krow_backend/.env.example

# ============================================================================
# Krow backend — example environment
#
# Copy to .env and fill in. .env is gitignored and must never be committed.
# Every value below is a placeholder or a safe local default: no real password,
# API key or token belongs in this file.
#
#   cp .env.example .env
# ============================================================================

# ── Application ─────────────────────────────────────────────────────────────
APP_ENV=development          # development | staging | production
LOG_LEVEL=info               # debug | info | warn | error

# ── HTTP server ─────────────────────────────────────────────────────────────
HTTP_HOST=127.0.0.1
HTTP_PORT=8080
HTTP_READ_TIMEOUT=15s
HTTP_WRITE_TIMEOUT=30s
HTTP_IDLE_TIMEOUT=60s
HTTP_SHUTDOWN_TIMEOUT=10s
# Browser origins allowed to call this API cross-origin, comma-separated.
# Unset in development it defaults to the Vite dev server on both hostnames
# (localhost and 127.0.0.1 are different origins to a browser) plus `vite
# preview`. Unset anywhere else it defaults to empty, meaning same-origin only.
# Origins are matched exactly, echoed back one at a time, and "*" is rejected.
# HTTP_CORS_ORIGINS=http://localhost:5173,http://127.0.0.1:5173

# ── PostgreSQL ──────────────────────────────────────────────────────────────
# The local development database. DATABASE_NAME is mixed-case and hyphenated,
# so anything that interpolates it into SQL must quote it: "Krow-force".
DATABASE_HOST=127.0.0.1
DATABASE_PORT=5432
DATABASE_NAME=Krow-force
DATABASE_USER=postgres
DATABASE_PASSWORD=
DATABASE_SCHEMA=public

# sslmode: disable is fine for a loopback dev database. APP_ENV=production
# rejects `disable` at startup — use require or verify-full there.
DATABASE_SSLMODE=disable

# Pool and timeout tuning.
DATABASE_MAX_OPEN_CONNS=25
DATABASE_MIN_IDLE_CONNS=2
DATABASE_CONN_MAX_LIFETIME=30m
DATABASE_CONNECT_TIMEOUT=5s
DATABASE_STATEMENT_TIMEOUT=10s

# ── Migrations ──────────────────────────────────────────────────────────────
# Consumed by the Makefile, which builds the golang-migrate URL from the
# DATABASE_* values above. Keep it pointed at the repository's migrations/.
MIGRATIONS_DIR=./migrations

# ── Seed ────────────────────────────────────────────────────────────────────
# The demo fixture, generated from the frontend repository's src/api/seed.js.
# The Makefile passes an absolute path; this default suits running from the
# repository root.
SEED_FIXTURE_PATH=./seed/fixtures/seed.json

# ── Model gateway ───────────────────────────────────────────────────────────
# The one place this service talks to a language model. An agent spec declares
# a `reasoning` tier — fast | balanced | deep — never a model id, so the
# mapping below is a deployment decision and changes without editing a single
# definition.
#
# WHICH PROVIDER ANSWERS is a deployment decision, but the wire protocol is no
# longer one. There is a single implementation:
#
#   openai      the chat-completions shape — which is NOT only OpenAI. Groq,
#               Gemini (through its OpenAI-compatible endpoint), OpenRouter,
#               Together, vLLM and a local Ollama all serve it, so moving
#               between them is MODEL_BASE_URL and MODEL_* ids, nothing more.
#
# The anthropic path was REMOVED. MODEL_PROVIDER=anthropic is refused at
# startup rather than ignored, because a stack still carrying it would
# otherwise run on a vendor it never chose. Leave this empty or set "openai".
MODEL_PROVIDER=openai

# Where the provider is. Defaults to Groq when unset — the model ids below are
# Groq ids, and an id is only meaningful against the service that serves it, so
# these two settings move together or not at all.
#
#   Groq        https://api.groq.com/openai/v1   (the default)
#   Gemini      https://generativelanguage.googleapis.com/v1beta/openai
#   OpenRouter  https://openrouter.ai/api/v1
#   Ollama      http://localhost:11434/v1        (no key needed)
MODEL_BASE_URL=https://api.groq.com/openai/v1

# The credential. ANTHROPIC_API_KEY is NO LONGER READ — if it is set while this
# is empty, startup fails rather than silently ignoring it.
# May be empty outside production: migrations, seeding and every endpoint that
# is not an agent run work without one, and an agent run fails with a
# structured `gateway.not_configured` rather than the service refusing to boot.
# APP_ENV=production requires one — unless the model is on localhost, which
# needs no credential at all.
MODEL_API_KEY=

# The tiers differ by model AND by *effort*, which the gateway fixes
# (fast=low, balanced=high, deep=xhigh) so that "deep" cannot mean two
# different things in two deployments.
#
# These must be ids your MODEL_BASE_URL actually serves. A leftover claude-*
# id is refused at startup: it would be accepted by this process, rejected by
# the provider, and fail every single run with a 400.
MODEL_FAST=llama-3.1-8b-instant
MODEL_BALANCED=llama-3.3-70b-versatile
MODEL_DEEP=llama-3.3-70b-versatile

MODEL_MAX_OUTPUT_TOKENS=16000

# Send the tier's effort level as `reasoning_effort` on the openai-compatible
# wire. OFF by default and it should stay off unless every model named above is
# a reasoning model: the others reject the entire request rather than ignoring
# an unknown key, so turning this on for a non-reasoning model breaks every run
# with a 400. Ignored by the anthropic provider, which always sends effort.
MODEL_REASONING_EFFORT=false

# ── Knowledge layer (retrieval) ─────────────────────────────────────────────
#
# The dense half of hybrid retrieval needs an embedding model. Three options,
# and the choice is worth making deliberately: all three return vectors and
# retrieval works with any of them, so a deployment running the wrong one looks
# exactly like one running the right one — until somebody phrases a question
# differently.
#
#   ollama    A model on this machine. Real semantics, no credential, no
#             per-token cost, and no tenant text leaving the host. Start here.
#
#                 brew install ollama
#                 ollama pull nomic-embed-text
#
#             then EMBED_PROVIDER=ollama.
#
#   voyage    Hosted, and better on subtle retrieval over a large messy corpus.
#             Needs VOYAGE_API_KEY. Anthropic does not serve embeddings, so
#             this is a separate credential.
#
#   lexical   A deterministic stand-in that hashes words into a vector. NOT
#             semantic — "annual leave" and "time off" are unrelated to it. It
#             exists so the permission filter and the citation path can be
#             tested without a network. Startup REFUSES it when
#             APP_ENV=production.
#
# Leave EMBED_PROVIDER empty and the choice is inferred from what is set,
# preferring the local model. With nothing configured at all, retrieval runs
# keyword-only and says so on every result.
#
# CHANGING PROVIDER MEANS RE-EMBEDDING. Vectors from two models are not
# comparable, and every chunk records which model produced it — so after a
# switch the old vectors are simply not searched, and retrieval silently drops
# to keyword-only until you run:
#
#     make reembed ORG=<slug>
#
EMBED_PROVIDER=ollama
EMBED_BASE_URL=http://localhost:11434
EMBED_MODEL=nomic-embed-text
EMBED_DIMENSIONS=768

# Only for EMBED_PROVIDER=voyage.
VOYAGE_API_KEY=

# Legacy switch for the stand-in. EMBED_PROVIDER=lexical is the current spelling.
EMBED_USE_LEXICAL=false