8715ed207c
- Added one-shot `llm(prompt, opts)` helpers in JS and Python eval runtimes. - Added `__llm__` eval bridge wiring for synthetic LLM tool dispatch and status/event output. - Added `runEvalLlm` with tier-to-model resolution, effort handling, and oneshot completion execution. - Added structured schema output handling via `respond` tool and JSON fallback parsing. - Documented new llm behavior in eval docs/changelog and added tests for tier mapping and error cases.