nucleus_telemetry
Configure LLM model tiers, record interaction telemetry for training signals, track costs, and manage safety controls like kill switches and notification pausing.
Instructions
Configure LLM model tiers, record interaction telemetry for training signal generation, track costs, and manage safety controls including kill switches and notification pausing. Use this tool when you need to set which AI models are used for different task types, log usage data, check cost dashboards, or control emergency stops. Do NOT use for persistent memory (use nucleus_engrams), task management (use nucleus_tasks), or agent lifecycle (use nucleus_agents). Actions: 'set_llm_tier' configures which model (opus/sonnet/haiku) to use for specific task contexts. 'get_llm_status' returns current tier configuration. 'record_interaction' logs a tool invocation with token counts and latency for training signal generation (side effect: appends to telemetry log). 'value_ratio' calculates cost-effectiveness metrics across recent interactions. 'check_kill_switch' queries whether all operations should halt — returns boolean. 'pause_notifications' temporarily stops PEFS alert delivery. 'resume_notifications' re-enables alerts. 'record_feedback' captures human ratings (1-5 scale) on AI outputs for DPO training pairs. 'mark_high_impact' flags an interaction for human review. 'agent_cost_dashboard' shows per-agent token spending and cost breakdown. 'request_handoff' initiates a work transfer between agents. 'dispatch_metrics' shows tool dispatch statistics. Prerequisites: .brain directory. Kill switch state persists in .brain/governance/kill_switch.json. Returns JSON with {success: boolean, data: object}. Example: {action: 'record_feedback', params: {interaction_id: 'int_abc', rating: 5, comment: 'Perfect fix'}} returns {success: true, data: {recorded: true, dpo_pair_created: true}}.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Select the telemetry or safety control action. 'get_llm_status'/'value_ratio'/'check_kill_switch'/'agent_cost_dashboard'/'dispatch_metrics'/'check_protocol'/'get_handoffs' are read-only queries. 'set_llm_tier' changes model configuration. 'record_interaction'/'record_feedback'/'mark_high_impact' write telemetry data to disk. 'pause_notifications'/'resume_notifications' toggle PEFS alert delivery. 'request_handoff' initiates agent-to-agent work transfer. | |
| params | No | Action-specific parameters as key-value pairs. set_llm_tier: {tier: string (required, 'opus'|'sonnet'|'haiku'), context: string (optional, task type this tier applies to, e.g. 'code_review')}. record_interaction: {tool_name: string (required), tokens_in: integer (required), tokens_out: integer (required), latency_ms: integer (required)}. record_feedback: {interaction_id: string (required), rating: integer (required, 1 to 5 scale), comment: string (optional)}. mark_high_impact: {interaction_id: string (required), reason: string (required, why this is high-impact)}. request_handoff: {from_agent: string (required), to_agent: string (required), context: object (required, handoff payload with task info)}. get_llm_status/value_ratio/check_kill_switch/pause_notifications/resume_notifications/check_protocol/get_handoffs/agent_cost_dashboard/dispatch_metrics: no parameters needed. |