bvandeusen 24d3c5bc68 Enable thinking mode in full chat view, keep disabled in widget/panel ...

stream_chat_with_tools now accepts a think parameter. run_generation
forwards it to Ollama. The message POST route reads think from the
request body. ChatView passes think=true so qwen3 uses chain-of-thought
reasoning for full conversations; the dashboard widget and ChatPanel
omit it, staying fast. Dashboard button updated to "Think it through
in Chat →" to signal the deeper capability.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-02-18 21:06:54 -05:00

..

public

Add multi-user auth, background generation, and chat UX improvements

2026-02-11 14:36:30 -05:00

src

Enable thinking mode in full chat view, keep disabled in widget/panel

2026-02-18 21:06:54 -05:00

index.html

Add multi-user auth, background generation, and chat UX improvements

2026-02-11 14:36:30 -05:00

package-lock.json

Initial commit: note-taking/task-tracking app with LLM integration scaffold

2026-02-09 23:35:44 -05:00

package.json

Add Tiptap inline-preview editor, layout improvements, and README

2026-02-11 21:24:35 -05:00

tsconfig.json

Initial commit: note-taking/task-tracking app with LLM integration scaffold

2026-02-09 23:35:44 -05:00

tsconfig.node.json

Initial commit: note-taking/task-tracking app with LLM integration scaffold

2026-02-09 23:35:44 -05:00

vite.config.ts

Initial commit: note-taking/task-tracking app with LLM integration scaffold

2026-02-09 23:35:44 -05:00