Files
provenance/deploy/.env.example
T
justin 330543f9ce Fix #215: pluggable LLM + embedding provider abstraction
Adds the vendor-agnostic seam the AI assistant + match-ranking plug into:
- LLMProvider / EmbeddingProvider ABCs (base.py). LLM and embeddings are
  SEPARATE abstractions — Anthropic has no embeddings endpoint, so each is
  configured independently and either can be off.
- NullLLMProvider / NullEmbeddingProvider — the default; fail loud with a clear
  "not configured" error so AI-off deployments don't silently no-op.
- AnthropicLLMProvider — first concrete LLM impl, via the official anthropic SDK
  (default model claude-opus-4-8). A local provider (e.g. Ollama) would be
  another subclass of the same interface.
- Factory in deps.py (get_llm_provider / get_embedding_provider) selects by
  env (MODEL_PROVIDER / EMBEDDING_PROVIDER); documented in .env.example.

Providers are read-only text/vector producers — they never touch the DB, so the
"AI never writes autonomously" invariant (CLAUDE.md #1) holds; writes will go
through ChangeProposal (#214).

Tests: provider selection (null default, anthropic when keyed, fallback without
key) + null providers raise. 81 passed.

Closes #215

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Signed-off-by: Justin Paul <justin@jpaul.me>
2026-06-09 12:51:01 -04:00

73 lines
2.5 KiB
Bash

# Provenance configuration — copy to `.env` and fill in. Never commit `.env`.
# Everything is twelve-factor; no endpoints or secrets live in code.
# --- Core ---
APP_ENV=development
# --- Images (pulled from git.jpaul.io; CI pushes to the LAN registry) ---
# test-main = current main build; or pin a semver / test-sha-<sha> for rollback.
IMAGE_TAG=test-main
# --- Database (Postgres) ---
POSTGRES_USER=provenance
POSTGRES_PASSWORD=change-me
POSTGRES_DB=provenance
# Backend connection string (async driver). Host 'postgres' = compose service.
DATABASE_URL=postgresql+asyncpg://provenance:change-me@postgres:5432/provenance
# --- Object storage (S3-compatible / MinIO) ---
MINIO_ROOT_USER=provenance
MINIO_ROOT_PASSWORD=change-me-too
S3_ENDPOINT_URL=http://minio:9000
S3_BUCKET=provenance
S3_ACCESS_KEY=provenance
S3_SECRET_KEY=change-me-too
S3_REGION=us-east-1
# --- Edge (Caddy) ---
# Local: ':80' (http://localhost). Production: 'provenance.example.com' for auto-HTTPS.
# Behind a Cloudflare Tunnel, keep ':80' — Cloudflare terminates TLS and the
# tunnel forwards plain HTTP to caddy:80.
PROVENANCE_SITE_ADDRESS=:80
# --- Deploy-host services (optional, selected via COMPOSE_PROFILES) ---
# 'tunnel' -> cloudflared connector (needs CLOUDFLARE_TUNNEL_TOKEN; public hostname -> http://caddy:80)
# Auto-deploy is handled by the host's global Watchtower (watches the
# watchtower-enabled backend/frontend labels) — no profile needed here.
CLOUDFLARE_TUNNEL_TOKEN=
COMPOSE_PROFILES=
# --- Auth / sessions ---
SESSION_TTL_DAYS=30
TOKEN_TTL_HOURS=24
# Set false for local http; true (default) behind TLS.
COOKIE_SECURE=false
# Base URL used to build links in outbound email.
APP_BASE_URL=http://localhost
# Mailer: 'console' logs links to stdout (dev); 'smtp' uses the SMTP settings below.
MAILER=console
# Require a verified email before an account has an active session. Leave false
# until SMTP works and existing accounts are verified, or you will lock users out.
REQUIRE_EMAIL_VERIFICATION=false
# --- Email (SMTP) — wired in a later phase ---
SMTP_HOST=
SMTP_PORT=587
SMTP_USERNAME=
SMTP_PASSWORD=
SMTP_FROM=
# --- Model providers (AI assistant + embeddings; both optional, default off) ---
# LLM: 'null' disables AI features; 'anthropic' uses the Claude API.
MODEL_PROVIDER=null
ANTHROPIC_API_KEY=
LLM_MODEL=claude-opus-4-8
LLM_MAX_TOKENS=4096
# Embeddings are separate (Anthropic has no embeddings endpoint). 'null' for now.
EMBEDDING_PROVIDER=null
# --- Model providers — wired in Phase 4 (AI assistant). BYO key. ---
# ANTHROPIC_API_KEY=
# OPENAI_API_KEY=
# XAI_API_KEY=