test(acp): snapshot the fs-policy rejection card

The fs-policy gate throws FS_NOT_OBSERVED when the model edits a file it
never read; that rejection surfaces as a failed tool_call_update, but no
snapshot pinned it — a regression that dropped or mis-rendered the failed
card would pass every gate. Record a scenario that edits a seeded file
without a preceding read: the edit is vetoed, the file stays unchanged on
disk, and the transcript shows the pending edit card followed by a
status:'failed' update carrying the policy error.

This commit is contained in:

Tianyi Cui

2026-07-02 23:41:02 +08:00

parent 3aa6b3c77a

commit 490fe002a1

5 changed files with 330 additions and 0 deletions

examples/acp-agent/tests/snapshots/fs-policy-reject/workspace/settings.txt

View File

				`@@ -0,0 +1 @@`
				`color: blue`