Cloud System Manage Tool
system_manageMonitor platform health, view KPIs and audit logs, and manage global settings, security policies, cache, compute providers, and browser relays.
Instructions
Platform system administration, monitoring, and infrastructure control — KPIs, health checks, audit log, semantic cache, GPU compute providers, browser-relay bridge. Mixed permission tiers: read actions (dashboard_kpis, health, version_check, audit_log, cache_stats) need any authenticated user; write actions marked PLATFORM ADMIN require the user's is_super_admin=true flag (HTTP 403 otherwise). Every write is audit-logged.
When to use: agent monitoring platform health, on-call investigating an incident via audit log, super-admin adjusting platform-wide settings or purging the semantic cache after a model swap. Do NOT use for tenant-level operations — those have dedicated tools (e.g. team_manage).
Read actions:
dashboard_kpis — { active_users, runs_today, spend_today_credits, ... }.
health — { status: ok|degraded|down, db, cache, queue, providers[] }.
version_check — { current, latest, update_available }.
audit_log — optional: actor_id, action, entity_type, since, limit (max 100). Cursor-paginated.
cache_stats — semantic cache hit/miss/savings since last purge.
Write actions:
global_settings (write — PLATFORM ADMIN) — settings object. Replaces platform-wide settings.
blacklist (write — PLATFORM ADMIN) — sub-actions: list, add, remove. Affects email/domain blocklists for sign-ups.
security_policy (write — PLATFORM ADMIN) — sub-actions: list, save, delete on security policies.
cache_purge (DESTRUCTIVE — PLATFORM ADMIN) — purges semantic cache CROSS-TEAM. All teams lose cached LLM responses; first calls after purge will be slower and more expensive.
compute (write — PLATFORM ADMIN) — sub-actions on compute provider records (Replicate, Fal.ai, Vast.ai, RunPod).
runpod (write — PLATFORM ADMIN, costs real $) — sub-actions on RunPod GPU pods. Spinning up a pod bills the platform Stripe account immediately at the pod's per-minute rate.
browser_relay (write — relays through local bridge) — sub-actions for browser automation through the team's connected FleetQ Bridge runner. Requires an active bridge.
Errors: 401, 403 (insufficient role for PLATFORM ADMIN action), 404, 422, 429, 503 (provider down).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Action to perform: dashboard_kpis, health, version_check, audit_log, global_settings, blacklist, security_policy, cache_stats, cache_purge, compute, runpod, browser_relay | |
| deadline_ms | No | Optional: max wall-clock time (ms) the tool may spend. If exceeded during the call, returns a DEADLINE_EXCEEDED error. Minimum 100 ms. Leave unset for no deadline. | |
| force | No | Bypass the cache and fetch the latest version from GitHub immediately. | |
| subject_type | No | Filter by subject type (e.g. experiment, agent, approval) | |
| ocsf_class_uid | No | Filter by OCSF class UID (e.g. 3002 = API Activity, 3001 = Account Change, 3006 = Financial Activity, 1001 = Process Activity, 4002 = HTTP Activity) | |
| limit | No | Max results to return (default 20, max 100) | |
| settings | Yes | Key-value pairs to update. Allowed keys: assistant_llm_provider, assistant_llm_model, default_llm_provider, default_llm_model, budget_cap_credits, rate_limit_rpm, outbound_rate_limit, experiment_timeout_seconds, weekly_digest_enabled, audit_retention_days | |
| operation | Yes | list: get all blacklist entries | add: add a new entry | remove: remove an entry by id | |
| type | No | Required for add. Type of entry to block. | |
| value | No | Required for add/remove. The value to block (e.g. "spam@example.com") or the entry UUID to remove. | |
| reason | No | Optional reason for add operations. Stored for audit purposes. | |
| policy | No | Required for update. Policy fields to set. | |
| provider | No | Filter by provider (e.g. "anthropic"). Omit to purge all. | |
| model | No | Filter by model (e.g. "claude-sonnet-4-5-20250929"). Omit to purge all. | |
| expired_only | No | When true, only purge entries past their expiry date. | |
| api_key | No | API key for credential_save | |
| endpoint_id | No | Provider endpoint/model identifier (required for health_check and run) | |
| input | No | Input payload for run | |
| use_sync | No | Use synchronous mode for run (default: true) | |
| timeout_seconds | No | Max wait time in seconds for run (default: 90) | |
| job_id | No | Job ID returned by endpoint_run async mode (required for endpoint_status) | |
| pod_id | No | Pod ID for pod_status or pod_stop | |
| pod_config | No | Pod configuration for pod_create (imageName, gpuTypeIds, gpuCount, env, etc.) | |
| tool | No | BrowserMCP tool name (required for call_tool) | |
| params | No | Tool parameters for BrowserMCP (optional for call_tool) |