chore: remove test.db from tracking

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

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

@@ -0,0 +1,125 @@
+---
+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

@@ -0,0 +1,55 @@
+---
+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

@@ -0,0 +1,49 @@
+---
+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

@@ -0,0 +1,38 @@
+---
+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

@@ -0,0 +1,80 @@
+---
+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

@@ -0,0 +1,36 @@
+---
+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

@@ -0,0 +1,28 @@
+---
+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

@@ -0,0 +1,99 @@
+---
+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

@@ -0,0 +1,59 @@
+---
+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

@@ -0,0 +1,31 @@
+---
+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

@@ -0,0 +1,49 @@
+---
+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

@@ -0,0 +1,35 @@
+---
+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

@@ -0,0 +1,50 @@
+---
+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

@@ -0,0 +1,74 @@
+---
+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

@@ -0,0 +1,56 @@
+---
+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

@@ -0,0 +1,82 @@
+---
+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

@@ -0,0 +1,80 @@
+---
+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

@@ -0,0 +1,28 @@
+---
+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

@@ -0,0 +1,70 @@
+---
+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

@@ -0,0 +1,32 @@
+---
+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

@@ -0,0 +1,50 @@
+---
+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

@@ -0,0 +1,45 @@
+---
+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

@@ -0,0 +1,37 @@
+---
+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

@@ -0,0 +1,49 @@
+---
+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

@@ -0,0 +1,82 @@
+---
+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

@@ -0,0 +1,24 @@
+---
+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

@@ -0,0 +1,57 @@
+---
+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

@@ -0,0 +1,26 @@
+---
+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

@@ -0,0 +1,47 @@
+---
+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

@@ -0,0 +1,40 @@
+---
+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

@@ -0,0 +1,38 @@
+---
+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

@@ -0,0 +1,46 @@
+---
+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

@@ -0,0 +1,82 @@
+---
+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

@@ -0,0 +1,28 @@
+---
+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

@@ -0,0 +1,39 @@
+---
+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

@@ -0,0 +1,45 @@
+---
+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

@@ -0,0 +1,29 @@
+---
+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

@@ -0,0 +1,74 @@
+---
+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

@@ -0,0 +1,58 @@
+---
+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

@@ -0,0 +1,44 @@
+---
+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

@@ -0,0 +1,40 @@
+---
+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

@@ -0,0 +1,73 @@
+---
+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

@@ -0,0 +1,41 @@
+---
+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

@@ -0,0 +1,26 @@
+---
+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

@@ -0,0 +1,79 @@
+---
+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

@@ -0,0 +1,38 @@
+---
+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

@@ -1,6 +1,9 @@
 # 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

.github/workflows/classic-autogpt-ci.yml

@@ -6,11 +6,15 @@ on:
     paths:
       - '.github/workflows/classic-autogpt-ci.yml'
       - 'classic/original_autogpt/**'
+      - 'classic/direct_benchmark/**'
+      - 'classic/forge/**'
   pull_request:
     branches: [ master, dev, release-* ]
     paths:
       - '.github/workflows/classic-autogpt-ci.yml'
       - 'classic/original_autogpt/**'
+      - 'classic/direct_benchmark/**'
+      - 'classic/forge/**'
 
 concurrency:
   group: ${{ format('classic-autogpt-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -19,47 +23,22 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: classic/original_autogpt
+    working-directory: classic
 
 jobs:
   test:
     permissions:
       contents: read
     timeout-minutes: 30
-    strategy:
+    runs-on: ubuntu-latest
-      fail-fast: false
-      matrix:
-        python-version: ["3.10"]
-        platform-os: [ubuntu, macos, macos-arm64, windows]
-    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
 
     steps:
-      # Quite slow on macOS (2~4 minutes to set up Docker)
+      - name: Start MinIO service
-      # - name: Set up Docker (macOS)
-      #   if: runner.os == 'macOS'
-      #   uses: crazy-max/ghaction-setup-docker@v3
-
-      - name: Start MinIO service (Linux)
-        if: runner.os == 'Linux'
         working-directory: '.'
         run: |
           docker pull minio/minio:edge-cicd
           docker run -d -p 9000:9000 minio/minio:edge-cicd
 
-      - name: Start MinIO service (macOS)
-        if: runner.os == 'macOS'
-        working-directory: ${{ runner.temp }}
-        run: |
-          brew install minio/stable/minio
-          mkdir data
-          minio server ./data &
-
-      # No MinIO on Windows:
-      # - Windows doesn't support running Linux Docker containers
-      # - It doesn't seem possible to start background processes on Windows. They are
-      #   killed after the step returns.
-      #   See: https://github.com/actions/runner/issues/598#issuecomment-2011890429
-
       - name: Checkout repository
         uses: actions/checkout@v4
         with:
@@ -71,41 +50,23 @@ jobs:
           git config --global user.name "Auto-GPT-Bot"
           git config --global user.email "github-bot@agpt.co"
 
-      - name: Set up Python ${{ matrix.python-version }}
+      - name: Set up Python 3.12
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: "3.12"
 
       - id: get_date
         name: Get date
         run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
 
       - name: Set up Python dependency cache
-        # On Windows, unpacking cached dependencies takes longer than just installing them
-        if: runner.os != 'Windows'
         uses: actions/cache@v4
         with:
-          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
+          path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/original_autogpt/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
 
-      - name: Install Poetry (Unix)
+      - name: Install Poetry
-        if: runner.os != 'Windows'
+        run: curl -sSL https://install.python-poetry.org | python3 -
-        run: |
-          curl -sSL https://install.python-poetry.org | python3 -
-
-          if [ "${{ runner.os }}" = "macOS" ]; then
-            PATH="$HOME/.local/bin:$PATH"
-            echo "$HOME/.local/bin" >> $GITHUB_PATH
-          fi
-
-      - name: Install Poetry (Windows)
-        if: runner.os == 'Windows'
-        shell: pwsh
-        run: |
-          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
-
-          $env:PATH += ";$env:APPDATA\Python\Scripts"
-          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
 
       - name: Install Python dependencies
         run: poetry install
@@ -116,12 +77,12 @@ jobs:
             --cov=autogpt --cov-branch --cov-report term-missing --cov-report xml \
             --numprocesses=logical --durations=10 \
             --junitxml=junit.xml -o junit_family=legacy \
-            tests/unit tests/integration
+            original_autogpt/tests/unit original_autogpt/tests/integration
         env:
           CI: true
           PLAIN_OUTPUT: True
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
+          S3_ENDPOINT_URL: http://127.0.0.1:9000
           AWS_ACCESS_KEY_ID: minioadmin
           AWS_SECRET_ACCESS_KEY: minioadmin
 
@@ -135,11 +96,11 @@ jobs:
         uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
-          flags: autogpt-agent,${{ runner.os }}
+          flags: autogpt-agent
 
       - name: Upload logs to artifact
         if: always()
         uses: actions/upload-artifact@v4
         with:
           name: test-logs
-          path: classic/original_autogpt/logs/
+          path: classic/logs/

.github/workflows/classic-autogpts-ci.yml

@@ -11,9 +11,6 @@ on:
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
       - 'classic/benchmark/**'
-      - 'classic/run'
-      - 'classic/cli.py'
-      - 'classic/setup.py'
       - '!**/*.md'
   pull_request:
     branches: [ master, dev, release-* ]
@@ -22,9 +19,6 @@ on:
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
       - 'classic/benchmark/**'
-      - 'classic/run'
-      - 'classic/cli.py'
-      - 'classic/setup.py'
       - '!**/*.md'
 
 defaults:
@@ -35,13 +29,9 @@ defaults:
 jobs:
   serve-agent-protocol:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        agent-name: [ original_autogpt ]
-      fail-fast: false
     timeout-minutes: 20
     env:
-      min-python-version: '3.10'
+      min-python-version: '3.12'
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -55,22 +45,22 @@ jobs:
           python-version: ${{ env.min-python-version }}
 
       - name: Install Poetry
-        working-directory: ./classic/${{ matrix.agent-name }}/
         run: |
           curl -sSL https://install.python-poetry.org | python -
 
-      - name: Run regression tests
+      - name: Install dependencies
+        run: poetry install
+
+      - name: Run smoke tests with direct-benchmark
         run: |
-          ./run agent start ${{ matrix.agent-name }}
+          poetry run direct-benchmark run \
-          cd ${{ matrix.agent-name }}
+            --strategies one_shot \
-          poetry run agbenchmark --mock --test=BasicRetrieval --test=Battleship --test=WebArenaTask_0
+            --models claude \
-          poetry run agbenchmark --test=WriteFile
+            --tests ReadFile,WriteFile \
+            --json
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          AGENT_NAME: ${{ matrix.agent-name }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           REQUESTS_CA_BUNDLE: /etc/ssl/certs/ca-certificates.crt
-          HELICONE_CACHE_ENABLED: false
+          NONINTERACTIVE_MODE: "true"
-          HELICONE_PROPERTY_AGENT: ${{ matrix.agent-name }}
+          CI: true
-          REPORTS_FOLDER: ${{ format('../../reports/{0}', matrix.agent-name) }}
-          TELEMETRY_ENVIRONMENT: autogpt-ci
-          TELEMETRY_OPT_IN: ${{ github.ref_name == 'master' }}

.github/workflows/classic-benchmark-ci.yml

@@ -1,17 +1,21 @@
-name: Classic - AGBenchmark CI
+name: Classic - Direct Benchmark CI
 
 on:
   push:
     branches: [ master, dev, ci-test* ]
     paths:
-      - 'classic/benchmark/**'
+      - 'classic/direct_benchmark/**'
-      - '!classic/benchmark/reports/**'
+      - 'classic/benchmark/agbenchmark/challenges/**'
+      - 'classic/original_autogpt/**'
+      - 'classic/forge/**'
       - .github/workflows/classic-benchmark-ci.yml
   pull_request:
     branches: [ master, dev, release-* ]
     paths:
-      - 'classic/benchmark/**'
+      - 'classic/direct_benchmark/**'
-      - '!classic/benchmark/reports/**'
+      - 'classic/benchmark/agbenchmark/challenges/**'
+      - 'classic/original_autogpt/**'
+      - 'classic/forge/**'
       - .github/workflows/classic-benchmark-ci.yml
 
 concurrency:
@@ -23,23 +27,16 @@ defaults:
     shell: bash
 
 env:
-  min-python-version: '3.10'
+  min-python-version: '3.12'
 
 jobs:
-  test:
+  benchmark-tests:
-    permissions:
+    runs-on: ubuntu-latest
-      contents: read
     timeout-minutes: 30
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.10"]
-        platform-os: [ubuntu, macos, macos-arm64, windows]
-    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
     defaults:
       run:
         shell: bash
-        working-directory: classic/benchmark
+        working-directory: classic
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -47,71 +44,84 @@ jobs:
           fetch-depth: 0
           submodules: true
 
-      - name: Set up Python ${{ matrix.python-version }}
+      - name: Set up Python ${{ env.min-python-version }}
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ env.min-python-version }}
 
       - name: Set up Python dependency cache
-        # On Windows, unpacking cached dependencies takes longer than just installing them
-        if: runner.os != 'Windows'
         uses: actions/cache@v4
         with:
-          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
+          path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/benchmark/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
 
-      - name: Install Poetry (Unix)
+      - name: Install Poetry
-        if: runner.os != 'Windows'
         run: |
           curl -sSL https://install.python-poetry.org | python3 -
 
-          if [ "${{ runner.os }}" = "macOS" ]; then
+      - name: Install dependencies
-            PATH="$HOME/.local/bin:$PATH"
-            echo "$HOME/.local/bin" >> $GITHUB_PATH
-          fi
-
-      - name: Install Poetry (Windows)
-        if: runner.os == 'Windows'
-        shell: pwsh
-        run: |
-          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
-
-          $env:PATH += ";$env:APPDATA\Python\Scripts"
-          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
-
-      - name: Install Python dependencies
         run: poetry install
 
-      - name: Run pytest with coverage
+      - name: Run basic benchmark tests
         run: |
-          poetry run pytest -vv \
+          echo "Testing ReadFile challenge with one_shot strategy..."
-            --cov=agbenchmark --cov-branch --cov-report term-missing --cov-report xml \
+          poetry run direct-benchmark run \
-            --durations=10 \
+            --strategies one_shot \
-            --junitxml=junit.xml -o junit_family=legacy \
+            --models claude \
-            tests
+            --tests ReadFile \
+            --json
+
+          echo "Testing WriteFile challenge..."
+          poetry run direct-benchmark run \
+            --strategies one_shot \
+            --models claude \
+            --tests WriteFile \
+            --json
         env:
           CI: true
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          NONINTERACTIVE_MODE: "true"
 
-      - name: Upload test results to Codecov
+      - name: Test category filtering
-        if: ${{ !cancelled() }}  # Run even if tests fail
+        run: |
-        uses: codecov/test-results-action@v1
+          echo "Testing coding category..."
-        with:
+          poetry run direct-benchmark run \
-          token: ${{ secrets.CODECOV_TOKEN }}
+            --strategies one_shot \
+            --models claude \
+            --categories coding \
+            --tests ReadFile,WriteFile \
+            --json
+        env:
+          CI: true
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          NONINTERACTIVE_MODE: "true"
 
-      - name: Upload coverage reports to Codecov
+      - name: Test multiple strategies
-        uses: codecov/codecov-action@v5
+        run: |
-        with:
+          echo "Testing multiple strategies..."
-          token: ${{ secrets.CODECOV_TOKEN }}
+          poetry run direct-benchmark run \
-          flags: agbenchmark,${{ runner.os }}
+            --strategies one_shot,plan_execute \
+            --models claude \
+            --tests ReadFile \
+            --parallel 2 \
+            --json
+        env:
+          CI: true
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          NONINTERACTIVE_MODE: "true"
 
-  self-test-with-agent:
+  # Run regression tests on maintain challenges
+  regression-tests:
     runs-on: ubuntu-latest
-    strategy:
+    timeout-minutes: 45
-      matrix:
+    if: github.ref == 'refs/heads/master' || github.ref == 'refs/heads/dev'
-        agent-name: [forge]
+    defaults:
-      fail-fast: false
+      run:
-    timeout-minutes: 20
+        shell: bash
+        working-directory: classic
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -126,51 +136,22 @@ jobs:
 
       - name: Install Poetry
         run: |
-          curl -sSL https://install.python-poetry.org | python -
+          curl -sSL https://install.python-poetry.org | python3 -
+
+      - name: Install dependencies
+        run: poetry install
 
       - name: Run regression tests
-        working-directory: classic
         run: |
-          ./run agent start ${{ matrix.agent-name }}
+          echo "Running regression tests (previously beaten challenges)..."
-          cd ${{ matrix.agent-name }}
+          poetry run direct-benchmark run \
-
+            --strategies one_shot \
-          set +e # Ignore non-zero exit codes and continue execution
+            --models claude \
-          echo "Running the following command: poetry run agbenchmark --maintain --mock"
+            --maintain \
-          poetry run agbenchmark --maintain --mock
+            --parallel 4 \
-          EXIT_CODE=$?
+            --json
-          set -e  # Stop ignoring non-zero exit codes
-          # Check if the exit code was 5, and if so, exit with 0 instead
-          if [ $EXIT_CODE -eq 5 ]; then
-            echo "regression_tests.json is empty."
-          fi
-
-          echo "Running the following command: poetry run agbenchmark --mock"
-          poetry run agbenchmark --mock
-
-          echo "Running the following command: poetry run agbenchmark --mock --category=data"
-          poetry run agbenchmark --mock --category=data
-
-          echo "Running the following command: poetry run agbenchmark --mock --category=coding"
-          poetry run agbenchmark --mock --category=coding
-
-          # echo "Running the following command: poetry run agbenchmark --test=WriteFile"
-          # poetry run agbenchmark --test=WriteFile
-          cd ../benchmark
-          poetry install
-          echo "Adding the BUILD_SKILL_TREE environment variable. This will attempt to add new elements in the skill tree. If new elements are added, the CI fails because they should have been pushed"
-          export BUILD_SKILL_TREE=true
-
-          # poetry run agbenchmark --mock
-
-          # CHANGED=$(git diff --name-only | grep -E '(agbenchmark/challenges)|(../classic/frontend/assets)') || echo "No diffs"
-          # if [ ! -z "$CHANGED" ]; then
-          #   echo "There are unstaged changes please run agbenchmark and commit those changes since they are needed."
-          #   echo "$CHANGED"
-          #   exit 1
-          # else
-          #   echo "No unstaged changes."
-          # fi
         env:
+          CI: true
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          TELEMETRY_ENVIRONMENT: autogpt-benchmark-ci
+          NONINTERACTIVE_MODE: "true"
-          TELEMETRY_OPT_IN: ${{ github.ref_name == 'master' }}

.github/workflows/classic-forge-ci.yml

@@ -6,13 +6,11 @@ on:
     paths:
       - '.github/workflows/classic-forge-ci.yml'
       - 'classic/forge/**'
-      - '!classic/forge/tests/vcr_cassettes'
   pull_request:
     branches: [ master, dev, release-* ]
     paths:
       - '.github/workflows/classic-forge-ci.yml'
       - 'classic/forge/**'
-      - '!classic/forge/tests/vcr_cassettes'
 
 concurrency:
   group: ${{ format('forge-ci-{0}', github.head_ref && format('{0}-{1}', github.event_name, github.event.pull_request.number) || github.sha) }}
@@ -21,115 +19,38 @@ concurrency:
 defaults:
   run:
     shell: bash
-    working-directory: classic/forge
+    working-directory: classic
 
 jobs:
   test:
     permissions:
       contents: read
     timeout-minutes: 30
-    strategy:
+    runs-on: ubuntu-latest
-      fail-fast: false
-      matrix:
-        python-version: ["3.10"]
-        platform-os: [ubuntu, macos, macos-arm64, windows]
-    runs-on: ${{ matrix.platform-os != 'macos-arm64' && format('{0}-latest', matrix.platform-os) || 'macos-14' }}
 
     steps:
-      # Quite slow on macOS (2~4 minutes to set up Docker)
+      - name: Start MinIO service
-      # - name: Set up Docker (macOS)
-      #   if: runner.os == 'macOS'
-      #   uses: crazy-max/ghaction-setup-docker@v3
-
-      - name: Start MinIO service (Linux)
-        if: runner.os == 'Linux'
         working-directory: '.'
         run: |
           docker pull minio/minio:edge-cicd
           docker run -d -p 9000:9000 minio/minio:edge-cicd
 
-      - name: Start MinIO service (macOS)
-        if: runner.os == 'macOS'
-        working-directory: ${{ runner.temp }}
-        run: |
-          brew install minio/stable/minio
-          mkdir data
-          minio server ./data &
-
-      # No MinIO on Windows:
-      # - Windows doesn't support running Linux Docker containers
-      # - It doesn't seem possible to start background processes on Windows. They are
-      #   killed after the step returns.
-      #   See: https://github.com/actions/runner/issues/598#issuecomment-2011890429
-
       - name: Checkout repository
         uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          submodules: true
 
-      - name: Checkout cassettes
+      - name: Set up Python 3.12
-        if: ${{ startsWith(github.event_name, 'pull_request') }}
-        env:
-          PR_BASE: ${{ github.event.pull_request.base.ref }}
-          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
-          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
-        run: |
-          cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
-          cassette_base_branch="${PR_BASE}"
-          cd tests/vcr_cassettes
-
-          if ! git ls-remote --exit-code --heads origin $cassette_base_branch ; then
-            cassette_base_branch="master"
-          fi
-
-          if git ls-remote --exit-code --heads origin $cassette_branch ; then
-            git fetch origin $cassette_branch
-            git fetch origin $cassette_base_branch
-
-            git checkout $cassette_branch
-
-            # Pick non-conflicting cassette updates from the base branch
-            git merge --no-commit --strategy-option=ours origin/$cassette_base_branch
-            echo "Using cassettes from mirror branch '$cassette_branch'," \
-              "synced to upstream branch '$cassette_base_branch'."
-          else
-            git checkout -b $cassette_branch
-            echo "Branch '$cassette_branch' does not exist in cassette submodule." \
-              "Using cassettes from '$cassette_base_branch'."
-          fi
-
-      - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: "3.12"
 
       - name: Set up Python dependency cache
-        # On Windows, unpacking cached dependencies takes longer than just installing them
-        if: runner.os != 'Windows'
         uses: actions/cache@v4
         with:
-          path: ${{ runner.os == 'macOS' && '~/Library/Caches/pypoetry' || '~/.cache/pypoetry' }}
+          path: ~/.cache/pypoetry
-          key: poetry-${{ runner.os }}-${{ hashFiles('classic/forge/poetry.lock') }}
+          key: poetry-${{ runner.os }}-${{ hashFiles('classic/poetry.lock') }}
 
-      - name: Install Poetry (Unix)
+      - name: Install Poetry
-        if: runner.os != 'Windows'
+        run: curl -sSL https://install.python-poetry.org | python3 -
-        run: |
-          curl -sSL https://install.python-poetry.org | python3 -
-
-          if [ "${{ runner.os }}" = "macOS" ]; then
-            PATH="$HOME/.local/bin:$PATH"
-            echo "$HOME/.local/bin" >> $GITHUB_PATH
-          fi
-
-      - name: Install Poetry (Windows)
-        if: runner.os == 'Windows'
-        shell: pwsh
-        run: |
-          (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
-
-          $env:PATH += ";$env:APPDATA\Python\Scripts"
-          echo "$env:APPDATA\Python\Scripts" >> $env:GITHUB_PATH
 
       - name: Install Python dependencies
         run: poetry install
@@ -140,12 +61,15 @@ jobs:
             --cov=forge --cov-branch --cov-report term-missing --cov-report xml \
             --durations=10 \
             --junitxml=junit.xml -o junit_family=legacy \
-            forge
+            forge/forge forge/tests
         env:
           CI: true
           PLAIN_OUTPUT: True
+          # API keys - tests that need these will skip if not available
+          # Secrets are not available to fork PRs (GitHub security feature)
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          S3_ENDPOINT_URL: ${{ runner.os != 'Windows' && 'http://127.0.0.1:9000' || '' }}
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          S3_ENDPOINT_URL: http://127.0.0.1:9000
           AWS_ACCESS_KEY_ID: minioadmin
           AWS_SECRET_ACCESS_KEY: minioadmin
 
@@ -159,85 +83,11 @@ jobs:
         uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
-          flags: forge,${{ runner.os }}
+          flags: forge
-
-      - id: setup_git_auth
-        name: Set up git token authentication
-        # Cassettes may be pushed even when tests fail
-        if: success() || failure()
-        run: |
-          config_key="http.${{ github.server_url }}/.extraheader"
-          if [ "${{ runner.os }}" = 'macOS' ]; then
-            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64)
-          else
-            base64_pat=$(echo -n "pat:${{ secrets.PAT_REVIEW }}" | base64 -w0)
-          fi
-
-          git config "$config_key" \
-            "Authorization: Basic $base64_pat"
-
-          cd tests/vcr_cassettes
-          git config "$config_key" \
-            "Authorization: Basic $base64_pat"
-
-          echo "config_key=$config_key" >> $GITHUB_OUTPUT
-
-      - id: push_cassettes
-        name: Push updated cassettes
-        # For pull requests, push updated cassettes even when tests fail
-        if: github.event_name == 'push' || (! github.event.pull_request.head.repo.fork && (success() || failure()))
-        env:
-          PR_BRANCH: ${{ github.event.pull_request.head.ref }}
-          PR_AUTHOR: ${{ github.event.pull_request.user.login }}
-        run: |
-          if [ "${{ startsWith(github.event_name, 'pull_request') }}" = "true" ]; then
-            is_pull_request=true
-            cassette_branch="${PR_AUTHOR}-${PR_BRANCH}"
-          else
-            cassette_branch="${{ github.ref_name }}"
-          fi
-
-          cd tests/vcr_cassettes
-          # Commit & push changes to cassettes if any
-          if ! git diff --quiet; then
-            git add .
-            git commit -m "Auto-update cassettes"
-            git push origin HEAD:$cassette_branch
-            if [ ! $is_pull_request ]; then
-              cd ../..
-              git add tests/vcr_cassettes
-              git commit -m "Update cassette submodule"
-              git push origin HEAD:$cassette_branch
-            fi
-            echo "updated=true" >> $GITHUB_OUTPUT
-          else
-            echo "updated=false" >> $GITHUB_OUTPUT
-            echo "No cassette changes to commit"
-          fi
-
-      - name: Post Set up git token auth
-        if: steps.setup_git_auth.outcome == 'success'
-        run: |
-          git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
-          git submodule foreach git config --unset-all '${{ steps.setup_git_auth.outputs.config_key }}'
-
-      - name: Apply "behaviour change" label and comment on PR
-        if: ${{ startsWith(github.event_name, 'pull_request') }}
-        run: |
-          PR_NUMBER="${{ github.event.pull_request.number }}"
-          TOKEN="${{ secrets.PAT_REVIEW }}"
-          REPO="${{ github.repository }}"
-
-          if [[ "${{ steps.push_cassettes.outputs.updated }}" == "true" ]]; then
-            echo "Adding label and comment..."
-            echo $TOKEN | gh auth login --with-token
-            gh issue edit $PR_NUMBER --add-label "behaviour change"
-            gh issue comment $PR_NUMBER --body "You changed AutoGPT's behaviour on ${{ runner.os }}. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged."
-          fi
 
       - name: Upload logs to artifact
         if: always()
         uses: actions/upload-artifact@v4
         with:
           name: test-logs
-          path: classic/forge/logs/
+          path: classic/logs/

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

@@ -1,60 +0,0 @@
-name: Classic - Frontend CI/CD
-
-on:
-  push:
-    branches:
-      - master
-      - dev
-      - 'ci-test*' # This will match any branch that starts with "ci-test"
-    paths:
-      - 'classic/frontend/**'
-      - '.github/workflows/classic-frontend-ci.yml'
-  pull_request:
-    paths:
-      - 'classic/frontend/**'
-      - '.github/workflows/classic-frontend-ci.yml'
-
-jobs:
-  build:
-    permissions:
-      contents: write
-      pull-requests: write
-    runs-on: ubuntu-latest
-    env:
-      BUILD_BRANCH: ${{ format('classic-frontend-build/{0}', github.ref_name) }}
-
-    steps:
-      - name: Checkout Repo
-        uses: actions/checkout@v4
-
-      - name: Setup Flutter
-        uses: subosito/flutter-action@v2
-        with:
-          flutter-version: '3.13.2'
-
-      - name: Build Flutter to Web
-        run: |
-          cd classic/frontend
-          flutter build web --base-href /app/
-
-      # - name: Commit and Push to ${{ env.BUILD_BRANCH }}
-      #   if: github.event_name == 'push'
-      #   run: |
-      #     git config --local user.email "action@github.com"
-      #     git config --local user.name "GitHub Action"
-      #     git add classic/frontend/build/web
-      #     git checkout -B ${{ env.BUILD_BRANCH }}
-      #     git commit -m "Update frontend build to ${GITHUB_SHA:0:7}" -a
-      #     git push -f origin ${{ env.BUILD_BRANCH }}
-
-      - name: Create PR ${{ env.BUILD_BRANCH }} -> ${{ github.ref_name }}
-        if: github.event_name == 'push'
-        uses: peter-evans/create-pull-request@v7
-        with:
-          add-paths: classic/frontend/build/web
-          base: ${{ github.ref_name }}
-          branch: ${{ env.BUILD_BRANCH }}
-          delete-branch: true
-          title: "Update frontend build in `${{ github.ref_name }}`"
-          body: "This PR updates the frontend build based on commit ${{ github.sha }}."
-          commit-message: "Update frontend build based on commit ${{ github.sha }}"

.github/workflows/classic-python-checks.yml

@@ -7,7 +7,9 @@ on:
       - '.github/workflows/classic-python-checks-ci.yml'
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
-      - 'classic/benchmark/**'
+      - 'classic/direct_benchmark/**'
+      - 'classic/pyproject.toml'
+      - 'classic/poetry.lock'
       - '**.py'
       - '!classic/forge/tests/vcr_cassettes'
   pull_request:
@@ -16,7 +18,9 @@ on:
       - '.github/workflows/classic-python-checks-ci.yml'
       - 'classic/original_autogpt/**'
       - 'classic/forge/**'
-      - 'classic/benchmark/**'
+      - 'classic/direct_benchmark/**'
+      - 'classic/pyproject.toml'
+      - 'classic/poetry.lock'
       - '**.py'
       - '!classic/forge/tests/vcr_cassettes'
 
@@ -27,44 +31,13 @@ concurrency:
 defaults:
   run:
     shell: bash
+    working-directory: classic
 
 jobs:
-  get-changed-parts:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
-      - id: changes-in
-        name: Determine affected subprojects
-        uses: dorny/paths-filter@v3
-        with:
-          filters: |
-            original_autogpt:
-              - classic/original_autogpt/autogpt/**
-              - classic/original_autogpt/tests/**
-              - classic/original_autogpt/poetry.lock
-            forge:
-              - classic/forge/forge/**
-              - classic/forge/tests/**
-              - classic/forge/poetry.lock
-            benchmark:
-              - classic/benchmark/agbenchmark/**
-              - classic/benchmark/tests/**
-              - classic/benchmark/poetry.lock
-    outputs:
-      changed-parts: ${{ steps.changes-in.outputs.changes }}
-
   lint:
-    needs: get-changed-parts
     runs-on: ubuntu-latest
     env:
-      min-python-version: "3.10"
+      min-python-version: "3.12"
-
-    strategy:
-      matrix:
-        sub-package: ${{ fromJson(needs.get-changed-parts.outputs.changed-parts) }}
-      fail-fast: false
 
     steps:
       - name: Checkout repository
@@ -81,42 +54,31 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/.cache/pypoetry
-          key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}
+          key: ${{ runner.os }}-poetry-${{ hashFiles('classic/poetry.lock') }}
 
       - name: Install Poetry
         run: curl -sSL https://install.python-poetry.org | python3 -
 
-      # Install dependencies
-
       - name: Install Python dependencies
-        run: poetry -C classic/${{ matrix.sub-package }} install
+        run: poetry install
 
       # Lint
 
       - name: Lint (isort)
         run: poetry run isort --check .
-        working-directory: classic/${{ matrix.sub-package }}
 
       - name: Lint (Black)
         if: success() || failure()
         run: poetry run black --check .
-        working-directory: classic/${{ matrix.sub-package }}
 
       - name: Lint (Flake8)
         if: success() || failure()
         run: poetry run flake8 .
-        working-directory: classic/${{ matrix.sub-package }}
 
   types:
-    needs: get-changed-parts
     runs-on: ubuntu-latest
     env:
-      min-python-version: "3.10"
+      min-python-version: "3.12"
-
-    strategy:
-      matrix:
-        sub-package: ${{ fromJson(needs.get-changed-parts.outputs.changed-parts) }}
-      fail-fast: false
 
     steps:
       - name: Checkout repository
@@ -133,19 +95,16 @@ jobs:
         uses: actions/cache@v4
         with:
           path: ~/.cache/pypoetry
-          key: ${{ runner.os }}-poetry-${{ hashFiles(format('{0}/poetry.lock', matrix.sub-package)) }}
+          key: ${{ runner.os }}-poetry-${{ hashFiles('classic/poetry.lock') }}
 
       - name: Install Poetry
         run: curl -sSL https://install.python-poetry.org | python3 -
 
-      # Install dependencies
-
       - name: Install Python dependencies
-        run: poetry -C classic/${{ matrix.sub-package }} install
+        run: poetry install
 
       # Typecheck
 
       - name: Typecheck
         if: success() || failure()
         run: poetry run pyright
-        working-directory: classic/${{ matrix.sub-package }}

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

@@ -93,5 +93,5 @@ jobs:
 
             Error logs:
             ${{ toJSON(fromJSON(steps.failure_details.outputs.result).errorLogs) }}
-          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
           claude_args: "--allowedTools 'Edit,MultiEdit,Write,Read,Glob,Grep,LS,Bash(git:*),Bash(bun:*),Bash(npm:*),Bash(npx:*),Bash(gh:*)'"

.github/workflows/claude-dependabot.yml

@@ -7,7 +7,7 @@
 # - Provide actionable recommendations for the development team
 #
 # Triggered on: Dependabot PRs (opened, synchronize)
-# Requirements: ANTHROPIC_API_KEY secret must be configured
+# Requirements: CLAUDE_CODE_OAUTH_TOKEN secret must be configured
 
 name: Claude Dependabot PR Review
 
@@ -308,7 +308,7 @@ jobs:
         id: claude_review
         uses: anthropics/claude-code-action@v1
         with:
-          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
           claude_args: |
             --allowedTools "Bash(npm:*),Bash(pnpm:*),Bash(poetry:*),Bash(git:*),Edit,Replace,NotebookEditCell,mcp__github_inline_comment__create_inline_comment,Bash(gh pr comment:*), Bash(gh pr diff:*), Bash(gh pr view:*)"
           prompt: |

.github/workflows/claude.yml

@@ -323,7 +323,7 @@ jobs:
         id: claude
         uses: anthropics/claude-code-action@v1
         with:
-          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
           claude_args: |
             --allowedTools "Bash(npm:*),Bash(pnpm:*),Bash(poetry:*),Bash(git:*),Edit,Replace,NotebookEditCell,mcp__github_inline_comment__create_inline_comment,Bash(gh pr comment:*), Bash(gh pr diff:*), Bash(gh pr view:*), Bash(gh pr edit:*)"
             --model opus

.github/workflows/docs-block-sync.yml

@@ -0,0 +1,78 @@
+name: Block Documentation Sync Check
+
+on:
+  push:
+    branches: [master, dev]
+    paths:
+      - "autogpt_platform/backend/backend/blocks/**"
+      - "docs/integrations/**"
+      - "autogpt_platform/backend/scripts/generate_block_docs.py"
+      - ".github/workflows/docs-block-sync.yml"
+  pull_request:
+    branches: [master, dev]
+    paths:
+      - "autogpt_platform/backend/backend/blocks/**"
+      - "docs/integrations/**"
+      - "autogpt_platform/backend/scripts/generate_block_docs.py"
+      - ".github/workflows/docs-block-sync.yml"
+
+jobs:
+  check-docs-sync:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Set up Python dependency cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pypoetry
+          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
+          restore-keys: |
+            poetry-${{ runner.os }}-
+
+      - name: Install Poetry
+        run: |
+          cd autogpt_platform/backend
+          HEAD_POETRY_VERSION=$(python3 ../../.github/workflows/scripts/get_package_version_from_lockfile.py poetry)
+          echo "Found Poetry version ${HEAD_POETRY_VERSION} in backend/poetry.lock"
+          curl -sSL https://install.python-poetry.org | POETRY_VERSION=$HEAD_POETRY_VERSION python3 -
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Install dependencies
+        working-directory: autogpt_platform/backend
+        run: |
+          poetry install --only main
+          poetry run prisma generate
+
+      - name: Check block documentation is in sync
+        working-directory: autogpt_platform/backend
+        run: |
+          echo "Checking if block documentation is in sync with code..."
+          poetry run python scripts/generate_block_docs.py --check
+
+      - name: Show diff if out of sync
+        if: failure()
+        working-directory: autogpt_platform/backend
+        run: |
+          echo "::error::Block documentation is out of sync with code!"
+          echo ""
+          echo "To fix this, run the following command locally:"
+          echo "  cd autogpt_platform/backend && poetry run python scripts/generate_block_docs.py"
+          echo ""
+          echo "Then commit the updated documentation files."
+          echo ""
+          echo "Regenerating docs to show diff..."
+          poetry run python scripts/generate_block_docs.py
+          echo ""
+          echo "Changes detected:"
+          git diff ../../docs/integrations/ || true

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

@@ -0,0 +1,95 @@
+name: Claude Block Docs Review
+
+on:
+  pull_request:
+    types: [opened, synchronize]
+    paths:
+      - "docs/integrations/**"
+      - "autogpt_platform/backend/backend/blocks/**"
+
+jobs:
+  claude-review:
+    # Only run for PRs from members/collaborators
+    if: |
+      github.event.pull_request.author_association == 'OWNER' ||
+      github.event.pull_request.author_association == 'MEMBER' ||
+      github.event.pull_request.author_association == 'COLLABORATOR'
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    permissions:
+      contents: read
+      pull-requests: write
+      id-token: write
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Set up Python dependency cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pypoetry
+          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
+          restore-keys: |
+            poetry-${{ runner.os }}-
+
+      - name: Install Poetry
+        run: |
+          cd autogpt_platform/backend
+          HEAD_POETRY_VERSION=$(python3 ../../.github/workflows/scripts/get_package_version_from_lockfile.py poetry)
+          curl -sSL https://install.python-poetry.org | POETRY_VERSION=$HEAD_POETRY_VERSION python3 -
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Install dependencies
+        working-directory: autogpt_platform/backend
+        run: |
+          poetry install --only main
+          poetry run prisma generate
+
+      - name: Run Claude Code Review
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          claude_args: |
+            --allowedTools "Read,Glob,Grep,Bash(gh pr comment:*),Bash(gh pr diff:*),Bash(gh pr view:*)"
+          prompt: |
+            You are reviewing a PR that modifies block documentation or block code for AutoGPT.
+
+            ## Your Task
+            Review the changes in this PR and provide constructive feedback. Focus on:
+
+            1. **Documentation Accuracy**: For any block code changes, verify that:
+               - Input/output tables in docs match the actual block schemas
+               - Description text accurately reflects what the block does
+               - Any new blocks have corresponding documentation
+
+            2. **Manual Content Quality**: Check manual sections (marked with `<!-- MANUAL: -->` markers):
+               - "How it works" sections should have clear technical explanations
+               - "Possible use case" sections should have practical, real-world examples
+               - Content should be helpful for users trying to understand the blocks
+
+            3. **Template Compliance**: Ensure docs follow the standard template:
+               - What it is (brief intro)
+               - What it does (description)
+               - How it works (technical explanation)
+               - Inputs table
+               - Outputs table
+               - Possible use case
+
+            4. **Cross-references**: Check that links and anchors are correct
+
+            ## Review Process
+            1. First, get the PR diff to see what changed: `gh pr diff ${{ github.event.pull_request.number }}`
+            2. Read any modified block files to understand the implementation
+            3. Read corresponding documentation files to verify accuracy
+            4. Provide your feedback as a PR comment
+
+            Be constructive and specific. If everything looks good, say so!
+            If there are issues, explain what's wrong and suggest how to fix it.

.github/workflows/docs-enhance.yml

@@ -0,0 +1,194 @@
+name: Enhance Block Documentation
+
+on:
+  workflow_dispatch:
+    inputs:
+      block_pattern:
+        description: 'Block file pattern to enhance (e.g., "google/*.md" or "*" for all blocks)'
+        required: true
+        default: '*'
+        type: string
+      dry_run:
+        description: 'Dry run mode - show proposed changes without committing'
+        type: boolean
+        default: true
+      max_blocks:
+        description: 'Maximum number of blocks to process (0 for unlimited)'
+        type: number
+        default: 10
+
+jobs:
+  enhance-docs:
+    runs-on: ubuntu-latest
+    timeout-minutes: 45
+    permissions:
+      contents: write
+      pull-requests: write
+      id-token: write
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Set up Python dependency cache
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pypoetry
+          key: poetry-${{ runner.os }}-${{ hashFiles('autogpt_platform/backend/poetry.lock') }}
+          restore-keys: |
+            poetry-${{ runner.os }}-
+
+      - name: Install Poetry
+        run: |
+          cd autogpt_platform/backend
+          HEAD_POETRY_VERSION=$(python3 ../../.github/workflows/scripts/get_package_version_from_lockfile.py poetry)
+          curl -sSL https://install.python-poetry.org | POETRY_VERSION=$HEAD_POETRY_VERSION python3 -
+          echo "$HOME/.local/bin" >> $GITHUB_PATH
+
+      - name: Install dependencies
+        working-directory: autogpt_platform/backend
+        run: |
+          poetry install --only main
+          poetry run prisma generate
+
+      - name: Run Claude Enhancement
+        uses: anthropics/claude-code-action@v1
+        with:
+          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
+          claude_args: |
+            --allowedTools "Read,Edit,Glob,Grep,Write,Bash(git:*),Bash(gh:*),Bash(find:*),Bash(ls:*)"
+          prompt: |
+            You are enhancing block documentation for AutoGPT. Your task is to improve the MANUAL sections
+            of block documentation files by reading the actual block implementations and writing helpful content.
+
+            ## Configuration
+            - Block pattern: ${{ inputs.block_pattern }}
+            - Dry run: ${{ inputs.dry_run }}
+            - Max blocks to process: ${{ inputs.max_blocks }}
+
+            ## Your Task
+
+            1. **Find Documentation Files**
+               Find block documentation files matching the pattern in `docs/integrations/`
+               Pattern: ${{ inputs.block_pattern }}
+
+               Use: `find docs/integrations -name "*.md" -type f`
+
+            2. **For Each Documentation File** (up to ${{ inputs.max_blocks }} files):
+
+               a. Read the documentation file
+
+               b. Identify which block(s) it documents (look for the block class name)
+
+               c. Find and read the corresponding block implementation in `autogpt_platform/backend/backend/blocks/`
+
+               d. Improve the MANUAL sections:
+
+                  **"How it works" section** (within `<!-- MANUAL: how_it_works -->` markers):
+                  - Explain the technical flow of the block
+                  - Describe what APIs or services it connects to
+                  - Note any important configuration or prerequisites
+                  - Keep it concise but informative (2-4 paragraphs)
+
+                  **"Possible use case" section** (within `<!-- MANUAL: use_case -->` markers):
+                  - Provide 2-3 practical, real-world examples
+                  - Make them specific and actionable
+                  - Show how this block could be used in an automation workflow
+
+            3. **Important Rules**
+               - ONLY modify content within `<!-- MANUAL: -->` and `<!-- END MANUAL -->` markers
+               - Do NOT modify auto-generated sections (inputs/outputs tables, descriptions)
+               - Keep content accurate based on the actual block implementation
+               - Write for users who may not be technical experts
+
+            4. **Output**
+               ${{ inputs.dry_run == true && 'DRY RUN MODE: Show proposed changes for each file but do NOT actually edit the files. Describe what you would change.' || 'LIVE MODE: Actually edit the files to improve the documentation.' }}
+
+            ## Example Improvements
+
+            **Before (How it works):**
+            ```
+            _Add technical explanation here._
+            ```
+
+            **After (How it works):**
+            ```
+            This block connects to the GitHub API to retrieve issue information. When executed,
+            it authenticates using your GitHub credentials and fetches issue details including
+            title, body, labels, and assignees.
+
+            The block requires a valid GitHub OAuth connection with repository access permissions.
+            It supports both public and private repositories you have access to.
+            ```
+
+            **Before (Possible use case):**
+            ```
+            _Add practical use case examples here._
+            ```
+
+            **After (Possible use case):**
+            ```
+            **Customer Support Automation**: Monitor a GitHub repository for new issues with
+            the "bug" label, then automatically create a ticket in your support system and
+            notify the on-call engineer via Slack.
+
+            **Release Notes Generation**: When a new release is published, gather all closed
+            issues since the last release and generate a summary for your changelog.
+            ```
+
+            Begin by finding and listing the documentation files to process.
+
+      - name: Create PR with enhanced documentation
+        if: ${{ inputs.dry_run == false }}
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Check if there are changes
+          if git diff --quiet docs/integrations/; then
+            echo "No changes to commit"
+            exit 0
+          fi
+
+          # Configure git
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+
+          # Create branch and commit
+          BRANCH_NAME="docs/enhance-blocks-$(date +%Y%m%d-%H%M%S)"
+          git checkout -b "$BRANCH_NAME"
+          git add docs/integrations/
+          git commit -m "docs: enhance block documentation with LLM-generated content
+
+          Pattern: ${{ inputs.block_pattern }}
+          Max blocks: ${{ inputs.max_blocks }}
+
+          🤖 Generated with [Claude Code](https://claude.com/claude-code)
+
+          Co-Authored-By: Claude <noreply@anthropic.com>"
+
+          # Push and create PR
+          git push -u origin "$BRANCH_NAME"
+          gh pr create \
+            --title "docs: LLM-enhanced block documentation" \
+            --body "## Summary
+          This PR contains LLM-enhanced documentation for block files matching pattern: \`${{ inputs.block_pattern }}\`
+
+          The following manual sections were improved:
+          - **How it works**: Technical explanations based on block implementations
+          - **Possible use case**: Practical, real-world examples
+
+          ## Review Checklist
+          - [ ] Content is accurate based on block implementations
+          - [ ] Examples are practical and helpful
+          - [ ] No auto-generated sections were modified
+
+          ---
+          🤖 Generated with [Claude Code](https://claude.com/claude-code)" \
+            --base dev

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

@@ -176,7 +176,7 @@ jobs:
           }
 
       - name: Run Database Migrations
-        run: poetry run prisma migrate dev --name updates
+        run: poetry run prisma migrate deploy
         env:
           DATABASE_URL: ${{ steps.supabase.outputs.DB_URL }}
           DIRECT_URL: ${{ steps.supabase.outputs.DB_URL }}

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

@@ -11,6 +11,7 @@ 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) }}
@@ -151,6 +152,14 @@ 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
 
@@ -226,13 +235,25 @@ jobs:
 
       - name: Run Playwright tests
         run: pnpm test:no-build
+        continue-on-error: false
 
-      - name: Upload Playwright artifacts
+      - name: Upload Playwright report
-        if: failure()
+        if: always()
         uses: actions/upload-artifact@v4
         with:
           name: playwright-report
           path: playwright-report
+          if-no-files-found: ignore
+          retention-days: 3
+
+      - name: Upload Playwright test results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: playwright-test-results
+          path: test-results
+          if-no-files-found: ignore
+          retention-days: 3
 
       - name: Print Final Docker Compose logs
         if: always()

.gitignore

@@ -3,6 +3,7 @@
 classic/original_autogpt/keys.py
 classic/original_autogpt/*.json
 auto_gpt_workspace/*
+.autogpt/
 *.mpeg
 .env
 # Root .env files
@@ -177,5 +178,5 @@ autogpt_platform/backend/settings.py
 
 *.ign.*
 .test-contents
-.claude/settings.local.json
+**/.claude/settings.local.json
 /autogpt_platform/backend/logs

.gitmodules

@@ -1,3 +0,0 @@
-[submodule "classic/forge/tests/vcr_cassettes"]
-	path = classic/forge/tests/vcr_cassettes
-	url = https://github.com/Significant-Gravitas/Auto-GPT-test-cassettes

.pre-commit-config.yaml

@@ -43,29 +43,10 @@ repos:
         pass_filenames: false
 
       - id: poetry-install
-        name: Check & Install dependencies - Classic - AutoGPT
+        name: Check & Install dependencies - Classic
-        alias: poetry-install-classic-autogpt
+        alias: poetry-install-classic
-        entry: poetry -C classic/original_autogpt install
+        entry: poetry -C classic install
-        # include forge source (since it's a path dependency)
+        files: ^classic/poetry\.lock$
-        files: ^classic/(original_autogpt|forge)/poetry\.lock$
-        types: [file]
-        language: system
-        pass_filenames: false
-
-      - id: poetry-install
-        name: Check & Install dependencies - Classic - Forge
-        alias: poetry-install-classic-forge
-        entry: poetry -C classic/forge install
-        files: ^classic/forge/poetry\.lock$
-        types: [file]
-        language: system
-        pass_filenames: false
-
-      - id: poetry-install
-        name: Check & Install dependencies - Classic - Benchmark
-        alias: poetry-install-classic-benchmark
-        entry: poetry -C classic/benchmark install
-        files: ^classic/benchmark/poetry\.lock$
         types: [file]
         language: system
         pass_filenames: false
@@ -116,26 +97,10 @@ repos:
         language: system
 
       - id: isort
-        name: Lint (isort) - Classic - AutoGPT
+        name: Lint (isort) - Classic
-        alias: isort-classic-autogpt
+        alias: isort-classic
-        entry: poetry -P classic/original_autogpt run isort -p autogpt
+        entry: bash -c 'cd classic && poetry run isort $(echo "$@" | sed "s|classic/||g")' --
-        files: ^classic/original_autogpt/
+        files: ^classic/(original_autogpt|forge|direct_benchmark)/
-        types: [file, python]
-        language: system
-
-      - id: isort
-        name: Lint (isort) - Classic - Forge
-        alias: isort-classic-forge
-        entry: poetry -P classic/forge run isort -p forge
-        files: ^classic/forge/
-        types: [file, python]
-        language: system
-
-      - id: isort
-        name: Lint (isort) - Classic - Benchmark
-        alias: isort-classic-benchmark
-        entry: poetry -P classic/benchmark run isort -p agbenchmark
-        files: ^classic/benchmark/
         types: [file, python]
         language: system
 
@@ -149,26 +114,13 @@ repos:
 
   - repo: https://github.com/PyCQA/flake8
     rev: 7.0.0
-    # To have flake8 load the config of the individual subprojects, we have to call
+    # Use consolidated flake8 config at classic/.flake8
-    # them separately.
     hooks:
       - id: flake8
-        name: Lint (Flake8) - Classic - AutoGPT
+        name: Lint (Flake8) - Classic
-        alias: flake8-classic-autogpt
+        alias: flake8-classic
-        files: ^classic/original_autogpt/(autogpt|scripts|tests)/
+        files: ^classic/(original_autogpt|forge|direct_benchmark)/
-        args: [--config=classic/original_autogpt/.flake8]
+        args: [--config=classic/.flake8]
-
-      - id: flake8
-        name: Lint (Flake8) - Classic - Forge
-        alias: flake8-classic-forge
-        files: ^classic/forge/(forge|tests)/
-        args: [--config=classic/forge/.flake8]
-
-      - id: flake8
-        name: Lint (Flake8) - Classic - Benchmark
-        alias: flake8-classic-benchmark
-        files: ^classic/benchmark/(agbenchmark|tests)/((?!reports).)*[/.]
-        args: [--config=classic/benchmark/.flake8]
 
   - repo: local
     hooks:
@@ -204,29 +156,10 @@ repos:
         pass_filenames: false
 
       - id: pyright
-        name: Typecheck - Classic - AutoGPT
+        name: Typecheck - Classic
-        alias: pyright-classic-autogpt
+        alias: pyright-classic
-        entry: poetry -C classic/original_autogpt run pyright
+        entry: poetry -C classic run pyright
-        # include forge source (since it's a path dependency) but exclude *_test.py files:
+        files: ^classic/(original_autogpt|forge|direct_benchmark)/.*\.py$|^classic/poetry\.lock$
-        files: ^(classic/original_autogpt/((autogpt|scripts|tests)/|poetry\.lock$)|classic/forge/(forge/.*(?<!_test)\.py|poetry\.lock)$)
-        types: [file]
-        language: system
-        pass_filenames: false
-
-      - id: pyright
-        name: Typecheck - Classic - Forge
-        alias: pyright-classic-forge
-        entry: poetry -C classic/forge run pyright
-        files: ^classic/forge/(forge/|poetry\.lock$)
-        types: [file]
-        language: system
-        pass_filenames: false
-
-      - id: pyright
-        name: Typecheck - Classic - Benchmark
-        alias: pyright-classic-benchmark
-        entry: poetry -C classic/benchmark run pyright
-        files: ^classic/benchmark/(agbenchmark/|tests/|poetry\.lock$)
         types: [file]
         language: system
         pass_filenames: false

autogpt_platform/Makefile

@@ -6,9 +6,10 @@ start-core:
 
 # Stop core services
 stop-core:
-	docker compose stop deps
+	docker compose stop 
 
 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
@@ -60,4 +61,4 @@ 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/backend/.env.default

@@ -58,6 +58,13 @@ 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

@@ -18,3 +18,4 @@ load-tests/results/
 load-tests/*.json
 load-tests/*.log
 load-tests/node_modules/*
+migrations/*/rollback*.sql

autogpt_platform/backend/Dockerfile

@@ -100,6 +100,7 @@ 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/backend/api/external/v1/tools.py

@@ -70,7 +70,7 @@ class RunAgentRequest(BaseModel):
     )
 
 
-def _create_ephemeral_session(user_id: str | None) -> ChatSession:
+def _create_ephemeral_session(user_id: str) -> ChatSession:
     """Create an ephemeral session for stateless API requests."""
     return ChatSession.new(user_id)
 

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

@@ -28,6 +28,7 @@ from backend.executor.manager import get_db_async_client
 from backend.util.settings import Settings
 
 logger = logging.getLogger(__name__)
+settings = Settings()
 
 
 class ExecutionAnalyticsRequest(BaseModel):
@@ -63,6 +64,8 @@ class ExecutionAnalyticsResult(BaseModel):
     score: Optional[float]
     status: str  # "success", "failed", "skipped"
     error_message: Optional[str] = None
+    started_at: Optional[datetime] = None
+    ended_at: Optional[datetime] = None
 
 
 class ExecutionAnalyticsResponse(BaseModel):
@@ -224,11 +227,6 @@ async def generate_execution_analytics(
     )
 
     try:
-        # Validate model configuration
-        settings = Settings()
-        if not settings.secrets.openai_internal_api_key:
-            raise HTTPException(status_code=500, detail="OpenAI API key not configured")
-
         # Get database client
         db_client = get_db_async_client()
 
@@ -320,6 +318,8 @@ async def generate_execution_analytics(
                     ),
                     status="skipped",
                     error_message=None,  # Not an error - just already processed
+                    started_at=execution.started_at,
+                    ended_at=execution.ended_at,
                 )
             )
 
@@ -349,6 +349,9 @@ async def _process_batch(
 ) -> list[ExecutionAnalyticsResult]:
     """Process a batch of executions concurrently."""
 
+    if not settings.secrets.openai_internal_api_key:
+        raise HTTPException(status_code=500, detail="OpenAI API key not configured")
+
     async def process_single_execution(execution) -> ExecutionAnalyticsResult:
         try:
             # Generate activity status and score using the specified model
@@ -387,6 +390,8 @@ async def _process_batch(
                     score=None,
                     status="skipped",
                     error_message="Activity generation returned None",
+                    started_at=execution.started_at,
+                    ended_at=execution.ended_at,
                 )
 
             # Update the execution stats
@@ -416,6 +421,8 @@ async def _process_batch(
                 summary_text=activity_response["activity_status"],
                 score=activity_response["correctness_score"],
                 status="success",
+                started_at=execution.started_at,
+                ended_at=execution.ended_at,
             )
 
         except Exception as e:
@@ -429,6 +436,8 @@ async def _process_batch(
                 score=None,
                 status="failed",
                 error_message=str(e),
+                started_at=execution.started_at,
+                ended_at=execution.ended_at,
             )
 
     # Process all executions in the batch concurrently

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

@@ -1,7 +1,6 @@
 """Configuration management for chat system."""
 
 import os
-from pathlib import Path
 
 from pydantic import Field, field_validator
 from pydantic_settings import BaseSettings
@@ -12,7 +11,11 @@ class ChatConfig(BaseSettings):
 
     # OpenAI API Configuration
     model: str = Field(
-        default="qwen/qwen3-235b-a22b-2507", description="Default model to use"
+        default="anthropic/claude-opus-4.5", description="Default model to use"
+    )
+    title_model: str = Field(
+        default="openai/gpt-4o-mini",
+        description="Model to use for generating session titles (should be fast/cheap)",
     )
     api_key: str | None = Field(default=None, description="OpenAI API key")
     base_url: str | None = Field(
@@ -23,12 +26,6 @@ class ChatConfig(BaseSettings):
     # Session TTL Configuration - 12 hours
     session_ttl: int = Field(default=43200, description="Session TTL in seconds")
 
-    # System Prompt Configuration
-    system_prompt_path: str = Field(
-        default="prompts/chat_system.md",
-        description="Path to system prompt file relative to chat module",
-    )
-
     # Streaming Configuration
     max_context_messages: int = Field(
         default=50, ge=1, le=200, description="Maximum context messages"
@@ -41,6 +38,13 @@ class ChatConfig(BaseSettings):
         default=3, description="Maximum number of agent schedules"
     )
 
+    # Langfuse Prompt Management Configuration
+    # Note: Langfuse credentials are in Settings().secrets (settings.py)
+    langfuse_prompt_name: str = Field(
+        default="CoPilot Prompt",
+        description="Name of the prompt in Langfuse to fetch",
+    )
+
     @field_validator("api_key", mode="before")
     @classmethod
     def get_api_key(cls, v):
@@ -72,43 +76,11 @@ class ChatConfig(BaseSettings):
                 v = "https://openrouter.ai/api/v1"
         return v
 
-    def get_system_prompt(self, **template_vars) -> str:
+    # Prompt paths for different contexts
-        """Load and render the system prompt from file.
+    PROMPT_PATHS: dict[str, str] = {
-
+        "default": "prompts/chat_system.md",
-        Args:
+        "onboarding": "prompts/onboarding_system.md",
-            **template_vars: Variables to substitute in the template
+    }
-
-        Returns:
-            Rendered system prompt string
-
-        """
-        # Get the path relative to this module
-        module_dir = Path(__file__).parent
-        prompt_path = module_dir / self.system_prompt_path
-
-        # Check for .j2 extension first (Jinja2 template)
-        j2_path = Path(str(prompt_path) + ".j2")
-        if j2_path.exists():
-            try:
-                from jinja2 import Template
-
-                template = Template(j2_path.read_text())
-                return template.render(**template_vars)
-            except ImportError:
-                # Jinja2 not installed, fall back to reading as plain text
-                return j2_path.read_text()
-
-        # Check for markdown file
-        if prompt_path.exists():
-            content = prompt_path.read_text()
-
-            # Simple variable substitution if Jinja2 is not available
-            for key, value in template_vars.items():
-                placeholder = f"{{{key}}}"
-                content = content.replace(placeholder, str(value))
-
-            return content
-        raise FileNotFoundError(f"System prompt file not found: {prompt_path}")
 
     class Config:
         """Pydantic config."""

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

@@ -0,0 +1,249 @@
+"""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

@@ -1,6 +1,9 @@
+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,
@@ -16,17 +19,63 @@ 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.exceptions import RedisError
+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
@@ -45,7 +94,8 @@ class Usage(BaseModel):
 
 class ChatSession(BaseModel):
     session_id: str
-    user_id: str | None
+    user_id: str
+    title: str | None = None
     messages: list[ChatMessage]
     usage: list[Usage]
     credentials: dict[str, dict] = {}  # Map of provider -> credential metadata
@@ -55,10 +105,11 @@ class ChatSession(BaseModel):
     successful_agent_schedules: dict[str, int] = {}
 
     @staticmethod
-    def new(user_id: str | None) -> "ChatSession":
+    def new(user_id: str) -> "ChatSession":
         return ChatSession(
             session_id=str(uuid.uuid4()),
             user_id=user_id,
+            title=None,
             messages=[],
             usage=[],
             credentials={},
@@ -66,6 +117,61 @@ class ChatSession(BaseModel):
             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:
@@ -155,50 +261,337 @@ class ChatSession(BaseModel):
         return messages
 
 
-async def get_chat_session(
+async def _get_session_from_cache(session_id: str) -> ChatSession | None:
-    session_id: str,
+    """Get a chat session from Redis cache."""
-    user_id: str | None,
+    redis_key = _get_session_cache_key(session_id)
-) -> ChatSession | None:
-    """Get a chat session by ID."""
-    redis_key = f"chat:session:{session_id}"
     async_redis = await get_redis_async()
-
     raw_session: bytes | None = await async_redis.get(redis_key)
 
     if raw_session is None:
-        logger.warning(f"Session {session_id} not found in Redis")
         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
 
-    if session.user_id is not None and session.user_id != user_id:
+
+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 with the given messages."""
+    """Update a chat session in both cache and database.
 
-    redis_key = f"chat:session:{session.session_id}"
+    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.
 
-    async_redis = await get_redis_async()
+    Raises:
-    resp = await async_redis.setex(
+        DatabaseError: If the database write fails. The cache is still updated
-        redis_key, config.session_ttl, session.model_dump_json()
+            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)
 
-    if not resp:
+    async with lock:
-        raise RedisError(
+        # Get existing message count from DB for incremental saves
-            f"Failed to persist chat session {session.session_id} to Redis: {resp}"
+        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

@@ -43,9 +43,9 @@ async def test_chatsession_serialization_deserialization():
 
 
 @pytest.mark.asyncio(loop_scope="session")
-async def test_chatsession_redis_storage():
+async def test_chatsession_redis_storage(setup_test_user, test_user_id):
 
-    s = ChatSession.new(user_id=None)
+    s = ChatSession.new(user_id=test_user_id)
     s.messages = messages
 
     s = await upsert_chat_session(s)
@@ -59,12 +59,61 @@ async def test_chatsession_redis_storage():
 
 
 @pytest.mark.asyncio(loop_scope="session")
-async def test_chatsession_redis_storage_user_id_mismatch():
+async def test_chatsession_redis_storage_user_id_mismatch(
+    setup_test_user, test_user_id
+):
 
-    s = ChatSession.new(user_id="abc123")
+    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, None)
+    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/prompts/chat_system.md

@@ -1,104 +0,0 @@
-You are Otto, an AI Co-Pilot and Forward Deployed Engineer for AutoGPT, an AI Business Automation tool. Your mission is to help users quickly find and set up AutoGPT agents to solve their business problems.
-
-Here are the functions available to you:
-
-<functions>
-1. **find_agent** - Search for agents that solve the user's problem
-2. **run_agent** - Run or schedule an agent (automatically handles setup)
-</functions>
-
-## HOW run_agent WORKS
-
-The `run_agent` tool automatically handles the entire setup flow:
-
-1. **First call** (no inputs) → Returns available inputs so user can decide what values to use
-2. **Credentials check** → If missing, UI automatically prompts user to add them (you don't need to mention this)
-3. **Execution** → Runs when you provide `inputs` OR set `use_defaults=true`
-
-Parameters:
-- `username_agent_slug` (required): Agent identifier like "creator/agent-name"
-- `inputs`: Object with input values for the agent
-- `use_defaults`: Set to `true` to run with default values (only after user confirms)
-- `schedule_name` + `cron`: For scheduled execution
-
-## WORKFLOW
-
-1. **find_agent** - Search for agents that solve the user's problem
-2. **run_agent** (first call, no inputs) - Get available inputs for the agent
-3. **Ask user** what values they want to use OR if they want to use defaults
-4. **run_agent** (second call) - Either with `inputs={...}` or `use_defaults=true`
-
-## YOUR APPROACH
-
-**Step 1: Understand the Problem**
-- Ask maximum 1-2 targeted questions
-- Focus on: What business problem are they solving?
-- Move quickly to searching for solutions
-
-**Step 2: Find Agents**
-- Use `find_agent` immediately with relevant keywords
-- Suggest the best option from search results
-- Explain briefly how it solves their problem
-
-**Step 3: Get Agent Inputs**
-- Call `run_agent(username_agent_slug="creator/agent-name")` without inputs
-- This returns the available inputs (required and optional)
-- Present these to the user and ask what values they want
-
-**Step 4: Run with User's Choice**
-- If user provides values: `run_agent(username_agent_slug="...", inputs={...})`
-- If user says "use defaults": `run_agent(username_agent_slug="...", use_defaults=true)`
-- On success, share the agent link with the user
-
-**For Scheduled Execution:**
-- Add `schedule_name` and `cron` parameters
-- Example: `run_agent(username_agent_slug="...", inputs={...}, schedule_name="Daily Report", cron="0 9 * * *")`
-
-## FUNCTION CALL FORMAT
-
-To call a function, use this exact format:
-`<function_call>function_name(parameter="value")</function_call>`
-
-Examples:
-- `<function_call>find_agent(query="social media automation")</function_call>`
-- `<function_call>run_agent(username_agent_slug="creator/agent-name")</function_call>` (get inputs)
-- `<function_call>run_agent(username_agent_slug="creator/agent-name", inputs={"topic": "AI news"})</function_call>`
-- `<function_call>run_agent(username_agent_slug="creator/agent-name", use_defaults=true)</function_call>`
-
-## KEY RULES
-
-**What You DON'T Do:**
-- Don't help with login (frontend handles this)
-- Don't mention or explain credentials to the user (frontend handles this automatically)
-- Don't run agents without first showing available inputs to the user
-- Don't use `use_defaults=true` without user explicitly confirming
-- Don't write responses longer than 3 sentences
-
-**What You DO:**
-- Always call run_agent first without inputs to see what's available
-- Ask user what values they want OR if they want to use defaults
-- Keep all responses to maximum 3 sentences
-- Include the agent link in your response after successful execution
-
-**Error Handling:**
-- Authentication needed → "Please sign in via the interface"
-- Credentials missing → The UI handles this automatically. Focus on asking the user about input values instead.
-
-## RESPONSE STRUCTURE
-
-Before responding, wrap your analysis in <thinking> tags to systematically plan your approach:
-- Extract the key business problem or request from the user's message
-- Determine what function call (if any) you need to make next
-- Plan your response to stay under the 3-sentence maximum
-
-Example interaction:
-```
-User: "Run the AI news agent for me"
-Otto: <function_call>run_agent(username_agent_slug="autogpt/ai-news")</function_call>
-[Tool returns: Agent accepts inputs - Required: topic. Optional: num_articles (default: 5)]
-Otto: The AI News agent needs a topic. What topic would you like news about, or should I use the defaults?
-User: "Use defaults"
-Otto: <function_call>run_agent(username_agent_slug="autogpt/ai-news", use_defaults=true)</function_call>
-```
-
-KEEP ANSWERS TO 3 SENTENCES

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

@@ -1,3 +1,10 @@
+"""
+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
 
@@ -5,97 +12,133 @@ from pydantic import BaseModel, Field
 
 
 class ResponseType(str, Enum):
-    """Types of streaming responses."""
+    """Types of streaming responses following AI SDK protocol."""
 
-    TEXT_CHUNK = "text_chunk"
+    # Message lifecycle
-    TEXT_ENDED = "text_ended"
+    START = "start"
-    TOOL_CALL = "tool_call"
+    FINISH = "finish"
-    TOOL_CALL_START = "tool_call_start"
+
-    TOOL_RESPONSE = "tool_response"
+    # 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"
-    STREAM_END = "stream_end"
 
 
 class StreamBaseResponse(BaseModel):
     """Base response model for all streaming responses."""
 
     type: ResponseType
-    timestamp: str | None = None
 
     def to_sse(self) -> str:
         """Convert to SSE format."""
         return f"data: {self.model_dump_json()}\n\n"
 
 
-class StreamTextChunk(StreamBaseResponse):
+# ========== Message Lifecycle ==========
-    """Streaming text content from the assistant."""
-
-    type: ResponseType = ResponseType.TEXT_CHUNK
-    content: str = Field(..., description="Text content chunk")
 
 
-class StreamToolCallStart(StreamBaseResponse):
+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_CALL_START
+    type: ResponseType = ResponseType.TOOL_INPUT_START
-    tool_name: str = Field(..., description="Name of the tool that was executed")
+    toolCallId: str = Field(..., description="Unique tool call ID")
-    tool_id: str = Field(..., description="Unique tool call ID")
+    toolName: str = Field(..., description="Name of the tool being called")
 
 
-class StreamToolCall(StreamBaseResponse):
+class StreamToolInputAvailable(StreamBaseResponse):
-    """Tool invocation notification."""
+    """Tool input is ready for execution."""
 
-    type: ResponseType = ResponseType.TOOL_CALL
+    type: ResponseType = ResponseType.TOOL_INPUT_AVAILABLE
-    tool_id: str = Field(..., description="Unique tool call ID")
+    toolCallId: str = Field(..., description="Unique tool call ID")
-    tool_name: str = Field(..., description="Name of the tool being called")
+    toolName: str = Field(..., description="Name of the tool being called")
-    arguments: dict[str, Any] = Field(
+    input: dict[str, Any] = Field(
-        default_factory=dict, description="Tool arguments"
+        default_factory=dict, description="Tool input arguments"
     )
 
 
-class StreamToolExecutionResult(StreamBaseResponse):
+class StreamToolOutputAvailable(StreamBaseResponse):
     """Tool execution result."""
 
-    type: ResponseType = ResponseType.TOOL_RESPONSE
+    type: ResponseType = ResponseType.TOOL_OUTPUT_AVAILABLE
-    tool_id: str = Field(..., description="Tool call ID this responds to")
+    toolCallId: str = Field(..., description="Tool call ID this responds to")
-    tool_name: str = Field(..., description="Name of the tool that was executed")
+    output: str | dict[str, Any] = Field(..., description="Tool execution output")
-    result: str | dict[str, Any] = Field(..., description="Tool execution result")
+    # 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
-    prompt_tokens: int
+    promptTokens: int = Field(..., description="Number of prompt tokens")
-    completion_tokens: int
+    completionTokens: int = Field(..., description="Number of completion tokens")
-    total_tokens: int
+    totalTokens: int = Field(..., description="Total number of tokens")
 
 
 class StreamError(StreamBaseResponse):
     """Error response."""
 
     type: ResponseType = ResponseType.ERROR
-    message: str = Field(..., description="Error message")
+    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"
     )
-
-
-class StreamTextEnded(StreamBaseResponse):
-    """Text streaming completed marker."""
-
-    type: ResponseType = ResponseType.TEXT_ENDED
-
-
-class StreamEnd(StreamBaseResponse):
-    """End of stream marker."""
-
-    type: ResponseType = ResponseType.STREAM_END
-    summary: dict[str, Any] | None = Field(
-        default=None, description="Stream summary statistics"
-    )

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

@@ -13,12 +13,25 @@ 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"],
 )
@@ -26,6 +39,14 @@ router = APIRouter(
 # ========== 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."""
 
@@ -44,22 +65,77 @@ class SessionDetailResponse(BaseModel):
     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 | None, Depends(auth.get_user_id)],
+    user_id: Annotated[str, Depends(auth.get_user_id)],
 ) -> CreateSessionResponse:
     """
     Create a new chat session.
 
-    Initiates a new chat session for either an authenticated or anonymous user.
+    Initiates a new chat session for the authenticated user.
 
     Args:
-        user_id: The optional authenticated user ID parsed from the JWT. If missing, creates an anonymous session.
+        user_id: The authenticated user ID parsed from the JWT (required).
 
     Returns:
         CreateSessionResponse: Details of the created session.
@@ -67,15 +143,15 @@ async def create_session(
     """
     logger.info(
         f"Creating session with user_id: "
-        f"...{user_id[-8:] if user_id and len(user_id) > 8 else '<redacted>'}"
+        f"...{user_id[-8:] if len(user_id) > 8 else '<redacted>'}"
     )
 
-    session = await chat_service.create_chat_session(user_id)
+    session = await create_chat_session(user_id)
 
     return CreateSessionResponse(
         id=session.session_id,
         created_at=session.started_at.isoformat(),
-        user_id=session.user_id or None,
+        user_id=session.user_id,
     )
 
 
@@ -99,29 +175,88 @@ async def get_session(
         SessionDetailResponse: Details for the requested session; raises NotFoundError if not found.
 
     """
-    session = await chat_service.get_session(session_id, user_id)
+    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=[message.model_dump() for message in session.messages],
+        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(
+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.
+    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
@@ -137,14 +272,7 @@ async def stream_chat(
         StreamingResponse: SSE-formatted response chunks.
 
     """
-    # Validate session exists before starting the stream
+    session = await _validate_and_get_session(session_id, user_id)
-    # This prevents errors after the response has already started
-    session = await chat_service.get_session(session_id, user_id)
-
-    if not session:
-        raise NotFoundError(f"Session {session_id} not found. ")
-    if session.user_id is None and user_id is not None:
-        session = await chat_service.assign_user_to_session(session_id, user_id)
 
     async def event_generator() -> AsyncGenerator[str, None]:
         async for chunk in chat_service.stream_chat_completion(
@@ -155,6 +283,8 @@ async def stream_chat(
             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(),
@@ -163,6 +293,7 @@ async def stream_chat(
             "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
         },
     )
 
@@ -201,16 +332,28 @@ async def health_check() -> dict:
     """
     Health check endpoint for the chat service.
 
-    Performs a full cycle test of session creation, assignment, and retrieval. Should always return healthy
+    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.
 
     """
-    session = await chat_service.create_chat_session(None)
+    from backend.data.user import get_or_create_user
-    await chat_service.assign_user_to_session(session.session_id, "test_user")
+
-    await chat_service.get_session(session.session_id, "test_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",

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

@@ -4,18 +4,19 @@ from os import getenv
 import pytest
 
 from . import service as chat_service
+from .model import create_chat_session, get_chat_session, upsert_chat_session
 from .response_model import (
-    StreamEnd,
     StreamError,
-    StreamTextChunk,
+    StreamFinish,
-    StreamToolExecutionResult,
+    StreamTextDelta,
+    StreamToolOutputAvailable,
 )
 
 logger = logging.getLogger(__name__)
 
 
 @pytest.mark.asyncio(loop_scope="session")
-async def test_stream_chat_completion():
+async def test_stream_chat_completion(setup_test_user, test_user_id):
     """
     Test the stream_chat_completion function.
     """
@@ -23,7 +24,7 @@ async def test_stream_chat_completion():
     if not api_key:
         return pytest.skip("OPEN_ROUTER_API_KEY is not set, skipping test")
 
-    session = await chat_service.create_chat_session()
+    session = await create_chat_session(test_user_id)
 
     has_errors = False
     has_ended = False
@@ -34,9 +35,9 @@ async def test_stream_chat_completion():
         logger.info(chunk)
         if isinstance(chunk, StreamError):
             has_errors = True
-        if isinstance(chunk, StreamTextChunk):
+        if isinstance(chunk, StreamTextDelta):
-            assistant_message += chunk.content
+            assistant_message += chunk.delta
-        if isinstance(chunk, StreamEnd):
+        if isinstance(chunk, StreamFinish):
             has_ended = True
 
     assert has_ended, "Chat completion did not end"
@@ -45,7 +46,7 @@ async def test_stream_chat_completion():
 
 
 @pytest.mark.asyncio(loop_scope="session")
-async def test_stream_chat_completion_with_tool_calls():
+async def test_stream_chat_completion_with_tool_calls(setup_test_user, test_user_id):
     """
     Test the stream_chat_completion function.
     """
@@ -53,8 +54,8 @@ async def test_stream_chat_completion_with_tool_calls():
     if not api_key:
         return pytest.skip("OPEN_ROUTER_API_KEY is not set, skipping test")
 
-    session = await chat_service.create_chat_session()
+    session = await create_chat_session(test_user_id)
-    session = await chat_service.upsert_chat_session(session)
+    session = await upsert_chat_session(session)
 
     has_errors = False
     has_ended = False
@@ -68,14 +69,14 @@ async def test_stream_chat_completion_with_tool_calls():
         if isinstance(chunk, StreamError):
             has_errors = True
 
-        if isinstance(chunk, StreamEnd):
+        if isinstance(chunk, StreamFinish):
             has_ended = True
-        if isinstance(chunk, StreamToolExecutionResult):
+        if isinstance(chunk, StreamToolOutputAvailable):
             had_tool_calls = True
 
     assert has_ended, "Chat completion did not end"
     assert not has_errors, "Error occurred while streaming chat completion"
     assert had_tool_calls, "Tool calls did not occur"
-    session = await chat_service.get_session(session.session_id)
+    session = await get_chat_session(session.session_id)
     assert session, "Session not found"
     assert session.usage, "Usage is empty"

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

@@ -4,21 +4,44 @@ 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 .create_agent import CreateAgentTool
+from .edit_agent import EditAgentTool
 from .find_agent import FindAgentTool
+from .find_block import FindBlockTool
+from .find_library_agent import FindLibraryAgentTool
+from .get_doc_page import GetDocPageTool
 from .run_agent import RunAgentTool
+from .run_block import RunBlockTool
+from .search_docs import SearchDocsTool
 
 if TYPE_CHECKING:
-    from backend.api.features.chat.response_model import StreamToolExecutionResult
+    from backend.api.features.chat.response_model import StreamToolOutputAvailable
 
-# Initialize tool instances
+# Single source of truth for all tools
-find_agent_tool = FindAgentTool()
+TOOL_REGISTRY: dict[str, BaseTool] = {
-run_agent_tool = RunAgentTool()
+    "add_understanding": AddUnderstandingTool(),
+    "create_agent": CreateAgentTool(),
+    "edit_agent": EditAgentTool(),
+    "find_agent": FindAgentTool(),
+    "find_block": FindBlockTool(),
+    "find_library_agent": FindLibraryAgentTool(),
+    "run_agent": RunAgentTool(),
+    "run_block": RunBlockTool(),
+    "view_agent_output": AgentOutputTool(),
+    "search_docs": SearchDocsTool(),
+    "get_doc_page": GetDocPageTool(),
+}
 
-# Export tools as OpenAI format
+# 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] = [
-    find_agent_tool.as_openai_tool(),
+    tool.as_openai_tool() for tool in TOOL_REGISTRY.values()
-    run_agent_tool.as_openai_tool(),
 ]
 
 
@@ -28,14 +51,9 @@ async def execute_tool(
     user_id: str | None,
     session: ChatSession,
     tool_call_id: str,
-) -> "StreamToolExecutionResult":
+) -> "StreamToolOutputAvailable":
-
+    """Execute a tool by name."""
-    tool_map: dict[str, BaseTool] = {
+    tool = TOOL_REGISTRY.get(tool_name)
-        "find_agent": find_agent_tool,
+    if not tool:
-        "run_agent": run_agent_tool,
-    }
-    if tool_name not in tool_map:
         raise ValueError(f"Tool {tool_name} not found")
-    return await tool_map[tool_name].execute(
+    return await tool.execute(user_id, session, tool_call_id, **parameters)
-        user_id, session, tool_call_id, **parameters
-    )

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

@@ -3,6 +3,7 @@ from datetime import UTC, datetime
 from os import getenv
 
 import pytest
+from prisma.types import ProfileCreateInput
 from pydantic import SecretStr
 
 from backend.api.features.chat.model import ChatSession
@@ -17,7 +18,7 @@ from backend.data.user import get_or_create_user
 from backend.integrations.credentials_store import IntegrationCredentialsStore
 
 
-def make_session(user_id: str | None = None):
+def make_session(user_id: str):
     return ChatSession(
         session_id=str(uuid.uuid4()),
         user_id=user_id,
@@ -49,13 +50,13 @@ async def setup_test_data():
     # 1b. Create a profile with username for the user (required for store agent lookup)
     username = user.email.split("@")[0]
     await prisma.profile.create(
-        data={
+        data=ProfileCreateInput(
-            "userId": user.id,
+            userId=user.id,
-            "username": username,
+            username=username,
-            "name": f"Test User {username}",
+            name=f"Test User {username}",
-            "description": "Test user profile",
+            description="Test user profile",
-            "links": [],  # Required field - empty array for test profiles
+            links=[],  # Required field - empty array for test profiles
-        }
+        )
     )
 
     # 2. Create a test graph with agent input -> agent output
@@ -172,13 +173,13 @@ async def setup_llm_test_data():
     # 1b. Create a profile with username for the user (required for store agent lookup)
     username = user.email.split("@")[0]
     await prisma.profile.create(
-        data={
+        data=ProfileCreateInput(
-            "userId": user.id,
+            userId=user.id,
-            "username": username,
+            username=username,
-            "name": f"Test User {username}",
+            name=f"Test User {username}",
-            "description": "Test user profile for LLM tests",
+            description="Test user profile for LLM tests",
-            "links": [],  # Required field - empty array for test profiles
+            links=[],  # Required field - empty array for test profiles
-        }
+        )
     )
 
     # 2. Create test OpenAI credentials for the user
@@ -332,13 +333,13 @@ async def setup_firecrawl_test_data():
     # 1b. Create a profile with username for the user (required for store agent lookup)
     username = user.email.split("@")[0]
     await prisma.profile.create(
-        data={
+        data=ProfileCreateInput(
-            "userId": user.id,
+            userId=user.id,
-            "username": username,
+            username=username,
-            "name": f"Test User {username}",
+            name=f"Test User {username}",
-            "description": "Test user profile for Firecrawl tests",
+            description="Test user profile for Firecrawl tests",
-            "links": [],  # Required field - empty array for test profiles
+            links=[],  # Required field - empty array for test profiles
-        }
+        )
     )
 
     # NOTE: We deliberately do NOT create Firecrawl credentials for this user

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

@@ -0,0 +1,122 @@
+"""Tool for capturing user business understanding incrementally."""
+
+import logging
+from typing import Any
+
+from langfuse import observe
+
+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
+
+    @observe(as_type="tool", name="add_understanding")
+    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_generator/__init__.py

@@ -0,0 +1,29 @@
+"""Agent generator package - Creates agents from natural language."""
+
+from .core import (
+    apply_agent_patch,
+    decompose_goal,
+    generate_agent,
+    generate_agent_patch,
+    get_agent_as_json,
+    save_agent_to_library,
+)
+from .fixer import apply_all_fixes
+from .utils import get_blocks_info
+from .validator import validate_agent
+
+__all__ = [
+    # Core functions
+    "decompose_goal",
+    "generate_agent",
+    "generate_agent_patch",
+    "apply_agent_patch",
+    "save_agent_to_library",
+    "get_agent_as_json",
+    # Fixer
+    "apply_all_fixes",
+    # Validator
+    "validate_agent",
+    # Utils
+    "get_blocks_info",
+]

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

@@ -0,0 +1,25 @@
+"""OpenRouter client configuration for agent generation."""
+
+import os
+
+from openai import AsyncOpenAI
+
+# Configuration - use OPEN_ROUTER_API_KEY for consistency with chat/config.py
+OPENROUTER_API_KEY = os.getenv("OPEN_ROUTER_API_KEY")
+AGENT_GENERATOR_MODEL = os.getenv("AGENT_GENERATOR_MODEL", "anthropic/claude-opus-4.5")
+
+# OpenRouter client (OpenAI-compatible API)
+_client: AsyncOpenAI | None = None
+
+
+def get_client() -> AsyncOpenAI:
+    """Get or create the OpenRouter client."""
+    global _client
+    if _client is None:
+        if not OPENROUTER_API_KEY:
+            raise ValueError("OPENROUTER_API_KEY environment variable is required")
+        _client = AsyncOpenAI(
+            base_url="https://openrouter.ai/api/v1",
+            api_key=OPENROUTER_API_KEY,
+        )
+    return _client

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

@@ -0,0 +1,390 @@
+"""Core agent generation functions."""
+
+import copy
+import json
+import logging
+import uuid
+from typing import Any
+
+from backend.api.features.library import db as library_db
+from backend.data.graph import Graph, Link, Node, create_graph
+
+from .client import AGENT_GENERATOR_MODEL, get_client
+from .prompts import DECOMPOSITION_PROMPT, GENERATION_PROMPT, PATCH_PROMPT
+from .utils import get_block_summaries, parse_json_from_llm
+
+logger = logging.getLogger(__name__)
+
+
+async def decompose_goal(description: str, context: str = "") -> dict[str, Any] | None:
+    """Break down a goal into steps or return clarifying questions.
+
+    Args:
+        description: Natural language goal description
+        context: Additional context (e.g., answers to previous questions)
+
+    Returns:
+        Dict with either:
+        - {"type": "clarifying_questions", "questions": [...]}
+        - {"type": "instructions", "steps": [...]}
+        Or None on error
+    """
+    client = get_client()
+    prompt = DECOMPOSITION_PROMPT.format(block_summaries=get_block_summaries())
+
+    full_description = description
+    if context:
+        full_description = f"{description}\n\nAdditional context:\n{context}"
+
+    try:
+        response = await client.chat.completions.create(
+            model=AGENT_GENERATOR_MODEL,
+            messages=[
+                {"role": "system", "content": prompt},
+                {"role": "user", "content": full_description},
+            ],
+            temperature=0,
+        )
+
+        content = response.choices[0].message.content
+        if content is None:
+            logger.error("LLM returned empty content for decomposition")
+            return None
+
+        result = parse_json_from_llm(content)
+
+        if result is None:
+            logger.error(f"Failed to parse decomposition response: {content[:200]}")
+            return None
+
+        return result
+
+    except Exception as e:
+        logger.error(f"Error decomposing goal: {e}")
+        return None
+
+
+async def generate_agent(instructions: dict[str, Any]) -> dict[str, Any] | None:
+    """Generate agent JSON from instructions.
+
+    Args:
+        instructions: Structured instructions from decompose_goal
+
+    Returns:
+        Agent JSON dict or None on error
+    """
+    client = get_client()
+    prompt = GENERATION_PROMPT.format(block_summaries=get_block_summaries())
+
+    try:
+        response = await client.chat.completions.create(
+            model=AGENT_GENERATOR_MODEL,
+            messages=[
+                {"role": "system", "content": prompt},
+                {"role": "user", "content": json.dumps(instructions, indent=2)},
+            ],
+            temperature=0,
+        )
+
+        content = response.choices[0].message.content
+        if content is None:
+            logger.error("LLM returned empty content for agent generation")
+            return None
+
+        result = parse_json_from_llm(content)
+
+        if result is None:
+            logger.error(f"Failed to parse agent JSON: {content[:200]}")
+            return None
+
+        # Ensure required fields
+        if "id" not in result:
+            result["id"] = str(uuid.uuid4())
+        if "version" not in result:
+            result["version"] = 1
+        if "is_active" not in result:
+            result["is_active"] = True
+
+        return result
+
+    except Exception as e:
+        logger.error(f"Error generating agent: {e}")
+        return None
+
+
+def json_to_graph(agent_json: dict[str, Any]) -> Graph:
+    """Convert agent JSON dict to Graph model.
+
+    Args:
+        agent_json: Agent JSON with nodes and links
+
+    Returns:
+        Graph ready for saving
+    """
+    nodes = []
+    for n in agent_json.get("nodes", []):
+        node = Node(
+            id=n.get("id", str(uuid.uuid4())),
+            block_id=n["block_id"],
+            input_default=n.get("input_default", {}),
+            metadata=n.get("metadata", {}),
+        )
+        nodes.append(node)
+
+    links = []
+    for link_data in agent_json.get("links", []):
+        link = Link(
+            id=link_data.get("id", str(uuid.uuid4())),
+            source_id=link_data["source_id"],
+            sink_id=link_data["sink_id"],
+            source_name=link_data["source_name"],
+            sink_name=link_data["sink_name"],
+            is_static=link_data.get("is_static", False),
+        )
+        links.append(link)
+
+    return Graph(
+        id=agent_json.get("id", str(uuid.uuid4())),
+        version=agent_json.get("version", 1),
+        is_active=agent_json.get("is_active", True),
+        name=agent_json.get("name", "Generated Agent"),
+        description=agent_json.get("description", ""),
+        nodes=nodes,
+        links=links,
+    )
+
+
+def _reassign_node_ids(graph: Graph) -> None:
+    """Reassign all node and link IDs to new UUIDs.
+
+    This is needed when creating a new version to avoid unique constraint violations.
+    """
+    # Create mapping from old node IDs to new UUIDs
+    id_map = {node.id: str(uuid.uuid4()) for node in graph.nodes}
+
+    # Reassign node IDs
+    for node in graph.nodes:
+        node.id = id_map[node.id]
+
+    # Update link references to use new node IDs
+    for link in graph.links:
+        link.id = str(uuid.uuid4())  # Also give links new IDs
+        if link.source_id in id_map:
+            link.source_id = id_map[link.source_id]
+        if link.sink_id in id_map:
+            link.sink_id = id_map[link.sink_id]
+
+
+async def save_agent_to_library(
+    agent_json: dict[str, Any], user_id: str, is_update: bool = False
+) -> tuple[Graph, Any]:
+    """Save agent to database and user's library.
+
+    Args:
+        agent_json: Agent JSON dict
+        user_id: User ID
+        is_update: Whether this is an update to an existing agent
+
+    Returns:
+        Tuple of (created Graph, LibraryAgent)
+    """
+    from backend.data.graph import get_graph_all_versions
+
+    graph = json_to_graph(agent_json)
+
+    if is_update:
+        # For updates, keep the same graph ID but increment version
+        # and reassign node/link IDs to avoid conflicts
+        if graph.id:
+            existing_versions = await get_graph_all_versions(graph.id, user_id)
+            if existing_versions:
+                latest_version = max(v.version for v in existing_versions)
+                graph.version = latest_version + 1
+                # Reassign node IDs (but keep graph ID the same)
+                _reassign_node_ids(graph)
+                logger.info(f"Updating agent {graph.id} to version {graph.version}")
+    else:
+        # For new agents, always generate a fresh UUID to avoid collisions
+        graph.id = str(uuid.uuid4())
+        graph.version = 1
+        # Reassign all node IDs as well
+        _reassign_node_ids(graph)
+        logger.info(f"Creating new agent with ID {graph.id}")
+
+    # Save to database
+    created_graph = await create_graph(graph, user_id)
+
+    # Add to user's library (or update existing library agent)
+    library_agents = await library_db.create_library_agent(
+        graph=created_graph,
+        user_id=user_id,
+        create_library_agents_for_sub_graphs=False,
+    )
+
+    return created_graph, library_agents[0]
+
+
+async def get_agent_as_json(
+    graph_id: str, user_id: str | None
+) -> dict[str, Any] | None:
+    """Fetch an agent and convert to JSON format for editing.
+
+    Args:
+        graph_id: Graph ID or library agent ID
+        user_id: User ID
+
+    Returns:
+        Agent as JSON dict or None if not found
+    """
+    from backend.data.graph import get_graph
+
+    # Try to get the graph (version=None gets the active version)
+    graph = await get_graph(graph_id, version=None, user_id=user_id)
+    if not graph:
+        return None
+
+    # Convert to JSON format
+    nodes = []
+    for node in graph.nodes:
+        nodes.append(
+            {
+                "id": node.id,
+                "block_id": node.block_id,
+                "input_default": node.input_default,
+                "metadata": node.metadata,
+            }
+        )
+
+    links = []
+    for node in graph.nodes:
+        for link in node.output_links:
+            links.append(
+                {
+                    "id": link.id,
+                    "source_id": link.source_id,
+                    "sink_id": link.sink_id,
+                    "source_name": link.source_name,
+                    "sink_name": link.sink_name,
+                    "is_static": link.is_static,
+                }
+            )
+
+    return {
+        "id": graph.id,
+        "name": graph.name,
+        "description": graph.description,
+        "version": graph.version,
+        "is_active": graph.is_active,
+        "nodes": nodes,
+        "links": links,
+    }
+
+
+async def generate_agent_patch(
+    update_request: str, current_agent: dict[str, Any]
+) -> dict[str, Any] | None:
+    """Generate a patch to update an existing agent.
+
+    Args:
+        update_request: Natural language description of changes
+        current_agent: Current agent JSON
+
+    Returns:
+        Patch dict or clarifying questions, or None on error
+    """
+    client = get_client()
+    prompt = PATCH_PROMPT.format(
+        current_agent=json.dumps(current_agent, indent=2),
+        block_summaries=get_block_summaries(),
+    )
+
+    try:
+        response = await client.chat.completions.create(
+            model=AGENT_GENERATOR_MODEL,
+            messages=[
+                {"role": "system", "content": prompt},
+                {"role": "user", "content": update_request},
+            ],
+            temperature=0,
+        )
+
+        content = response.choices[0].message.content
+        if content is None:
+            logger.error("LLM returned empty content for patch generation")
+            return None
+
+        return parse_json_from_llm(content)
+
+    except Exception as e:
+        logger.error(f"Error generating patch: {e}")
+        return None
+
+
+def apply_agent_patch(
+    current_agent: dict[str, Any], patch: dict[str, Any]
+) -> dict[str, Any]:
+    """Apply a patch to an existing agent.
+
+    Args:
+        current_agent: Current agent JSON
+        patch: Patch dict with operations
+
+    Returns:
+        Updated agent JSON
+    """
+    agent = copy.deepcopy(current_agent)
+    patches = patch.get("patches", [])
+
+    for p in patches:
+        patch_type = p.get("type")
+
+        if patch_type == "modify":
+            node_id = p.get("node_id")
+            changes = p.get("changes", {})
+
+            for node in agent.get("nodes", []):
+                if node["id"] == node_id:
+                    _deep_update(node, changes)
+                    logger.debug(f"Modified node {node_id}")
+                    break
+
+        elif patch_type == "add":
+            new_nodes = p.get("new_nodes", [])
+            new_links = p.get("new_links", [])
+
+            agent["nodes"] = agent.get("nodes", []) + new_nodes
+            agent["links"] = agent.get("links", []) + new_links
+            logger.debug(f"Added {len(new_nodes)} nodes, {len(new_links)} links")
+
+        elif patch_type == "remove":
+            node_ids_to_remove = set(p.get("node_ids", []))
+            link_ids_to_remove = set(p.get("link_ids", []))
+
+            # Remove nodes
+            agent["nodes"] = [
+                n for n in agent.get("nodes", []) if n["id"] not in node_ids_to_remove
+            ]
+
+            # Remove links (both explicit and those referencing removed nodes)
+            agent["links"] = [
+                link
+                for link in agent.get("links", [])
+                if link["id"] not in link_ids_to_remove
+                and link["source_id"] not in node_ids_to_remove
+                and link["sink_id"] not in node_ids_to_remove
+            ]
+
+            logger.debug(
+                f"Removed {len(node_ids_to_remove)} nodes, {len(link_ids_to_remove)} links"
+            )
+
+    return agent
+
+
+def _deep_update(target: dict, source: dict) -> None:
+    """Recursively update a dict with another dict."""
+    for key, value in source.items():
+        if key in target and isinstance(target[key], dict) and isinstance(value, dict):
+            _deep_update(target[key], value)
+        else:
+            target[key] = value

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

@@ -0,0 +1,606 @@
+"""Agent fixer - Fixes common LLM generation errors."""
+
+import logging
+import re
+import uuid
+from typing import Any
+
+from .utils import (
+    ADDTODICTIONARY_BLOCK_ID,
+    ADDTOLIST_BLOCK_ID,
+    CODE_EXECUTION_BLOCK_ID,
+    CONDITION_BLOCK_ID,
+    CREATEDICT_BLOCK_ID,
+    CREATELIST_BLOCK_ID,
+    DATA_SAMPLING_BLOCK_ID,
+    DOUBLE_CURLY_BRACES_BLOCK_IDS,
+    GET_CURRENT_DATE_BLOCK_ID,
+    STORE_VALUE_BLOCK_ID,
+    UNIVERSAL_TYPE_CONVERTER_BLOCK_ID,
+    get_blocks_info,
+    is_valid_uuid,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def fix_agent_ids(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix invalid UUIDs in agent and link IDs."""
+    # Fix agent ID
+    if not is_valid_uuid(agent.get("id", "")):
+        agent["id"] = str(uuid.uuid4())
+        logger.debug(f"Fixed agent ID: {agent['id']}")
+
+    # Fix node IDs
+    id_mapping = {}  # Old ID -> New ID
+    for node in agent.get("nodes", []):
+        if not is_valid_uuid(node.get("id", "")):
+            old_id = node.get("id", "")
+            new_id = str(uuid.uuid4())
+            id_mapping[old_id] = new_id
+            node["id"] = new_id
+            logger.debug(f"Fixed node ID: {old_id} -> {new_id}")
+
+    # Fix link IDs and update references
+    for link in agent.get("links", []):
+        if not is_valid_uuid(link.get("id", "")):
+            link["id"] = str(uuid.uuid4())
+            logger.debug(f"Fixed link ID: {link['id']}")
+
+        # Update source/sink IDs if they were remapped
+        if link.get("source_id") in id_mapping:
+            link["source_id"] = id_mapping[link["source_id"]]
+        if link.get("sink_id") in id_mapping:
+            link["sink_id"] = id_mapping[link["sink_id"]]
+
+    return agent
+
+
+def fix_double_curly_braces(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix single curly braces to double in template blocks."""
+    for node in agent.get("nodes", []):
+        if node.get("block_id") not in DOUBLE_CURLY_BRACES_BLOCK_IDS:
+            continue
+
+        input_data = node.get("input_default", {})
+        for key in ("prompt", "format"):
+            if key in input_data and isinstance(input_data[key], str):
+                original = input_data[key]
+                # Fix simple variable references: {var} -> {{var}}
+                fixed = re.sub(
+                    r"(?<!\{)\{([a-zA-Z_][a-zA-Z0-9_]*)\}(?!\})",
+                    r"{{\1}}",
+                    original,
+                )
+                if fixed != original:
+                    input_data[key] = fixed
+                    logger.debug(f"Fixed curly braces in {key}")
+
+    return agent
+
+
+def fix_storevalue_before_condition(agent: dict[str, Any]) -> dict[str, Any]:
+    """Add StoreValueBlock before ConditionBlock if needed for value2."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+
+    # Find all ConditionBlock nodes
+    condition_node_ids = {
+        node["id"] for node in nodes if node.get("block_id") == CONDITION_BLOCK_ID
+    }
+
+    if not condition_node_ids:
+        return agent
+
+    new_nodes = []
+    new_links = []
+    processed_conditions = set()
+
+    for link in links:
+        sink_id = link.get("sink_id")
+        sink_name = link.get("sink_name")
+
+        # Check if this link goes to a ConditionBlock's value2
+        if sink_id in condition_node_ids and sink_name == "value2":
+            source_node = next(
+                (n for n in nodes if n["id"] == link.get("source_id")), None
+            )
+
+            # Skip if source is already a StoreValueBlock
+            if source_node and source_node.get("block_id") == STORE_VALUE_BLOCK_ID:
+                continue
+
+            # Skip if we already processed this condition
+            if sink_id in processed_conditions:
+                continue
+
+            processed_conditions.add(sink_id)
+
+            # Create StoreValueBlock
+            store_node_id = str(uuid.uuid4())
+            store_node = {
+                "id": store_node_id,
+                "block_id": STORE_VALUE_BLOCK_ID,
+                "input_default": {"data": None},
+                "metadata": {"position": {"x": 0, "y": -100}},
+            }
+            new_nodes.append(store_node)
+
+            # Create link: original source -> StoreValueBlock
+            new_links.append(
+                {
+                    "id": str(uuid.uuid4()),
+                    "source_id": link["source_id"],
+                    "source_name": link["source_name"],
+                    "sink_id": store_node_id,
+                    "sink_name": "input",
+                    "is_static": False,
+                }
+            )
+
+            # Update original link: StoreValueBlock -> ConditionBlock
+            link["source_id"] = store_node_id
+            link["source_name"] = "output"
+
+            logger.debug(f"Added StoreValueBlock before ConditionBlock {sink_id}")
+
+    if new_nodes:
+        agent["nodes"] = nodes + new_nodes
+
+    return agent
+
+
+def fix_addtolist_blocks(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix AddToList blocks by adding prerequisite empty AddToList block.
+
+    When an AddToList block is found:
+    1. Checks if there's a CreateListBlock before it
+    2. Removes CreateListBlock if linked directly to AddToList
+    3. Adds an empty AddToList block before the original
+    4. Ensures the original has a self-referencing link
+    """
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+    new_nodes = []
+    original_addtolist_ids = set()
+    nodes_to_remove = set()
+    links_to_remove = []
+
+    # First pass: identify CreateListBlock nodes to remove
+    for link in links:
+        source_node = next(
+            (n for n in nodes if n.get("id") == link.get("source_id")), None
+        )
+        sink_node = next((n for n in nodes if n.get("id") == link.get("sink_id")), None)
+
+        if (
+            source_node
+            and sink_node
+            and source_node.get("block_id") == CREATELIST_BLOCK_ID
+            and sink_node.get("block_id") == ADDTOLIST_BLOCK_ID
+        ):
+            nodes_to_remove.add(source_node.get("id"))
+            links_to_remove.append(link)
+            logger.debug(f"Removing CreateListBlock {source_node.get('id')}")
+
+    # Second pass: process AddToList blocks
+    filtered_nodes = []
+    for node in nodes:
+        if node.get("id") in nodes_to_remove:
+            continue
+
+        if node.get("block_id") == ADDTOLIST_BLOCK_ID:
+            original_addtolist_ids.add(node.get("id"))
+            node_id = node.get("id")
+            pos = node.get("metadata", {}).get("position", {"x": 0, "y": 0})
+
+            # Check if already has prerequisite
+            has_prereq = any(
+                link.get("sink_id") == node_id
+                and link.get("sink_name") == "list"
+                and link.get("source_name") == "updated_list"
+                for link in links
+            )
+
+            if not has_prereq:
+                # Remove links to "list" input (except self-reference)
+                for link in links:
+                    if (
+                        link.get("sink_id") == node_id
+                        and link.get("sink_name") == "list"
+                        and link.get("source_id") != node_id
+                        and link not in links_to_remove
+                    ):
+                        links_to_remove.append(link)
+
+                # Create prerequisite AddToList block
+                prereq_id = str(uuid.uuid4())
+                prereq_node = {
+                    "id": prereq_id,
+                    "block_id": ADDTOLIST_BLOCK_ID,
+                    "input_default": {"list": [], "entry": None, "entries": []},
+                    "metadata": {
+                        "position": {"x": pos.get("x", 0) - 800, "y": pos.get("y", 0)}
+                    },
+                }
+                new_nodes.append(prereq_node)
+
+                # Link prerequisite to original
+                links.append(
+                    {
+                        "id": str(uuid.uuid4()),
+                        "source_id": prereq_id,
+                        "source_name": "updated_list",
+                        "sink_id": node_id,
+                        "sink_name": "list",
+                        "is_static": False,
+                    }
+                )
+                logger.debug(f"Added prerequisite AddToList block for {node_id}")
+
+        filtered_nodes.append(node)
+
+    # Remove marked links
+    filtered_links = [link for link in links if link not in links_to_remove]
+
+    # Add self-referencing links for original AddToList blocks
+    for node in filtered_nodes + new_nodes:
+        if (
+            node.get("block_id") == ADDTOLIST_BLOCK_ID
+            and node.get("id") in original_addtolist_ids
+        ):
+            node_id = node.get("id")
+            has_self_ref = any(
+                link["source_id"] == node_id
+                and link["sink_id"] == node_id
+                and link["source_name"] == "updated_list"
+                and link["sink_name"] == "list"
+                for link in filtered_links
+            )
+            if not has_self_ref:
+                filtered_links.append(
+                    {
+                        "id": str(uuid.uuid4()),
+                        "source_id": node_id,
+                        "source_name": "updated_list",
+                        "sink_id": node_id,
+                        "sink_name": "list",
+                        "is_static": False,
+                    }
+                )
+                logger.debug(f"Added self-reference for AddToList {node_id}")
+
+    agent["nodes"] = filtered_nodes + new_nodes
+    agent["links"] = filtered_links
+    return agent
+
+
+def fix_addtodictionary_blocks(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix AddToDictionary blocks by removing empty CreateDictionary nodes."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+    nodes_to_remove = set()
+    links_to_remove = []
+
+    for link in links:
+        source_node = next(
+            (n for n in nodes if n.get("id") == link.get("source_id")), None
+        )
+        sink_node = next((n for n in nodes if n.get("id") == link.get("sink_id")), None)
+
+        if (
+            source_node
+            and sink_node
+            and source_node.get("block_id") == CREATEDICT_BLOCK_ID
+            and sink_node.get("block_id") == ADDTODICTIONARY_BLOCK_ID
+        ):
+            nodes_to_remove.add(source_node.get("id"))
+            links_to_remove.append(link)
+            logger.debug(f"Removing CreateDictionary {source_node.get('id')}")
+
+    agent["nodes"] = [n for n in nodes if n.get("id") not in nodes_to_remove]
+    agent["links"] = [link for link in links if link not in links_to_remove]
+    return agent
+
+
+def fix_code_execution_output(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix CodeExecutionBlock output: change 'response' to 'stdout_logs'."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+
+    for link in links:
+        source_node = next(
+            (n for n in nodes if n.get("id") == link.get("source_id")), None
+        )
+        if (
+            source_node
+            and source_node.get("block_id") == CODE_EXECUTION_BLOCK_ID
+            and link.get("source_name") == "response"
+        ):
+            link["source_name"] = "stdout_logs"
+            logger.debug("Fixed CodeExecutionBlock output: response -> stdout_logs")
+
+    return agent
+
+
+def fix_data_sampling_sample_size(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix DataSamplingBlock by setting sample_size to 1 as default."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+    links_to_remove = []
+
+    for node in nodes:
+        if node.get("block_id") == DATA_SAMPLING_BLOCK_ID:
+            node_id = node.get("id")
+            input_default = node.get("input_default", {})
+
+            # Remove links to sample_size
+            for link in links:
+                if (
+                    link.get("sink_id") == node_id
+                    and link.get("sink_name") == "sample_size"
+                ):
+                    links_to_remove.append(link)
+
+            # Set default
+            input_default["sample_size"] = 1
+            node["input_default"] = input_default
+            logger.debug(f"Fixed DataSamplingBlock {node_id} sample_size to 1")
+
+    if links_to_remove:
+        agent["links"] = [link for link in links if link not in links_to_remove]
+
+    return agent
+
+
+def fix_node_x_coordinates(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix node x-coordinates to ensure 800+ unit spacing between linked nodes."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+    node_lookup = {n.get("id"): n for n in nodes}
+
+    for link in links:
+        source_id = link.get("source_id")
+        sink_id = link.get("sink_id")
+
+        source_node = node_lookup.get(source_id)
+        sink_node = node_lookup.get(sink_id)
+
+        if not source_node or not sink_node:
+            continue
+
+        source_pos = source_node.get("metadata", {}).get("position", {})
+        sink_pos = sink_node.get("metadata", {}).get("position", {})
+
+        source_x = source_pos.get("x", 0)
+        sink_x = sink_pos.get("x", 0)
+
+        if abs(sink_x - source_x) < 800:
+            new_x = source_x + 800
+            if "metadata" not in sink_node:
+                sink_node["metadata"] = {}
+            if "position" not in sink_node["metadata"]:
+                sink_node["metadata"]["position"] = {}
+            sink_node["metadata"]["position"]["x"] = new_x
+            logger.debug(f"Fixed node {sink_id} x: {sink_x} -> {new_x}")
+
+    return agent
+
+
+def fix_getcurrentdate_offset(agent: dict[str, Any]) -> dict[str, Any]:
+    """Fix GetCurrentDateBlock offset to ensure it's positive."""
+    for node in agent.get("nodes", []):
+        if node.get("block_id") == GET_CURRENT_DATE_BLOCK_ID:
+            input_default = node.get("input_default", {})
+            if "offset" in input_default:
+                offset = input_default["offset"]
+                if isinstance(offset, (int, float)) and offset < 0:
+                    input_default["offset"] = abs(offset)
+                    logger.debug(f"Fixed offset: {offset} -> {abs(offset)}")
+
+    return agent
+
+
+def fix_ai_model_parameter(
+    agent: dict[str, Any],
+    blocks_info: list[dict[str, Any]],
+    default_model: str = "gpt-4o",
+) -> dict[str, Any]:
+    """Add default model parameter to AI blocks if missing."""
+    block_map = {b.get("id"): b for b in blocks_info}
+
+    for node in agent.get("nodes", []):
+        block_id = node.get("block_id")
+        block = block_map.get(block_id)
+
+        if not block:
+            continue
+
+        # Check if block has AI category
+        categories = block.get("categories", [])
+        is_ai_block = any(
+            cat.get("category") == "AI" for cat in categories if isinstance(cat, dict)
+        )
+
+        if is_ai_block:
+            input_default = node.get("input_default", {})
+            if "model" not in input_default:
+                input_default["model"] = default_model
+                node["input_default"] = input_default
+                logger.debug(
+                    f"Added model '{default_model}' to AI block {node.get('id')}"
+                )
+
+    return agent
+
+
+def fix_link_static_properties(
+    agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+) -> dict[str, Any]:
+    """Fix is_static property based on source block's staticOutput."""
+    block_map = {b.get("id"): b for b in blocks_info}
+    node_lookup = {n.get("id"): n for n in agent.get("nodes", [])}
+
+    for link in agent.get("links", []):
+        source_node = node_lookup.get(link.get("source_id"))
+        if not source_node:
+            continue
+
+        source_block = block_map.get(source_node.get("block_id"))
+        if not source_block:
+            continue
+
+        static_output = source_block.get("staticOutput", False)
+        if link.get("is_static") != static_output:
+            link["is_static"] = static_output
+            logger.debug(f"Fixed link {link.get('id')} is_static to {static_output}")
+
+    return agent
+
+
+def fix_data_type_mismatch(
+    agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+) -> dict[str, Any]:
+    """Fix data type mismatches by inserting UniversalTypeConverterBlock."""
+    nodes = agent.get("nodes", [])
+    links = agent.get("links", [])
+    block_map = {b.get("id"): b for b in blocks_info}
+    node_lookup = {n.get("id"): n for n in nodes}
+
+    def get_property_type(schema: dict, name: str) -> str | None:
+        if "_#_" in name:
+            parent, child = name.split("_#_", 1)
+            parent_schema = schema.get(parent, {})
+            if "properties" in parent_schema:
+                return parent_schema["properties"].get(child, {}).get("type")
+            return None
+        return schema.get(name, {}).get("type")
+
+    def are_types_compatible(src: str, sink: str) -> bool:
+        if {src, sink} <= {"integer", "number"}:
+            return True
+        return src == sink
+
+    type_mapping = {
+        "string": "string",
+        "text": "string",
+        "integer": "number",
+        "number": "number",
+        "float": "number",
+        "boolean": "boolean",
+        "bool": "boolean",
+        "array": "list",
+        "list": "list",
+        "object": "dictionary",
+        "dict": "dictionary",
+        "dictionary": "dictionary",
+    }
+
+    new_links = []
+    nodes_to_add = []
+
+    for link in links:
+        source_node = node_lookup.get(link.get("source_id"))
+        sink_node = node_lookup.get(link.get("sink_id"))
+
+        if not source_node or not sink_node:
+            new_links.append(link)
+            continue
+
+        source_block = block_map.get(source_node.get("block_id"))
+        sink_block = block_map.get(sink_node.get("block_id"))
+
+        if not source_block or not sink_block:
+            new_links.append(link)
+            continue
+
+        source_outputs = source_block.get("outputSchema", {}).get("properties", {})
+        sink_inputs = sink_block.get("inputSchema", {}).get("properties", {})
+
+        source_type = get_property_type(source_outputs, link.get("source_name", ""))
+        sink_type = get_property_type(sink_inputs, link.get("sink_name", ""))
+
+        if (
+            source_type
+            and sink_type
+            and not are_types_compatible(source_type, sink_type)
+        ):
+            # Insert type converter
+            converter_id = str(uuid.uuid4())
+            target_type = type_mapping.get(sink_type, sink_type)
+
+            converter_node = {
+                "id": converter_id,
+                "block_id": UNIVERSAL_TYPE_CONVERTER_BLOCK_ID,
+                "input_default": {"type": target_type},
+                "metadata": {"position": {"x": 0, "y": 100}},
+            }
+            nodes_to_add.append(converter_node)
+
+            # source -> converter
+            new_links.append(
+                {
+                    "id": str(uuid.uuid4()),
+                    "source_id": link["source_id"],
+                    "source_name": link["source_name"],
+                    "sink_id": converter_id,
+                    "sink_name": "value",
+                    "is_static": False,
+                }
+            )
+
+            # converter -> sink
+            new_links.append(
+                {
+                    "id": str(uuid.uuid4()),
+                    "source_id": converter_id,
+                    "source_name": "value",
+                    "sink_id": link["sink_id"],
+                    "sink_name": link["sink_name"],
+                    "is_static": False,
+                }
+            )
+
+            logger.debug(f"Inserted type converter: {source_type} -> {target_type}")
+        else:
+            new_links.append(link)
+
+    if nodes_to_add:
+        agent["nodes"] = nodes + nodes_to_add
+        agent["links"] = new_links
+
+    return agent
+
+
+def apply_all_fixes(
+    agent: dict[str, Any], blocks_info: list[dict[str, Any]] | None = None
+) -> dict[str, Any]:
+    """Apply all fixes to an agent JSON.
+
+    Args:
+        agent: Agent JSON dict
+        blocks_info: Optional list of block info dicts for advanced fixes
+
+    Returns:
+        Fixed agent JSON
+    """
+    # Basic fixes (no block info needed)
+    agent = fix_agent_ids(agent)
+    agent = fix_double_curly_braces(agent)
+    agent = fix_storevalue_before_condition(agent)
+    agent = fix_addtolist_blocks(agent)
+    agent = fix_addtodictionary_blocks(agent)
+    agent = fix_code_execution_output(agent)
+    agent = fix_data_sampling_sample_size(agent)
+    agent = fix_node_x_coordinates(agent)
+    agent = fix_getcurrentdate_offset(agent)
+
+    # Advanced fixes (require block info)
+    if blocks_info is None:
+        blocks_info = get_blocks_info()
+
+    agent = fix_ai_model_parameter(agent, blocks_info)
+    agent = fix_link_static_properties(agent, blocks_info)
+    agent = fix_data_type_mismatch(agent, blocks_info)
+
+    return agent

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

@@ -0,0 +1,225 @@
+"""Prompt templates for agent generation."""
+
+DECOMPOSITION_PROMPT = """
+You are an expert AutoGPT Workflow Decomposer. Your task is to analyze a user's high-level goal and break it down into a clear, step-by-step plan using the available blocks.
+
+Each step should represent a distinct, automatable action suitable for execution by an AI automation system.
+
+---
+
+FIRST: Analyze the user's goal and determine:
+1) Design-time configuration (fixed settings that won't change per run)
+2) Runtime inputs (values the agent's end-user will provide each time it runs)
+
+For anything that can vary per run (email addresses, names, dates, search terms, etc.):
+- DO NOT ask for the actual value
+- Instead, define it as an Agent Input with a clear name, type, and description
+
+Only ask clarifying questions about design-time config that affects how you build the workflow:
+- Which external service to use (e.g., "Gmail vs Outlook", "Notion vs Google Docs")
+- Required formats or structures (e.g., "CSV, JSON, or PDF output?")
+- Business rules that must be hard-coded
+
+IMPORTANT CLARIFICATIONS POLICY:
+- Ask no more than five essential questions
+- Do not ask for concrete values that can be provided at runtime as Agent Inputs
+- Do not ask for API keys or credentials; the platform handles those directly
+- If there is enough information to infer reasonable defaults, prefer to propose defaults
+
+---
+
+GUIDELINES:
+1. List each step as a numbered item
+2. Describe the action clearly and specify inputs/outputs
+3. Ensure steps are in logical, sequential order
+4. Mention block names naturally (e.g., "Use GetWeatherByLocationBlock to...")
+5. Help the user reach their goal efficiently
+
+---
+
+RULES:
+1. OUTPUT FORMAT: Only output either clarifying questions OR step-by-step instructions, not both
+2. USE ONLY THE BLOCKS PROVIDED
+3. ALL required_input fields must be provided
+4. Data types of linked properties must match
+5. Write expert-level prompts for AI-related blocks
+
+---
+
+CRITICAL BLOCK RESTRICTIONS:
+1. AddToListBlock: Outputs updated list EVERY addition, not after all additions
+2. SendEmailBlock: Draft the email for user review; set SMTP config based on email type
+3. ConditionBlock: value2 is reference, value1 is contrast
+4. CodeExecutionBlock: DO NOT USE - use AI blocks instead
+5. ReadCsvBlock: Only use the 'rows' output, not 'row'
+
+---
+
+OUTPUT FORMAT:
+
+If more information is needed:
+```json
+{{
+  "type": "clarifying_questions",
+  "questions": [
+    {{
+      "question": "Which email provider should be used? (Gmail, Outlook, custom SMTP)",
+      "keyword": "email_provider",
+      "example": "Gmail"
+    }}
+  ]
+}}
+```
+
+If ready to proceed:
+```json
+{{
+  "type": "instructions",
+  "steps": [
+    {{
+      "step_number": 1,
+      "block_name": "AgentShortTextInputBlock",
+      "description": "Get the URL of the content to analyze.",
+      "inputs": [{{"name": "name", "value": "URL"}}],
+      "outputs": [{{"name": "result", "description": "The URL entered by user"}}]
+    }}
+  ]
+}}
+```
+
+---
+
+AVAILABLE BLOCKS:
+{block_summaries}
+"""
+
+GENERATION_PROMPT = """
+You are an expert AI workflow builder. Generate a valid agent JSON from the given instructions.
+
+---
+
+NODES:
+Each node must include:
+- `id`: Unique UUID v4 (e.g. `a8f5b1e2-c3d4-4e5f-8a9b-0c1d2e3f4a5b`)
+- `block_id`: The block identifier (must match an Allowed Block)
+- `input_default`: Dict of inputs (can be empty if no static inputs needed)
+- `metadata`: Must contain:
+  - `position`: {{"x": number, "y": number}} - adjacent nodes should differ by 800+ in X
+  - `customized_name`: Clear name describing this block's purpose in the workflow
+
+---
+
+LINKS:
+Each link connects a source node's output to a sink node's input:
+- `id`: MUST be UUID v4 (NOT "link-1", "link-2", etc.)
+- `source_id`: ID of the source node
+- `source_name`: Output field name from the source block
+- `sink_id`: ID of the sink node
+- `sink_name`: Input field name on the sink block
+- `is_static`: true only if source block has static_output: true
+
+CRITICAL: All IDs must be valid UUID v4 format!
+
+---
+
+AGENT (GRAPH):
+Wrap nodes and links in:
+- `id`: UUID of the agent
+- `name`: Short, generic name (avoid specific company names, URLs)
+- `description`: Short, generic description
+- `nodes`: List of all nodes
+- `links`: List of all links
+- `version`: 1
+- `is_active`: true
+
+---
+
+TIPS:
+- All required_input fields must be provided via input_default or a valid link
+- Ensure consistent source_id and sink_id references
+- Avoid dangling links
+- Input/output pins must match block schemas
+- Do not invent unknown block_ids
+
+---
+
+ALLOWED BLOCKS:
+{block_summaries}
+
+---
+
+Generate the complete agent JSON. Output ONLY valid JSON, no explanation.
+"""
+
+PATCH_PROMPT = """
+You are an expert at modifying AutoGPT agent workflows. Given the current agent and a modification request, generate a JSON patch to update the agent.
+
+CURRENT AGENT:
+{current_agent}
+
+AVAILABLE BLOCKS:
+{block_summaries}
+
+---
+
+PATCH FORMAT:
+Return a JSON object with the following structure:
+
+```json
+{{
+  "type": "patch",
+  "intent": "Brief description of what the patch does",
+  "patches": [
+    {{
+      "type": "modify",
+      "node_id": "uuid-of-node-to-modify",
+      "changes": {{
+        "input_default": {{"field": "new_value"}},
+        "metadata": {{"customized_name": "New Name"}}
+      }}
+    }},
+    {{
+      "type": "add",
+      "new_nodes": [
+        {{
+          "id": "new-uuid",
+          "block_id": "block-uuid",
+          "input_default": {{}},
+          "metadata": {{"position": {{"x": 0, "y": 0}}, "customized_name": "Name"}}
+        }}
+      ],
+      "new_links": [
+        {{
+          "id": "link-uuid",
+          "source_id": "source-node-id",
+          "source_name": "output_field",
+          "sink_id": "sink-node-id",
+          "sink_name": "input_field"
+        }}
+      ]
+    }},
+    {{
+      "type": "remove",
+      "node_ids": ["uuid-of-node-to-remove"],
+      "link_ids": ["uuid-of-link-to-remove"]
+    }}
+  ]
+}}
+```
+
+If you need more information, return:
+```json
+{{
+  "type": "clarifying_questions",
+  "questions": [
+    {{
+      "question": "What specific change do you want?",
+      "keyword": "change_type",
+      "example": "Add error handling"
+    }}
+  ]
+}}
+```
+
+Generate the minimal patch needed. Output ONLY valid JSON.
+"""

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

@@ -0,0 +1,213 @@
+"""Utilities for agent generation."""
+
+import json
+import re
+from typing import Any
+
+from backend.data.block import get_blocks
+
+# UUID validation regex
+UUID_REGEX = re.compile(
+    r"^[a-f0-9]{8}-[a-f0-9]{4}-4[a-f0-9]{3}-[89ab][a-f0-9]{3}-[a-f0-9]{12}$"
+)
+
+# Block IDs for various fixes
+STORE_VALUE_BLOCK_ID = "1ff065e9-88e8-4358-9d82-8dc91f622ba9"
+CONDITION_BLOCK_ID = "715696a0-e1da-45c8-b209-c2fa9c3b0be6"
+ADDTOLIST_BLOCK_ID = "aeb08fc1-2fc1-4141-bc8e-f758f183a822"
+ADDTODICTIONARY_BLOCK_ID = "31d1064e-7446-4693-a7d4-65e5ca1180d1"
+CREATELIST_BLOCK_ID = "a912d5c7-6e00-4542-b2a9-8034136930e4"
+CREATEDICT_BLOCK_ID = "b924ddf4-de4f-4b56-9a85-358930dcbc91"
+CODE_EXECUTION_BLOCK_ID = "0b02b072-abe7-11ef-8372-fb5d162dd712"
+DATA_SAMPLING_BLOCK_ID = "4a448883-71fa-49cf-91cf-70d793bd7d87"
+UNIVERSAL_TYPE_CONVERTER_BLOCK_ID = "95d1b990-ce13-4d88-9737-ba5c2070c97b"
+GET_CURRENT_DATE_BLOCK_ID = "b29c1b50-5d0e-4d9f-8f9d-1b0e6fcbf0b1"
+
+DOUBLE_CURLY_BRACES_BLOCK_IDS = [
+    "44f6c8ad-d75c-4ae1-8209-aad1c0326928",  # FillTextTemplateBlock
+    "6ab085e2-20b3-4055-bc3e-08036e01eca6",
+    "90f8c45e-e983-4644-aa0b-b4ebe2f531bc",
+    "363ae599-353e-4804-937e-b2ee3cef3da4",  # AgentOutputBlock
+    "3b191d9f-356f-482d-8238-ba04b6d18381",
+    "db7d8f02-2f44-4c55-ab7a-eae0941f0c30",
+    "3a7c4b8d-6e2f-4a5d-b9c1-f8d23c5a9b0e",
+    "ed1ae7a0-b770-4089-b520-1f0005fad19a",
+    "a892b8d9-3e4e-4e9c-9c1e-75f8efcf1bfa",
+    "b29c1b50-5d0e-4d9f-8f9d-1b0e6fcbf0b1",
+    "716a67b3-6760-42e7-86dc-18645c6e00fc",
+    "530cf046-2ce0-4854-ae2c-659db17c7a46",
+    "ed55ac19-356e-4243-a6cb-bc599e9b716f",
+    "1f292d4a-41a4-4977-9684-7c8d560b9f91",  # LLM blocks
+    "32a87eab-381e-4dd4-bdb8-4c47151be35a",
+]
+
+
+def is_valid_uuid(value: str) -> bool:
+    """Check if a string is a valid UUID v4."""
+    return isinstance(value, str) and UUID_REGEX.match(value) is not None
+
+
+def _compact_schema(schema: dict) -> dict[str, str]:
+    """Extract compact type info from a JSON schema properties dict.
+
+    Returns a dict of {field_name: type_string} for essential info only.
+    """
+    props = schema.get("properties", {})
+    result = {}
+
+    for name, prop in props.items():
+        # Skip internal/complex fields
+        if name.startswith("_"):
+            continue
+
+        # Get type string
+        type_str = prop.get("type", "any")
+
+        # Handle anyOf/oneOf (optional types)
+        if "anyOf" in prop:
+            types = [t.get("type", "?") for t in prop["anyOf"] if t.get("type")]
+            type_str = "|".join(types) if types else "any"
+        elif "allOf" in prop:
+            type_str = "object"
+
+        # Add array item type if present
+        if type_str == "array" and "items" in prop:
+            items = prop["items"]
+            if isinstance(items, dict):
+                item_type = items.get("type", "any")
+                type_str = f"array[{item_type}]"
+
+        result[name] = type_str
+
+    return result
+
+
+def get_block_summaries(include_schemas: bool = True) -> str:
+    """Generate compact block summaries for prompts.
+
+    Args:
+        include_schemas: Whether to include input/output type info
+
+    Returns:
+        Formatted string of block summaries (compact format)
+    """
+    blocks = get_blocks()
+    summaries = []
+
+    for block_id, block_cls in blocks.items():
+        block = block_cls()
+        name = block.name
+        desc = getattr(block, "description", "") or ""
+
+        # Truncate description
+        if len(desc) > 150:
+            desc = desc[:147] + "..."
+
+        if not include_schemas:
+            summaries.append(f"- {name} (id: {block_id}): {desc}")
+        else:
+            # Compact format with type info only
+            inputs = {}
+            outputs = {}
+            required = []
+
+            if hasattr(block, "input_schema"):
+                try:
+                    schema = block.input_schema.jsonschema()
+                    inputs = _compact_schema(schema)
+                    required = schema.get("required", [])
+                except Exception:
+                    pass
+
+            if hasattr(block, "output_schema"):
+                try:
+                    schema = block.output_schema.jsonschema()
+                    outputs = _compact_schema(schema)
+                except Exception:
+                    pass
+
+            # Build compact line format
+            # Format: NAME (id): desc | in: {field:type, ...} [required] | out: {field:type}
+            in_str = ", ".join(f"{k}:{v}" for k, v in inputs.items())
+            out_str = ", ".join(f"{k}:{v}" for k, v in outputs.items())
+            req_str = f" req=[{','.join(required)}]" if required else ""
+
+            static = " [static]" if getattr(block, "static_output", False) else ""
+
+            line = f"- {name} (id: {block_id}): {desc}"
+            if in_str:
+                line += f"\n  in: {{{in_str}}}{req_str}"
+            if out_str:
+                line += f"\n  out: {{{out_str}}}{static}"
+
+            summaries.append(line)
+
+    return "\n".join(summaries)
+
+
+def get_blocks_info() -> list[dict[str, Any]]:
+    """Get block information with schemas for validation and fixing."""
+    blocks = get_blocks()
+    blocks_info = []
+    for block_id, block_cls in blocks.items():
+        block = block_cls()
+        blocks_info.append(
+            {
+                "id": block_id,
+                "name": block.name,
+                "description": getattr(block, "description", ""),
+                "categories": getattr(block, "categories", []),
+                "staticOutput": getattr(block, "static_output", False),
+                "inputSchema": (
+                    block.input_schema.jsonschema()
+                    if hasattr(block, "input_schema")
+                    else {}
+                ),
+                "outputSchema": (
+                    block.output_schema.jsonschema()
+                    if hasattr(block, "output_schema")
+                    else {}
+                ),
+            }
+        )
+    return blocks_info
+
+
+def parse_json_from_llm(text: str) -> dict[str, Any] | None:
+    """Extract JSON from LLM response (handles markdown code blocks)."""
+    if not text:
+        return None
+
+    # Try fenced code block
+    match = re.search(r"```(?:json)?\s*([\s\S]*?)```", text, re.IGNORECASE)
+    if match:
+        try:
+            return json.loads(match.group(1).strip())
+        except json.JSONDecodeError:
+            pass
+
+    # Try raw text
+    try:
+        return json.loads(text.strip())
+    except json.JSONDecodeError:
+        pass
+
+    # Try finding {...} span
+    start = text.find("{")
+    end = text.rfind("}")
+    if start != -1 and end > start:
+        try:
+            return json.loads(text[start : end + 1])
+        except json.JSONDecodeError:
+            pass
+
+    # Try finding [...] span
+    start = text.find("[")
+    end = text.rfind("]")
+    if start != -1 and end > start:
+        try:
+            return json.loads(text[start : end + 1])
+        except json.JSONDecodeError:
+            pass
+
+    return None

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

@@ -0,0 +1,279 @@
+"""Agent validator - Validates agent structure and connections."""
+
+import logging
+import re
+from typing import Any
+
+from .utils import get_blocks_info
+
+logger = logging.getLogger(__name__)
+
+
+class AgentValidator:
+    """Validator for AutoGPT agents with detailed error reporting."""
+
+    def __init__(self):
+        self.errors: list[str] = []
+
+    def add_error(self, error: str) -> None:
+        """Add an error message."""
+        self.errors.append(error)
+
+    def validate_block_existence(
+        self, agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+    ) -> bool:
+        """Validate all block IDs exist in the blocks library."""
+        valid = True
+        valid_block_ids = {b.get("id") for b in blocks_info if b.get("id")}
+
+        for node in agent.get("nodes", []):
+            block_id = node.get("block_id")
+            node_id = node.get("id")
+
+            if not block_id:
+                self.add_error(f"Node '{node_id}' is missing 'block_id' field.")
+                valid = False
+                continue
+
+            if block_id not in valid_block_ids:
+                self.add_error(
+                    f"Node '{node_id}' references block_id '{block_id}' which does not exist."
+                )
+                valid = False
+
+        return valid
+
+    def validate_link_node_references(self, agent: dict[str, Any]) -> bool:
+        """Validate all node IDs referenced in links exist."""
+        valid = True
+        valid_node_ids = {n.get("id") for n in agent.get("nodes", []) if n.get("id")}
+
+        for link in agent.get("links", []):
+            link_id = link.get("id", "Unknown")
+            source_id = link.get("source_id")
+            sink_id = link.get("sink_id")
+
+            if not source_id:
+                self.add_error(f"Link '{link_id}' is missing 'source_id'.")
+                valid = False
+            elif source_id not in valid_node_ids:
+                self.add_error(
+                    f"Link '{link_id}' references non-existent source_id '{source_id}'."
+                )
+                valid = False
+
+            if not sink_id:
+                self.add_error(f"Link '{link_id}' is missing 'sink_id'.")
+                valid = False
+            elif sink_id not in valid_node_ids:
+                self.add_error(
+                    f"Link '{link_id}' references non-existent sink_id '{sink_id}'."
+                )
+                valid = False
+
+        return valid
+
+    def validate_required_inputs(
+        self, agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+    ) -> bool:
+        """Validate required inputs are provided."""
+        valid = True
+        block_map = {b.get("id"): b for b in blocks_info}
+
+        for node in agent.get("nodes", []):
+            block_id = node.get("block_id")
+            block = block_map.get(block_id)
+
+            if not block:
+                continue
+
+            required_inputs = block.get("inputSchema", {}).get("required", [])
+            input_defaults = node.get("input_default", {})
+            node_id = node.get("id")
+
+            # Get linked inputs
+            linked_inputs = {
+                link["sink_name"]
+                for link in agent.get("links", [])
+                if link.get("sink_id") == node_id
+            }
+
+            for req_input in required_inputs:
+                if (
+                    req_input not in input_defaults
+                    and req_input not in linked_inputs
+                    and req_input != "credentials"
+                ):
+                    block_name = block.get("name", "Unknown Block")
+                    self.add_error(
+                        f"Node '{node_id}' ({block_name}) is missing required input '{req_input}'."
+                    )
+                    valid = False
+
+        return valid
+
+    def validate_data_type_compatibility(
+        self, agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+    ) -> bool:
+        """Validate linked data types are compatible."""
+        valid = True
+        block_map = {b.get("id"): b for b in blocks_info}
+        node_lookup = {n.get("id"): n for n in agent.get("nodes", [])}
+
+        def get_type(schema: dict, name: str) -> str | None:
+            if "_#_" in name:
+                parent, child = name.split("_#_", 1)
+                parent_schema = schema.get(parent, {})
+                if "properties" in parent_schema:
+                    return parent_schema["properties"].get(child, {}).get("type")
+                return None
+            return schema.get(name, {}).get("type")
+
+        def are_compatible(src: str, sink: str) -> bool:
+            if {src, sink} <= {"integer", "number"}:
+                return True
+            return src == sink
+
+        for link in agent.get("links", []):
+            source_node = node_lookup.get(link.get("source_id"))
+            sink_node = node_lookup.get(link.get("sink_id"))
+
+            if not source_node or not sink_node:
+                continue
+
+            source_block = block_map.get(source_node.get("block_id"))
+            sink_block = block_map.get(sink_node.get("block_id"))
+
+            if not source_block or not sink_block:
+                continue
+
+            source_outputs = source_block.get("outputSchema", {}).get("properties", {})
+            sink_inputs = sink_block.get("inputSchema", {}).get("properties", {})
+
+            source_type = get_type(source_outputs, link.get("source_name", ""))
+            sink_type = get_type(sink_inputs, link.get("sink_name", ""))
+
+            if source_type and sink_type and not are_compatible(source_type, sink_type):
+                self.add_error(
+                    f"Type mismatch: {source_block.get('name')} output '{link['source_name']}' "
+                    f"({source_type}) -> {sink_block.get('name')} input '{link['sink_name']}' ({sink_type})."
+                )
+                valid = False
+
+        return valid
+
+    def validate_nested_sink_links(
+        self, agent: dict[str, Any], blocks_info: list[dict[str, Any]]
+    ) -> bool:
+        """Validate nested sink links (with _#_ notation)."""
+        valid = True
+        block_map = {b.get("id"): b for b in blocks_info}
+        node_lookup = {n.get("id"): n for n in agent.get("nodes", [])}
+
+        for link in agent.get("links", []):
+            sink_name = link.get("sink_name", "")
+
+            if "_#_" in sink_name:
+                parent, child = sink_name.split("_#_", 1)
+
+                sink_node = node_lookup.get(link.get("sink_id"))
+                if not sink_node:
+                    continue
+
+                block = block_map.get(sink_node.get("block_id"))
+                if not block:
+                    continue
+
+                input_props = block.get("inputSchema", {}).get("properties", {})
+                parent_schema = input_props.get(parent)
+
+                if not parent_schema:
+                    self.add_error(
+                        f"Invalid nested link '{sink_name}': parent '{parent}' not found."
+                    )
+                    valid = False
+                    continue
+
+                if not parent_schema.get("additionalProperties"):
+                    if not (
+                        isinstance(parent_schema, dict)
+                        and "properties" in parent_schema
+                        and child in parent_schema.get("properties", {})
+                    ):
+                        self.add_error(
+                            f"Invalid nested link '{sink_name}': child '{child}' not found in '{parent}'."
+                        )
+                        valid = False
+
+        return valid
+
+    def validate_prompt_spaces(self, agent: dict[str, Any]) -> bool:
+        """Validate prompts don't have spaces in template variables."""
+        valid = True
+
+        for node in agent.get("nodes", []):
+            input_default = node.get("input_default", {})
+            prompt = input_default.get("prompt", "")
+
+            if not isinstance(prompt, str):
+                continue
+
+            # Find {{...}} with spaces
+            matches = re.finditer(r"\{\{([^}]+)\}\}", prompt)
+            for match in matches:
+                content = match.group(1)
+                if " " in content:
+                    self.add_error(
+                        f"Node '{node.get('id')}' has spaces in template variable: "
+                        f"'{{{{{content}}}}}' should be '{{{{{content.replace(' ', '_')}}}}}'."
+                    )
+                    valid = False
+
+        return valid
+
+    def validate(
+        self, agent: dict[str, Any], blocks_info: list[dict[str, Any]] | None = None
+    ) -> tuple[bool, str | None]:
+        """Run all validations.
+
+        Returns:
+            Tuple of (is_valid, error_message)
+        """
+        self.errors = []
+
+        if blocks_info is None:
+            blocks_info = get_blocks_info()
+
+        checks = [
+            self.validate_block_existence(agent, blocks_info),
+            self.validate_link_node_references(agent),
+            self.validate_required_inputs(agent, blocks_info),
+            self.validate_data_type_compatibility(agent, blocks_info),
+            self.validate_nested_sink_links(agent, blocks_info),
+            self.validate_prompt_spaces(agent),
+        ]
+
+        all_passed = all(checks)
+
+        if all_passed:
+            logger.info("Agent validation successful")
+            return True, None
+
+        error_message = "Agent validation failed:\n"
+        for i, error in enumerate(self.errors, 1):
+            error_message += f"{i}. {error}\n"
+
+        logger.warning(f"Agent validation failed with {len(self.errors)} errors")
+        return False, error_message
+
+
+def validate_agent(
+    agent: dict[str, Any], blocks_info: list[dict[str, Any]] | None = None
+) -> tuple[bool, str | None]:
+    """Convenience function to validate an agent.
+
+    Returns:
+        Tuple of (is_valid, error_message)
+    """
+    validator = AgentValidator()
+    return validator.validate(agent, blocks_info)

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

@@ -0,0 +1,448 @@
+"""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 langfuse import observe
+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 "view_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,
+        )
+
+    @observe(as_type="tool", name="view_agent_output")
+    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

@@ -0,0 +1,151 @@
+"""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/base.py

@@ -6,7 +6,7 @@ from typing import Any
 from openai.types.chat import ChatCompletionToolParam
 
 from backend.api.features.chat.model import ChatSession
-from backend.api.features.chat.response_model import StreamToolExecutionResult
+from backend.api.features.chat.response_model import StreamToolOutputAvailable
 
 from .models import ErrorResponse, NeedLoginResponse, ToolResponseBase
 
@@ -53,7 +53,7 @@ class BaseTool:
         session: ChatSession,
         tool_call_id: str,
         **kwargs,
-    ) -> StreamToolExecutionResult:
+    ) -> StreamToolOutputAvailable:
         """Execute the tool with authentication check.
 
         Args:
@@ -69,10 +69,10 @@ class BaseTool:
             logger.error(
                 f"Attempted tool call for {self.name} but user not authenticated"
             )
-            return StreamToolExecutionResult(
+            return StreamToolOutputAvailable(
-                tool_id=tool_call_id,
+                toolCallId=tool_call_id,
-                tool_name=self.name,
+                toolName=self.name,
-                result=NeedLoginResponse(
+                output=NeedLoginResponse(
                     message=f"Please sign in to use {self.name}",
                     session_id=session.session_id,
                 ).model_dump_json(),
@@ -81,17 +81,17 @@ class BaseTool:
 
         try:
             result = await self._execute(user_id, session, **kwargs)
-            return StreamToolExecutionResult(
+            return StreamToolOutputAvailable(
-                tool_id=tool_call_id,
+                toolCallId=tool_call_id,
-                tool_name=self.name,
+                toolName=self.name,
-                result=result.model_dump_json(),
+                output=result.model_dump_json(),
             )
         except Exception as e:
             logger.error(f"Error in {self.name}: {e}", exc_info=True)
-            return StreamToolExecutionResult(
+            return StreamToolOutputAvailable(
-                tool_id=tool_call_id,
+                toolCallId=tool_call_id,
-                tool_name=self.name,
+                toolName=self.name,
-                result=ErrorResponse(
+                output=ErrorResponse(
                     message=f"An error occurred while executing {self.name}",
                     error=str(e),
                     session_id=session.session_id,

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

@@ -0,0 +1,282 @@
+"""CreateAgentTool - Creates agents from natural language descriptions."""
+
+import logging
+from typing import Any
+
+from langfuse import observe
+
+from backend.api.features.chat.model import ChatSession
+
+from .agent_generator import (
+    apply_all_fixes,
+    decompose_goal,
+    generate_agent,
+    get_blocks_info,
+    save_agent_to_library,
+    validate_agent,
+)
+from .base import BaseTool
+from .models import (
+    AgentPreviewResponse,
+    AgentSavedResponse,
+    ClarificationNeededResponse,
+    ClarifyingQuestion,
+    ErrorResponse,
+    ToolResponseBase,
+)
+
+logger = logging.getLogger(__name__)
+
+# Maximum retries for agent generation with validation feedback
+MAX_GENERATION_RETRIES = 2
+
+
+class CreateAgentTool(BaseTool):
+    """Tool for creating agents from natural language descriptions."""
+
+    @property
+    def name(self) -> str:
+        return "create_agent"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Create a new agent workflow from a natural language description. "
+            "First generates a preview, then saves to library if save=true."
+        )
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "description": {
+                    "type": "string",
+                    "description": (
+                        "Natural language description of what the agent should do. "
+                        "Be specific about inputs, outputs, and the workflow steps."
+                    ),
+                },
+                "context": {
+                    "type": "string",
+                    "description": (
+                        "Additional context or answers to previous clarifying questions. "
+                        "Include any preferences or constraints mentioned by the user."
+                    ),
+                },
+                "save": {
+                    "type": "boolean",
+                    "description": (
+                        "Whether to save the agent to the user's library. "
+                        "Default is true. Set to false for preview only."
+                    ),
+                    "default": True,
+                },
+            },
+            "required": ["description"],
+        }
+
+    @observe(as_type="tool", name="create_agent")
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        """Execute the create_agent tool.
+
+        Flow:
+        1. Decompose the description into steps (may return clarifying questions)
+        2. Generate agent JSON from the steps
+        3. Apply fixes to correct common LLM errors
+        4. Preview or save based on the save parameter
+        """
+        description = kwargs.get("description", "").strip()
+        context = kwargs.get("context", "")
+        save = kwargs.get("save", True)
+        session_id = session.session_id if session else None
+
+        if not description:
+            return ErrorResponse(
+                message="Please provide a description of what the agent should do.",
+                error="Missing description parameter",
+                session_id=session_id,
+            )
+
+        # Step 1: Decompose goal into steps
+        try:
+            decomposition_result = await decompose_goal(description, context)
+        except ValueError as e:
+            # Handle missing API key or configuration errors
+            return ErrorResponse(
+                message=f"Agent generation is not configured: {str(e)}",
+                error="configuration_error",
+                session_id=session_id,
+            )
+
+        if decomposition_result is None:
+            return ErrorResponse(
+                message="Failed to analyze the goal. Please try rephrasing.",
+                error="Decomposition failed",
+                session_id=session_id,
+            )
+
+        # Check if LLM returned clarifying questions
+        if decomposition_result.get("type") == "clarifying_questions":
+            questions = decomposition_result.get("questions", [])
+            return ClarificationNeededResponse(
+                message=(
+                    "I need some more information to create this agent. "
+                    "Please answer the following questions:"
+                ),
+                questions=[
+                    ClarifyingQuestion(
+                        question=q.get("question", ""),
+                        keyword=q.get("keyword", ""),
+                        example=q.get("example"),
+                    )
+                    for q in questions
+                ],
+                session_id=session_id,
+            )
+
+        # Check for unachievable/vague goals
+        if decomposition_result.get("type") == "unachievable_goal":
+            suggested = decomposition_result.get("suggested_goal", "")
+            reason = decomposition_result.get("reason", "")
+            return ErrorResponse(
+                message=(
+                    f"This goal cannot be accomplished with the available blocks. "
+                    f"{reason} "
+                    f"Suggestion: {suggested}"
+                ),
+                error="unachievable_goal",
+                details={"suggested_goal": suggested, "reason": reason},
+                session_id=session_id,
+            )
+
+        if decomposition_result.get("type") == "vague_goal":
+            suggested = decomposition_result.get("suggested_goal", "")
+            return ErrorResponse(
+                message=(
+                    f"The goal is too vague to create a specific workflow. "
+                    f"Suggestion: {suggested}"
+                ),
+                error="vague_goal",
+                details={"suggested_goal": suggested},
+                session_id=session_id,
+            )
+
+        # Step 2: Generate agent JSON with retry on validation failure
+        blocks_info = get_blocks_info()
+        agent_json = None
+        validation_errors = None
+
+        for attempt in range(MAX_GENERATION_RETRIES + 1):
+            # Generate agent (include validation errors from previous attempt)
+            if attempt == 0:
+                agent_json = await generate_agent(decomposition_result)
+            else:
+                # Retry with validation error feedback
+                logger.info(
+                    f"Retry {attempt}/{MAX_GENERATION_RETRIES} with validation feedback"
+                )
+                retry_instructions = {
+                    **decomposition_result,
+                    "previous_errors": validation_errors,
+                    "retry_instructions": (
+                        "The previous generation had validation errors. "
+                        "Please fix these issues in the new generation:\n"
+                        f"{validation_errors}"
+                    ),
+                }
+                agent_json = await generate_agent(retry_instructions)
+
+            if agent_json is None:
+                if attempt == MAX_GENERATION_RETRIES:
+                    return ErrorResponse(
+                        message="Failed to generate the agent. Please try again.",
+                        error="Generation failed",
+                        session_id=session_id,
+                    )
+                continue
+
+            # Step 3: Apply fixes to correct common errors
+            agent_json = apply_all_fixes(agent_json, blocks_info)
+
+            # Step 4: Validate the agent
+            is_valid, validation_errors = validate_agent(agent_json, blocks_info)
+
+            if is_valid:
+                logger.info(f"Agent generated successfully on attempt {attempt + 1}")
+                break
+
+            logger.warning(
+                f"Validation failed on attempt {attempt + 1}: {validation_errors}"
+            )
+
+            if attempt == MAX_GENERATION_RETRIES:
+                # Return error with validation details
+                return ErrorResponse(
+                    message=(
+                        f"Generated agent has validation errors after {MAX_GENERATION_RETRIES + 1} attempts. "
+                        f"Please try rephrasing your request or simplify the workflow."
+                    ),
+                    error="validation_failed",
+                    details={"validation_errors": validation_errors},
+                    session_id=session_id,
+                )
+
+        agent_name = agent_json.get("name", "Generated Agent")
+        agent_description = agent_json.get("description", "")
+        node_count = len(agent_json.get("nodes", []))
+        link_count = len(agent_json.get("links", []))
+
+        # Step 4: Preview or save
+        if not save:
+            return AgentPreviewResponse(
+                message=(
+                    f"I've generated an agent called '{agent_name}' with {node_count} blocks. "
+                    f"Review it and call create_agent with save=true to save it to your library."
+                ),
+                agent_json=agent_json,
+                agent_name=agent_name,
+                description=agent_description,
+                node_count=node_count,
+                link_count=link_count,
+                session_id=session_id,
+            )
+
+        # Save to library
+        if not user_id:
+            return ErrorResponse(
+                message="You must be logged in to save agents.",
+                error="auth_required",
+                session_id=session_id,
+            )
+
+        try:
+            created_graph, library_agent = await save_agent_to_library(
+                agent_json, user_id
+            )
+
+            return AgentSavedResponse(
+                message=f"Agent '{created_graph.name}' has been saved to your library!",
+                agent_id=created_graph.id,
+                agent_name=created_graph.name,
+                library_agent_id=library_agent.id,
+                library_agent_link=f"/library/{library_agent.id}",
+                agent_page_link=f"/build?flowID={created_graph.id}",
+                session_id=session_id,
+            )
+        except Exception as e:
+            return ErrorResponse(
+                message=f"Failed to save the agent: {str(e)}",
+                error="save_failed",
+                details={"exception": str(e)},
+                session_id=session_id,
+            )

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

@@ -0,0 +1,297 @@
+"""EditAgentTool - Edits existing agents using natural language."""
+
+import logging
+from typing import Any
+
+from langfuse import observe
+
+from backend.api.features.chat.model import ChatSession
+
+from .agent_generator import (
+    apply_agent_patch,
+    apply_all_fixes,
+    generate_agent_patch,
+    get_agent_as_json,
+    get_blocks_info,
+    save_agent_to_library,
+    validate_agent,
+)
+from .base import BaseTool
+from .models import (
+    AgentPreviewResponse,
+    AgentSavedResponse,
+    ClarificationNeededResponse,
+    ClarifyingQuestion,
+    ErrorResponse,
+    ToolResponseBase,
+)
+
+logger = logging.getLogger(__name__)
+
+# Maximum retries for patch generation with validation feedback
+MAX_GENERATION_RETRIES = 2
+
+
+class EditAgentTool(BaseTool):
+    """Tool for editing existing agents using natural language."""
+
+    @property
+    def name(self) -> str:
+        return "edit_agent"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Edit an existing agent from the user's library using natural language. "
+            "Generates a patch to update the agent while preserving unchanged parts."
+        )
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "agent_id": {
+                    "type": "string",
+                    "description": (
+                        "The ID of the agent to edit. "
+                        "Can be a graph ID or library agent ID."
+                    ),
+                },
+                "changes": {
+                    "type": "string",
+                    "description": (
+                        "Natural language description of what changes to make. "
+                        "Be specific about what to add, remove, or modify."
+                    ),
+                },
+                "context": {
+                    "type": "string",
+                    "description": (
+                        "Additional context or answers to previous clarifying questions."
+                    ),
+                },
+                "save": {
+                    "type": "boolean",
+                    "description": (
+                        "Whether to save the changes. "
+                        "Default is true. Set to false for preview only."
+                    ),
+                    "default": True,
+                },
+            },
+            "required": ["agent_id", "changes"],
+        }
+
+    @observe(as_type="tool", name="edit_agent")
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        """Execute the edit_agent tool.
+
+        Flow:
+        1. Fetch the current agent
+        2. Generate a patch based on the requested changes
+        3. Apply the patch to create an updated agent
+        4. Preview or save based on the save parameter
+        """
+        agent_id = kwargs.get("agent_id", "").strip()
+        changes = kwargs.get("changes", "").strip()
+        context = kwargs.get("context", "")
+        save = kwargs.get("save", True)
+        session_id = session.session_id if session else None
+
+        if not agent_id:
+            return ErrorResponse(
+                message="Please provide the agent ID to edit.",
+                error="Missing agent_id parameter",
+                session_id=session_id,
+            )
+
+        if not changes:
+            return ErrorResponse(
+                message="Please describe what changes you want to make.",
+                error="Missing changes parameter",
+                session_id=session_id,
+            )
+
+        # Step 1: Fetch current agent
+        current_agent = await get_agent_as_json(agent_id, user_id)
+
+        if current_agent is None:
+            return ErrorResponse(
+                message=f"Could not find agent with ID '{agent_id}' in your library.",
+                error="agent_not_found",
+                session_id=session_id,
+            )
+
+        # Build the update request with context
+        update_request = changes
+        if context:
+            update_request = f"{changes}\n\nAdditional context:\n{context}"
+
+        # Step 2: Generate patch with retry on validation failure
+        blocks_info = get_blocks_info()
+        updated_agent = None
+        validation_errors = None
+        intent = "Applied requested changes"
+
+        for attempt in range(MAX_GENERATION_RETRIES + 1):
+            # Generate patch (include validation errors from previous attempt)
+            try:
+                if attempt == 0:
+                    patch_result = await generate_agent_patch(
+                        update_request, current_agent
+                    )
+                else:
+                    # Retry with validation error feedback
+                    logger.info(
+                        f"Retry {attempt}/{MAX_GENERATION_RETRIES} with validation feedback"
+                    )
+                    retry_request = (
+                        f"{update_request}\n\n"
+                        f"IMPORTANT: The previous edit had validation errors. "
+                        f"Please fix these issues:\n{validation_errors}"
+                    )
+                    patch_result = await generate_agent_patch(
+                        retry_request, current_agent
+                    )
+            except ValueError as e:
+                # Handle missing API key or configuration errors
+                return ErrorResponse(
+                    message=f"Agent generation is not configured: {str(e)}",
+                    error="configuration_error",
+                    session_id=session_id,
+                )
+
+            if patch_result is None:
+                if attempt == MAX_GENERATION_RETRIES:
+                    return ErrorResponse(
+                        message="Failed to generate changes. Please try rephrasing.",
+                        error="Patch generation failed",
+                        session_id=session_id,
+                    )
+                continue
+
+            # Check if LLM returned clarifying questions
+            if patch_result.get("type") == "clarifying_questions":
+                questions = patch_result.get("questions", [])
+                return ClarificationNeededResponse(
+                    message=(
+                        "I need some more information about the changes. "
+                        "Please answer the following questions:"
+                    ),
+                    questions=[
+                        ClarifyingQuestion(
+                            question=q.get("question", ""),
+                            keyword=q.get("keyword", ""),
+                            example=q.get("example"),
+                        )
+                        for q in questions
+                    ],
+                    session_id=session_id,
+                )
+
+            # Step 3: Apply patch and fixes
+            try:
+                updated_agent = apply_agent_patch(current_agent, patch_result)
+                updated_agent = apply_all_fixes(updated_agent, blocks_info)
+            except Exception as e:
+                if attempt == MAX_GENERATION_RETRIES:
+                    return ErrorResponse(
+                        message=f"Failed to apply changes: {str(e)}",
+                        error="patch_apply_failed",
+                        details={"exception": str(e)},
+                        session_id=session_id,
+                    )
+                validation_errors = str(e)
+                continue
+
+            # Step 4: Validate the updated agent
+            is_valid, validation_errors = validate_agent(updated_agent, blocks_info)
+
+            if is_valid:
+                logger.info(f"Agent edited successfully on attempt {attempt + 1}")
+                intent = patch_result.get("intent", "Applied requested changes")
+                break
+
+            logger.warning(
+                f"Validation failed on attempt {attempt + 1}: {validation_errors}"
+            )
+
+            if attempt == MAX_GENERATION_RETRIES:
+                # Return error with validation details
+                return ErrorResponse(
+                    message=(
+                        f"Updated agent has validation errors after "
+                        f"{MAX_GENERATION_RETRIES + 1} attempts. "
+                        f"Please try rephrasing your request or simplify the changes."
+                    ),
+                    error="validation_failed",
+                    details={"validation_errors": validation_errors},
+                    session_id=session_id,
+                )
+
+        # At this point, updated_agent is guaranteed to be set (we return on all failure paths)
+        assert updated_agent is not None
+
+        agent_name = updated_agent.get("name", "Updated Agent")
+        agent_description = updated_agent.get("description", "")
+        node_count = len(updated_agent.get("nodes", []))
+        link_count = len(updated_agent.get("links", []))
+
+        # Step 5: Preview or save
+        if not save:
+            return AgentPreviewResponse(
+                message=(
+                    f"I've updated the agent. Changes: {intent}. "
+                    f"The agent now has {node_count} blocks. "
+                    f"Review it and call edit_agent with save=true to save the changes."
+                ),
+                agent_json=updated_agent,
+                agent_name=agent_name,
+                description=agent_description,
+                node_count=node_count,
+                link_count=link_count,
+                session_id=session_id,
+            )
+
+        # Save to library (creates a new version)
+        if not user_id:
+            return ErrorResponse(
+                message="You must be logged in to save agents.",
+                error="auth_required",
+                session_id=session_id,
+            )
+
+        try:
+            created_graph, library_agent = await save_agent_to_library(
+                updated_agent, user_id, is_update=True
+            )
+
+            return AgentSavedResponse(
+                message=(
+                    f"Updated agent '{created_graph.name}' has been saved to your library! "
+                    f"Changes: {intent}"
+                ),
+                agent_id=created_graph.id,
+                agent_name=created_graph.name,
+                library_agent_id=library_agent.id,
+                library_agent_link=f"/library/{library_agent.id}",
+                agent_page_link=f"/build?flowID={created_graph.id}",
+                session_id=session_id,
+            )
+        except Exception as e:
+            return ErrorResponse(
+                message=f"Failed to save the updated agent: {str(e)}",
+                error="save_failed",
+                details={"exception": str(e)},
+                session_id=session_id,
+            )

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

@@ -1,26 +1,18 @@
-"""Tool for discovering agents from marketplace and user library."""
+"""Tool for discovering agents from marketplace."""
 
-import logging
 from typing import Any
 
+from langfuse import observe
+
 from backend.api.features.chat.model import ChatSession
-from backend.api.features.store import db as store_db
-from backend.util.exceptions import DatabaseError, NotFoundError
 
+from .agent_search import search_agents
 from .base import BaseTool
-from .models import (
+from .models import ToolResponseBase
-    AgentCarouselResponse,
-    AgentInfo,
-    ErrorResponse,
-    NoResultsResponse,
-    ToolResponseBase,
-)
-
-logger = logging.getLogger(__name__)
 
 
 class FindAgentTool(BaseTool):
-    """Tool for discovering agents based on user needs."""
+    """Tool for discovering agents from the marketplace."""
 
     @property
     def name(self) -> str:
@@ -45,85 +37,13 @@ class FindAgentTool(BaseTool):
             "required": ["query"],
         }
 
+    @observe(as_type="tool", name="find_agent")
     async def _execute(
-        self,
+        self, user_id: str | None, session: ChatSession, **kwargs
-        user_id: str | None,
-        session: ChatSession,
-        **kwargs,
     ) -> ToolResponseBase:
-        """Search for agents in the marketplace.
+        return await search_agents(
-
+            query=kwargs.get("query", "").strip(),
-        Args:
+            source="marketplace",
-            user_id: User ID (may be anonymous)
+            session_id=session.session_id,
-            session_id: Chat session ID
+            user_id=user_id,
-            query: Search query
-
-        Returns:
-            AgentCarouselResponse: List of agents found in the marketplace
-            NoResultsResponse: No agents found in the marketplace
-            ErrorResponse: Error message
-        """
-        query = kwargs.get("query", "").strip()
-        session_id = session.session_id
-        if not query:
-            return ErrorResponse(
-                message="Please provide a search query",
-                session_id=session_id,
-            )
-        agents = []
-        try:
-            logger.info(f"Searching marketplace for: {query}")
-            store_results = await store_db.get_store_agents(
-                search_query=query,
-                page_size=5,
-            )
-
-            logger.info(f"Find agents tool found {len(store_results.agents)} agents")
-            for agent in store_results.agents:
-                agent_id = f"{agent.creator}/{agent.slug}"
-                logger.info(f"Building agent ID = {agent_id}")
-                agents.append(
-                    AgentInfo(
-                        id=agent_id,
-                        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,
-                    ),
-                )
-        except NotFoundError:
-            pass
-        except DatabaseError as e:
-            logger.error(f"Error searching agents: {e}", exc_info=True)
-            return ErrorResponse(
-                message="Failed to search for agents. Please try again.",
-                error=str(e),
-                session_id=session_id,
-            )
-        if not agents:
-            return NoResultsResponse(
-                message=f"No agents found matching '{query}'. Try different keywords or browse the marketplace. If you have 3 consecutive find_agent tool calls results and found no agents. Please stop trying and ask the user if there is anything else you can help with.",
-                session_id=session_id,
-                suggestions=[
-                    "Try more general terms",
-                    "Browse categories in the marketplace",
-                    "Check spelling",
-                ],
-            )
-
-        # Return formatted carousel
-        title = (
-            f"Found {len(agents)} agent{'s' if len(agents) != 1 else ''} for '{query}'"
-        )
-        return AgentCarouselResponse(
-            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 they do, please call the get_agent_details tool for this agent.",
-            title=title,
-            agents=agents,
-            count=len(agents),
-            session_id=session_id,
         )

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

@@ -0,0 +1,194 @@
+import logging
+from typing import Any
+
+from langfuse import observe
+from prisma.enums import ContentType
+
+from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.tools.base import BaseTool, ToolResponseBase
+from backend.api.features.chat.tools.models import (
+    BlockInfoSummary,
+    BlockInputFieldInfo,
+    BlockListResponse,
+    ErrorResponse,
+    NoResultsResponse,
+)
+from backend.api.features.store.hybrid_search import unified_hybrid_search
+from backend.data.block import get_block
+
+logger = logging.getLogger(__name__)
+
+
+class FindBlockTool(BaseTool):
+    """Tool for searching available blocks."""
+
+    @property
+    def name(self) -> str:
+        return "find_block"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Search for available blocks by name or description. "
+            "Blocks are reusable components that perform specific tasks like "
+            "sending emails, making API calls, processing text, etc. "
+            "IMPORTANT: Use this tool FIRST to get the block's 'id' before calling run_block. "
+            "The response includes each block's id, required_inputs, and input_schema."
+        )
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "description": (
+                        "Search query to find blocks by name or description. "
+                        "Use keywords like 'email', 'http', 'text', 'ai', etc."
+                    ),
+                },
+            },
+            "required": ["query"],
+        }
+
+    @property
+    def requires_auth(self) -> bool:
+        return True
+
+    @observe(as_type="tool", name="find_block")
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        """Search for blocks matching the query.
+
+        Args:
+            user_id: User ID (required)
+            session: Chat session
+            query: Search query
+
+        Returns:
+            BlockListResponse: List of matching blocks
+            NoResultsResponse: No blocks found
+            ErrorResponse: Error message
+        """
+        query = kwargs.get("query", "").strip()
+        session_id = session.session_id
+
+        if not query:
+            return ErrorResponse(
+                message="Please provide a search query",
+                session_id=session_id,
+            )
+
+        try:
+            # Search for blocks using hybrid search
+            results, total = await unified_hybrid_search(
+                query=query,
+                content_types=[ContentType.BLOCK],
+                page=1,
+                page_size=10,
+            )
+
+            if not results:
+                return NoResultsResponse(
+                    message=f"No blocks found for '{query}'",
+                    suggestions=[
+                        "Try broader keywords like 'email', 'http', 'text', 'ai'",
+                        "Check spelling of technical terms",
+                    ],
+                    session_id=session_id,
+                )
+
+            # Enrich results with full block information
+            blocks: list[BlockInfoSummary] = []
+            for result in results:
+                block_id = result["content_id"]
+                block = get_block(block_id)
+
+                if block:
+                    # Get input/output schemas
+                    input_schema = {}
+                    output_schema = {}
+                    try:
+                        input_schema = block.input_schema.jsonschema()
+                    except Exception:
+                        pass
+                    try:
+                        output_schema = block.output_schema.jsonschema()
+                    except Exception:
+                        pass
+
+                    # Get categories from block instance
+                    categories = []
+                    if hasattr(block, "categories") and block.categories:
+                        categories = [cat.value for cat in block.categories]
+
+                    # Extract required inputs for easier use
+                    required_inputs: list[BlockInputFieldInfo] = []
+                    if input_schema:
+                        properties = input_schema.get("properties", {})
+                        required_fields = set(input_schema.get("required", []))
+                        # Get credential field names to exclude from required inputs
+                        credentials_fields = set(
+                            block.input_schema.get_credentials_fields().keys()
+                        )
+
+                        for field_name, field_schema in properties.items():
+                            # Skip credential fields - they're handled separately
+                            if field_name in credentials_fields:
+                                continue
+
+                            required_inputs.append(
+                                BlockInputFieldInfo(
+                                    name=field_name,
+                                    type=field_schema.get("type", "string"),
+                                    description=field_schema.get("description", ""),
+                                    required=field_name in required_fields,
+                                    default=field_schema.get("default"),
+                                )
+                            )
+
+                    blocks.append(
+                        BlockInfoSummary(
+                            id=block_id,
+                            name=block.name,
+                            description=block.description or "",
+                            categories=categories,
+                            input_schema=input_schema,
+                            output_schema=output_schema,
+                            required_inputs=required_inputs,
+                        )
+                    )
+
+            if not blocks:
+                return NoResultsResponse(
+                    message=f"No blocks found for '{query}'",
+                    suggestions=[
+                        "Try broader keywords like 'email', 'http', 'text', 'ai'",
+                    ],
+                    session_id=session_id,
+                )
+
+            return BlockListResponse(
+                message=(
+                    f"Found {len(blocks)} block(s) matching '{query}'. "
+                    "To execute a block, use run_block with the block's 'id' field "
+                    "and provide 'input_data' matching the block's input_schema."
+                ),
+                blocks=blocks,
+                count=len(blocks),
+                query=query,
+                session_id=session_id,
+            )
+
+        except Exception as e:
+            logger.error(f"Error searching blocks: {e}", exc_info=True)
+            return ErrorResponse(
+                message="Failed to search blocks",
+                error=str(e),
+                session_id=session_id,
+            )

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

@@ -0,0 +1,55 @@
+"""Tool for searching agents in the user's library."""
+
+from typing import Any
+
+from langfuse import observe
+
+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
+
+    @observe(as_type="tool", name="find_library_agent")
+    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/chat/tools/get_doc_page.py

@@ -0,0 +1,151 @@
+"""GetDocPageTool - Fetch full content of a documentation page."""
+
+import logging
+from pathlib import Path
+from typing import Any
+
+from langfuse import observe
+
+from backend.api.features.chat.model import ChatSession
+from backend.api.features.chat.tools.base import BaseTool
+from backend.api.features.chat.tools.models import (
+    DocPageResponse,
+    ErrorResponse,
+    ToolResponseBase,
+)
+
+logger = logging.getLogger(__name__)
+
+# Base URL for documentation (can be configured)
+DOCS_BASE_URL = "https://docs.agpt.co"
+
+
+class GetDocPageTool(BaseTool):
+    """Tool for fetching full content of a documentation page."""
+
+    @property
+    def name(self) -> str:
+        return "get_doc_page"
+
+    @property
+    def description(self) -> str:
+        return (
+            "Get the full content of a documentation page by its path. "
+            "Use this after search_docs to read the complete content of a relevant page."
+        )
+
+    @property
+    def parameters(self) -> dict[str, Any]:
+        return {
+            "type": "object",
+            "properties": {
+                "path": {
+                    "type": "string",
+                    "description": (
+                        "The path to the documentation file, as returned by search_docs. "
+                        "Example: 'platform/block-sdk-guide.md'"
+                    ),
+                },
+            },
+            "required": ["path"],
+        }
+
+    @property
+    def requires_auth(self) -> bool:
+        return False  # Documentation is public
+
+    def _get_docs_root(self) -> Path:
+        """Get the documentation root directory."""
+        this_file = Path(__file__)
+        project_root = this_file.parent.parent.parent.parent.parent.parent.parent.parent
+        return project_root / "docs"
+
+    def _extract_title(self, content: str, fallback: str) -> str:
+        """Extract title from markdown content."""
+        lines = content.split("\n")
+        for line in lines:
+            if line.startswith("# "):
+                return line[2:].strip()
+        return fallback
+
+    def _make_doc_url(self, path: str) -> str:
+        """Create a URL for a documentation page."""
+        url_path = path.rsplit(".", 1)[0] if "." in path else path
+        return f"{DOCS_BASE_URL}/{url_path}"
+
+    @observe(as_type="tool", name="get_doc_page")
+    async def _execute(
+        self,
+        user_id: str | None,
+        session: ChatSession,
+        **kwargs,
+    ) -> ToolResponseBase:
+        """Fetch full content of a documentation page.
+
+        Args:
+            user_id: User ID (not required for docs)
+            session: Chat session
+            path: Path to the documentation file
+
+        Returns:
+            DocPageResponse: Full document content
+            ErrorResponse: Error message
+        """
+        path = kwargs.get("path", "").strip()
+        session_id = session.session_id if session else None
+
+        if not path:
+            return ErrorResponse(
+                message="Please provide a documentation path.",
+                error="Missing path parameter",
+                session_id=session_id,
+            )
+
+        # Sanitize path to prevent directory traversal
+        if ".." in path or path.startswith("/"):
+            return ErrorResponse(
+                message="Invalid documentation path.",
+                error="invalid_path",
+                session_id=session_id,
+            )
+
+        docs_root = self._get_docs_root()
+        full_path = docs_root / path
+
+        if not full_path.exists():
+            return ErrorResponse(
+                message=f"Documentation page not found: {path}",
+                error="not_found",
+                session_id=session_id,
+            )
+
+        # Ensure the path is within docs root
+        try:
+            full_path.resolve().relative_to(docs_root.resolve())
+        except ValueError:
+            return ErrorResponse(
+                message="Invalid documentation path.",
+                error="invalid_path",
+                session_id=session_id,
+            )
+
+        try:
+            content = full_path.read_text(encoding="utf-8")
+            title = self._extract_title(content, path)
+
+            return DocPageResponse(
+                message=f"Retrieved documentation page: {title}",
+                title=title,
+                path=path,
+                content=content,
+                doc_url=self._make_doc_url(path),
+                session_id=session_id,
+            )
+
+        except Exception as e:
+            logger.error(f"Failed to read documentation page {path}: {e}")
+            return ErrorResponse(
+                message=f"Failed to read documentation page: {str(e)}",
+                error="read_failed",
+                session_id=session_id,
+            )

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

@@ -1,5 +1,6 @@
 """Pydantic models for tool responses."""
 
+from datetime import datetime
 from enum import Enum
 from typing import Any
 
@@ -11,14 +12,22 @@ from backend.data.model import CredentialsMetaInput
 class ResponseType(str, Enum):
     """Types of tool responses."""
 
-    AGENT_CAROUSEL = "agent_carousel"
+    AGENTS_FOUND = "agents_found"
     AGENT_DETAILS = "agent_details"
     SETUP_REQUIREMENTS = "setup_requirements"
     EXECUTION_STARTED = "execution_started"
     NEED_LOGIN = "need_login"
     ERROR = "error"
     NO_RESULTS = "no_results"
-    SUCCESS = "success"
+    AGENT_OUTPUT = "agent_output"
+    UNDERSTANDING_UPDATED = "understanding_updated"
+    AGENT_PREVIEW = "agent_preview"
+    AGENT_SAVED = "agent_saved"
+    CLARIFICATION_NEEDED = "clarification_needed"
+    BLOCK_LIST = "block_list"
+    BLOCK_OUTPUT = "block_output"
+    DOC_SEARCH_RESULTS = "doc_search_results"
+    DOC_PAGE = "doc_page"
 
 
 # Base response model
@@ -51,14 +60,14 @@ class AgentInfo(BaseModel):
     graph_id: str | None = None
 
 
-class AgentCarouselResponse(ToolResponseBase):
+class AgentsFoundResponse(ToolResponseBase):
     """Response for find_agent tool."""
 
-    type: ResponseType = ResponseType.AGENT_CAROUSEL
+    type: ResponseType = ResponseType.AGENTS_FOUND
     title: str = "Available Agents"
     agents: list[AgentInfo]
     count: int
-    name: str = "agent_carousel"
+    name: str = "agents_found"
 
 
 class NoResultsResponse(ToolResponseBase):
@@ -173,3 +182,155 @@ class ErrorResponse(ToolResponseBase):
     type: ResponseType = ResponseType.ERROR
     error: str | None = None
     details: dict[str, Any] | None = None
+
+
+# Agent output models
+class ExecutionOutputInfo(BaseModel):
+    """Summary of a single execution's outputs."""
+
+    execution_id: str
+    status: str
+    started_at: datetime | None = None
+    ended_at: datetime | None = None
+    outputs: dict[str, list[Any]]
+    inputs_summary: dict[str, Any] | None = None
+
+
+class AgentOutputResponse(ToolResponseBase):
+    """Response for agent_output tool."""
+
+    type: ResponseType = ResponseType.AGENT_OUTPUT
+    agent_name: str
+    agent_id: str
+    library_agent_id: str | None = None
+    library_agent_link: str | None = None
+    execution: ExecutionOutputInfo | None = None
+    available_executions: list[dict[str, Any]] | None = None
+    total_executions: int = 0
+
+
+# Business understanding models
+class UnderstandingUpdatedResponse(ToolResponseBase):
+    """Response for add_understanding tool."""
+
+    type: ResponseType = ResponseType.UNDERSTANDING_UPDATED
+    updated_fields: list[str] = Field(default_factory=list)
+    current_understanding: dict[str, Any] = Field(default_factory=dict)
+
+
+# Agent generation models
+class ClarifyingQuestion(BaseModel):
+    """A question that needs user clarification."""
+
+    question: str
+    keyword: str
+    example: str | None = None
+
+
+class AgentPreviewResponse(ToolResponseBase):
+    """Response for previewing a generated agent before saving."""
+
+    type: ResponseType = ResponseType.AGENT_PREVIEW
+    agent_json: dict[str, Any]
+    agent_name: str
+    description: str
+    node_count: int
+    link_count: int = 0
+
+
+class AgentSavedResponse(ToolResponseBase):
+    """Response when an agent is saved to the library."""
+
+    type: ResponseType = ResponseType.AGENT_SAVED
+    agent_id: str
+    agent_name: str
+    library_agent_id: str
+    library_agent_link: str
+    agent_page_link: str  # Link to the agent builder/editor page
+
+
+class ClarificationNeededResponse(ToolResponseBase):
+    """Response when the LLM needs more information from the user."""
+
+    type: ResponseType = ResponseType.CLARIFICATION_NEEDED
+    questions: list[ClarifyingQuestion] = Field(default_factory=list)
+
+
+# Documentation search models
+class DocSearchResult(BaseModel):
+    """A single documentation search result."""
+
+    title: str
+    path: str
+    section: str
+    snippet: str  # Short excerpt for UI display
+    score: float
+    doc_url: str | None = None
+
+
+class DocSearchResultsResponse(ToolResponseBase):
+    """Response for search_docs tool."""
+
+    type: ResponseType = ResponseType.DOC_SEARCH_RESULTS
+    results: list[DocSearchResult]
+    count: int
+    query: str
+
+
+class DocPageResponse(ToolResponseBase):
+    """Response for get_doc_page tool."""
+
+    type: ResponseType = ResponseType.DOC_PAGE
+    title: str
+    path: str
+    content: str  # Full document content
+    doc_url: str | None = None
+
+
+# Block models
+class BlockInputFieldInfo(BaseModel):
+    """Information about a block input field."""
+
+    name: str
+    type: str
+    description: str = ""
+    required: bool = False
+    default: Any | None = None
+
+
+class BlockInfoSummary(BaseModel):
+    """Summary of a block for search results."""
+
+    id: str
+    name: str
+    description: str
+    categories: list[str]
+    input_schema: dict[str, Any]
+    output_schema: dict[str, Any]
+    required_inputs: list[BlockInputFieldInfo] = Field(
+        default_factory=list,
+        description="List of required input fields for this block",
+    )
+
+
+class BlockListResponse(ToolResponseBase):
+    """Response for find_block tool."""
+
+    type: ResponseType = ResponseType.BLOCK_LIST
+    blocks: list[BlockInfoSummary]
+    count: int
+    query: str
+    usage_hint: str = Field(
+        default="To execute a block, call run_block with block_id set to the block's "
+        "'id' field and input_data containing the required fields from input_schema."
+    )
+
+
+class BlockOutputResponse(ToolResponseBase):
+    """Response for run_block tool."""
+
+    type: ResponseType = ResponseType.BLOCK_OUTPUT
+    block_id: str
+    block_name: str
+    outputs: dict[str, list[Any]]
+    success: bool = True