Node heartbeats

.cspell/custom-dictionary.txt

@@ -203,6 +203,7 @@ multierror
 multiformats
 Muxed
 mypy
+NATS
 nbconvert
 nemt
 nocheck

cmd/cli/node/columns.go

@@ -25,9 +25,13 @@ var alwaysColumns = []output.TableColumn[*models.NodeInfo]{
 		Value:        func(ni *models.NodeInfo) string { return ni.NodeType.String() },
 	},
 	{
-		ColumnConfig: table.ColumnConfig{Name: "status"},
+		ColumnConfig: table.ColumnConfig{Name: "approval"},
 		Value:        func(ni *models.NodeInfo) string { return ni.Approval.String() },
 	},
+	{
+		ColumnConfig: table.ColumnConfig{Name: "status"},
+		Value:        func(ni *models.NodeInfo) string { return ni.State.String() },
+	},
 }
 
 var toggleColumns = map[string][]output.TableColumn[*models.NodeInfo]{

cmd/cli/node/list.go

@@ -16,15 +16,17 @@ import (
 
 var defaultColumnGroups = []string{"labels", "capacity"}
 var orderByFields = []string{"id", "type", "available_cpu", "available_memory", "available_disk", "available_gpu", "status"}
-var filterStatusValues = []string{"approved", "pending", "rejected"}
+var filterApprovalValues = []string{"approved", "pending", "rejected"}
+var filterStatusValues = []string{"healthy", "unhealthy", "unknown"}
 
 // ListOptions is a struct to support node command
 type ListOptions struct {
 	output.OutputOptions
 	cliflags.ListOptions
-	ColumnGroups   []string
-	Labels         string
-	FilterByStatus string
+	ColumnGroups     []string
+	Labels           string
+	FilterByApproval string
+	FilterByStatus   string
 }
 
 // NewListOptions returns initialized Options
@@ -42,22 +44,24 @@ func NewListCmd() *cobra.Command {
 		Use:   "list",
 		Short: "List info of network nodes. ",
 		Args:  cobra.NoArgs,
-		Run:   o.run,
+		RunE:  o.run,
 	}
 	nodeCmd.Flags().StringSliceVar(&o.ColumnGroups, "show", o.ColumnGroups,
 		fmt.Sprintf("What column groups to show. Zero or more of: %q", maps.Keys(toggleColumns)))
 	nodeCmd.Flags().StringVar(&o.Labels, "labels", o.Labels,
 		"Filter nodes by labels. See https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/ for more information.")
 	nodeCmd.Flags().AddFlagSet(cliflags.ListFlags(&o.ListOptions))
 	nodeCmd.Flags().AddFlagSet(cliflags.OutputFormatFlags(&o.OutputOptions))
+	nodeCmd.Flags().StringVar(&o.FilterByApproval, "filter-approval", o.FilterByApproval,
+		fmt.Sprintf("Filter nodes by approval. One of: %q", filterApprovalValues))
 	nodeCmd.Flags().StringVar(&o.FilterByStatus, "filter-status", o.FilterByStatus,
 		fmt.Sprintf("Filter nodes by status. One of: %q", filterStatusValues))
 
 	return nodeCmd
 }
 
 // Run executes node command
-func (o *ListOptions) run(cmd *cobra.Command, _ []string) {
+func (o *ListOptions) run(cmd *cobra.Command, _ []string) error {
 	ctx := cmd.Context()
 
 	var err error
@@ -69,15 +73,22 @@ func (o *ListOptions) run(cmd *cobra.Command, _ []string) {
 		}
 	}
 
+	if o.FilterByApproval != "" {
+		if !slices.Contains(filterApprovalValues, o.FilterByApproval) {
+			return fmt.Errorf("cannot use '%s' as filter approval value, should be one of: %q", o.FilterByApproval, filterApprovalValues)
+		}
+	}
+
 	if o.FilterByStatus != "" {
 		if !slices.Contains(filterStatusValues, o.FilterByStatus) {
-			util.Fatal(cmd, fmt.Errorf("cannot use '%s' as filter status value, should be one of: %q", o.FilterByStatus, filterStatusValues), 1)
+			return fmt.Errorf("cannot use '%s' as filter status value, should be one of: %q", o.FilterByStatus, filterStatusValues)
 		}
 	}
 
 	response, err := util.GetAPIClientV2(cmd).Nodes().List(ctx, &apimodels.ListNodesRequest{
-		Labels:         labelRequirements,
-		FilterByStatus: o.FilterByStatus,
+		Labels:           labelRequirements,
+		FilterByApproval: o.FilterByApproval,
+		FilterByStatus:   o.FilterByStatus,
 		BaseListRequest: apimodels.BaseListRequest{
 			Limit:     o.Limit,
 			NextToken: o.NextToken,
@@ -97,4 +108,6 @@ func (o *ListOptions) run(cmd *cobra.Command, _ []string) {
 	if err = output.Output(cmd, columns, o.OutputOptions, response.Nodes); err != nil {
 		util.Fatal(cmd, fmt.Errorf("failed to output: %w", err), 1)
 	}
+
+	return nil
 }

docs/docs/dev/cli-reference/cli/node/approve/index.md

@@ -0,0 +1,67 @@
+---
+sidebar_label: approve
+---
+
+# Command: `node approve`
+
+The `bacalhau node approve` command offers administrations the ability to approve the cluster membership for a node using its unique identifier.
+
+## Description:
+
+Using the `approve` sub-command under the `bacalhau node` umbrella, users can allow a node in the pending state to join the cluster and receive work. This feature is crucial for system administrators to manage the cluster.
+
+## Usage:
+
+```bash
+bacalhau node approve [id] [flags]
+```
+
+## Flags:
+
+- `[id]`:
+
+  - The unique identifier of the node you wish to describe.
+
+- `-h`, `--help`:
+
+  - Displays the help documentation for the `describe` command.
+
+- `-m message`:
+
+  - A message to be attached to the approval action.
+
+## Global Flags:
+
+- `--api-host string`:
+
+  - Specifies the host for client-server communication through REST. This flag is overridden if the `BACALHAU_API_HOST` environment variable is set.
+  - Default: `"bootstrap.production.bacalhau.org"`
+
+- `--api-port int`:
+
+  - Designates the port for REST-based communication between client and server. This flag is overlooked if the `BACALHAU_API_PORT` environment variable is defined.
+  - Default: `1234`
+
+- `--log-mode logging-mode`:
+
+  - Determines the log format preference.
+  - Options: `'default','station','json','combined','event'`
+  - Default: `'default'`
+
+- `--repo string`:
+  - Points to the bacalhau repository's path.
+  - Default: `"`$HOME/.bacalhau"`
+
+## Examples:
+
+1. Approve a Node with ID `nodeID123`:
+
+   ```bash
+   bacalhau node approve nodeID123
+   ```
+
+2. Approve a Node with an audit message:
+
+   ```bash
+   bacalhau node approve nodeID123 -m "okay"
+   ```

docs/docs/dev/cli-reference/cli/node/delete/index.md

@@ -0,0 +1,67 @@
+---
+sidebar_label: delete
+---
+
+# Command: `node approve`
+
+The `bacalhau node delete` command offers administrations the ability to remove a node from the cluster using its unique identifier.
+
+## Description:
+
+Using the `delete` sub-command, administrators can remove a node from the list of available compute nodes in the cluster. This feature is necessary for the management of the infrastructure.
+
+## Usage:
+
+```bash
+bacalhau node delete [id] [flags]
+```
+
+## Flags:
+
+- `[id]`:
+
+  - The unique identifier of the node you wish to describe.
+
+- `-h`, `--help`:
+
+  - Displays the help documentation for the `describe` command.
+
+- `-m message`:
+
+  - A message to be attached to the deletion action.
+
+## Global Flags:
+
+- `--api-host string`:
+
+  - Specifies the host for client-server communication through REST. This flag is overridden if the `BACALHAU_API_HOST` environment variable is set.
+  - Default: `"bootstrap.production.bacalhau.org"`
+
+- `--api-port int`:
+
+  - Designates the port for REST-based communication between client and server. This flag is overlooked if the `BACALHAU_API_PORT` environment variable is defined.
+  - Default: `1234`
+
+- `--log-mode logging-mode`:
+
+  - Determines the log format preference.
+  - Options: `'default','station','json','combined','event'`
+  - Default: `'default'`
+
+- `--repo string`:
+  - Points to the bacalhau repository's path.
+  - Default: `"`$HOME/.bacalhau"`
+
+## Examples:
+
+1. Delete the Node with ID `nodeID123`:
+
+   ```bash
+   bacalhau node delete nodeID123
+   ```
+
+2. Delete a Node with an audit message:
+
+   ```bash
+   bacalhau node delete nodeID123 -m "bad actor"
+   ```

docs/docs/dev/cli-reference/cli/node/index.md

@@ -12,48 +12,75 @@ bacalhau node [command]
 
 ## Available Commands
 
+1. **[approve](./approve)**:
+
+   - Description: Approves a single node to join the cluster.
+   - Usage:
+
+     ```bash
+     bacalhau node approve
+     ```
+
+1. **[delete](./delete)**:
+
+   - Description: Deletes a node from the cluster using its ID.
+   - Usage:
+     ```bash
+     bacalhau node delete
+     ```
+
 1. **[describe](./describe)**:
-    - Description: Retrieves detailed information of a node using its ID.
-    - Usage:
-        ```bash
-        bacalhau node describe
-        ```
-
-2. **[list](./list)**:
-    - Description: Lists the details of all nodes present in the network.
-    - Usage:
-        ```bash
-        bacalhau node list
-        ```
+
+   - Description: Retrieves detailed information of a node using its ID.
+   - Usage:
+     ```bash
+     bacalhau node describe
+     ```
+
+1. **[list](./list)**:
+
+   - Description: Lists the details of all nodes present in the network.
+   - Usage:
+     ```bash
+     bacalhau node list
+     ```
+
+1. **[reject](./reject)**:
+
+- Description: Reject a specific node's request to join the cluster.
+- Usage:
+  ```bash
+  bacalhau node reject
+  ```
 
 For comprehensive details on any of the sub-commands, run:
+
 ```bash
 bacalhau node [command] --help
 ```
 
 ## Flags
 
 - `-h`, `--help`:
-    - Description: Shows the help information for the `node` command.
+  - Description: Shows the help information for the `node` command.
 
 ## Global Flags
 
 - `--api-host string`:
-    - Description: Specifies the host for RESTful communication between the client and server. The flag will be ignored if the `BACALHAU_API_HOST` environment variable is set.
-    - Default: `bootstrap.production.bacalhau.org`
+
+  - Description: Specifies the host for RESTful communication between the client and server. The flag will be ignored if the `BACALHAU_API_HOST` environment variable is set.
+  - Default: `bootstrap.production.bacalhau.org`
 
 - `--api-port int`:
-    - Description: Designates the port for RESTful communication. The flag will be bypassed if the `BACALHAU_API_PORT` environment variable is active.
-    - Default: `1234`
 
-- `--log-mode logging-mode`:
-    - Description: Chooses the preferred log format. Available choices are: `default`, `station`, `json`, `combined`, and `event`.
-    - Default: `default`
+  - Description: Designates the port for RESTful communication. The flag will be bypassed if the `BACALHAU_API_PORT` environment variable is active.
+  - Default: `1234`
 
-- `--repo string`:
-    - Description: Specifies the path to the bacalhau repository.
-    - Default: `/Users/walid/.bacalhau`
+- `--log-mode logging-mode`:
 
----
+  - Description: Chooses the preferred log format. Available choices are: `default`, `station`, `json`, `combined`, and `event`.
+  - Default: `default`
 
-This should provide an organized and structured overview of the `node` command and its functionalities!
+- `--repo string`:
+  - Description: Specifies the path to the bacalhau repository.
+  - Default: `/Users/walid/.bacalhau`