feat: update admission gate - entries refuse while an update runs (Issue #72, decision 8, U2)
The update skill publishes .mam/update-in-progress (pid + lstart, the loop_lock.sh rules) while it holds .mam/update-admission.lock exclusively. create, resume, run_loop.sh and delegate submit (decision 8) and stop and orc-onboard (U2: a rollback would restore the registry without their write) take that lock shared (lib.sh mam_update_admit, fd 7), refuse while the marker is live or unknown, and hold the lock until their record is written. A stale marker refuses nothing. lib_py.pane_lock acquire gains --shared and --wait-env (MAM_UPDATE_ADMISSION_WAIT_S, default 120); create's wrapper path closes fd 7 for the long-lived child. The exit-1 rows of create/resume/stop name the refusal; skill_code_blocks.json pins follow the shifted lines. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
GodopuandClaude Opus 5.5 committed
1 parent
179473e5d5
commit
6359d65999
13 files changed
+311
-25
No files matched your search
@@ -11,7 +11,7 @@
|
||||
"kind": "example",
|
||||
"evidence": [
|
||||
"multi-agent-mux-create/scripts/create_session.sh:99",
|
||||
"multi-agent-mux-create/scripts/create_session.sh:356"
|
||||
"multi-agent-mux-create/scripts/create_session.sh:359"
|
||||
],
|
||||
"mismatch": null,
|
||||
"note": "HERDR_SESSION_NAME environment example"
|
||||
@@ -67,7 +67,7 @@
|
||||
"class": "c",
|
||||
"kind": "example",
|
||||
"evidence": [
|
||||
"multi-agent-mux-create/scripts/create_session.sh:514-541"
|
||||
"multi-agent-mux-create/scripts/create_session.sh:517-544"
|
||||
],
|
||||
"mismatch": null,
|
||||
"note": "Output format: the row create_session.sh writes"
|
||||
@@ -122,7 +122,7 @@
|
||||
"class": "c",
|
||||
"kind": "invocation",
|
||||
"evidence": [
|
||||
"multi-agent-mux-delegate-job/multi-agent-mux-delegate-job:1046-1057"
|
||||
"multi-agent-mux-delegate-job/multi-agent-mux-delegate-job:1051-1062"
|
||||
],
|
||||
"mismatch": null,
|
||||
"note": "CLI reference; subcommands submit/status/list/verify/wait/logs match main()"
|
||||
@@ -433,7 +433,7 @@
|
||||
"class": "c",
|
||||
"kind": "diagram",
|
||||
"evidence": [
|
||||
"multi-agent-mux-stop/scripts/stop_session.sh:245-259"
|
||||
"multi-agent-mux-stop/scripts/stop_session.sh:250-264"
|
||||
],
|
||||
"mismatch": null,
|
||||
"note": "state machine"
|
||||
@@ -477,10 +477,10 @@
|
||||
"multi-agent-mux-resume/scripts/resume_session.sh:111-130",
|
||||
"multi-agent-mux-resume/scripts/resume_session.sh:133-144",
|
||||
"multi-agent-mux-resume/scripts/resume_session.sh:147-170",
|
||||
"multi-agent-mux-resume/scripts/resume_session.sh:185-210",
|
||||
"multi-agent-mux-resume/scripts/resume_session.sh:258",
|
||||
"multi-agent-mux-resume/scripts/resume_session.sh:262",
|
||||
"multi-agent-mux-resume/scripts/resume_session.sh:268-271",
|
||||
"multi-agent-mux-resume/scripts/resume_session.sh:188-213",
|
||||
"multi-agent-mux-resume/scripts/resume_session.sh:265",
|
||||
"multi-agent-mux-resume/scripts/resume_session.sh:269",
|
||||
"multi-agent-mux-resume/scripts/resume_session.sh:275-278",
|
||||
"lib_py/agents/adapters/claude.py:109"
|
||||
],
|
||||
"mismatch": [
|
||||
@@ -504,8 +504,8 @@
|
||||
"class": "a",
|
||||
"evidence": [
|
||||
"multi-agent-mux-stop/scripts/stop_session.sh:101",
|
||||
"multi-agent-mux-stop/scripts/stop_session.sh:123-193",
|
||||
"multi-agent-mux-stop/scripts/stop_session.sh:245-249"
|
||||
"multi-agent-mux-stop/scripts/stop_session.sh:128-198",
|
||||
"multi-agent-mux-stop/scripts/stop_session.sh:250-254"
|
||||
],
|
||||
"mismatch": [
|
||||
"T1: the doc offered --force-no-yaml, which no script accepts"
|
||||
@@ -547,8 +547,8 @@
|
||||
"multi-agent-mux-create/scripts/create_session.sh:166-168",
|
||||
"multi-agent-mux-create/scripts/create_session.sh:207",
|
||||
"multi-agent-mux-create/scripts/create_session.sh:259-274",
|
||||
"multi-agent-mux-create/scripts/create_session.sh:361-398",
|
||||
"multi-agent-mux-create/scripts/create_session.sh:410-412"
|
||||
"multi-agent-mux-create/scripts/create_session.sh:364-401",
|
||||
"multi-agent-mux-create/scripts/create_session.sh:413-415"
|
||||
],
|
||||
"mismatch": [
|
||||
"C1: an existing session is exit 1 in the doc, exit 3 in the script",
|
||||
@@ -568,7 +568,7 @@
|
||||
"base_sha": "f71be0f26fb8",
|
||||
"class": "a",
|
||||
"evidence": [
|
||||
"multi-agent-mux-create/scripts/create_session.sh:486-604"
|
||||
"multi-agent-mux-create/scripts/create_session.sh:489-607"
|
||||
],
|
||||
"mismatch": [],
|
||||
"replacement": "bash .agents/skills/multi-agent-mux-create/scripts/create_session.sh --workspace <path> --agent <agent> --role <role>",
|
||||
@@ -601,7 +601,7 @@
|
||||
"other"
|
||||
],
|
||||
"passthrough": {
|
||||
"1": "multi-agent-mux-stop/scripts/stop_session.sh:384"
|
||||
"1": "multi-agent-mux-stop/scripts/stop_session.sh:389"
|
||||
}
|
||||
},
|
||||
"multi-agent-mux-create/scripts/create_session.sh": {
|
||||
@@ -619,7 +619,7 @@
|
||||
"other"
|
||||
],
|
||||
"passthrough": {
|
||||
"4": "multi-agent-mux-create/scripts/create_session.sh:546"
|
||||
"4": "multi-agent-mux-create/scripts/create_session.sh:549"
|
||||
}
|
||||
}
|
||||
},
|
||||
|
||||
@@ -0,0 +1,196 @@
|
||||
"""Issue #72 (decision 8, U2): while an update runs, the entries that start
|
||||
something or write the registry refuse - create, resume, run_loop.sh, delegate
|
||||
submit, stop (plain and --purge-conversation) and orc-onboard - and change
|
||||
nothing. A marker its update left behind (`stale`) refuses nothing.
|
||||
|
||||
The marker is .mam/update-in-progress as the update skill publishes it (pid +
|
||||
lstart, loop_lock.sh); `live` here is a sleeping helper process's.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
import yaml
|
||||
|
||||
UUID = "11111111-2222-3333-4444-555555555555"
|
||||
ORC = "99999999-8888-7777-6666-555555555555"
|
||||
ORC_OLD = "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def marker(mam_sandbox):
|
||||
procs = []
|
||||
|
||||
def make(live: bool):
|
||||
p = mam_sandbox / ".mam" / "update-in-progress"
|
||||
if live:
|
||||
proc = subprocess.Popen(["sleep", "120"], start_new_session=True)
|
||||
procs.append(proc)
|
||||
ls = " ".join(subprocess.run(["ps", "-p", str(proc.pid), "-o", "lstart="],
|
||||
capture_output=True, text=True).stdout.split())
|
||||
p.write_text("pid=%d\nlstart=%s\nstarted=x\n" % (proc.pid, ls))
|
||||
else:
|
||||
dead = subprocess.Popen(["true"])
|
||||
dead.wait()
|
||||
p.write_text("pid=%d\nlstart=Thu Jan 1 00:00:00 1970\nstarted=x\n" % dead.pid)
|
||||
return p
|
||||
|
||||
yield make
|
||||
for proc in procs:
|
||||
proc.kill()
|
||||
proc.wait()
|
||||
|
||||
|
||||
def _seed(sandbox, rows, **top):
|
||||
lib = sandbox / ".agents" / "skills" / "lib.sh"
|
||||
mutation = "d['herdr_sessions'] = %r\n" % (rows,) + "".join("d[%r] = %r\n" % kv for kv in top.items())
|
||||
res = subprocess.run(["bash", "-c", 'source "$1" && atomic_dump_yaml "$AGENT_SESSIONS_YAML"', "_", str(lib)],
|
||||
input=mutation, capture_output=True, text=True)
|
||||
assert res.returncode == 0, res.stderr
|
||||
|
||||
|
||||
def _registry(sandbox):
|
||||
out = {}
|
||||
for f in ("agent-sessions.yaml", "agent-sessions.db"):
|
||||
p = sandbox / ".mam" / f
|
||||
out[f] = hashlib.sha256(p.read_bytes()).hexdigest() if p.exists() else None
|
||||
return out
|
||||
|
||||
|
||||
def _script(sandbox, rel):
|
||||
return str(sandbox / ".agents" / "skills" / rel)
|
||||
|
||||
|
||||
def _run(sandbox, argv, env=None, timeout=120):
|
||||
return subprocess.run(argv, capture_output=True, text=True, cwd=str(sandbox), timeout=timeout,
|
||||
env=dict(os.environ, **(env or {})), stdin=subprocess.DEVNULL)
|
||||
|
||||
|
||||
def _refused(res, sandbox):
|
||||
assert res.returncode != 0, res.stdout + res.stderr
|
||||
assert "an update of %s is in progress" % sandbox in res.stderr, res.stdout + res.stderr
|
||||
|
||||
|
||||
def _row(name, status="running", agent="claude"):
|
||||
r = {"name": name, "status": status, "role": "creator", "herdr_session": "default", "herdr_server": "default",
|
||||
"pane": {"cwd": "", "cmd": agent}, "agent": agent}
|
||||
if agent == "claude":
|
||||
r["claude_session_id_own"] = UUID
|
||||
return r
|
||||
|
||||
|
||||
def _agent(cwd, pane):
|
||||
return {"agent": "claude", "status": "running", "cwd": str(cwd), "workspace_id": "w1",
|
||||
"pid": 9999, "pane_id": pane, "command": "claude", "buffer": "Ready"}
|
||||
|
||||
|
||||
def _set_mock(state_file, **kw):
|
||||
st = json.loads(Path(state_file).read_text())
|
||||
st.update(kw)
|
||||
Path(state_file).write_text(json.dumps(st))
|
||||
|
||||
|
||||
def test_create_refuses_while_an_update_runs(mam_sandbox, mock_herdr, mock_agents, marker):
|
||||
marker(True)
|
||||
before = _registry(mam_sandbox)
|
||||
res = _run(mam_sandbox, ["bash", _script(mam_sandbox, "multi-agent-mux-create/scripts/create_session.sh"),
|
||||
"--workspace", str(mam_sandbox), "--agent", "claude", "--role", "creator",
|
||||
"--session", "gated-create", "--no-onboard"], timeout=300)
|
||||
_refused(res, mam_sandbox)
|
||||
assert _registry(mam_sandbox) == before
|
||||
assert json.loads(Path(mock_herdr).read_text())["agents"] == {}, "nothing was spawned"
|
||||
|
||||
|
||||
def test_resume_refuses_on_the_spawn_and_the_alive_path(mam_sandbox, mock_herdr, mock_agents, marker):
|
||||
_seed(mam_sandbox, [dict(_row("gated-agy", status="stopped", agent="agy"), pane={"cwd": str(mam_sandbox), "cmd": "agy"})])
|
||||
marker(True)
|
||||
before = _registry(mam_sandbox)
|
||||
script = _script(mam_sandbox, "multi-agent-mux-resume/scripts/resume_session.sh")
|
||||
res = _run(mam_sandbox, ["bash", script, "--workspace", str(mam_sandbox), "--agent", "agy",
|
||||
"--session", "gated-agy"], timeout=300)
|
||||
_refused(res, mam_sandbox)
|
||||
assert _registry(mam_sandbox) == before
|
||||
assert json.loads(Path(mock_herdr).read_text())["agents"] == {}, "nothing was spawned"
|
||||
|
||||
_set_mock(mock_herdr, agents={"gated-agy": _agent(mam_sandbox, "w1:p9")})
|
||||
res = _run(mam_sandbox, ["bash", script, "--workspace", str(mam_sandbox), "--agent", "agy",
|
||||
"--session", "gated-agy"], timeout=300)
|
||||
_refused(res, mam_sandbox)
|
||||
assert _registry(mam_sandbox) == before
|
||||
|
||||
|
||||
def test_run_loop_refuses_before_its_loop_marker(mam_sandbox, marker):
|
||||
marker(True)
|
||||
loop_marker = mam_sandbox / ".mam" / "loop-guard-active"
|
||||
res = _run(mam_sandbox, ["bash", _script(mam_sandbox, "multi-agent-mux-loop/scripts/run_loop.sh"),
|
||||
"--creator", "c", "--task", "t"],
|
||||
env={"MAM_LOOP_NO_FREEZE": "1", "MAM_REAL_ROOT": str(mam_sandbox)})
|
||||
_refused(res, mam_sandbox)
|
||||
assert not loop_marker.exists()
|
||||
|
||||
|
||||
def test_delegate_submit_registers_no_job(mam_sandbox, mock_herdr, marker):
|
||||
marker(True)
|
||||
res = _run(mam_sandbox, ["bash", _script(mam_sandbox, "multi-agent-mux-delegate-job/multi-agent-mux-delegate-job"),
|
||||
"submit", "--agent", "claude-code", "--agent-session", "herdr:anyone", "--prompt", "hi"])
|
||||
_refused(res, mam_sandbox)
|
||||
jobs = mam_sandbox / ".mam" / "jobs"
|
||||
assert not list(jobs.glob("*.json")) if jobs.exists() else True
|
||||
|
||||
|
||||
@pytest.mark.parametrize("purge", [False, True])
|
||||
def test_stop_refuses_and_changes_nothing(mam_sandbox, mock_herdr, marker, purge):
|
||||
_seed(mam_sandbox, [_row("gated-stop")])
|
||||
_set_mock(mock_herdr, agents={"gated-stop": _agent(mam_sandbox, "w1:p8")})
|
||||
marker(True)
|
||||
before = _registry(mam_sandbox)
|
||||
extra = ["--purge-conversation", "--yes"] if purge else []
|
||||
res = _run(mam_sandbox, ["bash", _script(mam_sandbox, "multi-agent-mux-stop/scripts/stop_session.sh"),
|
||||
"--session", "gated-stop", "--agent", "claude", *extra])
|
||||
_refused(res, mam_sandbox)
|
||||
assert _registry(mam_sandbox) == before
|
||||
assert "gated-stop" in json.loads(Path(mock_herdr).read_text())["agents"], "the session was not touched"
|
||||
assert not (mam_sandbox / ".mam" / "purging-gated-stop").exists()
|
||||
|
||||
|
||||
def test_orc_onboard_refuses_and_changes_nothing(mam_sandbox, marker):
|
||||
_seed(mam_sandbox, [], orchestrator_uuids=[ORC_OLD])
|
||||
marker(True)
|
||||
before = _registry(mam_sandbox)
|
||||
script = _script(mam_sandbox, "multi-agent-mux-orc-onboard/scripts/orc_onboard.sh")
|
||||
for args in (["--uuid", ORC], ["--remove", ORC_OLD]):
|
||||
res = _run(mam_sandbox, ["bash", script, *args])
|
||||
_refused(res, mam_sandbox)
|
||||
assert _registry(mam_sandbox) == before
|
||||
|
||||
|
||||
def test_a_stale_marker_refuses_nothing(mam_sandbox, mock_herdr, marker):
|
||||
_seed(mam_sandbox, [_row("stale-stop")], orchestrator_uuids=[])
|
||||
_set_mock(mock_herdr, agents={"stale-stop": _agent(mam_sandbox, "w1:p7")})
|
||||
marker(False)
|
||||
res = _run(mam_sandbox, ["bash", _script(mam_sandbox, "multi-agent-mux-orc-onboard/scripts/orc_onboard.sh"),
|
||||
"--uuid", ORC])
|
||||
assert res.returncode == 0, res.stdout + res.stderr
|
||||
assert "stale update marker" in res.stderr
|
||||
res = _run(mam_sandbox, ["bash", _script(mam_sandbox, "multi-agent-mux-stop/scripts/stop_session.sh"),
|
||||
"--session", "stale-stop", "--agent", "claude"])
|
||||
assert res.returncode == 0, res.stdout + res.stderr
|
||||
d = yaml.safe_load((mam_sandbox / ".mam" / "agent-sessions.yaml").read_text())
|
||||
assert d["orchestrator_uuids"] == [ORC]
|
||||
assert {r["name"]: r["status"] for r in d["herdr_sessions"]} == {"stale-stop": "stopped"}
|
||||
|
||||
|
||||
def test_the_admission_lock_is_released_after_the_record(mam_sandbox, marker):
|
||||
"""An entry takes the lock shared and drops it once its record is written:
|
||||
a later exclusive taker (the update) gets it at once."""
|
||||
lib = mam_sandbox / ".agents" / "skills" / "lib.sh"
|
||||
res = subprocess.run(["bash", "-c", 'source "$1" && mam_update_admit && mam_update_admit_release && '
|
||||
'exec 7>>"$WORKSPACE_ROOT/.mam/update-admission.lock" && '
|
||||
'MAM_UPDATE_ADMISSION_WAIT_S=1 python3 -m lib_py.pane_lock acquire --fd 7 --wait-env MAM_UPDATE_ADMISSION_WAIT_S',
|
||||
"_", str(lib)], capture_output=True, text=True, timeout=60)
|
||||
assert res.returncode == 0 and res.stdout.strip() == "locked", res.stdout + res.stderr
|
||||
Reference in new issue
Block a user