deforestation           River deforestation: air and water temperatures
                        before/after
gemini_generate         Generate text with Google Gemini (Generative
                        Language API) - robust w/ retries
ham                     Ham: sensory descriptors and overall liking
poussin                 Poussin: weight by brooding temperature and sex
trainer_AovSum          Trainer: Interpret ANOVA (AovSum) with an
                        LLM-ready prompt
trainer_LinearModel     Trainer: Interpret FactoMineR::LinearModel with
                        an LLM-ready prompt
trainer_MCA             Trainer: Name an MCA dimension
                        (FactoMineR::MCA) with an LLM-ready prompt
trainer_PCA             Trainer: Name a PCA dimension (FactoMineR::PCA)
                        with an LLM-ready prompt
trainer_chisq_test      Interpret a chi-squared test (chisq.test) with
                        an audience-aware LLM prompt
trainer_cor_test        Interpret a correlation test (cor.test) with an
                        audience-aware LLM prompt
trainer_core_actually_shown
                        Determine which requested items were actually
                        shown after filtering
trainer_core_audience_profile
                        Build an audience profile (beginner / applied /
                        advanced) with optional summary-only mode
trainer_core_build_prompt
                        Assemble a standard prompt with common sections
trainer_core_conf_label
                        Confidence level label helper
trainer_core_detect_main_factors
                        Detect main-effect factor names present in
                        T-test lines (ignore interactions) Space-safe:
                        captures everything before " - " on
                        non-interaction rows.
trainer_core_extract_block_after
                        Extract lines following a header (up to first
                        blank line)
trainer_core_filter_ttest_by_factors
                        Filter T-test lines by requested factors (main
                        and/or interactions)
trainer_core_generate_or_return
                        Generate or return a prompt, depending on
                        'generate'
trainer_core_llm_generate
                        LLM generation helper for TraineR
trainer_core_prompt_header
                        Build the standard header for prompts
trainer_core_summary_only_block
                        Utility: render a standard 3-bullet
                        summary-only instruction
trainer_core_ttest_scope_msg
                        Scope message for T-test section based on
                        requested & found factors
trainer_prop_test       Interpret a proportion test (prop.test) with an
                        audience-aware LLM prompt
trainer_t_test          Interpret a Student's t-test (stats::t.test)
                        with an LLM-ready prompt
trainer_var_test        Interpret an F test comparing two variances
                        (var.test) with an audience-aware LLM prompt
