* fix(plugin-eval): populate model_usage from judge and Monte Carlo layers (#660)
* fix(plugin-eval): attribute judge usage to SDK model, scope it per-call
Addresses CodeRabbit + Codex review on #668:
- query_llm now keys usage_sink by the SDK-reported model
(collect_sdk_output(messages).model), falling back to the requested
model only when the stream reported none. Keeps judge attribution
consistent with the Monte Carlo layer, which already aggregates by
SDK-reported model, and stops routing/fallback substitutions from
misattributing tokens to the wrong model.
- JudgeAnalyzer no longer accumulates model_usage as instance state.
analyze_skill() now creates a local dict and threads it through the
four assess_* calls, so a reused analyzer (or concurrent
analyze_skill calls) can no longer leak or mix token counts between
runs.
- Parameterized a bare `dict` annotation introduced by this feature in
test_judge.py's _result() helper.
- Added tests: SDK-reported model differing from the requested model,
and repeated analyze_skill() calls on one analyzer not leaking usage.
Adds EvalEngine that coordinates static analysis, blends layer scores
across dimensions with renormalized weights, and produces PluginEvalResult
with composite score, badge, and per-dimension grades. Layer 2/3 stubs
ready for Tasks 8/9.
Seth Hobson