✨ feat: add native document extraction seam#596
Open
vaayne wants to merge 2 commits into
Open
Conversation
vaayne
force-pushed
the
xberg-document-extraction-plan
branch
from
4363592 to
5c0a9c9
Compare
📊 Coverage ReportTotal coverage: 48.8% (generated files excluded) Lowest-covered entries (first 200) |
This was referenced Jun 26, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Add an internal document extraction seam and route the
readimage text fallback through it instead of shelling out directly from the tool.Also upgrade the project toolchain to Go 1.26.4 and add a build-tagged
xbergextractor implementation behindxberg && cgo.Why
Document parsing should become a Stella platform capability, not a user-visible
kreuzberg extractinstruction in channel messages or tool internals. The xberg Go package requires Go 1.26, so the toolchain upgrade is the first unblocker.How
internal/documentwith extractor interface, result normalization, CLI compatibility fallback, and xberg build-tag implementation.internal/tools/read.goto depend on the extractor seam.readtool guidance and an extraction-preview helper.mise, Docker builder, andgo.modto Go 1.26.4.Validation:
mise run formatmise run buildmise run testKnown follow-up:
go test -tags xberg ./internal/documentreaches linking but needslibxberg_ffiunder xberg's.lib/<platform>path before native xberg can be enabled.Refs
Refs #595