fix(issue-10,11,13,15): complete agy purge, orchestrator purge, workspace-anchored registry

Issue #10 - agy purge_artifacts left resumable pieces behind: it now also
removes the SQLite sidecars (-wal/-shm/-journal), the title annotation and
the presence lock (the lock only once no live process references the
conversation), and residual_artifacts() reports anything under
~/.gemini/antigravity-cli still carrying the uuid.

Issue #13 - the orchestrator has no herdr_sessions row, so its conversation
could not be purged by any skill. `lib_py.agents purge <agent|auto> <uuid>`
resolves the adapter from what is on disk (orchestrator_uuids stores bare
uuids), refuses while a live process names the uuid (conversation_in_use:
process list minus the caller's own lineage, plus lsof), and prints what it
purged. `orc_onboard.sh --remove <uuid> --purge-conversation --yes [--agent]`
runs it before the registry update so a refusal changes nothing (exit 4
without --yes, 5 while in use).

Issue #11 - "Successfully removeed": conjugate add/remove explicitly.

Issue #15 - the job registry and audit log followed the caller's cwd, so the
pytest suite (create_session.sh with its default onboarding job, run from the
repo root) had left 593 test records in the real .mam/jobs. Defaults now
resolve MAM_JOBS_DIR / DELEGATE_JOB_LOGS_DIR, then $WORKSPACE_ROOT/.mam/...,
then the cwd (mqtt_common.default_registry_dir / get_logs_dir; registry.py,
publish_event.py, service.py, create_session.sh, stop_session.sh); the
sandbox fixture pins both. The tier suites that used to leak now leave the
real registry untouched (881 records before and after).

Tests: test_issue10_13_purge.py (13), test_issue15_registry_isolation.py (7);
T-O13 pins the corrected message; the R1 helper test and B-9 logs-dir test
now assert the workspace-anchored contract; publish_event snapshot updated.

Refs #10 #11 #13 #15

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VCgu9Fa9iT7TbJUSzdq4Ff
This commit is contained in:
GodopuandClaude Fable 5.1 committed 2026-09-13 08:18:56 +09:00
1 parent bd3df890dc
commit c82ea75a15
20 files changed
+723 -33

No files matched your search

+6
View File
@@ -42,6 +42,12 @@ def mam_sandbox(tmp_path, monkeypatch):
monkeypatch.setenv("LOCAL_BIN", str(tmp_path / ".local" / "bin"))
monkeypatch.setenv("AGENT_SESSIONS_YAML", str(yaml_path))
monkeypatch.setenv("WORKSPACE_ROOT", str(tmp_path))
# Issue #15: the job registry and its audit log must land in the sandbox
# too, whatever the cwd of the script under test - not in the repo's own
# .mam/jobs. Explicit here even though the defaults now follow
# WORKSPACE_ROOT, so a test that unsets WORKSPACE_ROOT still stays inside.
monkeypatch.setenv("MAM_JOBS_DIR", str(mam_dir / "jobs"))
monkeypatch.setenv("DELEGATE_JOB_LOGS_DIR", str(mam_dir / "delegate_job_logs"))
# D6 (issue #5 phase 1): point the delegation env loader at a file that does not
# exist, so importing or running delegation code inside a sandbox never injects the
# real .mam.env into this process's os.environ.
+264
View File
@@ -0,0 +1,264 @@
#!/usr/bin/env python3
"""Issues #10 and #13 — purging a conversation must leave nothing resumable
behind, and an orchestrator conversation (no herdr_sessions row) must be
purgeable through orc_onboard.sh.
#10: the agy adapter deleted only the conversation DB and the brain dir; the
SQLite sidecars (-wal/-shm/-journal), the title annotation and the presence
lock survived. The lock is removed only once nothing references the
conversation any more.
#13: `orc_onboard.sh --remove <uuid> --purge-conversation --yes` resolves the
adapter from what is on disk (orchestrator_uuids stores bare UUIDs), purges
through it, and refuses while a live process still names the UUID.
"""
from __future__ import annotations
import json
import os
import sqlite3
import subprocess
import sys
import time
from pathlib import Path
import pytest
REPO_ROOT = Path(__file__).resolve().parent.parent
SKILLS = REPO_ROOT / ".agents" / "skills"
ONBOARD_SH = SKILLS / "multi-agent-mux-orc-onboard" / "scripts" / "orc_onboard.sh"
sys.path.insert(0, str(SKILLS))
from lib_py.agents.registry import get_adapter # noqa: E402
from lib_py.agents.base import DiscoveryContext, conversation_in_use # noqa: E402
UUID = "7d0b6f12-3a4c-4e5f-8a9b-0c1d2e3f4a5b"
OTHER = "11111111-2222-4333-8444-555555555555"
def _agy_tree(home: Path, uuid: str) -> dict:
root = home / ".gemini" / "antigravity-cli"
paths = {
"db": root / "conversations" / f"{uuid}.db",
"wal": root / "conversations" / f"{uuid}.db-wal",
"shm": root / "conversations" / f"{uuid}.db-shm",
"brain": root / "brain" / uuid,
"annotation": root / "annotations" / f"{uuid}.pbtxt",
"lock": root / "presence" / f"{uuid}.lock",
}
for key, p in paths.items():
if key == "brain":
p.mkdir(parents=True, exist_ok=True)
(p / "note.txt").write_text("brain")
elif key == "db":
# A real conversation DB: the adapter's verify_artifact opens it
# with sqlite3, and sqlite discards a garbage -wal next to a
# garbage main file, which would hide the sidecar from the purge.
p.parent.mkdir(parents=True, exist_ok=True)
conn = sqlite3.connect(p)
conn.execute("CREATE TABLE steps (id INTEGER)")
conn.execute("INSERT INTO steps VALUES (1)")
conn.commit()
conn.close()
else:
p.parent.mkdir(parents=True, exist_ok=True)
p.write_text("x" if key != "lock" else "")
return paths
def _holder(uuid: str) -> subprocess.Popen:
"""A live process whose command line names the conversation, the way a
resumed `agy --conversation <uuid>` or `claude -r <uuid>` does. (Not
`sh -c 'sleep …'`: a shell execs its last simple command and the uuid
would vanish from the process list.)"""
proc = subprocess.Popen([sys.executable, "-c", "import sys, time; time.sleep(60)", "--conversation", uuid])
time.sleep(0.3)
return proc
def _stop(proc: subprocess.Popen) -> None:
proc.kill()
proc.wait(timeout=10)
def _run_onboard(args, sandbox: Path, extra_env=None) -> subprocess.CompletedProcess:
env = dict(os.environ)
for k in ("CLAUDE_CODE_SESSION_ID", "ANTIGRAVITY_CONVERSATION_ID", "HERMES_SESSION_ID", "MAM_ORCHESTRATOR_UUIDS"):
env.pop(k, None)
env.update({
"PYTHONPATH": f"{SKILLS}:{env.get('PYTHONPATH', '')}",
"AGENT_SESSIONS_YAML": str(sandbox / ".mam" / "agent-sessions.yaml"),
"YAML_PATH": str(sandbox / ".mam" / "agent-sessions.yaml"),
"HOME_DIR": str(sandbox),
"AGENT_PYTHON_BIN": sys.executable,
"DELEGATE_JOB_PYTHON": sys.executable,
})
if extra_env:
env.update(extra_env)
return subprocess.run(["bash", str(ONBOARD_SH)] + list(args), capture_output=True, text=True,
env=env, cwd=str(sandbox), timeout=120)
def _registered(sandbox: Path, uuid: str) -> bool:
return uuid in _run_onboard(["--list"], sandbox).stdout
# ---------------------------------------------------------------------------
# #10 — agy adapter
# ---------------------------------------------------------------------------
def test_agy_purge_removes_sidecars_annotation_and_lock(tmp_path):
paths = _agy_tree(tmp_path, UUID)
adapter = get_adapter("agy")
ctx = DiscoveryContext(workspace=str(tmp_path), agent_name="agy", home_dir=str(tmp_path))
purged = adapter.purge_artifacts(UUID, ctx)
assert len(purged) == 6, purged
for key, p in paths.items():
assert not p.exists(), f"{key} survived the purge: {p}"
assert adapter.residual_artifacts(UUID, ctx) == []
def test_agy_purge_keeps_presence_lock_while_in_use(tmp_path):
paths = _agy_tree(tmp_path, UUID)
adapter = get_adapter("agy")
ctx = DiscoveryContext(workspace=str(tmp_path), agent_name="agy", home_dir=str(tmp_path))
holder = _holder(UUID)
try:
purged = adapter.purge_artifacts(UUID, ctx)
finally:
_stop(holder)
assert paths["lock"].exists(), "presence lock must survive while a process references the conversation"
assert str(paths["lock"]) not in purged
for key in ("db", "wal", "shm", "brain", "annotation"):
assert not paths[key].exists(), key
assert adapter.residual_artifacts(UUID, ctx) == [str(paths["lock"])]
def test_agy_purge_reports_only_what_existed(tmp_path):
"""The historical 2-item contract (db + brain) still holds when no sidecar
exists (test_a4_adapter_contract pins len == 2)."""
root = tmp_path / ".gemini" / "antigravity-cli"
(root / "conversations").mkdir(parents=True)
(root / "conversations" / f"{UUID}.db").write_text("db")
(root / "brain" / UUID).mkdir(parents=True)
adapter = get_adapter("agy")
ctx = DiscoveryContext(workspace=str(tmp_path), agent_name="agy", home_dir=str(tmp_path))
assert len(adapter.purge_artifacts(UUID, ctx)) == 2
def test_conversation_in_use_ignores_own_lineage():
"""The purge command names the uuid on its own command line (and its
parent shell does); only *other* processes count as holders."""
assert conversation_in_use(OTHER) is False
holder = _holder(OTHER)
try:
assert conversation_in_use(OTHER) is True
finally:
_stop(holder)
assert conversation_in_use(OTHER) is False
# ---------------------------------------------------------------------------
# #13 — lib_py.agents purge CLI
# ---------------------------------------------------------------------------
def _purge_cli(agent: str, uuid: str, home: Path) -> subprocess.CompletedProcess:
env = dict(os.environ, HOME_DIR=str(home), PYTHONPATH=f"{SKILLS}:{os.environ.get('PYTHONPATH', '')}")
return subprocess.run([sys.executable, "-m", "lib_py.agents", "purge", agent, uuid, str(home)],
capture_output=True, text=True, env=env, cwd=str(home), timeout=60)
def test_purge_cli_auto_resolves_agy_from_disk(tmp_path):
paths = _agy_tree(tmp_path, UUID)
res = _purge_cli("auto", UUID, tmp_path)
assert res.returncode == 0, res.stderr
out = json.loads(res.stdout)
assert out["agent"] == "agy"
assert len(out["purged"]) == 6 and out["residual"] == [] and out["in_use"] is False
assert not any(p.exists() for p in paths.values())
def test_purge_cli_refuses_while_in_use(tmp_path):
paths = _agy_tree(tmp_path, UUID)
holder = _holder(UUID)
try:
res = _purge_cli("agy", UUID, tmp_path)
finally:
_stop(holder)
assert res.returncode == 4, res.stdout + res.stderr
assert json.loads(res.stdout)["in_use"] is True
assert all(p.exists() for p in paths.values()), "a refused purge must remove nothing"
def test_purge_cli_unresolved_uuid(tmp_path):
res = _purge_cli("auto", OTHER, tmp_path)
assert res.returncode == 5, res.stdout + res.stderr
assert json.loads(res.stdout)["agent"] is None
# ---------------------------------------------------------------------------
# #13 — orc_onboard.sh --remove --purge-conversation
# ---------------------------------------------------------------------------
def test_orc_remove_purge_requires_yes(mam_sandbox):
paths = _agy_tree(mam_sandbox, UUID)
assert _run_onboard(["--uuid", UUID], mam_sandbox).returncode == 0
res = _run_onboard(["--remove", UUID, "--purge-conversation"], mam_sandbox)
assert res.returncode == 4, res.stdout + res.stderr
assert "Re-run with --yes" in res.stderr
assert all(p.exists() for p in paths.values())
assert _registered(mam_sandbox, UUID), "registration must be untouched without --yes"
def test_orc_remove_purge_deletes_and_unregisters(mam_sandbox):
paths = _agy_tree(mam_sandbox, UUID)
assert _run_onboard(["--uuid", UUID], mam_sandbox).returncode == 0
res = _run_onboard(["--remove", UUID, "--purge-conversation", "--yes"], mam_sandbox)
assert res.returncode == 0, res.stdout + res.stderr
assert "Successfully removed orchestrator UUID" in res.stdout
assert res.stdout.count("purged: ") == 6, res.stdout
assert "residual: none (agent: agy)" in res.stdout
assert not any(p.exists() for p in paths.values())
assert not _registered(mam_sandbox, UUID)
def test_orc_remove_purge_refused_while_in_use(mam_sandbox):
paths = _agy_tree(mam_sandbox, UUID)
assert _run_onboard(["--uuid", UUID], mam_sandbox).returncode == 0
holder = _holder(UUID)
try:
res = _run_onboard(["--remove", UUID, "--purge-conversation", "--yes"], mam_sandbox)
finally:
_stop(holder)
assert res.returncode == 5, res.stdout + res.stderr
assert "still in use" in res.stderr
assert all(p.exists() for p in paths.values())
assert _registered(mam_sandbox, UUID), "a refused purge must leave the registration in place"
def test_orc_remove_purge_without_artifacts_still_unregisters(mam_sandbox):
assert _run_onboard(["--uuid", UUID], mam_sandbox).returncode == 0
res = _run_onboard(["--remove", UUID, "--purge-conversation", "--yes"], mam_sandbox)
assert res.returncode == 0, res.stdout + res.stderr
assert "nothing to purge" in res.stderr
assert not _registered(mam_sandbox, UUID)
def test_orc_purge_flag_needs_remove(mam_sandbox):
res = _run_onboard(["--uuid", UUID, "--purge-conversation", "--yes"], mam_sandbox)
assert res.returncode == 2
assert not _registered(mam_sandbox, UUID)
def test_orc_dry_run_purge_changes_nothing(mam_sandbox):
paths = _agy_tree(mam_sandbox, UUID)
assert _run_onboard(["--uuid", UUID], mam_sandbox).returncode == 0
res = _run_onboard(["--remove", UUID, "--purge-conversation", "--yes", "--dry-run"], mam_sandbox)
assert res.returncode == 0
assert "purge its conversation artifacts" in res.stdout
assert all(p.exists() for p in paths.values())
assert _registered(mam_sandbox, UUID)
+120
View File
@@ -0,0 +1,120 @@
#!/usr/bin/env python3
"""Issue #15 — the job registry and its audit log follow the workspace, not
the caller's cwd.
`DEFAULT_REGISTRY_DIR` (".mam/jobs") and the audit-log root were resolved
relative to the current directory, so `create_session.sh`'s default onboarding
job — registered through `lib_py.delegation.cli submit` without a
`--registry-dir` — landed in whatever `.mam/jobs` sat under the cwd. Run from
the repo root, the pytest suite left hundreds of `running` test records in the
real registry. The defaults now honour `MAM_JOBS_DIR` / `DELEGATE_JOB_LOGS_DIR`,
then `$WORKSPACE_ROOT/.mam/...`, and only then the cwd.
"""
from __future__ import annotations
import json
import os
import subprocess
import sys
from pathlib import Path
REPO_ROOT = Path(__file__).resolve().parent.parent
SKILLS = REPO_ROOT / ".agents" / "skills"
REAL_JOBS = REPO_ROOT / ".mam" / "jobs"
REAL_LOGS = REPO_ROOT / ".mam" / "delegate_job_logs"
sys.path.insert(0, str(SKILLS))
from lib_py.delegation import mqtt_common # noqa: E402
def _listing(d: Path) -> set:
return set(os.listdir(d)) if d.is_dir() else set()
# ---------------------------------------------------------------------------
# resolution order
# ---------------------------------------------------------------------------
def test_registry_dir_env_wins(monkeypatch, tmp_path):
monkeypatch.setenv("MAM_JOBS_DIR", str(tmp_path / "explicit"))
monkeypatch.setenv("WORKSPACE_ROOT", str(tmp_path))
assert mqtt_common.default_registry_dir() == str(tmp_path / "explicit")
def test_registry_dir_follows_workspace_root(monkeypatch, tmp_path):
monkeypatch.delenv("MAM_JOBS_DIR", raising=False)
monkeypatch.setenv("WORKSPACE_ROOT", str(tmp_path))
assert mqtt_common.default_registry_dir() == str(tmp_path / ".mam" / "jobs")
def test_registry_dir_falls_back_to_cwd_relative(monkeypatch, tmp_path):
monkeypatch.delenv("MAM_JOBS_DIR", raising=False)
monkeypatch.delenv("WORKSPACE_ROOT", raising=False)
assert mqtt_common.default_registry_dir() == ".mam/jobs"
# A WORKSPACE_ROOT that is not a directory is ignored, not trusted.
monkeypatch.setenv("WORKSPACE_ROOT", str(tmp_path / "does-not-exist"))
assert mqtt_common.default_registry_dir() == ".mam/jobs"
def test_logs_dir_follows_the_same_order(monkeypatch, tmp_path):
monkeypatch.setenv("DELEGATE_JOB_LOGS_DIR", str(tmp_path / "logs"))
monkeypatch.setenv("WORKSPACE_ROOT", str(tmp_path))
assert mqtt_common.get_logs_dir() == str(tmp_path / "logs")
monkeypatch.delenv("DELEGATE_JOB_LOGS_DIR")
assert mqtt_common.get_logs_dir() == str(tmp_path / ".mam" / "delegate_job_logs")
monkeypatch.delenv("WORKSPACE_ROOT")
assert mqtt_common.get_logs_dir() == os.path.join(os.getcwd(), ".mam", "delegate_job_logs")
def test_cli_defaults_are_resolved_per_process(monkeypatch, tmp_path):
"""registry.py / publish_event.py build their argparse defaults at call
time, so a process started with WORKSPACE_ROOT set registers there."""
monkeypatch.delenv("MAM_JOBS_DIR", raising=False)
env = dict(os.environ, WORKSPACE_ROOT=str(tmp_path), PYTHONPATH=f"{SKILLS}:{os.environ.get('PYTHONPATH', '')}")
env.pop("MAM_JOBS_DIR", None)
res = subprocess.run(
[sys.executable, "-m", "lib_py.delegation.cli", "submit", "--prompt", "issue 15", "--agent", "claude-code",
"--agent-session", "herdr:issue15-probe"],
capture_output=True, text=True, env=env, cwd=str(REPO_ROOT), timeout=60,
)
assert res.returncode == 0, res.stderr
records = list((tmp_path / ".mam" / "jobs").glob("*.json"))
assert len(records) == 1, records
assert json.loads(records[0].read_text())["agent_session"] == "herdr:issue15-probe"
# ---------------------------------------------------------------------------
# the leak itself: create_session.sh's onboarding job from the repo root cwd
# ---------------------------------------------------------------------------
def _create_session_from_repo_root(sandbox: Path, session: str) -> subprocess.CompletedProcess:
script = sandbox / ".agents" / "skills" / "multi-agent-mux-create" / "scripts" / "create_session.sh"
# cwd deliberately the repo root — the exact shape of the leaking tests.
return subprocess.run(
["bash", str(script), "--workspace", str(sandbox), "--agent", "claude", "--role", "Creator",
"--session", session],
capture_output=True, text=True, cwd=str(REPO_ROOT), timeout=180,
)
def _assert_registered_in_sandbox_only(sandbox: Path, session: str, before_jobs: set, before_logs: set, res):
assert res.returncode == 0, res.stderr + res.stdout
assert _listing(REAL_JOBS) == before_jobs, "onboarding job leaked into the repo's .mam/jobs"
assert _listing(REAL_LOGS) == before_logs, "audit log leaked into the repo's .mam/delegate_job_logs"
records = [json.loads(p.read_text()) for p in (sandbox / ".mam" / "jobs").glob("*.json")]
assert any(r.get("agent_session") == f"herdr:{session}" for r in records), records
def test_onboarding_job_stays_in_sandbox_with_explicit_env(mam_sandbox, mock_herdr, mock_agents):
before_jobs, before_logs = _listing(REAL_JOBS), _listing(REAL_LOGS)
res = _create_session_from_repo_root(mam_sandbox, "issue15-explicit-creator-claude")
_assert_registered_in_sandbox_only(mam_sandbox, "issue15-explicit-creator-claude", before_jobs, before_logs, res)
def test_onboarding_job_follows_workspace_root_alone(mam_sandbox, mock_herdr, mock_agents, monkeypatch):
"""Without the explicit MAM_JOBS_DIR / DELEGATE_JOB_LOGS_DIR overrides the
WORKSPACE_ROOT that lib.sh exports must be enough to keep the record out
of the repo's registry."""
monkeypatch.delenv("MAM_JOBS_DIR", raising=False)
monkeypatch.delenv("DELEGATE_JOB_LOGS_DIR", raising=False)
before_jobs, before_logs = _listing(REAL_JOBS), _listing(REAL_LOGS)
res = _create_session_from_repo_root(mam_sandbox, "issue15-wsroot-creator-claude")
_assert_registered_in_sandbox_only(mam_sandbox, "issue15-wsroot-creator-claude", before_jobs, before_logs, res)
+12 -3
View File
@@ -314,7 +314,9 @@ def test_publish_event_cli_contract_snapshot(mam_sandbox):
# Defaults that shell and wrapper callers depend on.
src = Path(publish_event.__file__).read_text(encoding="utf-8")
assert '"--attempts", type=int, default=3' in src
assert '"--registry-dir", default=DEFAULT_REGISTRY_DIR' in src
# Issue #15: resolved per process (MAM_JOBS_DIR, then WORKSPACE_ROOT, then
# the cwd-relative DEFAULT_REGISTRY_DIR) instead of the bare constant.
assert '"--registry-dir", default=default_registry_dir()' in src
assert '"--event", default="progress", choices=VALID_EVENTS' in src
@@ -1063,8 +1065,15 @@ def test_r1_shell_helper_ignores_a_lib_py_in_the_working_directory(mam_sandbox,
assert res.returncode == 0, res.stderr
job_id = res.stdout.strip()
assert re.fullmatch(r"[0-9a-f]+", job_id), repr(res.stdout)
assert (decoy / ".mam" / "jobs" / (job_id + ".json")).exists(), (
"the real cli should have registered the job in the cwd registry"
# Issue #15: the registry follows MAM_JOBS_DIR / WORKSPACE_ROOT (both point
# at the sandbox here), no longer the cwd — the decoy workspace's own
# .mam/jobs must stay empty.
registry = Path(env["MAM_JOBS_DIR"])
assert (registry / (job_id + ".json")).exists(), (
"the real cli should have registered the job in the sandbox registry"
)
assert not (decoy / ".mam" / "jobs" / (job_id + ".json")).exists(), (
"the job must not be registered relative to the cwd"
)
+2
View File
@@ -242,6 +242,8 @@ def test_o13_onboard_remove_uuid(mam_sandbox):
res = run_onboard(["--remove", orc_uuid], env=env, cwd=str(mam_sandbox))
assert res.returncode == 0
# Issue #11: "removeed" was the naive ${MODE}ed conjugation.
assert "Successfully removed orchestrator UUID" in res.stdout, res.stdout
res_list = run_onboard(["--list"], env=env, cwd=str(mam_sandbox))
assert orc_uuid not in res_list.stdout
+3
View File
@@ -493,6 +493,9 @@ def test_b9_logs_dir_follows_cwd_changes(mam_sandbox, tmp_path, monkeypatch):
"""B-9: the audit-log root must be resolved per call, not frozen at import."""
mq = get_mqtt_common(mam_sandbox)
monkeypatch.delenv("DELEGATE_JOB_LOGS_DIR", raising=False)
# Issue #15: with WORKSPACE_ROOT set the root is anchored on the workspace
# instead; the cwd only decides when neither override is present.
monkeypatch.delenv("WORKSPACE_ROOT", raising=False)
a = tmp_path / "a"; b = tmp_path / "b"
a.mkdir(); b.mkdir()