holmesgpt 0.11.5__py3-none-any.whl

holmes/plugins/toolsets/__init__.py

@@ -0,0 +1,171 @@
+import logging
+import os
+import os.path
+from typing import Any, List, Optional, Union
+
+from holmes.common.env_vars import USE_LEGACY_KUBERNETES_LOGS
+import yaml  # type: ignore
+from pydantic import ValidationError
+
+from holmes.plugins.toolsets.azure_sql.azure_sql_toolset import AzureSQLToolset
+import holmes.utils.env as env_utils
+from holmes.core.supabase_dal import SupabaseDal
+from holmes.core.tools import Toolset, ToolsetType, ToolsetYamlFromConfig, YAMLToolset
+from holmes.plugins.toolsets.coralogix.toolset_coralogix_logs import (
+    CoralogixLogsToolset,
+)
+from holmes.plugins.toolsets.datadog import DatadogToolset
+from holmes.plugins.toolsets.kubernetes_logs import KubernetesLogsToolset
+from holmes.plugins.toolsets.git import GitToolset
+from holmes.plugins.toolsets.grafana.toolset_grafana import GrafanaToolset
+from holmes.plugins.toolsets.bash.bash_toolset import BashExecutorToolset
+from holmes.plugins.toolsets.grafana.toolset_grafana_loki import GrafanaLokiToolset
+from holmes.plugins.toolsets.grafana.toolset_grafana_tempo import GrafanaTempoToolset
+from holmes.plugins.toolsets.internet.internet import InternetToolset
+from holmes.plugins.toolsets.internet.notion import NotionToolset
+from holmes.plugins.toolsets.kafka import KafkaToolset
+from holmes.plugins.toolsets.mcp.toolset_mcp import RemoteMCPToolset
+from holmes.plugins.toolsets.newrelic import NewRelicToolset
+from holmes.plugins.toolsets.opensearch.opensearch import OpenSearchToolset
+from holmes.plugins.toolsets.opensearch.opensearch_logs import OpenSearchLogsToolset
+from holmes.plugins.toolsets.opensearch.opensearch_traces import OpenSearchTracesToolset
+from holmes.plugins.toolsets.prometheus.prometheus import PrometheusToolset
+from holmes.plugins.toolsets.rabbitmq.toolset_rabbitmq import RabbitMQToolset
+from holmes.plugins.toolsets.robusta.robusta import RobustaToolset
+from holmes.plugins.toolsets.atlas_mongodb.mongodb_atlas import MongoDBAtlasToolset
+from holmes.plugins.toolsets.runbook.runbook_fetcher import RunbookToolset
+from holmes.plugins.toolsets.servicenow.servicenow import ServiceNowToolset
+
+THIS_DIR = os.path.abspath(os.path.dirname(__file__))
+
+
+def load_toolsets_from_file(
+    toolsets_path: str, strict_check: bool = True
+) -> List[Toolset]:
+    toolsets = []
+    with open(toolsets_path) as file:
+        parsed_yaml = yaml.safe_load(file)
+        if parsed_yaml is None:
+            raise ValueError(
+                f"Failed to load toolsets from {toolsets_path}: file is empty or invalid YAML."
+            )
+        toolsets_dict = parsed_yaml.get("toolsets", {})
+
+        toolsets.extend(load_toolsets_from_config(toolsets_dict, strict_check))
+
+    return toolsets
+
+
+def load_python_toolsets(dal: Optional[SupabaseDal]) -> List[Toolset]:
+    logging.debug("loading python toolsets")
+    toolsets: list[Toolset] = [
+        InternetToolset(),
+        RobustaToolset(dal),
+        OpenSearchToolset(),
+        GrafanaLokiToolset(),
+        GrafanaTempoToolset(),
+        NewRelicToolset(),
+        GrafanaToolset(),
+        NotionToolset(),
+        KafkaToolset(),
+        DatadogToolset(),
+        PrometheusToolset(),
+        OpenSearchLogsToolset(),
+        OpenSearchTracesToolset(),
+        CoralogixLogsToolset(),
+        RabbitMQToolset(),
+        GitToolset(),
+        BashExecutorToolset(),
+        MongoDBAtlasToolset(),
+        RunbookToolset(),
+        AzureSQLToolset(),
+        ServiceNowToolset(),
+    ]
+    if not USE_LEGACY_KUBERNETES_LOGS:
+        toolsets.append(KubernetesLogsToolset())
+
+    return toolsets
+
+
+def load_builtin_toolsets(dal: Optional[SupabaseDal] = None) -> List[Toolset]:
+    all_toolsets: List[Toolset] = []
+    logging.debug(f"loading toolsets from {THIS_DIR}")
+
+    # Handle YAML toolsets
+    for filename in os.listdir(THIS_DIR):
+        if not filename.endswith(".yaml"):
+            continue
+
+        if filename == "kubernetes_logs.yaml" and not USE_LEGACY_KUBERNETES_LOGS:
+            continue
+
+        path = os.path.join(THIS_DIR, filename)
+        toolsets_from_file = load_toolsets_from_file(path, strict_check=True)
+        all_toolsets.extend(toolsets_from_file)
+
+    all_toolsets.extend(load_python_toolsets(dal=dal))  # type: ignore
+
+    # disable built-in toolsets by default, and the user can enable them explicitly in config.
+    for toolset in all_toolsets:
+        toolset.type = ToolsetType.BUILTIN
+        # dont' expose build-in toolsets path
+        toolset.path = None
+
+    return all_toolsets  # type: ignore
+
+
+def is_old_toolset_config(
+    toolsets: Union[dict[str, dict[str, Any]], List[dict[str, Any]]],
+) -> bool:
+    # old config is a list of toolsets
+    if isinstance(toolsets, list):
+        return True
+    return False
+
+
+def load_toolsets_from_config(
+    toolsets: dict[str, dict[str, Any]],
+    strict_check: bool = True,
+) -> List[Toolset]:
+    """
+    Load toolsets from a dictionary or list of dictionaries.
+    :param toolsets: Dictionary of toolsets or list of toolset configurations.
+    :param strict_check: If True, all required fields for a toolset must be present.
+    :return: List of validated Toolset objects.
+    """
+
+    if not toolsets:
+        return []
+
+    loaded_toolsets: list[Toolset] = []
+    if is_old_toolset_config(toolsets):
+        message = "Old toolset config format detected, please update to the new format: https://docs.robusta.dev/master/configuration/holmesgpt/custom_toolsets.html"
+        logging.warning(message)
+        raise ValueError(message)
+
+    for name, config in toolsets.items():
+        try:
+            toolset_type = config.get("type", ToolsetType.BUILTIN.value)
+            # MCP server is not a built-in toolset, so we need to set the type explicitly
+            validated_toolset: Optional[Toolset] = None
+            if toolset_type is ToolsetType.MCP:
+                validated_toolset = RemoteMCPToolset(**config, name=name)
+            elif strict_check:
+                validated_toolset = YAMLToolset(**config, name=name)  # type: ignore
+            else:
+                validated_toolset = ToolsetYamlFromConfig(  # type: ignore
+                    **config, name=name
+                )
+
+            if validated_toolset.config:
+                validated_toolset.config = env_utils.replace_env_vars_values(
+                    validated_toolset.config
+                )
+            loaded_toolsets.append(validated_toolset)
+        except ValidationError as e:
+            logging.warning(f"Toolset '{name}' is invalid: {e}")
+
+        except Exception:
+            logging.warning("Failed to load toolset: %s", name, exc_info=True)
+
+    return loaded_toolsets

holmes/plugins/toolsets/aks-node-health.yaml

@@ -0,0 +1,65 @@
+toolsets:
+  aks/node-health:
+    description: "Set of tools to troubleshoot AKS node health issues"
+    tags:
+      - cli
+    prerequisites:
+      - command: "az account show"
+      - command: "az aks --help"
+      - command: "kubectl version --client"
+    tools:
+      - name: "check_node_status"
+        description: "Checks the status of all nodes in the AKS cluster."
+        user_description: "get the status of all nodes in the AKS cluster"
+        command: |
+          kubectl get nodes
+      - name: "describe_node"
+        description: "Describes a specific node in the AKS cluster to inspect its conditions."
+        user_description: "describe node {{ NODE_NAME }} in the AKS cluster"
+        command: |
+          kubectl describe node {{ NODE_NAME }}
+      - name: "get_node_events"
+        description: "Fetches recent events for a specific node to surface warnings and errors."
+        user_description: "get events for node {{ NODE_NAME }}"
+        command: |
+          kubectl get events --field-selector involvedObject.kind=Node,involvedObject.name={{ NODE_NAME }} --sort-by='.lastTimestamp'
+      - name: "check_node_resource_usage"
+        description: "Shows CPU/memory usage for a specific node (requires metrics-server)."
+        user_description: "get resource usage for node {{ NODE_NAME }}"
+        command: |
+          kubectl top node {{ NODE_NAME }}
+      - name: "review_activity_log"
+        description: "Reviews the Azure Activity Log for recent changes affecting the node."
+        user_description: "review Azure Activity Log for resource group {{ RESOURCE_GROUP_NAME }}"
+        command: |
+          az monitor activity-log list --resource-group {{ RESOURCE_GROUP_NAME }}
+      - name: "check_top_resource_consuming_pods"
+        description: "Checks for the top resource-consuming pods on a specific node."
+        user_description: "get the top resource-consuming pods on node {{ NODE_NAME }}"
+        command: |
+          kubectl top pod --all-namespaces --sort-by=cpu | grep {{ NODE_NAME }}
+      - name: "check_network_outbound"
+        description: "Checks the outbound network connectivity for an AKS cluster."
+        user_description: "check outbound network connectivity for AKS cluster {{ CLUSTER_NAME }} in resource group {{ RESOURCE_GROUP }}"
+        command: |
+          az aks check-network outbound --name {{ CLUSTER_NAME }} --resource-group {{ RESOURCE_GROUP }}
+      - name: "check_network_inbound"
+        description: "Checks the inbound network connectivity for an AKS cluster."
+        user_description: "check inbound network connectivity for AKS cluster {{ CLUSTER_NAME }} in resource group {{ RESOURCE_GROUP }}"
+        command: |
+          az aks check-network inbound --name {{ CLUSTER_NAME }} --resource-group {{ RESOURCE_GROUP }}
+      - name: "list_vmss_names"
+        description: |
+          Lists all VMSS names in the cluster node resource group.
+          Prerequisites: get_node_resource_group
+        user_description: "lists all VMSS names in {{ NODE_RESOURCE_GROUP }}"
+        command: |
+          az vmss list -g {{ NODE_RESOURCE_GROUP }} --query '[*].name' -o tsv --only-show-errors
+      - name: "vmss_run_command"
+        description: |
+          Execute a shell command on a specific VMSS VM instance using az vmss run-command.
+          VM_ID is the instance ID of the VMSS, which can be derived from node names.
+          Prerequisites: get_node_resource_group, list_vmss_names
+        user_description: "run command {{ SHELL_COMMAND }} on VM #{{ VM_ID }} of VMSS {{ VMSS_NAME }}"
+        command: |
+          az vmss run-command invoke --resource-group {{ NODE_RESOURCE_GROUP }} --name {{ VMSS_NAME }} --instance-id {{ VM_ID }} --command-id RunShellScript --scripts {{ SHELL_COMMAND }}

holmes/plugins/toolsets/aks.yaml

@@ -0,0 +1,86 @@
+toolsets:
+  aks/core:
+    description: "Set of tools to read Azure Kubernetes Service resources"
+    tags:
+      - cli
+    prerequisites:
+      - command: "az account show"
+      - command: "az aks --help"
+      - command: "kubectl version --client"
+    tools:
+      - name: "cloud_provider"
+        description: "Fetches the cloud provider of the kubernetes cluster, determined by the providerID of the nodes"
+        user_description: "get cloud provider of AKS cluster"
+        command: |
+          kubectl get nodes -o jsonpath='{range .items[*]}{.metadata.name}{"\t"}{.spec.providerID}{"\n"}{end}'
+      - name: "aks_get_cluster"
+        description: "Get the configuration details of a specific AKS cluster"
+        user_description: "get AKS cluster {{ CLUSTER_NAME }} under resource group {{ RESOURCE_GROUP_NAME }} in subscription {{ SUBSCRIPTION_ID }}"
+        command: |
+          az aks show --resource-group {{ RESOURCE_GROUP_NAME }} --name {{ CLUSTER_NAME }} --subscription {{ SUBSCRIPTION_ID }}
+      - name: "aks_list_clusters_by_rg"
+        description: "Lists all AKS clusters under a specific resource group. Only run this tool when you need to get all clusters in a resource group, rather than a specific one."
+        user_description: "list AKS clusters in resource group {{ RESOURCE_GROUP_NAME }} under subscription {{ SUBSCRIPTION_ID }}"
+        command: |
+          az aks list --resource-group {{ RESOURCE_GROUP_NAME }} --subscription {{ SUBSCRIPTION_ID }}
+      - name: "aks_list_node_pools"
+        description: "Lists node pools in an AKS cluster"
+        user_description: "list node pools for AKS cluster {{ CLUSTER_NAME }} under resource group {{ RESOURCE_GROUP_NAME }}"
+        command: |
+          az aks nodepool list --resource-group {{ RESOURCE_GROUP_NAME }} --cluster-name {{ CLUSTER_NAME }} --subscription {{ SUBSCRIPTION_ID }}
+      - name: "aks_show_node_pool"
+        description: "Shows details of a specific node pool in an AKS cluster"
+        user_description: "get node pool {{ NODE_POOL_NAME }} in AKS cluster {{ CLUSTER_NAME }} under resource group {{ RESOURCE_GROUP_NAME }}"
+        command: |
+          az aks nodepool show --resource-group {{ RESOURCE_GROUP_NAME }} --cluster-name {{ CLUSTER_NAME }} --name {{ NODE_POOL_NAME }} --subscription {{ SUBSCRIPTION_ID }}
+      - name: "aks_list_versions"
+        description: "Lists supported Kubernetes versions in a region"
+        user_description: "list supported Kubernetes versions for region {{ LOCATION }}"
+        command: |
+          az aks get-versions --location {{ LOCATION }} --subscription {{ SUBSCRIPTION_ID }}
+      - name: "aks_get_credentials"
+        description: "Downloads kubeconfig file for an AKS cluster"
+        user_description: "get kubeconfig credentials for AKS cluster {{ CLUSTER_NAME }} under resource group {{ RESOURCE_GROUP_NAME }}"
+        command: |
+          az aks get-credentials --resource-group {{ RESOURCE_GROUP_NAME }} --name {{ CLUSTER_NAME }} --subscription {{ SUBSCRIPTION_ID }}
+      - name: "aks_list_addons"
+        description: "Lists all available AKS addons"
+        user_description: "list available addons for AKS in region {{ LOCATION }}"
+        command: |
+          az aks get-versions --location {{ LOCATION }} --query "orchestrators[].addons"
+      # helper tools to auto-discover variables
+      - name: "get_default_subscription"
+        description: "Retrieves the current Azure CLI default subscription ID"
+        user_description: "get default subscription ID"
+        command: |
+          az account show --query id -o tsv
+      - name: "get_cluster_name"
+        description: "Retrieves the active Kubernetes cluster name from kubeconfig"
+        user_description: "get current AKS cluster name from kubeconfig"
+        command: |
+           kubectl config current-context
+      - name: "get_cluster_resource_group"
+        description: "Retrieves the resource group name for the AKS cluster"
+        user_description: "get resource group for cluster {{ CLUSTER_NAME }}"
+        command: |
+           az aks list --subscription {{ SUBSCRIPTION_ID }} --only-show-errors --query "[?name=='{{ CLUSTER_NAME }}'].resourceGroup | [0]" -o tsv
+      - name: "get_node_resource_group"
+        description: "Retrieves the node resource group name for the AKS cluster"
+        user_description: "get the node resource group name for cluster {{ CLUSTER_NAME }}"
+        command: |
+          az aks list --subscription {{ SUBSCRIPTION_ID }} --only-show-errors --query "[?name=='{{ CLUSTER_NAME }}'].nodeResourceGroup | [0]" -o tsv
+      - name: "get_api_server_public_ip"
+        description: "get the public IP of kube-apiserver for a public AKS cluster"
+        user_description: "get the public IP of kube-apiserver for a public AS cluster {{ CLUSTER_NAME }}"
+        command: |
+          API_SERVER=$(kubectl cluster-info | grep 'Kubernetes control plane' | sed -E 's|.*https://([^:]+):.*|\1|') && dig +short "${API_SERVER}"
+      - name: "get_all_nsgs"
+        description: "Gets all Network Security Group (NSG) instances in a subscription"
+        user_description: "list NSG instances in current Azure subscription {{ SUBSCRIPTION_ID }} context"
+        command: |
+            az network nsg list --subscription {{ SUBSCRIPTION_ID }} -o table
+      - name: "get_nsg_rules"
+        description: "Gets all NSG rules associated with a specific NSG"
+        user_description: "list NSG rules for NSG {{ NSG_NAME }} in resource group {{ RESOURCE_GROUP_NAME }} under subscription {{ SUBSCRIPTION_ID }}"
+        command: |
+            az network nsg rule list --resource-group {{ RESOURCE_GROUP_NAME }} --nsg-name {{ NSG_NAME }} --subscription {{ SUBSCRIPTION_ID }} --include-default -o table

holmes/plugins/toolsets/argocd.yaml

@@ -0,0 +1,70 @@
+toolsets:
+  argocd/core:
+    description: "Set of tools to get argocd metadata like list of apps, repositories, projects, etc."
+    docs_url: "https://docs.robusta.dev/master/configuration/holmesgpt/toolsets/argocd.html"
+    icon_url: "https://argo-cd.readthedocs.io/en/stable/assets/logo.png"
+    llm_instructions: |
+      You have access to a set of ArgoCD tools for debugging Kubernetes application deployments.
+      If an application's name does not exist in kubernetes, it may exist in argocd: call the tool `argocd_app_list` to find it.
+      These tools help you investigate issues with GitOps-managed applications in your Kubernetes clusters.
+      ALWAYS follow these steps:
+        1. List the applications
+        2. Retrieve the application status and its config
+        3. Retrieve the application's manifests for issues
+        4. Compare the ArgoCD config with the kubernetes status using kubectl tools
+        5. Check for resources mismatch between argocd and kubernetes
+      {% if tool_names|list|length > 0 %}
+      The following commands are available to introspect into ArgoCD: {{ ", ".join(tool_names) }}
+      {% endif %}
+      ALWAYS compare the argocd deployment with kubernetes so that you can suggest better solutions to the user.
+      DO NOT tell the user to check if a resource exists or to update the configuration without being specific, DO checks yourself on behalf of the user and then tell them the solution.
+    tags:
+      - core
+    prerequisites:
+      - command: "argocd version"
+      - env:
+          - ARGOCD_AUTH_TOKEN
+    tools:
+      - name: "argocd_app_list"
+        description: "List the applications in Argocd"
+        command: "argocd app list"
+
+      - name: "argocd_app_get"
+        description: "Retrieve information about an existing application, such as its status and configuration"
+        command: "argocd app get {{ app_name }} --show-operation -o wide"
+
+      - name: "argocd_app_diff"
+        description: "Display the differences between the current state of an application and the desired state specified in its Git repository"
+        command: "argocd app diff {{ app_name }}"
+
+      - name: "argocd_app_manifests"
+        description: "Retrieve manifests for an application"
+        command: "argocd app manifests {{app_name}}"
+
+      - name: "argocd_app_resources"
+        description: "List resources of application"
+        command: "argocd app resources {{app_name}}"
+
+      - name: "argocd_app_manifest_source_revision"
+        description: "Get manifests for a multi-source application at specific revision for specific source"
+        command: "argocd app manifests {{app_name}}{% if revision %} --revision {{ revision }}{% endif %}{% if source %} --source {{ source }}{% endif %}"
+
+      - name: "argocd_app_history"
+        description: "List the deployment history of an application in ArgoCD"
+        command: "argocd app history {{app_name}} --app-namespace {{namespace}}"
+
+      - name: "argocd_repo_list"
+        description: "List all the Git repositories that ArgoCD is currently managing"
+        command: "argocd repo list"
+
+      - name: "argocd_proj_list"
+        description: "List all available projects"
+        command: "argocd proj list"
+
+      - name: "argocd_proj_get"
+        description: "Retrieves information about an existing project, such as its applications and policies"
+        command: "argocd proj get {{ project_name }}"
+
+      - name: "argocd_cluster_list"
+        description: "List all known clusters"
+        command: "argocd cluster list"

holmes/plugins/toolsets/atlas_mongodb/instructions.jinja2

@@ -0,0 +1,8 @@
+When a user requests checking issues on Atlas mongodb project use these steps.
+
+* Use atlas_return_project_alerts and atlas_return_events_from_project first to find any known potential issues on the project.
+* For performance issues or collscan queries use atlas_return_project_slow_queries to see a list of slow queries. YOU MUST check this for all processes of the project. ALWAYS show the query in the result for every slow query.
+* atlas_return_project_slow_queries currently returns data from the last 24 hours. If the user asks for a different time range, mention its not supported.
+* atlas_return_events_from_project currently returns data from the last 24 hours, if the user asks for a different time range, mention its not supported.
+* CHECK logs for mongodb using atlas_return_logs_for_host_in_project if the user mentions checking the logs.
+* When asked for a specific number of slow queries. for example top 10 slow queries. DO NOT duplicate queries from different processes.