mirror of
https://github.com/hansjone/netx.git
synced 2026-10-17 14:33:18 +08:00
oliver
52679a7cfc
- netx_api/mcp_remote: ops / topology / bizMonitor tools, Bearer auth, per-tool RBAC filtering, ?groups= filter, readOnlyHint and group meta. - Mount the official MCP Streamable HTTP app at /mcp (stateless); AuthAuditMiddleware is pure ASGI and skips /mcp. - Let uvicorn chunk MCP responses; some Windows LSPs rewrite Content-Length replies on */mcp* paths into broken chunked framing. - NETX_MCP_ALLOWED_HOSTS opts into DNS-rebinding checks (off by default so LAN and reverse-proxy hosts work; Bearer is the gate). - Remove the three stdio Python MCP packages; tests moved to /mcp, including real-TCP framing regressions. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
262 lines
9.4 KiB
Python
262 lines
9.4 KiB
Python
"""Background layout jobs + slim payload helpers."""
|
|
|
|
|
|
|
|
from __future__ import annotations
|
|
|
|
|
|
|
|
import time
|
|
|
|
from unittest.mock import patch
|
|
|
|
|
|
|
|
from netx_api.mcp_remote.topology.http_tools import _layout_topology_view, _slim_layout_payload
|
|
|
|
from netx_api.mcp_remote.topology.layout_jobs import (
|
|
|
|
cancel_job,
|
|
|
|
get_job,
|
|
|
|
is_cancelled,
|
|
|
|
job_public,
|
|
|
|
report_progress,
|
|
|
|
start_job,
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
def test_terminal_job_survives_cache_reset_and_reports_failure(tmp_path) -> None:
|
|
|
|
from netx_api.mcp_remote.topology import layout_jobs as lj
|
|
|
|
|
|
|
|
lj._write_job_disk({"job_id": "persisted", "status": "running", "started_at": time.time()})
|
|
|
|
lj.finish_job("persisted", result={"ok": False, "error": "backend_write_failed", "applied": False})
|
|
|
|
lj._JOBS.clear()
|
|
|
|
out = _layout_topology_view({"action": "job_status", "params": {"job_id": "persisted"}})
|
|
|
|
assert out["ok"] is False
|
|
|
|
assert out["status"] == "error"
|
|
|
|
assert out["error"] == "backend_write_failed"
|
|
|
|
assert out["result"]["applied"] is False
|
|
|
|
|
|
|
|
|
|
|
|
def test_spawn_failure_is_persisted_as_terminal_error() -> None:
|
|
|
|
from netx_api.mcp_remote.topology import layout_jobs as lj
|
|
|
|
|
|
|
|
with patch.object(lj.subprocess, "Popen", side_effect=OSError("spawn denied")):
|
|
|
|
jid = start_job(action="layout", view_id="v", tool_args={"view_id": "v"})
|
|
|
|
lj._JOBS.clear()
|
|
|
|
out = _layout_topology_view({"action": "job_status", "params": {"job_id": jid}})
|
|
|
|
assert out["ok"] is False
|
|
|
|
assert out["status"] == "error"
|
|
|
|
assert out["error"].startswith("worker_start_failed:")
|
|
|
|
assert not lj._args_path(jid).exists()
|
|
|
|
|
|
|
|
|
|
|
|
def test_fast_worker_terminal_progress_is_not_overwritten() -> None:
|
|
|
|
from types import SimpleNamespace
|
|
|
|
from netx_api.mcp_remote.topology import layout_jobs as lj
|
|
|
|
|
|
|
|
def spawn(argv, **kwargs):
|
|
|
|
jid = argv[-1]
|
|
|
|
lj.finish_job(jid, result={"ok": True, "applied": True})
|
|
|
|
return SimpleNamespace(pid=123)
|
|
|
|
|
|
|
|
with patch.object(lj.subprocess, "Popen", side_effect=spawn):
|
|
|
|
jid = start_job(action="layout", view_id="v", tool_args={"view_id": "v"})
|
|
|
|
out = lj.job_public(jid)
|
|
|
|
assert out["status"] == "done"
|
|
|
|
assert out["progress"]["phase"] == "done"
|
|
|
|
assert out["progress"]["pct"] == 100.0
|
|
|
|
|
|
|
|
|
|
|
|
def test_pruning_preserves_active_jobs() -> None:
|
|
|
|
from netx_api.mcp_remote.topology import layout_jobs as lj
|
|
|
|
|
|
|
|
lj._write_job_disk({"job_id": "active", "status": "running"})
|
|
|
|
lj._write_job_disk({"job_id": "completed", "status": "done"})
|
|
|
|
with patch.object(lj, "_MAX_JOBS", 1):
|
|
|
|
lj._prune_disk()
|
|
|
|
assert lj._read_job_disk("active") is not None
|
|
|
|
assert lj._read_job_disk("completed") is None
|
|
|
|
|
|
|
|
|
|
|
|
def test_start_job_and_poll() -> None:
|
|
|
|
def runner() -> dict:
|
|
|
|
report_progress("mid", pct=50.0, message="halfway", step=1, total_steps=2)
|
|
|
|
time.sleep(0.05)
|
|
|
|
return {"ok": True, "action": "compose_views", "applied": True, "node_count": 3}
|
|
|
|
|
|
|
|
jid = start_job(action="compose_views", view_id="v1", runner=runner, meta={"n": 1})
|
|
|
|
assert jid
|
|
|
|
saw_progress = False
|
|
|
|
for _ in range(40):
|
|
|
|
pub = job_public(jid)
|
|
|
|
assert pub is not None
|
|
|
|
assert "elapsed_ms" in pub
|
|
|
|
assert "progress" in pub
|
|
|
|
assert "heartbeat_age_ms" in pub
|
|
|
|
if (pub.get("progress") or {}).get("phase") == "mid":
|
|
|
|
saw_progress = True
|
|
|
|
if pub["status"] != "running":
|
|
|
|
break
|
|
|
|
time.sleep(0.05)
|
|
|
|
assert saw_progress
|
|
|
|
job = get_job(jid)
|
|
|
|
assert job is not None
|
|
|
|
assert job["status"] == "done"
|
|
|
|
assert job["result"]["applied"] is True
|
|
|
|
|
|
|
|
st = _layout_topology_view({"action": "job_status", "params": {"job_id": jid}})
|
|
|
|
assert st.get("ok") is True
|
|
|
|
assert st.get("status") == "done"
|
|
|
|
assert st.get("result", {}).get("applied") is True
|
|
|
|
assert isinstance(st.get("progress"), dict)
|
|
|
|
|
|
|
|
|
|
|
|
def test_cancel_job_cooperative() -> None:
|
|
|
|
started = time.time()
|
|
|
|
|
|
|
|
def runner() -> dict:
|
|
|
|
report_progress("work", pct=10.0, message="before sleep")
|
|
|
|
for _ in range(40):
|
|
|
|
if is_cancelled():
|
|
|
|
from netx_api.mcp_remote.topology.layout_jobs import raise_if_cancelled
|
|
|
|
|
|
|
|
raise_if_cancelled()
|
|
|
|
time.sleep(0.05)
|
|
|
|
return {"ok": True, "applied": True}
|
|
|
|
|
|
|
|
jid = start_job(action="polish_crossings", view_id="v1", runner=runner)
|
|
|
|
time.sleep(0.08)
|
|
|
|
out = _layout_topology_view({"action": "job_cancel", "params": {"job_id": jid}})
|
|
|
|
assert out.get("ok") is True
|
|
|
|
assert out.get("cancel_requested") is True
|
|
|
|
for _ in range(40):
|
|
|
|
pub = job_public(jid)
|
|
|
|
assert pub is not None
|
|
|
|
if pub["status"] == "cancelled":
|
|
|
|
break
|
|
|
|
time.sleep(0.05)
|
|
|
|
pub = job_public(jid)
|
|
|
|
assert pub is not None
|
|
|
|
assert pub["status"] == "cancelled"
|
|
|
|
assert time.time() - started < 3.0
|
|
|
|
|
|
|
|
|
|
|
|
def test_slim_layout_payload_drops_guide() -> None:
|
|
|
|
fat = {
|
|
|
|
"ok": True,
|
|
|
|
"action": "compose_views",
|
|
|
|
"node_count": 1200,
|
|
|
|
"guide": {"how_to_read": "x" * 200},
|
|
|
|
"tried": [1, 2, 3],
|
|
|
|
"params_used": {"lane": 1},
|
|
|
|
"crossing": {
|
|
|
|
"status": "fail",
|
|
|
|
"score": 0,
|
|
|
|
"edge_crossings": 9,
|
|
|
|
"crossings_per_link": 0.1,
|
|
|
|
"top_nodes": [{"id": "a"}] * 20,
|
|
|
|
"top_edges": [{"id": "e"}] * 20,
|
|
|
|
"tip": "long",
|
|
|
|
},
|
|
|
|
"summary": {"total": 40},
|
|
|
|
}
|
|
|
|
slim = _slim_layout_payload(fat)
|
|
|
|
assert slim.get("slim") is True
|
|
|
|
assert "guide" not in slim
|
|
|
|
assert "tried" not in slim
|
|
|
|
assert len(slim["crossing"]["top_nodes"]) <= 5
|
|
|
|
|
|
|
|
|
|
|
|
def test_compose_views_is_not_public() -> None:
|
|
|
|
# compose_* was retired from the public surface (dual-unit drain is the main path).
|
|
|
|
out = _layout_topology_view(
|
|
|
|
{
|
|
|
|
"view_id": "full",
|
|
|
|
"action": "compose_views",
|
|
|
|
"mode": "apply",
|
|
|
|
"params": {"source_view_ids": [f"s{i:02d}" for i in range(12)]},
|
|
|
|
}
|
|
|
|
)
|
|
|
|
assert out.get("ok") is False
|
|
|
|
assert out.get("error") == "unknown_action:compose_views"
|
|
|
|
|
|
|
|
|
|
|
|
def test_orbit_background_returns_job_id() -> None:
|
|
|
|
graph = {
|
|
|
|
"ok": True,
|
|
|
|
"nodes": [
|
|
|
|
{"fabric_node_id": f"n{i}", "x": float(i * 100), "y": 0.0, "label": f"N{i}"}
|
|
|
|
for i in range(6)
|
|
|
|
],
|
|
|
|
"edges": [
|
|
|
|
{"id": f"e{i}", "a_node_id": f"n{i}", "b_node_id": f"n{i + 1}"} for i in range(5)
|
|
|
|
],
|
|
|
|
}
|
|
|
|
|
|
|
|
def fake_start(**kwargs):
|
|
|
|
assert kwargs["action"] == "orbit_sweep"
|
|
|
|
assert kwargs["view_id"] == "full"
|
|
|
|
tool_args = kwargs.get("tool_args")
|
|
|
|
assert isinstance(tool_args, dict)
|
|
|
|
# The worker re-runs the same call synchronously.
|
|
|
|
assert tool_args["params"].get("_force_sync") is True
|
|
|
|
assert "background" not in tool_args["params"]
|
|
|
|
return "abc123job"
|
|
|
|
|
|
|
|
with patch("netx_api.mcp_remote.topology.http_tools.http_json", return_value={"ok": True, "data": graph}), patch(
|
|
|
|
"netx_api.mcp_remote.topology.http_tools.start_job", side_effect=fake_start
|
|
|
|
):
|
|
|
|
out = _layout_topology_view(
|
|
|
|
{
|
|
|
|
"view_id": "full",
|
|
|
|
"action": "orbit_sweep",
|
|
|
|
"mode": "apply",
|
|
|
|
"params": {"background": True},
|
|
|
|
}
|
|
|
|
)
|
|
|
|
assert out.get("ok") is True, out
|
|
|
|
assert out.get("status") == "running"
|
|
|
|
assert out.get("job_id") == "abc123job"
|
|
|
|
assert out.get("applied") is False
|
|
|
|
|
|
|
|
|
|
|
|
def test_job_status_missing() -> None:
|
|
|
|
out = _layout_topology_view({"action": "job_status", "params": {}})
|
|
|
|
assert out.get("ok") is False
|
|
|
|
assert out.get("error") == "job_id_required"
|
|
|
|
|
|
|
|
|
|
|
|
def test_job_status_unknown() -> None:
|
|
|
|
out = _layout_topology_view(
|
|
|
|
{"action": "job_status", "params": {"job_id": "does-not-exist"}}
|
|
|
|
)
|
|
|
|
assert out.get("ok") is False
|
|
|
|
assert out.get("error") == "job_not_found"
|
|
|
|
|
|
|
|
|
|
|
|
def test_cancel_missing() -> None:
|
|
|
|
out = cancel_job("missing-job")
|
|
|
|
assert out.get("ok") is False
|
|
|
|
assert out.get("error") == "job_not_found"
|
|
|
|
|
|
|
|
|
|
|
|
def test_soft_stale_keeps_running_and_cancelable() -> None:
|
|
|
|
"""stale is a poll warning only -?must not freeze status or block cancel."""
|
|
|
|
from netx_api.mcp_remote.topology import layout_jobs as lj
|
|
|
|
|
|
|
|
def runner() -> dict:
|
|
|
|
time.sleep(0.3)
|
|
|
|
return {"ok": True, "applied": False}
|
|
|
|
|
|
|
|
jid = start_job(action="polish_crossings", view_id="v1", runner=runner)
|
|
|
|
with lj._LOCK: # noqa: SLF001 -?test injects silent heartbeat on disk
|
|
|
|
job = lj._read_job_disk(jid) or lj._JOBS[jid]
|
|
|
|
job["heartbeat_at"] = time.time() - (lj._STALE_AFTER_S + 5)
|
|
|
|
lj._JOBS[jid] = job
|
|
|
|
lj._write_job_disk(job)
|
|
|
|
pub = job_public(jid)
|
|
|
|
assert pub is not None
|
|
|
|
assert pub["stale"] is True
|
|
|
|
assert pub["status"] == "running"
|
|
|
|
cancelled = cancel_job(jid)
|
|
|
|
assert cancelled.get("ok") is True
|
|
|
|
assert cancelled.get("status") == "cancelling"
|
|
|
|
for _ in range(40):
|
|
|
|
pub2 = job_public(jid)
|
|
|
|
assert pub2 is not None
|
|
|
|
if pub2["status"] in {"cancelled", "done", "error"}:
|
|
|
|
break
|
|
|
|
time.sleep(0.05)
|
|
|
|
assert job_public(jid)["status"] == "cancelled"
|
|
|