feat(core): distinguish model usage intent from config slot#2464
Merged
Conversation
ec5db4c to
0d4451a
Compare
Deploying midscene with
|
| Latest commit: |
26c2137
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://16f066a3.midscene.pages.dev |
| Branch Preview URL: | https://zzy-semantic-intent-split-in.midscene.pages.dev |
0d4451a to
bd3e3ff
Compare
bd3e3ff to
26c2137
Compare
yuyutaotao
approved these changes
May 13, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This change separates two model usage concepts:
intent: the semantic purpose of the model call, such asdefault,planning, orinsight.slot: the resolved model config slot actually used, such asdefaultwhen aplanningcall falls back to the default model config.This makes report usage clearer: the UI shows what the call was for, while the raw usage still records where the model config came from.
It also updates the related types, report/visualizer reads, and unit tests for fallback and usage annotation cases.