PyPI - fastapi-fullstack - Versions diffs - 0.2.12__py3-none-any.whl → 0.2.13__py3-none-any.whl - Mend

fastapi-fullstack 0.2.12py3-none-any.whl → 0.2.13py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (591) hide show

{fastapi_fullstack-0.2.12.dist-info → fastapi_fullstack-0.2.13.dist-info}/METADATA RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fastapi-fullstack
-Version: 0.2.12
+Version: 0.2.13
 Summary: Full-stack FastAPI + Next.js template generator with PydanticAI/LangChain agents, WebSocket streaming, 20+ enterprise integrations, and Logfire/LangSmith observability. Ship AI apps fast. CLI tool to generate production-ready FastAPI + Next.js projects with AI agents, auth, and observability.
 Project-URL: Homepage, https://github.com/vstorm-co/full-stack-ai-agent-template
 Project-URL: Documentation, https://github.com/vstorm-co/full-stack-ai-agent-template#readme
@@ -25,7 +25,7 @@ Requires-Dist: click>=8.3.0
 Requires-Dist: cookiecutter>=2.7.0
 Requires-Dist: email-validator>=2.3.0
 Requires-Dist: httpx>=0.28.1
-Requires-Dist: pydantic-settings>=2.13.0
+Requires-Dist: pydantic-settings>=2.14.2
 Requires-Dist: pydantic>=2.13.0
 Requires-Dist: pytest-asyncio>=1.3.0
 Requires-Dist: pytest>=9.0.3
@@ -45,10 +45,6 @@ Requires-Dist: mkdocs>=1.6.1; extra == 'docs'
 Requires-Dist: pymdown-extensions>=10.20; extra == 'docs'
 Description-Content-Type: text/markdown
-<p align="center">
-  <img src="https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/chat_demo.gif" alt="Live chat — web search, tool calls, and chart generation" width="100%">
-</p>
 <h1 align="center">Full-Stack AI Agent Template</h1>
 <p align="center">
@@ -79,7 +75,11 @@ Description-Content-Type: text/markdown
 </p>
 <p align="center">
-  <b>🤖 6 AI Agent Frameworks</b> <i>(PydanticAI, PydanticDeep, LangChain, LangGraph, CrewAI, DeepAgents)</i>
+  <img src="https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/chat_demo_with_tasks.gif" alt="AI chat with live plan & task checklist" width="100%">
+</p>
+<p align="center">
+  <b>🤖 5 AI Agent Frameworks</b> <i>(PydanticAI, PydanticDeep, LangChain, LangGraph, DeepAgents)</i>
   <br>
   <b>📄 RAG Pipeline</b> <i>(Milvus, Qdrant, pgvector, ChromaDB)</i>
   <br>
@@ -150,50 +150,23 @@ uv tool install fastapi-fullstack
 pipx install fastapi-fullstack
 ```
-### Create Your Project
+### From zero to a running app
+Three steps. The wizard scaffolds the project, `make bootstrap` brings up the whole backend, and the frontend runs with a single command:
 ```bash
-# Interactive wizard (recommended — runs by default)
+# 1. Generate your project — just answer the wizard's prompts
 fastapi-fullstack
-# Quick mode with options
-fastapi-fullstack create my_ai_app \
-  --database postgresql \
-  --frontend nextjs
-# Use presets for common setups
-fastapi-fullstack create my_ai_app --preset production   # Full production setup
-fastapi-fullstack create my_ai_app --preset ai-agent     # AI agent with streaming
-# Minimal project (no extras)
-fastapi-fullstack create my_ai_app --minimal
-```
-### Start Development
-#### First time on a fresh clone
-```bash
+# 2. Backend + PostgreSQL up, migrations applied, default admin seeded
 cd my_ai_app
-make bootstrap       # = make dev + make seed
-```
-That's it — backend, database, Redis, vector store (if RAG), Celery (if selected) come up, migrations are applied, and a default admin is seeded.
+make bootstrap
-#### Day-to-day
-```bash
-make dev             # idempotent: build + up + migrate. Re-run anytime.
+# 3. Frontend (in a second terminal)
+cd frontend && bun install && bun dev
 ```
-`make dev` skips admin seeding (that's a one-shot in `make seed`) so it stays cheap to run after every code/config change.
-**Behind the scenes (`make dev`):**
-1. Builds the backend Docker image (cached after first run)
-2. Starts services via `docker-compose.dev.yml` (hot-reload bind mounts)
-3. Polls Postgres until ready (`pg_isready` — no fixed sleeps)
-4. Applies pending Alembic migrations (no-op if already at head)
+> **What `make bootstrap` does** (= `make dev` + `make seed`): builds the backend Docker image, starts the stack via `docker-compose.dev.yml`, waits for PostgreSQL (`pg_isready`), applies Alembic migrations, and seeds `admin@example.com` / `admin123`. It's idempotent — re-run it anytime.
 **Then access:**
@@ -215,6 +188,28 @@ make dev-rebuild   # force-rebuild backend image (after pyproject.toml changes)
 make dev-frontend  # start the Next.js container
 ```
+After the first `make bootstrap`, day-to-day you just run `make dev` (skips admin re-seed). Run `make help` inside the project for the full list.
+<details>
+<summary><b>Other ways to generate (flags, presets, minimal)</b></summary>
+Skip the wizard and pass options directly:
+```bash
+# Non-interactive with explicit options
+fastapi-fullstack create my_ai_app --database postgresql --frontend nextjs
+# Presets for common scenarios (run `fastapi-fullstack templates` for the full list)
+fastapi-fullstack create my_ai_app --preset ai-agent           # AI agent with streaming
+fastapi-fullstack create my_ai_app --preset production         # Full production setup
+fastapi-fullstack create my_ai_app --preset production-saas    # SaaS: billing, teams, admin
+# Bare-bones project (PostgreSQL, no Docker/Redis/CI)
+fastapi-fullstack create my_ai_app --minimal
+```
+</details>
 ### Environments
 | `make` target | Compose file | When to use |
@@ -292,156 +287,367 @@ Use `make help` to see all available Makefile shortcuts.
 ## 🎬 Demo
-**CLI generator:**
+**CLI generator** — configure and scaffold a full-stack AI project in under 60 seconds:
-<p align="center">
-  <img src="https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/app_start.gif" alt="FastAPI Fullstack Generator Demo">
-</p>
+![CLI generator demo](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/cli_generator_demo_2.gif)
-**File upload & RAG ingestion:**
+<table>
+<tr>
+<td width="50%">
-<p align="center">
-  <img src="https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/rag_demo.gif" alt="File upload &amp; RAG ingestion" width="100%">
-</p>
+**AI chat** — streaming responses, tool calls, reasoning, and ask-user pauses:
+![AI chat demo](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/chat_demo.gif)
+</td>
+<td width="50%">
+**RAG ingestion** — drop a document, watch it get chunked, embedded, and answered against:
+![RAG demo](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/rag_demo.gif)
+</td>
+</tr>
+</table>
+**Generated marketing site** — public landing page with hero, pricing, blog, and legal pages (`enable_marketing_site`):
+![Landing demo](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/landing.gif)
 ---
 ## 📸 Screenshots
-### Marketing Site
+### AI Chat
+The chat UI streams responses over WebSocket and renders each tool call as a purpose-built card.
+<table>
+<tr>
+<td width="50%">
+**Plan & tasks** — sticky checklist updating live as the agent works through steps.
+![Chat plan and tasks](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/chat_tasks.png)
+</td>
+<td width="50%">
+**Subagents** — live feed and side panel showing each subagent's status and messages.
+![Chat subagents](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/chat_subagents.png)
+</td>
+</tr>
+<tr>
+<td width="50%">
+**Charts** — interactive bar/area/line/pie/scatter charts rendered inline.
+![Chat charts](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/chat_graphs.png)
+</td>
+<td width="50%">
+**Code execution** — `run_python` shows code + stdout/result in a collapsible card.
-**Landing Page** — Full-page marketing site with hero, features breakdown, testimonials, pricing preview, and FAQ. Generated with the `enable_marketing_site` option.
+![Chat Python code execution](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/chat_python_code.png)
-![Landing Page](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/landing_page.png)
+</td>
+</tr>
+<tr>
+<td width="50%">
-**Pricing** — Three-tier pricing page (Starter / Pro / Business) with monthly/annual toggle. Pulls live plan data from Stripe when connected; shows template plans otherwise.
+**Ask user** — agent pauses to ask clarifying questions; card keeps the full transcript.
-![Pricing](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/pricing.png)
+![Chat ask-user tool](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/chat_ask_user.png)
-**Blog** — Engineering blog included out of the box. Posts are MDX files in the repo — no CMS needed. Supports tags, featured posts, and author bylines.
+</td>
+<td width="50%">
-![Blog](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/blog.png)
+**Reasoning** — clean thinking view + answered-question history for long agent turns.
-**Blog Post** — Individual post view with author card, reading time, and tag badges. Content is plain MDX — edit files and redeploy.
+![Chat reasoning and answered questions](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/chat_answered_questions_and_thinking.png)
-![Blog Post](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/blog_post.png)
+</td>
+</tr>
+</table>
-### Auth
+### Auth & Dashboard
-**Login** — Split-screen login with Google OAuth and email/password. Left panel shows a product pitch with a social proof quote. HTTP-only cookie session on submit.
+<table>
+<tr>
+<td width="50%">
-![Login](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/login.png)
+**Login** — split-screen with Google OAuth + email/password, HTTP-only cookie session.
-**Register** — Same split-screen layout as login. Google sign-up and email/password form with confirm-password field and terms acceptance.
+![Login](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/login.png)
-![Register](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/register.png)
+</td>
+<td width="50%">
-### Dashboard
+**Register** — same split-screen layout with confirm-password and terms acceptance.
-**Dashboard (light mode)** — Workspace overview showing conversation count, knowledge base vector count, recent activity feed, agent tool call stats, active sessions, and team info. Onboarding banner guides new users through setup in under 2 minutes.
+![Register](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/register.png)
-![Dashboard Light](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/dashboard_light.png)
+</td>
+</tr>
+<tr>
+<td width="50%">
-**Dashboard (dark mode)** — Same dashboard in dark theme. Theme is saved per-device and can be overridden per-workspace in appearance settings.
+**Dashboard (light)** — stat cards, usage timeline, recent activity, onboarding banner.
-![Dashboard Dark](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/dashboard_dark.png)
+![Dashboard Light](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/dashboard_light.png)
-### Teams & Organizations
+</td>
+<td width="50%">
-**Workspaces** — List of all organizations the user belongs to. Shows plan tier and role for each. Users can switch active workspace or create a new organization.
+**Dashboard (dark)** — same view in dark theme; saved per-device.
-![Organizations](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/organizations.png)
+![Dashboard Dark](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/dashboard_dark.png)
-**Team Management** — Organization detail page with workspace profile (name + avatar), member list with roles, and an "Invite teammate" button. Owners and admins can adjust roles inline.
+</td>
+</tr>
+</table>
-![Organization Details](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/organization_details.png)
+### Teams & Knowledge Bases
-### Knowledge Bases
+<table>
+<tr>
+<td width="50%">
-**Knowledge Bases** — List of RAG knowledge bases scoped to the current workspace. Each base shows its collection slug. Users can create new bases, toggle which ones are active in chat, and upload documents through the UI.
+**Workspaces** — list of all orgs with plan tier and role; switch or create new workspace.
-![Knowledge Bases](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/knowledge_bases.png)
+![Organizations](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/organizations_light.png)
-### Billing
+</td>
+<td width="50%">
-**Billing** — Workspace billing dashboard showing current plan, storage usage (chat attachments + indexed RAG documents), quick links to usage breakdown, invoices, payment methods, and subscription management. "Manage in Stripe" opens the Stripe customer portal.
+**Team management** — workspace profile, member list with roles, invite button.
-![Billing](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/billing.png)
+![Organization Details](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/organization_light.png)
+</td>
+</tr>
+<tr>
+<td width="50%">
+**Knowledge bases** — list of RAG collections; toggle active bases, upload documents.
+![Knowledge Bases](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/knowledge_bases_light.png)
+</td>
+<td width="50%">
+**Documents & sync sources** — preview files, manage Google Drive/S3 connectors, view run logs.
+![Knowledge Base Source](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/knowledge_base_source_light.png)
+</td>
+</tr>
+</table>
+### Billing & Usage
+<table>
+<tr>
+<td width="50%">
+**Billing overview** — current plan, seats, storage usage, Customer Portal link.
+![Billing and usage](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/billing_and_usage_light.png)
+</td>
+<td width="50%">
+**Usage charts** — daily credits-spent + call-count charts, by-model token breakdown.
+![Billing usage charts](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/billing_usage_light.png)
+</td>
+</tr>
+<tr>
+<td width="50%">
+**Credits** — balance, immutable transaction ledger, usage sparkline.
+![Billing credits](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/billing_credits_light.png)
+</td>
+<td width="50%">
+**Subscription & invoices** — plan management, invoice list, payment methods — all via Stripe.
+![Billing subscription](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/billing_subscription_light.png)
+</td>
+</tr>
+</table>
 ### Profile & Settings
-**Profile** — Personal info tab: avatar upload, display name, email, and active session list with per-device revoke buttons. Visibility note explains which fields are shown to teammates.
+<table>
+<tr>
+<td width="50%">
-![Profile](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/profile.png)
+**Profile** — avatar upload, display name, email, active sessions with per-device revoke.
-**Account & Security** — Change password form with strength guidance, "Sign out everywhere" button, and danger zone for permanent account deletion.
+![Profile](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/profile_light.png)
-![Account](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/profile_account.png)
+</td>
+<td width="50%">
-**Slash Commands** — Customize the `/command` palette in chat. Toggle built-in commands (`/clear`, `/regen`, `/settings`, `/summarize`, `/explain`) and create custom shortcuts that send a stored prompt with a few keystrokes.
+**Account & security** — password change, "sign out everywhere", account deletion zone.
-![Slash Commands](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/profile_commands.png)
+![Account](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/account_light.png)
-**Appearance** — Theme switcher (light / dark / system) and brand color picker with four presets: Blue (Stripe/Vercel), Green (healthtech), Red (energetic), Orange (B2C), Violet (Anthropic-style). Brand color updates CSS variables across the entire workspace and is saved per-device.
+</td>
+</tr>
+<tr>
+<td width="50%">
-![Appearance](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/profile_appearance.png)
+**Slash commands** — toggle built-ins, create custom prompt shortcuts for the chat palette.
-**Notification Preferences** — Per-category notification controls with separate toggles for email and in-app delivery. Categories: Billing, Team activity, Security alerts, and Product updates. Preferences stored locally and synced to the backend via `/users/me/notifications`.
+![Slash Commands](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/commands_light.png)
-![Notifications](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/profile_notifications.png)
+</td>
+<td width="50%">
+**Appearance** — light/dark/system theme + brand color picker (5 presets, saved per-device).
+![Appearance](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/appearance_light.png)
+</td>
+</tr>
+</table>
 ### Admin Panel
-**Admin Overview** — Workspace-wide metrics (total users, active sessions last 24h, conversation count, MRR) plus a recent activity feed showing all conversations across all users. Requires the `admin` role.
+<table>
+<tr>
+<td width="50%">
-![Admin Overview](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/admin_overview.png)
+**Overview** — workspace-wide metrics (users, sessions, conversations, MRR) + activity feed.
-**User Management** — Full user list with search by email or name. Shows role, status, join date, and an "Inspect" action to impersonate or suspend any user. Pagination built in.
+![Admin Overview](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/admin_overview_light.png)
-![Admin Users](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/admin_users.png)
+</td>
+<td width="50%">
-**Conversation Browser** — Browse all conversations across the workspace. Filter by status and owner, sort by any column, open any conversation in a read-only view. Useful for support and quality review.
+**User management** — search by email/name, roles, status, join date, inspect/suspend actions.
-![Admin Conversations](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/admin_conversations.png)
+![Admin Users](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/admin_users_light.png)
-**Message Quality & Ratings** — Aggregated like/dislike feedback on AI responses over the last 30 days. Shows approval rate, daily chart, and a filterable table of individual ratings with optional user comments. Export to CSV.
+</td>
+</tr>
+<tr>
+<td width="50%">
-![Admin Ratings](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/admin_ratings.png)
+**Conversation browser** — filter by status/owner, open any conversation read-only.
-**Stripe Events Log** — Webhook event browser for debugging Stripe billing flows. Lists all received events (type, customer, amount, status, timestamp) and lets admins manually replay any event via the backend `/admin/stripe-events/{id}/replay` endpoint.
+![Admin Conversations](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/admin_conversations_light.png)
-![Stripe Events](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/admin_stripe_events.png)
+</td>
+<td width="50%">
-**System Health** — Live readiness dashboard auto-refreshing every 30 seconds. Checks API, Database (PostgreSQL primary), Redis, Vector store, LLM provider, Background worker, and Stripe API. Shows uptime percentage per service.
+**Message ratings** — approval rate, daily chart, filterable rating table with comments.
-![System Health](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new2/admin_system_health.png)
+![Admin Ratings](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/admin_ratings_light.png)
-### Observability
+</td>
+</tr>
+<tr>
+<td width="50%">
+**Stripe events log** — webhook event browser with manual replay for debugging.
+![Stripe Events](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/admin_stripe_events_light.png)
+</td>
+<td width="50%">
-**Logfire (PydanticAI)** — Full distributed tracing for PydanticAI agent runs, FastAPI requests, database queries, Redis, Celery tasks, and HTTPX calls — all in one timeline.
+**System health** — live readiness checks: API, DB, Redis, vector store, LLM, worker, Stripe.
+![System Health](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/admin_system_light.png)
+</td>
+</tr>
+</table>
+### Marketing Site
+<table>
+<tr>
+<td width="50%">
+**Pricing** — three-tier page with monthly/annual toggle; pulls live Stripe plan data.
+![Pricing](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/landing_pricing.png)
+</td>
+<td width="50%">
+**Blog** — engineering blog from MDX files; tags, featured posts, author bylines. No CMS needed.
+![Blog](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/blogs.png)
+</td>
+</tr>
+</table>
+### Background Tasks, Observability & Channels
+<table>
+<tr>
+<td width="50%">
+**Prefect** — self-hosted server with RAG, billing, and email flows on cron schedules.
+![Prefect dashboard](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/prefect_dashboard.png)
+</td>
+<td width="50%">
+**Prefect flow runs** — per-run history, task timeline, and retry visibility.
+![Prefect flow runs](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/new3/prefect_runs.png)
+</td>
+</tr>
+<tr>
+<td width="50%">
+**Logfire** — distributed tracing: FastAPI, PydanticAI, DB, Redis, Celery, HTTPX in one timeline.
 ![Logfire](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/logfire.png)
-**LangSmith (LangChain / LangGraph)** — Trace viewer for LangChain agent runs with step-by-step chain inspection, token usage, and feedback collection.
+</td>
+<td width="50%">
+**LangSmith** — trace viewer for LangChain/LangGraph: chains, token usage, feedback.
 ![LangSmith](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/langsmith.png)
-### Messaging Channels
+</td>
+</tr>
+<tr>
+<td width="50%">
-**Telegram Bot** — Multi-bot integration with both polling and webhook modes. Each bot gets its own session, supports group concurrency control, and routes messages through the same agent pipeline as the web UI.
+**Telegram bot** — multi-bot, polling + webhook, per-thread sessions, group concurrency control.
 ![Telegram](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/telegram.png)
-### Monitoring & API
+</td>
+<td width="50%">
-**Celery Flower** — Real-time task queue monitor. Track worker status, task throughput, and failure rates for background jobs (document ingestion, email, webhooks).
-![Flower](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/flower.png)
-**API Documentation** — Auto-generated OpenAPI / Swagger UI at `/docs`. All endpoints documented with request/response schemas, auth requirements, and example payloads.
+**API docs** — auto-generated OpenAPI / Swagger UI with schemas, auth, and example payloads.
 ![API Docs](https://raw.githubusercontent.com/vstorm-co/full-stack-ai-agent-template/main/assets/docs_2.png)
+</td>
+</tr>
+</table>
 ---
 ## 🎯 Why This Template
@@ -467,6 +673,12 @@ This template gives you all of that out of the box, with **20+ configurable inte
 Generated projects include **CLAUDE.md** and **AGENTS.md** files optimized for AI coding assistants (Claude Code, Codex, Copilot, Cursor, Zed). Following [progressive disclosure](https://humanlayer.dev/blog/writing-a-good-claude-md) best practices - concise project overview with pointers to detailed docs when needed.
+They also ship a ready-to-use **`.claude/` toolkit** that adapts to the options you selected:
+- **Agent Skills** (`.claude/skills/`) — model-invoked playbooks that auto-trigger when relevant: `alembic-migration`, `pytest-suite`, `agent-tool` (framework-aware), `frontend-feature`, `rag-knowledge`, `background-task` (queue-aware), `billing-stripe`, and `channel-bot`. Feature-gated — only the skills that match your stack are generated.
+- **Slash commands** (`.claude/commands/`) — `/add-endpoint`, `/fix-issue`, `/review`.
+- **Convention rules** (`.claude/rules/`) — architecture, code style, schemas, exceptions/security, testing, and frontend conventions, loaded automatically.
 ---
 ## ✨ Features
@@ -475,7 +687,6 @@ Generated projects include **CLAUDE.md** and **AGENTS.md** files optimized for A
   <a href="https://ai.pydantic.dev"><img src="https://img.shields.io/badge/PydanticAI-E92063?logo=pydantic&logoColor=white" alt="PydanticAI"></a>
   <a href="https://python.langchain.com"><img src="https://img.shields.io/badge/LangChain-1C3C3C?logo=langchain&logoColor=white" alt="LangChain"></a>
   <a href="https://langchain-ai.github.io/langgraph/"><img src="https://img.shields.io/badge/LangGraph-005A9C?logo=langchain&logoColor=white" alt="LangGraph"></a>
-  <a href="https://www.crewai.com"><img src="https://img.shields.io/badge/CrewAI-FF6B35?logoColor=white" alt="CrewAI"></a>
   <a href="https://milvus.io"><img src="https://img.shields.io/badge/Milvus-FF6B35?logoColor=white" alt="Milvus"></a>
   <a href="https://openai.com"><img src="https://img.shields.io/badge/OpenAI-412991?logo=openai&logoColor=white" alt="OpenAI"></a>
   <a href="https://anthropic.com"><img src="https://img.shields.io/badge/Anthropic-D4A373?logo=anthropic&logoColor=white" alt="Anthropic"></a>
@@ -494,12 +705,12 @@ Generated projects include **CLAUDE.md** and **AGENTS.md** files optimized for A
 <p align="center">
   <a href="https://www.postgresql.org"><img src="https://img.shields.io/badge/PostgreSQL-4169E1?logo=postgresql&logoColor=white" alt="PostgreSQL"></a>
-  <a href="https://www.mongodb.com"><img src="https://img.shields.io/badge/MongoDB-47A248?logo=mongodb&logoColor=white" alt="MongoDB"></a>
   <a href="https://redis.io"><img src="https://img.shields.io/badge/Redis-DC382D?logo=redis&logoColor=white" alt="Redis"></a>
   <a href="https://milvus.io"><img src="https://img.shields.io/badge/Milvus-00A1EA?logoColor=white" alt="Milvus"></a>
   <a href="https://qdrant.tech"><img src="https://img.shields.io/badge/Qdrant-FF6B6B?logoColor=white" alt="Qdrant"></a>
   <a href="https://www.trychroma.com"><img src="https://img.shields.io/badge/ChromaDB-FF6F61?logoColor=white" alt="ChromaDB"></a>
   <a href="https://docs.celeryq.dev"><img src="https://img.shields.io/badge/Celery-37814A?logo=celery&logoColor=white" alt="Celery"></a>
+  <a href="https://www.prefect.io"><img src="https://img.shields.io/badge/Prefect-070E10?logo=prefect&logoColor=white" alt="Prefect"></a>
   <a href="https://logfire.pydantic.dev"><img src="https://img.shields.io/badge/Logfire-E92063?logo=pydantic&logoColor=white" alt="Logfire"></a>
   <a href="https://sentry.io"><img src="https://img.shields.io/badge/Sentry-362D59?logo=sentry&logoColor=white" alt="Sentry"></a>
   <a href="https://prometheus.io"><img src="https://img.shields.io/badge/Prometheus-E6522C?logo=prometheus&logoColor=white" alt="Prometheus"></a>
@@ -514,26 +725,28 @@ Generated projects include **CLAUDE.md** and **AGENTS.md** files optimized for A
 ### 🤖 AI/LLM First
-- **6 AI Frameworks** - [PydanticAI](https://ai.pydantic.dev), [PydanticDeep](https://github.com/vstorm-co/pydantic-deep), [LangChain](https://python.langchain.com), [LangGraph](https://langchain-ai.github.io/langgraph/), [CrewAI](https://www.crewai.com), [DeepAgents](https://github.com/vstorm-co/pydantic-deepagents)
+- **5 AI Frameworks** - [PydanticAI](https://ai.pydantic.dev), [PydanticDeep](https://github.com/vstorm-co/pydantic-deep), [LangChain](https://python.langchain.com), [LangGraph](https://langchain-ai.github.io/langgraph/), [DeepAgents](https://github.com/vstorm-co/pydantic-deepagents)
 - **4 LLM Providers** - OpenAI, Anthropic, Google Gemini, OpenRouter
 - **RAG** - Document ingestion, vector search, reranking (Milvus, Qdrant, ChromaDB, pgvector)
 - **WebSocket Streaming** - Real-time responses with full event access
+- **Rich Chat UI** - Specialized tool-call cards (web search, knowledge base, Python, charts, skills), live subagent feed, citation sources panel, plan/task checklist, reasoning view, and in-chat file previews
+- **Agent Tools** - Web search, URL fetch, charts, code execution (`run_python`), skills, `ask_user`, plus optional Deep Research (TODO planner + parallel subagents)
 - **Messaging Channels** - Telegram and Slack multi-bot integration with polling, webhooks, per-thread sessions, group concurrency control
 - **Conversation Sharing** - Share conversations with users or via public links, admin conversation browser
 - **Conversation Persistence** - Save chat history to database
 - **Message Ratings** - Like/dislike responses with feedback, admin analytics
 - **Image Description** - Extract images from documents, describe via LLM vision
-- **Multimodal Embeddings** - Google Gemini embedding model (text + images)
+- **Multimodal Embeddings** - Provider-aware: OpenAI, Voyage (Anthropic), Gemini (multimodal text + images)
 - **Document Sources** - Local files, API upload, Google Drive, S3/MinIO
-- **Sync Sources** - Configurable connectors (Google Drive, S3) with scheduled sync
+- **Sync Sources** - Per-organization connector management UI (Google Drive, S3/MinIO) with scheduled sync, manual triggers, encrypted credentials, and per-run logs
 - **Observability** - Logfire for PydanticAI, LangSmith for LangChain/LangGraph/DeepAgents
 ### ⚡ Backend (FastAPI)
 - **[FastAPI](https://fastapi.tiangolo.com)** + **[Pydantic v2](https://docs.pydantic.dev)** - High-performance async API
-- **Multiple Databases** - PostgreSQL (async), MongoDB (async), SQLite
+- **PostgreSQL** (async) - SQLAlchemy 2.0 + Alembic migrations, pgvector-ready
 - **Authentication** - JWT + Refresh tokens, API Keys, OAuth2 (Google)
-- **Background Tasks** - Celery, Taskiq, or ARQ
+- **Background Tasks** - Celery, Taskiq, ARQ, or Prefect
 - **Django-style CLI** - Custom management commands with auto-discovery
 ### 🎨 Frontend (Next.js 15)
@@ -542,8 +755,9 @@ Generated projects include **CLAUDE.md** and **AGENTS.md** files optimized for A
 - **AI Chat Interface** - WebSocket streaming, tool call visualization
 - **Authentication** - HTTP-only cookies, auto-refresh, password reset, magic link
 - **Marketing Site** - hero, pricing, FAQ, blog, contact form, legal pages (PL + EN)
+- **Billing Dashboard** - subscription, payment methods, invoices, credits balance/ledger, and usage charts (Stripe)
 - **User Settings** - profile, API keys CRUD (`sk_*` tokens), onboarding tracking
-- **Admin Panel** - workspace stats, Stripe events browser
+- **Admin Panel** - workspace stats, message-rating analytics, Stripe events browser
 - **SEO** - per-page metadata, OG image, sitemap, robots, manifest, favicons
 - **Dark Mode** + **i18n** (PL/EN via next-intl, locale-prefixed routes)
@@ -551,11 +765,13 @@ Generated projects include **CLAUDE.md** and **AGENTS.md** files optimized for A
 | Category | Integrations |
 |----------|-------------|
-| **AI Frameworks** | PydanticAI, PydanticDeep, LangChain, LangGraph, CrewAI, DeepAgents |
+| **AI Frameworks** | PydanticAI, PydanticDeep, LangChain, LangGraph, DeepAgents |
 | **LLM Providers** | OpenAI, Anthropic, Google Gemini, OpenRouter |
 | **RAG / Vector Stores** | Milvus, Qdrant, ChromaDB, pgvector |
-| **RAG Sources** | Local files, API upload, Google Drive, S3/MinIO, Sync Sources (configurable, scheduled) |
+| **RAG Sources** | Local files, API upload, Google Drive, S3/MinIO, Sync Sources (per-org UI, scheduled) |
 | **Embeddings** | OpenAI, Voyage, Gemini (multimodal), SentenceTransformers |
+| **Background Tasks** | Celery, Taskiq, ARQ, Prefect |
+| **Billing** | Stripe subscriptions (seat-based), credits + usage metering, invoices, Customer Portal |
 | **Caching & State** | Redis, fastapi-cache2 |
 | **Security** | Rate limiting, CORS, CSRF protection |
 | **Observability** | Logfire, LangSmith, Sentry, Prometheus |
@@ -579,7 +795,7 @@ Generated projects include **CLAUDE.md** and **AGENTS.md** files optimized for A
 │                                                                          │
 │  ┌─────────────────────────────────────────────────────────────────┐     │
 │  │                     AI AGENTS                                   │     │
-│  │  PydanticAI · LangChain · LangGraph · CrewAI · DeepAgents       │     │
+│  │  PydanticAI · LangChain · LangGraph · DeepAgents                │     │
 │  │  ────────────────────────────────────────────────────────────   │     │
 │  │  Tools: datetime · web_search (Tavily) · search_knowledge_base  │     │
 │  │  Providers: OpenAI · Anthropic · Gemini · OpenRouter            │     │
@@ -605,14 +821,15 @@ Generated projects include **CLAUDE.md** and **AGENTS.md** files optimized for A
 │  └─────────────────────────────────────────────────────────────────┘     │
 │                                                                          │
 │  Auth (JWT/API Key/OAuth) · Rate Limiting · Webhooks · Admin Panel       │
-│  Background Tasks (Celery/Taskiq/ARQ) · Django-style CLI                 │
-│  Observability (Logfire/LangSmith/Sentry/Prometheus)                     │
+│  Billing (Stripe + credits) · Background Tasks (Celery/Taskiq/ARQ/       │
+│  Prefect) · Django-style CLI · Observability (Logfire/LangSmith/         │
+│  Sentry/Prometheus)                                                      │
 └───────┬──────────────┬──────────────┬──────────────┬─────────────────────┘
         │              │              │              │
         ▼              ▼              ▼              ▼
    PostgreSQL       Redis         Vector DB      LLM APIs
-   MongoDB                        (Milvus/       (OpenAI/
-   SQLite                         Qdrant/        Anthropic/
+   (async)                        (Milvus/       (OpenAI/
+                                  Qdrant/        Anthropic/
                                   ChromaDB/      Gemini)
                                   pgvector)
 ```
@@ -637,9 +854,9 @@ graph TB
     end
     subgraph Infrastructure
-        DB[(PostgreSQL/MongoDB)]
+        DB[(PostgreSQL)]
         Redis[(Redis)]
-        Queue[Celery/Taskiq]
+        Queue[Celery/Taskiq/ARQ/Prefect]
     end
     subgraph External
@@ -685,7 +902,7 @@ See [Architecture Documentation](https://github.com/vstorm-co/full-stack-ai-agen
 ## 🤖 AI Agent
-Choose from **6 AI frameworks** and **4 LLM providers** when generating your project:
+Choose from **5 AI frameworks** and **4 LLM providers** when generating your project:
 ```bash
 # PydanticAI with OpenAI (default)
@@ -694,9 +911,6 @@ fastapi-fullstack create my_app --ai-framework pydantic_ai
 # LangGraph with Anthropic
 fastapi-fullstack create my_app --ai-framework langgraph --llm-provider anthropic
-# CrewAI with Google Gemini
-fastapi-fullstack create my_app --ai-framework crewai --llm-provider google
 # DeepAgents with OpenAI
 fastapi-fullstack create my_app --ai-framework deepagents
@@ -712,7 +926,6 @@ fastapi-fullstack create my_app --rag --database postgresql --task-queue celery
 | **PydanticDeep** | ✓ | ✓ | ✓ | - |
 | **LangChain** | ✓ | ✓ | ✓ | - |
 | **LangGraph** | ✓ | ✓ | ✓ | - |
-| **CrewAI** | ✓ | ✓ | ✓ | - |
 | **DeepAgents** | ✓ | ✓ | ✓ | - |
 ### PydanticAI Integration
@@ -833,7 +1046,7 @@ uv run my_app rag-sync-s3 --collection docs --prefix reports/ --bucket my-bucket
 - **Image description** - Extract images from documents, describe via LLM vision API (opt-in)
 - **Chunking** - RecursiveCharacterTextSplitter with configurable size/overlap
 - **Reranking** - Cohere API or local CrossEncoder for improved search quality
-- **Agent integration** - All 6 AI frameworks get a `search_knowledge_base` tool automatically
+- **Agent integration** - All 5 AI frameworks get a `search_knowledge_base` tool automatically
 ---
@@ -872,7 +1085,7 @@ graph LR
 |-----------|-------------|
 | **PydanticAI** | Agent runs, tool calls, LLM requests, token usage, streaming events |
 | **FastAPI** | Request/response traces, latency, status codes, route performance |
-| **PostgreSQL/MongoDB** | Query execution time, slow queries, connection pool stats |
+| **PostgreSQL** | Query execution time, slow queries, connection pool stats |
 | **Redis** | Cache hits/misses, command latency, key patterns |
 | **Celery/Taskiq** | Task execution, queue depth, worker performance |
 | **HTTPX** | External API calls, response times, error rates |
@@ -1000,7 +1213,7 @@ my_project/
 │   │   │   ├── deps.py          # Dependency injection
 │   │   │   └── router.py        # Route aggregation
 │   │   ├── core/                # Config, security, middleware
-│   │   ├── db/models/           # SQLAlchemy/MongoDB models
+│   │   ├── db/models/           # SQLAlchemy 2.0 models
 │   │   ├── schemas/             # Pydantic schemas
 │   │   ├── repositories/        # Data access layer
 │   │   ├── services/            # Business logic
@@ -1039,15 +1252,15 @@ generated_at = "2024-12-21T10:30:00+00:00"
 | Option | Values | Description |
 |--------|--------|-------------|
-| **Database** | `postgresql`, `mongodb`, `sqlite`, `none` | Async by default |
+| **Database** | `postgresql`, `none` | Async PostgreSQL (SQLAlchemy 2.0 + Alembic) |
 | **ORM** | `sqlalchemy`, `sqlmodel` | SQLModel for simplified syntax |
 | **Auth** | `jwt`, `api_key`, `both`, `none` | JWT includes user management |
 | **OAuth** | `none`, `google` | Social login |
-| **AI Framework** | `pydantic_ai`, `langchain`, `langgraph`, `crewai`, `deepagents` | Choose your AI agent framework |
+| **AI Framework** | `pydantic_ai`, `pydantic_deep`, `langchain`, `langgraph`, `deepagents` | Choose your AI agent framework |
 | **LLM Provider** | `openai`, `anthropic`, `google`, `openrouter` | OpenRouter only with PydanticAI |
 | **RAG** | `--rag` | Enable RAG with vector database |
 | **Vector Store** | `milvus`, `qdrant`, `chromadb`, `pgvector` | pgvector uses existing PostgreSQL |
-| **Background Tasks** | `none`, `celery`, `taskiq`, `arq` | Distributed queues |
+| **Background Tasks** | `none`, `celery`, `taskiq`, `arq`, `prefect` | Distributed queues / orchestration |
 | **Frontend** | `none`, `nextjs` | Next.js 15 + React 19 |
 ### Presets
@@ -1115,9 +1328,10 @@ fastapi-fullstack
 | **FastAPI Backend** | ✅ | ✅ | ❌ |
 | **Next.js Frontend** | ✅ (v15) | ❌ | ✅ |
 | **JWT + OAuth Authentication** | ✅ | ✅ | ✅ (NextAuth) |
-| **Background Tasks** (Celery/Taskiq/ARQ) | ✅ | ✅ (Celery) | ❌ |
+| **Background Tasks** (Celery/Taskiq/ARQ/Prefect) | ✅ | ✅ (Celery) | ❌ |
+| **Billing & Credits** (Stripe + usage metering) | ✅ | ❌ | ❌ |
 | **Admin Panel** | ✅ (SQLAdmin) | ❌ | ❌ |
-| **Multiple Databases** (PG/Mongo/SQLite) | ✅ | PostgreSQL only | Prisma |
+| **Async PostgreSQL** (SQLAlchemy 2.0 + pgvector) | ✅ | ✅ | Prisma |
 | **Docker + K8s** | ✅ | ✅ | ❌ |
 | **Interactive CLI Wizard** | ✅ | ❌ | ✅ |
 | **Django-style Commands** | ✅ | ❌ | ❌ |

fastapi-fullstack 0.2.12__py3-none-any.whl → 0.2.13__py3-none-any.whl

fastapi-fullstack 0.2.12py3-none-any.whl → 0.2.13py3-none-any.whl