coder · evgeniy-scherbina · May 6, 2025
diff --git a/cli/testdata/server-config.yaml.golden b/cli/testdata/server-config.yaml.golden
@@ -704,3 +704,7 @@ workspace_prebuilds:
   # backoff.
   # (default: 1h0m0s, type: duration)
   reconciliation_backoff_lookback_period: 1h0m0s
+  # Maximum number of consecutive failed prebuilds before a preset hits the hard
+  # limit. FailureHardLimit is disabled when set to zero.
+  # (default: 3, type: int)
+  failure_hard_limit: 3
diff --git a/coderd/apidoc/docs.go b/coderd/apidoc/docs.go
diff --git a/coderd/apidoc/swagger.json b/coderd/apidoc/swagger.json
diff --git a/coderd/database/dbauthz/dbauthz.go b/coderd/database/dbauthz/dbauthz.go
@@ -2234,6 +2234,15 @@ func (q *querier) GetPresetParametersByTemplateVersionID(ctx context.Context, ar
 	return q.db.GetPresetParametersByTemplateVersionID(ctx, args)
 }
 
+func (q *querier) GetPresetsAtFailureLimit(ctx context.Context, hardLimit int64) ([]database.GetPresetsAtFailureLimitRow, error) {
+	// GetPresetsAtFailureLimit returns a list of template version presets that have reached the hard failure limit.
+	// Request the same authorization permissions as GetPresetsBackoff, since the methods are similar.
+	if err := q.authorizeContext(ctx, policy.ActionViewInsights, rbac.ResourceTemplate.All()); err != nil {
+		return nil, err
+	}
+	return q.db.GetPresetsAtFailureLimit(ctx, hardLimit)
+}
+
 func (q *querier) GetPresetsBackoff(ctx context.Context, lookback time.Time) ([]database.GetPresetsBackoffRow, error) {
 	// GetPresetsBackoff returns a list of template version presets along with metadata such as the number of failed prebuilds.
 	if err := q.authorizeContext(ctx, policy.ActionViewInsights, rbac.ResourceTemplate.All()); err != nil {

diff --git a/coderd/database/dbauthz/dbauthz_test.go b/coderd/database/dbauthz/dbauthz_test.go
@@ -4857,6 +4857,11 @@ func (s *MethodTestSuite) TestPrebuilds() {
 			Asserts(rbac.ResourceWorkspace.All(), policy.ActionRead).
 			ErrorsWithInMemDB(dbmem.ErrUnimplemented)
 	}))
+	s.Run("GetPresetsAtFailureLimit", s.Subtest(func(_ database.Store, check *expects) {
+		check.Args(int64(0)).
+			Asserts(rbac.ResourceTemplate.All(), policy.ActionViewInsights).
+			ErrorsWithInMemDB(dbmem.ErrUnimplemented)
+	}))
 	s.Run("GetPresetsBackoff", s.Subtest(func(_ database.Store, check *expects) {
 		check.Args(time.Time{}).
 			Asserts(rbac.ResourceTemplate.All(), policy.ActionViewInsights).

diff --git a/coderd/database/dbmem/dbmem.go b/coderd/database/dbmem/dbmem.go
@@ -4362,6 +4362,10 @@ func (q *FakeQuerier) GetPresetParametersByTemplateVersionID(_ context.Context,
 	return parameters, nil
 }
 
+func (q *FakeQuerier) GetPresetsAtFailureLimit(ctx context.Context, hardLimit int64) ([]database.GetPresetsAtFailureLimitRow, error) {
+	return nil, ErrUnimplemented
+}
+
 func (*FakeQuerier) GetPresetsBackoff(_ context.Context, _ time.Time) ([]database.GetPresetsBackoffRow, error) {
 	return nil, ErrUnimplemented
 }

diff --git a/coderd/database/dbmetrics/querymetrics.go b/coderd/database/dbmetrics/querymetrics.go
diff --git a/coderd/database/dbmock/dbmock.go b/coderd/database/dbmock/dbmock.go
diff --git a/coderd/database/querier.go b/coderd/database/querier.go