Skip to content

Fix reasoning_effort param and add watchlist scroll-to-new#32

Open
ingpedrofernandez wants to merge 2 commits intoed-donner:agent-teamsfrom
ingpedrofernandez:agent-teams
Open

Fix reasoning_effort param and add watchlist scroll-to-new#32
ingpedrofernandez wants to merge 2 commits intoed-donner:agent-teamsfrom
ingpedrofernandez:agent-teams

Conversation

@ingpedrofernandez
Copy link
Copy Markdown

  • Remove unsupported reasoning_effort="low" from LiteLLM call; this parameter is only valid for OpenAI reasoning models and causes errors with gpt-oss-120b via OpenRouter
  • Watchlist auto-scrolls to bottom after adding a ticker so the newly added item is immediately visible without manual scrolling

ingpedrofernandez and others added 2 commits April 4, 2026 17:50
- Remove unsupported reasoning_effort="low" from LiteLLM call; this
  parameter is only valid for OpenAI reasoning models and causes errors
  with gpt-oss-120b via OpenRouter
- Watchlist auto-scrolls to bottom after adding a ticker so the newly
  added item is immediately visible without manual scrolling

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Switch LLM model to claude-sonnet-4-6 and remove extra_body param
- Auto-recover watchlist tickers not tracked in price cache (e.g. from previous session)
- Fix PriceChart resize handling with autoSize and absolute positioning

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant