Windows: a tool's normal closing steps do not run when Copilot stops it
Ninguém assumiu esta issue ainda.
Avaliação
- Dificuldade
- 4/5
- Tempo estimado
- 3-5 dias
- Facilidade para iniciantes
- 20/100
- Tipo de issue
- Bug
- Clareza
- Razoavelmente clara
- Status de atividade
- Ativa
- Stack de tecnologia
- javascript, nodejs, python
- Domínio
- devtools
Direção de pesquisa
Start by running reproduce.py with server.cjs on Windows to confirm the three cases: direct EOF exits with code 0 and both notes, while stop_server and client.stop() exit with code 1 and no closing notes. The gap is in how the Copilot runtime stops MCP child processes, not in server.cjs, so look at the Python SDK's mcp.stop_server and client.stop paths. Done means a graceful stop lets process.on('exit') and the stdin-end handler run before any forced kill.
Escrita pelo modelo de indexação a partir do texto da issue.
Descrição
What goes wrong
On Windows, a small tool connected to Copilot works correctly while it is running.
But when I ask Copilot to stop it, the tool closes without running the code it
normally runs before closing.
If I close the tool's incoming connection myself, that same code runs and the
tool closes normally.
Small example
I made a small tool that returns the number 2. It also writes a note to a file
when it starts, when it is used, when its connection closes, and when the program
closes.
The tool starts and returns the correct answer in all three cases:
| How I stop it | Does its normal closing code run? |
|---|---|
| Close its incoming connection directly | Yes |
| Ask Copilot to stop | No |
| Ask Copilot to stop only this tool | No |
This example does not call an AI model or use any other connected tools.
Why this matters
Tools may need their closing code to save information or release connections.
They cannot rely on that code running when Copilot stops them this way.
What should happen
Copilot should give the tool a chance to close normally first. If the tool still
does not close after a reasonable wait, Copilot can force it to end.
Please check how Copilot stops connected tools on Windows. The example shows
the difference, but does not prove exactly which part of Copilot causes it.
Version details and the two files needed to try the example
Versions used
- Windows on ARM64.
- Python 3.11.15, x64.
- Node.js 24.22.2, ARM64.
- Official Copilot program version 1.0.105-1, Windows ARM64.
- Python package 1.0.28+local.fa108e71, built from the public
v1.0.28 source atfa108e71ee3025663e0dac20f2a071055d3a6b14.
For the Python package, only the version label and the normal build step that
records the Copilot version were changed. There were no changes to how it starts,
stops, or communicates with programs. I did not test the already-packaged Python
download.
The official Copilot download had this SHA-256 file identifier:
9b1f5033f0b07b19575639d93b77b04cda9b9bdb39d934ffd2f179206d519167.
How to try it
Save server.cjs and reproduce.py beside each other. In the command below,
replace the example locations with the locations of Node.js and the Copilot
program on your computer. Keep runtime.node beside copilot-runtime.exe.
python .\reproduce.py --node 'C:\path\to\node.exe' --runtime 'C:\path\to\copilot-runtime.exe' --output '.\shutdown-output'
The output folder must not already exist. The script prints what happened and
saves a separate record for each of the three cases.
More detail about what was observed
When the connection is closed directly, Windows reports a normal ending
(result 0), and both closing notes are saved. When Copilot stops the tool,
Windows reports result 1, and neither closing note is saved.
The tool writes each note immediately and asks the operating system to save it
before continuing. Both Copilot cases record that the tool started, was ready,
and was used. Neither records that the connection ended or that the program's
normal closing code ran.
The tool itself only asks to end with result 0, shortly after its connection
closes. It has no instruction to end with result 1.
When asking Copilot to stop only the tool, the script checks that the tool has
ended before it asks Copilot itself to stop. It follows the exact program that
was started, rather than looking for any program with the same name.
Copilot starts Node.js directly. There is no extra startup script between them.
The example does not ask Copilot to restart the tool. Both ways of starting it
complete the initial connection setup and use the same tool.
server.cjs
const fs = require("node:fs");
const readline = require("node:readline");
const output = process.argv[2];
function record(phase, detail = {}) {
const fd = fs.openSync(output, "a");
try {
fs.writeSync(fd, JSON.stringify({ phase, ...detail }) + "\n");
fs.fsyncSync(fd);
} finally {
fs.closeSync(fd);
}
}
record("started");
process.once("exit", (code) => record("exit", { code }));
process.stdin.once("end", () => {
record("stdin-end");
setTimeout(() => process.exit(0), 25);
});
setImmediate(() => record("event-loop-ready"));
readline.createInterface({ input: process.stdin }).on("line", (line) => {
const request = JSON.parse(line);
if (request.id === undefined) return;
let result;
if (request.method === "initialize") {
result = {
protocolVersion: request.params.protocolVersion,
capabilities: { tools: {} },
serverInfo: { name: "shutdown-probe", version: "1.0.0" },
};
} else if (request.method === "ping") {
result = {};
} else if (request.method === "tools/list") {
result = { tools: [{
name: "probe",
description: "Return this process ID and the value two.",
inputSchema: { type: "object", properties: {}, additionalProperties: false },
}] };
} else if (request.method === "tools/call" && request.params.name === "probe") {
record("tool-called");
result = { content: [{ type: "text", text: "PROBE:" + JSON.stringify({
pid: process.pid, value: 2,
}) }] };
} else {
process.stdout.write(JSON.stringify({
jsonrpc: "2.0", id: request.id,
error: { code: -32601, message: "Unsupported request" },
}) + "\n");
return;
}
process.stdout.write(JSON.stringify({ jsonrpc: "2.0", id: request.id, result }) + "\n");
});
reproduce.py
"""Windows-only MCP shutdown control; no model requests or external services."""
import argparse
import asyncio
import ctypes
from ctypes import wintypes
import json
import os
from pathlib import Path
import re
import sys
from unittest.mock import patch
from copilot import CopilotClient, CopilotSession, PermissionHandler, RuntimeConnection
from copilot.generated.rpc import MCPStopServerRequest, ToolsExecuteRequest
if sys.platform != "win32":
raise SystemExit("This reproduction uses Windows process handles.")
kernel = ctypes.WinDLL("kernel32", use_last_error=True)
kernel.OpenProcess.argtypes = [wintypes.DWORD, wintypes.BOOL, wintypes.DWORD]
kernel.OpenProcess.restype = wintypes.HANDLE
kernel.WaitForSingleObject.argtypes = [wintypes.HANDLE, wintypes.DWORD]
kernel.WaitForSingleObject.restype = wintypes.DWORD
kernel.GetExitCodeProcess.argtypes = [wintypes.HANDLE, ctypes.POINTER(wintypes.DWORD)]
kernel.GetExitCodeProcess.restype = wintypes.BOOL
kernel.CloseHandle.argtypes = [wintypes.HANDLE]
kernel.CloseHandle.restype = wintypes.BOOL
def retain(pid):
handle = kernel.OpenProcess(0x00101000, False, pid)
if not handle:
raise ctypes.WinError(ctypes.get_last_error())
return handle
async def exit_code(handle):
result = await asyncio.to_thread(kernel.WaitForSingleObject, handle, 15000)
if result == 0x102:
raise TimeoutError("The exact child did not exit within 15 seconds.")
if result != 0:
raise ctypes.WinError(ctypes.get_last_error())
code = wintypes.DWORD()
if not kernel.GetExitCodeProcess(handle, ctypes.byref(code)):
raise ctypes.WinError(ctypes.get_last_error())
return code.value
async def direct(node, server, directory):
witness = directory / "events.jsonl"
with (directory / "stderr.log").open("wb") as errors:
process = await asyncio.create_subprocess_exec(
str(node), str(server), str(witness),
cwd=directory, env={**os.environ, "NODE_OPTIONS": ""},
stdin=asyncio.subprocess.PIPE, stdout=asyncio.subprocess.PIPE,
stderr=errors,
)
requests = [
{"method": "initialize", "params": {
"protocolVersion": "2025-11-25", "capabilities": {},
"clientInfo": {"name": "shutdown-probe", "version": "1.0.0"},
}},
{"method": "tools/list", "params": {}},
{"method": "tools/call", "params": {"name": "probe", "arguments": {}}},
]
for number, request in enumerate(requests, 1):
process.stdin.write((json.dumps({
"jsonrpc": "2.0", "id": number, **request,
}) + "\n").encode())
await process.stdin.drain()
reply = json.loads(await asyncio.wait_for(process.stdout.readline(), 15))
assert reply["id"] == number and "error" not in reply, reply
if number == 1:
process.stdin.write((json.dumps({
"jsonrpc": "2.0", "method": "notifications/initialized",
}) + "\n").encode())
await process.stdin.drain()
assert "PROBE:" in json.dumps(reply), reply
process.stdin.close()
await process.stdin.wait_closed()
return await asyncio.wait_for(process.wait(), 15)
async def through_sdk(node, server, runtime, directory, explicit):
witness = directory / "events.jsonl"
client = CopilotClient(
mode="empty", connection=RuntimeConnection.for_stdio(path=str(runtime)),
base_directory=str(directory / "storage"), working_directory=str(directory),
)
handle = None
try:
try:
await client.start()
session = await client.create_session(
available_tools=["mcp:*"],
mcp_servers={"shutdown-probe": {
"type": "local", "command": str(node),
"args": [str(server), str(witness)], "cwd": str(directory),
"env": {"NODE_OPTIONS": ""}, "tools": ["*"],
}},
on_permission_request=PermissionHandler.approve_all,
)
await session.rpc.tools.initialize_and_validate()
metadata = await session.rpc.tools.get_current_metadata()
names = [tool.name for tool in metadata.tools or []]
names = [name for name in names
if "shutdown-probe" in name and name.endswith("probe")]
assert len(names) == 1, names
result = await session.rpc.tools.execute(
ToolsExecuteRequest(name=names[0], arguments={}), timeout=30
)
if hasattr(result, "to_dict"):
result = result.to_dict()
assert result["resultType"] == "success", result
match = re.search(r"PROBE:(\{[^}]+\})", result["textResultForLlm"])
assert match, result
identity = json.loads(match[1])
assert identity["value"] == 2, identity
handle = retain(identity["pid"])
await asyncio.sleep(0.5)
if explicit:
await session.rpc.mcp.stop_server(
MCPStopServerRequest("shutdown-probe"), timeout=30
)
code = await exit_code(handle)
finally:
await client.stop()
return code if explicit else await exit_code(handle)
finally:
if handle is not None and not kernel.CloseHandle(handle):
raise ctypes.WinError(ctypes.get_last_error())
async def main():
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--node", required=True, type=Path)
parser.add_argument("--runtime", required=True, type=Path)
parser.add_argument("--output", required=True, type=Path)
args = parser.parse_args()
node = args.node.resolve(strict=True)
runtime = args.runtime.resolve(strict=True)
server = Path(__file__).with_name("server.cjs").resolve(strict=True)
root = args.output.resolve()
root.mkdir(parents=True, exist_ok=False)
results = []
for route in ("direct-eof", "sdk-stop", "sdk-stop-server"):
directory = root / route
directory.mkdir()
if route == "direct-eof":
code = await direct(node, server, directory)
else:
code = await through_sdk(
node, server, runtime, directory, explicit=route == "sdk-stop-server"
)
records = [json.loads(line) for line in
(directory / "events.jsonl").read_text().splitlines()]
results.append({"route": route, "exit_code": code, "events": records})
(root / "results.json").write_text(json.dumps(results, indent=2))
print(json.dumps(results, indent=2))
if __name__ == "__main__":
with (
patch.object(CopilotSession, "send", side_effect=AssertionError("Model calls forbidden")),
patch.object(CopilotSession, "send_and_wait", side_effect=AssertionError("Model calls forbidden")),
):
asyncio.run(main())
Other reports
github/copilot-sdk#1381
describes an earlier problem with stopping Copilot too quickly. Its fix is
already present in the Python package used here.
github/copilot-sdk#1804
and github/copilot-cli#4972
describe extra programs staying open after a startup script ends. This example
is different: Copilot starts the tool directly, and the tool ends without
running its normal closing code.
The connection standard also recommends letting a tool close normally before
forcing it to end:
https://modelcontextprotocol.io/specification/2025-11-25/basic/lifecycle#shutdown
- Linguagem predominante
- Java
- Estrelas
- 10.7k
- Forks
- 1.5k
- Métricas de merge de PRs
- Nenhum PR com merge em 30d
Preparar o ambiente
- Sem Dockerfile nem arquivo Docker Compose
- Sem modelo de pull request
- Ler o guia de contribuição
Primeiros passos
- Leia a issue inteira e depois o guia de contribuição do projeto.
- Comente na issue dizendo que vai assumir — evita que duas pessoas façam o mesmo trabalho.
- Faça um fork do repositório e trabalhe em uma branch.
- Abra um pull request que referencie o número da issue.
Mais de github/copilot-sdk
-
Rust: ElicitationRequest drops the tool call id from elicitation.requestedTalvez livre de novo Um pull request para esta issue foi fechado sem ser mesclado. Aberta
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 78/100
github/copilot-sdk#2900 ·
-
Bump zod version to 4.6.6.Aberta
Dificuldade 1/5 Menos de uma hora Facilidade para iniciantes 84/100
github/copilot-sdk#2876 · 1 comentário · 1 reação ·
-
Python ModelLimits drops max_output_tokens from model metadataTalvez livre de novo Um pull request para esta issue foi fechado sem ser mesclado. Abertabug
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 78/100
github/copilot-sdk#2798 · 1 comentário ·
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 65/100
github/copilot-sdk#2759 ·
-
docs/AGENTS.md is repo authoring guidance, but everything in docs/ gets publishedTalvez livre de novo Um pull request para esta issue foi fechado sem ser mesclado. Abertadocumentation
Dificuldade 1/5 Menos de uma hora Facilidade para iniciantes 85/100
github/copilot-sdk#2758 ·
Todas as issues de github/copilot-sdk
Issues semelhantes
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 72/100
aws/serverless-java-container#1729 ·
Mantenedores costumam responder em até 1 dia
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 75/100
Mantenedores costumam responder em até 1 dia
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 75/100
ls1intum/thesis-management#1473 ·
Mantenedores costumam responder em até 1 dia
-
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 76/100
LunaDeerMC/Dominion#301 · 1 comentário ·
-
[FEATURE] Expose external refresh, node-level translog and warmer statsTalvez já em andamento Um pull request vinculado a esta issue está aberto ou já foi mesclado. Abertauntriaged
Dificuldade 2/5 1-3 horas Facilidade para iniciantes 68/100
opensearch-project/opensearch-prometheus-exporter#680 ·
Mantenedores costumam responder em até 2 dias