fix: prevent RunDaemon from sending completed state before Close sends final logs

Split ReportState into a public method that skips when closed (used by
RunDaemon) and a private reportState that always sends (used by Close).
This prevents the server from deleting ephemeral runners before final
logs are uploaded. Add test reproducing the exact interleaving from #793.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

internal/pkg/report/reporter.go

@@ -261,7 +261,7 @@ func (r *Reporter) Close(lastWords string) error {
 		if err := r.ReportLog(true); err != nil {
 			return err
 		}
-		return r.ReportState()
+		return r.reportState()
 	}, retry.Context(r.ctx))
 }
 
@@ -300,7 +300,18 @@ func (r *Reporter) ReportLog(noMore bool) error {
 	return nil
 }
 
+// ReportState reports the current task state unless the reporter is closed.
 func (r *Reporter) ReportState() error {
+	r.stateMu.RLock()
+	closed := r.closed
+	r.stateMu.RUnlock()
+	if closed {
+		return nil
+	}
+	return r.reportState()
+}
+
+func (r *Reporter) reportState() error {
 	r.clientM.Lock()
 	defer r.clientM.Unlock()
 

internal/pkg/report/reporter_test.go

@@ -5,6 +5,7 @@ package report
 
 import (
 	"context"
+	"fmt"
 	"strings"
 	"sync"
 	"testing"
@@ -17,6 +18,7 @@ import (
 	"github.com/stretchr/testify/mock"
 	"github.com/stretchr/testify/require"
 	"google.golang.org/protobuf/types/known/structpb"
+	"google.golang.org/protobuf/types/known/timestamppb"
 
 	"gitea.com/gitea/act_runner/internal/pkg/client/mocks"
 )
@@ -198,6 +200,83 @@ func TestReporter_Fire(t *testing.T) {
 	})
 }
 
+// TestReporter_EphemeralRunnerDeletion reproduces the exact scenario from
+// https://gitea.com/gitea/act_runner/issues/793:
+//
+//  1. RunDaemon calls ReportLog(false) — runner is still alive
+//  2. Close() updates state to Result=FAILURE (between RunDaemon's ReportLog and ReportState)
+//  3. RunDaemon's ReportState() would clone the completed state and send it,
+//     but the fix makes ReportState return early when closed, preventing this
+//  4. Close's ReportLog(true) succeeds because the runner was not deleted
+func TestReporter_EphemeralRunnerDeletion(t *testing.T) {
+	runnerDeleted := false
+
+	client := mocks.NewClient(t)
+	client.On("UpdateLog", mock.Anything, mock.Anything).Return(
+		func(_ context.Context, req *connect_go.Request[runnerv1.UpdateLogRequest]) (*connect_go.Response[runnerv1.UpdateLogResponse], error) {
+			if runnerDeleted {
+				return nil, fmt.Errorf("runner has been deleted")
+			}
+			return connect_go.NewResponse(&runnerv1.UpdateLogResponse{
+				AckIndex: req.Msg.Index + int64(len(req.Msg.Rows)),
+			}), nil
+		},
+	)
+	client.On("UpdateTask", mock.Anything, mock.Anything).Maybe().Return(
+		func(_ context.Context, req *connect_go.Request[runnerv1.UpdateTaskRequest]) (*connect_go.Response[runnerv1.UpdateTaskResponse], error) {
+			// Server deletes ephemeral runner when it receives a completed state
+			if req.Msg.State != nil && req.Msg.State.Result != runnerv1.Result_RESULT_UNSPECIFIED {
+				runnerDeleted = true
+			}
+			return connect_go.NewResponse(&runnerv1.UpdateTaskResponse{}), nil
+		},
+	)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	taskCtx, err := structpb.NewStruct(map[string]interface{}{})
+	require.NoError(t, err)
+	reporter := NewReporter(ctx, cancel, client, &runnerv1.Task{Context: taskCtx})
+	reporter.ResetSteps(1)
+
+	// Fire a log entry to create pending data
+	assert.NoError(t, reporter.Fire(&log.Entry{
+		Message: "build output",
+		Data:    log.Fields{"stage": "Main", "stepNumber": 0, "raw_output": true},
+	}))
+
+	// Step 1: RunDaemon calls ReportLog(false) — runner is still alive
+	assert.NoError(t, reporter.ReportLog(false))
+
+	// Step 2: Close() updates state — sets Result=FAILURE and marks steps cancelled.
+	// In the real race, this happens while RunDaemon is between ReportLog and ReportState.
+	reporter.stateMu.Lock()
+	reporter.closed = true
+	for _, v := range reporter.state.Steps {
+		if v.Result == runnerv1.Result_RESULT_UNSPECIFIED {
+			v.Result = runnerv1.Result_RESULT_CANCELLED
+		}
+	}
+	reporter.state.Result = runnerv1.Result_RESULT_FAILURE
+	reporter.logRows = append(reporter.logRows, &runnerv1.LogRow{
+		Time:    timestamppb.Now(),
+		Content: "Early termination",
+	})
+	reporter.state.StoppedAt = timestamppb.Now()
+	reporter.stateMu.Unlock()
+
+	// Step 3: RunDaemon's ReportState() — with the fix, this returns early
+	// because closed=true, preventing the server from deleting the runner.
+	assert.NoError(t, reporter.ReportState())
+	assert.False(t, runnerDeleted, "runner must not be deleted by RunDaemon's ReportState")
+
+	// Step 4: Close's final log upload succeeds because the runner is still alive.
+	// Flush pending rows first, then send the noMore signal (matching Close's retry behavior).
+	assert.NoError(t, reporter.ReportLog(false))
+	err = reporter.ReportLog(true)
+	assert.NoError(t, err, "final log upload must not fail: runner should not be deleted before Close finishes sending logs")
+}
+
 func TestReporter_RunDaemonClose_Race(t *testing.T) {
 	client := mocks.NewClient(t)
 	client.On("UpdateLog", mock.Anything, mock.Anything).Return(