Gros Frumos 9cbb3cec37 Fix audit hanging: add auto_apply param + allow_write for tool access ... Root cause: claude agent without --dangerously-skip-permissions hangs on tool permission prompts when stdin=DEVNULL. Fixes: - run_audit() now passes allow_write=True so agent can use Read/Bash tools without interactive permission prompts - Added auto_apply param: False for API (result only), CLI confirms with user then applies manually - API explicitly passes auto_apply=False - Tests for auto_apply=True/False behavior Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-03-15 18:00:39 +02:00
..
__init__.py	Add core/models.py — data access functions for all 9 tables	2026-03-15 13:16:12 +02:00
test_api.py	Add backlog audit and task update command	2026-03-15 17:44:16 +02:00
test_bootstrap.py	Fix bootstrap: deep scan, CLAUDE.md fallback, noise filtering	2026-03-15 13:37:42 +02:00
test_cli.py	Add backlog audit and task update command	2026-03-15 17:44:16 +02:00
test_context_builder.py	Fix output truncation bug, add language support for agent responses	2026-03-15 14:39:33 +02:00
test_followup.py	Add permission-aware follow-up flow with interactive resolution	2026-03-15 15:16:48 +02:00
test_models.py	Add core/models.py — data access functions for all 9 tables	2026-03-15 13:16:12 +02:00
test_runner.py	Fix audit hanging: add auto_apply param + allow_write for tool access	2026-03-15 18:00:39 +02:00