mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
feat(example): sandbox-acp-agent — the live composition; RFCs to implemented
The three-entry cordis.yml (dsh-sandbox-local + dsh-bash-sandbox at a read-only default + dsh-approval) served over ACP: the first live approval composition. Recorded snapshot scenarios pin the wire end to end — config-options advertisement, the mode-switching arc as the suite pinned header (both switches, the prompt-section delta, one changed-by-the-user notice per knob, a confined write landing under the switched mode), and both escalation branches over scripted permissionAnswers (a grant runs confined under workspace-write; a rejection executes nothing and pins the fail-closed text). The with-key escalation e2e drives a real model + real runner + the real bridge answerer, world-verified; ci.yml snapshot lane and e2e.yml install bubblewrap so the confined replays actually execute. Both RFCs move to implemented/ (Decision/Consequences form, deferred phases tracked in their own sections), with every cross-reference flipped.
This commit is contained in:
14
.github/workflows/ci.yml
vendored
14
.github/workflows/ci.yml
vendored
@@ -82,6 +82,20 @@ jobs:
|
||||
- name: Install (immutable)
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
# The snapshot lane REPLAYS the sandbox example's recorded scenarios,
|
||||
# re-executing their bash calls under a real runner. ubuntu-latest has
|
||||
# no bubblewrap preinstalled and no built Landlock launcher, so without
|
||||
# this the confined executions fail closed (SANDBOX_UNAVAILABLE). Same
|
||||
# install as sandbox.yml's bwrap leg (incl. the Ubuntu 24.04 AppArmor
|
||||
# userns knob).
|
||||
- name: Install bubblewrap (unrestrict userns)
|
||||
if: matrix.lane == 'snapshot'
|
||||
run: |
|
||||
sudo apt-get update -q
|
||||
sudo apt-get install -yq bubblewrap
|
||||
sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 \
|
||||
|| echo "apparmor userns knob absent — the functional probe decides"
|
||||
|
||||
- uses: actions/cache@v4
|
||||
if: matrix.lane == 'lint'
|
||||
with:
|
||||
|
||||
14
.github/workflows/e2e.yml
vendored
14
.github/workflows/e2e.yml
vendored
@@ -82,6 +82,20 @@ jobs:
|
||||
- name: Install (immutable)
|
||||
run: pnpm install --frozen-lockfile
|
||||
|
||||
# The with-key escalation e2e (examples/sandbox-acp-agent/tests/
|
||||
# escalation.e2e.ts) self-skips without a usable runner — without this
|
||||
# step it would never actually execute anywhere (CI had no bwrap, dev
|
||||
# macs run Seatbelt instead), which is exactly how a broken harness
|
||||
# composition once survived unseen. Same recipe as ci.yml's bwrap
|
||||
# steps; the userns knob is best-effort (absent on pre-24.04 kernels,
|
||||
# the probe decides).
|
||||
- name: Install bubblewrap (unrestrict userns)
|
||||
run: |
|
||||
sudo apt-get update -q
|
||||
sudo apt-get install -yq bubblewrap
|
||||
sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 \
|
||||
|| echo "apparmor userns knob absent — the functional probe decides"
|
||||
|
||||
# Guard against a false green: the e2e suites self-skip when the key is
|
||||
# absent, so a missing/misconfigured secret would otherwise pass as
|
||||
# "all skipped". This job only runs on trusted events (the `if:` above
|
||||
|
||||
Reference in New Issue
Block a user