- once a day a background thread records the latest GitHub release and the notices for each version; the welcome screen shows them from that cache, so no run waits on the network
- the release notice names the upgrade command for how TradingAgents was installed
- TRADINGAGENTS_NO_UPDATE_CHECK=1 turns the check off; unattended and CI runs never make it
- notices are read from a new `notices` key, so earlier versions keep reading `announcements`
- quick_think_provider / deep_think_provider and their backend URLs (with TRADINGAGENTS_* variables) choose a tier's provider; unset, a tier uses llm_provider and backend_url
- a tier on another provider gets that provider's own settings and endpoint, and the run settings and report header name each tier's provider
- the CLI checks each tier provider's model variable and key before the run
- record_decision writes the run's state log, so CLI runs save full_states_log like propagate() does
- with both round counts from the environment, the CLI no longer says a chosen research depth was overridden
- an unknown --analysts name lists sentiment, not social
- --ticker, --date and --analysts answer their steps, checked as the prompts check them; --save/--no-save and --show/--no-show answer the questions after the run
- with no terminal, the run stops before it starts and names every flag or TRADINGAGENTS_* variable still needed; a missing API key and an announcement no longer wait for input
- README shows an unattended run
- 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
Yijia-Xiao