This commit updates the `fundamentals_analyst`, `market_analyst`, `social_media_analyst`, and `news_analyst` files to use `run_tool_loop` instead of `.invoke()`. Using `.invoke()` resulted in the LLM execution stopping immediately upon a tool call request without executing the tool, returning an empty report or raw JSON. The `run_tool_loop` function ensures tools are executed recursively and the final text content is returned. Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| agents | ||
| dataflows | ||
| graph | ||
| llm_clients | ||
| pipeline | ||
| portfolio | ||
| __init__.py | ||
| api_usage.py | ||
| daily_digest.py | ||
| default_config.py | ||
| notebook_sync.py | ||
| observability.py | ||
| report_paths.py | ||