test(issue-20): session guard for new entries in the recorded control planes' .mam/jobs and .mam/delegate_job_logs

Watches this checkout's .mam and the ones the recorded binding named. A new entry is a leak when it is an audit log without a registry record, or when its agent_session is missing or not a registered session; live delegations write the record first and target a registered session. Reports, never deletes. The #19 guard's docstring pointed at a #15 session guard that never existed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Sdga4A8i1iSc8DaaW9iKU2

tests/test_issue20_state_isolation.py

@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+"""Issue #20 - test state stays out of every real control plane.
+
+conftest records the control-plane binding an agent pane carries and drops it
+before collection (pytest_configure), gives every test a registry and an
+audit-log root under its own tmp_path (_isolate_mam_state_dirs), and a
+session guard reports new entries in a real `.mam/jobs` or
+`.mam/delegate_job_logs` (mam_state_leak_guard, helpers in _mam_state_guard).
+"""
+from __future__ import annotations
+
+import hashlib
+import json
+import os
+import subprocess
+import sys
+from pathlib import Path
+
+import pytest
+
+import _mam_state_guard as guard
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+SKILLS = REPO_ROOT / ".agents" / "skills"
+
+
+def _fake_control_plane(root: Path, sessions=()) -> Path:
+    """A checkout-shaped tree with a `.mam` registry, audit-log root and session yaml."""
+    mam = root / ".mam"
+    (mam / "jobs").mkdir(parents=True)
+    (mam / "delegate_job_logs").mkdir()
+    rows = "".join(f"- name: {s}\n  status: running\n  mcp_attachments:\n  - name: stitch\n" for s in sessions)
+    (mam / "agent-sessions.yaml").write_text("herdr_sessions:\n" + rows if rows else "herdr_sessions: []\n")
+    return root
+
+
+def _record(mam: Path, jid: str, session) -> None:
+    rec = {"job_id": jid, "prompt": f"prompt of {jid}"}
+    if session:
+        rec["agent_session"] = session
+    (mam / "jobs" / f"{jid}.json").write_text(json.dumps(rec))
+
+
+def _log(mam: Path, jid: str, session=None) -> None:
+    d = mam / "delegate_job_logs" / jid
+    d.mkdir()
+    if session:
+        (d / "meta.json").write_text(json.dumps({"job_id": jid, "agent_session": session}))
+
+
+# ---------------------------------------------------------------------------
+# the session guard (S4, S5)
+# ---------------------------------------------------------------------------
+def test_s4_guard_flags_only_entries_no_live_delegation_explains(tmp_path):
+    main = _fake_control_plane(tmp_path / "main", sessions=("creator-real",))
+    mam = main / ".mam"
+    _record(mam, "old00001", "herdr:nobody")        # before the snapshot: not judged
+    _log(mam, "old00001")
+    recorded = {"WORKSPACE_ROOT": str(main)}
+    roots = guard.watch_roots(tmp_path / "repo", recorded)
+    before = guard.snapshot(roots, recorded)
+
+    _record(mam, "live0001", "herdr:creator-real")  # a live delegation: record first, registered session
+    _log(mam, "live0001", "herdr:creator-real")
+    _record(mam, "live0002", "remote:creator-real")
+    _log(mam, "orphan01", "herdr:creator-real")     # (a) audit log with no record, even for a known session
+    _record(mam, "stray001", "herdr:nobody")         # (b) unknown session
+    _record(mam, "stitch01", "herdr:stitch")         # (b) `stitch` is an mcp attachment, not a session
+    _record(mam, "anon0001", None)                   # (b) no session at all
+
+    found = {Path(f["path"]).name: f for f in guard.leaks(roots, before, recorded)}
+    assert sorted(found) == ["anon0001.json", "orphan01", "stitch01.json", "stray001.json"], found
+    assert found["orphan01"]["reason"] == "audit log without a registry record"
+    assert found["anon0001.json"]["reason"] == "no agent_session"
+    assert found["stray001.json"]["reason"] == "agent_session names no registered session"
+    assert found["stray001.json"]["prompt"] == "prompt of stray001"
+    assert "orphan01" in guard.describe(list(found.values()))
+
+
+def test_s5_watch_roots_follow_the_recorded_binding(tmp_path):
+    repo = _fake_control_plane(tmp_path / "repo")
+    main = _fake_control_plane(tmp_path / "main")
+    (tmp_path / "main-link").symlink_to(main)
+    own, other = str((repo / ".mam").resolve()), str((main / ".mam").resolve())
+
+    assert guard.watch_roots(repo, {}) == [own]
+    # WORKSPACE_ROOT naming this checkout is counted once
+    assert guard.watch_roots(repo, {"WORKSPACE_ROOT": str(repo)}) == [own]
+    # a worktree creator's pane: all four at another checkout, reached through a symlink too
+    pane = {"WORKSPACE_ROOT": str(tmp_path / "main-link"),
+            "AGENT_SESSIONS_YAML": str(main / ".mam" / "agent-sessions.yaml"),
+            "MAM_JOBS_DIR": str(main / ".mam" / "jobs"),
+            "DELEGATE_JOB_LOGS_DIR": str(main / ".mam" / "delegate_job_logs")}
+    assert guard.watch_roots(repo, pane) == [own, other]
+    # a recorded root that does not exist is skipped; the checkout's own .mam never is
+    bare = tmp_path / "bare"
+    assert guard.watch_roots(bare, {"WORKSPACE_ROOT": str(tmp_path / "gone")}) == [str((bare / ".mam").resolve())]
+    # a registry outside any <root>/jobs is watched directly
+    odd = tmp_path / "elsewhere" / "registry"
+    odd.mkdir(parents=True)
+    rec = {"MAM_JOBS_DIR": str(odd)}
+    jobs, logs = guard.state_dirs(guard.watch_roots(repo, rec), rec)
+    assert str(odd.resolve()) in jobs and str(odd.resolve()) not in logs