ankra chat

AI-powered chat for troubleshooting and assistance

ankra chat

AI-powered chat for troubleshooting and assistance.

If a message is provided, sends a one-shot question. If no message is provided, enters interactive chat mode.

Use —cluster to provide cluster context for better answers.

ankra chat [message] [flags]

Flags

Flag	Default	Description
--cluster		Cluster name for context
--mode		Safety mode: ‘ask’ (read-only + safe creations) or ‘agent’ (can act). Defaults to the server default.

ankra chat actions

Agent-mode chat halts before every write and proposes it as a pending action. Confirm the action to run it, or reject it to discard it.

Pending actions expire, so confirm promptly. If the cluster changed since the action was proposed, confirming answers a drift conflict; re-run with —force to apply it against the changed state anyway.

ankra chat actions confirm

Confirm a pending action proposed by agent-mode chat.

The platform re-checks the action against live cluster state before running it. If the state drifted since the proposal, the command reports the drift and exits without running anything; pass —force to run it anyway.

ankra chat actions confirm <action_id> [flags]

Examples

# Confirm the action id printed by the chat stream
  ankra chat actions confirm 6f1c2f9e-6d5a-4a1e-9f0b-6d4c2b8a1e77

  # Apply it even though the cluster drifted since it was proposed
  ankra chat actions confirm 6f1c2f9e-6d5a-4a1e-9f0b-6d4c2b8a1e77 --force \
    --force-reason "drift is an unrelated label change"

Flags

Flag	Default	Description
--force	false	Confirm even though cluster state drifted since the action was proposed
--force-reason		Why the drift is acceptable (recorded in the audit trail, max 280 characters)
-o, --output		Output format: json or yaml (default: human-readable)

ankra chat actions list

List the actions awaiting confirmation in a conversation

ankra chat actions list <conversation_id> [flags]

Flags

Flag	Default	Description
-o, --output		Output format: json or yaml (default: human-readable)

ankra chat actions reject

Reject a pending AI action so it never runs

ankra chat actions reject <action_id> [flags]

Flags

Flag	Default	Description
-o, --output		Output format: json or yaml (default: human-readable)
--reason		Why the action was rejected

ankra chat delete

Delete a chat conversation

ankra chat delete <conversation_id> [flags]

Flags

Flag	Default	Description
--yes	false	Skip the confirmation prompt

ankra chat health

Get AI-analyzed cluster health

ankra chat health [flags]

Flags

Flag	Default	Description
--ai	true	Include AI analysis
--cluster		Target cluster name or ID (defaults to the selected cluster)
-o, --output		Output format: json or yaml (default: human-readable)

ankra chat history

List chat conversation history

ankra chat history [flags]

Flags

Flag	Default	Description
--cluster		Filter by cluster
--limit	20	Maximum number of conversations to show
-o, --output		Output format: json or yaml (default: human-readable)

ankra chat show

Show a specific chat conversation

ankra chat show <conversation_id> [flags]

Flags

Flag	Default	Description
-o, --output		Output format: json or yaml (default: human-readable)