github-mirrors/tradingagents
1
0
Fork 0
mirror of https://github.com/TauricResearch/TradingAgents.git synced 2026-09-26 22:42:40 +03:00
Code Issues Packages Projects Releases Wiki Activity
392 Commits 8 Branches 13 Tags
90be56b9b2ff2431853b81bfaec9497c65646b1f
Commit Graph
6 Commits
Author SHA1 Message Date
Yijia-Xiao 4a30cb1c0a refactor(cli): split the interactive choices and the run loop out of cli/main.py 
- selections.py asks what to run; run.py builds the graph, streams it to the live view and saves the report
- main.py keeps the Typer app and its two commands
 2026-09-24 05:00:36 +00:00
Yijia-Xiao e7354d8af4 refactor: move the decision log to tradingagents/decision_log.py 
- it is the run's persistent record, used by the graph, backtest and CLI, not an agent utility; agents/utils is gone
 2026-09-24 05:00:36 +00:00
Yijia-Xiao dcbff5ea42 feat(backtest): summarize a backtest result, or a decision log by its path 
- callers no longer construct TradingMemoryLog to score a run; README and CLI pass the result
 2026-09-24 05:00:36 +00:00
Yijia-Xiao 852ffead43 refactor(agents): organise the agents package by what each module holds 
- tools.py: the analysts' data tools, previously seven modules under utils
- context.py (was agent_utils, without its tool re-exports), state.py, rating.py and structured.py sit beside schemas.py
- every role package has an __init__
 2026-09-24 04:37:40 +00:00
Yijia-Xiao 4e1faf6465 chore(graph): remove SignalProcessor 
- process_signal reads the rating with parse_rating; the adapter ignored the model it was given
 2026-09-24 04:31:05 +00:00
Yijia-Xiao 8d30fee06b fix(agents): record the decision that was made, or flag it for review 
- the labelled rating decides, whatever dash separates it, and a scale the model echoed is not one
- prose naming several ratings is reviewed rather than read as the first word in the text
- an unreadable decision is tagged REVIEW everywhere instead of a tradeable Hold
- unrated decisions are counted apart from the backtest figures
 2026-09-17 05:00:08 +00:00