.env.test.example

# GraphDone test-pipeline configuration — LOCAL ONLY.
#
# Copy this file to `.env.test.local` (which is gitignored) and fill in your
# own values. NEVER put real hostnames, IPs, or keys in this committed example
# or anywhere else in the repo — the local VLM boxes (GPU workstations) must
# stay out of version control. The test harness auto-loads `.env.test.local`.
#
#   cp .env.test.example .env.test.local   # then edit .env.test.local

# --- Local Vision-Language-Model (VLM) endpoints ---------------------------
# Comma-separated base URLs of your local VLM server(s). Requests are
# round-robined across them so visual evaluation is spread over every GPU.
# Leave blank to skip all VLM-driven suites (they no-op cleanly in CI).
# Example shape (use your OWN hosts in .env.test.local, never here):
#   VLM_ENDPOINTS=http://<gpu-host-a>:<port>,http://<gpu-host-b>:<port>
VLM_ENDPOINTS=

# Model id/tag to request (e.g. a llava / qwen2-vl / llama-3.2-vision build).
VLM_MODEL=

# Optional bearer key for OpenAI-compatible servers that require one.
VLM_API_KEY=

# Wire protocol: auto (default) | openai | ollama.
#   auto   — probe each endpoint: /v1/models => OpenAI-compatible, else Ollama.
#   openai — POST /v1/chat/completions (vLLM, LM Studio, llama.cpp, Ollama compat)
#   ollama — POST /api/chat with an images[] array
VLM_PROTOCOL=auto

# Max concurrent VLM requests across all endpoints (default 3).
VLM_MAX_CONCURRENCY=3

# Per-request timeout in ms — VLMs can be slow on large images (default 120000).
VLM_TIMEOUT_MS=120000

# --- Large-scale performance sweep -----------------------------------------
# Node counts to sweep, comma-separated. Leave blank to use the built-in
# default (small in CI, large locally). Example: 50,200,500,1000,2000
SCALE_SWEEP_SIZES=

# Quality tiers to sweep per size (subset of LOW,MEDIUM,HIGH,ULTRA).
SCALE_SWEEP_QUALITIES=HIGH,ULTRA