Compare commits

...
Author SHA1 Message Date
Emil 330f95a375 Drop a leftover helper
coordinator / test (push) Waiting to run
python / test (push) Waiting to run
release / binaries (amd64, darwin) (push) Waiting to run
release / binaries (amd64, linux) (push) Waiting to run
release / binaries (amd64, windows) (push) Waiting to run
release / binaries (arm64, darwin) (push) Waiting to run
release / binaries (arm64, linux) (push) Waiting to run
release / binaries (arm64, windows) (push) Waiting to run
release / wheel (push) Waiting to run
release / release (push) Blocked by required conditions
release / image (push) Waiting to run
users / test (push) Waiting to run
2026-08-03 18:18:19 +03:00
Emil e744e62d03 Fix network URLs in serve: loopback agents, own-origin public URLs, longer transfer timeouts 2026-08-03 18:17:56 +03:00
Emil b9f47e556c Add uninstallers for the coordinator and the worker (release assets)
coordinator / test (push) Waiting to run
python / test (push) Waiting to run
release / binaries (amd64, darwin) (push) Waiting to run
release / binaries (amd64, linux) (push) Waiting to run
release / binaries (amd64, windows) (push) Waiting to run
release / binaries (arm64, darwin) (push) Waiting to run
release / binaries (arm64, linux) (push) Waiting to run
release / binaries (arm64, windows) (push) Waiting to run
release / wheel (push) Waiting to run
release / release (push) Blocked by required conditions
release / image (push) Waiting to run
users / test (push) Waiting to run
2026-08-03 18:04:04 +03:00
Emil e6b489f117 Log version control and isolation work in the session goal 2026-08-03 16:45:50 +03:00
9 changed files with 256 additions and 12 deletions
+2
View File
@@ -110,6 +110,8 @@ jobs:
artifacts/*
install.sh
install.ps1
uninstall.sh
uninstall.ps1
# Pre-release tags (e.g. v1.1.0-alpha.1) publish as pre-releases.
prerelease: ${{ contains(github.ref_name, '-alpha') }}
generate_release_notes: true
+10
View File
@@ -75,8 +75,18 @@
- ✅ На машине пользователя: визард alpha.15, правильный токен, venv из wheel, воркер emil-pc online, 15 пустых воркеров вычищены из БД.
- ✅ Гейт: race + lint + pytest 208.
## Progress (день 2: контроль версий + изоляция)
- ✅ Визард сверяет установленную версию scimesh с версией бинарника: preflight показывает «installed X, worker needs Y — press Install» и снова предлагает кнопку Install (ensureMatchingScimeshVersion, dev-сборки пропускают). Проверено на машине: a21 vs a22 → красный → Install → зелёный 1.1.0a22.
- ✅ Все проверки и task-раннеры запускаются с `-I` (isolated): каталог запуска больше не перекрывает venv (был артефакт cwd-затенения исходниками). Затронуты: check, дефолтные раннеры агента, визард (config/save/start), serve, agent_cmd.
- ✅ Релиз v1.1.0-alpha.22; полный гейт (race + lint 0 issues + pytest 213); бинарник юзера обновлён, рантайм переустановлен (a22), воркер с concurrency=4; большой джоб юзера (1934 шарда) завершён (очередь 0).
## Completion
COMPLETED — ночной план выполнен полностью (10 пунктов + 2 найденных бага, включая E2E quorum на релизном коде). Все гейты зелёные, релиз v1.1.0-alpha.16 опубликован.
## Progress (день 2: контроль версий + изоляция)
- ✅ Визард сверяет установленную версию scimesh с версией бинарника: preflight показывает «installed X, worker needs Y — press Install» и снова предлагает кнопку Install (ensureMatchingScimeshVersion, dev-сборки пропускают). Проверено на машине: a21 vs a22 → красный → Install → зелёный 1.1.0a22.
- ✅ Все проверки и task-раннеры запускаются с `-I` (isolated): каталог запуска больше не перекрывает venv (был артефакт cwd-затенения исходниками). Затронуты: check, дефолтные раннеры агента, визард (config/save/start), serve, agent_cmd.
- ✅ Релиз v1.1.0-alpha.22; полный гейт (race + lint 0 issues + pytest 213); бинарник юзера обновлён, рантайм переустановлен (a22), воркер с concurrency=4; большой джоб юзера (1934 шарда) завершён (очередь 0).
## Completion (предыдущая задача)
COMPLETED — пайплайн доведён до рабочего состояния и проверен на релизных артефактах v1.1.0-alpha.14.
+10 -1
View File
@@ -61,7 +61,16 @@ powershell -ExecutionPolicy Bypass -c "irm https://raw.githubusercontent.com/emi
```
Set `SCIMESH_AUTO_START=0` to install without starting anything. The old demo
control room was removed: `/ui` is the admin console. A standalone
control room was removed: `/ui` is the admin console.
To remove a component, run the matching uninstaller (data is kept unless you
pass `--purge`):
```bash
curl -fsSL https://raw.githubusercontent.com/emil28092005/SciMesh/main/uninstall.sh | bash -s coordinator
curl -fsSL https://raw.githubusercontent.com/emil28092005/SciMesh/main/uninstall.sh | bash -s worker --purge
# Windows: irm .../uninstall.ps1 | iex (set $env:SCIMESH_COMPONENT, -Purge deletes data)
``` A standalone
worker is installed the same way (`bash -s worker`, or
`SCIMESH_COMPONENT=worker` on Windows); its installer opens the local setup
wizard (`worker-agent setup`) in the browser automatically.
+42 -10
View File
@@ -10,6 +10,7 @@ import (
"flag"
"fmt"
"log/slog"
"net"
"os"
"os/exec"
"path/filepath"
@@ -96,18 +97,16 @@ func runServe(args []string) error {
defer func() { _ = closeUsers() }()
// 5. Local worker agents before the server, so they can claim immediately.
coordinatorURL := "http://" + *addr
agents, err := spawnAgents(ctx, log, *dataDir, *workers, coordinatorURL, workerToken, venvPython)
// They always dial the loopback address: an --addr of 0.0.0.0 is not a
// connectable target from the same host.
agentURL, resolvedPublic := serveURLs(*addr, *publicURL)
agents, err := spawnAgents(ctx, log, *dataDir, *workers, agentURL, workerToken, venvPython)
if err != nil {
return err
}
defer stopAgents(agents)
// 6. The coordinator server itself.
coordinatorPublicURL := *publicURL
if coordinatorPublicURL == "" {
coordinatorPublicURL = "http://" + *addr
}
cfg := infra.Config{
Addr: *addr,
DatabaseEngine: "sqlite",
@@ -115,8 +114,10 @@ func runServe(args []string) error {
Token: workerToken,
JWTSecret: jwtSecret,
UserserviceURL: "http://" + usersAddr,
PublicCoordinatorURL: coordinatorPublicURL,
PublicUserserviceURL: "http://" + usersAddr,
PublicCoordinatorURL: resolvedPublic,
// The exchange is fronted by the coordinator's own proxy, so the UI
// falls back to the coordinator origin for USERSERVICE_URL.
PublicUserserviceURL: "",
LogLevel: "info",
StorageDir: filepath.Join(*dataDir, "artifacts"),
DocsDir: *docsDir,
@@ -132,12 +133,13 @@ func runServe(args []string) error {
WorkerOfflineAfter: 1 * time.Minute,
AutoMigrate: true,
}
browserURL, _ := serveURLs(*addr, *publicURL)
if *open {
openBrowser("http://" + *addr + "/ui/admin")
openBrowser(browserURL + "/ui/admin")
}
// Print the login once the server is about to start.
fmt.Printf("\nSciMesh is starting at http://%s/ui\n", *addr)
fmt.Printf("\nSciMesh is starting at %s/ui\n", browserURL)
fmt.Printf(" admin login: %s / %s\n", *email, *password)
if runtimeStatus(venvPython) {
fmt.Printf(" scientific runtime: ready (%s)\n", venvPython)
@@ -337,3 +339,33 @@ func openBrowser(target string) {
// #nosec G204 -- target is the local UI URL the operator asked to open.
_ = exec.CommandContext(context.Background(), command, target).Start()
}
// serveURLs derives the two addresses of a serve instance from the listen
// address and the optional --public-url flag:
//
// - the agent URL is always the loopback form of the port, because spawned
// local workers share the host and 0.0.0.0 is not connectable from it;
// - the public URL is what browsers and remote workers are told. An explicit
// --public-url wins; a listen host that is a real address is used as-is;
// a wildcard host (0.0.0.0, ::, or empty) yields an empty public URL, so
// the UI falls back to the browser's own origin (the coordinator's LAN
// address as the browser sees it).
func serveURLs(addr, publicURL string) (agentURL, resolvedPublic string) {
host, port, err := net.SplitHostPort(addr)
if err != nil {
// No port in the listen address: assume the default and treat the
// whole string as a host (e.g. a bare wildcard).
host, port = addr, "8080"
}
agentURL = "http://127.0.0.1:" + port
if publicURL != "" {
return agentURL, publicURL
}
host = strings.Trim(host, "[]")
switch host {
case "", "0.0.0.0", "::":
return agentURL, ""
default:
return agentURL, "http://" + addr
}
}
@@ -0,0 +1,22 @@
package main
import "testing"
func TestServeURLs(t *testing.T) {
cases := []struct {
addr, public, agent, resolved string
}{
{"127.0.0.1:8080", "", "http://127.0.0.1:8080", "http://127.0.0.1:8080"},
{"0.0.0.0:8080", "", "http://127.0.0.1:8080", ""},
{":8080", "", "http://127.0.0.1:8080", ""},
{"::", "", "http://127.0.0.1:8080", ""},
{"192.168.1.10:8080", "", "http://127.0.0.1:8080", "http://192.168.1.10:8080"},
{"0.0.0.0:8080", "http://cluster.example:8080", "http://127.0.0.1:8080", "http://cluster.example:8080"},
}
for _, c := range cases {
agent, resolved := serveURLs(c.addr, c.public)
if agent != c.agent || resolved != c.resolved {
t.Errorf("serveURLs(%q, %q) = (%q, %q), want (%q, %q)", c.addr, c.public, agent, resolved, c.agent, c.resolved)
}
}
}
+7 -1
View File
@@ -48,6 +48,12 @@ type Client struct {
}
func NewClient(baseURL string, tokens TokenProvider, timeout time.Duration) *Client {
// Payload transfers get a more generous budget than control calls: a large
// shard over a slow link easily outlives the API timeout.
transferTimeout := timeout * 4
if transferTimeout < 2*time.Minute {
transferTimeout = 2 * time.Minute
}
return &Client{
baseURL: strings.TrimRight(baseURL, "/"),
tokens: tokens,
@@ -57,7 +63,7 @@ func NewClient(baseURL string, tokens TokenProvider, timeout time.Duration) *Cli
CheckRedirect: func(*http.Request, []*http.Request) error { return http.ErrUseLastResponse },
},
dlClient: &http.Client{
Timeout: timeout,
Timeout: transferTimeout,
CheckRedirect: func(req *http.Request, via []*http.Request) error {
if len(via) >= 10 {
return fmt.Errorf("too many redirects")
+14
View File
@@ -223,3 +223,17 @@ func sha256Of(t *testing.T, value string) string {
digest := sha256.Sum256([]byte(value))
return fmt.Sprintf("%x", digest)
}
func TestNewClientTransferTimeoutExceedsAPITimeout(t *testing.T) {
c := NewClient("http://coord:8080", &StaticToken{token: "t"}, 30*time.Second)
if c.apiClient.Timeout != 30*time.Second {
t.Errorf("api timeout = %v, want 30s", c.apiClient.Timeout)
}
if c.dlClient.Timeout < 2*time.Minute {
t.Errorf("transfer timeout = %v, want at least 2m", c.dlClient.Timeout)
}
short := NewClient("http://coord:8080", &StaticToken{token: "t"}, 3*time.Minute)
if short.dlClient.Timeout != 12*time.Minute {
t.Errorf("transfer timeout = %v, want 4x the api timeout", short.dlClient.Timeout)
}
}
+66
View File
@@ -0,0 +1,66 @@
# SciMesh uninstaller for Windows: stops the running component, removes its
# binary, and — when asked — deletes its data directory.
#
# powershell -ExecutionPolicy Bypass -c "irm https://raw.githubusercontent.com/emil28092005/SciMesh/main/uninstall.ps1 | iex"
#
# $env:SCIMESH_COMPONENT selects the component (coordinator | worker | all,
# default all). Data is kept unless $env:SCIMESH_PURGE -eq "1" or the
# -Purge switch is passed (in a pipe there is no interactive prompt).
param(
[switch]$Purge
)
$ErrorActionPreference = "Stop"
$Component = if ($env:SCIMESH_COMPONENT) { $env:SCIMESH_COMPONENT } else { "all" }
if ($Purge -or $env:SCIMESH_PURGE -eq "1") { $Purge = $true } else { $Purge = $false }
$InstallDir = if ($env:SCIMESH_INSTALL_DIR) {
$env:SCIMESH_INSTALL_DIR
} else {
Join-Path $env:LOCALAPPDATA "SciMesh"
}
function Remove-Component {
param([string]$Name, [string]$Binary)
Write-Host "Stopping $Name"
Get-Process -Name $Name -ErrorAction SilentlyContinue | Stop-Process -Force -ErrorAction SilentlyContinue
$target = Join-Path $InstallDir $Binary
if (Test-Path $target) {
Write-Host "Removing $target"
Remove-Item -Force $target
}
}
function Remove-Data {
param([string]$Dir, [string]$Label)
if (-not (Test-Path $Dir)) { return }
if ($Purge) {
Remove-Item -Recurse -Force $Dir
Write-Host "Deleted $Dir"
return
}
# No interactive prompt in a pipe: keep the data by default.
Write-Host "Keeping $Dir ($Label). Pass -Purge to delete it."
}
switch ($Component) {
"coordinator" {
Remove-Component -Name "coordinator" -Binary "coordinator.exe"
Remove-Data -Dir (Join-Path $HOME ".scimesh") -Label "secrets, databases, artifacts, users"
}
"worker" {
Remove-Component -Name "worker-agent" -Binary "worker-agent.exe"
Remove-Data -Dir (Join-Path $HOME ".scimesh-worker") -Label "worker config, runtime venv, logs"
}
"all" {
Remove-Component -Name "coordinator" -Binary "coordinator.exe"
Remove-Component -Name "worker-agent" -Binary "worker-agent.exe"
Remove-Data -Dir (Join-Path $HOME ".scimesh") -Label "secrets, databases, artifacts, users"
Remove-Data -Dir (Join-Path $HOME ".scimesh-worker") -Label "worker config, runtime venv, logs"
}
default { throw "unknown component: $Component (use 'coordinator', 'worker' or 'all')" }
}
Write-Host ""
Write-Host "SciMesh $Component uninstalled."
Write-Host "Pass -Purge to also delete the data directories."
+83
View File
@@ -0,0 +1,83 @@
#!/usr/bin/env bash
# SciMesh uninstaller: stops the running component, removes its binary, and —
# when asked — deletes its data directory.
#
# curl -fsSL https://raw.githubusercontent.com/emil28092005/SciMesh/main/uninstall.sh | bash -s coordinator
# curl -fsSL https://raw.githubusercontent.com/emil28092005/SciMesh/main/uninstall.sh | bash -s worker
# curl -fsSL https://raw.githubusercontent.com/emil28092005/SciMesh/main/uninstall.sh # both
#
# Data (jobs, artifacts, users, secrets, the managed venv) is kept by default.
# Pass --purge (or set SCIMESH_PURGE=1) to delete it without asking; without
# it the script prompts interactively. Because `curl | bash` pipes have no
# interactive stdin, the default is always "keep data".
set -eu
COMPONENT="${1:-all}"
PURGE=0
for arg in "$@"; do
case "$arg" in
--purge) PURGE=1 ;;
esac
done
[ "${SCIMESH_PURGE:-0}" = "1" ] && PURGE=1
INSTALL_DIR="${SCIMESH_INSTALL_DIR:-$HOME/.local/bin}"
remove_component() {
case "$1" in
coordinator)
echo "Stopping the coordinator (serve)…"
pkill -x coordinator 2>/dev/null || true
echo "Removing $INSTALL_DIR/coordinator…"
rm -f "$INSTALL_DIR/coordinator"
;;
worker)
echo "Stopping the worker agent and its setup wizard…"
pkill -x worker-agent 2>/dev/null || true
echo "Removing $INSTALL_DIR/worker-agent…"
rm -f "$INSTALL_DIR/worker-agent"
;;
*) echo "unknown component: $1 (use 'coordinator', 'worker' or 'all')" >&2; exit 1 ;;
esac
}
remove_data() {
local dir="$1" label="$2"
if [ ! -d "$dir" ]; then
return 0
fi
if [ "$PURGE" = "1" ]; then
rm -rf "$dir"
echo "Deleted $dir"
return 0
fi
# In a pipe (curl | bash) stdin is exhausted, so the prompt defaults to keep.
printf "Delete %s (%s)? [y/N] " "$dir" "$label"
read -r answer || answer=""
case "$answer" in
y|Y|yes|YES) rm -rf "$dir"; echo "Deleted $dir" ;;
*) echo "Keeping $dir" ;;
esac
}
case "$COMPONENT" in
coordinator)
remove_component coordinator
remove_data "$HOME/.scimesh" "secrets, databases, artifacts, users, managed venv"
;;
worker)
remove_component worker
remove_data "$HOME/.scimesh-worker" "worker config, runtime venv, logs"
;;
all)
remove_component coordinator
remove_component worker
remove_data "$HOME/.scimesh" "secrets, databases, artifacts, users, managed venv"
remove_data "$HOME/.scimesh-worker" "worker config, runtime venv, logs"
;;
*) echo "unknown component: $COMPONENT (use 'coordinator', 'worker' or 'all')" >&2; exit 1 ;;
esac
echo
echo "SciMesh $COMPONENT uninstalled."
echo "Pass --purge to also delete the data directories without asking."