updates

Auth API and other server-side routes were using NEXT_PUBLIC_AGPT_SERVER_URL
directly, which resolves to localhost:8006. When running in Docker, the
frontend container needs to reach the backend via the container name
(rest_server:8006) instead of localhost.

Updated all server-side auth routes to use environment.getAGPTServerApiUrl()
or environment.getAGPTServerBaseUrl() which correctly handle the Docker
environment by using AGPT_SERVER_URL when running server-side.

Files updated:
- src/lib/auth/api.ts
- src/app/api/auth/callback/reset-password/route.ts
- src/app/api/auth/user/route.ts
- src/app/(platform)/auth/callback/route.ts
- src/app/(platform)/auth/confirm/route.ts
- src/app/(platform)/profile/(user)/settings/.../actions.ts
- src/app/(platform)/reset-password/actions.ts

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

.branchlet.json

@@ -1,37 +0,0 @@
-{
-  "worktreeCopyPatterns": [
-    ".env*",
-    ".vscode/**",
-    ".auth/**",
-    ".claude/**",
-    "autogpt_platform/.env*",
-    "autogpt_platform/backend/.env*",
-    "autogpt_platform/frontend/.env*",
-    "autogpt_platform/frontend/.auth/**",
-    "autogpt_platform/db/docker/.env*"
-  ],
-  "worktreeCopyIgnores": [
-    "**/node_modules/**",
-    "**/dist/**",
-    "**/.git/**",
-    "**/Thumbs.db",
-    "**/.DS_Store",
-    "**/.next/**",
-    "**/__pycache__/**",
-    "**/.ruff_cache/**",
-    "**/.pytest_cache/**",
-    "**/*.pyc",
-    "**/playwright-report/**",
-    "**/logs/**",
-    "**/site/**"
-  ],
-  "worktreePathTemplate": "$BASE_PATH.worktree",
-  "postCreateCmd": [
-    "cd autogpt_platform/autogpt_libs && poetry install",
-    "cd autogpt_platform/backend && poetry install && poetry run prisma generate",
-    "cd autogpt_platform/frontend && pnpm install",
-    "cd docs && pip install -r requirements.txt"
-  ],
-  "terminalCommand": "code .",
-  "deleteBranchWithWorktree": false
-}

.dockerignore

@@ -1,9 +1,6 @@
 # Ignore everything by default, selectively add things to context
 *
 
-# Documentation (for embeddings/search)
-!docs/
-
 # Platform - Libs
 !autogpt_platform/autogpt_libs/autogpt_libs/
 !autogpt_platform/autogpt_libs/pyproject.toml
@@ -19,7 +16,6 @@
 !autogpt_platform/backend/poetry.lock
 !autogpt_platform/backend/README.md
 !autogpt_platform/backend/.env
-!autogpt_platform/backend/gen_prisma_types_stub.py
 
 # Platform - Market
 !autogpt_platform/market/market/

.github/copilot-instructions.md

@@ -142,7 +142,7 @@ pnpm storybook                      # Start component development server
 ### Security & Middleware
 
 **Cache Protection**: Backend includes middleware preventing sensitive data caching in browsers/proxies
-**Authentication**: JWT-based with Supabase integration
+**Authentication**: JWT-based with native authentication
 **User ID Validation**: All data access requires user ID checks - verify this for any `data/*.py` changes
 
 ### Development Workflow
@@ -168,9 +168,9 @@ pnpm storybook                      # Start component development server
 
 - `frontend/src/app/layout.tsx` - Root application layout
 - `frontend/src/app/page.tsx` - Home page
-- `frontend/src/lib/supabase/` - Authentication and database client
+- `frontend/src/lib/auth/` - Authentication client
 
-**Protected Routes**: Update `frontend/lib/supabase/middleware.ts` when adding protected routes
+**Protected Routes**: Update `frontend/middleware.ts` when adding protected routes
 
 ### Agent Block System
 
@@ -194,7 +194,7 @@ Agents are built using a visual block-based system where each block performs a s
 
 1. **Backend**: `/backend/.env.default` → `/backend/.env` (user overrides)
 2. **Frontend**: `/frontend/.env.default` → `/frontend/.env` (user overrides)
-3. **Platform**: `/.env.default` (Supabase/shared) → `/.env` (user overrides)
+3. **Platform**: `/.env.default` (shared) → `/.env` (user overrides)
 4. Docker Compose `environment:` sections override file-based config
 5. Shell environment variables have highest precedence
 

.github/workflows/claude-dependabot.yml

@@ -74,7 +74,7 @@ jobs:
 
       - name: Generate Prisma Client
         working-directory: autogpt_platform/backend
-        run: poetry run prisma generate && poetry run gen-prisma-stub
+        run: poetry run prisma generate
 
       # Frontend Node.js/pnpm setup (mirrors platform-frontend-ci.yml)
       - name: Set up Node.js
@@ -144,11 +144,7 @@ jobs:
             "rabbitmq:management"
             "clamav/clamav-debian:latest"
             "busybox:latest"
-            "kong:2.8.1"
-            "supabase/gotrue:v2.170.0"
-            "supabase/postgres:15.8.1.049"
-            "supabase/postgres-meta:v0.86.1"
-            "supabase/studio:20250224-d10db0f"
+            "pgvector/pgvector:pg18"
           )
           
           # Check if any cached tar files exist (more reliable than cache-hit)

.github/workflows/claude.yml

@@ -90,7 +90,7 @@ jobs:
 
       - name: Generate Prisma Client
         working-directory: autogpt_platform/backend
-        run: poetry run prisma generate && poetry run gen-prisma-stub
+        run: poetry run prisma generate
 
       # Frontend Node.js/pnpm setup (mirrors platform-frontend-ci.yml)
       - name: Set up Node.js
@@ -160,11 +160,7 @@ jobs:
             "rabbitmq:management"
             "clamav/clamav-debian:latest"
             "busybox:latest"
-            "kong:2.8.1"
-            "supabase/gotrue:v2.170.0"
-            "supabase/postgres:15.8.1.049"
-            "supabase/postgres-meta:v0.86.1"
-            "supabase/studio:20250224-d10db0f"
+            "pgvector/pgvector:pg18"
           )
           
           # Check if any cached tar files exist (more reliable than cache-hit)

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

@@ -72,7 +72,7 @@ jobs:
 
       - name: Generate Prisma Client
         working-directory: autogpt_platform/backend
-        run: poetry run prisma generate && poetry run gen-prisma-stub
+        run: poetry run prisma generate
 
       # Frontend Node.js/pnpm setup (mirrors platform-frontend-ci.yml)
       - name: Set up Node.js
@@ -108,16 +108,6 @@ jobs:
       #   run: pnpm playwright install --with-deps chromium
 
       # Docker setup for development environment
-      - name: Free up disk space
-        run: |
-          # Remove large unused tools to free disk space for Docker builds
-          sudo rm -rf /usr/share/dotnet
-          sudo rm -rf /usr/local/lib/android
-          sudo rm -rf /opt/ghc
-          sudo rm -rf /opt/hostedtoolcache/CodeQL
-          sudo docker system prune -af
-          df -h
-
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
@@ -152,11 +142,7 @@ jobs:
             "rabbitmq:management"
             "clamav/clamav-debian:latest"
             "busybox:latest"
-            "kong:2.8.1"
-            "supabase/gotrue:v2.170.0"
-            "supabase/postgres:15.8.1.049"
-            "supabase/postgres-meta:v0.86.1"
-            "supabase/studio:20250224-d10db0f"
+            "pgvector/pgvector:pg18"
           )
           
           # Check if any cached tar files exist (more reliable than cache-hit)

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

@@ -2,13 +2,13 @@ name: AutoGPT Platform - Backend CI
 
 on:
   push:
-    branches: [master, dev, ci-test*]
+    branches: [master, dev, ci-test*, native-auth]
     paths:
       - ".github/workflows/platform-backend-ci.yml"
       - "autogpt_platform/backend/**"
       - "autogpt_platform/autogpt_libs/**"
   pull_request:
-    branches: [master, dev, release-*]
+    branches: [master, dev, release-*, native-auth]
     paths:
       - ".github/workflows/platform-backend-ci.yml"
       - "autogpt_platform/backend/**"
@@ -36,6 +36,19 @@ jobs:
     runs-on: ubuntu-latest
 
     services:
+      postgres:
+        image: pgvector/pgvector:pg18
+        ports:
+          - 5432:5432
+        env:
+          POSTGRES_USER: postgres
+          POSTGRES_PASSWORD: your-super-secret-and-long-postgres-password
+          POSTGRES_DB: postgres
+        options: >-
+          --health-cmd "pg_isready -U postgres"
+          --health-interval 5s
+          --health-timeout 5s
+          --health-retries 10
       redis:
         image: redis:latest
         ports:
@@ -78,11 +91,6 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
 
-      - name: Setup Supabase
-        uses: supabase/setup-cli@v1
-        with:
-          version: 1.178.1
-
       - id: get_date
         name: Get date
         run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
@@ -134,17 +142,7 @@ jobs:
         run: poetry install
 
       - name: Generate Prisma Client
-        run: poetry run prisma generate && poetry run gen-prisma-stub
-
-      - id: supabase
-        name: Start Supabase
-        working-directory: .
-        run: |
-          supabase init
-          supabase start --exclude postgres-meta,realtime,storage-api,imgproxy,inbucket,studio,edge-runtime,logflare,vector,supavisor
-          supabase status -o env | sed 's/="/=/; s/"$//' >> $GITHUB_OUTPUT
-        # outputs:
-        # DB_URL, API_URL, GRAPHQL_URL, ANON_KEY, SERVICE_ROLE_KEY, JWT_SECRET
+        run: poetry run prisma generate
 
       - name: Wait for ClamAV to be ready
         run: |
@@ -176,10 +174,10 @@ jobs:
           }
 
       - name: Run Database Migrations
-        run: poetry run prisma migrate deploy
+        run: poetry run prisma migrate dev --name updates
         env:
-          DATABASE_URL: ${{ steps.supabase.outputs.DB_URL }}
-          DIRECT_URL: ${{ steps.supabase.outputs.DB_URL }}
+          DATABASE_URL: postgresql://postgres:your-super-secret-and-long-postgres-password@localhost:5432/postgres
+          DIRECT_URL: postgresql://postgres:your-super-secret-and-long-postgres-password@localhost:5432/postgres
 
       - id: lint
         name: Run Linter
@@ -195,11 +193,9 @@ jobs:
         if: success() || (failure() && steps.lint.outcome == 'failure')
         env:
           LOG_LEVEL: ${{ runner.debug && 'DEBUG' || 'INFO' }}
-          DATABASE_URL: ${{ steps.supabase.outputs.DB_URL }}
-          DIRECT_URL: ${{ steps.supabase.outputs.DB_URL }}
-          SUPABASE_URL: ${{ steps.supabase.outputs.API_URL }}
-          SUPABASE_SERVICE_ROLE_KEY: ${{ steps.supabase.outputs.SERVICE_ROLE_KEY }}
-          JWT_VERIFY_KEY: ${{ steps.supabase.outputs.JWT_SECRET }}
+          DATABASE_URL: postgresql://postgres:your-super-secret-and-long-postgres-password@localhost:5432/postgres
+          DIRECT_URL: postgresql://postgres:your-super-secret-and-long-postgres-password@localhost:5432/postgres
+          JWT_SECRET: your-super-secret-jwt-token-with-at-least-32-characters-long
           REDIS_HOST: "localhost"
           REDIS_PORT: "6379"
           ENCRYPTION_KEY: "dvziYgz0KSK8FENhju0ZYi8-fRTfAdlz6YLhdB_jhNw=" # DO NOT USE IN PRODUCTION!!

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

@@ -2,16 +2,16 @@ name: AutoGPT Platform - Frontend CI
 
 on:
   push:
-    branches: [master, dev]
+    branches: [master, dev, native-auth]
     paths:
       - ".github/workflows/platform-frontend-ci.yml"
       - "autogpt_platform/frontend/**"
   pull_request:
+    branches: [master, dev, native-auth]
     paths:
       - ".github/workflows/platform-frontend-ci.yml"
       - "autogpt_platform/frontend/**"
   merge_group:
-  workflow_dispatch:
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event_name == 'merge_group' && format('merge-queue-{0}', github.ref) || format('{0}-{1}', github.ref, github.event.pull_request.number || github.sha) }}
@@ -148,18 +148,10 @@ jobs:
       - name: Enable corepack
         run: corepack enable
 
-      - name: Copy default supabase .env
+      - name: Copy default platform .env
         run: |
           cp ../.env.default ../.env
 
-      - name: Copy backend .env and set OpenAI API key
-        run: |
-          cp ../backend/.env.default ../backend/.env
-          echo "OPENAI_INTERNAL_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> ../backend/.env
-        env:
-          # Used by E2E test data script to generate embeddings for approved store agents
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
@@ -235,25 +227,13 @@ jobs:
 
       - name: Run Playwright tests
         run: pnpm test:no-build
-        continue-on-error: false
 
-      - name: Upload Playwright report
-        if: always()
+      - name: Upload Playwright artifacts
+        if: failure()
         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()

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

@@ -1,12 +1,13 @@
-name: AutoGPT Platform - Frontend CI
+name: AutoGPT Platform - Fullstack CI
 
 on:
   push:
-    branches: [master, dev]
+    branches: [master, dev, native-auth]
     paths:
       - ".github/workflows/platform-fullstack-ci.yml"
       - "autogpt_platform/**"
   pull_request:
+    branches: [master, dev, native-auth]
     paths:
       - ".github/workflows/platform-fullstack-ci.yml"
       - "autogpt_platform/**"
@@ -58,14 +59,11 @@ jobs:
   types:
     runs-on: ubuntu-latest
     needs: setup
-    strategy:
-      fail-fast: false
+    timeout-minutes: 10
 
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
-        with:
-          submodules: recursive
 
       - name: Set up Node.js
         uses: actions/setup-node@v4
@@ -75,18 +73,6 @@ jobs:
       - 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 --profile deps_backend up -d
-
       - name: Restore dependencies cache
         uses: actions/cache@v4
         with:
@@ -101,36 +87,12 @@ jobs:
       - 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 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 "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
+        run: pnpm generate:api
 
       - name: Run Typescript checks
         run: pnpm types
+
+    env:
+      CI: true
+      PLAIN_OUTPUT: True

AGENTS.md

@@ -49,5 +49,5 @@ Use conventional commit messages for all commits (e.g. `feat(backend): add API`)
 - Keep out-of-scope changes under 20% of the PR.
 - Ensure PR descriptions are complete.
 - For changes touching `data/*.py`, validate user ID checks or explain why not needed.
-- If adding protected frontend routes, update `frontend/lib/supabase/middleware.ts`.
+- If adding protected frontend routes, update `frontend/lib/auth/helpers.ts`.
 - Use the linear ticket branch structure if given codex/open-1668-resume-dropped-runs

autogpt_platform/.env.default

@@ -5,12 +5,6 @@
 
 POSTGRES_PASSWORD=your-super-secret-and-long-postgres-password
 JWT_SECRET=your-super-secret-jwt-token-with-at-least-32-characters-long
-ANON_KEY=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyAgCiAgICAicm9sZSI6ICJhbm9uIiwKICAgICJpc3MiOiAic3VwYWJhc2UtZGVtbyIsCiAgICAiaWF0IjogMTY0MTc2OTIwMCwKICAgICJleHAiOiAxNzk5NTM1NjAwCn0.dc_X5iR_VP_qT0zsiyj_I_OZ2T9FtRU2BBNWN8Bu4GE
-SERVICE_ROLE_KEY=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyAgCiAgICAicm9sZSI6ICJzZXJ2aWNlX3JvbGUiLAogICAgImlzcyI6ICJzdXBhYmFzZS1kZW1vIiwKICAgICJpYXQiOiAxNjQxNzY5MjAwLAogICAgImV4cCI6IDE3OTk1MzU2MDAKfQ.DaYlNEoUrrEn2Ig7tqibS-PHK5vgusbcbo7X36XVt4Q
-DASHBOARD_USERNAME=supabase
-DASHBOARD_PASSWORD=this_password_is_insecure_and_should_be_updated
-SECRET_KEY_BASE=UpNVntn3cDxHJpq99YMc1T1AQgQpc8kfYTuRgBiYa15BLrx8etQoXz3gZv1/u2oq
-VAULT_ENC_KEY=your-encryption-key-32-chars-min
 
 
 ############
@@ -24,100 +18,31 @@ POSTGRES_PORT=5432
 
 
 ############
-# Supavisor -- Database pooler
-############
-POOLER_PROXY_PORT_TRANSACTION=6543
-POOLER_DEFAULT_POOL_SIZE=20
-POOLER_MAX_CLIENT_CONN=100
-POOLER_TENANT_ID=your-tenant-id
-
-
-############
-# API Proxy - Configuration for the Kong Reverse proxy.
+# Auth - Native authentication configuration
 ############
 
-KONG_HTTP_PORT=8000
-KONG_HTTPS_PORT=8443
-
-
-############
-# API - Configuration for PostgREST.
-############
-
-PGRST_DB_SCHEMAS=public,storage,graphql_public
-
-
-############
-# Auth - Configuration for the GoTrue authentication server.
-############
-
-## General
 SITE_URL=http://localhost:3000
-ADDITIONAL_REDIRECT_URLS=
-JWT_EXPIRY=3600
-DISABLE_SIGNUP=false
-API_EXTERNAL_URL=http://localhost:8000
 
-## Mailer Config
-MAILER_URLPATHS_CONFIRMATION="/auth/v1/verify"
-MAILER_URLPATHS_INVITE="/auth/v1/verify"
-MAILER_URLPATHS_RECOVERY="/auth/v1/verify"
-MAILER_URLPATHS_EMAIL_CHANGE="/auth/v1/verify"
+# JWT token configuration
+ACCESS_TOKEN_EXPIRE_MINUTES=15
+REFRESH_TOKEN_EXPIRE_DAYS=7
+JWT_ISSUER=autogpt-platform
 
-## Email auth
-ENABLE_EMAIL_SIGNUP=true
-ENABLE_EMAIL_AUTOCONFIRM=false
-SMTP_ADMIN_EMAIL=admin@example.com
-SMTP_HOST=supabase-mail
-SMTP_PORT=2500
-SMTP_USER=fake_mail_user
-SMTP_PASS=fake_mail_password
-SMTP_SENDER_NAME=fake_sender
-ENABLE_ANONYMOUS_USERS=false
-
-## Phone auth
-ENABLE_PHONE_SIGNUP=true
-ENABLE_PHONE_AUTOCONFIRM=true
+# Google OAuth (optional)
+GOOGLE_CLIENT_ID=
+GOOGLE_CLIENT_SECRET=
 
 
 ############
-# Studio - Configuration for the Dashboard
+# Email configuration (optional)
 ############
 
-STUDIO_DEFAULT_ORGANIZATION=Default Organization
-STUDIO_DEFAULT_PROJECT=Default Project
+SMTP_HOST=
+SMTP_PORT=587
+SMTP_USER=
+SMTP_PASS=
+SMTP_FROM_EMAIL=noreply@example.com
 
-STUDIO_PORT=3000
-# replace if you intend to use Studio outside of localhost
-SUPABASE_PUBLIC_URL=http://localhost:8000
-
-# Enable webp support
-IMGPROXY_ENABLE_WEBP_DETECTION=true
-
-# Add your OpenAI API key to enable SQL Editor Assistant
-OPENAI_API_KEY=
-
-
-############
-# Functions - Configuration for Functions
-############
-# NOTE: VERIFY_JWT applies to all functions. Per-function VERIFY_JWT is not supported yet.
-FUNCTIONS_VERIFY_JWT=false
-
-
-############
-# Logs - Configuration for Logflare
-# Please refer to https://supabase.com/docs/reference/self-hosting-analytics/introduction
-############
-
-LOGFLARE_LOGGER_BACKEND_API_KEY=your-super-secret-and-long-logflare-key
-
-# Change vector.toml sinks to reflect this change
-LOGFLARE_API_KEY=your-super-secret-and-long-logflare-key
 
 # Docker socket location - this value will differ depending on your OS
 DOCKER_SOCKET_LOCATION=/var/run/docker.sock
-
-# Google Cloud Project details
-GOOGLE_PROJECT_ID=GOOGLE_PROJECT_ID
-GOOGLE_PROJECT_NUMBER=GOOGLE_PROJECT_NUMBER

autogpt_platform/Makefile

@@ -1,19 +1,17 @@
 .PHONY: start-core stop-core logs-core format lint migrate run-backend run-frontend load-store-agents
 
-# Run just Supabase + Redis + RabbitMQ
+# Run just PostgreSQL + Redis + RabbitMQ + ClamAV
 start-core:
 	docker compose up -d deps
 
 # Stop core services
 stop-core:
-	docker compose stop 
+	docker compose stop deps
 
 reset-db:
-	docker compose stop db
 	rm -rf db/docker/volumes/db/data
 	cd backend && poetry run prisma migrate deploy
 	cd backend && poetry run prisma generate
-	cd backend && poetry run gen-prisma-stub
 	
 # View logs for core services
 logs-core:
@@ -35,7 +33,6 @@ init-env:
 migrate:
 	cd backend && poetry run prisma migrate deploy
 	cd backend && poetry run prisma generate
-	cd backend && poetry run gen-prisma-stub
 
 run-backend:
 	cd backend && poetry run app
@@ -52,7 +49,7 @@ load-store-agents:
 help:
 	@echo "Usage: make <target>"
 	@echo "Targets:"
-	@echo "  start-core - Start just the core services (Supabase, Redis, RabbitMQ) in background"
+	@echo "  start-core - Start just the core services (PostgreSQL, Redis, RabbitMQ, ClamAV) in background"
 	@echo "  stop-core - Stop the core services"
 	@echo "  reset-db - Reset the database by deleting the volume"
 	@echo "  logs-core - Tail the logs for core services"
@@ -61,4 +58,4 @@ help:
 	@echo "  run-backend - Run the backend FastAPI server"
 	@echo "  run-frontend - Run the frontend Next.js development server"
 	@echo "  test-data - Run the test data creator"
-	@echo "  load-store-agents - Load store agents from agents/ folder into test database"
+	@echo "  load-store-agents - Load store agents from agents/ folder into test database"

autogpt_platform/autogpt_libs/autogpt_libs/auth/config.py

@@ -16,17 +16,37 @@ ALGO_RECOMMENDATION = (
     "We highly recommend using an asymmetric algorithm such as ES256, "
     "because when leaked, a shared secret would allow anyone to "
     "forge valid tokens and impersonate users. "
-    "More info: https://supabase.com/docs/guides/auth/signing-keys#choosing-the-right-signing-algorithm"  # noqa
+    "More info: https://pyjwt.readthedocs.io/en/stable/algorithms.html"
 )
 
 
 class Settings:
     def __init__(self):
+        # JWT verification key (public key for asymmetric, shared secret for symmetric)
         self.JWT_VERIFY_KEY: str = os.getenv(
             "JWT_VERIFY_KEY", os.getenv("SUPABASE_JWT_SECRET", "")
         ).strip()
+
+        # JWT signing key (private key for asymmetric, shared secret for symmetric)
+        # Falls back to JWT_VERIFY_KEY for symmetric algorithms like HS256
+        self.JWT_SIGN_KEY: str = os.getenv("JWT_SIGN_KEY", self.JWT_VERIFY_KEY).strip()
+
         self.JWT_ALGORITHM: str = os.getenv("JWT_SIGN_ALGORITHM", "HS256").strip()
 
+        # Token expiration settings
+        self.ACCESS_TOKEN_EXPIRE_MINUTES: int = int(
+            os.getenv("ACCESS_TOKEN_EXPIRE_MINUTES", "15")
+        )
+        self.REFRESH_TOKEN_EXPIRE_DAYS: int = int(
+            os.getenv("REFRESH_TOKEN_EXPIRE_DAYS", "7")
+        )
+
+        # JWT issuer claim
+        self.JWT_ISSUER: str = os.getenv("JWT_ISSUER", "autogpt-platform").strip()
+
+        # JWT audience claim
+        self.JWT_AUDIENCE: str = os.getenv("JWT_AUDIENCE", "authenticated").strip()
+
         self.validate()
 
     def validate(self):

autogpt_platform/autogpt_libs/autogpt_libs/auth/helpers.py

@@ -1,25 +1,29 @@
 from fastapi import FastAPI
+from fastapi.openapi.utils import get_openapi
 
 from .jwt_utils import bearer_jwt_auth
 
 
 def add_auth_responses_to_openapi(app: FastAPI) -> None:
     """
-    Patch a FastAPI instance's `openapi()` method to add 401 responses
+    Set up custom OpenAPI schema generation that adds 401 responses
     to all authenticated endpoints.
 
     This is needed when using HTTPBearer with auto_error=False to get proper
     401 responses instead of 403, but FastAPI only automatically adds security
     responses when auto_error=True.
     """
-    # Wrap current method to allow stacking OpenAPI schema modifiers like this
-    wrapped_openapi = app.openapi
 
     def custom_openapi():
         if app.openapi_schema:
             return app.openapi_schema
 
-        openapi_schema = wrapped_openapi()
+        openapi_schema = get_openapi(
+            title=app.title,
+            version=app.version,
+            description=app.description,
+            routes=app.routes,
+        )
 
         # Add 401 response to all endpoints that have security requirements
         for path, methods in openapi_schema["paths"].items():

autogpt_platform/autogpt_libs/autogpt_libs/auth/jwt_utils.py

@@ -1,4 +1,8 @@
+import hashlib
 import logging
+import secrets
+import uuid
+from datetime import datetime, timedelta, timezone
 from typing import Any
 
 import jwt
@@ -16,6 +20,57 @@ bearer_jwt_auth = HTTPBearer(
 )
 
 
+def create_access_token(
+    user_id: str,
+    email: str,
+    role: str = "authenticated",
+    email_verified: bool = False,
+) -> str:
+    """
+    Generate a new JWT access token.
+
+    :param user_id: The user's unique identifier
+    :param email: The user's email address
+    :param role: The user's role (default: "authenticated")
+    :param email_verified: Whether the user's email is verified
+    :return: Encoded JWT token
+    """
+    settings = get_settings()
+    now = datetime.now(timezone.utc)
+
+    payload = {
+        "sub": user_id,
+        "email": email,
+        "role": role,
+        "email_verified": email_verified,
+        "aud": settings.JWT_AUDIENCE,
+        "iss": settings.JWT_ISSUER,
+        "iat": now,
+        "exp": now + timedelta(minutes=settings.ACCESS_TOKEN_EXPIRE_MINUTES),
+        "jti": str(uuid.uuid4()),  # Unique token ID
+    }
+
+    return jwt.encode(payload, settings.JWT_SIGN_KEY, algorithm=settings.JWT_ALGORITHM)
+
+
+def create_refresh_token() -> tuple[str, str]:
+    """
+    Generate a new refresh token.
+
+    Returns a tuple of (raw_token, hashed_token).
+    The raw token should be sent to the client.
+    The hashed token should be stored in the database.
+    """
+    raw_token = secrets.token_urlsafe(64)
+    hashed_token = hashlib.sha256(raw_token.encode()).hexdigest()
+    return raw_token, hashed_token
+
+
+def hash_token(token: str) -> str:
+    """Hash a token using SHA-256."""
+    return hashlib.sha256(token.encode()).hexdigest()
+
+
 async def get_jwt_payload(
     credentials: HTTPAuthorizationCredentials | None = Security(bearer_jwt_auth),
 ) -> dict[str, Any]:
@@ -52,11 +107,19 @@ def parse_jwt_token(token: str) -> dict[str, Any]:
     """
     settings = get_settings()
     try:
+        # Build decode options
+        options = {
+            "verify_aud": True,
+            "verify_iss": bool(settings.JWT_ISSUER),
+        }
+
         payload = jwt.decode(
             token,
             settings.JWT_VERIFY_KEY,
             algorithms=[settings.JWT_ALGORITHM],
-            audience="authenticated",
+            audience=settings.JWT_AUDIENCE,
+            issuer=settings.JWT_ISSUER if settings.JWT_ISSUER else None,
+            options=options,
         )
         return payload
     except jwt.ExpiredSignatureError:

autogpt_platform/autogpt_libs/autogpt_libs/auth/models.py

@@ -11,6 +11,7 @@ class User:
     email: str
     phone_number: str
     role: str
+    email_verified: bool = False
 
     @classmethod
     def from_payload(cls, payload):
@@ -18,5 +19,6 @@ class User:
             user_id=payload["sub"],
             email=payload.get("email", ""),
             phone_number=payload.get("phone", ""),
-            role=payload["role"],
+            role=payload.get("role", "authenticated"),
+            email_verified=payload.get("email_verified", False),
         )

autogpt_platform/autogpt_libs/poetry.lock

@@ -48,6 +48,21 @@ files = [
     {file = "async_timeout-5.0.1.tar.gz", hash = "sha256:d9321a7a3d5a6a5e187e824d2fa0793ce379a202935782d555d6e9d2735677d3"},
 ]
 
+[[package]]
+name = "authlib"
+version = "1.6.6"
+description = "The ultimate Python library in building OAuth and OpenID Connect servers and clients."
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "authlib-1.6.6-py2.py3-none-any.whl", hash = "sha256:7d9e9bc535c13974313a87f53e8430eb6ea3d1cf6ae4f6efcd793f2e949143fd"},
+    {file = "authlib-1.6.6.tar.gz", hash = "sha256:45770e8e056d0f283451d9996fbb59b70d45722b45d854d58f32878d0a40c38e"},
+]
+
+[package.dependencies]
+cryptography = "*"
+
 [[package]]
 name = "backports-asyncio-runner"
 version = "1.2.0"
@@ -61,6 +76,71 @@ files = [
     {file = "backports_asyncio_runner-1.2.0.tar.gz", hash = "sha256:a5aa7b2b7d8f8bfcaa2b57313f70792df84e32a2a746f585213373f900b42162"},
 ]
 
+[[package]]
+name = "bcrypt"
+version = "4.3.0"
+description = "Modern password hashing for your software and your servers"
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "bcrypt-4.3.0-cp313-cp313t-macosx_10_12_universal2.whl", hash = "sha256:f01e060f14b6b57bbb72fc5b4a83ac21c443c9a2ee708e04a10e9192f90a6281"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c5eeac541cefd0bb887a371ef73c62c3cd78535e4887b310626036a7c0a817bb"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:59e1aa0e2cd871b08ca146ed08445038f42ff75968c7ae50d2fdd7860ade2180"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:0042b2e342e9ae3d2ed22727c1262f76cc4f345683b5c1715f0250cf4277294f"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:74a8d21a09f5e025a9a23e7c0fd2c7fe8e7503e4d356c0a2c1486ba010619f09"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:0142b2cb84a009f8452c8c5a33ace5e3dfec4159e7735f5afe9a4d50a8ea722d"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-manylinux_2_34_aarch64.whl", hash = "sha256:12fa6ce40cde3f0b899729dbd7d5e8811cb892d31b6f7d0334a1f37748b789fd"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-manylinux_2_34_x86_64.whl", hash = "sha256:5bd3cca1f2aa5dbcf39e2aa13dd094ea181f48959e1071265de49cc2b82525af"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:335a420cfd63fc5bc27308e929bee231c15c85cc4c496610ffb17923abf7f231"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:0e30e5e67aed0187a1764911af023043b4542e70a7461ad20e837e94d23e1d6c"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:3b8d62290ebefd49ee0b3ce7500f5dbdcf13b81402c05f6dafab9a1e1b27212f"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:2ef6630e0ec01376f59a006dc72918b1bf436c3b571b80fa1968d775fa02fe7d"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-win32.whl", hash = "sha256:7a4be4cbf241afee43f1c3969b9103a41b40bcb3a3f467ab19f891d9bc4642e4"},
+    {file = "bcrypt-4.3.0-cp313-cp313t-win_amd64.whl", hash = "sha256:5c1949bf259a388863ced887c7861da1df681cb2388645766c89fdfd9004c669"},
+    {file = "bcrypt-4.3.0-cp38-abi3-macosx_10_12_universal2.whl", hash = "sha256:f81b0ed2639568bf14749112298f9e4e2b28853dab50a8b357e31798686a036d"},
+    {file = "bcrypt-4.3.0-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:864f8f19adbe13b7de11ba15d85d4a428c7e2f344bac110f667676a0ff84924b"},
+    {file = "bcrypt-4.3.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3e36506d001e93bffe59754397572f21bb5dc7c83f54454c990c74a468cd589e"},
+    {file = "bcrypt-4.3.0-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:842d08d75d9fe9fb94b18b071090220697f9f184d4547179b60734846461ed59"},
+    {file = "bcrypt-4.3.0-cp38-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:7c03296b85cb87db865d91da79bf63d5609284fc0cab9472fdd8367bbd830753"},
+    {file = "bcrypt-4.3.0-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:62f26585e8b219cdc909b6a0069efc5e4267e25d4a3770a364ac58024f62a761"},
+    {file = "bcrypt-4.3.0-cp38-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:beeefe437218a65322fbd0069eb437e7c98137e08f22c4660ac2dc795c31f8bb"},
+    {file = "bcrypt-4.3.0-cp38-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:97eea7408db3a5bcce4a55d13245ab3fa566e23b4c67cd227062bb49e26c585d"},
+    {file = "bcrypt-4.3.0-cp38-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:191354ebfe305e84f344c5964c7cd5f924a3bfc5d405c75ad07f232b6dffb49f"},
+    {file = "bcrypt-4.3.0-cp38-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:41261d64150858eeb5ff43c753c4b216991e0ae16614a308a15d909503617732"},
+    {file = "bcrypt-4.3.0-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:33752b1ba962ee793fa2b6321404bf20011fe45b9afd2a842139de3011898fef"},
+    {file = "bcrypt-4.3.0-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:50e6e80a4bfd23a25f5c05b90167c19030cf9f87930f7cb2eacb99f45d1c3304"},
+    {file = "bcrypt-4.3.0-cp38-abi3-win32.whl", hash = "sha256:67a561c4d9fb9465ec866177e7aebcad08fe23aaf6fbd692a6fab69088abfc51"},
+    {file = "bcrypt-4.3.0-cp38-abi3-win_amd64.whl", hash = "sha256:584027857bc2843772114717a7490a37f68da563b3620f78a849bcb54dc11e62"},
+    {file = "bcrypt-4.3.0-cp39-abi3-macosx_10_12_universal2.whl", hash = "sha256:0d3efb1157edebfd9128e4e46e2ac1a64e0c1fe46fb023158a407c7892b0f8c3"},
+    {file = "bcrypt-4.3.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:08bacc884fd302b611226c01014eca277d48f0a05187666bca23aac0dad6fe24"},
+    {file = "bcrypt-4.3.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f6746e6fec103fcd509b96bacdfdaa2fbde9a553245dbada284435173a6f1aef"},
+    {file = "bcrypt-4.3.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:afe327968aaf13fc143a56a3360cb27d4ad0345e34da12c7290f1b00b8fe9a8b"},
+    {file = "bcrypt-4.3.0-cp39-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:d9af79d322e735b1fc33404b5765108ae0ff232d4b54666d46730f8ac1a43676"},
+    {file = "bcrypt-4.3.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:f1e3ffa1365e8702dc48c8b360fef8d7afeca482809c5e45e653af82ccd088c1"},
+    {file = "bcrypt-4.3.0-cp39-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:3004df1b323d10021fda07a813fd33e0fd57bef0e9a480bb143877f6cba996fe"},
+    {file = "bcrypt-4.3.0-cp39-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:531457e5c839d8caea9b589a1bcfe3756b0547d7814e9ce3d437f17da75c32b0"},
+    {file = "bcrypt-4.3.0-cp39-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:17a854d9a7a476a89dcef6c8bd119ad23e0f82557afbd2c442777a16408e614f"},
+    {file = "bcrypt-4.3.0-cp39-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:6fb1fd3ab08c0cbc6826a2e0447610c6f09e983a281b919ed721ad32236b8b23"},
+    {file = "bcrypt-4.3.0-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:e965a9c1e9a393b8005031ff52583cedc15b7884fce7deb8b0346388837d6cfe"},
+    {file = "bcrypt-4.3.0-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:79e70b8342a33b52b55d93b3a59223a844962bef479f6a0ea318ebbcadf71505"},
+    {file = "bcrypt-4.3.0-cp39-abi3-win32.whl", hash = "sha256:b4d4e57f0a63fd0b358eb765063ff661328f69a04494427265950c71b992a39a"},
+    {file = "bcrypt-4.3.0-cp39-abi3-win_amd64.whl", hash = "sha256:e53e074b120f2877a35cc6c736b8eb161377caae8925c17688bd46ba56daaa5b"},
+    {file = "bcrypt-4.3.0-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c950d682f0952bafcceaf709761da0a32a942272fad381081b51096ffa46cea1"},
+    {file = "bcrypt-4.3.0-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:107d53b5c67e0bbc3f03ebf5b030e0403d24dda980f8e244795335ba7b4a027d"},
+    {file = "bcrypt-4.3.0-pp310-pypy310_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:b693dbb82b3c27a1604a3dff5bfc5418a7e6a781bb795288141e5f80cf3a3492"},
+    {file = "bcrypt-4.3.0-pp310-pypy310_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:b6354d3760fcd31994a14c89659dee887f1351a06e5dac3c1142307172a79f90"},
+    {file = "bcrypt-4.3.0-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:a839320bf27d474e52ef8cb16449bb2ce0ba03ca9f44daba6d93fa1d8828e48a"},
+    {file = "bcrypt-4.3.0-pp311-pypy311_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:bdc6a24e754a555d7316fa4774e64c6c3997d27ed2d1964d55920c7c227bc4ce"},
+    {file = "bcrypt-4.3.0-pp311-pypy311_pp73-manylinux_2_34_aarch64.whl", hash = "sha256:55a935b8e9a1d2def0626c4269db3fcd26728cbff1e84f0341465c31c4ee56d8"},
+    {file = "bcrypt-4.3.0-pp311-pypy311_pp73-manylinux_2_34_x86_64.whl", hash = "sha256:57967b7a28d855313a963aaea51bf6df89f833db4320da458e5b3c5ab6d4c938"},
+    {file = "bcrypt-4.3.0.tar.gz", hash = "sha256:3a3fd2204178b6d2adcf09cb4f6426ffef54762577a7c9b54c159008cb288c18"},
+]
+
+[package.extras]
+tests = ["pytest (>=3.2.1,!=3.3.0)"]
+typecheck = ["mypy"]
+
 [[package]]
 name = "cachetools"
 version = "5.5.2"
@@ -459,21 +539,6 @@ ssh = ["bcrypt (>=3.1.5)"]
 test = ["certifi (>=2024)", "cryptography-vectors (==45.0.6)", "pretend (>=0.7)", "pytest (>=7.4.0)", "pytest-benchmark (>=4.0)", "pytest-cov (>=2.10.1)", "pytest-xdist (>=3.5.0)"]
 test-randomorder = ["pytest-randomly"]
 
-[[package]]
-name = "deprecation"
-version = "2.1.0"
-description = "A library to handle automated deprecations"
-optional = false
-python-versions = "*"
-groups = ["main"]
-files = [
-    {file = "deprecation-2.1.0-py2.py3-none-any.whl", hash = "sha256:a10811591210e1fb0e768a8c25517cabeabcba6f0bf96564f8ff45189f90b14a"},
-    {file = "deprecation-2.1.0.tar.gz", hash = "sha256:72b3bde64e5d778694b0cf68178aed03d15e15477116add3fb773e581f9518ff"},
-]
-
-[package.dependencies]
-packaging = "*"
-
 [[package]]
 name = "exceptiongroup"
 version = "1.3.0"
@@ -695,23 +760,6 @@ protobuf = ">=3.20.2,<4.21.1 || >4.21.1,<4.21.2 || >4.21.2,<4.21.3 || >4.21.3,<4
 [package.extras]
 grpc = ["grpcio (>=1.44.0,<2.0.0)"]
 
-[[package]]
-name = "gotrue"
-version = "2.12.3"
-description = "Python Client Library for Supabase Auth"
-optional = false
-python-versions = "<4.0,>=3.9"
-groups = ["main"]
-files = [
-    {file = "gotrue-2.12.3-py3-none-any.whl", hash = "sha256:b1a3c6a5fe3f92e854a026c4c19de58706a96fd5fbdcc3d620b2802f6a46a26b"},
-    {file = "gotrue-2.12.3.tar.gz", hash = "sha256:f874cf9d0b2f0335bfbd0d6e29e3f7aff79998cd1c14d2ad814db8c06cee3852"},
-]
-
-[package.dependencies]
-httpx = {version = ">=0.26,<0.29", extras = ["http2"]}
-pydantic = ">=1.10,<3"
-pyjwt = ">=2.10.1,<3.0.0"
-
 [[package]]
 name = "grpc-google-iam-v1"
 version = "0.14.2"
@@ -822,94 +870,6 @@ files = [
     {file = "h11-0.16.0.tar.gz", hash = "sha256:4e35b956cf45792e4caa5885e69fba00bdbc6ffafbfa020300e549b208ee5ff1"},
 ]
 
-[[package]]
-name = "h2"
-version = "4.2.0"
-description = "Pure-Python HTTP/2 protocol implementation"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "h2-4.2.0-py3-none-any.whl", hash = "sha256:479a53ad425bb29af087f3458a61d30780bc818e4ebcf01f0b536ba916462ed0"},
-    {file = "h2-4.2.0.tar.gz", hash = "sha256:c8a52129695e88b1a0578d8d2cc6842bbd79128ac685463b887ee278126ad01f"},
-]
-
-[package.dependencies]
-hpack = ">=4.1,<5"
-hyperframe = ">=6.1,<7"
-
-[[package]]
-name = "hpack"
-version = "4.1.0"
-description = "Pure-Python HPACK header encoding"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "hpack-4.1.0-py3-none-any.whl", hash = "sha256:157ac792668d995c657d93111f46b4535ed114f0c9c8d672271bbec7eae1b496"},
-    {file = "hpack-4.1.0.tar.gz", hash = "sha256:ec5eca154f7056aa06f196a557655c5b009b382873ac8d1e66e79e87535f1dca"},
-]
-
-[[package]]
-name = "httpcore"
-version = "1.0.9"
-description = "A minimal low-level HTTP client."
-optional = false
-python-versions = ">=3.8"
-groups = ["main"]
-files = [
-    {file = "httpcore-1.0.9-py3-none-any.whl", hash = "sha256:2d400746a40668fc9dec9810239072b40b4484b640a8c38fd654a024c7a1bf55"},
-    {file = "httpcore-1.0.9.tar.gz", hash = "sha256:6e34463af53fd2ab5d807f399a9b45ea31c3dfa2276f15a2c3f00afff6e176e8"},
-]
-
-[package.dependencies]
-certifi = "*"
-h11 = ">=0.16"
-
-[package.extras]
-asyncio = ["anyio (>=4.0,<5.0)"]
-http2 = ["h2 (>=3,<5)"]
-socks = ["socksio (==1.*)"]
-trio = ["trio (>=0.22.0,<1.0)"]
-
-[[package]]
-name = "httpx"
-version = "0.28.1"
-description = "The next generation HTTP client."
-optional = false
-python-versions = ">=3.8"
-groups = ["main"]
-files = [
-    {file = "httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad"},
-    {file = "httpx-0.28.1.tar.gz", hash = "sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc"},
-]
-
-[package.dependencies]
-anyio = "*"
-certifi = "*"
-h2 = {version = ">=3,<5", optional = true, markers = "extra == \"http2\""}
-httpcore = "==1.*"
-idna = "*"
-
-[package.extras]
-brotli = ["brotli ; platform_python_implementation == \"CPython\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
-cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
-http2 = ["h2 (>=3,<5)"]
-socks = ["socksio (==1.*)"]
-zstd = ["zstandard (>=0.18.0)"]
-
-[[package]]
-name = "hyperframe"
-version = "6.1.0"
-description = "Pure-Python HTTP/2 framing"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "hyperframe-6.1.0-py3-none-any.whl", hash = "sha256:b03380493a519fce58ea5af42e4a42317bf9bd425596f7a0835ffce80f1a42e5"},
-    {file = "hyperframe-6.1.0.tar.gz", hash = "sha256:f630908a00854a7adeabd6382b43923a4c4cd4b821fcb527e6ab9e15382a3b08"},
-]
-
 [[package]]
 name = "idna"
 version = "3.10"
@@ -1036,7 +996,7 @@ version = "25.0"
 description = "Core utilities for Python packages"
 optional = false
 python-versions = ">=3.8"
-groups = ["main", "dev"]
+groups = ["dev"]
 files = [
     {file = "packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484"},
     {file = "packaging-25.0.tar.gz", hash = "sha256:d443872c98d677bf60f6a1f2f8c1cb748e8fe762d2bf9d3148b5599295b0fc4f"},
@@ -1058,24 +1018,6 @@ files = [
 dev = ["pre-commit", "tox"]
 testing = ["coverage", "pytest", "pytest-benchmark"]
 
-[[package]]
-name = "postgrest"
-version = "1.1.1"
-description = "PostgREST client for Python. This library provides an ORM interface to PostgREST."
-optional = false
-python-versions = "<4.0,>=3.9"
-groups = ["main"]
-files = [
-    {file = "postgrest-1.1.1-py3-none-any.whl", hash = "sha256:98a6035ee1d14288484bfe36235942c5fb2d26af6d8120dfe3efbe007859251a"},
-    {file = "postgrest-1.1.1.tar.gz", hash = "sha256:f3bb3e8c4602775c75c844a31f565f5f3dd584df4d36d683f0b67d01a86be322"},
-]
-
-[package.dependencies]
-deprecation = ">=2.1.0,<3.0.0"
-httpx = {version = ">=0.26,<0.29", extras = ["http2"]}
-pydantic = ">=1.9,<3.0"
-strenum = {version = ">=0.4.9,<0.5.0", markers = "python_version < \"3.11\""}
-
 [[package]]
 name = "proto-plus"
 version = "1.26.1"
@@ -1462,21 +1404,6 @@ pytest = ">=6.2.5"
 [package.extras]
 dev = ["pre-commit", "pytest-asyncio", "tox"]
 
-[[package]]
-name = "python-dateutil"
-version = "2.9.0.post0"
-description = "Extensions to the standard Python datetime module"
-optional = false
-python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
-groups = ["main"]
-files = [
-    {file = "python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3"},
-    {file = "python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427"},
-]
-
-[package.dependencies]
-six = ">=1.5"
-
 [[package]]
 name = "python-dotenv"
 version = "1.1.1"
@@ -1492,22 +1419,6 @@ files = [
 [package.extras]
 cli = ["click (>=5.0)"]
 
-[[package]]
-name = "realtime"
-version = "2.5.3"
-description = ""
-optional = false
-python-versions = "<4.0,>=3.9"
-groups = ["main"]
-files = [
-    {file = "realtime-2.5.3-py3-none-any.whl", hash = "sha256:eb0994636946eff04c4c7f044f980c8c633c7eb632994f549f61053a474ac970"},
-    {file = "realtime-2.5.3.tar.gz", hash = "sha256:0587594f3bc1c84bf007ff625075b86db6528843e03250dc84f4f2808be3d99a"},
-]
-
-[package.dependencies]
-typing-extensions = ">=4.14.0,<5.0.0"
-websockets = ">=11,<16"
-
 [[package]]
 name = "redis"
 version = "6.2.0"
@@ -1606,18 +1517,6 @@ files = [
     {file = "semver-3.0.4.tar.gz", hash = "sha256:afc7d8c584a5ed0a11033af086e8af226a9c0b206f313e0301f8dd7b6b589602"},
 ]
 
-[[package]]
-name = "six"
-version = "1.17.0"
-description = "Python 2 and 3 compatibility utilities"
-optional = false
-python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
-groups = ["main"]
-files = [
-    {file = "six-1.17.0-py2.py3-none-any.whl", hash = "sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274"},
-    {file = "six-1.17.0.tar.gz", hash = "sha256:ff70335d468e7eb6ec65b95b99d3a2836546063f63acc5171de367e834932a81"},
-]
-
 [[package]]
 name = "sniffio"
 version = "1.3.1"
@@ -1649,76 +1548,6 @@ typing-extensions = {version = ">=4.10.0", markers = "python_version < \"3.13\""
 [package.extras]
 full = ["httpx (>=0.27.0,<0.29.0)", "itsdangerous", "jinja2", "python-multipart (>=0.0.18)", "pyyaml"]
 
-[[package]]
-name = "storage3"
-version = "0.12.0"
-description = "Supabase Storage client for Python."
-optional = false
-python-versions = "<4.0,>=3.9"
-groups = ["main"]
-files = [
-    {file = "storage3-0.12.0-py3-none-any.whl", hash = "sha256:1c4585693ca42243ded1512b58e54c697111e91a20916cd14783eebc37e7c87d"},
-    {file = "storage3-0.12.0.tar.gz", hash = "sha256:94243f20922d57738bf42e96b9f5582b4d166e8bf209eccf20b146909f3f71b0"},
-]
-
-[package.dependencies]
-deprecation = ">=2.1.0,<3.0.0"
-httpx = {version = ">=0.26,<0.29", extras = ["http2"]}
-python-dateutil = ">=2.8.2,<3.0.0"
-
-[[package]]
-name = "strenum"
-version = "0.4.15"
-description = "An Enum that inherits from str."
-optional = false
-python-versions = "*"
-groups = ["main"]
-files = [
-    {file = "StrEnum-0.4.15-py3-none-any.whl", hash = "sha256:a30cda4af7cc6b5bf52c8055bc4bf4b2b6b14a93b574626da33df53cf7740659"},
-    {file = "StrEnum-0.4.15.tar.gz", hash = "sha256:878fb5ab705442070e4dd1929bb5e2249511c0bcf2b0eeacf3bcd80875c82eff"},
-]
-
-[package.extras]
-docs = ["myst-parser[linkify]", "sphinx", "sphinx-rtd-theme"]
-release = ["twine"]
-test = ["pylint", "pytest", "pytest-black", "pytest-cov", "pytest-pylint"]
-
-[[package]]
-name = "supabase"
-version = "2.16.0"
-description = "Supabase client for Python."
-optional = false
-python-versions = "<4.0,>=3.9"
-groups = ["main"]
-files = [
-    {file = "supabase-2.16.0-py3-none-any.whl", hash = "sha256:99065caab3d90a56650bf39fbd0e49740995da3738ab28706c61bd7f2401db55"},
-    {file = "supabase-2.16.0.tar.gz", hash = "sha256:98f3810158012d4ec0e3083f2e5515f5e10b32bd71e7d458662140e963c1d164"},
-]
-
-[package.dependencies]
-gotrue = ">=2.11.0,<3.0.0"
-httpx = ">=0.26,<0.29"
-postgrest = ">0.19,<1.2"
-realtime = ">=2.4.0,<2.6.0"
-storage3 = ">=0.10,<0.13"
-supafunc = ">=0.9,<0.11"
-
-[[package]]
-name = "supafunc"
-version = "0.10.1"
-description = "Library for Supabase Functions"
-optional = false
-python-versions = "<4.0,>=3.9"
-groups = ["main"]
-files = [
-    {file = "supafunc-0.10.1-py3-none-any.whl", hash = "sha256:26df9bd25ff2ef56cb5bfb8962de98f43331f7f8ff69572bac3ed9c3a9672040"},
-    {file = "supafunc-0.10.1.tar.gz", hash = "sha256:a5b33c8baecb6b5297d25da29a2503e2ec67ee6986f3d44c137e651b8a59a17d"},
-]
-
-[package.dependencies]
-httpx = {version = ">=0.26,<0.29", extras = ["http2"]}
-strenum = ">=0.4.15,<0.5.0"
-
 [[package]]
 name = "tomli"
 version = "2.2.1"
@@ -1827,85 +1656,6 @@ typing-extensions = {version = ">=4.0", markers = "python_version < \"3.11\""}
 [package.extras]
 standard = ["colorama (>=0.4) ; sys_platform == \"win32\"", "httptools (>=0.6.3)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.15.1) ; sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\"", "watchfiles (>=0.13)", "websockets (>=10.4)"]
 
-[[package]]
-name = "websockets"
-version = "15.0.1"
-description = "An implementation of the WebSocket Protocol (RFC 6455 & 7692)"
-optional = false
-python-versions = ">=3.9"
-groups = ["main"]
-files = [
-    {file = "websockets-15.0.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:d63efaa0cd96cf0c5fe4d581521d9fa87744540d4bc999ae6e08595a1014b45b"},
-    {file = "websockets-15.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ac60e3b188ec7574cb761b08d50fcedf9d77f1530352db4eef1707fe9dee7205"},
-    {file = "websockets-15.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:5756779642579d902eed757b21b0164cd6fe338506a8083eb58af5c372e39d9a"},
-    {file = "websockets-15.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0fdfe3e2a29e4db3659dbd5bbf04560cea53dd9610273917799f1cde46aa725e"},
-    {file = "websockets-15.0.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4c2529b320eb9e35af0fa3016c187dffb84a3ecc572bcee7c3ce302bfeba52bf"},
-    {file = "websockets-15.0.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ac1e5c9054fe23226fb11e05a6e630837f074174c4c2f0fe442996112a6de4fb"},
-    {file = "websockets-15.0.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:5df592cd503496351d6dc14f7cdad49f268d8e618f80dce0cd5a36b93c3fc08d"},
-    {file = "websockets-15.0.1-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:0a34631031a8f05657e8e90903e656959234f3a04552259458aac0b0f9ae6fd9"},
-    {file = "websockets-15.0.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:3d00075aa65772e7ce9e990cab3ff1de702aa09be3940d1dc88d5abf1ab8a09c"},
-    {file = "websockets-15.0.1-cp310-cp310-win32.whl", hash = "sha256:1234d4ef35db82f5446dca8e35a7da7964d02c127b095e172e54397fb6a6c256"},
-    {file = "websockets-15.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:39c1fec2c11dc8d89bba6b2bf1556af381611a173ac2b511cf7231622058af41"},
-    {file = "websockets-15.0.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:823c248b690b2fd9303ba00c4f66cd5e2d8c3ba4aa968b2779be9532a4dad431"},
-    {file = "websockets-15.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:678999709e68425ae2593acf2e3ebcbcf2e69885a5ee78f9eb80e6e371f1bf57"},
-    {file = "websockets-15.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d50fd1ee42388dcfb2b3676132c78116490976f1300da28eb629272d5d93e905"},
-    {file = "websockets-15.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d99e5546bf73dbad5bf3547174cd6cb8ba7273062a23808ffea025ecb1cf8562"},
-    {file = "websockets-15.0.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:66dd88c918e3287efc22409d426c8f729688d89a0c587c88971a0faa2c2f3792"},
-    {file = "websockets-15.0.1-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8dd8327c795b3e3f219760fa603dcae1dcc148172290a8ab15158cf85a953413"},
-    {file = "websockets-15.0.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8fdc51055e6ff4adeb88d58a11042ec9a5eae317a0a53d12c062c8a8865909e8"},
-    {file = "websockets-15.0.1-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:693f0192126df6c2327cce3baa7c06f2a117575e32ab2308f7f8216c29d9e2e3"},
-    {file = "websockets-15.0.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:54479983bd5fb469c38f2f5c7e3a24f9a4e70594cd68cd1fa6b9340dadaff7cf"},
-    {file = "websockets-15.0.1-cp311-cp311-win32.whl", hash = "sha256:16b6c1b3e57799b9d38427dda63edcbe4926352c47cf88588c0be4ace18dac85"},
-    {file = "websockets-15.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:27ccee0071a0e75d22cb35849b1db43f2ecd3e161041ac1ee9d2352ddf72f065"},
-    {file = "websockets-15.0.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:3e90baa811a5d73f3ca0bcbf32064d663ed81318ab225ee4f427ad4e26e5aff3"},
-    {file = "websockets-15.0.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:592f1a9fe869c778694f0aa806ba0374e97648ab57936f092fd9d87f8bc03665"},
-    {file = "websockets-15.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0701bc3cfcb9164d04a14b149fd74be7347a530ad3bbf15ab2c678a2cd3dd9a2"},
-    {file = "websockets-15.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8b56bdcdb4505c8078cb6c7157d9811a85790f2f2b3632c7d1462ab5783d215"},
-    {file = "websockets-15.0.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0af68c55afbd5f07986df82831c7bff04846928ea8d1fd7f30052638788bc9b5"},
-    {file = "websockets-15.0.1-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64dee438fed052b52e4f98f76c5790513235efaa1ef7f3f2192c392cd7c91b65"},
-    {file = "websockets-15.0.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:d5f6b181bb38171a8ad1d6aa58a67a6aa9d4b38d0f8c5f496b9e42561dfc62fe"},
-    {file = "websockets-15.0.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:5d54b09eba2bada6011aea5375542a157637b91029687eb4fdb2dab11059c1b4"},
-    {file = "websockets-15.0.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:3be571a8b5afed347da347bfcf27ba12b069d9d7f42cb8c7028b5e98bbb12597"},
-    {file = "websockets-15.0.1-cp312-cp312-win32.whl", hash = "sha256:c338ffa0520bdb12fbc527265235639fb76e7bc7faafbb93f6ba80d9c06578a9"},
-    {file = "websockets-15.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:fcd5cf9e305d7b8338754470cf69cf81f420459dbae8a3b40cee57417f4614a7"},
-    {file = "websockets-15.0.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:ee443ef070bb3b6ed74514f5efaa37a252af57c90eb33b956d35c8e9c10a1931"},
-    {file = "websockets-15.0.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:5a939de6b7b4e18ca683218320fc67ea886038265fd1ed30173f5ce3f8e85675"},
-    {file = "websockets-15.0.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:746ee8dba912cd6fc889a8147168991d50ed70447bf18bcda7039f7d2e3d9151"},
-    {file = "websockets-15.0.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:595b6c3969023ecf9041b2936ac3827e4623bfa3ccf007575f04c5a6aa318c22"},
-    {file = "websockets-15.0.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3c714d2fc58b5ca3e285461a4cc0c9a66bd0e24c5da9911e30158286c9b5be7f"},
-    {file = "websockets-15.0.1-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0f3c1e2ab208db911594ae5b4f79addeb3501604a165019dd221c0bdcabe4db8"},
-    {file = "websockets-15.0.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:229cf1d3ca6c1804400b0a9790dc66528e08a6a1feec0d5040e8b9eb14422375"},
-    {file = "websockets-15.0.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:756c56e867a90fb00177d530dca4b097dd753cde348448a1012ed6c5131f8b7d"},
-    {file = "websockets-15.0.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:558d023b3df0bffe50a04e710bc87742de35060580a293c2a984299ed83bc4e4"},
-    {file = "websockets-15.0.1-cp313-cp313-win32.whl", hash = "sha256:ba9e56e8ceeeedb2e080147ba85ffcd5cd0711b89576b83784d8605a7df455fa"},
-    {file = "websockets-15.0.1-cp313-cp313-win_amd64.whl", hash = "sha256:e09473f095a819042ecb2ab9465aee615bd9c2028e4ef7d933600a8401c79561"},
-    {file = "websockets-15.0.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:5f4c04ead5aed67c8a1a20491d54cdfba5884507a48dd798ecaf13c74c4489f5"},
-    {file = "websockets-15.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:abdc0c6c8c648b4805c5eacd131910d2a7f6455dfd3becab248ef108e89ab16a"},
-    {file = "websockets-15.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a625e06551975f4b7ea7102bc43895b90742746797e2e14b70ed61c43a90f09b"},
-    {file = "websockets-15.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d591f8de75824cbb7acad4e05d2d710484f15f29d4a915092675ad3456f11770"},
-    {file = "websockets-15.0.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:47819cea040f31d670cc8d324bb6435c6f133b8c7a19ec3d61634e62f8d8f9eb"},
-    {file = "websockets-15.0.1-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ac017dd64572e5c3bd01939121e4d16cf30e5d7e110a119399cf3133b63ad054"},
-    {file = "websockets-15.0.1-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:4a9fac8e469d04ce6c25bb2610dc535235bd4aa14996b4e6dbebf5e007eba5ee"},
-    {file = "websockets-15.0.1-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:363c6f671b761efcb30608d24925a382497c12c506b51661883c3e22337265ed"},
-    {file = "websockets-15.0.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:2034693ad3097d5355bfdacfffcbd3ef5694f9718ab7f29c29689a9eae841880"},
-    {file = "websockets-15.0.1-cp39-cp39-win32.whl", hash = "sha256:3b1ac0d3e594bf121308112697cf4b32be538fb1444468fb0a6ae4feebc83411"},
-    {file = "websockets-15.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:b7643a03db5c95c799b89b31c036d5f27eeb4d259c798e878d6937d71832b1e4"},
-    {file = "websockets-15.0.1-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:0c9e74d766f2818bb95f84c25be4dea09841ac0f734d1966f415e4edfc4ef1c3"},
-    {file = "websockets-15.0.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:1009ee0c7739c08a0cd59de430d6de452a55e42d6b522de7aa15e6f67db0b8e1"},
-    {file = "websockets-15.0.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:76d1f20b1c7a2fa82367e04982e708723ba0e7b8d43aa643d3dcd404d74f1475"},
-    {file = "websockets-15.0.1-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f29d80eb9a9263b8d109135351caf568cc3f80b9928bccde535c235de55c22d9"},
-    {file = "websockets-15.0.1-pp310-pypy310_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b359ed09954d7c18bbc1680f380c7301f92c60bf924171629c5db97febb12f04"},
-    {file = "websockets-15.0.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:cad21560da69f4ce7658ca2cb83138fb4cf695a2ba3e475e0559e05991aa8122"},
-    {file = "websockets-15.0.1-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:7f493881579c90fc262d9cdbaa05a6b54b3811c2f300766748db79f098db9940"},
-    {file = "websockets-15.0.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:47b099e1f4fbc95b701b6e85768e1fcdaf1630f3cbe4765fa216596f12310e2e"},
-    {file = "websockets-15.0.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:67f2b6de947f8c757db2db9c71527933ad0019737ec374a8a6be9a956786aaf9"},
-    {file = "websockets-15.0.1-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d08eb4c2b7d6c41da6ca0600c077e93f5adcfd979cd777d747e9ee624556da4b"},
-    {file = "websockets-15.0.1-pp39-pypy39_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4b826973a4a2ae47ba357e4e82fa44a463b8f168e1ca775ac64521442b19e87f"},
-    {file = "websockets-15.0.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:21c1fa28a6a7e3cbdc171c694398b6df4744613ce9b36b1a498e816787e28123"},
-    {file = "websockets-15.0.1-py3-none-any.whl", hash = "sha256:f7a866fbc1e97b5c617ee4116daaa09b722101d4a3c170c787450ba409f9736f"},
-    {file = "websockets-15.0.1.tar.gz", hash = "sha256:82544de02076bafba038ce055ee6412d68da13ab47f0c60cab827346de828dee"},
-]
-
 [[package]]
 name = "zipp"
 version = "3.23.0"
@@ -1929,4 +1679,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<4.0"
-content-hash = "0c40b63c3c921846cf05ccfb4e685d4959854b29c2c302245f9832e20aac6954"
+content-hash = "de209c97aa0feb29d669a20e4422d51bdf3a0872ec37e85ce9b88ce726fcee7a"

autogpt_platform/autogpt_libs/pyproject.toml

@@ -18,7 +18,8 @@ pydantic = "^2.11.7"
 pydantic-settings = "^2.10.1"
 pyjwt = { version = "^2.10.1", extras = ["crypto"] }
 redis = "^6.2.0"
-supabase = "^2.16.0"
+bcrypt = "^4.1.0"
+authlib = "^1.3.0"
 uvicorn = "^0.35.0"
 
 [tool.poetry.group.dev.dependencies]

autogpt_platform/backend/.env.default

@@ -27,10 +27,15 @@ REDIS_PORT=6379
 RABBITMQ_DEFAULT_USER=rabbitmq_user_default
 RABBITMQ_DEFAULT_PASS=k0VMxyIJF9S35f3x2uaw5IWAl6Y536O7
 
-# Supabase Authentication
-SUPABASE_URL=http://localhost:8000
-SUPABASE_SERVICE_ROLE_KEY=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyAgCiAgICAicm9sZSI6ICJzZXJ2aWNlX3JvbGUiLAogICAgImlzcyI6ICJzdXBhYmFzZS1kZW1vIiwKICAgICJpYXQiOiAxNjQxNzY5MjAwLAogICAgImV4cCI6IDE3OTk1MzU2MDAKfQ.DaYlNEoUrrEn2Ig7tqibS-PHK5vgusbcbo7X36XVt4Q
+# JWT Authentication
+# Generate a secure random key: python -c "import secrets; print(secrets.token_urlsafe(32))"
+JWT_SIGN_KEY=your-super-secret-jwt-token-with-at-least-32-characters-long
 JWT_VERIFY_KEY=your-super-secret-jwt-token-with-at-least-32-characters-long
+JWT_SIGN_ALGORITHM=HS256
+ACCESS_TOKEN_EXPIRE_MINUTES=15
+REFRESH_TOKEN_EXPIRE_DAYS=7
+JWT_ISSUER=autogpt-platform
+JWT_AUDIENCE=authenticated
 
 ## ===== REQUIRED SECURITY KEYS ===== ##
 # Generate using: from cryptography.fernet import Fernet;Fernet.generate_key().decode()
@@ -58,13 +63,6 @@ V0_API_KEY=
 OPEN_ROUTER_API_KEY=
 NVIDIA_API_KEY=
 
-# Langfuse Prompt Management
-# Used for managing the CoPilot system prompt externally
-# Get credentials from https://cloud.langfuse.com or your self-hosted instance
-LANGFUSE_PUBLIC_KEY=
-LANGFUSE_SECRET_KEY=
-LANGFUSE_HOST=https://cloud.langfuse.com
-
 # OAuth Credentials
 # For the OAuth callback URL, use <your_frontend_url>/auth/integrations/oauth_callback,
 # e.g. http://localhost:3000/auth/integrations/oauth_callback

autogpt_platform/backend/.gitignore

@@ -18,4 +18,6 @@ load-tests/results/
 load-tests/*.json
 load-tests/*.log
 load-tests/node_modules/*
-migrations/*/rollback*.sql
+
+# Migration backups (contain user data)
+migration_backups/

autogpt_platform/backend/Dockerfile

@@ -48,8 +48,7 @@ RUN poetry install --no-ansi --no-root
 # Generate Prisma client
 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 ./
-RUN poetry run prisma generate && poetry run gen-prisma-stub
+RUN poetry run prisma generate
 
 FROM debian:13-slim AS server_dependencies
 
@@ -100,7 +99,6 @@ COPY autogpt_platform/backend/migrations /app/autogpt_platform/backend/migration
 FROM server_dependencies AS server
 
 COPY autogpt_platform/backend /app/autogpt_platform/backend
-COPY docs /app/docs
 RUN poetry install --no-ansi --only-root
 
 ENV PORT=8000

autogpt_platform/backend/TESTING.md

@@ -108,7 +108,7 @@ import fastapi.testclient
 import pytest
 from pytest_snapshot.plugin import Snapshot
 
-from backend.api.features.myroute import router
+from backend.server.v2.myroute import router
 
 app = fastapi.FastAPI()
 app.include_router(router)
@@ -149,7 +149,7 @@ These provide the easiest way to set up authentication mocking in test modules:
 import fastapi
 import fastapi.testclient
 import pytest
-from backend.api.features.myroute import router
+from backend.server.v2.myroute import router
 
 app = fastapi.FastAPI()
 app.include_router(router)

autogpt_platform/backend/backend/api/external/fastapi_app.py

@@ -1,61 +0,0 @@
-"""
-External API Application
-
-This module defines the main FastAPI application for the external API,
-which mounts the v1 and v2 sub-applications.
-"""
-
-from fastapi import FastAPI
-from fastapi.responses import RedirectResponse
-
-from backend.monitoring.instrumentation import instrument_fastapi
-
-from .v1.app import v1_app
-from .v2.app import v2_app
-
-DESCRIPTION = """
-The external API provides programmatic access to the AutoGPT Platform for building
-integrations, automations, and custom applications.
-
-### API Versions
-
-| Version             | End of Life | Path                   | Documentation |
-|---------------------|-------------|------------------------|---------------|
-| **v2**              |             | `/external-api/v2/...` | [v2 docs](v2/docs) |
-| **v1** (deprecated) | 2025-05-01  | `/external-api/v1/...` | [v1 docs](v1/docs) |
-
-**Recommendation**: New integrations should use v2.
-
-For authentication details and usage examples, see the
-[API Integration Guide](https://docs.agpt.co/platform/integrating/api-guide/).
-"""
-
-external_api = FastAPI(
-    title="AutoGPT Platform API",
-    summary="External API for AutoGPT Platform integrations",
-    description=DESCRIPTION,
-    version="2.0.0",
-    docs_url="/docs",
-    redoc_url="/redoc",
-)
-
-
-@external_api.get("/", include_in_schema=False)
-async def root_redirect() -> RedirectResponse:
-    """Redirect root to API documentation."""
-    return RedirectResponse(url="/docs")
-
-
-# Mount versioned sub-applications
-# Each sub-app has its own /docs page at /v1/docs and /v2/docs
-external_api.mount("/v1", v1_app)
-external_api.mount("/v2", v2_app)
-
-# Add Prometheus instrumentation to the main app
-instrument_fastapi(
-    external_api,
-    service_name="external-api",
-    expose_endpoint=True,
-    endpoint="/metrics",
-    include_in_schema=True,
-)

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

@@ -1,39 +0,0 @@
-"""
-V1 External API Application
-
-This module defines the FastAPI application for the v1 external API.
-"""
-
-from fastapi import FastAPI
-
-from backend.api.middleware.security import SecurityHeadersMiddleware
-
-from .routes import v1_router
-
-DESCRIPTION = """
-The v1 API provides access to core AutoGPT functionality for external integrations.
-
-For authentication details and usage examples, see the
-[API Integration Guide](https://docs.agpt.co/platform/integrating/api-guide/).
-"""
-
-v1_app = FastAPI(
-    title="AutoGPT Platform API",
-    summary="External API for AutoGPT Platform integrations (v1)",
-    description=DESCRIPTION,
-    version="1.0.0",
-    docs_url="/docs",
-    redoc_url="/redoc",
-    openapi_url="/openapi.json",
-    openapi_tags=[
-        {"name": "user", "description": "User information"},
-        {"name": "blocks", "description": "Block operations"},
-        {"name": "graphs", "description": "Graph execution"},
-        {"name": "store", "description": "Marketplace agents and creators"},
-        {"name": "integrations", "description": "OAuth credential management"},
-        {"name": "tools", "description": "AI assistant tools"},
-    ],
-)
-
-v1_app.add_middleware(SecurityHeadersMiddleware)
-v1_app.include_router(v1_router)

autogpt_platform/backend/backend/api/external/v2/__init__.py

@@ -1,9 +0,0 @@
-"""
-V2 External API
-
-This module provides the v2 external API for programmatic access to the AutoGPT Platform.
-"""
-
-from .routes import v2_router
-
-__all__ = ["v2_router"]

autogpt_platform/backend/backend/api/external/v2/app.py

@@ -1,82 +0,0 @@
-"""
-V2 External API Application
-
-This module defines the FastAPI application for the v2 external API.
-"""
-
-from fastapi import FastAPI
-
-from backend.api.middleware.security import SecurityHeadersMiddleware
-
-from .routes import v2_router
-
-DESCRIPTION = """
-The v2 API provides comprehensive access to the AutoGPT Platform for building
-integrations, automations, and custom applications.
-
-### Key Improvements over v1
-
-- **Consistent naming**: Uses `graph_id`/`graph_version` consistently
-- **Better pagination**: All list endpoints support pagination
-- **Comprehensive coverage**: Access to library, runs, schedules, credits, and more
-- **Human-in-the-loop**: Review and approve agent decisions via the API
-
-For authentication details and usage examples, see the
-[API Integration Guide](https://docs.agpt.co/platform/integrating/api-guide/).
-
-### Pagination
-
-List endpoints return paginated responses. Use `page` and `page_size` query
-parameters to navigate results. Maximum page size is 100 items.
-"""
-
-v2_app = FastAPI(
-    title="AutoGPT Platform External API",
-    summary="External API for AutoGPT Platform integrations (v2)",
-    description=DESCRIPTION,
-    version="2.0.0",
-    docs_url="/docs",
-    redoc_url="/redoc",
-    openapi_url="/openapi.json",
-    openapi_tags=[
-        {
-            "name": "graphs",
-            "description": "Create, update, and manage agent graphs",
-        },
-        {
-            "name": "schedules",
-            "description": "Manage scheduled graph executions",
-        },
-        {
-            "name": "blocks",
-            "description": "Discover available building blocks",
-        },
-        {
-            "name": "marketplace",
-            "description": "Browse agents and creators, manage submissions",
-        },
-        {
-            "name": "library",
-            "description": "Access your agent library and execute agents",
-        },
-        {
-            "name": "runs",
-            "description": "Monitor execution runs and human-in-the-loop reviews",
-        },
-        {
-            "name": "credits",
-            "description": "Check balance and view transaction history",
-        },
-        {
-            "name": "integrations",
-            "description": "Manage OAuth credentials for external services",
-        },
-        {
-            "name": "files",
-            "description": "Upload files for agent input",
-        },
-    ],
-)
-
-v2_app.add_middleware(SecurityHeadersMiddleware)
-v2_app.include_router(v2_router)

autogpt_platform/backend/backend/api/external/v2/blocks.py

@@ -1,140 +0,0 @@
-"""
-V2 External API - Blocks Endpoints
-
-Provides read-only access to available building blocks.
-"""
-
-import logging
-from typing import Any
-
-from fastapi import APIRouter, Response, Security
-from fastapi.concurrency import run_in_threadpool
-from prisma.enums import APIKeyPermission
-from pydantic import BaseModel, Field
-
-from backend.api.external.middleware import require_permission
-from backend.data.auth.base import APIAuthorizationInfo
-from backend.data.block import get_blocks
-from backend.util.cache import cached
-from backend.util.json import dumps
-
-logger = logging.getLogger(__name__)
-
-blocks_router = APIRouter()
-
-
-# ============================================================================
-# Models
-# ============================================================================
-
-
-class BlockCost(BaseModel):
-    """Cost information for a block."""
-
-    cost_type: str = Field(description="Type of cost (e.g., 'per_call', 'per_token')")
-    cost_filter: dict[str, Any] = Field(
-        default_factory=dict, description="Conditions for this cost"
-    )
-    cost_amount: int = Field(description="Cost amount in credits")
-
-
-class Block(BaseModel):
-    """A building block that can be used in graphs."""
-
-    id: str
-    name: str
-    description: str
-    categories: list[str] = Field(default_factory=list)
-    input_schema: dict[str, Any]
-    output_schema: dict[str, Any]
-    costs: list[BlockCost] = Field(default_factory=list)
-    disabled: bool = Field(default=False)
-
-
-class BlocksListResponse(BaseModel):
-    """Response for listing blocks."""
-
-    blocks: list[Block]
-    total_count: int
-
-
-# ============================================================================
-# Internal Functions
-# ============================================================================
-
-
-def _compute_blocks_sync() -> str:
-    """
-    Synchronous function to compute blocks data.
-    This does the heavy lifting: instantiate 226+ blocks, compute costs, serialize.
-    """
-    from backend.data.credit import get_block_cost
-
-    block_classes = get_blocks()
-    result = []
-
-    for block_class in block_classes.values():
-        block_instance = block_class()
-        if not block_instance.disabled:
-            costs = get_block_cost(block_instance)
-            # Convert BlockCost BaseModel objects to dictionaries
-            costs_dict = [
-                cost.model_dump() if isinstance(cost, BaseModel) else cost
-                for cost in costs
-            ]
-            result.append({**block_instance.to_dict(), "costs": costs_dict})
-
-    return dumps(result)
-
-
-@cached(ttl_seconds=3600)
-async def _get_cached_blocks() -> str:
-    """
-    Async cached function with thundering herd protection.
-    On cache miss: runs heavy work in thread pool
-    On cache hit: returns cached string immediately
-    """
-    return await run_in_threadpool(_compute_blocks_sync)
-
-
-# ============================================================================
-# Endpoints
-# ============================================================================
-
-
-@blocks_router.get(
-    path="",
-    summary="List available blocks",
-    responses={
-        200: {
-            "description": "List of available building blocks",
-            "content": {
-                "application/json": {
-                    "schema": {
-                        "items": {"additionalProperties": True, "type": "object"},
-                        "type": "array",
-                    }
-                }
-            },
-        }
-    },
-)
-async def list_blocks(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_BLOCK)
-    ),
-) -> Response:
-    """
-    List all available building blocks that can be used in graphs.
-
-    Each block represents a specific capability (e.g., HTTP request, text processing,
-    AI completion, etc.) that can be connected in a graph to create an agent.
-
-    The response includes input/output schemas for each block, as well as
-    cost information for blocks that consume credits.
-    """
-    content = await _get_cached_blocks()
-    return Response(
-        content=content,
-        media_type="application/json",
-    )

autogpt_platform/backend/backend/api/external/v2/common.py

@@ -1,36 +0,0 @@
-"""
-Common utilities for V2 External API
-"""
-
-from typing import TypeVar
-
-from pydantic import BaseModel, Field
-
-# Constants for pagination
-MAX_PAGE_SIZE = 100
-DEFAULT_PAGE_SIZE = 20
-
-
-class PaginationParams(BaseModel):
-    """Common pagination parameters."""
-
-    page: int = Field(default=1, ge=1, description="Page number (1-indexed)")
-    page_size: int = Field(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Number of items per page (max {MAX_PAGE_SIZE})",
-    )
-
-
-T = TypeVar("T")
-
-
-class PaginatedResponse(BaseModel):
-    """Generic paginated response wrapper."""
-
-    items: list
-    total_count: int = Field(description="Total number of items across all pages")
-    page: int = Field(description="Current page number (1-indexed)")
-    page_size: int = Field(description="Number of items per page")
-    total_pages: int = Field(description="Total number of pages")

autogpt_platform/backend/backend/api/external/v2/credits.py

@@ -1,141 +0,0 @@
-"""
-V2 External API - Credits Endpoints
-
-Provides access to credit balance and transaction history.
-"""
-
-import logging
-from datetime import datetime
-from typing import Optional
-
-from fastapi import APIRouter, Query, Security
-from prisma.enums import APIKeyPermission
-from pydantic import BaseModel, Field
-
-from backend.api.external.middleware import require_permission
-from backend.data.auth.base import APIAuthorizationInfo
-from backend.data.credit import get_user_credit_model
-
-from .common import DEFAULT_PAGE_SIZE, MAX_PAGE_SIZE
-
-logger = logging.getLogger(__name__)
-
-credits_router = APIRouter()
-
-
-# ============================================================================
-# Models
-# ============================================================================
-
-
-class CreditBalance(BaseModel):
-    """User's credit balance."""
-
-    balance: int = Field(description="Current credit balance")
-
-
-class CreditTransaction(BaseModel):
-    """A credit transaction."""
-
-    transaction_key: str
-    amount: int = Field(description="Transaction amount (positive or negative)")
-    type: str = Field(description="One of: TOP_UP, USAGE, GRANT, REFUND")
-    transaction_time: datetime
-    running_balance: Optional[int] = Field(
-        default=None, description="Balance after this transaction"
-    )
-    description: Optional[str] = None
-
-
-class CreditTransactionsResponse(BaseModel):
-    """Response for listing credit transactions."""
-
-    transactions: list[CreditTransaction]
-    total_count: int
-    page: int
-    page_size: int
-    total_pages: int
-
-
-# ============================================================================
-# Endpoints
-# ============================================================================
-
-
-@credits_router.get(
-    path="",
-    summary="Get credit balance",
-    response_model=CreditBalance,
-)
-async def get_balance(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_CREDITS)
-    ),
-) -> CreditBalance:
-    """
-    Get the current credit balance for the authenticated user.
-    """
-    user_credit_model = await get_user_credit_model(auth.user_id)
-    balance = await user_credit_model.get_credits(auth.user_id)
-
-    return CreditBalance(balance=balance)
-
-
-@credits_router.get(
-    path="/transactions",
-    summary="Get transaction history",
-    response_model=CreditTransactionsResponse,
-)
-async def get_transactions(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_CREDITS)
-    ),
-    page: int = Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = Query(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Items per page (max {MAX_PAGE_SIZE})",
-    ),
-    transaction_type: Optional[str] = Query(
-        default=None,
-        description="Filter by transaction type (TOP_UP, USAGE, GRANT, REFUND)",
-    ),
-) -> CreditTransactionsResponse:
-    """
-    Get credit transaction history for the authenticated user.
-
-    Returns transactions sorted by most recent first.
-    """
-    user_credit_model = await get_user_credit_model(auth.user_id)
-
-    history = await user_credit_model.get_transaction_history(
-        user_id=auth.user_id,
-        transaction_count_limit=page_size,
-        transaction_type=transaction_type,
-    )
-
-    transactions = [
-        CreditTransaction(
-            transaction_key=t.transaction_key,
-            amount=t.amount,
-            type=t.transaction_type.value,
-            transaction_time=t.transaction_time,
-            running_balance=t.running_balance,
-            description=t.description,
-        )
-        for t in history.transactions
-    ]
-
-    # Note: The current credit module doesn't support true pagination,
-    # so we're returning what we have
-    total_count = len(transactions)
-    total_pages = 1  # Without true pagination support
-
-    return CreditTransactionsResponse(
-        transactions=transactions,
-        total_count=total_count,
-        page=page,
-        page_size=page_size,
-        total_pages=total_pages,
-    )

autogpt_platform/backend/backend/api/external/v2/files.py

@@ -1,132 +0,0 @@
-"""
-V2 External API - Files Endpoints
-
-Provides file upload functionality for agent inputs.
-"""
-
-import base64
-import logging
-
-from fastapi import APIRouter, File, HTTPException, Query, Security, UploadFile
-from prisma.enums import APIKeyPermission
-from pydantic import BaseModel, Field
-
-from backend.api.external.middleware import require_permission
-from backend.data.auth.base import APIAuthorizationInfo
-from backend.util.cloud_storage import get_cloud_storage_handler
-from backend.util.settings import Settings
-from backend.util.virus_scanner import scan_content_safe
-
-logger = logging.getLogger(__name__)
-settings = Settings()
-
-files_router = APIRouter()
-
-
-# ============================================================================
-# Models
-# ============================================================================
-
-
-class UploadFileResponse(BaseModel):
-    """Response after uploading a file."""
-
-    file_uri: str = Field(description="URI to reference the uploaded file in agents")
-    file_name: str
-    size: int = Field(description="File size in bytes")
-    content_type: str
-    expires_in_hours: int
-
-
-# ============================================================================
-# Endpoints
-# ============================================================================
-
-
-def _create_file_size_error(size_bytes: int, max_size_mb: int) -> HTTPException:
-    """Create standardized file size error response."""
-    return HTTPException(
-        status_code=400,
-        detail=f"File size ({size_bytes} bytes) exceeds the maximum allowed size of {max_size_mb}MB",
-    )
-
-
-@files_router.post(
-    path="/upload",
-    summary="Upload a file",
-    response_model=UploadFileResponse,
-)
-async def upload_file(
-    file: UploadFile = File(...),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.UPLOAD_FILES)
-    ),
-    provider: str = Query(
-        default="gcs", description="Storage provider (gcs, s3, azure)"
-    ),
-    expiration_hours: int = Query(
-        default=24, ge=1, le=48, description="Hours until file expires (1-48)"
-    ),
-) -> UploadFileResponse:
-    """
-    Upload a file to cloud storage for use with agents.
-
-    The returned `file_uri` can be used as input to agents that accept file inputs
-    (e.g., FileStoreBlock, AgentFileInputBlock).
-
-    Files are automatically scanned for viruses before storage.
-    """
-    # Check file size limit
-    max_size_mb = settings.config.upload_file_size_limit_mb
-    max_size_bytes = max_size_mb * 1024 * 1024
-
-    # Try to get file size from headers first
-    if hasattr(file, "size") and file.size is not None and file.size > max_size_bytes:
-        raise _create_file_size_error(file.size, max_size_mb)
-
-    # Read file content
-    content = await file.read()
-    content_size = len(content)
-
-    # Double-check file size after reading
-    if content_size > max_size_bytes:
-        raise _create_file_size_error(content_size, max_size_mb)
-
-    # Extract file info
-    file_name = file.filename or "uploaded_file"
-    content_type = file.content_type or "application/octet-stream"
-
-    # Virus scan the content
-    await scan_content_safe(content, filename=file_name)
-
-    # Check if cloud storage is configured
-    cloud_storage = await get_cloud_storage_handler()
-    if not cloud_storage.config.gcs_bucket_name:
-        # Fallback to base64 data URI when GCS is not configured
-        base64_content = base64.b64encode(content).decode("utf-8")
-        data_uri = f"data:{content_type};base64,{base64_content}"
-
-        return UploadFileResponse(
-            file_uri=data_uri,
-            file_name=file_name,
-            size=content_size,
-            content_type=content_type,
-            expires_in_hours=expiration_hours,
-        )
-
-    # Store in cloud storage
-    storage_path = await cloud_storage.store_file(
-        content=content,
-        filename=file_name,
-        provider=provider,
-        expiration_hours=expiration_hours,
-        user_id=auth.user_id,
-    )
-
-    return UploadFileResponse(
-        file_uri=storage_path,
-        file_name=file_name,
-        size=content_size,
-        content_type=content_type,
-        expires_in_hours=expiration_hours,
-    )

autogpt_platform/backend/backend/api/external/v2/graphs.py

@@ -1,445 +0,0 @@
-"""
-V2 External API - Graphs Endpoints
-
-Provides endpoints for managing agent graphs (CRUD operations).
-"""
-
-import logging
-
-from fastapi import APIRouter, HTTPException, Query, Security
-from prisma.enums import APIKeyPermission
-
-from backend.api.external.middleware import require_permission
-from backend.data import graph as graph_db
-from backend.data.auth.base import APIAuthorizationInfo
-from backend.integrations.webhooks.graph_lifecycle_hooks import (
-    on_graph_activate,
-    on_graph_deactivate,
-)
-
-from .common import DEFAULT_PAGE_SIZE, MAX_PAGE_SIZE
-from .models import (
-    CreateGraphRequest,
-    DeleteGraphResponse,
-    GraphDetails,
-    GraphLink,
-    GraphMeta,
-    GraphNode,
-    GraphSettings,
-    GraphsListResponse,
-    SetActiveVersionRequest,
-)
-
-logger = logging.getLogger(__name__)
-
-graphs_router = APIRouter()
-
-
-def _convert_graph_meta(graph: graph_db.GraphMeta) -> GraphMeta:
-    """Convert internal GraphMeta to v2 API model."""
-    return GraphMeta(
-        id=graph.id,
-        version=graph.version,
-        is_active=graph.is_active,
-        name=graph.name,
-        description=graph.description,
-        created_at=graph.created_at,
-        input_schema=graph.input_schema,
-        output_schema=graph.output_schema,
-    )
-
-
-def _convert_graph_details(graph: graph_db.GraphModel) -> GraphDetails:
-    """Convert internal GraphModel to v2 API GraphDetails model."""
-    return GraphDetails(
-        id=graph.id,
-        version=graph.version,
-        is_active=graph.is_active,
-        name=graph.name,
-        description=graph.description,
-        created_at=graph.created_at,
-        input_schema=graph.input_schema,
-        output_schema=graph.output_schema,
-        nodes=[
-            GraphNode(
-                id=node.id,
-                block_id=node.block_id,
-                input_default=node.input_default,
-                metadata=node.metadata,
-            )
-            for node in graph.nodes
-        ],
-        links=[
-            GraphLink(
-                id=link.id,
-                source_id=link.source_id,
-                sink_id=link.sink_id,
-                source_name=link.source_name,
-                sink_name=link.sink_name,
-                is_static=link.is_static,
-            )
-            for link in graph.links
-        ],
-        credentials_input_schema=graph.credentials_input_schema,
-    )
-
-
-@graphs_router.get(
-    path="",
-    summary="List user's graphs",
-    response_model=GraphsListResponse,
-)
-async def list_graphs(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_GRAPH)
-    ),
-    page: int = Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = Query(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Items per page (max {MAX_PAGE_SIZE})",
-    ),
-) -> GraphsListResponse:
-    """
-    List all graphs owned by the authenticated user.
-
-    Returns a paginated list of graph metadata (not full graph details).
-    """
-    graphs, pagination_info = await graph_db.list_graphs_paginated(
-        user_id=auth.user_id,
-        page=page,
-        page_size=page_size,
-        filter_by="active",
-    )
-    return GraphsListResponse(
-        graphs=[_convert_graph_meta(g) for g in graphs],
-        total_count=pagination_info.total_items,
-        page=pagination_info.current_page,
-        page_size=pagination_info.page_size,
-        total_pages=pagination_info.total_pages,
-    )
-
-
-@graphs_router.post(
-    path="",
-    summary="Create a new graph",
-    response_model=GraphDetails,
-)
-async def create_graph(
-    create_graph_request: CreateGraphRequest,
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_GRAPH)
-    ),
-) -> GraphDetails:
-    """
-    Create a new agent graph.
-
-    The graph will be validated and assigned a new ID. It will automatically
-    be added to the user's library.
-    """
-    # Import here to avoid circular imports
-    from backend.api.features.library import db as library_db
-
-    # Convert v2 API Graph model to internal Graph model
-    internal_graph = graph_db.Graph(
-        id=create_graph_request.graph.id or "",
-        version=create_graph_request.graph.version,
-        is_active=create_graph_request.graph.is_active,
-        name=create_graph_request.graph.name,
-        description=create_graph_request.graph.description,
-        nodes=[
-            graph_db.Node(
-                id=node.id,
-                block_id=node.block_id,
-                input_default=node.input_default,
-                metadata=node.metadata,
-            )
-            for node in create_graph_request.graph.nodes
-        ],
-        links=[
-            graph_db.Link(
-                id=link.id,
-                source_id=link.source_id,
-                sink_id=link.sink_id,
-                source_name=link.source_name,
-                sink_name=link.sink_name,
-                is_static=link.is_static,
-            )
-            for link in create_graph_request.graph.links
-        ],
-    )
-
-    graph = graph_db.make_graph_model(internal_graph, auth.user_id)
-    graph.reassign_ids(user_id=auth.user_id, reassign_graph_id=True)
-    graph.validate_graph(for_run=False)
-
-    await graph_db.create_graph(graph, user_id=auth.user_id)
-    await library_db.create_library_agent(graph, user_id=auth.user_id)
-    activated_graph = await on_graph_activate(graph, user_id=auth.user_id)
-
-    return _convert_graph_details(activated_graph)
-
-
-@graphs_router.get(
-    path="/{graph_id}",
-    summary="Get graph details",
-    response_model=GraphDetails,
-)
-async def get_graph(
-    graph_id: str,
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_GRAPH)
-    ),
-    version: int | None = Query(
-        default=None,
-        description="Specific version to retrieve (default: active version)",
-    ),
-) -> GraphDetails:
-    """
-    Get detailed information about a specific graph.
-
-    By default returns the active version. Use the `version` query parameter
-    to retrieve a specific version.
-    """
-    graph = await graph_db.get_graph(
-        graph_id,
-        version,
-        user_id=auth.user_id,
-        include_subgraphs=True,
-    )
-    if not graph:
-        raise HTTPException(status_code=404, detail=f"Graph #{graph_id} not found.")
-    return _convert_graph_details(graph)
-
-
-@graphs_router.put(
-    path="/{graph_id}",
-    summary="Update graph (creates new version)",
-    response_model=GraphDetails,
-)
-async def update_graph(
-    graph_id: str,
-    graph_request: CreateGraphRequest,
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_GRAPH)
-    ),
-) -> GraphDetails:
-    """
-    Update a graph by creating a new version.
-
-    This does not modify existing versions - it creates a new version with
-    the provided content. The new version becomes the active version.
-    """
-    # Import here to avoid circular imports
-    from backend.api.features.library import db as library_db
-
-    graph_data = graph_request.graph
-    if graph_data.id and graph_data.id != graph_id:
-        raise HTTPException(400, detail="Graph ID does not match ID in URI")
-
-    existing_versions = await graph_db.get_graph_all_versions(
-        graph_id, user_id=auth.user_id
-    )
-    if not existing_versions:
-        raise HTTPException(404, detail=f"Graph #{graph_id} not found")
-
-    latest_version_number = max(g.version for g in existing_versions)
-
-    # Convert v2 API Graph model to internal Graph model
-    internal_graph = graph_db.Graph(
-        id=graph_id,
-        version=latest_version_number + 1,
-        is_active=graph_data.is_active,
-        name=graph_data.name,
-        description=graph_data.description,
-        nodes=[
-            graph_db.Node(
-                id=node.id,
-                block_id=node.block_id,
-                input_default=node.input_default,
-                metadata=node.metadata,
-            )
-            for node in graph_data.nodes
-        ],
-        links=[
-            graph_db.Link(
-                id=link.id,
-                source_id=link.source_id,
-                sink_id=link.sink_id,
-                source_name=link.source_name,
-                sink_name=link.sink_name,
-                is_static=link.is_static,
-            )
-            for link in graph_data.links
-        ],
-    )
-
-    current_active_version = next((v for v in existing_versions if v.is_active), None)
-    graph = graph_db.make_graph_model(internal_graph, auth.user_id)
-    graph.reassign_ids(user_id=auth.user_id, reassign_graph_id=False)
-    graph.validate_graph(for_run=False)
-
-    new_graph_version = await graph_db.create_graph(graph, user_id=auth.user_id)
-
-    if new_graph_version.is_active:
-        await library_db.update_agent_version_in_library(
-            auth.user_id, new_graph_version.id, new_graph_version.version
-        )
-        new_graph_version = await on_graph_activate(
-            new_graph_version, user_id=auth.user_id
-        )
-        await graph_db.set_graph_active_version(
-            graph_id=graph_id, version=new_graph_version.version, user_id=auth.user_id
-        )
-        if current_active_version:
-            await on_graph_deactivate(current_active_version, user_id=auth.user_id)
-
-    new_graph_version_with_subgraphs = await graph_db.get_graph(
-        graph_id,
-        new_graph_version.version,
-        user_id=auth.user_id,
-        include_subgraphs=True,
-    )
-    assert new_graph_version_with_subgraphs
-    return _convert_graph_details(new_graph_version_with_subgraphs)
-
-
-@graphs_router.delete(
-    path="/{graph_id}",
-    summary="Delete graph permanently",
-    response_model=DeleteGraphResponse,
-)
-async def delete_graph(
-    graph_id: str,
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_GRAPH)
-    ),
-) -> DeleteGraphResponse:
-    """
-    Permanently delete a graph and all its versions.
-
-    This action cannot be undone. All associated executions will remain
-    but will reference a deleted graph.
-    """
-    if active_version := await graph_db.get_graph(
-        graph_id=graph_id, version=None, user_id=auth.user_id
-    ):
-        await on_graph_deactivate(active_version, user_id=auth.user_id)
-
-    version_count = await graph_db.delete_graph(graph_id, user_id=auth.user_id)
-    return DeleteGraphResponse(version_count=version_count)
-
-
-@graphs_router.get(
-    path="/{graph_id}/versions",
-    summary="List all graph versions",
-    response_model=list[GraphDetails],
-)
-async def list_graph_versions(
-    graph_id: str,
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_GRAPH)
-    ),
-) -> list[GraphDetails]:
-    """
-    Get all versions of a specific graph.
-
-    Returns a list of all versions, with the active version marked.
-    """
-    graphs = await graph_db.get_graph_all_versions(graph_id, user_id=auth.user_id)
-    if not graphs:
-        raise HTTPException(status_code=404, detail=f"Graph #{graph_id} not found.")
-    return [_convert_graph_details(g) for g in graphs]
-
-
-@graphs_router.put(
-    path="/{graph_id}/versions/active",
-    summary="Set active graph version",
-)
-async def set_active_version(
-    graph_id: str,
-    request_body: SetActiveVersionRequest,
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_GRAPH)
-    ),
-) -> None:
-    """
-    Set which version of a graph is the active version.
-
-    The active version is used when executing the graph without specifying
-    a version number.
-    """
-    # Import here to avoid circular imports
-    from backend.api.features.library import db as library_db
-
-    new_active_version = request_body.active_graph_version
-    new_active_graph = await graph_db.get_graph(
-        graph_id, new_active_version, user_id=auth.user_id
-    )
-    if not new_active_graph:
-        raise HTTPException(404, f"Graph #{graph_id} v{new_active_version} not found")
-
-    current_active_graph = await graph_db.get_graph(
-        graph_id=graph_id,
-        version=None,
-        user_id=auth.user_id,
-    )
-
-    await on_graph_activate(new_active_graph, user_id=auth.user_id)
-    await graph_db.set_graph_active_version(
-        graph_id=graph_id,
-        version=new_active_version,
-        user_id=auth.user_id,
-    )
-
-    await library_db.update_agent_version_in_library(
-        auth.user_id, new_active_graph.id, new_active_graph.version
-    )
-
-    if current_active_graph and current_active_graph.version != new_active_version:
-        await on_graph_deactivate(current_active_graph, user_id=auth.user_id)
-
-
-@graphs_router.patch(
-    path="/{graph_id}/settings",
-    summary="Update graph settings",
-    response_model=GraphSettings,
-)
-async def update_graph_settings(
-    graph_id: str,
-    settings: GraphSettings,
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_GRAPH)
-    ),
-) -> GraphSettings:
-    """
-    Update settings for a graph.
-
-    Currently supports:
-    - human_in_the_loop_safe_mode: Enable/disable safe mode for human-in-the-loop blocks
-    """
-    # Import here to avoid circular imports
-    from backend.api.features.library import db as library_db
-    from backend.data.graph import GraphSettings as InternalGraphSettings
-
-    library_agent = await library_db.get_library_agent_by_graph_id(
-        graph_id=graph_id, user_id=auth.user_id
-    )
-    if not library_agent:
-        raise HTTPException(404, f"Graph #{graph_id} not found in user's library")
-
-    # Convert to internal model
-    internal_settings = InternalGraphSettings(
-        human_in_the_loop_safe_mode=settings.human_in_the_loop_safe_mode
-    )
-
-    updated_agent = await library_db.update_library_agent_settings(
-        user_id=auth.user_id,
-        agent_id=library_agent.id,
-        settings=internal_settings,
-    )
-
-    return GraphSettings(
-        human_in_the_loop_safe_mode=updated_agent.settings.human_in_the_loop_safe_mode
-    )

autogpt_platform/backend/backend/api/external/v2/integrations.py

@@ -1,271 +0,0 @@
-"""
-V2 External API - Integrations Endpoints
-
-Provides access to user's integration credentials.
-"""
-
-import logging
-from typing import Optional
-
-from fastapi import APIRouter, HTTPException, Path, Security
-from prisma.enums import APIKeyPermission
-from pydantic import BaseModel, Field
-
-from backend.api.external.middleware import require_permission
-from backend.api.features.library import db as library_db
-from backend.data import graph as graph_db
-from backend.data.auth.base import APIAuthorizationInfo
-from backend.data.model import Credentials, OAuth2Credentials
-from backend.integrations.creds_manager import IntegrationCredentialsManager
-
-logger = logging.getLogger(__name__)
-
-integrations_router = APIRouter()
-creds_manager = IntegrationCredentialsManager()
-
-
-# ============================================================================
-# Models
-# ============================================================================
-
-
-class Credential(BaseModel):
-    """A user's credential for an integration."""
-
-    id: str
-    provider: str = Field(description="Integration provider name")
-    title: Optional[str] = Field(
-        default=None, description="User-assigned title for this credential"
-    )
-    scopes: list[str] = Field(default_factory=list, description="Granted scopes")
-
-
-class CredentialsListResponse(BaseModel):
-    """Response for listing credentials."""
-
-    credentials: list[Credential]
-
-
-class CredentialRequirement(BaseModel):
-    """A credential requirement for a graph or agent."""
-
-    provider: str = Field(description="Required provider name")
-    required_scopes: list[str] = Field(
-        default_factory=list, description="Required scopes"
-    )
-    matching_credentials: list[Credential] = Field(
-        default_factory=list,
-        description="User's credentials that match this requirement",
-    )
-
-
-class CredentialRequirementsResponse(BaseModel):
-    """Response for listing credential requirements."""
-
-    requirements: list[CredentialRequirement]
-
-
-# ============================================================================
-# Conversion Functions
-# ============================================================================
-
-
-def _convert_credential(cred: Credentials) -> Credential:
-    """Convert internal credential to v2 API model."""
-    scopes: list[str] = []
-    if isinstance(cred, OAuth2Credentials):
-        scopes = cred.scopes or []
-
-    return Credential(
-        id=cred.id,
-        provider=cred.provider,
-        title=cred.title,
-        scopes=scopes,
-    )
-
-
-# ============================================================================
-# Endpoints
-# ============================================================================
-
-
-@integrations_router.get(
-    path="/credentials",
-    summary="List all credentials",
-    response_model=CredentialsListResponse,
-)
-async def list_credentials(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_INTEGRATIONS)
-    ),
-) -> CredentialsListResponse:
-    """
-    List all integration credentials for the authenticated user.
-
-    This returns all OAuth credentials the user has connected, across
-    all integration providers.
-    """
-    credentials = await creds_manager.store.get_all_creds(auth.user_id)
-
-    return CredentialsListResponse(
-        credentials=[_convert_credential(c) for c in credentials]
-    )
-
-
-@integrations_router.get(
-    path="/credentials/{provider}",
-    summary="List credentials by provider",
-    response_model=CredentialsListResponse,
-)
-async def list_credentials_by_provider(
-    provider: str = Path(description="Provider name (e.g., 'github', 'google')"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_INTEGRATIONS)
-    ),
-) -> CredentialsListResponse:
-    """
-    List integration credentials for a specific provider.
-    """
-    all_credentials = await creds_manager.store.get_all_creds(auth.user_id)
-
-    # Filter by provider
-    filtered = [c for c in all_credentials if c.provider.lower() == provider.lower()]
-
-    return CredentialsListResponse(
-        credentials=[_convert_credential(c) for c in filtered]
-    )
-
-
-@integrations_router.get(
-    path="/graphs/{graph_id}/credentials",
-    summary="List credentials matching graph requirements",
-    response_model=CredentialRequirementsResponse,
-)
-async def list_graph_credential_requirements(
-    graph_id: str = Path(description="Graph ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_INTEGRATIONS)
-    ),
-) -> CredentialRequirementsResponse:
-    """
-    List credential requirements for a graph and matching user credentials.
-
-    This helps identify which credentials the user needs to provide
-    when executing a graph.
-    """
-    # Get the graph
-    graph = await graph_db.get_graph(
-        graph_id=graph_id,
-        version=None,  # Active version
-        user_id=auth.user_id,
-        include_subgraphs=True,
-    )
-    if not graph:
-        raise HTTPException(status_code=404, detail=f"Graph #{graph_id} not found")
-
-    # Get the credentials input schema which contains provider requirements
-    creds_schema = graph.credentials_input_schema
-    all_credentials = await creds_manager.store.get_all_creds(auth.user_id)
-
-    requirements = []
-    for field_name, field_schema in creds_schema.get("properties", {}).items():
-        # Extract provider from schema
-        # The schema structure varies, but typically has provider info
-        providers = []
-        if "anyOf" in field_schema:
-            for option in field_schema["anyOf"]:
-                if "provider" in option:
-                    providers.append(option["provider"])
-        elif "provider" in field_schema:
-            providers.append(field_schema["provider"])
-
-        for provider in providers:
-            # Find matching credentials
-            matching = [
-                _convert_credential(c)
-                for c in all_credentials
-                if c.provider.lower() == provider.lower()
-            ]
-
-            requirements.append(
-                CredentialRequirement(
-                    provider=provider,
-                    required_scopes=[],  # Would need to extract from schema
-                    matching_credentials=matching,
-                )
-            )
-
-    return CredentialRequirementsResponse(requirements=requirements)
-
-
-@integrations_router.get(
-    path="/library/{agent_id}/credentials",
-    summary="List credentials matching library agent requirements",
-    response_model=CredentialRequirementsResponse,
-)
-async def list_library_agent_credential_requirements(
-    agent_id: str = Path(description="Library agent ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_INTEGRATIONS)
-    ),
-) -> CredentialRequirementsResponse:
-    """
-    List credential requirements for a library agent and matching user credentials.
-
-    This helps identify which credentials the user needs to provide
-    when executing an agent from their library.
-    """
-    # Get the library agent
-    try:
-        library_agent = await library_db.get_library_agent(
-            id=agent_id,
-            user_id=auth.user_id,
-        )
-    except Exception:
-        raise HTTPException(status_code=404, detail=f"Agent #{agent_id} not found")
-
-    # Get the underlying graph
-    graph = await graph_db.get_graph(
-        graph_id=library_agent.graph_id,
-        version=library_agent.graph_version,
-        user_id=auth.user_id,
-        include_subgraphs=True,
-    )
-    if not graph:
-        raise HTTPException(
-            status_code=404,
-            detail=f"Graph for agent #{agent_id} not found",
-        )
-
-    # Get the credentials input schema
-    creds_schema = graph.credentials_input_schema
-    all_credentials = await creds_manager.store.get_all_creds(auth.user_id)
-
-    requirements = []
-    for field_name, field_schema in creds_schema.get("properties", {}).items():
-        # Extract provider from schema
-        providers = []
-        if "anyOf" in field_schema:
-            for option in field_schema["anyOf"]:
-                if "provider" in option:
-                    providers.append(option["provider"])
-        elif "provider" in field_schema:
-            providers.append(field_schema["provider"])
-
-        for provider in providers:
-            # Find matching credentials
-            matching = [
-                _convert_credential(c)
-                for c in all_credentials
-                if c.provider.lower() == provider.lower()
-            ]
-
-            requirements.append(
-                CredentialRequirement(
-                    provider=provider,
-                    required_scopes=[],
-                    matching_credentials=matching,
-                )
-            )
-
-    return CredentialRequirementsResponse(requirements=requirements)

autogpt_platform/backend/backend/api/external/v2/library.py

@@ -1,247 +0,0 @@
-"""
-V2 External API - Library Endpoints
-
-Provides access to the user's agent library and agent execution.
-"""
-
-import logging
-
-from fastapi import APIRouter, HTTPException, Path, Query, Security
-from prisma.enums import APIKeyPermission
-
-from backend.api.external.middleware import require_permission
-from backend.api.features.library import db as library_db
-from backend.api.features.library import model as library_model
-from backend.data import execution as execution_db
-from backend.data.auth.base import APIAuthorizationInfo
-from backend.data.credit import get_user_credit_model
-from backend.executor import utils as execution_utils
-
-from .common import DEFAULT_PAGE_SIZE, MAX_PAGE_SIZE
-from .models import (
-    ExecuteAgentRequest,
-    LibraryAgent,
-    LibraryAgentsResponse,
-    Run,
-    RunsListResponse,
-)
-
-logger = logging.getLogger(__name__)
-
-library_router = APIRouter()
-
-
-# ============================================================================
-# Conversion Functions
-# ============================================================================
-
-
-def _convert_library_agent(agent: library_model.LibraryAgent) -> LibraryAgent:
-    """Convert internal LibraryAgent to v2 API model."""
-    return LibraryAgent(
-        id=agent.id,
-        graph_id=agent.graph_id,
-        graph_version=agent.graph_version,
-        name=agent.name,
-        description=agent.description,
-        is_favorite=agent.is_favorite,
-        can_access_graph=agent.can_access_graph,
-        is_latest_version=agent.is_latest_version,
-        image_url=agent.image_url,
-        creator_name=agent.creator_name,
-        input_schema=agent.input_schema,
-        output_schema=agent.output_schema,
-        created_at=agent.created_at,
-        updated_at=agent.updated_at,
-    )
-
-
-def _convert_execution_to_run(exec: execution_db.GraphExecutionMeta) -> Run:
-    """Convert internal execution to v2 API Run model."""
-    return Run(
-        id=exec.id,
-        graph_id=exec.graph_id,
-        graph_version=exec.graph_version,
-        status=exec.status.value,
-        started_at=exec.started_at,
-        ended_at=exec.ended_at,
-        inputs=exec.inputs,
-        cost=exec.stats.cost if exec.stats else 0,
-        duration=exec.stats.duration if exec.stats else 0,
-        node_count=exec.stats.node_exec_count if exec.stats else 0,
-    )
-
-
-# ============================================================================
-# Endpoints
-# ============================================================================
-
-
-@library_router.get(
-    path="/agents",
-    summary="List library agents",
-    response_model=LibraryAgentsResponse,
-)
-async def list_library_agents(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_LIBRARY)
-    ),
-    page: int = Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = Query(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Items per page (max {MAX_PAGE_SIZE})",
-    ),
-) -> LibraryAgentsResponse:
-    """
-    List agents in the user's library.
-
-    The library contains agents the user has created or added from the marketplace.
-    """
-    result = await library_db.list_library_agents(
-        user_id=auth.user_id,
-        page=page,
-        page_size=page_size,
-    )
-
-    return LibraryAgentsResponse(
-        agents=[_convert_library_agent(a) for a in result.agents],
-        total_count=result.pagination.total_items,
-        page=result.pagination.current_page,
-        page_size=result.pagination.page_size,
-        total_pages=result.pagination.total_pages,
-    )
-
-
-@library_router.get(
-    path="/agents/favorites",
-    summary="List favorite agents",
-    response_model=LibraryAgentsResponse,
-)
-async def list_favorite_agents(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_LIBRARY)
-    ),
-    page: int = Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = Query(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Items per page (max {MAX_PAGE_SIZE})",
-    ),
-) -> LibraryAgentsResponse:
-    """
-    List favorite agents in the user's library.
-    """
-    result = await library_db.list_favorite_library_agents(
-        user_id=auth.user_id,
-        page=page,
-        page_size=page_size,
-    )
-
-    return LibraryAgentsResponse(
-        agents=[_convert_library_agent(a) for a in result.agents],
-        total_count=result.pagination.total_items,
-        page=result.pagination.current_page,
-        page_size=result.pagination.page_size,
-        total_pages=result.pagination.total_pages,
-    )
-
-
-@library_router.post(
-    path="/agents/{agent_id}/runs",
-    summary="Execute an agent",
-    response_model=Run,
-)
-async def execute_agent(
-    request: ExecuteAgentRequest,
-    agent_id: str = Path(description="Library agent ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.RUN_AGENT)
-    ),
-) -> Run:
-    """
-    Execute an agent from the library.
-
-    This creates a new run with the provided inputs. The run executes
-    asynchronously and you can poll the run status using GET /runs/{run_id}.
-    """
-    # Check credit balance
-    user_credit_model = await get_user_credit_model(auth.user_id)
-    current_balance = await user_credit_model.get_credits(auth.user_id)
-    if current_balance <= 0:
-        raise HTTPException(
-            status_code=402,
-            detail="Insufficient balance to execute the agent. Please top up your account.",
-        )
-
-    # Get the library agent to find the graph ID and version
-    try:
-        library_agent = await library_db.get_library_agent(
-            id=agent_id,
-            user_id=auth.user_id,
-        )
-    except Exception:
-        raise HTTPException(status_code=404, detail=f"Agent #{agent_id} not found")
-
-    try:
-        result = await execution_utils.add_graph_execution(
-            graph_id=library_agent.graph_id,
-            user_id=auth.user_id,
-            inputs=request.inputs,
-            graph_version=library_agent.graph_version,
-            graph_credentials_inputs=request.credentials_inputs,
-        )
-
-        return _convert_execution_to_run(result)
-
-    except Exception as e:
-        logger.error(f"Failed to execute agent: {e}")
-        raise HTTPException(status_code=400, detail=str(e))
-
-
-@library_router.get(
-    path="/agents/{agent_id}/runs",
-    summary="List runs for an agent",
-    response_model=RunsListResponse,
-)
-async def list_agent_runs(
-    agent_id: str = Path(description="Library agent ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_LIBRARY)
-    ),
-    page: int = Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = Query(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Items per page (max {MAX_PAGE_SIZE})",
-    ),
-) -> RunsListResponse:
-    """
-    List execution runs for a specific agent.
-    """
-    # Get the library agent to find the graph ID
-    try:
-        library_agent = await library_db.get_library_agent(
-            id=agent_id,
-            user_id=auth.user_id,
-        )
-    except Exception:
-        raise HTTPException(status_code=404, detail=f"Agent #{agent_id} not found")
-
-    result = await execution_db.get_graph_executions_paginated(
-        graph_id=library_agent.graph_id,
-        user_id=auth.user_id,
-        page=page,
-        page_size=page_size,
-    )
-
-    return RunsListResponse(
-        runs=[_convert_execution_to_run(e) for e in result.executions],
-        total_count=result.pagination.total_items,
-        page=result.pagination.current_page,
-        page_size=result.pagination.page_size,
-        total_pages=result.pagination.total_pages,
-    )

autogpt_platform/backend/backend/api/external/v2/marketplace.py

@@ -1,510 +0,0 @@
-"""
-V2 External API - Marketplace Endpoints
-
-Provides access to the agent marketplace (store).
-"""
-
-import logging
-import urllib.parse
-from datetime import datetime
-from typing import Literal, Optional
-
-from fastapi import APIRouter, HTTPException, Path, Query, Security
-from prisma.enums import APIKeyPermission
-from pydantic import BaseModel, Field
-
-from backend.api.external.middleware import require_permission
-from backend.api.features.store import cache as store_cache
-from backend.api.features.store import db as store_db
-from backend.api.features.store import model as store_model
-from backend.data.auth.base import APIAuthorizationInfo
-
-from .common import DEFAULT_PAGE_SIZE, MAX_PAGE_SIZE
-
-logger = logging.getLogger(__name__)
-
-marketplace_router = APIRouter()
-
-
-# ============================================================================
-# Models
-# ============================================================================
-
-
-class MarketplaceAgent(BaseModel):
-    """An agent available in the marketplace."""
-
-    slug: str
-    name: str
-    description: str
-    sub_heading: str
-    creator: str
-    creator_avatar: str
-    runs: int = Field(default=0, description="Number of times this agent has been run")
-    rating: float = Field(default=0.0, description="Average rating")
-    image_url: str = Field(default="")
-
-
-class MarketplaceAgentDetails(BaseModel):
-    """Detailed information about a marketplace agent."""
-
-    store_listing_version_id: str
-    slug: str
-    name: str
-    description: str
-    sub_heading: str
-    instructions: Optional[str] = None
-    creator: str
-    creator_avatar: str
-    categories: list[str] = Field(default_factory=list)
-    runs: int = Field(default=0)
-    rating: float = Field(default=0.0)
-    image_urls: list[str] = Field(default_factory=list)
-    video_url: str = Field(default="")
-    versions: list[str] = Field(default_factory=list, description="Available versions")
-    agent_graph_versions: list[str] = Field(default_factory=list)
-    agent_graph_id: str
-    last_updated: datetime
-
-
-class MarketplaceAgentsResponse(BaseModel):
-    """Response for listing marketplace agents."""
-
-    agents: list[MarketplaceAgent]
-    total_count: int
-    page: int
-    page_size: int
-    total_pages: int
-
-
-class MarketplaceCreator(BaseModel):
-    """A creator on the marketplace."""
-
-    name: str
-    username: str
-    description: str
-    avatar_url: str
-    num_agents: int
-    agent_rating: float
-    agent_runs: int
-    is_featured: bool = False
-
-
-class MarketplaceCreatorDetails(BaseModel):
-    """Detailed information about a marketplace creator."""
-
-    name: str
-    username: str
-    description: str
-    avatar_url: str
-    agent_rating: float
-    agent_runs: int
-    top_categories: list[str] = Field(default_factory=list)
-    links: list[str] = Field(default_factory=list)
-
-
-class MarketplaceCreatorsResponse(BaseModel):
-    """Response for listing marketplace creators."""
-
-    creators: list[MarketplaceCreator]
-    total_count: int
-    page: int
-    page_size: int
-    total_pages: int
-
-
-class MarketplaceSubmission(BaseModel):
-    """A marketplace submission."""
-
-    graph_id: str
-    graph_version: int
-    name: str
-    sub_heading: str
-    slug: str
-    description: str
-    instructions: Optional[str] = None
-    image_urls: list[str] = Field(default_factory=list)
-    date_submitted: datetime
-    status: str = Field(description="One of: DRAFT, PENDING, APPROVED, REJECTED")
-    runs: int = Field(default=0)
-    rating: float = Field(default=0.0)
-    store_listing_version_id: Optional[str] = None
-    version: Optional[int] = None
-    review_comments: Optional[str] = None
-    reviewed_at: Optional[datetime] = None
-    video_url: Optional[str] = None
-    categories: list[str] = Field(default_factory=list)
-
-
-class SubmissionsListResponse(BaseModel):
-    """Response for listing submissions."""
-
-    submissions: list[MarketplaceSubmission]
-    total_count: int
-    page: int
-    page_size: int
-    total_pages: int
-
-
-class CreateSubmissionRequest(BaseModel):
-    """Request to create a marketplace submission."""
-
-    graph_id: str = Field(description="ID of the graph to submit")
-    graph_version: int = Field(description="Version of the graph to submit")
-    name: str = Field(description="Display name for the agent")
-    slug: str = Field(description="URL-friendly identifier")
-    description: str = Field(description="Full description")
-    sub_heading: str = Field(description="Short tagline")
-    image_urls: list[str] = Field(default_factory=list)
-    video_url: Optional[str] = None
-    categories: list[str] = Field(default_factory=list)
-
-
-# ============================================================================
-# Conversion Functions
-# ============================================================================
-
-
-def _convert_store_agent(agent: store_model.StoreAgent) -> MarketplaceAgent:
-    """Convert internal StoreAgent to v2 API model."""
-    return MarketplaceAgent(
-        slug=agent.slug,
-        name=agent.agent_name,
-        description=agent.description,
-        sub_heading=agent.sub_heading,
-        creator=agent.creator,
-        creator_avatar=agent.creator_avatar,
-        runs=agent.runs,
-        rating=agent.rating,
-        image_url=agent.agent_image,
-    )
-
-
-def _convert_store_agent_details(
-    agent: store_model.StoreAgentDetails,
-) -> MarketplaceAgentDetails:
-    """Convert internal StoreAgentDetails to v2 API model."""
-    return MarketplaceAgentDetails(
-        store_listing_version_id=agent.store_listing_version_id,
-        slug=agent.slug,
-        name=agent.agent_name,
-        description=agent.description,
-        sub_heading=agent.sub_heading,
-        instructions=agent.instructions,
-        creator=agent.creator,
-        creator_avatar=agent.creator_avatar,
-        categories=agent.categories,
-        runs=agent.runs,
-        rating=agent.rating,
-        image_urls=agent.agent_image,
-        video_url=agent.agent_video,
-        versions=agent.versions,
-        agent_graph_versions=agent.agentGraphVersions,
-        agent_graph_id=agent.agentGraphId,
-        last_updated=agent.last_updated,
-    )
-
-
-def _convert_creator(creator: store_model.Creator) -> MarketplaceCreator:
-    """Convert internal Creator to v2 API model."""
-    return MarketplaceCreator(
-        name=creator.name,
-        username=creator.username,
-        description=creator.description,
-        avatar_url=creator.avatar_url,
-        num_agents=creator.num_agents,
-        agent_rating=creator.agent_rating,
-        agent_runs=creator.agent_runs,
-        is_featured=creator.is_featured,
-    )
-
-
-def _convert_creator_details(
-    creator: store_model.CreatorDetails,
-) -> MarketplaceCreatorDetails:
-    """Convert internal CreatorDetails to v2 API model."""
-    return MarketplaceCreatorDetails(
-        name=creator.name,
-        username=creator.username,
-        description=creator.description,
-        avatar_url=creator.avatar_url,
-        agent_rating=creator.agent_rating,
-        agent_runs=creator.agent_runs,
-        top_categories=creator.top_categories,
-        links=creator.links,
-    )
-
-
-def _convert_submission(sub: store_model.StoreSubmission) -> MarketplaceSubmission:
-    """Convert internal StoreSubmission to v2 API model."""
-    return MarketplaceSubmission(
-        graph_id=sub.agent_id,
-        graph_version=sub.agent_version,
-        name=sub.name,
-        sub_heading=sub.sub_heading,
-        slug=sub.slug,
-        description=sub.description,
-        instructions=sub.instructions,
-        image_urls=sub.image_urls,
-        date_submitted=sub.date_submitted,
-        status=sub.status.value,
-        runs=sub.runs,
-        rating=sub.rating,
-        store_listing_version_id=sub.store_listing_version_id,
-        version=sub.version,
-        review_comments=sub.review_comments,
-        reviewed_at=sub.reviewed_at,
-        video_url=sub.video_url,
-        categories=sub.categories,
-    )
-
-
-# ============================================================================
-# Endpoints - Read (authenticated)
-# ============================================================================
-
-
-@marketplace_router.get(
-    path="/agents",
-    summary="List marketplace agents",
-    response_model=MarketplaceAgentsResponse,
-)
-async def list_agents(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_STORE)
-    ),
-    featured: bool = Query(default=False, description="Filter to featured agents only"),
-    creator: Optional[str] = Query(
-        default=None, description="Filter by creator username"
-    ),
-    sorted_by: Optional[Literal["rating", "runs", "name", "updated_at"]] = Query(
-        default=None, description="Sort field"
-    ),
-    search_query: Optional[str] = Query(default=None, description="Search query"),
-    category: Optional[str] = Query(default=None, description="Filter by category"),
-    page: int = Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = Query(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Items per page (max {MAX_PAGE_SIZE})",
-    ),
-) -> MarketplaceAgentsResponse:
-    """
-    List agents available in the marketplace.
-
-    Supports filtering by featured status, creator, category, and search query.
-    Results can be sorted by rating, runs, name, or update time.
-    """
-    result = await store_cache._get_cached_store_agents(
-        featured=featured,
-        creator=creator,
-        sorted_by=sorted_by,
-        search_query=search_query,
-        category=category,
-        page=page,
-        page_size=page_size,
-    )
-
-    return MarketplaceAgentsResponse(
-        agents=[_convert_store_agent(a) for a in result.agents],
-        total_count=result.pagination.total_items,
-        page=result.pagination.current_page,
-        page_size=result.pagination.page_size,
-        total_pages=result.pagination.total_pages,
-    )
-
-
-@marketplace_router.get(
-    path="/agents/{username}/{agent_name}",
-    summary="Get agent details",
-    response_model=MarketplaceAgentDetails,
-)
-async def get_agent_details(
-    username: str = Path(description="Creator username"),
-    agent_name: str = Path(description="Agent slug/name"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_STORE)
-    ),
-) -> MarketplaceAgentDetails:
-    """
-    Get detailed information about a specific marketplace agent.
-    """
-    username = urllib.parse.unquote(username).lower()
-    agent_name = urllib.parse.unquote(agent_name).lower()
-
-    agent = await store_cache._get_cached_agent_details(
-        username=username, agent_name=agent_name
-    )
-
-    return _convert_store_agent_details(agent)
-
-
-@marketplace_router.get(
-    path="/creators",
-    summary="List marketplace creators",
-    response_model=MarketplaceCreatorsResponse,
-)
-async def list_creators(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_STORE)
-    ),
-    featured: bool = Query(
-        default=False, description="Filter to featured creators only"
-    ),
-    search_query: Optional[str] = Query(default=None, description="Search query"),
-    sorted_by: Optional[Literal["agent_rating", "agent_runs", "num_agents"]] = Query(
-        default=None, description="Sort field"
-    ),
-    page: int = Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = Query(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Items per page (max {MAX_PAGE_SIZE})",
-    ),
-) -> MarketplaceCreatorsResponse:
-    """
-    List creators on the marketplace.
-
-    Supports filtering by featured status and search query.
-    Results can be sorted by rating, runs, or number of agents.
-    """
-    result = await store_cache._get_cached_store_creators(
-        featured=featured,
-        search_query=search_query,
-        sorted_by=sorted_by,
-        page=page,
-        page_size=page_size,
-    )
-
-    return MarketplaceCreatorsResponse(
-        creators=[_convert_creator(c) for c in result.creators],
-        total_count=result.pagination.total_items,
-        page=result.pagination.current_page,
-        page_size=result.pagination.page_size,
-        total_pages=result.pagination.total_pages,
-    )
-
-
-@marketplace_router.get(
-    path="/creators/{username}",
-    summary="Get creator details",
-    response_model=MarketplaceCreatorDetails,
-)
-async def get_creator_details(
-    username: str = Path(description="Creator username"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_STORE)
-    ),
-) -> MarketplaceCreatorDetails:
-    """
-    Get detailed information about a specific marketplace creator.
-    """
-    username = urllib.parse.unquote(username).lower()
-
-    creator = await store_cache._get_cached_creator_details(username=username)
-
-    return _convert_creator_details(creator)
-
-
-# ============================================================================
-# Endpoints - Submissions (CRUD)
-# ============================================================================
-
-
-@marketplace_router.get(
-    path="/submissions",
-    summary="List my submissions",
-    response_model=SubmissionsListResponse,
-)
-async def list_submissions(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_STORE)
-    ),
-    page: int = Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = Query(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Items per page (max {MAX_PAGE_SIZE})",
-    ),
-) -> SubmissionsListResponse:
-    """
-    List your marketplace submissions.
-
-    Returns all submissions you've created, including drafts, pending,
-    approved, and rejected submissions.
-    """
-    result = await store_db.get_store_submissions(
-        user_id=auth.user_id,
-        page=page,
-        page_size=page_size,
-    )
-
-    return SubmissionsListResponse(
-        submissions=[_convert_submission(s) for s in result.submissions],
-        total_count=result.pagination.total_items,
-        page=result.pagination.current_page,
-        page_size=result.pagination.page_size,
-        total_pages=result.pagination.total_pages,
-    )
-
-
-@marketplace_router.post(
-    path="/submissions",
-    summary="Create a submission",
-    response_model=MarketplaceSubmission,
-)
-async def create_submission(
-    request: CreateSubmissionRequest,
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_STORE)
-    ),
-) -> MarketplaceSubmission:
-    """
-    Create a new marketplace submission.
-
-    This submits an agent for review to be published in the marketplace.
-    The submission will be in PENDING status until reviewed by the team.
-    """
-    submission = await store_db.create_store_submission(
-        user_id=auth.user_id,
-        agent_id=request.graph_id,
-        agent_version=request.graph_version,
-        slug=request.slug,
-        name=request.name,
-        sub_heading=request.sub_heading,
-        description=request.description,
-        image_urls=request.image_urls,
-        video_url=request.video_url,
-        categories=request.categories,
-    )
-
-    return _convert_submission(submission)
-
-
-@marketplace_router.delete(
-    path="/submissions/{submission_id}",
-    summary="Delete a submission",
-)
-async def delete_submission(
-    submission_id: str = Path(description="Submission ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_STORE)
-    ),
-) -> None:
-    """
-    Delete a marketplace submission.
-
-    Only submissions in DRAFT status can be deleted.
-    """
-    success = await store_db.delete_store_submission(
-        user_id=auth.user_id,
-        submission_id=submission_id,
-    )
-
-    if not success:
-        raise HTTPException(
-            status_code=404, detail=f"Submission #{submission_id} not found"
-        )

autogpt_platform/backend/backend/api/external/v2/models.py

@@ -1,552 +0,0 @@
-"""
-V2 External API - Request and Response Models
-
-This module defines all request and response models for the v2 external API.
-All models are self-contained and specific to the external API contract.
-"""
-
-from datetime import datetime
-from typing import Any, Optional
-
-from pydantic import BaseModel, Field
-
-# ============================================================================
-# Common/Shared Models
-# ============================================================================
-
-
-class PaginatedResponse(BaseModel):
-    """Base class for paginated responses."""
-
-    total_count: int = Field(description="Total number of items across all pages")
-    page: int = Field(description="Current page number (1-indexed)")
-    page_size: int = Field(description="Number of items per page")
-    total_pages: int = Field(description="Total number of pages")
-
-
-# ============================================================================
-# Graph Models
-# ============================================================================
-
-
-class GraphLink(BaseModel):
-    """A link between two nodes in a graph."""
-
-    id: str
-    source_id: str = Field(description="ID of the source node")
-    sink_id: str = Field(description="ID of the target node")
-    source_name: str = Field(description="Output pin name on source node")
-    sink_name: str = Field(description="Input pin name on target node")
-    is_static: bool = Field(
-        default=False, description="Whether this link provides static data"
-    )
-
-
-class GraphNode(BaseModel):
-    """A node in an agent graph."""
-
-    id: str
-    block_id: str = Field(description="ID of the block type")
-    input_default: dict[str, Any] = Field(
-        default_factory=dict, description="Default input values"
-    )
-    metadata: dict[str, Any] = Field(
-        default_factory=dict, description="Node metadata (e.g., position)"
-    )
-
-
-class Graph(BaseModel):
-    """Graph definition for creating or updating an agent."""
-
-    id: Optional[str] = Field(default=None, description="Graph ID (assigned by server)")
-    version: int = Field(default=1, description="Graph version")
-    is_active: bool = Field(default=True, description="Whether this version is active")
-    name: str = Field(description="Graph name")
-    description: str = Field(default="", description="Graph description")
-    nodes: list[GraphNode] = Field(default_factory=list, description="List of nodes")
-    links: list[GraphLink] = Field(
-        default_factory=list, description="Links between nodes"
-    )
-
-
-class GraphMeta(BaseModel):
-    """Graph metadata (summary information)."""
-
-    id: str
-    version: int
-    is_active: bool
-    name: str
-    description: str
-    created_at: datetime
-    input_schema: dict[str, Any] = Field(description="Input schema for the graph")
-    output_schema: dict[str, Any] = Field(description="Output schema for the graph")
-
-
-class GraphDetails(GraphMeta):
-    """Full graph details including nodes and links."""
-
-    nodes: list[GraphNode]
-    links: list[GraphLink]
-    credentials_input_schema: dict[str, Any] = Field(
-        description="Schema for required credentials"
-    )
-
-
-class GraphSettings(BaseModel):
-    """Settings for a graph."""
-
-    human_in_the_loop_safe_mode: Optional[bool] = Field(
-        default=None, description="Enable safe mode for human-in-the-loop blocks"
-    )
-
-
-class CreateGraphRequest(BaseModel):
-    """Request to create a new graph."""
-
-    graph: Graph = Field(description="The graph definition")
-
-
-class SetActiveVersionRequest(BaseModel):
-    """Request to set the active graph version."""
-
-    active_graph_version: int = Field(description="Version number to set as active")
-
-
-class GraphsListResponse(PaginatedResponse):
-    """Response for listing graphs."""
-
-    graphs: list[GraphMeta]
-
-
-class DeleteGraphResponse(BaseModel):
-    """Response for deleting a graph."""
-
-    version_count: int = Field(description="Number of versions deleted")
-
-
-# ============================================================================
-# Schedule Models
-# ============================================================================
-
-
-class Schedule(BaseModel):
-    """An execution schedule for a graph."""
-
-    id: str
-    name: str
-    graph_id: str
-    graph_version: int
-    cron: str = Field(description="Cron expression for the schedule")
-    input_data: dict[str, Any] = Field(
-        default_factory=dict, description="Input data for scheduled executions"
-    )
-    is_enabled: bool = Field(default=True, description="Whether schedule is enabled")
-    next_run_time: Optional[datetime] = Field(
-        default=None, description="Next scheduled run time"
-    )
-
-
-class CreateScheduleRequest(BaseModel):
-    """Request to create a schedule."""
-
-    name: str = Field(description="Display name for the schedule")
-    cron: str = Field(description="Cron expression (e.g., '0 9 * * *' for 9am daily)")
-    input_data: dict[str, Any] = Field(
-        default_factory=dict, description="Input data for scheduled executions"
-    )
-    credentials_inputs: dict[str, Any] = Field(
-        default_factory=dict, description="Credentials for the schedule"
-    )
-    graph_version: Optional[int] = Field(
-        default=None, description="Graph version (default: active version)"
-    )
-    timezone: Optional[str] = Field(
-        default=None,
-        description="Timezone for schedule (e.g., 'America/New_York')",
-    )
-
-
-class SchedulesListResponse(PaginatedResponse):
-    """Response for listing schedules."""
-
-    schedules: list[Schedule]
-
-
-# ============================================================================
-# Block Models
-# ============================================================================
-
-
-class BlockCost(BaseModel):
-    """Cost information for a block."""
-
-    cost_type: str = Field(description="Type of cost (e.g., 'per_call', 'per_token')")
-    cost_filter: dict[str, Any] = Field(
-        default_factory=dict, description="Conditions for this cost"
-    )
-    cost_amount: int = Field(description="Cost amount in credits")
-
-
-class Block(BaseModel):
-    """A building block that can be used in graphs."""
-
-    id: str
-    name: str
-    description: str
-    categories: list[str] = Field(default_factory=list)
-    input_schema: dict[str, Any]
-    output_schema: dict[str, Any]
-    costs: list[BlockCost] = Field(default_factory=list)
-
-
-class BlocksListResponse(BaseModel):
-    """Response for listing blocks."""
-
-    blocks: list[Block]
-
-
-# ============================================================================
-# Marketplace Models
-# ============================================================================
-
-
-class MarketplaceAgent(BaseModel):
-    """An agent available in the marketplace."""
-
-    slug: str
-    agent_name: str
-    agent_image: str
-    creator: str
-    creator_avatar: str
-    sub_heading: str
-    description: str
-    runs: int = Field(default=0, description="Number of times this agent has been run")
-    rating: float = Field(default=0.0, description="Average rating")
-
-
-class MarketplaceAgentDetails(BaseModel):
-    """Detailed information about a marketplace agent."""
-
-    store_listing_version_id: str
-    slug: str
-    agent_name: str
-    agent_video: str
-    agent_output_demo: str
-    agent_image: list[str]
-    creator: str
-    creator_avatar: str
-    sub_heading: str
-    description: str
-    instructions: Optional[str] = None
-    categories: list[str]
-    runs: int
-    rating: float
-    versions: list[str]
-    agent_graph_versions: list[str]
-    agent_graph_id: str
-    last_updated: datetime
-    recommended_schedule_cron: Optional[str] = None
-
-
-class MarketplaceCreator(BaseModel):
-    """A creator on the marketplace."""
-
-    name: str
-    username: str
-    description: str
-    avatar_url: str
-    num_agents: int
-    agent_rating: float
-    agent_runs: int
-    is_featured: bool = False
-
-
-class MarketplaceAgentsResponse(PaginatedResponse):
-    """Response for listing marketplace agents."""
-
-    agents: list[MarketplaceAgent]
-
-
-class MarketplaceCreatorsResponse(PaginatedResponse):
-    """Response for listing marketplace creators."""
-
-    creators: list[MarketplaceCreator]
-
-
-# Submission models
-class MarketplaceSubmission(BaseModel):
-    """A marketplace submission."""
-
-    agent_id: str
-    agent_version: int
-    name: str
-    sub_heading: str
-    slug: str
-    description: str
-    instructions: Optional[str] = None
-    image_urls: list[str] = Field(default_factory=list)
-    date_submitted: datetime
-    status: str = Field(description="One of: DRAFT, PENDING, APPROVED, REJECTED")
-    runs: int
-    rating: float
-    store_listing_version_id: Optional[str] = None
-    version: Optional[int] = None
-
-    # Review fields
-    review_comments: Optional[str] = None
-    reviewed_at: Optional[datetime] = None
-
-    # Additional optional fields
-    video_url: Optional[str] = None
-    categories: list[str] = Field(default_factory=list)
-
-
-class CreateSubmissionRequest(BaseModel):
-    """Request to create a marketplace submission."""
-
-    agent_id: str = Field(description="ID of the graph to submit")
-    agent_version: int = Field(description="Version of the graph to submit")
-    name: str = Field(description="Display name for the agent")
-    slug: str = Field(description="URL-friendly identifier")
-    description: str = Field(description="Full description")
-    sub_heading: str = Field(description="Short tagline")
-    image_urls: list[str] = Field(default_factory=list)
-    video_url: Optional[str] = None
-    categories: list[str] = Field(default_factory=list)
-
-
-class UpdateSubmissionRequest(BaseModel):
-    """Request to update a marketplace submission."""
-
-    name: Optional[str] = None
-    description: Optional[str] = None
-    sub_heading: Optional[str] = None
-    image_urls: Optional[list[str]] = None
-    video_url: Optional[str] = None
-    categories: Optional[list[str]] = None
-
-
-class SubmissionsListResponse(PaginatedResponse):
-    """Response for listing submissions."""
-
-    submissions: list[MarketplaceSubmission]
-
-
-# ============================================================================
-# Library Models
-# ============================================================================
-
-
-class LibraryAgent(BaseModel):
-    """An agent in the user's library."""
-
-    id: str
-    graph_id: str
-    graph_version: int
-    name: str
-    description: str
-    is_favorite: bool = False
-    can_access_graph: bool = False
-    is_latest_version: bool = False
-    image_url: Optional[str] = None
-    creator_name: str
-    input_schema: dict[str, Any] = Field(description="Input schema for the agent")
-    output_schema: dict[str, Any] = Field(description="Output schema for the agent")
-    created_at: datetime
-    updated_at: datetime
-
-
-class LibraryAgentsResponse(PaginatedResponse):
-    """Response for listing library agents."""
-
-    agents: list[LibraryAgent]
-
-
-class ExecuteAgentRequest(BaseModel):
-    """Request to execute an agent."""
-
-    inputs: dict[str, Any] = Field(
-        default_factory=dict, description="Input values for the agent"
-    )
-    credentials_inputs: dict[str, Any] = Field(
-        default_factory=dict, description="Credentials for the agent"
-    )
-
-
-# ============================================================================
-# Run Models
-# ============================================================================
-
-
-class Run(BaseModel):
-    """An execution run."""
-
-    id: str
-    graph_id: str
-    graph_version: int
-    status: str = Field(
-        description="One of: INCOMPLETE, QUEUED, RUNNING, COMPLETED, TERMINATED, FAILED, REVIEW"
-    )
-    started_at: datetime
-    ended_at: Optional[datetime] = None
-    inputs: Optional[dict[str, Any]] = None
-    cost: int = Field(default=0, description="Cost in credits")
-    duration: float = Field(default=0, description="Duration in seconds")
-    node_count: int = Field(default=0, description="Number of nodes executed")
-
-
-class RunDetails(Run):
-    """Detailed information about a run including node executions."""
-
-    outputs: Optional[dict[str, list[Any]]] = None
-    node_executions: list[dict[str, Any]] = Field(
-        default_factory=list, description="Individual node execution results"
-    )
-
-
-class RunsListResponse(PaginatedResponse):
-    """Response for listing runs."""
-
-    runs: list[Run]
-
-
-# ============================================================================
-# Run Review Models (Human-in-the-loop)
-# ============================================================================
-
-
-class PendingReview(BaseModel):
-    """A pending human-in-the-loop review."""
-
-    id: str  # node_exec_id
-    run_id: str
-    graph_id: str
-    graph_version: int
-    payload: Any = Field(description="Data to be reviewed")
-    instructions: Optional[str] = Field(
-        default=None, description="Instructions for the reviewer"
-    )
-    editable: bool = Field(
-        default=True, description="Whether the reviewer can edit the data"
-    )
-    status: str = Field(description="One of: WAITING, APPROVED, REJECTED")
-    created_at: datetime
-
-
-class PendingReviewsResponse(PaginatedResponse):
-    """Response for listing pending reviews."""
-
-    reviews: list[PendingReview]
-
-
-class ReviewDecision(BaseModel):
-    """Decision for a single review item."""
-
-    node_exec_id: str = Field(description="Node execution ID (review ID)")
-    approved: bool = Field(description="Whether to approve the data")
-    edited_payload: Optional[Any] = Field(
-        default=None, description="Modified payload data (if editing)"
-    )
-    message: Optional[str] = Field(
-        default=None, description="Optional message from reviewer", max_length=2000
-    )
-
-
-class SubmitReviewsRequest(BaseModel):
-    """Request to submit review responses for all pending reviews of an execution."""
-
-    reviews: list[ReviewDecision] = Field(
-        description="All review decisions for the execution"
-    )
-
-
-class SubmitReviewsResponse(BaseModel):
-    """Response after submitting reviews."""
-
-    run_id: str
-    approved_count: int = Field(description="Number of reviews approved")
-    rejected_count: int = Field(description="Number of reviews rejected")
-
-
-# ============================================================================
-# Credit Models
-# ============================================================================
-
-
-class CreditBalance(BaseModel):
-    """User's credit balance."""
-
-    balance: int = Field(description="Current credit balance")
-
-
-class CreditTransaction(BaseModel):
-    """A credit transaction."""
-
-    transaction_key: str
-    amount: int
-    transaction_type: str = Field(description="Transaction type")
-    transaction_time: datetime
-    running_balance: int
-    description: Optional[str] = None
-
-
-class CreditTransactionsResponse(PaginatedResponse):
-    """Response for listing credit transactions."""
-
-    transactions: list[CreditTransaction]
-
-
-# ============================================================================
-# Integration Models
-# ============================================================================
-
-
-class Credential(BaseModel):
-    """A user's credential for an integration."""
-
-    id: str
-    provider: str = Field(description="Integration provider name")
-    title: Optional[str] = Field(
-        default=None, description="User-assigned title for this credential"
-    )
-    scopes: list[str] = Field(default_factory=list, description="Granted scopes")
-
-
-class CredentialsListResponse(BaseModel):
-    """Response for listing credentials."""
-
-    credentials: list[Credential]
-
-
-class CredentialRequirement(BaseModel):
-    """A credential requirement for a graph or agent."""
-
-    provider: str = Field(description="Required provider name")
-    required_scopes: list[str] = Field(
-        default_factory=list, description="Required scopes"
-    )
-    matching_credentials: list[Credential] = Field(
-        default_factory=list,
-        description="User's credentials that match this requirement",
-    )
-
-
-class CredentialRequirementsResponse(BaseModel):
-    """Response for listing credential requirements."""
-
-    requirements: list[CredentialRequirement]
-
-
-# ============================================================================
-# File Models
-# ============================================================================
-
-
-class UploadFileResponse(BaseModel):
-    """Response after uploading a file."""
-
-    file_uri: str = Field(description="URI to reference the uploaded file")
-    file_name: str
-    size: int = Field(description="File size in bytes")
-    content_type: str
-    expires_in_hours: int

autogpt_platform/backend/backend/api/external/v2/routes.py

@@ -1,35 +0,0 @@
-"""
-V2 External API Routes
-
-This module defines the main v2 router that aggregates all v2 API endpoints.
-"""
-
-from fastapi import APIRouter
-
-from .blocks import blocks_router
-from .credits import credits_router
-from .files import files_router
-from .graphs import graphs_router
-from .integrations import integrations_router
-from .library import library_router
-from .marketplace import marketplace_router
-from .runs import runs_router
-from .schedules import graph_schedules_router, schedules_router
-
-v2_router = APIRouter()
-
-# Include all sub-routers
-v2_router.include_router(graphs_router, prefix="/graphs", tags=["graphs"])
-v2_router.include_router(graph_schedules_router, prefix="/graphs", tags=["schedules"])
-v2_router.include_router(schedules_router, prefix="/schedules", tags=["schedules"])
-v2_router.include_router(blocks_router, prefix="/blocks", tags=["blocks"])
-v2_router.include_router(
-    marketplace_router, prefix="/marketplace", tags=["marketplace"]
-)
-v2_router.include_router(library_router, prefix="/library", tags=["library"])
-v2_router.include_router(runs_router, prefix="/runs", tags=["runs"])
-v2_router.include_router(credits_router, prefix="/credits", tags=["credits"])
-v2_router.include_router(
-    integrations_router, prefix="/integrations", tags=["integrations"]
-)
-v2_router.include_router(files_router, prefix="/files", tags=["files"])

autogpt_platform/backend/backend/api/external/v2/runs.py

@@ -1,451 +0,0 @@
-"""
-V2 External API - Runs Endpoints
-
-Provides access to execution runs and human-in-the-loop reviews.
-"""
-
-import logging
-from datetime import datetime
-from typing import Any, Optional
-
-from fastapi import APIRouter, HTTPException, Path, Query, Security
-from prisma.enums import APIKeyPermission, ReviewStatus
-from pydantic import BaseModel, Field
-
-from backend.api.external.middleware import require_permission
-from backend.api.features.executions.review.model import (
-    PendingHumanReviewModel,
-    SafeJsonData,
-)
-from backend.data import execution as execution_db
-from backend.data import human_review as review_db
-from backend.data.auth.base import APIAuthorizationInfo
-from backend.executor import utils as execution_utils
-
-from .common import DEFAULT_PAGE_SIZE, MAX_PAGE_SIZE
-
-logger = logging.getLogger(__name__)
-
-runs_router = APIRouter()
-
-
-# ============================================================================
-# Models
-# ============================================================================
-
-
-class Run(BaseModel):
-    """An execution run."""
-
-    id: str
-    graph_id: str
-    graph_version: int
-    status: str = Field(
-        description="One of: INCOMPLETE, QUEUED, RUNNING, COMPLETED, TERMINATED, FAILED, REVIEW"
-    )
-    started_at: datetime
-    ended_at: Optional[datetime] = None
-    inputs: Optional[dict[str, Any]] = None
-    cost: int = Field(default=0, description="Cost in credits")
-    duration: float = Field(default=0, description="Duration in seconds")
-    node_count: int = Field(default=0, description="Number of nodes executed")
-
-
-class RunDetails(Run):
-    """Detailed information about a run including outputs and node executions."""
-
-    outputs: Optional[dict[str, list[Any]]] = None
-    node_executions: list[dict[str, Any]] = Field(
-        default_factory=list, description="Individual node execution results"
-    )
-
-
-class RunsListResponse(BaseModel):
-    """Response for listing runs."""
-
-    runs: list[Run]
-    total_count: int
-    page: int
-    page_size: int
-    total_pages: int
-
-
-class PendingReview(BaseModel):
-    """A pending human-in-the-loop review."""
-
-    id: str  # node_exec_id
-    run_id: str
-    graph_id: str
-    graph_version: int
-    payload: SafeJsonData = Field(description="Data to be reviewed")
-    instructions: Optional[str] = Field(
-        default=None, description="Instructions for the reviewer"
-    )
-    editable: bool = Field(
-        default=True, description="Whether the reviewer can edit the data"
-    )
-    status: str = Field(description="One of: WAITING, APPROVED, REJECTED")
-    created_at: datetime
-
-
-class PendingReviewsResponse(BaseModel):
-    """Response for listing pending reviews."""
-
-    reviews: list[PendingReview]
-    total_count: int
-    page: int
-    page_size: int
-    total_pages: int
-
-
-class ReviewDecision(BaseModel):
-    """Decision for a single review item."""
-
-    node_exec_id: str = Field(description="Node execution ID (review ID)")
-    approved: bool = Field(description="Whether to approve the data")
-    edited_payload: Optional[SafeJsonData] = Field(
-        default=None, description="Modified payload data (if editing)"
-    )
-    message: Optional[str] = Field(
-        default=None, description="Optional message from reviewer", max_length=2000
-    )
-
-
-class SubmitReviewsRequest(BaseModel):
-    """Request to submit review responses for all pending reviews of an execution."""
-
-    reviews: list[ReviewDecision] = Field(
-        description="All review decisions for the execution"
-    )
-
-
-class SubmitReviewsResponse(BaseModel):
-    """Response after submitting reviews."""
-
-    run_id: str
-    approved_count: int = Field(description="Number of reviews approved")
-    rejected_count: int = Field(description="Number of reviews rejected")
-
-
-# ============================================================================
-# Conversion Functions
-# ============================================================================
-
-
-def _convert_execution_to_run(exec: execution_db.GraphExecutionMeta) -> Run:
-    """Convert internal execution to v2 API Run model."""
-    return Run(
-        id=exec.id,
-        graph_id=exec.graph_id,
-        graph_version=exec.graph_version,
-        status=exec.status.value,
-        started_at=exec.started_at,
-        ended_at=exec.ended_at,
-        inputs=exec.inputs,
-        cost=exec.stats.cost if exec.stats else 0,
-        duration=exec.stats.duration if exec.stats else 0,
-        node_count=exec.stats.node_exec_count if exec.stats else 0,
-    )
-
-
-def _convert_execution_to_run_details(
-    exec: execution_db.GraphExecutionWithNodes,
-) -> RunDetails:
-    """Convert internal execution with nodes to v2 API RunDetails model."""
-    return RunDetails(
-        id=exec.id,
-        graph_id=exec.graph_id,
-        graph_version=exec.graph_version,
-        status=exec.status.value,
-        started_at=exec.started_at,
-        ended_at=exec.ended_at,
-        inputs=exec.inputs,
-        outputs=exec.outputs,
-        cost=exec.stats.cost if exec.stats else 0,
-        duration=exec.stats.duration if exec.stats else 0,
-        node_count=exec.stats.node_exec_count if exec.stats else 0,
-        node_executions=[
-            {
-                "node_id": node.node_id,
-                "status": node.status.value,
-                "input_data": node.input_data,
-                "output_data": node.output_data,
-                "started_at": node.start_time,
-                "ended_at": node.end_time,
-            }
-            for node in exec.node_executions
-        ],
-    )
-
-
-def _convert_pending_review(review: PendingHumanReviewModel) -> PendingReview:
-    """Convert internal PendingHumanReviewModel to v2 API PendingReview model."""
-    return PendingReview(
-        id=review.node_exec_id,
-        run_id=review.graph_exec_id,
-        graph_id=review.graph_id,
-        graph_version=review.graph_version,
-        payload=review.payload,
-        instructions=review.instructions,
-        editable=review.editable,
-        status=review.status.value,
-        created_at=review.created_at,
-    )
-
-
-# ============================================================================
-# Endpoints - Runs
-# ============================================================================
-
-
-@runs_router.get(
-    path="",
-    summary="List all runs",
-    response_model=RunsListResponse,
-)
-async def list_runs(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_RUN)
-    ),
-    page: int = Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = Query(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Items per page (max {MAX_PAGE_SIZE})",
-    ),
-) -> RunsListResponse:
-    """
-    List all execution runs for the authenticated user.
-
-    Returns runs across all agents, sorted by most recent first.
-    """
-    result = await execution_db.get_graph_executions_paginated(
-        user_id=auth.user_id,
-        page=page,
-        page_size=page_size,
-    )
-
-    return RunsListResponse(
-        runs=[_convert_execution_to_run(e) for e in result.executions],
-        total_count=result.pagination.total_items,
-        page=result.pagination.current_page,
-        page_size=result.pagination.page_size,
-        total_pages=result.pagination.total_pages,
-    )
-
-
-@runs_router.get(
-    path="/{run_id}",
-    summary="Get run details",
-    response_model=RunDetails,
-)
-async def get_run(
-    run_id: str = Path(description="Run ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_RUN)
-    ),
-) -> RunDetails:
-    """
-    Get detailed information about a specific run.
-
-    Includes outputs and individual node execution results.
-    """
-    result = await execution_db.get_graph_execution(
-        user_id=auth.user_id,
-        execution_id=run_id,
-        include_node_executions=True,
-    )
-
-    if not result:
-        raise HTTPException(status_code=404, detail=f"Run #{run_id} not found")
-
-    return _convert_execution_to_run_details(result)
-
-
-@runs_router.post(
-    path="/{run_id}/stop",
-    summary="Stop a run",
-)
-async def stop_run(
-    run_id: str = Path(description="Run ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_RUN)
-    ),
-) -> Run:
-    """
-    Stop a running execution.
-
-    Only runs in QUEUED or RUNNING status can be stopped.
-    """
-    # Verify the run exists and belongs to the user
-    exec = await execution_db.get_graph_execution(
-        user_id=auth.user_id,
-        execution_id=run_id,
-    )
-    if not exec:
-        raise HTTPException(status_code=404, detail=f"Run #{run_id} not found")
-
-    # Stop the execution
-    await execution_utils.stop_graph_execution(
-        graph_exec_id=run_id,
-        user_id=auth.user_id,
-    )
-
-    # Fetch updated execution
-    updated_exec = await execution_db.get_graph_execution(
-        user_id=auth.user_id,
-        execution_id=run_id,
-    )
-
-    if not updated_exec:
-        raise HTTPException(status_code=404, detail=f"Run #{run_id} not found")
-
-    return _convert_execution_to_run(updated_exec)
-
-
-@runs_router.delete(
-    path="/{run_id}",
-    summary="Delete a run",
-)
-async def delete_run(
-    run_id: str = Path(description="Run ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_RUN)
-    ),
-) -> None:
-    """
-    Delete an execution run.
-
-    This marks the run as deleted. The data may still be retained for
-    some time for recovery purposes.
-    """
-    await execution_db.delete_graph_execution(
-        graph_exec_id=run_id,
-        user_id=auth.user_id,
-    )
-
-
-# ============================================================================
-# Endpoints - Reviews (Human-in-the-loop)
-# ============================================================================
-
-
-@runs_router.get(
-    path="/reviews",
-    summary="List all pending reviews",
-    response_model=PendingReviewsResponse,
-)
-async def list_pending_reviews(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_RUN_REVIEW)
-    ),
-    page: int = Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = Query(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Items per page (max {MAX_PAGE_SIZE})",
-    ),
-) -> PendingReviewsResponse:
-    """
-    List all pending human-in-the-loop reviews.
-
-    These are blocks that require human approval or input before the
-    agent can continue execution.
-    """
-    reviews = await review_db.get_pending_reviews_for_user(
-        user_id=auth.user_id,
-        page=page,
-        page_size=page_size,
-    )
-
-    # Note: get_pending_reviews_for_user returns list directly, not a paginated result
-    # We compute pagination info based on results
-    total_count = len(reviews)
-    total_pages = max(1, (total_count + page_size - 1) // page_size)
-
-    return PendingReviewsResponse(
-        reviews=[_convert_pending_review(r) for r in reviews],
-        total_count=total_count,
-        page=page,
-        page_size=page_size,
-        total_pages=total_pages,
-    )
-
-
-@runs_router.get(
-    path="/{run_id}/reviews",
-    summary="List reviews for a run",
-    response_model=list[PendingReview],
-)
-async def list_run_reviews(
-    run_id: str = Path(description="Run ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_RUN_REVIEW)
-    ),
-) -> list[PendingReview]:
-    """
-    List all human-in-the-loop reviews for a specific run.
-    """
-    reviews = await review_db.get_pending_reviews_for_execution(
-        graph_exec_id=run_id,
-        user_id=auth.user_id,
-    )
-
-    return [_convert_pending_review(r) for r in reviews]
-
-
-@runs_router.post(
-    path="/{run_id}/reviews",
-    summary="Submit review responses for a run",
-    response_model=SubmitReviewsResponse,
-)
-async def submit_reviews(
-    request: SubmitReviewsRequest,
-    run_id: str = Path(description="Run ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_RUN_REVIEW)
-    ),
-) -> SubmitReviewsResponse:
-    """
-    Submit responses to all pending human-in-the-loop reviews for a run.
-
-    All pending reviews for the execution must be included. Approving
-    a review will allow the agent to continue; rejecting will terminate
-    execution at that point.
-    """
-    # Build review decisions dict for process_all_reviews_for_execution
-    review_decisions: dict[
-        str, tuple[ReviewStatus, SafeJsonData | None, str | None]
-    ] = {}
-
-    for decision in request.reviews:
-        status = ReviewStatus.APPROVED if decision.approved else ReviewStatus.REJECTED
-        review_decisions[decision.node_exec_id] = (
-            status,
-            decision.edited_payload,
-            decision.message,
-        )
-
-    try:
-        results = await review_db.process_all_reviews_for_execution(
-            user_id=auth.user_id,
-            review_decisions=review_decisions,
-        )
-
-        approved_count = sum(
-            1 for r in results.values() if r.status == ReviewStatus.APPROVED
-        )
-        rejected_count = sum(
-            1 for r in results.values() if r.status == ReviewStatus.REJECTED
-        )
-
-        return SubmitReviewsResponse(
-            run_id=run_id,
-            approved_count=approved_count,
-            rejected_count=rejected_count,
-        )
-
-    except ValueError as e:
-        raise HTTPException(status_code=400, detail=str(e))

autogpt_platform/backend/backend/api/external/v2/schedules.py

@@ -1,250 +0,0 @@
-"""
-V2 External API - Schedules Endpoints
-
-Provides endpoints for managing execution schedules.
-"""
-
-import logging
-from datetime import datetime
-from typing import Any, Optional
-
-from fastapi import APIRouter, HTTPException, Path, Query, Security
-from prisma.enums import APIKeyPermission
-from pydantic import BaseModel, Field
-
-from backend.api.external.middleware import require_permission
-from backend.data import graph as graph_db
-from backend.data.auth.base import APIAuthorizationInfo
-from backend.data.user import get_user_by_id
-from backend.executor import scheduler
-from backend.util.clients import get_scheduler_client
-from backend.util.timezone_utils import get_user_timezone_or_utc
-
-from .common import DEFAULT_PAGE_SIZE, MAX_PAGE_SIZE
-
-logger = logging.getLogger(__name__)
-
-schedules_router = APIRouter()
-
-
-# ============================================================================
-# Request/Response Models
-# ============================================================================
-
-
-class Schedule(BaseModel):
-    """An execution schedule for a graph."""
-
-    id: str
-    name: str
-    graph_id: str
-    graph_version: int
-    cron: str = Field(description="Cron expression for the schedule")
-    input_data: dict[str, Any] = Field(
-        default_factory=dict, description="Input data for scheduled executions"
-    )
-    next_run_time: Optional[datetime] = Field(
-        default=None, description="Next scheduled run time"
-    )
-    is_enabled: bool = Field(default=True, description="Whether schedule is enabled")
-
-
-class SchedulesListResponse(BaseModel):
-    """Response for listing schedules."""
-
-    schedules: list[Schedule]
-    total_count: int
-    page: int
-    page_size: int
-    total_pages: int
-
-
-class CreateScheduleRequest(BaseModel):
-    """Request to create a schedule."""
-
-    name: str = Field(description="Display name for the schedule")
-    cron: str = Field(description="Cron expression (e.g., '0 9 * * *' for 9am daily)")
-    input_data: dict[str, Any] = Field(
-        default_factory=dict, description="Input data for scheduled executions"
-    )
-    credentials_inputs: dict[str, Any] = Field(
-        default_factory=dict, description="Credentials for the schedule"
-    )
-    graph_version: Optional[int] = Field(
-        default=None, description="Graph version (default: active version)"
-    )
-    timezone: Optional[str] = Field(
-        default=None,
-        description=(
-            "Timezone for schedule (e.g., 'America/New_York'). "
-            "Defaults to user's timezone."
-        ),
-    )
-
-
-def _convert_schedule(job: scheduler.GraphExecutionJobInfo) -> Schedule:
-    """Convert internal schedule job info to v2 API model."""
-    # Parse the ISO format string to datetime
-    next_run = datetime.fromisoformat(job.next_run_time) if job.next_run_time else None
-
-    return Schedule(
-        id=job.id,
-        name=job.name or "",
-        graph_id=job.graph_id,
-        graph_version=job.graph_version,
-        cron=job.cron,
-        input_data=job.input_data,
-        next_run_time=next_run,
-        is_enabled=True,  # All returned schedules are enabled
-    )
-
-
-# ============================================================================
-# Endpoints
-# ============================================================================
-
-
-@schedules_router.get(
-    path="",
-    summary="List all user schedules",
-    response_model=SchedulesListResponse,
-)
-async def list_all_schedules(
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_SCHEDULE)
-    ),
-    page: int = Query(default=1, ge=1, description="Page number (1-indexed)"),
-    page_size: int = Query(
-        default=DEFAULT_PAGE_SIZE,
-        ge=1,
-        le=MAX_PAGE_SIZE,
-        description=f"Items per page (max {MAX_PAGE_SIZE})",
-    ),
-) -> SchedulesListResponse:
-    """
-    List all schedules for the authenticated user across all graphs.
-    """
-    schedules = await get_scheduler_client().get_execution_schedules(
-        user_id=auth.user_id
-    )
-    converted = [_convert_schedule(s) for s in schedules]
-
-    # Manual pagination (scheduler doesn't support pagination natively)
-    total_count = len(converted)
-    total_pages = (total_count + page_size - 1) // page_size if total_count > 0 else 1
-    start = (page - 1) * page_size
-    end = start + page_size
-    paginated = converted[start:end]
-
-    return SchedulesListResponse(
-        schedules=paginated,
-        total_count=total_count,
-        page=page,
-        page_size=page_size,
-        total_pages=total_pages,
-    )
-
-
-@schedules_router.delete(
-    path="/{schedule_id}",
-    summary="Delete a schedule",
-)
-async def delete_schedule(
-    schedule_id: str = Path(description="Schedule ID to delete"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_SCHEDULE)
-    ),
-) -> None:
-    """
-    Delete an execution schedule.
-    """
-    try:
-        await get_scheduler_client().delete_schedule(
-            schedule_id=schedule_id,
-            user_id=auth.user_id,
-        )
-    except Exception as e:
-        if "not found" in str(e).lower():
-            raise HTTPException(
-                status_code=404, detail=f"Schedule #{schedule_id} not found"
-            )
-        raise
-
-
-# ============================================================================
-# Graph-specific Schedule Endpoints (nested under /graphs)
-# These are included in the graphs router via include_router
-# ============================================================================
-
-graph_schedules_router = APIRouter()
-
-
-@graph_schedules_router.get(
-    path="/{graph_id}/schedules",
-    summary="List schedules for a graph",
-    response_model=list[Schedule],
-)
-async def list_graph_schedules(
-    graph_id: str = Path(description="Graph ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.READ_SCHEDULE)
-    ),
-) -> list[Schedule]:
-    """
-    List all schedules for a specific graph.
-    """
-    schedules = await get_scheduler_client().get_execution_schedules(
-        user_id=auth.user_id,
-        graph_id=graph_id,
-    )
-    return [_convert_schedule(s) for s in schedules]
-
-
-@graph_schedules_router.post(
-    path="/{graph_id}/schedules",
-    summary="Create a schedule for a graph",
-    response_model=Schedule,
-)
-async def create_graph_schedule(
-    request: CreateScheduleRequest,
-    graph_id: str = Path(description="Graph ID"),
-    auth: APIAuthorizationInfo = Security(
-        require_permission(APIKeyPermission.WRITE_SCHEDULE)
-    ),
-) -> Schedule:
-    """
-    Create a new execution schedule for a graph.
-
-    The schedule will execute the graph at times matching the cron expression,
-    using the provided input data.
-    """
-    graph = await graph_db.get_graph(
-        graph_id=graph_id,
-        version=request.graph_version,
-        user_id=auth.user_id,
-    )
-    if not graph:
-        raise HTTPException(
-            status_code=404,
-            detail=f"Graph #{graph_id} v{request.graph_version} not found.",
-        )
-
-    # Determine timezone
-    if request.timezone:
-        user_timezone = request.timezone
-    else:
-        user = await get_user_by_id(auth.user_id)
-        user_timezone = get_user_timezone_or_utc(user.timezone if user else None)
-
-    result = await get_scheduler_client().add_execution_schedule(
-        user_id=auth.user_id,
-        graph_id=graph_id,
-        graph_version=graph.version,
-        name=request.name,
-        cron=request.cron,
-        input_data=request.input_data,
-        input_credentials=request.credentials_inputs,
-        user_timezone=user_timezone,
-    )
-
-    return _convert_schedule(result)

autogpt_platform/backend/backend/api/features/analytics_test.py

@@ -1,340 +0,0 @@
-"""Tests for analytics API endpoints."""
-
-import json
-from unittest.mock import AsyncMock, Mock
-
-import fastapi
-import fastapi.testclient
-import pytest
-import pytest_mock
-from pytest_snapshot.plugin import Snapshot
-
-from .analytics import router as analytics_router
-
-app = fastapi.FastAPI()
-app.include_router(analytics_router)
-
-client = fastapi.testclient.TestClient(app)
-
-
-@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()
-
-
-# =============================================================================
-# /log_raw_metric endpoint tests
-# =============================================================================
-
-
-def test_log_raw_metric_success(
-    mocker: pytest_mock.MockFixture,
-    configured_snapshot: Snapshot,
-    test_user_id: str,
-) -> None:
-    """Test successful raw metric logging."""
-    mock_result = Mock(id="metric-123-uuid")
-    mock_log_metric = mocker.patch(
-        "backend.data.analytics.log_raw_metric",
-        new_callable=AsyncMock,
-        return_value=mock_result,
-    )
-
-    request_data = {
-        "metric_name": "page_load_time",
-        "metric_value": 2.5,
-        "data_string": "/dashboard",
-    }
-
-    response = client.post("/log_raw_metric", json=request_data)
-
-    assert response.status_code == 200, f"Unexpected response: {response.text}"
-    assert response.json() == "metric-123-uuid"
-
-    mock_log_metric.assert_called_once_with(
-        user_id=test_user_id,
-        metric_name="page_load_time",
-        metric_value=2.5,
-        data_string="/dashboard",
-    )
-
-    configured_snapshot.assert_match(
-        json.dumps({"metric_id": response.json()}, indent=2, sort_keys=True),
-        "analytics_log_metric_success",
-    )
-
-
-@pytest.mark.parametrize(
-    "metric_value,metric_name,data_string,test_id",
-    [
-        (100, "api_calls_count", "external_api", "integer_value"),
-        (0, "error_count", "no_errors", "zero_value"),
-        (-5.2, "temperature_delta", "cooling", "negative_value"),
-        (1.23456789, "precision_test", "float_precision", "float_precision"),
-        (999999999, "large_number", "max_value", "large_number"),
-        (0.0000001, "tiny_number", "min_value", "tiny_number"),
-    ],
-)
-def test_log_raw_metric_various_values(
-    mocker: pytest_mock.MockFixture,
-    configured_snapshot: Snapshot,
-    metric_value: float,
-    metric_name: str,
-    data_string: str,
-    test_id: str,
-) -> None:
-    """Test raw metric logging with various metric values."""
-    mock_result = Mock(id=f"metric-{test_id}-uuid")
-    mocker.patch(
-        "backend.data.analytics.log_raw_metric",
-        new_callable=AsyncMock,
-        return_value=mock_result,
-    )
-
-    request_data = {
-        "metric_name": metric_name,
-        "metric_value": metric_value,
-        "data_string": data_string,
-    }
-
-    response = client.post("/log_raw_metric", json=request_data)
-
-    assert response.status_code == 200, f"Failed for {test_id}: {response.text}"
-
-    configured_snapshot.assert_match(
-        json.dumps(
-            {"metric_id": response.json(), "test_case": test_id},
-            indent=2,
-            sort_keys=True,
-        ),
-        f"analytics_metric_{test_id}",
-    )
-
-
-@pytest.mark.parametrize(
-    "invalid_data,expected_error",
-    [
-        ({}, "Field required"),
-        ({"metric_name": "test"}, "Field required"),
-        (
-            {"metric_name": "test", "metric_value": "not_a_number", "data_string": "x"},
-            "Input should be a valid number",
-        ),
-        (
-            {"metric_name": "", "metric_value": 1.0, "data_string": "test"},
-            "String should have at least 1 character",
-        ),
-        (
-            {"metric_name": "test", "metric_value": 1.0, "data_string": ""},
-            "String should have at least 1 character",
-        ),
-    ],
-    ids=[
-        "empty_request",
-        "missing_metric_value_and_data_string",
-        "invalid_metric_value_type",
-        "empty_metric_name",
-        "empty_data_string",
-    ],
-)
-def test_log_raw_metric_validation_errors(
-    invalid_data: dict,
-    expected_error: str,
-) -> None:
-    """Test validation errors for invalid metric requests."""
-    response = client.post("/log_raw_metric", json=invalid_data)
-
-    assert response.status_code == 422
-    error_detail = response.json()
-    assert "detail" in error_detail, f"Missing 'detail' in error: {error_detail}"
-
-    error_text = json.dumps(error_detail)
-    assert (
-        expected_error in error_text
-    ), f"Expected '{expected_error}' in error response: {error_text}"
-
-
-def test_log_raw_metric_service_error(
-    mocker: pytest_mock.MockFixture,
-    test_user_id: str,
-) -> None:
-    """Test error handling when analytics service fails."""
-    mocker.patch(
-        "backend.data.analytics.log_raw_metric",
-        new_callable=AsyncMock,
-        side_effect=Exception("Database connection failed"),
-    )
-
-    request_data = {
-        "metric_name": "test_metric",
-        "metric_value": 1.0,
-        "data_string": "test",
-    }
-
-    response = client.post("/log_raw_metric", json=request_data)
-
-    assert response.status_code == 500
-    error_detail = response.json()["detail"]
-    assert "Database connection failed" in error_detail["message"]
-    assert "hint" in error_detail
-
-
-# =============================================================================
-# /log_raw_analytics endpoint tests
-# =============================================================================
-
-
-def test_log_raw_analytics_success(
-    mocker: pytest_mock.MockFixture,
-    configured_snapshot: Snapshot,
-    test_user_id: str,
-) -> None:
-    """Test successful raw analytics logging."""
-    mock_result = Mock(id="analytics-789-uuid")
-    mock_log_analytics = mocker.patch(
-        "backend.data.analytics.log_raw_analytics",
-        new_callable=AsyncMock,
-        return_value=mock_result,
-    )
-
-    request_data = {
-        "type": "user_action",
-        "data": {
-            "action": "button_click",
-            "button_id": "submit_form",
-            "timestamp": "2023-01-01T00:00:00Z",
-            "metadata": {"form_type": "registration", "fields_filled": 5},
-        },
-        "data_index": "button_click_submit_form",
-    }
-
-    response = client.post("/log_raw_analytics", json=request_data)
-
-    assert response.status_code == 200, f"Unexpected response: {response.text}"
-    assert response.json() == "analytics-789-uuid"
-
-    mock_log_analytics.assert_called_once_with(
-        test_user_id,
-        "user_action",
-        request_data["data"],
-        "button_click_submit_form",
-    )
-
-    configured_snapshot.assert_match(
-        json.dumps({"analytics_id": response.json()}, indent=2, sort_keys=True),
-        "analytics_log_analytics_success",
-    )
-
-
-def test_log_raw_analytics_complex_data(
-    mocker: pytest_mock.MockFixture,
-    configured_snapshot: Snapshot,
-) -> None:
-    """Test raw analytics logging with complex nested data structures."""
-    mock_result = Mock(id="analytics-complex-uuid")
-    mocker.patch(
-        "backend.data.analytics.log_raw_analytics",
-        new_callable=AsyncMock,
-        return_value=mock_result,
-    )
-
-    request_data = {
-        "type": "agent_execution",
-        "data": {
-            "agent_id": "agent_123",
-            "execution_id": "exec_456",
-            "status": "completed",
-            "duration_ms": 3500,
-            "nodes_executed": 15,
-            "blocks_used": [
-                {"block_id": "llm_block", "count": 3},
-                {"block_id": "http_block", "count": 5},
-                {"block_id": "code_block", "count": 2},
-            ],
-            "errors": [],
-            "metadata": {
-                "trigger": "manual",
-                "user_tier": "premium",
-                "environment": "production",
-            },
-        },
-        "data_index": "agent_123_exec_456",
-    }
-
-    response = client.post("/log_raw_analytics", json=request_data)
-
-    assert response.status_code == 200
-
-    configured_snapshot.assert_match(
-        json.dumps(
-            {"analytics_id": response.json(), "logged_data": request_data["data"]},
-            indent=2,
-            sort_keys=True,
-        ),
-        "analytics_log_analytics_complex_data",
-    )
-
-
-@pytest.mark.parametrize(
-    "invalid_data,expected_error",
-    [
-        ({}, "Field required"),
-        ({"type": "test"}, "Field required"),
-        (
-            {"type": "test", "data": "not_a_dict", "data_index": "test"},
-            "Input should be a valid dictionary",
-        ),
-        ({"type": "test", "data": {"key": "value"}}, "Field required"),
-    ],
-    ids=[
-        "empty_request",
-        "missing_data_and_data_index",
-        "invalid_data_type",
-        "missing_data_index",
-    ],
-)
-def test_log_raw_analytics_validation_errors(
-    invalid_data: dict,
-    expected_error: str,
-) -> None:
-    """Test validation errors for invalid analytics requests."""
-    response = client.post("/log_raw_analytics", json=invalid_data)
-
-    assert response.status_code == 422
-    error_detail = response.json()
-    assert "detail" in error_detail, f"Missing 'detail' in error: {error_detail}"
-
-    error_text = json.dumps(error_detail)
-    assert (
-        expected_error in error_text
-    ), f"Expected '{expected_error}' in error response: {error_text}"
-
-
-def test_log_raw_analytics_service_error(
-    mocker: pytest_mock.MockFixture,
-    test_user_id: str,
-) -> None:
-    """Test error handling when analytics service fails."""
-    mocker.patch(
-        "backend.data.analytics.log_raw_analytics",
-        new_callable=AsyncMock,
-        side_effect=Exception("Analytics DB unreachable"),
-    )
-
-    request_data = {
-        "type": "test_event",
-        "data": {"key": "value"},
-        "data_index": "test_index",
-    }
-
-    response = client.post("/log_raw_analytics", json=request_data)
-
-    assert response.status_code == 500
-    error_detail = response.json()["detail"]
-    assert "Analytics DB unreachable" in error_detail["message"]
-    assert "hint" in error_detail

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

@@ -1,249 +0,0 @@
-"""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,
-        include={"Messages": True},
-    )
-
-
-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

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

@@ -1,597 +0,0 @@
-import asyncio
-import logging
-import uuid
-from datetime import UTC, datetime
-from typing import Any
-from weakref import WeakValueDictionary
-
-from openai.types.chat import (
-    ChatCompletionAssistantMessageParam,
-    ChatCompletionDeveloperMessageParam,
-    ChatCompletionFunctionMessageParam,
-    ChatCompletionMessageParam,
-    ChatCompletionSystemMessageParam,
-    ChatCompletionToolMessageParam,
-    ChatCompletionUserMessageParam,
-)
-from openai.types.chat.chat_completion_assistant_message_param import FunctionCall
-from openai.types.chat.chat_completion_message_tool_call_param import (
-    ChatCompletionMessageToolCallParam,
-    Function,
-)
-from prisma.models import ChatMessage as PrismaChatMessage
-from prisma.models import ChatSession as PrismaChatSession
-from pydantic import BaseModel
-
-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:"
-
-
-def _get_session_cache_key(session_id: str) -> str:
-    """Get the Redis cache key for a chat session."""
-    return f"{CHAT_SESSION_CACHE_PREFIX}{session_id}"
-
-
-# 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):
-    role: str
-    content: str | None = None
-    name: str | None = None
-    tool_call_id: str | None = None
-    refusal: str | None = None
-    tool_calls: list[dict] | None = None
-    function_call: dict | None = None
-
-
-class Usage(BaseModel):
-    prompt_tokens: int
-    completion_tokens: int
-    total_tokens: int
-
-
-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
-    updated_at: datetime
-    successful_agent_runs: dict[str, int] = {}
-    successful_agent_schedules: dict[str, int] = {}
-
-    @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,
-        )
-
-    def to_openai_messages(self) -> list[ChatCompletionMessageParam]:
-        messages = []
-        for message in self.messages:
-            if message.role == "developer":
-                m = ChatCompletionDeveloperMessageParam(
-                    role="developer",
-                    content=message.content or "",
-                )
-                if message.name:
-                    m["name"] = message.name
-                messages.append(m)
-            elif message.role == "system":
-                m = ChatCompletionSystemMessageParam(
-                    role="system",
-                    content=message.content or "",
-                )
-                if message.name:
-                    m["name"] = message.name
-                messages.append(m)
-            elif message.role == "user":
-                m = ChatCompletionUserMessageParam(
-                    role="user",
-                    content=message.content or "",
-                )
-                if message.name:
-                    m["name"] = message.name
-                messages.append(m)
-            elif message.role == "assistant":
-                m = ChatCompletionAssistantMessageParam(
-                    role="assistant",
-                    content=message.content or "",
-                )
-                if message.function_call:
-                    m["function_call"] = FunctionCall(
-                        arguments=message.function_call["arguments"],
-                        name=message.function_call["name"],
-                    )
-                if message.refusal:
-                    m["refusal"] = message.refusal
-                if message.tool_calls:
-                    t: list[ChatCompletionMessageToolCallParam] = []
-                    for tool_call in message.tool_calls:
-                        # Tool calls are stored with nested structure: {id, type, function: {name, arguments}}
-                        function_data = tool_call.get("function", {})
-
-                        # Skip tool calls that are missing required fields
-                        if "id" not in tool_call or "name" not in function_data:
-                            logger.warning(
-                                f"Skipping invalid tool call: missing required fields. "
-                                f"Got: {tool_call.keys()}, function keys: {function_data.keys()}"
-                            )
-                            continue
-
-                        # Arguments are stored as a JSON string
-                        arguments_str = function_data.get("arguments", "{}")
-
-                        t.append(
-                            ChatCompletionMessageToolCallParam(
-                                id=tool_call["id"],
-                                type="function",
-                                function=Function(
-                                    arguments=arguments_str,
-                                    name=function_data["name"],
-                                ),
-                            )
-                        )
-                    m["tool_calls"] = t
-                if message.name:
-                    m["name"] = message.name
-                messages.append(m)
-            elif message.role == "tool":
-                messages.append(
-                    ChatCompletionToolMessageParam(
-                        role="tool",
-                        content=message.content or "",
-                        tool_call_id=message.tool_call_id or "",
-                    )
-                )
-            elif message.role == "function":
-                messages.append(
-                    ChatCompletionFunctionMessageParam(
-                        role="function",
-                        content=message.content,
-                        name=message.name or "",
-                    )
-                )
-        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)
-
-    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 _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 _get_session_from_db(session_id: str) -> ChatSession | None:
-    """Get a chat session from the database."""
-    prisma_session = await chat_db.get_chat_session(session_id)
-    if not prisma_session:
-        return None
-
-    messages = prisma_session.Messages
-    logger.info(
-        f"Loading session {session_id} from DB: "
-        f"has_messages={messages is not None}, "
-        f"message_count={len(messages) if messages else 0}, "
-        f"roles={[m.role for m in messages] if messages else []}"
-    )
-
-    return ChatSession.from_db(prisma_session, messages)
-
-
-async def _save_session_to_db(
-    session: ChatSession, existing_message_count: int
-) -> None:
-    """Save or update a chat session in the database."""
-    # Check if session exists in DB
-    existing = await chat_db.get_chat_session(session.session_id)
-
-    if not existing:
-        # Create new session
-        await chat_db.create_chat_session(
-            session_id=session.session_id,
-            user_id=session.user_id,
-        )
-        existing_message_count = 0
-
-    # Calculate total tokens from usage
-    total_prompt = sum(u.prompt_tokens for u in session.usage)
-    total_completion = sum(u.completion_tokens for u in session.usage)
-
-    # Update session metadata
-    await chat_db.update_chat_session(
-        session_id=session.session_id,
-        credentials=session.credentials,
-        successful_agent_runs=session.successful_agent_runs,
-        successful_agent_schedules=session.successful_agent_schedules,
-        total_prompt_tokens=total_prompt,
-        total_completion_tokens=total_completion,
-    )
-
-    # Add new messages (only those after existing count)
-    new_messages = session.messages[existing_message_count:]
-    if new_messages:
-        messages_data = []
-        for msg in new_messages:
-            messages_data.append(
-                {
-                    "role": msg.role,
-                    "content": msg.content,
-                    "name": msg.name,
-                    "tool_call_id": msg.tool_call_id,
-                    "refusal": msg.refusal,
-                    "tool_calls": msg.tool_calls,
-                    "function_call": msg.function_call,
-                }
-            )
-        logger.info(
-            f"Saving {len(new_messages)} new messages to DB for session {session.session_id}: "
-            f"roles={[m['role'] for m in messages_data]}, "
-            f"start_sequence={existing_message_count}"
-        )
-        await chat_db.add_chat_messages_batch(
-            session_id=session.session_id,
-            messages=messages_data,
-            start_sequence=existing_message_count,
-        )
-
-
-async def get_chat_session(
-    session_id: str,
-    user_id: str | None = None,
-) -> ChatSession | None:
-    """Get a chat session by ID.
-
-    Checks Redis cache first, falls back to database if not found.
-    Caches database results back to Redis.
-
-    Args:
-        session_id: The session ID to fetch.
-        user_id: If provided, validates that the session belongs to this user.
-            If None, ownership is not validated (admin/system access).
-    """
-    # Try cache first
-    try:
-        session = await _get_session_from_cache(session_id)
-        if session:
-            # Verify user ownership if user_id was provided for validation
-            if user_id is not None and session.user_id != user_id:
-                logger.warning(
-                    f"Session {session_id} user id mismatch: {session.user_id} != {user_id}"
-                )
-                return None
-            return session
-    except RedisError:
-        logger.warning(f"Cache error for session {session_id}, trying database")
-    except Exception as e:
-        logger.warning(f"Unexpected cache error for session {session_id}: {e}")
-
-    # Fall back to database
-    logger.info(f"Session {session_id} not in cache, checking database")
-    session = await _get_session_from_db(session_id)
-
-    if session is None:
-        logger.warning(f"Session {session_id} not found in cache or database")
-        return None
-
-    # Verify user ownership if user_id was provided for validation
-    if user_id is not None and session.user_id != user_id:
-        logger.warning(
-            f"Session {session_id} user id mismatch: {session.user_id} != {user_id}"
-        )
-        return None
-
-    # Cache the session from DB
-    try:
-        await _cache_session(session)
-        logger.info(f"Cached session {session_id} from database")
-    except Exception as e:
-        logger.warning(f"Failed to cache session {session_id}: {e}")
-
-    return session
-
-
-async def upsert_chat_session(
-    session: ChatSession,
-) -> ChatSession:
-    """Update a chat session in both cache and database.
-
-    Uses session-level locking to prevent race conditions when concurrent
-    operations (e.g., background title update and main stream handler)
-    attempt to upsert the same session simultaneously.
-
-    Raises:
-        DatabaseError: If the database write fails. The cache is still updated
-            as a best-effort optimization, but the error is propagated to ensure
-            callers are aware of the persistence failure.
-        RedisError: If the cache write fails (after successful DB write).
-    """
-    # Acquire session-specific lock to prevent concurrent upserts
-    lock = await _get_session_lock(session.session_id)
-
-    async with lock:
-        # 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)
-        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)
-        try:
-            await _cache_session(session)
-        except Exception as e:
-            # If DB succeeded but cache failed, raise cache error
-            if db_error is None:
-                raise RedisError(
-                    f"Failed to persist chat session {session.session_id} to Redis: {e}"
-                ) from e
-            # If both failed, log cache error but raise DB error (more critical)
-            logger.warning(
-                f"Cache write also failed for session {session.session_id}: {e}"
-            )
-
-        # Propagate DB error after attempting cache (prevents data loss)
-        if db_error is not None:
-            raise DatabaseError(
-                f"Failed to persist chat session {session.session_id} to database"
-            ) from db_error
-
-        return session
-
-
-async def create_chat_session(user_id: str) -> ChatSession:
-    """Create a new chat session and persist it.
-
-    Raises:
-        DatabaseError: If the database write fails. We fail fast to ensure
-            callers never receive a non-persisted session that only exists
-            in cache (which would be lost when the cache expires).
-    """
-    session = ChatSession.new(user_id)
-
-    # Create in database first - fail fast if this fails
-    try:
-        await chat_db.create_chat_session(
-            session_id=session.session_id,
-            user_id=user_id,
-        )
-    except Exception as e:
-        logger.error(f"Failed to create session {session.session_id} in database: {e}")
-        raise DatabaseError(
-            f"Failed to create chat session {session.session_id} in database"
-        ) from e
-
-    # Cache the session (best-effort optimization, DB is source of truth)
-    try:
-        await _cache_session(session)
-    except Exception as e:
-        logger.warning(f"Failed to cache new session {session.session_id}: {e}")
-
-    return session
-
-
-async def get_user_sessions(
-    user_id: str,
-    limit: int = 50,
-    offset: int = 0,
-) -> 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).
-    """
-    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
-
-
-async def delete_chat_session(session_id: str, user_id: str | None = None) -> bool:
-    """Delete a chat session from both cache and database.
-
-    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.
-
-    Returns:
-        True if deleted successfully, False otherwise.
-    """
-    # 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)
-
-    if not deleted:
-        return False
-
-    # Only invalidate cache and clean up lock after DB confirms deletion
-    try:
-        redis_key = _get_session_cache_key(session_id)
-        async_redis = await get_redis_async()
-        await async_redis.delete(redis_key)
-    except Exception as e:
-        logger.warning(f"Failed to delete session {session_id} from cache: {e}")
-
-    # Clean up session lock (belt-and-suspenders with WeakValueDictionary)
-    async with _session_locks_mutex:
-        _session_locks.pop(session_id, None)
-
-    return True
-
-
-async def update_session_title(session_id: str, title: str) -> bool:
-    """Update only the title of a chat session.
-
-    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.
-        title: The new title to set.
-
-    Returns:
-        True if updated successfully, False otherwise.
-    """
-    try:
-        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
-
-        # Invalidate cache so next fetch gets updated title
-        try:
-            redis_key = _get_session_cache_key(session_id)
-            async_redis = await get_redis_async()
-            await async_redis.delete(redis_key)
-        except Exception as e:
-            logger.warning(f"Failed to invalidate cache for session {session_id}: {e}")
-
-        return True
-    except Exception as e:
-        logger.error(f"Failed to update title for session {session_id}: {e}")
-        return False

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

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

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

@@ -1,144 +0,0 @@
-"""
-Response models for Vercel AI SDK UI Stream Protocol.
-
-This module implements the AI SDK UI Stream Protocol (v1) for streaming chat responses.
-See: https://ai-sdk.dev/docs/ai-sdk-ui/stream-protocol
-"""
-
-from enum import Enum
-from typing import Any
-
-from pydantic import BaseModel, Field
-
-
-class ResponseType(str, Enum):
-    """Types of streaming responses following AI SDK protocol."""
-
-    # Message lifecycle
-    START = "start"
-    FINISH = "finish"
-
-    # Text streaming
-    TEXT_START = "text-start"
-    TEXT_DELTA = "text-delta"
-    TEXT_END = "text-end"
-
-    # Tool interaction
-    TOOL_INPUT_START = "tool-input-start"
-    TOOL_INPUT_AVAILABLE = "tool-input-available"
-    TOOL_OUTPUT_AVAILABLE = "tool-output-available"
-
-    # Other
-    ERROR = "error"
-    USAGE = "usage"
-
-
-class StreamBaseResponse(BaseModel):
-    """Base response model for all streaming responses."""
-
-    type: ResponseType
-
-    def to_sse(self) -> str:
-        """Convert to SSE format."""
-        return f"data: {self.model_dump_json()}\n\n"
-
-
-# ========== Message Lifecycle ==========
-
-
-class StreamStart(StreamBaseResponse):
-    """Start of a new message."""
-
-    type: ResponseType = ResponseType.START
-    messageId: str = Field(..., description="Unique message ID")
-
-
-class StreamFinish(StreamBaseResponse):
-    """End of message/stream."""
-
-    type: ResponseType = ResponseType.FINISH
-
-
-# ========== Text Streaming ==========
-
-
-class StreamTextStart(StreamBaseResponse):
-    """Start of a text block."""
-
-    type: ResponseType = ResponseType.TEXT_START
-    id: str = Field(..., description="Text block ID")
-
-
-class StreamTextDelta(StreamBaseResponse):
-    """Streaming text content delta."""
-
-    type: ResponseType = ResponseType.TEXT_DELTA
-    id: str = Field(..., description="Text block ID")
-    delta: str = Field(..., description="Text content delta")
-
-
-class StreamTextEnd(StreamBaseResponse):
-    """End of a text block."""
-
-    type: ResponseType = ResponseType.TEXT_END
-    id: str = Field(..., description="Text block ID")
-
-
-# ========== Tool Interaction ==========
-
-
-class StreamToolInputStart(StreamBaseResponse):
-    """Tool call started notification."""
-
-    type: ResponseType = ResponseType.TOOL_INPUT_START
-    toolCallId: str = Field(..., description="Unique tool call ID")
-    toolName: str = Field(..., description="Name of the tool being called")
-
-
-class StreamToolInputAvailable(StreamBaseResponse):
-    """Tool input is ready for execution."""
-
-    type: ResponseType = ResponseType.TOOL_INPUT_AVAILABLE
-    toolCallId: str = Field(..., description="Unique tool call ID")
-    toolName: str = Field(..., description="Name of the tool being called")
-    input: dict[str, Any] = Field(
-        default_factory=dict, description="Tool input arguments"
-    )
-
-
-class StreamToolOutputAvailable(StreamBaseResponse):
-    """Tool execution result."""
-
-    type: ResponseType = ResponseType.TOOL_OUTPUT_AVAILABLE
-    toolCallId: str = Field(..., description="Tool call ID this responds to")
-    output: str | dict[str, Any] = Field(..., description="Tool execution output")
-    # Additional fields for internal use (not part of AI SDK spec but useful)
-    toolName: str | None = Field(
-        default=None, description="Name of the tool that was executed"
-    )
-    success: bool = Field(
-        default=True, description="Whether the tool execution succeeded"
-    )
-
-
-# ========== Other ==========
-
-
-class StreamUsage(StreamBaseResponse):
-    """Token usage statistics."""
-
-    type: ResponseType = ResponseType.USAGE
-    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):
-    """Error response."""
-
-    type: ResponseType = ResponseType.ERROR
-    errorText: str = Field(..., description="Error message text")
-    code: str | None = Field(default=None, description="Error code")
-    details: dict[str, Any] | None = Field(
-        default=None, description="Additional error details"
-    )

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

@@ -1,362 +0,0 @@
-"""Chat API routes for chat session management and streaming via SSE."""
-
-import logging
-from collections.abc import AsyncGenerator
-from typing import Annotated
-
-from autogpt_libs import auth
-from fastapi import APIRouter, Depends, Query, Security
-from fastapi.responses import StreamingResponse
-from pydantic import BaseModel
-
-from backend.util.exceptions import NotFoundError
-
-from . import service as chat_service
-from .config import ChatConfig
-from .model import ChatSession, create_chat_session, get_chat_session, get_user_sessions
-
-config = ChatConfig()
-
-
-logger = logging.getLogger(__name__)
-
-
-async def _validate_and_get_session(
-    session_id: str,
-    user_id: str | None,
-) -> ChatSession:
-    """Validate session exists and belongs to user."""
-    session = await get_chat_session(session_id, user_id)
-    if not session:
-        raise NotFoundError(f"Session {session_id} not found.")
-    return session
-
-
-router = APIRouter(
-    tags=["chat"],
-)
-
-# ========== Request/Response Models ==========
-
-
-class StreamChatRequest(BaseModel):
-    """Request model for streaming chat with optional context."""
-
-    message: str
-    is_user_message: bool = True
-    context: dict[str, str] | None = None  # {url: str, content: str}
-
-
-class CreateSessionResponse(BaseModel):
-    """Response model containing information on a newly created chat session."""
-
-    id: str
-    created_at: str
-    user_id: str | None
-
-
-class SessionDetailResponse(BaseModel):
-    """Response model providing complete details for a chat session, including messages."""
-
-    id: str
-    created_at: str
-    updated_at: str
-    user_id: str | None
-    messages: list[dict]
-
-
-class SessionSummaryResponse(BaseModel):
-    """Response model for a session summary (without messages)."""
-
-    id: str
-    created_at: str
-    updated_at: str
-    title: str | None = None
-
-
-class ListSessionsResponse(BaseModel):
-    """Response model for listing chat sessions."""
-
-    sessions: list[SessionSummaryResponse]
-    total: int
-
-
-# ========== Routes ==========
-
-
-@router.get(
-    "/sessions",
-    dependencies=[Security(auth.requires_user)],
-)
-async def list_sessions(
-    user_id: Annotated[str, Security(auth.get_user_id)],
-    limit: int = Query(default=50, ge=1, le=100),
-    offset: int = Query(default=0, ge=0),
-) -> ListSessionsResponse:
-    """
-    List chat sessions for the authenticated user.
-
-    Returns a paginated list of chat sessions belonging to the current user,
-    ordered by most recently updated.
-
-    Args:
-        user_id: The authenticated user's ID.
-        limit: Maximum number of sessions to return (1-100).
-        offset: Number of sessions to skip for pagination.
-
-    Returns:
-        ListSessionsResponse: List of session summaries and total count.
-    """
-    sessions, total_count = await get_user_sessions(user_id, limit, offset)
-
-    return ListSessionsResponse(
-        sessions=[
-            SessionSummaryResponse(
-                id=session.session_id,
-                created_at=session.started_at.isoformat(),
-                updated_at=session.updated_at.isoformat(),
-                title=session.title,
-            )
-            for session in sessions
-        ],
-        total=total_count,
-    )
-
-
-@router.post(
-    "/sessions",
-)
-async def create_session(
-    user_id: Annotated[str, Depends(auth.get_user_id)],
-) -> CreateSessionResponse:
-    """
-    Create a new chat session.
-
-    Initiates a new chat session for the authenticated user.
-
-    Args:
-        user_id: The authenticated user ID parsed from the JWT (required).
-
-    Returns:
-        CreateSessionResponse: Details of the created session.
-
-    """
-    logger.info(
-        f"Creating session with user_id: "
-        f"...{user_id[-8:] if len(user_id) > 8 else '<redacted>'}"
-    )
-
-    session = await create_chat_session(user_id)
-
-    return CreateSessionResponse(
-        id=session.session_id,
-        created_at=session.started_at.isoformat(),
-        user_id=session.user_id,
-    )
-
-
-@router.get(
-    "/sessions/{session_id}",
-)
-async def get_session(
-    session_id: str,
-    user_id: Annotated[str | None, Depends(auth.get_user_id)],
-) -> SessionDetailResponse:
-    """
-    Retrieve the details of a specific chat session.
-
-    Looks up a chat session by ID for the given user (if authenticated) and returns all session data including messages.
-
-    Args:
-        session_id: The unique identifier for the desired chat session.
-        user_id: The optional authenticated user ID, or None for anonymous access.
-
-    Returns:
-        SessionDetailResponse: Details for the requested session; raises NotFoundError if not found.
-
-    """
-    session = await get_chat_session(session_id, user_id)
-    if not session:
-        raise NotFoundError(f"Session {session_id} not found")
-
-    messages = [message.model_dump() for message in session.messages]
-    logger.info(
-        f"Returning session {session_id}: "
-        f"message_count={len(messages)}, "
-        f"roles={[m.get('role') for m in messages]}"
-    )
-
-    return SessionDetailResponse(
-        id=session.session_id,
-        created_at=session.started_at.isoformat(),
-        updated_at=session.updated_at.isoformat(),
-        user_id=session.user_id or None,
-        messages=messages,
-    )
-
-
-@router.post(
-    "/sessions/{session_id}/stream",
-)
-async def stream_chat_post(
-    session_id: str,
-    request: StreamChatRequest,
-    user_id: str | None = Depends(auth.get_user_id),
-):
-    """
-    Stream chat responses for a session (POST with context support).
-
-    Streams the AI/completion responses in real time over Server-Sent Events (SSE), including:
-      - Text fragments as they are generated
-      - Tool call UI elements (if invoked)
-      - Tool execution results
-
-    Args:
-        session_id: The chat session identifier to associate with the streamed messages.
-        request: Request body containing message, is_user_message, and optional context.
-        user_id: Optional authenticated user ID.
-    Returns:
-        StreamingResponse: SSE-formatted response chunks.
-
-    """
-    session = await _validate_and_get_session(session_id, user_id)
-
-    async def event_generator() -> AsyncGenerator[str, None]:
-        async for chunk in chat_service.stream_chat_completion(
-            session_id,
-            request.message,
-            is_user_message=request.is_user_message,
-            user_id=user_id,
-            session=session,  # Pass pre-fetched session to avoid double-fetch
-            context=request.context,
-        ):
-            yield chunk.to_sse()
-        # AI SDK protocol termination
-        yield "data: [DONE]\n\n"
-
-    return StreamingResponse(
-        event_generator(),
-        media_type="text/event-stream",
-        headers={
-            "Cache-Control": "no-cache",
-            "Connection": "keep-alive",
-            "X-Accel-Buffering": "no",  # Disable nginx buffering
-            "x-vercel-ai-ui-message-stream": "v1",  # AI SDK protocol header
-        },
-    )
-
-
-@router.get(
-    "/sessions/{session_id}/stream",
-)
-async def stream_chat_get(
-    session_id: str,
-    message: Annotated[str, Query(min_length=1, max_length=10000)],
-    user_id: str | None = Depends(auth.get_user_id),
-    is_user_message: bool = Query(default=True),
-):
-    """
-    Stream chat responses for a session (GET - legacy endpoint).
-
-    Streams the AI/completion responses in real time over Server-Sent Events (SSE), including:
-      - Text fragments as they are generated
-      - Tool call UI elements (if invoked)
-      - Tool execution results
-
-    Args:
-        session_id: The chat session identifier to associate with the streamed messages.
-        message: The user's new message to process.
-        user_id: Optional authenticated user ID.
-        is_user_message: Whether the message is a user message.
-    Returns:
-        StreamingResponse: SSE-formatted response chunks.
-
-    """
-    session = await _validate_and_get_session(session_id, user_id)
-
-    async def event_generator() -> AsyncGenerator[str, None]:
-        async for chunk in chat_service.stream_chat_completion(
-            session_id,
-            message,
-            is_user_message=is_user_message,
-            user_id=user_id,
-            session=session,  # Pass pre-fetched session to avoid double-fetch
-        ):
-            yield chunk.to_sse()
-        # AI SDK protocol termination
-        yield "data: [DONE]\n\n"
-
-    return StreamingResponse(
-        event_generator(),
-        media_type="text/event-stream",
-        headers={
-            "Cache-Control": "no-cache",
-            "Connection": "keep-alive",
-            "X-Accel-Buffering": "no",  # Disable nginx buffering
-            "x-vercel-ai-ui-message-stream": "v1",  # AI SDK protocol header
-        },
-    )
-
-
-@router.patch(
-    "/sessions/{session_id}/assign-user",
-    dependencies=[Security(auth.requires_user)],
-    status_code=200,
-)
-async def session_assign_user(
-    session_id: str,
-    user_id: Annotated[str, Security(auth.get_user_id)],
-) -> dict:
-    """
-    Assign an authenticated user to a chat session.
-
-    Used (typically post-login) to claim an existing anonymous session as the current authenticated user.
-
-    Args:
-        session_id: The identifier for the (previously anonymous) session.
-        user_id: The authenticated user's ID to associate with the session.
-
-    Returns:
-        dict: Status of the assignment.
-
-    """
-    await chat_service.assign_user_to_session(session_id, user_id)
-    return {"status": "ok"}
-
-
-# ========== Health Check ==========
-
-
-@router.get("/health", status_code=200)
-async def health_check() -> dict:
-    """
-    Health check endpoint for the chat service.
-
-    Performs a full cycle test of session creation and retrieval. Should always return healthy
-    if the service and data layer are operational.
-
-    Returns:
-        dict: A status dictionary indicating health, service name, and API version.
-
-    """
-    from backend.data.user import get_or_create_user
-
-    # Ensure health check user exists (required for FK constraint)
-    health_check_user_id = "health-check-user"
-    await get_or_create_user(
-        {
-            "sub": health_check_user_id,
-            "email": "health-check@system.local",
-            "user_metadata": {"name": "Health Check User"},
-        }
-    )
-
-    # Create and retrieve session to verify full data layer
-    session = await create_chat_session(health_check_user_id)
-    await get_chat_session(session.session_id, health_check_user_id)
-
-    return {
-        "status": "healthy",
-        "service": "chat",
-        "version": "0.1.0",
-    }

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

@@ -1,907 +0,0 @@
-import asyncio
-import logging
-from collections.abc import AsyncGenerator
-from typing import Any
-
-import orjson
-from langfuse import Langfuse
-from openai import (
-    APIConnectionError,
-    APIError,
-    APIStatusError,
-    AsyncOpenAI,
-    RateLimitError,
-)
-from openai.types.chat import ChatCompletionChunk, ChatCompletionToolParam
-
-from backend.data.understanding import (
-    format_understanding_for_prompt,
-    get_business_understanding,
-)
-from backend.util.exceptions import NotFoundError
-from backend.util.settings import Settings
-
-from . import db as chat_db
-from .config import ChatConfig
-from .model import (
-    ChatMessage,
-    ChatSession,
-    Usage,
-    get_chat_session,
-    update_session_title,
-    upsert_chat_session,
-)
-from .response_model import (
-    StreamBaseResponse,
-    StreamError,
-    StreamFinish,
-    StreamStart,
-    StreamTextDelta,
-    StreamTextEnd,
-    StreamTextStart,
-    StreamToolInputAvailable,
-    StreamToolInputStart,
-    StreamToolOutputAvailable,
-    StreamUsage,
-)
-from .tools import execute_tool, tools
-
-logger = logging.getLogger(__name__)
-
-config = ChatConfig()
-settings = Settings()
-client = AsyncOpenAI(api_key=config.api_key, base_url=config.base_url)
-
-# Langfuse client (lazy initialization)
-_langfuse_client: Langfuse | None = None
-
-
-class LangfuseNotConfiguredError(Exception):
-    """Raised when Langfuse is required but not configured."""
-
-    pass
-
-
-def _is_langfuse_configured() -> bool:
-    """Check if Langfuse credentials are configured."""
-    return bool(
-        settings.secrets.langfuse_public_key and settings.secrets.langfuse_secret_key
-    )
-
-
-def _get_langfuse_client() -> Langfuse:
-    """Get or create the Langfuse client for prompt management and tracing."""
-    global _langfuse_client
-    if _langfuse_client is None:
-        if not _is_langfuse_configured():
-            raise LangfuseNotConfiguredError(
-                "Langfuse is not configured. The chat feature requires Langfuse for prompt management. "
-                "Please set the LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY environment variables."
-            )
-        _langfuse_client = Langfuse(
-            public_key=settings.secrets.langfuse_public_key,
-            secret_key=settings.secrets.langfuse_secret_key,
-            host=settings.secrets.langfuse_host or "https://cloud.langfuse.com",
-        )
-    return _langfuse_client
-
-
-def _get_environment() -> str:
-    """Get the current environment name for Langfuse tagging."""
-    return settings.config.app_env.value
-
-
-def _get_langfuse_prompt() -> str:
-    """Fetch the latest production prompt from Langfuse.
-
-    Returns:
-        The compiled prompt text from Langfuse.
-
-    Raises:
-        Exception: If Langfuse is unavailable or prompt fetch fails.
-    """
-    try:
-        langfuse = _get_langfuse_client()
-        # cache_ttl_seconds=0 disables SDK caching to always get the latest prompt
-        prompt = langfuse.get_prompt(config.langfuse_prompt_name, cache_ttl_seconds=0)
-        compiled = prompt.compile()
-        logger.info(
-            f"Fetched prompt '{config.langfuse_prompt_name}' from Langfuse "
-            f"(version: {prompt.version})"
-        )
-        return compiled
-    except Exception as e:
-        logger.error(f"Failed to fetch prompt from Langfuse: {e}")
-        raise
-
-
-async def _is_first_session(user_id: str) -> bool:
-    """Check if this is the user's first chat session.
-
-    Returns True if the user has 1 or fewer sessions (meaning this is their first).
-    """
-    try:
-        session_count = await chat_db.get_user_session_count(user_id)
-        return session_count <= 1
-    except Exception as e:
-        logger.warning(f"Failed to check session count for user {user_id}: {e}")
-        return False  # Default to non-onboarding if we can't check
-
-
-async def _build_system_prompt(user_id: str | None) -> tuple[str, Any]:
-    """Build the full system prompt including business understanding if available.
-
-    Args:
-        user_id: The user ID for fetching business understanding
-                     If "default" and this is the user's first session, will use "onboarding" instead.
-
-    Returns:
-        Tuple of (compiled prompt string, Langfuse prompt object for tracing)
-    """
-
-    langfuse = _get_langfuse_client()
-
-    # cache_ttl_seconds=0 disables SDK caching to always get the latest prompt
-    prompt = langfuse.get_prompt(config.langfuse_prompt_name, cache_ttl_seconds=0)
-
-    # If user is authenticated, try to fetch their business understanding
-    understanding = None
-    if user_id:
-        try:
-            understanding = await get_business_understanding(user_id)
-        except Exception as e:
-            logger.warning(f"Failed to fetch business understanding: {e}")
-            understanding = None
-    if understanding:
-        context = format_understanding_for_prompt(understanding)
-    else:
-        context = "This is the first time you are meeting the user. Greet them and introduce them to the platform"
-
-    compiled = prompt.compile(users_information=context)
-    return compiled, prompt
-
-
-async def _generate_session_title(message: str) -> str | None:
-    """Generate a concise title for a chat session based on the first message.
-
-    Args:
-        message: The first user message in the session
-
-    Returns:
-        A short title (3-6 words) or None if generation fails
-    """
-    try:
-        response = await client.chat.completions.create(
-            model=config.title_model,
-            messages=[
-                {
-                    "role": "system",
-                    "content": (
-                        "Generate a very short title (3-6 words) for a chat conversation "
-                        "based on the user's first message. The title should capture the "
-                        "main topic or intent. Return ONLY the title, no quotes or punctuation."
-                    ),
-                },
-                {"role": "user", "content": message[:500]},  # Limit input length
-            ],
-            max_tokens=20,
-        )
-        title = response.choices[0].message.content
-        if title:
-            # Clean up the title
-            title = title.strip().strip("\"'")
-            # Limit length
-            if len(title) > 50:
-                title = title[:47] + "..."
-            return title
-        return None
-    except Exception as e:
-        logger.warning(f"Failed to generate session title: {e}")
-        return None
-
-
-async def assign_user_to_session(
-    session_id: str,
-    user_id: str,
-) -> ChatSession:
-    """
-    Assign a user to a chat session.
-    """
-    session = await get_chat_session(session_id, None)
-    if not session:
-        raise NotFoundError(f"Session {session_id} not found")
-    session.user_id = user_id
-    return await upsert_chat_session(session)
-
-
-async def stream_chat_completion(
-    session_id: str,
-    message: str | None = None,
-    is_user_message: bool = True,
-    user_id: str | None = None,
-    retry_count: int = 0,
-    session: ChatSession | None = None,
-    context: dict[str, str] | None = None,  # {url: str, content: str}
-) -> AsyncGenerator[StreamBaseResponse, None]:
-    """Main entry point for streaming chat completions with database handling.
-
-    This function handles all database operations and delegates streaming
-    to the internal _stream_chat_chunks function.
-
-    Args:
-        session_id: Chat session ID
-        user_message: User's input message
-        user_id: User ID for authentication (None for anonymous)
-        session: Optional pre-loaded session object (for recursive calls to avoid Redis refetch)
-
-    Yields:
-        StreamBaseResponse objects formatted as SSE
-
-    Raises:
-        NotFoundError: If session_id is invalid
-        ValueError: If max_context_messages is exceeded
-
-    """
-    logger.info(
-        f"Streaming chat completion for session {session_id} for message {message} and user id {user_id}. Message is user message: {is_user_message}"
-    )
-
-    # Check if Langfuse is configured - required for chat functionality
-    if not _is_langfuse_configured():
-        logger.error("Chat request failed: Langfuse is not configured")
-        yield StreamError(
-            errorText="Chat service is not available. Langfuse must be configured "
-            "with LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY environment variables."
-        )
-        yield StreamFinish()
-        return
-
-    # Langfuse observations will be created after session is loaded (need messages for input)
-    # Initialize to None so finally block can safely check and end them
-    trace = None
-    generation = None
-
-    # Only fetch from Redis if session not provided (initial call)
-    if session is None:
-        session = await get_chat_session(session_id, user_id)
-        logger.info(
-            f"Fetched session from Redis: {session.session_id if session else 'None'}, "
-            f"message_count={len(session.messages) if session else 0}"
-        )
-    else:
-        logger.info(
-            f"Using provided session object: {session.session_id}, "
-            f"message_count={len(session.messages)}"
-        )
-
-    if not session:
-        raise NotFoundError(
-            f"Session {session_id} not found. Please create a new session first."
-        )
-
-    if message:
-        # Build message content with context if provided
-        message_content = message
-        if context and context.get("url") and context.get("content"):
-            context_text = f"Page URL: {context['url']}\n\nPage Content:\n{context['content']}\n\n---\n\nUser Message: {message}"
-            message_content = context_text
-            logger.info(
-                f"Including page context: URL={context['url']}, content_length={len(context['content'])}"
-            )
-
-        session.messages.append(
-            ChatMessage(
-                role="user" if is_user_message else "assistant", content=message_content
-            )
-        )
-        logger.info(
-            f"Appended message (role={'user' if is_user_message else 'assistant'}), "
-            f"new message_count={len(session.messages)}"
-        )
-
-    if len(session.messages) > config.max_context_messages:
-        raise ValueError(f"Max messages exceeded: {config.max_context_messages}")
-
-    logger.info(
-        f"Upserting session: {session.session_id} with user id {session.user_id}, "
-        f"message_count={len(session.messages)}"
-    )
-    session = await upsert_chat_session(session)
-    assert session, "Session not found"
-
-    # Generate title for new sessions on first user message (non-blocking)
-    # Check: is_user_message, no title yet, and this is the first user message
-    if is_user_message and message and not session.title:
-        user_messages = [m for m in session.messages if m.role == "user"]
-        if len(user_messages) == 1:
-            # First user message - generate title in background
-            import asyncio
-
-            # Capture only the values we need (not the session object) to avoid
-            # stale data issues when the main flow modifies the session
-            captured_session_id = session_id
-            captured_message = message
-
-            async def _update_title():
-                try:
-                    title = await _generate_session_title(captured_message)
-                    if title:
-                        # Use dedicated title update function that doesn't
-                        # touch messages, avoiding race conditions
-                        await update_session_title(captured_session_id, title)
-                        logger.info(
-                            f"Generated title for session {captured_session_id}: {title}"
-                        )
-                except Exception as e:
-                    logger.warning(f"Failed to update session title: {e}")
-
-            # Fire and forget - don't block the chat response
-            asyncio.create_task(_update_title())
-
-    # Build system prompt with business understanding
-    system_prompt, langfuse_prompt = await _build_system_prompt(user_id)
-
-    # Build input messages including system prompt for complete Langfuse logging
-    trace_input_messages = [{"role": "system", "content": system_prompt}] + [
-        m.model_dump() for m in session.messages
-    ]
-
-    # Create Langfuse trace for this LLM call (each call gets its own trace, grouped by session_id)
-    # Using v3 SDK: start_observation creates a root span, update_trace sets trace-level attributes
-    try:
-        langfuse = _get_langfuse_client()
-        env = _get_environment()
-        trace = langfuse.start_observation(
-            name="chat_completion",
-            input={"messages": trace_input_messages},
-            metadata={
-                "environment": env,
-                "model": config.model,
-                "message_count": len(session.messages),
-                "prompt_name": langfuse_prompt.name if langfuse_prompt else None,
-                "prompt_version": langfuse_prompt.version if langfuse_prompt else None,
-            },
-        )
-        # Set trace-level attributes (session_id, user_id, tags)
-        trace.update_trace(
-            session_id=session_id,
-            user_id=user_id,
-            tags=[env, "copilot"],
-        )
-    except Exception as e:
-        logger.warning(f"Failed to create Langfuse trace: {e}")
-
-    # Initialize variables that will be used in finally block (must be defined before try)
-    assistant_response = ChatMessage(
-        role="assistant",
-        content="",
-    )
-    accumulated_tool_calls: list[dict[str, Any]] = []
-
-    # Wrap main logic in try/finally to ensure Langfuse observations are always ended
-    try:
-        has_yielded_end = False
-        has_yielded_error = False
-        has_done_tool_call = False
-        has_received_text = False
-        text_streaming_ended = False
-        tool_response_messages: list[ChatMessage] = []
-        should_retry = False
-
-        # Generate unique IDs for AI SDK protocol
-        import uuid as uuid_module
-
-        message_id = str(uuid_module.uuid4())
-        text_block_id = str(uuid_module.uuid4())
-
-        # Yield message start
-        yield StreamStart(messageId=message_id)
-
-        # Create Langfuse generation for each LLM call, linked to the prompt
-        # Using v3 SDK: start_observation with as_type="generation"
-        generation = (
-            trace.start_observation(
-                as_type="generation",
-                name="llm_call",
-                model=config.model,
-                input={"messages": trace_input_messages},
-                prompt=langfuse_prompt,
-            )
-            if trace
-            else None
-        )
-
-        try:
-            async for chunk in _stream_chat_chunks(
-                session=session,
-                tools=tools,
-                system_prompt=system_prompt,
-                text_block_id=text_block_id,
-            ):
-
-                if isinstance(chunk, StreamTextStart):
-                    # Emit text-start before first text delta
-                    if not has_received_text:
-                        yield chunk
-                elif isinstance(chunk, StreamTextDelta):
-                    delta = chunk.delta or ""
-                    assert assistant_response.content is not None
-                    assistant_response.content += delta
-                    has_received_text = True
-                    yield chunk
-                elif isinstance(chunk, StreamTextEnd):
-                    # Emit text-end after text completes
-                    if has_received_text and not text_streaming_ended:
-                        text_streaming_ended = True
-                        yield chunk
-                elif isinstance(chunk, StreamToolInputStart):
-                    # Emit text-end before first tool call, but only if we've received text
-                    if has_received_text and not text_streaming_ended:
-                        yield StreamTextEnd(id=text_block_id)
-                        text_streaming_ended = True
-                    yield chunk
-                elif isinstance(chunk, StreamToolInputAvailable):
-                    # Accumulate tool calls in OpenAI format
-                    accumulated_tool_calls.append(
-                        {
-                            "id": chunk.toolCallId,
-                            "type": "function",
-                            "function": {
-                                "name": chunk.toolName,
-                                "arguments": orjson.dumps(chunk.input).decode("utf-8"),
-                            },
-                        }
-                    )
-                elif isinstance(chunk, StreamToolOutputAvailable):
-                    result_content = (
-                        chunk.output
-                        if isinstance(chunk.output, str)
-                        else orjson.dumps(chunk.output).decode("utf-8")
-                    )
-                    tool_response_messages.append(
-                        ChatMessage(
-                            role="tool",
-                            content=result_content,
-                            tool_call_id=chunk.toolCallId,
-                        )
-                    )
-                    has_done_tool_call = True
-                    # Track if any tool execution failed
-                    if not chunk.success:
-                        logger.warning(
-                            f"Tool {chunk.toolName} (ID: {chunk.toolCallId}) execution failed"
-                        )
-                    yield chunk
-                elif isinstance(chunk, StreamFinish):
-                    if not has_done_tool_call:
-                        # Emit text-end before finish if we received text but haven't closed it
-                        if has_received_text and not text_streaming_ended:
-                            yield StreamTextEnd(id=text_block_id)
-                            text_streaming_ended = True
-                        has_yielded_end = True
-                        yield chunk
-                elif isinstance(chunk, StreamError):
-                    has_yielded_error = True
-                elif isinstance(chunk, StreamUsage):
-                    session.usage.append(
-                        Usage(
-                            prompt_tokens=chunk.promptTokens,
-                            completion_tokens=chunk.completionTokens,
-                            total_tokens=chunk.totalTokens,
-                        )
-                    )
-                else:
-                    logger.error(f"Unknown chunk type: {type(chunk)}", exc_info=True)
-        except Exception as e:
-            logger.error(f"Error during stream: {e!s}", exc_info=True)
-
-            # Check if this is a retryable error (JSON parsing, incomplete tool calls, etc.)
-            is_retryable = isinstance(e, (orjson.JSONDecodeError, KeyError, TypeError))
-
-            if is_retryable and retry_count < config.max_retries:
-                logger.info(
-                    f"Retryable error encountered. Attempt {retry_count + 1}/{config.max_retries}"
-                )
-                should_retry = True
-            else:
-                # Non-retryable error or max retries exceeded
-                # Save any partial progress before reporting error
-                messages_to_save: list[ChatMessage] = []
-
-                # Add assistant message if it has content or tool calls
-                if accumulated_tool_calls:
-                    assistant_response.tool_calls = accumulated_tool_calls
-                if assistant_response.content or assistant_response.tool_calls:
-                    messages_to_save.append(assistant_response)
-
-                # Add tool response messages after assistant message
-                messages_to_save.extend(tool_response_messages)
-
-                session.messages.extend(messages_to_save)
-                await upsert_chat_session(session)
-
-                if not has_yielded_error:
-                    error_message = str(e)
-                    if not is_retryable:
-                        error_message = f"Non-retryable error: {error_message}"
-                    elif retry_count >= config.max_retries:
-                        error_message = f"Max retries ({config.max_retries}) exceeded: {error_message}"
-
-                    error_response = StreamError(errorText=error_message)
-                    yield error_response
-                if not has_yielded_end:
-                    yield StreamFinish()
-                return
-
-        # Handle retry outside of exception handler to avoid nesting
-        if should_retry and retry_count < config.max_retries:
-            logger.info(
-                f"Retrying stream_chat_completion for session {session_id}, attempt {retry_count + 1}"
-            )
-            async for chunk in stream_chat_completion(
-                session_id=session.session_id,
-                user_id=user_id,
-                retry_count=retry_count + 1,
-                session=session,
-                context=context,
-            ):
-                yield chunk
-            return  # Exit after retry to avoid double-saving in finally block
-
-        # Normal completion path - save session and handle tool call continuation
-        logger.info(
-            f"Normal completion path: session={session.session_id}, "
-            f"current message_count={len(session.messages)}"
-        )
-
-        # Build the messages list in the correct order
-        messages_to_save: list[ChatMessage] = []
-
-        # Add assistant message with tool_calls if any
-        if accumulated_tool_calls:
-            assistant_response.tool_calls = accumulated_tool_calls
-            logger.info(
-                f"Added {len(accumulated_tool_calls)} tool calls to assistant message"
-            )
-        if assistant_response.content or assistant_response.tool_calls:
-            messages_to_save.append(assistant_response)
-            logger.info(
-                f"Saving assistant message with content_len={len(assistant_response.content or '')}, tool_calls={len(assistant_response.tool_calls or [])}"
-            )
-
-        # Add tool response messages after assistant message
-        messages_to_save.extend(tool_response_messages)
-        logger.info(
-            f"Saving {len(tool_response_messages)} tool response messages, "
-            f"total_to_save={len(messages_to_save)}"
-        )
-
-        session.messages.extend(messages_to_save)
-        logger.info(
-            f"Extended session messages, new message_count={len(session.messages)}"
-        )
-        await upsert_chat_session(session)
-
-        # If we did a tool call, stream the chat completion again to get the next response
-        if has_done_tool_call:
-            logger.info(
-                "Tool call executed, streaming chat completion again to get assistant response"
-            )
-            async for chunk in stream_chat_completion(
-                session_id=session.session_id,
-                user_id=user_id,
-                session=session,  # Pass session object to avoid Redis refetch
-                context=context,
-            ):
-                yield chunk
-
-    finally:
-        # Always end Langfuse observations to prevent resource leaks
-        # Guard against None and catch errors to avoid masking original exceptions
-        if generation is not None:
-            try:
-                latest_usage = session.usage[-1] if session.usage else None
-                generation.update(
-                    model=config.model,
-                    output={
-                        "content": assistant_response.content,
-                        "tool_calls": accumulated_tool_calls or None,
-                    },
-                    usage_details=(
-                        {
-                            "input": latest_usage.prompt_tokens,
-                            "output": latest_usage.completion_tokens,
-                            "total": latest_usage.total_tokens,
-                        }
-                        if latest_usage
-                        else None
-                    ),
-                )
-                generation.end()
-            except Exception as e:
-                logger.warning(f"Failed to end Langfuse generation: {e}")
-
-        if trace is not None:
-            try:
-                if accumulated_tool_calls:
-                    trace.update_trace(output={"tool_calls": accumulated_tool_calls})
-                else:
-                    trace.update_trace(output={"response": assistant_response.content})
-                trace.end()
-            except Exception as e:
-                logger.warning(f"Failed to end Langfuse trace: {e}")
-
-
-# Retry configuration for OpenAI API calls
-MAX_RETRIES = 3
-BASE_DELAY_SECONDS = 1.0
-MAX_DELAY_SECONDS = 30.0
-
-
-def _is_retryable_error(error: Exception) -> bool:
-    """Determine if an error is retryable."""
-    if isinstance(error, RateLimitError):
-        return True
-    if isinstance(error, APIConnectionError):
-        return True
-    if isinstance(error, APIStatusError):
-        # APIStatusError has a response with status_code
-        # Retry on 5xx status codes (server errors)
-        if error.response.status_code >= 500:
-            return True
-    if isinstance(error, APIError):
-        # Retry on overloaded errors or 500 errors (may not have status code)
-        error_message = str(error).lower()
-        if "overloaded" in error_message or "internal server error" in error_message:
-            return True
-    return False
-
-
-async def _stream_chat_chunks(
-    session: ChatSession,
-    tools: list[ChatCompletionToolParam],
-    system_prompt: str | None = None,
-    text_block_id: str | None = None,
-) -> AsyncGenerator[StreamBaseResponse, None]:
-    """
-    Pure streaming function for OpenAI chat completions with tool calling.
-
-    This function is database-agnostic and focuses only on streaming logic.
-    Implements exponential backoff retry for transient API errors.
-
-    Args:
-        session: Chat session with conversation history
-        tools: Available tools for the model
-        system_prompt: System prompt to prepend to messages
-
-    Yields:
-        SSE formatted JSON response objects
-
-    """
-    model = config.model
-
-    logger.info("Starting pure chat stream")
-
-    # Build messages with system prompt prepended
-    messages = session.to_openai_messages()
-    if system_prompt:
-        from openai.types.chat import ChatCompletionSystemMessageParam
-
-        system_message = ChatCompletionSystemMessageParam(
-            role="system",
-            content=system_prompt,
-        )
-        messages = [system_message] + messages
-
-    # Loop to handle tool calls and continue conversation
-    while True:
-        retry_count = 0
-        last_error: Exception | None = None
-
-        while retry_count <= MAX_RETRIES:
-            try:
-                logger.info(
-                    f"Creating OpenAI chat completion stream..."
-                    f"{f' (retry {retry_count}/{MAX_RETRIES})' if retry_count > 0 else ''}"
-                )
-
-                # Create the stream with proper types
-                stream = await client.chat.completions.create(
-                    model=model,
-                    messages=messages,
-                    tools=tools,
-                    tool_choice="auto",
-                    stream=True,
-                    stream_options={"include_usage": True},
-                )
-
-                # Variables to accumulate tool calls
-                tool_calls: list[dict[str, Any]] = []
-                active_tool_call_idx: int | None = None
-                finish_reason: str | None = None
-                # Track which tool call indices have had their start event emitted
-                emitted_start_for_idx: set[int] = set()
-
-                # Track if we've started the text block
-                text_started = False
-
-                # Process the stream
-                chunk: ChatCompletionChunk
-                async for chunk in stream:
-                    if chunk.usage:
-                        yield StreamUsage(
-                            promptTokens=chunk.usage.prompt_tokens,
-                            completionTokens=chunk.usage.completion_tokens,
-                            totalTokens=chunk.usage.total_tokens,
-                        )
-
-                    if chunk.choices:
-                        choice = chunk.choices[0]
-                        delta = choice.delta
-
-                        # Capture finish reason
-                        if choice.finish_reason:
-                            finish_reason = choice.finish_reason
-                            logger.info(f"Finish reason: {finish_reason}")
-
-                        # Handle content streaming
-                        if delta.content:
-                            # Emit text-start on first text content
-                            if not text_started and text_block_id:
-                                yield StreamTextStart(id=text_block_id)
-                                text_started = True
-                            # Stream the text delta
-                            text_response = StreamTextDelta(
-                                id=text_block_id or "",
-                                delta=delta.content,
-                            )
-                            yield text_response
-
-                        # Handle tool calls
-                        if delta.tool_calls:
-                            for tc_chunk in delta.tool_calls:
-                                idx = tc_chunk.index
-
-                                # Update active tool call index if needed
-                                if (
-                                    active_tool_call_idx is None
-                                    or active_tool_call_idx != idx
-                                ):
-                                    active_tool_call_idx = idx
-
-                                # Ensure we have a tool call object at this index
-                                while len(tool_calls) <= idx:
-                                    tool_calls.append(
-                                        {
-                                            "id": "",
-                                            "type": "function",
-                                            "function": {
-                                                "name": "",
-                                                "arguments": "",
-                                            },
-                                        },
-                                    )
-
-                                # Accumulate the tool call data
-                                if tc_chunk.id:
-                                    tool_calls[idx]["id"] = tc_chunk.id
-                                if tc_chunk.function:
-                                    if tc_chunk.function.name:
-                                        tool_calls[idx]["function"][
-                                            "name"
-                                        ] = tc_chunk.function.name
-                                    if tc_chunk.function.arguments:
-                                        tool_calls[idx]["function"][
-                                            "arguments"
-                                        ] += tc_chunk.function.arguments
-
-                                # Emit StreamToolInputStart only after we have the tool call ID
-                                if (
-                                    idx not in emitted_start_for_idx
-                                    and tool_calls[idx]["id"]
-                                    and tool_calls[idx]["function"]["name"]
-                                ):
-                                    yield StreamToolInputStart(
-                                        toolCallId=tool_calls[idx]["id"],
-                                        toolName=tool_calls[idx]["function"]["name"],
-                                    )
-                                    emitted_start_for_idx.add(idx)
-                logger.info(f"Stream complete. Finish reason: {finish_reason}")
-
-                # Yield all accumulated tool calls after the stream is complete
-                # This ensures all tool call arguments have been fully received
-                for idx, tool_call in enumerate(tool_calls):
-                    try:
-                        async for tc in _yield_tool_call(tool_calls, idx, session):
-                            yield tc
-                    except (orjson.JSONDecodeError, KeyError, TypeError) as e:
-                        logger.error(
-                            f"Failed to parse tool call {idx}: {e}",
-                            exc_info=True,
-                            extra={"tool_call": tool_call},
-                        )
-                        yield StreamError(
-                            errorText=f"Invalid tool call arguments for tool {tool_call.get('function', {}).get('name', 'unknown')}: {e}",
-                        )
-                        # Re-raise to trigger retry logic in the parent function
-                        raise
-
-                yield StreamFinish()
-                return
-            except Exception as e:
-                last_error = e
-                if _is_retryable_error(e) and retry_count < MAX_RETRIES:
-                    retry_count += 1
-                    # Calculate delay with exponential backoff
-                    delay = min(
-                        BASE_DELAY_SECONDS * (2 ** (retry_count - 1)),
-                        MAX_DELAY_SECONDS,
-                    )
-                    logger.warning(
-                        f"Retryable error in stream: {e!s}. "
-                        f"Retrying in {delay:.1f}s (attempt {retry_count}/{MAX_RETRIES})"
-                    )
-                    await asyncio.sleep(delay)
-                    continue  # Retry the stream
-                else:
-                    # Non-retryable error or max retries exceeded
-                    logger.error(
-                        f"Error in stream (not retrying): {e!s}",
-                        exc_info=True,
-                    )
-                    error_response = StreamError(errorText=str(e))
-                    yield error_response
-                    yield StreamFinish()
-                    return
-
-        # If we exit the retry loop without returning, it means we exhausted retries
-        if last_error:
-            logger.error(
-                f"Max retries ({MAX_RETRIES}) exceeded. Last error: {last_error!s}",
-                exc_info=True,
-            )
-            yield StreamError(errorText=f"Max retries exceeded: {last_error!s}")
-            yield StreamFinish()
-            return
-
-
-async def _yield_tool_call(
-    tool_calls: list[dict[str, Any]],
-    yield_idx: int,
-    session: ChatSession,
-) -> AsyncGenerator[StreamBaseResponse, None]:
-    """
-    Yield a tool call and its execution result.
-
-    Raises:
-        orjson.JSONDecodeError: If tool call arguments cannot be parsed as JSON
-        KeyError: If expected tool call fields are missing
-        TypeError: If tool call structure is invalid
-    """
-    tool_name = tool_calls[yield_idx]["function"]["name"]
-    tool_call_id = tool_calls[yield_idx]["id"]
-    logger.info(f"Yielding tool call: {tool_calls[yield_idx]}")
-
-    # Parse tool call arguments - handle empty arguments gracefully
-    raw_arguments = tool_calls[yield_idx]["function"]["arguments"]
-    if raw_arguments:
-        arguments = orjson.loads(raw_arguments)
-    else:
-        arguments = {}
-
-    yield StreamToolInputAvailable(
-        toolCallId=tool_call_id,
-        toolName=tool_name,
-        input=arguments,
-    )
-
-    tool_execution_response: StreamToolOutputAvailable = await execute_tool(
-        tool_name=tool_name,
-        parameters=arguments,
-        tool_call_id=tool_call_id,
-        user_id=session.user_id,
-        session=session,
-    )
-
-    logger.info(f"Yielding Tool execution response: {tool_execution_response}")
-    yield tool_execution_response

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

@@ -1,47 +0,0 @@
-from typing import TYPE_CHECKING, Any
-
-from openai.types.chat import ChatCompletionToolParam
-
-from backend.api.features.chat.model import ChatSession
-
-from .add_understanding import AddUnderstandingTool
-from .agent_output import AgentOutputTool
-from .base import BaseTool
-from .find_agent import FindAgentTool
-from .find_library_agent import FindLibraryAgentTool
-from .run_agent import RunAgentTool
-
-if TYPE_CHECKING:
-    from backend.api.features.chat.response_model import StreamToolOutputAvailable
-
-# Single source of truth for all tools
-TOOL_REGISTRY: dict[str, BaseTool] = {
-    "add_understanding": AddUnderstandingTool(),
-    "find_agent": FindAgentTool(),
-    "find_library_agent": FindLibraryAgentTool(),
-    "run_agent": RunAgentTool(),
-    "agent_output": AgentOutputTool(),
-}
-
-# Export individual tool instances for backwards compatibility
-find_agent_tool = TOOL_REGISTRY["find_agent"]
-run_agent_tool = TOOL_REGISTRY["run_agent"]
-
-# Generated from registry for OpenAI API
-tools: list[ChatCompletionToolParam] = [
-    tool.as_openai_tool() for tool in TOOL_REGISTRY.values()
-]
-
-
-async def execute_tool(
-    tool_name: str,
-    parameters: dict[str, Any],
-    user_id: str | None,
-    session: ChatSession,
-    tool_call_id: str,
-) -> "StreamToolOutputAvailable":
-    """Execute a tool by name."""
-    tool = TOOL_REGISTRY.get(tool_name)
-    if not tool:
-        raise ValueError(f"Tool {tool_name} not found")
-    return await tool.execute(user_id, session, tool_call_id, **parameters)

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

@@ -1,119 +0,0 @@
-"""Tool for capturing user business understanding incrementally."""
-
-import logging
-from typing import Any
-
-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
-
-logger = logging.getLogger(__name__)
-
-
-class AddUnderstandingTool(BaseTool):
-    """Tool for capturing user's business understanding incrementally."""
-
-    @property
-    def name(self) -> str:
-        return "add_understanding"
-
-    @property
-    def description(self) -> str:
-        return """Capture and store information about the user's business context,
-workflows, pain points, and automation goals. Call this tool whenever the user
-shares information about their business. Each call incrementally adds to the
-existing understanding - you don't need to provide all fields at once.
-
-Use this to build a comprehensive profile that helps recommend better agents
-and automations for the user's specific needs."""
-
-    @property
-    def parameters(self) -> dict[str, Any]:
-        # Auto-generate from Pydantic model schema
-        schema = BusinessUnderstandingInput.model_json_schema()
-        properties = {}
-        for field_name, field_schema in schema.get("properties", {}).items():
-            prop: dict[str, Any] = {"description": field_schema.get("description", "")}
-            # Handle anyOf for Optional types
-            if "anyOf" in field_schema:
-                for option in field_schema["anyOf"]:
-                    if option.get("type") != "null":
-                        prop["type"] = option.get("type", "string")
-                        if "items" in option:
-                            prop["items"] = option["items"]
-                        break
-            else:
-                prop["type"] = field_schema.get("type", "string")
-                if "items" in field_schema:
-                    prop["items"] = field_schema["items"]
-            properties[field_name] = prop
-        return {"type": "object", "properties": properties, "required": []}
-
-    @property
-    def requires_auth(self) -> bool:
-        """Requires authentication to store user-specific data."""
-        return True
-
-    async def _execute(
-        self,
-        user_id: str | None,
-        session: ChatSession,
-        **kwargs,
-    ) -> ToolResponseBase:
-        """
-        Capture and store business understanding incrementally.
-
-        Each call merges new data with existing understanding:
-        - String fields are overwritten if provided
-        - List fields are appended (with deduplication)
-        """
-        session_id = session.session_id
-
-        if not user_id:
-            return ErrorResponse(
-                message="Authentication required to save business understanding.",
-                session_id=session_id,
-            )
-
-        # Check if any data was provided
-        if not any(v is not None for v in kwargs.values()):
-            return ErrorResponse(
-                message="Please provide at least one field to update.",
-                session_id=session_id,
-            )
-
-        # Build input model from kwargs (only include fields defined in the model)
-        valid_fields = set(BusinessUnderstandingInput.model_fields.keys())
-        input_data = BusinessUnderstandingInput(
-            **{k: v for k, v in kwargs.items() if k in valid_fields}
-        )
-
-        # Track which fields were updated
-        updated_fields = [
-            k for k, v in kwargs.items() if k in valid_fields and v is not None
-        ]
-
-        # Upsert with merge
-        understanding = await upsert_business_understanding(user_id, input_data)
-
-        # Build current understanding summary (filter out empty values)
-        current_understanding = {
-            k: v
-            for k, v in understanding.model_dump(
-                exclude={"id", "user_id", "created_at", "updated_at"}
-            ).items()
-            if v is not None and v != [] and v != ""
-        }
-
-        return UnderstandingUpdatedResponse(
-            message=f"Updated understanding with: {', '.join(updated_fields)}. "
-            "I now have a better picture of your business context.",
-            session_id=session_id,
-            updated_fields=updated_fields,
-            current_understanding=current_understanding,
-        )

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

@@ -1,446 +0,0 @@
-"""Tool for retrieving agent execution outputs from user's library."""
-
-import logging
-import re
-from datetime import datetime, timedelta, timezone
-from typing import Any
-
-from pydantic import BaseModel, field_validator
-
-from backend.api.features.chat.model import ChatSession
-from backend.api.features.library import db as library_db
-from backend.api.features.library.model import LibraryAgent
-from backend.data import execution as execution_db
-from backend.data.execution import ExecutionStatus, GraphExecution, GraphExecutionMeta
-
-from .base import BaseTool
-from .models import (
-    AgentOutputResponse,
-    ErrorResponse,
-    ExecutionOutputInfo,
-    NoResultsResponse,
-    ToolResponseBase,
-)
-from .utils import fetch_graph_from_store_slug
-
-logger = logging.getLogger(__name__)
-
-
-class AgentOutputInput(BaseModel):
-    """Input parameters for the agent_output tool."""
-
-    agent_name: str = ""
-    library_agent_id: str = ""
-    store_slug: str = ""
-    execution_id: str = ""
-    run_time: str = "latest"
-
-    @field_validator(
-        "agent_name",
-        "library_agent_id",
-        "store_slug",
-        "execution_id",
-        "run_time",
-        mode="before",
-    )
-    @classmethod
-    def strip_strings(cls, v: Any) -> Any:
-        """Strip whitespace from string fields."""
-        return v.strip() if isinstance(v, str) else v
-
-
-def parse_time_expression(
-    time_expr: str | None,
-) -> tuple[datetime | None, datetime | None]:
-    """
-    Parse time expression into datetime range (start, end).
-
-    Supports: "latest", "yesterday", "today", "last week", "last 7 days",
-    "last month", "last 30 days", ISO date "YYYY-MM-DD", ISO datetime.
-    """
-    if not time_expr or time_expr.lower() == "latest":
-        return None, None
-
-    now = datetime.now(timezone.utc)
-    today_start = now.replace(hour=0, minute=0, second=0, microsecond=0)
-    expr = time_expr.lower().strip()
-
-    # Relative time expressions lookup
-    relative_times: dict[str, tuple[datetime, datetime]] = {
-        "yesterday": (today_start - timedelta(days=1), today_start),
-        "today": (today_start, now),
-        "last week": (now - timedelta(days=7), now),
-        "last 7 days": (now - timedelta(days=7), now),
-        "last month": (now - timedelta(days=30), now),
-        "last 30 days": (now - timedelta(days=30), now),
-    }
-    if expr in relative_times:
-        return relative_times[expr]
-
-    # Try ISO date format (YYYY-MM-DD)
-    date_match = re.match(r"^(\d{4})-(\d{2})-(\d{2})$", expr)
-    if date_match:
-        try:
-            year, month, day = map(int, date_match.groups())
-            start = datetime(year, month, day, 0, 0, 0, tzinfo=timezone.utc)
-            return start, start + timedelta(days=1)
-        except ValueError:
-            # Invalid date components (e.g., month=13, day=32)
-            pass
-
-    # Try ISO datetime
-    try:
-        parsed = datetime.fromisoformat(expr.replace("Z", "+00:00"))
-        if parsed.tzinfo is None:
-            parsed = parsed.replace(tzinfo=timezone.utc)
-        return parsed - timedelta(hours=1), parsed + timedelta(hours=1)
-    except ValueError:
-        return None, None
-
-
-class AgentOutputTool(BaseTool):
-    """Tool for retrieving execution outputs from user's library agents."""
-
-    @property
-    def name(self) -> str:
-        return "agent_output"
-
-    @property
-    def description(self) -> str:
-        return """Retrieve execution outputs from agents in the user's library.
-
-        Identify the agent using one of:
-        - agent_name: Fuzzy search in user's library
-        - library_agent_id: Exact library agent ID
-        - store_slug: Marketplace format 'username/agent-name'
-
-        Select which run to retrieve using:
-        - execution_id: Specific execution ID
-        - run_time: 'latest' (default), 'yesterday', 'last week', or ISO date 'YYYY-MM-DD'
-        """
-
-    @property
-    def parameters(self) -> dict[str, Any]:
-        return {
-            "type": "object",
-            "properties": {
-                "agent_name": {
-                    "type": "string",
-                    "description": "Agent name to search for in user's library (fuzzy match)",
-                },
-                "library_agent_id": {
-                    "type": "string",
-                    "description": "Exact library agent ID",
-                },
-                "store_slug": {
-                    "type": "string",
-                    "description": "Marketplace identifier: 'username/agent-slug'",
-                },
-                "execution_id": {
-                    "type": "string",
-                    "description": "Specific execution ID to retrieve",
-                },
-                "run_time": {
-                    "type": "string",
-                    "description": (
-                        "Time filter: 'latest', 'yesterday', 'last week', or 'YYYY-MM-DD'"
-                    ),
-                },
-            },
-            "required": [],
-        }
-
-    @property
-    def requires_auth(self) -> bool:
-        return True
-
-    async def _resolve_agent(
-        self,
-        user_id: str,
-        agent_name: str | None,
-        library_agent_id: str | None,
-        store_slug: str | None,
-    ) -> tuple[LibraryAgent | None, str | None]:
-        """
-        Resolve agent from provided identifiers.
-        Returns (library_agent, error_message).
-        """
-        # Priority 1: Exact library agent ID
-        if library_agent_id:
-            try:
-                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}")
-                return None, f"Library agent '{library_agent_id}' not found"
-
-        # Priority 2: Store slug (username/agent-name)
-        if store_slug and "/" in store_slug:
-            username, agent_slug = store_slug.split("/", 1)
-            graph, _ = await fetch_graph_from_store_slug(username, agent_slug)
-            if not graph:
-                return None, f"Agent '{store_slug}' not found in marketplace"
-
-            # Find in user's library by graph_id
-            agent = await library_db.get_library_agent_by_graph_id(user_id, graph.id)
-            if not agent:
-                return (
-                    None,
-                    f"Agent '{store_slug}' is not in your library. "
-                    "Add it first to see outputs.",
-                )
-            return agent, None
-
-        # Priority 3: Fuzzy name search in library
-        if agent_name:
-            try:
-                response = await library_db.list_library_agents(
-                    user_id=user_id,
-                    search_term=agent_name,
-                    page_size=5,
-                )
-                if not response.agents:
-                    return (
-                        None,
-                        f"No agents matching '{agent_name}' found in your library",
-                    )
-
-                # Return best match (first result from search)
-                return response.agents[0], None
-            except Exception as e:
-                logger.error(f"Error searching library agents: {e}")
-                return None, f"Error searching for agent: {e}"
-
-        return (
-            None,
-            "Please specify an agent name, library_agent_id, or store_slug",
-        )
-
-    async def _get_execution(
-        self,
-        user_id: str,
-        graph_id: str,
-        execution_id: str | None,
-        time_start: datetime | None,
-        time_end: datetime | None,
-    ) -> tuple[GraphExecution | None, list[GraphExecutionMeta], str | None]:
-        """
-        Fetch execution(s) based on filters.
-        Returns (single_execution, available_executions_meta, error_message).
-        """
-        # If specific execution_id provided, fetch it directly
-        if execution_id:
-            execution = await execution_db.get_graph_execution(
-                user_id=user_id,
-                execution_id=execution_id,
-                include_node_executions=False,
-            )
-            if not execution:
-                return None, [], f"Execution '{execution_id}' not found"
-            return execution, [], None
-
-        # Get completed executions with time filters
-        executions = await execution_db.get_graph_executions(
-            graph_id=graph_id,
-            user_id=user_id,
-            statuses=[ExecutionStatus.COMPLETED],
-            created_time_gte=time_start,
-            created_time_lte=time_end,
-            limit=10,
-        )
-
-        if not executions:
-            return None, [], None  # No error, just no executions
-
-        # If only one execution, fetch full details
-        if len(executions) == 1:
-            full_execution = await execution_db.get_graph_execution(
-                user_id=user_id,
-                execution_id=executions[0].id,
-                include_node_executions=False,
-            )
-            return full_execution, [], None
-
-        # Multiple executions - return latest with full details, plus list of available
-        full_execution = await execution_db.get_graph_execution(
-            user_id=user_id,
-            execution_id=executions[0].id,
-            include_node_executions=False,
-        )
-        return full_execution, executions, None
-
-    def _build_response(
-        self,
-        agent: LibraryAgent,
-        execution: GraphExecution | None,
-        available_executions: list[GraphExecutionMeta],
-        session_id: str | None,
-    ) -> AgentOutputResponse:
-        """Build the response based on execution data."""
-        library_agent_link = f"/library/agents/{agent.id}"
-
-        if not execution:
-            return AgentOutputResponse(
-                message=f"No completed executions found for agent '{agent.name}'",
-                session_id=session_id,
-                agent_name=agent.name,
-                agent_id=agent.graph_id,
-                library_agent_id=agent.id,
-                library_agent_link=library_agent_link,
-                total_executions=0,
-            )
-
-        execution_info = ExecutionOutputInfo(
-            execution_id=execution.id,
-            status=execution.status.value,
-            started_at=execution.started_at,
-            ended_at=execution.ended_at,
-            outputs=dict(execution.outputs),
-            inputs_summary=execution.inputs if execution.inputs else None,
-        )
-
-        available_list = None
-        if len(available_executions) > 1:
-            available_list = [
-                {
-                    "id": e.id,
-                    "status": e.status.value,
-                    "started_at": e.started_at.isoformat() if e.started_at else None,
-                }
-                for e in available_executions[:5]
-            ]
-
-        message = f"Found execution outputs for agent '{agent.name}'"
-        if len(available_executions) > 1:
-            message += (
-                f". Showing latest of {len(available_executions)} matching executions."
-            )
-
-        return AgentOutputResponse(
-            message=message,
-            session_id=session_id,
-            agent_name=agent.name,
-            agent_id=agent.graph_id,
-            library_agent_id=agent.id,
-            library_agent_link=library_agent_link,
-            execution=execution_info,
-            available_executions=available_list,
-            total_executions=len(available_executions) if available_executions else 1,
-        )
-
-    async def _execute(
-        self,
-        user_id: str | None,
-        session: ChatSession,
-        **kwargs,
-    ) -> ToolResponseBase:
-        """Execute the agent_output tool."""
-        session_id = session.session_id
-
-        # Parse and validate input
-        try:
-            input_data = AgentOutputInput(**kwargs)
-        except Exception as e:
-            logger.error(f"Invalid input: {e}")
-            return ErrorResponse(
-                message="Invalid input parameters",
-                error=str(e),
-                session_id=session_id,
-            )
-
-        # Ensure user_id is present (should be guaranteed by requires_auth)
-        if not user_id:
-            return ErrorResponse(
-                message="User authentication required",
-                session_id=session_id,
-            )
-
-        # Check if at least one identifier is provided
-        if not any(
-            [
-                input_data.agent_name,
-                input_data.library_agent_id,
-                input_data.store_slug,
-                input_data.execution_id,
-            ]
-        ):
-            return ErrorResponse(
-                message=(
-                    "Please specify at least one of: agent_name, "
-                    "library_agent_id, store_slug, or execution_id"
-                ),
-                session_id=session_id,
-            )
-
-        # If only execution_id provided, we need to find the agent differently
-        if (
-            input_data.execution_id
-            and not input_data.agent_name
-            and not input_data.library_agent_id
-            and not input_data.store_slug
-        ):
-            # Fetch execution directly to get graph_id
-            execution = await execution_db.get_graph_execution(
-                user_id=user_id,
-                execution_id=input_data.execution_id,
-                include_node_executions=False,
-            )
-            if not execution:
-                return ErrorResponse(
-                    message=f"Execution '{input_data.execution_id}' not found",
-                    session_id=session_id,
-                )
-
-            # Find library agent by graph_id
-            agent = await library_db.get_library_agent_by_graph_id(
-                user_id, execution.graph_id
-            )
-            if not agent:
-                return NoResultsResponse(
-                    message=(
-                        f"Execution found but agent not in your library. "
-                        f"Graph ID: {execution.graph_id}"
-                    ),
-                    session_id=session_id,
-                    suggestions=["Add the agent to your library to see more details"],
-                )
-
-            return self._build_response(agent, execution, [], session_id)
-
-        # Resolve agent from identifiers
-        agent, error = await self._resolve_agent(
-            user_id=user_id,
-            agent_name=input_data.agent_name or None,
-            library_agent_id=input_data.library_agent_id or None,
-            store_slug=input_data.store_slug or None,
-        )
-
-        if error or not agent:
-            return NoResultsResponse(
-                message=error or "Agent not found",
-                session_id=session_id,
-                suggestions=[
-                    "Check the agent name or ID",
-                    "Make sure the agent is in your library",
-                ],
-            )
-
-        # Parse time expression
-        time_start, time_end = parse_time_expression(input_data.run_time)
-
-        # 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,
-        )
-
-        if exec_error:
-            return ErrorResponse(
-                message=exec_error,
-                session_id=session_id,
-            )
-
-        return self._build_response(agent, execution, available_executions, session_id)

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

@@ -1,151 +0,0 @@
-"""Shared agent search functionality for find_agent and find_library_agent tools."""
-
-import logging
-from typing import Literal
-
-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 (
-    AgentInfo,
-    AgentsFoundResponse,
-    ErrorResponse,
-    NoResultsResponse,
-    ToolResponseBase,
-)
-
-logger = logging.getLogger(__name__)
-
-SearchSource = Literal["marketplace", "library"]
-
-
-async def search_agents(
-    query: str,
-    source: SearchSource,
-    session_id: str | None,
-    user_id: str | None = None,
-) -> ToolResponseBase:
-    """
-    Search for agents in marketplace or user library.
-
-    Args:
-        query: Search query string
-        source: "marketplace" or "library"
-        session_id: Chat session ID
-        user_id: User ID (required for library search)
-
-    Returns:
-        AgentsFoundResponse, NoResultsResponse, or ErrorResponse
-    """
-    if not query:
-        return ErrorResponse(
-            message="Please provide a search query", session_id=session_id
-        )
-
-    if source == "library" and not user_id:
-        return ErrorResponse(
-            message="User authentication required to search library",
-            session_id=session_id,
-        )
-
-    agents: list[AgentInfo] = []
-    try:
-        if source == "marketplace":
-            logger.info(f"Searching marketplace for: {query}")
-            results = await store_db.get_store_agents(search_query=query, page_size=5)
-            for agent in results.agents:
-                agents.append(
-                    AgentInfo(
-                        id=f"{agent.creator}/{agent.slug}",
-                        name=agent.agent_name,
-                        description=agent.description or "",
-                        source="marketplace",
-                        in_library=False,
-                        creator=agent.creator,
-                        category="general",
-                        rating=agent.rating,
-                        runs=agent.runs,
-                        is_featured=False,
-                    )
-                )
-        else:  # library
-            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=query,
-                page_size=10,
-            )
-            for agent in results.agents:
-                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
-    except DatabaseError as e:
-        logger.error(f"Error searching {source}: {e}", exc_info=True)
-        return ErrorResponse(
-            message=f"Failed to search {source}. Please try again.",
-            error=str(e),
-            session_id=session_id,
-        )
-
-    if not agents:
-        suggestions = (
-            [
-                "Try more general terms",
-                "Browse categories in the marketplace",
-                "Check spelling",
-            ]
-            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 found matching '{query}'. Try different keywords or browse the marketplace."
-            if source == "marketplace"
-            else f"No agents matching '{query}' found in your library."
-        )
-        return NoResultsResponse(
-            message=no_results_msg, session_id=session_id, suggestions=suggestions
-        )
-
-    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."
-        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."
-    )
-
-    return AgentsFoundResponse(
-        message=message,
-        title=title,
-        agents=agents,
-        count=len(agents),
-        session_id=session_id,
-    )

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

@@ -1,46 +0,0 @@
-"""Tool for discovering agents from marketplace."""
-
-from typing import Any
-
-from backend.api.features.chat.model import ChatSession
-
-from .agent_search import search_agents
-from .base import BaseTool
-from .models import ToolResponseBase
-
-
-class FindAgentTool(BaseTool):
-    """Tool for discovering agents from the marketplace."""
-
-    @property
-    def name(self) -> str:
-        return "find_agent"
-
-    @property
-    def description(self) -> str:
-        return (
-            "Discover agents from the marketplace based on capabilities and user needs."
-        )
-
-    @property
-    def parameters(self) -> dict[str, Any]:
-        return {
-            "type": "object",
-            "properties": {
-                "query": {
-                    "type": "string",
-                    "description": "Search query describing what the user wants to accomplish. Use single keywords for best results.",
-                },
-            },
-            "required": ["query"],
-        }
-
-    async def _execute(
-        self, user_id: str | None, session: ChatSession, **kwargs
-    ) -> ToolResponseBase:
-        return await search_agents(
-            query=kwargs.get("query", "").strip(),
-            source="marketplace",
-            session_id=session.session_id,
-            user_id=user_id,
-        )

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

@@ -1,52 +0,0 @@
-"""Tool for searching agents in the user's library."""
-
-from typing import Any
-
-from backend.api.features.chat.model import ChatSession
-
-from .agent_search import search_agents
-from .base import BaseTool
-from .models import ToolResponseBase
-
-
-class FindLibraryAgentTool(BaseTool):
-    """Tool for searching agents in the user's library."""
-
-    @property
-    def name(self) -> str:
-        return "find_library_agent"
-
-    @property
-    def description(self) -> str:
-        return (
-            "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
-    def parameters(self) -> dict[str, Any]:
-        return {
-            "type": "object",
-            "properties": {
-                "query": {
-                    "type": "string",
-                    "description": "Search query to find agents by name or description.",
-                },
-            },
-            "required": ["query"],
-        }
-
-    @property
-    def requires_auth(self) -> bool:
-        return True
-
-    async def _execute(
-        self, user_id: str | None, session: ChatSession, **kwargs
-    ) -> ToolResponseBase:
-        return await search_agents(
-            query=kwargs.get("query", "").strip(),
-            source="library",
-            session_id=session.session_id,
-            user_id=user_id,
-        )

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

@@ -1,431 +0,0 @@
-"""
-Content Type Handlers for Unified Embeddings
-
-Pluggable system for different content sources (store agents, blocks, docs).
-Each handler knows how to fetch and process its content type for embedding.
-"""
-
-import logging
-from abc import ABC, abstractmethod
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Any
-
-from prisma.enums import ContentType
-
-from backend.data.db import query_raw_with_schema
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class ContentItem:
-    """Represents a piece of content to be embedded."""
-
-    content_id: str  # Unique identifier (DB ID or file path)
-    content_type: ContentType
-    searchable_text: str  # Combined text for embedding
-    metadata: dict[str, Any]  # Content-specific metadata
-    user_id: str | None = None  # For user-scoped content
-
-
-class ContentHandler(ABC):
-    """Base handler for fetching and processing content for embeddings."""
-
-    @property
-    @abstractmethod
-    def content_type(self) -> ContentType:
-        """The ContentType this handler manages."""
-        pass
-
-    @abstractmethod
-    async def get_missing_items(self, batch_size: int) -> list[ContentItem]:
-        """
-        Fetch items that don't have embeddings yet.
-
-        Args:
-            batch_size: Maximum number of items to return
-
-        Returns:
-            List of ContentItem objects ready for embedding
-        """
-        pass
-
-    @abstractmethod
-    async def get_stats(self) -> dict[str, int]:
-        """
-        Get statistics about embedding coverage.
-
-        Returns:
-            Dict with keys: total, with_embeddings, without_embeddings
-        """
-        pass
-
-
-class StoreAgentHandler(ContentHandler):
-    """Handler for marketplace store agent listings."""
-
-    @property
-    def content_type(self) -> ContentType:
-        return ContentType.STORE_AGENT
-
-    async def get_missing_items(self, batch_size: int) -> list[ContentItem]:
-        """Fetch approved store listings without embeddings."""
-        from backend.api.features.store.embeddings import build_searchable_text
-
-        missing = await query_raw_with_schema(
-            """
-            SELECT
-                slv.id,
-                slv.name,
-                slv.description,
-                slv."subHeading",
-                slv.categories
-            FROM {schema_prefix}"StoreListingVersion" slv
-            LEFT JOIN {schema_prefix}"UnifiedContentEmbedding" uce
-                ON slv.id = uce."contentId" AND uce."contentType" = 'STORE_AGENT'::{schema_prefix}"ContentType"
-            WHERE slv."submissionStatus" = 'APPROVED'
-            AND slv."isDeleted" = false
-            AND uce."contentId" IS NULL
-            LIMIT $1
-            """,
-            batch_size,
-        )
-
-        return [
-            ContentItem(
-                content_id=row["id"],
-                content_type=ContentType.STORE_AGENT,
-                searchable_text=build_searchable_text(
-                    name=row["name"],
-                    description=row["description"],
-                    sub_heading=row["subHeading"],
-                    categories=row["categories"] or [],
-                ),
-                metadata={
-                    "name": row["name"],
-                    "categories": row["categories"] or [],
-                },
-                user_id=None,  # Store agents are public
-            )
-            for row in missing
-        ]
-
-    async def get_stats(self) -> dict[str, int]:
-        """Get statistics about store agent embedding coverage."""
-        # Count approved versions
-        approved_result = await query_raw_with_schema(
-            """
-            SELECT COUNT(*) as count
-            FROM {schema_prefix}"StoreListingVersion"
-            WHERE "submissionStatus" = 'APPROVED'
-            AND "isDeleted" = false
-            """
-        )
-        total_approved = approved_result[0]["count"] if approved_result else 0
-
-        # Count versions with embeddings
-        embedded_result = await query_raw_with_schema(
-            """
-            SELECT COUNT(*) as count
-            FROM {schema_prefix}"StoreListingVersion" slv
-            JOIN {schema_prefix}"UnifiedContentEmbedding" uce ON slv.id = uce."contentId" AND uce."contentType" = 'STORE_AGENT'::{schema_prefix}"ContentType"
-            WHERE slv."submissionStatus" = 'APPROVED'
-            AND slv."isDeleted" = false
-            """
-        )
-        with_embeddings = embedded_result[0]["count"] if embedded_result else 0
-
-        return {
-            "total": total_approved,
-            "with_embeddings": with_embeddings,
-            "without_embeddings": total_approved - with_embeddings,
-        }
-
-
-class BlockHandler(ContentHandler):
-    """Handler for block definitions (Python classes)."""
-
-    @property
-    def content_type(self) -> ContentType:
-        return ContentType.BLOCK
-
-    async def get_missing_items(self, batch_size: int) -> list[ContentItem]:
-        """Fetch blocks without embeddings."""
-        from backend.data.block import get_blocks
-
-        # Get all available blocks
-        all_blocks = get_blocks()
-
-        # Check which ones have embeddings
-        if not all_blocks:
-            return []
-
-        block_ids = list(all_blocks.keys())
-
-        # Query for existing embeddings
-        placeholders = ",".join([f"${i+1}" for i in range(len(block_ids))])
-        existing_result = await query_raw_with_schema(
-            f"""
-            SELECT "contentId"
-            FROM {{schema_prefix}}"UnifiedContentEmbedding"
-            WHERE "contentType" = 'BLOCK'::{{schema_prefix}}"ContentType"
-            AND "contentId" = ANY(ARRAY[{placeholders}])
-            """,
-            *block_ids,
-        )
-
-        existing_ids = {row["contentId"] for row in existing_result}
-        missing_blocks = [
-            (block_id, block_cls)
-            for block_id, block_cls in all_blocks.items()
-            if block_id not in existing_ids
-        ]
-
-        # Convert to ContentItem
-        items = []
-        for block_id, block_cls in missing_blocks[:batch_size]:
-            try:
-                block_instance = block_cls()
-
-                # Build searchable text from block metadata
-                parts = []
-                if hasattr(block_instance, "name") and block_instance.name:
-                    parts.append(block_instance.name)
-                if (
-                    hasattr(block_instance, "description")
-                    and block_instance.description
-                ):
-                    parts.append(block_instance.description)
-                if hasattr(block_instance, "categories") and block_instance.categories:
-                    # Convert BlockCategory enum to strings
-                    parts.append(
-                        " ".join(str(cat.value) for cat in block_instance.categories)
-                    )
-
-                # Add input/output schema info
-                if hasattr(block_instance, "input_schema"):
-                    schema = block_instance.input_schema
-                    if hasattr(schema, "model_json_schema"):
-                        schema_dict = schema.model_json_schema()
-                        if "properties" in schema_dict:
-                            for prop_name, prop_info in schema_dict[
-                                "properties"
-                            ].items():
-                                if "description" in prop_info:
-                                    parts.append(
-                                        f"{prop_name}: {prop_info['description']}"
-                                    )
-
-                searchable_text = " ".join(parts)
-
-                # Convert categories set of enums to list of strings for JSON serialization
-                categories = getattr(block_instance, "categories", set())
-                categories_list = (
-                    [cat.value for cat in categories] if categories else []
-                )
-
-                items.append(
-                    ContentItem(
-                        content_id=block_id,
-                        content_type=ContentType.BLOCK,
-                        searchable_text=searchable_text,
-                        metadata={
-                            "name": getattr(block_instance, "name", ""),
-                            "categories": categories_list,
-                        },
-                        user_id=None,  # Blocks are public
-                    )
-                )
-            except Exception as e:
-                logger.warning(f"Failed to process block {block_id}: {e}")
-                continue
-
-        return items
-
-    async def get_stats(self) -> dict[str, int]:
-        """Get statistics about block embedding coverage."""
-        from backend.data.block import get_blocks
-
-        all_blocks = get_blocks()
-        total_blocks = len(all_blocks)
-
-        if total_blocks == 0:
-            return {"total": 0, "with_embeddings": 0, "without_embeddings": 0}
-
-        block_ids = list(all_blocks.keys())
-        placeholders = ",".join([f"${i+1}" for i in range(len(block_ids))])
-
-        embedded_result = await query_raw_with_schema(
-            f"""
-            SELECT COUNT(*) as count
-            FROM {{schema_prefix}}"UnifiedContentEmbedding"
-            WHERE "contentType" = 'BLOCK'::{{schema_prefix}}"ContentType"
-            AND "contentId" = ANY(ARRAY[{placeholders}])
-            """,
-            *block_ids,
-        )
-
-        with_embeddings = embedded_result[0]["count"] if embedded_result else 0
-
-        return {
-            "total": total_blocks,
-            "with_embeddings": with_embeddings,
-            "without_embeddings": total_blocks - with_embeddings,
-        }
-
-
-class DocumentationHandler(ContentHandler):
-    """Handler for documentation files (.md/.mdx)."""
-
-    @property
-    def content_type(self) -> ContentType:
-        return ContentType.DOCUMENTATION
-
-    def _get_docs_root(self) -> Path:
-        """Get the documentation root directory."""
-        # content_handlers.py is at: backend/backend/api/features/store/content_handlers.py
-        # Need to go up to project root then into docs/
-        # In container: /app/autogpt_platform/backend/backend/api/features/store -> /app/docs
-        # In development: /repo/autogpt_platform/backend/backend/api/features/store -> /repo/docs
-        this_file = Path(
-            __file__
-        )  # .../backend/backend/api/features/store/content_handlers.py
-        project_root = (
-            this_file.parent.parent.parent.parent.parent.parent.parent
-        )  # -> /app or /repo
-        docs_root = project_root / "docs"
-        return docs_root
-
-    def _extract_title_and_content(self, file_path: Path) -> tuple[str, str]:
-        """Extract title and content from markdown file."""
-        try:
-            content = file_path.read_text(encoding="utf-8")
-
-            # Try to extract title from first # heading
-            lines = content.split("\n")
-            title = ""
-            body_lines = []
-
-            for line in lines:
-                if line.startswith("# ") and not title:
-                    title = line[2:].strip()
-                else:
-                    body_lines.append(line)
-
-            # If no title found, use filename
-            if not title:
-                title = file_path.stem.replace("-", " ").replace("_", " ").title()
-
-            body = "\n".join(body_lines)
-
-            return title, body
-        except Exception as e:
-            logger.warning(f"Failed to read {file_path}: {e}")
-            return file_path.stem, ""
-
-    async def get_missing_items(self, batch_size: int) -> list[ContentItem]:
-        """Fetch documentation files without embeddings."""
-        docs_root = self._get_docs_root()
-
-        if not docs_root.exists():
-            logger.warning(f"Documentation root not found: {docs_root}")
-            return []
-
-        # Find all .md and .mdx files
-        all_docs = list(docs_root.rglob("*.md")) + list(docs_root.rglob("*.mdx"))
-
-        # Get relative paths for content IDs
-        doc_paths = [str(doc.relative_to(docs_root)) for doc in all_docs]
-
-        if not doc_paths:
-            return []
-
-        # Check which ones have embeddings
-        placeholders = ",".join([f"${i+1}" for i in range(len(doc_paths))])
-        existing_result = await query_raw_with_schema(
-            f"""
-            SELECT "contentId"
-            FROM {{schema_prefix}}"UnifiedContentEmbedding"
-            WHERE "contentType" = 'DOCUMENTATION'::{{schema_prefix}}"ContentType"
-            AND "contentId" = ANY(ARRAY[{placeholders}])
-            """,
-            *doc_paths,
-        )
-
-        existing_ids = {row["contentId"] for row in existing_result}
-        missing_docs = [
-            (doc_path, doc_file)
-            for doc_path, doc_file in zip(doc_paths, all_docs)
-            if doc_path not in existing_ids
-        ]
-
-        # Convert to ContentItem
-        items = []
-        for doc_path, doc_file in missing_docs[:batch_size]:
-            try:
-                title, content = self._extract_title_and_content(doc_file)
-
-                # Build searchable text
-                searchable_text = f"{title} {content}"
-
-                items.append(
-                    ContentItem(
-                        content_id=doc_path,
-                        content_type=ContentType.DOCUMENTATION,
-                        searchable_text=searchable_text,
-                        metadata={
-                            "title": title,
-                            "path": doc_path,
-                        },
-                        user_id=None,  # Documentation is public
-                    )
-                )
-            except Exception as e:
-                logger.warning(f"Failed to process doc {doc_path}: {e}")
-                continue
-
-        return items
-
-    async def get_stats(self) -> dict[str, int]:
-        """Get statistics about documentation embedding coverage."""
-        docs_root = self._get_docs_root()
-
-        if not docs_root.exists():
-            return {"total": 0, "with_embeddings": 0, "without_embeddings": 0}
-
-        # Count all .md and .mdx files
-        all_docs = list(docs_root.rglob("*.md")) + list(docs_root.rglob("*.mdx"))
-        total_docs = len(all_docs)
-
-        if total_docs == 0:
-            return {"total": 0, "with_embeddings": 0, "without_embeddings": 0}
-
-        doc_paths = [str(doc.relative_to(docs_root)) for doc in all_docs]
-        placeholders = ",".join([f"${i+1}" for i in range(len(doc_paths))])
-
-        embedded_result = await query_raw_with_schema(
-            f"""
-            SELECT COUNT(*) as count
-            FROM {{schema_prefix}}"UnifiedContentEmbedding"
-            WHERE "contentType" = 'DOCUMENTATION'::{{schema_prefix}}"ContentType"
-            AND "contentId" = ANY(ARRAY[{placeholders}])
-            """,
-            *doc_paths,
-        )
-
-        with_embeddings = embedded_result[0]["count"] if embedded_result else 0
-
-        return {
-            "total": total_docs,
-            "with_embeddings": with_embeddings,
-            "without_embeddings": total_docs - with_embeddings,
-        }
-
-
-# Content handler registry
-CONTENT_HANDLERS: dict[ContentType, ContentHandler] = {
-    ContentType.STORE_AGENT: StoreAgentHandler(),
-    ContentType.BLOCK: BlockHandler(),
-    ContentType.DOCUMENTATION: DocumentationHandler(),
-}

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

@@ -1,215 +0,0 @@
-"""
-Integration tests for content handlers using real DB.
-
-Run with: poetry run pytest backend/api/features/store/content_handlers_integration_test.py -xvs
-
-These tests use the real database but mock OpenAI calls.
-"""
-
-from unittest.mock import patch
-
-import pytest
-
-from backend.api.features.store.content_handlers import (
-    CONTENT_HANDLERS,
-    BlockHandler,
-    DocumentationHandler,
-    StoreAgentHandler,
-)
-from backend.api.features.store.embeddings import (
-    EMBEDDING_DIM,
-    backfill_all_content_types,
-    ensure_content_embedding,
-    get_embedding_stats,
-)
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_store_agent_handler_real_db():
-    """Test StoreAgentHandler with real database queries."""
-    handler = StoreAgentHandler()
-
-    # Get stats from real DB
-    stats = await handler.get_stats()
-
-    # Stats should have correct structure
-    assert "total" in stats
-    assert "with_embeddings" in stats
-    assert "without_embeddings" in stats
-    assert stats["total"] >= 0
-    assert stats["with_embeddings"] >= 0
-    assert stats["without_embeddings"] >= 0
-
-    # Get missing items (max 1 to keep test fast)
-    items = await handler.get_missing_items(batch_size=1)
-
-    # Items should be list (may be empty if all have embeddings)
-    assert isinstance(items, list)
-
-    if items:
-        item = items[0]
-        assert item.content_id is not None
-        assert item.content_type.value == "STORE_AGENT"
-        assert item.searchable_text != ""
-        assert item.user_id is None
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_real_db():
-    """Test BlockHandler with real database queries."""
-    handler = BlockHandler()
-
-    # Get stats from real DB
-    stats = await handler.get_stats()
-
-    # Stats should have correct structure
-    assert "total" in stats
-    assert "with_embeddings" in stats
-    assert "without_embeddings" in stats
-    assert stats["total"] >= 0  # Should have at least some blocks
-    assert stats["with_embeddings"] >= 0
-    assert stats["without_embeddings"] >= 0
-
-    # Get missing items (max 1 to keep test fast)
-    items = await handler.get_missing_items(batch_size=1)
-
-    # Items should be list
-    assert isinstance(items, list)
-
-    if items:
-        item = items[0]
-        assert item.content_id is not None  # Should be block UUID
-        assert item.content_type.value == "BLOCK"
-        assert item.searchable_text != ""
-        assert item.user_id is None
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_documentation_handler_real_fs():
-    """Test DocumentationHandler with real filesystem."""
-    handler = DocumentationHandler()
-
-    # Get stats from real filesystem
-    stats = await handler.get_stats()
-
-    # Stats should have correct structure
-    assert "total" in stats
-    assert "with_embeddings" in stats
-    assert "without_embeddings" in stats
-    assert stats["total"] >= 0
-    assert stats["with_embeddings"] >= 0
-    assert stats["without_embeddings"] >= 0
-
-    # Get missing items (max 1 to keep test fast)
-    items = await handler.get_missing_items(batch_size=1)
-
-    # Items should be list
-    assert isinstance(items, list)
-
-    if items:
-        item = items[0]
-        assert item.content_id is not None  # Should be relative path
-        assert item.content_type.value == "DOCUMENTATION"
-        assert item.searchable_text != ""
-        assert item.user_id is None
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_get_embedding_stats_all_types():
-    """Test get_embedding_stats aggregates all content types."""
-    stats = await get_embedding_stats()
-
-    # Should have structure with by_type and totals
-    assert "by_type" in stats
-    assert "totals" in stats
-
-    # Check each content type is present
-    by_type = stats["by_type"]
-    assert "STORE_AGENT" in by_type
-    assert "BLOCK" in by_type
-    assert "DOCUMENTATION" in by_type
-
-    # Check totals are aggregated
-    totals = stats["totals"]
-    assert totals["total"] >= 0
-    assert totals["with_embeddings"] >= 0
-    assert totals["without_embeddings"] >= 0
-    assert "coverage_percent" in totals
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@patch("backend.api.features.store.embeddings.generate_embedding")
-async def test_ensure_content_embedding_blocks(mock_generate):
-    """Test creating embeddings for blocks (mocked OpenAI)."""
-    # Mock OpenAI to return fake embedding
-    mock_generate.return_value = [0.1] * EMBEDDING_DIM
-
-    # Get one block without embedding
-    handler = BlockHandler()
-    items = await handler.get_missing_items(batch_size=1)
-
-    if not items:
-        pytest.skip("No blocks without embeddings")
-
-    item = items[0]
-
-    # Try to create embedding (OpenAI mocked)
-    result = await ensure_content_embedding(
-        content_type=item.content_type,
-        content_id=item.content_id,
-        searchable_text=item.searchable_text,
-        metadata=item.metadata,
-        user_id=item.user_id,
-    )
-
-    # Should succeed with mocked OpenAI
-    assert result is True
-    mock_generate.assert_called_once()
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@patch("backend.api.features.store.embeddings.generate_embedding")
-async def test_backfill_all_content_types_dry_run(mock_generate):
-    """Test backfill_all_content_types processes all handlers in order."""
-    # Mock OpenAI to return fake embedding
-    mock_generate.return_value = [0.1] * EMBEDDING_DIM
-
-    # Run backfill with batch_size=1 to process max 1 per type
-    result = await backfill_all_content_types(batch_size=1)
-
-    # Should have results for all content types
-    assert "by_type" in result
-    assert "totals" in result
-
-    by_type = result["by_type"]
-    assert "BLOCK" in by_type
-    assert "STORE_AGENT" in by_type
-    assert "DOCUMENTATION" in by_type
-
-    # Each type should have correct structure
-    for content_type, type_result in by_type.items():
-        assert "processed" in type_result
-        assert "success" in type_result
-        assert "failed" in type_result
-
-    # Totals should aggregate
-    totals = result["totals"]
-    assert totals["processed"] >= 0
-    assert totals["success"] >= 0
-    assert totals["failed"] >= 0
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_content_handler_registry():
-    """Test all handlers are registered in correct order."""
-    from prisma.enums import ContentType
-
-    # All three types should be registered
-    assert ContentType.STORE_AGENT in CONTENT_HANDLERS
-    assert ContentType.BLOCK in CONTENT_HANDLERS
-    assert ContentType.DOCUMENTATION in CONTENT_HANDLERS
-
-    # Check handler types
-    assert isinstance(CONTENT_HANDLERS[ContentType.STORE_AGENT], StoreAgentHandler)
-    assert isinstance(CONTENT_HANDLERS[ContentType.BLOCK], BlockHandler)
-    assert isinstance(CONTENT_HANDLERS[ContentType.DOCUMENTATION], DocumentationHandler)

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

@@ -1,324 +0,0 @@
-"""
-E2E tests for content handlers (blocks, store agents, documentation).
-
-Tests the full flow: discovering content → generating embeddings → storing.
-"""
-
-from pathlib import Path
-from unittest.mock import MagicMock, patch
-
-import pytest
-from prisma.enums import ContentType
-
-from backend.api.features.store.content_handlers import (
-    CONTENT_HANDLERS,
-    BlockHandler,
-    DocumentationHandler,
-    StoreAgentHandler,
-)
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_store_agent_handler_get_missing_items(mocker):
-    """Test StoreAgentHandler fetches approved agents without embeddings."""
-    handler = StoreAgentHandler()
-
-    # Mock database query
-    mock_missing = [
-        {
-            "id": "agent-1",
-            "name": "Test Agent",
-            "description": "A test agent",
-            "subHeading": "Test heading",
-            "categories": ["AI", "Testing"],
-        }
-    ]
-
-    with patch(
-        "backend.api.features.store.content_handlers.query_raw_with_schema",
-        return_value=mock_missing,
-    ):
-        items = await handler.get_missing_items(batch_size=10)
-
-        assert len(items) == 1
-        assert items[0].content_id == "agent-1"
-        assert items[0].content_type == ContentType.STORE_AGENT
-        assert "Test Agent" in items[0].searchable_text
-        assert "A test agent" in items[0].searchable_text
-        assert items[0].metadata["name"] == "Test Agent"
-        assert items[0].user_id is None
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_store_agent_handler_get_stats(mocker):
-    """Test StoreAgentHandler returns correct stats."""
-    handler = StoreAgentHandler()
-
-    # Mock approved count query
-    mock_approved = [{"count": 50}]
-    # Mock embedded count query
-    mock_embedded = [{"count": 30}]
-
-    with patch(
-        "backend.api.features.store.content_handlers.query_raw_with_schema",
-        side_effect=[mock_approved, mock_embedded],
-    ):
-        stats = await handler.get_stats()
-
-        assert stats["total"] == 50
-        assert stats["with_embeddings"] == 30
-        assert stats["without_embeddings"] == 20
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_missing_items(mocker):
-    """Test BlockHandler discovers blocks without embeddings."""
-    handler = BlockHandler()
-
-    # Mock get_blocks to return test blocks
-    mock_block_class = MagicMock()
-    mock_block_instance = MagicMock()
-    mock_block_instance.name = "Calculator Block"
-    mock_block_instance.description = "Performs calculations"
-    mock_block_instance.categories = [MagicMock(value="MATH")]
-    mock_block_instance.input_schema.model_json_schema.return_value = {
-        "properties": {"expression": {"description": "Math expression to evaluate"}}
-    }
-    mock_block_class.return_value = mock_block_instance
-
-    mock_blocks = {"block-uuid-1": mock_block_class}
-
-    # Mock existing embeddings query (no embeddings exist)
-    mock_existing = []
-
-    with patch(
-        "backend.data.block.get_blocks",
-        return_value=mock_blocks,
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=mock_existing,
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            assert len(items) == 1
-            assert items[0].content_id == "block-uuid-1"
-            assert items[0].content_type == ContentType.BLOCK
-            assert "Calculator Block" in items[0].searchable_text
-            assert "Performs calculations" in items[0].searchable_text
-            assert "MATH" in items[0].searchable_text
-            assert "expression: Math expression" in items[0].searchable_text
-            assert items[0].user_id is None
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_get_stats(mocker):
-    """Test BlockHandler returns correct stats."""
-    handler = BlockHandler()
-
-    # Mock get_blocks
-    mock_blocks = {
-        "block-1": MagicMock(),
-        "block-2": MagicMock(),
-        "block-3": MagicMock(),
-    }
-
-    # Mock embedded count query (2 blocks have embeddings)
-    mock_embedded = [{"count": 2}]
-
-    with patch(
-        "backend.data.block.get_blocks",
-        return_value=mock_blocks,
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=mock_embedded,
-        ):
-            stats = await handler.get_stats()
-
-            assert stats["total"] == 3
-            assert stats["with_embeddings"] == 2
-            assert stats["without_embeddings"] == 1
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_documentation_handler_get_missing_items(tmp_path, mocker):
-    """Test DocumentationHandler discovers docs without embeddings."""
-    handler = DocumentationHandler()
-
-    # Create temporary docs directory with test files
-    docs_root = tmp_path / "docs"
-    docs_root.mkdir()
-
-    (docs_root / "guide.md").write_text("# Getting Started\n\nThis is a guide.")
-    (docs_root / "api.mdx").write_text("# API Reference\n\nAPI documentation.")
-
-    # Mock _get_docs_root to return temp dir
-    with patch.object(handler, "_get_docs_root", return_value=docs_root):
-        # Mock existing embeddings query (no embeddings exist)
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            assert len(items) == 2
-
-            # Check guide.md
-            guide_item = next(
-                (item for item in items if item.content_id == "guide.md"), None
-            )
-            assert guide_item is not None
-            assert guide_item.content_type == ContentType.DOCUMENTATION
-            assert "Getting Started" in guide_item.searchable_text
-            assert "This is a guide" in guide_item.searchable_text
-            assert guide_item.metadata["title"] == "Getting Started"
-            assert guide_item.user_id is None
-
-            # Check api.mdx
-            api_item = next(
-                (item for item in items if item.content_id == "api.mdx"), None
-            )
-            assert api_item is not None
-            assert "API Reference" in api_item.searchable_text
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_documentation_handler_get_stats(tmp_path, mocker):
-    """Test DocumentationHandler returns correct stats."""
-    handler = DocumentationHandler()
-
-    # Create temporary docs directory
-    docs_root = tmp_path / "docs"
-    docs_root.mkdir()
-    (docs_root / "doc1.md").write_text("# Doc 1")
-    (docs_root / "doc2.md").write_text("# Doc 2")
-    (docs_root / "doc3.mdx").write_text("# Doc 3")
-
-    # Mock embedded count query (1 doc has embedding)
-    mock_embedded = [{"count": 1}]
-
-    with patch.object(handler, "_get_docs_root", return_value=docs_root):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=mock_embedded,
-        ):
-            stats = await handler.get_stats()
-
-            assert stats["total"] == 3
-            assert stats["with_embeddings"] == 1
-            assert stats["without_embeddings"] == 2
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_documentation_handler_title_extraction(tmp_path):
-    """Test DocumentationHandler extracts title from markdown heading."""
-    handler = DocumentationHandler()
-
-    # Test with heading
-    doc_with_heading = tmp_path / "with_heading.md"
-    doc_with_heading.write_text("# My Title\n\nContent here")
-    title, content = handler._extract_title_and_content(doc_with_heading)
-    assert title == "My Title"
-    assert "# My Title" not in content
-    assert "Content here" in content
-
-    # Test without heading
-    doc_without_heading = tmp_path / "no-heading.md"
-    doc_without_heading.write_text("Just content, no heading")
-    title, content = handler._extract_title_and_content(doc_without_heading)
-    assert title == "No Heading"  # Uses filename
-    assert "Just content" in content
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_content_handlers_registry():
-    """Test all content types are registered."""
-    assert ContentType.STORE_AGENT in CONTENT_HANDLERS
-    assert ContentType.BLOCK in CONTENT_HANDLERS
-    assert ContentType.DOCUMENTATION in CONTENT_HANDLERS
-
-    assert isinstance(CONTENT_HANDLERS[ContentType.STORE_AGENT], StoreAgentHandler)
-    assert isinstance(CONTENT_HANDLERS[ContentType.BLOCK], BlockHandler)
-    assert isinstance(CONTENT_HANDLERS[ContentType.DOCUMENTATION], DocumentationHandler)
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_handles_missing_attributes():
-    """Test BlockHandler gracefully handles blocks with missing attributes."""
-    handler = BlockHandler()
-
-    # Mock block with minimal attributes
-    mock_block_class = MagicMock()
-    mock_block_instance = MagicMock()
-    mock_block_instance.name = "Minimal Block"
-    # No description, categories, or schema
-    del mock_block_instance.description
-    del mock_block_instance.categories
-    del mock_block_instance.input_schema
-    mock_block_class.return_value = mock_block_instance
-
-    mock_blocks = {"block-minimal": mock_block_class}
-
-    with patch(
-        "backend.data.block.get_blocks",
-        return_value=mock_blocks,
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            assert len(items) == 1
-            assert items[0].searchable_text == "Minimal Block"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_block_handler_skips_failed_blocks():
-    """Test BlockHandler skips blocks that fail to instantiate."""
-    handler = BlockHandler()
-
-    # Mock one good block and one bad block
-    good_block = MagicMock()
-    good_instance = MagicMock()
-    good_instance.name = "Good Block"
-    good_instance.description = "Works fine"
-    good_instance.categories = []
-    good_block.return_value = good_instance
-
-    bad_block = MagicMock()
-    bad_block.side_effect = Exception("Instantiation failed")
-
-    mock_blocks = {"good-block": good_block, "bad-block": bad_block}
-
-    with patch(
-        "backend.data.block.get_blocks",
-        return_value=mock_blocks,
-    ):
-        with patch(
-            "backend.api.features.store.content_handlers.query_raw_with_schema",
-            return_value=[],
-        ):
-            items = await handler.get_missing_items(batch_size=10)
-
-            # Should only get the good block
-            assert len(items) == 1
-            assert items[0].content_id == "good-block"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_documentation_handler_missing_docs_directory():
-    """Test DocumentationHandler handles missing docs directory gracefully."""
-    handler = DocumentationHandler()
-
-    # Mock _get_docs_root to return non-existent path
-    fake_path = Path("/nonexistent/docs")
-    with patch.object(handler, "_get_docs_root", return_value=fake_path):
-        items = await handler.get_missing_items(batch_size=10)
-        assert items == []
-
-        stats = await handler.get_stats()
-        assert stats["total"] == 0
-        assert stats["with_embeddings"] == 0
-        assert stats["without_embeddings"] == 0

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

@@ -1,962 +0,0 @@
-"""
-Unified Content Embeddings Service
-
-Handles generation and storage of OpenAI embeddings for all content types
-(store listings, blocks, documentation, library agents) to enable semantic/hybrid search.
-"""
-
-import asyncio
-import logging
-import time
-from typing import Any
-
-import prisma
-from prisma.enums import ContentType
-from tiktoken import encoding_for_model
-
-from backend.api.features.store.content_handlers import CONTENT_HANDLERS
-from backend.data.db import execute_raw_with_schema, query_raw_with_schema
-from backend.util.clients import get_openai_client
-from backend.util.json import dumps
-
-logger = logging.getLogger(__name__)
-
-
-# OpenAI embedding model configuration
-EMBEDDING_MODEL = "text-embedding-3-small"
-# Embedding dimension for the model above
-# text-embedding-3-small: 1536, text-embedding-3-large: 3072
-EMBEDDING_DIM = 1536
-# OpenAI embedding token limit (8,191 with 1 token buffer for safety)
-EMBEDDING_MAX_TOKENS = 8191
-
-
-def build_searchable_text(
-    name: str,
-    description: str,
-    sub_heading: str,
-    categories: list[str],
-) -> str:
-    """
-    Build searchable text from listing version fields.
-
-    Combines relevant fields into a single string for embedding.
-    """
-    parts = []
-
-    # Name is important - include it
-    if name:
-        parts.append(name)
-
-    # Sub-heading provides context
-    if sub_heading:
-        parts.append(sub_heading)
-
-    # Description is the main content
-    if description:
-        parts.append(description)
-
-    # Categories help with semantic matching
-    if categories:
-        parts.append(" ".join(categories))
-
-    return " ".join(parts)
-
-
-async def generate_embedding(text: str) -> list[float] | None:
-    """
-    Generate embedding for text using OpenAI API.
-
-    Returns None if embedding generation fails.
-    Fail-fast: no retries to maintain consistency with approval flow.
-    """
-    try:
-        client = get_openai_client()
-        if not client:
-            logger.error("openai_internal_api_key not set, cannot generate embedding")
-            return None
-
-        # Truncate text to token limit using tiktoken
-        # Character-based truncation is insufficient because token ratios vary by content type
-        enc = encoding_for_model(EMBEDDING_MODEL)
-        tokens = enc.encode(text)
-        if len(tokens) > EMBEDDING_MAX_TOKENS:
-            tokens = tokens[:EMBEDDING_MAX_TOKENS]
-            truncated_text = enc.decode(tokens)
-            logger.info(
-                f"Truncated text from {len(enc.encode(text))} to {len(tokens)} tokens"
-            )
-        else:
-            truncated_text = text
-
-        start_time = time.time()
-        response = await client.embeddings.create(
-            model=EMBEDDING_MODEL,
-            input=truncated_text,
-        )
-        latency_ms = (time.time() - start_time) * 1000
-
-        embedding = response.data[0].embedding
-        logger.info(
-            f"Generated embedding: {len(embedding)} dims, "
-            f"{len(tokens)} tokens, {latency_ms:.0f}ms"
-        )
-        return embedding
-
-    except Exception as e:
-        logger.error(f"Failed to generate embedding: {e}")
-        return None
-
-
-async def store_embedding(
-    version_id: str,
-    embedding: list[float],
-    tx: prisma.Prisma | None = None,
-) -> bool:
-    """
-    Store embedding in the database.
-
-    BACKWARD COMPATIBILITY: Maintained for existing store listing usage.
-    DEPRECATED: Use ensure_embedding() instead (includes searchable_text).
-    """
-    return await store_content_embedding(
-        content_type=ContentType.STORE_AGENT,
-        content_id=version_id,
-        embedding=embedding,
-        searchable_text="",  # Empty for backward compat; ensure_embedding() populates this
-        metadata=None,
-        user_id=None,  # Store agents are public
-        tx=tx,
-    )
-
-
-async def store_content_embedding(
-    content_type: ContentType,
-    content_id: str,
-    embedding: list[float],
-    searchable_text: str,
-    metadata: dict | None = None,
-    user_id: str | None = None,
-    tx: prisma.Prisma | None = None,
-) -> bool:
-    """
-    Store embedding in the unified content embeddings table.
-
-    New function for unified content embedding storage.
-    Uses raw SQL since Prisma doesn't natively support pgvector.
-    """
-    try:
-        client = tx if tx else prisma.get_client()
-
-        # Convert embedding to PostgreSQL vector format
-        embedding_str = embedding_to_vector_string(embedding)
-        metadata_json = dumps(metadata or {})
-
-        # Upsert the embedding
-        # WHERE clause in DO UPDATE prevents PostgreSQL 15 bug with NULLS NOT DISTINCT
-        await execute_raw_with_schema(
-            """
-            INSERT INTO {schema_prefix}"UnifiedContentEmbedding" (
-                "id", "contentType", "contentId", "userId", "embedding", "searchableText", "metadata", "createdAt", "updatedAt"
-            )
-            VALUES (gen_random_uuid()::text, $1::{schema_prefix}"ContentType", $2, $3, $4::vector, $5, $6::jsonb, NOW(), NOW())
-            ON CONFLICT ("contentType", "contentId", "userId")
-            DO UPDATE SET
-                "embedding" = $4::vector,
-                "searchableText" = $5,
-                "metadata" = $6::jsonb,
-                "updatedAt" = NOW()
-            WHERE {schema_prefix}"UnifiedContentEmbedding"."contentType" = $1::{schema_prefix}"ContentType"
-                AND {schema_prefix}"UnifiedContentEmbedding"."contentId" = $2
-                AND ({schema_prefix}"UnifiedContentEmbedding"."userId" = $3 OR ($3 IS NULL AND {schema_prefix}"UnifiedContentEmbedding"."userId" IS NULL))
-            """,
-            content_type,
-            content_id,
-            user_id,
-            embedding_str,
-            searchable_text,
-            metadata_json,
-            client=client,
-            set_public_search_path=True,
-        )
-
-        logger.info(f"Stored embedding for {content_type}:{content_id}")
-        return True
-
-    except Exception as e:
-        logger.error(f"Failed to store embedding for {content_type}:{content_id}: {e}")
-        return False
-
-
-async def get_embedding(version_id: str) -> dict[str, Any] | None:
-    """
-    Retrieve embedding record for a listing version.
-
-    BACKWARD COMPATIBILITY: Maintained for existing store listing usage.
-    Returns dict with storeListingVersionId, embedding, timestamps or None if not found.
-    """
-    result = await get_content_embedding(
-        ContentType.STORE_AGENT, version_id, user_id=None
-    )
-    if result:
-        # Transform to old format for backward compatibility
-        return {
-            "storeListingVersionId": result["contentId"],
-            "embedding": result["embedding"],
-            "createdAt": result["createdAt"],
-            "updatedAt": result["updatedAt"],
-        }
-    return None
-
-
-async def get_content_embedding(
-    content_type: ContentType, content_id: str, user_id: str | None = None
-) -> dict[str, Any] | None:
-    """
-    Retrieve embedding record for any content type.
-
-    New function for unified content embedding retrieval.
-    Returns dict with contentType, contentId, embedding, timestamps or None if not found.
-    """
-    try:
-        result = await query_raw_with_schema(
-            """
-            SELECT
-                "contentType",
-                "contentId",
-                "userId",
-                "embedding"::text as "embedding",
-                "searchableText",
-                "metadata",
-                "createdAt",
-                "updatedAt"
-            FROM {schema_prefix}"UnifiedContentEmbedding"
-            WHERE "contentType" = $1::{schema_prefix}"ContentType" AND "contentId" = $2 AND ("userId" = $3 OR ($3 IS NULL AND "userId" IS NULL))
-            """,
-            content_type,
-            content_id,
-            user_id,
-            set_public_search_path=True,
-        )
-
-        if result and len(result) > 0:
-            return result[0]
-        return None
-
-    except Exception as e:
-        logger.error(f"Failed to get embedding for {content_type}:{content_id}: {e}")
-        return None
-
-
-async def ensure_embedding(
-    version_id: str,
-    name: str,
-    description: str,
-    sub_heading: str,
-    categories: list[str],
-    force: bool = False,
-    tx: prisma.Prisma | None = None,
-) -> bool:
-    """
-    Ensure an embedding exists for the listing version.
-
-    Creates embedding if missing. Use force=True to regenerate.
-    Backward-compatible wrapper for store listings.
-
-    Args:
-        version_id: The StoreListingVersion ID
-        name: Agent name
-        description: Agent description
-        sub_heading: Agent sub-heading
-        categories: Agent categories
-        force: Force regeneration even if embedding exists
-        tx: Optional transaction client
-
-    Returns:
-        True if embedding exists/was created, False on failure
-    """
-    try:
-        # Check if embedding already exists
-        if not force:
-            existing = await get_embedding(version_id)
-            if existing and existing.get("embedding"):
-                logger.debug(f"Embedding for version {version_id} already exists")
-                return True
-
-        # Build searchable text for embedding
-        searchable_text = build_searchable_text(
-            name, description, sub_heading, categories
-        )
-
-        # Generate new embedding
-        embedding = await generate_embedding(searchable_text)
-        if embedding is None:
-            logger.warning(f"Could not generate embedding for version {version_id}")
-            return False
-
-        # Store the embedding with metadata using new function
-        metadata = {
-            "name": name,
-            "subHeading": sub_heading,
-            "categories": categories,
-        }
-        return await store_content_embedding(
-            content_type=ContentType.STORE_AGENT,
-            content_id=version_id,
-            embedding=embedding,
-            searchable_text=searchable_text,
-            metadata=metadata,
-            user_id=None,  # Store agents are public
-            tx=tx,
-        )
-
-    except Exception as e:
-        logger.error(f"Failed to ensure embedding for version {version_id}: {e}")
-        return False
-
-
-async def delete_embedding(version_id: str) -> bool:
-    """
-    Delete embedding for a listing version.
-
-    BACKWARD COMPATIBILITY: Maintained for existing store listing usage.
-    Note: This is usually handled automatically by CASCADE delete,
-    but provided for manual cleanup if needed.
-    """
-    return await delete_content_embedding(ContentType.STORE_AGENT, version_id)
-
-
-async def delete_content_embedding(
-    content_type: ContentType, content_id: str, user_id: str | None = None
-) -> bool:
-    """
-    Delete embedding for any content type.
-
-    New function for unified content embedding deletion.
-    Note: This is usually handled automatically by CASCADE delete,
-    but provided for manual cleanup if needed.
-
-    Args:
-        content_type: The type of content (STORE_AGENT, LIBRARY_AGENT, etc.)
-        content_id: The unique identifier for the content
-        user_id: Optional user ID. For public content (STORE_AGENT, BLOCK), pass None.
-                 For user-scoped content (LIBRARY_AGENT), pass the user's ID to avoid
-                 deleting embeddings belonging to other users.
-
-    Returns:
-        True if deletion succeeded, False otherwise
-    """
-    try:
-        client = prisma.get_client()
-
-        await execute_raw_with_schema(
-            """
-            DELETE FROM {schema_prefix}"UnifiedContentEmbedding"
-            WHERE "contentType" = $1::{schema_prefix}"ContentType"
-              AND "contentId" = $2
-              AND ("userId" = $3 OR ($3 IS NULL AND "userId" IS NULL))
-            """,
-            content_type,
-            content_id,
-            user_id,
-            client=client,
-        )
-
-        user_str = f" (user: {user_id})" if user_id else ""
-        logger.info(f"Deleted embedding for {content_type}:{content_id}{user_str}")
-        return True
-
-    except Exception as e:
-        logger.error(f"Failed to delete embedding for {content_type}:{content_id}: {e}")
-        return False
-
-
-async def get_embedding_stats() -> dict[str, Any]:
-    """
-    Get statistics about embedding coverage for all content types.
-
-    Returns stats per content type and overall totals.
-    """
-    try:
-        stats_by_type = {}
-        total_items = 0
-        total_with_embeddings = 0
-        total_without_embeddings = 0
-
-        # Aggregate stats from all handlers
-        for content_type, handler in CONTENT_HANDLERS.items():
-            try:
-                stats = await handler.get_stats()
-                stats_by_type[content_type.value] = {
-                    "total": stats["total"],
-                    "with_embeddings": stats["with_embeddings"],
-                    "without_embeddings": stats["without_embeddings"],
-                    "coverage_percent": (
-                        round(stats["with_embeddings"] / stats["total"] * 100, 1)
-                        if stats["total"] > 0
-                        else 0
-                    ),
-                }
-
-                total_items += stats["total"]
-                total_with_embeddings += stats["with_embeddings"]
-                total_without_embeddings += stats["without_embeddings"]
-
-            except Exception as e:
-                logger.error(f"Failed to get stats for {content_type.value}: {e}")
-                stats_by_type[content_type.value] = {
-                    "total": 0,
-                    "with_embeddings": 0,
-                    "without_embeddings": 0,
-                    "coverage_percent": 0,
-                    "error": str(e),
-                }
-
-        return {
-            "by_type": stats_by_type,
-            "totals": {
-                "total": total_items,
-                "with_embeddings": total_with_embeddings,
-                "without_embeddings": total_without_embeddings,
-                "coverage_percent": (
-                    round(total_with_embeddings / total_items * 100, 1)
-                    if total_items > 0
-                    else 0
-                ),
-            },
-        }
-
-    except Exception as e:
-        logger.error(f"Failed to get embedding stats: {e}")
-        return {
-            "by_type": {},
-            "totals": {
-                "total": 0,
-                "with_embeddings": 0,
-                "without_embeddings": 0,
-                "coverage_percent": 0,
-            },
-            "error": str(e),
-        }
-
-
-async def backfill_missing_embeddings(batch_size: int = 10) -> dict[str, Any]:
-    """
-    Generate embeddings for approved listings that don't have them.
-
-    BACKWARD COMPATIBILITY: Maintained for existing usage.
-    This now delegates to backfill_all_content_types() to process all content types.
-
-    Args:
-        batch_size: Number of embeddings to generate per content type
-
-    Returns:
-        Dict with success/failure counts aggregated across all content types
-    """
-    # Delegate to the new generic backfill system
-    result = await backfill_all_content_types(batch_size)
-
-    # Return in the old format for backward compatibility
-    return result["totals"]
-
-
-async def backfill_all_content_types(batch_size: int = 10) -> dict[str, Any]:
-    """
-    Generate embeddings for all content types using registered handlers.
-
-    Processes content types in order: BLOCK → STORE_AGENT → DOCUMENTATION.
-    This ensures foundational content (blocks) are searchable first.
-
-    Args:
-        batch_size: Number of embeddings to generate per content type
-
-    Returns:
-        Dict with stats per content type and overall totals
-    """
-    results_by_type = {}
-    total_processed = 0
-    total_success = 0
-    total_failed = 0
-
-    # Process content types in explicit order
-    processing_order = [
-        ContentType.BLOCK,
-        ContentType.STORE_AGENT,
-        ContentType.DOCUMENTATION,
-    ]
-
-    for content_type in processing_order:
-        handler = CONTENT_HANDLERS.get(content_type)
-        if not handler:
-            logger.warning(f"No handler registered for {content_type.value}")
-            continue
-        try:
-            logger.info(f"Processing {content_type.value} content type...")
-
-            # Get missing items from handler
-            missing_items = await handler.get_missing_items(batch_size)
-
-            if not missing_items:
-                results_by_type[content_type.value] = {
-                    "processed": 0,
-                    "success": 0,
-                    "failed": 0,
-                    "message": "No missing embeddings",
-                }
-                continue
-
-            # Process embeddings concurrently for better performance
-            embedding_tasks = [
-                ensure_content_embedding(
-                    content_type=item.content_type,
-                    content_id=item.content_id,
-                    searchable_text=item.searchable_text,
-                    metadata=item.metadata,
-                    user_id=item.user_id,
-                )
-                for item in missing_items
-            ]
-
-            results = await asyncio.gather(*embedding_tasks, return_exceptions=True)
-
-            success = sum(1 for result in results if result is True)
-            failed = len(results) - success
-
-            results_by_type[content_type.value] = {
-                "processed": len(missing_items),
-                "success": success,
-                "failed": failed,
-                "message": f"Backfilled {success} embeddings, {failed} failed",
-            }
-
-            total_processed += len(missing_items)
-            total_success += success
-            total_failed += failed
-
-            logger.info(
-                f"{content_type.value}: processed {len(missing_items)}, "
-                f"success {success}, failed {failed}"
-            )
-
-        except Exception as e:
-            logger.error(f"Failed to process {content_type.value}: {e}")
-            results_by_type[content_type.value] = {
-                "processed": 0,
-                "success": 0,
-                "failed": 0,
-                "error": str(e),
-            }
-
-    return {
-        "by_type": results_by_type,
-        "totals": {
-            "processed": total_processed,
-            "success": total_success,
-            "failed": total_failed,
-            "message": f"Overall: {total_success} succeeded, {total_failed} failed",
-        },
-    }
-
-
-async def embed_query(query: str) -> list[float] | None:
-    """
-    Generate embedding for a search query.
-
-    Same as generate_embedding but with clearer intent.
-    """
-    return await generate_embedding(query)
-
-
-def embedding_to_vector_string(embedding: list[float]) -> str:
-    """Convert embedding list to PostgreSQL vector string format."""
-    return "[" + ",".join(str(x) for x in embedding) + "]"
-
-
-async def ensure_content_embedding(
-    content_type: ContentType,
-    content_id: str,
-    searchable_text: str,
-    metadata: dict | None = None,
-    user_id: str | None = None,
-    force: bool = False,
-    tx: prisma.Prisma | None = None,
-) -> bool:
-    """
-    Ensure an embedding exists for any content type.
-
-    Generic function for creating embeddings for store agents, blocks, docs, etc.
-
-    Args:
-        content_type: ContentType enum value (STORE_AGENT, BLOCK, etc.)
-        content_id: Unique identifier for the content
-        searchable_text: Combined text for embedding generation
-        metadata: Optional metadata to store with embedding
-        force: Force regeneration even if embedding exists
-        tx: Optional transaction client
-
-    Returns:
-        True if embedding exists/was created, False on failure
-    """
-    try:
-        # Check if embedding already exists
-        if not force:
-            existing = await get_content_embedding(content_type, content_id, user_id)
-            if existing and existing.get("embedding"):
-                logger.debug(
-                    f"Embedding for {content_type}:{content_id} already exists"
-                )
-                return True
-
-        # Generate new embedding
-        embedding = await generate_embedding(searchable_text)
-        if embedding is None:
-            logger.warning(
-                f"Could not generate embedding for {content_type}:{content_id}"
-            )
-            return False
-
-        # Store the embedding
-        return await store_content_embedding(
-            content_type=content_type,
-            content_id=content_id,
-            embedding=embedding,
-            searchable_text=searchable_text,
-            metadata=metadata or {},
-            user_id=user_id,
-            tx=tx,
-        )
-
-    except Exception as e:
-        logger.error(f"Failed to ensure embedding for {content_type}:{content_id}: {e}")
-        return False
-
-
-async def cleanup_orphaned_embeddings() -> dict[str, Any]:
-    """
-    Clean up embeddings for content that no longer exists or is no longer valid.
-
-    Compares current content with embeddings in database and removes orphaned records:
-    - STORE_AGENT: Removes embeddings for rejected/deleted store listings
-    - BLOCK: Removes embeddings for blocks no longer registered
-    - DOCUMENTATION: Removes embeddings for deleted doc files
-
-    Returns:
-        Dict with cleanup statistics per content type
-    """
-    results_by_type = {}
-    total_deleted = 0
-
-    # Cleanup orphaned embeddings for all content types
-    cleanup_types = [
-        ContentType.STORE_AGENT,
-        ContentType.BLOCK,
-        ContentType.DOCUMENTATION,
-    ]
-
-    for content_type in cleanup_types:
-        try:
-            handler = CONTENT_HANDLERS.get(content_type)
-            if not handler:
-                logger.warning(f"No handler registered for {content_type}")
-                results_by_type[content_type.value] = {
-                    "deleted": 0,
-                    "error": "No handler registered",
-                }
-                continue
-
-            # Get all current content IDs from handler
-            if content_type == ContentType.STORE_AGENT:
-                # Get IDs of approved store listing versions from non-deleted listings
-                valid_agents = await query_raw_with_schema(
-                    """
-                    SELECT slv.id
-                    FROM {schema_prefix}"StoreListingVersion" slv
-                    JOIN {schema_prefix}"StoreListing" sl ON slv."storeListingId" = sl.id
-                    WHERE slv."submissionStatus" = 'APPROVED'
-                      AND slv."isDeleted" = false
-                      AND sl."isDeleted" = false
-                    """,
-                )
-                current_ids = {row["id"] for row in valid_agents}
-            elif content_type == ContentType.BLOCK:
-                from backend.data.block import get_blocks
-
-                current_ids = set(get_blocks().keys())
-            elif content_type == ContentType.DOCUMENTATION:
-                from pathlib import Path
-
-                # embeddings.py is at: backend/backend/api/features/store/embeddings.py
-                # Need to go up to project root then into docs/
-                this_file = Path(__file__)
-                project_root = (
-                    this_file.parent.parent.parent.parent.parent.parent.parent
-                )
-                docs_root = project_root / "docs"
-                if docs_root.exists():
-                    all_docs = list(docs_root.rglob("*.md")) + list(
-                        docs_root.rglob("*.mdx")
-                    )
-                    current_ids = {str(doc.relative_to(docs_root)) for doc in all_docs}
-                else:
-                    current_ids = set()
-            else:
-                # Skip unknown content types to avoid accidental deletion
-                logger.warning(
-                    f"Skipping cleanup for unknown content type: {content_type}"
-                )
-                results_by_type[content_type.value] = {
-                    "deleted": 0,
-                    "error": "Unknown content type - skipped for safety",
-                }
-                continue
-
-            # Get all embedding IDs from database
-            db_embeddings = await query_raw_with_schema(
-                """
-                SELECT "contentId"
-                FROM {schema_prefix}"UnifiedContentEmbedding"
-                WHERE "contentType" = $1::{schema_prefix}"ContentType"
-                """,
-                content_type,
-            )
-
-            db_ids = {row["contentId"] for row in db_embeddings}
-
-            # Find orphaned embeddings (in DB but not in current content)
-            orphaned_ids = db_ids - current_ids
-
-            if not orphaned_ids:
-                logger.info(f"{content_type.value}: No orphaned embeddings found")
-                results_by_type[content_type.value] = {
-                    "deleted": 0,
-                    "message": "No orphaned embeddings",
-                }
-                continue
-
-            # Delete orphaned embeddings in batch for better performance
-            orphaned_list = list(orphaned_ids)
-            try:
-                await execute_raw_with_schema(
-                    """
-                    DELETE FROM {schema_prefix}"UnifiedContentEmbedding"
-                    WHERE "contentType" = $1::{schema_prefix}"ContentType"
-                      AND "contentId" = ANY($2::text[])
-                    """,
-                    content_type,
-                    orphaned_list,
-                )
-                deleted = len(orphaned_list)
-            except Exception as e:
-                logger.error(f"Failed to batch delete orphaned embeddings: {e}")
-                deleted = 0
-
-            logger.info(
-                f"{content_type.value}: Deleted {deleted}/{len(orphaned_ids)} orphaned embeddings"
-            )
-            results_by_type[content_type.value] = {
-                "deleted": deleted,
-                "orphaned": len(orphaned_ids),
-                "message": f"Deleted {deleted} orphaned embeddings",
-            }
-
-            total_deleted += deleted
-
-        except Exception as e:
-            logger.error(f"Failed to cleanup {content_type.value}: {e}")
-            results_by_type[content_type.value] = {
-                "deleted": 0,
-                "error": str(e),
-            }
-
-    return {
-        "by_type": results_by_type,
-        "totals": {
-            "deleted": total_deleted,
-            "message": f"Deleted {total_deleted} orphaned embeddings",
-        },
-    }
-
-
-async def semantic_search(
-    query: str,
-    content_types: list[ContentType] | None = None,
-    user_id: str | None = None,
-    limit: int = 20,
-    min_similarity: float = 0.5,
-) -> list[dict[str, Any]]:
-    """
-    Semantic search across content types using embeddings.
-
-    Performs vector similarity search on UnifiedContentEmbedding table.
-    Used directly for blocks/docs/library agents, or as the semantic component
-    within hybrid_search for store agents.
-
-    If embedding generation fails, falls back to lexical search on searchableText.
-
-    Args:
-        query: Search query string
-        content_types: List of ContentType to search. Defaults to [BLOCK, STORE_AGENT, DOCUMENTATION]
-        user_id: Optional user ID for searching private content (library agents)
-        limit: Maximum number of results to return (default: 20)
-        min_similarity: Minimum cosine similarity threshold (0-1, default: 0.5)
-
-    Returns:
-        List of search results with the following structure:
-        [
-            {
-                "content_id": str,
-                "content_type": str,  # "BLOCK", "STORE_AGENT", "DOCUMENTATION", or "LIBRARY_AGENT"
-                "searchable_text": str,
-                "metadata": dict,
-                "similarity": float,  # Cosine similarity score (0-1)
-            },
-            ...
-        ]
-
-    Examples:
-        # Search blocks only
-        results = await semantic_search("calculate", content_types=[ContentType.BLOCK])
-
-        # Search blocks and documentation
-        results = await semantic_search(
-            "how to use API",
-            content_types=[ContentType.BLOCK, ContentType.DOCUMENTATION]
-        )
-
-        # Search all public content (default)
-        results = await semantic_search("AI agent")
-
-        # Search user's library agents
-        results = await semantic_search(
-            "my custom agent",
-            content_types=[ContentType.LIBRARY_AGENT],
-            user_id="user123"
-        )
-    """
-    # Default to searching all public content types
-    if content_types is None:
-        content_types = [
-            ContentType.BLOCK,
-            ContentType.STORE_AGENT,
-            ContentType.DOCUMENTATION,
-        ]
-
-    # Validate inputs
-    if not content_types:
-        return []  # Empty content_types would cause invalid SQL (IN ())
-
-    query = query.strip()
-    if not query:
-        return []
-
-    if limit < 1:
-        limit = 1
-    if limit > 100:
-        limit = 100
-
-    # Generate query embedding
-    query_embedding = await embed_query(query)
-
-    if query_embedding is not None:
-        # Semantic search with embeddings
-        embedding_str = embedding_to_vector_string(query_embedding)
-
-        # Build params in order: limit, then user_id (if provided), then content types
-        params: list[Any] = [limit]
-        user_filter = ""
-        if user_id is not None:
-            user_filter = 'AND "userId" = ${}'.format(len(params) + 1)
-            params.append(user_id)
-
-        # Add content type parameters and build placeholders dynamically
-        content_type_start_idx = len(params) + 1
-        content_type_placeholders = ", ".join(
-            f'${content_type_start_idx + i}::{{{{schema_prefix}}}}"ContentType"'
-            for i in range(len(content_types))
-        )
-        params.extend([ct.value for ct in content_types])
-
-        sql = f"""
-            SELECT
-                "contentId" as content_id,
-                "contentType" as content_type,
-                "searchableText" as searchable_text,
-                metadata,
-                1 - (embedding <=> '{embedding_str}'::vector) as similarity
-            FROM {{{{schema_prefix}}}}"UnifiedContentEmbedding"
-            WHERE "contentType" IN ({content_type_placeholders})
-            {user_filter}
-            AND 1 - (embedding <=> '{embedding_str}'::vector) >= ${len(params) + 1}
-            ORDER BY similarity DESC
-            LIMIT $1
-        """
-        params.append(min_similarity)
-
-        try:
-            results = await query_raw_with_schema(
-                sql, *params, set_public_search_path=True
-            )
-            return [
-                {
-                    "content_id": row["content_id"],
-                    "content_type": row["content_type"],
-                    "searchable_text": row["searchable_text"],
-                    "metadata": row["metadata"],
-                    "similarity": float(row["similarity"]),
-                }
-                for row in results
-            ]
-        except Exception as e:
-            logger.error(f"Semantic search failed: {e}")
-            # Fall through to lexical search below
-
-    # Fallback to lexical search if embeddings unavailable
-    logger.warning("Falling back to lexical search (embeddings unavailable)")
-
-    params_lexical: list[Any] = [limit]
-    user_filter = ""
-    if user_id is not None:
-        user_filter = 'AND "userId" = ${}'.format(len(params_lexical) + 1)
-        params_lexical.append(user_id)
-
-    # Add content type parameters and build placeholders dynamically
-    content_type_start_idx = len(params_lexical) + 1
-    content_type_placeholders_lexical = ", ".join(
-        f'${content_type_start_idx + i}::{{{{schema_prefix}}}}"ContentType"'
-        for i in range(len(content_types))
-    )
-    params_lexical.extend([ct.value for ct in content_types])
-
-    sql_lexical = f"""
-        SELECT
-            "contentId" as content_id,
-            "contentType" as content_type,
-            "searchableText" as searchable_text,
-            metadata,
-            0.0 as similarity
-        FROM {{{{schema_prefix}}}}"UnifiedContentEmbedding"
-        WHERE "contentType" IN ({content_type_placeholders_lexical})
-        {user_filter}
-        AND "searchableText" ILIKE ${len(params_lexical) + 1}
-        ORDER BY "updatedAt" DESC
-        LIMIT $1
-    """
-    params_lexical.append(f"%{query}%")
-
-    try:
-        results = await query_raw_with_schema(
-            sql_lexical, *params_lexical, set_public_search_path=True
-        )
-        return [
-            {
-                "content_id": row["content_id"],
-                "content_type": row["content_type"],
-                "searchable_text": row["searchable_text"],
-                "metadata": row["metadata"],
-                "similarity": 0.0,  # Lexical search doesn't provide similarity
-            }
-            for row in results
-        ]
-    except Exception as e:
-        logger.error(f"Lexical search failed: {e}")
-        return []

autogpt_platform/backend/backend/api/features/store/embeddings_e2e_test.py

@@ -1,666 +0,0 @@
-"""
-End-to-end database tests for embeddings and hybrid search.
-
-These tests hit the actual database to verify SQL queries work correctly.
-Tests cover:
-1. Embedding storage (store_content_embedding)
-2. Embedding retrieval (get_content_embedding)
-3. Embedding deletion (delete_content_embedding)
-4. Unified hybrid search across content types
-5. Store agent hybrid search
-"""
-
-import uuid
-from typing import AsyncGenerator
-
-import pytest
-from prisma.enums import ContentType
-
-from backend.api.features.store import embeddings
-from backend.api.features.store.embeddings import EMBEDDING_DIM
-from backend.api.features.store.hybrid_search import (
-    hybrid_search,
-    unified_hybrid_search,
-)
-
-# ============================================================================
-# Test Fixtures
-# ============================================================================
-
-
-@pytest.fixture
-def test_content_id() -> str:
-    """Generate unique content ID for test isolation."""
-    return f"test-content-{uuid.uuid4()}"
-
-
-@pytest.fixture
-def test_user_id() -> str:
-    """Generate unique user ID for test isolation."""
-    return f"test-user-{uuid.uuid4()}"
-
-
-@pytest.fixture
-def mock_embedding() -> list[float]:
-    """Generate a mock embedding vector."""
-    # Create a normalized embedding vector
-    import math
-
-    raw = [float(i % 10) / 10.0 for i in range(EMBEDDING_DIM)]
-    # Normalize to unit length (required for cosine similarity)
-    magnitude = math.sqrt(sum(x * x for x in raw))
-    return [x / magnitude for x in raw]
-
-
-@pytest.fixture
-def similar_embedding() -> list[float]:
-    """Generate an embedding similar to mock_embedding."""
-    import math
-
-    # Similar but slightly different values
-    raw = [float(i % 10) / 10.0 + 0.01 for i in range(EMBEDDING_DIM)]
-    magnitude = math.sqrt(sum(x * x for x in raw))
-    return [x / magnitude for x in raw]
-
-
-@pytest.fixture
-def different_embedding() -> list[float]:
-    """Generate an embedding very different from mock_embedding."""
-    import math
-
-    # Reversed pattern to be maximally different
-    raw = [float((EMBEDDING_DIM - i) % 10) / 10.0 for i in range(EMBEDDING_DIM)]
-    magnitude = math.sqrt(sum(x * x for x in raw))
-    return [x / magnitude for x in raw]
-
-
-@pytest.fixture
-async def cleanup_embeddings(
-    server,
-) -> AsyncGenerator[list[tuple[ContentType, str, str | None]], None]:
-    """
-    Fixture that tracks created embeddings and cleans them up after tests.
-
-    Yields a list to which tests can append (content_type, content_id, user_id) tuples.
-    """
-    created_embeddings: list[tuple[ContentType, str, str | None]] = []
-    yield created_embeddings
-
-    # Cleanup all created embeddings
-    for content_type, content_id, user_id in created_embeddings:
-        try:
-            await embeddings.delete_content_embedding(content_type, content_id, user_id)
-        except Exception:
-            pass  # Ignore cleanup errors
-
-
-# ============================================================================
-# store_content_embedding Tests
-# ============================================================================
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_store_content_embedding_store_agent(
-    server,
-    test_content_id: str,
-    mock_embedding: list[float],
-    cleanup_embeddings: list,
-):
-    """Test storing embedding for STORE_AGENT content type."""
-    # Track for cleanup
-    cleanup_embeddings.append((ContentType.STORE_AGENT, test_content_id, None))
-
-    result = await embeddings.store_content_embedding(
-        content_type=ContentType.STORE_AGENT,
-        content_id=test_content_id,
-        embedding=mock_embedding,
-        searchable_text="AI assistant for productivity tasks",
-        metadata={"name": "Test Agent", "categories": ["productivity"]},
-        user_id=None,  # Store agents are public
-    )
-
-    assert result is True
-
-    # Verify it was stored
-    stored = await embeddings.get_content_embedding(
-        ContentType.STORE_AGENT, test_content_id, user_id=None
-    )
-    assert stored is not None
-    assert stored["contentId"] == test_content_id
-    assert stored["contentType"] == "STORE_AGENT"
-    assert stored["searchableText"] == "AI assistant for productivity tasks"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_store_content_embedding_block(
-    server,
-    test_content_id: str,
-    mock_embedding: list[float],
-    cleanup_embeddings: list,
-):
-    """Test storing embedding for BLOCK content type."""
-    cleanup_embeddings.append((ContentType.BLOCK, test_content_id, None))
-
-    result = await embeddings.store_content_embedding(
-        content_type=ContentType.BLOCK,
-        content_id=test_content_id,
-        embedding=mock_embedding,
-        searchable_text="HTTP request block for API calls",
-        metadata={"name": "HTTP Request Block"},
-        user_id=None,  # Blocks are public
-    )
-
-    assert result is True
-
-    stored = await embeddings.get_content_embedding(
-        ContentType.BLOCK, test_content_id, user_id=None
-    )
-    assert stored is not None
-    assert stored["contentType"] == "BLOCK"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_store_content_embedding_documentation(
-    server,
-    test_content_id: str,
-    mock_embedding: list[float],
-    cleanup_embeddings: list,
-):
-    """Test storing embedding for DOCUMENTATION content type."""
-    cleanup_embeddings.append((ContentType.DOCUMENTATION, test_content_id, None))
-
-    result = await embeddings.store_content_embedding(
-        content_type=ContentType.DOCUMENTATION,
-        content_id=test_content_id,
-        embedding=mock_embedding,
-        searchable_text="Getting started guide for AutoGPT platform",
-        metadata={"title": "Getting Started", "url": "/docs/getting-started"},
-        user_id=None,  # Docs are public
-    )
-
-    assert result is True
-
-    stored = await embeddings.get_content_embedding(
-        ContentType.DOCUMENTATION, test_content_id, user_id=None
-    )
-    assert stored is not None
-    assert stored["contentType"] == "DOCUMENTATION"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_store_content_embedding_upsert(
-    server,
-    test_content_id: str,
-    mock_embedding: list[float],
-    cleanup_embeddings: list,
-):
-    """Test that storing embedding twice updates instead of duplicates."""
-    cleanup_embeddings.append((ContentType.BLOCK, test_content_id, None))
-
-    # Store first time
-    result1 = await embeddings.store_content_embedding(
-        content_type=ContentType.BLOCK,
-        content_id=test_content_id,
-        embedding=mock_embedding,
-        searchable_text="Original text",
-        metadata={"version": 1},
-        user_id=None,
-    )
-    assert result1 is True
-
-    # Store again with different text (upsert)
-    result2 = await embeddings.store_content_embedding(
-        content_type=ContentType.BLOCK,
-        content_id=test_content_id,
-        embedding=mock_embedding,
-        searchable_text="Updated text",
-        metadata={"version": 2},
-        user_id=None,
-    )
-    assert result2 is True
-
-    # Verify only one record with updated text
-    stored = await embeddings.get_content_embedding(
-        ContentType.BLOCK, test_content_id, user_id=None
-    )
-    assert stored is not None
-    assert stored["searchableText"] == "Updated text"
-
-
-# ============================================================================
-# get_content_embedding Tests
-# ============================================================================
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_get_content_embedding_not_found(server):
-    """Test retrieving non-existent embedding returns None."""
-    result = await embeddings.get_content_embedding(
-        ContentType.STORE_AGENT, "non-existent-id", user_id=None
-    )
-    assert result is None
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_get_content_embedding_with_metadata(
-    server,
-    test_content_id: str,
-    mock_embedding: list[float],
-    cleanup_embeddings: list,
-):
-    """Test that metadata is correctly stored and retrieved."""
-    cleanup_embeddings.append((ContentType.STORE_AGENT, test_content_id, None))
-
-    metadata = {
-        "name": "Test Agent",
-        "subHeading": "A test agent",
-        "categories": ["ai", "productivity"],
-        "customField": 123,
-    }
-
-    await embeddings.store_content_embedding(
-        content_type=ContentType.STORE_AGENT,
-        content_id=test_content_id,
-        embedding=mock_embedding,
-        searchable_text="test",
-        metadata=metadata,
-        user_id=None,
-    )
-
-    stored = await embeddings.get_content_embedding(
-        ContentType.STORE_AGENT, test_content_id, user_id=None
-    )
-
-    assert stored is not None
-    assert stored["metadata"]["name"] == "Test Agent"
-    assert stored["metadata"]["categories"] == ["ai", "productivity"]
-    assert stored["metadata"]["customField"] == 123
-
-
-# ============================================================================
-# delete_content_embedding Tests
-# ============================================================================
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_delete_content_embedding(
-    server,
-    test_content_id: str,
-    mock_embedding: list[float],
-):
-    """Test deleting embedding removes it from database."""
-    # Store embedding
-    await embeddings.store_content_embedding(
-        content_type=ContentType.BLOCK,
-        content_id=test_content_id,
-        embedding=mock_embedding,
-        searchable_text="To be deleted",
-        metadata=None,
-        user_id=None,
-    )
-
-    # Verify it exists
-    stored = await embeddings.get_content_embedding(
-        ContentType.BLOCK, test_content_id, user_id=None
-    )
-    assert stored is not None
-
-    # Delete it
-    result = await embeddings.delete_content_embedding(
-        ContentType.BLOCK, test_content_id, user_id=None
-    )
-    assert result is True
-
-    # Verify it's gone
-    stored = await embeddings.get_content_embedding(
-        ContentType.BLOCK, test_content_id, user_id=None
-    )
-    assert stored is None
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_delete_content_embedding_not_found(server):
-    """Test deleting non-existent embedding doesn't error."""
-    result = await embeddings.delete_content_embedding(
-        ContentType.BLOCK, "non-existent-id", user_id=None
-    )
-    # Should succeed even if nothing to delete
-    assert result is True
-
-
-# ============================================================================
-# unified_hybrid_search Tests
-# ============================================================================
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_unified_hybrid_search_finds_matching_content(
-    server,
-    mock_embedding: list[float],
-    cleanup_embeddings: list,
-):
-    """Test unified search finds content matching the query."""
-    # Create unique content IDs
-    agent_id = f"test-agent-{uuid.uuid4()}"
-    block_id = f"test-block-{uuid.uuid4()}"
-    doc_id = f"test-doc-{uuid.uuid4()}"
-
-    cleanup_embeddings.append((ContentType.STORE_AGENT, agent_id, None))
-    cleanup_embeddings.append((ContentType.BLOCK, block_id, None))
-    cleanup_embeddings.append((ContentType.DOCUMENTATION, doc_id, None))
-
-    # Store embeddings for different content types
-    await embeddings.store_content_embedding(
-        content_type=ContentType.STORE_AGENT,
-        content_id=agent_id,
-        embedding=mock_embedding,
-        searchable_text="AI writing assistant for blog posts",
-        metadata={"name": "Writing Assistant"},
-        user_id=None,
-    )
-
-    await embeddings.store_content_embedding(
-        content_type=ContentType.BLOCK,
-        content_id=block_id,
-        embedding=mock_embedding,
-        searchable_text="Text generation block for creative writing",
-        metadata={"name": "Text Generator"},
-        user_id=None,
-    )
-
-    await embeddings.store_content_embedding(
-        content_type=ContentType.DOCUMENTATION,
-        content_id=doc_id,
-        embedding=mock_embedding,
-        searchable_text="How to use writing blocks in AutoGPT",
-        metadata={"title": "Writing Guide"},
-        user_id=None,
-    )
-
-    # Search for "writing" - should find all three
-    results, total = await unified_hybrid_search(
-        query="writing",
-        page=1,
-        page_size=20,
-    )
-
-    # Should find at least our test content (may find others too)
-    content_ids = [r["content_id"] for r in results]
-    assert agent_id in content_ids or total >= 1  # Lexical search should find it
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_unified_hybrid_search_filter_by_content_type(
-    server,
-    mock_embedding: list[float],
-    cleanup_embeddings: list,
-):
-    """Test unified search can filter by content type."""
-    agent_id = f"test-agent-{uuid.uuid4()}"
-    block_id = f"test-block-{uuid.uuid4()}"
-
-    cleanup_embeddings.append((ContentType.STORE_AGENT, agent_id, None))
-    cleanup_embeddings.append((ContentType.BLOCK, block_id, None))
-
-    # Store both types with same searchable text
-    await embeddings.store_content_embedding(
-        content_type=ContentType.STORE_AGENT,
-        content_id=agent_id,
-        embedding=mock_embedding,
-        searchable_text="unique_search_term_xyz123",
-        metadata={},
-        user_id=None,
-    )
-
-    await embeddings.store_content_embedding(
-        content_type=ContentType.BLOCK,
-        content_id=block_id,
-        embedding=mock_embedding,
-        searchable_text="unique_search_term_xyz123",
-        metadata={},
-        user_id=None,
-    )
-
-    # Search only for BLOCK type
-    results, total = await unified_hybrid_search(
-        query="unique_search_term_xyz123",
-        content_types=[ContentType.BLOCK],
-        page=1,
-        page_size=20,
-    )
-
-    # All results should be BLOCK type
-    for r in results:
-        assert r["content_type"] == "BLOCK"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_unified_hybrid_search_empty_query(server):
-    """Test unified search with empty query returns empty results."""
-    results, total = await unified_hybrid_search(
-        query="",
-        page=1,
-        page_size=20,
-    )
-
-    assert results == []
-    assert total == 0
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_unified_hybrid_search_pagination(
-    server,
-    mock_embedding: list[float],
-    cleanup_embeddings: list,
-):
-    """Test unified search pagination works correctly."""
-    # Create multiple items
-    content_ids = []
-    for i in range(5):
-        content_id = f"test-pagination-{uuid.uuid4()}"
-        content_ids.append(content_id)
-        cleanup_embeddings.append((ContentType.BLOCK, content_id, None))
-
-        await embeddings.store_content_embedding(
-            content_type=ContentType.BLOCK,
-            content_id=content_id,
-            embedding=mock_embedding,
-            searchable_text=f"pagination test item number {i}",
-            metadata={"index": i},
-            user_id=None,
-        )
-
-    # Get first page
-    page1_results, total1 = await unified_hybrid_search(
-        query="pagination test",
-        content_types=[ContentType.BLOCK],
-        page=1,
-        page_size=2,
-    )
-
-    # Get second page
-    page2_results, total2 = await unified_hybrid_search(
-        query="pagination test",
-        content_types=[ContentType.BLOCK],
-        page=2,
-        page_size=2,
-    )
-
-    # Total should be consistent
-    assert total1 == total2
-
-    # Pages should have different content (if we have enough results)
-    if len(page1_results) > 0 and len(page2_results) > 0:
-        page1_ids = {r["content_id"] for r in page1_results}
-        page2_ids = {r["content_id"] for r in page2_results}
-        # No overlap between pages
-        assert page1_ids.isdisjoint(page2_ids)
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_unified_hybrid_search_min_score_filtering(
-    server,
-    mock_embedding: list[float],
-    cleanup_embeddings: list,
-):
-    """Test unified search respects min_score threshold."""
-    content_id = f"test-minscore-{uuid.uuid4()}"
-    cleanup_embeddings.append((ContentType.BLOCK, content_id, None))
-
-    await embeddings.store_content_embedding(
-        content_type=ContentType.BLOCK,
-        content_id=content_id,
-        embedding=mock_embedding,
-        searchable_text="completely unrelated content about bananas",
-        metadata={},
-        user_id=None,
-    )
-
-    # Search with very high min_score - should filter out low relevance
-    results_high, _ = await unified_hybrid_search(
-        query="quantum computing algorithms",
-        content_types=[ContentType.BLOCK],
-        min_score=0.9,  # Very high threshold
-        page=1,
-        page_size=20,
-    )
-
-    # Search with low min_score
-    results_low, _ = await unified_hybrid_search(
-        query="quantum computing algorithms",
-        content_types=[ContentType.BLOCK],
-        min_score=0.01,  # Very low threshold
-        page=1,
-        page_size=20,
-    )
-
-    # High threshold should have fewer or equal results
-    assert len(results_high) <= len(results_low)
-
-
-# ============================================================================
-# hybrid_search (Store Agents) Tests
-# ============================================================================
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_hybrid_search_store_agents_sql_valid(server):
-    """Test that hybrid_search SQL executes without errors."""
-    # This test verifies the SQL is syntactically correct
-    # even if no results are found
-    results, total = await hybrid_search(
-        query="test agent",
-        page=1,
-        page_size=20,
-    )
-
-    # Should not raise - verifies SQL is valid
-    assert isinstance(results, list)
-    assert isinstance(total, int)
-    assert total >= 0
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_hybrid_search_with_filters(server):
-    """Test hybrid_search with various filter options."""
-    # Test with all filter types
-    results, total = await hybrid_search(
-        query="productivity",
-        featured=True,
-        creators=["test-creator"],
-        category="productivity",
-        page=1,
-        page_size=10,
-    )
-
-    # Should not raise - verifies filter SQL is valid
-    assert isinstance(results, list)
-    assert isinstance(total, int)
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_hybrid_search_pagination(server):
-    """Test hybrid_search pagination."""
-    # Page 1
-    results1, total1 = await hybrid_search(
-        query="agent",
-        page=1,
-        page_size=5,
-    )
-
-    # Page 2
-    results2, total2 = await hybrid_search(
-        query="agent",
-        page=2,
-        page_size=5,
-    )
-
-    # Verify SQL executes without error
-    assert isinstance(results1, list)
-    assert isinstance(results2, list)
-    assert isinstance(total1, int)
-    assert isinstance(total2, int)
-
-    # If page 1 has results, total should be > 0
-    # Note: total from page 2 may be 0 if no results on that page (COUNT(*) OVER limitation)
-    if results1:
-        assert total1 > 0
-
-
-# ============================================================================
-# SQL Validity Tests (verify queries don't break)
-# ============================================================================
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_all_content_types_searchable(server):
-    """Test that all content types can be searched without SQL errors."""
-    for content_type in [
-        ContentType.STORE_AGENT,
-        ContentType.BLOCK,
-        ContentType.DOCUMENTATION,
-    ]:
-        results, total = await unified_hybrid_search(
-            query="test",
-            content_types=[content_type],
-            page=1,
-            page_size=10,
-        )
-
-        # Should not raise
-        assert isinstance(results, list)
-        assert isinstance(total, int)
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_multiple_content_types_searchable(server):
-    """Test searching multiple content types at once."""
-    results, total = await unified_hybrid_search(
-        query="test",
-        content_types=[ContentType.BLOCK, ContentType.DOCUMENTATION],
-        page=1,
-        page_size=20,
-    )
-
-    # Should not raise
-    assert isinstance(results, list)
-    assert isinstance(total, int)
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_search_all_content_types_default(server):
-    """Test searching all content types (default behavior)."""
-    results, total = await unified_hybrid_search(
-        query="test",
-        content_types=None,  # Should search all
-        page=1,
-        page_size=20,
-    )
-
-    # Should not raise
-    assert isinstance(results, list)
-    assert isinstance(total, int)
-
-
-if __name__ == "__main__":
-    pytest.main([__file__, "-v", "-s"])

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

@@ -1,315 +0,0 @@
-"""
-Integration tests for embeddings with schema handling.
-
-These tests verify that embeddings operations work correctly across different database schemas.
-"""
-
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-from prisma.enums import ContentType
-
-from backend.api.features.store import embeddings
-from backend.api.features.store.embeddings import EMBEDDING_DIM
-
-# Schema prefix tests removed - functionality moved to db.raw_with_schema() helper
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_store_content_embedding_with_schema():
-    """Test storing embeddings with proper schema handling."""
-    with patch("backend.data.db.get_database_schema") as mock_schema:
-        mock_schema.return_value = "platform"
-
-        with patch("prisma.get_client") as mock_get_client:
-            mock_client = AsyncMock()
-            mock_get_client.return_value = mock_client
-
-            result = await embeddings.store_content_embedding(
-                content_type=ContentType.STORE_AGENT,
-                content_id="test-id",
-                embedding=[0.1] * EMBEDDING_DIM,
-                searchable_text="test text",
-                metadata={"test": "data"},
-                user_id=None,
-            )
-
-            # Verify the query was called
-            assert mock_client.execute_raw.called
-
-            # Get the SQL query that was executed
-            call_args = mock_client.execute_raw.call_args
-            sql_query = call_args[0][0]
-
-            # Verify schema prefix is in the query
-            assert '"platform"."UnifiedContentEmbedding"' in sql_query
-
-            # Verify result
-            assert result is True
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_get_content_embedding_with_schema():
-    """Test retrieving embeddings with proper schema handling."""
-    with patch("backend.data.db.get_database_schema") as mock_schema:
-        mock_schema.return_value = "platform"
-
-        with patch("prisma.get_client") as mock_get_client:
-            mock_client = AsyncMock()
-            mock_client.query_raw.return_value = [
-                {
-                    "contentType": "STORE_AGENT",
-                    "contentId": "test-id",
-                    "userId": None,
-                    "embedding": "[0.1, 0.2]",
-                    "searchableText": "test",
-                    "metadata": {},
-                    "createdAt": "2024-01-01",
-                    "updatedAt": "2024-01-01",
-                }
-            ]
-            mock_get_client.return_value = mock_client
-
-            result = await embeddings.get_content_embedding(
-                ContentType.STORE_AGENT,
-                "test-id",
-                user_id=None,
-            )
-
-            # Verify the query was called
-            assert mock_client.query_raw.called
-
-            # Get the SQL query that was executed
-            call_args = mock_client.query_raw.call_args
-            sql_query = call_args[0][0]
-
-            # Verify schema prefix is in the query
-            assert '"platform"."UnifiedContentEmbedding"' in sql_query
-
-            # Verify result
-            assert result is not None
-            assert result["contentId"] == "test-id"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_delete_content_embedding_with_schema():
-    """Test deleting embeddings with proper schema handling."""
-    with patch("backend.data.db.get_database_schema") as mock_schema:
-        mock_schema.return_value = "platform"
-
-        with patch("prisma.get_client") as mock_get_client:
-            mock_client = AsyncMock()
-            mock_get_client.return_value = mock_client
-
-            result = await embeddings.delete_content_embedding(
-                ContentType.STORE_AGENT,
-                "test-id",
-            )
-
-            # Verify the query was called
-            assert mock_client.execute_raw.called
-
-            # Get the SQL query that was executed
-            call_args = mock_client.execute_raw.call_args
-            sql_query = call_args[0][0]
-
-            # Verify schema prefix is in the query
-            assert '"platform"."UnifiedContentEmbedding"' in sql_query
-
-            # Verify result
-            assert result is True
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_get_embedding_stats_with_schema():
-    """Test embedding statistics with proper schema handling via content handlers."""
-    # Mock handler to return stats
-    mock_handler = MagicMock()
-    mock_handler.get_stats = AsyncMock(
-        return_value={
-            "total": 100,
-            "with_embeddings": 80,
-            "without_embeddings": 20,
-        }
-    )
-
-    with patch(
-        "backend.api.features.store.embeddings.CONTENT_HANDLERS",
-        {ContentType.STORE_AGENT: mock_handler},
-    ):
-        result = await embeddings.get_embedding_stats()
-
-        # Verify handler was called
-        mock_handler.get_stats.assert_called_once()
-
-        # Verify new result structure
-        assert "by_type" in result
-        assert "totals" in result
-        assert result["totals"]["total"] == 100
-        assert result["totals"]["with_embeddings"] == 80
-        assert result["totals"]["without_embeddings"] == 20
-        assert result["totals"]["coverage_percent"] == 80.0
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_backfill_missing_embeddings_with_schema():
-    """Test backfilling embeddings via content handlers."""
-    from backend.api.features.store.content_handlers import ContentItem
-
-    # Create mock content item
-    mock_item = ContentItem(
-        content_id="version-1",
-        content_type=ContentType.STORE_AGENT,
-        searchable_text="Test Agent Test description",
-        metadata={"name": "Test Agent"},
-    )
-
-    # Mock handler
-    mock_handler = MagicMock()
-    mock_handler.get_missing_items = AsyncMock(return_value=[mock_item])
-
-    with patch(
-        "backend.api.features.store.embeddings.CONTENT_HANDLERS",
-        {ContentType.STORE_AGENT: mock_handler},
-    ):
-        with patch(
-            "backend.api.features.store.embeddings.generate_embedding",
-            return_value=[0.1] * EMBEDDING_DIM,
-        ):
-            with patch(
-                "backend.api.features.store.embeddings.store_content_embedding",
-                return_value=True,
-            ):
-                result = await embeddings.backfill_missing_embeddings(batch_size=10)
-
-                # Verify handler was called
-                mock_handler.get_missing_items.assert_called_once_with(10)
-
-                # Verify results
-                assert result["processed"] == 1
-                assert result["success"] == 1
-                assert result["failed"] == 0
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_ensure_content_embedding_with_schema():
-    """Test ensuring embeddings exist with proper schema handling."""
-    with patch("backend.data.db.get_database_schema") as mock_schema:
-        mock_schema.return_value = "platform"
-
-        with patch(
-            "backend.api.features.store.embeddings.get_content_embedding"
-        ) as mock_get:
-            # Simulate no existing embedding
-            mock_get.return_value = None
-
-            with patch(
-                "backend.api.features.store.embeddings.generate_embedding"
-            ) as mock_generate:
-                mock_generate.return_value = [0.1] * EMBEDDING_DIM
-
-                with patch(
-                    "backend.api.features.store.embeddings.store_content_embedding"
-                ) as mock_store:
-                    mock_store.return_value = True
-
-                    result = await embeddings.ensure_content_embedding(
-                        content_type=ContentType.STORE_AGENT,
-                        content_id="test-id",
-                        searchable_text="test text",
-                        metadata={"test": "data"},
-                        user_id=None,
-                        force=False,
-                    )
-
-                    # Verify the flow
-                    assert mock_get.called
-                    assert mock_generate.called
-                    assert mock_store.called
-                    assert result is True
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_backward_compatibility_store_embedding():
-    """Test backward compatibility wrapper for store_embedding."""
-    with patch(
-        "backend.api.features.store.embeddings.store_content_embedding"
-    ) as mock_store:
-        mock_store.return_value = True
-
-        result = await embeddings.store_embedding(
-            version_id="test-version-id",
-            embedding=[0.1] * EMBEDDING_DIM,
-            tx=None,
-        )
-
-        # Verify it calls the new function with correct parameters
-        assert mock_store.called
-        call_args = mock_store.call_args
-
-        assert call_args[1]["content_type"] == ContentType.STORE_AGENT
-        assert call_args[1]["content_id"] == "test-version-id"
-        assert call_args[1]["user_id"] is None
-        assert result is True
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_backward_compatibility_get_embedding():
-    """Test backward compatibility wrapper for get_embedding."""
-    with patch(
-        "backend.api.features.store.embeddings.get_content_embedding"
-    ) as mock_get:
-        mock_get.return_value = {
-            "contentType": "STORE_AGENT",
-            "contentId": "test-version-id",
-            "embedding": "[0.1, 0.2]",
-            "createdAt": "2024-01-01",
-            "updatedAt": "2024-01-01",
-        }
-
-        result = await embeddings.get_embedding("test-version-id")
-
-        # Verify it calls the new function
-        assert mock_get.called
-
-        # Verify it transforms to old format
-        assert result is not None
-        assert result["storeListingVersionId"] == "test-version-id"
-        assert "embedding" in result
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_schema_handling_error_cases():
-    """Test error handling in schema-aware operations."""
-    with patch("backend.data.db.get_database_schema") as mock_schema:
-        mock_schema.return_value = "platform"
-
-        with patch("prisma.get_client") as mock_get_client:
-            mock_client = AsyncMock()
-            mock_client.execute_raw.side_effect = Exception("Database error")
-            mock_get_client.return_value = mock_client
-
-            result = await embeddings.store_content_embedding(
-                content_type=ContentType.STORE_AGENT,
-                content_id="test-id",
-                embedding=[0.1] * EMBEDDING_DIM,
-                searchable_text="test",
-                metadata=None,
-                user_id=None,
-            )
-
-            # Should return False on error, not raise
-            assert result is False
-
-
-if __name__ == "__main__":
-    pytest.main([__file__, "-v", "-s"])

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

@@ -1,407 +0,0 @@
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import prisma
-import pytest
-from prisma import Prisma
-from prisma.enums import ContentType
-
-from backend.api.features.store import embeddings
-
-
-@pytest.fixture(autouse=True)
-async def setup_prisma():
-    """Setup Prisma client for tests."""
-    try:
-        Prisma()
-    except prisma.errors.ClientAlreadyRegisteredError:
-        pass
-    yield
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_build_searchable_text():
-    """Test searchable text building from listing fields."""
-    result = embeddings.build_searchable_text(
-        name="AI Assistant",
-        description="A helpful AI assistant for productivity",
-        sub_heading="Boost your productivity",
-        categories=["AI", "Productivity"],
-    )
-
-    expected = "AI Assistant Boost your productivity A helpful AI assistant for productivity AI Productivity"
-    assert result == expected
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_build_searchable_text_empty_fields():
-    """Test searchable text building with empty fields."""
-    result = embeddings.build_searchable_text(
-        name="", description="Test description", sub_heading="", categories=[]
-    )
-
-    assert result == "Test description"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_generate_embedding_success():
-    """Test successful embedding generation."""
-    # Mock OpenAI response
-    mock_client = MagicMock()
-    mock_response = MagicMock()
-    mock_response.data = [MagicMock()]
-    mock_response.data[0].embedding = [0.1, 0.2, 0.3] * 512  # 1536 dimensions
-
-    # Use AsyncMock for async embeddings.create method
-    mock_client.embeddings.create = AsyncMock(return_value=mock_response)
-
-    # Patch at the point of use in embeddings.py
-    with patch(
-        "backend.api.features.store.embeddings.get_openai_client"
-    ) as mock_get_client:
-        mock_get_client.return_value = mock_client
-
-        result = await embeddings.generate_embedding("test text")
-
-        assert result is not None
-        assert len(result) == embeddings.EMBEDDING_DIM
-        assert result[0] == 0.1
-
-        mock_client.embeddings.create.assert_called_once_with(
-            model="text-embedding-3-small", input="test text"
-        )
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_generate_embedding_no_api_key():
-    """Test embedding generation without API key."""
-    # Patch at the point of use in embeddings.py
-    with patch(
-        "backend.api.features.store.embeddings.get_openai_client"
-    ) as mock_get_client:
-        mock_get_client.return_value = None
-
-        result = await embeddings.generate_embedding("test text")
-
-        assert result is None
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_generate_embedding_api_error():
-    """Test embedding generation with API error."""
-    mock_client = MagicMock()
-    mock_client.embeddings.create = AsyncMock(side_effect=Exception("API Error"))
-
-    # Patch at the point of use in embeddings.py
-    with patch(
-        "backend.api.features.store.embeddings.get_openai_client"
-    ) as mock_get_client:
-        mock_get_client.return_value = mock_client
-
-        result = await embeddings.generate_embedding("test text")
-
-        assert result is None
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_generate_embedding_text_truncation():
-    """Test that long text is properly truncated using tiktoken."""
-    from tiktoken import encoding_for_model
-
-    mock_client = MagicMock()
-    mock_response = MagicMock()
-    mock_response.data = [MagicMock()]
-    mock_response.data[0].embedding = [0.1] * embeddings.EMBEDDING_DIM
-
-    # Use AsyncMock for async embeddings.create method
-    mock_client.embeddings.create = AsyncMock(return_value=mock_response)
-
-    # Patch at the point of use in embeddings.py
-    with patch(
-        "backend.api.features.store.embeddings.get_openai_client"
-    ) as mock_get_client:
-        mock_get_client.return_value = mock_client
-
-        # Create text that will exceed 8191 tokens
-        # Use varied characters to ensure token-heavy text: each word is ~1 token
-        words = [f"word{i}" for i in range(10000)]
-        long_text = " ".join(words)  # ~10000 tokens
-
-        await embeddings.generate_embedding(long_text)
-
-        # Verify text was truncated to 8191 tokens
-        call_args = mock_client.embeddings.create.call_args
-        truncated_text = call_args.kwargs["input"]
-
-        # Count actual tokens in truncated text
-        enc = encoding_for_model("text-embedding-3-small")
-        actual_tokens = len(enc.encode(truncated_text))
-
-        # Should be at or just under 8191 tokens
-        assert actual_tokens <= 8191
-        # Should be close to the limit (not over-truncated)
-        assert actual_tokens >= 8100
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_store_embedding_success(mocker):
-    """Test successful embedding storage."""
-    mock_client = mocker.AsyncMock()
-    mock_client.execute_raw = mocker.AsyncMock()
-
-    embedding = [0.1, 0.2, 0.3]
-
-    result = await embeddings.store_embedding(
-        version_id="test-version-id", embedding=embedding, tx=mock_client
-    )
-
-    assert result is True
-    # execute_raw is called twice: once for SET search_path, once for INSERT
-    assert mock_client.execute_raw.call_count == 2
-
-    # First call: SET search_path
-    first_call_args = mock_client.execute_raw.call_args_list[0][0]
-    assert "SET search_path" in first_call_args[0]
-
-    # Second call: INSERT query with the actual data
-    second_call_args = mock_client.execute_raw.call_args_list[1][0]
-    assert "test-version-id" in second_call_args
-    assert "[0.1,0.2,0.3]" in second_call_args
-    assert None in second_call_args  # userId should be None for store agents
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_store_embedding_database_error(mocker):
-    """Test embedding storage with database error."""
-    mock_client = mocker.AsyncMock()
-    mock_client.execute_raw.side_effect = Exception("Database error")
-
-    embedding = [0.1, 0.2, 0.3]
-
-    result = await embeddings.store_embedding(
-        version_id="test-version-id", embedding=embedding, tx=mock_client
-    )
-
-    assert result is False
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_get_embedding_success():
-    """Test successful embedding retrieval."""
-    mock_result = [
-        {
-            "contentType": "STORE_AGENT",
-            "contentId": "test-version-id",
-            "userId": None,
-            "embedding": "[0.1,0.2,0.3]",
-            "searchableText": "Test text",
-            "metadata": {},
-            "createdAt": "2024-01-01T00:00:00Z",
-            "updatedAt": "2024-01-01T00:00:00Z",
-        }
-    ]
-
-    with patch(
-        "backend.api.features.store.embeddings.query_raw_with_schema",
-        return_value=mock_result,
-    ):
-        result = await embeddings.get_embedding("test-version-id")
-
-        assert result is not None
-        assert result["storeListingVersionId"] == "test-version-id"
-        assert result["embedding"] == "[0.1,0.2,0.3]"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_get_embedding_not_found():
-    """Test embedding retrieval when not found."""
-    with patch(
-        "backend.api.features.store.embeddings.query_raw_with_schema",
-        return_value=[],
-    ):
-        result = await embeddings.get_embedding("test-version-id")
-
-        assert result is None
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@patch("backend.api.features.store.embeddings.generate_embedding")
-@patch("backend.api.features.store.embeddings.store_embedding")
-@patch("backend.api.features.store.embeddings.get_embedding")
-async def test_ensure_embedding_already_exists(mock_get, mock_store, mock_generate):
-    """Test ensure_embedding when embedding already exists."""
-    mock_get.return_value = {"embedding": "[0.1,0.2,0.3]"}
-
-    result = await embeddings.ensure_embedding(
-        version_id="test-id",
-        name="Test",
-        description="Test description",
-        sub_heading="Test heading",
-        categories=["test"],
-    )
-
-    assert result is True
-    mock_generate.assert_not_called()
-    mock_store.assert_not_called()
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@patch("backend.api.features.store.embeddings.generate_embedding")
-@patch("backend.api.features.store.embeddings.store_content_embedding")
-@patch("backend.api.features.store.embeddings.get_embedding")
-async def test_ensure_embedding_create_new(mock_get, mock_store, mock_generate):
-    """Test ensure_embedding creating new embedding."""
-    mock_get.return_value = None
-    mock_generate.return_value = [0.1, 0.2, 0.3]
-    mock_store.return_value = True
-
-    result = await embeddings.ensure_embedding(
-        version_id="test-id",
-        name="Test",
-        description="Test description",
-        sub_heading="Test heading",
-        categories=["test"],
-    )
-
-    assert result is True
-    mock_generate.assert_called_once_with("Test Test heading Test description test")
-    mock_store.assert_called_once_with(
-        content_type=ContentType.STORE_AGENT,
-        content_id="test-id",
-        embedding=[0.1, 0.2, 0.3],
-        searchable_text="Test Test heading Test description test",
-        metadata={"name": "Test", "subHeading": "Test heading", "categories": ["test"]},
-        user_id=None,
-        tx=None,
-    )
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@patch("backend.api.features.store.embeddings.generate_embedding")
-@patch("backend.api.features.store.embeddings.get_embedding")
-async def test_ensure_embedding_generation_fails(mock_get, mock_generate):
-    """Test ensure_embedding when generation fails."""
-    mock_get.return_value = None
-    mock_generate.return_value = None
-
-    result = await embeddings.ensure_embedding(
-        version_id="test-id",
-        name="Test",
-        description="Test description",
-        sub_heading="Test heading",
-        categories=["test"],
-    )
-
-    assert result is False
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_get_embedding_stats():
-    """Test embedding statistics retrieval."""
-    # Mock handler stats for each content type
-    mock_handler = MagicMock()
-    mock_handler.get_stats = AsyncMock(
-        return_value={
-            "total": 100,
-            "with_embeddings": 75,
-            "without_embeddings": 25,
-        }
-    )
-
-    # Patch the CONTENT_HANDLERS where it's used (in embeddings module)
-    with patch(
-        "backend.api.features.store.embeddings.CONTENT_HANDLERS",
-        {ContentType.STORE_AGENT: mock_handler},
-    ):
-        result = await embeddings.get_embedding_stats()
-
-        assert "by_type" in result
-        assert "totals" in result
-        assert result["totals"]["total"] == 100
-        assert result["totals"]["with_embeddings"] == 75
-        assert result["totals"]["without_embeddings"] == 25
-        assert result["totals"]["coverage_percent"] == 75.0
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@patch("backend.api.features.store.embeddings.store_content_embedding")
-async def test_backfill_missing_embeddings_success(mock_store):
-    """Test backfill with successful embedding generation."""
-    # Mock ContentItem from handlers
-    from backend.api.features.store.content_handlers import ContentItem
-
-    mock_items = [
-        ContentItem(
-            content_id="version-1",
-            content_type=ContentType.STORE_AGENT,
-            searchable_text="Agent 1 Description 1",
-            metadata={"name": "Agent 1"},
-        ),
-        ContentItem(
-            content_id="version-2",
-            content_type=ContentType.STORE_AGENT,
-            searchable_text="Agent 2 Description 2",
-            metadata={"name": "Agent 2"},
-        ),
-    ]
-
-    # Mock handler to return missing items
-    mock_handler = MagicMock()
-    mock_handler.get_missing_items = AsyncMock(return_value=mock_items)
-
-    # Mock store_content_embedding to succeed for first, fail for second
-    mock_store.side_effect = [True, False]
-
-    with patch(
-        "backend.api.features.store.embeddings.CONTENT_HANDLERS",
-        {ContentType.STORE_AGENT: mock_handler},
-    ):
-        with patch(
-            "backend.api.features.store.embeddings.generate_embedding",
-            return_value=[0.1] * embeddings.EMBEDDING_DIM,
-        ):
-            result = await embeddings.backfill_missing_embeddings(batch_size=5)
-
-            assert result["processed"] == 2
-            assert result["success"] == 1
-            assert result["failed"] == 1
-            assert mock_store.call_count == 2
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_backfill_missing_embeddings_no_missing():
-    """Test backfill when no embeddings are missing."""
-    # Mock handler to return no missing items
-    mock_handler = MagicMock()
-    mock_handler.get_missing_items = AsyncMock(return_value=[])
-
-    with patch(
-        "backend.api.features.store.embeddings.CONTENT_HANDLERS",
-        {ContentType.STORE_AGENT: mock_handler},
-    ):
-        result = await embeddings.backfill_missing_embeddings(batch_size=5)
-
-        assert result["processed"] == 0
-        assert result["success"] == 0
-        assert result["failed"] == 0
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_embedding_to_vector_string():
-    """Test embedding to PostgreSQL vector string conversion."""
-    embedding = [0.1, 0.2, 0.3, -0.4]
-    result = embeddings.embedding_to_vector_string(embedding)
-    assert result == "[0.1,0.2,0.3,-0.4]"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-async def test_embed_query():
-    """Test embed_query function (alias for generate_embedding)."""
-    with patch(
-        "backend.api.features.store.embeddings.generate_embedding"
-    ) as mock_generate:
-        mock_generate.return_value = [0.1, 0.2, 0.3]
-
-        result = await embeddings.embed_query("test query")
-
-        assert result == [0.1, 0.2, 0.3]
-        mock_generate.assert_called_once_with("test query")

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

@@ -1,625 +0,0 @@
-"""
-Unified Hybrid Search
-
-Combines semantic (embedding) search with lexical (tsvector) search
-for improved relevance across all content types (agents, blocks, docs).
-"""
-
-import logging
-from dataclasses import dataclass
-from typing import Any, Literal
-
-from prisma.enums import ContentType
-
-from backend.api.features.store.embeddings import (
-    EMBEDDING_DIM,
-    embed_query,
-    embedding_to_vector_string,
-)
-from backend.data.db import query_raw_with_schema
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class UnifiedSearchWeights:
-    """Weights for unified search (no popularity signal)."""
-
-    semantic: float = 0.40  # Embedding cosine similarity
-    lexical: float = 0.40  # tsvector ts_rank_cd score
-    category: float = 0.10  # Category match boost (for types that have categories)
-    recency: float = 0.10  # Newer content ranked higher
-
-    def __post_init__(self):
-        """Validate weights are non-negative and sum to approximately 1.0."""
-        total = self.semantic + self.lexical + self.category + self.recency
-
-        if any(
-            w < 0 for w in [self.semantic, self.lexical, self.category, self.recency]
-        ):
-            raise ValueError("All weights must be non-negative")
-
-        if not (0.99 <= total <= 1.01):
-            raise ValueError(f"Weights must sum to ~1.0, got {total:.3f}")
-
-
-# Default weights for unified search
-DEFAULT_UNIFIED_WEIGHTS = UnifiedSearchWeights()
-
-# Minimum relevance score thresholds
-DEFAULT_MIN_SCORE = 0.15  # For unified search (more permissive)
-DEFAULT_STORE_AGENT_MIN_SCORE = 0.20  # For store agent search (original threshold)
-
-
-async def unified_hybrid_search(
-    query: str,
-    content_types: list[ContentType] | None = None,
-    category: str | None = None,
-    page: int = 1,
-    page_size: int = 20,
-    weights: UnifiedSearchWeights | None = None,
-    min_score: float | None = None,
-    user_id: str | None = None,
-) -> tuple[list[dict[str, Any]], int]:
-    """
-    Unified hybrid search across all content types.
-
-    Searches UnifiedContentEmbedding using both semantic (vector) and lexical (tsvector) signals.
-
-    Args:
-        query: Search query string
-        content_types: List of content types to search. Defaults to all public types.
-        category: Filter by category (for content types that support it)
-        page: Page number (1-indexed)
-        page_size: Results per page
-        weights: Custom weights for search signals
-        min_score: Minimum relevance score threshold (0-1)
-        user_id: User ID for searching private content (library agents)
-
-    Returns:
-        Tuple of (results list, total count)
-    """
-    # Validate inputs
-    query = query.strip()
-    if not query:
-        return [], 0
-
-    if page < 1:
-        page = 1
-    if page_size < 1:
-        page_size = 1
-    if page_size > 100:
-        page_size = 100
-
-    if content_types is None:
-        content_types = [
-            ContentType.STORE_AGENT,
-            ContentType.BLOCK,
-            ContentType.DOCUMENTATION,
-        ]
-
-    if weights is None:
-        weights = DEFAULT_UNIFIED_WEIGHTS
-    if min_score is None:
-        min_score = DEFAULT_MIN_SCORE
-
-    offset = (page - 1) * page_size
-
-    # Generate query embedding
-    query_embedding = await embed_query(query)
-
-    # Graceful degradation if embedding unavailable
-    if query_embedding is None or not query_embedding:
-        logger.warning(
-            "Failed to generate query embedding - falling back to lexical-only search. "
-            "Check that openai_internal_api_key is configured and OpenAI API is accessible."
-        )
-        query_embedding = [0.0] * EMBEDDING_DIM
-        # Redistribute semantic weight to lexical
-        total_non_semantic = weights.lexical + weights.category + weights.recency
-        if total_non_semantic > 0:
-            factor = 1.0 / total_non_semantic
-            weights = UnifiedSearchWeights(
-                semantic=0.0,
-                lexical=weights.lexical * factor,
-                category=weights.category * factor,
-                recency=weights.recency * factor,
-            )
-        else:
-            weights = UnifiedSearchWeights(
-                semantic=0.0, lexical=1.0, category=0.0, recency=0.0
-            )
-
-    # Build parameters
-    params: list[Any] = []
-    param_idx = 1
-
-    # Query for lexical search
-    params.append(query)
-    query_param = f"${param_idx}"
-    param_idx += 1
-
-    # Query lowercase for category matching
-    params.append(query.lower())
-    query_lower_param = f"${param_idx}"
-    param_idx += 1
-
-    # Embedding
-    embedding_str = embedding_to_vector_string(query_embedding)
-    params.append(embedding_str)
-    embedding_param = f"${param_idx}"
-    param_idx += 1
-
-    # Content types
-    content_type_values = [ct.value for ct in content_types]
-    params.append(content_type_values)
-    content_types_param = f"${param_idx}"
-    param_idx += 1
-
-    # User ID filter (for private content)
-    user_filter = ""
-    if user_id is not None:
-        params.append(user_id)
-        user_filter = f'AND (uce."userId" = ${param_idx} OR uce."userId" IS NULL)'
-        param_idx += 1
-    else:
-        user_filter = 'AND uce."userId" IS NULL'
-
-    # Weights
-    params.append(weights.semantic)
-    w_semantic = f"${param_idx}"
-    param_idx += 1
-
-    params.append(weights.lexical)
-    w_lexical = f"${param_idx}"
-    param_idx += 1
-
-    params.append(weights.category)
-    w_category = f"${param_idx}"
-    param_idx += 1
-
-    params.append(weights.recency)
-    w_recency = f"${param_idx}"
-    param_idx += 1
-
-    # Min score
-    params.append(min_score)
-    min_score_param = f"${param_idx}"
-    param_idx += 1
-
-    # Pagination
-    params.append(page_size)
-    limit_param = f"${param_idx}"
-    param_idx += 1
-
-    params.append(offset)
-    offset_param = f"${param_idx}"
-    param_idx += 1
-
-    # Unified search query on UnifiedContentEmbedding
-    sql_query = f"""
-        WITH candidates AS (
-            -- Lexical matches (uses GIN index on search column)
-            SELECT uce.id, uce."contentType", uce."contentId"
-            FROM {{schema_prefix}}"UnifiedContentEmbedding" uce
-            WHERE uce."contentType" = ANY({content_types_param}::{{schema_prefix}}"ContentType"[])
-            {user_filter}
-            AND uce.search @@ plainto_tsquery('english', {query_param})
-
-            UNION
-
-            -- Semantic matches (uses HNSW index on embedding)
-            (
-                SELECT uce.id, uce."contentType", uce."contentId"
-                FROM {{schema_prefix}}"UnifiedContentEmbedding" uce
-                WHERE uce."contentType" = ANY({content_types_param}::{{schema_prefix}}"ContentType"[])
-                {user_filter}
-                ORDER BY uce.embedding <=> {embedding_param}::vector
-                LIMIT 200
-            )
-        ),
-        search_scores AS (
-            SELECT
-                uce."contentType" as content_type,
-                uce."contentId" as content_id,
-                uce."searchableText" as searchable_text,
-                uce.metadata,
-                uce."updatedAt" as updated_at,
-                -- Semantic score: cosine similarity (1 - distance)
-                COALESCE(1 - (uce.embedding <=> {embedding_param}::vector), 0) as semantic_score,
-                -- Lexical score: ts_rank_cd
-                COALESCE(ts_rank_cd(uce.search, plainto_tsquery('english', {query_param})), 0) as lexical_raw,
-                -- Category match from metadata
-                CASE
-                    WHEN uce.metadata ? 'categories' AND EXISTS (
-                        SELECT 1 FROM jsonb_array_elements_text(uce.metadata->'categories') cat
-                        WHERE LOWER(cat) LIKE '%' || {query_lower_param} || '%'
-                    )
-                    THEN 1.0
-                    ELSE 0.0
-                END as category_score,
-                -- Recency score: linear decay over 90 days
-                GREATEST(0, 1 - EXTRACT(EPOCH FROM (NOW() - uce."updatedAt")) / (90 * 24 * 3600)) as recency_score
-            FROM candidates c
-            INNER JOIN {{schema_prefix}}"UnifiedContentEmbedding" uce ON c.id = uce.id
-        ),
-        max_lexical AS (
-            SELECT GREATEST(MAX(lexical_raw), 0.001) as max_val FROM search_scores
-        ),
-        normalized AS (
-            SELECT
-                ss.*,
-                ss.lexical_raw / ml.max_val as lexical_score
-            FROM search_scores ss
-            CROSS JOIN max_lexical ml
-        ),
-        scored AS (
-            SELECT
-                content_type,
-                content_id,
-                searchable_text,
-                metadata,
-                updated_at,
-                semantic_score,
-                lexical_score,
-                category_score,
-                recency_score,
-                (
-                    {w_semantic} * semantic_score +
-                    {w_lexical} * lexical_score +
-                    {w_category} * category_score +
-                    {w_recency} * recency_score
-                ) as combined_score
-            FROM normalized
-        ),
-        filtered AS (
-            SELECT
-                *,
-                COUNT(*) OVER () as total_count
-            FROM scored
-            WHERE combined_score >= {min_score_param}
-        )
-        SELECT * FROM filtered
-        ORDER BY combined_score DESC
-        LIMIT {limit_param} OFFSET {offset_param}
-    """
-
-    results = await query_raw_with_schema(
-        sql_query, *params, set_public_search_path=True
-    )
-
-    total = results[0]["total_count"] if results else 0
-
-    # Clean up results
-    for result in results:
-        result.pop("total_count", None)
-
-    logger.info(f"Unified hybrid search: {len(results)} results, {total} total")
-
-    return results, total
-
-
-# ============================================================================
-# Store Agent specific search (with full metadata)
-# ============================================================================
-
-
-@dataclass
-class StoreAgentSearchWeights:
-    """Weights for store agent search including popularity."""
-
-    semantic: float = 0.30
-    lexical: float = 0.30
-    category: float = 0.20
-    recency: float = 0.10
-    popularity: float = 0.10
-
-    def __post_init__(self):
-        total = (
-            self.semantic
-            + self.lexical
-            + self.category
-            + self.recency
-            + self.popularity
-        )
-        if any(
-            w < 0
-            for w in [
-                self.semantic,
-                self.lexical,
-                self.category,
-                self.recency,
-                self.popularity,
-            ]
-        ):
-            raise ValueError("All weights must be non-negative")
-        if not (0.99 <= total <= 1.01):
-            raise ValueError(f"Weights must sum to ~1.0, got {total:.3f}")
-
-
-DEFAULT_STORE_AGENT_WEIGHTS = StoreAgentSearchWeights()
-
-
-async def hybrid_search(
-    query: str,
-    featured: bool = False,
-    creators: list[str] | None = None,
-    category: str | None = None,
-    sorted_by: (
-        Literal["relevance", "rating", "runs", "name", "updated_at"] | None
-    ) = None,
-    page: int = 1,
-    page_size: int = 20,
-    weights: StoreAgentSearchWeights | None = None,
-    min_score: float | None = None,
-) -> tuple[list[dict[str, Any]], int]:
-    """
-    Hybrid search for store agents with full metadata.
-
-    Uses UnifiedContentEmbedding for search, joins to StoreAgent for metadata.
-    """
-    query = query.strip()
-    if not query:
-        return [], 0
-
-    if page < 1:
-        page = 1
-    if page_size < 1:
-        page_size = 1
-    if page_size > 100:
-        page_size = 100
-
-    if weights is None:
-        weights = DEFAULT_STORE_AGENT_WEIGHTS
-    if min_score is None:
-        min_score = (
-            DEFAULT_STORE_AGENT_MIN_SCORE  # Use original threshold for store agents
-        )
-
-    offset = (page - 1) * page_size
-
-    # Generate query embedding
-    query_embedding = await embed_query(query)
-
-    # Graceful degradation
-    if query_embedding is None or not query_embedding:
-        logger.warning(
-            "Failed to generate query embedding - falling back to lexical-only search."
-        )
-        query_embedding = [0.0] * EMBEDDING_DIM
-        total_non_semantic = (
-            weights.lexical + weights.category + weights.recency + weights.popularity
-        )
-        if total_non_semantic > 0:
-            factor = 1.0 / total_non_semantic
-            weights = StoreAgentSearchWeights(
-                semantic=0.0,
-                lexical=weights.lexical * factor,
-                category=weights.category * factor,
-                recency=weights.recency * factor,
-                popularity=weights.popularity * factor,
-            )
-        else:
-            weights = StoreAgentSearchWeights(
-                semantic=0.0, lexical=1.0, category=0.0, recency=0.0, popularity=0.0
-            )
-
-    # Build parameters
-    params: list[Any] = []
-    param_idx = 1
-
-    params.append(query)
-    query_param = f"${param_idx}"
-    param_idx += 1
-
-    params.append(query.lower())
-    query_lower_param = f"${param_idx}"
-    param_idx += 1
-
-    embedding_str = embedding_to_vector_string(query_embedding)
-    params.append(embedding_str)
-    embedding_param = f"${param_idx}"
-    param_idx += 1
-
-    # Build WHERE clause for StoreAgent filters
-    where_parts = ["sa.is_available = true"]
-
-    if featured:
-        where_parts.append("sa.featured = true")
-
-    if creators:
-        params.append(creators)
-        where_parts.append(f"sa.creator_username = ANY(${param_idx})")
-        param_idx += 1
-
-    if category:
-        params.append(category)
-        where_parts.append(f"${param_idx} = ANY(sa.categories)")
-        param_idx += 1
-
-    where_clause = " AND ".join(where_parts)
-
-    # Weights
-    params.append(weights.semantic)
-    w_semantic = f"${param_idx}"
-    param_idx += 1
-
-    params.append(weights.lexical)
-    w_lexical = f"${param_idx}"
-    param_idx += 1
-
-    params.append(weights.category)
-    w_category = f"${param_idx}"
-    param_idx += 1
-
-    params.append(weights.recency)
-    w_recency = f"${param_idx}"
-    param_idx += 1
-
-    params.append(weights.popularity)
-    w_popularity = f"${param_idx}"
-    param_idx += 1
-
-    params.append(min_score)
-    min_score_param = f"${param_idx}"
-    param_idx += 1
-
-    params.append(page_size)
-    limit_param = f"${param_idx}"
-    param_idx += 1
-
-    params.append(offset)
-    offset_param = f"${param_idx}"
-    param_idx += 1
-
-    # Query using UnifiedContentEmbedding for search, StoreAgent for metadata
-    sql_query = f"""
-        WITH candidates AS (
-            -- Lexical matches via UnifiedContentEmbedding.search
-            SELECT uce."contentId" as "storeListingVersionId"
-            FROM {{schema_prefix}}"UnifiedContentEmbedding" uce
-            INNER JOIN {{schema_prefix}}"StoreAgent" sa
-                ON uce."contentId" = sa."storeListingVersionId"
-            WHERE uce."contentType" = 'STORE_AGENT'::{{schema_prefix}}"ContentType"
-            AND uce."userId" IS NULL
-            AND uce.search @@ plainto_tsquery('english', {query_param})
-            AND {where_clause}
-
-            UNION
-
-            -- Semantic matches via UnifiedContentEmbedding.embedding
-            SELECT uce."contentId" as "storeListingVersionId"
-            FROM (
-                SELECT uce."contentId", uce.embedding
-                FROM {{schema_prefix}}"UnifiedContentEmbedding" uce
-                INNER JOIN {{schema_prefix}}"StoreAgent" sa
-                    ON uce."contentId" = sa."storeListingVersionId"
-                WHERE uce."contentType" = 'STORE_AGENT'::{{schema_prefix}}"ContentType"
-                AND uce."userId" IS NULL
-                AND {where_clause}
-                ORDER BY uce.embedding <=> {embedding_param}::vector
-                LIMIT 200
-            ) uce
-        ),
-        search_scores AS (
-            SELECT
-                sa.slug,
-                sa.agent_name,
-                sa.agent_image,
-                sa.creator_username,
-                sa.creator_avatar,
-                sa.sub_heading,
-                sa.description,
-                sa.runs,
-                sa.rating,
-                sa.categories,
-                sa.featured,
-                sa.is_available,
-                sa.updated_at,
-                -- Semantic score
-                COALESCE(1 - (uce.embedding <=> {embedding_param}::vector), 0) as semantic_score,
-                -- Lexical score (raw, will normalize)
-                COALESCE(ts_rank_cd(uce.search, plainto_tsquery('english', {query_param})), 0) as lexical_raw,
-                -- Category match
-                CASE
-                    WHEN EXISTS (
-                        SELECT 1 FROM unnest(sa.categories) cat
-                        WHERE LOWER(cat) LIKE '%' || {query_lower_param} || '%'
-                    )
-                    THEN 1.0
-                    ELSE 0.0
-                END as category_score,
-                -- Recency
-                GREATEST(0, 1 - EXTRACT(EPOCH FROM (NOW() - sa.updated_at)) / (90 * 24 * 3600)) as recency_score,
-                -- Popularity (raw)
-                sa.runs as popularity_raw
-            FROM candidates c
-            INNER JOIN {{schema_prefix}}"StoreAgent" sa
-                ON c."storeListingVersionId" = sa."storeListingVersionId"
-            INNER JOIN {{schema_prefix}}"UnifiedContentEmbedding" uce
-                ON sa."storeListingVersionId" = uce."contentId"
-                AND uce."contentType" = 'STORE_AGENT'::{{schema_prefix}}"ContentType"
-        ),
-        max_vals AS (
-            SELECT
-                GREATEST(MAX(lexical_raw), 0.001) as max_lexical,
-                GREATEST(MAX(popularity_raw), 1) as max_popularity
-            FROM search_scores
-        ),
-        normalized AS (
-            SELECT
-                ss.*,
-                ss.lexical_raw / mv.max_lexical as lexical_score,
-                CASE
-                    WHEN ss.popularity_raw > 0
-                    THEN LN(1 + ss.popularity_raw) / LN(1 + mv.max_popularity)
-                    ELSE 0
-                END as popularity_score
-            FROM search_scores ss
-            CROSS JOIN max_vals mv
-        ),
-        scored AS (
-            SELECT
-                slug,
-                agent_name,
-                agent_image,
-                creator_username,
-                creator_avatar,
-                sub_heading,
-                description,
-                runs,
-                rating,
-                categories,
-                featured,
-                is_available,
-                updated_at,
-                semantic_score,
-                lexical_score,
-                category_score,
-                recency_score,
-                popularity_score,
-                (
-                    {w_semantic} * semantic_score +
-                    {w_lexical} * lexical_score +
-                    {w_category} * category_score +
-                    {w_recency} * recency_score +
-                    {w_popularity} * popularity_score
-                ) as combined_score
-            FROM normalized
-        ),
-        filtered AS (
-            SELECT *, COUNT(*) OVER () as total_count
-            FROM scored
-            WHERE combined_score >= {min_score_param}
-        )
-        SELECT * FROM filtered
-        ORDER BY combined_score DESC
-        LIMIT {limit_param} OFFSET {offset_param}
-    """
-
-    results = await query_raw_with_schema(
-        sql_query, *params, set_public_search_path=True
-    )
-
-    total = results[0]["total_count"] if results else 0
-
-    for result in results:
-        result.pop("total_count", None)
-
-    logger.info(f"Hybrid search (store agents): {len(results)} results, {total} total")
-
-    return results, total
-
-
-async def hybrid_search_simple(
-    query: str,
-    page: int = 1,
-    page_size: int = 20,
-) -> tuple[list[dict[str, Any]], int]:
-    """Simplified hybrid search for store agents."""
-    return await hybrid_search(query=query, page=page, page_size=page_size)
-
-
-# Backward compatibility alias - HybridSearchWeights maps to StoreAgentSearchWeights
-# for existing code that expects the popularity parameter
-HybridSearchWeights = StoreAgentSearchWeights

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

@@ -1,667 +0,0 @@
-"""
-Integration tests for hybrid search with schema handling.
-
-These tests verify that hybrid search works correctly across different database schemas.
-"""
-
-from unittest.mock import patch
-
-import pytest
-from prisma.enums import ContentType
-
-from backend.api.features.store import embeddings
-from backend.api.features.store.hybrid_search import (
-    HybridSearchWeights,
-    UnifiedSearchWeights,
-    hybrid_search,
-    unified_hybrid_search,
-)
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_hybrid_search_with_schema_handling():
-    """Test that hybrid search correctly handles database schema prefixes."""
-    # Test with a mock query to ensure schema handling works
-    query = "test agent"
-
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        # Mock the query result
-        mock_query.return_value = [
-            {
-                "slug": "test/agent",
-                "agent_name": "Test Agent",
-                "agent_image": "test.png",
-                "creator_username": "test",
-                "creator_avatar": "avatar.png",
-                "sub_heading": "Test sub-heading",
-                "description": "Test description",
-                "runs": 10,
-                "rating": 4.5,
-                "categories": ["test"],
-                "featured": False,
-                "is_available": True,
-                "updated_at": "2024-01-01T00:00:00Z",
-                "combined_score": 0.8,
-                "semantic_score": 0.7,
-                "lexical_score": 0.6,
-                "category_score": 0.5,
-                "recency_score": 0.4,
-                "total_count": 1,
-            }
-        ]
-
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM  # Mock embedding
-
-            results, total = await hybrid_search(
-                query=query,
-                page=1,
-                page_size=20,
-            )
-
-            # Verify the query was called
-            assert mock_query.called
-            # Verify the SQL template uses schema_prefix placeholder
-            call_args = mock_query.call_args
-            sql_template = call_args[0][0]
-            assert "{schema_prefix}" in sql_template
-
-            # Verify results
-            assert len(results) == 1
-            assert total == 1
-            assert results[0]["slug"] == "test/agent"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_hybrid_search_with_public_schema():
-    """Test hybrid search when using public schema (no prefix needed)."""
-    with patch("backend.data.db.get_database_schema") as mock_schema:
-        mock_schema.return_value = "public"
-
-        with patch(
-            "backend.api.features.store.hybrid_search.query_raw_with_schema"
-        ) as mock_query:
-            mock_query.return_value = []
-
-            with patch(
-                "backend.api.features.store.hybrid_search.embed_query"
-            ) as mock_embed:
-                mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-                results, total = await hybrid_search(
-                    query="test",
-                    page=1,
-                    page_size=20,
-                )
-
-                # Verify the mock was set up correctly
-                assert mock_schema.return_value == "public"
-
-                # Results should work even with empty results
-                assert results == []
-                assert total == 0
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_hybrid_search_with_custom_schema():
-    """Test hybrid search when using custom schema (e.g., 'platform')."""
-    with patch("backend.data.db.get_database_schema") as mock_schema:
-        mock_schema.return_value = "platform"
-
-        with patch(
-            "backend.api.features.store.hybrid_search.query_raw_with_schema"
-        ) as mock_query:
-            mock_query.return_value = []
-
-            with patch(
-                "backend.api.features.store.hybrid_search.embed_query"
-            ) as mock_embed:
-                mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-                results, total = await hybrid_search(
-                    query="test",
-                    page=1,
-                    page_size=20,
-                )
-
-                # Verify the mock was set up correctly
-                assert mock_schema.return_value == "platform"
-
-                assert results == []
-                assert total == 0
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_hybrid_search_without_embeddings():
-    """Test hybrid search gracefully degrades when embeddings are unavailable."""
-    # Mock database to return some results
-    mock_results = [
-        {
-            "slug": "test-agent",
-            "agent_name": "Test Agent",
-            "agent_image": "test.png",
-            "creator_username": "creator",
-            "creator_avatar": "avatar.png",
-            "sub_heading": "Test heading",
-            "description": "Test description",
-            "runs": 100,
-            "rating": 4.5,
-            "categories": ["AI"],
-            "featured": False,
-            "is_available": True,
-            "updated_at": "2025-01-01T00:00:00Z",
-            "semantic_score": 0.0,  # Zero because no embedding
-            "lexical_score": 0.5,
-            "category_score": 0.0,
-            "recency_score": 0.1,
-            "popularity_score": 0.2,
-            "combined_score": 0.3,
-            "total_count": 1,
-        }
-    ]
-
-    with patch("backend.api.features.store.hybrid_search.embed_query") as mock_embed:
-        with patch(
-            "backend.api.features.store.hybrid_search.query_raw_with_schema"
-        ) as mock_query:
-            # Simulate embedding failure
-            mock_embed.return_value = None
-            mock_query.return_value = mock_results
-
-            # Should NOT raise - graceful degradation
-            results, total = await hybrid_search(
-                query="test",
-                page=1,
-                page_size=20,
-            )
-
-            # Verify it returns results even without embeddings
-            assert len(results) == 1
-            assert results[0]["slug"] == "test-agent"
-            assert total == 1
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_hybrid_search_with_filters():
-    """Test hybrid search with various filters."""
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        mock_query.return_value = []
-
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-            # Test with featured filter
-            results, total = await hybrid_search(
-                query="test",
-                featured=True,
-                creators=["user1", "user2"],
-                category="productivity",
-                page=1,
-                page_size=10,
-            )
-
-            # Verify filters were applied in the query
-            call_args = mock_query.call_args
-            params = call_args[0][1:]  # Skip SQL template
-
-            # Should have query, query_lower, creators array, category
-            assert len(params) >= 4
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_hybrid_search_weights():
-    """Test hybrid search with custom weights."""
-    custom_weights = HybridSearchWeights(
-        semantic=0.5,
-        lexical=0.3,
-        category=0.1,
-        recency=0.1,
-        popularity=0.0,
-    )
-
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        mock_query.return_value = []
-
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-            results, total = await hybrid_search(
-                query="test",
-                weights=custom_weights,
-                page=1,
-                page_size=20,
-            )
-
-            # Verify custom weights were used in the query
-            call_args = mock_query.call_args
-            sql_template = call_args[0][0]
-            params = call_args[0][1:]  # Get all parameters passed
-
-            # Check that SQL uses parameterized weights (not f-string interpolation)
-            assert "$" in sql_template  # Verify parameterization is used
-
-            # Check that custom weights are in the params
-            assert 0.5 in params  # semantic weight
-            assert 0.3 in params  # lexical weight
-            assert 0.1 in params  # category and recency weights
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_hybrid_search_min_score_filtering():
-    """Test hybrid search minimum score threshold."""
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        # Return results with varying scores
-        mock_query.return_value = [
-            {
-                "slug": "high-score/agent",
-                "agent_name": "High Score Agent",
-                "combined_score": 0.8,
-                "total_count": 1,
-                # ... other fields
-            }
-        ]
-
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-            # Test with custom min_score
-            results, total = await hybrid_search(
-                query="test",
-                min_score=0.5,  # High threshold
-                page=1,
-                page_size=20,
-            )
-
-            # Verify min_score was applied in query
-            call_args = mock_query.call_args
-            sql_template = call_args[0][0]
-            params = call_args[0][1:]  # Get all parameters
-
-            # Check that SQL uses parameterized min_score
-            assert "combined_score >=" in sql_template
-            assert "$" in sql_template  # Verify parameterization
-
-            # Check that custom min_score is in the params
-            assert 0.5 in params
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_hybrid_search_pagination():
-    """Test hybrid search pagination."""
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        mock_query.return_value = []
-
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-            # Test page 2 with page_size 10
-            results, total = await hybrid_search(
-                query="test",
-                page=2,
-                page_size=10,
-            )
-
-            # Verify pagination parameters
-            call_args = mock_query.call_args
-            params = call_args[0]
-
-            # Last two params should be LIMIT and OFFSET
-            limit = params[-2]
-            offset = params[-1]
-
-            assert limit == 10  # page_size
-            assert offset == 10  # (page - 1) * page_size = (2 - 1) * 10
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_hybrid_search_error_handling():
-    """Test hybrid search error handling."""
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        # Simulate database error
-        mock_query.side_effect = Exception("Database connection error")
-
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-            # Should raise exception
-            with pytest.raises(Exception) as exc_info:
-                await hybrid_search(
-                    query="test",
-                    page=1,
-                    page_size=20,
-                )
-
-            assert "Database connection error" in str(exc_info.value)
-
-
-# =============================================================================
-# Unified Hybrid Search Tests
-# =============================================================================
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_unified_hybrid_search_basic():
-    """Test basic unified hybrid search across all content types."""
-    mock_results = [
-        {
-            "content_type": "STORE_AGENT",
-            "content_id": "agent-1",
-            "searchable_text": "Test Agent Description",
-            "metadata": {"name": "Test Agent"},
-            "updated_at": "2025-01-01T00:00:00Z",
-            "semantic_score": 0.7,
-            "lexical_score": 0.8,
-            "category_score": 0.5,
-            "recency_score": 0.3,
-            "combined_score": 0.6,
-            "total_count": 2,
-        },
-        {
-            "content_type": "BLOCK",
-            "content_id": "block-1",
-            "searchable_text": "Test Block Description",
-            "metadata": {"name": "Test Block"},
-            "updated_at": "2025-01-01T00:00:00Z",
-            "semantic_score": 0.6,
-            "lexical_score": 0.7,
-            "category_score": 0.4,
-            "recency_score": 0.2,
-            "combined_score": 0.5,
-            "total_count": 2,
-        },
-    ]
-
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_query.return_value = mock_results
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-            results, total = await unified_hybrid_search(
-                query="test",
-                page=1,
-                page_size=20,
-            )
-
-            assert len(results) == 2
-            assert total == 2
-            assert results[0]["content_type"] == "STORE_AGENT"
-            assert results[1]["content_type"] == "BLOCK"
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_unified_hybrid_search_filter_by_content_type():
-    """Test unified search filtering by specific content types."""
-    mock_results = [
-        {
-            "content_type": "BLOCK",
-            "content_id": "block-1",
-            "searchable_text": "Test Block",
-            "metadata": {},
-            "updated_at": "2025-01-01T00:00:00Z",
-            "semantic_score": 0.7,
-            "lexical_score": 0.8,
-            "category_score": 0.0,
-            "recency_score": 0.3,
-            "combined_score": 0.5,
-            "total_count": 1,
-        },
-    ]
-
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_query.return_value = mock_results
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-            results, total = await unified_hybrid_search(
-                query="test",
-                content_types=[ContentType.BLOCK],
-                page=1,
-                page_size=20,
-            )
-
-            # Verify content_types parameter was passed correctly
-            call_args = mock_query.call_args
-            params = call_args[0][1:]
-            # The content types should be in the params as a list
-            assert ["BLOCK"] in params
-
-            assert len(results) == 1
-            assert total == 1
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_unified_hybrid_search_with_user_id():
-    """Test unified search with user_id for private content."""
-    mock_results = [
-        {
-            "content_type": "STORE_AGENT",
-            "content_id": "agent-1",
-            "searchable_text": "My Private Agent",
-            "metadata": {},
-            "updated_at": "2025-01-01T00:00:00Z",
-            "semantic_score": 0.7,
-            "lexical_score": 0.8,
-            "category_score": 0.0,
-            "recency_score": 0.3,
-            "combined_score": 0.6,
-            "total_count": 1,
-        },
-    ]
-
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_query.return_value = mock_results
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-            results, total = await unified_hybrid_search(
-                query="test",
-                user_id="user-123",
-                page=1,
-                page_size=20,
-            )
-
-            # Verify SQL contains user_id filter
-            call_args = mock_query.call_args
-            sql_template = call_args[0][0]
-            params = call_args[0][1:]
-
-            assert 'uce."userId"' in sql_template
-            assert "user-123" in params
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_unified_hybrid_search_custom_weights():
-    """Test unified search with custom weights."""
-    custom_weights = UnifiedSearchWeights(
-        semantic=0.6,
-        lexical=0.2,
-        category=0.1,
-        recency=0.1,
-    )
-
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_query.return_value = []
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-            results, total = await unified_hybrid_search(
-                query="test",
-                weights=custom_weights,
-                page=1,
-                page_size=20,
-            )
-
-            # Verify custom weights are in parameters
-            call_args = mock_query.call_args
-            params = call_args[0][1:]
-
-            assert 0.6 in params  # semantic weight
-            assert 0.2 in params  # lexical weight
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_unified_hybrid_search_graceful_degradation():
-    """Test unified search gracefully degrades when embeddings unavailable."""
-    mock_results = [
-        {
-            "content_type": "DOCUMENTATION",
-            "content_id": "doc-1",
-            "searchable_text": "API Documentation",
-            "metadata": {},
-            "updated_at": "2025-01-01T00:00:00Z",
-            "semantic_score": 0.0,  # Zero because no embedding
-            "lexical_score": 0.8,
-            "category_score": 0.0,
-            "recency_score": 0.2,
-            "combined_score": 0.5,
-            "total_count": 1,
-        },
-    ]
-
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_query.return_value = mock_results
-            mock_embed.return_value = None  # Embedding failure
-
-            # Should NOT raise - graceful degradation
-            results, total = await unified_hybrid_search(
-                query="test",
-                page=1,
-                page_size=20,
-            )
-
-            assert len(results) == 1
-            assert total == 1
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_unified_hybrid_search_empty_query():
-    """Test unified search with empty query returns empty results."""
-    results, total = await unified_hybrid_search(
-        query="",
-        page=1,
-        page_size=20,
-    )
-
-    assert results == []
-    assert total == 0
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_unified_hybrid_search_pagination():
-    """Test unified search pagination."""
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_query.return_value = []
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-            results, total = await unified_hybrid_search(
-                query="test",
-                page=3,
-                page_size=15,
-            )
-
-            # Verify pagination parameters (last two params are LIMIT and OFFSET)
-            call_args = mock_query.call_args
-            params = call_args[0]
-
-            limit = params[-2]
-            offset = params[-1]
-
-            assert limit == 15  # page_size
-            assert offset == 30  # (page - 1) * page_size = (3 - 1) * 15
-
-
-@pytest.mark.asyncio(loop_scope="session")
-@pytest.mark.integration
-async def test_unified_hybrid_search_schema_prefix():
-    """Test unified search uses schema_prefix placeholder."""
-    with patch(
-        "backend.api.features.store.hybrid_search.query_raw_with_schema"
-    ) as mock_query:
-        with patch(
-            "backend.api.features.store.hybrid_search.embed_query"
-        ) as mock_embed:
-            mock_query.return_value = []
-            mock_embed.return_value = [0.1] * embeddings.EMBEDDING_DIM
-
-            await unified_hybrid_search(
-                query="test",
-                page=1,
-                page_size=20,
-            )
-
-            call_args = mock_query.call_args
-            sql_template = call_args[0][0]
-
-            # Verify schema_prefix placeholder is used for table references
-            assert "{schema_prefix}" in sql_template
-            assert '"UnifiedContentEmbedding"' in sql_template
-
-
-if __name__ == "__main__":
-    pytest.main([__file__, "-v", "-s"])

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

@@ -1,272 +0,0 @@
-"""Tests for the semantic_search function."""
-
-import pytest
-from prisma.enums import ContentType
-
-from backend.api.features.store.embeddings import EMBEDDING_DIM, semantic_search
-
-
-@pytest.mark.asyncio
-async def test_search_blocks_only(mocker):
-    """Test searching only BLOCK content type."""
-    # Mock embed_query to return a test embedding
-    mock_embedding = [0.1] * EMBEDDING_DIM
-    mocker.patch(
-        "backend.api.features.store.embeddings.embed_query",
-        return_value=mock_embedding,
-    )
-
-    # Mock query_raw_with_schema to return test results
-    mock_results = [
-        {
-            "content_id": "block-123",
-            "content_type": "BLOCK",
-            "searchable_text": "Calculator Block - Performs arithmetic operations",
-            "metadata": {"name": "Calculator", "categories": ["Math"]},
-            "similarity": 0.85,
-        }
-    ]
-    mocker.patch(
-        "backend.api.features.store.embeddings.query_raw_with_schema",
-        return_value=mock_results,
-    )
-
-    results = await semantic_search(
-        query="calculate numbers",
-        content_types=[ContentType.BLOCK],
-    )
-
-    assert len(results) == 1
-    assert results[0]["content_type"] == "BLOCK"
-    assert results[0]["content_id"] == "block-123"
-    assert results[0]["similarity"] == 0.85
-
-
-@pytest.mark.asyncio
-async def test_search_multiple_content_types(mocker):
-    """Test searching multiple content types simultaneously."""
-    mock_embedding = [0.1] * EMBEDDING_DIM
-    mocker.patch(
-        "backend.api.features.store.embeddings.embed_query",
-        return_value=mock_embedding,
-    )
-
-    mock_results = [
-        {
-            "content_id": "block-123",
-            "content_type": "BLOCK",
-            "searchable_text": "Calculator Block",
-            "metadata": {},
-            "similarity": 0.85,
-        },
-        {
-            "content_id": "doc-456",
-            "content_type": "DOCUMENTATION",
-            "searchable_text": "How to use Calculator",
-            "metadata": {},
-            "similarity": 0.75,
-        },
-    ]
-    mocker.patch(
-        "backend.api.features.store.embeddings.query_raw_with_schema",
-        return_value=mock_results,
-    )
-
-    results = await semantic_search(
-        query="calculator",
-        content_types=[ContentType.BLOCK, ContentType.DOCUMENTATION],
-    )
-
-    assert len(results) == 2
-    assert results[0]["content_type"] == "BLOCK"
-    assert results[1]["content_type"] == "DOCUMENTATION"
-
-
-@pytest.mark.asyncio
-async def test_search_with_min_similarity_threshold(mocker):
-    """Test that results below min_similarity are filtered out."""
-    mock_embedding = [0.1] * EMBEDDING_DIM
-    mocker.patch(
-        "backend.api.features.store.embeddings.embed_query",
-        return_value=mock_embedding,
-    )
-
-    # Only return results above 0.7 similarity
-    mock_results = [
-        {
-            "content_id": "block-123",
-            "content_type": "BLOCK",
-            "searchable_text": "Calculator Block",
-            "metadata": {},
-            "similarity": 0.85,
-        }
-    ]
-    mocker.patch(
-        "backend.api.features.store.embeddings.query_raw_with_schema",
-        return_value=mock_results,
-    )
-
-    results = await semantic_search(
-        query="calculate",
-        content_types=[ContentType.BLOCK],
-        min_similarity=0.7,
-    )
-
-    assert len(results) == 1
-    assert results[0]["similarity"] >= 0.7
-
-
-@pytest.mark.asyncio
-async def test_search_fallback_to_lexical(mocker):
-    """Test fallback to lexical search when embeddings fail."""
-    # Mock embed_query to return None (embeddings unavailable)
-    mocker.patch(
-        "backend.api.features.store.embeddings.embed_query",
-        return_value=None,
-    )
-
-    mock_lexical_results = [
-        {
-            "content_id": "block-123",
-            "content_type": "BLOCK",
-            "searchable_text": "Calculator Block performs calculations",
-            "metadata": {},
-            "similarity": 0.0,
-        }
-    ]
-    mocker.patch(
-        "backend.api.features.store.embeddings.query_raw_with_schema",
-        return_value=mock_lexical_results,
-    )
-
-    results = await semantic_search(
-        query="calculator",
-        content_types=[ContentType.BLOCK],
-    )
-
-    assert len(results) == 1
-    assert results[0]["similarity"] == 0.0  # Lexical search returns 0 similarity
-
-
-@pytest.mark.asyncio
-async def test_search_empty_query():
-    """Test that empty query returns no results."""
-    results = await semantic_search(query="")
-    assert results == []
-
-    results = await semantic_search(query="   ")
-    assert results == []
-
-
-@pytest.mark.asyncio
-async def test_search_with_user_id_filter(mocker):
-    """Test searching with user_id filter for private content."""
-    mock_embedding = [0.1] * EMBEDDING_DIM
-    mocker.patch(
-        "backend.api.features.store.embeddings.embed_query",
-        return_value=mock_embedding,
-    )
-
-    mock_results = [
-        {
-            "content_id": "agent-789",
-            "content_type": "LIBRARY_AGENT",
-            "searchable_text": "My Custom Agent",
-            "metadata": {},
-            "similarity": 0.9,
-        }
-    ]
-    mocker.patch(
-        "backend.api.features.store.embeddings.query_raw_with_schema",
-        return_value=mock_results,
-    )
-
-    results = await semantic_search(
-        query="custom agent",
-        content_types=[ContentType.LIBRARY_AGENT],
-        user_id="user-123",
-    )
-
-    assert len(results) == 1
-    assert results[0]["content_type"] == "LIBRARY_AGENT"
-
-
-@pytest.mark.asyncio
-async def test_search_limit_parameter(mocker):
-    """Test that limit parameter correctly limits results."""
-    mock_embedding = [0.1] * EMBEDDING_DIM
-    mocker.patch(
-        "backend.api.features.store.embeddings.embed_query",
-        return_value=mock_embedding,
-    )
-
-    # Return 5 results
-    mock_results = [
-        {
-            "content_id": f"block-{i}",
-            "content_type": "BLOCK",
-            "searchable_text": f"Block {i}",
-            "metadata": {},
-            "similarity": 0.8,
-        }
-        for i in range(5)
-    ]
-    mocker.patch(
-        "backend.api.features.store.embeddings.query_raw_with_schema",
-        return_value=mock_results,
-    )
-
-    results = await semantic_search(
-        query="block",
-        content_types=[ContentType.BLOCK],
-        limit=5,
-    )
-
-    assert len(results) == 5
-
-
-@pytest.mark.asyncio
-async def test_search_default_content_types(mocker):
-    """Test that default content_types includes BLOCK, STORE_AGENT, and DOCUMENTATION."""
-    mock_embedding = [0.1] * EMBEDDING_DIM
-    mocker.patch(
-        "backend.api.features.store.embeddings.embed_query",
-        return_value=mock_embedding,
-    )
-
-    mock_query_raw = mocker.patch(
-        "backend.api.features.store.embeddings.query_raw_with_schema",
-        return_value=[],
-    )
-
-    await semantic_search(query="test")
-
-    # Check that the SQL query includes all three default content types
-    call_args = mock_query_raw.call_args
-    assert "BLOCK" in str(call_args)
-    assert "STORE_AGENT" in str(call_args)
-    assert "DOCUMENTATION" in str(call_args)
-
-
-@pytest.mark.asyncio
-async def test_search_handles_database_error(mocker):
-    """Test that database errors are handled gracefully."""
-    mock_embedding = [0.1] * EMBEDDING_DIM
-    mocker.patch(
-        "backend.api.features.store.embeddings.embed_query",
-        return_value=mock_embedding,
-    )
-
-    # Simulate database error
-    mocker.patch(
-        "backend.api.features.store.embeddings.query_raw_with_schema",
-        side_effect=Exception("Database connection failed"),
-    )
-
-    results = await semantic_search(
-        query="test",
-        content_types=[ContentType.BLOCK],
-    )
-
-    # Should return empty list on error
-    assert results == []

autogpt_platform/backend/backend/api/utils/openapi.py

@@ -1,41 +0,0 @@
-from fastapi import FastAPI
-
-
-def sort_openapi(app: FastAPI) -> None:
-    """
-    Patch a FastAPI instance's `openapi()` method to sort the endpoints,
-    schemas, and responses.
-    """
-    wrapped_openapi = app.openapi
-
-    def custom_openapi():
-        if app.openapi_schema:
-            return app.openapi_schema
-
-        openapi_schema = wrapped_openapi()
-
-        # Sort endpoints
-        openapi_schema["paths"] = dict(sorted(openapi_schema["paths"].items()))
-
-        # Sort endpoints -> methods
-        for p in openapi_schema["paths"].keys():
-            openapi_schema["paths"][p] = dict(
-                sorted(openapi_schema["paths"][p].items())
-            )
-
-            # Sort endpoints -> methods -> responses
-            for m in openapi_schema["paths"][p].keys():
-                openapi_schema["paths"][p][m]["responses"] = dict(
-                    sorted(openapi_schema["paths"][p][m]["responses"].items())
-                )
-
-        # Sort schemas and responses as well
-        for k in openapi_schema["components"].keys():
-            openapi_schema["components"][k] = dict(
-                sorted(openapi_schema["components"][k].items())
-            )
-
-        app.openapi_schema = openapi_schema
-        return openapi_schema
-
-    app.openapi = custom_openapi

autogpt_platform/backend/backend/app.py

@@ -36,10 +36,10 @@ def main(**kwargs):
     Run all the processes required for the AutoGPT-server (REST and WebSocket APIs).
     """
 
-    from backend.api.rest_api import AgentServer
-    from backend.api.ws_api import WebsocketServer
     from backend.executor import DatabaseManager, ExecutionManager, Scheduler
     from backend.notifications import NotificationManager
+    from backend.server.rest_api import AgentServer
+    from backend.server.ws_api import WebsocketServer
 
     run_processes(
         DatabaseManager().set_log_level("warning"),

autogpt_platform/backend/backend/blocks/ai_condition.py

@@ -1,7 +1,6 @@
 from typing import Any
 
 from backend.blocks.llm import (
-    DEFAULT_LLM_MODEL,
     TEST_CREDENTIALS,
     TEST_CREDENTIALS_INPUT,
     AIBlockBase,
@@ -50,7 +49,7 @@ class AIConditionBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default=DEFAULT_LLM_MODEL,
+            default=LlmModel.GPT4O,
             description="The language model to use for evaluating the condition.",
             advanced=False,
         )
@@ -82,7 +81,7 @@ class AIConditionBlock(AIBlockBase):
                 "condition": "the input is an email address",
                 "yes_value": "Valid email",
                 "no_value": "Not an email",
-                "model": DEFAULT_LLM_MODEL,
+                "model": LlmModel.GPT4O,
                 "credentials": TEST_CREDENTIALS_INPUT,
             },
             test_credentials=TEST_CREDENTIALS,

autogpt_platform/backend/backend/blocks/airtable/_webhook.py

@@ -6,9 +6,6 @@ import hashlib
 import hmac
 import logging
 from enum import Enum
-from typing import cast
-
-from prisma.types import Serializable
 
 from backend.sdk import (
     BaseWebhooksManager,
@@ -87,9 +84,7 @@ class AirtableWebhookManager(BaseWebhooksManager):
         # update webhook config
         await update_webhook(
             webhook.id,
-            config=cast(
-                dict[str, Serializable], {"base_id": base_id, "cursor": response.cursor}
-            ),
+            config={"base_id": base_id, "cursor": response.cursor},
         )
 
         event_type = "notification"

autogpt_platform/backend/backend/blocks/dataforseo/related_keywords.py

@@ -182,10 +182,13 @@ class DataForSeoRelatedKeywordsBlock(Block):
             if results and len(results) > 0:
                 # results is a list, get the first element
                 first_result = results[0] if isinstance(results, list) else results
-                # Handle missing key, null value, or valid list value
-                if isinstance(first_result, dict):
-                    items = first_result.get("items") or []
-                else:
+                items = (
+                    first_result.get("items", [])
+                    if isinstance(first_result, dict)
+                    else []
+                )
+                # Ensure items is never None
+                if items is None:
                     items = []
                 for item in items:
                     # Extract keyword_data from the item

autogpt_platform/backend/backend/blocks/exa/helpers.py

@@ -319,7 +319,7 @@ class CostDollars(BaseModel):
 
 # Helper functions for payload processing
 def process_text_field(
-    text: Union[bool, TextEnabled, TextDisabled, TextAdvanced, None]
+    text: Union[bool, TextEnabled, TextDisabled, TextAdvanced, None],
 ) -> Optional[Union[bool, Dict[str, Any]]]:
     """Process text field for API payload."""
     if text is None:
@@ -400,7 +400,7 @@ def process_contents_settings(contents: Optional[ContentSettings]) -> Dict[str,
 
 
 def process_context_field(
-    context: Union[bool, dict, ContextEnabled, ContextDisabled, ContextAdvanced, None]
+    context: Union[bool, dict, ContextEnabled, ContextDisabled, ContextAdvanced, None],
 ) -> Optional[Union[bool, Dict[str, int]]]:
     """Process context field for API payload."""
     if context is None:

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

@@ -1,184 +0,0 @@
-"""
-Shared helpers for Human-In-The-Loop (HITL) review functionality.
-Used by both the dedicated HumanInTheLoopBlock and blocks that require human review.
-"""
-
-import logging
-from typing import Any, Optional
-
-from prisma.enums import ReviewStatus
-from pydantic import BaseModel
-
-from backend.data.execution import ExecutionContext, ExecutionStatus
-from backend.data.human_review import ReviewResult
-from backend.executor.manager import async_update_node_execution_status
-from backend.util.clients import get_database_manager_async_client
-
-logger = logging.getLogger(__name__)
-
-
-class ReviewDecision(BaseModel):
-    """Result of a review decision."""
-
-    should_proceed: bool
-    message: str
-    review_result: ReviewResult
-
-
-class HITLReviewHelper:
-    """Helper class for Human-In-The-Loop review operations."""
-
-    @staticmethod
-    async def get_or_create_human_review(**kwargs) -> Optional[ReviewResult]:
-        """Create or retrieve a human review from the database."""
-        return await get_database_manager_async_client().get_or_create_human_review(
-            **kwargs
-        )
-
-    @staticmethod
-    async def update_node_execution_status(**kwargs) -> None:
-        """Update the execution status of a node."""
-        await async_update_node_execution_status(
-            db_client=get_database_manager_async_client(), **kwargs
-        )
-
-    @staticmethod
-    async def update_review_processed_status(
-        node_exec_id: str, processed: bool
-    ) -> None:
-        """Update the processed status of a review."""
-        return await get_database_manager_async_client().update_review_processed_status(
-            node_exec_id, processed
-        )
-
-    @staticmethod
-    async def _handle_review_request(
-        input_data: Any,
-        user_id: str,
-        node_exec_id: str,
-        graph_exec_id: str,
-        graph_id: str,
-        graph_version: int,
-        execution_context: ExecutionContext,
-        block_name: str = "Block",
-        editable: bool = False,
-    ) -> Optional[ReviewResult]:
-        """
-        Handle a review request for a block that requires human review.
-
-        Args:
-            input_data: The input data to be reviewed
-            user_id: ID of the user requesting the review
-            node_exec_id: ID of the node execution
-            graph_exec_id: ID of the graph execution
-            graph_id: ID of the graph
-            graph_version: Version of the graph
-            execution_context: Current execution context
-            block_name: Name of the block requesting review
-            editable: Whether the reviewer can edit the data
-
-        Returns:
-            ReviewResult if review is complete, None if waiting for human input
-
-        Raises:
-            Exception: If review creation or status update fails
-        """
-        # Skip review if safe mode is disabled - return auto-approved result
-        if not execution_context.safe_mode:
-            logger.info(
-                f"Block {block_name} skipping review for node {node_exec_id} - safe mode disabled"
-            )
-            return ReviewResult(
-                data=input_data,
-                status=ReviewStatus.APPROVED,
-                message="Auto-approved (safe mode disabled)",
-                processed=True,
-                node_exec_id=node_exec_id,
-            )
-
-        result = await HITLReviewHelper.get_or_create_human_review(
-            user_id=user_id,
-            node_exec_id=node_exec_id,
-            graph_exec_id=graph_exec_id,
-            graph_id=graph_id,
-            graph_version=graph_version,
-            input_data=input_data,
-            message=f"Review required for {block_name} execution",
-            editable=editable,
-        )
-
-        if result is None:
-            logger.info(
-                f"Block {block_name} pausing execution for node {node_exec_id} - awaiting human review"
-            )
-            await HITLReviewHelper.update_node_execution_status(
-                exec_id=node_exec_id,
-                status=ExecutionStatus.REVIEW,
-            )
-            return None  # Signal that execution should pause
-
-        # Mark review as processed if not already done
-        if not result.processed:
-            await HITLReviewHelper.update_review_processed_status(
-                node_exec_id=node_exec_id, processed=True
-            )
-
-        return result
-
-    @staticmethod
-    async def handle_review_decision(
-        input_data: Any,
-        user_id: str,
-        node_exec_id: str,
-        graph_exec_id: str,
-        graph_id: str,
-        graph_version: int,
-        execution_context: ExecutionContext,
-        block_name: str = "Block",
-        editable: bool = False,
-    ) -> Optional[ReviewDecision]:
-        """
-        Handle a review request and return the decision in a single call.
-
-        Args:
-            input_data: The input data to be reviewed
-            user_id: ID of the user requesting the review
-            node_exec_id: ID of the node execution
-            graph_exec_id: ID of the graph execution
-            graph_id: ID of the graph
-            graph_version: Version of the graph
-            execution_context: Current execution context
-            block_name: Name of the block requesting review
-            editable: Whether the reviewer can edit the data
-
-        Returns:
-            ReviewDecision if review is complete (approved/rejected),
-            None if execution should pause (awaiting review)
-        """
-        review_result = await HITLReviewHelper._handle_review_request(
-            input_data=input_data,
-            user_id=user_id,
-            node_exec_id=node_exec_id,
-            graph_exec_id=graph_exec_id,
-            graph_id=graph_id,
-            graph_version=graph_version,
-            execution_context=execution_context,
-            block_name=block_name,
-            editable=editable,
-        )
-
-        if review_result is None:
-            # Still awaiting review - return None to pause execution
-            return None
-
-        # Review is complete, determine outcome
-        should_proceed = review_result.status == ReviewStatus.APPROVED
-        message = review_result.message or (
-            "Execution approved by reviewer"
-            if should_proceed
-            else "Execution rejected by reviewer"
-        )
-
-        return ReviewDecision(
-            should_proceed=should_proceed, message=message, review_result=review_result
-        )

autogpt_platform/backend/backend/blocks/human_in_the_loop.py

@@ -3,7 +3,6 @@ from typing import Any
 
 from prisma.enums import ReviewStatus
 
-from backend.blocks.helpers.review import HITLReviewHelper
 from backend.data.block import (
     Block,
     BlockCategory,
@@ -12,9 +11,11 @@ from backend.data.block import (
     BlockSchemaOutput,
     BlockType,
 )
-from backend.data.execution import ExecutionContext
+from backend.data.execution import ExecutionContext, ExecutionStatus
 from backend.data.human_review import ReviewResult
 from backend.data.model import SchemaField
+from backend.executor.manager import async_update_node_execution_status
+from backend.util.clients import get_database_manager_async_client
 
 logger = logging.getLogger(__name__)
 
@@ -71,26 +72,32 @@ class HumanInTheLoopBlock(Block):
                 ("approved_data", {"name": "John Doe", "age": 30}),
             ],
             test_mock={
-                "handle_review_decision": lambda **kwargs: type(
-                    "ReviewDecision",
-                    (),
-                    {
-                        "should_proceed": True,
-                        "message": "Test approval message",
-                        "review_result": ReviewResult(
-                            data={"name": "John Doe", "age": 30},
-                            status=ReviewStatus.APPROVED,
-                            message="",
-                            processed=False,
-                            node_exec_id="test-node-exec-id",
-                        ),
-                    },
-                )(),
+                "get_or_create_human_review": lambda *_args, **_kwargs: ReviewResult(
+                    data={"name": "John Doe", "age": 30},
+                    status=ReviewStatus.APPROVED,
+                    message="",
+                    processed=False,
+                    node_exec_id="test-node-exec-id",
+                ),
+                "update_node_execution_status": lambda *_args, **_kwargs: None,
+                "update_review_processed_status": lambda *_args, **_kwargs: None,
             },
         )
 
-    async def handle_review_decision(self, **kwargs):
-        return await HITLReviewHelper.handle_review_decision(**kwargs)
+    async def get_or_create_human_review(self, **kwargs):
+        return await get_database_manager_async_client().get_or_create_human_review(
+            **kwargs
+        )
+
+    async def update_node_execution_status(self, **kwargs):
+        return await async_update_node_execution_status(
+            db_client=get_database_manager_async_client(), **kwargs
+        )
+
+    async def update_review_processed_status(self, node_exec_id: str, processed: bool):
+        return await get_database_manager_async_client().update_review_processed_status(
+            node_exec_id, processed
+        )
 
     async def run(
         self,
@@ -102,7 +109,7 @@ class HumanInTheLoopBlock(Block):
         graph_id: str,
         graph_version: int,
         execution_context: ExecutionContext,
-        **_kwargs,
+        **kwargs,
     ) -> BlockOutput:
         if not execution_context.safe_mode:
             logger.info(
@@ -112,28 +119,48 @@ class HumanInTheLoopBlock(Block):
             yield "review_message", "Auto-approved (safe mode disabled)"
             return
 
-        decision = await self.handle_review_decision(
-            input_data=input_data.data,
-            user_id=user_id,
-            node_exec_id=node_exec_id,
-            graph_exec_id=graph_exec_id,
-            graph_id=graph_id,
-            graph_version=graph_version,
-            execution_context=execution_context,
-            block_name=self.name,
-            editable=input_data.editable,
-        )
+        try:
+            result = await self.get_or_create_human_review(
+                user_id=user_id,
+                node_exec_id=node_exec_id,
+                graph_exec_id=graph_exec_id,
+                graph_id=graph_id,
+                graph_version=graph_version,
+                input_data=input_data.data,
+                message=input_data.name,
+                editable=input_data.editable,
+            )
+        except Exception as e:
+            logger.error(f"Error in HITL block for node {node_exec_id}: {str(e)}")
+            raise
 
-        if decision is None:
-            return
+        if result is None:
+            logger.info(
+                f"HITL block pausing execution for node {node_exec_id} - awaiting human review"
+            )
+            try:
+                await self.update_node_execution_status(
+                    exec_id=node_exec_id,
+                    status=ExecutionStatus.REVIEW,
+                )
+                return
+            except Exception as e:
+                logger.error(
+                    f"Failed to update node status for HITL block {node_exec_id}: {str(e)}"
+                )
+                raise
 
-        status = decision.review_result.status
-        if status == ReviewStatus.APPROVED:
-            yield "approved_data", decision.review_result.data
-        elif status == ReviewStatus.REJECTED:
-            yield "rejected_data", decision.review_result.data
-        else:
-            raise RuntimeError(f"Unexpected review status: {status}")
+        if not result.processed:
+            await self.update_review_processed_status(
+                node_exec_id=node_exec_id, processed=True
+            )
 
-        if decision.message:
-            yield "review_message", decision.message
+            if result.status == ReviewStatus.APPROVED:
+                yield "approved_data", result.data
+                if result.message:
+                    yield "review_message", result.message
+
+            elif result.status == ReviewStatus.REJECTED:
+                yield "rejected_data", result.data
+                if result.message:
+                    yield "review_message", result.message

autogpt_platform/backend/backend/blocks/llm.py

@@ -92,9 +92,8 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
     O1 = "o1"
     O1_MINI = "o1-mini"
     # GPT-5 models
-    GPT5_2 = "gpt-5.2-2025-12-11"
-    GPT5_1 = "gpt-5.1-2025-11-13"
     GPT5 = "gpt-5-2025-08-07"
+    GPT5_1 = "gpt-5.1-2025-11-13"
     GPT5_MINI = "gpt-5-mini-2025-08-07"
     GPT5_NANO = "gpt-5-nano-2025-08-07"
     GPT5_CHAT = "gpt-5-chat-latest"
@@ -195,9 +194,8 @@ MODEL_METADATA = {
     LlmModel.O1: ModelMetadata("openai", 200000, 100000),  # o1-2024-12-17
     LlmModel.O1_MINI: ModelMetadata("openai", 128000, 65536),  # o1-mini-2024-09-12
     # GPT-5 models
-    LlmModel.GPT5_2: ModelMetadata("openai", 400000, 128000),
-    LlmModel.GPT5_1: ModelMetadata("openai", 400000, 128000),
     LlmModel.GPT5: ModelMetadata("openai", 400000, 128000),
+    LlmModel.GPT5_1: ModelMetadata("openai", 400000, 128000),
     LlmModel.GPT5_MINI: ModelMetadata("openai", 400000, 128000),
     LlmModel.GPT5_NANO: ModelMetadata("openai", 400000, 128000),
     LlmModel.GPT5_CHAT: ModelMetadata("openai", 400000, 16384),
@@ -305,8 +303,6 @@ MODEL_METADATA = {
     LlmModel.V0_1_0_MD: ModelMetadata("v0", 128000, 64000),
 }
 
-DEFAULT_LLM_MODEL = LlmModel.GPT5_2
-
 for model in LlmModel:
     if model not in MODEL_METADATA:
         raise ValueError(f"Missing MODEL_METADATA metadata for model: {model}")
@@ -794,7 +790,7 @@ class AIStructuredResponseGeneratorBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default=DEFAULT_LLM_MODEL,
+            default=LlmModel.GPT4O,
             description="The language model to use for answering the prompt.",
             advanced=False,
         )
@@ -859,7 +855,7 @@ class AIStructuredResponseGeneratorBlock(AIBlockBase):
             input_schema=AIStructuredResponseGeneratorBlock.Input,
             output_schema=AIStructuredResponseGeneratorBlock.Output,
             test_input={
-                "model": DEFAULT_LLM_MODEL,
+                "model": LlmModel.GPT4O,
                 "credentials": TEST_CREDENTIALS_INPUT,
                 "expected_format": {
                     "key1": "value1",
@@ -1225,7 +1221,7 @@ class AITextGeneratorBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default=DEFAULT_LLM_MODEL,
+            default=LlmModel.GPT4O,
             description="The language model to use for answering the prompt.",
             advanced=False,
         )
@@ -1321,7 +1317,7 @@ class AITextSummarizerBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default=DEFAULT_LLM_MODEL,
+            default=LlmModel.GPT4O,
             description="The language model to use for summarizing the text.",
         )
         focus: str = SchemaField(
@@ -1538,7 +1534,7 @@ class AIConversationBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default=DEFAULT_LLM_MODEL,
+            default=LlmModel.GPT4O,
             description="The language model to use for the conversation.",
         )
         credentials: AICredentials = AICredentialsField()
@@ -1576,7 +1572,7 @@ class AIConversationBlock(AIBlockBase):
                     },
                     {"role": "user", "content": "Where was it played?"},
                 ],
-                "model": DEFAULT_LLM_MODEL,
+                "model": LlmModel.GPT4O,
                 "credentials": TEST_CREDENTIALS_INPUT,
             },
             test_credentials=TEST_CREDENTIALS,
@@ -1639,7 +1635,7 @@ class AIListGeneratorBlock(AIBlockBase):
         )
         model: LlmModel = SchemaField(
             title="LLM Model",
-            default=DEFAULT_LLM_MODEL,
+            default=LlmModel.GPT4O,
             description="The language model to use for generating the list.",
             advanced=True,
         )
@@ -1696,7 +1692,7 @@ class AIListGeneratorBlock(AIBlockBase):
                     "drawing explorers to uncover its mysteries. Each planet showcases the limitless possibilities of "
                     "fictional worlds."
                 ),
-                "model": DEFAULT_LLM_MODEL,
+                "model": LlmModel.GPT4O,
                 "credentials": TEST_CREDENTIALS_INPUT,
                 "max_retries": 3,
                 "force_json_output": False,

autogpt_platform/backend/backend/blocks/search.py

@@ -18,7 +18,6 @@ from backend.data.model import (
     SchemaField,
 )
 from backend.integrations.providers import ProviderName
-from backend.util.request import DEFAULT_USER_AGENT
 
 
 class GetWikipediaSummaryBlock(Block, GetRequest):
@@ -40,27 +39,17 @@ class GetWikipediaSummaryBlock(Block, GetRequest):
             output_schema=GetWikipediaSummaryBlock.Output,
             test_input={"topic": "Artificial Intelligence"},
             test_output=("summary", "summary content"),
-            test_mock={
-                "get_request": lambda url, headers, json: {"extract": "summary content"}
-            },
+            test_mock={"get_request": lambda url, json: {"extract": "summary content"}},
         )
 
     async def run(self, input_data: Input, **kwargs) -> BlockOutput:
         topic = input_data.topic
-        # URL-encode the topic to handle spaces and special characters
-        encoded_topic = quote(topic, safe="")
-        url = f"https://en.wikipedia.org/api/rest_v1/page/summary/{encoded_topic}"
-
-        # Set headers per Wikimedia robot policy (https://w.wiki/4wJS)
-        # - User-Agent: Required, must identify the bot
-        # - Accept-Encoding: gzip recommended to reduce bandwidth
-        headers = {
-            "User-Agent": DEFAULT_USER_AGENT,
-            "Accept-Encoding": "gzip, deflate",
-        }
+        url = f"https://en.wikipedia.org/api/rest_v1/page/summary/{topic}"
 
+        # Note: User-Agent is now automatically set by the request library
+        # to comply with Wikimedia's robot policy (https://w.wiki/4wJS)
         try:
-            response = await self.get_request(url, headers=headers, json=True)
+            response = await self.get_request(url, json=True)
             if "extract" not in response:
                 raise ValueError(f"Unable to parse Wikipedia response: {response}")
             yield "summary", response["extract"]

autogpt_platform/backend/backend/blocks/smart_decision_maker.py

@@ -226,7 +226,7 @@ class SmartDecisionMakerBlock(Block):
         )
         model: llm.LlmModel = SchemaField(
             title="LLM Model",
-            default=llm.DEFAULT_LLM_MODEL,
+            default=llm.LlmModel.GPT4O,
             description="The language model to use for answering the prompt.",
             advanced=False,
         )
@@ -391,12 +391,8 @@ class SmartDecisionMakerBlock(Block):
         """
         block = sink_node.block
 
-        # Use custom name from node metadata if set, otherwise fall back to block.name
-        custom_name = sink_node.metadata.get("customized_name")
-        tool_name = custom_name if custom_name else block.name
-
         tool_function: dict[str, Any] = {
-            "name": SmartDecisionMakerBlock.cleanup(tool_name),
+            "name": SmartDecisionMakerBlock.cleanup(block.name),
             "description": block.description,
         }
         sink_block_input_schema = block.input_schema
@@ -493,24 +489,14 @@ class SmartDecisionMakerBlock(Block):
                 f"Sink graph metadata not found: {graph_id} {graph_version}"
             )
 
-        # Use custom name from node metadata if set, otherwise fall back to graph name
-        custom_name = sink_node.metadata.get("customized_name")
-        tool_name = custom_name if custom_name else sink_graph_meta.name
-
         tool_function: dict[str, Any] = {
-            "name": SmartDecisionMakerBlock.cleanup(tool_name),
+            "name": SmartDecisionMakerBlock.cleanup(sink_graph_meta.name),
             "description": sink_graph_meta.description,
         }
 
         properties = {}
-        field_mapping = {}
 
         for link in links:
-            field_name = link.sink_name
-
-            clean_field_name = SmartDecisionMakerBlock.cleanup(field_name)
-            field_mapping[clean_field_name] = field_name
-
             sink_block_input_schema = sink_node.input_default["input_schema"]
             sink_block_properties = sink_block_input_schema.get("properties", {}).get(
                 link.sink_name, {}
@@ -520,7 +506,7 @@ class SmartDecisionMakerBlock(Block):
                 if "description" in sink_block_properties
                 else f"The {link.sink_name} of the tool"
             )
-            properties[clean_field_name] = {
+            properties[link.sink_name] = {
                 "type": "string",
                 "description": description,
                 "default": json.dumps(sink_block_properties.get("default", None)),
@@ -533,7 +519,7 @@ class SmartDecisionMakerBlock(Block):
             "strict": True,
         }
 
-        tool_function["_field_mapping"] = field_mapping
+        # Store node info for later use in output processing
         tool_function["_sink_node_id"] = sink_node.id
 
         return {"type": "function", "function": tool_function}
@@ -989,28 +975,10 @@ class SmartDecisionMakerBlock(Block):
         graph_version: int,
         execution_context: ExecutionContext,
         execution_processor: "ExecutionProcessor",
-        nodes_to_skip: set[str] | None = None,
         **kwargs,
     ) -> BlockOutput:
 
         tool_functions = await self._create_tool_node_signatures(node_id)
-        original_tool_count = len(tool_functions)
-
-        # Filter out tools for nodes that should be skipped (e.g., missing optional credentials)
-        if nodes_to_skip:
-            tool_functions = [
-                tf
-                for tf in tool_functions
-                if tf.get("function", {}).get("_sink_node_id") not in nodes_to_skip
-            ]
-
-            # Only raise error if we had tools but they were all filtered out
-            if original_tool_count > 0 and not tool_functions:
-                raise ValueError(
-                    "No available tools to execute - all downstream nodes are unavailable "
-                    "(possibly due to missing optional credentials)"
-                )
-
         yield "tool_functions", json.dumps(tool_functions)
 
         conversation_history = input_data.conversation_history or []
@@ -1161,9 +1129,8 @@ class SmartDecisionMakerBlock(Block):
                 original_field_name = field_mapping.get(clean_arg_name, clean_arg_name)
                 arg_value = tool_args.get(clean_arg_name)
 
-                # Use original_field_name directly (not sanitized) to match link sink_name
-                # The field_mapping already translates from LLM's cleaned names to original names
-                emit_key = f"tools_^_{sink_node_id}_~_{original_field_name}"
+                sanitized_arg_name = self.cleanup(original_field_name)
+                emit_key = f"tools_^_{sink_node_id}_~_{sanitized_arg_name}"
 
                 logger.debug(
                     "[SmartDecisionMakerBlock|geid:%s|neid:%s] emit %s",

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

@@ -196,15 +196,6 @@ class TestXMLParserBlockSecurity:
             async for _ in block.run(XMLParserBlock.Input(input_xml=large_xml)):
                 pass
 
-    async def test_rejects_text_outside_root(self):
-        """Ensure parser surfaces readable errors for invalid root text."""
-        block = XMLParserBlock()
-        invalid_xml = "<root><child>value</child></root> trailing"
-
-        with pytest.raises(ValueError, match="text outside the root element"):
-            async for _ in block.run(XMLParserBlock.Input(input_xml=invalid_xml)):
-                pass
-
 
 class TestStoreMediaFileSecurity:
     """Test file storage security limits."""

autogpt_platform/backend/backend/blocks/test/test_llm.py

@@ -28,7 +28,7 @@ class TestLLMStatsTracking:
 
             response = await llm.llm_call(
                 credentials=llm.TEST_CREDENTIALS,
-                llm_model=llm.DEFAULT_LLM_MODEL,
+                llm_model=llm.LlmModel.GPT4O,
                 prompt=[{"role": "user", "content": "Hello"}],
                 max_tokens=100,
             )
@@ -65,7 +65,7 @@ class TestLLMStatsTracking:
         input_data = llm.AIStructuredResponseGeneratorBlock.Input(
             prompt="Test prompt",
             expected_format={"key1": "desc1", "key2": "desc2"},
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore  # type: ignore
         )
 
@@ -109,7 +109,7 @@ class TestLLMStatsTracking:
         # Run the block
         input_data = llm.AITextGeneratorBlock.Input(
             prompt="Generate text",
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
         )
 
@@ -170,7 +170,7 @@ class TestLLMStatsTracking:
         input_data = llm.AIStructuredResponseGeneratorBlock.Input(
             prompt="Test prompt",
             expected_format={"key1": "desc1", "key2": "desc2"},
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
             retry=2,
         )
@@ -228,7 +228,7 @@ class TestLLMStatsTracking:
 
         input_data = llm.AITextSummarizerBlock.Input(
             text=long_text,
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
             max_tokens=100,  # Small chunks
             chunk_overlap=10,
@@ -299,7 +299,7 @@ class TestLLMStatsTracking:
             # Test with very short text (should only need 1 chunk + 1 final summary)
             input_data = llm.AITextSummarizerBlock.Input(
                 text="This is a short text.",
-                model=llm.DEFAULT_LLM_MODEL,
+                model=llm.LlmModel.GPT4O,
                 credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
                 max_tokens=1000,  # Large enough to avoid chunking
             )
@@ -346,7 +346,7 @@ class TestLLMStatsTracking:
                 {"role": "assistant", "content": "Hi there!"},
                 {"role": "user", "content": "How are you?"},
             ],
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
         )
 
@@ -387,7 +387,7 @@ class TestLLMStatsTracking:
         # Run the block
         input_data = llm.AIListGeneratorBlock.Input(
             focus="test items",
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
             max_retries=3,
         )
@@ -469,7 +469,7 @@ class TestLLMStatsTracking:
         input_data = llm.AIStructuredResponseGeneratorBlock.Input(
             prompt="Test",
             expected_format={"result": "desc"},
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
         )
 
@@ -513,7 +513,7 @@ class TestAITextSummarizerValidation:
         # Create input data
         input_data = llm.AITextSummarizerBlock.Input(
             text="Some text to summarize",
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
             style=llm.SummaryStyle.BULLET_POINTS,
         )
@@ -558,7 +558,7 @@ class TestAITextSummarizerValidation:
         # Create input data
         input_data = llm.AITextSummarizerBlock.Input(
             text="Some text to summarize",
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
             style=llm.SummaryStyle.BULLET_POINTS,
             max_tokens=1000,
@@ -593,7 +593,7 @@ class TestAITextSummarizerValidation:
         # Create input data
         input_data = llm.AITextSummarizerBlock.Input(
             text="Some text to summarize",
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
         )
 
@@ -623,7 +623,7 @@ class TestAITextSummarizerValidation:
         # Create input data
         input_data = llm.AITextSummarizerBlock.Input(
             text="Some text to summarize",
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
             max_tokens=1000,
         )
@@ -654,7 +654,7 @@ class TestAITextSummarizerValidation:
         # Create input data
         input_data = llm.AITextSummarizerBlock.Input(
             text="Some text to summarize",
-            model=llm.DEFAULT_LLM_MODEL,
+            model=llm.LlmModel.GPT4O,
             credentials=llm.TEST_CREDENTIALS_INPUT,  # type: ignore
         )
 

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

@@ -5,10 +5,10 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
-from backend.api.model import CreateGraph
-from backend.api.rest_api import AgentServer
 from backend.data.execution import ExecutionContext
 from backend.data.model import ProviderName, User
+from backend.server.model import CreateGraph
+from backend.server.rest_api import AgentServer
 from backend.usecases.sample import create_test_graph, create_test_user
 from backend.util.test import SpinTestServer, wait_execution
 
@@ -233,7 +233,7 @@ async def test_smart_decision_maker_tracks_llm_stats():
         # Create test input
         input_data = SmartDecisionMakerBlock.Input(
             prompt="Should I continue with this task?",
-            model=llm_module.DEFAULT_LLM_MODEL,
+            model=llm_module.LlmModel.GPT4O,
             credentials=llm_module.TEST_CREDENTIALS_INPUT,  # type: ignore
             agent_mode_max_iterations=0,
         )
@@ -335,7 +335,7 @@ async def test_smart_decision_maker_parameter_validation():
 
         input_data = SmartDecisionMakerBlock.Input(
             prompt="Search for keywords",
-            model=llm_module.DEFAULT_LLM_MODEL,
+            model=llm_module.LlmModel.GPT4O,
             credentials=llm_module.TEST_CREDENTIALS_INPUT,  # type: ignore
             retry=2,  # Set retry to 2 for testing
             agent_mode_max_iterations=0,
@@ -402,7 +402,7 @@ async def test_smart_decision_maker_parameter_validation():
 
         input_data = SmartDecisionMakerBlock.Input(
             prompt="Search for keywords",
-            model=llm_module.DEFAULT_LLM_MODEL,
+            model=llm_module.LlmModel.GPT4O,
             credentials=llm_module.TEST_CREDENTIALS_INPUT,  # type: ignore
             agent_mode_max_iterations=0,
         )
@@ -462,7 +462,7 @@ async def test_smart_decision_maker_parameter_validation():
 
         input_data = SmartDecisionMakerBlock.Input(
             prompt="Search for keywords",
-            model=llm_module.DEFAULT_LLM_MODEL,
+            model=llm_module.LlmModel.GPT4O,
             credentials=llm_module.TEST_CREDENTIALS_INPUT,  # type: ignore
             agent_mode_max_iterations=0,
         )
@@ -526,7 +526,7 @@ async def test_smart_decision_maker_parameter_validation():
 
         input_data = SmartDecisionMakerBlock.Input(
             prompt="Search for keywords",
-            model=llm_module.DEFAULT_LLM_MODEL,
+            model=llm_module.LlmModel.GPT4O,
             credentials=llm_module.TEST_CREDENTIALS_INPUT,  # type: ignore
             agent_mode_max_iterations=0,
         )
@@ -648,7 +648,7 @@ async def test_smart_decision_maker_raw_response_conversion():
 
         input_data = SmartDecisionMakerBlock.Input(
             prompt="Test prompt",
-            model=llm_module.DEFAULT_LLM_MODEL,
+            model=llm_module.LlmModel.GPT4O,
             credentials=llm_module.TEST_CREDENTIALS_INPUT,  # type: ignore
             retry=2,
             agent_mode_max_iterations=0,
@@ -722,7 +722,7 @@ async def test_smart_decision_maker_raw_response_conversion():
     ):
         input_data = SmartDecisionMakerBlock.Input(
             prompt="Simple prompt",
-            model=llm_module.DEFAULT_LLM_MODEL,
+            model=llm_module.LlmModel.GPT4O,
             credentials=llm_module.TEST_CREDENTIALS_INPUT,  # type: ignore
             agent_mode_max_iterations=0,
         )
@@ -778,7 +778,7 @@ async def test_smart_decision_maker_raw_response_conversion():
     ):
         input_data = SmartDecisionMakerBlock.Input(
             prompt="Another test",
-            model=llm_module.DEFAULT_LLM_MODEL,
+            model=llm_module.LlmModel.GPT4O,
             credentials=llm_module.TEST_CREDENTIALS_INPUT,  # type: ignore
             agent_mode_max_iterations=0,
         )
@@ -931,7 +931,7 @@ async def test_smart_decision_maker_agent_mode():
         # Test agent mode with max_iterations = 3
         input_data = SmartDecisionMakerBlock.Input(
             prompt="Complete this task using tools",
-            model=llm_module.DEFAULT_LLM_MODEL,
+            model=llm_module.LlmModel.GPT4O,
             credentials=llm_module.TEST_CREDENTIALS_INPUT,  # type: ignore
             agent_mode_max_iterations=3,  # Enable agent mode with 3 max iterations
         )
@@ -1020,7 +1020,7 @@ async def test_smart_decision_maker_traditional_mode_default():
         # Test default behavior (traditional mode)
         input_data = SmartDecisionMakerBlock.Input(
             prompt="Test prompt",
-            model=llm_module.DEFAULT_LLM_MODEL,
+            model=llm_module.LlmModel.GPT4O,
             credentials=llm_module.TEST_CREDENTIALS_INPUT,  # type: ignore
             agent_mode_max_iterations=0,  # Traditional mode
         )
@@ -1057,153 +1057,3 @@ async def test_smart_decision_maker_traditional_mode_default():
         )  # Should yield individual tool parameters
         assert "tools_^_test-sink-node-id_~_max_keyword_difficulty" in outputs
         assert "conversations" in outputs
-
-
-@pytest.mark.asyncio
-async def test_smart_decision_maker_uses_customized_name_for_blocks():
-    """Test that SmartDecisionMakerBlock uses customized_name from node metadata for tool names."""
-    from unittest.mock import MagicMock
-
-    from backend.blocks.basic import StoreValueBlock
-    from backend.blocks.smart_decision_maker import SmartDecisionMakerBlock
-    from backend.data.graph import Link, Node
-
-    # Create a mock node with customized_name in metadata
-    mock_node = MagicMock(spec=Node)
-    mock_node.id = "test-node-id"
-    mock_node.block_id = StoreValueBlock().id
-    mock_node.metadata = {"customized_name": "My Custom Tool Name"}
-    mock_node.block = StoreValueBlock()
-
-    # Create a mock link
-    mock_link = MagicMock(spec=Link)
-    mock_link.sink_name = "input"
-
-    # Call the function directly
-    result = await SmartDecisionMakerBlock._create_block_function_signature(
-        mock_node, [mock_link]
-    )
-
-    # Verify the tool name uses the customized name (cleaned up)
-    assert result["type"] == "function"
-    assert result["function"]["name"] == "my_custom_tool_name"  # Cleaned version
-    assert result["function"]["_sink_node_id"] == "test-node-id"
-
-
-@pytest.mark.asyncio
-async def test_smart_decision_maker_falls_back_to_block_name():
-    """Test that SmartDecisionMakerBlock falls back to block.name when no customized_name."""
-    from unittest.mock import MagicMock
-
-    from backend.blocks.basic import StoreValueBlock
-    from backend.blocks.smart_decision_maker import SmartDecisionMakerBlock
-    from backend.data.graph import Link, Node
-
-    # Create a mock node without customized_name
-    mock_node = MagicMock(spec=Node)
-    mock_node.id = "test-node-id"
-    mock_node.block_id = StoreValueBlock().id
-    mock_node.metadata = {}  # No customized_name
-    mock_node.block = StoreValueBlock()
-
-    # Create a mock link
-    mock_link = MagicMock(spec=Link)
-    mock_link.sink_name = "input"
-
-    # Call the function directly
-    result = await SmartDecisionMakerBlock._create_block_function_signature(
-        mock_node, [mock_link]
-    )
-
-    # Verify the tool name uses the block's default name
-    assert result["type"] == "function"
-    assert result["function"]["name"] == "storevalueblock"  # Default block name cleaned
-    assert result["function"]["_sink_node_id"] == "test-node-id"
-
-
-@pytest.mark.asyncio
-async def test_smart_decision_maker_uses_customized_name_for_agents():
-    """Test that SmartDecisionMakerBlock uses customized_name from metadata for agent nodes."""
-    from unittest.mock import AsyncMock, MagicMock, patch
-
-    from backend.blocks.smart_decision_maker import SmartDecisionMakerBlock
-    from backend.data.graph import Link, Node
-
-    # Create a mock node with customized_name in metadata
-    mock_node = MagicMock(spec=Node)
-    mock_node.id = "test-agent-node-id"
-    mock_node.metadata = {"customized_name": "My Custom Agent"}
-    mock_node.input_default = {
-        "graph_id": "test-graph-id",
-        "graph_version": 1,
-        "input_schema": {"properties": {"test_input": {"description": "Test input"}}},
-    }
-
-    # Create a mock link
-    mock_link = MagicMock(spec=Link)
-    mock_link.sink_name = "test_input"
-
-    # Mock the database client
-    mock_graph_meta = MagicMock()
-    mock_graph_meta.name = "Original Agent Name"
-    mock_graph_meta.description = "Agent description"
-
-    mock_db_client = AsyncMock()
-    mock_db_client.get_graph_metadata.return_value = mock_graph_meta
-
-    with patch(
-        "backend.blocks.smart_decision_maker.get_database_manager_async_client",
-        return_value=mock_db_client,
-    ):
-        result = await SmartDecisionMakerBlock._create_agent_function_signature(
-            mock_node, [mock_link]
-        )
-
-    # Verify the tool name uses the customized name (cleaned up)
-    assert result["type"] == "function"
-    assert result["function"]["name"] == "my_custom_agent"  # Cleaned version
-    assert result["function"]["_sink_node_id"] == "test-agent-node-id"
-
-
-@pytest.mark.asyncio
-async def test_smart_decision_maker_agent_falls_back_to_graph_name():
-    """Test that agent node falls back to graph name when no customized_name."""
-    from unittest.mock import AsyncMock, MagicMock, patch
-
-    from backend.blocks.smart_decision_maker import SmartDecisionMakerBlock
-    from backend.data.graph import Link, Node
-
-    # Create a mock node without customized_name
-    mock_node = MagicMock(spec=Node)
-    mock_node.id = "test-agent-node-id"
-    mock_node.metadata = {}  # No customized_name
-    mock_node.input_default = {
-        "graph_id": "test-graph-id",
-        "graph_version": 1,
-        "input_schema": {"properties": {"test_input": {"description": "Test input"}}},
-    }
-
-    # Create a mock link
-    mock_link = MagicMock(spec=Link)
-    mock_link.sink_name = "test_input"
-
-    # Mock the database client
-    mock_graph_meta = MagicMock()
-    mock_graph_meta.name = "Original Agent Name"
-    mock_graph_meta.description = "Agent description"
-
-    mock_db_client = AsyncMock()
-    mock_db_client.get_graph_metadata.return_value = mock_graph_meta
-
-    with patch(
-        "backend.blocks.smart_decision_maker.get_database_manager_async_client",
-        return_value=mock_db_client,
-    ):
-        result = await SmartDecisionMakerBlock._create_agent_function_signature(
-            mock_node, [mock_link]
-        )
-
-    # Verify the tool name uses the graph's default name
-    assert result["type"] == "function"
-    assert result["function"]["name"] == "original_agent_name"  # Graph name cleaned
-    assert result["function"]["_sink_node_id"] == "test-agent-node-id"

autogpt_platform/backend/backend/blocks/test/test_smart_decision_maker_dict.py

@@ -15,7 +15,6 @@ async def test_smart_decision_maker_handles_dynamic_dict_fields():
     mock_node.block = CreateDictionaryBlock()
     mock_node.block_id = CreateDictionaryBlock().id
     mock_node.input_default = {}
-    mock_node.metadata = {}
 
     # Create mock links with dynamic dictionary fields
     mock_links = [
@@ -78,7 +77,6 @@ async def test_smart_decision_maker_handles_dynamic_list_fields():
     mock_node.block = AddToListBlock()
     mock_node.block_id = AddToListBlock().id
     mock_node.input_default = {}
-    mock_node.metadata = {}
 
     # Create mock links with dynamic list fields
     mock_links = [

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

@@ -44,7 +44,6 @@ async def test_create_block_function_signature_with_dict_fields():
     mock_node.block = CreateDictionaryBlock()
     mock_node.block_id = CreateDictionaryBlock().id
     mock_node.input_default = {}
-    mock_node.metadata = {}
 
     # Create mock links with dynamic dictionary fields (source sanitized, sink original)
     mock_links = [
@@ -107,7 +106,6 @@ async def test_create_block_function_signature_with_list_fields():
     mock_node.block = AddToListBlock()
     mock_node.block_id = AddToListBlock().id
     mock_node.input_default = {}
-    mock_node.metadata = {}
 
     # Create mock links with dynamic list fields
     mock_links = [
@@ -161,7 +159,6 @@ async def test_create_block_function_signature_with_object_fields():
     mock_node.block = MatchTextPatternBlock()
     mock_node.block_id = MatchTextPatternBlock().id
     mock_node.input_default = {}
-    mock_node.metadata = {}
 
     # Create mock links with dynamic object fields
     mock_links = [
@@ -211,13 +208,11 @@ async def test_create_tool_node_signatures():
         mock_dict_node.block = CreateDictionaryBlock()
         mock_dict_node.block_id = CreateDictionaryBlock().id
         mock_dict_node.input_default = {}
-        mock_dict_node.metadata = {}
 
         mock_list_node = Mock()
         mock_list_node.block = AddToListBlock()
         mock_list_node.block_id = AddToListBlock().id
         mock_list_node.input_default = {}
-        mock_list_node.metadata = {}
 
         # Mock links with dynamic fields
         dict_link1 = Mock(
@@ -378,7 +373,7 @@ async def test_output_yielding_with_dynamic_fields():
             input_data = block.input_schema(
                 prompt="Create a user dictionary",
                 credentials=llm.TEST_CREDENTIALS_INPUT,
-                model=llm.DEFAULT_LLM_MODEL,
+                model=llm.LlmModel.GPT4O,
                 agent_mode_max_iterations=0,  # Use traditional mode to test output yielding
             )
 
@@ -428,7 +423,6 @@ async def test_mixed_regular_and_dynamic_fields():
     mock_node.block.name = "TestBlock"
     mock_node.block.description = "A test block"
     mock_node.block.input_schema = Mock()
-    mock_node.metadata = {}
 
     # Mock the get_field_schema to return a proper schema for regular fields
     def get_field_schema(field_name):
@@ -600,7 +594,7 @@ async def test_validation_errors_dont_pollute_conversation():
                 input_data = block.input_schema(
                     prompt="Test prompt",
                     credentials=llm.TEST_CREDENTIALS_INPUT,
-                    model=llm.DEFAULT_LLM_MODEL,
+                    model=llm.LlmModel.GPT4O,
                     retry=3,  # Allow retries
                     agent_mode_max_iterations=1,
                 )

autogpt_platform/backend/backend/blocks/wordpress/__init__.py

@@ -1,3 +1,3 @@
-from .blog import WordPressCreatePostBlock, WordPressGetAllPostsBlock
+from .blog import WordPressCreatePostBlock
 
-__all__ = ["WordPressCreatePostBlock", "WordPressGetAllPostsBlock"]
+__all__ = ["WordPressCreatePostBlock"]

autogpt_platform/backend/backend/blocks/wordpress/_api.py

@@ -161,7 +161,7 @@ async def oauth_exchange_code_for_tokens(
         grant_type="authorization_code",
     ).model_dump(exclude_none=True)
 
-    response = await Requests(raise_for_status=False).post(
+    response = await Requests().post(
         f"{WORDPRESS_BASE_URL}oauth2/token",
         headers=headers,
         data=data,
@@ -205,7 +205,7 @@ async def oauth_refresh_tokens(
         grant_type="refresh_token",
     ).model_dump(exclude_none=True)
 
-    response = await Requests(raise_for_status=False).post(
+    response = await Requests().post(
         f"{WORDPRESS_BASE_URL}oauth2/token",
         headers=headers,
         data=data,
@@ -252,7 +252,7 @@ async def validate_token(
         "token": token,
     }
 
-    response = await Requests(raise_for_status=False).get(
+    response = await Requests().get(
         f"{WORDPRESS_BASE_URL}oauth2/token-info",
         params=params,
     )
@@ -296,7 +296,7 @@ async def make_api_request(
 
     url = f"{WORDPRESS_BASE_URL.rstrip('/')}{endpoint}"
 
-    request_method = getattr(Requests(raise_for_status=False), method.lower())
+    request_method = getattr(Requests(), method.lower())
     response = await request_method(
         url,
         headers=headers,
@@ -476,7 +476,6 @@ async def create_post(
         data["tags"] = ",".join(str(t) for t in data["tags"])
 
     # Make the API request
-    site = normalize_site(site)
     endpoint = f"/rest/v1.1/sites/{site}/posts/new"
 
     headers = {
@@ -484,7 +483,7 @@ async def create_post(
         "Content-Type": "application/x-www-form-urlencoded",
     }
 
-    response = await Requests(raise_for_status=False).post(
+    response = await Requests().post(
         f"{WORDPRESS_BASE_URL.rstrip('/')}{endpoint}",
         headers=headers,
         data=data,
@@ -500,132 +499,3 @@ async def create_post(
     )
     error_message = error_data.get("message", response.text)
     raise ValueError(f"Failed to create post: {response.status} - {error_message}")
-
-
-class Post(BaseModel):
-    """Response model for individual posts in a posts list response.
-
-    This is a simplified version compared to PostResponse, as the list endpoint
-    returns less detailed information than the create/get single post endpoints.
-    """
-
-    ID: int
-    site_ID: int
-    author: PostAuthor
-    date: datetime
-    modified: datetime
-    title: str
-    URL: str
-    short_URL: str
-    content: str | None = None
-    excerpt: str | None = None
-    slug: str
-    guid: str
-    status: str
-    sticky: bool
-    password: str | None = ""
-    parent: Union[Dict[str, Any], bool, None] = None
-    type: str
-    discussion: Dict[str, Union[str, bool, int]] | None = None
-    likes_enabled: bool | None = None
-    sharing_enabled: bool | None = None
-    like_count: int | None = None
-    i_like: bool | None = None
-    is_reblogged: bool | None = None
-    is_following: bool | None = None
-    global_ID: str | None = None
-    featured_image: str | None = None
-    post_thumbnail: Dict[str, Any] | None = None
-    format: str | None = None
-    geo: Union[Dict[str, Any], bool, None] = None
-    menu_order: int | None = None
-    page_template: str | None = None
-    publicize_URLs: List[str] | None = None
-    terms: Dict[str, Dict[str, Any]] | None = None
-    tags: Dict[str, Dict[str, Any]] | None = None
-    categories: Dict[str, Dict[str, Any]] | None = None
-    attachments: Dict[str, Dict[str, Any]] | None = None
-    attachment_count: int | None = None
-    metadata: List[Dict[str, Any]] | None = None
-    meta: Dict[str, Any] | None = None
-    capabilities: Dict[str, bool] | None = None
-    revisions: List[int] | None = None
-    other_URLs: Dict[str, Any] | None = None
-
-
-class PostsResponse(BaseModel):
-    """Response model for WordPress posts list."""
-
-    found: int
-    posts: List[Post]
-    meta: Dict[str, Any]
-
-
-def normalize_site(site: str) -> str:
-    """
-    Normalize a site identifier by stripping protocol and trailing slashes.
-
-    Args:
-        site: Site URL, domain, or ID (e.g., "https://myblog.wordpress.com/", "myblog.wordpress.com", "123456789")
-
-    Returns:
-        Normalized site identifier (domain or ID only)
-    """
-    site = site.strip()
-    if site.startswith("https://"):
-        site = site[8:]
-    elif site.startswith("http://"):
-        site = site[7:]
-    return site.rstrip("/")
-
-
-async def get_posts(
-    credentials: Credentials,
-    site: str,
-    status: PostStatus | None = None,
-    number: int = 100,
-    offset: int = 0,
-) -> PostsResponse:
-    """
-    Get posts from a WordPress site.
-
-    Args:
-        credentials: OAuth credentials
-        site: Site ID or domain (e.g., "myblog.wordpress.com" or "123456789")
-        status: Filter by post status using PostStatus enum, or None for all
-        number: Number of posts to retrieve (max 100)
-        offset: Number of posts to skip (for pagination)
-
-    Returns:
-        PostsResponse with the list of posts
-    """
-    site = normalize_site(site)
-    endpoint = f"/rest/v1.1/sites/{site}/posts"
-
-    headers = {
-        "Authorization": credentials.auth_header(),
-    }
-
-    params: Dict[str, Any] = {
-        "number": max(1, min(number, 100)),  # 1–100 posts per request
-        "offset": offset,
-    }
-
-    if status:
-        params["status"] = status.value
-    response = await Requests(raise_for_status=False).get(
-        f"{WORDPRESS_BASE_URL.rstrip('/')}{endpoint}",
-        headers=headers,
-        params=params,
-    )
-
-    if response.ok:
-        return PostsResponse.model_validate(response.json())
-
-    error_data = (
-        response.json()
-        if response.headers.get("content-type", "").startswith("application/json")
-        else {}
-    )
-    error_message = error_data.get("message", response.text)
-    raise ValueError(f"Failed to get posts: {response.status} - {error_message}")

autogpt_platform/backend/backend/blocks/wordpress/blog.py

@@ -9,15 +9,7 @@ from backend.sdk import (
     SchemaField,
 )
 
-from ._api import (
-    CreatePostRequest,
-    Post,
-    PostResponse,
-    PostsResponse,
-    PostStatus,
-    create_post,
-    get_posts,
-)
+from ._api import CreatePostRequest, PostResponse, PostStatus, create_post
 from ._config import wordpress
 
 
@@ -57,15 +49,8 @@ class WordPressCreatePostBlock(Block):
         media_urls: list[str] = SchemaField(
             description="URLs of images to sideload and attach to the post", default=[]
         )
-        publish_as_draft: bool = SchemaField(
-            description="If True, publishes the post as a draft. If False, publishes it publicly.",
-            default=False,
-        )
 
     class Output(BlockSchemaOutput):
-        site: str = SchemaField(
-            description="The site ID or domain (pass-through for chaining with other blocks)"
-        )
         post_id: int = SchemaField(description="The ID of the created post")
         post_url: str = SchemaField(description="The full URL of the created post")
         short_url: str = SchemaField(description="The shortened wp.me URL")
@@ -93,9 +78,7 @@ class WordPressCreatePostBlock(Block):
             tags=input_data.tags,
             featured_image=input_data.featured_image,
             media_urls=input_data.media_urls,
-            status=(
-                PostStatus.DRAFT if input_data.publish_as_draft else PostStatus.PUBLISH
-            ),
+            status=PostStatus.PUBLISH,
         )
 
         post_response: PostResponse = await create_post(
@@ -104,69 +87,7 @@ class WordPressCreatePostBlock(Block):
             post_data=post_request,
         )
 
-        yield "site", input_data.site
         yield "post_id", post_response.ID
         yield "post_url", post_response.URL
         yield "short_url", post_response.short_URL
         yield "post_data", post_response.model_dump()
-
-
-class WordPressGetAllPostsBlock(Block):
-    """
-    Fetches all posts from a WordPress.com site or Jetpack-enabled site.
-    Supports filtering by status and pagination.
-    """
-
-    class Input(BlockSchemaInput):
-        credentials: CredentialsMetaInput = wordpress.credentials_field()
-        site: str = SchemaField(
-            description="Site ID or domain (e.g., 'myblog.wordpress.com' or '123456789')"
-        )
-        status: PostStatus | None = SchemaField(
-            description="Filter by post status, or None for all",
-            default=None,
-        )
-        number: int = SchemaField(
-            description="Number of posts to retrieve (max 100 per request)", default=20
-        )
-        offset: int = SchemaField(
-            description="Number of posts to skip (for pagination)", default=0
-        )
-
-    class Output(BlockSchemaOutput):
-        site: str = SchemaField(
-            description="The site ID or domain (pass-through for chaining with other blocks)"
-        )
-        found: int = SchemaField(description="Total number of posts found")
-        posts: list[Post] = SchemaField(
-            description="List of post objects with their details"
-        )
-        post: Post = SchemaField(
-            description="Individual post object (yielded for each post)"
-        )
-
-    def __init__(self):
-        super().__init__(
-            id="97728fa7-7f6f-4789-ba0c-f2c114119536",
-            description="Fetch all posts from WordPress.com or Jetpack sites",
-            categories={BlockCategory.SOCIAL},
-            input_schema=self.Input,
-            output_schema=self.Output,
-        )
-
-    async def run(
-        self, input_data: Input, *, credentials: Credentials, **kwargs
-    ) -> BlockOutput:
-        posts_response: PostsResponse = await get_posts(
-            credentials=credentials,
-            site=input_data.site,
-            status=input_data.status,
-            number=input_data.number,
-            offset=input_data.offset,
-        )
-
-        yield "site", input_data.site
-        yield "found", posts_response.found
-        yield "posts", posts_response.posts
-        for post in posts_response.posts:
-            yield "post", post

autogpt_platform/backend/backend/blocks/xml_parser.py

@@ -1,5 +1,5 @@
 from gravitasml.parser import Parser
-from gravitasml.token import Token, tokenize
+from gravitasml.token import tokenize
 
 from backend.data.block import Block, BlockOutput, BlockSchemaInput, BlockSchemaOutput
 from backend.data.model import SchemaField
@@ -25,38 +25,6 @@ class XMLParserBlock(Block):
             ],
         )
 
-    @staticmethod
-    def _validate_tokens(tokens: list[Token]) -> None:
-        """Ensure the XML has a single root element and no stray text."""
-        if not tokens:
-            raise ValueError("XML input is empty.")
-
-        depth = 0
-        root_seen = False
-
-        for token in tokens:
-            if token.type == "TAG_OPEN":
-                if depth == 0 and root_seen:
-                    raise ValueError("XML must have a single root element.")
-                depth += 1
-                if depth == 1:
-                    root_seen = True
-            elif token.type == "TAG_CLOSE":
-                depth -= 1
-                if depth < 0:
-                    raise SyntaxError("Unexpected closing tag in XML input.")
-            elif token.type in {"TEXT", "ESCAPE"}:
-                if depth == 0 and token.value:
-                    raise ValueError(
-                        "XML contains text outside the root element; "
-                        "wrap content in a single root tag."
-                    )
-
-        if depth != 0:
-            raise SyntaxError("Unclosed tag detected in XML input.")
-        if not root_seen:
-            raise ValueError("XML must include a root element.")
-
     async def run(self, input_data: Input, **kwargs) -> BlockOutput:
         # Security fix: Add size limits to prevent XML bomb attacks
         MAX_XML_SIZE = 10 * 1024 * 1024  # 10MB limit for XML input
@@ -67,9 +35,7 @@ class XMLParserBlock(Block):
             )
 
         try:
-            tokens = list(tokenize(input_data.input_xml))
-            self._validate_tokens(tokens)
-
+            tokens = tokenize(input_data.input_xml)
             parser = Parser(tokens)
             parsed_result = parser.parse()
             yield "parsed_xml", parsed_result

autogpt_platform/backend/backend/blocks/youtube.py

@@ -111,8 +111,6 @@ class TranscribeYoutubeVideoBlock(Block):
                 return parsed_url.path.split("/")[2]
             if parsed_url.path[:3] == "/v/":
                 return parsed_url.path.split("/")[2]
-            if parsed_url.path.startswith("/shorts/"):
-                return parsed_url.path.split("/")[2]
         raise ValueError(f"Invalid YouTube URL: {url}")
 
     def get_transcript(

autogpt_platform/backend/backend/cli.py

@@ -244,7 +244,11 @@ def websocket(server_address: str, graph_exec_id: str):
 
     import websockets.asyncio.client
 
-    from backend.api.ws_api import WSMessage, WSMethod, WSSubscribeGraphExecutionRequest
+    from backend.server.ws_api import (
+        WSMessage,
+        WSMethod,
+        WSSubscribeGraphExecutionRequest,
+    )
 
     async def send_message(server_address: str):
         uri = f"ws://{server_address}"

autogpt_platform/backend/backend/cli/generate_openapi_json.py

@@ -2,7 +2,7 @@
 """
 Script to generate OpenAPI JSON specification for the FastAPI app.
 
-This script imports the FastAPI app from backend.api.rest_api and outputs
+This script imports the FastAPI app from backend.server.rest_api and outputs
 the OpenAPI specification as JSON to stdout or a specified file.
 
 Usage:
@@ -46,7 +46,7 @@ def main(output: Path, pretty: bool):
 
 def get_openapi_schema():
     """Get the OpenAPI schema from the FastAPI app"""
-    from backend.api.rest_api import app
+    from backend.server.rest_api import app
 
     return app.openapi()
 

autogpt_platform/backend/backend/cli/oauth_tool.py

@@ -36,12 +36,13 @@ import secrets
 import sys
 import uuid
 from datetime import datetime
-from typing import Optional
+from typing import Optional, cast
 from urllib.parse import urlparse
 
 import click
 from autogpt_libs.api_key.keysmith import APIKeySmith
 from prisma.enums import APIKeyPermission
+from prisma.types import OAuthApplicationCreateInput
 
 keysmith = APIKeySmith()
 
@@ -834,19 +835,22 @@ async def create_test_app_in_db(
 
     # Insert into database
     app = await OAuthApplication.prisma().create(
-        data={
-            "id": creds["id"],
-            "name": creds["name"],
-            "description": creds["description"],
-            "clientId": creds["client_id"],
-            "clientSecret": creds["client_secret_hash"],
-            "clientSecretSalt": creds["client_secret_salt"],
-            "redirectUris": creds["redirect_uris"],
-            "grantTypes": creds["grant_types"],
-            "scopes": creds["scopes"],
-            "ownerId": owner_id,
-            "isActive": True,
-        }
+        data=cast(
+            OAuthApplicationCreateInput,
+            {
+                "id": creds["id"],
+                "name": creds["name"],
+                "description": creds["description"],
+                "clientId": creds["client_id"],
+                "clientSecret": creds["client_secret_hash"],
+                "clientSecretSalt": creds["client_secret_salt"],
+                "redirectUris": creds["redirect_uris"],
+                "grantTypes": creds["grant_types"],
+                "scopes": creds["scopes"],
+                "ownerId": owner_id,
+                "isActive": True,
+            },
+        )
     )
 
     click.echo(f"✓ Created test OAuth application: {app.clientId}")

autogpt_platform/backend/backend/data/__init__.py

@@ -1,4 +1,4 @@
-from backend.api.features.library.model import LibraryAgentPreset
+from backend.server.v2.library.model import LibraryAgentPreset
 
 from .graph import NodeModel
 from .integrations import Webhook  # noqa: F401

autogpt_platform/backend/backend/data/auth/api_key.py

@@ -1,12 +1,12 @@
 import logging
 import uuid
 from datetime import datetime, timezone
-from typing import Literal, Optional
+from typing import Literal, Optional, cast
 
 from autogpt_libs.api_key.keysmith import APIKeySmith
 from prisma.enums import APIKeyPermission, APIKeyStatus
 from prisma.models import APIKey as PrismaAPIKey
-from prisma.types import APIKeyWhereUniqueInput
+from prisma.types import APIKeyCreateInput, APIKeyWhereUniqueInput
 from pydantic import Field
 
 from backend.data.includes import MAX_USER_API_KEYS_FETCH
@@ -82,17 +82,20 @@ async def create_api_key(
     generated_key = keysmith.generate_key()
 
     saved_key_obj = await PrismaAPIKey.prisma().create(
-        data={
-            "id": str(uuid.uuid4()),
-            "name": name,
-            "head": generated_key.head,
-            "tail": generated_key.tail,
-            "hash": generated_key.hash,
-            "salt": generated_key.salt,
-            "permissions": [p for p in permissions],
-            "description": description,
-            "userId": user_id,
-        }
+        data=cast(
+            APIKeyCreateInput,
+            {
+                "id": str(uuid.uuid4()),
+                "name": name,
+                "head": generated_key.head,
+                "tail": generated_key.tail,
+                "hash": generated_key.hash,
+                "salt": generated_key.salt,
+                "permissions": [p for p in permissions],
+                "description": description,
+                "userId": user_id,
+            },
+        )
     )
 
     return APIKeyInfo.from_db(saved_key_obj), generated_key.key

autogpt_platform/backend/backend/data/auth/oauth.py

@@ -14,7 +14,7 @@ import logging
 import secrets
 import uuid
 from datetime import datetime, timedelta, timezone
-from typing import Literal, Optional
+from typing import Literal, Optional, cast
 
 from autogpt_libs.api_key.keysmith import APIKeySmith
 from prisma.enums import APIKeyPermission as APIPermission
@@ -22,7 +22,12 @@ from prisma.models import OAuthAccessToken as PrismaOAuthAccessToken
 from prisma.models import OAuthApplication as PrismaOAuthApplication
 from prisma.models import OAuthAuthorizationCode as PrismaOAuthAuthorizationCode
 from prisma.models import OAuthRefreshToken as PrismaOAuthRefreshToken
-from prisma.types import OAuthApplicationUpdateInput
+from prisma.types import (
+    OAuthAccessTokenCreateInput,
+    OAuthApplicationUpdateInput,
+    OAuthAuthorizationCodeCreateInput,
+    OAuthRefreshTokenCreateInput,
+)
 from pydantic import BaseModel, Field, SecretStr
 
 from .base import APIAuthorizationInfo
@@ -359,17 +364,20 @@ async def create_authorization_code(
     expires_at = now + AUTHORIZATION_CODE_TTL
 
     saved_code = await PrismaOAuthAuthorizationCode.prisma().create(
-        data={
-            "id": str(uuid.uuid4()),
-            "code": code,
-            "expiresAt": expires_at,
-            "applicationId": application_id,
-            "userId": user_id,
-            "scopes": [s for s in scopes],
-            "redirectUri": redirect_uri,
-            "codeChallenge": code_challenge,
-            "codeChallengeMethod": code_challenge_method,
-        }
+        data=cast(
+            OAuthAuthorizationCodeCreateInput,
+            {
+                "id": str(uuid.uuid4()),
+                "code": code,
+                "expiresAt": expires_at,
+                "applicationId": application_id,
+                "userId": user_id,
+                "scopes": [s for s in scopes],
+                "redirectUri": redirect_uri,
+                "codeChallenge": code_challenge,
+                "codeChallengeMethod": code_challenge_method,
+            },
+        )
     )
 
     return OAuthAuthorizationCodeInfo.from_db(saved_code)
@@ -490,14 +498,17 @@ async def create_access_token(
     expires_at = now + ACCESS_TOKEN_TTL
 
     saved_token = await PrismaOAuthAccessToken.prisma().create(
-        data={
-            "id": str(uuid.uuid4()),
-            "token": token_hash,  # SHA256 hash for direct lookup
-            "expiresAt": expires_at,
-            "applicationId": application_id,
-            "userId": user_id,
-            "scopes": [s for s in scopes],
-        }
+        data=cast(
+            OAuthAccessTokenCreateInput,
+            {
+                "id": str(uuid.uuid4()),
+                "token": token_hash,  # SHA256 hash for direct lookup
+                "expiresAt": expires_at,
+                "applicationId": application_id,
+                "userId": user_id,
+                "scopes": [s for s in scopes],
+            },
+        )
     )
 
     return OAuthAccessToken.from_db(saved_token, plaintext_token=plaintext_token)
@@ -607,14 +618,17 @@ async def create_refresh_token(
     expires_at = now + REFRESH_TOKEN_TTL
 
     saved_token = await PrismaOAuthRefreshToken.prisma().create(
-        data={
-            "id": str(uuid.uuid4()),
-            "token": token_hash,  # SHA256 hash for direct lookup
-            "expiresAt": expires_at,
-            "applicationId": application_id,
-            "userId": user_id,
-            "scopes": [s for s in scopes],
-        }
+        data=cast(
+            OAuthRefreshTokenCreateInput,
+            {
+                "id": str(uuid.uuid4()),
+                "token": token_hash,  # SHA256 hash for direct lookup
+                "expiresAt": expires_at,
+                "applicationId": application_id,
+                "userId": user_id,
+                "scopes": [s for s in scopes],
+            },
+        )
     )
 
     return OAuthRefreshToken.from_db(saved_token, plaintext_token=plaintext_token)

autogpt_platform/backend/backend/data/block.py

@@ -50,8 +50,6 @@ from .model import (
 logger = logging.getLogger(__name__)
 
 if TYPE_CHECKING:
-    from backend.data.execution import ExecutionContext
-
     from .graph import Link
 
 app_config = Config()
@@ -474,7 +472,6 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
         self.block_type = block_type
         self.webhook_config = webhook_config
         self.execution_stats: NodeExecutionStats = NodeExecutionStats()
-        self.requires_human_review: bool = False
 
         if self.webhook_config:
             if isinstance(self.webhook_config, BlockWebhookConfig):
@@ -617,77 +614,7 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
                     block_id=self.id,
                 ) from ex
 
-    async def is_block_exec_need_review(
-        self,
-        input_data: BlockInput,
-        *,
-        user_id: str,
-        node_exec_id: str,
-        graph_exec_id: str,
-        graph_id: str,
-        graph_version: int,
-        execution_context: "ExecutionContext",
-        **kwargs,
-    ) -> tuple[bool, BlockInput]:
-        """
-        Check if this block execution needs human review and handle the review process.
-
-        Returns:
-            Tuple of (should_pause, input_data_to_use)
-            - should_pause: True if execution should be paused for review
-            - input_data_to_use: The input data to use (may be modified by reviewer)
-        """
-        # Skip review if not required or safe mode is disabled
-        if not self.requires_human_review or not execution_context.safe_mode:
-            return False, input_data
-
-        from backend.blocks.helpers.review import HITLReviewHelper
-
-        # Handle the review request and get decision
-        decision = await HITLReviewHelper.handle_review_decision(
-            input_data=input_data,
-            user_id=user_id,
-            node_exec_id=node_exec_id,
-            graph_exec_id=graph_exec_id,
-            graph_id=graph_id,
-            graph_version=graph_version,
-            execution_context=execution_context,
-            block_name=self.name,
-            editable=True,
-        )
-
-        if decision is None:
-            # We're awaiting review - pause execution
-            return True, input_data
-
-        if not decision.should_proceed:
-            # Review was rejected, raise an error to stop execution
-            raise BlockExecutionError(
-                message=f"Block execution rejected by reviewer: {decision.message}",
-                block_name=self.name,
-                block_id=self.id,
-            )
-
-        # Review was approved - use the potentially modified data
-        # ReviewResult.data must be a dict for block inputs
-        reviewed_data = decision.review_result.data
-        if not isinstance(reviewed_data, dict):
-            raise BlockExecutionError(
-                message=f"Review data must be a dict for block input, got {type(reviewed_data).__name__}",
-                block_name=self.name,
-                block_id=self.id,
-            )
-        return False, reviewed_data
-
     async def _execute(self, input_data: BlockInput, **kwargs) -> BlockOutput:
-        # Check for review requirement and get potentially modified input data
-        should_pause, input_data = await self.is_block_exec_need_review(
-            input_data, **kwargs
-        )
-        if should_pause:
-            return
-
-        # Validate the input data (original or reviewer-modified) once
         if error := self.input_schema.validate_data(input_data):
             raise BlockInputError(
                 message=f"Unable to execute block with invalid input data: {error}",
@@ -695,7 +622,6 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
                 block_id=self.id,
             )
 
-        # Use the validated input data
         async for output_name, output_data in self.run(
             self.input_schema(**{k: v for k, v in input_data.items() if v is not None}),
             **kwargs,

autogpt_platform/backend/backend/data/block_cost_config.py

@@ -59,13 +59,12 @@ from backend.integrations.credentials_store import (
 
 MODEL_COST: dict[LlmModel, int] = {
     LlmModel.O3: 4,
-    LlmModel.O3_MINI: 2,
-    LlmModel.O1: 16,
+    LlmModel.O3_MINI: 2,  # $1.10 / $4.40
+    LlmModel.O1: 16,  # $15 / $60
     LlmModel.O1_MINI: 4,
     # GPT-5 models
-    LlmModel.GPT5_2: 6,
-    LlmModel.GPT5_1: 5,
     LlmModel.GPT5: 2,
+    LlmModel.GPT5_1: 5,
     LlmModel.GPT5_MINI: 1,
     LlmModel.GPT5_NANO: 1,
     LlmModel.GPT5_CHAT: 5,
@@ -88,7 +87,7 @@ MODEL_COST: dict[LlmModel, int] = {
     LlmModel.AIML_API_LLAMA3_3_70B: 1,
     LlmModel.AIML_API_META_LLAMA_3_1_70B: 1,
     LlmModel.AIML_API_LLAMA_3_2_3B: 1,
-    LlmModel.LLAMA3_3_70B: 1,
+    LlmModel.LLAMA3_3_70B: 1,  # $0.59 / $0.79
     LlmModel.LLAMA3_1_8B: 1,
     LlmModel.OLLAMA_LLAMA3_3: 1,
     LlmModel.OLLAMA_LLAMA3_2: 1,