docs: refresh planner priorities for 4416

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

.github/loop/PRIORITIES.md

@@ -21,9 +21,8 @@ changes, architectural rewrites. Those go to the human.
 
 ## Work queue (ranked)
 
-1. **Trace agent RunInfo in OpenTelemetry spans** ([#4315](https://github.com/micro/go-micro/issues/4315)) — #4384 shipped the first-agent command/wayfinding harness and #4381 is closed, so the highest-value remaining gap is operability for people who make it past the on-ramp: connect existing run metadata to traces so real agent runs can be debugged across steps, tool calls, delegation, failures, services, and flows without inventing a new surface.
-2. **Resume agent runs from checkpoints** ([#4368](https://github.com/micro/go-micro/issues/4368)) — Durable agent runs are the next lifecycle seam after observability: flows already checkpoint, and agents need a focused, non-breaking resume slice that preserves completed tool calls and avoids duplicate side effects before broader durability or API design work.
-3. **Broaden provider streaming conformance** ([#4386](https://github.com/micro/go-micro/issues/4386)) — The blog says Anthropic streaming shipped, but the roadmap still calls for provider-backed streaming across chat and A2A. Add a focused, provider-gated conformance slice so streaming stays end-to-end rather than becoming a one-provider success story.
+1. **Fix race in GenerateWithRetry timeout test** ([#4415](https://github.com/micro/go-micro/issues/4415)) — #4411 closed the provider-timeout hardening slice, but the follow-up CI signal shows the new per-attempt timeout coverage has an unsafe test-local counter under `go test -race`. Restore the green evaluator first so the loop can safely continue shipping adoption and harness work.
+2. **Broaden provider streaming conformance** ([#4386](https://github.com/micro/go-micro/issues/4386)) — The blog says Anthropic streaming shipped, but the roadmap still calls for provider-backed streaming across chat and A2A. Add a focused, provider-gated conformance slice so streaming stays end-to-end rather than becoming a one-provider success story.
 
 _Seeded by Claude Code from the roadmap + open issues; thereafter maintained by the
 architecture-review pass._

agent/agent.go

@@ -432,9 +432,13 @@ func (a *agentImpl) askLocked(ctx context.Context, runID, message, parentRunID s
 		reply += resp.Answer
 	}
 
+	completedToolCalls := checkpointToolCalls(run.Steps)
+	if a.currentRun != nil {
+		completedToolCalls = checkpointToolCalls(a.currentRun.Steps)
+	}
 	res := &Response{
 		Reply:     reply,
-		ToolCalls: resp.ToolCalls,
+		ToolCalls: mergeCheckpointToolCalls(completedToolCalls, resp.ToolCalls),
 		Agent:     a.opts.Name,
 		RunID:     a.runID,
 		ParentID:  parentRunID,

agent/checkpoint.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"strings"
 	"time"
 
 	"go-micro.dev/v6/ai"
@@ -288,3 +289,56 @@ func upsertStep(steps *[]flow.StepRecord, rec flow.StepRecord) int {
 	*steps = append(*steps, rec)
 	return len(*steps) - 1
 }
+
+func checkpointToolCalls(steps []flow.StepRecord) []ai.ToolCall {
+	calls := make([]ai.ToolCall, 0, len(steps))
+	for _, step := range steps {
+		call, ok := checkpointToolCall(step)
+		if !ok {
+			continue
+		}
+		calls = append(calls, call)
+	}
+	return calls
+}
+
+func checkpointToolCall(step flow.StepRecord) (ai.ToolCall, bool) {
+	if step.Status != "done" || !strings.HasPrefix(step.Name, "tool:") {
+		return ai.ToolCall{}, false
+	}
+	parts := strings.SplitN(strings.TrimPrefix(step.Name, "tool:"), ":", 2)
+	if len(parts) != 2 || parts[0] == "" {
+		return ai.ToolCall{}, false
+	}
+	input := map[string]any{}
+	if parts[1] != "null" && parts[1] != "" {
+		if err := json.Unmarshal([]byte(parts[1]), &input); err != nil {
+			return ai.ToolCall{}, false
+		}
+	}
+	return ai.ToolCall{Name: parts[0], Input: input, Result: step.Result}, true
+}
+
+func mergeCheckpointToolCalls(checkpointed, current []ai.ToolCall) []ai.ToolCall {
+	if len(checkpointed) == 0 {
+		return current
+	}
+	seen := make(map[string]struct{}, len(current))
+	for _, call := range current {
+		seen[toolCallKey(call.Name, call.Input)] = struct{}{}
+	}
+	merged := make([]ai.ToolCall, 0, len(checkpointed)+len(current))
+	for _, call := range checkpointed {
+		if _, ok := seen[toolCallKey(call.Name, call.Input)]; ok {
+			continue
+		}
+		merged = append(merged, call)
+	}
+	merged = append(merged, current...)
+	return merged
+}
+
+func toolCallKey(name string, input map[string]any) string {
+	b, _ := json.Marshal(input)
+	return name + ":" + string(b)
+}

agent/checkpoint_test.go

@@ -21,7 +21,7 @@ func TestResumeCompletedCheckpointDoesNotReplayModel(t *testing.T) {
 	calls := 0
 	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
 		calls++
-		return &ai.Response{Reply: "done"}, nil
+		return &ai.Response{Reply: "done", ToolCalls: []ai.ToolCall{{ID: "call-1", Name: "external.lookup", Result: "cached"}}}, nil
 	}
 	defer func() { fakeGen = nil }()
 
@@ -49,6 +49,9 @@ func TestResumeCompletedCheckpointDoesNotReplayModel(t *testing.T) {
 	if resumed.RunID != resp.RunID {
 		t.Fatalf("resumed run id = %q, want %q", resumed.RunID, resp.RunID)
 	}
+	if len(resumed.ToolCalls) != 1 || resumed.ToolCalls[0].Name != "external.lookup" || resumed.ToolCalls[0].Result != "cached" {
+		t.Fatalf("resumed tool calls = %#v, want persisted completed call", resumed.ToolCalls)
+	}
 	if calls != 1 {
 		t.Fatalf("model calls after Resume = %d, want 1", calls)
 	}
@@ -101,6 +104,12 @@ func TestResumeFailedCheckpointDoesNotReplayCompletedTool(t *testing.T) {
 	if resp.Reply != "finished from checkpoint" {
 		t.Fatalf("Resume reply = %q", resp.Reply)
 	}
+	if len(resp.ToolCalls) != 1 || resp.ToolCalls[0].Name != "external.charge" || resp.ToolCalls[0].Result != "charged" {
+		t.Fatalf("resumed tool calls = %#v, want preserved completed charge call", resp.ToolCalls)
+	}
+	if got := resp.ToolCalls[0].Input["order"]; got != "42" {
+		t.Fatalf("resumed tool input order = %#v, want 42", got)
+	}
 	if toolRuns != 1 {
 		t.Fatalf("tool executions after Resume = %d, want completed tool was not replayed", toolRuns)
 	}

agent/resilience_test.go

@@ -240,6 +240,55 @@ func TestAskCancellationDuringToolCallFailsRun(t *testing.T) {
 	}
 }
 
+func TestSlowProviderTimeoutPreventsLateToolSideEffects(t *testing.T) {
+	started := make(chan struct{})
+	release := make(chan struct{})
+	done := make(chan struct{})
+	fakeGen = func(ctx context.Context, opts ai.Options, req *ai.Request) (*ai.Response, error) {
+		close(started)
+		<-release
+		defer close(done)
+		if opts.ToolHandler == nil {
+			t.Fatal("missing tool handler")
+		}
+		res := opts.ToolHandler(ctx, ai.ToolCall{ID: "late-1", Name: "external.create", Input: map[string]any{"title": "too late"}})
+		if !strings.Contains(res.Content, context.DeadlineExceeded.Error()) {
+			t.Errorf("late tool result = %q, want deadline exceeded", res.Content)
+		}
+		return &ai.Response{Reply: "late", ToolCalls: []ai.ToolCall{{ID: "late-1", Name: "external.create", Input: map[string]any{"title": "too late"}, Result: res.Content}}}, nil
+	}
+	defer func() { fakeGen = nil }()
+
+	toolRuns := 0
+	a := newTestAgent(
+		Name("slow-provider-late-tool"),
+		ModelCallTimeout(10*time.Millisecond),
+		WithTool("external.create", "create once", nil, func(context.Context, map[string]any) (string, error) {
+			toolRuns++
+			return "created", nil
+		}),
+	)
+
+	_, err := a.Ask(context.Background(), "provider times out before tool")
+	if !errors.Is(err, context.DeadlineExceeded) {
+		t.Fatalf("Ask error = %v, want deadline exceeded", err)
+	}
+	select {
+	case <-started:
+	default:
+		t.Fatal("provider was not called")
+	}
+	close(release)
+	select {
+	case <-done:
+	case <-time.After(time.Second):
+		t.Fatal("late provider call did not finish")
+	}
+	if toolRuns != 0 {
+		t.Fatalf("late tool executions = %d, want 0", toolRuns)
+	}
+}
+
 func TestAskCheckpointRecordsTerminalOperationalFailureStatus(t *testing.T) {
 	tests := []struct {
 		name string

ai/retry.go

@@ -157,7 +157,7 @@ func GenerateWithRetry(ctx context.Context, m Model, req *Request, policy Genera
 			info.MaxAttempts = policy.MaxAttempts
 			callCtx = WithRunInfo(callCtx, info)
 		}
-		resp, err := m.Generate(callCtx, req, opts...)
+		resp, err := generateAttempt(callCtx, m, req, opts...)
 		cancel()
 
 		// Caller cancellation/deadline always wins and is not retried, even if
@@ -197,6 +197,27 @@ func GenerateWithRetry(ctx context.Context, m Model, req *Request, policy Genera
 	return nil, &RetryError{Attempts: policy.MaxAttempts, Kind: ClassifyError(last), Err: last}
 }
 
+func generateAttempt(ctx context.Context, m Model, req *Request, opts ...GenerateOption) (*Response, error) {
+	if err := ctx.Err(); err != nil {
+		return nil, err
+	}
+	type result struct {
+		resp *Response
+		err  error
+	}
+	done := make(chan result, 1)
+	go func() {
+		resp, err := m.Generate(ctx, req, opts...)
+		done <- result{resp: resp, err: err}
+	}()
+	select {
+	case res := <-done:
+		return res.resp, res.err
+	case <-ctx.Done():
+		return nil, ctx.Err()
+	}
+}
+
 func retryBackoff(err error, attempt int, base time.Duration) time.Duration {
 	backoff := base
 	if backoff <= 0 {

ai/retry_test.go

@@ -135,6 +135,34 @@ func TestGenerateWithRetryAddsAttemptMetadataToRunInfo(t *testing.T) {
 	}
 }
 
+func TestGenerateWithRetryReturnsWhenProviderIgnoresTimeout(t *testing.T) {
+	started := make(chan struct{})
+	release := make(chan struct{})
+	model := retryModel{generate: func(ctx context.Context, req *Request, opts ...GenerateOption) (*Response, error) {
+		close(started)
+		<-release
+		return &Response{Reply: "late"}, nil
+	}}
+	defer close(release)
+
+	start := time.Now()
+	_, err := GenerateWithRetry(context.Background(), model, &Request{Prompt: "hi"}, GeneratePolicy{
+		Timeout:     10 * time.Millisecond,
+		MaxAttempts: 1,
+	})
+	if !errors.Is(err, context.DeadlineExceeded) {
+		t.Fatalf("GenerateWithRetry error = %v, want deadline exceeded", err)
+	}
+	if elapsed := time.Since(start); elapsed > 200*time.Millisecond {
+		t.Fatalf("GenerateWithRetry took %s after deadline, want prompt return", elapsed)
+	}
+	select {
+	case <-started:
+	default:
+		t.Fatal("provider was not called")
+	}
+}
+
 type statusErr int
 
 func (e statusErr) Error() string   { return "provider status" }

internal/harness/zero-to-hero-ci/run.sh

@@ -4,17 +4,36 @@ set -euo pipefail
 ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../../.." && pwd)"
 cd "$ROOT"
 
+run_step() {
+  local name=$1
+  shift
+
+  printf '\n==> %s\n' "$name"
+  printf '+ %q' "$@"
+  printf '\n'
+  "$@"
+}
+
 # Keep the developer inner-loop boundaries executable and discoverable in CI
-# without secrets or long-running daemons.
-go test ./cmd/micro/cli/new -run TestZeroToOne -count=1
-go test ./cmd/micro -run 'TestFirstAgentWalkthroughCLIBoundaries|TestExamplesWayfindingIndexStaysLinked|TestExamplesCommandPointsAtWayfindingIndex|TestZeroToHeroCLIBoundaries|TestZeroToHeroCommandPrintsMaintainedNoSecretPath' -count=1
-go test ./cmd/micro/cli/deploy -run TestDeployDryRun -count=1
-go test ./internal/harness/zero-to-hero-ci -run 'TestNoSecretFirstAgentTranscript|TestNoSecretFirstAgentDebuggingSmoke|TestZeroToHeroReferenceDocs|TestZeroToHeroDeployDryRunCommandSmoke|TestYourFirstAgentTutorialSmoke' -count=1
+# without secrets or long-running daemons. Step names mirror the documented
+# install → scaffold → run/chat → inspect → deploy-dry-run seams so failures
+# identify the broken part of the getting-started contract.
+run_step "scaffold: 0→1 service contract" \
+  go test ./cmd/micro/cli/new -run TestZeroToOne -count=1
+run_step "run/chat/inspect: first-agent CLI boundaries" \
+  go test ./cmd/micro -run 'TestFirstAgentWalkthroughCLIBoundaries|TestExamplesWayfindingIndexStaysLinked|TestExamplesCommandPointsAtWayfindingIndex|TestZeroToHeroCLIBoundaries|TestZeroToHeroCommandPrintsMaintainedNoSecretPath' -count=1
+run_step "deploy dry-run: configured target plan" \
+  go test ./cmd/micro/cli/deploy -run TestDeployDryRun -count=1
+run_step "chat/inspect: no-secret first-agent transcript and docs" \
+  go test ./internal/harness/zero-to-hero-ci -run 'TestNoSecretFirstAgentTranscript|TestNoSecretFirstAgentDebuggingSmoke|TestZeroToHeroReferenceDocs|TestZeroToHeroDeployDryRunCommandSmoke|TestYourFirstAgentTutorialSmoke' -count=1
 
 # Deterministic no-secret reference scenarios. These use the real Go Micro
 # runtime and mock only the LLM provider. The support example is the maintained
 # runnable 0→hero app; keep it in this CI path so its documented run/chat/inspect
 # journey cannot drift from the framework.
-go test ./examples/first-agent -run TestRunFirstAgent -count=1
-go test ./examples/support -run 'TestRunSupportMockSmoke|TestZeroToHeroReadmeDocumentsLifecycle' -count=1
-go test ./internal/harness/universe ./internal/harness/plan-delegate -run 'Test.*Harness|TestPlanDelegateEndToEnd|TestPlanDelegateFlowHandoff' -count=1
+run_step "first-agent app: runnable provider-free example" \
+  go test ./examples/first-agent -run TestRunFirstAgent -count=1
+run_step "0→hero app: support lifecycle smoke" \
+  go test ./examples/support -run 'TestRunSupportMockSmoke|TestZeroToHeroReadmeDocumentsLifecycle' -count=1
+run_step "workflows: deterministic services → agents → workflows harnesses" \
+  go test ./internal/harness/universe ./internal/harness/plan-delegate -run 'Test.*Harness|TestPlanDelegateEndToEnd|TestPlanDelegateFlowHandoff' -count=1

micro.go

@@ -215,7 +215,10 @@ func AgentWithCheckpoint(c Checkpoint) AgentOption { return agent.WithCheckpoint
 func AgentPending(ctx context.Context, a Agent) ([]FlowRun, error) { return agent.Pending(ctx, a) }
 
 // AgentResume resumes a checkpointed agent run by id. Completed runs return
-// the persisted response without calling the model or replaying tool calls.
+// the persisted response, including completed tool-call metadata, without
+// calling the model or replaying tool calls. Incomplete runs resume from the
+// saved prompt plus completed tool checkpoints; a provider call interrupted
+// mid-stream is retried rather than continued byte-for-byte.
 func AgentResume(ctx context.Context, a Agent, runID string) (*AgentResponse, error) {
 	return agent.Resume(ctx, a, runID)
 }