feat(ocr): add higher-level text search helpers on top of OCR #13

New Issue

luna · 2026-05-01T15:39:00+02:00

luna commented

2026-05-01 15:39:00 +02:00

Why

Raw OCR blocks are useful but noisy. Agents often need “find matching text and give me candidate targets,” not a raw dump.

Scope

Add a higher-level OCR/text helper endpoint or mode that can:

search visible text by exact match / substring / regex-like pattern
return confidence-sorted matches
optionally group adjacent words into lines
optionally constrain to a region

Done when

agents can ask for “find text X on screen” without implementing custom client-side OCR post-processing every time

## Why Raw OCR blocks are useful but noisy. Agents often need “find matching text and give me candidate targets,” not a raw dump. ## Scope Add a higher-level OCR/text helper endpoint or mode that can: - search visible text by exact match / substring / regex-like pattern - return confidence-sorted matches - optionally group adjacent words into lines - optionally constrain to a region ## Done when - agents can ask for “find text X on screen” without implementing custom client-side OCR post-processing every time

luna closed this issue

2026-05-01 16:23:17 +02:00

This repo is archived. You cannot comment on issues.

1 Participants

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: space/clickthrough#13