- Run test with cache disabled using local LLM mock
- Compare cache ON vs OFF: identical performance (~15s avg, <2% diff)
- Update problem_tracker.md with key findings summary
- Update test_config_123.yaml to use REDIS_PORT env var
- problem_tracker: add user none + cache ON run (local LLM), results table and note
- user_none_1_request_per_user_local_llm_cache_on.txt: 100 req, 100 users, cache ON
- measure_latency.py: add --user-mode created, --key-mode per_user
Pre-creates end users via POST /customer/new and keys via /key/generate
- problem_tracker: add created-mode scenarios, checkboxes, and analysis
Created mode (pre-existing users) shows better latency than random
(non-existent users) at 10 req/user: 1.2s avg vs 1.5s, 10% vs 33% above 1s
- Add --user-mode created to pre-create end users via /customer/new (requires --key-mode per_user)
- Remove defaults for --user-mode and --key-mode; both are now required
- Update problem_tracker.md Next Steps and Findings
