Vendor LLMmap / llm-verify / llm-fingerprint-detector under bash/fingerprint/tools so the three fingerprint benchmarks run with only /data1/eval mounted (no /data1/xii dependency): - run.py DEFAULT_TOOLS_ROOT prefers builtin tools/, falls back to /data1/xii - exclude .git / node_modules / template backups - detector dist/ (pre-built) retained; node_modules not needed at runtime
14 lines
389 B
Plaintext
14 lines
389 B
Plaintext
# === REQUIRED ===
|
|
DATABASE_URL=sqlite+aiosqlite:///./benchmarker.db
|
|
|
|
# === AI PROVIDER API KEYS (add as needed) ===
|
|
# OPENAI_API_KEY=your-openai-key-here
|
|
# ANTHROPIC_API_KEY=your-anthropic-key-here
|
|
# SUSPECT_API_KEY=the-api-key-you-are-testing
|
|
# SUSPECT_API_BASE_URL=https://api.suspect-provider.com/v1
|
|
|
|
# === OPTIONAL ===
|
|
# LOG_LEVEL=INFO
|
|
# BENCHMARK_TIMEOUT=30
|
|
# MAX_CONCURRENT_CALLS=5
|