TPTBusiness 97e42d7a1a fix(loop): compress old experiment history in proposal prompt to reduce context size ...

- Summarize all but the 2 most recent experiments to compact bullet lines
  (factor name, PASS/FAIL, IC value, 120-char observation snippet) instead
  of including full verbatim traces; reduces prompt from ~121k to ~40-60k tokens
- Fix _evaluate_factor_directly and _save_factor_values to look for result.h5
  and factor.py in sub_workspace_list instead of experiment_workspace
- Fix Series.to_parquet() → Series.to_frame().to_parquet() in _save_factor_values
- Update factor_data_template README: correct bars-per-day (1440, not 96)
- Update prompts to accept 2024-only debug dataset output as valid factor result
- Fix factor_coder prompts: allow 2024 debug data in date-range instruction

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-25 09:10:39 +02:00

..

CoSTEER

feat: Fast mode - CoSTEER goes to backtest after 1 iteration

2026-04-04 20:52:39 +02:00

data_science

fix: Add Bandit security scanning and fix critical vulnerabilities

2026-04-03 11:55:05 +02:00

factor_coder

fix(loop): compress old experiment history in proposal prompt to reduce context size

2026-04-25 09:10:39 +02:00

finetune

feat: add LLM-finetune scenario (#1314)

2026-03-02 19:04:10 +08:00

model_coder

fix(security): resolve all 30 Bandit security alerts (B301, B614, B104)

2026-04-21 22:24:57 +02:00

rl

feat: Full system integration - RL + Protections + Backtesting + CLI

2026-04-03 13:53:32 +02:00

kronos_adapter.py

fix(kronos): replace rdagent_logger with stdlib logging for CI compatibility

2026-04-18 12:24:47 +02:00

optuna_optimizer.py

feat(backtest): use backtest_signal_ftmo in strategy orchestrator and optuna optimizer

2026-04-18 15:29:39 +02:00

strategy_orchestrator.py

feat(backtest): use backtest_signal_ftmo in strategy orchestrator and optuna optimizer

2026-04-18 15:29:39 +02:00