#!/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 /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 # --------------------------------------------------------------------------- # per-test defaults and the dropped binding (S1-S3, S6, S7) # --------------------------------------------------------------------------- # Copied at import, like test_orc_onboard.SCRUBBED_ENV: the binding has to be # gone before collection, not merely before the first test (S6). _IMPORT_ENV = dict(os.environ) PROBE_ENV = "MAM_ISSUE20_PROBE" BINDING = ("WORKSPACE_ROOT", "AGENT_SESSIONS_YAML", "MAM_JOBS_DIR", "DELEGATE_JOB_LOGS_DIR") def _tree(root: Path) -> dict: return {str(p.relative_to(root)): hashlib.sha256(p.read_bytes()).hexdigest() if p.is_file() else None for p in sorted(root.rglob("*"))} def _binding(root: Path) -> dict: """The four variables a worktree creator's pane carries, aimed at `root`.""" mam = root / ".mam" return {"WORKSPACE_ROOT": str(root), "AGENT_SESSIONS_YAML": str(mam / "agent-sessions.yaml"), "MAM_JOBS_DIR": str(mam / "jobs"), "DELEGATE_JOB_LOGS_DIR": str(mam / "delegate_job_logs")} def test_s1_every_test_defaults_to_state_dirs_under_tmp_path(tmp_path, monkeypatch): from lib_py.delegation import mqtt_common state = tmp_path / ".mam-test-state" assert os.environ["MAM_JOBS_DIR"] == str(state / "jobs") assert os.environ["DELEGATE_JOB_LOGS_DIR"] == str(state / "delegate_job_logs") # a WORKSPACE_ROOT on a checkout with a .mam no longer decides where state goes monkeypatch.setenv("WORKSPACE_ROOT", str(_fake_control_plane(tmp_path / "repo"))) assert mqtt_common.default_registry_dir() == str(state / "jobs") assert mqtt_common.get_logs_dir() == str(state / "delegate_job_logs") def test_s2_mam_sandbox_overrides_the_default(mam_sandbox): assert os.environ["MAM_JOBS_DIR"] == str(mam_sandbox / ".mam" / "jobs") assert os.environ["DELEGATE_JOB_LOGS_DIR"] == str(mam_sandbox / ".mam" / "delegate_job_logs") def test_s3_submit_with_workspace_root_on_a_checkout_leaves_its_mam_alone(tmp_path): """The issue's acceptance check in small: WORKSPACE_ROOT names a checkout with a real-looking .mam and the test sets nothing else.""" repo = _fake_control_plane(tmp_path / "repo", sessions=("creator-real",)) before = _tree(repo) env = dict(os.environ, WORKSPACE_ROOT=str(repo), MAM_ENV_FILE=str(tmp_path / ".mam.env.absent"), PYTHONPATH=f"{SKILLS}:{os.environ.get('PYTHONPATH', '')}") res = subprocess.run( [sys.executable, "-m", "lib_py.delegation.cli", "submit", "--prompt", "issue 20 probe", "--agent", "claude-code", "--agent-session", "herdr:issue20-probe"], capture_output=True, text=True, env=env, cwd=str(REPO_ROOT), timeout=60, ) assert res.returncode == 0, res.stderr state = tmp_path / ".mam-test-state" records = list((state / "jobs").glob("*.json")) assert len(records) == 1, records assert (state / "delegate_job_logs" / records[0].stem).is_dir() assert _tree(repo) == before def test_s6_a_pane_binding_is_dropped_before_collection(tmp_path): """A pytest started with a worktree creator pane's binding - all four at another checkout F - sees none of it, not even in a module-level copy of os.environ, and leaves F untouched.""" fake_main = _fake_control_plane(tmp_path / "main", sessions=("creator-real",)) before = _tree(fake_main) env = dict(os.environ, **_binding(fake_main), **{PROBE_ENV: "1"}) # An explicit basetemp: the inner run must not clean up the outer one's. res = subprocess.run( [sys.executable, "-m", "pytest", f"{__file__}::test_s6_probe", "-q", "-p", "no:cacheprovider", f"--basetemp={tmp_path / 'inner'}"], capture_output=True, text=True, env=env, cwd=str(REPO_ROOT), timeout=300, ) assert res.returncode == 0, res.stdout[-4000:] + res.stderr[-2000:] assert "1 passed" in res.stdout, res.stdout[-2000:] assert _tree(fake_main) == before @pytest.mark.skipif(not os.environ.get(PROBE_ENV), reason="the inner half of S6 (nested pytest) only") def test_s6_probe(tmp_path): assert not [k for k in BINDING if k in _IMPORT_ENV], {k: _IMPORT_ENV[k] for k in BINDING if k in _IMPORT_ENV} assert "AGENT_SESSIONS_YAML" not in os.environ assert "WORKSPACE_ROOT" not in os.environ # it named another checkout state = tmp_path / ".mam-test-state" assert os.environ["MAM_JOBS_DIR"] == str(state / "jobs") assert os.environ["DELEGATE_JOB_LOGS_DIR"] == str(state / "delegate_job_logs") def test_s7_lib_sh_takes_the_session_registry_from_a_tests_workspace_root(tmp_path): """An ambient AGENT_SESSIONS_YAML (a worktree pane's) would win over the test's WORKSPACE_ROOT in lib.sh; conftest dropped it before collection.""" assert "AGENT_SESSIONS_YAML" not in os.environ repo = tmp_path / "repo" repo.mkdir() script = f'source "{SKILLS / "lib.sh"}" >/dev/null 2>&1; printf %s "$AGENT_SESSIONS_YAML"' res = subprocess.run(["bash", "-c", script], capture_output=True, text=True, env=dict(os.environ, WORKSPACE_ROOT=str(repo)), timeout=60) assert res.stdout == str(repo / ".mam" / "agent-sessions.yaml"), (res.stdout, res.stderr)