Explanation

Decisions beside the LLM

A decision model answers typed questions about supplied information. Nawa can use one beside the active language model for optional candidate ranking. It does not control the browser.

Two models, one client

The Fast decisions cards select Jev by TypeSafe, directly or through OpenRouter, or Laya, served from the configured machine or fleet. One is active at a time; the section switch controls availability without deleting the saved connections.

Both use a state and typed questions: a choice among options, an ordinal score, or a yes/no probability. The shared client in server/decisions.js preserves provider responses, identity, usage, input-completeness metadata and errors. Calls produce a decision timing event and an immutable evidence record; if storage fails, the exchange stays inline with the storage error.

Where a decision is asked

With a decision model enabled, these existing tools accept an optional intent:

• web_search ranks the returned search candidates.
• use_skill ranks the skill catalogue without loading instructions.
• load_plugin_tools ranks plugin catalogue entries, or a selected plugin's tools, without loading or executing them.

The same semantic ranker asks an independent question for each candidate, batching by its token allowance. Returned indexes refer to the original list. Every candidate stays available; unknown scores and failed requests stay explicit. Rankings are advisory, and the main model chooses what to use. The selected decision model's identity is available to the lead and workers.

Browser actions

The main model controls browser plugins through their native tools. The coder uses the existing workspace browser tools for application checks. Neither path adds decision-model ranking, target selection or expectation checks, and neither calls Jev or Laya during browser execution. Browser schemas are unchanged by the decision-model switch. Native permissions, observations, errors and external-content screening remain authoritative.

Practical limits

Probabilities express model judgments, not proof. A ranking does not authorize an operation or verify task completion. Enabling a decision model allows the configured endpoint to receive the supplied candidates; saved credentials retain their separate protection. Total speed and quality must be measured for each use, including any correction work.

The earlier browser experiments did not demonstrate a reliable overall speed benefit. Their task loop and per-action integrations were removed rather than retained as disabled fallbacks. Historical measurements remain in the dated engineering reports.