feat: add langchain,langgraph,langsmith, update python version to 3.11

Author: remember-5

.env.example

@@ -18,6 +18,7 @@ STACK_NAME=full-stack-fastapi-project
 
 # Backend
 BACKEND_CORS_ORIGINS="http://localhost,http://localhost:5173,https://localhost,https://localhost:5173,http://localhost.tiangolo.com"
+# python -c "import secrets; print(secrets.token_urlsafe(32))"
 SECRET_KEY=changethis
 FIRST_SUPERUSER=admin@example.com
 FIRST_SUPERUSER_PASSWORD=changethis
@@ -38,6 +39,22 @@ POSTGRES_DB=app
 POSTGRES_USER=postgres
 POSTGRES_PASSWORD=changethis
 
+# LLM
+OPENAI_API_KEY=
+OPENAI_BASE_URL=
+ANTHROPIC_API_KEY=
+ANTHROPIC_BASE_URL=
+
+LLM_PROVIDER_DEFAULT=openai
+LLM_MODEL_OPENAI_DEFAULT=gpt-5.4
+LLM_MODEL_ANTHROPIC_DEFAULT=claude-sonnet-4-5
+
+# LangSmith
+LANGSMITH_TRACING=true
+LANGSMITH_ENDPOINT=https://api.smith.langchain.com
+LANGSMITH_API_KEY=<your-api-key>
+LANGSMITH_PROJECT="ontology-py"
+
 SENTRY_DSN=
 
 # Configure these with your own Docker registry images

.github/workflows/playwright.yml

@@ -51,7 +51,7 @@ jobs:
     - uses: oven-sh/setup-bun@v2
     - uses: actions/setup-python@v6
       with:
-        python-version: '3.10'
+        python-version: '3.11'
     - name: Setup tmate session
       uses: mxschmitt/action-tmate@v3
       if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.debug_enabled == 'true' }}

.github/workflows/test-backend.yml

@@ -18,7 +18,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
-          python-version: "3.10"
+          python-version: "3.11"
       - name: Install uv
         uses: astral-sh/setup-uv@v7
       - run: docker compose down -v --remove-orphans

.gitignore

@@ -11,3 +11,5 @@ node_modules/
 .evn.local
 
 .worktrees
+
+.langgraph_api/

AGENTS.md

@@ -27,7 +27,7 @@ Agent guidance for working in `full-stack-fastapi-template`.
 ## Tooling
 
 - Python package management: `uv`
-- Python version: `>=3.10,<4.0`
+- Python version: `>=3.11,<4.0`
 - Backend linting/formatting: `ruff`
 - Backend type checking: `mypy --strict`
 - Backend testing: `pytest` with `coverage`

backend/Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.10
+FROM python:3.11
 
 ENV PYTHONUNBUFFERED=1
 

backend/README.md

@@ -4,6 +4,7 @@
 
 * [Docker](https://www.docker.com/).
 * [uv](https://docs.astral.sh/uv/) for Python package and environment management.
+* Python 3.11+ for local LangGraph CLI development.
 
 ## Docker Compose
 
@@ -29,6 +30,42 @@ Make sure your editor is using the correct Python virtual environment, with the
 
 Modify or add SQLModel models for data and SQL tables in `./backend/app/models.py`, API endpoints in `./backend/app/api/`, CRUD (Create, Read, Update, Delete) utils in `./backend/app/crud.py`.
 
+## LangGraph Local Development
+
+The backend now includes a minimal LangChain/LangGraph agent skeleton under `./backend/app/ai/`.
+
+To start the LangGraph local development server:
+
+```console
+$ cd backend
+$ uv run langgraph dev
+```
+
+The CLI configuration lives in `./backend/langgraph.json` and loads environment variables from the repository root `../.env`. The exported agent currently points directly at `./backend/app/ai/agents/chat/graph.py`.
+
+The chat agent keeps its prompt, tools, and graph export under `./backend/app/ai/agents/chat/`, while shared helpers live under `./backend/app/ai/shared/`.
+
+Relevant environment variables in the repository root `.env`:
+
+```dotenv
+# LLM
+OPENAI_API_KEY=
+OPENAI_BASE_URL=
+ANTHROPIC_API_KEY=
+ANTHROPIC_BASE_URL=
+LLM_PROVIDER_DEFAULT=openai
+LLM_MODEL_OPENAI_DEFAULT=gpt-4.1-mini
+LLM_MODEL_ANTHROPIC_DEFAULT=claude-3-5-haiku-latest
+
+# LangSmith
+LANGSMITH_TRACING=true
+LANGSMITH_ENDPOINT=https://api.smith.langchain.com
+LANGSMITH_API_KEY=
+LANGSMITH_PROJECT="ontology-py"
+```
+
+Use `OPENAI_BASE_URL` or `ANTHROPIC_BASE_URL` when you need a custom provider endpoint. Set `LANGSMITH_API_KEY` when you want to connect LangGraph Studio to the local server.
+
 ## VS Code
 
 There are already configurations in place to run the backend through the VS Code debugger, so that you can use breakpoints, pause and explore variables, etc.

backend/app/ai/__init__.py

@@ -0,0 +1 @@
+"""AI package with shared helpers and agent-specific modules."""

backend/app/ai/agents/__init__.py

@@ -0,0 +1 @@
+"""Agent implementations and their private assets."""

backend/app/ai/agents/chat/__init__.py

@@ -0,0 +1 @@
+"""Chat agent implementation."""