SneakyCode

Files

Phillip Tarrant 2ad3df521d fix: display assistant content with finish tool call + block shell write redirects

Bug 1: Assistant text content was silently dropped when the LLM response
included both content and tool calls (e.g. finish with a summary). Now
content is displayed before tool call execution regardless.

Bug 2: Shell redirect operators (>, >>, <<) allowed bypassing file-write
permissions when the base command (e.g. cat) was in the allowed list.
Redirects now require explicit user approval in permissions, and the
shell tool itself blocks them as defense-in-depth.

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

2026-03-11 20:58:07 -05:00

__init__.py

init commit

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

debug_log.py

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

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

llm.py

feat: add thinking mode toggle to suppress reasoning-only response loops

2026-03-11 19:34:36 -05:00

permissions.py

fix: display assistant content with finish tool call + block shell write redirects