) referencing the fixing commit — this is what resolves the conversation for bot reviewers (coderabbitai, sentry):
-
-| Comment type | How to reply |
-|---|---|
-| Inline review (`pulls/{N}/comments`) | `gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/comments/{ID}/replies -f body="Fixed in <commit-sha>: <description>"` |
-| Conversation (`issues/{N}/comments`) | `gh api repos/Significant-Gravitas/AutoGPT/issues/{N}/comments -f body="Fixed in <commit-sha>: <description>"` |
-
-## Format and commit
-
-After fixing, format the changed code:
-
-- **Backend** (from `autogpt_platform/backend/`): `poetry run format`
-- **Frontend** (from `autogpt_platform/frontend/`): `pnpm format && pnpm lint && pnpm types`
-
-If API routes changed, regenerate the frontend client:
-```bash
-cd autogpt_platform/backend && poetry run rest &
-REST_PID=$!
-trap "kill $REST_PID 2>/dev/null" EXIT
-WAIT=0; until curl -sf http://localhost:8006/health > /dev/null 2>&1; do sleep 1; WAIT=$((WAIT+1)); [ $WAIT -ge 60 ] && echo "Timed out" && exit 1; done
-cd ../frontend && pnpm generate:api:force
-kill $REST_PID 2>/dev/null; trap - EXIT
-```
-Never manually edit files in `src/app/api/__generated__/`.
-
-Then commit and **push immediately** — never batch commits without pushing.
-
-For backend commits in worktrees: `poetry run git commit` (pre-commit hooks).
-
-## The loop
-
-```text
-address comments → format → commit → push
-→ re-check comments → fix new ones → push
-→ wait for CI → re-check comments after CI settles
-→ repeat until: all comments addressed AND CI green AND no new comments arriving
-```
-
-While CI runs, stay productive: run local tests, address remaining comments.
-
-**The loop ends when:** CI fully green + all comments addressed + no new comments since CI settled.

.claude/skills/pr-review/SKILL.md

@@ -1,74 +0,0 @@
----
-name: pr-review
-description: Review a PR for correctness, security, code quality, and testing issues. TRIGGER when user asks to review a PR, check PR quality, or give feedback on a PR.
-user-invocable: true
-args: "[PR number or URL] — if omitted, finds PR for current branch."
-metadata:
-  author: autogpt-team
-  version: "1.0.0"
----
-
-# PR Review
-
-## Find the PR
-
-```bash
-gh pr list --head $(git branch --show-current) --repo Significant-Gravitas/AutoGPT
-gh pr view {N}
-```
-
-## Read the diff
-
-```bash
-gh pr diff {N}
-```
-
-## Fetch existing review comments
-
-Before posting anything, fetch existing inline comments to avoid duplicates:
-
-```bash
-gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/comments
-gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/reviews
-```
-
-## What to check
-
-**Correctness:** logic errors, off-by-one, missing edge cases, race conditions (TOCTOU in file access, credit charging), error handling gaps, async correctness (missing `await`, unclosed resources).
-
-**Security:** input validation at boundaries, no injection (command, XSS, SQL), secrets not logged, file paths sanitized (`os.path.basename()` in error messages).
-
-**Code quality:** apply rules from backend/frontend CLAUDE.md files.
-
-**Architecture:** DRY, single responsibility, modular functions. `Security()` vs `Depends()` for FastAPI auth. `data:` for SSE events, `: comment` for heartbeats. `transaction=True` for Redis pipelines.
-
-**Testing:** edge cases covered, colocated `*_test.py` (backend) / `__tests__/` (frontend), mocks target where symbol is **used** not defined, `AsyncMock` for async.
-
-## Output format
-
-Every comment **must** be prefixed with `🤖` and a criticality badge:
-
-| Tier | Badge | Meaning |
-|---|---|---|
-| Blocker | `🔴 **Blocker**` | Must fix before merge |
-| Should Fix | `🟠 **Should Fix**` | Important improvement |
-| Nice to Have | `🟡 **Nice to Have**` | Minor suggestion |
-| Nit | `🔵 **Nit**` | Style / wording |
-
-Example: `🤖 🔴 **Blocker**: Missing error handling for X — suggest wrapping in try/except.`
-
-## Post inline comments
-
-For each finding, post an inline comment on the PR (do not just write a local report):
-
-```bash
-# Get the latest commit SHA for the PR
-COMMIT_SHA=$(gh api repos/Significant-Gravitas/AutoGPT/pulls/{N} --jq '.head.sha')
-
-# Post an inline comment on a specific file/line
-gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/comments \
-  -f body="🤖 🔴 **Blocker**: <description>" \
-  -f commit_id="$COMMIT_SHA" \
-  -f path="<file path>" \
-  -F line=<line number>
-```

.claude/skills/worktree/SKILL.md

@@ -1,85 +0,0 @@
----
-name: worktree
-description: Set up a new git worktree for parallel development. Creates the worktree, copies .env files, installs dependencies, and generates Prisma client. TRIGGER when user asks to set up a worktree, work on a branch in isolation, or needs a separate environment for a branch or PR.
-user-invocable: true
-args: "[name] — optional worktree name (e.g., 'AutoGPT7'). If omitted, uses next available AutoGPT<N>."
-metadata:
-  author: autogpt-team
-  version: "3.0.0"
----
-
-# Worktree Setup
-
-## Create the worktree
-
-Derive paths from the git toplevel. If a name is provided as argument, use it. Otherwise, check `git worktree list` and pick the next `AutoGPT<N>`.
-
-```bash
-ROOT=$(git rev-parse --show-toplevel)
-PARENT=$(dirname "$ROOT")
-
-# From an existing branch
-git worktree add "$PARENT/<NAME>" <branch-name>
-
-# From a new branch off dev
-git worktree add -b <new-branch> "$PARENT/<NAME>" dev
-```
-
-## Copy environment files
-
-Copy `.env` from the root worktree. Falls back to `.env.default` if `.env` doesn't exist.
-
-```bash
-ROOT=$(git rev-parse --show-toplevel)
-TARGET="$(dirname "$ROOT")/<NAME>"
-
-for envpath in autogpt_platform/backend autogpt_platform/frontend autogpt_platform; do
-  if [ -f "$ROOT/$envpath/.env" ]; then
-    cp "$ROOT/$envpath/.env" "$TARGET/$envpath/.env"
-  elif [ -f "$ROOT/$envpath/.env.default" ]; then
-    cp "$ROOT/$envpath/.env.default" "$TARGET/$envpath/.env"
-  fi
-done
-```
-
-## Install dependencies
-
-```bash
-TARGET="$(dirname "$(git rev-parse --show-toplevel)")/<NAME>"
-cd "$TARGET/autogpt_platform/autogpt_libs" && poetry install
-cd "$TARGET/autogpt_platform/backend" && poetry install && poetry run prisma generate
-cd "$TARGET/autogpt_platform/frontend" && pnpm install
-```
-
-Replace `<NAME>` with the actual worktree name (e.g., `AutoGPT7`).
-
-## Running the app (optional)
-
-Backend uses ports: 8001, 8002, 8003, 8005, 8006, 8007, 8008. Free them first if needed:
-
-```bash
-TARGET="$(dirname "$(git rev-parse --show-toplevel)")/<NAME>"
-for port in 8001 8002 8003 8005 8006 8007 8008; do
-  lsof -ti :$port | xargs kill -9 2>/dev/null || true
-done
-cd "$TARGET/autogpt_platform/backend" && poetry run app
-```
-
-## CoPilot testing
-
-SDK mode spawns a Claude subprocess — won't work inside Claude Code. Set `CHAT_USE_CLAUDE_AGENT_SDK=false` in `backend/.env` to use baseline mode.
-
-## Cleanup
-
-```bash
-# Replace <NAME> with the actual worktree name (e.g., AutoGPT7)
-git worktree remove "$(dirname "$(git rev-parse --show-toplevel)")/<NAME>"
-```
-
-## Alternative: Branchlet (optional)
-
-If [branchlet](https://www.npmjs.com/package/branchlet) is installed:
-
-```bash
-branchlet create -n <name> -s <source-branch> -b <new-branch>
-```

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

@@ -5,14 +5,12 @@ on:
     branches: [master, dev, ci-test*]
     paths:
       - ".github/workflows/platform-backend-ci.yml"
-      - ".github/workflows/scripts/get_package_version_from_lockfile.py"
       - "autogpt_platform/backend/**"
       - "autogpt_platform/autogpt_libs/**"
   pull_request:
     branches: [master, dev, release-*]
     paths:
       - ".github/workflows/platform-backend-ci.yml"
-      - ".github/workflows/scripts/get_package_version_from_lockfile.py"
       - "autogpt_platform/backend/**"
       - "autogpt_platform/autogpt_libs/**"
   merge_group:
@@ -43,18 +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:

.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:
 
@@ -120,6 +114,175 @@ jobs:
           token: ${{ secrets.GITHUB_TOKEN }}
           exitOnceUploaded: true
 
+  e2e_test:
+    name: end-to-end tests
+    runs-on: big-boi
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v6
+        with:
+          submodules: recursive
+
+      - name: Set up Platform - Copy default supabase .env
+        run: |
+          cp ../.env.default ../.env
+
+      - name: Set up Platform - Copy backend .env and set OpenAI API key
+        run: |
+          cp ../backend/.env.default ../backend/.env
+          echo "OPENAI_INTERNAL_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> ../backend/.env
+        env:
+          # Used by E2E test data script to generate embeddings for approved store agents
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+
+      - name: Set up Platform - Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          driver: docker-container
+          driver-opts: network=host
+
+      - name: Set up Platform - Expose GHA cache to docker buildx CLI
+        uses: crazy-max/ghaction-github-runtime@v3
+
+      - name: Set up Platform - Build Docker images (with cache)
+        working-directory: autogpt_platform
+        run: |
+          pip install pyyaml
+
+          # Resolve extends and generate a flat compose file that bake can understand
+          docker compose -f docker-compose.yml config > docker-compose.resolved.yml
+
+          # Add cache configuration to the resolved compose file
+          python ../.github/workflows/scripts/docker-ci-fix-compose-build-cache.py \
+            --source docker-compose.resolved.yml \
+            --cache-from "type=gha" \
+            --cache-to "type=gha,mode=max" \
+            --backend-hash "${{ 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
+        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') }}
+
+      - name: Set up Platform - Start Supabase DB + Auth
+        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"
+        env:
+          NEXT_PUBLIC_PW_TEST: true
+
+      - name: Set up tests - Load cached E2E test data
+        if: steps.e2e-data-cache.outputs.cache-hit == 'true'
+        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
+
+          echo "✅ E2E test data restored from cache"
+
+      - name: Set up Platform - Start (all other services)
+        run: |
+          docker compose -f ../docker-compose.resolved.yml up -d --no-build
+          echo "Waiting for rest_server to be ready..."
+          timeout 60 sh -c 'until curl -f http://localhost:8006/health 2>/dev/null; do sleep 2; done' || echo "Rest server health check timeout, continuing..."
+        env:
+          NEXT_PUBLIC_PW_TEST: true
+
+      - name: Set up tests - Create E2E test data
+        if: steps.e2e-data-cache.outputs.cache-hit != 'true'
+        run: |
+          echo "Creating E2E test data..."
+          docker cp ../backend/test/e2e_test_data.py $(docker compose -f ../docker-compose.resolved.yml ps -q rest_server):/tmp/e2e_test_data.py
+          docker compose -f ../docker-compose.resolved.yml exec -T rest_server sh -c "cd /app/autogpt_platform && python /tmp/e2e_test_data.py" || {
+            echo "❌ E2E test data creation failed!"
+            docker compose -f ../docker-compose.resolved.yml logs --tail=50 rest_server
+            exit 1
+          }
+
+          # Dump auth.users + platform schema for cache (two separate dumps)
+          echo "Dumping database for cache..."
+          {
+            docker compose -f ../docker-compose.resolved.yml exec -T db \
+              pg_dump -U postgres --data-only --column-inserts \
+              --table='auth.users' postgres
+            docker compose -f ../docker-compose.resolved.yml exec -T db \
+              pg_dump -U postgres --data-only --column-inserts \
+              --schema=platform \
+              --exclude-table='platform._prisma_migrations' \
+              --exclude-table='platform.apscheduler_jobs' \
+              --exclude-table='platform.apscheduler_jobs_batched_notifications' \
+              postgres
+          } > /tmp/e2e_test_data.sql
+
+          echo "✅ Database dump created for caching ($(wc -l < /tmp/e2e_test_data.sql) lines)"
+
+      - name: Set up tests - Enable corepack
+        run: corepack enable
+
+      - name: Set up tests - Set up Node
+        uses: actions/setup-node@v6
+        with:
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
+
+      - name: Set up tests - Install dependencies
+        run: pnpm install --frozen-lockfile
+
+      - name: Set up tests - Install browser 'chromium'
+        run: pnpm playwright install --with-deps chromium
+
+      - name: Run Playwright tests
+        run: pnpm test:no-build
+        continue-on-error: false
+
+      - name: Upload Playwright report
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: playwright-report
+          path: playwright-report
+          if-no-files-found: ignore
+          retention-days: 3
+
+      - name: Upload Playwright test results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: playwright-test-results
+          path: test-results
+          if-no-files-found: ignore
+          retention-days: 3
+
+      - name: Print Final Docker Compose logs
+        if: always()
+        run: docker compose -f ../docker-compose.resolved.yml logs
+
   integration_test:
     runs-on: ubuntu-latest
     needs: setup

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

@@ -1,18 +1,14 @@
-name: AutoGPT Platform - Full-stack CI
+name: AutoGPT Platform - Frontend CI
 
 on:
   push:
     branches: [master, dev]
     paths:
       - ".github/workflows/platform-fullstack-ci.yml"
-      - ".github/workflows/scripts/docker-ci-fix-compose-build-cache.py"
-      - ".github/workflows/scripts/get_package_version_from_lockfile.py"
       - "autogpt_platform/**"
   pull_request:
     paths:
       - ".github/workflows/platform-fullstack-ci.yml"
-      - ".github/workflows/scripts/docker-ci-fix-compose-build-cache.py"
-      - ".github/workflows/scripts/get_package_version_from_lockfile.py"
       - "autogpt_platform/**"
   merge_group:
 
@@ -28,28 +24,42 @@ defaults:
 jobs:
   setup:
     runs-on: ubuntu-latest
+    outputs:
+      cache-key: ${{ steps.cache-key.outputs.key }}
 
     steps:
       - 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: 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
 
-  check-api-types:
-    name: check API types
-    runs-on: ubuntu-latest
+  types:
+    runs-on: big-boi
     needs: setup
+    strategy:
+      fail-fast: false
 
     steps:
       - name: Checkout repository
@@ -57,256 +67,70 @@ jobs:
         with:
           submodules: recursive
 
-      # ------------------------ Backend setup ------------------------
-
-      - name: Set up Backend - Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
-      - name: Set up Backend - Install Poetry
-        working-directory: autogpt_platform/backend
-        run: |
-          POETRY_VERSION=$(python ../../.github/workflows/scripts/get_package_version_from_lockfile.py poetry)
-          echo "Installing Poetry version ${POETRY_VERSION}"
-          curl -sSL https://install.python-poetry.org | POETRY_VERSION=$POETRY_VERSION python3 -
-
-      - name: Set up Backend - Set up dependency cache
-        uses: actions/cache@v5
-        with:
-          path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
-
-      - name: Set up Backend - Install dependencies
-        working-directory: autogpt_platform/backend
-        run: poetry install
-
-      - name: Set up Backend - Generate Prisma client
-        working-directory: autogpt_platform/backend
-        run: poetry run prisma generate && poetry run gen-prisma-stub
-
-      - name: Set up Frontend - Export OpenAPI schema from Backend
-        working-directory: autogpt_platform/backend
-        run: poetry run export-api-schema --output ../frontend/src/app/api/openapi.json
-
-      # ------------------------ Frontend setup ------------------------
-
-      - name: Set up Frontend - Enable corepack
-        run: corepack enable
-
-      - name: Set up Frontend - 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: Set up Frontend - Install dependencies
+      - name: Enable corepack
+        run: corepack enable
+
+      - name: Copy default supabase .env
+        run: |
+          cp ../.env.default ../.env
+
+      - name: Copy backend .env
+        run: |
+          cp ../backend/.env.default ../backend/.env
+
+      - name: Run docker compose
+        run: |
+          docker compose -f ../docker-compose.yml --profile local up -d deps_backend
+
+      - name: Restore dependencies cache
+        uses: actions/cache@v5
+        with:
+          path: ~/.pnpm-store
+          key: ${{ needs.setup.outputs.cache-key }}
+          restore-keys: |
+            ${{ runner.os }}-pnpm-
+
+      - name: Install dependencies
         run: pnpm install --frozen-lockfile
 
-      - name: Set up Frontend - Format OpenAPI schema
-        id: format-schema
-        run: pnpm prettier --write ./src/app/api/openapi.json
+      - name: Setup .env
+        run: cp .env.default .env
+
+      - name: Wait for services to be ready
+        run: |
+          echo "Waiting for rest_server to be ready..."
+          timeout 60 sh -c 'until curl -f http://localhost:8006/health 2>/dev/null; do sleep 2; done' || echo "Rest server health check timeout, continuing..."
+          echo "Waiting for database to be ready..."
+          timeout 60 sh -c 'until docker compose -f ../docker-compose.yml exec -T db pg_isready -U postgres 2>/dev/null; do sleep 2; done' || echo "Database ready check timeout, continuing..."
+
+      - name: Generate API queries
+        run: pnpm generate:api:force
 
       - name: Check for API schema changes
         run: |
           if ! git diff --exit-code src/app/api/openapi.json; then
             echo "❌ API schema changes detected in src/app/api/openapi.json"
             echo ""
-            echo "The openapi.json file has been modified after exporting the API schema."
+            echo "The openapi.json file has been modified after running 'pnpm generate:api-all'."
             echo "This usually means changes have been made in the BE endpoints without updating the Frontend."
             echo "The API schema is now out of sync with the Front-end queries."
             echo ""
             echo "To fix this:"
-            echo "\nIn the backend directory:"
-            echo "1. Run 'poetry run export-api-schema --output ../frontend/src/app/api/openapi.json'"
-            echo "\nIn the frontend directory:"
-            echo "2. Run 'pnpm prettier --write src/app/api/openapi.json'"
-            echo "3. Run 'pnpm generate:api'"
-            echo "4. Run 'pnpm types'"
-            echo "5. Fix any TypeScript errors that may have been introduced"
-            echo "6. Commit and push your changes"
+            echo "1. Pull the backend 'docker compose pull && docker compose up -d --build --force-recreate'"
+            echo "2. Run 'pnpm generate:api' locally"
+            echo "3. Run 'pnpm types' locally"
+            echo "4. Fix any TypeScript errors that may have been introduced"
+            echo "5. Commit and push your changes"
             echo ""
             exit 1
           else
             echo "✅ No API schema changes detected"
           fi
 
-      - name: Set up Frontend - Generate API client
-        id: generate-api-client
-        run: pnpm orval --config ./orval.config.ts
-        # Continue with type generation & check even if there are schema changes
-        if: success() || (steps.format-schema.outcome == 'success')
-
-      - name: Check for TypeScript errors
+      - name: Run Typescript checks
         run: pnpm types
-        if: success() || (steps.generate-api-client.outcome == 'success')
-
-  e2e_test:
-    name: end-to-end tests
-    runs-on: big-boi
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v6
-        with:
-          submodules: recursive
-
-      - name: Set up Platform - Copy default supabase .env
-        run: |
-          cp ../.env.default ../.env
-
-      - name: Set up Platform - Copy backend .env and set OpenAI API key
-        run: |
-          cp ../backend/.env.default ../backend/.env
-          echo "OPENAI_INTERNAL_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> ../backend/.env
-        env:
-          # Used by E2E test data script to generate embeddings for approved store agents
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-
-      - name: Set up Platform - Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-        with:
-          driver: docker-container
-          driver-opts: network=host
-
-      - name: Set up Platform - Expose GHA cache to docker buildx CLI
-        uses: crazy-max/ghaction-github-runtime@v4
-
-      - name: Set up Platform - Build Docker images (with cache)
-        working-directory: autogpt_platform
-        run: |
-          pip install pyyaml
-
-          # Resolve extends and generate a flat compose file that bake can understand
-          docker compose -f docker-compose.yml config > docker-compose.resolved.yml
-
-          # Add cache configuration to the resolved compose file
-          python ../.github/workflows/scripts/docker-ci-fix-compose-build-cache.py \
-            --source docker-compose.resolved.yml \
-            --cache-from "type=gha" \
-            --cache-to "type=gha,mode=max" \
-            --backend-hash "${{ hashFiles('autogpt_platform/backend/Dockerfile', 'autogpt_platform/backend/poetry.lock', 'autogpt_platform/backend/backend/**') }}" \
-            --frontend-hash "${{ hashFiles('autogpt_platform/frontend/Dockerfile', 'autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/src/**') }}" \
-            --git-ref "${{ github.ref }}"
-
-          # Build with bake using the resolved compose file (now includes cache config)
-          docker buildx bake --allow=fs.read=.. -f docker-compose.resolved.yml --load
-        env:
-          NEXT_PUBLIC_PW_TEST: true
-
-      - name: Set up tests - Cache E2E test data
-        id: e2e-data-cache
-        uses: actions/cache@v5
-        with:
-          path: /tmp/e2e_test_data.sql
-          key: e2e-test-data-${{ hashFiles('autogpt_platform/backend/test/e2e_test_data.py', 'autogpt_platform/backend/migrations/**', '.github/workflows/platform-fullstack-ci.yml') }}
-
-      - name: Set up Platform - Start Supabase DB + Auth
-        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"
-        env:
-          NEXT_PUBLIC_PW_TEST: true
-
-      - name: Set up tests - Load cached E2E test data
-        if: steps.e2e-data-cache.outputs.cache-hit == 'true'
-        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
-
-          echo "✅ E2E test data restored from cache"
-
-      - name: Set up Platform - Start (all other services)
-        run: |
-          docker compose -f ../docker-compose.resolved.yml up -d --no-build
-          echo "Waiting for rest_server to be ready..."
-          timeout 60 sh -c 'until curl -f http://localhost:8006/health 2>/dev/null; do sleep 2; done' || echo "Rest server health check timeout, continuing..."
-        env:
-          NEXT_PUBLIC_PW_TEST: true
-
-      - name: Set up tests - Create E2E test data
-        if: steps.e2e-data-cache.outputs.cache-hit != 'true'
-        run: |
-          echo "Creating E2E test data..."
-          docker cp ../backend/test/e2e_test_data.py $(docker compose -f ../docker-compose.resolved.yml ps -q rest_server):/tmp/e2e_test_data.py
-          docker compose -f ../docker-compose.resolved.yml exec -T rest_server sh -c "cd /app/autogpt_platform && python /tmp/e2e_test_data.py" || {
-            echo "❌ E2E test data creation failed!"
-            docker compose -f ../docker-compose.resolved.yml logs --tail=50 rest_server
-            exit 1
-          }
-
-          # Dump auth.users + platform schema for cache (two separate dumps)
-          echo "Dumping database for cache..."
-          {
-            docker compose -f ../docker-compose.resolved.yml exec -T db \
-              pg_dump -U postgres --data-only --column-inserts \
-              --table='auth.users' postgres
-            docker compose -f ../docker-compose.resolved.yml exec -T db \
-              pg_dump -U postgres --data-only --column-inserts \
-              --schema=platform \
-              --exclude-table='platform._prisma_migrations' \
-              --exclude-table='platform.apscheduler_jobs' \
-              --exclude-table='platform.apscheduler_jobs_batched_notifications' \
-              postgres
-          } > /tmp/e2e_test_data.sql
-
-          echo "✅ Database dump created for caching ($(wc -l < /tmp/e2e_test_data.sql) lines)"
-
-      - name: Set up tests - Enable corepack
-        run: corepack enable
-
-      - name: Set up tests - Set up Node
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-          cache: "pnpm"
-          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
-
-      - name: Set up tests - Install dependencies
-        run: pnpm install --frozen-lockfile
-
-      - name: Set up tests - Install browser 'chromium'
-        run: pnpm playwright install --with-deps chromium
-
-      - name: Run Playwright tests
-        run: pnpm test:no-build
-        continue-on-error: false
-
-      - name: Upload Playwright report
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: playwright-report
-          path: playwright-report
-          if-no-files-found: ignore
-          retention-days: 3
-
-      - name: Upload Playwright test results
-        if: always()
-        uses: actions/upload-artifact@v4
-        with:
-          name: playwright-test-results
-          path: test-results
-          if-no-files-found: ignore
-          retention-days: 3
-
-      - name: Print Final Docker Compose logs
-        if: always()
-        run: docker compose -f ../docker-compose.resolved.yml logs

.gitignore

@@ -180,6 +180,4 @@ autogpt_platform/backend/settings.py
 .claude/settings.local.json
 CLAUDE.local.md
 /autogpt_platform/backend/logs
-.next
-# Implementation plans (generated by AI agents)
-plans/
+.next

.nvmrc

@@ -1 +0,0 @@
-22

.pre-commit-config.yaml

@@ -1,10 +1,3 @@
-default_install_hook_types:
-  - pre-commit
-  - pre-push
-  - post-checkout
-
-default_stages: [pre-commit]
-
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.4.0
@@ -24,7 +17,6 @@ repos:
         name: Detect secrets
         description: Detects high entropy strings that are likely to be passwords.
         files: ^autogpt_platform/
-        exclude: pnpm-lock\.yaml$
         stages: [pre-push]
 
   - repo: local
@@ -34,106 +26,49 @@ repos:
       - id: poetry-install
         name: Check & Install dependencies - AutoGPT Platform - Backend
         alias: poetry-install-platform-backend
+        entry: poetry -C autogpt_platform/backend install
         # include autogpt_libs source (since it's a path dependency)
-        entry: >
-          bash -c '
-          if [ -n "$PRE_COMMIT_FROM_REF" ]; then
-            git diff --name-only "$PRE_COMMIT_FROM_REF" "$PRE_COMMIT_TO_REF"
-          else
-            git diff --cached --name-only
-          fi | grep -qE "^autogpt_platform/(backend|autogpt_libs)/poetry\.lock$" || exit 0;
-          poetry -C autogpt_platform/backend install
-          '
-        always_run: true
+        files: ^autogpt_platform/(backend|autogpt_libs)/poetry\.lock$
+        types: [file]
         language: system
         pass_filenames: false
-        stages: [pre-commit, post-checkout]
 
       - id: poetry-install
         name: Check & Install dependencies - AutoGPT Platform - Libs
         alias: poetry-install-platform-libs
-        entry: >
-          bash -c '
-          if [ -n "$PRE_COMMIT_FROM_REF" ]; then
-            git diff --name-only "$PRE_COMMIT_FROM_REF" "$PRE_COMMIT_TO_REF"
-          else
-            git diff --cached --name-only
-          fi | grep -qE "^autogpt_platform/autogpt_libs/poetry\.lock$" || exit 0;
-          poetry -C autogpt_platform/autogpt_libs install
-          '
-        always_run: true
+        entry: poetry -C autogpt_platform/autogpt_libs install
+        files: ^autogpt_platform/autogpt_libs/poetry\.lock$
+        types: [file]
         language: system
         pass_filenames: false
-        stages: [pre-commit, post-checkout]
-
-      - id: pnpm-install
-        name: Check & Install dependencies - AutoGPT Platform - Frontend
-        alias: pnpm-install-platform-frontend
-        entry: >
-          bash -c '
-          if [ -n "$PRE_COMMIT_FROM_REF" ]; then
-            git diff --name-only "$PRE_COMMIT_FROM_REF" "$PRE_COMMIT_TO_REF"
-          else
-            git diff --cached --name-only
-          fi | grep -qE "^autogpt_platform/frontend/pnpm-lock\.yaml$" || exit 0;
-          pnpm --prefix autogpt_platform/frontend install
-          '
-        always_run: true
-        language: system
-        pass_filenames: false
-        stages: [pre-commit, post-checkout]
 
       - id: poetry-install
         name: Check & Install dependencies - Classic - AutoGPT
         alias: poetry-install-classic-autogpt
-        entry: >
-          bash -c '
-          if [ -n "$PRE_COMMIT_FROM_REF" ]; then
-            git diff --name-only "$PRE_COMMIT_FROM_REF" "$PRE_COMMIT_TO_REF"
-          else
-            git diff --cached --name-only
-          fi | grep -qE "^classic/(original_autogpt|forge)/poetry\.lock$" || exit 0;
-          poetry -C classic/original_autogpt install
-          '
+        entry: poetry -C classic/original_autogpt install
         # include forge source (since it's a path dependency)
-        always_run: true
+        files: ^classic/(original_autogpt|forge)/poetry\.lock$
+        types: [file]
         language: system
         pass_filenames: false
-        stages: [pre-commit, post-checkout]
 
       - id: poetry-install
         name: Check & Install dependencies - Classic - Forge
         alias: poetry-install-classic-forge
-        entry: >
-          bash -c '
-          if [ -n "$PRE_COMMIT_FROM_REF" ]; then
-            git diff --name-only "$PRE_COMMIT_FROM_REF" "$PRE_COMMIT_TO_REF"
-          else
-            git diff --cached --name-only
-          fi | grep -qE "^classic/forge/poetry\.lock$" || exit 0;
-          poetry -C classic/forge install
-          '
-        always_run: true
+        entry: poetry -C classic/forge install
+        files: ^classic/forge/poetry\.lock$
+        types: [file]
         language: system
         pass_filenames: false
-        stages: [pre-commit, post-checkout]
 
       - id: poetry-install
         name: Check & Install dependencies - Classic - Benchmark
         alias: poetry-install-classic-benchmark
-        entry: >
-          bash -c '
-          if [ -n "$PRE_COMMIT_FROM_REF" ]; then
-            git diff --name-only "$PRE_COMMIT_FROM_REF" "$PRE_COMMIT_TO_REF"
-          else
-            git diff --cached --name-only
-          fi | grep -qE "^classic/benchmark/poetry\.lock$" || exit 0;
-          poetry -C classic/benchmark install
-          '
-        always_run: true
+        entry: poetry -C classic/benchmark install
+        files: ^classic/benchmark/poetry\.lock$
+        types: [file]
         language: system
         pass_filenames: false
-        stages: [pre-commit, post-checkout]
 
   - repo: local
     # For proper type checking, Prisma client must be up-to-date.
@@ -141,54 +76,12 @@ repos:
       - id: prisma-generate
         name: Prisma Generate - AutoGPT Platform - Backend
         alias: prisma-generate-platform-backend
-        entry: >
-          bash -c '
-          if [ -n "$PRE_COMMIT_FROM_REF" ]; then
-            git diff --name-only "$PRE_COMMIT_FROM_REF" "$PRE_COMMIT_TO_REF"
-          else
-            git diff --cached --name-only
-          fi | grep -qE "^autogpt_platform/((backend|autogpt_libs)/poetry\.lock|backend/schema\.prisma)$" || exit 0;
-          cd autogpt_platform/backend
-          && poetry run prisma generate
-          && poetry run gen-prisma-stub
-          '
+        entry: bash -c 'cd autogpt_platform/backend && poetry run prisma generate'
         # include everything that triggers poetry install + the prisma schema
-        always_run: true
+        files: ^autogpt_platform/((backend|autogpt_libs)/poetry\.lock|backend/schema.prisma)$
+        types: [file]
         language: system
         pass_filenames: false
-        stages: [pre-commit, post-checkout]
-
-      - id: export-api-schema
-        name: Export API schema - AutoGPT Platform - Backend -> Frontend
-        alias: export-api-schema-platform
-        entry: >
-          bash -c '
-          cd autogpt_platform/backend
-          && poetry run export-api-schema --output ../frontend/src/app/api/openapi.json
-          && cd ../frontend
-          && pnpm prettier --write ./src/app/api/openapi.json
-          '
-        files: ^autogpt_platform/backend/
-        language: system
-        pass_filenames: false
-
-      - id: generate-api-client
-        name: Generate API client - AutoGPT Platform - Frontend
-        alias: generate-api-client-platform-frontend
-        entry: >
-          bash -c '
-          SCHEMA=autogpt_platform/frontend/src/app/api/openapi.json;
-          if [ -n "$PRE_COMMIT_FROM_REF" ]; then
-            git diff --quiet "$PRE_COMMIT_FROM_REF" "$PRE_COMMIT_TO_REF" -- "$SCHEMA" && exit 0
-          else
-            git diff --quiet HEAD -- "$SCHEMA" && exit 0
-          fi;
-          cd autogpt_platform/frontend && pnpm generate:api
-          '
-        always_run: true
-        language: system
-        pass_filenames: false
-        stages: [pre-commit, post-checkout]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.7.2

autogpt_platform/.gitignore

@@ -1,3 +1,2 @@
 *.ignore.*
-*.ign.*
-.application.logs
+*.ign.*

autogpt_platform/CLAUDE.md

@@ -60,12 +60,9 @@ AutoGPT Platform is a monorepo containing:
 
 ### Reviewing/Revising Pull Requests
 
-Use `/pr-review` to review a PR or `/pr-address` to address comments.
-
-When fetching comments manually:
-- `gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/reviews` — top-level reviews
-- `gh api repos/Significant-Gravitas/AutoGPT/pulls/{N}/comments` — inline review comments
-- `gh api repos/Significant-Gravitas/AutoGPT/issues/{N}/comments` — PR conversation comments
+- When the user runs /pr-comments or tries to fetch them, also run gh api /repos/Significant-Gravitas/AutoGPT/pulls/[issuenum]/reviews to get the reviews
+- Use gh api /repos/Significant-Gravitas/AutoGPT/pulls/[issuenum]/reviews/[review_id]/comments to get the review contents
+- Use gh api /repos/Significant-Gravitas/AutoGPT/issues/9924/comments to get the pr specific comments
 
 ### Conventional Commits
 

autogpt_platform/analytics/queries/auth_activities.sql

@@ -1,40 +0,0 @@
--- =============================================================
--- View: analytics.auth_activities
--- Looker source alias: ds49  |  Charts: 1
--- =============================================================
--- DESCRIPTION
---   Tracks authentication events (login, logout, SSO, password
---   reset, etc.) from Supabase's internal audit log.
---   Useful for monitoring sign-in patterns and detecting anomalies.
---
--- SOURCE TABLES
---   auth.audit_log_entries  — Supabase internal auth event log
---
--- OUTPUT COLUMNS
---   created_at      TIMESTAMPTZ  When the auth event occurred
---   actor_id        TEXT         User ID who triggered the event
---   actor_via_sso   TEXT         Whether the action was via SSO ('true'/'false')
---   action          TEXT         Event type (e.g. 'login', 'logout', 'token_refreshed')
---
--- WINDOW
---   Rolling 90 days from current date
---
--- EXAMPLE QUERIES
---   -- Daily login counts
---   SELECT DATE_TRUNC('day', created_at) AS day, COUNT(*) AS logins
---   FROM analytics.auth_activities
---   WHERE action = 'login'
---   GROUP BY 1 ORDER BY 1;
---
---   -- SSO vs password login breakdown
---   SELECT actor_via_sso, COUNT(*) FROM analytics.auth_activities
---   WHERE action = 'login' GROUP BY 1;
--- =============================================================
-
-SELECT
-    created_at,
-    payload->>'actor_id'      AS actor_id,
-    payload->>'actor_via_sso' AS actor_via_sso,
-    payload->>'action'        AS action
-FROM auth.audit_log_entries
-WHERE created_at >= NOW() - INTERVAL '90 days'

autogpt_platform/analytics/queries/graph_execution.sql

@@ -1,105 +0,0 @@
--- =============================================================
--- View: analytics.graph_execution
--- Looker source alias: ds16  |  Charts: 21
--- =============================================================
--- DESCRIPTION
---   One row per agent graph execution (last 90 days).
---   Unpacks the JSONB stats column into individual numeric columns
---   and normalises the executionStatus — runs that failed due to
---   insufficient credits are reclassified as 'NO_CREDITS' for
---   easier filtering.  Error messages are scrubbed of IDs and URLs
---   to allow safe grouping.
---
--- SOURCE TABLES
---   platform.AgentGraphExecution  — Execution records
---   platform.AgentGraph           — Agent graph metadata (for name)
---   platform.LibraryAgent         — To flag possibly-AI (safe-mode) agents
---
--- OUTPUT COLUMNS
---   id                TEXT         Execution UUID
---   agentGraphId      TEXT         Agent graph UUID
---   agentGraphVersion INT          Graph version number
---   executionStatus   TEXT         COMPLETED | FAILED | NO_CREDITS | RUNNING | QUEUED | TERMINATED
---   createdAt         TIMESTAMPTZ  When the execution was queued
---   updatedAt         TIMESTAMPTZ  Last status update time
---   userId            TEXT         Owner user UUID
---   agentGraphName    TEXT         Human-readable agent name
---   cputime           DECIMAL      Total CPU seconds consumed
---   walltime          DECIMAL      Total wall-clock seconds
---   node_count        DECIMAL      Number of nodes in the graph
---   nodes_cputime     DECIMAL      CPU time across all nodes
---   nodes_walltime    DECIMAL      Wall time across all nodes
---   execution_cost    DECIMAL      Credit cost of this execution
---   correctness_score FLOAT        AI correctness score (if available)
---   possibly_ai       BOOLEAN      True if agent has sensitive_action_safe_mode enabled
---   groupedErrorMessage TEXT       Scrubbed error string (IDs/URLs replaced with wildcards)
---
--- WINDOW
---   Rolling 90 days (createdAt > CURRENT_DATE - 90 days)
---
--- EXAMPLE QUERIES
---   -- Daily execution counts by status
---   SELECT DATE_TRUNC('day', "createdAt") AS day, "executionStatus", COUNT(*)
---   FROM analytics.graph_execution
---   GROUP BY 1, 2 ORDER BY 1;
---
---   -- Average cost per execution by agent
---   SELECT "agentGraphName", AVG("execution_cost") AS avg_cost, COUNT(*) AS runs
---   FROM analytics.graph_execution
---   WHERE "executionStatus" = 'COMPLETED'
---   GROUP BY 1 ORDER BY avg_cost DESC;
---
---   -- Top error messages
---   SELECT "groupedErrorMessage", COUNT(*) AS occurrences
---   FROM analytics.graph_execution
---   WHERE "executionStatus" = 'FAILED'
---   GROUP BY 1 ORDER BY 2 DESC LIMIT 20;
--- =============================================================
-
-SELECT
-    ge."id"                                                        AS id,
-    ge."agentGraphId"                                              AS agentGraphId,
-    ge."agentGraphVersion"                                         AS agentGraphVersion,
-    CASE
-        WHEN jsonb_exists(ge."stats"::jsonb, 'error')
-         AND (
-               (ge."stats"::jsonb->>'error') ILIKE '%insufficient balance%'
-            OR (ge."stats"::jsonb->>'error') ILIKE '%you have no credits left%'
-             )
-        THEN 'NO_CREDITS'
-        ELSE CAST(ge."executionStatus" AS TEXT)
-    END                                                            AS executionStatus,
-    ge."createdAt"                                                 AS createdAt,
-    ge."updatedAt"                                                 AS updatedAt,
-    ge."userId"                                                    AS userId,
-    g."name"                                                       AS agentGraphName,
-    (ge."stats"::jsonb->>'cputime')::decimal                       AS cputime,
-    (ge."stats"::jsonb->>'walltime')::decimal                      AS walltime,
-    (ge."stats"::jsonb->>'node_count')::decimal                    AS node_count,
-    (ge."stats"::jsonb->>'nodes_cputime')::decimal                 AS nodes_cputime,
-    (ge."stats"::jsonb->>'nodes_walltime')::decimal                AS nodes_walltime,
-    (ge."stats"::jsonb->>'cost')::decimal                          AS execution_cost,
-    (ge."stats"::jsonb->>'correctness_score')::float               AS correctness_score,
-    COALESCE(la.possibly_ai, FALSE)                                AS possibly_ai,
-    REGEXP_REPLACE(
-        REGEXP_REPLACE(
-            TRIM(BOTH '"' FROM ge."stats"::jsonb->>'error'),
-            '(https?://)([A-Za-z0-9.-]+)(:[0-9]+)?(/[^\s]*)?',
-            '\1\2/...', 'gi'
-        ),
-        '[a-zA-Z0-9_:-]*\d[a-zA-Z0-9_:-]*', '*', 'g'
-    )                                                              AS groupedErrorMessage
-FROM platform."AgentGraphExecution" ge
-LEFT JOIN platform."AgentGraph" g
-       ON ge."agentGraphId" = g."id"
-      AND ge."agentGraphVersion" = g."version"
-LEFT JOIN (
-    SELECT DISTINCT ON ("userId", "agentGraphId")
-           "userId", "agentGraphId",
-           ("settings"::jsonb->>'sensitive_action_safe_mode')::boolean AS possibly_ai
-    FROM platform."LibraryAgent"
-    WHERE "isDeleted"  = FALSE
-      AND "isArchived" = FALSE
-    ORDER BY "userId", "agentGraphId", "agentGraphVersion" DESC
-) la ON la."userId" = ge."userId" AND la."agentGraphId" = ge."agentGraphId"
-WHERE ge."createdAt" > CURRENT_DATE - INTERVAL '90 days'

autogpt_platform/analytics/queries/node_block_execution.sql

@@ -1,101 +0,0 @@
--- =============================================================
--- View: analytics.node_block_execution
--- Looker source alias: ds14  |  Charts: 11
--- =============================================================
--- DESCRIPTION
---   One row per node (block) execution (last 90 days).
---   Unpacks stats JSONB and joins to identify which block type
---   was run.  For failed nodes, joins the error output and
---   scrubs it for safe grouping.
---
--- SOURCE TABLES
---   platform.AgentNodeExecution              — Node execution records
---   platform.AgentNode                       — Node → block mapping
---   platform.AgentBlock                      — Block name/ID
---   platform.AgentNodeExecutionInputOutput   — Error output values
---
--- OUTPUT COLUMNS
---   id                    TEXT         Node execution UUID
---   agentGraphExecutionId TEXT         Parent graph execution UUID
---   agentNodeId           TEXT         Node UUID within the graph
---   executionStatus       TEXT         COMPLETED | FAILED | QUEUED | RUNNING | TERMINATED
---   addedTime             TIMESTAMPTZ  When the node was queued
---   queuedTime            TIMESTAMPTZ  When it entered the queue
---   startedTime           TIMESTAMPTZ  When execution started
---   endedTime             TIMESTAMPTZ  When execution finished
---   inputSize             BIGINT       Input payload size in bytes
---   outputSize            BIGINT       Output payload size in bytes
---   walltime              NUMERIC      Wall-clock seconds for this node
---   cputime               NUMERIC      CPU seconds for this node
---   llmRetryCount         INT          Number of LLM retries
---   llmCallCount          INT          Number of LLM API calls made
---   inputTokenCount       BIGINT       LLM input tokens consumed
---   outputTokenCount      BIGINT       LLM output tokens produced
---   blockName             TEXT         Human-readable block name (e.g. 'OpenAIBlock')
---   blockId               TEXT         Block UUID
---   groupedErrorMessage   TEXT         Scrubbed error (IDs/URLs wildcarded)
---   errorMessage          TEXT         Raw error output (only set when FAILED)
---
--- WINDOW
---   Rolling 90 days (addedTime > CURRENT_DATE - 90 days)
---
--- EXAMPLE QUERIES
---   -- Most-used blocks by execution count
---   SELECT "blockName", COUNT(*) AS executions,
---          COUNT(*) FILTER (WHERE "executionStatus"='FAILED') AS failures
---   FROM analytics.node_block_execution
---   GROUP BY 1 ORDER BY executions DESC LIMIT 20;
---
---   -- Average LLM token usage per block
---   SELECT "blockName",
---          AVG("inputTokenCount") AS avg_input_tokens,
---          AVG("outputTokenCount") AS avg_output_tokens
---   FROM analytics.node_block_execution
---   WHERE "llmCallCount" > 0
---   GROUP BY 1 ORDER BY avg_input_tokens DESC;
---
---   -- Top failure reasons
---   SELECT "blockName", "groupedErrorMessage", COUNT(*) AS count
---   FROM analytics.node_block_execution
---   WHERE "executionStatus" = 'FAILED'
---   GROUP BY 1, 2 ORDER BY count DESC LIMIT 20;
--- =============================================================
-
-SELECT
-    ne."id"                                                            AS id,
-    ne."agentGraphExecutionId"                                         AS agentGraphExecutionId,
-    ne."agentNodeId"                                                   AS agentNodeId,
-    CAST(ne."executionStatus" AS TEXT)                                 AS executionStatus,
-    ne."addedTime"                                                     AS addedTime,
-    ne."queuedTime"                                                    AS queuedTime,
-    ne."startedTime"                                                   AS startedTime,
-    ne."endedTime"                                                     AS endedTime,
-    (ne."stats"::jsonb->>'input_size')::bigint                         AS inputSize,
-    (ne."stats"::jsonb->>'output_size')::bigint                        AS outputSize,
-    (ne."stats"::jsonb->>'walltime')::numeric                          AS walltime,
-    (ne."stats"::jsonb->>'cputime')::numeric                           AS cputime,
-    (ne."stats"::jsonb->>'llm_retry_count')::int                       AS llmRetryCount,
-    (ne."stats"::jsonb->>'llm_call_count')::int                        AS llmCallCount,
-    (ne."stats"::jsonb->>'input_token_count')::bigint                  AS inputTokenCount,
-    (ne."stats"::jsonb->>'output_token_count')::bigint                 AS outputTokenCount,
-    b."name"                                                           AS blockName,
-    b."id"                                                             AS blockId,
-    REGEXP_REPLACE(
-        REGEXP_REPLACE(
-            TRIM(BOTH '"' FROM eio."data"::text),
-            '(https?://)([A-Za-z0-9.-]+)(:[0-9]+)?(/[^\s]*)?',
-            '\1\2/...', 'gi'
-        ),
-        '[a-zA-Z0-9_:-]*\d[a-zA-Z0-9_:-]*', '*', 'g'
-    )                                                                  AS groupedErrorMessage,
-    eio."data"                                                         AS errorMessage
-FROM platform."AgentNodeExecution" ne
-LEFT JOIN platform."AgentNode" nd
-       ON ne."agentNodeId" = nd."id"
-LEFT JOIN platform."AgentBlock" b
-       ON nd."agentBlockId" = b."id"
-LEFT JOIN platform."AgentNodeExecutionInputOutput" eio
-       ON eio."referencedByOutputExecId" = ne."id"
-      AND eio."name" = 'error'
-      AND ne."executionStatus" = 'FAILED'
-WHERE ne."addedTime" > CURRENT_DATE - INTERVAL '90 days'

autogpt_platform/analytics/queries/retention_agent.sql

@@ -1,97 +0,0 @@
--- =============================================================
--- View: analytics.retention_agent
--- Looker source alias: ds35  |  Charts: 2
--- =============================================================
--- DESCRIPTION
---   Weekly cohort retention broken down per individual agent.
---   Cohort = week of a user's first use of THAT specific agent.
---   Tells you which agents keep users coming back vs. one-shot
---   use. Only includes cohorts from the last 180 days.
---
--- SOURCE TABLES
---   platform.AgentGraphExecution  — Execution records (user × agent × time)
---   platform.AgentGraph           — Agent names
---
--- OUTPUT COLUMNS
---   agent_id            TEXT   Agent graph UUID
---   agent_label         TEXT   'AgentName [first8chars]'
---   agent_label_n       TEXT   'AgentName [first8chars] (n=total_users)'
---   cohort_week_start   DATE   Week users first ran this agent
---   cohort_label        TEXT   ISO week label
---   cohort_label_n      TEXT   ISO week label with cohort size
---   user_lifetime_week  INT    Weeks since first use of this agent
---   cohort_users        BIGINT Users in this cohort for this agent
---   active_users        BIGINT Users who ran the agent again in week k
---   retention_rate      FLOAT  active_users / cohort_users
---   cohort_users_w0     BIGINT cohort_users only at week 0 (safe to SUM)
---   agent_total_users   BIGINT Total users across all cohorts for this agent
---
--- EXAMPLE QUERIES
---   -- Best-retained agents at week 2
---   SELECT agent_label, AVG(retention_rate) AS w2_retention
---   FROM analytics.retention_agent
---   WHERE user_lifetime_week = 2 AND cohort_users >= 10
---   GROUP BY 1 ORDER BY w2_retention DESC LIMIT 10;
---
---   -- Agents with most unique users
---   SELECT DISTINCT agent_label, agent_total_users
---   FROM analytics.retention_agent
---   ORDER BY agent_total_users DESC LIMIT 20;
--- =============================================================
-
-WITH params AS (SELECT 12::int AS max_weeks, (CURRENT_DATE - INTERVAL '180 days') AS cohort_start),
-events AS (
-  SELECT e."userId"::text AS user_id, e."agentGraphId" AS agent_id,
-         e."createdAt"::timestamptz AS created_at,
-         DATE_TRUNC('week', e."createdAt")::date AS week_start
-  FROM platform."AgentGraphExecution" e
-),
-first_use AS (
-  SELECT user_id, agent_id, MIN(created_at) AS first_use_at,
-         DATE_TRUNC('week', MIN(created_at))::date AS cohort_week_start
-  FROM events GROUP BY 1,2
-  HAVING MIN(created_at) >= (SELECT cohort_start FROM params)
-),
-activity_weeks AS (SELECT DISTINCT user_id, agent_id, week_start FROM events),
-user_week_age AS (
-  SELECT aw.user_id, aw.agent_id, fu.cohort_week_start,
-         ((aw.week_start - DATE_TRUNC('week',fu.first_use_at)::date)/7)::int AS user_lifetime_week
-  FROM activity_weeks aw JOIN first_use fu USING (user_id, agent_id)
-  WHERE aw.week_start >= DATE_TRUNC('week',fu.first_use_at)::date
-),
-active_counts AS (
-  SELECT agent_id, cohort_week_start, user_lifetime_week, COUNT(DISTINCT user_id) AS active_users
-  FROM user_week_age WHERE user_lifetime_week >= 0 GROUP BY 1,2,3
-),
-cohort_sizes AS (
-  SELECT agent_id, cohort_week_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_use GROUP BY 1,2
-),
-cohort_caps AS (
-  SELECT cs.agent_id, cs.cohort_week_start, cs.cohort_users,
-         LEAST((SELECT max_weeks FROM params),
-               GREATEST(0,((DATE_TRUNC('week',CURRENT_DATE)::date-cs.cohort_week_start)/7)::int)) AS cap_weeks
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.agent_id, cc.cohort_week_start, gs AS user_lifetime_week, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_weeks) gs
-),
-agent_names AS (SELECT DISTINCT ON (g."id") g."id" AS agent_id, g."name" AS agent_name FROM platform."AgentGraph" g ORDER BY g."id", g."version" DESC),
-agent_total_users AS (SELECT agent_id, SUM(cohort_users) AS agent_total_users FROM cohort_sizes GROUP BY 1)
-SELECT
-  g.agent_id,
-  COALESCE(an.agent_name,'(unnamed)')||' ['||LEFT(g.agent_id::text,8)||']'  AS agent_label,
-  COALESCE(an.agent_name,'(unnamed)')||' ['||LEFT(g.agent_id::text,8)||'] (n='||COALESCE(atu.agent_total_users,0)||')' AS agent_label_n,
-  g.cohort_week_start,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')                               AS cohort_label,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')||' (n='||g.cohort_users||')'  AS cohort_label_n,
-  g.user_lifetime_week, g.cohort_users,
-  COALESCE(ac.active_users,0)                                              AS active_users,
-  COALESCE(ac.active_users,0)::float / NULLIF(g.cohort_users,0)           AS retention_rate,
-  CASE WHEN g.user_lifetime_week=0 THEN g.cohort_users ELSE 0 END         AS cohort_users_w0,
-  COALESCE(atu.agent_total_users,0)                                        AS agent_total_users
-FROM grid g
-LEFT JOIN active_counts     ac  ON ac.agent_id=g.agent_id AND ac.cohort_week_start=g.cohort_week_start AND ac.user_lifetime_week=g.user_lifetime_week
-LEFT JOIN agent_names       an  ON an.agent_id=g.agent_id
-LEFT JOIN agent_total_users atu ON atu.agent_id=g.agent_id
-ORDER BY agent_label, g.cohort_week_start, g.user_lifetime_week;

autogpt_platform/analytics/queries/retention_execution_daily.sql

@@ -1,81 +0,0 @@
--- =============================================================
--- View: analytics.retention_execution_daily
--- Looker source alias: ds111  |  Charts: 1
--- =============================================================
--- DESCRIPTION
---   Daily cohort retention based on agent executions.
---   Cohort anchor = day of user's FIRST ever execution.
---   Only includes cohorts from the last 90 days, up to day 30.
---   Great for early engagement analysis (did users run another
---   agent the next day?).
---
--- SOURCE TABLES
---   platform.AgentGraphExecution  — Execution records
---
--- OUTPUT COLUMNS
---   Same pattern as retention_login_daily.
---   cohort_day_start = day of first execution (not first login)
---
--- EXAMPLE QUERIES
---   -- Day-3 execution retention
---   SELECT cohort_label, retention_rate_bounded AS d3_retention
---   FROM analytics.retention_execution_daily
---   WHERE user_lifetime_day = 3 ORDER BY cohort_day_start;
--- =============================================================
-
-WITH params AS (SELECT 30::int AS max_days, (CURRENT_DATE - INTERVAL '90 days') AS cohort_start),
-events AS (
-  SELECT e."userId"::text AS user_id, e."createdAt"::timestamptz AS created_at,
-         DATE_TRUNC('day', e."createdAt")::date AS day_start
-  FROM platform."AgentGraphExecution" e WHERE e."userId" IS NOT NULL
-),
-first_exec AS (
-  SELECT user_id, MIN(created_at) AS first_exec_at,
-         DATE_TRUNC('day', MIN(created_at))::date AS cohort_day_start
-  FROM events GROUP BY 1
-  HAVING MIN(created_at) >= (SELECT cohort_start FROM params)
-),
-activity_days AS (SELECT DISTINCT user_id, day_start FROM events),
-user_day_age AS (
-  SELECT ad.user_id, fe.cohort_day_start,
-         (ad.day_start - DATE_TRUNC('day',fe.first_exec_at)::date)::int AS user_lifetime_day
-  FROM activity_days ad JOIN first_exec fe USING (user_id)
-  WHERE ad.day_start >= DATE_TRUNC('day',fe.first_exec_at)::date
-),
-bounded_counts AS (
-  SELECT cohort_day_start, user_lifetime_day, COUNT(DISTINCT user_id) AS active_users_bounded
-  FROM user_day_age WHERE user_lifetime_day >= 0 GROUP BY 1,2
-),
-last_active AS (
-  SELECT cohort_day_start, user_id, MAX(user_lifetime_day) AS last_active_day FROM user_day_age GROUP BY 1,2
-),
-unbounded_counts AS (
-  SELECT la.cohort_day_start, gs AS user_lifetime_day, COUNT(*) AS retained_users_unbounded
-  FROM last_active la
-  CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_day,(SELECT max_days FROM params))) gs
-  GROUP BY 1,2
-),
-cohort_sizes AS (SELECT cohort_day_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_exec GROUP BY 1),
-cohort_caps AS (
-  SELECT cs.cohort_day_start, cs.cohort_users,
-         LEAST((SELECT max_days FROM params), GREATEST(0,(CURRENT_DATE-cs.cohort_day_start)::int)) AS cap_days
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.cohort_day_start, gs AS user_lifetime_day, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_days) gs
-)
-SELECT
-  g.cohort_day_start,
-  TO_CHAR(g.cohort_day_start,'YYYY-MM-DD')                                AS cohort_label,
-  TO_CHAR(g.cohort_day_start,'YYYY-MM-DD')||' (n='||g.cohort_users||')'   AS cohort_label_n,
-  g.user_lifetime_day, g.cohort_users,
-  COALESCE(b.active_users_bounded,0)     AS active_users_bounded,
-  COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END    AS retention_rate_bounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
-  CASE WHEN g.user_lifetime_day=0 THEN g.cohort_users ELSE 0 END          AS cohort_users_d0
-FROM grid g
-LEFT JOIN bounded_counts   b ON b.cohort_day_start=g.cohort_day_start AND b.user_lifetime_day=g.user_lifetime_day
-LEFT JOIN unbounded_counts u ON u.cohort_day_start=g.cohort_day_start AND u.user_lifetime_day=g.user_lifetime_day
-ORDER BY g.cohort_day_start, g.user_lifetime_day;

autogpt_platform/analytics/queries/retention_execution_weekly.sql

@@ -1,81 +0,0 @@
--- =============================================================
--- View: analytics.retention_execution_weekly
--- Looker source alias: ds92  |  Charts: 2
--- =============================================================
--- DESCRIPTION
---   Weekly cohort retention based on agent executions.
---   Cohort anchor = week of user's FIRST ever agent execution
---   (not first login). Only includes cohorts from the last 180 days.
---   Useful when you care about product engagement, not just visits.
---
--- SOURCE TABLES
---   platform.AgentGraphExecution  — Execution records
---
--- OUTPUT COLUMNS
---   Same pattern as retention_login_weekly.
---   cohort_week_start = week of first execution (not first login)
---
--- EXAMPLE QUERIES
---   -- Week-2 execution retention
---   SELECT cohort_label, retention_rate_bounded
---   FROM analytics.retention_execution_weekly
---   WHERE user_lifetime_week = 2 ORDER BY cohort_week_start;
--- =============================================================
-
-WITH params AS (SELECT 12::int AS max_weeks, (CURRENT_DATE - INTERVAL '180 days') AS cohort_start),
-events AS (
-  SELECT e."userId"::text AS user_id, e."createdAt"::timestamptz AS created_at,
-         DATE_TRUNC('week', e."createdAt")::date AS week_start
-  FROM platform."AgentGraphExecution" e WHERE e."userId" IS NOT NULL
-),
-first_exec AS (
-  SELECT user_id, MIN(created_at) AS first_exec_at,
-         DATE_TRUNC('week', MIN(created_at))::date AS cohort_week_start
-  FROM events GROUP BY 1
-  HAVING MIN(created_at) >= (SELECT cohort_start FROM params)
-),
-activity_weeks AS (SELECT DISTINCT user_id, week_start FROM events),
-user_week_age AS (
-  SELECT aw.user_id, fe.cohort_week_start,
-         ((aw.week_start - DATE_TRUNC('week',fe.first_exec_at)::date)/7)::int AS user_lifetime_week
-  FROM activity_weeks aw JOIN first_exec fe USING (user_id)
-  WHERE aw.week_start >= DATE_TRUNC('week',fe.first_exec_at)::date
-),
-bounded_counts AS (
-  SELECT cohort_week_start, user_lifetime_week, COUNT(DISTINCT user_id) AS active_users_bounded
-  FROM user_week_age WHERE user_lifetime_week >= 0 GROUP BY 1,2
-),
-last_active AS (
-  SELECT cohort_week_start, user_id, MAX(user_lifetime_week) AS last_active_week FROM user_week_age GROUP BY 1,2
-),
-unbounded_counts AS (
-  SELECT la.cohort_week_start, gs AS user_lifetime_week, COUNT(*) AS retained_users_unbounded
-  FROM last_active la
-  CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_week,(SELECT max_weeks FROM params))) gs
-  GROUP BY 1,2
-),
-cohort_sizes AS (SELECT cohort_week_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_exec GROUP BY 1),
-cohort_caps AS (
-  SELECT cs.cohort_week_start, cs.cohort_users,
-         LEAST((SELECT max_weeks FROM params),
-               GREATEST(0,((DATE_TRUNC('week',CURRENT_DATE)::date-cs.cohort_week_start)/7)::int)) AS cap_weeks
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.cohort_week_start, gs AS user_lifetime_week, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_weeks) gs
-)
-SELECT
-  g.cohort_week_start,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')                               AS cohort_label,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')||' (n='||g.cohort_users||')'  AS cohort_label_n,
-  g.user_lifetime_week, g.cohort_users,
-  COALESCE(b.active_users_bounded,0)     AS active_users_bounded,
-  COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END    AS retention_rate_bounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
-  CASE WHEN g.user_lifetime_week=0 THEN g.cohort_users ELSE 0 END         AS cohort_users_w0
-FROM grid g
-LEFT JOIN bounded_counts   b ON b.cohort_week_start=g.cohort_week_start AND b.user_lifetime_week=g.user_lifetime_week
-LEFT JOIN unbounded_counts u ON u.cohort_week_start=g.cohort_week_start AND u.user_lifetime_week=g.user_lifetime_week
-ORDER BY g.cohort_week_start, g.user_lifetime_week;

autogpt_platform/analytics/queries/retention_login_daily.sql

@@ -1,94 +0,0 @@
--- =============================================================
--- View: analytics.retention_login_daily
--- Looker source alias: ds112  |  Charts: 1
--- =============================================================
--- DESCRIPTION
---   Daily cohort retention based on login sessions.
---   Same logic as retention_login_weekly but at day granularity,
---   showing up to day 30 for cohorts from the last 90 days.
---   Useful for analysing early activation (days 1-7) in detail.
---
--- SOURCE TABLES
---   auth.sessions  — Login session records
---
--- OUTPUT COLUMNS (same pattern as retention_login_weekly)
---   cohort_day_start          DATE     First day the cohort logged in
---   cohort_label              TEXT     Date string (e.g. '2025-03-01')
---   cohort_label_n            TEXT     Date + cohort size (e.g. '2025-03-01 (n=12)')
---   user_lifetime_day         INT      Days since first login (0 = signup day)
---   cohort_users              BIGINT   Total users in cohort
---   active_users_bounded      BIGINT   Users active on exactly day k
---   retained_users_unbounded  BIGINT   Users active any time on/after day k
---   retention_rate_bounded    FLOAT    bounded / cohort_users
---   retention_rate_unbounded  FLOAT    unbounded / cohort_users
---   cohort_users_d0           BIGINT   cohort_users only at day 0, else 0 (safe to SUM)
---
--- EXAMPLE QUERIES
---   -- Day-1 retention rate (came back next day)
---   SELECT cohort_label, retention_rate_bounded AS d1_retention
---   FROM analytics.retention_login_daily
---   WHERE user_lifetime_day = 1 ORDER BY cohort_day_start;
---
---   -- Average retention curve across all cohorts
---   SELECT user_lifetime_day,
---          SUM(active_users_bounded)::float / NULLIF(SUM(cohort_users_d0), 0) AS avg_retention
---   FROM analytics.retention_login_daily
---   GROUP BY 1 ORDER BY 1;
--- =============================================================
-
-WITH params AS (SELECT 30::int AS max_days, (CURRENT_DATE - INTERVAL '90 days')::date AS cohort_start),
-events AS (
-  SELECT s.user_id::text AS user_id, s.created_at::timestamptz AS created_at,
-         DATE_TRUNC('day', s.created_at)::date AS day_start
-  FROM auth.sessions s WHERE s.user_id IS NOT NULL
-),
-first_login AS (
-  SELECT user_id, MIN(created_at) AS first_login_time,
-         DATE_TRUNC('day', MIN(created_at))::date AS cohort_day_start
-  FROM events GROUP BY 1
-  HAVING MIN(created_at) >= (SELECT cohort_start FROM params)
-),
-activity_days AS (SELECT DISTINCT user_id, day_start FROM events),
-user_day_age AS (
-  SELECT ad.user_id, fl.cohort_day_start,
-         (ad.day_start - DATE_TRUNC('day', fl.first_login_time)::date)::int AS user_lifetime_day
-  FROM activity_days ad JOIN first_login fl USING (user_id)
-  WHERE ad.day_start >= DATE_TRUNC('day', fl.first_login_time)::date
-),
-bounded_counts AS (
-  SELECT cohort_day_start, user_lifetime_day, COUNT(DISTINCT user_id) AS active_users_bounded
-  FROM user_day_age WHERE user_lifetime_day >= 0 GROUP BY 1,2
-),
-last_active AS (
-  SELECT cohort_day_start, user_id, MAX(user_lifetime_day) AS last_active_day FROM user_day_age GROUP BY 1,2
-),
-unbounded_counts AS (
-  SELECT la.cohort_day_start, gs AS user_lifetime_day, COUNT(*) AS retained_users_unbounded
-  FROM last_active la
-  CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_day,(SELECT max_days FROM params))) gs
-  GROUP BY 1,2
-),
-cohort_sizes AS (SELECT cohort_day_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_login GROUP BY 1),
-cohort_caps AS (
-  SELECT cs.cohort_day_start, cs.cohort_users,
-         LEAST((SELECT max_days FROM params), GREATEST(0,(CURRENT_DATE-cs.cohort_day_start)::int)) AS cap_days
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.cohort_day_start, gs AS user_lifetime_day, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_days) gs
-)
-SELECT
-  g.cohort_day_start,
-  TO_CHAR(g.cohort_day_start,'YYYY-MM-DD')                                  AS cohort_label,
-  TO_CHAR(g.cohort_day_start,'YYYY-MM-DD')||' (n='||g.cohort_users||')'     AS cohort_label_n,
-  g.user_lifetime_day, g.cohort_users,
-  COALESCE(b.active_users_bounded,0)     AS active_users_bounded,
-  COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END    AS retention_rate_bounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
-  CASE WHEN g.user_lifetime_day=0 THEN g.cohort_users ELSE 0 END            AS cohort_users_d0
-FROM grid g
-LEFT JOIN bounded_counts   b ON b.cohort_day_start=g.cohort_day_start AND b.user_lifetime_day=g.user_lifetime_day
-LEFT JOIN unbounded_counts u ON u.cohort_day_start=g.cohort_day_start AND u.user_lifetime_day=g.user_lifetime_day
-ORDER BY g.cohort_day_start, g.user_lifetime_day;

autogpt_platform/analytics/queries/retention_login_onboarded_weekly.sql

@@ -1,96 +0,0 @@
--- =============================================================
--- View: analytics.retention_login_onboarded_weekly
--- Looker source alias: ds101  |  Charts: 2
--- =============================================================
--- DESCRIPTION
---   Weekly cohort retention from login sessions, restricted to
---   users who "onboarded" — defined as running at least one
---   agent within 365 days of their first login.
---   Filters out users who signed up but never activated,
---   giving a cleaner view of engaged-user retention.
---
--- SOURCE TABLES
---   auth.sessions                  — Login session records
---   platform.AgentGraphExecution   — Used to identify onboarders
---
--- OUTPUT COLUMNS
---   Same as retention_login_weekly (cohort_week_start, user_lifetime_week,
---   retention_rate_bounded, retention_rate_unbounded, etc.)
---   Only difference: cohort is filtered to onboarded users only.
---
--- EXAMPLE QUERIES
---   -- Compare week-4 retention: all users vs onboarded only
---   SELECT 'all_users' AS segment, AVG(retention_rate_bounded) AS w4_retention
---   FROM analytics.retention_login_weekly WHERE user_lifetime_week = 4
---   UNION ALL
---   SELECT 'onboarded', AVG(retention_rate_bounded)
---   FROM analytics.retention_login_onboarded_weekly WHERE user_lifetime_week = 4;
--- =============================================================
-
-WITH params AS (SELECT 12::int AS max_weeks, 365::int AS onboarding_window_days),
-events AS (
-  SELECT s.user_id::text AS user_id, s.created_at::timestamptz AS created_at,
-         DATE_TRUNC('week', s.created_at)::date AS week_start
-  FROM auth.sessions s WHERE s.user_id IS NOT NULL
-),
-first_login_all AS (
-  SELECT user_id, MIN(created_at) AS first_login_time,
-         DATE_TRUNC('week', MIN(created_at))::date AS cohort_week_start
-  FROM events GROUP BY 1
-),
-onboarders AS (
-  SELECT fl.user_id FROM first_login_all fl
-  WHERE EXISTS (
-    SELECT 1 FROM platform."AgentGraphExecution" e
-    WHERE e."userId"::text = fl.user_id
-      AND e."createdAt" >= fl.first_login_time
-      AND e."createdAt" < fl.first_login_time
-          + make_interval(days => (SELECT onboarding_window_days FROM params))
-  )
-),
-first_login AS (SELECT * FROM first_login_all WHERE user_id IN (SELECT user_id FROM onboarders)),
-activity_weeks AS (SELECT DISTINCT user_id, week_start FROM events),
-user_week_age AS (
-  SELECT aw.user_id, fl.cohort_week_start,
-         ((aw.week_start - DATE_TRUNC('week',fl.first_login_time)::date)/7)::int AS user_lifetime_week
-  FROM activity_weeks aw JOIN first_login fl USING (user_id)
-  WHERE aw.week_start >= DATE_TRUNC('week',fl.first_login_time)::date
-),
-bounded_counts AS (
-  SELECT cohort_week_start, user_lifetime_week, COUNT(DISTINCT user_id) AS active_users_bounded
-  FROM user_week_age WHERE user_lifetime_week >= 0 GROUP BY 1,2
-),
-last_active AS (
-  SELECT cohort_week_start, user_id, MAX(user_lifetime_week) AS last_active_week FROM user_week_age GROUP BY 1,2
-),
-unbounded_counts AS (
-  SELECT la.cohort_week_start, gs AS user_lifetime_week, COUNT(*) AS retained_users_unbounded
-  FROM last_active la
-  CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_week,(SELECT max_weeks FROM params))) gs
-  GROUP BY 1,2
-),
-cohort_sizes AS (SELECT cohort_week_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_login GROUP BY 1),
-cohort_caps AS (
-  SELECT cs.cohort_week_start, cs.cohort_users,
-         LEAST((SELECT max_weeks FROM params),
-               GREATEST(0,((DATE_TRUNC('week',CURRENT_DATE)::date-cs.cohort_week_start)/7)::int)) AS cap_weeks
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.cohort_week_start, gs AS user_lifetime_week, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_weeks) gs
-)
-SELECT
-  g.cohort_week_start,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')                               AS cohort_label,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')||' (n='||g.cohort_users||')'  AS cohort_label_n,
-  g.user_lifetime_week, g.cohort_users,
-  COALESCE(b.active_users_bounded,0)     AS active_users_bounded,
-  COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END    AS retention_rate_bounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
-  CASE WHEN g.user_lifetime_week=0 THEN g.cohort_users ELSE 0 END         AS cohort_users_w0
-FROM grid g
-LEFT JOIN bounded_counts   b ON b.cohort_week_start=g.cohort_week_start AND b.user_lifetime_week=g.user_lifetime_week
-LEFT JOIN unbounded_counts u ON u.cohort_week_start=g.cohort_week_start AND u.user_lifetime_week=g.user_lifetime_week
-ORDER BY g.cohort_week_start, g.user_lifetime_week;

autogpt_platform/analytics/queries/retention_login_weekly.sql

@@ -1,103 +0,0 @@
--- =============================================================
--- View: analytics.retention_login_weekly
--- Looker source alias: ds83  |  Charts: 2
--- =============================================================
--- DESCRIPTION
---   Weekly cohort retention based on login sessions.
---   Users are grouped by the ISO week of their first ever login.
---   For each cohort × lifetime-week combination, outputs both:
---     - bounded rate: % active in exactly that week
---     - unbounded rate: % who were ever active on or after that week
---   Weeks are capped to the cohort's actual age (no future data points).
---
--- SOURCE TABLES
---   auth.sessions  — Login session records
---
--- HOW TO READ THE OUTPUT
---   cohort_week_start   The Monday of the week users first logged in
---   user_lifetime_week  0 = signup week, 1 = one week later, etc.
---   retention_rate_bounded   = active_users_bounded / cohort_users
---   retention_rate_unbounded = retained_users_unbounded / cohort_users
---
--- OUTPUT COLUMNS
---   cohort_week_start         DATE     First day of the cohort's signup week
---   cohort_label              TEXT     ISO week label (e.g. '2025-W01')
---   cohort_label_n            TEXT     ISO week label with cohort size (e.g. '2025-W01 (n=42)')
---   user_lifetime_week        INT      Weeks since first login (0 = signup week)
---   cohort_users              BIGINT   Total users in this cohort (denominator)
---   active_users_bounded      BIGINT   Users active in exactly week k
---   retained_users_unbounded  BIGINT   Users active any time on/after week k
---   retention_rate_bounded    FLOAT    bounded active / cohort_users
---   retention_rate_unbounded  FLOAT    unbounded retained / cohort_users
---   cohort_users_w0           BIGINT   cohort_users only at week 0, else 0 (safe to SUM in pivot tables)
---
--- EXAMPLE QUERIES
---   -- Week-1 retention rate per cohort
---   SELECT cohort_label, retention_rate_bounded AS w1_retention
---   FROM analytics.retention_login_weekly
---   WHERE user_lifetime_week = 1
---   ORDER BY cohort_week_start;
---
---   -- Overall average retention curve (all cohorts combined)
---   SELECT user_lifetime_week,
---          SUM(active_users_bounded)::float / NULLIF(SUM(cohort_users_w0), 0) AS avg_retention
---   FROM analytics.retention_login_weekly
---   GROUP BY 1 ORDER BY 1;
--- =============================================================
-
-WITH params AS (SELECT 12::int AS max_weeks),
-events AS (
-  SELECT s.user_id::text AS user_id, s.created_at::timestamptz AS created_at,
-         DATE_TRUNC('week', s.created_at)::date AS week_start
-  FROM auth.sessions s WHERE s.user_id IS NOT NULL
-),
-first_login AS (
-  SELECT user_id, MIN(created_at) AS first_login_time,
-         DATE_TRUNC('week', MIN(created_at))::date AS cohort_week_start
-  FROM events GROUP BY 1
-),
-activity_weeks AS (SELECT DISTINCT user_id, week_start FROM events),
-user_week_age AS (
-  SELECT aw.user_id, fl.cohort_week_start,
-         ((aw.week_start - DATE_TRUNC('week', fl.first_login_time)::date) / 7)::int AS user_lifetime_week
-  FROM activity_weeks aw JOIN first_login fl USING (user_id)
-  WHERE aw.week_start >= DATE_TRUNC('week', fl.first_login_time)::date
-),
-bounded_counts AS (
-  SELECT cohort_week_start, user_lifetime_week, COUNT(DISTINCT user_id) AS active_users_bounded
-  FROM user_week_age WHERE user_lifetime_week >= 0 GROUP BY 1,2
-),
-last_active AS (
-  SELECT cohort_week_start, user_id, MAX(user_lifetime_week) AS last_active_week FROM user_week_age GROUP BY 1,2
-),
-unbounded_counts AS (
-  SELECT la.cohort_week_start, gs AS user_lifetime_week, COUNT(*) AS retained_users_unbounded
-  FROM last_active la
-  CROSS JOIN LATERAL generate_series(0, LEAST(la.last_active_week,(SELECT max_weeks FROM params))) gs
-  GROUP BY 1,2
-),
-cohort_sizes AS (SELECT cohort_week_start, COUNT(DISTINCT user_id) AS cohort_users FROM first_login GROUP BY 1),
-cohort_caps AS (
-  SELECT cs.cohort_week_start, cs.cohort_users,
-         LEAST((SELECT max_weeks FROM params),
-               GREATEST(0,((DATE_TRUNC('week',CURRENT_DATE)::date - cs.cohort_week_start)/7)::int)) AS cap_weeks
-  FROM cohort_sizes cs
-),
-grid AS (
-  SELECT cc.cohort_week_start, gs AS user_lifetime_week, cc.cohort_users
-  FROM cohort_caps cc CROSS JOIN LATERAL generate_series(0, cc.cap_weeks) gs
-)
-SELECT
-  g.cohort_week_start,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')                                    AS cohort_label,
-  TO_CHAR(g.cohort_week_start,'IYYY-"W"IW')||' (n='||g.cohort_users||')'       AS cohort_label_n,
-  g.user_lifetime_week, g.cohort_users,
-  COALESCE(b.active_users_bounded,0)     AS active_users_bounded,
-  COALESCE(u.retained_users_unbounded,0) AS retained_users_unbounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(b.active_users_bounded,0)::float/g.cohort_users END    AS retention_rate_bounded,
-  CASE WHEN g.cohort_users>0 THEN COALESCE(u.retained_users_unbounded,0)::float/g.cohort_users END AS retention_rate_unbounded,
-  CASE WHEN g.user_lifetime_week=0 THEN g.cohort_users ELSE 0 END               AS cohort_users_w0
-FROM grid g
-LEFT JOIN bounded_counts   b ON b.cohort_week_start=g.cohort_week_start AND b.user_lifetime_week=g.user_lifetime_week
-LEFT JOIN unbounded_counts u ON u.cohort_week_start=g.cohort_week_start AND u.user_lifetime_week=g.user_lifetime_week
-ORDER BY g.cohort_week_start, g.user_lifetime_week

autogpt_platform/analytics/queries/user_block_spending.sql

@@ -1,71 +0,0 @@
--- =============================================================
--- View: analytics.user_block_spending
--- Looker source alias: ds6  |  Charts: 5
--- =============================================================
--- DESCRIPTION
---   One row per credit transaction (last 90 days).
---   Shows how users spend credits broken down by block type,
---   LLM provider and model.  Joins node execution stats for
---   token-level detail.
---
--- SOURCE TABLES
---   platform.CreditTransaction   — Credit debit/credit records
---   platform.AgentNodeExecution  — Node execution stats (for token counts)
---
--- OUTPUT COLUMNS
---   transactionKey        TEXT         Unique transaction identifier
---   userId                TEXT         User who was charged
---   amount                DECIMAL      Credit amount (positive = credit, negative = debit)
---   negativeAmount        DECIMAL      amount * -1 (convenience for spend charts)
---   transactionType       TEXT         Transaction type (e.g. 'USAGE', 'REFUND', 'TOP_UP')
---   transactionTime       TIMESTAMPTZ  When the transaction was recorded
---   blockId               TEXT         Block UUID that triggered the spend
---   blockName             TEXT         Human-readable block name
---   llm_provider          TEXT         LLM provider (e.g. 'openai', 'anthropic')
---   llm_model             TEXT         Model name (e.g. 'gpt-4o', 'claude-3-5-sonnet')
---   node_exec_id          TEXT         Linked node execution UUID
---   llm_call_count        INT          LLM API calls made in that execution
---   llm_retry_count       INT          LLM retries in that execution
---   llm_input_token_count INT          Input tokens consumed
---   llm_output_token_count INT         Output tokens produced
---
--- WINDOW
---   Rolling 90 days (createdAt > CURRENT_DATE - 90 days)
---
--- EXAMPLE QUERIES
---   -- Total spend per user (last 90 days)
---   SELECT "userId", SUM("negativeAmount") AS total_spent
---   FROM analytics.user_block_spending
---   WHERE "transactionType" = 'USAGE'
---   GROUP BY 1 ORDER BY total_spent DESC;
---
---   -- Spend by LLM provider + model
---   SELECT "llm_provider", "llm_model",
---          SUM("negativeAmount") AS total_cost,
---          SUM("llm_input_token_count") AS input_tokens,
---          SUM("llm_output_token_count") AS output_tokens
---   FROM analytics.user_block_spending
---   WHERE "llm_provider" IS NOT NULL
---   GROUP BY 1, 2 ORDER BY total_cost DESC;
--- =============================================================
-
-SELECT
-    c."transactionKey"                                        AS transactionKey,
-    c."userId"                                                AS userId,
-    c."amount"                                                AS amount,
-    c."amount" * -1                                           AS negativeAmount,
-    c."type"                                                  AS transactionType,
-    c."createdAt"                                             AS transactionTime,
-    c.metadata->>'block_id'                                   AS blockId,
-    c.metadata->>'block'                                      AS blockName,
-    c.metadata->'input'->'credentials'->>'provider'           AS llm_provider,
-    c.metadata->'input'->>'model'                             AS llm_model,
-    c.metadata->>'node_exec_id'                               AS node_exec_id,
-    (ne."stats"->>'llm_call_count')::int                       AS llm_call_count,
-    (ne."stats"->>'llm_retry_count')::int                      AS llm_retry_count,
-    (ne."stats"->>'input_token_count')::int                    AS llm_input_token_count,
-    (ne."stats"->>'output_token_count')::int                   AS llm_output_token_count
-FROM platform."CreditTransaction" c
-LEFT JOIN platform."AgentNodeExecution" ne
-       ON (c.metadata->>'node_exec_id') = ne."id"::text
-WHERE c."createdAt" > CURRENT_DATE - INTERVAL '90 days'

autogpt_platform/analytics/queries/user_onboarding.sql

@@ -1,45 +0,0 @@
--- =============================================================
--- View: analytics.user_onboarding
--- Looker source alias: ds68  |  Charts: 3
--- =============================================================
--- DESCRIPTION
---   One row per user onboarding record.  Contains the user's
---   stated usage reason, selected integrations, completed
---   onboarding steps and optional first agent selection.
---   Full history (no date filter) since onboarding happens
---   once per user.
---
--- SOURCE TABLES
---   platform.UserOnboarding  — Onboarding state per user
---
--- OUTPUT COLUMNS
---   id                            TEXT         Onboarding record UUID
---   createdAt                     TIMESTAMPTZ  When onboarding started
---   updatedAt                     TIMESTAMPTZ  Last update to onboarding state
---   usageReason                   TEXT         Why user signed up (e.g. 'work', 'personal')
---   integrations                  TEXT[]       Array of integration names the user selected
---   userId                        TEXT         User UUID
---   completedSteps                TEXT[]       Array of onboarding step enums completed
---   selectedStoreListingVersionId TEXT         First marketplace agent the user chose (if any)
---
--- EXAMPLE QUERIES
---   -- Usage reason breakdown
---   SELECT "usageReason", COUNT(*) FROM analytics.user_onboarding GROUP BY 1;
---
---   -- Completion rate per step
---   SELECT step, COUNT(*) AS users_completed
---   FROM analytics.user_onboarding
---   CROSS JOIN LATERAL UNNEST("completedSteps") AS step
---   GROUP BY 1 ORDER BY users_completed DESC;
--- =============================================================
-
-SELECT
-    id,
-    "createdAt",
-    "updatedAt",
-    "usageReason",
-    integrations,
-    "userId",
-    "completedSteps",
-    "selectedStoreListingVersionId"
-FROM platform."UserOnboarding"

autogpt_platform/analytics/queries/user_onboarding_funnel.sql

@@ -1,100 +0,0 @@
--- =============================================================
--- View: analytics.user_onboarding_funnel
--- Looker source alias: ds74  |  Charts: 1
--- =============================================================
--- DESCRIPTION
---   Pre-aggregated onboarding funnel showing how many users
---   completed each step and the drop-off percentage from the
---   previous step.  One row per onboarding step (all 22 steps
---   always present, even with 0 completions — prevents sparse
---   gaps from making LAG compare the wrong predecessors).
---
--- SOURCE TABLES
---   platform.UserOnboarding  — Onboarding records with completedSteps array
---
--- OUTPUT COLUMNS
---   step             TEXT     Onboarding step enum name (e.g. 'WELCOME', 'CONGRATS')
---   step_order       INT      Numeric position in the funnel (1=first, 22=last)
---   users_completed  BIGINT   Distinct users who completed this step
---   pct_from_prev    NUMERIC  % of users from the previous step who reached this one
---
--- STEP ORDER
---   1  WELCOME               9  MARKETPLACE_VISIT     17  SCHEDULE_AGENT
---   2  USAGE_REASON         10  MARKETPLACE_ADD_AGENT  18  RUN_AGENTS
---   3  INTEGRATIONS         11  MARKETPLACE_RUN_AGENT  19  RUN_3_DAYS
---   4  AGENT_CHOICE         12  BUILDER_OPEN           20  TRIGGER_WEBHOOK
---   5  AGENT_NEW_RUN        13  BUILDER_SAVE_AGENT     21  RUN_14_DAYS
---   6  AGENT_INPUT          14  BUILDER_RUN_AGENT      22  RUN_AGENTS_100
---   7  CONGRATS             15  VISIT_COPILOT
---   8  GET_RESULTS          16  RE_RUN_AGENT
---
--- WINDOW
---   Users who started onboarding in the last 90 days
---
--- EXAMPLE QUERIES
---   -- Full funnel
---   SELECT * FROM analytics.user_onboarding_funnel ORDER BY step_order;
---
---   -- Biggest drop-off point
---   SELECT step, pct_from_prev FROM analytics.user_onboarding_funnel
---   ORDER BY pct_from_prev ASC LIMIT 3;
--- =============================================================
-
-WITH all_steps AS (
-  -- Complete ordered grid of all 22 steps so zero-completion steps
-  -- are always present, keeping LAG comparisons correct.
-  SELECT step_name, step_order
-  FROM (VALUES
-    ('WELCOME',               1),
-    ('USAGE_REASON',          2),
-    ('INTEGRATIONS',          3),
-    ('AGENT_CHOICE',          4),
-    ('AGENT_NEW_RUN',         5),
-    ('AGENT_INPUT',           6),
-    ('CONGRATS',              7),
-    ('GET_RESULTS',           8),
-    ('MARKETPLACE_VISIT',     9),
-    ('MARKETPLACE_ADD_AGENT', 10),
-    ('MARKETPLACE_RUN_AGENT', 11),
-    ('BUILDER_OPEN',          12),
-    ('BUILDER_SAVE_AGENT',    13),
-    ('BUILDER_RUN_AGENT',     14),
-    ('VISIT_COPILOT',         15),
-    ('RE_RUN_AGENT',          16),
-    ('SCHEDULE_AGENT',        17),
-    ('RUN_AGENTS',            18),
-    ('RUN_3_DAYS',            19),
-    ('TRIGGER_WEBHOOK',       20),
-    ('RUN_14_DAYS',           21),
-    ('RUN_AGENTS_100',        22)
-  ) AS t(step_name, step_order)
-),
-raw AS (
-  SELECT
-      u."userId",
-      step_txt::text AS step
-  FROM platform."UserOnboarding" u
-  CROSS JOIN LATERAL UNNEST(u."completedSteps") AS step_txt
-  WHERE u."createdAt" >= CURRENT_DATE - INTERVAL '90 days'
-),
-step_counts AS (
-  SELECT step, COUNT(DISTINCT "userId") AS users_completed
-  FROM raw GROUP BY step
-),
-funnel AS (
-  SELECT
-      a.step_name                          AS step,
-      a.step_order,
-      COALESCE(sc.users_completed, 0)      AS users_completed,
-      ROUND(
-        100.0 * COALESCE(sc.users_completed, 0)
-        / NULLIF(
-            LAG(COALESCE(sc.users_completed, 0)) OVER (ORDER BY a.step_order),
-            0
-          ),
-        2
-      )                                    AS pct_from_prev
-  FROM all_steps a
-  LEFT JOIN step_counts sc ON sc.step = a.step_name
-)
-SELECT * FROM funnel ORDER BY step_order

autogpt_platform/analytics/queries/user_onboarding_integration.sql

@@ -1,41 +0,0 @@
--- =============================================================
--- View: analytics.user_onboarding_integration
--- Looker source alias: ds75  |  Charts: 1
--- =============================================================
--- DESCRIPTION
---   Pre-aggregated count of users who selected each integration
---   during onboarding.  One row per integration type, sorted
---   by popularity.
---
--- SOURCE TABLES
---   platform.UserOnboarding  — integrations array column
---
--- OUTPUT COLUMNS
---   integration            TEXT    Integration name (e.g. 'github', 'slack', 'notion')
---   users_with_integration BIGINT  Distinct users who selected this integration
---
--- WINDOW
---   Users who started onboarding in the last 90 days
---
--- EXAMPLE QUERIES
---   -- Full integration popularity ranking
---   SELECT * FROM analytics.user_onboarding_integration;
---
---   -- Top 5 integrations
---   SELECT * FROM analytics.user_onboarding_integration LIMIT 5;
--- =============================================================
-
-WITH exploded AS (
-  SELECT
-      u."userId" AS user_id,
-      UNNEST(u."integrations") AS integration
-  FROM platform."UserOnboarding" u
-  WHERE u."createdAt" >= CURRENT_DATE - INTERVAL '90 days'
-)
-SELECT
-    integration,
-    COUNT(DISTINCT user_id) AS users_with_integration
-FROM exploded
-WHERE integration IS NOT NULL AND integration <> ''
-GROUP BY integration
-ORDER BY users_with_integration DESC

autogpt_platform/analytics/queries/users_activities.sql

@@ -1,145 +0,0 @@
--- =============================================================
--- View: analytics.users_activities
--- Looker source alias: ds56  |  Charts: 5
--- =============================================================
--- DESCRIPTION
---   One row per user with lifetime activity summary.
---   Joins login sessions with agent graphs, executions and
---   node-level runs to give a full picture of how engaged
---   each user is.  Includes a convenience flag for 7-day
---   activation (did the user return at least 7 days after
---   their first login?).
---
--- SOURCE TABLES
---   auth.sessions                    — Login/session records
---   platform.AgentGraph              — Graphs (agents) built by the user
---   platform.AgentGraphExecution     — Agent run history
---   platform.AgentNodeExecution      — Individual block execution history
---
--- PERFORMANCE NOTE
---   Each CTE aggregates its own table independently by userId.
---   This avoids the fan-out that occurs when driving every join
---   from user_logins across the two largest tables
---   (AgentGraphExecution and AgentNodeExecution).
---
--- OUTPUT COLUMNS
---   user_id                   TEXT         Supabase user UUID
---   first_login_time          TIMESTAMPTZ  First ever session created_at
---   last_login_time           TIMESTAMPTZ  Most recent session created_at
---   last_visit_time           TIMESTAMPTZ  Max of last refresh or login
---   last_agent_save_time      TIMESTAMPTZ  Last time user saved an agent graph
---   agent_count               BIGINT       Number of distinct active graphs built (0 if none)
---   first_agent_run_time      TIMESTAMPTZ  First ever graph execution
---   last_agent_run_time       TIMESTAMPTZ  Most recent graph execution
---   unique_agent_runs         BIGINT       Distinct agent graphs ever run (0 if none)
---   agent_runs                BIGINT       Total graph execution count (0 if none)
---   node_execution_count      BIGINT       Total node executions across all runs
---   node_execution_failed     BIGINT       Node executions with FAILED status
---   node_execution_completed  BIGINT       Node executions with COMPLETED status
---   node_execution_terminated BIGINT       Node executions with TERMINATED status
---   node_execution_queued     BIGINT       Node executions with QUEUED status
---   node_execution_running    BIGINT       Node executions with RUNNING status
---   is_active_after_7d        INT          1=returned after day 7, 0=did not, NULL=too early to tell
---   node_execution_incomplete BIGINT       Node executions with INCOMPLETE status
---   node_execution_review     BIGINT       Node executions with REVIEW status
---
--- EXAMPLE QUERIES
---   -- Users who ran at least one agent and returned after 7 days
---   SELECT COUNT(*) FROM analytics.users_activities
---   WHERE agent_runs > 0 AND is_active_after_7d = 1;
---
---   -- Top 10 most active users by agent runs
---   SELECT user_id, agent_runs, node_execution_count
---   FROM analytics.users_activities
---   ORDER BY agent_runs DESC LIMIT 10;
---
---   -- 7-day activation rate
---   SELECT
---     SUM(CASE WHEN is_active_after_7d = 1 THEN 1 ELSE 0 END)::float
---     / NULLIF(COUNT(CASE WHEN is_active_after_7d IS NOT NULL THEN 1 END), 0)
---     AS activation_rate
---   FROM analytics.users_activities;
--- =============================================================
-
-WITH user_logins AS (
-  SELECT
-    user_id::text                                    AS user_id,
-    MIN(created_at)                                  AS first_login_time,
-    MAX(created_at)                                  AS last_login_time,
-    GREATEST(
-      MAX(refreshed_at)::timestamptz,
-      MAX(created_at)::timestamptz
-    )                                                AS last_visit_time
-  FROM auth.sessions
-  GROUP BY user_id
-),
-user_agents AS (
-  -- Aggregate AgentGraph directly by userId (no fan-out from user_logins)
-  SELECT
-    "userId"::text                AS user_id,
-    MAX("updatedAt")              AS last_agent_save_time,
-    COUNT(DISTINCT "id")          AS agent_count
-  FROM platform."AgentGraph"
-  WHERE "isActive"
-  GROUP BY "userId"
-),
-user_graph_runs AS (
-  -- Aggregate AgentGraphExecution directly by userId
-  SELECT
-    "userId"::text                        AS user_id,
-    MIN("createdAt")                      AS first_agent_run_time,
-    MAX("createdAt")                      AS last_agent_run_time,
-    COUNT(DISTINCT "agentGraphId")        AS unique_agent_runs,
-    COUNT("id")                           AS agent_runs
-  FROM platform."AgentGraphExecution"
-  GROUP BY "userId"
-),
-user_node_runs AS (
-  -- Aggregate AgentNodeExecution directly; resolve userId via a
-  -- single join to AgentGraphExecution instead of fanning out from
-  -- user_logins through both large tables.
-  SELECT
-    g."userId"::text                                                   AS user_id,
-    COUNT(*)                                                           AS node_execution_count,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'FAILED')             AS node_execution_failed,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'COMPLETED')          AS node_execution_completed,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'TERMINATED')         AS node_execution_terminated,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'QUEUED')             AS node_execution_queued,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'RUNNING')            AS node_execution_running,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'INCOMPLETE')         AS node_execution_incomplete,
-    COUNT(*) FILTER (WHERE n."executionStatus" = 'REVIEW')             AS node_execution_review
-  FROM platform."AgentNodeExecution" n
-  JOIN platform."AgentGraphExecution" g
-    ON g."id" = n."agentGraphExecutionId"
-  GROUP BY g."userId"
-)
-SELECT
-  ul.user_id,
-  ul.first_login_time,
-  ul.last_login_time,
-  ul.last_visit_time,
-  ua.last_agent_save_time,
-  COALESCE(ua.agent_count, 0)             AS agent_count,
-  gr.first_agent_run_time,
-  gr.last_agent_run_time,
-  COALESCE(gr.unique_agent_runs, 0)       AS unique_agent_runs,
-  COALESCE(gr.agent_runs, 0)              AS agent_runs,
-  COALESCE(nr.node_execution_count, 0)      AS node_execution_count,
-  COALESCE(nr.node_execution_failed, 0)     AS node_execution_failed,
-  COALESCE(nr.node_execution_completed, 0)  AS node_execution_completed,
-  COALESCE(nr.node_execution_terminated, 0) AS node_execution_terminated,
-  COALESCE(nr.node_execution_queued, 0)     AS node_execution_queued,
-  COALESCE(nr.node_execution_running, 0)    AS node_execution_running,
-  CASE
-    WHEN ul.first_login_time < NOW() - INTERVAL '7 days'
-     AND ul.last_visit_time  >= ul.first_login_time + INTERVAL '7 days' THEN 1
-    WHEN ul.first_login_time < NOW() - INTERVAL '7 days'
-     AND ul.last_visit_time  <  ul.first_login_time + INTERVAL '7 days' THEN 0
-    ELSE NULL
-  END AS is_active_after_7d,
-  COALESCE(nr.node_execution_incomplete, 0) AS node_execution_incomplete,
-  COALESCE(nr.node_execution_review, 0)     AS node_execution_review
-FROM user_logins ul
-LEFT JOIN user_agents     ua ON ul.user_id = ua.user_id
-LEFT JOIN user_graph_runs gr ON ul.user_id = gr.user_id
-LEFT JOIN user_node_runs  nr ON ul.user_id = nr.user_id

autogpt_platform/backend/.env.default

@@ -37,10 +37,6 @@ JWT_VERIFY_KEY=your-super-secret-jwt-token-with-at-least-32-characters-long
 ENCRYPTION_KEY=dvziYgz0KSK8FENhju0ZYi8-fRTfAdlz6YLhdB_jhNw=
 UNSUBSCRIBE_SECRET_KEY=HlP8ivStJjmbf6NKi78m_3FnOogut0t5ckzjsIqeaio=
 
-## ===== SIGNUP / INVITE GATE ===== ##
-# Set to true to require an invite before users can sign up
-ENABLE_INVITE_GATE=false
-
 ## ===== IMPORTANT OPTIONAL CONFIGURATION ===== ##
 # Platform URLs (set these for webhooks and OAuth to work)
 PLATFORM_BASE_URL=http://localhost:8000
@@ -194,8 +190,5 @@ ZEROBOUNCE_API_KEY=
 POSTHOG_API_KEY=
 POSTHOG_HOST=https://eu.i.posthog.com
 
-# Tally Form Integration (pre-populate business understanding on signup)
-TALLY_API_KEY=
-
 # Other Services
 AUTOMOD_API_KEY=

autogpt_platform/backend/CLAUDE.md

@@ -58,31 +58,10 @@ poetry run pytest path/to/test.py --snapshot-update
 - **Authentication**: JWT-based with Supabase integration
 - **Security**: Cache protection middleware prevents sensitive data caching in browsers/proxies
 
-## Code Style
-
-- **Top-level imports only** — no local/inner imports (lazy imports only for heavy optional deps like `openpyxl`)
-- **No duck typing** — no `hasattr`/`getattr`/`isinstance` for type dispatch; use typed interfaces/unions/protocols
-- **Pydantic models** over dataclass/namedtuple/dict for structured data
-- **No linter suppressors** — no `# type: ignore`, `# noqa`, `# pyright: ignore`; fix the type/code
-- **List comprehensions** over manual loop-and-append
-- **Early return** — guard clauses first, avoid deep nesting
-- **Lazy `%s` logging** — `logger.info("Processing %s items", count)` not `logger.info(f"Processing {count} items")`
-- **Sanitize error paths** — `os.path.basename()` in error messages to avoid leaking directory structure
-- **TOCTOU awareness** — avoid check-then-act patterns for file access and credit charging
-- **`Security()` vs `Depends()`** — use `Security()` for auth deps to get proper OpenAPI security spec
-- **Redis pipelines** — `transaction=True` for atomicity on multi-step operations
-- **`max(0, value)` guards** — for computed values that should never be negative
-- **SSE protocol** — `data:` lines for frontend-parsed events (must match Zod schema), `: comment` lines for heartbeats/status
-- **File length** — keep files under ~300 lines; if a file grows beyond this, split by responsibility (e.g. extract helpers, models, or a sub-module into a new file). Never keep appending to a long file.
-- **Function length** — keep functions under ~40 lines; extract named helpers when a function grows longer. Long functions are a sign of mixed concerns, not complexity.
-
 ## Testing Approach
 
 - Uses pytest with snapshot testing for API responses
 - Test files are colocated with source files (`*_test.py`)
-- Mock at boundaries — mock where the symbol is **used**, not where it's **defined**
-- After refactoring, update mock targets to match new module paths
-- Use `AsyncMock` for async functions (`from unittest.mock import AsyncMock`)
 
 ## Database Schema
 

autogpt_platform/backend/Dockerfile

@@ -53,6 +53,63 @@ 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
 
+# ============================== BACKEND SERVER ============================== #
+
+FROM debian:13-slim AS server
+
+WORKDIR /app
+
+ENV POETRY_HOME=/opt/poetry \
+    POETRY_NO_INTERACTION=1 \
+    POETRY_VIRTUALENVS_CREATE=true \
+    POETRY_VIRTUALENVS_IN_PROJECT=true \
+    DEBIAN_FRONTEND=noninteractive
+ENV PATH=/opt/poetry/bin:$PATH
+
+# Install Python, FFmpeg, ImageMagick, and CLI tools for agent use.
+# bubblewrap provides OS-level sandbox (whitelist-only FS + no network)
+# for the bash_exec MCP tool.
+# Using --no-install-recommends saves ~650MB by skipping unnecessary deps like llvm, mesa, etc.
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    python3.13 \
+    python3-pip \
+    ffmpeg \
+    imagemagick \
+    jq \
+    ripgrep \
+    tree \
+    bubblewrap \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY --from=builder /usr/local/lib/python3* /usr/local/lib/python3*
+COPY --from=builder /usr/local/bin/poetry /usr/local/bin/poetry
+# Copy Node.js installation for Prisma
+COPY --from=builder /usr/bin/node /usr/bin/node
+COPY --from=builder /usr/lib/node_modules /usr/lib/node_modules
+COPY --from=builder /usr/bin/npm /usr/bin/npm
+COPY --from=builder /usr/bin/npx /usr/bin/npx
+COPY --from=builder /root/.cache/prisma-python/binaries /root/.cache/prisma-python/binaries
+
+WORKDIR /app/autogpt_platform/backend
+
+# Copy only the .venv from builder (not the entire /app directory)
+# The .venv includes the generated Prisma client
+COPY --from=builder /app/autogpt_platform/backend/.venv ./.venv
+ENV PATH="/app/autogpt_platform/backend/.venv/bin:$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 ./
+
+# Copy backend code + docs (for Copilot docs search)
+COPY autogpt_platform/backend ./
+COPY docs /app/docs
+RUN poetry install --no-ansi --only-root
+
+ENV PORT=8000
+
+CMD ["poetry", "run", "rest"]
+
 # =============================== DB MIGRATOR =============================== #
 
 # Lightweight migrate stage - only needs Prisma CLI, not full Python environment
@@ -84,75 +141,3 @@ COPY autogpt_platform/backend/schema.prisma ./
 COPY autogpt_platform/backend/backend/data/partial_types.py ./backend/data/partial_types.py
 COPY autogpt_platform/backend/gen_prisma_types_stub.py ./
 COPY autogpt_platform/backend/migrations ./migrations
-
-# ============================== BACKEND SERVER ============================== #
-
-FROM debian:13-slim AS server
-
-WORKDIR /app
-
-ENV DEBIAN_FRONTEND=noninteractive
-
-# 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 (fallback when E2B is not configured).
-# Using --no-install-recommends saves ~650MB by skipping unnecessary deps like llvm, mesa, etc.
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    python3.13 \
-    python3-pip \
-    ffmpeg \
-    imagemagick \
-    jq \
-    ripgrep \
-    tree \
-    bubblewrap \
-    && rm -rf /var/lib/apt/lists/*
-
-# Copy poetry (build-time only, for `poetry install --only-root` to create entry points)
-COPY --from=builder /usr/local/lib/python3* /usr/local/lib/python3*
-COPY --from=builder /usr/local/bin/poetry /usr/local/bin/poetry
-# Copy Node.js installation for Prisma and agent-browser.
-# npm/npx are symlinks in the builder (-> ../lib/node_modules/npm/bin/*-cli.js);
-# COPY resolves them to regular files, breaking require() paths.  Recreate as
-# proper symlinks so npm/npx can find their modules.
-COPY --from=builder /usr/bin/node /usr/bin/node
-COPY --from=builder /usr/lib/node_modules /usr/lib/node_modules
-RUN ln -s ../lib/node_modules/npm/bin/npm-cli.js /usr/bin/npm \
-    && ln -s ../lib/node_modules/npm/bin/npx-cli.js /usr/bin/npx
-COPY --from=builder /root/.cache/prisma-python/binaries /root/.cache/prisma-python/binaries
-
-# Install agent-browser (Copilot browser tool) + Chromium runtime dependencies.
-# These are the runtime libraries Chromium/Playwright needs on Debian 13 (trixie).
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    libnss3 libnspr4 libatk1.0-0 libatk-bridge2.0-0 libcups2 libdrm2 \
-    libdbus-1-3 libxkbcommon0 libatspi2.0-0t64 libxcomposite1 libxdamage1 \
-    libxfixes3 libxrandr2 libgbm1 libasound2t64 libpango-1.0-0 libcairo2 \
-    libx11-6 libx11-xcb1 libxcb1 libxext6 libglib2.0-0t64 \
-    fonts-liberation libfontconfig1 \
-    && rm -rf /var/lib/apt/lists/* \
-    && npm install -g agent-browser \
-    && agent-browser install \
-    && rm -rf /tmp/* /root/.npm
-
-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 ./
-
-# Copy backend code + docs (for Copilot docs search)
-COPY 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
-
-ENV PORT=8000
-
-CMD ["rest"]

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."""

autogpt_platform/backend/backend/api/external/middleware.py

@@ -88,23 +88,20 @@ async def require_auth(
     )
 
 
-def require_permission(*permissions: APIKeyPermission):
+def require_permission(permission: APIKeyPermission):
     """
-    Dependency function for checking required permissions.
-    All listed permissions must be present.
+    Dependency function for checking specific permissions
     (works with API keys and OAuth tokens)
     """
 
-    async def check_permissions(
+    async def check_permission(
         auth: APIAuthorizationInfo = Security(require_auth),
     ) -> APIAuthorizationInfo:
-        missing = [p for p in permissions if p not in auth.scopes]
-        if missing:
+        if permission not in auth.scopes:
             raise HTTPException(
                 status_code=status.HTTP_403_FORBIDDEN,
-                detail=f"Missing required permission(s): "
-                f"{', '.join(p.value for p in missing)}",
+                detail=f"Missing required permission: {permission.value}",
             )
         return auth
 
-    return check_permissions
+    return check_permission

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

@@ -1,7 +1,7 @@
 import logging
 import urllib.parse
 from collections import defaultdict
-from typing import Annotated, Any, Optional, Sequence
+from typing import Annotated, Any, Literal, Optional, Sequence
 
 from fastapi import APIRouter, Body, HTTPException, Security
 from prisma.enums import AgentExecutionStatus, APIKeyPermission
@@ -9,17 +9,15 @@ from pydantic import BaseModel, Field
 from typing_extensions import TypedDict
 
 import backend.api.features.store.cache as store_cache
-import backend.api.features.store.db as store_db
 import backend.api.features.store.model as store_model
 import backend.blocks
-from backend.api.external.middleware import require_auth, require_permission
+from backend.api.external.middleware import require_permission
 from backend.data import execution as execution_db
 from backend.data import graph as graph_db
 from backend.data import user as user_db
 from backend.data.auth.base import APIAuthorizationInfo
 from backend.data.block import BlockInput, CompletedBlockOutput
 from backend.executor.utils import add_graph_execution
-from backend.integrations.webhooks.graph_lifecycle_hooks import on_graph_activate
 from backend.util.settings import Settings
 
 from .integrations import integrations_router
@@ -97,43 +95,6 @@ async def execute_graph_block(
     return output
 
 
-@v1_router.post(
-    path="/graphs",
-    tags=["graphs"],
-    status_code=201,
-    dependencies=[
-        Security(
-            require_permission(
-                APIKeyPermission.WRITE_GRAPH, APIKeyPermission.WRITE_LIBRARY
-            )
-        )
-    ],
-)
-async def create_graph(
-    graph: graph_db.Graph,
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_GRAPH, APIKeyPermission.WRITE_LIBRARY)
-    ),
-) -> graph_db.GraphModel:
-    """
-    Create a new agent graph.
-
-    The graph will be validated and assigned a new ID.
-    It is automatically added to the user's library.
-    """
-    from backend.api.features.library import db as library_db
-
-    graph_model = graph_db.make_graph_model(graph, auth.user_id)
-    graph_model.reassign_ids(user_id=auth.user_id, reassign_graph_id=True)
-    graph_model.validate_graph(for_run=False)
-
-    await graph_db.create_graph(graph_model, user_id=auth.user_id)
-    await library_db.create_library_agent(graph_model, auth.user_id)
-    activated_graph = await on_graph_activate(graph_model, user_id=auth.user_id)
-
-    return activated_graph
-
-
 @v1_router.post(
     path="/graphs/{graph_id}/execute/{graph_version}",
     tags=["graphs"],
@@ -231,13 +192,13 @@ async def get_graph_execution_results(
 @v1_router.get(
     path="/store/agents",
     tags=["store"],
-    dependencies=[Security(require_auth)],  # data is public; auth required as anti-DDoS
+    dependencies=[Security(require_permission(APIKeyPermission.READ_STORE))],
     response_model=store_model.StoreAgentsResponse,
 )
 async def get_store_agents(
     featured: bool = False,
     creator: str | None = None,
-    sorted_by: store_db.StoreAgentsSortOptions | None = None,
+    sorted_by: Literal["rating", "runs", "name", "updated_at"] | None = None,
     search_query: str | None = None,
     category: str | None = None,
     page: int = 1,
@@ -279,7 +240,7 @@ async def get_store_agents(
 @v1_router.get(
     path="/store/agents/{username}/{agent_name}",
     tags=["store"],
-    dependencies=[Security(require_auth)],  # data is public; auth required as anti-DDoS
+    dependencies=[Security(require_permission(APIKeyPermission.READ_STORE))],
     response_model=store_model.StoreAgentDetails,
 )
 async def get_store_agent(
@@ -307,13 +268,13 @@ async def get_store_agent(
 @v1_router.get(
     path="/store/creators",
     tags=["store"],
-    dependencies=[Security(require_auth)],  # data is public; auth required as anti-DDoS
+    dependencies=[Security(require_permission(APIKeyPermission.READ_STORE))],
     response_model=store_model.CreatorsResponse,
 )
 async def get_store_creators(
     featured: bool = False,
     search_query: str | None = None,
-    sorted_by: store_db.StoreCreatorsSortOptions | None = None,
+    sorted_by: Literal["agent_rating", "agent_runs", "num_agents"] | None = None,
     page: int = 1,
     page_size: int = 20,
 ) -> store_model.CreatorsResponse:
@@ -349,7 +310,7 @@ async def get_store_creators(
 @v1_router.get(
     path="/store/creators/{username}",
     tags=["store"],
-    dependencies=[Security(require_auth)],  # data is public; auth required as anti-DDoS
+    dependencies=[Security(require_permission(APIKeyPermission.READ_STORE))],
     response_model=store_model.CreatorDetails,
 )
 async def get_store_creator(

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__)

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

@@ -1,17 +1,8 @@
-from __future__ import annotations
-
-from datetime import datetime
-from typing import TYPE_CHECKING, Any, Literal, Optional
-
-import prisma.enums
-from pydantic import BaseModel, EmailStr
+from pydantic import BaseModel
 
 from backend.data.model import UserTransaction
 from backend.util.models import Pagination
 
-if TYPE_CHECKING:
-    from backend.data.invited_user import BulkInvitedUsersResult, InvitedUserRecord
-
 
 class UserHistoryResponse(BaseModel):
     """Response model for listings with version history"""
@@ -23,70 +14,3 @@ class UserHistoryResponse(BaseModel):
 class AddUserCreditsResponse(BaseModel):
     new_balance: int
     transaction_key: str
-
-
-class CreateInvitedUserRequest(BaseModel):
-    email: EmailStr
-    name: Optional[str] = None
-
-
-class InvitedUserResponse(BaseModel):
-    id: str
-    email: str
-    status: prisma.enums.InvitedUserStatus
-    auth_user_id: Optional[str] = None
-    name: Optional[str] = None
-    tally_understanding: Optional[dict[str, Any]] = None
-    tally_status: prisma.enums.TallyComputationStatus
-    tally_computed_at: Optional[datetime] = None
-    tally_error: Optional[str] = None
-    created_at: datetime
-    updated_at: datetime
-
-    @classmethod
-    def from_record(cls, record: InvitedUserRecord) -> InvitedUserResponse:
-        return cls.model_validate(record.model_dump())
-
-
-class InvitedUsersResponse(BaseModel):
-    invited_users: list[InvitedUserResponse]
-    pagination: Pagination
-
-
-class BulkInvitedUserRowResponse(BaseModel):
-    row_number: int
-    email: Optional[str] = None
-    name: Optional[str] = None
-    status: Literal["CREATED", "SKIPPED", "ERROR"]
-    message: str
-    invited_user: Optional[InvitedUserResponse] = None
-
-
-class BulkInvitedUsersResponse(BaseModel):
-    created_count: int
-    skipped_count: int
-    error_count: int
-    results: list[BulkInvitedUserRowResponse]
-
-    @classmethod
-    def from_result(cls, result: BulkInvitedUsersResult) -> BulkInvitedUsersResponse:
-        return cls(
-            created_count=result.created_count,
-            skipped_count=result.skipped_count,
-            error_count=result.error_count,
-            results=[
-                BulkInvitedUserRowResponse(
-                    row_number=row.row_number,
-                    email=row.email,
-                    name=row.name,
-                    status=row.status,
-                    message=row.message,
-                    invited_user=(
-                        InvitedUserResponse.from_record(row.invited_user)
-                        if row.invited_user is not None
-                        else None
-                    ),
-                )
-                for row in result.results
-            ],
-        )

autogpt_platform/backend/backend/api/features/admin/store_admin_routes.py

@@ -24,13 +24,14 @@ router = fastapi.APIRouter(
 @router.get(
     "/listings",
     summary="Get Admin Listings History",
+    response_model=store_model.StoreListingsWithVersionsResponse,
 )
 async def get_admin_listings_with_versions(
     status: typing.Optional[prisma.enums.SubmissionStatus] = None,
     search: typing.Optional[str] = None,
     page: int = 1,
     page_size: int = 20,
-) -> store_model.StoreListingsWithVersionsAdminViewResponse:
+):
     """
     Get store listings with their version history for admins.
 
@@ -44,26 +45,36 @@ async def get_admin_listings_with_versions(
         page_size: Number of items per page
 
     Returns:
-        Paginated listings with their versions
+        StoreListingsWithVersionsResponse with listings and their versions
     """
-    listings = await store_db.get_admin_listings_with_versions(
-        status=status,
-        search_query=search,
-        page=page,
-        page_size=page_size,
-    )
-    return listings
+    try:
+        listings = await store_db.get_admin_listings_with_versions(
+            status=status,
+            search_query=search,
+            page=page,
+            page_size=page_size,
+        )
+        return listings
+    except Exception as e:
+        logger.exception("Error getting admin listings with versions: %s", e)
+        return fastapi.responses.JSONResponse(
+            status_code=500,
+            content={
+                "detail": "An error occurred while retrieving listings with versions"
+            },
+        )
 
 
 @router.post(
     "/submissions/{store_listing_version_id}/review",
     summary="Review Store Submission",
+    response_model=store_model.StoreSubmission,
 )
 async def review_submission(
     store_listing_version_id: str,
     request: store_model.ReviewSubmissionRequest,
     user_id: str = fastapi.Security(autogpt_libs.auth.get_user_id),
-) -> store_model.StoreSubmissionAdminView:
+):
     """
     Review a store listing submission.
 
@@ -73,24 +84,31 @@ async def review_submission(
         user_id: Authenticated admin user performing the review
 
     Returns:
-        StoreSubmissionAdminView with updated review information
+        StoreSubmission with updated review information
     """
-    already_approved = await store_db.check_submission_already_approved(
-        store_listing_version_id=store_listing_version_id,
-    )
-    submission = await store_db.review_store_submission(
-        store_listing_version_id=store_listing_version_id,
-        is_approved=request.is_approved,
-        external_comments=request.comments,
-        internal_comments=request.internal_comments or "",
-        reviewer_id=user_id,
-    )
+    try:
+        already_approved = await store_db.check_submission_already_approved(
+            store_listing_version_id=store_listing_version_id,
+        )
+        submission = await store_db.review_store_submission(
+            store_listing_version_id=store_listing_version_id,
+            is_approved=request.is_approved,
+            external_comments=request.comments,
+            internal_comments=request.internal_comments or "",
+            reviewer_id=user_id,
+        )
 
-    state_changed = already_approved != request.is_approved
-    # Clear caches whenever approval state changes, since store visibility can change
-    if state_changed:
-        store_cache.clear_all_caches()
-    return submission
+        state_changed = already_approved != request.is_approved
+        # Clear caches when the request is approved as it updates what is shown on the store
+        if state_changed:
+            store_cache.clear_all_caches()
+        return submission
+    except Exception as e:
+        logger.exception("Error reviewing submission: %s", e)
+        return fastapi.responses.JSONResponse(
+            status_code=500,
+            content={"detail": "An error occurred while reviewing the submission"},
+        )
 
 
 @router.get(

autogpt_platform/backend/backend/api/features/admin/user_admin_routes.py

@@ -1,137 +0,0 @@
-import logging
-import math
-
-from autogpt_libs.auth import get_user_id, requires_admin_user
-from fastapi import APIRouter, File, Query, Security, UploadFile
-
-from backend.data.invited_user import (
-    bulk_create_invited_users_from_file,
-    create_invited_user,
-    list_invited_users,
-    retry_invited_user_tally,
-    revoke_invited_user,
-)
-from backend.data.tally import mask_email
-from backend.util.models import Pagination
-
-from .model import (
-    BulkInvitedUsersResponse,
-    CreateInvitedUserRequest,
-    InvitedUserResponse,
-    InvitedUsersResponse,
-)
-
-logger = logging.getLogger(__name__)
-
-
-router = APIRouter(
-    prefix="/admin",
-    tags=["users", "admin"],
-    dependencies=[Security(requires_admin_user)],
-)
-
-
-@router.get(
-    "/invited-users",
-    response_model=InvitedUsersResponse,
-    summary="List Invited Users",
-)
-async def get_invited_users(
-    admin_user_id: str = Security(get_user_id),
-    page: int = Query(1, ge=1),
-    page_size: int = Query(50, ge=1, le=200),
-) -> InvitedUsersResponse:
-    logger.info("Admin user %s requested invited users", admin_user_id)
-    invited_users, total = await list_invited_users(page=page, page_size=page_size)
-    return InvitedUsersResponse(
-        invited_users=[InvitedUserResponse.from_record(iu) for iu in invited_users],
-        pagination=Pagination(
-            total_items=total,
-            total_pages=max(1, math.ceil(total / page_size)),
-            current_page=page,
-            page_size=page_size,
-        ),
-    )
-
-
-@router.post(
-    "/invited-users",
-    response_model=InvitedUserResponse,
-    summary="Create Invited User",
-)
-async def create_invited_user_route(
-    request: CreateInvitedUserRequest,
-    admin_user_id: str = Security(get_user_id),
-) -> InvitedUserResponse:
-    logger.info(
-        "Admin user %s creating invited user for %s",
-        admin_user_id,
-        mask_email(request.email),
-    )
-    invited_user = await create_invited_user(request.email, request.name)
-    logger.info(
-        "Admin user %s created invited user %s",
-        admin_user_id,
-        invited_user.id,
-    )
-    return InvitedUserResponse.from_record(invited_user)
-
-
-@router.post(
-    "/invited-users/bulk",
-    response_model=BulkInvitedUsersResponse,
-    summary="Bulk Create Invited Users",
-    operation_id="postV2BulkCreateInvitedUsers",
-)
-async def bulk_create_invited_users_route(
-    file: UploadFile = File(...),
-    admin_user_id: str = Security(get_user_id),
-) -> BulkInvitedUsersResponse:
-    logger.info(
-        "Admin user %s bulk invited users from %s",
-        admin_user_id,
-        file.filename or "<unnamed>",
-    )
-    content = await file.read()
-    result = await bulk_create_invited_users_from_file(file.filename, content)
-    return BulkInvitedUsersResponse.from_result(result)
-
-
-@router.post(
-    "/invited-users/{invited_user_id}/revoke",
-    response_model=InvitedUserResponse,
-    summary="Revoke Invited User",
-)
-async def revoke_invited_user_route(
-    invited_user_id: str,
-    admin_user_id: str = Security(get_user_id),
-) -> InvitedUserResponse:
-    logger.info(
-        "Admin user %s revoking invited user %s", admin_user_id, invited_user_id
-    )
-    invited_user = await revoke_invited_user(invited_user_id)
-    logger.info("Admin user %s revoked invited user %s", admin_user_id, invited_user_id)
-    return InvitedUserResponse.from_record(invited_user)
-
-
-@router.post(
-    "/invited-users/{invited_user_id}/retry-tally",
-    response_model=InvitedUserResponse,
-    summary="Retry Invited User Tally",
-)
-async def retry_invited_user_tally_route(
-    invited_user_id: str,
-    admin_user_id: str = Security(get_user_id),
-) -> InvitedUserResponse:
-    logger.info(
-        "Admin user %s retrying Tally seed for invited user %s",
-        admin_user_id,
-        invited_user_id,
-    )
-    invited_user = await retry_invited_user_tally(invited_user_id)
-    logger.info(
-        "Admin user %s retried Tally seed for invited user %s",
-        admin_user_id,
-        invited_user_id,
-    )
-    return InvitedUserResponse.from_record(invited_user)

autogpt_platform/backend/backend/api/features/admin/user_admin_routes_test.py

@@ -1,168 +0,0 @@
-from datetime import datetime, timezone
-from unittest.mock import AsyncMock
-
-import fastapi
-import fastapi.testclient
-import prisma.enums
-import pytest
-import pytest_mock
-from autogpt_libs.auth.jwt_utils import get_jwt_payload
-
-from backend.data.invited_user import (
-    BulkInvitedUserRowResult,
-    BulkInvitedUsersResult,
-    InvitedUserRecord,
-)
-
-from .user_admin_routes import router as user_admin_router
-
-app = fastapi.FastAPI()
-app.include_router(user_admin_router)
-
-client = fastapi.testclient.TestClient(app)
-
-
-@pytest.fixture(autouse=True)
-def setup_app_admin_auth(mock_jwt_admin):
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_admin["get_jwt_payload"]
-    yield
-    app.dependency_overrides.clear()
-
-
-def _sample_invited_user() -> InvitedUserRecord:
-    now = datetime.now(timezone.utc)
-    return InvitedUserRecord(
-        id="invite-1",
-        email="invited@example.com",
-        status=prisma.enums.InvitedUserStatus.INVITED,
-        auth_user_id=None,
-        name="Invited User",
-        tally_understanding=None,
-        tally_status=prisma.enums.TallyComputationStatus.PENDING,
-        tally_computed_at=None,
-        tally_error=None,
-        created_at=now,
-        updated_at=now,
-    )
-
-
-def _sample_bulk_invited_users_result() -> BulkInvitedUsersResult:
-    return BulkInvitedUsersResult(
-        created_count=1,
-        skipped_count=1,
-        error_count=0,
-        results=[
-            BulkInvitedUserRowResult(
-                row_number=1,
-                email="invited@example.com",
-                name=None,
-                status="CREATED",
-                message="Invite created",
-                invited_user=_sample_invited_user(),
-            ),
-            BulkInvitedUserRowResult(
-                row_number=2,
-                email="duplicate@example.com",
-                name=None,
-                status="SKIPPED",
-                message="An invited user with this email already exists",
-                invited_user=None,
-            ),
-        ],
-    )
-
-
-def test_get_invited_users(
-    mocker: pytest_mock.MockerFixture,
-) -> None:
-    mocker.patch(
-        "backend.api.features.admin.user_admin_routes.list_invited_users",
-        AsyncMock(return_value=([_sample_invited_user()], 1)),
-    )
-
-    response = client.get("/admin/invited-users")
-
-    assert response.status_code == 200
-    data = response.json()
-    assert len(data["invited_users"]) == 1
-    assert data["invited_users"][0]["email"] == "invited@example.com"
-    assert data["invited_users"][0]["status"] == "INVITED"
-    assert data["pagination"]["total_items"] == 1
-    assert data["pagination"]["current_page"] == 1
-    assert data["pagination"]["page_size"] == 50
-
-
-def test_create_invited_user(
-    mocker: pytest_mock.MockerFixture,
-) -> None:
-    mocker.patch(
-        "backend.api.features.admin.user_admin_routes.create_invited_user",
-        AsyncMock(return_value=_sample_invited_user()),
-    )
-
-    response = client.post(
-        "/admin/invited-users",
-        json={"email": "invited@example.com", "name": "Invited User"},
-    )
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["email"] == "invited@example.com"
-    assert data["name"] == "Invited User"
-
-
-def test_bulk_create_invited_users(
-    mocker: pytest_mock.MockerFixture,
-) -> None:
-    mocker.patch(
-        "backend.api.features.admin.user_admin_routes.bulk_create_invited_users_from_file",
-        AsyncMock(return_value=_sample_bulk_invited_users_result()),
-    )
-
-    response = client.post(
-        "/admin/invited-users/bulk",
-        files={
-            "file": ("invites.txt", b"invited@example.com\nduplicate@example.com\n")
-        },
-    )
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["created_count"] == 1
-    assert data["skipped_count"] == 1
-    assert data["results"][0]["status"] == "CREATED"
-    assert data["results"][1]["status"] == "SKIPPED"
-
-
-def test_revoke_invited_user(
-    mocker: pytest_mock.MockerFixture,
-) -> None:
-    revoked = _sample_invited_user().model_copy(
-        update={"status": prisma.enums.InvitedUserStatus.REVOKED}
-    )
-    mocker.patch(
-        "backend.api.features.admin.user_admin_routes.revoke_invited_user",
-        AsyncMock(return_value=revoked),
-    )
-
-    response = client.post("/admin/invited-users/invite-1/revoke")
-
-    assert response.status_code == 200
-    assert response.json()["status"] == "REVOKED"
-
-
-def test_retry_invited_user_tally(
-    mocker: pytest_mock.MockerFixture,
-) -> None:
-    retried = _sample_invited_user().model_copy(
-        update={"tally_status": prisma.enums.TallyComputationStatus.RUNNING}
-    )
-    mocker.patch(
-        "backend.api.features.admin.user_admin_routes.retry_invited_user_tally",
-        AsyncMock(return_value=retried),
-    )
-
-    response = client.post("/admin/invited-users/invite-1/retry-tally")
-
-    assert response.status_code == 200
-    assert response.json()["tally_status"] == "RUNNING"

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

@@ -1,17 +1,15 @@
 import logging
 from dataclasses import dataclass
+from datetime import datetime, timedelta, timezone
 from difflib import SequenceMatcher
-from typing import Any, Sequence, get_args, get_origin
+from typing import Sequence
 
 import prisma
-from prisma.enums import ContentType
-from prisma.models import mv_suggested_blocks
 
 import backend.api.features.library.db as library_db
 import backend.api.features.library.model as library_model
 import backend.api.features.store.db as store_db
 import backend.api.features.store.model as store_model
-from backend.api.features.store.hybrid_search import unified_hybrid_search
 from backend.blocks import load_all_blocks
 from backend.blocks._base import (
     AnyBlockSchema,
@@ -21,6 +19,7 @@ from backend.blocks._base import (
     BlockType,
 )
 from backend.blocks.llm import LlmModel
+from backend.data.db import query_raw_with_schema
 from backend.integrations.providers import ProviderName
 from backend.util.cache import cached
 from backend.util.models import Pagination
@@ -43,16 +42,6 @@ MAX_LIBRARY_AGENT_RESULTS = 100
 MAX_MARKETPLACE_AGENT_RESULTS = 100
 MIN_SCORE_FOR_FILTERED_RESULTS = 10.0
 
-# Boost blocks over marketplace agents in search results
-BLOCK_SCORE_BOOST = 50.0
-
-# Block IDs to exclude from search results
-EXCLUDED_BLOCK_IDS = frozenset(
-    {
-        "e189baac-8c20-45a1-94a7-55177ea42565",  # AgentExecutorBlock
-    }
-)
-
 SearchResultItem = BlockInfo | library_model.LibraryAgent | store_model.StoreAgent
 
 
@@ -75,8 +64,8 @@ def get_block_categories(category_blocks: int = 3) -> list[BlockCategoryResponse
 
     for block_type in load_all_blocks().values():
         block: AnyBlockSchema = block_type()
-        # Skip disabled and excluded blocks
-        if block.disabled or block.id in EXCLUDED_BLOCK_IDS:
+        # Skip disabled blocks
+        if block.disabled:
             continue
         # Skip blocks that don't have categories (all should have at least one)
         if not block.categories:
@@ -127,9 +116,6 @@ def get_blocks(
         # Skip disabled blocks
         if block.disabled:
             continue
-        # Skip excluded blocks
-        if block.id in EXCLUDED_BLOCK_IDS:
-            continue
         # Skip blocks that don't match the category
         if category and category not in {c.name.lower() for c in block.categories}:
             continue
@@ -269,25 +255,14 @@ async def _build_cached_search_results(
         "my_agents": 0,
     }
 
-    # Use hybrid search when query is present, otherwise list all blocks
-    if (include_blocks or include_integrations) and normalized_query:
-        block_results, block_total, integration_total = await _hybrid_search_blocks(
-            query=search_query,
-            include_blocks=include_blocks,
-            include_integrations=include_integrations,
-        )
-        scored_items.extend(block_results)
-        total_items["blocks"] = block_total
-        total_items["integrations"] = integration_total
-    elif include_blocks or include_integrations:
-        # No query - list all blocks using in-memory approach
-        block_results, block_total, integration_total = _collect_block_results(
-            include_blocks=include_blocks,
-            include_integrations=include_integrations,
-        )
-        scored_items.extend(block_results)
-        total_items["blocks"] = block_total
-        total_items["integrations"] = integration_total
+    block_results, block_total, integration_total = _collect_block_results(
+        normalized_query=normalized_query,
+        include_blocks=include_blocks,
+        include_integrations=include_integrations,
+    )
+    scored_items.extend(block_results)
+    total_items["blocks"] = block_total
+    total_items["integrations"] = integration_total
 
     if include_library_agents:
         library_response = await library_db.list_library_agents(
@@ -332,14 +307,10 @@ async def _build_cached_search_results(
 
 def _collect_block_results(
     *,
+    normalized_query: str,
     include_blocks: bool,
     include_integrations: bool,
 ) -> tuple[list[_ScoredItem], int, int]:
-    """
-    Collect all blocks for listing (no search query).
-
-    All blocks get BLOCK_SCORE_BOOST to prioritize them over marketplace agents.
-    """
     results: list[_ScoredItem] = []
     block_count = 0
     integration_count = 0
@@ -352,10 +323,6 @@ def _collect_block_results(
         if block.disabled:
             continue
 
-        # Skip excluded blocks
-        if block.id in EXCLUDED_BLOCK_IDS:
-            continue
-
         block_info = block.get_info()
         credentials = list(block.input_schema.get_credentials_fields().values())
         is_integration = len(credentials) > 0
@@ -365,6 +332,10 @@ def _collect_block_results(
         if not is_integration and not include_blocks:
             continue
 
+        score = _score_block(block, block_info, normalized_query)
+        if not _should_include_item(score, normalized_query):
+            continue
+
         filter_type: FilterType = "integrations" if is_integration else "blocks"
         if is_integration:
             integration_count += 1
@@ -375,122 +346,8 @@ def _collect_block_results(
             _ScoredItem(
                 item=block_info,
                 filter_type=filter_type,
-                score=BLOCK_SCORE_BOOST,
-                sort_key=block_info.name.lower(),
-            )
-        )
-
-    return results, block_count, integration_count
-
-
-async def _hybrid_search_blocks(
-    *,
-    query: str,
-    include_blocks: bool,
-    include_integrations: bool,
-) -> tuple[list[_ScoredItem], int, int]:
-    """
-    Search blocks using hybrid search with builder-specific filtering.
-
-    Uses unified_hybrid_search for semantic + lexical search, then applies
-    post-filtering for block/integration types and scoring adjustments.
-
-    Scoring:
-        - Base: hybrid relevance score (0-1) scaled to 0-100, plus BLOCK_SCORE_BOOST
-          to prioritize blocks over marketplace agents in combined results
-        - +30 for exact name match, +15 for prefix name match
-        - +20 if the block has an LlmModel field and the query matches an LLM model name
-
-    Args:
-        query: The search query string
-        include_blocks: Whether to include regular blocks
-        include_integrations: Whether to include integration blocks
-
-    Returns:
-        Tuple of (scored_items, block_count, integration_count)
-    """
-    results: list[_ScoredItem] = []
-    block_count = 0
-    integration_count = 0
-
-    if not include_blocks and not include_integrations:
-        return results, block_count, integration_count
-
-    normalized_query = query.strip().lower()
-
-    # Fetch more results to account for post-filtering
-    search_results, _ = await unified_hybrid_search(
-        query=query,
-        content_types=[ContentType.BLOCK],
-        page=1,
-        page_size=150,
-        min_score=0.10,
-    )
-
-    # Load all blocks for getting BlockInfo
-    all_blocks = load_all_blocks()
-
-    for result in search_results:
-        block_id = result["content_id"]
-
-        # Skip excluded blocks
-        if block_id in EXCLUDED_BLOCK_IDS:
-            continue
-
-        metadata = result.get("metadata", {})
-        hybrid_score = result.get("relevance", 0.0)
-
-        # Get the actual block class
-        if block_id not in all_blocks:
-            continue
-
-        block_cls = all_blocks[block_id]
-        block: AnyBlockSchema = block_cls()
-
-        if block.disabled:
-            continue
-
-        # Check block/integration filter using metadata
-        is_integration = metadata.get("is_integration", False)
-
-        if is_integration and not include_integrations:
-            continue
-        if not is_integration and not include_blocks:
-            continue
-
-        # Get block info
-        block_info = block.get_info()
-
-        # Calculate final score: scale hybrid score and add builder-specific bonuses
-        # Hybrid scores are 0-1, builder scores were 0-200+
-        # Add BLOCK_SCORE_BOOST to prioritize blocks over marketplace agents
-        final_score = hybrid_score * 100 + BLOCK_SCORE_BOOST
-
-        # Add LLM model match bonus
-        has_llm_field = metadata.get("has_llm_model_field", False)
-        if has_llm_field and _matches_llm_model(block.input_schema, normalized_query):
-            final_score += 20
-
-        # Add exact/prefix match bonus for deterministic tie-breaking
-        name = block_info.name.lower()
-        if name == normalized_query:
-            final_score += 30
-        elif name.startswith(normalized_query):
-            final_score += 15
-
-        # Track counts
-        filter_type: FilterType = "integrations" if is_integration else "blocks"
-        if is_integration:
-            integration_count += 1
-        else:
-            block_count += 1
-
-        results.append(
-            _ScoredItem(
-                item=block_info,
-                filter_type=filter_type,
-                score=final_score,
-                sort_key=name,
+                score=score,
+                sort_key=_get_item_name(block_info),
             )
         )
 
@@ -615,8 +472,6 @@ async def _get_static_counts():
         block: AnyBlockSchema = block_type()
         if block.disabled:
             continue
-        if block.id in EXCLUDED_BLOCK_IDS:
-            continue
 
         all_blocks += 1
 
@@ -643,25 +498,47 @@ async def _get_static_counts():
     }
 
 
-def _contains_type(annotation: Any, target: type) -> bool:
-    """Check if an annotation is or contains the target type (handles Optional/Union/Annotated)."""
-    if annotation is target:
-        return True
-    origin = get_origin(annotation)
-    if origin is None:
-        return False
-    return any(_contains_type(arg, target) for arg in get_args(annotation))
-
-
 def _matches_llm_model(schema_cls: type[BlockSchema], query: str) -> bool:
     for field in schema_cls.model_fields.values():
-        if _contains_type(field.annotation, LlmModel):
+        if field.annotation == LlmModel:
             # Check if query matches any value in llm_models
             if any(query in name for name in llm_models):
                 return True
     return False
 
 
+def _score_block(
+    block: AnyBlockSchema,
+    block_info: BlockInfo,
+    normalized_query: str,
+) -> float:
+    if not normalized_query:
+        return 0.0
+
+    name = block_info.name.lower()
+    description = block_info.description.lower()
+    score = _score_primary_fields(name, description, normalized_query)
+
+    category_text = " ".join(
+        category.get("category", "").lower() for category in block_info.categories
+    )
+    score += _score_additional_field(category_text, normalized_query, 12, 6)
+
+    credentials_info = block.input_schema.get_credentials_fields_info().values()
+    provider_names = [
+        provider.value.lower()
+        for info in credentials_info
+        for provider in info.provider
+    ]
+    provider_text = " ".join(provider_names)
+    score += _score_additional_field(provider_text, normalized_query, 15, 6)
+
+    if _matches_llm_model(block.input_schema, normalized_query):
+        score += 20
+
+    return score
+
+
 def _score_library_agent(
     agent: library_model.LibraryAgent,
     normalized_query: str,
@@ -768,20 +645,31 @@ def _get_all_providers() -> dict[ProviderName, Provider]:
     return providers
 
 
-@cached(ttl_seconds=3600, shared_cache=True)
+@cached(ttl_seconds=3600)
 async def get_suggested_blocks(count: int = 5) -> list[BlockInfo]:
-    """Return the most-executed blocks from the last 14 days.
+    suggested_blocks = []
+    # Sum the number of executions for each block type
+    # Prisma cannot group by nested relations, so we do a raw query
+    # Calculate the cutoff timestamp
+    timestamp_threshold = datetime.now(timezone.utc) - timedelta(days=30)
 
-    Queries the mv_suggested_blocks materialized view (refreshed hourly via pg_cron)
-    and returns the top `count` blocks sorted by execution count, excluding
-    Input/Output/Agent block types and blocks in EXCLUDED_BLOCK_IDS.
-    """
-    results = await mv_suggested_blocks.prisma().find_many()
+    results = await query_raw_with_schema(
+        """
+        SELECT
+            agent_node."agentBlockId" AS block_id,
+            COUNT(execution.id) AS execution_count
+        FROM {schema_prefix}"AgentNodeExecution" execution
+        JOIN {schema_prefix}"AgentNode" agent_node ON execution."agentNodeId" = agent_node.id
+        WHERE execution."endedTime" >= $1::timestamp
+        GROUP BY agent_node."agentBlockId"
+        ORDER BY execution_count DESC;
+        """,
+        timestamp_threshold,
+    )
 
     # Get the top blocks based on execution count
-    # But ignore Input, Output, Agent, and excluded blocks
+    # But ignore Input and Output blocks
     blocks: list[tuple[BlockInfo, int]] = []
-    execution_counts = {row.block_id: row.execution_count for row in results}
 
     for block_type in load_all_blocks().values():
         block: AnyBlockSchema = block_type()
@@ -791,9 +679,11 @@ async def get_suggested_blocks(count: int = 5) -> list[BlockInfo]:
             BlockType.AGENT,
         ):
             continue
-        if block.id in EXCLUDED_BLOCK_IDS:
-            continue
-        execution_count = execution_counts.get(block.id, 0)
+        # Find the execution count for this block
+        execution_count = next(
+            (row["execution_count"] for row in results if row["block_id"] == block.id),
+            0,
+        )
         blocks.append((block.get_info(), execution_count))
     # Sort blocks by execution count
     blocks.sort(key=lambda x: x[1], reverse=True)

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

@@ -27,6 +27,7 @@ class SearchEntry(BaseModel):
 
 # Suggestions
 class SuggestionsResponse(BaseModel):
+    otto_suggestions: list[str]
     recent_searches: list[SearchEntry]
     providers: list[ProviderName]
     top_blocks: list[BlockInfo]

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

@@ -1,5 +1,5 @@
 import logging
-from typing import Annotated, Sequence, cast, get_args
+from typing import Annotated, Sequence
 
 import fastapi
 from autogpt_libs.auth.dependencies import get_user_id, requires_user
@@ -10,8 +10,6 @@ from backend.util.models import Pagination
 from . import db as builder_db
 from . import model as builder_model
 
-VALID_FILTER_VALUES = get_args(builder_model.FilterType)
-
 logger = logging.getLogger(__name__)
 
 router = fastapi.APIRouter(
@@ -51,6 +49,11 @@ async def get_suggestions(
     Get all suggestions for the Blocks Menu.
     """
     return builder_model.SuggestionsResponse(
+        otto_suggestions=[
+            "What blocks do I need to get started?",
+            "Help me create a list",
+            "Help me feed my data to Google Maps",
+        ],
         recent_searches=await builder_db.get_recent_searches(user_id),
         providers=[
             ProviderName.TWITTER,
@@ -148,7 +151,7 @@ async def get_providers(
 async def search(
     user_id: Annotated[str, fastapi.Security(get_user_id)],
     search_query: Annotated[str | None, fastapi.Query()] = None,
-    filter: Annotated[str | None, fastapi.Query()] = None,
+    filter: Annotated[list[builder_model.FilterType] | None, fastapi.Query()] = None,
     search_id: Annotated[str | None, fastapi.Query()] = None,
     by_creator: Annotated[list[str] | None, fastapi.Query()] = None,
     page: Annotated[int, fastapi.Query()] = 1,
@@ -157,20 +160,9 @@ async def search(
     """
     Search for blocks (including integrations), marketplace agents, and user library agents.
     """
-    # Parse and validate filter parameter
-    filters: list[builder_model.FilterType]
-    if filter:
-        filter_values = [f.strip() for f in filter.split(",")]
-        invalid_filters = [f for f in filter_values if f not in VALID_FILTER_VALUES]
-        if invalid_filters:
-            raise fastapi.HTTPException(
-                status_code=400,
-                detail=f"Invalid filter value(s): {', '.join(invalid_filters)}. "
-                f"Valid values are: {', '.join(VALID_FILTER_VALUES)}",
-            )
-        filters = cast(list[builder_model.FilterType], filter_values)
-    else:
-        filters = [
+    # If no filters are provided, then we will return all types
+    if not filter:
+        filter = [
             "blocks",
             "integrations",
             "marketplace_agents",
@@ -182,7 +174,7 @@ async def search(
     cached_results = await builder_db.get_sorted_search_results(
         user_id=user_id,
         search_query=search_query,
-        filters=filters,
+        filters=filter,
         by_creator=by_creator,
     )
 
@@ -204,7 +196,7 @@ async def search(
         user_id,
         builder_model.SearchEntry(
             search_query=search_query,
-            filter=filters,
+            filter=filter,
             by_creator=by_creator,
             search_id=search_id,
         ),

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

@@ -0,0 +1,368 @@
+"""Redis Streams consumer for operation completion messages.
+
+This module provides a consumer (ChatCompletionConsumer) that listens for
+completion notifications (OperationCompleteMessage) from external services
+(like Agent Generator) and triggers the appropriate stream registry and
+chat service updates via process_operation_success/process_operation_failure.
+
+Why Redis Streams instead of RabbitMQ?
+--------------------------------------
+While the project typically uses RabbitMQ for async task queues (e.g., execution
+queue), Redis Streams was chosen for chat completion notifications because:
+
+1. **Unified Infrastructure**: The SSE reconnection feature already uses Redis
+   Streams (via stream_registry) for message persistence and replay. Using Redis
+   Streams for completion notifications keeps all chat streaming infrastructure
+   in one system, simplifying operations and reducing cross-system coordination.
+
+2. **Message Replay**: Redis Streams support XREAD with arbitrary message IDs,
+   allowing consumers to replay missed messages after reconnection. This aligns
+   with the SSE reconnection pattern where clients can resume from last_message_id.
+
+3. **Consumer Groups with XAUTOCLAIM**: Redis consumer groups provide automatic
+   load balancing across pods with explicit message claiming (XAUTOCLAIM) for
+   recovering from dead consumers - ideal for the completion callback pattern.
+
+4. **Lower Latency**: For real-time SSE updates, Redis (already in-memory for
+   stream_registry) provides lower latency than an additional RabbitMQ hop.
+
+5. **Atomicity with Task State**: Completion processing often needs to update
+   task metadata stored in Redis. Keeping both in Redis enables simpler
+   transactional semantics without distributed coordination.
+
+The consumer uses Redis Streams with consumer groups for reliable message
+processing across multiple platform pods, with XAUTOCLAIM for reclaiming
+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
+
+from backend.data.redis_client import get_redis_async
+
+from . import stream_registry
+from .completion_handler import process_operation_failure, process_operation_success
+from .config import ChatConfig
+
+logger = logging.getLogger(__name__)
+config = ChatConfig()
+
+
+class OperationCompleteMessage(BaseModel):
+    """Message format for operation completion notifications."""
+
+    operation_id: str
+    task_id: str
+    success: bool
+    result: dict | str | None = None
+    error: str | None = None
+
+
+class ChatCompletionConsumer:
+    """Consumer for chat operation completion messages from Redis Streams.
+
+    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.
+    """
+
+    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:
+        """Start the completion consumer."""
+        if self._running:
+            logger.warning("Completion consumer already running")
+            return
+
+        # Create consumer group if it doesn't exist
+        try:
+            redis = await get_redis_async()
+            await redis.xgroup_create(
+                config.stream_completion_name,
+                config.stream_consumer_group,
+                id="0",
+                mkstream=True,
+            )
+            logger.info(
+                f"Created consumer group '{config.stream_consumer_group}' "
+                f"on stream '{config.stream_completion_name}'"
+            )
+        except ResponseError as e:
+            if "BUSYGROUP" in str(e):
+                logger.debug(
+                    f"Consumer group '{config.stream_consumer_group}' already exists"
+                )
+            else:
+                raise
+
+        self._running = True
+        self._consumer_task = asyncio.create_task(self._consume_messages())
+        logger.info(
+            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
+
+        if self._consumer_task:
+            self._consumer_task.cancel()
+            try:
+                await self._consumer_task
+            except asyncio.CancelledError:
+                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:
+        """Main message consumption loop with retry logic."""
+        max_retries = 10
+        retry_delay = 5  # seconds
+        retry_count = 0
+        block_timeout = 5000  # milliseconds
+
+        while self._running and retry_count < max_retries:
+            try:
+                redis = await get_redis_async()
+
+                # Reset retry count on successful connection
+                retry_count = 0
+
+                while self._running:
+                    # First, claim any stale pending messages from dead consumers
+                    # Redis does NOT auto-redeliver pending messages; we must explicitly
+                    # claim them using XAUTOCLAIM
+                    try:
+                        claimed_result = await redis.xautoclaim(
+                            name=config.stream_completion_name,
+                            groupname=config.stream_consumer_group,
+                            consumername=self._consumer_name,
+                            min_idle_time=config.stream_claim_min_idle_ms,
+                            start_id="0-0",
+                            count=10,
+                        )
+                        # xautoclaim returns: (next_start_id, [(id, data), ...], [deleted_ids])
+                        if claimed_result and len(claimed_result) >= 2:
+                            claimed_entries = claimed_result[1]
+                            if claimed_entries:
+                                logger.info(
+                                    f"Claimed {len(claimed_entries)} stale pending messages"
+                                )
+                                for entry_id, data in claimed_entries:
+                                    if not self._running:
+                                        return
+                                    await self._process_entry(redis, entry_id, data)
+                    except Exception as e:
+                        logger.warning(f"XAUTOCLAIM failed (non-fatal): {e}")
+
+                    # Read new messages from the stream
+                    messages = await redis.xreadgroup(
+                        groupname=config.stream_consumer_group,
+                        consumername=self._consumer_name,
+                        streams={config.stream_completion_name: ">"},
+                        block=block_timeout,
+                        count=10,
+                    )
+
+                    if not messages:
+                        continue
+
+                    for stream_name, entries in messages:
+                        for entry_id, data in entries:
+                            if not self._running:
+                                return
+                            await self._process_entry(redis, entry_id, data)
+
+            except asyncio.CancelledError:
+                logger.info("Consumer cancelled")
+                return
+            except Exception as e:
+                retry_count += 1
+                logger.error(
+                    f"Consumer error (retry {retry_count}/{max_retries}): {e}",
+                    exc_info=True,
+                )
+                if self._running and retry_count < max_retries:
+                    await asyncio.sleep(retry_delay)
+                else:
+                    logger.error("Max retries reached, stopping consumer")
+                    return
+
+    async def _process_entry(
+        self, redis: Any, entry_id: str, data: dict[str, Any]
+    ) -> None:
+        """Process a single stream entry and acknowledge it on success.
+
+        Args:
+            redis: Redis client connection
+            entry_id: The stream entry ID
+            data: The entry data dict
+        """
+        try:
+            # Handle the message
+            message_data = data.get("data")
+            if message_data:
+                await self._handle_message(
+                    message_data.encode()
+                    if isinstance(message_data, str)
+                    else message_data
+                )
+
+            # Acknowledge the message after successful processing
+            await redis.xack(
+                config.stream_completion_name,
+                config.stream_consumer_group,
+                entry_id,
+            )
+        except Exception as e:
+            logger.error(
+                f"Error processing completion message {entry_id}: {e}",
+                exc_info=True,
+            )
+            # Message remains in pending state and will be claimed by
+            # XAUTOCLAIM after min_idle_time expires
+
+    async def _handle_message(self, body: bytes) -> None:
+        """Handle a completion message using our own Prisma client."""
+        try:
+            data = orjson.loads(body)
+            message = OperationCompleteMessage(**data)
+        except Exception as e:
+            logger.error(f"Failed to parse completion message: {e}")
+            return
+
+        logger.info(
+            f"[COMPLETION] Received completion for operation {message.operation_id} "
+            f"(task_id={message.task_id}, success={message.success})"
+        )
+
+        # Find task in registry
+        task = await stream_registry.find_task_by_operation_id(message.operation_id)
+        if task is None:
+            task = await stream_registry.get_task(message.task_id)
+
+        if task is None:
+            logger.warning(
+                f"[COMPLETION] Task not found for operation {message.operation_id} "
+                f"(task_id={message.task_id})"
+            )
+            return
+
+        logger.info(
+            f"[COMPLETION] Found task: task_id={task.task_id}, "
+            f"session_id={task.session_id}, tool_call_id={task.tool_call_id}"
+        )
+
+        # Guard against empty task fields
+        if not task.task_id or not task.session_id or not task.tool_call_id:
+            logger.error(
+                f"[COMPLETION] Task has empty critical fields! "
+                f"task_id={task.task_id!r}, session_id={task.session_id!r}, "
+                f"tool_call_id={task.tool_call_id!r}"
+            )
+            return
+
+        if message.success:
+            await self._handle_success(task, message)
+        else:
+            await self._handle_failure(task, message)
+
+    async def _handle_success(
+        self,
+        task: stream_registry.ActiveTask,
+        message: OperationCompleteMessage,
+    ) -> None:
+        """Handle successful operation completion."""
+        prisma = await self._ensure_prisma()
+        await process_operation_success(task, message.result, prisma)
+
+    async def _handle_failure(
+        self,
+        task: stream_registry.ActiveTask,
+        message: OperationCompleteMessage,
+    ) -> None:
+        """Handle failed operation completion."""
+        prisma = await self._ensure_prisma()
+        await process_operation_failure(task, message.error, prisma)
+
+
+# Module-level consumer instance
+_consumer: ChatCompletionConsumer | None = None
+
+
+async def start_completion_consumer() -> None:
+    """Start the global completion consumer."""
+    global _consumer
+    if _consumer is None:
+        _consumer = ChatCompletionConsumer()
+    await _consumer.start()
+
+
+async def stop_completion_consumer() -> None:
+    """Stop the global completion consumer."""
+    global _consumer
+    if _consumer:
+        await _consumer.stop()
+        _consumer = None
+
+
+async def publish_operation_complete(
+    operation_id: str,
+    task_id: str,
+    success: bool,
+    result: dict | str | None = None,
+    error: str | None = None,
+) -> None:
+    """Publish an operation completion message to Redis Streams.
+
+    Args:
+        operation_id: The operation ID that completed.
+        task_id: The task ID associated with the operation.
+        success: Whether the operation succeeded.
+        result: The result data (for success).
+        error: The error message (for failure).
+    """
+    message = OperationCompleteMessage(
+        operation_id=operation_id,
+        task_id=task_id,
+        success=success,
+        result=result,
+        error=error,
+    )
+
+    redis = await get_redis_async()
+    await redis.xadd(
+        config.stream_completion_name,
+        {"data": message.model_dump_json()},
+        maxlen=config.stream_max_length,
+    )
+    logger.info(f"Published completion for operation {operation_id}")

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

@@ -0,0 +1,344 @@
+"""Shared completion handling for operation success and failure.
+
+This module provides common logic for handling operation completion from both:
+- The Redis Streams consumer (completion_consumer.py)
+- The HTTP webhook endpoint (routes.py)
+"""
+
+import logging
+from typing import Any
+
+import orjson
+from prisma import Prisma
+
+from . import service as chat_service
+from . import stream_registry
+from .response_model import StreamError, StreamToolOutputAvailable
+from .tools.models import ErrorResponse
+
+logger = logging.getLogger(__name__)
+
+# Tools that produce agent_json that needs to be saved to library
+AGENT_GENERATION_TOOLS = {"create_agent", "edit_agent"}
+
+# Keys that should be stripped from agent_json when returning in error responses
+SENSITIVE_KEYS = frozenset(
+    {
+        "api_key",
+        "apikey",
+        "api_secret",
+        "password",
+        "secret",
+        "credentials",
+        "credential",
+        "token",
+        "access_token",
+        "refresh_token",
+        "private_key",
+        "privatekey",
+        "auth",
+        "authorization",
+    }
+)
+
+
+def _sanitize_agent_json(obj: Any) -> Any:
+    """Recursively sanitize agent_json by removing sensitive keys.
+
+    Args:
+        obj: The object to sanitize (dict, list, or primitive)
+
+    Returns:
+        Sanitized copy with sensitive keys removed/redacted
+    """
+    if isinstance(obj, dict):
+        return {
+            k: "[REDACTED]" if k.lower() in SENSITIVE_KEYS else _sanitize_agent_json(v)
+            for k, v in obj.items()
+        }
+    elif isinstance(obj, list):
+        return [_sanitize_agent_json(item) for item in obj]
+    else:
+        return obj
+
+
+class ToolMessageUpdateError(Exception):
+    """Raised when updating a tool message in the database fails."""
+
+    pass
+
+
+async def _update_tool_message(
+    session_id: str,
+    tool_call_id: str,
+    content: str,
+    prisma_client: Prisma | None,
+) -> None:
+    """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. The caller should
+            handle this to avoid marking the task as completed with inconsistent state.
+    """
+    try:
+        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)
+        raise ToolMessageUpdateError(
+            f"Failed to update tool message for tool_call_id={tool_call_id}: {e}"
+        ) from e
+
+
+def serialize_result(result: dict | list | str | int | float | bool | None) -> str:
+    """Serialize result to JSON string with sensible defaults.
+
+    Args:
+        result: The result to serialize. Can be a dict, list, string,
+            number, boolean, or None.
+
+    Returns:
+        JSON string representation of the result. Returns '{"status": "completed"}'
+        only when result is explicitly None.
+    """
+    if isinstance(result, str):
+        return result
+    if result is None:
+        return '{"status": "completed"}'
+    return orjson.dumps(result).decode("utf-8")
+
+
+async def _save_agent_from_result(
+    result: dict[str, Any],
+    user_id: str | None,
+    tool_name: str,
+) -> dict[str, Any]:
+    """Save agent to library if result contains agent_json.
+
+    Args:
+        result: The result dict that may contain agent_json
+        user_id: The user ID to save the agent for
+        tool_name: The tool name (create_agent or edit_agent)
+
+    Returns:
+        Updated result dict with saved agent details, or original result if no agent_json
+    """
+    if not user_id:
+        logger.warning("[COMPLETION] Cannot save agent: no user_id in task")
+        return result
+
+    agent_json = result.get("agent_json")
+    if not agent_json:
+        logger.warning(
+            f"[COMPLETION] {tool_name} completed but no agent_json in result"
+        )
+        return result
+
+    try:
+        from .tools.agent_generator import save_agent_to_library
+
+        is_update = tool_name == "edit_agent"
+        created_graph, library_agent = await save_agent_to_library(
+            agent_json, user_id, is_update=is_update
+        )
+
+        logger.info(
+            f"[COMPLETION] Saved agent '{created_graph.name}' to library "
+            f"(graph_id={created_graph.id}, library_agent_id={library_agent.id})"
+        )
+
+        # Return a response similar to AgentSavedResponse
+        return {
+            "type": "agent_saved",
+            "message": f"Agent '{created_graph.name}' has been saved to your library!",
+            "agent_id": created_graph.id,
+            "agent_name": created_graph.name,
+            "library_agent_id": library_agent.id,
+            "library_agent_link": f"/library/agents/{library_agent.id}",
+            "agent_page_link": f"/build?flowID={created_graph.id}",
+        }
+    except Exception as e:
+        logger.error(
+            f"[COMPLETION] Failed to save agent to library: {e}",
+            exc_info=True,
+        )
+        # Return error but don't fail the whole operation
+        # Sanitize agent_json to remove sensitive keys before returning
+        return {
+            "type": "error",
+            "message": f"Agent was generated but failed to save: {str(e)}",
+            "error": str(e),
+            "agent_json": _sanitize_agent_json(agent_json),
+        }
+
+
+async def process_operation_success(
+    task: stream_registry.ActiveTask,
+    result: dict | str | None,
+    prisma_client: Prisma | None = None,
+) -> None:
+    """Handle successful operation completion.
+
+    Publishes the result to the stream registry, updates the database,
+    generates LLM continuation, and marks the task as completed.
+
+    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 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):
+        result = await _save_agent_from_result(result, task.user_id, task.tool_name)
+
+    # Serialize result for output (only substitute default when result is exactly None)
+    result_output = result if result is not None else {"status": "completed"}
+    output_str = (
+        result_output
+        if isinstance(result_output, str)
+        else orjson.dumps(result_output).decode("utf-8")
+    )
+
+    # Publish result to stream registry
+    await stream_registry.publish_chunk(
+        task.task_id,
+        StreamToolOutputAvailable(
+            toolCallId=task.tool_call_id,
+            toolName=task.tool_name,
+            output=output_str,
+            success=True,
+        ),
+    )
+
+    # Update pending operation in database
+    # If this fails, we must not continue to mark the task as completed
+    result_str = serialize_result(result)
+    try:
+        await _update_tool_message(
+            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
+        logger.error(
+            f"[COMPLETION] DB update failed for task {task.task_id}, "
+            "marking as failed instead of completed"
+        )
+        await stream_registry.publish_chunk(
+            task.task_id,
+            StreamError(errorText="Failed to save operation result to database"),
+        )
+        await stream_registry.mark_task_completed(task.task_id, status="failed")
+        raise
+
+    # Generate LLM continuation with streaming
+    try:
+        await chat_service._generate_llm_continuation_with_streaming(
+            session_id=task.session_id,
+            user_id=task.user_id,
+            task_id=task.task_id,
+        )
+    except Exception as e:
+        logger.error(
+            f"[COMPLETION] Failed to generate LLM continuation: {e}",
+            exc_info=True,
+        )
+
+    # Mark task as completed and release Redis lock
+    await stream_registry.mark_task_completed(task.task_id, status="completed")
+    try:
+        await chat_service._mark_operation_completed(task.tool_call_id)
+    except Exception as e:
+        logger.error(f"[COMPLETION] Failed to mark operation completed: {e}")
+
+    logger.info(
+        f"[COMPLETION] Successfully processed completion for task {task.task_id}"
+    )
+
+
+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.
+
+    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"
+
+    # Publish error to stream registry
+    await stream_registry.publish_chunk(
+        task.task_id,
+        StreamError(errorText=error_msg),
+    )
+
+    # Update pending operation with error
+    # If this fails, we still continue to mark the task as failed
+    error_response = ErrorResponse(
+        message=error_msg,
+        error=error,
+    )
+    try:
+        await _update_tool_message(
+            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
+        logger.error(
+            f"[COMPLETION] DB update failed while processing failure for task {task.task_id}, "
+            "continuing with cleanup"
+        )
+
+    # Mark task as failed and release Redis lock
+    await stream_registry.mark_task_completed(task.task_id, status="failed")
+    try:
+        await chat_service._mark_operation_completed(task.tool_call_id)
+    except Exception as e:
+        logger.error(f"[COMPLETION] Failed to mark operation completed: {e}")
+
+    logger.info(f"[COMPLETION] Processed failure for task {task.task_id}: {error_msg}")

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

@@ -0,0 +1,187 @@
+"""Configuration management for chat system."""
+
+import os
+
+from pydantic import Field, field_validator
+from pydantic_settings import BaseSettings
+
+
+class ChatConfig(BaseSettings):
+    """Configuration for the chat system."""
+
+    # OpenAI API Configuration
+    model: str = Field(
+        default="anthropic/claude-opus-4.6", description="Default model to use"
+    )
+    title_model: str = Field(
+        default="openai/gpt-4o-mini",
+        description="Model to use for generating session titles (should be fast/cheap)",
+    )
+    api_key: str | None = Field(default=None, description="OpenAI API key")
+    base_url: str | None = Field(
+        default="https://openrouter.ai/api/v1",
+        description="Base URL for API (e.g., for OpenRouter)",
+    )
+
+    # Session TTL Configuration - 12 hours
+    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_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"
+    )
+
+    # Long-running operation configuration
+    long_running_operation_ttl: int = Field(
+        default=600,
+        description="TTL in seconds for long-running operation tracking in Redis (safety net if pod dies)",
+    )
+
+    # Stream registry configuration for SSE reconnection
+    stream_ttl: int = Field(
+        default=3600,
+        description="TTL in seconds for stream data in Redis (1 hour)",
+    )
+    stream_max_length: int = Field(
+        default=10000,
+        description="Maximum number of messages to store per stream",
+    )
+
+    # Redis Streams configuration for completion consumer
+    stream_completion_name: str = Field(
+        default="chat:completions",
+        description="Redis Stream name for operation completions",
+    )
+    stream_consumer_group: str = Field(
+        default="chat_consumers",
+        description="Consumer group name for completion stream",
+    )
+    stream_claim_min_idle_ms: int = Field(
+        default=60000,
+        description="Minimum idle time in milliseconds before claiming pending messages from dead consumers",
+    )
+
+    # Redis key prefixes for stream registry
+    task_meta_prefix: str = Field(
+        default="chat:task:meta:",
+        description="Prefix for task metadata hash keys",
+    )
+    task_stream_prefix: str = Field(
+        default="chat:stream:",
+        description="Prefix for task message stream keys",
+    )
+    task_op_prefix: str = Field(
+        default="chat:task:op:",
+        description="Prefix for operation ID to task ID mapping keys",
+    )
+    internal_api_key: str | None = Field(
+        default=None,
+        description="API key for internal webhook callbacks (env: CHAT_INTERNAL_API_KEY)",
+    )
+
+    # Langfuse Prompt Management Configuration
+    # Note: Langfuse credentials are in Settings().secrets (settings.py)
+    langfuse_prompt_name: str = Field(
+        default="CoPilot Prompt",
+        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,
+        description="Enable adaptive thinking for Claude models via OpenRouter",
+    )
+
+    @field_validator("api_key", mode="before")
+    @classmethod
+    def get_api_key(cls, v):
+        """Get API key from environment if not provided."""
+        if v is None:
+            # Try to get from environment variables
+            # First check for CHAT_API_KEY (Pydantic prefix)
+            v = os.getenv("CHAT_API_KEY")
+            if not v:
+                # Fall back to OPEN_ROUTER_API_KEY
+                v = os.getenv("OPEN_ROUTER_API_KEY")
+            if not v:
+                # Fall back to OPENAI_API_KEY
+                v = os.getenv("OPENAI_API_KEY")
+        return v
+
+    @field_validator("base_url", mode="before")
+    @classmethod
+    def get_base_url(cls, v):
+        """Get base URL from environment if not provided."""
+        if v is None:
+            # Check for OpenRouter or custom base URL
+            v = os.getenv("CHAT_BASE_URL")
+            if not v:
+                v = os.getenv("OPENROUTER_BASE_URL")
+            if not v:
+                v = os.getenv("OPENAI_BASE_URL")
+            if not v:
+                v = "https://openrouter.ai/api/v1"
+        return v
+
+    @field_validator("internal_api_key", mode="before")
+    @classmethod
+    def get_internal_api_key(cls, v):
+        """Get internal API key from environment if not provided."""
+        if v is None:
+            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",
+        "onboarding": "prompts/onboarding_system.md",
+    }
+
+    class Config:
+        """Pydantic config."""
+
+        env_file = ".env"
+        env_file_encoding = "utf-8"
+        extra = "ignore"  # Ignore extra environment variables

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

@@ -0,0 +1,288 @@
+"""Database operations for chat sessions."""
+
+import asyncio
+import logging
+from datetime import UTC, datetime
+from typing import Any, cast
+
+from prisma.models import ChatMessage as PrismaChatMessage
+from prisma.models import ChatSession as PrismaChatSession
+from prisma.types import (
+    ChatMessageCreateInput,
+    ChatSessionCreateInput,
+    ChatSessionUpdateInput,
+    ChatSessionWhereInput,
+)
+
+from backend.data.db import transaction
+from backend.util.json import SafeJson
+
+logger = logging.getLogger(__name__)
+
+
+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": True},
+    )
+    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,
+) -> PrismaChatSession:
+    """Create a new chat session in the database."""
+    data = ChatSessionCreateInput(
+        id=session_id,
+        userId=user_id,
+        credentials=SafeJson({}),
+        successfulAgentRuns=SafeJson({}),
+        successfulAgentSchedules=SafeJson({}),
+    )
+    return await PrismaChatSession.prisma().create(data=data)
+
+
+async def update_chat_session(
+    session_id: str,
+    credentials: dict[str, Any] | None = None,
+    successful_agent_runs: dict[str, Any] | None = None,
+    successful_agent_schedules: dict[str, Any] | None = None,
+    total_prompt_tokens: int | None = None,
+    total_completion_tokens: int | None = None,
+    title: str | None = None,
+) -> PrismaChatSession | None:
+    """Update a chat session's metadata."""
+    data: ChatSessionUpdateInput = {"updatedAt": datetime.now(UTC)}
+
+    if credentials is not None:
+        data["credentials"] = SafeJson(credentials)
+    if successful_agent_runs is not None:
+        data["successfulAgentRuns"] = SafeJson(successful_agent_runs)
+    if successful_agent_schedules is not None:
+        data["successfulAgentSchedules"] = SafeJson(successful_agent_schedules)
+    if total_prompt_tokens is not None:
+        data["totalPromptTokens"] = total_prompt_tokens
+    if total_completion_tokens is not None:
+        data["totalCompletionTokens"] = total_completion_tokens
+    if title is not None:
+        data["title"] = title
+
+    session = await PrismaChatSession.prisma().update(
+        where={"id": session_id},
+        data=data,
+        include={"Messages": True},
+    )
+    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(
+    session_id: str,
+    role: str,
+    sequence: int,
+    content: str | None = None,
+    name: str | None = None,
+    tool_call_id: str | None = None,
+    refusal: str | None = None,
+    tool_calls: list[dict[str, Any]] | None = None,
+    function_call: dict[str, Any] | None = None,
+) -> 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.
+    # We only include fields that have values, then cast at the end.
+    data: dict[str, Any] = {
+        "Session": {"connect": {"id": session_id}},
+        "role": role,
+        "sequence": sequence,
+    }
+
+    # Add optional string fields
+    if content is not None:
+        data["content"] = content
+    if name is not None:
+        data["name"] = name
+    if tool_call_id is not None:
+        data["toolCallId"] = tool_call_id
+    if refusal is not None:
+        data["refusal"] = refusal
+
+    # Add optional JSON fields only when they have values
+    if tool_calls is not None:
+        data["toolCalls"] = SafeJson(tool_calls)
+    if function_call is not None:
+        data["functionCall"] = SafeJson(function_call)
+
+    # Run message create and session timestamp update in parallel for lower latency
+    _, message = await asyncio.gather(
+        PrismaChatSession.prisma().update(
+            where={"id": session_id},
+            data={"updatedAt": datetime.now(UTC)},
+        ),
+        PrismaChatMessage.prisma().create(data=cast(ChatMessageCreateInput, data)),
+    )
+    return message
+
+
+async def add_chat_messages_batch(
+    session_id: str,
+    messages: list[dict[str, Any]],
+    start_sequence: int,
+) -> list[PrismaChatMessage]:
+    """Add multiple messages to a chat session in a batch.
+
+    Uses a transaction for atomicity - if any message creation fails,
+    the entire batch is rolled back.
+    """
+    if not messages:
+        return []
+
+    created_messages = []
+
+    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
+            # set to None. We only include fields that have values, then cast.
+            data: dict[str, Any] = {
+                "Session": {"connect": {"id": session_id}},
+                "role": msg["role"],
+                "sequence": start_sequence + i,
+            }
+
+            # Add optional string fields
+            if msg.get("content") is not None:
+                data["content"] = msg["content"]
+            if msg.get("name") is not None:
+                data["name"] = msg["name"]
+            if msg.get("tool_call_id") is not None:
+                data["toolCallId"] = msg["tool_call_id"]
+            if msg.get("refusal") is not None:
+                data["refusal"] = msg["refusal"]
+
+            # Add optional JSON fields only when they have values
+            if msg.get("tool_calls") is not None:
+                data["toolCalls"] = SafeJson(msg["tool_calls"])
+            if msg.get("function_call") is not None:
+                data["functionCall"] = SafeJson(msg["function_call"])
+
+            created = await PrismaChatMessage.prisma(tx).create(
+                data=cast(ChatMessageCreateInput, data)
+            )
+            created_messages.append(created)
+
+        # Update session's updatedAt timestamp within the same transaction.
+        # Note: Token usage (total_prompt_tokens, total_completion_tokens) is updated
+        # separately via update_chat_session() after streaming completes.
+        await PrismaChatSession.prisma(tx).update(
+            where={"id": session_id},
+            data={"updatedAt": datetime.now(UTC)},
+        )
+
+    return created_messages
+
+
+async def get_user_chat_sessions(
+    user_id: str,
+    limit: int = 50,
+    offset: int = 0,
+) -> list[PrismaChatSession]:
+    """Get chat sessions for a user, ordered by most recent."""
+    return await PrismaChatSession.prisma().find_many(
+        where={"userId": user_id},
+        order={"updatedAt": "desc"},
+        take=limit,
+        skip=offset,
+    )
+
+
+async def get_user_session_count(user_id: str) -> int:
+    """Get the total number of chat sessions for a user."""
+    return await PrismaChatSession.prisma().count(where={"userId": user_id})
+
+
+async def delete_chat_session(session_id: str, user_id: str | None = None) -> bool:
+    """Delete a chat session and all its messages.
+
+    Args:
+        session_id: The session ID to delete.
+        user_id: If provided, validates that the session belongs to this user
+            before deletion. This prevents unauthorized deletion of other
+            users' sessions.
+
+    Returns:
+        True if deleted successfully, False otherwise.
+    """
+    try:
+        # Build typed where clause with optional user_id validation
+        where_clause: ChatSessionWhereInput = {"id": session_id}
+        if user_id is not None:
+            where_clause["userId"] = user_id
+
+        result = await PrismaChatSession.prisma().delete_many(where=where_clause)
+        if result == 0:
+            logger.warning(
+                f"No session deleted for {session_id} "
+                f"(user_id validation: {user_id is not None})"
+            )
+            return False
+        return True
+    except Exception as e:
+        logger.error(f"Failed to delete chat session {session_id}: {e}")
+        return False
+
+
+async def get_chat_session_message_count(session_id: str) -> int:
+    """Get the number of messages in a chat session."""
+    count = await PrismaChatMessage.prisma().count(where={"sessionId": session_id})
+    return count
+
+
+async def update_tool_message_content(
+    session_id: str,
+    tool_call_id: str,
+    new_content: str,
+) -> bool:
+    """Update the content of a tool message in chat history.
+
+    Used by background tasks to update pending operation messages with final results.
+
+    Args:
+        session_id: The chat session ID.
+        tool_call_id: The tool call ID to find the message.
+        new_content: The new content to set.
+
+    Returns:
+        True if a message was updated, False otherwise.
+    """
+    try:
+        result = await PrismaChatMessage.prisma().update_many(
+            where={
+                "sessionId": session_id,
+                "toolCallId": tool_call_id,
+            },
+            data={
+                "content": new_content,
+            },
+        )
+        if result == 0:
+            logger.warning(
+                f"No message found to update for session {session_id}, "
+                f"tool_call_id {tool_call_id}"
+            )
+            return False
+        return True
+    except Exception as e:
+        logger.error(
+            f"Failed to update tool message for session {session_id}, "
+            f"tool_call_id {tool_call_id}: {e}"
+        )
+        return False

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

@@ -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):
@@ -55,33 +85,18 @@ 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
     completion_tokens: int
     total_tokens: int
-    # Cache breakdown (Anthropic-specific; zero for non-Anthropic models)
-    cache_read_tokens: int = 0
-    cache_creation_tokens: int = 0
 
 
-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
@@ -89,75 +104,6 @@ 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."""
-        # Parse JSON fields from Prisma
-        credentials = _parse_json_field(prisma_session.credentials, default={})
-        successful_agent_runs = _parse_json_field(
-            prisma_session.successfulAgentRuns, default={}
-        )
-        successful_agent_schedules = _parse_json_field(
-            prisma_session.successfulAgentSchedules, default={}
-        )
-
-        # Calculate usage from token counts.
-        # NOTE: Per-turn cache_read_tokens / cache_creation_tokens breakdown
-        # is lost after persistence — the DB only stores aggregate prompt and
-        # completion totals. This is a known limitation.
-        usage = []
-        if prisma_session.totalPromptTokens or prisma_session.totalCompletionTokens:
-            usage.append(
-                Usage(
-                    prompt_tokens=prisma_session.totalPromptTokens or 0,
-                    completion_tokens=prisma_session.totalCompletionTokens or 0,
-                    total_tokens=(prisma_session.totalPromptTokens or 0)
-                    + (prisma_session.totalCompletionTokens or 0),
-                )
-            )
-
-        return cls(
-            session_id=prisma_session.id,
-            user_id=prisma_session.userId,
-            title=prisma_session.title,
-            usage=usage,
-            credentials=credentials,
-            started_at=prisma_session.createdAt,
-            updated_at=prisma_session.updatedAt,
-            successful_agent_runs=successful_agent_runs,
-            successful_agent_schedules=successful_agent_schedules,
-        )
-
-
-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.
 
@@ -178,6 +124,115 @@ class ChatSession(ChatSessionInfo):
             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(
+            prisma_session.successfulAgentRuns, default={}
+        )
+        successful_agent_schedules = _parse_json_field(
+            prisma_session.successfulAgentSchedules, default={}
+        )
+
+        # Calculate usage from token counts
+        usage = []
+        if prisma_session.totalPromptTokens or prisma_session.totalCompletionTokens:
+            usage.append(
+                Usage(
+                    prompt_tokens=prisma_session.totalPromptTokens or 0,
+                    completion_tokens=prisma_session.totalCompletionTokens or 0,
+                    total_tokens=(prisma_session.totalPromptTokens or 0)
+                    + (prisma_session.totalCompletionTokens or 0),
+                )
+            )
+
+        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,
+            updated_at=prisma_session.updatedAt,
+            successful_agent_runs=successful_agent_runs,
+            successful_agent_schedules=successful_agent_schedules,
+        )
+
+    @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
+
+        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 = []
         for message in self.messages:
@@ -266,70 +321,40 @@ 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"[CACHE] Loaded session {session_id}: {len(session.messages)} messages, "
+            f"last_roles={[m.role for m in session.messages[-3:]]}"  # Last 3 roles
+        )
+        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.
 
@@ -345,6 +370,77 @@ 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.debug(
+        f"[DB] Loaded session {session_id}: {len(messages) if messages else 0} messages, "
+        f"roles={[m.role for m in messages[-3:]] if messages else []}"  # Last 3 roles
+    )
+
+    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.debug(
+            f"[DB] Saving {len(new_messages)} messages to session {session.session_id}, "
+            f"roles={[m['role'] for m in messages_data]}"
+        )
+        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,
@@ -392,52 +488,13 @@ async def get_chat_session(
 
     # Cache the session from DB
     try:
-        await cache_chat_session(session)
-        logger.info(f"Cached session {session_id} from database")
+        await _cache_session(session)
     except Exception as e:
         logger.warning(f"Failed to cache session {session_id}: {e}")
 
     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:
@@ -457,35 +514,25 @@ async def upsert_chat_session(
     lock = await _get_session_lock(session.session_id)
 
     async with lock:
-        # Always query DB for existing message count to ensure consistency
-        existing_message_count = await chat_db().get_next_sequence(session.session_id)
+        # Get existing message count from DB for incremental saves
+        existing_message_count = await chat_db.get_chat_session_message_count(
+            session.session_id
+        )
 
         db_error: Exception | None = None
 
         # Save to database (primary storage)
         try:
-            await _save_session_to_db(
-                session,
-                existing_message_count,
-                skip_existence_check=existing_message_count > 0,
-            )
+            await _save_session_to_db(session, existing_message_count)
         except Exception as e:
             logger.error(
                 f"Failed to save session {session.session_id} to database: {e}"
             )
             db_error = e
 
-        # Save to cache (best-effort, even if DB failed).
-        # Title updates (update_session_title) run *outside* this lock because
-        # they only touch the title field, not messages.  So a concurrent rename
-        # or auto-title may have written a newer title to Redis while this
-        # upsert was in progress.  Always prefer the cached title to avoid
-        # overwriting it with the stale in-memory copy.
+        # Save to cache (best-effort, even if DB failed)
         try:
-            existing_cached = await _get_session_from_cache(session.session_id)
-            if existing_cached and existing_cached.title:
-                session = session.model_copy(update={"title": existing_cached.title})
-            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:
@@ -506,75 +553,6 @@ async def upsert_chat_session(
         return session
 
 
-async def _save_session_to_db(
-    session: ChatSession,
-    existing_message_count: int,
-    *,
-    skip_existence_check: bool = False,
-) -> None:
-    """Save or update a chat session in the database.
-
-    Args:
-        skip_existence_check: When True, skip the ``get_chat_session`` query
-            and assume the session row already exists.  Saves one DB round trip
-            for incremental saves during streaming.
-    """
-    db = chat_db()
-
-    if not skip_existence_check:
-        # 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.
 
@@ -590,7 +568,9 @@ async def append_and_save_message(session_id: str, message: ChatMessage) -> Chat
             raise ValueError(f"Session {session_id} not found")
 
         session.messages.append(message)
-        existing_message_count = await chat_db().get_next_sequence(session_id)
+        existing_message_count = await chat_db.get_chat_session_message_count(
+            session_id
+        )
 
         try:
             await _save_session_to_db(session, existing_message_count)
@@ -600,7 +580,7 @@ async def append_and_save_message(session_id: str, message: ChatMessage) -> Chat
             ) from e
 
         try:
-            await cache_chat_session(session)
+            await _cache_session(session)
         except Exception as e:
             logger.warning(f"Cache write failed for session {session_id}: {e}")
 
@@ -619,7 +599,7 @@ 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,
         )
@@ -631,7 +611,7 @@ 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}")
 
@@ -642,16 +622,20 @@ 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
 
@@ -669,7 +653,7 @@ 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
@@ -686,47 +670,27 @@ async def delete_chat_session(session_id: str, user_id: str | None = None) -> bo
     async with _session_locks_mutex:
         _session_locks.pop(session_id, None)
 
-    # Shut down any local browser daemon for this session (best-effort).
-    # Inline import required: all tool modules import ChatSession from this
-    # module, so any top-level import from tools.* would create a cycle.
-    try:
-        from .tools.agent_browser import close_browser_session
-
-        await close_browser_session(session_id, user_id=user_id)
-    except Exception as e:
-        logger.debug(f"Browser cleanup for session {session_id}: {e}")
-
     return True
 
 
-async def update_session_title(
-    session_id: str,
-    user_id: str,
-    title: str,
-    *,
-    only_if_empty: bool = False,
-) -> bool:
-    """Update the title of a chat session, scoped to the owning user.
+async def update_session_title(session_id: str, title: str) -> bool:
+    """Update only the title of a chat session.
 
-    Lightweight operation that doesn't touch messages, avoiding race conditions
-    with concurrent message updates.
+    This is a lightweight operation that doesn't touch messages, avoiding
+    race conditions with concurrent message updates. Use this for background
+    title generation instead of upsert_chat_session.
 
     Args:
         session_id: The session ID to update.
-        user_id: Owning user — the DB query filters on this.
         title: The new title to set.
-        only_if_empty: When True, uses an atomic ``UPDATE WHERE title IS NULL``
-            so auto-generated titles never overwrite a user-set title.
 
     Returns:
-        True if updated successfully, False otherwise (not found, wrong user,
-        or — when only_if_empty — title was already set).
+        True if updated successfully, False otherwise.
     """
     try:
-        updated = await chat_db().update_chat_session_title(
-            session_id, user_id, title, only_if_empty=only_if_empty
-        )
-        if not updated:
+        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).
@@ -736,39 +700,14 @@ async def update_session_title(
             cached = await _get_session_from_cache(session_id)
             if cached:
                 cached.title = title
-                await cache_chat_session(cached)
+                await _cache_session(cached)
         except Exception as e:
+            # Not critical - title will be correct on next full cache refresh
             logger.warning(
-                f"Cache title update failed for session {session_id} (non-critical): {e}"
+                f"Failed to update title in 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

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

@@ -331,96 +331,3 @@ def test_to_openai_messages_merges_split_assistants():
     tc_list = merged.get("tool_calls")
     assert tc_list is not None and len(list(tc_list)) == 1
     assert list(tc_list)[0]["id"] == "tc1"
-
-
-# --------------------------------------------------------------------------- #
-#  Concurrent save collision detection                                        #
-# --------------------------------------------------------------------------- #
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_concurrent_saves_collision_detection(setup_test_user, test_user_id):
-    """Test that concurrent saves from streaming loop and callback handle collisions correctly.
-
-    Simulates the race condition where:
-    1. Streaming loop starts with saved_msg_count=5
-    2. Long-running callback appends message #5 and saves
-    3. Streaming loop tries to save with stale count=5
-
-    The collision detection should handle this gracefully.
-    """
-    import asyncio
-
-    # Create a session with initial messages
-    session = ChatSession.new(user_id=test_user_id)
-    for i in range(3):
-        session.messages.append(
-            ChatMessage(
-                role="user" if i % 2 == 0 else "assistant", content=f"Message {i}"
-            )
-        )
-
-    # Save initial messages
-    session = await upsert_chat_session(session)
-
-    # Simulate streaming loop and callback saving concurrently
-    async def streaming_loop_save():
-        """Simulates streaming loop saving messages."""
-        # Add 2 messages
-        session.messages.append(ChatMessage(role="user", content="Streaming message 1"))
-        session.messages.append(
-            ChatMessage(role="assistant", content="Streaming message 2")
-        )
-
-        # Wait a bit to let callback potentially save first
-        await asyncio.sleep(0.01)
-
-        # Save (will query DB for existing count)
-        return await upsert_chat_session(session)
-
-    async def callback_save():
-        """Simulates long-running callback saving a message."""
-        # Add 1 message
-        session.messages.append(
-            ChatMessage(role="tool", content="Callback result", tool_call_id="tc1")
-        )
-
-        # Save immediately (will query DB for existing count)
-        return await upsert_chat_session(session)
-
-    # Run both saves concurrently - one will hit collision detection
-    results = await asyncio.gather(streaming_loop_save(), callback_save())
-
-    # Both should succeed
-    assert all(r is not None for r in results)
-
-    # Reload session from DB to verify
-    from backend.data.redis_client import get_redis_async
-
-    redis_key = f"chat:session:{session.session_id}"
-    async_redis = await get_redis_async()
-    await async_redis.delete(redis_key)  # Clear cache to force DB load
-
-    loaded_session = await get_chat_session(session.session_id, test_user_id)
-    assert loaded_session is not None
-
-    # Should have all 6 messages (3 initial + 2 streaming + 1 callback)
-    assert len(loaded_session.messages) == 6
-
-    # Verify no duplicate sequences
-    sequences = []
-    for i, msg in enumerate(loaded_session.messages):
-        # Messages should have sequential sequence numbers starting from 0
-        sequences.append(i)
-
-    # All sequences should be unique and sequential
-    assert sequences == list(range(6))
-
-    # Verify message content is preserved
-    contents = [m.content for m in loaded_session.messages]
-    assert "Message 0" in contents
-    assert "Message 1" in contents
-    assert "Message 2" in contents
-    assert "Streaming message 1" in contents
-    assert "Streaming message 2" in contents
-    assert "Callback result" in contents

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

@@ -5,17 +5,12 @@ This module implements the AI SDK UI Stream Protocol (v1) for streaming chat res
 See: https://ai-sdk.dev/docs/ai-sdk-ui/stream-protocol
 """
 
-import json
-import logging
 from enum import Enum
 from typing import Any
 
 from pydantic import BaseModel, Field
 
 from backend.util.json import dumps as json_dumps
-from backend.util.truncate import truncate
-
-logger = logging.getLogger(__name__)
 
 
 class ResponseType(str, Enum):
@@ -52,8 +47,7 @@ class StreamBaseResponse(BaseModel):
 
     def to_sse(self) -> str:
         """Convert to SSE format."""
-        json_str = self.model_dump_json(exclude_none=True)
-        return f"data: {json_str}\n\n"
+        return f"data: {self.model_dump_json()}\n\n"
 
 
 # ========== Message Lifecycle ==========
@@ -64,13 +58,15 @@ class StreamStart(StreamBaseResponse):
 
     type: ResponseType = ResponseType.START
     messageId: str = Field(..., description="Unique message ID")
-    sessionId: str | None = Field(
+    taskId: str | None = Field(
         default=None,
-        description="Session ID for SSE reconnection.",
+        description="Task ID for SSE reconnection. Clients can reconnect using GET /tasks/{taskId}/stream",
     )
 
     def to_sse(self) -> str:
-        """Convert to SSE format, excluding non-protocol fields like sessionId."""
+        """Convert to SSE format, excluding non-protocol fields like taskId."""
+        import json
+
         data: dict[str, Any] = {
             "type": self.type.value,
             "messageId": self.messageId,
@@ -151,9 +147,6 @@ class StreamToolInputAvailable(StreamBaseResponse):
     )
 
 
-_MAX_TOOL_OUTPUT_SIZE = 100_000  # ~100 KB; truncate to avoid bloating SSE/DB
-
-
 class StreamToolOutputAvailable(StreamBaseResponse):
     """Tool execution result."""
 
@@ -168,12 +161,10 @@ class StreamToolOutputAvailable(StreamBaseResponse):
         default=True, description="Whether the tool execution succeeded"
     )
 
-    def model_post_init(self, __context: Any) -> None:
-        """Truncate oversized outputs after construction."""
-        self.output = truncate(self.output, _MAX_TOOL_OUTPUT_SIZE)
-
     def to_sse(self) -> str:
         """Convert to SSE format, excluding non-spec fields."""
+        import json
+
         data = {
             "type": self.type.value,
             "toolCallId": self.toolCallId,
@@ -186,43 +177,12 @@ class StreamToolOutputAvailable(StreamBaseResponse):
 
 
 class StreamUsage(StreamBaseResponse):
-    """Token usage statistics.
-
-    Emitted as an SSE comment so the Vercel AI SDK parser ignores it
-    (it uses z.strictObject() and rejects unknown event types).
-    Usage data is recorded server-side (session DB + Redis counters).
-    """
+    """Token usage statistics."""
 
     type: ResponseType = ResponseType.USAGE
-    prompt_tokens: int = Field(
-        ...,
-        serialization_alias="promptTokens",
-        description="Number of uncached prompt tokens",
-    )
-    completion_tokens: int = Field(
-        ...,
-        serialization_alias="completionTokens",
-        description="Number of completion tokens",
-    )
-    total_tokens: int = Field(
-        ...,
-        serialization_alias="totalTokens",
-        description="Total number of tokens (raw, not weighted)",
-    )
-    cache_read_tokens: int = Field(
-        default=0,
-        serialization_alias="cacheReadTokens",
-        description="Prompt tokens served from cache (10% cost)",
-    )
-    cache_creation_tokens: int = Field(
-        default=0,
-        serialization_alias="cacheCreationTokens",
-        description="Prompt tokens written to cache (25% cost)",
-    )
-
-    def to_sse(self) -> str:
-        """Emit as SSE comment so the AI SDK parser ignores it."""
-        return f": usage {self.model_dump_json(exclude_none=True, by_alias=True)}\n\n"
+    promptTokens: int = Field(..., description="Number of prompt tokens")
+    completionTokens: int = Field(..., description="Number of completion tokens")
+    totalTokens: int = Field(..., description="Total number of tokens")
 
 
 class StreamError(StreamBaseResponse):

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

@@ -1,461 +0,0 @@
-"""Tests for chat API routes: session title update, file attachment validation, usage, rate limiting, and suggested prompts."""
-
-from datetime import UTC, datetime, timedelta
-from unittest.mock import AsyncMock, MagicMock
-
-import fastapi
-import fastapi.testclient
-import pytest
-import pytest_mock
-
-from backend.api.features.chat import routes as chat_routes
-
-app = fastapi.FastAPI()
-app.include_router(chat_routes.router)
-
-client = fastapi.testclient.TestClient(app)
-
-TEST_USER_ID = "3e53486c-cf57-477e-ba2a-cb02dc828e1a"
-
-
-@pytest.fixture(autouse=True)
-def setup_app_auth(mock_jwt_user):
-    """Setup auth overrides for all tests in this module"""
-    from autogpt_libs.auth.jwt_utils import get_jwt_payload
-
-    app.dependency_overrides[get_jwt_payload] = mock_jwt_user["get_jwt_payload"]
-    yield
-    app.dependency_overrides.clear()
-
-
-def _mock_update_session_title(
-    mocker: pytest_mock.MockerFixture, *, success: bool = True
-):
-    """Mock update_session_title."""
-    return mocker.patch(
-        "backend.api.features.chat.routes.update_session_title",
-        new_callable=AsyncMock,
-        return_value=success,
-    )
-
-
-# ─── Update title: success ─────────────────────────────────────────────
-
-
-def test_update_title_success(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    mock_update = _mock_update_session_title(mocker, success=True)
-
-    response = client.patch(
-        "/sessions/sess-1/title",
-        json={"title": "My project"},
-    )
-
-    assert response.status_code == 200
-    assert response.json() == {"status": "ok"}
-    mock_update.assert_called_once_with("sess-1", test_user_id, "My project")
-
-
-def test_update_title_trims_whitespace(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    mock_update = _mock_update_session_title(mocker, success=True)
-
-    response = client.patch(
-        "/sessions/sess-1/title",
-        json={"title": "  trimmed  "},
-    )
-
-    assert response.status_code == 200
-    mock_update.assert_called_once_with("sess-1", test_user_id, "trimmed")
-
-
-# ─── Update title: blank / whitespace-only → 422 ──────────────────────
-
-
-def test_update_title_blank_rejected(
-    test_user_id: str,
-) -> None:
-    """Whitespace-only titles must be rejected before hitting the DB."""
-    response = client.patch(
-        "/sessions/sess-1/title",
-        json={"title": "   "},
-    )
-
-    assert response.status_code == 422
-
-
-def test_update_title_empty_rejected(
-    test_user_id: str,
-) -> None:
-    response = client.patch(
-        "/sessions/sess-1/title",
-        json={"title": ""},
-    )
-
-    assert response.status_code == 422
-
-
-# ─── Update title: session not found or wrong user → 404 ──────────────
-
-
-def test_update_title_not_found(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    _mock_update_session_title(mocker, success=False)
-
-    response = client.patch(
-        "/sessions/sess-1/title",
-        json={"title": "New name"},
-    )
-
-    assert response.status_code == 404
-
-
-# ─── file_ids Pydantic validation ─────────────────────────────────────
-
-
-def test_stream_chat_rejects_too_many_file_ids():
-    """More than 20 file_ids should be rejected by Pydantic validation (422)."""
-    response = client.post(
-        "/sessions/sess-1/stream",
-        json={
-            "message": "hello",
-            "file_ids": [f"00000000-0000-0000-0000-{i:012d}" for i in range(21)],
-        },
-    )
-    assert response.status_code == 422
-
-
-def _mock_stream_internals(mocker: pytest_mock.MockFixture):
-    """Mock the async internals of stream_chat_post so tests can exercise
-    validation and enrichment logic without needing Redis/RabbitMQ."""
-    mocker.patch(
-        "backend.api.features.chat.routes._validate_and_get_session",
-        return_value=None,
-    )
-    mocker.patch(
-        "backend.api.features.chat.routes.append_and_save_message",
-        return_value=None,
-    )
-    mock_registry = mocker.MagicMock()
-    mock_registry.create_session = mocker.AsyncMock(return_value=None)
-    mocker.patch(
-        "backend.api.features.chat.routes.stream_registry",
-        mock_registry,
-    )
-    mocker.patch(
-        "backend.api.features.chat.routes.enqueue_copilot_turn",
-        return_value=None,
-    )
-    mocker.patch(
-        "backend.api.features.chat.routes.track_user_message",
-        return_value=None,
-    )
-
-
-def test_stream_chat_accepts_20_file_ids(mocker: pytest_mock.MockFixture):
-    """Exactly 20 file_ids should be accepted (not rejected by validation)."""
-    _mock_stream_internals(mocker)
-    # Patch workspace lookup as imported by the routes module
-    mocker.patch(
-        "backend.api.features.chat.routes.get_or_create_workspace",
-        return_value=type("W", (), {"id": "ws-1"})(),
-    )
-    mock_prisma = mocker.MagicMock()
-    mock_prisma.find_many = mocker.AsyncMock(return_value=[])
-    mocker.patch(
-        "prisma.models.UserWorkspaceFile.prisma",
-        return_value=mock_prisma,
-    )
-
-    response = client.post(
-        "/sessions/sess-1/stream",
-        json={
-            "message": "hello",
-            "file_ids": [f"00000000-0000-0000-0000-{i:012d}" for i in range(20)],
-        },
-    )
-    # Should get past validation — 200 streaming response expected
-    assert response.status_code == 200
-
-
-# ─── UUID format filtering ─────────────────────────────────────────────
-
-
-def test_file_ids_filters_invalid_uuids(mocker: pytest_mock.MockFixture):
-    """Non-UUID strings in file_ids should be silently filtered out
-    and NOT passed to the database query."""
-    _mock_stream_internals(mocker)
-    mocker.patch(
-        "backend.api.features.chat.routes.get_or_create_workspace",
-        return_value=type("W", (), {"id": "ws-1"})(),
-    )
-
-    mock_prisma = mocker.MagicMock()
-    mock_prisma.find_many = mocker.AsyncMock(return_value=[])
-    mocker.patch(
-        "prisma.models.UserWorkspaceFile.prisma",
-        return_value=mock_prisma,
-    )
-
-    valid_id = "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
-    client.post(
-        "/sessions/sess-1/stream",
-        json={
-            "message": "hello",
-            "file_ids": [
-                valid_id,
-                "not-a-uuid",
-                "../../../etc/passwd",
-                "",
-            ],
-        },
-    )
-
-    # The find_many call should only receive the one valid UUID
-    mock_prisma.find_many.assert_called_once()
-    call_kwargs = mock_prisma.find_many.call_args[1]
-    assert call_kwargs["where"]["id"]["in"] == [valid_id]
-
-
-# ─── Cross-workspace file_ids ─────────────────────────────────────────
-
-
-def test_file_ids_scoped_to_workspace(mocker: pytest_mock.MockFixture):
-    """The batch query should scope to the user's workspace."""
-    _mock_stream_internals(mocker)
-    mocker.patch(
-        "backend.api.features.chat.routes.get_or_create_workspace",
-        return_value=type("W", (), {"id": "my-workspace-id"})(),
-    )
-
-    mock_prisma = mocker.MagicMock()
-    mock_prisma.find_many = mocker.AsyncMock(return_value=[])
-    mocker.patch(
-        "prisma.models.UserWorkspaceFile.prisma",
-        return_value=mock_prisma,
-    )
-
-    fid = "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
-    client.post(
-        "/sessions/sess-1/stream",
-        json={"message": "hi", "file_ids": [fid]},
-    )
-
-    call_kwargs = mock_prisma.find_many.call_args[1]
-    assert call_kwargs["where"]["workspaceId"] == "my-workspace-id"
-    assert call_kwargs["where"]["isDeleted"] is False
-
-
-# ─── Rate limit → 429 ─────────────────────────────────────────────────
-
-
-def test_stream_chat_returns_429_on_daily_rate_limit(mocker: pytest_mock.MockFixture):
-    """When check_rate_limit raises RateLimitExceeded for daily limit the endpoint returns 429."""
-    from backend.copilot.rate_limit import RateLimitExceeded
-
-    _mock_stream_internals(mocker)
-    # Ensure the rate-limit branch is entered by setting a non-zero limit.
-    mocker.patch.object(chat_routes.config, "daily_token_limit", 10000)
-    mocker.patch.object(chat_routes.config, "weekly_token_limit", 50000)
-    mocker.patch(
-        "backend.api.features.chat.routes.check_rate_limit",
-        side_effect=RateLimitExceeded("daily", datetime.now(UTC) + timedelta(hours=1)),
-    )
-
-    response = client.post(
-        "/sessions/sess-1/stream",
-        json={"message": "hello"},
-    )
-    assert response.status_code == 429
-    assert "daily" in response.json()["detail"].lower()
-
-
-def test_stream_chat_returns_429_on_weekly_rate_limit(mocker: pytest_mock.MockFixture):
-    """When check_rate_limit raises RateLimitExceeded for weekly limit the endpoint returns 429."""
-    from backend.copilot.rate_limit import RateLimitExceeded
-
-    _mock_stream_internals(mocker)
-    mocker.patch.object(chat_routes.config, "daily_token_limit", 10000)
-    mocker.patch.object(chat_routes.config, "weekly_token_limit", 50000)
-    resets_at = datetime.now(UTC) + timedelta(days=3)
-    mocker.patch(
-        "backend.api.features.chat.routes.check_rate_limit",
-        side_effect=RateLimitExceeded("weekly", resets_at),
-    )
-
-    response = client.post(
-        "/sessions/sess-1/stream",
-        json={"message": "hello"},
-    )
-    assert response.status_code == 429
-    detail = response.json()["detail"].lower()
-    assert "weekly" in detail
-    assert "resets in" in detail
-
-
-def test_stream_chat_429_includes_reset_time(mocker: pytest_mock.MockFixture):
-    """The 429 response detail should include the human-readable reset time."""
-    from backend.copilot.rate_limit import RateLimitExceeded
-
-    _mock_stream_internals(mocker)
-    mocker.patch.object(chat_routes.config, "daily_token_limit", 10000)
-    mocker.patch.object(chat_routes.config, "weekly_token_limit", 50000)
-    mocker.patch(
-        "backend.api.features.chat.routes.check_rate_limit",
-        side_effect=RateLimitExceeded(
-            "daily", datetime.now(UTC) + timedelta(hours=2, minutes=30)
-        ),
-    )
-
-    response = client.post(
-        "/sessions/sess-1/stream",
-        json={"message": "hello"},
-    )
-    assert response.status_code == 429
-    detail = response.json()["detail"]
-    assert "2h" in detail
-    assert "Resets in" in detail
-
-
-# ─── Usage endpoint ───────────────────────────────────────────────────
-
-
-def _mock_usage(
-    mocker: pytest_mock.MockerFixture,
-    *,
-    daily_used: int = 500,
-    weekly_used: int = 2000,
-) -> AsyncMock:
-    """Mock get_usage_status to return a predictable CoPilotUsageStatus."""
-    from backend.copilot.rate_limit import CoPilotUsageStatus, UsageWindow
-
-    resets_at = datetime.now(UTC) + timedelta(days=1)
-    status = CoPilotUsageStatus(
-        daily=UsageWindow(used=daily_used, limit=10000, resets_at=resets_at),
-        weekly=UsageWindow(used=weekly_used, limit=50000, resets_at=resets_at),
-    )
-    return mocker.patch(
-        "backend.api.features.chat.routes.get_usage_status",
-        new_callable=AsyncMock,
-        return_value=status,
-    )
-
-
-def test_usage_returns_daily_and_weekly(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """GET /usage returns daily and weekly usage."""
-    mock_get = _mock_usage(mocker, daily_used=500, weekly_used=2000)
-
-    mocker.patch.object(chat_routes.config, "daily_token_limit", 10000)
-    mocker.patch.object(chat_routes.config, "weekly_token_limit", 50000)
-
-    response = client.get("/usage")
-
-    assert response.status_code == 200
-    data = response.json()
-    assert data["daily"]["used"] == 500
-    assert data["weekly"]["used"] == 2000
-
-    mock_get.assert_called_once_with(
-        user_id=test_user_id,
-        daily_token_limit=10000,
-        weekly_token_limit=50000,
-    )
-
-
-def test_usage_uses_config_limits(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """The endpoint forwards daily_token_limit and weekly_token_limit from config."""
-    mock_get = _mock_usage(mocker)
-
-    mocker.patch.object(chat_routes.config, "daily_token_limit", 99999)
-    mocker.patch.object(chat_routes.config, "weekly_token_limit", 77777)
-
-    response = client.get("/usage")
-
-    assert response.status_code == 200
-    mock_get.assert_called_once_with(
-        user_id=test_user_id,
-        daily_token_limit=99999,
-        weekly_token_limit=77777,
-    )
-
-
-def test_usage_rejects_unauthenticated_request() -> None:
-    """GET /usage should return 401 when no valid JWT is provided."""
-    unauthenticated_app = fastapi.FastAPI()
-    unauthenticated_app.include_router(chat_routes.router)
-    unauthenticated_client = fastapi.testclient.TestClient(unauthenticated_app)
-
-    response = unauthenticated_client.get("/usage")
-
-    assert response.status_code == 401
-
-
-# ─── Suggested prompts endpoint ──────────────────────────────────────
-
-
-def _mock_get_business_understanding(
-    mocker: pytest_mock.MockerFixture,
-    *,
-    return_value=None,
-):
-    """Mock get_business_understanding."""
-    return mocker.patch(
-        "backend.api.features.chat.routes.get_business_understanding",
-        new_callable=AsyncMock,
-        return_value=return_value,
-    )
-
-
-def test_suggested_prompts_returns_prompts(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """User with understanding and prompts gets them back."""
-    mock_understanding = MagicMock()
-    mock_understanding.suggested_prompts = ["Do X", "Do Y", "Do Z"]
-    _mock_get_business_understanding(mocker, return_value=mock_understanding)
-
-    response = client.get("/suggested-prompts")
-
-    assert response.status_code == 200
-    assert response.json() == {"prompts": ["Do X", "Do Y", "Do Z"]}
-
-
-def test_suggested_prompts_no_understanding(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """User with no understanding gets empty list."""
-    _mock_get_business_understanding(mocker, return_value=None)
-
-    response = client.get("/suggested-prompts")
-
-    assert response.status_code == 200
-    assert response.json() == {"prompts": []}
-
-
-def test_suggested_prompts_empty_prompts(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """User with understanding but no prompts gets empty list."""
-    mock_understanding = MagicMock()
-    mock_understanding.suggested_prompts = []
-    _mock_get_business_understanding(mocker, return_value=mock_understanding)
-
-    response = client.get("/suggested-prompts")
-
-    assert response.status_code == 200
-    assert response.json() == {"prompts": []}

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

@@ -0,0 +1,14 @@
+"""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",
+]

autogpt_platform/backend/backend/api/features/chat/sdk/response_adapter.py

@@ -0,0 +1,203 @@
+"""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.api.features.chat.response_model import (
+    StreamBaseResponse,
+    StreamError,
+    StreamFinish,
+    StreamFinishStep,
+    StreamStart,
+    StreamStartStep,
+    StreamTextDelta,
+    StreamTextEnd,
+    StreamTextStart,
+    StreamToolInputAvailable,
+    StreamToolInputStart,
+    StreamToolOutputAvailable,
+)
+from backend.api.features.chat.sdk.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)

autogpt_platform/backend/backend/api/features/chat/sdk/response_adapter_test.py

@@ -1,8 +1,5 @@
 """Unit tests for the SDK response adapter."""
 
-import asyncio
-
-import pytest
 from claude_agent_sdk import (
     AssistantMessage,
     ResultMessage,
@@ -13,7 +10,7 @@ from claude_agent_sdk import (
     UserMessage,
 )
 
-from backend.copilot.response_model import (
+from backend.api.features.chat.response_model import (
     StreamBaseResponse,
     StreamError,
     StreamFinish,
@@ -30,14 +27,12 @@ from backend.copilot.response_model import (
 
 from .response_adapter import SDKResponseAdapter
 from .tool_adapter import MCP_TOOL_PREFIX
-from .tool_adapter import _pending_tool_outputs as _pto
-from .tool_adapter import _stash_event
-from .tool_adapter import stash_pending_tool_output as _stash
-from .tool_adapter import wait_for_stash
 
 
 def _adapter() -> SDKResponseAdapter:
-    return SDKResponseAdapter(message_id="msg-1", session_id="session-1")
+    a = SDKResponseAdapter(message_id="msg-1")
+    a.set_task_id("task-1")
+    return a
 
 
 # -- SystemMessage -----------------------------------------------------------
@@ -49,7 +44,7 @@ def test_system_init_emits_start_and_step():
     assert len(results) == 2
     assert isinstance(results[0], StreamStart)
     assert results[0].messageId == "msg-1"
-    assert results[0].sessionId == "session-1"
+    assert results[0].taskId == "task-1"
     assert isinstance(results[1], StreamStartStep)
 
 
@@ -369,314 +364,3 @@ def test_full_conversation_flow():
         "StreamFinishStep",  # step 2 closed
         "StreamFinish",
     ]
-
-
-# -- Flush unresolved tool calls --------------------------------------------
-
-
-def test_flush_unresolved_at_result_message():
-    """Built-in tools (WebSearch) without UserMessage results get flushed at ResultMessage."""
-    adapter = _adapter()
-    all_responses: list[StreamBaseResponse] = []
-
-    # 1. Init
-    all_responses.extend(
-        adapter.convert_message(SystemMessage(subtype="init", data={}))
-    )
-    # 2. Tool use (built-in tool — no MCP prefix)
-    all_responses.extend(
-        adapter.convert_message(
-            AssistantMessage(
-                content=[
-                    ToolUseBlock(id="ws-1", name="WebSearch", input={"query": "test"})
-                ],
-                model="test",
-            )
-        )
-    )
-    # 3. No UserMessage for this tool — go straight to ResultMessage
-    all_responses.extend(
-        adapter.convert_message(
-            ResultMessage(
-                subtype="success",
-                duration_ms=100,
-                duration_api_ms=50,
-                is_error=False,
-                num_turns=1,
-                session_id="s1",
-            )
-        )
-    )
-
-    types = [type(r).__name__ for r in all_responses]
-    assert types == [
-        "StreamStart",
-        "StreamStartStep",
-        "StreamToolInputStart",
-        "StreamToolInputAvailable",
-        "StreamToolOutputAvailable",  # flushed with empty output
-        "StreamFinishStep",  # step closed by flush
-        "StreamFinish",
-    ]
-    # The flushed output should be empty (no stash available)
-    output_event = [
-        r for r in all_responses if isinstance(r, StreamToolOutputAvailable)
-    ][0]
-    assert output_event.toolCallId == "ws-1"
-    assert output_event.toolName == "WebSearch"
-    assert output_event.output == ""
-
-
-def test_flush_unresolved_at_next_assistant_message():
-    """Built-in tools get flushed when the next AssistantMessage arrives."""
-    adapter = _adapter()
-    all_responses: list[StreamBaseResponse] = []
-
-    # 1. Init
-    all_responses.extend(
-        adapter.convert_message(SystemMessage(subtype="init", data={}))
-    )
-    # 2. Tool use (built-in — no UserMessage will come)
-    all_responses.extend(
-        adapter.convert_message(
-            AssistantMessage(
-                content=[
-                    ToolUseBlock(id="ws-1", name="WebSearch", input={"query": "test"})
-                ],
-                model="test",
-            )
-        )
-    )
-    # 3. Next AssistantMessage triggers flush before processing its blocks
-    all_responses.extend(
-        adapter.convert_message(
-            AssistantMessage(
-                content=[TextBlock(text="Here are the results")], model="test"
-            )
-        )
-    )
-
-    types = [type(r).__name__ for r in all_responses]
-    assert types == [
-        "StreamStart",
-        "StreamStartStep",
-        "StreamToolInputStart",
-        "StreamToolInputAvailable",
-        # Flush at next AssistantMessage:
-        "StreamToolOutputAvailable",
-        "StreamFinishStep",  # step closed by flush
-        # New step for continuation text:
-        "StreamStartStep",
-        "StreamTextStart",
-        "StreamTextDelta",
-    ]
-
-
-def test_flush_with_stashed_output():
-    """Stashed output from PostToolUse hook is used when flushing."""
-    adapter = _adapter()
-
-    # Simulate PostToolUse hook stashing output
-    _pto.set({})
-    _stash("WebSearch", "Search result: 5 items found")
-
-    all_responses: list[StreamBaseResponse] = []
-
-    # Tool use
-    all_responses.extend(
-        adapter.convert_message(
-            AssistantMessage(
-                content=[
-                    ToolUseBlock(id="ws-1", name="WebSearch", input={"query": "test"})
-                ],
-                model="test",
-            )
-        )
-    )
-    # ResultMessage triggers flush
-    all_responses.extend(
-        adapter.convert_message(
-            ResultMessage(
-                subtype="success",
-                duration_ms=100,
-                duration_api_ms=50,
-                is_error=False,
-                num_turns=1,
-                session_id="s1",
-            )
-        )
-    )
-
-    output_events = [
-        r for r in all_responses if isinstance(r, StreamToolOutputAvailable)
-    ]
-    assert len(output_events) == 1
-    assert output_events[0].output == "Search result: 5 items found"
-
-    # Cleanup
-    _pto.set({})  # type: ignore[arg-type]
-
-
-# -- wait_for_stash synchronisation tests --
-
-
-@pytest.mark.asyncio
-async def test_wait_for_stash_signaled():
-    """wait_for_stash returns True when stash_pending_tool_output signals."""
-    _pto.set({})
-    event = asyncio.Event()
-    _stash_event.set(event)
-
-    # Simulate a PostToolUse hook that stashes output after a short delay
-    async def delayed_stash():
-        await asyncio.sleep(0.01)
-        _stash("WebSearch", "result data")
-
-    asyncio.create_task(delayed_stash())
-    result = await wait_for_stash(timeout=1.0)
-
-    assert result is True
-    pto = _pto.get()
-    assert pto is not None
-    assert pto.get("WebSearch") == ["result data"]
-
-    # Cleanup
-    _pto.set({})
-    _stash_event.set(None)
-
-
-@pytest.mark.asyncio
-async def test_wait_for_stash_timeout():
-    """wait_for_stash returns False on timeout when no stash occurs."""
-    _pto.set({})
-    event = asyncio.Event()
-    _stash_event.set(event)
-
-    result = await wait_for_stash(timeout=0.05)
-    assert result is False
-
-    # Cleanup
-    _pto.set({})
-    _stash_event.set(None)
-
-
-@pytest.mark.asyncio
-async def test_wait_for_stash_already_stashed():
-    """wait_for_stash picks up a stash that happened just before the wait."""
-    _pto.set({})
-    event = asyncio.Event()
-    _stash_event.set(event)
-
-    # Stash before waiting — simulates hook completing before message arrives
-    _stash("Read", "file contents")
-    # Event is now set; wait_for_stash detects the fast path and returns
-    # immediately without timing out.
-    result = await wait_for_stash(timeout=0.05)
-    assert result is True
-
-    # But the stash itself is populated
-    pto = _pto.get()
-    assert pto is not None
-    assert pto.get("Read") == ["file contents"]
-
-    # Cleanup
-    _pto.set({})
-    _stash_event.set(None)
-
-
-# -- Parallel tool call tests --
-
-
-def test_parallel_tool_calls_not_flushed_prematurely():
-    """Parallel tool calls should NOT be flushed when the next AssistantMessage
-    only contains ToolUseBlocks (parallel continuation)."""
-    adapter = SDKResponseAdapter()
-
-    # Init
-    adapter.convert_message(SystemMessage(subtype="init", data={}))
-
-    # First AssistantMessage: tool call #1
-    msg1 = AssistantMessage(
-        content=[ToolUseBlock(id="t1", name="WebSearch", input={"q": "foo"})],
-        model="test",
-    )
-    r1 = adapter.convert_message(msg1)
-    assert any(isinstance(r, StreamToolInputAvailable) for r in r1)
-    assert adapter.has_unresolved_tool_calls
-
-    # Second AssistantMessage: tool call #2 (parallel continuation)
-    msg2 = AssistantMessage(
-        content=[ToolUseBlock(id="t2", name="WebSearch", input={"q": "bar"})],
-        model="test",
-    )
-    r2 = adapter.convert_message(msg2)
-
-    # No flush should have happened — t1 should NOT have StreamToolOutputAvailable
-    output_events = [r for r in r2 if isinstance(r, StreamToolOutputAvailable)]
-    assert len(output_events) == 0, (
-        f"Tool-only AssistantMessage should not flush prior tools, "
-        f"but got {len(output_events)} output events"
-    )
-
-    # Both t1 and t2 should still be unresolved
-    assert "t1" not in adapter.resolved_tool_calls
-    assert "t2" not in adapter.resolved_tool_calls
-
-
-def test_text_assistant_message_flushes_prior_tools():
-    """An AssistantMessage with text (new turn) should flush unresolved tools."""
-    adapter = SDKResponseAdapter()
-
-    # Init
-    adapter.convert_message(SystemMessage(subtype="init", data={}))
-
-    # Tool call
-    msg1 = AssistantMessage(
-        content=[ToolUseBlock(id="t1", name="WebSearch", input={"q": "foo"})],
-        model="test",
-    )
-    adapter.convert_message(msg1)
-    assert adapter.has_unresolved_tool_calls
-
-    # Text AssistantMessage (new turn after tools completed)
-    msg2 = AssistantMessage(
-        content=[TextBlock(text="Here are the results")],
-        model="test",
-    )
-    r2 = adapter.convert_message(msg2)
-
-    # Flush SHOULD have happened — t1 gets empty output
-    output_events = [r for r in r2 if isinstance(r, StreamToolOutputAvailable)]
-    assert len(output_events) == 1
-    assert output_events[0].toolCallId == "t1"
-    assert "t1" in adapter.resolved_tool_calls
-
-
-def test_already_resolved_tool_skipped_in_user_message():
-    """A tool result in UserMessage should be skipped if already resolved by flush."""
-    adapter = SDKResponseAdapter()
-
-    adapter.convert_message(SystemMessage(subtype="init", data={}))
-
-    # Tool call + flush via text message
-    adapter.convert_message(
-        AssistantMessage(
-            content=[ToolUseBlock(id="t1", name="WebSearch", input={})],
-            model="test",
-        )
-    )
-    adapter.convert_message(
-        AssistantMessage(
-            content=[TextBlock(text="Done")],
-            model="test",
-        )
-    )
-    assert "t1" in adapter.resolved_tool_calls
-
-    # Now UserMessage arrives with the real result — should be skipped
-    user_msg = UserMessage(content=[ToolResultBlock(tool_use_id="t1", content="real")])
-    r = adapter.convert_message(user_msg)
-    output_events = [r_ for r_ in r if isinstance(r_, StreamToolOutputAvailable)]
-    assert (
-        len(output_events) == 0
-    ), "Already-resolved tool should not emit duplicate output"

autogpt_platform/backend/backend/api/features/chat/sdk/security_hooks.py

@@ -6,18 +6,16 @@ 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 backend.copilot.context import is_allowed_local_path
-
-from .tool_adapter import (
+from backend.api.features.chat.sdk.tool_adapter import (
     BLOCKED_TOOLS,
     DANGEROUS_PATTERNS,
     MCP_TOOL_PREFIX,
     WORKSPACE_SCOPED_TOOLS,
-    stash_pending_tool_output,
 )
 
 logger = logging.getLogger(__name__)
@@ -39,20 +37,40 @@ def _validate_workspace_path(
 ) -> dict[str, Any]:
     """Validate that a workspace-scoped tool only accesses allowed paths.
 
-    Delegates to :func:`is_allowed_local_path` which permits:
+    Allowed directories:
     - The SDK working directory (``/tmp/copilot-<session>/``)
-    - The current session's tool-results directory
-      (``~/.claude/projects/<encoded-cwd>/tool-results/``)
+    - 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 {}
 
-    if is_allowed_local_path(path, sdk_cwd):
+    # 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}")
+    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 "
@@ -105,20 +123,20 @@ def _validate_user_isolation(
     """Validate that tool calls respect user isolation."""
     # For workspace file tools, ensure path doesn't escape
     if "workspace" in tool_name.lower():
-        # The "path" param is a cloud storage key (e.g. "/ASEAN/report.md")
-        # where a leading "/" is normal.  Only check for ".." traversal.
-        # Filesystem paths (source_path, save_to_path) are validated inside
-        # the tool itself via _validate_ephemeral_path.
         path = tool_input.get("path", "") or tool_input.get("file_path", "")
-        if path and ".." in path:
-            logger.warning(f"Blocked path traversal attempt: {path} by user {user_id}")
-            return {
-                "hookSpecificOutput": {
-                    "hookEventName": "PreToolUse",
-                    "permissionDecision": "deny",
-                    "permissionDecisionReason": "Path traversal not allowed",
+        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 {}
 
@@ -127,7 +145,7 @@ def create_security_hooks(
     user_id: str | None,
     sdk_cwd: str | None = None,
     max_subtasks: int = 3,
-    on_compact: Callable[[str], None] | None = None,
+    on_stop: Callable[[str, str], None] | None = None,
 ) -> dict[str, Any]:
     """Create the security hooks configuration for Claude Agent SDK.
 
@@ -136,13 +154,15 @@ def create_security_hooks(
     - 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 concurrent Task (sub-agent) spawns allowed per session
-        on_compact: Callback invoked when SDK starts compacting context.
-            Receives the transcript_path from the hook input.
+        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
@@ -151,9 +171,8 @@ def create_security_hooks(
         from claude_agent_sdk import HookMatcher
         from claude_agent_sdk.types import HookContext, HookInput, SyncHookJSONOutput
 
-        # Per-session tracking for Task sub-agent concurrency.
-        # Set of tool_use_ids that consumed a slot — len() is the active count.
-        task_tool_use_ids: set[str] = set()
+        # Per-session counter for Task sub-agent spawns
+        task_spawn_count = 0
 
         async def pre_tool_use_hook(
             input_data: HookInput,
@@ -161,34 +180,23 @@ def create_security_hooks(
             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":
-                # Block background task execution first — denied calls
-                # should not consume a subtask slot.
-                if tool_input.get("run_in_background"):
-                    logger.info(f"[SDK] Blocked background Task, user={user_id}")
-                    return cast(
-                        SyncHookJSONOutput,
-                        _deny(
-                            "Background task execution is not supported. "
-                            "Run tasks in the foreground instead "
-                            "(remove the run_in_background parameter)."
-                        ),
-                    )
-                if len(task_tool_use_ids) >= max_subtasks:
+                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} concurrent sub-tasks. "
-                            "Wait for running sub-tasks to finish, "
-                            "or continue in the main conversation."
+                            f"Maximum {max_subtasks} sub-tasks per session. "
+                            "Please continue in the main conversation."
                         ),
                     )
 
@@ -208,68 +216,18 @@ def create_security_hooks(
             if result:
                 return cast(SyncHookJSONOutput, result)
 
-            # Reserve the Task slot only after all validations pass
-            if tool_name == "Task" and tool_use_id is not None:
-                task_tool_use_ids.add(tool_use_id)
-
             logger.debug(f"[SDK] Tool start: {tool_name}, user={user_id}")
             return cast(SyncHookJSONOutput, {})
 
-        def _release_task_slot(tool_name: str, tool_use_id: str | None) -> None:
-            """Release a Task concurrency slot if one was reserved."""
-            if tool_name == "Task" and tool_use_id in task_tool_use_ids:
-                task_tool_use_ids.discard(tool_use_id)
-                logger.info(
-                    "[SDK] Task slot released, active=%d/%d, user=%s",
-                    len(task_tool_use_ids),
-                    max_subtasks,
-                    user_id,
-                )
-
         async def post_tool_use_hook(
             input_data: HookInput,
             tool_use_id: str | None,
             context: HookContext,
         ) -> SyncHookJSONOutput:
-            """Log successful tool executions and stash SDK built-in tool outputs.
-
-            MCP tools stash their output in ``_execute_tool_sync`` before the
-            SDK can truncate it.  SDK built-in tools (WebSearch, Read, etc.)
-            are executed by the CLI internally — this hook captures their
-            output so the response adapter can forward it to the frontend.
-            """
+            """Log successful tool executions for observability."""
             _ = context
             tool_name = cast(str, input_data.get("tool_name", ""))
-
-            _release_task_slot(tool_name, tool_use_id)
-            is_builtin = not tool_name.startswith(MCP_TOOL_PREFIX)
-            logger.info(
-                "[SDK] PostToolUse: %s (builtin=%s, tool_use_id=%s)",
-                tool_name,
-                is_builtin,
-                (tool_use_id or "")[:12],
-            )
-
-            # Stash output for SDK built-in tools so the response adapter can
-            # emit StreamToolOutputAvailable even when the CLI doesn't surface
-            # a separate UserMessage with ToolResultBlock content.
-            if is_builtin:
-                tool_response = input_data.get("tool_response")
-                if tool_response is not None:
-                    resp_preview = str(tool_response)[:100]
-                    logger.info(
-                        "[SDK] Stashing builtin output for %s (%d chars): %s...",
-                        tool_name,
-                        len(str(tool_response)),
-                        resp_preview,
-                    )
-                    stash_pending_tool_output(tool_name, tool_response)
-                else:
-                    logger.warning(
-                        "[SDK] PostToolUse for builtin %s but tool_response is None",
-                        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(
@@ -285,9 +243,6 @@ def create_security_hooks(
                 f"[SDK] Tool failed: {tool_name}, error={error}, "
                 f"user={user_id}, tool_use_id={tool_use_id}"
             )
-
-            _release_task_slot(tool_name, tool_use_id)
-
             return cast(SyncHookJSONOutput, {})
 
         async def pre_compact_hook(
@@ -302,21 +257,33 @@ def create_security_hooks(
             """
             _ = context, tool_use_id
             trigger = input_data.get("trigger", "auto")
-            # Sanitize untrusted input before logging to prevent log injection
-            transcript_path = (
-                str(input_data.get("transcript_path", ""))
-                .replace("\n", "")
-                .replace("\r", "")
-            )
             logger.info(
-                "[SDK] Context compaction triggered: %s, user=%s, "
-                "transcript_path=%s",
-                trigger,
-                user_id,
-                transcript_path,
+                f"[SDK] Context compaction triggered: {trigger}, user={user_id}"
             )
-            if on_compact is not None:
-                on_compact(transcript_path)
+            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] = {
@@ -328,6 +295,9 @@ def create_security_hooks(
             "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

autogpt_platform/backend/backend/api/features/chat/sdk/security_hooks_test.py

@@ -0,0 +1,165 @@
+"""Unit tests for SDK security hooks."""
+
+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"
+
+
+# -- 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 == {}

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

@@ -0,0 +1,752 @@
+"""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.api.features.chat.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."
+        )
+
+    if message:
+        session.messages.append(
+            ChatMessage(
+                role="user" if is_user_message else "assistant", 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:
+                        task = asyncio.create_task(
+                            _upload_transcript_bg(user_id, session_id, raw_transcript)
+                        )
+                        _background_tasks.add(task)
+                        task.add_done_callback(_background_tasks.discard)
+                    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}")

autogpt_platform/backend/backend/api/features/chat/sdk/tool_adapter.py

@@ -0,0 +1,363 @@
+"""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.api.features.chat.model import ChatSession
+from backend.api.features.chat.tools import TOOL_REGISTRY
+from backend.api.features.chat.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,
+]

autogpt_platform/backend/backend/api/features/chat/sdk/transcript.py

@@ -0,0 +1,356 @@
+"""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}")

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

@@ -4,14 +4,87 @@ 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, StreamTextDelta
+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.
@@ -41,6 +114,7 @@ async def test_sdk_resume_multi_turn(setup_test_user, test_user_id):
     )
     turn1_text = ""
     turn1_errors: list[str] = []
+    turn1_ended = False
 
     async for chunk in sdk_service.stream_chat_completion_sdk(
         session.session_id,
@@ -51,28 +125,25 @@ async def test_sdk_resume_multi_turn(setup_test_user, test_user_id):
             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).
-    # The CLI may not produce a usable transcript for very short
-    # conversations (only metadata entries) — this is environment-dependent
-    # (CLI version, platform).  When that happens, multi-turn still works
-    # via conversation compression (non-resume path), but we can't test
-    # the --resume round-trip.
+    # 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
-    if not transcript:
-        return pytest.skip(
-            "CLI did not produce a usable transcript — "
-            "cannot test --resume round-trip in this environment"
-        )
-    logger.info(f"Turn 1 transcript uploaded: {len(transcript.content)} bytes")
+    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)
@@ -82,6 +153,7 @@ async def test_sdk_resume_multi_turn(setup_test_user, test_user_id):
     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,
@@ -93,7 +165,10 @@ async def test_sdk_resume_multi_turn(setup_test_user, test_user_id):
             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, (

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

@@ -1,18 +1,16 @@
-from __future__ import annotations
-
 import logging
 from typing import TYPE_CHECKING, Any
 
 from openai.types.chat import ChatCompletionToolParam
 
-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_browser import BrowserActTool, BrowserNavigateTool, BrowserScreenshotTool
 from .agent_output import AgentOutputTool
 from .base import BaseTool
 from .bash_exec import BashExecTool
-from .continue_run_block import ContinueRunBlockTool
+from .check_operation_status import CheckOperationStatusTool
 from .create_agent import CreateAgentTool
 from .customize_agent import CustomizeAgentTool
 from .edit_agent import EditAgentTool
@@ -20,23 +18,10 @@ from .feature_requests import CreateFeatureRequestTool, SearchFeatureRequestsToo
 from .find_agent import FindAgentTool
 from .find_block import FindBlockTool
 from .find_library_agent import FindLibraryAgentTool
-from .fix_agent import FixAgentGraphTool
-from .get_agent_building_guide import GetAgentBuildingGuideTool
 from .get_doc_page import GetDocPageTool
-from .get_mcp_guide import GetMCPGuideTool
-from .manage_folders import (
-    CreateFolderTool,
-    DeleteFolderTool,
-    ListFoldersTool,
-    MoveAgentsToFolderTool,
-    MoveFolderTool,
-    UpdateFolderTool,
-)
 from .run_agent import RunAgentTool
 from .run_block import RunBlockTool
-from .run_mcp_tool import RunMCPToolTool
 from .search_docs import SearchDocsTool
-from .validate_agent import ValidateAgentGraphTool
 from .web_fetch import WebFetchTool
 from .workspace_files import (
     DeleteWorkspaceFileTool,
@@ -46,8 +31,7 @@ from .workspace_files import (
 )
 
 if TYPE_CHECKING:
-    from backend.copilot.model import ChatSession
-    from backend.copilot.response_model import StreamToolOutputAvailable
+    from backend.api.features.chat.response_model import StreamToolOutputAvailable
 
 logger = logging.getLogger(__name__)
 
@@ -60,37 +44,20 @@ TOOL_REGISTRY: dict[str, BaseTool] = {
     "find_agent": FindAgentTool(),
     "find_block": FindBlockTool(),
     "find_library_agent": FindLibraryAgentTool(),
-    # Folder management tools
-    "create_folder": CreateFolderTool(),
-    "list_folders": ListFoldersTool(),
-    "update_folder": UpdateFolderTool(),
-    "move_folder": MoveFolderTool(),
-    "delete_folder": DeleteFolderTool(),
-    "move_agents_to_folder": MoveAgentsToFolderTool(),
     "run_agent": RunAgentTool(),
     "run_block": RunBlockTool(),
-    "continue_run_block": ContinueRunBlockTool(),
-    "run_mcp_tool": RunMCPToolTool(),
-    "get_mcp_guide": GetMCPGuideTool(),
     "view_agent_output": AgentOutputTool(),
+    "check_operation_status": CheckOperationStatusTool(),
     "search_docs": SearchDocsTool(),
     "get_doc_page": GetDocPageTool(),
-    "get_agent_building_guide": GetAgentBuildingGuideTool(),
     # Web fetch for safe URL retrieval
     "web_fetch": WebFetchTool(),
-    # Agent-browser multi-step automation (navigate, act, screenshot)
-    "browser_navigate": BrowserNavigateTool(),
-    "browser_act": BrowserActTool(),
-    "browser_screenshot": BrowserScreenshotTool(),
     # 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(),
-    # Agent generation tools (local validation/fixing)
-    "validate_agent_graph": ValidateAgentGraphTool(),
-    "fix_agent_graph": FixAgentGraphTool(),
     # Workspace tools for CoPilot file operations
     "list_workspace_files": ListWorkspaceFilesTool(),
     "read_workspace_file": ReadWorkspaceFileTool(),
@@ -102,17 +69,10 @@ TOOL_REGISTRY: dict[str, BaseTool] = {
 find_agent_tool = TOOL_REGISTRY["find_agent"]
 run_agent_tool = TOOL_REGISTRY["run_agent"]
 
-
-def get_available_tools() -> list[ChatCompletionToolParam]:
-    """Return OpenAI tool schemas for tools available in the current environment.
-
-    Called per-request so that env-var or binary availability is evaluated
-    fresh each time (e.g. browser_* tools are excluded when agent-browser
-    CLI is not installed).
-    """
-    return [
-        tool.as_openai_tool() for tool in TOOL_REGISTRY.values() if tool.is_available
-    ]
+# Generated from registry for OpenAI API
+tools: list[ChatCompletionToolParam] = [
+    tool.as_openai_tool() for tool in TOOL_REGISTRY.values()
+]
 
 
 def get_tool(tool_name: str) -> BaseTool | None:

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

@@ -1,46 +1,22 @@
-import logging
 import uuid
 from datetime import UTC, datetime
 from os import getenv
 
 import pytest
-import pytest_asyncio
 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 import db as db_module
 from backend.data.db import prisma
 from backend.data.graph import Graph, Link, Node, create_graph
 from backend.data.model import APIKeyCredentials
 from backend.data.user import get_or_create_user
 from backend.integrations.credentials_store import IntegrationCredentialsStore
 
-_logger = logging.getLogger(__name__)
-
-
-async def _ensure_db_connected() -> None:
-    """Ensure the Prisma connection is alive on the current event loop.
-
-    On Python 3.11, the httpx transport inside Prisma can reference a stale
-    (closed) event loop when session-scoped async fixtures are evaluated long
-    after the initial ``server`` fixture connected Prisma.  A cheap health-check
-    followed by a reconnect fixes this without affecting other fixtures.
-    """
-    try:
-        await prisma.query_raw("SELECT 1")
-    except Exception:
-        _logger.info("Prisma connection stale – reconnecting")
-        try:
-            await db_module.disconnect()
-        except Exception:
-            pass
-        await db_module.connect()
-
 
 def make_session(user_id: str):
     return ChatSession(
@@ -55,19 +31,15 @@ def make_session(user_id: str):
     )
 
 
-@pytest_asyncio.fixture(scope="session", loop_scope="session")
-async def setup_test_data(server):
+@pytest.fixture(scope="session")
+async def setup_test_data():
     """
     Set up test data for run_agent tests:
     1. Create a test user
     2. Create a test graph (agent input -> agent output)
     3. Create a store listing and store listing version
     4. Approve the store listing version
-
-    Depends on ``server`` to ensure Prisma is connected.
     """
-    await _ensure_db_connected()
-
     # 1. Create a test user
     user_data = {
         "sub": f"test-user-{uuid.uuid4()}",
@@ -151,8 +123,8 @@ async def setup_test_data(server):
     unique_slug = f"test-agent-{str(uuid.uuid4())[:8]}"
     store_submission = await store_db.create_store_submission(
         user_id=user.id,
-        graph_id=created_graph.id,
-        graph_version=created_graph.version,
+        agent_id=created_graph.id,
+        agent_version=created_graph.version,
         slug=unique_slug,
         name="Test Agent",
         description="A simple test agent",
@@ -161,10 +133,10 @@ async def setup_test_data(server):
         image_urls=["https://example.com/image.jpg"],
     )
 
-    assert store_submission.listing_version_id is not None
+    assert store_submission.store_listing_version_id is not None
     # 4. Approve the store listing version
     await store_db.review_store_submission(
-        store_listing_version_id=store_submission.listing_version_id,
+        store_listing_version_id=store_submission.store_listing_version_id,
         is_approved=True,
         external_comments="Approved for testing",
         internal_comments="Test approval",
@@ -178,19 +150,15 @@ async def setup_test_data(server):
     }
 
 
-@pytest_asyncio.fixture(scope="session", loop_scope="session")
-async def setup_llm_test_data(server):
+@pytest.fixture(scope="session")
+async def setup_llm_test_data():
     """
     Set up test data for LLM agent tests:
     1. Create a test user
     2. Create test OpenAI credentials for the user
     3. Create a test graph with input -> LLM block -> output
     4. Create and approve a store listing
-
-    Depends on ``server`` to ensure Prisma is connected.
     """
-    await _ensure_db_connected()
-
     key = getenv("OPENAI_API_KEY")
     if not key:
         return pytest.skip("OPENAI_API_KEY is not set")
@@ -321,8 +289,8 @@ async def setup_llm_test_data(server):
     unique_slug = f"llm-test-agent-{str(uuid.uuid4())[:8]}"
     store_submission = await store_db.create_store_submission(
         user_id=user.id,
-        graph_id=created_graph.id,
-        graph_version=created_graph.version,
+        agent_id=created_graph.id,
+        agent_version=created_graph.version,
         slug=unique_slug,
         name="LLM Test Agent",
         description="An agent with LLM capabilities",
@@ -330,9 +298,9 @@ async def setup_llm_test_data(server):
         categories=["testing", "ai"],
         image_urls=["https://example.com/image.jpg"],
     )
-    assert store_submission.listing_version_id is not None
+    assert store_submission.store_listing_version_id is not None
     await store_db.review_store_submission(
-        store_listing_version_id=store_submission.listing_version_id,
+        store_listing_version_id=store_submission.store_listing_version_id,
         is_approved=True,
         external_comments="Approved for testing",
         internal_comments="Test approval for LLM agent",
@@ -347,18 +315,14 @@ async def setup_llm_test_data(server):
     }
 
 
-@pytest_asyncio.fixture(scope="session", loop_scope="session")
-async def setup_firecrawl_test_data(server):
+@pytest.fixture(scope="session")
+async def setup_firecrawl_test_data():
     """
     Set up test data for Firecrawl agent tests (missing credentials scenario):
     1. Create a test user (WITHOUT Firecrawl credentials)
     2. Create a test graph with input -> Firecrawl block -> output
     3. Create and approve a store listing
-
-    Depends on ``server`` to ensure Prisma is connected.
     """
-    await _ensure_db_connected()
-
     # 1. Create a test user
     user_data = {
         "sub": f"test-user-{uuid.uuid4()}",
@@ -476,8 +440,8 @@ async def setup_firecrawl_test_data(server):
     unique_slug = f"firecrawl-test-agent-{str(uuid.uuid4())[:8]}"
     store_submission = await store_db.create_store_submission(
         user_id=user.id,
-        graph_id=created_graph.id,
-        graph_version=created_graph.version,
+        agent_id=created_graph.id,
+        agent_version=created_graph.version,
         slug=unique_slug,
         name="Firecrawl Test Agent",
         description="An agent with Firecrawl integration (no credentials)",
@@ -485,9 +449,9 @@ async def setup_firecrawl_test_data(server):
         categories=["testing", "scraping"],
         image_urls=["https://example.com/image.jpg"],
     )
-    assert store_submission.listing_version_id is not None
+    assert store_submission.store_listing_version_id is not None
     await store_db.review_store_submission(
-        store_listing_version_id=store_submission.listing_version_id,
+        store_listing_version_id=store_submission.store_listing_version_id,
         is_approved=True,
         external_comments="Approved for testing",
         internal_comments="Test approval for Firecrawl agent",

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 = {

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

@@ -1,20 +1,24 @@
 """Agent generator package - Creates agents from natural language."""
 
 from .core import (
+    AgentGeneratorNotConfiguredError,
     AgentJsonValidationError,
     AgentSummary,
     DecompositionResult,
     DecompositionStep,
     LibraryAgentSummary,
     MarketplaceAgentSummary,
+    customize_template,
+    decompose_goal,
     enrich_library_agents_from_steps,
     extract_search_terms_from_steps,
     extract_uuids_from_text,
+    generate_agent,
+    generate_agent_patch,
     get_agent_as_json,
     get_all_relevant_agents_for_generation,
     get_library_agent_by_graph_id,
     get_library_agent_by_id,
-    get_library_agents_by_ids,
     get_library_agents_for_generation,
     graph_to_json,
     json_to_graph,
@@ -22,28 +26,33 @@ from .core import (
     search_marketplace_agents_for_generation,
 )
 from .errors import get_user_message_for_error
-from .validation import AgentFixer, AgentValidator
+from .service import health_check as check_external_service_health
+from .service import is_external_service_configured
 
 __all__ = [
-    "AgentFixer",
-    "AgentValidator",
+    "AgentGeneratorNotConfiguredError",
     "AgentJsonValidationError",
     "AgentSummary",
     "DecompositionResult",
     "DecompositionStep",
     "LibraryAgentSummary",
     "MarketplaceAgentSummary",
+    "check_external_service_health",
+    "customize_template",
+    "decompose_goal",
     "enrich_library_agents_from_steps",
     "extract_search_terms_from_steps",
     "extract_uuids_from_text",
+    "generate_agent",
+    "generate_agent_patch",
     "get_agent_as_json",
     "get_all_relevant_agents_for_generation",
     "get_library_agent_by_graph_id",
     "get_library_agent_by_id",
-    "get_library_agents_by_ids",
     "get_library_agents_for_generation",
     "get_user_message_for_error",
     "graph_to_json",
+    "is_external_service_configured",
     "json_to_graph",
     "save_agent_to_library",
     "search_marketplace_agents_for_generation",

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

@@ -3,14 +3,20 @@
 import logging
 import re
 import uuid
-from collections.abc import Sequence
 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 .helpers import UUID_RE_STR
+from .service import (
+    customize_template_external,
+    decompose_goal_external,
+    generate_agent_external,
+    generate_agent_patch_external,
+    is_external_service_configured,
+)
 
 logger = logging.getLogger(__name__)
 
@@ -72,7 +78,38 @@ class DecompositionResult(TypedDict, total=False):
 AgentSummary = LibraryAgentSummary | MarketplaceAgentSummary | dict[str, Any]
 
 
-_UUID_PATTERN = re.compile(UUID_RE_STR, re.IGNORECASE)
+def _to_dict_list(
+    agents: list[AgentSummary] | list[dict[str, Any]] | None,
+) -> list[dict[str, Any]] | None:
+    """Convert typed agent summaries to plain dicts for external service calls."""
+    if agents is None:
+        return None
+    return [dict(a) for a in agents]
+
+
+class AgentGeneratorNotConfiguredError(Exception):
+    """Raised when the external Agent Generator service is not configured."""
+
+    pass
+
+
+def _check_service_configured() -> None:
+    """Check if the external Agent Generator service is configured.
+
+    Raises:
+        AgentGeneratorNotConfiguredError: If the service is not configured.
+    """
+    if not is_external_service_configured():
+        raise AgentGeneratorNotConfiguredError(
+            "Agent Generator service is not configured. "
+            "Set AGENTGENERATOR_HOST environment variable to enable agent generation."
+        )
+
+
+_UUID_PATTERN = re.compile(
+    r"[a-f0-9]{8}-[a-f0-9]{4}-4[a-f0-9]{3}-[89ab][a-f0-9]{3}-[a-f0-9]{12}",
+    re.IGNORECASE,
+)
 
 
 def extract_uuids_from_text(text: str) -> list[str]:
@@ -108,9 +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(
@@ -127,7 +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(
@@ -154,36 +190,6 @@ async def get_library_agent_by_id(
 get_library_agent_by_graph_id = get_library_agent_by_id
 
 
-async def get_library_agents_by_ids(
-    user_id: str,
-    agent_ids: list[str],
-) -> list[LibraryAgentSummary]:
-    """Fetch multiple library agents by their IDs.
-
-    Args:
-        user_id: The user ID
-        agent_ids: List of agent IDs (can be graph_ids or library agent IDs)
-
-    Returns:
-        List of LibraryAgentSummary for found agents (silently skips not found)
-    """
-    agents: list[LibraryAgentSummary] = []
-    for agent_id in agent_ids:
-        try:
-            agent = await get_library_agent_by_id(user_id, agent_id)
-            if agent:
-                agents.append(agent)
-                logger.debug(f"Fetched library agent by ID: {agent['name']}")
-            else:
-                logger.warning(f"Library agent not found for ID: {agent_id}")
-        except Exception as e:
-            logger.warning(f"Failed to fetch library agent {agent_id}: {e}")
-            continue
-
-    logger.info(f"Fetched {len(agents)}/{len(agent_ids)} library agents by ID")
-    return agents
-
-
 async def get_library_agents_for_generation(
     user_id: str,
     search_query: str | None = None,
@@ -208,17 +214,10 @@ async def get_library_agents_for_generation(
     Returns:
         List of LibraryAgentSummary with schemas and recent executions for sub-agent composition
     """
-    search_term = search_query.strip() if search_query else None
-    if search_term and len(search_term) > 100:
-        raise ValueError(
-            f"Search query is too long ({len(search_term)} chars, max 100). "
-            f"Please use a shorter, more specific search term."
-        )
-
     try:
-        response = await library_db().list_library_agents(
+        response = await library_db.list_library_agents(
             user_id=user_id,
-            search_term=search_term,
+            search_term=search_query,
             page=1,
             page_size=max_results,
             include_executions=True,
@@ -272,16 +271,9 @@ async def search_marketplace_agents_for_generation(
     Returns:
         List of LibraryAgentSummary with full input/output schemas
     """
-    search_term = search_query.strip()
-    if len(search_term) > 100:
-        raise ValueError(
-            f"Search query is too long ({len(search_term)} chars, max 100). "
-            f"Please use a shorter, more specific search term."
-        )
-
     try:
-        response = await store_db().get_store_agents(
-            search_query=search_term,
+        response = await store_db.get_store_agents(
+            search_query=search_query,
             page=1,
             page_size=max_results,
         )
@@ -294,7 +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:
@@ -432,7 +424,7 @@ def extract_search_terms_from_steps(
 async def enrich_library_agents_from_steps(
     user_id: str,
     decomposition_result: DecompositionResult | dict[str, Any],
-    existing_agents: Sequence[AgentSummary] | Sequence[dict[str, Any]],
+    existing_agents: list[AgentSummary] | list[dict[str, Any]],
     exclude_graph_id: str | None = None,
     include_marketplace: bool = True,
     max_additional_results: int = 10,
@@ -456,7 +448,7 @@ async def enrich_library_agents_from_steps(
     search_terms = extract_search_terms_from_steps(decomposition_result)
 
     if not search_terms:
-        return list(existing_agents)
+        return existing_agents
 
     existing_ids: set[str] = set()
     existing_names: set[str] = set()
@@ -516,6 +508,79 @@ async def enrich_library_agents_from_steps(
     return all_agents
 
 
+async def decompose_goal(
+    description: str,
+    context: str = "",
+    library_agents: list[AgentSummary] | None = None,
+) -> DecompositionResult | None:
+    """Break down a goal into steps or return clarifying questions.
+
+    Args:
+        description: Natural language goal description
+        context: Additional context (e.g., answers to previous questions)
+        library_agents: User's library agents available for sub-agent composition
+
+    Returns:
+        DecompositionResult with either:
+        - {"type": "clarifying_questions", "questions": [...]}
+        - {"type": "instructions", "steps": [...]}
+        Or None on error
+
+    Raises:
+        AgentGeneratorNotConfiguredError: If the external service is not configured.
+    """
+    _check_service_configured()
+    logger.info("Calling external Agent Generator service for decompose_goal")
+    result = await decompose_goal_external(
+        description, context, _to_dict_list(library_agents)
+    )
+    return result  # type: ignore[return-value]
+
+
+async def generate_agent(
+    instructions: DecompositionResult | dict[str, Any],
+    library_agents: list[AgentSummary] | list[dict[str, Any]] | None = None,
+    operation_id: str | None = None,
+    task_id: str | None = None,
+) -> dict[str, Any] | None:
+    """Generate agent JSON from instructions.
+
+    Args:
+        instructions: Structured instructions from decompose_goal
+        library_agents: User's library agents available for sub-agent composition
+        operation_id: Operation ID for async processing (enables Redis Streams
+            completion notification)
+        task_id: Task ID for async processing (enables Redis Streams persistence
+            and SSE delivery)
+
+    Returns:
+        Agent JSON dict, {"status": "accepted"} for async, error dict {"type": "error", ...}, or None on error
+
+    Raises:
+        AgentGeneratorNotConfiguredError: If the external service is not configured.
+    """
+    _check_service_configured()
+    logger.info("Calling external Agent Generator service for generate_agent")
+    result = await generate_agent_external(
+        dict(instructions), _to_dict_list(library_agents), operation_id, task_id
+    )
+
+    # Don't modify async response
+    if result and result.get("status") == "accepted":
+        return result
+
+    if result:
+        if isinstance(result, dict) and result.get("type") == "error":
+            return result
+        if "id" not in result:
+            result["id"] = str(uuid.uuid4())
+        if "version" not in result:
+            result["version"] = 1
+        if "is_active" not in result:
+            result["is_active"] = True
+    return result
+
+
 class AgentJsonValidationError(Exception):
     """Raised when agent JSON is invalid or missing required fields."""
 
@@ -595,10 +660,7 @@ def json_to_graph(agent_json: dict[str, Any]) -> Graph:
 
 
 async def save_agent_to_library(
-    agent_json: dict[str, Any],
-    user_id: str,
-    is_update: bool = False,
-    folder_id: str | None = None,
+    agent_json: dict[str, Any], user_id: str, is_update: bool = False
 ) -> tuple[Graph, Any]:
     """Save agent to database and user's library.
 
@@ -606,16 +668,14 @@ async def save_agent_to_library(
         agent_json: Agent JSON dict
         user_id: User ID
         is_update: Whether this is an update to an existing agent
-        folder_id: Optional folder ID to place the agent in
 
     Returns:
         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, folder_id=folder_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]:
@@ -675,14 +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:
@@ -692,3 +750,76 @@ async def get_agent_as_json(
         return None
 
     return graph_to_json(graph)
+
+
+async def generate_agent_patch(
+    update_request: str,
+    current_agent: dict[str, Any],
+    library_agents: list[AgentSummary] | None = None,
+    operation_id: str | None = None,
+    task_id: str | None = None,
+) -> dict[str, Any] | None:
+    """Update an existing agent using natural language.
+
+    The external Agent Generator service handles:
+    - Generating the patch
+    - Applying the patch
+    - Fixing and validating the result
+
+    Args:
+        update_request: Natural language description of changes
+        current_agent: Current agent JSON
+        library_agents: User's library agents available for sub-agent composition
+        operation_id: Operation ID for async processing (enables Redis Streams callback)
+        task_id: Task ID for async processing (enables Redis Streams callback)
+
+    Returns:
+        Updated agent JSON, clarifying questions dict {"type": "clarifying_questions", ...},
+        {"status": "accepted"} for async, error dict {"type": "error", ...}, or None on error
+
+    Raises:
+        AgentGeneratorNotConfiguredError: If the external service is not configured.
+    """
+    _check_service_configured()
+    logger.info("Calling external Agent Generator service for generate_agent_patch")
+    return await generate_agent_patch_external(
+        update_request,
+        current_agent,
+        _to_dict_list(library_agents),
+        operation_id,
+        task_id,
+    )
+
+
+async def customize_template(
+    template_agent: dict[str, Any],
+    modification_request: str,
+    context: str = "",
+) -> dict[str, Any] | None:
+    """Customize a template/marketplace agent using natural language.
+
+    This is used when users want to modify a template or marketplace agent
+    to fit their specific needs before adding it to their library.
+
+    The external Agent Generator service handles:
+    - Understanding the modification request
+    - Applying changes to the template
+    - Fixing and validating the result
+
+    Args:
+        template_agent: The template agent JSON to customize
+        modification_request: Natural language description of customizations
+        context: Additional context (e.g., answers to previous questions)
+
+    Returns:
+        Customized agent JSON, clarifying questions dict {"type": "clarifying_questions", ...},
+        error dict {"type": "error", ...}, or None on unexpected error
+
+    Raises:
+        AgentGeneratorNotConfiguredError: If the external service is not configured.
+    """
+    _check_service_configured()
+    logger.info("Calling external Agent Generator service for customize_template")
+    return await customize_template_external(
+        template_agent, modification_request, context
+    )

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

@@ -0,0 +1,154 @@
+"""Dummy Agent Generator for testing.
+
+Returns mock responses matching the format expected from the external service.
+Enable via AGENTGENERATOR_USE_DUMMY=true in settings.
+
+WARNING: This is for testing only. Do not use in production.
+"""
+
+import asyncio
+import logging
+import uuid
+from typing import Any
+
+logger = logging.getLogger(__name__)
+
+# Dummy decomposition result (instructions type)
+DUMMY_DECOMPOSITION_RESULT: dict[str, Any] = {
+    "type": "instructions",
+    "steps": [
+        {
+            "description": "Get input from user",
+            "action": "input",
+            "block_name": "AgentInputBlock",
+        },
+        {
+            "description": "Process the input",
+            "action": "process",
+            "block_name": "TextFormatterBlock",
+        },
+        {
+            "description": "Return output to user",
+            "action": "output",
+            "block_name": "AgentOutputBlock",
+        },
+    ],
+}
+
+# Block IDs from backend/blocks/io.py
+AGENT_INPUT_BLOCK_ID = "c0a8e994-ebf1-4a9c-a4d8-89d09c86741b"
+AGENT_OUTPUT_BLOCK_ID = "363ae599-353e-4804-937e-b2ee3cef3da4"
+
+
+def _generate_dummy_agent_json() -> dict[str, Any]:
+    """Generate a minimal valid agent JSON for testing."""
+    input_node_id = str(uuid.uuid4())
+    output_node_id = str(uuid.uuid4())
+
+    return {
+        "id": str(uuid.uuid4()),
+        "version": 1,
+        "is_active": True,
+        "name": "Dummy Test Agent",
+        "description": "A dummy agent generated for testing purposes",
+        "nodes": [
+            {
+                "id": input_node_id,
+                "block_id": AGENT_INPUT_BLOCK_ID,
+                "input_default": {
+                    "name": "input",
+                    "title": "Input",
+                    "description": "Enter your input",
+                    "placeholder_values": [],
+                },
+                "metadata": {"position": {"x": 0, "y": 0}},
+            },
+            {
+                "id": output_node_id,
+                "block_id": AGENT_OUTPUT_BLOCK_ID,
+                "input_default": {
+                    "name": "output",
+                    "title": "Output",
+                    "description": "Agent output",
+                    "format": "{output}",
+                },
+                "metadata": {"position": {"x": 400, "y": 0}},
+            },
+        ],
+        "links": [
+            {
+                "id": str(uuid.uuid4()),
+                "source_id": input_node_id,
+                "sink_id": output_node_id,
+                "source_name": "result",
+                "sink_name": "value",
+                "is_static": False,
+            },
+        ],
+    }
+
+
+async def decompose_goal_dummy(
+    description: str,
+    context: str = "",
+    library_agents: list[dict[str, Any]] | None = None,
+) -> dict[str, Any]:
+    """Return dummy decomposition result."""
+    logger.info("Using dummy agent generator for decompose_goal")
+    return DUMMY_DECOMPOSITION_RESULT.copy()
+
+
+async def generate_agent_dummy(
+    instructions: dict[str, Any],
+    library_agents: list[dict[str, Any]] | None = None,
+    operation_id: str | None = None,
+    task_id: str | None = None,
+) -> dict[str, Any]:
+    """Return dummy agent JSON after a simulated delay."""
+    logger.info("Using dummy agent generator for generate_agent (30s delay)")
+    await asyncio.sleep(30)
+    return _generate_dummy_agent_json()
+
+
+async def generate_agent_patch_dummy(
+    update_request: str,
+    current_agent: dict[str, Any],
+    library_agents: list[dict[str, Any]] | None = None,
+    operation_id: str | None = None,
+    task_id: str | None = None,
+) -> dict[str, Any]:
+    """Return dummy patched agent (returns the current agent with updated description)."""
+    logger.info("Using dummy agent generator for generate_agent_patch")
+    patched = current_agent.copy()
+    patched["description"] = (
+        f"{current_agent.get('description', '')} (updated: {update_request})"
+    )
+    return patched
+
+
+async def customize_template_dummy(
+    template_agent: dict[str, Any],
+    modification_request: str,
+    context: str = "",
+) -> dict[str, Any]:
+    """Return dummy customized template (returns template with updated description)."""
+    logger.info("Using dummy agent generator for customize_template")
+    customized = template_agent.copy()
+    customized["description"] = (
+        f"{template_agent.get('description', '')} (customized: {modification_request})"
+    )
+    return customized
+
+
+async def get_blocks_dummy() -> list[dict[str, Any]]:
+    """Return dummy blocks list."""
+    logger.info("Using dummy agent generator for get_blocks")
+    return [
+        {"id": AGENT_INPUT_BLOCK_ID, "name": "AgentInputBlock"},
+        {"id": AGENT_OUTPUT_BLOCK_ID, "name": "AgentOutputBlock"},
+    ]
+
+
+async def health_check_dummy() -> bool:
+    """Always returns healthy for dummy service."""
+    return True

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

@@ -0,0 +1,549 @@
+"""External Agent Generator service client.
+
+This module provides a client for communicating with the external Agent Generator
+microservice. When AGENTGENERATOR_HOST is configured, the agent generation functions
+will delegate to the external service instead of using the built-in LLM-based implementation.
+"""
+
+import logging
+from typing import Any
+
+import httpx
+
+from backend.util.settings import Settings
+
+from .dummy import (
+    customize_template_dummy,
+    decompose_goal_dummy,
+    generate_agent_dummy,
+    generate_agent_patch_dummy,
+    get_blocks_dummy,
+    health_check_dummy,
+)
+
+logger = logging.getLogger(__name__)
+
+_dummy_mode_warned = False
+
+
+def _create_error_response(
+    error_message: str,
+    error_type: str = "unknown",
+    details: dict[str, Any] | None = None,
+) -> dict[str, Any]:
+    """Create a standardized error response dict.
+
+    Args:
+        error_message: Human-readable error message
+        error_type: Machine-readable error type
+        details: Optional additional error details
+
+    Returns:
+        Error dict with type="error" and error details
+    """
+    response: dict[str, Any] = {
+        "type": "error",
+        "error": error_message,
+        "error_type": error_type,
+    }
+    if details:
+        response["details"] = details
+    return response
+
+
+def _classify_http_error(e: httpx.HTTPStatusError) -> tuple[str, str]:
+    """Classify an HTTP error into error_type and message.
+
+    Args:
+        e: The HTTP status error
+
+    Returns:
+        Tuple of (error_type, error_message)
+    """
+    status = e.response.status_code
+    if status == 429:
+        return "rate_limit", f"Agent Generator rate limited: {e}"
+    elif status == 503:
+        return "service_unavailable", f"Agent Generator unavailable: {e}"
+    elif status == 504 or status == 408:
+        return "timeout", f"Agent Generator timed out: {e}"
+    else:
+        return "http_error", f"HTTP error calling Agent Generator: {e}"
+
+
+def _classify_request_error(e: httpx.RequestError) -> tuple[str, str]:
+    """Classify a request error into error_type and message.
+
+    Args:
+        e: The request error
+
+    Returns:
+        Tuple of (error_type, error_message)
+    """
+    error_str = str(e).lower()
+    if "timeout" in error_str or "timed out" in error_str:
+        return "timeout", f"Agent Generator request timed out: {e}"
+    elif "connect" in error_str:
+        return "connection_error", f"Could not connect to Agent Generator: {e}"
+    else:
+        return "request_error", f"Request error calling Agent Generator: {e}"
+
+
+_client: httpx.AsyncClient | None = None
+_settings: Settings | None = None
+
+
+def _get_settings() -> Settings:
+    """Get or create settings singleton."""
+    global _settings
+    if _settings is None:
+        _settings = Settings()
+    return _settings
+
+
+def _is_dummy_mode() -> bool:
+    """Check if dummy mode is enabled for testing."""
+    global _dummy_mode_warned
+    settings = _get_settings()
+    is_dummy = bool(settings.config.agentgenerator_use_dummy)
+    if is_dummy and not _dummy_mode_warned:
+        logger.warning(
+            "Agent Generator running in DUMMY MODE - returning mock responses. "
+            "Do not use in production!"
+        )
+        _dummy_mode_warned = True
+    return is_dummy
+
+
+def is_external_service_configured() -> bool:
+    """Check if external Agent Generator service is configured (or dummy mode)."""
+    settings = _get_settings()
+    return bool(settings.config.agentgenerator_host) or bool(
+        settings.config.agentgenerator_use_dummy
+    )
+
+
+def _get_base_url() -> str:
+    """Get the base URL for the external service."""
+    settings = _get_settings()
+    host = settings.config.agentgenerator_host
+    port = settings.config.agentgenerator_port
+    return f"http://{host}:{port}"
+
+
+def _get_client() -> httpx.AsyncClient:
+    """Get or create the HTTP client for the external service."""
+    global _client
+    if _client is None:
+        settings = _get_settings()
+        _client = httpx.AsyncClient(
+            base_url=_get_base_url(),
+            timeout=httpx.Timeout(settings.config.agentgenerator_timeout),
+        )
+    return _client
+
+
+async def decompose_goal_external(
+    description: str,
+    context: str = "",
+    library_agents: list[dict[str, Any]] | None = None,
+) -> dict[str, Any] | None:
+    """Call the external service to decompose a goal.
+
+    Args:
+        description: Natural language goal description
+        context: Additional context (e.g., answers to previous questions)
+        library_agents: User's library agents available for sub-agent composition
+
+    Returns:
+        Dict with either:
+        - {"type": "clarifying_questions", "questions": [...]}
+        - {"type": "instructions", "steps": [...]}
+        - {"type": "unachievable_goal", ...}
+        - {"type": "vague_goal", ...}
+        - {"type": "error", "error": "...", "error_type": "..."} on error
+        Or None on unexpected error
+    """
+    if _is_dummy_mode():
+        return await decompose_goal_dummy(description, context, library_agents)
+
+    client = _get_client()
+
+    if context:
+        description = f"{description}\n\nAdditional context from user:\n{context}"
+
+    payload: dict[str, Any] = {"description": description}
+    if library_agents:
+        payload["library_agents"] = library_agents
+
+    try:
+        response = await client.post("/api/decompose-description", json=payload)
+        response.raise_for_status()
+        data = response.json()
+
+        if not data.get("success"):
+            error_msg = data.get("error", "Unknown error from Agent Generator")
+            error_type = data.get("error_type", "unknown")
+            logger.error(
+                f"Agent Generator decomposition failed: {error_msg} "
+                f"(type: {error_type})"
+            )
+            return _create_error_response(error_msg, error_type)
+
+        # Map the response to the expected format
+        response_type = data.get("type")
+        if response_type == "instructions":
+            return {"type": "instructions", "steps": data.get("steps", [])}
+        elif response_type == "clarifying_questions":
+            return {
+                "type": "clarifying_questions",
+                "questions": data.get("questions", []),
+            }
+        elif response_type == "unachievable_goal":
+            return {
+                "type": "unachievable_goal",
+                "reason": data.get("reason"),
+                "suggested_goal": data.get("suggested_goal"),
+            }
+        elif response_type == "vague_goal":
+            return {
+                "type": "vague_goal",
+                "suggested_goal": data.get("suggested_goal"),
+            }
+        elif response_type == "error":
+            # Pass through error from the service
+            return _create_error_response(
+                data.get("error", "Unknown error"),
+                data.get("error_type", "unknown"),
+            )
+        else:
+            logger.error(
+                f"Unknown response type from external service: {response_type}"
+            )
+            return _create_error_response(
+                f"Unknown response type from Agent Generator: {response_type}",
+                "invalid_response",
+            )
+
+    except httpx.HTTPStatusError as e:
+        error_type, error_msg = _classify_http_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
+    except httpx.RequestError as e:
+        error_type, error_msg = _classify_request_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
+    except Exception as e:
+        error_msg = f"Unexpected error calling Agent Generator: {e}"
+        logger.error(error_msg)
+        return _create_error_response(error_msg, "unexpected_error")
+
+
+async def generate_agent_external(
+    instructions: dict[str, Any],
+    library_agents: list[dict[str, Any]] | None = None,
+    operation_id: str | None = None,
+    task_id: str | None = None,
+) -> dict[str, Any] | None:
+    """Call the external service to generate an agent from instructions.
+
+    Args:
+        instructions: Structured instructions from decompose_goal
+        library_agents: User's library agents available for sub-agent composition
+        operation_id: Operation ID for async processing (enables Redis Streams callback)
+        task_id: Task ID for async processing (enables Redis Streams callback)
+
+    Returns:
+        Agent JSON dict, {"status": "accepted"} for async, or error dict {"type": "error", ...} on error
+    """
+    if _is_dummy_mode():
+        return await generate_agent_dummy(
+            instructions, library_agents, operation_id, task_id
+        )
+
+    client = _get_client()
+
+    # Build request payload
+    payload: dict[str, Any] = {"instructions": instructions}
+    if library_agents:
+        payload["library_agents"] = library_agents
+    if operation_id and task_id:
+        payload["operation_id"] = operation_id
+        payload["task_id"] = task_id
+
+    try:
+        response = await client.post("/api/generate-agent", json=payload)
+
+        # Handle 202 Accepted for async processing
+        if response.status_code == 202:
+            logger.info(
+                f"Agent Generator accepted async request "
+                f"(operation_id={operation_id}, task_id={task_id})"
+            )
+            return {
+                "status": "accepted",
+                "operation_id": operation_id,
+                "task_id": task_id,
+            }
+
+        response.raise_for_status()
+        data = response.json()
+
+        if not data.get("success"):
+            error_msg = data.get("error", "Unknown error from Agent Generator")
+            error_type = data.get("error_type", "unknown")
+            logger.error(
+                f"Agent Generator generation failed: {error_msg} (type: {error_type})"
+            )
+            return _create_error_response(error_msg, error_type)
+
+        return data.get("agent_json")
+
+    except httpx.HTTPStatusError as e:
+        error_type, error_msg = _classify_http_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
+    except httpx.RequestError as e:
+        error_type, error_msg = _classify_request_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
+    except Exception as e:
+        error_msg = f"Unexpected error calling Agent Generator: {e}"
+        logger.error(error_msg)
+        return _create_error_response(error_msg, "unexpected_error")
+
+
+async def generate_agent_patch_external(
+    update_request: str,
+    current_agent: dict[str, Any],
+    library_agents: list[dict[str, Any]] | None = None,
+    operation_id: str | None = None,
+    task_id: str | None = None,
+) -> dict[str, Any] | None:
+    """Call the external service to generate a patch for an existing agent.
+
+    Args:
+        update_request: Natural language description of changes
+        current_agent: Current agent JSON
+        library_agents: User's library agents available for sub-agent composition
+        operation_id: Operation ID for async processing (enables Redis Streams callback)
+        task_id: Task ID for async processing (enables Redis Streams callback)
+
+    Returns:
+        Updated agent JSON, clarifying questions dict, {"status": "accepted"} for async, or error dict on error
+    """
+    if _is_dummy_mode():
+        return await generate_agent_patch_dummy(
+            update_request, current_agent, library_agents, operation_id, task_id
+        )
+
+    client = _get_client()
+
+    # Build request payload
+    payload: dict[str, Any] = {
+        "update_request": update_request,
+        "current_agent_json": current_agent,
+    }
+    if library_agents:
+        payload["library_agents"] = library_agents
+    if operation_id and task_id:
+        payload["operation_id"] = operation_id
+        payload["task_id"] = task_id
+
+    try:
+        response = await client.post("/api/update-agent", json=payload)
+
+        # Handle 202 Accepted for async processing
+        if response.status_code == 202:
+            logger.info(
+                f"Agent Generator accepted async update request "
+                f"(operation_id={operation_id}, task_id={task_id})"
+            )
+            return {
+                "status": "accepted",
+                "operation_id": operation_id,
+                "task_id": task_id,
+            }
+
+        response.raise_for_status()
+        data = response.json()
+
+        if not data.get("success"):
+            error_msg = data.get("error", "Unknown error from Agent Generator")
+            error_type = data.get("error_type", "unknown")
+            logger.error(
+                f"Agent Generator patch generation failed: {error_msg} "
+                f"(type: {error_type})"
+            )
+            return _create_error_response(error_msg, error_type)
+
+        # Check if it's clarifying questions
+        if data.get("type") == "clarifying_questions":
+            return {
+                "type": "clarifying_questions",
+                "questions": data.get("questions", []),
+            }
+
+        # Check if it's an error passed through
+        if data.get("type") == "error":
+            return _create_error_response(
+                data.get("error", "Unknown error"),
+                data.get("error_type", "unknown"),
+            )
+
+        # Otherwise return the updated agent JSON
+        return data.get("agent_json")
+
+    except httpx.HTTPStatusError as e:
+        error_type, error_msg = _classify_http_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
+    except httpx.RequestError as e:
+        error_type, error_msg = _classify_request_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
+    except Exception as e:
+        error_msg = f"Unexpected error calling Agent Generator: {e}"
+        logger.error(error_msg)
+        return _create_error_response(error_msg, "unexpected_error")
+
+
+async def customize_template_external(
+    template_agent: dict[str, Any],
+    modification_request: str,
+    context: str = "",
+) -> dict[str, Any] | None:
+    """Call the external service to customize a template/marketplace agent.
+
+    Args:
+        template_agent: The template agent JSON to customize
+        modification_request: Natural language description of customizations
+        context: Additional context (e.g., answers to previous questions)
+
+    Returns:
+        Customized agent JSON, clarifying questions dict, or error dict on error
+    """
+    if _is_dummy_mode():
+        return await customize_template_dummy(
+            template_agent, modification_request, context
+        )
+
+    client = _get_client()
+
+    request = modification_request
+    if context:
+        request = f"{modification_request}\n\nAdditional context from user:\n{context}"
+
+    payload: dict[str, Any] = {
+        "template_agent_json": template_agent,
+        "modification_request": request,
+    }
+
+    try:
+        response = await client.post("/api/template-modification", json=payload)
+        response.raise_for_status()
+        data = response.json()
+
+        if not data.get("success"):
+            error_msg = data.get("error", "Unknown error from Agent Generator")
+            error_type = data.get("error_type", "unknown")
+            logger.error(
+                f"Agent Generator template customization failed: {error_msg} "
+                f"(type: {error_type})"
+            )
+            return _create_error_response(error_msg, error_type)
+
+        # Check if it's clarifying questions
+        if data.get("type") == "clarifying_questions":
+            return {
+                "type": "clarifying_questions",
+                "questions": data.get("questions", []),
+            }
+
+        # Check if it's an error passed through
+        if data.get("type") == "error":
+            return _create_error_response(
+                data.get("error", "Unknown error"),
+                data.get("error_type", "unknown"),
+            )
+
+        # Otherwise return the customized agent JSON
+        return data.get("agent_json")
+
+    except httpx.HTTPStatusError as e:
+        error_type, error_msg = _classify_http_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
+    except httpx.RequestError as e:
+        error_type, error_msg = _classify_request_error(e)
+        logger.error(error_msg)
+        return _create_error_response(error_msg, error_type)
+    except Exception as e:
+        error_msg = f"Unexpected error calling Agent Generator: {e}"
+        logger.error(error_msg)
+        return _create_error_response(error_msg, "unexpected_error")
+
+
+async def get_blocks_external() -> list[dict[str, Any]] | None:
+    """Get available blocks from the external service.
+
+    Returns:
+        List of block info dicts or None on error
+    """
+    if _is_dummy_mode():
+        return await get_blocks_dummy()
+
+    client = _get_client()
+
+    try:
+        response = await client.get("/api/blocks")
+        response.raise_for_status()
+        data = response.json()
+
+        if not data.get("success"):
+            logger.error("External service returned error getting blocks")
+            return None
+
+        return data.get("blocks", [])
+
+    except httpx.HTTPStatusError as e:
+        logger.error(f"HTTP error getting blocks from external service: {e}")
+        return None
+    except httpx.RequestError as e:
+        logger.error(f"Request error getting blocks from external service: {e}")
+        return None
+    except Exception as e:
+        logger.error(f"Unexpected error getting blocks from external service: {e}")
+        return None
+
+
+async def health_check() -> bool:
+    """Check if the external service is healthy.
+
+    Returns:
+        True if healthy, False otherwise
+    """
+    if not is_external_service_configured():
+        return False
+
+    if _is_dummy_mode():
+        return await health_check_dummy()
+
+    client = _get_client()
+
+    try:
+        response = await client.get("/health")
+        response.raise_for_status()
+        data = response.json()
+        return data.get("status") == "healthy" and data.get("blocks_loaded", False)
+    except Exception as e:
+        logger.warning(f"External agent generator health check failed: {e}")
+        return False
+
+
+async def close_client() -> None:
+    """Close the HTTP client."""
+    global _client
+    if _client is not None:
+        await _client.aclose()
+        _client = None

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

@@ -5,15 +5,15 @@ import re
 from datetime import datetime, timedelta, timezone
 from typing import Any
 
-from pydantic import BaseModel, Field, field_validator
+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
-from .execution_utils import TERMINAL_STATUSES, wait_for_execution
 from .models import (
     AgentOutputResponse,
     ErrorResponse,
@@ -34,7 +34,6 @@ class AgentOutputInput(BaseModel):
     store_slug: str = ""
     execution_id: str = ""
     run_time: str = "latest"
-    wait_if_running: int = Field(default=0, ge=0, le=300)
 
     @field_validator(
         "agent_name",
@@ -118,11 +117,6 @@ class AgentOutputTool(BaseTool):
         Select which run to retrieve using:
         - execution_id: Specific execution ID
         - run_time: 'latest' (default), 'yesterday', 'last week', or ISO date 'YYYY-MM-DD'
-
-        Wait for completion (optional):
-        - wait_if_running: Max seconds to wait if execution is still running (0-300).
-          If the execution is running/queued, waits up to this many seconds for completion.
-          Returns current status on timeout. If already finished, returns immediately.
         """
 
     @property
@@ -152,13 +146,6 @@ class AgentOutputTool(BaseTool):
                         "Time filter: 'latest', 'yesterday', 'last week', or 'YYYY-MM-DD'"
                     ),
                 },
-                "wait_if_running": {
-                    "type": "integer",
-                    "description": (
-                        "Max seconds to wait if execution is still running (0-300). "
-                        "If running, waits for completion. Returns current state on timeout."
-                    ),
-                },
             },
             "required": [],
         }
@@ -178,12 +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}")
@@ -197,7 +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,
@@ -209,7 +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,
@@ -238,20 +223,14 @@ class AgentOutputTool(BaseTool):
         execution_id: str | None,
         time_start: datetime | None,
         time_end: datetime | None,
-        include_running: bool = False,
     ) -> tuple[GraphExecution | None, list[GraphExecutionMeta], str | None]:
         """
         Fetch execution(s) based on filters.
         Returns (single_execution, available_executions_meta, error_message).
-
-        Args:
-            include_running: If True, also look for running/queued executions (for waiting)
         """
-        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,
@@ -260,25 +239,11 @@ class AgentOutputTool(BaseTool):
                 return None, [], f"Execution '{execution_id}' not found"
             return execution, [], None
 
-        # Determine which statuses to query
-        statuses = [ExecutionStatus.COMPLETED]
-        if include_running:
-            statuses.extend(
-                [
-                    ExecutionStatus.RUNNING,
-                    ExecutionStatus.QUEUED,
-                    ExecutionStatus.INCOMPLETE,
-                    ExecutionStatus.REVIEW,
-                    ExecutionStatus.FAILED,
-                    ExecutionStatus.TERMINATED,
-                ]
-            )
-
-        # Get executions with time filters
-        executions = await exec_db.get_graph_executions(
+        # Get completed executions with time filters
+        executions = await execution_db.get_graph_executions(
             graph_id=graph_id,
             user_id=user_id,
-            statuses=statuses,
+            statuses=[ExecutionStatus.COMPLETED],
             created_time_gte=time_start,
             created_time_lte=time_end,
             limit=10,
@@ -289,7 +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,
@@ -297,7 +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,
@@ -345,33 +310,10 @@ class AgentOutputTool(BaseTool):
                 for e in available_executions[:5]
             ]
 
-        # Build appropriate message based on execution status
-        if execution.status == ExecutionStatus.COMPLETED:
-            message = f"Found execution outputs for agent '{agent.name}'"
-        elif execution.status == ExecutionStatus.FAILED:
-            message = f"Execution for agent '{agent.name}' failed"
-        elif execution.status == ExecutionStatus.TERMINATED:
-            message = f"Execution for agent '{agent.name}' was terminated"
-        elif execution.status == ExecutionStatus.REVIEW:
-            message = (
-                f"Execution for agent '{agent.name}' is awaiting human review. "
-                "The user needs to approve it before it can continue."
-            )
-        elif execution.status in (
-            ExecutionStatus.RUNNING,
-            ExecutionStatus.QUEUED,
-            ExecutionStatus.INCOMPLETE,
-        ):
-            message = (
-                f"Execution for agent '{agent.name}' is still {execution.status.value}. "
-                "Results may be incomplete. Use wait_if_running to wait for completion."
-            )
-        else:
-            message = f"Found execution for agent '{agent.name}' (status: {execution.status.value})"
-
+        message = f"Found execution outputs for agent '{agent.name}'"
         if len(available_executions) > 1:
             message += (
-                f" Showing latest of {len(available_executions)} matching executions."
+                f". Showing latest of {len(available_executions)} matching executions."
             )
 
         return AgentOutputResponse(
@@ -438,7 +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,
@@ -450,7 +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:
@@ -486,17 +428,13 @@ class AgentOutputTool(BaseTool):
         # Parse time expression
         time_start, time_end = parse_time_expression(input_data.run_time)
 
-        # Check if we should wait for running executions
-        wait_timeout = input_data.wait_if_running
-
-        # Fetch execution(s) - include running if we're going to wait
+        # Fetch execution(s)
         execution, available_executions, exec_error = await self._get_execution(
             user_id=user_id,
             graph_id=agent.graph_id,
             execution_id=input_data.execution_id or None,
             time_start=time_start,
             time_end=time_end,
-            include_running=wait_timeout > 0,
         )
 
         if exec_error:
@@ -505,17 +443,4 @@ class AgentOutputTool(BaseTool):
                 session_id=session_id,
             )
 
-        # If we have an execution that's still running and we should wait
-        if execution and wait_timeout > 0 and execution.status not in TERMINAL_STATUSES:
-            logger.info(
-                f"Execution {execution.id} is {execution.status}, "
-                f"waiting up to {wait_timeout}s for completion"
-            )
-            execution = await wait_for_execution(
-                user_id=user_id,
-                graph_id=agent.graph_id,
-                execution_id=execution.id,
-                timeout_seconds=wait_timeout,
-            )
-
         return self._build_response(agent, execution, available_executions, session_id)

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

@@ -1,15 +1,11 @@
 """Shared agent search functionality for find_agent and find_library_agent tools."""
 
-from __future__ import annotations
-
 import logging
 import re
-from typing import TYPE_CHECKING, Literal
+from typing import Literal
 
-if TYPE_CHECKING:
-    from backend.api.features.library.model import LibraryAgent
-
-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 (
@@ -29,24 +25,92 @@ _UUID_PATTERN = re.compile(
     re.IGNORECASE,
 )
 
-# Keywords that should be treated as "list all" rather than a literal search
-_LIST_ALL_KEYWORDS = frozenset({"all", "*", "everything", "any", ""})
+
+def _is_uuid(text: str) -> bool:
+    """Check if text is a valid UUID v4."""
+    return bool(_UUID_PATTERN.match(text.strip()))
+
+
+async def _get_library_agent_by_id(user_id: str, agent_id: str) -> AgentInfo | None:
+    """Fetch a library agent by ID (library agent ID or graph_id).
+
+    Tries multiple lookup strategies:
+    1. First by graph_id (AgentGraph primary key)
+    2. Then by library agent ID (LibraryAgent primary key)
+
+    Args:
+        user_id: The user ID
+        agent_id: The ID to look up (can be graph_id or library agent ID)
+
+    Returns:
+        AgentInfo if found, None otherwise
+    """
+    try:
+        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(
+                id=agent.id,
+                name=agent.name,
+                description=agent.description or "",
+                source="library",
+                in_library=True,
+                creator=agent.creator_name,
+                status=agent.status.value,
+                can_access_graph=agent.can_access_graph,
+                has_external_trigger=agent.has_external_trigger,
+                new_output=agent.new_output,
+                graph_id=agent.graph_id,
+            )
+    except DatabaseError:
+        raise
+    except Exception as e:
+        logger.warning(
+            f"Could not fetch library agent by graph_id {agent_id}: {e}",
+            exc_info=True,
+        )
+
+    try:
+        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(
+                id=agent.id,
+                name=agent.name,
+                description=agent.description or "",
+                source="library",
+                in_library=True,
+                creator=agent.creator_name,
+                status=agent.status.value,
+                can_access_graph=agent.can_access_graph,
+                has_external_trigger=agent.has_external_trigger,
+                new_output=agent.new_output,
+                graph_id=agent.graph_id,
+            )
+    except NotFoundError:
+        logger.debug(f"Library agent not found by library_id: {agent_id}")
+    except DatabaseError:
+        raise
+    except Exception as e:
+        logger.warning(
+            f"Could not fetch library agent by library_id {agent_id}: {e}",
+            exc_info=True,
+        )
+
+    return None
 
 
 async def search_agents(
     query: str,
     source: SearchSource,
-    session_id: str | None = None,
+    session_id: str | None,
     user_id: str | None = None,
 ) -> ToolResponseBase:
     """
     Search for agents in marketplace or user library.
 
-    For library searches, keywords like "all", "*", "everything", or an empty
-    query will list all agents without filtering.
-
     Args:
-        query: Search query string. Special keywords list all library agents.
+        query: Search query string
         source: "marketplace" or "library"
         session_id: Chat session ID
         user_id: User ID (required for library search)
@@ -54,11 +118,7 @@ async def search_agents(
     Returns:
         AgentsFoundResponse, NoResultsResponse, or ErrorResponse
     """
-    # Normalize list-all keywords to empty string for library searches
-    if source == "library" and query.lower().strip() in _LIST_ALL_KEYWORDS:
-        query = ""
-
-    if source == "marketplace" and not query:
+    if not query:
         return ErrorResponse(
             message="Please provide a search query", session_id=session_id
         )
@@ -73,7 +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(
@@ -98,18 +158,28 @@ async def search_agents(
                     logger.info(f"Found agent by direct ID lookup: {agent.name}")
 
             if not agents:
-                search_term = query or None
-                logger.info(
-                    f"{'Listing all agents in' if not query else 'Searching'} "
-                    f"user library{'' if not query else f' for: {query}'}"
-                )
-                results = await library_db().list_library_agents(
+                logger.info(f"Searching user library for: {query}")
+                results = await library_db.list_library_agents(
                     user_id=user_id,  # type: ignore[arg-type]
-                    search_term=search_term,
-                    page_size=50 if not query else 10,
+                    search_term=query,
+                    page_size=10,
                 )
                 for agent in results.agents:
-                    agents.append(_library_agent_to_info(agent))
+                    agents.append(
+                        AgentInfo(
+                            id=agent.id,
+                            name=agent.name,
+                            description=agent.description or "",
+                            source="library",
+                            in_library=True,
+                            creator=agent.creator_name,
+                            status=agent.status.value,
+                            can_access_graph=agent.can_access_graph,
+                            has_external_trigger=agent.has_external_trigger,
+                            new_output=agent.new_output,
+                            graph_id=agent.graph_id,
+                        )
+                    )
         logger.info(f"Found {len(agents)} agents in {source}")
     except NotFoundError:
         pass
@@ -122,62 +192,42 @@ async def search_agents(
         )
 
     if not agents:
-        if source == "marketplace":
-            suggestions = [
+        suggestions = (
+            [
                 "Try more general terms",
                 "Browse categories in the marketplace",
                 "Check spelling",
             ]
-            no_results_msg = (
-                f"No agents found matching '{query}'. Let the user know they can "
-                "try different keywords or browse the marketplace. Also let them "
-                "know you can create a custom agent for them based on their needs."
-            )
-        elif not query:
-            # User asked to list all but library is empty
-            suggestions = [
-                "Browse the marketplace to find and add agents",
-                "Use find_agent to search the marketplace",
-            ]
-            no_results_msg = (
-                "Your library is empty. Let the user know they can browse the "
-                "marketplace to find agents, or you can create a custom agent "
-                "for them based on their needs."
-            )
-        else:
-            suggestions = [
+            if source == "marketplace"
+            else [
                 "Try different keywords",
                 "Use find_agent to search the marketplace",
                 "Check your library at /library",
             ]
-            no_results_msg = (
-                f"No agents matching '{query}' found in your library. Let the "
-                "user know you can create a custom agent for them based on "
-                "their needs."
-            )
+        )
+        no_results_msg = (
+            f"No agents found matching '{query}'. Let the user know they can try different keywords or browse the marketplace. Also let them know you can create a custom agent for them based on their needs."
+            if source == "marketplace"
+            else f"No agents matching '{query}' found in your library. Let the user know you can create a custom agent for them based on their needs."
+        )
         return NoResultsResponse(
             message=no_results_msg, session_id=session_id, suggestions=suggestions
         )
 
-    if source == "marketplace":
-        title = (
-            f"Found {len(agents)} agent{'s' if len(agents) != 1 else ''} for '{query}'"
-        )
-    elif not query:
-        title = f"Found {len(agents)} agent{'s' if len(agents) != 1 else ''} in your library"
-    else:
-        title = f"Found {len(agents)} agent{'s' if len(agents) != 1 else ''} in your library for '{query}'"
+    title = f"Found {len(agents)} agent{'s' if len(agents) != 1 else ''} "
+    title += (
+        f"for '{query}'"
+        if source == "marketplace"
+        else f"in your library for '{query}'"
+    )
 
     message = (
         "Now you have found some options for the user to choose from. "
         "You can add a link to a recommended agent at: /marketplace/agent/agent_id "
-        "Please ask the user if they would like to use any of these agents. "
-        "Let the user know we can create a custom agent for them based on their needs."
+        "Please ask the user if they would like to use any of these agents. Let the user know we can create a custom agent for them based on their needs."
         if source == "marketplace"
-        else "Found agents in the user's library. You can provide a link to view "
-        "an agent at: /library/agents/{agent_id}. Use agent_output to get "
-        "execution results, or run_agent to execute. Let the user know we can "
-        "create a custom agent for them based on their needs."
+        else "Found agents in the user's library. You can provide a link to view an agent at: "
+        "/library/agents/{agent_id}. Use agent_output to get execution results, or run_agent to execute. Let the user know we can create a custom agent for them based on their needs."
     )
 
     return AgentsFoundResponse(
@@ -187,70 +237,3 @@ async def search_agents(
         count=len(agents),
         session_id=session_id,
     )
-
-
-def _is_uuid(text: str) -> bool:
-    """Check if text is a valid UUID v4."""
-    return bool(_UUID_PATTERN.match(text.strip()))
-
-
-def _library_agent_to_info(agent: LibraryAgent) -> AgentInfo:
-    """Convert a library agent model to an AgentInfo."""
-    return AgentInfo(
-        id=agent.id,
-        name=agent.name,
-        description=agent.description or "",
-        source="library",
-        in_library=True,
-        creator=agent.creator_name,
-        status=agent.status.value,
-        can_access_graph=agent.can_access_graph,
-        has_external_trigger=agent.has_external_trigger,
-        new_output=agent.new_output,
-        graph_id=agent.graph_id,
-        graph_version=agent.graph_version,
-        input_schema=agent.input_schema,
-        output_schema=agent.output_schema,
-    )
-
-
-async def _get_library_agent_by_id(user_id: str, agent_id: str) -> AgentInfo | None:
-    """Fetch a library agent by ID (library agent ID or graph_id).
-
-    Tries multiple lookup strategies:
-    1. First by graph_id (AgentGraph primary key)
-    2. Then by library agent ID (LibraryAgent primary key)
-    """
-    lib_db = library_db()
-
-    try:
-        agent = await lib_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 _library_agent_to_info(agent)
-    except NotFoundError:
-        logger.debug(f"Library agent not found by graph_id: {agent_id}")
-    except DatabaseError:
-        raise
-    except Exception as e:
-        logger.warning(
-            f"Could not fetch library agent by graph_id {agent_id}: {e}",
-            exc_info=True,
-        )
-
-    try:
-        agent = await lib_db.get_library_agent(agent_id, user_id)
-        if agent:
-            logger.debug(f"Found library agent by library_id: {agent.name}")
-            return _library_agent_to_info(agent)
-    except NotFoundError:
-        logger.debug(f"Library agent not found by library_id: {agent_id}")
-    except DatabaseError:
-        raise
-    except Exception as e:
-        logger.warning(
-            f"Could not fetch library agent by library_id {agent_id}: {e}",
-            exc_info=True,
-        )
-
-    return None

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

@@ -0,0 +1,129 @@
+"""Base classes and shared utilities for chat tools."""
+
+import logging
+from typing import Any
+
+from openai.types.chat import ChatCompletionToolParam
+
+from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.response_model import StreamToolOutputAvailable
+
+from .models import ErrorResponse, NeedLoginResponse, ToolResponseBase
+
+logger = logging.getLogger(__name__)
+
+
+class BaseTool:
+    """Base class for all chat tools."""
+
+    @property
+    def name(self) -> str:
+        """Tool name for OpenAI function calling."""
+        raise NotImplementedError
+
+    @property
+    def description(self) -> str:
+        """Tool description for OpenAI."""
+        raise NotImplementedError
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        """Tool parameters schema for OpenAI."""
+        raise NotImplementedError
+
+    @property
+    def requires_auth(self) -> bool:
+        """Whether this tool requires authentication."""
+        return False
+
+    @property
+    def is_long_running(self) -> bool:
+        """Whether this tool is long-running and should execute in background.
+
+        Long-running tools (like agent generation) are executed via background
+        tasks to survive SSE disconnections. The result is persisted to chat
+        history and visible when the user refreshes.
+        """
+        return False
+
+    def as_openai_tool(self) -> ChatCompletionToolParam:
+        """Convert to OpenAI tool format."""
+        return ChatCompletionToolParam(
+            type="function",
+            function={
+                "name": self.name,
+                "description": self.description,
+                "parameters": self.parameters,
+            },
+        )
+
+    async def execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        tool_call_id: str,
+        **kwargs,
+    ) -> StreamToolOutputAvailable:
+        """Execute the tool with authentication check.
+
+        Args:
+            user_id: User ID (may be anonymous like "anon_123")
+            session_id: Chat session ID
+            **kwargs: Tool-specific parameters
+
+        Returns:
+            Pydantic response object
+
+        """
+        if self.requires_auth and not user_id:
+            logger.error(
+                f"Attempted tool call for {self.name} but user not authenticated"
+            )
+            return StreamToolOutputAvailable(
+                toolCallId=tool_call_id,
+                toolName=self.name,
+                output=NeedLoginResponse(
+                    message=f"Please sign in to use {self.name}",
+                    session_id=session.session_id,
+                ).model_dump_json(),
+                success=False,
+            )
+
+        try:
+            result = await self._execute(user_id, session, **kwargs)
+            return StreamToolOutputAvailable(
+                toolCallId=tool_call_id,
+                toolName=self.name,
+                output=result.model_dump_json(),
+            )
+        except Exception as e:
+            logger.error(f"Error in {self.name}: {e}", exc_info=True)
+            return StreamToolOutputAvailable(
+                toolCallId=tool_call_id,
+                toolName=self.name,
+                output=ErrorResponse(
+                    message=f"An error occurred while executing {self.name}",
+                    error=str(e),
+                    session_id=session.session_id,
+                ).model_dump_json(),
+                success=False,
+            )
+
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        """Internal execution logic to be implemented by subclasses.
+
+        Args:
+            user_id: User ID (authenticated or anonymous)
+            session_id: Chat session ID
+            **kwargs: Tool-specific parameters
+
+        Returns:
+            Pydantic response object
+
+        """
+        raise NotImplementedError

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

@@ -0,0 +1,131 @@
+"""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.api.features.chat.model import ChatSession
+from backend.api.features.chat.tools.base import BaseTool
+from backend.api.features.chat.tools.models import (
+    BashExecResponse,
+    ErrorResponse,
+    ToolResponseBase,
+)
+from backend.api.features.chat.tools.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,
+        )

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

@@ -0,0 +1,127 @@
+"""CheckOperationStatusTool — query the status of a long-running operation."""
+
+import logging
+from typing import Any
+
+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 (
+    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.api.features.chat 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}"),
+        )

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

@@ -0,0 +1,335 @@
+"""CreateAgentTool - Creates agents from natural language descriptions."""
+
+import logging
+from typing import Any
+
+from backend.api.features.chat.model import ChatSession
+
+from .agent_generator import (
+    AgentGeneratorNotConfiguredError,
+    decompose_goal,
+    enrich_library_agents_from_steps,
+    generate_agent,
+    get_all_relevant_agents_for_generation,
+    get_user_message_for_error,
+    save_agent_to_library,
+)
+from .base import BaseTool
+from .models import (
+    AgentPreviewResponse,
+    AgentSavedResponse,
+    AsyncProcessingResponse,
+    ClarificationNeededResponse,
+    ClarifyingQuestion,
+    ErrorResponse,
+    ToolResponseBase,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class CreateAgentTool(BaseTool):
+    """Tool for creating agents from natural language descriptions."""
+
+    @property
+    def name(self) -> str:
+        return "create_agent"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Create a new agent workflow from a natural language description. "
+            "First generates a preview, then saves to library if save=true."
+        )
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    @property
+    def is_long_running(self) -> bool:
+        return True
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "description": {
+                    "type": "string",
+                    "description": (
+                        "Natural language description of what the agent should do. "
+                        "Be specific about inputs, outputs, and the workflow steps."
+                    ),
+                },
+                "context": {
+                    "type": "string",
+                    "description": (
+                        "Additional context or answers to previous clarifying questions. "
+                        "Include any preferences or constraints mentioned by the user."
+                    ),
+                },
+                "save": {
+                    "type": "boolean",
+                    "description": (
+                        "Whether to save the agent to the user's library. "
+                        "Default is true. Set to false for preview only."
+                    ),
+                    "default": True,
+                },
+            },
+            "required": ["description"],
+        }
+
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        """Execute the create_agent tool.
+
+        Flow:
+        1. Decompose the description into steps (may return clarifying questions)
+        2. Generate agent JSON (external service handles fixing and validation)
+        3. Preview or save based on the save parameter
+        """
+        description = kwargs.get("description", "").strip()
+        context = kwargs.get("context", "")
+        save = kwargs.get("save", True)
+        session_id = session.session_id if session else None
+
+        # Extract async processing params (passed by long-running tool handler)
+        operation_id = kwargs.get("_operation_id")
+        task_id = kwargs.get("_task_id")
+
+        if not description:
+            return ErrorResponse(
+                message="Please provide a description of what the agent should do.",
+                error="Missing description parameter",
+                session_id=session_id,
+            )
+
+        library_agents = None
+        if user_id:
+            try:
+                library_agents = await get_all_relevant_agents_for_generation(
+                    user_id=user_id,
+                    search_query=description,
+                    include_marketplace=True,
+                )
+                logger.debug(
+                    f"Found {len(library_agents)} relevant agents for sub-agent composition"
+                )
+            except Exception as e:
+                logger.warning(f"Failed to fetch library agents: {e}")
+
+        try:
+            decomposition_result = await decompose_goal(
+                description, context, library_agents
+            )
+        except AgentGeneratorNotConfiguredError:
+            return ErrorResponse(
+                message=(
+                    "Agent generation is not available. "
+                    "The Agent Generator service is not configured."
+                ),
+                error="service_not_configured",
+                session_id=session_id,
+            )
+
+        if decomposition_result is None:
+            return ErrorResponse(
+                message="Failed to analyze the goal. The agent generation service may be unavailable. Please try again.",
+                error="decomposition_failed",
+                details={"description": description[:100]},
+                session_id=session_id,
+            )
+
+        if decomposition_result.get("type") == "error":
+            error_msg = decomposition_result.get("error", "Unknown error")
+            error_type = decomposition_result.get("error_type", "unknown")
+            user_message = get_user_message_for_error(
+                error_type,
+                operation="analyze the goal",
+                llm_parse_message="The AI had trouble understanding this request. Please try rephrasing your goal.",
+            )
+            return ErrorResponse(
+                message=user_message,
+                error=f"decomposition_failed:{error_type}",
+                details={
+                    "description": description[:100],
+                    "service_error": error_msg,
+                    "error_type": error_type,
+                },
+                session_id=session_id,
+            )
+
+        if decomposition_result.get("type") == "clarifying_questions":
+            questions = decomposition_result.get("questions", [])
+            return ClarificationNeededResponse(
+                message=(
+                    "I need some more information to create this agent. "
+                    "Please answer the following questions:"
+                ),
+                questions=[
+                    ClarifyingQuestion(
+                        question=q.get("question", ""),
+                        keyword=q.get("keyword", ""),
+                        example=q.get("example"),
+                    )
+                    for q in questions
+                ],
+                session_id=session_id,
+            )
+
+        if decomposition_result.get("type") == "unachievable_goal":
+            suggested = decomposition_result.get("suggested_goal", "")
+            reason = decomposition_result.get("reason", "")
+            return ErrorResponse(
+                message=(
+                    f"This goal cannot be accomplished with the available blocks. "
+                    f"{reason} "
+                    f"Suggestion: {suggested}"
+                ),
+                error="unachievable_goal",
+                details={"suggested_goal": suggested, "reason": reason},
+                session_id=session_id,
+            )
+
+        if decomposition_result.get("type") == "vague_goal":
+            suggested = decomposition_result.get("suggested_goal", "")
+            return ErrorResponse(
+                message=(
+                    f"The goal is too vague to create a specific workflow. "
+                    f"Suggestion: {suggested}"
+                ),
+                error="vague_goal",
+                details={"suggested_goal": suggested},
+                session_id=session_id,
+            )
+
+        if user_id and library_agents is not None:
+            try:
+                library_agents = await enrich_library_agents_from_steps(
+                    user_id=user_id,
+                    decomposition_result=decomposition_result,
+                    existing_agents=library_agents,
+                    include_marketplace=True,
+                )
+                logger.debug(
+                    f"After enrichment: {len(library_agents)} total agents for sub-agent composition"
+                )
+            except Exception as e:
+                logger.warning(f"Failed to enrich library agents from steps: {e}")
+
+        try:
+            agent_json = await generate_agent(
+                decomposition_result,
+                library_agents,
+                operation_id=operation_id,
+                task_id=task_id,
+            )
+        except AgentGeneratorNotConfiguredError:
+            return ErrorResponse(
+                message=(
+                    "Agent generation is not available. "
+                    "The Agent Generator service is not configured."
+                ),
+                error="service_not_configured",
+                session_id=session_id,
+            )
+
+        if agent_json is None:
+            return ErrorResponse(
+                message="Failed to generate the agent. The agent generation service may be unavailable. Please try again.",
+                error="generation_failed",
+                details={"description": description[:100]},
+                session_id=session_id,
+            )
+
+        if isinstance(agent_json, dict) and agent_json.get("type") == "error":
+            error_msg = agent_json.get("error", "Unknown error")
+            error_type = agent_json.get("error_type", "unknown")
+            user_message = get_user_message_for_error(
+                error_type,
+                operation="generate the agent",
+                llm_parse_message="The AI had trouble generating the agent. Please try again or simplify your goal.",
+                validation_message=(
+                    "I wasn't able to create a valid agent for this request. "
+                    "The generated workflow had some structural issues. "
+                    "Please try simplifying your goal or breaking it into smaller steps."
+                ),
+                error_details=error_msg,
+            )
+            return ErrorResponse(
+                message=user_message,
+                error=f"generation_failed:{error_type}",
+                details={
+                    "description": description[:100],
+                    "service_error": error_msg,
+                    "error_type": error_type,
+                },
+                session_id=session_id,
+            )
+
+        # Check if Agent Generator accepted for async processing
+        if agent_json.get("status") == "accepted":
+            logger.info(
+                f"Agent generation delegated to async processing "
+                f"(operation_id={operation_id}, task_id={task_id})"
+            )
+            return AsyncProcessingResponse(
+                message="Agent generation started. You'll be notified when it's complete.",
+                operation_id=operation_id,
+                task_id=task_id,
+                session_id=session_id,
+            )
+
+        agent_name = agent_json.get("name", "Generated Agent")
+        agent_description = agent_json.get("description", "")
+        node_count = len(agent_json.get("nodes", []))
+        link_count = len(agent_json.get("links", []))
+
+        if not save:
+            return AgentPreviewResponse(
+                message=(
+                    f"I've generated an agent called '{agent_name}' with {node_count} blocks. "
+                    f"Review it and call create_agent with save=true to save it to your library."
+                ),
+                agent_json=agent_json,
+                agent_name=agent_name,
+                description=agent_description,
+                node_count=node_count,
+                link_count=link_count,
+                session_id=session_id,
+            )
+
+        if not user_id:
+            return ErrorResponse(
+                message="You must be logged in to save agents.",
+                error="auth_required",
+                session_id=session_id,
+            )
+
+        try:
+            created_graph, library_agent = await save_agent_to_library(
+                agent_json, user_id
+            )
+
+            return AgentSavedResponse(
+                message=f"Agent '{created_graph.name}' has been saved to your library!",
+                agent_id=created_graph.id,
+                agent_name=created_graph.name,
+                library_agent_id=library_agent.id,
+                library_agent_link=f"/library/agents/{library_agent.id}",
+                agent_page_link=f"/build?flowID={created_graph.id}",
+                session_id=session_id,
+            )
+        except Exception as e:
+            return ErrorResponse(
+                message=f"Failed to save the agent: {str(e)}",
+                error="save_failed",
+                details={"exception": str(e)},
+                session_id=session_id,
+            )

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

@@ -0,0 +1,337 @@
+"""CustomizeAgentTool - Customizes marketplace/template agents using natural language."""
+
+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 .agent_generator import (
+    AgentGeneratorNotConfiguredError,
+    customize_template,
+    get_user_message_for_error,
+    graph_to_json,
+    save_agent_to_library,
+)
+from .base import BaseTool
+from .models import (
+    AgentPreviewResponse,
+    AgentSavedResponse,
+    ClarificationNeededResponse,
+    ClarifyingQuestion,
+    ErrorResponse,
+    ToolResponseBase,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class CustomizeAgentTool(BaseTool):
+    """Tool for customizing marketplace/template agents using natural language."""
+
+    @property
+    def name(self) -> str:
+        return "customize_agent"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Customize a marketplace or template agent using natural language. "
+            "Takes an existing agent from the marketplace and modifies it based on "
+            "the user's requirements before adding to their library."
+        )
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    @property
+    def is_long_running(self) -> bool:
+        return True
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "agent_id": {
+                    "type": "string",
+                    "description": (
+                        "The marketplace agent ID in format 'creator/slug' "
+                        "(e.g., 'autogpt/newsletter-writer'). "
+                        "Get this from find_agent results."
+                    ),
+                },
+                "modifications": {
+                    "type": "string",
+                    "description": (
+                        "Natural language description of how to customize the agent. "
+                        "Be specific about what changes you want to make."
+                    ),
+                },
+                "context": {
+                    "type": "string",
+                    "description": (
+                        "Additional context or answers to previous clarifying questions."
+                    ),
+                },
+                "save": {
+                    "type": "boolean",
+                    "description": (
+                        "Whether to save the customized agent to the user's library. "
+                        "Default is true. Set to false for preview only."
+                    ),
+                    "default": True,
+                },
+            },
+            "required": ["agent_id", "modifications"],
+        }
+
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        """Execute the customize_agent tool.
+
+        Flow:
+        1. Parse the agent ID to get creator/slug
+        2. Fetch the template agent from the marketplace
+        3. Call customize_template with the modification request
+        4. Preview or save based on the save parameter
+        """
+        agent_id = kwargs.get("agent_id", "").strip()
+        modifications = kwargs.get("modifications", "").strip()
+        context = kwargs.get("context", "")
+        save = kwargs.get("save", True)
+        session_id = session.session_id if session else None
+
+        if not agent_id:
+            return ErrorResponse(
+                message="Please provide the marketplace agent ID (e.g., 'creator/agent-name').",
+                error="missing_agent_id",
+                session_id=session_id,
+            )
+
+        if not modifications:
+            return ErrorResponse(
+                message="Please describe how you want to customize this agent.",
+                error="missing_modifications",
+                session_id=session_id,
+            )
+
+        # Parse agent_id in format "creator/slug"
+        parts = [p.strip() for p in agent_id.split("/")]
+        if len(parts) != 2 or not parts[0] or not parts[1]:
+            return ErrorResponse(
+                message=(
+                    f"Invalid agent ID format: '{agent_id}'. "
+                    "Expected format is 'creator/agent-name' "
+                    "(e.g., 'autogpt/newsletter-writer')."
+                ),
+                error="invalid_agent_id_format",
+                session_id=session_id,
+            )
+
+        creator_username, agent_slug = parts
+
+        # Fetch the marketplace agent details
+        try:
+            agent_details = await store_db.get_store_agent_details(
+                username=creator_username, agent_name=agent_slug
+            )
+        except AgentNotFoundError:
+            return ErrorResponse(
+                message=(
+                    f"Could not find marketplace agent '{agent_id}'. "
+                    "Please check the agent ID and try again."
+                ),
+                error="agent_not_found",
+                session_id=session_id,
+            )
+        except Exception as e:
+            logger.error(f"Error fetching marketplace agent {agent_id}: {e}")
+            return ErrorResponse(
+                message="Failed to fetch the marketplace agent. Please try again.",
+                error="fetch_error",
+                session_id=session_id,
+            )
+
+        if not agent_details.store_listing_version_id:
+            return ErrorResponse(
+                message=(
+                    f"The agent '{agent_id}' does not have an available version. "
+                    "Please try a different agent."
+                ),
+                error="no_version_available",
+                session_id=session_id,
+            )
+
+        # Get the full agent graph
+        try:
+            graph = await store_db.get_agent(agent_details.store_listing_version_id)
+            template_agent = graph_to_json(graph)
+        except Exception as e:
+            logger.error(f"Error fetching agent graph for {agent_id}: {e}")
+            return ErrorResponse(
+                message="Failed to fetch the agent configuration. Please try again.",
+                error="graph_fetch_error",
+                session_id=session_id,
+            )
+
+        # Call customize_template
+        try:
+            result = await customize_template(
+                template_agent=template_agent,
+                modification_request=modifications,
+                context=context,
+            )
+        except AgentGeneratorNotConfiguredError:
+            return ErrorResponse(
+                message=(
+                    "Agent customization is not available. "
+                    "The Agent Generator service is not configured."
+                ),
+                error="service_not_configured",
+                session_id=session_id,
+            )
+        except Exception as e:
+            logger.error(f"Error calling customize_template for {agent_id}: {e}")
+            return ErrorResponse(
+                message=(
+                    "Failed to customize the agent due to a service error. "
+                    "Please try again."
+                ),
+                error="customization_service_error",
+                session_id=session_id,
+            )
+
+        if result is None:
+            return ErrorResponse(
+                message=(
+                    "Failed to customize the agent. "
+                    "The agent generation service may be unavailable or timed out. "
+                    "Please try again."
+                ),
+                error="customization_failed",
+                session_id=session_id,
+            )
+
+        # Handle error response
+        if isinstance(result, dict) and result.get("type") == "error":
+            error_msg = result.get("error", "Unknown error")
+            error_type = result.get("error_type", "unknown")
+            user_message = get_user_message_for_error(
+                error_type,
+                operation="customize the agent",
+                llm_parse_message=(
+                    "The AI had trouble customizing the agent. "
+                    "Please try again or simplify your request."
+                ),
+                validation_message=(
+                    "The customized agent failed validation. "
+                    "Please try rephrasing your request."
+                ),
+                error_details=error_msg,
+            )
+            return ErrorResponse(
+                message=user_message,
+                error=f"customization_failed:{error_type}",
+                session_id=session_id,
+            )
+
+        # Handle clarifying questions
+        if isinstance(result, dict) and result.get("type") == "clarifying_questions":
+            questions = result.get("questions") or []
+            if not isinstance(questions, list):
+                logger.error(
+                    f"Unexpected clarifying questions format: {type(questions)}"
+                )
+                questions = []
+            return ClarificationNeededResponse(
+                message=(
+                    "I need some more information to customize this agent. "
+                    "Please answer the following questions:"
+                ),
+                questions=[
+                    ClarifyingQuestion(
+                        question=q.get("question", ""),
+                        keyword=q.get("keyword", ""),
+                        example=q.get("example"),
+                    )
+                    for q in questions
+                    if isinstance(q, dict)
+                ],
+                session_id=session_id,
+            )
+
+        # Result should be the customized agent JSON
+        if not isinstance(result, dict):
+            logger.error(f"Unexpected customize_template response type: {type(result)}")
+            return ErrorResponse(
+                message="Failed to customize the agent due to an unexpected response.",
+                error="unexpected_response_type",
+                session_id=session_id,
+            )
+
+        customized_agent = result
+
+        agent_name = customized_agent.get(
+            "name", f"Customized {agent_details.agent_name}"
+        )
+        agent_description = customized_agent.get("description", "")
+        nodes = customized_agent.get("nodes")
+        links = customized_agent.get("links")
+        node_count = len(nodes) if isinstance(nodes, list) else 0
+        link_count = len(links) if isinstance(links, list) else 0
+
+        if not save:
+            return AgentPreviewResponse(
+                message=(
+                    f"I've customized the agent '{agent_details.agent_name}'. "
+                    f"The customized agent has {node_count} blocks. "
+                    f"Review it and call customize_agent with save=true to save it."
+                ),
+                agent_json=customized_agent,
+                agent_name=agent_name,
+                description=agent_description,
+                node_count=node_count,
+                link_count=link_count,
+                session_id=session_id,
+            )
+
+        if not user_id:
+            return ErrorResponse(
+                message="You must be logged in to save agents.",
+                error="auth_required",
+                session_id=session_id,
+            )
+
+        # Save to user's library
+        try:
+            created_graph, library_agent = await save_agent_to_library(
+                customized_agent, user_id, is_update=False
+            )
+
+            return AgentSavedResponse(
+                message=(
+                    f"Customized agent '{created_graph.name}' "
+                    f"(based on '{agent_details.agent_name}') "
+                    f"has been saved to your library!"
+                ),
+                agent_id=created_graph.id,
+                agent_name=created_graph.name,
+                library_agent_id=library_agent.id,
+                library_agent_link=f"/library/agents/{library_agent.id}",
+                agent_page_link=f"/build?flowID={created_graph.id}",
+                session_id=session_id,
+            )
+        except Exception as e:
+            logger.error(f"Error saving customized agent: {e}")
+            return ErrorResponse(
+                message="Failed to save the customized agent. Please try again.",
+                error="save_failed",
+                session_id=session_id,
+            )

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

@@ -0,0 +1,284 @@
+"""EditAgentTool - Edits existing agents using natural language."""
+
+import logging
+from typing import Any
+
+from backend.api.features.chat.model import ChatSession
+
+from .agent_generator import (
+    AgentGeneratorNotConfiguredError,
+    generate_agent_patch,
+    get_agent_as_json,
+    get_all_relevant_agents_for_generation,
+    get_user_message_for_error,
+    save_agent_to_library,
+)
+from .base import BaseTool
+from .models import (
+    AgentPreviewResponse,
+    AgentSavedResponse,
+    AsyncProcessingResponse,
+    ClarificationNeededResponse,
+    ClarifyingQuestion,
+    ErrorResponse,
+    ToolResponseBase,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class EditAgentTool(BaseTool):
+    """Tool for editing existing agents using natural language."""
+
+    @property
+    def name(self) -> str:
+        return "edit_agent"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Edit an existing agent from the user's library using natural language. "
+            "Generates updates to the agent while preserving unchanged parts."
+        )
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    @property
+    def is_long_running(self) -> bool:
+        return True
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "agent_id": {
+                    "type": "string",
+                    "description": (
+                        "The ID of the agent to edit. "
+                        "Can be a graph ID or library agent ID."
+                    ),
+                },
+                "changes": {
+                    "type": "string",
+                    "description": (
+                        "Natural language description of what changes to make. "
+                        "Be specific about what to add, remove, or modify."
+                    ),
+                },
+                "context": {
+                    "type": "string",
+                    "description": (
+                        "Additional context or answers to previous clarifying questions."
+                    ),
+                },
+                "save": {
+                    "type": "boolean",
+                    "description": (
+                        "Whether to save the changes. "
+                        "Default is true. Set to false for preview only."
+                    ),
+                    "default": True,
+                },
+            },
+            "required": ["agent_id", "changes"],
+        }
+
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        """Execute the edit_agent tool.
+
+        Flow:
+        1. Fetch the current agent
+        2. Generate updated agent (external service handles fixing and validation)
+        3. Preview or save based on the save parameter
+        """
+        agent_id = kwargs.get("agent_id", "").strip()
+        changes = kwargs.get("changes", "").strip()
+        context = kwargs.get("context", "")
+        save = kwargs.get("save", True)
+        session_id = session.session_id if session else None
+
+        # Extract async processing params (passed by long-running tool handler)
+        operation_id = kwargs.get("_operation_id")
+        task_id = kwargs.get("_task_id")
+
+        if not agent_id:
+            return ErrorResponse(
+                message="Please provide the agent ID to edit.",
+                error="Missing agent_id parameter",
+                session_id=session_id,
+            )
+
+        if not changes:
+            return ErrorResponse(
+                message="Please describe what changes you want to make.",
+                error="Missing changes parameter",
+                session_id=session_id,
+            )
+
+        current_agent = await get_agent_as_json(agent_id, user_id)
+
+        if current_agent is None:
+            return ErrorResponse(
+                message=f"Could not find agent with ID '{agent_id}' in your library.",
+                error="agent_not_found",
+                session_id=session_id,
+            )
+
+        library_agents = None
+        if user_id:
+            try:
+                graph_id = current_agent.get("id")
+                library_agents = await get_all_relevant_agents_for_generation(
+                    user_id=user_id,
+                    search_query=changes,
+                    exclude_graph_id=graph_id,
+                    include_marketplace=True,
+                )
+                logger.debug(
+                    f"Found {len(library_agents)} relevant agents for sub-agent composition"
+                )
+            except Exception as e:
+                logger.warning(f"Failed to fetch library agents: {e}")
+
+        update_request = changes
+        if context:
+            update_request = f"{changes}\n\nAdditional context:\n{context}"
+
+        try:
+            result = await generate_agent_patch(
+                update_request,
+                current_agent,
+                library_agents,
+                operation_id=operation_id,
+                task_id=task_id,
+            )
+        except AgentGeneratorNotConfiguredError:
+            return ErrorResponse(
+                message=(
+                    "Agent editing is not available. "
+                    "The Agent Generator service is not configured."
+                ),
+                error="service_not_configured",
+                session_id=session_id,
+            )
+
+        if result is None:
+            return ErrorResponse(
+                message="Failed to generate changes. The agent generation service may be unavailable or timed out. Please try again.",
+                error="update_generation_failed",
+                details={"agent_id": agent_id, "changes": changes[:100]},
+                session_id=session_id,
+            )
+
+        # Check if Agent Generator accepted for async processing
+        if result.get("status") == "accepted":
+            logger.info(
+                f"Agent edit delegated to async processing "
+                f"(operation_id={operation_id}, task_id={task_id})"
+            )
+            return AsyncProcessingResponse(
+                message="Agent edit started. You'll be notified when it's complete.",
+                operation_id=operation_id,
+                task_id=task_id,
+                session_id=session_id,
+            )
+
+        # Check if the result is an error from the external service
+        if isinstance(result, dict) and result.get("type") == "error":
+            error_msg = result.get("error", "Unknown error")
+            error_type = result.get("error_type", "unknown")
+            user_message = get_user_message_for_error(
+                error_type,
+                operation="generate the changes",
+                llm_parse_message="The AI had trouble generating the changes. Please try again or simplify your request.",
+                validation_message="The generated changes failed validation. Please try rephrasing your request.",
+                error_details=error_msg,
+            )
+            return ErrorResponse(
+                message=user_message,
+                error=f"update_generation_failed:{error_type}",
+                details={
+                    "agent_id": agent_id,
+                    "changes": changes[:100],
+                    "service_error": error_msg,
+                    "error_type": error_type,
+                },
+                session_id=session_id,
+            )
+
+        if result.get("type") == "clarifying_questions":
+            questions = result.get("questions", [])
+            return ClarificationNeededResponse(
+                message=(
+                    "I need some more information about the changes. "
+                    "Please answer the following questions:"
+                ),
+                questions=[
+                    ClarifyingQuestion(
+                        question=q.get("question", ""),
+                        keyword=q.get("keyword", ""),
+                        example=q.get("example"),
+                    )
+                    for q in questions
+                ],
+                session_id=session_id,
+            )
+
+        updated_agent = result
+
+        agent_name = updated_agent.get("name", "Updated Agent")
+        agent_description = updated_agent.get("description", "")
+        node_count = len(updated_agent.get("nodes", []))
+        link_count = len(updated_agent.get("links", []))
+
+        if not save:
+            return AgentPreviewResponse(
+                message=(
+                    f"I've updated the agent. "
+                    f"The agent now has {node_count} blocks. "
+                    f"Review it and call edit_agent with save=true to save the changes."
+                ),
+                agent_json=updated_agent,
+                agent_name=agent_name,
+                description=agent_description,
+                node_count=node_count,
+                link_count=link_count,
+                session_id=session_id,
+            )
+
+        if not user_id:
+            return ErrorResponse(
+                message="You must be logged in to save agents.",
+                error="auth_required",
+                session_id=session_id,
+            )
+
+        try:
+            created_graph, library_agent = await save_agent_to_library(
+                updated_agent, user_id, is_update=True
+            )
+
+            return AgentSavedResponse(
+                message=f"Updated agent '{created_graph.name}' has been saved to your library!",
+                agent_id=created_graph.id,
+                agent_name=created_graph.name,
+                library_agent_id=library_agent.id,
+                library_agent_link=f"/library/agents/{library_agent.id}",
+                agent_page_link=f"/build?flowID={created_graph.id}",
+                session_id=session_id,
+            )
+        except Exception as e:
+            return ErrorResponse(
+                message=f"Failed to save the updated agent: {str(e)}",
+                error="save_failed",
+                details={"exception": str(e)},
+                session_id=session_id,
+            )

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

@@ -5,14 +5,9 @@ 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 (
+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 (
     ErrorResponse,
     FeatureRequestCreatedResponse,
     FeatureRequestInfo,
@@ -20,6 +15,10 @@ from .models import (
     NoResultsResponse,
     ToolResponseBase,
 )
+from backend.blocks.linear._api import LinearClient
+from backend.data.model import APIKeyCredentials
+from backend.data.user import get_user_email_by_id
+from backend.util.settings import Settings
 
 logger = logging.getLogger(__name__)
 
@@ -33,6 +32,7 @@ query SearchFeatureRequests($term: String!, $filter: IssueFilter, $first: Int) {
       id
       identifier
       title
+      description
     }
   }
 }
@@ -104,8 +104,8 @@ def _get_linear_config() -> tuple[LinearClient, str, str]:
     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_api_key:
+        raise RuntimeError("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:
@@ -114,7 +114,7 @@ def _get_linear_config() -> tuple[LinearClient, str, str]:
     credentials = APIKeyCredentials(
         id="system-linear",
         provider="linear",
-        api_key=SecretStr(secrets.copilot_linear_api_key),
+        api_key=SecretStr(secrets.linear_api_key),
         title="System Linear API Key",
     )
     client = LinearClient(credentials=credentials)
@@ -204,6 +204,7 @@ class SearchFeatureRequestsTool(BaseTool):
                     id=node["id"],
                     identifier=node["identifier"],
                     title=node["title"],
+                    description=node.get("description"),
                 )
                 for node in nodes
             ]
@@ -237,11 +238,7 @@ class CreateFeatureRequestTool(BaseTool):
             "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."
+            "the user's need to it instead of creating a duplicate."
         )
 
     @property
@@ -251,20 +248,11 @@ class CreateFeatureRequestTool(BaseTool):
             "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": "Title for the feature request.",
                 },
                 "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."
-                    ),
+                    "description": "Detailed description of what the user wants and why.",
                 },
                 "existing_issue_id": {
                     "type": "string",
@@ -344,9 +332,7 @@ class CreateFeatureRequestTool(BaseTool):
         # 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
-            )
+            customer_display_name = await get_user_email_by_id(user_id) or user_id
         except Exception:
             customer_display_name = user_id
 

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

@@ -1,18 +1,22 @@
 """Tests for SearchFeatureRequestsTool and CreateFeatureRequestTool."""
 
-from unittest.mock import AsyncMock, MagicMock, patch
+from unittest.mock import AsyncMock, patch
 
 import pytest
 
-from ._test_data import make_session
-from .feature_requests import CreateFeatureRequestTool, SearchFeatureRequestsTool
-from .models import (
+from backend.api.features.chat.tools.feature_requests import (
+    CreateFeatureRequestTool,
+    SearchFeatureRequestsTool,
+)
+from backend.api.features.chat.tools.models import (
     ErrorResponse,
     FeatureRequestCreatedResponse,
     FeatureRequestSearchResponse,
     NoResultsResponse,
 )
 
+from ._test_data import make_session
+
 _TEST_USER_ID = "test-user-feature-requests"
 _TEST_USER_EMAIL = "testuser@example.com"
 
@@ -35,7 +39,7 @@ def _mock_linear_config(*, query_return=None, mutate_return=None):
         client.mutate.return_value = mutate_return
     return (
         patch(
-            "backend.copilot.tools.feature_requests._get_linear_config",
+            "backend.api.features.chat.tools.feature_requests._get_linear_config",
             return_value=(client, _FAKE_PROJECT_ID, _FAKE_TEAM_ID),
         ),
         client,
@@ -117,11 +121,13 @@ class TestSearchFeatureRequestsTool:
                 "id": "id-1",
                 "identifier": "FR-1",
                 "title": "Dark mode",
+                "description": "Add dark mode support",
             },
             {
                 "id": "id-2",
                 "identifier": "FR-2",
                 "title": "Dark theme",
+                "description": None,
             },
         ]
         patcher, _ = _mock_linear_config(query_return=_search_response(nodes))
@@ -202,7 +208,7 @@ class TestSearchFeatureRequestsTool:
     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",
+            "backend.api.features.chat.tools.feature_requests._get_linear_config",
             side_effect=RuntimeError("No API key"),
         ):
             tool = SearchFeatureRequestsTool()
@@ -225,11 +231,10 @@ class TestCreateFeatureRequestTool:
 
     @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,
+            "backend.api.features.chat.tools.feature_requests.get_user_email_by_id",
+            new_callable=AsyncMock,
+            return_value=_TEST_USER_EMAIL,
         ):
             yield
 
@@ -342,7 +347,7 @@ class TestCreateFeatureRequestTool:
     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",
+            "backend.api.features.chat.tools.feature_requests._get_linear_config",
             side_effect=RuntimeError("No API key"),
         ):
             tool = CreateFeatureRequestTool()

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

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

@@ -3,18 +3,17 @@ 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,
     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__)
 
@@ -32,7 +31,6 @@ COPILOT_EXCLUDED_BLOCK_TYPES = {
     BlockType.NOTE,  # Visual annotation only - no runtime behavior
     BlockType.HUMAN_IN_THE_LOOP,  # Pauses for human approval - CoPilot IS human-in-the-loop
     BlockType.AGENT,  # AgentExecutorBlock requires execution_context - use run_agent tool
-    BlockType.MCP_TOOL,  # Has dedicated run_mcp_tool tool with discovery + auth flow
 }
 
 # Specific block IDs excluded from CoPilot (STANDARD type but still require graph context)
@@ -72,15 +70,6 @@ class FindBlockTool(BaseTool):
                         "Use keywords like 'email', 'http', 'text', 'ai', etc."
                     ),
                 },
-                "include_schemas": {
-                    "type": "boolean",
-                    "description": (
-                        "If true, include full input_schema and output_schema "
-                        "for each block. Use when generating agent JSON that "
-                        "needs block schemas. Default is false."
-                    ),
-                    "default": False,
-                },
             },
             "required": ["query"],
         }
@@ -108,7 +97,6 @@ class FindBlockTool(BaseTool):
             ErrorResponse: Error message
         """
         query = kwargs.get("query", "").strip()
-        include_schemas = kwargs.get("include_schemas", False)
         session_id = session.session_id
 
         if not query:
@@ -119,7 +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,
@@ -153,21 +141,15 @@ class FindBlockTool(BaseTool):
                 ):
                     continue
 
-                summary = BlockInfoSummary(
-                    id=block_id,
-                    name=block.name,
-                    description=block.optimized_description or block.description or "",
-                    categories=[c.value for c in block.categories],
+                blocks.append(
+                    BlockInfoSummary(
+                        id=block_id,
+                        name=block.name,
+                        description=block.description or "",
+                        categories=[c.value for c in block.categories],
+                    )
                 )
 
-                if include_schemas:
-                    info = block.get_info()
-                    summary.input_schema = info.inputSchema
-                    summary.output_schema = info.outputSchema
-                    summary.static_output = info.staticOutput
-
-                blocks.append(summary)
-
                 if len(blocks) >= _TARGET_RESULTS:
                     break
 

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

@@ -4,15 +4,15 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
-from backend.blocks._base import BlockType
-
-from ._test_data import make_session
-from .find_block import (
+from backend.api.features.chat.tools.find_block import (
     COPILOT_EXCLUDED_BLOCK_IDS,
     COPILOT_EXCLUDED_BLOCK_TYPES,
     FindBlockTool,
 )
-from .models import BlockListResponse
+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"
 
@@ -25,7 +25,6 @@ def make_mock_block(
     input_schema: dict | None = None,
     output_schema: dict | None = None,
     credentials_fields: dict | None = None,
-    static_output: bool = False,
 ):
     """Create a mock block for testing."""
     mock = MagicMock()
@@ -34,7 +33,6 @@ def make_mock_block(
     mock.description = f"{name} description"
     mock.block_type = block_type
     mock.disabled = disabled
-    mock.static_output = static_output
     mock.input_schema = MagicMock()
     mock.input_schema.jsonschema.return_value = input_schema or {
         "properties": {},
@@ -44,15 +42,6 @@ def make_mock_block(
     mock.output_schema = MagicMock()
     mock.output_schema.jsonschema.return_value = output_schema or {}
     mock.categories = []
-    mock.optimized_description = None
-
-    # Mock get_info() for include_schemas support
-    mock_info = MagicMock()
-    mock_info.inputSchema = input_schema or {"properties": {}, "required": []}
-    mock_info.outputSchema = output_schema or {}
-    mock_info.staticOutput = static_output
-    mock.get_info.return_value = mock_info
-
     return mock
 
 
@@ -95,17 +84,13 @@ class TestFindBlockFiltering:
                 "standard-block-id": standard_block,
             }.get(block_id)
 
-        mock_search_db = MagicMock()
-        mock_search_db.unified_hybrid_search = AsyncMock(
-            return_value=(search_results, 2)
-        )
-
         with patch(
-            "backend.copilot.tools.find_block.search",
-            return_value=mock_search_db,
+            "backend.api.features.chat.tools.find_block.unified_hybrid_search",
+            new_callable=AsyncMock,
+            return_value=(search_results, 2),
         ):
             with patch(
-                "backend.copilot.tools.find_block.get_block",
+                "backend.api.features.chat.tools.find_block.get_block",
                 side_effect=mock_get_block,
             ):
                 tool = FindBlockTool()
@@ -143,17 +128,13 @@ class TestFindBlockFiltering:
                 "normal-block-id": normal_block,
             }.get(block_id)
 
-        mock_search_db = MagicMock()
-        mock_search_db.unified_hybrid_search = AsyncMock(
-            return_value=(search_results, 2)
-        )
-
         with patch(
-            "backend.copilot.tools.find_block.search",
-            return_value=mock_search_db,
+            "backend.api.features.chat.tools.find_block.unified_hybrid_search",
+            new_callable=AsyncMock,
+            return_value=(search_results, 2),
         ):
             with patch(
-                "backend.copilot.tools.find_block.get_block",
+                "backend.api.features.chat.tools.find_block.get_block",
                 side_effect=mock_get_block,
             ):
                 tool = FindBlockTool()
@@ -372,20 +353,13 @@ class TestFindBlockFiltering:
             for d in block_defs
         }
 
-        mock_search_db = MagicMock()
-        mock_search_db.unified_hybrid_search = AsyncMock(
-            return_value=(search_results, len(search_results))
-        )
-
-        with (
-            patch(
-                "backend.copilot.tools.find_block.search",
-                return_value=mock_search_db,
-            ),
-            patch(
-                "backend.copilot.tools.find_block.get_block",
-                side_effect=lambda bid: mock_blocks.get(bid),
-            ),
+        with patch(
+            "backend.api.features.chat.tools.find_block.unified_hybrid_search",
+            new_callable=AsyncMock,
+            return_value=(search_results, len(search_results)),
+        ), patch(
+            "backend.api.features.chat.tools.find_block.get_block",
+            side_effect=lambda bid: mock_blocks.get(bid),
         ):
             tool = FindBlockTool()
             response = await tool._execute(
@@ -410,92 +384,3 @@ class TestFindBlockFiltering:
             f"Average chars per block ({avg_chars}) exceeds 500. "
             f"Total response: {total_chars} chars for {response.count} blocks."
         )
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_include_schemas_false_omits_schemas(self):
-        """Without include_schemas, schemas should be empty dicts."""
-        session = make_session(user_id=_TEST_USER_ID)
-        input_schema = {"properties": {"url": {"type": "string"}}, "required": ["url"]}
-        output_schema = {"properties": {"result": {"type": "string"}}}
-
-        search_results = [{"content_id": "block-1", "score": 0.9}]
-        block = make_mock_block(
-            "block-1",
-            "Test Block",
-            BlockType.STANDARD,
-            input_schema=input_schema,
-            output_schema=output_schema,
-        )
-
-        mock_search_db = MagicMock()
-        mock_search_db.unified_hybrid_search = AsyncMock(
-            return_value=(search_results, 1)
-        )
-
-        with (
-            patch(
-                "backend.copilot.tools.find_block.search",
-                return_value=mock_search_db,
-            ),
-            patch(
-                "backend.copilot.tools.find_block.get_block",
-                return_value=block,
-            ),
-        ):
-            tool = FindBlockTool()
-            response = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                query="test",
-                include_schemas=False,
-            )
-
-        assert isinstance(response, BlockListResponse)
-        assert response.blocks[0].input_schema == {}
-        assert response.blocks[0].output_schema == {}
-        assert response.blocks[0].static_output is False
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_include_schemas_true_populates_schemas(self):
-        """With include_schemas=true, schemas should be populated from block info."""
-        session = make_session(user_id=_TEST_USER_ID)
-        input_schema = {"properties": {"url": {"type": "string"}}, "required": ["url"]}
-        output_schema = {"properties": {"result": {"type": "string"}}}
-
-        search_results = [{"content_id": "block-1", "score": 0.9}]
-        block = make_mock_block(
-            "block-1",
-            "Test Block",
-            BlockType.STANDARD,
-            input_schema=input_schema,
-            output_schema=output_schema,
-            static_output=True,
-        )
-
-        mock_search_db = MagicMock()
-        mock_search_db.unified_hybrid_search = AsyncMock(
-            return_value=(search_results, 1)
-        )
-
-        with (
-            patch(
-                "backend.copilot.tools.find_block.search",
-                return_value=mock_search_db,
-            ),
-            patch(
-                "backend.copilot.tools.find_block.get_block",
-                return_value=block,
-            ),
-        ):
-            tool = FindBlockTool()
-            response = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                query="test",
-                include_schemas=True,
-            )
-
-        assert isinstance(response, BlockListResponse)
-        assert response.blocks[0].input_schema == input_schema
-        assert response.blocks[0].output_schema == output_schema
-        assert response.blocks[0].static_output is True

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
@@ -19,13 +19,9 @@ class FindLibraryAgentTool(BaseTool):
     @property
     def description(self) -> str:
         return (
-            "Search for or list agents in the user's library. Use this to find "
-            "agents the user has already added to their library, including agents "
-            "they created or added from the marketplace. "
-            "When creating agents with sub-agent composition, use this to get "
-            "the agent's graph_id, graph_version, input_schema, and output_schema "
-            "needed for AgentExecutorBlock nodes. "
-            "Omit the query to list all agents."
+            "Search for agents in the user's library. Use this to find agents "
+            "the user has already added to their library, including agents they "
+            "created or added from the marketplace."
         )
 
     @property
@@ -35,13 +31,10 @@ class FindLibraryAgentTool(BaseTool):
             "properties": {
                 "query": {
                     "type": "string",
-                    "description": (
-                        "Search query to find agents by name or description. "
-                        "Omit to list all agents in the library."
-                    ),
+                    "description": "Search query to find agents by name or description.",
                 },
             },
-            "required": [],
+            "required": ["query"],
         }
 
     @property
@@ -52,7 +45,7 @@ class FindLibraryAgentTool(BaseTool):
         self, user_id: str | None, session: ChatSession, **kwargs
     ) -> ToolResponseBase:
         return await search_agents(
-            query=(kwargs.get("query") or "").strip(),
+            query=kwargs.get("query", "").strip(),
             source="library",
             session_id=session.session_id,
             user_id=user_id,

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__)
 

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

@@ -0,0 +1,29 @@
+"""Shared helpers for chat tools."""
+
+from typing import Any
+
+
+def get_inputs_from_schema(
+    input_schema: dict[str, Any],
+    exclude_fields: set[str] | None = None,
+) -> list[dict[str, Any]]:
+    """Extract input field info from JSON schema."""
+    if not isinstance(input_schema, dict):
+        return []
+
+    exclude = exclude_fields or set()
+    properties = input_schema.get("properties", {})
+    required = set(input_schema.get("required", []))
+
+    return [
+        {
+            "name": name,
+            "title": schema.get("title", name),
+            "type": schema.get("type", "string"),
+            "description": schema.get("description", ""),
+            "required": name in required,
+            "default": schema.get("default"),
+        }
+        for name, schema in properties.items()
+        if name not in exclude
+    ]

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

@@ -2,7 +2,7 @@
 
 from datetime import datetime
 from enum import Enum
-from typing import Any, Literal
+from typing import Any
 
 from pydantic import BaseModel, Field
 
@@ -12,71 +12,42 @@ from backend.data.model import CredentialsMetaInput
 class ResponseType(str, Enum):
     """Types of tool responses."""
 
-    # General
-    ERROR = "error"
-    NO_RESULTS = "no_results"
-    NEED_LOGIN = "need_login"
-
-    # Agent discovery & execution
     AGENTS_FOUND = "agents_found"
     AGENT_DETAILS = "agent_details"
     SETUP_REQUIREMENTS = "setup_requirements"
-    INPUT_VALIDATION_ERROR = "input_validation_error"
     EXECUTION_STARTED = "execution_started"
+    NEED_LOGIN = "need_login"
+    ERROR = "error"
+    NO_RESULTS = "no_results"
     AGENT_OUTPUT = "agent_output"
     UNDERSTANDING_UPDATED = "understanding_updated"
-    SUGGESTED_GOAL = "suggested_goal"
-
-    # Agent builder (create / edit / validate / fix)
-    AGENT_BUILDER_GUIDE = "agent_builder_guide"
-    AGENT_BUILDER_PREVIEW = "agent_builder_preview"
-    AGENT_BUILDER_SAVED = "agent_builder_saved"
-    AGENT_BUILDER_CLARIFICATION_NEEDED = "agent_builder_clarification_needed"
-    AGENT_BUILDER_VALIDATION_RESULT = "agent_builder_validation_result"
-    AGENT_BUILDER_FIX_RESULT = "agent_builder_fix_result"
-
-    # Block
+    AGENT_PREVIEW = "agent_preview"
+    AGENT_SAVED = "agent_saved"
+    CLARIFICATION_NEEDED = "clarification_needed"
     BLOCK_LIST = "block_list"
     BLOCK_DETAILS = "block_details"
     BLOCK_OUTPUT = "block_output"
-    REVIEW_REQUIRED = "review_required"
-
-    # MCP
-    MCP_GUIDE = "mcp_guide"
-    MCP_TOOLS_DISCOVERED = "mcp_tools_discovered"
-    MCP_TOOL_OUTPUT = "mcp_tool_output"
-
-    # Docs
     DOC_SEARCH_RESULTS = "doc_search_results"
     DOC_PAGE = "doc_page"
-
-    # Workspace files
+    # Workspace response types
     WORKSPACE_FILE_LIST = "workspace_file_list"
     WORKSPACE_FILE_CONTENT = "workspace_file_content"
     WORKSPACE_FILE_METADATA = "workspace_file_metadata"
     WORKSPACE_FILE_WRITTEN = "workspace_file_written"
     WORKSPACE_FILE_DELETED = "workspace_file_deleted"
-
-    # Folder management
-    FOLDER_CREATED = "folder_created"
-    FOLDER_LIST = "folder_list"
-    FOLDER_UPDATED = "folder_updated"
-    FOLDER_MOVED = "folder_moved"
-    FOLDER_DELETED = "folder_deleted"
-    AGENTS_MOVED_TO_FOLDER = "agents_moved_to_folder"
-
-    # Browser automation
-    BROWSER_NAVIGATE = "browser_navigate"
-    BROWSER_ACT = "browser_act"
-    BROWSER_SCREENSHOT = "browser_screenshot"
-
+    # Long-running operation types
+    OPERATION_STARTED = "operation_started"
+    OPERATION_PENDING = "operation_pending"
+    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"
-
-    # Web
-    WEB_FETCH = "web_fetch"
-
-    # Feature requests
+    # Operation status check
+    OPERATION_STATUS = "operation_status"
+    # Feature request types
     FEATURE_REQUEST_SEARCH = "feature_request_search"
     FEATURE_REQUEST_CREATED = "feature_request_created"
 
@@ -109,15 +80,6 @@ class AgentInfo(BaseModel):
     has_external_trigger: bool | None = None
     new_output: bool | None = None
     graph_id: str | None = None
-    graph_version: int | None = None
-    input_schema: dict[str, Any] | None = Field(
-        default=None,
-        description="JSON Schema for the agent's inputs (for AgentExecutorBlock)",
-    )
-    output_schema: dict[str, Any] | None = Field(
-        default=None,
-        description="JSON Schema for the agent's outputs (for AgentExecutorBlock)",
-    )
     inputs: dict[str, Any] | None = Field(
         default=None,
         description="Input schema for the agent, including field names, types, and defaults",
@@ -308,7 +270,7 @@ class ClarifyingQuestion(BaseModel):
 class AgentPreviewResponse(ToolResponseBase):
     """Response for previewing a generated agent before saving."""
 
-    type: ResponseType = ResponseType.AGENT_BUILDER_PREVIEW
+    type: ResponseType = ResponseType.AGENT_PREVIEW
     agent_json: dict[str, Any]
     agent_name: str
     description: str
@@ -319,7 +281,7 @@ class AgentPreviewResponse(ToolResponseBase):
 class AgentSavedResponse(ToolResponseBase):
     """Response when an agent is saved to the library."""
 
-    type: ResponseType = ResponseType.AGENT_BUILDER_SAVED
+    type: ResponseType = ResponseType.AGENT_SAVED
     agent_id: str
     agent_name: str
     library_agent_id: str
@@ -330,26 +292,10 @@ class AgentSavedResponse(ToolResponseBase):
 class ClarificationNeededResponse(ToolResponseBase):
     """Response when the LLM needs more information from the user."""
 
-    type: ResponseType = ResponseType.AGENT_BUILDER_CLARIFICATION_NEEDED
+    type: ResponseType = ResponseType.CLARIFICATION_NEEDED
     questions: list[ClarifyingQuestion] = Field(default_factory=list)
 
 
-class SuggestedGoalResponse(ToolResponseBase):
-    """Response when the goal needs refinement with a suggested alternative."""
-
-    type: ResponseType = ResponseType.SUGGESTED_GOAL
-    suggested_goal: str = Field(description="The suggested alternative goal")
-    reason: str = Field(
-        default="", description="Why the original goal needs refinement"
-    )
-    original_goal: str = Field(
-        default="", description="The user's original goal for context"
-    )
-    goal_type: Literal["vague", "unachievable"] = Field(
-        default="vague", description="Type: 'vague' or 'unachievable'"
-    )
-
-
 # Documentation search models
 class DocSearchResult(BaseModel):
     """A single documentation search result."""
@@ -407,10 +353,6 @@ class BlockInfoSummary(BaseModel):
         default_factory=dict,
         description="Full JSON schema for block outputs",
     )
-    static_output: bool = Field(
-        default=False,
-        description="Whether the block produces output without needing input",
-    )
     required_inputs: list[BlockInputFieldInfo] = Field(
         default_factory=list,
         description="List of input fields for this block",
@@ -459,19 +401,61 @@ class BlockOutputResponse(ToolResponseBase):
     success: bool = True
 
 
-class ReviewRequiredResponse(ToolResponseBase):
-    """Response when a block requires human review before execution."""
+# Long-running operation models
+class OperationStartedResponse(ToolResponseBase):
+    """Response when a long-running operation has been started in the background.
 
-    type: ResponseType = ResponseType.REVIEW_REQUIRED
-    block_id: str
-    block_name: str
-    review_id: str = Field(description="The review ID for tracking approval status")
-    graph_exec_id: str = Field(
-        description="The graph execution ID for fetching review status"
-    )
-    input_data: dict[str, Any] = Field(
-        description="The input data that requires review"
-    )
+    This is returned immediately to the client while the operation continues
+    to execute. The user can close the tab and check back later.
+
+    The task_id can be used to reconnect to the SSE stream via
+    GET /chat/tasks/{task_id}/stream?last_idx=0
+    """
+
+    type: ResponseType = ResponseType.OPERATION_STARTED
+    operation_id: str
+    tool_name: str
+    task_id: str | None = None  # For SSE reconnection
+
+
+class OperationPendingResponse(ToolResponseBase):
+    """Response stored in chat history while a long-running operation is executing.
+
+    This is persisted to the database so users see a pending state when they
+    refresh before the operation completes.
+    """
+
+    type: ResponseType = ResponseType.OPERATION_PENDING
+    operation_id: str
+    tool_name: str
+
+
+class OperationInProgressResponse(ToolResponseBase):
+    """Response when an operation is already in progress.
+
+    Returned for idempotency when the same tool_call_id is requested again
+    while the background task is still running.
+    """
+
+    type: ResponseType = ResponseType.OPERATION_IN_PROGRESS
+    tool_call_id: str
+
+
+class AsyncProcessingResponse(ToolResponseBase):
+    """Response when an operation has been delegated to async processing.
+
+    This is returned by tools when the external service accepts the request
+    for async processing (HTTP 202 Accepted). The Redis Streams completion
+    consumer will handle the result when the external service completes.
+
+    The status field is specifically "accepted" to allow the long-running tool
+    handler to detect this response and skip LLM continuation.
+    """
+
+    type: ResponseType = ResponseType.OPERATION_STARTED
+    status: str = "accepted"  # Must be "accepted" for detection
+    operation_id: str | None = None
+    task_id: str | None = None
 
 
 class WebFetchResponse(ToolResponseBase):
@@ -502,6 +486,7 @@ class FeatureRequestInfo(BaseModel):
     id: str
     identifier: str
     title: str
+    description: str | None = None
 
 
 class FeatureRequestSearchResponse(ToolResponseBase):
@@ -523,161 +508,3 @@ class FeatureRequestCreatedResponse(ToolResponseBase):
     issue_url: str
     is_new_issue: bool  # False if added to existing
     customer_name: str
-
-
-# MCP tool models
-class MCPToolInfo(BaseModel):
-    """Information about a single MCP tool discovered from a server."""
-
-    name: str
-    description: str
-    input_schema: dict[str, Any]
-
-
-class MCPToolsDiscoveredResponse(ToolResponseBase):
-    """Response when MCP tools are discovered from a server (agent-internal)."""
-
-    type: ResponseType = ResponseType.MCP_TOOLS_DISCOVERED
-    server_url: str
-    tools: list[MCPToolInfo]
-
-
-class MCPToolOutputResponse(ToolResponseBase):
-    """Response after executing an MCP tool."""
-
-    type: ResponseType = ResponseType.MCP_TOOL_OUTPUT
-    server_url: str
-    tool_name: str
-    result: Any = None
-    success: bool = True
-
-
-# Agent-browser multi-step automation models
-
-
-class BrowserNavigateResponse(ToolResponseBase):
-    """Response for browser_navigate tool."""
-
-    type: ResponseType = ResponseType.BROWSER_NAVIGATE
-    url: str
-    title: str
-    snapshot: str  # Interactive accessibility tree with @ref IDs
-
-
-class BrowserActResponse(ToolResponseBase):
-    """Response for browser_act tool."""
-
-    type: ResponseType = ResponseType.BROWSER_ACT
-    action: str
-    current_url: str = ""
-    snapshot: str  # Updated accessibility tree after the action
-
-
-class BrowserScreenshotResponse(ToolResponseBase):
-    """Response for browser_screenshot tool."""
-
-    type: ResponseType = ResponseType.BROWSER_SCREENSHOT
-    file_id: str  # Workspace file ID — use read_workspace_file to retrieve
-    filename: str
-
-
-# Agent generation tool response models
-
-
-class ValidationResultResponse(ToolResponseBase):
-    """Response for validate_agent_graph tool."""
-
-    type: ResponseType = ResponseType.AGENT_BUILDER_VALIDATION_RESULT
-    valid: bool
-    errors: list[str] = Field(default_factory=list)
-    error_count: int = 0
-
-
-class FixResultResponse(ToolResponseBase):
-    """Response for fix_agent_graph tool."""
-
-    type: ResponseType = ResponseType.AGENT_BUILDER_FIX_RESULT
-    fixed_agent_json: dict[str, Any]
-    fixes_applied: list[str] = Field(default_factory=list)
-    fix_count: int = 0
-    valid_after_fix: bool = False
-    remaining_errors: list[str] = Field(default_factory=list)
-
-
-# Folder management models
-
-
-class FolderAgentSummary(BaseModel):
-    """Lightweight agent info for folder listings."""
-
-    id: str
-    name: str
-    description: str = ""
-
-
-class FolderInfo(BaseModel):
-    """Information about a folder."""
-
-    id: str
-    name: str
-    parent_id: str | None = None
-    icon: str | None = None
-    color: str | None = None
-    agent_count: int = 0
-    subfolder_count: int = 0
-    agents: list[FolderAgentSummary] | None = None
-
-
-class FolderTreeInfo(FolderInfo):
-    """Folder with nested children for tree display."""
-
-    children: list["FolderTreeInfo"] = []
-
-
-class FolderCreatedResponse(ToolResponseBase):
-    """Response when a folder is created."""
-
-    type: ResponseType = ResponseType.FOLDER_CREATED
-    folder: FolderInfo
-
-
-class FolderListResponse(ToolResponseBase):
-    """Response for listing folders."""
-
-    type: ResponseType = ResponseType.FOLDER_LIST
-    folders: list[FolderInfo] = Field(default_factory=list)
-    tree: list[FolderTreeInfo] | None = None
-    root_agents: list[FolderAgentSummary] | None = None
-    count: int = 0
-
-
-class FolderUpdatedResponse(ToolResponseBase):
-    """Response when a folder is updated."""
-
-    type: ResponseType = ResponseType.FOLDER_UPDATED
-    folder: FolderInfo
-
-
-class FolderMovedResponse(ToolResponseBase):
-    """Response when a folder is moved."""
-
-    type: ResponseType = ResponseType.FOLDER_MOVED
-    folder: FolderInfo
-    target_parent_id: str | None = None
-
-
-class FolderDeletedResponse(ToolResponseBase):
-    """Response when a folder is deleted."""
-
-    type: ResponseType = ResponseType.FOLDER_DELETED
-    folder_id: str
-
-
-class AgentsMovedToFolderResponse(ToolResponseBase):
-    """Response when agents are moved to a folder."""
-
-    type: ResponseType = ResponseType.AGENTS_MOVED_TO_FOLDER
-    agent_ids: list[str]
-    agent_names: list[str] = []
-    folder_id: str | None = None
-    count: int = 0

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

@@ -5,13 +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.data.execution import ExecutionStatus
+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
@@ -21,15 +24,12 @@ from backend.util.timezone_utils import (
 )
 
 from .base import BaseTool
-from .execution_utils import get_execution_outputs, wait_for_execution
 from .helpers import get_inputs_from_schema
 from .models import (
     AgentDetails,
     AgentDetailsResponse,
-    AgentOutputResponse,
     ErrorResponse,
     ExecutionOptions,
-    ExecutionOutputInfo,
     ExecutionStartedResponse,
     InputValidationErrorResponse,
     SetupInfo,
@@ -70,7 +70,6 @@ class RunAgentInput(BaseModel):
     schedule_name: str = ""
     cron: str = ""
     timezone: str = "UTC"
-    wait_for_result: int = Field(default=0, ge=0, le=300)
 
     @field_validator(
         "username_agent_slug",
@@ -152,14 +151,6 @@ class RunAgentTool(BaseTool):
                     "type": "string",
                     "description": "IANA timezone for schedule (default: UTC)",
                 },
-                "wait_for_result": {
-                    "type": "integer",
-                    "description": (
-                        "Max seconds to wait for execution to complete (0-300). "
-                        "If >0, blocks until the execution finishes or times out. "
-                        "Returns execution outputs when complete."
-                    ),
-                },
             },
             "required": [],
         }
@@ -209,7 +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:
@@ -218,7 +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,
@@ -354,7 +347,6 @@ class RunAgentTool(BaseTool):
                     graph=graph,
                     graph_credentials=graph_credentials,
                     inputs=params.inputs,
-                    wait_for_result=params.wait_for_result,
                 )
 
         except NotFoundError as e:
@@ -438,9 +430,8 @@ class RunAgentTool(BaseTool):
         graph: GraphModel,
         graph_credentials: dict[str, CredentialsMetaInput],
         inputs: dict[str, Any],
-        wait_for_result: int = 0,
     ) -> ToolResponseBase:
-        """Execute an agent immediately, optionally waiting for completion."""
+        """Execute an agent immediately."""
         session_id = session.session_id
 
         # Check rate limits
@@ -477,93 +468,6 @@ class RunAgentTool(BaseTool):
         )
 
         library_agent_link = f"/library/agents/{library_agent.id}"
-
-        # If wait_for_result is requested, wait for execution to complete
-        if wait_for_result > 0:
-            logger.info(
-                f"Waiting up to {wait_for_result}s for execution {execution.id}"
-            )
-            completed = await wait_for_execution(
-                user_id=user_id,
-                graph_id=library_agent.graph_id,
-                execution_id=execution.id,
-                timeout_seconds=wait_for_result,
-            )
-
-            if completed and completed.status == ExecutionStatus.COMPLETED:
-                outputs = get_execution_outputs(completed)
-                return AgentOutputResponse(
-                    message=(
-                        f"Agent '{library_agent.name}' completed successfully. "
-                        f"View at {library_agent_link}."
-                    ),
-                    session_id=session_id,
-                    agent_name=library_agent.name,
-                    agent_id=library_agent.graph_id,
-                    library_agent_id=library_agent.id,
-                    library_agent_link=library_agent_link,
-                    execution=ExecutionOutputInfo(
-                        execution_id=execution.id,
-                        status=completed.status.value,
-                        started_at=completed.started_at,
-                        ended_at=completed.ended_at,
-                        outputs=outputs or {},
-                    ),
-                )
-            elif completed and completed.status == ExecutionStatus.FAILED:
-                error_detail = completed.stats.error if completed.stats else None
-                return ErrorResponse(
-                    message=(
-                        f"Agent '{library_agent.name}' execution failed. "
-                        f"View details at {library_agent_link}."
-                    ),
-                    session_id=session_id,
-                    error=error_detail,
-                )
-            elif completed and completed.status == ExecutionStatus.TERMINATED:
-                error_detail = completed.stats.error if completed.stats else None
-                return ErrorResponse(
-                    message=(
-                        f"Agent '{library_agent.name}' execution was terminated. "
-                        f"View details at {library_agent_link}."
-                    ),
-                    session_id=session_id,
-                    error=error_detail,
-                )
-            elif completed and completed.status == ExecutionStatus.REVIEW:
-                return ExecutionStartedResponse(
-                    message=(
-                        f"Agent '{library_agent.name}' is awaiting human review. "
-                        f"The user can approve or reject inline. After approval, "
-                        f"the execution resumes automatically. Use view_agent_output "
-                        f"with execution_id='{execution.id}' to check the result."
-                    ),
-                    session_id=session_id,
-                    execution_id=execution.id,
-                    graph_id=library_agent.graph_id,
-                    graph_name=library_agent.name,
-                    library_agent_id=library_agent.id,
-                    library_agent_link=library_agent_link,
-                    status=ExecutionStatus.REVIEW.value,
-                )
-            else:
-                status = completed.status.value if completed else "unknown"
-                return ExecutionStartedResponse(
-                    message=(
-                        f"Agent '{library_agent.name}' is still {status} after "
-                        f"{wait_for_result}s. Check results later at "
-                        f"{library_agent_link}. "
-                        f"Use view_agent_output with wait_if_running to check again."
-                    ),
-                    session_id=session_id,
-                    execution_id=execution.id,
-                    graph_id=library_agent.graph_id,
-                    graph_name=library_agent.name,
-                    library_agent_id=library_agent.id,
-                    library_agent_link=library_agent_link,
-                    status=status,
-                )
-
         return ExecutionStartedResponse(
             message=(
                 f"Agent '{library_agent.name}' execution started successfully. "
@@ -618,7 +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

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

@@ -2,35 +2,41 @@
 
 import logging
 import uuid
+from collections import defaultdict
 from typing import Any
 
-from backend.blocks import BlockType, get_block
-from backend.blocks._base import AnyBlockSchema
-from backend.copilot.constants import (
-    COPILOT_NODE_EXEC_ID_SEPARATOR,
-    COPILOT_NODE_PREFIX,
-    COPILOT_SESSION_PREFIX,
+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.copilot.model import ChatSession
-from backend.copilot.sdk.file_ref import FileRefExpansionError, expand_file_refs_in_args
-from backend.data.db_accessors import review_db
+from backend.blocks import get_block
+from backend.blocks._base import AnyBlockSchema
 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 execute_block, get_inputs_from_schema, resolve_block_credentials
+from .helpers import get_inputs_from_schema
 from .models import (
     BlockDetails,
     BlockDetailsResponse,
+    BlockOutputResponse,
     ErrorResponse,
     InputValidationErrorResponse,
-    ReviewRequiredResponse,
     SetupInfo,
     SetupRequirementsResponse,
     ToolResponseBase,
     UserReadiness,
 )
-from .utils import build_missing_credentials_from_field_info
+from .utils import (
+    build_missing_credentials_from_field_info,
+    match_credentials_to_requirements,
+)
 
 logger = logging.getLogger(__name__)
 
@@ -49,9 +55,7 @@ class RunBlockTool(BaseTool):
             "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. "
-            "If a block requires human review, use continue_run_block with the "
-            "review_id after the user approves."
+            "required inputs and outputs. Then call again with proper input_data to execute."
         )
 
     @property
@@ -82,7 +86,7 @@ class RunBlockTool(BaseTool):
                     ),
                 },
             },
-            "required": ["block_id", "block_name", "input_data"],
+            "required": ["block_id", "input_data"],
         }
 
     @property
@@ -148,27 +152,20 @@ class RunBlockTool(BaseTool):
             block.block_type in COPILOT_EXCLUDED_BLOCK_TYPES
             or block.id in COPILOT_EXCLUDED_BLOCK_IDS
         ):
-            # Provide actionable guidance for blocks with dedicated tools
-            if block.block_type == BlockType.MCP_TOOL:
-                hint = (
-                    " Use the `run_mcp_tool` tool instead — it handles "
-                    "MCP server discovery, authentication, and execution."
-                )
-            elif block.block_type == BlockType.AGENT:
-                hint = " Use the `run_agent` tool instead."
-            else:
-                hint = " This block is designed for use within graphs only."
             return ErrorResponse(
-                message=f"Block '{block.name}' cannot be run directly.{hint}",
+                message=(
+                    f"Block '{block.name}' cannot be run directly in CoPilot. "
+                    "This block is designed for use within graphs only."
+                ),
                 session_id=session_id,
             )
 
         logger.info(f"Executing block {block.name} ({block_id}) for user {user_id}")
 
-        (
-            matched_credentials,
-            missing_credentials,
-        ) = await resolve_block_credentials(user_id, block, input_data)
+        creds_manager = IntegrationCredentialsManager()
+        matched_credentials, missing_credentials = (
+            await self._resolve_block_credentials(user_id, block, input_data)
+        )
 
         # Get block schemas for details/validation
         try:
@@ -198,29 +195,6 @@ class RunBlockTool(BaseTool):
                 session_id=session_id,
             )
 
-        # Expand @@agptfile: refs in input_data with the block's input
-        # schema.  The generic _truncating wrapper skips opaque object
-        # properties (input_data has no declared inner properties in the
-        # tool schema), so file ref tokens are still intact here.
-        # Using the block's schema lets us return raw text for string-typed
-        # fields and parsed structures for list/dict-typed fields.
-        if input_data:
-            try:
-                input_data = await expand_file_refs_in_args(
-                    input_data,
-                    user_id,
-                    session,
-                    input_schema=input_schema,
-                )
-            except FileRefExpansionError as exc:
-                return ErrorResponse(
-                    message=(
-                        f"Failed to resolve file reference: {exc}. "
-                        "Ensure the file exists before referencing it."
-                    ),
-                    session_id=session_id,
-                )
-
         if missing_credentials:
             # Return setup requirements response with missing credentials
             credentials_fields_info = block.input_schema.get_credentials_fields_info()
@@ -300,97 +274,169 @@ class RunBlockTool(BaseTool):
                 user_authenticated=True,
             )
 
-        # Generate synthetic IDs for CoPilot context.
-        # Encode node_id in node_exec_id so it can be extracted later
-        # (e.g. for auto-approve, where we need node_id but have no NodeExecution row).
-        synthetic_graph_id = f"{COPILOT_SESSION_PREFIX}{session.session_id}"
-        synthetic_node_id = f"{COPILOT_NODE_PREFIX}{block_id}"
+        try:
+            # Get or create user's workspace for CoPilot file operations
+            workspace = await get_or_create_workspace(user_id)
 
-        # Check for an existing WAITING review for this block with the same input.
-        # If the LLM retries run_block with identical input, we reuse the existing
-        # review instead of creating duplicates. Different inputs = new execution.
-        existing_reviews = await review_db().get_pending_reviews_for_execution(
-            synthetic_graph_id, user_id
-        )
-        existing_review = next(
-            (
-                r
-                for r in existing_reviews
-                if r.node_id == synthetic_node_id
-                and r.status.value == "WAITING"
-                and r.payload == input_data
-            ),
-            None,
-        )
-        if existing_review:
-            return ReviewRequiredResponse(
-                message=(
-                    f"Block '{block.name}' requires human review. "
-                    f"After the user approves, call continue_run_block with "
-                    f"review_id='{existing_review.node_exec_id}' to execute."
-                ),
-                session_id=session_id,
-                block_id=block_id,
-                block_name=block.name,
-                review_id=existing_review.node_exec_id,
-                graph_exec_id=synthetic_graph_id,
-                input_data=input_data,
+            # Generate synthetic IDs for CoPilot context
+            # Each chat session is treated as its own agent with one continuous run
+            # This means:
+            # - graph_id (agent) = session (memories scoped to session when limit_to_agent=True)
+            # - graph_exec_id (run) = session (memories scoped to session when limit_to_run=True)
+            # - node_exec_id = unique per block execution
+            synthetic_graph_id = f"copilot-session-{session.session_id}"
+            synthetic_graph_exec_id = f"copilot-session-{session.session_id}"
+            synthetic_node_id = f"copilot-node-{block_id}"
+            synthetic_node_exec_id = (
+                f"copilot-{session.session_id}-{uuid.uuid4().hex[:8]}"
             )
 
-        synthetic_node_exec_id = (
-            f"{synthetic_node_id}{COPILOT_NODE_EXEC_ID_SEPARATOR}"
-            f"{uuid.uuid4().hex[:8]}"
-        )
-
-        # Check for HITL review before execution.
-        # This creates the review record in the DB for CoPilot flows.
-        review_context = ExecutionContext(
-            user_id=user_id,
-            graph_id=synthetic_graph_id,
-            graph_exec_id=synthetic_graph_id,
-            graph_version=1,
-            node_id=synthetic_node_id,
-            node_exec_id=synthetic_node_exec_id,
-            sensitive_action_safe_mode=True,
-        )
-        should_pause, input_data = await block.is_block_exec_need_review(
-            input_data,
-            user_id=user_id,
-            node_id=synthetic_node_id,
-            node_exec_id=synthetic_node_exec_id,
-            graph_exec_id=synthetic_graph_id,
-            graph_id=synthetic_graph_id,
-            graph_version=1,
-            execution_context=review_context,
-            is_graph_execution=False,
-        )
-        if should_pause:
-            return ReviewRequiredResponse(
-                message=(
-                    f"Block '{block.name}' requires human review. "
-                    f"After the user approves, call continue_run_block with "
-                    f"review_id='{synthetic_node_exec_id}' to execute."
-                ),
-                session_id=session_id,
-                block_id=block_id,
-                block_name=block.name,
-                review_id=synthetic_node_exec_id,
-                graph_exec_id=synthetic_graph_id,
-                input_data=input_data,
+            # Create unified execution context with all required fields
+            execution_context = ExecutionContext(
+                # Execution identity
+                user_id=user_id,
+                graph_id=synthetic_graph_id,
+                graph_exec_id=synthetic_graph_exec_id,
+                graph_version=1,  # Versions are 1-indexed
+                node_id=synthetic_node_id,
+                node_exec_id=synthetic_node_exec_id,
+                # Workspace with session scoping
+                workspace_id=workspace.id,
+                session_id=session.session_id,
             )
 
-        return await execute_block(
-            block=block,
-            block_id=block_id,
-            input_data=input_data,
-            user_id=user_id,
-            session_id=session_id,
-            node_exec_id=synthetic_node_exec_id,
-            matched_credentials=matched_credentials,
-        )
+            # Prepare kwargs for block execution
+            # Keep individual kwargs for backwards compatibility with existing blocks
+            exec_kwargs: dict[str, Any] = {
+                "user_id": user_id,
+                "execution_context": execution_context,
+                # Legacy: individual kwargs for blocks not yet using execution_context
+                "workspace_id": workspace.id,
+                "graph_exec_id": synthetic_graph_exec_id,
+                "node_exec_id": synthetic_node_exec_id,
+                "node_id": synthetic_node_id,
+                "graph_version": 1,  # Versions are 1-indexed
+                "graph_id": synthetic_graph_id,
+            }
+
+            for field_name, cred_meta in matched_credentials.items():
+                # Inject metadata into input_data (for validation)
+                if field_name not in input_data:
+                    input_data[field_name] = cred_meta.model_dump()
+
+                # Fetch actual credentials and pass as kwargs (for execution)
+                actual_credentials = await creds_manager.get(
+                    user_id, cred_meta.id, lock=False
+                )
+                if actual_credentials:
+                    exec_kwargs[field_name] = actual_credentials
+                else:
+                    return ErrorResponse(
+                        message=f"Failed to retrieve credentials for {field_name}",
+                        session_id=session_id,
+                    )
+
+            # Execute the block and collect outputs
+            outputs: dict[str, list[Any]] = defaultdict(list)
+            async for output_name, output_data in block.execute(
+                input_data,
+                **exec_kwargs,
+            ):
+                outputs[output_name].append(output_data)
+
+            return BlockOutputResponse(
+                message=f"Block '{block.name}' executed successfully",
+                block_id=block_id,
+                block_name=block.name,
+                outputs=dict(outputs),
+                success=True,
+                session_id=session_id,
+            )
+
+        except BlockError as e:
+            logger.warning(f"Block execution failed: {e}")
+            return ErrorResponse(
+                message=f"Block execution failed: {e}",
+                error=str(e),
+                session_id=session_id,
+            )
+        except Exception as e:
+            logger.error(f"Unexpected error executing block: {e}", exc_info=True)
+            return ErrorResponse(
+                message=f"Failed to execute block: {str(e)}",
+                error=str(e),
+                session_id=session_id,
+            )
+
+    async def _resolve_block_credentials(
+        self,
+        user_id: str,
+        block: AnyBlockSchema,
+        input_data: dict[str, Any] | None = None,
+    ) -> tuple[dict[str, CredentialsMetaInput], list[CredentialsMetaInput]]:
+        """
+        Resolve credentials for a block by matching user's available credentials.
+
+        Args:
+            user_id: User ID
+            block: Block to resolve credentials for
+            input_data: Input data for the block (used to determine provider via discriminator)
+
+        Returns:
+            tuple of (matched_credentials, missing_credentials) - matched credentials
+            are used for block execution, missing ones indicate setup requirements.
+        """
+        input_data = input_data or {}
+        requirements = self._resolve_discriminated_credentials(block, input_data)
+
+        if not requirements:
+            return {}, []
+
+        return await match_credentials_to_requirements(user_id, requirements)
 
     def _get_inputs_list(self, block: AnyBlockSchema) -> list[dict[str, Any]]:
         """Extract non-credential inputs from block schema."""
         schema = block.input_schema.jsonschema()
         credentials_fields = set(block.input_schema.get_credentials_fields().keys())
         return get_inputs_from_schema(schema, exclude_fields=credentials_fields)
+
+    def _resolve_discriminated_credentials(
+        self,
+        block: AnyBlockSchema,
+        input_data: dict[str, Any],
+    ) -> dict[str, CredentialsFieldInfo]:
+        """Resolve credential requirements, applying discriminator logic where needed."""
+        credentials_fields_info = block.input_schema.get_credentials_fields_info()
+        if not credentials_fields_info:
+            return {}
+
+        resolved: dict[str, CredentialsFieldInfo] = {}
+
+        for field_name, field_info in credentials_fields_info.items():
+            effective_field_info = field_info
+
+            if field_info.discriminator and field_info.discriminator_mapping:
+                discriminator_value = input_data.get(field_info.discriminator)
+                if discriminator_value is None:
+                    field = block.input_schema.model_fields.get(
+                        field_info.discriminator
+                    )
+                    if field and field.default is not PydanticUndefined:
+                        discriminator_value = field.default
+
+                if (
+                    discriminator_value
+                    and discriminator_value in field_info.discriminator_mapping
+                ):
+                    effective_field_info = field_info.discriminate(discriminator_value)
+                    # For host-scoped credentials, add the discriminator value
+                    # (e.g., URL) so _credential_is_for_host can match it
+                    effective_field_info.discriminator_values.add(discriminator_value)
+                    logger.debug(
+                        f"Discriminated provider for {field_name}: "
+                        f"{discriminator_value} -> {effective_field_info.provider}"
+                    )
+
+            resolved[field_name] = effective_field_info
+
+        return resolved

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

@@ -4,17 +4,16 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
-from backend.blocks._base import BlockType
-
-from ._test_data import make_session
-from .models import (
+from backend.api.features.chat.tools.models import (
     BlockDetailsResponse,
     BlockOutputResponse,
     ErrorResponse,
     InputValidationErrorResponse,
-    ReviewRequiredResponse,
 )
-from .run_block import RunBlockTool
+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"
 
@@ -28,16 +27,9 @@ def make_mock_block(
     mock.name = name
     mock.block_type = block_type
     mock.disabled = disabled
-    mock.is_sensitive_action = False
     mock.input_schema = MagicMock()
     mock.input_schema.jsonschema.return_value = {"properties": {}, "required": []}
-    mock.input_schema.get_credentials_fields_info.return_value = {}
-    mock.input_schema.get_credentials_fields.return_value = {}
-
-    async def _no_review(input_data, **kwargs):
-        return False, input_data
-
-    mock.is_block_exec_need_review = _no_review
+    mock.input_schema.get_credentials_fields_info.return_value = []
     return mock
 
 
@@ -54,7 +46,6 @@ def make_mock_block_with_schema(
     mock.name = name
     mock.block_type = BlockType.STANDARD
     mock.disabled = False
-    mock.is_sensitive_action = False
     mock.description = f"Test block: {name}"
 
     input_schema = {
@@ -72,12 +63,6 @@ def make_mock_block_with_schema(
     mock.output_schema = MagicMock()
     mock.output_schema.jsonschema.return_value = output_schema
 
-    # Default: no review needed, pass through input_data unchanged
-    async def _no_review(input_data, **kwargs):
-        return False, input_data
-
-    mock.is_block_exec_need_review = _no_review
-
     return mock
 
 
@@ -92,7 +77,7 @@ class TestRunBlockFiltering:
         input_block = make_mock_block("input-block-id", "Input Block", BlockType.INPUT)
 
         with patch(
-            "backend.copilot.tools.run_block.get_block",
+            "backend.api.features.chat.tools.run_block.get_block",
             return_value=input_block,
         ):
             tool = RunBlockTool()
@@ -104,7 +89,7 @@ class TestRunBlockFiltering:
             )
 
         assert isinstance(response, ErrorResponse)
-        assert "cannot be run directly" in response.message
+        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")
@@ -118,7 +103,7 @@ class TestRunBlockFiltering:
         )
 
         with patch(
-            "backend.copilot.tools.run_block.get_block",
+            "backend.api.features.chat.tools.run_block.get_block",
             return_value=smart_block,
         ):
             tool = RunBlockTool()
@@ -130,7 +115,7 @@ class TestRunBlockFiltering:
             )
 
         assert isinstance(response, ErrorResponse)
-        assert "cannot be run directly" in response.message
+        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):
@@ -141,15 +126,9 @@ class TestRunBlockFiltering:
             "standard-id", "HTTP Request", BlockType.STANDARD
         )
 
-        with (
-            patch(
-                "backend.copilot.tools.run_block.get_block",
-                return_value=standard_block,
-            ),
-            patch(
-                "backend.copilot.tools.helpers.match_credentials_to_requirements",
-                return_value=({}, []),
-            ),
+        with patch(
+            "backend.api.features.chat.tools.run_block.get_block",
+            return_value=standard_block,
         ):
             tool = RunBlockTool()
             response = await tool._execute(
@@ -162,7 +141,7 @@ class TestRunBlockFiltering:
         # 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" not in response.message
+            assert "cannot be run directly in CoPilot" not in response.message
 
 
 class TestRunBlockInputValidation:
@@ -175,7 +154,12 @@ class TestRunBlockInputValidation:
 
     @pytest.mark.asyncio(loop_scope="session")
     async def test_unknown_input_fields_are_rejected(self):
-        """run_block rejects unknown input fields instead of silently ignoring them."""
+        """run_block rejects unknown input fields instead of silently ignoring them.
+
+        Scenario: The AI Text Generator block has a field called 'model' (for LLM model
+        selection), but the LLM calling the tool guesses wrong and sends 'LLM_Model'
+        instead. The block should reject the request and return the valid schema.
+        """
         session = make_session(user_id=_TEST_USER_ID)
 
         mock_block = make_mock_block_with_schema(
@@ -198,31 +182,27 @@ class TestRunBlockInputValidation:
             output_properties={"response": {"type": "string"}},
         )
 
-        with (
-            patch(
-                "backend.copilot.tools.run_block.get_block",
-                return_value=mock_block,
-            ),
-            patch(
-                "backend.copilot.tools.helpers.match_credentials_to_requirements",
-                return_value=({}, []),
-            ),
+        with patch(
+            "backend.api.features.chat.tools.run_block.get_block",
+            return_value=mock_block,
         ):
             tool = RunBlockTool()
+
+            # Provide 'prompt' (correct) but 'LLM_Model' instead of 'model' (wrong key)
             response = await tool._execute(
                 user_id=_TEST_USER_ID,
                 session=session,
                 block_id="ai-text-gen-id",
                 input_data={
                     "prompt": "Write a haiku about coding",
-                    "LLM_Model": "claude-opus-4-6",
+                    "LLM_Model": "claude-opus-4-6",  # WRONG KEY - should be 'model'
                 },
             )
 
         assert isinstance(response, InputValidationErrorResponse)
         assert "LLM_Model" in response.unrecognized_fields
         assert "Block was not executed" in response.message
-        assert "inputs" in response.model_dump()
+        assert "inputs" in response.model_dump()  # valid schema included
 
     @pytest.mark.asyncio(loop_scope="session")
     async def test_multiple_wrong_keys_are_all_reported(self):
@@ -241,26 +221,21 @@ class TestRunBlockInputValidation:
             required_fields=["prompt"],
         )
 
-        with (
-            patch(
-                "backend.copilot.tools.run_block.get_block",
-                return_value=mock_block,
-            ),
-            patch(
-                "backend.copilot.tools.helpers.match_credentials_to_requirements",
-                return_value=({}, []),
-            ),
+        with patch(
+            "backend.api.features.chat.tools.run_block.get_block",
+            return_value=mock_block,
         ):
             tool = RunBlockTool()
+
             response = await tool._execute(
                 user_id=_TEST_USER_ID,
                 session=session,
                 block_id="ai-text-gen-id",
                 input_data={
-                    "prompt": "Hello",
-                    "llm_model": "claude-opus-4-6",
-                    "system_prompt": "Be helpful",
-                    "retries": 5,
+                    "prompt": "Hello",  # correct
+                    "llm_model": "claude-opus-4-6",  # WRONG - should be 'model'
+                    "system_prompt": "Be helpful",  # WRONG - should be 'sys_prompt'
+                    "retries": 5,  # WRONG - should be 'retry'
                 },
             )
 
@@ -287,26 +262,23 @@ class TestRunBlockInputValidation:
             required_fields=["prompt"],
         )
 
-        with (
-            patch(
-                "backend.copilot.tools.run_block.get_block",
-                return_value=mock_block,
-            ),
-            patch(
-                "backend.copilot.tools.helpers.match_credentials_to_requirements",
-                return_value=({}, []),
-            ),
+        with patch(
+            "backend.api.features.chat.tools.run_block.get_block",
+            return_value=mock_block,
         ):
             tool = RunBlockTool()
+
+            # 'prompt' is missing AND 'LLM_Model' is an unknown field
             response = await tool._execute(
                 user_id=_TEST_USER_ID,
                 session=session,
                 block_id="ai-text-gen-id",
                 input_data={
-                    "LLM_Model": "claude-opus-4-6",
+                    "LLM_Model": "claude-opus-4-6",  # wrong key, and 'prompt' is missing
                 },
             )
 
+        # Unknown fields are caught first
         assert isinstance(response, InputValidationErrorResponse)
         assert "LLM_Model" in response.unrecognized_fields
 
@@ -330,23 +302,15 @@ class TestRunBlockInputValidation:
 
         mock_block.execute = mock_execute
 
-        mock_workspace_db = MagicMock()
-        mock_workspace_db.get_or_create_workspace = AsyncMock(
-            return_value=MagicMock(id="test-workspace-id")
-        )
-
         with (
             patch(
-                "backend.copilot.tools.run_block.get_block",
+                "backend.api.features.chat.tools.run_block.get_block",
                 return_value=mock_block,
             ),
             patch(
-                "backend.copilot.tools.helpers.match_credentials_to_requirements",
-                return_value=({}, []),
-            ),
-            patch(
-                "backend.copilot.tools.helpers.workspace_db",
-                return_value=mock_workspace_db,
+                "backend.api.features.chat.tools.run_block.get_or_create_workspace",
+                new_callable=AsyncMock,
+                return_value=MagicMock(id="test-workspace-id"),
             ),
         ):
             tool = RunBlockTool()
@@ -357,7 +321,7 @@ class TestRunBlockInputValidation:
                 block_id="ai-text-gen-id",
                 input_data={
                     "prompt": "Write a haiku",
-                    "model": "gpt-4o-mini",
+                    "model": "gpt-4o-mini",  # correct field name
                 },
             )
 
@@ -379,191 +343,20 @@ class TestRunBlockInputValidation:
             required_fields=["prompt"],
         )
 
-        with (
-            patch(
-                "backend.copilot.tools.run_block.get_block",
-                return_value=mock_block,
-            ),
-            patch(
-                "backend.copilot.tools.helpers.match_credentials_to_requirements",
-                return_value=({}, []),
-            ),
+        with patch(
+            "backend.api.features.chat.tools.run_block.get_block",
+            return_value=mock_block,
         ):
             tool = RunBlockTool()
 
+            # Only provide valid optional field, missing required 'prompt'
             response = await tool._execute(
                 user_id=_TEST_USER_ID,
                 session=session,
                 block_id="ai-text-gen-id",
                 input_data={
-                    "model": "gpt-4o-mini",
+                    "model": "gpt-4o-mini",  # valid but optional
                 },
             )
 
         assert isinstance(response, BlockDetailsResponse)
-
-
-class TestRunBlockSensitiveAction:
-    """Tests for sensitive action HITL review in RunBlockTool.
-
-    run_block calls is_block_exec_need_review() explicitly before execution.
-    When review is needed (should_pause=True), ReviewRequiredResponse is returned.
-    """
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_sensitive_block_paused_returns_review_required(self):
-        """When is_block_exec_need_review returns should_pause=True, ReviewRequiredResponse is returned."""
-        session = make_session(user_id=_TEST_USER_ID)
-
-        input_data = {
-            "repo_url": "https://github.com/test/repo",
-            "branch": "feature-branch",
-        }
-        mock_block = make_mock_block_with_schema(
-            block_id="delete-branch-id",
-            name="Delete Branch",
-            input_properties={
-                "repo_url": {"type": "string"},
-                "branch": {"type": "string"},
-            },
-            required_fields=["repo_url", "branch"],
-        )
-        mock_block.is_sensitive_action = True
-        mock_block.is_block_exec_need_review = AsyncMock(
-            return_value=(True, input_data)
-        )
-
-        with (
-            patch(
-                "backend.copilot.tools.run_block.get_block",
-                return_value=mock_block,
-            ),
-            patch(
-                "backend.copilot.tools.helpers.match_credentials_to_requirements",
-                return_value=({}, []),
-            ),
-        ):
-            tool = RunBlockTool()
-            response = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                block_id="delete-branch-id",
-                input_data=input_data,
-            )
-
-        assert isinstance(response, ReviewRequiredResponse)
-        assert "requires human review" in response.message
-        assert "continue_run_block" in response.message
-        assert response.block_name == "Delete Branch"
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_sensitive_block_executes_after_approval(self):
-        """After approval (should_pause=False), sensitive blocks execute and return outputs."""
-        session = make_session(user_id=_TEST_USER_ID)
-
-        input_data = {
-            "repo_url": "https://github.com/test/repo",
-            "branch": "feature-branch",
-        }
-        mock_block = make_mock_block_with_schema(
-            block_id="delete-branch-id",
-            name="Delete Branch",
-            input_properties={
-                "repo_url": {"type": "string"},
-                "branch": {"type": "string"},
-            },
-            required_fields=["repo_url", "branch"],
-        )
-        mock_block.is_sensitive_action = True
-        mock_block.is_block_exec_need_review = AsyncMock(
-            return_value=(False, input_data)
-        )
-
-        async def mock_execute(input_data, **kwargs):
-            yield "result", "Branch deleted successfully"
-
-        mock_block.execute = mock_execute
-
-        mock_workspace_db = MagicMock()
-        mock_workspace_db.get_or_create_workspace = AsyncMock(
-            return_value=MagicMock(id="test-workspace-id")
-        )
-
-        with (
-            patch(
-                "backend.copilot.tools.run_block.get_block",
-                return_value=mock_block,
-            ),
-            patch(
-                "backend.copilot.tools.helpers.match_credentials_to_requirements",
-                return_value=({}, []),
-            ),
-            patch(
-                "backend.copilot.tools.helpers.workspace_db",
-                return_value=mock_workspace_db,
-            ),
-        ):
-            tool = RunBlockTool()
-            response = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                block_id="delete-branch-id",
-                input_data=input_data,
-            )
-
-        assert isinstance(response, BlockOutputResponse)
-        assert response.success is True
-
-    @pytest.mark.asyncio(loop_scope="session")
-    async def test_non_sensitive_block_executes_normally(self):
-        """Non-sensitive blocks skip review and execute directly."""
-        session = make_session(user_id=_TEST_USER_ID)
-
-        input_data = {"url": "https://example.com"}
-        mock_block = make_mock_block_with_schema(
-            block_id="http-request-id",
-            name="HTTP Request",
-            input_properties={
-                "url": {"type": "string"},
-            },
-            required_fields=["url"],
-        )
-        mock_block.is_sensitive_action = False
-        mock_block.is_block_exec_need_review = AsyncMock(
-            return_value=(False, input_data)
-        )
-
-        async def mock_execute(input_data, **kwargs):
-            yield "response", {"status": 200}
-
-        mock_block.execute = mock_execute
-
-        mock_workspace_db = MagicMock()
-        mock_workspace_db.get_or_create_workspace = AsyncMock(
-            return_value=MagicMock(id="test-workspace-id")
-        )
-
-        with (
-            patch(
-                "backend.copilot.tools.run_block.get_block",
-                return_value=mock_block,
-            ),
-            patch(
-                "backend.copilot.tools.helpers.match_credentials_to_requirements",
-                return_value=({}, []),
-            ),
-            patch(
-                "backend.copilot.tools.helpers.workspace_db",
-                return_value=mock_workspace_db,
-            ),
-        ):
-            tool = RunBlockTool()
-            response = await tool._execute(
-                user_id=_TEST_USER_ID,
-                session=session,
-                block_id="http-request-id",
-                input_data=input_data,
-            )
-
-        assert isinstance(response, BlockOutputResponse)
-        assert response.success is True

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

@@ -13,7 +13,6 @@ import logging
 import os
 import platform
 import shutil
-import signal
 
 logger = logging.getLogger(__name__)
 
@@ -246,7 +245,6 @@ async def run_sandboxed(
             stderr=asyncio.subprocess.PIPE,
             cwd=cwd,
             env=safe_env,
-            start_new_session=True,  # Own process group for clean kill
         )
 
         try:
@@ -257,18 +255,7 @@ async def run_sandboxed(
             stderr = stderr_bytes.decode("utf-8", errors="replace")
             return stdout, stderr, proc.returncode or 0, False
         except asyncio.TimeoutError:
-            # Kill entire process group (bwrap + all children).
-            # proc.kill() alone only kills the bwrap parent, leaving
-            # children running until they finish naturally.
-            try:
-                os.killpg(proc.pid, signal.SIGKILL)
-            except ProcessLookupError:
-                pass  # Already exited
-            except OSError as kill_err:
-                logger.warning(
-                    "Failed to kill process group %d: %s", proc.pid, kill_err
-                )
-            # Always reap the subprocess regardless of killpg outcome.
+            proc.kill()
             await proc.communicate()
             return "", f"Execution timed out after {timeout}s", -1, True
 

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,

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

@@ -4,13 +4,13 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
+from backend.api.features.chat.tools.models import BlockDetailsResponse
+from backend.api.features.chat.tools.run_block import RunBlockTool
 from backend.blocks._base import BlockType
 from backend.data.model import CredentialsMetaInput
 from backend.integrations.providers import ProviderName
 
 from ._test_data import make_session
-from .models import BlockDetailsResponse
-from .run_block import RunBlockTool
 
 _TEST_USER_ID = "test-user-run-block-details"
 
@@ -61,12 +61,13 @@ async def test_run_block_returns_details_when_no_input_provided():
     )
 
     with patch(
-        "backend.copilot.tools.run_block.get_block",
+        "backend.api.features.chat.tools.run_block.get_block",
         return_value=http_block,
     ):
         # Mock credentials check to return no missing credentials
-        with patch(
-            "backend.copilot.tools.run_block.resolve_block_credentials",
+        with patch.object(
+            RunBlockTool,
+            "_resolve_block_credentials",
             new_callable=AsyncMock,
             return_value=({}, []),  # (matched_credentials, missing_credentials)
         ):
@@ -119,11 +120,12 @@ async def test_run_block_returns_details_when_only_credentials_provided():
     }
 
     with patch(
-        "backend.copilot.tools.run_block.get_block",
+        "backend.api.features.chat.tools.run_block.get_block",
         return_value=mock,
     ):
-        with patch(
-            "backend.copilot.tools.run_block.resolve_block_credentials",
+        with patch.object(
+            RunBlockTool,
+            "_resolve_block_credentials",
             new_callable=AsyncMock,
             return_value=(
                 {

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,
@@ -38,14 +39,13 @@ 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
@@ -119,7 +119,7 @@ def build_missing_credentials_from_graph(
     preserving all supported credential types for each field.
     """
     matched_keys = set(matched_credentials.keys()) if matched_credentials else set()
-    aggregated_fields = graph.aggregate_credentials_inputs()
+    aggregated_fields = graph.regular_credentials_inputs
 
     return {
         field_key: _serialize_missing_credential(field_key, field_info)
@@ -210,13 +210,13 @@ 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,
@@ -339,7 +339,7 @@ async def match_user_credentials_to_graph(
     missing_creds: list[str] = []
 
     # Get aggregated credentials requirements from the graph
-    aggregated_creds = graph.aggregate_credentials_inputs()
+    aggregated_creds = graph.regular_credentials_inputs
     logger.debug(
         f"Matching credentials for graph {graph.id}: {len(aggregated_creds)} required"
     )

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

@@ -0,0 +1,78 @@
+"""Tests for chat tools utility functions."""
+
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+
+from backend.data.model import CredentialsFieldInfo
+
+
+def _make_regular_field() -> CredentialsFieldInfo:
+    return CredentialsFieldInfo.model_validate(
+        {
+            "credentials_provider": ["github"],
+            "credentials_types": ["api_key"],
+            "is_auto_credential": False,
+        },
+        by_alias=True,
+    )
+
+
+def test_build_missing_credentials_excludes_auto_creds():
+    """
+    build_missing_credentials_from_graph() should use regular_credentials_inputs
+    and thus exclude auto_credentials from the "missing" set.
+    """
+    from backend.api.features.chat.tools.utils import (
+        build_missing_credentials_from_graph,
+    )
+
+    regular_field = _make_regular_field()
+
+    mock_graph = MagicMock()
+    # regular_credentials_inputs should only return the non-auto field
+    mock_graph.regular_credentials_inputs = {
+        "github_api_key": (regular_field, {("node-1", "credentials")}, True),
+    }
+
+    result = build_missing_credentials_from_graph(mock_graph, matched_credentials=None)
+
+    # Should include the regular credential
+    assert "github_api_key" in result
+    # Should NOT include the auto_credential (not in regular_credentials_inputs)
+    assert "google_oauth2" not in result
+
+
+@pytest.mark.asyncio
+async def test_match_user_credentials_excludes_auto_creds():
+    """
+    match_user_credentials_to_graph() should use regular_credentials_inputs
+    and thus exclude auto_credentials from matching.
+    """
+    from backend.api.features.chat.tools.utils import match_user_credentials_to_graph
+
+    regular_field = _make_regular_field()
+
+    mock_graph = MagicMock()
+    mock_graph.id = "test-graph"
+    # regular_credentials_inputs returns only non-auto fields
+    mock_graph.regular_credentials_inputs = {
+        "github_api_key": (regular_field, {("node-1", "credentials")}, True),
+    }
+
+    # Mock the credentials manager to return no credentials
+    with patch(
+        "backend.api.features.chat.tools.utils.IntegrationCredentialsManager"
+    ) as MockCredsMgr:
+        mock_store = AsyncMock()
+        mock_store.get_all_creds.return_value = []
+        MockCredsMgr.return_value.store = mock_store
+
+        matched, missing = await match_user_credentials_to_graph(
+            user_id="test-user", graph=mock_graph
+        )
+
+    # No credentials available, so github should be missing
+    assert len(matched) == 0
+    assert len(missing) == 1
+    assert "github_api_key" in missing[0]

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

@@ -6,12 +6,15 @@ from typing import Any
 import aiohttp
 import html2text
 
-from backend.copilot.model import ChatSession
+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 (
+    ErrorResponse,
+    ToolResponseBase,
+    WebFetchResponse,
+)
 from backend.util.request import Requests
 
-from .base import BaseTool
-from .models import ErrorResponse, ToolResponseBase, WebFetchResponse
-
 logger = logging.getLogger(__name__)
 
 # Limits
@@ -30,10 +33,6 @@ _TEXT_CONTENT_TYPES = {
     "application/xhtml+xml",
     "application/rss+xml",
     "application/atom+xml",
-    # RFC 7807 — JSON problem details; used by many REST APIs for error responses
-    "application/problem+json",
-    "application/problem+xml",
-    "application/ld+json",
 }
 
 

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

@@ -0,0 +1,626 @@
+"""CoPilot tools for workspace file operations."""
+
+import base64
+import logging
+from typing import Any, Optional
+
+from pydantic import BaseModel
+
+from backend.api.features.chat.model import ChatSession
+from backend.data.workspace import get_or_create_workspace
+from backend.util.settings import Config
+from backend.util.virus_scanner import scan_content_safe
+from backend.util.workspace import WorkspaceManager
+
+from .base import BaseTool
+from .models import ErrorResponse, ResponseType, ToolResponseBase
+
+logger = logging.getLogger(__name__)
+
+
+class WorkspaceFileInfoData(BaseModel):
+    """Data model for workspace file information (not a response itself)."""
+
+    file_id: str
+    name: str
+    path: str
+    mime_type: str
+    size_bytes: int
+
+
+class WorkspaceFileListResponse(ToolResponseBase):
+    """Response containing list of workspace files."""
+
+    type: ResponseType = ResponseType.WORKSPACE_FILE_LIST
+    files: list[WorkspaceFileInfoData]
+    total_count: int
+
+
+class WorkspaceFileContentResponse(ToolResponseBase):
+    """Response containing workspace file content (legacy, for small text files)."""
+
+    type: ResponseType = ResponseType.WORKSPACE_FILE_CONTENT
+    file_id: str
+    name: str
+    path: str
+    mime_type: str
+    content_base64: str
+
+
+class WorkspaceFileMetadataResponse(ToolResponseBase):
+    """Response containing workspace file metadata and download URL (prevents context bloat)."""
+
+    type: ResponseType = ResponseType.WORKSPACE_FILE_METADATA
+    file_id: str
+    name: str
+    path: str
+    mime_type: str
+    size_bytes: int
+    download_url: str
+    preview: str | None = None  # First 500 chars for text files
+
+
+class WorkspaceWriteResponse(ToolResponseBase):
+    """Response after writing a file to workspace."""
+
+    type: ResponseType = ResponseType.WORKSPACE_FILE_WRITTEN
+    file_id: str
+    name: str
+    path: str
+    size_bytes: int
+
+
+class WorkspaceDeleteResponse(ToolResponseBase):
+    """Response after deleting a file from workspace."""
+
+    type: ResponseType = ResponseType.WORKSPACE_FILE_DELETED
+    file_id: str
+    success: bool
+
+
+class ListWorkspaceFilesTool(BaseTool):
+    """Tool for listing files in user's workspace."""
+
+    @property
+    def name(self) -> str:
+        return "list_workspace_files"
+
+    @property
+    def description(self) -> str:
+        return (
+            "List files in the user's persistent workspace (cloud storage). "
+            "These files survive across sessions. "
+            "For ephemeral session files, use the SDK Read/Glob tools instead. "
+            "Returns file names, paths, sizes, and metadata. "
+            "Optionally filter by path prefix."
+        )
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "path_prefix": {
+                    "type": "string",
+                    "description": (
+                        "Optional path prefix to filter files "
+                        "(e.g., '/documents/' to list only files in documents folder). "
+                        "By default, only files from the current session are listed."
+                    ),
+                },
+                "limit": {
+                    "type": "integer",
+                    "description": "Maximum number of files to return (default 50, max 100)",
+                    "minimum": 1,
+                    "maximum": 100,
+                },
+                "include_all_sessions": {
+                    "type": "boolean",
+                    "description": (
+                        "If true, list files from all sessions. "
+                        "Default is false (only current session's files)."
+                    ),
+                },
+            },
+            "required": [],
+        }
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        session_id = session.session_id
+
+        if not user_id:
+            return ErrorResponse(
+                message="Authentication required",
+                session_id=session_id,
+            )
+
+        path_prefix: Optional[str] = kwargs.get("path_prefix")
+        limit = min(kwargs.get("limit", 50), 100)
+        include_all_sessions: bool = kwargs.get("include_all_sessions", False)
+
+        try:
+            workspace = await get_or_create_workspace(user_id)
+            # Pass session_id for session-scoped file access
+            manager = WorkspaceManager(user_id, workspace.id, session_id)
+
+            files = await manager.list_files(
+                path=path_prefix,
+                limit=limit,
+                include_all_sessions=include_all_sessions,
+            )
+            total = await manager.get_file_count(
+                path=path_prefix,
+                include_all_sessions=include_all_sessions,
+            )
+
+            file_infos = [
+                WorkspaceFileInfoData(
+                    file_id=f.id,
+                    name=f.name,
+                    path=f.path,
+                    mime_type=f.mimeType,
+                    size_bytes=f.sizeBytes,
+                )
+                for f in files
+            ]
+
+            scope_msg = "all sessions" if include_all_sessions else "current session"
+            return WorkspaceFileListResponse(
+                files=file_infos,
+                total_count=total,
+                message=f"Found {len(files)} files in workspace ({scope_msg})",
+                session_id=session_id,
+            )
+
+        except Exception as e:
+            logger.error(f"Error listing workspace files: {e}", exc_info=True)
+            return ErrorResponse(
+                message=f"Failed to list workspace files: {str(e)}",
+                error=str(e),
+                session_id=session_id,
+            )
+
+
+class ReadWorkspaceFileTool(BaseTool):
+    """Tool for reading file content from workspace."""
+
+    # Size threshold for returning full content vs metadata+URL
+    # Files larger than this return metadata with download URL to prevent context bloat
+    MAX_INLINE_SIZE_BYTES = 32 * 1024  # 32KB
+    # Preview size for text files
+    PREVIEW_SIZE = 500
+
+    @property
+    def name(self) -> str:
+        return "read_workspace_file"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Read a file from the user's persistent workspace (cloud storage). "
+            "These files survive across sessions. "
+            "For ephemeral session files, use the SDK Read tool instead. "
+            "Specify either file_id or path to identify the file. "
+            "For small text files, returns content directly. "
+            "For large or binary files, returns metadata and a download URL. "
+            "Paths are scoped to the current session by default. "
+            "Use /sessions/<session_id>/... for cross-session access."
+        )
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "file_id": {
+                    "type": "string",
+                    "description": "The file's unique ID (from list_workspace_files)",
+                },
+                "path": {
+                    "type": "string",
+                    "description": (
+                        "The virtual file path (e.g., '/documents/report.pdf'). "
+                        "Scoped to current session by default."
+                    ),
+                },
+                "force_download_url": {
+                    "type": "boolean",
+                    "description": (
+                        "If true, always return metadata+URL instead of inline content. "
+                        "Default is false (auto-selects based on file size/type)."
+                    ),
+                },
+            },
+            "required": [],  # At least one must be provided
+        }
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    def _is_text_mime_type(self, mime_type: str) -> bool:
+        """Check if the MIME type is a text-based type."""
+        text_types = [
+            "text/",
+            "application/json",
+            "application/xml",
+            "application/javascript",
+            "application/x-python",
+            "application/x-sh",
+        ]
+        return any(mime_type.startswith(t) for t in text_types)
+
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        session_id = session.session_id
+
+        if not user_id:
+            return ErrorResponse(
+                message="Authentication required",
+                session_id=session_id,
+            )
+
+        file_id: Optional[str] = kwargs.get("file_id")
+        path: Optional[str] = kwargs.get("path")
+        force_download_url: bool = kwargs.get("force_download_url", False)
+
+        if not file_id and not path:
+            return ErrorResponse(
+                message="Please provide either file_id or path",
+                session_id=session_id,
+            )
+
+        try:
+            workspace = await get_or_create_workspace(user_id)
+            # Pass session_id for session-scoped file access
+            manager = WorkspaceManager(user_id, workspace.id, session_id)
+
+            # Get file info
+            if file_id:
+                file_info = await manager.get_file_info(file_id)
+                if file_info is None:
+                    return ErrorResponse(
+                        message=f"File not found: {file_id}",
+                        session_id=session_id,
+                    )
+                target_file_id = file_id
+            else:
+                # path is guaranteed to be non-None here due to the check above
+                assert path is not None
+                file_info = await manager.get_file_info_by_path(path)
+                if file_info is None:
+                    return ErrorResponse(
+                        message=f"File not found at path: {path}",
+                        session_id=session_id,
+                    )
+                target_file_id = file_info.id
+
+            # Decide whether to return inline content or metadata+URL
+            is_small_file = file_info.sizeBytes <= self.MAX_INLINE_SIZE_BYTES
+            is_text_file = self._is_text_mime_type(file_info.mimeType)
+
+            # Return inline content for small text files (unless force_download_url)
+            if is_small_file and is_text_file and not force_download_url:
+                content = await manager.read_file_by_id(target_file_id)
+                content_b64 = base64.b64encode(content).decode("utf-8")
+
+                return WorkspaceFileContentResponse(
+                    file_id=file_info.id,
+                    name=file_info.name,
+                    path=file_info.path,
+                    mime_type=file_info.mimeType,
+                    content_base64=content_b64,
+                    message=f"Successfully read file: {file_info.name}",
+                    session_id=session_id,
+                )
+
+            # Return metadata + workspace:// reference for large or binary files
+            # This prevents context bloat (100KB file = ~133KB as base64)
+            # Use workspace:// format so frontend urlTransform can add proxy prefix
+            download_url = f"workspace://{target_file_id}"
+
+            # Generate preview for text files
+            preview: str | None = None
+            if is_text_file:
+                try:
+                    content = await manager.read_file_by_id(target_file_id)
+                    preview_text = content[: self.PREVIEW_SIZE].decode(
+                        "utf-8", errors="replace"
+                    )
+                    if len(content) > self.PREVIEW_SIZE:
+                        preview_text += "..."
+                    preview = preview_text
+                except Exception:
+                    pass  # Preview is optional
+
+            return WorkspaceFileMetadataResponse(
+                file_id=file_info.id,
+                name=file_info.name,
+                path=file_info.path,
+                mime_type=file_info.mimeType,
+                size_bytes=file_info.sizeBytes,
+                download_url=download_url,
+                preview=preview,
+                message=f"File: {file_info.name} ({file_info.sizeBytes} bytes). Use download_url to retrieve content.",
+                session_id=session_id,
+            )
+
+        except FileNotFoundError as e:
+            return ErrorResponse(
+                message=str(e),
+                session_id=session_id,
+            )
+        except Exception as e:
+            logger.error(f"Error reading workspace file: {e}", exc_info=True)
+            return ErrorResponse(
+                message=f"Failed to read workspace file: {str(e)}",
+                error=str(e),
+                session_id=session_id,
+            )
+
+
+class WriteWorkspaceFileTool(BaseTool):
+    """Tool for writing files to workspace."""
+
+    @property
+    def name(self) -> str:
+        return "write_workspace_file"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Write or create a file in the user's persistent workspace (cloud storage). "
+            "These files survive across sessions. "
+            "For ephemeral session files, use the SDK Write tool instead. "
+            "Provide the content as a base64-encoded string. "
+            f"Maximum file size is {Config().max_file_size_mb}MB. "
+            "Files are saved to the current session's folder by default. "
+            "Use /sessions/<session_id>/... for cross-session access."
+        )
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "filename": {
+                    "type": "string",
+                    "description": "Name for the file (e.g., 'report.pdf')",
+                },
+                "content_base64": {
+                    "type": "string",
+                    "description": "Base64-encoded file content",
+                },
+                "path": {
+                    "type": "string",
+                    "description": (
+                        "Optional virtual path where to save the file "
+                        "(e.g., '/documents/report.pdf'). "
+                        "Defaults to '/{filename}'. Scoped to current session."
+                    ),
+                },
+                "mime_type": {
+                    "type": "string",
+                    "description": (
+                        "Optional MIME type of the file. "
+                        "Auto-detected from filename if not provided."
+                    ),
+                },
+                "overwrite": {
+                    "type": "boolean",
+                    "description": "Whether to overwrite if file exists at path (default: false)",
+                },
+            },
+            "required": ["filename", "content_base64"],
+        }
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        session_id = session.session_id
+
+        if not user_id:
+            return ErrorResponse(
+                message="Authentication required",
+                session_id=session_id,
+            )
+
+        filename: str = kwargs.get("filename", "")
+        content_b64: str = kwargs.get("content_base64", "")
+        path: Optional[str] = kwargs.get("path")
+        mime_type: Optional[str] = kwargs.get("mime_type")
+        overwrite: bool = kwargs.get("overwrite", False)
+
+        if not filename:
+            return ErrorResponse(
+                message="Please provide a filename",
+                session_id=session_id,
+            )
+
+        if not content_b64:
+            return ErrorResponse(
+                message="Please provide content_base64",
+                session_id=session_id,
+            )
+
+        # Decode content
+        try:
+            content = base64.b64decode(content_b64)
+        except Exception:
+            return ErrorResponse(
+                message="Invalid base64-encoded content",
+                session_id=session_id,
+            )
+
+        # Check size
+        max_file_size = Config().max_file_size_mb * 1024 * 1024
+        if len(content) > max_file_size:
+            return ErrorResponse(
+                message=f"File too large. Maximum size is {Config().max_file_size_mb}MB",
+                session_id=session_id,
+            )
+
+        try:
+            # Virus scan
+            await scan_content_safe(content, filename=filename)
+
+            workspace = await get_or_create_workspace(user_id)
+            # Pass session_id for session-scoped file access
+            manager = WorkspaceManager(user_id, workspace.id, session_id)
+
+            file_record = await manager.write_file(
+                content=content,
+                filename=filename,
+                path=path,
+                mime_type=mime_type,
+                overwrite=overwrite,
+            )
+
+            return WorkspaceWriteResponse(
+                file_id=file_record.id,
+                name=file_record.name,
+                path=file_record.path,
+                size_bytes=file_record.sizeBytes,
+                message=f"Successfully wrote file: {file_record.name}",
+                session_id=session_id,
+            )
+
+        except ValueError as e:
+            return ErrorResponse(
+                message=str(e),
+                session_id=session_id,
+            )
+        except Exception as e:
+            logger.error(f"Error writing workspace file: {e}", exc_info=True)
+            return ErrorResponse(
+                message=f"Failed to write workspace file: {str(e)}",
+                error=str(e),
+                session_id=session_id,
+            )
+
+
+class DeleteWorkspaceFileTool(BaseTool):
+    """Tool for deleting files from workspace."""
+
+    @property
+    def name(self) -> str:
+        return "delete_workspace_file"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Delete a file from the user's persistent workspace (cloud storage). "
+            "Specify either file_id or path to identify the file. "
+            "Paths are scoped to the current session by default. "
+            "Use /sessions/<session_id>/... for cross-session access."
+        )
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "file_id": {
+                    "type": "string",
+                    "description": "The file's unique ID (from list_workspace_files)",
+                },
+                "path": {
+                    "type": "string",
+                    "description": (
+                        "The virtual file path (e.g., '/documents/report.pdf'). "
+                        "Scoped to current session by default."
+                    ),
+                },
+            },
+            "required": [],  # At least one must be provided
+        }
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        session_id = session.session_id
+
+        if not user_id:
+            return ErrorResponse(
+                message="Authentication required",
+                session_id=session_id,
+            )
+
+        file_id: Optional[str] = kwargs.get("file_id")
+        path: Optional[str] = kwargs.get("path")
+
+        if not file_id and not path:
+            return ErrorResponse(
+                message="Please provide either file_id or path",
+                session_id=session_id,
+            )
+
+        try:
+            workspace = await get_or_create_workspace(user_id)
+            # Pass session_id for session-scoped file access
+            manager = WorkspaceManager(user_id, workspace.id, session_id)
+
+            # Determine the file_id to delete
+            target_file_id: str
+            if file_id:
+                target_file_id = file_id
+            else:
+                # path is guaranteed to be non-None here due to the check above
+                assert path is not None
+                file_info = await manager.get_file_info_by_path(path)
+                if file_info is None:
+                    return ErrorResponse(
+                        message=f"File not found at path: {path}",
+                        session_id=session_id,
+                    )
+                target_file_id = file_info.id
+
+            success = await manager.delete_file(target_file_id)
+
+            if not success:
+                return ErrorResponse(
+                    message=f"File not found: {target_file_id}",
+                    session_id=session_id,
+                )
+
+            return WorkspaceDeleteResponse(
+                file_id=target_file_id,
+                success=True,
+                message="File deleted successfully",
+                session_id=session_id,
+            )
+
+        except Exception as e:
+            logger.error(f"Error deleting workspace file: {e}", exc_info=True)
+            return ErrorResponse(
+                message=f"Failed to delete workspace file: {str(e)}",
+                error=str(e),
+                session_id=session_id,
+            )

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

@@ -638,7 +638,7 @@ async def test_process_review_action_auto_approve_creates_auto_approval_records(
 
     # Mock get_node_executions to return node_id mapping
     mock_get_node_executions = mocker.patch(
-        "backend.api.features.executions.review.routes.get_node_executions"
+        "backend.data.execution.get_node_executions"
     )
     mock_node_exec = mocker.Mock(spec=NodeExecutionResult)
     mock_node_exec.node_exec_id = "test_node_123"
@@ -936,7 +936,7 @@ async def test_process_review_action_auto_approve_only_applies_to_approved_revie
 
     # Mock get_node_executions to return node_id mapping
     mock_get_node_executions = mocker.patch(
-        "backend.api.features.executions.review.routes.get_node_executions"
+        "backend.data.execution.get_node_executions"
     )
     mock_node_exec = mocker.Mock(spec=NodeExecutionResult)
     mock_node_exec.node_exec_id = "node_exec_approved"
@@ -1148,7 +1148,7 @@ async def test_process_review_action_per_review_auto_approve_granularity(
 
     # Mock get_node_executions to return batch node data
     mock_get_node_executions = mocker.patch(
-        "backend.api.features.executions.review.routes.get_node_executions"
+        "backend.data.execution.get_node_executions"
     )
     # Create mock node executions for each review
     mock_node_execs = []

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

@@ -6,15 +6,10 @@ import autogpt_libs.auth as autogpt_auth_lib
 from fastapi import APIRouter, HTTPException, Query, Security, status
 from prisma.enums import ReviewStatus
 
-from backend.copilot.constants import (
-    is_copilot_synthetic_id,
-    parse_node_id_from_exec_id,
-)
 from backend.data.execution import (
     ExecutionContext,
     ExecutionStatus,
     get_graph_execution_meta,
-    get_node_executions,
 )
 from backend.data.graph import get_graph_settings
 from backend.data.human_review import (
@@ -27,7 +22,6 @@ from backend.data.human_review import (
 )
 from backend.data.model import USER_TIMEZONE_NOT_SET
 from backend.data.user import get_user_by_id
-from backend.data.workspace import get_or_create_workspace
 from backend.executor.utils import add_graph_execution
 
 from .model import PendingHumanReviewModel, ReviewRequest, ReviewResponse
@@ -41,38 +35,6 @@ router = APIRouter(
 )
 
 
-async def _resolve_node_ids(
-    node_exec_ids: list[str],
-    graph_exec_id: str,
-    is_copilot: bool,
-) -> dict[str, str]:
-    """Resolve node_exec_id -> node_id for auto-approval records.
-
-    CoPilot synthetic IDs encode node_id in the format "{node_id}:{random}".
-    Graph executions look up node_id from NodeExecution records.
-    """
-    if not node_exec_ids:
-        return {}
-
-    if is_copilot:
-        return {neid: parse_node_id_from_exec_id(neid) for neid in node_exec_ids}
-
-    node_execs = await get_node_executions(
-        graph_exec_id=graph_exec_id, include_exec_data=False
-    )
-    node_exec_map = {ne.node_exec_id: ne.node_id for ne in node_execs}
-
-    result = {}
-    for neid in node_exec_ids:
-        if neid in node_exec_map:
-            result[neid] = node_exec_map[neid]
-        else:
-            logger.error(
-                f"Failed to resolve node_id for {neid}: Node execution not found."
-            )
-    return result
-
-
 @router.get(
     "/pending",
     summary="Get Pending Reviews",
@@ -147,16 +109,14 @@ async def list_pending_reviews_for_execution(
     """
 
     # Verify user owns the graph execution before returning reviews
-    # (CoPilot synthetic IDs don't have graph execution records)
-    if not is_copilot_synthetic_id(graph_exec_id):
-        graph_exec = await get_graph_execution_meta(
-            user_id=user_id, execution_id=graph_exec_id
+    graph_exec = await get_graph_execution_meta(
+        user_id=user_id, execution_id=graph_exec_id
+    )
+    if not graph_exec:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=f"Graph execution #{graph_exec_id} not found",
         )
-        if not graph_exec:
-            raise HTTPException(
-                status_code=status.HTTP_404_NOT_FOUND,
-                detail=f"Graph execution #{graph_exec_id} not found",
-            )
 
     return await get_pending_reviews_for_execution(graph_exec_id, user_id)
 
@@ -199,26 +159,30 @@ async def process_review_action(
         )
 
     graph_exec_id = next(iter(graph_exec_ids))
-    is_copilot = is_copilot_synthetic_id(graph_exec_id)
 
-    # Validate execution status for graph executions (skip for CoPilot synthetic IDs)
-    if not is_copilot:
-        graph_exec_meta = await get_graph_execution_meta(
-            user_id=user_id, execution_id=graph_exec_id
+    # Validate execution status before processing reviews
+    graph_exec_meta = await get_graph_execution_meta(
+        user_id=user_id, execution_id=graph_exec_id
+    )
+
+    if not graph_exec_meta:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=f"Graph execution #{graph_exec_id} not found",
+        )
+
+    # Only allow processing reviews if execution is paused for review
+    # or incomplete (partial execution with some reviews already processed)
+    if graph_exec_meta.status not in (
+        ExecutionStatus.REVIEW,
+        ExecutionStatus.INCOMPLETE,
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_409_CONFLICT,
+            detail=f"Cannot process reviews while execution status is {graph_exec_meta.status}. "
+            f"Reviews can only be processed when execution is paused (REVIEW status). "
+            f"Current status: {graph_exec_meta.status}",
         )
-        if not graph_exec_meta:
-            raise HTTPException(
-                status_code=status.HTTP_404_NOT_FOUND,
-                detail=f"Graph execution #{graph_exec_id} not found",
-            )
-        if graph_exec_meta.status not in (
-            ExecutionStatus.REVIEW,
-            ExecutionStatus.INCOMPLETE,
-        ):
-            raise HTTPException(
-                status_code=status.HTTP_409_CONFLICT,
-                detail=f"Cannot process reviews while execution status is {graph_exec_meta.status}",
-            )
 
     # Build review decisions map and track which reviews requested auto-approval
     # Auto-approved reviews use original data (no modifications allowed)
@@ -271,7 +235,7 @@ async def process_review_action(
             )
             return (node_id, False)
 
-    # Collect node_exec_ids that need auto-approval and resolve their node_ids
+    # Collect node_exec_ids that need auto-approval
     node_exec_ids_needing_auto_approval = [
         node_exec_id
         for node_exec_id, review_result in updated_reviews.items()
@@ -279,16 +243,29 @@ async def process_review_action(
         and auto_approve_requests.get(node_exec_id, False)
     ]
 
-    node_id_map = await _resolve_node_ids(
-        node_exec_ids_needing_auto_approval, graph_exec_id, is_copilot
-    )
-
-    # Deduplicate by node_id — one auto-approval per node
+    # Batch-fetch node executions to get node_ids
     nodes_needing_auto_approval: dict[str, Any] = {}
-    for node_exec_id in node_exec_ids_needing_auto_approval:
-        node_id = node_id_map.get(node_exec_id)
-        if node_id and node_id not in nodes_needing_auto_approval:
-            nodes_needing_auto_approval[node_id] = updated_reviews[node_exec_id]
+    if node_exec_ids_needing_auto_approval:
+        from backend.data.execution import get_node_executions
+
+        node_execs = await get_node_executions(
+            graph_exec_id=graph_exec_id, include_exec_data=False
+        )
+        node_exec_map = {node_exec.node_exec_id: node_exec for node_exec in node_execs}
+
+        for node_exec_id in node_exec_ids_needing_auto_approval:
+            node_exec = node_exec_map.get(node_exec_id)
+            if node_exec:
+                review_result = updated_reviews[node_exec_id]
+                # Use the first approved review for this node (deduplicate by node_id)
+                if node_exec.node_id not in nodes_needing_auto_approval:
+                    nodes_needing_auto_approval[node_exec.node_id] = review_result
+            else:
+                logger.error(
+                    f"Failed to create auto-approval record for {node_exec_id}: "
+                    f"Node execution not found. This may indicate a race condition "
+                    f"or data inconsistency."
+                )
 
     # Execute all auto-approval creations in parallel (deduplicated by node_id)
     auto_approval_results = await asyncio.gather(
@@ -303,11 +280,13 @@ async def process_review_action(
     auto_approval_failed_count = 0
     for result in auto_approval_results:
         if isinstance(result, Exception):
+            # Unexpected exception during auto-approval creation
             auto_approval_failed_count += 1
             logger.error(
                 f"Unexpected exception during auto-approval creation: {result}"
             )
         elif isinstance(result, tuple) and len(result) == 2 and not result[1]:
+            # Auto-approval creation failed (returned False)
             auto_approval_failed_count += 1
 
     # Count results
@@ -322,31 +301,30 @@ async def process_review_action(
         if review.status == ReviewStatus.REJECTED
     )
 
-    # Resume graph execution only for real graph executions (not CoPilot)
-    # CoPilot sessions are resumed by the LLM retrying run_block with review_id
-    if not is_copilot and updated_reviews:
+    # Resume execution only if ALL pending reviews for this execution have been processed
+    if updated_reviews:
         still_has_pending = await has_pending_reviews_for_graph_exec(graph_exec_id)
 
         if not still_has_pending:
+            # Get the graph_id from any processed review
             first_review = next(iter(updated_reviews.values()))
 
             try:
+                # Fetch user and settings to build complete execution context
                 user = await get_user_by_id(user_id)
                 settings = await get_graph_settings(
                     user_id=user_id, graph_id=first_review.graph_id
                 )
 
+                # Preserve user's timezone preference when resuming execution
                 user_timezone = (
                     user.timezone if user.timezone != USER_TIMEZONE_NOT_SET else "UTC"
                 )
 
-                workspace = await get_or_create_workspace(user_id)
-
                 execution_context = ExecutionContext(
                     human_in_the_loop_safe_mode=settings.human_in_the_loop_safe_mode,
                     sensitive_action_safe_mode=settings.sensitive_action_safe_mode,
                     user_timezone=user_timezone,
-                    workspace_id=workspace.id,
                 )
 
                 await add_graph_execution(