fix(guard): split on & and unwrap subshells so real daemon kills classify (Closes #787)

`runtime_recovery_guard._SEGMENT_SPLIT_RE` claimed to split a compound command
line "on shell separators", but omitted the background-job separator `&`, and no
caller stripped a subshell wrapper before tokenising. `_analyse_kill_segment`
only inspects the first command token of a segment, so in both forms the kill
verb never reached the classifier.

Measured against the previous implementation at 35e94e10:

    sleep 1 & pkill -f mcp_server.py   ->  process_kill False, contamination False
    (pkill -f mcp_server.py)           ->  process_kill False, contamination False

Changes:

- Add `&` to `_SEGMENT_SPLIT_RE` as `(?:\|\||&&|[|;&\n])`; the two-character
  logical forms stay first so `&&` and `||` are consumed whole.
- Add `_strip_subshell()` and apply it in `_split_segments()`, removing leading
  `(` and trailing `)` (including nested wrappers) before tokenising.

Both forms now classify as contamination with reason class `manual_daemon_kill`,
and the record tool writes a durable marker for each. Direct-command behaviour is
unchanged. The contamination model, gated-task set, marker lifecycle, and
reconciler-only clearing path are untouched.

Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
This commit is contained in:
2026-07-21 19:56:00 -05:00
co-authored by Claude Opus 4.8
parent 35e94e107c
commit 6b58f04d39
2 changed files with 103 additions and 3 deletions
@@ -91,6 +91,44 @@ def test_compound_command_detects_the_kill_half():
assert result["contamination"] is True
# ── #787: background separator and subshell forms reach the classifier ───────
def test_background_separator_kill_is_contamination():
result = guard.classify_recovery_command("sleep 1 & pkill -f mcp_server.py")
assert result["process_kill"] is True
assert result["contamination"] is True
assert result["reason_class"] == guard.REASON_MANUAL_DAEMON_KILL
assert result["ambiguous"] is False
def test_subshell_wrapped_kill_is_contamination():
result = guard.classify_recovery_command("(pkill -f mcp_server.py)")
assert result["process_kill"] is True
assert result["contamination"] is True
assert result["reason_class"] == guard.REASON_MANUAL_DAEMON_KILL
assert result["ambiguous"] is False
def test_further_background_and_subshell_forms_are_contamination():
for command in (
"pkill -f mcp_server.py &",
"( sudo pkill -f mcp_server.py )",
"((pkill -f gitea_mcp_server))",
"sleep 1 & killall mcp_server",
"(ps aux | grep mcp_server) & pkill -f mcp_server.py",
):
result = guard.classify_recovery_command(command)
assert result["contamination"] is True, command
assert result["reason_class"] == guard.REASON_MANUAL_DAEMON_KILL, command
def test_logical_operators_are_not_split_into_single_characters():
# ``&&``/``||`` must still be consumed whole by the widened alternation.
assert guard._split_segments("a && b || c") == ["a", "b", "c"]
assert guard._split_segments("a & b") == ["a", "b"]
assert guard._split_segments("(a)") == ["a"]
# ── no false positives ───────────────────────────────────────────────────────
def test_read_only_inspection_is_not_a_kill():
@@ -112,6 +150,22 @@ def test_unrelated_pkill_target_is_not_contamination():
assert result["ambiguous"] is False
def test_user_scoped_pkill_of_unrelated_app_is_not_contamination():
# ``-u`` consumes ``mcpuser``; the surviving operand names no daemon (#787).
result = guard.classify_recovery_command("pkill -u mcpuser -f myapp")
assert result["process_kill"] is True
assert result["contamination"] is False
assert result["ambiguous"] is False
def test_commit_message_quoting_the_kill_string_is_not_a_kill():
result = guard.classify_recovery_command(
'git commit -m "block pkill -f mcp_server.py as workflow recovery"'
)
assert result["process_kill"] is False
assert result["contamination"] is False
def test_bare_kill_of_unknown_pid_is_ambiguous_not_contamination():
result = guard.classify_recovery_command("kill 31337")
assert result["contamination"] is False
@@ -333,6 +387,32 @@ def test_record_tool_marks_manual_daemon_kill():
assert "mcp_server.py" in loaded["command_summary"]
def test_record_tool_marks_background_separator_kill():
_clear_marker()
res = srv.gitea_record_daemon_process_kill_attempt(
command="sleep 1 & pkill -f mcp_server.py", remote="prgs"
)
assert res["contaminated"] is True
assert res["marked"] is True
assert res["marker"]["reason_class"] == guard.REASON_MANUAL_DAEMON_KILL
loaded = srv._load_runtime_recovery_marker("prgs")
assert loaded is not None
assert "mcp_server.py" in loaded["command_summary"]
def test_record_tool_marks_subshell_wrapped_kill():
_clear_marker()
res = srv.gitea_record_daemon_process_kill_attempt(
command="(pkill -f mcp_server.py)", remote="prgs"
)
assert res["contaminated"] is True
assert res["marked"] is True
assert res["marker"]["reason_class"] == guard.REASON_MANUAL_DAEMON_KILL
loaded = srv._load_runtime_recovery_marker("prgs")
assert loaded is not None
assert "mcp_server.py" in loaded["command_summary"]
def test_record_tool_marks_broad_sweep():
_clear_marker()
res = srv.gitea_record_daemon_process_kill_attempt(