Session Persistence
Medium
- Category
- Rogue Agent
- Content
metadata: {"openclaw":{"requires":{"env":["INFERENCE_AIOPS_CONFIG"],"bins":["inference-aiops"],"config":["~/.inference-aiops/config.yaml"]},"optional":{"env":["INFERENCE_AIOPS_MASTER_PASSWORD"],"config":["~/.inference-aiops/secrets.enc"]},"primaryEnv":"INFERENCE_AIOPS_CONFIG","homepage":"https://github.com/AIops-tools/Inference-AIops","emoji":"🚀","os":["macos","linux"]}} compatibility: > Standalone, self-governed GPU-inference operations (preview). The governance harness (audit, policy, token/runaway budget, undo, risk-tiers) is bundled in the package — no external skill-family dependency. All write operations are audited to a local SQLite DB under ~/.inference-aiops/ (relocatable via INFERENCE_AIOPS_HOME). Auth: a bearer token is OPTIONAL — many vLLM / Ray stacks run open. When the API requires one it is stored ENCRYPTED in ~/.inference-aiops/secrets.enc (Fernet/AES-128 + scrypt-derived key) — never plaintext on disk. Run 'inference-aiops init' to onboard, or 'inference-aiops secret set <target>' to add one. The store is unlocked by a master password from INFERENCE_AIOPS_MASTER_PASSWORD (non-interactive/MCP/CI) or an interactive prompt (CLI on a TTY). A legacy plaintext env var INFERENCE_<TARGET_NAME_UPPER>_TOKEN is still honoured as a fallback (migrate with 'inference-aiops secret migrate'). The token is sent as an Authorization: Bearer header at request time and held only in memory; it is never logged or echoed. State-changing operations require double confirmation at the CLI layer and support --dry-run. All write tools pass through the @governed_tool decorator (pre-check + budget guard + audit + risk-tier gate). The fragile prod ops — scale_replicas_down, scale_to_zero, drain_replica, lora_unload, model_hot_swap, replica_restart, model_undeploy, deployment_redeploy — are high-risk with a dry_run preview; reversible writes (scale, autoscale-config, routing, hot-swap, LoRA load) record an undo descriptor. Metrics: vLLM's Prometheus /metrics endpoint is ...[truncated 24 chars]- Confidence
- 83% confidence
- Finding
- write operations are audited to a local SQLite DB under ~/.inference-aiops/ (relocatable via INFERENCE_AIOPS_HOME). Auth: a bearer token is OPTIONAL — many vLLM / Ray stacks run open. When the API r