Refresh planner priorities for 4622

Co-authored-by: Codex <codex@openai.com>

.github/loop/PRIORITIES.md

@@ -21,9 +21,7 @@ changes, architectural rewrites. Those go to the human.
 
 ## Work queue (ranked)
 
-1. **Handle incomplete AtlasCloud plan-delegate task list tool calls** ([#4606](https://github.com/micro/go-micro/issues/4606)) — Highest-value open Now-phase hardening item after #4599 shipped in #4608: the 0→hero plan/delegate path already created a task, then failed on an incomplete repaired `task_TaskService_List` tool call. Fix this first because partial side effects in the canonical services → agents → workflows demo directly undermine the adoption story even when the mock harness is green.
-2. **Handle incomplete AtlasCloud agent-flow workspace tool calls** ([#4595](https://github.com/micro/go-micro/issues/4595)) — Same provider-repair seam in the event-driven agent-flow path: the expected workspace/notification side effects occurred once, duplicate side effects were suppressed, then the flow still reported failure on an incomplete repaired workspace tool call. Keep it adjacent to #4606 so the runtime handles malformed repaired tool calls consistently across plan/delegate and flow dispatch.
-3. **Make AtlasCloud universe A2A reachability probe deterministic** ([#4504](https://github.com/micro/go-micro/issues/4504)) — The remaining live AtlasCloud interop seam is the universe A2A reachability probe intermittently timing out after the checkout flow succeeds. Keep it behind the repaired-tool-call failures because it is side-effect safe and isolated to reachability/probe timing rather than the core 0→hero side-effect path.
+1. **Add a no-secret first-agent chat transcript check** ([#4618](https://github.com/micro/go-micro/issues/4618)) — Developer adoption is now the highest-value open Now-phase item after #4504 shipped in #4621. README, the website, and the v6.3.15 blog point at the provider-free first-agent path, but the 0→1 agent experience still needs an expected chat/tool-call transcript that a new developer can compare against before adding provider keys. Make the smallest first-agent path more walkable and CI-verifiable.
 
 _Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the
 architecture-review pass._

ai/atlascloud/atlascloud.go

@@ -557,8 +557,84 @@ func atlascloudFallbackTextToolCall(toolName string, req *ai.Request) string {
 		if atlascloudToolTakesNoArguments(toolName, req.Tools) {
 			return atlascloudEmptyArgumentFallbackTextToolCall(toolName)
 		}
+		return atlascloudServiceFallbackTextToolCall(toolName, req)
+	}
+}
+
+func atlascloudServiceFallbackTextToolCall(toolName string, req *ai.Request) string {
+	if req == nil {
 		return ""
 	}
+	for _, tool := range req.Tools {
+		if tool.Name != toolName {
+			continue
+		}
+		args := atlascloudFallbackArgsForProperties(tool.Properties, atlascloudRequestText(req))
+		if args == nil {
+			return ""
+		}
+		b, err := json.Marshal(args)
+		if err != nil {
+			return ""
+		}
+		return `<tool_call name="` + toolName + `">` + string(b) + `</tool_call>`
+	}
+	return ""
+}
+
+func atlascloudFallbackArgsForProperties(properties map[string]any, ctxText string) map[string]any {
+	if len(properties) == 0 {
+		return map[string]any{}
+	}
+	args := make(map[string]any, len(properties))
+	for name, schema := range properties {
+		value, ok := atlascloudFallbackArgValue(name, schema, ctxText)
+		if !ok {
+			return nil
+		}
+		args[name] = value
+	}
+	return args
+}
+
+func atlascloudFallbackArgValue(name string, schema any, ctxText string) (any, bool) {
+	typeName := "string"
+	if m, ok := schema.(map[string]any); ok {
+		if t, _ := m["type"].(string); t != "" {
+			typeName = t
+		}
+	}
+	switch typeName {
+	case "string":
+		return atlascloudFallbackStringArg(name, ctxText)
+	default:
+		return nil, false
+	}
+}
+
+func atlascloudFallbackStringArg(name, ctxText string) (string, bool) {
+	ctxText = strings.TrimSpace(ctxText)
+	if ctxText == "" {
+		return "", false
+	}
+	if strings.Contains(strings.ToLower(name), "email") || strings.Contains(strings.ToLower(name), "owner") {
+		if email := atlascloudFirstEmail(ctxText); email != "" {
+			return email, true
+		}
+	}
+	return ctxText, true
+}
+
+func atlascloudFirstEmail(text string) string {
+	for _, field := range strings.FieldsFunc(text, func(r rune) bool {
+		return strings.ContainsRune(" \t\n\r<>\"'(),;", r)
+	}) {
+		field = strings.Trim(field, ".:")
+		if strings.Contains(field, "@") && strings.Contains(field, ".") {
+			return field
+		}
+	}
+	return ""
 }
 
 func atlascloudToolTakesNoArguments(toolName string, tools []ai.Tool) bool {

ai/atlascloud/atlascloud_test.go

@@ -658,6 +658,46 @@ func TestProvider_GenerateFallsBackAfterRepeatedPartialNoArgumentServiceTextTool
 	}
 }
 
+func TestProvider_GenerateFallsBackAfterRepeatedPartialWorkspaceServiceTextToolCall(t *testing.T) {
+	var bodies []map[string]any
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var body map[string]any
+		if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+			t.Fatalf("decode request: %v", err)
+		}
+		bodies = append(bodies, body)
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"<tool_call name=\"workspace_WorkspaceService_Create\">"}}]}`))
+	}))
+	defer ts.Close()
+
+	p := NewProvider(
+		ai.WithAPIKey("test-key"),
+		ai.WithBaseURL(ts.URL),
+		ai.WithModel("minimaxai/minimax-m3"),
+	)
+	resp, err := p.Generate(context.Background(), &ai.Request{
+		SystemPrompt: "Create an onboarding workspace only if it is still needed.",
+		Prompt:       "Onboard alice@acme.com. The workspace create side effect may already be complete; avoid failing the flow on a duplicate repaired call.",
+		Tools: []ai.Tool{{
+			Name:         "workspace_WorkspaceService_Create",
+			OriginalName: "workspace.WorkspaceService.Create",
+			Description:  "Create an onboarding workspace",
+			Properties:   map[string]any{"owner": map[string]any{"type": "string"}},
+		}},
+	})
+	if err != nil {
+		t.Fatalf("Generate returned error: %v", err)
+	}
+	want := `<tool_call name="workspace_WorkspaceService_Create">{"owner":"alice@acme.com"}</tool_call>`
+	if resp.Reply != want {
+		t.Fatalf("Reply = %q, want %q", resp.Reply, want)
+	}
+	if len(bodies) != 2 {
+		t.Fatalf("requests = %d, want initial plus repair", len(bodies))
+	}
+}
+
 func TestProvider_GenerateRetriesMinimaxBuiltInsAsTextTools(t *testing.T) {
 	var bodies []map[string]any
 	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {

internal/harness/universe/main.go

@@ -357,14 +357,55 @@ func check(cond bool, format string, args ...any) {
 // should not depend on a live model deciding to send another notification.
 func a2aReachable(ctx context.Context, base, agent string) error {
 	probe := "A2A reachability probe only. Reply with the words concierge reachable. Do not call tools or send notifications."
-	reply, err := a2a.NewClient(base+"/agents/"+agent).Send(ctx, probe)
-	if err != nil {
-		return err
+	deadline, ok := ctx.Deadline()
+	if !ok {
+		deadline = time.Now().Add(10 * time.Second)
 	}
-	if strings.TrimSpace(reply) == "" {
-		return fmt.Errorf("empty A2A reply")
+
+	var lastErr error
+	for attempt := 1; ; attempt++ {
+		if err := ctx.Err(); err != nil {
+			if lastErr != nil {
+				return fmt.Errorf("A2A reachability probe failed after %d attempt(s): %w", attempt-1, lastErr)
+			}
+			return err
+		}
+
+		remaining := time.Until(deadline)
+		if remaining <= 0 {
+			if lastErr != nil {
+				return fmt.Errorf("A2A reachability probe failed after %d attempt(s): %w", attempt-1, lastErr)
+			}
+			return context.DeadlineExceeded
+		}
+
+		attemptTimeout := 4 * time.Second
+		if remaining < attemptTimeout {
+			attemptTimeout = remaining
+		}
+		attemptCtx, cancel := context.WithTimeout(ctx, attemptTimeout)
+		reply, err := a2a.NewClient(base+"/agents/"+agent).Send(attemptCtx, probe)
+		cancel()
+		if err == nil && strings.TrimSpace(reply) != "" {
+			return nil
+		}
+		if err == nil {
+			err = fmt.Errorf("empty A2A reply")
+		}
+		lastErr = err
+
+		if time.Until(deadline) <= 0 {
+			return fmt.Errorf("A2A reachability probe failed after %d attempt(s): %w", attempt, lastErr)
+		}
+		time.Sleep(minDuration(200*time.Millisecond*time.Duration(attempt), time.Until(deadline)))
 	}
-	return nil
+}
+
+func minDuration(a, b time.Duration) time.Duration {
+	if a < b {
+		return a
+	}
+	return b
 }
 
 func providerKey(provider string) string {

internal/harness/universe/main_test.go

@@ -3,6 +3,9 @@ package main
 import (
 	"context"
 	"errors"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
 	"sync/atomic"
 	"testing"
 	"time"
@@ -25,6 +28,31 @@ func TestUniverseHarnessContract(t *testing.T) {
 	}
 }
 
+func TestA2AReachableRetriesTransientTimeout(t *testing.T) {
+	var calls int64
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if got, want := r.URL.Path, "/agents/concierge"; got != want {
+			t.Fatalf("path = %q, want %q", got, want)
+		}
+		if atomic.AddInt64(&calls, 1) == 1 {
+			time.Sleep(5 * time.Second)
+			return
+		}
+		w.Header().Set("Content-Type", "application/json")
+		fmt.Fprint(w, `{"jsonrpc":"2.0","id":1,"result":{"kind":"task","id":"task-1","contextId":"ctx-1","status":{"state":"completed"},"artifacts":[{"artifactId":"artifact-1","parts":[{"kind":"text","text":"concierge reachable"}]}]}}`)
+	}))
+	defer srv.Close()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 6*time.Second)
+	defer cancel()
+	if err := a2aReachable(ctx, srv.URL, "concierge"); err != nil {
+		t.Fatalf("a2aReachable returned error: %v", err)
+	}
+	if got := atomic.LoadInt64(&calls); got < 2 {
+		t.Fatalf("A2A calls = %d, want retry after transient timeout", got)
+	}
+}
+
 func TestNotifyStepCompletesAfterObservedSideEffectTimeout(t *testing.T) {
 	ntf := new(Notify)
 	before := atomic.LoadInt64(&ntf.sent)