Prevent stale issue cleanup from crossing repository boundaries

The previous missing-issue cleanup only keyed deletes by connection and issue identifiers, which could reach too broadly when an issue was transferred between repositories under the same DevLake connection. This change scopes cleanup to the source repository by carrying RepoId through the refresh path and requiring the source RawDataOrigin parameters before deleting stale tool rows.

Constraint: Keep the fix inside the existing github_graphql collector path without schema changes
Rejected: Continue deleting by connection_id + github_id only | could remove destination-repository rows after transfers
Rejected: Disable stale cleanup for all missing issues | would leave deleted-issue failures recurring
Confidence: medium
Scope-risk: moderate
Directive: Preserve source-scope guards if future cleanup paths touch transferred issues again
Tested: go test ./plugins/github_graphql/tasks; go build ./helpers/pluginhelper/api ./plugins/github_graphql/tasks
Not-tested: End-to-end transfer scenario against a live GitHub repository

Author: squatboy

backend/plugins/github_graphql/tasks/issue_collector.go

@@ -90,6 +90,15 @@ type GraphqlQueryIssue struct {
 
 type missingGithubIssueRef struct {
 	ConnectionId  uint64
+	RepoId        int
+	GithubId      int
+	Number        int
+	RawDataOrigin common.RawDataOrigin
+}
+
+type missingGithubIssueCleanupScope struct {
+	ConnectionId  uint64
+	RepoId        int
 	GithubId      int
 	Number        int
 	RawDataOrigin common.RawDataOrigin
@@ -195,6 +204,7 @@ func CollectIssues(taskCtx plugin.SubTaskContext) errors.Error {
 				issueUpdatedAt[inputIssue.Number] = inputIssue.GithubUpdatedAt
 				query.requestedIssues[inputIssue.Number] = missingGithubIssueRef{
 					ConnectionId:  inputIssue.ConnectionId,
+					RepoId:        inputIssue.RepoId,
 					GithubId:      inputIssue.GithubId,
 					Number:        inputIssue.Number,
 					RawDataOrigin: inputIssue.RawDataOrigin,
@@ -261,18 +271,82 @@ func findMissingGithubIssues(requestedIssues map[int]missingGithubIssueRef, reso
 func cleanupMissingGithubIssues(db dal.Dal, logger log.Logger, issues []missingGithubIssueRef) errors.Error {
 	var allErrors []error
 	for _, issue := range issues {
-		logger.Warn(nil, "GitHub issue #%d no longer resolves from the source API, deleting stale local data", issue.Number)
-		err := cleanupMissingGithubIssue(db, issue)
+		scope, ok := buildMissingGithubIssueCleanupScope(issue)
+		if !ok {
+			logger.Warn(nil, "GitHub issue #%d no longer resolves from the source API, but source scope is incomplete so stale cleanup is skipped", issue.Number)
+			continue
+		}
+		logger.Warn(nil, "GitHub issue #%d no longer resolves from the source API, deleting stale local data for the current repository scope", issue.Number)
+		err := cleanupMissingGithubIssue(db, scope)
 		if err != nil {
 			allErrors = append(allErrors, err)
 		}
 	}
 	return errors.Default.Combine(allErrors)
 }
 
-func cleanupMissingGithubIssue(db dal.Dal, issue missingGithubIssueRef) errors.Error {
+func buildMissingGithubIssueCleanupScope(issue missingGithubIssueRef) (*missingGithubIssueCleanupScope, bool) {
+	if issue.ConnectionId == 0 || issue.RepoId == 0 || issue.GithubId == 0 || issue.RawDataOrigin.RawDataTable == "" || issue.RawDataOrigin.RawDataParams == "" {
+		return nil, false
+	}
+	return &missingGithubIssueCleanupScope{
+		ConnectionId:  issue.ConnectionId,
+		RepoId:        issue.RepoId,
+		GithubId:      issue.GithubId,
+		Number:        issue.Number,
+		RawDataOrigin: issue.RawDataOrigin,
+	}, true
+}
+
+func (scope *missingGithubIssueCleanupScope) issueScopedClauses() []dal.Clause {
+	return []dal.Clause{
+		dal.Where(
+			"connection_id = ? AND issue_id = ? AND _raw_data_table = ? AND _raw_data_params = ?",
+			scope.ConnectionId,
+			scope.GithubId,
+			scope.RawDataOrigin.RawDataTable,
+			scope.RawDataOrigin.RawDataParams,
+		),
+	}
+}
+
+func (scope *missingGithubIssueCleanupScope) assigneeScopedClauses() []dal.Clause {
+	return []dal.Clause{
+		dal.Where(
+			"connection_id = ? AND repo_id = ? AND issue_id = ? AND _raw_data_table = ? AND _raw_data_params = ?",
+			scope.ConnectionId,
+			scope.RepoId,
+			scope.GithubId,
+			scope.RawDataOrigin.RawDataTable,
+			scope.RawDataOrigin.RawDataParams,
+		),
+	}
+}
+
+func (scope *missingGithubIssueCleanupScope) githubIssueScopedClauses() []dal.Clause {
+	return []dal.Clause{
+		dal.Where(
+			"connection_id = ? AND repo_id = ? AND github_id = ? AND _raw_data_table = ? AND _raw_data_params = ?",
+			scope.ConnectionId,
+			scope.RepoId,
+			scope.GithubId,
+			scope.RawDataOrigin.RawDataTable,
+			scope.RawDataOrigin.RawDataParams,
+		),
+	}
+}
+
+func (scope *missingGithubIssueCleanupScope) rawDataScopedClauses() []dal.Clause {
+	if scope.RawDataOrigin.RawDataId == 0 {
+		return nil
+	}
+	return []dal.Clause{dal.Where("id = ?", scope.RawDataOrigin.RawDataId)}
+}
+
+func cleanupMissingGithubIssue(db dal.Dal, scope *missingGithubIssueCleanupScope) errors.Error {
 	deleteByIssueId := func(model any, table string) errors.Error {
-		err := db.Delete(model, dal.From(table), dal.Where("connection_id = ? AND issue_id = ?", issue.ConnectionId, issue.GithubId))
+		clauses := append([]dal.Clause{dal.From(table)}, scope.issueScopedClauses()...)
+		err := db.Delete(model, clauses...)
 		if err != nil {
 			return errors.Default.Wrap(err, "failed to delete stale github issue data from "+table)
 		}
@@ -291,31 +365,31 @@ func cleanupMissingGithubIssue(db dal.Dal, issue missingGithubIssueRef) errors.E
 	if err != nil {
 		return err
 	}
-	err = deleteByIssueId(&models.GithubIssueAssignee{}, models.GithubIssueAssignee{}.TableName())
+	err = db.Delete(
+		&models.GithubIssueAssignee{},
+		append([]dal.Clause{dal.From(models.GithubIssueAssignee{}.TableName())}, scope.assigneeScopedClauses()...)...,
+	)
 	if err != nil {
-		return err
+		return errors.Default.Wrap(err, "failed to delete stale github issue assignees")
 	}
 	err = db.Delete(
 		&models.GithubPrIssue{},
-		dal.From(models.GithubPrIssue{}.TableName()),
-		dal.Where("connection_id = ? AND issue_id = ?", issue.ConnectionId, issue.GithubId),
+		append([]dal.Clause{dal.From(models.GithubPrIssue{}.TableName())}, scope.issueScopedClauses()...)...,
 	)
 	if err != nil {
 		return errors.Default.Wrap(err, "failed to delete stale github pull request issue links")
 	}
 	err = db.Delete(
 		&models.GithubIssue{},
-		dal.From(models.GithubIssue{}.TableName()),
-		dal.Where("connection_id = ? AND github_id = ?", issue.ConnectionId, issue.GithubId),
+		append([]dal.Clause{dal.From(models.GithubIssue{}.TableName())}, scope.githubIssueScopedClauses()...)...,
 	)
 	if err != nil {
 		return errors.Default.Wrap(err, "failed to delete stale github issue")
 	}
-	if issue.RawDataOrigin.RawDataTable != "" && issue.RawDataOrigin.RawDataId != 0 {
+	if rawDataClauses := scope.rawDataScopedClauses(); len(rawDataClauses) > 0 {
 		err = db.Delete(
 			&api.RawData{},
-			dal.From(issue.RawDataOrigin.RawDataTable),
-			dal.Where("id = ?", issue.RawDataOrigin.RawDataId),
+			append([]dal.Clause{dal.From(scope.RawDataOrigin.RawDataTable)}, rawDataClauses...)...,
 		)
 		if err != nil {
 			return errors.Default.Wrap(err, "failed to delete stale raw github issue")

backend/plugins/github_graphql/tasks/issue_collector_test.go

@@ -20,6 +20,7 @@ package tasks
 import (
 	"testing"
 
+	"github.com/apache/incubator-devlake/core/dal"
 	"github.com/apache/incubator-devlake/core/models/common"
 	"github.com/stretchr/testify/assert"
 )
@@ -28,15 +29,18 @@ func TestFindMissingGithubIssues(t *testing.T) {
 	requestedIssues := map[int]missingGithubIssueRef{
 		17: {
 			ConnectionId: 1,
+			RepoId:       101,
 			GithubId:     1700,
 			Number:       17,
 			RawDataOrigin: common.RawDataOrigin{
-				RawDataTable: "_raw_github_graphql_issues",
-				RawDataId:    10,
+				RawDataTable:  "_raw_github_graphql_issues",
+				RawDataParams: "{\"connectionId\":1,\"name\":\"repo-a\"}",
+				RawDataId:     10,
 			},
 		},
 		18: {
 			ConnectionId: 1,
+			RepoId:       101,
 			GithubId:     1800,
 			Number:       18,
 		},
@@ -51,6 +55,7 @@ func TestFindMissingGithubIssues(t *testing.T) {
 	if assert.Len(t, missingIssues, 1) {
 		assert.Equal(t, 17, missingIssues[0].Number)
 		assert.Equal(t, 1700, missingIssues[0].GithubId)
+		assert.Equal(t, 101, missingIssues[0].RepoId)
 		assert.Equal(t, uint64(10), missingIssues[0].RawDataOrigin.RawDataId)
 	}
 }
@@ -72,3 +77,63 @@ func TestFindMissingGithubIssuesSkipsZeroValueResponses(t *testing.T) {
 		assert.Equal(t, 17, missingIssues[0].Number)
 	}
 }
+
+func TestBuildMissingGithubIssueCleanupScopeRequiresSourceRawDataParams(t *testing.T) {
+	scope, ok := buildMissingGithubIssueCleanupScope(missingGithubIssueRef{
+		ConnectionId: 1,
+		RepoId:       101,
+		GithubId:     1700,
+		Number:       17,
+		RawDataOrigin: common.RawDataOrigin{
+			RawDataTable: "_raw_github_graphql_issues",
+		},
+	})
+
+	assert.False(t, ok)
+	assert.Nil(t, scope)
+}
+
+func TestBuildMissingGithubIssueCleanupScopeBuildsRepoScopedClauses(t *testing.T) {
+	scope, ok := buildMissingGithubIssueCleanupScope(missingGithubIssueRef{
+		ConnectionId: 1,
+		RepoId:       101,
+		GithubId:     1700,
+		Number:       17,
+		RawDataOrigin: common.RawDataOrigin{
+			RawDataTable:  "_raw_github_graphql_issues",
+			RawDataParams: "{\"connectionId\":1,\"name\":\"repo-a\"}",
+			RawDataId:     10,
+		},
+	})
+	if !assert.True(t, ok) {
+		return
+	}
+
+	issueClause := scope.issueScopedClauses()[0]
+	issueWhere, ok := issueClause.Data.(dal.DalClause)
+	if assert.True(t, ok) {
+		assert.Equal(t, "connection_id = ? AND issue_id = ? AND _raw_data_table = ? AND _raw_data_params = ?", issueWhere.Expr)
+		assert.Equal(t, []interface{}{uint64(1), 1700, "_raw_github_graphql_issues", "{\"connectionId\":1,\"name\":\"repo-a\"}"}, issueWhere.Params)
+	}
+
+	assigneeClause := scope.assigneeScopedClauses()[0]
+	assigneeWhere, ok := assigneeClause.Data.(dal.DalClause)
+	if assert.True(t, ok) {
+		assert.Equal(t, "connection_id = ? AND repo_id = ? AND issue_id = ? AND _raw_data_table = ? AND _raw_data_params = ?", assigneeWhere.Expr)
+		assert.Equal(t, []interface{}{uint64(1), 101, 1700, "_raw_github_graphql_issues", "{\"connectionId\":1,\"name\":\"repo-a\"}"}, assigneeWhere.Params)
+	}
+
+	githubIssueClause := scope.githubIssueScopedClauses()[0]
+	githubIssueWhere, ok := githubIssueClause.Data.(dal.DalClause)
+	if assert.True(t, ok) {
+		assert.Equal(t, "connection_id = ? AND repo_id = ? AND github_id = ? AND _raw_data_table = ? AND _raw_data_params = ?", githubIssueWhere.Expr)
+		assert.Equal(t, []interface{}{uint64(1), 101, 1700, "_raw_github_graphql_issues", "{\"connectionId\":1,\"name\":\"repo-a\"}"}, githubIssueWhere.Params)
+	}
+
+	rawDataClause := scope.rawDataScopedClauses()[0]
+	rawDataWhere, ok := rawDataClause.Data.(dal.DalClause)
+	if assert.True(t, ok) {
+		assert.Equal(t, "id = ?", rawDataWhere.Expr)
+		assert.Equal(t, []interface{}{uint64(10)}, rawDataWhere.Params)
+	}
+}