fix: hypothesis_hunter v2 — pass field descriptions, signs, arities + strict constraint to use ONLY listed fields"

fix: add explicit operator arities to LLM compiler prompt — prevents 'Invalid number of inputs' BRAIN errors"

fix: add operator arity validation to lint + enrich LLM prompt with exact arities to prevent 'Invalid number of inputs' errors"

fix: auto-load .env file at startup using python-dotenv

fix: add PROVEN_ARCHETYPES constant back to theme_sampler.py for direct imports

fix: restore PROVEN_ARCHETYPES export + add new exports (get_theme_archetype, get_theme_fields, THEME_TO_ARCHETYPE)"

feat: config v2 — add dataset tier priorities, field selection strategy, and novel group preference

feat: expression_compiler v2 — new archetypes for model77 SUE/PEAD, supply chain, analyst guidance, PCR contrarian + auto field-aware backfill/sign"

feat: lint v2 — loads 71 operators from data/operators.csv, validates field IDs against registry, improved checks

feat: theme_sampler v2 — real BRAIN fields from model77/analyst4/news12/option9/pv13, data-driven gap scoring

feat: add alternative neutralization groups (85+ under-explored keys with AC≤100)

feat: add complete BRAIN operators catalog (71 operators with categories)

fix: upload actual brain_fields.py content (not path string)

feat: add canonical BRAIN field registry (3,447 candidates with AC, coverage, sign, tier metadata)

feat: add data layer __init__.py

Fix pipeline: enforce ts_decay_linear on all expressions + flip short-horizon returns to reversal"

Add .gitignore to protect secrets and local data"

Add .env.example with all configurable environment variables"

Fix LLM client: handle HF API response format limitations + better error handling"

Fix: use dependency-groups.dev instead of deprecated tool.uv.dev-dependencies"

Fix expression_compiler: use tier instead of hardcoded model name"

Fix: personas use tier-based model resolution instead of hardcoded defaults"

Update ML Intern artifact metadata

Update README: use uv instead of pip"

Switch to uv package manager: add uv.lock support and update pyproject.toml"

Fix pyproject.toml: explicit package discovery to resolve flat-layout error"

Upload alpha_factory/run.py with huggingface_hub

Upload alpha_factory/infra/llm_client.py with huggingface_hub

Upload alpha_factory/infra/model_manager.py with huggingface_hub

Upload alpha_factory/infra/__init__.py with huggingface_hub

Upload tests/test_fitness_and_theme.py with huggingface_hub

Upload prompts/templates/vol_shock.j2 with huggingface_hub

Upload prompts/templates/value_quality.j2 with huggingface_hub

Upload prompts/templates/social.j2 with huggingface_hub

Upload prompts/templates/skew_term.j2 with huggingface_hub

Upload prompts/templates/pead.j2 with huggingface_hub

Upload prompts/templates/intraday_mr.j2 with huggingface_hub

Upload alpha_factory/local/brain_sim.py with huggingface_hub

Upload alpha_factory/local/__init__.py with huggingface_hub

Upload alpha_factory/infra/rag.py with huggingface_hub

Upload alpha_factory/deterministic/regime_tagger.py with huggingface_hub

Upload alpha_factory/deterministic/acceptance_checklist.py with huggingface_hub

Update ML Intern artifact metadata

Add README with setup and architecture docs

Delete **/__pycache__/**, **/*.pyc

Upload tests/test_lint.py with huggingface_hub

Upload pyproject.toml with huggingface_hub

Upload factor_store/alphas.duckdb with huggingface_hub

Upload alpha_factory/schemas/__pycache__/__init__.cpython-312.pyc with huggingface_hub

Upload alpha_factory/schemas/__init__.py with huggingface_hub