Conversation
…hitecture Phase 3 of the grounding cascade design (v3): - grounding.py: GroundingTarget (rich target per click step — description, crop, nearby text, window title, structured transition expectations) and GroundingCandidate (normalized output from each grounding tier) - demo_library.py: DemoStep gains optional grounding_target field, serialization/deserialization handles GroundingTarget objects - Fix demo description: "Clear data" → "Clear now" (actual button text) - Design docs: v1, v2, v3 cascade architecture GroundingTarget is the foundation for the entire cascade. Every downstream tier (OCR, CLIP, UI-Venus, GPT-5.4) operates on the same rich signal instead of a weak description string. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Phase 3 of the grounding cascade design — the foundation data model.
grounding.py:GroundingTarget(rich target per click step) +GroundingCandidate(normalized tier output)demo_library.py:DemoStep.grounding_targetfield with serialization/deserializationEvery downstream phase (state narrowing, text anchoring, CLIP retrieval, verification) depends on this data model.
🤖 Generated with Claude Code