This repository has been archived on 2026-07-17. You can view files and clone it. You cannot open issues or pull requests or push a commit.
Files
codespace/internal/process/manager.go
T
tao.chen 568423751f fix(process): remove data race on cmd.ProcessState (was read across goroutines)
The race: os/exec writes cmd.ProcessState inside cmd.Wait(), which
runs in the waitExit goroutine. Start, Status, Subscribe, and
Restart all read cmd.ProcessState from other goroutines to decide
'still running?'. That's a textbook Go data race — fixed by
TestStartRejectsDuplicateRunningSession under -race.

Fix: port the same pattern the shell package uses for its multi-shell
refactor. The manager now owns an exited map[string]struct{} guarded
by exitedMu. waitExit is the ONLY place that calls cmd.Wait(); after
Wait() returns it records exited[workspaceID]. Everyone else checks
the exited map instead of reading cmd.ProcessState.

- internal/process/manager.go: add exited + exitedMu to LocalManager;
  Start conflict check, Status, Subscribe, Restart, Stop all consult
  the exited map; Start clears the entry on new process; Stop and
  Restart delete the entry on stop; waitExit sets it after Wait().
- go.mod / go.sum: tidied (uuid v1.6.0 was already direct dep from
  the shell refactor).

go test -race -count=3 ./...  clean across the whole repo.
go test -race -count=5 ./internal/process/...  clean.
2026-07-06 15:52:07 +08:00

300 lines
7.1 KiB
Go

package process
import (
"fmt"
"io"
"os"
"os/exec"
"sync"
"syscall"
"codespace/internal/util"
)
const (
outputBufferSize = 4 * 1024
)
// Manager manages OpenCode processes per workspace.
type Manager interface {
Start(workspaceID string, workspaceRoot string) error
Stop(workspaceID string) error
Restart(workspaceID string, workspaceRoot string) error
Status(workspaceID string) Status
Subscribe(workspaceID string) (Subscription, error)
Stdin(workspaceID string) (io.WriteCloser, error)
ExitStatus(workspaceID string) (ExitInfo, error)
}
// LocalManager implements Manager using local OS processes.
type LocalManager struct {
command string
args []string
mu sync.Mutex
sessions map[string]*Session
exitedMu sync.Mutex
exited map[string]struct{}
}
// NewManager creates a LocalManager with the given command.
// If command is empty, it defaults to "opencode".
func NewManager(command string, args []string) *LocalManager {
return &LocalManager{
command: normalizeCommand(command),
args: args,
sessions: make(map[string]*Session),
exited: make(map[string]struct{}),
}
}
// Start launches a process for the given workspace.
// Returns CodeConflict if a session is already running.
func (m *LocalManager) Start(workspaceID string, workspaceRoot string) error {
m.mu.Lock()
defer m.mu.Unlock()
if _, ok := m.sessions[workspaceID]; ok {
m.exitedMu.Lock()
_, exited := m.exited[workspaceID]
m.exitedMu.Unlock()
if !exited {
return util.New(util.CodeConflict, "process already running")
}
}
cmd := exec.Command(m.command, m.args...)
cmd.Dir = workspaceRoot
cmd.Env = append(os.Environ(), fmt.Sprintf("HOME=%s", workspaceRoot))
stdinR, stdinW, err := os.Pipe()
if err != nil {
return util.Wrap(util.CodeInternal, "failed to create stdin pipe", err)
}
stdoutR, stdoutW, err := os.Pipe()
if err != nil {
stdinR.Close()
stdinW.Close()
return util.Wrap(util.CodeInternal, "failed to create stdout pipe", err)
}
cmd.Stdin = stdinR
cmd.Stdout = stdoutW
cmd.Stderr = stdoutW
if err := cmd.Start(); err != nil {
stdinR.Close()
stdinW.Close()
stdoutR.Close()
stdoutW.Close()
return util.Wrap(util.CodeInternal, "failed to start process", err)
}
stdinR.Close()
stdoutW.Close()
sess := &Session{
WorkspaceID: workspaceID,
Root: workspaceRoot,
Cmd: cmd,
Stdin: stdinW,
Subscribers: make(map[Subscription]struct{}),
}
m.sessions[workspaceID] = sess
m.exitedMu.Lock()
delete(m.exited, workspaceID)
m.exitedMu.Unlock()
outputDone := make(chan struct{})
go m.captureOutput(sess, stdoutR, outputDone)
go m.waitExit(sess, outputDone)
return nil
}
// captureOutput reads from the merged stdout/stderr pipe and fans out each
// chunk to all subscribers using non-blocking sends.
func (m *LocalManager) captureOutput(sess *Session, stdoutR *os.File, done chan<- struct{}) {
defer close(done)
defer stdoutR.Close()
buf := make([]byte, outputBufferSize)
for {
n, err := stdoutR.Read(buf)
if n > 0 {
chunk := make([]byte, n)
copy(chunk, buf[:n])
sess.mu.Lock()
for sub := range sess.Subscribers {
sub.(*subscription).send(chunk)
}
sess.mu.Unlock()
}
if err != nil {
if err != io.EOF {
// Ignore read errors; the pipe is closing.
}
break
}
}
}
// waitExit waits for the process to exit, then records the exit status, closes
// the stdin writer, and closes every subscriber channel exactly once.
func (m *LocalManager) waitExit(sess *Session, outputDone <-chan struct{}) {
_ = sess.Cmd.Wait()
<-outputDone
m.exitedMu.Lock()
m.exited[sess.WorkspaceID] = struct{}{}
m.exitedMu.Unlock()
sess.mu.Lock()
defer sess.mu.Unlock()
if sess.Cmd.ProcessState != nil {
sess.Exit.Code = sess.Cmd.ProcessState.ExitCode()
if ws, ok := sess.Cmd.ProcessState.Sys().(syscall.WaitStatus); ok && ws.Signaled() {
sess.Exit.Signal = ws.Signal().String()
}
}
if sess.Stdin != nil {
_ = sess.Stdin.Close()
}
for sub := range sess.Subscribers {
sub.(*subscription).closeChan()
}
}
// Stop kills the process for the given workspace.
// Returns CodeNotFound if no session exists.
func (m *LocalManager) Stop(workspaceID string) error {
m.mu.Lock()
defer m.mu.Unlock()
sess, ok := m.sessions[workspaceID]
if !ok || sess.Cmd.Process == nil {
return util.New(util.CodeNotFound, "no running process for workspace")
}
if err := sess.Cmd.Process.Kill(); err != nil {
return util.Wrap(util.CodeInternal, "failed to stop process", err)
}
delete(m.sessions, workspaceID)
m.exitedMu.Lock()
delete(m.exited, workspaceID)
m.exitedMu.Unlock()
return nil
}
// Restart stops (if running) then starts the process.
func (m *LocalManager) Restart(workspaceID string, workspaceRoot string) error {
m.mu.Lock()
if sess, ok := m.sessions[workspaceID]; ok {
m.exitedMu.Lock()
_, exited := m.exited[workspaceID]
m.exitedMu.Unlock()
if !exited && sess.Cmd.Process != nil {
_ = sess.Cmd.Process.Kill()
}
delete(m.sessions, workspaceID)
m.exitedMu.Lock()
delete(m.exited, workspaceID)
m.exitedMu.Unlock()
}
m.mu.Unlock()
return m.Start(workspaceID, workspaceRoot)
}
// Status returns the current process status for the workspace.
func (m *LocalManager) Status(workspaceID string) Status {
m.mu.Lock()
sess, ok := m.sessions[workspaceID]
m.mu.Unlock()
if !ok || sess.Cmd.Process == nil {
return Status{WorkspaceID: workspaceID, Running: false}
}
m.exitedMu.Lock()
_, exited := m.exited[workspaceID]
m.exitedMu.Unlock()
if exited {
return Status{WorkspaceID: workspaceID, Running: false}
}
return Status{
WorkspaceID: workspaceID,
Running: true,
PID: sess.Cmd.Process.Pid,
}
}
// Subscribe creates a new output subscription for the workspace.
// Returns CodeNotFound if the workspace has no session.
func (m *LocalManager) Subscribe(workspaceID string) (Subscription, error) {
m.mu.Lock()
sess, ok := m.sessions[workspaceID]
m.mu.Unlock()
if !ok {
return nil, util.New(util.CodeNotFound, "no running process")
}
sess.mu.Lock()
sub := newSubscription(sess)
sess.Subscribers[sub] = struct{}{}
sess.mu.Unlock()
m.exitedMu.Lock()
_, exited := m.exited[workspaceID]
m.exitedMu.Unlock()
if exited {
sub.closeChan()
}
return sub, nil
}
// Stdin returns the stdin writer for the workspace process.
func (m *LocalManager) Stdin(workspaceID string) (io.WriteCloser, error) {
return m.stdinOf(workspaceID)
}
// ExitStatus returns the exit status for the workspace process.
func (m *LocalManager) ExitStatus(workspaceID string) (ExitInfo, error) {
return m.exitOf(workspaceID)
}
// stdinOf returns the session's stdin writer or CodeNotFound.
func (m *LocalManager) stdinOf(workspaceID string) (io.WriteCloser, error) {
m.mu.Lock()
defer m.mu.Unlock()
sess, ok := m.sessions[workspaceID]
if !ok {
return nil, util.New(util.CodeNotFound, "no running process")
}
return sess.Stdin, nil
}
// exitOf returns the session's recorded exit info or CodeNotFound.
func (m *LocalManager) exitOf(workspaceID string) (ExitInfo, error) {
m.mu.Lock()
sess, ok := m.sessions[workspaceID]
m.mu.Unlock()
if !ok {
return ExitInfo{}, util.New(util.CodeNotFound, "no running process")
}
sess.mu.Lock()
defer sess.mu.Unlock()
return sess.Exit, nil
}