demo: surface route-probe decision + clean probe trace - #23
Merged
Conversation
- dispatch: Ctx.last_route stashes (task, confidence) from the auto-route so the trace can show what the router detected. - demo: show "🧭 route probe → <task> (NN%)" when auto-routing, and render a recognition answer as "⊨ recognized (C)" instead of dumping the raw selection-marginalized scores dict. Drop the per-probe confidence number (max per-option P is misleading for choice_probe vs the selection softmax); the router's task-confidence is the meaningful one and it's shown in the 🧭 line.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Two small demo-facing polish items: (1) show the route probe's detected task + confidence (🧭 line) so auto-routing is visible; (2) render recognition answers cleanly (
⊨ recognized (C)) instead of the raw scores dict, and drop the misleading per-probe confidence number (the router's task-confidence is the meaningful one).