{"version":"2.1.280","anchor":"new-speculative-execution-for-the-remote-tool-auto-mode-clas","canonical_anchor":"new-speculative-execution-for-the-remote-tool-auto-mode-clas","heading":"New speculative execution for the remote-tool auto-mode classifier","tier":"internal","area":"Auto Mode","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/new-speculative-execution-for-the-remote-tool-auto-mode-clas","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### New speculative execution for the remote-tool auto-mode classifier\n\nThe remote-tool auto-mode classifier can now guess a tool call's permission ahead of time and reuse that guess if it turns out right\n\n**Unclear.** The finding doesn't say what triggers a speculative run to start or how often predictions are expected to match.\n\n**What**\n\nThe classifier that decides whether a remote tool call is automatically allowed can now run ahead of time, speculatively predicting the answer before the actual permission request arrives. If the real request matches the prediction, the pre-computed result is reused; if it doesn't match, the speculative work is discarded and the classifier runs normally.\n\nNew internal helper functions handle building, checking, and abandoning these speculative runs. The `tengu_remote_tool_classifier` telemetry event, which tracks this classifier's behavior, now also records `speculative_*` and `queue_*` fields, including a `speculative_discard_reason` for when a prediction doesn't pan out.\n\n**Why**\n\nRunning the classification speculatively can let the permission decision be ready sooner when the prediction is correct, since the work happens ahead of the actual ask instead of starting after it.\n\n- Area: Auto Mode\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 2\/5"}