# surfsense_evals — environment template.
#
# Copy this file to `.env` (in the surfsense_evals/ project root or your
# CWD) and fill in the values. `python-dotenv` loads it automatically
# the first time `core.config` is imported, so every CLI subcommand
# (`setup`, `ingest`, `run`, `report`, `teardown`, `models list`, …)
# will pick the values up.
#
#   cp .env.example .env
#   # then edit .env with your values
#
# `.env` is gitignored — never commit real secrets.

# ---------------------------------------------------------------------------
# 1. Backend target — REQUIRED (default works for a local dev backend)
# ---------------------------------------------------------------------------
SURFSENSE_API_BASE=http://localhost:8000

# ---------------------------------------------------------------------------
# 2. OpenRouter — REQUIRED for any `run` invocation
# ---------------------------------------------------------------------------
# The `native_pdf` arm calls OpenRouter directly; the `surfsense` arm
# routes through SurfSense which uses the same key under the hood.
OPENROUTER_API_KEY=sk-or-...

# Override only if you proxy OpenRouter through a private gateway:
# OPENROUTER_BASE_URL=https://openrouter.ai/api/v1

# Multimodal benchmarks (medxpertqa, mmlongbench) require a vision-capable
# slug. Recommended (verify in your catalog with `models list --grep ...`):
#   anthropic/claude-sonnet-4.5    (default recommendation)
#   anthropic/claude-opus-4.7      (strongest)
#   openai/gpt-5                   (top-tier vision)
#   google/gemini-2.5-pro          (1M-token context, best for long PDFs)
# DO NOT use openai/gpt-5.4-mini for image-bearing benchmarks — it's
# text-only on PDF content and the runner emits a warning if pinned.

# ---------------------------------------------------------------------------
# 3. Auth — pick EXACTLY ONE of the two modes below
# ---------------------------------------------------------------------------

# --- Mode A: LOCAL (backend started with AUTH_TYPE=LOCAL)
# The harness POSTs these to /auth/jwt/login automatically.
# SURFSENSE_USER_EMAIL=you@example.com
# SURFSENSE_USER_PASSWORD=...

# --- Mode B: GOOGLE OAuth (or any pre-issued JWT)
# Open the SurfSense web UI in your browser, log in via Google, then in
# DevTools → Application → Local Storage copy:
#   surfsense_bearer_token  → SURFSENSE_JWT
#   surfsense_refresh_token → SURFSENSE_REFRESH_TOKEN  (optional, enables
#                                                       auto-refresh on 401)
# SURFSENSE_JWT=eyJhbGciOi...
# SURFSENSE_REFRESH_TOKEN=eyJhbGciOi...

# ---------------------------------------------------------------------------
# 4. Filesystem paths — OPTIONAL (defaults below)
# ---------------------------------------------------------------------------
# Where datasets, rendered PDFs, ingestion id maps, run outputs, and
# state.json live. Default: <surfsense_evals>/data/
# EVAL_DATA_DIR=./data

# Where generated reports (summary.md / summary.json) get written.
# Default: <surfsense_evals>/reports/
# EVAL_REPORTS_DIR=./reports

# ---------------------------------------------------------------------------
# 5. Parser SDKs — REQUIRED for the multimodal_doc / parser_compare suite
# ---------------------------------------------------------------------------
# parser_compare calls Azure Document Intelligence and LlamaParse SDKs
# directly from the eval harness so each (basic / premium) extraction
# is a clean A/B test independent of the SurfSense backend's ETL routing.
#
# Azure Document Intelligence — used for the `azure_basic_lc` (prebuilt-read)
# and `azure_premium_lc` (prebuilt-layout) arms. Get an endpoint + key from
# https://portal.azure.com (Document Intelligence resource, F0 / S0 tier).
# AZURE_DI_ENDPOINT=https://<your-resource>.cognitiveservices.azure.com/
# AZURE_DI_KEY=<your-32-char-key>
#
# LlamaCloud (LlamaParse) — used for `llamacloud_basic_lc` (parse_page_with_llm)
# and `llamacloud_premium_lc` (parse_page_with_agent). Get a key from
# https://cloud.llamaindex.ai/api-key.
# LLAMA_CLOUD_API_KEY=llx-...