.env.example

# ===========================================
# CodebaseQA Environment Configuration
# ===========================================
# Never commit .env to version control!
#
# WHERE THIS FILE GOES depends on how you run the app -- the two are different:
#
#   Local dev:  apps/api/.env
#               config.py loads env_file=".env" relative to the working directory,
#               and the README starts uvicorn from apps/api.
#
#   Docker:     docker/.env
#               docker-compose.yml expands ${VAR} from the file next to itself.
#               A .env at the repo root is NOT picked up for that interpolation.
#
# -----------------------
# LLM Providers (at least one required)
# -----------------------
# Leave commented until you have a real key: a placeholder is still a non-empty
# value, so the app would believe it is configured and fail only on first use.
# OPENAI_API_KEY=sk-...
# ANTHROPIC_API_KEY=sk-ant-...

# For local LLM (optional, no key needed)
# OLLAMA_BASE_URL=http://localhost:11434

# -----------------------
# Azure OpenAI (optional)
# -----------------------
# Uses Azure's v1 OpenAI-compatible surface, so the standard OpenAI client talks to
# it directly -- the endpoint below is normalised to <endpoint>/openai/v1 for you.
#
# The two things that differ from public OpenAI:
#   1. You pass DEPLOYMENT NAMES, not model ids. Azure sends the deployment name
#      where a model id normally goes.
#   2. Because a deployment name is not a model id, tiktoken cannot derive an
#      encoding from it. Name the underlying model in AZURE_OPENAI_TOKENIZER_MODEL
#      so token counting (used for truncation and batch splitting) stays exact.
#
# LLM_PROVIDER=azure_openai
# EMBEDDING_PROVIDER=azure_openai
# AZURE_OPENAI_ENDPOINT=https://my-resource.openai.azure.com
# AZURE_OPENAI_API_KEY=...
# AZURE_OPENAI_DEPLOYMENT=my-gpt4o-deployment
# AZURE_OPENAI_EMBEDDING_DEPLOYMENT=my-embedding-deployment
# AZURE_OPENAI_TOKENIZER_MODEL=text-embedding-3-small
#
# Set this to your deployed embedding model's output size, or Chroma will reject the
# insert: text-embedding-3-small is 1536, text-embedding-3-large is 3072.
# OPENAI_EMBEDDING_DIMENSIONS=1536

# -----------------------
# Neo4j graph read model (optional)
# -----------------------
# Off by default. SQL (code_dependencies) stays authoritative; Neo4j is a projection
# rebuilt at index time, and reads fall back to SQL when it is unreachable.
# Enables transitive traversals the SQL path cannot do: blast radius, shortest path
# between two files, and import-cycle detection.
#
# Do NOT use AuraDB Free for a public demo: it auto-pauses after 72h idle and a paused
# instance's hostname stops resolving, so the graph silently degrades to SQL.
# NEO4J_ENABLED=false
# NEO4J_URI=bolt://localhost:7687
# NEO4J_USER=neo4j
# NEO4J_PASSWORD=
# NEO4J_DATABASE=

# -----------------------
# Embedding Providers
# -----------------------
# Uses OpenAI by default. Uncomment to use alternatives:
# EMBEDDING_PROVIDER=openai  # openai, azure_openai, or ollama
# LLM_PROVIDER=openai        # openai, azure_openai, anthropic, or ollama
# OPENAI_EMBEDDING_MAX_TOKENS_PER_REQUEST=250000
# OPENAI_EMBEDDING_MAX_TEXTS_PER_REQUEST=128
# OPENAI_EMBEDDING_REQUEST_CONCURRENCY=1
# OPENAI_EMBEDDING_MIN_SECONDS_BETWEEN_REQUESTS=0.0
# OPENAI_EMBEDDING_RATE_LIMIT_MAX_RETRIES=6
# OPENAI_EMBEDDING_RATE_LIMIT_BASE_BACKOFF_SECONDS=1.0
# OPENAI_EMBEDDING_RATE_LIMIT_MAX_BACKOFF_SECONDS=30.0
# Ollama TAG (as in `ollama pull <tag>`), never a HuggingFace repo id. A HF id such as
# nomic-ai/nomic-embed-text-v1.5 404s on every request, and fail-open then lands every
# chunk in the index as a zero vector -- which scores every chunk identically.
# LOCAL_EMBEDDING_MODEL=nomic-embed-text

# -----------------------
# GitHub (optional, for private repos)
# -----------------------
# GITHUB_TOKEN=ghp_...

# -----------------------
# Database
# -----------------------
# Defaults to SQLite. Uncomment for PostgreSQL:
DATABASE_URL=sqlite:///./data/codebaseqa.db
# DATABASE_URL=postgresql://user:pass@localhost:5432/codebaseqa

# -----------------------
# Vector Database
# -----------------------
VECTOR_DB_TYPE=chroma
# VECTOR_DB_TYPE=qdrant
# QDRANT_URL=http://localhost:6333

# Optional Redis (recommended for distributed cache/rate-limits)
# REDIS_URL=redis://localhost:6379/0

# -----------------------
# Application Settings
# -----------------------
DEBUG=false
CORS_ORIGINS=http://localhost:3000,http://127.0.0.1:3000

# -----------------------
# Live Demo Mode (optional)
# -----------------------
DEMO_MODE=false
SEED_DEMO=false
DEMO_REPO_URL=https://github.com/vercel/nextjs-subscription-payments
DEMO_REPO_OWNER=vercel
DEMO_REPO_NAME=nextjs-subscription-payments
DEMO_REPO_BRANCH=main
DEMO_ALLOW_PUBLIC_IMPORTS=false
DEMO_BANNER_TEXT=Live demo mode: this deployment is pinned to one featured repository. For your own repository, self-host with your API key.
DEMO_BUSY_MODE=false

# Soft guardrails for public demo traffic
DEMO_RATE_LIMIT_ENABLED=true
DEMO_RATE_LIMIT_COOLDOWN_SECONDS=30
DEMO_CHAT_REQUESTS=18
DEMO_CHAT_WINDOW_SECONDS=60
DEMO_CURRICULUM_REQUESTS=6
DEMO_CURRICULUM_WINDOW_SECONDS=60
DEMO_LESSON_REQUESTS=8
DEMO_LESSON_WINDOW_SECONDS=60
DEMO_GRAPH_REQUESTS=5
DEMO_GRAPH_WINDOW_SECONDS=60
DEMO_CHALLENGE_REQUESTS=10
DEMO_CHALLENGE_WINDOW_SECONDS=60

# Graph V2 settings
# GRAPH_V2_ENABLED=true
# GRAPH_V2_MAX_NODES=160
# GRAPH_V2_MAX_EDGES=600
# GRAPH_V2_ENRICH_DESCRIPTIONS=false
# GRAPH_DENSE_MODE_V21=true
# GRAPH_V21_AUTO_NODES_THRESHOLD=90
# GRAPH_V21_AUTO_EDGES_THRESHOLD=240
# GRAPH_V21_SCOPE_MAX_NODES=220
# GRAPH_V21_SCOPE_MAX_EDGES=420
# GRAPH_V21_MODULE_MAX_NODES=120
# GRAPH_V21_MODULE_MAX_EDGES=260
# GRAPH_V21_CACHE_TTL_SECONDS=45
# GRAPH_V21_CACHE_MAX_ENTRIES=64
# GRAPH_V21_EDGE_BUDGET_FILE_PER_NODE=10
# GRAPH_V21_EDGE_BUDGET_MODULE_PER_NODE=14
# GRAPH_V22_MIN_CROSS_MODULE_RATIO_FOR_OVERVIEW=0.08
# GRAPH_V22_MIN_CROSS_MODULE_EDGES_FOR_OVERVIEW=18
# GRAPH_V22_MODULE_FILTER_ORPHANS=false

# Frontend Graph V2.1 gate
# NEXT_PUBLIC_GRAPH_DENSE_MODE_V21=true
# Set to false for strict file-first fallback during rollback:
# NEXT_PUBLIC_GRAPH_DENSE_MODE_V21=false

# -----------------------
# Chat Hardening (Quality + Scalability)
# -----------------------
# CHAT_INTENT_ROUTING_ENABLED=true
# CHAT_CONTENT_RERANK_ENABLED=true
# CHAT_DOCS_FIRST_OVERVIEW_ENABLED=true
# CHAT_INTENT_LLM_TIEBREAK_ENABLED=true
# CHAT_EMIT_META_EVENT=true
# CHAT_HISTORY_MAX_MESSAGES=20
# CHAT_HISTORY_MAX_TOKENS=1800
# CHAT_CONTEXT_MAX_CHARS=18000
# CHAT_RETRIEVAL_CANDIDATE_LIMIT=24
# CHAT_RERANK_CANDIDATE_LIMIT=18
# CHAT_REQUEST_TIMEOUT_SECONDS=90
# CHAT_CONCURRENCY_WAIT_SECONDS=2.0
# CHAT_MAX_CONCURRENT_PER_REPO=4
# CHAT_REDIS_CACHE_ENABLED=false
# CHAT_RETRIEVAL_CACHE_TTL_SECONDS=600
# CHAT_ANSWER_CACHE_TTL_SECONDS=1800
# CHAT_EMBED_CACHE_TTL_SECONDS=3600

# Demo rate-limit backend
# RATE_LIMIT_REDIS_ENABLED=true