fix(bench): remove hardcoded credential paths from benchmark runners (#177)

The `_load_api_key()` function in longmemeval_bench.py and locomo_bench.py
searched for API keys in a fixed path (`~/.config/lu/keys.json`) using
personal key names (`anthropic_milla`, `anthropic_claude_code_main`).

This leaks internal infrastructure details into the public codebase and
trains contributors to store credentials in a non-standard location
rather than using the standard ANTHROPIC_API_KEY env var.

Simplified to: CLI flag > env var > empty string. Updated help text
and HYBRID_MODE.md docs to match.

Co-authored-by: Tadao <tadao@travisfixes.com>

benchmarks/HYBRID_MODE.md

@@ -435,7 +435,6 @@ If the API call fails (timeout, rate limit, no key), the function catches the ex
 **Key loading priority:**
 1. `--llm-key` CLI flag
 2. `ANTHROPIC_API_KEY` environment variable
-3. `~/.config/lu/keys.json` (checks `anthropic.lu_key` and similar paths)
 
 ## What Changed in the Code