# DGR-013 — exact commands and real results (worktree venv)
VP=/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python

# Targeted story tests (this story)
$VP -m pytest -q tests/test_failure_semantics.py
# -> 22 passed

# Dependency gates stay green
$VP -m pytest -q tests/test_batch_scheduler.py        # DGR-012
# -> 16 passed
$VP -m pytest -q tests/test_hot_kv_state.py           # DGR-007
# -> 22 passed
$VP -m pytest -q tests/test_gguf_backend.py           # DGR-009
# -> 2 passed

# Quality gates
$VP -m compileall -q packages tests
# -> exit 0
git diff --check
# -> exit 0

# Machine-readable evidence
$VP .scratch/distributed-gguf-runtime/evidence/DGR-013/generate_evidence.py
# -> wrote results.json; work statuses {'completed':2,'cancelled':1,'failed':0,'unverified':2} billable_tokens=16

# Full deterministic suite
$VP -m pytest -q -p no:cacheprovider
# -> 16 failed, 792 passed, 14 skipped in 253.93s

# Clean-tree reproduction of the 16 pre-existing failures (DGR-013 files removed)
# rm packages/node/meshnet_node/failure_semantics.py tests/test_failure_semantics.py
$VP -m pytest -q tests/test_dynamic_routing.py::test_admin_can_replace_a_served_model_and_release_it \
  tests/test_node_doctor.py::test_the_shipped_recipes_are_all_applicable_by_the_backend \
  tests/test_tracker_routing.py::test_torch_node_applies_tracker_load_shard_directive \
  tests/test_node_startup.py::test_preset_model_with_hf_repo_loads_torch_backend
# -> 4 failed (same failures reproduce without any DGR-013 change)