db6b196631
Implements the runtime side of `molecule connect <id>`. After this PR the CLI can actually attach to an external workspace and round-trip inter-agent messages through any registered backend. What's in: - `internal/connect/client.go` — platform-API client with bearer auth. Endpoints: POST /registry/register (delivery_mode=poll, no URL), POST /registry/heartbeat, GET /workspaces/:id/activity?type=a2a_receive, POST /workspaces/:id/a2a (reply target). Errors split into TransientError (network/5xx — retry with backoff) and PermanentError (4xx — abort with clear message). - `internal/connect/state.go` — atomic cursor persistence at ~/.config/molecule/state/<workspace-id>.json. Mode 0o600 (owner-only) from day 1 because future state additions may include rotated tokens. Atomic write-then-rename so a crash mid-write can never produce a half-written cursor. - `internal/connect/connect.go` — Run() orchestrator. Wires register- with-bounded-retry, then heartbeat goroutine + poll goroutine. Both respect ctx cancellation for clean SIGTERM. Robustness contract per RFC #10: * Cursor advances AFTER successful dispatch — crash mid-batch re-delivers, never drops. * 410 on cursor lookup → reset to "" and re-fetch (don't deadlock on a pruned cursor). * Heartbeat permanent error stops the heartbeat loop only; poll loop keeps running so the operator sees "stopped" + reason in logs and can SIGTERM. * Backend dispatch is sequential within a batch (avoids out-of- order replies for in-flight conversations). * Inter-agent reply path: POST envelope to /workspaces/<source>/a2a. * Canvas-origin reply (source_id == nil) logs + skips for now — M1.3 wires that via the task_update activity convention. - `internal/cmd/connect.go` — runConnect now actually calls connect.Run() (was a placeholder ctx-wait in M1.1). Test plan: - httptest workspace-server stub covers register / heartbeat / activity / a2a reply endpoints. - TestRun_RoundTrip_AgentReply: end-to-end ping → mock backend → pong reply lands at source, cursor saved. - TestRun_CanvasOriginMessageNotReplied: source_id=nil → backend fires but no reply post; cursor still advances. - TestRun_CursorPruned410ResetsAndContinues: server returns 410 once, cursor resets to "", next poll dispatches the fresh row. - TestRun_PermanentRegisterErrorAborts: 401 surfaces immediately. - TestRun_TransientRegisterErrorRetries: 503 then 200 → register succeeds on second attempt. - TestRun_OptionsValidation: missing Backend / WorkspaceID surface before any I/O. - State: round-trip, file mode 0o600, atomic-rename leaves no .tmp artifacts, corrupted file surfaces error. - All tests green under -race. Out of scope (next PRs in this stack): - M1.3: claude-code backend (canvas-origin reply convention rides with this) - M1.4: GoReleaser tag-triggered release.yml workflow - Push-mode (--mode push currently surfaces a clear "M4" error) RFC: https://github.com/Molecule-AI/molecule-cli/issues/10 Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
85 lines
2.2 KiB
Go
85 lines
2.2 KiB
Go
package connect_test
|
|
|
|
import (
|
|
"os"
|
|
"path/filepath"
|
|
"testing"
|
|
|
|
"github.com/Molecule-AI/molecule-cli/internal/connect"
|
|
)
|
|
|
|
func TestState_LoadMissingReturnsZero(t *testing.T) {
|
|
dir := t.TempDir()
|
|
got, err := connect.LoadState(dir, "ws-x")
|
|
if err != nil {
|
|
t.Fatalf("LoadState missing: %v", err)
|
|
}
|
|
if got.WorkspaceID != "ws-x" {
|
|
t.Errorf("WorkspaceID: got %q, want ws-x", got.WorkspaceID)
|
|
}
|
|
if got.LastSinceID != "" {
|
|
t.Errorf("LastSinceID: got %q, want empty", got.LastSinceID)
|
|
}
|
|
}
|
|
|
|
func TestState_SaveLoadRoundtrip(t *testing.T) {
|
|
dir := t.TempDir()
|
|
in := connect.State{WorkspaceID: "ws-1", LastSinceID: "act-42"}
|
|
if err := connect.SaveState(dir, in); err != nil {
|
|
t.Fatalf("SaveState: %v", err)
|
|
}
|
|
got, err := connect.LoadState(dir, "ws-1")
|
|
if err != nil {
|
|
t.Fatalf("LoadState: %v", err)
|
|
}
|
|
if got != in {
|
|
t.Errorf("roundtrip: got %+v, want %+v", got, in)
|
|
}
|
|
}
|
|
|
|
func TestState_AtomicRenameProducesNoTmp(t *testing.T) {
|
|
dir := t.TempDir()
|
|
if err := connect.SaveState(dir, connect.State{WorkspaceID: "ws-1", LastSinceID: "x"}); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
entries, _ := os.ReadDir(dir)
|
|
for _, e := range entries {
|
|
if filepath.Ext(e.Name()) == ".tmp" {
|
|
t.Errorf("found leftover tmp file: %s", e.Name())
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestState_SaveRequiresWorkspaceID(t *testing.T) {
|
|
if err := connect.SaveState(t.TempDir(), connect.State{}); err == nil {
|
|
t.Error("expected error on empty WorkspaceID")
|
|
}
|
|
}
|
|
|
|
func TestState_LoadCorruptedSurfaces(t *testing.T) {
|
|
dir := t.TempDir()
|
|
if err := os.WriteFile(connect.StatePath(dir, "ws-broken"), []byte("not json"), 0o600); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
_, err := connect.LoadState(dir, "ws-broken")
|
|
if err == nil {
|
|
t.Error("expected error on corrupted file")
|
|
}
|
|
}
|
|
|
|
func TestState_FilePermissions(t *testing.T) {
|
|
dir := t.TempDir()
|
|
if err := connect.SaveState(dir, connect.State{WorkspaceID: "ws-perm", LastSinceID: "x"}); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
info, err := os.Stat(connect.StatePath(dir, "ws-perm"))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
// 0o600 — owner-only read/write. Tokens may end up here in future
|
|
// state additions; lock it down from day 1.
|
|
if perm := info.Mode().Perm(); perm != 0o600 {
|
|
t.Errorf("perm: got %o, want 600", perm)
|
|
}
|
|
}
|