Phillip Tarrant be1ea81102 fix: preserve streaming UI callbacks across agent loop iterations ...

StreamHandler.reset() was clearing on_content, on_thinking, and on_done
callbacks after every LLM response, but they were only set once per turn.
This caused the thinking indicator and streaming display to stop working
after the first tool call in a multi-step agent turn.

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

2026-03-11 21:56:59 -05:00

..

agent

feat: add custom HeaderPanel widget and switchable agent modes

2026-03-11 21:36:23 -05:00

models

feat: add custom HeaderPanel widget and switchable agent modes

2026-03-11 21:36:23 -05:00

services

fix: preserve streaming UI callbacks across agent loop iterations

2026-03-11 21:56:59 -05:00

tools

feat: add read_many_files tool for batch file reading

2026-03-11 21:56:53 -05:00

ui

style: change header background from orange to dark cyan

2026-03-11 21:56:57 -05:00

utils

feat: re-echo condensed user prompt in chat log

2026-03-11 20:05:10 -05:00

__init__.py

init commit

2026-03-11 07:21:21 -05:00

main.py

feat: implement tweaks plan - modals, smart shell, spinner, /models, debug log, skills

2026-03-11 15:46:44 -05:00