feat: implement agent socket api, client and cli (#20758)

closes: https://github.com/coder/coder/issues/10352
closes: https://github.com/coder/internal/issues/1094
closes: https://github.com/coder/internal/issues/1095

In this pull request, we enable a new set of experimental cli commands
grouped under `coder exp sync`.
These commands allow any process acting within a coder workspace to
inform the coder agent of its requirements and execution progress. The
coder agent will then relay this information to other processes that
have subscribed.

These commands are:
```
# Check if this feature is enabled in your environment 
coder exp sync ping

# express that your unit depends on another
coder exp sync want <unit> <dependency_unit> 

# express that your unit intends to start a portion of the script that requires 
# other units to have completed first. This command blocks until all dependencies have been met
coder exp sync start <unit> 

# express that your unit has completes its work, allowing dependent units to begin their execution
coder exp sync complete <unit>
```

Example:

In order to automatically run claude code in a new workspace, it must
first have a git repository cloned. The scripts responsible for cloning
the repository and for running claude code would coordinate in the
following way:

```bash
# Script A: Claude code

# Inform the agent that the claude script wants the git script.
# That is, the git script must have completed before the claude script can begin its execution
coder exp sync want claude git

# Inform the agent that we would now like to begin execution of claude.
# This command will block until the git script (and any other defined dependencies)
# have completed
coder exp sync start claude

# Now we run claude code and any other commands we need
claude ...

# Once our script has completed, we inform the agent, so that any scripts that depend on this one
# may begin their execution

coder exp sync complete claude
```

```bash
# Script B: Git

# Because the git script does not have any dependencies, we can simply inform the agent that we 
# intend to start
coder exp sync start git

git clone ssh://git@github.com/coder/coder

# Once the repository have been cloned, we inform the agent that this script is complete, so that
# scripts that depend on it may begin their execution.
coder exp sync complete git
```

Notes:
* Unit names (ie. `claude` and `git`) given as input to the sync
commands are arbitrary strings. You do not have to conform to specific
identifiers. We recommend naming your scripts descriptively, but
succinctly.
* Scripts unit names should be well documented. Other scripts will need
to know the names you've chosen in order to depend on yours. Therefore,
you

---------

Co-authored-by: Mathias Fredriksson <mafredri@gmail.com>
This commit is contained in:
Sas Swart
2025-11-28 08:33:50 +02:00
committed by GitHub
co-authored by Mathias Fredriksson
parent ee58f40cad
commit ce627bf23f
37 changed files with 1313 additions and 276 deletions
+11 -58
View File
@@ -7,8 +7,6 @@ import (
"sync"
"golang.org/x/xerrors"
"github.com/hashicorp/yamux"
"storj.io/drpc/drpcmux"
"storj.io/drpc/drpcserver"
@@ -33,11 +31,17 @@ type Server struct {
wg sync.WaitGroup
}
func NewServer(path string, logger slog.Logger) (*Server, error) {
// NewServer creates a new agent socket server.
func NewServer(logger slog.Logger, opts ...Option) (*Server, error) {
options := &options{}
for _, opt := range opts {
opt(options)
}
logger = logger.Named("agentsocket-server")
server := &Server{
logger: logger,
path: path,
path: options.path,
service: &DRPCAgentSocketService{
logger: logger,
unitManager: unit.NewManager(),
@@ -61,14 +65,6 @@ func NewServer(path string, logger slog.Logger) (*Server, error) {
},
})
if server.path == "" {
var err error
server.path, err = getDefaultSocketPath()
if err != nil {
return nil, xerrors.Errorf("get default socket path: %w", err)
}
}
listener, err := createSocket(server.path)
if err != nil {
return nil, xerrors.Errorf("create socket: %w", err)
@@ -91,6 +87,7 @@ func NewServer(path string, logger slog.Logger) (*Server, error) {
return server, nil
}
// Close stops the server and cleans up resources.
func (s *Server) Close() error {
s.mu.Lock()
@@ -134,52 +131,8 @@ func (s *Server) acceptConnections() {
return
}
for {
select {
case <-s.ctx.Done():
return
default:
}
conn, err := listener.Accept()
if err != nil {
s.logger.Warn(s.ctx, "error accepting connection", slog.Error(err))
continue
}
s.mu.Lock()
if s.listener == nil {
s.mu.Unlock()
_ = conn.Close()
return
}
s.wg.Add(1)
s.mu.Unlock()
go func() {
defer s.wg.Done()
s.handleConnection(conn)
}()
}
}
func (s *Server) handleConnection(conn net.Conn) {
defer conn.Close()
s.logger.Debug(s.ctx, "new connection accepted", slog.F("remote_addr", conn.RemoteAddr()))
config := yamux.DefaultConfig()
config.LogOutput = nil
config.Logger = slog.Stdlib(s.ctx, s.logger.Named("agentsocket-yamux"), slog.LevelInfo)
session, err := yamux.Server(conn, config)
err := s.drpcServer.Serve(s.ctx, listener)
if err != nil {
s.logger.Warn(s.ctx, "failed to create yamux session", slog.Error(err))
return
}
defer session.Close()
err = s.drpcServer.Serve(s.ctx, session)
if err != nil {
s.logger.Debug(s.ctx, "drpc server finished", slog.Error(err))
s.logger.Warn(s.ctx, "error serving drpc server", slog.Error(err))
}
}