Compare commits

..

5 Commits

Author SHA1 Message Date
Codex eeaac92742 docs: refresh planner priorities for 3994
Harness (E2E) / Harnesses (mock LLM) (push) Waiting to run
Harness (E2E) / Provider harnesses (live LLM conformance) (push) Waiting to run
Lint / golangci-lint (push) Waiting to run
Run Tests / Unit Tests (push) Waiting to run
Run Tests / Etcd Integration Tests (push) Waiting to run
2026-07-05 00:49:07 +00:00
Asim Aslam 6ecfcd5cdf cli: surface first-agent next steps (#3993)
Co-authored-by: Codex <codex@openai.com>
2026-07-05 00:59:18 +01:00
Asim Aslam 3ceb23e9cb docs: refresh planner queue for 3987 (#3988)
Co-authored-by: Codex <codex@openai.com>
2026-07-05 00:32:58 +01:00
Asim Aslam af4d81cba3 harness: require notify inside plan delegate flow (#3986)
goreleaser / goreleaser (push) Waiting to run
Co-authored-by: Codex <codex@openai.com>
2026-07-05 00:00:26 +01:00
Asim Aslam 021e3e1bd9 docs: refresh planner priorities for 3982 (#3984)
Co-authored-by: Codex <codex@openai.com>
2026-07-04 23:33:46 +01:00
5 changed files with 124 additions and 55 deletions
+3 -3
View File
@@ -21,9 +21,9 @@ changes, architectural rewrites. Those go to the human.
## Work queue (ranked)
1. **Require delegated notify before plan-delegate completion** ([#3972](https://github.com/micro/go-micro/issues/3972)) — #3981 closed the first-agent broker isolation gap, leaving this as the latest live AtlasCloud plan/delegate harness regression. A tasks-complete-but-notify-missing run undermines evaluator trust at the agents → workflows seam, so it stays at the top until the harness can prove delegated work only completes after the required notification.
2. **Surface the first-agent and 0→hero example paths in the CLI** ([#3983](https://github.com/micro/go-micro/issues/3983)) — the README, website docs, and examples now describe a strong on-ramp, but adoption still depends on users finding those paths after install. Current goal is developer adoption, so the queue should keep a CI-verifiable CLI wayfinding task near the top instead of drifting entirely into internal conformance and observability work.
3. **Broaden provider streaming and keep chat/A2A streaming end to end** ([#3903](https://github.com/micro/go-micro/issues/3903)) — streaming remains the highest developer-visible Next-phase seam after the current conformance and wayfinding gaps. Real chat and long-running A2A tasks need token streaming to stay coherent from provider → `ai.Stream``micro chat` → A2A `message/stream`, with mock/default CI coverage plus key-gated live provider checks and safe fallback for non-streaming providers.
1. **Make AtlasCloud live conformance exercise the guarded delegate path** ([#3990](https://github.com/micro/go-micro/issues/3990)) — #3993 shipped the highest-priority adoption wayfinding gap by surfacing first-agent and 0→hero next steps from `micro new`, so the queue should not re-run #3983. The current top risk is a live provider-conformance regression in the Now-phase “battle-tested across providers” contract: AtlasCloud completed the model/tool path but skipped the guarded delegation attempt, leaving the harness unable to prove delegation refusal behavior across providers.
2. **Make AtlasCloud plan/delegate complete required tasks before notification** ([#3991](https://github.com/micro/go-micro/issues/3991)) — the same scheduled live harness exposed a 0→hero correctness seam: the conductor emitted the delegated notification side effect while required task-creation plan steps remained unfinished. This is ranked just behind #3990 because it protects the services → agents → workflows story users now discover through the CLI and should fail safely before side effects or recover before checkpoint validation.
3. **Broaden provider streaming and keep chat/A2A streaming end to end** ([#3903](https://github.com/micro/go-micro/issues/3903)) — once the live conformance regressions are fixed, streaming remains the highest developer-visible Next-phase seam. Real chat and long-running A2A tasks need token streaming to stay coherent from provider → `ai.Stream``micro chat` → A2A `message/stream`, with mock/default CI coverage plus key-gated live provider checks and safe fallback for non-streaming providers.
4. **Trace agent runs as OpenTelemetry spans** ([#3908](https://github.com/micro/go-micro/issues/3908)) — the blog/README/roadmap story promises an operable harness, and the developer on-ramp now includes chat, inspect, and run-history checkpoints. The next observability gap is production-grade trace correlation for `RunInfo`: steps, tool calls, delegation, status, durations, and failures should be visible as spans while defaulting to no-op when tracing is not configured.
_Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the
architecture-review pass._
+38
View File
@@ -1,6 +1,7 @@
package new
import (
"bytes"
"errors"
"flag"
"os"
@@ -57,6 +58,43 @@ func TestZeroToOneNoMCPContract(t *testing.T) {
generated.call(t, "Bob", "Hello Bob")
}
func TestPrintNextStepsSurfacesFirstAgentPath(t *testing.T) {
var out bytes.Buffer
printNextSteps(&out, "helloworld", false)
for _, want := range []string{
"cd helloworld",
"micro agent preflight",
"go run .",
"micro chat",
"micro inspect agent",
"micro docs",
"your-first-agent.html",
"zero-to-hero.html",
"http://localhost:3001/mcp/tools",
} {
if !strings.Contains(out.String(), want) {
t.Fatalf("next steps missing %q:\n%s", want, out.String())
}
}
}
func TestPrintNextStepsNoMCPSkipsMCPHints(t *testing.T) {
var out bytes.Buffer
printNextSteps(&out, "worker", true)
for _, want := range []string{"micro agent preflight", "micro chat", "micro inspect agent", "micro docs"} {
if !strings.Contains(out.String(), want) {
t.Fatalf("--no-mcp next steps missing %q:\n%s", want, out.String())
}
}
for _, notWant := range []string{"http://localhost:3001/mcp/tools", "micro mcp serve"} {
if strings.Contains(out.String(), notWant) {
t.Fatalf("--no-mcp next steps should not include %q:\n%s", notWant, out.String())
}
}
}
type generatedService struct {
dir string
repoRoot string
+22 -9
View File
@@ -6,6 +6,7 @@ import (
"context"
"fmt"
"go/build"
"io"
"os"
"os/exec"
"os/signal"
@@ -280,18 +281,30 @@ func Run(ctx *cli.Context) error {
fmt.Println()
fmt.Printf(" \033[32m✓\033[0m Service \033[36m%s\033[0m created\n\n", dir)
fmt.Println(" Next steps:")
fmt.Printf(" cd %s\n", dir)
fmt.Println(" go run .")
if !noMCP {
fmt.Println()
fmt.Printf(" MCP tools \033[36mhttp://localhost:3001/mcp/tools\033[0m\n")
fmt.Println(" Claude Code \033[2mmicro mcp serve\033[0m")
}
fmt.Println()
printNextSteps(os.Stdout, dir, noMCP)
return nil
}
func printNextSteps(w io.Writer, dir string, noMCP bool) {
fmt.Fprintln(w, " Next steps:")
fmt.Fprintf(w, " cd %s\n", dir)
fmt.Fprintln(w, " micro agent preflight")
fmt.Fprintln(w, " go run .")
fmt.Fprintln(w, " micro chat")
fmt.Fprintln(w, " micro inspect agent")
fmt.Fprintln(w)
fmt.Fprintln(w, " First-agent path:")
fmt.Fprintln(w, " micro docs")
fmt.Fprintln(w, " https://go-micro.dev/docs/guides/your-first-agent.html")
fmt.Fprintln(w, " https://go-micro.dev/docs/guides/zero-to-hero.html")
if !noMCP {
fmt.Fprintln(w)
fmt.Fprintf(w, " MCP tools \033[36mhttp://localhost:3001/mcp/tools\033[0m\n")
fmt.Fprintln(w, " Claude Code \033[2mmicro mcp serve\033[0m")
}
fmt.Fprintln(w)
}
func selectTemplates(name string, noMCP bool) (mainTmpl, handlerTmpl, protoTmpl string) {
switch name {
case "crud":
+52 -30
View File
@@ -403,8 +403,14 @@ func runPlanDelegate(provider string) error {
}
f := flow.New("zero-to-hero",
flow.Agent("conductor"),
flow.Prompt("Create three launch tasks (Design, Build, Ship), then make sure owner@acme.com is notified: {{.Data}}"),
flow.Steps(
flow.Step{Name: "conductor", Run: planDelegateConductorStep(conductor)},
flow.Step{Name: "require-notify", Run: requireDelegatedNotifyStep(taskSvc, notifySvc, func(ctx context.Context) error {
_, err := conductor.Ask(ctx, "The Design, Build, and Ship tasks already exist, but the owner notification is still missing. Delegate exactly one notification to the \"comms\" agent now with this exact subtask: "+delegatedNotifyTask+" Do not create more tasks and do not answer until comms has handled the notification.")
return err
})},
),
flow.WithCheckpoint(flow.StoreCheckpoint(mem, "flow-zero-to-hero")),
flow.Timeout(harnessutil.LiveTimeout(provider)),
)
if err := f.Register(reg, broker.DefaultBroker, cl); err != nil {
@@ -419,15 +425,8 @@ func runPlanDelegate(provider string) error {
executeDone <- f.Execute(ctx, "launch readiness")
}()
if err := waitForPlanDelegateExecution(executeDone, taskSvc, notifySvc, func(ctx context.Context) error {
_, err := conductor.Ask(ctx, "The Design, Build, and Ship tasks already exist, but the owner notification is still missing. Delegate exactly one notification to the \"comms\" agent now with this exact subtask: "+delegatedNotifyTask+" Do not create more tasks and do not answer until comms has handled the notification.")
if err := waitForPlanDelegateExecution(executeDone, taskSvc, notifySvc); err != nil {
return err
}); err != nil {
return err
}
if rs := f.Results(); len(rs) > 0 {
fmt.Println("\n\033[1m< conductor reply:\033[0m", rs[len(rs)-1].Reply)
}
// Prove plan was persisted to the real store.
@@ -444,7 +443,48 @@ func runPlanDelegate(provider string) error {
return nil
}
func waitForPlanDelegateExecution(done <-chan error, taskSvc *TaskService, notifySvc *NotifyService, recoverMissingNotify func(context.Context) error) error {
func planDelegateConductorStep(conductor agent.Agent) flow.StepFunc {
return func(ctx context.Context, in flow.State) (flow.State, error) {
prompt := "Create three launch tasks (Design, Build, Ship), then make sure owner@acme.com is notified: " + in.String()
rsp, err := conductor.Ask(ctx, prompt)
if err != nil {
return in, err
}
if rsp != nil && rsp.Reply != "" {
fmt.Println("\n\033[1m< conductor reply:\033[0m", rsp.Reply)
}
return in, nil
}
}
func requireDelegatedNotifyStep(taskSvc *TaskService, notifySvc *NotifyService, recoverMissingNotify func(context.Context) error) flow.StepFunc {
return func(ctx context.Context, in flow.State) (flow.State, error) {
tasks := taskSvc.count()
notify := notifySvc.count()
if notify == 1 {
return in, nil
}
if recoverMissingNotify == nil || tasks != 3 || notify != 0 {
return in, fmt.Errorf("delegation completed without required notify side effect: notify=%d, want 1", notify)
}
settled, err := waitForNotifySideEffect(notifySvc, delegatedNotifySettleTimeout)
if err != nil {
return in, err
}
if !settled {
fmt.Print("\n\033[33mwarning:\033[0m conductor step completed before delegated notify; retrying the missing comms handoff once before the flow can complete.\n")
if err := recoverMissingNotify(ctx); err != nil {
return in, fmt.Errorf("delegation completed without required notify side effect and recovery failed: notify=%d, want 1: %w", notify, err)
}
}
if notify = notifySvc.count(); notify != 1 {
return in, fmt.Errorf("delegation recovery completed without required notify side effect: notify=%d, want 1", notify)
}
return in, nil
}
}
func waitForPlanDelegateExecution(done <-chan error, taskSvc *TaskService, notifySvc *NotifyService) error {
ticker := time.NewTicker(50 * time.Millisecond)
defer ticker.Stop()
for {
@@ -463,25 +503,7 @@ func waitForPlanDelegateExecution(done <-chan error, taskSvc *TaskService, notif
return fmt.Errorf("flow execute after side effects tasks=%d notify=%d: %w", tasks, notify, err)
}
if notify != 1 {
if recoverMissingNotify == nil || tasks != 3 || notify != 0 {
return fmt.Errorf("delegation completed without required notify side effect: notify=%d, want 1", notify)
}
settled, err := waitForNotifySideEffect(notifySvc, delegatedNotifySettleTimeout)
if err != nil {
return err
}
if !settled {
fmt.Print("\n\033[33mwarning:\033[0m flow completed before delegated notify; retrying the missing comms handoff once.\n")
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
retryErr := recoverMissingNotify(ctx)
cancel()
if retryErr != nil {
return fmt.Errorf("delegation completed without required notify side effect and recovery failed: notify=%d, want 1: %w", notify, retryErr)
}
}
if notify = notifySvc.count(); notify != 1 {
return fmt.Errorf("delegation recovery completed without required notify side effect: notify=%d, want 1", notify)
}
return fmt.Errorf("delegation completed without required notify side effect: notify=%d, want 1", notify)
}
return nil
case <-ticker.C:
+9 -13
View File
@@ -258,7 +258,7 @@ func TestPlanDelegateExecutionReportsDuplicateNotifyBeforeTimeout(t *testing.T)
done := make(chan error)
errCh := make(chan error, 1)
go func() { errCh <- waitForPlanDelegateExecution(done, new(TaskService), notifySvc, nil) }()
go func() { errCh <- waitForPlanDelegateExecution(done, new(TaskService), notifySvc) }()
select {
case err := <-errCh:
@@ -278,7 +278,7 @@ func TestPlanDelegateExecutionRejectsClaimedCompletionWithoutNotify(t *testing.T
done := make(chan error, 1)
done <- nil
err := waitForPlanDelegateExecution(done, new(TaskService), notifySvc, nil)
err := waitForPlanDelegateExecution(done, new(TaskService), notifySvc)
if err == nil {
t.Fatal("waitForPlanDelegateExecution returned nil, want missing notify side-effect error")
}
@@ -296,15 +296,13 @@ func TestPlanDelegateExecutionRecoversMissingNotifyOnce(t *testing.T) {
}
}
notifySvc := new(NotifyService)
done := make(chan error, 1)
done <- nil
recovered := false
err := waitForPlanDelegateExecution(done, taskSvc, notifySvc, func(ctx context.Context) error {
_, err := requireDelegatedNotifyStep(taskSvc, notifySvc, func(ctx context.Context) error {
recovered = true
var rsp SendResponse
return notifySvc.Send(ctx, &SendRequest{To: "owner@acme.com", Message: "The launch plan is ready"}, &rsp)
})
})(context.Background(), flow.State{})
if err != nil {
t.Fatalf("waitForPlanDelegateExecution returned %v, want recovery success", err)
}
@@ -325,8 +323,6 @@ func TestPlanDelegateExecutionWaitsForInFlightNotifyAfterFlowCompletion(t *testi
}
}
notifySvc := new(NotifyService)
done := make(chan error, 1)
done <- nil
go func() {
time.Sleep(100 * time.Millisecond)
@@ -335,11 +331,11 @@ func TestPlanDelegateExecutionWaitsForInFlightNotifyAfterFlowCompletion(t *testi
}()
recovered := false
err := waitForPlanDelegateExecution(done, taskSvc, notifySvc, func(ctx context.Context) error {
_, err := requireDelegatedNotifyStep(taskSvc, notifySvc, func(ctx context.Context) error {
recovered = true
var rsp SendResponse
return notifySvc.Send(ctx, &SendRequest{To: "owner@acme.com", Message: "The launch plan is ready"}, &rsp)
})
})(context.Background(), flow.State{})
if err != nil {
t.Fatalf("waitForPlanDelegateExecution returned %v, want in-flight notify success", err)
}
@@ -374,7 +370,7 @@ func TestPlanDelegateExecutionAcceptsClientTimeoutAfterSideEffects(t *testing.T)
done := make(chan error, 1)
done <- errors.New(`{"id":"go.micro.client","code":408,"detail":"<nil>","status":"Request Timeout"}`)
if err := waitForPlanDelegateExecution(done, taskSvc, notifySvc, nil); err != nil {
if err := waitForPlanDelegateExecution(done, taskSvc, notifySvc); err != nil {
t.Fatalf("waitForPlanDelegateExecution returned %v, want completed side effects to satisfy client timeout", err)
}
}
@@ -383,7 +379,7 @@ func TestPlanDelegateExecutionClassifiesClientTimeoutBeforeSideEffects(t *testin
done := make(chan error, 1)
done <- errors.New(`{"id":"go.micro.client","code":408,"detail":"<nil>","status":"Request Timeout"}`)
err := waitForPlanDelegateExecution(done, new(TaskService), new(NotifyService), nil)
err := waitForPlanDelegateExecution(done, new(TaskService), new(NotifyService))
if err == nil {
t.Fatal("waitForPlanDelegateExecution returned nil, want timeout before side effects to fail")
}
@@ -410,7 +406,7 @@ func TestPlanDelegateExecutionClassifiesPartialClientTimeout(t *testing.T) {
done := make(chan error, 1)
done <- errors.New(`{"id":"go.micro.client","code":408,"detail":"<nil>","status":"Request Timeout"}`)
err := waitForPlanDelegateExecution(done, taskSvc, new(NotifyService), nil)
err := waitForPlanDelegateExecution(done, taskSvc, new(NotifyService))
if err == nil {
t.Fatal("waitForPlanDelegateExecution returned nil, want timeout before notify to fail")
}