VisionMode
Namespace: E2E
public enum VisionModeWhat evidence a judgment (CancellationToken), CancellationToken),
CancellationToken)) is given: the semantic tree, a masked screenshot of the current screen, or both.
<p>
Only exists because a tree sent beside pixels is a cheaper path to an answer, and a model takes it:
asked whether a form is covered by an overlay, it can read from the tree that the form is present and named and
answer yes, while the pixels show the overlay. For a judgment about what the screen presents, the tree is a
distractor, so the mode that means it removes it. It also costs fewer input tokens than On.
</p>
<p>
In every mode that sends pixels and the tree, pixel evidence degrades away rather than failing the call when it
cannot be proven redacted. Only has nothing to degrade to, so it fails with POLICY_DENIED
instead of answering the wrong question from the tree.
</p>
<p>
CancellationToken) takes no vision mode: the act model works from the tree.
</p>
Fields
Section titled “Fields”Off = 0The tree. The default.
Value: VisionMode
On = 1The tree and a masked screenshot, on every call.
Value: VisionMode
Only = 2The masked screenshot, and not the tree.
Value: VisionMode