This workspace uses GOOGLE_API_KEY as the canonical Google credential. Accept it ahead of the Gemini-specific aliases so the local evaluation harness can run without a separate GEMINI_API_KEY export.
Validation: uv run python -m unittest tests.test_env_project tests.test_evaluate_search_quality and a one-shot keychain-backed resolution check.
Add an optional local evaluator that compares a baseline revision against a candidate checkout, computes deterministic stability metrics, and can call Gemini for judged ranking metrics when configured.
The harness isolates child runs with a temporary HOME and a node-free PATH so historical revisions cannot trigger Bird browser-cookie auth during evaluation.
Validation: uv run python -m unittest and local smoke/full deterministic eval runs.
Update README, launch copy, and UI guidance to prefer popup-free AUTH_TOKEN/CT0 configuration, and keep X backend selection on the verified Bird or xAI paths.
Validation: uv run python -m unittest tests.test_env_project
Add per-project configuration via .claude/last30days.env, discovered by
walking up from cwd. Uses the same .env format as the existing global
config — no new parsers or formats.
Priority (highest wins):
1. Environment variables
2. .claude/last30days.env (per-project)
3. ~/.config/last30days/.env (global)
Also adds file permission checking — warns to stderr if config files
are readable by other users (should be chmod 600).
Includes tests for discovery, precedence, source tracking, and
permission warnings.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Matt Van Horn