Files
resolutionflow/backend
Michael Chihlas 067574ad6a feat(ai): robust response extraction + structured-output foundation
Harden the Anthropic provider and lay the groundwork for schema-constrained
JSON, optimizing the existing claude-sonnet-4-6 / claude-haiku-4-5 usage
(no model changes).

ai_provider.py:
- _extract_text_from_response replaces fragile response.content[0].text:
  skips non-text leading blocks (e.g. thinking), returns the first text
  block, logs an anthropic.stop_reason warning on max_tokens/refusal
  (truncation now observable), and raises ValueError on a no-text response.
- generate_json gains an optional `schema` param. Anthropic wires it to
  output_config.format (structured outputs); schema=None preserves the exact
  prior call for every existing caller. Gemini accepts-and-ignores it.

kb_conversion_service.py:
- TROUBLESHOOTING_SCHEMA / PROCEDURAL_SCHEMA + _schema_for_target_type(),
  modelled as a strict superset of every field the prompts emit.
- convert_document passes the schema only when the new
  AI_KB_CONVERT_STRUCTURED_OUTPUT setting is True (default False). The
  _try_repair_json fallback stays as belt-and-suspenders.

Tests: 14 provider + 7 schema, TDD (red-green). Live constrained-decoding
smoke-test still required before enabling the flag in production.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-28 21:48:49 -04:00
..

Troubleshooting Decision Tree - Backend API

FastAPI backend for the Troubleshooting Decision Tree application.

Quick Start

1. Set up Python environment

cd backend
python -m venv venv

# Windows
venv\Scripts\activate

# macOS/Linux
source venv/bin/activate

pip install -r requirements.txt

2. Start PostgreSQL database

Using Docker:

docker-compose up -d

Or install PostgreSQL locally and create a database:

CREATE DATABASE decision_tree;

3. Configure environment

Copy the example env file and update as needed:

cp .env.example .env

4. Run database migrations

alembic upgrade head

5. Start the server

uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

The API will be available at:

API Endpoints

Authentication

  • POST /api/v1/auth/register - Register new user
  • POST /api/v1/auth/login - Login (form data)
  • POST /api/v1/auth/login/json - Login (JSON body)
  • POST /api/v1/auth/refresh - Refresh token
  • GET /api/v1/auth/me - Get current user
  • POST /api/v1/auth/logout - Logout

Trees

  • GET /api/v1/trees - List all trees
  • GET /api/v1/trees/categories - List categories
  • GET /api/v1/trees/search?q=query - Search trees
  • GET /api/v1/trees/{id} - Get specific tree
  • POST /api/v1/trees - Create tree (engineer/admin)
  • PUT /api/v1/trees/{id} - Update tree (engineer/admin)
  • DELETE /api/v1/trees/{id} - Delete tree (admin)

Sessions

  • GET /api/v1/sessions - List user's sessions
  • GET /api/v1/sessions/{id} - Get specific session
  • POST /api/v1/sessions - Start new session
  • PUT /api/v1/sessions/{id} - Update session
  • POST /api/v1/sessions/{id}/complete - Complete session
  • POST /api/v1/sessions/{id}/export - Export session

Development

Create new migration

alembic revision --autogenerate -m "description"

Run migrations

alembic upgrade head

Rollback migration

alembic downgrade -1

Project Structure

backend/
├── alembic/              # Database migrations
│   └── versions/
├── app/
│   ├── api/
│   │   ├── endpoints/    # API route handlers
│   │   ├── deps.py       # Dependencies (auth, etc.)
│   │   └── router.py     # Main router
│   ├── core/
│   │   ├── config.py     # Settings
│   │   ├── database.py   # DB connection
│   │   └── security.py   # JWT, password hashing
│   ├── models/           # SQLAlchemy models
│   ├── schemas/          # Pydantic schemas
│   └── main.py           # FastAPI app
├── tests/
├── alembic.ini
├── docker-compose.yml
├── requirements.txt
└── README.md