resolve merge conflits

.github/workflows/dependency-review.yml

@@ -0,0 +1,18 @@
+name: 'Dependency Review'
+on: [pull_request]
+permissions:
+  contents: read
+  pull-requests: write
+jobs:
+  dependency-review:
+    runs-on: ubuntu-latest
+    steps:
+      - name: 'Checkout Repository'
+        uses: actions/checkout@v4
+      - name: Dependency Review
+        uses: actions/dependency-review-action@v4
+        with:
+          comment-summary-in-pr: on-failure
+          # Licenses need to come from https://spdx.org/licenses/
+          deny-licenses: GPL-1.0-only, GPL-1.0-or-later, GPL-2.0-only, GPL-2.0-or-later, GPL-3.0-only, GPL-3.0-or-later
+

CONTRIBUTING.md

@@ -1,3 +1,15 @@
 # Contributing to Flyte
 
-For information related to contributing to Flyte, please check out the [Contributing to Flyte](https://docs.flyte.org/en/latest/community/contribute.html) section of the documentation.
+For information related to contributing to Flyte, please check out the [Contributing to Flyte](https://docs.flyte.org/en/latest/community/contribute/index.html) section of the documentation.
+
+## Recommendation Order (For Beginners)
+* Setup dev environment 
+* Read the following and run at least 5 examples. Pay close attention to the generated outputs, the Graph view, task  
+  logs, etc. Repeat with as many examples as you need to have an initial understanding of what an execution looks like:
+  * https://docs.flyte.org/en/latest/user_guide/introduction.html
+  * https://docs.flyte.org/en/latest/flytesnacks/userguide.html
+* Finish reading the [Concepts](https://docs.flyte.org/en/latest/user_guide/concepts/main_concepts/index.html)
+* Finish reading the [Control Plane](https://docs.flyte.org/en/latest/user_guide/concepts/control_plane/index.html)
+* Finish reading the [Component Architecture](https://docs.flyte.org/en/latest/user_guide/concepts/component_architecture/index.html)
+* Choose 2 good first issues from the following and start solving them with the knowledge you have read.
+* Familiar with using [ImageSpec to push images to localhost for development](https://docs.flyte.org/en/latest/user_guide/customizing_dependencies/imagespec.html#image-spec-example)

charts/flyte-binary/README.md

@@ -116,6 +116,8 @@ Chart for basic single Flyte executable deployment
 | flyte-core-components.admin.disableClusterResourceManager | bool | `false` |  |
 | flyte-core-components.admin.disableScheduler | bool | `false` |  |
 | flyte-core-components.admin.disabled | bool | `false` |  |
+| flyte-core-components.admin.seedProjectsWithDetails[0].description | string | `"Default project setup."` |  |
+| flyte-core-components.admin.seedProjectsWithDetails[0].name | string | `"flytesnacks"` |  |
 | flyte-core-components.admin.seedProjects[0] | string | `"flytesnacks"` |  |
 | flyte-core-components.dataCatalog.disabled | bool | `false` |  |
 | flyte-core-components.propeller.disableWebhook | bool | `false` |  |

charts/flyte-binary/values.yaml

@@ -20,6 +20,14 @@ flyte-core-components:
     # seedProjects flyte projects to create by default
     seedProjects:
       - flytesnacks
+    # seedProjectsWithDetails flyte projects to create by default with description
+    # If there is an overlap between seedProjects and seedProjectsWithDetails,
+    # the description provided in seedProjectsWithDetails will take precedence.
+    # For seedProjects without a corresponding description in seedProjectsWithDetails,
+    # a default description will be auto-generated for the project.
+    seedProjectsWithDetails:
+      - name: flytesnacks
+        description: Default project setup.
   # propeller Configuration to disable propeller or any of its components
   propeller:
     # disabled Disables flytepropeller

charts/flyte-core/README.md

@@ -55,10 +55,25 @@ helm install gateway bitnami/contour -n flyte
 
 | Key | Type | Default | Description |
 |-----|------|---------|-------------|
-| cloud_events.aws.region | string | `"us-east-2"` |  |
+| cloud_events.aws | object | `{"region":"us-east-2"}` | Configuration for sending cloud events to AWS SNS |
 | cloud_events.enable | bool | `false` |  |
 | cloud_events.eventsPublisher.eventTypes[0] | string | `"all"` |  |
 | cloud_events.eventsPublisher.topicName | string | `"arn:aws:sns:us-east-2:123456:123-my-topic"` |  |
+| cloud_events.gcp | object | `{"region":"us-east1"}` | Configuration for sending cloud events to GCP Pub Sub |
+| cloud_events.kafka | object | `{"brokers":["mybroker:443"],"saslConfig":{"enabled":false,"handshake":true,"mechanism":"PLAIN","password":"","passwordPath":"","user":"kafka"},"tlsConfig":{"certPath":"/etc/ssl/certs/kafka-client.crt","enabled":false,"keyPath":"/etc/ssl/certs/kafka-client.key"},"version":"3.7.0"}` | Configuration for sending cloud events to Kafka |
+| cloud_events.kafka.brokers | list | `["mybroker:443"]` | The kafka brokers to talk to |
+| cloud_events.kafka.saslConfig | object | `{"enabled":false,"handshake":true,"mechanism":"PLAIN","password":"","passwordPath":"","user":"kafka"}` | SASL based authentication |
+| cloud_events.kafka.saslConfig.enabled | bool | `false` | Whether to use SASL authentication |
+| cloud_events.kafka.saslConfig.handshake | bool | `true` | Whether the send the SASL handsahke first |
+| cloud_events.kafka.saslConfig.mechanism | string | `"PLAIN"` | Which SASL mechanism to use. Defaults to PLAIN |
+| cloud_events.kafka.saslConfig.password | string | `""` | The password for the kafka user |
+| cloud_events.kafka.saslConfig.passwordPath | string | `""` | Optional mount path of file containing the kafka password. |
+| cloud_events.kafka.saslConfig.user | string | `"kafka"` | The kafka user |
+| cloud_events.kafka.tlsConfig | object | `{"certPath":"/etc/ssl/certs/kafka-client.crt","enabled":false,"keyPath":"/etc/ssl/certs/kafka-client.key"}` | Certificate based authentication |
+| cloud_events.kafka.tlsConfig.certPath | string | `"/etc/ssl/certs/kafka-client.crt"` | Path to the client certificate |
+| cloud_events.kafka.tlsConfig.enabled | bool | `false` | Whether to use certificate based authentication or TLS |
+| cloud_events.kafka.tlsConfig.keyPath | string | `"/etc/ssl/certs/kafka-client.key"` | Path to the client private key |
+| cloud_events.kafka.version | string | `"3.7.0"` | The version of Kafka |
 | cloud_events.type | string | `"aws"` |  |
 | cluster_resource_manager | object | `{"config":{"cluster_resources":{"customData":[{"production":[{"projectQuotaCpu":{"value":"5"}},{"projectQuotaMemory":{"value":"4000Mi"}}]},{"staging":[{"projectQuotaCpu":{"value":"2"}},{"projectQuotaMemory":{"value":"3000Mi"}}]},{"development":[{"projectQuotaCpu":{"value":"4"}},{"projectQuotaMemory":{"value":"3000Mi"}}]}],"refreshInterval":"5m","standaloneDeployment":false,"templatePath":"/etc/flyte/clusterresource/templates"}},"enabled":true,"nodeSelector":{},"podAnnotations":{},"podEnv":{},"podLabels":{},"prometheus":{"enabled":false,"path":"/metrics","port":10254},"resources":{},"service_account_name":"flyteadmin","standaloneDeployment":false,"templates":[{"key":"aa_namespace","value":"apiVersion: v1\nkind: Namespace\nmetadata:\n  name: {{ namespace }}\nspec:\n  finalizers:\n  - kubernetes\n"},{"key":"ab_project_resource_quota","value":"apiVersion: v1\nkind: ResourceQuota\nmetadata:\n  name: project-quota\n  namespace: {{ namespace }}\nspec:\n  hard:\n    limits.cpu: {{ projectQuotaCpu }}\n    limits.memory: {{ projectQuotaMemory }}\n"}]}` | Configuration for the Cluster resource manager component. This is an optional component, that enables automatic cluster configuration. This is useful to set default quotas, manage namespaces etc that map to a project/domain |
 | cluster_resource_manager.config | object | `{"cluster_resources":{"customData":[{"production":[{"projectQuotaCpu":{"value":"5"}},{"projectQuotaMemory":{"value":"4000Mi"}}]},{"staging":[{"projectQuotaCpu":{"value":"2"}},{"projectQuotaMemory":{"value":"3000Mi"}}]},{"development":[{"projectQuotaCpu":{"value":"4"}},{"projectQuotaMemory":{"value":"3000Mi"}}]}],"refreshInterval":"5m","standaloneDeployment":false,"templatePath":"/etc/flyte/clusterresource/templates"}}` | Configmap for ClusterResource parameters |
@@ -230,7 +245,6 @@ helm install gateway bitnami/contour -n flyte
 | flytepropeller.additionalVolumeMounts | list | `[]` | Appends additional volume mounts to the main container's spec. May include template values. |
 | flytepropeller.additionalVolumes | list | `[]` | Appends additional volumes to the deployment spec. May include template values. |
 | flytepropeller.affinity | object | `{}` | affinity for Flytepropeller deployment |
-| flytepropeller.cacheSizeMbs | int | `0` |  |
 | flytepropeller.clusterName | string | `""` | Defines the cluster name used in events sent to Admin |
 | flytepropeller.configPath | string | `"/etc/flyte/config/*.yaml"` | Default regex string for searching configuration files |
 | flytepropeller.createCRDs | bool | `true` | Whether to install the flyteworkflows CRD with helm |
@@ -292,7 +306,7 @@ helm install gateway bitnami/contour -n flyte
 | sparkoperator.enabled | bool | `false` | - enable or disable Sparkoperator deployment installation |
 | sparkoperator.plugin_config | object | `{"plugins":{"spark":{"spark-config-default":[{"spark.hadoop.fs.s3a.aws.credentials.provider":"com.amazonaws.auth.DefaultAWSCredentialsProviderChain"},{"spark.hadoop.mapreduce.fileoutputcommitter.algorithm.version":"2"},{"spark.kubernetes.allocation.batch.size":"50"},{"spark.hadoop.fs.s3a.acl.default":"BucketOwnerFullControl"},{"spark.hadoop.fs.s3n.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem"},{"spark.hadoop.fs.AbstractFileSystem.s3n.impl":"org.apache.hadoop.fs.s3a.S3A"},{"spark.hadoop.fs.s3.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem"},{"spark.hadoop.fs.AbstractFileSystem.s3.impl":"org.apache.hadoop.fs.s3a.S3A"},{"spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem"},{"spark.hadoop.fs.AbstractFileSystem.s3a.impl":"org.apache.hadoop.fs.s3a.S3A"},{"spark.hadoop.fs.s3a.multipart.threshold":"536870912"},{"spark.blacklist.enabled":"true"},{"spark.blacklist.timeout":"5m"},{"spark.task.maxfailures":"8"}]}}}` | Spark plugin configuration |
 | sparkoperator.plugin_config.plugins.spark.spark-config-default | list | `[{"spark.hadoop.fs.s3a.aws.credentials.provider":"com.amazonaws.auth.DefaultAWSCredentialsProviderChain"},{"spark.hadoop.mapreduce.fileoutputcommitter.algorithm.version":"2"},{"spark.kubernetes.allocation.batch.size":"50"},{"spark.hadoop.fs.s3a.acl.default":"BucketOwnerFullControl"},{"spark.hadoop.fs.s3n.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem"},{"spark.hadoop.fs.AbstractFileSystem.s3n.impl":"org.apache.hadoop.fs.s3a.S3A"},{"spark.hadoop.fs.s3.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem"},{"spark.hadoop.fs.AbstractFileSystem.s3.impl":"org.apache.hadoop.fs.s3a.S3A"},{"spark.hadoop.fs.s3a.impl":"org.apache.hadoop.fs.s3a.S3AFileSystem"},{"spark.hadoop.fs.AbstractFileSystem.s3a.impl":"org.apache.hadoop.fs.s3a.S3A"},{"spark.hadoop.fs.s3a.multipart.threshold":"536870912"},{"spark.blacklist.enabled":"true"},{"spark.blacklist.timeout":"5m"},{"spark.task.maxfailures":"8"}]` | Spark default configuration |
-| storage | object | `{"bucketName":"my-s3-bucket","custom":{},"enableMultiContainer":false,"gcs":null,"limits":{"maxDownloadMBs":10},"s3":{"accessKey":"","authType":"iam","region":"us-east-1","secretKey":""},"type":"sandbox"}` | ----------------------------------------------------  STORAGE SETTINGS  |
+| storage | object | `{"bucketName":"my-s3-bucket","cache":{"maxSizeMBs":0,"targetGCPercent":70},"custom":{},"enableMultiContainer":false,"gcs":null,"limits":{"maxDownloadMBs":10},"s3":{"accessKey":"","authType":"iam","region":"us-east-1","secretKey":""},"type":"sandbox"}` | ----------------------------------------------------  STORAGE SETTINGS  |
 | storage.bucketName | string | `"my-s3-bucket"` | bucketName defines the storage bucket flyte will use. Required for all types except for sandbox. |
 | storage.custom | object | `{}` | Settings for storage type custom. See https://github.com/graymeta/stow for supported storage providers/settings. |
 | storage.enableMultiContainer | bool | `false` | toggles multi-container storage config |

charts/flyte-core/templates/_helpers.tpl

@@ -237,4 +237,7 @@ storage:
   enable-multicontainer: {{ .Values.storage.enableMultiContainer }}
   limits:
     maxDownloadMBs: {{ .Values.storage.limits.maxDownloadMBs }}
+  cache:
+    max_size_mbs: {{ .Values.storage.cache.maxSizeMBs }}
+    target_gc_percent: {{ .Values.storage.cache.targetGCPercent }}
 {{- end }}

charts/flyte-core/templates/propeller/configmap.yaml

@@ -47,11 +47,6 @@ data:
 {{- end }}
 {{- end }}
   storage.yaml: | {{ tpl (include "storage" .) $ | nindent 4 }}
-  cache.yaml: |
-    storage:
-      cache:
-        max_size_mbs: {{ .Values.flytepropeller.cacheSizeMbs }}
-        target_gc_percent: 70
 {{- with .Values.configmap.task_logs }}
   task_logs.yaml: | {{ tpl (toYaml .) $ | nindent 4 }}
 {{- end }}

charts/flyte-core/values-eks.yaml

@@ -102,7 +102,6 @@ flytepropeller:
       cpu: 1
       ephemeral-storage: 1Gi
       memory: 2Gi
-  cacheSizeMbs: 1024
   # -- Sets priorityClassName for propeller pod(s).
   priorityClassName: "system-cluster-critical"
   affinity:
@@ -191,6 +190,8 @@ storage:
   bucketName: "{{ .Values.userSettings.bucketName }}"
   s3:
     region: "{{ .Values.userSettings.accountRegion }}"
+  cache:
+    maxSizeMBs: 1024
 
 db:
   datacatalog:

charts/flyte-core/values-keycloak-idp-flyteclients-without-browser.yaml

@@ -215,7 +215,6 @@ flytepropeller:
       cpu: 10m
       ephemeral-storage: 50Mi
       memory: 100Mi
-  cacheSizeMbs: 0
   # -- Default regex string for searching configuration files
   configPath: /etc/flyte/config/*.yaml
 
@@ -399,6 +398,8 @@ storage:
   # -- default limits being applied to storage config
   limits:
     maxDownloadMBs: 10
+  cache:
+    maxSizeMBs: 0
 
 # Database configuration(These are the values for a pgdb instance with hostname of postgres-flyte and postgres/password creds)
 db:

charts/flyte-core/values.yaml

@@ -319,7 +319,6 @@ flytepropeller:
       cpu: 10m
       ephemeral-storage: 50Mi
       memory: 100Mi
-  cacheSizeMbs: 0
   # -- Error reporting
   terminationMessagePolicy: FallbackToLogsOnError
   # -- Default regex string for searching configuration files
@@ -610,6 +609,9 @@ storage:
   # -- default limits being applied to storage config
   limits:
     maxDownloadMBs: 10
+  cache:
+    maxSizeMBs: 0
+    targetGCPercent: 70
 
 # Database configuration
 db:
@@ -944,15 +946,48 @@ external_events:
 # an SNS topic (or gcp equivalent)
 cloud_events:
   enable: false
-  type: aws
-  aws:
-    region: us-east-2
   eventsPublisher:
     # Make sure this is not a fifo queue. Admin does not yet support
     # writing to fifo sns topics.
     topicName: "arn:aws:sns:us-east-2:123456:123-my-topic"
     eventTypes:
       - all  # Or workflow, node, task. Or "*"
+  type: aws
+  # -- Configuration for sending cloud events to AWS SNS
+  aws:
+    region: us-east-2
+  # -- Configuration for sending cloud events to GCP Pub Sub
+  gcp:
+    region: us-east1
+  # -- Configuration for sending cloud events to Kafka
+  kafka:
+    # -- The version of Kafka
+    version: "3.7.0"
+    # -- The kafka brokers to talk to
+    brokers:
+      - mybroker:443
+    # -- SASL based authentication
+    saslConfig:
+      # -- Whether to use SASL authentication
+      enabled: false
+      # -- The kafka user
+      user: kafka
+      # -- The password for the kafka user
+      password: ""
+      # -- Optional mount path of file containing the kafka password.
+      passwordPath: ""
+      # -- Whether the send the SASL handsahke first
+      handshake: true
+      # -- Which SASL mechanism to use. Defaults to PLAIN
+      mechanism: PLAIN
+    # -- Certificate based authentication
+    tlsConfig:
+      # -- Whether to use certificate based authentication or TLS
+      enabled: false
+      # -- Path to the client certificate
+      certPath: /etc/ssl/certs/kafka-client.crt
+      # -- Path to the client private key
+      keyPath: /etc/ssl/certs/kafka-client.key
 
 # -- Configuration for the Cluster resource manager component. This is an optional component, that enables automatic
 # cluster configuration. This is useful to set default quotas, manage namespaces etc that map to a project/domain