TPTBusiness 108a63fd79 feat: Strategy Generator working with local LLM (P0-P4) ...

Integrated strategy generation into fin_quant loop:
- Fixed LLM code extraction from JSON responses
- Fixed factor loading (MultiIndex parquet handling)
- Fixed return calculation (realistic proxy)
- Fixed max drawdown (NaN/inf handling)
- Added llama.cpp --reasoning off support
- Strategy orchestrator with LLM + evaluation
- Optuna optimizer integration

100% acceptance rate on test run (2/2 strategies).
Total changes: +2006 lines, -129 lines across 8 files.

Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>

2026-04-09 12:55:04 +02:00

..

benchmark

feat(backend): integrate LiteLLM API Backend (#564)

2025-02-13 15:16:18 +08:00

CI

fix mypy error (#91)

2024-07-25 15:20:04 +08:00

data_science

feat: add a web UI server (#1345)

2026-03-18 14:04:52 +08:00

finetune

fix: Harden path validation in Job Summary UI to fix CodeQL alert #17

2026-04-03 10:46:46 +02:00

general_model

chore: remove redundant tag in old scenarios (#917)

2025-06-13 17:49:58 +08:00

kaggle

feat: add option to enable hyperparameter tuning only in first eval loop (#1211)

2025-08-29 16:59:22 +08:00

qlib_rd_loop

feat: Strategy Generator working with local LLM (P0-P4)

2026-04-09 12:55:04 +02:00

rl

fix: Harden _safe_resolve to fix CodeQL alert #3

2026-04-03 10:48:43 +02:00

utils

feat: add a web UI server (#1345)

2026-03-18 14:04:52 +08:00

cli.py

feat: Strategy Generator working with local LLM (P0-P4)

2026-04-09 12:55:04 +02:00