Discard changes to .github/workflows/classic-python-checks.yml

Bumps [actions/setup-python](https://github.com/actions/setup-python) from 5 to 6.
- [Release notes](https://github.com/actions/setup-python/releases)
- [Commits](https://github.com/actions/setup-python/compare/v5...v6)

---
updated-dependencies:
- dependency-name: actions/setup-python
  dependency-version: '6'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.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
-}

.claude/skills/vercel-react-best-practices/SKILL.md

@@ -1,125 +0,0 @@
----
-name: vercel-react-best-practices
-description: React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
-license: MIT
-metadata:
-  author: vercel
-  version: "1.0.0"
----
-
-# Vercel React Best Practices
-
-Comprehensive performance optimization guide for React and Next.js applications, maintained by Vercel. Contains 45 rules across 8 categories, prioritized by impact to guide automated refactoring and code generation.
-
-## When to Apply
-
-Reference these guidelines when:
-- Writing new React components or Next.js pages
-- Implementing data fetching (client or server-side)
-- Reviewing code for performance issues
-- Refactoring existing React/Next.js code
-- Optimizing bundle size or load times
-
-## Rule Categories by Priority
-
-| Priority | Category | Impact | Prefix |
-|----------|----------|--------|--------|
-| 1 | Eliminating Waterfalls | CRITICAL | `async-` |
-| 2 | Bundle Size Optimization | CRITICAL | `bundle-` |
-| 3 | Server-Side Performance | HIGH | `server-` |
-| 4 | Client-Side Data Fetching | MEDIUM-HIGH | `client-` |
-| 5 | Re-render Optimization | MEDIUM | `rerender-` |
-| 6 | Rendering Performance | MEDIUM | `rendering-` |
-| 7 | JavaScript Performance | LOW-MEDIUM | `js-` |
-| 8 | Advanced Patterns | LOW | `advanced-` |
-
-## Quick Reference
-
-### 1. Eliminating Waterfalls (CRITICAL)
-
-- `async-defer-await` - Move await into branches where actually used
-- `async-parallel` - Use Promise.all() for independent operations
-- `async-dependencies` - Use better-all for partial dependencies
-- `async-api-routes` - Start promises early, await late in API routes
-- `async-suspense-boundaries` - Use Suspense to stream content
-
-### 2. Bundle Size Optimization (CRITICAL)
-
-- `bundle-barrel-imports` - Import directly, avoid barrel files
-- `bundle-dynamic-imports` - Use next/dynamic for heavy components
-- `bundle-defer-third-party` - Load analytics/logging after hydration
-- `bundle-conditional` - Load modules only when feature is activated
-- `bundle-preload` - Preload on hover/focus for perceived speed
-
-### 3. Server-Side Performance (HIGH)
-
-- `server-cache-react` - Use React.cache() for per-request deduplication
-- `server-cache-lru` - Use LRU cache for cross-request caching
-- `server-serialization` - Minimize data passed to client components
-- `server-parallel-fetching` - Restructure components to parallelize fetches
-- `server-after-nonblocking` - Use after() for non-blocking operations
-
-### 4. Client-Side Data Fetching (MEDIUM-HIGH)
-
-- `client-swr-dedup` - Use SWR for automatic request deduplication
-- `client-event-listeners` - Deduplicate global event listeners
-
-### 5. Re-render Optimization (MEDIUM)
-
-- `rerender-defer-reads` - Don't subscribe to state only used in callbacks
-- `rerender-memo` - Extract expensive work into memoized components
-- `rerender-dependencies` - Use primitive dependencies in effects
-- `rerender-derived-state` - Subscribe to derived booleans, not raw values
-- `rerender-functional-setstate` - Use functional setState for stable callbacks
-- `rerender-lazy-state-init` - Pass function to useState for expensive values
-- `rerender-transitions` - Use startTransition for non-urgent updates
-
-### 6. Rendering Performance (MEDIUM)
-
-- `rendering-animate-svg-wrapper` - Animate div wrapper, not SVG element
-- `rendering-content-visibility` - Use content-visibility for long lists
-- `rendering-hoist-jsx` - Extract static JSX outside components
-- `rendering-svg-precision` - Reduce SVG coordinate precision
-- `rendering-hydration-no-flicker` - Use inline script for client-only data
-- `rendering-activity` - Use Activity component for show/hide
-- `rendering-conditional-render` - Use ternary, not && for conditionals
-
-### 7. JavaScript Performance (LOW-MEDIUM)
-
-- `js-batch-dom-css` - Group CSS changes via classes or cssText
-- `js-index-maps` - Build Map for repeated lookups
-- `js-cache-property-access` - Cache object properties in loops
-- `js-cache-function-results` - Cache function results in module-level Map
-- `js-cache-storage` - Cache localStorage/sessionStorage reads
-- `js-combine-iterations` - Combine multiple filter/map into one loop
-- `js-length-check-first` - Check array length before expensive comparison
-- `js-early-exit` - Return early from functions
-- `js-hoist-regexp` - Hoist RegExp creation outside loops
-- `js-min-max-loop` - Use loop for min/max instead of sort
-- `js-set-map-lookups` - Use Set/Map for O(1) lookups
-- `js-tosorted-immutable` - Use toSorted() for immutability
-
-### 8. Advanced Patterns (LOW)
-
-- `advanced-event-handler-refs` - Store event handlers in refs
-- `advanced-use-latest` - useLatest for stable callback refs
-
-## How to Use
-
-Read individual rule files for detailed explanations and code examples:
-
-```
-rules/async-parallel.md
-rules/bundle-barrel-imports.md
-rules/_sections.md
-```
-
-Each rule file contains:
-- Brief explanation of why it matters
-- Incorrect code example with explanation
-- Correct code example with explanation
-- Additional context and references
-
-## Full Compiled Document
-
-For the complete guide with all rules expanded: `AGENTS.md`

.claude/skills/vercel-react-best-practices/rules/advanced-event-handler-refs.md

@@ -1,55 +0,0 @@
----
-title: Store Event Handlers in Refs
-impact: LOW
-impactDescription: stable subscriptions
-tags: advanced, hooks, refs, event-handlers, optimization
----
-
-## Store Event Handlers in Refs
-
-Store callbacks in refs when used in effects that shouldn't re-subscribe on callback changes.
-
-**Incorrect (re-subscribes on every render):**
-
-```tsx
-function useWindowEvent(event: string, handler: () => void) {
-  useEffect(() => {
-    window.addEventListener(event, handler)
-    return () => window.removeEventListener(event, handler)
-  }, [event, handler])
-}
-```
-
-**Correct (stable subscription):**
-
-```tsx
-function useWindowEvent(event: string, handler: () => void) {
-  const handlerRef = useRef(handler)
-  useEffect(() => {
-    handlerRef.current = handler
-  }, [handler])
-
-  useEffect(() => {
-    const listener = () => handlerRef.current()
-    window.addEventListener(event, listener)
-    return () => window.removeEventListener(event, listener)
-  }, [event])
-}
-```
-
-**Alternative: use `useEffectEvent` if you're on latest React:**
-
-```tsx
-import { useEffectEvent } from 'react'
-
-function useWindowEvent(event: string, handler: () => void) {
-  const onEvent = useEffectEvent(handler)
-
-  useEffect(() => {
-    window.addEventListener(event, onEvent)
-    return () => window.removeEventListener(event, onEvent)
-  }, [event])
-}
-```
-
-`useEffectEvent` provides a cleaner API for the same pattern: it creates a stable function reference that always calls the latest version of the handler.

.claude/skills/vercel-react-best-practices/rules/advanced-use-latest.md

@@ -1,49 +0,0 @@
----
-title: useLatest for Stable Callback Refs
-impact: LOW
-impactDescription: prevents effect re-runs
-tags: advanced, hooks, useLatest, refs, optimization
----
-
-## useLatest for Stable Callback Refs
-
-Access latest values in callbacks without adding them to dependency arrays. Prevents effect re-runs while avoiding stale closures.
-
-**Implementation:**
-
-```typescript
-function useLatest<T>(value: T) {
-  const ref = useRef(value)
-  useEffect(() => {
-    ref.current = value
-  }, [value])
-  return ref
-}
-```
-
-**Incorrect (effect re-runs on every callback change):**
-
-```tsx
-function SearchInput({ onSearch }: { onSearch: (q: string) => void }) {
-  const [query, setQuery] = useState('')
-
-  useEffect(() => {
-    const timeout = setTimeout(() => onSearch(query), 300)
-    return () => clearTimeout(timeout)
-  }, [query, onSearch])
-}
-```
-
-**Correct (stable effect, fresh callback):**
-
-```tsx
-function SearchInput({ onSearch }: { onSearch: (q: string) => void }) {
-  const [query, setQuery] = useState('')
-  const onSearchRef = useLatest(onSearch)
-
-  useEffect(() => {
-    const timeout = setTimeout(() => onSearchRef.current(query), 300)
-    return () => clearTimeout(timeout)
-  }, [query])
-}
-```

.claude/skills/vercel-react-best-practices/rules/async-api-routes.md

@@ -1,38 +0,0 @@
----
-title: Prevent Waterfall Chains in API Routes
-impact: CRITICAL
-impactDescription: 2-10× improvement
-tags: api-routes, server-actions, waterfalls, parallelization
----
-
-## Prevent Waterfall Chains in API Routes
-
-In API routes and Server Actions, start independent operations immediately, even if you don't await them yet.
-
-**Incorrect (config waits for auth, data waits for both):**
-
-```typescript
-export async function GET(request: Request) {
-  const session = await auth()
-  const config = await fetchConfig()
-  const data = await fetchData(session.user.id)
-  return Response.json({ data, config })
-}
-```
-
-**Correct (auth and config start immediately):**
-
-```typescript
-export async function GET(request: Request) {
-  const sessionPromise = auth()
-  const configPromise = fetchConfig()
-  const session = await sessionPromise
-  const [config, data] = await Promise.all([
-    configPromise,
-    fetchData(session.user.id)
-  ])
-  return Response.json({ data, config })
-}
-```
-
-For operations with more complex dependency chains, use `better-all` to automatically maximize parallelism (see Dependency-Based Parallelization).

.claude/skills/vercel-react-best-practices/rules/async-defer-await.md

@@ -1,80 +0,0 @@
----
-title: Defer Await Until Needed
-impact: HIGH
-impactDescription: avoids blocking unused code paths
-tags: async, await, conditional, optimization
----
-
-## Defer Await Until Needed
-
-Move `await` operations into the branches where they're actually used to avoid blocking code paths that don't need them.
-
-**Incorrect (blocks both branches):**
-
-```typescript
-async function handleRequest(userId: string, skipProcessing: boolean) {
-  const userData = await fetchUserData(userId)
-  
-  if (skipProcessing) {
-    // Returns immediately but still waited for userData
-    return { skipped: true }
-  }
-  
-  // Only this branch uses userData
-  return processUserData(userData)
-}
-```
-
-**Correct (only blocks when needed):**
-
-```typescript
-async function handleRequest(userId: string, skipProcessing: boolean) {
-  if (skipProcessing) {
-    // Returns immediately without waiting
-    return { skipped: true }
-  }
-  
-  // Fetch only when needed
-  const userData = await fetchUserData(userId)
-  return processUserData(userData)
-}
-```
-
-**Another example (early return optimization):**
-
-```typescript
-// Incorrect: always fetches permissions
-async function updateResource(resourceId: string, userId: string) {
-  const permissions = await fetchPermissions(userId)
-  const resource = await getResource(resourceId)
-  
-  if (!resource) {
-    return { error: 'Not found' }
-  }
-  
-  if (!permissions.canEdit) {
-    return { error: 'Forbidden' }
-  }
-  
-  return await updateResourceData(resource, permissions)
-}
-
-// Correct: fetches only when needed
-async function updateResource(resourceId: string, userId: string) {
-  const resource = await getResource(resourceId)
-  
-  if (!resource) {
-    return { error: 'Not found' }
-  }
-  
-  const permissions = await fetchPermissions(userId)
-  
-  if (!permissions.canEdit) {
-    return { error: 'Forbidden' }
-  }
-  
-  return await updateResourceData(resource, permissions)
-}
-```
-
-This optimization is especially valuable when the skipped branch is frequently taken, or when the deferred operation is expensive.

.claude/skills/vercel-react-best-practices/rules/async-dependencies.md

@@ -1,36 +0,0 @@
----
-title: Dependency-Based Parallelization
-impact: CRITICAL
-impactDescription: 2-10× improvement
-tags: async, parallelization, dependencies, better-all
----
-
-## Dependency-Based Parallelization
-
-For operations with partial dependencies, use `better-all` to maximize parallelism. It automatically starts each task at the earliest possible moment.
-
-**Incorrect (profile waits for config unnecessarily):**
-
-```typescript
-const [user, config] = await Promise.all([
-  fetchUser(),
-  fetchConfig()
-])
-const profile = await fetchProfile(user.id)
-```
-
-**Correct (config and profile run in parallel):**
-
-```typescript
-import { all } from 'better-all'
-
-const { user, config, profile } = await all({
-  async user() { return fetchUser() },
-  async config() { return fetchConfig() },
-  async profile() {
-    return fetchProfile((await this.$.user).id)
-  }
-})
-```
-
-Reference: [https://github.com/shuding/better-all](https://github.com/shuding/better-all)

.claude/skills/vercel-react-best-practices/rules/async-parallel.md

@@ -1,28 +0,0 @@
----
-title: Promise.all() for Independent Operations
-impact: CRITICAL
-impactDescription: 2-10× improvement
-tags: async, parallelization, promises, waterfalls
----
-
-## Promise.all() for Independent Operations
-
-When async operations have no interdependencies, execute them concurrently using `Promise.all()`.
-
-**Incorrect (sequential execution, 3 round trips):**
-
-```typescript
-const user = await fetchUser()
-const posts = await fetchPosts()
-const comments = await fetchComments()
-```
-
-**Correct (parallel execution, 1 round trip):**
-
-```typescript
-const [user, posts, comments] = await Promise.all([
-  fetchUser(),
-  fetchPosts(),
-  fetchComments()
-])
-```

.claude/skills/vercel-react-best-practices/rules/async-suspense-boundaries.md

@@ -1,99 +0,0 @@
----
-title: Strategic Suspense Boundaries
-impact: HIGH
-impactDescription: faster initial paint
-tags: async, suspense, streaming, layout-shift
----
-
-## Strategic Suspense Boundaries
-
-Instead of awaiting data in async components before returning JSX, use Suspense boundaries to show the wrapper UI faster while data loads.
-
-**Incorrect (wrapper blocked by data fetching):**
-
-```tsx
-async function Page() {
-  const data = await fetchData() // Blocks entire page
-  
-  return (
-    <div>
-      <div>Sidebar</div>
-      <div>Header</div>
-      <div>
-        <DataDisplay data={data} />
-      </div>
-      <div>Footer</div>
-    </div>
-  )
-}
-```
-
-The entire layout waits for data even though only the middle section needs it.
-
-**Correct (wrapper shows immediately, data streams in):**
-
-```tsx
-function Page() {
-  return (
-    <div>
-      <div>Sidebar</div>
-      <div>Header</div>
-      <div>
-        <Suspense fallback={<Skeleton />}>
-          <DataDisplay />
-        </Suspense>
-      </div>
-      <div>Footer</div>
-    </div>
-  )
-}
-
-async function DataDisplay() {
-  const data = await fetchData() // Only blocks this component
-  return <div>{data.content}</div>
-}
-```
-
-Sidebar, Header, and Footer render immediately. Only DataDisplay waits for data.
-
-**Alternative (share promise across components):**
-
-```tsx
-function Page() {
-  // Start fetch immediately, but don't await
-  const dataPromise = fetchData()
-  
-  return (
-    <div>
-      <div>Sidebar</div>
-      <div>Header</div>
-      <Suspense fallback={<Skeleton />}>
-        <DataDisplay dataPromise={dataPromise} />
-        <DataSummary dataPromise={dataPromise} />
-      </Suspense>
-      <div>Footer</div>
-    </div>
-  )
-}
-
-function DataDisplay({ dataPromise }: { dataPromise: Promise<Data> }) {
-  const data = use(dataPromise) // Unwraps the promise
-  return <div>{data.content}</div>
-}
-
-function DataSummary({ dataPromise }: { dataPromise: Promise<Data> }) {
-  const data = use(dataPromise) // Reuses the same promise
-  return <div>{data.summary}</div>
-}
-```
-
-Both components share the same promise, so only one fetch occurs. Layout renders immediately while both components wait together.
-
-**When NOT to use this pattern:**
-
-- Critical data needed for layout decisions (affects positioning)
-- SEO-critical content above the fold
-- Small, fast queries where suspense overhead isn't worth it
-- When you want to avoid layout shift (loading → content jump)
-
-**Trade-off:** Faster initial paint vs potential layout shift. Choose based on your UX priorities.

.claude/skills/vercel-react-best-practices/rules/bundle-barrel-imports.md

@@ -1,59 +0,0 @@
----
-title: Avoid Barrel File Imports
-impact: CRITICAL
-impactDescription: 200-800ms import cost, slow builds
-tags: bundle, imports, tree-shaking, barrel-files, performance
----
-
-## Avoid Barrel File Imports
-
-Import directly from source files instead of barrel files to avoid loading thousands of unused modules. **Barrel files** are entry points that re-export multiple modules (e.g., `index.js` that does `export * from './module'`).
-
-Popular icon and component libraries can have **up to 10,000 re-exports** in their entry file. For many React packages, **it takes 200-800ms just to import them**, affecting both development speed and production cold starts.
-
-**Why tree-shaking doesn't help:** When a library is marked as external (not bundled), the bundler can't optimize it. If you bundle it to enable tree-shaking, builds become substantially slower analyzing the entire module graph.
-
-**Incorrect (imports entire library):**
-
-```tsx
-import { Check, X, Menu } from 'lucide-react'
-// Loads 1,583 modules, takes ~2.8s extra in dev
-// Runtime cost: 200-800ms on every cold start
-
-import { Button, TextField } from '@mui/material'
-// Loads 2,225 modules, takes ~4.2s extra in dev
-```
-
-**Correct (imports only what you need):**
-
-```tsx
-import Check from 'lucide-react/dist/esm/icons/check'
-import X from 'lucide-react/dist/esm/icons/x'
-import Menu from 'lucide-react/dist/esm/icons/menu'
-// Loads only 3 modules (~2KB vs ~1MB)
-
-import Button from '@mui/material/Button'
-import TextField from '@mui/material/TextField'
-// Loads only what you use
-```
-
-**Alternative (Next.js 13.5+):**
-
-```js
-// next.config.js - use optimizePackageImports
-module.exports = {
-  experimental: {
-    optimizePackageImports: ['lucide-react', '@mui/material']
-  }
-}
-
-// Then you can keep the ergonomic barrel imports:
-import { Check, X, Menu } from 'lucide-react'
-// Automatically transformed to direct imports at build time
-```
-
-Direct imports provide 15-70% faster dev boot, 28% faster builds, 40% faster cold starts, and significantly faster HMR.
-
-Libraries commonly affected: `lucide-react`, `@mui/material`, `@mui/icons-material`, `@tabler/icons-react`, `react-icons`, `@headlessui/react`, `@radix-ui/react-*`, `lodash`, `ramda`, `date-fns`, `rxjs`, `react-use`.
-
-Reference: [How we optimized package imports in Next.js](https://vercel.com/blog/how-we-optimized-package-imports-in-next-js)

.claude/skills/vercel-react-best-practices/rules/bundle-conditional.md

@@ -1,31 +0,0 @@
----
-title: Conditional Module Loading
-impact: HIGH
-impactDescription: loads large data only when needed
-tags: bundle, conditional-loading, lazy-loading
----
-
-## Conditional Module Loading
-
-Load large data or modules only when a feature is activated.
-
-**Example (lazy-load animation frames):**
-
-```tsx
-function AnimationPlayer({ enabled }: { enabled: boolean }) {
-  const [frames, setFrames] = useState<Frame[] | null>(null)
-
-  useEffect(() => {
-    if (enabled && !frames && typeof window !== 'undefined') {
-      import('./animation-frames.js')
-        .then(mod => setFrames(mod.frames))
-        .catch(() => setEnabled(false))
-    }
-  }, [enabled, frames])
-
-  if (!frames) return <Skeleton />
-  return <Canvas frames={frames} />
-}
-```
-
-The `typeof window !== 'undefined'` check prevents bundling this module for SSR, optimizing server bundle size and build speed.

.claude/skills/vercel-react-best-practices/rules/bundle-defer-third-party.md

@@ -1,49 +0,0 @@
----
-title: Defer Non-Critical Third-Party Libraries
-impact: MEDIUM
-impactDescription: loads after hydration
-tags: bundle, third-party, analytics, defer
----
-
-## Defer Non-Critical Third-Party Libraries
-
-Analytics, logging, and error tracking don't block user interaction. Load them after hydration.
-
-**Incorrect (blocks initial bundle):**
-
-```tsx
-import { Analytics } from '@vercel/analytics/react'
-
-export default function RootLayout({ children }) {
-  return (
-    <html>
-      <body>
-        {children}
-        <Analytics />
-      </body>
-    </html>
-  )
-}
-```
-
-**Correct (loads after hydration):**
-
-```tsx
-import dynamic from 'next/dynamic'
-
-const Analytics = dynamic(
-  () => import('@vercel/analytics/react').then(m => m.Analytics),
-  { ssr: false }
-)
-
-export default function RootLayout({ children }) {
-  return (
-    <html>
-      <body>
-        {children}
-        <Analytics />
-      </body>
-    </html>
-  )
-}
-```

.claude/skills/vercel-react-best-practices/rules/bundle-dynamic-imports.md

@@ -1,35 +0,0 @@
----
-title: Dynamic Imports for Heavy Components
-impact: CRITICAL
-impactDescription: directly affects TTI and LCP
-tags: bundle, dynamic-import, code-splitting, next-dynamic
----
-
-## Dynamic Imports for Heavy Components
-
-Use `next/dynamic` to lazy-load large components not needed on initial render.
-
-**Incorrect (Monaco bundles with main chunk ~300KB):**
-
-```tsx
-import { MonacoEditor } from './monaco-editor'
-
-function CodePanel({ code }: { code: string }) {
-  return <MonacoEditor value={code} />
-}
-```
-
-**Correct (Monaco loads on demand):**
-
-```tsx
-import dynamic from 'next/dynamic'
-
-const MonacoEditor = dynamic(
-  () => import('./monaco-editor').then(m => m.MonacoEditor),
-  { ssr: false }
-)
-
-function CodePanel({ code }: { code: string }) {
-  return <MonacoEditor value={code} />
-}
-```

.claude/skills/vercel-react-best-practices/rules/bundle-preload.md

@@ -1,50 +0,0 @@
----
-title: Preload Based on User Intent
-impact: MEDIUM
-impactDescription: reduces perceived latency
-tags: bundle, preload, user-intent, hover
----
-
-## Preload Based on User Intent
-
-Preload heavy bundles before they're needed to reduce perceived latency.
-
-**Example (preload on hover/focus):**
-
-```tsx
-function EditorButton({ onClick }: { onClick: () => void }) {
-  const preload = () => {
-    if (typeof window !== 'undefined') {
-      void import('./monaco-editor')
-    }
-  }
-
-  return (
-    <button
-      onMouseEnter={preload}
-      onFocus={preload}
-      onClick={onClick}
-    >
-      Open Editor
-    </button>
-  )
-}
-```
-
-**Example (preload when feature flag is enabled):**
-
-```tsx
-function FlagsProvider({ children, flags }: Props) {
-  useEffect(() => {
-    if (flags.editorEnabled && typeof window !== 'undefined') {
-      void import('./monaco-editor').then(mod => mod.init())
-    }
-  }, [flags.editorEnabled])
-
-  return <FlagsContext.Provider value={flags}>
-    {children}
-  </FlagsContext.Provider>
-}
-```
-
-The `typeof window !== 'undefined'` check prevents bundling preloaded modules for SSR, optimizing server bundle size and build speed.

.claude/skills/vercel-react-best-practices/rules/client-event-listeners.md

@@ -1,74 +0,0 @@
----
-title: Deduplicate Global Event Listeners
-impact: LOW
-impactDescription: single listener for N components
-tags: client, swr, event-listeners, subscription
----
-
-## Deduplicate Global Event Listeners
-
-Use `useSWRSubscription()` to share global event listeners across component instances.
-
-**Incorrect (N instances = N listeners):**
-
-```tsx
-function useKeyboardShortcut(key: string, callback: () => void) {
-  useEffect(() => {
-    const handler = (e: KeyboardEvent) => {
-      if (e.metaKey && e.key === key) {
-        callback()
-      }
-    }
-    window.addEventListener('keydown', handler)
-    return () => window.removeEventListener('keydown', handler)
-  }, [key, callback])
-}
-```
-
-When using the `useKeyboardShortcut` hook multiple times, each instance will register a new listener.
-
-**Correct (N instances = 1 listener):**
-
-```tsx
-import useSWRSubscription from 'swr/subscription'
-
-// Module-level Map to track callbacks per key
-const keyCallbacks = new Map<string, Set<() => void>>()
-
-function useKeyboardShortcut(key: string, callback: () => void) {
-  // Register this callback in the Map
-  useEffect(() => {
-    if (!keyCallbacks.has(key)) {
-      keyCallbacks.set(key, new Set())
-    }
-    keyCallbacks.get(key)!.add(callback)
-
-    return () => {
-      const set = keyCallbacks.get(key)
-      if (set) {
-        set.delete(callback)
-        if (set.size === 0) {
-          keyCallbacks.delete(key)
-        }
-      }
-    }
-  }, [key, callback])
-
-  useSWRSubscription('global-keydown', () => {
-    const handler = (e: KeyboardEvent) => {
-      if (e.metaKey && keyCallbacks.has(e.key)) {
-        keyCallbacks.get(e.key)!.forEach(cb => cb())
-      }
-    }
-    window.addEventListener('keydown', handler)
-    return () => window.removeEventListener('keydown', handler)
-  })
-}
-
-function Profile() {
-  // Multiple shortcuts will share the same listener
-  useKeyboardShortcut('p', () => { /* ... */ }) 
-  useKeyboardShortcut('k', () => { /* ... */ })
-  // ...
-}
-```

.claude/skills/vercel-react-best-practices/rules/client-swr-dedup.md

@@ -1,56 +0,0 @@
----
-title: Use SWR for Automatic Deduplication
-impact: MEDIUM-HIGH
-impactDescription: automatic deduplication
-tags: client, swr, deduplication, data-fetching
----
-
-## Use SWR for Automatic Deduplication
-
-SWR enables request deduplication, caching, and revalidation across component instances.
-
-**Incorrect (no deduplication, each instance fetches):**
-
-```tsx
-function UserList() {
-  const [users, setUsers] = useState([])
-  useEffect(() => {
-    fetch('/api/users')
-      .then(r => r.json())
-      .then(setUsers)
-  }, [])
-}
-```
-
-**Correct (multiple instances share one request):**
-
-```tsx
-import useSWR from 'swr'
-
-function UserList() {
-  const { data: users } = useSWR('/api/users', fetcher)
-}
-```
-
-**For immutable data:**
-
-```tsx
-import { useImmutableSWR } from '@/lib/swr'
-
-function StaticContent() {
-  const { data } = useImmutableSWR('/api/config', fetcher)
-}
-```
-
-**For mutations:**
-
-```tsx
-import { useSWRMutation } from 'swr/mutation'
-
-function UpdateButton() {
-  const { trigger } = useSWRMutation('/api/user', updateUser)
-  return <button onClick={() => trigger()}>Update</button>
-}
-```
-
-Reference: [https://swr.vercel.app](https://swr.vercel.app)

.claude/skills/vercel-react-best-practices/rules/js-batch-dom-css.md

@@ -1,82 +0,0 @@
----
-title: Batch DOM CSS Changes
-impact: MEDIUM
-impactDescription: reduces reflows/repaints
-tags: javascript, dom, css, performance, reflow
----
-
-## Batch DOM CSS Changes
-
-Avoid changing styles one property at a time. Group multiple CSS changes together via classes or `cssText` to minimize browser reflows.
-
-**Incorrect (multiple reflows):**
-
-```typescript
-function updateElementStyles(element: HTMLElement) {
-  // Each line triggers a reflow
-  element.style.width = '100px'
-  element.style.height = '200px'
-  element.style.backgroundColor = 'blue'
-  element.style.border = '1px solid black'
-}
-```
-
-**Correct (add class - single reflow):**
-
-```typescript
-// CSS file
-.highlighted-box {
-  width: 100px;
-  height: 200px;
-  background-color: blue;
-  border: 1px solid black;
-}
-
-// JavaScript
-function updateElementStyles(element: HTMLElement) {
-  element.classList.add('highlighted-box')
-}
-```
-
-**Correct (change cssText - single reflow):**
-
-```typescript
-function updateElementStyles(element: HTMLElement) {
-  element.style.cssText = `
-    width: 100px;
-    height: 200px;
-    background-color: blue;
-    border: 1px solid black;
-  `
-}
-```
-
-**React example:**
-
-```tsx
-// Incorrect: changing styles one by one
-function Box({ isHighlighted }: { isHighlighted: boolean }) {
-  const ref = useRef<HTMLDivElement>(null)
-  
-  useEffect(() => {
-    if (ref.current && isHighlighted) {
-      ref.current.style.width = '100px'
-      ref.current.style.height = '200px'
-      ref.current.style.backgroundColor = 'blue'
-    }
-  }, [isHighlighted])
-  
-  return <div ref={ref}>Content</div>
-}
-
-// Correct: toggle class
-function Box({ isHighlighted }: { isHighlighted: boolean }) {
-  return (
-    <div className={isHighlighted ? 'highlighted-box' : ''}>
-      Content
-    </div>
-  )
-}
-```
-
-Prefer CSS classes over inline styles when possible. Classes are cached by the browser and provide better separation of concerns.

.claude/skills/vercel-react-best-practices/rules/js-cache-function-results.md

@@ -1,80 +0,0 @@
----
-title: Cache Repeated Function Calls
-impact: MEDIUM
-impactDescription: avoid redundant computation
-tags: javascript, cache, memoization, performance
----
-
-## Cache Repeated Function Calls
-
-Use a module-level Map to cache function results when the same function is called repeatedly with the same inputs during render.
-
-**Incorrect (redundant computation):**
-
-```typescript
-function ProjectList({ projects }: { projects: Project[] }) {
-  return (
-    <div>
-      {projects.map(project => {
-        // slugify() called 100+ times for same project names
-        const slug = slugify(project.name)
-        
-        return <ProjectCard key={project.id} slug={slug} />
-      })}
-    </div>
-  )
-}
-```
-
-**Correct (cached results):**
-
-```typescript
-// Module-level cache
-const slugifyCache = new Map<string, string>()
-
-function cachedSlugify(text: string): string {
-  if (slugifyCache.has(text)) {
-    return slugifyCache.get(text)!
-  }
-  const result = slugify(text)
-  slugifyCache.set(text, result)
-  return result
-}
-
-function ProjectList({ projects }: { projects: Project[] }) {
-  return (
-    <div>
-      {projects.map(project => {
-        // Computed only once per unique project name
-        const slug = cachedSlugify(project.name)
-        
-        return <ProjectCard key={project.id} slug={slug} />
-      })}
-    </div>
-  )
-}
-```
-
-**Simpler pattern for single-value functions:**
-
-```typescript
-let isLoggedInCache: boolean | null = null
-
-function isLoggedIn(): boolean {
-  if (isLoggedInCache !== null) {
-    return isLoggedInCache
-  }
-  
-  isLoggedInCache = document.cookie.includes('auth=')
-  return isLoggedInCache
-}
-
-// Clear cache when auth changes
-function onAuthChange() {
-  isLoggedInCache = null
-}
-```
-
-Use a Map (not a hook) so it works everywhere: utilities, event handlers, not just React components.
-
-Reference: [How we made the Vercel Dashboard twice as fast](https://vercel.com/blog/how-we-made-the-vercel-dashboard-twice-as-fast)

.claude/skills/vercel-react-best-practices/rules/js-cache-property-access.md

@@ -1,28 +0,0 @@
----
-title: Cache Property Access in Loops
-impact: LOW-MEDIUM
-impactDescription: reduces lookups
-tags: javascript, loops, optimization, caching
----
-
-## Cache Property Access in Loops
-
-Cache object property lookups in hot paths.
-
-**Incorrect (3 lookups × N iterations):**
-
-```typescript
-for (let i = 0; i < arr.length; i++) {
-  process(obj.config.settings.value)
-}
-```
-
-**Correct (1 lookup total):**
-
-```typescript
-const value = obj.config.settings.value
-const len = arr.length
-for (let i = 0; i < len; i++) {
-  process(value)
-}
-```

.claude/skills/vercel-react-best-practices/rules/js-cache-storage.md

@@ -1,70 +0,0 @@
----
-title: Cache Storage API Calls
-impact: LOW-MEDIUM
-impactDescription: reduces expensive I/O
-tags: javascript, localStorage, storage, caching, performance
----
-
-## Cache Storage API Calls
-
-`localStorage`, `sessionStorage`, and `document.cookie` are synchronous and expensive. Cache reads in memory.
-
-**Incorrect (reads storage on every call):**
-
-```typescript
-function getTheme() {
-  return localStorage.getItem('theme') ?? 'light'
-}
-// Called 10 times = 10 storage reads
-```
-
-**Correct (Map cache):**
-
-```typescript
-const storageCache = new Map<string, string | null>()
-
-function getLocalStorage(key: string) {
-  if (!storageCache.has(key)) {
-    storageCache.set(key, localStorage.getItem(key))
-  }
-  return storageCache.get(key)
-}
-
-function setLocalStorage(key: string, value: string) {
-  localStorage.setItem(key, value)
-  storageCache.set(key, value)  // keep cache in sync
-}
-```
-
-Use a Map (not a hook) so it works everywhere: utilities, event handlers, not just React components.
-
-**Cookie caching:**
-
-```typescript
-let cookieCache: Record<string, string> | null = null
-
-function getCookie(name: string) {
-  if (!cookieCache) {
-    cookieCache = Object.fromEntries(
-      document.cookie.split('; ').map(c => c.split('='))
-    )
-  }
-  return cookieCache[name]
-}
-```
-
-**Important (invalidate on external changes):**
-
-If storage can change externally (another tab, server-set cookies), invalidate cache:
-
-```typescript
-window.addEventListener('storage', (e) => {
-  if (e.key) storageCache.delete(e.key)
-})
-
-document.addEventListener('visibilitychange', () => {
-  if (document.visibilityState === 'visible') {
-    storageCache.clear()
-  }
-})
-```

.claude/skills/vercel-react-best-practices/rules/js-combine-iterations.md

@@ -1,32 +0,0 @@
----
-title: Combine Multiple Array Iterations
-impact: LOW-MEDIUM
-impactDescription: reduces iterations
-tags: javascript, arrays, loops, performance
----
-
-## Combine Multiple Array Iterations
-
-Multiple `.filter()` or `.map()` calls iterate the array multiple times. Combine into one loop.
-
-**Incorrect (3 iterations):**
-
-```typescript
-const admins = users.filter(u => u.isAdmin)
-const testers = users.filter(u => u.isTester)
-const inactive = users.filter(u => !u.isActive)
-```
-
-**Correct (1 iteration):**
-
-```typescript
-const admins: User[] = []
-const testers: User[] = []
-const inactive: User[] = []
-
-for (const user of users) {
-  if (user.isAdmin) admins.push(user)
-  if (user.isTester) testers.push(user)
-  if (!user.isActive) inactive.push(user)
-}
-```

.claude/skills/vercel-react-best-practices/rules/js-early-exit.md

@@ -1,50 +0,0 @@
----
-title: Early Return from Functions
-impact: LOW-MEDIUM
-impactDescription: avoids unnecessary computation
-tags: javascript, functions, optimization, early-return
----
-
-## Early Return from Functions
-
-Return early when result is determined to skip unnecessary processing.
-
-**Incorrect (processes all items even after finding answer):**
-
-```typescript
-function validateUsers(users: User[]) {
-  let hasError = false
-  let errorMessage = ''
-  
-  for (const user of users) {
-    if (!user.email) {
-      hasError = true
-      errorMessage = 'Email required'
-    }
-    if (!user.name) {
-      hasError = true
-      errorMessage = 'Name required'
-    }
-    // Continues checking all users even after error found
-  }
-  
-  return hasError ? { valid: false, error: errorMessage } : { valid: true }
-}
-```
-
-**Correct (returns immediately on first error):**
-
-```typescript
-function validateUsers(users: User[]) {
-  for (const user of users) {
-    if (!user.email) {
-      return { valid: false, error: 'Email required' }
-    }
-    if (!user.name) {
-      return { valid: false, error: 'Name required' }
-    }
-  }
-
-  return { valid: true }
-}
-```

.claude/skills/vercel-react-best-practices/rules/js-hoist-regexp.md

@@ -1,45 +0,0 @@
----
-title: Hoist RegExp Creation
-impact: LOW-MEDIUM
-impactDescription: avoids recreation
-tags: javascript, regexp, optimization, memoization
----
-
-## Hoist RegExp Creation
-
-Don't create RegExp inside render. Hoist to module scope or memoize with `useMemo()`.
-
-**Incorrect (new RegExp every render):**
-
-```tsx
-function Highlighter({ text, query }: Props) {
-  const regex = new RegExp(`(${query})`, 'gi')
-  const parts = text.split(regex)
-  return <>{parts.map((part, i) => ...)}</>
-}
-```
-
-**Correct (memoize or hoist):**
-
-```tsx
-const EMAIL_REGEX = /^[^\s@]+@[^\s@]+\.[^\s@]+$/
-
-function Highlighter({ text, query }: Props) {
-  const regex = useMemo(
-    () => new RegExp(`(${escapeRegex(query)})`, 'gi'),
-    [query]
-  )
-  const parts = text.split(regex)
-  return <>{parts.map((part, i) => ...)}</>
-}
-```
-
-**Warning (global regex has mutable state):**
-
-Global regex (`/g`) has mutable `lastIndex` state:
-
-```typescript
-const regex = /foo/g
-regex.test('foo')  // true, lastIndex = 3
-regex.test('foo')  // false, lastIndex = 0
-```

.claude/skills/vercel-react-best-practices/rules/js-index-maps.md

@@ -1,37 +0,0 @@
----
-title: Build Index Maps for Repeated Lookups
-impact: LOW-MEDIUM
-impactDescription: 1M ops to 2K ops
-tags: javascript, map, indexing, optimization, performance
----
-
-## Build Index Maps for Repeated Lookups
-
-Multiple `.find()` calls by the same key should use a Map.
-
-**Incorrect (O(n) per lookup):**
-
-```typescript
-function processOrders(orders: Order[], users: User[]) {
-  return orders.map(order => ({
-    ...order,
-    user: users.find(u => u.id === order.userId)
-  }))
-}
-```
-
-**Correct (O(1) per lookup):**
-
-```typescript
-function processOrders(orders: Order[], users: User[]) {
-  const userById = new Map(users.map(u => [u.id, u]))
-
-  return orders.map(order => ({
-    ...order,
-    user: userById.get(order.userId)
-  }))
-}
-```
-
-Build map once (O(n)), then all lookups are O(1).
-For 1000 orders × 1000 users: 1M ops → 2K ops.

.claude/skills/vercel-react-best-practices/rules/js-length-check-first.md

@@ -1,49 +0,0 @@
----
-title: Early Length Check for Array Comparisons
-impact: MEDIUM-HIGH
-impactDescription: avoids expensive operations when lengths differ
-tags: javascript, arrays, performance, optimization, comparison
----
-
-## Early Length Check for Array Comparisons
-
-When comparing arrays with expensive operations (sorting, deep equality, serialization), check lengths first. If lengths differ, the arrays cannot be equal.
-
-In real-world applications, this optimization is especially valuable when the comparison runs in hot paths (event handlers, render loops).
-
-**Incorrect (always runs expensive comparison):**
-
-```typescript
-function hasChanges(current: string[], original: string[]) {
-  // Always sorts and joins, even when lengths differ
-  return current.sort().join() !== original.sort().join()
-}
-```
-
-Two O(n log n) sorts run even when `current.length` is 5 and `original.length` is 100. There is also overhead of joining the arrays and comparing the strings.
-
-**Correct (O(1) length check first):**
-
-```typescript
-function hasChanges(current: string[], original: string[]) {
-  // Early return if lengths differ
-  if (current.length !== original.length) {
-    return true
-  }
-  // Only sort/join when lengths match
-  const currentSorted = current.toSorted()
-  const originalSorted = original.toSorted()
-  for (let i = 0; i < currentSorted.length; i++) {
-    if (currentSorted[i] !== originalSorted[i]) {
-      return true
-    }
-  }
-  return false
-}
-```
-
-This new approach is more efficient because:
-- It avoids the overhead of sorting and joining the arrays when lengths differ
-- It avoids consuming memory for the joined strings (especially important for large arrays)
-- It avoids mutating the original arrays
-- It returns early when a difference is found

.claude/skills/vercel-react-best-practices/rules/js-min-max-loop.md

@@ -1,82 +0,0 @@
----
-title: Use Loop for Min/Max Instead of Sort
-impact: LOW
-impactDescription: O(n) instead of O(n log n)
-tags: javascript, arrays, performance, sorting, algorithms
----
-
-## Use Loop for Min/Max Instead of Sort
-
-Finding the smallest or largest element only requires a single pass through the array. Sorting is wasteful and slower.
-
-**Incorrect (O(n log n) - sort to find latest):**
-
-```typescript
-interface Project {
-  id: string
-  name: string
-  updatedAt: number
-}
-
-function getLatestProject(projects: Project[]) {
-  const sorted = [...projects].sort((a, b) => b.updatedAt - a.updatedAt)
-  return sorted[0]
-}
-```
-
-Sorts the entire array just to find the maximum value.
-
-**Incorrect (O(n log n) - sort for oldest and newest):**
-
-```typescript
-function getOldestAndNewest(projects: Project[]) {
-  const sorted = [...projects].sort((a, b) => a.updatedAt - b.updatedAt)
-  return { oldest: sorted[0], newest: sorted[sorted.length - 1] }
-}
-```
-
-Still sorts unnecessarily when only min/max are needed.
-
-**Correct (O(n) - single loop):**
-
-```typescript
-function getLatestProject(projects: Project[]) {
-  if (projects.length === 0) return null
-  
-  let latest = projects[0]
-  
-  for (let i = 1; i < projects.length; i++) {
-    if (projects[i].updatedAt > latest.updatedAt) {
-      latest = projects[i]
-    }
-  }
-  
-  return latest
-}
-
-function getOldestAndNewest(projects: Project[]) {
-  if (projects.length === 0) return { oldest: null, newest: null }
-  
-  let oldest = projects[0]
-  let newest = projects[0]
-  
-  for (let i = 1; i < projects.length; i++) {
-    if (projects[i].updatedAt < oldest.updatedAt) oldest = projects[i]
-    if (projects[i].updatedAt > newest.updatedAt) newest = projects[i]
-  }
-  
-  return { oldest, newest }
-}
-```
-
-Single pass through the array, no copying, no sorting.
-
-**Alternative (Math.min/Math.max for small arrays):**
-
-```typescript
-const numbers = [5, 2, 8, 1, 9]
-const min = Math.min(...numbers)
-const max = Math.max(...numbers)
-```
-
-This works for small arrays but can be slower for very large arrays due to spread operator limitations. Use the loop approach for reliability.

.claude/skills/vercel-react-best-practices/rules/js-set-map-lookups.md

@@ -1,24 +0,0 @@
----
-title: Use Set/Map for O(1) Lookups
-impact: LOW-MEDIUM
-impactDescription: O(n) to O(1)
-tags: javascript, set, map, data-structures, performance
----
-
-## Use Set/Map for O(1) Lookups
-
-Convert arrays to Set/Map for repeated membership checks.
-
-**Incorrect (O(n) per check):**
-
-```typescript
-const allowedIds = ['a', 'b', 'c', ...]
-items.filter(item => allowedIds.includes(item.id))
-```
-
-**Correct (O(1) per check):**
-
-```typescript
-const allowedIds = new Set(['a', 'b', 'c', ...])
-items.filter(item => allowedIds.has(item.id))
-```

.claude/skills/vercel-react-best-practices/rules/js-tosorted-immutable.md

@@ -1,57 +0,0 @@
----
-title: Use toSorted() Instead of sort() for Immutability
-impact: MEDIUM-HIGH
-impactDescription: prevents mutation bugs in React state
-tags: javascript, arrays, immutability, react, state, mutation
----
-
-## Use toSorted() Instead of sort() for Immutability
-
-`.sort()` mutates the array in place, which can cause bugs with React state and props. Use `.toSorted()` to create a new sorted array without mutation.
-
-**Incorrect (mutates original array):**
-
-```typescript
-function UserList({ users }: { users: User[] }) {
-  // Mutates the users prop array!
-  const sorted = useMemo(
-    () => users.sort((a, b) => a.name.localeCompare(b.name)),
-    [users]
-  )
-  return <div>{sorted.map(renderUser)}</div>
-}
-```
-
-**Correct (creates new array):**
-
-```typescript
-function UserList({ users }: { users: User[] }) {
-  // Creates new sorted array, original unchanged
-  const sorted = useMemo(
-    () => users.toSorted((a, b) => a.name.localeCompare(b.name)),
-    [users]
-  )
-  return <div>{sorted.map(renderUser)}</div>
-}
-```
-
-**Why this matters in React:**
-
-1. Props/state mutations break React's immutability model - React expects props and state to be treated as read-only
-2. Causes stale closure bugs - Mutating arrays inside closures (callbacks, effects) can lead to unexpected behavior
-
-**Browser support (fallback for older browsers):**
-
-`.toSorted()` is available in all modern browsers (Chrome 110+, Safari 16+, Firefox 115+, Node.js 20+). For older environments, use spread operator:
-
-```typescript
-// Fallback for older browsers
-const sorted = [...items].sort((a, b) => a.value - b.value)
-```
-
-**Other immutable array methods:**
-
-- `.toSorted()` - immutable sort
-- `.toReversed()` - immutable reverse
-- `.toSpliced()` - immutable splice
-- `.with()` - immutable element replacement

.claude/skills/vercel-react-best-practices/rules/rendering-activity.md

@@ -1,26 +0,0 @@
----
-title: Use Activity Component for Show/Hide
-impact: MEDIUM
-impactDescription: preserves state/DOM
-tags: rendering, activity, visibility, state-preservation
----
-
-## Use Activity Component for Show/Hide
-
-Use React's `<Activity>` to preserve state/DOM for expensive components that frequently toggle visibility.
-
-**Usage:**
-
-```tsx
-import { Activity } from 'react'
-
-function Dropdown({ isOpen }: Props) {
-  return (
-    <Activity mode={isOpen ? 'visible' : 'hidden'}>
-      <ExpensiveMenu />
-    </Activity>
-  )
-}
-```
-
-Avoids expensive re-renders and state loss.

.claude/skills/vercel-react-best-practices/rules/rendering-animate-svg-wrapper.md

@@ -1,47 +0,0 @@
----
-title: Animate SVG Wrapper Instead of SVG Element
-impact: LOW
-impactDescription: enables hardware acceleration
-tags: rendering, svg, css, animation, performance
----
-
-## Animate SVG Wrapper Instead of SVG Element
-
-Many browsers don't have hardware acceleration for CSS3 animations on SVG elements. Wrap SVG in a `<div>` and animate the wrapper instead.
-
-**Incorrect (animating SVG directly - no hardware acceleration):**
-
-```tsx
-function LoadingSpinner() {
-  return (
-    <svg 
-      className="animate-spin"
-      width="24" 
-      height="24" 
-      viewBox="0 0 24 24"
-    >
-      <circle cx="12" cy="12" r="10" stroke="currentColor" />
-    </svg>
-  )
-}
-```
-
-**Correct (animating wrapper div - hardware accelerated):**
-
-```tsx
-function LoadingSpinner() {
-  return (
-    <div className="animate-spin">
-      <svg 
-        width="24" 
-        height="24" 
-        viewBox="0 0 24 24"
-      >
-        <circle cx="12" cy="12" r="10" stroke="currentColor" />
-      </svg>
-    </div>
-  )
-}
-```
-
-This applies to all CSS transforms and transitions (`transform`, `opacity`, `translate`, `scale`, `rotate`). The wrapper div allows browsers to use GPU acceleration for smoother animations.

.claude/skills/vercel-react-best-practices/rules/rendering-conditional-render.md

@@ -1,40 +0,0 @@
----
-title: Use Explicit Conditional Rendering
-impact: LOW
-impactDescription: prevents rendering 0 or NaN
-tags: rendering, conditional, jsx, falsy-values
----
-
-## Use Explicit Conditional Rendering
-
-Use explicit ternary operators (`? :`) instead of `&&` for conditional rendering when the condition can be `0`, `NaN`, or other falsy values that render.
-
-**Incorrect (renders "0" when count is 0):**
-
-```tsx
-function Badge({ count }: { count: number }) {
-  return (
-    <div>
-      {count && <span className="badge">{count}</span>}
-    </div>
-  )
-}
-
-// When count = 0, renders: <div>0</div>
-// When count = 5, renders: <div><span class="badge">5</span></div>
-```
-
-**Correct (renders nothing when count is 0):**
-
-```tsx
-function Badge({ count }: { count: number }) {
-  return (
-    <div>
-      {count > 0 ? <span className="badge">{count}</span> : null}
-    </div>
-  )
-}
-
-// When count = 0, renders: <div></div>
-// When count = 5, renders: <div><span class="badge">5</span></div>
-```

.claude/skills/vercel-react-best-practices/rules/rendering-content-visibility.md

@@ -1,38 +0,0 @@
----
-title: CSS content-visibility for Long Lists
-impact: HIGH
-impactDescription: faster initial render
-tags: rendering, css, content-visibility, long-lists
----
-
-## CSS content-visibility for Long Lists
-
-Apply `content-visibility: auto` to defer off-screen rendering.
-
-**CSS:**
-
-```css
-.message-item {
-  content-visibility: auto;
-  contain-intrinsic-size: 0 80px;
-}
-```
-
-**Example:**
-
-```tsx
-function MessageList({ messages }: { messages: Message[] }) {
-  return (
-    <div className="overflow-y-auto h-screen">
-      {messages.map(msg => (
-        <div key={msg.id} className="message-item">
-          <Avatar user={msg.author} />
-          <div>{msg.content}</div>
-        </div>
-      ))}
-    </div>
-  )
-}
-```
-
-For 1000 messages, browser skips layout/paint for ~990 off-screen items (10× faster initial render).

.claude/skills/vercel-react-best-practices/rules/rendering-hoist-jsx.md

@@ -1,46 +0,0 @@
----
-title: Hoist Static JSX Elements
-impact: LOW
-impactDescription: avoids re-creation
-tags: rendering, jsx, static, optimization
----
-
-## Hoist Static JSX Elements
-
-Extract static JSX outside components to avoid re-creation.
-
-**Incorrect (recreates element every render):**
-
-```tsx
-function LoadingSkeleton() {
-  return <div className="animate-pulse h-20 bg-gray-200" />
-}
-
-function Container() {
-  return (
-    <div>
-      {loading && <LoadingSkeleton />}
-    </div>
-  )
-}
-```
-
-**Correct (reuses same element):**
-
-```tsx
-const loadingSkeleton = (
-  <div className="animate-pulse h-20 bg-gray-200" />
-)
-
-function Container() {
-  return (
-    <div>
-      {loading && loadingSkeleton}
-    </div>
-  )
-}
-```
-
-This is especially helpful for large and static SVG nodes, which can be expensive to recreate on every render.
-
-**Note:** If your project has [React Compiler](https://react.dev/learn/react-compiler) enabled, the compiler automatically hoists static JSX elements and optimizes component re-renders, making manual hoisting unnecessary.

.claude/skills/vercel-react-best-practices/rules/rendering-hydration-no-flicker.md

@@ -1,82 +0,0 @@
----
-title: Prevent Hydration Mismatch Without Flickering
-impact: MEDIUM
-impactDescription: avoids visual flicker and hydration errors
-tags: rendering, ssr, hydration, localStorage, flicker
----
-
-## Prevent Hydration Mismatch Without Flickering
-
-When rendering content that depends on client-side storage (localStorage, cookies), avoid both SSR breakage and post-hydration flickering by injecting a synchronous script that updates the DOM before React hydrates.
-
-**Incorrect (breaks SSR):**
-
-```tsx
-function ThemeWrapper({ children }: { children: ReactNode }) {
-  // localStorage is not available on server - throws error
-  const theme = localStorage.getItem('theme') || 'light'
-  
-  return (
-    <div className={theme}>
-      {children}
-    </div>
-  )
-}
-```
-
-Server-side rendering will fail because `localStorage` is undefined.
-
-**Incorrect (visual flickering):**
-
-```tsx
-function ThemeWrapper({ children }: { children: ReactNode }) {
-  const [theme, setTheme] = useState('light')
-  
-  useEffect(() => {
-    // Runs after hydration - causes visible flash
-    const stored = localStorage.getItem('theme')
-    if (stored) {
-      setTheme(stored)
-    }
-  }, [])
-  
-  return (
-    <div className={theme}>
-      {children}
-    </div>
-  )
-}
-```
-
-Component first renders with default value (`light`), then updates after hydration, causing a visible flash of incorrect content.
-
-**Correct (no flicker, no hydration mismatch):**
-
-```tsx
-function ThemeWrapper({ children }: { children: ReactNode }) {
-  return (
-    <>
-      <div id="theme-wrapper">
-        {children}
-      </div>
-      <script
-        dangerouslySetInnerHTML={{
-          __html: `
-            (function() {
-              try {
-                var theme = localStorage.getItem('theme') || 'light';
-                var el = document.getElementById('theme-wrapper');
-                if (el) el.className = theme;
-              } catch (e) {}
-            })();
-          `,
-        }}
-      />
-    </>
-  )
-}
-```
-
-The inline script executes synchronously before showing the element, ensuring the DOM already has the correct value. No flickering, no hydration mismatch.
-
-This pattern is especially useful for theme toggles, user preferences, authentication states, and any client-only data that should render immediately without flashing default values.

.claude/skills/vercel-react-best-practices/rules/rendering-svg-precision.md

@@ -1,28 +0,0 @@
----
-title: Optimize SVG Precision
-impact: LOW
-impactDescription: reduces file size
-tags: rendering, svg, optimization, svgo
----
-
-## Optimize SVG Precision
-
-Reduce SVG coordinate precision to decrease file size. The optimal precision depends on the viewBox size, but in general reducing precision should be considered.
-
-**Incorrect (excessive precision):**
-
-```svg
-<path d="M 10.293847 20.847362 L 30.938472 40.192837" />
-```
-
-**Correct (1 decimal place):**
-
-```svg
-<path d="M 10.3 20.8 L 30.9 40.2" />
-```
-
-**Automate with SVGO:**
-
-```bash
-npx svgo --precision=1 --multipass icon.svg
-```

.claude/skills/vercel-react-best-practices/rules/rerender-defer-reads.md

@@ -1,39 +0,0 @@
----
-title: Defer State Reads to Usage Point
-impact: MEDIUM
-impactDescription: avoids unnecessary subscriptions
-tags: rerender, searchParams, localStorage, optimization
----
-
-## Defer State Reads to Usage Point
-
-Don't subscribe to dynamic state (searchParams, localStorage) if you only read it inside callbacks.
-
-**Incorrect (subscribes to all searchParams changes):**
-
-```tsx
-function ShareButton({ chatId }: { chatId: string }) {
-  const searchParams = useSearchParams()
-
-  const handleShare = () => {
-    const ref = searchParams.get('ref')
-    shareChat(chatId, { ref })
-  }
-
-  return <button onClick={handleShare}>Share</button>
-}
-```
-
-**Correct (reads on demand, no subscription):**
-
-```tsx
-function ShareButton({ chatId }: { chatId: string }) {
-  const handleShare = () => {
-    const params = new URLSearchParams(window.location.search)
-    const ref = params.get('ref')
-    shareChat(chatId, { ref })
-  }
-
-  return <button onClick={handleShare}>Share</button>
-}
-```

.claude/skills/vercel-react-best-practices/rules/rerender-dependencies.md

@@ -1,45 +0,0 @@
----
-title: Narrow Effect Dependencies
-impact: LOW
-impactDescription: minimizes effect re-runs
-tags: rerender, useEffect, dependencies, optimization
----
-
-## Narrow Effect Dependencies
-
-Specify primitive dependencies instead of objects to minimize effect re-runs.
-
-**Incorrect (re-runs on any user field change):**
-
-```tsx
-useEffect(() => {
-  console.log(user.id)
-}, [user])
-```
-
-**Correct (re-runs only when id changes):**
-
-```tsx
-useEffect(() => {
-  console.log(user.id)
-}, [user.id])
-```
-
-**For derived state, compute outside effect:**
-
-```tsx
-// Incorrect: runs on width=767, 766, 765...
-useEffect(() => {
-  if (width < 768) {
-    enableMobileMode()
-  }
-}, [width])
-
-// Correct: runs only on boolean transition
-const isMobile = width < 768
-useEffect(() => {
-  if (isMobile) {
-    enableMobileMode()
-  }
-}, [isMobile])
-```

.claude/skills/vercel-react-best-practices/rules/rerender-derived-state.md

@@ -1,29 +0,0 @@
----
-title: Subscribe to Derived State
-impact: MEDIUM
-impactDescription: reduces re-render frequency
-tags: rerender, derived-state, media-query, optimization
----
-
-## Subscribe to Derived State
-
-Subscribe to derived boolean state instead of continuous values to reduce re-render frequency.
-
-**Incorrect (re-renders on every pixel change):**
-
-```tsx
-function Sidebar() {
-  const width = useWindowWidth()  // updates continuously
-  const isMobile = width < 768
-  return <nav className={isMobile ? 'mobile' : 'desktop'}>
-}
-```
-
-**Correct (re-renders only when boolean changes):**
-
-```tsx
-function Sidebar() {
-  const isMobile = useMediaQuery('(max-width: 767px)')
-  return <nav className={isMobile ? 'mobile' : 'desktop'}>
-}
-```

.claude/skills/vercel-react-best-practices/rules/rerender-functional-setstate.md

@@ -1,74 +0,0 @@
----
-title: Use Functional setState Updates
-impact: MEDIUM
-impactDescription: prevents stale closures and unnecessary callback recreations
-tags: react, hooks, useState, useCallback, callbacks, closures
----
-
-## Use Functional setState Updates
-
-When updating state based on the current state value, use the functional update form of setState instead of directly referencing the state variable. This prevents stale closures, eliminates unnecessary dependencies, and creates stable callback references.
-
-**Incorrect (requires state as dependency):**
-
-```tsx
-function TodoList() {
-  const [items, setItems] = useState(initialItems)
-  
-  // Callback must depend on items, recreated on every items change
-  const addItems = useCallback((newItems: Item[]) => {
-    setItems([...items, ...newItems])
-  }, [items])  // ❌ items dependency causes recreations
-  
-  // Risk of stale closure if dependency is forgotten
-  const removeItem = useCallback((id: string) => {
-    setItems(items.filter(item => item.id !== id))
-  }, [])  // ❌ Missing items dependency - will use stale items!
-  
-  return <ItemsEditor items={items} onAdd={addItems} onRemove={removeItem} />
-}
-```
-
-The first callback is recreated every time `items` changes, which can cause child components to re-render unnecessarily. The second callback has a stale closure bug—it will always reference the initial `items` value.
-
-**Correct (stable callbacks, no stale closures):**
-
-```tsx
-function TodoList() {
-  const [items, setItems] = useState(initialItems)
-  
-  // Stable callback, never recreated
-  const addItems = useCallback((newItems: Item[]) => {
-    setItems(curr => [...curr, ...newItems])
-  }, [])  // ✅ No dependencies needed
-  
-  // Always uses latest state, no stale closure risk
-  const removeItem = useCallback((id: string) => {
-    setItems(curr => curr.filter(item => item.id !== id))
-  }, [])  // ✅ Safe and stable
-  
-  return <ItemsEditor items={items} onAdd={addItems} onRemove={removeItem} />
-}
-```
-
-**Benefits:**
-
-1. **Stable callback references** - Callbacks don't need to be recreated when state changes
-2. **No stale closures** - Always operates on the latest state value
-3. **Fewer dependencies** - Simplifies dependency arrays and reduces memory leaks
-4. **Prevents bugs** - Eliminates the most common source of React closure bugs
-
-**When to use functional updates:**
-
-- Any setState that depends on the current state value
-- Inside useCallback/useMemo when state is needed
-- Event handlers that reference state
-- Async operations that update state
-
-**When direct updates are fine:**
-
-- Setting state to a static value: `setCount(0)`
-- Setting state from props/arguments only: `setName(newName)`
-- State doesn't depend on previous value
-
-**Note:** If your project has [React Compiler](https://react.dev/learn/react-compiler) enabled, the compiler can automatically optimize some cases, but functional updates are still recommended for correctness and to prevent stale closure bugs.

.claude/skills/vercel-react-best-practices/rules/rerender-lazy-state-init.md

@@ -1,58 +0,0 @@
----
-title: Use Lazy State Initialization
-impact: MEDIUM
-impactDescription: wasted computation on every render
-tags: react, hooks, useState, performance, initialization
----
-
-## Use Lazy State Initialization
-
-Pass a function to `useState` for expensive initial values. Without the function form, the initializer runs on every render even though the value is only used once.
-
-**Incorrect (runs on every render):**
-
-```tsx
-function FilteredList({ items }: { items: Item[] }) {
-  // buildSearchIndex() runs on EVERY render, even after initialization
-  const [searchIndex, setSearchIndex] = useState(buildSearchIndex(items))
-  const [query, setQuery] = useState('')
-  
-  // When query changes, buildSearchIndex runs again unnecessarily
-  return <SearchResults index={searchIndex} query={query} />
-}
-
-function UserProfile() {
-  // JSON.parse runs on every render
-  const [settings, setSettings] = useState(
-    JSON.parse(localStorage.getItem('settings') || '{}')
-  )
-  
-  return <SettingsForm settings={settings} onChange={setSettings} />
-}
-```
-
-**Correct (runs only once):**
-
-```tsx
-function FilteredList({ items }: { items: Item[] }) {
-  // buildSearchIndex() runs ONLY on initial render
-  const [searchIndex, setSearchIndex] = useState(() => buildSearchIndex(items))
-  const [query, setQuery] = useState('')
-  
-  return <SearchResults index={searchIndex} query={query} />
-}
-
-function UserProfile() {
-  // JSON.parse runs only on initial render
-  const [settings, setSettings] = useState(() => {
-    const stored = localStorage.getItem('settings')
-    return stored ? JSON.parse(stored) : {}
-  })
-  
-  return <SettingsForm settings={settings} onChange={setSettings} />
-}
-```
-
-Use lazy initialization when computing initial values from localStorage/sessionStorage, building data structures (indexes, maps), reading from the DOM, or performing heavy transformations.
-
-For simple primitives (`useState(0)`), direct references (`useState(props.value)`), or cheap literals (`useState({})`), the function form is unnecessary.

.claude/skills/vercel-react-best-practices/rules/rerender-memo.md

@@ -1,44 +0,0 @@
----
-title: Extract to Memoized Components
-impact: MEDIUM
-impactDescription: enables early returns
-tags: rerender, memo, useMemo, optimization
----
-
-## Extract to Memoized Components
-
-Extract expensive work into memoized components to enable early returns before computation.
-
-**Incorrect (computes avatar even when loading):**
-
-```tsx
-function Profile({ user, loading }: Props) {
-  const avatar = useMemo(() => {
-    const id = computeAvatarId(user)
-    return <Avatar id={id} />
-  }, [user])
-
-  if (loading) return <Skeleton />
-  return <div>{avatar}</div>
-}
-```
-
-**Correct (skips computation when loading):**
-
-```tsx
-const UserAvatar = memo(function UserAvatar({ user }: { user: User }) {
-  const id = useMemo(() => computeAvatarId(user), [user])
-  return <Avatar id={id} />
-})
-
-function Profile({ user, loading }: Props) {
-  if (loading) return <Skeleton />
-  return (
-    <div>
-      <UserAvatar user={user} />
-    </div>
-  )
-}
-```
-
-**Note:** If your project has [React Compiler](https://react.dev/learn/react-compiler) enabled, manual memoization with `memo()` and `useMemo()` is not necessary. The compiler automatically optimizes re-renders.

.claude/skills/vercel-react-best-practices/rules/rerender-transitions.md

@@ -1,40 +0,0 @@
----
-title: Use Transitions for Non-Urgent Updates
-impact: MEDIUM
-impactDescription: maintains UI responsiveness
-tags: rerender, transitions, startTransition, performance
----
-
-## Use Transitions for Non-Urgent Updates
-
-Mark frequent, non-urgent state updates as transitions to maintain UI responsiveness.
-
-**Incorrect (blocks UI on every scroll):**
-
-```tsx
-function ScrollTracker() {
-  const [scrollY, setScrollY] = useState(0)
-  useEffect(() => {
-    const handler = () => setScrollY(window.scrollY)
-    window.addEventListener('scroll', handler, { passive: true })
-    return () => window.removeEventListener('scroll', handler)
-  }, [])
-}
-```
-
-**Correct (non-blocking updates):**
-
-```tsx
-import { startTransition } from 'react'
-
-function ScrollTracker() {
-  const [scrollY, setScrollY] = useState(0)
-  useEffect(() => {
-    const handler = () => {
-      startTransition(() => setScrollY(window.scrollY))
-    }
-    window.addEventListener('scroll', handler, { passive: true })
-    return () => window.removeEventListener('scroll', handler)
-  }, [])
-}
-```

.claude/skills/vercel-react-best-practices/rules/server-after-nonblocking.md

@@ -1,73 +0,0 @@
----
-title: Use after() for Non-Blocking Operations
-impact: MEDIUM
-impactDescription: faster response times
-tags: server, async, logging, analytics, side-effects
----
-
-## Use after() for Non-Blocking Operations
-
-Use Next.js's `after()` to schedule work that should execute after a response is sent. This prevents logging, analytics, and other side effects from blocking the response.
-
-**Incorrect (blocks response):**
-
-```tsx
-import { logUserAction } from '@/app/utils'
-
-export async function POST(request: Request) {
-  // Perform mutation
-  await updateDatabase(request)
-  
-  // Logging blocks the response
-  const userAgent = request.headers.get('user-agent') || 'unknown'
-  await logUserAction({ userAgent })
-  
-  return new Response(JSON.stringify({ status: 'success' }), {
-    status: 200,
-    headers: { 'Content-Type': 'application/json' }
-  })
-}
-```
-
-**Correct (non-blocking):**
-
-```tsx
-import { after } from 'next/server'
-import { headers, cookies } from 'next/headers'
-import { logUserAction } from '@/app/utils'
-
-export async function POST(request: Request) {
-  // Perform mutation
-  await updateDatabase(request)
-  
-  // Log after response is sent
-  after(async () => {
-    const userAgent = (await headers()).get('user-agent') || 'unknown'
-    const sessionCookie = (await cookies()).get('session-id')?.value || 'anonymous'
-    
-    logUserAction({ sessionCookie, userAgent })
-  })
-  
-  return new Response(JSON.stringify({ status: 'success' }), {
-    status: 200,
-    headers: { 'Content-Type': 'application/json' }
-  })
-}
-```
-
-The response is sent immediately while logging happens in the background.
-
-**Common use cases:**
-
-- Analytics tracking
-- Audit logging
-- Sending notifications
-- Cache invalidation
-- Cleanup tasks
-
-**Important notes:**
-
-- `after()` runs even if the response fails or redirects
-- Works in Server Actions, Route Handlers, and Server Components
-
-Reference: [https://nextjs.org/docs/app/api-reference/functions/after](https://nextjs.org/docs/app/api-reference/functions/after)

.claude/skills/vercel-react-best-practices/rules/server-cache-lru.md

@@ -1,41 +0,0 @@
----
-title: Cross-Request LRU Caching
-impact: HIGH
-impactDescription: caches across requests
-tags: server, cache, lru, cross-request
----
-
-## Cross-Request LRU Caching
-
-`React.cache()` only works within one request. For data shared across sequential requests (user clicks button A then button B), use an LRU cache.
-
-**Implementation:**
-
-```typescript
-import { LRUCache } from 'lru-cache'
-
-const cache = new LRUCache<string, any>({
-  max: 1000,
-  ttl: 5 * 60 * 1000  // 5 minutes
-})
-
-export async function getUser(id: string) {
-  const cached = cache.get(id)
-  if (cached) return cached
-
-  const user = await db.user.findUnique({ where: { id } })
-  cache.set(id, user)
-  return user
-}
-
-// Request 1: DB query, result cached
-// Request 2: cache hit, no DB query
-```
-
-Use when sequential user actions hit multiple endpoints needing the same data within seconds.
-
-**With Vercel's [Fluid Compute](https://vercel.com/docs/fluid-compute):** LRU caching is especially effective because multiple concurrent requests can share the same function instance and cache. This means the cache persists across requests without needing external storage like Redis.
-
-**In traditional serverless:** Each invocation runs in isolation, so consider Redis for cross-process caching.
-
-Reference: [https://github.com/isaacs/node-lru-cache](https://github.com/isaacs/node-lru-cache)

.claude/skills/vercel-react-best-practices/rules/server-cache-react.md

@@ -1,26 +0,0 @@
----
-title: Per-Request Deduplication with React.cache()
-impact: MEDIUM
-impactDescription: deduplicates within request
-tags: server, cache, react-cache, deduplication
----
-
-## Per-Request Deduplication with React.cache()
-
-Use `React.cache()` for server-side request deduplication. Authentication and database queries benefit most.
-
-**Usage:**
-
-```typescript
-import { cache } from 'react'
-
-export const getCurrentUser = cache(async () => {
-  const session = await auth()
-  if (!session?.user?.id) return null
-  return await db.user.findUnique({
-    where: { id: session.user.id }
-  })
-})
-```
-
-Within a single request, multiple calls to `getCurrentUser()` execute the query only once.

.claude/skills/vercel-react-best-practices/rules/server-parallel-fetching.md

@@ -1,79 +0,0 @@
----
-title: Parallel Data Fetching with Component Composition
-impact: CRITICAL
-impactDescription: eliminates server-side waterfalls
-tags: server, rsc, parallel-fetching, composition
----
-
-## Parallel Data Fetching with Component Composition
-
-React Server Components execute sequentially within a tree. Restructure with composition to parallelize data fetching.
-
-**Incorrect (Sidebar waits for Page's fetch to complete):**
-
-```tsx
-export default async function Page() {
-  const header = await fetchHeader()
-  return (
-    <div>
-      <div>{header}</div>
-      <Sidebar />
-    </div>
-  )
-}
-
-async function Sidebar() {
-  const items = await fetchSidebarItems()
-  return <nav>{items.map(renderItem)}</nav>
-}
-```
-
-**Correct (both fetch simultaneously):**
-
-```tsx
-async function Header() {
-  const data = await fetchHeader()
-  return <div>{data}</div>
-}
-
-async function Sidebar() {
-  const items = await fetchSidebarItems()
-  return <nav>{items.map(renderItem)}</nav>
-}
-
-export default function Page() {
-  return (
-    <div>
-      <Header />
-      <Sidebar />
-    </div>
-  )
-}
-```
-
-**Alternative with children prop:**
-
-```tsx
-async function Layout({ children }: { children: ReactNode }) {
-  const header = await fetchHeader()
-  return (
-    <div>
-      <div>{header}</div>
-      {children}
-    </div>
-  )
-}
-
-async function Sidebar() {
-  const items = await fetchSidebarItems()
-  return <nav>{items.map(renderItem)}</nav>
-}
-
-export default function Page() {
-  return (
-    <Layout>
-      <Sidebar />
-    </Layout>
-  )
-}
-```

.claude/skills/vercel-react-best-practices/rules/server-serialization.md

@@ -1,38 +0,0 @@
----
-title: Minimize Serialization at RSC Boundaries
-impact: HIGH
-impactDescription: reduces data transfer size
-tags: server, rsc, serialization, props
----
-
-## Minimize Serialization at RSC Boundaries
-
-The React Server/Client boundary serializes all object properties into strings and embeds them in the HTML response and subsequent RSC requests. This serialized data directly impacts page weight and load time, so **size matters a lot**. Only pass fields that the client actually uses.
-
-**Incorrect (serializes all 50 fields):**
-
-```tsx
-async function Page() {
-  const user = await fetchUser()  // 50 fields
-  return <Profile user={user} />
-}
-
-'use client'
-function Profile({ user }: { user: User }) {
-  return <div>{user.name}</div>  // uses 1 field
-}
-```
-
-**Correct (serializes only 1 field):**
-
-```tsx
-async function Page() {
-  const user = await fetchUser()
-  return <Profile name={user.name} />
-}
-
-'use client'
-function Profile({ name }: { name: string }) {
-  return <div>{name}</div>
-}
-```

.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/workflows/claude-dependabot.yml

@@ -36,7 +36,7 @@ jobs:
 
       # Backend Python/Poetry setup (mirrors platform-backend-ci.yml)
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.11"  # Use standard version matching CI
 
@@ -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

.github/workflows/claude.yml

@@ -52,7 +52,7 @@ jobs:
 
       # Backend Python/Poetry setup (mirrors platform-backend-ci.yml)
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.11"  # Use standard version matching CI
 
@@ -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

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

@@ -34,7 +34,7 @@ jobs:
 
       # Backend Python/Poetry setup (mirrors platform-backend-ci.yml)
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.11"  # Use standard version matching CI
 
@@ -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
 

.github/workflows/platform-autogpt-deploy-dev.yaml

@@ -30,7 +30,7 @@ jobs:
           ref: ${{ github.event.inputs.git_ref || github.ref_name }}
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: '3.11'
 

.github/workflows/platform-autogpt-deploy-prod.yml

@@ -22,7 +22,7 @@ jobs:
           ref: ${{ github.ref_name || 'master' }}
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: '3.11'
 

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

@@ -74,7 +74,7 @@ jobs:
           submodules: true
 
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: ${{ matrix.python-version }}
 
@@ -134,7 +134,7 @@ jobs:
         run: poetry install
 
       - name: Generate Prisma Client
-        run: poetry run prisma generate && poetry run gen-prisma-stub
+        run: poetry run prisma generate
 
       - id: supabase
         name: Start Supabase
@@ -176,7 +176,7 @@ 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 }}

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

@@ -11,7 +11,6 @@ on:
       - ".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) }}
@@ -152,14 +151,6 @@ jobs:
         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 +226,13 @@ 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/repo-close-stale-issues.yml

@@ -11,7 +11,7 @@ jobs:
   stale:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@v10
+      - uses: actions/stale@v9
         with:
           # operations-per-run: 5000
           stale-issue-message: >

.github/workflows/repo-pr-label.yml

@@ -61,6 +61,6 @@ jobs:
       pull-requests: write
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/labeler@v6
+      - uses: actions/labeler@v5
         with:
           sync-labels: true

.github/workflows/repo-workflow-checker.yml

@@ -15,7 +15,7 @@ jobs:
         # with:
           # fetch-depth: 0
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v6
         with:
           python-version: "3.10"
       - name: Install dependencies

autogpt_platform/Makefile

@@ -6,14 +6,12 @@ start-core:
 
 # 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
@@ -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/api_key/keysmith.py

@@ -57,9 +57,6 @@ class APIKeySmith:
 
     def hash_key(self, raw_key: str) -> tuple[str, str]:
         """Migrate a legacy hash to secure hash format."""
-        if not raw_key.startswith(self.PREFIX):
-            raise ValueError("Key without 'agpt_' prefix would fail validation")
-
         salt = self._generate_salt()
         hash = self._hash_key_with_salt(raw_key, salt)
         return hash, salt.hex()

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/backend/.env.default

@@ -58,13 +58,6 @@ 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 +18,3 @@ load-tests/results/
 load-tests/*.json
 load-tests/*.log
 load-tests/node_modules/*
-migrations/*/rollback*.sql

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

@@ -1,25 +0,0 @@
-from fastapi import FastAPI
-
-from backend.api.middleware.security import SecurityHeadersMiddleware
-from backend.monitoring.instrumentation import instrument_fastapi
-
-from .v1.routes import v1_router
-
-external_api = FastAPI(
-    title="AutoGPT External API",
-    description="External API for AutoGPT integrations",
-    docs_url="/docs",
-    version="1.0",
-)
-
-external_api.add_middleware(SecurityHeadersMiddleware)
-external_api.include_router(v1_router, prefix="/v1")
-
-# Add Prometheus instrumentation
-instrument_fastapi(
-    external_api,
-    service_name="external-api",
-    expose_endpoint=True,
-    endpoint="/metrics",
-    include_in_schema=True,
-)

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

@@ -1,107 +0,0 @@
-from fastapi import HTTPException, Security, status
-from fastapi.security import APIKeyHeader, HTTPAuthorizationCredentials, HTTPBearer
-from prisma.enums import APIKeyPermission
-
-from backend.data.auth.api_key import APIKeyInfo, validate_api_key
-from backend.data.auth.base import APIAuthorizationInfo
-from backend.data.auth.oauth import (
-    InvalidClientError,
-    InvalidTokenError,
-    OAuthAccessTokenInfo,
-    validate_access_token,
-)
-
-api_key_header = APIKeyHeader(name="X-API-Key", auto_error=False)
-bearer_auth = HTTPBearer(auto_error=False)
-
-
-async def require_api_key(api_key: str | None = Security(api_key_header)) -> APIKeyInfo:
-    """Middleware for API key authentication only"""
-    if api_key is None:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED, detail="Missing API key"
-        )
-
-    api_key_obj = await validate_api_key(api_key)
-
-    if not api_key_obj:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED, detail="Invalid API key"
-        )
-
-    return api_key_obj
-
-
-async def require_access_token(
-    bearer: HTTPAuthorizationCredentials | None = Security(bearer_auth),
-) -> OAuthAccessTokenInfo:
-    """Middleware for OAuth access token authentication only"""
-    if bearer is None:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail="Missing Authorization header",
-        )
-
-    try:
-        token_info, _ = await validate_access_token(bearer.credentials)
-    except (InvalidClientError, InvalidTokenError) as e:
-        raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail=str(e))
-
-    return token_info
-
-
-async def require_auth(
-    api_key: str | None = Security(api_key_header),
-    bearer: HTTPAuthorizationCredentials | None = Security(bearer_auth),
-) -> APIAuthorizationInfo:
-    """
-    Unified authentication middleware supporting both API keys and OAuth tokens.
-
-    Supports two authentication methods, which are checked in order:
-    1. X-API-Key header (existing API key authentication)
-    2. Authorization: Bearer <token> header (OAuth access token)
-
-    Returns:
-        APIAuthorizationInfo: base class of both APIKeyInfo and OAuthAccessTokenInfo.
-    """
-    # Try API key first
-    if api_key is not None:
-        api_key_info = await validate_api_key(api_key)
-        if api_key_info:
-            return api_key_info
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED, detail="Invalid API key"
-        )
-
-    # Try OAuth bearer token
-    if bearer is not None:
-        try:
-            token_info, _ = await validate_access_token(bearer.credentials)
-            return token_info
-        except (InvalidClientError, InvalidTokenError) as e:
-            raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail=str(e))
-
-    # No credentials provided
-    raise HTTPException(
-        status_code=status.HTTP_401_UNAUTHORIZED,
-        detail="Missing authentication. Provide API key or access token.",
-    )
-
-
-def require_permission(permission: APIKeyPermission):
-    """
-    Dependency function for checking specific permissions
-    (works with API keys and OAuth tokens)
-    """
-
-    async def check_permission(
-        auth: APIAuthorizationInfo = Security(require_auth),
-    ) -> APIAuthorizationInfo:
-        if permission not in auth.scopes:
-            raise HTTPException(
-                status_code=status.HTTP_403_FORBIDDEN,
-                detail=f"Missing required permission: {permission.value}",
-            )
-        return auth
-
-    return check_permission

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/oauth.py

@@ -1,833 +0,0 @@
-"""
-OAuth 2.0 Provider Endpoints
-
-Implements OAuth 2.0 Authorization Code flow with PKCE support.
-
-Flow:
-1. User clicks "Login with AutoGPT" in 3rd party app
-2. App redirects user to /auth/authorize with client_id, redirect_uri, scope, state
-3. User sees consent screen (if not already logged in, redirects to login first)
-4. User approves → backend creates authorization code
-5. User redirected back to app with code
-6. App exchanges code for access/refresh tokens at /api/oauth/token
-7. App uses access token to call external API endpoints
-"""
-
-import io
-import logging
-import os
-import uuid
-from datetime import datetime
-from typing import Literal, Optional
-from urllib.parse import urlencode
-
-from autogpt_libs.auth import get_user_id
-from fastapi import APIRouter, Body, HTTPException, Security, UploadFile, status
-from gcloud.aio import storage as async_storage
-from PIL import Image
-from prisma.enums import APIKeyPermission
-from pydantic import BaseModel, Field
-
-from backend.data.auth.oauth import (
-    InvalidClientError,
-    InvalidGrantError,
-    OAuthApplicationInfo,
-    TokenIntrospectionResult,
-    consume_authorization_code,
-    create_access_token,
-    create_authorization_code,
-    create_refresh_token,
-    get_oauth_application,
-    get_oauth_application_by_id,
-    introspect_token,
-    list_user_oauth_applications,
-    refresh_tokens,
-    revoke_access_token,
-    revoke_refresh_token,
-    update_oauth_application,
-    validate_client_credentials,
-    validate_redirect_uri,
-    validate_scopes,
-)
-from backend.util.settings import Settings
-from backend.util.virus_scanner import scan_content_safe
-
-settings = Settings()
-logger = logging.getLogger(__name__)
-
-router = APIRouter()
-
-
-# ============================================================================
-# Request/Response Models
-# ============================================================================
-
-
-class TokenResponse(BaseModel):
-    """OAuth 2.0 token response"""
-
-    token_type: Literal["Bearer"] = "Bearer"
-    access_token: str
-    access_token_expires_at: datetime
-    refresh_token: str
-    refresh_token_expires_at: datetime
-    scopes: list[str]
-
-
-class ErrorResponse(BaseModel):
-    """OAuth 2.0 error response"""
-
-    error: str
-    error_description: Optional[str] = None
-
-
-class OAuthApplicationPublicInfo(BaseModel):
-    """Public information about an OAuth application (for consent screen)"""
-
-    name: str
-    description: Optional[str] = None
-    logo_url: Optional[str] = None
-    scopes: list[str]
-
-
-# ============================================================================
-# Application Info Endpoint
-# ============================================================================
-
-
-@router.get(
-    "/app/{client_id}",
-    responses={
-        404: {"description": "Application not found or disabled"},
-    },
-)
-async def get_oauth_app_info(
-    client_id: str, user_id: str = Security(get_user_id)
-) -> OAuthApplicationPublicInfo:
-    """
-    Get public information about an OAuth application.
-
-    This endpoint is used by the consent screen to display application details
-    to the user before they authorize access.
-
-    Returns:
-    - name: Application name
-    - description: Application description (if provided)
-    - scopes: List of scopes the application is allowed to request
-    """
-    app = await get_oauth_application(client_id)
-    if not app or not app.is_active:
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail="Application not found",
-        )
-
-    return OAuthApplicationPublicInfo(
-        name=app.name,
-        description=app.description,
-        logo_url=app.logo_url,
-        scopes=[s.value for s in app.scopes],
-    )
-
-
-# ============================================================================
-# Authorization Endpoint
-# ============================================================================
-
-
-class AuthorizeRequest(BaseModel):
-    """OAuth 2.0 authorization request"""
-
-    client_id: str = Field(description="Client identifier")
-    redirect_uri: str = Field(description="Redirect URI")
-    scopes: list[str] = Field(description="List of scopes")
-    state: str = Field(description="Anti-CSRF token from client")
-    response_type: str = Field(
-        default="code", description="Must be 'code' for authorization code flow"
-    )
-    code_challenge: str = Field(description="PKCE code challenge (required)")
-    code_challenge_method: Literal["S256", "plain"] = Field(
-        default="S256", description="PKCE code challenge method (S256 recommended)"
-    )
-
-
-class AuthorizeResponse(BaseModel):
-    """OAuth 2.0 authorization response with redirect URL"""
-
-    redirect_url: str = Field(description="URL to redirect the user to")
-
-
-@router.post("/authorize")
-async def authorize(
-    request: AuthorizeRequest = Body(),
-    user_id: str = Security(get_user_id),
-) -> AuthorizeResponse:
-    """
-    OAuth 2.0 Authorization Endpoint
-
-    User must be logged in (authenticated with Supabase JWT).
-    This endpoint creates an authorization code and returns a redirect URL.
-
-    PKCE (Proof Key for Code Exchange) is REQUIRED for all authorization requests.
-
-    The frontend consent screen should call this endpoint after the user approves,
-    then redirect the user to the returned `redirect_url`.
-
-    Request Body:
-    - client_id: The OAuth application's client ID
-    - redirect_uri: Where to redirect after authorization (must match registered URI)
-    - scopes: List of permissions (e.g., "EXECUTE_GRAPH READ_GRAPH")
-    - state: Anti-CSRF token provided by client (will be returned in redirect)
-    - response_type: Must be "code" (for authorization code flow)
-    - code_challenge: PKCE code challenge (required)
-    - code_challenge_method: "S256" (recommended) or "plain"
-
-    Returns:
-    - redirect_url: The URL to redirect the user to (includes authorization code)
-
-    Error cases return a redirect_url with error parameters, or raise HTTPException
-    for critical errors (like invalid redirect_uri).
-    """
-    try:
-        # Validate response_type
-        if request.response_type != "code":
-            return _error_redirect_url(
-                request.redirect_uri,
-                request.state,
-                "unsupported_response_type",
-                "Only 'code' response type is supported",
-            )
-
-        # Get application
-        app = await get_oauth_application(request.client_id)
-        if not app:
-            return _error_redirect_url(
-                request.redirect_uri,
-                request.state,
-                "invalid_client",
-                "Unknown client_id",
-            )
-
-        if not app.is_active:
-            return _error_redirect_url(
-                request.redirect_uri,
-                request.state,
-                "invalid_client",
-                "Application is not active",
-            )
-
-        # Validate redirect URI
-        if not validate_redirect_uri(app, request.redirect_uri):
-            # For invalid redirect_uri, we can't redirect safely
-            # Must return error instead
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail=(
-                    "Invalid redirect_uri. "
-                    f"Must be one of: {', '.join(app.redirect_uris)}"
-                ),
-            )
-
-        # Parse and validate scopes
-        try:
-            requested_scopes = [APIKeyPermission(s.strip()) for s in request.scopes]
-        except ValueError as e:
-            return _error_redirect_url(
-                request.redirect_uri,
-                request.state,
-                "invalid_scope",
-                f"Invalid scope: {e}",
-            )
-
-        if not requested_scopes:
-            return _error_redirect_url(
-                request.redirect_uri,
-                request.state,
-                "invalid_scope",
-                "At least one scope is required",
-            )
-
-        if not validate_scopes(app, requested_scopes):
-            return _error_redirect_url(
-                request.redirect_uri,
-                request.state,
-                "invalid_scope",
-                "Application is not authorized for all requested scopes. "
-                f"Allowed: {', '.join(s.value for s in app.scopes)}",
-            )
-
-        # Create authorization code
-        auth_code = await create_authorization_code(
-            application_id=app.id,
-            user_id=user_id,
-            scopes=requested_scopes,
-            redirect_uri=request.redirect_uri,
-            code_challenge=request.code_challenge,
-            code_challenge_method=request.code_challenge_method,
-        )
-
-        # Build redirect URL with authorization code
-        params = {
-            "code": auth_code.code,
-            "state": request.state,
-        }
-        redirect_url = f"{request.redirect_uri}?{urlencode(params)}"
-
-        logger.info(
-            f"Authorization code issued for user #{user_id} "
-            f"and app {app.name} (#{app.id})"
-        )
-
-        return AuthorizeResponse(redirect_url=redirect_url)
-
-    except HTTPException:
-        raise
-    except Exception as e:
-        logger.error(f"Error in authorization endpoint: {e}", exc_info=True)
-        return _error_redirect_url(
-            request.redirect_uri,
-            request.state,
-            "server_error",
-            "An unexpected error occurred",
-        )
-
-
-def _error_redirect_url(
-    redirect_uri: str,
-    state: str,
-    error: str,
-    error_description: Optional[str] = None,
-) -> AuthorizeResponse:
-    """Helper to build redirect URL with OAuth error parameters"""
-    params = {
-        "error": error,
-        "state": state,
-    }
-    if error_description:
-        params["error_description"] = error_description
-
-    redirect_url = f"{redirect_uri}?{urlencode(params)}"
-    return AuthorizeResponse(redirect_url=redirect_url)
-
-
-# ============================================================================
-# Token Endpoint
-# ============================================================================
-
-
-class TokenRequestByCode(BaseModel):
-    grant_type: Literal["authorization_code"]
-    code: str = Field(description="Authorization code")
-    redirect_uri: str = Field(
-        description="Redirect URI (must match authorization request)"
-    )
-    client_id: str
-    client_secret: str
-    code_verifier: str = Field(description="PKCE code verifier")
-
-
-class TokenRequestByRefreshToken(BaseModel):
-    grant_type: Literal["refresh_token"]
-    refresh_token: str
-    client_id: str
-    client_secret: str
-
-
-@router.post("/token")
-async def token(
-    request: TokenRequestByCode | TokenRequestByRefreshToken = Body(),
-) -> TokenResponse:
-    """
-    OAuth 2.0 Token Endpoint
-
-    Exchanges authorization code or refresh token for access token.
-
-    Grant Types:
-    1. authorization_code: Exchange authorization code for tokens
-       - Required: grant_type, code, redirect_uri, client_id, client_secret
-       - Optional: code_verifier (required if PKCE was used)
-
-    2. refresh_token: Exchange refresh token for new access token
-       - Required: grant_type, refresh_token, client_id, client_secret
-
-    Returns:
-    - access_token: Bearer token for API access (1 hour TTL)
-    - token_type: "Bearer"
-    - expires_in: Seconds until access token expires
-    - refresh_token: Token for refreshing access (30 days TTL)
-    - scopes: List of scopes
-    """
-    # Validate client credentials
-    try:
-        app = await validate_client_credentials(
-            request.client_id, request.client_secret
-        )
-    except InvalidClientError as e:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=str(e),
-        )
-
-    # Handle authorization_code grant
-    if request.grant_type == "authorization_code":
-        # Consume authorization code
-        try:
-            user_id, scopes = await consume_authorization_code(
-                code=request.code,
-                application_id=app.id,
-                redirect_uri=request.redirect_uri,
-                code_verifier=request.code_verifier,
-            )
-        except InvalidGrantError as e:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail=str(e),
-            )
-
-        # Create access and refresh tokens
-        access_token = await create_access_token(app.id, user_id, scopes)
-        refresh_token = await create_refresh_token(app.id, user_id, scopes)
-
-        logger.info(
-            f"Access token issued for user #{user_id} and app {app.name} (#{app.id})"
-            "via authorization code"
-        )
-
-        if not access_token.token or not refresh_token.token:
-            raise HTTPException(
-                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail="Failed to generate tokens",
-            )
-
-        return TokenResponse(
-            token_type="Bearer",
-            access_token=access_token.token.get_secret_value(),
-            access_token_expires_at=access_token.expires_at,
-            refresh_token=refresh_token.token.get_secret_value(),
-            refresh_token_expires_at=refresh_token.expires_at,
-            scopes=list(s.value for s in scopes),
-        )
-
-    # Handle refresh_token grant
-    elif request.grant_type == "refresh_token":
-        # Refresh access token
-        try:
-            new_access_token, new_refresh_token = await refresh_tokens(
-                request.refresh_token, app.id
-            )
-        except InvalidGrantError as e:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail=str(e),
-            )
-
-        logger.info(
-            f"Tokens refreshed for user #{new_access_token.user_id} "
-            f"by app {app.name} (#{app.id})"
-        )
-
-        if not new_access_token.token or not new_refresh_token.token:
-            raise HTTPException(
-                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                detail="Failed to generate tokens",
-            )
-
-        return TokenResponse(
-            token_type="Bearer",
-            access_token=new_access_token.token.get_secret_value(),
-            access_token_expires_at=new_access_token.expires_at,
-            refresh_token=new_refresh_token.token.get_secret_value(),
-            refresh_token_expires_at=new_refresh_token.expires_at,
-            scopes=list(s.value for s in new_access_token.scopes),
-        )
-
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=f"Unsupported grant_type: {request.grant_type}. "
-            "Must be 'authorization_code' or 'refresh_token'",
-        )
-
-
-# ============================================================================
-# Token Introspection Endpoint
-# ============================================================================
-
-
-@router.post("/introspect")
-async def introspect(
-    token: str = Body(description="Token to introspect"),
-    token_type_hint: Optional[Literal["access_token", "refresh_token"]] = Body(
-        None, description="Hint about token type ('access_token' or 'refresh_token')"
-    ),
-    client_id: str = Body(description="Client identifier"),
-    client_secret: str = Body(description="Client secret"),
-) -> TokenIntrospectionResult:
-    """
-    OAuth 2.0 Token Introspection Endpoint (RFC 7662)
-
-    Allows clients to check if a token is valid and get its metadata.
-
-    Returns:
-    - active: Whether the token is currently active
-    - scopes: List of authorized scopes (if active)
-    - client_id: The client the token was issued to (if active)
-    - user_id: The user the token represents (if active)
-    - exp: Expiration timestamp (if active)
-    - token_type: "access_token" or "refresh_token" (if active)
-    """
-    # Validate client credentials
-    try:
-        await validate_client_credentials(client_id, client_secret)
-    except InvalidClientError as e:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=str(e),
-        )
-
-    # Introspect the token
-    return await introspect_token(token, token_type_hint)
-
-
-# ============================================================================
-# Token Revocation Endpoint
-# ============================================================================
-
-
-@router.post("/revoke")
-async def revoke(
-    token: str = Body(description="Token to revoke"),
-    token_type_hint: Optional[Literal["access_token", "refresh_token"]] = Body(
-        None, description="Hint about token type ('access_token' or 'refresh_token')"
-    ),
-    client_id: str = Body(description="Client identifier"),
-    client_secret: str = Body(description="Client secret"),
-):
-    """
-    OAuth 2.0 Token Revocation Endpoint (RFC 7009)
-
-    Allows clients to revoke an access or refresh token.
-
-    Note: Revoking a refresh token does NOT revoke associated access tokens.
-    Revoking an access token does NOT revoke the associated refresh token.
-    """
-    # Validate client credentials
-    try:
-        app = await validate_client_credentials(client_id, client_secret)
-    except InvalidClientError as e:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=str(e),
-        )
-
-    # Try to revoke as access token first
-    # Note: We pass app.id to ensure the token belongs to the authenticated app
-    if token_type_hint != "refresh_token":
-        revoked = await revoke_access_token(token, app.id)
-        if revoked:
-            logger.info(
-                f"Access token revoked for app {app.name} (#{app.id}); "
-                f"user #{revoked.user_id}"
-            )
-            return {"status": "ok"}
-
-    # Try to revoke as refresh token
-    revoked = await revoke_refresh_token(token, app.id)
-    if revoked:
-        logger.info(
-            f"Refresh token revoked for app {app.name} (#{app.id}); "
-            f"user #{revoked.user_id}"
-        )
-        return {"status": "ok"}
-
-    # Per RFC 7009, revocation endpoint returns 200 even if token not found
-    # or if token belongs to a different application.
-    # This prevents token scanning attacks.
-    logger.warning(f"Unsuccessful token revocation attempt by app {app.name} #{app.id}")
-    return {"status": "ok"}
-
-
-# ============================================================================
-# Application Management Endpoints (for app owners)
-# ============================================================================
-
-
-@router.get("/apps/mine")
-async def list_my_oauth_apps(
-    user_id: str = Security(get_user_id),
-) -> list[OAuthApplicationInfo]:
-    """
-    List all OAuth applications owned by the current user.
-
-    Returns a list of OAuth applications with their details including:
-    - id, name, description, logo_url
-    - client_id (public identifier)
-    - redirect_uris, grant_types, scopes
-    - is_active status
-    - created_at, updated_at timestamps
-
-    Note: client_secret is never returned for security reasons.
-    """
-    return await list_user_oauth_applications(user_id)
-
-
-@router.patch("/apps/{app_id}/status")
-async def update_app_status(
-    app_id: str,
-    user_id: str = Security(get_user_id),
-    is_active: bool = Body(description="Whether the app should be active", embed=True),
-) -> OAuthApplicationInfo:
-    """
-    Enable or disable an OAuth application.
-
-    Only the application owner can update the status.
-    When disabled, the application cannot be used for new authorizations
-    and existing access tokens will fail validation.
-
-    Returns the updated application info.
-    """
-    updated_app = await update_oauth_application(
-        app_id=app_id,
-        owner_id=user_id,
-        is_active=is_active,
-    )
-
-    if not updated_app:
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail="Application not found or you don't have permission to update it",
-        )
-
-    action = "enabled" if is_active else "disabled"
-    logger.info(f"OAuth app {updated_app.name} (#{app_id}) {action} by user #{user_id}")
-
-    return updated_app
-
-
-class UpdateAppLogoRequest(BaseModel):
-    logo_url: str = Field(description="URL of the uploaded logo image")
-
-
-@router.patch("/apps/{app_id}/logo")
-async def update_app_logo(
-    app_id: str,
-    request: UpdateAppLogoRequest = Body(),
-    user_id: str = Security(get_user_id),
-) -> OAuthApplicationInfo:
-    """
-    Update the logo URL for an OAuth application.
-
-    Only the application owner can update the logo.
-    The logo should be uploaded first using the media upload endpoint,
-    then this endpoint is called with the resulting URL.
-
-    Logo requirements:
-    - Must be square (1:1 aspect ratio)
-    - Minimum 512x512 pixels
-    - Maximum 2048x2048 pixels
-
-    Returns the updated application info.
-    """
-    if (
-        not (app := await get_oauth_application_by_id(app_id))
-        or app.owner_id != user_id
-    ):
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail="OAuth App not found",
-        )
-
-    # Delete the current app logo file (if any and it's in our cloud storage)
-    await _delete_app_current_logo_file(app)
-
-    updated_app = await update_oauth_application(
-        app_id=app_id,
-        owner_id=user_id,
-        logo_url=request.logo_url,
-    )
-
-    if not updated_app:
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail="Application not found or you don't have permission to update it",
-        )
-
-    logger.info(
-        f"OAuth app {updated_app.name} (#{app_id}) logo updated by user #{user_id}"
-    )
-
-    return updated_app
-
-
-# Logo upload constraints
-LOGO_MIN_SIZE = 512
-LOGO_MAX_SIZE = 2048
-LOGO_ALLOWED_TYPES = {"image/jpeg", "image/png", "image/webp"}
-LOGO_MAX_FILE_SIZE = 3 * 1024 * 1024  # 3MB
-
-
-@router.post("/apps/{app_id}/logo/upload")
-async def upload_app_logo(
-    app_id: str,
-    file: UploadFile,
-    user_id: str = Security(get_user_id),
-) -> OAuthApplicationInfo:
-    """
-    Upload a logo image for an OAuth application.
-
-    Requirements:
-    - Image must be square (1:1 aspect ratio)
-    - Minimum 512x512 pixels
-    - Maximum 2048x2048 pixels
-    - Allowed formats: JPEG, PNG, WebP
-    - Maximum file size: 3MB
-
-    The image is uploaded to cloud storage and the app's logoUrl is updated.
-    Returns the updated application info.
-    """
-    # Verify ownership to reduce vulnerability to DoS(torage) or DoM(oney) attacks
-    if (
-        not (app := await get_oauth_application_by_id(app_id))
-        or app.owner_id != user_id
-    ):
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail="OAuth App not found",
-        )
-
-    # Check GCS configuration
-    if not settings.config.media_gcs_bucket_name:
-        raise HTTPException(
-            status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
-            detail="Media storage is not configured",
-        )
-
-    # Validate content type
-    content_type = file.content_type
-    if content_type not in LOGO_ALLOWED_TYPES:
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=f"Invalid file type. Allowed: JPEG, PNG, WebP. Got: {content_type}",
-        )
-
-    # Read file content
-    try:
-        file_bytes = await file.read()
-    except Exception as e:
-        logger.error(f"Error reading logo file: {e}")
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail="Failed to read uploaded file",
-        )
-
-    # Check file size
-    if len(file_bytes) > LOGO_MAX_FILE_SIZE:
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=(
-                "File too large. "
-                f"Maximum size is {LOGO_MAX_FILE_SIZE // 1024 // 1024}MB"
-            ),
-        )
-
-    # Validate image dimensions
-    try:
-        image = Image.open(io.BytesIO(file_bytes))
-        width, height = image.size
-
-        if width != height:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail=f"Logo must be square. Got {width}x{height}",
-            )
-
-        if width < LOGO_MIN_SIZE:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail=f"Logo too small. Minimum {LOGO_MIN_SIZE}x{LOGO_MIN_SIZE}. "
-                f"Got {width}x{height}",
-            )
-
-        if width > LOGO_MAX_SIZE:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail=f"Logo too large. Maximum {LOGO_MAX_SIZE}x{LOGO_MAX_SIZE}. "
-                f"Got {width}x{height}",
-            )
-    except HTTPException:
-        raise
-    except Exception as e:
-        logger.error(f"Error validating logo image: {e}")
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail="Invalid image file",
-        )
-
-    # Scan for viruses
-    filename = file.filename or "logo"
-    await scan_content_safe(file_bytes, filename=filename)
-
-    # Generate unique filename
-    file_ext = os.path.splitext(filename)[1].lower() or ".png"
-    unique_filename = f"{uuid.uuid4()}{file_ext}"
-    storage_path = f"oauth-apps/{app_id}/logo/{unique_filename}"
-
-    # Upload to GCS
-    try:
-        async with async_storage.Storage() as async_client:
-            bucket_name = settings.config.media_gcs_bucket_name
-
-            await async_client.upload(
-                bucket_name, storage_path, file_bytes, content_type=content_type
-            )
-
-            logo_url = f"https://storage.googleapis.com/{bucket_name}/{storage_path}"
-    except Exception as e:
-        logger.error(f"Error uploading logo to GCS: {e}")
-        raise HTTPException(
-            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail="Failed to upload logo",
-        )
-
-    # Delete the current app logo file (if any and it's in our cloud storage)
-    await _delete_app_current_logo_file(app)
-
-    # Update the app with the new logo URL
-    updated_app = await update_oauth_application(
-        app_id=app_id,
-        owner_id=user_id,
-        logo_url=logo_url,
-    )
-
-    if not updated_app:
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail="Application not found or you don't have permission to update it",
-        )
-
-    logger.info(
-        f"OAuth app {updated_app.name} (#{app_id}) logo uploaded by user #{user_id}"
-    )
-
-    return updated_app
-
-
-async def _delete_app_current_logo_file(app: OAuthApplicationInfo):
-    """
-    Delete the current logo file for the given app, if there is one in our cloud storage
-    """
-    bucket_name = settings.config.media_gcs_bucket_name
-    storage_base_url = f"https://storage.googleapis.com/{bucket_name}/"
-
-    if app.logo_url and app.logo_url.startswith(storage_base_url):
-        # Parse blob path from URL: https://storage.googleapis.com/{bucket}/{path}
-        old_path = app.logo_url.replace(storage_base_url, "")
-        try:
-            async with async_storage.Storage() as async_client:
-                await async_client.delete(bucket_name, old_path)
-            logger.info(f"Deleted old logo for OAuth app #{app.id}: {old_path}")
-        except Exception as e:
-            # Log but don't fail - the new logo was uploaded successfully
-            logger.warning(
-                f"Failed to delete old logo for OAuth app #{app.id}: {e}", exc_info=e
-            )

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"])