feat: argocd toolset, use env var

README.md

@@ -523,6 +523,15 @@ HolmesGPT can consult webpages containing runbooks or other relevant information
 HolmesGPT uses playwright to scrape webpages and requires playwright to be installed and working through `playwright install`.
 </details>
 
+<details>
+<summary>
+ArgoCD
+</summary>
+
+Holmes can use the `argocd` CLI to get details about the ArgoCD setup like the apps contifuration and status, clusters and projects within ArgoCD.
+To enable ArgoCD, set the `ARGOCD_AUTH_TOKEN` environment variable as described in the [argocd documentation](https://argo-cd.readthedocs.io/en/latest/user-guide/commands/argocd_account_generate-token/).
+</details>
+
 ## More Use Cases
 
 HolmesGPT was designed for incident response, but it is a general DevOps assistant too. Here are some examples:

holmes/config.py

@@ -124,6 +124,7 @@ def create_tool_executor(
             )
 
         enabled_toolsets = [ts for ts in matching_toolsets if ts.is_enabled()]
+        print(f"toolsets={str([ts.name for ts in enabled_toolsets])}")
         for ts in all_toolsets:
             if ts not in matching_toolsets:
                 console.print(

holmes/plugins/prompts/_general_instructions.jinja2

@@ -37,4 +37,3 @@ Special cases and how to reply:
 * Issues are a subset of findings. When asked about an issue or a finding and you have an id, use the tool `fetch_finding_by_id`.
 * For any question, try to make the answer specific to the user's cluster.
 ** For example, if asked to port forward, find out the app or pod port (kubectl decribe) and provide a port forward command specific to the user's question
-* If you need to use ArgoCD tools, ask the user for their argocd auth_token if they haven't given it yet

holmes/plugins/toolsets/argocd.yaml

@@ -6,32 +6,32 @@ toolsets:
     tools:
       - 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 yaml --auth-token {{ auth_token }}"
+        command: "argocd app get {{ app_name }} --show-operation -o yaml"
 
       - 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 }} --auth-token {{ auth_token }}"
+        command: "argocd app diff {{ app_name }}"
 
       - name: "argocd_app_list"
         description: "List the applications in Argocd"
-        command: "argocd app list --auth-token {{ auth_token }}"
+        command: "argocd app list"
 
       - name: "argocd_app_history"
         description: "List the deployment history of an application in ArgoCD"
-        command: "argocd app history {{app_name}} --app-namespace {{namespace}} --auth-token {{ auth_token }}"
+        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 --auth-token {{ auth_token }}"
+        command: "argocd repo list"
 
       - name: "argocd_proj_list"
         description: "List all available projects"
-        command: "argocd proj list {{ project_name }} --auth-token {{ auth_token }}"
+        command: "argocd proj list {{ project_name }}"
 
       - name: "argocd_proj_get"
         description: "Retrieves information about an existing project, such as its applications and policies"
-        command: "argocd proj get {{ project_name }} --auth-token {{ auth_token }}"
+        command: "argocd proj get {{ project_name }}"
 
       - name: "argocd_cluster_list"
         description: "List all known clusters"
-        command: "argocd cluster list --auth-token {{ auth_token }}"
+        command: "argocd cluster list"